diff --git a/.mailmap b/.mailmap
index 38f8bed..e51d76d 100644
--- a/.mailmap
+++ b/.mailmap
@@ -260,6 +260,7 @@
 Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
 James Bottomley <jejb@mulgrave.(none)>
 James Bottomley <jejb@titanic.il.steeleye.com>
+James Clark <james.clark@linaro.org> <james.clark@arm.com>
 James E Wilson <wilson@specifix.com>
 James Hogan <jhogan@kernel.org> <james@albanarts.com>
 James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
@@ -474,6 +475,8 @@
 Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
+Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.ibm.com>
+Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.vnet.ibm.com>
 Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <quic_neeraju@quicinc.com>
 Neeraj Upadhyay <neeraj.upadhyay@kernel.org> <neeraju@codeaurora.org>
 Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
diff --git a/Documentation/ABI/testing/debugfs-cxl b/Documentation/ABI/testing/debugfs-cxl
index c61f9b8..12488c1 100644
--- a/Documentation/ABI/testing/debugfs-cxl
+++ b/Documentation/ABI/testing/debugfs-cxl
@@ -14,9 +14,10 @@
 		event to its internal Informational Event log, updates the
 		Event Status register, and if configured, interrupts the host.
 		It is not an error to inject poison into an address that
-		already has poison present and no error is returned. The
-		inject_poison attribute is only visible for devices supporting
-		the capability.
+		already has poison present and no error is returned. If the
+		device returns 'Inject Poison Limit Reached' an -EBUSY error
+		is returned to the user. The inject_poison attribute is only
+		visible for devices supporting the capability.
 
 
 What:		/sys/kernel/debug/memX/clear_poison
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c1134ad..f1384c7 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3830,9 +3830,6 @@
 
 	noalign		[KNL,ARM]
 
-	noaltinstr	[S390,EARLY] Disables alternative instructions
-			patching (CPU alternatives feature).
-
 	noapic		[SMP,APIC,EARLY] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 7fd43947..f8bc163 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -454,7 +454,7 @@
 
 On architectures where unaligned accesses cause traps, and where this
 feature is supported (``CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN``;
-currently, ``arc`` and ``loongarch``), controls whether all
+currently, ``arc``, ``parisc`` and ``loongarch``), controls whether all
 unaligned traps are logged.
 
 = =============================================================
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 02eb4d9..3db60a0 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -264,3 +264,5 @@
 
 * :c:macro:`RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS`: An unsigned long which
   represent the highest userspace virtual address usable.
+
+* :c:macro:`RISCV_HWPROBE_KEY_TIME_CSR_FREQ`: Frequency (in Hz) of `time CSR`.
diff --git a/Documentation/arch/riscv/vm-layout.rst b/Documentation/arch/riscv/vm-layout.rst
index e476b43..077b968 100644
--- a/Documentation/arch/riscv/vm-layout.rst
+++ b/Documentation/arch/riscv/vm-layout.rst
@@ -47,11 +47,12 @@
                                                               | Kernel-space virtual memory, shared between all processes:
   ____________________________________________________________|___________________________________________________________
                     |            |                  |         |
-   ffffffc6fea00000 | -228    GB | ffffffc6feffffff |    6 MB | fixmap
-   ffffffc6ff000000 | -228    GB | ffffffc6ffffffff |   16 MB | PCI io
-   ffffffc700000000 | -228    GB | ffffffc7ffffffff |    4 GB | vmemmap
-   ffffffc800000000 | -224    GB | ffffffd7ffffffff |   64 GB | vmalloc/ioremap space
-   ffffffd800000000 | -160    GB | fffffff6ffffffff |  124 GB | direct mapping of all physical memory
+   ffffffc4fea00000 | -236    GB | ffffffc4feffffff |    6 MB | fixmap
+   ffffffc4ff000000 | -236    GB | ffffffc4ffffffff |   16 MB | PCI io
+   ffffffc500000000 | -236    GB | ffffffc5ffffffff |    4 GB | vmemmap
+   ffffffc600000000 | -232    GB | ffffffd5ffffffff |   64 GB | vmalloc/ioremap space
+   ffffffd600000000 | -168    GB | fffffff5ffffffff |  128 GB | direct mapping of all physical memory
+                    |            |                  |         |
    fffffff700000000 |  -36    GB | fffffffeffffffff |   32 GB | kasan
   __________________|____________|__________________|_________|____________________________________________________________
                                                               |
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
index c960c8e..08b89b6 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
@@ -30,7 +30,7 @@
 maintainers:
   - Mike Leach <mike.leach@linaro.org>
   - Suzuki K Poulose <suzuki.poulose@arm.com>
-  - James Clark <james.clark@arm.com>
+  - James Clark <james.clark@linaro.org>
   - Mao Jinlong <quic_jinlmao@quicinc.com>
   - Hao Zhang <quic_hazha@quicinc.com>
 
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
index 6745b4c..d50a603 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
@@ -29,7 +29,7 @@
 maintainers:
   - Mike Leach <mike.leach@linaro.org>
   - Suzuki K Poulose <suzuki.poulose@arm.com>
-  - James Clark <james.clark@arm.com>
+  - James Clark <james.clark@linaro.org>
   - Mao Jinlong <quic_jinlmao@quicinc.com>
   - Hao Zhang <quic_hazha@quicinc.com>
 
diff --git a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
index 765ca15..5192c93 100644
--- a/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
+++ b/Documentation/devicetree/bindings/display/panel/samsung,atna33xc20.yaml
@@ -14,7 +14,13 @@
 
 properties:
   compatible:
-    const: samsung,atna33xc20
+    oneOf:
+      # Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel
+      - const: samsung,atna33xc20
+      # Samsung 14.5" WQXGA+ (2880x1800 pixels) eDP AMOLED panel
+      - items:
+          - const: samsung,atna45af01
+          - const: samsung,atna33xc20
 
   enable-gpios: true
   port: true
diff --git a/Documentation/devicetree/bindings/dma/fsl,imx-dma.yaml b/Documentation/devicetree/bindings/dma/fsl,imx-dma.yaml
new file mode 100644
index 0000000..902a11f6
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/fsl,imx-dma.yaml
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/fsl,imx-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale Direct Memory Access (DMA) Controller for i.MX
+
+maintainers:
+  - Animesh Agarwal <animeshagarwal28@gmail.com>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    enum:
+      - fsl,imx1-dma
+      - fsl,imx21-dma
+      - fsl,imx27-dma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    items:
+      - description: DMA complete interrupt
+      - description: DMA Error interrupt
+    minItems: 1
+
+  "#dma-cells":
+    const: 1
+
+  dma-channels:
+    const: 16
+
+  dma-requests:
+    description: Number of DMA requests supported.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - "#dma-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    dma-controller@10001000 {
+      compatible = "fsl,imx27-dma";
+      reg = <0x10001000 0x1000>;
+      interrupts = <32 33>;
+      #dma-cells = <1>;
+      dma-channels = <16>;
+    };
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt
deleted file mode 100644
index 1c9929d..0000000
--- a/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt
+++ /dev/null
@@ -1,50 +0,0 @@
-* Freescale Direct Memory Access (DMA) Controller for i.MX
-
-This document will only describe differences to the generic DMA Controller and
-DMA request bindings as described in dma/dma.txt .
-
-* DMA controller
-
-Required properties:
-- compatible : Should be "fsl,<chip>-dma". chip can be imx1, imx21 or imx27
-- reg : Should contain DMA registers location and length
-- interrupts : First item should be DMA interrupt, second one is optional and
-    should contain DMA Error interrupt
-- #dma-cells : Has to be 1. imx-dma does not support anything else.
-
-Optional properties:
-- dma-channels : Number of DMA channels supported. Should be 16.
-- #dma-channels : deprecated
-- dma-requests : Number of DMA requests supported.
-- #dma-requests : deprecated
-
-Example:
-
-	dma: dma@10001000 {
-		compatible = "fsl,imx27-dma";
-		reg = <0x10001000 0x1000>;
-		interrupts = <32 33>;
-		#dma-cells = <1>;
-		dma-channels = <16>;
-	};
-
-
-* DMA client
-
-Clients have to specify the DMA requests with phandles in a list.
-
-Required properties:
-- dmas: List of one or more DMA request specifiers. One DMA request specifier
-    consists of a phandle to the DMA controller followed by the integer
-    specifying the request line.
-- dma-names: List of string identifiers for the DMA requests. For the correct
-    names, have a look at the specific client driver.
-
-Example:
-
-	sdhci1: sdhci@10013000 {
-		...
-		dmas = <&dma 7>;
-		dma-names = "rx-tx";
-		...
-	};
diff --git a/Documentation/devicetree/bindings/dma/fsl-qdma.txt b/Documentation/devicetree/bindings/dma/fsl-qdma.txt
deleted file mode 100644
index da371c4..0000000
--- a/Documentation/devicetree/bindings/dma/fsl-qdma.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-NXP Layerscape SoC qDMA Controller
-==================================
-
-This device follows the generic DMA bindings defined in dma/dma.txt.
-
-Required properties:
-
-- compatible:		Must be one of
-			 "fsl,ls1021a-qdma": for LS1021A Board
-			 "fsl,ls1028a-qdma": for LS1028A Board
-			 "fsl,ls1043a-qdma": for ls1043A Board
-			 "fsl,ls1046a-qdma": for ls1046A Board
-- reg:			Should contain the register's base address and length.
-- interrupts:		Should contain a reference to the interrupt used by this
-			device.
-- interrupt-names:	Should contain interrupt names:
-			 "qdma-queue0": the block0 interrupt
-			 "qdma-queue1": the block1 interrupt
-			 "qdma-queue2": the block2 interrupt
-			 "qdma-queue3": the block3 interrupt
-			 "qdma-error":  the error interrupt
-- fsl,dma-queues:	Should contain number of queues supported.
-- dma-channels:	Number of DMA channels supported
-- block-number:	the virtual block number
-- block-offset:	the offset of different virtual block
-- status-sizes:	status queue size of per virtual block
-- queue-sizes:		command queue size of per virtual block, the size number
-			based on queues
-
-Optional properties:
-
-- dma-channels:		Number of DMA channels supported by the controller.
-- big-endian:		If present registers and hardware scatter/gather descriptors
-			of the qDMA are implemented in big endian mode, otherwise in little
-			mode.
-
-Examples:
-
-	qdma: dma-controller@8390000 {
-			compatible = "fsl,ls1021a-qdma";
-			reg = <0x0 0x8388000 0x0 0x1000>, /* Controller regs */
-			      <0x0 0x8389000 0x0 0x1000>, /* Status regs */
-			      <0x0 0x838a000 0x0 0x2000>; /* Block regs */
-			interrupts = <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "qdma-error",
-				"qdma-queue0", "qdma-queue1";
-			dma-channels = <8>;
-			block-number = <2>;
-			block-offset = <0x1000>;
-			fsl,dma-queues = <2>;
-			status-sizes = <64>;
-			queue-sizes = <64 64>;
-			big-endian;
-		};
-
-DMA clients must use the format described in dma/dma.txt file.
diff --git a/Documentation/devicetree/bindings/dma/fsl-qdma.yaml b/Documentation/devicetree/bindings/dma/fsl-qdma.yaml
new file mode 100644
index 0000000..1b9ebdb
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/fsl-qdma.yaml
@@ -0,0 +1,132 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/fsl-qdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP Layerscape SoC qDMA Controller
+
+maintainers:
+  - Frank Li <Frank.Li@nxp.com>
+
+properties:
+  compatible:
+    enum:
+      - fsl,ls1021a-qdma
+      - fsl,ls1028a-qdma
+      - fsl,ls1043a-qdma
+      - fsl,ls1046a-qdma
+
+  reg:
+    items:
+      - description: Controller regs
+      - description: Status regs
+      - description: Block regs
+
+  interrupts:
+    minItems: 2
+    maxItems: 5
+
+  interrupt-names:
+    minItems: 2
+    items:
+      - const: qdma-error
+      - const: qdma-queue0
+      - const: qdma-queue1
+      - const: qdma-queue2
+      - const: qdma-queue3
+
+  dma-channels:
+    minimum: 1
+    maximum: 64
+
+  fsl,dma-queues:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: Should contain number of queues supported.
+    minimum: 1
+    maximum: 4
+
+  block-number:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: the virtual block number
+
+  block-offset:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: the offset of different virtual block
+
+  status-sizes:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: status queue size of per virtual block
+
+  queue-sizes:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description:
+      command queue size of per virtual block, the size number
+      based on queues
+
+  big-endian:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      If present registers and hardware scatter/gather descriptors
+      of the qDMA are implemented in big endian mode, otherwise in little
+      mode.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-names
+  - fsl,dma-queues
+  - block-number
+  - block-offset
+  - status-sizes
+  - queue-sizes
+
+allOf:
+  - $ref: dma-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,ls1028a-qdma
+              - fsl,ls1043a-qdma
+              - fsl,ls1046a-qdma
+    then:
+      properties:
+        interrupts:
+          minItems: 5
+        interrupt-names:
+          minItems: 5
+    else:
+      properties:
+        interrupts:
+          maxItems: 3
+        interrupt-names:
+          maxItems: 3
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    dma-controller@8390000 {
+        compatible = "fsl,ls1021a-qdma";
+        reg = <0x8388000 0x1000>, /* Controller regs */
+              <0x8389000 0x1000>, /* Status regs */
+              <0x838a000 0x2000>; /* Block regs */
+        interrupts = <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "qdma-error", "qdma-queue0", "qdma-queue1";
+        #dma-cells = <1>;
+        dma-channels = <8>;
+        block-number = <2>;
+        block-offset = <0x1000>;
+        status-sizes = <64>;
+        queue-sizes = <64 64>;
+        big-endian;
+        fsl,dma-queues = <2>;
+    };
+
diff --git a/Documentation/devicetree/bindings/dma/sprd,sc9860-dma.yaml b/Documentation/devicetree/bindings/dma/sprd,sc9860-dma.yaml
new file mode 100644
index 0000000..9464721
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/sprd,sc9860-dma.yaml
@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/sprd,sc9860-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Spreadtrum SC9860 DMA controller
+
+description: |
+  There are three DMA controllers: AP DMA, AON DMA and AGCP DMA. For AGCP
+  DMA controller, it can or do not request the IRQ, which will save
+  system power without resuming system by DMA interrupts if AGCP DMA
+  does not request the IRQ.
+
+maintainers:
+  - Orson Zhai <orsonzhai@gmail.com>
+  - Baolin Wang <baolin.wang7@gmail.com>
+  - Chunyan Zhang <zhang.lyra@gmail.com>
+
+properties:
+  compatible:
+    const: sprd,sc9860-dma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    items:
+      - description: DMA enable clock
+      - description: optional ashb_eb clock, only for the AGCP DMA controller
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: enable
+      - const: ashb_eb
+
+  '#dma-cells':
+    const: 1
+
+  dma-channels:
+    const: 32
+
+  '#dma-channels':
+    const: 32
+    deprecated: true
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#dma-cells'
+  - dma-channels
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sprd,sc9860-clk.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    /* AP DMA controller */
+    dma-controller@20100000 {
+      compatible = "sprd,sc9860-dma";
+      reg = <0x20100000 0x4000>;
+      interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&apahb_gate CLK_DMA_EB>;
+      clock-names = "enable";
+      #dma-cells = <1>;
+      dma-channels = <32>;
+    };
+
+    /* AGCP DMA controller */
+    dma-controller@41580000 {
+      compatible = "sprd,sc9860-dma";
+      reg = <0x41580000 0x4000>;
+      clocks = <&agcp_gate CLK_AGCP_DMAAP_EB>,
+               <&agcp_gate CLK_AGCP_AP_ASHB_EB>;
+      clock-names = "enable", "ashb_eb";
+      #dma-cells = <1>;
+      dma-channels = <32>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/dma/sprd-dma.txt b/Documentation/devicetree/bindings/dma/sprd-dma.txt
deleted file mode 100644
index c7e9b5f..0000000
--- a/Documentation/devicetree/bindings/dma/sprd-dma.txt
+++ /dev/null
@@ -1,44 +0,0 @@
-* Spreadtrum DMA controller
-
-This binding follows the generic DMA bindings defined in dma.txt.
-
-Required properties:
-- compatible: Should be "sprd,sc9860-dma".
-- reg: Should contain DMA registers location and length.
-- interrupts: Should contain one interrupt shared by all channel.
-- #dma-cells: must be <1>. Used to represent the number of integer
-	cells in the dmas property of client device.
-- dma-channels : Number of DMA channels supported. Should be 32.
-- clock-names: Should contain the clock of the DMA controller.
-- clocks: Should contain a clock specifier for each entry in clock-names.
-
-Deprecated properties:
-- #dma-channels : Number of DMA channels supported. Should be 32.
-
-Example:
-
-Controller:
-apdma: dma-controller@20100000 {
-	compatible = "sprd,sc9860-dma";
-	reg = <0x20100000 0x4000>;
-	interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
-	#dma-cells = <1>;
-	dma-channels = <32>;
-	clock-names = "enable";
-	clocks = <&clk_ap_ahb_gates 5>;
-};
-
-
-Client:
-DMA clients connected to the Spreadtrum DMA controller must use the format
-described in the dma.txt file, using a two-cell specifier for each channel.
-The two cells in order are:
-1. A phandle pointing to the DMA controller.
-2. The slave id.
-
-spi0: spi@70a00000{
-	...
-	dma-names = "rx_chn", "tx_chn";
-	dmas = <&apdma 11>, <&apdma 12>;
-	...
-};
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma.yaml
similarity index 96%
rename from Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
rename to Documentation/devicetree/bindings/dma/stm32/st,stm32-dma.yaml
index ff935a0..11a289f 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/dma/st,stm32-dma.yaml#
+$id: http://devicetree.org/schemas/dma/stm32/st,stm32-dma.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: STMicroelectronics STM32 DMA Controller
@@ -53,7 +53,7 @@
   - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
-  - $ref: dma-controller.yaml#
+  - $ref: /schemas/dma/dma-controller.yaml#
 
 properties:
   "#dma-cells":
diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
new file mode 100644
index 0000000..7fdc44b
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dma3.yaml
@@ -0,0 +1,135 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/stm32/st,stm32-dma3.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 DMA3 Controller
+
+description: |
+  The STM32 DMA3 is a direct memory access controller with different features
+  depending on its hardware configuration.
+  It is either called LPDMA (Low Power), GPDMA (General Purpose) or HPDMA (High
+  Performance).
+  Its hardware configuration registers allow to dynamically expose its features.
+
+  GPDMA and HPDMA support 16 independent DMA channels, while only 4 for LPDMA.
+  GPDMA and HPDMA support 256 DMA requests from peripherals, 8 for LPDMA.
+
+  Bindings are generic for these 3 STM32 DMA3 configurations.
+
+  DMA clients connected to the STM32 DMA3 controller must use the format
+  described in "#dma-cells" property description below, using a three-cell
+  specifier for each channel.
+
+maintainers:
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
+
+allOf:
+  - $ref: /schemas/dma/dma-controller.yaml#
+
+properties:
+  compatible:
+    const: st,stm32mp25-dma3
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 4
+    maxItems: 16
+    description:
+      Should contain all of the per-channel DMA interrupts in ascending order
+      with respect to the DMA channel index.
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  "#dma-cells":
+    const: 3
+    description: |
+      Specifies the number of cells needed to provide DMA controller specific
+      information.
+      The first cell is the request line number.
+      The second cell is a 32-bit mask specifying the DMA channel requirements:
+        -bit 0-1: The priority level
+          0x0: low priority, low weight
+          0x1: low priority, mid weight
+          0x2: low priority, high weight
+          0x3: high priority
+        -bit 4-7: The FIFO requirement for queuing source/destination transfers
+          0x0: no FIFO requirement/any channel can fit
+          0x2: FIFO of 8 bytes (2^2+1)
+          0x4: FIFO of 32 bytes (2^4+1)
+          0x6: FIFO of 128 bytes (2^6+1)
+          0x7: FIFO of 256 bytes (2^7+1)
+      The third cell is a 32-bit mask specifying the DMA transfer requirements:
+        -bit 0: The source incrementing burst
+          0x0: fixed burst
+          0x1: contiguously incremented burst
+        -bit 1: The source allocated port
+          0x0: port 0 is allocated to the source transfer
+          0x1: port 1 is allocated to the source transfer
+        -bit 4: The destination incrementing burst
+          0x0: fixed burst
+          0x1: contiguously incremented burst
+        -bit 5: The destination allocated port
+          0x0: port 0 is allocated to the destination transfer
+          0x1: port 1 is allocated to the destination transfer
+        -bit 8: The type of hardware request
+          0x0: burst
+          0x1: block
+        -bit 9: The control mode
+          0x0: DMA controller control mode
+          0x1: peripheral control mode
+        -bit 12-13: The transfer complete event mode
+          0x0: at block level, transfer complete event is generated at the end
+               of a block
+          0x2: at LLI level, the transfer complete event is generated at the end
+               of the LLI transfer
+               including the update of the LLI if any
+          0x3: at channel level, the transfer complete event is generated at the
+               end of the last LLI
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - "#dma-cells"
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/st,stm32mp25-rcc.h>
+    dma-controller@40400000 {
+      compatible = "st,stm32mp25-dma3";
+      reg = <0x40400000 0x1000>;
+      interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+                   <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&rcc CK_BUS_HPDMA1>;
+      #dma-cells = <3>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
similarity index 90%
rename from Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
rename to Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
index ddf82bf..f26c914 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/dma/st,stm32-dmamux.yaml#
+$id: http://devicetree.org/schemas/dma/stm32/st,stm32-dmamux.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: STMicroelectronics STM32 DMA MUX (DMA request router)
@@ -10,7 +10,7 @@
   - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
-  - $ref: dma-router.yaml#
+  - $ref: /schemas/dma/dma-router.yaml#
 
 properties:
   "#dma-cells":
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-mdma.yaml
similarity index 96%
rename from Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
rename to Documentation/devicetree/bindings/dma/stm32/st,stm32-mdma.yaml
index 3874544..45fe91d 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-mdma.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/dma/st,stm32-mdma.yaml#
+$id: http://devicetree.org/schemas/dma/stm32/st,stm32-mdma.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: STMicroelectronics STM32 MDMA Controller
@@ -53,7 +53,7 @@
   - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
-  - $ref: dma-controller.yaml#
+  - $ref: /schemas/dma/dma-controller.yaml#
 
 properties:
   "#dma-cells":
diff --git a/Documentation/devicetree/bindings/i3c/i3c.yaml b/Documentation/devicetree/bindings/i3c/i3c.yaml
index 113957e..e25fa72 100644
--- a/Documentation/devicetree/bindings/i3c/i3c.yaml
+++ b/Documentation/devicetree/bindings/i3c/i3c.yaml
@@ -91,6 +91,7 @@
               - const: 0
               - description: |
                   Shall encode the I3C LVR (Legacy Virtual Register):
+                  See include/dt-bindings/i3c/i3c.h
                     bit[31:8]: unused/ignored
                     bit[7:5]: I2C device index. Possible values:
                       * 0: I2C device has a 50 ns spike filter
@@ -153,6 +154,8 @@
 
 examples:
   - |
+    #include <dt-bindings/i3c/i3c.h>
+
     i3c@d040000 {
         compatible = "cdns,i3c-master";
         clocks = <&coreclock>, <&i3csysclock>;
@@ -166,7 +169,7 @@
         /* I2C device. */
         eeprom@57 {
             compatible = "atmel,24c01";
-            reg = <0x57 0x0 0x10>;
+            reg = <0x57 0x0 (I2C_FM | I2C_FILTER)>;
             pagesize = <0x8>;
         };
 
diff --git a/Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml b/Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml
index c0e805e..4fc13e3 100644
--- a/Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml
+++ b/Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml
@@ -20,7 +20,16 @@
     maxItems: 1
 
   clocks:
-    maxItems: 1
+    minItems: 1
+    items:
+      - description: Core clock
+      - description: APB clock
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: core
+      - const: apb
 
   interrupts:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index a03da94..190889c 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -120,9 +120,8 @@
         description:
           Positive input can be connected to pins AIN1 to AIN16 by choosing the
           appropriate value from 1 to 16. Negative input is connected to AINCOM.
-        items:
-          minimum: 1
-          maximum: 16
+        minimum: 1
+        maximum: 16
 
     oneOf:
       - required:
diff --git a/Documentation/devicetree/bindings/phy/airoha,en7581-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/airoha,en7581-pcie-phy.yaml
new file mode 100644
index 0000000..98fcb1b
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/airoha,en7581-pcie-phy.yaml
@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/airoha,en7581-pcie-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha EN7581 PCI-Express PHY
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+description:
+  The PCIe PHY supports physical layer functionality for PCIe Gen2/Gen3 port.
+
+properties:
+  compatible:
+    const: airoha,en7581-pcie-phy
+
+  reg:
+    items:
+      - description: PCIE analog base address
+      - description: PCIE lane0 base address
+      - description: PCIE lane1 base address
+      - description: PCIE lane0 detection time base address
+      - description: PCIE lane1 detection time base address
+      - description: PCIE Rx AEQ base address
+
+  reg-names:
+    items:
+      - const: csr-2l
+      - const: pma0
+      - const: pma1
+      - const: p0-xr-dtime
+      - const: p1-xr-dtime
+      - const: rx-aeq
+
+  "#phy-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - "#phy-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/phy/phy.h>
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        phy@11e80000 {
+            compatible = "airoha,en7581-pcie-phy";
+            #phy-cells = <0>;
+            reg = <0x0 0x1fa5a000 0x0 0xfff>,
+                  <0x0 0x1fa5b000 0x0 0xfff>,
+                  <0x0 0x1fa5c000 0x0 0xfff>,
+                  <0x0 0x1fc10044 0x0 0x4>,
+                  <0x0 0x1fc30044 0x0 0x4>,
+                  <0x0 0x1fc15030 0x0 0x104>;
+            reg-names = "csr-2l", "pma0", "pma1",
+                        "p0-xr-dtime", "p1-xr-dtime",
+                        "rx-aeq";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
index 0031fb6..1a0c436 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
@@ -41,6 +41,9 @@
       Phandle to a regulator that provides power to the PHY. This
       regulator will be managed during the PHY power on/off sequence.
 
+  power-domains:
+    maxItems: 1
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/phy/fsl,imx8qm-hsio.yaml b/Documentation/devicetree/bindings/phy/fsl,imx8qm-hsio.yaml
new file mode 100644
index 0000000..147bbfd
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/fsl,imx8qm-hsio.yaml
@@ -0,0 +1,164 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/fsl,imx8qm-hsio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale i.MX8QM SoC series High Speed IO(HSIO) SERDES PHY
+
+maintainers:
+  - Richard Zhu <hongxing.zhu@nxp.com>
+
+properties:
+  compatible:
+    enum:
+      - fsl,imx8qm-hsio
+      - fsl,imx8qxp-hsio
+  reg:
+    items:
+      - description: Base address and length of the PHY block
+      - description: HSIO control and status registers(CSR) of the PHY
+      - description: HSIO CSR of the controller bound to the PHY
+      - description: HSIO CSR for MISC
+
+  reg-names:
+    items:
+      - const: reg
+      - const: phy
+      - const: ctrl
+      - const: misc
+
+  "#phy-cells":
+    const: 3
+    description:
+      The first defines lane index.
+      The second defines the type of the PHY refer to the include phy.h.
+      The third defines the controller index, indicated which controller
+      is bound to the lane.
+
+  clocks:
+    minItems: 5
+    maxItems: 14
+
+  clock-names:
+    minItems: 5
+    maxItems: 14
+
+  fsl,hsio-cfg:
+    description: |
+      Specifies the use case of the HSIO module in the hardware design.
+      Regarding the design of i.MX8QM HSIO subsystem, HSIO module can be
+      confiured as following three use cases.
+      +---------------------------------------+
+      |                  | i.MX8QM            |
+      |------------------|--------------------|
+      |                  | Lane0| Lane1| Lane2|
+      |------------------|------|------|------|
+      | pciea-x2-sata    | PCIEA| PCIEA| SATA |
+      |------------------|------|------|------|
+      | pciea-x2-pcieb   | PCIEA| PCIEA| PCIEB|
+      |------------------|------|------|------|
+      | pciea-pcieb-sata | PCIEA| PCIEB| SATA |
+      +---------------------------------------+
+    $ref: /schemas/types.yaml#/definitions/string
+    enum: [ pciea-x2-sata, pciea-x2-pcieb, pciea-pcieb-sata]
+    default: pciea-pcieb-sata
+
+  fsl,refclk-pad-mode:
+    description:
+      Specifies the mode of the refclk pad used. INPUT(PHY refclock is
+      provided externally via the refclk pad) or OUTPUT(PHY refclock is
+      derived from SoC internal source and provided on the refclk pad).
+      This property not exists means unused(PHY refclock is derived from
+      SoC internal source).
+    $ref: /schemas/types.yaml#/definitions/string
+    enum: [ input, output, unused ]
+    default: unused
+
+  power-domains:
+    minItems: 1
+    maxItems: 2
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - "#phy-cells"
+  - clocks
+  - clock-names
+  - fsl,hsio-cfg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx8qxp-hsio
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: pclk0
+            - const: apb_pclk0
+            - const: phy0_crr
+            - const: ctl0_crr
+            - const: misc_crr
+        power-domains:
+          maxItems: 1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx8qm-hsio
+    then:
+      properties:
+        clock-names:
+          items:
+            - const: pclk0
+            - const: pclk1
+            - const: apb_pclk0
+            - const: apb_pclk1
+            - const: pclk2
+            - const: epcs_tx
+            - const: epcs_rx
+            - const: apb_pclk2
+            - const: phy0_crr
+            - const: phy1_crr
+            - const: ctl0_crr
+            - const: ctl1_crr
+            - const: ctl2_crr
+            - const: misc_crr
+        power-domains:
+          minItems: 2
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/imx8-clock.h>
+    #include <dt-bindings/clock/imx8-lpcg.h>
+    #include <dt-bindings/firmware/imx/rsrc.h>
+    #include <dt-bindings/phy/phy-imx8-pcie.h>
+
+    phy@5f1a0000 {
+        compatible = "fsl,imx8qxp-hsio";
+        reg = <0x5f1a0000 0x10000>,
+              <0x5f120000 0x10000>,
+              <0x5f140000 0x10000>,
+              <0x5f160000 0x10000>;
+        reg-names = "reg", "phy", "ctrl", "misc";
+        clocks = <&phyx1_lpcg IMX_LPCG_CLK_0>,
+                 <&phyx1_lpcg IMX_LPCG_CLK_4>,
+                 <&phyx1_crr1_lpcg IMX_LPCG_CLK_4>,
+                 <&pcieb_crr3_lpcg IMX_LPCG_CLK_4>,
+                 <&misc_crr5_lpcg IMX_LPCG_CLK_4>;
+        clock-names = "pclk0", "apb_pclk0", "phy0_crr", "ctl0_crr", "misc_crr";
+        power-domains = <&pd IMX_SC_R_SERDES_1>;
+        #phy-cells = <3>;
+        fsl,hsio-cfg = "pciea-pcieb-sata";
+        fsl,refclk-pad-mode = "input";
+    };
+...
diff --git a/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml b/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml
index 9ce7b4c..2ef02aa 100644
--- a/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml
@@ -41,6 +41,12 @@
       Phandle to the system controller node
     $ref: /schemas/types.yaml#/definitions/phandle
 
+  swap-dx-lanes:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description: |
+      Specifies the ports which will swap the differential-pair (D+/D-),
+      default is not-swapped.
+
 # Required child nodes:
 
 patternProperties:
diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
index 634cec5..58ce2d9 100644
--- a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
@@ -19,6 +19,8 @@
       - qcom,ipq6018-qmp-pcie-phy
       - qcom,ipq8074-qmp-gen3-pcie-phy
       - qcom,ipq8074-qmp-pcie-phy
+      - qcom,ipq9574-qmp-gen3x1-pcie-phy
+      - qcom,ipq9574-qmp-gen3x2-pcie-phy
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index 16634f7..03dbd02 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -91,8 +91,7 @@
   "#clock-cells": true
 
   clock-output-names:
-    minItems: 1
-    maxItems: 2
+    maxItems: 1
 
   "#phy-cells":
     const: 0
@@ -222,14 +221,10 @@
               - qcom,sm8650-qmp-gen4x2-pcie-phy
     then:
       properties:
-        clock-output-names:
-          minItems: 2
         "#clock-cells":
           const: 1
     else:
       properties:
-        clock-output-names:
-          maxItems: 1
         "#clock-cells":
           const: 0
 
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
index 325585b..0e0b6ca 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
@@ -20,8 +20,9 @@
       - qcom,ipq8074-qmp-usb3-phy
       - qcom,ipq9574-qmp-usb3-phy
       - qcom,msm8996-qmp-usb3-phy
-      - com,qdu1000-qmp-usb3-uni-phy
+      - qcom,qdu1000-qmp-usb3-uni-phy
       - qcom,sa8775p-qmp-usb3-uni-phy
+      - qcom,sc8180x-qmp-usb3-uni-phy
       - qcom,sc8280xp-qmp-usb3-uni-phy
       - qcom,sdm845-qmp-usb3-uni-phy
       - qcom,sdx55-qmp-usb3-uni-phy
@@ -112,6 +113,7 @@
             enum:
               - qcom,qdu1000-qmp-usb3-uni-phy
               - qcom,sa8775p-qmp-usb3-uni-phy
+              - qcom,sc8180x-qmp-usb3-uni-phy
               - qcom,sc8280xp-qmp-usb3-uni-phy
               - qcom,sm8150-qmp-usb3-uni-phy
               - qcom,sm8250-qmp-usb3-uni-phy
@@ -152,6 +154,7 @@
           contains:
             enum:
               - qcom,sa8775p-qmp-usb3-uni-phy
+              - qcom,sc8180x-qmp-usb3-uni-phy
               - qcom,sc8280xp-qmp-usb3-uni-phy
               - qcom,x1e80100-qmp-usb3-uni-phy
     then:
diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml
index f042d6a..e03b516 100644
--- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml
@@ -15,6 +15,7 @@
       contains:
         enum:
           - qcom,usb-hs-phy-apq8064
+          - qcom,usb-hs-phy-msm8660
           - qcom,usb-hs-phy-msm8960
 then:
   properties:
@@ -41,6 +42,7 @@
       - enum:
           - qcom,usb-hs-phy-apq8064
           - qcom,usb-hs-phy-msm8226
+          - qcom,usb-hs-phy-msm8660
           - qcom,usb-hs-phy-msm8916
           - qcom,usb-hs-phy-msm8960
           - qcom,usb-hs-phy-msm8974
diff --git a/Documentation/devicetree/bindings/phy/rockchip,rk3399-emmc-phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,rk3399-emmc-phy.yaml
new file mode 100644
index 0000000..3e3729b
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/rockchip,rk3399-emmc-phy.yaml
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/rockchip,rk3399-emmc-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip EMMC PHY
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    const: rockchip,rk3399-emmc-phy
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: emmcclk
+
+  drive-impedance-ohm:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Specifies the drive impedance in Ohm.
+    enum: [33, 40, 50, 66, 100]
+    default: 50
+
+  rockchip,enable-strobe-pulldown:
+    type: boolean
+    description: |
+      Enable internal pull-down for the strobe
+      line.  If not set, pull-down is not used.
+
+  rockchip,output-tapdelay-select:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Specifies the phyctrl_otapdlysec register.
+    default: 0x4
+    maximum: 0xf
+
+  "#phy-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - "#phy-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    phy@f780 {
+      compatible = "rockchip,rk3399-emmc-phy";
+      reg = <0xf780 0x20>;
+      clocks = <&sdhci>;
+      clock-names = "emmcclk";
+      drive-impedance-ohm = <50>;
+      #phy-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt b/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
deleted file mode 100644
index 57d28c0..0000000
--- a/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
+++ /dev/null
@@ -1,43 +0,0 @@
-Rockchip EMMC PHY
------------------------
-
-Required properties:
- - compatible: rockchip,rk3399-emmc-phy
- - #phy-cells: must be 0
- - reg: PHY register address offset and length in "general
-   register files"
-
-Optional properties:
- - clock-names: Should contain "emmcclk".  Although this is listed as optional
-		(because most boards can get basic functionality without having
-		access to it), it is strongly suggested.
-		See ../clock/clock-bindings.txt for details.
- - clocks: Should have a phandle to the card clock exported by the SDHCI driver.
- - drive-impedance-ohm: Specifies the drive impedance in Ohm.
-                        Possible values are 33, 40, 50, 66 and 100.
-                        If not set, the default value of 50 will be applied.
- - rockchip,enable-strobe-pulldown: Enable internal pull-down for the strobe
-                                    line.  If not set, pull-down is not used.
- - rockchip,output-tapdelay-select: Specifies the phyctrl_otapdlysec register.
-                                    If not set, the register defaults to 0x4.
-                                    Maximum value 0xf.
-
-Example:
-
-
-grf: syscon@ff770000 {
-	compatible = "rockchip,rk3399-grf", "syscon", "simple-mfd";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-...
-
-	emmcphy: phy@f780 {
-		compatible = "rockchip,rk3399-emmc-phy";
-		reg = <0xf780 0x20>;
-		clocks = <&sdhci>;
-		clock-names = "emmcclk";
-		drive-impedance-ohm = <50>;
-		#phy-cells = <0>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
index 452e584..16321cd 100644
--- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
@@ -25,6 +25,7 @@
 properties:
   compatible:
     enum:
+      - google,gs101-usb31drd-phy
       - samsung,exynos5250-usbdrd-phy
       - samsung,exynos5420-usbdrd-phy
       - samsung,exynos5433-usbdrd-phy
@@ -57,7 +58,15 @@
       the OF graph bindings specified.
 
   reg:
-    maxItems: 1
+    minItems: 1
+    maxItems: 3
+
+  reg-names:
+    minItems: 1
+    items:
+      - const: phy
+      - const: pcs
+      - const: pma
 
   samsung,pmu-syscon:
     $ref: /schemas/types.yaml#/definitions/phandle
@@ -72,6 +81,19 @@
     description:
       VBUS Boost 5V power source.
 
+  pll-supply:
+    description: Power supply for the USB PLL.
+  dvdd-usb20-supply:
+    description: DVDD power supply for the USB 2.0 phy.
+  vddh-usb20-supply:
+    description: VDDh power supply for the USB 2.0 phy.
+  vdd33-usb20-supply:
+    description: 3.3V power supply for the USB 2.0 phy.
+  vdda-usbdp-supply:
+    description: VDDa power supply for the USB DP phy.
+  vddh-usbdp-supply:
+    description: VDDh power supply for the USB DP phy.
+
 required:
   - compatible
   - clocks
@@ -85,6 +107,40 @@
       properties:
         compatible:
           contains:
+            const: google,gs101-usb31drd-phy
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Gate of main PHY clock
+            - description: Gate of PHY reference clock
+            - description: Gate of control interface AXI clock
+            - description: Gate of control interface APB clock
+            - description: Gate of SCL APB clock
+        clock-names:
+          items:
+            - const: phy
+            - const: ref
+            - const: ctrl_aclk
+            - const: ctrl_pclk
+            - const: scl_pclk
+        reg:
+          minItems: 3
+        reg-names:
+          minItems: 3
+      required:
+        - reg-names
+        - pll-supply
+        - dvdd-usb20-supply
+        - vddh-usb20-supply
+        - vdd33-usb20-supply
+        - vdda-usbdp-supply
+        - vddh-usbdp-supply
+
+  - if:
+      properties:
+        compatible:
+          contains:
             enum:
               - samsung,exynos5433-usbdrd-phy
               - samsung,exynos7-usbdrd-phy
@@ -100,7 +156,20 @@
             - const: phy_utmi
             - const: phy_pipe
             - const: itp
-    else:
+        reg:
+          maxItems: 1
+        reg-names:
+          maxItems: 1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - samsung,exynos5250-usbdrd-phy
+              - samsung,exynos5420-usbdrd-phy
+              - samsung,exynos850-usbdrd-phy
+    then:
       properties:
         clocks:
           minItems: 2
@@ -109,6 +178,10 @@
           items:
             - const: phy
             - const: ref
+        reg:
+          maxItems: 1
+        reg-names:
+          maxItems: 1
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml b/Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml
new file mode 100644
index 0000000..4a06a26
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/starfive,jh7110-dphy-tx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Starfive SoC MIPI D-PHY Tx Controller
+
+maintainers:
+  - Keith Zhao <keith.zhao@starfivetech.com>
+  - Shengyang Chen <shengyang.chen@starfivetech.com>
+
+description:
+  The Starfive SoC uses the MIPI DSI D-PHY based on M31 IP to transfer
+  DSI data.
+
+properties:
+  compatible:
+    const: starfive,jh7110-dphy-tx
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: txesc
+
+  resets:
+    items:
+      - description: MIPITX_DPHY_SYS reset
+
+  reset-names:
+    items:
+      - const: sys
+
+  power-domains:
+    maxItems: 1
+
+  "#phy-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - power-domains
+  - "#phy-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    phy@295e0000 {
+      compatible = "starfive,jh7110-dphy-tx";
+      reg = <0x295e0000 0x10000>;
+      clocks = <&voutcrg 14>;
+      clock-names = "txesc";
+      resets = <&syscrg 10>;
+      reset-names = "sys";
+      power-domains = <&aon_syscon 0>;
+      #phy-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index 79798c7..78c6d5b 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -176,9 +176,10 @@
             Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt
 
       patternProperties:
-        "phy@[0-9a-f]+$":
-          description:
-            Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
+        "^phy@[0-9a-f]+$":
+          type: object
+          $ref: /schemas/phy/rockchip,rk3399-emmc-phy.yaml#
+          unevaluatedProperties: false
 
   - if:
       properties:
@@ -292,6 +293,15 @@
         #phy-cells = <0>;
       };
 
+      phy@f780 {
+        compatible = "rockchip,rk3399-emmc-phy";
+        reg = <0xf780 0x20>;
+        clocks = <&sdhci>;
+        clock-names = "emmcclk";
+        drive-impedance-ohm = <50>;
+        #phy-cells = <0>;
+      };
+
       u2phy0: usb2phy@e450 {
         compatible = "rockchip,rk3399-usb2phy";
         reg = <0xe450 0x10>;
diff --git a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
index a55c863..76e43c0 100644
--- a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
@@ -42,7 +42,7 @@
   dmas:
     description: |
       DMA specifiers for tx and rx dma. DMA fifo mode must be used. See
-      the STM32 DMA bindings Documentation/devicetree/bindings/dma/st,stm32-dma.yaml.
+      the STM32 DMA controllers bindings Documentation/devicetree/bindings/dma/stm32/*.yaml.
     items:
       - description: rx DMA channel
       - description: tx DMA channel
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 5d3dc95..7913ca9 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -328,7 +328,9 @@
           - renesas,hs3001
             # Renesas ISL29501 time-of-flight sensor
           - renesas,isl29501
-            # Rohm DH2228FV
+            # Rohm BH2228FV 8 channel DAC
+          - rohm,bh2228fv
+            # Rohm DH2228FV - This device does not exist, use rohm,bh2228fv instead.
           - rohm,dh2228fv
             # S524AD0XF1 (128K/256K-bit Serial EEPROM for Low Power)
           - samsung,24ad0xd1
diff --git a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
index 69845ec..d0eff1e 100644
--- a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
@@ -21,6 +21,7 @@
           - amlogic,t7-wdt
       - items:
           - enum:
+              - amlogic,a4-wdt
               - amlogic,c3-wdt
               - amlogic,s4-wdt
           - const: amlogic,t7-wdt
diff --git a/Documentation/devicetree/bindings/watchdog/dlg,da9062-watchdog.yaml b/Documentation/devicetree/bindings/watchdog/dlg,da9062-watchdog.yaml
index c8f6981..64619ba 100644
--- a/Documentation/devicetree/bindings/watchdog/dlg,da9062-watchdog.yaml
+++ b/Documentation/devicetree/bindings/watchdog/dlg,da9062-watchdog.yaml
@@ -28,7 +28,7 @@
       Add this property to disable the watchdog during suspend.
       Only use this option if you can't use the watchdog automatic suspend
       function during a suspend (see register CONTROL_B).
-  
+
   dlg,wdt-sd:
     $ref: /schemas/types.yaml#/definitions/uint32
     enum: [0, 1]
diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
index ffb17ad..eba454d 100644
--- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml
@@ -29,6 +29,7 @@
               - renesas,r9a07g043-wdt    # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-wdt    # RZ/G2{L,LC}
               - renesas,r9a07g054-wdt    # RZ/V2L
+              - renesas,r9a08g045-wdt    # RZ/G3S
           - const: renesas,rzg2l-wdt
 
       - items:
diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst
index 036e495..12b8272 100644
--- a/Documentation/driver-api/cxl/index.rst
+++ b/Documentation/driver-api/cxl/index.rst
@@ -9,4 +9,6 @@
 
    memory-devices
 
+   maturity-map
+
 .. only::  subproject and html
diff --git a/Documentation/driver-api/cxl/maturity-map.rst b/Documentation/driver-api/cxl/maturity-map.rst
new file mode 100644
index 0000000..df8e2ac
--- /dev/null
+++ b/Documentation/driver-api/cxl/maturity-map.rst
@@ -0,0 +1,202 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+===========================================
+Compute Express Link Subsystem Maturity Map
+===========================================
+
+The Linux CXL subsystem tracks the dynamic `CXL specification
+<https://computeexpresslink.org/cxl-specification-landing-page>`_ that
+continues to respond to new use cases with new features, capability
+updates and fixes. At any given point some aspects of the subsystem are
+more mature than others. While the periodic pull requests summarize the
+`work being incorporated each merge window
+<https://lore.kernel.org/linux-cxl/?q=s%3APULL+s%3ACXL+tc%3Atorvalds+NOT+s%3ARe>`_,
+those do not always convey progress relative to a starting point and a
+future end goal.
+
+What follows is a coarse breakdown of the subsystem's major
+responsibilities along with a maturity score. The expectation is that
+the change-history of this document provides an overview summary of the
+subsystem maturation over time.
+
+The maturity scores are:
+
+- [3] Mature: Work in this area is complete and no changes on the horizon.
+  Note that this score can regress from one kernel release to the next
+  based on new test results or end user reports.
+
+- [2] Stabilizing: Major functionality operational, common cases are
+  mature, but known corner cases are still a work in progress.
+
+- [1] Initial: Capability that has exited the Proof of Concept phase, but
+  may still have significant gaps to close and fixes to apply as real
+  world testing occurs.
+
+- [0] Known gap: Feature is on a medium to long term horizon to
+  implement.  If the specification has a feature that does not even have
+  a '0' score in this document, there is a good chance that no one in
+  the linux-cxl@vger.kernel.org community has started to look at it.
+
+- X: Out of scope for kernel enabling, or kernel enabling not required
+
+Feature and Capabilities
+========================
+
+Enumeration / Provisioning
+--------------------------
+All of the fundamental enumeration an object model of the subsystem is
+in place, but there are several corner cases that are pending closure.
+
+
+* [2] CXL Window Enumeration
+
+  * [0] :ref:`Extended-linear memory-side cache <extended-linear>`
+  * [0] Low Memory-hole
+  * [0] Hetero-interleave
+
+* [2] Switch Enumeration
+
+  * [0] CXL register enumeration link-up dependency
+
+* [2] HDM Decoder Configuration
+
+  * [0] Decoder target and granularity constraints
+
+* [2] Performance enumeration
+
+  * [3] Endpoint CDAT
+  * [3] Switch CDAT
+  * [1] CDAT to Core-mm integration
+
+    * [1] x86
+    * [0] Arm64
+    * [0] All other arch.
+
+  * [0] Shared link
+
+* [2] Hotplug
+  (see CXL Window Enumeration)
+
+  * [0] Handle Soft Reserved conflicts
+
+* [0] :ref:`RCH link status <rch-link-status>`
+* [0] Fabrics / G-FAM (chapter 7)
+* [0] Global Access Endpoint
+
+
+RAS
+---
+In many ways CXL can be seen as a standardization of what would normally
+be handled by custom EDAC drivers. The open development here is
+mainly caused by the enumeration corner cases above.
+
+* [3] Component events (OS)
+* [2] Component events (FFM)
+* [1] Endpoint protocol errors (OS)
+* [1] Endpoint protocol errors (FFM)
+* [0] Switch protocol errors (OS)
+* [1] Switch protocol errors (FFM)
+* [2] DPA->HPA Address translation
+
+    * [1] XOR Interleave translation
+      (see CXL Window Enumeration)
+
+* [1] Memory Failure coordination
+* [0] Scrub control
+* [2] ACPI error injection EINJ
+
+  * [0] EINJ v2
+  * [X] Compliance DOE
+
+* [2] Native error injection
+* [3] RCH error handling
+* [1] VH error handling
+* [0] PPR
+* [0] Sparing
+* [0] Device built in test
+
+
+Mailbox commands
+----------------
+
+* [3] Firmware update
+* [3] Health / Alerts
+* [1] :ref:`Background commands <background-commands>`
+* [3] Sanitization
+* [3] Security commands
+* [3] RAW Command Debug Passthrough
+* [0] CEL-only-validation Passthrough
+* [0] Switch CCI
+* [3] Timestamp
+* [1] PMEM labels
+* [0] PMEM GPF / Dirty Shutdown
+* [0] Scan Media
+
+PMU
+---
+* [1] Type 3 PMU
+* [0] Switch USP/ DSP, Root Port
+
+Security
+--------
+
+* [X] CXL Trusted Execution Environment Security Protocol (TSP)
+* [X] CXL IDE (subsumed by TSP)
+
+Memory-pooling
+--------------
+
+* [1] Hotplug of LDs (via PCI hotplug)
+* [0] Dynamic Capacity Device (DCD) Support
+
+Multi-host sharing
+------------------
+
+* [0] Hardware coherent shared memory
+* [0] Software managed coherency shared memory
+
+Multi-host memory
+-----------------
+
+* [0] Dynamic Capacity Device Support
+* [0] Sharing
+
+Accelerator
+-----------
+
+* [0] Accelerator memory enumeration HDM-D (CXL 1.1/2.0 Type-2)
+* [0] Accelerator memory enumeration HDM-DB (CXL 3.0 Type-2)
+* [0] CXL.cache 68b (CXL 2.0)
+* [0] CXL.cache 256b Cache IDs (CXL 3.0)
+
+User Flow Support
+-----------------
+
+* [0] HPA->DPA Address translation (need xormaps export solution)
+
+Details
+=======
+
+.. _extended-linear:
+
+* **Extended-linear memory-side cache**: An HMAT proposal to enumerate the presence of a
+  memory-side cache where the cache capacity extends the SRAT address
+  range capacity. `See the ECN
+  <https://lore.kernel.org/linux-cxl/6650e4f835a0e_195e294a8@dwillia2-mobl3.amr.corp.intel.com.notmuch/>`_
+  for more details:
+
+.. _rch-link-status:
+
+* **RCH Link Status**: RCH (Restricted CXL Host) topologies, end up
+  hiding some standard registers like PCIe Link Status / Capabilities in
+  the CXL RCRB (Root Complex Register Block).
+
+.. _background-commands:
+
+* **Background commands**: The CXL background command mechanism is
+  awkward as the single slot is monopolized potentially indefinitely by
+  various commands. A `cancel on conflict
+  <http://lore.kernel.org/r/66035c2e8ba17_770232948b@dwillia2-xfh.jf.intel.com.notmuch>`_
+  facility is needed to make sure the kernel can ensure forward progress
+  of priority commands.
diff --git a/Documentation/gpu/amdgpu/display/dcn-blocks.rst b/Documentation/gpu/amdgpu/display/dcn-blocks.rst
index a3fbd3e..5e34366 100644
--- a/Documentation/gpu/amdgpu/display/dcn-blocks.rst
+++ b/Documentation/gpu/amdgpu/display/dcn-blocks.rst
@@ -8,37 +8,22 @@
 DCHUBBUB
 --------
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :internal:
-
 HUBP
 ----
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :internal:
-
 DPP
 ---
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
    :internal:
 
 MPC
@@ -48,10 +33,8 @@
    :doc: overview
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
    :internal:
+   :no-identifiers: mpcc_blnd_cfg mpcc_alpha_blend_mode
 
 OPP
 ---
@@ -60,19 +43,13 @@
    :doc: overview
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
    :internal:
 
 DIO
 ---
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
-   :export:
-
-.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+.. kernel-doc:: drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
    :internal:
diff --git a/Documentation/gpu/amdgpu/display/display-manager.rst b/Documentation/gpu/amdgpu/display/display-manager.rst
index 67a811e..b269ff3 100644
--- a/Documentation/gpu/amdgpu/display/display-manager.rst
+++ b/Documentation/gpu/amdgpu/display/display-manager.rst
@@ -132,7 +132,7 @@
 (MPC), as follows:
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :functions: mpcc_blnd_cfg
+   :identifiers: mpcc_blnd_cfg
 
 Therefore, the blending configuration for a single MPCC instance on the MPC
 tree is defined by :c:type:`mpcc_blnd_cfg`, where
@@ -144,7 +144,7 @@
 :c:type:`MPCC_ALPHA_BLND_MODE`, as described below.
 
 .. kernel-doc:: drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
-   :functions: mpcc_alpha_blend_mode
+   :identifiers: mpcc_alpha_blend_mode
 
 DM then maps the elements of `enum mpcc_alpha_blend_mode` to those in the DRM
 blend formula, as follows:
diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
index bd033fe..e76b0cfc 100644
--- a/Documentation/networking/xsk-tx-metadata.rst
+++ b/Documentation/networking/xsk-tx-metadata.rst
@@ -11,12 +11,16 @@
 General Design
 ==============
 
-The headroom for the metadata is reserved via ``tx_metadata_len`` in
-``struct xdp_umem_reg``. The metadata length is therefore the same for
-every socket that shares the same umem. The metadata layout is a fixed UAPI,
-refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
-Thus, generally, the ``tx_metadata_len`` field above should contain
-``sizeof(union xsk_tx_metadata)``.
+The headroom for the metadata is reserved via ``tx_metadata_len`` and
+``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata
+length is therefore the same for every socket that shares the same umem.
+The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in
+``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len``
+field above should contain ``sizeof(union xsk_tx_metadata)``.
+
+Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN``
+flag was not required. Applications might attempt to create a umem
+with a flag first and if it fails, do another attempt without a flag.
 
 The headroom and the metadata itself should be located right before
 ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 1497e80f..3fc63f27 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -89,14 +89,7 @@
 Rust (optional)
 ---------------
 
-A particular version of the Rust toolchain is required. Newer versions may or
-may not work because the kernel depends on some unstable Rust features, for
-the moment.
-
-Each Rust toolchain comes with several "components", some of which are required
-(like ``rustc``) and some that are optional. The ``rust-src`` component (which
-is optional) needs to be installed to build the kernel. Other components are
-useful for developing.
+A recent version of the Rust compiler is required.
 
 Please see Documentation/rust/quick-start.rst for instructions on how to
 satisfy the build requirements of Rust support. In particular, the ``Makefile``
diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index b13e19d..750ff37 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -18,7 +18,7 @@
 ``arm64``      Maintained        Little Endian only.
 ``loongarch``  Maintained        \-
 ``riscv``      Maintained        ``riscv64`` only.
-``um``         Maintained        ``x86_64`` only.
+``um``         Maintained        \-
 ``x86``        Maintained        ``x86_64`` only.
 =============  ================  ==============================================
 
diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst
index 4bb6ac1..e3f388e 100644
--- a/Documentation/rust/general-information.rst
+++ b/Documentation/rust/general-information.rst
@@ -7,6 +7,14 @@
 the Rust support in the kernel.
 
 
+``no_std``
+----------
+
+The Rust support in the kernel can link only `core <https://doc.rust-lang.org/core/>`_,
+but not `std <https://doc.rust-lang.org/std/>`_. Crates for use in the
+kernel must opt into this behavior using the ``#![no_std]`` attribute.
+
+
 Code documentation
 ------------------
 
diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
index cc3f11e..d06a361 100644
--- a/Documentation/rust/quick-start.rst
+++ b/Documentation/rust/quick-start.rst
@@ -5,17 +5,93 @@
 
 This document describes how to get started with kernel development in Rust.
 
+There are a few ways to install a Rust toolchain needed for kernel development.
+A simple way is to use the packages from your Linux distribution if they are
+suitable -- the first section below explains this approach. An advantage of this
+approach is that, typically, the distribution will match the LLVM used by Rust
+and Clang.
+
+Another way is using the prebuilt stable versions of LLVM+Rust provided on
+`kernel.org <https://kernel.org/pub/tools/llvm/rust/>`_. These are the same slim
+and fast LLVM toolchains from :ref:`Getting LLVM <getting_llvm>` with versions
+of Rust added to them that Rust for Linux supports. Two sets are provided: the
+"latest LLVM" and "matching LLVM" (please see the link for more information).
+
+Alternatively, the next two "Requirements" sections explain each component and
+how to install them through ``rustup``, the standalone installers from Rust
+and/or building them.
+
+The rest of the document explains other aspects on how to get started.
+
+
+Distributions
+-------------
+
+Arch Linux
+**********
+
+Arch Linux provides recent Rust releases and thus it should generally work out
+of the box, e.g.::
+
+	pacman -S rust rust-src rust-bindgen
+
+
+Debian
+******
+
+Debian Unstable (Sid), outside of the freeze period, provides recent Rust
+releases and thus it should generally work out of the box, e.g.::
+
+	apt install rustc rust-src bindgen rustfmt rust-clippy
+
+
+Fedora Linux
+************
+
+Fedora Linux provides recent Rust releases and thus it should generally work out
+of the box, e.g.::
+
+	dnf install rust rust-src bindgen-cli rustfmt clippy
+
+
+Gentoo Linux
+************
+
+Gentoo Linux (and especially the testing branch) provides recent Rust releases
+and thus it should generally work out of the box, e.g.::
+
+	USE='rust-src rustfmt clippy' emerge dev-lang/rust dev-util/bindgen
+
+``LIBCLANG_PATH`` may need to be set.
+
+
+Nix
+***
+
+Nix (unstable channel) provides recent Rust releases and thus it should
+generally work out of the box, e.g.::
+
+	{ pkgs ? import <nixpkgs> {} }:
+	pkgs.mkShell {
+	  nativeBuildInputs = with pkgs; [ rustc rust-bindgen rustfmt clippy ];
+	  RUST_LIB_SRC = "${pkgs.rust.packages.stable.rustPlatform.rustLibSrc}";
+	}
+
+
+openSUSE
+********
+
+openSUSE Slowroll and openSUSE Tumbleweed provide recent Rust releases and thus
+they should generally work out of the box, e.g.::
+
+	zypper install rust rust1.79-src rust-bindgen clang
+
 
 Requirements: Building
 ----------------------
 
 This section explains how to fetch the tools needed for building.
 
-Some of these requirements might be available from Linux distributions
-under names like ``rustc``, ``rust-src``, ``rust-bindgen``, etc. However,
-at the time of writing, they are likely not to be recent enough unless
-the distribution tracks the latest releases.
-
 To easily check whether the requirements are met, the following target
 can be used::
 
@@ -29,16 +105,15 @@
 rustc
 *****
 
-A particular version of the Rust compiler is required. Newer versions may or
-may not work because, for the moment, the kernel depends on some unstable
-Rust features.
+A recent version of the Rust compiler is required.
 
 If ``rustup`` is being used, enter the kernel build directory (or use
-``--path=<build-dir>`` argument to the ``set`` sub-command) and run::
+``--path=<build-dir>`` argument to the ``set`` sub-command) and run,
+for instance::
 
-	rustup override set $(scripts/min-tool-version.sh rustc)
+	rustup override set stable
 
-This will configure your working directory to use the correct version of
+This will configure your working directory to use the given version of
 ``rustc`` without affecting your default toolchain.
 
 Note that the override applies to the current working directory (and its
@@ -65,9 +140,9 @@
 Otherwise, if a standalone installer is used, the Rust source tree may be
 downloaded into the toolchain's installation folder::
 
-	curl -L "https://static.rust-lang.org/dist/rust-src-$(scripts/min-tool-version.sh rustc).tar.gz" |
+	curl -L "https://static.rust-lang.org/dist/rust-src-$(rustc --version | cut -d' ' -f2).tar.gz" |
 		tar -xzf - -C "$(rustc --print sysroot)/lib" \
-		"rust-src-$(scripts/min-tool-version.sh rustc)/rust-src/lib/" \
+		"rust-src-$(rustc --version | cut -d' ' -f2)/rust-src/lib/" \
 		--strip-components=3
 
 In this case, upgrading the Rust compiler version later on requires manually
@@ -101,26 +176,22 @@
 *******
 
 The bindings to the C side of the kernel are generated at build time using
-the ``bindgen`` tool. A particular version is required.
+the ``bindgen`` tool.
 
-Install it via (note that this will download and build the tool from source)::
+Install it, for instance, via (note that this will download and build the tool
+from source)::
 
-	cargo install --locked --version $(scripts/min-tool-version.sh bindgen) bindgen-cli
+	cargo install --locked bindgen-cli
 
-``bindgen`` needs to find a suitable ``libclang`` in order to work. If it is
-not found (or a different ``libclang`` than the one found should be used),
-the process can be tweaked using the environment variables understood by
-``clang-sys`` (the Rust bindings crate that ``bindgen`` uses to access
-``libclang``):
+``bindgen`` uses the ``clang-sys`` crate to find a suitable ``libclang`` (which
+may be linked statically, dynamically or loaded at runtime). By default, the
+``cargo`` command above will produce a ``bindgen`` binary that will load
+``libclang`` at runtime. If it is not found (or a different ``libclang`` than
+the one found should be used), the process can be tweaked, e.g. by using the
+``LIBCLANG_PATH`` environment variable. For details, please see ``clang-sys``'s
+documentation at:
 
-* ``LLVM_CONFIG_PATH`` can be pointed to an ``llvm-config`` executable.
-
-* Or ``LIBCLANG_PATH`` can be pointed to a ``libclang`` shared library
-  or to the directory containing it.
-
-* Or ``CLANG_PATH`` can be pointed to a ``clang`` executable.
-
-For details, please see ``clang-sys``'s documentation at:
+	https://github.com/KyleMayes/clang-sys#linking
 
 	https://github.com/KyleMayes/clang-sys#environment-variables
 
@@ -164,20 +235,6 @@
 The standalone installers also come with ``clippy``.
 
 
-cargo
-*****
-
-``cargo`` is the Rust native build system. It is currently required to run
-the tests since it is used to build a custom standard library that contains
-the facilities provided by the custom ``alloc`` in the kernel. The tests can
-be run using the ``rusttest`` Make target.
-
-If ``rustup`` is being used, all the profiles already install the tool,
-thus nothing needs to be done.
-
-The standalone installers also come with ``cargo``.
-
-
 rustdoc
 *******
 
diff --git a/Documentation/rust/testing.rst b/Documentation/rust/testing.rst
index acfd0c2..568b71b 100644
--- a/Documentation/rust/testing.rst
+++ b/Documentation/rust/testing.rst
@@ -131,9 +131,8 @@
 
 	make LLVM=1 rusttest
 
-This requires the kernel ``.config`` and downloads external repositories. It
-runs the ``#[test]`` tests on the host (currently) and thus is fairly limited in
-what these tests can test.
+This requires the kernel ``.config``. It runs the ``#[test]`` tests on the host
+(currently) and thus is fairly limited in what these tests can test.
 
 The Kselftests
 --------------
diff --git a/Documentation/virt/uml/user_mode_linux_howto_v2.rst b/Documentation/virt/uml/user_mode_linux_howto_v2.rst
index d1cfe41..2794244 100644
--- a/Documentation/virt/uml/user_mode_linux_howto_v2.rst
+++ b/Documentation/virt/uml/user_mode_linux_howto_v2.rst
@@ -223,8 +223,6 @@
 +-----------+--------+------------------------------------+------------+
 | socket    | legacy | none                               | ~ 450Mbit  |
 +-----------+--------+------------------------------------+------------+
-| pcap      | legacy | rx only                            | ~ 450Mbit  |
-+-----------+--------+------------------------------------+------------+
 | ethertap  | legacy | obsolete                           | ~ 500Mbit  |
 +-----------+--------+------------------------------------+------------+
 | vde       | legacy | obsolete                           | ~ 500Mbit  |
diff --git a/MAINTAINERS b/MAINTAINERS
index 85fbbc2..42decde 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -702,6 +702,14 @@
 F:	Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
 F:	drivers/net/ethernet/mediatek/airoha_eth.c
 
+AIROHA PCIE PHY DRIVER
+M:	Lorenzo Bianconi <lorenzo@kernel.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/phy/airoha,en7581-pcie-phy.yaml
+F:	drivers/phy/phy-airoha-pcie-regs.h
+F:	drivers/phy/phy-airoha-pcie.c
+
 AIROHA SPI SNFI DRIVER
 M:	Lorenzo Bianconi <lorenzo@kernel.org>
 M:	Ray Liu <ray.liu@airoha.com>
@@ -2188,7 +2196,7 @@
 ARM/CORESIGHT FRAMEWORK AND DRIVERS
 M:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
-R:	James Clark <james.clark@arm.com>
+R:	James Clark <james.clark@linaro.org>
 L:	coresight@lists.linaro.org (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -3898,11 +3906,10 @@
 F:	net/bluetooth/
 
 BONDING DRIVER
-M:	Jay Vosburgh <j.vosburgh@gmail.com>
+M:	Jay Vosburgh <jv@jvosburgh.net>
 M:	Andy Gospodarek <andy@greyhouse.net>
 L:	netdev@vger.kernel.org
-S:	Supported
-W:	http://sourceforge.net/projects/bonding/
+S:	Maintained
 F:	Documentation/networking/bonding.rst
 F:	drivers/net/bonding/
 F:	include/net/bond*
@@ -3966,8 +3973,10 @@
 F:	drivers/net/ethernet/netronome/nfp/bpf/
 
 BPF JIT for POWERPC (32-BIT AND 64-BIT)
-M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
 M:	Michael Ellerman <mpe@ellerman.id.au>
+M:	Hari Bathini <hbathini@linux.ibm.com>
+M:	Christophe Leroy <christophe.leroy@csgroup.eu>
+R:	Naveen N Rao <naveen@kernel.org>
 L:	bpf@vger.kernel.org
 S:	Supported
 F:	arch/powerpc/net/
@@ -5604,6 +5613,7 @@
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-cxl@vger.kernel.org
 S:	Maintained
+F:	Documentation/driver-api/cxl
 F:	drivers/cxl/
 F:	include/linux/einj-cxl.h
 F:	include/linux/cxl-event.h
@@ -6842,6 +6852,7 @@
 F:	include/linux/kobj*
 F:	include/linux/property.h
 F:	lib/kobj*
+F:	rust/kernel/device.rs
 
 DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS)
 M:	Nishanth Menon <nm@ti.com>
@@ -8354,7 +8365,8 @@
 F:	fs/*binfmt_*.c
 F:	fs/Kconfig.binfmt
 F:	fs/exec.c
-F:	fs/exec_test.c
+F:	fs/tests/binfmt_*_kunit.c
+F:	fs/tests/exec_kunit.c
 F:	include/linux/binfmts.h
 F:	include/linux/elf.h
 F:	include/uapi/linux/binfmts.h
@@ -8707,10 +8719,12 @@
 FIRMWARE LOADER (request_firmware)
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Russ Weight <russ.weight@linux.dev>
+M:	Danilo Krummrich <dakr@redhat.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	Documentation/firmware_class/
 F:	drivers/base/firmware_loader/
+F:	rust/kernel/firmware.rs
 F:	include/linux/firmware.h
 
 FLEXTIMER FTM-QUADDEC DRIVER
@@ -10642,6 +10656,7 @@
 F:	Documentation/devicetree/bindings/i3c/
 F:	Documentation/driver-api/i3c
 F:	drivers/i3c/
+F:	include/dt-bindings/i3c/
 F:	include/linux/i3c/
 
 IBM Operation Panel Input Driver
@@ -12517,7 +12532,7 @@
 F:	scripts/Makefile.kmsan
 
 KPROBES
-M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M:	Naveen N Rao <naveen@kernel.org>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
@@ -12894,7 +12909,7 @@
 M:	Michael Ellerman <mpe@ellerman.id.au>
 R:	Nicholas Piggin <npiggin@gmail.com>
 R:	Christophe Leroy <christophe.leroy@csgroup.eu>
-R:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+R:	Naveen N Rao <naveen@kernel.org>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 W:	https://github.com/linuxppc/wiki/wiki
@@ -15750,6 +15765,12 @@
 F:	Documentation/devicetree/bindings/hwmon/nuvoton,nct6775.yaml
 F:	drivers/hwmon/nct6775-i2c.c
 
+NETCONSOLE
+M:	Breno Leitao <leitao@debian.org>
+S:	Maintained
+F:	Documentation/networking/netconsole.rst
+F:	drivers/net/netconsole.c
+
 NETDEVSIM
 M:	Jakub Kicinski <kuba@kernel.org>
 S:	Maintained
@@ -17875,7 +17896,7 @@
 PERFORMANCE EVENTS TOOLING ARM64
 R:	John Garry <john.g.garry@oracle.com>
 R:	Will Deacon <will@kernel.org>
-R:	James Clark <james.clark@arm.com>
+R:	James Clark <james.clark@linaro.org>
 R:	Mike Leach <mike.leach@linaro.org>
 R:	Leo Yan <leo.yan@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -19056,7 +19077,13 @@
 T:	git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git
 F:	Documentation/devicetree/bindings/rng/microsoft,vmgenid.yaml
 F:	drivers/char/random.c
+F:	include/linux/random.h
+F:	include/uapi/linux/random.h
 F:	drivers/virt/vmgenid.c
+F:	include/vdso/getrandom.h
+F:	lib/vdso/getrandom.c
+F:	arch/x86/entry/vdso/vgetrandom*
+F:	arch/x86/include/asm/vdso/getrandom*
 
 RAPIDIO SUBSYSTEM
 M:	Matt Porter <mporter@kernel.crashing.org>
@@ -21675,6 +21702,13 @@
 F:	Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-rx.yaml
 F:	drivers/phy/starfive/phy-jh7110-dphy-rx.c
 
+STARFIVE JH7110 DPHY TX DRIVER
+M:	Keith Zhao <keith.zhao@starfivetech.com>
+M:	Shengyang Chen <shengyang.chen@starfivetech.com>
+S:	Supported
+F:	Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml
+F:	drivers/phy/starfive/phy-jh7110-dphy-tx.c
+
 STARFIVE JH7110 MMC/SD/SDIO DRIVER
 M:	William Qiu <william.qiu@starfivetech.com>
 S:	Supported
@@ -21832,6 +21866,15 @@
 F:	Documentation/devicetree/bindings/sound/st,stm32-*.yaml
 F:	sound/soc/stm/
 
+STM32 DMA DRIVERS
+M:	Amélie Delaunay <amelie.delaunay@foss.st.com>
+L:	dmaengine@vger.kernel.org
+L:	linux-stm32@st-md-mailman.stormreply.com (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/arch/arm/stm32/stm32-dma-mdma-chaining.rst
+F:	Documentation/devicetree/bindings/dma/stm32/
+F:	drivers/dma/stm32/
+
 STM32 TIMER/LPTIMER DRIVERS
 M:	Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 S:	Maintained
diff --git a/Makefile b/Makefile
index 11e7438..2c02daf 100644
--- a/Makefile
+++ b/Makefile
@@ -445,17 +445,17 @@
 # host programs.
 export rust_common_flags := --edition=2021 \
 			    -Zbinary_dep_depinfo=y \
-			    -Dunsafe_op_in_unsafe_fn -Drust_2018_idioms \
-			    -Dunreachable_pub -Dnon_ascii_idents \
+			    -Dunsafe_op_in_unsafe_fn \
+			    -Dnon_ascii_idents \
+			    -Wrust_2018_idioms \
+			    -Wunreachable_pub \
 			    -Wmissing_docs \
-			    -Drustdoc::missing_crate_level_docs \
-			    -Dclippy::correctness -Dclippy::style \
-			    -Dclippy::suspicious -Dclippy::complexity \
-			    -Dclippy::perf \
-			    -Dclippy::let_unit_value -Dclippy::mut_mut \
-			    -Dclippy::needless_bitwise_bool \
-			    -Dclippy::needless_continue \
-			    -Dclippy::no_mangle_with_rust_abi \
+			    -Wrustdoc::missing_crate_level_docs \
+			    -Wclippy::all \
+			    -Wclippy::mut_mut \
+			    -Wclippy::needless_bitwise_bool \
+			    -Wclippy::needless_continue \
+			    -Wclippy::no_mangle_with_rust_abi \
 			    -Wclippy::dbg_macro
 
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) \
@@ -493,7 +493,6 @@
 RUSTFMT		= rustfmt
 CLIPPY_DRIVER	= clippy-driver
 BINDGEN		= bindgen
-CARGO		= cargo
 PAHOLE		= pahole
 RESOLVE_BTFIDS	= $(objtree)/tools/bpf/resolve_btfids/resolve_btfids
 LEX		= flex
@@ -559,7 +558,7 @@
 		    -Csymbol-mangling-version=v0 \
 		    -Crelocation-model=static \
 		    -Zfunction-sections=n \
-		    -Dclippy::float_arithmetic
+		    -Wclippy::float_arithmetic
 
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
@@ -587,7 +586,7 @@
 export RUSTC_BOOTSTRAP := 1
 
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC HOSTPKG_CONFIG
-export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN CARGO
+export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN
 export HOSTRUSTC KBUILD_HOSTRUSTFLAGS
 export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
@@ -1959,9 +1958,12 @@
 tags TAGS cscope gtags: FORCE
 	$(call cmd,tags)
 
-# IDE support targets
+# Generate rust-project.json (a file that describes the structure of non-Cargo
+# Rust projects) for rust-analyzer (an implementation of the Language Server
+# Protocol).
 PHONY += rust-analyzer
 rust-analyzer:
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
 	$(Q)$(MAKE) $(build)=rust $@
 
 # Script to generate missing namespace dependencies
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 6d0c9f7..06b0e5f 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -816,10 +816,10 @@ EXPORT_SYMBOL(locomo_frontlight_set);
  *	We model this as a regular bus type, and hang devices directly
  *	off this.
  */
-static int locomo_match(struct device *_dev, struct device_driver *_drv)
+static int locomo_match(struct device *_dev, const struct device_driver *_drv)
 {
 	struct locomo_dev *dev = LOCOMO_DEV(_dev);
-	struct locomo_driver *drv = LOCOMO_DRV(_drv);
+	const struct locomo_driver *drv = LOCOMO_DRV(_drv);
 
 	return dev->devid == drv->devid;
 }
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 1fbd736..550978d 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -1339,10 +1339,10 @@ EXPORT_SYMBOL_GPL(sa1111_get_irq);
  *	We model this as a regular bus type, and hang devices directly
  *	off this.
  */
-static int sa1111_match(struct device *_dev, struct device_driver *_drv)
+static int sa1111_match(struct device *_dev, const struct device_driver *_drv)
 {
 	struct sa1111_dev *dev = to_sa1111_device(_dev);
-	struct sa1111_driver *drv = SA1111_DRV(_drv);
+	const struct sa1111_driver *drv = SA1111_DRV(_drv);
 
 	return !!(dev->devid & drv->devid);
 }
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index 9fd9ad5..3190e1e 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -189,7 +189,7 @@ struct locomo_driver {
 	void (*remove)(struct locomo_dev *);
 };
 
-#define LOCOMO_DRV(_d)	container_of((_d), struct locomo_driver, drv)
+#define LOCOMO_DRV(_d)	container_of_const((_d), struct locomo_driver, drv)
 
 #define LOCOMO_DRIVER_NAME(_ldev) ((_ldev)->dev.driver->name)
 
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
index d8c6f8a..a815f39 100644
--- a/arch/arm/include/asm/hardware/sa1111.h
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -404,7 +404,7 @@ struct sa1111_driver {
 	void (*remove)(struct sa1111_dev *);
 };
 
-#define SA1111_DRV(_d)	container_of((_d), struct sa1111_driver, drv)
+#define SA1111_DRV(_d)	container_of_const((_d), struct sa1111_driver, drv)
 
 #define SA1111_DRIVER_NAME(_sadev) ((_sadev)->dev.driver->name)
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7fd70be..b3fc891f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -168,9 +168,9 @@
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
-	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
-	select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN
-	select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE)
+	select HAVE_ARCH_KASAN_VMALLOC
+	select HAVE_ARCH_KASAN_SW_TAGS
+	select HAVE_ARCH_KASAN_HW_TAGS if ARM64_MTE
 	# Some instrumentation may be unsound, hence EXPERT
 	select HAVE_ARCH_KCSAN if EXPERT
 	select HAVE_ARCH_KFENCE
@@ -211,8 +211,8 @@
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
-	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_RETVAL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \
 		HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI
@@ -1471,7 +1471,6 @@
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
 	select GENERIC_ARCH_NUMA
-	select ACPI_NUMA if ACPI
 	select OF_NUMA
 	select HAVE_SETUP_PER_CPU_AREA
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
@@ -2337,6 +2336,17 @@
 	  allow the kernel to be booted as an EFI application. This
 	  is only useful on systems that have UEFI firmware.
 
+config COMPRESSED_INSTALL
+	bool "Install compressed image by default"
+	help
+	  This makes the regular "make install" install the compressed
+	  image we built, not the legacy uncompressed one.
+
+	  You can check that a compressed image works for you by doing
+	  "make zinstall" first, and verifying that everything is fine
+	  in your environment before making "make install" do this for
+	  you.
+
 config DMI
 	bool "Enable support for SMBIOS (DMI) tables"
 	depends on EFI
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 3f0f35fd..f6bc3da 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -182,7 +182,13 @@
 Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-install: KBUILD_IMAGE := $(boot)/Image
+ifeq ($(CONFIG_COMPRESSED_INSTALL),y)
+ DEFAULT_KBUILD_IMAGE = $(KBUILD_IMAGE)
+else
+ DEFAULT_KBUILD_IMAGE = $(boot)/Image
+endif
+
+install: KBUILD_IMAGE := $(DEFAULT_KBUILD_IMAGE)
 install zinstall:
 	$(call cmd,install)
 
@@ -229,7 +235,7 @@
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
   echo  '  image.fit     - Flat Image Tree (arch/$(ARCH)/boot/image.fit)'
-  echo  '  install       - Install uncompressed kernel'
+  echo  '  install       - Install kernel (compressed if COMPRESSED_INSTALL set)'
   echo  '  zinstall      - Install compressed kernel'
   echo  '                  Install using (your) ~/bin/installkernel or'
   echo  '                  (distribution) /sbin/installkernel or'
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index f8efbc1..7a4f560 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1065,6 +1065,28 @@ static inline bool pgtable_l5_enabled(void) { return false; }
 
 #define p4d_offset_kimg(dir,addr)	((p4d_t *)dir)
 
+static inline
+p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr)
+{
+	/*
+	 * With runtime folding of the pud, pud_offset_lockless() passes
+	 * the 'pgd_t *' we return here to p4d_to_folded_pud(), which
+	 * will offset the pointer assuming that it points into
+	 * a page-table page. However, the fast GUP path passes us a
+	 * pgd_t allocated on the stack and so we must use the original
+	 * pointer in 'pgdp' to construct the p4d pointer instead of
+	 * using the generic p4d_offset_lockless() implementation.
+	 *
+	 * Note: reusing the original pointer means that we may
+	 * dereference the same (live) page-table entry multiple times.
+	 * This is safe because it is still only loaded once in the
+	 * context of each level and the CPU guarantees same-address
+	 * read-after-read ordering.
+	 */
+	return p4d_offset(pgdp, addr);
+}
+#define p4d_offset_lockless p4d_offset_lockless_folded
+
 #endif  /* CONFIG_PGTABLE_LEVELS > 4 */
 
 #define pgd_ERROR(e)	\
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index b776e74..e737c629 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -507,7 +507,7 @@ static int update_insn_emulation_mode(struct insn_emulation *insn,
 	return ret;
 }
 
-static int emulation_proc_handler(struct ctl_table *table, int write,
+static int emulation_proc_handler(const struct ctl_table *table, int write,
 				  void *buffer, size_t *lenp,
 				  loff_t *ppos)
 {
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 82e8a60..77006df 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -535,7 +535,7 @@ static unsigned int find_supported_vector_length(enum vec_type type,
 
 #if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
-static int vec_proc_do_default_vl(struct ctl_table *table, int write,
+static int vec_proc_do_default_vl(const struct ctl_table *table, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct vl_info *info = table->extra1;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d63930c..d11da64 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -21,7 +21,7 @@
 # potential future proofing if we end up with internal calls to the exported
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
-ldflags-y := -shared -soname=linux-vdso.so.1 --hash-style=sysv	\
+ldflags-y := -shared -soname=linux-vdso.so.1 \
 	     -Bsymbolic --build-id=sha1 -n $(btildflags-y)
 
 ifdef CONFIG_LD_ORPHAN_WARN
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index cc4508c..25a2cb6 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -98,7 +98,7 @@
 # From arm vDSO Makefile
 VDSO_LDFLAGS += -Bsymbolic --no-undefined -soname=linux-vdso.so.1
 VDSO_LDFLAGS += -z max-page-size=4096 -z common-page-size=4096
-VDSO_LDFLAGS += -shared --hash-style=sysv --build-id=sha1
+VDSO_LDFLAGS += -shared --build-id=sha1
 VDSO_LDFLAGS += --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
 
 
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index a4c1dd47..7ceaa1e 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -149,7 +149,7 @@
 UnsignedEnum	31:28	GIC
 	0b0000	NI
 	0b0001	GICv3
-	0b0010	GICv4p1
+	0b0011	GICv4p1
 EndEnum
 UnsignedEnum	27:24	Virt_frac
 	0b0000	NI
@@ -903,7 +903,7 @@
 UnsignedEnum	27:24	GIC
 	0b0000	NI
 	0b0001	IMP
-	0b0010	V4P1
+	0b0011	V4P1
 EndEnum
 SignedEnum	23:20	AdvSIMD
 	0b0000	IMP
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ebdb715..70f1692 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -476,7 +476,6 @@
 config NUMA
 	bool "NUMA Support"
 	select SMP
-	select ACPI_NUMA if ACPI
 	help
 	  Say Y to compile the kernel with NUMA (Non-Uniform Memory Access)
 	  support.  This option improves performance on systems with more
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f9d252b..60077e5 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -478,6 +478,7 @@
 	select BOARD_SCACHE
 	select CSRC_R4K
 	select CEVT_R4K
+	select SYNC_R4K
 	select FORCE_PCI
 	select ISA
 	select I8259
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index c2930a7..1e78227 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -240,6 +240,10 @@ GCR_ACCESSOR_RO(32, 0x0d0, gic_status)
 GCR_ACCESSOR_RO(32, 0x0f0, cpc_status)
 #define CM_GCR_CPC_STATUS_EX			BIT(0)
 
+/* GCR_ACCESS - Controls core/IOCU access to GCRs */
+GCR_ACCESSOR_RW(32, 0x120, access_cm3)
+#define CM_GCR_ACCESS_ACCESSEN			GENMASK(7, 0)
+
 /* GCR_L2_CONFIG - Indicates L2 cache configuration when Config5.L2C=1 */
 GCR_ACCESSOR_RW(32, 0x130, l2_config)
 #define CM_GCR_L2_CONFIG_BYPASS			BIT(20)
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index bc2c240..2427d76f 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -50,7 +50,6 @@ extern int __cpu_logical_map[NR_CPUS];
 #define SMP_CALL_FUNCTION	0x2
 /* Octeon - Tell another core to flush its icache */
 #define SMP_ICACHE_FLUSH	0x4
-#define SMP_ASK_C0COUNT		0x8
 
 /* Mask of CPUs which are currently definitely operating coherently */
 extern cpumask_t cpu_coherent_mask;
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 9cc087d..395622c 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -317,7 +317,10 @@ static void boot_core(unsigned int core, unsigned int vpe_id)
 	write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB);
 
 	/* Ensure the core can access the GCRs */
-	set_gcr_access(1 << core);
+	if (mips_cm_revision() < CM_REV_CM3)
+		set_gcr_access(1 << core);
+	else
+		set_gcr_access_cm3(1 << core);
 
 	if (mips_cpc_present()) {
 		/* Reset the core */
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index 66d049c..147acd9 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -33,7 +33,6 @@ static void __iomem *ipi_clear0_regs[16];
 static void __iomem *ipi_status0_regs[16];
 static void __iomem *ipi_en0_regs[16];
 static void __iomem *ipi_mailbox_buf[16];
-static uint32_t core0_c0count[NR_CPUS];
 
 static u32 (*ipi_read_clear)(int cpu);
 static void (*ipi_write_action)(int cpu, u32 action);
@@ -382,11 +381,10 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 		ipi_write_action(cpu_logical_map(i), (u32)action);
 }
 
-
 static irqreturn_t loongson3_ipi_interrupt(int irq, void *dev_id)
 {
-	int i, cpu = smp_processor_id();
-	unsigned int action, c0count;
+	int cpu = smp_processor_id();
+	unsigned int action;
 
 	action = ipi_read_clear(cpu);
 
@@ -399,26 +397,14 @@ static irqreturn_t loongson3_ipi_interrupt(int irq, void *dev_id)
 		irq_exit();
 	}
 
-	if (action & SMP_ASK_C0COUNT) {
-		BUG_ON(cpu != 0);
-		c0count = read_c0_count();
-		c0count = c0count ? c0count : 1;
-		for (i = 1; i < nr_cpu_ids; i++)
-			core0_c0count[i] = c0count;
-		nudge_writes(); /* Let others see the result ASAP */
-	}
-
 	return IRQ_HANDLED;
 }
 
-#define MAX_LOOPS 800
 /*
  * SMP init and finish on secondary CPUs
  */
 static void loongson3_init_secondary(void)
 {
-	int i;
-	uint32_t initcount;
 	unsigned int cpu = smp_processor_id();
 	unsigned int imask = STATUSF_IP7 | STATUSF_IP6 |
 			     STATUSF_IP3 | STATUSF_IP2;
@@ -432,23 +418,6 @@ static void loongson3_init_secondary(void)
 		     cpu_logical_map(cpu) % loongson_sysconf.cores_per_package);
 	cpu_data[cpu].package =
 		cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
-
-	i = 0;
-	core0_c0count[cpu] = 0;
-	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
-	while (!core0_c0count[cpu]) {
-		i++;
-		cpu_relax();
-	}
-
-	if (i > MAX_LOOPS)
-		i = MAX_LOOPS;
-	if (cpu_data[cpu].package)
-		initcount = core0_c0count[cpu] + i;
-	else /* Local access is faster for loops */
-		initcount = core0_c0count[cpu] + i/2;
-
-	write_c0_count(initcount);
 }
 
 static void loongson3_smp_finish(void)
diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c
index af53339..149a915 100644
--- a/arch/mips/sibyte/common/sb_tbprof.c
+++ b/arch/mips/sibyte/common/sb_tbprof.c
@@ -589,4 +589,5 @@ module_exit(sbprof_tb_cleanup);
 
 MODULE_ALIAS_CHARDEV_MAJOR(SBPROF_TB_MAJOR);
 MODULE_AUTHOR("Ralf Baechle <ralf@linux-mips.org>");
+MODULE_DESCRIPTION("Support for ZBbus profiling");
 MODULE_LICENSE("GPL");
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index dc9b902..5d650e0 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -46,6 +46,7 @@
 	select GENERIC_CPU_DEVICES if !SMP
 	select GENERIC_LIB_DEVMEM_IS_ALLOWED
 	select SYSCTL_ARCH_UNALIGN_ALLOW
+	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
@@ -86,6 +87,7 @@
 	select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS
 	select TRACE_IRQFLAGS_SUPPORT
 	select HAVE_FUNCTION_DESCRIPTORS if 64BIT
+	select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/parisc/include/asm/parisc-device.h b/arch/parisc/include/asm/parisc-device.h
index 7ddd7f4..9e74cef 100644
--- a/arch/parisc/include/asm/parisc-device.h
+++ b/arch/parisc/include/asm/parisc-device.h
@@ -41,7 +41,7 @@ struct parisc_driver {
 
 
 #define to_parisc_device(d)	container_of(d, struct parisc_device, dev)
-#define to_parisc_driver(d)	container_of(d, struct parisc_driver, drv)
+#define to_parisc_driver(d)	container_of_const(d, struct parisc_driver, drv)
 #define parisc_parent(d)	to_parisc_device(d->dev.parent)
 
 static inline const char *parisc_pathname(struct parisc_device *d)
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index 98851ff..a97c0fd 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -20,7 +20,7 @@
  * sysdeps/unix/sysv/linux/hppa/sysdep.h
  */
 
-#ifdef PIC
+#ifndef DONT_USE_PIC
 /* WARNING: CANNOT BE USED IN A NOP! */
 # define K_STW_ASM_PIC	"       copy %%r19, %%r4\n"
 # define K_LDW_ASM_PIC	"       copy %%r4, %%r19\n"
@@ -43,7 +43,7 @@
    across the syscall. */
 
 #define K_CALL_CLOB_REGS "%r1", "%r2", K_USING_GR4 \
-	        	 "%r20", "%r29", "%r31"
+			 "%r20", "%r29", "%r31"
 
 #undef K_INLINE_SYSCALL
 #define K_INLINE_SYSCALL(name, nr, args...)	({			\
@@ -58,7 +58,7 @@
 			"	ldi %1, %%r20\n"			\
 			K_LDW_ASM_PIC					\
 			: "=r" (__res)					\
-			: "i" (SYS_ify(name)) K_ASM_ARGS_##nr   	\
+			: "i" (name) K_ASM_ARGS_##nr			\
 			: "memory", K_CALL_CLOB_REGS K_CLOB_ARGS_##nr	\
 		);							\
 		__sys_res = (long)__res;				\
@@ -104,42 +104,18 @@
 #define K_CLOB_ARGS_1 K_CLOB_ARGS_2, "%r25"
 #define K_CLOB_ARGS_0 K_CLOB_ARGS_1, "%r26"
 
-#define _syscall0(type,name)						\
-type name(void)								\
-{									\
-    return K_INLINE_SYSCALL(name, 0);	                                \
-}
-
-#define _syscall1(type,name,type1,arg1)					\
-type name(type1 arg1)							\
-{									\
-    return K_INLINE_SYSCALL(name, 1, arg1);	                        \
-}
-
-#define _syscall2(type,name,type1,arg1,type2,arg2)			\
-type name(type1 arg1, type2 arg2)					\
-{									\
-    return K_INLINE_SYSCALL(name, 2, arg1, arg2);	                \
-}
-
-#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3)		\
-type name(type1 arg1, type2 arg2, type3 arg3)				\
-{									\
-    return K_INLINE_SYSCALL(name, 3, arg1, arg2, arg3);	                \
-}
-
-#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
-type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4)		\
-{									\
-    return K_INLINE_SYSCALL(name, 4, arg1, arg2, arg3, arg4);	        \
-}
-
-/* select takes 5 arguments */
-#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,type5,arg5) \
-type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
-{									\
-    return K_INLINE_SYSCALL(name, 5, arg1, arg2, arg3, arg4, arg5);	\
-}
+#define syscall0(name)						\
+	K_INLINE_SYSCALL(name, 0)
+#define syscall1(name, arg1)					\
+	K_INLINE_SYSCALL(name, 1, arg1)
+#define syscall2(name, arg1, arg2)				\
+	K_INLINE_SYSCALL(name, 2, arg1, arg2)
+#define syscall3(name, arg1, arg2, arg3)			\
+	K_INLINE_SYSCALL(name, 3, arg1, arg2, arg3)
+#define syscall4(name, arg1, arg2, arg3, arg4)			\
+	K_INLINE_SYSCALL(name, 4, arg1, arg2, arg3, arg4)
+#define syscall5(name, arg1, arg2, arg3, arg4, arg5)		\
+	K_INLINE_SYSCALL(name, 5, arg1, arg2, arg3, arg4, arg5)
 
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/parisc/include/asm/vdso.h b/arch/parisc/include/asm/vdso.h
index ef82061..2a2dc11 100644
--- a/arch/parisc/include/asm/vdso.h
+++ b/arch/parisc/include/asm/vdso.h
@@ -19,6 +19,6 @@ extern struct vdso_data *vdso_data;
 /* Default link addresses for the vDSOs */
 #define VDSO_LBASE	0
 
-#define VDSO_VERSION_STRING	LINUX_5.18
+#define VDSO_VERSION_STRING	LINUX_6.11
 
 #endif /* __PARISC_VDSO_H__ */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 483bfaf..db531e5 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -611,11 +611,7 @@ void __init parisc_setup_cache_timing(void)
 		threshold/1024);
 
 set_tlb_threshold:
-	if (threshold > FLUSH_TLB_THRESHOLD)
-		parisc_tlb_flush_threshold = threshold;
-	else
-		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
-
+	parisc_tlb_flush_threshold = max(threshold, FLUSH_TLB_THRESHOLD);
 	printk(KERN_INFO "TLB flush threshold set to %lu KiB\n",
 		parisc_tlb_flush_threshold/1024);
 }
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index ac19d68..1e793f7 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -97,7 +97,7 @@ static int for_each_padev(int (*fn)(struct device *, void *), void * data)
  * @driver: the PA-RISC driver to try
  * @dev: the PA-RISC device to try
  */
-static int match_device(struct parisc_driver *driver, struct parisc_device *dev)
+static int match_device(const struct parisc_driver *driver, struct parisc_device *dev)
 {
 	const struct parisc_device_id *ids;
 
@@ -548,7 +548,7 @@ alloc_pa_dev(unsigned long hpa, struct hardware_path *mod_path)
 	return dev;
 }
 
-static int parisc_generic_match(struct device *dev, struct device_driver *drv)
+static int parisc_generic_match(struct device *dev, const struct device_driver *drv)
 {
 	return match_device(to_parisc_driver(drv), to_parisc_device(dev));
 }
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 71e596c..3e79e40 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -104,6 +104,7 @@
 #define ERR_NOTHANDLED	-1
 
 int unaligned_enabled __read_mostly = 1;
+int no_unaligned_warning __read_mostly;
 
 static int emulate_ldh(struct pt_regs *regs, int toreg)
 {
@@ -399,6 +400,7 @@ void handle_unaligned(struct pt_regs *regs)
 	} else {
 		static DEFINE_RATELIMIT_STATE(kernel_ratelimit, 5 * HZ, 5);
 		if (!(current->thread.flags & PARISC_UAC_NOPRINT) &&
+			!no_unaligned_warning &&
 			__ratelimit(&kernel_ratelimit))
 			pr_warn("Kernel: unaligned access to " RFMT " in %pS "
 					"(iir " RFMT ")\n",
diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile
index 1350d50..2b36d25 100644
--- a/arch/parisc/kernel/vdso32/Makefile
+++ b/arch/parisc/kernel/vdso32/Makefile
@@ -1,11 +1,25 @@
-# List of files in the vdso, has to be asm only for now
+# Include the generic Makefile to check the built vdso.
+include $(srctree)/lib/vdso/Makefile
+
+KCOV_INSTRUMENT := n
+
+# Disable gcov profiling, ubsan and kasan for VDSO code
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
 
 obj-vdso32 = note.o sigtramp.o restart_syscall.o
+obj-cvdso32 = vdso32_generic.o
 
 # Build rules
 
-targets := $(obj-vdso32) vdso32.so
+targets := $(obj-vdso32) $(obj-cvdso32) vdso32.so
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
+obj-cvdso32 := $(addprefix $(obj)/, $(obj-cvdso32))
+
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_vdso32_generic.o = $(VDSO_CFLAGS_REMOVE)
 
 ccflags-y := -shared -fno-common -fbuiltin -mno-fast-indirect-calls -O2 -mno-long-calls
 #  -march=1.1 -mschedule=7100LC
@@ -26,18 +40,22 @@
 
 # Force dependency (incbin is bad)
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so: $(obj)/vdso32.lds $(obj-vdso32) $(VDSO_LIBGCC) FORCE
+$(obj)/vdso32.so: $(obj)/vdso32.lds $(obj-vdso32) $(obj-cvdso32) $(VDSO_LIBGCC) FORCE
 	$(call if_changed,vdso32ld)
 
 # assembly rules for the .S files
 $(obj-vdso32): %.o: %.S FORCE
 	$(call if_changed_dep,vdso32as)
+$(obj-cvdso32): %.o: %.c FORCE
+	$(call if_changed_dep,vdso32cc)
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
       cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $(filter-out FORCE, $^) -o $@
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $<
+quiet_cmd_vdso32cc = VDSO32C $@
+      cmd_vdso32cc = $(CROSS32CC) $(c_flags) -c -o $@ $<
 
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(src)/gen_vdso_offsets.sh
diff --git a/arch/parisc/kernel/vdso32/vdso32.lds.S b/arch/parisc/kernel/vdso32/vdso32.lds.S
index d4aff3a..4273baa 100644
--- a/arch/parisc/kernel/vdso32/vdso32.lds.S
+++ b/arch/parisc/kernel/vdso32/vdso32.lds.S
@@ -106,6 +106,9 @@
     global:
 	__kernel_sigtramp_rt32;
 	__kernel_restart_syscall32;
+	__vdso_gettimeofday;
+	__vdso_clock_gettime;
+	__vdso_clock_gettime64;
     local: *;
   };
 }
diff --git a/arch/parisc/kernel/vdso32/vdso32_generic.c b/arch/parisc/kernel/vdso32/vdso32_generic.c
new file mode 100644
index 0000000..8d5bd59
--- /dev/null
+++ b/arch/parisc/kernel/vdso32/vdso32_generic.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "asm/unistd.h"
+#include <linux/types.h>
+#include <uapi/asm/unistd_32.h>
+
+struct timezone;
+struct old_timespec32;
+struct __kernel_timespec;
+struct __kernel_old_timeval;
+
+/* forward declarations */
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
+
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			struct timezone *tz)
+{
+	return syscall2(__NR_gettimeofday, (long)tv, (long)tz);
+}
+
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
+{
+	return syscall2(__NR_clock_gettime, (long)clock, (long)ts);
+}
+
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return syscall2(__NR_clock_gettime64, (long)clock, (long)ts);
+}
diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile
index 0b1c1cc..bd87bd6 100644
--- a/arch/parisc/kernel/vdso64/Makefile
+++ b/arch/parisc/kernel/vdso64/Makefile
@@ -1,12 +1,25 @@
-# List of files in the vdso, has to be asm only for now
+# Include the generic Makefile to check the built vdso.
+include $(srctree)/lib/vdso/Makefile
+
+KCOV_INSTRUMENT := n
+
+# Disable gcov profiling, ubsan and kasan for VDSO code
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
 
 obj-vdso64 = note.o sigtramp.o restart_syscall.o
+obj-cvdso64 = vdso64_generic.o
 
 # Build rules
 
-targets := $(obj-vdso64) vdso64.so
-obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
+targets := $(obj-vdso64) $(obj-cvdso64) vdso64.so
+obj-vdso64  := $(addprefix $(obj)/, $(obj-vdso64))
+obj-cvdso64 := $(addprefix $(obj)/, $(obj-cvdso64))
 
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE)
 
 ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
@@ -26,18 +39,22 @@
 
 # Force dependency (incbin is bad)
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so: $(obj)/vdso64.lds $(obj-vdso64) $(VDSO_LIBGCC) FORCE
+$(obj)/vdso64.so: $(obj)/vdso64.lds $(obj-vdso64) $(obj-cvdso64) $(VDSO_LIBGCC) FORCE
 	$(call if_changed,vdso64ld)
 
 # assembly rules for the .S files
 $(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
+$(obj-cvdso64): %.o: %.c FORCE
+	$(call if_changed_dep,vdso64cc)
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
       cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter-out FORCE, $^) -o $@
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
+quiet_cmd_vdso64cc = VDSO64C $@
+      cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $<
 
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(src)/gen_vdso_offsets.sh
diff --git a/arch/parisc/kernel/vdso64/vdso64.lds.S b/arch/parisc/kernel/vdso64/vdso64.lds.S
index de1fb4b..10f25e4 100644
--- a/arch/parisc/kernel/vdso64/vdso64.lds.S
+++ b/arch/parisc/kernel/vdso64/vdso64.lds.S
@@ -104,6 +104,8 @@
     global:
 	__kernel_sigtramp_rt64;
 	__kernel_restart_syscall64;
+	__vdso_gettimeofday;
+	__vdso_clock_gettime;
     local: *;
   };
 }
diff --git a/arch/parisc/kernel/vdso64/vdso64_generic.c b/arch/parisc/kernel/vdso64/vdso64_generic.c
new file mode 100644
index 0000000..fc6836a
--- /dev/null
+++ b/arch/parisc/kernel/vdso64/vdso64_generic.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "asm/unistd.h"
+#include <linux/types.h>
+
+struct timezone;
+struct __kernel_timespec;
+struct __kernel_old_timeval;
+
+/* forward declarations */
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			struct timezone *tz)
+{
+	return syscall2(__NR_gettimeofday, (long)tv, (long)tz);
+}
+
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return syscall2(__NR_clock_gettime, (long)clock, (long)ts);
+}
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index d13d8fd..987e23a 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -390,11 +390,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev);
 int ps3_system_bus_driver_register(struct ps3_system_bus_driver *drv);
 void ps3_system_bus_driver_unregister(struct ps3_system_bus_driver *drv);
 
-static inline struct ps3_system_bus_driver *ps3_drv_to_system_bus_drv(
-	struct device_driver *_drv)
-{
-	return container_of(_drv, struct ps3_system_bus_driver, core);
-}
+#define ps3_drv_to_system_bus_drv(_drv) container_of_const(_drv, struct ps3_system_bus_driver, core)
 static inline struct ps3_system_bus_device *ps3_dev_to_system_bus_dev(
 	const struct device *_dev)
 {
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 6faf2a9..7c44415 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -156,11 +156,7 @@ static inline int vio_enable_interrupts(struct vio_dev *dev)
 }
 #endif
 
-static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct vio_driver, driver);
-}
-
+#define to_vio_driver(__drv)	container_of_const(__drv, struct vio_driver, driver)
 #define to_vio_dev(__dev)	container_of_const(__dev, struct vio_dev, dev)
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 961aadc..5e6c7b5 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1984,8 +1984,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 			break;
 
 		r = -ENXIO;
-		if (!xive_enabled())
+		if (!xive_enabled()) {
+			fdput(f);
 			break;
+		}
 
 		r = -EPERM;
 		dev = kvm_device_from_filp(f.file);
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 56dc6b2..b9a7d9b 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -333,10 +333,10 @@ int ps3_mmio_region_init(struct ps3_system_bus_device *dev,
 EXPORT_SYMBOL_GPL(ps3_mmio_region_init);
 
 static int ps3_system_bus_match(struct device *_dev,
-	struct device_driver *_drv)
+	const struct device_driver *_drv)
 {
 	int result;
-	struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
+	const struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 
 	if (!dev->match_sub_id)
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index b401282..3436b0a 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -339,7 +339,7 @@ static struct attribute *ibmbus_bus_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ibmbus_bus);
 
-static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
+static int ibmebus_bus_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct of_device_id *matches = drv->of_match_table;
 
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 36d1c7d..ac1d2d2 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1576,10 +1576,10 @@ void vio_unregister_device(struct vio_dev *viodev)
 }
 EXPORT_SYMBOL(vio_unregister_device);
 
-static int vio_bus_match(struct device *dev, struct device_driver *drv)
+static int vio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct vio_dev *vio_dev = to_vio_dev(dev);
-	struct vio_driver *vio_drv = to_vio_driver(drv);
+	const struct vio_driver *vio_drv = to_vio_driver(drv);
 	const struct vio_device_id *ids = vio_drv->id_table;
 
 	return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
@@ -1689,7 +1689,7 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
 	/* construct the kobject name from the device node */
 	if (of_node_is_type(vnode_parent, "vdevice")) {
 		const __be32 *prop;
-		
+
 		prop = of_get_property(vnode, "reg", NULL);
 		if (!prop)
 			goto out;
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 517b963..a0934b5 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -559,9 +559,7 @@ bool __init xive_native_init(void)
 	struct device_node *np;
 	struct resource r;
 	void __iomem *tima;
-	struct property *prop;
 	u8 max_prio = 7;
-	const __be32 *p;
 	u32 val, cpu;
 	s64 rc;
 
@@ -592,7 +590,7 @@ bool __init xive_native_init(void)
 		max_prio = val - 1;
 
 	/* Iterate the EQ sizes and pick one */
-	of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, p, val) {
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
 		xive_queue_shift = val;
 		if (val == PAGE_SHIFT)
 			break;
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index e454192..f2fa985 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -814,7 +814,6 @@ bool __init xive_spapr_init(void)
 	struct device_node *np;
 	struct resource r;
 	void __iomem *tima;
-	struct property *prop;
 	u8 max_prio;
 	u32 val;
 	u32 len;
@@ -866,7 +865,7 @@ bool __init xive_spapr_init(void)
 	}
 
 	/* Iterate the EQ sizes and pick one */
-	of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) {
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
 		xive_queue_shift = val;
 		if (val == PAGE_SHIFT)
 			break;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 3ceec2c..0f3cd7c 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -13,7 +13,9 @@
 config RISCV
 	def_bool y
 	select ACPI_GENERIC_GSI if ACPI
+	select ACPI_PPTT if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
+	select ACPI_SPCR_TABLE if ACPI
 	select ARCH_DMA_DEFAULT_COHERENT
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP
@@ -123,6 +125,7 @@
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
@@ -154,7 +157,6 @@
 	select HAVE_KERNEL_UNCOMPRESSED if !XIP_KERNEL && !EFI_ZBOOT
 	select HAVE_KERNEL_ZSTD if !XIP_KERNEL && !EFI_ZBOOT
 	select HAVE_KPROBES if !XIP_KERNEL
-	select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL
 	select HAVE_KRETPROBES if !XIP_KERNEL
 	# https://github.com/ClangBuiltLinux/linux/issues/1881
 	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD
@@ -820,6 +822,8 @@
 
 endchoice
 
+source "arch/riscv/Kconfig.vendor"
+
 endmenu # "Platform type"
 
 menu "Kernel features"
diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor
new file mode 100644
index 0000000..6f1cdd3
--- /dev/null
+++ b/arch/riscv/Kconfig.vendor
@@ -0,0 +1,19 @@
+menu "Vendor extensions"
+
+config RISCV_ISA_VENDOR_EXT
+	bool
+
+menu "Andes"
+config RISCV_ISA_VENDOR_EXT_ANDES
+	bool "Andes vendor extension support"
+	select RISCV_ISA_VENDOR_EXT
+	default y
+	help
+	  Say N here if you want to disable all Andes vendor extension
+	  support. This will cause any Andes vendor extensions that are
+	  requested by hardware probing to be ignored.
+
+	  If you don't know what to do here, say Y.
+endmenu
+
+endmenu
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
index 869c034..4e9e7a2 100644
--- a/arch/riscv/boot/Makefile
+++ b/arch/riscv/boot/Makefile
@@ -18,7 +18,6 @@
 OBJCOPYFLAGS_loader.bin :=-O binary
 OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-targets := Image Image.* loader loader.o loader.lds loader.bin
 targets := Image Image.* loader loader.o loader.lds loader.bin xipImage
 
 ifeq ($(CONFIG_XIP_KERNEL),y)
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 3f1f0558..0d67832 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -7,6 +7,7 @@
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
 CONFIG_MEMCG=y
+CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
@@ -35,9 +36,6 @@
 CONFIG_ARCH_VIRT=y
 CONFIG_ARCH_CANAAN=y
 CONFIG_SMP=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PM=y
-CONFIG_CPU_IDLE=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
@@ -52,13 +50,11 @@
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
-CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_BLK_DEV_THROTTLING=y
+CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_NET=y
 CONFIG_PACKET=y
-CONFIG_UNIX=y
 CONFIG_XFRM_USER=m
-CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_PNP=y
@@ -102,9 +98,9 @@
 CONFIG_NET_CLS_CGROUP=m
 CONFIG_NETLINK_DIAG=y
 CONFIG_CGROUP_NET_PRIO=y
+CONFIG_CAN=m
 CONFIG_NET_9P=y
 CONFIG_NET_9P_VIRTIO=y
-CONFIG_CAN=m
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_HOST_GENERIC=y
@@ -153,8 +149,8 @@
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_SERIAL_SH_SCI=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
@@ -179,7 +175,6 @@
 CONFIG_RZG2L_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
-CONFIG_RENESAS_RZG2LWDT=y
 CONFIG_MFD_AXP20X_I2C=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
@@ -193,11 +188,9 @@
 CONFIG_DRM_SUN4I=m
 CONFIG_DRM_VIRTIO_GPU=m
 CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SOC=y
-CONFIG_SND_SOC_RZ=m
 CONFIG_SND_DESIGNWARE_I2S=m
 CONFIG_SND_SOC_STARFIVE=m
 CONFIG_SND_SOC_JH7110_PWMDAC=m
@@ -239,34 +232,31 @@
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
-CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SDHCI_OF_DWCMSHC=y
+CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SPI=y
+CONFIG_MMC_SDHI=y
 CONFIG_MMC_DW=y
 CONFIG_MMC_DW_STARFIVE=y
-CONFIG_MMC_SDHI=y
 CONFIG_MMC_SUNXI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_SUN6I=y
 CONFIG_DMADEVICES=y
 CONFIG_DMA_SUN6I=m
 CONFIG_DW_AXI_DMAC=y
-CONFIG_RZ_DMAC=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VIRTIO_MMIO=y
-CONFIG_RENESAS_OSTM=y
 CONFIG_CLK_SOPHGO_CV1800=y
 CONFIG_SUN8I_DE2_CCU=m
+CONFIG_RENESAS_OSTM=y
 CONFIG_SUN50I_IOMMU=y
 CONFIG_RPMSG_CHAR=y
 CONFIG_RPMSG_CTRL=y
 CONFIG_RPMSG_VIRTIO=y
-CONFIG_ARCH_R9A07G043=y
+CONFIG_PM_DEVFREQ=y
 CONFIG_IIO=y
-CONFIG_RZG2L_ADC=m
-CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_PHY_SUN4I_USB=m
 CONFIG_PHY_RCAR_GEN3_USB2=y
 CONFIG_PHY_STARFIVE_JH7110_DPHY_RX=m
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
index f2708a9..fc1a34f 100644
--- a/arch/riscv/errata/andes/errata.c
+++ b/arch/riscv/errata/andes/errata.c
@@ -17,6 +17,7 @@
 #include <asm/processor.h>
 #include <asm/sbi.h>
 #include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
 
 #define ANDES_AX45MP_MARCHID		0x8000000000008a45UL
 #define ANDES_AX45MP_MIMPID		0x500UL
@@ -65,6 +66,8 @@ void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct al
 					      unsigned long archid, unsigned long impid,
 					      unsigned int stage)
 {
+	BUILD_BUG_ON(ERRATA_ANDES_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
 	if (stage == RISCV_ALTERNATIVES_BOOT)
 		errata_probe_iocp(stage, archid, impid);
 
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
index 716cfed..cea3b96 100644
--- a/arch/riscv/errata/sifive/errata.c
+++ b/arch/riscv/errata/sifive/errata.c
@@ -12,6 +12,7 @@
 #include <asm/alternative.h>
 #include <asm/vendorid_list.h>
 #include <asm/errata_list.h>
+#include <asm/vendor_extensions.h>
 
 struct errata_info_t {
 	char name[32];
@@ -96,6 +97,8 @@ void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 	u32 cpu_apply_errata = 0;
 	u32 tmp;
 
+	BUILD_BUG_ON(ERRATA_SIFIVE_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		return;
 
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index bf6a0a6..f5120e0 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -18,6 +18,7 @@
 #include <asm/io.h>
 #include <asm/patch.h>
 #include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
 
 #define CSR_TH_SXSTATUS		0x5c0
 #define SXSTATUS_MAEE		_AC(0x200000, UL)
@@ -166,6 +167,8 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 	u32 tmp;
 	void *oldptr, *altptr;
 
+	BUILD_BUG_ON(ERRATA_THEAD_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != THEAD_VENDOR_ID)
 			continue;
diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h
index 7dad0cf..e0a1f84 100644
--- a/arch/riscv/include/asm/acpi.h
+++ b/arch/riscv/include/asm/acpi.h
@@ -61,11 +61,14 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 
 void acpi_init_rintc_map(void);
 struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu);
-u32 get_acpi_id_for_cpu(int cpu);
+static inline u32 get_acpi_id_for_cpu(int cpu)
+{
+	return acpi_cpu_get_madt_rintc(cpu)->uid;
+}
+
 int acpi_get_riscv_isa(struct acpi_table_header *table,
 		       unsigned int cpu, const char **isa);
 
-static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
 void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
 			     u32 *cboz_size, u32 *cbop_size);
 #else
@@ -87,4 +90,12 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
 
 #endif /* CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI_NUMA
+int acpi_numa_get_nid(unsigned int cpu);
+void acpi_map_cpus_to_nodes(void);
+#else
+static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+static inline void acpi_map_cpus_to_nodes(void) { }
+#endif /* CONFIG_ACPI_NUMA */
+
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 880606b..71af9ec 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -170,7 +170,7 @@ static __always_inline int variable_fls(unsigned int x)
 ({								\
 	typeof(x) x_ = (x);					\
 	__builtin_constant_p(x_) ?				\
-	 (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0)	\
+	 ((x_ != 0) ? (32 - __builtin_clz(x_)) : 0)		\
 	 :							\
 	 variable_fls(x_);					\
 })
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 000796c..45f9c11 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -33,6 +33,31 @@ extern struct riscv_isainfo hart_isa[NR_CPUS];
 
 void riscv_user_isa_enable(void);
 
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
+	.name = #_name,									\
+	.property = #_name,								\
+	.id = _id,									\
+	.subset_ext_ids = _subset_exts,							\
+	.subset_ext_size = _subset_exts_size,						\
+	.validate = _validate								\
+}
+
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, NULL)
+
+#define __RISCV_ISA_EXT_DATA_VALIDATE(_name, _id, _validate) \
+			_RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, _validate)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
+			    ARRAY_SIZE(_bundled_exts), NULL)
+
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), NULL)
+#define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
+
 #if defined(CONFIG_RISCV_MISALIGNED)
 bool check_unaligned_access_emulated_all_cpus(void);
 void unaligned_emulation_finish(void);
@@ -79,59 +104,66 @@ extern bool riscv_isa_fallback;
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
 
+#define STANDARD_EXT		0
+
 bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
 #define riscv_isa_extension_available(isa_bitmap, ext)	\
 	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
 
-static __always_inline bool
-riscv_has_extension_likely(const unsigned long ext)
+static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
+							 const unsigned long ext)
 {
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm goto(
-		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_no);
-	} else {
-		if (!__riscv_isa_extension_available(NULL, ext))
-			goto l_no;
-	}
+	asm goto(ALTERNATIVE("j	%l[l_no]", "nop", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_no);
 
 	return true;
 l_no:
 	return false;
 }
 
-static __always_inline bool
-riscv_has_extension_unlikely(const unsigned long ext)
+static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
+							   const unsigned long ext)
 {
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm goto(
-		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_yes);
-	} else {
-		if (__riscv_isa_extension_available(NULL, ext))
-			goto l_yes;
-	}
+	asm goto(ALTERNATIVE("nop", "j	%l[l_yes]", %[vendor], %[ext], 1)
+	:
+	: [vendor] "i" (vendor), [ext] "i" (ext)
+	:
+	: l_yes);
 
 	return false;
 l_yes:
 	return true;
 }
 
+static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
+static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_likely(STANDARD_EXT, ext);
+
+	return __riscv_isa_extension_available(NULL, ext);
+}
+
 static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
 {
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+	    __riscv_has_extension_likely(STANDARD_EXT, ext))
 		return true;
 
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
@@ -139,7 +171,10 @@ static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsign
 
 static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
 {
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+	    __riscv_has_extension_unlikely(STANDARD_EXT, ext))
 		return true;
 
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index b18b202..5a0bd27 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -80,19 +80,18 @@
 #define RISCV_ISA_EXT_ZFA		71
 #define RISCV_ISA_EXT_ZTSO		72
 #define RISCV_ISA_EXT_ZACAS		73
-#define RISCV_ISA_EXT_XANDESPMU		74
-#define RISCV_ISA_EXT_ZVE32X		75
-#define RISCV_ISA_EXT_ZVE32F		76
-#define RISCV_ISA_EXT_ZVE64X		77
-#define RISCV_ISA_EXT_ZVE64F		78
-#define RISCV_ISA_EXT_ZVE64D		79
-#define RISCV_ISA_EXT_ZIMOP		80
-#define RISCV_ISA_EXT_ZCA		81
-#define RISCV_ISA_EXT_ZCB		82
-#define RISCV_ISA_EXT_ZCD		83
-#define RISCV_ISA_EXT_ZCF		84
-#define RISCV_ISA_EXT_ZCMOP		85
-#define RISCV_ISA_EXT_ZAWRS		86
+#define RISCV_ISA_EXT_ZVE32X		74
+#define RISCV_ISA_EXT_ZVE32F		75
+#define RISCV_ISA_EXT_ZVE64X		76
+#define RISCV_ISA_EXT_ZVE64F		77
+#define RISCV_ISA_EXT_ZVE64D		78
+#define RISCV_ISA_EXT_ZIMOP		79
+#define RISCV_ISA_EXT_ZCA		80
+#define RISCV_ISA_EXT_ZCB		81
+#define RISCV_ISA_EXT_ZCD		82
+#define RISCV_ISA_EXT_ZCF		83
+#define RISCV_ISA_EXT_ZCMOP		84
+#define RISCV_ISA_EXT_ZAWRS		85
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 150a987..ef01c18 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 7
+#define RISCV_HWPROBE_MAX_KEY 8
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 235fd45..7ede211 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -37,7 +37,7 @@
  * define the PAGE_OFFSET value for SV48 and SV39.
  */
 #define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
-#define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)
+#define PAGE_OFFSET_L3		_AC(0xffffffd600000000, UL)
 #else
 #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 #endif /* CONFIG_64BIT */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 5d47334..fca5c6b 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -10,6 +10,7 @@
 
 #include <asm/page.h>
 #include <linux/const.h>
+#include <linux/sizes.h>
 
 /* thread information allocation */
 #define THREAD_SIZE_ORDER	CONFIG_THREAD_SIZE_ORDER
diff --git a/arch/riscv/include/asm/vendor_extensions.h b/arch/riscv/include/asm/vendor_extensions.h
new file mode 100644
index 0000000..7437304
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_VENDOR_EXTENSIONS_H
+#define _ASM_VENDOR_EXTENSIONS_H
+
+#include <asm/cpufeature.h>
+
+#include <linux/array_size.h>
+#include <linux/types.h>
+
+/*
+ * The extension keys of each vendor must be strictly less than this value.
+ */
+#define RISCV_ISA_VENDOR_EXT_MAX 32
+
+struct riscv_isavendorinfo {
+	DECLARE_BITMAP(isa, RISCV_ISA_VENDOR_EXT_MAX);
+};
+
+struct riscv_isa_vendor_ext_data_list {
+	bool is_initialized;
+	const size_t ext_data_count;
+	const struct riscv_isa_ext_data *ext_data;
+	struct riscv_isavendorinfo per_hart_isa_bitmap[NR_CPUS];
+	struct riscv_isavendorinfo all_harts_isa_bitmap;
+};
+
+extern struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[];
+
+extern const size_t riscv_isa_vendor_ext_list_size;
+
+/*
+ * The alternatives need some way of distinguishing between vendor extensions
+ * and errata. Incrementing all of the vendor extension keys so they are at
+ * least 0x8000 accomplishes that.
+ */
+#define RISCV_VENDOR_EXT_ALTERNATIVES_BASE	0x8000
+
+#define VENDOR_EXT_ALL_CPUS			-1
+
+bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsigned int bit);
+#define riscv_cpu_isa_vendor_extension_available(cpu, vendor, ext)	\
+	__riscv_isa_vendor_extension_available(cpu, vendor, RISCV_ISA_VENDOR_EXT_##ext)
+#define riscv_isa_vendor_extension_available(vendor, ext)	\
+	__riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, \
+					       RISCV_ISA_VENDOR_EXT_##ext)
+
+static __always_inline bool riscv_has_vendor_extension_likely(const unsigned long vendor,
+							      const unsigned long ext)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return false;
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_likely(vendor,
+						    ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
+	return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext);
+}
+
+static __always_inline bool riscv_has_vendor_extension_unlikely(const unsigned long vendor,
+								const unsigned long ext)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return false;
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+		return __riscv_has_extension_unlikely(vendor,
+						      ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
+	return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext);
+}
+
+static __always_inline bool riscv_cpu_has_vendor_extension_likely(const unsigned long vendor,
+								  int cpu, const unsigned long ext)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return false;
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+	    __riscv_has_extension_likely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE))
+		return true;
+
+	return __riscv_isa_vendor_extension_available(cpu, vendor, ext);
+}
+
+static __always_inline bool riscv_cpu_has_vendor_extension_unlikely(const unsigned long vendor,
+								    int cpu,
+								    const unsigned long ext)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return false;
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+	    __riscv_has_extension_unlikely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE))
+		return true;
+
+	return __riscv_isa_vendor_extension_available(cpu, vendor, ext);
+}
+
+#endif /* _ASM_VENDOR_EXTENSIONS_H */
diff --git a/arch/riscv/include/asm/vendor_extensions/andes.h b/arch/riscv/include/asm/vendor_extensions/andes.h
new file mode 100644
index 0000000..7bb2fc4
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/andes.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+#define RISCV_ISA_VENDOR_EXT_XANDESPMU		0
+
+/*
+ * Extension keys should be strictly less than max.
+ * It is safe to increment this when necessary.
+ */
+#define RISCV_ISA_VENDOR_EXT_MAX_ANDES			32
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_andes;
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 8b8f6ac..b706c8e 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -81,6 +81,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_MASK		(7 << 0)
 #define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 #define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS	7
+#define RISCV_HWPROBE_KEY_TIME_CSR_FREQ	8
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 5b243d4..06d407f 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -58,6 +58,8 @@
 obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o
+obj-y	+= vendor_extensions.o
+obj-y	+= vendor_extensions/
 obj-y	+= probes/
 obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
@@ -110,3 +112,4 @@
 
 obj-$(CONFIG_64BIT)		+= pi/
 obj-$(CONFIG_ACPI)		+= acpi.o
+obj-$(CONFIG_ACPI_NUMA)	+= acpi_numa.o
diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c
index e619edc..ba957aa 100644
--- a/arch/riscv/kernel/acpi.c
+++ b/arch/riscv/kernel/acpi.c
@@ -17,7 +17,9 @@
 #include <linux/efi.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
+#include <linux/of_fdt.h>
 #include <linux/pci.h>
+#include <linux/serial_core.h>
 
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
@@ -131,7 +133,7 @@ void __init acpi_boot_table_init(void)
 	if (param_acpi_off ||
 	    (!param_acpi_on && !param_acpi_force &&
 	     efi.acpi20 == EFI_INVALID_TABLE_ADDR))
-		return;
+		goto done;
 
 	/*
 	 * ACPI is disabled at this point. Enable it in order to parse
@@ -151,6 +153,14 @@ void __init acpi_boot_table_init(void)
 		if (!param_acpi_force)
 			disable_acpi();
 	}
+
+done:
+	if (acpi_disabled) {
+		if (earlycon_acpi_spcr_enable)
+			early_init_dt_scan_chosen_stdout();
+	} else {
+		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
+	}
 }
 
 static int acpi_parse_madt_rintc(union acpi_subtable_headers *header, const unsigned long end)
@@ -191,11 +201,6 @@ struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)
 	return &cpu_madt_rintc[cpu];
 }
 
-u32 get_acpi_id_for_cpu(int cpu)
-{
-	return acpi_cpu_get_madt_rintc(cpu)->uid;
-}
-
 /*
  * __acpi_map_table() will be called before paging_init(), so early_ioremap()
  * or early_memremap() should be called here to for ACPI table mapping.
diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c
new file mode 100644
index 0000000..0231482
--- /dev/null
+++ b/arch/riscv/kernel/acpi_numa.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACPI 6.6 based NUMA setup for RISCV
+ * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ *		Author: Hanjun Guo <hanjun.guo@linaro.org>
+ * Copyright (C) 2024 Intel Corporation.
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <asm/numa.h>
+
+static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
+
+int __init acpi_numa_get_nid(unsigned int cpu)
+{
+	return acpi_early_node_map[cpu];
+}
+
+static inline int get_cpu_for_acpi_id(u32 uid)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (uid == get_acpi_id_for_cpu(cpu))
+			return cpu;
+
+	return -EINVAL;
+}
+
+static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header,
+				       const unsigned long end)
+{
+	struct acpi_srat_rintc_affinity *pa;
+	int cpu, pxm, node;
+
+	if (srat_disabled())
+		return -EINVAL;
+
+	pa = (struct acpi_srat_rintc_affinity *)header;
+	if (!pa)
+		return -EINVAL;
+
+	if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED))
+		return 0;
+
+	pxm = pa->proximity_domain;
+	node = pxm_to_node(pxm);
+
+	/*
+	 * If we can't map the UID to a logical cpu this
+	 * means that the UID is not part of possible cpus
+	 * so we do not need a NUMA mapping for it, skip
+	 * the SRAT entry and keep parsing.
+	 */
+	cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid);
+	if (cpu < 0)
+		return 0;
+
+	acpi_early_node_map[cpu] = node;
+	pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm,
+		cpuid_to_hartid_map(cpu), node);
+
+	return 0;
+}
+
+void __init acpi_map_cpus_to_nodes(void)
+{
+	int i;
+
+	/*
+	 * In ACPI, SMP and CPU NUMA information is provided in separate
+	 * static tables, namely the MADT and the SRAT.
+	 *
+	 * Thus, it is simpler to first create the cpu logical map through
+	 * an MADT walk and then map the logical cpus to their node ids
+	 * as separate steps.
+	 */
+	acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat),
+				 ACPI_SRAT_TYPE_RINTC_AFFINITY, acpi_parse_rintc_pxm, 0);
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		early_map_cpu_to_node(i, acpi_numa_get_nid(i));
+}
+
+/* Callback for Proximity Domain -> logical node ID mapping */
+void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa)
+{
+	int pxm, node;
+
+	if (srat_disabled())
+		return;
+
+	if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) {
+		pr_err("SRAT: Invalid SRAT header length: %d\n", pa->header.length);
+		bad_srat();
+		return;
+	}
+
+	if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED))
+		return;
+
+	pxm = pa->proximity_domain;
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE) {
+		pr_err("SRAT: Too many proximity domains %d\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	node_set(node, numa_nodes_parsed);
+}
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 09e9b88..d6c108c 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/acpi.h>
 #include <linux/cpu.h>
 #include <linux/of.h>
 #include <asm/cacheinfo.h>
@@ -64,7 +65,6 @@ uintptr_t get_cache_geometry(u32 level, enum cache_type type)
 }
 
 static void ci_leaf_init(struct cacheinfo *this_leaf,
-			 struct device_node *node,
 			 enum cache_type type, unsigned int level)
 {
 	this_leaf->level = level;
@@ -79,12 +79,33 @@ int populate_cache_leaves(unsigned int cpu)
 	struct device_node *prev = NULL;
 	int levels = 1, level = 1;
 
+	if (!acpi_disabled) {
+		int ret, fw_levels, split_levels;
+
+		ret = acpi_get_cache_info(cpu, &fw_levels, &split_levels);
+		if (ret)
+			return ret;
+
+		BUG_ON((split_levels > fw_levels) ||
+		       (split_levels + fw_levels > this_cpu_ci->num_leaves));
+
+		for (; level <= this_cpu_ci->num_levels; level++) {
+			if (level <= split_levels) {
+				ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
+				ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
+			} else {
+				ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
+			}
+		}
+		return 0;
+	}
+
 	if (of_property_read_bool(np, "cache-size"))
-		ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
 	if (of_property_read_bool(np, "i-cache-size"))
-		ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
 	if (of_property_read_bool(np, "d-cache-size"))
-		ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
 	while ((np = of_find_next_cache_node(np))) {
@@ -97,11 +118,11 @@ int populate_cache_leaves(unsigned int cpu)
 		if (level <= levels)
 			break;
 		if (of_property_read_bool(np, "cache-size"))
-			ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level);
+			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
 		if (of_property_read_bool(np, "i-cache-size"))
-			ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level);
+			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
 		if (of_property_read_bool(np, "d-cache-size"))
-			ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level);
+			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}
 	of_node_put(np);
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index c1f3655..f6b13e9 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -16,6 +16,7 @@
 #include <asm/sbi.h>
 #include <asm/smp.h>
 #include <asm/pgtable.h>
+#include <asm/vendor_extensions.h>
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
@@ -235,7 +236,33 @@ arch_initcall(riscv_cpuinfo_init);
 
 #ifdef CONFIG_PROC_FS
 
-static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap)
+#define ALL_CPUS -1
+
+static void print_vendor_isa(struct seq_file *f, int cpu)
+{
+	struct riscv_isavendorinfo *vendor_bitmap;
+	struct riscv_isa_vendor_ext_data_list *ext_list;
+	const struct riscv_isa_ext_data *ext_data;
+
+	for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) {
+		ext_list = riscv_isa_vendor_ext_list[i];
+		ext_data = riscv_isa_vendor_ext_list[i]->ext_data;
+
+		if (cpu == ALL_CPUS)
+			vendor_bitmap = &ext_list->all_harts_isa_bitmap;
+		else
+			vendor_bitmap = &ext_list->per_hart_isa_bitmap[cpu];
+
+		for (int j = 0; j < ext_list->ext_data_count; j++) {
+			if (!__riscv_isa_extension_available(vendor_bitmap->isa, ext_data[j].id))
+				continue;
+
+			seq_printf(f, "_%s", ext_data[j].name);
+		}
+	}
+}
+
+static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap, int cpu)
 {
 
 	if (IS_ENABLED(CONFIG_32BIT))
@@ -254,6 +281,8 @@ static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap)
 		seq_printf(f, "%s", riscv_isa_ext[i].name);
 	}
 
+	print_vendor_isa(f, cpu);
+
 	seq_puts(f, "\n");
 }
 
@@ -316,7 +345,7 @@ static int c_show(struct seq_file *m, void *v)
 	 * line.
 	 */
 	seq_puts(m, "isa\t\t: ");
-	print_isa(m, NULL);
+	print_isa(m, NULL, ALL_CPUS);
 	print_mmu(m);
 
 	if (acpi_disabled) {
@@ -338,7 +367,7 @@ static int c_show(struct seq_file *m, void *v)
 	 * additional extensions not present across all harts.
 	 */
 	seq_puts(m, "hart isa\t: ");
-	print_isa(m, hart_isa[cpu_id].isa);
+	print_isa(m, hart_isa[cpu_id].isa, cpu_id);
 	seq_puts(m, "\n");
 
 	return 0;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 0366dc3..8f20607 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -24,6 +24,7 @@
 #include <asm/processor.h>
 #include <asm/sbi.h>
 #include <asm/vector.h>
+#include <asm/vendor_extensions.h>
 
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
@@ -100,31 +101,6 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
-#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
-	.name = #_name,									\
-	.property = #_name,								\
-	.id = _id,									\
-	.subset_ext_ids = _subset_exts,							\
-	.subset_ext_size = _subset_exts_size,						\
-	.validate = _validate								\
-}
-
-#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, NULL)
-
-#define __RISCV_ISA_EXT_DATA_VALIDATE(_name, _id, _validate) \
-			_RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, _validate)
-
-/* Used to declare pure "lasso" extension (Zk for instance) */
-#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
-	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
-			    ARRAY_SIZE(_bundled_exts), NULL)
-
-/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
-#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
-	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), NULL)
-#define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
-	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
-
 static int riscv_ext_zca_depends(const struct riscv_isa_ext_data *data,
 				 const unsigned long *isa_bitmap)
 {
@@ -405,7 +381,6 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
-	__RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_EXT_XANDESPMU),
 };
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
@@ -512,6 +487,21 @@ static void __init riscv_parse_isa_string(const char *isa, unsigned long *bitmap
 		bool ext_err = false;
 
 		switch (*ext) {
+		case 'x':
+		case 'X':
+			if (acpi_disabled)
+				pr_warn_once("Vendor extensions are ignored in riscv,isa. Use riscv,isa-extensions instead.");
+			/*
+			 * To skip an extension, we find its end.
+			 * As multi-letter extensions must be split from other multi-letter
+			 * extensions with an "_", the end of a multi-letter extension will
+			 * either be the null character or the "_" at the start of the next
+			 * multi-letter extension.
+			 */
+			for (; *isa && *isa != '_'; ++isa)
+				;
+			ext_err = true;
+			break;
 		case 's':
 			/*
 			 * Workaround for invalid single-letter 's' & 'u' (QEMU).
@@ -527,8 +517,6 @@ static void __init riscv_parse_isa_string(const char *isa, unsigned long *bitmap
 			}
 			fallthrough;
 		case 'S':
-		case 'x':
-		case 'X':
 		case 'z':
 		case 'Z':
 			/*
@@ -728,6 +716,61 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 		acpi_put_table((struct acpi_table_header *)rhct);
 }
 
+static void __init riscv_fill_cpu_vendor_ext(struct device_node *cpu_node, int cpu)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return;
+
+	for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) {
+		struct riscv_isa_vendor_ext_data_list *ext_list = riscv_isa_vendor_ext_list[i];
+
+		for (int j = 0; j < ext_list->ext_data_count; j++) {
+			const struct riscv_isa_ext_data ext = ext_list->ext_data[j];
+			struct riscv_isavendorinfo *isavendorinfo = &ext_list->per_hart_isa_bitmap[cpu];
+
+			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
+						     ext.property) < 0)
+				continue;
+
+			/*
+			 * Assume that subset extensions are all members of the
+			 * same vendor.
+			 */
+			if (ext.subset_ext_size)
+				for (int k = 0; k < ext.subset_ext_size; k++)
+					set_bit(ext.subset_ext_ids[k], isavendorinfo->isa);
+
+			set_bit(ext.id, isavendorinfo->isa);
+		}
+	}
+}
+
+/*
+ * Populate all_harts_isa_bitmap for each vendor with all of the extensions that
+ * are shared across CPUs for that vendor.
+ */
+static void __init riscv_fill_vendor_ext_list(int cpu)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+		return;
+
+	for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) {
+		struct riscv_isa_vendor_ext_data_list *ext_list = riscv_isa_vendor_ext_list[i];
+
+		if (!ext_list->is_initialized) {
+			bitmap_copy(ext_list->all_harts_isa_bitmap.isa,
+				    ext_list->per_hart_isa_bitmap[cpu].isa,
+				    RISCV_ISA_VENDOR_EXT_MAX);
+			ext_list->is_initialized = true;
+		} else {
+			bitmap_and(ext_list->all_harts_isa_bitmap.isa,
+				   ext_list->all_harts_isa_bitmap.isa,
+				   ext_list->per_hart_isa_bitmap[cpu].isa,
+				   RISCV_ISA_VENDOR_EXT_MAX);
+		}
+	}
+}
+
 static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 {
 	unsigned int cpu;
@@ -760,6 +803,7 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		}
 
 		riscv_resolve_isa(source_isa, isainfo->isa, &this_hwcap, isa2hwcap);
+		riscv_fill_cpu_vendor_ext(cpu_node, cpu);
 
 		of_node_put(cpu_node);
 
@@ -776,6 +820,8 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 			bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
 		else
 			bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+
+		riscv_fill_vendor_ext_list(cpu);
 	}
 
 	if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
@@ -918,29 +964,46 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
 {
 	struct alt_entry *alt;
 	void *oldptr, *altptr;
-	u16 id, value;
+	u16 id, value, vendor;
 
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		return;
 
 	for (alt = begin; alt < end; alt++) {
-		if (alt->vendor_id != 0)
-			continue;
-
 		id = PATCH_ID_CPUFEATURE_ID(alt->patch_id);
+		vendor = PATCH_ID_CPUFEATURE_ID(alt->vendor_id);
 
-		if (id >= RISCV_ISA_EXT_MAX) {
+		/*
+		 * Any alternative with a patch_id that is less than
+		 * RISCV_ISA_EXT_MAX is interpreted as a standard extension.
+		 *
+		 * Any alternative with patch_id that is greater than or equal
+		 * to RISCV_VENDOR_EXT_ALTERNATIVES_BASE is interpreted as a
+		 * vendor extension.
+		 */
+		if (id < RISCV_ISA_EXT_MAX) {
+			/*
+			 * This patch should be treated as errata so skip
+			 * processing here.
+			 */
+			if (alt->vendor_id != 0)
+				continue;
+
+			if (!__riscv_isa_extension_available(NULL, id))
+				continue;
+
+			value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id);
+			if (!riscv_cpufeature_patch_check(id, value))
+				continue;
+		} else if (id >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE) {
+			if (!__riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor,
+								    id - RISCV_VENDOR_EXT_ALTERNATIVES_BASE))
+				continue;
+		} else {
 			WARN(1, "This extension id:%d is not in ISA extension list", id);
 			continue;
 		}
 
-		if (!__riscv_isa_extension_available(NULL, id))
-			continue;
-
-		value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id);
-		if (!riscv_cpufeature_patch_check(id, value))
-			continue;
-
 		oldptr = ALT_OLD_PTR(alt);
 		altptr = ALT_ALT_PTR(alt);
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 68a24cf..ac2e908 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -88,7 +88,6 @@
 	call riscv_v_context_nesting_start
 #endif
 	move a0, sp /* pt_regs */
-	la ra, ret_from_exception
 
 	/*
 	 * MSB of cause differentiates between
@@ -97,7 +96,8 @@
 	bge s4, zero, 1f
 
 	/* Handle interrupts */
-	tail do_irq
+	call do_irq
+	j ret_from_exception
 1:
 	/* Handle other exceptions */
 	slli t0, s4, RISCV_LGPTR
@@ -105,11 +105,14 @@
 	la t2, excp_vect_table_end
 	add t0, t1, t0
 	/* Check if exception code lies within bounds */
-	bgeu t0, t2, 1f
-	REG_L t0, 0(t0)
-	jr t0
-1:
-	tail do_trap_unknown
+	bgeu t0, t2, 3f
+	REG_L t1, 0(t0)
+2:	jalr t1
+	j ret_from_exception
+3:
+
+	la t1, do_trap_unknown
+	j 2b
 SYM_CODE_END(handle_exception)
 ASM_NOKPROBE(handle_exception)
 
@@ -130,6 +133,10 @@
 #endif
 	bnez s0, 1f
 
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+	call	stackleak_erase_on_task_stack
+#endif
+
 	/* Save unwound kernel stack pointer in thread_info */
 	addi s0, sp, PT_SIZE_ON_STACK
 	REG_S s0, TASK_TI_KERNEL_SP(tp)
diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile
index 8265ff4..d2129f2 100644
--- a/arch/riscv/kernel/probes/Makefile
+++ b/arch/riscv/kernel/probes/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o simulate-insn.o
 obj-$(CONFIG_RETHOOK)		+= rethook.o rethook_trampoline.o
-obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o simulate-insn.o
 CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
deleted file mode 100644
index a69dfa6..0000000
--- a/arch/riscv/kernel/probes/ftrace.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/kprobes.h>
-
-/* Ftrace callback handler for kprobes -- called under preepmt disabled */
-void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
-{
-	struct kprobe *p;
-	struct pt_regs *regs;
-	struct kprobe_ctlblk *kcb;
-	int bit;
-
-	if (unlikely(kprobe_ftrace_disabled))
-		return;
-
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0)
-		return;
-
-	p = get_kprobe((kprobe_opcode_t *)ip);
-	if (unlikely(!p) || kprobe_disabled(p))
-		goto out;
-
-	regs = ftrace_get_regs(fregs);
-	kcb = get_kprobe_ctlblk();
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(p);
-	} else {
-		unsigned long orig_ip = instruction_pointer(regs);
-
-		instruction_pointer_set(regs, ip);
-
-		__this_cpu_write(current_kprobe, p);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs)) {
-			/*
-			 * Emulate singlestep (and also recover regs->pc)
-			 * as if there is a nop
-			 */
-			instruction_pointer_set(regs,
-				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
-			if (unlikely(p->post_handler)) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				p->post_handler(p, regs, 0);
-			}
-			instruction_pointer_set(regs, orig_ip);
-		}
-
-		/*
-		 * If pre_handler returns !0, it changes regs->pc. We have to
-		 * skip emulating post_handler.
-		 */
-		__this_cpu_write(current_kprobe, NULL);
-	}
-out:
-	ftrace_test_recursion_unlock(bit);
-}
-NOKPROBE_SYMBOL(kprobe_ftrace_handler);
-
-int arch_prepare_kprobe_ftrace(struct kprobe *p)
-{
-	p->ainsn.api.insn = NULL;
-	return 0;
-}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 4f73c0a..a2cde65 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -281,8 +281,10 @@ void __init setup_arch(char **cmdline_p)
 	setup_smp();
 #endif
 
-	if (!acpi_disabled)
+	if (!acpi_disabled) {
 		acpi_init_rintc_map();
+		acpi_map_cpus_to_nodes();
+	}
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 5a2edd7..dcd2824 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -84,7 +84,7 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	datap = state + 1;
 
 	/* datap is designed to be 16 byte aligned for better performance */
-	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
+	WARN_ON(!IS_ALIGNED((unsigned long)datap, 16));
 
 	get_cpu_vector_context();
 	riscv_v_vstate_save(&current->thread.vstate, regs);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 19baf0d..0f8f1c9 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -96,7 +96,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 	if (hart == cpuid_to_hartid_map(0)) {
 		BUG_ON(found_boot_cpu);
 		found_boot_cpu = true;
-		early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count));
 		return 0;
 	}
 
@@ -106,7 +105,6 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 	}
 
 	cpuid_to_hartid_map(cpu_count) = hart;
-	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count));
 	cpu_count++;
 
 	return 0;
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 10e311b..c6d5de2 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_FRAME_POINTER
 
-extern asmlinkage void ret_from_exception(void);
+extern asmlinkage void handle_exception(void);
 
 static inline int fp_is_valid(unsigned long fp, unsigned long sp)
 {
@@ -71,7 +71,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			fp = frame->fp;
 			pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra,
 						   &frame->ra);
-			if (pc == (unsigned long)ret_from_exception) {
+			if (pc == (unsigned long)handle_exception) {
 				if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))
 					break;
 
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index 6855947..8d1b5c3 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -9,6 +9,7 @@
 #include <asm/cpufeature.h>
 #include <asm/hwprobe.h>
 #include <asm/processor.h>
+#include <asm/delay.h>
 #include <asm/sbi.h>
 #include <asm/switch_to.h>
 #include <asm/uaccess.h>
@@ -93,44 +94,45 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		 * regardless of the kernel's configuration, as no other checks, besides
 		 * presence in the hart_isa bitmap, are made.
 		 */
+		EXT_KEY(ZACAS);
+		EXT_KEY(ZAWRS);
 		EXT_KEY(ZBA);
 		EXT_KEY(ZBB);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZICBOZ);
 		EXT_KEY(ZBC);
-
 		EXT_KEY(ZBKB);
 		EXT_KEY(ZBKC);
 		EXT_KEY(ZBKX);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZCA);
+		EXT_KEY(ZCB);
+		EXT_KEY(ZCMOP);
+		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZICOND);
+		EXT_KEY(ZIHINTNTL);
+		EXT_KEY(ZIHINTPAUSE);
+		EXT_KEY(ZIMOP);
 		EXT_KEY(ZKND);
 		EXT_KEY(ZKNE);
 		EXT_KEY(ZKNH);
 		EXT_KEY(ZKSED);
 		EXT_KEY(ZKSH);
 		EXT_KEY(ZKT);
-		EXT_KEY(ZIHINTNTL);
 		EXT_KEY(ZTSO);
-		EXT_KEY(ZACAS);
-		EXT_KEY(ZICOND);
-		EXT_KEY(ZIHINTPAUSE);
-		EXT_KEY(ZIMOP);
-		EXT_KEY(ZCA);
-		EXT_KEY(ZCB);
-		EXT_KEY(ZCMOP);
-		EXT_KEY(ZAWRS);
 
 		/*
 		 * All the following extensions must depend on the kernel
 		 * support of V.
 		 */
 		if (has_vector()) {
-			EXT_KEY(ZVE32X);
-			EXT_KEY(ZVE32F);
-			EXT_KEY(ZVE64X);
-			EXT_KEY(ZVE64F);
-			EXT_KEY(ZVE64D);
 			EXT_KEY(ZVBB);
 			EXT_KEY(ZVBC);
+			EXT_KEY(ZVE32F);
+			EXT_KEY(ZVE32X);
+			EXT_KEY(ZVE64D);
+			EXT_KEY(ZVE64F);
+			EXT_KEY(ZVE64X);
+			EXT_KEY(ZVFH);
+			EXT_KEY(ZVFHMIN);
 			EXT_KEY(ZVKB);
 			EXT_KEY(ZVKG);
 			EXT_KEY(ZVKNED);
@@ -139,16 +141,14 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZVKSED);
 			EXT_KEY(ZVKSH);
 			EXT_KEY(ZVKT);
-			EXT_KEY(ZVFH);
-			EXT_KEY(ZVFHMIN);
 		}
 
 		if (has_fpu()) {
-			EXT_KEY(ZFH);
-			EXT_KEY(ZFHMIN);
-			EXT_KEY(ZFA);
 			EXT_KEY(ZCD);
 			EXT_KEY(ZCF);
+			EXT_KEY(ZFA);
+			EXT_KEY(ZFH);
+			EXT_KEY(ZFHMIN);
 		}
 #undef EXT_KEY
 	}
@@ -237,6 +237,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = user_max_virt_addr();
 		break;
 
+	case RISCV_HWPROBE_KEY_TIME_CSR_FREQ:
+		pair->value = riscv_timebase;
+		break;
+
 	/*
 	 * For forward compatibility, unknown keys don't fail the whole
 	 * call, but get their element key set to -1 and value set to 0
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
new file mode 100644
index 0000000..b6c1e7b
--- /dev/null
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/andes.h>
+
+#include <linux/array_size.h>
+#include <linux/types.h>
+
+struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = {
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES
+	&riscv_isa_vendor_ext_list_andes,
+#endif
+};
+
+const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list);
+
+/**
+ * __riscv_isa_vendor_extension_available() - Check whether given vendor
+ * extension is available or not.
+ *
+ * @cpu: check if extension is available on this cpu
+ * @vendor: vendor that the extension is a member of
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: When cpu is -1, will check if extension is available on all cpus
+ */
+bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsigned int bit)
+{
+	struct riscv_isavendorinfo *bmap;
+	struct riscv_isavendorinfo *cpu_bmap;
+
+	switch (vendor) {
+	#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES
+	case ANDES_VENDOR_ID:
+		bmap = &riscv_isa_vendor_ext_list_andes.all_harts_isa_bitmap;
+		cpu_bmap = &riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap[cpu];
+		break;
+	#endif
+	default:
+		return false;
+	}
+
+	if (cpu != -1)
+		bmap = &cpu_bmap[cpu];
+
+	if (bit >= RISCV_ISA_VENDOR_EXT_MAX)
+		return false;
+
+	return test_bit(bit, bmap->isa) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_vendor_extension_available);
diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile
new file mode 100644
index 0000000..6a61aed
--- /dev/null
+++ b/arch/riscv/kernel/vendor_extensions/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES)	+= andes.o
diff --git a/arch/riscv/kernel/vendor_extensions/andes.c b/arch/riscv/kernel/vendor_extensions/andes.c
new file mode 100644
index 0000000..ec688c8
--- /dev/null
+++ b/arch/riscv/kernel/vendor_extensions/andes.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <asm/cpufeature.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/andes.h>
+
+#include <linux/array_size.h>
+#include <linux/types.h>
+
+/* All Andes vendor extensions supported in Linux */
+const struct riscv_isa_ext_data riscv_isa_vendor_ext_andes[] = {
+	__RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_VENDOR_EXT_XANDESPMU),
+};
+
+struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_andes = {
+	.ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_andes),
+	.ext_data = riscv_isa_vendor_ext_andes,
+};
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 59e0d86..a822f95 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -799,17 +799,6 @@
 
 menu "Virtualization"
 
-config PROTECTED_VIRTUALIZATION_GUEST
-	def_bool n
-	prompt "Protected virtualization guest support"
-	help
-	  Select this option, if you want to be able to run this
-	  kernel as a protected virtualization KVM guest.
-	  Protected virtualization capable machines have a mini hypervisor
-	  located at machine level (an ultravisor). With help of the
-	  Ultravisor, KVM will be able to run "protected" VMs, special
-	  VMs whose memory and management data are unavailable to KVM.
-
 config PFAULT
 	def_bool y
 	prompt "Pseudo page fault support"
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index c2978cb..91a30e0 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -46,9 +46,9 @@
  * /proc entries (sysctl)
  */
 static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata";
-static int appldata_timer_handler(struct ctl_table *ctl, int write,
+static int appldata_timer_handler(const struct ctl_table *ctl, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos);
-static int appldata_interval_handler(struct ctl_table *ctl, int write,
+static int appldata_interval_handler(const struct ctl_table *ctl, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos);
 
 static struct ctl_table_header *appldata_sysctl_header;
@@ -199,7 +199,7 @@ static void __appldata_vtimer_setup(int cmd)
  * Start/Stop timer, show status of timer (0 = not active, 1 = active)
  */
 static int
-appldata_timer_handler(struct ctl_table *ctl, int write,
+appldata_timer_handler(const struct ctl_table *ctl, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int timer_active = appldata_timer_active;
@@ -232,7 +232,7 @@ appldata_timer_handler(struct ctl_table *ctl, int write,
  * current timer interval.
  */
 static int
-appldata_interval_handler(struct ctl_table *ctl, int write,
+appldata_interval_handler(const struct ctl_table *ctl, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int interval = appldata_interval;
@@ -262,7 +262,7 @@ appldata_interval_handler(struct ctl_table *ctl, int write,
  * monitoring (0 = not in process, 1 = in process)
  */
 static int
-appldata_generic_handler(struct ctl_table *ctl, int write,
+appldata_generic_handler(const struct ctl_table *ctl, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct appldata_ops *ops = NULL, *tmp_ops;
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index e765899..4f47688 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -39,8 +39,7 @@
 
 obj-y	:= head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o
 obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o relocs.o
-obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE))	+= uv.o
+obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o relocs.o alternative.o uv.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 obj-y	+= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
 obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o
diff --git a/arch/s390/boot/alternative.c b/arch/s390/boot/alternative.c
new file mode 100644
index 0000000..abc08d2
--- /dev/null
+++ b/arch/s390/boot/alternative.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../kernel/alternative.c"
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 18027fd..83e2ce0 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -30,6 +30,8 @@ struct vmlinux_info {
 	unsigned long init_mm_off;
 	unsigned long swapper_pg_dir_off;
 	unsigned long invalid_pg_dir_off;
+	unsigned long alt_instructions;
+	unsigned long alt_instructions_end;
 #ifdef CONFIG_KASAN
 	unsigned long kasan_early_shadow_page_off;
 	unsigned long kasan_early_shadow_pte_off;
@@ -89,8 +91,10 @@ extern char _end[], _decompressor_end[];
 extern unsigned char _compressed_start[];
 extern unsigned char _compressed_end[];
 extern struct vmlinux_info _vmlinux_info;
+
 #define vmlinux _vmlinux_info
 
+#define __lowcore_pa(x)		((unsigned long)(x) % sizeof(struct lowcore))
 #define __abs_lowcore_pa(x)	(((unsigned long)(x) - __abs_lowcore) % sizeof(struct lowcore))
 #define __kernel_va(x)		((void *)((unsigned long)(x) - __kaslr_offset_phys + __kaslr_offset))
 #define __kernel_pa(x)		((unsigned long)(x) - __kaslr_offset + __kaslr_offset_phys)
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index a21f301..1773b72 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/ctype.h>
 #include <linux/pgtable.h>
+#include <asm/abs_lowcore.h>
 #include <asm/page-states.h>
 #include <asm/ebcdic.h>
 #include <asm/sclp.h>
@@ -310,5 +311,7 @@ void parse_boot_command_line(void)
 				prot_virt_host = 1;
 		}
 #endif
+		if (!strcmp(param, "relocate_lowcore") && test_facility(193))
+			relocate_lowcore = 1;
 	}
 }
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index c590149..ce23255 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -30,6 +30,7 @@ unsigned long __bootdata_preserved(vmemmap_size);
 unsigned long __bootdata_preserved(MODULES_VADDR);
 unsigned long __bootdata_preserved(MODULES_END);
 unsigned long __bootdata_preserved(max_mappable);
+int __bootdata_preserved(relocate_lowcore);
 
 u64 __bootdata_preserved(stfle_fac_list[16]);
 struct oldmem_data __bootdata_preserved(oldmem_data);
@@ -376,6 +377,8 @@ static void kaslr_adjust_vmlinux_info(long offset)
 	vmlinux.init_mm_off += offset;
 	vmlinux.swapper_pg_dir_off += offset;
 	vmlinux.invalid_pg_dir_off += offset;
+	vmlinux.alt_instructions += offset;
+	vmlinux.alt_instructions_end += offset;
 #ifdef CONFIG_KASAN
 	vmlinux.kasan_early_shadow_page_off += offset;
 	vmlinux.kasan_early_shadow_pte_off += offset;
@@ -478,8 +481,12 @@ void startup_kernel(void)
 	 * before the kernel started. Therefore, in case the two sections
 	 * overlap there is no risk of corrupting any data.
 	 */
-	if (kaslr_enabled())
-		amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G);
+	if (kaslr_enabled()) {
+		unsigned long amode31_min;
+
+		amode31_min = (unsigned long)_decompressor_end;
+		amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, amode31_min, SZ_2G);
+	}
 	if (!amode31_lma)
 		amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size;
 	physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);
@@ -503,6 +510,9 @@ void startup_kernel(void)
 	kaslr_adjust_got(__kaslr_offset);
 	setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
 	copy_bootdata();
+	__apply_alternatives((struct alt_instr *)_vmlinux_info.alt_instructions,
+			     (struct alt_instr *)_vmlinux_info.alt_instructions_end,
+			     ALT_CTX_EARLY);
 
 	/*
 	 * Save KASLR offset for early dumps, before vmcore_info is set.
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index 1e66d2c..318e6ba 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -8,12 +8,8 @@
 #include "uv.h"
 
 /* will be used in arch/s390/kernel/uv.c */
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 int __bootdata_preserved(prot_virt_guest);
-#endif
-#if IS_ENABLED(CONFIG_KVM)
 int __bootdata_preserved(prot_virt_host);
-#endif
 struct uv_info __bootdata_preserved(uv_info);
 
 void uv_query_info(void)
@@ -53,14 +49,11 @@ void uv_query_info(void)
 		uv_info.max_secrets = uvcb.max_secrets;
 	}
 
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 	if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
 	    test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list))
 		prot_virt_guest = 1;
-#endif
 }
 
-#if IS_ENABLED(CONFIG_KVM)
 unsigned long adjust_to_uv_max(unsigned long limit)
 {
 	if (is_prot_virt_host() && uv_info.max_sec_stor_addr)
@@ -92,4 +85,3 @@ void sanitize_prot_virt_host(void)
 {
 	prot_virt_host = is_prot_virt_host_capable();
 }
-#endif
diff --git a/arch/s390/boot/uv.h b/arch/s390/boot/uv.h
index 0f30708..da4a4a8 100644
--- a/arch/s390/boot/uv.h
+++ b/arch/s390/boot/uv.h
@@ -2,21 +2,8 @@
 #ifndef BOOT_UV_H
 #define BOOT_UV_H
 
-#if IS_ENABLED(CONFIG_KVM)
 unsigned long adjust_to_uv_max(unsigned long limit);
 void sanitize_prot_virt_host(void);
-#else
-static inline unsigned long adjust_to_uv_max(unsigned long limit)
-{
-	return limit;
-}
-static inline void sanitize_prot_virt_host(void) {}
-#endif
-
-#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
 void uv_query_info(void);
-#else
-static inline void uv_query_info(void) {}
-#endif
 
 #endif /* BOOT_UV_H */
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index a255ca1..2847cc0 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -26,6 +26,7 @@ atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]);
 enum populate_mode {
 	POPULATE_NONE,
 	POPULATE_DIRECT,
+	POPULATE_LOWCORE,
 	POPULATE_ABS_LOWCORE,
 	POPULATE_IDENTITY,
 	POPULATE_KERNEL,
@@ -242,6 +243,8 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m
 		return -1;
 	case POPULATE_DIRECT:
 		return addr;
+	case POPULATE_LOWCORE:
+		return __lowcore_pa(addr);
 	case POPULATE_ABS_LOWCORE:
 		return __abs_lowcore_pa(addr);
 	case POPULATE_KERNEL:
@@ -418,6 +421,7 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat
 
 void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit)
 {
+	unsigned long lowcore_address = 0;
 	unsigned long start, end;
 	unsigned long asce_type;
 	unsigned long asce_bits;
@@ -455,12 +459,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
 	__arch_set_page_dat((void *)swapper_pg_dir, 1UL << CRST_ALLOC_ORDER);
 	__arch_set_page_dat((void *)invalid_pg_dir, 1UL << CRST_ALLOC_ORDER);
 
+	if (relocate_lowcore)
+		lowcore_address = LOWCORE_ALT_ADDRESS;
+
 	/*
 	 * To allow prefixing the lowcore must be mapped with 4KB pages.
 	 * To prevent creation of a large page at address 0 first map
 	 * the lowcore and create the identity mapping only afterwards.
 	 */
-	pgtable_populate(0, sizeof(struct lowcore), POPULATE_DIRECT);
+	pgtable_populate(lowcore_address,
+			 lowcore_address + sizeof(struct lowcore),
+			 POPULATE_LOWCORE);
 	for_each_physmem_usable_range(i, &start, &end) {
 		pgtable_populate((unsigned long)__identity_va(start),
 				 (unsigned long)__identity_va(end),
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index f360241..ea63a73 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -55,7 +55,6 @@
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
-CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_S390_HYPFS_FS=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index d0d8925..d8b28ff 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -53,7 +53,6 @@
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
-CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_S390_HYPFS_FS=y
diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h
index 6f264b7..d20df8c 100644
--- a/arch/s390/include/asm/abs_lowcore.h
+++ b/arch/s390/include/asm/abs_lowcore.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_S390_ABS_LOWCORE_H
 #define _ASM_S390_ABS_LOWCORE_H
 
+#include <asm/sections.h>
 #include <asm/lowcore.h>
 
 #define ABS_LOWCORE_MAP_SIZE	(NR_CPUS * sizeof(struct lowcore))
@@ -24,4 +25,11 @@ static inline void put_abs_lowcore(struct lowcore *lc)
 	put_cpu();
 }
 
+extern int __bootdata_preserved(relocate_lowcore);
+
+static inline int have_relocated_lowcore(void)
+{
+	return relocate_lowcore;
+}
+
 #endif /* _ASM_S390_ABS_LOWCORE_H */
diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h
deleted file mode 100644
index 608f628..0000000
--- a/arch/s390/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_ALTERNATIVE_ASM_H
-#define _ASM_S390_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro alt_entry orig_start, orig_end, alt_start, alt_end, feature
-	.long	\orig_start - .
-	.long	\alt_start - .
-	.word	\feature
-	.byte	\orig_end - \orig_start
-	.org	. - ( \orig_end - \orig_start ) & 1
-	.org	. - ( \orig_end - \orig_start ) + ( \alt_end - \alt_start )
-	.org	. - ( \alt_end - \alt_start ) + ( \orig_end - \orig_start )
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-	.pushsection .altinstr_replacement,"ax"
-770:	\newinstr
-771:	.popsection
-772:	\oldinstr
-773:	.pushsection .altinstructions,"a"
-	alt_entry 772b, 773b, 770b, 771b, \feature
-	.popsection
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-	.pushsection .altinstr_replacement,"ax"
-770:	\newinstr1
-771:	\newinstr2
-772:	.popsection
-773:	\oldinstr
-774:	.pushsection .altinstructions,"a"
-	alt_entry 773b, 774b, 770b, 771b,\feature1
-	alt_entry 773b, 774b, 771b, 772b,\feature2
-	.popsection
-.endm
-
-#endif	/*  __ASSEMBLY__  */
-
-#endif /* _ASM_S390_ALTERNATIVE_ASM_H */
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index dd93b92..de980c9 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -2,6 +2,58 @@
 #ifndef _ASM_S390_ALTERNATIVE_H
 #define _ASM_S390_ALTERNATIVE_H
 
+/*
+ * Each alternative comes with a 32 bit feature field:
+ *	union {
+ *		u32 feature;
+ *		struct {
+ *			u32 ctx	 : 4;
+ *			u32 type : 8;
+ *			u32 data : 20;
+ *		};
+ *	}
+ *
+ * @ctx is a bitfield, where only one bit must be set. Each bit defines
+ * in which context an alternative is supposed to be applied to the
+ * kernel image:
+ *
+ * - from the decompressor before the kernel itself is executed
+ * - from early kernel code from within the kernel
+ *
+ * @type is a number which defines the type and with that the type
+ * specific alternative patching.
+ *
+ * @data is additional type specific information which defines if an
+ * alternative should be applied.
+ */
+
+#define ALT_CTX_EARLY		1
+#define ALT_CTX_LATE		2
+#define ALT_CTX_ALL		(ALT_CTX_EARLY | ALT_CTX_LATE)
+
+#define ALT_TYPE_FACILITY	0
+#define ALT_TYPE_SPEC		1
+#define ALT_TYPE_LOWCORE	2
+
+#define ALT_DATA_SHIFT		0
+#define ALT_TYPE_SHIFT		20
+#define ALT_CTX_SHIFT		28
+
+#define ALT_FACILITY_EARLY(facility)	(ALT_CTX_EARLY << ALT_CTX_SHIFT		| \
+					 ALT_TYPE_FACILITY << ALT_TYPE_SHIFT	| \
+					 (facility) << ALT_DATA_SHIFT)
+
+#define ALT_FACILITY(facility)		(ALT_CTX_LATE << ALT_CTX_SHIFT		| \
+					 ALT_TYPE_FACILITY << ALT_TYPE_SHIFT	| \
+					 (facility) << ALT_DATA_SHIFT)
+
+#define ALT_SPEC(facility)		(ALT_CTX_LATE << ALT_CTX_SHIFT		| \
+					 ALT_TYPE_SPEC << ALT_TYPE_SHIFT	| \
+					 (facility) << ALT_DATA_SHIFT)
+
+#define ALT_LOWCORE			(ALT_CTX_EARLY << ALT_CTX_SHIFT		| \
+					 ALT_TYPE_LOWCORE << ALT_TYPE_SHIFT)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
@@ -11,12 +63,30 @@
 struct alt_instr {
 	s32 instr_offset;	/* original instruction */
 	s32 repl_offset;	/* offset to replacement instruction */
-	u16 facility;		/* facility bit set for replacement */
+	union {
+		u32 feature;	/* feature required for replacement */
+		struct {
+			u32 ctx	 : 4;  /* context */
+			u32 type : 8;  /* type of alternative */
+			u32 data : 20; /* patching information */
+		};
+	};
 	u8  instrlen;		/* length of original instruction */
 } __packed;
 
-void apply_alternative_instructions(void);
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
+void __apply_alternatives(struct alt_instr *start, struct alt_instr *end, unsigned int ctx);
+
+static inline void apply_alternative_instructions(void)
+{
+	__apply_alternatives(__alt_instructions, __alt_instructions_end, ALT_CTX_LATE);
+}
+
+static inline void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
+{
+	__apply_alternatives(start, end, ALT_CTX_ALL);
+}
 
 /*
  * +---------------------------------+
@@ -48,10 +118,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 #define OLDINSTR(oldinstr) \
 	"661:\n\t" oldinstr "\n662:\n"
 
-#define ALTINSTR_ENTRY(facility, num)					\
+#define ALTINSTR_ENTRY(feature, num)					\
 	"\t.long 661b - .\n"			/* old instruction */	\
 	"\t.long " b_altinstr(num)"b - .\n"	/* alt instruction */	\
-	"\t.word " __stringify(facility) "\n"	/* facility bit    */	\
+	"\t.long " __stringify(feature) "\n"	/* feature	   */	\
 	"\t.byte " oldinstr_len "\n"		/* instruction len */	\
 	"\t.org . - (" oldinstr_len ") & 1\n"				\
 	"\t.org . - (" oldinstr_len ") + (" altinstr_len(num) ")\n"	\
@@ -61,24 +131,24 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 	b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n"
 
 /* alternative assembly primitive: */
-#define ALTERNATIVE(oldinstr, altinstr, facility) \
+#define ALTERNATIVE(oldinstr, altinstr, feature) \
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(altinstr, 1)				\
 	".popsection\n"							\
 	OLDINSTR(oldinstr)						\
 	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(facility, 1)					\
+	ALTINSTR_ENTRY(feature, 1)					\
 	".popsection\n"
 
-#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2)\
+#define ALTERNATIVE_2(oldinstr, altinstr1, feature1, altinstr2, feature2)\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(altinstr1, 1)				\
 	ALTINSTR_REPLACEMENT(altinstr2, 2)				\
 	".popsection\n"							\
 	OLDINSTR(oldinstr)						\
 	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(facility1, 1)					\
-	ALTINSTR_ENTRY(facility2, 2)					\
+	ALTINSTR_ENTRY(feature1, 1)					\
+	ALTINSTR_ENTRY(feature2, 2)					\
 	".popsection\n"
 
 /*
@@ -93,12 +163,12 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
  * For non barrier like inlines please define new variants
  * without volatile and memory clobber.
  */
-#define alternative(oldinstr, altinstr, facility)			\
-	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory")
+#define alternative(oldinstr, altinstr, feature)			\
+	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, feature) : : : "memory")
 
-#define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1,   \
-				   altinstr2, facility2) ::: "memory")
+#define alternative_2(oldinstr, altinstr1, feature1, altinstr2, feature2) \
+	asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, feature1,   \
+				   altinstr2, feature2) ::: "memory")
 
 /* Alternative inline assembly with input. */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
@@ -106,8 +176,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 		: : input)
 
 /* Like alternative_input, but with a single output argument */
-#define alternative_io(oldinstr, altinstr, facility, output, input...)	\
-	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility)	\
+#define alternative_io(oldinstr, altinstr, feature, output, input...)	\
+	asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, feature)	\
 		: output : input)
 
 /* Use this macro if more than one output parameter is needed. */
@@ -116,6 +186,56 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 /* Use this macro if clobbers are needed without inputs. */
 #define ASM_NO_INPUT_CLOBBER(clobber...) : clobber
 
+#else  /* __ASSEMBLY__ */
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro alt_entry orig_start, orig_end, alt_start, alt_end, feature
+	.long	\orig_start - .
+	.long	\alt_start - .
+	.long	\feature
+	.byte	\orig_end - \orig_start
+	.org	. - ( \orig_end - \orig_start ) & 1
+	.org	. - ( \orig_end - \orig_start ) + ( \alt_end - \alt_start )
+	.org	. - ( \alt_end - \alt_start ) + ( \orig_end - \orig_start )
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+	.pushsection .altinstr_replacement,"ax"
+770:	\newinstr
+771:	.popsection
+772:	\oldinstr
+773:	.pushsection .altinstructions,"a"
+	alt_entry 772b, 773b, 770b, 771b, \feature
+	.popsection
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+	.pushsection .altinstr_replacement,"ax"
+770:	\newinstr1
+771:	\newinstr2
+772:	.popsection
+773:	\oldinstr
+774:	.pushsection .altinstructions,"a"
+	alt_entry 773b, 774b, 770b, 771b,\feature1
+	alt_entry 773b, 774b, 771b, 772b,\feature2
+	.popsection
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_S390_ALTERNATIVE_H */
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index 2b379d1..742c791 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -188,7 +188,8 @@ static __always_inline long __atomic64_cmpxchg(long *ptr, long old, long new)
 	return old;
 }
 
-#ifdef __GCC_ASM_FLAG_OUTPUTS__
+/* GCC versions before 14.2.0 may die with an ICE in some configurations. */
+#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_CC_IS_GCC) && (GCC_VERSION < 140200))
 
 static __always_inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
 {
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index 436365f..e3afcec 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -210,7 +210,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define get_ccwdev_lock(x) (x)->ccwlock
 
 #define to_ccwdev(n) container_of(n, struct ccw_device, dev)
-#define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
+#define to_ccwdrv(n) container_of_const(n, struct ccw_driver, driver)
 
 extern struct ccw_device *ccw_device_create_console(struct ccw_driver *);
 extern void ccw_device_destroy_console(struct ccw_device *);
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index d46cc72..b7d2348 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -20,7 +20,6 @@
 #define MAX_FACILITY_BIT (sizeof(stfle_fac_list) * 8)
 
 extern u64 stfle_fac_list[16];
-extern u64 alt_stfle_fac_list[16];
 
 static inline void __set_facility(unsigned long nr, void *facilities)
 {
diff --git a/arch/s390/include/asm/kmsan.h b/arch/s390/include/asm/kmsan.h
index 27db65f..f73e181 100644
--- a/arch/s390/include/asm/kmsan.h
+++ b/arch/s390/include/asm/kmsan.h
@@ -12,8 +12,8 @@
 
 static inline bool is_lowcore_addr(void *addr)
 {
-	return addr >= (void *)&S390_lowcore &&
-	       addr < (void *)(&S390_lowcore + 1);
+	return addr >= (void *)get_lowcore() &&
+	       addr < (void *)(get_lowcore() + 1);
 }
 
 static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin)
@@ -25,7 +25,7 @@ static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin)
 		 * order to get a distinct struct page.
 		 */
 		addr += (void *)lowcore_ptr[raw_smp_processor_id()] -
-			(void *)&S390_lowcore;
+			(void *)get_lowcore();
 		if (KMSAN_WARN_ON(is_lowcore_addr(addr)))
 			return NULL;
 		return kmsan_get_metadata(addr, is_origin);
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index c724e71..183ac29 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -14,10 +14,15 @@
 #include <asm/ctlreg.h>
 #include <asm/cpu.h>
 #include <asm/types.h>
+#include <asm/alternative.h>
 
 #define LC_ORDER 1
 #define LC_PAGES 2
 
+#define LOWCORE_ALT_ADDRESS	_AC(0x70000, UL)
+
+#ifndef __ASSEMBLY__
+
 struct pgm_tdb {
 	u64 data[32];
 };
@@ -97,8 +102,7 @@ struct lowcore {
 	__u64	save_area_async[8];		/* 0x0240 */
 	__u64	save_area_restart[1];		/* 0x0280 */
 
-	/* CPU flags. */
-	__u64	cpu_flags;			/* 0x0288 */
+	__u64	pcpu;				/* 0x0288 */
 
 	/* Return psws. */
 	psw_t	return_psw;			/* 0x0290 */
@@ -215,7 +219,14 @@ struct lowcore {
 
 static __always_inline struct lowcore *get_lowcore(void)
 {
-	return NULL;
+	struct lowcore *lc;
+
+	if (__is_defined(__DECOMPRESSOR))
+		return NULL;
+	asm(ALTERNATIVE("llilh %[lc],0", "llilh %[lc],%[alt]", ALT_LOWCORE)
+	    : [lc] "=d" (lc)
+	    : [alt] "i" (LOWCORE_ALT_ADDRESS >> 16));
+	return lc;
 }
 
 extern struct lowcore *lowcore_ptr[];
@@ -225,4 +236,19 @@ static inline void set_prefix(__u32 address)
 	asm volatile("spx %0" : : "Q" (address) : "memory");
 }
 
+#else /* __ASSEMBLY__ */
+
+.macro GET_LC reg
+	ALTERNATIVE "llilh	\reg,0",					\
+		__stringify(llilh	\reg, LOWCORE_ALT_ADDRESS >> 16),	\
+		ALT_LOWCORE
+.endm
+
+.macro STMG_LC start, end, savearea
+	ALTERNATIVE "stmg	\start, \end, \savearea",				\
+		__stringify(stmg	\start, \end, LOWCORE_ALT_ADDRESS + \savearea),	\
+		ALT_LOWCORE
+.endm
+
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_S390_LOWCORE_H */
diff --git a/arch/s390/include/asm/nospec-branch.h b/arch/s390/include/asm/nospec-branch.h
index b9c1f3c..192835a 100644
--- a/arch/s390/include/asm/nospec-branch.h
+++ b/arch/s390/include/asm/nospec-branch.h
@@ -5,8 +5,17 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <asm/facility.h>
 
 extern int nospec_disable;
+extern int nobp;
+
+static inline bool nobp_enabled(void)
+{
+	if (__is_defined(__DECOMPRESSOR))
+		return false;
+	return nobp && test_facility(82);
+}
 
 void nospec_init_branches(void);
 void nospec_auto_detect(void);
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 5ec41ec..06416b3 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -174,12 +174,10 @@ static inline int devmem_is_allowed(unsigned long pfn)
 #define HAVE_ARCH_FREE_PAGE
 #define HAVE_ARCH_ALLOC_PAGE
 
-#if IS_ENABLED(CONFIG_PGSTE)
 int arch_make_folio_accessible(struct folio *folio);
 #define HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
 int arch_make_page_accessible(struct page *page);
 #define HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
-#endif
 
 struct vm_layout {
 	unsigned long kaslr_offset;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index c87cf2b..5ecd442 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,13 +14,11 @@
 
 #include <linux/bits.h>
 
-#define CIF_SIE			0	/* CPU needs SIE exit cleanup */
 #define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 #define CIF_ENABLED_WAIT	5	/* in enabled wait state */
 #define CIF_MCCK_GUEST		6	/* machine check happening in guest */
 #define CIF_DEDICATED_CPU	7	/* this CPU is dedicated */
 
-#define _CIF_SIE		BIT(CIF_SIE)
 #define _CIF_NOHZ_DELAY		BIT(CIF_NOHZ_DELAY)
 #define _CIF_ENABLED_WAIT	BIT(CIF_ENABLED_WAIT)
 #define _CIF_MCCK_GUEST		BIT(CIF_MCCK_GUEST)
@@ -42,21 +40,37 @@
 #include <asm/irqflags.h>
 #include <asm/alternative.h>
 
+struct pcpu {
+	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
+	unsigned long ec_clk;		/* sigp timestamp for ec_xxx */
+	unsigned long flags;		/* per CPU flags */
+	signed char state;		/* physical cpu state */
+	signed char polarization;	/* physical polarization */
+	u16 address;			/* physical cpu address */
+};
+
+DECLARE_PER_CPU(struct pcpu, pcpu_devices);
+
 typedef long (*sys_call_ptr_t)(struct pt_regs *regs);
 
+static __always_inline struct pcpu *this_pcpu(void)
+{
+	return (struct pcpu *)(get_lowcore()->pcpu);
+}
+
 static __always_inline void set_cpu_flag(int flag)
 {
-	get_lowcore()->cpu_flags |= (1UL << flag);
+	this_pcpu()->flags |= (1UL << flag);
 }
 
 static __always_inline void clear_cpu_flag(int flag)
 {
-	get_lowcore()->cpu_flags &= ~(1UL << flag);
+	this_pcpu()->flags &= ~(1UL << flag);
 }
 
 static __always_inline bool test_cpu_flag(int flag)
 {
-	return get_lowcore()->cpu_flags & (1UL << flag);
+	return this_pcpu()->flags & (1UL << flag);
 }
 
 static __always_inline bool test_and_set_cpu_flag(int flag)
@@ -81,9 +95,7 @@ static __always_inline bool test_and_clear_cpu_flag(int flag)
  */
 static __always_inline bool test_cpu_flag_of(int flag, int cpu)
 {
-	struct lowcore *lc = lowcore_ptr[cpu];
-
-	return lc->cpu_flags & (1UL << flag);
+	return per_cpu(pcpu_devices, cpu).flags & (1UL << flag);
 }
 
 #define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
@@ -405,7 +417,7 @@ static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 
 static __always_inline void bpon(void)
 {
-	asm volatile(ALTERNATIVE("nop", ".insn	rrf,0xb2e80000,0,0,13,0", 82));
+	asm volatile(ALTERNATIVE("nop", ".insn	rrf,0xb2e80000,0,0,13,0", ALT_SPEC(82)));
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/runtime-const.h b/arch/s390/include/asm/runtime-const.h
new file mode 100644
index 0000000..17878b1
--- /dev/null
+++ b/arch/s390/include/asm/runtime-const.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_RUNTIME_CONST_H
+#define _ASM_S390_RUNTIME_CONST_H
+
+#include <linux/uaccess.h>
+
+#define runtime_const_ptr(sym)					\
+({								\
+	typeof(sym) __ret;					\
+								\
+	asm_inline(						\
+		"0:	iihf	%[__ret],%[c1]\n"		\
+		"	iilf	%[__ret],%[c2]\n"		\
+		".pushsection runtime_ptr_" #sym ",\"a\"\n"	\
+		".long 0b - .\n"				\
+		".popsection"					\
+		: [__ret] "=d" (__ret)				\
+		: [c1] "i" (0x01234567UL),			\
+		  [c2] "i" (0x89abcdefUL));			\
+	__ret;							\
+})
+
+#define runtime_const_shift_right_32(val, sym)			\
+({								\
+	unsigned int __ret = (val);				\
+								\
+	asm_inline(						\
+		"0:	srl	%[__ret],12\n"			\
+		".pushsection runtime_shift_" #sym ",\"a\"\n"	\
+		".long 0b - .\n"				\
+		".popsection"					\
+		: [__ret] "+d" (__ret));			\
+	__ret;							\
+})
+
+#define runtime_const_init(type, sym) do {			\
+	extern s32 __start_runtime_##type##_##sym[];		\
+	extern s32 __stop_runtime_##type##_##sym[];		\
+								\
+	runtime_const_fixup(__runtime_fixup_##type,		\
+			    (unsigned long)(sym),		\
+			    __start_runtime_##type##_##sym,	\
+			    __stop_runtime_##type##_##sym);	\
+} while (0)
+
+/* 32-bit immediate for iihf and iilf in bits in I2 field */
+static inline void __runtime_fixup_32(u32 *p, unsigned int val)
+{
+	s390_kernel_write(p, &val, sizeof(val));
+}
+
+static inline void __runtime_fixup_ptr(void *where, unsigned long val)
+{
+	__runtime_fixup_32(where + 2, val >> 32);
+	__runtime_fixup_32(where + 8, val);
+}
+
+/* Immediate value is lower 12 bits of D2 field of srl */
+static inline void __runtime_fixup_shift(void *where, unsigned long val)
+{
+	u32 insn = *(u32 *)where;
+
+	insn &= 0xfffff000;
+	insn |= (val & 63);
+	s390_kernel_write(where, &insn, sizeof(insn));
+}
+
+static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
+				       unsigned long val, s32 *start, s32 *end)
+{
+	while (start < end) {
+		fn(*start + (void *)start, val);
+		start++;
+	}
+}
+
+#endif /* _ASM_S390_RUNTIME_CONST_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index c13c790..cd835f4 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -24,7 +24,6 @@ extern int __cpu_up(unsigned int cpu, struct task_struct *tidle);
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-extern void smp_call_online_cpu(void (*func)(void *), void *);
 extern void smp_call_ipl_cpu(void (*func)(void *), void *);
 extern void smp_emergency_stop(void);
 
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 3e43c90..77d5e80 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -79,7 +79,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
 	typecheck(int, lp->lock);
 	kcsan_release();
 	asm_inline volatile(
-		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */
+		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,7,0", ALT_FACILITY(49)) /* NIAI 7 */
 		"	sth	%1,%0\n"
 		: "=R" (((unsigned short *) &lp->lock)[1])
 		: "d" (0) : "cc", "memory");
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index d02a709..00ac018 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -40,6 +40,7 @@ struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
 	unsigned int		cpu;		/* current CPU */
+	unsigned char		sie;		/* running in SIE context */
 };
 
 /*
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 9213be0..a81f897 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -332,7 +332,14 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return __clear_user(to, n);
 }
 
-void *s390_kernel_write(void *dst, const void *src, size_t size);
+void *__s390_kernel_write(void *dst, const void *src, size_t size);
+
+static inline void *s390_kernel_write(void *dst, const void *src, size_t size)
+{
+	if (__is_defined(__DECOMPRESSOR))
+		return memcpy(dst, src, size);
+	return __s390_kernel_write(dst, src, size);
+}
 
 int __noreturn __put_kernel_bad(void);
 
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index 0679445..0b5f8f3 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -414,7 +414,6 @@ static inline bool uv_has_feature(u8 feature_bit)
 	return test_bit_inv(feature_bit, &uv_info.uv_feature_indications);
 }
 
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 extern int prot_virt_guest;
 
 static inline int is_prot_virt_guest(void)
@@ -466,13 +465,6 @@ static inline int uv_remove_shared(unsigned long addr)
 	return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
 }
 
-#else
-#define is_prot_virt_guest() 0
-static inline int uv_set_shared(unsigned long addr) { return 0; }
-static inline int uv_remove_shared(unsigned long addr) { return 0; }
-#endif
-
-#if IS_ENABLED(CONFIG_KVM)
 extern int prot_virt_host;
 
 static inline int is_prot_virt_host(void)
@@ -489,29 +481,5 @@ int uv_convert_from_secure_pte(pte_t pte);
 int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
 
 void setup_uv(void);
-#else
-#define is_prot_virt_host() 0
-static inline void setup_uv(void) {}
-
-static inline int uv_pin_shared(unsigned long paddr)
-{
-	return 0;
-}
-
-static inline int uv_destroy_folio(struct folio *folio)
-{
-	return 0;
-}
-
-static inline int uv_destroy_pte(pte_t pte)
-{
-	return 0;
-}
-
-static inline int uv_convert_from_secure_pte(pte_t pte)
-{
-	return 0;
-}
-#endif
 
 #endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 7241fa1..e47a4be 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -43,7 +43,7 @@
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
-obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o
+obj-y	+= smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o uv.o
 
 extra-y				+= vmlinux.lds
 
@@ -80,7 +80,6 @@
 obj-$(CONFIG_PERF_EVENTS)	+= perf_pai_crypto.o perf_pai_ext.o
 
 obj-$(CONFIG_TRACEPOINTS)	+= trace.o
-obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE))	+= uv.o
 
 # vdso
 obj-y				+= vdso64/
diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c
index f9efc54..09cd24c 100644
--- a/arch/s390/kernel/abs_lowcore.c
+++ b/arch/s390/kernel/abs_lowcore.c
@@ -4,6 +4,7 @@
 #include <asm/abs_lowcore.h>
 
 unsigned long __bootdata_preserved(__abs_lowcore);
+int __bootdata_preserved(relocate_lowcore);
 
 int abs_lowcore_map(int cpu, struct lowcore *lc, bool alloc)
 {
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 1ac5f70..8d5d0de 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -1,68 +1,41 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <asm/text-patching.h>
+
+#include <linux/uaccess.h>
+#include <asm/nospec-branch.h>
+#include <asm/abs_lowcore.h>
 #include <asm/alternative.h>
 #include <asm/facility.h>
-#include <asm/nospec-branch.h>
 
-static int __initdata_or_module alt_instr_disabled;
-
-static int __init disable_alternative_instructions(char *str)
+void __apply_alternatives(struct alt_instr *start, struct alt_instr *end, unsigned int ctx)
 {
-	alt_instr_disabled = 1;
-	return 0;
-}
-
-early_param("noaltinstr", disable_alternative_instructions);
-
-static void __init_or_module __apply_alternatives(struct alt_instr *start,
-						  struct alt_instr *end)
-{
-	struct alt_instr *a;
 	u8 *instr, *replacement;
+	struct alt_instr *a;
+	bool replace;
 
 	/*
 	 * The scan order should be from start to end. A later scanned
 	 * alternative code can overwrite previously scanned alternative code.
 	 */
 	for (a = start; a < end; a++) {
+		if (!(a->ctx & ctx))
+			continue;
+		switch (a->type) {
+		case ALT_TYPE_FACILITY:
+			replace = test_facility(a->data);
+			break;
+		case ALT_TYPE_SPEC:
+			replace = nobp_enabled();
+			break;
+		case ALT_TYPE_LOWCORE:
+			replace = have_relocated_lowcore();
+			break;
+		default:
+			replace = false;
+		}
+		if (!replace)
+			continue;
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-
-		if (!__test_facility(a->facility, alt_stfle_fac_list))
-			continue;
 		s390_kernel_write(instr, replacement, a->instrlen);
 	}
 }
-
-void __init_or_module apply_alternatives(struct alt_instr *start,
-					 struct alt_instr *end)
-{
-	if (!alt_instr_disabled)
-		__apply_alternatives(start, end);
-}
-
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-void __init apply_alternative_instructions(void)
-{
-	apply_alternatives(__alt_instructions, __alt_instructions_end);
-}
-
-static void do_sync_core(void *info)
-{
-	sync_core();
-}
-
-void text_poke_sync(void)
-{
-	on_each_cpu(do_sync_core, NULL, 1);
-}
-
-void text_poke_sync_lock(void)
-{
-	cpus_read_lock();
-	text_poke_sync();
-	cpus_read_unlock();
-}
diff --git a/arch/s390/kernel/alternative.h b/arch/s390/kernel/alternative.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/arch/s390/kernel/alternative.h
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 26bb45d..ffa0dd2 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -28,6 +28,7 @@ int main(void)
 	BLANK();
 	/* thread info offsets */
 	OFFSET(__TI_flags, task_struct, thread_info.flags);
+	OFFSET(__TI_sie, task_struct, thread_info.sie);
 	BLANK();
 	/* pt_regs offsets */
 	OFFSET(__PT_PSW, pt_regs, psw);
@@ -114,7 +115,7 @@ int main(void)
 	OFFSET(__LC_SAVE_AREA_SYNC, lowcore, save_area_sync);
 	OFFSET(__LC_SAVE_AREA_ASYNC, lowcore, save_area_async);
 	OFFSET(__LC_SAVE_AREA_RESTART, lowcore, save_area_restart);
-	OFFSET(__LC_CPU_FLAGS, lowcore, cpu_flags);
+	OFFSET(__LC_PCPU, lowcore, pcpu);
 	OFFSET(__LC_RETURN_PSW, lowcore, return_psw);
 	OFFSET(__LC_RETURN_MCCK_PSW, lowcore, return_mcck_psw);
 	OFFSET(__LC_SYS_ENTER_TIMER, lowcore, sys_enter_timer);
@@ -186,5 +187,7 @@ int main(void)
 #endif
 	OFFSET(__FTRACE_REGS_PT_REGS, ftrace_regs, regs);
 	DEFINE(__FTRACE_REGS_SIZE, sizeof(struct ftrace_regs));
+
+	OFFSET(__PCPU_FLAGS, pcpu, flags);
 	return 0;
 }
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 85328a0..bce50ca 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -954,7 +954,7 @@ static int debug_active = 1;
  * always allow read, allow write only if debug_stoppable is set or
  * if debug_active is already off
  */
-static int s390dbf_procactive(struct ctl_table *table, int write,
+static int s390dbf_procactive(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!write || debug_stoppable || !debug_active)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 467ed4d..14d3248 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -48,6 +48,7 @@ decompressor_handled_param(dfltcc);
 decompressor_handled_param(facilities);
 decompressor_handled_param(nokaslr);
 decompressor_handled_param(cmma);
+decompressor_handled_param(relocate_lowcore);
 #if IS_ENABLED(CONFIG_KVM)
 decompressor_handled_param(prot_virt);
 #endif
@@ -190,13 +191,6 @@ static noinline __init void setup_lowcore_early(void)
 	get_lowcore()->preempt_count = INIT_PREEMPT_COUNT;
 }
 
-static noinline __init void setup_facility_list(void)
-{
-	memcpy(alt_stfle_fac_list, stfle_fac_list, sizeof(alt_stfle_fac_list));
-	if (!IS_ENABLED(CONFIG_KERNEL_NOBP))
-		__clear_facility(82, alt_stfle_fac_list);
-}
-
 static __init void detect_diag9c(void)
 {
 	unsigned int cpu_address;
@@ -291,7 +285,6 @@ void __init startup_init(void)
 	lockdep_off();
 	sort_amode31_extable();
 	setup_lowcore_early();
-	setup_facility_list();
 	detect_machine_type();
 	setup_arch_string();
 	setup_boot_command_line();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 454b6b9..749410c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/asm-extable.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/dwarf.h>
@@ -28,49 +28,54 @@
 #include <asm/setup.h>
 #include <asm/nmi.h>
 #include <asm/nospec-insn.h>
+#include <asm/lowcore.h>
 
 _LPP_OFFSET	= __LC_LPP
 
 	.macro STBEAR address
-	ALTERNATIVE "nop", ".insn s,0xb2010000,\address", 193
+	ALTERNATIVE "nop", ".insn s,0xb2010000,\address", ALT_FACILITY(193)
 	.endm
 
 	.macro LBEAR address
-	ALTERNATIVE "nop", ".insn s,0xb2000000,\address", 193
+	ALTERNATIVE "nop", ".insn s,0xb2000000,\address", ALT_FACILITY(193)
 	.endm
 
-	.macro LPSWEY address,lpswe
-	ALTERNATIVE "b \lpswe; nopr", ".insn siy,0xeb0000000071,\address,0", 193
+	.macro LPSWEY address, lpswe
+	ALTERNATIVE_2 "b \lpswe;nopr", \
+		".insn siy,0xeb0000000071,\address,0", ALT_FACILITY_EARLY(193),		\
+		__stringify(.insn siy,0xeb0000000071,LOWCORE_ALT_ADDRESS+\address,0),	\
+		ALT_LOWCORE
 	.endm
 
-	.macro MBEAR reg
-	ALTERNATIVE "brcl 0,0", __stringify(mvc __PT_LAST_BREAK(8,\reg),__LC_LAST_BREAK), 193
+	.macro MBEAR reg, lowcore
+	ALTERNATIVE "brcl 0,0", __stringify(mvc __PT_LAST_BREAK(8,\reg),__LC_LAST_BREAK(\lowcore)),\
+		ALT_FACILITY(193)
 	.endm
 
-	.macro	CHECK_STACK savearea
+	.macro	CHECK_STACK savearea, lowcore
 #ifdef CONFIG_CHECK_STACK
 	tml	%r15,THREAD_SIZE - CONFIG_STACK_GUARD
-	lghi	%r14,\savearea
+	la	%r14,\savearea(\lowcore)
 	jz	stack_overflow
 #endif
 	.endm
 
-	.macro	CHECK_VMAP_STACK savearea,oklabel
+	.macro	CHECK_VMAP_STACK savearea, lowcore, oklabel
 #ifdef CONFIG_VMAP_STACK
 	lgr	%r14,%r15
 	nill	%r14,0x10000 - THREAD_SIZE
 	oill	%r14,STACK_INIT_OFFSET
-	clg	%r14,__LC_KERNEL_STACK
+	clg	%r14,__LC_KERNEL_STACK(\lowcore)
 	je	\oklabel
-	clg	%r14,__LC_ASYNC_STACK
+	clg	%r14,__LC_ASYNC_STACK(\lowcore)
 	je	\oklabel
-	clg	%r14,__LC_MCCK_STACK
+	clg	%r14,__LC_MCCK_STACK(\lowcore)
 	je	\oklabel
-	clg	%r14,__LC_NODAT_STACK
+	clg	%r14,__LC_NODAT_STACK(\lowcore)
 	je	\oklabel
-	clg	%r14,__LC_RESTART_STACK
+	clg	%r14,__LC_RESTART_STACK(\lowcore)
 	je	\oklabel
-	lghi	%r14,\savearea
+	la	%r14,\savearea(\lowcore)
 	j	stack_overflow
 #else
 	j	\oklabel
@@ -100,30 +105,31 @@
 	.endm
 
 	.macro BPOFF
-	ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,12,0", 82
+	ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,12,0", ALT_SPEC(82)
 	.endm
 
 	.macro BPON
-	ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,13,0", 82
+	ALTERNATIVE "nop", ".insn rrf,0xb2e80000,0,0,13,0", ALT_SPEC(82)
 	.endm
 
 	.macro BPENTER tif_ptr,tif_mask
 	ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .insn rrf,0xb2e80000,0,0,13,0", \
-		    "j .+12; nop; nop", 82
+		    "j .+12; nop; nop", ALT_SPEC(82)
 	.endm
 
 	.macro BPEXIT tif_ptr,tif_mask
 	TSTMSK	\tif_ptr,\tif_mask
 	ALTERNATIVE "jz .+8;  .insn rrf,0xb2e80000,0,0,12,0", \
-		    "jnz .+8; .insn rrf,0xb2e80000,0,0,13,0", 82
+		    "jnz .+8; .insn rrf,0xb2e80000,0,0,13,0", ALT_SPEC(82)
 	.endm
 
 #if IS_ENABLED(CONFIG_KVM)
-	.macro SIEEXIT sie_control
-	lg	%r9,\sie_control		# get control block pointer
-	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE	# load primary asce
-	ni	__LC_CPU_FLAGS+7,255-_CIF_SIE
+	.macro SIEEXIT sie_control,lowcore
+	lg	%r9,\sie_control			# get control block pointer
+	ni	__SIE_PROG0C+3(%r9),0xfe		# no longer in SIE
+	lctlg	%c1,%c1,__LC_KERNEL_ASCE(\lowcore)	# load primary asce
+	lg	%r9,__LC_CURRENT(\lowcore)
+	mvi	__TI_sie(%r9),0
 	larl	%r9,sie_exit			# skip forward to sie_exit
 	.endm
 #endif
@@ -163,13 +169,14 @@
 	stg	%r15,__THREAD_ksp(%r1,%r2)	# store kernel stack of prev
 	lg	%r15,0(%r4,%r3)			# start of kernel stack of next
 	agr	%r15,%r5			# end of kernel stack of next
-	stg	%r3,__LC_CURRENT		# store task struct of next
-	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
+	GET_LC	%r13
+	stg	%r3,__LC_CURRENT(%r13)		# store task struct of next
+	stg	%r15,__LC_KERNEL_STACK(%r13)	# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1,%r3)	# load kernel stack of next
 	aghi	%r3,__TASK_pid
-	mvc	__LC_CURRENT_PID(4,%r0),0(%r3)	# store pid of next
+	mvc	__LC_CURRENT_PID(4,%r13),0(%r3)	# store pid of next
+	ALTERNATIVE "nop", "lpp _LPP_OFFSET(%r13)", ALT_FACILITY(40)
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
-	ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40
 	BR_EX	%r14
 SYM_FUNC_END(__switch_to_asm)
 
@@ -183,15 +190,16 @@
  */
 SYM_FUNC_START(__sie64a)
 	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
-	lg	%r12,__LC_CURRENT
+	GET_LC	%r13
+	lg	%r14,__LC_CURRENT(%r13)
 	stg	%r2,__SF_SIE_CONTROL_PHYS(%r15)	# save sie block physical..
 	stg	%r3,__SF_SIE_CONTROL(%r15)	# ...and virtual addresses
 	stg	%r4,__SF_SIE_SAVEAREA(%r15)	# save guest register save area
 	stg	%r5,__SF_SIE_GUEST_ASCE(%r15)	# save guest asce
 	xc	__SF_SIE_REASON(8,%r15),__SF_SIE_REASON(%r15) # reason code = 0
-	mvc	__SF_SIE_FLAGS(8,%r15),__TI_flags(%r12) # copy thread flags
+	mvc	__SF_SIE_FLAGS(8,%r15),__TI_flags(%r14) # copy thread flags
 	lmg	%r0,%r13,0(%r4)			# load guest gprs 0-13
-	oi	__LC_CPU_FLAGS+7,_CIF_SIE
+	mvi	__TI_sie(%r14),1
 	lctlg	%c1,%c1,__SF_SIE_GUEST_ASCE(%r15) # load primary asce
 	lg	%r14,__SF_SIE_CONTROL(%r15)	# get control block pointer
 	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
@@ -210,8 +218,10 @@
 .Lsie_skip:
 	lg	%r14,__SF_SIE_CONTROL(%r15)	# get control block pointer
 	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE	# load primary asce
-	ni	__LC_CPU_FLAGS+7,255-_CIF_SIE
+	GET_LC	%r14
+	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r14)	# load primary asce
+	lg	%r14,__LC_CURRENT(%r14)
+	mvi	__TI_sie(%r14),0
 # some program checks are suppressing. C code (e.g. do_protection_exception)
 # will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
 # are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
@@ -254,14 +264,15 @@
  */
 
 SYM_CODE_START(system_call)
-	stpt	__LC_SYS_ENTER_TIMER
-	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
+	STMG_LC	%r8,%r15,__LC_SAVE_AREA_SYNC
+	GET_LC	%r13
+	stpt	__LC_SYS_ENTER_TIMER(%r13)
 	BPOFF
 	lghi	%r14,0
 .Lsysc_per:
-	STBEAR	__LC_LAST_BREAK
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE
-	lg	%r15,__LC_KERNEL_STACK
+	STBEAR	__LC_LAST_BREAK(%r13)
+	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
+	lg	%r15,__LC_KERNEL_STACK(%r13)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	stmg	%r0,%r7,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
 	# clear user controlled register to prevent speculative use
@@ -276,17 +287,17 @@
 	xgr	%r10,%r10
 	xgr	%r11,%r11
 	la	%r2,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
-	mvc	__PT_R8(64,%r2),__LC_SAVE_AREA_SYNC
-	MBEAR	%r2
+	mvc	__PT_R8(64,%r2),__LC_SAVE_AREA_SYNC(%r13)
+	MBEAR	%r2,%r13
 	lgr	%r3,%r14
 	brasl	%r14,__do_syscall
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE
-	mvc	__LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
+	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
+	mvc	__LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
 	BPON
 	LBEAR	STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
+	stpt	__LC_EXIT_TIMER(%r13)
 	lmg	%r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
-	stpt	__LC_EXIT_TIMER
 	LPSWEY	__LC_RETURN_PSW,__LC_RETURN_LPSWE
 SYM_CODE_END(system_call)
 
@@ -297,12 +308,13 @@
 	lgr	%r3,%r11
 	brasl	%r14,__ret_from_fork
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE
-	mvc	__LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
+	GET_LC	%r13
+	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
+	mvc	__LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
 	BPON
 	LBEAR	STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
+	stpt	__LC_EXIT_TIMER(%r13)
 	lmg	%r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
-	stpt	__LC_EXIT_TIMER
 	LPSWEY	__LC_RETURN_PSW,__LC_RETURN_LPSWE
 SYM_CODE_END(ret_from_fork)
 
@@ -311,39 +323,40 @@
  */
 
 SYM_CODE_START(pgm_check_handler)
-	stpt	__LC_SYS_ENTER_TIMER
+	STMG_LC	%r8,%r15,__LC_SAVE_AREA_SYNC
+	GET_LC	%r13
+	stpt	__LC_SYS_ENTER_TIMER(%r13)
 	BPOFF
-	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lgr	%r10,%r15
-	lmg	%r8,%r9,__LC_PGM_OLD_PSW
+	lmg	%r8,%r9,__LC_PGM_OLD_PSW(%r13)
 	tmhh	%r8,0x0001		# coming from user space?
 	jno	.Lpgm_skip_asce
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE
+	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
 	j	3f			# -> fault in user space
 .Lpgm_skip_asce:
 1:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
 	jnz	2f			# -> enabled, can't be a double fault
-	tm	__LC_PGM_ILC+3,0x80	# check for per exception
+	tm	__LC_PGM_ILC+3(%r13),0x80	# check for per exception
 	jnz	.Lpgm_svcper		# -> single stepped svc
-2:	CHECK_STACK __LC_SAVE_AREA_SYNC
+2:	CHECK_STACK __LC_SAVE_AREA_SYNC,%r13
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	# CHECK_VMAP_STACK branches to stack_overflow or 4f
-	CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f
-3:	lg	%r15,__LC_KERNEL_STACK
+	CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,%r13,4f
+3:	lg	%r15,__LC_KERNEL_STACK(%r13)
 4:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
-	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
-	mvc	__PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC(%r13)
+	mvc	__PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK(%r13)
 	stctg	%c1,%c1,__PT_CR1(%r11)
 #if IS_ENABLED(CONFIG_KVM)
-	ltg	%r12,__LC_GMAP
+	ltg	%r12,__LC_GMAP(%r13)
 	jz	5f
 	clc	__GMAP_ASCE(8,%r12), __PT_CR1(%r11)
 	jne	5f
 	BPENTER	__SF_SIE_FLAGS(%r10),_TIF_ISOLATE_BP_GUEST
-	SIEEXIT __SF_SIE_CONTROL(%r10)
+	SIEEXIT __SF_SIE_CONTROL(%r10),%r13
 #endif
 5:	stmg	%r8,%r9,__PT_PSW(%r11)
 	# clear user controlled registers to prevent speculative use
@@ -359,11 +372,11 @@
 	tmhh	%r8,0x0001		# returning to user space?
 	jno	.Lpgm_exit_kernel
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE
+	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	BPON
-	stpt	__LC_EXIT_TIMER
+	stpt	__LC_EXIT_TIMER(%r13)
 .Lpgm_exit_kernel:
-	mvc	__LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
+	mvc	__LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
 	LBEAR	STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
 	lmg	%r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
 	LPSWEY	__LC_RETURN_PSW,__LC_RETURN_LPSWE
@@ -372,11 +385,11 @@
 # single stepped system call
 #
 .Lpgm_svcper:
-	mvc	__LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
+	mvc	__LC_RETURN_PSW(8,%r13),__LC_SVC_NEW_PSW(%r13)
 	larl	%r14,.Lsysc_per
-	stg	%r14,__LC_RETURN_PSW+8
+	stg	%r14,__LC_RETURN_PSW+8(%r13)
 	lghi	%r14,1
-	LBEAR	__LC_PGM_LAST_BREAK
+	LBEAR	__LC_PGM_LAST_BREAK(%r13)
 	LPSWEY	__LC_RETURN_PSW,__LC_RETURN_LPSWE # branch to .Lsysc_per
 SYM_CODE_END(pgm_check_handler)
 
@@ -385,25 +398,27 @@
  */
 .macro INT_HANDLER name,lc_old_psw,handler
 SYM_CODE_START(\name)
-	stckf	__LC_INT_CLOCK
-	stpt	__LC_SYS_ENTER_TIMER
-	STBEAR	__LC_LAST_BREAK
+	STMG_LC	%r8,%r15,__LC_SAVE_AREA_ASYNC
+	GET_LC	%r13
+	stckf	__LC_INT_CLOCK(%r13)
+	stpt	__LC_SYS_ENTER_TIMER(%r13)
+	STBEAR	__LC_LAST_BREAK(%r13)
 	BPOFF
-	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
-	lmg	%r8,%r9,\lc_old_psw
+	lmg	%r8,%r9,\lc_old_psw(%r13)
 	tmhh	%r8,0x0001			# interrupting from user ?
 	jnz	1f
 #if IS_ENABLED(CONFIG_KVM)
-	TSTMSK	__LC_CPU_FLAGS,_CIF_SIE
+	lg	%r10,__LC_CURRENT(%r13)
+	tm	__TI_sie(%r10),0xff
 	jz	0f
 	BPENTER	__SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
-	SIEEXIT __SF_SIE_CONTROL(%r15)
+	SIEEXIT __SF_SIE_CONTROL(%r15),%r13
 #endif
-0:	CHECK_STACK __LC_SAVE_AREA_ASYNC
+0:	CHECK_STACK __LC_SAVE_AREA_ASYNC,%r13
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	2f
-1:	lctlg	%c1,%c1,__LC_KERNEL_ASCE
-	lg	%r15,__LC_KERNEL_STACK
+1:	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
+	lg	%r15,__LC_KERNEL_STACK(%r13)
 2:	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
@@ -417,18 +432,18 @@
 	xgr	%r7,%r7
 	xgr	%r10,%r10
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
-	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
-	MBEAR	%r11
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC(%r13)
+	MBEAR	%r11,%r13
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,\handler
-	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+	mvc	__LC_RETURN_PSW(16,%r13),__PT_PSW(%r11)
 	tmhh	%r8,0x0001		# returning to user ?
 	jno	2f
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE
+	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	BPON
-	stpt	__LC_EXIT_TIMER
+	stpt	__LC_EXIT_TIMER(%r13)
 2:	LBEAR	__PT_LAST_BREAK(%r11)
 	lmg	%r0,%r15,__PT_R0(%r11)
 	LPSWEY	__LC_RETURN_PSW,__LC_RETURN_LPSWE
@@ -443,35 +458,37 @@
  */
 SYM_CODE_START(mcck_int_handler)
 	BPOFF
-	lmg	%r8,%r9,__LC_MCK_OLD_PSW
-	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE
+	GET_LC	%r13
+	lmg	%r8,%r9,__LC_MCK_OLD_PSW(%r13)
+	TSTMSK	__LC_MCCK_CODE(%r13),MCCK_CODE_SYSTEM_DAMAGE
 	jo	.Lmcck_panic		# yes -> rest of mcck code invalid
-	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_CR_VALID
+	TSTMSK	__LC_MCCK_CODE(%r13),MCCK_CODE_CR_VALID
 	jno	.Lmcck_panic		# control registers invalid -> panic
 	ptlb
-	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
-	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
-	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_CPU_TIMER_VALID
+	lay	%r14,__LC_CPU_TIMER_SAVE_AREA(%r13)
+	mvc	__LC_MCCK_ENTER_TIMER(8,%r13),0(%r14)
+	TSTMSK	__LC_MCCK_CODE(%r13),MCCK_CODE_CPU_TIMER_VALID
 	jo	3f
-	la	%r14,__LC_SYS_ENTER_TIMER
-	clc	0(8,%r14),__LC_EXIT_TIMER
+	la	%r14,__LC_SYS_ENTER_TIMER(%r13)
+	clc	0(8,%r14),__LC_EXIT_TIMER(%r13)
 	jl	1f
-	la	%r14,__LC_EXIT_TIMER
-1:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
+	la	%r14,__LC_EXIT_TIMER(%r13)
+1:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER(%r13)
 	jl	2f
-	la	%r14,__LC_LAST_UPDATE_TIMER
+	la	%r14,__LC_LAST_UPDATE_TIMER(%r13)
 2:	spt	0(%r14)
-	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
-3:	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_PSW_MWP_VALID
+	mvc	__LC_MCCK_ENTER_TIMER(8,%r13),0(%r14)
+3:	TSTMSK	__LC_MCCK_CODE(%r13),MCCK_CODE_PSW_MWP_VALID
 	jno	.Lmcck_panic
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jnz	.Lmcck_user
-	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID
+	TSTMSK	__LC_MCCK_CODE(%r13),MCCK_CODE_PSW_IA_VALID
 	jno	.Lmcck_panic
 #if IS_ENABLED(CONFIG_KVM)
-	TSTMSK	__LC_CPU_FLAGS,_CIF_SIE
+	lg	%r10,__LC_CURRENT(%r13)
+	tm	__TI_sie(%r10),0xff
 	jz	.Lmcck_user
-	# Need to compare the address instead of a CIF_SIE* flag.
+	# Need to compare the address instead of __TI_SIE flag.
 	# Otherwise there would be a race between setting the flag
 	# and entering SIE (or leaving and clearing the flag). This
 	# would cause machine checks targeted at the guest to be
@@ -480,18 +497,19 @@
 	clgrjl	%r9,%r14, 4f
 	larl	%r14,.Lsie_leave
 	clgrjhe	%r9,%r14, 4f
-	oi	__LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
+	lg	%r10,__LC_PCPU
+	oi	__PCPU_FLAGS+7(%r10), _CIF_MCCK_GUEST
 4:	BPENTER	__SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
-	SIEEXIT __SF_SIE_CONTROL(%r15)
+	SIEEXIT __SF_SIE_CONTROL(%r15),%r13
 #endif
 .Lmcck_user:
-	lg	%r15,__LC_MCCK_STACK
+	lg	%r15,__LC_MCCK_STACK(%r13)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stctg	%c1,%c1,__PT_CR1(%r11)
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE
+	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-	lghi	%r14,__LC_GPREGS_SAVE_AREA+64
-	stmg	%r0,%r7,__PT_R0(%r11)
+	lay	%r14,__LC_GPREGS_SAVE_AREA(%r13)
+	mvc	__PT_R0(128,%r11),0(%r14)
 	# clear user controlled registers to prevent speculative use
 	xgr	%r0,%r0
 	xgr	%r1,%r1
@@ -501,7 +519,6 @@
 	xgr	%r6,%r6
 	xgr	%r7,%r7
 	xgr	%r10,%r10
-	mvc	__PT_R8(64,%r11),0(%r14)
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
@@ -509,12 +526,13 @@
 	brasl	%r14,s390_do_machine_check
 	lctlg	%c1,%c1,__PT_CR1(%r11)
 	lmg	%r0,%r10,__PT_R0(%r11)
-	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
-	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
+	mvc	__LC_RETURN_MCCK_PSW(16,%r13),__PT_PSW(%r11) # move return PSW
+	tm	__LC_RETURN_MCCK_PSW+1(%r13),0x01 # returning to user ?
 	jno	0f
 	BPON
-	stpt	__LC_EXIT_TIMER
-0:	ALTERNATIVE "nop", __stringify(lghi %r12,__LC_LAST_BREAK_SAVE_AREA),193
+	stpt	__LC_EXIT_TIMER(%r13)
+0:	ALTERNATIVE "brcl 0,0", __stringify(lay %r12,__LC_LAST_BREAK_SAVE_AREA(%r13)),\
+		ALT_FACILITY(193)
 	LBEAR	0(%r12)
 	lmg	%r11,%r15,__PT_R11(%r11)
 	LPSWEY	__LC_RETURN_MCCK_PSW,__LC_RETURN_MCCK_LPSWE
@@ -550,7 +568,7 @@
 SYM_CODE_END(mcck_int_handler)
 
 SYM_CODE_START(restart_int_handler)
-	ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40
+	ALTERNATIVE "nop", "lpp _LPP_OFFSET", ALT_FACILITY(40)
 	stg	%r15,__LC_SAVE_AREA_RESTART
 	TSTMSK	__LC_RESTART_FLAGS,RESTART_FLAG_CTLREGS,4
 	jz	0f
@@ -558,15 +576,17 @@
 0:	larl	%r15,daton_psw
 	lpswe	0(%r15)				# turn dat on, keep irqs off
 .Ldaton:
-	lg	%r15,__LC_RESTART_STACK
+	GET_LC	%r15
+	lg	%r15,__LC_RESTART_STACK(%r15)
 	xc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r15),STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r14,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
-	mvc	STACK_FRAME_OVERHEAD+__PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
-	mvc	STACK_FRAME_OVERHEAD+__PT_PSW(16,%r15),__LC_RST_OLD_PSW
+	GET_LC	%r13
+	mvc	STACK_FRAME_OVERHEAD+__PT_R15(8,%r15),__LC_SAVE_AREA_RESTART(%r13)
+	mvc	STACK_FRAME_OVERHEAD+__PT_PSW(16,%r15),__LC_RST_OLD_PSW(%r13)
 	xc	0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
-	lg	%r1,__LC_RESTART_FN		# load fn, parm & source cpu
-	lg	%r2,__LC_RESTART_DATA
-	lgf	%r3,__LC_RESTART_SOURCE
+	lg	%r1,__LC_RESTART_FN(%r13)	# load fn, parm & source cpu
+	lg	%r2,__LC_RESTART_DATA(%r13)
+	lgf	%r3,__LC_RESTART_SOURCE(%r13)
 	ltgr	%r3,%r3				# test source cpu address
 	jm	1f				# negative -> skip source stop
 0:	sigp	%r4,%r3,SIGP_SENSE		# sigp sense to source cpu
@@ -588,7 +608,8 @@
  * Setup a pt_regs so that show_trace can provide a good call trace.
  */
 SYM_CODE_START(stack_overflow)
-	lg	%r15,__LC_NODAT_STACK	# change to panic stack
+	GET_LC	%r15
+	lg	%r15,__LC_NODAT_STACK(%r15) # change to panic stack
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	stmg	%r8,%r9,__PT_PSW(%r11)
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 45413b0..396034b 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/lowcore.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
@@ -18,14 +19,15 @@
 __HEAD
 SYM_CODE_START(startup_continue)
 	larl	%r1,tod_clock_base
-	mvc	0(16,%r1),__LC_BOOT_CLOCK
+	GET_LC	%r2
+	mvc	0(16,%r1),__LC_BOOT_CLOCK(%r2)
 #
 # Setup stack
 #
 	larl	%r14,init_task
-	stg	%r14,__LC_CURRENT
+	stg	%r14,__LC_CURRENT(%r2)
 	larl	%r15,init_thread_union+STACK_INIT_OFFSET
-	stg	%r15,__LC_KERNEL_STACK
+	stg	%r15,__LC_KERNEL_STACK(%r2)
 	brasl	%r14,sclp_early_adjust_va	# allow sclp_early_printk
 	brasl	%r14,startup_init		# s390 specific early init
 	brasl	%r14,start_kernel		# common init code
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 3a7d6e1..f17bb7b 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2112,7 +2112,7 @@ void do_restart(void *arg)
 	tracing_off();
 	debug_locks_off();
 	lgr_info_log();
-	smp_call_online_cpu(__do_restart, arg);
+	smp_call_ipl_cpu(__do_restart, arg);
 }
 
 /* on halt */
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index f4cf65d..8f681cc 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -62,7 +62,7 @@ static void __do_machine_kdump(void *data)
 	 * This need to be done *after* s390_reset_system set the
 	 * prefix register of this CPU to zero
 	 */
-	memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA),
+	memcpy(absolute_pointer(get_lowcore()->floating_pt_save_area),
 	       phys_to_virt(prefix + __LC_FPREGS_SAVE_AREA), 512);
 
 	call_nodat(1, int, purgatory, int, 1);
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index 9b8c24e..e11ec15 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -4,6 +4,8 @@
 #include <linux/cpu.h>
 #include <asm/nospec-branch.h>
 
+int nobp = IS_ENABLED(CONFIG_KERNEL_NOBP);
+
 static int __init nobp_setup_early(char *str)
 {
 	bool enabled;
@@ -17,11 +19,11 @@ static int __init nobp_setup_early(char *str)
 		 * The user explicitly requested nobp=1, enable it and
 		 * disable the expoline support.
 		 */
-		__set_facility(82, alt_stfle_fac_list);
+		nobp = 1;
 		if (IS_ENABLED(CONFIG_EXPOLINE))
 			nospec_disable = 1;
 	} else {
-		__clear_facility(82, alt_stfle_fac_list);
+		nobp = 0;
 	}
 	return 0;
 }
@@ -29,7 +31,7 @@ early_param("nobp", nobp_setup_early);
 
 static int __init nospec_setup_early(char *str)
 {
-	__clear_facility(82, alt_stfle_fac_list);
+	nobp = 0;
 	return 0;
 }
 early_param("nospec", nospec_setup_early);
@@ -40,7 +42,7 @@ static int __init nospec_report(void)
 		pr_info("Spectre V2 mitigation: etokens\n");
 	if (nospec_uses_trampoline())
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
-	if (__test_facility(82, alt_stfle_fac_list))
+	if (nobp_enabled())
 		pr_info("Spectre V2 mitigation: limited branch prediction\n");
 	return 0;
 }
@@ -66,14 +68,14 @@ void __init nospec_auto_detect(void)
 		 */
 		if (__is_defined(CC_USING_EXPOLINE))
 			nospec_disable = 1;
-		__clear_facility(82, alt_stfle_fac_list);
+		nobp = 0;
 	} else if (__is_defined(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
 		 */
 		nospec_disable = 0;
-		__clear_facility(82, alt_stfle_fac_list);
+		nobp = 0;
 	}
 	/*
 	 * If the kernel has not been compiled with expolines the
@@ -86,7 +88,7 @@ static int __init spectre_v2_setup_early(char *str)
 {
 	if (str && !strncmp(str, "on", 2)) {
 		nospec_disable = 0;
-		__clear_facility(82, alt_stfle_fac_list);
+		nobp = 0;
 	}
 	if (str && !strncmp(str, "off", 3))
 		nospec_disable = 1;
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index 52d4353..a951888 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -17,7 +17,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 		return sprintf(buf, "Mitigation: etokens\n");
 	if (nospec_uses_trampoline())
 		return sprintf(buf, "Mitigation: execute trampolines\n");
-	if (__test_facility(82, alt_stfle_fac_list))
+	if (nobp_enabled())
 		return sprintf(buf, "Mitigation: limited branch prediction\n");
 	return sprintf(buf, "Vulnerable\n");
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 1434642..6968be9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -556,25 +556,31 @@ static int cfdiag_diffctr(struct cpu_cf_events *cpuhw, unsigned long auth)
 	struct cf_trailer_entry *trailer_start, *trailer_stop;
 	struct cf_ctrset_entry *ctrstart, *ctrstop;
 	size_t offset = 0;
+	int i;
 
-	auth &= (1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1;
-	do {
+	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
 		ctrstart = (struct cf_ctrset_entry *)(cpuhw->start + offset);
 		ctrstop = (struct cf_ctrset_entry *)(cpuhw->stop + offset);
 
+		/* Counter set not authorized */
+		if (!(auth & cpumf_ctr_ctl[i]))
+			continue;
+		/* Counter set size zero was not saved */
+		if (!cpum_cf_read_setsize(i))
+			continue;
+
 		if (memcmp(ctrstop, ctrstart, sizeof(*ctrstop))) {
 			pr_err_once("cpum_cf_diag counter set compare error "
 				    "in set %i\n", ctrstart->set);
 			return 0;
 		}
-		auth &= ~cpumf_ctr_ctl[ctrstart->set];
 		if (ctrstart->def == CF_DIAG_CTRSET_DEF) {
 			cfdiag_diffctrset((u64 *)(ctrstart + 1),
 					  (u64 *)(ctrstop + 1), ctrstart->ctr);
 			offset += ctrstart->ctr * sizeof(u64) +
 							sizeof(*ctrstart);
 		}
-	} while (ctrstart->def && auth);
+	}
 
 	/* Save time_stamp from start of event in stop's trailer */
 	trailer_start = (struct cf_trailer_entry *)(cpuhw->start + offset);
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 65c1464..5ce9a79 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -17,7 +17,8 @@
 #include <linux/mm_types.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
-
+#include <linux/smp.h>
+#include <asm/text-patching.h>
 #include <asm/diag.h>
 #include <asm/facility.h>
 #include <asm/elf.h>
@@ -79,6 +80,23 @@ void notrace stop_machine_yield(const struct cpumask *cpumask)
 	}
 }
 
+static void do_sync_core(void *info)
+{
+	sync_core();
+}
+
+void text_poke_sync(void)
+{
+	on_each_cpu(do_sync_core, NULL, 1);
+}
+
+void text_poke_sync_lock(void)
+{
+	cpus_read_lock();
+	text_poke_sync();
+	cpus_read_unlock();
+}
+
 /*
  * cpu_init - initializes state that is per-CPU.
  */
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 88087a3..69fcaf5 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -9,6 +9,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/nospec-insn.h>
 #include <asm/sigp.h>
+#include <asm/lowcore.h>
 
 	GEN_BR_THUNK %r9
 
@@ -20,20 +21,15 @@
 # r3 = Parameter for function
 #
 SYM_CODE_START(store_status)
-	/* Save register one and load save area base */
-	stg	%r1,__LC_SAVE_AREA_RESTART
+	STMG_LC	%r0,%r15,__LC_GPREGS_SAVE_AREA
 	/* General purpose registers */
-	lghi	%r1,__LC_GPREGS_SAVE_AREA
-	stmg	%r0,%r15,0(%r1)
-	mvc	8(8,%r1),__LC_SAVE_AREA_RESTART
+	GET_LC	%r13
 	/* Control registers */
-	lghi	%r1,__LC_CREGS_SAVE_AREA
-	stctg	%c0,%c15,0(%r1)
+	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA(%r13)
 	/* Access registers */
-	lghi	%r1,__LC_AREGS_SAVE_AREA
-	stam	%a0,%a15,0(%r1)
+	stamy	%a0,%a15,__LC_AREGS_SAVE_AREA(%r13)
 	/* Floating point registers */
-	lghi	%r1,__LC_FPREGS_SAVE_AREA
+	lay	%r1,__LC_FPREGS_SAVE_AREA(%r13)
 	std	%f0, 0x00(%r1)
 	std	%f1, 0x08(%r1)
 	std	%f2, 0x10(%r1)
@@ -51,21 +47,21 @@
 	std	%f14,0x70(%r1)
 	std	%f15,0x78(%r1)
 	/* Floating point control register */
-	lghi	%r1,__LC_FP_CREG_SAVE_AREA
+	lay	%r1,__LC_FP_CREG_SAVE_AREA(%r13)
 	stfpc	0(%r1)
 	/* CPU timer */
-	lghi	%r1,__LC_CPU_TIMER_SAVE_AREA
+	lay	%r1,__LC_CPU_TIMER_SAVE_AREA(%r13)
 	stpt	0(%r1)
 	/* Store prefix register */
-	lghi	%r1,__LC_PREFIX_SAVE_AREA
+	lay	%r1,__LC_PREFIX_SAVE_AREA(%r13)
 	stpx	0(%r1)
 	/* Clock comparator - seven bytes */
-	lghi	%r1,__LC_CLOCK_COMP_SAVE_AREA
 	larl	%r4,clkcmp
 	stckc	0(%r4)
+	lay	%r1,__LC_CLOCK_COMP_SAVE_AREA(%r13)
 	mvc	1(7,%r1),1(%r4)
 	/* Program status word */
-	lghi	%r1,__LC_PSW_SAVE_AREA
+	lay	%r1,__LC_PSW_SAVE_AREA(%r13)
 	epsw	%r4,%r5
 	st	%r4,0(%r1)
 	st	%r5,4(%r1)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3993f4c..4ec99f7 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -149,13 +149,12 @@ unsigned long __bootdata_preserved(max_mappable);
 struct physmem_info __bootdata(physmem_info);
 
 struct vm_layout __bootdata_preserved(vm_layout);
-EXPORT_SYMBOL_GPL(vm_layout);
+EXPORT_SYMBOL(vm_layout);
 int __bootdata_preserved(__kaslr_enabled);
 unsigned int __bootdata_preserved(zlib_dfltcc_support);
 EXPORT_SYMBOL(zlib_dfltcc_support);
 u64 __bootdata_preserved(stfle_fac_list[16]);
 EXPORT_SYMBOL(stfle_fac_list);
-u64 alt_stfle_fac_list[16];
 struct oldmem_data __bootdata_preserved(oldmem_data);
 
 unsigned long VMALLOC_START;
@@ -406,6 +405,7 @@ static void __init setup_lowcore(void)
 		panic("%s: Failed to allocate %zu bytes align=%zx\n",
 		      __func__, sizeof(*lc), sizeof(*lc));
 
+	lc->pcpu = (unsigned long)per_cpu_ptr(&pcpu_devices, 0);
 	lc->restart_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_DAT;
 	lc->restart_psw.addr = __pa(restart_int_handler);
 	lc->external_new_psw.mask = PSW_KERNEL_BITS;
@@ -889,6 +889,9 @@ void __init setup_arch(char **cmdline_p)
 	else
 		pr_info("Linux is running as a guest in 64-bit mode\n");
 
+	if (have_relocated_lowcore())
+		pr_info("Lowcore relocated to 0x%px\n", get_lowcore());
+
 	log_component_list();
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index c3c54ad..fbba37e 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -74,16 +74,15 @@ enum {
 	CPU_STATE_CONFIGURED,
 };
 
-struct pcpu {
-	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
-	unsigned long ec_clk;		/* sigp timestamp for ec_xxx */
-	signed char state;		/* physical cpu state */
-	signed char polarization;	/* physical polarization */
-	u16 address;			/* physical cpu address */
-};
-
 static u8 boot_core_type;
-static struct pcpu pcpu_devices[NR_CPUS];
+DEFINE_PER_CPU(struct pcpu, pcpu_devices);
+/*
+ * Pointer to the pcpu area of the boot CPU. This is required when a restart
+ * interrupt is triggered on an offline CPU. For that case accessing percpu
+ * data with the common primitives does not work, since the percpu offset is
+ * stored in a non existent lowcore.
+ */
+static struct pcpu *ipl_pcpu;
 
 unsigned int smp_cpu_mt_shift;
 EXPORT_SYMBOL(smp_cpu_mt_shift);
@@ -174,8 +173,8 @@ static struct pcpu *pcpu_find_address(const struct cpumask *mask, u16 address)
 	int cpu;
 
 	for_each_cpu(cpu, mask)
-		if (pcpu_devices[cpu].address == address)
-			return pcpu_devices + cpu;
+		if (per_cpu(pcpu_devices, cpu).address == address)
+			return &per_cpu(pcpu_devices, cpu);
 	return NULL;
 }
 
@@ -230,13 +229,11 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	return -ENOMEM;
 }
 
-static void pcpu_free_lowcore(struct pcpu *pcpu)
+static void pcpu_free_lowcore(struct pcpu *pcpu, int cpu)
 {
 	unsigned long async_stack, nodat_stack, mcck_stack;
 	struct lowcore *lc;
-	int cpu;
 
-	cpu = pcpu - pcpu_devices;
 	lc = lowcore_ptr[cpu];
 	nodat_stack = lc->nodat_stack - STACK_INIT_OFFSET;
 	async_stack = lc->async_stack - STACK_INIT_OFFSET;
@@ -259,6 +256,7 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
 	lc->cpu_nr = cpu;
+	lc->pcpu = (unsigned long)pcpu;
 	lc->restart_flags = RESTART_FLAG_CTLREGS;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->spinlock_index = 0;
@@ -277,12 +275,10 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	arch_spin_lock_setup(cpu);
 }
 
-static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
+static void pcpu_attach_task(int cpu, struct task_struct *tsk)
 {
 	struct lowcore *lc;
-	int cpu;
 
-	cpu = pcpu - pcpu_devices;
 	lc = lowcore_ptr[cpu];
 	lc->kernel_stack = (unsigned long)task_stack_page(tsk) + STACK_INIT_OFFSET;
 	lc->current_task = (unsigned long)tsk;
@@ -296,18 +292,16 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
 	lc->steal_timer = 0;
 }
 
-static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
+static void pcpu_start_fn(int cpu, void (*func)(void *), void *data)
 {
 	struct lowcore *lc;
-	int cpu;
 
-	cpu = pcpu - pcpu_devices;
 	lc = lowcore_ptr[cpu];
 	lc->restart_stack = lc->kernel_stack;
 	lc->restart_fn = (unsigned long) func;
 	lc->restart_data = (unsigned long) data;
 	lc->restart_source = -1U;
-	pcpu_sigp_retry(pcpu, SIGP_RESTART, 0);
+	pcpu_sigp_retry(per_cpu_ptr(&pcpu_devices, cpu), SIGP_RESTART, 0);
 }
 
 typedef void (pcpu_delegate_fn)(void *);
@@ -320,14 +314,14 @@ static void __pcpu_delegate(pcpu_delegate_fn *func, void *data)
 	func(data);	/* should not return */
 }
 
-static void pcpu_delegate(struct pcpu *pcpu,
+static void pcpu_delegate(struct pcpu *pcpu, int cpu,
 			  pcpu_delegate_fn *func,
 			  void *data, unsigned long stack)
 {
 	struct lowcore *lc, *abs_lc;
 	unsigned int source_cpu;
 
-	lc = lowcore_ptr[pcpu - pcpu_devices];
+	lc = lowcore_ptr[cpu];
 	source_cpu = stap();
 
 	if (pcpu->address == source_cpu) {
@@ -377,38 +371,22 @@ static int pcpu_set_smt(unsigned int mtid)
 		smp_cpu_mt_shift = 0;
 		while (smp_cpu_mtid >= (1U << smp_cpu_mt_shift))
 			smp_cpu_mt_shift++;
-		pcpu_devices[0].address = stap();
+		per_cpu(pcpu_devices, 0).address = stap();
 	}
 	return cc;
 }
 
 /*
- * Call function on an online CPU.
- */
-void smp_call_online_cpu(void (*func)(void *), void *data)
-{
-	struct pcpu *pcpu;
-
-	/* Use the current cpu if it is online. */
-	pcpu = pcpu_find_address(cpu_online_mask, stap());
-	if (!pcpu)
-		/* Use the first online cpu. */
-		pcpu = pcpu_devices + cpumask_first(cpu_online_mask);
-	pcpu_delegate(pcpu, func, data, (unsigned long) restart_stack);
-}
-
-/*
  * Call function on the ipl CPU.
  */
 void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
 	struct lowcore *lc = lowcore_ptr[0];
 
-	if (pcpu_devices[0].address == stap())
+	if (ipl_pcpu->address == stap())
 		lc = get_lowcore();
 
-	pcpu_delegate(&pcpu_devices[0], func, data,
-		      lc->nodat_stack);
+	pcpu_delegate(ipl_pcpu, 0, func, data, lc->nodat_stack);
 }
 
 int smp_find_processor_id(u16 address)
@@ -416,21 +394,21 @@ int smp_find_processor_id(u16 address)
 	int cpu;
 
 	for_each_present_cpu(cpu)
-		if (pcpu_devices[cpu].address == address)
+		if (per_cpu(pcpu_devices, cpu).address == address)
 			return cpu;
 	return -1;
 }
 
 void schedule_mcck_handler(void)
 {
-	pcpu_ec_call(pcpu_devices + smp_processor_id(), ec_mcck_pending);
+	pcpu_ec_call(this_cpu_ptr(&pcpu_devices), ec_mcck_pending);
 }
 
 bool notrace arch_vcpu_is_preempted(int cpu)
 {
 	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
 		return false;
-	if (pcpu_running(pcpu_devices + cpu))
+	if (pcpu_running(per_cpu_ptr(&pcpu_devices, cpu)))
 		return false;
 	return true;
 }
@@ -442,7 +420,7 @@ void notrace smp_yield_cpu(int cpu)
 		return;
 	diag_stat_inc_norecursion(DIAG_STAT_X09C);
 	asm volatile("diag %0,0,0x9c"
-		     : : "d" (pcpu_devices[cpu].address));
+		     : : "d" (per_cpu(pcpu_devices, cpu).address));
 }
 EXPORT_SYMBOL_GPL(smp_yield_cpu);
 
@@ -463,7 +441,7 @@ void notrace smp_emergency_stop(void)
 
 	end = get_tod_clock() + (1000000UL << 12);
 	for_each_cpu(cpu, &cpumask) {
-		struct pcpu *pcpu = pcpu_devices + cpu;
+		struct pcpu *pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 		set_bit(ec_stop_cpu, &pcpu->ec_mask);
 		while (__pcpu_sigp(pcpu->address, SIGP_EMERGENCY_SIGNAL,
 				   0, NULL) == SIGP_CC_BUSY &&
@@ -472,7 +450,7 @@ void notrace smp_emergency_stop(void)
 	}
 	while (get_tod_clock() < end) {
 		for_each_cpu(cpu, &cpumask)
-			if (pcpu_stopped(pcpu_devices + cpu))
+			if (pcpu_stopped(per_cpu_ptr(&pcpu_devices, cpu)))
 				cpumask_clear_cpu(cpu, &cpumask);
 		if (cpumask_empty(&cpumask))
 			break;
@@ -487,6 +465,7 @@ NOKPROBE_SYMBOL(smp_emergency_stop);
  */
 void smp_send_stop(void)
 {
+	struct pcpu *pcpu;
 	int cpu;
 
 	/* Disable all interrupts/machine checks */
@@ -502,8 +481,9 @@ void smp_send_stop(void)
 	for_each_online_cpu(cpu) {
 		if (cpu == smp_processor_id())
 			continue;
-		pcpu_sigp_retry(pcpu_devices + cpu, SIGP_STOP, 0);
-		while (!pcpu_stopped(pcpu_devices + cpu))
+		pcpu = per_cpu_ptr(&pcpu_devices, cpu);
+		pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
+		while (!pcpu_stopped(pcpu))
 			cpu_relax();
 	}
 }
@@ -517,7 +497,7 @@ static void smp_handle_ext_call(void)
 	unsigned long bits;
 
 	/* handle bit signal external calls */
-	bits = xchg(&pcpu_devices[smp_processor_id()].ec_mask, 0);
+	bits = this_cpu_xchg(pcpu_devices.ec_mask, 0);
 	if (test_bit(ec_stop_cpu, &bits))
 		smp_stop_cpu();
 	if (test_bit(ec_schedule, &bits))
@@ -542,12 +522,12 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 	int cpu;
 
 	for_each_cpu(cpu, mask)
-		pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
+		pcpu_ec_call(per_cpu_ptr(&pcpu_devices, cpu), ec_call_function_single);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
+	pcpu_ec_call(per_cpu_ptr(&pcpu_devices, cpu), ec_call_function_single);
 }
 
 /*
@@ -557,13 +537,13 @@ void arch_send_call_function_single_ipi(int cpu)
  */
 void arch_smp_send_reschedule(int cpu)
 {
-	pcpu_ec_call(pcpu_devices + cpu, ec_schedule);
+	pcpu_ec_call(per_cpu_ptr(&pcpu_devices, cpu), ec_schedule);
 }
 
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	pcpu_ec_call(pcpu_devices + smp_processor_id(), ec_irq_work);
+	pcpu_ec_call(this_cpu_ptr(&pcpu_devices), ec_irq_work);
 }
 #endif
 
@@ -575,7 +555,7 @@ int smp_store_status(int cpu)
 	struct pcpu *pcpu;
 	unsigned long pa;
 
-	pcpu = pcpu_devices + cpu;
+	pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 	lc = lowcore_ptr[cpu];
 	pa = __pa(&lc->floating_pt_save_area);
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
@@ -683,17 +663,17 @@ void __init smp_save_dump_secondary_cpus(void)
 
 void smp_cpu_set_polarization(int cpu, int val)
 {
-	pcpu_devices[cpu].polarization = val;
+	per_cpu(pcpu_devices, cpu).polarization = val;
 }
 
 int smp_cpu_get_polarization(int cpu)
 {
-	return pcpu_devices[cpu].polarization;
+	return per_cpu(pcpu_devices, cpu).polarization;
 }
 
 int smp_cpu_get_cpu_address(int cpu)
 {
-	return pcpu_devices[cpu].address;
+	return per_cpu(pcpu_devices, cpu).address;
 }
 
 static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
@@ -732,7 +712,7 @@ static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
 	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
 		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		pcpu = pcpu_devices + cpu;
+		pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 		pcpu->address = address + i;
 		if (configured)
 			pcpu->state = CPU_STATE_CONFIGURED;
@@ -767,7 +747,7 @@ static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
 	 * that all SMT threads get subsequent logical CPU numbers.
 	 */
 	if (early) {
-		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		core_id = per_cpu(pcpu_devices, 0).address >> smp_cpu_mt_shift;
 		for (i = 0; i < info->configured; i++) {
 			core = &info->core[i];
 			if (core->core_id == core_id) {
@@ -867,7 +847,7 @@ static void smp_start_secondary(void *cpuvoid)
 /* Upping and downing of CPUs */
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
-	struct pcpu *pcpu = pcpu_devices + cpu;
+	struct pcpu *pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 	int rc;
 
 	if (pcpu->state != CPU_STATE_CONFIGURED)
@@ -885,8 +865,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 */
 	system_ctlreg_lock();
 	pcpu_prepare_secondary(pcpu, cpu);
-	pcpu_attach_task(pcpu, tidle);
-	pcpu_start_fn(pcpu, smp_start_secondary, NULL);
+	pcpu_attach_task(cpu, tidle);
+	pcpu_start_fn(cpu, smp_start_secondary, NULL);
 	/* Wait until cpu puts itself in the online & active maps */
 	while (!cpu_online(cpu))
 		cpu_relax();
@@ -931,18 +911,19 @@ void __cpu_die(unsigned int cpu)
 	struct pcpu *pcpu;
 
 	/* Wait until target cpu is down */
-	pcpu = pcpu_devices + cpu;
+	pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 	while (!pcpu_stopped(pcpu))
 		cpu_relax();
-	pcpu_free_lowcore(pcpu);
+	pcpu_free_lowcore(pcpu, cpu);
 	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
 	cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	pcpu->flags = 0;
 }
 
 void __noreturn cpu_die(void)
 {
 	idle_task_exit();
-	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
+	pcpu_sigp_retry(this_cpu_ptr(&pcpu_devices), SIGP_STOP, 0);
 	for (;;) ;
 }
 
@@ -972,11 +953,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	struct pcpu *pcpu = pcpu_devices;
+	struct lowcore *lc = get_lowcore();
 
 	WARN_ON(!cpu_present(0) || !cpu_online(0));
-	pcpu->state = CPU_STATE_CONFIGURED;
-	get_lowcore()->percpu_offset = __per_cpu_offset[0];
+	lc->percpu_offset = __per_cpu_offset[0];
+	ipl_pcpu = per_cpu_ptr(&pcpu_devices, 0);
+	ipl_pcpu->state = CPU_STATE_CONFIGURED;
+	lc->pcpu = (unsigned long)ipl_pcpu;
 	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
 }
 
@@ -984,8 +967,8 @@ void __init smp_setup_processor_id(void)
 {
 	struct lowcore *lc = get_lowcore();
 
-	pcpu_devices[0].address = stap();
 	lc->cpu_nr = 0;
+	per_cpu(pcpu_devices, 0).address = stap();
 	lc->spinlock_lockval = arch_spin_lockval(0);
 	lc->spinlock_index = 0;
 }
@@ -1007,7 +990,7 @@ static ssize_t cpu_configure_show(struct device *dev,
 	ssize_t count;
 
 	mutex_lock(&smp_cpu_state_mutex);
-	count = sprintf(buf, "%d\n", pcpu_devices[dev->id].state);
+	count = sprintf(buf, "%d\n", per_cpu(pcpu_devices, dev->id).state);
 	mutex_unlock(&smp_cpu_state_mutex);
 	return count;
 }
@@ -1033,7 +1016,7 @@ static ssize_t cpu_configure_store(struct device *dev,
 	for (i = 0; i <= smp_cpu_mtid; i++)
 		if (cpu_online(cpu + i))
 			goto out;
-	pcpu = pcpu_devices + cpu;
+	pcpu = per_cpu_ptr(&pcpu_devices, cpu);
 	rc = 0;
 	switch (val) {
 	case 0:
@@ -1045,7 +1028,7 @@ static ssize_t cpu_configure_store(struct device *dev,
 		for (i = 0; i <= smp_cpu_mtid; i++) {
 			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
 				continue;
-			pcpu[i].state = CPU_STATE_STANDBY;
+			per_cpu(pcpu_devices, cpu + i).state = CPU_STATE_STANDBY;
 			smp_cpu_set_polarization(cpu + i,
 						 POLARIZATION_UNKNOWN);
 		}
@@ -1060,7 +1043,7 @@ static ssize_t cpu_configure_store(struct device *dev,
 		for (i = 0; i <= smp_cpu_mtid; i++) {
 			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
 				continue;
-			pcpu[i].state = CPU_STATE_CONFIGURED;
+			per_cpu(pcpu_devices, cpu + i).state = CPU_STATE_CONFIGURED;
 			smp_cpu_set_polarization(cpu + i,
 						 POLARIZATION_UNKNOWN);
 		}
@@ -1079,7 +1062,7 @@ static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
 static ssize_t show_cpu_address(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", pcpu_devices[dev->id].address);
+	return sprintf(buf, "%d\n", per_cpu(pcpu_devices, dev->id).address);
 }
 static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
 
@@ -1105,14 +1088,14 @@ static struct attribute_group cpu_online_attr_group = {
 
 static int smp_cpu_online(unsigned int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct cpu *c = per_cpu_ptr(&cpu_devices, cpu);
 
 	return sysfs_create_group(&c->dev.kobj, &cpu_online_attr_group);
 }
 
 static int smp_cpu_pre_down(unsigned int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct cpu *c = per_cpu_ptr(&cpu_devices, cpu);
 
 	sysfs_remove_group(&c->dev.kobj, &cpu_online_attr_group);
 	return 0;
@@ -1125,7 +1108,7 @@ bool arch_cpu_is_hotpluggable(int cpu)
 
 int arch_register_cpu(int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct cpu *c = per_cpu_ptr(&cpu_devices, cpu);
 	int rc;
 
 	c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 98ef6dc..22029ec 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -594,7 +594,7 @@ static int __init topology_setup(char *str)
 }
 early_param("topology", topology_setup);
 
-static int topology_ctl_handler(struct ctl_table *ctl, int write,
+static int topology_ctl_handler(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int enabled = topology_is_enabled();
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index fa62fa0..36db065 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -18,11 +18,22 @@
 #include <asm/sections.h>
 #include <asm/uv.h>
 
+#if !IS_ENABLED(CONFIG_KVM)
+unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
+{
+	return 0;
+}
+
+int gmap_fault(struct gmap *gmap, unsigned long gaddr,
+	       unsigned int fault_flags)
+{
+	return 0;
+}
+#endif
+
 /* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 int __bootdata_preserved(prot_virt_guest);
 EXPORT_SYMBOL(prot_virt_guest);
-#endif
 
 /*
  * uv_info contains both host and guest information but it's currently only
@@ -35,7 +46,6 @@ EXPORT_SYMBOL(prot_virt_guest);
 struct uv_info __bootdata_preserved(uv_info);
 EXPORT_SYMBOL(uv_info);
 
-#if IS_ENABLED(CONFIG_KVM)
 int __bootdata_preserved(prot_virt_host);
 EXPORT_SYMBOL(prot_virt_host);
 
@@ -543,9 +553,6 @@ int arch_make_page_accessible(struct page *page)
 	return arch_make_folio_accessible(page_folio(page));
 }
 EXPORT_SYMBOL_GPL(arch_make_page_accessible);
-#endif
-
-#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
 static ssize_t uv_query_facilities(struct kobject *kobj,
 				   struct kobj_attribute *attr, char *buf)
 {
@@ -721,24 +728,13 @@ static struct attribute_group uv_query_attr_group = {
 static ssize_t uv_is_prot_virt_guest(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *buf)
 {
-	int val = 0;
-
-#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
-	val = prot_virt_guest;
-#endif
-	return sysfs_emit(buf, "%d\n", val);
+	return sysfs_emit(buf, "%d\n", prot_virt_guest);
 }
 
 static ssize_t uv_is_prot_virt_host(struct kobject *kobj,
 				    struct kobj_attribute *attr, char *buf)
 {
-	int val = 0;
-
-#if IS_ENABLED(CONFIG_KVM)
-	val = prot_virt_host;
-#endif
-
-	return sysfs_emit(buf, "%d\n", val);
+	return sysfs_emit(buf, "%d\n", prot_virt_host);
 }
 
 static struct kobj_attribute uv_prot_virt_guest =
@@ -790,4 +786,3 @@ static int __init uv_info_init(void)
 	return rc;
 }
 device_initcall(uv_info_init);
-#endif
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index a1ce3925..975c654 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -190,6 +190,9 @@
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)
 
+	RUNTIME_CONST(shift, d_hash_shift)
+	RUNTIME_CONST(ptr, dentry_hashtable)
+
 	PERCPU_SECTION(0x100)
 
 	. = ALIGN(PAGE_SIZE);
@@ -219,6 +222,8 @@
 		QUAD(init_mm)
 		QUAD(swapper_pg_dir)
 		QUAD(invalid_pg_dir)
+		QUAD(__alt_instructions)
+		QUAD(__alt_instructions_end)
 #ifdef CONFIG_KASAN
 		QUAD(kasan_early_shadow_page)
 		QUAD(kasan_early_shadow_pte)
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 0c9a73a..9f86ad8 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -75,7 +75,7 @@ static inline int arch_load_niai4(int *lock)
 	int owner;
 
 	asm_inline volatile(
-		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */
+		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,4,0", ALT_FACILITY(49)) /* NIAI 4 */
 		"	l	%0,%1\n"
 		: "=d" (owner) : "Q" (*lock) : "memory");
 	return owner;
@@ -86,7 +86,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new)
 	int expected = old;
 
 	asm_inline volatile(
-		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */
+		ALTERNATIVE("nop", ".insn rre,0xb2fa0000,8,0", ALT_FACILITY(49)) /* NIAI 8 */
 		"	cs	%0,%3,%1\n"
 		: "=d" (old), "=Q" (*lock)
 		: "0" (old), "d" (new), "Q" (*lock)
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 5cb5e72..75d15bf 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -243,7 +243,7 @@ static int cmm_skip_blanks(char *cp, char **endp)
 	return str != cp;
 }
 
-static int cmm_pages_handler(struct ctl_table *ctl, int write,
+static int cmm_pages_handler(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	long nr = cmm_get_pages();
@@ -262,7 +262,7 @@ static int cmm_pages_handler(struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
+static int cmm_timed_pages_handler(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp,
 				   loff_t *ppos)
 {
@@ -282,7 +282,7 @@ static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static int cmm_timeout_handler(struct ctl_table *ctl, int write,
+static int cmm_timeout_handler(const struct ctl_table *ctl, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char buf[64], *p;
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 45db5f4..98dab3e0 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -36,6 +36,16 @@ enum address_markers_idx {
 	VMEMMAP_END_NR,
 	VMALLOC_NR,
 	VMALLOC_END_NR,
+#ifdef CONFIG_KMSAN
+	KMSAN_VMALLOC_SHADOW_START_NR,
+	KMSAN_VMALLOC_SHADOW_END_NR,
+	KMSAN_VMALLOC_ORIGIN_START_NR,
+	KMSAN_VMALLOC_ORIGIN_END_NR,
+	KMSAN_MODULES_SHADOW_START_NR,
+	KMSAN_MODULES_SHADOW_END_NR,
+	KMSAN_MODULES_ORIGIN_START_NR,
+	KMSAN_MODULES_ORIGIN_END_NR,
+#endif
 	MODULES_NR,
 	MODULES_END_NR,
 	ABS_LOWCORE_NR,
@@ -65,6 +75,16 @@ static struct addr_marker address_markers[] = {
 	[VMEMMAP_END_NR]	= {0, "vmemmap Area End"},
 	[VMALLOC_NR]		= {0, "vmalloc Area Start"},
 	[VMALLOC_END_NR]	= {0, "vmalloc Area End"},
+#ifdef CONFIG_KMSAN
+	[KMSAN_VMALLOC_SHADOW_START_NR]	= {0, "Kmsan vmalloc Shadow Start"},
+	[KMSAN_VMALLOC_SHADOW_END_NR]	= {0, "Kmsan vmalloc Shadow End"},
+	[KMSAN_VMALLOC_ORIGIN_START_NR]	= {0, "Kmsan vmalloc Origins Start"},
+	[KMSAN_VMALLOC_ORIGIN_END_NR]	= {0, "Kmsan vmalloc Origins End"},
+	[KMSAN_MODULES_SHADOW_START_NR]	= {0, "Kmsan Modules Shadow Start"},
+	[KMSAN_MODULES_SHADOW_END_NR]	= {0, "Kmsan Modules Shadow End"},
+	[KMSAN_MODULES_ORIGIN_START_NR]	= {0, "Kmsan Modules Origins Start"},
+	[KMSAN_MODULES_ORIGIN_END_NR]	= {0, "Kmsan Modules Origins End"},
+#endif
 	[MODULES_NR]		= {0, "Modules Area Start"},
 	[MODULES_END_NR]	= {0, "Modules Area End"},
 	[ABS_LOWCORE_NR]	= {0, "Lowcore Area Start"},
@@ -307,6 +327,16 @@ static int pt_dump_init(void)
 	address_markers[KFENCE_START_NR].start_address = kfence_start;
 	address_markers[KFENCE_END_NR].start_address = kfence_start + KFENCE_POOL_SIZE;
 #endif
+#ifdef CONFIG_KMSAN
+	address_markers[KMSAN_VMALLOC_SHADOW_START_NR].start_address = KMSAN_VMALLOC_SHADOW_START;
+	address_markers[KMSAN_VMALLOC_SHADOW_END_NR].start_address = KMSAN_VMALLOC_SHADOW_END;
+	address_markers[KMSAN_VMALLOC_ORIGIN_START_NR].start_address = KMSAN_VMALLOC_ORIGIN_START;
+	address_markers[KMSAN_VMALLOC_ORIGIN_END_NR].start_address = KMSAN_VMALLOC_ORIGIN_END;
+	address_markers[KMSAN_MODULES_SHADOW_START_NR].start_address = KMSAN_MODULES_SHADOW_START;
+	address_markers[KMSAN_MODULES_SHADOW_END_NR].start_address = KMSAN_MODULES_SHADOW_END;
+	address_markers[KMSAN_MODULES_ORIGIN_START_NR].start_address = KMSAN_MODULES_ORIGIN_START;
+	address_markers[KMSAN_MODULES_ORIGIN_END_NR].start_address = KMSAN_MODULES_ORIGIN_END;
+#endif
 	sort_address_markers();
 #ifdef CONFIG_PTDUMP_DEBUGFS
 	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 632c3a5..28a18c4 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -48,7 +48,7 @@ static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t siz
 }
 
 /*
- * s390_kernel_write - write to kernel memory bypassing DAT
+ * __s390_kernel_write - write to kernel memory bypassing DAT
  * @dst: destination address
  * @src: source address
  * @size: number of bytes to copy
@@ -61,7 +61,7 @@ static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t siz
  */
 static DEFINE_SPINLOCK(s390_kernel_write_lock);
 
-notrace void *s390_kernel_write(void *dst, const void *src, size_t size)
+notrace void *__s390_kernel_write(void *dst, const void *src, size_t size)
 {
 	void *tmp = dst;
 	unsigned long flags;
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 0ef83b6..84482a9 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -268,33 +268,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq,
 	}
 }
 
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs,
+			unsigned long *bit)
 {
-	struct zpci_dev *zdev = to_zpci(pdev);
-	unsigned int hwirq, msi_vecs, cpu;
-	unsigned long bit;
-	struct msi_desc *msi;
-	struct msi_msg msg;
-	int cpu_addr;
-	int rc, irq;
-
-	zdev->aisb = -1UL;
-	zdev->msi_first_bit = -1U;
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
-
 	if (irq_delivery == DIRECTED) {
 		/* Allocate cpu vector bits */
-		bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
-		if (bit == -1UL)
+		*bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+		if (*bit == -1UL)
 			return -EIO;
 	} else {
 		/* Allocate adapter summary indicator bit */
-		bit = airq_iv_alloc_bit(zpci_sbv);
-		if (bit == -1UL)
+		*bit = airq_iv_alloc_bit(zpci_sbv);
+		if (*bit == -1UL)
 			return -EIO;
-		zdev->aisb = bit;
+		zdev->aisb = *bit;
 
 		/* Create adapter interrupt vector */
 		zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL);
@@ -302,27 +289,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 			return -ENOMEM;
 
 		/* Wire up shortcut pointer */
-		zpci_ibv[bit] = zdev->aibv;
+		zpci_ibv[*bit] = zdev->aibv;
 		/* Each function has its own interrupt vector */
-		bit = 0;
+		*bit = 0;
+	}
+	return 0;
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu;
+	struct zpci_dev *zdev = to_zpci(pdev);
+	struct msi_desc *msi;
+	struct msi_msg msg;
+	unsigned long bit;
+	int cpu_addr;
+	int rc, irq;
+
+	zdev->aisb = -1UL;
+	zdev->msi_first_bit = -1U;
+
+	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+	if (msi_vecs < nvec) {
+		pr_info("%s requested %d irqs, allocate system limit of %d",
+			pci_name(pdev), nvec, zdev->max_msi);
 	}
 
-	/* Request MSI interrupts */
+	rc = __alloc_airq(zdev, msi_vecs, &bit);
+	if (rc < 0)
+		return rc;
+
+	/*
+	 * Request MSI interrupts:
+	 * When using MSI, nvec_used interrupt sources and their irq
+	 * descriptors are controlled through one msi descriptor.
+	 * Thus the outer loop over msi descriptors shall run only once,
+	 * while two inner loops iterate over the interrupt vectors.
+	 * When using MSI-X, each interrupt vector/irq descriptor
+	 * is bound to exactly one msi descriptor (nvec_used is one).
+	 * So the inner loops are executed once, while the outer iterates
+	 * over the MSI-X descriptors.
+	 */
 	hwirq = bit;
 	msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
-		rc = -EIO;
 		if (hwirq - bit >= msi_vecs)
 			break;
-		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
-				(irq_delivery == DIRECTED) ?
-				msi->affinity : NULL);
+		irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used);
+		irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE,
+					(irq_delivery == DIRECTED) ?
+					msi->affinity : NULL);
 		if (irq < 0)
 			return -ENOMEM;
-		rc = irq_set_msi_desc(irq, msi);
-		if (rc)
-			return rc;
-		irq_set_chip_and_handler(irq, &zpci_irq_chip,
-					 handle_percpu_irq);
+
+		for (i = 0; i < irqs_per_msi; i++) {
+			rc = irq_set_msi_desc_off(irq, i, msi);
+			if (rc)
+				return rc;
+			irq_set_chip_and_handler(irq + i, &zpci_irq_chip,
+						 handle_percpu_irq);
+		}
+
 		msg.data = hwirq - bit;
 		if (irq_delivery == DIRECTED) {
 			if (msi->affinity)
@@ -335,31 +361,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 			msg.address_lo |= (cpu_addr << 8);
 
 			for_each_possible_cpu(cpu) {
-				airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
+				for (i = 0; i < irqs_per_msi; i++)
+					airq_iv_set_data(zpci_ibv[cpu],
+							 hwirq + i, irq + i);
 			}
 		} else {
 			msg.address_lo = zdev->msi_addr & 0xffffffff;
-			airq_iv_set_data(zdev->aibv, hwirq, irq);
+			for (i = 0; i < irqs_per_msi; i++)
+				airq_iv_set_data(zdev->aibv, hwirq + i, irq + i);
 		}
 		msg.address_hi = zdev->msi_addr >> 32;
 		pci_write_msi_msg(irq, &msg);
-		hwirq++;
+		hwirq += irqs_per_msi;
 	}
 
 	zdev->msi_first_bit = bit;
-	zdev->msi_nr_irqs = msi_vecs;
+	zdev->msi_nr_irqs = hwirq - bit;
 
 	rc = zpci_set_irq(zdev);
 	if (rc)
 		return rc;
 
-	return (msi_vecs == nvec) ? 0 : msi_vecs;
+	return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs;
 }
 
 void arch_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
 	struct msi_desc *msi;
+	unsigned int i;
 	int rc;
 
 	/* Disable interrupts */
@@ -369,8 +399,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 
 	/* Release MSI interrupts */
 	msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) {
-		irq_set_msi_desc(msi->irq, NULL);
-		irq_free_desc(msi->irq);
+		for (i = 0; i < msi->nvec_used; i++) {
+			irq_set_msi_desc(msi->irq + i, NULL);
+			irq_free_desc(msi->irq + i);
+		}
 		msi->msg.address_lo = 0;
 		msi->msg.address_hi = 0;
 		msi->msg.data = 0;
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 587fb78..0ca8c34 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -483,11 +483,7 @@ int __vio_register_driver(struct vio_driver *drv, struct module *owner,
 	__vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
 void vio_unregister_driver(struct vio_driver *drv);
 
-static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct vio_driver, driver);
-}
-
+#define to_vio_driver(__drv)	container_of_const(__drv, struct vio_driver, driver)
 #define to_vio_dev(__dev)	container_of_const(__dev, struct vio_dev, dev)
 
 int vio_ldc_send(struct vio_driver_state *vio, void *data, int len);
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 846a55f..07933d7 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -54,10 +54,10 @@ static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-static int vio_bus_match(struct device *dev, struct device_driver *drv)
+static int vio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct vio_dev *vio_dev = to_vio_dev(dev);
-	struct vio_driver *vio_drv = to_vio_driver(drv);
+	const struct vio_driver *vio_drv = to_vio_driver(drv);
 	const struct vio_device_id *matches = vio_drv->id_table;
 
 	if (!matches)
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 93a5a89..dca84fd 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -11,7 +11,7 @@
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_STRNCPY_FROM_USER
 	select ARCH_HAS_STRNLEN_USER
-	select ARCH_NO_PREEMPT
+	select ARCH_NO_PREEMPT_DYNAMIC
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_KASAN if X86_64
 	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
@@ -31,7 +31,8 @@
 	select TRACE_IRQFLAGS_SUPPORT
 	select TTY # Needed for line.c
 	select HAVE_ARCH_VMAP_STACK
-	select HAVE_RUST			if X86_64
+	select HAVE_RUST
+	select ARCH_HAS_UBSAN
 
 config MMU
 	bool
@@ -48,12 +49,13 @@
 config UML_IOMEM_EMULATION
 	bool
 	select INDIRECT_IOMEM
+	select HAS_IOPORT
 	select GENERIC_PCI_IOMAP
 	select GENERIC_IOMAP
 	select NO_GENERIC_PCI_IOPORT_MAP
 
 config NO_IOPORT_MAP
-	def_bool y
+	def_bool !UML_IOMEM_EMULATION
 
 config ISA
 	bool
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
index b94b261..ede40a1 100644
--- a/arch/um/drivers/Kconfig
+++ b/arch/um/drivers/Kconfig
@@ -297,26 +297,6 @@
 
 	  If unsure, say N.
 
-config UML_NET_PCAP
-	bool "pcap transport (obsolete)"
-	depends on UML_NET
-	depends on !MODVERSIONS
-	select MAY_HAVE_RUNTIME_DEPS
-	help
-	  The pcap transport makes a pcap packet stream on the host look
-	  like an ethernet device inside UML.  This is useful for making
-	  UML act as a network monitor for the host.  You must have libcap
-	  installed in order to build the pcap transport into UML.
-
-	  For more information, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-	  has examples of the UML command line to use to enable this option.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
 config UML_NET_SLIRP
 	bool "SLiRP transport (obsolete)"
 	depends on UML_NET
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index 0e6af81..57882e6 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -20,14 +20,9 @@
 harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o
 rtc-objs := rtc_kern.o rtc_user.o
 
-LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a)
-
 LDFLAGS_vde.o = $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a)
 
-targets := pcap_kern.o pcap_user.o vde_kern.o vde_user.o
-
-$(obj)/pcap.o: $(obj)/pcap_kern.o $(obj)/pcap_user.o
-	$(LD) -r -dp -o $@ $^ $(ld_flags)
+targets := vde_kern.o vde_user.o
 
 $(obj)/vde.o: $(obj)/vde_kern.o $(obj)/vde_user.o
 	$(LD) -r -dp -o $@ $^ $(ld_flags)
@@ -49,7 +44,6 @@
 obj-$(CONFIG_UML_NET_VECTOR) += vector.o
 obj-$(CONFIG_UML_NET_VDE) += vde.o
 obj-$(CONFIG_UML_NET_MCAST) += umcast.o
-obj-$(CONFIG_UML_NET_PCAP) += pcap.o
 obj-$(CONFIG_UML_NET) += net.o 
 obj-$(CONFIG_MCONSOLE) += mconsole.o
 obj-$(CONFIG_MMAPPER) += mmapper_kern.o 
@@ -69,7 +63,7 @@
 obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virt-pci.o
 
 # pcap_user.o must be added explicitly.
-USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o vector_user.o
+USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o vde_user.o vector_user.o
 CFLAGS_null.o = -DDEV_NULL=$(DEV_NULL_PATH)
 
 CFLAGS_xterm.o += '-DCONFIG_XTERM_CHAN_DEFAULT_EMULATOR="$(CONFIG_XTERM_CHAN_DEFAULT_EMULATOR)"'
diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h
index e14b9cd..5a61db5 100644
--- a/arch/um/drivers/chan.h
+++ b/arch/um/drivers/chan.h
@@ -22,7 +22,8 @@ struct chan {
 	unsigned int output:1;
 	unsigned int opened:1;
 	unsigned int enabled:1;
-	int fd;
+	int fd_in;
+	int fd_out; /* only different to fd_in if blocking output is needed */
 	const struct chan_ops *ops;
 	void *data;
 };
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index 37538b4..e78a998 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -81,6 +81,12 @@ static const struct chan_ops not_configged_ops = {
 };
 #endif /* CONFIG_NOCONFIG_CHAN */
 
+static inline bool need_output_blocking(void)
+{
+	return time_travel_mode == TT_MODE_INFCPU ||
+	       time_travel_mode == TT_MODE_EXTERNAL;
+}
+
 static int open_one_chan(struct chan *chan)
 {
 	int fd, err;
@@ -96,15 +102,43 @@ static int open_one_chan(struct chan *chan)
 		return fd;
 
 	err = os_set_fd_block(fd, 0);
-	if (err) {
-		(*chan->ops->close)(fd, chan->data);
-		return err;
-	}
+	if (err)
+		goto out_close;
 
-	chan->fd = fd;
+	chan->fd_in = fd;
+	chan->fd_out = fd;
+
+	/*
+	 * In time-travel modes infinite-CPU and external we need to guarantee
+	 * that any writes to the output succeed immdiately from the point of
+	 * the VM. The best way to do this is to put the FD in blocking mode
+	 * and simply wait/retry until everything is written.
+	 * As every write is guaranteed to complete, we also do not need to
+	 * request an IRQ for the output.
+	 *
+	 * Note that input cannot happen in a time synchronized way. We permit
+	 * it, but time passes very quickly if anything waits for a read.
+	 */
+	if (chan->output && need_output_blocking()) {
+		err = os_dup_file(chan->fd_out);
+		if (err < 0)
+			goto out_close;
+
+		chan->fd_out = err;
+
+		err = os_set_fd_block(chan->fd_out, 1);
+		if (err) {
+			os_close_file(chan->fd_out);
+			goto out_close;
+		}
+	}
 
 	chan->opened = 1;
 	return 0;
+
+out_close:
+	(*chan->ops->close)(fd, chan->data);
+	return err;
 }
 
 static int open_chan(struct list_head *chans)
@@ -125,7 +159,7 @@ static int open_chan(struct list_head *chans)
 void chan_enable_winch(struct chan *chan, struct tty_port *port)
 {
 	if (chan && chan->primary && chan->ops->winch)
-		register_winch(chan->fd, port);
+		register_winch(chan->fd_in, port);
 }
 
 static void line_timer_cb(struct work_struct *work)
@@ -156,8 +190,9 @@ int enable_chan(struct line *line)
 
 		if (chan->enabled)
 			continue;
-		err = line_setup_irq(chan->fd, chan->input, chan->output, line,
-				     chan);
+		err = line_setup_irq(chan->fd_in, chan->input,
+				     chan->output && !need_output_blocking(),
+				     line, chan);
 		if (err)
 			goto out_close;
 
@@ -196,7 +231,8 @@ void free_irqs(void)
 
 		if (chan->input && chan->enabled)
 			um_free_irq(chan->line->read_irq, chan);
-		if (chan->output && chan->enabled)
+		if (chan->output && chan->enabled &&
+		    !need_output_blocking())
 			um_free_irq(chan->line->write_irq, chan);
 		chan->enabled = 0;
 	}
@@ -216,15 +252,19 @@ static void close_one_chan(struct chan *chan, int delay_free_irq)
 	} else {
 		if (chan->input && chan->enabled)
 			um_free_irq(chan->line->read_irq, chan);
-		if (chan->output && chan->enabled)
+		if (chan->output && chan->enabled &&
+		    !need_output_blocking())
 			um_free_irq(chan->line->write_irq, chan);
 		chan->enabled = 0;
 	}
+	if (chan->fd_out != chan->fd_in)
+		os_close_file(chan->fd_out);
 	if (chan->ops->close != NULL)
-		(*chan->ops->close)(chan->fd, chan->data);
+		(*chan->ops->close)(chan->fd_in, chan->data);
 
 	chan->opened = 0;
-	chan->fd = -1;
+	chan->fd_in = -1;
+	chan->fd_out = -1;
 }
 
 void close_chan(struct line *line)
@@ -244,7 +284,7 @@ void close_chan(struct line *line)
 void deactivate_chan(struct chan *chan, int irq)
 {
 	if (chan && chan->enabled)
-		deactivate_fd(chan->fd, irq);
+		deactivate_fd(chan->fd_in, irq);
 }
 
 int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq)
@@ -254,7 +294,7 @@ int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq)
 	if (len == 0 || !chan || !chan->ops->write)
 		return 0;
 
-	n = chan->ops->write(chan->fd, buf, len, chan->data);
+	n = chan->ops->write(chan->fd_out, buf, len, chan->data);
 	if (chan->primary) {
 		ret = n;
 	}
@@ -268,7 +308,7 @@ int console_write_chan(struct chan *chan, const char *buf, int len)
 	if (!chan || !chan->ops->console_write)
 		return 0;
 
-	n = chan->ops->console_write(chan->fd, buf, len);
+	n = chan->ops->console_write(chan->fd_out, buf, len);
 	if (chan->primary)
 		ret = n;
 	return ret;
@@ -296,14 +336,14 @@ int chan_window_size(struct line *line, unsigned short *rows_out,
 	if (chan && chan->primary) {
 		if (chan->ops->window_size == NULL)
 			return 0;
-		return chan->ops->window_size(chan->fd, chan->data,
+		return chan->ops->window_size(chan->fd_in, chan->data,
 					      rows_out, cols_out);
 	}
 	chan = line->chan_out;
 	if (chan && chan->primary) {
 		if (chan->ops->window_size == NULL)
 			return 0;
-		return chan->ops->window_size(chan->fd, chan->data,
+		return chan->ops->window_size(chan->fd_in, chan->data,
 					      rows_out, cols_out);
 	}
 	return 0;
@@ -319,7 +359,7 @@ static void free_one_chan(struct chan *chan)
 		(*chan->ops->free)(chan->data);
 
 	if (chan->primary && chan->output)
-		ignore_sigio_fd(chan->fd);
+		ignore_sigio_fd(chan->fd_in);
 	kfree(chan);
 }
 
@@ -478,7 +518,8 @@ static struct chan *parse_chan(struct line *line, char *str, int device,
 				 .output 	= 0,
 				 .opened  	= 0,
 				 .enabled  	= 0,
-				 .fd 		= -1,
+				 .fd_in		= -1,
+				 .fd_out	= -1,
 				 .ops 		= ops,
 				 .data 		= data });
 	return chan;
@@ -549,7 +590,7 @@ void chan_interrupt(struct line *line, int irq)
 			schedule_delayed_work(&line->task, 1);
 			goto out;
 		}
-		err = chan->ops->read(chan->fd, &c, chan->data);
+		err = chan->ops->read(chan->fd_in, &c, chan->data);
 		if (err > 0)
 			tty_insert_flip_char(port, c, TTY_NORMAL);
 	} while (err > 0);
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index ec04e47..a66e556 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -23,7 +23,7 @@ int generic_read(int fd, __u8 *c_out, void *unused)
 {
 	int n;
 
-	n = read(fd, c_out, sizeof(*c_out));
+	CATCH_EINTR(n = read(fd, c_out, sizeof(*c_out)));
 	if (n > 0)
 		return n;
 	else if (n == 0)
@@ -37,11 +37,23 @@ int generic_read(int fd, __u8 *c_out, void *unused)
 
 int generic_write(int fd, const __u8 *buf, size_t n, void *unused)
 {
+	int written = 0;
 	int err;
 
-	err = write(fd, buf, n);
-	if (err > 0)
-		return err;
+	/* The FD may be in blocking mode, as such, need to retry short writes,
+	 * they may have been interrupted by a signal.
+	 */
+	do {
+		errno = 0;
+		err = write(fd, buf + written, n - written);
+		if (err > 0) {
+			written += err;
+			continue;
+		}
+	} while (err < 0 && errno == EINTR);
+
+	if (written > 0)
+		return written;
 	else if (errno == EAGAIN)
 		return 0;
 	else if (err == 0)
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index 60d1c6c..99a7144 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -49,6 +49,7 @@
 #include "mconsole.h"
 #include "harddog.h"
 
+MODULE_DESCRIPTION("UML hardware watchdog");
 MODULE_LICENSE("GPL");
 
 static DEFINE_MUTEX(harddog_mutex);
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index d82bc3f..43d8959 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init,
 			parse_chan_pair(NULL, line, n, opts, error_out);
 			err = 0;
 		}
+		*error_out = "configured as 'none'";
 	} else {
 		char *new = kstrdup(init, GFP_KERNEL);
 		if (!new) {
@@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init,
 			}
 		}
 		if (err) {
+			*error_out = "failed to parse channel pair";
 			line->init_str = NULL;
 			line->valid = 0;
 			kfree(new);
diff --git a/arch/um/drivers/pcap_kern.c b/arch/um/drivers/pcap_kern.c
deleted file mode 100644
index d9bf95d..0000000
--- a/arch/um/drivers/pcap_kern.c
+++ /dev/null
@@ -1,113 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <net_kern.h>
-#include "pcap_user.h"
-
-struct pcap_init {
-	char *host_if;
-	int promisc;
-	int optimize;
-	char *filter;
-};
-
-static void pcap_init_kern(struct net_device *dev, void *data)
-{
-	struct uml_net_private *pri;
-	struct pcap_data *ppri;
-	struct pcap_init *init = data;
-
-	pri = netdev_priv(dev);
-	ppri = (struct pcap_data *) pri->user;
-	ppri->host_if = init->host_if;
-	ppri->promisc = init->promisc;
-	ppri->optimize = init->optimize;
-	ppri->filter = init->filter;
-
-	printk("pcap backend, host interface %s\n", ppri->host_if);
-}
-
-static int pcap_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return pcap_user_read(fd, skb_mac_header(skb),
-			      skb->dev->mtu + ETH_HEADER_OTHER,
-			      (struct pcap_data *) &lp->user);
-}
-
-static int pcap_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return -EPERM;
-}
-
-static const struct net_kern_info pcap_kern_info = {
-	.init			= pcap_init_kern,
-	.protocol		= eth_protocol,
-	.read			= pcap_read,
-	.write			= pcap_write,
-};
-
-static int pcap_setup(char *str, char **mac_out, void *data)
-{
-	struct pcap_init *init = data;
-	char *remain, *host_if = NULL, *options[2] = { NULL, NULL };
-	int i;
-
-	*init = ((struct pcap_init)
-		{ .host_if 	= "eth0",
-		  .promisc 	= 1,
-		  .optimize 	= 0,
-		  .filter 	= NULL });
-
-	remain = split_if_spec(str, &host_if, &init->filter,
-			       &options[0], &options[1], mac_out, NULL);
-	if (remain != NULL) {
-		printk(KERN_ERR "pcap_setup - Extra garbage on "
-		       "specification : '%s'\n", remain);
-		return 0;
-	}
-
-	if (host_if != NULL)
-		init->host_if = host_if;
-
-	for (i = 0; i < ARRAY_SIZE(options); i++) {
-		if (options[i] == NULL)
-			continue;
-		if (!strcmp(options[i], "promisc"))
-			init->promisc = 1;
-		else if (!strcmp(options[i], "nopromisc"))
-			init->promisc = 0;
-		else if (!strcmp(options[i], "optimize"))
-			init->optimize = 1;
-		else if (!strcmp(options[i], "nooptimize"))
-			init->optimize = 0;
-		else {
-			printk(KERN_ERR "pcap_setup : bad option - '%s'\n",
-			       options[i]);
-			return 0;
-		}
-	}
-
-	return 1;
-}
-
-static struct transport pcap_transport = {
-	.list 		= LIST_HEAD_INIT(pcap_transport.list),
-	.name 		= "pcap",
-	.setup  	= pcap_setup,
-	.user 		= &pcap_user_info,
-	.kern 		= &pcap_kern_info,
-	.private_size 	= sizeof(struct pcap_data),
-	.setup_size 	= sizeof(struct pcap_init),
-};
-
-static int register_pcap(void)
-{
-	register_transport(&pcap_transport);
-	return 0;
-}
-
-late_initcall(register_pcap);
diff --git a/arch/um/drivers/pcap_user.c b/arch/um/drivers/pcap_user.c
deleted file mode 100644
index 52ddda3..0000000
--- a/arch/um/drivers/pcap_user.c
+++ /dev/null
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <errno.h>
-#include <pcap.h>
-#include <string.h>
-#include <asm/types.h>
-#include <net_user.h>
-#include "pcap_user.h"
-#include <um_malloc.h>
-
-#define PCAP_FD(p) (*(int *)(p))
-
-static int pcap_user_init(void *data, void *dev)
-{
-	struct pcap_data *pri = data;
-	pcap_t *p;
-	char errors[PCAP_ERRBUF_SIZE];
-
-	p = pcap_open_live(pri->host_if, ETH_MAX_PACKET + ETH_HEADER_OTHER,
-			   pri->promisc, 0, errors);
-	if (p == NULL) {
-		printk(UM_KERN_ERR "pcap_user_init : pcap_open_live failed - "
-		       "'%s'\n", errors);
-		return -EINVAL;
-	}
-
-	pri->dev = dev;
-	pri->pcap = p;
-	return 0;
-}
-
-static int pcap_user_open(void *data)
-{
-	struct pcap_data *pri = data;
-	__u32 netmask;
-	int err;
-
-	if (pri->pcap == NULL)
-		return -ENODEV;
-
-	if (pri->filter != NULL) {
-		err = dev_netmask(pri->dev, &netmask);
-		if (err < 0) {
-			printk(UM_KERN_ERR "pcap_user_open : dev_netmask failed\n");
-			return -EIO;
-		}
-
-		pri->compiled = uml_kmalloc(sizeof(struct bpf_program),
-					UM_GFP_KERNEL);
-		if (pri->compiled == NULL) {
-			printk(UM_KERN_ERR "pcap_user_open : kmalloc failed\n");
-			return -ENOMEM;
-		}
-
-		err = pcap_compile(pri->pcap,
-				   (struct bpf_program *) pri->compiled,
-				   pri->filter, pri->optimize, netmask);
-		if (err < 0) {
-			printk(UM_KERN_ERR "pcap_user_open : pcap_compile failed - "
-			       "'%s'\n", pcap_geterr(pri->pcap));
-			goto out;
-		}
-
-		err = pcap_setfilter(pri->pcap, pri->compiled);
-		if (err < 0) {
-			printk(UM_KERN_ERR "pcap_user_open : pcap_setfilter "
-			       "failed - '%s'\n", pcap_geterr(pri->pcap));
-			goto out;
-		}
-	}
-
-	return PCAP_FD(pri->pcap);
-
- out:
-	kfree(pri->compiled);
-	return -EIO;
-}
-
-static void pcap_remove(void *data)
-{
-	struct pcap_data *pri = data;
-
-	if (pri->compiled != NULL)
-		pcap_freecode(pri->compiled);
-
-	if (pri->pcap != NULL)
-		pcap_close(pri->pcap);
-}
-
-struct pcap_handler_data {
-	char *buffer;
-	int len;
-};
-
-static void handler(u_char *data, const struct pcap_pkthdr *header,
-		    const u_char *packet)
-{
-	int len;
-
-	struct pcap_handler_data *hdata = (struct pcap_handler_data *) data;
-
-	len = hdata->len < header->caplen ? hdata->len : header->caplen;
-	memcpy(hdata->buffer, packet, len);
-	hdata->len = len;
-}
-
-int pcap_user_read(int fd, void *buffer, int len, struct pcap_data *pri)
-{
-	struct pcap_handler_data hdata = ((struct pcap_handler_data)
-		                          { .buffer  	= buffer,
-					    .len 	= len });
-	int n;
-
-	n = pcap_dispatch(pri->pcap, 1, handler, (u_char *) &hdata);
-	if (n < 0) {
-		printk(UM_KERN_ERR "pcap_dispatch failed - %s\n",
-		       pcap_geterr(pri->pcap));
-		return -EIO;
-	}
-	else if (n == 0)
-		return 0;
-	return hdata.len;
-}
-
-const struct net_user_info pcap_user_info = {
-	.init		= pcap_user_init,
-	.open		= pcap_user_open,
-	.close	 	= NULL,
-	.remove	 	= pcap_remove,
-	.add_address	= NULL,
-	.delete_address = NULL,
-	.mtu		= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
diff --git a/arch/um/drivers/pcap_user.h b/arch/um/drivers/pcap_user.h
deleted file mode 100644
index 216246f..0000000
--- a/arch/um/drivers/pcap_user.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- */
-
-#include <net_user.h>
-
-struct pcap_data {
-	char *host_if;
-	int promisc;
-	int optimize;
-	char *filter;
-	void *compiled;
-	void *pcap;
-	void *dev;
-};
-
-extern const struct net_user_info pcap_user_info;
-
-extern int pcap_user_read(int fd, void *buf, int len, struct pcap_data *pri);
-
diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c
index c52b3ff..a450847 100644
--- a/arch/um/drivers/port_kern.c
+++ b/arch/um/drivers/port_kern.c
@@ -45,15 +45,17 @@ struct connection {
 static irqreturn_t pipe_interrupt(int irq, void *data)
 {
 	struct connection *conn = data;
-	int fd;
+	int n_fds = 1, fd = -1;
+	ssize_t ret;
 
-	fd = os_rcv_fd(conn->socket[0], &conn->helper_pid);
-	if (fd < 0) {
-		if (fd == -EAGAIN)
+	ret = os_rcv_fd_msg(conn->socket[0], &fd, n_fds, &conn->helper_pid,
+			    sizeof(conn->helper_pid));
+	if (ret != sizeof(conn->helper_pid)) {
+		if (ret == -EAGAIN)
 			return IRQ_NONE;
 
-		printk(KERN_ERR "pipe_interrupt : os_rcv_fd returned %d\n",
-		       -fd);
+		printk(KERN_ERR "pipe_interrupt : os_rcv_fd_msg returned %zd\n",
+		       ret);
 		os_close_file(conn->fd);
 	}
 
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 9f1e76d..7f28ec1 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -36,7 +36,6 @@
 #include <linux/vmalloc.h>
 #include <linux/platform_device.h>
 #include <linux/scatterlist.h>
-#include <asm/tlbflush.h>
 #include <kern_util.h>
 #include "mconsole_kern.h"
 #include <init.h>
@@ -106,7 +105,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 #define DRIVER_NAME "uml-blkdev"
 
 static DEFINE_MUTEX(ubd_lock);
-static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
 static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
@@ -759,7 +757,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 			printk(KERN_ERR "Failed to vmalloc COW bitmap\n");
 			goto error;
 		}
-		flush_tlb_kernel_vm();
 
 		err = read_cow_bitmap(ubd_dev->fd, ubd_dev->cow.bitmap,
 				      ubd_dev->cow.bitmap_offset,
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 4279793..2d47328 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1115,11 +1115,12 @@ static int irq_rr;
 static int vector_net_close(struct net_device *dev)
 {
 	struct vector_private *vp = netdev_priv(dev);
-	unsigned long flags;
 
 	netif_stop_queue(dev);
 	del_timer(&vp->tl);
 
+	vp->opened = false;
+
 	if (vp->fds == NULL)
 		return 0;
 
@@ -1158,10 +1159,7 @@ static int vector_net_close(struct net_device *dev)
 		destroy_queue(vp->tx_queue);
 	kfree(vp->fds);
 	vp->fds = NULL;
-	spin_lock_irqsave(&vp->lock, flags);
-	vp->opened = false;
 	vp->in_error = false;
-	spin_unlock_irqrestore(&vp->lock, flags);
 	return 0;
 }
 
@@ -1203,17 +1201,12 @@ static void vector_reset_tx(struct work_struct *work)
 static int vector_net_open(struct net_device *dev)
 {
 	struct vector_private *vp = netdev_priv(dev);
-	unsigned long flags;
 	int err = -EINVAL;
 	struct vector_device *vdevice;
 
-	spin_lock_irqsave(&vp->lock, flags);
-	if (vp->opened) {
-		spin_unlock_irqrestore(&vp->lock, flags);
+	if (vp->opened)
 		return -ENXIO;
-	}
 	vp->opened = true;
-	spin_unlock_irqrestore(&vp->lock, flags);
 
 	vp->bpf = uml_vector_user_bpf(get_bpf_file(vp->parsed));
 
@@ -1387,8 +1380,6 @@ static int vector_net_load_bpf_flash(struct net_device *dev,
 		return -1;
 	}
 
-	spin_lock(&vp->lock);
-
 	if (vp->bpf != NULL) {
 		if (vp->opened)
 			uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf);
@@ -1417,15 +1408,12 @@ static int vector_net_load_bpf_flash(struct net_device *dev,
 	if (vp->opened)
 		result = uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf);
 
-	spin_unlock(&vp->lock);
-
 	return result;
 
 free_buffer:
 	release_firmware(fw);
 
 flash_fail:
-	spin_unlock(&vp->lock);
 	if (vp->bpf != NULL)
 		kfree(vp->bpf->filter);
 	kfree(vp->bpf);
@@ -1631,7 +1619,6 @@ static void vector_eth_configure(
 	INIT_WORK(&vp->reset_tx, vector_reset_tx);
 
 	timer_setup(&vp->tl, vector_timer_expire, 0);
-	spin_lock_init(&vp->lock);
 
 	/* FIXME */
 	dev->netdev_ops = &vector_netdev_ops;
diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h
index 2a1fa8e..806df55 100644
--- a/arch/um/drivers/vector_kern.h
+++ b/arch/um/drivers/vector_kern.h
@@ -71,7 +71,6 @@ struct vector_estats {
 
 struct vector_private {
 	struct list_head list;
-	spinlock_t lock;
 	struct net_device *dev;
 	struct napi_struct		napi	____cacheline_aligned;
 
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index 6918de5..e4316c7 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -156,7 +156,7 @@ static int xterm_open(int input, int output, int primary, void *d,
 	new = xterm_fd(fd, &data->helper_pid);
 	if (new < 0) {
 		err = new;
-		printk(UM_KERN_ERR "xterm_open : os_rcv_fd failed, err = %d\n",
+		printk(UM_KERN_ERR "xterm_open : xterm_fd failed, err = %d\n",
 		       -err);
 		goto out_kill;
 	}
diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c
index 8011e51..3971252 100644
--- a/arch/um/drivers/xterm_kern.c
+++ b/arch/um/drivers/xterm_kern.c
@@ -21,12 +21,19 @@ struct xterm_wait {
 static irqreturn_t xterm_interrupt(int irq, void *data)
 {
 	struct xterm_wait *xterm = data;
-	int fd;
+	int fd = -1, n_fds = 1;
+	ssize_t ret;
 
-	fd = os_rcv_fd(xterm->fd, &xterm->pid);
-	if (fd == -EAGAIN)
+	ret = os_rcv_fd_msg(xterm->fd, &fd, n_fds,
+			    &xterm->pid, sizeof(xterm->pid));
+	if (ret == -EAGAIN)
 		return IRQ_NONE;
 
+	if (ret < 0)
+		fd = ret;
+	else if (ret != sizeof(xterm->pid))
+		fd = -EMSGSIZE;
+
 	xterm->new_fd = fd;
 	complete(&xterm->ready);
 
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index f2923c7..a3eaca4 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -7,15 +7,13 @@
 #define __ARCH_UM_MMU_H
 
 #include <mm_id.h>
-#include <asm/mm_context.h>
 
 typedef struct mm_context {
 	struct mm_id id;
-	struct uml_arch_mm_context arch;
-} mm_context_t;
 
-/* Avoid tangled inclusion with asm/ldt.h */
-extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm);
-extern void free_ldt(struct mm_context *mm);
+	/* Address range in need of a TLB sync */
+	unsigned long sync_tlb_range_from;
+	unsigned long sync_tlb_range_to;
+} mm_context_t;
 
 #endif
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 68e2eb9c..23dcc91 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -13,8 +13,6 @@
 #include <asm/mm_hooks.h>
 #include <asm/mmu.h>
 
-extern void force_flush_all(void);
-
 #define activate_mm activate_mm
 static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
 {
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index e1ece21..5bb397b 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -244,6 +244,38 @@ static inline void set_pte(pte_t *pteptr, pte_t pteval)
 
 #define PFN_PTE_SHIFT		PAGE_SHIFT
 
+static inline void um_tlb_mark_sync(struct mm_struct *mm, unsigned long start,
+				    unsigned long end)
+{
+	if (!mm->context.sync_tlb_range_to) {
+		mm->context.sync_tlb_range_from = start;
+		mm->context.sync_tlb_range_to = end;
+	} else {
+		if (start < mm->context.sync_tlb_range_from)
+			mm->context.sync_tlb_range_from = start;
+		if (end > mm->context.sync_tlb_range_to)
+			mm->context.sync_tlb_range_to = end;
+	}
+}
+
+#define set_ptes set_ptes
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte, int nr)
+{
+	/* Basically the default implementation */
+	size_t length = nr * PAGE_SIZE;
+
+	for (;;) {
+		set_pte(ptep, pte);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte = __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT));
+	}
+
+	um_tlb_mark_sync(mm, addr, addr + length);
+}
+
 #define __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/arch/um/include/asm/tlbflush.h b/arch/um/include/asm/tlbflush.h
index a5bda89..db99797 100644
--- a/arch/um/include/asm/tlbflush.h
+++ b/arch/um/include/asm/tlbflush.h
@@ -9,23 +9,51 @@
 #include <linux/mm.h>
 
 /*
- * TLB flushing:
+ * In UML, we need to sync the TLB over by using mmap/munmap/mprotect syscalls
+ * from the process handling the MM (which can be the kernel itself).
  *
- *  - flush_tlb() flushes the current mm struct TLBs
+ * To track updates, we can hook into set_ptes and flush_tlb_*. With set_ptes
+ * we catch all PTE transitions where memory that was unusable becomes usable.
+ * While with flush_tlb_* we can track any memory that becomes unusable and
+ * even if a higher layer of the page table was modified.
+ *
+ * So, we simply track updates using both methods and mark the memory area to
+ * be synced later on. The only special case is that flush_tlb_kern_* needs to
+ * be executed immediately as there is no good synchronization point in that
+ * case. In contrast, in the set_ptes case we can wait for the next kernel
+ * segfault before we do the synchornization.
+ *
  *  - flush_tlb_all() flushes all processes TLBs
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
- *  - flush_tlb_kernel_vm() flushes the kernel vm area
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
  */
 
+extern int um_tlb_sync(struct mm_struct *mm);
+
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm(struct mm_struct *mm);
-extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, 
-			    unsigned long end);
-extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long address);
-extern void flush_tlb_kernel_vm(void);
-extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-extern void __flush_tlb_one(unsigned long addr);
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long address)
+{
+	um_tlb_mark_sync(vma->vm_mm, address, address + PAGE_SIZE);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	um_tlb_mark_sync(vma->vm_mm, start, end);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+	um_tlb_mark_sync(&init_mm, start, end);
+
+	/* Kernel needs to be synced immediately */
+	um_tlb_sync(&init_mm);
+}
 
 #endif
diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h
index c22f46a..06292fc 100644
--- a/arch/um/include/shared/as-layout.h
+++ b/arch/um/include/shared/as-layout.h
@@ -23,7 +23,7 @@
 #define STUB_START stub_start
 #define STUB_CODE STUB_START
 #define STUB_DATA (STUB_CODE + UM_KERN_PAGE_SIZE)
-#define STUB_DATA_PAGES 1 /* must be a power of two */
+#define STUB_DATA_PAGES 2 /* must be a power of two */
 #define STUB_END (STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index 9619548..579ed946 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -1,6 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* for use by sys-$SUBARCH/kernel-offsets.c */
-#include <stub-data.h>
 
 DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
 
@@ -30,7 +29,3 @@ DEFINE(UML_CONFIG_64BIT, CONFIG_64BIT);
 DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT);
 #endif
 
-/* for stub */
-DEFINE(UML_STUB_FIELD_OFFSET, offsetof(struct stub_data, offset));
-DEFINE(UML_STUB_FIELD_CHILD_ERR, offsetof(struct stub_data, child_err));
-DEFINE(UML_STUB_FIELD_FD, offsetof(struct stub_data, fd));
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index 95521b1..d8ffd2d 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -13,7 +13,6 @@ struct siginfo;
 
 extern int uml_exitcode;
 
-extern int ncpus;
 extern int kmalloc_ok;
 
 #define UML_ROUND_UP(addr) \
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index aff8906..9a039d6 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -163,8 +163,10 @@ extern int os_set_fd_block(int fd, int blocking);
 extern int os_accept_connection(int fd);
 extern int os_create_unix_socket(const char *file, int len, int close_on_exec);
 extern int os_shutdown_socket(int fd, int r, int w);
+extern int os_dup_file(int fd);
 extern void os_close_file(int fd);
-extern int os_rcv_fd(int fd, int *helper_pid_out);
+ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds,
+		      void *data, size_t data_len);
 extern int os_connect_socket(const char *name);
 extern int os_file_type(char *file);
 extern int os_file_mode(const char *file, struct openflags *mode_out);
@@ -179,6 +181,8 @@ extern int os_eventfd(unsigned int initval, int flags);
 extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len,
 			  const int *fds, unsigned int fds_num);
 int os_poll(unsigned int n, const int *fds);
+void *os_mmap_rw_shared(int fd, size_t size);
+void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size);
 
 /* start_up.c */
 extern void os_early_checks(void);
@@ -191,6 +195,9 @@ extern void get_host_cpu_features(
 /* mem.c */
 extern int create_mem_file(unsigned long long len);
 
+/* tlb.c */
+extern void report_enomem(void);
+
 /* process.c */
 extern unsigned long os_process_pc(int pid);
 extern int os_process_parent(int pid);
@@ -268,24 +275,20 @@ extern long long os_persistent_clock_emulation(void);
 extern long long os_nsecs(void);
 
 /* skas/mem.c */
-extern long run_syscall_stub(struct mm_id * mm_idp,
-			     int syscall, unsigned long *args, long expected,
-			     void **addr, int done);
-extern long syscall_stub_data(struct mm_id * mm_idp,
-			      unsigned long *data, int data_count,
-			      void **addr, void **stub_addr);
-extern int map(struct mm_id * mm_idp, unsigned long virt,
-	       unsigned long len, int prot, int phys_fd,
-	       unsigned long long offset, int done, void **data);
-extern int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len,
-		 int done, void **data);
-extern int protect(struct mm_id * mm_idp, unsigned long addr,
-		   unsigned long len, unsigned int prot, int done, void **data);
+int syscall_stub_flush(struct mm_id *mm_idp);
+struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp);
+void syscall_stub_dump_error(struct mm_id *mm_idp);
+
+int map(struct mm_id *mm_idp, unsigned long virt,
+	unsigned long len, int prot, int phys_fd,
+	unsigned long long offset);
+int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len);
+int protect(struct mm_id *mm_idp, unsigned long addr,
+	    unsigned long len, unsigned int prot);
 
 /* skas/process.c */
 extern int is_skas_winch(int pid, int fd, void *data);
 extern int start_userspace(unsigned long stub_stack);
-extern int copy_context_skas0(unsigned long stack, int pid);
 extern void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs);
 extern void new_thread(void *stack, jmp_buf *buf, void (*handler)(void));
 extern void switch_threads(jmp_buf *me, jmp_buf *you);
diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h
index 92dbf72..1e76ba4 100644
--- a/arch/um/include/shared/skas/mm_id.h
+++ b/arch/um/include/shared/skas/mm_id.h
@@ -12,7 +12,7 @@ struct mm_id {
 		int pid;
 	} u;
 	unsigned long stack;
-	int kill;
+	int syscall_data_len;
 };
 
 void __switch_mm(struct mm_id *mm_idp);
diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h
index c93d2cb..ebaa116 100644
--- a/arch/um/include/shared/skas/skas.h
+++ b/arch/um/include/shared/skas/skas.h
@@ -15,5 +15,7 @@ extern void new_thread_handler(void);
 extern void handle_syscall(struct uml_pt_regs *regs);
 extern long execute_syscall_skas(void *r);
 extern unsigned long current_stub_stack(void);
+extern struct mm_id *current_mm_id(void);
+extern void current_mm_sync(void);
 
 #endif
diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h
index 5e3ade3..2b6b447 100644
--- a/arch/um/include/shared/skas/stub-data.h
+++ b/arch/um/include/shared/skas/stub-data.h
@@ -8,10 +8,42 @@
 #ifndef __STUB_DATA_H
 #define __STUB_DATA_H
 
+#include <linux/compiler_types.h>
+#include <as-layout.h>
+#include <sysdep/tls.h>
+
+#define STUB_NEXT_SYSCALL(s) \
+	((struct stub_syscall *) (((unsigned long) s) + (s)->cmd_len))
+
+enum stub_syscall_type {
+	STUB_SYSCALL_UNSET = 0,
+	STUB_SYSCALL_MMAP,
+	STUB_SYSCALL_MUNMAP,
+	STUB_SYSCALL_MPROTECT,
+};
+
+struct stub_syscall {
+	struct {
+		unsigned long addr;
+		unsigned long length;
+		unsigned long offset;
+		int fd;
+		int prot;
+	} mem;
+
+	enum stub_syscall_type syscall;
+};
+
 struct stub_data {
 	unsigned long offset;
-	int fd;
-	long parent_err, child_err;
+	long err, child_err;
+
+	int syscall_data_len;
+	/* 128 leaves enough room for additional fields in the struct */
+	struct stub_syscall syscall_data[(UM_KERN_PAGE_SIZE - 128) / sizeof(struct stub_syscall)] __aligned(16);
+
+	/* Stack for our signal handlers and for calling into . */
+	unsigned char sigstack[UM_KERN_PAGE_SIZE] __aligned(UM_KERN_PAGE_SIZE);
 };
 
 #endif
diff --git a/arch/um/include/shared/timetravel.h b/arch/um/include/shared/timetravel.h
index e5c3d69..c8db2f2 100644
--- a/arch/um/include/shared/timetravel.h
+++ b/arch/um/include/shared/timetravel.h
@@ -15,8 +15,17 @@ enum time_travel_mode {
 #if defined(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT) || \
     defined(CONFIG_UML_TIME_TRAVEL_SUPPORT)
 extern enum time_travel_mode time_travel_mode;
+extern int time_travel_should_print_bc_msg;
 #else
 #define time_travel_mode TT_MODE_OFF
+#define time_travel_should_print_bc_msg 0
 #endif /* (UML_)CONFIG_UML_TIME_TRAVEL_SUPPORT */
 
+void _time_travel_print_bc_msg(void);
+static inline void time_travel_print_bc_msg(void)
+{
+	if (time_travel_should_print_bc_msg)
+		_time_travel_print_bc_msg();
+}
+
 #endif /* _UM_TIME_TRAVEL_H_ */
diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h
index 326e524..bbab79c 100644
--- a/arch/um/include/shared/user.h
+++ b/arch/um/include/shared/user.h
@@ -42,11 +42,19 @@ extern void panic(const char *fmt, ...)
 #define printk(...) _printk(__VA_ARGS__)
 extern int _printk(const char *fmt, ...)
 	__attribute__ ((format (printf, 1, 2)));
+extern void print_hex_dump(const char *level, const char *prefix_str,
+			   int prefix_type, int rowsize, int groupsize,
+			   const void *buf, size_t len, _Bool ascii);
 #else
 static inline int printk(const char *fmt, ...)
 {
 	return 0;
 }
+static inline void print_hex_dump(const char *level, const char *prefix_str,
+				  int prefix_type, int rowsize, int groupsize,
+				  const void *buf, size_t len, _Bool ascii)
+{
+}
 #endif
 
 extern int in_aton(char *str);
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 827a0d3..2c15bb2 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -22,17 +22,8 @@
 
 void flush_thread(void)
 {
-	void *data = NULL;
-	int ret;
-
 	arch_flush_thread(&current->thread.arch);
 
-	ret = unmap(&current->mm->context.id, 0, TASK_SIZE, 1, &data);
-	if (ret) {
-		printk(KERN_ERR "%s - clearing address space failed, err = %d\n",
-		       __func__, ret);
-		force_sig(SIGKILL);
-	}
 	get_safe_registers(current_pt_regs()->regs.gp,
 			   current_pt_regs()->regs.fp);
 
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 635d446..534e917 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -37,7 +37,7 @@ struct irq_reg {
 	bool pending;
 	bool wakeup;
 #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
-	bool pending_on_resume;
+	bool pending_event;
 	void (*timetravel_handler)(int, int, void *,
 				   struct time_travel_event *);
 	struct time_travel_event event;
@@ -56,6 +56,9 @@ static DEFINE_SPINLOCK(irq_lock);
 static LIST_HEAD(active_fds);
 static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ);
 static bool irqs_suspended;
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+static bool irqs_pending;
+#endif
 
 static void irq_io_loop(struct irq_reg *irq, struct uml_pt_regs *regs)
 {
@@ -84,9 +87,12 @@ static void irq_event_handler(struct time_travel_event *ev)
 {
 	struct irq_reg *reg = container_of(ev, struct irq_reg, event);
 
-	/* do nothing if suspended - just to cause a wakeup */
-	if (irqs_suspended)
+	/* do nothing if suspended; just cause a wakeup and mark as pending */
+	if (irqs_suspended) {
+		irqs_pending = true;
+		reg->pending_event = true;
 		return;
+	}
 
 	generic_handle_irq(reg->irq);
 }
@@ -110,16 +116,47 @@ static bool irq_do_timetravel_handler(struct irq_entry *entry,
 	if (!reg->event.pending)
 		return false;
 
-	if (irqs_suspended)
-		reg->pending_on_resume = true;
 	return true;
 }
+
+static void irq_do_pending_events(bool timetravel_handlers_only)
+{
+	struct irq_entry *entry;
+
+	if (!irqs_pending || timetravel_handlers_only)
+		return;
+
+	irqs_pending = false;
+
+	list_for_each_entry(entry, &active_fds, list) {
+		enum um_irq_type t;
+
+		for (t = 0; t < NUM_IRQ_TYPES; t++) {
+			struct irq_reg *reg = &entry->reg[t];
+
+			/*
+			 * Any timetravel_handler was invoked already, just
+			 * directly run the IRQ.
+			 */
+			if (reg->pending_event) {
+				irq_enter();
+				generic_handle_irq(reg->irq);
+				irq_exit();
+				reg->pending_event = false;
+			}
+		}
+	}
+}
 #else
 static bool irq_do_timetravel_handler(struct irq_entry *entry,
 				      enum um_irq_type t)
 {
 	return false;
 }
+
+static void irq_do_pending_events(bool timetravel_handlers_only)
+{
+}
 #endif
 
 static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type t,
@@ -145,6 +182,8 @@ static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type
 	 */
 	if (timetravel_handlers_only) {
 #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+		reg->pending_event = true;
+		irqs_pending = true;
 		mark_sigio_pending();
 #endif
 		return;
@@ -162,6 +201,10 @@ static void _sigio_handler(struct uml_pt_regs *regs,
 	if (timetravel_handlers_only && !um_irq_timetravel_handler_used())
 		return;
 
+	/* Flush out pending events that were ignored due to time-travel. */
+	if (!irqs_suspended)
+		irq_do_pending_events(timetravel_handlers_only);
+
 	while (1) {
 		/* This is now lockless - epoll keeps back-referencesto the irqs
 		 * which have trigger it so there is no need to walk the irq
@@ -195,7 +238,9 @@ static void _sigio_handler(struct uml_pt_regs *regs,
 
 void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 {
+	preempt_disable();
 	_sigio_handler(regs, irqs_suspended);
+	preempt_enable();
 }
 
 static struct irq_entry *get_irq_entry_by_fd(int fd)
@@ -543,30 +588,7 @@ void um_irqs_resume(void)
 	unsigned long flags;
 
 
-	local_irq_save(flags);
-#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
-	/*
-	 * We don't need to lock anything here since we're in resume
-	 * and nothing else is running, but have disabled IRQs so we
-	 * don't try anything else with the interrupt list from there.
-	 */
-	list_for_each_entry(entry, &active_fds, list) {
-		enum um_irq_type t;
-
-		for (t = 0; t < NUM_IRQ_TYPES; t++) {
-			struct irq_reg *reg = &entry->reg[t];
-
-			if (reg->pending_on_resume) {
-				irq_enter();
-				generic_handle_irq(reg->irq);
-				irq_exit();
-				reg->pending_on_resume = false;
-			}
-		}
-	}
-#endif
-
-	spin_lock(&irq_lock);
+	spin_lock_irqsave(&irq_lock, flags);
 	list_for_each_entry(entry, &active_fds, list) {
 		if (entry->suspended) {
 			int err = os_set_fd_async(entry->fd);
diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c
index 3a85bde..f2fb77d 100644
--- a/arch/um/kernel/ksyms.c
+++ b/arch/um/kernel/ksyms.c
@@ -33,7 +33,7 @@ EXPORT_SYMBOL(os_shutdown_socket);
 EXPORT_SYMBOL(os_create_unix_socket);
 EXPORT_SYMBOL(os_connect_socket);
 EXPORT_SYMBOL(os_accept_connection);
-EXPORT_SYMBOL(os_rcv_fd);
+EXPORT_SYMBOL(os_rcv_fd_msg);
 EXPORT_SYMBOL(run_helper);
 EXPORT_SYMBOL(os_major);
 EXPORT_SYMBOL(os_minor);
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index ca91acc..a5b4fe2 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -73,7 +73,6 @@ void __init mem_init(void)
 
 	/* this will put all low memory onto the freelists */
 	memblock_free_all();
-	max_low_pfn = totalram_pages();
 	max_pfn = max_low_pfn;
 	kmalloc_ok = 1;
 }
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index d213480..f36b63f 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -122,8 +122,6 @@ void new_thread_handler(void)
 /* Called magically, see new_thread_handler above */
 static void fork_handler(void)
 {
-	force_flush_all();
-
 	schedule_tail(current->thread.prev_sched);
 
 	/*
@@ -237,73 +235,6 @@ int copy_from_user_proc(void *to, void __user *from, int size)
 	return copy_from_user(to, from, size);
 }
 
-static atomic_t using_sysemu = ATOMIC_INIT(0);
-int sysemu_supported;
-
-static void set_using_sysemu(int value)
-{
-	if (value > sysemu_supported)
-		return;
-	atomic_set(&using_sysemu, value);
-}
-
-static int get_using_sysemu(void)
-{
-	return atomic_read(&using_sysemu);
-}
-
-static int sysemu_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%d\n", get_using_sysemu());
-	return 0;
-}
-
-static int sysemu_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sysemu_proc_show, NULL);
-}
-
-static ssize_t sysemu_proc_write(struct file *file, const char __user *buf,
-				 size_t count, loff_t *pos)
-{
-	char tmp[2];
-
-	if (copy_from_user(tmp, buf, 1))
-		return -EFAULT;
-
-	if (tmp[0] >= '0' && tmp[0] <= '2')
-		set_using_sysemu(tmp[0] - '0');
-	/* We use the first char, but pretend to write everything */
-	return count;
-}
-
-static const struct proc_ops sysemu_proc_ops = {
-	.proc_open	= sysemu_proc_open,
-	.proc_read	= seq_read,
-	.proc_lseek	= seq_lseek,
-	.proc_release	= single_release,
-	.proc_write	= sysemu_proc_write,
-};
-
-static int __init make_proc_sysemu(void)
-{
-	struct proc_dir_entry *ent;
-	if (!sysemu_supported)
-		return 0;
-
-	ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_ops);
-
-	if (ent == NULL)
-	{
-		printk(KERN_WARNING "Failed to register /proc/sysemu\n");
-		return 0;
-	}
-
-	return 0;
-}
-
-late_initcall(make_proc_sysemu);
-
 int singlestepping(void)
 {
 	return test_thread_flag(TIF_SINGLESTEP);
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index 25840ee..3736bca 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -59,3 +59,18 @@ void machine_halt(void)
 {
 	machine_power_off();
 }
+
+static int sys_power_off_handler(struct sys_off_data *data)
+{
+	machine_power_off();
+	return 0;
+}
+
+static int register_power_off(void)
+{
+	register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
+				 SYS_OFF_PRIO_DEFAULT,
+				 sys_power_off_handler, NULL);
+	return 0;
+}
+__initcall(register_power_off);
diff --git a/arch/um/kernel/skas/Makefile b/arch/um/kernel/skas/Makefile
index f93972a..6f86d53 100644
--- a/arch/um/kernel/skas/Makefile
+++ b/arch/um/kernel/skas/Makefile
@@ -3,15 +3,14 @@
 # Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
 #
 
-obj-y := clone.o mmu.o process.o syscall.o uaccess.o
+obj-y := stub.o mmu.o process.o syscall.o uaccess.o
 
-# clone.o is in the stub, so it can't be built with profiling
+# stub.o is in the stub, so it can't be built with profiling
 # GCC hardened also auto-enables -fpic, but we need %ebx so it can't work ->
 # disable it
 
-CFLAGS_clone.o := $(CFLAGS_NO_HARDENING)
-UNPROFILE_OBJS := clone.o
-
+CFLAGS_stub.o := $(CFLAGS_NO_HARDENING)
+UNPROFILE_OBJS := stub.o
 KCOV_INSTRUMENT := n
 
 include $(srctree)/arch/um/scripts/Makefile.rules
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
deleted file mode 100644
index 6243518..0000000
--- a/arch/um/kernel/skas/clone.c
+++ /dev/null
@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <signal.h>
-#include <sched.h>
-#include <asm/unistd.h>
-#include <sys/time.h>
-#include <as-layout.h>
-#include <ptrace_user.h>
-#include <stub-data.h>
-#include <sysdep/stub.h>
-
-/*
- * This is in a separate file because it needs to be compiled with any
- * extraneous gcc flags (-pg, -fprofile-arcs, -ftest-coverage) disabled
- *
- * Use UM_KERN_PAGE_SIZE instead of PAGE_SIZE because that calls getpagesize
- * on some systems.
- */
-
-void __attribute__ ((__section__ (".__syscall_stub")))
-stub_clone_handler(void)
-{
-	struct stub_data *data = get_stub_data();
-	long err;
-
-	err = stub_syscall2(__NR_clone, CLONE_PARENT | CLONE_FILES | SIGCHLD,
-			    (unsigned long)data +
-				STUB_DATA_PAGES * UM_KERN_PAGE_SIZE / 2);
-	if (err) {
-		data->parent_err = err;
-		goto done;
-	}
-
-	err = stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
-	if (err) {
-		data->child_err = err;
-		goto done;
-	}
-
-	remap_stack_and_trap();
-
- done:
-	trap_myself();
-}
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index aeed1c2a..47f98d8 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -14,11 +14,14 @@
 #include <as-layout.h>
 #include <os.h>
 #include <skas.h>
+#include <stub-data.h>
+
+/* Ensure the stub_data struct covers the allocated area */
+static_assert(sizeof(struct stub_data) == STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
 
 int init_new_context(struct task_struct *task, struct mm_struct *mm)
 {
- 	struct mm_context *from_mm = NULL;
-	struct mm_context *to_mm = &mm->context;
+	struct mm_id *new_id = &mm->context.id;
 	unsigned long stack = 0;
 	int ret = -ENOMEM;
 
@@ -26,34 +29,46 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 	if (stack == 0)
 		goto out;
 
-	to_mm->id.stack = stack;
-	if (current->mm != NULL && current->mm != &init_mm)
-		from_mm = &current->mm->context;
+	new_id->stack = stack;
 
 	block_signals_trace();
-	if (from_mm)
-		to_mm->id.u.pid = copy_context_skas0(stack,
-						     from_mm->id.u.pid);
-	else to_mm->id.u.pid = start_userspace(stack);
+	new_id->u.pid = start_userspace(stack);
 	unblock_signals_trace();
 
-	if (to_mm->id.u.pid < 0) {
-		ret = to_mm->id.u.pid;
+	if (new_id->u.pid < 0) {
+		ret = new_id->u.pid;
 		goto out_free;
 	}
 
-	ret = init_new_ldt(to_mm, from_mm);
-	if (ret < 0) {
-		printk(KERN_ERR "init_new_context_skas - init_ldt"
-		       " failed, errno = %d\n", ret);
-		goto out_free;
-	}
+	/*
+	 * Ensure the new MM is clean and nothing unwanted is mapped.
+	 *
+	 * TODO: We should clear the memory up to STUB_START to ensure there is
+	 * nothing mapped there, i.e. we (currently) have:
+	 *
+	 * |- user memory -|- unused        -|- stub        -|- unused    -|
+	 *                 ^ TASK_SIZE      ^ STUB_START
+	 *
+	 * Meaning we have two unused areas where we may still have valid
+	 * mappings from our internal clone(). That isn't really a problem as
+	 * userspace is not going to access them, but it is definitely not
+	 * correct.
+	 *
+	 * However, we are "lucky" and if rseq is configured, then on 32 bit
+	 * it will fall into the first empty range while on 64 bit it is going
+	 * to use an anonymous mapping in the second range. As such, things
+	 * continue to work for now as long as we don't start unmapping these
+	 * areas.
+	 *
+	 * Change this to STUB_START once we have a clean userspace.
+	 */
+	unmap(new_id, 0, TASK_SIZE);
 
 	return 0;
 
  out_free:
-	if (to_mm->id.stack != 0)
-		free_pages(to_mm->id.stack, ilog2(STUB_DATA_PAGES));
+	if (new_id->stack != 0)
+		free_pages(new_id->stack, ilog2(STUB_DATA_PAGES));
  out:
 	return ret;
 }
@@ -76,5 +91,4 @@ void destroy_context(struct mm_struct *mm)
 	os_kill_ptraced_process(mmu->id.u.pid, 1);
 
 	free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES));
-	free_ldt(mmu);
 }
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 99a5cbb..5f9c1c5 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -8,6 +8,8 @@
 #include <linux/sched/task_stack.h>
 #include <linux/sched/task.h>
 
+#include <asm/tlbflush.h>
+
 #include <as-layout.h>
 #include <kern.h>
 #include <os.h>
@@ -50,3 +52,19 @@ unsigned long current_stub_stack(void)
 
 	return current->mm->context.id.stack;
 }
+
+struct mm_id *current_mm_id(void)
+{
+	if (current->mm == NULL)
+		return NULL;
+
+	return &current->mm->context.id;
+}
+
+void current_mm_sync(void)
+{
+	if (current->mm == NULL)
+		return;
+
+	um_tlb_sync(current->mm);
+}
diff --git a/arch/um/kernel/skas/stub.c b/arch/um/kernel/skas/stub.c
new file mode 100644
index 0000000..5d52ffa
--- /dev/null
+++ b/arch/um/kernel/skas/stub.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
+ */
+
+#include <sysdep/stub.h>
+
+static __always_inline int syscall_handler(struct stub_data *d)
+{
+	int i;
+	unsigned long res;
+
+	for (i = 0; i < d->syscall_data_len; i++) {
+		struct stub_syscall *sc = &d->syscall_data[i];
+
+		switch (sc->syscall) {
+		case STUB_SYSCALL_MMAP:
+			res = stub_syscall6(STUB_MMAP_NR,
+					    sc->mem.addr, sc->mem.length,
+					    sc->mem.prot,
+					    MAP_SHARED | MAP_FIXED,
+					    sc->mem.fd, sc->mem.offset);
+			if (res != sc->mem.addr) {
+				d->err = res;
+				d->syscall_data_len = i;
+				return -1;
+			}
+			break;
+		case STUB_SYSCALL_MUNMAP:
+			res = stub_syscall2(__NR_munmap,
+					    sc->mem.addr, sc->mem.length);
+			if (res) {
+				d->err = res;
+				d->syscall_data_len = i;
+				return -1;
+			}
+			break;
+		case STUB_SYSCALL_MPROTECT:
+			res = stub_syscall3(__NR_mprotect,
+					    sc->mem.addr, sc->mem.length,
+					    sc->mem.prot);
+			if (res) {
+				d->err = res;
+				d->syscall_data_len = i;
+				return -1;
+			}
+			break;
+		default:
+			d->err = -95; /* EOPNOTSUPP */
+			d->syscall_data_len = i;
+			return -1;
+		}
+	}
+
+	d->err = 0;
+	d->syscall_data_len = 0;
+
+	return 0;
+}
+
+void __section(".__syscall_stub")
+stub_syscall_handler(void)
+{
+	struct stub_data *d = get_stub_data();
+
+	syscall_handler(d);
+
+	trap_myself();
+}
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index a8bfe8b..47b9f5e 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -31,6 +31,7 @@ EXPORT_SYMBOL_GPL(time_travel_mode);
 static bool time_travel_start_set;
 static unsigned long long time_travel_start;
 static unsigned long long time_travel_time;
+static unsigned long long time_travel_shm_offset;
 static LIST_HEAD(time_travel_events);
 static LIST_HEAD(time_travel_irqs);
 static unsigned long long time_travel_timer_interval;
@@ -40,8 +41,11 @@ static int time_travel_ext_fd = -1;
 static unsigned int time_travel_ext_waiting;
 static bool time_travel_ext_prev_request_valid;
 static unsigned long long time_travel_ext_prev_request;
-static bool time_travel_ext_free_until_valid;
-static unsigned long long time_travel_ext_free_until;
+static unsigned long long *time_travel_ext_free_until;
+static unsigned long long _time_travel_ext_free_until;
+static u16 time_travel_shm_id;
+static struct um_timetravel_schedshm *time_travel_shm;
+static union um_timetravel_schedshm_client *time_travel_shm_client;
 
 static void time_travel_set_time(unsigned long long ns)
 {
@@ -58,8 +62,52 @@ enum time_travel_message_handling {
 	TTMH_IDLE,
 	TTMH_POLL,
 	TTMH_READ,
+	TTMH_READ_START_ACK,
 };
 
+static u64 bc_message;
+int time_travel_should_print_bc_msg;
+
+void _time_travel_print_bc_msg(void)
+{
+	time_travel_should_print_bc_msg = 0;
+	printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message);
+}
+
+static void time_travel_setup_shm(int fd, u16 id)
+{
+	u32 len;
+
+	time_travel_shm = os_mmap_rw_shared(fd, sizeof(*time_travel_shm));
+
+	if (!time_travel_shm)
+		goto out;
+
+	len = time_travel_shm->len;
+
+	if (time_travel_shm->version != UM_TIMETRAVEL_SCHEDSHM_VERSION ||
+	    len < struct_size(time_travel_shm, clients, id + 1)) {
+		os_unmap_memory(time_travel_shm, sizeof(*time_travel_shm));
+		time_travel_shm = NULL;
+		goto out;
+	}
+
+	time_travel_shm = os_mremap_rw_shared(time_travel_shm,
+					      sizeof(*time_travel_shm),
+					      len);
+	if (!time_travel_shm)
+		goto out;
+
+	time_travel_shm_offset = time_travel_shm->current_time;
+	time_travel_shm_client = &time_travel_shm->clients[id];
+	time_travel_shm_client->capa |= UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE;
+	time_travel_shm_id = id;
+	/* always look at that free_until from now on */
+	time_travel_ext_free_until = &time_travel_shm->free_until;
+out:
+	os_close_file(fd);
+}
+
 static void time_travel_handle_message(struct um_timetravel_msg *msg,
 				       enum time_travel_message_handling mode)
 {
@@ -80,7 +128,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg,
 		}
 	}
 
-	ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg));
+	if (unlikely(mode == TTMH_READ_START_ACK)) {
+		int fd[UM_TIMETRAVEL_SHARED_MAX_FDS];
+
+		ret = os_rcv_fd_msg(time_travel_ext_fd, fd,
+				    ARRAY_SIZE(fd), msg, sizeof(*msg));
+		if (ret == sizeof(*msg)) {
+			time_travel_setup_shm(fd[UM_TIMETRAVEL_SHARED_MEMFD],
+					      msg->time & UM_TIMETRAVEL_START_ACK_ID);
+			/* we don't use the logging for now */
+			os_close_file(fd[UM_TIMETRAVEL_SHARED_LOGFD]);
+		}
+	} else {
+		ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg));
+	}
 
 	if (ret == 0)
 		panic("time-travel external link is broken\n");
@@ -96,10 +157,24 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg,
 		return;
 	case UM_TIMETRAVEL_RUN:
 		time_travel_set_time(msg->time);
+		if (time_travel_shm) {
+			/* no request right now since we're running */
+			time_travel_shm_client->flags &=
+				~UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN;
+			/* no ack for shared memory RUN */
+			return;
+		}
 		break;
 	case UM_TIMETRAVEL_FREE_UNTIL:
-		time_travel_ext_free_until_valid = true;
-		time_travel_ext_free_until = msg->time;
+		/* not supposed to get this with shm, but ignore it */
+		if (time_travel_shm)
+			break;
+		time_travel_ext_free_until = &_time_travel_ext_free_until;
+		_time_travel_ext_free_until = msg->time;
+		break;
+	case UM_TIMETRAVEL_BROADCAST:
+		bc_message = msg->time;
+		time_travel_should_print_bc_msg = 1;
 		break;
 	}
 
@@ -136,8 +211,15 @@ static u64 time_travel_ext_req(u32 op, u64 time)
 	block_signals_hard();
 	os_write_file(time_travel_ext_fd, &msg, sizeof(msg));
 
+	/* no ACK expected for WAIT in shared memory mode */
+	if (msg.op == UM_TIMETRAVEL_WAIT && time_travel_shm)
+		goto done;
+
 	while (msg.op != UM_TIMETRAVEL_ACK)
-		time_travel_handle_message(&msg, TTMH_READ);
+		time_travel_handle_message(&msg,
+					   op == UM_TIMETRAVEL_START ?
+						TTMH_READ_START_ACK :
+						TTMH_READ);
 
 	if (msg.seq != mseq)
 		panic("time-travel: ACK message has different seqno! op=%d, seq=%d != %d time=%lld\n",
@@ -145,6 +227,7 @@ static u64 time_travel_ext_req(u32 op, u64 time)
 
 	if (op == UM_TIMETRAVEL_GET)
 		time_travel_set_time(msg.time);
+done:
 	unblock_signals_hard();
 
 	return msg.time;
@@ -180,13 +263,33 @@ static void time_travel_ext_update_request(unsigned long long time)
 	/*
 	 * if we're running and are allowed to run past the request
 	 * then we don't need to update it either
+	 *
+	 * Note for shm we ignore FREE_UNTIL messages and leave the pointer
+	 * to shared memory, and for non-shm the offset is 0.
 	 */
-	if (!time_travel_ext_waiting && time_travel_ext_free_until_valid &&
-	    time < time_travel_ext_free_until)
+	if (!time_travel_ext_waiting && time_travel_ext_free_until &&
+	    time < (*time_travel_ext_free_until - time_travel_shm_offset))
 		return;
 
 	time_travel_ext_prev_request = time;
 	time_travel_ext_prev_request_valid = true;
+
+	if (time_travel_shm) {
+		union um_timetravel_schedshm_client *running;
+
+		running = &time_travel_shm->clients[time_travel_shm->running_id];
+
+		if (running->capa & UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE) {
+			time_travel_shm_client->flags |=
+				UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN;
+			time += time_travel_shm_offset;
+			time_travel_shm_client->req_time = time;
+			if (time < time_travel_shm->free_until)
+				time_travel_shm->free_until = time;
+			return;
+		}
+	}
+
 	time_travel_ext_req(UM_TIMETRAVEL_REQUEST, time);
 }
 
@@ -194,6 +297,14 @@ void __time_travel_propagate_time(void)
 {
 	static unsigned long long last_propagated;
 
+	if (time_travel_shm) {
+		if (time_travel_shm->running_id != time_travel_shm_id)
+			panic("time-travel: setting time while not running\n");
+		time_travel_shm->current_time = time_travel_time +
+						time_travel_shm_offset;
+		return;
+	}
+
 	if (last_propagated == time_travel_time)
 		return;
 
@@ -209,9 +320,12 @@ static bool time_travel_ext_request(unsigned long long time)
 	 * If we received an external sync point ("free until") then we
 	 * don't have to request/wait for anything until then, unless
 	 * we're already waiting.
+	 *
+	 * Note for shm we ignore FREE_UNTIL messages and leave the pointer
+	 * to shared memory, and for non-shm the offset is 0.
 	 */
-	if (!time_travel_ext_waiting && time_travel_ext_free_until_valid &&
-	    time < time_travel_ext_free_until)
+	if (!time_travel_ext_waiting && time_travel_ext_free_until &&
+	    time < (*time_travel_ext_free_until - time_travel_shm_offset))
 		return false;
 
 	time_travel_ext_update_request(time);
@@ -225,7 +339,8 @@ static void time_travel_ext_wait(bool idle)
 	};
 
 	time_travel_ext_prev_request_valid = false;
-	time_travel_ext_free_until_valid = false;
+	if (!time_travel_shm)
+		time_travel_ext_free_until = NULL;
 	time_travel_ext_waiting++;
 
 	time_travel_ext_req(UM_TIMETRAVEL_WAIT, -1);
@@ -248,7 +363,11 @@ static void time_travel_ext_wait(bool idle)
 
 static void time_travel_ext_get_time(void)
 {
-	time_travel_ext_req(UM_TIMETRAVEL_GET, -1);
+	if (time_travel_shm)
+		time_travel_set_time(time_travel_shm->current_time -
+				     time_travel_shm_offset);
+	else
+		time_travel_ext_req(UM_TIMETRAVEL_GET, -1);
 }
 
 static void __time_travel_update_time(unsigned long long ns, bool idle)
@@ -875,9 +994,49 @@ static int setup_time_travel_start(char *str)
 	return 1;
 }
 
-__setup("time-travel-start", setup_time_travel_start);
+__setup("time-travel-start=", setup_time_travel_start);
 __uml_help(setup_time_travel_start,
-"time-travel-start=<seconds>\n"
+"time-travel-start=<nanoseconds>\n"
 "Configure the UML instance's wall clock to start at this value rather than\n"
 "the host's wall clock at the time of UML boot.\n");
+static struct kobject *bc_time_kobject;
+
+static ssize_t bc_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%llx", bc_message);
+}
+
+static ssize_t bc_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	int ret;
+	u64 user_bc_message;
+
+	ret = kstrtou64(buf, 0, &user_bc_message);
+	if (ret)
+		return ret;
+
+	bc_message = user_bc_message;
+
+	time_travel_ext_req(UM_TIMETRAVEL_BROADCAST, bc_message);
+	pr_info("um: time: sent broadcast message: 0x%llx\n", bc_message);
+	return count;
+}
+
+static struct kobj_attribute bc_attribute = __ATTR(bc-message, 0660, bc_show, bc_store);
+
+static int __init um_bc_start(void)
+{
+	if (time_travel_mode != TT_MODE_EXTERNAL)
+		return 0;
+
+	bc_time_kobject = kobject_create_and_add("um-ext-time", kernel_kobj);
+	if (!bc_time_kobject)
+		return 0;
+
+	if (sysfs_create_file(bc_time_kobject, &bc_attribute.attr))
+		pr_debug("failed to create the bc file in /sys/kernel/um_time");
+
+	return 0;
+}
+late_initcall(um_bc_start);
 #endif
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 8784f03..44c6fc6 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -15,209 +15,54 @@
 #include <skas.h>
 #include <kern_util.h>
 
-struct host_vm_change {
-	struct host_vm_op {
-		enum { NONE, MMAP, MUNMAP, MPROTECT } type;
-		union {
-			struct {
-				unsigned long addr;
-				unsigned long len;
-				unsigned int prot;
-				int fd;
-				__u64 offset;
-			} mmap;
-			struct {
-				unsigned long addr;
-				unsigned long len;
-			} munmap;
-			struct {
-				unsigned long addr;
-				unsigned long len;
-				unsigned int prot;
-			} mprotect;
-		} u;
-	} ops[1];
-	int userspace;
-	int index;
-	struct mm_struct *mm;
-	void *data;
-	int force;
+struct vm_ops {
+	struct mm_id *mm_idp;
+
+	int (*mmap)(struct mm_id *mm_idp,
+		    unsigned long virt, unsigned long len, int prot,
+		    int phys_fd, unsigned long long offset);
+	int (*unmap)(struct mm_id *mm_idp,
+		     unsigned long virt, unsigned long len);
+	int (*mprotect)(struct mm_id *mm_idp,
+			unsigned long virt, unsigned long len,
+			unsigned int prot);
 };
 
-#define INIT_HVC(mm, force, userspace) \
-	((struct host_vm_change) \
-	 { .ops		= { { .type = NONE } },	\
-	   .mm		= mm, \
-       	   .data	= NULL, \
-	   .userspace	= userspace, \
-	   .index	= 0, \
-	   .force	= force })
+static int kern_map(struct mm_id *mm_idp,
+		    unsigned long virt, unsigned long len, int prot,
+		    int phys_fd, unsigned long long offset)
+{
+	/* TODO: Why is executable needed to be always set in the kernel? */
+	return os_map_memory((void *)virt, phys_fd, offset, len,
+			     prot & UM_PROT_READ, prot & UM_PROT_WRITE,
+			     1);
+}
 
-static void report_enomem(void)
+static int kern_unmap(struct mm_id *mm_idp,
+		      unsigned long virt, unsigned long len)
+{
+	return os_unmap_memory((void *)virt, len);
+}
+
+static int kern_mprotect(struct mm_id *mm_idp,
+			 unsigned long virt, unsigned long len,
+			 unsigned int prot)
+{
+	return os_protect_memory((void *)virt, len,
+				 prot & UM_PROT_READ, prot & UM_PROT_WRITE,
+				 1);
+}
+
+void report_enomem(void)
 {
 	printk(KERN_ERR "UML ran out of memory on the host side! "
 			"This can happen due to a memory limitation or "
 			"vm.max_map_count has been reached.\n");
 }
 
-static int do_ops(struct host_vm_change *hvc, int end,
-		  int finished)
-{
-	struct host_vm_op *op;
-	int i, ret = 0;
-
-	for (i = 0; i < end && !ret; i++) {
-		op = &hvc->ops[i];
-		switch (op->type) {
-		case MMAP:
-			if (hvc->userspace)
-				ret = map(&hvc->mm->context.id, op->u.mmap.addr,
-					  op->u.mmap.len, op->u.mmap.prot,
-					  op->u.mmap.fd,
-					  op->u.mmap.offset, finished,
-					  &hvc->data);
-			else
-				map_memory(op->u.mmap.addr, op->u.mmap.offset,
-					   op->u.mmap.len, 1, 1, 1);
-			break;
-		case MUNMAP:
-			if (hvc->userspace)
-				ret = unmap(&hvc->mm->context.id,
-					    op->u.munmap.addr,
-					    op->u.munmap.len, finished,
-					    &hvc->data);
-			else
-				ret = os_unmap_memory(
-					(void *) op->u.munmap.addr,
-						      op->u.munmap.len);
-
-			break;
-		case MPROTECT:
-			if (hvc->userspace)
-				ret = protect(&hvc->mm->context.id,
-					      op->u.mprotect.addr,
-					      op->u.mprotect.len,
-					      op->u.mprotect.prot,
-					      finished, &hvc->data);
-			else
-				ret = os_protect_memory(
-					(void *) op->u.mprotect.addr,
-							op->u.mprotect.len,
-							1, 1, 1);
-			break;
-		default:
-			printk(KERN_ERR "Unknown op type %d in do_ops\n",
-			       op->type);
-			BUG();
-			break;
-		}
-	}
-
-	if (ret == -ENOMEM)
-		report_enomem();
-
-	return ret;
-}
-
-static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len,
-		    unsigned int prot, struct host_vm_change *hvc)
-{
-	__u64 offset;
-	struct host_vm_op *last;
-	int fd = -1, ret = 0;
-
-	if (hvc->userspace)
-		fd = phys_mapping(phys, &offset);
-	else
-		offset = phys;
-	if (hvc->index != 0) {
-		last = &hvc->ops[hvc->index - 1];
-		if ((last->type == MMAP) &&
-		   (last->u.mmap.addr + last->u.mmap.len == virt) &&
-		   (last->u.mmap.prot == prot) && (last->u.mmap.fd == fd) &&
-		   (last->u.mmap.offset + last->u.mmap.len == offset)) {
-			last->u.mmap.len += len;
-			return 0;
-		}
-	}
-
-	if (hvc->index == ARRAY_SIZE(hvc->ops)) {
-		ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0);
-		hvc->index = 0;
-	}
-
-	hvc->ops[hvc->index++] = ((struct host_vm_op)
-				  { .type	= MMAP,
-				    .u = { .mmap = { .addr	= virt,
-						     .len	= len,
-						     .prot	= prot,
-						     .fd	= fd,
-						     .offset	= offset }
-			   } });
-	return ret;
-}
-
-static int add_munmap(unsigned long addr, unsigned long len,
-		      struct host_vm_change *hvc)
-{
-	struct host_vm_op *last;
-	int ret = 0;
-
-	if (hvc->index != 0) {
-		last = &hvc->ops[hvc->index - 1];
-		if ((last->type == MUNMAP) &&
-		   (last->u.munmap.addr + last->u.mmap.len == addr)) {
-			last->u.munmap.len += len;
-			return 0;
-		}
-	}
-
-	if (hvc->index == ARRAY_SIZE(hvc->ops)) {
-		ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0);
-		hvc->index = 0;
-	}
-
-	hvc->ops[hvc->index++] = ((struct host_vm_op)
-				  { .type	= MUNMAP,
-			     	    .u = { .munmap = { .addr	= addr,
-						       .len	= len } } });
-	return ret;
-}
-
-static int add_mprotect(unsigned long addr, unsigned long len,
-			unsigned int prot, struct host_vm_change *hvc)
-{
-	struct host_vm_op *last;
-	int ret = 0;
-
-	if (hvc->index != 0) {
-		last = &hvc->ops[hvc->index - 1];
-		if ((last->type == MPROTECT) &&
-		   (last->u.mprotect.addr + last->u.mprotect.len == addr) &&
-		   (last->u.mprotect.prot == prot)) {
-			last->u.mprotect.len += len;
-			return 0;
-		}
-	}
-
-	if (hvc->index == ARRAY_SIZE(hvc->ops)) {
-		ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0);
-		hvc->index = 0;
-	}
-
-	hvc->ops[hvc->index++] = ((struct host_vm_op)
-				  { .type	= MPROTECT,
-			     	    .u = { .mprotect = { .addr	= addr,
-							 .len	= len,
-							 .prot	= prot } } });
-	return ret;
-}
-
-#define ADD_ROUND(n, inc) (((n) + (inc)) & ~((inc) - 1))
-
 static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
 				   unsigned long end,
-				   struct host_vm_change *hvc)
+				   struct vm_ops *ops)
 {
 	pte_t *pte;
 	int r, w, x, prot, ret = 0;
@@ -235,15 +80,22 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
 
 		prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |
 			(x ? UM_PROT_EXEC : 0));
-		if (hvc->force || pte_newpage(*pte)) {
+		if (pte_newpage(*pte)) {
 			if (pte_present(*pte)) {
-				if (pte_newpage(*pte))
-					ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK,
-						       PAGE_SIZE, prot, hvc);
+				if (pte_newpage(*pte)) {
+					__u64 offset;
+					unsigned long phys =
+						pte_val(*pte) & PAGE_MASK;
+					int fd =  phys_mapping(phys, &offset);
+
+					ret = ops->mmap(ops->mm_idp, addr,
+							PAGE_SIZE, prot, fd,
+							offset);
+				}
 			} else
-				ret = add_munmap(addr, PAGE_SIZE, hvc);
+				ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE);
 		} else if (pte_newprot(*pte))
-			ret = add_mprotect(addr, PAGE_SIZE, prot, hvc);
+			ret = ops->mprotect(ops->mm_idp, addr, PAGE_SIZE, prot);
 		*pte = pte_mkuptodate(*pte);
 	} while (pte++, addr += PAGE_SIZE, ((addr < end) && !ret));
 	return ret;
@@ -251,7 +103,7 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
 
 static inline int update_pmd_range(pud_t *pud, unsigned long addr,
 				   unsigned long end,
-				   struct host_vm_change *hvc)
+				   struct vm_ops *ops)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -261,19 +113,20 @@ static inline int update_pmd_range(pud_t *pud, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		if (!pmd_present(*pmd)) {
-			if (hvc->force || pmd_newpage(*pmd)) {
-				ret = add_munmap(addr, next - addr, hvc);
+			if (pmd_newpage(*pmd)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
 				pmd_mkuptodate(*pmd);
 			}
 		}
-		else ret = update_pte_range(pmd, addr, next, hvc);
+		else ret = update_pte_range(pmd, addr, next, ops);
 	} while (pmd++, addr = next, ((addr < end) && !ret));
 	return ret;
 }
 
 static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
 				   unsigned long end,
-				   struct host_vm_change *hvc)
+				   struct vm_ops *ops)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -283,19 +136,20 @@ static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
 	do {
 		next = pud_addr_end(addr, end);
 		if (!pud_present(*pud)) {
-			if (hvc->force || pud_newpage(*pud)) {
-				ret = add_munmap(addr, next - addr, hvc);
+			if (pud_newpage(*pud)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
 				pud_mkuptodate(*pud);
 			}
 		}
-		else ret = update_pmd_range(pud, addr, next, hvc);
+		else ret = update_pmd_range(pud, addr, next, ops);
 	} while (pud++, addr = next, ((addr < end) && !ret));
 	return ret;
 }
 
 static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
 				   unsigned long end,
-				   struct host_vm_change *hvc)
+				   struct vm_ops *ops)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -305,227 +159,59 @@ static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
 	do {
 		next = p4d_addr_end(addr, end);
 		if (!p4d_present(*p4d)) {
-			if (hvc->force || p4d_newpage(*p4d)) {
-				ret = add_munmap(addr, next - addr, hvc);
+			if (p4d_newpage(*p4d)) {
+				ret = ops->unmap(ops->mm_idp, addr,
+						 next - addr);
 				p4d_mkuptodate(*p4d);
 			}
 		} else
-			ret = update_pud_range(p4d, addr, next, hvc);
+			ret = update_pud_range(p4d, addr, next, ops);
 	} while (p4d++, addr = next, ((addr < end) && !ret));
 	return ret;
 }
 
-static void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
-			     unsigned long end_addr, int force)
+int um_tlb_sync(struct mm_struct *mm)
 {
 	pgd_t *pgd;
-	struct host_vm_change hvc;
-	unsigned long addr = start_addr, next;
-	int ret = 0, userspace = 1;
+	struct vm_ops ops;
+	unsigned long addr = mm->context.sync_tlb_range_from, next;
+	int ret = 0;
 
-	hvc = INIT_HVC(mm, force, userspace);
+	if (mm->context.sync_tlb_range_to == 0)
+		return 0;
+
+	ops.mm_idp = &mm->context.id;
+	if (mm == &init_mm) {
+		ops.mmap = kern_map;
+		ops.unmap = kern_unmap;
+		ops.mprotect = kern_mprotect;
+	} else {
+		ops.mmap = map;
+		ops.unmap = unmap;
+		ops.mprotect = protect;
+	}
+
 	pgd = pgd_offset(mm, addr);
 	do {
-		next = pgd_addr_end(addr, end_addr);
+		next = pgd_addr_end(addr, mm->context.sync_tlb_range_to);
 		if (!pgd_present(*pgd)) {
-			if (force || pgd_newpage(*pgd)) {
-				ret = add_munmap(addr, next - addr, &hvc);
+			if (pgd_newpage(*pgd)) {
+				ret = ops.unmap(ops.mm_idp, addr,
+						next - addr);
 				pgd_mkuptodate(*pgd);
 			}
 		} else
-			ret = update_p4d_range(pgd, addr, next, &hvc);
-	} while (pgd++, addr = next, ((addr < end_addr) && !ret));
+			ret = update_p4d_range(pgd, addr, next, &ops);
+	} while (pgd++, addr = next,
+		 ((addr < mm->context.sync_tlb_range_to) && !ret));
 
-	if (!ret)
-		ret = do_ops(&hvc, hvc.index, 1);
+	if (ret == -ENOMEM)
+		report_enomem();
 
-	/* This is not an else because ret is modified above */
-	if (ret) {
-		struct mm_id *mm_idp = &current->mm->context.id;
+	mm->context.sync_tlb_range_from = 0;
+	mm->context.sync_tlb_range_to = 0;
 
-		printk(KERN_ERR "fix_range_common: failed, killing current "
-		       "process: %d\n", task_tgid_vnr(current));
-		mm_idp->kill = 1;
-	}
-}
-
-static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
-{
-	struct mm_struct *mm;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	unsigned long addr, last;
-	int updated = 0, err = 0, force = 0, userspace = 0;
-	struct host_vm_change hvc;
-
-	mm = &init_mm;
-	hvc = INIT_HVC(mm, force, userspace);
-	for (addr = start; addr < end;) {
-		pgd = pgd_offset(mm, addr);
-		if (!pgd_present(*pgd)) {
-			last = ADD_ROUND(addr, PGDIR_SIZE);
-			if (last > end)
-				last = end;
-			if (pgd_newpage(*pgd)) {
-				updated = 1;
-				err = add_munmap(addr, last - addr, &hvc);
-				if (err < 0)
-					panic("munmap failed, errno = %d\n",
-					      -err);
-			}
-			addr = last;
-			continue;
-		}
-
-		p4d = p4d_offset(pgd, addr);
-		if (!p4d_present(*p4d)) {
-			last = ADD_ROUND(addr, P4D_SIZE);
-			if (last > end)
-				last = end;
-			if (p4d_newpage(*p4d)) {
-				updated = 1;
-				err = add_munmap(addr, last - addr, &hvc);
-				if (err < 0)
-					panic("munmap failed, errno = %d\n",
-					      -err);
-			}
-			addr = last;
-			continue;
-		}
-
-		pud = pud_offset(p4d, addr);
-		if (!pud_present(*pud)) {
-			last = ADD_ROUND(addr, PUD_SIZE);
-			if (last > end)
-				last = end;
-			if (pud_newpage(*pud)) {
-				updated = 1;
-				err = add_munmap(addr, last - addr, &hvc);
-				if (err < 0)
-					panic("munmap failed, errno = %d\n",
-					      -err);
-			}
-			addr = last;
-			continue;
-		}
-
-		pmd = pmd_offset(pud, addr);
-		if (!pmd_present(*pmd)) {
-			last = ADD_ROUND(addr, PMD_SIZE);
-			if (last > end)
-				last = end;
-			if (pmd_newpage(*pmd)) {
-				updated = 1;
-				err = add_munmap(addr, last - addr, &hvc);
-				if (err < 0)
-					panic("munmap failed, errno = %d\n",
-					      -err);
-			}
-			addr = last;
-			continue;
-		}
-
-		pte = pte_offset_kernel(pmd, addr);
-		if (!pte_present(*pte) || pte_newpage(*pte)) {
-			updated = 1;
-			err = add_munmap(addr, PAGE_SIZE, &hvc);
-			if (err < 0)
-				panic("munmap failed, errno = %d\n",
-				      -err);
-			if (pte_present(*pte))
-				err = add_mmap(addr, pte_val(*pte) & PAGE_MASK,
-					       PAGE_SIZE, 0, &hvc);
-		}
-		else if (pte_newprot(*pte)) {
-			updated = 1;
-			err = add_mprotect(addr, PAGE_SIZE, 0, &hvc);
-		}
-		addr += PAGE_SIZE;
-	}
-	if (!err)
-		err = do_ops(&hvc, hvc.index, 1);
-
-	if (err < 0)
-		panic("flush_tlb_kernel failed, errno = %d\n", err);
-	return updated;
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	struct mm_struct *mm = vma->vm_mm;
-	void *flush = NULL;
-	int r, w, x, prot, err = 0;
-	struct mm_id *mm_id;
-
-	address &= PAGE_MASK;
-
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		goto kill;
-
-	p4d = p4d_offset(pgd, address);
-	if (!p4d_present(*p4d))
-		goto kill;
-
-	pud = pud_offset(p4d, address);
-	if (!pud_present(*pud))
-		goto kill;
-
-	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd))
-		goto kill;
-
-	pte = pte_offset_kernel(pmd, address);
-
-	r = pte_read(*pte);
-	w = pte_write(*pte);
-	x = pte_exec(*pte);
-	if (!pte_young(*pte)) {
-		r = 0;
-		w = 0;
-	} else if (!pte_dirty(*pte)) {
-		w = 0;
-	}
-
-	mm_id = &mm->context.id;
-	prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |
-		(x ? UM_PROT_EXEC : 0));
-	if (pte_newpage(*pte)) {
-		if (pte_present(*pte)) {
-			unsigned long long offset;
-			int fd;
-
-			fd = phys_mapping(pte_val(*pte) & PAGE_MASK, &offset);
-			err = map(mm_id, address, PAGE_SIZE, prot, fd, offset,
-				  1, &flush);
-		}
-		else err = unmap(mm_id, address, PAGE_SIZE, 1, &flush);
-	}
-	else if (pte_newprot(*pte))
-		err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush);
-
-	if (err) {
-		if (err == -ENOMEM)
-			report_enomem();
-
-		goto kill;
-	}
-
-	*pte = pte_mkuptodate(*pte);
-
-	return;
-
-kill:
-	printk(KERN_ERR "Failed to flush page for address 0x%lx\n", address);
-	force_sig(SIGKILL);
+	return ret;
 }
 
 void flush_tlb_all(void)
@@ -540,60 +226,11 @@ void flush_tlb_all(void)
 	flush_tlb_mm(current->mm);
 }
 
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	flush_tlb_kernel_range_common(start, end);
-}
-
-void flush_tlb_kernel_vm(void)
-{
-	flush_tlb_kernel_range_common(start_vm, end_vm);
-}
-
-void __flush_tlb_one(unsigned long addr)
-{
-	flush_tlb_kernel_range_common(addr, addr + PAGE_SIZE);
-}
-
-static void fix_range(struct mm_struct *mm, unsigned long start_addr,
-		      unsigned long end_addr, int force)
-{
-	/*
-	 * Don't bother flushing if this address space is about to be
-	 * destroyed.
-	 */
-	if (atomic_read(&mm->mm_users) == 0)
-		return;
-
-	fix_range_common(mm, start_addr, end_addr, force);
-}
-
-void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
-		     unsigned long end)
-{
-	if (vma->vm_mm == NULL)
-		flush_tlb_kernel_range_common(start, end);
-	else fix_range(vma->vm_mm, start, end, 0);
-}
-EXPORT_SYMBOL(flush_tlb_range);
-
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
 	VMA_ITERATOR(vmi, mm, 0);
 
 	for_each_vma(vmi, vma)
-		fix_range(mm, vma->vm_start, vma->vm_end, 0);
-}
-
-void force_flush_all(void)
-{
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma)
-		fix_range(mm, vma->vm_start, vma->vm_end, 1);
-	mmap_read_unlock(mm);
+		um_tlb_mark_sync(mm, vma->vm_start, vma->vm_end);
 }
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 6d8ae86..97c8df9 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -113,7 +113,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 #if 0
 	WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
 #endif
-	flush_tlb_page(vma, address);
+
 out:
 	mmap_read_unlock(mm);
 out_nosemaphore:
@@ -210,8 +210,17 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 	if (!is_user && regs)
 		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);
 
-	if (!is_user && (address >= start_vm) && (address < end_vm)) {
-		flush_tlb_kernel_vm();
+	if (!is_user && init_mm.context.sync_tlb_range_to) {
+		/*
+		 * Kernel has pending updates from set_ptes that were not
+		 * flushed yet. Syncing them should fix the pagefault (if not
+		 * we'll get here again and panic).
+		 */
+		err = um_tlb_sync(&init_mm);
+		if (err == -ENOMEM)
+			report_enomem();
+		if (err)
+			panic("Failed to sync kernel TLBs: %d", err);
 		goto out;
 	}
 	else if (current->mm == NULL) {
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index e95f805..8e594cd 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -126,9 +126,6 @@ unsigned long uml_reserved; /* Also modified in mem_init */
 unsigned long start_vm;
 unsigned long end_vm;
 
-/* Set in uml_ncpus_setup */
-int ncpus = 1;
-
 /* Set in early boot */
 static int have_root __initdata;
 static int have_console __initdata;
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index fc4450d..5adf8f6 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -17,6 +17,7 @@
 #include <sys/stat.h>
 #include <sys/sysmacros.h>
 #include <sys/un.h>
+#include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/eventfd.h>
 #include <poll.h>
@@ -240,6 +241,16 @@ int os_connect_socket(const char *name)
 	return err;
 }
 
+int os_dup_file(int fd)
+{
+	int new_fd = dup(fd);
+
+	if (new_fd < 0)
+		return -errno;
+
+	return new_fd;
+}
+
 void os_close_file(int fd)
 {
 	close(fd);
@@ -502,44 +513,47 @@ int os_shutdown_socket(int fd, int r, int w)
 	return 0;
 }
 
-int os_rcv_fd(int fd, int *helper_pid_out)
+/**
+ * os_rcv_fd_msg - receive message with (optional) FDs
+ * @fd: the FD to receive from
+ * @fds: the array for FDs to write to
+ * @n_fds: number of FDs to receive (@fds array size)
+ * @data: the message buffer
+ * @data_len: the size of the message to receive
+ *
+ * Receive a message with FDs.
+ *
+ * Returns: the size of the received message, or an error code
+ */
+ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds,
+		      void *data, size_t data_len)
 {
-	int new, n;
-	char buf[CMSG_SPACE(sizeof(new))];
-	struct msghdr msg;
+	char buf[CMSG_SPACE(sizeof(*fds) * n_fds)];
 	struct cmsghdr *cmsg;
-	struct iovec iov;
-
-	msg.msg_name = NULL;
-	msg.msg_namelen = 0;
-	iov = ((struct iovec) { .iov_base  = helper_pid_out,
-				.iov_len   = sizeof(*helper_pid_out) });
-	msg.msg_iov = &iov;
-	msg.msg_iovlen = 1;
-	msg.msg_control = buf;
-	msg.msg_controllen = sizeof(buf);
-	msg.msg_flags = 0;
+	struct iovec iov = {
+		.iov_base = data,
+		.iov_len = data_len,
+	};
+	struct msghdr msg = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = buf,
+		.msg_controllen = sizeof(buf),
+	};
+	int n;
 
 	n = recvmsg(fd, &msg, 0);
 	if (n < 0)
 		return -errno;
-	else if (n != iov.iov_len)
-		*helper_pid_out = -1;
 
 	cmsg = CMSG_FIRSTHDR(&msg);
-	if (cmsg == NULL) {
-		printk(UM_KERN_ERR "rcv_fd didn't receive anything, "
-		       "error = %d\n", errno);
-		return -1;
-	}
-	if ((cmsg->cmsg_level != SOL_SOCKET) ||
-	    (cmsg->cmsg_type != SCM_RIGHTS)) {
-		printk(UM_KERN_ERR "rcv_fd didn't receive a descriptor\n");
-		return -1;
-	}
+	if (!cmsg ||
+	    cmsg->cmsg_level != SOL_SOCKET ||
+	    cmsg->cmsg_type != SCM_RIGHTS)
+		return n;
 
-	new = ((int *) CMSG_DATA(cmsg))[0];
-	return new;
+	memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len);
+	return n;
 }
 
 int os_create_unix_socket(const char *file, int len, int close_on_exec)
@@ -705,3 +719,25 @@ int os_poll(unsigned int n, const int *fds)
 
 	return -EIO;
 }
+
+void *os_mmap_rw_shared(int fd, size_t size)
+{
+	void *res = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+
+	if (res == MAP_FAILED)
+		return NULL;
+
+	return res;
+}
+
+void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size)
+{
+	void *res;
+
+	res = mremap(old_addr, old_size, new_size, MREMAP_MAYMOVE, NULL);
+
+	if (res == MAP_FAILED)
+		return NULL;
+
+	return res;
+}
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 787cfb9..b11ed66 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -8,6 +8,7 @@
 
 #include <stdlib.h>
 #include <stdarg.h>
+#include <stdbool.h>
 #include <errno.h>
 #include <signal.h>
 #include <string.h>
@@ -65,9 +66,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 
 int signals_enabled;
 #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
-static int signals_blocked;
-#else
-#define signals_blocked 0
+static int signals_blocked, signals_blocked_pending;
 #endif
 static unsigned int signals_pending;
 static unsigned int signals_active = 0;
@@ -76,14 +75,27 @@ static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
 {
 	int enabled = signals_enabled;
 
-	if ((signals_blocked || !enabled) && (sig == SIGIO)) {
+#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
+	if ((signals_blocked ||
+	     __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) &&
+	    (sig == SIGIO)) {
+		/* increment so unblock will do another round */
+		__atomic_add_fetch(&signals_blocked_pending, 1,
+				   __ATOMIC_SEQ_CST);
+		return;
+	}
+#endif
+
+	if (!enabled && (sig == SIGIO)) {
 		/*
 		 * In TT_MODE_EXTERNAL, need to still call time-travel
-		 * handlers unless signals are also blocked for the
-		 * external time message processing. This will mark
-		 * signals_pending by itself (only if necessary.)
+		 * handlers. This will mark signals_pending by itself
+		 * (only if necessary.)
+		 * Note we won't get here if signals are hard-blocked
+		 * (which is handled above), in that case the hard-
+		 * unblock will handle things.
 		 */
-		if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL)
+		if (time_travel_mode == TT_MODE_EXTERNAL)
 			sigio_run_timetravel_handlers();
 		else
 			signals_pending |= SIGIO_MASK;
@@ -380,33 +392,99 @@ int um_set_signals_trace(int enable)
 #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
 void mark_sigio_pending(void)
 {
+	/*
+	 * It would seem that this should be atomic so
+	 * it isn't a read-modify-write with a signal
+	 * that could happen in the middle, losing the
+	 * value set by the signal.
+	 *
+	 * However, this function is only called when in
+	 * time-travel=ext simulation mode, in which case
+	 * the only signal ever pending is SIGIO, which
+	 * is blocked while this can be called, and the
+	 * timer signal (SIGALRM) cannot happen.
+	 */
 	signals_pending |= SIGIO_MASK;
 }
 
 void block_signals_hard(void)
 {
-	if (signals_blocked)
-		return;
-	signals_blocked = 1;
+	signals_blocked++;
 	barrier();
 }
 
 void unblock_signals_hard(void)
 {
+	static bool unblocking;
+
 	if (!signals_blocked)
+		panic("unblocking signals while not blocked");
+
+	if (--signals_blocked)
 		return;
-	/* Must be set to 0 before we check the pending bits etc. */
-	signals_blocked = 0;
+	/*
+	 * Must be set to 0 before we check pending so the
+	 * SIGIO handler will run as normal unless we're still
+	 * going to process signals_blocked_pending.
+	 */
 	barrier();
 
-	if (signals_pending && signals_enabled) {
-		/* this is a bit inefficient, but that's not really important */
-		block_signals();
-		unblock_signals();
-	} else if (signals_pending & SIGIO_MASK) {
-		/* we need to run time-travel handlers even if not enabled */
-		sigio_run_timetravel_handlers();
+	/*
+	 * Note that block_signals_hard()/unblock_signals_hard() can be called
+	 * within the unblock_signals()/sigio_run_timetravel_handlers() below.
+	 * This would still be prone to race conditions since it's actually a
+	 * call _within_ e.g. vu_req_read_message(), where we observed this
+	 * issue, which loops. Thus, if the inner call handles the recorded
+	 * pending signals, we can get out of the inner call with the real
+	 * signal hander no longer blocked, and still have a race. Thus don't
+	 * handle unblocking in the inner call, if it happens, but only in
+	 * the outermost call - 'unblocking' serves as an ownership for the
+	 * signals_blocked_pending decrement.
+	 */
+	if (unblocking)
+		return;
+	unblocking = true;
+
+	while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) {
+		if (signals_enabled) {
+			/* signals are enabled so we can touch this */
+			signals_pending |= SIGIO_MASK;
+			/*
+			 * this is a bit inefficient, but that's
+			 * not really important
+			 */
+			block_signals();
+			unblock_signals();
+		} else {
+			/*
+			 * we need to run time-travel handlers even
+			 * if not enabled
+			 */
+			sigio_run_timetravel_handlers();
+		}
+
+		/*
+		 * The decrement of signals_blocked_pending must be atomic so
+		 * that the signal handler will either happen before or after
+		 * the decrement, not during a read-modify-write:
+		 *  - If it happens before, it can increment it and we'll
+		 *    decrement it and do another round in the loop.
+		 *  - If it happens after it'll see 0 for both signals_blocked
+		 *    and signals_blocked_pending and thus run the handler as
+		 *    usual (subject to signals_enabled, but that's unrelated.)
+		 *
+		 * Note that a call to unblock_signals_hard() within the calls
+		 * to unblock_signals() or sigio_run_timetravel_handlers() above
+		 * will do nothing due to the 'unblocking' state, so this cannot
+		 * underflow as the only one decrementing will be the outermost
+		 * one.
+		 */
+		if (__atomic_sub_fetch(&signals_blocked_pending, 1,
+				       __ATOMIC_SEQ_CST) < 0)
+			panic("signals_blocked_pending underflow");
 	}
+
+	unblocking = false;
 }
 #endif
 
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index 1f9c1bf..c554307 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
  * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  */
 
@@ -19,7 +20,30 @@
 #include <sysdep/stub.h>
 #include "../internal.h"
 
-extern char batch_syscall_stub[], __syscall_stub_start[];
+extern char __syscall_stub_start[];
+
+void syscall_stub_dump_error(struct mm_id *mm_idp)
+{
+	struct stub_data *proc_data = (void *)mm_idp->stack;
+	struct stub_syscall *sc;
+
+	if (proc_data->syscall_data_len < 0 ||
+	    proc_data->syscall_data_len >= ARRAY_SIZE(proc_data->syscall_data))
+		panic("Syscall data was corrupted by stub (len is: %d, expected maximum: %d)!",
+			proc_data->syscall_data_len,
+			mm_idp->syscall_data_len);
+
+	sc = &proc_data->syscall_data[proc_data->syscall_data_len];
+
+	printk(UM_KERN_ERR "%s : length = %d, last offset = %d",
+		__func__, mm_idp->syscall_data_len,
+		proc_data->syscall_data_len);
+	printk(UM_KERN_ERR "%s : stub syscall type %d failed, return value = 0x%lx\n",
+		__func__, sc->syscall, proc_data->err);
+
+	print_hex_dump(UM_KERN_ERR, "    syscall data: ", 0,
+		       16, 4, sc, sizeof(*sc), 0);
+}
 
 static inline unsigned long *check_init_stack(struct mm_id * mm_idp,
 					      unsigned long *stack)
@@ -36,22 +60,24 @@ static unsigned long syscall_regs[MAX_REG_NR];
 static int __init init_syscall_regs(void)
 {
 	get_safe_registers(syscall_regs, NULL);
+
 	syscall_regs[REGS_IP_INDEX] = STUB_CODE +
-		((unsigned long) batch_syscall_stub -
+		((unsigned long) stub_syscall_handler -
 		 (unsigned long) __syscall_stub_start);
-	syscall_regs[REGS_SP_INDEX] = STUB_DATA;
+	syscall_regs[REGS_SP_INDEX] = STUB_DATA +
+		offsetof(struct stub_data, sigstack) +
+		sizeof(((struct stub_data *) 0)->sigstack) -
+		sizeof(void *);
 
 	return 0;
 }
 
 __initcall(init_syscall_regs);
 
-static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
+static inline long do_syscall_stub(struct mm_id *mm_idp)
 {
+	struct stub_data *proc_data = (void *)mm_idp->stack;
 	int n, i;
-	long ret, offset;
-	unsigned long * data;
-	unsigned long * syscall;
 	int err, pid = mm_idp->u.pid;
 
 	n = ptrace_setregs(pid, syscall_regs);
@@ -63,6 +89,9 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
 		      __func__, -n);
 	}
 
+	/* Inform process how much we have filled in. */
+	proc_data->syscall_data_len = mm_idp->syscall_data_len;
+
 	err = ptrace(PTRACE_CONT, pid, 0, 0);
 	if (err)
 		panic("Failed to continue stub, pid = %d, errno = %d\n", pid,
@@ -71,135 +100,141 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr)
 	wait_stub_done(pid);
 
 	/*
-	 * When the stub stops, we find the following values on the
-	 * beginning of the stack:
-	 * (long )return_value
-	 * (long )offset to failed sycall-data (0, if no error)
+	 * proc_data->err will be non-zero if there was an (unexpected) error.
+	 * In that case, syscall_data_len points to the last executed syscall,
+	 * otherwise it will be zero (but we do not need to rely on that).
 	 */
-	ret = *((unsigned long *) mm_idp->stack);
-	offset = *((unsigned long *) mm_idp->stack + 1);
-	if (offset) {
-		data = (unsigned long *)(mm_idp->stack + offset - STUB_DATA);
-		printk(UM_KERN_ERR "%s : ret = %ld, offset = %ld, data = %p\n",
-		       __func__, ret, offset, data);
-		syscall = (unsigned long *)((unsigned long)data + data[0]);
-		printk(UM_KERN_ERR "%s: syscall %ld failed, return value = 0x%lx, expected return value = 0x%lx\n",
-		       __func__, syscall[0], ret, syscall[7]);
-		printk(UM_KERN_ERR "    syscall parameters: 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
-		       syscall[1], syscall[2], syscall[3],
-		       syscall[4], syscall[5], syscall[6]);
-		for (n = 1; n < data[0]/sizeof(long); n++) {
-			if (n == 1)
-				printk(UM_KERN_ERR "    additional syscall data:");
-			if (n % 4 == 1)
-				printk("\n" UM_KERN_ERR "      ");
-			printk("  0x%lx", data[n]);
-		}
-		if (n > 1)
-			printk("\n");
+	if (proc_data->err < 0) {
+		syscall_stub_dump_error(mm_idp);
+
+		/* Store error code in case someone tries to add more syscalls */
+		mm_idp->syscall_data_len = proc_data->err;
+	} else {
+		mm_idp->syscall_data_len = 0;
 	}
-	else ret = 0;
 
-	*addr = check_init_stack(mm_idp, NULL);
-
-	return ret;
+	return mm_idp->syscall_data_len;
 }
 
-long run_syscall_stub(struct mm_id * mm_idp, int syscall,
-		      unsigned long *args, long expected, void **addr,
-		      int done)
+int syscall_stub_flush(struct mm_id *mm_idp)
 {
-	unsigned long *stack = check_init_stack(mm_idp, *addr);
+	int res;
 
-	*stack += sizeof(long);
-	stack += *stack / sizeof(long);
+	if (mm_idp->syscall_data_len == 0)
+		return 0;
 
-	*stack++ = syscall;
-	*stack++ = args[0];
-	*stack++ = args[1];
-	*stack++ = args[2];
-	*stack++ = args[3];
-	*stack++ = args[4];
-	*stack++ = args[5];
-	*stack++ = expected;
-	*stack = 0;
+	/* If an error happened already, report it and reset the state. */
+	if (mm_idp->syscall_data_len < 0) {
+		res = mm_idp->syscall_data_len;
+		mm_idp->syscall_data_len = 0;
+		return res;
+	}
 
-	if (!done && ((((unsigned long) stack) & ~UM_KERN_PAGE_MASK) <
-		     UM_KERN_PAGE_SIZE - 10 * sizeof(long))) {
-		*addr = stack;
+	res = do_syscall_stub(mm_idp);
+	mm_idp->syscall_data_len = 0;
+
+	return res;
+}
+
+struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp)
+{
+	struct stub_syscall *sc;
+	struct stub_data *proc_data = (struct stub_data *) mm_idp->stack;
+
+	if (mm_idp->syscall_data_len > 0 &&
+	    mm_idp->syscall_data_len == ARRAY_SIZE(proc_data->syscall_data))
+		do_syscall_stub(mm_idp);
+
+	if (mm_idp->syscall_data_len < 0) {
+		/* Return dummy to retain error state. */
+		sc = &proc_data->syscall_data[0];
+	} else {
+		sc = &proc_data->syscall_data[mm_idp->syscall_data_len];
+		mm_idp->syscall_data_len += 1;
+	}
+	memset(sc, 0, sizeof(*sc));
+
+	return sc;
+}
+
+static struct stub_syscall *syscall_stub_get_previous(struct mm_id *mm_idp,
+						      int syscall_type,
+						      unsigned long virt)
+{
+	if (mm_idp->syscall_data_len > 0) {
+		struct stub_data *proc_data = (void *) mm_idp->stack;
+		struct stub_syscall *sc;
+
+		sc = &proc_data->syscall_data[mm_idp->syscall_data_len - 1];
+
+		if (sc->syscall == syscall_type &&
+		    sc->mem.addr + sc->mem.length == virt)
+			return sc;
+	}
+
+	return NULL;
+}
+
+int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot,
+	int phys_fd, unsigned long long offset)
+{
+	struct stub_syscall *sc;
+
+	/* Compress with previous syscall if that is possible */
+	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MMAP, virt);
+	if (sc && sc->mem.prot == prot && sc->mem.fd == phys_fd &&
+	    sc->mem.offset == MMAP_OFFSET(offset - sc->mem.length)) {
+		sc->mem.length += len;
 		return 0;
 	}
 
-	return do_syscall_stub(mm_idp, addr);
-}
-
-long syscall_stub_data(struct mm_id * mm_idp,
-		       unsigned long *data, int data_count,
-		       void **addr, void **stub_addr)
-{
-	unsigned long *stack;
-	int ret = 0;
-
-	/*
-	 * If *addr still is uninitialized, it *must* contain NULL.
-	 * Thus in this case do_syscall_stub correctly won't be called.
-	 */
-	if ((((unsigned long) *addr) & ~UM_KERN_PAGE_MASK) >=
-	   UM_KERN_PAGE_SIZE - (10 + data_count) * sizeof(long)) {
-		ret = do_syscall_stub(mm_idp, addr);
-		/* in case of error, don't overwrite data on stack */
-		if (ret)
-			return ret;
-	}
-
-	stack = check_init_stack(mm_idp, *addr);
-	*addr = stack;
-
-	*stack = data_count * sizeof(long);
-
-	memcpy(stack + 1, data, data_count * sizeof(long));
-
-	*stub_addr = (void *)(((unsigned long)(stack + 1) &
-			       ~UM_KERN_PAGE_MASK) + STUB_DATA);
+	sc = syscall_stub_alloc(mm_idp);
+	sc->syscall = STUB_SYSCALL_MMAP;
+	sc->mem.addr = virt;
+	sc->mem.length = len;
+	sc->mem.prot = prot;
+	sc->mem.fd = phys_fd;
+	sc->mem.offset = MMAP_OFFSET(offset);
 
 	return 0;
 }
 
-int map(struct mm_id * mm_idp, unsigned long virt, unsigned long len, int prot,
-	int phys_fd, unsigned long long offset, int done, void **data)
+int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len)
 {
-	int ret;
-	unsigned long args[] = { virt, len, prot,
-				 MAP_SHARED | MAP_FIXED, phys_fd,
-				 MMAP_OFFSET(offset) };
+	struct stub_syscall *sc;
 
-	ret = run_syscall_stub(mm_idp, STUB_MMAP_NR, args, virt,
-			       data, done);
+	/* Compress with previous syscall if that is possible */
+	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MUNMAP, addr);
+	if (sc) {
+		sc->mem.length += len;
+		return 0;
+	}
 
-	return ret;
+	sc = syscall_stub_alloc(mm_idp);
+	sc->syscall = STUB_SYSCALL_MUNMAP;
+	sc->mem.addr = addr;
+	sc->mem.length = len;
+
+	return 0;
 }
 
-int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len,
-	  int done, void **data)
+int protect(struct mm_id *mm_idp, unsigned long addr, unsigned long len,
+	    unsigned int prot)
 {
-	int ret;
-	unsigned long args[] = { (unsigned long) addr, len, 0, 0, 0,
-				 0 };
+	struct stub_syscall *sc;
 
-	ret = run_syscall_stub(mm_idp, __NR_munmap, args, 0,
-			       data, done);
+	/* Compress with previous syscall if that is possible */
+	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MPROTECT, addr);
+	if (sc && sc->mem.prot == prot) {
+		sc->mem.length += len;
+		return 0;
+	}
 
-	return ret;
-}
+	sc = syscall_stub_alloc(mm_idp);
+	sc->syscall = STUB_SYSCALL_MPROTECT;
+	sc->mem.addr = addr;
+	sc->mem.length = len;
+	sc->mem.prot = prot;
 
-int protect(struct mm_id * mm_idp, unsigned long addr, unsigned long len,
-	    unsigned int prot, int done, void **data)
-{
-	int ret;
-	unsigned long args[] = { addr, len, prot, 0, 0, 0 };
-
-	ret = run_syscall_stub(mm_idp, __NR_mprotect, args, 0,
-			       data, done);
-
-	return ret;
+	return 0;
 }
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 41a288d..f708834 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -23,6 +23,7 @@
 #include <skas.h>
 #include <sysdep/stub.h>
 #include <linux/threads.h>
+#include <timetravel.h>
 #include "../internal.h"
 
 int is_skas_winch(int pid, int fd, void *data)
@@ -253,7 +254,6 @@ static int userspace_tramp(void *stack)
 }
 
 int userspace_pid[NR_CPUS];
-int kill_userspace_mm[NR_CPUS];
 
 /**
  * start_userspace() - prepare a new userspace process
@@ -345,8 +345,20 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 	interrupt_end();
 
 	while (1) {
-		if (kill_userspace_mm[0])
+		time_travel_print_bc_msg();
+
+		current_mm_sync();
+
+		/* Flush out any pending syscalls */
+		err = syscall_stub_flush(current_mm_id());
+		if (err) {
+			if (err == -ENOMEM)
+				report_enomem();
+
+			printk(UM_KERN_ERR "%s - Error flushing stub syscalls: %d",
+				__func__, -err);
 			fatal_sigsegv();
+		}
 
 		/*
 		 * This can legitimately fail if the process loads a
@@ -461,113 +473,6 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 	}
 }
 
-static unsigned long thread_regs[MAX_REG_NR];
-static unsigned long thread_fp_regs[FP_SIZE];
-
-static int __init init_thread_regs(void)
-{
-	get_safe_registers(thread_regs, thread_fp_regs);
-	/* Set parent's instruction pointer to start of clone-stub */
-	thread_regs[REGS_IP_INDEX] = STUB_CODE +
-				(unsigned long) stub_clone_handler -
-				(unsigned long) __syscall_stub_start;
-	thread_regs[REGS_SP_INDEX] = STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE -
-		sizeof(void *);
-#ifdef __SIGNAL_FRAMESIZE
-	thread_regs[REGS_SP_INDEX] -= __SIGNAL_FRAMESIZE;
-#endif
-	return 0;
-}
-
-__initcall(init_thread_regs);
-
-int copy_context_skas0(unsigned long new_stack, int pid)
-{
-	int err;
-	unsigned long current_stack = current_stub_stack();
-	struct stub_data *data = (struct stub_data *) current_stack;
-	struct stub_data *child_data = (struct stub_data *) new_stack;
-	unsigned long long new_offset;
-	int new_fd = phys_mapping(uml_to_phys((void *)new_stack), &new_offset);
-
-	/*
-	 * prepare offset and fd of child's stack as argument for parent's
-	 * and child's mmap2 calls
-	 */
-	*data = ((struct stub_data) {
-		.offset	= MMAP_OFFSET(new_offset),
-		.fd     = new_fd,
-		.parent_err = -ESRCH,
-		.child_err = 0,
-	});
-
-	*child_data = ((struct stub_data) {
-		.child_err = -ESRCH,
-	});
-
-	err = ptrace_setregs(pid, thread_regs);
-	if (err < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_SETREGS failed, pid = %d, errno = %d\n",
-		      __func__, pid, -err);
-		return err;
-	}
-
-	err = put_fp_registers(pid, thread_fp_regs);
-	if (err < 0) {
-		printk(UM_KERN_ERR "%s : put_fp_registers failed, pid = %d, err = %d\n",
-		       __func__, pid, err);
-		return err;
-	}
-
-	/*
-	 * Wait, until parent has finished its work: read child's pid from
-	 * parent's stack, and check, if bad result.
-	 */
-	err = ptrace(PTRACE_CONT, pid, 0, 0);
-	if (err) {
-		err = -errno;
-		printk(UM_KERN_ERR "Failed to continue new process, pid = %d, errno = %d\n",
-		       pid, errno);
-		return err;
-	}
-
-	wait_stub_done(pid);
-
-	pid = data->parent_err;
-	if (pid < 0) {
-		printk(UM_KERN_ERR "%s - stub-parent reports error %d\n",
-		      __func__, -pid);
-		return pid;
-	}
-
-	/*
-	 * Wait, until child has finished too: read child's result from
-	 * child's stack and check it.
-	 */
-	wait_stub_done(pid);
-	if (child_data->child_err != STUB_DATA) {
-		printk(UM_KERN_ERR "%s - stub-child %d reports error %ld\n",
-		       __func__, pid, data->child_err);
-		err = data->child_err;
-		goto out_kill;
-	}
-
-	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
-		   (void *)PTRACE_O_TRACESYSGOOD) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
-		       __func__, errno);
-		goto out_kill;
-	}
-
-	return pid;
-
- out_kill:
-	os_kill_ptraced_process(pid, 1);
-	return err;
-}
-
 void new_thread(void *stack, jmp_buf *buf, void (*handler)(void))
 {
 	(*buf)[0].JB_IP = (unsigned long) handler;
@@ -684,5 +589,4 @@ void reboot_skas(void)
 void __switch_mm(struct mm_id *mm_idp)
 {
 	userspace_pid[0] = mm_idp->u.pid;
-	kill_userspace_mm[0] = mm_idp->kill;
 }
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 89ad9f4..93fc82c 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -17,6 +17,7 @@
 #include <sys/wait.h>
 #include <sys/time.h>
 #include <sys/resource.h>
+#include <asm/ldt.h>
 #include <asm/unistd.h>
 #include <init.h>
 #include <os.h>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cbe5fac..007bab9f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -287,6 +287,7 @@
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
 	select HAVE_GENERIC_VDSO
+	select VDSO_GETRANDOM			if X86_64
 	select HOTPLUG_PARALLEL			if SMP && X86_64
 	select HOTPLUG_SMT			if SMP
 	select HOTPLUG_SPLIT_STARTUP		if SMP && X86_32
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 2106a2b..a46b139 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -9,6 +9,7 @@
 #
 ifeq ($(CONFIG_CC_IS_CLANG),y)
 KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
+KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
 KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
 endif
 
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 215a1b2..c9216ac 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -7,7 +7,7 @@
 include $(srctree)/lib/vdso/Makefile
 
 # Files to link into the vDSO:
-vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrandom-chacha.o
 vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
 vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o
 vobjs-$(CONFIG_X86_SGX)	+= vsgx.o
@@ -73,6 +73,7 @@
 CFLAGS_REMOVE_vgetcpu.o = -pg
 CFLAGS_REMOVE_vdso32/vgetcpu.o = -pg
 CFLAGS_REMOVE_vsgx.o = -pg
+CFLAGS_REMOVE_vgetrandom.o = -pg
 
 #
 # X32 processes use x32 vDSO to access 64bit kernel data.
diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index e8c60ae..0bab5f4 100644
--- a/arch/x86/entry/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
@@ -30,6 +30,8 @@
 #ifdef CONFIG_X86_SGX
 		__vdso_sgx_enter_enclave;
 #endif
+		getrandom;
+		__vdso_getrandom;
 	local: *;
 	};
 }
diff --git a/arch/x86/entry/vdso/vgetrandom-chacha.S b/arch/x86/entry/vdso/vgetrandom-chacha.S
new file mode 100644
index 0000000..bcba563
--- /dev/null
+++ b/arch/x86/entry/vdso/vgetrandom-chacha.S
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+.section	.rodata, "a"
+.align 16
+CONSTANTS:	.octa 0x6b20657479622d323320646e61707865
+.text
+
+/*
+ * Very basic SSE2 implementation of ChaCha20. Produces a given positive number
+ * of blocks of output with a nonce of 0, taking an input key and 8-byte
+ * counter. Importantly does not spill to the stack. Its arguments are:
+ *
+ *	rdi: output bytes
+ *	rsi: 32-byte key input
+ *	rdx: 8-byte counter input/output
+ *	rcx: number of 64-byte blocks to write to output
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+
+.set	output,		%rdi
+.set	key,		%rsi
+.set	counter,	%rdx
+.set	nblocks,	%rcx
+.set	i,		%al
+/* xmm registers are *not* callee-save. */
+.set	temp,		%xmm0
+.set	state0,		%xmm1
+.set	state1,		%xmm2
+.set	state2,		%xmm3
+.set	state3,		%xmm4
+.set	copy0,		%xmm5
+.set	copy1,		%xmm6
+.set	copy2,		%xmm7
+.set	copy3,		%xmm8
+.set	one,		%xmm9
+
+	/* copy0 = "expand 32-byte k" */
+	movaps		CONSTANTS(%rip),copy0
+	/* copy1,copy2 = key */
+	movups		0x00(key),copy1
+	movups		0x10(key),copy2
+	/* copy3 = counter || zero nonce */
+	movq		0x00(counter),copy3
+	/* one = 1 || 0 */
+	movq		$1,%rax
+	movq		%rax,one
+
+.Lblock:
+	/* state0,state1,state2,state3 = copy0,copy1,copy2,copy3 */
+	movdqa		copy0,state0
+	movdqa		copy1,state1
+	movdqa		copy2,state2
+	movdqa		copy3,state3
+
+	movb		$10,i
+.Lpermute:
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$16,temp
+	psrld		$16,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$12,temp
+	psrld		$20,state1
+	por		temp,state1
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$8,temp
+	psrld		$24,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$7,temp
+	psrld		$25,state1
+	por		temp,state1
+
+	/* state1[0,1,2,3] = state1[1,2,3,0] */
+	pshufd		$0x39,state1,state1
+	/* state2[0,1,2,3] = state2[2,3,0,1] */
+	pshufd		$0x4e,state2,state2
+	/* state3[0,1,2,3] = state3[3,0,1,2] */
+	pshufd		$0x93,state3,state3
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$16,temp
+	psrld		$16,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$12,temp
+	psrld		$20,state1
+	por		temp,state1
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$8,temp
+	psrld		$24,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$7,temp
+	psrld		$25,state1
+	por		temp,state1
+
+	/* state1[0,1,2,3] = state1[3,0,1,2] */
+	pshufd		$0x93,state1,state1
+	/* state2[0,1,2,3] = state2[2,3,0,1] */
+	pshufd		$0x4e,state2,state2
+	/* state3[0,1,2,3] = state3[1,2,3,0] */
+	pshufd		$0x39,state3,state3
+
+	decb		i
+	jnz		.Lpermute
+
+	/* output0 = state0 + copy0 */
+	paddd		copy0,state0
+	movups		state0,0x00(output)
+	/* output1 = state1 + copy1 */
+	paddd		copy1,state1
+	movups		state1,0x10(output)
+	/* output2 = state2 + copy2 */
+	paddd		copy2,state2
+	movups		state2,0x20(output)
+	/* output3 = state3 + copy3 */
+	paddd		copy3,state3
+	movups		state3,0x30(output)
+
+	/* ++copy3.counter */
+	paddq		one,copy3
+
+	/* output += 64, --nblocks */
+	addq		$64,output
+	decq		nblocks
+	jnz		.Lblock
+
+	/* counter = copy3.counter */
+	movq		copy3,0x00(counter)
+
+	/* Zero out the potentially sensitive regs, in case nothing uses these again. */
+	pxor		state0,state0
+	pxor		state1,state1
+	pxor		state2,state2
+	pxor		state3,state3
+	pxor		copy1,copy1
+	pxor		copy2,copy2
+	pxor		temp,temp
+
+	ret
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)
diff --git a/arch/x86/entry/vdso/vgetrandom.c b/arch/x86/entry/vdso/vgetrandom.c
new file mode 100644
index 0000000..52d3c7f
--- /dev/null
+++ b/arch/x86/entry/vdso/vgetrandom.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+#include <linux/types.h>
+
+#include "../../../../lib/vdso/getrandom.c"
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len);
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len);
+}
+
+ssize_t getrandom(void *, size_t, unsigned int, void *, size_t)
+	__attribute__((weak, alias("__vdso_getrandom")));
diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h
new file mode 100644
index 0000000..b96e674
--- /dev/null
+++ b/arch/x86/include/asm/vdso/getrandom.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+#ifndef __ASM_VDSO_GETRANDOM_H
+#define __ASM_VDSO_GETRANDOM_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+#include <asm/vvar.h>
+
+/**
+ * getrandom_syscall - Invoke the getrandom() syscall.
+ * @buffer:	Destination buffer to fill with random bytes.
+ * @len:	Size of @buffer in bytes.
+ * @flags:	Zero or more GRND_* flags.
+ * Returns:	The number of random bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags)
+{
+	long ret;
+
+	asm ("syscall" : "=a" (ret) :
+	     "0" (__NR_getrandom), "D" (buffer), "S" (len), "d" (flags) :
+	     "rcx", "r11", "memory");
+
+	return ret;
+}
+
+#define __vdso_rng_data (VVAR(_vdso_rng_data))
+
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
+{
+	if (IS_ENABLED(CONFIG_TIME_NS) && __vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
+		return (void *)&__vdso_rng_data + ((void *)&__timens_vdso_data - (void *)&__vdso_data);
+	return &__vdso_rng_data;
+}
+
+/**
+ * __arch_chacha20_blocks_nostack - Generate ChaCha20 stream without using the stack.
+ * @dst_bytes:	Destination buffer to hold @nblocks * 64 bytes of output.
+ * @key:	32-byte input key.
+ * @counter:	8-byte counter, read on input and updated on return.
+ * @nblocks:	Number of blocks to generate.
+ *
+ * Generates a given positive number of blocks of ChaCha20 output with nonce=0, and does not write
+ * to any stack or memory outside of the parameters passed to it, in order to mitigate stack data
+ * leaking into forked child processes.
+ */
+extern void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index 9322628..972415a 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -10,6 +10,8 @@
 #include <asm/vvar.h>
 
 DEFINE_VVAR(struct vdso_data, _vdso_data);
+DEFINE_VVAR_SINGLE(struct vdso_rng_data, _vdso_rng_data);
+
 /*
  * Update the vDSO data page to keep in sync with kernel timekeeping.
  */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 183e98e4..9d9af37 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -26,6 +26,8 @@
  */
 #define DECLARE_VVAR(offset, type, name) \
 	EMIT_VVAR(name, offset)
+#define DECLARE_VVAR_SINGLE(offset, type, name) \
+	EMIT_VVAR(name, offset)
 
 #else
 
@@ -37,6 +39,10 @@ extern char __vvar_page;
 	extern type timens_ ## name[CS_BASES]				\
 	__attribute__((visibility("hidden")));				\
 
+#define DECLARE_VVAR_SINGLE(offset, type, name)				\
+	extern type vvar_ ## name					\
+	__attribute__((visibility("hidden")));				\
+
 #define VVAR(name) (vvar_ ## name)
 #define TIMENS(name) (timens_ ## name)
 
@@ -44,12 +50,22 @@ extern char __vvar_page;
 	type name[CS_BASES]						\
 	__attribute__((section(".vvar_" #name), aligned(16))) __visible
 
+#define DEFINE_VVAR_SINGLE(type, name)					\
+	type name							\
+	__attribute__((section(".vvar_" #name), aligned(16))) __visible
+
 #endif
 
 /* DECLARE_VVAR(offset, type, name) */
 
 DECLARE_VVAR(128, struct vdso_data, _vdso_data)
 
+#if !defined(_SINGLE_DATA)
+#define _SINGLE_DATA
+DECLARE_VVAR_SINGLE(640, struct vdso_rng_data, _vdso_rng_data)
+#endif
+
 #undef DECLARE_VVAR
+#undef DECLARE_VVAR_SINGLE
 
 #endif
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 64fbd2d..a908825 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,11 +62,6 @@ void xen_arch_unregister_cpu(int num);
 #ifdef CONFIG_PVH
 void __init xen_pvh_init(struct boot_params *boot_params);
 void __init mem_map_via_hcall(struct boot_params *boot_params_p);
-#ifdef CONFIG_XEN_PVH
-void __init xen_reserve_extra_memory(struct boot_params *bootp);
-#else
-static inline void xen_reserve_extra_memory(struct boot_params *bootp) { }
-#endif
 #endif
 
 /* Lazy mode for batching updates / context switch */
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 9a7c03d..51b805c 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -38,7 +38,7 @@ static bool __read_mostly sched_itmt_capable;
  */
 unsigned int __read_mostly sysctl_sched_itmt_enabled;
 
-static int sched_itmt_update_handler(struct ctl_table *table, int write,
+static int sched_itmt_update_handler(const struct ctl_table *table, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int old_sysctl;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 93e54ba..f593149 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -110,7 +110,7 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 #define MAX_UNSHARED_PTRS_PER_PGD			\
-	max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
+	MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
 
 
 static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 8c2d4b8..944e029 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -75,9 +75,6 @@ static void __init init_pvh_bootparams(bool xen_guest)
 	} else
 		xen_raw_printk("Warning: Can fit ISA range into e820\n");
 
-	if (xen_guest)
-		xen_reserve_extra_memory(&pvh_bootparams);
-
 	pvh_bootparams.hdr.cmd_line_ptr =
 		pvh_start_info.cmdline_paddr;
 
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 8bc72a5..36e67fc 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -9,9 +9,9 @@
 	BITS := 64
 endif
 
-obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \
+obj-y = bugs_$(BITS).o delay.o fault.o \
 	ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
-	stub_$(BITS).o stub_segv.o \
+	stub_segv.o \
 	sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
 	mem_$(BITS).o subarch.o os-Linux/
 
@@ -31,7 +31,6 @@
 
 subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \
 	../lib/memmove_64.o ../lib/memset_64.o
-subarch-$(CONFIG_PREEMPTION) += ../entry/thunk_64.o
 
 endif
 
diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h
deleted file mode 100644
index dc32dc0..0000000
--- a/arch/x86/um/asm/mm_context.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
- * Licensed under the GPL
- *
- * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
- */
-
-#ifndef __ASM_LDT_H
-#define __ASM_LDT_H
-
-#include <linux/mutex.h>
-#include <asm/ldt.h>
-
-#define LDT_PAGES_MAX \
-	((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
-#define LDT_ENTRIES_PER_PAGE \
-	(PAGE_SIZE/LDT_ENTRY_SIZE)
-#define LDT_DIRECT_ENTRIES \
-	((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
-
-struct ldt_entry {
-	__u32 a;
-	__u32 b;
-};
-
-typedef struct uml_ldt {
-	int entry_count;
-	struct mutex lock;
-	union {
-		struct ldt_entry * pages[LDT_PAGES_MAX];
-		struct ldt_entry entries[LDT_DIRECT_ENTRIES];
-	} u;
-} uml_ldt_t;
-
-#define LDT_entry_a(info) \
-	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-#define LDT_entry_b(info) \
-	(((info)->base_addr & 0xff000000) | \
-	(((info)->base_addr & 0x00ff0000) >> 16) | \
-	((info)->limit & 0xf0000) | \
-	(((info)->read_exec_only ^ 1) << 9) | \
-	((info)->contents << 10) | \
-	(((info)->seg_not_present ^ 1) << 15) | \
-	((info)->seg_32bit << 22) | \
-	((info)->limit_in_pages << 23) | \
-	((info)->useable << 20) | \
-	0x7000)
-
-#define _LDT_empty(info) (\
-	(info)->base_addr	== 0	&& \
-	(info)->limit		== 0	&& \
-	(info)->contents	== 0	&& \
-	(info)->read_exec_only	== 1	&& \
-	(info)->seg_32bit	== 0	&& \
-	(info)->limit_in_pages	== 0	&& \
-	(info)->seg_not_present	== 1	&& \
-	(info)->useable		== 0	)
-
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
-
-struct uml_arch_mm_context {
-	uml_ldt_t ldt;
-};
-
-#endif
diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c
deleted file mode 100644
index 255a44d..0000000
--- a/arch/x86/um/ldt.c
+++ /dev/null
@@ -1,380 +0,0 @@
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <asm/unistd.h>
-#include <os.h>
-#include <skas.h>
-#include <sysdep/tls.h>
-
-static inline int modify_ldt (int func, void *ptr, unsigned long bytecount)
-{
-	return syscall(__NR_modify_ldt, func, ptr, bytecount);
-}
-
-static long write_ldt_entry(struct mm_id *mm_idp, int func,
-		     struct user_desc *desc, void **addr, int done)
-{
-	long res;
-	void *stub_addr;
-
-	BUILD_BUG_ON(sizeof(*desc) % sizeof(long));
-
-	res = syscall_stub_data(mm_idp, (unsigned long *)desc,
-				sizeof(*desc) / sizeof(long),
-				addr, &stub_addr);
-	if (!res) {
-		unsigned long args[] = { func,
-					 (unsigned long)stub_addr,
-					 sizeof(*desc),
-					 0, 0, 0 };
-		res = run_syscall_stub(mm_idp, __NR_modify_ldt, args,
-				       0, addr, done);
-	}
-
-	return res;
-}
-
-/*
- * In skas mode, we hold our own ldt data in UML.
- * Thus, the code implementing sys_modify_ldt_skas
- * is very similar to (and mostly stolen from) sys_modify_ldt
- * for arch/i386/kernel/ldt.c
- * The routines copied and modified in part are:
- * - read_ldt
- * - read_default_ldt
- * - write_ldt
- * - sys_modify_ldt_skas
- */
-
-static int read_ldt(void __user * ptr, unsigned long bytecount)
-{
-	int i, err = 0;
-	unsigned long size;
-	uml_ldt_t *ldt = &current->mm->context.arch.ldt;
-
-	if (!ldt->entry_count)
-		goto out;
-	if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
-		bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
-	err = bytecount;
-
-	mutex_lock(&ldt->lock);
-	if (ldt->entry_count <= LDT_DIRECT_ENTRIES) {
-		size = LDT_ENTRY_SIZE*LDT_DIRECT_ENTRIES;
-		if (size > bytecount)
-			size = bytecount;
-		if (copy_to_user(ptr, ldt->u.entries, size))
-			err = -EFAULT;
-		bytecount -= size;
-		ptr += size;
-	}
-	else {
-		for (i=0; i<ldt->entry_count/LDT_ENTRIES_PER_PAGE && bytecount;
-		     i++) {
-			size = PAGE_SIZE;
-			if (size > bytecount)
-				size = bytecount;
-			if (copy_to_user(ptr, ldt->u.pages[i], size)) {
-				err = -EFAULT;
-				break;
-			}
-			bytecount -= size;
-			ptr += size;
-		}
-	}
-	mutex_unlock(&ldt->lock);
-
-	if (bytecount == 0 || err == -EFAULT)
-		goto out;
-
-	if (clear_user(ptr, bytecount))
-		err = -EFAULT;
-
-out:
-	return err;
-}
-
-static int read_default_ldt(void __user * ptr, unsigned long bytecount)
-{
-	int err;
-
-	if (bytecount > 5*LDT_ENTRY_SIZE)
-		bytecount = 5*LDT_ENTRY_SIZE;
-
-	err = bytecount;
-	/*
-	 * UML doesn't support lcall7 and lcall27.
-	 * So, we don't really have a default ldt, but emulate
-	 * an empty ldt of common host default ldt size.
-	 */
-	if (clear_user(ptr, bytecount))
-		err = -EFAULT;
-
-	return err;
-}
-
-static int write_ldt(void __user * ptr, unsigned long bytecount, int func)
-{
-	uml_ldt_t *ldt = &current->mm->context.arch.ldt;
-	struct mm_id * mm_idp = &current->mm->context.id;
-	int i, err;
-	struct user_desc ldt_info;
-	struct ldt_entry entry0, *ldt_p;
-	void *addr = NULL;
-
-	err = -EINVAL;
-	if (bytecount != sizeof(ldt_info))
-		goto out;
-	err = -EFAULT;
-	if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
-		goto out;
-
-	err = -EINVAL;
-	if (ldt_info.entry_number >= LDT_ENTRIES)
-		goto out;
-	if (ldt_info.contents == 3) {
-		if (func == 1)
-			goto out;
-		if (ldt_info.seg_not_present == 0)
-			goto out;
-	}
-
-	mutex_lock(&ldt->lock);
-
-	err = write_ldt_entry(mm_idp, func, &ldt_info, &addr, 1);
-	if (err)
-		goto out_unlock;
-
-	if (ldt_info.entry_number >= ldt->entry_count &&
-	    ldt_info.entry_number >= LDT_DIRECT_ENTRIES) {
-		for (i=ldt->entry_count/LDT_ENTRIES_PER_PAGE;
-		     i*LDT_ENTRIES_PER_PAGE <= ldt_info.entry_number;
-		     i++) {
-			if (i == 0)
-				memcpy(&entry0, ldt->u.entries,
-				       sizeof(entry0));
-			ldt->u.pages[i] = (struct ldt_entry *)
-				__get_free_page(GFP_KERNEL|__GFP_ZERO);
-			if (!ldt->u.pages[i]) {
-				err = -ENOMEM;
-				/* Undo the change in host */
-				memset(&ldt_info, 0, sizeof(ldt_info));
-				write_ldt_entry(mm_idp, 1, &ldt_info, &addr, 1);
-				goto out_unlock;
-			}
-			if (i == 0) {
-				memcpy(ldt->u.pages[0], &entry0,
-				       sizeof(entry0));
-				memcpy(ldt->u.pages[0]+1, ldt->u.entries+1,
-				       sizeof(entry0)*(LDT_DIRECT_ENTRIES-1));
-			}
-			ldt->entry_count = (i + 1) * LDT_ENTRIES_PER_PAGE;
-		}
-	}
-	if (ldt->entry_count <= ldt_info.entry_number)
-		ldt->entry_count = ldt_info.entry_number + 1;
-
-	if (ldt->entry_count <= LDT_DIRECT_ENTRIES)
-		ldt_p = ldt->u.entries + ldt_info.entry_number;
-	else
-		ldt_p = ldt->u.pages[ldt_info.entry_number/LDT_ENTRIES_PER_PAGE] +
-			ldt_info.entry_number%LDT_ENTRIES_PER_PAGE;
-
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0 &&
-	   (func == 1 || LDT_empty(&ldt_info))) {
-		ldt_p->a = 0;
-		ldt_p->b = 0;
-	}
-	else{
-		if (func == 1)
-			ldt_info.useable = 0;
-		ldt_p->a = LDT_entry_a(&ldt_info);
-		ldt_p->b = LDT_entry_b(&ldt_info);
-	}
-	err = 0;
-
-out_unlock:
-	mutex_unlock(&ldt->lock);
-out:
-	return err;
-}
-
-static long do_modify_ldt_skas(int func, void __user *ptr,
-			       unsigned long bytecount)
-{
-	int ret = -ENOSYS;
-
-	switch (func) {
-		case 0:
-			ret = read_ldt(ptr, bytecount);
-			break;
-		case 1:
-		case 0x11:
-			ret = write_ldt(ptr, bytecount, func);
-			break;
-		case 2:
-			ret = read_default_ldt(ptr, bytecount);
-			break;
-	}
-	return ret;
-}
-
-static DEFINE_SPINLOCK(host_ldt_lock);
-static short dummy_list[9] = {0, -1};
-static short * host_ldt_entries = NULL;
-
-static void ldt_get_host_info(void)
-{
-	long ret;
-	struct ldt_entry * ldt;
-	short *tmp;
-	int i, size, k, order;
-
-	spin_lock(&host_ldt_lock);
-
-	if (host_ldt_entries != NULL) {
-		spin_unlock(&host_ldt_lock);
-		return;
-	}
-	host_ldt_entries = dummy_list+1;
-
-	spin_unlock(&host_ldt_lock);
-
-	for (i = LDT_PAGES_MAX-1, order=0; i; i>>=1, order++)
-		;
-
-	ldt = (struct ldt_entry *)
-	      __get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
-	if (ldt == NULL) {
-		printk(KERN_ERR "ldt_get_host_info: couldn't allocate buffer "
-		       "for host ldt\n");
-		return;
-	}
-
-	ret = modify_ldt(0, ldt, (1<<order)*PAGE_SIZE);
-	if (ret < 0) {
-		printk(KERN_ERR "ldt_get_host_info: couldn't read host ldt\n");
-		goto out_free;
-	}
-	if (ret == 0) {
-		/* default_ldt is active, simply write an empty entry 0 */
-		host_ldt_entries = dummy_list;
-		goto out_free;
-	}
-
-	for (i=0, size=0; i<ret/LDT_ENTRY_SIZE; i++) {
-		if (ldt[i].a != 0 || ldt[i].b != 0)
-			size++;
-	}
-
-	if (size < ARRAY_SIZE(dummy_list))
-		host_ldt_entries = dummy_list;
-	else {
-		size = (size + 1) * sizeof(dummy_list[0]);
-		tmp = kmalloc(size, GFP_KERNEL);
-		if (tmp == NULL) {
-			printk(KERN_ERR "ldt_get_host_info: couldn't allocate "
-			       "host ldt list\n");
-			goto out_free;
-		}
-		host_ldt_entries = tmp;
-	}
-
-	for (i=0, k=0; i<ret/LDT_ENTRY_SIZE; i++) {
-		if (ldt[i].a != 0 || ldt[i].b != 0)
-			host_ldt_entries[k++] = i;
-	}
-	host_ldt_entries[k] = -1;
-
-out_free:
-	free_pages((unsigned long)ldt, order);
-}
-
-long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm)
-{
-	struct user_desc desc;
-	short * num_p;
-	int i;
-	long page, err=0;
-	void *addr = NULL;
-
-
-	mutex_init(&new_mm->arch.ldt.lock);
-
-	if (!from_mm) {
-		memset(&desc, 0, sizeof(desc));
-		/*
-		 * Now we try to retrieve info about the ldt, we
-		 * inherited from the host. All ldt-entries found
-		 * will be reset in the following loop
-		 */
-		ldt_get_host_info();
-		for (num_p=host_ldt_entries; *num_p != -1; num_p++) {
-			desc.entry_number = *num_p;
-			err = write_ldt_entry(&new_mm->id, 1, &desc,
-					      &addr, *(num_p + 1) == -1);
-			if (err)
-				break;
-		}
-		new_mm->arch.ldt.entry_count = 0;
-
-		goto out;
-	}
-
-	/*
-	 * Our local LDT is used to supply the data for
-	 * modify_ldt(READLDT), if PTRACE_LDT isn't available,
-	 * i.e., we have to use the stub for modify_ldt, which
-	 * can't handle the big read buffer of up to 64kB.
-	 */
-	mutex_lock(&from_mm->arch.ldt.lock);
-	if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES)
-		memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries,
-		       sizeof(new_mm->arch.ldt.u.entries));
-	else {
-		i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
-		while (i-->0) {
-			page = __get_free_page(GFP_KERNEL|__GFP_ZERO);
-			if (!page) {
-				err = -ENOMEM;
-				break;
-			}
-			new_mm->arch.ldt.u.pages[i] =
-				(struct ldt_entry *) page;
-			memcpy(new_mm->arch.ldt.u.pages[i],
-			       from_mm->arch.ldt.u.pages[i], PAGE_SIZE);
-		}
-	}
-	new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count;
-	mutex_unlock(&from_mm->arch.ldt.lock);
-
-    out:
-	return err;
-}
-
-
-void free_ldt(struct mm_context *mm)
-{
-	int i;
-
-	if (mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) {
-		i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE;
-		while (i-- > 0)
-			free_page((long) mm->arch.ldt.u.pages[i]);
-	}
-	mm->arch.ldt.entry_count = 0;
-}
-
-SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
-		unsigned long , bytecount)
-{
-	/* See non-um modify_ldt() for why we do this cast */
-	return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount);
-}
diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h
index ce0ca46..dc89f44 100644
--- a/arch/x86/um/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub.h
@@ -12,4 +12,4 @@
 #endif
 
 extern void stub_segv_handler(int, siginfo_t *, void *);
-extern void stub_clone_handler(void);
+extern void stub_syscall_handler(void);
diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index ea8b5a2..0b44a86 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -6,6 +6,7 @@
 #ifndef __SYSDEP_STUB_H
 #define __SYSDEP_STUB_H
 
+#include <stddef.h>
 #include <asm/ptrace.h>
 #include <generated/asm-offsets.h>
 
@@ -79,35 +80,33 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
 	return ret;
 }
 
+static __always_inline long stub_syscall6(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5,
+					  long arg6)
+{
+	struct syscall_args {
+		int ebx, ebp;
+	} args = { arg1, arg6 };
+	long ret;
+
+	__asm__ volatile ("pushl %%ebp;"
+			"movl 0x4(%%ebx),%%ebp;"
+			"movl (%%ebx),%%ebx;"
+			"int $0x80;"
+			"popl %%ebp"
+			: "=a" (ret)
+			: "0" (syscall), "b" (&args),
+			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)
+			: "memory");
+
+	return ret;
+}
+
 static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static __always_inline void remap_stack_and_trap(void)
-{
-	__asm__ volatile (
-		"movl %%esp,%%ebx ;"
-		"andl %0,%%ebx ;"
-		"movl %1,%%eax ;"
-		"movl %%ebx,%%edi ; addl %2,%%edi ; movl (%%edi),%%edi ;"
-		"movl %%ebx,%%ebp ; addl %3,%%ebp ; movl (%%ebp),%%ebp ;"
-		"int $0x80 ;"
-		"addl %4,%%ebx ; movl %%eax, (%%ebx) ;"
-		"int $3"
-		: :
-		"g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)),
-		"g" (STUB_MMAP_NR),
-		"g" (UML_STUB_FIELD_FD),
-		"g" (UML_STUB_FIELD_OFFSET),
-		"g" (UML_STUB_FIELD_CHILD_ERR),
-		"c" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE),
-		"d" (PROT_READ | PROT_WRITE),
-		"S" (MAP_FIXED | MAP_SHARED)
-		:
-		"memory");
-}
-
 static __always_inline void *get_stub_data(void)
 {
 	unsigned long ret;
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index b24168e..67f4428 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -6,6 +6,7 @@
 #ifndef __SYSDEP_STUB_H
 #define __SYSDEP_STUB_H
 
+#include <stddef.h>
 #include <sysdep/ptrace_user.h>
 #include <generated/asm-offsets.h>
 #include <linux/stddef.h>
@@ -79,37 +80,27 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
 	return ret;
 }
 
+static __always_inline long stub_syscall6(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5,
+					  long arg6)
+{
+	long ret;
+
+	__asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; movq %7,%%r9 ; "
+		__syscall
+		: "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3),
+		  "g" (arg4), "g" (arg5), "g" (arg6)
+		: __syscall_clobber, "r10", "r8", "r9");
+
+	return ret;
+}
+
 static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static __always_inline void remap_stack_and_trap(void)
-{
-	__asm__ volatile (
-		"movq %0,%%rax ;"
-		"movq %%rsp,%%rdi ;"
-		"andq %1,%%rdi ;"
-		"movq %2,%%r10 ;"
-		"movq %%rdi,%%r8 ; addq %3,%%r8 ; movq (%%r8),%%r8 ;"
-		"movq %%rdi,%%r9 ; addq %4,%%r9 ; movq (%%r9),%%r9 ;"
-		__syscall ";"
-		"movq %%rsp,%%rdi ; andq %1,%%rdi ;"
-		"addq %5,%%rdi ; movq %%rax, (%%rdi) ;"
-		"int3"
-		: :
-		"g" (STUB_MMAP_NR),
-		"g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)),
-		"g" (MAP_FIXED | MAP_SHARED),
-		"g" (UML_STUB_FIELD_FD),
-		"g" (UML_STUB_FIELD_OFFSET),
-		"g" (UML_STUB_FIELD_CHILD_ERR),
-		"S" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE),
-		"d" (PROT_READ | PROT_WRITE)
-		:
-		__syscall_clobber, "r10", "r8", "r9");
-}
-
 static __always_inline void *get_stub_data(void)
 {
 	unsigned long ret;
diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S
deleted file mode 100644
index 8291899..0000000
--- a/arch/x86/um/stub_32.S
+++ /dev/null
@@ -1,56 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <as-layout.h>
-
-.section .__syscall_stub, "ax"
-
-	.globl batch_syscall_stub
-batch_syscall_stub:
-	/* %esp comes in as "top of page" */
-	mov %esp, %ecx
-	/* %esp has pointer to first operation */
-	add $8, %esp
-again:
-	/* load length of additional data */
-	mov	0x0(%esp), %eax
-
-	/* if(length == 0) : end of list */
-	/* write possible 0 to header */
-	mov	%eax, 0x4(%ecx)
-	cmpl	$0, %eax
-	jz	done
-
-	/* save current pointer */
-	mov	%esp, 0x4(%ecx)
-
-	/* skip additional data */
-	add	%eax, %esp
-
-	/* load syscall-# */
-	pop	%eax
-
-	/* load syscall params */
-	pop	%ebx
-	pop	%ecx
-	pop	%edx
-	pop	%esi
- 	pop	%edi
-	pop	%ebp
-
-	/* execute syscall */
-	int	$0x80
-
-	/* restore top of page pointer in %ecx */
-	mov	%esp, %ecx
-	andl	$(~UM_KERN_PAGE_SIZE) + 1, %ecx
-
-	/* check return value */
-	pop	%ebx
-	cmp	%ebx, %eax
-	je	again
-
-done:
-	/* save return value */
-	mov	%eax, (%ecx)
-
-	/* stop */
-	int3
diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S
deleted file mode 100644
index f340464..0000000
--- a/arch/x86/um/stub_64.S
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <as-layout.h>
-
-.section .__syscall_stub, "ax"
-	.globl batch_syscall_stub
-batch_syscall_stub:
-	/* %rsp has the pointer to first operation */
-	mov	%rsp, %rbx
-	add	$0x10, %rsp
-again:
-	/* load length of additional data */
-	mov	0x0(%rsp), %rax
-
-	/* if(length == 0) : end of list */
-	/* write possible 0 to header */
-	mov	%rax, 8(%rbx)
-	cmp	$0, %rax
-	jz	done
-
-	/* save current pointer */
-	mov	%rsp, 8(%rbx)
-
-	/* skip additional data */
-	add	%rax, %rsp
-
-	/* load syscall-# */
-	pop	%rax
-
-	/* load syscall params */
-	pop	%rdi
-	pop	%rsi
-	pop	%rdx
-	pop	%r10
- 	pop	%r8
-	pop	%r9
-
-	/* execute syscall */
-	syscall
-
-	/* check return value */
-	pop	%rcx
-	cmp	%rcx, %rax
-	je	again
-
-done:
-	/* save return value */
-	mov	%rax, (%rbx)
-
-	/* stop */
-	int3
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index d301dee..fbb1290 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -11,6 +11,7 @@
 #include <os.h>
 #include <skas.h>
 #include <sysdep/tls.h>
+#include <asm/desc.h>
 
 /*
  * If needed we can detect when it's uninitialized.
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 27a2a02..728a436 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -9,6 +9,7 @@
 #include <asm/io_apic.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
+#include <asm/setup.h>
 
 #include <xen/xen.h>
 #include <asm/xen/interface.h>
@@ -27,54 +28,6 @@
 bool __ro_after_init xen_pvh;
 EXPORT_SYMBOL_GPL(xen_pvh);
 
-void __init xen_pvh_init(struct boot_params *boot_params)
-{
-	u32 msr;
-	u64 pfn;
-
-	xen_pvh = 1;
-	xen_domain_type = XEN_HVM_DOMAIN;
-	xen_start_flags = pvh_start_info.flags;
-
-	msr = cpuid_ebx(xen_cpuid_base() + 2);
-	pfn = __pa(hypercall_page);
-	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-
-	if (xen_initial_domain())
-		x86_init.oem.arch_setup = xen_add_preferred_consoles;
-	x86_init.oem.banner = xen_banner;
-
-	xen_efi_init(boot_params);
-
-	if (xen_initial_domain()) {
-		struct xen_platform_op op = {
-			.cmd = XENPF_get_dom0_console,
-		};
-		int ret = HYPERVISOR_platform_op(&op);
-
-		if (ret > 0)
-			xen_init_vga(&op.u.dom0_console,
-				     min(ret * sizeof(char),
-					 sizeof(op.u.dom0_console)),
-				     &boot_params->screen_info);
-	}
-}
-
-void __init mem_map_via_hcall(struct boot_params *boot_params_p)
-{
-	struct xen_memory_map memmap;
-	int rc;
-
-	memmap.nr_entries = ARRAY_SIZE(boot_params_p->e820_table);
-	set_xen_guest_handle(memmap.buffer, boot_params_p->e820_table);
-	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
-	if (rc) {
-		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
-		BUG();
-	}
-	boot_params_p->e820_entries = memmap.nr_entries;
-}
-
 /*
  * Reserve e820 UNUSABLE regions to inflate the memory balloon.
  *
@@ -89,8 +42,9 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p)
  * hypervisor should notify us which memory ranges are suitable for creating
  * foreign mappings, but that's not yet implemented.
  */
-void __init xen_reserve_extra_memory(struct boot_params *bootp)
+static void __init pvh_reserve_extra_memory(void)
 {
+	struct boot_params *bootp = &boot_params;
 	unsigned int i, ram_pages = 0, extra_pages;
 
 	for (i = 0; i < bootp->e820_entries; i++) {
@@ -141,3 +95,58 @@ void __init xen_reserve_extra_memory(struct boot_params *bootp)
 		xen_add_extra_mem(PFN_UP(e->addr), pages);
 	}
 }
+
+static void __init pvh_arch_setup(void)
+{
+	pvh_reserve_extra_memory();
+
+	if (xen_initial_domain())
+		xen_add_preferred_consoles();
+}
+
+void __init xen_pvh_init(struct boot_params *boot_params)
+{
+	u32 msr;
+	u64 pfn;
+
+	xen_pvh = 1;
+	xen_domain_type = XEN_HVM_DOMAIN;
+	xen_start_flags = pvh_start_info.flags;
+
+	msr = cpuid_ebx(xen_cpuid_base() + 2);
+	pfn = __pa(hypercall_page);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	x86_init.oem.arch_setup = pvh_arch_setup;
+	x86_init.oem.banner = xen_banner;
+
+	xen_efi_init(boot_params);
+
+	if (xen_initial_domain()) {
+		struct xen_platform_op op = {
+			.cmd = XENPF_get_dom0_console,
+		};
+		int ret = HYPERVISOR_platform_op(&op);
+
+		if (ret > 0)
+			xen_init_vga(&op.u.dom0_console,
+				     min(ret * sizeof(char),
+					 sizeof(op.u.dom0_console)),
+				     &boot_params->screen_info);
+	}
+}
+
+void __init mem_map_via_hcall(struct boot_params *boot_params_p)
+{
+	struct xen_memory_map memmap;
+	int rc;
+
+	memmap.nr_entries = ARRAY_SIZE(boot_params_p->e820_table);
+	set_xen_guest_handle(memmap.buffer, boot_params_p->e820_table);
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc) {
+		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
+		BUG();
+	}
+	boot_params_p->e820_entries = memmap.nr_entries;
+}
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index d4cefd8..10c660f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,8 +54,9 @@ struct mc_debug_data {
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 static struct mc_debug_data mc_debug_data_early __initdata;
-static struct mc_debug_data __percpu *mc_debug_data __refdata =
+static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
 	&mc_debug_data_early;
+static struct mc_debug_data __percpu *mc_debug_data_ptr;
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 static struct static_key mc_debug __ro_after_init;
@@ -70,16 +71,20 @@ static int __init xen_parse_mc_debug(char *arg)
 }
 early_param("xen_mc_debug", xen_parse_mc_debug);
 
+void mc_percpu_init(unsigned int cpu)
+{
+	per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
+}
+
 static int __init mc_debug_enable(void)
 {
-	struct mc_debug_data __percpu *mcdb;
 	unsigned long flags;
 
 	if (!mc_debug_enabled)
 		return 0;
 
-	mcdb = alloc_percpu(struct mc_debug_data);
-	if (!mcdb) {
+	mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
+	if (!mc_debug_data_ptr) {
 		pr_err("xen_mc_debug inactive\n");
 		static_key_slow_dec(&mc_debug);
 		return -ENOMEM;
@@ -88,7 +93,7 @@ static int __init mc_debug_enable(void)
 	/* Be careful when switching to percpu debug data. */
 	local_irq_save(flags);
 	xen_mc_flush();
-	mc_debug_data = mcdb;
+	mc_percpu_init(0);
 	local_irq_restore(flags);
 
 	pr_info("xen_mc_debug active\n");
@@ -150,7 +155,7 @@ void xen_mc_flush(void)
 	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
 
 	if (static_key_false(&mc_debug)) {
-		mcdb = this_cpu_ptr(mc_debug_data);
+		mcdb = __this_cpu_read(mc_debug_data);
 		memcpy(mcdb->entries, b->entries,
 		       b->mcidx * sizeof(struct multicall_entry));
 	}
@@ -230,7 +235,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 	ret.mc = &b->entries[b->mcidx];
 	if (static_key_false(&mc_debug)) {
-		struct mc_debug_data *mcdb = this_cpu_ptr(mc_debug_data);
+		struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
 
 		mcdb->caller[b->mcidx] = __builtin_return_address(0);
 		mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a0c3e77..806ddb2 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -690,6 +690,7 @@ char * __init xen_memory_setup(void)
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
 	unsigned long extra_pages = 0;
+	unsigned long maxmem_pages;
 	int i;
 	int op;
 
@@ -761,8 +762,8 @@ char * __init xen_memory_setup(void)
 	 * Make sure we have no memory above max_pages, as this area
 	 * isn't handled by the p2m management.
 	 */
-	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
-			   extra_pages, max_pages - max_pfn);
+	maxmem_pages = EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM));
+	extra_pages = min3(maxmem_pages, extra_pages, max_pages - max_pfn);
 	i = 0;
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 7ea57f7..6863d3d 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -305,6 +305,7 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
 		return rc;
 
 	xen_pmu_init(cpu);
+	mc_percpu_init(cpu);
 
 	/*
 	 * Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index e7775df..0cf16fc 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -257,6 +257,9 @@ void xen_mc_callback(void (*fn)(void *), void *data);
  */
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
 
+/* Do percpu data initialization for multicalls. */
+void mc_percpu_init(unsigned int cpu);
+
 extern bool is_xen_pmu;
 
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
diff --git a/block/genhd.c b/block/genhd.c
index 4dc95a4..1c05dd4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -663,12 +663,12 @@ void del_gendisk(struct gendisk *disk)
 	 */
 	if (!test_bit(GD_DEAD, &disk->state))
 		blk_report_disk_dead(disk, false);
-	__blk_mark_disk_dead(disk);
 
 	/*
 	 * Drop all partitions now that the disk is marked dead.
 	 */
 	mutex_lock(&disk->open_mutex);
+	__blk_mark_disk_dead(disk);
 	xa_for_each_start(&disk->part_tbl, idx, part, 1)
 		drop_partition(part);
 	mutex_unlock(&disk->open_mutex);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index bdbd60a..284bc2e0 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1047,10 +1047,10 @@ EXPORT_SYMBOL(acpi_bus_unregister_driver);
                               ACPI Bus operations
    -------------------------------------------------------------------------- */
 
-static int acpi_bus_match(struct device *dev, struct device_driver *drv)
+static int acpi_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
+	const struct acpi_driver *acpi_drv = to_acpi_driver(drv);
 
 	return acpi_dev->flags.match_driver
 		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig
index 849c2bd..f33194d 100644
--- a/drivers/acpi/numa/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 config ACPI_NUMA
-	bool "NUMA support"
-	depends on NUMA
-	depends on (X86 || ARM64 || LOONGARCH)
-	default y if ARM64
+	def_bool NUMA && !X86
 
 config ACPI_HMAT
 	bool "ACPI Heterogeneous Memory Attribute Table Support"
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index e3f26e7..44f91f2 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -167,6 +167,19 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 		}
 	}
 	break;
+
+	case ACPI_SRAT_TYPE_RINTC_AFFINITY:
+		{
+			struct acpi_srat_rintc_affinity *p =
+			    (struct acpi_srat_rintc_affinity *)header;
+			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+				 p->acpi_processor_uid,
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_RINTC_ENABLED) ?
+				 "enabled" : "disabled");
+		}
+		break;
+
 	default:
 		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
 			header->type);
@@ -450,6 +463,21 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header,
 }
 #endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
 
+static int __init
+acpi_parse_rintc_affinity(union acpi_subtable_headers *header,
+			  const unsigned long end)
+{
+	struct acpi_srat_rintc_affinity *rintc_affinity;
+
+	rintc_affinity = (struct acpi_srat_rintc_affinity *)header;
+	acpi_table_print_srat_entry(&header->common);
+
+	/* let architecture-dependent part to do it */
+	acpi_numa_rintc_affinity_init(rintc_affinity);
+
+	return 0;
+}
+
 static int __init acpi_parse_srat(struct acpi_table_header *table)
 {
 	struct acpi_table_srat *srat = (struct acpi_table_srat *)table;
@@ -485,7 +513,7 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: System Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[4];
+		struct acpi_subtable_proc srat_proc[5];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
@@ -496,6 +524,8 @@ int __init acpi_numa_init(void)
 		srat_proc[2].handler = acpi_parse_gicc_affinity;
 		srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY;
 		srat_proc[3].handler = acpi_parse_gi_affinity;
+		srat_proc[4].id = ACPI_SRAT_TYPE_RINTC_AFFINITY;
+		srat_proc[4].handler = acpi_parse_rintc_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index aba3aa9..34bc880 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -26,7 +26,7 @@
 #include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
 
-#define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
+#define to_amba_driver(d)	container_of_const(d, struct amba_driver, drv)
 
 /* called on periphid match and class 0x9 coresight device. */
 static int
@@ -205,10 +205,10 @@ static int amba_read_periphid(struct amba_device *dev)
 	return ret;
 }
 
-static int amba_match(struct device *dev, struct device_driver *drv)
+static int amba_match(struct device *dev, const struct device_driver *drv)
 {
 	struct amba_device *pcdev = to_amba_device(dev);
-	struct amba_driver *pcdrv = to_amba_driver(drv);
+	const struct amba_driver *pcdrv = to_amba_driver(drv);
 
 	mutex_lock(&pcdev->periphid_lock);
 	if (!pcdev->periphid) {
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index 69d2138..21545ff 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -316,7 +316,7 @@
 
 config PANEL_CHANGE_MESSAGE
 	bool "Change LCD initialization message ?"
-	depends on CHARLCD
+	depends on CHARLCD || LINEDISP
 	help
 	  This allows you to replace the boot message indicating the kernel version
 	  and the driver version with a custom message. This is useful on appliances
diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c
index 0b1c99c..a7eae99 100644
--- a/drivers/auxdisplay/arm-charlcd.c
+++ b/drivers/auxdisplay/arm-charlcd.c
@@ -270,7 +270,7 @@ static int __init charlcd_probe(struct platform_device *pdev)
 	struct charlcd *lcd;
 	struct resource *res;
 
-	lcd = kzalloc(sizeof(struct charlcd), GFP_KERNEL);
+	lcd = kzalloc(sizeof(*lcd), GFP_KERNEL);
 	if (!lcd)
 		return -ENOMEM;
 
diff --git a/drivers/auxdisplay/charlcd.h b/drivers/auxdisplay/charlcd.h
index eed8006..4d428720 100644
--- a/drivers/auxdisplay/charlcd.h
+++ b/drivers/auxdisplay/charlcd.h
@@ -36,6 +36,8 @@ enum charlcd_lines {
 	CHARLCD_LINES_2,
 };
 
+struct charlcd_ops;
+
 struct charlcd {
 	const struct charlcd_ops *ops;
 	const unsigned char *char_conv;	/* Optional */
diff --git a/drivers/auxdisplay/hd44780.c b/drivers/auxdisplay/hd44780.c
index 7ac0b1b..025dc68 100644
--- a/drivers/auxdisplay/hd44780.c
+++ b/drivers/auxdisplay/hd44780.c
@@ -230,7 +230,7 @@ static int hd44780_probe(struct platform_device *pdev)
 	if (!lcd)
 		goto fail1;
 
-	hd = kzalloc(sizeof(struct hd44780), GFP_KERNEL);
+	hd = kzalloc(sizeof(*hd), GFP_KERNEL);
 	if (!hd)
 		goto fail2;
 
diff --git a/drivers/auxdisplay/hd44780_common.c b/drivers/auxdisplay/hd44780_common.c
index 7cbf375..4ef87c3 100644
--- a/drivers/auxdisplay/hd44780_common.c
+++ b/drivers/auxdisplay/hd44780_common.c
@@ -366,4 +366,5 @@ struct hd44780_common *hd44780_common_alloc(void)
 }
 EXPORT_SYMBOL_GPL(hd44780_common_alloc);
 
+MODULE_DESCRIPTION("Common functions for HD44780 (and compatibles) LCD displays");
 MODULE_LICENSE("GPL");
diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c
index ce98794..8a7034b 100644
--- a/drivers/auxdisplay/ht16k33.c
+++ b/drivers/auxdisplay/ht16k33.c
@@ -483,6 +483,7 @@ static int ht16k33_led_probe(struct device *dev, struct led_classdev *led,
 	led->max_brightness = MAX_BRIGHTNESS;
 
 	err = devm_led_classdev_register_ext(dev, led, &init_data);
+	fwnode_handle_put(init_data.fwnode);
 	if (err)
 		dev_err(dev, "Failed to register LED\n");
 
diff --git a/drivers/auxdisplay/line-display.c b/drivers/auxdisplay/line-display.c
index e2b5462..731ffdf 100644
--- a/drivers/auxdisplay/line-display.c
+++ b/drivers/auxdisplay/line-display.c
@@ -8,7 +8,9 @@
  * Copyright (C) 2021 Glider bv
  */
 
+#ifndef CONFIG_PANEL_BOOT_MESSAGE
 #include <generated/utsrelease.h>
+#endif
 
 #include <linux/container_of.h>
 #include <linux/device.h>
@@ -312,6 +314,12 @@ static int linedisp_init_map(struct linedisp *linedisp)
 	return 0;
 }
 
+#ifdef CONFIG_PANEL_BOOT_MESSAGE
+#define LINEDISP_INIT_TEXT CONFIG_PANEL_BOOT_MESSAGE
+#else
+#define LINEDISP_INIT_TEXT "Linux " UTS_RELEASE "       "
+#endif
+
 /**
  * linedisp_register - register a character line display
  * @linedisp: pointer to character line display structure
@@ -359,7 +367,7 @@ int linedisp_register(struct linedisp *linedisp, struct device *parent,
 		goto out_del_timer;
 
 	/* display a default message */
-	err = linedisp_display(linedisp, "Linux " UTS_RELEASE "       ", -1);
+	err = linedisp_display(linedisp, LINEDISP_INIT_TEXT, -1);
 	if (err)
 		goto out_del_dev;
 
@@ -388,4 +396,5 @@ void linedisp_unregister(struct linedisp *linedisp)
 }
 EXPORT_SYMBOL_NS_GPL(linedisp_unregister, LINEDISP);
 
+MODULE_DESCRIPTION("Character line display core support");
 MODULE_LICENSE("GPL");
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index 5b59d13..555aee3 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -445,7 +445,7 @@ static int __init arch_acpi_numa_init(void)
 
 	ret = acpi_numa_init();
 	if (ret) {
-		pr_info("Failed to initialise from firmware\n");
+		pr_debug("Failed to initialise from firmware\n");
 		return ret;
 	}
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index c66d070..75fcb75d 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/cacheinfo.h>
+#include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
@@ -513,10 +514,10 @@ core_initcall(free_raw_capacity);
  */
 static int __init get_cpu_for_node(struct device_node *node)
 {
-	struct device_node *cpu_node;
 	int cpu;
+	struct device_node *cpu_node __free(device_node) =
+		of_parse_phandle(node, "cpu", 0);
 
-	cpu_node = of_parse_phandle(node, "cpu", 0);
 	if (!cpu_node)
 		return -1;
 
@@ -527,7 +528,6 @@ static int __init get_cpu_for_node(struct device_node *node)
 		pr_info("CPU node for %pOF exist but the possible cpu range is :%*pbl\n",
 			cpu_node, cpumask_pr_args(cpu_possible_mask));
 
-	of_node_put(cpu_node);
 	return cpu;
 }
 
@@ -538,28 +538,28 @@ static int __init parse_core(struct device_node *core, int package_id,
 	bool leaf = true;
 	int i = 0;
 	int cpu;
-	struct device_node *t;
 
 	do {
 		snprintf(name, sizeof(name), "thread%d", i);
-		t = of_get_child_by_name(core, name);
-		if (t) {
-			leaf = false;
-			cpu = get_cpu_for_node(t);
-			if (cpu >= 0) {
-				cpu_topology[cpu].package_id = package_id;
-				cpu_topology[cpu].cluster_id = cluster_id;
-				cpu_topology[cpu].core_id = core_id;
-				cpu_topology[cpu].thread_id = i;
-			} else if (cpu != -ENODEV) {
-				pr_err("%pOF: Can't get CPU for thread\n", t);
-				of_node_put(t);
-				return -EINVAL;
-			}
-			of_node_put(t);
+		struct device_node *t __free(device_node) =
+			of_get_child_by_name(core, name);
+
+		if (!t)
+			break;
+
+		leaf = false;
+		cpu = get_cpu_for_node(t);
+		if (cpu >= 0) {
+			cpu_topology[cpu].package_id = package_id;
+			cpu_topology[cpu].cluster_id = cluster_id;
+			cpu_topology[cpu].core_id = core_id;
+			cpu_topology[cpu].thread_id = i;
+		} else if (cpu != -ENODEV) {
+			pr_err("%pOF: Can't get CPU for thread\n", t);
+			return -EINVAL;
 		}
 		i++;
-	} while (t);
+	} while (1);
 
 	cpu = get_cpu_for_node(core);
 	if (cpu >= 0) {
@@ -586,7 +586,6 @@ static int __init parse_cluster(struct device_node *cluster, int package_id,
 	char name[20];
 	bool leaf = true;
 	bool has_cores = false;
-	struct device_node *c;
 	int core_id = 0;
 	int i, ret;
 
@@ -598,49 +597,50 @@ static int __init parse_cluster(struct device_node *cluster, int package_id,
 	i = 0;
 	do {
 		snprintf(name, sizeof(name), "cluster%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			leaf = false;
-			ret = parse_cluster(c, package_id, i, depth + 1);
-			if (depth > 0)
-				pr_warn("Topology for clusters of clusters not yet supported\n");
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
+		struct device_node *c __free(device_node) =
+			of_get_child_by_name(cluster, name);
+
+		if (!c)
+			break;
+
+		leaf = false;
+		ret = parse_cluster(c, package_id, i, depth + 1);
+		if (depth > 0)
+			pr_warn("Topology for clusters of clusters not yet supported\n");
+		if (ret != 0)
+			return ret;
 		i++;
-	} while (c);
+	} while (1);
 
 	/* Now check for cores */
 	i = 0;
 	do {
 		snprintf(name, sizeof(name), "core%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			has_cores = true;
+		struct device_node *c __free(device_node) =
+			of_get_child_by_name(cluster, name);
 
-			if (depth == 0) {
-				pr_err("%pOF: cpu-map children should be clusters\n",
-				       c);
-				of_node_put(c);
-				return -EINVAL;
-			}
+		if (!c)
+			break;
 
-			if (leaf) {
-				ret = parse_core(c, package_id, cluster_id,
-						 core_id++);
-			} else {
-				pr_err("%pOF: Non-leaf cluster with core %s\n",
-				       cluster, name);
-				ret = -EINVAL;
-			}
+		has_cores = true;
 
-			of_node_put(c);
+		if (depth == 0) {
+			pr_err("%pOF: cpu-map children should be clusters\n", c);
+			return -EINVAL;
+		}
+
+		if (leaf) {
+			ret = parse_core(c, package_id, cluster_id, core_id++);
 			if (ret != 0)
 				return ret;
+		} else {
+			pr_err("%pOF: Non-leaf cluster with core %s\n",
+			       cluster, name);
+			return -EINVAL;
 		}
+
 		i++;
-	} while (c);
+	} while (1);
 
 	if (leaf && !has_cores)
 		pr_warn("%pOF: empty cluster\n", cluster);
@@ -651,22 +651,24 @@ static int __init parse_cluster(struct device_node *cluster, int package_id,
 static int __init parse_socket(struct device_node *socket)
 {
 	char name[20];
-	struct device_node *c;
 	bool has_socket = false;
 	int package_id = 0, ret;
 
 	do {
 		snprintf(name, sizeof(name), "socket%d", package_id);
-		c = of_get_child_by_name(socket, name);
-		if (c) {
-			has_socket = true;
-			ret = parse_cluster(c, package_id, -1, 0);
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
+		struct device_node *c __free(device_node) =
+			of_get_child_by_name(socket, name);
+
+		if (!c)
+			break;
+
+		has_socket = true;
+		ret = parse_cluster(c, package_id, -1, 0);
+		if (ret != 0)
+			return ret;
+
 		package_id++;
-	} while (c);
+	} while (1);
 
 	if (!has_socket)
 		ret = parse_cluster(socket, 0, -1, 0);
@@ -676,11 +678,11 @@ static int __init parse_socket(struct device_node *socket)
 
 static int __init parse_dt_topology(void)
 {
-	struct device_node *cn, *map;
 	int ret = 0;
 	int cpu;
+	struct device_node *cn __free(device_node) =
+		of_find_node_by_path("/cpus");
 
-	cn = of_find_node_by_path("/cpus");
 	if (!cn) {
 		pr_err("No CPU information found in DT\n");
 		return 0;
@@ -690,13 +692,15 @@ static int __init parse_dt_topology(void)
 	 * When topology is provided cpu-map is essentially a root
 	 * cluster with restricted subnodes.
 	 */
-	map = of_get_child_by_name(cn, "cpu-map");
+	struct device_node *map __free(device_node) =
+		of_get_child_by_name(cn, "cpu-map");
+
 	if (!map)
-		goto out;
+		return ret;
 
 	ret = parse_socket(map);
 	if (ret != 0)
-		goto out_map;
+		return ret;
 
 	topology_normalize_cpu_scale();
 
@@ -706,14 +710,9 @@ static int __init parse_dt_topology(void)
 	 */
 	for_each_possible_cpu(cpu)
 		if (cpu_topology[cpu].package_id < 0) {
-			ret = -EINVAL;
-			break;
+			return -EINVAL;
 		}
 
-out_map:
-	of_node_put(map);
-out:
-	of_node_put(cn);
 	return ret;
 }
 #endif
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index 3f01f4e..54b9283 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -177,10 +177,10 @@ static const struct auxiliary_device_id *auxiliary_match_id(const struct auxilia
 	return NULL;
 }
 
-static int auxiliary_match(struct device *dev, struct device_driver *drv)
+static int auxiliary_match(struct device *dev, const struct device_driver *drv)
 {
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
-	struct auxiliary_driver *auxdrv = to_auxiliary_drv(drv);
+	const struct auxiliary_driver *auxdrv = to_auxiliary_drv(drv);
 
 	return !!auxiliary_match_id(auxdrv->id_table, auxdev);
 }
@@ -203,7 +203,7 @@ static const struct dev_pm_ops auxiliary_dev_pm_ops = {
 
 static int auxiliary_bus_probe(struct device *dev)
 {
-	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
+	const struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
 	int ret;
 
@@ -222,7 +222,7 @@ static int auxiliary_bus_probe(struct device *dev)
 
 static void auxiliary_bus_remove(struct device *dev)
 {
-	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
+	const struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
 
 	if (auxdrv->remove)
@@ -232,7 +232,7 @@ static void auxiliary_bus_remove(struct device *dev)
 
 static void auxiliary_bus_shutdown(struct device *dev)
 {
-	struct auxiliary_driver *auxdrv = NULL;
+	const struct auxiliary_driver *auxdrv = NULL;
 	struct auxiliary_device *auxdev;
 
 	if (dev->driver) {
diff --git a/drivers/base/base.h b/drivers/base/base.h
index db4f910..0b53593 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -112,7 +112,7 @@ struct device_private {
 	struct klist_node knode_bus;
 	struct klist_node knode_class;
 	struct list_head deferred_probe;
-	struct device_driver *async_driver;
+	const struct device_driver *async_driver;
 	char *deferred_probe_reason;
 	struct device *device;
 	u8 dead:1;
@@ -155,13 +155,13 @@ bool bus_is_registered(const struct bus_type *bus);
 
 int bus_add_driver(struct device_driver *drv);
 void bus_remove_driver(struct device_driver *drv);
-void device_release_driver_internal(struct device *dev, struct device_driver *drv,
+void device_release_driver_internal(struct device *dev, const struct device_driver *drv,
 				    struct device *parent);
 
-void driver_detach(struct device_driver *drv);
+void driver_detach(const struct device_driver *drv);
 void driver_deferred_probe_del(struct device *dev);
 void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf);
-static inline int driver_match_device(struct device_driver *drv,
+static inline int driver_match_device(const struct device_driver *drv,
 				      struct device *dev)
 {
 	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
@@ -175,8 +175,8 @@ static inline void dev_sync_state(struct device *dev)
 		dev->driver->sync_state(dev);
 }
 
-int driver_add_groups(struct device_driver *drv, const struct attribute_group **groups);
-void driver_remove_groups(struct device_driver *drv, const struct attribute_group **groups);
+int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups);
+void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
 void device_driver_detach(struct device *dev);
 
 int devres_release_all(struct device *dev);
@@ -192,8 +192,8 @@ extern struct kset *devices_kset;
 void devices_kset_move_last(struct device *dev);
 
 #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
-int module_add_driver(struct module *mod, struct device_driver *drv);
-void module_remove_driver(struct device_driver *drv);
+int module_add_driver(struct module *mod, const struct device_driver *drv);
+void module_remove_driver(const struct device_driver *drv);
 #else
 static inline int module_add_driver(struct module *mod,
 				    struct device_driver *drv)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2b4c062..730cae6 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -5021,11 +5021,22 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (err != -EPROBE_DEFER) {
-		dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
-	} else {
+	switch (err) {
+	case -EPROBE_DEFER:
 		device_set_deferred_probe_reason(dev, &vaf);
 		dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
+		break;
+
+	case -ENOMEM:
+		/*
+		 * We don't print anything on -ENOMEM, there is already enough
+		 * output.
+		 */
+		break;
+
+	default:
+		dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
+		break;
 	}
 
 	va_end(args);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index b57326f..fdaa24b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -26,7 +26,7 @@
 
 static DEFINE_PER_CPU(struct device *, cpu_sys_devices);
 
-static int cpu_subsys_match(struct device *dev, struct device_driver *drv)
+static int cpu_subsys_match(struct device *dev, const struct device_driver *drv)
 {
 	/* ACPI style match is the only one that may succeed. */
 	if (acpi_driver_match_device(dev, drv))
@@ -316,7 +316,7 @@ static ssize_t crash_hotplug_show(struct device *dev,
 {
 	return sysfs_emit(buf, "%d\n", crash_check_hotplug_support());
 }
-static DEVICE_ATTR_ADMIN_RO(crash_hotplug);
+static DEVICE_ATTR_RO(crash_hotplug);
 #endif
 
 static void cpu_device_release(struct device *dev)
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 83d3523..9b745ba 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -568,7 +568,7 @@ static void device_remove(struct device *dev)
 		dev->driver->remove(dev);
 }
 
-static int call_driver_probe(struct device *dev, struct device_driver *drv)
+static int call_driver_probe(struct device *dev, const struct device_driver *drv)
 {
 	int ret = 0;
 
@@ -599,7 +599,7 @@ static int call_driver_probe(struct device *dev, struct device_driver *drv)
 	return ret;
 }
 
-static int really_probe(struct device *dev, struct device_driver *drv)
+static int really_probe(struct device *dev, const struct device_driver *drv)
 {
 	bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) &&
 			   !drv->suppress_bind_attrs;
@@ -628,7 +628,8 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	}
 
 re_probe:
-	dev->driver = drv;
+	// FIXME - this cast should not be needed "soon"
+	dev->driver = (struct device_driver *)drv;
 
 	/* If using pinctrl, bind pins now before probing */
 	ret = pinctrl_bind_pins(dev);
@@ -727,7 +728,7 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 /*
  * For initcall_debug, show the driver probe time.
  */
-static int really_probe_debug(struct device *dev, struct device_driver *drv)
+static int really_probe_debug(struct device *dev, const struct device_driver *drv)
 {
 	ktime_t calltime, rettime;
 	int ret;
@@ -774,7 +775,7 @@ void wait_for_device_probe(void)
 }
 EXPORT_SYMBOL_GPL(wait_for_device_probe);
 
-static int __driver_probe_device(struct device_driver *drv, struct device *dev)
+static int __driver_probe_device(const struct device_driver *drv, struct device *dev)
 {
 	int ret = 0;
 
@@ -819,7 +820,7 @@ static int __driver_probe_device(struct device_driver *drv, struct device *dev)
  *
  * If the device has a parent, runtime-resume the parent before driver probing.
  */
-static int driver_probe_device(struct device_driver *drv, struct device *dev)
+static int driver_probe_device(const struct device_driver *drv, struct device *dev)
 {
 	int trigger_count = atomic_read(&deferred_trigger_count);
 	int ret;
@@ -863,7 +864,7 @@ static int __init save_async_options(char *buf)
 }
 __setup("driver_async_probe=", save_async_options);
 
-static bool driver_allows_async_probing(struct device_driver *drv)
+static bool driver_allows_async_probing(const struct device_driver *drv)
 {
 	switch (drv->probe_type) {
 	case PROBE_PREFER_ASYNCHRONOUS:
@@ -1117,7 +1118,7 @@ static void __device_driver_unlock(struct device *dev, struct device *parent)
  * Manually attach driver to a device. Will acquire both @dev lock and
  * @dev->parent lock if needed. Returns 0 on success, -ERR on failure.
  */
-int device_driver_attach(struct device_driver *drv, struct device *dev)
+int device_driver_attach(const struct device_driver *drv, struct device *dev)
 {
 	int ret;
 
@@ -1137,7 +1138,7 @@ EXPORT_SYMBOL_GPL(device_driver_attach);
 static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie)
 {
 	struct device *dev = _dev;
-	struct device_driver *drv;
+	const struct device_driver *drv;
 	int ret;
 
 	__device_driver_lock(dev, dev->parent);
@@ -1153,7 +1154,7 @@ static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie)
 
 static int __driver_attach(struct device *dev, void *data)
 {
-	struct device_driver *drv = data;
+	const struct device_driver *drv = data;
 	bool async = false;
 	int ret;
 
@@ -1226,9 +1227,10 @@ static int __driver_attach(struct device *dev, void *data)
  * returns 0 and the @dev->driver is set, we've found a
  * compatible pair.
  */
-int driver_attach(struct device_driver *drv)
+int driver_attach(const struct device_driver *drv)
 {
-	return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
+	/* The (void *) will be put back to const * in __driver_attach() */
+	return bus_for_each_dev(drv->bus, NULL, (void *)drv, __driver_attach);
 }
 EXPORT_SYMBOL_GPL(driver_attach);
 
@@ -1284,7 +1286,7 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 }
 
 void device_release_driver_internal(struct device *dev,
-				    struct device_driver *drv,
+				    const struct device_driver *drv,
 				    struct device *parent)
 {
 	__device_driver_lock(dev, parent);
@@ -1333,7 +1335,7 @@ void device_driver_detach(struct device *dev)
  * driver_detach - detach driver from all devices it controls.
  * @drv: driver.
  */
-void driver_detach(struct device_driver *drv)
+void driver_detach(const struct device_driver *drv)
 {
 	struct device_private *dev_prv;
 	struct device *dev;
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 3df0025..a2ce0ea 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -85,7 +85,7 @@ static void group_close_release(struct device *dev, void *res)
 	/* noop */
 }
 
-static struct devres_group * node_to_group(struct devres_node *node)
+static struct devres_group *node_to_group(struct devres_node *node)
 {
 	if (node->release == &group_open_release)
 		return container_of(node, struct devres_group, node[0]);
@@ -107,8 +107,8 @@ static bool check_dr_size(size_t size, size_t *tot_size)
 	return true;
 }
 
-static __always_inline struct devres * alloc_dr(dr_release_t release,
-						size_t size, gfp_t gfp, int nid)
+static __always_inline struct devres *alloc_dr(dr_release_t release,
+					       size_t size, gfp_t gfp, int nid)
 {
 	size_t tot_size;
 	struct devres *dr;
@@ -283,8 +283,8 @@ static struct devres *find_dr(struct device *dev, dr_release_t release,
  * RETURNS:
  * Pointer to found devres, NULL if not found.
  */
-void * devres_find(struct device *dev, dr_release_t release,
-		   dr_match_t match, void *match_data)
+void *devres_find(struct device *dev, dr_release_t release,
+		  dr_match_t match, void *match_data)
 {
 	struct devres *dr;
 	unsigned long flags;
@@ -313,8 +313,8 @@ EXPORT_SYMBOL_GPL(devres_find);
  * RETURNS:
  * Pointer to found or added devres.
  */
-void * devres_get(struct device *dev, void *new_res,
-		  dr_match_t match, void *match_data)
+void *devres_get(struct device *dev, void *new_res,
+		 dr_match_t match, void *match_data)
 {
 	struct devres *new_dr = container_of(new_res, struct devres, data);
 	struct devres *dr;
@@ -349,8 +349,8 @@ EXPORT_SYMBOL_GPL(devres_get);
  * RETURNS:
  * Pointer to removed devres on success, NULL if not found.
  */
-void * devres_remove(struct device *dev, dr_release_t release,
-		     dr_match_t match, void *match_data)
+void *devres_remove(struct device *dev, dr_release_t release,
+		    dr_match_t match, void *match_data)
 {
 	struct devres *dr;
 	unsigned long flags;
@@ -549,7 +549,7 @@ int devres_release_all(struct device *dev)
  * RETURNS:
  * ID of the new group, NULL on failure.
  */
-void * devres_open_group(struct device *dev, void *id, gfp_t gfp)
+void *devres_open_group(struct device *dev, void *id, gfp_t gfp)
 {
 	struct devres_group *grp;
 	unsigned long flags;
@@ -567,6 +567,7 @@ void * devres_open_group(struct device *dev, void *id, gfp_t gfp)
 	grp->id = grp;
 	if (id)
 		grp->id = id;
+	grp->color = 0;
 
 	spin_lock_irqsave(&dev->devres_lock, flags);
 	add_dr(dev, &grp->node[0]);
@@ -576,7 +577,7 @@ void * devres_open_group(struct device *dev, void *id, gfp_t gfp)
 EXPORT_SYMBOL_GPL(devres_open_group);
 
 /* Find devres group with ID @id.  If @id is NULL, look for the latest. */
-static struct devres_group * find_group(struct device *dev, void *id)
+static struct devres_group *find_group(struct device *dev, void *id)
 {
 	struct devres_node *node;
 
@@ -896,9 +897,12 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp)
 	/*
 	 * Otherwise: allocate new, larger chunk. We need to allocate before
 	 * taking the lock as most probably the caller uses GFP_KERNEL.
+	 * alloc_dr() will call check_dr_size() to reserve extra memory
+	 * for struct devres automatically, so size @new_size user request
+	 * is delivered to it directly as devm_kmalloc() does.
 	 */
 	new_dr = alloc_dr(devm_kmalloc_release,
-			  total_new_size, gfp, dev_to_node(dev));
+			  new_size, gfp, dev_to_node(dev));
 	if (!new_dr)
 		return NULL;
 
@@ -1222,7 +1226,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu);
  */
 void devm_free_percpu(struct device *dev, void __percpu *pdata)
 {
-	WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match,
+	/*
+	 * Use devres_release() to prevent memory leakage as
+	 * devm_free_pages() does.
+	 */
+	WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match,
 			       (__force void *)pdata));
 }
 EXPORT_SYMBOL_GPL(devm_free_percpu);
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index c8436c2..88c6fd1 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -148,7 +148,7 @@ EXPORT_SYMBOL_GPL(driver_for_each_device);
  * if it does.  If the callback returns non-zero, this function will
  * return to the caller and not iterate over any more devices.
  */
-struct device *driver_find_device(struct device_driver *drv,
+struct device *driver_find_device(const struct device_driver *drv,
 				  struct device *start, const void *data,
 				  int (*match)(struct device *dev, const void *data))
 {
@@ -173,7 +173,7 @@ EXPORT_SYMBOL_GPL(driver_find_device);
  * @drv: driver.
  * @attr: driver attribute descriptor.
  */
-int driver_create_file(struct device_driver *drv,
+int driver_create_file(const struct device_driver *drv,
 		       const struct driver_attribute *attr)
 {
 	int error;
@@ -191,7 +191,7 @@ EXPORT_SYMBOL_GPL(driver_create_file);
  * @drv: driver.
  * @attr: driver attribute descriptor.
  */
-void driver_remove_file(struct device_driver *drv,
+void driver_remove_file(const struct device_driver *drv,
 			const struct driver_attribute *attr)
 {
 	if (drv)
@@ -199,13 +199,13 @@ void driver_remove_file(struct device_driver *drv,
 }
 EXPORT_SYMBOL_GPL(driver_remove_file);
 
-int driver_add_groups(struct device_driver *drv,
+int driver_add_groups(const struct device_driver *drv,
 		      const struct attribute_group **groups)
 {
 	return sysfs_create_groups(&drv->p->kobj, groups);
 }
 
-void driver_remove_groups(struct device_driver *drv,
+void driver_remove_groups(const struct device_driver *drv,
 			  const struct attribute_group **groups)
 {
 	sysfs_remove_groups(&drv->p->kobj, groups);
diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig
index 5ca00e0..a037016 100644
--- a/drivers/base/firmware_loader/Kconfig
+++ b/drivers/base/firmware_loader/Kconfig
@@ -37,6 +37,13 @@
 	  SHA256 checksums to the kernel log for each firmware file that is
 	  loaded.
 
+config RUST_FW_LOADER_ABSTRACTIONS
+	bool "Rust Firmware Loader abstractions"
+	depends on RUST
+	depends on FW_LOADER=y
+	help
+	  This enables the Rust abstractions for the firmware loader API.
+
 if FW_LOADER
 
 config FW_LOADER_PAGED_BUF
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index da8ca01..a03ee4b 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -1172,6 +1172,49 @@ static void request_firmware_work_func(struct work_struct *work)
 	kfree(fw_work);
 }
 
+
+static int _request_firmware_nowait(
+	struct module *module, bool uevent,
+	const char *name, struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context), bool nowarn)
+{
+	struct firmware_work *fw_work;
+
+	fw_work = kzalloc(sizeof(struct firmware_work), gfp);
+	if (!fw_work)
+		return -ENOMEM;
+
+	fw_work->module = module;
+	fw_work->name = kstrdup_const(name, gfp);
+	if (!fw_work->name) {
+		kfree(fw_work);
+		return -ENOMEM;
+	}
+	fw_work->device = device;
+	fw_work->context = context;
+	fw_work->cont = cont;
+	fw_work->opt_flags = FW_OPT_NOWAIT |
+		(uevent ? FW_OPT_UEVENT : FW_OPT_USERHELPER) |
+		(nowarn ? FW_OPT_NO_WARN : 0);
+
+	if (!uevent && fw_cache_is_setup(device, name)) {
+		kfree_const(fw_work->name);
+		kfree(fw_work);
+		return -EOPNOTSUPP;
+	}
+
+	if (!try_module_get(module)) {
+		kfree_const(fw_work->name);
+		kfree(fw_work);
+		return -EFAULT;
+	}
+
+	get_device(fw_work->device);
+	INIT_WORK(&fw_work->work, request_firmware_work_func);
+	schedule_work(&fw_work->work);
+	return 0;
+}
+
 /**
  * request_firmware_nowait() - asynchronous version of request_firmware
  * @module: module requesting the firmware
@@ -1195,49 +1238,42 @@ static void request_firmware_work_func(struct work_struct *work)
  *
  *		- can't sleep at all if @gfp is GFP_ATOMIC.
  **/
-int
-request_firmware_nowait(
+int request_firmware_nowait(
 	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
-	struct firmware_work *fw_work;
+	return _request_firmware_nowait(module, uevent, name, device, gfp,
+					context, cont, false);
 
-	fw_work = kzalloc(sizeof(struct firmware_work), gfp);
-	if (!fw_work)
-		return -ENOMEM;
-
-	fw_work->module = module;
-	fw_work->name = kstrdup_const(name, gfp);
-	if (!fw_work->name) {
-		kfree(fw_work);
-		return -ENOMEM;
-	}
-	fw_work->device = device;
-	fw_work->context = context;
-	fw_work->cont = cont;
-	fw_work->opt_flags = FW_OPT_NOWAIT |
-		(uevent ? FW_OPT_UEVENT : FW_OPT_USERHELPER);
-
-	if (!uevent && fw_cache_is_setup(device, name)) {
-		kfree_const(fw_work->name);
-		kfree(fw_work);
-		return -EOPNOTSUPP;
-	}
-
-	if (!try_module_get(module)) {
-		kfree_const(fw_work->name);
-		kfree(fw_work);
-		return -EFAULT;
-	}
-
-	get_device(fw_work->device);
-	INIT_WORK(&fw_work->work, request_firmware_work_func);
-	schedule_work(&fw_work->work);
-	return 0;
 }
 EXPORT_SYMBOL(request_firmware_nowait);
 
+/**
+ * firmware_request_nowait_nowarn() - async version of request_firmware_nowarn
+ * @module: module requesting the firmware
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ * @gfp: allocation flags
+ * @context: will be passed over to @cont, and
+ *	@fw may be %NULL if firmware request fails.
+ * @cont: function will be called asynchronously when the firmware
+ *	request is over.
+ *
+ * Similar in function to request_firmware_nowait(), but doesn't print a warning
+ * when the firmware file could not be found and always sends a uevent to copy
+ * the firmware image.
+ */
+int firmware_request_nowait_nowarn(
+	struct module *module, const char *name,
+	struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context))
+{
+	return _request_firmware_nowait(module, FW_ACTION_UEVENT, name, device,
+					gfp, context, cont, true);
+}
+EXPORT_SYMBOL_GPL(firmware_request_nowait_nowarn);
+
 #ifdef CONFIG_FW_CACHE
 static ASYNC_DOMAIN_EXCLUSIVE(fw_cache_domain);
 
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index e23d0b4..bfd9215 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -23,7 +23,7 @@ struct isa_dev {
 
 #define to_isa_dev(x) container_of((x), struct isa_dev, dev)
 
-static int isa_bus_match(struct device *dev, struct device_driver *driver)
+static int isa_bus_match(struct device *dev, const struct device_driver *driver)
 {
 	struct isa_driver *isa_driver = to_isa_driver(driver);
 
diff --git a/drivers/base/module.c b/drivers/base/module.c
index a1b55da..7af224e 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -9,7 +9,7 @@
 #include <linux/string.h>
 #include "base.h"
 
-static char *make_driver_name(struct device_driver *drv)
+static char *make_driver_name(const struct device_driver *drv)
 {
 	char *driver_name;
 
@@ -30,7 +30,7 @@ static void module_create_drivers_dir(struct module_kobject *mk)
 	mutex_unlock(&drivers_dir_mutex);
 }
 
-int module_add_driver(struct module *mod, struct device_driver *drv)
+int module_add_driver(struct module *mod, const struct device_driver *drv)
 {
 	char *driver_name;
 	struct module_kobject *mk = NULL;
@@ -89,7 +89,7 @@ int module_add_driver(struct module *mod, struct device_driver *drv)
 	return ret;
 }
 
-void module_remove_driver(struct device_driver *drv)
+void module_remove_driver(const struct device_driver *drv)
 {
 	struct module_kobject *mk = NULL;
 	char *driver_name;
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 10c5779..4c3ee65 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -608,7 +608,7 @@ int platform_device_add_resources(struct platform_device *pdev,
 	struct resource *r = NULL;
 
 	if (res) {
-		r = kmemdup(res, sizeof(struct resource) * num, GFP_KERNEL);
+		r = kmemdup_array(res, num, sizeof(*r), GFP_KERNEL);
 		if (!r)
 			return -ENOMEM;
 	}
@@ -1122,7 +1122,7 @@ static int platform_legacy_resume(struct device *dev)
 
 int platform_pm_suspend(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1140,7 +1140,7 @@ int platform_pm_suspend(struct device *dev)
 
 int platform_pm_resume(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1162,7 +1162,7 @@ int platform_pm_resume(struct device *dev)
 
 int platform_pm_freeze(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1180,7 +1180,7 @@ int platform_pm_freeze(struct device *dev)
 
 int platform_pm_thaw(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1198,7 +1198,7 @@ int platform_pm_thaw(struct device *dev)
 
 int platform_pm_poweroff(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1216,7 +1216,7 @@ int platform_pm_poweroff(struct device *dev)
 
 int platform_pm_restore(struct device *dev)
 {
-	struct device_driver *drv = dev->driver;
+	const struct device_driver *drv = dev->driver;
 	int ret = 0;
 
 	if (!drv)
@@ -1332,7 +1332,7 @@ __ATTRIBUTE_GROUPS(platform_dev);
  * and compare it against the name of the driver. Return whether they match
  * or not.
  */
-static int platform_match(struct device *dev, struct device_driver *drv)
+static int platform_match(struct device *dev, const struct device_driver *drv)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct platform_driver *pdrv = to_platform_driver(drv);
@@ -1420,14 +1420,8 @@ static void platform_remove(struct device *_dev)
 	struct platform_driver *drv = to_platform_driver(_dev->driver);
 	struct platform_device *dev = to_platform_device(_dev);
 
-	if (drv->remove_new) {
-		drv->remove_new(dev);
-	} else if (drv->remove) {
-		int ret = drv->remove(dev);
-
-		if (ret)
-			dev_warn(_dev, "remove callback returned a non-zero value. This will be ignored.\n");
-	}
+	if (drv->remove)
+		drv->remove(dev);
 	dev_pm_domain_detach(_dev, true);
 }
 
diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c
index f0df2da..2dea9d2 100644
--- a/drivers/base/regmap/regcache-maple.c
+++ b/drivers/base/regmap/regcache-maple.c
@@ -110,7 +110,8 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
 	struct maple_tree *mt = map->cache;
 	MA_STATE(mas, mt, min, max);
 	unsigned long *entry, *lower, *upper;
-	unsigned long lower_index, lower_last;
+	/* initialized to work around false-positive -Wuninitialized warning */
+	unsigned long lower_index = 0, lower_last = 0;
 	unsigned long upper_index, upper_last;
 	int ret = 0;
 
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 6b5d349..6ecfc82 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -26,7 +26,7 @@ static unsigned int bcma_bus_next_num;
 /* bcma_buses_mutex locks the bcma_bus_next_num */
 static DEFINE_MUTEX(bcma_buses_mutex);
 
-static int bcma_bus_match(struct device *dev, struct device_driver *drv);
+static int bcma_bus_match(struct device *dev, const struct device_driver *drv);
 static int bcma_device_probe(struct device *dev);
 static void bcma_device_remove(struct device *dev);
 static int bcma_device_uevent(const struct device *dev, struct kobj_uevent_env *env);
@@ -584,10 +584,10 @@ void bcma_driver_unregister(struct bcma_driver *drv)
 }
 EXPORT_SYMBOL_GPL(bcma_driver_unregister);
 
-static int bcma_bus_match(struct device *dev, struct device_driver *drv)
+static int bcma_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct bcma_device *core = container_of(dev, struct bcma_device, dev);
-	struct bcma_driver *adrv = container_of(drv, struct bcma_driver, drv);
+	const struct bcma_driver *adrv = container_of_const(drv, struct bcma_driver, drv);
 	const struct bcma_device_id *cid = &core->id;
 	const struct bcma_device_id *did;
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index f92673f..a9e49b2 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -3422,6 +3422,7 @@ void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local)
 /**
  * drbd_bmio_set_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io()
  * @device:	DRBD device.
+ * @peer_device: Peer DRBD device.
  *
  * Sets all bits in the bitmap and writes the whole bitmap to stable storage.
  */
@@ -3448,6 +3449,7 @@ int drbd_bmio_set_n_write(struct drbd_device *device,
 /**
  * drbd_bmio_clear_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io()
  * @device:	DRBD device.
+ * @peer_device: Peer DRBD device.
  *
  * Clears all bits in the bitmap and writes the whole bitmap to stable storage.
  */
@@ -3501,6 +3503,7 @@ static int w_bitmap_io(struct drbd_work *w, int unused)
  * @done:	callback to be called after the bitmap IO was performed
  * @why:	Descriptive text of the reason for doing the IO
  * @flags:	Bitmap flags
+ * @peer_device: Peer DRBD device.
  *
  * While IO on the bitmap happens we freeze application IO thus we ensure
  * that drbd_set_out_of_sync() can not be called. This function MAY ONLY be
@@ -3549,6 +3552,7 @@ void drbd_queue_bitmap_io(struct drbd_device *device,
  * @io_fn:	IO callback to be called when bitmap IO is possible
  * @why:	Descriptive text of the reason for doing the IO
  * @flags:	Bitmap flags
+ * @peer_device: Peer DRBD device.
  *
  * freezes application IO while that the actual IO operations runs. This
  * functions MAY NOT be called from worker context.
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 008e850..9c8b19a 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -362,7 +362,7 @@ enum rbd_watch_state {
 enum rbd_lock_state {
 	RBD_LOCK_STATE_UNLOCKED,
 	RBD_LOCK_STATE_LOCKED,
-	RBD_LOCK_STATE_RELEASING,
+	RBD_LOCK_STATE_QUIESCING,
 };
 
 /* WatchNotify::ClientId */
@@ -422,7 +422,7 @@ struct rbd_device {
 	struct list_head	running_list;
 	struct completion	acquire_wait;
 	int			acquire_err;
-	struct completion	releasing_wait;
+	struct completion	quiescing_wait;
 
 	spinlock_t		object_map_lock;
 	u8			*object_map;
@@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev)
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 
 	return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED ||
-	       rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING;
+	       rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING;
 }
 
 static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
@@ -3457,13 +3457,14 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req)
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 	spin_lock(&rbd_dev->lock_lists_lock);
 	if (!list_empty(&img_req->lock_item)) {
+		rbd_assert(!list_empty(&rbd_dev->running_list));
 		list_del_init(&img_req->lock_item);
-		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING &&
 			       list_empty(&rbd_dev->running_list));
 	}
 	spin_unlock(&rbd_dev->lock_lists_lock);
 	if (need_wakeup)
-		complete(&rbd_dev->releasing_wait);
+		complete(&rbd_dev->quiescing_wait);
 }
 
 static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
@@ -3476,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
 	if (rbd_lock_add_request(img_req))
 		return 1;
 
-	if (rbd_dev->opts->exclusive) {
-		WARN_ON(1); /* lock got released? */
-		return -EROFS;
-	}
-
 	/*
 	 * Note the use of mod_delayed_work() in rbd_acquire_lock()
 	 * and cancel_delayed_work() in wake_lock_waiters().
@@ -4181,16 +4177,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
 	/*
 	 * Ensure that all in-flight IO is flushed.
 	 */
-	rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
-	rbd_assert(!completion_done(&rbd_dev->releasing_wait));
+	rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING;
+	rbd_assert(!completion_done(&rbd_dev->quiescing_wait));
 	if (list_empty(&rbd_dev->running_list))
 		return true;
 
 	up_write(&rbd_dev->lock_rwsem);
-	wait_for_completion(&rbd_dev->releasing_wait);
+	wait_for_completion(&rbd_dev->quiescing_wait);
 
 	down_write(&rbd_dev->lock_rwsem);
-	if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
+	if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING)
 		return false;
 
 	rbd_assert(list_empty(&rbd_dev->running_list));
@@ -4601,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
 			rbd_warn(rbd_dev, "failed to update lock cookie: %d",
 				 ret);
 
+		if (rbd_dev->opts->exclusive)
+			rbd_warn(rbd_dev,
+			     "temporarily releasing lock on exclusive mapping");
+
 		/*
 		 * Lock cookie cannot be updated on older OSDs, so do
 		 * a manual release and queue an acquire.
@@ -5376,7 +5376,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec)
 	INIT_LIST_HEAD(&rbd_dev->acquiring_list);
 	INIT_LIST_HEAD(&rbd_dev->running_list);
 	init_completion(&rbd_dev->acquire_wait);
-	init_completion(&rbd_dev->releasing_wait);
+	init_completion(&rbd_dev->quiescing_wait);
 
 	spin_lock_init(&rbd_dev->object_map_lock);
 
@@ -6582,11 +6582,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 	if (ret)
 		return ret;
 
-	/*
-	 * The lock may have been released by now, unless automatic lock
-	 * transitions are disabled.
-	 */
-	rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev));
 	return 0;
 }
 
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 6fb799e..890c08792b 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -48,6 +48,9 @@
 
 #define UBLK_MINORS		(1U << MINORBITS)
 
+/* private ioctl command mirror */
+#define UBLK_CMD_DEL_DEV_ASYNC	_IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC)
+
 /* All UBLK_F_* have to be included into UBLK_F_ALL */
 #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \
 		| UBLK_F_URING_CMD_COMP_IN_TASK \
@@ -2903,7 +2906,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	case UBLK_CMD_DEL_DEV:
 		ret = ublk_ctrl_del_dev(&ub, true);
 		break;
-	case UBLK_U_CMD_DEL_DEV_ASYNC:
+	case UBLK_CMD_DEL_DEV_ASYNC:
 		ret = ublk_ctrl_del_dev(&ub, false);
 		break;
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 78b96cd..dd68b819 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -80,11 +80,11 @@ static phys_addr_t mc_portal_base_phys_addr;
  *
  * Returns 1 on success, 0 otherwise.
  */
-static int fsl_mc_bus_match(struct device *dev, struct device_driver *drv)
+static int fsl_mc_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct fsl_mc_device_id *id;
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
-	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(drv);
+	const struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(drv);
 	bool found = false;
 
 	/* When driver_override is set, only bind to the matching driver */
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 4acfac7..b3eafcf 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -1694,10 +1694,10 @@ static int mhi_ep_uevent(const struct device *dev, struct kobj_uevent_env *env)
 					mhi_dev->name);
 }
 
-static int mhi_ep_match(struct device *dev, struct device_driver *drv)
+static int mhi_ep_match(struct device *dev, const struct device_driver *drv)
 {
 	struct mhi_ep_device *mhi_dev = to_mhi_ep_device(dev);
-	struct mhi_ep_driver *mhi_drv = to_mhi_ep_driver(drv);
+	const struct mhi_ep_driver *mhi_drv = to_mhi_ep_driver(drv);
 	const struct mhi_device_id *id;
 
 	/*
diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c
index 173f799..ce7d2e6 100644
--- a/drivers/bus/mhi/host/init.c
+++ b/drivers/bus/mhi/host/init.c
@@ -1442,10 +1442,10 @@ static int mhi_uevent(const struct device *dev, struct kobj_uevent_env *env)
 					mhi_dev->name);
 }
 
-static int mhi_match(struct device *dev, struct device_driver *drv)
+static int mhi_match(struct device *dev, const struct device_driver *drv)
 {
 	struct mhi_device *mhi_dev = to_mhi_device(dev);
-	struct mhi_driver *mhi_drv = to_mhi_driver(drv);
+	const struct mhi_driver *mhi_drv = to_mhi_driver(drv);
 	const struct mhi_device_id *id;
 
 	/*
diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c
index 8baf14b..12dd32f 100644
--- a/drivers/bus/mips_cdmm.c
+++ b/drivers/bus/mips_cdmm.c
@@ -37,7 +37,7 @@
 /* Each block of device registers is 64 bytes */
 #define CDMM_DRB_SIZE		64
 
-#define to_mips_cdmm_driver(d)	container_of(d, struct mips_cdmm_driver, drv)
+#define to_mips_cdmm_driver(d)	container_of_const(d, struct mips_cdmm_driver, drv)
 
 /* Default physical base address */
 static phys_addr_t mips_cdmm_default_base;
@@ -59,10 +59,10 @@ mips_cdmm_lookup(const struct mips_cdmm_device_id *table,
 	return ret ? table : NULL;
 }
 
-static int mips_cdmm_match(struct device *dev, struct device_driver *drv)
+static int mips_cdmm_match(struct device *dev, const struct device_driver *drv)
 {
 	struct mips_cdmm_device *cdev = to_mips_cdmm_device(dev);
-	struct mips_cdmm_driver *cdrv = to_mips_cdmm_driver(drv);
+	const struct mips_cdmm_driver *cdrv = to_mips_cdmm_driver(drv);
 
 	return mips_cdmm_lookup(cdrv->id_table, cdev) != NULL;
 }
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index 641c1a6a..8412406 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -83,10 +83,10 @@ static const struct attribute_group *moxtet_dev_groups[] = {
 	NULL,
 };
 
-static int moxtet_match(struct device *dev, struct device_driver *drv)
+static int moxtet_match(struct device *dev, const struct device_driver *drv)
 {
 	struct moxtet_device *mdev = to_moxtet_device(dev);
-	struct moxtet_driver *tdrv = to_moxtet_driver(drv);
+	const struct moxtet_driver *tdrv = to_moxtet_driver(drv);
 	const enum turris_mox_module_id *t;
 
 	if (of_driver_match_device(dev, drv))
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index ac6c7e4..eee41fb 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -130,7 +130,7 @@ struct sunxi_rsb {
 /* bus / slave device related functions */
 static const struct bus_type sunxi_rsb_bus;
 
-static int sunxi_rsb_device_match(struct device *dev, struct device_driver *drv)
+static int sunxi_rsb_device_match(struct device *dev, const struct device_driver *drv)
 {
 	return of_driver_match_device(dev, drv);
 }
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 8767e04..2b59ef6 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -2291,11 +2291,9 @@ static int sysc_init_idlemode(struct sysc *ddata, u8 *idlemodes,
 			      const char *name)
 {
 	struct device_node *np = ddata->dev->of_node;
-	struct property *prop;
-	const __be32 *p;
 	u32 val;
 
-	of_property_for_each_u32(np, name, prop, p, val) {
+	of_property_for_each_u32(np, name, val) {
 		if (val >= SYSC_NR_IDLEMODES) {
 			dev_err(ddata->dev, "invalid idlemode: %i\n", val);
 			return -EINVAL;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 49e4829..9b0f37d 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -3473,7 +3473,7 @@ static int cdrom_print_info(const char *header, int val, char *info,
 	return 0;
 }
 
-static int cdrom_sysctl_info(struct ctl_table *ctl, int write,
+static int cdrom_sysctl_info(const struct ctl_table *ctl, int write,
                            void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int pos;
@@ -3586,7 +3586,7 @@ static void cdrom_update_settings(void)
 	mutex_unlock(&cdrom_mutex);
 }
 
-static int cdrom_sysctl_handler(struct ctl_table *ctl, int write,
+static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 236d381..07371cb 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -262,10 +262,10 @@ EXPORT_SYMBOL_GPL(cdx_clear_master);
  *
  * Return: true on success, false otherwise.
  */
-static int cdx_bus_match(struct device *dev, struct device_driver *drv)
+static int cdx_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
-	struct cdx_driver *cdx_drv = to_cdx_driver(drv);
+	const struct cdx_driver *cdx_drv = to_cdx_driver(drv);
 	const struct cdx_device_id *found_id = NULL;
 	const struct cdx_device_id *ids;
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2597cb4..87fe612 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /*
- * Copyright (C) 2017-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
  * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved.
  *
@@ -56,6 +56,10 @@
 #include <linux/sched/isolation.h>
 #include <crypto/chacha.h>
 #include <crypto/blake2s.h>
+#ifdef CONFIG_VDSO_GETRANDOM
+#include <vdso/getrandom.h>
+#include <vdso/datapage.h>
+#endif
 #include <asm/archrandom.h>
 #include <asm/processor.h>
 #include <asm/irq.h>
@@ -271,6 +275,15 @@ static void crng_reseed(struct work_struct *work)
 	if (next_gen == ULONG_MAX)
 		++next_gen;
 	WRITE_ONCE(base_crng.generation, next_gen);
+#ifdef CONFIG_VDSO_GETRANDOM
+	/* base_crng.generation's invalid value is ULONG_MAX, while
+	 * _vdso_rng_data.generation's invalid value is 0, so add one to the
+	 * former to arrive at the latter. Use smp_store_release so that this
+	 * is ordered with the write above to base_crng.generation. Pairs with
+	 * the smp_rmb() before the syscall in the vDSO code.
+	 */
+	smp_store_release(&_vdso_rng_data.generation, next_gen + 1);
+#endif
 	if (!static_branch_likely(&crng_is_ready))
 		crng_init = CRNG_READY;
 	spin_unlock_irqrestore(&base_crng.lock, flags);
@@ -721,6 +734,9 @@ static void __cold _credit_init_bits(size_t bits)
 		if (static_key_initialized && system_unbound_wq)
 			queue_work(system_unbound_wq, &set_ready);
 		atomic_notifier_call_chain(&random_ready_notifier, 0, NULL);
+#ifdef CONFIG_VDSO_GETRANDOM
+		WRITE_ONCE(_vdso_rng_data.is_ready, true);
+#endif
 		wake_up_interruptible(&crng_init_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 		pr_notice("crng init done\n");
@@ -1604,7 +1620,7 @@ static u8 sysctl_bootid[UUID_SIZE];
  * UUID. The difference is in whether table->data is NULL; if it is,
  * then a new UUID is generated and returned to the user.
  */
-static int proc_do_uuid(struct ctl_table *table, int write, void *buf,
+static int proc_do_uuid(const struct ctl_table *table, int write, void *buf,
 			size_t *lenp, loff_t *ppos)
 {
 	u8 tmp_uuid[UUID_SIZE], *uuid;
@@ -1635,7 +1651,7 @@ static int proc_do_uuid(struct ctl_table *table, int write, void *buf,
 }
 
 /* The same as proc_dointvec, but writes don't change anything. */
-static int proc_do_rointvec(struct ctl_table *table, int write, void *buf,
+static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf,
 			    size_t *lenp, loff_t *ppos)
 {
 	return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c
index 1a4e634..0584205 100644
--- a/drivers/clk/clk-conf.c
+++ b/drivers/clk/clk-conf.c
@@ -81,13 +81,11 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier)
 static int __set_clk_rates(struct device_node *node, bool clk_supplier)
 {
 	struct of_phandle_args clkspec;
-	struct property	*prop;
-	const __be32 *cur;
 	int rc, index = 0;
 	struct clk *clk;
 	u32 rate;
 
-	of_property_for_each_u32(node, "assigned-clock-rates", prop, cur, rate) {
+	of_property_for_each_u32(node, "assigned-clock-rates", rate) {
 		if (rate) {
 			rc = of_parse_phandle_with_args(node, "assigned-clocks",
 					"#clock-cells",	index, &clkspec);
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 4ce83c5..a4c92c5 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -1175,8 +1175,8 @@ static int si5351_dt_parse(struct i2c_client *client,
 {
 	struct device_node *child, *np = client->dev.of_node;
 	struct si5351_platform_data *pdata;
-	struct property *prop;
-	const __be32 *p;
+	u32 array[4];
+	int sz, i;
 	int num = 0;
 	u32 val;
 
@@ -1191,20 +1191,24 @@ static int si5351_dt_parse(struct i2c_client *client,
 	 * property silabs,pll-source : <num src>, [<..>]
 	 * allow to selectively set pll source
 	 */
-	of_property_for_each_u32(np, "silabs,pll-source", prop, p, num) {
+	sz = of_property_read_variable_u32_array(np, "silabs,pll-source", array, 2, 4);
+	sz = (sz == -EINVAL) ? 0 : sz; /* Missing property is OK */
+	if (sz < 0)
+		return dev_err_probe(&client->dev, sz, "invalid pll-source\n");
+	if (sz % 2)
+		return dev_err_probe(&client->dev, -EINVAL,
+				     "missing pll-source for pll %d\n", array[sz - 1]);
+
+	for (i = 0; i < sz; i += 2) {
+		num = array[i];
+		val = array[i + 1];
+
 		if (num >= 2) {
 			dev_err(&client->dev,
 				"invalid pll %d on pll-source prop\n", num);
 			return -EINVAL;
 		}
 
-		p = of_prop_next_u32(prop, p, &val);
-		if (!p) {
-			dev_err(&client->dev,
-				"missing pll-source for pll %d\n", num);
-			return -EINVAL;
-		}
-
 		switch (val) {
 		case 0:
 			pdata->pll_src[num] = SI5351_PLL_SRC_XTAL;
@@ -1232,19 +1236,24 @@ static int si5351_dt_parse(struct i2c_client *client,
 	pdata->pll_reset[0] = true;
 	pdata->pll_reset[1] = true;
 
-	of_property_for_each_u32(np, "silabs,pll-reset-mode", prop, p, num) {
+	sz = of_property_read_variable_u32_array(np, "silabs,pll-reset-mode", array, 2, 4);
+	sz = (sz == -EINVAL) ? 0 : sz; /* Missing property is OK */
+	if (sz < 0)
+		return dev_err_probe(&client->dev, sz, "invalid pll-reset-mode\n");
+	if (sz % 2)
+		return dev_err_probe(&client->dev, -EINVAL,
+				     "missing pll-reset-mode for pll %d\n", array[sz - 1]);
+
+	for (i = 0; i < sz; i += 2) {
+		num = array[i];
+		val = array[i + 1];
+
 		if (num >= 2) {
 			dev_err(&client->dev,
 				"invalid pll %d on pll-reset-mode prop\n", num);
 			return -EINVAL;
 		}
 
-		p = of_prop_next_u32(prop, p, &val);
-		if (!p) {
-			dev_err(&client->dev,
-				"missing pll-reset-mode for pll %d\n", num);
-			return -EINVAL;
-		}
 
 		switch (val) {
 		case 0:
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 8cca52b..285ed1a 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -5364,9 +5364,8 @@ EXPORT_SYMBOL_GPL(of_clk_get_parent_count);
 const char *of_clk_get_parent_name(const struct device_node *np, int index)
 {
 	struct of_phandle_args clkspec;
-	struct property *prop;
 	const char *clk_name;
-	const __be32 *vp;
+	bool found = false;
 	u32 pv;
 	int rc;
 	int count;
@@ -5383,15 +5382,16 @@ const char *of_clk_get_parent_name(const struct device_node *np, int index)
 	/* if there is an indices property, use it to transfer the index
 	 * specified into an array offset for the clock-output-names property.
 	 */
-	of_property_for_each_u32(clkspec.np, "clock-indices", prop, vp, pv) {
+	of_property_for_each_u32(clkspec.np, "clock-indices", pv) {
 		if (index == pv) {
 			index = count;
+			found = true;
 			break;
 		}
 		count++;
 	}
 	/* We went off the end of 'clock-indices' without finding it */
-	if (prop && !vp)
+	if (of_property_present(clkspec.np, "clock-indices") && !found)
 		return NULL;
 
 	if (of_property_read_string_index(clkspec.np, "clock-output-names",
@@ -5504,14 +5504,12 @@ static int parent_ready(struct device_node *np)
 int of_clk_detect_critical(struct device_node *np, int index,
 			   unsigned long *flags)
 {
-	struct property *prop;
-	const __be32 *cur;
 	uint32_t idx;
 
 	if (!np || !flags)
 		return -EINVAL;
 
-	of_property_for_each_u32(np, "clock-critical", prop, cur, idx)
+	of_property_for_each_u32(np, "clock-critical", idx)
 		if (index == idx)
 			*flags |= CLK_IS_CRITICAL;
 
diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c
index ad2d0df..ec60ecb 100644
--- a/drivers/clk/davinci/da8xx-cfgchip.c
+++ b/drivers/clk/davinci/da8xx-cfgchip.c
@@ -508,7 +508,7 @@ da8xx_cfgchip_register_usb0_clk48(struct device *dev,
 	const char * const parent_names[] = { "usb_refclkin", "pll0_auxclk" };
 	struct clk *fck_clk;
 	struct da8xx_usb0_clk48 *usb0;
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	int ret;
 
 	fck_clk = devm_clk_get(dev, "fck");
@@ -583,7 +583,7 @@ da8xx_cfgchip_register_usb1_clk48(struct device *dev,
 {
 	const char * const parent_names[] = { "usb0_clk48", "usb_refclkin" };
 	struct da8xx_usb1_clk48 *usb1;
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	int ret;
 
 	usb1 = devm_kzalloc(dev, sizeof(*usb1), GFP_KERNEL);
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index ea3788b..33cc1f7 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -227,11 +227,9 @@ EXPORT_SYMBOL_GPL(qcom_cc_register_sleep_clk);
 static void qcom_cc_drop_protected(struct device *dev, struct qcom_cc *cc)
 {
 	struct device_node *np = dev->of_node;
-	struct property *prop;
-	const __be32 *p;
 	u32 i;
 
-	of_property_for_each_u32(np, "protected-clocks", prop, p, i) {
+	of_property_for_each_u32(np, "protected-clocks", i) {
 		if (i >= cc->num_rclks)
 			continue;
 
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index a026ccc..28945b6 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -1040,19 +1040,20 @@ static unsigned long __init exynos4_get_xom(void)
 static void __init exynos4_clk_register_finpll(struct samsung_clk_provider *ctx)
 {
 	struct samsung_fixed_rate_clock fclk;
-	struct clk *clk;
-	unsigned long finpll_f = 24000000;
+	unsigned long finpll_f;
+	unsigned int parent;
 	char *parent_name;
 	unsigned int xom = exynos4_get_xom();
 
 	parent_name = xom & 1 ? "xusbxti" : "xxti";
-	clk = clk_get(NULL, parent_name);
-	if (IS_ERR(clk)) {
+	parent = xom & 1 ? CLK_XUSBXTI : CLK_XXTI;
+
+	finpll_f = clk_hw_get_rate(ctx->clk_data.hws[parent]);
+	if (!finpll_f) {
 		pr_err("%s: failed to lookup parent clock %s, assuming "
 			"fin_pll clock frequency is 24MHz\n", __func__,
 			parent_name);
-	} else {
-		finpll_f = clk_get_rate(clk);
+		finpll_f = 24000000;
 	}
 
 	fclk.id = CLK_FIN_PLL;
diff --git a/drivers/clk/sophgo/clk-sg2042-pll.c b/drivers/clk/sophgo/clk-sg2042-pll.c
index 9695e64..ff9deee 100644
--- a/drivers/clk/sophgo/clk-sg2042-pll.c
+++ b/drivers/clk/sophgo/clk-sg2042-pll.c
@@ -387,7 +387,7 @@ static int sg2042_clk_pll_set_rate(struct clk_hw *hw,
 	struct sg2042_pll_clock *pll = to_sg2042_pll_clk(hw);
 	struct sg2042_pll_ctrl pctrl_table;
 	unsigned long flags;
-	u32 value;
+	u32 value = 0;
 	int ret;
 
 	spin_lock_irqsave(pll->lock, flags);
diff --git a/drivers/clk/sunxi/clk-simple-gates.c b/drivers/clk/sunxi/clk-simple-gates.c
index 0399627..845efc1 100644
--- a/drivers/clk/sunxi/clk-simple-gates.c
+++ b/drivers/clk/sunxi/clk-simple-gates.c
@@ -21,11 +21,9 @@ static void __init sunxi_simple_gates_setup(struct device_node *node,
 {
 	struct clk_onecell_data *clk_data;
 	const char *clk_parent, *clk_name;
-	struct property *prop;
 	struct resource res;
 	void __iomem *clk_reg;
 	void __iomem *reg;
-	const __be32 *p;
 	int number, i = 0, j;
 	u8 clk_bit;
 	u32 index;
@@ -47,7 +45,7 @@ static void __init sunxi_simple_gates_setup(struct device_node *node,
 	if (!clk_data->clks)
 		goto err_free_data;
 
-	of_property_for_each_u32(node, "clock-indices", prop, p, index) {
+	of_property_for_each_u32(node, "clock-indices", index) {
 		of_property_read_string_index(node, "clock-output-names",
 					      i, &clk_name);
 
diff --git a/drivers/clk/sunxi/clk-sun8i-bus-gates.c b/drivers/clk/sunxi/clk-sun8i-bus-gates.c
index b87f331..8482ac8 100644
--- a/drivers/clk/sunxi/clk-sun8i-bus-gates.c
+++ b/drivers/clk/sunxi/clk-sun8i-bus-gates.c
@@ -24,11 +24,9 @@ static void __init sun8i_h3_bus_gates_init(struct device_node *node)
 	const char *parents[PARENT_MAX];
 	struct clk_onecell_data *clk_data;
 	const char *clk_name;
-	struct property *prop;
 	struct resource res;
 	void __iomem *clk_reg;
 	void __iomem *reg;
-	const __be32 *p;
 	int number, i;
 	u8 clk_bit;
 	int index;
@@ -58,7 +56,7 @@ static void __init sun8i_h3_bus_gates_init(struct device_node *node)
 		goto err_free_data;
 
 	i = 0;
-	of_property_for_each_u32(node, "clock-indices", prop, p, index) {
+	of_property_for_each_u32(node, "clock-indices", index) {
 		of_property_read_string_index(node, "clock-output-names",
 					      i, &clk_name);
 
diff --git a/drivers/clk/thead/Kconfig b/drivers/clk/thead/Kconfig
index 1710d50..95e0d9e 100644
--- a/drivers/clk/thead/Kconfig
+++ b/drivers/clk/thead/Kconfig
@@ -3,6 +3,7 @@
 config CLK_THEAD_TH1520_AP
 	bool "T-HEAD TH1520 AP clock support"
 	depends on ARCH_THEAD || COMPILE_TEST
+	depends on 64BIT
 	default ARCH_THEAD
 	select REGMAP_MMIO
 	help
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 6e46781..b9561e3 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -418,8 +418,6 @@ void __init samsung_pwm_clocksource_init(void __iomem *base,
 static int __init samsung_pwm_alloc(struct device_node *np,
 				    const struct samsung_pwm_variant *variant)
 {
-	struct property *prop;
-	const __be32 *cur;
 	u32 val;
 	int i, ret;
 
@@ -427,7 +425,7 @@ static int __init samsung_pwm_alloc(struct device_node *np,
 	for (i = 0; i < SAMSUNG_PWM_NUM; ++i)
 		pwm.irq[i] = irq_of_parse_and_map(np, i);
 
-	of_property_for_each_u32(np, "samsung,pwm-outputs", prop, cur, val) {
+	of_property_for_each_u32(np, "samsung,pwm-outputs", val) {
 		if (val >= SAMSUNG_PWM_NUM) {
 			pr_warn("%s: invalid channel index in samsung,pwm-outputs property\n", __func__);
 			continue;
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 5710698..82b78e3 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -22,56 +22,42 @@ static const guid_t acpi_cxl_qtg_id_guid =
 	GUID_INIT(0xF365F9A6, 0xA7DE, 0x4071,
 		  0xA6, 0x6A, 0xB4, 0x0C, 0x0B, 0x4F, 0x8E, 0x52);
 
-/*
- * Find a targets entry (n) in the host bridge interleave list.
- * CXL Specification 3.0 Table 9-22
- */
-static int cxl_xor_calc_n(u64 hpa, struct cxl_cxims_data *cximsd, int iw,
-			  int ig)
-{
-	int i = 0, n = 0;
-	u8 eiw;
 
-	/* IW: 2,4,6,8,12,16 begin building 'n' using xormaps */
-	if (iw != 3) {
-		for (i = 0; i < cximsd->nr_maps; i++)
-			n |= (hweight64(hpa & cximsd->xormaps[i]) & 1) << i;
-	}
-	/* IW: 3,6,12 add a modulo calculation to 'n' */
-	if (!is_power_of_2(iw)) {
-		if (ways_to_eiw(iw, &eiw))
-			return -1;
-		hpa &= GENMASK_ULL(51, eiw + ig);
-		n |= do_div(hpa, 3) << i;
-	}
-	return n;
-}
-
-static struct cxl_dport *cxl_hb_xor(struct cxl_root_decoder *cxlrd, int pos)
+static u64 cxl_xor_hpa_to_spa(struct cxl_root_decoder *cxlrd, u64 hpa)
 {
 	struct cxl_cxims_data *cximsd = cxlrd->platform_data;
-	struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
-	struct cxl_decoder *cxld = &cxlsd->cxld;
-	int ig = cxld->interleave_granularity;
-	int iw = cxld->interleave_ways;
-	int n = 0;
-	u64 hpa;
+	int hbiw = cxlrd->cxlsd.nr_targets;
+	u64 val;
+	int pos;
 
-	if (dev_WARN_ONCE(&cxld->dev,
-			  cxld->interleave_ways != cxlsd->nr_targets,
-			  "misconfigured root decoder\n"))
-		return NULL;
+	/* No xormaps for host bridge interleave ways of 1 or 3 */
+	if (hbiw == 1 || hbiw == 3)
+		return hpa;
 
-	hpa = cxlrd->res->start + pos * ig;
+	/*
+	 * For root decoders using xormaps (hbiw: 2,4,6,8,12,16) restore
+	 * the position bit to its value before the xormap was applied at
+	 * HPA->DPA translation.
+	 *
+	 * pos is the lowest set bit in an XORMAP
+	 * val is the XORALLBITS(HPA & XORMAP)
+	 *
+	 * XORALLBITS: The CXL spec (3.1 Table 9-22) defines XORALLBITS
+	 * as an operation that outputs a single bit by XORing all the
+	 * bits in the input (hpa & xormap). Implement XORALLBITS using
+	 * hweight64(). If the hamming weight is even the XOR of those
+	 * bits results in val==0, if odd the XOR result is val==1.
+	 */
 
-	/* Entry (n) is 0 for no interleave (iw == 1) */
-	if (iw != 1)
-		n = cxl_xor_calc_n(hpa, cximsd, iw, ig);
+	for (int i = 0; i < cximsd->nr_maps; i++) {
+		if (!cximsd->xormaps[i])
+			continue;
+		pos = __ffs(cximsd->xormaps[i]);
+		val = (hweight64(hpa & cximsd->xormaps[i]) & 1);
+		hpa = (hpa & ~(1ULL << pos)) | (val << pos);
+	}
 
-	if (n < 0)
-		return NULL;
-
-	return cxlrd->cxlsd.target[n];
+	return hpa;
 }
 
 struct cxl_cxims_context {
@@ -361,7 +347,6 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	struct cxl_port *root_port = ctx->root_port;
 	struct cxl_cxims_context cxims_ctx;
 	struct device *dev = ctx->dev;
-	cxl_calc_hb_fn cxl_calc_hb;
 	struct cxl_decoder *cxld;
 	unsigned int ways, i, ig;
 	int rc;
@@ -389,13 +374,9 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	if (rc)
 		return rc;
 
-	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_MODULO)
-		cxl_calc_hb = cxl_hb_modulo;
-	else
-		cxl_calc_hb = cxl_hb_xor;
-
 	struct cxl_root_decoder *cxlrd __free(put_cxlrd) =
-		cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb);
+		cxl_root_decoder_alloc(root_port, ways);
+
 	if (IS_ERR(cxlrd))
 		return PTR_ERR(cxlrd);
 
@@ -434,6 +415,9 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 
 	cxlrd->qos_class = cfmws->qtg_id;
 
+	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR)
+		cxlrd->hpa_to_spa = cxl_xor_hpa_to_spa;
+
 	rc = cxl_decoder_add(cxld, target_map);
 	if (rc)
 		return rc;
@@ -482,6 +466,8 @@ struct cxl_chbs_context {
 	unsigned long long uid;
 	resource_size_t base;
 	u32 cxl_version;
+	int nr_versions;
+	u32 saved_version;
 };
 
 static int cxl_get_chbs_iter(union acpi_subtable_headers *header, void *arg,
@@ -490,22 +476,31 @@ static int cxl_get_chbs_iter(union acpi_subtable_headers *header, void *arg,
 	struct cxl_chbs_context *ctx = arg;
 	struct acpi_cedt_chbs *chbs;
 
-	if (ctx->base != CXL_RESOURCE_NONE)
-		return 0;
-
 	chbs = (struct acpi_cedt_chbs *) header;
 
-	if (ctx->uid != chbs->uid)
-		return 0;
-
-	ctx->cxl_version = chbs->cxl_version;
-	if (!chbs->base)
-		return 0;
-
 	if (chbs->cxl_version == ACPI_CEDT_CHBS_VERSION_CXL11 &&
 	    chbs->length != CXL_RCRB_SIZE)
 		return 0;
 
+	if (!chbs->base)
+		return 0;
+
+	if (ctx->saved_version != chbs->cxl_version) {
+		/*
+		 * cxl_version cannot be overwritten before the next two
+		 * checks, then use saved_version
+		 */
+		ctx->saved_version = chbs->cxl_version;
+		ctx->nr_versions++;
+	}
+
+	if (ctx->base != CXL_RESOURCE_NONE)
+		return 0;
+
+	if (ctx->uid != chbs->uid)
+		return 0;
+
+	ctx->cxl_version = chbs->cxl_version;
 	ctx->base = chbs->base;
 
 	return 0;
@@ -529,10 +524,19 @@ static int cxl_get_chbs(struct device *dev, struct acpi_device *hb,
 		.uid = uid,
 		.base = CXL_RESOURCE_NONE,
 		.cxl_version = UINT_MAX,
+		.saved_version = UINT_MAX,
 	};
 
 	acpi_table_parse_cedt(ACPI_CEDT_TYPE_CHBS, cxl_get_chbs_iter, ctx);
 
+	if (ctx->nr_versions > 1) {
+		/*
+		 * Disclaim eRCD support given some component register may
+		 * only be found via CHBCR
+		 */
+		dev_info(dev, "Unsupported platform config, mixed Virtual Host and Restricted CXL Host hierarchy.");
+	}
+
 	return 0;
 }
 
@@ -921,6 +925,7 @@ static void __exit cxl_acpi_exit(void)
 /* load before dax_hmem sees 'Soft Reserved' CXL ranges */
 subsys_initcall(cxl_acpi_init);
 module_exit(cxl_acpi_exit);
+MODULE_DESCRIPTION("CXL ACPI: Platform Support");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
 MODULE_IMPORT_NS(ACPI);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 6253944..72a506c 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -28,12 +28,12 @@ int cxl_region_init(void);
 void cxl_region_exit(void);
 int cxl_get_poison_by_endpoint(struct cxl_port *port);
 struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa);
-u64 cxl_trace_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
-		  u64 dpa);
+u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
+		   u64 dpa);
 
 #else
-static inline u64
-cxl_trace_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, u64 dpa)
+static inline u64 cxl_dpa_to_hpa(struct cxl_region *cxlr,
+				 const struct cxl_memdev *cxlmd, u64 dpa)
 {
 	return ULLONG_MAX;
 }
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 2626f3f..e5cdeaf 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -875,10 +875,10 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 		guard(rwsem_read)(&cxl_region_rwsem);
 		guard(rwsem_read)(&cxl_dpa_rwsem);
 
-		dpa = le64_to_cpu(evt->common.phys_addr) & CXL_DPA_MASK;
+		dpa = le64_to_cpu(evt->media_hdr.phys_addr) & CXL_DPA_MASK;
 		cxlr = cxl_dpa_to_region(cxlmd, dpa);
 		if (cxlr)
-			hpa = cxl_trace_hpa(cxlr, cxlmd, dpa);
+			hpa = cxl_dpa_to_hpa(cxlr, cxlmd, dpa);
 
 		if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
 			trace_cxl_general_media(cxlmd, type, cxlr, hpa,
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 8567dd1..a663e75 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -338,10 +338,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 	if (rc)
 		return rc;
 
-	rc = pci_read_config_word(pdev, d + CXL_DVSEC_CTRL_OFFSET, &ctrl);
-	if (rc)
-		return rc;
-
 	if (!(cap & CXL_DVSEC_MEM_CAPABLE)) {
 		dev_dbg(dev, "Not MEM Capable\n");
 		return -ENXIO;
@@ -368,6 +364,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 	 * disabled, and they will remain moot after the HDM Decoder
 	 * capability is enabled.
 	 */
+	rc = pci_read_config_word(pdev, d + CXL_DVSEC_CTRL_OFFSET, &ctrl);
+	if (rc)
+		return rc;
+
 	info->mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl);
 	if (!info->mem_enabled)
 		return 0;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 887ed6e3..1d5007e 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1733,21 +1733,6 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 	return 0;
 }
 
-struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos)
-{
-	struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
-	struct cxl_decoder *cxld = &cxlsd->cxld;
-	int iw;
-
-	iw = cxld->interleave_ways;
-	if (dev_WARN_ONCE(&cxld->dev, iw != cxlsd->nr_targets,
-			  "misconfigured root decoder\n"))
-		return NULL;
-
-	return cxlrd->cxlsd.target[pos % iw];
-}
-EXPORT_SYMBOL_NS_GPL(cxl_hb_modulo, CXL);
-
 static struct lock_class_key cxl_decoder_key;
 
 /**
@@ -1807,7 +1792,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port,
  * cxl_root_decoder_alloc - Allocate a root level decoder
  * @port: owning CXL root of this decoder
  * @nr_targets: static number of downstream targets
- * @calc_hb: which host bridge covers the n'th position by granularity
  *
  * Return: A new cxl decoder to be registered by cxl_decoder_add(). A
  * 'CXL root' decoder is one that decodes from a top-level / static platform
@@ -1815,8 +1799,7 @@ static int cxl_switch_decoder_init(struct cxl_port *port,
  * topology.
  */
 struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
-						unsigned int nr_targets,
-						cxl_calc_hb_fn calc_hb)
+						unsigned int nr_targets)
 {
 	struct cxl_root_decoder *cxlrd;
 	struct cxl_switch_decoder *cxlsd;
@@ -1838,7 +1821,6 @@ struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 		return ERR_PTR(rc);
 	}
 
-	cxlrd->calc_hb = calc_hb;
 	mutex_init(&cxlrd->range_lock);
 
 	cxld = &cxlsd->cxld;
@@ -2082,7 +2064,7 @@ static int cxl_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
 			      cxl_device_id(dev));
 }
 
-static int cxl_bus_match(struct device *dev, struct device_driver *drv)
+static int cxl_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	return cxl_device_id(dev) == to_cxl_drv(drv)->id;
 }
@@ -2356,5 +2338,6 @@ static void cxl_core_exit(void)
 
 subsys_initcall(cxl_core_init);
 module_exit(cxl_core_exit);
+MODULE_DESCRIPTION("CXL: Core Compute Express Link support");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 538ebd5..21ad5f2 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -9,6 +9,7 @@
 #include <linux/uuid.h>
 #include <linux/sort.h>
 #include <linux/idr.h>
+#include <linux/memory-tiers.h>
 #include <cxlmem.h>
 #include <cxl.h>
 #include "core.h"
@@ -1632,10 +1633,13 @@ static int cxl_region_attach_position(struct cxl_region *cxlr,
 				      const struct cxl_dport *dport, int pos)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
+	struct cxl_decoder *cxld = &cxlsd->cxld;
+	int iw = cxld->interleave_ways;
 	struct cxl_port *iter;
 	int rc;
 
-	if (cxlrd->calc_hb(cxlrd, pos) != dport) {
+	if (dport != cxlrd->cxlsd.target[pos % iw]) {
 		dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n",
 			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
 			dev_name(&cxlrd->cxlsd.cxld.dev));
@@ -2310,6 +2314,7 @@ static void unregister_region(void *_cxlr)
 	int i;
 
 	unregister_memory_notifier(&cxlr->memory_notifier);
+	unregister_mt_adistance_algorithm(&cxlr->adist_notifier);
 	device_del(&cxlr->dev);
 
 	/*
@@ -2386,14 +2391,23 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
 	return true;
 }
 
+static int cxl_region_nid(struct cxl_region *cxlr)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	struct resource *res;
+
+	guard(rwsem_read)(&cxl_region_rwsem);
+	res = p->res;
+	if (!res)
+		return NUMA_NO_NODE;
+	return phys_to_target_node(res->start);
+}
+
 static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 					  unsigned long action, void *arg)
 {
 	struct cxl_region *cxlr = container_of(nb, struct cxl_region,
 					       memory_notifier);
-	struct cxl_region_params *p = &cxlr->params;
-	struct cxl_endpoint_decoder *cxled = p->targets[0];
-	struct cxl_decoder *cxld = &cxled->cxld;
 	struct memory_notify *mnb = arg;
 	int nid = mnb->status_change_nid;
 	int region_nid;
@@ -2401,7 +2415,7 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 	if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
 		return NOTIFY_DONE;
 
-	region_nid = phys_to_target_node(cxld->hpa_range.start);
+	region_nid = cxl_region_nid(cxlr);
 	if (nid != region_nid)
 		return NOTIFY_DONE;
 
@@ -2411,6 +2425,27 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static int cxl_region_calculate_adistance(struct notifier_block *nb,
+					  unsigned long nid, void *data)
+{
+	struct cxl_region *cxlr = container_of(nb, struct cxl_region,
+					       adist_notifier);
+	struct access_coordinate *perf;
+	int *adist = data;
+	int region_nid;
+
+	region_nid = cxl_region_nid(cxlr);
+	if (nid != region_nid)
+		return NOTIFY_OK;
+
+	perf = &cxlr->coord[ACCESS_COORDINATE_CPU];
+
+	if (mt_perf_to_adistance(perf, adist))
+		return NOTIFY_OK;
+
+	return NOTIFY_STOP;
+}
+
 /**
  * devm_cxl_add_region - Adds a region to a decoder
  * @cxlrd: root decoder
@@ -2453,6 +2488,10 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	cxlr->memory_notifier.priority = CXL_CALLBACK_PRI;
 	register_memory_notifier(&cxlr->memory_notifier);
 
+	cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance;
+	cxlr->adist_notifier.priority = 100;
+	register_mt_adistance_algorithm(&cxlr->adist_notifier);
+
 	rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr);
 	if (rc)
 		return ERR_PTR(rc);
@@ -2816,20 +2855,13 @@ struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa)
 	return ctx.cxlr;
 }
 
-static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos)
+static bool cxl_is_hpa_in_chunk(u64 hpa, struct cxl_region *cxlr, int pos)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	int gran = p->interleave_granularity;
 	int ways = p->interleave_ways;
 	u64 offset;
 
-	/* Is the hpa within this region at all */
-	if (hpa < p->res->start || hpa > p->res->end) {
-		dev_dbg(&cxlr->dev,
-			"Addr trans fail: hpa 0x%llx not in region\n", hpa);
-		return false;
-	}
-
 	/* Is the hpa in an expected chunk for its pos(-ition) */
 	offset = hpa - p->res->start;
 	offset = do_div(offset, gran * ways);
@@ -2842,15 +2874,26 @@ static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos)
 	return false;
 }
 
-static u64 cxl_dpa_to_hpa(u64 dpa,  struct cxl_region *cxlr,
-			  struct cxl_endpoint_decoder *cxled)
+u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
+		   u64 dpa)
 {
+	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	u64 dpa_offset, hpa_offset, bits_upper, mask_upper, hpa;
 	struct cxl_region_params *p = &cxlr->params;
-	int pos = cxled->pos;
+	struct cxl_endpoint_decoder *cxled = NULL;
 	u16 eig = 0;
 	u8 eiw = 0;
+	int pos;
 
+	for (int i = 0; i < p->nr_targets; i++) {
+		cxled = p->targets[i];
+		if (cxlmd == cxled_to_memdev(cxled))
+			break;
+	}
+	if (!cxled || cxlmd != cxled_to_memdev(cxled))
+		return ULLONG_MAX;
+
+	pos = cxled->pos;
 	ways_to_eiw(p->interleave_ways, &eiw);
 	granularity_to_eig(p->interleave_granularity, &eig);
 
@@ -2884,29 +2927,23 @@ static u64 cxl_dpa_to_hpa(u64 dpa,  struct cxl_region *cxlr,
 	/* Apply the hpa_offset to the region base address */
 	hpa = hpa_offset + p->res->start;
 
-	if (!cxl_is_hpa_in_range(hpa, cxlr, cxled->pos))
+	/* Root decoder translation overrides typical modulo decode */
+	if (cxlrd->hpa_to_spa)
+		hpa = cxlrd->hpa_to_spa(cxlrd, hpa);
+
+	if (hpa < p->res->start || hpa > p->res->end) {
+		dev_dbg(&cxlr->dev,
+			"Addr trans fail: hpa 0x%llx not in region\n", hpa);
+		return ULLONG_MAX;
+	}
+
+	/* Simple chunk check, by pos & gran, only applies to modulo decodes */
+	if (!cxlrd->hpa_to_spa && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos)))
 		return ULLONG_MAX;
 
 	return hpa;
 }
 
-u64 cxl_trace_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
-		  u64 dpa)
-{
-	struct cxl_region_params *p = &cxlr->params;
-	struct cxl_endpoint_decoder *cxled = NULL;
-
-	for (int i = 0; i <  p->nr_targets; i++) {
-		cxled = p->targets[i];
-		if (cxlmd == cxled_to_memdev(cxled))
-			break;
-	}
-	if (!cxled || cxlmd != cxled_to_memdev(cxled))
-		return ULLONG_MAX;
-
-	return cxl_dpa_to_hpa(dpa, cxlr, cxled);
-}
-
 static struct lock_class_key cxl_pmem_region_key;
 
 static int cxl_pmem_region_alloc(struct cxl_region *cxlr)
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index ee5cd4e..9167cfb 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -340,23 +340,23 @@ TRACE_EVENT(cxl_general_media,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->media_hdr.hdr);
 		__entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
 
 		/* General Media */
-		__entry->dpa = le64_to_cpu(rec->phys_addr);
+		__entry->dpa = le64_to_cpu(rec->media_hdr.phys_addr);
 		__entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK;
 		/* Mask after flags have been parsed */
 		__entry->dpa &= CXL_DPA_MASK;
-		__entry->descriptor = rec->descriptor;
-		__entry->type = rec->type;
-		__entry->transaction_type = rec->transaction_type;
-		__entry->channel = rec->channel;
-		__entry->rank = rec->rank;
+		__entry->descriptor = rec->media_hdr.descriptor;
+		__entry->type = rec->media_hdr.type;
+		__entry->transaction_type = rec->media_hdr.transaction_type;
+		__entry->channel = rec->media_hdr.channel;
+		__entry->rank = rec->media_hdr.rank;
 		__entry->device = get_unaligned_le24(rec->device);
 		memcpy(__entry->comp_id, &rec->component_id,
 			CXL_EVENT_GEN_MED_COMP_ID_SIZE);
-		__entry->validity_flags = get_unaligned_le16(&rec->validity_flags);
+		__entry->validity_flags = get_unaligned_le16(&rec->media_hdr.validity_flags);
 		__entry->hpa = hpa;
 		if (cxlr) {
 			__assign_str(region_name);
@@ -440,19 +440,19 @@ TRACE_EVENT(cxl_dram,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->media_hdr.hdr);
 		__entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
 
 		/* DRAM */
-		__entry->dpa = le64_to_cpu(rec->phys_addr);
+		__entry->dpa = le64_to_cpu(rec->media_hdr.phys_addr);
 		__entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK;
 		__entry->dpa &= CXL_DPA_MASK;
-		__entry->descriptor = rec->descriptor;
-		__entry->type = rec->type;
-		__entry->transaction_type = rec->transaction_type;
-		__entry->validity_flags = get_unaligned_le16(rec->validity_flags);
-		__entry->channel = rec->channel;
-		__entry->rank = rec->rank;
+		__entry->descriptor = rec->media_hdr.descriptor;
+		__entry->type = rec->media_hdr.type;
+		__entry->transaction_type = rec->media_hdr.transaction_type;
+		__entry->validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);
+		__entry->channel = rec->media_hdr.channel;
+		__entry->rank = rec->media_hdr.rank;
 		__entry->nibble_mask = get_unaligned_le24(rec->nibble_mask);
 		__entry->bank_group = rec->bank_group;
 		__entry->bank = rec->bank;
@@ -704,8 +704,8 @@ TRACE_EVENT(cxl_poison,
 		if (cxlr) {
 			__assign_str(region);
 			memcpy(__entry->uuid, &cxlr->params.uuid, 16);
-			__entry->hpa = cxl_trace_hpa(cxlr, cxlmd,
-						     __entry->dpa);
+			__entry->hpa = cxl_dpa_to_hpa(cxlr, cxlmd,
+						      __entry->dpa);
 		} else {
 			__assign_str(region);
 			memset(__entry->uuid, 0, 16);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index a6613a6..9afb407 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -434,14 +434,13 @@ struct cxl_switch_decoder {
 };
 
 struct cxl_root_decoder;
-typedef struct cxl_dport *(*cxl_calc_hb_fn)(struct cxl_root_decoder *cxlrd,
-					    int pos);
+typedef u64 (*cxl_hpa_to_spa_fn)(struct cxl_root_decoder *cxlrd, u64 hpa);
 
 /**
  * struct cxl_root_decoder - Static platform CXL address decoder
  * @res: host / parent resource for region allocations
  * @region_id: region id for next region provisioning event
- * @calc_hb: which host bridge covers the n'th position by granularity
+ * @hpa_to_spa: translate CXL host-physical-address to Platform system-physical-address
  * @platform_data: platform specific configuration data
  * @range_lock: sync region autodiscovery by address range
  * @qos_class: QoS performance class cookie
@@ -450,7 +449,7 @@ typedef struct cxl_dport *(*cxl_calc_hb_fn)(struct cxl_root_decoder *cxlrd,
 struct cxl_root_decoder {
 	struct resource *res;
 	atomic_t region_id;
-	cxl_calc_hb_fn calc_hb;
+	cxl_hpa_to_spa_fn hpa_to_spa;
 	void *platform_data;
 	struct mutex range_lock;
 	int qos_class;
@@ -524,6 +523,7 @@ struct cxl_region_params {
  * @params: active + config params for the region
  * @coord: QoS access coordinates for the region
  * @memory_notifier: notifier for setting the access coordinates to node
+ * @adist_notifier: notifier for calculating the abstract distance of node
  */
 struct cxl_region {
 	struct device dev;
@@ -536,6 +536,7 @@ struct cxl_region {
 	struct cxl_region_params params;
 	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	struct notifier_block memory_notifier;
+	struct notifier_block adist_notifier;
 };
 
 struct cxl_nvdimm_bridge {
@@ -774,9 +775,7 @@ bool is_root_decoder(struct device *dev);
 bool is_switch_decoder(struct device *dev);
 bool is_endpoint_decoder(struct device *dev);
 struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
-						unsigned int nr_targets,
-						cxl_calc_hb_fn calc_hb);
-struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos);
+						unsigned int nr_targets);
 struct cxl_switch_decoder *cxl_switch_decoder_alloc(struct cxl_port *port,
 						    unsigned int nr_targets);
 int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map);
@@ -825,10 +824,7 @@ struct cxl_driver {
 	int id;
 };
 
-static inline struct cxl_driver *to_cxl_drv(struct device_driver *drv)
-{
-	return container_of(drv, struct cxl_driver, drv);
-}
+#define to_cxl_drv(__drv)	container_of_const(__drv, struct cxl_driver, drv)
 
 int __cxl_driver_register(struct cxl_driver *cxl_drv, struct module *owner,
 			  const char *modname);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index af8169c..afb53d0 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -161,7 +161,7 @@ struct cxl_mbox_cmd {
 	C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"),		\
 	C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"),     \
 	C(PADDR, -EFAULT, "physical address specified is invalid"),		\
-	C(POISONLMT, -ENXIO, "poison injection limit has been reached"),        \
+	C(POISONLMT, -EBUSY, "poison injection limit has been reached"),        \
 	C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"),		\
 	C(ABORT, -ENXIO, "background cmd was aborted by device"),               \
 	C(SECURITY, -ENXIO, "not valid in the current security state"),         \
@@ -563,7 +563,7 @@ enum cxl_opcode {
 		  0x3b, 0x3f, 0x17)
 
 #define DEFINE_CXL_VENDOR_DEBUG_UUID                                           \
-	UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19,     \
+	UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19,     \
 		  0x40, 0x3d, 0x86)
 
 struct cxl_mbox_get_supported_logs {
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 2f1b49b..7de232e 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -253,6 +253,7 @@ static struct cxl_driver cxl_mem_driver = {
 
 module_cxl_driver(cxl_mem_driver);
 
+MODULE_DESCRIPTION("CXL: Memory Expansion");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
 MODULE_ALIAS_CXL(CXL_DEVICE_MEMORY_EXPANDER);
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index e53646e..4be35dc 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1066,5 +1066,6 @@ static void __exit cxl_pci_driver_exit(void)
 
 module_init(cxl_pci_driver_init);
 module_exit(cxl_pci_driver_exit);
+MODULE_DESCRIPTION("CXL: PCI manageability");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index 2ecdaee..4ef93da 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -453,6 +453,7 @@ static __exit void cxl_pmem_exit(void)
 	cxl_driver_unregister(&cxl_nvdimm_bridge_driver);
 }
 
+MODULE_DESCRIPTION("CXL PMEM: Persistent Memory Support");
 MODULE_LICENSE("GPL v2");
 module_init(cxl_pmem_init);
 module_exit(cxl_pmem_exit);
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 97c2156..d7d5d98 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -209,6 +209,7 @@ static struct cxl_driver cxl_port_driver = {
 };
 
 module_cxl_driver(cxl_port_driver);
+MODULE_DESCRIPTION("CXL: Port enumeration and services");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
 MODULE_ALIAS_CXL(CXL_DEVICE_PORT);
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 3ef9550..fde29e0 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -39,12 +39,9 @@ static int dax_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "MODALIAS=" DAX_DEVICE_MODALIAS_FMT, 0);
 }
 
-static struct dax_device_driver *to_dax_drv(struct device_driver *drv)
-{
-	return container_of(drv, struct dax_device_driver, drv);
-}
+#define to_dax_drv(__drv)	container_of_const(__drv, struct dax_device_driver, drv)
 
-static struct dax_id *__dax_match_id(struct dax_device_driver *dax_drv,
+static struct dax_id *__dax_match_id(const struct dax_device_driver *dax_drv,
 		const char *dev_name)
 {
 	struct dax_id *dax_id;
@@ -57,7 +54,7 @@ static struct dax_id *__dax_match_id(struct dax_device_driver *dax_drv,
 	return NULL;
 }
 
-static int dax_match_id(struct dax_device_driver *dax_drv, struct device *dev)
+static int dax_match_id(const struct dax_device_driver *dax_drv, struct device *dev)
 {
 	int match;
 
@@ -68,7 +65,7 @@ static int dax_match_id(struct dax_device_driver *dax_drv, struct device *dev)
 	return match;
 }
 
-static int dax_match_type(struct dax_device_driver *dax_drv, struct device *dev)
+static int dax_match_type(const struct dax_device_driver *dax_drv, struct device *dev)
 {
 	enum dax_driver_type type = DAXDRV_DEVICE_TYPE;
 	struct dev_dax *dev_dax = to_dev_dax(dev);
@@ -156,7 +153,7 @@ static struct attribute *dax_drv_attrs[] = {
 };
 ATTRIBUTE_GROUPS(dax_drv);
 
-static int dax_bus_match(struct device *dev, struct device_driver *drv);
+static int dax_bus_match(struct device *dev, const struct device_driver *drv);
 
 /*
  * Static dax regions are regions created by an external subsystem
@@ -250,9 +247,9 @@ static const struct bus_type dax_bus_type = {
 	.drv_groups = dax_drv_groups,
 };
 
-static int dax_bus_match(struct device *dev, struct device_driver *drv)
+static int dax_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct dax_device_driver *dax_drv = to_dax_drv(drv);
+	const struct dax_device_driver *dax_drv = to_dax_drv(drv);
 
 	if (dax_match_id(dax_drv, dev))
 		return 1;
diff --git a/drivers/dca/dca-sysfs.c b/drivers/dca/dca-sysfs.c
index fcc83ed..b915c2b 100644
--- a/drivers/dca/dca-sysfs.c
+++ b/drivers/dca/dca-sysfs.c
@@ -13,7 +13,9 @@
 #include <linux/gfp.h>
 #include <linux/export.h>
 
-static struct class *dca_class;
+static const struct class dca_class = {
+	.name = "dca",
+};
 static struct idr dca_idr;
 static spinlock_t dca_idr_lock;
 
@@ -22,14 +24,14 @@ int dca_sysfs_add_req(struct dca_provider *dca, struct device *dev, int slot)
 	struct device *cd;
 	static int req_count;
 
-	cd = device_create(dca_class, dca->cd, MKDEV(0, slot + 1), NULL,
+	cd = device_create(&dca_class, dca->cd, MKDEV(0, slot + 1), NULL,
 			   "requester%d", req_count++);
 	return PTR_ERR_OR_ZERO(cd);
 }
 
 void dca_sysfs_remove_req(struct dca_provider *dca, int slot)
 {
-	device_destroy(dca_class, MKDEV(0, slot + 1));
+	device_destroy(&dca_class, MKDEV(0, slot + 1));
 }
 
 int dca_sysfs_add_provider(struct dca_provider *dca, struct device *dev)
@@ -49,7 +51,7 @@ int dca_sysfs_add_provider(struct dca_provider *dca, struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	cd = device_create(dca_class, dev, MKDEV(0, 0), NULL, "dca%d", dca->id);
+	cd = device_create(&dca_class, dev, MKDEV(0, 0), NULL, "dca%d", dca->id);
 	if (IS_ERR(cd)) {
 		spin_lock(&dca_idr_lock);
 		idr_remove(&dca_idr, dca->id);
@@ -71,20 +73,22 @@ void dca_sysfs_remove_provider(struct dca_provider *dca)
 
 int __init dca_sysfs_init(void)
 {
+	int err;
+
 	idr_init(&dca_idr);
 	spin_lock_init(&dca_idr_lock);
 
-	dca_class = class_create("dca");
-	if (IS_ERR(dca_class)) {
+	err = class_register(&dca_class);
+	if (err) {
 		idr_destroy(&dca_idr);
-		return PTR_ERR(dca_class);
+		return err;
 	}
 	return 0;
 }
 
 void __exit dca_sysfs_exit(void)
 {
-	class_destroy(dca_class);
+	class_unregister(&dca_class);
 	idr_destroy(&dca_idr);
 }
 
diff --git a/drivers/dio/dio-driver.c b/drivers/dio/dio-driver.c
index 2d9fa60..12fa2d2 100644
--- a/drivers/dio/dio-driver.c
+++ b/drivers/dio/dio-driver.c
@@ -110,10 +110,10 @@ void dio_unregister_driver(struct dio_driver *drv)
  *  and 0 if there is no match.
  */
 
-static int dio_bus_match(struct device *dev, struct device_driver *drv)
+static int dio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct dio_dev *d = to_dio_dev(dev);
-	struct dio_driver *dio_drv = to_dio_driver(drv);
+	const struct dio_driver *dio_drv = to_dio_driver(drv);
 	const struct dio_device_id *ids = dio_drv->id_table;
 
 	if (!ids)
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 9fc99cf..cc0a62c 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -568,38 +568,6 @@
 	  Say Y here if you have such a chipset.
 	  If unsure, say N.
 
-config STM32_DMA
-	bool "STMicroelectronics STM32 DMA support"
-	depends on ARCH_STM32 || COMPILE_TEST
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Enable support for the on-chip DMA controller on STMicroelectronics
-	  STM32 MCUs.
-	  If you have a board based on such a MCU and wish to use DMA say Y
-	  here.
-
-config STM32_DMAMUX
-	bool "STMicroelectronics STM32 dma multiplexer support"
-	depends on STM32_DMA || COMPILE_TEST
-	help
-	  Enable support for the on-chip DMA multiplexer on STMicroelectronics
-	  STM32 MCUs.
-	  If you have a board based on such a MCU and wish to use DMAMUX say Y
-	  here.
-
-config STM32_MDMA
-	bool "STMicroelectronics STM32 master dma support"
-	depends on ARCH_STM32 || COMPILE_TEST
-	depends on OF
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Enable support for the on-chip MDMA controller on STMicroelectronics
-	  STM32 platforms.
-	  If you have a board based on STM32 SoC and wish to use the master DMA
-	  say Y here.
-
 config SPRD_DMA
 	tristate "Spreadtrum DMA support"
 	depends on ARCH_SPRD || COMPILE_TEST
@@ -772,6 +740,8 @@
 
 source "drivers/dma/lgm/Kconfig"
 
+source "drivers/dma/stm32/Kconfig"
+
 # clients
 comment "DMA Clients"
 	depends on DMA_ENGINE
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 802ca91..374ea98 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -70,9 +70,6 @@
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SF_PDMA) += sf-pdma/
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
-obj-$(CONFIG_STM32_DMA) += stm32-dma.o
-obj-$(CONFIG_STM32_DMAMUX) += stm32-dmamux.o
-obj-$(CONFIG_STM32_MDMA) += stm32-mdma.o
 obj-$(CONFIG_SPRD_DMA) += sprd-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA186_GPC_DMA) += tegra186-gpc-dma.o
@@ -88,5 +85,6 @@
 
 obj-y += mediatek/
 obj-y += qcom/
+obj-y += stm32/
 obj-y += ti/
 obj-y += xilinx/
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index a8e3615..0968176 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -233,7 +233,7 @@ static void msgdma_free_descriptor(struct msgdma_device *mdev,
 	struct msgdma_sw_desc *child, *next;
 
 	mdev->desc_free_cnt++;
-	list_add_tail(&desc->node, &mdev->free_list);
+	list_move_tail(&desc->node, &mdev->free_list);
 	list_for_each_entry_safe(child, next, &desc->tx_list, node) {
 		mdev->desc_free_cnt++;
 		list_move_tail(&child->node, &mdev->free_list);
@@ -583,22 +583,25 @@ static void msgdma_issue_pending(struct dma_chan *chan)
 static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev)
 {
 	struct msgdma_sw_desc *desc, *next;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&mdev->lock, irqflags);
 
 	list_for_each_entry_safe(desc, next, &mdev->done_list, node) {
 		struct dmaengine_desc_callback cb;
 
-		list_del(&desc->node);
-
 		dmaengine_desc_get_callback(&desc->async_tx, &cb);
 		if (dmaengine_desc_callback_valid(&cb)) {
-			spin_unlock(&mdev->lock);
+			spin_unlock_irqrestore(&mdev->lock, irqflags);
 			dmaengine_desc_callback_invoke(&cb, NULL);
-			spin_lock(&mdev->lock);
+			spin_lock_irqsave(&mdev->lock, irqflags);
 		}
 
 		/* Run any dependencies, then free the descriptor */
 		msgdma_free_descriptor(mdev, desc);
 	}
+
+	spin_unlock_irqrestore(&mdev->lock, irqflags);
 }
 
 /**
@@ -713,10 +716,11 @@ static void msgdma_tasklet(struct tasklet_struct *t)
 		}
 
 		msgdma_complete_descriptor(mdev);
-		msgdma_chan_desc_cleanup(mdev);
 	}
 
 	spin_unlock_irqrestore(&mdev->lock, flags);
+
+	msgdma_chan_desc_cleanup(mdev);
 }
 
 /**
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 491b222..c380a4d 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1037,7 +1037,8 @@ static int get_dma_id(struct dma_device *device)
 }
 
 static int __dma_async_device_channel_register(struct dma_device *device,
-					       struct dma_chan *chan)
+					       struct dma_chan *chan,
+					       const char *name)
 {
 	int rc;
 
@@ -1066,8 +1067,10 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	chan->dev->device.parent = device->dev;
 	chan->dev->chan = chan;
 	chan->dev->dev_id = device->dev_id;
-	dev_set_name(&chan->dev->device, "dma%dchan%d",
-		     device->dev_id, chan->chan_id);
+	if (!name)
+		dev_set_name(&chan->dev->device, "dma%dchan%d", device->dev_id, chan->chan_id);
+	else
+		dev_set_name(&chan->dev->device, name);
 	rc = device_register(&chan->dev->device);
 	if (rc)
 		goto err_out_ida;
@@ -1087,11 +1090,12 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 }
 
 int dma_async_device_channel_register(struct dma_device *device,
-				      struct dma_chan *chan)
+				      struct dma_chan *chan,
+				      const char *name)
 {
 	int rc;
 
-	rc = __dma_async_device_channel_register(device, chan);
+	rc = __dma_async_device_channel_register(device, chan, name);
 	if (rc < 0)
 		return rc;
 
@@ -1203,7 +1207,7 @@ int dma_async_device_register(struct dma_device *device)
 
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
-		rc = __dma_async_device_channel_register(device, chan);
+		rc = __dma_async_device_channel_register(device, chan, NULL);
 		if (rc < 0)
 			goto err_out;
 	}
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index a4f6088..1f201a54 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -1372,4 +1372,5 @@ static void __exit dmatest_exit(void)
 module_exit(dmatest_exit);
 
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
+MODULE_DESCRIPTION("DMA Engine test module");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/fsl-dpaa2-qdma/dpdmai.c b/drivers/dma/fsl-dpaa2-qdma/dpdmai.c
index 36897b4..b4323d24 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpdmai.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpdmai.c
@@ -367,4 +367,5 @@ int dpdmai_get_tx_queue(struct fsl_mc_io *mc_io, u32 cmd_flags,
 }
 EXPORT_SYMBOL_GPL(dpdmai_get_tx_queue);
 
+MODULE_DESCRIPTION("NXP DPAA2 QDMA driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 3af4307..b7f15ab 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -59,7 +59,6 @@ void fsl_edma_tx_chan_handler(struct fsl_edma_chan *fsl_chan)
 		vchan_cookie_complete(&fsl_chan->edesc->vdesc);
 		fsl_chan->edesc = NULL;
 		fsl_chan->status = DMA_COMPLETE;
-		fsl_chan->idle = true;
 	} else {
 		vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
 	}
@@ -239,7 +238,7 @@ int fsl_edma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 	fsl_edma_disable_request(fsl_chan);
 	fsl_chan->edesc = NULL;
-	fsl_chan->idle = true;
+	fsl_chan->status = DMA_COMPLETE;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
@@ -259,7 +258,6 @@ int fsl_edma_pause(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_disable_request(fsl_chan);
 		fsl_chan->status = DMA_PAUSED;
-		fsl_chan->idle = true;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -274,7 +272,6 @@ int fsl_edma_resume(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_enable_request(fsl_chan);
 		fsl_chan->status = DMA_IN_PROGRESS;
-		fsl_chan->idle = false;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -758,6 +755,8 @@ struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan,
 	fsl_desc->iscyclic = false;
 
 	fsl_chan->is_sw = true;
+	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_MEM_REMOTE)
+		fsl_chan->is_remote = true;
 
 	/* To match with copy_align and max_seg_size so 1 tcd is enough */
 	fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[0].vtcd, dma_src, dma_dst,
@@ -780,7 +779,6 @@ void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
 	fsl_edma_enable_request(fsl_chan);
 	fsl_chan->status = DMA_IN_PROGRESS;
-	fsl_chan->idle = false;
 }
 
 void fsl_edma_issue_pending(struct dma_chan *chan)
@@ -805,6 +803,7 @@ void fsl_edma_issue_pending(struct dma_chan *chan)
 int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	int ret;
 
 	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK)
 		clk_prepare_enable(fsl_chan->clk);
@@ -813,6 +812,17 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 				fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_TCD64 ?
 				sizeof(struct fsl_edma_hw_tcd64) : sizeof(struct fsl_edma_hw_tcd),
 				32, 0);
+
+	if (fsl_chan->txirq) {
+		ret = request_irq(fsl_chan->txirq, fsl_chan->irq_handler, IRQF_SHARED,
+				 fsl_chan->chan_name, fsl_chan);
+
+		if (ret) {
+			dma_pool_destroy(fsl_chan->tcd_pool);
+			return ret;
+		}
+	}
+
 	return 0;
 }
 
@@ -832,11 +842,15 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	fsl_edma_unprep_slave_dma(fsl_chan);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 
+	if (fsl_chan->txirq)
+		free_irq(fsl_chan->txirq, fsl_chan);
+
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 	dma_pool_destroy(fsl_chan->tcd_pool);
 	fsl_chan->tcd_pool = NULL;
 	fsl_chan->is_sw = false;
 	fsl_chan->srcid = 0;
+	fsl_chan->is_remote = false;
 	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK)
 		clk_disable_unprepare(fsl_chan->clk);
 }
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index ac66222..ce37e1e 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -150,7 +150,6 @@ struct fsl_edma_chan {
 	struct virt_dma_chan		vchan;
 	enum dma_status			status;
 	enum fsl_edma_pm_state		pm_state;
-	bool				idle;
 	struct fsl_edma_engine		*edma;
 	struct fsl_edma_desc		*edesc;
 	struct dma_slave_config		cfg;
@@ -172,6 +171,7 @@ struct fsl_edma_chan {
 	int                             priority;
 	int				hw_chanid;
 	int				txirq;
+	irqreturn_t			(*irq_handler)(int irq, void *dev_id);
 	bool				is_rxchan;
 	bool				is_remote;
 	bool				is_multi_fifo;
@@ -194,6 +194,7 @@ struct fsl_edma_desc {
 #define FSL_EDMA_DRV_HAS_PD		BIT(5)
 #define FSL_EDMA_DRV_HAS_CHCLK		BIT(6)
 #define FSL_EDMA_DRV_HAS_CHMUX		BIT(7)
+#define FSL_EDMA_DRV_MEM_REMOTE		BIT(8)
 /* control and status register is in tcd address space, edma3 reg layout */
 #define FSL_EDMA_DRV_SPLIT_REG		BIT(9)
 #define FSL_EDMA_DRV_BUS_8BYTE		BIT(10)
@@ -455,7 +456,6 @@ static inline struct fsl_edma_desc *to_fsl_edma_desc(struct virt_dma_desc *vd)
 static inline void fsl_edma_err_chan_handler(struct fsl_edma_chan *fsl_chan)
 {
 	fsl_chan->status = DMA_ERROR;
-	fsl_chan->idle = true;
 }
 
 void fsl_edma_tx_chan_handler(struct fsl_edma_chan *fsl_chan);
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 391e4f1..c66185c 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -65,6 +65,13 @@ static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t fsl_edma2_tx_handler(int irq, void *devi_id)
+{
+	struct fsl_edma_chan *fsl_chan = devi_id;
+
+	return fsl_edma_tx_handler(irq, fsl_chan->edma);
+}
+
 static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_engine *fsl_edma = dev_id;
@@ -228,7 +235,6 @@ fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma
 
 static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
 {
-	int ret;
 	int i;
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
@@ -243,13 +249,7 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
 		if (fsl_chan->txirq < 0)
 			return  -EINVAL;
 
-		ret = devm_request_irq(&pdev->dev, fsl_chan->txirq,
-			fsl_edma3_tx_handler, IRQF_SHARED,
-			fsl_chan->chan_name, fsl_chan);
-		if (ret) {
-			dev_err(&pdev->dev, "Can't register chan%d's IRQ.\n", i);
-			return -EINVAL;
-		}
+		fsl_chan->irq_handler = fsl_edma3_tx_handler;
 	}
 
 	return 0;
@@ -278,19 +278,20 @@ fsl_edma2_irq_init(struct platform_device *pdev,
 	 */
 	for (i = 0; i < count; i++) {
 		irq = platform_get_irq(pdev, i);
+		ret = 0;
 		if (irq < 0)
 			return -ENXIO;
 
 		/* The last IRQ is for eDMA err */
-		if (i == count - 1)
+		if (i == count - 1) {
 			ret = devm_request_irq(&pdev->dev, irq,
 						fsl_edma_err_handler,
 						0, "eDMA2-ERR", fsl_edma);
-		else
-			ret = devm_request_irq(&pdev->dev, irq,
-						fsl_edma_tx_handler, 0,
-						fsl_edma->chans[i].chan_name,
-						fsl_edma);
+		} else {
+			fsl_edma->chans[i].txirq = irq;
+			fsl_edma->chans[i].irq_handler = fsl_edma2_tx_handler;
+		}
+
 		if (ret)
 			return ret;
 	}
@@ -342,7 +343,7 @@ static struct fsl_edma_drvdata imx7ulp_data = {
 };
 
 static struct fsl_edma_drvdata imx8qm_data = {
-	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3,
+	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE,
 	.chreg_space_sz = 0x10000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
@@ -543,7 +544,6 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		fsl_chan->edma = fsl_edma;
 		fsl_chan->pm_state = RUNNING;
 		fsl_chan->srcid = 0;
-		fsl_chan->idle = true;
 		fsl_chan->dma_dir = DMA_NONE;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 
@@ -668,7 +668,7 @@ static int fsl_edma_suspend_late(struct device *dev)
 			continue;
 		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 		/* Make sure chan is idle or will force disable. */
-		if (unlikely(!fsl_chan->idle)) {
+		if (unlikely(fsl_chan->status == DMA_IN_PROGRESS)) {
 			dev_warn(dev, "WARN: There is non-idle channel.");
 			fsl_edma_disable_request(fsl_chan);
 			fsl_edma_chan_mux(fsl_chan, 0, false);
diff --git a/drivers/dma/idxd/bus.c b/drivers/dma/idxd/bus.c
index b83b27e..e647a68 100644
--- a/drivers/dma/idxd/bus.c
+++ b/drivers/dma/idxd/bus.c
@@ -33,10 +33,10 @@ void idxd_driver_unregister(struct idxd_device_driver *idxd_drv)
 EXPORT_SYMBOL_GPL(idxd_driver_unregister);
 
 static int idxd_config_bus_match(struct device *dev,
-				 struct device_driver *drv)
+				 const struct device_driver *drv)
 {
-	struct idxd_device_driver *idxd_drv =
-		container_of(drv, struct idxd_device_driver, drv);
+	const struct idxd_device_driver *idxd_drv =
+		container_of_const(drv, struct idxd_device_driver, drv);
 	struct idxd_dev *idxd_dev = confdev_to_idxd_dev(dev);
 	int i = 0;
 
diff --git a/drivers/dma/idxd/compat.c b/drivers/dma/idxd/compat.c
index 5fd38d1..a4adb0c 100644
--- a/drivers/dma/idxd/compat.c
+++ b/drivers/dma/idxd/compat.c
@@ -7,7 +7,6 @@
 #include <linux/device/bus.h>
 #include "idxd.h"
 
-extern int device_driver_attach(struct device_driver *drv, struct device *dev);
 extern void device_driver_detach(struct device *dev);
 
 #define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)	\
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index cd835ea..dbecd69 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -269,7 +269,7 @@ static int idxd_register_dma_channel(struct idxd_wq *wq)
 		desc->txd.tx_submit = idxd_dma_tx_submit;
 	}
 
-	rc = dma_async_device_channel_register(dma, chan);
+	rc = dma_async_device_channel_register(dma, chan, NULL);
 	if (rc < 0) {
 		kfree(idxd_chan);
 		return rc;
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 385c488..21f6905 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -22,6 +22,7 @@
 #include "perfmon.h"
 
 MODULE_VERSION(IDXD_DRIVER_VERSION);
+MODULE_DESCRIPTION("Intel Data Streaming Accelerator and In-Memory Analytics Accelerator common driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Intel Corporation");
 MODULE_IMPORT_NS(IDXD);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 003e158..72299a0 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -2107,9 +2107,8 @@ static int sdma_get_firmware(struct sdma_engine *sdma,
 {
 	int ret;
 
-	ret = request_firmware_nowait(THIS_MODULE,
-			FW_ACTION_UEVENT, fw_name, sdma->dev,
-			GFP_KERNEL, sdma, sdma_load_firmware);
+	ret = firmware_request_nowait_nowarn(THIS_MODULE, fw_name, sdma->dev,
+					GFP_KERNEL, sdma, sdma_load_firmware);
 
 	return ret;
 }
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index e8f45a7..7b502b6 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -23,6 +23,7 @@
 #include "../dmaengine.h"
 
 MODULE_VERSION(IOAT_DMA_VERSION);
+MODULE_DESCRIPTION("Intel I/OAT DMA Linux driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel Corporation");
 
diff --git a/drivers/dma/mcf-edma-main.c b/drivers/dma/mcf-edma-main.c
index 78c606f..0c5862b 100644
--- a/drivers/dma/mcf-edma-main.c
+++ b/drivers/dma/mcf-edma-main.c
@@ -64,7 +64,6 @@ static irqreturn_t mcf_edma_err_handler(int irq, void *dev_id)
 			fsl_edma_disable_request(&mcf_edma->chans[ch]);
 			iowrite8(EDMA_CERR_CERR(ch), regs->cerr);
 			mcf_edma->chans[ch].status = DMA_ERROR;
-			mcf_edma->chans[ch].idle = true;
 		}
 	}
 
@@ -196,7 +195,6 @@ static int mcf_edma_probe(struct platform_device *pdev)
 
 		mcf_chan->edma = mcf_edma;
 		mcf_chan->srcid = i;
-		mcf_chan->idle = true;
 		mcf_chan->dma_dir = DMA_NONE;
 		mcf_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index c48d68c..66dc6d3 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -148,11 +148,6 @@ struct moxart_dmadev {
 	unsigned int			irq;
 };
 
-struct moxart_filter_data {
-	struct moxart_dmadev		*mdc;
-	struct of_phandle_args		*dma_spec;
-};
-
 static const unsigned int es_bytes[] = {
 	[MOXART_DMA_DATA_TYPE_S8] = 1,
 	[MOXART_DMA_DATA_TYPE_S16] = 2,
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 1c93864..e6ebd68 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -476,12 +476,6 @@ struct gpi_dev {
 	struct gpii *gpiis;
 };
 
-struct reg_info {
-	char *name;
-	u32 offset;
-	u32 val;
-};
-
 struct gchan {
 	struct virt_dma_chan vc;
 	u32 chid;
@@ -1197,7 +1191,6 @@ static int gpi_reset_chan(struct gchan *gchan, enum gpi_cmd gpi_cmd)
 {
 	struct gpii *gpii = gchan->gpii;
 	struct gpi_ring *ch_ring = &gchan->ch_ring;
-	unsigned long flags;
 	LIST_HEAD(list);
 	int ret;
 
@@ -1220,9 +1213,9 @@ static int gpi_reset_chan(struct gchan *gchan, enum gpi_cmd gpi_cmd)
 	gpi_mark_stale_events(gchan);
 
 	/* remove all async descriptors */
-	spin_lock_irqsave(&gchan->vc.lock, flags);
+	spin_lock(&gchan->vc.lock);
 	vchan_get_all_descriptors(&gchan->vc, &list);
-	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	spin_unlock(&gchan->vc.lock);
 	write_unlock_irq(&gpii->pm_lock);
 	vchan_dma_desc_free_list(&gchan->vc, &list);
 
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 721b4ac..4d2cd8d 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -957,4 +957,5 @@ static struct platform_driver hidma_driver = {
 };
 
 module_platform_driver(hidma_driver);
+MODULE_DESCRIPTION("Qualcomm Technologies HIDMA Channel support");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index bb883e1..4805ce3 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -331,4 +331,5 @@ static struct platform_driver hidma_mgmt_driver = {
 };
 
 module_platform_driver(hidma_mgmt_driver);
+MODULE_DESCRIPTION("Qualcomm Technologies HIDMA DMA engine interface");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 1f1e86b..65a27c5 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -540,8 +540,8 @@ static int rz_dmac_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&channel->vc.lock, flags);
 	list_splice_tail_init(&channel->ld_active, &channel->ld_free);
 	list_splice_tail_init(&channel->ld_queue, &channel->ld_free);
-	spin_unlock_irqrestore(&channel->vc.lock, flags);
 	vchan_get_all_descriptors(&channel->vc, &head);
+	spin_unlock_irqrestore(&channel->vc.lock, flags);
 	vchan_dma_desc_free_list(&channel->vc, &head);
 
 	return 0;
diff --git a/drivers/dma/stm32/Kconfig b/drivers/dma/stm32/Kconfig
new file mode 100644
index 0000000..4d8d806
--- /dev/null
+++ b/drivers/dma/stm32/Kconfig
@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# STM32 DMA controllers drivers
+#
+if ARCH_STM32 || COMPILE_TEST
+
+config STM32_DMA
+	bool "STMicroelectronics STM32 DMA support"
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip DMA controller on STMicroelectronics
+	  STM32 platforms.
+	  If you have a board based on STM32 SoC with such DMA controller
+	  and want to use DMA say Y here.
+
+config STM32_DMAMUX
+	bool "STMicroelectronics STM32 DMA multiplexer support"
+	depends on STM32_DMA
+	help
+	  Enable support for the on-chip DMA multiplexer on STMicroelectronics
+	  STM32 platforms.
+	  If you have a board based on STM32 SoC with such DMA multiplexer
+	  and want to use DMAMUX say Y here.
+
+config STM32_MDMA
+	bool "STMicroelectronics STM32 master DMA support"
+	depends on OF
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip MDMA controller on STMicroelectronics
+	  STM32 platforms.
+	  If you have a board based on STM32 SoC with such DMA controller
+	  and want to use MDMA say Y here.
+
+config STM32_DMA3
+	tristate "STMicroelectronics STM32 DMA3 support"
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip DMA3 controller on STMicroelectronics
+	  STM32 platforms.
+	  If you have a board based on STM32 SoC with such DMA3 controller
+	  and want to use DMA3, say Y here.
+
+endif
diff --git a/drivers/dma/stm32/Makefile b/drivers/dma/stm32/Makefile
new file mode 100644
index 0000000..5082db4
--- /dev/null
+++ b/drivers/dma/stm32/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_STM32_DMA) += stm32-dma.o
+obj-$(CONFIG_STM32_DMAMUX) += stm32-dmamux.o
+obj-$(CONFIG_STM32_MDMA) += stm32-mdma.o
+obj-$(CONFIG_STM32_DMA3) += stm32-dma3.o
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32/stm32-dma.c
similarity index 99%
rename from drivers/dma/stm32-dma.c
rename to drivers/dma/stm32/stm32-dma.c
index 90857d0..917f8e9 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32/stm32-dma.c
@@ -28,7 +28,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
-#include "virt-dma.h"
+#include "../virt-dma.h"
 
 #define STM32_DMA_LISR			0x0000 /* DMA Low Int Status Reg */
 #define STM32_DMA_HISR			0x0004 /* DMA High Int Status Reg */
diff --git a/drivers/dma/stm32/stm32-dma3.c b/drivers/dma/stm32/stm32-dma3.c
new file mode 100644
index 0000000..4087e02
--- /dev/null
+++ b/drivers/dma/stm32/stm32-dma3.c
@@ -0,0 +1,1847 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * STM32 DMA3 controller driver
+ *
+ * Copyright (C) STMicroelectronics 2024
+ * Author(s): Amelie Delaunay <amelie.delaunay@foss.st.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/init.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+
+#include "../virt-dma.h"
+
+#define STM32_DMA3_SECCFGR		0x00
+#define STM32_DMA3_PRIVCFGR		0x04
+#define STM32_DMA3_RCFGLOCKR		0x08
+#define STM32_DMA3_MISR			0x0c
+#define STM32_DMA3_SMISR		0x10
+
+#define STM32_DMA3_CLBAR(x)		(0x50 + 0x80 * (x))
+#define STM32_DMA3_CCIDCFGR(x)		(0x54 + 0x80 * (x))
+#define STM32_DMA3_CSEMCR(x)		(0x58 + 0x80 * (x))
+#define STM32_DMA3_CFCR(x)		(0x5c + 0x80 * (x))
+#define STM32_DMA3_CSR(x)		(0x60 + 0x80 * (x))
+#define STM32_DMA3_CCR(x)		(0x64 + 0x80 * (x))
+#define STM32_DMA3_CTR1(x)		(0x90 + 0x80 * (x))
+#define STM32_DMA3_CTR2(x)		(0x94 + 0x80 * (x))
+#define STM32_DMA3_CBR1(x)		(0x98 + 0x80 * (x))
+#define STM32_DMA3_CSAR(x)		(0x9c + 0x80 * (x))
+#define STM32_DMA3_CDAR(x)		(0xa0 + 0x80 * (x))
+#define STM32_DMA3_CLLR(x)		(0xcc + 0x80 * (x))
+
+#define STM32_DMA3_HWCFGR13		0xfc0 /* G_PER_CTRL(X) x=8..15 */
+#define STM32_DMA3_HWCFGR12		0xfc4 /* G_PER_CTRL(X) x=0..7 */
+#define STM32_DMA3_HWCFGR4		0xfe4 /* G_FIFO_SIZE(X) x=8..15 */
+#define STM32_DMA3_HWCFGR3		0xfe8 /* G_FIFO_SIZE(X) x=0..7 */
+#define STM32_DMA3_HWCFGR2		0xfec /* G_MAX_REQ_ID */
+#define STM32_DMA3_HWCFGR1		0xff0 /* G_MASTER_PORTS, G_NUM_CHANNELS, G_Mx_DATA_WIDTH */
+#define STM32_DMA3_VERR			0xff4
+
+/* SECCFGR DMA secure configuration register */
+#define SECCFGR_SEC(x)			BIT(x)
+
+/* MISR DMA non-secure/secure masked interrupt status register */
+#define MISR_MIS(x)			BIT(x)
+
+/* CxLBAR DMA channel x linked_list base address register */
+#define CLBAR_LBA			GENMASK(31, 16)
+
+/* CxCIDCFGR DMA channel x CID register */
+#define CCIDCFGR_CFEN			BIT(0)
+#define CCIDCFGR_SEM_EN			BIT(1)
+#define CCIDCFGR_SCID			GENMASK(5, 4)
+#define CCIDCFGR_SEM_WLIST_CID0		BIT(16)
+#define CCIDCFGR_SEM_WLIST_CID1		BIT(17)
+#define CCIDCFGR_SEM_WLIST_CID2		BIT(18)
+
+enum ccidcfgr_cid {
+	CCIDCFGR_CID0,
+	CCIDCFGR_CID1,
+	CCIDCFGR_CID2,
+};
+
+/* CxSEMCR DMA channel x semaphore control register */
+#define CSEMCR_SEM_MUTEX		BIT(0)
+#define CSEMCR_SEM_CCID			GENMASK(5, 4)
+
+/* CxFCR DMA channel x flag clear register */
+#define CFCR_TCF			BIT(8)
+#define CFCR_HTF			BIT(9)
+#define CFCR_DTEF			BIT(10)
+#define CFCR_ULEF			BIT(11)
+#define CFCR_USEF			BIT(12)
+#define CFCR_SUSPF			BIT(13)
+
+/* CxSR DMA channel x status register */
+#define CSR_IDLEF			BIT(0)
+#define CSR_TCF				BIT(8)
+#define CSR_HTF				BIT(9)
+#define CSR_DTEF			BIT(10)
+#define CSR_ULEF			BIT(11)
+#define CSR_USEF			BIT(12)
+#define CSR_SUSPF			BIT(13)
+#define CSR_ALL_F			GENMASK(13, 8)
+#define CSR_FIFOL			GENMASK(24, 16)
+
+/* CxCR DMA channel x control register */
+#define CCR_EN				BIT(0)
+#define CCR_RESET			BIT(1)
+#define CCR_SUSP			BIT(2)
+#define CCR_TCIE			BIT(8)
+#define CCR_HTIE			BIT(9)
+#define CCR_DTEIE			BIT(10)
+#define CCR_ULEIE			BIT(11)
+#define CCR_USEIE			BIT(12)
+#define CCR_SUSPIE			BIT(13)
+#define CCR_ALLIE			GENMASK(13, 8)
+#define CCR_LSM				BIT(16)
+#define CCR_LAP				BIT(17)
+#define CCR_PRIO			GENMASK(23, 22)
+
+enum ccr_prio {
+	CCR_PRIO_LOW,
+	CCR_PRIO_MID,
+	CCR_PRIO_HIGH,
+	CCR_PRIO_VERY_HIGH,
+};
+
+/* CxTR1 DMA channel x transfer register 1 */
+#define CTR1_SINC			BIT(3)
+#define CTR1_SBL_1			GENMASK(9, 4)
+#define CTR1_DINC			BIT(19)
+#define CTR1_DBL_1			GENMASK(25, 20)
+#define CTR1_SDW_LOG2			GENMASK(1, 0)
+#define CTR1_PAM			GENMASK(12, 11)
+#define CTR1_SAP			BIT(14)
+#define CTR1_DDW_LOG2			GENMASK(17, 16)
+#define CTR1_DAP			BIT(30)
+
+enum ctr1_dw {
+	CTR1_DW_BYTE,
+	CTR1_DW_HWORD,
+	CTR1_DW_WORD,
+	CTR1_DW_DWORD, /* Depends on HWCFGR1.G_M0_DATA_WIDTH_ENC and .G_M1_DATA_WIDTH_ENC */
+};
+
+enum ctr1_pam {
+	CTR1_PAM_0S_LT,		/* if DDW > SDW, padded with 0s else left-truncated */
+	CTR1_PAM_SE_RT,		/* if DDW > SDW, sign extended else right-truncated */
+	CTR1_PAM_PACK_UNPACK,	/* FIFO queued */
+};
+
+/* CxTR2 DMA channel x transfer register 2 */
+#define CTR2_REQSEL			GENMASK(7, 0)
+#define CTR2_SWREQ			BIT(9)
+#define CTR2_DREQ			BIT(10)
+#define CTR2_BREQ			BIT(11)
+#define CTR2_PFREQ			BIT(12)
+#define CTR2_TCEM			GENMASK(31, 30)
+
+enum ctr2_tcem {
+	CTR2_TCEM_BLOCK,
+	CTR2_TCEM_REPEAT_BLOCK,
+	CTR2_TCEM_LLI,
+	CTR2_TCEM_CHANNEL,
+};
+
+/* CxBR1 DMA channel x block register 1 */
+#define CBR1_BNDT			GENMASK(15, 0)
+
+/* CxLLR DMA channel x linked-list address register */
+#define CLLR_LA				GENMASK(15, 2)
+#define CLLR_ULL			BIT(16)
+#define CLLR_UDA			BIT(27)
+#define CLLR_USA			BIT(28)
+#define CLLR_UB1			BIT(29)
+#define CLLR_UT2			BIT(30)
+#define CLLR_UT1			BIT(31)
+
+/* HWCFGR13 DMA hardware configuration register 13 x=8..15 */
+/* HWCFGR12 DMA hardware configuration register 12 x=0..7 */
+#define G_PER_CTRL(x)			(ULL(0x1) << (4 * (x)))
+
+/* HWCFGR4 DMA hardware configuration register 4 x=8..15 */
+/* HWCFGR3 DMA hardware configuration register 3 x=0..7 */
+#define G_FIFO_SIZE(x)			(ULL(0x7) << (4 * (x)))
+
+#define get_chan_hwcfg(x, mask, reg)	(((reg) & (mask)) >> (4 * (x)))
+
+/* HWCFGR2 DMA hardware configuration register 2 */
+#define G_MAX_REQ_ID			GENMASK(7, 0)
+
+/* HWCFGR1 DMA hardware configuration register 1 */
+#define G_MASTER_PORTS			GENMASK(2, 0)
+#define G_NUM_CHANNELS			GENMASK(12, 8)
+#define G_M0_DATA_WIDTH_ENC		GENMASK(25, 24)
+#define G_M1_DATA_WIDTH_ENC		GENMASK(29, 28)
+
+enum stm32_dma3_master_ports {
+	AXI64,		/* 1x AXI: 64-bit port 0 */
+	AHB32,		/* 1x AHB: 32-bit port 0 */
+	AHB32_AHB32,	/* 2x AHB: 32-bit port 0 and 32-bit port 1 */
+	AXI64_AHB32,	/* 1x AXI 64-bit port 0 and 1x AHB 32-bit port 1 */
+	AXI64_AXI64,	/* 2x AXI: 64-bit port 0 and 64-bit port 1 */
+	AXI128_AHB32,	/* 1x AXI 128-bit port 0 and 1x AHB 32-bit port 1 */
+};
+
+enum stm32_dma3_port_data_width {
+	DW_32,		/* 32-bit, for AHB */
+	DW_64,		/* 64-bit, for AXI */
+	DW_128,		/* 128-bit, for AXI */
+	DW_INVALID,
+};
+
+/* VERR DMA version register */
+#define VERR_MINREV			GENMASK(3, 0)
+#define VERR_MAJREV			GENMASK(7, 4)
+
+/* Device tree */
+/* struct stm32_dma3_dt_conf */
+/* .ch_conf */
+#define STM32_DMA3_DT_PRIO		GENMASK(1, 0) /* CCR_PRIO */
+#define STM32_DMA3_DT_FIFO		GENMASK(7, 4)
+/* .tr_conf */
+#define STM32_DMA3_DT_SINC		BIT(0) /* CTR1_SINC */
+#define STM32_DMA3_DT_SAP		BIT(1) /* CTR1_SAP */
+#define STM32_DMA3_DT_DINC		BIT(4) /* CTR1_DINC */
+#define STM32_DMA3_DT_DAP		BIT(5) /* CTR1_DAP */
+#define STM32_DMA3_DT_BREQ		BIT(8) /* CTR2_BREQ */
+#define STM32_DMA3_DT_PFREQ		BIT(9) /* CTR2_PFREQ */
+#define STM32_DMA3_DT_TCEM		GENMASK(13, 12) /* CTR2_TCEM */
+
+/* struct stm32_dma3_chan .config_set bitfield */
+#define STM32_DMA3_CFG_SET_DT		BIT(0)
+#define STM32_DMA3_CFG_SET_DMA		BIT(1)
+#define STM32_DMA3_CFG_SET_BOTH		(STM32_DMA3_CFG_SET_DT | STM32_DMA3_CFG_SET_DMA)
+
+#define STM32_DMA3_MAX_BLOCK_SIZE	ALIGN_DOWN(CBR1_BNDT, 64)
+#define port_is_ahb(maxdw)		({ typeof(maxdw) (_maxdw) = (maxdw); \
+					   ((_maxdw) != DW_INVALID) && ((_maxdw) == DW_32); })
+#define port_is_axi(maxdw)		({ typeof(maxdw) (_maxdw) = (maxdw); \
+					   ((_maxdw) != DW_INVALID) && ((_maxdw) != DW_32); })
+#define get_chan_max_dw(maxdw, maxburst)((port_is_ahb(maxdw) ||			     \
+					  (maxburst) < DMA_SLAVE_BUSWIDTH_8_BYTES) ? \
+					 DMA_SLAVE_BUSWIDTH_4_BYTES : DMA_SLAVE_BUSWIDTH_8_BYTES)
+
+/* Static linked-list data structure (depends on update bits UT1/UT2/UB1/USA/UDA/ULL) */
+struct stm32_dma3_hwdesc {
+	u32 ctr1;
+	u32 ctr2;
+	u32 cbr1;
+	u32 csar;
+	u32 cdar;
+	u32 cllr;
+} __packed __aligned(32);
+
+/*
+ * CLLR_LA / sizeof(struct stm32_dma3_hwdesc) represents the number of hdwdesc that can be addressed
+ * by the pointer to the next linked-list data structure. The __aligned forces the 32-byte
+ * alignment. So use hardcoded 32. Multiplied by the max block size of each item, it represents
+ * the sg size limitation.
+ */
+#define STM32_DMA3_MAX_SEG_SIZE		((CLLR_LA / 32) * STM32_DMA3_MAX_BLOCK_SIZE)
+
+/*
+ * Linked-list items
+ */
+struct stm32_dma3_lli {
+	struct stm32_dma3_hwdesc *hwdesc;
+	dma_addr_t hwdesc_addr;
+};
+
+struct stm32_dma3_swdesc {
+	struct virt_dma_desc vdesc;
+	u32 ccr;
+	bool cyclic;
+	u32 lli_size;
+	struct stm32_dma3_lli lli[] __counted_by(lli_size);
+};
+
+struct stm32_dma3_dt_conf {
+	u32 ch_id;
+	u32 req_line;
+	u32 ch_conf;
+	u32 tr_conf;
+};
+
+struct stm32_dma3_chan {
+	struct virt_dma_chan vchan;
+	u32 id;
+	int irq;
+	u32 fifo_size;
+	u32 max_burst;
+	bool semaphore_mode;
+	struct stm32_dma3_dt_conf dt_config;
+	struct dma_slave_config dma_config;
+	u8 config_set;
+	struct dma_pool *lli_pool;
+	struct stm32_dma3_swdesc *swdesc;
+	enum ctr2_tcem tcem;
+	u32 dma_status;
+};
+
+struct stm32_dma3_ddata {
+	struct dma_device dma_dev;
+	void __iomem *base;
+	struct clk *clk;
+	struct stm32_dma3_chan *chans;
+	u32 dma_channels;
+	u32 dma_requests;
+	enum stm32_dma3_port_data_width ports_max_dw[2];
+};
+
+static inline struct stm32_dma3_ddata *to_stm32_dma3_ddata(struct stm32_dma3_chan *chan)
+{
+	return container_of(chan->vchan.chan.device, struct stm32_dma3_ddata, dma_dev);
+}
+
+static inline struct stm32_dma3_chan *to_stm32_dma3_chan(struct dma_chan *c)
+{
+	return container_of(c, struct stm32_dma3_chan, vchan.chan);
+}
+
+static inline struct stm32_dma3_swdesc *to_stm32_dma3_swdesc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct stm32_dma3_swdesc, vdesc);
+}
+
+static struct device *chan2dev(struct stm32_dma3_chan *chan)
+{
+	return &chan->vchan.chan.dev->device;
+}
+
+static void stm32_dma3_chan_dump_reg(struct stm32_dma3_chan *chan)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct device *dev = chan2dev(chan);
+	u32 id = chan->id, offset;
+
+	offset = STM32_DMA3_SECCFGR;
+	dev_dbg(dev, "SECCFGR(0x%03x): %08x\n", offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_PRIVCFGR;
+	dev_dbg(dev, "PRIVCFGR(0x%03x): %08x\n", offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CCIDCFGR(id);
+	dev_dbg(dev, "C%dCIDCFGR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CSEMCR(id);
+	dev_dbg(dev, "C%dSEMCR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CSR(id);
+	dev_dbg(dev, "C%dSR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CCR(id);
+	dev_dbg(dev, "C%dCR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CTR1(id);
+	dev_dbg(dev, "C%dTR1(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CTR2(id);
+	dev_dbg(dev, "C%dTR2(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CBR1(id);
+	dev_dbg(dev, "C%dBR1(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CSAR(id);
+	dev_dbg(dev, "C%dSAR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CDAR(id);
+	dev_dbg(dev, "C%dDAR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CLLR(id);
+	dev_dbg(dev, "C%dLLR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+	offset = STM32_DMA3_CLBAR(id);
+	dev_dbg(dev, "C%dLBAR(0x%03x): %08x\n", id, offset, readl_relaxed(ddata->base + offset));
+}
+
+static void stm32_dma3_chan_dump_hwdesc(struct stm32_dma3_chan *chan,
+					struct stm32_dma3_swdesc *swdesc)
+{
+	struct stm32_dma3_hwdesc *hwdesc;
+	int i;
+
+	for (i = 0; i < swdesc->lli_size; i++) {
+		hwdesc = swdesc->lli[i].hwdesc;
+		if (i)
+			dev_dbg(chan2dev(chan), "V\n");
+		dev_dbg(chan2dev(chan), "[%d]@%pad\n", i, &swdesc->lli[i].hwdesc_addr);
+		dev_dbg(chan2dev(chan), "| C%dTR1: %08x\n", chan->id, hwdesc->ctr1);
+		dev_dbg(chan2dev(chan), "| C%dTR2: %08x\n", chan->id, hwdesc->ctr2);
+		dev_dbg(chan2dev(chan), "| C%dBR1: %08x\n", chan->id, hwdesc->cbr1);
+		dev_dbg(chan2dev(chan), "| C%dSAR: %08x\n", chan->id, hwdesc->csar);
+		dev_dbg(chan2dev(chan), "| C%dDAR: %08x\n", chan->id, hwdesc->cdar);
+		dev_dbg(chan2dev(chan), "| C%dLLR: %08x\n", chan->id, hwdesc->cllr);
+	}
+
+	if (swdesc->cyclic) {
+		dev_dbg(chan2dev(chan), "|\n");
+		dev_dbg(chan2dev(chan), "-->[0]@%pad\n", &swdesc->lli[0].hwdesc_addr);
+	} else {
+		dev_dbg(chan2dev(chan), "X\n");
+	}
+}
+
+static struct stm32_dma3_swdesc *stm32_dma3_chan_desc_alloc(struct stm32_dma3_chan *chan, u32 count)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct stm32_dma3_swdesc *swdesc;
+	int i;
+
+	/*
+	 * If the memory to be allocated for the number of hwdesc (6 u32 members but 32-bytes
+	 * aligned) is greater than the maximum address of CLLR_LA, then the last items can't be
+	 * addressed, so abort the allocation.
+	 */
+	if ((count * 32) > CLLR_LA) {
+		dev_err(chan2dev(chan), "Transfer is too big (> %luB)\n", STM32_DMA3_MAX_SEG_SIZE);
+		return NULL;
+	}
+
+	swdesc = kzalloc(struct_size(swdesc, lli, count), GFP_NOWAIT);
+	if (!swdesc)
+		return NULL;
+
+	for (i = 0; i < count; i++) {
+		swdesc->lli[i].hwdesc = dma_pool_zalloc(chan->lli_pool, GFP_NOWAIT,
+							&swdesc->lli[i].hwdesc_addr);
+		if (!swdesc->lli[i].hwdesc)
+			goto err_pool_free;
+	}
+	swdesc->lli_size = count;
+	swdesc->ccr = 0;
+
+	/* Set LL base address */
+	writel_relaxed(swdesc->lli[0].hwdesc_addr & CLBAR_LBA,
+		       ddata->base + STM32_DMA3_CLBAR(chan->id));
+
+	/* Set LL allocated port */
+	swdesc->ccr &= ~CCR_LAP;
+
+	return swdesc;
+
+err_pool_free:
+	dev_err(chan2dev(chan), "Failed to alloc descriptors\n");
+	while (--i >= 0)
+		dma_pool_free(chan->lli_pool, swdesc->lli[i].hwdesc, swdesc->lli[i].hwdesc_addr);
+	kfree(swdesc);
+
+	return NULL;
+}
+
+static void stm32_dma3_chan_desc_free(struct stm32_dma3_chan *chan,
+				      struct stm32_dma3_swdesc *swdesc)
+{
+	int i;
+
+	for (i = 0; i < swdesc->lli_size; i++)
+		dma_pool_free(chan->lli_pool, swdesc->lli[i].hwdesc, swdesc->lli[i].hwdesc_addr);
+
+	kfree(swdesc);
+}
+
+static void stm32_dma3_chan_vdesc_free(struct virt_dma_desc *vdesc)
+{
+	struct stm32_dma3_swdesc *swdesc = to_stm32_dma3_swdesc(vdesc);
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(vdesc->tx.chan);
+
+	stm32_dma3_chan_desc_free(chan, swdesc);
+}
+
+static void stm32_dma3_check_user_setting(struct stm32_dma3_chan *chan)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct device *dev = chan2dev(chan);
+	u32 ctr1 = readl_relaxed(ddata->base + STM32_DMA3_CTR1(chan->id));
+	u32 cbr1 = readl_relaxed(ddata->base + STM32_DMA3_CBR1(chan->id));
+	u32 csar = readl_relaxed(ddata->base + STM32_DMA3_CSAR(chan->id));
+	u32 cdar = readl_relaxed(ddata->base + STM32_DMA3_CDAR(chan->id));
+	u32 cllr = readl_relaxed(ddata->base + STM32_DMA3_CLLR(chan->id));
+	u32 bndt = FIELD_GET(CBR1_BNDT, cbr1);
+	u32 sdw = 1 << FIELD_GET(CTR1_SDW_LOG2, ctr1);
+	u32 ddw = 1 << FIELD_GET(CTR1_DDW_LOG2, ctr1);
+	u32 sap = FIELD_GET(CTR1_SAP, ctr1);
+	u32 dap = FIELD_GET(CTR1_DAP, ctr1);
+
+	if (!bndt && !FIELD_GET(CLLR_UB1, cllr))
+		dev_err(dev, "null source block size and no update of this value\n");
+	if (bndt % sdw)
+		dev_err(dev, "source block size not multiple of src data width\n");
+	if (FIELD_GET(CTR1_PAM, ctr1) == CTR1_PAM_PACK_UNPACK && bndt % ddw)
+		dev_err(dev, "(un)packing mode w/ src block size not multiple of dst data width\n");
+	if (csar % sdw)
+		dev_err(dev, "unaligned source address not multiple of src data width\n");
+	if (cdar % ddw)
+		dev_err(dev, "unaligned destination address not multiple of dst data width\n");
+	if (sdw == DMA_SLAVE_BUSWIDTH_8_BYTES && port_is_ahb(ddata->ports_max_dw[sap]))
+		dev_err(dev, "double-word source data width not supported on port %u\n", sap);
+	if (ddw == DMA_SLAVE_BUSWIDTH_8_BYTES && port_is_ahb(ddata->ports_max_dw[dap]))
+		dev_err(dev, "double-word destination data width not supported on port %u\n", dap);
+}
+
+static void stm32_dma3_chan_prep_hwdesc(struct stm32_dma3_chan *chan,
+					struct stm32_dma3_swdesc *swdesc,
+					u32 curr, dma_addr_t src, dma_addr_t dst, u32 len,
+					u32 ctr1, u32 ctr2, bool is_last, bool is_cyclic)
+{
+	struct stm32_dma3_hwdesc *hwdesc;
+	dma_addr_t next_lli;
+	u32 next = curr + 1;
+
+	hwdesc = swdesc->lli[curr].hwdesc;
+	hwdesc->ctr1 = ctr1;
+	hwdesc->ctr2 = ctr2;
+	hwdesc->cbr1 = FIELD_PREP(CBR1_BNDT, len);
+	hwdesc->csar = src;
+	hwdesc->cdar = dst;
+
+	if (is_last) {
+		if (is_cyclic)
+			next_lli = swdesc->lli[0].hwdesc_addr;
+		else
+			next_lli = 0;
+	} else {
+		next_lli = swdesc->lli[next].hwdesc_addr;
+	}
+
+	hwdesc->cllr = 0;
+	if (next_lli) {
+		hwdesc->cllr |= CLLR_UT1 | CLLR_UT2 | CLLR_UB1;
+		hwdesc->cllr |= CLLR_USA | CLLR_UDA | CLLR_ULL;
+		hwdesc->cllr |= (next_lli & CLLR_LA);
+	}
+
+	/*
+	 * Make sure to flush the CPU's write buffers so that the descriptors are ready to be read
+	 * by DMA3. By explicitly using a write memory barrier here, instead of doing it with writel
+	 * to enable the channel, we avoid an unnecessary barrier in the case where the descriptors
+	 * are reused (DMA_CTRL_REUSE).
+	 */
+	if (is_last)
+		dma_wmb();
+}
+
+static enum dma_slave_buswidth stm32_dma3_get_max_dw(u32 chan_max_burst,
+						     enum stm32_dma3_port_data_width port_max_dw,
+						     u32 len, dma_addr_t addr)
+{
+	enum dma_slave_buswidth max_dw = get_chan_max_dw(port_max_dw, chan_max_burst);
+
+	/* len and addr must be a multiple of dw */
+	return 1 << __ffs(len | addr | max_dw);
+}
+
+static u32 stm32_dma3_get_max_burst(u32 len, enum dma_slave_buswidth dw, u32 chan_max_burst)
+{
+	u32 max_burst = chan_max_burst ? chan_max_burst / dw : 1;
+
+	/* len is a multiple of dw, so if len is < chan_max_burst, shorten burst */
+	if (len < chan_max_burst)
+		max_burst = len / dw;
+
+	/*
+	 * HW doesn't modify the burst if burst size <= half of the fifo size.
+	 * If len is not a multiple of burst size, last burst is shortened by HW.
+	 */
+	return max_burst;
+}
+
+static int stm32_dma3_chan_prep_hw(struct stm32_dma3_chan *chan, enum dma_transfer_direction dir,
+				   u32 *ccr, u32 *ctr1, u32 *ctr2,
+				   dma_addr_t src_addr, dma_addr_t dst_addr, u32 len)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct dma_device dma_device = ddata->dma_dev;
+	u32 sdw, ddw, sbl_max, dbl_max, tcem, init_dw, init_bl_max;
+	u32 _ctr1 = 0, _ctr2 = 0;
+	u32 ch_conf = chan->dt_config.ch_conf;
+	u32 tr_conf = chan->dt_config.tr_conf;
+	u32 sap = FIELD_GET(STM32_DMA3_DT_SAP, tr_conf), sap_max_dw;
+	u32 dap = FIELD_GET(STM32_DMA3_DT_DAP, tr_conf), dap_max_dw;
+
+	dev_dbg(chan2dev(chan), "%s from %pad to %pad\n",
+		dmaengine_get_direction_text(dir), &src_addr, &dst_addr);
+
+	sdw = chan->dma_config.src_addr_width ? : get_chan_max_dw(sap, chan->max_burst);
+	ddw = chan->dma_config.dst_addr_width ? : get_chan_max_dw(dap, chan->max_burst);
+	sbl_max = chan->dma_config.src_maxburst ? : 1;
+	dbl_max = chan->dma_config.dst_maxburst ? : 1;
+
+	/* Following conditions would raise User Setting Error interrupt */
+	if (!(dma_device.src_addr_widths & BIT(sdw)) || !(dma_device.dst_addr_widths & BIT(ddw))) {
+		dev_err(chan2dev(chan), "Bus width (src=%u, dst=%u) not supported\n", sdw, ddw);
+		return -EINVAL;
+	}
+
+	if (ddata->ports_max_dw[1] == DW_INVALID && (sap || dap)) {
+		dev_err(chan2dev(chan), "Only one master port, port 1 is not supported\n");
+		return -EINVAL;
+	}
+
+	sap_max_dw = ddata->ports_max_dw[sap];
+	dap_max_dw = ddata->ports_max_dw[dap];
+	if ((port_is_ahb(sap_max_dw) && sdw == DMA_SLAVE_BUSWIDTH_8_BYTES) ||
+	    (port_is_ahb(dap_max_dw) && ddw == DMA_SLAVE_BUSWIDTH_8_BYTES)) {
+		dev_err(chan2dev(chan),
+			"8 bytes buswidth (src=%u, dst=%u) not supported on port (sap=%u, dap=%u\n",
+			sdw, ddw, sap, dap);
+		return -EINVAL;
+	}
+
+	if (FIELD_GET(STM32_DMA3_DT_SINC, tr_conf))
+		_ctr1 |= CTR1_SINC;
+	if (sap)
+		_ctr1 |= CTR1_SAP;
+	if (FIELD_GET(STM32_DMA3_DT_DINC, tr_conf))
+		_ctr1 |= CTR1_DINC;
+	if (dap)
+		_ctr1 |= CTR1_DAP;
+
+	_ctr2 |= FIELD_PREP(CTR2_REQSEL, chan->dt_config.req_line) & ~CTR2_SWREQ;
+	if (FIELD_GET(STM32_DMA3_DT_BREQ, tr_conf))
+		_ctr2 |= CTR2_BREQ;
+	if (dir == DMA_DEV_TO_MEM && FIELD_GET(STM32_DMA3_DT_PFREQ, tr_conf))
+		_ctr2 |= CTR2_PFREQ;
+	tcem = FIELD_GET(STM32_DMA3_DT_TCEM, tr_conf);
+	_ctr2 |= FIELD_PREP(CTR2_TCEM, tcem);
+
+	/* Store TCEM to know on which event TC flag occurred */
+	chan->tcem = tcem;
+	/* Store direction for residue computation */
+	chan->dma_config.direction = dir;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		/* Set destination (device) data width and burst */
+		ddw = min_t(u32, ddw, stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw,
+							    len, dst_addr));
+		dbl_max = min_t(u32, dbl_max, stm32_dma3_get_max_burst(len, ddw, chan->max_burst));
+
+		/* Set source (memory) data width and burst */
+		sdw = stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw, len, src_addr);
+		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst);
+
+		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
+		_ctr1 |= FIELD_PREP(CTR1_SBL_1, sbl_max - 1);
+		_ctr1 |= FIELD_PREP(CTR1_DDW_LOG2, ilog2(ddw));
+		_ctr1 |= FIELD_PREP(CTR1_DBL_1, dbl_max - 1);
+
+		if (ddw != sdw) {
+			_ctr1 |= FIELD_PREP(CTR1_PAM, CTR1_PAM_PACK_UNPACK);
+			/* Should never reach this case as ddw is clamped down */
+			if (len & (ddw - 1)) {
+				dev_err(chan2dev(chan),
+					"Packing mode is enabled and len is not multiple of ddw");
+				return -EINVAL;
+			}
+		}
+
+		/* dst = dev */
+		_ctr2 |= CTR2_DREQ;
+
+		break;
+
+	case DMA_DEV_TO_MEM:
+		/* Set source (device) data width and burst */
+		sdw = min_t(u32, sdw, stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw,
+							    len, src_addr));
+		sbl_max = min_t(u32, sbl_max, stm32_dma3_get_max_burst(len, sdw, chan->max_burst));
+
+		/* Set destination (memory) data width and burst */
+		ddw = stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw, len, dst_addr);
+		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst);
+
+		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
+		_ctr1 |= FIELD_PREP(CTR1_SBL_1, sbl_max - 1);
+		_ctr1 |= FIELD_PREP(CTR1_DDW_LOG2, ilog2(ddw));
+		_ctr1 |= FIELD_PREP(CTR1_DBL_1, dbl_max - 1);
+
+		if (ddw != sdw) {
+			_ctr1 |= FIELD_PREP(CTR1_PAM, CTR1_PAM_PACK_UNPACK);
+			/* Should never reach this case as ddw is clamped down */
+			if (len & (ddw - 1)) {
+				dev_err(chan2dev(chan),
+					"Packing mode is enabled and len is not multiple of ddw\n");
+				return -EINVAL;
+			}
+		}
+
+		/* dst = mem */
+		_ctr2 &= ~CTR2_DREQ;
+
+		break;
+
+	case DMA_MEM_TO_MEM:
+		/* Set source (memory) data width and burst */
+		init_dw = sdw;
+		init_bl_max = sbl_max;
+		sdw = stm32_dma3_get_max_dw(chan->max_burst, sap_max_dw, len, src_addr);
+		sbl_max = stm32_dma3_get_max_burst(len, sdw, chan->max_burst);
+		if (chan->config_set & STM32_DMA3_CFG_SET_DMA) {
+			sdw = min_t(u32, init_dw, sdw);
+			sbl_max = min_t(u32, init_bl_max,
+					stm32_dma3_get_max_burst(len, sdw, chan->max_burst));
+		}
+
+		/* Set destination (memory) data width and burst */
+		init_dw = ddw;
+		init_bl_max = dbl_max;
+		ddw = stm32_dma3_get_max_dw(chan->max_burst, dap_max_dw, len, dst_addr);
+		dbl_max = stm32_dma3_get_max_burst(len, ddw, chan->max_burst);
+		if (chan->config_set & STM32_DMA3_CFG_SET_DMA) {
+			ddw = min_t(u32, init_dw, ddw);
+			dbl_max = min_t(u32, init_bl_max,
+					stm32_dma3_get_max_burst(len, ddw, chan->max_burst));
+		}
+
+		_ctr1 |= FIELD_PREP(CTR1_SDW_LOG2, ilog2(sdw));
+		_ctr1 |= FIELD_PREP(CTR1_SBL_1, sbl_max - 1);
+		_ctr1 |= FIELD_PREP(CTR1_DDW_LOG2, ilog2(ddw));
+		_ctr1 |= FIELD_PREP(CTR1_DBL_1, dbl_max - 1);
+
+		if (ddw != sdw) {
+			_ctr1 |= FIELD_PREP(CTR1_PAM, CTR1_PAM_PACK_UNPACK);
+			/* Should never reach this case as ddw is clamped down */
+			if (len & (ddw - 1)) {
+				dev_err(chan2dev(chan),
+					"Packing mode is enabled and len is not multiple of ddw");
+				return -EINVAL;
+			}
+		}
+
+		/* CTR2_REQSEL/DREQ/BREQ/PFREQ are ignored with CTR2_SWREQ=1 */
+		_ctr2 |= CTR2_SWREQ;
+
+		break;
+
+	default:
+		dev_err(chan2dev(chan), "Direction %s not supported\n",
+			dmaengine_get_direction_text(dir));
+		return -EINVAL;
+	}
+
+	*ccr |= FIELD_PREP(CCR_PRIO, FIELD_GET(STM32_DMA3_DT_PRIO, ch_conf));
+	*ctr1 = _ctr1;
+	*ctr2 = _ctr2;
+
+	dev_dbg(chan2dev(chan), "%s: sdw=%u bytes sbl=%u beats ddw=%u bytes dbl=%u beats\n",
+		__func__, sdw, sbl_max, ddw, dbl_max);
+
+	return 0;
+}
+
+static void stm32_dma3_chan_start(struct stm32_dma3_chan *chan)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct virt_dma_desc *vdesc;
+	struct stm32_dma3_hwdesc *hwdesc;
+	u32 id = chan->id;
+	u32 csr, ccr;
+
+	vdesc = vchan_next_desc(&chan->vchan);
+	if (!vdesc) {
+		chan->swdesc = NULL;
+		return;
+	}
+	list_del(&vdesc->node);
+
+	chan->swdesc = to_stm32_dma3_swdesc(vdesc);
+	hwdesc = chan->swdesc->lli[0].hwdesc;
+
+	stm32_dma3_chan_dump_hwdesc(chan, chan->swdesc);
+
+	writel_relaxed(chan->swdesc->ccr, ddata->base + STM32_DMA3_CCR(id));
+	writel_relaxed(hwdesc->ctr1, ddata->base + STM32_DMA3_CTR1(id));
+	writel_relaxed(hwdesc->ctr2, ddata->base + STM32_DMA3_CTR2(id));
+	writel_relaxed(hwdesc->cbr1, ddata->base + STM32_DMA3_CBR1(id));
+	writel_relaxed(hwdesc->csar, ddata->base + STM32_DMA3_CSAR(id));
+	writel_relaxed(hwdesc->cdar, ddata->base + STM32_DMA3_CDAR(id));
+	writel_relaxed(hwdesc->cllr, ddata->base + STM32_DMA3_CLLR(id));
+
+	/* Clear any pending interrupts */
+	csr = readl_relaxed(ddata->base + STM32_DMA3_CSR(id));
+	if (csr & CSR_ALL_F)
+		writel_relaxed(csr, ddata->base + STM32_DMA3_CFCR(id));
+
+	stm32_dma3_chan_dump_reg(chan);
+
+	ccr = readl_relaxed(ddata->base + STM32_DMA3_CCR(id));
+	writel_relaxed(ccr | CCR_EN, ddata->base + STM32_DMA3_CCR(id));
+
+	chan->dma_status = DMA_IN_PROGRESS;
+
+	dev_dbg(chan2dev(chan), "vchan %pK: started\n", &chan->vchan);
+}
+
+static int stm32_dma3_chan_suspend(struct stm32_dma3_chan *chan, bool susp)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 csr, ccr = readl_relaxed(ddata->base + STM32_DMA3_CCR(chan->id)) & ~CCR_EN;
+	int ret = 0;
+
+	if (susp)
+		ccr |= CCR_SUSP;
+	else
+		ccr &= ~CCR_SUSP;
+
+	writel_relaxed(ccr, ddata->base + STM32_DMA3_CCR(chan->id));
+
+	if (susp) {
+		ret = readl_relaxed_poll_timeout_atomic(ddata->base + STM32_DMA3_CSR(chan->id), csr,
+							csr & CSR_SUSPF, 1, 10);
+		if (!ret)
+			writel_relaxed(CFCR_SUSPF, ddata->base + STM32_DMA3_CFCR(chan->id));
+
+		stm32_dma3_chan_dump_reg(chan);
+	}
+
+	return ret;
+}
+
+static void stm32_dma3_chan_reset(struct stm32_dma3_chan *chan)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 ccr = readl_relaxed(ddata->base + STM32_DMA3_CCR(chan->id)) & ~CCR_EN;
+
+	writel_relaxed(ccr |= CCR_RESET, ddata->base + STM32_DMA3_CCR(chan->id));
+}
+
+static int stm32_dma3_chan_get_curr_hwdesc(struct stm32_dma3_swdesc *swdesc, u32 cllr, u32 *residue)
+{
+	u32 i, lli_offset, next_lli_offset = cllr & CLLR_LA;
+
+	/* If cllr is null, it means it is either the last or single item */
+	if (!cllr)
+		return swdesc->lli_size - 1;
+
+	/* In cyclic mode, go fast and first check we are not on the last item */
+	if (swdesc->cyclic && next_lli_offset == (swdesc->lli[0].hwdesc_addr & CLLR_LA))
+		return swdesc->lli_size - 1;
+
+	/* As transfer is in progress, look backward from the last item */
+	for (i = swdesc->lli_size - 1; i > 0; i--) {
+		*residue += FIELD_GET(CBR1_BNDT, swdesc->lli[i].hwdesc->cbr1);
+		lli_offset = swdesc->lli[i].hwdesc_addr & CLLR_LA;
+		if (lli_offset == next_lli_offset)
+			return i - 1;
+	}
+
+	return -EINVAL;
+}
+
+static void stm32_dma3_chan_set_residue(struct stm32_dma3_chan *chan,
+					struct stm32_dma3_swdesc *swdesc,
+					struct dma_tx_state *txstate)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct device *dev = chan2dev(chan);
+	struct stm32_dma3_hwdesc *hwdesc;
+	u32 residue, curr_lli, csr, cdar, cbr1, cllr, bndt, fifol;
+	bool pack_unpack;
+	int ret;
+
+	csr = readl_relaxed(ddata->base + STM32_DMA3_CSR(chan->id));
+	if (!(csr & CSR_IDLEF) && chan->dma_status != DMA_PAUSED) {
+		/* Suspend current transfer to read registers for a snapshot */
+		writel_relaxed(swdesc->ccr | CCR_SUSP, ddata->base + STM32_DMA3_CCR(chan->id));
+		ret = readl_relaxed_poll_timeout_atomic(ddata->base + STM32_DMA3_CSR(chan->id), csr,
+							csr & (CSR_SUSPF | CSR_IDLEF), 1, 10);
+
+		if (ret || ((csr & CSR_TCF) && (csr & CSR_IDLEF))) {
+			writel_relaxed(CFCR_SUSPF, ddata->base + STM32_DMA3_CFCR(chan->id));
+			writel_relaxed(swdesc->ccr, ddata->base + STM32_DMA3_CCR(chan->id));
+			if (ret)
+				dev_err(dev, "Channel suspension timeout, csr=%08x\n", csr);
+		}
+	}
+
+	/* If channel is still active (CSR_IDLEF is not set), can't get a reliable residue */
+	if (!(csr & CSR_IDLEF))
+		dev_warn(dev, "Can't get residue: channel still active, csr=%08x\n", csr);
+
+	/*
+	 * If channel is not suspended, but Idle and Transfer Complete are set,
+	 * linked-list is over, no residue
+	 */
+	if (!(csr & CSR_SUSPF) && (csr & CSR_TCF) && (csr & CSR_IDLEF))
+		return;
+
+	/* Read registers to have a snapshot */
+	cllr = readl_relaxed(ddata->base + STM32_DMA3_CLLR(chan->id));
+	cbr1 = readl_relaxed(ddata->base + STM32_DMA3_CBR1(chan->id));
+	cdar = readl_relaxed(ddata->base + STM32_DMA3_CDAR(chan->id));
+
+	/* Resume current transfer */
+	if (csr & CSR_SUSPF) {
+		writel_relaxed(CFCR_SUSPF, ddata->base + STM32_DMA3_CFCR(chan->id));
+		writel_relaxed(swdesc->ccr, ddata->base + STM32_DMA3_CCR(chan->id));
+	}
+
+	/* Add current BNDT */
+	bndt = FIELD_GET(CBR1_BNDT, cbr1);
+	residue = bndt;
+
+	/* Get current hwdesc and cumulate residue of pending hwdesc BNDT */
+	ret = stm32_dma3_chan_get_curr_hwdesc(swdesc, cllr, &residue);
+	if (ret < 0) {
+		dev_err(chan2dev(chan), "Can't get residue: current hwdesc not found\n");
+		return;
+	}
+	curr_lli = ret;
+
+	/* Read current FIFO level - in units of programmed destination data width */
+	hwdesc = swdesc->lli[curr_lli].hwdesc;
+	fifol = FIELD_GET(CSR_FIFOL, csr) * (1 << FIELD_GET(CTR1_DDW_LOG2, hwdesc->ctr1));
+	/* If the FIFO contains as many bytes as its size, it can't contain more */
+	if (fifol == (1 << (chan->fifo_size + 1)))
+		goto skip_fifol_update;
+
+	/*
+	 * In case of PACKING (Destination burst length > Source burst length) or UNPACKING
+	 * (Source burst length > Destination burst length), bytes could be pending in the FIFO
+	 * (to be packed up to Destination burst length or unpacked into Destination burst length
+	 * chunks).
+	 * BNDT is not reliable, as it reflects the number of bytes read from the source but not the
+	 * number of bytes written to the destination.
+	 * FIFOL is also not sufficient, because it reflects the number of available write beats in
+	 * units of Destination data width but not the bytes not yet packed or unpacked.
+	 * In case of Destination increment DINC, it is possible to compute the number of bytes in
+	 * the FIFO:
+	 * fifol_in_bytes = bytes_read - bytes_written.
+	 */
+	pack_unpack = !!(FIELD_GET(CTR1_PAM, hwdesc->ctr1) == CTR1_PAM_PACK_UNPACK);
+	if (pack_unpack && (hwdesc->ctr1 & CTR1_DINC)) {
+		int bytes_read = FIELD_GET(CBR1_BNDT, hwdesc->cbr1) - bndt;
+		int bytes_written = cdar - hwdesc->cdar;
+
+		if (bytes_read > 0)
+			fifol = bytes_read - bytes_written;
+	}
+
+skip_fifol_update:
+	if (fifol) {
+		dev_dbg(chan2dev(chan), "%u byte(s) in the FIFO\n", fifol);
+		dma_set_in_flight_bytes(txstate, fifol);
+		/*
+		 * Residue is already accurate for DMA_MEM_TO_DEV as BNDT reflects data read from
+		 * the source memory buffer, so just need to add fifol to residue in case of
+		 * DMA_DEV_TO_MEM transfer because these bytes are not yet written in destination
+		 * memory buffer.
+		 */
+		if (chan->dma_config.direction == DMA_DEV_TO_MEM)
+			residue += fifol;
+	}
+	dma_set_residue(txstate, residue);
+}
+
+static int stm32_dma3_chan_stop(struct stm32_dma3_chan *chan)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 ccr;
+	int ret = 0;
+
+	chan->dma_status = DMA_COMPLETE;
+
+	/* Disable interrupts */
+	ccr = readl_relaxed(ddata->base + STM32_DMA3_CCR(chan->id));
+	writel_relaxed(ccr & ~(CCR_ALLIE | CCR_EN), ddata->base + STM32_DMA3_CCR(chan->id));
+
+	if (!(ccr & CCR_SUSP) && (ccr & CCR_EN)) {
+		/* Suspend the channel */
+		ret = stm32_dma3_chan_suspend(chan, true);
+		if (ret)
+			dev_warn(chan2dev(chan), "%s: timeout, data might be lost\n", __func__);
+	}
+
+	/*
+	 * Reset the channel: this causes the reset of the FIFO and the reset of the channel
+	 * internal state, the reset of CCR_EN and CCR_SUSP bits.
+	 */
+	stm32_dma3_chan_reset(chan);
+
+	return ret;
+}
+
+static void stm32_dma3_chan_complete(struct stm32_dma3_chan *chan)
+{
+	if (!chan->swdesc)
+		return;
+
+	vchan_cookie_complete(&chan->swdesc->vdesc);
+	chan->swdesc = NULL;
+	stm32_dma3_chan_start(chan);
+}
+
+static irqreturn_t stm32_dma3_chan_irq(int irq, void *devid)
+{
+	struct stm32_dma3_chan *chan = devid;
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 misr, csr, ccr;
+
+	spin_lock(&chan->vchan.lock);
+
+	misr = readl_relaxed(ddata->base + STM32_DMA3_MISR);
+	if (!(misr & MISR_MIS(chan->id))) {
+		spin_unlock(&chan->vchan.lock);
+		return IRQ_NONE;
+	}
+
+	csr = readl_relaxed(ddata->base + STM32_DMA3_CSR(chan->id));
+	ccr = readl_relaxed(ddata->base + STM32_DMA3_CCR(chan->id)) & CCR_ALLIE;
+
+	if (csr & CSR_TCF && ccr & CCR_TCIE) {
+		if (chan->swdesc->cyclic)
+			vchan_cyclic_callback(&chan->swdesc->vdesc);
+		else
+			stm32_dma3_chan_complete(chan);
+	}
+
+	if (csr & CSR_USEF && ccr & CCR_USEIE) {
+		dev_err(chan2dev(chan), "User setting error\n");
+		chan->dma_status = DMA_ERROR;
+		/* CCR.EN automatically cleared by HW */
+		stm32_dma3_check_user_setting(chan);
+		stm32_dma3_chan_reset(chan);
+	}
+
+	if (csr & CSR_ULEF && ccr & CCR_ULEIE) {
+		dev_err(chan2dev(chan), "Update link transfer error\n");
+		chan->dma_status = DMA_ERROR;
+		/* CCR.EN automatically cleared by HW */
+		stm32_dma3_chan_reset(chan);
+	}
+
+	if (csr & CSR_DTEF && ccr & CCR_DTEIE) {
+		dev_err(chan2dev(chan), "Data transfer error\n");
+		chan->dma_status = DMA_ERROR;
+		/* CCR.EN automatically cleared by HW */
+		stm32_dma3_chan_reset(chan);
+	}
+
+	/*
+	 * Half Transfer Interrupt may be disabled but Half Transfer Flag can be set,
+	 * ensure HTF flag to be cleared, with other flags.
+	 */
+	csr &= (ccr | CCR_HTIE);
+
+	if (csr)
+		writel_relaxed(csr, ddata->base + STM32_DMA3_CFCR(chan->id));
+
+	spin_unlock(&chan->vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int stm32_dma3_alloc_chan_resources(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 id = chan->id, csemcr, ccid;
+	int ret;
+
+	ret = pm_runtime_resume_and_get(ddata->dma_dev.dev);
+	if (ret < 0)
+		return ret;
+
+	/* Ensure the channel is free */
+	if (chan->semaphore_mode &&
+	    readl_relaxed(ddata->base + STM32_DMA3_CSEMCR(chan->id)) & CSEMCR_SEM_MUTEX) {
+		ret = -EBUSY;
+		goto err_put_sync;
+	}
+
+	chan->lli_pool = dmam_pool_create(dev_name(&c->dev->device), c->device->dev,
+					  sizeof(struct stm32_dma3_hwdesc),
+					  __alignof__(struct stm32_dma3_hwdesc), SZ_64K);
+	if (!chan->lli_pool) {
+		dev_err(chan2dev(chan), "Failed to create LLI pool\n");
+		ret = -ENOMEM;
+		goto err_put_sync;
+	}
+
+	/* Take the channel semaphore */
+	if (chan->semaphore_mode) {
+		writel_relaxed(CSEMCR_SEM_MUTEX, ddata->base + STM32_DMA3_CSEMCR(id));
+		csemcr = readl_relaxed(ddata->base + STM32_DMA3_CSEMCR(id));
+		ccid = FIELD_GET(CSEMCR_SEM_CCID, csemcr);
+		/* Check that the channel is well taken */
+		if (ccid != CCIDCFGR_CID1) {
+			dev_err(chan2dev(chan), "Not under CID1 control (in-use by CID%d)\n", ccid);
+			ret = -EPERM;
+			goto err_pool_destroy;
+		}
+		dev_dbg(chan2dev(chan), "Under CID1 control (semcr=0x%08x)\n", csemcr);
+	}
+
+	return 0;
+
+err_pool_destroy:
+	dmam_pool_destroy(chan->lli_pool);
+	chan->lli_pool = NULL;
+
+err_put_sync:
+	pm_runtime_put_sync(ddata->dma_dev.dev);
+
+	return ret;
+}
+
+static void stm32_dma3_free_chan_resources(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	unsigned long flags;
+
+	/* Ensure channel is in idle state */
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	stm32_dma3_chan_stop(chan);
+	chan->swdesc = NULL;
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	vchan_free_chan_resources(to_virt_chan(c));
+
+	dmam_pool_destroy(chan->lli_pool);
+	chan->lli_pool = NULL;
+
+	/* Release the channel semaphore */
+	if (chan->semaphore_mode)
+		writel_relaxed(0, ddata->base + STM32_DMA3_CSEMCR(chan->id));
+
+	pm_runtime_put_sync(ddata->dma_dev.dev);
+
+	/* Reset configuration */
+	memset(&chan->dt_config, 0, sizeof(chan->dt_config));
+	memset(&chan->dma_config, 0, sizeof(chan->dma_config));
+	chan->config_set = 0;
+}
+
+static void stm32_dma3_init_chan_config_for_memcpy(struct stm32_dma3_chan *chan,
+						   dma_addr_t dst, dma_addr_t src)
+{
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	u32 dw = get_chan_max_dw(ddata->ports_max_dw[0], chan->max_burst); /* port 0 by default */
+	u32 burst = chan->max_burst / dw;
+
+	/* Initialize dt_config if channel not pre-configured through DT */
+	if (!(chan->config_set & STM32_DMA3_CFG_SET_DT)) {
+		chan->dt_config.ch_conf = FIELD_PREP(STM32_DMA3_DT_PRIO, CCR_PRIO_VERY_HIGH);
+		chan->dt_config.ch_conf |= FIELD_PREP(STM32_DMA3_DT_FIFO, chan->fifo_size);
+		chan->dt_config.tr_conf = STM32_DMA3_DT_SINC | STM32_DMA3_DT_DINC;
+		chan->dt_config.tr_conf |= FIELD_PREP(STM32_DMA3_DT_TCEM, CTR2_TCEM_CHANNEL);
+	}
+
+	/* Initialize dma_config if dmaengine_slave_config() not used */
+	if (!(chan->config_set & STM32_DMA3_CFG_SET_DMA)) {
+		chan->dma_config.src_addr_width = dw;
+		chan->dma_config.dst_addr_width = dw;
+		chan->dma_config.src_maxburst = burst;
+		chan->dma_config.dst_maxburst = burst;
+		chan->dma_config.src_addr = src;
+		chan->dma_config.dst_addr = dst;
+	}
+}
+
+static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_chan *c,
+								  dma_addr_t dst, dma_addr_t src,
+								  size_t len, unsigned long flags)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_swdesc *swdesc;
+	size_t next_size, offset;
+	u32 count, i, ctr1, ctr2;
+
+	count = DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE);
+
+	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
+	if (!swdesc)
+		return NULL;
+
+	if (chan->config_set != STM32_DMA3_CFG_SET_BOTH)
+		stm32_dma3_init_chan_config_for_memcpy(chan, dst, src);
+
+	for (i = 0, offset = 0; offset < len; i++, offset += next_size) {
+		size_t remaining;
+		int ret;
+
+		remaining = len - offset;
+		next_size = min_t(size_t, remaining, STM32_DMA3_MAX_BLOCK_SIZE);
+
+		ret = stm32_dma3_chan_prep_hw(chan, DMA_MEM_TO_MEM, &swdesc->ccr, &ctr1, &ctr2,
+					      src + offset, dst + offset, next_size);
+		if (ret)
+			goto err_desc_free;
+
+		stm32_dma3_chan_prep_hwdesc(chan, swdesc, i, src + offset, dst + offset, next_size,
+					    ctr1, ctr2, next_size == remaining, false);
+	}
+
+	/* Enable Errors interrupts */
+	swdesc->ccr |= CCR_USEIE | CCR_ULEIE | CCR_DTEIE;
+	/* Enable Transfer state interrupts */
+	swdesc->ccr |= CCR_TCIE;
+
+	swdesc->cyclic = false;
+
+	return vchan_tx_prep(&chan->vchan, &swdesc->vdesc, flags);
+
+err_desc_free:
+	stm32_dma3_chan_desc_free(chan, swdesc);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan *c,
+								struct scatterlist *sgl,
+								unsigned int sg_len,
+								enum dma_transfer_direction dir,
+								unsigned long flags, void *context)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_swdesc *swdesc;
+	struct scatterlist *sg;
+	size_t len;
+	dma_addr_t sg_addr, dev_addr, src, dst;
+	u32 i, j, count, ctr1, ctr2;
+	int ret;
+
+	count = sg_len;
+	for_each_sg(sgl, sg, sg_len, i) {
+		len = sg_dma_len(sg);
+		if (len > STM32_DMA3_MAX_BLOCK_SIZE)
+			count += DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE) - 1;
+	}
+
+	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
+	if (!swdesc)
+		return NULL;
+
+	/* sg_len and i correspond to the initial sgl; count and j correspond to the hwdesc LL */
+	j = 0;
+	for_each_sg(sgl, sg, sg_len, i) {
+		sg_addr = sg_dma_address(sg);
+		dev_addr = (dir == DMA_MEM_TO_DEV) ? chan->dma_config.dst_addr :
+						     chan->dma_config.src_addr;
+		len = sg_dma_len(sg);
+
+		do {
+			size_t chunk = min_t(size_t, len, STM32_DMA3_MAX_BLOCK_SIZE);
+
+			if (dir == DMA_MEM_TO_DEV) {
+				src = sg_addr;
+				dst = dev_addr;
+
+				ret = stm32_dma3_chan_prep_hw(chan, dir, &swdesc->ccr, &ctr1, &ctr2,
+							      src, dst, chunk);
+
+				if (FIELD_GET(CTR1_DINC, ctr1))
+					dev_addr += chunk;
+			} else { /* (dir == DMA_DEV_TO_MEM || dir == DMA_MEM_TO_MEM) */
+				src = dev_addr;
+				dst = sg_addr;
+
+				ret = stm32_dma3_chan_prep_hw(chan, dir, &swdesc->ccr, &ctr1, &ctr2,
+							      src, dst, chunk);
+
+				if (FIELD_GET(CTR1_SINC, ctr1))
+					dev_addr += chunk;
+			}
+
+			if (ret)
+				goto err_desc_free;
+
+			stm32_dma3_chan_prep_hwdesc(chan, swdesc, j, src, dst, chunk,
+						    ctr1, ctr2, j == (count - 1), false);
+
+			sg_addr += chunk;
+			len -= chunk;
+			j++;
+		} while (len);
+	}
+
+	/* Enable Error interrupts */
+	swdesc->ccr |= CCR_USEIE | CCR_ULEIE | CCR_DTEIE;
+	/* Enable Transfer state interrupts */
+	swdesc->ccr |= CCR_TCIE;
+
+	swdesc->cyclic = false;
+
+	return vchan_tx_prep(&chan->vchan, &swdesc->vdesc, flags);
+
+err_desc_free:
+	stm32_dma3_chan_desc_free(chan, swdesc);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_cyclic(struct dma_chan *c,
+								  dma_addr_t buf_addr,
+								  size_t buf_len, size_t period_len,
+								  enum dma_transfer_direction dir,
+								  unsigned long flags)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_swdesc *swdesc;
+	dma_addr_t src, dst;
+	u32 count, i, ctr1, ctr2;
+	int ret;
+
+	if (!buf_len || !period_len || period_len > STM32_DMA3_MAX_BLOCK_SIZE) {
+		dev_err(chan2dev(chan), "Invalid buffer/period length\n");
+		return NULL;
+	}
+
+	if (buf_len % period_len) {
+		dev_err(chan2dev(chan), "Buffer length not multiple of period length\n");
+		return NULL;
+	}
+
+	count = buf_len / period_len;
+	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
+	if (!swdesc)
+		return NULL;
+
+	if (dir == DMA_MEM_TO_DEV) {
+		src = buf_addr;
+		dst = chan->dma_config.dst_addr;
+
+		ret = stm32_dma3_chan_prep_hw(chan, DMA_MEM_TO_DEV, &swdesc->ccr, &ctr1, &ctr2,
+					      src, dst, period_len);
+	} else if (dir == DMA_DEV_TO_MEM) {
+		src = chan->dma_config.src_addr;
+		dst = buf_addr;
+
+		ret = stm32_dma3_chan_prep_hw(chan, DMA_DEV_TO_MEM, &swdesc->ccr, &ctr1, &ctr2,
+					      src, dst, period_len);
+	} else {
+		dev_err(chan2dev(chan), "Invalid direction\n");
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		goto err_desc_free;
+
+	for (i = 0; i < count; i++) {
+		if (dir == DMA_MEM_TO_DEV) {
+			src = buf_addr + i * period_len;
+			dst = chan->dma_config.dst_addr;
+		} else { /* (dir == DMA_DEV_TO_MEM) */
+			src = chan->dma_config.src_addr;
+			dst = buf_addr + i * period_len;
+		}
+
+		stm32_dma3_chan_prep_hwdesc(chan, swdesc, i, src, dst, period_len,
+					    ctr1, ctr2, i == (count - 1), true);
+	}
+
+	/* Enable Error interrupts */
+	swdesc->ccr |= CCR_USEIE | CCR_ULEIE | CCR_DTEIE;
+	/* Enable Transfer state interrupts */
+	swdesc->ccr |= CCR_TCIE;
+
+	swdesc->cyclic = true;
+
+	return vchan_tx_prep(&chan->vchan, &swdesc->vdesc, flags);
+
+err_desc_free:
+	stm32_dma3_chan_desc_free(chan, swdesc);
+
+	return NULL;
+}
+
+static void stm32_dma3_caps(struct dma_chan *c, struct dma_slave_caps *caps)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+
+	if (!chan->fifo_size) {
+		caps->max_burst = 0;
+		caps->src_addr_widths &= ~BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+		caps->dst_addr_widths &= ~BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+	} else {
+		/* Burst transfer should not exceed half of the fifo size */
+		caps->max_burst = chan->max_burst;
+		if (caps->max_burst < DMA_SLAVE_BUSWIDTH_8_BYTES) {
+			caps->src_addr_widths &= ~BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+			caps->dst_addr_widths &= ~BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+		}
+	}
+}
+
+static int stm32_dma3_config(struct dma_chan *c, struct dma_slave_config *config)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+
+	memcpy(&chan->dma_config, config, sizeof(*config));
+	chan->config_set |= STM32_DMA3_CFG_SET_DMA;
+
+	return 0;
+}
+
+static int stm32_dma3_pause(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	int ret;
+
+	ret = stm32_dma3_chan_suspend(chan, true);
+	if (ret)
+		return ret;
+
+	chan->dma_status = DMA_PAUSED;
+
+	dev_dbg(chan2dev(chan), "vchan %pK: paused\n", &chan->vchan);
+
+	return 0;
+}
+
+static int stm32_dma3_resume(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+
+	stm32_dma3_chan_suspend(chan, false);
+
+	chan->dma_status = DMA_IN_PROGRESS;
+
+	dev_dbg(chan2dev(chan), "vchan %pK: resumed\n", &chan->vchan);
+
+	return 0;
+}
+
+static int stm32_dma3_terminate_all(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+
+	if (chan->swdesc) {
+		vchan_terminate_vdesc(&chan->swdesc->vdesc);
+		chan->swdesc = NULL;
+	}
+
+	stm32_dma3_chan_stop(chan);
+
+	vchan_get_all_descriptors(&chan->vchan, &head);
+
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&chan->vchan, &head);
+
+	dev_dbg(chan2dev(chan), "vchan %pK: terminated\n", &chan->vchan);
+
+	return 0;
+}
+
+static void stm32_dma3_synchronize(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+
+	vchan_synchronize(&chan->vchan);
+}
+
+static enum dma_status stm32_dma3_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+					    struct dma_tx_state *txstate)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_swdesc *swdesc = NULL;
+	enum dma_status status;
+	unsigned long flags;
+	struct virt_dma_desc *vd;
+
+	status = dma_cookie_status(c, cookie, txstate);
+	if (status == DMA_COMPLETE)
+		return status;
+
+	if (!txstate)
+		return chan->dma_status;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+
+	vd = vchan_find_desc(&chan->vchan, cookie);
+	if (vd)
+		swdesc = to_stm32_dma3_swdesc(vd);
+	else if (chan->swdesc && chan->swdesc->vdesc.tx.cookie == cookie)
+		swdesc = chan->swdesc;
+
+	/* Get residue/in_flight_bytes only if a transfer is currently running (swdesc != NULL) */
+	if (swdesc)
+		stm32_dma3_chan_set_residue(chan, swdesc, txstate);
+
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	return chan->dma_status;
+}
+
+static void stm32_dma3_issue_pending(struct dma_chan *c)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+
+	if (vchan_issue_pending(&chan->vchan) && !chan->swdesc) {
+		dev_dbg(chan2dev(chan), "vchan %pK: issued\n", &chan->vchan);
+		stm32_dma3_chan_start(chan);
+	}
+
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+}
+
+static bool stm32_dma3_filter_fn(struct dma_chan *c, void *fn_param)
+{
+	struct stm32_dma3_chan *chan = to_stm32_dma3_chan(c);
+	struct stm32_dma3_ddata *ddata = to_stm32_dma3_ddata(chan);
+	struct stm32_dma3_dt_conf *conf = fn_param;
+	u32 mask, semcr;
+	int ret;
+
+	dev_dbg(c->device->dev, "%s(%s): req_line=%d ch_conf=%08x tr_conf=%08x\n",
+		__func__, dma_chan_name(c), conf->req_line, conf->ch_conf, conf->tr_conf);
+
+	if (!of_property_read_u32(c->device->dev->of_node, "dma-channel-mask", &mask))
+		if (!(mask & BIT(chan->id)))
+			return false;
+
+	ret = pm_runtime_resume_and_get(ddata->dma_dev.dev);
+	if (ret < 0)
+		return false;
+	semcr = readl_relaxed(ddata->base + STM32_DMA3_CSEMCR(chan->id));
+	pm_runtime_put_sync(ddata->dma_dev.dev);
+
+	/* Check if chan is free */
+	if (semcr & CSEMCR_SEM_MUTEX)
+		return false;
+
+	/* Check if chan fifo fits well */
+	if (FIELD_GET(STM32_DMA3_DT_FIFO, conf->ch_conf) != chan->fifo_size)
+		return false;
+
+	return true;
+}
+
+static struct dma_chan *stm32_dma3_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma)
+{
+	struct stm32_dma3_ddata *ddata = ofdma->of_dma_data;
+	dma_cap_mask_t mask = ddata->dma_dev.cap_mask;
+	struct stm32_dma3_dt_conf conf;
+	struct stm32_dma3_chan *chan;
+	struct dma_chan *c;
+
+	if (dma_spec->args_count < 3) {
+		dev_err(ddata->dma_dev.dev, "Invalid args count\n");
+		return NULL;
+	}
+
+	conf.req_line = dma_spec->args[0];
+	conf.ch_conf = dma_spec->args[1];
+	conf.tr_conf = dma_spec->args[2];
+
+	if (conf.req_line >= ddata->dma_requests) {
+		dev_err(ddata->dma_dev.dev, "Invalid request line\n");
+		return NULL;
+	}
+
+	/* Request dma channel among the generic dma controller list */
+	c = dma_request_channel(mask, stm32_dma3_filter_fn, &conf);
+	if (!c) {
+		dev_err(ddata->dma_dev.dev, "No suitable channel found\n");
+		return NULL;
+	}
+
+	chan = to_stm32_dma3_chan(c);
+	chan->dt_config = conf;
+	chan->config_set |= STM32_DMA3_CFG_SET_DT;
+
+	return c;
+}
+
+static u32 stm32_dma3_check_rif(struct stm32_dma3_ddata *ddata)
+{
+	u32 chan_reserved, mask = 0, i, ccidcfgr, invalid_cid = 0;
+
+	/* Reserve Secure channels */
+	chan_reserved = readl_relaxed(ddata->base + STM32_DMA3_SECCFGR);
+
+	/*
+	 * CID filtering must be configured to ensure that the DMA3 channel will inherit the CID of
+	 * the processor which is configuring and using the given channel.
+	 * In case CID filtering is not configured, dma-channel-mask property can be used to
+	 * specify available DMA channels to the kernel.
+	 */
+	of_property_read_u32(ddata->dma_dev.dev->of_node, "dma-channel-mask", &mask);
+
+	/* Reserve !CID-filtered not in dma-channel-mask, static CID != CID1, CID1 not allowed */
+	for (i = 0; i < ddata->dma_channels; i++) {
+		ccidcfgr = readl_relaxed(ddata->base + STM32_DMA3_CCIDCFGR(i));
+
+		if (!(ccidcfgr & CCIDCFGR_CFEN)) { /* !CID-filtered */
+			invalid_cid |= BIT(i);
+			if (!(mask & BIT(i))) /* Not in dma-channel-mask */
+				chan_reserved |= BIT(i);
+		} else { /* CID-filtered */
+			if (!(ccidcfgr & CCIDCFGR_SEM_EN)) { /* Static CID mode */
+				if (FIELD_GET(CCIDCFGR_SCID, ccidcfgr) != CCIDCFGR_CID1)
+					chan_reserved |= BIT(i);
+			} else { /* Semaphore mode */
+				if (!FIELD_GET(CCIDCFGR_SEM_WLIST_CID1, ccidcfgr))
+					chan_reserved |= BIT(i);
+				ddata->chans[i].semaphore_mode = true;
+			}
+		}
+		dev_dbg(ddata->dma_dev.dev, "chan%d: %s mode, %s\n", i,
+			!(ccidcfgr & CCIDCFGR_CFEN) ? "!CID-filtered" :
+			ddata->chans[i].semaphore_mode ? "Semaphore" : "Static CID",
+			(chan_reserved & BIT(i)) ? "denied" :
+			mask & BIT(i) ? "force allowed" : "allowed");
+	}
+
+	if (invalid_cid)
+		dev_warn(ddata->dma_dev.dev, "chan%*pbl have invalid CID configuration\n",
+			 ddata->dma_channels, &invalid_cid);
+
+	return chan_reserved;
+}
+
+static const struct of_device_id stm32_dma3_of_match[] = {
+	{ .compatible = "st,stm32mp25-dma3", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, stm32_dma3_of_match);
+
+static int stm32_dma3_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct stm32_dma3_ddata *ddata;
+	struct reset_control *reset;
+	struct stm32_dma3_chan *chan;
+	struct dma_device *dma_dev;
+	u32 master_ports, chan_reserved, i, verr;
+	u64 hwcfgr;
+	int ret;
+
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, ddata);
+
+	dma_dev = &ddata->dma_dev;
+
+	ddata->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ddata->base))
+		return PTR_ERR(ddata->base);
+
+	ddata->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(ddata->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(ddata->clk), "Failed to get clk\n");
+
+	reset = devm_reset_control_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(reset))
+		return dev_err_probe(&pdev->dev, PTR_ERR(reset), "Failed to get reset\n");
+
+	ret = clk_prepare_enable(ddata->clk);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to enable clk\n");
+
+	reset_control_reset(reset);
+
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+	dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, dma_dev->cap_mask);
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	dma_dev->dev = &pdev->dev;
+	/*
+	 * This controller supports up to 8-byte buswidth depending on the port used and the
+	 * channel, and can only access address at even boundaries, multiple of the buswidth.
+	 */
+	dma_dev->copy_align = DMAENGINE_ALIGN_8_BYTES;
+	dma_dev->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+				   BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+				   BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
+				   BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+	dma_dev->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+				   BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+				   BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
+				   BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
+	dma_dev->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) | BIT(DMA_MEM_TO_MEM);
+
+	dma_dev->descriptor_reuse = true;
+	dma_dev->max_sg_burst = STM32_DMA3_MAX_SEG_SIZE;
+	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	dma_dev->device_alloc_chan_resources = stm32_dma3_alloc_chan_resources;
+	dma_dev->device_free_chan_resources = stm32_dma3_free_chan_resources;
+	dma_dev->device_prep_dma_memcpy = stm32_dma3_prep_dma_memcpy;
+	dma_dev->device_prep_slave_sg = stm32_dma3_prep_slave_sg;
+	dma_dev->device_prep_dma_cyclic = stm32_dma3_prep_dma_cyclic;
+	dma_dev->device_caps = stm32_dma3_caps;
+	dma_dev->device_config = stm32_dma3_config;
+	dma_dev->device_pause = stm32_dma3_pause;
+	dma_dev->device_resume = stm32_dma3_resume;
+	dma_dev->device_terminate_all = stm32_dma3_terminate_all;
+	dma_dev->device_synchronize = stm32_dma3_synchronize;
+	dma_dev->device_tx_status = stm32_dma3_tx_status;
+	dma_dev->device_issue_pending = stm32_dma3_issue_pending;
+
+	/* if dma_channels is not modified, get it from hwcfgr1 */
+	if (of_property_read_u32(np, "dma-channels", &ddata->dma_channels)) {
+		hwcfgr = readl_relaxed(ddata->base + STM32_DMA3_HWCFGR1);
+		ddata->dma_channels = FIELD_GET(G_NUM_CHANNELS, hwcfgr);
+	}
+
+	/* if dma_requests is not modified, get it from hwcfgr2 */
+	if (of_property_read_u32(np, "dma-requests", &ddata->dma_requests)) {
+		hwcfgr = readl_relaxed(ddata->base + STM32_DMA3_HWCFGR2);
+		ddata->dma_requests = FIELD_GET(G_MAX_REQ_ID, hwcfgr) + 1;
+	}
+
+	/* G_MASTER_PORTS, G_M0_DATA_WIDTH_ENC, G_M1_DATA_WIDTH_ENC in HWCFGR1 */
+	hwcfgr = readl_relaxed(ddata->base + STM32_DMA3_HWCFGR1);
+	master_ports = FIELD_GET(G_MASTER_PORTS, hwcfgr);
+
+	ddata->ports_max_dw[0] = FIELD_GET(G_M0_DATA_WIDTH_ENC, hwcfgr);
+	if (master_ports == AXI64 || master_ports == AHB32) /* Single master port */
+		ddata->ports_max_dw[1] = DW_INVALID;
+	else /* Dual master ports */
+		ddata->ports_max_dw[1] = FIELD_GET(G_M1_DATA_WIDTH_ENC, hwcfgr);
+
+	ddata->chans = devm_kcalloc(&pdev->dev, ddata->dma_channels, sizeof(*ddata->chans),
+				    GFP_KERNEL);
+	if (!ddata->chans) {
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	chan_reserved = stm32_dma3_check_rif(ddata);
+
+	if (chan_reserved == GENMASK(ddata->dma_channels - 1, 0)) {
+		ret = -ENODEV;
+		dev_err_probe(&pdev->dev, ret, "No channel available, abort registration\n");
+		goto err_clk_disable;
+	}
+
+	/* G_FIFO_SIZE x=0..7 in HWCFGR3 and G_FIFO_SIZE x=8..15 in HWCFGR4 */
+	hwcfgr = readl_relaxed(ddata->base + STM32_DMA3_HWCFGR3);
+	hwcfgr |= ((u64)readl_relaxed(ddata->base + STM32_DMA3_HWCFGR4)) << 32;
+
+	for (i = 0; i < ddata->dma_channels; i++) {
+		if (chan_reserved & BIT(i))
+			continue;
+
+		chan = &ddata->chans[i];
+		chan->id = i;
+		chan->fifo_size = get_chan_hwcfg(i, G_FIFO_SIZE(i), hwcfgr);
+		/* If chan->fifo_size > 0 then half of the fifo size, else no burst when no FIFO */
+		chan->max_burst = (chan->fifo_size) ? (1 << (chan->fifo_size + 1)) / 2 : 0;
+	}
+
+	ret = dmaenginem_async_device_register(dma_dev);
+	if (ret)
+		goto err_clk_disable;
+
+	for (i = 0; i < ddata->dma_channels; i++) {
+		char name[12];
+
+		if (chan_reserved & BIT(i))
+			continue;
+
+		chan = &ddata->chans[i];
+		snprintf(name, sizeof(name), "dma%dchan%d", ddata->dma_dev.dev_id, chan->id);
+
+		chan->vchan.desc_free = stm32_dma3_chan_vdesc_free;
+		vchan_init(&chan->vchan, dma_dev);
+
+		ret = dma_async_device_channel_register(&ddata->dma_dev, &chan->vchan.chan, name);
+		if (ret) {
+			dev_err_probe(&pdev->dev, ret, "Failed to register channel %s\n", name);
+			goto err_clk_disable;
+		}
+
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0)
+			goto err_clk_disable;
+		chan->irq = ret;
+
+		ret = devm_request_irq(&pdev->dev, chan->irq, stm32_dma3_chan_irq, 0,
+				       dev_name(chan2dev(chan)), chan);
+		if (ret) {
+			dev_err_probe(&pdev->dev, ret, "Failed to request channel %s IRQ\n",
+				      dev_name(chan2dev(chan)));
+			goto err_clk_disable;
+		}
+	}
+
+	ret = of_dma_controller_register(np, stm32_dma3_of_xlate, ddata);
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "Failed to register controller\n");
+		goto err_clk_disable;
+	}
+
+	verr = readl_relaxed(ddata->base + STM32_DMA3_VERR);
+
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
+
+	dev_info(&pdev->dev, "STM32 DMA3 registered rev:%lu.%lu\n",
+		 FIELD_GET(VERR_MAJREV, verr), FIELD_GET(VERR_MINREV, verr));
+
+	return 0;
+
+err_clk_disable:
+	clk_disable_unprepare(ddata->clk);
+
+	return ret;
+}
+
+static void stm32_dma3_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+}
+
+static int stm32_dma3_runtime_suspend(struct device *dev)
+{
+	struct stm32_dma3_ddata *ddata = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(ddata->clk);
+
+	return 0;
+}
+
+static int stm32_dma3_runtime_resume(struct device *dev)
+{
+	struct stm32_dma3_ddata *ddata = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(ddata->clk);
+	if (ret)
+		dev_err(dev, "Failed to enable clk: %d\n", ret);
+
+	return ret;
+}
+
+static const struct dev_pm_ops stm32_dma3_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	RUNTIME_PM_OPS(stm32_dma3_runtime_suspend, stm32_dma3_runtime_resume, NULL)
+};
+
+static struct platform_driver stm32_dma3_driver = {
+	.probe = stm32_dma3_probe,
+	.remove_new = stm32_dma3_remove,
+	.driver = {
+		.name = "stm32-dma3",
+		.of_match_table = stm32_dma3_of_match,
+		.pm = pm_ptr(&stm32_dma3_pm_ops),
+	},
+};
+
+static int __init stm32_dma3_init(void)
+{
+	return platform_driver_register(&stm32_dma3_driver);
+}
+
+subsys_initcall(stm32_dma3_init);
+
+MODULE_DESCRIPTION("STM32 DMA3 controller driver");
+MODULE_AUTHOR("Amelie Delaunay <amelie.delaunay@foss.st.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32/stm32-dmamux.c
similarity index 100%
rename from drivers/dma/stm32-dmamux.c
rename to drivers/dma/stm32/stm32-dmamux.c
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32/stm32-mdma.c
similarity index 99%
rename from drivers/dma/stm32-mdma.c
rename to drivers/dma/stm32/stm32-mdma.c
index 6505081..e6d5259 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32/stm32-mdma.c
@@ -30,7 +30,7 @@
 #include <linux/reset.h>
 #include <linux/slab.h>
 
-#include "virt-dma.h"
+#include "../virt-dma.h"
 
 #define STM32_MDMA_GISR0		0x0000 /* MDMA Int Status Reg 1 */
 
diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c
index 7e0b06b..a8bb70c 100644
--- a/drivers/dma/ti/cppi41.c
+++ b/drivers/dma/ti/cppi41.c
@@ -1252,5 +1252,6 @@ static struct platform_driver cpp41_dma_driver = {
 };
 
 module_platform_driver(cpp41_dma_driver);
+MODULE_DESCRIPTION("Texas Instruments CPPI 4.1 DMA support");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Sebastian Andrzej Siewior <bigeasy@linutronix.de>");
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index 25148d9..c4b6f0d 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -106,4 +106,5 @@ int psil_set_new_ep_config(struct device *dev, const char *name,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(psil_set_new_ep_config);
+MODULE_DESCRIPTION("K3 PSI-L endpoint configuration");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index dd1a068..7c224c3 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -1574,4 +1574,5 @@ static int __init k3_udma_glue_class_init(void)
 }
 
 module_init(k3_udma_glue_class_init);
+MODULE_DESCRIPTION("TI K3 NAVSS DMA glue interface");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 6400d06..406ee19 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4405,6 +4405,7 @@ static const struct of_device_id udma_of_match[] = {
 	},
 	{ /* Sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, udma_of_match);
 
 static struct udma_soc_data am654_soc_data = {
 	.oes = {
@@ -4472,7 +4473,9 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
 		ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2);
 		break;
 	case DMA_TYPE_BCDMA:
-		ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2);
+		ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2) +
+				BCDMA_CAP3_HBCHAN_CNT(cap3) +
+				BCDMA_CAP3_UBCHAN_CNT(cap3);
 		ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2);
 		ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2);
 		ud->rflow_cnt = ud->rchan_cnt;
@@ -5621,6 +5624,7 @@ static struct platform_driver udma_driver = {
 };
 
 module_platform_driver(udma_driver);
+MODULE_DESCRIPTION("Texas Instruments UDMA support");
 MODULE_LICENSE("GPL v2");
 
 /* Private interfaces to UDMA */
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index b9e0e22..7e6c04a 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -1950,4 +1950,5 @@ static void __exit omap_dma_exit(void)
 module_exit(omap_dma_exit);
 
 MODULE_AUTHOR("Russell King");
+MODULE_DESCRIPTION("Texas Instruments sDMA DMAengine support");
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index a6f4265..7961172 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -139,4 +139,5 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 EXPORT_SYMBOL_GPL(vchan_init);
 
 MODULE_AUTHOR("Russell King");
+MODULE_DESCRIPTION("Virtual DMA channel support for DMAengine");
 MODULE_LICENSE("GPL");
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index cbc92d3..e5c05a8 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -109,8 +109,8 @@ static const u32 knl_interleave_list[] = {
 	0x104, 0x10c, 0x114, 0x11c,   /* 20-23 */
 };
 #define MAX_INTERLEAVE							\
-	(max_t(unsigned int, ARRAY_SIZE(sbridge_interleave_list),	\
-	       max_t(unsigned int, ARRAY_SIZE(ibridge_interleave_list),	\
+	(MAX_T(unsigned int, ARRAY_SIZE(sbridge_interleave_list),	\
+	       MAX_T(unsigned int, ARRAY_SIZE(ibridge_interleave_list),	\
 		     ARRAY_SIZE(knl_interleave_list))))
 
 struct interleave_pkg {
diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c
index 33f0ba1..cb586a3 100644
--- a/drivers/eisa/eisa-bus.c
+++ b/drivers/eisa/eisa-bus.c
@@ -105,10 +105,10 @@ static char __init *decode_eisa_sig(unsigned long addr)
 	return sig_str;
 }
 
-static int eisa_bus_match(struct device *dev, struct device_driver *drv)
+static int eisa_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct eisa_device *edev = to_eisa_device(dev);
-	struct eisa_driver *edrv = to_eisa_driver(drv);
+	const struct eisa_driver *edrv = to_eisa_driver(drv);
 	const struct eisa_device_id *eids = edrv->id_table;
 
 	if (!eids)
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index e6cdb90..00e9a13 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -190,10 +190,10 @@ static bool match_ids(const struct ieee1394_device_id *id_table, int *id)
 }
 
 static const struct ieee1394_device_id *unit_match(struct device *dev,
-						   struct device_driver *drv)
+						   const struct device_driver *drv)
 {
 	const struct ieee1394_device_id *id_table =
-			container_of(drv, struct fw_driver, driver)->id_table;
+			container_of_const(drv, struct fw_driver, driver)->id_table;
 	int id[] = {0, 0, 0, 0};
 
 	get_modalias_ids(fw_unit(dev), id);
@@ -207,7 +207,7 @@ static const struct ieee1394_device_id *unit_match(struct device *dev,
 
 static bool is_fw_unit(const struct device *dev);
 
-static int fw_unit_match(struct device *dev, struct device_driver *drv)
+static int fw_unit_match(struct device *dev, const struct device_driver *drv)
 {
 	/* We only allow binding to fw_units. */
 	return is_fw_unit(dev) && unit_match(dev, drv) != NULL;
diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c
index 0c83931..eb17d03 100644
--- a/drivers/firmware/arm_ffa/bus.c
+++ b/drivers/firmware/arm_ffa/bus.c
@@ -19,7 +19,7 @@
 
 static DEFINE_IDA(ffa_bus_id);
 
-static int ffa_device_match(struct device *dev, struct device_driver *drv)
+static int ffa_device_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct ffa_device_id *id_table;
 	struct ffa_device *ffa_dev;
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 77c78be..96b2e5f 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -207,7 +207,7 @@ scmi_protocol_table_unregister(const struct scmi_device_id *id_table)
 }
 
 static const struct scmi_device_id *
-scmi_dev_match_id(struct scmi_device *scmi_dev, struct scmi_driver *scmi_drv)
+scmi_dev_match_id(struct scmi_device *scmi_dev, const struct scmi_driver *scmi_drv)
 {
 	const struct scmi_device_id *id = scmi_drv->id_table;
 
@@ -225,9 +225,9 @@ scmi_dev_match_id(struct scmi_device *scmi_dev, struct scmi_driver *scmi_drv)
 	return NULL;
 }
 
-static int scmi_dev_match(struct device *dev, struct device_driver *drv)
+static int scmi_dev_match(struct device *dev, const struct device_driver *drv)
 {
-	struct scmi_driver *scmi_drv = to_scmi_driver(drv);
+	const struct scmi_driver *scmi_drv = to_scmi_driver(drv);
 	struct scmi_device *scmi_dev = to_scmi_dev(dev);
 	const struct scmi_device_id *id;
 
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 1f32d6c..f23ba62 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,8 @@
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax
+cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax \
+				   $(DISABLE_STACKLEAK_PLUGIN)
 cflags-$(CONFIG_LOONGARCH)	+= -fpie
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
diff --git a/drivers/firmware/efi/libstub/screen_info.c b/drivers/firmware/efi/libstub/screen_info.c
index a51ec20..5d3a1e3 100644
--- a/drivers/firmware/efi/libstub/screen_info.c
+++ b/drivers/firmware/efi/libstub/screen_info.c
@@ -32,6 +32,8 @@ struct screen_info *__alloc_screen_info(void)
 	if (status != EFI_SUCCESS)
 		return NULL;
 
+	memset(si, 0, sizeof(*si));
+
 	status = efi_bs_call(install_configuration_table,
 			     &screen_info_guid, si);
 	if (status == EFI_SUCCESS)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 078055b..f8e465d 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -534,11 +534,12 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 				   efi_system_table_t *sys_table_arg)
 {
-	static struct boot_params boot_params __page_aligned_bss;
-	struct setup_header *hdr = &boot_params.hdr;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
+	struct boot_params *boot_params;
+	struct setup_header *hdr;
 	int options_size = 0;
 	efi_status_t status;
+	unsigned long alloc;
 	char *cmdline_ptr;
 
 	efi_system_table = sys_table_arg;
@@ -553,6 +554,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 		efi_exit(handle, status);
 	}
 
+	status = efi_allocate_pages(PARAM_SIZE, &alloc, ULONG_MAX);
+	if (status != EFI_SUCCESS)
+		efi_exit(handle, status);
+
+	boot_params = memset((void *)alloc, 0x0, PARAM_SIZE);
+	hdr	    = &boot_params->hdr;
+
 	/* Assign the setup_header fields that the kernel actually cares about */
 	hdr->root_flags	= 1;
 	hdr->vid_mode	= 0xffff;
@@ -562,13 +570,15 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 
 	/* Convert unicode cmdline to ascii */
 	cmdline_ptr = efi_convert_cmdline(image, &options_size);
-	if (!cmdline_ptr)
+	if (!cmdline_ptr) {
+		efi_free(PARAM_SIZE, alloc);
 		efi_exit(handle, EFI_OUT_OF_RESOURCES);
+	}
 
 	efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr,
-			  &boot_params.ext_cmd_line_ptr);
+			  &boot_params->ext_cmd_line_ptr);
 
-	efi_stub_entry(handle, sys_table_arg, &boot_params);
+	efi_stub_entry(handle, sys_table_arg, boot_params);
 	/* not reached */
 }
 
diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c
index a4e3bbd..208652a 100644
--- a/drivers/firmware/google/coreboot_table.c
+++ b/drivers/firmware/google/coreboot_table.c
@@ -22,12 +22,12 @@
 #include "coreboot_table.h"
 
 #define CB_DEV(d) container_of(d, struct coreboot_device, dev)
-#define CB_DRV(d) container_of(d, struct coreboot_driver, drv)
+#define CB_DRV(d) container_of_const(d, struct coreboot_driver, drv)
 
-static int coreboot_bus_match(struct device *dev, struct device_driver *drv)
+static int coreboot_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct coreboot_device *device = CB_DEV(dev);
-	struct coreboot_driver *driver = CB_DRV(drv);
+	const struct coreboot_driver *driver = CB_DRV(drv);
 	const struct coreboot_device_id *id;
 
 	if (!driver->id_table)
diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index 094ee97..c406b94 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -257,10 +257,10 @@ dfl_match_one_device(const struct dfl_device_id *id, struct dfl_device *ddev)
 	return NULL;
 }
 
-static int dfl_bus_match(struct device *dev, struct device_driver *drv)
+static int dfl_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct dfl_device *ddev = to_dfl_dev(dev);
-	struct dfl_driver *ddrv = to_dfl_drv(drv);
+	const struct dfl_driver *ddrv = to_dfl_drv(drv);
 	const struct dfl_device_id *id_entry;
 
 	id_entry = ddrv->id_table;
diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c
index 097d5a7..46ac5a8 100644
--- a/drivers/fsi/fsi-core.c
+++ b/drivers/fsi/fsi-core.c
@@ -1361,10 +1361,10 @@ EXPORT_SYMBOL_GPL(fsi_master_unregister);
 
 /* FSI core & Linux bus type definitions */
 
-static int fsi_bus_match(struct device *dev, struct device_driver *drv)
+static int fsi_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct fsi_device *fsi_dev = to_fsi_dev(dev);
-	struct fsi_driver *fsi_drv = to_fsi_drv(drv);
+	const struct fsi_driver *fsi_drv = to_fsi_drv(drv);
 	const struct fsi_device_id *id;
 
 	if (!fsi_drv->id_table)
diff --git a/drivers/fsi/fsi-master-aspeed.c b/drivers/fsi/fsi-master-aspeed.c
index f0a19cd..b0b624c 100644
--- a/drivers/fsi/fsi-master-aspeed.c
+++ b/drivers/fsi/fsi-master-aspeed.c
@@ -646,14 +646,12 @@ static int fsi_master_aspeed_probe(struct platform_device *pdev)
 	return rc;
 }
 
-static int fsi_master_aspeed_remove(struct platform_device *pdev)
+static void fsi_master_aspeed_remove(struct platform_device *pdev)
 {
 	struct fsi_master_aspeed *aspeed = platform_get_drvdata(pdev);
 
 	fsi_master_unregister(&aspeed->master);
 	clk_disable_unprepare(aspeed->clk);
-
-	return 0;
 }
 
 static const struct of_device_id fsi_master_aspeed_match[] = {
@@ -668,7 +666,7 @@ static struct platform_driver fsi_master_aspeed_driver = {
 		.of_match_table	= fsi_master_aspeed_match,
 	},
 	.probe	= fsi_master_aspeed_probe,
-	.remove = fsi_master_aspeed_remove,
+	.remove_new = fsi_master_aspeed_remove,
 };
 
 module_platform_driver(fsi_master_aspeed_driver);
diff --git a/drivers/fsi/fsi-master-ast-cf.c b/drivers/fsi/fsi-master-ast-cf.c
index 812dfa9..f8c776c 100644
--- a/drivers/fsi/fsi-master-ast-cf.c
+++ b/drivers/fsi/fsi-master-ast-cf.c
@@ -1412,15 +1412,13 @@ static int fsi_master_acf_probe(struct platform_device *pdev)
 }
 
 
-static int fsi_master_acf_remove(struct platform_device *pdev)
+static void fsi_master_acf_remove(struct platform_device *pdev)
 {
 	struct fsi_master_acf *master = platform_get_drvdata(pdev);
 
 	device_remove_file(master->dev, &dev_attr_external_mode);
 
 	fsi_master_unregister(&master->master);
-
-	return 0;
 }
 
 static const struct of_device_id fsi_master_acf_match[] = {
@@ -1436,7 +1434,7 @@ static struct platform_driver fsi_master_acf = {
 		.of_match_table	= fsi_master_acf_match,
 	},
 	.probe	= fsi_master_acf_probe,
-	.remove = fsi_master_acf_remove,
+	.remove_new = fsi_master_acf_remove,
 };
 
 module_platform_driver(fsi_master_acf);
diff --git a/drivers/fsi/fsi-master-gpio.c b/drivers/fsi/fsi-master-gpio.c
index ed03da4..10fc344 100644
--- a/drivers/fsi/fsi-master-gpio.c
+++ b/drivers/fsi/fsi-master-gpio.c
@@ -867,15 +867,13 @@ static int fsi_master_gpio_probe(struct platform_device *pdev)
 
 
 
-static int fsi_master_gpio_remove(struct platform_device *pdev)
+static void fsi_master_gpio_remove(struct platform_device *pdev)
 {
 	struct fsi_master_gpio *master = platform_get_drvdata(pdev);
 
 	device_remove_file(&pdev->dev, &dev_attr_external_mode);
 
 	fsi_master_unregister(&master->master);
-
-	return 0;
 }
 
 static const struct of_device_id fsi_master_gpio_match[] = {
@@ -890,7 +888,7 @@ static struct platform_driver fsi_master_gpio_driver = {
 		.of_match_table	= fsi_master_gpio_match,
 	},
 	.probe	= fsi_master_gpio_probe,
-	.remove = fsi_master_gpio_remove,
+	.remove_new = fsi_master_gpio_remove,
 };
 
 module_platform_driver(fsi_master_gpio_driver);
diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c
index f7157c1..f58b158 100644
--- a/drivers/fsi/fsi-occ.c
+++ b/drivers/fsi/fsi-occ.c
@@ -702,7 +702,7 @@ static int occ_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int occ_remove(struct platform_device *pdev)
+static void occ_remove(struct platform_device *pdev)
 {
 	struct occ *occ = platform_get_drvdata(pdev);
 
@@ -719,8 +719,6 @@ static int occ_remove(struct platform_device *pdev)
 		device_for_each_child(&pdev->dev, NULL, occ_unregister_of_child);
 
 	ida_free(&occ_ida, occ->idx);
-
-	return 0;
 }
 
 static const struct of_device_id occ_match[] = {
@@ -742,7 +740,7 @@ static struct platform_driver occ_driver = {
 		.of_match_table	= occ_match,
 	},
 	.probe	= occ_probe,
-	.remove = occ_remove,
+	.remove_new = occ_remove,
 };
 
 static int occ_init(void)
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 8dce78e..5762e51 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -591,8 +591,6 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 	void __iomem *reg_base;
 	struct brcmstb_gpio_priv *priv;
 	struct resource *res;
-	struct property *prop;
-	const __be32 *p;
 	u32 bank_width;
 	int num_banks = 0;
 	int num_gpios = 0;
@@ -636,8 +634,7 @@ static int brcmstb_gpio_probe(struct platform_device *pdev)
 	flags = BGPIOF_BIG_ENDIAN_BYTE_ORDER;
 #endif
 
-	of_property_for_each_u32(np, "brcm,gpio-bank-widths", prop, p,
-			bank_width) {
+	of_property_for_each_u32(np, "brcm,gpio-bank-widths", bank_width) {
 		struct brcmstb_gpio_bank *bank;
 		struct gpio_chip *gc;
 
diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c
index 0e0d55d..ccc47ea 100644
--- a/drivers/gpio/gpio-virtuser.c
+++ b/drivers/gpio/gpio-virtuser.c
@@ -805,7 +805,7 @@ static int gpio_virtuser_dbgfs_init_line_attrs(struct device *dev,
 		return -ENOMEM;
 
 	data->ad.desc = desc;
-	sprintf(data->consumer, id);
+	strscpy(data->consumer, id);
 	atomic_set(&data->irq, 0);
 	atomic_set(&data->irq_count, 0);
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index edaeee5..3a9668c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -55,7 +55,7 @@ static DEFINE_IDA(gpio_ida);
 static dev_t gpio_devt;
 #define GPIO_DEV_MAX 256 /* 256 GPIO chip devices supported */
 
-static int gpio_bus_match(struct device *dev, struct device_driver *drv)
+static int gpio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct fwnode_handle *fwnode = dev_fwnode(dev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 9dd8294..38408e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -106,7 +106,8 @@
 	df_v1_7.o \
 	df_v3_6.o \
 	df_v4_3.o \
-	df_v4_6_2.o
+	df_v4_6_2.o \
+	df_v4_15.o
 
 # add GMC block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
index 1538b2d..eb605e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
@@ -33,6 +33,7 @@ struct amdgpu_df_hash_status {
 struct amdgpu_df_funcs {
 	void (*sw_init)(struct amdgpu_device *adev);
 	void (*sw_fini)(struct amdgpu_device *adev);
+	void (*hw_init)(struct amdgpu_device *adev);
 	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
 				      bool enable);
 	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index b241f61..ac108fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -37,6 +37,7 @@
 #include "df_v3_6.h"
 #include "df_v4_3.h"
 #include "df_v4_6_2.h"
+#include "df_v4_15.h"
 #include "nbio_v6_1.h"
 #include "nbio_v7_0.h"
 #include "nbio_v7_4.h"
@@ -2803,6 +2804,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(4, 6, 2):
 		adev->df.funcs = &df_v4_6_2_funcs;
 		break;
+	case IP_VERSION(4, 15, 0):
+	case IP_VERSION(4, 15, 1):
+		adev->df.funcs = &df_v4_15_funcs;
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 78089f2..094498a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -116,9 +116,10 @@
  * - 3.55.0 - Add AMDGPU_INFO_GPUVM_FAULT query
  * - 3.56.0 - Update IB start address and size alignment for decode and encode
  * - 3.57.0 - Compute tunneling on GFX10+
+ * - 3.58.0 - Add GFX12 DCC support
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	57
+#define KMS_DRIVER_MINOR	58
 #define KMS_DRIVER_PATCHLEVEL	0
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 800cc7a..189574d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1591,6 +1591,66 @@ static void psp_ras_ta_check_status(struct psp_context *psp)
 	}
 }
 
+static int psp_ras_send_cmd(struct psp_context *psp,
+		enum ras_command cmd_id, void *in, void *out)
+{
+	struct ta_ras_shared_memory *ras_cmd;
+	uint32_t cmd = cmd_id;
+	int ret = 0;
+
+	if (!in)
+		return -EINVAL;
+
+	mutex_lock(&psp->ras_context.mutex);
+	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
+	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+
+	switch (cmd) {
+	case TA_RAS_COMMAND__ENABLE_FEATURES:
+	case TA_RAS_COMMAND__DISABLE_FEATURES:
+		memcpy(&ras_cmd->ras_in_message,
+			in, sizeof(ras_cmd->ras_in_message));
+		break;
+	case TA_RAS_COMMAND__TRIGGER_ERROR:
+		memcpy(&ras_cmd->ras_in_message.trigger_error,
+			in, sizeof(ras_cmd->ras_in_message.trigger_error));
+		break;
+	case TA_RAS_COMMAND__QUERY_ADDRESS:
+		memcpy(&ras_cmd->ras_in_message.address,
+			in, sizeof(ras_cmd->ras_in_message.address));
+		break;
+	default:
+		dev_err(psp->adev->dev, "Invalid ras cmd id: %u\n", cmd);
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	ras_cmd->cmd_id = cmd;
+	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+
+	switch (cmd) {
+	case TA_RAS_COMMAND__TRIGGER_ERROR:
+		if (!ret && out)
+			memcpy(out, &ras_cmd->ras_status, sizeof(ras_cmd->ras_status));
+		break;
+	case TA_RAS_COMMAND__QUERY_ADDRESS:
+		if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
+			ret = -EINVAL;
+		else if (out)
+			memcpy(out,
+				&ras_cmd->ras_out_message.address,
+				sizeof(ras_cmd->ras_out_message.address));
+		break;
+	default:
+		break;
+	}
+
+err_out:
+	mutex_unlock(&psp->ras_context.mutex);
+
+	return ret;
+}
+
 int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
 	struct ta_ras_shared_memory *ras_cmd;
@@ -1632,23 +1692,15 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 int psp_ras_enable_features(struct psp_context *psp,
 		union ta_ras_cmd_input *info, bool enable)
 {
-	struct ta_ras_shared_memory *ras_cmd;
+	enum ras_command cmd_id;
 	int ret;
 
-	if (!psp->ras_context.context.initialized)
+	if (!psp->ras_context.context.initialized || !info)
 		return -EINVAL;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
-
-	if (enable)
-		ras_cmd->cmd_id = TA_RAS_COMMAND__ENABLE_FEATURES;
-	else
-		ras_cmd->cmd_id = TA_RAS_COMMAND__DISABLE_FEATURES;
-
-	ras_cmd->ras_in_message = *info;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+	cmd_id = enable ?
+		TA_RAS_COMMAND__ENABLE_FEATURES : TA_RAS_COMMAND__DISABLE_FEATURES;
+	ret = psp_ras_send_cmd(psp, cmd_id, info, NULL);
 	if (ret)
 		return -EINVAL;
 
@@ -1672,6 +1724,8 @@ int psp_ras_terminate(struct psp_context *psp)
 
 	psp->ras_context.context.initialized = false;
 
+	mutex_destroy(&psp->ras_context.mutex);
+
 	return ret;
 }
 
@@ -1756,9 +1810,10 @@ int psp_ras_initialize(struct psp_context *psp)
 
 	ret = psp_ta_load(psp, &psp->ras_context.context);
 
-	if (!ret && !ras_cmd->ras_status)
+	if (!ret && !ras_cmd->ras_status) {
 		psp->ras_context.context.initialized = true;
-	else {
+		mutex_init(&psp->ras_context.mutex);
+	} else {
 		if (ras_cmd->ras_status)
 			dev_warn(adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
 
@@ -1772,12 +1827,12 @@ int psp_ras_initialize(struct psp_context *psp)
 int psp_ras_trigger_error(struct psp_context *psp,
 			  struct ta_ras_trigger_error_input *info, uint32_t instance_mask)
 {
-	struct ta_ras_shared_memory *ras_cmd;
 	struct amdgpu_device *adev = psp->adev;
 	int ret;
 	uint32_t dev_mask;
+	uint32_t ras_status = 0;
 
-	if (!psp->ras_context.context.initialized)
+	if (!psp->ras_context.context.initialized || !info)
 		return -EINVAL;
 
 	switch (info->block_id) {
@@ -1801,13 +1856,8 @@ int psp_ras_trigger_error(struct psp_context *psp,
 	dev_mask &= AMDGPU_RAS_INST_MASK;
 	info->sub_block_index |= dev_mask;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
-
-	ras_cmd->cmd_id = TA_RAS_COMMAND__TRIGGER_ERROR;
-	ras_cmd->ras_in_message.trigger_error = *info;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+	ret = psp_ras_send_cmd(psp,
+			TA_RAS_COMMAND__TRIGGER_ERROR, info, &ras_status);
 	if (ret)
 		return -EINVAL;
 
@@ -1817,9 +1867,9 @@ int psp_ras_trigger_error(struct psp_context *psp,
 	if (amdgpu_ras_intr_triggered())
 		return 0;
 
-	if (ras_cmd->ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
+	if (ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
 		return -EACCES;
-	else if (ras_cmd->ras_status)
+	else if (ras_status)
 		return -EINVAL;
 
 	return 0;
@@ -1829,25 +1879,16 @@ int psp_ras_query_address(struct psp_context *psp,
 			  struct ta_ras_query_address_input *addr_in,
 			  struct ta_ras_query_address_output *addr_out)
 {
-	struct ta_ras_shared_memory *ras_cmd;
 	int ret;
 
-	if (!psp->ras_context.context.initialized)
+	if (!psp->ras_context.context.initialized ||
+		!addr_in || !addr_out)
 		return -EINVAL;
 
-	ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
-	memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+	ret = psp_ras_send_cmd(psp,
+			TA_RAS_COMMAND__QUERY_ADDRESS, addr_in, addr_out);
 
-	ras_cmd->cmd_id = TA_RAS_COMMAND__QUERY_ADDRESS;
-	ras_cmd->ras_in_message.address = *addr_in;
-
-	ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
-	if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
-		return -EINVAL;
-
-	*addr_out = ras_cmd->ras_out_message.address;
-
-	return 0;
+	return ret;
 }
 // ras end
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 3635303..74a9651 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -200,6 +200,7 @@ struct psp_xgmi_context {
 struct psp_ras_context {
 	struct ta_context		context;
 	struct amdgpu_ras		*ras;
+	struct mutex			mutex;
 };
 
 #define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 8e8afbd..0c85600 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -348,6 +348,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 
 	context->session_id = ta_id;
 
+	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
 		goto err_free_shared_buf;
@@ -366,6 +367,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		ret = -EFAULT;
 
 err_free_shared_buf:
+	mutex_unlock(&psp->ras_context.mutex);
 	kfree(shared_buf);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index eae0a55..aab8077 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1011,6 +1011,9 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 
 uint32_t amdgpu_ras_eeprom_max_record_count(struct amdgpu_ras_eeprom_control *control)
 {
+	/* get available eeprom table version first before eeprom table init */
+	amdgpu_ras_set_eeprom_table_version(control);
+
 	if (control->tbl_hdr.version == RAS_TABLE_VER_V2_1)
 		return RAS_MAX_RECORD_COUNT_V2_1;
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 8d65b09..43f44cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -147,6 +147,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		}
 	}
 
+	/* from vcn4 and above, only unified queue is used */
+	adev->vcn.using_unified_queue =
+		amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0);
+
 	hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data;
 	adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
@@ -275,18 +279,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	return 0;
 }
 
-/* from vcn4 and above, only unified queue is used */
-static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	bool ret = false;
-
-	if (amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0))
-		ret = true;
-
-	return ret;
-}
-
 bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
 {
 	bool ret = false;
@@ -397,7 +389,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+		/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+		    !adev->vcn.using_unified_queue) {
 			struct dpg_pause_state new_state;
 
 			if (fence[j] ||
@@ -443,7 +437,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 	       AMD_PG_STATE_UNGATE);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+	    !adev->vcn.using_unified_queue) {
 		struct dpg_pause_state new_state;
 
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
@@ -469,8 +465,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
+
+	/* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
 	if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
-		ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+	    ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
+	    !adev->vcn.using_unified_queue)
 		atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
 
 	atomic_dec(&ring->adev->vcn.total_submission_cnt);
@@ -724,12 +724,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr);
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	uint32_t *ib_checksum;
 	uint32_t ib_pack_in_dw;
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -742,7 +741,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	ib->length_dw = 0;
 
 	/* single queue headers */
-	if (sq) {
+	if (adev->vcn.using_unified_queue) {
 		ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
 						+ 4 + 2; /* engine info + decoding ib in dw */
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
@@ -761,7 +760,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -851,15 +850,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 					 struct dma_fence **fence)
 {
 	unsigned int ib_size_dw = 16;
+	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
 	uint32_t *ib_checksum = NULL;
 	uint64_t addr;
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -873,7 +872,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 
 	ib->length_dw = 0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -895,7 +894,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
@@ -918,15 +917,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 					  struct dma_fence **fence)
 {
 	unsigned int ib_size_dw = 16;
+	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
 	uint32_t *ib_checksum = NULL;
 	uint64_t addr;
-	bool sq = amdgpu_vcn_using_unified_queue(ring);
 	int i, r;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_size_dw += 8;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -940,7 +939,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
 	ib->length_dw = 0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
 	ib->ptr[ib->length_dw++] = 0x00000018;
@@ -962,7 +961,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (sq)
+	if (adev->vcn.using_unified_queue)
 		amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
 	r = amdgpu_job_submit_direct(job, ring, &f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 9f06def..1a5439a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -329,6 +329,7 @@ struct amdgpu_vcn {
 
 	uint16_t inst_mask;
 	uint8_t	num_inst_per_aid;
+	bool using_unified_queue;
 };
 
 struct amdgpu_fw_shared_rb_ptrs_struct {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 3abfa66..a060c28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -434,7 +434,7 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	if (!vm)
 		return result;
 
-	result += vm->generation;
+	result += lower_32_bits(vm->generation);
 	/* Add one if the page tables will be re-generated on next CS */
 	if (drm_sched_entity_error(&vm->delayed))
 		++result;
@@ -463,13 +463,14 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		       int (*validate)(void *p, struct amdgpu_bo *bo),
 		       void *param)
 {
+	uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
 	struct amdgpu_vm_bo_base *bo_base;
 	struct amdgpu_bo *shadow;
 	struct amdgpu_bo *bo;
 	int r;
 
-	if (drm_sched_entity_error(&vm->delayed)) {
-		++vm->generation;
+	if (vm->generation != new_vm_generation) {
+		vm->generation = new_vm_generation;
 		amdgpu_vm_bo_reset_state_machine(vm);
 		amdgpu_vm_fini_entities(vm);
 		r = amdgpu_vm_init_entities(adev, vm);
@@ -2439,7 +2440,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	vm->last_update = dma_fence_get_stub();
 	vm->last_unlocked = dma_fence_get_stub();
 	vm->last_tlb_flush = dma_fence_get_stub();
-	vm->generation = 0;
+	vm->generation = amdgpu_vm_generation(adev, NULL);
 
 	mutex_init(&vm->eviction_lock);
 	vm->evicting = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v4_15.c b/drivers/gpu/drm/amd/amdgpu/df_v4_15.c
new file mode 100644
index 0000000..2a573e3
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/df_v4_15.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2024 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "df_v4_15.h"
+
+#include "df/df_4_15_offset.h"
+#include "df/df_4_15_sh_mask.h"
+
+static void df_v4_15_hw_init(struct amdgpu_device *adev)
+{
+	if (adev->have_atomics_support) {
+		uint32_t tmp;
+		uint32_t dis_lcl_proc = (1 <<  1 |
+					1 <<  2 |
+					1 << 13);
+
+		tmp = RREG32_SOC15(DF, 0, regNCSConfigurationRegister1);
+		tmp |= (dis_lcl_proc << NCSConfigurationRegister1__DisIntAtomicsLclProcessing__SHIFT);
+		WREG32_SOC15(DF, 0, regNCSConfigurationRegister1, tmp);
+	}
+}
+
+const struct amdgpu_df_funcs df_v4_15_funcs = {
+	.hw_init = df_v4_15_hw_init
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v4_15.h b/drivers/gpu/drm/amd/amdgpu/df_v4_15.h
new file mode 100644
index 0000000..dddf242
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/df_v4_15.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright 2024 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __DF_V4_15_H__
+#define __DF_V4_15_H__
+
+extern const struct amdgpu_df_funcs df_v4_15_funcs;
+
+#endif /* __DF_V4_15_H__ */
+
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 04d8966..ad524dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -32,6 +32,9 @@
 #include "vcn/vcn_4_0_3_sh_mask.h"
 #include "ivsrcid/vcn/irqsrcs_vcn_4_0.h"
 
+#define NORMALIZE_JPEG_REG_OFFSET(offset) \
+		(offset & 0x1FFFF)
+
 enum jpeg_engin_status {
 	UVD_PGFSM_STATUS__UVDJ_PWR_ON  = 0,
 	UVD_PGFSM_STATUS__UVDJ_PWR_OFF = 2,
@@ -621,6 +624,13 @@ static uint64_t jpeg_v4_0_3_dec_ring_get_wptr(struct amdgpu_ring *ring)
 			ring->pipe ? (0x40 * ring->pipe - 0xc80) : 0);
 }
 
+static void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	/* JPEG engine access for HDP flush doesn't work when RRMT is enabled.
+	 * This is a workaround to avoid any HDP flush through JPEG ring.
+	 */
+}
+
 /**
  * jpeg_v4_0_3_dec_ring_set_wptr - set write pointer
  *
@@ -817,7 +827,13 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
 void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 				uint32_t val, uint32_t mask)
 {
-	uint32_t reg_offset = (reg << 2);
+	uint32_t reg_offset;
+
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_JPEG_REG_OFFSET(reg);
+
+	reg_offset = (reg << 2);
 
 	amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
@@ -858,7 +874,13 @@ void jpeg_v4_0_3_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
 {
-	uint32_t reg_offset = (reg << 2);
+	uint32_t reg_offset;
+
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_JPEG_REG_OFFSET(reg);
+
+	reg_offset = (reg << 2);
 
 	amdgpu_ring_write(ring,	PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
@@ -1072,6 +1094,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
 	.emit_ib = jpeg_v4_0_3_dec_ring_emit_ib,
 	.emit_fence = jpeg_v4_0_3_dec_ring_emit_fence,
 	.emit_vm_flush = jpeg_v4_0_3_dec_ring_emit_vm_flush,
+	.emit_hdp_flush = jpeg_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
 	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
 	.insert_nop = jpeg_v4_0_3_dec_ring_nop,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index cc9e961..af1e901 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -176,6 +176,14 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
 		DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
+		/* SDMA seems to miss doorbells sometimes when powergating kicks in.
+		 * Updating the wptr directly will wake it. This is only safe because
+		 * we disallow gfxoff in begin_use() and then allow it again in end_use().
+		 */
+		WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
+		       lower_32_bits(ring->wptr << 2));
+		WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
+		       upper_32_bits(ring->wptr << 2));
 	} else {
 		DRM_DEBUG("Not using doorbell -- "
 				"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
@@ -1647,6 +1655,10 @@ static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring)
 	 * but it shouldn't hurt for other parts since
 	 * this GFXOFF will be disallowed anyway when SDMA is
 	 * active, this just makes it explicit.
+	 * sdma_v5_2_ring_set_wptr() takes advantage of this
+	 * to update the wptr because sometimes SDMA seems to miss
+	 * doorbells when entering PG.  If you remove this, update
+	 * sdma_v5_2_ring_set_wptr() as well!
 	 */
 	amdgpu_gfx_off_ctrl(adev, false);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
index 04c797d..0af6489 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
@@ -91,7 +91,7 @@ static int smu_v13_0_10_mode2_suspend_ip(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
-	return r;
+	return 0;
 }
 
 static int
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index d27fb4e..7d641d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -484,6 +484,10 @@ static int soc24_common_hw_init(void *handle)
 	 */
 	if (adev->nbio.funcs->remap_hdp_registers)
 		adev->nbio.funcs->remap_hdp_registers(adev);
+
+	if (adev->df.funcs->hw_init)
+		adev->df.funcs->hw_init(adev);
+
 	/* enable the doorbell aperture */
 	soc24_enable_doorbell_aperture(adev, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index f6d96a4..776c539 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1045,6 +1045,9 @@ static int vcn_v4_0_start(struct amdgpu_device *adev)
 		amdgpu_dpm_enable_uvd(adev, true);
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
@@ -1498,6 +1501,9 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
 	int i, r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index f53054e..9bae955 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -45,6 +45,9 @@
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
 
+#define NORMALIZE_VCN_REG_OFFSET(offset) \
+		(offset & 0x1FFFF)
+
 static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev);
@@ -1375,6 +1378,50 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
 				    regUVD_RB_WPTR);
 }
 
+static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
+	amdgpu_ring_write(ring, reg << 2);
+	amdgpu_ring_write(ring, mask);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	reg << 2);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned int vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub];
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for reg writes */
+	vcn_v4_0_3_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
+					vmid * hub->ctx_addr_distance,
+					lower_32_bits(pd_addr), 0xffffffff);
+}
+
+static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	/* VCN engine access for HDP flush doesn't work when RRMT is enabled.
+	 * This is a workaround to avoid any HDP flush through VCN ring.
+	 */
+}
+
 /**
  * vcn_v4_0_3_unified_ring_set_wptr - set enc write pointer
  *
@@ -1414,7 +1461,8 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
 	.emit_ib = vcn_v2_0_enc_ring_emit_ib,
 	.emit_fence = vcn_v2_0_enc_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush,
+	.emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
+	.emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_vcn_enc_ring_test_ring,
 	.test_ib = amdgpu_vcn_unified_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
@@ -1422,8 +1470,8 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_vcn_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_enc_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait,
+	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
+	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index f45495d..8d75061 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -958,6 +958,9 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev)
 		amdgpu_dpm_enable_uvd(adev, true);
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
@@ -1162,6 +1165,9 @@ static int vcn_v4_0_5_stop(struct amdgpu_device *adev)
 	int i, r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 070b566..68c97fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -721,6 +721,9 @@ static int vcn_v5_0_0_start(struct amdgpu_device *adev)
 		amdgpu_dpm_enable_uvd(adev, true);
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
@@ -898,6 +901,9 @@ static int vcn_v5_0_0_stop(struct amdgpu_device *adev)
 	int i, r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
 		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 5fd1b6b..2d7755e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -137,6 +137,13 @@ struct vblank_control_work {
 	bool enable;
 };
 
+/**
+ * struct idle_workqueue - Work data for periodic action in idle
+ * @work: Kernel work data for the work event
+ * @dm: amdgpu display manager device
+ * @enable: true if idle worker is enabled
+ * @running: true if idle worker is running
+ */
 struct idle_workqueue {
 	struct work_struct work;
 	struct amdgpu_display_manager *dm;
@@ -502,6 +509,12 @@ struct amdgpu_display_manager {
 	 * Deferred work for vblank control events.
 	 */
 	struct workqueue_struct *vblank_control_workqueue;
+
+	/**
+	 * @idle_workqueue:
+	 *
+	 * Periodic work for idle events.
+	 */
 	struct idle_workqueue *idle_workqueue;
 
 	struct drm_atomic_state *cached_state;
@@ -587,7 +600,9 @@ struct amdgpu_display_manager {
 	 */
 	struct mutex dpia_aux_lock;
 
-	/*
+	/**
+	 * @bb_from_dmub:
+	 *
 	 * Bounding box data read from dmub during early initialization for DCN4+
 	 */
 	struct dml2_soc_bb *bb_from_dmub;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index 067f655..ccbb15f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -143,7 +143,8 @@ const struct dc_plane_status *dc_plane_get_status(
 		if (pipe_ctx->plane_state != plane_state)
 			continue;
 
-		pipe_ctx->plane_state->status.is_flip_pending = false;
+		if (pipe_ctx->plane_state)
+			pipe_ctx->plane_state->status.is_flip_pending = false;
 
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_standalone_libraries/lib_float_math.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_standalone_libraries/lib_float_math.c
index defe134..e73579f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_standalone_libraries/lib_float_math.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_standalone_libraries/lib_float_math.c
@@ -64,8 +64,6 @@ double math_ceil(const double arg)
 
 double math_ceil2(const double arg, const double significance)
 {
-	ASSERT(significance != 0);
-
 	return ((int)(arg / significance + 0.99999)) * significance;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 9ac7fc7..0150f25 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -147,16 +147,28 @@ struct cnv_color_keyer_params {
 	int color_keyer_blue_high;
 };
 
-/* new for dcn2: set the 8bit alpha values based on the 2 bit alpha
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT0   default: 0b00000000
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT1   default: 0b01010101
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT2   default: 0b10101010
- *ALPHA_2BIT_LUT. ALPHA_2BIT_LUT3   default: 0b11111111
+/**
+ * struct cnv_alpha_2bit_lut - Set the 8bit alpha values based on the 2 bit alpha
  */
 struct cnv_alpha_2bit_lut {
+	/**
+	* @lut0: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT0. Default: 0b00000000
+	*/
 	int lut0;
+
+	/**
+	 * @lut1: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT1. Default: 0b01010101
+	 */
 	int lut1;
+
+	/**
+	 * @lut2: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT2. Default: 0b10101010
+	 */
 	int lut2;
+
+	/**
+	 * @lut3: ALPHA_2BIT_LUT. ALPHA_2BIT_LUT3. Default: 0b11111111
+	 */
 	int lut3;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 40a9b34..3a89cc0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -1039,6 +1039,20 @@ struct mpc_funcs {
 	*/
 	void (*program_lut_mode)(struct mpc *mpc, const enum MCM_LUT_ID id, const enum MCM_LUT_XABLE xable,
 			bool lut_bank_a, int mpcc_id);
+	/**
+	* @program_3dlut_size:
+	*
+	* Program 3D LUT size.
+	*
+	* Parameters:
+	* - [in/out] mpc - MPC context.
+	* - [in] is_17x17x17 - is 3dlut 17x17x17
+	* - [in] mpcc_id
+	*
+	* Return:
+	*
+	* void
+	*/
 	void (*program_3dlut_size)(struct mpc *mpc, bool is_17x17x17, int mpcc_id);
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 127fb1a5..747679c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -205,9 +205,24 @@ struct gamma_coefficients {
 	struct fixed31_32 user_brightness;
 };
 
+/**
+ * struct pwl_float_data - Fixed point RGB color
+ */
 struct pwl_float_data {
+	/**
+	 * @r: Component Red.
+	 */
 	struct fixed31_32 r;
+
+	/**
+	 * @g: Component Green.
+	 */
+
 	struct fixed31_32 g;
+
+	/**
+	 * @b: Component Blue.
+	 */
 	struct fixed31_32 b;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
index 50459d7a..b76737b 100644
--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
+++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
@@ -26,6 +26,16 @@
 #include "core_types.h"
 #include "link_enc_cfg.h"
 
+/**
+ * DOC: overview
+ *
+ * Display Input Output (DIO), is the display input and output unit in DCN. It
+ * includes output encoders to support different display output, like
+ * DisplayPort, HDMI, DVI interface, and others. It also includes the control
+ * and status channels for these interfaces.
+ */
+
+
 void set_dio_throttled_vcp_size(struct pipe_ctx *pipe_ctx,
 		struct fixed31_32 throttled_vcp_size)
 {
@@ -254,12 +264,31 @@ static const struct link_hwss dio_link_hwss = {
 	},
 };
 
+/**
+ * can_use_dio_link_hwss - Check if the link_hwss is accessible
+ *
+ * @link: Reference a link struct containing one or more sinks and the
+ *	  connective status.
+ * @link_res: Mappable hardware resource used to enable a link.
+ *
+ * Returns:
+ * Return true if the link encoder is accessible from link.
+ */
 bool can_use_dio_link_hwss(const struct dc_link *link,
 		const struct link_resource *link_res)
 {
 	return link->link_enc != NULL;
 }
 
+/**
+ * get_dio_link_hwss - Return link_hwss reference
+ *
+ * This function behaves like a get function to return the link_hwss populated
+ * in the link_hwss_dio.c file.
+ *
+ * Returns:
+ * Return the reference to the filled struct of link_hwss.
+ */
 const struct link_hwss *get_dio_link_hwss(void)
 {
 	return &dio_link_hwss;
diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
index a1f72fe..45f0e09 100644
--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
+++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.h
@@ -23,15 +23,6 @@
  *
  */
 
-/**
- * DOC: overview
- *
- * Display Input Output (DIO), is the display input and output unit in DCN. It
- * includes output encoders to support different display output, like
- * DisplayPort, HDMI, DVI interface, and others. It also includes the control
- * and status channels for these interfaces.
- */
-
 #ifndef __LINK_HWSS_DIO_H__
 #define __LINK_HWSS_DIO_H__
 
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
index 336488c..9442787 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
@@ -945,19 +945,10 @@ void optc1_set_drr(
 				OTG_FORCE_LOCK_ON_EVENT, 0,
 				OTG_SET_V_TOTAL_MIN_MASK_EN, 0,
 				OTG_SET_V_TOTAL_MIN_MASK, 0);
-
-		// Setup manual flow control for EOF via TRIG_A
-		optc->funcs->setup_manual_trigger(optc);
-
-	} else {
-		REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
-				OTG_SET_V_TOTAL_MIN_MASK, 0,
-				OTG_V_TOTAL_MIN_SEL, 0,
-				OTG_V_TOTAL_MAX_SEL, 0,
-				OTG_FORCE_LOCK_ON_EVENT, 0);
-
-		optc->funcs->set_vtotal_min_max(optc, 0, 0);
 	}
+
+	// Setup manual flow control for EOF via TRIG_A
+	optc->funcs->setup_manual_trigger(optc);
 }
 
 void optc1_set_vtotal_min_max(struct timing_generator *optc, int vtotal_min, int vtotal_max)
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
index 43417cf..b469498 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
@@ -453,6 +453,16 @@ void optc2_setup_manual_trigger(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	/* Set the min/max selectors unconditionally so that
+	 * DMCUB fw may change OTG timings when necessary
+	 * TODO: Remove the w/a after fixing the issue in DMCUB firmware
+	 */
+	REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
+				 OTG_V_TOTAL_MIN_SEL, 1,
+				 OTG_V_TOTAL_MAX_SEL, 1,
+				 OTG_FORCE_LOCK_ON_EVENT, 0,
+				 OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */
+
 	REG_SET_8(OTG_TRIGA_CNTL, 0,
 			OTG_TRIGA_SOURCE_SELECT, 21,
 			OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst,
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_offset.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_offset.h
new file mode 100644
index 0000000..c2b0097
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_offset.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2024  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _df_4_15_OFFSET_HEADER
+#define _df_4_15_OFFSET_HEADER
+
+#define regNCSConfigurationRegister1               0x0901
+#define regNCSConfigurationRegister1_BASE_IDX           4
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_sh_mask.h
new file mode 100644
index 0000000..9868a9c
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_4_15_sh_mask.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2024  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _df_4_15_SH_MASK_HEADER
+#define _df_4_15_SH_MASK_HEADER
+
+#define NCSConfigurationRegister1__DisIntAtomicsLclProcessing__SHIFT         0x3
+#define NCSConfigurationRegister1__DisIntAtomicsLclProcessing_MASK    0x0003FFF8L
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fb8643d..9d7454b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1924,20 +1924,12 @@ static int smu_disable_dpms(struct smu_context *smu)
 	}
 
 	/*
-	 * For SMU 13.0.4/11 and 14.0.0, PMFW will handle the features disablement properly
+	 * For GFX11 and subsequent APUs, PMFW will handle the features disablement properly
 	 * for gpu reset and S0i3 cases. Driver involvement is unnecessary.
 	 */
-	if (amdgpu_in_reset(adev) || adev->in_s0ix) {
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 4):
-		case IP_VERSION(13, 0, 11):
-		case IP_VERSION(14, 0, 0):
-		case IP_VERSION(14, 0, 1):
-			return 0;
-		default:
-			break;
-		}
-	}
+	if (IP_VERSION_MAJ(amdgpu_ip_version(adev, GC_HWIP, 0)) >= 11 &&
+	    smu->is_apu && (amdgpu_in_reset(adev) || adev->in_s0ix))
+		return 0;
 
 	/*
 	 * For gpu reset, runpm and hibernation through BACO,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 5d47d58..8798ebf 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -69,6 +69,9 @@
 #define SMU_14_0_0_UMD_PSTATE_SOCCLK			678
 #define SMU_14_0_0_UMD_PSTATE_FCLK			1800
 
+#define SMU_14_0_4_UMD_PSTATE_GFXCLK			938
+#define SMU_14_0_4_UMD_PSTATE_SOCCLK			938
+
 #define FEATURE_MASK(feature) (1ULL << feature)
 #define SMC_DPM_FEATURE ( \
 	FEATURE_MASK(FEATURE_CCLK_DPM_BIT) | \
@@ -1296,19 +1299,28 @@ static int smu_v14_0_common_get_dpm_profile_freq(struct smu_context *smu,
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_GFXCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			clk_limit = SMU_14_0_4_UMD_PSTATE_GFXCLK;
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_GFXCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &clk_limit);
 		else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &clk_limit, NULL);
 		break;
 	case SMU_SOCCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_SOCCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			clk_limit = SMU_14_0_4_UMD_PSTATE_SOCCLK;
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_SOCCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &clk_limit);
 		break;
 	case SMU_FCLK:
-		clk_limit = SMU_14_0_0_UMD_PSTATE_FCLK;
+		if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 4))
+			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &clk_limit);
+		else
+			clk_limit = SMU_14_0_0_UMD_PSTATE_FCLK;
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &clk_limit);
 		else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK)
diff --git a/drivers/gpu/drm/display/drm_dp_aux_bus.c b/drivers/gpu/drm/display/drm_dp_aux_bus.c
index 5afc26b..d810529 100644
--- a/drivers/gpu/drm/display/drm_dp_aux_bus.c
+++ b/drivers/gpu/drm/display/drm_dp_aux_bus.c
@@ -36,7 +36,7 @@ struct dp_aux_ep_device_with_data {
  *
  * Return: True if this driver matches this device; false otherwise.
  */
-static int dp_aux_ep_match(struct device *dev, struct device_driver *drv)
+static int dp_aux_ep_match(struct device *dev, const struct device_driver *drv)
 {
 	return !!of_match_device(drv->of_match_table, dev);
 }
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c
index d021497..3969dc5 100644
--- a/drivers/gpu/drm/drm_color_mgmt.c
+++ b/drivers/gpu/drm/drm_color_mgmt.c
@@ -532,7 +532,7 @@ int drm_plane_create_color_properties(struct drm_plane *plane,
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_property *prop;
-	struct drm_prop_enum_list enum_list[max_t(int, DRM_COLOR_ENCODING_MAX,
+	struct drm_prop_enum_list enum_list[MAX_T(int, DRM_COLOR_ENCODING_MAX,
 						       DRM_COLOR_RANGE_MAX)];
 	int i, len;
 
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index a471c46..969cfd5 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -48,7 +48,7 @@
  * subset of the MIPI DCS command set.
  */
 
-static int mipi_dsi_device_match(struct device *dev, struct device_driver *drv)
+static int mipi_dsi_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 3903f6e..59f11af 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -5314,6 +5314,8 @@ static int intel_dp_retrain_link(struct intel_encoder *encoder,
 		const struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
+		intel_dp->link_trained = false;
+
 		intel_dp_check_frl_training(intel_dp);
 		intel_dp_pcon_dsc_configure(intel_dp, crtc_state);
 		intel_dp_start_link_train(NULL, intel_dp, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 1bc4ef8..d044c8e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -117,10 +117,24 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable)
 	return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1;
 }
 
-static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+static bool intel_dp_lttpr_transparent_mode_enabled(struct intel_dp *intel_dp)
+{
+	return intel_dp->lttpr_common_caps[DP_PHY_REPEATER_MODE -
+					   DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] ==
+		DP_PHY_REPEATER_MODE_TRANSPARENT;
+}
+
+/*
+ * Read the LTTPR common capabilities and switch the LTTPR PHYs to
+ * non-transparent mode if this is supported. Preserve the
+ * transparent/non-transparent mode on an active link.
+ *
+ * Return the number of detected LTTPRs in non-transparent mode or 0 if the
+ * LTTPRs are in transparent mode or the detection failed.
+ */
+static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
 	int lttpr_count;
-	int i;
 
 	if (!intel_dp_read_lttpr_common_caps(intel_dp, dpcd))
 		return 0;
@@ -135,6 +149,19 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI
 		return 0;
 
 	/*
+	 * Don't change the mode on an active link, to prevent a loss of link
+	 * synchronization. See DP Standard v2.0 3.6.7. about the LTTPR
+	 * resetting its internal state when the mode is changed from
+	 * non-transparent to transparent.
+	 */
+	if (intel_dp->link_trained) {
+		if (lttpr_count < 0 || intel_dp_lttpr_transparent_mode_enabled(intel_dp))
+			goto out_reset_lttpr_count;
+
+		return lttpr_count;
+	}
+
+	/*
 	 * See DP Standard v2.0 3.6.6.1. about the explicit disabling of
 	 * non-transparent mode and the disable->enable non-transparent mode
 	 * sequence.
@@ -154,11 +181,25 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI
 		       "Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n");
 
 		intel_dp_set_lttpr_transparent_mode(intel_dp, true);
-		intel_dp_reset_lttpr_count(intel_dp);
 
-		return 0;
+		goto out_reset_lttpr_count;
 	}
 
+	return lttpr_count;
+
+out_reset_lttpr_count:
+	intel_dp_reset_lttpr_count(intel_dp);
+
+	return 0;
+}
+
+static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	int lttpr_count;
+	int i;
+
+	lttpr_count = intel_dp_init_lttpr_phys(intel_dp, dpcd);
+
 	for (i = 0; i < lttpr_count; i++)
 		intel_dp_read_lttpr_phy_caps(intel_dp, dpcd, DP_PHY_LTTPR(i));
 
@@ -1482,10 +1523,10 @@ void intel_dp_start_link_train(struct intel_atomic_state *state,
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &dig_port->base;
 	bool passed;
-
 	/*
-	 * TODO: Reiniting LTTPRs here won't be needed once proper connector
-	 * HW state readout is added.
+	 * Reinit the LTTPRs here to ensure that they are switched to
+	 * non-transparent mode. During an earlier LTTPR detection this
+	 * could've been prevented by an active link.
 	 */
 	int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2182943..72090f5 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3315,11 +3315,7 @@ static void remove_from_engine(struct i915_request *rq)
 
 static bool can_preempt(struct intel_engine_cs *engine)
 {
-	if (GRAPHICS_VER(engine->i915) > 8)
-		return true;
-
-	/* GPGPU on bdw requires extra w/a; not implemented */
-	return engine->class != RENDER_CLASS;
+	return GRAPHICS_VER(engine->i915) > 8;
 }
 
 static void kick_execlists(const struct i915_request *rq, int prio)
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 172dfa7..d40ee1b 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -368,8 +368,10 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
 			goto out_cleanup;
 		}
 
-		mem->id = i;
-		i915->mm.regions[i] = mem;
+		if (mem) { /* Skip on non-fatal errors */
+			mem->id = i;
+			i915->mm.regions[i] = mem;
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(i915->mm.regions); i++) {
diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c
index 5c3b2d5..1a0cb7a 100644
--- a/drivers/gpu/drm/imagination/pvr_drv.c
+++ b/drivers/gpu/drm/imagination/pvr_drv.c
@@ -1451,8 +1451,7 @@ pvr_probe(struct platform_device *plat_dev)
 	return err;
 }
 
-static int
-pvr_remove(struct platform_device *plat_dev)
+static void pvr_remove(struct platform_device *plat_dev)
 {
 	struct drm_device *drm_dev = platform_get_drvdata(plat_dev);
 	struct pvr_device *pvr_dev = to_pvr_device(drm_dev);
@@ -1469,8 +1468,6 @@ pvr_remove(struct platform_device *plat_dev)
 	pvr_watchdog_fini(pvr_dev);
 	pvr_queue_device_fini(pvr_dev);
 	pvr_context_device_fini(pvr_dev);
-
-	return 0;
 }
 
 static const struct of_device_id dt_match[] = {
@@ -1485,7 +1482,7 @@ static const struct dev_pm_ops pvr_pm_ops = {
 
 static struct platform_driver pvr_driver = {
 	.probe = pvr_probe,
-	.remove = pvr_remove,
+	.remove_new = pvr_remove,
 	.driver = {
 		.name = PVR_DRIVER_NAME,
 		.pm = &pvr_pm_ops,
diff --git a/drivers/gpu/drm/stm/lvds.c b/drivers/gpu/drm/stm/lvds.c
index bfc8cb1..2fa2c81 100644
--- a/drivers/gpu/drm/stm/lvds.c
+++ b/drivers/gpu/drm/stm/lvds.c
@@ -1186,15 +1186,13 @@ static int lvds_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int lvds_remove(struct platform_device *pdev)
+static void lvds_remove(struct platform_device *pdev)
 {
 	struct stm_lvds *lvds = platform_get_drvdata(pdev);
 
 	lvds_pixel_clk_unregister(lvds);
 
 	drm_bridge_remove(&lvds->lvds_bridge);
-
-	return 0;
 }
 
 static const struct of_device_id lvds_dt_ids[] = {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index a47f00b..5982941 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -265,7 +265,7 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	struct v3d_dev *v3d;
 	int ret;
 	u32 mmu_debug;
-	u32 ident1;
+	u32 ident1, ident3;
 	u64 mask;
 
 	v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm);
@@ -298,6 +298,9 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
 	WARN_ON(v3d->cores > 1); /* multicore not yet implemented */
 
+	ident3 = V3D_READ(V3D_HUB_IDENT3);
+	v3d->rev = V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPREV);
+
 	if (v3d->ver >= 71)
 		v3d->max_counters = V3D_V71_NUM_PERFCOUNTERS;
 	else if (v3d->ver >= 42)
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 099b962..49089ee 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -98,10 +98,12 @@ struct v3d_perfmon {
 struct v3d_dev {
 	struct drm_device drm;
 
-	/* Short representation (e.g. 33, 41) of the V3D tech version
-	 * and revision.
-	 */
+	/* Short representation (e.g. 33, 41) of the V3D tech version */
 	int ver;
+
+	/* Short representation (e.g. 5, 6) of the V3D tech revision */
+	int rev;
+
 	bool single_irq_line;
 
 	/* Different revisions of V3D have different total number of performance
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 03df37a..271a6d0 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -331,7 +331,8 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
 	struct v3d_bo *indirect = to_v3d_bo(indirect_csd->indirect);
 	struct drm_v3d_submit_csd *args = &indirect_csd->job->args;
-	u32 *wg_counts;
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 num_batches, *wg_counts;
 
 	v3d_get_bo_vaddr(bo);
 	v3d_get_bo_vaddr(indirect);
@@ -344,8 +345,17 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	args->cfg[0] = wg_counts[0] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[1] = wg_counts[1] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
 	args->cfg[2] = wg_counts[2] << V3D_CSD_CFG012_WG_COUNT_SHIFT;
-	args->cfg[4] = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
-		       (wg_counts[0] * wg_counts[1] * wg_counts[2]) - 1;
+
+	num_batches = DIV_ROUND_UP(indirect_csd->wg_size, 16) *
+		      (wg_counts[0] * wg_counts[1] * wg_counts[2]);
+
+	/* V3D 7.1.6 and later don't subtract 1 from the number of batches */
+	if (v3d->ver < 71 || (v3d->ver == 71 && v3d->rev < 6))
+		args->cfg[4] = num_batches - 1;
+	else
+		args->cfg[4] = num_batches;
+
+	WARN_ON(args->cfg[4] == ~0);
 
 	for (int i = 0; i < 3; i++) {
 		/* 0xffffffff indicates that the uniform rewrite is not needed */
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 03492fb..7610941 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -854,6 +854,13 @@ u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address)
 	return address & GENMASK_ULL(xe->info.va_bits - 1, 0);
 }
 
+static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
+{
+	struct xe_device *xe = arg;
+
+	xe_pm_runtime_put(xe);
+}
+
 /**
  * xe_device_declare_wedged - Declare device wedged
  * @xe: xe device instance
@@ -870,11 +877,21 @@ u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address)
  */
 void xe_device_declare_wedged(struct xe_device *xe)
 {
+	struct xe_gt *gt;
+	u8 id;
+
 	if (xe->wedged.mode == 0) {
 		drm_dbg(&xe->drm, "Wedged mode is forcibly disabled\n");
 		return;
 	}
 
+	if (drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe)) {
+		drm_err(&xe->drm, "Failed to register xe_device_wedged_fini clean-up. Although device is wedged.\n");
+		return;
+	}
+
+	xe_pm_runtime_get_noresume(xe);
+
 	if (!atomic_xchg(&xe->wedged.flag, 1)) {
 		xe->needs_flr_on_fini = true;
 		drm_err(&xe->drm,
@@ -883,4 +900,7 @@ void xe_device_declare_wedged(struct xe_device *xe)
 			"Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n",
 			dev_name(xe->drm.dev));
 	}
+
+	for_each_gt(gt, xe, id)
+		xe_gt_declare_wedged(gt);
 }
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 2d72cde..f36980a 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -118,7 +118,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
 	struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
 	struct drm_exec *exec = &vm_exec.exec;
-	u32 i, num_syncs = 0, num_ufence = 0;
+	u32 i, num_syncs, num_ufence = 0;
 	struct xe_sched_job *job;
 	struct xe_vm *vm;
 	bool write_locked, skip_retry = false;
@@ -156,15 +156,15 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	vm = q->vm;
 
-	for (i = 0; i < args->num_syncs; i++) {
-		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs++],
-					  &syncs_user[i], SYNC_PARSE_FLAG_EXEC |
+	for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
+		err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
+					  &syncs_user[num_syncs], SYNC_PARSE_FLAG_EXEC |
 					  (xe_vm_in_lr_mode(vm) ?
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
 			goto err_syncs;
 
-		if (xe_sync_is_ufence(&syncs[i]))
+		if (xe_sync_is_ufence(&syncs[num_syncs]))
 			num_ufence++;
 	}
 
@@ -325,8 +325,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (err == -EAGAIN && !skip_retry)
 		goto retry;
 err_syncs:
-	for (i = 0; i < num_syncs; i++)
-		xe_sync_entry_cleanup(&syncs[i]);
+	while (num_syncs--)
+		xe_sync_entry_cleanup(&syncs[num_syncs]);
 	kfree(syncs);
 err_exec_queue:
 	xe_exec_queue_put(q);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 0ba2e2d..31b2e64 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -904,3 +904,18 @@ struct xe_hw_engine *xe_gt_any_hw_engine(struct xe_gt *gt)
 
 	return NULL;
 }
+
+/**
+ * xe_gt_declare_wedged() - Declare GT wedged
+ * @gt: the GT object
+ *
+ * Wedge the GT which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_gt_declare_wedged(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, gt_to_xe(gt)->wedged.mode);
+
+	xe_uc_declare_wedged(&gt->uc);
+	xe_gt_tlb_invalidation_reset(gt);
+}
diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
index 1123fdf..8b1a502 100644
--- a/drivers/gpu/drm/xe/xe_gt.h
+++ b/drivers/gpu/drm/xe/xe_gt.h
@@ -37,6 +37,7 @@ struct xe_gt *xe_gt_alloc(struct xe_tile *tile);
 int xe_gt_init_hwconfig(struct xe_gt *gt);
 int xe_gt_init_early(struct xe_gt *gt);
 int xe_gt_init(struct xe_gt *gt);
+void xe_gt_declare_wedged(struct xe_gt *gt);
 int xe_gt_record_default_lrcs(struct xe_gt *gt);
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index db6c213..4699b78 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1543,6 +1543,7 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs)
 	u64 fair;
 
 	fair = div_u64(available, num_vfs);
+	fair = rounddown_pow_of_two(fair);	/* XXX: ttm_vram_mgr & drm_buddy limitation */
 	fair = ALIGN_DOWN(fair, alignment);
 #ifdef MAX_FAIR_LMEM
 	fair = min_t(u64, MAX_FAIR_LMEM, fair);
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index eb655ce..de0fe9e6 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -1178,3 +1178,19 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p)
 	xe_guc_ct_print(&guc->ct, p, false);
 	xe_guc_submit_print(guc, p);
 }
+
+/**
+ * xe_guc_declare_wedged() - Declare GuC wedged
+ * @guc: the GuC object
+ *
+ * Wedge the GuC which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_guc_declare_wedged(struct xe_guc *guc)
+{
+	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
+
+	xe_guc_reset_prepare(guc);
+	xe_guc_ct_stop(&guc->ct);
+	xe_guc_submit_wedge(guc);
+}
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
index af59c95..e0bbf98 100644
--- a/drivers/gpu/drm/xe/xe_guc.h
+++ b/drivers/gpu/drm/xe/xe_guc.h
@@ -37,6 +37,7 @@ void xe_guc_reset_wait(struct xe_guc *guc);
 void xe_guc_stop_prepare(struct xe_guc *guc);
 void xe_guc_stop(struct xe_guc *guc);
 int xe_guc_start(struct xe_guc *guc);
+void xe_guc_declare_wedged(struct xe_guc *guc);
 
 static inline u16 xe_engine_class_to_guc_class(enum xe_engine_class class)
 {
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 3734477..8d7e7f4 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -861,13 +861,40 @@ static void xe_guc_exec_queue_trigger_cleanup(struct xe_exec_queue *q)
 		xe_sched_tdr_queue_imm(&q->guc->sched);
 }
 
-static bool guc_submit_hint_wedged(struct xe_guc *guc)
+/**
+ * xe_guc_submit_wedge() - Wedge GuC submission
+ * @guc: the GuC object
+ *
+ * Save exec queue's registered with GuC state by taking a ref to each queue.
+ * Register a DRMM handler to drop refs upon driver unload.
+ */
+void xe_guc_submit_wedge(struct xe_guc *guc)
 {
 	struct xe_device *xe = guc_to_xe(guc);
 	struct xe_exec_queue *q;
 	unsigned long index;
 	int err;
 
+	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);
+
+	err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
+				       guc_submit_wedged_fini, guc);
+	if (err) {
+		drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
+		return;
+	}
+
+	mutex_lock(&guc->submission_state.lock);
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+		if (xe_exec_queue_get_unless_zero(q))
+			set_exec_queue_wedged(q);
+	mutex_unlock(&guc->submission_state.lock);
+}
+
+static bool guc_submit_hint_wedged(struct xe_guc *guc)
+{
+	struct xe_device *xe = guc_to_xe(guc);
+
 	if (xe->wedged.mode != 2)
 		return false;
 
@@ -876,22 +903,6 @@ static bool guc_submit_hint_wedged(struct xe_guc *guc)
 
 	xe_device_declare_wedged(xe);
 
-	xe_guc_submit_reset_prepare(guc);
-	xe_guc_ct_stop(&guc->ct);
-
-	err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
-				       guc_submit_wedged_fini, guc);
-	if (err) {
-		drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
-		return true; /* Device is wedged anyway */
-	}
-
-	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (xe_exec_queue_get_unless_zero(q))
-			set_exec_queue_wedged(q);
-	mutex_unlock(&guc->submission_state.lock);
-
 	return true;
 }
 
@@ -1677,7 +1688,8 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 
 void xe_guc_submit_reset_wait(struct xe_guc *guc)
 {
-	wait_event(guc->ct.wq, !guc_read_stopped(guc));
+	wait_event(guc->ct.wq, xe_device_wedged(guc_to_xe(guc)) ||
+		   !guc_read_stopped(guc));
 }
 
 void xe_guc_submit_stop(struct xe_guc *guc)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 4ad5f4c..bdf8c9f 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -18,6 +18,7 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc);
 void xe_guc_submit_reset_wait(struct xe_guc *guc);
 void xe_guc_submit_stop(struct xe_guc *guc);
 int xe_guc_submit_start(struct xe_guc *guc);
+void xe_guc_submit_wedge(struct xe_guc *guc);
 
 int xe_guc_sched_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index 0f24053..0d073a9 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -300,3 +300,17 @@ void xe_uc_remove(struct xe_uc *uc)
 {
 	xe_gsc_remove(&uc->gsc);
 }
+
+/**
+ * xe_uc_declare_wedged() - Declare UC wedged
+ * @uc: the UC object
+ *
+ * Wedge the UC which stops all submission, saves desired debug state, and
+ * cleans up anything which could timeout.
+ */
+void xe_uc_declare_wedged(struct xe_uc *uc)
+{
+	xe_gt_assert(uc_to_gt(uc), uc_to_xe(uc)->wedged.mode);
+
+	xe_guc_declare_wedged(&uc->guc);
+}
diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
index 11856f2..506517c 100644
--- a/drivers/gpu/drm/xe/xe_uc.h
+++ b/drivers/gpu/drm/xe/xe_uc.h
@@ -21,5 +21,6 @@ int xe_uc_start(struct xe_uc *uc);
 int xe_uc_suspend(struct xe_uc *uc);
 int xe_uc_sanitize_reset(struct xe_uc *uc);
 void xe_uc_remove(struct xe_uc *uc);
+void xe_uc_declare_wedged(struct xe_uc *uc);
 
 #endif
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 7c52757..8e09d6d 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -333,7 +333,7 @@ static int host1x_del_client(struct host1x *host1x,
 	return -ENODEV;
 }
 
-static int host1x_device_match(struct device *dev, struct device_driver *drv)
+static int host1x_device_match(struct device *dev, const struct device_driver *drv)
 {
 	return strcmp(dev_name(dev), drv->name) == 0;
 }
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 3a0aaa6..f006bc9 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -677,7 +677,7 @@ static int host1x_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int host1x_remove(struct platform_device *pdev)
+static void host1x_remove(struct platform_device *pdev)
 {
 	struct host1x *host = platform_get_drvdata(pdev);
 
@@ -692,8 +692,6 @@ static int host1x_remove(struct platform_device *pdev)
 	host1x_channel_list_free(&host->channel_list);
 	host1x_iommu_exit(host);
 	host1x_bo_cache_destroy(&host->cache);
-
-	return 0;
 }
 
 static int __maybe_unused host1x_runtime_suspend(struct device *dev)
@@ -778,7 +776,7 @@ static struct platform_driver tegra_host1x_driver = {
 		.pm = &host1x_pm_ops,
 	},
 	.probe = host1x_probe,
-	.remove = host1x_remove,
+	.remove_new = host1x_remove,
 };
 
 static struct platform_driver * const drivers[] = {
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index 4dcec53..e51b43d 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -501,7 +501,6 @@ static int tegra_mipi_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
 	struct tegra_mipi *mipi;
-	int err;
 
 	match = of_match_node(tegra_mipi_of_match, pdev->dev.of_node);
 	if (!match)
@@ -520,35 +519,21 @@ static int tegra_mipi_probe(struct platform_device *pdev)
 
 	mutex_init(&mipi->lock);
 
-	mipi->clk = devm_clk_get(&pdev->dev, NULL);
+	mipi->clk = devm_clk_get_prepared(&pdev->dev, NULL);
 	if (IS_ERR(mipi->clk)) {
 		dev_err(&pdev->dev, "failed to get clock\n");
 		return PTR_ERR(mipi->clk);
 	}
 
-	err = clk_prepare(mipi->clk);
-	if (err < 0)
-		return err;
-
 	platform_set_drvdata(pdev, mipi);
 
 	return 0;
 }
 
-static int tegra_mipi_remove(struct platform_device *pdev)
-{
-	struct tegra_mipi *mipi = platform_get_drvdata(pdev);
-
-	clk_unprepare(mipi->clk);
-
-	return 0;
-}
-
 struct platform_driver tegra_mipi_driver = {
 	.driver = {
 		.name = "tegra-mipi",
 		.of_match_table = tegra_mipi_of_match,
 	},
 	.probe = tegra_mipi_probe,
-	.remove = tegra_mipi_remove,
 };
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 71ec1e7..3535be9 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1450,7 +1450,7 @@ static int ipu_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int ipu_remove(struct platform_device *pdev)
+static void ipu_remove(struct platform_device *pdev)
 {
 	struct ipu_soc *ipu = platform_get_drvdata(pdev);
 
@@ -1459,8 +1459,6 @@ static int ipu_remove(struct platform_device *pdev)
 	ipu_irq_exit(ipu);
 
 	clk_disable_unprepare(ipu->clk);
-
-	return 0;
 }
 
 static struct platform_driver imx_ipu_driver = {
@@ -1469,7 +1467,7 @@ static struct platform_driver imx_ipu_driver = {
 		.of_match_table = imx_ipu_dt_ids,
 	},
 	.probe = ipu_probe,
-	.remove = ipu_remove,
+	.remove_new = ipu_remove,
 };
 
 static struct platform_driver * const drivers[] = {
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 624b761..41bd5db 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -351,7 +351,7 @@ static int ipu_pre_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ipu_pre_remove(struct platform_device *pdev)
+static void ipu_pre_remove(struct platform_device *pdev)
 {
 	struct ipu_pre *pre = platform_get_drvdata(pdev);
 
@@ -365,7 +365,6 @@ static int ipu_pre_remove(struct platform_device *pdev)
 	if (pre->buffer_virt)
 		gen_pool_free(pre->iram, (unsigned long)pre->buffer_virt,
 			      IPU_PRE_MAX_WIDTH * IPU_PRE_NUM_SCANLINES * 4);
-	return 0;
 }
 
 static const struct of_device_id ipu_pre_dt_ids[] = {
@@ -375,7 +374,7 @@ static const struct of_device_id ipu_pre_dt_ids[] = {
 
 struct platform_driver ipu_pre_drv = {
 	.probe		= ipu_pre_probe,
-	.remove		= ipu_pre_remove,
+	.remove_new	= ipu_pre_remove,
 	.driver		= {
 		.name	= "imx-ipu-pre",
 		.of_match_table = ipu_pre_dt_ids,
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 661dedf..afb2d72 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -419,15 +419,13 @@ static int ipu_prg_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ipu_prg_remove(struct platform_device *pdev)
+static void ipu_prg_remove(struct platform_device *pdev)
 {
 	struct ipu_prg *prg = platform_get_drvdata(pdev);
 
 	mutex_lock(&ipu_prg_list_mutex);
 	list_del(&prg->list);
 	mutex_unlock(&ipu_prg_list_mutex);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -471,7 +469,7 @@ static const struct of_device_id ipu_prg_dt_ids[] = {
 
 struct platform_driver ipu_prg_drv = {
 	.probe		= ipu_prg_probe,
-	.remove		= ipu_prg_remove,
+	.remove_new	= ipu_prg_remove,
 	.driver		= {
 		.name	= "imx-ipu-prg",
 		.pm	= &prg_pm_ops,
diff --git a/drivers/greybus/core.c b/drivers/greybus/core.c
index 33a47e7..313eb65 100644
--- a/drivers/greybus/core.c
+++ b/drivers/greybus/core.c
@@ -90,9 +90,9 @@ greybus_match_id(struct gb_bundle *bundle, const struct greybus_bundle_id *id)
 	return NULL;
 }
 
-static int greybus_match_device(struct device *dev, struct device_driver *drv)
+static int greybus_match_device(struct device *dev, const struct device_driver *drv)
 {
-	struct greybus_driver *driver = to_greybus_driver(drv);
+	const struct greybus_driver *driver = to_greybus_driver(drv);
 	struct gb_bundle *bundle;
 	const struct greybus_bundle_id *id;
 
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 2540061..988d0ac 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2604,7 +2604,7 @@ const struct hid_device_id *hid_match_device(struct hid_device *hdev,
 }
 EXPORT_SYMBOL_GPL(hid_match_device);
 
-static int hid_bus_match(struct device *dev, struct device_driver *drv)
+static int hid_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct hid_driver *hdrv = to_hid_driver(drv);
 	struct hid_device *hdev = to_hid_device(dev);
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index cc76b29..5ac7d70 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -236,7 +236,7 @@ static int ishtp_cl_device_probe(struct device *dev)
  *
  * Return: 1 if dev & drv matches, 0 otherwise.
  */
-static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv)
+static int ishtp_cl_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct ishtp_cl_device *device = to_ishtp_cl_device(dev);
 	struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv);
diff --git a/drivers/hsi/hsi_core.c b/drivers/hsi/hsi_core.c
index e3beeac..8113cb9 100644
--- a/drivers/hsi/hsi_core.c
+++ b/drivers/hsi/hsi_core.c
@@ -37,7 +37,7 @@ static int hsi_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-static int hsi_bus_match(struct device *dev, struct device_driver *driver)
+static int hsi_bus_match(struct device *dev, const struct device_driver *driver)
 {
 	if (of_driver_match_device(dev, driver))
 		return true;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 12a707a..c857dc3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -685,7 +685,7 @@ static const struct hv_vmbus_device_id vmbus_device_null;
  * Return a matching hv_vmbus_device_id pointer.
  * If there is no match, return NULL.
  */
-static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv,
+static const struct hv_vmbus_device_id *hv_vmbus_get_id(const struct hv_driver *drv,
 							struct hv_device *dev)
 {
 	const guid_t *guid = &dev->dev_type;
@@ -696,7 +696,7 @@ static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv,
 		return NULL;
 
 	/* Look at the dynamic ids first, before the static ones */
-	id = hv_vmbus_dynid_match(drv, guid);
+	id = hv_vmbus_dynid_match((struct hv_driver *)drv, guid);
 	if (!id)
 		id = hv_vmbus_dev_match(drv->id_table, guid);
 
@@ -809,9 +809,9 @@ ATTRIBUTE_GROUPS(vmbus_drv);
 /*
  * vmbus_match - Attempt to match the specified device to the specified driver
  */
-static int vmbus_match(struct device *device, struct device_driver *driver)
+static int vmbus_match(struct device *device, const struct device_driver *driver)
 {
-	struct hv_driver *drv = drv_to_hv_drv(driver);
+	const struct hv_driver *drv = drv_to_hv_drv(driver);
 	struct hv_device *hv_dev = device_to_hv_device(device);
 
 	/* The hv_sock driver handles all hv_sock offers. */
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index a121dc5..d729933 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -26,9 +26,9 @@ module_param(host_mode, bool, 0444);
 
 static DEFINE_IDA(intel_th_ida);
 
-static int intel_th_match(struct device *dev, struct device_driver *driver)
+static int intel_th_match(struct device *dev, const struct device_driver *driver)
 {
-	struct intel_th_driver *thdrv = to_intel_th_driver(driver);
+	const struct intel_th_driver *thdrv = to_intel_th_driver(driver);
 	struct intel_th_device *thdev = to_intel_th_device(dev);
 
 	if (thdev->type == INTEL_TH_SWITCH &&
diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h
index 6cbba733..3b87cd5 100644
--- a/drivers/hwtracing/intel_th/intel_th.h
+++ b/drivers/hwtracing/intel_th/intel_th.h
@@ -189,7 +189,7 @@ struct intel_th_driver {
 };
 
 #define to_intel_th_driver(_d)					\
-	container_of((_d), struct intel_th_driver, driver)
+	container_of_const((_d), struct intel_th_driver, driver)
 
 #define to_intel_th_driver_or_null(_d)		\
 	((_d) ? to_intel_th_driver(_d) : NULL)
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index f76b7f4..b63f75e 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -136,10 +136,10 @@ const void *i2c_get_match_data(const struct i2c_client *client)
 }
 EXPORT_SYMBOL(i2c_get_match_data);
 
-static int i2c_device_match(struct device *dev, struct device_driver *drv)
+static int i2c_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct i2c_client	*client = i2c_verify_client(dev);
-	struct i2c_driver	*driver;
+	const struct i2c_driver	*driver;
 
 
 	/* Attempt an OF style match */
diff --git a/drivers/i3c/internals.h b/drivers/i3c/internals.h
index 4d99a35..433f608 100644
--- a/drivers/i3c/internals.h
+++ b/drivers/i3c/internals.h
@@ -10,8 +10,6 @@
 
 #include <linux/i3c/master.h>
 
-extern const struct bus_type i3c_bus_type;
-
 void i3c_bus_normaluse_lock(struct i3c_bus *bus);
 void i3c_bus_normaluse_unlock(struct i3c_bus *bus);
 
diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 3b4d6a8..7028f03 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -301,10 +301,10 @@ static const struct device_type i3c_device_type = {
 	.uevent = i3c_device_uevent,
 };
 
-static int i3c_device_match(struct device *dev, struct device_driver *drv)
+static int i3c_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct i3c_device *i3cdev;
-	struct i3c_driver *i3cdrv;
+	const struct i3c_driver *i3cdrv;
 
 	if (dev->type != &i3c_device_type)
 		return 0;
@@ -342,6 +342,7 @@ const struct bus_type i3c_bus_type = {
 	.probe = i3c_device_probe,
 	.remove = i3c_device_remove,
 };
+EXPORT_SYMBOL_GPL(i3c_bus_type);
 
 static enum i3c_addr_slot_status
 i3c_bus_get_addr_slot_status(struct i3c_bus *bus, u16 addr)
diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c
index 01a47d3..84942dbb 100644
--- a/drivers/i3c/master/ast2600-i3c-master.c
+++ b/drivers/i3c/master/ast2600-i3c-master.c
@@ -156,7 +156,6 @@ static int ast2600_i3c_probe(struct platform_device *pdev)
 			i3c->sda_pullup);
 
 	i3c->dw.platform_ops = &ast2600_i3c_ops;
-	i3c->dw.ibi_capable = true;
 	return dw_i3c_common_probe(&i3c->dw, pdev);
 }
 
diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 0ec00e6..8d69467 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -17,7 +17,9 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
 
@@ -217,7 +219,7 @@
 #define I3C_BUS_THIGH_MAX_NS		41
 
 #define XFER_TIMEOUT (msecs_to_jiffies(1000))
-
+#define RPM_AUTOSUSPEND_TIMEOUT 1000 /* ms */
 struct dw_i3c_cmd {
 	u32 cmd_lo;
 	u32 cmd_hi;
@@ -300,7 +302,14 @@ static void dw_i3c_master_disable(struct dw_i3c_master *master)
 
 static void dw_i3c_master_enable(struct dw_i3c_master *master)
 {
-	writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_ENABLE,
+	u32 dev_ctrl;
+
+	dev_ctrl = readl(master->regs + DEVICE_CTRL);
+	/* For now don't support Hot-Join */
+	dev_ctrl |= DEV_CTRL_HOT_JOIN_NACK;
+	if (master->i2c_slv_prsnt)
+		dev_ctrl |= DEV_CTRL_I2C_SLAVE_PRESENT;
+	writel(dev_ctrl | DEV_CTRL_ENABLE,
 	       master->regs + DEVICE_CTRL);
 }
 
@@ -521,6 +530,32 @@ static void dw_i3c_master_end_xfer_locked(struct dw_i3c_master *master, u32 isr)
 	dw_i3c_master_start_xfer_locked(master);
 }
 
+static void dw_i3c_master_set_intr_regs(struct dw_i3c_master *master)
+{
+	u32 thld_ctrl;
+
+	thld_ctrl = readl(master->regs + QUEUE_THLD_CTRL);
+	thld_ctrl &= ~(QUEUE_THLD_CTRL_RESP_BUF_MASK |
+		       QUEUE_THLD_CTRL_IBI_STAT_MASK |
+		       QUEUE_THLD_CTRL_IBI_DATA_MASK);
+	thld_ctrl |= QUEUE_THLD_CTRL_IBI_STAT(1) |
+		QUEUE_THLD_CTRL_IBI_DATA(31);
+	writel(thld_ctrl, master->regs + QUEUE_THLD_CTRL);
+
+	thld_ctrl = readl(master->regs + DATA_BUFFER_THLD_CTRL);
+	thld_ctrl &= ~DATA_BUFFER_THLD_CTRL_RX_BUF;
+	writel(thld_ctrl, master->regs + DATA_BUFFER_THLD_CTRL);
+
+	writel(INTR_ALL, master->regs + INTR_STATUS);
+	writel(INTR_MASTER_MASK, master->regs + INTR_STATUS_EN);
+	writel(INTR_MASTER_MASK, master->regs + INTR_SIGNAL_EN);
+
+	master->sir_rej_mask = IBI_REQ_REJECT_ALL;
+	writel(master->sir_rej_mask, master->regs + IBI_SIR_REQ_REJECT);
+
+	writel(IBI_REQ_REJECT_ALL, master->regs + IBI_MR_REQ_REJECT);
+}
+
 static int dw_i3c_clk_cfg(struct dw_i3c_master *master)
 {
 	unsigned long core_rate, core_period;
@@ -543,18 +578,22 @@ static int dw_i3c_clk_cfg(struct dw_i3c_master *master)
 
 	scl_timing = SCL_I3C_TIMING_HCNT(hcnt) | SCL_I3C_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I3C_PP_TIMING);
+	master->i3c_pp_timing = scl_timing;
 
 	/*
 	 * In pure i3c mode, MST_FREE represents tCAS. In shared mode, this
 	 * will be set up by dw_i2c_clk_cfg as tLOW.
 	 */
-	if (master->base.bus.mode == I3C_BUS_MODE_PURE)
+	if (master->base.bus.mode == I3C_BUS_MODE_PURE) {
 		writel(BUS_I3C_MST_FREE(lcnt), master->regs + BUS_FREE_TIMING);
+		master->bus_free_timing = BUS_I3C_MST_FREE(lcnt);
+	}
 
 	lcnt = max_t(u8,
 		     DIV_ROUND_UP(I3C_BUS_TLOW_OD_MIN_NS, core_period), lcnt);
 	scl_timing = SCL_I3C_TIMING_HCNT(hcnt) | SCL_I3C_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I3C_OD_TIMING);
+	master->i3c_od_timing = scl_timing;
 
 	lcnt = DIV_ROUND_UP(core_rate, I3C_BUS_SDR1_SCL_RATE) - hcnt;
 	scl_timing = SCL_EXT_LCNT_1(lcnt);
@@ -565,6 +604,7 @@ static int dw_i3c_clk_cfg(struct dw_i3c_master *master)
 	lcnt = DIV_ROUND_UP(core_rate, I3C_BUS_SDR4_SCL_RATE) - hcnt;
 	scl_timing |= SCL_EXT_LCNT_4(lcnt);
 	writel(scl_timing, master->regs + SCL_EXT_LCNT_TIMING);
+	master->ext_lcnt_timing = scl_timing;
 
 	return 0;
 }
@@ -586,16 +626,21 @@ static int dw_i2c_clk_cfg(struct dw_i3c_master *master)
 	scl_timing = SCL_I2C_FMP_TIMING_HCNT(hcnt) |
 		     SCL_I2C_FMP_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I2C_FMP_TIMING);
+	master->i2c_fmp_timing = scl_timing;
 
 	lcnt = DIV_ROUND_UP(I3C_BUS_I2C_FM_TLOW_MIN_NS, core_period);
 	hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_SCL_RATE) - lcnt;
 	scl_timing = SCL_I2C_FM_TIMING_HCNT(hcnt) |
 		     SCL_I2C_FM_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I2C_FM_TIMING);
+	master->i2c_fm_timing = scl_timing;
 
 	writel(BUS_I3C_MST_FREE(lcnt), master->regs + BUS_FREE_TIMING);
+	master->bus_free_timing = BUS_I3C_MST_FREE(lcnt);
+
 	writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_I2C_SLAVE_PRESENT,
 	       master->regs + DEVICE_CTRL);
+	master->i2c_slv_prsnt = true;
 
 	return 0;
 }
@@ -605,69 +650,58 @@ static int dw_i3c_master_bus_init(struct i3c_master_controller *m)
 	struct dw_i3c_master *master = to_dw_i3c_master(m);
 	struct i3c_bus *bus = i3c_master_get_bus(m);
 	struct i3c_device_info info = { };
-	u32 thld_ctrl;
 	int ret;
 
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
 	ret = master->platform_ops->init(master);
 	if (ret)
-		return ret;
+		goto rpm_out;
 
 	switch (bus->mode) {
 	case I3C_BUS_MODE_MIXED_FAST:
 	case I3C_BUS_MODE_MIXED_LIMITED:
 		ret = dw_i2c_clk_cfg(master);
 		if (ret)
-			return ret;
+			goto rpm_out;
 		fallthrough;
 	case I3C_BUS_MODE_PURE:
 		ret = dw_i3c_clk_cfg(master);
 		if (ret)
-			return ret;
+			goto rpm_out;
 		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		goto rpm_out;
 	}
 
-	thld_ctrl = readl(master->regs + QUEUE_THLD_CTRL);
-	thld_ctrl &= ~(QUEUE_THLD_CTRL_RESP_BUF_MASK |
-		       QUEUE_THLD_CTRL_IBI_STAT_MASK |
-		       QUEUE_THLD_CTRL_IBI_STAT_MASK);
-	thld_ctrl |= QUEUE_THLD_CTRL_IBI_STAT(1) |
-		QUEUE_THLD_CTRL_IBI_DATA(31);
-	writel(thld_ctrl, master->regs + QUEUE_THLD_CTRL);
-
-	thld_ctrl = readl(master->regs + DATA_BUFFER_THLD_CTRL);
-	thld_ctrl &= ~DATA_BUFFER_THLD_CTRL_RX_BUF;
-	writel(thld_ctrl, master->regs + DATA_BUFFER_THLD_CTRL);
-
-	writel(INTR_ALL, master->regs + INTR_STATUS);
-	writel(INTR_MASTER_MASK, master->regs + INTR_STATUS_EN);
-	writel(INTR_MASTER_MASK, master->regs + INTR_SIGNAL_EN);
-
 	ret = i3c_master_get_free_addr(m, 0);
 	if (ret < 0)
-		return ret;
+		goto rpm_out;
 
 	writel(DEV_ADDR_DYNAMIC_ADDR_VALID | DEV_ADDR_DYNAMIC(ret),
 	       master->regs + DEVICE_ADDR);
-
+	master->dev_addr = ret;
 	memset(&info, 0, sizeof(info));
 	info.dyn_addr = ret;
 
 	ret = i3c_master_set_info(&master->base, &info);
 	if (ret)
-		return ret;
+		goto rpm_out;
 
-	writel(IBI_REQ_REJECT_ALL, master->regs + IBI_SIR_REQ_REJECT);
-	writel(IBI_REQ_REJECT_ALL, master->regs + IBI_MR_REQ_REJECT);
-
-	/* For now don't support Hot-Join */
-	writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_HOT_JOIN_NACK,
-	       master->regs + DEVICE_CTRL);
-
+	dw_i3c_master_set_intr_regs(master);
 	dw_i3c_master_enable(master);
 
-	return 0;
+rpm_out:
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
+	return ret;
 }
 
 static void dw_i3c_master_bus_cleanup(struct i3c_master_controller *m)
@@ -769,11 +803,21 @@ static int dw_i3c_master_send_ccc_cmd(struct i3c_master_controller *m,
 	if (ccc->id == I3C_CCC_ENTDAA)
 		return -EINVAL;
 
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
 	if (ccc->rnw)
 		ret = dw_i3c_ccc_get(master, ccc);
 	else
 		ret = dw_i3c_ccc_set(master, ccc);
 
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
 	return ret;
 }
 
@@ -786,6 +830,14 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m)
 	u8 p, last_addr = 0;
 	int ret, pos;
 
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
 	olddevs = ~(master->free_pos);
 
 	/* Prepare DAT before launching DAA. */
@@ -794,8 +846,10 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m)
 			continue;
 
 		ret = i3c_master_get_free_addr(m, last_addr + 1);
-		if (ret < 0)
-			return -ENOSPC;
+		if (ret < 0) {
+			ret = -ENOSPC;
+			goto rpm_out;
+		}
 
 		master->devs[pos].addr = ret;
 		p = even_parity(ret);
@@ -805,16 +859,21 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m)
 		writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(ret),
 		       master->regs +
 		       DEV_ADDR_TABLE_LOC(master->datstartaddr, pos));
+
+		ret = 0;
 	}
 
 	xfer = dw_i3c_master_alloc_xfer(master, 1);
-	if (!xfer)
-		return -ENOMEM;
+	if (!xfer) {
+		ret = -ENOMEM;
+		goto rpm_out;
+	}
 
 	pos = dw_i3c_master_get_free_pos(master);
 	if (pos < 0) {
 		dw_i3c_master_free_xfer(xfer);
-		return pos;
+		ret = pos;
+		goto rpm_out;
 	}
 	cmd = &xfer->cmds[0];
 	cmd->cmd_hi = 0x1;
@@ -839,7 +898,10 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m)
 
 	dw_i3c_master_free_xfer(xfer);
 
-	return 0;
+rpm_out:
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
+	return ret;
 }
 
 static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
@@ -874,6 +936,14 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
 	if (!xfer)
 		return -ENOMEM;
 
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
 	for (i = 0; i < i3c_nxfers; i++) {
 		struct dw_i3c_cmd *cmd = &xfer->cmds[i];
 
@@ -915,6 +985,8 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev,
 	ret = xfer->ret;
 	dw_i3c_master_free_xfer(xfer);
 
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
 	return ret;
 }
 
@@ -1025,6 +1097,14 @@ static int dw_i3c_master_i2c_xfers(struct i2c_dev_desc *dev,
 	if (!xfer)
 		return -ENOMEM;
 
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
 	for (i = 0; i < i2c_nxfers; i++) {
 		struct dw_i3c_cmd *cmd = &xfer->cmds[i];
 
@@ -1055,6 +1135,8 @@ static int dw_i3c_master_i2c_xfers(struct i2c_dev_desc *dev,
 	ret = xfer->ret;
 	dw_i3c_master_free_xfer(xfer);
 
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
 	return ret;
 }
 
@@ -1075,6 +1157,7 @@ static int dw_i3c_master_attach_i2c_dev(struct i2c_dev_desc *dev)
 
 	data->index = pos;
 	master->devs[pos].addr = dev->addr;
+	master->devs[pos].is_i2c_addr = true;
 	master->free_pos &= ~BIT(pos);
 	i2c_dev_set_master_data(dev, data);
 
@@ -1175,17 +1258,16 @@ static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master,
 	master->platform_ops->set_dat_ibi(master, dev, enable, &reg);
 	writel(reg, master->regs + dat_entry);
 
-	reg = readl(master->regs + IBI_SIR_REQ_REJECT);
 	if (enable) {
-		global = reg == 0xffffffff;
-		reg &= ~BIT(idx);
+		global = (master->sir_rej_mask == IBI_REQ_REJECT_ALL);
+		master->sir_rej_mask &= ~BIT(idx);
 	} else {
 		bool hj_rejected = !!(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_HOT_JOIN_NACK);
 
-		reg |= BIT(idx);
-		global = (reg == 0xffffffff) && hj_rejected;
+		master->sir_rej_mask |= BIT(idx);
+		global = (master->sir_rej_mask == IBI_REQ_REJECT_ALL) && hj_rejected;
 	}
-	writel(reg, master->regs + IBI_SIR_REQ_REJECT);
+	writel(master->sir_rej_mask, master->regs + IBI_SIR_REQ_REJECT);
 
 	if (global)
 		dw_i3c_master_enable_sir_signal(master, enable);
@@ -1197,6 +1279,15 @@ static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master,
 static int dw_i3c_master_enable_hotjoin(struct i3c_master_controller *m)
 {
 	struct dw_i3c_master *master = to_dw_i3c_master(m);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(master->dev);
+	if (ret < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, ret);
+		return ret;
+	}
 
 	dw_i3c_master_enable_sir_signal(master, true);
 	writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_HOT_JOIN_NACK,
@@ -1212,6 +1303,8 @@ static int dw_i3c_master_disable_hotjoin(struct i3c_master_controller *m)
 	writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_HOT_JOIN_NACK,
 	       master->regs + DEVICE_CTRL);
 
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
 	return 0;
 }
 
@@ -1222,12 +1315,23 @@ static int dw_i3c_master_enable_ibi(struct i3c_dev_desc *dev)
 	struct dw_i3c_master *master = to_dw_i3c_master(m);
 	int rc;
 
+	rc = pm_runtime_resume_and_get(master->dev);
+	if (rc < 0) {
+		dev_err(master->dev,
+			"<%s> cannot resume i3c bus master, err: %d\n",
+			__func__, rc);
+		return rc;
+	}
+
 	dw_i3c_master_set_sir_enabled(master, dev, data->index, true);
 
 	rc = i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR);
 
-	if (rc)
+	if (rc) {
 		dw_i3c_master_set_sir_enabled(master, dev, data->index, false);
+		pm_runtime_mark_last_busy(master->dev);
+		pm_runtime_put_autosuspend(master->dev);
+	}
 
 	return rc;
 }
@@ -1245,6 +1349,8 @@ static int dw_i3c_master_disable_ibi(struct i3c_dev_desc *dev)
 
 	dw_i3c_master_set_sir_enabled(master, dev, data->index, false);
 
+	pm_runtime_mark_last_busy(master->dev);
+	pm_runtime_put_autosuspend(master->dev);
 	return 0;
 }
 
@@ -1403,21 +1509,6 @@ static const struct i3c_master_controller_ops dw_mipi_i3c_ops = {
 	.attach_i2c_dev = dw_i3c_master_attach_i2c_dev,
 	.detach_i2c_dev = dw_i3c_master_detach_i2c_dev,
 	.i2c_xfers = dw_i3c_master_i2c_xfers,
-};
-
-static const struct i3c_master_controller_ops dw_mipi_i3c_ibi_ops = {
-	.bus_init = dw_i3c_master_bus_init,
-	.bus_cleanup = dw_i3c_master_bus_cleanup,
-	.attach_i3c_dev = dw_i3c_master_attach_i3c_dev,
-	.reattach_i3c_dev = dw_i3c_master_reattach_i3c_dev,
-	.detach_i3c_dev = dw_i3c_master_detach_i3c_dev,
-	.do_daa = dw_i3c_master_daa,
-	.supports_ccc_cmd = dw_i3c_master_supports_ccc_cmd,
-	.send_ccc_cmd = dw_i3c_master_send_ccc_cmd,
-	.priv_xfers = dw_i3c_master_priv_xfers,
-	.attach_i2c_dev = dw_i3c_master_attach_i2c_dev,
-	.detach_i2c_dev = dw_i3c_master_detach_i2c_dev,
-	.i2c_xfers = dw_i3c_master_i2c_xfers,
 	.request_ibi = dw_i3c_master_request_ibi,
 	.free_ibi = dw_i3c_master_free_ibi,
 	.enable_ibi = dw_i3c_master_enable_ibi,
@@ -1455,29 +1546,30 @@ static void dw_i3c_hj_work(struct work_struct *work)
 int dw_i3c_common_probe(struct dw_i3c_master *master,
 			struct platform_device *pdev)
 {
-	const struct i3c_master_controller_ops *ops;
 	int ret, irq;
 
 	if (!master->platform_ops)
 		master->platform_ops = &dw_i3c_platform_ops_default;
 
+	master->dev = &pdev->dev;
+
 	master->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(master->regs))
 		return PTR_ERR(master->regs);
 
-	master->core_clk = devm_clk_get(&pdev->dev, NULL);
+	master->core_clk = devm_clk_get_enabled(&pdev->dev, NULL);
 	if (IS_ERR(master->core_clk))
 		return PTR_ERR(master->core_clk);
 
+	master->pclk = devm_clk_get_optional_enabled(&pdev->dev, "pclk");
+	if (IS_ERR(master->pclk))
+		return PTR_ERR(master->pclk);
+
 	master->core_rst = devm_reset_control_get_optional_exclusive(&pdev->dev,
 								    "core_rst");
 	if (IS_ERR(master->core_rst))
 		return PTR_ERR(master->core_rst);
 
-	ret = clk_prepare_enable(master->core_clk);
-	if (ret)
-		goto err_disable_core_clk;
-
 	reset_control_deassert(master->core_rst);
 
 	spin_lock_init(&master->xferqueue.lock);
@@ -1493,6 +1585,11 @@ int dw_i3c_common_probe(struct dw_i3c_master *master,
 
 	platform_set_drvdata(pdev, master);
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, RPM_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	/* Information regarding the FIFOs/QUEUEs depth */
 	ret = readl(master->regs + QUEUE_STATUS_LEVEL);
 	master->caps.cmdfifodepth = QUEUE_STATUS_LEVEL_CMD(ret);
@@ -1505,23 +1602,22 @@ int dw_i3c_common_probe(struct dw_i3c_master *master,
 	master->maxdevs = ret >> 16;
 	master->free_pos = GENMASK(master->maxdevs - 1, 0);
 
-	ops = &dw_mipi_i3c_ops;
-	if (master->ibi_capable)
-		ops = &dw_mipi_i3c_ibi_ops;
-
 	INIT_WORK(&master->hj_work, dw_i3c_hj_work);
-	ret = i3c_master_register(&master->base, &pdev->dev, ops, false);
+	ret = i3c_master_register(&master->base, &pdev->dev,
+				  &dw_mipi_i3c_ops, false);
 	if (ret)
-		goto err_assert_rst;
+		goto err_disable_pm;
 
 	return 0;
 
+err_disable_pm:
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+
 err_assert_rst:
 	reset_control_assert(master->core_rst);
 
-err_disable_core_clk:
-	clk_disable_unprepare(master->core_clk);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dw_i3c_common_probe);
@@ -1530,9 +1626,9 @@ void dw_i3c_common_remove(struct dw_i3c_master *master)
 {
 	i3c_master_unregister(&master->base);
 
-	reset_control_assert(master->core_rst);
-
-	clk_disable_unprepare(master->core_clk);
+	pm_runtime_disable(master->dev);
+	pm_runtime_set_suspended(master->dev);
+	pm_runtime_dont_use_autosuspend(master->dev);
 }
 EXPORT_SYMBOL_GPL(dw_i3c_common_remove);
 
@@ -1556,6 +1652,96 @@ static void dw_i3c_remove(struct platform_device *pdev)
 	dw_i3c_common_remove(master);
 }
 
+static void dw_i3c_master_restore_addrs(struct dw_i3c_master *master)
+{
+	u32 pos, reg_val;
+
+	writel(DEV_ADDR_DYNAMIC_ADDR_VALID | DEV_ADDR_DYNAMIC(master->dev_addr),
+	       master->regs + DEVICE_ADDR);
+
+	for (pos = 0; pos < master->maxdevs; pos++) {
+		if (master->free_pos & BIT(pos))
+			continue;
+
+		if (master->devs[pos].is_i2c_addr)
+			reg_val = DEV_ADDR_TABLE_LEGACY_I2C_DEV |
+			       DEV_ADDR_TABLE_STATIC_ADDR(master->devs[pos].addr);
+		else
+			reg_val = DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr);
+
+		writel(reg_val, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, pos));
+	}
+}
+
+static void dw_i3c_master_restore_timing_regs(struct dw_i3c_master *master)
+{
+	writel(master->i3c_pp_timing, master->regs + SCL_I3C_PP_TIMING);
+	writel(master->bus_free_timing, master->regs + BUS_FREE_TIMING);
+	writel(master->i3c_od_timing, master->regs + SCL_I3C_OD_TIMING);
+	writel(master->ext_lcnt_timing, master->regs + SCL_EXT_LCNT_TIMING);
+
+	if (master->i2c_slv_prsnt) {
+		writel(master->i2c_fmp_timing, master->regs + SCL_I2C_FMP_TIMING);
+		writel(master->i2c_fm_timing, master->regs + SCL_I2C_FM_TIMING);
+	}
+}
+
+static int dw_i3c_master_enable_clks(struct dw_i3c_master *master)
+{
+	int ret = 0;
+
+	ret = clk_prepare_enable(master->core_clk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(master->pclk);
+	if (ret) {
+		clk_disable_unprepare(master->core_clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline void dw_i3c_master_disable_clks(struct dw_i3c_master *master)
+{
+	clk_disable_unprepare(master->pclk);
+	clk_disable_unprepare(master->core_clk);
+}
+
+static int __maybe_unused dw_i3c_master_runtime_suspend(struct device *dev)
+{
+	struct dw_i3c_master *master = dev_get_drvdata(dev);
+
+	dw_i3c_master_disable(master);
+
+	reset_control_assert(master->core_rst);
+	dw_i3c_master_disable_clks(master);
+	pinctrl_pm_select_sleep_state(dev);
+	return 0;
+}
+
+static int __maybe_unused dw_i3c_master_runtime_resume(struct device *dev)
+{
+	struct dw_i3c_master *master = dev_get_drvdata(dev);
+
+	pinctrl_pm_select_default_state(dev);
+	dw_i3c_master_enable_clks(master);
+	reset_control_deassert(master->core_rst);
+
+	dw_i3c_master_set_intr_regs(master);
+	dw_i3c_master_restore_timing_regs(master);
+	dw_i3c_master_restore_addrs(master);
+
+	dw_i3c_master_enable(master);
+	return 0;
+}
+
+static const struct dev_pm_ops dw_i3c_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(dw_i3c_master_runtime_suspend, dw_i3c_master_runtime_resume, NULL)
+};
+
 static const struct of_device_id dw_i3c_master_of_match[] = {
 	{ .compatible = "snps,dw-i3c-master-1.00a", },
 	{},
@@ -1568,6 +1754,7 @@ static struct platform_driver dw_i3c_driver = {
 	.driver = {
 		.name = "dw-i3c-master",
 		.of_match_table = dw_i3c_master_of_match,
+		.pm = &dw_i3c_pm_ops,
 	},
 };
 module_platform_driver(dw_i3c_driver);
diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h
index 4ab94aa..219ff81 100644
--- a/drivers/i3c/master/dw-i3c-master.h
+++ b/drivers/i3c/master/dw-i3c-master.h
@@ -19,11 +19,13 @@ struct dw_i3c_master_caps {
 
 struct dw_i3c_dat_entry {
 	u8 addr;
+	bool is_i2c_addr;
 	struct i3c_dev_desc *ibi_dev;
 };
 
 struct dw_i3c_master {
 	struct i3c_master_controller base;
+	struct device *dev;
 	u16 maxdevs;
 	u16 datstartaddr;
 	u32 free_pos;
@@ -36,10 +38,18 @@ struct dw_i3c_master {
 	void __iomem *regs;
 	struct reset_control *core_rst;
 	struct clk *core_clk;
+	struct clk *pclk;
 	char version[5];
 	char type[5];
-	bool ibi_capable;
-
+	u32 sir_rej_mask;
+	bool i2c_slv_prsnt;
+	u32 dev_addr;
+	u32 i3c_pp_timing;
+	u32 i3c_od_timing;
+	u32 ext_lcnt_timing;
+	u32 bus_free_timing;
+	u32 i2c_fm_timing;
+	u32 i2c_fmp_timing;
 	/*
 	 * Per-device hardware data, used to manage the device address table
 	 * (DAT)
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index d7e966a..4e7d6a4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -631,6 +631,7 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 static int i3c_hci_init(struct i3c_hci *hci)
 {
 	u32 regval, offset;
+	bool size_in_dwords;
 	int ret;
 
 	/* Validate HCI hardware version */
@@ -654,11 +655,16 @@ static int i3c_hci_init(struct i3c_hci *hci)
 	hci->caps = reg_read(HC_CAPABILITIES);
 	DBG("caps = %#x", hci->caps);
 
+	size_in_dwords = hci->version_major < 1 ||
+			 (hci->version_major == 1 && hci->version_minor < 1);
+
 	regval = reg_read(DAT_SECTION);
 	offset = FIELD_GET(DAT_TABLE_OFFSET, regval);
 	hci->DAT_regs = offset ? hci->base_regs + offset : NULL;
 	hci->DAT_entries = FIELD_GET(DAT_TABLE_SIZE, regval);
 	hci->DAT_entry_size = FIELD_GET(DAT_ENTRY_SIZE, regval) ? 0 : 8;
+	if (size_in_dwords)
+		hci->DAT_entries = 4 * hci->DAT_entries / hci->DAT_entry_size;
 	dev_info(&hci->master.dev, "DAT: %u %u-bytes entries at offset %#x\n",
 		 hci->DAT_entries, hci->DAT_entry_size, offset);
 
@@ -667,6 +673,8 @@ static int i3c_hci_init(struct i3c_hci *hci)
 	hci->DCT_regs = offset ? hci->base_regs + offset : NULL;
 	hci->DCT_entries = FIELD_GET(DCT_TABLE_SIZE, regval);
 	hci->DCT_entry_size = FIELD_GET(DCT_ENTRY_SIZE, regval) ? 0 : 16;
+	if (size_in_dwords)
+		hci->DCT_entries = 4 * hci->DCT_entries / hci->DCT_entry_size;
 	dev_info(&hci->master.dev, "DCT: %u %u-bytes entries at offset %#x\n",
 		 hci->DCT_entries, hci->DCT_entry_size, offset);
 
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 4e01a95..a918e96 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -147,21 +147,6 @@ struct hci_dma_dev_ibi_data {
 	unsigned int max_len;
 };
 
-static inline u32 lo32(dma_addr_t physaddr)
-{
-	return physaddr;
-}
-
-static inline u32 hi32(dma_addr_t physaddr)
-{
-	/* trickery to avoid compiler warnings on 32-bit build targets */
-	if (sizeof(dma_addr_t) > 4) {
-		u64 hi = physaddr;
-		return hi >> 32;
-	}
-	return 0;
-}
-
 static void hci_dma_cleanup(struct i3c_hci *hci)
 {
 	struct hci_rings_data *rings = hci->io_data;
@@ -265,10 +250,10 @@ static int hci_dma_init(struct i3c_hci *hci)
 		if (!rh->xfer || !rh->resp || !rh->src_xfers)
 			goto err_out;
 
-		rh_reg_write(CMD_RING_BASE_LO, lo32(rh->xfer_dma));
-		rh_reg_write(CMD_RING_BASE_HI, hi32(rh->xfer_dma));
-		rh_reg_write(RESP_RING_BASE_LO, lo32(rh->resp_dma));
-		rh_reg_write(RESP_RING_BASE_HI, hi32(rh->resp_dma));
+		rh_reg_write(CMD_RING_BASE_LO, lower_32_bits(rh->xfer_dma));
+		rh_reg_write(CMD_RING_BASE_HI, upper_32_bits(rh->xfer_dma));
+		rh_reg_write(RESP_RING_BASE_LO, lower_32_bits(rh->resp_dma));
+		rh_reg_write(RESP_RING_BASE_HI, upper_32_bits(rh->resp_dma));
 
 		regval = FIELD_PREP(CR_RING_SIZE, rh->xfer_entries);
 		rh_reg_write(CR_SETUP, regval);
@@ -294,7 +279,17 @@ static int hci_dma_init(struct i3c_hci *hci)
 
 		rh->ibi_chunk_sz = dma_get_cache_alignment();
 		rh->ibi_chunk_sz *= IBI_CHUNK_CACHELINES;
-		BUG_ON(rh->ibi_chunk_sz > 256);
+		/*
+		 * Round IBI data chunk size to number of bytes supported by
+		 * the HW. Chunk size can be 2^n number of DWORDs which is the
+		 * same as 2^(n+2) bytes, where n is 0..6.
+		 */
+		rh->ibi_chunk_sz = umax(4, rh->ibi_chunk_sz);
+		rh->ibi_chunk_sz = roundup_pow_of_two(rh->ibi_chunk_sz);
+		if (rh->ibi_chunk_sz > 256) {
+			ret = -EINVAL;
+			goto err_out;
+		}
 
 		ibi_status_ring_sz = rh->ibi_status_sz * rh->ibi_status_entries;
 		ibi_data_ring_sz = rh->ibi_chunk_sz * rh->ibi_chunks_total;
@@ -315,6 +310,11 @@ static int hci_dma_init(struct i3c_hci *hci)
 			goto err_out;
 		}
 
+		rh_reg_write(IBI_STATUS_RING_BASE_LO, lower_32_bits(rh->ibi_status_dma));
+		rh_reg_write(IBI_STATUS_RING_BASE_HI, upper_32_bits(rh->ibi_status_dma));
+		rh_reg_write(IBI_DATA_RING_BASE_LO, lower_32_bits(rh->ibi_data_dma));
+		rh_reg_write(IBI_DATA_RING_BASE_HI, upper_32_bits(rh->ibi_data_dma));
+
 		regval = FIELD_PREP(IBI_STATUS_RING_SIZE,
 				    rh->ibi_status_entries) |
 			 FIELD_PREP(IBI_DATA_CHUNK_SIZE,
@@ -404,8 +404,8 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 				hci_dma_unmap_xfer(hci, xfer_list, i);
 				return -ENOMEM;
 			}
-			*ring_data++ = lo32(xfer->data_dma);
-			*ring_data++ = hi32(xfer->data_dma);
+			*ring_data++ = lower_32_bits(xfer->data_dma);
+			*ring_data++ = upper_32_bits(xfer->data_dma);
 		} else {
 			*ring_data++ = 0;
 			*ring_data++ = 0;
diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index bb299ce..0a68fd1 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -790,7 +790,20 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 	int ret, i;
 
 	while (true) {
-		/* Enter/proceed with DAA */
+		/* SVC_I3C_MCTRL_REQUEST_PROC_DAA have two mode, ENTER DAA or PROCESS DAA.
+		 *
+		 * ENTER DAA:
+		 *   1 will issue START, 7E, ENTDAA, and then emits 7E/R to process first target.
+		 *   2 Stops just before the new Dynamic Address (DA) is to be emitted.
+		 *
+		 * PROCESS DAA:
+		 *   1 The DA is written using MWDATAB or ADDR bits 6:0.
+		 *   2 ProcessDAA is requested again to write the new address, and then starts the
+		 *     next (START, 7E, ENTDAA)  unless marked to STOP; an MSTATUS indicating NACK
+		 *     means DA was not accepted (e.g. parity error). If PROCESSDAA is NACKed on the
+		 *     7E/R, which means no more Slaves need a DA, then a COMPLETE will be signaled
+		 *     (along with DONE), and a STOP issued automatically.
+		 */
 		writel(SVC_I3C_MCTRL_REQUEST_PROC_DAA |
 		       SVC_I3C_MCTRL_TYPE_I3C |
 		       SVC_I3C_MCTRL_IBIRESP_NACK |
@@ -807,7 +820,7 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 						SVC_I3C_MSTATUS_MCTRLDONE(reg),
 						1, 1000);
 		if (ret)
-			return ret;
+			break;
 
 		if (SVC_I3C_MSTATUS_RXPEND(reg)) {
 			u8 data[6];
@@ -819,7 +832,7 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 			 */
 			ret = svc_i3c_master_readb(master, data, 6);
 			if (ret)
-				return ret;
+				break;
 
 			for (i = 0; i < 6; i++)
 				prov_id[dev_nb] |= (u64)(data[i]) << (8 * (5 - i));
@@ -827,7 +840,7 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 			/* We do not care about the BCR and DCR yet */
 			ret = svc_i3c_master_readb(master, data, 2);
 			if (ret)
-				return ret;
+				break;
 		} else if (SVC_I3C_MSTATUS_MCTRLDONE(reg)) {
 			if (SVC_I3C_MSTATUS_STATE_IDLE(reg) &&
 			    SVC_I3C_MSTATUS_COMPLETE(reg)) {
@@ -835,12 +848,23 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 				 * All devices received and acked they dynamic
 				 * address, this is the natural end of the DAA
 				 * procedure.
+				 *
+				 * Hardware will auto emit STOP at this case.
 				 */
-				break;
+				*count = dev_nb;
+				return 0;
+
 			} else if (SVC_I3C_MSTATUS_NACKED(reg)) {
 				/* No I3C devices attached */
-				if (dev_nb == 0)
+				if (dev_nb == 0) {
+					/*
+					 * Hardware can't treat first NACK for ENTAA as normal
+					 * COMPLETE. So need manual emit STOP.
+					 */
+					ret = 0;
+					*count = 0;
 					break;
+				}
 
 				/*
 				 * A slave device nacked the address, this is
@@ -849,8 +873,10 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 				 * answer again immediately and shall ack the
 				 * address this time.
 				 */
-				if (prov_id[dev_nb] == nacking_prov_id)
-					return -EIO;
+				if (prov_id[dev_nb] == nacking_prov_id) {
+					ret = -EIO;
+					break;
+				}
 
 				dev_nb--;
 				nacking_prov_id = prov_id[dev_nb];
@@ -858,7 +884,7 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 
 				continue;
 			} else {
-				return -EIO;
+				break;
 			}
 		}
 
@@ -870,12 +896,12 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 						SVC_I3C_MSTATUS_BETWEEN(reg),
 						0, 1000);
 		if (ret)
-			return ret;
+			break;
 
 		/* Give the slave device a suitable dynamic address */
 		ret = i3c_master_get_free_addr(&master->base, last_addr + 1);
 		if (ret < 0)
-			return ret;
+			break;
 
 		addrs[dev_nb] = ret;
 		dev_dbg(master->dev, "DAA: device %d assigned to 0x%02x\n",
@@ -885,9 +911,9 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master,
 		last_addr = addrs[dev_nb++];
 	}
 
-	*count = dev_nb;
-
-	return 0;
+	/* Need manual issue STOP except for Complete condition */
+	svc_i3c_master_emit_stop(master);
+	return ret;
 }
 
 static int svc_i3c_update_ibirules(struct svc_i3c_master *master)
@@ -961,11 +987,10 @@ static int svc_i3c_master_do_daa(struct i3c_master_controller *m)
 	spin_lock_irqsave(&master->xferqueue.lock, flags);
 	ret = svc_i3c_master_do_daa_locked(master, addrs, &dev_nb);
 	spin_unlock_irqrestore(&master->xferqueue.lock, flags);
-	if (ret) {
-		svc_i3c_master_emit_stop(master);
-		svc_i3c_master_clear_merrwarn(master);
+
+	svc_i3c_master_clear_merrwarn(master);
+	if (ret)
 		goto rpm_out;
-	}
 
 	/* Register all devices who participated to the core */
 	for (i = 0; i < dev_nb; i++) {
@@ -1052,29 +1077,59 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 			       u8 *in, const u8 *out, unsigned int xfer_len,
 			       unsigned int *actual_len, bool continued)
 {
+	int retry = 2;
 	u32 reg;
 	int ret;
 
 	/* clean SVC_I3C_MINT_IBIWON w1c bits */
 	writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
 
-	writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
-	       xfer_type |
-	       SVC_I3C_MCTRL_IBIRESP_NACK |
-	       SVC_I3C_MCTRL_DIR(rnw) |
-	       SVC_I3C_MCTRL_ADDR(addr) |
-	       SVC_I3C_MCTRL_RDTERM(*actual_len),
-	       master->regs + SVC_I3C_MCTRL);
 
-	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
+	while (retry--) {
+		writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
+		       xfer_type |
+		       SVC_I3C_MCTRL_IBIRESP_NACK |
+		       SVC_I3C_MCTRL_DIR(rnw) |
+		       SVC_I3C_MCTRL_ADDR(addr) |
+		       SVC_I3C_MCTRL_RDTERM(*actual_len),
+		       master->regs + SVC_I3C_MCTRL);
+
+		ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
 				 SVC_I3C_MSTATUS_MCTRLDONE(reg), 0, 1000);
-	if (ret)
-		goto emit_stop;
+		if (ret)
+			goto emit_stop;
 
-	if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
-		ret = -ENXIO;
-		*actual_len = 0;
-		goto emit_stop;
+		if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
+			/*
+			 * According to I3C Spec 1.1.1, 11-Jun-2021, section: 5.1.2.2.3.
+			 * If the Controller chooses to start an I3C Message with an I3C Dynamic
+			 * Address, then special provisions shall be made because that same I3C
+			 * Target may be initiating an IBI or a Controller Role Request. So, one of
+			 * three things may happen: (skip 1, 2)
+			 *
+			 * 3. The Addresses match and the RnW bits also match, and so neither
+			 * Controller nor Target will ACK since both are expecting the other side to
+			 * provide ACK. As a result, each side might think it had "won" arbitration,
+			 * but neither side would continue, as each would subsequently see that the
+			 * other did not provide ACK.
+			 * ...
+			 * For either value of RnW: Due to the NACK, the Controller shall defer the
+			 * Private Write or Private Read, and should typically transmit the Target
+			 * Address again after a Repeated START (i.e., the next one or any one prior
+			 * to a STOP in the Frame). Since the Address Header following a Repeated
+			 * START is not arbitrated, the Controller will always win (see Section
+			 * 5.1.2.2.4).
+			 */
+			if (retry && addr != 0x7e) {
+				writel(SVC_I3C_MERRWARN_NACK, master->regs + SVC_I3C_MERRWARN);
+			} else {
+				ret = -ENXIO;
+				*actual_len = 0;
+				goto emit_stop;
+			}
+		} else {
+			break;
+		}
 	}
 
 	/*
@@ -1321,7 +1376,7 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master,
 	cmd->addr = ccc->dests[0].addr;
 	cmd->rnw = ccc->rnw;
 	cmd->in = ccc->rnw ? ccc->dests[0].payload.data : NULL;
-	cmd->out = ccc->rnw ? NULL : ccc->dests[0].payload.data,
+	cmd->out = ccc->rnw ? NULL : ccc->dests[0].payload.data;
 	cmd->len = xfer_len;
 	cmd->actual_len = actual_len;
 	cmd->continued = false;
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index 95fa857..426e3c9 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -564,13 +564,11 @@ static int tiadc_parse_dt(struct platform_device *pdev,
 			  struct tiadc_device *adc_dev)
 {
 	struct device_node *node = pdev->dev.of_node;
-	struct property *prop;
-	const __be32 *cur;
 	int channels = 0;
 	u32 val;
 	int i;
 
-	of_property_for_each_u32(node, "ti,adc-channels", prop, cur, val) {
+	of_property_for_each_u32(node, "ti,adc-channels", val) {
 		adc_dev->channel_line[channels] = val;
 
 		/* Set Default values for optional DT parameters */
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index ad39ac6f..10cc958 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -806,9 +806,9 @@ void gameport_unregister_driver(struct gameport_driver *drv)
 }
 EXPORT_SYMBOL(gameport_unregister_driver);
 
-static int gameport_bus_match(struct device *dev, struct device_driver *drv)
+static int gameport_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct gameport_driver *gameport_drv = to_gameport_driver(drv);
+	const struct gameport_driver *gameport_drv = to_gameport_driver(drv);
 
 	return !gameport_drv->ignore;
 }
diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c
index 3430302..3aee048 100644
--- a/drivers/input/rmi4/rmi_bus.c
+++ b/drivers/input/rmi4/rmi_bus.c
@@ -144,9 +144,9 @@ bool rmi_is_function_device(struct device *dev)
 	return dev->type == &rmi_function_type;
 }
 
-static int rmi_function_match(struct device *dev, struct device_driver *drv)
+static int rmi_function_match(struct device *dev, const struct device_driver *drv)
 {
-	struct rmi_function_handler *handler = to_rmi_function_handler(drv);
+	const struct rmi_function_handler *handler = to_rmi_function_handler(drv);
 	struct rmi_function *fn = to_rmi_function(dev);
 
 	return fn->fd.function_number == handler->func;
@@ -333,7 +333,7 @@ EXPORT_SYMBOL_GPL(rmi_unregister_function_handler);
 
 /* Bus specific stuff */
 
-static int rmi_bus_match(struct device *dev, struct device_driver *drv)
+static int rmi_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	bool physical = rmi_is_physical_device(dev);
 
diff --git a/drivers/input/rmi4/rmi_bus.h b/drivers/input/rmi4/rmi_bus.h
index ea46ad9..d4d0d82 100644
--- a/drivers/input/rmi4/rmi_bus.h
+++ b/drivers/input/rmi4/rmi_bus.h
@@ -87,7 +87,7 @@ struct rmi_function_handler {
 };
 
 #define to_rmi_function_handler(d) \
-		container_of(d, struct rmi_function_handler, driver)
+		container_of_const(d, struct rmi_function_handler, driver)
 
 int __must_check __rmi_register_function_handler(struct rmi_function_handler *,
 						 struct module *, const char *);
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index ef9ea29..2168b6c 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -1258,7 +1258,7 @@ static struct rmi_driver rmi_physical_driver = {
 	.set_input_params = rmi_driver_set_input_params,
 };
 
-bool rmi_is_physical_driver(struct device_driver *drv)
+bool rmi_is_physical_driver(const struct device_driver *drv)
 {
 	return drv == &rmi_physical_driver.driver;
 }
diff --git a/drivers/input/rmi4/rmi_driver.h b/drivers/input/rmi4/rmi_driver.h
index 1c6c608..3bfe901 100644
--- a/drivers/input/rmi4/rmi_driver.h
+++ b/drivers/input/rmi4/rmi_driver.h
@@ -84,7 +84,7 @@ int rmi_register_desc_calc_reg_offset(
 bool rmi_register_desc_has_subpacket(const struct rmi_register_desc_item *item,
 			u8 subpacket);
 
-bool rmi_is_physical_driver(struct device_driver *);
+bool rmi_is_physical_driver(const struct device_driver *);
 int rmi_register_physical_driver(void);
 void rmi_unregister_physical_driver(void);
 void rmi_free_function_list(struct rmi_device *rmi_dev);
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 0496749..97d8eac 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -877,10 +877,10 @@ static void serio_set_drv(struct serio *serio, struct serio_driver *drv)
 	serio_continue_rx(serio);
 }
 
-static int serio_bus_match(struct device *dev, struct device_driver *drv)
+static int serio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct serio *serio = to_serio_port(dev);
-	struct serio_driver *serio_drv = to_serio_driver(drv);
+	const struct serio_driver *serio_drv = to_serio_driver(drv);
 
 	if (serio->manual_bind || serio_drv->manual_bind)
 		return 0;
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 9d9a7fd..1074ee2 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -588,9 +588,9 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo
 {
 	struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg);
 
-	cfg->pgsize_bitmap  = AMD_IOMMU_PGSIZES,
-	cfg->ias            = IOMMU_IN_ADDR_BIT_SIZE,
-	cfg->oas            = IOMMU_OUT_ADDR_BIT_SIZE,
+	cfg->pgsize_bitmap  = AMD_IOMMU_PGSIZES;
+	cfg->ias            = IOMMU_IN_ADDR_BIT_SIZE;
+	cfg->oas            = IOMMU_OUT_ADDR_BIT_SIZE;
 	cfg->tlb            = &v1_flush_ops;
 
 	pgtable->iop.ops.map_pages    = iommu_v1_map_pages;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 4b2994b..2fce4f6 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -277,7 +277,7 @@ static int nvidia_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	 */
 	if (of_device_is_compatible(np, "nvidia,tegra234-smmu") ||
 	    of_device_is_compatible(np, "nvidia,tegra194-smmu")) {
-		smmu->pgsize_bitmap = PAGE_SIZE;
+		smmu->pgsize_bitmap &= GENMASK(PAGE_SHIFT, 0);
 		pgtbl_cfg->pgsize_bitmap = smmu->pgsize_bitmap;
 	}
 
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index ba53571..a2f4ffe 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -232,8 +232,8 @@ static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom)
 
 	pgt_size = sprd_iommu_pgt_size(&dom->domain);
 	dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa);
-	dom->sdev = NULL;
 	sprd_iommu_hw_en(dom->sdev, false);
+	dom->sdev = NULL;
 }
 
 static void sprd_iommu_domain_free(struct iommu_domain *domain)
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index 866bf48..57d232c 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -13,7 +13,7 @@
 #include <linux/ipack.h>
 
 #define to_ipack_dev(device) container_of(device, struct ipack_device, dev)
-#define to_ipack_driver(drv) container_of(drv, struct ipack_driver, driver)
+#define to_ipack_driver(drv) container_of_const(drv, struct ipack_driver, driver)
 
 static DEFINE_IDA(ipack_ida);
 
@@ -49,10 +49,10 @@ ipack_match_id(const struct ipack_device_id *ids, struct ipack_device *idev)
 	return NULL;
 }
 
-static int ipack_bus_match(struct device *dev, struct device_driver *drv)
+static int ipack_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct ipack_device *idev = to_ipack_dev(dev);
-	struct ipack_driver *idrv = to_ipack_driver(drv);
+	const struct ipack_driver *idrv = to_ipack_driver(drv);
 	const struct ipack_device_id *found_id;
 
 	found_id = ipack_match_id(idrv->id_table, idev);
diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c
index 072bd22..4525366 100644
--- a/drivers/irqchip/irq-atmel-aic-common.c
+++ b/drivers/irqchip/irq-atmel-aic-common.c
@@ -111,8 +111,6 @@ static void __init aic_common_ext_irq_of_init(struct irq_domain *domain)
 	struct device_node *node = irq_domain_get_of_node(domain);
 	struct irq_chip_generic *gc;
 	struct aic_chip_data *aic;
-	struct property *prop;
-	const __be32 *p;
 	u32 hwirq;
 
 	gc = irq_get_domain_generic_chip(domain, 0);
@@ -120,7 +118,7 @@ static void __init aic_common_ext_irq_of_init(struct irq_domain *domain)
 	aic = gc->private;
 	aic->ext_irqs |= 1;
 
-	of_property_for_each_u32(node, "atmel,external-irqs", prop, p, hwirq) {
+	of_property_for_each_u32(node, "atmel,external-irqs", hwirq) {
 		gc = irq_get_domain_generic_chip(domain, hwirq);
 		if (!gc) {
 			pr_warn("AIC: external irq %d >= %d skip it\n",
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index 1d9bb28..5d6b8e0 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -190,13 +190,11 @@ static void __init pic32_ext_irq_of_init(struct irq_domain *domain)
 {
 	struct device_node *node = irq_domain_get_of_node(domain);
 	struct evic_chip_data *priv = domain->host_data;
-	struct property *prop;
-	const __le32 *p;
 	u32 hwirq;
 	int i = 0;
 	const char *pname = "microchip,external-irqs";
 
-	of_property_for_each_u32(node, pname, prop, p, hwirq) {
+	of_property_for_each_u32(node, pname, hwirq) {
 		if (i >= ARRAY_SIZE(priv->ext_irqs)) {
 			pr_warn("More than %d external irq, skip rest\n",
 				ARRAY_SIZE(priv->ext_irqs));
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 0d2928d..e5a483f 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -1901,7 +1901,7 @@ hfcmulti_dtmf(struct hfc_multi *hc)
 static void
 hfcmulti_tx(struct hfc_multi *hc, int ch)
 {
-	int i, ii, temp, len = 0;
+	int i, ii, temp, tmp_len, len = 0;
 	int Zspace, z1, z2; /* must be int for calculation */
 	int Fspace, f1, f2;
 	u_char *d;
@@ -2122,14 +2122,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch)
 		HFC_wait_nodebug(hc);
 	}
 
+	tmp_len = (*sp)->len;
 	dev_kfree_skb(*sp);
 	/* check for next frame */
 	if (bch && get_next_bframe(bch)) {
-		len = (*sp)->len;
+		len = tmp_len;
 		goto next_frame;
 	}
 	if (dch && get_next_dframe(dch)) {
-		len = (*sp)->len;
+		len = tmp_len;
 		goto next_frame;
 	}
 
diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c
index b7b3ef1..b461b1b 100644
--- a/drivers/macintosh/mac_hid.c
+++ b/drivers/macintosh/mac_hid.c
@@ -183,7 +183,7 @@ static void mac_hid_stop_emulation(void)
 	mac_hid_destroy_emumouse();
 }
 
-static int mac_hid_toggle_emumouse(struct ctl_table *table, int write,
+static int mac_hid_toggle_emumouse(const struct ctl_table *table, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = table->data;
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 565f1e2..1362620 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -36,7 +36,7 @@
 
 static struct macio_chip      *macio_on_hold;
 
-static int macio_bus_match(struct device *dev, struct device_driver *drv) 
+static int macio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct of_device_id * matches = drv->of_match_table;
 
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index 267045b..91bbd94 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -28,9 +28,9 @@ static const struct mcb_device_id *mcb_match_id(const struct mcb_device_id *ids,
 	return NULL;
 }
 
-static int mcb_match(struct device *dev, struct device_driver *drv)
+static int mcb_match(struct device *dev, const struct device_driver *drv)
 {
-	struct mcb_driver *mdrv = to_mcb_driver(drv);
+	const struct mcb_driver *mdrv = to_mcb_driver(drv);
 	struct mcb_device *mdev = to_mcb_device(dev);
 	const struct mcb_device_id *found_id;
 
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 48ac628..51e6964 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1776,7 +1776,7 @@ static void integrity_metadata(struct work_struct *w)
 		struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 		char *checksums;
 		unsigned int extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
-		char checksums_onstack[max_t(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+		char checksums_onstack[MAX_T(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 		sector_t sector;
 		unsigned int sectors_to_process;
 
@@ -2064,7 +2064,7 @@ static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio,
 				} while (++s < ic->sectors_per_block);
 #ifdef INTERNAL_VERIFY
 				if (ic->internal_hash) {
-					char checksums_onstack[max_t(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+					char checksums_onstack[MAX_T(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 
 					integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
 					if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
@@ -2837,7 +2837,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned int write_start
 				    unlikely(from_replay) &&
 #endif
 				    ic->internal_hash) {
-					char test_tag[max_t(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+					char test_tag[MAX_T(size_t, HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 
 					integrity_sector_checksum(ic, sec + ((l - j) << ic->sb->log2_sectors_per_block),
 								  (char *)access_journal_data(ic, i, l), test_tag);
diff --git a/drivers/media/pci/bt8xx/bttv-gpio.c b/drivers/media/pci/bt8xx/bttv-gpio.c
index 6b7fea5..59a6f16 100644
--- a/drivers/media/pci/bt8xx/bttv-gpio.c
+++ b/drivers/media/pci/bt8xx/bttv-gpio.c
@@ -28,9 +28,9 @@
 /* ----------------------------------------------------------------------- */
 /* internal: the bttv "bus"                                                */
 
-static int bttv_sub_bus_match(struct device *dev, struct device_driver *drv)
+static int bttv_sub_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct bttv_sub_driver *sub = to_bttv_sub_drv(drv);
+	const struct bttv_sub_driver *sub = to_bttv_sub_drv(drv);
 	int len = strlen(sub->wanted);
 
 	if (0 == strncmp(dev_name(dev), sub->wanted, len))
diff --git a/drivers/media/pci/bt8xx/bttv.h b/drivers/media/pci/bt8xx/bttv.h
index eed7eeb..97bbed9 100644
--- a/drivers/media/pci/bt8xx/bttv.h
+++ b/drivers/media/pci/bt8xx/bttv.h
@@ -341,7 +341,7 @@ struct bttv_sub_driver {
 	int                    (*probe)(struct bttv_sub_device *sub);
 	void                   (*remove)(struct bttv_sub_device *sub);
 };
-#define to_bttv_sub_drv(x) container_of((x), struct bttv_sub_driver, drv)
+#define to_bttv_sub_drv(x) container_of_const((x), struct bttv_sub_driver, drv)
 
 int bttv_sub_register(struct bttv_sub_driver *drv, char *wanted);
 int bttv_sub_unregister(struct bttv_sub_driver *drv);
diff --git a/drivers/media/pci/intel/ipu6/ipu6-bus.h b/drivers/media/pci/intel/ipu6/ipu6-bus.h
index b26c6ae..bb4926d 100644
--- a/drivers/media/pci/intel/ipu6/ipu6-bus.h
+++ b/drivers/media/pci/intel/ipu6/ipu6-bus.h
@@ -21,7 +21,7 @@ struct ipu6_buttress_ctrl;
 
 struct ipu6_bus_device {
 	struct auxiliary_device auxdev;
-	struct auxiliary_driver *auxdrv;
+	const struct auxiliary_driver *auxdrv;
 	const struct ipu6_auxdrv_data *auxdrv_data;
 	struct list_head list;
 	void *pdata;
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 52aea416..717c441 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -828,8 +828,10 @@ struct rc_dev *rc_dev_get_from_fd(int fd, bool write)
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (write && !(f.file->f_mode & FMODE_WRITE))
+	if (write && !(f.file->f_mode & FMODE_WRITE)) {
+		fdput(f);
 		return ERR_PTR(-EPERM);
+	}
 
 	fh = f.file->private_data;
 	dev = fh->rc;
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index 23fea51..9a3a784 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -38,13 +38,12 @@ static int memstick_dev_match(struct memstick_dev *card,
 	return 0;
 }
 
-static int memstick_bus_match(struct device *dev, struct device_driver *drv)
+static int memstick_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct memstick_dev *card = container_of(dev, struct memstick_dev,
 						 dev);
-	struct memstick_driver *ms_drv = container_of(drv,
-						      struct memstick_driver,
-						      driver);
+	const struct memstick_driver *ms_drv = container_of_const(drv, struct memstick_driver,
+								  driver);
 	struct memstick_device_id *ids = ms_drv->id_table;
 
 	if (ids) {
diff --git a/drivers/mfd/mcp-core.c b/drivers/mfd/mcp-core.c
index 16ca233..be08eae 100644
--- a/drivers/mfd/mcp-core.c
+++ b/drivers/mfd/mcp-core.c
@@ -20,7 +20,7 @@
 #define to_mcp(d)		container_of(d, struct mcp, attached_device)
 #define to_mcp_driver(d)	container_of(d, struct mcp_driver, drv)
 
-static int mcp_bus_match(struct device *dev, struct device_driver *drv)
+static int mcp_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	return 1;
 }
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index 4bbd542..0c1364d 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -119,8 +119,6 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	struct clk *clk;
 	struct device_node *node;
 	struct mfd_cell *cell;
-	struct property *prop;
-	const __be32 *cur;
 	bool use_tsc = false, use_mag = false;
 	u32 val;
 	int err;
@@ -167,7 +165,7 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	}
 
 	node = of_get_child_by_name(pdev->dev.of_node, "adc");
-	of_property_for_each_u32(node, "ti,adc-channels", prop, cur, val) {
+	of_property_for_each_u32(node, "ti,adc-channels", val) {
 		adc_channels++;
 		if (val > 7) {
 			dev_err(&pdev->dev, " PIN numbers are 0..7 (not %d)\n",
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 99393f6..5576146 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -19,7 +19,7 @@
 #include "mei_dev.h"
 #include "client.h"
 
-#define to_mei_cl_driver(d) container_of(d, struct mei_cl_driver, driver)
+#define to_mei_cl_driver(d) container_of_const(d, struct mei_cl_driver, driver)
 
 /**
  * __mei_cl_send - internal client send (write)
@@ -1124,7 +1124,7 @@ struct mei_cl_device_id *mei_cl_device_find(const struct mei_cl_device *cldev,
  *
  * Return:  1 if matching device was found 0 otherwise
  */
-static int mei_cl_device_match(struct device *dev, struct device_driver *drv)
+static int mei_cl_device_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct mei_cl_device *cldev = to_mei_cl_device(dev);
 	const struct mei_cl_driver *cldrv = to_mei_cl_driver(drv);
diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c
index fd9c3cbb..12355d34 100644
--- a/drivers/misc/tifm_core.c
+++ b/drivers/misc/tifm_core.c
@@ -38,11 +38,11 @@ static int tifm_dev_match(struct tifm_dev *sock, struct tifm_device_id *id)
 	return 0;
 }
 
-static int tifm_bus_match(struct device *dev, struct device_driver *drv)
+static int tifm_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct tifm_dev *sock = container_of(dev, struct tifm_dev, dev);
-	struct tifm_driver *fm_drv = container_of(drv, struct tifm_driver,
-						  driver);
+	const struct tifm_driver *fm_drv = container_of_const(drv, struct tifm_driver,
+							      driver);
 	struct tifm_device_id *ids = fm_drv->id_table;
 
 	if (ids) {
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index c5fdfe2..b66b637 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -26,7 +26,7 @@
 #include "sdio_cis.h"
 #include "sdio_bus.h"
 
-#define to_sdio_driver(d)	container_of(d, struct sdio_driver, drv)
+#define to_sdio_driver(d)	container_of_const(d, struct sdio_driver, drv)
 
 /* show configuration fields */
 #define sdio_config_attr(field, format_string, args...)			\
@@ -91,7 +91,7 @@ static const struct sdio_device_id *sdio_match_one(struct sdio_func *func,
 }
 
 static const struct sdio_device_id *sdio_match_device(struct sdio_func *func,
-	struct sdio_driver *sdrv)
+	const struct sdio_driver *sdrv)
 {
 	const struct sdio_device_id *ids;
 
@@ -108,10 +108,10 @@ static const struct sdio_device_id *sdio_match_device(struct sdio_func *func,
 	return NULL;
 }
 
-static int sdio_bus_match(struct device *dev, struct device_driver *drv)
+static int sdio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct sdio_func *func = dev_to_sdio_func(dev);
-	struct sdio_driver *sdrv = to_sdio_driver(drv);
+	const struct sdio_driver *sdrv = to_sdio_driver(drv);
 
 	if (sdio_match_device(func, sdrv))
 		return 1;
@@ -129,7 +129,7 @@ sdio_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
 			"SDIO_CLASS=%02X", func->class))
 		return -ENOMEM;
 
-	if (add_uevent_var(env, 
+	if (add_uevent_var(env,
 			"SDIO_ID=%04X:%04X", func->vendor, func->device))
 		return -ENOMEM;
 
diff --git a/drivers/most/core.c b/drivers/most/core.c
index 10342e8..a635d50 100644
--- a/drivers/most/core.c
+++ b/drivers/most/core.c
@@ -491,7 +491,7 @@ static int print_links(struct device *dev, void *data)
 	return 0;
 }
 
-static int most_match(struct device *dev, struct device_driver *drv)
+static int most_match(struct device *dev, const struct device_driver *drv)
 {
 	if (!strcmp(dev_name(dev), "most"))
 		return 0;
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index f82e342..60d0155 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -390,7 +390,8 @@ int ubiblock_create(struct ubi_volume_info *vi)
 
 	ret = blk_mq_alloc_tag_set(&dev->tag_set);
 	if (ret) {
-		dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed");
+		pr_err("ubiblock%d_%d: blk_mq_alloc_tag_set failed\n",
+			dev->ubi_num, dev->vol_id);
 		goto out_free_dev;
 	}
 
@@ -407,8 +408,8 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	gd->minors = 1;
 	gd->first_minor = idr_alloc(&ubiblock_minor_idr, dev, 0, 0, GFP_KERNEL);
 	if (gd->first_minor < 0) {
-		dev_err(disk_to_dev(gd),
-			"block: dynamic minor allocation failed");
+		pr_err("ubiblock%d_%d: block: dynamic minor allocation failed\n",
+			dev->ubi_num, dev->vol_id);
 		ret = -ENODEV;
 		goto out_cleanup_disk;
 	}
@@ -669,7 +670,7 @@ int __init ubiblock_init(void)
 	return ret;
 }
 
-void __exit ubiblock_exit(void)
+void ubiblock_exit(void)
 {
 	ubi_unregister_volume_notifier(&ubiblock_notifier);
 	ubiblock_remove_all();
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index a7e3a62..30be4ed 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -112,7 +112,7 @@ static struct attribute *ubi_class_attrs[] = {
 ATTRIBUTE_GROUPS(ubi_class);
 
 /* Root UBI "class" object (corresponds to '/<sysfs>/class/ubi/') */
-struct class ubi_class = {
+const struct class ubi_class = {
 	.name		= UBI_NAME_STR,
 	.class_groups	= ubi_class_groups,
 };
@@ -1372,7 +1372,7 @@ static int __init ubi_init(void)
 
 		/* See comment above re-ubi_is_module(). */
 		if (ubi_is_module())
-			goto out_slab;
+			goto out_debugfs;
 	}
 
 	register_mtd_user(&ubi_mtd_notifier);
@@ -1387,6 +1387,9 @@ static int __init ubi_init(void)
 
 out_mtd_notifier:
 	unregister_mtd_user(&ubi_mtd_notifier);
+	ubiblock_exit();
+out_debugfs:
+	ubi_debugfs_exit();
 out_slab:
 	kmem_cache_destroy(ubi_wl_entry_slab);
 out_dev_unreg:
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index d57f52b..9ec3b8b 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -598,9 +598,9 @@ int ubi_debugfs_init_dev(struct ubi_device *ubi)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	n = snprintf(d->dfs_dir_name, UBI_DFS_DIR_LEN + 1, UBI_DFS_DIR_NAME,
+	n = snprintf(d->dfs_dir_name, UBI_DFS_DIR_LEN, UBI_DFS_DIR_NAME,
 		     ubi->ubi_num);
-	if (n > UBI_DFS_DIR_LEN) {
+	if (n >= UBI_DFS_DIR_LEN) {
 		/* The array size is too small */
 		return -EINVAL;
 	}
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index e5ac3cd..c7ba7a1 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -1564,6 +1564,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
 					  GFP_KERNEL);
 		if (!fm_eba[i]) {
 			ret = -ENOMEM;
+			kfree(scan_eba[i]);
 			goto out_free;
 		}
 
@@ -1599,7 +1600,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
 	}
 
 out_free:
-	for (i = 0; i < num_volumes; i++) {
+	while (--i >= 0) {
 		if (!ubi->volumes[i])
 			continue;
 
diff --git a/drivers/mtd/ubi/nvmem.c b/drivers/mtd/ubi/nvmem.c
index 8aeb9c4..a94a1a9 100644
--- a/drivers/mtd/ubi/nvmem.c
+++ b/drivers/mtd/ubi/nvmem.c
@@ -6,7 +6,6 @@
 /* UBI NVMEM provider */
 #include "ubi.h"
 #include <linux/nvmem-provider.h>
-#include <asm/div64.h>
 
 /* List of all NVMEM devices */
 static LIST_HEAD(nvmem_devices);
@@ -27,14 +26,15 @@ static int ubi_nvmem_reg_read(void *priv, unsigned int from,
 	struct ubi_nvmem *unv = priv;
 	struct ubi_volume_desc *desc;
 	uint32_t offs;
-	uint64_t lnum = from;
+	uint32_t lnum;
 	int err = 0;
 
 	desc = ubi_open_volume(unv->ubi_num, unv->vol_id, UBI_READONLY);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
 
-	offs = do_div(lnum, unv->usable_leb_size);
+	offs = from % unv->usable_leb_size;
+	lnum = from / unv->usable_leb_size;
 	while (bytes_left) {
 		to_read = unv->usable_leb_size - offs;
 
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 32009a2..1c9e874 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -420,7 +420,7 @@ struct ubi_debug_info {
 	unsigned int power_cut_min;
 	unsigned int power_cut_max;
 	unsigned int emulate_failures;
-	char dfs_dir_name[UBI_DFS_DIR_LEN + 1];
+	char dfs_dir_name[UBI_DFS_DIR_LEN];
 	struct dentry *dfs_dir;
 	struct dentry *dfs_chk_gen;
 	struct dentry *dfs_chk_io;
@@ -814,7 +814,7 @@ extern struct kmem_cache *ubi_wl_entry_slab;
 extern const struct file_operations ubi_ctrl_cdev_operations;
 extern const struct file_operations ubi_cdev_operations;
 extern const struct file_operations ubi_vol_cdev_operations;
-extern struct class ubi_class;
+extern const struct class ubi_class;
 extern struct mutex ubi_devices_mutex;
 extern struct blocking_notifier_head ubi_notifiers;
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index af9ddd3..1cd92c1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1121,13 +1121,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	return bestslave;
 }
 
+/* must be called in RCU critical section or with RTNL held */
 static bool bond_should_notify_peers(struct bonding *bond)
 {
-	struct slave *slave;
-
-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	rcu_read_unlock();
+	struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
 
 	if (!slave || !bond->send_peer_notif ||
 	    bond->send_peer_notif %
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bb3be33..ffa74c2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4052,6 +4052,7 @@ static void bnxt_reset_rx_ring_struct(struct bnxt *bp,
 
 	rxr->page_pool->p.napi = NULL;
 	rxr->page_pool = NULL;
+	memset(&rxr->xdp_rxq, 0, sizeof(struct xdp_rxq_info));
 
 	ring = &rxr->rx_ring_struct;
 	rmem = &ring->ring_mem;
@@ -15018,6 +15019,16 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	if (rc)
 		return rc;
 
+	rc = xdp_rxq_info_reg(&clone->xdp_rxq, bp->dev, idx, 0);
+	if (rc < 0)
+		goto err_page_pool_destroy;
+
+	rc = xdp_rxq_info_reg_mem_model(&clone->xdp_rxq,
+					MEM_TYPE_PAGE_POOL,
+					clone->page_pool);
+	if (rc)
+		goto err_rxq_info_unreg;
+
 	ring = &clone->rx_ring_struct;
 	rc = bnxt_alloc_ring(bp, &ring->ring_mem);
 	if (rc)
@@ -15047,6 +15058,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
 err_free_rx_ring:
 	bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem);
+err_rxq_info_unreg:
+	xdp_rxq_info_unreg(&clone->xdp_rxq);
+err_page_pool_destroy:
 	clone->page_pool->p.napi = NULL;
 	page_pool_destroy(clone->page_pool);
 	clone->page_pool = NULL;
@@ -15062,6 +15076,8 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	bnxt_free_one_rx_ring(bp, rxr);
 	bnxt_free_one_rx_agg_ring(bp, rxr);
 
+	xdp_rxq_info_unreg(&rxr->xdp_rxq);
+
 	page_pool_destroy(rxr->page_pool);
 	rxr->page_pool = NULL;
 
@@ -15145,6 +15161,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod;
 	rxr->rx_next_cons = clone->rx_next_cons;
 	rxr->page_pool = clone->page_pool;
+	rxr->xdp_rxq = clone->xdp_rxq;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index ba3fa1c..b9e7d3e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -239,7 +239,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 
 		adev = &aux_priv->aux_dev;
 		if (adev->dev.driver) {
-			struct auxiliary_driver *adrv;
+			const struct auxiliary_driver *adrv;
 			pm_message_t pm = {};
 
 			adrv = to_auxiliary_drv(adev->dev.driver);
@@ -277,7 +277,7 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 
 		adev = &aux_priv->aux_dev;
 		if (adev->dev.driver) {
-			struct auxiliary_driver *adrv;
+			const struct auxiliary_driver *adrv;
 
 			adrv = to_auxiliary_drv(adev->dev.driver);
 			edev->en_state = bp->state;
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 0b3cca3..f879426 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -866,22 +866,42 @@ static bool gve_can_send_tso(const struct sk_buff *skb)
 	const int header_len = skb_tcp_all_headers(skb);
 	const int gso_size = shinfo->gso_size;
 	int cur_seg_num_bufs;
+	int prev_frag_size;
 	int cur_seg_size;
 	int i;
 
 	cur_seg_size = skb_headlen(skb) - header_len;
+	prev_frag_size = skb_headlen(skb);
 	cur_seg_num_bufs = cur_seg_size > 0;
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		if (cur_seg_size >= gso_size) {
 			cur_seg_size %= gso_size;
 			cur_seg_num_bufs = cur_seg_size > 0;
+
+			if (prev_frag_size > GVE_TX_MAX_BUF_SIZE_DQO) {
+				int prev_frag_remain = prev_frag_size %
+					GVE_TX_MAX_BUF_SIZE_DQO;
+
+				/* If the last descriptor of the previous frag
+				 * is less than cur_seg_size, the segment will
+				 * span two descriptors in the previous frag.
+				 * Since max gso size (9728) is less than
+				 * GVE_TX_MAX_BUF_SIZE_DQO, it is impossible
+				 * for the segment to span more than two
+				 * descriptors.
+				 */
+				if (prev_frag_remain &&
+				    cur_seg_size > prev_frag_remain)
+					cur_seg_num_bufs++;
+			}
 		}
 
 		if (unlikely(++cur_seg_num_bufs > max_bufs_per_seg))
 			return false;
 
-		cur_seg_size += skb_frag_size(&shinfo->frags[i]);
+		prev_frag_size = skb_frag_size(&shinfo->frags[i]);
+		cur_seg_size += prev_frag_size;
 	}
 
 	return true;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index e3cab8e..5412eff 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -534,7 +534,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
  *
  * Returns the number of available flow director filters to this VSI
  */
-static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
+int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
 {
 	u16 vsi_num = ice_get_hw_vsi_num(hw, vsi->idx);
 	u16 num_guar;
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 021ecba..ab5b118 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -207,6 +207,8 @@ struct ice_fdir_base_pkt {
 	const u8 *tun_pkt;
 };
 
+struct ice_vsi;
+
 int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
 int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
 int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
@@ -218,6 +220,7 @@ int
 ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 			  u8 *pkt, bool frag, bool tun);
 int ice_get_fdir_cnt_all(struct ice_hw *hw);
+int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi);
 bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input);
 bool ice_fdir_has_frag(enum ice_fltr_ptype flow);
 struct ice_fdir_fltr *
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 51fac8f..e2786cc 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2915,7 +2915,7 @@ static struct ice_pf *
 ice_ptp_aux_dev_to_owner_pf(struct auxiliary_device *aux_dev)
 {
 	struct ice_ptp_port_owner *ports_owner;
-	struct auxiliary_driver *aux_drv;
+	const struct auxiliary_driver *aux_drv;
 	struct ice_ptp *owner_ptp;
 
 	if (!aux_dev->dev.driver)
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 3caafcd..fe88471 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2400,10 +2400,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
 
 		/* Propagate some data to the recipe database */
 		recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority;
-		recps[idx].need_pass_l2 = root_bufs.content.act_ctrl &
-					  ICE_AQ_RECIPE_ACT_NEED_PASS_L2;
-		recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl &
-					   ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2;
+		recps[idx].need_pass_l2 = !!(root_bufs.content.act_ctrl &
+					     ICE_AQ_RECIPE_ACT_NEED_PASS_L2);
+		recps[idx].allow_pass_l2 = !!(root_bufs.content.act_ctrl &
+					      ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2);
 		bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS);
 		if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) {
 			set_bit(root_bufs.content.result_indx &
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 8e4ff3a..b4feb09 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -536,6 +536,8 @@ static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir)
 		fdir->fdir_fltr_cnt[flow][0] = 0;
 		fdir->fdir_fltr_cnt[flow][1] = 0;
 	}
+
+	fdir->fdir_fltr_cnt_total = 0;
 }
 
 /**
@@ -1560,6 +1562,7 @@ ice_vc_add_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 	resp->status = status;
 	resp->flow_id = conf->flow_id;
 	vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]++;
+	vf->fdir.fdir_fltr_cnt_total++;
 
 	ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
 				    (u8 *)resp, len);
@@ -1624,6 +1627,7 @@ ice_vc_del_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
 	resp->status = status;
 	ice_vc_fdir_remove_entry(vf, conf, conf->flow_id);
 	vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]--;
+	vf->fdir.fdir_fltr_cnt_total--;
 
 	ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
 				    (u8 *)resp, len);
@@ -1790,6 +1794,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	struct virtchnl_fdir_add *stat = NULL;
 	struct virtchnl_fdir_fltr_conf *conf;
 	enum virtchnl_status_code v_ret;
+	struct ice_vsi *vf_vsi;
 	struct device *dev;
 	struct ice_pf *pf;
 	int is_tun = 0;
@@ -1798,6 +1803,17 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 
 	pf = vf->pf;
 	dev = ice_pf_to_dev(pf);
+	vf_vsi = ice_get_vf_vsi(vf);
+
+#define ICE_VF_MAX_FDIR_FILTERS	128
+	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
+	    vf->fdir.fdir_fltr_cnt_total >= ICE_VF_MAX_FDIR_FILTERS) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		dev_err(dev, "Max number of FDIR filters for VF %d is reached\n",
+			vf->vf_id);
+		goto err_exit;
+	}
+
 	ret = ice_vc_fdir_param_check(vf, fltr->vsi_id);
 	if (ret) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
index c5bcc8d..ac6dcab 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
@@ -29,6 +29,7 @@ struct ice_vf_fdir_ctx {
 struct ice_vf_fdir {
 	u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
 	int prof_entry_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
+	u16 fdir_fltr_cnt_total;
 	struct ice_fd_hw_prof **fdir_prof;
 
 	struct idr fdir_rule_idr;
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 16761fd..1c5b85a 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -249,7 +249,7 @@
 #define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
 
 #define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
-#define MBI_RX_AGE_SEL_MASK		GENMASK(18, 17)
+#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
 #define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
 
 #define REG_GDM3_FWD_CFG		GDM3_BASE
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 0cc2dd8..16ca427 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4223,8 +4223,6 @@ static int mtk_free_dev(struct mtk_eth *eth)
 		metadata_dst_free(eth->dsa_meta[i]);
 	}
 
-	free_netdev(eth->dummy_dev);
-
 	return 0;
 }
 
@@ -5090,6 +5088,7 @@ static void mtk_remove(struct platform_device *pdev)
 	netif_napi_del(&eth->tx_napi);
 	netif_napi_del(&eth->rx_napi);
 	mtk_cleanup(eth);
+	free_netdev(eth->dummy_dev);
 	mtk_mdio_cleanup(eth);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 47e7c26..9a79674 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -349,7 +349,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct auxiliary_device *adev;
-	struct auxiliary_driver *adrv;
+	const struct auxiliary_driver *adrv;
 	int ret = 0, i;
 
 	devl_assert_locked(priv_to_devlink(dev));
@@ -406,7 +406,7 @@ void mlx5_detach_device(struct mlx5_core_dev *dev, bool suspend)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct auxiliary_device *adev;
-	struct auxiliary_driver *adrv;
+	const struct auxiliary_driver *adrv;
 	pm_message_t pm = {};
 	int i;
 
diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c
index 577227c..0e6cea4 100644
--- a/drivers/net/ethernet/renesas/rtsn.c
+++ b/drivers/net/ethernet/renesas/rtsn.c
@@ -1358,7 +1358,7 @@ static int rtsn_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int rtsn_remove(struct platform_device *pdev)
+static void rtsn_remove(struct platform_device *pdev)
 {
 	struct rtsn_private *priv = platform_get_drvdata(pdev);
 
@@ -1372,8 +1372,6 @@ static int rtsn_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 
 	free_netdev(priv->ndev);
-
-	return 0;
 }
 
 static struct platform_driver rtsn_driver = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index dbd9f93b..f98741d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -977,7 +977,7 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
 }
 
 static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				    __le16 perfect_match, bool is_double)
+				    u16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 6a987cf..f196cd9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -615,7 +615,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 }
 
 static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
-				      __le16 perfect_match, bool is_double)
+				      u16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 97934cc..e53c323 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -393,7 +393,7 @@ struct stmmac_ops {
 			     struct stmmac_rss *cfg, u32 num_rxq);
 	/* VLAN */
 	void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
-				 __le16 perfect_match, bool is_double);
+				 u16 perfect_match, bool is_double);
 	void (*enable_vlan)(struct mac_device_info *hw, u32 type);
 	void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
 			   struct sk_buff *skb);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4b6a359..f3a1b17 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2912,7 +2912,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 	u32 channels_to_check = tx_channel_count > rx_channel_count ?
 				tx_channel_count : rx_channel_count;
 	u32 chan;
-	int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)];
+	int status[MAX_T(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)];
 
 	/* Make sure we never check beyond our status buffer. */
 	if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status)))
@@ -6641,7 +6641,7 @@ static u32 stmmac_vid_crc32_le(__le16 vid_le)
 static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 {
 	u32 crc, hash = 0;
-	__le16 pmatch = 0;
+	u16 pmatch = 0;
 	int count = 0;
 	u16 vid = 0;
 
@@ -6656,7 +6656,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 		if (count > 2) /* VID = 0 always passes filter */
 			return -EOPNOTSUPP;
 
-		pmatch = cpu_to_le16(vid);
+		pmatch = vid;
 		hash = 0;
 	}
 
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 8b9ead7..7e2f101 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -1375,9 +1375,9 @@ EXPORT_SYMBOL_GPL(mdiobus_c45_modify_changed);
  *   require calling the devices own match function, since different classes
  *   of MDIO devices have different match criteria.
  */
-static int mdio_bus_match(struct device *dev, struct device_driver *drv)
+static int mdio_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct mdio_driver *mdiodrv = to_mdio_driver(drv);
+	const struct mdio_driver *mdiodrv = to_mdio_driver(drv);
 	struct mdio_device *mdio = to_mdio_device(dev);
 
 	/* Both the driver and device must type-match */
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 73f6539..e747ee6 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -35,10 +35,10 @@ static void mdio_device_release(struct device *dev)
 	kfree(to_mdio_device(dev));
 }
 
-int mdio_device_bus_match(struct device *dev, struct device_driver *drv)
+int mdio_device_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct mdio_device *mdiodev = to_mdio_device(dev);
-	struct mdio_driver *mdiodrv = to_mdio_driver(drv);
+	const struct mdio_driver *mdiodrv = to_mdio_driver(drv);
 
 	if (mdiodrv->mdiodrv.flags & MDIO_DEVICE_IS_PHY)
 		return 0;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 70b07e6..7752e938 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -533,10 +533,10 @@ static int phy_scan_fixups(struct phy_device *phydev)
 	return 0;
 }
 
-static int phy_bus_match(struct device *dev, struct device_driver *drv)
+static int phy_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct phy_device *phydev = to_phy_device(dev);
-	struct phy_driver *phydrv = to_phy_driver(drv);
+	const struct phy_driver *phydrv = to_phy_driver(drv);
 	const int num_ids = ARRAY_SIZE(phydev->c45_ids.device_ids);
 	int i;
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index bfdd387..77574f7 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1177,6 +1177,11 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	struct sk_buff *skb;
 	int err, depth;
 
+	if (unlikely(xdp->data_end - xdp->data < ETH_HLEN)) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	if (q->flags & IFF_VNET_HDR)
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9b24861..1d06c56 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2455,6 +2455,9 @@ static int tun_xdp_one(struct tun_struct *tun,
 	bool skb_xdp = false;
 	struct page *page;
 
+	if (unlikely(datasize < ETH_HLEN))
+		return -EINVAL;
+
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog) {
 		if (gso->gso_type) {
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 9af316c..040f0bb 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1886,7 +1886,7 @@ static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode)
 	return res;
 }
 
-static int vrf_shared_table_handler(struct ctl_table *table, int write,
+static int vrf_shared_table_handler(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = (struct net *)table->extra1;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f9e7847..77e55de 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -284,7 +284,7 @@ static void ntb_memcpy_rx(struct ntb_queue_entry *entry, void *offset);
 
 
 static int ntb_transport_bus_match(struct device *dev,
-				   struct device_driver *drv)
+				   const struct device_driver *drv)
 {
 	return !strncmp(dev_name(dev), drv->name, strlen(drv->name));
 }
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 508aed0..2237715 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -25,9 +25,12 @@
 
 int nvdimm_major;
 static int nvdimm_bus_major;
-static struct class *nd_class;
 static DEFINE_IDA(nd_ida);
 
+static const struct class nd_class = {
+	.name = "nd",
+};
+
 static int to_nd_device_type(const struct device *dev)
 {
 	if (is_nvdimm(dev))
@@ -269,7 +272,7 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 }
 EXPORT_SYMBOL_GPL(nvdimm_clear_poison);
 
-static int nvdimm_bus_match(struct device *dev, struct device_driver *drv);
+static int nvdimm_bus_match(struct device *dev, const struct device_driver *drv);
 
 static const struct bus_type nvdimm_bus_type = {
 	.name = "nd",
@@ -465,9 +468,9 @@ static struct nd_device_driver nd_bus_driver = {
 	},
 };
 
-static int nvdimm_bus_match(struct device *dev, struct device_driver *drv)
+static int nvdimm_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct nd_device_driver *nd_drv = to_nd_device_driver(drv);
+	const struct nd_device_driver *nd_drv = to_nd_device_driver(drv);
 
 	if (is_nvdimm_bus(dev) && nd_drv == &nd_bus_driver)
 		return true;
@@ -742,7 +745,7 @@ int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
 	device_initialize(dev);
 	lockdep_set_class(&dev->mutex, &nvdimm_ndctl_key);
 	device_set_pm_not_required(dev);
-	dev->class = nd_class;
+	dev->class = &nd_class;
 	dev->parent = &nvdimm_bus->dev;
 	dev->devt = devt;
 	dev->release = ndctl_release;
@@ -765,7 +768,7 @@ int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
 
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus)
 {
-	device_destroy(nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id));
+	device_destroy(&nd_class, MKDEV(nvdimm_bus_major, nvdimm_bus->id));
 }
 
 static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = {
@@ -1320,11 +1323,9 @@ int __init nvdimm_bus_init(void)
 		goto err_dimm_chrdev;
 	nvdimm_major = rc;
 
-	nd_class = class_create("nd");
-	if (IS_ERR(nd_class)) {
-		rc = PTR_ERR(nd_class);
+	rc = class_register(&nd_class);
+	if (rc)
 		goto err_class;
-	}
 
 	rc = driver_register(&nd_bus_driver.drv);
 	if (rc)
@@ -1333,7 +1334,7 @@ int __init nvdimm_bus_init(void)
 	return 0;
 
  err_nd_bus:
-	class_destroy(nd_class);
+	class_unregister(&nd_class);
  err_class:
 	unregister_chrdev(nvdimm_major, "dimmctl");
  err_dimm_chrdev:
@@ -1347,7 +1348,7 @@ int __init nvdimm_bus_init(void)
 void nvdimm_bus_exit(void)
 {
 	driver_unregister(&nd_bus_driver.drv);
-	class_destroy(nd_class);
+	class_unregister(&nd_class);
 	unregister_chrdev(nvdimm_bus_major, "ndctl");
 	unregister_chrdev(nvdimm_major, "dimmctl");
 	bus_unregister(&nvdimm_bus_type);
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index 008b9aa..09822153 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -9,12 +9,11 @@
 #include <linux/module.h>
 #include <linux/numa.h>
 
-static int e820_pmem_remove(struct platform_device *pdev)
+static void e820_pmem_remove(struct platform_device *pdev)
 {
 	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
 
 	nvdimm_bus_unregister(nvdimm_bus);
-	return 0;
 }
 
 static int e820_register_one(struct resource *res, void *data)
@@ -60,7 +59,7 @@ static int e820_pmem_probe(struct platform_device *pdev)
 
 static struct platform_driver e820_pmem_driver = {
 	.probe = e820_pmem_probe,
-	.remove = e820_pmem_remove,
+	.remove_new = e820_pmem_remove,
 	.driver = {
 		.name = "e820_pmem",
 	},
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 5134a8d..403384f 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -84,14 +84,12 @@ static int of_pmem_region_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int of_pmem_region_remove(struct platform_device *pdev)
+static void of_pmem_region_remove(struct platform_device *pdev)
 {
 	struct of_pmem_private *priv = platform_get_drvdata(pdev);
 
 	nvdimm_bus_unregister(priv->bus);
 	kfree(priv);
-
-	return 0;
 }
 
 static const struct of_device_id of_pmem_region_match[] = {
@@ -102,7 +100,7 @@ static const struct of_device_id of_pmem_region_match[] = {
 
 static struct platform_driver of_pmem_region_driver = {
 	.probe = of_pmem_region_probe,
-	.remove = of_pmem_region_remove,
+	.remove_new = of_pmem_region_remove,
 	.driver = {
 		.name = "of_pmem",
 		.of_match_table = of_pmem_region_match,
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 19917253..053d5b4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1876,12 +1876,18 @@ static void nvme_configure_pi_elbas(struct nvme_ns_head *head,
 		struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm)
 {
 	u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]);
+	u8 guard_type;
 
 	/* no support for storage tag formats right now */
 	if (nvme_elbaf_sts(elbaf))
 		return;
 
-	head->guard_type = nvme_elbaf_guard_type(elbaf);
+	guard_type = nvme_elbaf_guard_type(elbaf);
+	if ((nvm->pic & NVME_ID_NS_NVM_QPIFS) &&
+	     guard_type == NVME_NVM_NS_QTYPE_GUARD)
+		guard_type = nvme_elbaf_qualified_guard_type(elbaf);
+
+	head->guard_type = guard_type;
 	switch (head->guard_type) {
 	case NVME_NVM_NS_64B_GUARD:
 		head->pi_size = sizeof(struct crc64_pi_tuple);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 44e342a..f5f545f 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -1403,10 +1403,10 @@ static void __nvmf_concat_opt_tokens(struct seq_file *seq_file)
 		tok = &opt_tokens[idx];
 		if (tok->token == NVMF_OPT_ERR)
 			continue;
-		seq_puts(seq_file, ",");
+		seq_putc(seq_file, ',');
 		seq_puts(seq_file, tok->pattern);
 	}
-	seq_puts(seq_file, "\n");
+	seq_putc(seq_file, '\n');
 }
 
 static int nvmf_dev_show(struct seq_file *seq_file, void *private)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 21f8e1b..6cd9395 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -863,7 +863,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	nvme_start_request(req);
 	return BLK_STS_OK;
 out_unmap_data:
-	nvme_unmap_data(dev, req);
+	if (blk_rq_nr_phys_segments(req))
+		nvme_unmap_data(dev, req);
 out_free_cmd:
 	nvme_cleanup_cmd(req);
 	return ret;
@@ -1309,7 +1310,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
 	dev_warn(dev->ctrl.device,
 		 "Does your device have a faulty power saving mode enabled?\n");
 	dev_warn(dev->ctrl.device,
-		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
+		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off\" and report a bug\n");
 }
 
 static enum blk_eh_timer_return nvme_timeout(struct request *req)
@@ -2968,6 +2969,13 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 			return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
 	}
 
+	/*
+	 * NVMe SSD drops off the PCIe bus after system idle
+	 * for 10 hours on a Lenovo N60z board.
+	 */
+	if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6"))
+		return NVME_QUIRK_NO_APST;
+
 	return 0;
 }
 
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 3c55f7e..ba05faaa 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -233,13 +233,12 @@ static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
 {
 	struct nvme_ns_head *head = dev_to_ns_head(dev);
 	struct gendisk *disk = dev_to_disk(dev);
-	struct block_device *bdev = disk->part0;
 	int ret;
 
-	if (nvme_disk_is_ns_head(bdev->bd_disk))
+	if (nvme_disk_is_ns_head(disk))
 		ret = ns_head_update_nuse(head);
 	else
-		ret = ns_update_nuse(bdev->bd_disk->private_data);
+		ret = ns_update_nuse(disk->private_data);
 	if (ret)
 		return ret;
 
diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c
index 64dc701..77a4119 100644
--- a/drivers/nvmem/layouts.c
+++ b/drivers/nvmem/layouts.c
@@ -17,11 +17,11 @@
 #include "internals.h"
 
 #define to_nvmem_layout_driver(drv) \
-	(container_of((drv), struct nvmem_layout_driver, driver))
+	(container_of_const((drv), struct nvmem_layout_driver, driver))
 #define to_nvmem_layout_device(_dev) \
 	container_of((_dev), struct nvmem_layout, dev)
 
-static int nvmem_layout_bus_match(struct device *dev, struct device_driver *drv)
+static int nvmem_layout_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	return of_driver_match_device(dev, drv);
 }
diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c
index c2e371c..3ef486c 100644
--- a/drivers/parport/procfs.c
+++ b/drivers/parport/procfs.c
@@ -33,7 +33,7 @@
 #define PARPORT_MIN_SPINTIME_VALUE 1
 #define PARPORT_MAX_SPINTIME_VALUE 1000
 
-static int do_active_device(struct ctl_table *table, int write,
+static int do_active_device(const struct ctl_table *table, int write,
 		      void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport *port = (struct parport *)table->extra1;
@@ -70,7 +70,7 @@ static int do_active_device(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_PARPORT_1284
-static int do_autoprobe(struct ctl_table *table, int write,
+static int do_autoprobe(const struct ctl_table *table, int write,
 			void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport_device_info *info = table->extra2;
@@ -113,7 +113,7 @@ static int do_autoprobe(struct ctl_table *table, int write,
 }
 #endif /* IEEE1284.3 support. */
 
-static int do_hardware_base_addr(struct ctl_table *table, int write,
+static int do_hardware_base_addr(const struct ctl_table *table, int write,
 				 void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport *port = (struct parport *)table->extra1;
@@ -140,7 +140,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int do_hardware_irq(struct ctl_table *table, int write,
+static int do_hardware_irq(const struct ctl_table *table, int write,
 			   void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport *port = (struct parport *)table->extra1;
@@ -167,7 +167,7 @@ static int do_hardware_irq(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int do_hardware_dma(struct ctl_table *table, int write,
+static int do_hardware_dma(const struct ctl_table *table, int write,
 			   void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport *port = (struct parport *)table->extra1;
@@ -194,7 +194,7 @@ static int do_hardware_dma(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int do_hardware_modes(struct ctl_table *table, int write,
+static int do_hardware_modes(const struct ctl_table *table, int write,
 			     void *result, size_t *lenp, loff_t *ppos)
 {
 	struct parport *port = (struct parport *)table->extra1;
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 2d34f78..427abdf 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -128,7 +128,7 @@ static int parport_probe(struct device *dev)
 	return drv->probe(to_pardevice(dev));
 }
 
-static struct bus_type parport_bus_type = {
+static const struct bus_type parport_bus_type = {
 	.name = "parport",
 	.probe = parport_probe,
 };
diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 323f2a6..8fa2797 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -488,10 +488,10 @@ pci_epf_match_id(const struct pci_epf_device_id *id, const struct pci_epf *epf)
 	return NULL;
 }
 
-static int pci_epf_device_match(struct device *dev, struct device_driver *drv)
+static int pci_epf_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct pci_epf *epf = to_pci_epf(dev);
-	struct pci_epf_driver *driver = to_pci_epf_driver(drv);
+	const struct pci_epf_driver *driver = to_pci_epf_driver(drv);
 
 	if (driver->id_table)
 		return !!pci_epf_match_id(driver->id_table, epf);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index af2996d..f412ef7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1503,7 +1503,7 @@ EXPORT_SYMBOL(pci_dev_driver);
  * system is in its list of supported devices. Returns the matching
  * pci_device_id structure or %NULL if there is no match.
  */
-static int pci_bus_match(struct device *dev, struct device_driver *drv)
+static int pci_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct pci_driver *pci_drv;
@@ -1512,7 +1512,7 @@ static int pci_bus_match(struct device *dev, struct device_driver *drv)
 	if (!pci_dev->match_driver)
 		return 0;
 
-	pci_drv = to_pci_driver(drv);
+	pci_drv = (struct pci_driver *)to_pci_driver(drv);
 	found_id = pci_match_device(pci_drv, pci_dev);
 	if (found_id)
 		return 1;
@@ -1688,10 +1688,10 @@ struct bus_type pci_bus_type = {
 EXPORT_SYMBOL(pci_bus_type);
 
 #ifdef CONFIG_PCIEPORTBUS
-static int pcie_port_bus_match(struct device *dev, struct device_driver *drv)
+static int pcie_port_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct pcie_device *pciedev;
-	struct pcie_port_service_driver *driver;
+	const struct pcie_port_service_driver *driver;
 
 	if (drv->bus != &pcie_port_bus_type || dev->bus != &pcie_port_bus_type)
 		return 0;
diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index d3cfd353..da6f66f 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -900,7 +900,7 @@ static inline int pcmcia_devmatch(struct pcmcia_device *dev,
 }
 
 
-static int pcmcia_bus_match(struct device *dev, struct device_driver *drv)
+static int pcmcia_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
 	struct pcmcia_driver *p_drv = to_pcmcia_drv(drv);
diff --git a/drivers/peci/core.c b/drivers/peci/core.c
index 8ff3e5d..25e4657 100644
--- a/drivers/peci/core.c
+++ b/drivers/peci/core.c
@@ -172,10 +172,10 @@ peci_bus_match_device_id(const struct peci_device_id *id, struct peci_device *de
 	return NULL;
 }
 
-static int peci_bus_device_match(struct device *dev, struct device_driver *drv)
+static int peci_bus_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct peci_device *device = to_peci_device(dev);
-	struct peci_driver *peci_drv = to_peci_driver(drv);
+	const struct peci_driver *peci_drv = to_peci_driver(drv);
 
 	if (dev->type != &peci_device_type)
 		return 0;
diff --git a/drivers/peci/internal.h b/drivers/peci/internal.h
index 7a4f6ea..99924a1 100644
--- a/drivers/peci/internal.h
+++ b/drivers/peci/internal.h
@@ -96,10 +96,7 @@ struct peci_driver {
 	const struct peci_device_id *id_table;
 };
 
-static inline struct peci_driver *to_peci_driver(struct device_driver *d)
-{
-	return container_of(d, struct peci_driver, driver);
-}
+#define to_peci_driver(__drv)	container_of_const(__drv, struct peci_driver, driver)
 
 int __peci_driver_register(struct peci_driver *driver, struct module *owner,
 			   const char *mod_name);
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index cf0430c..d246840 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1257,7 +1257,7 @@ static void armv8pmu_disable_user_access_ipi(void *unused)
 	armv8pmu_disable_user_access();
 }
 
-static int armv8pmu_proc_user_access_handler(struct ctl_table *table, int write,
+static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 4e842dc..44d3951 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -25,6 +25,8 @@
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
 #include <asm/cpufeature.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/andes.h>
 
 #define ALT_SBI_PMU_OVERFLOW(__ovl)					\
 asm volatile(ALTERNATIVE_2(						\
@@ -33,7 +35,8 @@ asm volatile(ALTERNATIVE_2(						\
 		THEAD_VENDOR_ID, ERRATA_THEAD_PMU,			\
 		CONFIG_ERRATA_THEAD_PMU,				\
 	"csrr %0, " __stringify(ANDES_CSR_SCOUNTEROF),			\
-		0, RISCV_ISA_EXT_XANDESPMU,				\
+		ANDES_VENDOR_ID,					\
+		RISCV_ISA_VENDOR_EXT_XANDESPMU + RISCV_VENDOR_EXT_ALTERNATIVES_BASE, \
 		CONFIG_ANDES_CUSTOM_PMU)				\
 	: "=r" (__ovl) :						\
 	: "memory")
@@ -42,7 +45,8 @@ asm volatile(ALTERNATIVE_2(						\
 asm volatile(ALTERNATIVE(						\
 	"csrc " __stringify(CSR_IP) ", %0\n\t",				\
 	"csrc " __stringify(ANDES_CSR_SLIP) ", %0\n\t",			\
-		0, RISCV_ISA_EXT_XANDESPMU,				\
+		ANDES_VENDOR_ID,					\
+		RISCV_ISA_VENDOR_EXT_XANDESPMU + RISCV_VENDOR_EXT_ALTERNATIVES_BASE, \
 		CONFIG_ANDES_CUSTOM_PMU)				\
 	: : "r"(__irq_mask)						\
 	: "memory")
@@ -1095,7 +1099,8 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		   riscv_cached_mimpid(0) == 0) {
 		riscv_pmu_irq_num = THEAD_C9XX_RV_IRQ_PMU;
 		riscv_pmu_use_irq = true;
-	} else if (riscv_isa_extension_available(NULL, XANDESPMU) &&
+	} else if (riscv_has_vendor_extension_unlikely(ANDES_VENDOR_ID,
+						       RISCV_ISA_VENDOR_EXT_XANDESPMU) &&
 		   IS_ENABLED(CONFIG_ANDES_CUSTOM_PMU)) {
 		riscv_pmu_irq_num = ANDES_SLI_CAUSE_BASE + ANDES_RV_IRQ_PMOVI;
 		riscv_pmu_use_irq = true;
@@ -1277,7 +1282,7 @@ static void riscv_pmu_update_counter_access(void *info)
 		csr_write(CSR_SCOUNTEREN, 0x2);
 }
 
-static int riscv_pmu_proc_user_access_handler(struct ctl_table *table,
+static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table,
 					      int write, void *buffer,
 					      size_t *lenp, loff_t *ppos)
 {
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 787354b..dfab1c6 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -72,6 +72,16 @@
 	  functional modes using gpios and sets the attribute max link
 	  rate, for CAN drivers.
 
+config PHY_AIROHA_PCIE
+	tristate "Airoha PCIe-PHY Driver"
+	depends on ARCH_AIROHA || COMPILE_TEST
+	depends on OF
+	select GENERIC_PHY
+	help
+	  Say Y here to add support for Airoha PCIe PHY driver.
+	  This driver create the basic PHY instance and provides initialize
+	  callback for PCIe GEN3 port.
+
 source "drivers/phy/allwinner/Kconfig"
 source "drivers/phy/amlogic/Kconfig"
 source "drivers/phy/broadcom/Kconfig"
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 868a220..5fcbce5 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -10,6 +10,7 @@
 obj-$(CONFIG_PHY_XGENE)			+= phy-xgene.o
 obj-$(CONFIG_PHY_PISTACHIO_USB)		+= phy-pistachio-usb.o
 obj-$(CONFIG_USB_LGM_PHY)		+= phy-lgm-usb.o
+obj-$(CONFIG_PHY_AIROHA_PCIE)		+= phy-airoha-pcie.o
 obj-y					+= allwinner/	\
 					   amlogic/	\
 					   broadcom/	\
diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb2.c b/drivers/phy/broadcom/phy-bcm-ns-usb2.c
index 269564b..5213c75 100644
--- a/drivers/phy/broadcom/phy-bcm-ns-usb2.c
+++ b/drivers/phy/broadcom/phy-bcm-ns-usb2.c
@@ -162,4 +162,5 @@ static struct platform_driver bcm_ns_usb2_driver = {
 };
 module_platform_driver(bcm_ns_usb2_driver);
 
+MODULE_DESCRIPTION("Broadcom Northstar USB 2.0 PHY Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb3.c b/drivers/phy/broadcom/phy-bcm-ns-usb3.c
index 2c8b1b7dd..9f995e1 100644
--- a/drivers/phy/broadcom/phy-bcm-ns-usb3.c
+++ b/drivers/phy/broadcom/phy-bcm-ns-usb3.c
@@ -240,5 +240,6 @@ static struct mdio_driver bcm_ns_usb3_mdio_driver = {
 
 mdio_module_driver(bcm_ns_usb3_mdio_driver);
 
+MODULE_DESCRIPTION("Broadcom Northstar USB 3.0 PHY Driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, bcm_ns_usb3_id_table);
diff --git a/drivers/phy/cadence/phy-cadence-torrent.c b/drivers/phy/cadence/phy-cadence-torrent.c
index 95924a0..56ce82a 100644
--- a/drivers/phy/cadence/phy-cadence-torrent.c
+++ b/drivers/phy/cadence/phy-cadence-torrent.c
@@ -360,6 +360,7 @@ struct cdns_torrent_phy {
 	enum cdns_torrent_ref_clk ref_clk1_rate;
 	struct cdns_torrent_inst phys[MAX_NUM_LANES];
 	int nsubnodes;
+	int already_configured;
 	const struct cdns_torrent_data *init_data;
 	struct regmap *regmap_common_cdb;
 	struct regmap *regmap_phy_pcs_common_cdb;
@@ -1156,6 +1157,9 @@ static int cdns_torrent_dp_set_power_state(struct cdns_torrent_phy *cdns_phy,
 	ret = regmap_read_poll_timeout(regmap, PHY_PMA_XCVR_POWER_STATE_ACK,
 				       read_val, (read_val & mask) == value, 0,
 				       POLL_TIMEOUT_US);
+	if (ret)
+		return ret;
+
 	cdns_torrent_dp_write(regmap, PHY_PMA_XCVR_POWER_STATE_REQ, 0x00000000);
 	ndelay(100);
 
@@ -1594,6 +1598,9 @@ static int cdns_torrent_dp_configure(struct phy *phy,
 	struct cdns_torrent_phy *cdns_phy = dev_get_drvdata(phy->dev.parent);
 	int ret;
 
+	if (cdns_phy->already_configured)
+		return 0;
+
 	ret = cdns_torrent_dp_verify_config(inst, &opts->dp);
 	if (ret) {
 		dev_err(&phy->dev, "invalid params for phy configure\n");
@@ -1629,6 +1636,12 @@ static int cdns_torrent_phy_on(struct phy *phy)
 	u32 read_val;
 	int ret;
 
+	if (cdns_phy->already_configured) {
+		/* Give 5ms to 10ms delay for the PIPE clock to be stable */
+		usleep_range(5000, 10000);
+		return 0;
+	}
+
 	if (cdns_phy->nsubnodes == 1) {
 		/* Take the PHY lane group out of reset */
 		reset_control_deassert(inst->lnk_rst);
@@ -2307,6 +2320,9 @@ static int cdns_torrent_phy_init(struct phy *phy)
 	u32 num_regs;
 	int i, j;
 
+	if (cdns_phy->already_configured)
+		return 0;
+
 	if (cdns_phy->nsubnodes > 1) {
 		if (phy_type == TYPE_DP)
 			return cdns_torrent_dp_multilink_init(cdns_phy, inst, phy);
@@ -2444,19 +2460,6 @@ static const struct phy_ops cdns_torrent_phy_ops = {
 	.owner		= THIS_MODULE,
 };
 
-static int cdns_torrent_noop_phy_on(struct phy *phy)
-{
-	/* Give 5ms to 10ms delay for the PIPE clock to be stable */
-	usleep_range(5000, 10000);
-
-	return 0;
-}
-
-static const struct phy_ops noop_ops = {
-	.power_on	= cdns_torrent_noop_phy_on,
-	.owner		= THIS_MODULE,
-};
-
 static
 int cdns_torrent_phy_configure_multilink(struct cdns_torrent_phy *cdns_phy)
 {
@@ -2678,7 +2681,7 @@ static int cdns_torrent_clk_register(struct cdns_torrent_phy *cdns_phy)
 	return 0;
 }
 
-static int cdns_torrent_reset(struct cdns_torrent_phy *cdns_phy)
+static int cdns_torrent_of_get_reset(struct cdns_torrent_phy *cdns_phy)
 {
 	struct device *dev = cdns_phy->dev;
 
@@ -2699,20 +2702,29 @@ static int cdns_torrent_reset(struct cdns_torrent_phy *cdns_phy)
 	return 0;
 }
 
+static int cdns_torrent_of_get_clk(struct cdns_torrent_phy *cdns_phy)
+{
+	/* refclk: Input reference clock for PLL0 */
+	cdns_phy->clk = devm_clk_get(cdns_phy->dev, "refclk");
+	if (IS_ERR(cdns_phy->clk))
+		return dev_err_probe(cdns_phy->dev, PTR_ERR(cdns_phy->clk),
+				     "phy ref clock not found\n");
+
+	/* refclk1: Input reference clock for PLL1 */
+	cdns_phy->clk1 = devm_clk_get_optional(cdns_phy->dev, "pll1_refclk");
+	if (IS_ERR(cdns_phy->clk1))
+		return dev_err_probe(cdns_phy->dev, PTR_ERR(cdns_phy->clk1),
+				     "phy PLL1 ref clock not found\n");
+
+	return 0;
+}
+
 static int cdns_torrent_clk(struct cdns_torrent_phy *cdns_phy)
 {
-	struct device *dev = cdns_phy->dev;
 	unsigned long ref_clk1_rate;
 	unsigned long ref_clk_rate;
 	int ret;
 
-	/* refclk: Input reference clock for PLL0 */
-	cdns_phy->clk = devm_clk_get(dev, "refclk");
-	if (IS_ERR(cdns_phy->clk)) {
-		dev_err(dev, "phy ref clock not found\n");
-		return PTR_ERR(cdns_phy->clk);
-	}
-
 	ret = clk_prepare_enable(cdns_phy->clk);
 	if (ret) {
 		dev_err(cdns_phy->dev, "Failed to prepare ref clock: %d\n", ret);
@@ -2745,14 +2757,6 @@ static int cdns_torrent_clk(struct cdns_torrent_phy *cdns_phy)
 		goto disable_clk;
 	}
 
-	/* refclk1: Input reference clock for PLL1 */
-	cdns_phy->clk1 = devm_clk_get_optional(dev, "pll1_refclk");
-	if (IS_ERR(cdns_phy->clk1)) {
-		dev_err(dev, "phy PLL1 ref clock not found\n");
-		ret = PTR_ERR(cdns_phy->clk1);
-		goto disable_clk;
-	}
-
 	if (cdns_phy->clk1) {
 		ret = clk_prepare_enable(cdns_phy->clk1);
 		if (ret) {
@@ -2807,7 +2811,6 @@ static int cdns_torrent_phy_probe(struct platform_device *pdev)
 	struct device_node *child;
 	int ret, subnodes, node = 0, i;
 	u32 total_num_lanes = 0;
-	int already_configured;
 	u8 init_dp_regmap = 0;
 	u32 phy_type;
 
@@ -2846,13 +2849,17 @@ static int cdns_torrent_phy_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	regmap_field_read(cdns_phy->phy_pma_cmn_ctrl_1, &already_configured);
+	ret = cdns_torrent_of_get_reset(cdns_phy);
+	if (ret)
+		goto clk_cleanup;
 
-	if (!already_configured) {
-		ret = cdns_torrent_reset(cdns_phy);
-		if (ret)
-			goto clk_cleanup;
+	ret = cdns_torrent_of_get_clk(cdns_phy);
+	if (ret)
+		goto clk_cleanup;
 
+	regmap_field_read(cdns_phy->phy_pma_cmn_ctrl_1, &cdns_phy->already_configured);
+
+	if (!cdns_phy->already_configured) {
 		ret = cdns_torrent_clk(cdns_phy);
 		if (ret)
 			goto clk_cleanup;
@@ -2932,10 +2939,7 @@ static int cdns_torrent_phy_probe(struct platform_device *pdev)
 		of_property_read_u32(child, "cdns,ssc-mode",
 				     &cdns_phy->phys[node].ssc_mode);
 
-		if (!already_configured)
-			gphy = devm_phy_create(dev, child, &cdns_torrent_phy_ops);
-		else
-			gphy = devm_phy_create(dev, child, &noop_ops);
+		gphy = devm_phy_create(dev, child, &cdns_torrent_phy_ops);
 		if (IS_ERR(gphy)) {
 			ret = PTR_ERR(gphy);
 			goto put_child;
@@ -3018,7 +3022,7 @@ static int cdns_torrent_phy_probe(struct platform_device *pdev)
 		goto put_lnk_rst;
 	}
 
-	if (cdns_phy->nsubnodes > 1 && !already_configured) {
+	if (cdns_phy->nsubnodes > 1 && !cdns_phy->already_configured) {
 		ret = cdns_torrent_phy_configure_multilink(cdns_phy);
 		if (ret)
 			goto put_lnk_rst;
@@ -3074,6 +3078,82 @@ static void cdns_torrent_phy_remove(struct platform_device *pdev)
 	cdns_torrent_clk_cleanup(cdns_phy);
 }
 
+/* SGMII and QSGMII link configuration */
+static struct cdns_reg_pairs sgmii_qsgmii_link_cmn_regs[] = {
+	{0x0002, PHY_PLL_CFG}
+};
+
+static struct cdns_reg_pairs sgmii_qsgmii_xcvr_diag_ln_regs[] = {
+	{0x0003, XCVR_DIAG_HSCLK_DIV},
+	{0x0113, XCVR_DIAG_PLLDRC_CTRL}
+};
+
+static struct cdns_torrent_vals sgmii_qsgmii_link_cmn_vals = {
+	.reg_pairs = sgmii_qsgmii_link_cmn_regs,
+	.num_regs = ARRAY_SIZE(sgmii_qsgmii_link_cmn_regs),
+};
+
+static struct cdns_torrent_vals sgmii_qsgmii_xcvr_diag_ln_vals = {
+	.reg_pairs = sgmii_qsgmii_xcvr_diag_ln_regs,
+	.num_regs = ARRAY_SIZE(sgmii_qsgmii_xcvr_diag_ln_regs),
+};
+
+static int cdns_torrent_phy_suspend_noirq(struct device *dev)
+{
+	struct cdns_torrent_phy *cdns_phy = dev_get_drvdata(dev);
+	int i;
+
+	reset_control_assert(cdns_phy->phy_rst);
+	reset_control_assert(cdns_phy->apb_rst);
+	for (i = 0; i < cdns_phy->nsubnodes; i++)
+		reset_control_assert(cdns_phy->phys[i].lnk_rst);
+
+	if (cdns_phy->already_configured)
+		cdns_phy->already_configured = 0;
+	else {
+		clk_disable_unprepare(cdns_phy->clk1);
+		clk_disable_unprepare(cdns_phy->clk);
+	}
+
+	return 0;
+}
+
+static int cdns_torrent_phy_resume_noirq(struct device *dev)
+{
+	struct cdns_torrent_phy *cdns_phy = dev_get_drvdata(dev);
+	int node = cdns_phy->nsubnodes;
+	int ret, i;
+
+	ret = cdns_torrent_clk(cdns_phy);
+	if (ret)
+		return ret;
+
+	/* Enable APB */
+	reset_control_deassert(cdns_phy->apb_rst);
+
+	if (cdns_phy->nsubnodes > 1) {
+		ret = cdns_torrent_phy_configure_multilink(cdns_phy);
+		if (ret)
+			goto put_lnk_rst;
+	}
+
+	return 0;
+
+put_lnk_rst:
+	for (i = 0; i < node; i++)
+		reset_control_assert(cdns_phy->phys[i].lnk_rst);
+	reset_control_assert(cdns_phy->apb_rst);
+
+	clk_disable_unprepare(cdns_phy->clk1);
+	clk_disable_unprepare(cdns_phy->clk);
+
+	return ret;
+}
+
+static DEFINE_NOIRQ_DEV_PM_OPS(cdns_torrent_phy_pm_ops,
+			       cdns_torrent_phy_suspend_noirq,
+			       cdns_torrent_phy_resume_noirq);
+
 /* USB and DP link configuration */
 static struct cdns_reg_pairs usb_dp_link_cmn_regs[] = {
 	{0x0002, PHY_PLL_CFG},
@@ -4043,7 +4123,8 @@ static struct cdns_reg_pairs sgmii_100_no_ssc_tx_ln_regs[] = {
 	{0x04A2, TX_PSC_A2},
 	{0x04A2, TX_PSC_A3},
 	{0x0000, TX_TXCC_CPOST_MULT_00},
-	{0x00B3, DRV_DIAG_TX_DRV}
+	{0x00B3, DRV_DIAG_TX_DRV},
+	{0x0002, XCVR_DIAG_PSC_OVRD}
 };
 
 static struct cdns_reg_pairs ti_sgmii_100_no_ssc_tx_ln_regs[] = {
@@ -4052,7 +4133,8 @@ static struct cdns_reg_pairs ti_sgmii_100_no_ssc_tx_ln_regs[] = {
 	{0x04A2, TX_PSC_A3},
 	{0x0000, TX_TXCC_CPOST_MULT_00},
 	{0x00B3, DRV_DIAG_TX_DRV},
-	{0x4000, XCVR_DIAG_RXCLK_CTRL},
+	{0x0002, XCVR_DIAG_PSC_OVRD},
+	{0x4000, XCVR_DIAG_RXCLK_CTRL}
 };
 
 static struct cdns_reg_pairs sgmii_100_no_ssc_rx_ln_regs[] = {
@@ -4219,7 +4301,8 @@ static struct cdns_reg_pairs qsgmii_100_no_ssc_tx_ln_regs[] = {
 	{0x04A2, TX_PSC_A3},
 	{0x0000, TX_TXCC_CPOST_MULT_00},
 	{0x0011, TX_TXCC_MGNFS_MULT_100},
-	{0x0003, DRV_DIAG_TX_DRV}
+	{0x0003, DRV_DIAG_TX_DRV},
+	{0x0002, XCVR_DIAG_PSC_OVRD}
 };
 
 static struct cdns_reg_pairs ti_qsgmii_100_no_ssc_tx_ln_regs[] = {
@@ -4229,7 +4312,8 @@ static struct cdns_reg_pairs ti_qsgmii_100_no_ssc_tx_ln_regs[] = {
 	{0x0000, TX_TXCC_CPOST_MULT_00},
 	{0x0011, TX_TXCC_MGNFS_MULT_100},
 	{0x0003, DRV_DIAG_TX_DRV},
-	{0x4000, XCVR_DIAG_RXCLK_CTRL},
+	{0x0002, XCVR_DIAG_PSC_OVRD},
+	{0x4000, XCVR_DIAG_RXCLK_CTRL}
 };
 
 static struct cdns_reg_pairs qsgmii_100_no_ssc_rx_ln_regs[] = {
@@ -4541,11 +4625,13 @@ static struct cdns_torrent_vals_entry link_cmn_vals_entries[] = {
 
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_NONE), &sl_sgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_PCIE), &pcie_sgmii_link_cmn_vals},
+	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_QSGMII), &sgmii_qsgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_USB), &usb_sgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_USXGMII), &usxgmii_sgmii_link_cmn_vals},
 
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_NONE), &sl_sgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_PCIE), &pcie_sgmii_link_cmn_vals},
+	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_SGMII), &sgmii_qsgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_USB), &usb_sgmii_link_cmn_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_USXGMII), &usxgmii_sgmii_link_cmn_vals},
 
@@ -4575,11 +4661,13 @@ static struct cdns_torrent_vals_entry xcvr_diag_vals_entries[] = {
 
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_NONE), &sl_sgmii_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_PCIE), &sgmii_pcie_xcvr_diag_ln_vals},
+	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_QSGMII), &sgmii_qsgmii_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_USB), &sgmii_usb_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_SGMII, TYPE_USXGMII), &sgmii_usxgmii_xcvr_diag_ln_vals},
 
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_NONE), &sl_sgmii_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_PCIE), &sgmii_pcie_xcvr_diag_ln_vals},
+	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_SGMII), &sgmii_qsgmii_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_USB), &sgmii_usb_xcvr_diag_ln_vals},
 	{CDNS_TORRENT_KEY_ANYCLK(TYPE_QSGMII, TYPE_USXGMII), &sgmii_usxgmii_xcvr_diag_ln_vals},
 
@@ -4635,6 +4723,8 @@ static struct cdns_torrent_vals_entry cmn_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &sgmii_100_int_ssc_cmn_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &sl_sgmii_100_no_ssc_cmn_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
@@ -4645,6 +4735,8 @@ static struct cdns_torrent_vals_entry cmn_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &qsgmii_100_int_ssc_cmn_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &sl_qsgmii_100_no_ssc_cmn_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
@@ -4713,6 +4805,8 @@ static struct cdns_torrent_vals_entry cdns_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &sgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &sgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &sgmii_100_no_ssc_tx_ln_vals},
@@ -4723,6 +4817,8 @@ static struct cdns_torrent_vals_entry cdns_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &qsgmii_100_no_ssc_tx_ln_vals},
@@ -4791,6 +4887,8 @@ static struct cdns_torrent_vals_entry cdns_rx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &sgmii_100_no_ssc_rx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
@@ -4801,6 +4899,8 @@ static struct cdns_torrent_vals_entry cdns_rx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
@@ -4905,6 +5005,8 @@ static struct cdns_torrent_vals_entry ti_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
@@ -4915,6 +5017,8 @@ static struct cdns_torrent_vals_entry ti_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
@@ -5017,6 +5121,8 @@ static struct cdns_torrent_vals_entry ti_j7200_cmn_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &sgmii_100_int_ssc_cmn_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &sl_sgmii_100_no_ssc_cmn_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &sgmii_100_no_ssc_cmn_vals},
@@ -5027,6 +5133,8 @@ static struct cdns_torrent_vals_entry ti_j7200_cmn_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &qsgmii_100_int_ssc_cmn_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &sl_qsgmii_100_no_ssc_cmn_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &qsgmii_100_no_ssc_cmn_vals},
@@ -5095,6 +5203,8 @@ static struct cdns_torrent_vals_entry ti_j7200_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &ti_sgmii_100_no_ssc_tx_ln_vals},
@@ -5105,6 +5215,8 @@ static struct cdns_torrent_vals_entry ti_j7200_tx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &ti_qsgmii_100_no_ssc_tx_ln_vals},
@@ -5173,6 +5285,8 @@ static struct cdns_torrent_vals_entry ti_j7200_rx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, EXTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_PCIE, INTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_QSGMII, NO_SSC), &sgmii_100_no_ssc_rx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, NO_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, EXTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_SGMII, TYPE_USB, INTERNAL_SSC), &sgmii_100_no_ssc_rx_ln_vals},
@@ -5183,6 +5297,8 @@ static struct cdns_torrent_vals_entry ti_j7200_rx_ln_vals_entries[] = {
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, EXTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_PCIE, INTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 
+	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_SGMII, NO_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
+
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, NO_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, EXTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
 	{CDNS_TORRENT_KEY(CLK_100_MHZ, CLK_100_MHZ, TYPE_QSGMII, TYPE_USB, INTERNAL_SSC), &qsgmii_100_no_ssc_rx_ln_vals},
@@ -5275,6 +5391,7 @@ static struct platform_driver cdns_torrent_phy_driver = {
 	.driver = {
 		.name	= "cdns-torrent-phy",
 		.of_match_table	= cdns_torrent_phy_of_match,
+		.pm	= pm_sleep_ptr(&cdns_torrent_phy_pm_ops),
 	}
 };
 module_platform_driver(cdns_torrent_phy_driver);
diff --git a/drivers/phy/freescale/Kconfig b/drivers/phy/freescale/Kconfig
index 45aaaea..dcd9acf 100644
--- a/drivers/phy/freescale/Kconfig
+++ b/drivers/phy/freescale/Kconfig
@@ -35,12 +35,19 @@
 	  Enable this to add support for the PCIE PHY as found on
 	  i.MX8M family of SOCs.
 
+config PHY_FSL_IMX8QM_HSIO
+	tristate "Freescale i.MX8QM HSIO PHY"
+	depends on OF && HAS_IOMEM
+	select GENERIC_PHY
+	help
+	  Enable this to add support for the HSIO PHY as found on
+	  i.MX8QM family of SOCs.
+
 config PHY_FSL_SAMSUNG_HDMI_PHY
 	tristate "Samsung HDMI PHY support"
 	depends on OF && HAS_IOMEM && COMMON_CLK
 	help
 	  Enable this to add support for the Samsung HDMI PHY in i.MX8MP.
-
 endif
 
 config PHY_FSL_LYNX_28G
diff --git a/drivers/phy/freescale/Makefile b/drivers/phy/freescale/Makefile
index c4386bf..658eac7 100644
--- a/drivers/phy/freescale/Makefile
+++ b/drivers/phy/freescale/Makefile
@@ -3,5 +3,6 @@
 obj-$(CONFIG_PHY_MIXEL_LVDS_PHY)	+= phy-fsl-imx8qm-lvds-phy.o
 obj-$(CONFIG_PHY_MIXEL_MIPI_DPHY)	+= phy-fsl-imx8-mipi-dphy.o
 obj-$(CONFIG_PHY_FSL_IMX8M_PCIE)	+= phy-fsl-imx8m-pcie.o
+obj-$(CONFIG_PHY_FSL_IMX8QM_HSIO)	+= phy-fsl-imx8qm-hsio.o
 obj-$(CONFIG_PHY_FSL_LYNX_28G)		+= phy-fsl-lynx-28g.o
 obj-$(CONFIG_PHY_FSL_SAMSUNG_HDMI_PHY)	+= phy-fsl-samsung-hdmi.o
diff --git a/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c b/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c
new file mode 100644
index 0000000..5dca93c
--- /dev/null
+++ b/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c
@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2024 NXP
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pci_regs.h>
+#include <linux/phy/phy.h>
+#include <linux/phy/pcie.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/phy/phy-imx8-pcie.h>
+
+#define MAX_NUM_LANE	3
+#define LANE_NUM_CLKS	5
+
+/* Parameters for the waiting for PCIe PHY PLL to lock */
+#define PHY_INIT_WAIT_USLEEP_MAX	10
+#define PHY_INIT_WAIT_TIMEOUT		(1000 * PHY_INIT_WAIT_USLEEP_MAX)
+
+/* i.MX8Q HSIO registers */
+#define HSIO_CTRL0			0x0
+#define HSIO_APB_RSTN_0			BIT(0)
+#define HSIO_APB_RSTN_1			BIT(1)
+#define HSIO_PIPE_RSTN_0_MASK		GENMASK(25, 24)
+#define HSIO_PIPE_RSTN_1_MASK		GENMASK(27, 26)
+#define HSIO_MODE_MASK			GENMASK(20, 17)
+#define HSIO_MODE_PCIE			0x0
+#define HSIO_MODE_SATA			0x4
+#define HSIO_DEVICE_TYPE_MASK		GENMASK(27, 24)
+#define HSIO_EPCS_TXDEEMP		BIT(5)
+#define HSIO_EPCS_TXDEEMP_SEL		BIT(6)
+#define HSIO_EPCS_PHYRESET_N		BIT(7)
+#define HSIO_RESET_N			BIT(12)
+
+#define HSIO_IOB_RXENA			BIT(0)
+#define HSIO_IOB_TXENA			BIT(1)
+#define HSIO_IOB_A_0_TXOE		BIT(2)
+#define HSIO_IOB_A_0_M1M0_2		BIT(4)
+#define HSIO_IOB_A_0_M1M0_MASK		GENMASK(4, 3)
+#define HSIO_PHYX1_EPCS_SEL		BIT(12)
+#define HSIO_PCIE_AB_SELECT		BIT(13)
+
+#define HSIO_PHY_STS0			0x4
+#define HSIO_LANE0_TX_PLL_LOCK		BIT(4)
+#define HSIO_LANE1_TX_PLL_LOCK		BIT(12)
+
+#define HSIO_CTRL2			0x8
+#define HSIO_LTSSM_ENABLE		BIT(4)
+#define HSIO_BUTTON_RST_N		BIT(21)
+#define HSIO_PERST_N			BIT(22)
+#define HSIO_POWER_UP_RST_N		BIT(23)
+
+#define HSIO_PCIE_STS0			0xc
+#define HSIO_PM_REQ_CORE_RST		BIT(19)
+
+#define HSIO_REG48_PMA_STATUS		0x30
+#define HSIO_REG48_PMA_RDY		BIT(7)
+
+struct imx_hsio_drvdata {
+	int lane_num;
+};
+
+struct imx_hsio_lane {
+	u32 ctrl_index;
+	u32 ctrl_off;
+	u32 idx;
+	u32 phy_off;
+	u32 phy_type;
+	const char * const *clk_names;
+	struct clk_bulk_data clks[LANE_NUM_CLKS];
+	struct imx_hsio_priv *priv;
+	struct phy *phy;
+	enum phy_mode phy_mode;
+};
+
+struct imx_hsio_priv {
+	void __iomem *base;
+	struct device *dev;
+	struct mutex lock;
+	const char *hsio_cfg;
+	const char *refclk_pad;
+	u32 open_cnt;
+	struct regmap *phy;
+	struct regmap *ctrl;
+	struct regmap *misc;
+	const struct imx_hsio_drvdata *drvdata;
+	struct imx_hsio_lane lane[MAX_NUM_LANE];
+};
+
+static const char * const lan0_pcie_clks[] = {"apb_pclk0", "pclk0", "ctl0_crr",
+					      "phy0_crr", "misc_crr"};
+static const char * const lan1_pciea_clks[] = {"apb_pclk1", "pclk1", "ctl0_crr",
+					       "phy0_crr", "misc_crr"};
+static const char * const lan1_pcieb_clks[] = {"apb_pclk1", "pclk1", "ctl1_crr",
+					       "phy0_crr", "misc_crr"};
+static const char * const lan2_pcieb_clks[] = {"apb_pclk2", "pclk2", "ctl1_crr",
+					       "phy1_crr", "misc_crr"};
+static const char * const lan2_sata_clks[] = {"pclk2", "epcs_tx", "epcs_rx",
+					      "phy1_crr", "misc_crr"};
+
+static const struct regmap_config regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
+static int imx_hsio_init(struct phy *phy)
+{
+	int ret, i;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+	struct device *dev = priv->dev;
+
+	/* Assign clocks refer to different modes */
+	switch (lane->phy_type) {
+	case PHY_TYPE_PCIE:
+		lane->phy_mode = PHY_MODE_PCIE;
+		if (lane->ctrl_index == 0) { /* PCIEA */
+			lane->ctrl_off = 0;
+			lane->phy_off = 0;
+
+			for (i = 0; i < LANE_NUM_CLKS; i++) {
+				if (lane->idx == 0)
+					lane->clks[i].id = lan0_pcie_clks[i];
+				else
+					lane->clks[i].id = lan1_pciea_clks[i];
+			}
+		} else { /* PCIEB */
+			if (lane->idx == 0) { /* i.MX8QXP */
+				lane->ctrl_off = 0;
+				lane->phy_off = 0;
+			} else {
+				/*
+				 * On i.MX8QM, only second or third lane can be
+				 * bound to PCIEB.
+				 */
+				lane->ctrl_off = SZ_64K;
+				if (lane->idx == 1)
+					lane->phy_off = 0;
+				else /* the third lane is bound to PCIEB */
+					lane->phy_off = SZ_64K;
+			}
+
+			for (i = 0; i < LANE_NUM_CLKS; i++) {
+				if (lane->idx == 1)
+					lane->clks[i].id = lan1_pcieb_clks[i];
+				else if (lane->idx == 2)
+					lane->clks[i].id = lan2_pcieb_clks[i];
+				else /* i.MX8QXP only has PCIEB, idx is 0 */
+					lane->clks[i].id = lan0_pcie_clks[i];
+			}
+		}
+		break;
+	case PHY_TYPE_SATA:
+		/* On i.MX8QM, only the third lane can be bound to SATA */
+		lane->phy_mode = PHY_MODE_SATA;
+		lane->ctrl_off = SZ_128K;
+		lane->phy_off = SZ_64K;
+
+		for (i = 0; i < LANE_NUM_CLKS; i++)
+			lane->clks[i].id = lan2_sata_clks[i];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Fetch clocks and enable them */
+	ret = devm_clk_bulk_get(dev, LANE_NUM_CLKS, lane->clks);
+	if (ret)
+		return ret;
+	ret = clk_bulk_prepare_enable(LANE_NUM_CLKS, lane->clks);
+	if (ret)
+		return ret;
+
+	/* allow the clocks to stabilize */
+	usleep_range(200, 500);
+	return 0;
+}
+
+static int imx_hsio_exit(struct phy *phy)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+
+	clk_bulk_disable_unprepare(LANE_NUM_CLKS, lane->clks);
+
+	return 0;
+}
+
+static void imx_hsio_pcie_phy_resets(struct phy *phy)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	regmap_clear_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			  HSIO_BUTTON_RST_N);
+	regmap_clear_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			  HSIO_PERST_N);
+	regmap_clear_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			  HSIO_POWER_UP_RST_N);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			HSIO_BUTTON_RST_N);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			HSIO_PERST_N);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			HSIO_POWER_UP_RST_N);
+
+	if (lane->idx == 1) {
+		regmap_set_bits(priv->phy, lane->phy_off + HSIO_CTRL0,
+				HSIO_APB_RSTN_1);
+		regmap_set_bits(priv->phy, lane->phy_off + HSIO_CTRL0,
+				HSIO_PIPE_RSTN_1_MASK);
+	} else {
+		regmap_set_bits(priv->phy, lane->phy_off + HSIO_CTRL0,
+				HSIO_APB_RSTN_0);
+		regmap_set_bits(priv->phy, lane->phy_off + HSIO_CTRL0,
+				HSIO_PIPE_RSTN_0_MASK);
+	}
+}
+
+static void imx_hsio_sata_phy_resets(struct phy *phy)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	/* clear PHY RST, then set it */
+	regmap_clear_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+			  HSIO_EPCS_PHYRESET_N);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+			HSIO_EPCS_PHYRESET_N);
+
+	/* CTRL RST: SET -> delay 1 us -> CLEAR -> SET */
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0, HSIO_RESET_N);
+	udelay(1);
+	regmap_clear_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+			  HSIO_RESET_N);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0, HSIO_RESET_N);
+}
+
+static void imx_hsio_configure_clk_pad(struct phy *phy)
+{
+	bool pll = false;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	if (strncmp(priv->refclk_pad, "output", 6) == 0) {
+		pll = true;
+		regmap_update_bits(priv->misc, HSIO_CTRL0,
+				   HSIO_IOB_A_0_TXOE | HSIO_IOB_A_0_M1M0_MASK,
+				   HSIO_IOB_A_0_TXOE | HSIO_IOB_A_0_M1M0_2);
+	} else {
+		regmap_update_bits(priv->misc, HSIO_CTRL0,
+				   HSIO_IOB_A_0_TXOE | HSIO_IOB_A_0_M1M0_MASK,
+				   0);
+	}
+
+	regmap_update_bits(priv->misc, HSIO_CTRL0, HSIO_IOB_RXENA,
+			   pll ? 0 : HSIO_IOB_RXENA);
+	regmap_update_bits(priv->misc, HSIO_CTRL0, HSIO_IOB_TXENA,
+			   pll ? HSIO_IOB_TXENA : 0);
+}
+
+static void imx_hsio_pre_set(struct phy *phy)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	if (strncmp(priv->hsio_cfg, "pciea-x2-pcieb", 14) == 0) {
+		regmap_set_bits(priv->misc, HSIO_CTRL0, HSIO_PCIE_AB_SELECT);
+	} else if (strncmp(priv->hsio_cfg, "pciea-x2-sata", 13) == 0) {
+		regmap_set_bits(priv->misc, HSIO_CTRL0, HSIO_PHYX1_EPCS_SEL);
+	} else if (strncmp(priv->hsio_cfg, "pciea-pcieb-sata", 16) == 0) {
+		regmap_set_bits(priv->misc, HSIO_CTRL0, HSIO_PCIE_AB_SELECT);
+		regmap_set_bits(priv->misc, HSIO_CTRL0, HSIO_PHYX1_EPCS_SEL);
+	}
+
+	imx_hsio_configure_clk_pad(phy);
+}
+
+static int imx_hsio_pcie_power_on(struct phy *phy)
+{
+	int ret;
+	u32 val, addr, cond;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	imx_hsio_pcie_phy_resets(phy);
+
+	/* Toggle apb_pclk to make sure PM_REQ_CORE_RST is cleared. */
+	clk_disable_unprepare(lane->clks[0].clk);
+	mdelay(1);
+	ret = clk_prepare_enable(lane->clks[0].clk);
+	if (ret) {
+		dev_err(priv->dev, "unable to enable phy apb_pclk\n");
+		return ret;
+	}
+
+	addr = lane->ctrl_off + HSIO_PCIE_STS0;
+	cond = HSIO_PM_REQ_CORE_RST;
+	ret = regmap_read_poll_timeout(priv->ctrl, addr, val,
+				       (val & cond) == 0,
+				       PHY_INIT_WAIT_USLEEP_MAX,
+				       PHY_INIT_WAIT_TIMEOUT);
+	if (ret)
+		dev_err(priv->dev, "HSIO_PM_REQ_CORE_RST is set\n");
+	return ret;
+}
+
+static int imx_hsio_sata_power_on(struct phy *phy)
+{
+	int ret;
+	u32 val, cond;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	regmap_set_bits(priv->phy, lane->phy_off + HSIO_CTRL0, HSIO_APB_RSTN_0);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+			HSIO_EPCS_TXDEEMP);
+	regmap_set_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+			HSIO_EPCS_TXDEEMP_SEL);
+
+	imx_hsio_sata_phy_resets(phy);
+
+	cond = HSIO_REG48_PMA_RDY;
+	ret = read_poll_timeout(readb, val, ((val & cond) == cond),
+				PHY_INIT_WAIT_USLEEP_MAX,
+				PHY_INIT_WAIT_TIMEOUT, false,
+				priv->base + HSIO_REG48_PMA_STATUS);
+	if (ret)
+		dev_err(priv->dev, "PHY calibration is timeout\n");
+	else
+		dev_dbg(priv->dev, "PHY calibration is done\n");
+
+	return ret;
+}
+
+static int imx_hsio_power_on(struct phy *phy)
+{
+	int ret;
+	u32 val, cond;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	scoped_guard(mutex, &priv->lock) {
+		if (!priv->open_cnt)
+			imx_hsio_pre_set(phy);
+		priv->open_cnt++;
+	}
+
+	if (lane->phy_mode == PHY_MODE_PCIE)
+		ret = imx_hsio_pcie_power_on(phy);
+	else /* SATA */
+		ret = imx_hsio_sata_power_on(phy);
+	if (ret)
+		return ret;
+
+	/* Polling to check the PHY is ready or not. */
+	if (lane->idx == 1)
+		cond = HSIO_LANE1_TX_PLL_LOCK;
+	else
+		/*
+		 * Except the phy_off, the bit-offset of lane2 is same to lane0.
+		 * Merge the lane0 and lane2 bit-operations together.
+		 */
+		cond = HSIO_LANE0_TX_PLL_LOCK;
+
+	ret = regmap_read_poll_timeout(priv->phy, lane->phy_off + HSIO_PHY_STS0,
+				       val, ((val & cond) == cond),
+				       PHY_INIT_WAIT_USLEEP_MAX,
+				       PHY_INIT_WAIT_TIMEOUT);
+	if (ret) {
+		dev_err(priv->dev, "IMX8Q PHY%d PLL lock timeout\n", lane->idx);
+		return ret;
+	}
+	dev_dbg(priv->dev, "IMX8Q PHY%d PLL is locked\n", lane->idx);
+
+	return ret;
+}
+
+static int imx_hsio_power_off(struct phy *phy)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	scoped_guard(mutex, &priv->lock) {
+		priv->open_cnt--;
+		if (priv->open_cnt == 0) {
+			regmap_clear_bits(priv->misc, HSIO_CTRL0,
+					  HSIO_PCIE_AB_SELECT);
+			regmap_clear_bits(priv->misc, HSIO_CTRL0,
+					  HSIO_PHYX1_EPCS_SEL);
+
+			if (lane->phy_mode == PHY_MODE_PCIE) {
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL2,
+						  HSIO_BUTTON_RST_N);
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL2,
+						  HSIO_PERST_N);
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL2,
+						  HSIO_POWER_UP_RST_N);
+			} else {
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL0,
+						  HSIO_EPCS_TXDEEMP);
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL0,
+						  HSIO_EPCS_TXDEEMP_SEL);
+				regmap_clear_bits(priv->ctrl,
+						  lane->ctrl_off + HSIO_CTRL0,
+						  HSIO_RESET_N);
+			}
+
+			if (lane->idx == 1) {
+				regmap_clear_bits(priv->phy,
+						  lane->phy_off + HSIO_CTRL0,
+						  HSIO_APB_RSTN_1);
+				regmap_clear_bits(priv->phy,
+						  lane->phy_off + HSIO_CTRL0,
+						  HSIO_PIPE_RSTN_1_MASK);
+			} else {
+				/*
+				 * Except the phy_off, the bit-offset of lane2 is same
+				 * to lane0. Merge the lane0 and lane2 bit-operations
+				 * together.
+				 */
+				regmap_clear_bits(priv->phy,
+						  lane->phy_off + HSIO_CTRL0,
+						  HSIO_APB_RSTN_0);
+				regmap_clear_bits(priv->phy,
+						  lane->phy_off + HSIO_CTRL0,
+						  HSIO_PIPE_RSTN_0_MASK);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int imx_hsio_set_mode(struct phy *phy, enum phy_mode mode,
+			     int submode)
+{
+	u32 val;
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	if (lane->phy_mode != mode)
+		return -EINVAL;
+
+	val = (mode == PHY_MODE_PCIE) ? HSIO_MODE_PCIE : HSIO_MODE_SATA;
+	val = FIELD_PREP(HSIO_MODE_MASK, val);
+	regmap_update_bits(priv->phy, lane->phy_off + HSIO_CTRL0,
+			   HSIO_MODE_MASK, val);
+
+	switch (submode) {
+	case PHY_MODE_PCIE_RC:
+		val = FIELD_PREP(HSIO_DEVICE_TYPE_MASK, PCI_EXP_TYPE_ROOT_PORT);
+		break;
+	case PHY_MODE_PCIE_EP:
+		val = FIELD_PREP(HSIO_DEVICE_TYPE_MASK, PCI_EXP_TYPE_ENDPOINT);
+		break;
+	default: /* Support only PCIe EP and RC now. */
+		return 0;
+	}
+	if (submode)
+		regmap_update_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL0,
+				   HSIO_DEVICE_TYPE_MASK, val);
+
+	return 0;
+}
+
+static int imx_hsio_set_speed(struct phy *phy, int speed)
+{
+	struct imx_hsio_lane *lane = phy_get_drvdata(phy);
+	struct imx_hsio_priv *priv = lane->priv;
+
+	regmap_update_bits(priv->ctrl, lane->ctrl_off + HSIO_CTRL2,
+			   HSIO_LTSSM_ENABLE,
+			   speed ? HSIO_LTSSM_ENABLE : 0);
+	return 0;
+}
+
+static const struct phy_ops imx_hsio_ops = {
+	.init = imx_hsio_init,
+	.exit = imx_hsio_exit,
+	.power_on = imx_hsio_power_on,
+	.power_off = imx_hsio_power_off,
+	.set_mode = imx_hsio_set_mode,
+	.set_speed = imx_hsio_set_speed,
+	.owner = THIS_MODULE,
+};
+
+static const struct imx_hsio_drvdata imx8qxp_hsio_drvdata = {
+	.lane_num = 0x1,
+};
+
+static const struct imx_hsio_drvdata imx8qm_hsio_drvdata = {
+	.lane_num = 0x3,
+};
+
+static const struct of_device_id imx_hsio_of_match[] = {
+	{.compatible = "fsl,imx8qm-hsio", .data = &imx8qm_hsio_drvdata},
+	{.compatible = "fsl,imx8qxp-hsio", .data = &imx8qxp_hsio_drvdata},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, imx_hsio_of_match);
+
+static struct phy *imx_hsio_xlate(struct device *dev,
+				  const struct of_phandle_args *args)
+{
+	struct imx_hsio_priv *priv = dev_get_drvdata(dev);
+	int idx = args->args[0];
+	int phy_type = args->args[1];
+	int ctrl_index = args->args[2];
+
+	if (idx < 0 || idx >= priv->drvdata->lane_num)
+		return ERR_PTR(-EINVAL);
+	priv->lane[idx].idx = idx;
+	priv->lane[idx].phy_type = phy_type;
+	priv->lane[idx].ctrl_index = ctrl_index;
+
+	return priv->lane[idx].phy;
+}
+
+static int imx_hsio_probe(struct platform_device *pdev)
+{
+	int i;
+	void __iomem *off;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct imx_hsio_priv *priv;
+	struct phy_provider *provider;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->dev = &pdev->dev;
+	priv->drvdata = of_device_get_match_data(dev);
+
+	/* Get HSIO configuration mode */
+	if (of_property_read_string(np, "fsl,hsio-cfg", &priv->hsio_cfg))
+		priv->hsio_cfg = "pciea-pcieb-sata";
+	/* Get PHY refclk pad mode */
+	if (of_property_read_string(np, "fsl,refclk-pad-mode",
+				    &priv->refclk_pad))
+		priv->refclk_pad = NULL;
+
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	off = devm_platform_ioremap_resource_byname(pdev, "phy");
+	priv->phy = devm_regmap_init_mmio(dev, off, &regmap_config);
+	if (IS_ERR(priv->phy))
+		return dev_err_probe(dev, PTR_ERR(priv->phy),
+				     "unable to find phy csr registers\n");
+
+	off = devm_platform_ioremap_resource_byname(pdev, "ctrl");
+	priv->ctrl = devm_regmap_init_mmio(dev, off, &regmap_config);
+	if (IS_ERR(priv->ctrl))
+		return dev_err_probe(dev, PTR_ERR(priv->ctrl),
+				     "unable to find ctrl csr registers\n");
+
+	off = devm_platform_ioremap_resource_byname(pdev, "misc");
+	priv->misc = devm_regmap_init_mmio(dev, off, &regmap_config);
+	if (IS_ERR(priv->misc))
+		return dev_err_probe(dev, PTR_ERR(priv->misc),
+				     "unable to find misc csr registers\n");
+
+	for (i = 0; i < priv->drvdata->lane_num; i++) {
+		struct imx_hsio_lane *lane = &priv->lane[i];
+		struct phy *phy;
+
+		phy = devm_phy_create(&pdev->dev, NULL, &imx_hsio_ops);
+		if (IS_ERR(phy))
+			return PTR_ERR(phy);
+
+		lane->priv = priv;
+		lane->phy = phy;
+		lane->idx = i;
+		phy_set_drvdata(phy, lane);
+	}
+
+	dev_set_drvdata(dev, priv);
+	dev_set_drvdata(&pdev->dev, priv);
+
+	provider = devm_of_phy_provider_register(&pdev->dev, imx_hsio_xlate);
+
+	return PTR_ERR_OR_ZERO(provider);
+}
+
+static struct platform_driver imx_hsio_driver = {
+	.probe	= imx_hsio_probe,
+	.driver = {
+		.name	= "imx8qm-hsio-phy",
+		.of_match_table	= imx_hsio_of_match,
+	}
+};
+module_platform_driver(imx_hsio_driver);
+
+MODULE_DESCRIPTION("FSL IMX8QM HSIO SERDES PHY driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/phy-airoha-pcie-regs.h b/drivers/phy/phy-airoha-pcie-regs.h
new file mode 100644
index 0000000..bb1f679
--- /dev/null
+++ b/drivers/phy/phy-airoha-pcie-regs.h
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef _PHY_AIROHA_PCIE_H
+#define _PHY_AIROHA_PCIE_H
+
+/* CSR_2L */
+#define REG_CSR_2L_CMN				0x0000
+#define CSR_2L_PXP_CMN_LANE_EN			BIT(0)
+#define CSR_2L_PXP_CMN_TRIM_MASK		GENMASK(28, 24)
+
+#define REG_CSR_2L_JCPLL_IB_EXT			0x0004
+#define REG_CSR_2L_JCPLL_LPF_SHCK_EN		BIT(8)
+#define CSR_2L_PXP_JCPLL_CHP_IBIAS		GENMASK(21, 16)
+#define CSR_2L_PXP_JCPLL_CHP_IOFST		GENMASK(29, 24)
+
+#define REG_CSR_2L_JCPLL_LPF_BR			0x0008
+#define CSR_2L_PXP_JCPLL_LPF_BR			GENMASK(4, 0)
+#define CSR_2L_PXP_JCPLL_LPF_BC			GENMASK(12, 8)
+#define CSR_2L_PXP_JCPLL_LPF_BP			GENMASK(20, 16)
+#define CSR_2L_PXP_JCPLL_LPF_BWR		GENMASK(28, 24)
+
+#define REG_CSR_2L_JCPLL_LPF_BWC		0x000c
+#define CSR_2L_PXP_JCPLL_LPF_BWC		GENMASK(4, 0)
+#define CSR_2L_PXP_JCPLL_KBAND_CODE		GENMASK(23, 16)
+#define CSR_2L_PXP_JCPLL_KBAND_DIV		GENMASK(26, 24)
+
+#define REG_CSR_2L_JCPLL_KBAND_KFC		0x0010
+#define CSR_2L_PXP_JCPLL_KBAND_KFC		GENMASK(1, 0)
+#define CSR_2L_PXP_JCPLL_KBAND_KF		GENMASK(9, 8)
+#define CSR_2L_PXP_JCPLL_KBAND_KS		GENMASK(17, 16)
+#define CSR_2L_PXP_JCPLL_POSTDIV_EN		BIT(24)
+
+#define REG_CSR_2L_JCPLL_MMD_PREDIV_MODE	0x0014
+#define CSR_2L_PXP_JCPLL_MMD_PREDIV_MODE	GENMASK(1, 0)
+#define CSR_2L_PXP_JCPLL_POSTDIV_D2		BIT(16)
+#define CSR_2L_PXP_JCPLL_POSTDIV_D5		BIT(24)
+
+#define CSR_2L_PXP_JCPLL_MONCK			0x0018
+#define CSR_2L_PXP_JCPLL_REFIN_DIV		GENMASK(25, 24)
+
+#define REG_CSR_2L_JCPLL_RST_DLY		0x001c
+#define CSR_2L_PXP_JCPLL_RST_DLY		GENMASK(2, 0)
+#define CSR_2L_PXP_JCPLL_RST			BIT(8)
+#define CSR_2L_PXP_JCPLL_SDM_DI_EN		BIT(16)
+#define CSR_2L_PXP_JCPLL_SDM_DI_LS		GENMASK(25, 24)
+
+#define REG_CSR_2L_JCPLL_SDM_IFM		0x0020
+#define CSR_2L_PXP_JCPLL_SDM_IFM		BIT(0)
+
+#define REG_CSR_2L_JCPLL_SDM_HREN		0x0024
+#define CSR_2L_PXP_JCPLL_SDM_HREN		BIT(0)
+#define CSR_2L_PXP_JCPLL_TCL_AMP_EN		BIT(8)
+#define CSR_2L_PXP_JCPLL_TCL_AMP_GAIN		GENMASK(18, 16)
+#define CSR_2L_PXP_JCPLL_TCL_AMP_VREF		GENMASK(28, 24)
+
+#define REG_CSR_2L_JCPLL_TCL_CMP		0x0028
+#define CSR_2L_PXP_JCPLL_TCL_LPF_EN		BIT(16)
+#define CSR_2L_PXP_JCPLL_TCL_LPF_BW		GENMASK(26, 24)
+
+#define REG_CSR_2L_JCPLL_VCODIV			0x002c
+#define CSR_2L_PXP_JCPLL_VCO_CFIX		GENMASK(9, 8)
+#define CSR_2L_PXP_JCPLL_VCO_HALFLSB_EN		BIT(16)
+#define CSR_2L_PXP_JCPLL_VCO_SCAPWR		GENMASK(26, 24)
+
+#define REG_CSR_2L_JCPLL_VCO_TCLVAR		0x0030
+#define CSR_2L_PXP_JCPLL_VCO_TCLVAR		GENMASK(2, 0)
+
+#define REG_CSR_2L_JCPLL_SSC				0x0038
+#define CSR_2L_PXP_JCPLL_SSC_EN			BIT(0)
+#define CSR_2L_PXP_JCPLL_SSC_PHASE_INI		BIT(8)
+#define CSR_2L_PXP_JCPLL_SSC_TRI_EN		BIT(16)
+
+#define REG_CSR_2L_JCPLL_SSC_DELTA1		0x003c
+#define CSR_2L_PXP_JCPLL_SSC_DELTA1		GENMASK(15, 0)
+#define CSR_2L_PXP_JCPLL_SSC_DELTA		GENMASK(31, 16)
+
+#define REG_CSR_2L_JCPLL_SSC_PERIOD		0x0040
+#define CSR_2L_PXP_JCPLL_SSC_PERIOD		GENMASK(15, 0)
+
+#define REG_CSR_2L_JCPLL_TCL_VTP_EN		0x004c
+#define CSR_2L_PXP_JCPLL_SPARE_LOW		GENMASK(31, 24)
+
+#define REG_CSR_2L_JCPLL_TCL_KBAND_VREF		0x0050
+#define CSR_2L_PXP_JCPLL_TCL_KBAND_VREF		GENMASK(4, 0)
+#define CSR_2L_PXP_JCPLL_VCO_KBAND_MEAS_EN	BIT(24)
+
+#define REG_CSR_2L_750M_SYS_CK			0x0054
+#define CSR_2L_PXP_TXPLL_LPF_SHCK_EN		BIT(16)
+#define CSR_2L_PXP_TXPLL_CHP_IBIAS		GENMASK(29, 24)
+
+#define REG_CSR_2L_TXPLL_CHP_IOFST		0x0058
+#define CSR_2L_PXP_TXPLL_CHP_IOFST		GENMASK(5, 0)
+#define CSR_2L_PXP_TXPLL_LPF_BR			GENMASK(12, 8)
+#define CSR_2L_PXP_TXPLL_LPF_BC			GENMASK(20, 16)
+#define CSR_2L_PXP_TXPLL_LPF_BP			GENMASK(28, 24)
+
+#define REG_CSR_2L_TXPLL_LPF_BWR		0x005c
+#define CSR_2L_PXP_TXPLL_LPF_BWR		GENMASK(4, 0)
+#define CSR_2L_PXP_TXPLL_LPF_BWC		GENMASK(12, 8)
+#define CSR_2L_PXP_TXPLL_KBAND_CODE		GENMASK(31, 24)
+
+#define REG_CSR_2L_TXPLL_KBAND_DIV		0x0060
+#define CSR_2L_PXP_TXPLL_KBAND_DIV		GENMASK(2, 0)
+#define CSR_2L_PXP_TXPLL_KBAND_KFC		GENMASK(9, 8)
+#define CSR_2L_PXP_TXPLL_KBAND_KF		GENMASK(17, 16)
+#define CSR_2L_PXP_txpll_KBAND_KS		GENMASK(25, 24)
+
+#define REG_CSR_2L_TXPLL_POSTDIV		0x0064
+#define CSR_2L_PXP_TXPLL_POSTDIV_EN		BIT(0)
+#define CSR_2L_PXP_TXPLL_MMD_PREDIV_MODE	GENMASK(9, 8)
+#define CSR_2L_PXP_TXPLL_PHY_CK1_EN		BIT(24)
+
+#define REG_CSR_2L_TXPLL_PHY_CK2		0x0068
+#define CSR_2L_PXP_TXPLL_REFIN_INTERNAL		BIT(24)
+
+#define REG_CSR_2L_TXPLL_REFIN_DIV		0x006c
+#define CSR_2L_PXP_TXPLL_REFIN_DIV		GENMASK(1, 0)
+#define CSR_2L_PXP_TXPLL_RST_DLY		GENMASK(10, 8)
+#define CSR_2L_PXP_TXPLL_PLL_RSTB		BIT(16)
+
+#define REG_CSR_2L_TXPLL_SDM_DI_LS		0x0070
+#define CSR_2L_PXP_TXPLL_SDM_DI_LS		GENMASK(1, 0)
+#define CSR_2L_PXP_TXPLL_SDM_IFM		BIT(8)
+#define CSR_2L_PXP_TXPLL_SDM_ORD		GENMASK(25, 24)
+
+#define REG_CSR_2L_TXPLL_SDM_OUT		0x0074
+#define CSR_2L_PXP_TXPLL_TCL_AMP_EN		BIT(16)
+#define CSR_2L_PXP_TXPLL_TCL_AMP_GAIN		GENMASK(26, 24)
+
+#define REG_CSR_2L_TXPLL_TCL_AMP_VREF		0x0078
+#define CSR_2L_PXP_TXPLL_TCL_AMP_VREF		GENMASK(4, 0)
+#define CSR_2L_PXP_TXPLL_TCL_LPF_EN		BIT(24)
+
+#define REG_CSR_2L_TXPLL_TCL_LPF_BW		0x007c
+#define CSR_2L_PXP_TXPLL_TCL_LPF_BW		GENMASK(2, 0)
+#define CSR_2L_PXP_TXPLL_VCO_CFIX		GENMASK(17, 16)
+#define CSR_2L_PXP_TXPLL_VCO_HALFLSB_EN		BIT(24)
+
+#define REG_CSR_2L_TXPLL_VCO_SCAPWR		0x0080
+#define CSR_2L_PXP_TXPLL_VCO_SCAPWR		GENMASK(2, 0)
+
+#define REG_CSR_2L_TXPLL_SSC			0x0084
+#define CSR_2L_PXP_TXPLL_SSC_EN			BIT(0)
+#define CSR_2L_PXP_TXPLL_SSC_PHASE_INI		BIT(8)
+
+#define REG_CSR_2L_TXPLL_SSC_DELTA1		0x0088
+#define CSR_2L_PXP_TXPLL_SSC_DELTA1		GENMASK(15, 0)
+#define CSR_2L_PXP_TXPLL_SSC_DELTA		GENMASK(31, 16)
+
+#define REG_CSR_2L_TXPLL_SSC_PERIOD		0x008c
+#define CSR_2L_PXP_txpll_SSC_PERIOD		GENMASK(15, 0)
+
+#define REG_CSR_2L_TXPLL_VTP			0x0090
+#define CSR_2L_PXP_TXPLL_VTP_EN			BIT(0)
+
+#define REG_CSR_2L_TXPLL_TCL_VTP		0x0098
+#define CSR_2L_PXP_TXPLL_SPARE_L		GENMASK(31, 24)
+
+#define REG_CSR_2L_TXPLL_TCL_KBAND_VREF		0x009c
+#define CSR_2L_PXP_TXPLL_TCL_KBAND_VREF		GENMASK(4, 0)
+#define CSR_2L_PXP_TXPLL_VCO_KBAND_MEAS_EN	BIT(24)
+
+#define REG_CSR_2L_TXPLL_POSTDIV_D256		0x00a0
+#define CSR_2L_PXP_CLKTX0_AMP			GENMASK(10, 8)
+#define CSR_2L_PXP_CLKTX0_OFFSET		GENMASK(17, 16)
+#define CSR_2L_PXP_CLKTX0_SR			GENMASK(25, 24)
+
+#define REG_CSR_2L_CLKTX0_FORCE_OUT1		0x00a4
+#define CSR_2L_PXP_CLKTX0_HZ			BIT(8)
+#define CSR_2L_PXP_CLKTX0_IMP_SEL		GENMASK(20, 16)
+#define CSR_2L_PXP_CLKTX1_AMP			GENMASK(26, 24)
+
+#define REG_CSR_2L_CLKTX1_OFFSET		0x00a8
+#define CSR_2L_PXP_CLKTX1_OFFSET		GENMASK(1, 0)
+#define CSR_2L_PXP_CLKTX1_SR			GENMASK(9, 8)
+#define CSR_2L_PXP_CLKTX1_HZ			BIT(24)
+
+#define REG_CSR_2L_CLKTX1_IMP_SEL		0x00ac
+#define CSR_2L_PXP_CLKTX1_IMP_SEL		GENMASK(4, 0)
+
+#define REG_CSR_2L_PLL_CMN_RESERVE0		0x00b0
+#define CSR_2L_PXP_PLL_RESERVE_MASK		GENMASK(15, 0)
+
+#define REG_CSR_2L_TX0_CKLDO			0x00cc
+#define CSR_2L_PXP_TX0_CKLDO_EN			BIT(0)
+#define CSR_2L_PXP_TX0_DMEDGEGEN_EN		BIT(24)
+
+#define REG_CSR_2L_TX1_CKLDO			0x00e8
+#define CSR_2L_PXP_TX1_CKLDO_EN			BIT(0)
+#define CSR_2L_PXP_TX1_DMEDGEGEN_EN		BIT(24)
+
+#define REG_CSR_2L_TX1_MULTLANE			0x00ec
+#define CSR_2L_PXP_TX1_MULTLANE_EN		BIT(0)
+
+#define REG_CSR_2L_RX0_REV0			0x00fc
+#define CSR_2L_PXP_VOS_PNINV			GENMASK(3, 2)
+#define CSR_2L_PXP_FE_GAIN_NORMAL_MODE		GENMASK(6, 4)
+#define CSR_2L_PXP_FE_GAIN_TRAIN_MODE		GENMASK(10, 8)
+
+#define REG_CSR_2L_RX0_PHYCK_DIV		0x0100
+#define CSR_2L_PXP_RX0_PHYCK_SEL		GENMASK(9, 8)
+#define CSR_2L_PXP_RX0_PHYCK_RSTB		BIT(16)
+#define CSR_2L_PXP_RX0_TDC_CK_SEL		BIT(24)
+
+#define REG_CSR_2L_CDR0_PD_PICAL_CKD8_INV	0x0104
+#define CSR_2L_PXP_CDR0_PD_EDGE_DISABLE		BIT(8)
+
+#define REG_CSR_2L_CDR0_LPF_RATIO		0x0110
+#define CSR_2L_PXP_CDR0_LPF_TOP_LIM		GENMASK(26, 8)
+
+#define REG_CSR_2L_CDR0_PR_INJ_MODE		0x011c
+#define CSR_2L_PXP_CDR0_INJ_FORCE_OFF		BIT(24)
+
+#define REG_CSR_2L_CDR0_PR_BETA_DAC		0x0120
+#define CSR_2L_PXP_CDR0_PR_BETA_SEL		GENMASK(19, 16)
+#define CSR_2L_PXP_CDR0_PR_KBAND_DIV		GENMASK(26, 24)
+
+#define REG_CSR_2L_CDR0_PR_VREG_IBAND		0x0124
+#define CSR_2L_PXP_CDR0_PR_VREG_IBAND		GENMASK(2, 0)
+#define CSR_2L_PXP_CDR0_PR_VREG_CKBUF		GENMASK(10, 8)
+
+#define REG_CSR_2L_CDR0_PR_CKREF_DIV		0x0128
+#define CSR_2L_PXP_CDR0_PR_CKREF_DIV		GENMASK(1, 0)
+
+#define REG_CSR_2L_CDR0_PR_MONCK		0x012c
+#define CSR_2L_PXP_CDR0_PR_MONCK_ENABLE		BIT(0)
+#define CSR_2L_PXP_CDR0_PR_RESERVE0		GENMASK(19, 16)
+
+#define REG_CSR_2L_CDR0_PR_COR_HBW		0x0130
+#define CSR_2L_PXP_CDR0_PR_LDO_FORCE_ON		BIT(8)
+#define CSR_2L_PXP_CDR0_PR_CKREF_DIV1		GENMASK(17, 16)
+
+#define REG_CSR_2L_CDR0_PR_MONPI		0x0134
+#define CSR_2L_PXP_CDR0_PR_XFICK_EN		BIT(8)
+
+#define REG_CSR_2L_RX0_SIGDET_DCTEST		0x0140
+#define CSR_2L_PXP_RX0_SIGDET_LPF_CTRL		GENMASK(9, 8)
+#define CSR_2L_PXP_RX0_SIGDET_PEAK		GENMASK(25, 24)
+
+#define REG_CSR_2L_RX0_SIGDET_VTH_SEL		0x0144
+#define CSR_2L_PXP_RX0_SIGDET_VTH_SEL		GENMASK(4, 0)
+#define CSR_2L_PXP_RX0_FE_VB_EQ1_EN		BIT(24)
+
+#define REG_CSR_2L_PXP_RX0_FE_VB_EQ2		0x0148
+#define CSR_2L_PXP_RX0_FE_VB_EQ2_EN		BIT(0)
+#define CSR_2L_PXP_RX0_FE_VB_EQ3_EN		BIT(8)
+#define CSR_2L_PXP_RX0_FE_VCM_GEN_PWDB		BIT(16)
+
+#define REG_CSR_2L_PXP_RX0_OSCAL_CTLE1IOS	0x0158
+#define CSR_2L_PXP_RX0_PR_OSCAL_VGA1IOS		GENMASK(29, 24)
+
+#define REG_CSR_2L_PXP_RX0_OSCA_VGA1VOS		0x015c
+#define CSR_2L_PXP_RX0_PR_OSCAL_VGA1VOS		GENMASK(5, 0)
+#define CSR_2L_PXP_RX0_PR_OSCAL_VGA2IOS		GENMASK(13, 8)
+
+#define REG_CSR_2L_RX1_REV0			0x01b4
+
+#define REG_CSR_2L_RX1_PHYCK_DIV		0x01b8
+#define CSR_2L_PXP_RX1_PHYCK_SEL		GENMASK(9, 8)
+#define CSR_2L_PXP_RX1_PHYCK_RSTB		BIT(16)
+#define CSR_2L_PXP_RX1_TDC_CK_SEL		BIT(24)
+
+#define REG_CSR_2L_CDR1_PD_PICAL_CKD8_INV	0x01bc
+#define CSR_2L_PXP_CDR1_PD_EDGE_DISABLE		BIT(8)
+
+#define REG_CSR_2L_CDR1_PR_BETA_DAC		0x01d8
+#define CSR_2L_PXP_CDR1_PR_BETA_SEL		GENMASK(19, 16)
+#define CSR_2L_PXP_CDR1_PR_KBAND_DIV		GENMASK(26, 24)
+
+#define REG_CSR_2L_CDR1_PR_MONCK		0x01e4
+#define CSR_2L_PXP_CDR1_PR_MONCK_ENABLE		BIT(0)
+#define CSR_2L_PXP_CDR1_PR_RESERVE0		GENMASK(19, 16)
+
+#define REG_CSR_2L_CDR1_LPF_RATIO		0x01c8
+#define CSR_2L_PXP_CDR1_LPF_TOP_LIM		GENMASK(26, 8)
+
+#define REG_CSR_2L_CDR1_PR_INJ_MODE		0x01d4
+#define CSR_2L_PXP_CDR1_INJ_FORCE_OFF		BIT(24)
+
+#define REG_CSR_2L_CDR1_PR_VREG_IBAND_VAL	0x01dc
+#define CSR_2L_PXP_CDR1_PR_VREG_IBAND		GENMASK(2, 0)
+#define CSR_2L_PXP_CDR1_PR_VREG_CKBUF		GENMASK(10, 8)
+
+#define REG_CSR_2L_CDR1_PR_CKREF_DIV		0x01e0
+#define CSR_2L_PXP_CDR1_PR_CKREF_DIV		GENMASK(1, 0)
+
+#define REG_CSR_2L_CDR1_PR_COR_HBW		0x01e8
+#define CSR_2L_PXP_CDR1_PR_LDO_FORCE_ON		BIT(8)
+#define CSR_2L_PXP_CDR1_PR_CKREF_DIV1		GENMASK(17, 16)
+
+#define REG_CSR_2L_CDR1_PR_MONPI		0x01ec
+#define CSR_2L_PXP_CDR1_PR_XFICK_EN		BIT(8)
+
+#define REG_CSR_2L_RX1_DAC_RANGE_EYE		0x01f4
+#define CSR_2L_PXP_RX1_SIGDET_LPF_CTRL		GENMASK(25, 24)
+
+#define REG_CSR_2L_RX1_SIGDET_NOVTH		0x01f8
+#define CSR_2L_PXP_RX1_SIGDET_PEAK		GENMASK(9, 8)
+#define CSR_2L_PXP_RX1_SIGDET_VTH_SEL		GENMASK(20, 16)
+
+#define REG_CSR_2L_RX1_FE_VB_EQ1		0x0200
+#define CSR_2L_PXP_RX1_FE_VB_EQ1_EN		BIT(0)
+#define CSR_2L_PXP_RX1_FE_VB_EQ2_EN		BIT(8)
+#define CSR_2L_PXP_RX1_FE_VB_EQ3_EN		BIT(16)
+#define CSR_2L_PXP_RX1_FE_VCM_GEN_PWDB		BIT(24)
+
+#define REG_CSR_2L_RX1_OSCAL_VGA1IOS		0x0214
+#define CSR_2L_PXP_RX1_PR_OSCAL_VGA1IOS		GENMASK(5, 0)
+#define CSR_2L_PXP_RX1_PR_OSCAL_VGA1VOS		GENMASK(13, 8)
+#define CSR_2L_PXP_RX1_PR_OSCAL_VGA2IOS		GENMASK(21, 16)
+
+/* PMA */
+#define REG_PCIE_PMA_SS_LCPLL_PWCTL_SETTING_1	0x0004
+#define PCIE_LCPLL_MAN_PWDB			BIT(0)
+
+#define REG_PCIE_PMA_SEQUENCE_DISB_CTRL1	0x010c
+#define PCIE_DISB_RX_SDCAL_EN			BIT(0)
+
+#define REG_PCIE_PMA_CTRL_SEQUENCE_FORCE_CTRL1	0x0114
+#define PCIE_FORCE_RX_SDCAL_EN			BIT(0)
+
+#define REG_PCIE_PMA_SS_RX_FREQ_DET1		0x014c
+#define PCIE_PLL_FT_LOCK_CYCLECNT		GENMASK(15, 0)
+#define PCIE_PLL_FT_UNLOCK_CYCLECNT		GENMASK(31, 16)
+
+#define REG_PCIE_PMA_SS_RX_FREQ_DET2		0x0150
+#define PCIE_LOCK_TARGET_BEG			GENMASK(15, 0)
+#define PCIE_LOCK_TARGET_END			GENMASK(31, 16)
+
+#define REG_PCIE_PMA_SS_RX_FREQ_DET3		0x0154
+#define PCIE_UNLOCK_TARGET_BEG			GENMASK(15, 0)
+#define PCIE_UNLOCK_TARGET_END			GENMASK(31, 16)
+
+#define REG_PCIE_PMA_SS_RX_FREQ_DET4		0x0158
+#define PCIE_FREQLOCK_DET_EN			GENMASK(2, 0)
+#define PCIE_LOCK_LOCKTH			GENMASK(11, 8)
+#define PCIE_UNLOCK_LOCKTH			GENMASK(15, 12)
+
+#define REG_PCIE_PMA_SS_RX_CAL1			0x0160
+#define REG_PCIE_PMA_SS_RX_CAL2			0x0164
+#define PCIE_CAL_OUT_OS				GENMASK(11, 8)
+
+#define REG_PCIE_PMA_SS_RX_SIGDET0		0x0168
+#define PCIE_SIGDET_WIN_NONVLD_TIMES		GENMASK(28, 24)
+
+#define REG_PCIE_PMA_TX_RESET			0x0260
+#define PCIE_TX_TOP_RST				BIT(0)
+#define PCIE_TX_CAL_RST				BIT(8)
+
+#define REG_PCIE_PMA_RX_FORCE_MODE0		0x0294
+#define PCIE_FORCE_DA_XPON_RX_FE_GAIN_CTRL	GENMASK(1, 0)
+
+#define REG_PCIE_PMA_SS_DA_XPON_PWDB0		0x034c
+#define PCIE_DA_XPON_CDR_PR_PWDB		BIT(8)
+
+#define REG_PCIE_PMA_SW_RESET			0x0460
+#define PCIE_SW_RX_FIFO_RST			BIT(0)
+#define PCIE_SW_RX_RST				BIT(1)
+#define PCIE_SW_TX_RST				BIT(2)
+#define PCIE_SW_PMA_RST				BIT(3)
+#define PCIE_SW_ALLPCS_RST			BIT(4)
+#define PCIE_SW_REF_RST				BIT(5)
+#define PCIE_SW_TX_FIFO_RST			BIT(6)
+#define PCIE_SW_XFI_TXPCS_RST			BIT(7)
+#define PCIE_SW_XFI_RXPCS_RST			BIT(8)
+#define PCIE_SW_XFI_RXPCS_BIST_RST		BIT(9)
+#define PCIE_SW_HSG_TXPCS_RST			BIT(10)
+#define PCIE_SW_HSG_RXPCS_RST			BIT(11)
+#define PCIE_PMA_SW_RST				(PCIE_SW_RX_FIFO_RST | \
+						 PCIE_SW_RX_RST | \
+						 PCIE_SW_TX_RST | \
+						 PCIE_SW_PMA_RST | \
+						 PCIE_SW_ALLPCS_RST | \
+						 PCIE_SW_REF_RST | \
+						 PCIE_SW_TX_FIFO_RST | \
+						 PCIE_SW_XFI_TXPCS_RST | \
+						 PCIE_SW_XFI_RXPCS_RST | \
+						 PCIE_SW_XFI_RXPCS_BIST_RST | \
+						 PCIE_SW_HSG_TXPCS_RST | \
+						 PCIE_SW_HSG_RXPCS_RST)
+
+#define REG_PCIE_PMA_RO_RX_FREQDET		0x0530
+#define PCIE_RO_FBCK_LOCK			BIT(0)
+#define PCIE_RO_FL_OUT				GENMASK(31, 16)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC	0x0794
+#define PCIE_FORCE_DA_PXP_CDR_PR_IDAC		GENMASK(10, 0)
+#define PCIE_FORCE_SEL_DA_PXP_CDR_PR_IDAC	BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_TXPLL_SDM_PCW	BIT(24)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_SDM_PCW	0x0798
+#define PCIE_FORCE_DA_PXP_TXPLL_SDM_PCW		GENMASK(30, 0)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_VOS	0x079c
+#define PCIE_FORCE_SEL_DA_PXP_JCPLL_SDM_PCW	BIT(16)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_JCPLL_SDM_PCW	0x0800
+#define PCIE_FORCE_DA_PXP_JCPLL_SDM_PCW		GENMASK(30, 0)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_CDR_PD_PWDB	0x081c
+#define PCIE_FORCE_DA_PXP_CDR_PD_PWDB		BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_CDR_PD_PWDB	BIT(8)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C	0x0820
+#define PCIE_FORCE_DA_PXP_CDR_PR_LPF_C_EN	BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_C_EN	BIT(8)
+#define PCIE_FORCE_DA_PXP_CDR_PR_LPF_R_EN	BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_R_EN	BIT(24)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB	0x0824
+#define PCIE_FORCE_DA_PXP_CDR_PR_PWDB			BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_CDR_PR_PWDB		BIT(24)
+
+#define REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT	0x0828
+#define PCIE_FORCE_DA_PXP_JCPLL_CKOUT_EN	BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_JCPLL_CKOUT_EN	BIT(8)
+#define PCIE_FORCE_DA_PXP_JCPLL_EN		BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_JCPLL_EN		BIT(24)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_RX_SCAN_RST	0x0084c
+#define PCIE_FORCE_DA_PXP_RX_SIGDET_PWDB	BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_RX_SIGDET_PWDB	BIT(24)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT	0x0854
+#define PCIE_FORCE_DA_PXP_TXPLL_CKOUT_EN	BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_TXPLL_CKOUT_EN	BIT(8)
+#define PCIE_FORCE_DA_PXP_TXPLL_EN		BIT(16)
+#define PCIE_FORCE_SEL_DA_PXP_TXPLL_EN		BIT(24)
+
+#define REG_PCIE_PMA_SCAN_MODE				0x0884
+#define PCIE_FORCE_DA_PXP_JCPLL_KBAND_LOAD_EN		BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_JCPLL_KBAND_LOAD_EN	BIT(8)
+
+#define REG_PCIE_PMA_DIG_RESERVE_13		0x08bc
+#define PCIE_FLL_IDAC_PCIEG1			GENMASK(10, 0)
+#define PCIE_FLL_IDAC_PCIEG2			GENMASK(26, 16)
+
+#define REG_PCIE_PMA_DIG_RESERVE_14		0x08c0
+#define PCIE_FLL_IDAC_PCIEG3			GENMASK(10, 0)
+#define PCIE_FLL_LOAD_EN			BIT(16)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_GAIN_CTRL	0x088c
+#define PCIE_FORCE_DA_PXP_RX_FE_GAIN_CTRL		GENMASK(1, 0)
+#define PCIE_FORCE_SEL_DA_PXP_RX_FE_GAIN_CTRL		BIT(8)
+
+#define REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_PWDB	0x0894
+#define PCIE_FORCE_DA_PXP_RX_FE_PWDB		BIT(0)
+#define PCIE_FORCE_SEL_DA_PXP_RX_FE_PWDB	BIT(8)
+
+#define REG_PCIE_PMA_DIG_RESERVE_12		0x08b8
+#define PCIE_FORCE_PMA_RX_SPEED			GENMASK(7, 4)
+#define PCIE_FORCE_SEL_PMA_RX_SPEED		BIT(7)
+
+#define REG_PCIE_PMA_DIG_RESERVE_17		0x08e0
+
+#define REG_PCIE_PMA_DIG_RESERVE_18		0x08e4
+#define PCIE_PXP_RX_VTH_SEL_PCIE_G1		GENMASK(4, 0)
+#define PCIE_PXP_RX_VTH_SEL_PCIE_G2		GENMASK(12, 8)
+#define PCIE_PXP_RX_VTH_SEL_PCIE_G3		GENMASK(20, 16)
+
+#define REG_PCIE_PMA_DIG_RESERVE_19		0x08e8
+#define PCIE_PCP_RX_REV0_PCIE_GEN1		GENMASK(31, 16)
+
+#define REG_PCIE_PMA_DIG_RESERVE_20		0x08ec
+#define PCIE_PCP_RX_REV0_PCIE_GEN2		GENMASK(15, 0)
+#define PCIE_PCP_RX_REV0_PCIE_GEN3		GENMASK(31, 16)
+
+#define REG_PCIE_PMA_DIG_RESERVE_21		0x08f0
+#define REG_PCIE_PMA_DIG_RESERVE_22		0x08f4
+#define REG_PCIE_PMA_DIG_RESERVE_27		0x0908
+#define REG_PCIE_PMA_DIG_RESERVE_30		0x0914
+
+/* DTIME */
+#define REG_PCIE_PEXTP_DIG_GLB44		0x00
+#define PCIE_XTP_RXDET_VCM_OFF_STB_T_SEL	GENMASK(7, 0)
+#define PCIE_XTP_RXDET_EN_STB_T_SEL		GENMASK(15, 8)
+#define PCIE_XTP_RXDET_FINISH_STB_T_SEL		GENMASK(23, 16)
+#define PCIE_XTP_TXPD_TX_DATA_EN_DLY		GENMASK(27, 24)
+#define PCIE_XTP_TXPD_RXDET_DONE_CDT		BIT(28)
+#define PCIE_XTP_RXDET_LATCH_STB_T_SEL		GENMASK(31, 29)
+
+/* RX AEQ */
+#define REG_PCIE_PEXTP_DIG_LN_RX30_P0		0x0000
+#define PCIE_XTP_LN_RX_PDOWN_L1P2_EXIT_WAIT	GENMASK(7, 0)
+#define PCIE_XTP_LN_RX_PDOWN_T2RLB_DIG_EN	BIT(8)
+#define PCIE_XTP_LN_RX_PDOWN_E0_AEQEN_WAIT	GENMASK(31, 16)
+
+#define REG_PCIE_PEXTP_DIG_LN_RX30_P1		0x0100
+
+#endif /* _PHY_AIROHA_PCIE_H */
diff --git a/drivers/phy/phy-airoha-pcie.c b/drivers/phy/phy-airoha-pcie.c
new file mode 100644
index 0000000..bd3edaa
--- /dev/null
+++ b/drivers/phy/phy-airoha-pcie.c
@@ -0,0 +1,1286 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "phy-airoha-pcie-regs.h"
+
+#define LEQ_LEN_CTRL_MAX_VAL	7
+#define FREQ_LOCK_MAX_ATTEMPT	10
+
+enum airoha_pcie_port_gen {
+	PCIE_PORT_GEN1 = 1,
+	PCIE_PORT_GEN2,
+	PCIE_PORT_GEN3,
+};
+
+/**
+ * struct airoha_pcie_phy - PCIe phy driver main structure
+ * @dev: pointer to device
+ * @phy: pointer to generic phy
+ * @csr_2l: Analogic lane IO mapped register base address
+ * @pma0: IO mapped register base address of PMA0-PCIe
+ * @pma1: IO mapped register base address of PMA1-PCIe
+ * @p0_xr_dtime: IO mapped register base address of port0 Tx-Rx detection time
+ * @p1_xr_dtime: IO mapped register base address of port1 Tx-Rx detection time
+ * @rx_aeq: IO mapped register base address of Rx AEQ training
+ */
+struct airoha_pcie_phy {
+	struct device *dev;
+	struct phy *phy;
+	void __iomem *csr_2l;
+	void __iomem *pma0;
+	void __iomem *pma1;
+	void __iomem *p0_xr_dtime;
+	void __iomem *p1_xr_dtime;
+	void __iomem *rx_aeq;
+};
+
+static void airoha_phy_clear_bits(void __iomem *reg, u32 mask)
+{
+	u32 val = readl(reg) & ~mask;
+
+	writel(val, reg);
+}
+
+static void airoha_phy_set_bits(void __iomem *reg, u32 mask)
+{
+	u32 val = readl(reg) | mask;
+
+	writel(val, reg);
+}
+
+static void airoha_phy_update_bits(void __iomem *reg, u32 mask, u32 val)
+{
+	u32 tmp = readl(reg);
+
+	tmp &= ~mask;
+	tmp |= val & mask;
+	writel(tmp, reg);
+}
+
+#define airoha_phy_update_field(reg, mask, val)					\
+	do {									\
+		BUILD_BUG_ON_MSG(!__builtin_constant_p((mask)),			\
+				 "mask is not constant");			\
+		airoha_phy_update_bits((reg), (mask),				\
+				       FIELD_PREP((mask), (val)));		\
+	} while (0)
+
+#define airoha_phy_csr_2l_clear_bits(pcie_phy, reg, mask)			\
+	airoha_phy_clear_bits((pcie_phy)->csr_2l + (reg), (mask))
+#define airoha_phy_csr_2l_set_bits(pcie_phy, reg, mask)				\
+	airoha_phy_set_bits((pcie_phy)->csr_2l + (reg), (mask))
+#define airoha_phy_csr_2l_update_field(pcie_phy, reg, mask, val)		\
+	airoha_phy_update_field((pcie_phy)->csr_2l + (reg), (mask), (val))
+#define airoha_phy_pma0_clear_bits(pcie_phy, reg, mask)				\
+	airoha_phy_clear_bits((pcie_phy)->pma0 + (reg), (mask))
+#define airoha_phy_pma1_clear_bits(pcie_phy, reg, mask)				\
+	airoha_phy_clear_bits((pcie_phy)->pma1 + (reg), (mask))
+#define airoha_phy_pma0_set_bits(pcie_phy, reg, mask)				\
+	airoha_phy_set_bits((pcie_phy)->pma0 + (reg), (mask))
+#define airoha_phy_pma1_set_bits(pcie_phy, reg, mask)				\
+	airoha_phy_set_bits((pcie_phy)->pma1 + (reg), (mask))
+#define airoha_phy_pma0_update_field(pcie_phy, reg, mask, val)			\
+	airoha_phy_update_field((pcie_phy)->pma0 + (reg), (mask), (val))
+#define airoha_phy_pma1_update_field(pcie_phy, reg, mask, val)			\
+	airoha_phy_update_field((pcie_phy)->pma1 + (reg), (mask), (val))
+
+static void
+airoha_phy_init_lane0_rx_fw_pre_calib(struct airoha_pcie_phy *pcie_phy,
+				      enum airoha_pcie_port_gen gen)
+{
+	u32 fl_out_target = gen == PCIE_PORT_GEN3 ? 41600 : 41941;
+	u32 lock_cyclecnt = gen == PCIE_PORT_GEN3 ? 26000 : 32767;
+	u32 pr_idac, val, cdr_pr_idac_tmp = 0;
+	int i;
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_SS_LCPLL_PWCTL_SETTING_1,
+				 PCIE_LCPLL_MAN_PWDB);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET2,
+				     PCIE_LOCK_TARGET_BEG,
+				     fl_out_target - 100);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET2,
+				     PCIE_LOCK_TARGET_END,
+				     fl_out_target + 100);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET1,
+				     PCIE_PLL_FT_LOCK_CYCLECNT, lock_cyclecnt);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET4,
+				     PCIE_LOCK_LOCKTH, 0x3);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET3,
+				     PCIE_UNLOCK_TARGET_BEG,
+				     fl_out_target - 100);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET3,
+				     PCIE_UNLOCK_TARGET_END,
+				     fl_out_target + 100);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET1,
+				     PCIE_PLL_FT_UNLOCK_CYCLECNT,
+				     lock_cyclecnt);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET4,
+				     PCIE_UNLOCK_LOCKTH, 0x3);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR0_PR_INJ_MODE,
+				   CSR_2L_PXP_CDR0_INJ_FORCE_OFF);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_IDAC);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				   PCIE_FORCE_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				 PCIE_FORCE_DA_PXP_CDR_PR_PWDB);
+
+	for (i = 0; i < LEQ_LEN_CTRL_MAX_VAL; i++) {
+		airoha_phy_pma0_update_field(pcie_phy,
+				REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				PCIE_FORCE_DA_PXP_CDR_PR_IDAC, i << 8);
+		airoha_phy_pma0_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = FIELD_GET(PCIE_RO_FL_OUT,
+				readl(pcie_phy->pma0 +
+				      REG_PCIE_PMA_RO_RX_FREQDET));
+		if (val > fl_out_target)
+			cdr_pr_idac_tmp = i << 8;
+	}
+
+	for (i = LEQ_LEN_CTRL_MAX_VAL; i >= 0; i--) {
+		pr_idac = cdr_pr_idac_tmp | (0x1 << i);
+		airoha_phy_pma0_update_field(pcie_phy,
+				REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				PCIE_FORCE_DA_PXP_CDR_PR_IDAC, pr_idac);
+		airoha_phy_pma0_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = FIELD_GET(PCIE_RO_FL_OUT,
+				readl(pcie_phy->pma0 +
+				      REG_PCIE_PMA_RO_RX_FREQDET));
+		if (val < fl_out_target)
+			pr_idac &= ~(0x1 << i);
+
+		cdr_pr_idac_tmp = pr_idac;
+	}
+
+	airoha_phy_pma0_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				     PCIE_FORCE_DA_PXP_CDR_PR_IDAC,
+				     cdr_pr_idac_tmp);
+
+	for (i = 0; i < FREQ_LOCK_MAX_ATTEMPT; i++) {
+		u32 val;
+
+		airoha_phy_pma0_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = readl(pcie_phy->pma0 + REG_PCIE_PMA_RO_RX_FREQDET);
+		if (val & PCIE_RO_FBCK_LOCK)
+			break;
+	}
+
+	/* turn off force mode and update band values */
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR0_PR_INJ_MODE,
+				     CSR_2L_PXP_CDR0_INJ_FORCE_OFF);
+
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_IDAC);
+	if (gen == PCIE_PORT_GEN3) {
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_14,
+					     PCIE_FLL_IDAC_PCIEG3,
+					     cdr_pr_idac_tmp);
+	} else {
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_13,
+					     PCIE_FLL_IDAC_PCIEG1,
+					     cdr_pr_idac_tmp);
+		airoha_phy_pma0_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_13,
+					     PCIE_FLL_IDAC_PCIEG2,
+					     cdr_pr_idac_tmp);
+	}
+}
+
+static void
+airoha_phy_init_lane1_rx_fw_pre_calib(struct airoha_pcie_phy *pcie_phy,
+				      enum airoha_pcie_port_gen gen)
+{
+	u32 fl_out_target = gen == PCIE_PORT_GEN3 ? 41600 : 41941;
+	u32 lock_cyclecnt = gen == PCIE_PORT_GEN3 ? 26000 : 32767;
+	u32 pr_idac, val, cdr_pr_idac_tmp = 0;
+	int i;
+
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_SS_LCPLL_PWCTL_SETTING_1,
+				 PCIE_LCPLL_MAN_PWDB);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET2,
+				     PCIE_LOCK_TARGET_BEG,
+				     fl_out_target - 100);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET2,
+				     PCIE_LOCK_TARGET_END,
+				     fl_out_target + 100);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET1,
+				     PCIE_PLL_FT_LOCK_CYCLECNT, lock_cyclecnt);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET4,
+				     PCIE_LOCK_LOCKTH, 0x3);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET3,
+				     PCIE_UNLOCK_TARGET_BEG,
+				     fl_out_target - 100);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET3,
+				     PCIE_UNLOCK_TARGET_END,
+				     fl_out_target + 100);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET1,
+				     PCIE_PLL_FT_UNLOCK_CYCLECNT,
+				     lock_cyclecnt);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_FREQ_DET4,
+				     PCIE_UNLOCK_LOCKTH, 0x3);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR1_PR_INJ_MODE,
+				   CSR_2L_PXP_CDR1_INJ_FORCE_OFF);
+
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_IDAC);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				   PCIE_FORCE_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				 PCIE_FORCE_DA_PXP_CDR_PR_PWDB);
+
+	for (i = 0; i < LEQ_LEN_CTRL_MAX_VAL; i++) {
+		airoha_phy_pma1_update_field(pcie_phy,
+				REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				PCIE_FORCE_DA_PXP_CDR_PR_IDAC, i << 8);
+		airoha_phy_pma1_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = FIELD_GET(PCIE_RO_FL_OUT,
+				readl(pcie_phy->pma1 +
+				      REG_PCIE_PMA_RO_RX_FREQDET));
+		if (val > fl_out_target)
+			cdr_pr_idac_tmp = i << 8;
+	}
+
+	for (i = LEQ_LEN_CTRL_MAX_VAL; i >= 0; i--) {
+		pr_idac = cdr_pr_idac_tmp | (0x1 << i);
+		airoha_phy_pma1_update_field(pcie_phy,
+				REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				PCIE_FORCE_DA_PXP_CDR_PR_IDAC, pr_idac);
+		airoha_phy_pma1_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = FIELD_GET(PCIE_RO_FL_OUT,
+				readl(pcie_phy->pma1 +
+				      REG_PCIE_PMA_RO_RX_FREQDET));
+		if (val < fl_out_target)
+			pr_idac &= ~(0x1 << i);
+
+		cdr_pr_idac_tmp = pr_idac;
+	}
+
+	airoha_phy_pma1_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				     PCIE_FORCE_DA_PXP_CDR_PR_IDAC,
+				     cdr_pr_idac_tmp);
+
+	for (i = 0; i < FREQ_LOCK_MAX_ATTEMPT; i++) {
+		u32 val;
+
+		airoha_phy_pma1_clear_bits(pcie_phy,
+					   REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					   PCIE_FREQLOCK_DET_EN);
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_SS_RX_FREQ_DET4,
+					     PCIE_FREQLOCK_DET_EN, 0x3);
+
+		usleep_range(10000, 15000);
+
+		val = readl(pcie_phy->pma1 + REG_PCIE_PMA_RO_RX_FREQDET);
+		if (val & PCIE_RO_FBCK_LOCK)
+			break;
+	}
+
+	/* turn off force mode and update band values */
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR1_PR_INJ_MODE,
+				     CSR_2L_PXP_CDR1_INJ_FORCE_OFF);
+
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_R_EN);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_LPF_C,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_LPF_C_EN);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_PIEYE_PWDB,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_PWDB);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				   PCIE_FORCE_SEL_DA_PXP_CDR_PR_IDAC);
+	if (gen == PCIE_PORT_GEN3) {
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_14,
+					     PCIE_FLL_IDAC_PCIEG3,
+					     cdr_pr_idac_tmp);
+	} else {
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_13,
+					     PCIE_FLL_IDAC_PCIEG1,
+					     cdr_pr_idac_tmp);
+		airoha_phy_pma1_update_field(pcie_phy,
+					     REG_PCIE_PMA_DIG_RESERVE_13,
+					     PCIE_FLL_IDAC_PCIEG2,
+					     cdr_pr_idac_tmp);
+	}
+}
+
+static void airoha_pcie_phy_init_default(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CMN,
+				       CSR_2L_PXP_CMN_TRIM_MASK, 0x10);
+	writel(0xcccbcccb, pcie_phy->pma0 + REG_PCIE_PMA_DIG_RESERVE_21);
+	writel(0xcccb, pcie_phy->pma0 + REG_PCIE_PMA_DIG_RESERVE_22);
+	writel(0xcccbcccb, pcie_phy->pma1 + REG_PCIE_PMA_DIG_RESERVE_21);
+	writel(0xcccb, pcie_phy->pma1 + REG_PCIE_PMA_DIG_RESERVE_22);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CMN,
+				   CSR_2L_PXP_CMN_LANE_EN);
+}
+
+static void airoha_pcie_phy_init_clk_out(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_TXPLL_POSTDIV_D256,
+				       CSR_2L_PXP_CLKTX0_AMP, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_CLKTX0_FORCE_OUT1,
+				       CSR_2L_PXP_CLKTX1_AMP, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_TXPLL_POSTDIV_D256,
+				       CSR_2L_PXP_CLKTX0_OFFSET, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CLKTX1_OFFSET,
+				       CSR_2L_PXP_CLKTX1_OFFSET, 0x2);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CLKTX0_FORCE_OUT1,
+				     CSR_2L_PXP_CLKTX0_HZ);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CLKTX1_OFFSET,
+				     CSR_2L_PXP_CLKTX1_HZ);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_CLKTX0_FORCE_OUT1,
+				       CSR_2L_PXP_CLKTX0_IMP_SEL, 0x12);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CLKTX1_IMP_SEL,
+				       CSR_2L_PXP_CLKTX1_IMP_SEL, 0x12);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_POSTDIV_D256,
+				     CSR_2L_PXP_CLKTX0_SR);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CLKTX1_OFFSET,
+				     CSR_2L_PXP_CLKTX1_SR);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_PLL_CMN_RESERVE0,
+				       CSR_2L_PXP_PLL_RESERVE_MASK, 0xdd);
+}
+
+static void airoha_pcie_phy_init_csr_2l(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				 PCIE_SW_XFI_RXPCS_RST | PCIE_SW_REF_RST |
+				 PCIE_SW_RX_RST);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				 PCIE_SW_XFI_RXPCS_RST | PCIE_SW_REF_RST |
+				 PCIE_SW_RX_RST);
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_TX_RESET,
+				 PCIE_TX_TOP_RST | REG_PCIE_PMA_TX_RESET);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_TX_RESET,
+				 PCIE_TX_TOP_RST | REG_PCIE_PMA_TX_RESET);
+}
+
+static void airoha_pcie_phy_init_rx(struct airoha_pcie_phy *pcie_phy)
+{
+	writel(0x2a00090b, pcie_phy->pma0 + REG_PCIE_PMA_DIG_RESERVE_17);
+	writel(0x2a00090b, pcie_phy->pma1 + REG_PCIE_PMA_DIG_RESERVE_17);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR0_PR_MONPI,
+				   CSR_2L_PXP_CDR0_PR_XFICK_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR1_PR_MONPI,
+				   CSR_2L_PXP_CDR1_PR_XFICK_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy,
+				     REG_CSR_2L_CDR0_PD_PICAL_CKD8_INV,
+				     CSR_2L_PXP_CDR0_PD_EDGE_DISABLE);
+	airoha_phy_csr_2l_clear_bits(pcie_phy,
+				     REG_CSR_2L_CDR1_PD_PICAL_CKD8_INV,
+				     CSR_2L_PXP_CDR1_PD_EDGE_DISABLE);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_PHYCK_DIV,
+				       CSR_2L_PXP_RX0_PHYCK_SEL, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_PHYCK_DIV,
+				       CSR_2L_PXP_RX1_PHYCK_SEL, 0x1);
+}
+
+static void airoha_pcie_phy_init_jcpll(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				   PCIE_FORCE_DA_PXP_JCPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_EN);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				   PCIE_FORCE_DA_PXP_JCPLL_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_TCL_VTP_EN,
+				       CSR_2L_PXP_JCPLL_SPARE_LOW, 0x20);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_RST_DLY,
+				   CSR_2L_PXP_JCPLL_RST);
+	writel(0x0, pcie_phy->csr_2l + REG_CSR_2L_JCPLL_SSC_DELTA1);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC_PERIOD,
+				     CSR_2L_PXP_JCPLL_SSC_PERIOD);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				     CSR_2L_PXP_JCPLL_SSC_PHASE_INI);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				     CSR_2L_PXP_JCPLL_SSC_TRI_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BR,
+				       CSR_2L_PXP_JCPLL_LPF_BR, 0xa);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BR,
+				       CSR_2L_PXP_JCPLL_LPF_BP, 0xc);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BR,
+				       CSR_2L_PXP_JCPLL_LPF_BC, 0x1f);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BWC,
+				       CSR_2L_PXP_JCPLL_LPF_BWC, 0x1e);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BR,
+				       CSR_2L_PXP_JCPLL_LPF_BWR, 0xa);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_JCPLL_MMD_PREDIV_MODE,
+				       CSR_2L_PXP_JCPLL_MMD_PREDIV_MODE,
+				       0x1);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, CSR_2L_PXP_JCPLL_MONCK,
+				     CSR_2L_PXP_JCPLL_REFIN_DIV);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_VOS,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_SDM_PCW);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_VOS,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_SDM_PCW);
+	airoha_phy_pma0_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_JCPLL_SDM_PCW,
+				     PCIE_FORCE_DA_PXP_JCPLL_SDM_PCW,
+				     0x50000000);
+	airoha_phy_pma1_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_JCPLL_SDM_PCW,
+				     PCIE_FORCE_DA_PXP_JCPLL_SDM_PCW,
+				     0x50000000);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy,
+				   REG_CSR_2L_JCPLL_MMD_PREDIV_MODE,
+				   CSR_2L_PXP_JCPLL_POSTDIV_D5);
+	airoha_phy_csr_2l_set_bits(pcie_phy,
+				   REG_CSR_2L_JCPLL_MMD_PREDIV_MODE,
+				   CSR_2L_PXP_JCPLL_POSTDIV_D2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_RST_DLY,
+				       CSR_2L_PXP_JCPLL_RST_DLY, 0x4);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_RST_DLY,
+				     CSR_2L_PXP_JCPLL_SDM_DI_LS);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_TCL_KBAND_VREF,
+				     CSR_2L_PXP_JCPLL_VCO_KBAND_MEAS_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_IB_EXT,
+				     CSR_2L_PXP_JCPLL_CHP_IOFST);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_IB_EXT,
+				       CSR_2L_PXP_JCPLL_CHP_IBIAS, 0xc);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_JCPLL_MMD_PREDIV_MODE,
+				       CSR_2L_PXP_JCPLL_MMD_PREDIV_MODE,
+				       0x1);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_VCODIV,
+				   CSR_2L_PXP_JCPLL_VCO_HALFLSB_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_VCODIV,
+				       CSR_2L_PXP_JCPLL_VCO_CFIX, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_VCODIV,
+				       CSR_2L_PXP_JCPLL_VCO_SCAPWR, 0x4);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_IB_EXT,
+				     REG_CSR_2L_JCPLL_LPF_SHCK_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_KBAND_KFC,
+				   CSR_2L_PXP_JCPLL_POSTDIV_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_KBAND_KFC,
+				     CSR_2L_PXP_JCPLL_KBAND_KFC);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_KBAND_KFC,
+				       CSR_2L_PXP_JCPLL_KBAND_KF, 0x3);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_KBAND_KFC,
+				     CSR_2L_PXP_JCPLL_KBAND_KS);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BWC,
+				       CSR_2L_PXP_JCPLL_KBAND_DIV, 0x1);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_SCAN_MODE,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_KBAND_LOAD_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy, REG_PCIE_PMA_SCAN_MODE,
+				   PCIE_FORCE_DA_PXP_JCPLL_KBAND_LOAD_EN);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_LPF_BWC,
+				       CSR_2L_PXP_JCPLL_KBAND_CODE, 0xe4);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SDM_HREN,
+				   CSR_2L_PXP_JCPLL_TCL_AMP_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_TCL_CMP,
+				   CSR_2L_PXP_JCPLL_TCL_LPF_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_JCPLL_TCL_KBAND_VREF,
+				       CSR_2L_PXP_JCPLL_TCL_KBAND_VREF, 0xf);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_SDM_HREN,
+				       CSR_2L_PXP_JCPLL_TCL_AMP_GAIN, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_SDM_HREN,
+				       CSR_2L_PXP_JCPLL_TCL_AMP_VREF, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_TCL_CMP,
+				       CSR_2L_PXP_JCPLL_TCL_LPF_BW, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_VCO_TCLVAR,
+				       CSR_2L_PXP_JCPLL_VCO_TCLVAR, 0x3);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_CKOUT_EN);
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_JCPLL_CKOUT_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_CKOUT_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_JCPLL_CKOUT_EN);
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_EN);
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_JCPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_JCPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_PXP_JCPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_JCPLL_EN);
+}
+
+static void airoha_pcie_phy_txpll(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_EN);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				   PCIE_FORCE_DA_PXP_TXPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_EN);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				   PCIE_FORCE_DA_PXP_TXPLL_EN);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_REFIN_DIV,
+				   CSR_2L_PXP_TXPLL_PLL_RSTB);
+	writel(0x0, pcie_phy->csr_2l + REG_CSR_2L_TXPLL_SSC_DELTA1);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SSC_PERIOD,
+				     CSR_2L_PXP_txpll_SSC_PERIOD);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_CHP_IOFST,
+				       CSR_2L_PXP_TXPLL_CHP_IOFST, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_750M_SYS_CK,
+				       CSR_2L_PXP_TXPLL_CHP_IBIAS, 0x2d);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_REFIN_DIV,
+				     CSR_2L_PXP_TXPLL_REFIN_DIV);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_TCL_LPF_BW,
+				       CSR_2L_PXP_TXPLL_VCO_CFIX, 0x3);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_SDM_PCW);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_SDM_PCW);
+	airoha_phy_pma0_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_SDM_PCW,
+				     PCIE_FORCE_DA_PXP_TXPLL_SDM_PCW,
+				     0xc800000);
+	airoha_phy_pma1_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_SDM_PCW,
+				     PCIE_FORCE_DA_PXP_TXPLL_SDM_PCW,
+				     0xc800000);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SDM_DI_LS,
+				     CSR_2L_PXP_TXPLL_SDM_IFM);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SSC,
+				     CSR_2L_PXP_TXPLL_SSC_PHASE_INI);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_REFIN_DIV,
+				       CSR_2L_PXP_TXPLL_RST_DLY, 0x4);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SDM_DI_LS,
+				     CSR_2L_PXP_TXPLL_SDM_DI_LS);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_SDM_DI_LS,
+				       CSR_2L_PXP_TXPLL_SDM_ORD, 0x3);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_TCL_KBAND_VREF,
+				     CSR_2L_PXP_TXPLL_VCO_KBAND_MEAS_EN);
+	writel(0x0, pcie_phy->csr_2l + REG_CSR_2L_TXPLL_SSC_DELTA1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_CHP_IOFST,
+				       CSR_2L_PXP_TXPLL_LPF_BP, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_CHP_IOFST,
+				       CSR_2L_PXP_TXPLL_LPF_BC, 0x18);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_CHP_IOFST,
+				       CSR_2L_PXP_TXPLL_LPF_BR, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_CHP_IOFST,
+				       CSR_2L_PXP_TXPLL_CHP_IOFST, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_750M_SYS_CK,
+				       CSR_2L_PXP_TXPLL_CHP_IBIAS, 0x2d);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_TCL_VTP,
+				       CSR_2L_PXP_TXPLL_SPARE_L, 0x1);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_LPF_BWR,
+				     CSR_2L_PXP_TXPLL_LPF_BWC);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_POSTDIV,
+				     CSR_2L_PXP_TXPLL_MMD_PREDIV_MODE);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_REFIN_DIV,
+				     CSR_2L_PXP_TXPLL_REFIN_DIV);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_TCL_LPF_BW,
+				   CSR_2L_PXP_TXPLL_VCO_HALFLSB_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_VCO_SCAPWR,
+				       CSR_2L_PXP_TXPLL_VCO_SCAPWR, 0x7);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_TCL_LPF_BW,
+				       CSR_2L_PXP_TXPLL_VCO_CFIX, 0x3);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_SDM_PCW);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PR_IDAC,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_SDM_PCW);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SSC,
+				     CSR_2L_PXP_TXPLL_SSC_PHASE_INI);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_LPF_BWR,
+				     CSR_2L_PXP_TXPLL_LPF_BWR);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_PHY_CK2,
+				   CSR_2L_PXP_TXPLL_REFIN_INTERNAL);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_TCL_KBAND_VREF,
+				     CSR_2L_PXP_TXPLL_VCO_KBAND_MEAS_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_VTP,
+				     CSR_2L_PXP_TXPLL_VTP_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_POSTDIV,
+				     CSR_2L_PXP_TXPLL_PHY_CK1_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_PHY_CK2,
+				   CSR_2L_PXP_TXPLL_REFIN_INTERNAL);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_SSC,
+				     CSR_2L_PXP_TXPLL_SSC_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_750M_SYS_CK,
+				     CSR_2L_PXP_TXPLL_LPF_SHCK_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_POSTDIV,
+				     CSR_2L_PXP_TXPLL_POSTDIV_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TXPLL_KBAND_DIV,
+				     CSR_2L_PXP_TXPLL_KBAND_KFC);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_KBAND_DIV,
+				       CSR_2L_PXP_TXPLL_KBAND_KF, 0x3);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_KBAND_DIV,
+				       CSR_2L_PXP_txpll_KBAND_KS, 0x1);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_KBAND_DIV,
+				       CSR_2L_PXP_TXPLL_KBAND_DIV, 0x4);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_LPF_BWR,
+				       CSR_2L_PXP_TXPLL_KBAND_CODE, 0xe4);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_SDM_OUT,
+				   CSR_2L_PXP_TXPLL_TCL_AMP_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TXPLL_TCL_AMP_VREF,
+				   CSR_2L_PXP_TXPLL_TCL_LPF_EN);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_TXPLL_TCL_KBAND_VREF,
+				       CSR_2L_PXP_TXPLL_TCL_KBAND_VREF, 0xf);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_SDM_OUT,
+				       CSR_2L_PXP_TXPLL_TCL_AMP_GAIN, 0x3);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_TXPLL_TCL_AMP_VREF,
+				       CSR_2L_PXP_TXPLL_TCL_AMP_VREF, 0xb);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_TXPLL_TCL_LPF_BW,
+				       CSR_2L_PXP_TXPLL_TCL_LPF_BW, 0x3);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_CKOUT_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_TXPLL_CKOUT_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_CKOUT_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_TXPLL_CKOUT_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_EN);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_TXPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_SEL_DA_PXP_TXPLL_EN);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_TXPLL_CKOUT,
+				 PCIE_FORCE_DA_PXP_TXPLL_EN);
+}
+
+static void airoha_pcie_phy_init_ssc_jcpll(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_SSC_DELTA1,
+				       CSR_2L_PXP_JCPLL_SSC_DELTA1, 0x106);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_SSC_DELTA1,
+				       CSR_2L_PXP_JCPLL_SSC_DELTA, 0x106);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_JCPLL_SSC_PERIOD,
+				       CSR_2L_PXP_JCPLL_SSC_PERIOD, 0x31b);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				   CSR_2L_PXP_JCPLL_SSC_PHASE_INI);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				   CSR_2L_PXP_JCPLL_SSC_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SDM_IFM,
+				   CSR_2L_PXP_JCPLL_SDM_IFM);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SDM_HREN,
+				   REG_CSR_2L_JCPLL_SDM_HREN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_RST_DLY,
+				     CSR_2L_PXP_JCPLL_SDM_DI_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				   CSR_2L_PXP_JCPLL_SSC_TRI_EN);
+}
+
+static void
+airoha_pcie_phy_set_rxlan0_signal_detect(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR0_PR_COR_HBW,
+				   CSR_2L_PXP_CDR0_PR_LDO_FORCE_ON);
+
+	usleep_range(100, 200);
+
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_19,
+				     PCIE_PCP_RX_REV0_PCIE_GEN1, 0x18b0);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_20,
+				     PCIE_PCP_RX_REV0_PCIE_GEN2, 0x18b0);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_20,
+				     PCIE_PCP_RX_REV0_PCIE_GEN3, 0x1030);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_SIGDET_DCTEST,
+				       CSR_2L_PXP_RX0_SIGDET_PEAK, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_SIGDET_VTH_SEL,
+				       CSR_2L_PXP_RX0_SIGDET_VTH_SEL, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_REV0,
+				       CSR_2L_PXP_VOS_PNINV, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_SIGDET_DCTEST,
+				       CSR_2L_PXP_RX0_SIGDET_LPF_CTRL, 0x1);
+
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_CAL2,
+				     PCIE_CAL_OUT_OS, 0x0);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_PXP_RX0_FE_VB_EQ2,
+				   CSR_2L_PXP_RX0_FE_VCM_GEN_PWDB);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_GAIN_CTRL,
+				 PCIE_FORCE_SEL_DA_PXP_RX_FE_PWDB);
+	airoha_phy_pma0_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_GAIN_CTRL,
+				     PCIE_FORCE_DA_PXP_RX_FE_GAIN_CTRL, 0x3);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_RX_FORCE_MODE0,
+				     PCIE_FORCE_DA_XPON_RX_FE_GAIN_CTRL, 0x1);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_SIGDET0,
+				     PCIE_SIGDET_WIN_NONVLD_TIMES, 0x3);
+	airoha_phy_pma0_clear_bits(pcie_phy, REG_PCIE_PMA_SEQUENCE_DISB_CTRL1,
+				   PCIE_DISB_RX_SDCAL_EN);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_CTRL_SEQUENCE_FORCE_CTRL1,
+				 PCIE_FORCE_RX_SDCAL_EN);
+	usleep_range(150, 200);
+	airoha_phy_pma0_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_CTRL_SEQUENCE_FORCE_CTRL1,
+				   PCIE_FORCE_RX_SDCAL_EN);
+}
+
+static void
+airoha_pcie_phy_set_rxlan1_signal_detect(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_CDR1_PR_COR_HBW,
+				   CSR_2L_PXP_CDR1_PR_LDO_FORCE_ON);
+
+	usleep_range(100, 200);
+
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_19,
+				     PCIE_PCP_RX_REV0_PCIE_GEN1, 0x18b0);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_20,
+				     PCIE_PCP_RX_REV0_PCIE_GEN2, 0x18b0);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_20,
+				     PCIE_PCP_RX_REV0_PCIE_GEN3, 0x1030);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_SIGDET_NOVTH,
+				       CSR_2L_PXP_RX1_SIGDET_PEAK, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_SIGDET_NOVTH,
+				       CSR_2L_PXP_RX1_SIGDET_VTH_SEL, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_REV0,
+				       CSR_2L_PXP_VOS_PNINV, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_DAC_RANGE_EYE,
+				       CSR_2L_PXP_RX1_SIGDET_LPF_CTRL, 0x1);
+
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_CAL2,
+				     PCIE_CAL_OUT_OS, 0x0);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_RX1_FE_VB_EQ1,
+				   CSR_2L_PXP_RX1_FE_VCM_GEN_PWDB);
+
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_GAIN_CTRL,
+				 PCIE_FORCE_SEL_DA_PXP_RX_FE_PWDB);
+	airoha_phy_pma1_update_field(pcie_phy,
+				     REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_GAIN_CTRL,
+				     PCIE_FORCE_DA_PXP_RX_FE_GAIN_CTRL, 0x3);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_RX_FORCE_MODE0,
+				     PCIE_FORCE_DA_XPON_RX_FE_GAIN_CTRL, 0x1);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_SS_RX_SIGDET0,
+				     PCIE_SIGDET_WIN_NONVLD_TIMES, 0x3);
+	airoha_phy_pma1_clear_bits(pcie_phy, REG_PCIE_PMA_SEQUENCE_DISB_CTRL1,
+				   PCIE_DISB_RX_SDCAL_EN);
+
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_CTRL_SEQUENCE_FORCE_CTRL1,
+				 PCIE_FORCE_RX_SDCAL_EN);
+	usleep_range(150, 200);
+	airoha_phy_pma1_clear_bits(pcie_phy,
+				   REG_PCIE_PMA_CTRL_SEQUENCE_FORCE_CTRL1,
+				   PCIE_FORCE_RX_SDCAL_EN);
+}
+
+static void airoha_pcie_phy_set_rxflow(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_SCAN_RST,
+				 PCIE_FORCE_DA_PXP_RX_SIGDET_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_RX_SIGDET_PWDB);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_SCAN_RST,
+				 PCIE_FORCE_DA_PXP_RX_SIGDET_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_RX_SIGDET_PWDB);
+
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PD_PWDB,
+				 PCIE_FORCE_DA_PXP_CDR_PD_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PD_PWDB);
+	airoha_phy_pma0_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_PWDB,
+				 PCIE_FORCE_DA_PXP_RX_FE_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_RX_FE_PWDB);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_CDR_PD_PWDB,
+				 PCIE_FORCE_DA_PXP_CDR_PD_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_CDR_PD_PWDB);
+	airoha_phy_pma1_set_bits(pcie_phy,
+				 REG_PCIE_PMA_FORCE_DA_PXP_RX_FE_PWDB,
+				 PCIE_FORCE_DA_PXP_RX_FE_PWDB |
+				 PCIE_FORCE_SEL_DA_PXP_RX_FE_PWDB);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_RX0_PHYCK_DIV,
+				   CSR_2L_PXP_RX0_PHYCK_RSTB |
+				   CSR_2L_PXP_RX0_TDC_CK_SEL);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_RX1_PHYCK_DIV,
+				   CSR_2L_PXP_RX1_PHYCK_RSTB |
+				   CSR_2L_PXP_RX1_TDC_CK_SEL);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				 PCIE_SW_RX_FIFO_RST | PCIE_SW_TX_RST |
+				 PCIE_SW_PMA_RST | PCIE_SW_ALLPCS_RST |
+				 PCIE_SW_TX_FIFO_RST);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				 PCIE_SW_RX_FIFO_RST | PCIE_SW_TX_RST |
+				 PCIE_SW_PMA_RST | PCIE_SW_ALLPCS_RST |
+				 PCIE_SW_TX_FIFO_RST);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_PXP_RX0_FE_VB_EQ2,
+				   CSR_2L_PXP_RX0_FE_VB_EQ2_EN |
+				   CSR_2L_PXP_RX0_FE_VB_EQ3_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_RX0_SIGDET_VTH_SEL,
+				   CSR_2L_PXP_RX0_FE_VB_EQ1_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_RX1_FE_VB_EQ1,
+				   CSR_2L_PXP_RX1_FE_VB_EQ1_EN |
+				   CSR_2L_PXP_RX1_FE_VB_EQ2_EN |
+				   CSR_2L_PXP_RX1_FE_VB_EQ3_EN);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_REV0,
+				       CSR_2L_PXP_FE_GAIN_NORMAL_MODE, 0x4);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX0_REV0,
+				       CSR_2L_PXP_FE_GAIN_TRAIN_MODE, 0x4);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_REV0,
+				       CSR_2L_PXP_FE_GAIN_NORMAL_MODE, 0x4);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_REV0,
+				       CSR_2L_PXP_FE_GAIN_TRAIN_MODE, 0x4);
+}
+
+static void airoha_pcie_phy_set_pr(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_PR_VREG_IBAND,
+				       CSR_2L_PXP_CDR0_PR_VREG_IBAND, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_PR_VREG_IBAND,
+				       CSR_2L_PXP_CDR0_PR_VREG_CKBUF, 0x5);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR0_PR_CKREF_DIV,
+				     CSR_2L_PXP_CDR0_PR_CKREF_DIV);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR0_PR_COR_HBW,
+				     CSR_2L_PXP_CDR0_PR_CKREF_DIV1);
+
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_CDR1_PR_VREG_IBAND_VAL,
+				       CSR_2L_PXP_CDR1_PR_VREG_IBAND, 0x5);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_CDR1_PR_VREG_IBAND_VAL,
+				       CSR_2L_PXP_CDR1_PR_VREG_CKBUF, 0x5);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR1_PR_CKREF_DIV,
+				     CSR_2L_PXP_CDR1_PR_CKREF_DIV);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR1_PR_COR_HBW,
+				     CSR_2L_PXP_CDR1_PR_CKREF_DIV1);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_LPF_RATIO,
+				       CSR_2L_PXP_CDR0_LPF_TOP_LIM, 0x20000);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR1_LPF_RATIO,
+				       CSR_2L_PXP_CDR1_LPF_TOP_LIM, 0x20000);
+
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_PR_BETA_DAC,
+				       CSR_2L_PXP_CDR0_PR_BETA_SEL, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR1_PR_BETA_DAC,
+				       CSR_2L_PXP_CDR1_PR_BETA_SEL, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_PR_BETA_DAC,
+				       CSR_2L_PXP_CDR0_PR_KBAND_DIV, 0x4);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR1_PR_BETA_DAC,
+				       CSR_2L_PXP_CDR1_PR_KBAND_DIV, 0x4);
+}
+
+static void airoha_pcie_phy_set_txflow(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TX0_CKLDO,
+				   CSR_2L_PXP_TX0_CKLDO_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TX1_CKLDO,
+				   CSR_2L_PXP_TX1_CKLDO_EN);
+
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TX0_CKLDO,
+				   CSR_2L_PXP_TX0_DMEDGEGEN_EN);
+	airoha_phy_csr_2l_set_bits(pcie_phy, REG_CSR_2L_TX1_CKLDO,
+				   CSR_2L_PXP_TX1_DMEDGEGEN_EN);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_TX1_MULTLANE,
+				     CSR_2L_PXP_TX1_MULTLANE_EN);
+}
+
+static void airoha_pcie_phy_set_rx_mode(struct airoha_pcie_phy *pcie_phy)
+{
+	writel(0x804000, pcie_phy->pma0 + REG_PCIE_PMA_DIG_RESERVE_27);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G1, 0x5);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G2, 0x5);
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G3, 0x5);
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_30,
+				 0x77700);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR0_PR_MONCK,
+				     CSR_2L_PXP_CDR0_PR_MONCK_ENABLE);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR0_PR_MONCK,
+				       CSR_2L_PXP_CDR0_PR_RESERVE0, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_PXP_RX0_OSCAL_CTLE1IOS,
+				       CSR_2L_PXP_RX0_PR_OSCAL_VGA1IOS, 0x19);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_PXP_RX0_OSCA_VGA1VOS,
+				       CSR_2L_PXP_RX0_PR_OSCAL_VGA1VOS, 0x19);
+	airoha_phy_csr_2l_update_field(pcie_phy,
+				       REG_CSR_2L_PXP_RX0_OSCA_VGA1VOS,
+				       CSR_2L_PXP_RX0_PR_OSCAL_VGA2IOS, 0x14);
+
+	writel(0x804000, pcie_phy->pma1 + REG_PCIE_PMA_DIG_RESERVE_27);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G1, 0x5);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G2, 0x5);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_18,
+				     PCIE_PXP_RX_VTH_SEL_PCIE_G3, 0x5);
+
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_30,
+				 0x77700);
+
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_CDR1_PR_MONCK,
+				     CSR_2L_PXP_CDR1_PR_MONCK_ENABLE);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_CDR1_PR_MONCK,
+				       CSR_2L_PXP_CDR1_PR_RESERVE0, 0x2);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_OSCAL_VGA1IOS,
+				       CSR_2L_PXP_RX1_PR_OSCAL_VGA1IOS, 0x19);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_OSCAL_VGA1IOS,
+				       CSR_2L_PXP_RX1_PR_OSCAL_VGA1VOS, 0x19);
+	airoha_phy_csr_2l_update_field(pcie_phy, REG_CSR_2L_RX1_OSCAL_VGA1IOS,
+				       CSR_2L_PXP_RX1_PR_OSCAL_VGA2IOS, 0x14);
+}
+
+static void airoha_pcie_phy_load_kflow(struct airoha_pcie_phy *pcie_phy)
+{
+	airoha_phy_pma0_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_12,
+				     PCIE_FORCE_PMA_RX_SPEED, 0xa);
+	airoha_phy_pma1_update_field(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_12,
+				     PCIE_FORCE_PMA_RX_SPEED, 0xa);
+	airoha_phy_init_lane0_rx_fw_pre_calib(pcie_phy, PCIE_PORT_GEN3);
+	airoha_phy_init_lane1_rx_fw_pre_calib(pcie_phy, PCIE_PORT_GEN3);
+
+	airoha_phy_pma0_clear_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_12,
+				   PCIE_FORCE_PMA_RX_SPEED);
+	airoha_phy_pma1_clear_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_12,
+				   PCIE_FORCE_PMA_RX_SPEED);
+	usleep_range(100, 200);
+
+	airoha_phy_init_lane0_rx_fw_pre_calib(pcie_phy, PCIE_PORT_GEN2);
+	airoha_phy_init_lane1_rx_fw_pre_calib(pcie_phy, PCIE_PORT_GEN2);
+}
+
+/**
+ * airoha_pcie_phy_init() - Initialize the phy
+ * @phy: the phy to be initialized
+ *
+ * Initialize the phy registers.
+ * The hardware settings will be reset during suspend, it should be
+ * reinitialized when the consumer calls phy_init() again on resume.
+ */
+static int airoha_pcie_phy_init(struct phy *phy)
+{
+	struct airoha_pcie_phy *pcie_phy = phy_get_drvdata(phy);
+	u32 val;
+
+	/* Setup Tx-Rx detection time */
+	val = FIELD_PREP(PCIE_XTP_RXDET_VCM_OFF_STB_T_SEL, 0x33) |
+	      FIELD_PREP(PCIE_XTP_RXDET_EN_STB_T_SEL, 0x1) |
+	      FIELD_PREP(PCIE_XTP_RXDET_FINISH_STB_T_SEL, 0x2) |
+	      FIELD_PREP(PCIE_XTP_TXPD_TX_DATA_EN_DLY, 0x3) |
+	      FIELD_PREP(PCIE_XTP_RXDET_LATCH_STB_T_SEL, 0x1);
+	writel(val, pcie_phy->p0_xr_dtime + REG_PCIE_PEXTP_DIG_GLB44);
+	writel(val, pcie_phy->p1_xr_dtime + REG_PCIE_PEXTP_DIG_GLB44);
+	/* Setup Rx AEQ training time */
+	val = FIELD_PREP(PCIE_XTP_LN_RX_PDOWN_L1P2_EXIT_WAIT, 0x32) |
+	      FIELD_PREP(PCIE_XTP_LN_RX_PDOWN_E0_AEQEN_WAIT, 0x5050);
+	writel(val, pcie_phy->rx_aeq + REG_PCIE_PEXTP_DIG_LN_RX30_P0);
+	writel(val, pcie_phy->rx_aeq + REG_PCIE_PEXTP_DIG_LN_RX30_P1);
+
+	/* enable load FLL-K flow */
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_14,
+				 PCIE_FLL_LOAD_EN);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_DIG_RESERVE_14,
+				 PCIE_FLL_LOAD_EN);
+
+	airoha_pcie_phy_init_default(pcie_phy);
+	airoha_pcie_phy_init_clk_out(pcie_phy);
+	airoha_pcie_phy_init_csr_2l(pcie_phy);
+
+	usleep_range(100, 200);
+
+	airoha_pcie_phy_init_rx(pcie_phy);
+	/* phase 1, no ssc for K TXPLL */
+	airoha_pcie_phy_init_jcpll(pcie_phy);
+
+	usleep_range(500, 600);
+
+	/* TX PLL settings */
+	airoha_pcie_phy_txpll(pcie_phy);
+
+	usleep_range(200, 300);
+
+	/* SSC JCPLL setting */
+	airoha_pcie_phy_init_ssc_jcpll(pcie_phy);
+
+	usleep_range(100, 200);
+
+	/* Rx lan0 signal detect */
+	airoha_pcie_phy_set_rxlan0_signal_detect(pcie_phy);
+	/* Rx lan1 signal detect */
+	airoha_pcie_phy_set_rxlan1_signal_detect(pcie_phy);
+	/* RX FLOW */
+	airoha_pcie_phy_set_rxflow(pcie_phy);
+
+	usleep_range(100, 200);
+
+	airoha_pcie_phy_set_pr(pcie_phy);
+	/* TX FLOW */
+	airoha_pcie_phy_set_txflow(pcie_phy);
+
+	usleep_range(100, 200);
+	/* RX mode setting */
+	airoha_pcie_phy_set_rx_mode(pcie_phy);
+	/* Load K-Flow */
+	airoha_pcie_phy_load_kflow(pcie_phy);
+	airoha_phy_pma0_clear_bits(pcie_phy, REG_PCIE_PMA_SS_DA_XPON_PWDB0,
+				   PCIE_DA_XPON_CDR_PR_PWDB);
+	airoha_phy_pma1_clear_bits(pcie_phy, REG_PCIE_PMA_SS_DA_XPON_PWDB0,
+				   PCIE_DA_XPON_CDR_PR_PWDB);
+
+	usleep_range(100, 200);
+
+	airoha_phy_pma0_set_bits(pcie_phy, REG_PCIE_PMA_SS_DA_XPON_PWDB0,
+				 PCIE_DA_XPON_CDR_PR_PWDB);
+	airoha_phy_pma1_set_bits(pcie_phy, REG_PCIE_PMA_SS_DA_XPON_PWDB0,
+				 PCIE_DA_XPON_CDR_PR_PWDB);
+
+	usleep_range(100, 200);
+
+	return 0;
+}
+
+static int airoha_pcie_phy_exit(struct phy *phy)
+{
+	struct airoha_pcie_phy *pcie_phy = phy_get_drvdata(phy);
+
+	airoha_phy_pma0_clear_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				   PCIE_PMA_SW_RST);
+	airoha_phy_pma1_clear_bits(pcie_phy, REG_PCIE_PMA_SW_RESET,
+				   PCIE_PMA_SW_RST);
+	airoha_phy_csr_2l_clear_bits(pcie_phy, REG_CSR_2L_JCPLL_SSC,
+				     CSR_2L_PXP_JCPLL_SSC_PHASE_INI |
+				     CSR_2L_PXP_JCPLL_SSC_TRI_EN |
+				     CSR_2L_PXP_JCPLL_SSC_EN);
+
+	return 0;
+}
+
+static const struct phy_ops airoha_pcie_phy_ops = {
+	.init = airoha_pcie_phy_init,
+	.exit = airoha_pcie_phy_exit,
+	.owner = THIS_MODULE,
+};
+
+static int airoha_pcie_phy_probe(struct platform_device *pdev)
+{
+	struct airoha_pcie_phy *pcie_phy;
+	struct device *dev = &pdev->dev;
+	struct phy_provider *provider;
+
+	pcie_phy = devm_kzalloc(dev, sizeof(*pcie_phy), GFP_KERNEL);
+	if (!pcie_phy)
+		return -ENOMEM;
+
+	pcie_phy->csr_2l = devm_platform_ioremap_resource_byname(pdev, "csr-2l");
+	if (IS_ERR(pcie_phy->csr_2l))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->csr_2l),
+				     "Failed to map phy-csr-2l base\n");
+
+	pcie_phy->pma0 = devm_platform_ioremap_resource_byname(pdev, "pma0");
+	if (IS_ERR(pcie_phy->pma0))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->pma0),
+				     "Failed to map phy-pma0 base\n");
+
+	pcie_phy->pma1 = devm_platform_ioremap_resource_byname(pdev, "pma1");
+	if (IS_ERR(pcie_phy->pma1))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->pma1),
+				     "Failed to map phy-pma1 base\n");
+
+	pcie_phy->phy = devm_phy_create(dev, dev->of_node, &airoha_pcie_phy_ops);
+	if (IS_ERR(pcie_phy->phy))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->phy),
+				     "Failed to create PCIe phy\n");
+
+	pcie_phy->p0_xr_dtime =
+		devm_platform_ioremap_resource_byname(pdev, "p0-xr-dtime");
+	if (IS_ERR(pcie_phy->p0_xr_dtime))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->p0_xr_dtime),
+				     "Failed to map P0 Tx-Rx dtime base\n");
+
+	pcie_phy->p1_xr_dtime =
+		devm_platform_ioremap_resource_byname(pdev, "p1-xr-dtime");
+	if (IS_ERR(pcie_phy->p1_xr_dtime))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->p1_xr_dtime),
+				     "Failed to map P1 Tx-Rx dtime base\n");
+
+	pcie_phy->rx_aeq = devm_platform_ioremap_resource_byname(pdev, "rx-aeq");
+	if (IS_ERR(pcie_phy->rx_aeq))
+		return dev_err_probe(dev, PTR_ERR(pcie_phy->rx_aeq),
+				     "Failed to map Rx AEQ base\n");
+
+	pcie_phy->dev = dev;
+	phy_set_drvdata(pcie_phy->phy, pcie_phy);
+
+	provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(provider))
+		return dev_err_probe(dev, PTR_ERR(provider),
+				     "PCIe phy probe failed\n");
+
+	return 0;
+}
+
+static const struct of_device_id airoha_pcie_phy_of_match[] = {
+	{ .compatible = "airoha,en7581-pcie-phy" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, airoha_pcie_phy_of_match);
+
+static struct platform_driver airoha_pcie_phy_driver = {
+	.probe	= airoha_pcie_phy_probe,
+	.driver	= {
+		.name = "airoha-pcie-phy",
+		.of_match_table = airoha_pcie_phy_of_match,
+	},
+};
+module_platform_driver(airoha_pcie_phy_driver);
+
+MODULE_DESCRIPTION("Airoha PCIe PHY driver");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index bf6a075..f053b52 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -664,7 +664,7 @@ static struct phy *_of_phy_get(struct device_node *np, int index)
  *
  * Returns the phy driver, after getting a refcount to it; or
  * -ENODEV if there is no such phy. The caller is responsible for
- * calling phy_put() to release that count.
+ * calling of_phy_put() to release that count.
  */
 struct phy *of_phy_get(struct device_node *np, const char *con_id)
 {
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index 6c79672..5b36cc7 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -489,6 +489,243 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_gen3_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1),
 };
 
+static const struct qmp_phy_init_tbl ipq9574_gen3x1_pcie_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BIAS_EN_CLKBUFLR_EN, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BIAS_EN_CTRL_BY_PSM, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_SELECT, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BG_TRIM, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CMN_CONFIG, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP_EN, 0x42),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_RESETSM_CNTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_TIMER2, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x30),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x21),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DEC_START_MODE0, 0x68),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START2_MODE0, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP2_MODE0, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP1_MODE0, 0xd4),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CP_CTRL_MODE0, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_CCTRL_MODE0, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN1_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN0_MODE0, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE1_MODE0, 0x24),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORECLK_DIV, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_SELECT, 0x32),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYS_CLK_CTRL, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYSCLK_BUF_ENABLE, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYSCLK_EN_SEL, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BG_TIMER, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DEC_START_MODE1, 0x53),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START3_MODE1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START2_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP2_MODE1, 0x29),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP1_MODE1, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CP_CTRL_MODE1, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_CCTRL_MODE1, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN1_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN0_MODE1, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE2_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE1_MODE1, 0xb4),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORECLK_DIV_MODE1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER1, 0x7d),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_ADJ_PER1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_ADJ_PER2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE1_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE2_MODE0, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE1_MODE1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE2_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_EP_DIV_MODE0, 0x19),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_EP_DIV_MODE1, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_ENABLE1, 0x90),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x89),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_ENABLE1, 0x10),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BIAS_EN_CLKBUFLR_EN, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BIAS_EN_CTRL_BY_PSM, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_SELECT, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BG_TRIM, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CMN_CONFIG, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP_EN, 0x42),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_RESETSM_CNTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE_TIMER2, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x30),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x21),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DEC_START_MODE0, 0x68),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START2_MODE0, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP2_MODE0, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP1_MODE0, 0xd4),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CP_CTRL_MODE0, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_CCTRL_MODE0, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN1_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN0_MODE0, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE1_MODE0, 0x24),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORECLK_DIV, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_SELECT, 0x32),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYS_CLK_CTRL, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYSCLK_BUF_ENABLE, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SYSCLK_EN_SEL, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_BG_TIMER, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DEC_START_MODE1, 0x53),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START3_MODE1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START2_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP2_MODE1, 0x29),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_LOCK_CMP1_MODE1, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CP_CTRL_MODE1, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_PLL_CCTRL_MODE1, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN1_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_INTEGLOOP_GAIN0_MODE1, 0xa0),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE2_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_VCO_TUNE1_MODE1, 0xb4),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SVS_MODE_CLK_SEL, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORE_CLK_EN, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CORECLK_DIV_MODE1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER1, 0x7d),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_ADJ_PER1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_ADJ_PER2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE1_MODE0, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE2_MODE0, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE1_MODE1, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_STEP_SIZE2_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_EP_DIV_MODE0, 0x19),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_EP_DIV_MODE1, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_ENABLE1, 0x90),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_HSCLK_SEL, 0x89),
+	QMP_PHY_INIT_CFG(QSERDES_PLL_CLK_ENABLE1, 0x10),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_pcie_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_CNTRL, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_ENABLES, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_DEGLITCH_CNTRL, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL2, 0x61),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL3, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL4, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_DFE_EN_TIMER, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_FO_GAIN, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_SO_GAIN, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7f),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_PI_CONTROLS, 0x70),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL1, 0x73),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_LOW, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH2, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH3, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH4, 0xb1),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_LOW, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH2, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH3, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH4, 0xb1),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_LOW, 0xf0),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH2, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH3, 0xd3),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH4, 0x40),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_IDAC_TSETTLE_LOW, 0xc0),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_gen3x1_pcie_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_P2U3_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_P2U3_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_RX_DCC_CAL_CONFIG, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_RX_SIGDET_LVL, 0xaa),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_REFGEN_REQ_CONFIG1, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_G12S1_TXDEEMPH_M3P5DB, 0x10),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_gen3x1_pcie_pcs_misc_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_POWER_STATE_CONFIG2, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_EQ_CONFIG1, 0x14),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_EQ_CONFIG1, 0x10),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_EQ_CONFIG2, 0x0b),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_PRESET_P10_PRE, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_PRESET_P10_POST, 0x58),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_POWER_STATE_CONFIG4, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_CONFIG2, 0x52),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_INT_AUX_CLK_CONFIG1, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_MODE2_CONFIG2, 0x50),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_MODE2_CONFIG4, 0x1a),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_MODE2_CONFIG5, 0x06),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_OSC_DTCT_MODE2_CONFIG6, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_REFGEN_REQ_CONFIG1, 0x0d),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_G12S1_TXDEEMPH_M3P5DB, 0x10),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_P2U3_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_P2U3_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_RX_DCC_CAL_CONFIG, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V4_PCS_RX_SIGDET_LVL, 0xaa),
+};
+
+static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_pcs_misc_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_POWER_STATE_CONFIG2, 0x1d),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_H, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_L, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_EQ_CONFIG1, 0x14),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_EQ_CONFIG1, 0x10),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_EQ_CONFIG2, 0x0b),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_PRESET_P10_PRE, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_PRESET_P10_POST, 0x58),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_POWER_STATE_CONFIG4, 0x07),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG1, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG2, 0x52),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG4, 0x19),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_INT_AUX_CLK_CONFIG1, 0x00),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG2, 0x49),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG4, 0x2a),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG5, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG6, 0x03),
+	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1),
+};
+
 static const struct qmp_phy_init_tbl sdm845_qmp_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30),
@@ -2535,6 +2772,16 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v5 = {
 	.rx2		= 0x1800,
 };
 
+static const struct qmp_pcie_offsets qmp_pcie_offsets_ipq9574 = {
+	.serdes         = 0,
+	.pcs            = 0x1000,
+	.pcs_misc       = 0x1400,
+	.tx             = 0x0200,
+	.rx             = 0x0400,
+	.tx2            = 0x0600,
+	.rx2            = 0x0800,
+};
+
 static const struct qmp_pcie_offsets qmp_pcie_offsets_v5_20 = {
 	.serdes		= 0x1000,
 	.pcs		= 0x1200,
@@ -2647,6 +2894,62 @@ static const struct qmp_phy_cfg ipq6018_pciephy_cfg = {
 	.phy_status		= PHYSTATUS,
 };
 
+static const struct qmp_phy_cfg ipq9574_gen3x1_pciephy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_pcie_offsets_v4x1,
+
+	.tbls = {
+		.serdes		= ipq9574_gen3x1_pcie_serdes_tbl,
+		.serdes_num	= ARRAY_SIZE(ipq9574_gen3x1_pcie_serdes_tbl),
+		.tx		= ipq8074_pcie_gen3_tx_tbl,
+		.tx_num		= ARRAY_SIZE(ipq8074_pcie_gen3_tx_tbl),
+		.rx		= ipq9574_pcie_rx_tbl,
+		.rx_num		= ARRAY_SIZE(ipq9574_pcie_rx_tbl),
+		.pcs		= ipq9574_gen3x1_pcie_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(ipq9574_gen3x1_pcie_pcs_tbl),
+		.pcs_misc	= ipq9574_gen3x1_pcie_pcs_misc_tbl,
+		.pcs_misc_num	= ARRAY_SIZE(ipq9574_gen3x1_pcie_pcs_misc_tbl),
+	},
+	.reset_list		= ipq8074_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(ipq8074_pciephy_reset_l),
+	.vreg_list		= NULL,
+	.num_vregs		= 0,
+	.regs			= pciephy_v4_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS,
+	.pipe_clock_rate	= 250000000,
+};
+
+static const struct qmp_phy_cfg ipq9574_gen3x2_pciephy_cfg = {
+	.lanes			= 2,
+
+	.offsets		= &qmp_pcie_offsets_ipq9574,
+
+	.tbls = {
+		.serdes		= ipq9574_gen3x2_pcie_serdes_tbl,
+		.serdes_num	= ARRAY_SIZE(ipq9574_gen3x2_pcie_serdes_tbl),
+		.tx		= ipq8074_pcie_gen3_tx_tbl,
+		.tx_num		= ARRAY_SIZE(ipq8074_pcie_gen3_tx_tbl),
+		.rx		= ipq9574_pcie_rx_tbl,
+		.rx_num		= ARRAY_SIZE(ipq9574_pcie_rx_tbl),
+		.pcs		= ipq9574_gen3x2_pcie_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(ipq9574_gen3x2_pcie_pcs_tbl),
+		.pcs_misc	= ipq9574_gen3x2_pcie_pcs_misc_tbl,
+		.pcs_misc_num	= ARRAY_SIZE(ipq9574_gen3x2_pcie_pcs_misc_tbl),
+	},
+	.reset_list		= ipq8074_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(ipq8074_pciephy_reset_l),
+	.vreg_list		= NULL,
+	.num_vregs		= 0,
+	.regs			= pciephy_v5_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS,
+	.pipe_clock_rate	= 250000000,
+};
+
 static const struct qmp_phy_cfg sdm845_qmp_pciephy_cfg = {
 	.lanes			= 1,
 
@@ -3730,14 +4033,11 @@ static int phy_aux_clk_register(struct qmp_pcie *qmp, struct device_node *np)
 {
 	struct clk_fixed_rate *fixed = &qmp->aux_clk_fixed;
 	struct clk_init_data init = { };
-	int ret;
+	char name[64];
 
-	ret = of_property_read_string_index(np, "clock-output-names", 1, &init.name);
-	if (ret) {
-		dev_err(qmp->dev, "%pOFn: No clock-output-names index 1\n", np);
-		return ret;
-	}
+	snprintf(name, sizeof(name), "%s::phy_aux_clk", dev_name(qmp->dev));
 
+	init.name = name;
 	init.ops = &clk_fixed_rate_ops;
 
 	fixed->fixed_rate = qmp->cfg->aux_clock_rate;
@@ -4031,6 +4331,12 @@ static const struct of_device_id qmp_pcie_of_match_table[] = {
 		.compatible = "qcom,ipq8074-qmp-pcie-phy",
 		.data = &ipq8074_pciephy_cfg,
 	}, {
+		.compatible = "qcom,ipq9574-qmp-gen3x1-pcie-phy",
+		.data = &ipq9574_gen3x1_pciephy_cfg,
+	}, {
+		.compatible = "qcom,ipq9574-qmp-gen3x2-pcie-phy",
+		.data = &ipq9574_gen3x2_pciephy_cfg,
+	}, {
 		.compatible = "qcom,msm8998-qmp-pcie-phy",
 		.data = &msm8998_pciephy_cfg,
 	}, {
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5.h
index a469ae2..fa15a03 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5.h
@@ -11,8 +11,22 @@
 #define QPHY_V5_PCS_PCIE_POWER_STATE_CONFIG2		0x0c
 #define QPHY_V5_PCS_PCIE_POWER_STATE_CONFIG4		0x14
 #define QPHY_V5_PCS_PCIE_ENDPOINT_REFCLK_DRIVE		0x20
+#define QPHY_V5_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_L	0x44
+#define QPHY_V5_PCS_PCIE_L1P1_WAKEUP_DLY_TIME_AUXCLK_H	0x48
+#define QPHY_V5_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_L	0x4c
+#define QPHY_V5_PCS_PCIE_L1P2_WAKEUP_DLY_TIME_AUXCLK_H	0x50
 #define QPHY_V5_PCS_PCIE_INT_AUX_CLK_CONFIG1		0x54
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG1		0x5c
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG2		0x60
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_CONFIG4		0x68
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG2		0x7c
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG4		0x84
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG5		0x88
+#define QPHY_V5_PCS_PCIE_OSC_DTCT_MODE2_CONFIG6		0x8c
 #define QPHY_V5_PCS_PCIE_OSC_DTCT_ACTIONS		0x94
+#define QPHY_V5_PCS_PCIE_EQ_CONFIG1			0xa4
 #define QPHY_V5_PCS_PCIE_EQ_CONFIG2			0xa8
+#define QPHY_V5_PCS_PCIE_PRESET_P10_PRE			0xc0
+#define QPHY_V5_PCS_PCIE_PRESET_P10_POST		0xe4
 
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-pll.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-pll.h
index ad326e3..231e593 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-pll.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-pll.h
@@ -8,6 +8,9 @@
 
 /* QMP V2 PHY for PCIE gen3 ports - QSERDES PLL registers */
 #define QSERDES_PLL_BG_TIMER				0x00c
+#define QSERDES_PLL_SSC_EN_CENTER			0x010
+#define QSERDES_PLL_SSC_ADJ_PER1			0x014
+#define QSERDES_PLL_SSC_ADJ_PER2			0x018
 #define QSERDES_PLL_SSC_PER1				0x01c
 #define QSERDES_PLL_SSC_PER2				0x020
 #define QSERDES_PLL_SSC_STEP_SIZE1_MODE0		0x024
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index c174463..9b0eb87 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -2253,6 +2253,9 @@ static const struct of_device_id qmp_usb_of_match_table[] = {
 		.compatible = "qcom,sa8775p-qmp-usb3-uni-phy",
 		.data = &sa8775p_usb3_uniphy_cfg,
 	}, {
+		.compatible = "qcom,sc8180x-qmp-usb3-uni-phy",
+		.data = &sm8150_usb3_uniphy_cfg,
+	}, {
 		.compatible = "qcom,sc8280xp-qmp-usb3-uni-phy",
 		.data = &sc8280xp_usb3_uniphy_cfg,
 	}, {
diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index 08b0f43..4902633 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -86,7 +86,9 @@
 config PHY_ROCKCHIP_SAMSUNG_HDPTX
 	tristate "Rockchip Samsung HDMI/eDP Combo PHY driver"
 	depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF
+	depends on HAS_IOMEM
 	select GENERIC_PHY
+	select MFD_SYSCON
 	select RATIONAL
 	help
 	  Enable this to support the Rockchip HDMI/eDP Combo PHY
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 04171ee..df52b78 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -8,6 +8,7 @@
  * Author: Vivek Gautam <gautam.vivek@samsung.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -30,18 +31,16 @@
 #define EXYNOS5_FSEL_19MHZ2		0x3
 #define EXYNOS5_FSEL_20MHZ		0x4
 #define EXYNOS5_FSEL_24MHZ		0x5
-#define EXYNOS5_FSEL_26MHZ		0x82
+#define EXYNOS5_FSEL_26MHZ		0x6
 #define EXYNOS5_FSEL_50MHZ		0x7
 
 /* Exynos5: USB 3.0 DRD PHY registers */
 #define EXYNOS5_DRD_LINKSYSTEM			0x04
-
+#define LINKSYSTEM_XHCI_VERSION_CONTROL		BIT(27)
 #define LINKSYSTEM_FLADJ_MASK			(0x3f << 1)
 #define LINKSYSTEM_FLADJ(_x)			((_x) << 1)
-#define LINKSYSTEM_XHCI_VERSION_CONTROL		BIT(27)
 
 #define EXYNOS5_DRD_PHYUTMI			0x08
-
 #define PHYUTMI_OTGDISABLE			BIT(6)
 #define PHYUTMI_FORCESUSPEND			BIT(1)
 #define PHYUTMI_FORCESLEEP			BIT(0)
@@ -49,40 +48,31 @@
 #define EXYNOS5_DRD_PHYPIPE			0x0c
 
 #define EXYNOS5_DRD_PHYCLKRST			0x10
-
 #define PHYCLKRST_EN_UTMISUSPEND		BIT(31)
-
 #define PHYCLKRST_SSC_REFCLKSEL_MASK		(0xff << 23)
 #define PHYCLKRST_SSC_REFCLKSEL(_x)		((_x) << 23)
-
 #define PHYCLKRST_SSC_RANGE_MASK		(0x03 << 21)
 #define PHYCLKRST_SSC_RANGE(_x)			((_x) << 21)
-
 #define PHYCLKRST_SSC_EN			BIT(20)
 #define PHYCLKRST_REF_SSP_EN			BIT(19)
 #define PHYCLKRST_REF_CLKDIV2			BIT(18)
-
 #define PHYCLKRST_MPLL_MULTIPLIER_MASK		(0x7f << 11)
 #define PHYCLKRST_MPLL_MULTIPLIER_100MHZ_REF	(0x19 << 11)
 #define PHYCLKRST_MPLL_MULTIPLIER_50M_REF	(0x32 << 11)
 #define PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF	(0x68 << 11)
 #define PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF	(0x7d << 11)
 #define PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF	(0x02 << 11)
-
-#define PHYCLKRST_FSEL_UTMI_MASK		(0x7 << 5)
 #define PHYCLKRST_FSEL_PIPE_MASK		(0x7 << 8)
+#define PHYCLKRST_FSEL_UTMI_MASK		(0x7 << 5)
 #define PHYCLKRST_FSEL(_x)			((_x) << 5)
 #define PHYCLKRST_FSEL_PAD_100MHZ		(0x27 << 5)
 #define PHYCLKRST_FSEL_PAD_24MHZ		(0x2a << 5)
 #define PHYCLKRST_FSEL_PAD_20MHZ		(0x31 << 5)
 #define PHYCLKRST_FSEL_PAD_19_2MHZ		(0x38 << 5)
-
 #define PHYCLKRST_RETENABLEN			BIT(4)
-
 #define PHYCLKRST_REFCLKSEL_MASK		(0x03 << 2)
 #define PHYCLKRST_REFCLKSEL_PAD_REFCLK		(0x2 << 2)
 #define PHYCLKRST_REFCLKSEL_EXT_REFCLK		(0x3 << 2)
-
 #define PHYCLKRST_PORTRESET			BIT(1)
 #define PHYCLKRST_COMMONONN			BIT(0)
 
@@ -100,30 +90,27 @@
 #define PHYREG1_CR_ACK				BIT(0)
 
 #define EXYNOS5_DRD_PHYPARAM0			0x1c
-
 #define PHYPARAM0_REF_USE_PAD			BIT(31)
 #define PHYPARAM0_REF_LOSLEVEL_MASK		(0x1f << 26)
 #define PHYPARAM0_REF_LOSLEVEL			(0x9 << 26)
 
 #define EXYNOS5_DRD_PHYPARAM1			0x20
-
 #define PHYPARAM1_PCS_TXDEEMPH_MASK		(0x1f << 0)
 #define PHYPARAM1_PCS_TXDEEMPH			(0x1c)
 
 #define EXYNOS5_DRD_PHYTERM			0x24
 
 #define EXYNOS5_DRD_PHYTEST			0x28
-
 #define PHYTEST_POWERDOWN_SSP			BIT(3)
 #define PHYTEST_POWERDOWN_HSP			BIT(2)
 
 #define EXYNOS5_DRD_PHYADP			0x2c
 
 #define EXYNOS5_DRD_PHYUTMICLKSEL		0x30
-
 #define PHYUTMICLKSEL_UTMI_CLKSEL		BIT(2)
 
 #define EXYNOS5_DRD_PHYRESUME			0x34
+
 #define EXYNOS5_DRD_LINKPORT			0x44
 
 /* USB 3.0 DRD PHY SS Function Control Reg; accessed by CR_PORT */
@@ -147,35 +134,215 @@
 
 /* Exynos850: USB DRD PHY registers */
 #define EXYNOS850_DRD_LINKCTRL			0x04
-#define LINKCTRL_BUS_FILTER_BYPASS(_x)		((_x) << 4)
+#define LINKCTRL_FORCE_RXELECIDLE		BIT(18)
+#define LINKCTRL_FORCE_PHYSTATUS		BIT(17)
+#define LINKCTRL_FORCE_PIPE_EN			BIT(16)
 #define LINKCTRL_FORCE_QACT			BIT(8)
+#define LINKCTRL_BUS_FILTER_BYPASS(_x)		((_x) << 4)
+
+#define EXYNOS850_DRD_LINKPORT			0x08
+#define LINKPORT_HOST_NUM_U3			GENMASK(19, 16)
+#define LINKPORT_HOST_NUM_U2			GENMASK(15, 12)
 
 #define EXYNOS850_DRD_CLKRST			0x20
-#define CLKRST_LINK_SW_RST			BIT(0)
-#define CLKRST_PORT_RST				BIT(1)
+/*
+ * On versions without SS ports (like E850), bit 3 is for the 2.0 phy (HS),
+ * while on versions with (like gs101), bits 2 and 3 are for the 3.0 phy (SS)
+ * and bits 12 & 13 for the 2.0 phy.
+ */
+#define CLKRST_PHY20_SW_POR			BIT(13)
+#define CLKRST_PHY20_SW_POR_SEL			BIT(12)
+#define CLKRST_LINK_PCLK_SEL			BIT(7)
 #define CLKRST_PHY_SW_RST			BIT(3)
+#define CLKRST_PHY_RESET_SEL			BIT(2)
+#define CLKRST_PORT_RST				BIT(1)
+#define CLKRST_LINK_SW_RST			BIT(0)
+
+#define EXYNOS850_DRD_SSPPLLCTL			0x30
+#define SSPPLLCTL_FSEL				GENMASK(2, 0)
 
 #define EXYNOS850_DRD_UTMI			0x50
-#define UTMI_FORCE_SLEEP			BIT(0)
-#define UTMI_FORCE_SUSPEND			BIT(1)
-#define UTMI_DM_PULLDOWN			BIT(2)
-#define UTMI_DP_PULLDOWN			BIT(3)
-#define UTMI_FORCE_BVALID			BIT(4)
 #define UTMI_FORCE_VBUSVALID			BIT(5)
+#define UTMI_FORCE_BVALID			BIT(4)
+#define UTMI_DP_PULLDOWN			BIT(3)
+#define UTMI_DM_PULLDOWN			BIT(2)
+#define UTMI_FORCE_SUSPEND			BIT(1)
+#define UTMI_FORCE_SLEEP			BIT(0)
 
 #define EXYNOS850_DRD_HSP			0x54
-#define HSP_COMMONONN				BIT(8)
-#define HSP_EN_UTMISUSPEND			BIT(9)
-#define HSP_VBUSVLDEXT				BIT(12)
-#define HSP_VBUSVLDEXTSEL			BIT(13)
 #define HSP_FSV_OUT_EN				BIT(24)
+#define HSP_VBUSVLDEXTSEL			BIT(13)
+#define HSP_VBUSVLDEXT				BIT(12)
+#define HSP_EN_UTMISUSPEND			BIT(9)
+#define HSP_COMMONONN				BIT(8)
+
+#define EXYNOS850_DRD_HSPPARACON		0x58
+#define HSPPARACON_TXVREF			GENMASK(31, 28)
+#define HSPPARACON_TXRISE			GENMASK(25, 24)
+#define HSPPARACON_TXRES			GENMASK(22, 21)
+#define HSPPARACON_TXPREEMPPULSE		BIT(20)
+#define HSPPARACON_TXPREEMPAMP			GENMASK(19, 18)
+#define HSPPARACON_TXHSXV			GENMASK(17, 16)
+#define HSPPARACON_TXFSLS			GENMASK(15, 12)
+#define HSPPARACON_SQRX				GENMASK(10, 8)
+#define HSPPARACON_OTG				GENMASK(6, 4)
+#define HSPPARACON_COMPDIS			GENMASK(2, 0)
 
 #define EXYNOS850_DRD_HSP_TEST			0x5c
 #define HSP_TEST_SIDDQ				BIT(24)
 
+/* Exynos9 - GS101 */
+#define EXYNOS850_DRD_SECPMACTL			0x48
+#define SECPMACTL_PMA_ROPLL_REF_CLK_SEL		GENMASK(13, 12)
+#define SECPMACTL_PMA_LCPLL_REF_CLK_SEL		GENMASK(11, 10)
+#define SECPMACTL_PMA_REF_FREQ_SEL		GENMASK(9, 8)
+#define SECPMACTL_PMA_LOW_PWR			BIT(4)
+#define SECPMACTL_PMA_TRSV_SW_RST		BIT(3)
+#define SECPMACTL_PMA_CMN_SW_RST		BIT(2)
+#define SECPMACTL_PMA_INIT_SW_RST		BIT(1)
+#define SECPMACTL_PMA_APB_SW_RST		BIT(0)
+
+/* PMA registers */
+#define EXYNOS9_PMA_USBDP_CMN_REG0008		0x0020
+#define CMN_REG0008_OVRD_AUX_EN			BIT(3)
+#define CMN_REG0008_AUX_EN			BIT(2)
+
+#define EXYNOS9_PMA_USBDP_CMN_REG00B8		0x02e0
+#define CMN_REG00B8_LANE_MUX_SEL_DP		GENMASK(3, 0)
+
+#define EXYNOS9_PMA_USBDP_CMN_REG01C0		0x0700
+#define CMN_REG01C0_ANA_LCPLL_LOCK_DONE		BIT(7)
+#define CMN_REG01C0_ANA_LCPLL_AFC_DONE		BIT(6)
+
+/* these have similar register layout, for lanes 0 and 2 */
+#define EXYNOS9_PMA_USBDP_TRSV_REG03C3			0x0f0c
+#define EXYNOS9_PMA_USBDP_TRSV_REG07C3			0x1f0c
+#define TRSV_REG03C3_LN0_MON_RX_CDR_AFC_DONE		BIT(3)
+#define TRSV_REG03C3_LN0_MON_RX_CDR_CAL_DONE		BIT(2)
+#define TRSV_REG03C3_LN0_MON_RX_CDR_FLD_PLL_MODE_DONE	BIT(1)
+#define TRSV_REG03C3_LN0_MON_RX_CDR_LOCK_DONE		BIT(0)
+
+/* TRSV_REG0413 and TRSV_REG0813 have similar register layout */
+#define EXYNOS9_PMA_USBDP_TRSV_REG0413		0x104c
+#define TRSV_REG0413_OVRD_LN1_TX_RXD_COMP_EN	BIT(7)
+#define TRSV_REG0413_OVRD_LN1_TX_RXD_EN		BIT(5)
+
+#define EXYNOS9_PMA_USBDP_TRSV_REG0813		0x204c
+#define TRSV_REG0813_OVRD_LN3_TX_RXD_COMP_EN	BIT(7)
+#define TRSV_REG0813_OVRD_LN3_TX_RXD_EN		BIT(5)
+
+/* PCS registers */
+#define EXYNOS9_PCS_NS_VEC_PS1_N1		0x010c
+#define EXYNOS9_PCS_NS_VEC_PS2_N0		0x0110
+#define EXYNOS9_PCS_NS_VEC_PS3_N0		0x0118
+#define NS_VEC_NS_REQ				GENMASK(31, 24)
+#define NS_VEC_ENABLE_TIMER			BIT(22)
+#define NS_VEC_SEL_TIMEOUT			GENMASK(21, 20)
+#define NS_VEC_INV_MASK				GENMASK(19, 16)
+#define NS_VEC_COND_MASK			GENMASK(11, 8)
+#define NS_VEC_EXP_COND				GENMASK(3, 0)
+
+#define EXYNOS9_PCS_OUT_VEC_2			0x014c
+#define EXYNOS9_PCS_OUT_VEC_3			0x0150
+#define PCS_OUT_VEC_B9_DYNAMIC			BIT(19)
+#define PCS_OUT_VEC_B9_SEL_OUT			BIT(18)
+#define PCS_OUT_VEC_B8_DYNAMIC			BIT(17)
+#define PCS_OUT_VEC_B8_SEL_OUT			BIT(16)
+#define PCS_OUT_VEC_B7_DYNAMIC			BIT(15)
+#define PCS_OUT_VEC_B7_SEL_OUT			BIT(14)
+#define PCS_OUT_VEC_B6_DYNAMIC			BIT(13)
+#define PCS_OUT_VEC_B6_SEL_OUT			BIT(12)
+#define PCS_OUT_VEC_B5_DYNAMIC			BIT(11)
+#define PCS_OUT_VEC_B5_SEL_OUT			BIT(10)
+#define PCS_OUT_VEC_B4_DYNAMIC			BIT(9)
+#define PCS_OUT_VEC_B4_SEL_OUT			BIT(8)
+#define PCS_OUT_VEC_B3_DYNAMIC			BIT(7)
+#define PCS_OUT_VEC_B3_SEL_OUT			BIT(6)
+#define PCS_OUT_VEC_B2_DYNAMIC			BIT(5)
+#define PCS_OUT_VEC_B2_SEL_OUT			BIT(4)
+#define PCS_OUT_VEC_B1_DYNAMIC			BIT(3)
+#define PCS_OUT_VEC_B1_SEL_OUT			BIT(2)
+#define PCS_OUT_VEC_B0_DYNAMIC			BIT(1)
+#define PCS_OUT_VEC_B0_SEL_OUT			BIT(0)
+
+#define EXYNOS9_PCS_TIMEOUT_0			0x0170
+
+#define EXYNOS9_PCS_TIMEOUT_3			0x017c
+
+#define EXYNOS9_PCS_EBUF_PARAM			0x0304
+#define EBUF_PARAM_SKP_REMOVE_TH_EMPTY_MODE	GENMASK(29, 24)
+
+#define EXYNOS9_PCS_BACK_END_MODE_VEC		0x030c
+#define BACK_END_MODE_VEC_FORCE_EBUF_EMPTY_MODE	BIT(1)
+#define BACK_END_MODE_VEC_DISABLE_DATA_MASK	BIT(0)
+
+#define EXYNOS9_PCS_RX_CONTROL			0x03f0
+#define RX_CONTROL_EN_BLOCK_ALIGNER_TYPE_B	BIT(22)
+
+#define EXYNOS9_PCS_RX_CONTROL_DEBUG		0x03f4
+#define RX_CONTROL_DEBUG_EN_TS_CHECK		BIT(5)
+#define RX_CONTROL_DEBUG_NUM_COM_FOUND		GENMASK(3, 0)
+
+#define EXYNOS9_PCS_LOCAL_COEF			0x040c
+#define LOCAL_COEF_PMA_CENTER_COEF		GENMASK(21, 16)
+#define LOCAL_COEF_LF				GENMASK(13, 8)
+#define LOCAL_COEF_FS				GENMASK(5, 0)
+
+#define EXYNOS9_PCS_HS_TX_COEF_MAP_0		0x0410
+#define HS_TX_COEF_MAP_0_SSTX_DEEMP		GENMASK(17, 12)
+#define HS_TX_COEF_MAP_0_SSTX_LEVEL		GENMASK(11, 6)
+#define HS_TX_COEF_MAP_0_SSTX_PRE_SHOOT		GENMASK(5, 0)
+
+
 #define KHZ	1000
 #define MHZ	(KHZ * KHZ)
 
+#define PHY_TUNING_ENTRY_PHY(o, m, v) {	\
+		.off = (o),		\
+		.mask = (m),		\
+		.val = (v),		\
+		.region = PTR_PHY	\
+	}
+
+#define PHY_TUNING_ENTRY_PCS(o, m, v) {	\
+		.off = (o),		\
+		.mask = (m),		\
+		.val = (v),		\
+		.region = PTR_PCS	\
+	}
+
+#define PHY_TUNING_ENTRY_PMA(o, m, v) {	\
+		.off = (o),		\
+		.mask = (m),		\
+		.val = (v),		\
+		.region = PTR_PMA,	\
+	}
+
+#define PHY_TUNING_ENTRY_LAST { .region = PTR_INVALID }
+
+#define for_each_phy_tune(tune) \
+	for (; (tune)->region != PTR_INVALID; ++(tune))
+
+struct exynos5_usbdrd_phy_tuning {
+	u32 off;
+	u32 mask;
+	u32 val;
+	char region;
+#define PTR_INVALID	0
+#define PTR_PHY		1
+#define PTR_PCS		2
+#define PTR_PMA		3
+};
+
+enum exynos5_usbdrd_phy_tuning_state {
+	PTS_UTMI_POSTINIT,
+	PTS_PIPE3_PREINIT,
+	PTS_PIPE3_INIT,
+	PTS_PIPE3_POSTINIT,
+	PTS_PIPE3_POSTLOCK,
+	PTS_MAX,
+};
+
 enum exynos5_usbdrd_phy_id {
 	EXYNOS5_DRDPHY_UTMI,
 	EXYNOS5_DRDPHY_PIPE3,
@@ -187,44 +354,48 @@ struct exynos5_usbdrd_phy;
 
 struct exynos5_usbdrd_phy_config {
 	u32 id;
-	void (*phy_isol)(struct phy_usb_instance *inst, u32 on);
+	void (*phy_isol)(struct phy_usb_instance *inst, bool isolate);
 	void (*phy_init)(struct exynos5_usbdrd_phy *phy_drd);
 	unsigned int (*set_refclk)(struct phy_usb_instance *inst);
 };
 
 struct exynos5_usbdrd_phy_drvdata {
 	const struct exynos5_usbdrd_phy_config *phy_cfg;
+	const struct exynos5_usbdrd_phy_tuning **phy_tunes;
 	const struct phy_ops *phy_ops;
+	const char * const *clk_names;
+	int n_clks;
+	const char * const *core_clk_names;
+	int n_core_clks;
+	const char * const *regulator_names;
+	int n_regulators;
 	u32 pmu_offset_usbdrd0_phy;
+	u32 pmu_offset_usbdrd0_phy_ss;
 	u32 pmu_offset_usbdrd1_phy;
-	bool has_common_clk_gate;
 };
 
 /**
  * struct exynos5_usbdrd_phy - driver data for USB 3.0 PHY
  * @dev: pointer to device instance of this platform device
  * @reg_phy: usb phy controller register memory base
- * @clk: phy clock for register access
- * @pipeclk: clock for pipe3 phy
- * @utmiclk: clock for utmi+ phy
- * @itpclk: clock for ITP generation
+ * @reg_pcs: usb phy physical coding sublayer register memory base
+ * @reg_pma: usb phy physical media attachment register memory base
+ * @clks: clocks for register access
+ * @core_clks: core clocks for phy (ref, pipe3, utmi+, ITP, etc. as required)
  * @drv_data: pointer to SoC level driver data structure
  * @phys: array for 'EXYNOS5_DRDPHYS_NUM' number of PHY
  *	    instances each with its 'phy' and 'phy_cfg'.
  * @extrefclk: frequency select settings when using 'separate
  *	       reference clocks' for SS and HS operations
- * @ref_clk: reference clock to PHY block from which PHY's
- *	     operational clocks are derived
- * @vbus: VBUS regulator for phy
- * @vbus_boost: Boost regulator for VBUS present on few Exynos boards
+ * @regulators: regulators for phy
  */
 struct exynos5_usbdrd_phy {
 	struct device *dev;
 	void __iomem *reg_phy;
-	struct clk *clk;
-	struct clk *pipeclk;
-	struct clk *utmiclk;
-	struct clk *itpclk;
+	void __iomem *reg_pcs;
+	void __iomem *reg_pma;
+	struct clk_bulk_data *clks;
+	struct clk_bulk_data *core_clks;
 	const struct exynos5_usbdrd_phy_drvdata *drv_data;
 	struct phy_usb_instance {
 		struct phy *phy;
@@ -234,9 +405,7 @@ struct exynos5_usbdrd_phy {
 		const struct exynos5_usbdrd_phy_config *phy_cfg;
 	} phys[EXYNOS5_DRDPHYS_NUM];
 	u32 extrefclk;
-	struct clk *ref_clk;
-	struct regulator *vbus;
-	struct regulator *vbus_boost;
+	struct regulator_bulk_data *regulators;
 };
 
 static inline
@@ -287,14 +456,14 @@ static unsigned int exynos5_rate_to_clk(unsigned long rate, u32 *reg)
 }
 
 static void exynos5_usbdrd_phy_isol(struct phy_usb_instance *inst,
-						unsigned int on)
+				    bool isolate)
 {
 	unsigned int val;
 
 	if (!inst->reg_pmu)
 		return;
 
-	val = on ? 0 : EXYNOS4_PHY_ENABLE;
+	val = isolate ? 0 : EXYNOS4_PHY_ENABLE;
 
 	regmap_update_bits(inst->reg_pmu, inst->pmu_offset,
 			   EXYNOS4_PHY_ENABLE, val);
@@ -371,6 +540,45 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
 	return reg;
 }
 
+static void
+exynos5_usbdrd_apply_phy_tunes(struct exynos5_usbdrd_phy *phy_drd,
+			       enum exynos5_usbdrd_phy_tuning_state state)
+{
+	const struct exynos5_usbdrd_phy_tuning *tune;
+
+	tune = phy_drd->drv_data->phy_tunes[state];
+	if (!tune)
+		return;
+
+	for_each_phy_tune(tune) {
+		void __iomem *reg_base;
+		u32 reg = 0;
+
+		switch (tune->region) {
+		case PTR_PHY:
+			reg_base = phy_drd->reg_phy;
+			break;
+		case PTR_PCS:
+			reg_base = phy_drd->reg_pcs;
+			break;
+		case PTR_PMA:
+			reg_base = phy_drd->reg_pma;
+			break;
+		default:
+			dev_warn_once(phy_drd->dev,
+				      "unknown phy region %d\n", tune->region);
+			continue;
+		}
+
+		if (~tune->mask) {
+			reg = readl(reg_base + tune->off);
+			reg &= ~tune->mask;
+		}
+		reg |= tune->val;
+		writel(reg, reg_base + tune->off);
+	}
+}
+
 static void exynos5_usbdrd_pipe3_init(struct exynos5_usbdrd_phy *phy_drd)
 {
 	u32 reg;
@@ -386,6 +594,129 @@ static void exynos5_usbdrd_pipe3_init(struct exynos5_usbdrd_phy *phy_drd)
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYTEST);
 }
 
+static void
+exynos5_usbdrd_usbdp_g2_v4_ctrl_pma_ready(struct exynos5_usbdrd_phy *phy_drd)
+{
+	void __iomem *regs_base = phy_drd->reg_phy;
+	u32 reg;
+
+	/* link pipe_clock selection to pclk of PMA */
+	reg = readl(regs_base + EXYNOS850_DRD_CLKRST);
+	reg |= CLKRST_LINK_PCLK_SEL;
+	writel(reg, regs_base + EXYNOS850_DRD_CLKRST);
+
+	reg = readl(regs_base + EXYNOS850_DRD_SECPMACTL);
+	reg &= ~SECPMACTL_PMA_REF_FREQ_SEL;
+	reg |= FIELD_PREP_CONST(SECPMACTL_PMA_REF_FREQ_SEL, 1);
+	/* SFR reset */
+	reg |= (SECPMACTL_PMA_LOW_PWR | SECPMACTL_PMA_APB_SW_RST);
+	reg &= ~(SECPMACTL_PMA_ROPLL_REF_CLK_SEL |
+		 SECPMACTL_PMA_LCPLL_REF_CLK_SEL);
+	/* PMA power off */
+	reg |= (SECPMACTL_PMA_TRSV_SW_RST | SECPMACTL_PMA_CMN_SW_RST |
+		SECPMACTL_PMA_INIT_SW_RST);
+	writel(reg, regs_base + EXYNOS850_DRD_SECPMACTL);
+
+	udelay(1);
+
+	reg = readl(regs_base + EXYNOS850_DRD_SECPMACTL);
+	reg &= ~SECPMACTL_PMA_LOW_PWR;
+	writel(reg, regs_base + EXYNOS850_DRD_SECPMACTL);
+
+	udelay(1);
+
+	/* release override */
+	reg = readl(regs_base + EXYNOS850_DRD_LINKCTRL);
+	reg &= ~LINKCTRL_FORCE_PIPE_EN;
+	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
+
+	udelay(1);
+
+	/* APB enable */
+	reg = readl(regs_base + EXYNOS850_DRD_SECPMACTL);
+	reg &= ~SECPMACTL_PMA_APB_SW_RST;
+	writel(reg, regs_base + EXYNOS850_DRD_SECPMACTL);
+}
+
+static void
+exynos5_usbdrd_usbdp_g2_v4_pma_lane_mux_sel(struct exynos5_usbdrd_phy *phy_drd)
+{
+	void __iomem *regs_base = phy_drd->reg_pma;
+	u32 reg;
+
+	/* lane configuration: USB on all lanes */
+	reg = readl(regs_base + EXYNOS9_PMA_USBDP_CMN_REG00B8);
+	reg &= ~CMN_REG00B8_LANE_MUX_SEL_DP;
+	writel(reg, regs_base + EXYNOS9_PMA_USBDP_CMN_REG00B8);
+
+	/*
+	 * FIXME: below code supports one connector orientation only. It needs
+	 * updating once we can receive connector events.
+	 */
+	/* override of TX receiver detector and comparator: lane 1 */
+	reg = readl(regs_base + EXYNOS9_PMA_USBDP_TRSV_REG0413);
+	reg &= ~TRSV_REG0413_OVRD_LN1_TX_RXD_COMP_EN;
+	reg &= ~TRSV_REG0413_OVRD_LN1_TX_RXD_EN;
+	writel(reg, regs_base + EXYNOS9_PMA_USBDP_TRSV_REG0413);
+
+	/* lane 3 */
+	reg = readl(regs_base + EXYNOS9_PMA_USBDP_TRSV_REG0813);
+	reg |= TRSV_REG0813_OVRD_LN3_TX_RXD_COMP_EN;
+	reg |= TRSV_REG0813_OVRD_LN3_TX_RXD_EN;
+	writel(reg, regs_base + EXYNOS9_PMA_USBDP_TRSV_REG0813);
+}
+
+static int
+exynos5_usbdrd_usbdp_g2_v4_pma_check_pll_lock(struct exynos5_usbdrd_phy *phy_drd)
+{
+	static const unsigned int timeout_us = 40000;
+	static const unsigned int sleep_us = 40;
+	static const u32 locked = (CMN_REG01C0_ANA_LCPLL_LOCK_DONE |
+				   CMN_REG01C0_ANA_LCPLL_AFC_DONE);
+	u32 reg;
+	int err;
+
+	err = readl_poll_timeout(
+			phy_drd->reg_pma + EXYNOS9_PMA_USBDP_CMN_REG01C0,
+			reg, (reg & locked) == locked, sleep_us, timeout_us);
+	if (err)
+		dev_err(phy_drd->dev,
+			"timed out waiting for PLL lock: %#.8x\n", reg);
+
+	return err;
+}
+
+static void
+exynos5_usbdrd_usbdp_g2_v4_pma_check_cdr_lock(struct exynos5_usbdrd_phy *phy_drd)
+{
+	static const unsigned int timeout_us = 40000;
+	static const unsigned int sleep_us = 40;
+	static const u32 locked =
+		(TRSV_REG03C3_LN0_MON_RX_CDR_AFC_DONE
+		 | TRSV_REG03C3_LN0_MON_RX_CDR_CAL_DONE
+		 | TRSV_REG03C3_LN0_MON_RX_CDR_FLD_PLL_MODE_DONE
+		 | TRSV_REG03C3_LN0_MON_RX_CDR_LOCK_DONE);
+	u32 reg;
+	int err;
+
+	err = readl_poll_timeout(
+			phy_drd->reg_pma + EXYNOS9_PMA_USBDP_TRSV_REG03C3,
+			reg, (reg & locked) == locked, sleep_us, timeout_us);
+	if (!err)
+		return;
+
+	dev_err(phy_drd->dev,
+		"timed out waiting for CDR lock (l0): %#.8x, retrying\n", reg);
+
+	/* based on cable orientation, this might be on the other phy port */
+	err = readl_poll_timeout(
+			phy_drd->reg_pma + EXYNOS9_PMA_USBDP_TRSV_REG07C3,
+			reg, (reg & locked) == locked, sleep_us, timeout_us);
+	if (err)
+		dev_err(phy_drd->dev,
+			"timed out waiting for CDR lock (l2): %#.8x\n", reg);
+}
+
 static void exynos5_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 {
 	u32 reg;
@@ -417,7 +748,7 @@ static int exynos5_usbdrd_phy_init(struct phy *phy)
 	struct phy_usb_instance *inst = phy_get_drvdata(phy);
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 
-	ret = clk_prepare_enable(phy_drd->clk);
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
 	if (ret)
 		return ret;
 
@@ -462,12 +793,12 @@ static int exynos5_usbdrd_phy_init(struct phy *phy)
 
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
 
-	udelay(10);
+	fsleep(10);
 
 	reg &= ~PHYCLKRST_PORTRESET;
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
 
-	clk_disable_unprepare(phy_drd->clk);
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
 
 	return 0;
 }
@@ -479,7 +810,7 @@ static int exynos5_usbdrd_phy_exit(struct phy *phy)
 	struct phy_usb_instance *inst = phy_get_drvdata(phy);
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 
-	ret = clk_prepare_enable(phy_drd->clk);
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
 	if (ret)
 		return ret;
 
@@ -501,7 +832,7 @@ static int exynos5_usbdrd_phy_exit(struct phy *phy)
 		PHYTEST_POWERDOWN_HSP;
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYTEST);
 
-	clk_disable_unprepare(phy_drd->clk);
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
 
 	return 0;
 }
@@ -514,47 +845,27 @@ static int exynos5_usbdrd_phy_power_on(struct phy *phy)
 
 	dev_dbg(phy_drd->dev, "Request to power_on usbdrd_phy phy\n");
 
-	clk_prepare_enable(phy_drd->ref_clk);
-	if (!phy_drd->drv_data->has_common_clk_gate) {
-		clk_prepare_enable(phy_drd->pipeclk);
-		clk_prepare_enable(phy_drd->utmiclk);
-		clk_prepare_enable(phy_drd->itpclk);
-	}
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_core_clks,
+				      phy_drd->core_clks);
+	if (ret)
+		return ret;
 
 	/* Enable VBUS supply */
-	if (phy_drd->vbus_boost) {
-		ret = regulator_enable(phy_drd->vbus_boost);
-		if (ret) {
-			dev_err(phy_drd->dev,
-				"Failed to enable VBUS boost supply\n");
-			goto fail_vbus;
-		}
+	ret = regulator_bulk_enable(phy_drd->drv_data->n_regulators,
+				    phy_drd->regulators);
+	if (ret) {
+		dev_err(phy_drd->dev, "Failed to enable PHY regulator(s)\n");
+		goto fail_vbus;
 	}
 
-	if (phy_drd->vbus) {
-		ret = regulator_enable(phy_drd->vbus);
-		if (ret) {
-			dev_err(phy_drd->dev, "Failed to enable VBUS supply\n");
-			goto fail_vbus_boost;
-		}
-	}
-
-	/* Power-on PHY*/
-	inst->phy_cfg->phy_isol(inst, 0);
+	/* Power-on PHY */
+	inst->phy_cfg->phy_isol(inst, false);
 
 	return 0;
 
-fail_vbus_boost:
-	if (phy_drd->vbus_boost)
-		regulator_disable(phy_drd->vbus_boost);
-
 fail_vbus:
-	clk_disable_unprepare(phy_drd->ref_clk);
-	if (!phy_drd->drv_data->has_common_clk_gate) {
-		clk_disable_unprepare(phy_drd->itpclk);
-		clk_disable_unprepare(phy_drd->utmiclk);
-		clk_disable_unprepare(phy_drd->pipeclk);
-	}
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_core_clks,
+				   phy_drd->core_clks);
 
 	return ret;
 }
@@ -567,20 +878,14 @@ static int exynos5_usbdrd_phy_power_off(struct phy *phy)
 	dev_dbg(phy_drd->dev, "Request to power_off usbdrd_phy phy\n");
 
 	/* Power-off the PHY */
-	inst->phy_cfg->phy_isol(inst, 1);
+	inst->phy_cfg->phy_isol(inst, true);
 
 	/* Disable VBUS supply */
-	if (phy_drd->vbus)
-		regulator_disable(phy_drd->vbus);
-	if (phy_drd->vbus_boost)
-		regulator_disable(phy_drd->vbus_boost);
+	regulator_bulk_disable(phy_drd->drv_data->n_regulators,
+			       phy_drd->regulators);
 
-	clk_disable_unprepare(phy_drd->ref_clk);
-	if (!phy_drd->drv_data->has_common_clk_gate) {
-		clk_disable_unprepare(phy_drd->itpclk);
-		clk_disable_unprepare(phy_drd->pipeclk);
-		clk_disable_unprepare(phy_drd->utmiclk);
-	}
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_core_clks,
+				   phy_drd->core_clks);
 
 	return 0;
 }
@@ -744,10 +1049,29 @@ static const struct phy_ops exynos5_usbdrd_phy_ops = {
 	.owner		= THIS_MODULE,
 };
 
+static void
+exynos5_usbdrd_usb_v3p1_pipe_override(struct exynos5_usbdrd_phy *phy_drd)
+{
+	void __iomem *regs_base = phy_drd->reg_phy;
+	u32 reg;
+
+	/* force pipe3 signal for link */
+	reg = readl(regs_base + EXYNOS850_DRD_LINKCTRL);
+	reg &= ~LINKCTRL_FORCE_PHYSTATUS;
+	reg |= LINKCTRL_FORCE_PIPE_EN | LINKCTRL_FORCE_RXELECIDLE;
+	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
+
+	/* PMA disable */
+	reg = readl(regs_base + EXYNOS850_DRD_SECPMACTL);
+	reg |= SECPMACTL_PMA_LOW_PWR;
+	writel(reg, regs_base + EXYNOS850_DRD_SECPMACTL);
+}
+
 static void exynos850_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 {
 	void __iomem *regs_base = phy_drd->reg_phy;
 	u32 reg;
+	u32 ss_ports;
 
 	/*
 	 * Disable HWACG (hardware auto clock gating control). This will force
@@ -758,8 +1082,16 @@ static void exynos850_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 	reg |= LINKCTRL_FORCE_QACT;
 	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
 
+	reg = readl(regs_base + EXYNOS850_DRD_LINKPORT);
+	ss_ports = FIELD_GET(LINKPORT_HOST_NUM_U3, reg);
+
 	/* Start PHY Reset (POR=high) */
 	reg = readl(regs_base + EXYNOS850_DRD_CLKRST);
+	if (ss_ports) {
+		reg |= CLKRST_PHY20_SW_POR;
+		reg |= CLKRST_PHY20_SW_POR_SEL;
+		reg |= CLKRST_PHY_RESET_SEL;
+	}
 	reg |= CLKRST_PHY_SW_RST;
 	writel(reg, regs_base + EXYNOS850_DRD_CLKRST);
 
@@ -787,22 +1119,58 @@ static void exynos850_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 	reg |= HSP_VBUSVLDEXT | HSP_VBUSVLDEXTSEL;
 	writel(reg, regs_base + EXYNOS850_DRD_HSP);
 
+	reg = readl(regs_base + EXYNOS850_DRD_SSPPLLCTL);
+	reg &= ~SSPPLLCTL_FSEL;
+	switch (phy_drd->extrefclk) {
+	case EXYNOS5_FSEL_50MHZ:
+		reg |= FIELD_PREP_CONST(SSPPLLCTL_FSEL, 7);
+		break;
+	case EXYNOS5_FSEL_26MHZ:
+		reg |= FIELD_PREP_CONST(SSPPLLCTL_FSEL, 6);
+		break;
+	case EXYNOS5_FSEL_24MHZ:
+		reg |= FIELD_PREP_CONST(SSPPLLCTL_FSEL, 2);
+		break;
+	case EXYNOS5_FSEL_20MHZ:
+		reg |= FIELD_PREP_CONST(SSPPLLCTL_FSEL, 1);
+		break;
+	case EXYNOS5_FSEL_19MHZ2:
+		reg |= FIELD_PREP_CONST(SSPPLLCTL_FSEL, 0);
+		break;
+	default:
+		dev_warn(phy_drd->dev, "unsupported ref clk: %#.2x\n",
+			 phy_drd->extrefclk);
+		break;
+	}
+	writel(reg, regs_base + EXYNOS850_DRD_SSPPLLCTL);
+
+	if (phy_drd->drv_data->phy_tunes)
+		exynos5_usbdrd_apply_phy_tunes(phy_drd,
+					       PTS_UTMI_POSTINIT);
+
 	/* Power up PHY analog blocks */
 	reg = readl(regs_base + EXYNOS850_DRD_HSP_TEST);
 	reg &= ~HSP_TEST_SIDDQ;
 	writel(reg, regs_base + EXYNOS850_DRD_HSP_TEST);
 
 	/* Finish PHY reset (POR=low) */
-	udelay(10); /* required before doing POR=low */
+	fsleep(10); /* required before doing POR=low */
 	reg = readl(regs_base + EXYNOS850_DRD_CLKRST);
+	if (ss_ports) {
+		reg |= CLKRST_PHY20_SW_POR_SEL;
+		reg &= ~CLKRST_PHY20_SW_POR;
+	}
 	reg &= ~(CLKRST_PHY_SW_RST | CLKRST_PORT_RST);
 	writel(reg, regs_base + EXYNOS850_DRD_CLKRST);
-	udelay(75); /* required after POR=low for guaranteed PHY clock */
+	fsleep(75); /* required after POR=low for guaranteed PHY clock */
 
 	/* Disable single ended signal out */
 	reg = readl(regs_base + EXYNOS850_DRD_HSP);
 	reg &= ~HSP_FSV_OUT_EN;
 	writel(reg, regs_base + EXYNOS850_DRD_HSP);
+
+	if (ss_ports)
+		exynos5_usbdrd_usb_v3p1_pipe_override(phy_drd);
 }
 
 static int exynos850_usbdrd_phy_init(struct phy *phy)
@@ -811,14 +1179,14 @@ static int exynos850_usbdrd_phy_init(struct phy *phy)
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 	int ret;
 
-	ret = clk_prepare_enable(phy_drd->clk);
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
 	if (ret)
 		return ret;
 
 	/* UTMI or PIPE3 specific init */
 	inst->phy_cfg->phy_init(phy_drd);
 
-	clk_disable_unprepare(phy_drd->clk);
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
 
 	return 0;
 }
@@ -831,7 +1199,7 @@ static int exynos850_usbdrd_phy_exit(struct phy *phy)
 	u32 reg;
 	int ret;
 
-	ret = clk_prepare_enable(phy_drd->clk);
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
 	if (ret)
 		return ret;
 
@@ -850,11 +1218,11 @@ static int exynos850_usbdrd_phy_exit(struct phy *phy)
 	reg = readl(regs_base + EXYNOS850_DRD_CLKRST);
 	reg |= CLKRST_LINK_SW_RST;
 	writel(reg, regs_base + EXYNOS850_DRD_CLKRST);
-	udelay(10); /* required before doing POR=low */
+	fsleep(10); /* required before doing POR=low */
 	reg &= ~CLKRST_LINK_SW_RST;
 	writel(reg, regs_base + EXYNOS850_DRD_CLKRST);
 
-	clk_disable_unprepare(phy_drd->clk);
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
 
 	return 0;
 }
@@ -867,53 +1235,138 @@ static const struct phy_ops exynos850_usbdrd_phy_ops = {
 	.owner		= THIS_MODULE,
 };
 
-static int exynos5_usbdrd_phy_clk_handle(struct exynos5_usbdrd_phy *phy_drd)
+static void exynos5_usbdrd_gs101_pipe3_init(struct exynos5_usbdrd_phy *phy_drd)
 {
-	unsigned long ref_rate;
+	void __iomem *regs_pma = phy_drd->reg_pma;
+	void __iomem *regs_phy = phy_drd->reg_phy;
+	u32 reg;
+
+	exynos5_usbdrd_usbdp_g2_v4_ctrl_pma_ready(phy_drd);
+
+	/* force aux off */
+	reg = readl(regs_pma + EXYNOS9_PMA_USBDP_CMN_REG0008);
+	reg &= ~CMN_REG0008_AUX_EN;
+	reg |= CMN_REG0008_OVRD_AUX_EN;
+	writel(reg, regs_pma + EXYNOS9_PMA_USBDP_CMN_REG0008);
+
+	exynos5_usbdrd_apply_phy_tunes(phy_drd, PTS_PIPE3_PREINIT);
+	exynos5_usbdrd_apply_phy_tunes(phy_drd, PTS_PIPE3_INIT);
+	exynos5_usbdrd_apply_phy_tunes(phy_drd, PTS_PIPE3_POSTINIT);
+
+	exynos5_usbdrd_usbdp_g2_v4_pma_lane_mux_sel(phy_drd);
+
+	/* reset release from port */
+	reg = readl(regs_phy + EXYNOS850_DRD_SECPMACTL);
+	reg &= ~(SECPMACTL_PMA_TRSV_SW_RST | SECPMACTL_PMA_CMN_SW_RST |
+		 SECPMACTL_PMA_INIT_SW_RST);
+	writel(reg, regs_phy + EXYNOS850_DRD_SECPMACTL);
+
+	if (!exynos5_usbdrd_usbdp_g2_v4_pma_check_pll_lock(phy_drd))
+		exynos5_usbdrd_usbdp_g2_v4_pma_check_cdr_lock(phy_drd);
+}
+
+static int exynos5_usbdrd_gs101_phy_init(struct phy *phy)
+{
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 	int ret;
 
-	phy_drd->clk = devm_clk_get(phy_drd->dev, "phy");
-	if (IS_ERR(phy_drd->clk)) {
-		dev_err(phy_drd->dev, "Failed to get phy clock\n");
-		return PTR_ERR(phy_drd->clk);
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		/* Power-on PHY ... */
+		ret = regulator_bulk_enable(phy_drd->drv_data->n_regulators,
+					    phy_drd->regulators);
+		if (ret) {
+			dev_err(phy_drd->dev,
+				"Failed to enable PHY regulator(s)\n");
+			return ret;
+		}
 	}
+	/*
+	 * ... and ungate power via PMU. Without this here, we get an SError
+	 * trying to access PMA registers
+	 */
+	exynos5_usbdrd_phy_isol(inst, false);
 
-	phy_drd->ref_clk = devm_clk_get(phy_drd->dev, "ref");
-	if (IS_ERR(phy_drd->ref_clk)) {
-		dev_err(phy_drd->dev, "Failed to get phy reference clock\n");
-		return PTR_ERR(phy_drd->ref_clk);
-	}
-	ref_rate = clk_get_rate(phy_drd->ref_clk);
+	return exynos850_usbdrd_phy_init(phy);
+}
 
-	ret = exynos5_rate_to_clk(ref_rate, &phy_drd->extrefclk);
-	if (ret) {
-		dev_err(phy_drd->dev, "Clock rate (%ld) not supported\n",
-			ref_rate);
+static int exynos5_usbdrd_gs101_phy_exit(struct phy *phy)
+{
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+	int ret;
+
+	if (inst->phy_cfg->id != EXYNOS5_DRDPHY_UTMI)
+		return 0;
+
+	ret = exynos850_usbdrd_phy_exit(phy);
+	if (ret)
 		return ret;
-	}
 
-	if (!phy_drd->drv_data->has_common_clk_gate) {
-		phy_drd->pipeclk = devm_clk_get(phy_drd->dev, "phy_pipe");
-		if (IS_ERR(phy_drd->pipeclk)) {
-			dev_info(phy_drd->dev,
-				 "PIPE3 phy operational clock not specified\n");
-			phy_drd->pipeclk = NULL;
-		}
+	exynos5_usbdrd_phy_isol(inst, true);
+	return regulator_bulk_disable(phy_drd->drv_data->n_regulators,
+				      phy_drd->regulators);
+}
 
-		phy_drd->utmiclk = devm_clk_get(phy_drd->dev, "phy_utmi");
-		if (IS_ERR(phy_drd->utmiclk)) {
-			dev_info(phy_drd->dev,
-				 "UTMI phy operational clock not specified\n");
-			phy_drd->utmiclk = NULL;
-		}
+static const struct phy_ops gs101_usbdrd_phy_ops = {
+	.init		= exynos5_usbdrd_gs101_phy_init,
+	.exit		= exynos5_usbdrd_gs101_phy_exit,
+	.owner		= THIS_MODULE,
+};
 
-		phy_drd->itpclk = devm_clk_get(phy_drd->dev, "itp");
-		if (IS_ERR(phy_drd->itpclk)) {
-			dev_info(phy_drd->dev,
-				 "ITP clock from main OSC not specified\n");
-			phy_drd->itpclk = NULL;
+static int exynos5_usbdrd_phy_clk_handle(struct exynos5_usbdrd_phy *phy_drd)
+{
+	int ret;
+	struct clk *ref_clk;
+	unsigned long ref_rate;
+
+	phy_drd->clks = devm_kcalloc(phy_drd->dev, phy_drd->drv_data->n_clks,
+				     sizeof(*phy_drd->clks), GFP_KERNEL);
+	if (!phy_drd->clks)
+		return -ENOMEM;
+
+	for (int i = 0; i < phy_drd->drv_data->n_clks; ++i)
+		phy_drd->clks[i].id = phy_drd->drv_data->clk_names[i];
+
+	ret = devm_clk_bulk_get(phy_drd->dev, phy_drd->drv_data->n_clks,
+				phy_drd->clks);
+	if (ret)
+		return dev_err_probe(phy_drd->dev, ret,
+				     "failed to get phy clock(s)\n");
+
+	phy_drd->core_clks = devm_kcalloc(phy_drd->dev,
+					  phy_drd->drv_data->n_core_clks,
+					  sizeof(*phy_drd->core_clks),
+					  GFP_KERNEL);
+	if (!phy_drd->core_clks)
+		return -ENOMEM;
+
+	for (int i = 0; i < phy_drd->drv_data->n_core_clks; ++i)
+		phy_drd->core_clks[i].id = phy_drd->drv_data->core_clk_names[i];
+
+	ret = devm_clk_bulk_get(phy_drd->dev, phy_drd->drv_data->n_core_clks,
+				phy_drd->core_clks);
+	if (ret)
+		return dev_err_probe(phy_drd->dev, ret,
+				     "failed to get phy core clock(s)\n");
+
+	ref_clk = NULL;
+	for (int i = 0; i < phy_drd->drv_data->n_core_clks; ++i) {
+		if (!strcmp(phy_drd->core_clks[i].id, "ref")) {
+			ref_clk = phy_drd->core_clks[i].clk;
+			break;
 		}
 	}
+	if (!ref_clk)
+		return dev_err_probe(phy_drd->dev, -ENODEV,
+				     "failed to find phy reference clock\n");
+
+	ref_rate = clk_get_rate(ref_clk);
+	ret = exynos5_rate_to_clk(ref_rate, &phy_drd->extrefclk);
+	if (ret)
+		return dev_err_probe(phy_drd->dev, ret,
+				     "clock rate (%ld) not supported\n",
+				     ref_rate);
 
 	return 0;
 }
@@ -941,19 +1394,45 @@ static const struct exynos5_usbdrd_phy_config phy_cfg_exynos850[] = {
 	},
 };
 
+static const char * const exynos5_clk_names[] = {
+	"phy",
+};
+
+static const char * const exynos5_core_clk_names[] = {
+	"ref",
+};
+
+static const char * const exynos5433_core_clk_names[] = {
+	"ref", "phy_pipe", "phy_utmi", "itp",
+};
+
+static const char * const exynos5_regulator_names[] = {
+	"vbus", "vbus-boost",
+};
+
 static const struct exynos5_usbdrd_phy_drvdata exynos5420_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos5,
 	.phy_ops		= &exynos5_usbdrd_phy_ops,
 	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
 	.pmu_offset_usbdrd1_phy	= EXYNOS5420_USBDRD1_PHY_CONTROL,
-	.has_common_clk_gate	= true,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
 static const struct exynos5_usbdrd_phy_drvdata exynos5250_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos5,
 	.phy_ops		= &exynos5_usbdrd_phy_ops,
 	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
-	.has_common_clk_gate	= true,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
 static const struct exynos5_usbdrd_phy_drvdata exynos5433_usbdrd_phy = {
@@ -961,25 +1440,218 @@ static const struct exynos5_usbdrd_phy_drvdata exynos5433_usbdrd_phy = {
 	.phy_ops		= &exynos5_usbdrd_phy_ops,
 	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
 	.pmu_offset_usbdrd1_phy	= EXYNOS5433_USBHOST30_PHY_CONTROL,
-	.has_common_clk_gate	= false,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5433_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5433_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
 static const struct exynos5_usbdrd_phy_drvdata exynos7_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos5,
 	.phy_ops		= &exynos5_usbdrd_phy_ops,
 	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
-	.has_common_clk_gate	= false,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5433_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5433_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
 static const struct exynos5_usbdrd_phy_drvdata exynos850_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos850,
 	.phy_ops		= &exynos850_usbdrd_phy_ops,
 	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
-	.has_common_clk_gate	= true,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
+};
+
+static const struct exynos5_usbdrd_phy_config phy_cfg_gs101[] = {
+	{
+		.id		= EXYNOS5_DRDPHY_UTMI,
+		.phy_isol	= exynos5_usbdrd_phy_isol,
+		.phy_init	= exynos850_usbdrd_utmi_init,
+	},
+	{
+		.id		= EXYNOS5_DRDPHY_PIPE3,
+		.phy_isol	= exynos5_usbdrd_phy_isol,
+		.phy_init	= exynos5_usbdrd_gs101_pipe3_init,
+	},
+};
+
+static const struct exynos5_usbdrd_phy_tuning gs101_tunes_utmi_postinit[] = {
+	PHY_TUNING_ENTRY_PHY(EXYNOS850_DRD_HSPPARACON,
+			     (HSPPARACON_TXVREF | HSPPARACON_TXRES |
+			      HSPPARACON_TXPREEMPAMP | HSPPARACON_SQRX |
+			      HSPPARACON_COMPDIS),
+			     (FIELD_PREP_CONST(HSPPARACON_TXVREF, 6) |
+			      FIELD_PREP_CONST(HSPPARACON_TXRES, 1) |
+			      FIELD_PREP_CONST(HSPPARACON_TXPREEMPAMP, 3) |
+			      FIELD_PREP_CONST(HSPPARACON_SQRX, 5) |
+			      FIELD_PREP_CONST(HSPPARACON_COMPDIS, 7))),
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning gs101_tunes_pipe3_preinit[] = {
+	/* preinit */
+	/* CDR data mode exit GEN1 ON / GEN2 OFF */
+	PHY_TUNING_ENTRY_PMA(0x0c8c, -1, 0xff),
+	PHY_TUNING_ENTRY_PMA(0x1c8c, -1, 0xff),
+	PHY_TUNING_ENTRY_PMA(0x0c9c, -1, 0x7d),
+	PHY_TUNING_ENTRY_PMA(0x1c9c, -1, 0x7d),
+	/* improve EDS distribution */
+	PHY_TUNING_ENTRY_PMA(0x0e7c, -1, 0x06),
+	PHY_TUNING_ENTRY_PMA(0x09e0, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x09e4, -1, 0x36),
+	PHY_TUNING_ENTRY_PMA(0x1e7c, -1, 0x06),
+	PHY_TUNING_ENTRY_PMA(0x1e90, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x1e94, -1, 0x36),
+	/* improve LVCC */
+	PHY_TUNING_ENTRY_PMA(0x08f0, -1, 0x30),
+	PHY_TUNING_ENTRY_PMA(0x18f0, -1, 0x30),
+	/* LFPS RX VIH shmoo hole */
+	PHY_TUNING_ENTRY_PMA(0x0a08, -1, 0x0c),
+	PHY_TUNING_ENTRY_PMA(0x1a08, -1, 0x0c),
+	/* remove unrelated option for v4 phy */
+	PHY_TUNING_ENTRY_PMA(0x0a0c, -1, 0x05),
+	PHY_TUNING_ENTRY_PMA(0x1a0c, -1, 0x05),
+	/* improve Gen2 LVCC */
+	PHY_TUNING_ENTRY_PMA(0x00f8, -1, 0x1c),
+	PHY_TUNING_ENTRY_PMA(0x00fc, -1, 0x54),
+	/* Change Vth of RCV_DET because of TD 7.40 Polling Retry Test */
+	PHY_TUNING_ENTRY_PMA(0x104c, -1, 0x07),
+	PHY_TUNING_ENTRY_PMA(0x204c, -1, 0x07),
+	/* reduce Ux Exit time, assuming 26MHz clock */
+	/* Gen1 */
+	PHY_TUNING_ENTRY_PMA(0x0ca8, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x0cac, -1, 0x04),
+	PHY_TUNING_ENTRY_PMA(0x1ca8, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x1cac, -1, 0x04),
+	/* Gen2 */
+	PHY_TUNING_ENTRY_PMA(0x0cb8, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x0cbc, -1, 0x04),
+	PHY_TUNING_ENTRY_PMA(0x1cb8, -1, 0x00),
+	PHY_TUNING_ENTRY_PMA(0x1cbc, -1, 0x04),
+	/* RX impedance setting */
+	PHY_TUNING_ENTRY_PMA(0x0bb0, 0x03, 0x01),
+	PHY_TUNING_ENTRY_PMA(0x0bb4, 0xf0, 0xa0),
+	PHY_TUNING_ENTRY_PMA(0x1bb0, 0x03, 0x01),
+	PHY_TUNING_ENTRY_PMA(0x1bb4, 0xf0, 0xa0),
+
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning gs101_tunes_pipe3_init[] = {
+	/* init */
+	/* abnormal common pattern mask */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_BACK_END_MODE_VEC,
+			     BACK_END_MODE_VEC_DISABLE_DATA_MASK, 0),
+	/* de-serializer enabled when U2 */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_OUT_VEC_2, PCS_OUT_VEC_B4_DYNAMIC,
+			     PCS_OUT_VEC_B4_SEL_OUT),
+	/* TX Keeper Disable, Squelch on when U3 */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_OUT_VEC_3, PCS_OUT_VEC_B7_DYNAMIC,
+			     PCS_OUT_VEC_B7_SEL_OUT | PCS_OUT_VEC_B2_SEL_OUT),
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_NS_VEC_PS1_N1, -1,
+			     (FIELD_PREP_CONST(NS_VEC_NS_REQ, 5) |
+			      NS_VEC_ENABLE_TIMER |
+			      FIELD_PREP_CONST(NS_VEC_SEL_TIMEOUT, 3))),
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_NS_VEC_PS2_N0, -1,
+			     (FIELD_PREP_CONST(NS_VEC_NS_REQ, 1) |
+			      NS_VEC_ENABLE_TIMER |
+			      FIELD_PREP_CONST(NS_VEC_SEL_TIMEOUT, 3) |
+			      FIELD_PREP_CONST(NS_VEC_COND_MASK, 2) |
+			      FIELD_PREP_CONST(NS_VEC_EXP_COND, 2))),
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_NS_VEC_PS3_N0, -1,
+			     (FIELD_PREP_CONST(NS_VEC_NS_REQ, 1) |
+			      NS_VEC_ENABLE_TIMER |
+			      FIELD_PREP_CONST(NS_VEC_SEL_TIMEOUT, 3) |
+			      FIELD_PREP_CONST(NS_VEC_COND_MASK, 7) |
+			      FIELD_PREP_CONST(NS_VEC_EXP_COND, 7))),
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_TIMEOUT_0, -1, 112),
+	/* Block Aligner Type B */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_RX_CONTROL, 0,
+			     RX_CONTROL_EN_BLOCK_ALIGNER_TYPE_B),
+	/* Block align at TS1/TS2 for Gen2 stability (Gen2 only) */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_RX_CONTROL_DEBUG,
+		RX_CONTROL_DEBUG_NUM_COM_FOUND,
+		(RX_CONTROL_DEBUG_EN_TS_CHECK |
+		 /*
+		  * increase pcs ts1 adding packet-cnt 1 --> 4
+		  * lnx_rx_valid_rstn_delay_rise_sp/ssp :
+		  * 19.6us(0x200) -> 15.3us(0x4)
+		  */
+		 FIELD_PREP_CONST(RX_CONTROL_DEBUG_NUM_COM_FOUND, 4))),
+	/* Gen1 Tx DRIVER pre-shoot, de-emphasis, level ctrl */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_HS_TX_COEF_MAP_0,
+		(HS_TX_COEF_MAP_0_SSTX_DEEMP | HS_TX_COEF_MAP_0_SSTX_LEVEL |
+		 HS_TX_COEF_MAP_0_SSTX_PRE_SHOOT),
+		(FIELD_PREP_CONST(HS_TX_COEF_MAP_0_SSTX_DEEMP, 8) |
+		 FIELD_PREP_CONST(HS_TX_COEF_MAP_0_SSTX_LEVEL, 0xb) |
+		 FIELD_PREP_CONST(HS_TX_COEF_MAP_0_SSTX_PRE_SHOOT, 0))),
+	/* Gen2 Tx DRIVER level ctrl */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_LOCAL_COEF,
+		LOCAL_COEF_PMA_CENTER_COEF,
+		FIELD_PREP_CONST(LOCAL_COEF_PMA_CENTER_COEF, 0xb)),
+	/* Gen2 U1 exit LFPS duration : 900ns ~ 1.2us */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_TIMEOUT_3, -1, 4096),
+	/* set skp_remove_th 0x2 -> 0x7 for avoiding retry problem. */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_EBUF_PARAM,
+		EBUF_PARAM_SKP_REMOVE_TH_EMPTY_MODE,
+		FIELD_PREP_CONST(EBUF_PARAM_SKP_REMOVE_TH_EMPTY_MODE, 0x7)),
+
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning gs101_tunes_pipe3_postlock[] = {
+	/* Squelch off when U3 */
+	PHY_TUNING_ENTRY_PCS(EXYNOS9_PCS_OUT_VEC_3, PCS_OUT_VEC_B2_SEL_OUT, 0),
+
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning *gs101_tunes[PTS_MAX] = {
+	[PTS_UTMI_POSTINIT] = gs101_tunes_utmi_postinit,
+	[PTS_PIPE3_PREINIT] = gs101_tunes_pipe3_preinit,
+	[PTS_PIPE3_INIT] = gs101_tunes_pipe3_init,
+	[PTS_PIPE3_POSTLOCK] = gs101_tunes_pipe3_postlock,
+};
+
+static const char * const gs101_clk_names[] = {
+	"phy", "ctrl_aclk", "ctrl_pclk", "scl_pclk",
+};
+
+static const char * const gs101_regulator_names[] = {
+	"pll",
+	"dvdd-usb20", "vddh-usb20", "vdd33-usb20",
+	"vdda-usbdp", "vddh-usbdp",
+};
+
+static const struct exynos5_usbdrd_phy_drvdata gs101_usbd31rd_phy = {
+	.phy_cfg			= phy_cfg_gs101,
+	.phy_tunes			= gs101_tunes,
+	.phy_ops			= &gs101_usbdrd_phy_ops,
+	.pmu_offset_usbdrd0_phy		= GS101_PHY_CTRL_USB20,
+	.pmu_offset_usbdrd0_phy_ss	= GS101_PHY_CTRL_USBDP,
+	.clk_names			= gs101_clk_names,
+	.n_clks				= ARRAY_SIZE(gs101_clk_names),
+	.core_clk_names			= exynos5_core_clk_names,
+	.n_core_clks			= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names		= gs101_regulator_names,
+	.n_regulators			= ARRAY_SIZE(gs101_regulator_names),
 };
 
 static const struct of_device_id exynos5_usbdrd_phy_of_match[] = {
 	{
+		.compatible = "google,gs101-usb31drd-phy",
+		.data = &gs101_usbd31rd_phy
+	}, {
 		.compatible = "samsung,exynos5250-usbdrd-phy",
 		.data = &exynos5250_usbdrd_phy
 	}, {
@@ -1018,22 +1690,39 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
 	dev_set_drvdata(dev, phy_drd);
 	phy_drd->dev = dev;
 
-	phy_drd->reg_phy = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(phy_drd->reg_phy))
-		return PTR_ERR(phy_drd->reg_phy);
-
 	drv_data = of_device_get_match_data(dev);
 	if (!drv_data)
 		return -EINVAL;
-
 	phy_drd->drv_data = drv_data;
 
-	ret = exynos5_usbdrd_phy_clk_handle(phy_drd);
-	if (ret) {
-		dev_err(dev, "Failed to initialize clocks\n");
-		return ret;
+	if (of_property_present(dev->of_node, "reg-names")) {
+		void __iomem *reg;
+
+		reg = devm_platform_ioremap_resource_byname(pdev, "phy");
+		if (IS_ERR(reg))
+			return PTR_ERR(reg);
+		phy_drd->reg_phy = reg;
+
+		reg = devm_platform_ioremap_resource_byname(pdev, "pcs");
+		if (IS_ERR(reg))
+			return PTR_ERR(reg);
+		phy_drd->reg_pcs = reg;
+
+		reg = devm_platform_ioremap_resource_byname(pdev, "pma");
+		if (IS_ERR(reg))
+			return PTR_ERR(reg);
+		phy_drd->reg_pma = reg;
+	} else {
+		/* DTB with just a single region */
+		phy_drd->reg_phy = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(phy_drd->reg_phy))
+			return PTR_ERR(phy_drd->reg_phy);
 	}
 
+	ret = exynos5_usbdrd_phy_clk_handle(phy_drd);
+	if (ret)
+		return ret;
+
 	reg_pmu = syscon_regmap_lookup_by_phandle(dev->of_node,
 						   "samsung,pmu-syscon");
 	if (IS_ERR(reg_pmu)) {
@@ -1050,36 +1739,20 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
 	if (channel < 0)
 		dev_dbg(dev, "Not a multi-controller usbdrd phy\n");
 
-	switch (channel) {
-	case 1:
-		pmu_offset = phy_drd->drv_data->pmu_offset_usbdrd1_phy;
-		break;
-	case 0:
-	default:
-		pmu_offset = phy_drd->drv_data->pmu_offset_usbdrd0_phy;
-		break;
-	}
-
-	/* Get Vbus regulators */
-	phy_drd->vbus = devm_regulator_get(dev, "vbus");
-	if (IS_ERR(phy_drd->vbus)) {
-		ret = PTR_ERR(phy_drd->vbus);
-		if (ret == -EPROBE_DEFER)
-			return ret;
-
-		dev_warn(dev, "Failed to get VBUS supply regulator\n");
-		phy_drd->vbus = NULL;
-	}
-
-	phy_drd->vbus_boost = devm_regulator_get(dev, "vbus-boost");
-	if (IS_ERR(phy_drd->vbus_boost)) {
-		ret = PTR_ERR(phy_drd->vbus_boost);
-		if (ret == -EPROBE_DEFER)
-			return ret;
-
-		dev_warn(dev, "Failed to get VBUS boost supply regulator\n");
-		phy_drd->vbus_boost = NULL;
-	}
+	/* Get regulators */
+	phy_drd->regulators = devm_kcalloc(dev,
+					   drv_data->n_regulators,
+					   sizeof(*phy_drd->regulators),
+					   GFP_KERNEL);
+	if (!phy_drd->regulators)
+		return ENOMEM;
+	regulator_bulk_set_supply_names(phy_drd->regulators,
+					drv_data->regulator_names,
+					drv_data->n_regulators);
+	ret = devm_regulator_bulk_get(dev, drv_data->n_regulators,
+				      phy_drd->regulators);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to get regulators\n");
 
 	dev_vdbg(dev, "Creating usbdrd_phy phy\n");
 
@@ -1094,6 +1767,18 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
 		phy_drd->phys[i].phy = phy;
 		phy_drd->phys[i].index = i;
 		phy_drd->phys[i].reg_pmu = reg_pmu;
+		switch (channel) {
+		case 1:
+			pmu_offset = drv_data->pmu_offset_usbdrd1_phy;
+			break;
+		case 0:
+		default:
+			pmu_offset = drv_data->pmu_offset_usbdrd0_phy;
+			if (i == EXYNOS5_DRDPHY_PIPE3 && drv_data
+						->pmu_offset_usbdrd0_phy_ss)
+				pmu_offset = drv_data->pmu_offset_usbdrd0_phy_ss;
+			break;
+		}
 		phy_drd->phys[i].pmu_offset = pmu_offset;
 		phy_drd->phys[i].phy_cfg = &drv_data->phy_cfg[i];
 		phy_set_drvdata(phy, &phy_drd->phys[i]);
diff --git a/drivers/phy/samsung/phy-exynos5250-usb2.c b/drivers/phy/samsung/phy-exynos5250-usb2.c
index e198010..21b0607 100644
--- a/drivers/phy/samsung/phy-exynos5250-usb2.c
+++ b/drivers/phy/samsung/phy-exynos5250-usb2.c
@@ -121,7 +121,7 @@
 #define EXYNOS_5420_USB_ISOL_HOST_OFFSET	0x70C
 #define EXYNOS_5250_USB_ISOL_ENABLE		BIT(0)
 
-/* Mode swtich register */
+/* Mode switch register */
 #define EXYNOS_5250_MODE_SWITCH_OFFSET		0x230
 #define EXYNOS_5250_MODE_SWITCH_MASK		1
 #define EXYNOS_5250_MODE_SWITCH_DEVICE		0
diff --git a/drivers/phy/st/phy-miphy28lp.c b/drivers/phy/st/phy-miphy28lp.c
index 063fc38..43cef89 100644
--- a/drivers/phy/st/phy-miphy28lp.c
+++ b/drivers/phy/st/phy-miphy28lp.c
@@ -228,11 +228,6 @@ struct miphy28lp_dev {
 	int nphys;
 };
 
-struct miphy_initval {
-	u16 reg;
-	u16 val;
-};
-
 enum miphy_sata_gen { SATA_GEN1, SATA_GEN2, SATA_GEN3 };
 
 static char *PHY_TYPE_name[] = { "sata-up", "pcie-up", "", "usb3-up" };
diff --git a/drivers/phy/starfive/Kconfig b/drivers/phy/starfive/Kconfig
index 9508e21..d0cdd7c 100644
--- a/drivers/phy/starfive/Kconfig
+++ b/drivers/phy/starfive/Kconfig
@@ -15,6 +15,16 @@
 	  system. If M is selected, the module will be called
 	  phy-jh7110-dphy-rx.ko.
 
+config PHY_STARFIVE_JH7110_DPHY_TX
+	tristate "StarFive JH7110 D-PHY TX Support"
+	depends on HAS_IOMEM
+	select GENERIC_PHY
+	select GENERIC_PHY_MIPI_DPHY
+	help
+	  Choose this option if you have a StarFive D-PHY TX in your
+	  system. If M is selected, the module will be called
+	  phy-jh7110-dphy-tx.ko.
+
 config PHY_STARFIVE_JH7110_PCIE
 	tristate "Starfive JH7110 PCIE 2.0/USB 3.0 PHY support"
 	depends on HAS_IOMEM
diff --git a/drivers/phy/starfive/Makefile b/drivers/phy/starfive/Makefile
index b391018..eedc4a6 100644
--- a/drivers/phy/starfive/Makefile
+++ b/drivers/phy/starfive/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_PHY_STARFIVE_JH7110_DPHY_RX)	+= phy-jh7110-dphy-rx.o
+obj-$(CONFIG_PHY_STARFIVE_JH7110_DPHY_TX)	+= phy-jh7110-dphy-tx.o
 obj-$(CONFIG_PHY_STARFIVE_JH7110_PCIE)		+= phy-jh7110-pcie.o
 obj-$(CONFIG_PHY_STARFIVE_JH7110_USB)		+= phy-jh7110-usb.o
diff --git a/drivers/phy/starfive/phy-jh7110-dphy-rx.c b/drivers/phy/starfive/phy-jh7110-dphy-rx.c
index 037a9e0..0b039e1 100644
--- a/drivers/phy/starfive/phy-jh7110-dphy-rx.c
+++ b/drivers/phy/starfive/phy-jh7110-dphy-rx.c
@@ -46,11 +46,6 @@
 
 #define STF_MAP_LANES_NUM			6
 
-struct regval {
-	u32 addr;
-	u32 val;
-};
-
 struct stf_dphy_info {
 	/**
 	 * @maps:
diff --git a/drivers/phy/starfive/phy-jh7110-dphy-tx.c b/drivers/phy/starfive/phy-jh7110-dphy-tx.c
new file mode 100644
index 0000000..c64d1c9
--- /dev/null
+++ b/drivers/phy/starfive/phy-jh7110-dphy-tx.c
@@ -0,0 +1,461 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DPHY TX driver for the StarFive JH7110 SoC
+ *
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ * Author: Keith Zhao <keith.zhao@starfivetech.com>
+ * Author: Shengyang Chen <shengyang.chen@starfivetech.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/phy/phy.h>
+#include <linux/phy/phy-mipi-dphy.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#define STF_DPHY_APBIFSAIF_SYSCFG(x)			(x)
+
+#define STF_DPHY_AON_POWER_READY_N_ACTIVE		0
+#define STF_DPHY_AON_POWER_READY_N			BIT(0)
+#define STF_DPHY_CFG_L0_SWAP_SEL			GENMASK(14, 12)
+#define STF_DPHY_CFG_L1_SWAP_SEL			GENMASK(17, 15)
+#define STF_DPHY_CFG_L2_SWAP_SEL			GENMASK(20, 18)
+#define STF_DPHY_CFG_L3_SWAP_SEL			GENMASK(23, 21)
+#define STF_DPHY_CFG_L4_SWAP_SEL			GENMASK(26, 24)
+#define STF_DPHY_RGS_CDTX_PLL_UNLOCK			BIT(18)
+#define STF_DPHY_RG_CDTX_L0N_HSTX_RES			GENMASK(23, 19)
+#define STF_DPHY_RG_CDTX_L0P_HSTX_RES			GENMASK(28, 24)
+
+#define STF_DPHY_RG_CDTX_L1P_HSTX_RES			GENMASK(9, 5)
+#define STF_DPHY_RG_CDTX_L2N_HSTX_RES			GENMASK(14, 10)
+#define STF_DPHY_RG_CDTX_L2P_HSTX_RES			GENMASK(19, 15)
+#define STF_DPHY_RG_CDTX_L3N_HSTX_RES			GENMASK(24, 20)
+#define STF_DPHY_RG_CDTX_L3P_HSTX_RES			GENMASK(29, 25)
+
+#define STF_DPHY_RG_CDTX_L4N_HSTX_RES			GENMASK(4, 0)
+#define STF_DPHY_RG_CDTX_L4P_HSTX_RES			GENMASK(9, 5)
+#define STF_DPHY_RG_CDTX_PLL_FBK_FRA			GENMASK(23, 0)
+
+#define STF_DPHY_RG_CDTX_PLL_FBK_INT			GENMASK(8, 0)
+#define STF_DPHY_RG_CDTX_PLL_FM_EN			BIT(9)
+#define STF_DPHY_RG_CDTX_PLL_LDO_STB_X2_EN		BIT(10)
+#define STF_DPHY_RG_CDTX_PLL_PRE_DIV			GENMASK(12, 11)
+
+#define STF_DPHY_RG_CDTX_PLL_SSC_EN			BIT(18)
+
+#define STF_DPHY_RG_CLANE_HS_CLK_POST_TIME		GENMASK(7, 0)
+#define STF_DPHY_RG_CLANE_HS_CLK_PRE_TIME		GENMASK(15, 8)
+#define STF_DPHY_RG_CLANE_HS_PRE_TIME			GENMASK(23, 16)
+#define STF_DPHY_RG_CLANE_HS_TRAIL_TIME			GENMASK(31, 24)
+
+#define STF_DPHY_RG_CLANE_HS_ZERO_TIME			GENMASK(7, 0)
+#define STF_DPHY_RG_DLANE_HS_PRE_TIME			GENMASK(15, 8)
+#define STF_DPHY_RG_DLANE_HS_TRAIL_TIME			GENMASK(23, 16)
+#define STF_DPHY_RG_DLANE_HS_ZERO_TIME			GENMASK(31, 24)
+
+#define STF_DPHY_RG_EXTD_CYCLE_SEL			GENMASK(2, 0)
+#define STF_DPHY_SCFG_C_HS_PRE_ZERO_TIME		GENMASK(31, 0)
+
+#define STF_DPHY_SCFG_DSI_TXREADY_ESC_SEL		GENMASK(2, 1)
+#define STF_DPHY_SCFG_PPI_C_READY_SEL			GENMASK(4, 3)
+
+#define STF_DPHY_REFCLK_IN_SEL				GENMASK(28, 26)
+#define STF_DPHY_RESETB					BIT(29)
+
+#define STF_DPHY_REFCLK_12M				1
+#define STF_DPHY_BITRATE_ALIGN				10000000
+
+#define STF_MAP_LANES_NUM				5
+
+#define STF_DPHY_LSHIFT_16(x)				(FIELD_PREP(GENMASK(23, 16), (x)))
+#define STF_DPHY_LSHIFT_8(x)				(FIELD_PREP(GENMASK(15, 8), (x)))
+
+#define STF_DPHY_HW_DELAY_US				200
+#define STF_DPHY_HW_TIMEOUT_US				5000
+
+struct stf_dphy_config {
+	unsigned long bitrate;
+	u32 pll_fbk_int;
+	u32 pll_fbk_fra_val;
+	u32 extd_cycle_sel;
+	u32 dlane_hs_pre_time;
+	u32 dlane_hs_zero_time;
+	u32 dlane_hs_trail_time;
+	u32 clane_hs_pre_time;
+	u32 clane_hs_zero_time;
+	u32 clane_hs_trail_time;
+	u32 clane_hs_clk_pre_time;
+	u32 clane_hs_clk_post_time;
+};
+
+static const struct stf_dphy_config reg_configs[] = {
+	{160000000, 0x6a, 0xaa, 0x3, 0xa, 0x17, 0x11, 0x5, 0x2b, 0xd, 0x7, 0x3d},
+	{170000000, 0x71, 0x55, 0x3, 0xb, 0x18, 0x11, 0x5, 0x2e, 0xd, 0x7, 0x3d},
+	{180000000, 0x78, 0x0, 0x3, 0xb, 0x19, 0x12, 0x6, 0x30, 0xe, 0x7, 0x3e},
+	{190000000, 0x7e, 0xaa, 0x3, 0xc, 0x1a, 0x12, 0x6, 0x33, 0xe, 0x7, 0x3e},
+	{200000000, 0x85, 0x55, 0x3, 0xc, 0x1b, 0x13, 0x7, 0x35, 0xf, 0x7, 0x3f},
+	{320000000, 0x6a, 0xaa, 0x2, 0x8, 0x14, 0xf, 0x5, 0x2b, 0xd, 0x3, 0x23},
+	{330000000, 0x6e, 0x0, 0x2, 0x8, 0x15, 0xf, 0x5, 0x2d, 0xd, 0x3, 0x23},
+	{340000000, 0x71, 0x55, 0x2, 0x9, 0x15, 0xf, 0x5, 0x2e, 0xd, 0x3, 0x23},
+	{350000000, 0x74, 0xaa, 0x2, 0x9, 0x15, 0x10, 0x6, 0x2f, 0xe, 0x3, 0x24},
+	{360000000, 0x78, 0x0, 0x2, 0x9, 0x16, 0x10, 0x6, 0x30, 0xe, 0x3, 0x24},
+	{370000000, 0x7b, 0x55, 0x2, 0x9, 0x17, 0x10, 0x6, 0x32, 0xe, 0x3, 0x24},
+	{380000000, 0x7e, 0xaa, 0x2, 0xa, 0x17, 0x10, 0x6, 0x33, 0xe, 0x3, 0x24},
+	{390000000, 0x82, 0x0, 0x2, 0xa, 0x17, 0x11, 0x6, 0x35, 0xf, 0x3, 0x25},
+	{400000000, 0x85, 0x55, 0x2, 0xa, 0x18, 0x11, 0x7, 0x35, 0xf, 0x3, 0x25},
+	{410000000, 0x88, 0xaa, 0x2, 0xa, 0x19, 0x11, 0x7, 0x37, 0xf, 0x3, 0x25},
+	{420000000, 0x8c, 0x0, 0x2, 0xa, 0x19, 0x12, 0x7, 0x38, 0x10, 0x3, 0x26},
+	{430000000, 0x8f, 0x55, 0x2, 0xb, 0x19, 0x12, 0x7, 0x39, 0x10, 0x3, 0x26},
+	{440000000, 0x92, 0xaa, 0x2, 0xb, 0x1a, 0x12, 0x7, 0x3b, 0x10, 0x3, 0x26},
+	{450000000, 0x96, 0x0, 0x2, 0xb, 0x1b, 0x12, 0x8, 0x3c, 0x10, 0x3, 0x26},
+	{460000000, 0x99, 0x55, 0x2, 0xb, 0x1b, 0x13, 0x8, 0x3d, 0x11, 0x3, 0x27},
+	{470000000, 0x9c, 0xaa, 0x2, 0xc, 0x1b, 0x13, 0x8, 0x3e, 0x11, 0x3, 0x27},
+	{480000000, 0xa0, 0x27, 0x2, 0xc, 0x1c, 0x13, 0x8, 0x40, 0x11, 0x3, 0x27},
+	{490000000, 0xa3, 0x55, 0x2, 0xc, 0x1d, 0x14, 0x8, 0x42, 0x12, 0x3, 0x28},
+	{500000000, 0xa6, 0xaa, 0x2, 0xc, 0x1d, 0x14, 0x9, 0x42, 0x12, 0x3, 0x28},
+	{510000000, 0xaa, 0x0, 0x2, 0xc, 0x1e, 0x14, 0x9, 0x44, 0x12, 0x3, 0x28},
+	{520000000, 0xad, 0x55, 0x2, 0xd, 0x1e, 0x15, 0x9, 0x45, 0x13, 0x3, 0x29},
+	{530000000, 0xb0, 0xaa, 0x2, 0xd, 0x1e, 0x15, 0x9, 0x47, 0x13, 0x3, 0x29},
+	{540000000, 0xb4, 0x0, 0x2, 0xd, 0x1f, 0x15, 0x9, 0x48, 0x13, 0x3, 0x29},
+	{550000000, 0xb7, 0x55, 0x2, 0xd, 0x20, 0x16, 0x9, 0x4a, 0x14, 0x3, 0x2a},
+	{560000000, 0xba, 0xaa, 0x2, 0xe, 0x20, 0x16, 0xa, 0x4a, 0x14, 0x3, 0x2a},
+	{570000000, 0xbe, 0x0, 0x2, 0xe, 0x20, 0x16, 0xa, 0x4c, 0x14, 0x3, 0x2a},
+	{580000000, 0xc1, 0x55, 0x2, 0xe, 0x21, 0x16, 0xa, 0x4d, 0x14, 0x3, 0x2a},
+	{590000000, 0xc4, 0xaa, 0x2, 0xe, 0x22, 0x17, 0xa, 0x4f, 0x15, 0x3, 0x2b},
+	{600000000, 0xc8, 0x0, 0x2, 0xe, 0x23, 0x17, 0xa, 0x50, 0x15, 0x3, 0x2b},
+	{610000000, 0xcb, 0x55, 0x2, 0xf, 0x22, 0x17, 0xb, 0x50, 0x15, 0x3, 0x2b},
+	{620000000, 0xce, 0xaa, 0x2, 0xf, 0x23, 0x18, 0xb, 0x52, 0x16, 0x3, 0x2c},
+	{630000000, 0x69, 0x0, 0x1, 0x7, 0x12, 0xd, 0x5, 0x2a, 0xc, 0x1, 0x15},
+	{640000000, 0x6a, 0xaa, 0x1, 0x7, 0x13, 0xe, 0x5, 0x2b, 0xd, 0x1, 0x16},
+	{650000000, 0x6c, 0x55, 0x1, 0x7, 0x13, 0xe, 0x5, 0x2c, 0xd, 0x1, 0x16},
+	{660000000, 0x6e, 0x0, 0x1, 0x7, 0x13, 0xe, 0x5, 0x2d, 0xd, 0x1, 0x16},
+	{670000000, 0x6f, 0xaa, 0x1, 0x8, 0x13, 0xe, 0x5, 0x2d, 0xd, 0x1, 0x16},
+	{680000000, 0x71, 0x55, 0x1, 0x8, 0x13, 0xe, 0x5, 0x2e, 0xd, 0x1, 0x16},
+	{690000000, 0x73, 0x0, 0x1, 0x8, 0x14, 0xe, 0x6, 0x2e, 0xd, 0x1, 0x16},
+	{700000000, 0x74, 0xaa, 0x1, 0x8, 0x14, 0xf, 0x6, 0x2f, 0xe, 0x1, 0x16},
+	{710000000, 0x76, 0x55, 0x1, 0x8, 0x14, 0xf, 0x6, 0x2f, 0xe, 0x1, 0x17},
+	{720000000, 0x78, 0x0, 0x1, 0x8, 0x15, 0xf, 0x6, 0x30, 0xe, 0x1, 0x17},
+	{730000000, 0x79, 0xaa, 0x1, 0x8, 0x15, 0xf, 0x6, 0x31, 0xe, 0x1, 0x17},
+	{740000000, 0x7b, 0x55, 0x1, 0x8, 0x15, 0xf, 0x6, 0x32, 0xe, 0x1, 0x17},
+	{750000000, 0x7d, 0x0, 0x1, 0x8, 0x16, 0xf, 0x6, 0x32, 0xe, 0x1, 0x17},
+	{760000000, 0x7e, 0xaa, 0x1, 0x9, 0x15, 0xf, 0x6, 0x33, 0xe, 0x1, 0x17},
+	{770000000, 0x80, 0x55, 0x1, 0x9, 0x15, 0x10, 0x6, 0x34, 0xf, 0x1, 0x18},
+	{780000000, 0x82, 0x0, 0x1, 0x9, 0x16, 0x10, 0x6, 0x35, 0xf, 0x1, 0x18,},
+	{790000000, 0x83, 0xaa, 0x1, 0x9, 0x16, 0x10, 0x7, 0x34, 0xf, 0x1, 0x18},
+	{800000000, 0x85, 0x55, 0x1, 0x9, 0x17, 0x10, 0x7, 0x35, 0xf, 0x1, 0x18},
+	{810000000, 0x87, 0x0, 0x1, 0x9, 0x17, 0x10, 0x7, 0x36, 0xf, 0x1, 0x18},
+	{820000000, 0x88, 0xaa, 0x1, 0x9, 0x17, 0x10, 0x7, 0x37, 0xf, 0x1, 0x18},
+	{830000000, 0x8a, 0x55, 0x1, 0x9, 0x18, 0x10, 0x7, 0x37, 0xf, 0x1, 0x18},
+	{840000000, 0x8c, 0x0, 0x1, 0x9, 0x18, 0x11, 0x7, 0x38, 0x10, 0x1, 0x19},
+	{850000000, 0x8d, 0xaa, 0x1, 0xa, 0x17, 0x11, 0x7, 0x39, 0x10, 0x1, 0x19},
+	{860000000, 0x8f, 0x55, 0x1, 0xa, 0x18, 0x11, 0x7, 0x39, 0x10, 0x1, 0x19},
+	{870000000, 0x91, 0x0, 0x1, 0xa, 0x18, 0x11, 0x7, 0x3a, 0x10, 0x1, 0x19},
+	{880000000, 0x92, 0xaa, 0x1, 0xa, 0x18, 0x11, 0x7, 0x3b, 0x10, 0x1, 0x19},
+	{890000000, 0x94, 0x55, 0x1, 0xa, 0x19, 0x11, 0x7, 0x3c, 0x10, 0x1, 0x19},
+	{900000000, 0x96, 0x0, 0x1, 0xa, 0x19, 0x12, 0x8, 0x3c, 0x10, 0x1, 0x19},
+	{910000000, 0x97, 0xaa, 0x1, 0xa, 0x19, 0x12, 0x8, 0x3c, 0x11, 0x1, 0x1a},
+	{920000000, 0x99, 0x55, 0x1, 0xa, 0x1a, 0x12, 0x8, 0x3d, 0x11, 0x1, 0x1a},
+	{930000000, 0x9b, 0x0, 0x1, 0xa, 0x1a, 0x12, 0x8, 0x3e, 0x11, 0x1, 0x1a},
+	{940000000, 0x9c, 0xaa, 0x1, 0xb, 0x1a, 0x12, 0x8, 0x3e, 0x11, 0x1, 0x1a},
+	{950000000, 0x9e, 0x55, 0x1, 0xb, 0x1a, 0x12, 0x8, 0x3f, 0x11, 0x1, 0x1a},
+	{960000000, 0xa0, 0x0, 0x1, 0xb, 0x1a, 0x12, 0x8, 0x40, 0x11, 0x1, 0x1a},
+	{970000000, 0xa1, 0xaa, 0x1, 0xb, 0x1b, 0x13, 0x8, 0x41, 0x12, 0x1, 0x1b},
+	{980000000, 0xa3, 0x55, 0x1, 0xb, 0x1b, 0x13, 0x8, 0x42, 0x12, 0x1, 0x1b},
+	{990000000, 0xa5, 0x0, 0x1, 0xb, 0x1b, 0x13, 0x8, 0x42, 0x12, 0x1, 0x1b},
+	{1000000000, 0xa6, 0xaa, 0x1, 0xb, 0x1c, 0x13, 0x9, 0x42, 0x12, 0x1, 0x1b},
+};
+
+struct stf_dphy_info {
+	/**
+	 * @maps:
+	 *
+	 * Physical lanes and logic lanes mapping table.
+	 *
+	 * The default order is:
+	 * [data lane 0, data lane 1, data lane 2, date lane 3, clk lane]
+	 */
+	u8 maps[STF_MAP_LANES_NUM];
+};
+
+struct stf_dphy {
+	struct device *dev;
+	void __iomem *topsys;
+	struct clk *txesc_clk;
+	struct reset_control *sys_rst;
+
+	struct phy_configure_opts_mipi_dphy config;
+
+	struct phy *phy;
+	const struct stf_dphy_info *info;
+};
+
+static u32 stf_dphy_get_config_index(u32 bitrate)
+{
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(reg_configs); i++) {
+		if (reg_configs[i].bitrate == bitrate)
+			return i;
+	}
+
+	return 0;
+}
+
+static void stf_dphy_hw_reset(struct stf_dphy *dphy, int assert)
+{
+	int rc;
+	u32 status = 0;
+
+	writel(FIELD_PREP(STF_DPHY_RESETB, assert),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(100));
+
+	if (assert) {
+		rc = readl_poll_timeout_atomic(dphy->topsys +
+					       STF_DPHY_APBIFSAIF_SYSCFG(8),
+					       status,
+					       !(FIELD_GET(STF_DPHY_RGS_CDTX_PLL_UNLOCK, status)),
+					       STF_DPHY_HW_DELAY_US, STF_DPHY_HW_TIMEOUT_US);
+		if (rc)
+			dev_err(dphy->dev, "MIPI dphy-tx # PLL Locked\n");
+	}
+}
+
+static int stf_dphy_configure(struct phy *phy, union phy_configure_opts *opts)
+{
+	struct stf_dphy *dphy = phy_get_drvdata(phy);
+	const struct stf_dphy_info *info = dphy->info;
+	const struct stf_dphy_config *p = reg_configs;
+	unsigned long alignment  = STF_DPHY_BITRATE_ALIGN;
+	u32 bitrate = opts->mipi_dphy.hs_clk_rate;
+	u32 tmp;
+	u32 i;
+
+	if (bitrate % alignment)
+		bitrate += alignment - (bitrate % alignment);
+
+	i = stf_dphy_get_config_index(bitrate);
+
+	tmp = readl(dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(100));
+	tmp &= ~STF_DPHY_REFCLK_IN_SEL;
+	tmp |= FIELD_PREP(STF_DPHY_REFCLK_IN_SEL, STF_DPHY_REFCLK_12M);
+	writel(tmp, dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(100));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_L0N_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L0P_HSTX_RES, 0x10),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(8));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_L0N_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L2N_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L3N_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L1P_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L2P_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L3P_HSTX_RES, 0x10),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(12));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_L4N_HSTX_RES, 0x10) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_L4P_HSTX_RES, 0x10),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(16));
+
+	/* Lane setting */
+	writel(FIELD_PREP(STF_DPHY_AON_POWER_READY_N,
+			  STF_DPHY_AON_POWER_READY_N_ACTIVE) |
+	       FIELD_PREP(STF_DPHY_CFG_L0_SWAP_SEL, info->maps[0]) |
+	       FIELD_PREP(STF_DPHY_CFG_L1_SWAP_SEL, info->maps[1]) |
+	       FIELD_PREP(STF_DPHY_CFG_L2_SWAP_SEL, info->maps[2]) |
+	       FIELD_PREP(STF_DPHY_CFG_L3_SWAP_SEL, info->maps[3]) |
+	       FIELD_PREP(STF_DPHY_CFG_L4_SWAP_SEL, info->maps[4]),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(0));
+
+	/* PLL setting */
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_PLL_SSC_EN, 0x0),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(28));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_PLL_LDO_STB_X2_EN, 0x1) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_PLL_FM_EN, 0x1) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_PLL_PRE_DIV, 0x0) |
+	       FIELD_PREP(STF_DPHY_RG_CDTX_PLL_FBK_INT, p[i].pll_fbk_int),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(24));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CDTX_PLL_FBK_FRA,
+			  STF_DPHY_LSHIFT_16(p[i].pll_fbk_fra_val) |
+			  STF_DPHY_LSHIFT_8(p[i].pll_fbk_fra_val) |
+			  p[i].pll_fbk_fra_val),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(20));
+
+	writel(FIELD_PREP(STF_DPHY_RG_EXTD_CYCLE_SEL, p[i].extd_cycle_sel),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(40));
+
+	writel(FIELD_PREP(STF_DPHY_RG_DLANE_HS_PRE_TIME,  p[i].dlane_hs_pre_time) |
+	       FIELD_PREP(STF_DPHY_RG_DLANE_HS_ZERO_TIME, p[i].dlane_hs_zero_time) |
+	       FIELD_PREP(STF_DPHY_RG_DLANE_HS_TRAIL_TIME, p[i].dlane_hs_trail_time) |
+	       FIELD_PREP(STF_DPHY_RG_CLANE_HS_ZERO_TIME, p[i].clane_hs_zero_time),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(36));
+
+	writel(FIELD_PREP(STF_DPHY_RG_CLANE_HS_PRE_TIME,  p[i].clane_hs_pre_time) |
+	       FIELD_PREP(STF_DPHY_RG_CLANE_HS_TRAIL_TIME, p[i].clane_hs_trail_time) |
+	       FIELD_PREP(STF_DPHY_RG_CLANE_HS_CLK_PRE_TIME, p[i].clane_hs_clk_pre_time) |
+	       FIELD_PREP(STF_DPHY_RG_CLANE_HS_CLK_POST_TIME, p[i].clane_hs_clk_post_time),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(32));
+
+	return 0;
+}
+
+static int stf_dphy_init(struct phy *phy)
+{
+	struct stf_dphy *dphy = phy_get_drvdata(phy);
+	int ret;
+
+	stf_dphy_hw_reset(dphy, 1);
+
+	writel(FIELD_PREP(STF_DPHY_SCFG_PPI_C_READY_SEL, 0) |
+	       FIELD_PREP(STF_DPHY_SCFG_DSI_TXREADY_ESC_SEL, 0),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(48));
+
+	writel(FIELD_PREP(STF_DPHY_SCFG_C_HS_PRE_ZERO_TIME, 0x30),
+	       dphy->topsys + STF_DPHY_APBIFSAIF_SYSCFG(44));
+
+	ret = clk_prepare_enable(dphy->txesc_clk);
+	if (ret) {
+		dev_err(dphy->dev, "Failed to prepare/enable txesc_clk\n");
+		return ret;
+	}
+
+	ret = reset_control_deassert(dphy->sys_rst);
+	if (ret) {
+		dev_err(dphy->dev, "Failed to deassert sys_rst\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int stf_dphy_exit(struct phy *phy)
+{
+	struct stf_dphy *dphy = phy_get_drvdata(phy);
+	int ret;
+
+	ret = reset_control_assert(dphy->sys_rst);
+	if (ret) {
+		dev_err(dphy->dev, "Failed to assert sys_rst\n");
+		return ret;
+	}
+
+	clk_disable_unprepare(dphy->txesc_clk);
+
+	stf_dphy_hw_reset(dphy, 0);
+
+	return 0;
+}
+
+static int stf_dphy_power_on(struct phy *phy)
+{
+	struct stf_dphy *dphy = phy_get_drvdata(phy);
+
+	return pm_runtime_resume_and_get(dphy->dev);
+}
+
+static int stf_dphy_validate(struct phy *phy, enum phy_mode mode, int submode,
+			     union phy_configure_opts *opts)
+{
+	if (mode != PHY_MODE_MIPI_DPHY)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int stf_dphy_power_off(struct phy *phy)
+{
+	struct stf_dphy *dphy = phy_get_drvdata(phy);
+
+	return pm_runtime_put_sync(dphy->dev);
+}
+
+static const struct phy_ops stf_dphy_ops = {
+	.power_on	= stf_dphy_power_on,
+	.power_off	= stf_dphy_power_off,
+	.init		= stf_dphy_init,
+	.exit		= stf_dphy_exit,
+	.configure	= stf_dphy_configure,
+	.validate	= stf_dphy_validate,
+	.owner		= THIS_MODULE,
+};
+
+static int stf_dphy_probe(struct platform_device *pdev)
+{
+	struct phy_provider *phy_provider;
+	struct stf_dphy *dphy;
+
+	dphy = devm_kzalloc(&pdev->dev, sizeof(*dphy), GFP_KERNEL);
+	if (!dphy)
+		return -ENOMEM;
+
+	dphy->info = of_device_get_match_data(&pdev->dev);
+
+	dphy->dev = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, dphy);
+
+	dphy->topsys = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(dphy->topsys))
+		return PTR_ERR(dphy->topsys);
+
+	pm_runtime_enable(&pdev->dev);
+
+	dphy->txesc_clk = devm_clk_get(&pdev->dev, "txesc");
+	if (IS_ERR(dphy->txesc_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(dphy->txesc_clk),
+				     "Failed to get txesc clock\n");
+
+	dphy->sys_rst = devm_reset_control_get_exclusive(&pdev->dev, "sys");
+	if (IS_ERR(dphy->sys_rst))
+		return dev_err_probe(&pdev->dev, PTR_ERR(dphy->sys_rst),
+				     "Failed to get sys reset\n");
+
+	dphy->phy = devm_phy_create(&pdev->dev, NULL, &stf_dphy_ops);
+	if (IS_ERR(dphy->phy))
+		return dev_err_probe(&pdev->dev, PTR_ERR(dphy->phy),
+				     "Failed to create phy\n");
+
+	phy_set_drvdata(dphy->phy, dphy);
+
+	phy_provider = devm_of_phy_provider_register(&pdev->dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return dev_err_probe(&pdev->dev, PTR_ERR(phy_provider),
+				     "Failed to register phy\n");
+
+	return 0;
+}
+
+static const struct stf_dphy_info starfive_dphy_info = {
+	.maps = {0, 1, 2, 3, 4},
+};
+
+static const struct of_device_id stf_dphy_dt_ids[] = {
+	{
+		.compatible = "starfive,jh7110-dphy-tx",
+		.data = &starfive_dphy_info,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, stf_dphy_dt_ids);
+
+static struct platform_driver stf_dphy_driver = {
+	.driver = {
+		.name	= "starfive-dphy-tx",
+		.of_match_table = stf_dphy_dt_ids,
+	},
+	.probe = stf_dphy_probe,
+};
+module_platform_driver(stf_dphy_driver);
+
+MODULE_AUTHOR("Keith Zhao <keith.zhao@starfivetech.com>");
+MODULE_AUTHOR("Shengyang Chen <shengyang.chen@starfivetech.com>");
+MODULE_DESCRIPTION("StarFive JH7110 DPHY TX driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c
index 8b3b937..6734496 100644
--- a/drivers/phy/ti/phy-am654-serdes.c
+++ b/drivers/phy/ti/phy-am654-serdes.c
@@ -30,7 +30,6 @@
 #define LANE_R058		0x258
 #define LANE_R06c		0x26c
 #define LANE_R070		0x270
-#define LANE_R070		0x270
 #define LANE_R19C		0x39c
 
 #define COMLANE_R004		0xa04
diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index 00d7e6a..7f626c5 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1076,27 +1076,12 @@ static int wiz_clock_register(struct wiz *wiz)
 	return ret;
 }
 
-static int wiz_clock_init(struct wiz *wiz, struct device_node *node)
+static void wiz_clock_init(struct wiz *wiz)
 {
-	const struct wiz_clk_mux_sel *clk_mux_sel = wiz->clk_mux_sel;
-	struct device *dev = wiz->dev;
-	struct device_node *clk_node;
-	const char *node_name;
 	unsigned long rate;
-	struct clk *clk;
-	int ret;
-	int i;
 
-	clk = devm_clk_get(dev, "core_ref_clk");
-	if (IS_ERR(clk)) {
-		dev_err(dev, "core_ref_clk clock not found\n");
-		ret = PTR_ERR(clk);
-		return ret;
-	}
-	wiz->input_clks[WIZ_CORE_REFCLK] = clk;
-
-	rate = clk_get_rate(clk);
-	if (rate >= 100000000)
+	rate = clk_get_rate(wiz->input_clks[WIZ_CORE_REFCLK]);
+	if (rate >= REF_CLK_100MHZ)
 		regmap_field_write(wiz->pma_cmn_refclk_int_mode, 0x1);
 	else
 		regmap_field_write(wiz->pma_cmn_refclk_int_mode, 0x3);
@@ -1120,35 +1105,55 @@ static int wiz_clock_init(struct wiz *wiz, struct device_node *node)
 		break;
 	}
 
-	if (wiz->data->pma_cmn_refclk1_int_mode) {
-		clk = devm_clk_get(dev, "core_ref1_clk");
-		if (IS_ERR(clk)) {
-			dev_err(dev, "core_ref1_clk clock not found\n");
-			ret = PTR_ERR(clk);
-			return ret;
-		}
-		wiz->input_clks[WIZ_CORE_REFCLK1] = clk;
-
-		rate = clk_get_rate(clk);
-		if (rate >= 100000000)
+	if (wiz->input_clks[WIZ_CORE_REFCLK1]) {
+		rate = clk_get_rate(wiz->input_clks[WIZ_CORE_REFCLK1]);
+		if (rate >= REF_CLK_100MHZ)
 			regmap_field_write(wiz->pma_cmn_refclk1_int_mode, 0x1);
 		else
 			regmap_field_write(wiz->pma_cmn_refclk1_int_mode, 0x3);
 	}
 
-	clk = devm_clk_get(dev, "ext_ref_clk");
-	if (IS_ERR(clk)) {
-		dev_err(dev, "ext_ref_clk clock not found\n");
-		ret = PTR_ERR(clk);
-		return ret;
-	}
-	wiz->input_clks[WIZ_EXT_REFCLK] = clk;
-
-	rate = clk_get_rate(clk);
-	if (rate >= 100000000)
+	rate = clk_get_rate(wiz->input_clks[WIZ_EXT_REFCLK]);
+	if (rate >= REF_CLK_100MHZ)
 		regmap_field_write(wiz->pma_cmn_refclk_mode, 0x0);
 	else
 		regmap_field_write(wiz->pma_cmn_refclk_mode, 0x2);
+}
+
+static int wiz_clock_probe(struct wiz *wiz, struct device_node *node)
+{
+	const struct wiz_clk_mux_sel *clk_mux_sel = wiz->clk_mux_sel;
+	struct device *dev = wiz->dev;
+	struct device_node *clk_node;
+	const char *node_name;
+	struct clk *clk;
+	int ret;
+	int i;
+
+	clk = devm_clk_get(dev, "core_ref_clk");
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk),
+				     "core_ref_clk clock not found\n");
+
+	wiz->input_clks[WIZ_CORE_REFCLK] = clk;
+
+	if (wiz->data->pma_cmn_refclk1_int_mode) {
+		clk = devm_clk_get(dev, "core_ref1_clk");
+		if (IS_ERR(clk))
+			return dev_err_probe(dev, PTR_ERR(clk),
+					     "core_ref1_clk clock not found\n");
+
+		wiz->input_clks[WIZ_CORE_REFCLK1] = clk;
+	}
+
+	clk = devm_clk_get(dev, "ext_ref_clk");
+	if (IS_ERR(clk))
+		return dev_err_probe(dev, PTR_ERR(clk),
+				     "ext_ref_clk clock not found\n");
+
+	wiz->input_clks[WIZ_EXT_REFCLK] = clk;
+
+	wiz_clock_init(wiz);
 
 	switch (wiz->type) {
 	case AM64_WIZ_10G:
@@ -1157,8 +1162,9 @@ static int wiz_clock_init(struct wiz *wiz, struct device_node *node)
 	case J721S2_WIZ_10G:
 		ret = wiz_clock_register(wiz);
 		if (ret)
-			dev_err(dev, "Failed to register wiz clocks\n");
-		return ret;
+			return dev_err_probe(dev, ret, "Failed to register wiz clocks\n");
+
+		return 0;
 	default:
 		break;
 	}
@@ -1167,16 +1173,15 @@ static int wiz_clock_init(struct wiz *wiz, struct device_node *node)
 		node_name = clk_mux_sel[i].node_name;
 		clk_node = of_get_child_by_name(node, node_name);
 		if (!clk_node) {
-			dev_err(dev, "Unable to get %s node\n", node_name);
-			ret = -EINVAL;
+			ret = dev_err_probe(dev, -EINVAL, "Unable to get %s node\n", node_name);
 			goto err;
 		}
 
 		ret = wiz_mux_of_clk_register(wiz, clk_node, wiz->mux_sel_field[i],
 					      clk_mux_sel[i].table);
 		if (ret) {
-			dev_err(dev, "Failed to register %s clock\n",
-				node_name);
+			dev_err_probe(dev, ret, "Failed to register %s clock\n",
+				      node_name);
 			of_node_put(clk_node);
 			goto err;
 		}
@@ -1188,16 +1193,15 @@ static int wiz_clock_init(struct wiz *wiz, struct device_node *node)
 		node_name = clk_div_sel[i].node_name;
 		clk_node = of_get_child_by_name(node, node_name);
 		if (!clk_node) {
-			dev_err(dev, "Unable to get %s node\n", node_name);
-			ret = -EINVAL;
+			ret = dev_err_probe(dev, -EINVAL, "Unable to get %s node\n", node_name);
 			goto err;
 		}
 
 		ret = wiz_div_clk_register(wiz, clk_node, wiz->div_sel_field[i],
 					   clk_div_sel[i].table);
 		if (ret) {
-			dev_err(dev, "Failed to register %s clock\n",
-				node_name);
+			dev_err_probe(dev, ret, "Failed to register %s clock\n",
+				      node_name);
 			of_node_put(clk_node);
 			goto err;
 		}
@@ -1593,7 +1597,7 @@ static int wiz_probe(struct platform_device *pdev)
 		goto err_get_sync;
 	}
 
-	ret = wiz_clock_init(wiz, node);
+	ret = wiz_clock_probe(wiz, node);
 	if (ret < 0) {
 		dev_warn(dev, "Failed to initialize clocks\n");
 		goto err_get_sync;
@@ -1655,12 +1659,41 @@ static void wiz_remove(struct platform_device *pdev)
 	pm_runtime_disable(dev);
 }
 
+static int wiz_resume_noirq(struct device *dev)
+{
+	struct device_node *node = dev->of_node;
+	struct wiz *wiz = dev_get_drvdata(dev);
+	int ret;
+
+	/* Enable supplemental Control override if available */
+	if (wiz->sup_legacy_clk_override)
+		regmap_field_write(wiz->sup_legacy_clk_override, 1);
+
+	wiz_clock_init(wiz);
+
+	ret = wiz_init(wiz);
+	if (ret) {
+		dev_err(dev, "WIZ initialization failed\n");
+		goto err_wiz_init;
+	}
+
+	return 0;
+
+err_wiz_init:
+	wiz_clock_cleanup(wiz, node);
+
+	return ret;
+}
+
+static DEFINE_NOIRQ_DEV_PM_OPS(wiz_pm_ops, NULL, wiz_resume_noirq);
+
 static struct platform_driver wiz_driver = {
 	.probe		= wiz_probe,
 	.remove_new	= wiz_remove,
 	.driver		= {
 		.name	= "wiz",
 		.of_match_table = wiz_id_table,
+		.pm	= pm_sleep_ptr(&wiz_pm_ops),
 	},
 };
 module_platform_driver(wiz_driver);
diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
index dc8319b..cb15041 100644
--- a/drivers/phy/xilinx/phy-zynqmp.c
+++ b/drivers/phy/xilinx/phy-zynqmp.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -80,7 +81,8 @@
 
 /* Reference clock selection parameters */
 #define L0_Ln_REF_CLK_SEL(n)		(0x2860 + (n) * 4)
-#define L0_REF_CLK_SEL_MASK		0x8f
+#define L0_REF_CLK_LCL_SEL		BIT(7)
+#define L0_REF_CLK_SEL_MASK		0x9f
 
 /* Calibration digital logic parameters */
 #define L3_TM_CALIB_DIG19		0xec4c
@@ -122,6 +124,15 @@
 #define ICM_PROTOCOL_DP			0x4
 #define ICM_PROTOCOL_SGMII		0x5
 
+static const char *const xpsgtr_icm_str[] = {
+	[ICM_PROTOCOL_PD] = "none",
+	[ICM_PROTOCOL_PCIE] = "PCIe",
+	[ICM_PROTOCOL_SATA] = "SATA",
+	[ICM_PROTOCOL_USB] = "USB",
+	[ICM_PROTOCOL_DP] = "DisplayPort",
+	[ICM_PROTOCOL_SGMII] = "SGMII",
+};
+
 /* Test Mode common reset control  parameters */
 #define TM_CMN_RST			0x10018
 #define TM_CMN_RST_EN			0x1
@@ -146,22 +157,6 @@
 /* Total number of controllers */
 #define CONTROLLERS_PER_LANE		5
 
-/* Protocol Type parameters */
-#define XPSGTR_TYPE_USB0		0  /* USB controller 0 */
-#define XPSGTR_TYPE_USB1		1  /* USB controller 1 */
-#define XPSGTR_TYPE_SATA_0		2  /* SATA controller lane 0 */
-#define XPSGTR_TYPE_SATA_1		3  /* SATA controller lane 1 */
-#define XPSGTR_TYPE_PCIE_0		4  /* PCIe controller lane 0 */
-#define XPSGTR_TYPE_PCIE_1		5  /* PCIe controller lane 1 */
-#define XPSGTR_TYPE_PCIE_2		6  /* PCIe controller lane 2 */
-#define XPSGTR_TYPE_PCIE_3		7  /* PCIe controller lane 3 */
-#define XPSGTR_TYPE_DP_0		8  /* Display Port controller lane 0 */
-#define XPSGTR_TYPE_DP_1		9  /* Display Port controller lane 1 */
-#define XPSGTR_TYPE_SGMII0		10 /* Ethernet SGMII controller 0 */
-#define XPSGTR_TYPE_SGMII1		11 /* Ethernet SGMII controller 1 */
-#define XPSGTR_TYPE_SGMII2		12 /* Ethernet SGMII controller 2 */
-#define XPSGTR_TYPE_SGMII3		13 /* Ethernet SGMII controller 3 */
-
 /* Timeout values */
 #define TIMEOUT_US			1000
 
@@ -184,7 +179,8 @@ struct xpsgtr_ssc {
 /**
  * struct xpsgtr_phy - representation of a lane
  * @phy: pointer to the kernel PHY device
- * @type: controller which uses this lane
+ * @instance: instance of the protocol type (such as the lane within a
+ *            protocol, or the USB/Ethernet controller)
  * @lane: lane number
  * @protocol: protocol in which the lane operates
  * @skip_phy_init: skip phy_init() if true
@@ -193,7 +189,7 @@ struct xpsgtr_ssc {
  */
 struct xpsgtr_phy {
 	struct phy *phy;
-	u8 type;
+	u8 instance;
 	u8 lane;
 	u8 protocol;
 	bool skip_phy_init;
@@ -308,10 +304,30 @@ static int xpsgtr_wait_pll_lock(struct phy *phy)
 	struct xpsgtr_phy *gtr_phy = phy_get_drvdata(phy);
 	struct xpsgtr_dev *gtr_dev = gtr_phy->dev;
 	unsigned int timeout = TIMEOUT_US;
+	u8 protocol = gtr_phy->protocol;
 	int ret;
 
 	dev_dbg(gtr_dev->dev, "Waiting for PLL lock\n");
 
+	/*
+	 * For DP and PCIe, only the instance 0 PLL is used. Switch to that phy
+	 * so we wait on the right PLL.
+	 */
+	if ((protocol == ICM_PROTOCOL_DP || protocol == ICM_PROTOCOL_PCIE) &&
+	    gtr_phy->instance) {
+		int i;
+
+		for (i = 0; i < NUM_LANES; i++) {
+			gtr_phy = &gtr_dev->phys[i];
+
+			if (gtr_phy->protocol == protocol && !gtr_phy->instance)
+				goto got_phy;
+		}
+
+		return -EBUSY;
+	}
+
+got_phy:
 	while (1) {
 		u32 reg = xpsgtr_read_phy(gtr_phy, L0_PLL_STATUS_READ_1);
 
@@ -330,8 +346,8 @@ static int xpsgtr_wait_pll_lock(struct phy *phy)
 
 	if (ret == -ETIMEDOUT)
 		dev_err(gtr_dev->dev,
-			"lane %u (type %u, protocol %u): PLL lock timeout\n",
-			gtr_phy->lane, gtr_phy->type, gtr_phy->protocol);
+			"lane %u (protocol %u, instance %u): PLL lock timeout\n",
+			gtr_phy->lane, gtr_phy->protocol, gtr_phy->instance);
 
 	return ret;
 }
@@ -349,11 +365,12 @@ static void xpsgtr_configure_pll(struct xpsgtr_phy *gtr_phy)
 		       PLL_FREQ_MASK, ssc->pll_ref_clk);
 
 	/* Enable lane clock sharing, if required */
-	if (gtr_phy->refclk != gtr_phy->lane) {
-		/* Lane3 Ref Clock Selection Register */
+	if (gtr_phy->refclk == gtr_phy->lane)
+		xpsgtr_clr_set(gtr_phy->dev, L0_Ln_REF_CLK_SEL(gtr_phy->lane),
+			       L0_REF_CLK_SEL_MASK, L0_REF_CLK_LCL_SEL);
+	else
 		xpsgtr_clr_set(gtr_phy->dev, L0_Ln_REF_CLK_SEL(gtr_phy->lane),
 			       L0_REF_CLK_SEL_MASK, 1 << gtr_phy->refclk);
-	}
 
 	/* SSC step size [7:0] */
 	xpsgtr_clr_set_phy(gtr_phy, L0_PLL_SS_STEP_SIZE_0_LSB,
@@ -573,7 +590,7 @@ static int xpsgtr_phy_init(struct phy *phy)
 	mutex_lock(&gtr_dev->gtr_mutex);
 
 	/* Configure and enable the clock when peripheral phy_init call */
-	if (clk_prepare_enable(gtr_dev->clk[gtr_phy->lane]))
+	if (clk_prepare_enable(gtr_dev->clk[gtr_phy->refclk]))
 		goto out;
 
 	/* Skip initialization if not required. */
@@ -625,7 +642,7 @@ static int xpsgtr_phy_exit(struct phy *phy)
 	gtr_phy->skip_phy_init = false;
 
 	/* Ensure that disable clock only, which configure for lane */
-	clk_disable_unprepare(gtr_dev->clk[gtr_phy->lane]);
+	clk_disable_unprepare(gtr_dev->clk[gtr_phy->refclk]);
 
 	return 0;
 }
@@ -638,16 +655,7 @@ static int xpsgtr_phy_power_on(struct phy *phy)
 	/* Skip initialization if not required. */
 	if (!xpsgtr_phy_init_required(gtr_phy))
 		return ret;
-	/*
-	 * Wait for the PLL to lock. For DP, only wait on DP0 to avoid
-	 * cumulating waits for both lanes. The user is expected to initialize
-	 * lane 0 last.
-	 */
-	if (gtr_phy->protocol != ICM_PROTOCOL_DP ||
-	    gtr_phy->type == XPSGTR_TYPE_DP_0)
-		ret = xpsgtr_wait_pll_lock(phy);
-
-	return ret;
+	return xpsgtr_wait_pll_lock(phy);
 }
 
 static int xpsgtr_phy_configure(struct phy *phy, union phy_configure_opts *opts)
@@ -674,73 +682,33 @@ static const struct phy_ops xpsgtr_phyops = {
  * OF Xlate Support
  */
 
-/* Set the lane type and protocol based on the PHY type and instance number. */
+/* Set the lane protocol and instance based on the PHY type and instance number. */
 static int xpsgtr_set_lane_type(struct xpsgtr_phy *gtr_phy, u8 phy_type,
 				unsigned int phy_instance)
 {
 	unsigned int num_phy_types;
-	const int *phy_types;
 
 	switch (phy_type) {
-	case PHY_TYPE_SATA: {
-		static const int types[] = {
-			XPSGTR_TYPE_SATA_0,
-			XPSGTR_TYPE_SATA_1,
-		};
-
-		phy_types = types;
-		num_phy_types = ARRAY_SIZE(types);
+	case PHY_TYPE_SATA:
+		num_phy_types = 2;
 		gtr_phy->protocol = ICM_PROTOCOL_SATA;
 		break;
-	}
-	case PHY_TYPE_USB3: {
-		static const int types[] = {
-			XPSGTR_TYPE_USB0,
-			XPSGTR_TYPE_USB1,
-		};
-
-		phy_types = types;
-		num_phy_types = ARRAY_SIZE(types);
+	case PHY_TYPE_USB3:
+		num_phy_types = 2;
 		gtr_phy->protocol = ICM_PROTOCOL_USB;
 		break;
-	}
-	case PHY_TYPE_DP: {
-		static const int types[] = {
-			XPSGTR_TYPE_DP_0,
-			XPSGTR_TYPE_DP_1,
-		};
-
-		phy_types = types;
-		num_phy_types = ARRAY_SIZE(types);
+	case PHY_TYPE_DP:
+		num_phy_types = 2;
 		gtr_phy->protocol = ICM_PROTOCOL_DP;
 		break;
-	}
-	case PHY_TYPE_PCIE: {
-		static const int types[] = {
-			XPSGTR_TYPE_PCIE_0,
-			XPSGTR_TYPE_PCIE_1,
-			XPSGTR_TYPE_PCIE_2,
-			XPSGTR_TYPE_PCIE_3,
-		};
-
-		phy_types = types;
-		num_phy_types = ARRAY_SIZE(types);
+	case PHY_TYPE_PCIE:
+		num_phy_types = 4;
 		gtr_phy->protocol = ICM_PROTOCOL_PCIE;
 		break;
-	}
-	case PHY_TYPE_SGMII: {
-		static const int types[] = {
-			XPSGTR_TYPE_SGMII0,
-			XPSGTR_TYPE_SGMII1,
-			XPSGTR_TYPE_SGMII2,
-			XPSGTR_TYPE_SGMII3,
-		};
-
-		phy_types = types;
-		num_phy_types = ARRAY_SIZE(types);
+	case PHY_TYPE_SGMII:
+		num_phy_types = 4;
 		gtr_phy->protocol = ICM_PROTOCOL_SGMII;
 		break;
-	}
 	default:
 		return -EINVAL;
 	}
@@ -748,22 +716,25 @@ static int xpsgtr_set_lane_type(struct xpsgtr_phy *gtr_phy, u8 phy_type,
 	if (phy_instance >= num_phy_types)
 		return -EINVAL;
 
-	gtr_phy->type = phy_types[phy_instance];
+	gtr_phy->instance = phy_instance;
 	return 0;
 }
 
 /*
- * Valid combinations of controllers and lanes (Interconnect Matrix).
+ * Valid combinations of controllers and lanes (Interconnect Matrix). Each
+ * "instance" represents one controller for a lane. For PCIe and DP, the
+ * "instance" is the logical lane in the link. For SATA, USB, and SGMII,
+ * the instance is the index of the controller.
+ *
+ * This information is only used to validate the devicetree reference, and is
+ * not used when programming the hardware.
  */
 static const unsigned int icm_matrix[NUM_LANES][CONTROLLERS_PER_LANE] = {
-	{ XPSGTR_TYPE_PCIE_0, XPSGTR_TYPE_SATA_0, XPSGTR_TYPE_USB0,
-		XPSGTR_TYPE_DP_1, XPSGTR_TYPE_SGMII0 },
-	{ XPSGTR_TYPE_PCIE_1, XPSGTR_TYPE_SATA_1, XPSGTR_TYPE_USB0,
-		XPSGTR_TYPE_DP_0, XPSGTR_TYPE_SGMII1 },
-	{ XPSGTR_TYPE_PCIE_2, XPSGTR_TYPE_SATA_0, XPSGTR_TYPE_USB0,
-		XPSGTR_TYPE_DP_1, XPSGTR_TYPE_SGMII2 },
-	{ XPSGTR_TYPE_PCIE_3, XPSGTR_TYPE_SATA_1, XPSGTR_TYPE_USB1,
-		XPSGTR_TYPE_DP_0, XPSGTR_TYPE_SGMII3 }
+	/* PCIe, SATA, USB, DP, SGMII */
+	{ 0, 0, 0, 1, 0 }, /* Lane 0 */
+	{ 1, 1, 0, 0, 1 }, /* Lane 1 */
+	{ 2, 0, 0, 1, 2 }, /* Lane 2 */
+	{ 3, 1, 1, 0, 3 }, /* Lane 3 */
 };
 
 /* Translate OF phandle and args to PHY instance. */
@@ -798,6 +769,7 @@ static struct phy *xpsgtr_xlate(struct device *dev,
 	phy_type = args->args[1];
 	phy_instance = args->args[2];
 
+	guard(mutex)(&gtr_phy->phy->mutex);
 	ret = xpsgtr_set_lane_type(gtr_phy, phy_type, phy_instance);
 	if (ret < 0) {
 		dev_err(gtr_dev->dev, "Invalid PHY type and/or instance\n");
@@ -818,7 +790,7 @@ static struct phy *xpsgtr_xlate(struct device *dev,
 	 * is allowed to operate on the lane.
 	 */
 	for (i = 0; i < CONTROLLERS_PER_LANE; i++) {
-		if (icm_matrix[phy_lane][i] == gtr_phy->type)
+		if (icm_matrix[phy_lane][i] == gtr_phy->instance)
 			return gtr_phy->phy;
 	}
 
@@ -826,6 +798,34 @@ static struct phy *xpsgtr_xlate(struct device *dev,
 }
 
 /*
+ * DebugFS
+ */
+
+static int xpsgtr_status_read(struct seq_file *seq, void *data)
+{
+	struct device *dev = seq->private;
+	struct xpsgtr_phy *gtr_phy = dev_get_drvdata(dev);
+	struct clk *clk;
+	u32 pll_status;
+
+	mutex_lock(&gtr_phy->phy->mutex);
+	pll_status = xpsgtr_read_phy(gtr_phy, L0_PLL_STATUS_READ_1);
+	clk = gtr_phy->dev->clk[gtr_phy->refclk];
+
+	seq_printf(seq, "Lane:            %u\n", gtr_phy->lane);
+	seq_printf(seq, "Protocol:        %s\n",
+		   xpsgtr_icm_str[gtr_phy->protocol]);
+	seq_printf(seq, "Instance:        %u\n", gtr_phy->instance);
+	seq_printf(seq, "Reference clock: %u (%pC)\n", gtr_phy->refclk, clk);
+	seq_printf(seq, "Reference rate:  %lu\n", clk_get_rate(clk));
+	seq_printf(seq, "PLL locked:      %s\n",
+		   pll_status & PLL_STATUS_LOCKED ? "yes" : "no");
+
+	mutex_unlock(&gtr_phy->phy->mutex);
+	return 0;
+}
+
+/*
  * Power Management
  */
 
@@ -974,6 +974,8 @@ static int xpsgtr_probe(struct platform_device *pdev)
 
 		gtr_phy->phy = phy;
 		phy_set_drvdata(phy, gtr_phy);
+		debugfs_create_devm_seqfile(&phy->dev, "status", phy->debugfs,
+					    xpsgtr_status_read);
 	}
 
 	/* Register the PHY provider. */
diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c
index df3e5d8..f2609a3 100644
--- a/drivers/pinctrl/nxp/pinctrl-s32cc.c
+++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c
@@ -730,9 +730,7 @@ static int s32_pinctrl_parse_groups(struct device_node *np,
 				     struct s32_pin_group *grp,
 				     struct s32_pinctrl_soc_info *info)
 {
-	const __be32 *p;
 	struct device *dev;
-	struct property *prop;
 	unsigned int *pins, *sss;
 	int i, npins;
 	u32 pinmux;
@@ -763,7 +761,7 @@ static int s32_pinctrl_parse_groups(struct device_node *np,
 		return -ENOMEM;
 
 	i = 0;
-	of_property_for_each_u32(np, "pinmux", prop, p, pinmux) {
+	of_property_for_each_u32(np, "pinmux", pinmux) {
 		pins[i] = get_pin_no(pinmux);
 		sss[i] = get_pin_func(pinmux);
 
diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c
index 2753e14..a898e40 100644
--- a/drivers/pinctrl/pinctrl-k210.c
+++ b/drivers/pinctrl/pinctrl-k210.c
@@ -763,8 +763,6 @@ static int k210_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 					  unsigned int *reserved_maps,
 					  unsigned int *num_maps)
 {
-	struct property *prop;
-	const __be32 *p;
 	int ret, pinmux_groups;
 	u32 pinmux_group;
 	unsigned long *configs = NULL;
@@ -797,7 +795,7 @@ static int k210_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 	if (ret < 0)
 		goto exit;
 
-	of_property_for_each_u32(np, "pinmux", prop, p, pinmux_group) {
+	of_property_for_each_u32(np, "pinmux", pinmux_group) {
 		const char *group_name, *func_name;
 		u32 pin = FIELD_GET(K210_PG_PIN, pinmux_group);
 		u32 func = FIELD_GET(K210_PG_FUNC, pinmux_group);
diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c
index 118caa6..af8d573 100644
--- a/drivers/platform/surface/aggregator/bus.c
+++ b/drivers/platform/surface/aggregator/bus.c
@@ -306,9 +306,9 @@ const void *ssam_device_get_match_data(const struct ssam_device *dev)
 }
 EXPORT_SYMBOL_GPL(ssam_device_get_match_data);
 
-static int ssam_bus_match(struct device *dev, struct device_driver *drv)
+static int ssam_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct ssam_device_driver *sdrv = to_ssam_device_driver(drv);
+	const struct ssam_device_driver *sdrv = to_ssam_device_driver(drv);
 	struct ssam_device *sdev = to_ssam_device(dev);
 
 	if (!is_ssam_device(dev))
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 6bfae28..1d0b2d6 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -727,10 +727,7 @@ char *wmi_get_acpi_device_uid(const char *guid_string)
 }
 EXPORT_SYMBOL_GPL(wmi_get_acpi_device_uid);
 
-static inline struct wmi_driver *drv_to_wdrv(struct device_driver *drv)
-{
-	return container_of(drv, struct wmi_driver, driver);
-}
+#define drv_to_wdrv(__drv)	container_of_const(__drv, struct wmi_driver, driver)
 
 /*
  * sysfs interface
@@ -877,9 +874,9 @@ static void wmi_dev_release(struct device *dev)
 	kfree(wblock);
 }
 
-static int wmi_dev_match(struct device *dev, struct device_driver *driver)
+static int wmi_dev_match(struct device *dev, const struct device_driver *driver)
 {
-	struct wmi_driver *wmi_driver = drv_to_wdrv(driver);
+	const struct wmi_driver *wmi_driver = drv_to_wdrv(driver);
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	const struct wmi_device_id *id = wmi_driver->id_table;
 
diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 3483e52..7de7aab 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -41,7 +41,7 @@ int compare_pnp_id(struct pnp_id *pos, const char *id)
 	return 0;
 }
 
-static const struct pnp_device_id *match_device(struct pnp_driver *drv,
+static const struct pnp_device_id *match_device(const struct pnp_driver *drv,
 						struct pnp_dev *dev)
 {
 	const struct pnp_device_id *drv_id = drv->id_table;
@@ -150,10 +150,10 @@ static void pnp_device_shutdown(struct device *dev)
 		drv->shutdown(pnp_dev);
 }
 
-static int pnp_bus_match(struct device *dev, struct device_driver *drv)
+static int pnp_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct pnp_dev *pnp_dev = to_pnp_dev(dev);
-	struct pnp_driver *pnp_drv = to_pnp_driver(drv);
+	const struct pnp_driver *pnp_drv = to_pnp_driver(drv);
 
 	if (match_device(pnp_drv, pnp_dev) == NULL)
 		return 0;
diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
index 2f4b11b..791fdc9 100644
--- a/drivers/pps/clients/pps-gpio.c
+++ b/drivers/pps/clients/pps-gpio.c
@@ -220,7 +220,7 @@ static int pps_gpio_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int pps_gpio_remove(struct platform_device *pdev)
+static void pps_gpio_remove(struct platform_device *pdev)
 {
 	struct pps_gpio_device_data *data = platform_get_drvdata(pdev);
 
@@ -229,7 +229,6 @@ static int pps_gpio_remove(struct platform_device *pdev)
 	/* reset echo pin in any case */
 	gpiod_set_value(data->echo_pin, 0);
 	dev_info(&pdev->dev, "removed IRQ %d as PPS source\n", data->irq);
-	return 0;
 }
 
 static const struct of_device_id pps_gpio_dt_ids[] = {
@@ -240,7 +239,7 @@ MODULE_DEVICE_TABLE(of, pps_gpio_dt_ids);
 
 static struct platform_driver pps_gpio_driver = {
 	.probe		= pps_gpio_probe,
-	.remove		= pps_gpio_remove,
+	.remove_new	= pps_gpio_remove,
 	.driver		= {
 		.name	= PPS_GPIO_NAME,
 		.of_match_table	= pps_gpio_dt_ids,
diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index 7adf4f2..951b38f 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -510,8 +510,6 @@ static int pwm_samsung_parse_dt(struct pwm_chip *chip)
 	struct samsung_pwm_chip *our_chip = to_samsung_pwm_chip(chip);
 	struct device_node *np = pwmchip_parent(chip)->of_node;
 	const struct of_device_id *match;
-	struct property *prop;
-	const __be32 *cur;
 	u32 val;
 
 	match = of_match_node(samsung_pwm_matches, np);
@@ -520,7 +518,7 @@ static int pwm_samsung_parse_dt(struct pwm_chip *chip)
 
 	memcpy(&our_chip->variant, match->data, sizeof(our_chip->variant));
 
-	of_property_for_each_u32(np, "samsung,pwm-outputs", prop, cur, val) {
+	of_property_for_each_u32(np, "samsung,pwm-outputs", val) {
 		if (val >= SAMSUNG_PWM_NUM) {
 			dev_err(pwmchip_parent(chip),
 				"%s: invalid channel index in samsung,pwm-outputs property\n",
diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c
index 1b3b4c2..238250e 100644
--- a/drivers/rapidio/rio-driver.c
+++ b/drivers/rapidio/rio-driver.c
@@ -186,10 +186,10 @@ EXPORT_SYMBOL_GPL(rio_attach_device);
  *  there is a matching &struct rio_device_id or 0 if there is
  *  no match.
  */
-static int rio_match_bus(struct device *dev, struct device_driver *drv)
+static int rio_match_bus(struct device *dev, const struct device_driver *drv)
 {
 	struct rio_dev *rdev = to_rio_dev(dev);
-	struct rio_driver *rdrv = to_rio_driver(drv);
+	const struct rio_driver *rdrv = to_rio_driver(drv);
 	const struct rio_device_id *id = rdrv->id_table;
 	const struct rio_device_id *found_id;
 
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index e6a9027..4b411a0 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -1661,10 +1661,10 @@
 
 config REGULATOR_RZG2L_VBCTRL
 	tristate "Renesas RZ/G2L USB VBUS regulator driver"
-	depends on ARCH_RZG2L || COMPILE_TEST
+	depends on RESET_RZG2L_USBPHY_CTRL || COMPILE_TEST
 	depends on OF
 	select REGMAP_MMIO
-	default ARCH_RZG2L
+	default RESET_RZG2L_USBPHY_CTRL
 	help
 	  Support for VBUS regulators implemented on Renesas RZ/G2L SoCs.
 
diff --git a/drivers/reset/reset-meson-audio-arb.c b/drivers/reset/reset-meson-audio-arb.c
index 894ad9d..421ccb4 100644
--- a/drivers/reset/reset-meson-audio-arb.c
+++ b/drivers/reset/reset-meson-audio-arb.c
@@ -120,7 +120,7 @@ static const struct of_device_id meson_audio_arb_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, meson_audio_arb_of_match);
 
-static int meson_audio_arb_remove(struct platform_device *pdev)
+static void meson_audio_arb_remove(struct platform_device *pdev)
 {
 	struct meson_audio_arb_data *arb = platform_get_drvdata(pdev);
 
@@ -128,8 +128,6 @@ static int meson_audio_arb_remove(struct platform_device *pdev)
 	spin_lock(&arb->lock);
 	writel(0, arb->regs);
 	spin_unlock(&arb->lock);
-
-	return 0;
 }
 
 static int meson_audio_arb_probe(struct platform_device *pdev)
@@ -182,7 +180,7 @@ static int meson_audio_arb_probe(struct platform_device *pdev)
 
 static struct platform_driver meson_audio_arb_pdrv = {
 	.probe = meson_audio_arb_probe,
-	.remove = meson_audio_arb_remove,
+	.remove_new = meson_audio_arb_remove,
 	.driver = {
 		.name = "meson-audio-arb-reset",
 		.of_match_table = meson_audio_arb_of_match,
diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
index 255c894..1cd157f 100644
--- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c
+++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
@@ -192,7 +192,7 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev)
 	return error;
 }
 
-static int rzg2l_usbphy_ctrl_remove(struct platform_device *pdev)
+static void rzg2l_usbphy_ctrl_remove(struct platform_device *pdev)
 {
 	struct rzg2l_usbphy_ctrl_priv *priv = dev_get_drvdata(&pdev->dev);
 
@@ -200,8 +200,6 @@ static int rzg2l_usbphy_ctrl_remove(struct platform_device *pdev)
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(priv->rstc);
-
-	return 0;
 }
 
 static struct platform_driver rzg2l_usbphy_ctrl_driver = {
@@ -210,7 +208,7 @@ static struct platform_driver rzg2l_usbphy_ctrl_driver = {
 		.of_match_table	= rzg2l_usbphy_ctrl_match_table,
 	},
 	.probe	= rzg2l_usbphy_ctrl_probe,
-	.remove	= rzg2l_usbphy_ctrl_remove,
+	.remove_new = rzg2l_usbphy_ctrl_remove,
 };
 module_platform_driver(rzg2l_usbphy_ctrl_driver);
 
diff --git a/drivers/reset/reset-ti-sci.c b/drivers/reset/reset-ti-sci.c
index cc01fa5..d384da0 100644
--- a/drivers/reset/reset-ti-sci.c
+++ b/drivers/reset/reset-ti-sci.c
@@ -235,20 +235,18 @@ static int ti_sci_reset_probe(struct platform_device *pdev)
 	return reset_controller_register(&data->rcdev);
 }
 
-static int ti_sci_reset_remove(struct platform_device *pdev)
+static void ti_sci_reset_remove(struct platform_device *pdev)
 {
 	struct ti_sci_reset_data *data = platform_get_drvdata(pdev);
 
 	reset_controller_unregister(&data->rcdev);
 
 	idr_destroy(&data->idr);
-
-	return 0;
 }
 
 static struct platform_driver ti_sci_reset_driver = {
 	.probe = ti_sci_reset_probe,
-	.remove = ti_sci_reset_remove,
+	.remove_new = ti_sci_reset_remove,
 	.driver = {
 		.name = "ti-sci-reset",
 		.of_match_table = ti_sci_reset_of_match,
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index 0fa0826..712c06c 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -493,10 +493,10 @@ static inline int rpmsg_id_match(const struct rpmsg_device *rpdev,
 }
 
 /* match rpmsg channel and rpmsg driver */
-static int rpmsg_dev_match(struct device *dev, struct device_driver *drv)
+static int rpmsg_dev_match(struct device *dev, const struct device_driver *drv)
 {
 	struct rpmsg_device *rpdev = to_rpmsg_device(dev);
-	struct rpmsg_driver *rpdrv = to_rpmsg_driver(drv);
+	const struct rpmsg_driver *rpdrv = to_rpmsg_driver(drv);
 	const struct rpmsg_device_id *ids = rpdrv->id_table;
 	unsigned int i;
 
diff --git a/drivers/rpmsg/rpmsg_internal.h b/drivers/rpmsg/rpmsg_internal.h
index a3ba768..42c7007 100644
--- a/drivers/rpmsg/rpmsg_internal.h
+++ b/drivers/rpmsg/rpmsg_internal.h
@@ -16,7 +16,7 @@
 #include <linux/poll.h>
 
 #define to_rpmsg_device(d) container_of(d, struct rpmsg_device, dev)
-#define to_rpmsg_driver(d) container_of(d, struct rpmsg_driver, drv)
+#define to_rpmsg_driver(d) container_of_const(d, struct rpmsg_driver, drv)
 
 extern const struct class rpmsg_class;
 
diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig
index 8a03af5..80c4e51 100644
--- a/drivers/s390/char/Kconfig
+++ b/drivers/s390/char/Kconfig
@@ -96,7 +96,7 @@
 config S390_UV_UAPI
 	def_tristate m
 	prompt "Ultravisor userspace API"
-	depends on S390 && (KVM || PROTECTED_VIRTUALIZATION_GUEST)
+	depends on S390
 	help
 	  Selecting exposes parts of the UV interface to userspace
 	  by providing a misc character device at /dev/uv.
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 781f849..53b68f8 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -1354,10 +1354,10 @@ int sch_is_pseudo_sch(struct subchannel *sch)
 	return sch == to_css(sch->dev.parent)->pseudo_subchannel;
 }
 
-static int css_bus_match(struct device *dev, struct device_driver *drv)
+static int css_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct subchannel *sch = to_subchannel(dev);
-	struct css_driver *driver = to_cssdriver(drv);
+	const struct css_driver *driver = to_cssdriver(drv);
 	struct css_device_id *id;
 
 	/* When driver_override is set, only bind to the matching driver */
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index c2b1755..a65a27d 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -103,7 +103,7 @@ struct css_driver {
 	int (*settle)(void);
 };
 
-#define to_cssdriver(n) container_of(n, struct css_driver, drv)
+#define to_cssdriver(n) container_of_const(n, struct css_driver, drv)
 
 extern int css_driver_register(struct css_driver *);
 extern void css_driver_unregister(struct css_driver *);
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 920f550b..b0f2324 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -58,10 +58,10 @@ static const struct bus_type ccw_bus_type;
  * subsystem driver and one channel system per machine, but
  * we still use the abstraction. T.R. says it's a good idea. */
 static int
-ccw_bus_match (struct device * dev, struct device_driver * drv)
+ccw_bus_match (struct device * dev, const struct device_driver * drv)
 {
 	struct ccw_device *cdev = to_ccwdev(dev);
-	struct ccw_driver *cdrv = to_ccwdrv(drv);
+	const struct ccw_driver *cdrv = to_ccwdrv(drv);
 	const struct ccw_device_id *ids = cdrv->ids, *found;
 
 	if (!ids)
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 898865b..0998b17 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -552,9 +552,9 @@ static void ap_poll_thread_stop(void)
  *
  * AP bus driver registration/unregistration.
  */
-static int ap_bus_match(struct device *dev, struct device_driver *drv)
+static int ap_bus_match(struct device *dev, const struct device_driver *drv)
 {
-	struct ap_driver *ap_drv = to_ap_drv(drv);
+	const struct ap_driver *ap_drv = to_ap_drv(drv);
 	struct ap_device_id *id;
 
 	/*
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index fdbc6fd..0b275c7 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -158,7 +158,7 @@ struct ap_driver {
 				 struct ap_config_info *old_config_info);
 };
 
-#define to_ap_drv(x) container_of((x), struct ap_driver, driver)
+#define to_ap_drv(x) container_of_const((x), struct ap_driver, driver)
 
 int ap_driver_register(struct ap_driver *, struct module *, char *);
 void ap_driver_unregister(struct ap_driver *);
diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c
index 453665a..7d3b904 100644
--- a/drivers/scsi/fcoe/fcoe_sysfs.c
+++ b/drivers/scsi/fcoe/fcoe_sysfs.c
@@ -600,7 +600,7 @@ static const struct attribute_group *fcoe_fcf_attr_groups[] = {
 static const struct bus_type fcoe_bus_type;
 
 static int fcoe_bus_match(struct device *dev,
-			  struct device_driver *drv)
+			  const struct device_driver *drv)
 {
 	if (dev->bus == &fcoe_bus_type)
 		return 1;
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index b5aae4e..32f94db 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -528,7 +528,7 @@ static struct class sdev_class = {
 };
 
 /* all probing is done in the individual ->probe routines */
-static int scsi_bus_match(struct device *dev, struct device_driver *gendrv)
+static int scsi_bus_match(struct device *dev, const struct device_driver *gendrv)
 {
 	struct scsi_device *sdp;
 
@@ -661,7 +661,7 @@ static int scsi_sdev_check_buf_bit(const char *buf)
 			return 1;
 		else if (buf[0] == '0')
 			return 0;
-		else 
+		else
 			return -EINVAL;
 	} else
 		return -EINVAL;
@@ -886,7 +886,7 @@ store_queue_type_field(struct device *dev, struct device_attribute *attr,
 
 	if (!sdev->tagged_supported)
 		return -EINVAL;
-		
+
 	sdev_printk(KERN_INFO, sdev,
 		    "ignoring write to deprecated queue_type attribute");
 	return count;
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 93e1978..fde7de3 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1204,7 +1204,7 @@ static const struct device_type iscsi_flashnode_conn_dev_type = {
 static const struct bus_type iscsi_flashnode_bus;
 
 int iscsi_flashnode_bus_match(struct device *dev,
-				     struct device_driver *drv)
+			      const struct device_driver *drv)
 {
 	if (dev->bus == &iscsi_flashnode_bus)
 		return 1;
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index 1601800..6dc0549 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -747,9 +747,9 @@ static int maple_get_dma_buffer(void)
 }
 
 static int maple_match_bus_driver(struct device *devptr,
-				  struct device_driver *drvptr)
+				  const struct device_driver *drvptr)
 {
-	struct maple_driver *maple_drv = to_maple_driver(drvptr);
+	const struct maple_driver *maple_drv = to_maple_driver(drvptr);
 	struct maple_device *maple_dev = to_maple_dev(devptr);
 
 	/* Trap empty port case */
diff --git a/drivers/siox/siox-core.c b/drivers/siox/siox-core.c
index 24a4592..f98f5a2 100644
--- a/drivers/siox/siox-core.c
+++ b/drivers/siox/siox-core.c
@@ -503,7 +503,7 @@ static const struct device_type siox_device_type = {
 	.release = siox_device_release,
 };
 
-static int siox_match(struct device *dev, struct device_driver *drv)
+static int siox_match(struct device *dev, const struct device_driver *drv)
 {
 	if (dev->type != &siox_device_type)
 		return 0;
diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index 41e62de..65e5515 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -30,10 +30,10 @@ static const struct slim_device_id *slim_match(const struct slim_device_id *id,
 	return NULL;
 }
 
-static int slim_device_match(struct device *dev, struct device_driver *drv)
+static int slim_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct slim_device *sbdev = to_slim_device(dev);
-	struct slim_driver *sbdrv = to_slim_driver(drv);
+	const struct slim_driver *sbdrv = to_slim_driver(drv);
 
 	/* Attempt an OF style match first */
 	if (of_driver_match_device(dev, drv))
diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c
index 50749e8..4fbff3a 100644
--- a/drivers/soc/qcom/apr.c
+++ b/drivers/soc/qcom/apr.c
@@ -338,10 +338,10 @@ static void apr_rxwq(struct work_struct *work)
 	}
 }
 
-static int apr_device_match(struct device *dev, struct device_driver *drv)
+static int apr_device_match(struct device *dev, const struct device_driver *drv)
 {
 	struct apr_device *adev = to_apr_device(dev);
-	struct apr_driver *adrv = to_apr_driver(drv);
+	const struct apr_driver *adrv = to_apr_driver(drv);
 	const struct apr_device_id *id = adrv->id_table;
 
 	/* Attempt an OF style match first */
diff --git a/drivers/soundwire/amd_init.c b/drivers/soundwire/amd_init.c
index 4cd26f3..db040f4 100644
--- a/drivers/soundwire/amd_init.c
+++ b/drivers/soundwire/amd_init.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cleanup.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/module.h>
@@ -69,7 +70,6 @@ static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
 {
 	struct sdw_amd_ctx *ctx;
 	struct acpi_device *adev;
-	struct resource *sdw_res;
 	struct acp_sdw_pdata sdw_pdata[2];
 	struct platform_device_info pdevinfo[2];
 	u32 link_mask;
@@ -104,7 +104,8 @@ static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
 
 	ctx->count = count;
 	ctx->link_mask = res->link_mask;
-	sdw_res = kzalloc(sizeof(*sdw_res), GFP_KERNEL);
+	struct resource *sdw_res __free(kfree) = kzalloc(sizeof(*sdw_res),
+							 GFP_KERNEL);
 	if (!sdw_res) {
 		kfree(ctx);
 		return NULL;
@@ -132,7 +133,6 @@ static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
 		if (IS_ERR(ctx->pdev[index]))
 			goto err;
 	}
-	kfree(sdw_res);
 	return ctx;
 err:
 	while (index--) {
@@ -142,7 +142,6 @@ static struct sdw_amd_ctx *sdw_amd_probe_controller(struct sdw_amd_res *res)
 		platform_device_unregister(ctx->pdev[index]);
 	}
 
-	kfree(sdw_res);
 	kfree(ctx);
 	return NULL;
 }
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 795e223..0d01849 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/completion.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
@@ -603,7 +604,6 @@ static int amd_sdw_hw_params(struct snd_pcm_substream *substream,
 	struct amd_sdw_manager *amd_manager = snd_soc_dai_get_drvdata(dai);
 	struct sdw_amd_dai_runtime *dai_runtime;
 	struct sdw_stream_config sconfig;
-	struct sdw_port_config *pconfig;
 	int ch, dir;
 	int ret;
 
@@ -626,11 +626,10 @@ static int amd_sdw_hw_params(struct snd_pcm_substream *substream,
 	sconfig.bps = snd_pcm_format_width(params_format(params));
 
 	/* Port configuration */
-	pconfig = kzalloc(sizeof(*pconfig), GFP_KERNEL);
-	if (!pconfig) {
-		ret =  -ENOMEM;
-		goto error;
-	}
+	struct sdw_port_config *pconfig __free(kfree) = kzalloc(sizeof(*pconfig),
+								GFP_KERNEL);
+	if (!pconfig)
+		return -ENOMEM;
 
 	pconfig->num = dai->id;
 	pconfig->ch_mask = (1 << ch) - 1;
@@ -639,8 +638,6 @@ static int amd_sdw_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		dev_err(amd_manager->dev, "add manager to stream failed:%d\n", ret);
 
-	kfree(pconfig);
-error:
 	return ret;
 }
 
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 191e6cc..263ca32 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1410,7 +1410,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 		}
 	}
 	if ((slave->bus->prop.quirks & SDW_MASTER_QUIRKS_CLEAR_INITIAL_PARITY) &&
-	    !(slave->prop.quirks & SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY)) {
+	    !(prop->quirks & SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY)) {
 		/* Clear parity interrupt before enabling interrupt mask */
 		status = sdw_read_no_pm(slave, SDW_SCP_INT1);
 		if (status < 0) {
@@ -1436,7 +1436,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 	 * device-dependent, it might e.g. only be enabled in
 	 * steady-state after a couple of frames.
 	 */
-	val = slave->prop.scp_int1_mask;
+	val = prop->scp_int1_mask;
 
 	/* Enable SCP interrupts */
 	ret = sdw_update_no_pm(slave, SDW_SCP_INTMASK1, val, val);
@@ -1447,7 +1447,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 	}
 
 	/* No need to continue if DP0 is not present */
-	if (!slave->prop.dp0_prop)
+	if (!prop->dp0_prop)
 		return 0;
 
 	/* Enable DP0 interrupts */
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index c32faac..d928258 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -19,7 +19,7 @@
  * struct sdw_device_id.
  */
 static const struct sdw_device_id *
-sdw_get_device_id(struct sdw_slave *slave, struct sdw_driver *drv)
+sdw_get_device_id(struct sdw_slave *slave, const struct sdw_driver *drv)
 {
 	const struct sdw_device_id *id;
 
@@ -35,10 +35,10 @@ sdw_get_device_id(struct sdw_slave *slave, struct sdw_driver *drv)
 	return NULL;
 }
 
-static int sdw_bus_match(struct device *dev, struct device_driver *ddrv)
+static int sdw_bus_match(struct device *dev, const struct device_driver *ddrv)
 {
 	struct sdw_slave *slave;
-	struct sdw_driver *drv;
+	const struct sdw_driver *drv;
 	int ret = 0;
 
 	if (is_sdw_slave(dev)) {
diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 74da990..e0683a5 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -6,6 +6,7 @@
  * Used by Master driver
  */
 
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/debugfs.h>
@@ -323,12 +324,11 @@ static ssize_t cdns_sprintf(struct sdw_cdns *cdns,
 static int cdns_reg_show(struct seq_file *s, void *data)
 {
 	struct sdw_cdns *cdns = s->private;
-	char *buf;
 	ssize_t ret;
 	int num_ports;
 	int i, j;
 
-	buf = kzalloc(RD_BUF, GFP_KERNEL);
+	char *buf __free(kfree) = kzalloc(RD_BUF, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -389,7 +389,6 @@ static int cdns_reg_show(struct seq_file *s, void *data)
 		ret += cdns_sprintf(cdns, buf, ret, CDNS_PDI_CONFIG(i));
 
 	seq_printf(s, "%s", buf);
-	kfree(buf);
 
 	return 0;
 }
diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c
index 67abd7e..c30f571 100644
--- a/drivers/soundwire/debugfs.c
+++ b/drivers/soundwire/debugfs.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 // Copyright(c) 2017-2019 Intel Corporation.
 
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/debugfs.h>
+#include <linux/firmware.h>
 #include <linux/mod_devicetable.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -48,18 +50,16 @@ static ssize_t sdw_sprintf(struct sdw_slave *slave,
 static int sdw_slave_reg_show(struct seq_file *s_file, void *data)
 {
 	struct sdw_slave *slave = s_file->private;
-	char *buf;
 	ssize_t ret;
 	int i, j;
 
-	buf = kzalloc(RD_BUF, GFP_KERNEL);
+	char *buf __free(kfree) = kzalloc(RD_BUF, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	ret = pm_runtime_get_sync(&slave->dev);
 	if (ret < 0 && ret != -EACCES) {
 		pm_runtime_put_noidle(&slave->dev);
-		kfree(buf);
 		return ret;
 	}
 
@@ -131,12 +131,149 @@ static int sdw_slave_reg_show(struct seq_file *s_file, void *data)
 	pm_runtime_mark_last_busy(&slave->dev);
 	pm_runtime_put(&slave->dev);
 
-	kfree(buf);
-
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(sdw_slave_reg);
 
+#define MAX_CMD_BYTES 256
+
+static int cmd;
+static u32 start_addr;
+static size_t num_bytes;
+static u8 read_buffer[MAX_CMD_BYTES];
+static char *firmware_file;
+
+static int set_command(void *data, u64 value)
+{
+	struct sdw_slave *slave = data;
+
+	if (value > 1)
+		return -EINVAL;
+
+	/* Userspace changed the hardware state behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+
+	dev_dbg(&slave->dev, "command: %s\n", value ? "read" : "write");
+	cmd = value;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(set_command_fops, NULL,
+			 set_command, "%llu\n");
+
+static int set_start_address(void *data, u64 value)
+{
+	struct sdw_slave *slave = data;
+
+	/* Userspace changed the hardware state behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+
+	dev_dbg(&slave->dev, "start address %#llx\n", value);
+
+	start_addr = value;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(set_start_address_fops, NULL,
+			 set_start_address, "%llu\n");
+
+static int set_num_bytes(void *data, u64 value)
+{
+	struct sdw_slave *slave = data;
+
+	if (value == 0 || value > MAX_CMD_BYTES)
+		return -EINVAL;
+
+	/* Userspace changed the hardware state behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+
+	dev_dbg(&slave->dev, "number of bytes %lld\n", value);
+
+	num_bytes = value;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(set_num_bytes_fops, NULL,
+			 set_num_bytes, "%llu\n");
+
+static int cmd_go(void *data, u64 value)
+{
+	struct sdw_slave *slave = data;
+	int ret;
+
+	if (value != 1)
+		return -EINVAL;
+
+	/* one last check */
+	if (start_addr > SDW_REG_MAX ||
+	    num_bytes == 0 || num_bytes > MAX_CMD_BYTES)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(&slave->dev);
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_noidle(&slave->dev);
+		return ret;
+	}
+
+	/* Userspace changed the hardware state behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+
+	dev_dbg(&slave->dev, "starting command\n");
+
+	if (cmd == 0) {
+		const struct firmware *fw;
+
+		ret = request_firmware(&fw, firmware_file, &slave->dev);
+		if (ret < 0) {
+			dev_err(&slave->dev, "firmware %s not found\n", firmware_file);
+			goto out;
+		}
+
+		if (fw->size != num_bytes) {
+			dev_err(&slave->dev,
+				"firmware %s: unexpected size %zd, desired %zd\n",
+				firmware_file, fw->size, num_bytes);
+			release_firmware(fw);
+			goto out;
+		}
+
+		ret = sdw_nwrite_no_pm(slave, start_addr, num_bytes, fw->data);
+		release_firmware(fw);
+	} else {
+		ret = sdw_nread_no_pm(slave, start_addr, num_bytes, read_buffer);
+	}
+
+	dev_dbg(&slave->dev, "command completed %d\n", ret);
+
+out:
+	pm_runtime_mark_last_busy(&slave->dev);
+	pm_runtime_put(&slave->dev);
+
+	return ret;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(cmd_go_fops, NULL,
+			 cmd_go, "%llu\n");
+
+#define MAX_LINE_LEN 128
+
+static int read_buffer_show(struct seq_file *s_file, void *data)
+{
+	char buf[MAX_LINE_LEN];
+	int i;
+
+	if (num_bytes == 0 || num_bytes > MAX_CMD_BYTES)
+		return -EINVAL;
+
+	for (i = 0; i < num_bytes; i++) {
+		scnprintf(buf, MAX_LINE_LEN, "address %#x val 0x%02x\n",
+			  start_addr + i, read_buffer[i]);
+		seq_printf(s_file, "%s", buf);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(read_buffer);
+
 void sdw_slave_debugfs_init(struct sdw_slave *slave)
 {
 	struct dentry *master;
@@ -151,6 +288,16 @@ void sdw_slave_debugfs_init(struct sdw_slave *slave)
 
 	debugfs_create_file("registers", 0400, d, slave, &sdw_slave_reg_fops);
 
+	/* interface to send arbitrary commands */
+	debugfs_create_file("command", 0200, d, slave, &set_command_fops);
+	debugfs_create_file("start_address", 0200, d, slave, &set_start_address_fops);
+	debugfs_create_file("num_bytes", 0200, d, slave, &set_num_bytes_fops);
+	debugfs_create_file("go", 0200, d, slave, &cmd_go_fops);
+
+	debugfs_create_file("read_buffer", 0400, d, slave, &read_buffer_fops);
+	firmware_file = NULL;
+	debugfs_create_str("firmware_file", 0200, d, &firmware_file);
+
 	slave->debugfs = d;
 }
 
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index c70a63d0..b931620 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -83,7 +83,7 @@ EXPORT_SYMBOL(sdw_compute_slave_ports);
 
 static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 				     struct sdw_group_params *params,
-				     int port_bo, int hstop)
+				     int *port_bo, int hstop)
 {
 	struct sdw_transport_data t_data = {0};
 	struct sdw_port_runtime *p_rt;
@@ -108,7 +108,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 
 		sdw_fill_xport_params(&p_rt->transport_params, p_rt->num,
 				      false, SDW_BLK_GRP_CNT_1, sample_int,
-				      port_bo, port_bo >> 8, hstart, hstop,
+				      *port_bo, (*port_bo) >> 8, hstart, hstop,
 				      SDW_BLK_PKG_PER_PORT, 0x0);
 
 		sdw_fill_port_params(&p_rt->port_params,
@@ -120,15 +120,15 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 		if (!(p_rt == list_first_entry(&m_rt->port_list,
 					       struct sdw_port_runtime,
 					       port_node))) {
-			port_bo += bps * ch;
+			(*port_bo) += bps * ch;
 			continue;
 		}
 
 		t_data.hstart = hstart;
 		t_data.hstop = hstop;
-		t_data.block_offset = port_bo;
+		t_data.block_offset = *port_bo;
 		t_data.sub_block_offset = 0;
-		port_bo += bps * ch;
+		(*port_bo) += bps * ch;
 	}
 
 	sdw_compute_slave_ports(m_rt, &t_data);
@@ -146,9 +146,7 @@ static void _sdw_compute_port_params(struct sdw_bus *bus,
 		port_bo = 1;
 
 		list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
-			sdw_compute_master_ports(m_rt, &params[i], port_bo, hstop);
-
-			port_bo += m_rt->ch_count * m_rt->stream->params.bps;
+			sdw_compute_master_ports(m_rt, &params[i], &port_bo, hstop);
 		}
 
 		hstop = hstop - params[i].hwidth;
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index 01e1a0f..421da0f 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -73,12 +74,11 @@ static int intel_reg_show(struct seq_file *s_file, void *data)
 	struct sdw_intel *sdw = s_file->private;
 	void __iomem *s = sdw->link_res->shim;
 	void __iomem *a = sdw->link_res->alh;
-	char *buf;
 	ssize_t ret;
 	int i, j;
 	unsigned int links, reg;
 
-	buf = kzalloc(RD_BUF, GFP_KERNEL);
+	char *buf __free(kfree) = kzalloc(RD_BUF, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -129,7 +129,6 @@ static int intel_reg_show(struct seq_file *s_file, void *data)
 		ret += intel_sprintf(a, true, buf, ret, SDW_ALH_STRMZCFG(i));
 
 	seq_printf(s_file, "%s", buf);
-	kfree(buf);
 
 	return 0;
 }
@@ -727,7 +726,6 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	struct sdw_cdns_dai_runtime *dai_runtime;
 	struct sdw_cdns_pdi *pdi;
 	struct sdw_stream_config sconfig;
-	struct sdw_port_config *pconfig;
 	int ch, dir;
 	int ret;
 
@@ -743,10 +741,8 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 
 	pdi = sdw_cdns_alloc_pdi(cdns, &cdns->pcm, ch, dir, dai->id);
 
-	if (!pdi) {
-		ret = -EINVAL;
-		goto error;
-	}
+	if (!pdi)
+		return -EINVAL;
 
 	/* do run-time configurations for SHIM, ALH and PDI/PORT */
 	intel_pdi_shim_configure(sdw, pdi);
@@ -763,7 +759,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 				  sdw->instance,
 				  pdi->intel_alh_id);
 	if (ret)
-		goto error;
+		return ret;
 
 	sconfig.direction = dir;
 	sconfig.ch_count = ch;
@@ -773,11 +769,10 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	sconfig.bps = snd_pcm_format_width(params_format(params));
 
 	/* Port configuration */
-	pconfig = kzalloc(sizeof(*pconfig), GFP_KERNEL);
-	if (!pconfig) {
-		ret =  -ENOMEM;
-		goto error;
-	}
+	struct sdw_port_config *pconfig __free(kfree) = kzalloc(sizeof(*pconfig),
+								GFP_KERNEL);
+	if (!pconfig)
+		return -ENOMEM;
 
 	pconfig->num = pdi->num;
 	pconfig->ch_mask = (1 << ch) - 1;
@@ -787,8 +782,6 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		dev_err(cdns->dev, "add master to stream failed:%d\n", ret);
 
-	kfree(pconfig);
-error:
 	return ret;
 }
 
diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h
index b68e74c..68838e8 100644
--- a/drivers/soundwire/intel.h
+++ b/drivers/soundwire/intel.h
@@ -59,6 +59,11 @@ struct sdw_intel {
 };
 
 struct sdw_intel_prop {
+	u16 clde;
+	u16 doaise2;
+	u16 dodse2;
+	u16 clds;
+	u16 clss;
 	u16 doaise;
 	u16 doais;
 	u16 dodse;
diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c
index 8b1b6ad..781fe0a 100644
--- a/drivers/soundwire/intel_ace2x.c
+++ b/drivers/soundwire/intel_ace2x.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
-// Copyright(c) 2023 Intel Corporation. All rights reserved.
+// Copyright(c) 2023 Intel Corporation
 
 /*
  * Soundwire Intel ops for LunarLake
  */
 
 #include <linux/acpi.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/soundwire/sdw_registers.h>
 #include <linux/soundwire/sdw.h>
@@ -27,6 +28,11 @@ static void intel_shim_vs_init(struct sdw_intel *sdw)
 	void __iomem *shim_vs = sdw->link_res->shim_vs;
 	struct sdw_bus *bus = &sdw->cdns.bus;
 	struct sdw_intel_prop *intel_prop;
+	u16 clde;
+	u16 doaise2;
+	u16 dodse2;
+	u16 clds;
+	u16 clss;
 	u16 doaise;
 	u16 doais;
 	u16 dodse;
@@ -34,12 +40,22 @@ static void intel_shim_vs_init(struct sdw_intel *sdw)
 	u16 act;
 
 	intel_prop = bus->vendor_specific_prop;
+	clde = intel_prop->clde;
+	doaise2 = intel_prop->doaise2;
+	dodse2 = intel_prop->dodse2;
+	clds = intel_prop->clds;
+	clss = intel_prop->clss;
 	doaise = intel_prop->doaise;
 	doais = intel_prop->doais;
 	dodse = intel_prop->dodse;
 	dods = intel_prop->dods;
 
 	act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL);
+	u16p_replace_bits(&act, clde, SDW_SHIM3_INTEL_VS_ACTMCTL_CLDE);
+	u16p_replace_bits(&act, doaise2, SDW_SHIM3_INTEL_VS_ACTMCTL_DOAISE2);
+	u16p_replace_bits(&act, dodse2, SDW_SHIM3_INTEL_VS_ACTMCTL_DODSE2);
+	u16p_replace_bits(&act, clds, SDW_SHIM3_INTEL_VS_ACTMCTL_CLDS);
+	u16p_replace_bits(&act, clss, SDW_SHIM3_INTEL_VS_ACTMCTL_CLSS);
 	u16p_replace_bits(&act, doaise, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAISE);
 	u16p_replace_bits(&act, doais, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS);
 	u16p_replace_bits(&act, dodse, SDW_SHIM2_INTEL_VS_ACTMCTL_DODSE);
@@ -295,7 +311,6 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	struct sdw_cdns_dai_runtime *dai_runtime;
 	struct sdw_cdns_pdi *pdi;
 	struct sdw_stream_config sconfig;
-	struct sdw_port_config *pconfig;
 	int ch, dir;
 	int ret;
 
@@ -310,11 +325,8 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 		dir = SDW_DATA_DIR_TX;
 
 	pdi = sdw_cdns_alloc_pdi(cdns, &cdns->pcm, ch, dir, dai->id);
-
-	if (!pdi) {
-		ret = -EINVAL;
-		goto error;
-	}
+	if (!pdi)
+		return -EINVAL;
 
 	/* use same definitions for alh_id as previous generations */
 	pdi->intel_alh_id = (sdw->instance * 16) + pdi->num + 3;
@@ -335,7 +347,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 				  sdw->instance,
 				  pdi->intel_alh_id);
 	if (ret)
-		goto error;
+		return ret;
 
 	sconfig.direction = dir;
 	sconfig.ch_count = ch;
@@ -345,11 +357,10 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	sconfig.bps = snd_pcm_format_width(params_format(params));
 
 	/* Port configuration */
-	pconfig = kzalloc(sizeof(*pconfig), GFP_KERNEL);
-	if (!pconfig) {
-		ret =  -ENOMEM;
-		goto error;
-	}
+	struct sdw_port_config *pconfig __free(kfree) = kzalloc(sizeof(*pconfig),
+								GFP_KERNEL);
+	if (!pconfig)
+		return -ENOMEM;
 
 	pconfig->num = pdi->num;
 	pconfig->ch_mask = (1 << ch) - 1;
@@ -359,8 +370,6 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		dev_err(cdns->dev, "add master to stream failed:%d\n", ret);
 
-	kfree(pconfig);
-error:
 	return ret;
 }
 
diff --git a/drivers/soundwire/intel_ace2x_debugfs.c b/drivers/soundwire/intel_ace2x_debugfs.c
index 3d24661..206a8d5 100644
--- a/drivers/soundwire/intel_ace2x_debugfs.c
+++ b/drivers/soundwire/intel_ace2x_debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-// Copyright(c) 2023 Intel Corporation. All rights reserved.
+// Copyright(c) 2023 Intel Corporation
 
 #include <linux/acpi.h>
 #include <linux/debugfs.h>
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 1851712..8807e01 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -47,6 +47,7 @@ struct wake_capable_part {
 };
 
 static struct wake_capable_part wake_capable_list[] = {
+	{0x01fa, 0x4243},
 	{0x025d, 0x5682},
 	{0x025d, 0x700},
 	{0x025d, 0x711},
@@ -161,12 +162,32 @@ static int sdw_master_read_intel_prop(struct sdw_bus *bus)
 	}
 
 	/* initialize with hardware defaults, in case the properties are not found */
+	intel_prop->clde = 0x0;
+	intel_prop->doaise2 = 0x0;
+	intel_prop->dodse2 = 0x0;
+	intel_prop->clds = 0x0;
+	intel_prop->clss = 0x0;
 	intel_prop->doaise = 0x1;
 	intel_prop->doais = 0x3;
 	intel_prop->dodse  = 0x0;
 	intel_prop->dods  = 0x1;
 
 	fwnode_property_read_u16(link,
+				 "intel-sdw-clde",
+				 &intel_prop->clde);
+	fwnode_property_read_u16(link,
+				 "intel-sdw-doaise2",
+				 &intel_prop->doaise2);
+	fwnode_property_read_u16(link,
+				 "intel-sdw-dodse2",
+				 &intel_prop->dodse2);
+	fwnode_property_read_u16(link,
+				 "intel-sdw-clds",
+				 &intel_prop->clds);
+	fwnode_property_read_u16(link,
+				 "intel-sdw-clss",
+				 &intel_prop->clss);
+	fwnode_property_read_u16(link,
 				 "intel-sdw-doaise",
 				 &intel_prop->doaise);
 	fwnode_property_read_u16(link,
@@ -193,9 +214,30 @@ static int sdw_master_read_intel_prop(struct sdw_bus *bus)
 
 static int intel_prop_read(struct sdw_bus *bus)
 {
+	struct sdw_master_prop *prop;
+
 	/* Initialize with default handler to read all DisCo properties */
 	sdw_master_read_prop(bus);
 
+	/*
+	 * Only one bus frequency is supported so far, filter
+	 * frequencies reported in the DSDT
+	 */
+	prop = &bus->prop;
+	if (prop->clk_freq && prop->num_clk_freq > 1) {
+		unsigned int default_bus_frequency;
+
+		default_bus_frequency =
+			prop->default_frame_rate *
+			prop->default_row *
+			prop->default_col /
+			SDW_DOUBLE_RATE_FACTOR;
+
+		prop->num_clk_freq = 1;
+		prop->clk_freq[0] = default_bus_frequency;
+		prop->max_clk_freq = default_bus_frequency;
+	}
+
 	/* read Intel-specific properties */
 	sdw_master_read_intel_prop(bus);
 
diff --git a/drivers/soundwire/intel_bus_common.c b/drivers/soundwire/intel_bus_common.c
index e5ac3cc..df944e1 100644
--- a/drivers/soundwire/intel_bus_common.c
+++ b/drivers/soundwire/intel_bus_common.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
-// Copyright(c) 2015-2023 Intel Corporation. All rights reserved.
+// Copyright(c) 2015-2023 Intel Corporation
 
 #include <linux/acpi.h>
 #include <linux/soundwire/sdw_registers.h>
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index ce5cf3e..aed5700 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -197,8 +197,7 @@ struct qcom_swrm_ctrl {
 	int num_dout_ports;
 	int cols_index;
 	int rows_index;
-	unsigned long dout_port_mask;
-	unsigned long din_port_mask;
+	unsigned long port_mask;
 	u32 intr_mask;
 	u8 rcmd_id;
 	u8 wcmd_id;
@@ -1146,11 +1145,7 @@ static void qcom_swrm_stream_free_ports(struct qcom_swrm_ctrl *ctrl,
 	mutex_lock(&ctrl->port_lock);
 
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
-		if (m_rt->direction == SDW_DATA_DIR_RX)
-			port_mask = &ctrl->dout_port_mask;
-		else
-			port_mask = &ctrl->din_port_mask;
-
+		port_mask = &ctrl->port_mask;
 		list_for_each_entry(p_rt, &m_rt->port_list, port_node)
 			clear_bit(p_rt->num, port_mask);
 	}
@@ -1195,13 +1190,9 @@ static int qcom_swrm_stream_alloc_ports(struct qcom_swrm_ctrl *ctrl,
 		if (ctrl->bus.id != m_rt->bus->id)
 			continue;
 
-		if (m_rt->direction == SDW_DATA_DIR_RX) {
-			maxport = ctrl->num_dout_ports;
-			port_mask = &ctrl->dout_port_mask;
-		} else {
-			maxport = ctrl->num_din_ports;
-			port_mask = &ctrl->din_port_mask;
-		}
+		port_mask = &ctrl->port_mask;
+		maxport = ctrl->num_dout_ports + ctrl->num_din_ports;
+
 
 		list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
 			slave = s_rt->slave;
@@ -1401,8 +1392,7 @@ static int qcom_swrm_get_port_config(struct qcom_swrm_ctrl *ctrl)
 		return -EINVAL;
 
 	/* Valid port numbers are from 1-14, so mask out port 0 explicitly */
-	set_bit(0, &ctrl->dout_port_mask);
-	set_bit(0, &ctrl->din_port_mask);
+	set_bit(0, &ctrl->port_mask);
 
 	ret = of_property_read_u8_array(np, "qcom,ports-offset1",
 					off1, nports);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 4e9e7d2..7aa4900 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -1181,6 +1181,8 @@ static struct sdw_master_runtime
 	m_rt->bus = bus;
 	m_rt->stream = stream;
 
+	bus->stream_refcount++;
+
 	return m_rt;
 }
 
@@ -1217,6 +1219,7 @@ static void sdw_master_rt_free(struct sdw_master_runtime *m_rt,
 			       struct sdw_stream_runtime *stream)
 {
 	struct sdw_slave_runtime *s_rt, *_s_rt;
+	struct sdw_bus *bus = m_rt->bus;
 
 	list_for_each_entry_safe(s_rt, _s_rt, &m_rt->slave_rt_list, m_rt_node) {
 		sdw_slave_port_free(s_rt->slave, stream);
@@ -1226,6 +1229,8 @@ static void sdw_master_rt_free(struct sdw_master_runtime *m_rt,
 	list_del(&m_rt->stream_node);
 	list_del(&m_rt->bus_node);
 	kfree(m_rt);
+
+	bus->stream_refcount--;
 }
 
 /**
diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-microchip-core.c
index 6246254..7c1a9a9 100644
--- a/drivers/spi/spi-microchip-core.c
+++ b/drivers/spi/spi-microchip-core.c
@@ -75,6 +75,7 @@
 
 #define REG_CONTROL		(0x00)
 #define REG_FRAME_SIZE		(0x04)
+#define  FRAME_SIZE_MASK	GENMASK(5, 0)
 #define REG_STATUS		(0x08)
 #define REG_INT_CLEAR		(0x0c)
 #define REG_RX_DATA		(0x10)
@@ -89,6 +90,9 @@
 #define REG_RIS			(0x24)
 #define REG_CONTROL2		(0x28)
 #define REG_COMMAND		(0x2c)
+#define  COMMAND_CLRFRAMECNT	BIT(4)
+#define  COMMAND_TXFIFORST		BIT(3)
+#define  COMMAND_RXFIFORST		BIT(2)
 #define REG_PKTSIZE		(0x30)
 #define REG_CMD_SIZE		(0x34)
 #define REG_HWSTATUS		(0x38)
@@ -103,10 +107,11 @@ struct mchp_corespi {
 	u8 *rx_buf;
 	u32 clk_gen; /* divider for spi output clock generated by the controller */
 	u32 clk_mode;
+	u32 pending_slave_select;
 	int irq;
 	int tx_len;
 	int rx_len;
-	int pending;
+	int n_bytes;
 };
 
 static inline u32 mchp_corespi_read(struct mchp_corespi *spi, unsigned int reg)
@@ -130,113 +135,126 @@ static inline void mchp_corespi_disable(struct mchp_corespi *spi)
 
 static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi)
 {
-	u8 data;
-	int fifo_max, i = 0;
+	while (spi->rx_len >= spi->n_bytes && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)) {
+		u32 data = mchp_corespi_read(spi, REG_RX_DATA);
 
-	fifo_max = min(spi->rx_len, FIFO_DEPTH);
+		spi->rx_len -= spi->n_bytes;
 
-	while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)) {
-		data = mchp_corespi_read(spi, REG_RX_DATA);
+		if (!spi->rx_buf)
+			continue;
 
-		if (spi->rx_buf)
-			*spi->rx_buf++ = data;
-		i++;
+		if (spi->n_bytes == 4)
+			*((u32 *)spi->rx_buf) = data;
+		else if (spi->n_bytes == 2)
+			*((u16 *)spi->rx_buf) = data;
+		else
+			*spi->rx_buf = data;
+
+		spi->rx_buf += spi->n_bytes;
 	}
-	spi->rx_len -= i;
-	spi->pending -= i;
 }
 
 static void mchp_corespi_enable_ints(struct mchp_corespi *spi)
 {
-	u32 control, mask = INT_ENABLE_MASK;
+	u32 control = mchp_corespi_read(spi, REG_CONTROL);
 
-	mchp_corespi_disable(spi);
-
-	control = mchp_corespi_read(spi, REG_CONTROL);
-
-	control |= mask;
-	mchp_corespi_write(spi, REG_CONTROL, control);
-
-	control |= CONTROL_ENABLE;
+	control |= INT_ENABLE_MASK;
 	mchp_corespi_write(spi, REG_CONTROL, control);
 }
 
 static void mchp_corespi_disable_ints(struct mchp_corespi *spi)
 {
-	u32 control, mask = INT_ENABLE_MASK;
+	u32 control = mchp_corespi_read(spi, REG_CONTROL);
 
-	mchp_corespi_disable(spi);
-
-	control = mchp_corespi_read(spi, REG_CONTROL);
-	control &= ~mask;
-	mchp_corespi_write(spi, REG_CONTROL, control);
-
-	control |= CONTROL_ENABLE;
+	control &= ~INT_ENABLE_MASK;
 	mchp_corespi_write(spi, REG_CONTROL, control);
 }
 
 static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
 {
 	u32 control;
-	u16 lenpart;
+	u32 lenpart;
+	u32 frames = mchp_corespi_read(spi, REG_FRAMESUP);
 
 	/*
-	 * Disable the SPI controller. Writes to transfer length have
-	 * no effect when the controller is enabled.
+	 * Writing to FRAMECNT in REG_CONTROL will reset the frame count, taking
+	 * a shortcut requires an explicit clear.
 	 */
-	mchp_corespi_disable(spi);
+	if (frames == len) {
+		mchp_corespi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT);
+		return;
+	}
 
 	/*
 	 * The lower 16 bits of the frame count are stored in the control reg
 	 * for legacy reasons, but the upper 16 written to a different register:
 	 * FRAMESUP. While both the upper and lower bits can be *READ* from the
-	 * FRAMESUP register, writing to the lower 16 bits is a NOP
+	 * FRAMESUP register, writing to the lower 16 bits is (supposedly) a NOP.
+	 *
+	 * The driver used to disable the controller while modifying the frame
+	 * count, and mask off the lower 16 bits of len while writing to
+	 * FRAMES_UP. When the driver was changed to disable the controller as
+	 * infrequently as possible, it was discovered that the logic of
+	 * lenpart = len & 0xffff_0000
+	 * write(REG_FRAMESUP, lenpart)
+	 * would actually write zeros into the lower 16 bits on an mpfs250t-es,
+	 * despite documentation stating these bits were read-only.
+	 * Writing len unmasked into FRAMES_UP ensures those bits aren't zeroed
+	 * on an mpfs250t-es and will be a NOP for the lower 16 bits on hardware
+	 * that matches the documentation.
 	 */
 	lenpart = len & 0xffff;
-
 	control = mchp_corespi_read(spi, REG_CONTROL);
 	control &= ~CONTROL_FRAMECNT_MASK;
 	control |= lenpart << CONTROL_FRAMECNT_SHIFT;
 	mchp_corespi_write(spi, REG_CONTROL, control);
-
-	lenpart = len & 0xffff0000;
-	mchp_corespi_write(spi, REG_FRAMESUP, lenpart);
-
-	control |= CONTROL_ENABLE;
-	mchp_corespi_write(spi, REG_CONTROL, control);
+	mchp_corespi_write(spi, REG_FRAMESUP, len);
 }
 
 static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi)
 {
-	u8 byte;
 	int fifo_max, i = 0;
 
-	fifo_max = min(spi->tx_len, FIFO_DEPTH);
+	fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
 	mchp_corespi_set_xfer_size(spi, fifo_max);
 
 	while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) {
-		byte = spi->tx_buf ? *spi->tx_buf++ : 0xaa;
-		mchp_corespi_write(spi, REG_TX_DATA, byte);
+		u32 word;
+
+		if (spi->n_bytes == 4)
+			word = spi->tx_buf ? *((u32 *)spi->tx_buf) : 0xaa;
+		else if (spi->n_bytes == 2)
+			word = spi->tx_buf ? *((u16 *)spi->tx_buf) : 0xaa;
+		else
+			word = spi->tx_buf ? *spi->tx_buf : 0xaa;
+
+		mchp_corespi_write(spi, REG_TX_DATA, word);
+		if (spi->tx_buf)
+			spi->tx_buf += spi->n_bytes;
 		i++;
 	}
 
-	spi->tx_len -= i;
-	spi->pending += i;
+	spi->tx_len -= i * spi->n_bytes;
 }
 
 static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt)
 {
+	u32 frame_size = mchp_corespi_read(spi, REG_FRAME_SIZE);
 	u32 control;
 
+	if ((frame_size & FRAME_SIZE_MASK) == bt)
+		return;
+
 	/*
 	 * Disable the SPI controller. Writes to the frame size have
 	 * no effect when the controller is enabled.
 	 */
-	mchp_corespi_disable(spi);
+	control = mchp_corespi_read(spi, REG_CONTROL);
+	control &= ~CONTROL_ENABLE;
+	mchp_corespi_write(spi, REG_CONTROL, control);
 
 	mchp_corespi_write(spi, REG_FRAME_SIZE, bt);
 
-	control = mchp_corespi_read(spi, REG_CONTROL);
 	control |= CONTROL_ENABLE;
 	mchp_corespi_write(spi, REG_CONTROL, control);
 }
@@ -249,8 +267,18 @@ static void mchp_corespi_set_cs(struct spi_device *spi, bool disable)
 	reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
 	reg &= ~BIT(spi_get_chipselect(spi, 0));
 	reg |= !disable << spi_get_chipselect(spi, 0);
+	corespi->pending_slave_select = reg;
 
-	mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
+	/*
+	 * Only deassert chip select immediately. Writing to some registers
+	 * requires the controller to be disabled, which results in the
+	 * output pins being tristated and can cause the SCLK and MOSI lines
+	 * to transition. Therefore asserting the chip select is deferred
+	 * until just before writing to the TX FIFO, to ensure the device
+	 * doesn't see any spurious clock transitions whilst CS is enabled.
+	 */
+	if (((spi->mode & SPI_CS_HIGH) == 0) == disable)
+		mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
 }
 
 static int mchp_corespi_setup(struct spi_device *spi)
@@ -269,6 +297,7 @@ static int mchp_corespi_setup(struct spi_device *spi)
 	if (spi->mode & SPI_CS_HIGH) {
 		reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
 		reg |= BIT(spi_get_chipselect(spi, 0));
+		corespi->pending_slave_select = reg;
 		mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
 	}
 	return 0;
@@ -279,17 +308,13 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
 	unsigned long clk_hz;
 	u32 control = mchp_corespi_read(spi, REG_CONTROL);
 
-	control |= CONTROL_MASTER;
+	control &= ~CONTROL_ENABLE;
+	mchp_corespi_write(spi, REG_CONTROL, control);
 
+	control |= CONTROL_MASTER;
 	control &= ~CONTROL_MODE_MASK;
 	control |= MOTOROLA_MODE;
 
-	mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
-
-	/* max. possible spi clock rate is the apb clock rate */
-	clk_hz = clk_get_rate(spi->clk);
-	host->max_speed_hz = clk_hz;
-
 	/*
 	 * The controller must be configured so that it doesn't remove Chip
 	 * Select until the entire message has been transferred, even if at
@@ -298,11 +323,16 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
 	 * BIGFIFO mode is also enabled, which sets the fifo depth to 32 frames
 	 * for the 8 bit transfers that this driver uses.
 	 */
-	control = mchp_corespi_read(spi, REG_CONTROL);
 	control |= CONTROL_SPS | CONTROL_BIGFIFO;
 
 	mchp_corespi_write(spi, REG_CONTROL, control);
 
+	mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
+
+	/* max. possible spi clock rate is the apb clock rate */
+	clk_hz = clk_get_rate(spi->clk);
+	host->max_speed_hz = clk_hz;
+
 	mchp_corespi_enable_ints(spi);
 
 	/*
@@ -310,7 +340,8 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
 	 * select is relinquished to the hardware. SSELOUT is enabled too so we
 	 * can deal with active high targets.
 	 */
-	mchp_corespi_write(spi, REG_SLAVE_SELECT, SSELOUT | SSEL_DIRECT);
+	spi->pending_slave_select = SSELOUT | SSEL_DIRECT;
+	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
 
 	control = mchp_corespi_read(spi, REG_CONTROL);
 
@@ -324,8 +355,6 @@ static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi)
 {
 	u32 control;
 
-	mchp_corespi_disable(spi);
-
 	control = mchp_corespi_read(spi, REG_CONTROL);
 	if (spi->clk_mode)
 		control |= CONTROL_CLKMODE;
@@ -334,12 +363,12 @@ static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi)
 
 	mchp_corespi_write(spi, REG_CLK_GEN, spi->clk_gen);
 	mchp_corespi_write(spi, REG_CONTROL, control);
-	mchp_corespi_write(spi, REG_CONTROL, control | CONTROL_ENABLE);
 }
 
 static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int mode)
 {
-	u32 control, mode_val;
+	u32 mode_val;
+	u32 control = mchp_corespi_read(spi, REG_CONTROL);
 
 	switch (mode & SPI_MODE_X_MASK) {
 	case SPI_MODE_0:
@@ -357,12 +386,13 @@ static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int
 	}
 
 	/*
-	 * Disable the SPI controller. Writes to the frame size have
+	 * Disable the SPI controller. Writes to the frame protocol have
 	 * no effect when the controller is enabled.
 	 */
-	mchp_corespi_disable(spi);
 
-	control = mchp_corespi_read(spi, REG_CONTROL);
+	control &= ~CONTROL_ENABLE;
+	mchp_corespi_write(spi, REG_CONTROL, control);
+
 	control &= ~(SPI_MODE_X_MASK << MODE_X_MASK_SHIFT);
 	control |= mode_val;
 
@@ -383,21 +413,18 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 	if (intfield == 0)
 		return IRQ_NONE;
 
-	if (intfield & INT_TXDONE) {
+	if (intfield & INT_TXDONE)
 		mchp_corespi_write(spi, REG_INT_CLEAR, INT_TXDONE);
 
+	if (intfield & INT_RXRDY) {
+		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
+
 		if (spi->rx_len)
 			mchp_corespi_read_fifo(spi);
-
-		if (spi->tx_len)
-			mchp_corespi_write_fifo(spi);
-
-		if (!spi->rx_len)
-			finalise = true;
 	}
 
-	if (intfield & INT_RXRDY)
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
+	if (!spi->rx_len && !spi->tx_len)
+		finalise = true;
 
 	if (intfield & INT_RX_CHANNEL_OVERFLOW) {
 		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
@@ -477,13 +504,17 @@ static int mchp_corespi_transfer_one(struct spi_controller *host,
 	spi->rx_buf = xfer->rx_buf;
 	spi->tx_len = xfer->len;
 	spi->rx_len = xfer->len;
-	spi->pending = 0;
+	spi->n_bytes = roundup_pow_of_two(DIV_ROUND_UP(xfer->bits_per_word, BITS_PER_BYTE));
 
-	mchp_corespi_set_xfer_size(spi, (spi->tx_len > FIFO_DEPTH)
-				   ? FIFO_DEPTH : spi->tx_len);
+	mchp_corespi_set_framesize(spi, xfer->bits_per_word);
 
-	if (spi->tx_len)
+	mchp_corespi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST);
+
+	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
+
+	while (spi->tx_len)
 		mchp_corespi_write_fifo(spi);
+
 	return 1;
 }
 
@@ -493,7 +524,6 @@ static int mchp_corespi_prepare_message(struct spi_controller *host,
 	struct spi_device *spi_dev = msg->spi;
 	struct mchp_corespi *spi = spi_controller_get_devdata(host);
 
-	mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
 	mchp_corespi_set_mode(spi, spi_dev->mode);
 
 	return 0;
@@ -521,7 +551,7 @@ static int mchp_corespi_probe(struct platform_device *pdev)
 	host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	host->use_gpio_descriptors = true;
 	host->setup = mchp_corespi_setup;
-	host->bits_per_word_mask = SPI_BPW_MASK(8);
+	host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 	host->transfer_one = mchp_corespi_transfer_one;
 	host->prepare_message = mchp_corespi_prepare_message;
 	host->set_cs = mchp_corespi_set_cs;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d4da546..6ebe5dd 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -371,7 +371,7 @@ const void *spi_get_device_match_data(const struct spi_device *sdev)
 }
 EXPORT_SYMBOL_GPL(spi_get_device_match_data);
 
-static int spi_match_device(struct device *dev, struct device_driver *drv)
+static int spi_match_device(struct device *dev, const struct device_driver *drv)
 {
 	const struct spi_device	*spi = to_spi_device(dev);
 	const struct spi_driver	*sdrv = to_spi_driver(drv);
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 95fb5f1c..05e6d00 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -734,6 +734,7 @@ static const struct of_device_id spidev_dt_ids[] = {
 	{ .compatible = "lwn,bk4", .data = &spidev_of_check },
 	{ .compatible = "menlo,m53cpld", .data = &spidev_of_check },
 	{ .compatible = "micron,spi-authenta", .data = &spidev_of_check },
+	{ .compatible = "rohm,bh2228fv", .data = &spidev_of_check },
 	{ .compatible = "rohm,dh2228fv", .data = &spidev_of_check },
 	{ .compatible = "semtech,sx1301", .data = &spidev_of_check },
 	{ .compatible = "silabs,em3581", .data = &spidev_of_check },
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 667085c..fb0101d 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -43,7 +43,7 @@ static const struct device_type spmi_ctrl_type = {
 	.release	= spmi_ctrl_release,
 };
 
-static int spmi_device_match(struct device *dev, struct device_driver *drv)
+static int spmi_device_match(struct device *dev, const struct device_driver *drv)
 {
 	if (of_driver_match_device(dev, drv))
 		return 1;
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 4da8848..aa6165e 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -323,10 +323,10 @@ static int ssb_match_devid(const struct ssb_device_id *tabid,
 	return 1;
 }
 
-static int ssb_bus_match(struct device *dev, struct device_driver *drv)
+static int ssb_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct ssb_device *ssb_dev = dev_to_ssb_dev(dev);
-	struct ssb_driver *ssb_drv = drv_to_ssb_drv(drv);
+	const struct ssb_driver *ssb_drv = drv_to_ssb_drv(drv);
 	const struct ssb_device_id *id;
 
 	for (id = ssb_drv->id_table;
diff --git a/drivers/staging/fieldbus/anybuss/anybuss-client.h b/drivers/staging/fieldbus/anybuss/anybuss-client.h
index a219688..c21c4be 100644
--- a/drivers/staging/fieldbus/anybuss/anybuss-client.h
+++ b/drivers/staging/fieldbus/anybuss/anybuss-client.h
@@ -44,11 +44,7 @@ static inline struct anybuss_client *to_anybuss_client(struct device *dev)
 	return container_of(dev, struct anybuss_client, dev);
 }
 
-static inline struct anybuss_client_driver *
-to_anybuss_client_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct anybuss_client_driver, driver);
-}
+#define to_anybuss_client_driver(__drv) container_of_const(__drv, struct anybuss_client_driver, driver)
 
 static inline void *
 anybuss_get_drvdata(const struct anybuss_client *client)
diff --git a/drivers/staging/fieldbus/anybuss/host.c b/drivers/staging/fieldbus/anybuss/host.c
index 410e6f8..4f2b2fc 100644
--- a/drivers/staging/fieldbus/anybuss/host.c
+++ b/drivers/staging/fieldbus/anybuss/host.c
@@ -1166,9 +1166,9 @@ EXPORT_SYMBOL_GPL(anybuss_recv_msg);
 /* ------------------------ bus functions ------------------------ */
 
 static int anybus_bus_match(struct device *dev,
-			    struct device_driver *drv)
+			    const struct device_driver *drv)
 {
-	struct anybuss_client_driver *adrv =
+	const struct anybuss_client_driver *adrv =
 		to_anybuss_client_driver(drv);
 	struct anybuss_client *adev =
 		to_anybuss_client(dev);
diff --git a/drivers/staging/greybus/gbphy.c b/drivers/staging/greybus/gbphy.c
index d992db8d..6adcad2 100644
--- a/drivers/staging/greybus/gbphy.c
+++ b/drivers/staging/greybus/gbphy.c
@@ -117,7 +117,7 @@ gbphy_dev_match_id(struct gbphy_device *gbphy_dev,
 	return NULL;
 }
 
-static int gbphy_dev_match(struct device *dev, struct device_driver *drv)
+static int gbphy_dev_match(struct device *dev, const struct device_driver *drv)
 {
 	struct gbphy_driver *gbphy_drv = to_gbphy_driver(drv);
 	struct gbphy_device *gbphy_dev = to_gbphy_dev(dev);
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_bus.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_bus.c
index 3f87b93..41ece91 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_bus.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_bus.c
@@ -14,7 +14,7 @@
 #include "vchiq_arm.h"
 #include "vchiq_bus.h"
 
-static int vchiq_bus_type_match(struct device *dev, struct device_driver *drv)
+static int vchiq_bus_type_match(struct device *dev, const struct device_driver *drv)
 {
 	if (dev->bus == &vchiq_bus_type &&
 	    strcmp(dev_name(dev), drv->name) == 0)
diff --git a/drivers/staging/vme_user/vme.c b/drivers/staging/vme_user/vme.c
index 0cd370a..9a09146 100644
--- a/drivers/staging/vme_user/vme.c
+++ b/drivers/staging/vme_user/vme.c
@@ -1931,7 +1931,7 @@ EXPORT_SYMBOL(vme_unregister_driver);
 
 /* - Bus Registration ------------------------------------------------------ */
 
-static int vme_bus_match(struct device *dev, struct device_driver *drv)
+static int vme_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct vme_driver *vme_drv;
 
diff --git a/drivers/tc/tc-driver.c b/drivers/tc/tc-driver.c
index 1c9d983..2f6d147 100644
--- a/drivers/tc/tc-driver.c
+++ b/drivers/tc/tc-driver.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL(tc_unregister_driver);
  * system is in its list of supported devices.  Returns the matching
  * tc_device_id structure or %NULL if there is no match.
  */
-static const struct tc_device_id *tc_match_device(struct tc_driver *tdrv,
+static const struct tc_device_id *tc_match_device(const struct tc_driver *tdrv,
 						  struct tc_dev *tdev)
 {
 	const struct tc_device_id *id = tdrv->id_table;
@@ -82,10 +82,10 @@ static const struct tc_device_id *tc_match_device(struct tc_driver *tdrv,
  * system is in its list of supported devices.  Returns 1 if there
  * is a match or 0 otherwise.
  */
-static int tc_bus_match(struct device *dev, struct device_driver *drv)
+static int tc_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct tc_dev *tdev = to_tc_dev(dev);
-	struct tc_driver *tdrv = to_tc_driver(drv);
+	const struct tc_driver *tdrv = to_tc_driver(drv);
 	const struct tc_device_id *id;
 
 	id = tc_match_device(tdrv, tdev);
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 82ad095..d52e879 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -1201,7 +1201,7 @@ int tee_client_cancel_req(struct tee_context *ctx,
 }
 
 static int tee_client_device_match(struct device *dev,
-				   struct device_driver *drv)
+				   const struct device_driver *drv)
 {
 	const struct tee_client_device_id *id_table;
 	struct tee_client_device *tee_device;
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index f6e700e..95c399f 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -272,6 +272,44 @@ static int __init thermal_register_governors(void)
 	return ret;
 }
 
+static int __thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+					  enum thermal_device_mode mode)
+{
+	if (tz->ops.change_mode) {
+		int ret;
+
+		ret = tz->ops.change_mode(tz, mode);
+		if (ret)
+			return ret;
+	}
+
+	tz->mode = mode;
+
+	return 0;
+}
+
+static void thermal_zone_broken_disable(struct thermal_zone_device *tz)
+{
+	struct thermal_trip_desc *td;
+
+	dev_err(&tz->device, "Unable to get temperature, disabling!\n");
+	/*
+	 * This function only runs for enabled thermal zones, so no need to
+	 * check for the current mode.
+	 */
+	__thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED);
+	thermal_notify_tz_disable(tz);
+
+	for_each_trip_desc(tz, td) {
+		if (td->trip.type == THERMAL_TRIP_CRITICAL &&
+		    td->trip.temperature > THERMAL_TEMP_INVALID) {
+			dev_crit(&tz->device,
+				 "Disabled thermal zone with critical trip point\n");
+			return;
+		}
+	}
+}
+
 /*
  * Zone update section: main control loop applied to each zone while monitoring
  * in polling mode. The monitoring is done using a workqueue.
@@ -292,6 +330,34 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 		cancel_delayed_work(&tz->poll_queue);
 }
 
+static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
+{
+	if (error == -EAGAIN) {
+		thermal_zone_device_set_polling(tz, THERMAL_RECHECK_DELAY);
+		return;
+	}
+
+	/*
+	 * Print the message once to reduce log noise.  It will be followed by
+	 * another one if the temperature cannot be determined after multiple
+	 * attempts.
+	 */
+	if (tz->recheck_delay_jiffies == THERMAL_RECHECK_DELAY)
+		dev_info(&tz->device, "Temperature check failed (%d)\n", error);
+
+	thermal_zone_device_set_polling(tz, tz->recheck_delay_jiffies);
+
+	tz->recheck_delay_jiffies += max(tz->recheck_delay_jiffies >> 1, 1ULL);
+	if (tz->recheck_delay_jiffies > THERMAL_MAX_RECHECK_DELAY) {
+		thermal_zone_broken_disable(tz);
+		/*
+		 * Restore the original recheck delay value to allow the thermal
+		 * zone to try to recover when it is reenabled by user space.
+		 */
+		tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+	}
+}
+
 static void monitor_thermal_zone(struct thermal_zone_device *tz)
 {
 	if (tz->mode != THERMAL_DEVICE_ENABLED)
@@ -491,10 +557,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 
 	ret = __thermal_zone_get_temp(tz, &temp);
 	if (ret) {
-		if (ret != -EAGAIN)
-			dev_info(&tz->device, "Temperature check failed (%d)\n", ret);
-
-		thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
+		thermal_zone_recheck(tz, ret);
 		return;
 	} else if (temp <= THERMAL_TEMP_INVALID) {
 		/*
@@ -506,6 +569,8 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 		goto monitor;
 	}
 
+	tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+
 	tz->last_temperature = tz->temperature;
 	tz->temperature = temp;
 
@@ -540,7 +605,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 					enum thermal_device_mode mode)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&tz->lock);
 
@@ -548,14 +613,15 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	if (mode == tz->mode) {
 		mutex_unlock(&tz->lock);
 
-		return ret;
+		return 0;
 	}
 
-	if (tz->ops.change_mode)
-		ret = tz->ops.change_mode(tz, mode);
+	ret = __thermal_zone_device_set_mode(tz, mode);
+	if (ret) {
+		mutex_unlock(&tz->lock);
 
-	if (!ret)
-		tz->mode = mode;
+		return ret;
+	}
 
 	__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
@@ -566,7 +632,7 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	else
 		thermal_notify_tz_disable(tz);
 
-	return ret;
+	return 0;
 }
 
 int thermal_zone_device_enable(struct thermal_zone_device *tz)
@@ -1445,6 +1511,7 @@ thermal_zone_device_register_with_trips(const char *type,
 
 	thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
 	thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);
+	tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
 
 	/* sys I/F */
 	/* Add nodes that are always present via .groups */
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index ba8e6fc..4cf2b72 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -67,6 +67,8 @@ struct thermal_governor {
  * @polling_delay_jiffies: number of jiffies to wait between polls when
  *			checking whether trip points have been crossed (0 for
  *			interrupt driven systems)
+ * @recheck_delay_jiffies: delay after a failed attempt to determine the zone
+ * 			temperature before trying again
  * @temperature:	current temperature.  This is only for core code,
  *			drivers should use thermal_zone_get_temp() to get the
  *			current temperature
@@ -108,6 +110,7 @@ struct thermal_zone_device {
 	int num_trips;
 	unsigned long passive_delay_jiffies;
 	unsigned long polling_delay_jiffies;
+	unsigned long recheck_delay_jiffies;
 	int temperature;
 	int last_temperature;
 	int emul_temperature;
@@ -137,10 +140,11 @@ struct thermal_zone_device {
 #define THERMAL_TEMP_INIT	INT_MIN
 
 /*
- * Default delay after a failing thermal zone temperature check before
- * attempting to check it again.
+ * Default and maximum delay after a failed thermal zone temperature check
+ * before attempting to check it again (in jiffies).
  */
-#define THERMAL_RECHECK_DELAY_MS	250
+#define THERMAL_RECHECK_DELAY		msecs_to_jiffies(250)
+#define THERMAL_MAX_RECHECK_DELAY	(120 * HZ)
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 0023017..144d023 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -45,9 +45,9 @@ static bool match_service_id(const struct tb_service_id *id,
 }
 
 static const struct tb_service_id *__tb_service_match(struct device *dev,
-						      struct device_driver *drv)
+						      const struct device_driver *drv)
 {
-	struct tb_service_driver *driver;
+	const struct tb_service_driver *driver;
 	const struct tb_service_id *ids;
 	struct tb_service *svc;
 
@@ -55,7 +55,7 @@ static const struct tb_service_id *__tb_service_match(struct device *dev,
 	if (!svc)
 		return NULL;
 
-	driver = container_of(drv, struct tb_service_driver, driver);
+	driver = container_of_const(drv, struct tb_service_driver, driver);
 	if (!driver->id_table)
 		return NULL;
 
@@ -67,7 +67,7 @@ static const struct tb_service_id *__tb_service_match(struct device *dev,
 	return NULL;
 }
 
-static int tb_service_match(struct device *dev, struct device_driver *drv)
+static int tb_service_match(struct device *dev, const struct device_driver *drv)
 {
 	return !!__tb_service_match(dev, drv);
 }
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index 613cb35..8913cdd 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -85,7 +85,7 @@ static const struct device_type serdev_ctrl_type = {
 	.release	= serdev_ctrl_release,
 };
 
-static int serdev_device_match(struct device *dev, struct device_driver *drv)
+static int serdev_device_match(struct device *dev, const struct device_driver *drv)
 {
 	if (!is_serdev_device(dev))
 		return 0;
diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c
index d822499..5d1677f 100644
--- a/drivers/tty/serial/serial_base_bus.c
+++ b/drivers/tty/serial/serial_base_bus.c
@@ -29,7 +29,7 @@ static const struct device_type serial_port_type = {
 	.name = "port",
 };
 
-static int serial_base_match(struct device *dev, struct device_driver *drv)
+static int serial_base_match(struct device *dev, const struct device_driver *drv)
 {
 	if (dev->type == &serial_ctrl_type &&
 	    str_has_prefix(drv->name, serial_ctrl_type.name))
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index e5974b8..14f8f00 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -452,7 +452,7 @@ static const struct sysrq_key_op sysrq_unrt_op = {
 
 static void sysrq_handle_replay_logs(u8 key)
 {
-	console_replay_all();
+	console_try_replay_all();
 }
 static struct sysrq_key_op sysrq_replay_logs_op = {
 	.handler        = sysrq_handle_replay_logs,
@@ -770,8 +770,6 @@ static void sysrq_of_get_keyreset_config(void)
 {
 	u32 key;
 	struct device_node *np;
-	struct property *prop;
-	const __be32 *p;
 
 	np = of_find_node_by_path("/chosen/linux,sysrq-reset-seq");
 	if (!np) {
@@ -782,7 +780,7 @@ static void sysrq_of_get_keyreset_config(void)
 	/* Reset in case a __weak definition was present */
 	sysrq_reset_seq_len = 0;
 
-	of_property_for_each_u32(np, "keyset", prop, p, key) {
+	of_property_for_each_u32(np, "keyset", key) {
 		if (key == KEY_RESERVED || key > KEY_MAX ||
 		    sysrq_reset_seq_len == SYSRQ_KEY_RESET_MAX)
 			break;
diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 0886b19..4a2ee44 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -34,7 +34,7 @@ EXPORT_SYMBOL_GPL(ulpi_write);
 
 /* -------------------------------------------------------------------------- */
 
-static int ulpi_match(struct device *dev, struct device_driver *driver)
+static int ulpi_match(struct device *dev, const struct device_driver *driver)
 {
 	struct ulpi_driver *drv = to_ulpi_driver(driver);
 	struct ulpi *ulpi = to_ulpi_dev(dev);
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index b35734d..0c3f12d 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -868,7 +868,7 @@ bool usb_driver_applicable(struct usb_device *udev,
 	return false;
 }
 
-static int usb_device_match(struct device *dev, struct device_driver *drv)
+static int usb_device_match(struct device *dev, const struct device_driver *drv)
 {
 	/* devices and interfaces are handled separately */
 	if (is_usb_device(dev)) {
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 2dfae7a..b0a6137 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1568,7 +1568,7 @@ EXPORT_SYMBOL_GPL(usb_del_gadget_udc);
 
 /* ------------------------------------------------------------------------- */
 
-static int gadget_match_driver(struct device *dev, struct device_driver *drv)
+static int gadget_match_driver(struct device *dev, const struct device_driver *drv)
 {
 	struct usb_gadget *gadget = dev_to_usb_gadget(dev);
 	struct usb_udc *udc = gadget->udc;
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index b98cda1..e24cdb6 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -382,11 +382,9 @@ static void usb251xb_get_ports_field(struct usb251xb *hub,
 				    bool ds_only, u8 *fld)
 {
 	struct device *dev = hub->dev;
-	struct property *prop;
-	const __be32 *p;
 	u32 port;
 
-	of_property_for_each_u32(dev->of_node, prop_name, prop, p, port) {
+	of_property_for_each_u32(dev->of_node, prop_name, port) {
 		if ((port >= ds_only ? 1 : 0) && (port <= port_cnt))
 			*fld |= BIT(port);
 		else
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 6c812d0..d200e2c 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -14,7 +14,7 @@
 #include <linux/usb/serial.h>
 
 static int usb_serial_device_match(struct device *dev,
-						struct device_driver *drv)
+				   const struct device_driver *drv)
 {
 	const struct usb_serial_port *port = to_usb_serial_port(dev);
 	struct usb_serial_driver *driver = to_usb_serial_driver(drv);
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index 6ea103e..aa87925 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -447,7 +447,7 @@ static struct attribute *typec_attrs[] = {
 };
 ATTRIBUTE_GROUPS(typec);
 
-static int typec_match(struct device *dev, struct device_driver *driver)
+static int typec_match(struct device *dev, const struct device_driver *driver)
 {
 	struct typec_altmode_driver *drv = to_altmode_driver(driver);
 	struct typec_altmode *altmode = to_typec_altmode(dev);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 1ca445e..4dbd2e5 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -65,7 +65,7 @@ static void vdpa_dev_remove(struct device *d)
 		drv->remove(vdev);
 }
 
-static int vdpa_dev_match(struct device *dev, struct device_driver *drv)
+static int vdpa_dev_match(struct device *dev, const struct device_driver *drv)
 {
 	struct vdpa_device *vdev = dev_to_vdpa(dev);
 
diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c
index b983229..ad5b834 100644
--- a/drivers/vfio/mdev/mdev_driver.c
+++ b/drivers/vfio/mdev/mdev_driver.c
@@ -31,7 +31,7 @@ static void mdev_remove(struct device *dev)
 		drv->remove(to_mdev_device(dev));
 }
 
-static int mdev_match(struct device *dev, struct device_driver *drv)
+static int mdev_match(struct device *dev, const struct device_driver *drv)
 {
 	/*
 	 * No drivers automatically match. Drivers are only bound by explicit
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 396d3cd..a9b93e9 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -82,7 +82,7 @@ static inline int virtio_id_match(const struct virtio_device *dev,
 
 /* This looks through all the IDs a driver claims to support.  If any of them
  * match, we return 1 and the kernel will call virtio_dev_probe(). */
-static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
+static int virtio_dev_match(struct device *_dv, const struct device_driver *_dr)
 {
 	unsigned int i;
 	struct virtio_device *dev = dev_to_virtio(_dv);
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index c449187..bae1d97 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -946,7 +946,8 @@
 
 config RENESAS_RZG2LWDT
 	tristate "Renesas RZ/G2L WDT Watchdog"
-	depends on ARCH_RENESAS || COMPILE_TEST
+	depends on ARCH_RZG2L || ARCH_R9A09G011 || COMPILE_TEST
+	depends on PM || COMPILE_TEST
 	select WATCHDOG_CORE
 	help
 	  This driver adds watchdog support for the integrated watchdogs in the
diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c
index b21d7a7..94914a2 100644
--- a/drivers/watchdog/imx7ulp_wdt.c
+++ b/drivers/watchdog/imx7ulp_wdt.c
@@ -290,6 +290,11 @@ static int imx7ulp_wdt_init(struct imx7ulp_wdt_device *wdt, unsigned int timeout
 	if (wdt->ext_reset)
 		val |= WDOG_CS_INT_EN;
 
+	if (readl(wdt->base + WDOG_CS) & WDOG_CS_EN) {
+		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
+		val |= WDOG_CS_EN;
+	}
+
 	do {
 		ret = _imx7ulp_wdt_init(wdt, timeout, val);
 		toval = readl(wdt->base + WDOG_TOVAL);
diff --git a/drivers/watchdog/lenovo_se10_wdt.c b/drivers/watchdog/lenovo_se10_wdt.c
index 139ff0e..cd0500e 100644
--- a/drivers/watchdog/lenovo_se10_wdt.c
+++ b/drivers/watchdog/lenovo_se10_wdt.c
@@ -196,8 +196,8 @@ static int se10_wdt_probe(struct platform_device *pdev)
 	watchdog_set_drvdata(&priv->wdd, priv);
 
 	priv->wdd.parent = dev;
-	priv->wdd.info = &wdt_info,
-	priv->wdd.ops = &se10_wdt_ops,
+	priv->wdd.info = &wdt_info;
+	priv->wdd.ops = &se10_wdt_ops;
 	priv->wdd.timeout = WATCHDOG_TIMEOUT; /* Set default timeout */
 	priv->wdd.min_timeout = MIN_TIMEOUT;
 	priv->wdd.max_timeout = MAX_TIMEOUT;
diff --git a/drivers/watchdog/rzg2l_wdt.c b/drivers/watchdog/rzg2l_wdt.c
index 1741f98..2a35f89 100644
--- a/drivers/watchdog/rzg2l_wdt.c
+++ b/drivers/watchdog/rzg2l_wdt.c
@@ -8,7 +8,6 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/io.h>
-#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -54,35 +53,11 @@ struct rzg2l_wdt_priv {
 	struct reset_control *rstc;
 	unsigned long osc_clk_rate;
 	unsigned long delay;
-	unsigned long minimum_assertion_period;
 	struct clk *pclk;
 	struct clk *osc_clk;
 	enum rz_wdt_type devtype;
 };
 
-static int rzg2l_wdt_reset(struct rzg2l_wdt_priv *priv)
-{
-	int err, status;
-
-	if (priv->devtype == WDT_RZV2M) {
-		/* WDT needs TYPE-B reset control */
-		err = reset_control_assert(priv->rstc);
-		if (err)
-			return err;
-		ndelay(priv->minimum_assertion_period);
-		err = reset_control_deassert(priv->rstc);
-		if (err)
-			return err;
-		err = read_poll_timeout(reset_control_status, status,
-					status != 1, 0, 1000, false,
-					priv->rstc);
-	} else {
-		err = reset_control_reset(priv->rstc);
-	}
-
-	return err;
-}
-
 static void rzg2l_wdt_wait_delay(struct rzg2l_wdt_priv *priv)
 {
 	/* delay timer when change the setting register */
@@ -123,8 +98,17 @@ static void rzg2l_wdt_init_timeout(struct watchdog_device *wdev)
 static int rzg2l_wdt_start(struct watchdog_device *wdev)
 {
 	struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	int ret;
 
-	pm_runtime_get_sync(wdev->parent);
+	ret = pm_runtime_resume_and_get(wdev->parent);
+	if (ret)
+		return ret;
+
+	ret = reset_control_deassert(priv->rstc);
+	if (ret) {
+		pm_runtime_put(wdev->parent);
+		return ret;
+	}
 
 	/* Initialize time out */
 	rzg2l_wdt_init_timeout(wdev);
@@ -141,15 +125,23 @@ static int rzg2l_wdt_start(struct watchdog_device *wdev)
 static int rzg2l_wdt_stop(struct watchdog_device *wdev)
 {
 	struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	int ret;
 
-	rzg2l_wdt_reset(priv);
-	pm_runtime_put(wdev->parent);
+	ret = reset_control_assert(priv->rstc);
+	if (ret)
+		return ret;
+
+	ret = pm_runtime_put(wdev->parent);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
 
 static int rzg2l_wdt_set_timeout(struct watchdog_device *wdev, unsigned int timeout)
 {
+	int ret = 0;
+
 	wdev->timeout = timeout;
 
 	/*
@@ -158,22 +150,30 @@ static int rzg2l_wdt_set_timeout(struct watchdog_device *wdev, unsigned int time
 	 * to reset the module) so that it is updated with new timeout values.
 	 */
 	if (watchdog_active(wdev)) {
-		rzg2l_wdt_stop(wdev);
-		rzg2l_wdt_start(wdev);
+		ret = rzg2l_wdt_stop(wdev);
+		if (ret)
+			return ret;
+
+		ret = rzg2l_wdt_start(wdev);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int rzg2l_wdt_restart(struct watchdog_device *wdev,
 			     unsigned long action, void *data)
 {
 	struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
+	int ret;
 
 	clk_prepare_enable(priv->pclk);
 	clk_prepare_enable(priv->osc_clk);
 
 	if (priv->devtype == WDT_RZG2L) {
+		ret = reset_control_deassert(priv->rstc);
+		if (ret)
+			return ret;
+
 		/* Generate Reset (WDTRSTB) Signal on parity error */
 		rzg2l_wdt_write(priv, 0, PECR);
 
@@ -181,7 +181,9 @@ static int rzg2l_wdt_restart(struct watchdog_device *wdev,
 		rzg2l_wdt_write(priv, PEEN_FORCE, PEEN);
 	} else {
 		/* RZ/V2M doesn't have parity error registers */
-		rzg2l_wdt_reset(priv);
+		ret = reset_control_reset(priv->rstc);
+		if (ret)
+			return ret;
 
 		wdev->timeout = 0;
 
@@ -224,13 +226,11 @@ static const struct watchdog_ops rzg2l_wdt_ops = {
 	.restart = rzg2l_wdt_restart,
 };
 
-static void rzg2l_wdt_reset_assert_pm_disable(void *data)
+static void rzg2l_wdt_pm_disable(void *data)
 {
 	struct watchdog_device *wdev = data;
-	struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
 
 	pm_runtime_disable(wdev->parent);
-	reset_control_assert(priv->rstc);
 }
 
 static int rzg2l_wdt_probe(struct platform_device *pdev)
@@ -273,19 +273,8 @@ static int rzg2l_wdt_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, PTR_ERR(priv->rstc),
 				     "failed to get cpg reset");
 
-	ret = reset_control_deassert(priv->rstc);
-	if (ret)
-		return dev_err_probe(dev, ret, "failed to deassert");
-
 	priv->devtype = (uintptr_t)of_device_get_match_data(dev);
 
-	if (priv->devtype == WDT_RZV2M) {
-		priv->minimum_assertion_period = RZV2M_A_NSEC +
-			3 * F2CYCLE_NSEC(pclk_rate) + 5 *
-			max(F2CYCLE_NSEC(priv->osc_clk_rate),
-			    F2CYCLE_NSEC(pclk_rate));
-	}
-
 	pm_runtime_enable(&pdev->dev);
 
 	priv->wdev.info = &rzg2l_wdt_ident;
@@ -297,10 +286,9 @@ static int rzg2l_wdt_probe(struct platform_device *pdev)
 	priv->wdev.timeout = WDT_DEFAULT_TIMEOUT;
 
 	watchdog_set_drvdata(&priv->wdev, priv);
-	ret = devm_add_action_or_reset(&pdev->dev,
-				       rzg2l_wdt_reset_assert_pm_disable,
-				       &priv->wdev);
-	if (ret < 0)
+	dev_set_drvdata(dev, priv);
+	ret = devm_add_action_or_reset(&pdev->dev, rzg2l_wdt_pm_disable, &priv->wdev);
+	if (ret)
 		return ret;
 
 	watchdog_set_nowayout(&priv->wdev, nowayout);
@@ -320,10 +308,35 @@ static const struct of_device_id rzg2l_wdt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, rzg2l_wdt_ids);
 
+static int rzg2l_wdt_suspend_late(struct device *dev)
+{
+	struct rzg2l_wdt_priv *priv = dev_get_drvdata(dev);
+
+	if (!watchdog_active(&priv->wdev))
+		return 0;
+
+	return rzg2l_wdt_stop(&priv->wdev);
+}
+
+static int rzg2l_wdt_resume_early(struct device *dev)
+{
+	struct rzg2l_wdt_priv *priv = dev_get_drvdata(dev);
+
+	if (!watchdog_active(&priv->wdev))
+		return 0;
+
+	return rzg2l_wdt_start(&priv->wdev);
+}
+
+static const struct dev_pm_ops rzg2l_wdt_pm_ops = {
+	LATE_SYSTEM_SLEEP_PM_OPS(rzg2l_wdt_suspend_late, rzg2l_wdt_resume_early)
+};
+
 static struct platform_driver rzg2l_wdt_driver = {
 	.driver = {
 		.name = "rzg2l_wdt",
 		.of_match_table = rzg2l_wdt_ids,
+		.pm = &rzg2l_wdt_pm_ops,
 	},
 	.probe = rzg2l_wdt_probe,
 };
diff --git a/drivers/watchdog/rzn1_wdt.c b/drivers/watchdog/rzn1_wdt.c
index 980c171..7d3192d 100644
--- a/drivers/watchdog/rzn1_wdt.c
+++ b/drivers/watchdog/rzn1_wdt.c
@@ -140,9 +140,9 @@ static int rzn1_wdt_probe(struct platform_device *pdev)
 	}
 
 	wdt->clk_rate_khz = clk_rate / 1000;
-	wdt->wdtdev.info = &rzn1_wdt_info,
-	wdt->wdtdev.ops = &rzn1_wdt_ops,
-	wdt->wdtdev.status = WATCHDOG_NOWAYOUT_INIT_STATUS,
+	wdt->wdtdev.info = &rzn1_wdt_info;
+	wdt->wdtdev.ops = &rzn1_wdt_ops;
+	wdt->wdtdev.status = WATCHDOG_NOWAYOUT_INIT_STATUS;
 	wdt->wdtdev.parent = dev;
 	/*
 	 * The period of the watchdog cannot be changed once set
diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c
index b4b0598..19a2620 100644
--- a/drivers/watchdog/starfive-wdt.c
+++ b/drivers/watchdog/starfive-wdt.c
@@ -152,8 +152,10 @@ static int starfive_wdt_enable_clock(struct starfive_wdt *wdt)
 		return dev_err_probe(wdt->wdd.parent, ret, "failed to enable apb clock\n");
 
 	ret = clk_prepare_enable(wdt->core_clk);
-	if (ret)
+	if (ret) {
+		clk_disable_unprepare(wdt->apb_clk);
 		return dev_err_probe(wdt->wdd.parent, ret, "failed to enable core clock\n");
+	}
 
 	return 0;
 }
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index e2bd266..4190cb8 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -1004,7 +1004,7 @@ static struct miscdevice watchdog_miscdev = {
 	.fops		= &watchdog_fops,
 };
 
-static struct class watchdog_class = {
+static const struct class watchdog_class = {
 	.name =		"watchdog",
 	.dev_groups =	wdt_groups,
 };
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 2754bdf..13821e7 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -104,7 +104,7 @@ void xb_deinit_comms(void);
 int xs_watch_msg(struct xs_watch_event *event);
 void xs_request_exit(struct xb_req_data *req);
 
-int xenbus_match(struct device *_dev, struct device_driver *_drv);
+int xenbus_match(struct device *_dev, const struct device_driver *_drv);
 int xenbus_dev_probe(struct device *_dev);
 void xenbus_dev_remove(struct device *_dev);
 int xenbus_register_driver_common(struct xenbus_driver *drv,
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 1a9ded0..9f097f1 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -94,9 +94,9 @@ match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
 	return NULL;
 }
 
-int xenbus_match(struct device *_dev, struct device_driver *_drv)
+int xenbus_match(struct device *_dev, const struct device_driver *_drv)
 {
-	struct xenbus_driver *drv = to_xenbus_driver(_drv);
+	const struct xenbus_driver *drv = to_xenbus_driver(_drv);
 
 	if (!drv->ids)
 		return 0;
diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c
index f49d199..e7d3af1 100644
--- a/drivers/zorro/zorro-driver.c
+++ b/drivers/zorro/zorro-driver.c
@@ -118,10 +118,10 @@ EXPORT_SYMBOL(zorro_unregister_driver);
      *  supported, and 0 if there is no match.
      */
 
-static int zorro_bus_match(struct device *dev, struct device_driver *drv)
+static int zorro_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct zorro_dev *z = to_zorro_dev(dev);
-	struct zorro_driver *zorro_drv = to_zorro_driver(drv);
+	const struct zorro_driver *zorro_drv = to_zorro_driver(drv);
 	const struct zorro_device_id *ids = zorro_drv->id_table;
 
 	if (!ids)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 5ae8045..19fa49c 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2150,5 +2150,5 @@ core_initcall(init_elf_binfmt);
 module_exit(exit_elf_binfmt);
 
 #ifdef CONFIG_BINFMT_ELF_KUNIT_TEST
-#include "binfmt_elf_test.c"
+#include "tests/binfmt_elf_kunit.c"
 #endif
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index e667dbc..a91acd0 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -630,7 +630,7 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq)
 
 	_enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start);
 
-	subreq->max_len = ULONG_MAX;
+	subreq->max_len = MAX_RW_COUNT;
 	subreq->max_nr_segs = BIO_MAX_VECS;
 
 	if (!cachefiles_cres_file(cres)) {
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c4941ba..e98aa82 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3067,10 +3067,13 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 				       flags, &_got);
 		WARN_ON_ONCE(ret == -EAGAIN);
 		if (!ret) {
+#ifdef CONFIG_DEBUG_FS
 			struct ceph_mds_client *mdsc = fsc->mdsc;
 			struct cap_wait cw;
+#endif
 			DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+#ifdef CONFIG_DEBUG_FS
 			cw.ino = ceph_ino(inode);
 			cw.tgid = current->tgid;
 			cw.need = need;
@@ -3079,6 +3082,7 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 			spin_lock(&mdsc->caps_list_lock);
 			list_add(&cw.list, &mdsc->cap_wait_list);
 			spin_unlock(&mdsc->caps_list_lock);
+#endif
 
 			/* make sure used fmode not timeout */
 			ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS);
@@ -3097,9 +3101,11 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 			remove_wait_queue(&ci->i_cap_wq, &wait);
 			ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS);
 
+#ifdef CONFIG_DEBUG_FS
 			spin_lock(&mdsc->caps_list_lock);
 			list_del(&cw.list);
 			spin_unlock(&mdsc->caps_list_lock);
+#endif
 
 			if (ret == -EAGAIN)
 				continue;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 5aadc56..18c72b3 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1589,7 +1589,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
 	}
 
 	spin_lock(&mdsc->dentry_list_lock);
-	__dentry_dir_lease_touch(mdsc, di),
+	__dentry_dir_lease_touch(mdsc, di);
 	spin_unlock(&mdsc->dentry_list_lock);
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index c2157f6..276e34a 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5446,6 +5446,8 @@ static void delayed_work(struct work_struct *work)
 		}
 		mutex_unlock(&mdsc->mutex);
 
+		ceph_flush_cap_releases(mdsc, s);
+
 		mutex_lock(&s->s_mutex);
 		if (renew_caps)
 			send_renew_caps(mdsc, s);
@@ -5505,7 +5507,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	INIT_DELAYED_WORK(&mdsc->delayed_work, delayed_work);
 	mdsc->last_renew_caps = jiffies;
 	INIT_LIST_HEAD(&mdsc->cap_delay_list);
+#ifdef CONFIG_DEBUG_FS
 	INIT_LIST_HEAD(&mdsc->cap_wait_list);
+#endif
 	spin_lock_init(&mdsc->cap_delay_lock);
 	INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index cfa18cf..9bcc7f1 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -416,6 +416,8 @@ struct ceph_quotarealm_inode {
 	struct inode *inode;
 };
 
+#ifdef CONFIG_DEBUG_FS
+
 struct cap_wait {
 	struct list_head	list;
 	u64			ino;
@@ -424,6 +426,8 @@ struct cap_wait {
 	int			want;
 };
 
+#endif
+
 enum {
 	CEPH_MDSC_STOPPING_BEGIN = 1,
 	CEPH_MDSC_STOPPING_FLUSHING = 2,
@@ -512,7 +516,9 @@ struct ceph_mds_client {
 	spinlock_t	caps_list_lock;
 	struct		list_head caps_list; /* unused (reserved or
 						unreserved) */
+#ifdef CONFIG_DEBUG_FS
 	struct		list_head cap_wait_list;
+#endif
 	int		caps_total_count;    /* total caps allocated */
 	int		caps_use_count;      /* in use */
 	int		caps_use_max;	     /* max used caps */
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 885cb5d..0cdf84c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -961,7 +961,8 @@ static int __init init_caches(void)
 	if (!ceph_mds_request_cachep)
 		goto bad_mds_req;
 
-	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
+	ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+	    (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *));
 	if (!ceph_wb_pagevec_pool)
 		goto bad_pagevec_pool;
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 4dc5140..7f12ff6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -991,7 +991,7 @@ void validate_coredump_safety(void)
 	}
 }
 
-static int proc_dostring_coredump(struct ctl_table *table, int write,
+static int proc_dostring_coredump(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int error = proc_dostring(table, write, buffer, lenp, ppos);
diff --git a/fs/dcache.c b/fs/dcache.c
index 8bdc278..3d8daae 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -177,7 +177,7 @@ static long get_nr_dentry_negative(void)
 	return sum < 0 ? 0 : sum;
 }
 
-static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer,
+static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer,
 			  size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index b957595..d45ef54 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -48,7 +48,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	iput(toput_inode);
 }
 
-int drop_caches_sysctl_handler(struct ctl_table *table, int write,
+int drop_caches_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret;
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 8be6079..1b7eba3 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -21,38 +21,32 @@ void erofs_put_metabuf(struct erofs_buf *buf)
 	if (!buf->page)
 		return;
 	erofs_unmap_metabuf(buf);
-	put_page(buf->page);
+	folio_put(page_folio(buf->page));
 	buf->page = NULL;
 }
 
-/*
- * Derive the block size from inode->i_blkbits to make compatible with
- * anonymous inode in fscache mode.
- */
 void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset,
 		  enum erofs_kmap_type type)
 {
 	pgoff_t index = offset >> PAGE_SHIFT;
-	struct page *page = buf->page;
-	struct folio *folio;
-	unsigned int nofs_flag;
+	struct folio *folio = NULL;
 
-	if (!page || page->index != index) {
+	if (buf->page) {
+		folio = page_folio(buf->page);
+		if (folio_file_page(folio, index) != buf->page)
+			erofs_unmap_metabuf(buf);
+	}
+	if (!folio || !folio_contains(folio, index)) {
 		erofs_put_metabuf(buf);
-
-		nofs_flag = memalloc_nofs_save();
-		folio = read_cache_folio(buf->mapping, index, NULL, NULL);
-		memalloc_nofs_restore(nofs_flag);
+		folio = read_mapping_folio(buf->mapping, index, NULL);
 		if (IS_ERR(folio))
 			return folio;
-
-		/* should already be PageUptodate, no need to lock page */
-		page = folio_file_page(folio, index);
-		buf->page = page;
 	}
+	buf->page = folio_file_page(folio, index);
+
 	if (buf->kmap_type == EROFS_NO_KMAP) {
 		if (type == EROFS_KMAP)
-			buf->base = kmap_local_page(page);
+			buf->base = kmap_local_page(buf->page);
 		buf->kmap_type = type;
 	} else if (buf->kmap_type != type) {
 		DBG_BUGON(1);
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 06a722b8..4066681 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -188,7 +188,7 @@ static int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
 			       !rq->partial_decoding);
 	buf.in_size = min(rq->inputsize, PAGE_SIZE - rq->pageofs_in);
 	rq->inputsize -= buf.in_size;
-	buf.in = dctx.kin + rq->pageofs_in,
+	buf.in = dctx.kin + rq->pageofs_in;
 	dctx.bounce = strm->bounce;
 	do {
 		dctx.avail_out = buf.out_size - buf.out_pos;
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 5f6439a..43c09aa 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -334,14 +334,29 @@ int erofs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		  unsigned int query_flags)
 {
 	struct inode *const inode = d_inode(path->dentry);
+	bool compressed =
+		erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout);
 
-	if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout))
+	if (compressed)
 		stat->attributes |= STATX_ATTR_COMPRESSED;
-
 	stat->attributes |= STATX_ATTR_IMMUTABLE;
 	stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
 				  STATX_ATTR_IMMUTABLE);
 
+	/*
+	 * Return the DIO alignment restrictions if requested.
+	 *
+	 * In EROFS, STATX_DIOALIGN is not supported in ondemand mode and
+	 * compressed files, so in these cases we report no DIO support.
+	 */
+	if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
+		stat->result_mask |= STATX_DIOALIGN;
+		if (!erofs_is_fscache_mode(inode->i_sb) && !compressed) {
+			stat->dio_mem_align =
+				bdev_logical_block_size(inode->i_sb->s_bdev);
+			stat->dio_offset_align = stat->dio_mem_align;
+		}
+	}
 	generic_fillattr(idmap, request_mask, inode, stat);
 	return 0;
 }
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 3526826..32ce5b3 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -576,6 +576,21 @@ static const struct export_operations erofs_export_ops = {
 	.get_parent = erofs_get_parent,
 };
 
+static void erofs_set_sysfs_name(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	if (erofs_is_fscache_mode(sb)) {
+		if (sbi->domain_id)
+			super_set_sysfs_name_generic(sb, "%s,%s",sbi->domain_id,
+						     sbi->fsid);
+		else
+			super_set_sysfs_name_generic(sb, "%s", sbi->fsid);
+		return;
+	}
+	super_set_sysfs_name_id(sb);
+}
+
 static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct inode *inode;
@@ -643,6 +658,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		sb->s_flags |= SB_POSIXACL;
 	else
 		sb->s_flags &= ~SB_POSIXACL;
+	erofs_set_sysfs_name(sb);
 
 #ifdef CONFIG_EROFS_FS_ZIP
 	xa_init(&sbi->managed_pslots);
diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
index b80f612..9b53883 100644
--- a/fs/erofs/zutil.c
+++ b/fs/erofs/zutil.c
@@ -38,11 +38,13 @@ void *z_erofs_get_gbuf(unsigned int requiredpages)
 {
 	struct z_erofs_gbuf *gbuf;
 
+	migrate_disable();
 	gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()];
 	spin_lock(&gbuf->lock);
 	/* check if the buffer is too small */
 	if (requiredpages > gbuf->nrpages) {
 		spin_unlock(&gbuf->lock);
+		migrate_enable();
 		/* (for sparse checker) pretend gbuf->lock is still taken */
 		__acquire(gbuf->lock);
 		return NULL;
@@ -57,6 +59,7 @@ void z_erofs_put_gbuf(void *ptr) __releases(gbuf->lock)
 	gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()];
 	DBG_BUGON(gbuf->ptr != ptr);
 	spin_unlock(&gbuf->lock);
+	migrate_enable();
 }
 
 int z_erofs_gbuf_growsize(unsigned int nrpages)
diff --git a/fs/exec.c b/fs/exec.c
index a47d0e4..a126e3d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2204,7 +2204,7 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
 
 #ifdef CONFIG_SYSCTL
 
-static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
+static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -2236,5 +2236,5 @@ fs_initcall(init_fs_exec_sysctls);
 #endif /* CONFIG_SYSCTL */
 
 #ifdef CONFIG_EXEC_KUNIT_TEST
-#include "exec_test.c"
+#include "tests/exec_kunit.c"
 #endif
diff --git a/fs/file_table.c b/fs/file_table.c
index 4f03bee..ca7843dd 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(get_max_files);
 /*
  * Handle nr_files sysctl
  */
-static int proc_nr_files(struct ctl_table *table, int write, void *buffer,
+static int proc_nr_files(const struct ctl_table *table, int write, void *buffer,
 			 size_t *lenp, loff_t *ppos)
 {
 	files_stat.nr_files = get_nr_files();
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 92a5b82..b865a3f 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2413,7 +2413,7 @@ static int __init start_dirtytime_writeback(void)
 }
 __initcall(start_dirtytime_writeback);
 
-int dirtytime_interval_handler(struct ctl_table *table, int write,
+int dirtytime_interval_handler(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 0239e3a..8b39c15 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -63,9 +63,10 @@ struct hostfs_stat {
 	struct hostfs_timespec atime, mtime, ctime;
 	unsigned int blksize;
 	unsigned long long blocks;
-	unsigned int maj;
-	unsigned int min;
-	dev_t dev;
+	struct {
+		unsigned int maj;
+		unsigned int min;
+	} rdev, dev;
 };
 
 extern int stat_file(const char *path, struct hostfs_stat *p, int fd);
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 3eb747d..22df574 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -17,6 +17,7 @@
 #include <linux/writeback.h>
 #include <linux/mount.h>
 #include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/namei.h>
 #include "hostfs.h"
 #include <init.h>
@@ -455,7 +456,7 @@ static int hostfs_read_folio(struct file *file, struct folio *folio)
 	if (bytes_read < 0)
 		ret = bytes_read;
 	else
-		buffer = folio_zero_tail(folio, bytes_read, buffer);
+		buffer = folio_zero_tail(folio, bytes_read, buffer + bytes_read);
 	kunmap_local(buffer);
 
 	folio_end_read(folio, ret == 0);
@@ -532,10 +533,11 @@ static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st)
 static int hostfs_inode_set(struct inode *ino, void *data)
 {
 	struct hostfs_stat *st = data;
-	dev_t rdev;
+	dev_t dev, rdev;
 
 	/* Reencode maj and min with the kernel encoding.*/
-	rdev = MKDEV(st->maj, st->min);
+	rdev = MKDEV(st->rdev.maj, st->rdev.min);
+	dev = MKDEV(st->dev.maj, st->dev.min);
 
 	switch (st->mode & S_IFMT) {
 	case S_IFLNK:
@@ -561,7 +563,7 @@ static int hostfs_inode_set(struct inode *ino, void *data)
 		return -EIO;
 	}
 
-	HOSTFS_I(ino)->dev = st->dev;
+	HOSTFS_I(ino)->dev = dev;
 	ino->i_ino = st->ino;
 	ino->i_mode = st->mode;
 	return hostfs_inode_update(ino, st);
@@ -570,8 +572,9 @@ static int hostfs_inode_set(struct inode *ino, void *data)
 static int hostfs_inode_test(struct inode *inode, void *data)
 {
 	const struct hostfs_stat *st = data;
+	dev_t dev = MKDEV(st->dev.maj, st->dev.min);
 
-	return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == st->dev;
+	return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == dev;
 }
 
 static struct inode *hostfs_iget(struct super_block *sb, char *name)
@@ -927,7 +930,6 @@ static const struct inode_operations hostfs_link_iops = {
 static int hostfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct hostfs_fs_info *fsi = sb->s_fs_info;
-	const char *host_root = fc->source;
 	struct inode *root_inode;
 	int err;
 
@@ -941,15 +943,6 @@ static int hostfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	/* NULL is printed as '(null)' by printf(): avoid that. */
-	if (fc->source == NULL)
-		host_root = "";
-
-	fsi->host_root_path =
-		kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root);
-	if (fsi->host_root_path == NULL)
-		return -ENOMEM;
-
 	root_inode = hostfs_iget(sb, fsi->host_root_path);
 	if (IS_ERR(root_inode))
 		return PTR_ERR(root_inode);
@@ -975,6 +968,58 @@ static int hostfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	return 0;
 }
 
+enum hostfs_parma {
+	Opt_hostfs,
+};
+
+static const struct fs_parameter_spec hostfs_param_specs[] = {
+	fsparam_string_empty("hostfs",		Opt_hostfs),
+	{}
+};
+
+static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct hostfs_fs_info *fsi = fc->s_fs_info;
+	struct fs_parse_result result;
+	char *host_root;
+	int opt;
+
+	opt = fs_parse(fc, hostfs_param_specs, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_hostfs:
+		host_root = param->string;
+		if (!*host_root)
+			host_root = "";
+		fsi->host_root_path =
+			kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root);
+		if (fsi->host_root_path == NULL)
+			return -ENOMEM;
+		break;
+	}
+
+	return 0;
+}
+
+static int hostfs_parse_monolithic(struct fs_context *fc, void *data)
+{
+	struct hostfs_fs_info *fsi = fc->s_fs_info;
+	char *host_root = (char *)data;
+
+	/* NULL is printed as '(null)' by printf(): avoid that. */
+	if (host_root == NULL)
+		host_root = "";
+
+	fsi->host_root_path =
+		kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root);
+	if (fsi->host_root_path == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int hostfs_fc_get_tree(struct fs_context *fc)
 {
 	return get_tree_nodev(fc, hostfs_fill_super);
@@ -992,6 +1037,8 @@ static void hostfs_fc_free(struct fs_context *fc)
 }
 
 static const struct fs_context_operations hostfs_context_ops = {
+	.parse_monolithic = hostfs_parse_monolithic,
+	.parse_param	= hostfs_parse_param,
 	.get_tree	= hostfs_fc_get_tree,
 	.free		= hostfs_fc_free,
 };
@@ -1040,4 +1087,5 @@ static void __exit exit_hostfs(void)
 
 module_init(init_hostfs)
 module_exit(exit_hostfs)
+MODULE_DESCRIPTION("User-Mode Linux Host filesystem");
 MODULE_LICENSE("GPL");
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index 840619e..97e9c40 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -34,9 +34,10 @@ static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
 	p->mtime.tv_nsec = 0;
 	p->blksize = buf->st_blksize;
 	p->blocks = buf->st_blocks;
-	p->maj = os_major(buf->st_rdev);
-	p->min = os_minor(buf->st_rdev);
-	p->dev = buf->st_dev;
+	p->rdev.maj = os_major(buf->st_rdev);
+	p->rdev.min = os_minor(buf->st_rdev);
+	p->dev.maj = os_major(buf->st_dev);
+	p->dev.min = os_minor(buf->st_dev);
 }
 
 int stat_file(const char *path, struct hostfs_stat *p, int fd)
diff --git a/fs/inode.c b/fs/inode.c
index f356fe2..8667094 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -107,7 +107,7 @@ long get_nr_dirty_inodes(void)
  */
 static struct inodes_stat_t inodes_stat;
 
-static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer,
+static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer,
 			  size_t *lenp, loff_t *ppos)
 {
 	inodes_stat.nr_inodes = get_nr_inodes();
@@ -676,6 +676,16 @@ static void evict(struct inode *inode)
 
 	remove_inode_hash(inode);
 
+	/*
+	 * Wake up waiters in __wait_on_freeing_inode().
+	 *
+	 * Lockless hash lookup may end up finding the inode before we removed
+	 * it above, but only lock it *after* we are done with the wakeup below.
+	 * In this case the potential waiter cannot safely block.
+	 *
+	 * The inode being unhashed after the call to remove_inode_hash() is
+	 * used as an indicator whether blocking on it is safe.
+	 */
 	spin_lock(&inode->i_lock);
 	wake_up_bit(&inode->i_state, __I_NEW);
 	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
@@ -888,18 +898,18 @@ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
 	return freed;
 }
 
-static void __wait_on_freeing_inode(struct inode *inode, bool locked);
+static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked);
 /*
  * Called with the inode lock held.
  */
 static struct inode *find_inode(struct super_block *sb,
 				struct hlist_head *head,
 				int (*test)(struct inode *, void *),
-				void *data, bool locked)
+				void *data, bool is_inode_hash_locked)
 {
 	struct inode *inode = NULL;
 
-	if (locked)
+	if (is_inode_hash_locked)
 		lockdep_assert_held(&inode_hash_lock);
 	else
 		lockdep_assert_not_held(&inode_hash_lock);
@@ -913,7 +923,7 @@ static struct inode *find_inode(struct super_block *sb,
 			continue;
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
-			__wait_on_freeing_inode(inode, locked);
+			__wait_on_freeing_inode(inode, is_inode_hash_locked);
 			goto repeat;
 		}
 		if (unlikely(inode->i_state & I_CREATING)) {
@@ -936,11 +946,11 @@ static struct inode *find_inode(struct super_block *sb,
  */
 static struct inode *find_inode_fast(struct super_block *sb,
 				struct hlist_head *head, unsigned long ino,
-				bool locked)
+				bool is_inode_hash_locked)
 {
 	struct inode *inode = NULL;
 
-	if (locked)
+	if (is_inode_hash_locked)
 		lockdep_assert_held(&inode_hash_lock);
 	else
 		lockdep_assert_not_held(&inode_hash_lock);
@@ -954,7 +964,7 @@ static struct inode *find_inode_fast(struct super_block *sb,
 			continue;
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
-			__wait_on_freeing_inode(inode, locked);
+			__wait_on_freeing_inode(inode, is_inode_hash_locked);
 			goto repeat;
 		}
 		if (unlikely(inode->i_state & I_CREATING)) {
@@ -2287,19 +2297,29 @@ EXPORT_SYMBOL(inode_needs_sync);
  * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
  * will DTRT.
  */
-static void __wait_on_freeing_inode(struct inode *inode, bool locked)
+static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked)
 {
 	wait_queue_head_t *wq;
 	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
+
+	/*
+	 * Handle racing against evict(), see that routine for more details.
+	 */
+	if (unlikely(inode_unhashed(inode))) {
+		WARN_ON(is_inode_hash_locked);
+		spin_unlock(&inode->i_lock);
+		return;
+	}
+
 	wq = bit_waitqueue(&inode->i_state, __I_NEW);
 	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 	spin_unlock(&inode->i_lock);
 	rcu_read_unlock();
-	if (locked)
+	if (is_inode_hash_locked)
 		spin_unlock(&inode_hash_lock);
 	schedule();
 	finish_wait(wq, &wait.wq_entry);
-	if (locked)
+	if (is_inode_hash_locked)
 		spin_lock(&inode_hash_lock);
 	rcu_read_lock();
 }
diff --git a/fs/locks.c b/fs/locks.c
index bdd94c3..9afb16e 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2570,8 +2570,9 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by releasing the
-	 * lock that was just acquired. There is no need to do that when we're
+	 * Detect close/fcntl races and recover by zapping all POSIX locks
+	 * associated with this file and our files_struct, just like on
+	 * filp_flush(). There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
 	if (!error && file_lock->c.flc_type != F_UNLCK &&
@@ -2586,9 +2587,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->c.flc_type = F_UNLCK;
-			error = do_lock_file_wait(filp, cmd, file_lock);
-			WARN_ON_ONCE(error);
+			locks_remove_posix(filp, files);
 			error = -EBADF;
 		}
 	}
diff --git a/fs/namei.c b/fs/namei.c
index 3a4c40e..5512cb1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3248,9 +3248,9 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
 /**
  * vfs_create - create new file
  * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- * @mode:	mode of the new file
+ * @dir:	inode of the parent directory
+ * @dentry:	dentry of the child file
+ * @mode:	mode of the child file
  * @want_excl:	whether the file must not yet exist
  *
  * Create a new file.
@@ -4047,9 +4047,9 @@ EXPORT_SYMBOL(user_path_create);
 /**
  * vfs_mknod - create device node or file
  * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- * @mode:	mode of the new device node or file
+ * @dir:	inode of the parent directory
+ * @dentry:	dentry of the child device node
+ * @mode:	mode of the child device node
  * @dev:	device number of device to create
  *
  * Create a device node or file.
@@ -4174,9 +4174,9 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
 /**
  * vfs_mkdir - create directory
  * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- * @mode:	mode of the new directory
+ * @dir:	inode of the parent directory
+ * @dentry:	dentry of the child directory
+ * @mode:	mode of the child directory
  *
  * Create a directory.
  *
@@ -4256,8 +4256,8 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 /**
  * vfs_rmdir - remove directory
  * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
+ * @dir:	inode of the parent directory
+ * @dentry:	dentry of the child directory
  *
  * Remove a directory.
  *
@@ -4537,8 +4537,8 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname)
 /**
  * vfs_symlink - create symlink
  * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
+ * @dir:	inode of the parent directory
+ * @dentry:	dentry of the child symlink file
  * @oldname:	name of the file to link to
  *
  * Create a symlink.
diff --git a/fs/namespace.c b/fs/namespace.c
index 221db9d..328087a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -70,7 +70,7 @@ static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 
 /* Don't allow confusion with old 32bit mount ID */
-#define MNT_UNIQUE_ID_OFFSET (1ULL << 32)
+#define MNT_UNIQUE_ID_OFFSET (1ULL << 31)
 static atomic64_t mnt_id_ctr = ATOMIC64_INIT(MNT_UNIQUE_ID_OFFSET);
 
 static struct hlist_head *mount_hashtable __ro_after_init;
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index bec805e..1b78e8b 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -22,6 +22,14 @@
 	  between CPUs.  On the other hand, the stats are very useful for
 	  debugging purposes.  Saying 'Y' here is recommended.
 
+config NETFS_DEBUG
+	bool "Enable dynamic debugging netfslib and FS-Cache"
+	depends on NETFS
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/module/netfs/parameters/debug.
+
 config FSCACHE
 	bool "General filesystem local caching manager"
 	depends on NETFS_SUPPORT
@@ -50,13 +58,3 @@
 	  debugging purposes.  Saying 'Y' here is recommended.
 
 	  See Documentation/filesystems/caching/fscache.rst for more information.
-
-config FSCACHE_DEBUG
-	bool "Debug FS-Cache"
-	depends on FSCACHE
-	help
-	  This permits debugging to be dynamically enabled in the local caching
-	  management module.  If this is set, the debugging output may be
-	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
-
-	  See Documentation/filesystems/caching/fscache.rst for more information.
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index a6d5d07c..a688d4c 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -117,7 +117,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
 			if (folio->index == rreq->no_unlock_folio &&
 			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
-				kdebug("no unlock");
+				_debug("no unlock");
 			else
 				folio_unlock(folio);
 		}
@@ -204,7 +204,7 @@ void netfs_readahead(struct readahead_control *ractl)
 	struct netfs_inode *ctx = netfs_inode(ractl->mapping->host);
 	int ret;
 
-	kenter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
+	_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
 
 	if (readahead_count(ractl) == 0)
 		return;
@@ -268,7 +268,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct folio *sink = NULL;
 	int ret;
 
-	kenter("%lx", folio->index);
+	_enter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
 				   folio_pos(folio), folio_size(folio),
@@ -508,7 +508,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
 
 have_folio:
 	*_folio = folio;
-	kleave(" = 0");
+	_leave(" = 0");
 	return 0;
 
 error_put:
@@ -518,7 +518,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
 		folio_unlock(folio);
 		folio_put(folio);
 	}
-	kleave(" = %d", ret);
+	_leave(" = %d", ret);
 	return ret;
 }
 EXPORT_SYMBOL(netfs_write_begin);
@@ -536,7 +536,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 	size_t flen = folio_size(folio);
 	int ret;
 
-	kenter("%zx @%llx", flen, start);
+	_enter("%zx @%llx", flen, start);
 
 	ret = -ENOMEM;
 
@@ -567,7 +567,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 error_put:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
 error:
-	kleave(" = %d", ret);
+	_leave(" = %d", ret);
 	return ret;
 }
 
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 68a3f13..4726c31 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -56,7 +56,7 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	struct netfs_group *group = netfs_folio_group(folio);
 	loff_t pos = folio_pos(folio);
 
-	kenter("");
+	_enter("");
 
 	if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE)
 		return NETFS_FLUSH_CONTENT;
@@ -272,12 +272,12 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		 */
 		howto = netfs_how_to_modify(ctx, file, folio, netfs_group,
 					    flen, offset, part, maybe_trouble);
-		kdebug("howto %u", howto);
+		_debug("howto %u", howto);
 		switch (howto) {
 		case NETFS_JUST_PREFETCH:
 			ret = netfs_prefetch_for_write(file, folio, offset, part);
 			if (ret < 0) {
-				kdebug("prefetch = %zd", ret);
+				_debug("prefetch = %zd", ret);
 				goto error_folio_unlock;
 			}
 			break;
@@ -418,7 +418,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	iocb->ki_pos += written;
-	kleave(" = %zd [%zd]", written, ret);
+	_leave(" = %zd [%zd]", written, ret);
 	return written ? written : ret;
 
 error_folio_unlock:
@@ -491,7 +491,7 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct netfs_inode *ictx = netfs_inode(inode);
 	ssize_t ret;
 
-	kenter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
 
 	if (!iov_iter_count(from))
 		return 0;
@@ -529,7 +529,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	vm_fault_t ret = VM_FAULT_RETRY;
 	int err;
 
-	kenter("%lx", folio->index);
+	_enter("%lx", folio->index);
 
 	sb_start_pagefault(inode->i_sb);
 
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
index b6debac..10a1e4d 100644
--- a/fs/netfs/direct_read.c
+++ b/fs/netfs/direct_read.c
@@ -33,7 +33,7 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i
 	size_t orig_count = iov_iter_count(iter);
 	bool async = !is_sync_kiocb(iocb);
 
-	kenter("");
+	_enter("");
 
 	if (!orig_count)
 		return 0; /* Don't update atime */
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 792ef17..88f2adf 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -37,7 +37,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	size_t len = iov_iter_count(iter);
 	bool async = !is_sync_kiocb(iocb);
 
-	kenter("");
+	_enter("");
 
 	/* We're going to need a bounce buffer if what we transmit is going to
 	 * be different in some way to the source buffer, e.g. because it gets
@@ -45,7 +45,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	 */
 	// TODO
 
-	kdebug("uw %llx-%llx", start, end);
+	_debug("uw %llx-%llx", start, end);
 
 	wreq = netfs_create_write_req(iocb->ki_filp->f_mapping, iocb->ki_filp, start,
 				      iocb->ki_flags & IOCB_DIRECT ?
@@ -96,7 +96,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	wreq->cleanup = netfs_cleanup_dio_write;
 	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
 	if (ret < 0) {
-		kdebug("begin = %zd", ret);
+		_debug("begin = %zd", ret);
 		goto out;
 	}
 
@@ -143,7 +143,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	loff_t pos = iocb->ki_pos;
 	unsigned long long end = pos + iov_iter_count(from) - 1;
 
-	kenter("%llx,%zx,%llx", pos, iov_iter_count(from), i_size_read(inode));
+	_enter("%llx,%zx,%llx", pos, iov_iter_count(from), i_size_read(inode));
 
 	if (!iov_iter_count(from))
 		return 0;
diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c
index 288a73c..9397ed3 100644
--- a/fs/netfs/fscache_cache.c
+++ b/fs/netfs/fscache_cache.c
@@ -237,7 +237,7 @@ int fscache_add_cache(struct fscache_cache *cache,
 {
 	int n_accesses;
 
-	kenter("{%s,%s}", ops->name, cache->name);
+	_enter("{%s,%s}", ops->name, cache->name);
 
 	BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING);
 
@@ -257,7 +257,7 @@ int fscache_add_cache(struct fscache_cache *cache,
 
 	up_write(&fscache_addremove_sem);
 	pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name);
-	kleave(" = 0 [%s]", cache->name);
+	_leave(" = 0 [%s]", cache->name);
 	return 0;
 }
 EXPORT_SYMBOL(fscache_add_cache);
diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
index 4d1e8bf..bce2492 100644
--- a/fs/netfs/fscache_cookie.c
+++ b/fs/netfs/fscache_cookie.c
@@ -456,7 +456,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
 {
 	struct fscache_cookie *cookie;
 
-	kenter("V=%x", volume->debug_id);
+	_enter("V=%x", volume->debug_id);
 
 	if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255)
 		return NULL;
@@ -484,7 +484,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
 
 	trace_fscache_acquire(cookie);
 	fscache_stat(&fscache_n_acquires_ok);
-	kleave(" = c=%08x", cookie->debug_id);
+	_leave(" = c=%08x", cookie->debug_id);
 	return cookie;
 }
 EXPORT_SYMBOL(__fscache_acquire_cookie);
@@ -505,7 +505,7 @@ static void fscache_perform_lookup(struct fscache_cookie *cookie)
 	enum fscache_access_trace trace = fscache_access_lookup_cookie_end_failed;
 	bool need_withdraw = false;
 
-	kenter("");
+	_enter("");
 
 	if (!cookie->volume->cache_priv) {
 		fscache_create_volume(cookie->volume, true);
@@ -519,7 +519,7 @@ static void fscache_perform_lookup(struct fscache_cookie *cookie)
 		if (cookie->state != FSCACHE_COOKIE_STATE_FAILED)
 			fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT);
 		need_withdraw = true;
-		kleave(" [fail]");
+		_leave(" [fail]");
 		goto out;
 	}
 
@@ -572,7 +572,7 @@ void __fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify)
 	bool queue = false;
 	int n_active;
 
-	kenter("c=%08x", cookie->debug_id);
+	_enter("c=%08x", cookie->debug_id);
 
 	if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags),
 		 "Trying to use relinquished cookie\n"))
@@ -636,7 +636,7 @@ void __fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify)
 	spin_unlock(&cookie->lock);
 	if (queue)
 		fscache_queue_cookie(cookie, fscache_cookie_get_use_work);
-	kleave("");
+	_leave("");
 }
 EXPORT_SYMBOL(__fscache_use_cookie);
 
@@ -702,7 +702,7 @@ static void fscache_cookie_state_machine(struct fscache_cookie *cookie)
 	enum fscache_cookie_state state;
 	bool wake = false;
 
-	kenter("c=%x", cookie->debug_id);
+	_enter("c=%x", cookie->debug_id);
 
 again:
 	spin_lock(&cookie->lock);
@@ -820,7 +820,7 @@ static void fscache_cookie_state_machine(struct fscache_cookie *cookie)
 	spin_unlock(&cookie->lock);
 	if (wake)
 		wake_up_cookie_state(cookie);
-	kleave("");
+	_leave("");
 }
 
 static void fscache_cookie_worker(struct work_struct *work)
@@ -867,7 +867,7 @@ static void fscache_cookie_lru_do_one(struct fscache_cookie *cookie)
 		set_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags);
 		spin_unlock(&cookie->lock);
 		fscache_stat(&fscache_n_cookies_lru_expired);
-		kdebug("lru c=%x", cookie->debug_id);
+		_debug("lru c=%x", cookie->debug_id);
 		__fscache_withdraw_cookie(cookie);
 	}
 
@@ -971,7 +971,7 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire)
 	if (retire)
 		fscache_stat(&fscache_n_relinquishes_retire);
 
-	kenter("c=%08x{%d},%d",
+	_enter("c=%08x{%d},%d",
 	       cookie->debug_id, atomic_read(&cookie->n_active), retire);
 
 	if (WARN(test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags),
@@ -1050,7 +1050,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie,
 {
 	bool is_caching;
 
-	kenter("c=%x", cookie->debug_id);
+	_enter("c=%x", cookie->debug_id);
 
 	fscache_stat(&fscache_n_invalidates);
 
@@ -1072,7 +1072,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie,
 	case FSCACHE_COOKIE_STATE_INVALIDATING: /* is_still_valid will catch it */
 	default:
 		spin_unlock(&cookie->lock);
-		kleave(" [no %u]", cookie->state);
+		_leave(" [no %u]", cookie->state);
 		return;
 
 	case FSCACHE_COOKIE_STATE_LOOKING_UP:
@@ -1081,7 +1081,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie,
 		fallthrough;
 	case FSCACHE_COOKIE_STATE_CREATING:
 		spin_unlock(&cookie->lock);
-		kleave(" [look %x]", cookie->inval_counter);
+		_leave(" [look %x]", cookie->inval_counter);
 		return;
 
 	case FSCACHE_COOKIE_STATE_ACTIVE:
@@ -1094,7 +1094,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie,
 
 		if (is_caching)
 			fscache_queue_cookie(cookie, fscache_cookie_get_inval_work);
-		kleave(" [inv]");
+		_leave(" [inv]");
 		return;
 	}
 }
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index bf4eaee..38637e5 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -28,12 +28,12 @@ bool fscache_wait_for_operation(struct netfs_cache_resources *cres,
 
 again:
 	if (!fscache_cache_is_live(cookie->volume->cache)) {
-		kleave(" [broken]");
+		_leave(" [broken]");
 		return false;
 	}
 
 	state = fscache_cookie_state(cookie);
-	kenter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
+	_enter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
 
 	switch (state) {
 	case FSCACHE_COOKIE_STATE_CREATING:
@@ -52,7 +52,7 @@ bool fscache_wait_for_operation(struct netfs_cache_resources *cres,
 	case FSCACHE_COOKIE_STATE_DROPPED:
 	case FSCACHE_COOKIE_STATE_RELINQUISHING:
 	default:
-		kleave(" [not live]");
+		_leave(" [not live]");
 		return false;
 	}
 
@@ -92,7 +92,7 @@ static int fscache_begin_operation(struct netfs_cache_resources *cres,
 	spin_lock(&cookie->lock);
 
 	state = fscache_cookie_state(cookie);
-	kenter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
+	_enter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
 
 	switch (state) {
 	case FSCACHE_COOKIE_STATE_LOOKING_UP:
@@ -140,7 +140,7 @@ static int fscache_begin_operation(struct netfs_cache_resources *cres,
 	cres->cache_priv = NULL;
 	cres->ops = NULL;
 	fscache_end_cookie_access(cookie, fscache_access_io_not_live);
-	kleave(" = -ENOBUFS");
+	_leave(" = -ENOBUFS");
 	return -ENOBUFS;
 }
 
@@ -224,7 +224,7 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie,
 	if (len == 0)
 		goto abandon;
 
-	kenter("%llx,%zx", start, len);
+	_enter("%llx,%zx", start, len);
 
 	wreq = kzalloc(sizeof(struct fscache_write_request), GFP_NOFS);
 	if (!wreq)
diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
index bf9b33d..42e98bb 100644
--- a/fs/netfs/fscache_main.c
+++ b/fs/netfs/fscache_main.c
@@ -99,7 +99,7 @@ int __init fscache_init(void)
  */
 void __exit fscache_exit(void)
 {
-	kenter("");
+	_enter("");
 
 	kmem_cache_destroy(fscache_cookie_jar);
 	fscache_proc_cleanup();
diff --git a/fs/netfs/fscache_volume.c b/fs/netfs/fscache_volume.c
index 2e2a405..cb75c07 100644
--- a/fs/netfs/fscache_volume.c
+++ b/fs/netfs/fscache_volume.c
@@ -264,7 +264,7 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key,
 	fscache_see_volume(volume, fscache_volume_new_acquire);
 	fscache_stat(&fscache_n_volumes);
 	up_write(&fscache_addremove_sem);
-	kleave(" = v=%x", volume->debug_id);
+	_leave(" = v=%x", volume->debug_id);
 	return volume;
 
 err_vol:
@@ -466,7 +466,7 @@ void fscache_withdraw_volume(struct fscache_volume *volume)
 {
 	int n_accesses;
 
-	kdebug("withdraw V=%x", volume->debug_id);
+	_debug("withdraw V=%x", volume->debug_id);
 
 	/* Allow wakeups on dec-to-0 */
 	n_accesses = atomic_dec_return(&volume->n_accesses);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 21e46bc..7773f3d8 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -34,6 +34,7 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync);
 /*
  * main.c
  */
+extern unsigned int netfs_debug;
 extern struct list_head netfs_io_requests;
 extern spinlock_t netfs_proc_lock;
 extern mempool_t netfs_request_pool;
@@ -353,12 +354,42 @@ void fscache_create_volume(struct fscache_volume *volume, bool wait);
  * debug tracing
  */
 #define dbgprintk(FMT, ...) \
-	pr_debug("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
 #define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
 #define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
 
+#ifdef __KDEBUG
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_NETFS_DEBUG)
+#define _enter(FMT, ...)			\
+do {						\
+	if (netfs_debug)			\
+		kenter(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _leave(FMT, ...)			\
+do {						\
+	if (netfs_debug)			\
+		kleave(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _debug(FMT, ...)			\
+do {						\
+	if (netfs_debug)			\
+		kdebug(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#else
+#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
+#endif
+
 /*
  * assertions
  */
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c757648..c93851b 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -130,7 +130,7 @@ static void netfs_reset_subreq_iter(struct netfs_io_request *rreq,
 	if (count == remaining)
 		return;
 
-	kdebug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
+	_debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
 	       rreq->debug_id, subreq->debug_index,
 	       iov_iter_count(&subreq->io_iter), subreq->transferred,
 	       subreq->len, rreq->i_size,
@@ -326,7 +326,7 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 	int u;
 
-	kenter("R=%x[%x]{%llx,%lx},%zd",
+	_enter("R=%x[%x]{%llx,%lx},%zd",
 	       rreq->debug_id, subreq->debug_index,
 	       subreq->start, subreq->flags, transferred_or_error);
 
@@ -435,7 +435,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	size_t lsize;
 
-	kenter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
+	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
 	if (rreq->origin != NETFS_DIO_READ) {
 		source = netfs_cache_prepare_read(subreq, rreq->i_size);
@@ -518,7 +518,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 	subreq->start		= rreq->start + rreq->submitted;
 	subreq->len		= io_iter->count;
 
-	kdebug("slice %llx,%zx,%llx", subreq->start, subreq->len, rreq->submitted);
+	_debug("slice %llx,%zx,%llx", subreq->start, subreq->len, rreq->submitted);
 	list_add_tail(&subreq->rreq_link, &rreq->subrequests);
 
 	/* Call out to the cache to find out what it can do with the remaining
@@ -570,7 +570,7 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	struct iov_iter io_iter;
 	int ret;
 
-	kenter("R=%x %llx-%llx",
+	_enter("R=%x %llx-%llx",
 	       rreq->debug_id, rreq->start, rreq->start + rreq->len - 1);
 
 	if (rreq->len == 0) {
@@ -593,7 +593,7 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
-		kdebug("submit %llx + %llx >= %llx",
+		_debug("submit %llx + %llx >= %llx",
 		       rreq->start, rreq->submitted, rreq->i_size);
 		if (rreq->origin == NETFS_DIO_READ &&
 		    rreq->start + rreq->submitted >= rreq->i_size)
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index db824c3..5f0f438 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -20,6 +20,10 @@ MODULE_LICENSE("GPL");
 
 EXPORT_TRACEPOINT_SYMBOL(netfs_sreq);
 
+unsigned netfs_debug;
+module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
+
 static struct kmem_cache *netfs_request_slab;
 static struct kmem_cache *netfs_subrequest_slab;
 mempool_t netfs_request_pool;
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 172808e..83e644b 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -26,7 +26,7 @@ bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio)
 	struct fscache_cookie *cookie = netfs_i_cookie(ictx);
 	bool need_use = false;
 
-	kenter("");
+	_enter("");
 
 	if (!filemap_dirty_folio(mapping, folio))
 		return false;
@@ -99,7 +99,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 	struct netfs_folio *finfo;
 	size_t flen = folio_size(folio);
 
-	kenter("{%lx},%zx,%zx", folio->index, offset, length);
+	_enter("{%lx},%zx,%zx", folio->index, offset, length);
 
 	if (!folio_test_private(folio))
 		return;
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 4881474..426cf87 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -161,7 +161,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 {
 	struct list_head *next;
 
-	kenter("R=%x[%x:]", wreq->debug_id, stream->stream_nr);
+	_enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr);
 
 	if (list_empty(&stream->subrequests))
 		return;
@@ -374,7 +374,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq)
 	unsigned int notes;
 	int s;
 
-	kenter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+	_enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
 	trace_netfs_collect(wreq);
 	trace_netfs_rreq(wreq, netfs_rreq_trace_collect);
 
@@ -409,7 +409,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq)
 		front = stream->front;
 		while (front) {
 			trace_netfs_collect_sreq(wreq, front);
-			//kdebug("sreq [%x] %llx %zx/%zx",
+			//_debug("sreq [%x] %llx %zx/%zx",
 			//       front->debug_index, front->start, front->transferred, front->len);
 
 			/* Stall if there may be a discontinuity. */
@@ -598,7 +598,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq)
 out:
 	netfs_put_group_many(wreq->group, wreq->nr_group_rel);
 	wreq->nr_group_rel = 0;
-	kleave(" = %x", notes);
+	_leave(" = %x", notes);
 	return;
 
 need_retry:
@@ -606,7 +606,7 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq)
 	 * that any partially completed op will have had any wholly transferred
 	 * folios removed from it.
 	 */
-	kdebug("retry");
+	_debug("retry");
 	netfs_retry_writes(wreq);
 	goto out;
 }
@@ -621,7 +621,7 @@ void netfs_write_collection_worker(struct work_struct *work)
 	size_t transferred;
 	int s;
 
-	kenter("R=%x", wreq->debug_id);
+	_enter("R=%x", wreq->debug_id);
 
 	netfs_see_request(wreq, netfs_rreq_trace_see_work);
 	if (!test_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags)) {
@@ -684,7 +684,7 @@ void netfs_write_collection_worker(struct work_struct *work)
 	if (wreq->origin == NETFS_DIO_WRITE)
 		inode_dio_end(wreq->inode);
 
-	kdebug("finished");
+	_debug("finished");
 	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
@@ -744,7 +744,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
 	struct netfs_io_request *wreq = subreq->rreq;
 	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 
-	kenter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
+	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
 
 	switch (subreq->source) {
 	case NETFS_UPLOAD_TO_SERVER:
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index d7c971d..9258d30 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -99,7 +99,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	if (IS_ERR(wreq))
 		return wreq;
 
-	kenter("R=%x", wreq->debug_id);
+	_enter("R=%x", wreq->debug_id);
 
 	ictx = netfs_inode(wreq->inode);
 	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
@@ -122,6 +122,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	wreq->io_streams[1].transferred		= LONG_MAX;
 	if (fscache_resources_valid(&wreq->cache_resources)) {
 		wreq->io_streams[1].avail	= true;
+		wreq->io_streams[1].active	= true;
 		wreq->io_streams[1].prepare_write = wreq->cache_resources.ops->prepare_write_subreq;
 		wreq->io_streams[1].issue_write = wreq->cache_resources.ops->issue_write;
 	}
@@ -159,7 +160,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq,
 	subreq->max_nr_segs	= INT_MAX;
 	subreq->stream_nr	= stream->stream_nr;
 
-	kenter("R=%x[%x]", wreq->debug_id, subreq->debug_index);
+	_enter("R=%x[%x]", wreq->debug_id, subreq->debug_index);
 
 	trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
 			     refcount_read(&subreq->ref),
@@ -215,7 +216,7 @@ static void netfs_do_issue_write(struct netfs_io_stream *stream,
 {
 	struct netfs_io_request *wreq = subreq->rreq;
 
-	kenter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
+	_enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
 
 	if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
 		return netfs_write_subrequest_terminated(subreq, subreq->error, false);
@@ -272,11 +273,11 @@ int netfs_advance_write(struct netfs_io_request *wreq,
 	size_t part;
 
 	if (!stream->avail) {
-		kleave("no write");
+		_leave("no write");
 		return len;
 	}
 
-	kenter("R=%x[%x]", wreq->debug_id, subreq ? subreq->debug_index : 0);
+	_enter("R=%x[%x]", wreq->debug_id, subreq ? subreq->debug_index : 0);
 
 	if (subreq && start != subreq->start + subreq->len) {
 		netfs_issue_write(wreq, stream);
@@ -288,7 +289,7 @@ int netfs_advance_write(struct netfs_io_request *wreq,
 	subreq = stream->construct;
 
 	part = min(subreq->max_len - subreq->len, len);
-	kdebug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len);
+	_debug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len);
 	subreq->len += part;
 	subreq->nr_segs++;
 
@@ -319,7 +320,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 	bool to_eof = false, streamw = false;
 	bool debug = false;
 
-	kenter("");
+	_enter("");
 
 	/* netfs_perform_write() may shift i_size around the page or from out
 	 * of the page to beyond it, but cannot move i_size into or through the
@@ -329,7 +330,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 
 	if (fpos >= i_size) {
 		/* mmap beyond eof. */
-		kdebug("beyond eof");
+		_debug("beyond eof");
 		folio_start_writeback(folio);
 		folio_unlock(folio);
 		wreq->nr_group_rel += netfs_folio_written_back(folio);
@@ -363,7 +364,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 	}
 	flen -= foff;
 
-	kdebug("folio %zx %zx %zx", foff, flen, fsize);
+	_debug("folio %zx %zx %zx", foff, flen, fsize);
 
 	/* Deal with discontinuities in the stream of dirty pages.  These can
 	 * arise from a number of sources:
@@ -487,7 +488,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 		for (int s = 0; s < NR_IO_STREAMS; s++)
 			netfs_issue_write(wreq, &wreq->io_streams[s]);
 
-	kleave(" = 0");
+	_leave(" = 0");
 	return 0;
 }
 
@@ -522,7 +523,7 @@ int netfs_writepages(struct address_space *mapping,
 	netfs_stat(&netfs_n_wh_writepages);
 
 	do {
-		kdebug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted);
+		_debug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted);
 
 		/* It appears we don't have to handle cyclic writeback wrapping. */
 		WARN_ON_ONCE(wreq && folio_pos(folio) < wreq->start + wreq->submitted);
@@ -546,14 +547,14 @@ int netfs_writepages(struct address_space *mapping,
 	mutex_unlock(&ictx->wb_lock);
 
 	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
-	kleave(" = %d", error);
+	_leave(" = %d", error);
 	return error;
 
 couldnt_start:
 	netfs_kill_dirty_pages(mapping, wbc, folio);
 out:
 	mutex_unlock(&ictx->wb_lock);
-	kleave(" = %d", error);
+	_leave(" = %d", error);
 	return error;
 }
 EXPORT_SYMBOL(netfs_writepages);
@@ -590,7 +591,7 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 			       struct folio *folio, size_t copied, bool to_page_end,
 			       struct folio **writethrough_cache)
 {
-	kenter("R=%x ic=%zu ws=%u cp=%zu tp=%u",
+	_enter("R=%x ic=%zu ws=%u cp=%zu tp=%u",
 	       wreq->debug_id, wreq->iter.count, wreq->wsize, copied, to_page_end);
 
 	if (!*writethrough_cache) {
@@ -624,7 +625,7 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	int ret;
 
-	kenter("R=%x", wreq->debug_id);
+	_enter("R=%x", wreq->debug_id);
 
 	if (writethrough_cache)
 		netfs_write_folio(wreq, wbc, writethrough_cache);
@@ -657,7 +658,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
 	loff_t start = wreq->start;
 	int error = 0;
 
-	kenter("%zx", len);
+	_enter("%zx", len);
 
 	if (wreq->origin == NETFS_DIO_WRITE)
 		inode_dio_begin(wreq->inode);
@@ -665,7 +666,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
 	while (len) {
 		// TODO: Prepare content encryption
 
-		kdebug("unbuffered %zx", len);
+		_debug("unbuffered %zx", len);
 		part = netfs_advance_write(wreq, upload, start, len, false);
 		start += part;
 		len -= part;
@@ -684,6 +685,6 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
 	if (list_empty(&upload->subrequests))
 		netfs_wake_write_collector(wreq, false);
 
-	kleave(" = %d", error);
+	_leave(" = %d", error);
 	return error;
 }
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 0131d83..c034080 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 
 	bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
 	if (unlikely(!bh))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) ||
 		     buffer_dirty(bh))) {
-		brelse(bh);
-		BUG();
+		/*
+		 * The block buffer at the specified new address was already
+		 * in use.  This can happen if it is a virtual block number
+		 * and has been reallocated due to corruption of the bitmap
+		 * used to manage its allocation state (if not, the buffer
+		 * clearing of an abandoned b-tree node is missing somewhere).
+		 */
+		nilfs_error(inode->i_sb,
+			    "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)",
+			    (unsigned long long)blocknr, inode->i_ino);
+		goto failed;
 	}
 	memset(bh->b_data, 0, i_blocksize(inode));
 	bh->b_bdev = inode->i_sb->s_bdev;
@@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 	folio_unlock(bh->b_folio);
 	folio_put(bh->b_folio);
 	return bh;
+
+failed:
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
+	brelse(bh);
+	return ERR_PTR(-EIO);
 }
 
 int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
@@ -217,8 +232,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
 	}
 
 	nbh = nilfs_btnode_create_block(btnc, newkey);
-	if (!nbh)
-		return -ENOMEM;
+	if (IS_ERR(nbh))
+		return PTR_ERR(nbh);
 
 	BUG_ON(nbh == obh);
 	ctxt->newbh = nbh;
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index a139970..862bdf2 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree,
 	struct buffer_head *bh;
 
 	bh = nilfs_btnode_create_block(btnc, ptr);
-	if (!bh)
-		return -ENOMEM;
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 
 	set_buffer_nilfs_volatile(bh);
 	*bhp = bh;
diff --git a/fs/pidfs.c b/fs/pidfs.c
index c9cb141..7ffdc88 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -119,7 +119,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct task_struct *task __free(put_task) = NULL;
 	struct nsproxy *nsp __free(put_nsproxy) = NULL;
 	struct pid *pid = pidfd_pid(file);
-	struct ns_common *ns_common;
+	struct ns_common *ns_common = NULL;
 
 	if (arg)
 		return -EINVAL;
@@ -146,52 +146,73 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	switch (cmd) {
 	/* Namespaces that hang of nsproxy. */
 	case PIDFD_GET_CGROUP_NAMESPACE:
-		get_cgroup_ns(nsp->cgroup_ns);
-		ns_common = to_ns_common(nsp->cgroup_ns);
+		if (IS_ENABLED(CONFIG_CGROUPS)) {
+			get_cgroup_ns(nsp->cgroup_ns);
+			ns_common = to_ns_common(nsp->cgroup_ns);
+		}
 		break;
 	case PIDFD_GET_IPC_NAMESPACE:
-		get_ipc_ns(nsp->ipc_ns);
-		ns_common = to_ns_common(nsp->ipc_ns);
+		if (IS_ENABLED(CONFIG_IPC_NS)) {
+			get_ipc_ns(nsp->ipc_ns);
+			ns_common = to_ns_common(nsp->ipc_ns);
+		}
 		break;
 	case PIDFD_GET_MNT_NAMESPACE:
 		get_mnt_ns(nsp->mnt_ns);
 		ns_common = to_ns_common(nsp->mnt_ns);
 		break;
 	case PIDFD_GET_NET_NAMESPACE:
-		ns_common = to_ns_common(nsp->net_ns);
-		get_net_ns(ns_common);
+		if (IS_ENABLED(CONFIG_NET_NS)) {
+			ns_common = to_ns_common(nsp->net_ns);
+			get_net_ns(ns_common);
+		}
 		break;
 	case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE:
-		get_pid_ns(nsp->pid_ns_for_children);
-		ns_common = to_ns_common(nsp->pid_ns_for_children);
+		if (IS_ENABLED(CONFIG_PID_NS)) {
+			get_pid_ns(nsp->pid_ns_for_children);
+			ns_common = to_ns_common(nsp->pid_ns_for_children);
+		}
 		break;
 	case PIDFD_GET_TIME_NAMESPACE:
-		get_time_ns(nsp->time_ns);
-		ns_common = to_ns_common(nsp->time_ns);
+		if (IS_ENABLED(CONFIG_TIME_NS)) {
+			get_time_ns(nsp->time_ns);
+			ns_common = to_ns_common(nsp->time_ns);
+		}
 		break;
 	case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE:
-		get_time_ns(nsp->time_ns_for_children);
-		ns_common = to_ns_common(nsp->time_ns_for_children);
+		if (IS_ENABLED(CONFIG_TIME_NS)) {
+			get_time_ns(nsp->time_ns_for_children);
+			ns_common = to_ns_common(nsp->time_ns_for_children);
+		}
 		break;
 	case PIDFD_GET_UTS_NAMESPACE:
-		get_uts_ns(nsp->uts_ns);
-		ns_common = to_ns_common(nsp->uts_ns);
+		if (IS_ENABLED(CONFIG_UTS_NS)) {
+			get_uts_ns(nsp->uts_ns);
+			ns_common = to_ns_common(nsp->uts_ns);
+		}
 		break;
 	/* Namespaces that don't hang of nsproxy. */
 	case PIDFD_GET_USER_NAMESPACE:
-		rcu_read_lock();
-		ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns)));
-		rcu_read_unlock();
+		if (IS_ENABLED(CONFIG_USER_NS)) {
+			rcu_read_lock();
+			ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns)));
+			rcu_read_unlock();
+		}
 		break;
 	case PIDFD_GET_PID_NAMESPACE:
-		rcu_read_lock();
-		ns_common = to_ns_common(get_pid_ns(task_active_pid_ns(task)));
-		rcu_read_unlock();
+		if (IS_ENABLED(CONFIG_PID_NS)) {
+			rcu_read_lock();
+			ns_common = to_ns_common( get_pid_ns(task_active_pid_ns(task)));
+			rcu_read_unlock();
+		}
 		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
 
+	if (!ns_common)
+		return -EOPNOTSUPP;
+
 	/* open_namespace() unconditionally consumes the reference */
 	return open_namespace(ns_common);
 }
diff --git a/fs/pipe.c b/fs/pipe.c
index 50c8a85..7dff2aa 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1469,7 +1469,7 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
 	return 0;
 }
 
-static int proc_dopipe_max_size(struct ctl_table *table, int write,
+static int proc_dopipe_max_size(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return do_proc_douintvec(table, write, buffer, lenp, ppos,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 775a2e8..5f171ad 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -988,6 +988,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_SHADOW_STACK)] = "ss",
 #endif
 #ifdef CONFIG_64BIT
+		[ilog2(VM_DROPPABLE)] = "dp",
 		[ilog2(VM_SEALED)] = "sl",
 #endif
 	};
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a2b256d..7ae885e 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2913,7 +2913,7 @@ const struct quotactl_ops dquot_quotactl_sysfile_ops = {
 };
 EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
 
-static int do_proc_dqstats(struct ctl_table *table, int write,
+static int do_proc_dqstats(const struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int type = (unsigned long *)table->data - dqstats.stat;
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index c92937b..2c4b357 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1894,12 +1894,12 @@ init_cifs(void)
 					   WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 	if (!serverclose_wq) {
 		rc = -ENOMEM;
-		goto out_destroy_serverclose_wq;
+		goto out_destroy_deferredclose_wq;
 	}
 
 	rc = cifs_init_inodecache();
 	if (rc)
-		goto out_destroy_deferredclose_wq;
+		goto out_destroy_serverclose_wq;
 
 	rc = cifs_init_netfs();
 	if (rc)
@@ -1967,6 +1967,8 @@ init_cifs(void)
 	cifs_destroy_netfs();
 out_destroy_inodecache:
 	cifs_destroy_inodecache();
+out_destroy_serverclose_wq:
+	destroy_workqueue(serverclose_wq);
 out_destroy_deferredclose_wq:
 	destroy_workqueue(deferredclose_wq);
 out_destroy_cifsoplockd_wq:
@@ -1977,8 +1979,6 @@ init_cifs(void)
 	destroy_workqueue(decrypt_wq);
 out_destroy_cifsiod_wq:
 	destroy_workqueue(cifsiod_wq);
-out_destroy_serverclose_wq:
-	destroy_workqueue(serverclose_wq);
 out_clean_proc:
 	cifs_proc_clean();
 	return rc;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 7a16e12..d2307162 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2614,6 +2614,13 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 			cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions\n");
 			rc = -EOPNOTSUPP;
 			goto out_fail;
+		} else if (ses->server->vals->protocol_id == SMB10_PROT_ID)
+			if (cap_unix(ses))
+				cifs_dbg(FYI, "Unix Extensions requested on SMB1 mount\n");
+			else {
+				cifs_dbg(VFS, "SMB1 Unix Extensions not supported by server\n");
+				rc = -EOPNOTSUPP;
+				goto out_fail;
 		} else {
 			cifs_dbg(VFS,
 				"Check vers= mount option. SMB3.11 disabled but required for POSIX extensions\n");
@@ -3686,6 +3693,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 }
 #endif
 
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 /*
  * Issue a TREE_CONNECT request.
  */
@@ -3807,11 +3815,25 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
 		else
 			tcon->Flags = 0;
 		cifs_dbg(FYI, "Tcon flags: 0x%x\n", tcon->Flags);
-	}
 
+		/*
+		 * reset_cifs_unix_caps calls QFSInfo which requires
+		 * need_reconnect to be false, but we would not need to call
+		 * reset_caps if this were not a reconnect case so must check
+		 * need_reconnect flag here.  The caller will also clear
+		 * need_reconnect when tcon was successful but needed to be
+		 * cleared earlier in the case of unix extensions reconnect
+		 */
+		if (tcon->need_reconnect && tcon->unix_ext) {
+			cifs_dbg(FYI, "resetting caps for %s\n", tcon->tree_name);
+			tcon->need_reconnect = false;
+			reset_cifs_unix_caps(xid, tcon, NULL, NULL);
+		}
+	}
 	cifs_buf_release(smb_buffer);
 	return rc;
 }
+#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 
 static void delayed_free(struct rcu_head *p)
 {
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 7fe5923..322cabc 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1812,6 +1812,10 @@ smb2_copychunk_range(const unsigned int xid,
 
 	tcon = tlink_tcon(trgtfile->tlink);
 
+	trace_smb3_copychunk_enter(xid, srcfile->fid.volatile_fid,
+				   trgtfile->fid.volatile_fid, tcon->tid,
+				   tcon->ses->Suid, src_off, dest_off, len);
+
 	while (len > 0) {
 		pcchunk->SourceOffset = cpu_to_le64(src_off);
 		pcchunk->TargetOffset = cpu_to_le64(dest_off);
@@ -1863,6 +1867,9 @@ smb2_copychunk_range(const unsigned int xid,
 				le32_to_cpu(retbuf->ChunksWritten),
 				le32_to_cpu(retbuf->ChunkBytesWritten),
 				bytes_written);
+			trace_smb3_copychunk_done(xid, srcfile->fid.volatile_fid,
+				trgtfile->fid.volatile_fid, tcon->tid,
+				tcon->ses->Suid, src_off, dest_off, len);
 		} else if (rc == -EINVAL) {
 			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
 				goto cchunk_out;
@@ -2046,7 +2053,9 @@ smb2_duplicate_extents(const unsigned int xid,
 	dup_ext_buf.ByteCount = cpu_to_le64(len);
 	cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
 		src_off, dest_off, len);
-
+	trace_smb3_clone_enter(xid, srcfile->fid.volatile_fid,
+			       trgtfile->fid.volatile_fid, tcon->tid,
+			       tcon->ses->Suid, src_off, dest_off, len);
 	inode = d_inode(trgtfile->dentry);
 	if (inode->i_size < dest_off + len) {
 		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
@@ -2075,6 +2084,15 @@ smb2_duplicate_extents(const unsigned int xid,
 		cifs_dbg(FYI, "Non-zero response length in duplicate extents\n");
 
 duplicate_extents_out:
+	if (rc)
+		trace_smb3_clone_err(xid, srcfile->fid.volatile_fid,
+				     trgtfile->fid.volatile_fid,
+				     tcon->tid, tcon->ses->Suid, src_off,
+				     dest_off, len, rc);
+	else
+		trace_smb3_clone_done(xid, srcfile->fid.volatile_fid,
+				      trgtfile->fid.volatile_fid, tcon->tid,
+				      tcon->ses->Suid, src_off, dest_off, len);
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 9fc5b11..9a06b55 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1562,8 +1562,14 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 	cifs_small_buf_release(sess_data->iov[0].iov_base);
 	if (rc == 0)
 		sess_data->ses->expired_pwd = false;
-	else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED))
+	else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) {
+		if (sess_data->ses->expired_pwd == false)
+			trace_smb3_key_expired(sess_data->server->hostname,
+					       sess_data->ses->user_name,
+					       sess_data->server->conn_id,
+					       &sess_data->server->dstaddr, rc);
 		sess_data->ses->expired_pwd = true;
+	}
 
 	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 36d5295..6b3bdfb 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -206,6 +206,116 @@ DEFINE_SMB3_OTHER_ERR_EVENT(query_dir_err);
 DEFINE_SMB3_OTHER_ERR_EVENT(zero_err);
 DEFINE_SMB3_OTHER_ERR_EVENT(falloc_err);
 
+/*
+ * For logging errors in reflink and copy_range ops e.g. smb2_copychunk_range
+ * and smb2_duplicate_extents
+ */
+DECLARE_EVENT_CLASS(smb3_copy_range_err_class,
+	TP_PROTO(unsigned int xid,
+		__u64	src_fid,
+		__u64   target_fid,
+		__u32	tid,
+		__u64	sesid,
+		__u64	src_offset,
+		__u64   target_offset,
+		__u32	len,
+		int	rc),
+	TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, src_fid)
+		__field(__u64, target_fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, src_offset)
+		__field(__u64, target_offset)
+		__field(__u32, len)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->src_fid = src_fid;
+		__entry->target_fid = target_fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->src_offset = src_offset;
+		__entry->target_offset = target_offset;
+		__entry->len = len;
+		__entry->rc = rc;
+	),
+	TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->target_fid,
+		__entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len, __entry->rc)
+)
+
+#define DEFINE_SMB3_COPY_RANGE_ERR_EVENT(name)	\
+DEFINE_EVENT(smb3_copy_range_err_class, smb3_##name, \
+	TP_PROTO(unsigned int xid,		\
+		__u64	src_fid,		\
+		__u64   target_fid,		\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u64	src_offset,		\
+		__u64	target_offset,		\
+		__u32	len,			\
+		int	rc),			\
+	TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len, rc))
+
+DEFINE_SMB3_COPY_RANGE_ERR_EVENT(clone_err);
+/* TODO: Add SMB3_COPY_RANGE_ERR_EVENT(copychunk_err) */
+
+DECLARE_EVENT_CLASS(smb3_copy_range_done_class,
+	TP_PROTO(unsigned int xid,
+		__u64	src_fid,
+		__u64   target_fid,
+		__u32	tid,
+		__u64	sesid,
+		__u64	src_offset,
+		__u64   target_offset,
+		__u32	len),
+	TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u64, src_fid)
+		__field(__u64, target_fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, src_offset)
+		__field(__u64, target_offset)
+		__field(__u32, len)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->src_fid = src_fid;
+		__entry->target_fid = target_fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->src_offset = src_offset;
+		__entry->target_offset = target_offset;
+		__entry->len = len;
+	),
+	TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x",
+		__entry->xid, __entry->sesid, __entry->tid, __entry->target_fid,
+		__entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len)
+)
+
+#define DEFINE_SMB3_COPY_RANGE_DONE_EVENT(name)	\
+DEFINE_EVENT(smb3_copy_range_done_class, smb3_##name, \
+	TP_PROTO(unsigned int xid,		\
+		__u64	src_fid,		\
+		__u64   target_fid,		\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u64	src_offset,		\
+		__u64	target_offset,		\
+		__u32	len),			\
+	TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len))
+
+DEFINE_SMB3_COPY_RANGE_DONE_EVENT(copychunk_enter);
+DEFINE_SMB3_COPY_RANGE_DONE_EVENT(clone_enter);
+DEFINE_SMB3_COPY_RANGE_DONE_EVENT(copychunk_done);
+DEFINE_SMB3_COPY_RANGE_DONE_EVENT(clone_done);
+
 
 /* For logging successful read or write */
 DECLARE_EVENT_CLASS(smb3_rw_done_class,
@@ -1171,6 +1281,46 @@ DEFINE_EVENT(smb3_connect_err_class, smb3_##name,  \
 
 DEFINE_SMB3_CONNECT_ERR_EVENT(connect_err);
 
+DECLARE_EVENT_CLASS(smb3_sess_setup_err_class,
+	TP_PROTO(char *hostname, char *username, __u64 conn_id,
+		const struct __kernel_sockaddr_storage *dst_addr, int rc),
+	TP_ARGS(hostname, username, conn_id, dst_addr, rc),
+	TP_STRUCT__entry(
+		__string(hostname, hostname)
+		__string(username, username)
+		__field(__u64, conn_id)
+		__array(__u8, dst_addr, sizeof(struct sockaddr_storage))
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		struct sockaddr_storage *pss = NULL;
+
+		__entry->conn_id = conn_id;
+		__entry->rc = rc;
+		pss = (struct sockaddr_storage *)__entry->dst_addr;
+		*pss = *dst_addr;
+		__assign_str(hostname);
+		__assign_str(username);
+	),
+	TP_printk("rc=%d user=%s conn_id=0x%llx server=%s addr=%pISpsfc",
+		__entry->rc,
+		__get_str(username),
+		__entry->conn_id,
+		__get_str(hostname),
+		__entry->dst_addr)
+)
+
+#define DEFINE_SMB3_SES_SETUP_ERR_EVENT(name)        \
+DEFINE_EVENT(smb3_sess_setup_err_class, smb3_##name,  \
+	TP_PROTO(char *hostname,		\
+		char *username,			\
+		__u64 conn_id,			\
+		const struct __kernel_sockaddr_storage *addr,	\
+		int rc),			\
+	TP_ARGS(hostname, username, conn_id, addr, rc))
+
+DEFINE_SMB3_SES_SETUP_ERR_EVENT(key_expired);
+
 DECLARE_EVENT_CLASS(smb3_reconnect_class,
 	TP_PROTO(__u64	currmid,
 		__u64 conn_id,
diff --git a/fs/super.c b/fs/super.c
index 095ba79..38d72a3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -736,6 +736,17 @@ struct super_block *sget_fc(struct fs_context *fc,
 	struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns;
 	int err;
 
+	/*
+	 * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is
+	 * not set, as the filesystem is likely unprepared to handle it.
+	 * This can happen when fsconfig() is called from init_user_ns with
+	 * an fs_fd opened in another user namespace.
+	 */
+	if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) {
+		errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed");
+		return ERR_PTR(-EPERM);
+	}
+
 retry:
 	spin_lock(&sb_lock);
 	if (test) {
diff --git a/fs/binfmt_elf_test.c b/fs/tests/binfmt_elf_kunit.c
similarity index 100%
rename from fs/binfmt_elf_test.c
rename to fs/tests/binfmt_elf_kunit.c
diff --git a/fs/exec_test.c b/fs/tests/exec_kunit.c
similarity index 100%
rename from fs/exec_test.c
rename to fs/tests/exec_kunit.c
diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c
index 7546177..0b48cba 100644
--- a/fs/ubifs/compress.c
+++ b/fs/ubifs/compress.c
@@ -82,6 +82,7 @@ struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
 
 /**
  * ubifs_compress - compress data.
+ * @c: UBIFS file-system description object
  * @in_buf: data to compress
  * @in_len: length of the data to compress
  * @out_buf: output buffer where compressed data should be stored
@@ -140,6 +141,7 @@ void ubifs_compress(const struct ubifs_info *c, const void *in_buf,
 
 /**
  * ubifs_decompress - decompress data.
+ * @c: UBIFS file-system description object
  * @in_buf: data to decompress
  * @in_len: length of the data to decompress
  * @out_buf: output buffer where decompressed data should
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index ac77ac1..d91cec93d 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2827,9 +2827,9 @@ void dbg_debugfs_init_fs(struct ubifs_info *c)
 	const char *fname;
 	struct ubifs_debug_info *d = c->dbg;
 
-	n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME,
+	n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN, UBIFS_DFS_DIR_NAME,
 		     c->vi.ubi_num, c->vi.vol_id);
-	if (n > UBIFS_DFS_DIR_LEN) {
+	if (n >= UBIFS_DFS_DIR_LEN) {
 		/* The array size is too small */
 		return;
 	}
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index ed96610..d425861 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -19,10 +19,11 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c,
 
 /*
  * The UBIFS debugfs directory name pattern and maximum name length (3 for "ubi"
- * + 1 for "_" and plus 2x2 for 2 UBI numbers and 1 for the trailing zero byte.
+ * + 1 for "_" and 2 for UBI device numbers and 3 for volume number and 1 for
+ * the trailing zero byte.
  */
 #define UBIFS_DFS_DIR_NAME "ubi%d_%d"
-#define UBIFS_DFS_DIR_LEN  (3 + 1 + 2*2 + 1)
+#define UBIFS_DFS_DIR_LEN  (3 + 1 + 2 + 3 + 1)
 
 /**
  * ubifs_debug_info - per-FS debugging information.
@@ -103,7 +104,7 @@ struct ubifs_debug_info {
 	unsigned int chk_fs:1;
 	unsigned int tst_rcvry:1;
 
-	char dfs_dir_name[UBIFS_DFS_DIR_LEN + 1];
+	char dfs_dir_name[UBIFS_DFS_DIR_LEN];
 	struct dentry *dfs_dir;
 	struct dentry *dfs_dump_lprops;
 	struct dentry *dfs_dump_budg;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index eac0fef..c77ea57 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -71,8 +71,13 @@ static int inherit_flags(const struct inode *dir, umode_t mode)
  * @is_xattr: whether the inode is xattr inode
  *
  * This function finds an unused inode number, allocates new inode and
- * initializes it. Returns new inode in case of success and an error code in
- * case of failure.
+ * initializes it. Non-xattr new inode may be written with xattrs(selinux/
+ * encryption) before writing dentry, which could cause inconsistent problem
+ * when powercut happens between two operations. To deal with it, non-xattr
+ * new inode is initialized with zero-nlink and added into orphan list, caller
+ * should make sure that inode is relinked later, and make sure that orphan
+ * removing and journal writing into an committing atomic operation. Returns
+ * new inode in case of success and an error code in case of failure.
  */
 struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 			      umode_t mode, bool is_xattr)
@@ -163,9 +168,25 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 	ui->creat_sqnum = ++c->max_sqnum;
 	spin_unlock(&c->cnt_lock);
 
+	if (!is_xattr) {
+		set_nlink(inode, 0);
+		err = ubifs_add_orphan(c, inode->i_ino);
+		if (err) {
+			ubifs_err(c, "ubifs_add_orphan failed: %i", err);
+			goto out_iput;
+		}
+		down_read(&c->commit_sem);
+		ui->del_cmtno = c->cmt_no;
+		up_read(&c->commit_sem);
+	}
+
 	if (encrypted) {
 		err = fscrypt_set_context(inode, NULL);
 		if (err) {
+			if (!is_xattr) {
+				set_nlink(inode, 1);
+				ubifs_delete_orphan(c, inode->i_ino);
+			}
 			ubifs_err(c, "fscrypt_set_context failed: %i", err);
 			goto out_iput;
 		}
@@ -320,12 +341,13 @@ static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir,
 	if (err)
 		goto out_inode;
 
+	set_nlink(inode, 1);
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0, 1);
 	if (err)
 		goto out_cancel;
 	mutex_unlock(&dir_ui->ui_mutex);
@@ -340,8 +362,8 @@ static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir,
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
+	set_nlink(inode, 0);
 out_inode:
-	make_bad_inode(inode);
 	iput(inode);
 out_fname:
 	fscrypt_free_filename(&nm);
@@ -386,7 +408,6 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry)
 	return inode;
 
 out_inode:
-	make_bad_inode(inode);
 	iput(inode);
 out_free:
 	ubifs_err(c, "cannot create whiteout file, error %d", err);
@@ -470,6 +491,7 @@ static int ubifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 	if (err)
 		goto out_inode;
 
+	set_nlink(inode, 1);
 	mutex_lock(&ui->ui_mutex);
 	insert_inode_hash(inode);
 	d_tmpfile(file, inode);
@@ -479,7 +501,7 @@ static int ubifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 	mutex_unlock(&ui->ui_mutex);
 
 	lock_2_inodes(dir, inode);
-	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0, 1);
 	if (err)
 		goto out_cancel;
 	unlock_2_inodes(dir, inode);
@@ -492,7 +514,6 @@ static int ubifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 out_cancel:
 	unlock_2_inodes(dir, inode);
 out_inode:
-	make_bad_inode(inode);
 	if (!instantiated)
 		iput(inode);
 out_budg:
@@ -760,10 +781,6 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 
 	lock_2_inodes(dir, inode);
 
-	/* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */
-	if (inode->i_nlink == 0)
-		ubifs_delete_orphan(c, inode->i_ino);
-
 	inc_nlink(inode);
 	ihold(inode);
 	inode_set_ctime_current(inode);
@@ -771,7 +788,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0, inode->i_nlink == 1);
 	if (err)
 		goto out_cancel;
 	unlock_2_inodes(dir, inode);
@@ -785,8 +802,6 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	drop_nlink(inode);
-	if (inode->i_nlink == 0)
-		ubifs_add_orphan(c, inode->i_ino);
 	unlock_2_inodes(dir, inode);
 	ubifs_release_budget(c, &req);
 	iput(inode);
@@ -846,7 +861,7 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry)
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0, 0);
 	if (err)
 		goto out_cancel;
 	unlock_2_inodes(dir, inode);
@@ -950,7 +965,7 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry)
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0, 0);
 	if (err)
 		goto out_cancel;
 	unlock_2_inodes(dir, inode);
@@ -1017,6 +1032,7 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (err)
 		goto out_inode;
 
+	set_nlink(inode, 1);
 	mutex_lock(&dir_ui->ui_mutex);
 	insert_inode_hash(inode);
 	inc_nlink(inode);
@@ -1025,7 +1041,7 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0, 1);
 	if (err) {
 		ubifs_err(c, "cannot create directory, error %d", err);
 		goto out_cancel;
@@ -1042,8 +1058,8 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	dir_ui->ui_size = dir->i_size;
 	drop_nlink(dir);
 	mutex_unlock(&dir_ui->ui_mutex);
+	set_nlink(inode, 0);
 out_inode:
-	make_bad_inode(inode);
 	iput(inode);
 out_fname:
 	fscrypt_free_filename(&nm);
@@ -1102,22 +1118,25 @@ static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		goto out_fname;
 	}
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err) {
+		kfree(dev);
+		goto out_inode;
+	}
+
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_size = ubifs_inode(inode)->ui_size = devlen;
 	ui = ubifs_inode(inode);
 	ui->data = dev;
 	ui->data_len = devlen;
-
-	err = ubifs_init_security(dir, inode, &dentry->d_name);
-	if (err)
-		goto out_inode;
+	set_nlink(inode, 1);
 
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0, 1);
 	if (err)
 		goto out_cancel;
 	mutex_unlock(&dir_ui->ui_mutex);
@@ -1132,10 +1151,8 @@ static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
+	set_nlink(inode, 0);
 out_inode:
-	/* Free inode->i_link before inode is marked as bad. */
-	fscrypt_free_inode(inode);
-	make_bad_inode(inode);
 	iput(inode);
 out_fname:
 	fscrypt_free_filename(&nm);
@@ -1186,6 +1203,10 @@ static int ubifs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		goto out_fname;
 	}
 
+	err = ubifs_init_security(dir, inode, &dentry->d_name);
+	if (err)
+		goto out_inode;
+
 	ui = ubifs_inode(inode);
 	ui->data = kmalloc(disk_link.len, GFP_NOFS);
 	if (!ui->data) {
@@ -1210,17 +1231,14 @@ static int ubifs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	 */
 	ui->data_len = disk_link.len - 1;
 	inode->i_size = ubifs_inode(inode)->ui_size = disk_link.len - 1;
-
-	err = ubifs_init_security(dir, inode, &dentry->d_name);
-	if (err)
-		goto out_inode;
+	set_nlink(inode, 1);
 
 	mutex_lock(&dir_ui->ui_mutex);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
 	inode_set_mtime_to_ts(dir,
 			      inode_set_ctime_to_ts(dir, inode_get_ctime(inode)));
-	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0);
+	err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0, 1);
 	if (err)
 		goto out_cancel;
 	mutex_unlock(&dir_ui->ui_mutex);
@@ -1234,10 +1252,10 @@ static int ubifs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	mutex_unlock(&dir_ui->ui_mutex);
+	set_nlink(inode, 0);
 out_inode:
 	/* Free inode->i_link before inode is marked as bad. */
 	fscrypt_free_inode(inode);
-	make_bad_inode(inode);
 	iput(inode);
 out_fname:
 	fscrypt_free_filename(&nm);
@@ -1405,14 +1423,10 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 */
 		err = ubifs_budget_space(c, &wht_req);
 		if (err) {
-			/*
-			 * Whiteout inode can not be written on flash by
-			 * ubifs_jnl_write_inode(), because it's neither
-			 * dirty nor zero-nlink.
-			 */
 			iput(whiteout);
 			goto out_release;
 		}
+		set_nlink(whiteout, 1);
 
 		/* Add the old_dentry size to the old_dir size. */
 		old_sz -= CALC_DENT_SIZE(fname_len(&old_nm));
@@ -1491,7 +1505,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	err = ubifs_jnl_rename(c, old_dir, old_inode, &old_nm, new_dir,
-			       new_inode, &new_nm, whiteout, sync);
+			       new_inode, &new_nm, whiteout, sync, !!whiteout);
 	if (err)
 		goto out_cancel;
 
@@ -1544,6 +1558,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
 	if (whiteout) {
 		ubifs_release_budget(c, &wht_req);
+		set_nlink(whiteout, 0);
 		iput(whiteout);
 	}
 out_release:
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index a1f4691..68e1044 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1027,7 +1027,7 @@ static int ubifs_writepage(struct folio *folio, struct writeback_control *wbc,
 
 	/* Is the folio fully inside i_size? */
 	if (folio_pos(folio) + len <= i_size) {
-		if (folio_pos(folio) >= synced_i_size) {
+		if (folio_pos(folio) + len > synced_i_size) {
 			err = inode->i_sb->s_op->write_inode(inode, NULL);
 			if (err)
 				goto out_redirty;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 6ebf3c0..6437189 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -73,7 +73,7 @@ static int valuable(struct ubifs_info *c, const struct ubifs_lprops *lprops)
  * @c: the UBIFS file-system description object
  * @lprops: LEB properties to scan
  * @in_tree: whether the LEB properties are in main memory
- * @data: information passed to and from the caller of the scan
+ * @arg: information passed to and from the caller of the scan
  *
  * This function returns a code that indicates whether the scan should continue
  * (%LPT_SCAN_CONTINUE), whether the LEB properties should be added to the tree
@@ -340,7 +340,7 @@ int ubifs_find_dirty_leb(struct ubifs_info *c, struct ubifs_lprops *ret_lp,
  * @c: the UBIFS file-system description object
  * @lprops: LEB properties to scan
  * @in_tree: whether the LEB properties are in main memory
- * @data: information passed to and from the caller of the scan
+ * @arg: information passed to and from the caller of the scan
  *
  * This function returns a code that indicates whether the scan should continue
  * (%LPT_SCAN_CONTINUE), whether the LEB properties should be added to the tree
@@ -581,7 +581,7 @@ int ubifs_find_free_space(struct ubifs_info *c, int min_space, int *offs,
  * @c: the UBIFS file-system description object
  * @lprops: LEB properties to scan
  * @in_tree: whether the LEB properties are in main memory
- * @data: information passed to and from the caller of the scan
+ * @arg: information passed to and from the caller of the scan
  *
  * This function returns a code that indicates whether the scan should continue
  * (%LPT_SCAN_CONTINUE), whether the LEB properties should be added to the tree
@@ -773,7 +773,7 @@ int ubifs_save_dirty_idx_lnums(struct ubifs_info *c)
  * @c: the UBIFS file-system description object
  * @lprops: LEB properties to scan
  * @in_tree: whether the LEB properties are in main memory
- * @data: information passed to and from the caller of the scan
+ * @arg: information passed to and from the caller of the scan
  *
  * This function returns a code that indicates whether the scan should continue
  * (%LPT_SCAN_CONTINUE), whether the LEB properties should be added to the tree
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 74aee92..4a35f9e 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -359,7 +359,7 @@ static void wake_up_reservation(struct ubifs_info *c)
 }
 
 /**
- * wake_up_reservation - add current task in queue or start queuing.
+ * add_or_start_queue - add current task in queue or start queuing.
  * @c: UBIFS file-system description object
  *
  * This function starts queuing if queuing is not started, otherwise adds
@@ -643,6 +643,7 @@ static void set_dent_cookie(struct ubifs_info *c, struct ubifs_dent_node *dent)
  * @inode: inode to update
  * @deletion: indicates a directory entry deletion i.e unlink or rmdir
  * @xent: non-zero if the directory entry is an extended attribute entry
+ * @in_orphan: indicates whether the @inode is in orphan list
  *
  * This function updates an inode by writing a directory entry (or extended
  * attribute entry), the inode itself, and the parent directory inode (or the
@@ -664,7 +665,7 @@ static void set_dent_cookie(struct ubifs_info *c, struct ubifs_dent_node *dent)
  */
 int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 		     const struct fscrypt_name *nm, const struct inode *inode,
-		     int deletion, int xent)
+		     int deletion, int xent, int in_orphan)
 {
 	int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0;
 	int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir);
@@ -750,7 +751,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	if (err)
 		goto out_release;
 
-	if (last_reference) {
+	if (last_reference && !in_orphan) {
 		err = ubifs_add_orphan(c, inode->i_ino);
 		if (err) {
 			release_head(c, BASEHD);
@@ -806,6 +807,9 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	if (err)
 		goto out_ro;
 
+	if (in_orphan && inode->i_nlink)
+		ubifs_delete_orphan(c, inode->i_ino);
+
 	finish_reservation(c);
 	spin_lock(&ui->ui_lock);
 	ui->synced_i_size = ui->ui_size;
@@ -1336,6 +1340,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
  * @new_nm: new name of the new directory entry
  * @whiteout: whiteout inode
  * @sync: non-zero if the write-buffer has to be synchronized
+ * @delete_orphan: indicates an orphan entry deletion for @whiteout
  *
  * This function implements the re-name operation which may involve writing up
  * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes)
@@ -1348,7 +1353,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct inode *new_dir,
 		     const struct inode *new_inode,
 		     const struct fscrypt_name *new_nm,
-		     const struct inode *whiteout, int sync)
+		     const struct inode *whiteout, int sync, int delete_orphan)
 {
 	void *p;
 	union ubifs_key key;
@@ -1565,6 +1570,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 			goto out_ro;
 	}
 
+	if (delete_orphan)
+		ubifs_delete_orphan(c, whiteout->i_ino);
+
 	finish_reservation(c);
 	if (new_inode) {
 		mark_inode_clean(c, new_ui);
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index a11c3da..8788740 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -1005,7 +1005,7 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat,
  * @c: the UBIFS file-system description object
  * @lp: LEB properties to scan
  * @in_tree: whether the LEB properties are in main memory
- * @lst: lprops statistics to update
+ * @arg: lprops statistics to update
  *
  * This function returns a code that indicates whether the scan should continue
  * (%LPT_SCAN_CONTINUE), whether the LEB properties should be added to the tree
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index 778a22b..441d0be 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -1918,6 +1918,7 @@ int ubifs_lpt_init(struct ubifs_info *c, int rd, int wr)
  * @pnode: where to keep a pnode
  * @cnode: where to keep a cnode
  * @in_tree: is the node in the tree in memory
+ * @ptr: union of node pointers
  * @ptr.nnode: pointer to the nnode (if it is an nnode) which may be here or in
  * the tree
  * @ptr.pnode: ditto for pnode
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index 7adc37c..a148760 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -67,10 +67,13 @@ static int mst_node_check_hash(const struct ubifs_info *c,
 {
 	u8 calc[UBIFS_MAX_HASH_LEN];
 	const void *node = mst;
+	int ret;
 
-	crypto_shash_tfm_digest(c->hash_tfm, node + sizeof(struct ubifs_ch),
+	ret = crypto_shash_tfm_digest(c->hash_tfm, node + sizeof(struct ubifs_ch),
 				UBIFS_MST_NODE_SZ - sizeof(struct ubifs_ch),
 				calc);
+	if (ret)
+		return ret;
 
 	if (ubifs_check_hash(c, expected, calc))
 		return -EPERM;
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 4909321..fb957d9 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -42,24 +42,30 @@
 
 static int dbg_check_orphans(struct ubifs_info *c);
 
-static struct ubifs_orphan *orphan_add(struct ubifs_info *c, ino_t inum,
-				       struct ubifs_orphan *parent_orphan)
+/**
+ * ubifs_add_orphan - add an orphan.
+ * @c: UBIFS file-system description object
+ * @inum: orphan inode number
+ *
+ * Add an orphan. This function is called when an inodes link count drops to
+ * zero.
+ */
+int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
 {
 	struct ubifs_orphan *orphan, *o;
 	struct rb_node **p, *parent = NULL;
 
 	orphan = kzalloc(sizeof(struct ubifs_orphan), GFP_NOFS);
 	if (!orphan)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	orphan->inum = inum;
 	orphan->new = 1;
-	INIT_LIST_HEAD(&orphan->child_list);
 
 	spin_lock(&c->orphan_lock);
 	if (c->tot_orphans >= c->max_orphans) {
 		spin_unlock(&c->orphan_lock);
 		kfree(orphan);
-		return ERR_PTR(-ENFILE);
+		return -ENFILE;
 	}
 	p = &c->orph_tree.rb_node;
 	while (*p) {
@@ -73,7 +79,7 @@ static struct ubifs_orphan *orphan_add(struct ubifs_info *c, ino_t inum,
 			ubifs_err(c, "orphaned twice");
 			spin_unlock(&c->orphan_lock);
 			kfree(orphan);
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 		}
 	}
 	c->tot_orphans += 1;
@@ -83,14 +89,9 @@ static struct ubifs_orphan *orphan_add(struct ubifs_info *c, ino_t inum,
 	list_add_tail(&orphan->list, &c->orph_list);
 	list_add_tail(&orphan->new_list, &c->orph_new);
 
-	if (parent_orphan) {
-		list_add_tail(&orphan->child_list,
-			      &parent_orphan->child_list);
-	}
-
 	spin_unlock(&c->orphan_lock);
 	dbg_gen("ino %lu", (unsigned long)inum);
-	return orphan;
+	return 0;
 }
 
 static struct ubifs_orphan *lookup_orphan(struct ubifs_info *c, ino_t inum)
@@ -135,6 +136,7 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 
 	if (orph->cmt) {
 		orph->del = 1;
+		rb_erase(&orph->rb, &c->orph_tree);
 		orph->dnext = c->orph_dnext;
 		c->orph_dnext = orph;
 		dbg_gen("delete later ino %lu", (unsigned long)orph->inum);
@@ -145,59 +147,6 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 }
 
 /**
- * ubifs_add_orphan - add an orphan.
- * @c: UBIFS file-system description object
- * @inum: orphan inode number
- *
- * Add an orphan. This function is called when an inodes link count drops to
- * zero.
- */
-int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
-{
-	int err = 0;
-	ino_t xattr_inum;
-	union ubifs_key key;
-	struct ubifs_dent_node *xent, *pxent = NULL;
-	struct fscrypt_name nm = {0};
-	struct ubifs_orphan *xattr_orphan;
-	struct ubifs_orphan *orphan;
-
-	orphan = orphan_add(c, inum, NULL);
-	if (IS_ERR(orphan))
-		return PTR_ERR(orphan);
-
-	lowest_xent_key(c, &key, inum);
-	while (1) {
-		xent = ubifs_tnc_next_ent(c, &key, &nm);
-		if (IS_ERR(xent)) {
-			err = PTR_ERR(xent);
-			if (err == -ENOENT)
-				break;
-			kfree(pxent);
-			return err;
-		}
-
-		fname_name(&nm) = xent->name;
-		fname_len(&nm) = le16_to_cpu(xent->nlen);
-		xattr_inum = le64_to_cpu(xent->inum);
-
-		xattr_orphan = orphan_add(c, xattr_inum, orphan);
-		if (IS_ERR(xattr_orphan)) {
-			kfree(pxent);
-			kfree(xent);
-			return PTR_ERR(xattr_orphan);
-		}
-
-		kfree(pxent);
-		pxent = xent;
-		key_read(c, &xent->key, &key);
-	}
-	kfree(pxent);
-
-	return 0;
-}
-
-/**
  * ubifs_delete_orphan - delete an orphan.
  * @c: UBIFS file-system description object
  * @inum: orphan inode number
@@ -206,7 +155,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
  */
 void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum)
 {
-	struct ubifs_orphan *orph, *child_orph, *tmp_o;
+	struct ubifs_orphan *orph;
 
 	spin_lock(&c->orphan_lock);
 
@@ -219,11 +168,6 @@ void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum)
 		return;
 	}
 
-	list_for_each_entry_safe(child_orph, tmp_o, &orph->child_list, child_list) {
-		list_del(&child_orph->child_list);
-		orphan_delete(c, child_orph);
-	}
-	
 	orphan_delete(c, orph);
 
 	spin_unlock(&c->orphan_lock);
@@ -518,7 +462,6 @@ static void erase_deleted(struct ubifs_info *c)
 		dnext = orphan->dnext;
 		ubifs_assert(c, !orphan->new);
 		ubifs_assert(c, orphan->del);
-		rb_erase(&orphan->rb, &c->orph_tree);
 		list_del(&orphan->list);
 		c->tot_orphans -= 1;
 		dbg_gen("deleting orphan ino %lu", (unsigned long)orphan->inum);
@@ -571,51 +514,6 @@ int ubifs_clear_orphans(struct ubifs_info *c)
 }
 
 /**
- * insert_dead_orphan - insert an orphan.
- * @c: UBIFS file-system description object
- * @inum: orphan inode number
- *
- * This function is a helper to the 'do_kill_orphans()' function. The orphan
- * must be kept until the next commit, so it is added to the rb-tree and the
- * deletion list.
- */
-static int insert_dead_orphan(struct ubifs_info *c, ino_t inum)
-{
-	struct ubifs_orphan *orphan, *o;
-	struct rb_node **p, *parent = NULL;
-
-	orphan = kzalloc(sizeof(struct ubifs_orphan), GFP_KERNEL);
-	if (!orphan)
-		return -ENOMEM;
-	orphan->inum = inum;
-
-	p = &c->orph_tree.rb_node;
-	while (*p) {
-		parent = *p;
-		o = rb_entry(parent, struct ubifs_orphan, rb);
-		if (inum < o->inum)
-			p = &(*p)->rb_left;
-		else if (inum > o->inum)
-			p = &(*p)->rb_right;
-		else {
-			/* Already added - no problem */
-			kfree(orphan);
-			return 0;
-		}
-	}
-	c->tot_orphans += 1;
-	rb_link_node(&orphan->rb, parent, p);
-	rb_insert_color(&orphan->rb, &c->orph_tree);
-	list_add_tail(&orphan->list, &c->orph_list);
-	orphan->del = 1;
-	orphan->dnext = c->orph_dnext;
-	c->orph_dnext = orphan;
-	dbg_mnt("ino %lu, new %d, tot %d", (unsigned long)inum,
-		c->new_orphans, c->tot_orphans);
-	return 0;
-}
-
-/**
  * do_kill_orphans - remove orphan inodes from the index.
  * @c: UBIFS file-system description object
  * @sleb: scanned LEB
@@ -691,12 +589,12 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 
 		n = (le32_to_cpu(orph->ch.len) - UBIFS_ORPH_NODE_SZ) >> 3;
 		for (i = 0; i < n; i++) {
-			union ubifs_key key1, key2;
+			union ubifs_key key;
 
 			inum = le64_to_cpu(orph->inos[i]);
 
-			ino_key_init(c, &key1, inum);
-			err = ubifs_tnc_lookup(c, &key1, ino);
+			ino_key_init(c, &key, inum);
+			err = ubifs_tnc_lookup(c, &key, ino);
 			if (err && err != -ENOENT)
 				goto out_free;
 
@@ -708,17 +606,10 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 				dbg_rcvry("deleting orphaned inode %lu",
 					  (unsigned long)inum);
 
-				lowest_ino_key(c, &key1, inum);
-				highest_ino_key(c, &key2, inum);
-
-				err = ubifs_tnc_remove_range(c, &key1, &key2);
+				err = ubifs_tnc_remove_ino(c, inum);
 				if (err)
 					goto out_ro;
 			}
-
-			err = insert_dead_orphan(c, inum);
-			if (err)
-				goto out_free;
 		}
 
 		*last_cmt_no = cmt_no;
@@ -925,8 +816,12 @@ static int dbg_orphan_check(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 
 	inum = key_inum(c, &zbr->key);
 	if (inum != ci->last_ino) {
-		/* Lowest node type is the inode node, so it comes first */
-		if (key_type(c, &zbr->key) != UBIFS_INO_KEY)
+		/*
+		 * Lowest node type is the inode node or xattr entry(when
+		 * selinux/encryption is enabled), so it comes first
+		 */
+		if (key_type(c, &zbr->key) != UBIFS_INO_KEY &&
+		    key_type(c, &zbr->key) != UBIFS_XENT_KEY)
 			ubifs_err(c, "found orphan node ino %lu, type %d",
 				  (unsigned long)inum, key_type(c, &zbr->key));
 		ci->last_ino = inum;
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 17da28d..a950c5f 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -29,6 +29,7 @@
  * @lnum: logical eraseblock number of the node
  * @offs: node offset
  * @len: node length
+ * @hash: node hash
  * @deletion: non-zero if this entry corresponds to a node deletion
  * @sqnum: node sequence number
  * @list: links the replay list
diff --git a/fs/ubifs/sysfs.c b/fs/ubifs/sysfs.c
index 1c95814..aae3222 100644
--- a/fs/ubifs/sysfs.c
+++ b/fs/ubifs/sysfs.c
@@ -91,17 +91,17 @@ static struct kset ubifs_kset = {
 int ubifs_sysfs_register(struct ubifs_info *c)
 {
 	int ret, n;
-	char dfs_dir_name[UBIFS_DFS_DIR_LEN+1];
+	char dfs_dir_name[UBIFS_DFS_DIR_LEN];
 
 	c->stats = kzalloc(sizeof(struct ubifs_stats_info), GFP_KERNEL);
 	if (!c->stats) {
 		ret = -ENOMEM;
 		goto out_last;
 	}
-	n = snprintf(dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME,
+	n = snprintf(dfs_dir_name, UBIFS_DFS_DIR_LEN, UBIFS_DFS_DIR_NAME,
 		     c->vi.ubi_num, c->vi.vol_id);
 
-	if (n > UBIFS_DFS_DIR_LEN) {
+	if (n >= UBIFS_DFS_DIR_LEN) {
 		/* The array size is too small */
 		ret = -EINVAL;
 		goto out_free;
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 1f3ea87..d69a5a4 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -158,13 +158,6 @@
 #endif
 
 /*
- * The UBIFS sysfs directory name pattern and maximum name length (3 for "ubi"
- * + 1 for "_" and plus 2x2 for 2 UBI numbers and 1 for the trailing zero byte.
- */
-#define UBIFS_DFS_DIR_NAME "ubi%d_%d"
-#define UBIFS_DFS_DIR_LEN  (3 + 1 + 2*2 + 1)
-
-/*
  * Lockdep classes for UBIFS inode @ui_mutex.
  */
 enum {
@@ -923,8 +916,6 @@ struct ubifs_budget_req {
  * @rb: rb-tree node of rb-tree of orphans sorted by inode number
  * @list: list head of list of orphans in order added
  * @new_list: list head of list of orphans added since the last commit
- * @child_list: list of xattr children if this orphan hosts xattrs, list head
- * if this orphan is a xattr, not used otherwise.
  * @cnext: next orphan to commit
  * @dnext: next orphan to delete
  * @inum: inode number
@@ -936,7 +927,6 @@ struct ubifs_orphan {
 	struct rb_node rb;
 	struct list_head list;
 	struct list_head new_list;
-	struct list_head child_list;
 	struct ubifs_orphan *cnext;
 	struct ubifs_orphan *dnext;
 	ino_t inum;
@@ -1803,7 +1793,7 @@ int ubifs_consolidate_log(struct ubifs_info *c);
 /* journal.c */
 int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 		     const struct fscrypt_name *nm, const struct inode *inode,
-		     int deletion, int xent);
+		     int deletion, int xent, int in_orphan);
 int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
 			 const union ubifs_key *key, const void *buf, int len);
 int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode);
@@ -1820,7 +1810,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 		     const struct inode *new_dir,
 		     const struct inode *new_inode,
 		     const struct fscrypt_name *new_nm,
-		     const struct inode *whiteout, int sync);
+		     const struct inode *whiteout, int sync, int delete_orphan);
 int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode,
 		       loff_t old_size, loff_t new_size);
 int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 0847db5..f734588 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -149,7 +149,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 	if (strcmp(fname_name(nm), UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT) == 0)
 		host_ui->flags |= UBIFS_CRYPT_FL;
 
-	err = ubifs_jnl_update(c, host, nm, inode, 0, 1);
+	err = ubifs_jnl_update(c, host, nm, inode, 0, 1, 0);
 	if (err)
 		goto out_cancel;
 	ubifs_set_inode_flags(host);
diff --git a/fs/unicode/mkutf8data.c b/fs/unicode/mkutf8data.c
index bc1a7c8..77b685d 100644
--- a/fs/unicode/mkutf8data.c
+++ b/fs/unicode/mkutf8data.c
@@ -3352,6 +3352,7 @@ static void write_file(void)
 	fprintf(file, "};\n");
 	fprintf(file, "EXPORT_SYMBOL_GPL(utf8_data_table);");
 	fprintf(file, "\n");
+	fprintf(file, "MODULE_DESCRIPTION(\"UTF8 data table\");\n");
 	fprintf(file, "MODULE_LICENSE(\"GPL v2\");\n");
 	fclose(file);
 }
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index eb2bbdd..600e15e 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -14,8 +14,8 @@
 
 #include "utf8n.h"
 
-unsigned int failed_tests;
-unsigned int total_tests;
+static unsigned int failed_tests;
+static unsigned int total_tests;
 
 /* Tests will be based on this version. */
 #define UTF8_LATEST	UNICODE_AGE(12, 1, 0)
@@ -307,4 +307,5 @@ module_init(init_test_ucd);
 module_exit(exit_test_ucd);
 
 MODULE_AUTHOR("Gabriel Krisman Bertazi <krisman@collabora.co.uk>");
+MODULE_DESCRIPTION("Kernel module for testing utf-8 support");
 MODULE_LICENSE("GPL");
diff --git a/fs/unicode/utf8data.c_shipped b/fs/unicode/utf8data.c_shipped
index d9b6290..dafa5fe 100644
--- a/fs/unicode/utf8data.c_shipped
+++ b/fs/unicode/utf8data.c_shipped
@@ -4120,4 +4120,5 @@
 	.utf8data = utf8data,
 };
 EXPORT_SYMBOL_GPL(utf8_data_table);
+MODULE_DESCRIPTION("UTF8 data table");
 MODULE_LICENSE("GPL v2");
diff --git a/fs/xattr.c b/fs/xattr.c
index f8b643f..7672ce5 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -630,10 +630,9 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			ctx->kvalue, ctx->size, ctx->flags);
 }
 
-static long
-setxattr(struct mnt_idmap *idmap, struct dentry *d,
-	const char __user *name, const void __user *value, size_t size,
-	int flags)
+static int path_setxattr(const char __user *pathname,
+			 const char __user *name, const void __user *value,
+			 size_t size, int flags, unsigned int lookup_flags)
 {
 	struct xattr_name kname;
 	struct xattr_ctx ctx = {
@@ -643,33 +642,20 @@ setxattr(struct mnt_idmap *idmap, struct dentry *d,
 		.kname    = &kname,
 		.flags    = flags,
 	};
+	struct path path;
 	int error;
 
 	error = setxattr_copy(name, &ctx);
 	if (error)
 		return error;
 
-	error = do_setxattr(idmap, d, &ctx);
-
-	kvfree(ctx.kvalue);
-	return error;
-}
-
-static int path_setxattr(const char __user *pathname,
-			 const char __user *name, const void __user *value,
-			 size_t size, int flags, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
-
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
-		return error;
+		goto out;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = setxattr(mnt_idmap(path.mnt), path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(mnt_idmap(path.mnt), path.dentry, &ctx);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
@@ -677,6 +663,9 @@ static int path_setxattr(const char __user *pathname,
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+
+out:
+	kvfree(ctx.kvalue);
 	return error;
 }
 
@@ -697,20 +686,32 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 		const void __user *,value, size_t, size, int, flags)
 {
-	struct fd f = fdget(fd);
-	int error = -EBADF;
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.cvalue   = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = flags,
+	};
+	int error;
 
+	CLASS(fd, f)(fd);
 	if (!f.file)
-		return error;
+		return -EBADF;
+
 	audit_file(f.file);
+	error = setxattr_copy(name, &ctx);
+	if (error)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
-		error = setxattr(file_mnt_idmap(f.file),
-				 f.file->f_path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(file_mnt_idmap(f.file),
+				    f.file->f_path.dentry, &ctx);
 		mnt_drop_write_file(f.file);
 	}
-	fdput(f);
+	kvfree(ctx.kvalue);
 	return error;
 }
 
@@ -899,9 +900,17 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
  * Extended attribute REMOVE operations
  */
 static long
-removexattr(struct mnt_idmap *idmap, struct dentry *d,
-	    const char __user *name)
+removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
 {
+	if (is_posix_acl_xattr(name))
+		return vfs_remove_acl(idmap, d, name);
+	return vfs_removexattr(idmap, d, name);
+}
+
+static int path_removexattr(const char __user *pathname,
+			    const char __user *name, unsigned int lookup_flags)
+{
+	struct path path;
 	int error;
 	char kname[XATTR_NAME_MAX + 1];
 
@@ -910,25 +919,13 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d,
 		error = -ERANGE;
 	if (error < 0)
 		return error;
-
-	if (is_posix_acl_xattr(kname))
-		return vfs_remove_acl(idmap, d, kname);
-
-	return vfs_removexattr(idmap, d, kname);
-}
-
-static int path_removexattr(const char __user *pathname,
-			    const char __user *name, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = removexattr(mnt_idmap(path.mnt), path.dentry, name);
+		error = removexattr(mnt_idmap(path.mnt), path.dentry, kname);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
@@ -954,15 +951,23 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 {
 	struct fd f = fdget(fd);
+	char kname[XATTR_NAME_MAX + 1];
 	int error = -EBADF;
 
 	if (!f.file)
 		return error;
 	audit_file(f.file);
+
+	error = strncpy_from_user(kname, name, sizeof(kname));
+	if (error == 0 || error == sizeof(kname))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
 		error = removexattr(file_mnt_idmap(f.file),
-				    f.file->f_path.dentry, name);
+				    f.file->f_path.dentry, kname);
 		mnt_drop_write_file(f.file);
 	}
 	fdput(f);
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index a191f65..c84df23 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -11,7 +11,7 @@ static struct ctl_table_header *xfs_table_header;
 #ifdef CONFIG_PROC_FS
 STATIC int
 xfs_stats_clear_proc_handler(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
@@ -31,7 +31,7 @@ xfs_stats_clear_proc_handler(
 
 STATIC int
 xfs_panic_mask_proc_handler(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
@@ -52,7 +52,7 @@ xfs_panic_mask_proc_handler(
 
 STATIC int
 xfs_deprecated_dointvec_minmax(
-	struct ctl_table	*ctl,
+	const struct ctl_table	*ctl,
 	int			write,
 	void			*buffer,
 	size_t			*lenp,
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 5d14834..8db5bd3 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -563,7 +563,7 @@ static inline void *acpi_driver_data(struct acpi_device *d)
 }
 
 #define to_acpi_device(d)	container_of(d, struct acpi_device, dev)
-#define to_acpi_driver(d)	container_of(d, struct acpi_driver, drv)
+#define to_acpi_driver(d)	container_of_const(d, struct acpi_driver, drv)
 
 static inline struct acpi_device *acpi_dev_parent(struct acpi_device *adev)
 {
diff --git a/include/dt-bindings/i3c/i3c.h b/include/dt-bindings/i3c/i3c.h
new file mode 100644
index 0000000..3734392
--- /dev/null
+++ b/include/dt-bindings/i3c/i3c.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright 2024 NXP
+ */
+
+#ifndef _DT_BINDINGS_I3C_I3C_H
+#define _DT_BINDINGS_I3C_I3C_H
+
+#define I2C_FM      (1 << 4)
+#define I2C_FM_PLUS (0 << 4)
+
+#define I2C_FILTER  (0 << 5)
+#define I2C_NO_FILTER_HIGH_FREQUENCY    (1 << 5)
+#define I2C_NO_FILTER_LOW_FREQUENCY     (2 << 5)
+
+#endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index f0b95c7..0687a44 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -259,6 +259,12 @@ static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
 #endif
 
+#ifdef CONFIG_RISCV
+void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa);
+#else
+static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { }
+#endif
+
 #ifndef PHYS_CPUID_INVALID
 typedef u32 phys_cpuid_t;
 #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1)
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index c6d18f5..89683f3 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -149,7 +149,7 @@ struct ffa_driver {
 	struct device_driver driver;
 };
 
-#define to_ffa_driver(d) container_of(d, struct ffa_driver, driver)
+#define to_ffa_driver(d) container_of_const(d, struct ffa_driver, driver)
 
 static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data)
 {
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index 1539bbd..662b8ae 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -212,7 +212,7 @@ static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev)
 	return container_of(dev, struct auxiliary_device, dev);
 }
 
-static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv)
+static inline const struct auxiliary_driver *to_auxiliary_drv(const struct device_driver *drv)
 {
 	return container_of(drv, struct auxiliary_driver, driver);
 }
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 46d4bdc..ba35bbf 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -47,12 +47,17 @@ extern unsigned long __sw_hweight64(__u64 w);
 	  __builtin_constant_p(*(const unsigned long *)(addr))) ?	\
 	 const##op(nr, addr) : op(nr, addr))
 
+/*
+ * The following macros are non-atomic versions of their non-underscored
+ * counterparts.
+ */
 #define __set_bit(nr, addr)		bitop(___set_bit, nr, addr)
 #define __clear_bit(nr, addr)		bitop(___clear_bit, nr, addr)
 #define __change_bit(nr, addr)		bitop(___change_bit, nr, addr)
 #define __test_and_set_bit(nr, addr)	bitop(___test_and_set_bit, nr, addr)
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
+
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
 #define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index b57118aa..79bb80e 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -211,7 +211,7 @@ struct cdx_driver {
 };
 
 #define to_cdx_driver(_drv) \
-	container_of(_drv, struct cdx_driver, driver)
+	container_of_const(_drv, struct cdx_driver, driver)
 
 /* Macro to avoid include chaining to get THIS_MODULE */
 #define cdx_driver_register(drv) \
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 89f5c34..51ba681 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -122,6 +122,7 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
+	CPUHP_TMIGR_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 099e8b3..801a7e5 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1033,53 +1033,17 @@ void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
 void init_cpu_online(const struct cpumask *src);
 
-static inline void
-set_cpu_possible(unsigned int cpu, bool possible)
-{
-	if (possible)
-		cpumask_set_cpu(cpu, &__cpu_possible_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_possible_mask);
-}
+#define assign_cpu(cpu, mask, val)	\
+	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
-static inline void
-set_cpu_enabled(unsigned int cpu, bool can_be_onlined)
-{
-	if (can_be_onlined)
-		cpumask_set_cpu(cpu, &__cpu_enabled_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_enabled_mask);
-}
-
-static inline void
-set_cpu_present(unsigned int cpu, bool present)
-{
-	if (present)
-		cpumask_set_cpu(cpu, &__cpu_present_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_present_mask);
-}
+#define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
+#define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_possible_mask, (enabled))
+#define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
+#define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
+#define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
 void set_cpu_online(unsigned int cpu, bool online);
 
-static inline void
-set_cpu_active(unsigned int cpu, bool active)
-{
-	if (active)
-		cpumask_set_cpu(cpu, &__cpu_active_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_active_mask);
-}
-
-static inline void
-set_cpu_dying(unsigned int cpu, bool dying)
-{
-	if (dying)
-		cpumask_set_cpu(cpu, &__cpu_dying_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_dying_mask);
-}
-
 /**
  * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
  * @bitmap: the bitmap
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 60b2502..0bea1af 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -21,6 +21,21 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
+struct cxl_event_media_hdr {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	/*
+	 * The meaning of Validity Flags from bit 2 is
+	 * different across DRAM and General Media records
+	 */
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+} __packed;
+
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
 struct cxl_event_generic {
 	struct cxl_event_record_hdr hdr;
@@ -33,14 +48,7 @@ struct cxl_event_generic {
  */
 #define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
 struct cxl_event_gen_media {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
+	struct cxl_event_media_hdr media_hdr;
 	u8 device[3];
 	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
 	u8 reserved[46];
@@ -52,14 +60,7 @@ struct cxl_event_gen_media {
  */
 #define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
 struct cxl_event_dram {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
+	struct cxl_event_media_hdr media_hdr;
 	u8 nibble_mask[3];
 	u8 bank_group;
 	u8 bank;
@@ -95,21 +96,13 @@ struct cxl_event_mem_module {
 	u8 reserved[0x3d];
 } __packed;
 
-/*
- * General Media or DRAM Event Common Fields
- * - provides common access to phys_addr
- */
-struct cxl_event_common {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-} __packed;
-
 union cxl_event {
 	struct cxl_event_generic generic;
 	struct cxl_event_gen_media gen_media;
 	struct cxl_event_dram dram;
 	struct cxl_event_mem_module mem_module;
-	struct cxl_event_common common;
+	/* dram & gen_media event header */
+	struct cxl_event_media_hdr media_hdr;
 } __packed;
 
 /*
diff --git a/include/linux/device.h b/include/linux/device.h
index ace0391..34eb20f 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1031,13 +1031,6 @@ static inline void device_lock_assert(struct device *dev)
 	lockdep_assert_held(&dev->mutex);
 }
 
-static inline struct device_node *dev_of_node(struct device *dev)
-{
-	if (!IS_ENABLED(CONFIG_OF) || !dev)
-		return NULL;
-	return dev->of_node;
-}
-
 static inline bool dev_has_sync_state(struct device *dev)
 {
 	if (!dev)
@@ -1144,10 +1137,18 @@ void unlock_device_hotplug(void);
 int lock_device_hotplug_sysfs(void);
 int device_offline(struct device *dev);
 int device_online(struct device *dev);
+
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
 void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
-void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
 void device_set_node(struct device *dev, struct fwnode_handle *fwnode);
+void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
+
+static inline struct device_node *dev_of_node(struct device *dev)
+{
+	if (!IS_ENABLED(CONFIG_OF) || !dev)
+		return NULL;
+	return dev->of_node;
+}
 
 static inline int dev_num_vf(struct device *dev)
 {
@@ -1176,12 +1177,12 @@ static inline void *dev_get_platdata(const struct device *dev)
  * Manual binding of a device to driver. See drivers/base/bus.c
  * for information on use.
  */
-int __must_check device_driver_attach(struct device_driver *drv,
+int __must_check device_driver_attach(const struct device_driver *drv,
 				      struct device *dev);
 int __must_check device_bind_driver(struct device *dev);
 void device_release_driver(struct device *dev);
 int  __must_check device_attach(struct device *dev);
-int __must_check driver_attach(struct device_driver *drv);
+int __must_check driver_attach(const struct device_driver *drv);
 void device_initial_probe(struct device *dev);
 int __must_check device_reprobe(struct device *dev);
 
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 5ef4ec1..807831d 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -81,7 +81,7 @@ struct bus_type {
 	const struct attribute_group **dev_groups;
 	const struct attribute_group **drv_groups;
 
-	int (*match)(struct device *dev, struct device_driver *drv);
+	int (*match)(struct device *dev, const struct device_driver *drv);
 	int (*uevent)(const struct device *dev, struct kobj_uevent_env *env);
 	int (*probe)(struct device *dev);
 	void (*sync_state)(struct device *dev);
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index 7738f45..1fc8b68 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -146,16 +146,16 @@ struct driver_attribute {
 #define DRIVER_ATTR_WO(_name) \
 	struct driver_attribute driver_attr_##_name = __ATTR_WO(_name)
 
-int __must_check driver_create_file(struct device_driver *driver,
+int __must_check driver_create_file(const struct device_driver *driver,
 				    const struct driver_attribute *attr);
-void driver_remove_file(struct device_driver *driver,
+void driver_remove_file(const struct device_driver *driver,
 			const struct driver_attribute *attr);
 
 int driver_set_override(struct device *dev, const char **override,
 			const char *s, size_t len);
 int __must_check driver_for_each_device(struct device_driver *drv, struct device *start,
 					void *data, int (*fn)(struct device *dev, void *));
-struct device *driver_find_device(struct device_driver *drv,
+struct device *driver_find_device(const struct device_driver *drv,
 				  struct device *start, const void *data,
 				  int (*match)(struct device *dev, const void *data));
 
@@ -165,7 +165,7 @@ struct device *driver_find_device(struct device_driver *drv,
  * @drv: the driver we're iterating
  * @name: name of the device to match
  */
-static inline struct device *driver_find_device_by_name(struct device_driver *drv,
+static inline struct device *driver_find_device_by_name(const struct device_driver *drv,
 							const char *name)
 {
 	return driver_find_device(drv, NULL, name, device_match_name);
@@ -178,7 +178,7 @@ static inline struct device *driver_find_device_by_name(struct device_driver *dr
  * @np: of_node pointer to match.
  */
 static inline struct device *
-driver_find_device_by_of_node(struct device_driver *drv,
+driver_find_device_by_of_node(const struct device_driver *drv,
 			      const struct device_node *np)
 {
 	return driver_find_device(drv, NULL, np, device_match_of_node);
@@ -203,13 +203,13 @@ driver_find_device_by_fwnode(struct device_driver *drv,
  * @drv: the driver we're iterating
  * @devt: devt pointer to match.
  */
-static inline struct device *driver_find_device_by_devt(struct device_driver *drv,
+static inline struct device *driver_find_device_by_devt(const struct device_driver *drv,
 							dev_t devt)
 {
 	return driver_find_device(drv, NULL, &devt, device_match_devt);
 }
 
-static inline struct device *driver_find_next_device(struct device_driver *drv,
+static inline struct device *driver_find_next_device(const struct device_driver *drv,
 						     struct device *start)
 {
 	return driver_find_device(drv, start, NULL, device_match_any);
@@ -223,14 +223,14 @@ static inline struct device *driver_find_next_device(struct device_driver *drv,
  * @adev: ACPI_COMPANION device to match.
  */
 static inline struct device *
-driver_find_device_by_acpi_dev(struct device_driver *drv,
+driver_find_device_by_acpi_dev(const struct device_driver *drv,
 			       const struct acpi_device *adev)
 {
 	return driver_find_device(drv, NULL, adev, device_match_acpi_dev);
 }
 #else
 static inline struct device *
-driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev)
+driver_find_device_by_acpi_dev(const struct device_driver *drv, const void *adev)
 {
 	return NULL;
 }
diff --git a/include/linux/dfl.h b/include/linux/dfl.h
index 0a7a00a..1f02db0 100644
--- a/include/linux/dfl.h
+++ b/include/linux/dfl.h
@@ -71,7 +71,7 @@ struct dfl_driver {
 };
 
 #define to_dfl_dev(d) container_of(d, struct dfl_device, dev)
-#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv)
+#define to_dfl_drv(d) container_of_const(d, struct dfl_driver, drv)
 
 /*
  * use a macro to avoid include chaining to get THIS_MODULE.
diff --git a/include/linux/dio.h b/include/linux/dio.h
index 2b59239..464331c 100644
--- a/include/linux/dio.h
+++ b/include/linux/dio.h
@@ -93,7 +93,7 @@ struct dio_driver {
 	struct device_driver driver;
 };
 
-#define to_dio_driver(drv)    container_of(drv, struct dio_driver, driver)
+#define to_dio_driver(drv)    container_of_const(drv, struct dio_driver, driver)
 
 /* DIO/DIO-II boards all have the following 8bit registers.
  * These are offsets from the base of the device.
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 9fc0306..b137fdb 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1608,7 +1608,8 @@ int dma_async_device_register(struct dma_device *device);
 int dmaenginem_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
 int dma_async_device_channel_register(struct dma_device *device,
-				      struct dma_chan *chan);
+				      struct dma_chan *chan,
+				      const char *name);
 void dma_async_device_channel_unregister(struct dma_device *device,
 					 struct dma_chan *chan);
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
diff --git a/include/linux/eisa.h b/include/linux/eisa.h
index b012e30..f98200c 100644
--- a/include/linux/eisa.h
+++ b/include/linux/eisa.h
@@ -60,7 +60,7 @@ struct eisa_driver {
 	struct device_driver         driver;
 };
 
-#define to_eisa_driver(drv) container_of(drv,struct eisa_driver, driver)
+#define to_eisa_driver(drv) container_of_const(drv,struct eisa_driver, driver)
 
 /* These external functions are only available when EISA support is enabled. */
 #ifdef CONFIG_EISA
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 00abe0e..1cca14c 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -462,9 +462,8 @@ struct fw_iso_packet {
 				/* rx: Sync bit, wait for matching sy	*/
 	u32 tag:2;		/* tx: Tag in packet header		*/
 	u32 sy:4;		/* tx: Sy in packet header		*/
-	u32 header_length:8;	/* Length of immediate header		*/
-				/* tx: Top of 1394 isoch. data_block    */
-	u32 header[] __counted_by(header_length);
+	u32 header_length:8;	/* Size of immediate header		*/
+	u32 header[];		/* tx: Top of 1394 isoch. data_block	*/
 };
 
 #define FW_ISO_CONTEXT_TRANSMIT			0
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index f026f89..aae1b85 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -98,6 +98,10 @@ static inline bool firmware_request_builtin(struct firmware *fw,
 #if IS_REACHABLE(CONFIG_FW_LOADER)
 int request_firmware(const struct firmware **fw, const char *name,
 		     struct device *device);
+int firmware_request_nowait_nowarn(
+	struct module *module, const char *name,
+	struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context));
 int firmware_request_nowarn(const struct firmware **fw, const char *name,
 			    struct device *device);
 int firmware_request_platform(const struct firmware **fw, const char *name,
@@ -123,6 +127,14 @@ static inline int request_firmware(const struct firmware **fw,
 	return -EINVAL;
 }
 
+static inline int firmware_request_nowait_nowarn(
+	struct module *module, const char *name,
+	struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context))
+{
+	return -EINVAL;
+}
+
 static inline int firmware_request_nowarn(const struct firmware **fw,
 					  const char *name,
 					  struct device *device)
diff --git a/include/linux/fsi.h b/include/linux/fsi.h
index 3df8c54..8c5eef8 100644
--- a/include/linux/fsi.h
+++ b/include/linux/fsi.h
@@ -44,7 +44,7 @@ struct fsi_driver {
 };
 
 #define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev)
-#define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv)
+#define to_fsi_drv(drvp) container_of_const(drvp, struct fsi_driver, drv)
 
 extern int fsi_driver_register(struct fsi_driver *fsi_drv);
 extern void fsi_driver_unregister(struct fsi_driver *fsi_drv);
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index a1b3de8..083c860 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -56,7 +56,7 @@ struct fsl_mc_driver {
 };
 
 #define to_fsl_mc_driver(_drv) \
-	container_of(_drv, struct fsl_mc_driver, driver)
+	container_of_const(_drv, struct fsl_mc_driver, driver)
 
 /**
  * enum fsl_mc_pool_type - Types of allocatable MC bus resources
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 51575b7..fd5e84d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -471,7 +471,7 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 
 extern int stack_tracer_enabled;
 
-int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
 		       size_t *lenp, loff_t *ppos);
 
 /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
@@ -1175,7 +1175,7 @@ extern int tracepoint_printk;
 extern void disable_trace_on_warning(void);
 extern int __disable_trace_on_warning;
 
-int tracepoint_printk_sysctl(struct ctl_table *table, int write,
+int tracepoint_printk_sysctl(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos);
 
 #else /* CONFIG_TRACING */
diff --git a/include/linux/gameport.h b/include/linux/gameport.h
index 07e3701..86d62fd 100644
--- a/include/linux/gameport.h
+++ b/include/linux/gameport.h
@@ -58,7 +58,7 @@ struct gameport_driver {
 
 	bool ignore;
 };
-#define to_gameport_driver(d)	container_of(d, struct gameport_driver, driver)
+#define to_gameport_driver(d)	container_of_const(d, struct gameport_driver, driver)
 
 int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode);
 void gameport_close(struct gameport *gameport);
diff --git a/include/linux/greybus.h b/include/linux/greybus.h
index 634c951..4d58e27 100644
--- a/include/linux/greybus.h
+++ b/include/linux/greybus.h
@@ -64,7 +64,7 @@ struct greybus_driver {
 
 	struct device_driver driver;
 };
-#define to_greybus_driver(d) container_of(d, struct greybus_driver, driver)
+#define to_greybus_driver(d) container_of_const(d, struct greybus_driver, driver)
 
 static inline void greybus_set_drvdata(struct gb_bundle *bundle, void *data)
 {
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cff002b..e25d9eb 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -74,14 +74,20 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
 
 /*
- * Mask of all large folio orders supported for file THP.
+ * Mask of all large folio orders supported for file THP. Folios in a DAX
+ * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to
+ * it.
  */
-#define THP_ORDERS_ALL_FILE	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DAX		\
+	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DEFAULT	\
+	((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0))
 
 /*
  * Mask of all large folio orders supported for THP.
  */
-#define THP_ORDERS_ALL		(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+#define THP_ORDERS_ALL	\
+	(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT)
 
 #define TVA_SMAPS		(1 << 0)	/* Will be used for procfs */
 #define TVA_IN_PF		(1 << 1)	/* Page fault handler */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 5e39baa..22c22fb 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1330,11 +1330,7 @@ struct hv_device {
 
 
 #define device_to_hv_device(d)	container_of_const(d, struct hv_device, device)
-
-static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d)
-{
-	return container_of(d, struct hv_driver, driver);
-}
+#define drv_to_hv_drv(d)	container_of_const(d, struct hv_driver, driver)
 
 static inline void hv_set_drvdata(struct hv_device *dev, void *data)
 {
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 8caaa13..07e33bb 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -303,7 +303,7 @@ struct i2c_driver {
 
 	u32 flags;
 };
-#define to_i2c_driver(d) container_of(d, struct i2c_driver, driver)
+#define to_i2c_driver(d) container_of_const(d, struct i2c_driver, driver)
 
 /**
  * struct i2c_client - represent an I2C slave device
diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index e119f11..0a8a44a 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -183,10 +183,7 @@ struct i3c_driver {
 	const struct i3c_device_id *id_table;
 };
 
-static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv)
-{
-	return container_of(drv, struct i3c_driver, driver);
-}
+#define drv_to_i3cdrv(__drv)	container_of_const(__drv, struct i3c_driver, driver)
 
 struct device *i3cdev_to_dev(struct i3c_device *i3cdev);
 
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 0ca27dd..074f632 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -33,6 +33,7 @@ enum {
 struct i3c_master_controller;
 struct i3c_bus;
 struct i3c_device;
+extern const struct bus_type i3c_bus_type;
 
 /**
  * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3bb6198..3315005 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -404,7 +404,7 @@ struct io_ring_ctx {
 	spinlock_t		napi_lock;	/* napi_list lock */
 
 	/* napi busy poll default timeout */
-	unsigned int		napi_busy_poll_to;
+	ktime_t			napi_busy_poll_dt;
 	bool			napi_prefer_busy_poll;
 	bool			napi_enabled;
 
@@ -461,7 +461,6 @@ enum {
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
 	REQ_F_POLL_NO_LAZY_BIT,
-	REQ_F_CANCEL_SEQ_BIT,
 	REQ_F_CAN_POLL_BIT,
 	REQ_F_BL_EMPTY_BIT,
 	REQ_F_BL_NO_RECYCLE_BIT,
@@ -536,8 +535,6 @@ enum {
 	REQ_F_HASH_LOCKED	= IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
 	/* don't use lazy poll wake for this request */
 	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
-	/* cancel sequence is set and valid */
-	REQ_F_CANCEL_SEQ	= IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
 	/* file is pollable */
 	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
 	/* buffer list was empty after selection of buffer */
diff --git a/include/linux/maple.h b/include/linux/maple.h
index 9aae44e..3be4e56 100644
--- a/include/linux/maple.h
+++ b/include/linux/maple.h
@@ -97,7 +97,7 @@ int maple_add_packet(struct maple_device *mdev, u32 function,
 void maple_clear_dev(struct maple_device *mdev);
 
 #define to_maple_dev(n) container_of(n, struct maple_device, dev)
-#define to_maple_driver(n) container_of(n, struct maple_driver, drv)
+#define to_maple_driver(n) container_of_const(n, struct maple_driver, drv)
 
 #define maple_get_drvdata(d)		dev_get_drvdata(&(d)->dev)
 #define maple_set_drvdata(d,p)		dev_set_drvdata(&(d)->dev, (p))
diff --git a/include/linux/mcb.h b/include/linux/mcb.h
index 0b971b2..4ab2691 100644
--- a/include/linux/mcb.h
+++ b/include/linux/mcb.h
@@ -94,10 +94,7 @@ struct mcb_driver {
 	void (*shutdown)(struct mcb_device *mdev);
 };
 
-static inline struct mcb_driver *to_mcb_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct mcb_driver, driver);
-}
+#define to_mcb_driver(__drv)	container_of_const(__drv, struct mcb_driver, driver)
 
 static inline void *mcb_get_drvdata(struct mcb_device *dev)
 {
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 68f8d2e..efeca5b 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -31,7 +31,7 @@ struct mdio_device {
 	struct mii_bus *bus;
 	char modalias[MDIO_NAME_SIZE];
 
-	int (*bus_match)(struct device *dev, struct device_driver *drv);
+	int (*bus_match)(struct device *dev, const struct device_driver *drv);
 	void (*device_free)(struct mdio_device *mdiodev);
 	void (*device_remove)(struct mdio_device *mdiodev);
 
@@ -57,11 +57,8 @@ struct mdio_driver_common {
 };
 #define MDIO_DEVICE_FLAG_PHY		1
 
-static inline struct mdio_driver_common *
-to_mdio_common_driver(const struct device_driver *driver)
-{
-	return container_of(driver, struct mdio_driver_common, driver);
-}
+#define to_mdio_common_driver(__drv_c)	container_of_const(__drv_c, struct mdio_driver_common,	\
+							   driver)
 
 /* struct mdio_driver: Generic MDIO driver */
 struct mdio_driver {
@@ -80,12 +77,8 @@ struct mdio_driver {
 	void (*shutdown)(struct mdio_device *mdiodev);
 };
 
-static inline struct mdio_driver *
-to_mdio_driver(const struct device_driver *driver)
-{
-	return container_of(to_mdio_common_driver(driver), struct mdio_driver,
-			    mdiodrv);
-}
+#define to_mdio_driver(__drv_m)	container_of_const(to_mdio_common_driver(__drv_m),	\
+						   struct mdio_driver, mdiodrv)
 
 /* device driver data */
 static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data)
@@ -105,7 +98,7 @@ void mdio_device_remove(struct mdio_device *mdiodev);
 void mdio_device_reset(struct mdio_device *mdiodev, int value);
 int mdio_driver_register(struct mdio_driver *drv);
 void mdio_driver_unregister(struct mdio_driver *drv);
-int mdio_device_bus_match(struct device *dev, struct device_driver *drv);
+int mdio_device_bus_match(struct device *dev, const struct device_driver *drv);
 
 static inline void mdio_device_get(struct mdio_device *mdiodev)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7e2eb09..0e5bf25 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -109,6 +109,7 @@ struct mem_cgroup_per_node {
 
 	/* Fields which get updated often at the end. */
 	struct lruvec		lruvec;
+	CACHELINE_PADDING(_pad2_);
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
 };
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index fabd6ed..059dc94 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -528,7 +528,7 @@ struct mhi_driver {
 	struct device_driver driver;
 };
 
-#define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver)
+#define to_mhi_driver(drv) container_of_const(drv, struct mhi_driver, driver)
 #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev)
 
 /**
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 11bf321..7b40fc8 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -221,7 +221,7 @@ struct mhi_ep_driver {
 };
 
 #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev)
-#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver)
+#define to_mhi_ep_driver(drv) container_of_const(drv, struct mhi_ep_driver, driver)
 
 /*
  * module_mhi_ep_driver() - Helper macro for drivers that don't do
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 2ec5592..9c2848a 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -45,17 +45,20 @@
 
 #define __cmp(op, x, y)	((x) __cmp_op_##op (y) ? (x) : (y))
 
-#define __cmp_once(op, x, y, unique_x, unique_y) ({	\
-	typeof(x) unique_x = (x);			\
-	typeof(y) unique_y = (y);			\
+#define __cmp_once_unique(op, type, x, y, ux, uy) \
+	({ type ux = (x); type uy = (y); __cmp(op, ux, uy); })
+
+#define __cmp_once(op, type, x, y) \
+	__cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
+
+#define __careful_cmp_once(op, x, y) ({			\
 	static_assert(__types_ok(x, y),			\
 		#op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \
-	__cmp(op, unique_x, unique_y); })
+	__cmp_once(op, __auto_type, x, y); })
 
 #define __careful_cmp(op, x, y)					\
 	__builtin_choose_expr(__is_constexpr((x) - (y)),	\
-		__cmp(op, x, y),				\
-		__cmp_once(op, x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y)))
+		__cmp(op, x, y), __careful_cmp_once(op, x, y))
 
 #define __clamp(val, lo, hi)	\
 	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
@@ -158,7 +161,7 @@
  * @x: first value
  * @y: second value
  */
-#define min_t(type, x, y)	__careful_cmp(min, (type)(x), (type)(y))
+#define min_t(type, x, y) __cmp_once(min, type, x, y)
 
 /**
  * max_t - return maximum of two values, using the specified type
@@ -166,7 +169,7 @@
  * @x: first value
  * @y: second value
  */
-#define max_t(type, x, y)	__careful_cmp(max, (type)(x), (type)(y))
+#define max_t(type, x, y) __cmp_once(max, type, x, y)
 
 /*
  * Do not check the array parameter using __must_be_array().
@@ -270,4 +273,11 @@ static inline bool in_range32(u32 val, u32 start, u32 len)
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
+/*
+ * Use these carefully: no type checking, and uses the arguments
+ * multiple times. Use for obvious constants only.
+ */
+#define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b))
+#define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b))
+
 #endif	/* _LINUX_MINMAX_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7d044e7..c4b238a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -204,11 +204,11 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
 
-int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
+int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -407,6 +407,13 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 #ifdef CONFIG_64BIT
+#define VM_DROPPABLE_BIT	40
+#define VM_DROPPABLE		BIT(VM_DROPPABLE_BIT)
+#else
+#define VM_DROPPABLE		VM_NONE
+#endif
+
+#ifdef CONFIG_64BIT
 /* VM is sealed, in vm_flags */
 #define VM_SEALED	_BITUL(63)
 #endif
@@ -3130,21 +3137,7 @@ extern void reserve_bootmem_region(phys_addr_t start,
 				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
-static inline void free_reserved_page(struct page *page)
-{
-	if (mem_alloc_profiling_enabled()) {
-		union codetag_ref *ref = get_page_tag_ref(page);
-
-		if (ref) {
-			set_codetag_empty(ref);
-			put_page_tag_ref(ref);
-		}
-	}
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	adjust_managed_page_count(page, 1);
-}
+void free_reserved_page(struct page *page);
 #define free_highmem_page(page) free_reserved_page(page)
 
 static inline void mark_page_reserved(struct page *page)
@@ -3847,7 +3840,7 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 #endif
 
diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index ac57769..dfa4800 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -61,13 +61,8 @@ struct moxtet_driver {
 	struct device_driver		driver;
 };
 
-static inline struct moxtet_driver *
-to_moxtet_driver(struct device_driver *drv)
-{
-	if (!drv)
-		return NULL;
-	return container_of(drv, struct moxtet_driver, driver);
-}
+#define to_moxtet_driver(__drv)	\
+	( __drv ? container_of_const(__drv, struct moxtet_driver, driver) : NULL )
 
 extern int __moxtet_register_driver(struct module *owner,
 				    struct moxtet_driver *mdrv);
diff --git a/include/linux/nd.h b/include/linux/nd.h
index b9771ba..fa099e2 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -84,11 +84,7 @@ struct nd_device_driver {
 	void (*notify)(struct device *dev, enum nvdimm_event event);
 };
 
-static inline struct nd_device_driver *to_nd_device_driver(
-		struct device_driver *drv)
-{
-	return container_of(drv, struct nd_device_driver, drv);
-};
+#define to_nd_device_driver(__drv)	container_of_const(__drv, struct nd_device_driver, drv)
 
 /**
  * struct nd_namespace_common - core infrastructure of a namespace
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index c12a329..7b2ae2e 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -485,6 +485,9 @@ enum {
 	NVME_ID_NS_NVM_STS_MASK		= 0x7f,
 	NVME_ID_NS_NVM_GUARD_SHIFT	= 7,
 	NVME_ID_NS_NVM_GUARD_MASK	= 0x3,
+	NVME_ID_NS_NVM_QPIF_SHIFT	= 9,
+	NVME_ID_NS_NVM_QPIF_MASK	= 0xf,
+	NVME_ID_NS_NVM_QPIFS		= 1 << 3,
 };
 
 static inline __u8 nvme_elbaf_sts(__u32 elbaf)
@@ -497,6 +500,11 @@ static inline __u8 nvme_elbaf_guard_type(__u32 elbaf)
 	return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK;
 }
 
+static inline __u8 nvme_elbaf_qualified_guard_type(__u32 elbaf)
+{
+	return (elbaf >> NVME_ID_NS_NVM_QPIF_SHIFT) & NVME_ID_NS_NVM_QPIF_MASK;
+}
+
 struct nvme_id_ctrl_nvm {
 	__u8	vsl;
 	__u8	wzsl;
@@ -576,6 +584,7 @@ enum {
 	NVME_NVM_NS_16B_GUARD	= 0,
 	NVME_NVM_NS_32B_GUARD	= 1,
 	NVME_NVM_NS_64B_GUARD	= 2,
+	NVME_NVM_NS_QTYPE_GUARD	= 3,
 };
 
 static inline __u8 nvme_lbaf_index(__u8 flbas)
diff --git a/include/linux/of.h b/include/linux/of.h
index 13cf7a4..85b60ac 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -430,11 +430,9 @@ extern int of_detach_node(struct device_node *);
 #define of_match_ptr(_ptr)	(_ptr)
 
 /*
- * struct property *prop;
- * const __be32 *p;
  * u32 u;
  *
- * of_property_for_each_u32(np, "propname", prop, p, u)
+ * of_property_for_each_u32(np, "propname", u)
  *         printk("U32 value: %x\n", u);
  */
 const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur,
@@ -1431,11 +1429,12 @@ static inline int of_property_read_s32(const struct device_node *np,
 	     err == 0;							\
 	     err = of_phandle_iterator_next(it))
 
-#define of_property_for_each_u32(np, propname, prop, p, u)	\
-	for (prop = of_find_property(np, propname, NULL),	\
-		p = of_prop_next_u32(prop, NULL, &u);		\
-		p;						\
-		p = of_prop_next_u32(prop, p, &u))
+#define of_property_for_each_u32(np, propname, u)			\
+	for (struct {struct property *prop; const __be32 *item; } _it =	\
+		{of_find_property(np, propname, NULL),			\
+		 of_prop_next_u32(_it.prop, NULL, &u)};			\
+	     _it.item;							\
+	     _it.item = of_prop_next_u32(_it.prop, _it.item, &u))
 
 #define of_property_for_each_string(np, propname, prop, s)	\
 	for (prop = of_find_property(np, propname, NULL),	\
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 547e82c..fc6b9c8 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -41,13 +41,13 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
 #elif defined(CONFIG_TRANSPARENT_HUGEPAGE)
 
-#define pageblock_order		min_t(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER)
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 0639d4d..18a3aeb 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -107,8 +107,7 @@ struct pci_epf_driver {
 	const struct pci_epf_device_id	*id_table;
 };
 
-#define to_pci_epf_driver(drv) (container_of((drv), struct pci_epf_driver, \
-				driver))
+#define to_pci_epf_driver(drv) container_of_const((drv), struct pci_epf_driver, driver)
 
 /**
  * struct pci_epf_bar - represents the BAR of EPF device
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9e36b6c..4cf89a4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -959,10 +959,8 @@ struct pci_driver {
 	bool driver_managed_dma;
 };
 
-static inline struct pci_driver *to_pci_driver(struct device_driver *drv)
-{
-    return drv ? container_of(drv, struct pci_driver, driver) : NULL;
-}
+#define to_pci_driver(__drv)	\
+	( __drv ? container_of_const(__drv, struct pci_driver, driver) : NULL )
 
 /**
  * PCI_DEVICE - macro used to describe a specific PCI device
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 65ece0d..1a89422 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1582,11 +1582,11 @@ extern int sysctl_perf_cpu_time_max_percent;
 
 extern void perf_sample_event_took(u64 sample_len_ns);
 
-int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
+int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_event_max_stack_handler(struct ctl_table *table, int write,
+int perf_event_max_stack_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
 
 /* Access to perf_event_open(2) syscall. */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 04ae5c8..6b7d40d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1187,7 +1187,7 @@ struct phy_driver {
 	int (*led_polarity_set)(struct phy_device *dev, int index,
 				unsigned long modes);
 };
-#define to_phy_driver(d) container_of(to_mdio_common_driver(d),		\
+#define to_phy_driver(d) container_of_const(to_mdio_common_driver(d),		\
 				      struct phy_driver, mdiodrv)
 
 #define PHY_ANY_ID "MATCH ANY PHY"
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 7a41c72..d422db6 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -237,15 +237,14 @@ struct platform_driver {
 	int (*probe)(struct platform_device *);
 
 	/*
-	 * Traditionally the remove callback returned an int which however is
-	 * ignored by the driver core. This led to wrong expectations by driver
-	 * authors who thought returning an error code was a valid error
-	 * handling strategy. To convert to a callback returning void, new
-	 * drivers should implement .remove_new() until the conversion it done
-	 * that eventually makes .remove() return void.
+	 * .remove_new() is a relic from a prototype conversion of .remove().
+	 * New drivers are supposed to implement .remove(). Once all drivers are
+	 * converted to not use .remove_new any more, it will be dropped.
 	 */
-	int (*remove)(struct platform_device *);
-	void (*remove_new)(struct platform_device *);
+	union {
+		void (*remove)(struct platform_device *);
+		void (*remove_new)(struct platform_device *);
+	};
 
 	void (*shutdown)(struct platform_device *);
 	int (*suspend)(struct platform_device *, pm_message_t state);
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 7f2ff95..b7a7158 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -383,7 +383,7 @@ struct pnp_driver {
 	struct device_driver driver;
 };
 
-#define	to_pnp_driver(drv) container_of(drv, struct pnp_driver, driver)
+#define	to_pnp_driver(drv) container_of_const(drv, struct pnp_driver, driver)
 
 struct pnp_card_driver {
 	struct list_head global_list;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 7239976..b937cef 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -196,7 +196,7 @@ void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
 extern asmlinkage void dump_stack(void) __cold;
 void printk_trigger_flush(void);
-void console_replay_all(void);
+void console_try_replay_all(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -276,7 +276,7 @@ static inline void dump_stack(void)
 static inline void printk_trigger_flush(void)
 {
 }
-static inline void console_replay_all(void)
+static inline void console_try_replay_all(void)
 {
 }
 #endif
diff --git a/include/linux/rio.h b/include/linux/rio.h
index 2cd6372..3c29f40 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -465,7 +465,7 @@ struct rio_driver {
 	struct device_driver driver;
 };
 
-#define	to_rio_driver(drv) container_of(drv,struct rio_driver, driver)
+#define	to_rio_driver(drv) container_of_const(drv,struct rio_driver, driver)
 
 union rio_pw_msg {
 	struct {
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 3a9bb5b..688466a 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -945,7 +945,7 @@ struct scmi_device {
 	struct scmi_handle *handle;
 };
 
-#define to_scmi_dev(d) container_of(d, struct scmi_device, dev)
+#define to_scmi_dev(d) container_of_const(d, struct scmi_device, dev)
 
 struct scmi_device_id {
 	u8 protocol_id;
diff --git a/include/linux/security.h b/include/linux/security.h
index de3af33..1390f1e 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -228,7 +228,7 @@ struct request_sock;
 #define LSM_UNSAFE_NO_NEW_PRIVS	4
 
 #ifdef CONFIG_MMU
-extern int mmap_min_addr_handler(struct ctl_table *table, int write,
+extern int mmap_min_addr_handler(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
diff --git a/include/linux/serio.h b/include/linux/serio.h
index 7ca41af..bf2191f 100644
--- a/include/linux/serio.h
+++ b/include/linux/serio.h
@@ -80,7 +80,7 @@ struct serio_driver {
 
 	struct device_driver driver;
 };
-#define to_serio_driver(d)	container_of(d, struct serio_driver, driver)
+#define to_serio_driver(d)	container_of_const(d, struct serio_driver, driver)
 
 int serio_open(struct serio *serio, struct serio_driver *drv);
 void serio_close(struct serio *serio);
diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h
index 3042385..a4608d9 100644
--- a/include/linux/slimbus.h
+++ b/include/linux/slimbus.h
@@ -91,7 +91,7 @@ struct slim_driver {
 	struct device_driver		driver;
 	const struct slim_device_id	*id_table;
 };
-#define to_slim_driver(d) container_of(d, struct slim_driver, driver)
+#define to_slim_driver(d) container_of_const(d, struct slim_driver, driver)
 
 /**
  * struct slim_val_inf - Slimbus value or information element
diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h
index 7161a31..a532d1e 100644
--- a/include/linux/soc/qcom/apr.h
+++ b/include/linux/soc/qcom/apr.h
@@ -162,7 +162,7 @@ struct apr_driver {
 };
 
 typedef struct apr_driver gpr_driver_t;
-#define to_apr_driver(d) container_of(d, struct apr_driver, driver)
+#define to_apr_driver(d) container_of_const(d, struct apr_driver, driver)
 
 /*
  * use a macro to avoid include chaining to get THIS_MODULE
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index f411c17..ce1a379 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -660,5 +660,7 @@
 /* For Tensor GS101 */
 #define GS101_SYSIP_DAT0					(0x810)
 #define GS101_SYSTEM_CONFIGURATION				(0x3A00)
+#define GS101_PHY_CTRL_USB20					(0x3EB0)
+#define GS101_PHY_CTRL_USBDP					(0x3EB4)
 
 #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 13e96d8..94fc1b5 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -903,6 +903,7 @@ struct sdw_master_ops {
  * meaningful if multi_link is set. If set to 1, hardware-based
  * synchronization will be used even if a stream only uses a single
  * SoundWire segment.
+ * @stream_refcount: number of streams currently using this bus
  */
 struct sdw_bus {
 	struct device *dev;
@@ -933,6 +934,7 @@ struct sdw_bus {
 	u32 bank_switch_timeout;
 	bool multi_link;
 	int hw_sync_min_links;
+	int stream_refcount;
 };
 
 int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index 8e78417..d537587b 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -182,6 +182,11 @@
 #define SDW_SHIM2_INTEL_VS_ACTMCTL_DODSE	BIT(2)
 #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS	GENMASK(4, 3)
 #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAISE	BIT(5)
+#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLSS		BIT(6)
+#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDS		GENMASK(11, 7)
+#define SDW_SHIM3_INTEL_VS_ACTMCTL_DODSE2	GENMASK(13, 12)
+#define SDW_SHIM3_INTEL_VS_ACTMCTL_DOAISE2	BIT(14)
+#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDE		BIT(15)
 
 /**
  * struct sdw_intel_stream_params_data: configuration passed during
diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h
index 693320b..d405935 100644
--- a/include/linux/soundwire/sdw_type.h
+++ b/include/linux/soundwire/sdw_type.h
@@ -13,7 +13,7 @@ static inline int is_sdw_slave(const struct device *dev)
 	return dev->type == &sdw_slave_type;
 }
 
-#define drv_to_sdw_driver(_drv) container_of(_drv, struct sdw_driver, driver)
+#define drv_to_sdw_driver(_drv) container_of_const(_drv, struct sdw_driver, driver)
 
 #define sdw_register_driver(drv) \
 	__sdw_register_driver(drv, THIS_MODULE)
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index d7a16e0..e4f3f3d 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -351,10 +351,8 @@ struct spi_driver {
 	struct device_driver	driver;
 };
 
-static inline struct spi_driver *to_spi_driver(struct device_driver *drv)
-{
-	return drv ? container_of(drv, struct spi_driver, driver) : NULL;
-}
+#define to_spi_driver(__drv)   \
+	( __drv ? container_of_const(__drv, struct spi_driver, driver) : NULL )
 
 extern int __spi_register_driver(struct module *owner, struct spi_driver *sdrv);
 
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index a225738..e1fb11e 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -325,7 +325,7 @@ struct ssb_driver {
 
 	struct device_driver drv;
 };
-#define drv_to_ssb_drv(_drv) container_of(_drv, struct ssb_driver, drv)
+#define drv_to_ssb_drv(_drv) container_of_const(_drv, struct ssb_driver, drv)
 
 extern int __ssb_driver_register(struct ssb_driver *drv, struct module *owner);
 #define ssb_driver_register(drv) \
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 54fbec0..aa4c6d4 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -61,31 +61,31 @@ extern const int sysctl_vals[];
 
 extern const unsigned long sysctl_long_vals[];
 
-typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer,
+typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
-int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_dobool(struct ctl_table *table, int write, void *buffer,
+int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dobool(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer,
+int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer,
+int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer,
 			size_t *lenp, loff_t *ppos);
-int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+int proc_dointvec_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
-int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *,
+int proc_dointvec_userhz_jiffies(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *,
+int proc_dointvec_ms_jiffies(const struct ctl_table *, int, void *, size_t *,
 		loff_t *);
-int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *,
+int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int, void *,
 		size_t *, loff_t *);
-int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_do_static_key(struct ctl_table *table, int write, void *buffer,
+int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *);
+int proc_do_static_key(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
 /*
@@ -287,7 +287,7 @@ static inline bool sysctl_is_alias(char *param)
 }
 #endif /* CONFIG_SYSCTL */
 
-int sysctl_max_threads(struct ctl_table *table, int write, void *buffer,
+int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 
 #endif /* _LINUX_SYSCTL_H */
diff --git a/include/linux/tc.h b/include/linux/tc.h
index 1638660..8416bae 100644
--- a/include/linux/tc.h
+++ b/include/linux/tc.h
@@ -108,7 +108,7 @@ struct tc_driver {
 	struct device_driver driver;
 };
 
-#define to_tc_driver(drv) container_of(drv, struct tc_driver, driver)
+#define to_tc_driver(drv) container_of_const(drv, struct tc_driver, driver)
 
 /*
  * Return TURBOchannel clock frequency in Hz.
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index 786b9ae..a54c203 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -298,6 +298,6 @@ struct tee_client_driver {
 };
 
 #define to_tee_client_driver(d) \
-		container_of(d, struct tee_client_driver, driver)
+		container_of_const(d, struct tee_client_driver, driver)
 
 #endif /*__TEE_DRV_H*/
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 3064314..d8e4105 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -5,6 +5,7 @@
 #include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/minmax.h>
+#include <linux/nospec.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
@@ -138,13 +139,26 @@ __copy_to_user(void __user *to, const void *from, unsigned long n)
 	return raw_copy_to_user(to, from, n);
 }
 
-#ifdef INLINE_COPY_FROM_USER
+/*
+ * Architectures that #define INLINE_COPY_TO_USER use this function
+ * directly in the normal copy_to/from_user(), the other ones go
+ * through an extern _copy_to/from_user(), which expands the same code
+ * here.
+ *
+ * Rust code always uses the extern definition.
+ */
 static inline __must_check unsigned long
-_copy_from_user(void *to, const void __user *from, unsigned long n)
+_inline_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
 	might_fault();
 	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+		/*
+		 * Ensure that bad access_ok() speculation will not
+		 * lead to nasty side effects *after* the copy is
+		 * finished:
+		 */
+		barrier_nospec();
 		instrument_copy_from_user_before(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 		instrument_copy_from_user_after(to, from, n, res);
@@ -153,14 +167,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
 		memset(to + (n - res), 0, res);
 	return res;
 }
-#else
 extern __must_check unsigned long
 _copy_from_user(void *, const void __user *, unsigned long);
-#endif
 
-#ifdef INLINE_COPY_TO_USER
 static inline __must_check unsigned long
-_copy_to_user(void __user *to, const void *from, unsigned long n)
+_inline_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
 	if (should_fail_usercopy())
@@ -171,25 +182,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n)
 	}
 	return n;
 }
-#else
 extern __must_check unsigned long
 _copy_to_user(void __user *, const void *, unsigned long);
-#endif
 
 static __always_inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (check_copy_size(to, n, false))
-		n = _copy_from_user(to, from, n);
-	return n;
+	if (!check_copy_size(to, n, false))
+		return n;
+#ifdef INLINE_COPY_FROM_USER
+	return _inline_copy_from_user(to, from, n);
+#else
+	return _copy_from_user(to, from, n);
+#endif
 }
 
 static __always_inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (check_copy_size(from, n, true))
-		n = _copy_to_user(to, from, n);
-	return n;
+	if (!check_copy_size(from, n, true))
+		return n;
+
+#ifdef INLINE_COPY_TO_USER
+	return _inline_copy_to_user(to, from, n);
+#else
+	return _copy_to_user(to, from, n);
+#endif
 }
 
 #ifndef copy_mc_to_kernel
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 05d59f7..a12bcf0 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 {
 	vm_flags &= __VM_UFFD_FLAGS;
 
+	if (vm_flags & VM_DROPPABLE)
+		return false;
+
 	if ((vm_flags & VM_UFFD_MINOR) &&
 	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
 		return false;
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 96fea92..ecc5cb7 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -209,10 +209,7 @@ struct virtio_driver {
 	int (*restore)(struct virtio_device *dev);
 };
 
-static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv)
-{
-	return container_of(drv, struct virtio_driver, driver);
-}
+#define drv_to_virtio(__drv)	container_of_const(__drv, struct virtio_driver, driver)
 
 /* use a macro to avoid include chaining to get THIS_MODULE */
 #define register_virtio_driver(drv) \
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 16b0cfa..23cd179 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -17,7 +17,7 @@ extern int sysctl_stat_interval;
 #define DISABLE_NUMA_STAT   0
 extern int sysctl_vm_numa_stat;
 DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
-int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
+int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
@@ -301,7 +301,7 @@ void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
 struct ctl_table;
-int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp,
+int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp,
 		loff_t *ppos);
 
 void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 112d806..1a54676 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -350,7 +350,7 @@ extern unsigned int dirty_expire_interval;
 extern unsigned int dirtytime_expire_interval;
 extern int laptop_mode;
 
-int dirtytime_interval_handler(struct ctl_table *table, int write,
+int dirtytime_interval_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos);
 
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
diff --git a/include/linux/zorro.h b/include/linux/zorro.h
index db7416e..f36c8d3 100644
--- a/include/linux/zorro.h
+++ b/include/linux/zorro.h
@@ -52,7 +52,7 @@ struct zorro_driver {
     struct device_driver driver;
 };
 
-#define	to_zorro_driver(drv)	container_of(drv, struct zorro_driver, driver)
+#define	to_zorro_driver(drv)	container_of_const(drv, struct zorro_driver, driver)
 
 
 #define zorro_for_each_dev(dev)	\
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 9bbdf6e..7a533d5 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -486,7 +486,7 @@ void igmp6_event_report(struct sk_buff *skb);
 
 
 #ifdef CONFIG_SYSCTL
-int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write,
+int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 0d28172..a44f262 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -412,12 +412,12 @@ void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *,
 void *neigh_seq_next(struct seq_file *, void *, loff_t *);
 void neigh_seq_stop(struct seq_file *, void *);
 
-int neigh_proc_dointvec(struct ctl_table *ctl, int write,
+int neigh_proc_dointvec(const struct ctl_table *ctl, int write,
 			void *buffer, size_t *lenp, loff_t *ppos);
-int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
+int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write,
 				void *buffer,
 				size_t *lenp, loff_t *ppos);
-int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
+int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos);
 
 int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
diff --git a/include/net/netfilter/nf_hooks_lwtunnel.h b/include/net/netfilter/nf_hooks_lwtunnel.h
index 52e2792..cef7a4e 100644
--- a/include/net/netfilter/nf_hooks_lwtunnel.h
+++ b/include/net/netfilter/nf_hooks_lwtunnel.h
@@ -2,6 +2,6 @@
 #include <linux/types.h>
 
 #ifdef CONFIG_SYSCTL
-int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write,
+int nf_hooks_lwtunnel_sysctl_handler(const struct ctl_table *table, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos);
 #endif
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index fb3399e..bd12436 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -495,7 +495,7 @@ iscsi_destroy_flashnode_sess(struct iscsi_bus_flash_session *fnode_sess);
 
 extern void iscsi_destroy_all_flashnode(struct Scsi_Host *shost);
 extern int iscsi_flashnode_bus_match(struct device *dev,
-				     struct device_driver *drv);
+				     const struct device_driver *drv);
 extern struct device *
 iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data,
 			  int (*fn)(struct device *dev, void *data));
diff --git a/include/sound/ac97/codec.h b/include/sound/ac97/codec.h
index 2fc641c..882b849b 100644
--- a/include/sound/ac97/codec.h
+++ b/include/sound/ac97/codec.h
@@ -73,10 +73,7 @@ static inline struct ac97_codec_device *to_ac97_device(struct device *d)
 	return container_of(d, struct ac97_codec_device, dev);
 }
 
-static inline struct ac97_codec_driver *to_ac97_driver(struct device_driver *d)
-{
-	return container_of(d, struct ac97_codec_driver, driver);
-}
+#define to_ac97_driver(__drv) container_of_const(__drv, struct ac97_codec_driver, driver)
 
 #if IS_ENABLED(CONFIG_AC97_BUS_NEW)
 int snd_ac97_codec_driver_register(struct ac97_codec_driver *drv);
diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h
index 99c41bf..00fd4d4 100644
--- a/include/sound/tas2781-tlv.h
+++ b/include/sound/tas2781-tlv.h
@@ -16,11 +16,11 @@
 #define __TAS2781_TLV_H__
 
 static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0);
-static const DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0);
-static const DECLARE_TLV_DB_SCALE(tas2563_dvc_tlv, -12150, 50, 1);
+static const __maybe_unused DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0);
+static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2563_dvc_tlv, -12150, 50, 1);
 
 /* pow(10, db/20) * pow(2,30) */
-static const unsigned char tas2563_dvc_table[][4] = {
+static const __maybe_unused unsigned char tas2563_dvc_table[][4] = {
 	{ 0X00, 0X00, 0X00, 0X00 }, /* -121.5db */
 	{ 0X00, 0X00, 0X03, 0XBC }, /* -121.0db */
 	{ 0X00, 0X00, 0X03, 0XF5 }, /* -120.5db */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index e46d6e8..b63d211 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3)
 # define IF_HAVE_UFFD_MINOR(flag, name)
 #endif
 
+#ifdef CONFIG_64BIT
+# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name},
+#else
+# define IF_HAVE_VM_DROPPABLE(flag, name)
+#endif
+
 #define __def_vmaflag_names						\
 	{VM_READ,			"read"		},		\
 	{VM_WRITE,			"write"		},		\
@@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
 	{VM_MIXEDMAP,			"mixedmap"	},		\
 	{VM_HUGEPAGE,			"hugepage"	},		\
 	{VM_NOHUGEPAGE,			"nohugepage"	},		\
+IF_HAVE_VM_DROPPABLE(VM_DROPPABLE,	"droppable"	)		\
 	{VM_MERGEABLE,			"mergeable"	}		\
 
 #define show_vma_flags(flags)						\
diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h
index 79f19e7..47db5ea 100644
--- a/include/trace/events/timer_migration.h
+++ b/include/trace/events/timer_migration.h
@@ -43,7 +43,7 @@ TRACE_EVENT(tmigr_connect_child_parent,
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
 		__field( unsigned int,	num_children	)
-		__field( u32,		childmask	)
+		__field( u32,		groupmask	)
 	),
 
 	TP_fast_assign(
@@ -52,11 +52,11 @@ TRACE_EVENT(tmigr_connect_child_parent,
 		__entry->lvl		= child->parent->level;
 		__entry->numa_node	= child->parent->numa_node;
 		__entry->num_children	= child->parent->num_children;
-		__entry->childmask	= child->childmask;
+		__entry->groupmask	= child->groupmask;
 	),
 
-	TP_printk("group=%p childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->child,  __entry->childmask, __entry->parent,
+	TP_printk("group=%p groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->child,  __entry->groupmask, __entry->parent,
 		  __entry->lvl, __entry->numa_node, __entry->num_children)
 );
 
@@ -72,7 +72,7 @@ TRACE_EVENT(tmigr_connect_cpu_parent,
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
 		__field( unsigned int,	num_children	)
-		__field( u32,		childmask	)
+		__field( u32,		groupmask	)
 	),
 
 	TP_fast_assign(
@@ -81,11 +81,11 @@ TRACE_EVENT(tmigr_connect_cpu_parent,
 		__entry->lvl		= tmc->tmgroup->level;
 		__entry->numa_node	= tmc->tmgroup->numa_node;
 		__entry->num_children	= tmc->tmgroup->num_children;
-		__entry->childmask	= tmc->childmask;
+		__entry->groupmask	= tmc->groupmask;
 	),
 
-	TP_printk("cpu=%d childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->cpu,	 __entry->childmask, __entry->parent,
+	TP_printk("cpu=%d groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->cpu,	 __entry->groupmask, __entry->parent,
 		  __entry->lvl, __entry->numa_node, __entry->num_children)
 );
 
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index d316984..42ec5dd 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;
diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
index a246e11..e89d005 100644
--- a/include/uapi/linux/mman.h
+++ b/include/uapi/linux/mman.h
@@ -17,6 +17,7 @@
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
 #define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#define MAP_DROPPABLE	0x08		/* Zero memory under memory pressure. */
 
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index e744c23..1dd047e 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -20,7 +20,7 @@
 /* Add to (or subtract from) the entropy count.  (Superuser only.) */
 #define RNDADDTOENTCNT	_IOW( 'R', 0x01, int )
 
-/* Get the contents of the entropy pool.  (Superuser only.) */
+/* Get the contents of the entropy pool.  (Superuser only.) (Removed in 2.6.9-rc2.) */
 #define RNDGETPOOL	_IOR( 'R', 0x02, int [2] )
 
 /* 
@@ -55,4 +55,19 @@ struct rand_pool_info {
 #define GRND_RANDOM	0x0002
 #define GRND_INSECURE	0x0004
 
+/**
+ * struct vgetrandom_opaque_params - arguments for allocating memory for vgetrandom
+ *
+ * @size_per_opaque_state:	Size of each state that is to be passed to vgetrandom().
+ * @mmap_prot:			Value of the prot argument in mmap(2).
+ * @mmap_flags:			Value of the flags argument in mmap(2).
+ * @reserved:			Reserved for future use.
+ */
+struct vgetrandom_opaque_params {
+	__u32 size_of_opaque_state;
+	__u32 mmap_prot;
+	__u32 mmap_flags;
+	__u32 reserved[13];
+};
+
 #endif /* _UAPI_LINUX_RANDOM_H */
diff --git a/include/uapi/linux/um_timetravel.h b/include/uapi/linux/um_timetravel.h
index ca32382..546a690 100644
--- a/include/uapi/linux/um_timetravel.h
+++ b/include/uapi/linux/um_timetravel.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
 /*
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- *
- * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2019 - 2023 Intel Corporation
  */
 #ifndef _UAPI_LINUX_UM_TIMETRAVEL_H
 #define _UAPI_LINUX_UM_TIMETRAVEL_H
@@ -50,6 +39,36 @@ struct um_timetravel_msg {
 	__u64 time;
 };
 
+/* max number of file descriptors that can be sent/received in a message */
+#define UM_TIMETRAVEL_MAX_FDS 2
+
+/**
+ * enum um_timetravel_shared_mem_fds - fds sent in ACK message for START message
+ */
+enum um_timetravel_shared_mem_fds {
+	/**
+	 * @UM_TIMETRAVEL_SHARED_MEMFD: Index of the shared memory file
+	 *	descriptor in the control message
+	 */
+	UM_TIMETRAVEL_SHARED_MEMFD,
+	/**
+	 * @UM_TIMETRAVEL_SHARED_LOGFD: Index of the logging file descriptor
+	 *	in the control message
+	 */
+	UM_TIMETRAVEL_SHARED_LOGFD,
+	UM_TIMETRAVEL_SHARED_MAX_FDS,
+};
+
+/**
+ * enum um_timetravel_start_ack - ack-time mask for start message
+ */
+enum um_timetravel_start_ack {
+	/**
+	 * @UM_TIMETRAVEL_START_ACK_ID: client ID that controller allocated.
+	 */
+	UM_TIMETRAVEL_START_ACK_ID = 0xffff,
+};
+
 /**
  * enum um_timetravel_ops - Operation codes
  */
@@ -57,7 +76,9 @@ enum um_timetravel_ops {
 	/**
 	 * @UM_TIMETRAVEL_ACK: response (ACK) to any previous message,
 	 *	this usually doesn't carry any data in the 'time' field
-	 *	unless otherwise specified below
+	 *	unless otherwise specified below, note: while using shared
+	 *	memory no ACK for WAIT and RUN messages, for more info see
+	 *	&struct um_timetravel_schedshm.
 	 */
 	UM_TIMETRAVEL_ACK		= 0,
 
@@ -123,6 +144,147 @@ enum um_timetravel_ops {
 	 *	the simulation.
 	 */
 	UM_TIMETRAVEL_GET_TOD		= 8,
+
+	/**
+	 * @UM_TIMETRAVEL_BROADCAST: Send/Receive a broadcast message.
+	 *	This message can be used to sync all components in the system
+	 *	with a single message, if the calender gets the message, the
+	 *	calender broadcast the message to all components, and if a
+	 *	component receives it it should act based on it e.g print a
+	 *	message to it's log system.
+	 *	(calendar <-> host)
+	 */
+	UM_TIMETRAVEL_BROADCAST		= 9,
 };
 
+/* version of struct um_timetravel_schedshm */
+#define UM_TIMETRAVEL_SCHEDSHM_VERSION 2
+
+/**
+ * enum um_timetravel_schedshm_cap - time travel capabilities of every client
+ *
+ * These flags must be set immediately after processing the ACK to
+ * the START message, before sending any message to the controller.
+ */
+enum um_timetravel_schedshm_cap {
+	/**
+	 * @UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE: client can read current time
+	 *	update internal time request to shared memory and read
+	 *	free until and send no Ack on RUN and doesn't expect ACK on
+	 *	WAIT.
+	 */
+	UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE = 0x1,
+};
+
+/**
+ * enum um_timetravel_schedshm_flags - time travel flags of every client
+ */
+enum um_timetravel_schedshm_flags {
+	/**
+	 * @UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN: client has a request to run.
+	 *	It's set by client when it has a request to run, if (and only
+	 *	if) the @running_id points to a client that is able to use
+	 *	shared memory, i.e. has %UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE
+	 *	(this includes the client itself). Otherwise, a message must
+	 *	be used.
+	 */
+	UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN = 0x1,
+};
+
+/**
+ * DOC: Time travel shared memory overview
+ *
+ * The main purpose of the shared memory is to avoid all time travel message
+ * that don't need any action, for example current time can be held in shared
+ * memory without the need of any client to send a message UM_TIMETRAVEL_GET
+ * in order to know what's the time.
+ *
+ * Since this is shared memory with all clients and controller and controller
+ * creates the shared memory space, all time values are absolute to controller
+ * time. So first time client connects to shared memory mode it should take the
+ * current_time value in shared memory and keep it internally as a diff to
+ * shared memory times, and once shared memory is initialized, any interaction
+ * with the controller must happen in the controller time domain, including any
+ * messages (for clients that are not using shared memory, the controller will
+ * handle an offset and make the clients think they start at time zero.)
+ *
+ * Along with the shared memory file descriptor is sent to the client a logging
+ * file descriptor, to have all logs related to shared memory,
+ * logged into one place. note: to have all logs synced into log file at write,
+ * file should be flushed (fflush) after writing to it.
+ *
+ * To avoid memory corruption, we define below for each field who can write to
+ * it at what time, defined in the structure fields.
+ *
+ * To avoid having to pack this struct, all fields in it must be naturally aligned
+ * (i.e. aligned to their size).
+ */
+
+/**
+ * union um_timetravel_schedshm_client - UM time travel client struct
+ *
+ * Every entity using the shared memory including the controller has a place in
+ * the um_timetravel_schedshm clients array, that holds info related to the client
+ * using the shared memory, and can be set only by the client after it gets the
+ * fd memory.
+ *
+ * @capa: bit fields with client capabilities see
+ *	&enum um_timetravel_schedshm_cap, set by client once after getting the
+ *	shared memory file descriptor.
+ * @flags: bit fields for flags see &enum um_timetravel_schedshm_flags for doc.
+ * @req_time: request time to run, set by client on every request it needs.
+ * @name: unique id sent to the controller by client with START message.
+ */
+union um_timetravel_schedshm_client {
+	struct {
+		__u32 capa;
+		__u32 flags;
+		__u64 req_time;
+		__u64 name;
+	};
+	char reserve[128]; /* reserved for future usage */
+};
+
+/**
+ * struct um_timetravel_schedshm - UM time travel shared memory struct
+ *
+ * @hdr: header fields:
+ * @version: Current version struct UM_TIMETRAVEL_SCHEDSHM_VERSION,
+ *	set by controller once at init, clients must check this after mapping
+ *	and work without shared memory if they cannot handle the indicated
+ *	version.
+ * @len: Length of all the memory including header (@hdr), clients should once
+ *	per connection first mmap the header and take the length (@len) to remap the entire size.
+ *	This is done in order to support dynamic struct size letting number of
+ *	clients be dynamic based on controller support.
+ * @free_until: Stores the next request to run by any client, in order for the
+ *	current client to know how long it can still run. A client needs to (at
+ *	least) reload this value immediately after communicating with any other
+ *	client, since the controller will update this field when a new request
+ *	is made by any client. Clients also must update this value when they
+ *	insert/update an own request into the shared memory while not running
+ *	themselves, and the new request is before than the current value.
+ * current_time: Current time, can only be set by the client in running state
+ *	(indicated by @running_id), though that client may only run until @free_until,
+ *	so it must remain smaller than @free_until.
+ * @running_id: The current client in state running, set before a client is
+ *	notified that it's now running.
+ * @max_clients: size of @clients array, set once at init by the controller.
+ * @clients: clients array see &union um_timetravel_schedshm_client for doc,
+ *	set only by client.
+ */
+struct um_timetravel_schedshm {
+	union {
+		struct {
+			__u32 version;
+			__u32 len;
+			__u64 free_until;
+			__u64 current_time;
+			__u16 running_id;
+			__u16 max_clients;
+		};
+		char hdr[4096]; /* align to 4K page size */
+	};
+	union um_timetravel_schedshm_client clients[];
+};
 #endif /* _UAPI_LINUX_UM_TIMETRAVEL_H */
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 7647e09..b85f24c 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -117,6 +117,16 @@ struct vdso_data {
 	struct arch_vdso_data	arch_data;
 };
 
+/**
+ * struct vdso_rng_data - vdso RNG state information
+ * @generation:	counter representing the number of RNG reseeds
+ * @is_ready:	boolean signaling whether the RNG is initialized
+ */
+struct vdso_rng_data {
+	u64	generation;
+	u8	is_ready;
+};
+
 /*
  * We use the hidden visibility to prevent the compiler from generating a GOT
  * relocation. Not only is going through a GOT useless (the entry couldn't and
@@ -128,6 +138,7 @@ struct vdso_data {
  */
 extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")));
 
 /**
  * union vdso_data_store - Generic vDSO data page
diff --git a/include/vdso/getrandom.h b/include/vdso/getrandom.h
new file mode 100644
index 0000000..a8b7c14
--- /dev/null
+++ b/include/vdso/getrandom.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _VDSO_GETRANDOM_H
+#define _VDSO_GETRANDOM_H
+
+#include <linux/types.h>
+
+#define CHACHA_KEY_SIZE         32
+#define CHACHA_BLOCK_SIZE       64
+
+/**
+ * struct vgetrandom_state - State used by vDSO getrandom().
+ *
+ * @batch:	One and a half ChaCha20 blocks of buffered RNG output.
+ *
+ * @key:	Key to be used for generating next batch.
+ *
+ * @batch_key:	Union of the prior two members, which is exactly two full
+ * 		ChaCha20 blocks in size, so that @batch and @key can be filled
+ * 		together.
+ *
+ * @generation:	Snapshot of @rng_info->generation in the vDSO data page at
+ *		the time @key was generated.
+ *
+ * @pos:	Offset into @batch of the next available random byte.
+ *
+ * @in_use:	Reentrancy guard for reusing a state within the same thread
+ *		due to signal handlers.
+ */
+struct vgetrandom_state {
+	union {
+		struct {
+			u8	batch[CHACHA_BLOCK_SIZE * 3 / 2];
+			u32	key[CHACHA_KEY_SIZE / sizeof(u32)];
+		};
+		u8		batch_key[CHACHA_BLOCK_SIZE * 2];
+	};
+	u64			generation;
+	u8			pos;
+	bool 			in_use;
+};
+
+#endif /* _VDSO_GETRANDOM_H */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index ac22cf0..3f90bdd 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -124,10 +124,7 @@ struct xenbus_driver {
 	void (*reclaim_memory)(struct xenbus_device *dev);
 };
 
-static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct xenbus_driver, driver);
-}
+#define to_xenbus_driver(__drv)	container_of_const(__drv, struct xenbus_driver, driver)
 
 int __must_check __xenbus_register_frontend(struct xenbus_driver *drv,
 					    struct module *owner,
diff --git a/init/Kconfig b/init/Kconfig
index c41260f..a465ea9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1924,7 +1924,10 @@
 config BINDGEN_VERSION_TEXT
 	string
 	depends on RUST
-	default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n)
+	# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0
+	# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when
+	# the minimum version is upgraded past that (0.69.1 already fixed the issue).
+	default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version workaround-for-0.69.0 || echo n)
 
 #
 # Place an empty function call at each tracepoint site. Can be
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8e6faa9..3942db16 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1849,7 +1849,7 @@ void io_wq_submit_work(struct io_wq_work *work)
 	} while (1);
 
 	/* avoid locking problems by failing it from a clean context */
-	if (ret < 0)
+	if (ret)
 		io_req_task_queue_fail(req, ret);
 }
 
@@ -2416,12 +2416,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 	if (uts) {
 		struct timespec64 ts;
+		ktime_t dt;
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
 
-		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
-		io_napi_adjust_timeout(ctx, &iowq, &ts);
+		dt = timespec64_to_ktime(ts);
+		iowq.timeout = ktime_add(dt, ktime_get());
+		io_napi_adjust_timeout(ctx, &iowq, dt);
 	}
 
 	if (sig) {
@@ -3031,8 +3033,11 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 		bool loop = false;
 
 		io_uring_drop_tctx_refs(current);
+		if (!tctx_inflight(tctx, !cancel_all))
+			break;
+
 		/* read completions before cancelations */
-		inflight = tctx_inflight(tctx, !cancel_all);
+		inflight = tctx_inflight(tctx, false);
 		if (!inflight)
 			break;
 
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index e1ce908..c2acf61 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -43,7 +43,7 @@ struct io_wait_queue {
 	ktime_t timeout;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int napi_busy_poll_to;
+	ktime_t napi_busy_poll_dt;
 	bool napi_prefer_busy_poll;
 #endif
 };
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 29fa928..7fd9bad 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -110,10 +110,10 @@ static struct io_kiocb *io_msg_get_kiocb(struct io_ring_ctx *ctx)
 	if (spin_trylock(&ctx->msg_lock)) {
 		req = io_alloc_cache_get(&ctx->msg_cache);
 		spin_unlock(&ctx->msg_lock);
+		if (req)
+			return req;
 	}
-	if (req)
-		return req;
-	return kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN);
+	return kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
 }
 
 static int io_msg_data_remote(struct io_kiocb *req)
diff --git a/io_uring/napi.c b/io_uring/napi.c
index 762254a7..4fd6bb3 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -33,6 +33,12 @@ static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
 	return NULL;
 }
 
+static inline ktime_t net_to_ktime(unsigned long t)
+{
+	/* napi approximating usecs, reverse busy_loop_current_time */
+	return ns_to_ktime(t << 10);
+}
+
 void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
 {
 	struct hlist_head *hash_list;
@@ -102,14 +108,14 @@ static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
 		__io_napi_remove_stale(ctx);
 }
 
-static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
-					     unsigned long bp_usec)
+static inline bool io_napi_busy_loop_timeout(ktime_t start_time,
+					     ktime_t bp)
 {
-	if (bp_usec) {
-		unsigned long end_time = start_time + bp_usec;
-		unsigned long now = busy_loop_current_time();
+	if (bp) {
+		ktime_t end_time = ktime_add(start_time, bp);
+		ktime_t now = net_to_ktime(busy_loop_current_time());
 
-		return time_after(now, end_time);
+		return ktime_after(now, end_time);
 	}
 
 	return true;
@@ -124,7 +130,8 @@ static bool io_napi_busy_loop_should_end(void *data,
 		return true;
 	if (io_should_wake(iowq) || io_has_work(iowq->ctx))
 		return true;
-	if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to))
+	if (io_napi_busy_loop_timeout(net_to_ktime(start_time),
+				      iowq->napi_busy_poll_dt))
 		return true;
 
 	return false;
@@ -181,10 +188,12 @@ static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
  */
 void io_napi_init(struct io_ring_ctx *ctx)
 {
+	u64 sys_dt = READ_ONCE(sysctl_net_busy_poll) * NSEC_PER_USEC;
+
 	INIT_LIST_HEAD(&ctx->napi_list);
 	spin_lock_init(&ctx->napi_lock);
 	ctx->napi_prefer_busy_poll = false;
-	ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
+	ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt);
 }
 
 /*
@@ -217,11 +226,13 @@ void io_napi_free(struct io_ring_ctx *ctx)
 int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 {
 	const struct io_uring_napi curr = {
-		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.busy_poll_to 	  = ktime_to_us(ctx->napi_busy_poll_dt),
 		.prefer_busy_poll = ctx->napi_prefer_busy_poll
 	};
 	struct io_uring_napi napi;
 
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		return -EINVAL;
 	if (copy_from_user(&napi, arg, sizeof(napi)))
 		return -EFAULT;
 	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
@@ -230,7 +241,7 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 	if (copy_to_user(arg, &curr, sizeof(curr)))
 		return -EFAULT;
 
-	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_busy_poll_dt, napi.busy_poll_to * NSEC_PER_USEC);
 	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
 	WRITE_ONCE(ctx->napi_enabled, true);
 	return 0;
@@ -247,14 +258,14 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 {
 	const struct io_uring_napi curr = {
-		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.busy_poll_to 	  = ktime_to_us(ctx->napi_busy_poll_dt),
 		.prefer_busy_poll = ctx->napi_prefer_busy_poll
 	};
 
 	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
 		return -EFAULT;
 
-	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_busy_poll_dt, 0);
 	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
 	WRITE_ONCE(ctx->napi_enabled, false);
 	return 0;
@@ -271,25 +282,14 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
  * the NAPI timeout accordingly.
  */
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
-			      struct timespec64 *ts)
+			      ktime_t to_wait)
 {
-	unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
+	ktime_t poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);
 
-	if (ts) {
-		struct timespec64 poll_to_ts;
+	if (to_wait)
+		poll_dt = min(poll_dt, to_wait);
 
-		poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
-		if (timespec64_compare(ts, &poll_to_ts) < 0) {
-			s64 poll_to_ns = timespec64_to_ns(ts);
-			if (poll_to_ns > 0) {
-				u64 val = poll_to_ns + 999;
-				do_div(val, 1000);
-				poll_to = val;
-			}
-		}
-	}
-
-	iowq->napi_busy_poll_to = poll_to;
+	iowq->napi_busy_poll_dt = poll_dt;
 }
 
 /*
@@ -318,7 +318,7 @@ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
 	LIST_HEAD(napi_list);
 	bool is_stale = false;
 
-	if (!READ_ONCE(ctx->napi_busy_poll_to))
+	if (!READ_ONCE(ctx->napi_busy_poll_dt))
 		return 0;
 	if (list_empty_careful(&ctx->napi_list))
 		return 0;
diff --git a/io_uring/napi.h b/io_uring/napi.h
index 6fc0393..88f1c21 100644
--- a/io_uring/napi.h
+++ b/io_uring/napi.h
@@ -18,7 +18,7 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
 void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
 
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
-		struct io_wait_queue *iowq, struct timespec64 *ts);
+		struct io_wait_queue *iowq, ktime_t to_wait);
 void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq);
 int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx);
 
@@ -29,11 +29,11 @@ static inline bool io_napi(struct io_ring_ctx *ctx)
 
 static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
-					  struct timespec64 *ts)
+					  ktime_t to_wait)
 {
 	if (!io_napi(ctx))
 		return;
-	__io_napi_adjust_timeout(ctx, iowq, ts);
+	__io_napi_adjust_timeout(ctx, iowq, to_wait);
 }
 
 static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
@@ -55,7 +55,7 @@ static inline void io_napi_add(struct io_kiocb *req)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct socket *sock;
 
-	if (!READ_ONCE(ctx->napi_busy_poll_to))
+	if (!READ_ONCE(ctx->napi_busy_poll_dt))
 		return;
 
 	sock = sock_from_file(req->file);
@@ -88,7 +88,7 @@ static inline void io_napi_add(struct io_kiocb *req)
 }
 static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
-					  struct timespec64 *ts)
+					  ktime_t to_wait)
 {
 }
 static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 1c9bf07..9973876 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -639,7 +639,7 @@ void io_queue_linked_timeout(struct io_kiocb *req)
 
 static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
 			  bool cancel_all)
-	__must_hold(&req->ctx->timeout_lock)
+	__must_hold(&head->ctx->timeout_lock)
 {
 	struct io_kiocb *req;
 
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index a54163a..8391c7c 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -265,7 +265,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 		req_set_fail(req);
 	io_req_uring_cleanup(req, issue_flags);
 	io_req_set_res(req, ret, 0);
-	return ret < 0 ? ret : IOU_OK;
+	return IOU_OK;
 }
 
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 9465b0a..54318e0 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -17,7 +17,7 @@
 #include <linux/cred.h>
 #include "util.h"
 
-static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
+static int proc_ipc_dointvec_minmax_orphans(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ipc_namespace *ns =
@@ -33,7 +33,7 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
+static int proc_ipc_auto_msgmni(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
@@ -48,7 +48,7 @@ static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 
-static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
+static int proc_ipc_sem_dointvec(const struct ctl_table *table, int write,
 	void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ipc_namespace *ns =
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0719192..bf6c5f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5983,7 +5983,7 @@ const struct bpf_prog_ops bpf_syscall_prog_ops = {
 };
 
 #ifdef CONFIG_SYSCTL
-static int bpf_stats_handler(struct ctl_table *table, int write,
+static int bpf_stats_handler(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct static_key *key = (struct static_key *)table->data;
@@ -6018,7 +6018,7 @@ void __weak unpriv_ebpf_notify(int new_state)
 {
 }
 
-static int bpf_unpriv_handler(struct ctl_table *table, int write,
+static int bpf_unpriv_handler(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, unpriv_enable = *(int *)table->data;
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 10b4545..137ba73 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -144,7 +144,7 @@ kdb_bt(int argc, const char **argv)
 			kdb_ps_suppressed();
 		/* Run the active tasks first */
 		for_each_online_cpu(cpu) {
-			p = kdb_curr_task(cpu);
+			p = curr_task(cpu);
 			if (kdb_bt1(p, mask, btaprompt))
 				return 0;
 		}
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 3131334..6a77f1c 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -206,7 +206,7 @@ char kdb_getchar(void)
  */
 static void kdb_position_cursor(char *prompt, char *buffer, char *cp)
 {
-	kdb_printf("\r%s", kdb_prompt_str);
+	kdb_printf("\r%s", prompt);
 	if (cp > buffer)
 		kdb_printf("%.*s", (int)(cp - buffer), buffer);
 }
@@ -362,7 +362,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
 			if (i >= dtab_count)
 				kdb_printf("...");
 			kdb_printf("\n");
-			kdb_printf(kdb_prompt_str);
+			kdb_printf("%s",  kdb_prompt_str);
 			kdb_printf("%s", buffer);
 			if (cp != lastchar)
 				kdb_position_cursor(kdb_prompt_str, buffer, cp);
@@ -453,7 +453,7 @@ char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt)
 {
 	if (prompt && kdb_prompt_str != prompt)
 		strscpy(kdb_prompt_str, prompt, CMD_BUFLEN);
-	kdb_printf(kdb_prompt_str);
+	kdb_printf("%s", kdb_prompt_str);
 	kdb_nextline = 1;	/* Prompt and input resets line number */
 	return kdb_read(buffer, bufsize);
 }
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 664bae5..f5f7d7f 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -155,16 +155,6 @@ static char *__env[31] = {
 
 static const int __nenv = ARRAY_SIZE(__env);
 
-struct task_struct *kdb_curr_task(int cpu)
-{
-	struct task_struct *p = curr_task(cpu);
-#ifdef	_TIF_MCA_INIT
-	if ((task_thread_info(p)->flags & _TIF_MCA_INIT) && KDB_TSK(cpu))
-		p = krp->p;
-#endif
-	return p;
-}
-
 /*
  * Update the permissions flags (kdb_cmd_enabled) to match the
  * current lockdown state.
@@ -1228,7 +1218,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 	char *cmdbuf;
 	int diag;
 	struct task_struct *kdb_current =
-		kdb_curr_task(raw_smp_processor_id());
+		curr_task(raw_smp_processor_id());
 
 	KDB_DEBUG_STATE("kdb_local 1", reason);
 
@@ -2278,7 +2268,7 @@ void kdb_ps_suppressed(void)
 	unsigned long cpu;
 	const struct task_struct *p, *g;
 	for_each_online_cpu(cpu) {
-		p = kdb_curr_task(cpu);
+		p = curr_task(cpu);
 		if (kdb_task_state(p, "-"))
 			++idle;
 	}
@@ -2314,7 +2304,7 @@ void kdb_ps1(const struct task_struct *p)
 		   kdb_task_has_cpu(p), kdb_process_cpu(p),
 		   kdb_task_state_char(p),
 		   (void *)(&p->thread),
-		   p == kdb_curr_task(raw_smp_processor_id()) ? '*' : ' ',
+		   p == curr_task(raw_smp_processor_id()) ? '*' : ' ',
 		   p->comm);
 	if (kdb_task_has_cpu(p)) {
 		if (!KDB_TSK(cpu)) {
@@ -2350,7 +2340,7 @@ static int kdb_ps(int argc, const char **argv)
 	for_each_online_cpu(cpu) {
 		if (KDB_FLAG(CMD_INTERRUPT))
 			return 0;
-		p = kdb_curr_task(cpu);
+		p = curr_task(cpu);
 		if (kdb_task_state(p, mask))
 			kdb_ps1(p);
 	}
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 548fd40..d2520d72 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -210,8 +210,6 @@ extern void kdb_gdb_state_pass(char *buf);
 #define KDB_TSK(cpu) kgdb_info[cpu].task
 #define KDB_TSKREGS(cpu) kgdb_info[cpu].debuggerinfo
 
-extern struct task_struct *kdb_curr_task(int);
-
 #define kdb_task_has_cpu(p) (task_curr(p))
 
 #define GFP_KDB (in_dbg_master() ? GFP_ATOMIC : GFP_KERNEL)
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e039b0f..dead51d 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,7 +44,7 @@ void delayacct_init(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-static int sysctl_delayacct(struct ctl_table *table, int write, void *buffer,
+static int sysctl_delayacct(const struct ctl_table *table, int write, void *buffer,
 		     size_t *lenp, loff_t *ppos)
 {
 	int state = delayacct_on;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 81de843..b1c1805 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -67,8 +67,8 @@ void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 {
 	struct dma_devres match_data = { size, vaddr, dma_handle };
 
-	dma_free_coherent(dev, size, vaddr, dma_handle);
 	WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
+	dma_free_coherent(dev, size, vaddr, dma_handle);
 }
 EXPORT_SYMBOL(dmam_free_coherent);
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 8d57255..8a47e52 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -270,7 +270,7 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
  * Used for sysctl_perf_event_max_stack and
  * sysctl_perf_event_max_contexts_per_stack.
  */
-int perf_event_max_stack_handler(struct ctl_table *table, int write,
+int perf_event_max_stack_handler(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *value = table->data;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index af2e3a06..aa3450b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -450,7 +450,7 @@ static void update_perf_cpu_limits(void)
 
 static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);
 
-int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
+int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -474,7 +474,7 @@ int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
 
 int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
 
-int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -9328,21 +9328,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
 	int i;
 
-	if (prog->aux->func_cnt == 0) {
-		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
-				   (u64)(unsigned long)prog->bpf_func,
-				   prog->jited_len, unregister,
-				   prog->aux->ksym.name);
-	} else {
-		for (i = 0; i < prog->aux->func_cnt; i++) {
-			struct bpf_prog *subprog = prog->aux->func[i];
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+			   (u64)(unsigned long)prog->bpf_func,
+			   prog->jited_len, unregister,
+			   prog->aux->ksym.name);
 
-			perf_event_ksymbol(
-				PERF_RECORD_KSYMBOL_TYPE_BPF,
-				(u64)(unsigned long)subprog->bpf_func,
-				subprog->jited_len, unregister,
-				subprog->aux->ksym.name);
-		}
+	for (i = 1; i < prog->aux->func_cnt; i++) {
+		struct bpf_prog *subprog = prog->aux->func[i];
+
+		perf_event_ksymbol(
+			PERF_RECORD_KSYMBOL_TYPE_BPF,
+			(u64)(unsigned long)subprog->bpf_func,
+			subprog->jited_len, unregister,
+			subprog->aux->ksym.name);
 	}
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a8362c2..cc76049 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3404,7 +3404,7 @@ int unshare_files(void)
 	return 0;
 }
 
-int sysctl_max_threads(struct ctl_table *table, int write,
+int sysctl_max_threads(const struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 6ca8597..959d995 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -239,7 +239,7 @@ static long hung_timeout_jiffies(unsigned long last_checked,
 /*
  * Process updating of timeout sysctl
  */
-static int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int write,
 				  void *buffer,
 				  size_t *lenp, loff_t *ppos)
 {
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 9112d69..c0caa14 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -888,7 +888,7 @@ struct kimage *kexec_crash_image;
 static int kexec_load_disabled;
 
 #ifdef CONFIG_SYSCTL
-static int kexec_limit_handler(struct ctl_table *table, int write,
+static int kexec_limit_handler(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct kexec_load_limit *limit = table->data;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 6a76a81..e85de37 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -939,7 +939,7 @@ static void unoptimize_all_kprobes(void)
 
 static DEFINE_MUTEX(kprobe_sysctl_mutex);
 static int sysctl_kprobes_optimization;
-static int proc_kprobes_optimization_handler(struct ctl_table *table,
+static int proc_kprobes_optimization_handler(const struct ctl_table *table,
 					     int write, void *buffer,
 					     size_t *length, loff_t *ppos)
 {
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 84c53285..7a75eab 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -65,7 +65,7 @@ static struct latency_record latency_record[MAXLR];
 int latencytop_enabled;
 
 #ifdef CONFIG_SYSCTL
-static int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
+static int sysctl_latencytop(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int err;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index bdf0087..d70ab49 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -261,7 +261,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
-static int pid_ns_ctl_handler(struct ctl_table *table, int write,
+static int pid_ns_ctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(current);
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
index fe9fb99..18ecaef 100644
--- a/kernel/pid_sysctl.h
+++ b/kernel/pid_sysctl.h
@@ -5,7 +5,7 @@
 #include <linux/pid_namespace.h>
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
-static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table,
+static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table,
 	int write, void *buf, size_t *lenp, loff_t *ppos)
 {
 	struct pid_namespace *ns = task_active_pid_ns(current);
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 6c2afee..19dcc58 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -8,7 +8,7 @@
 
 #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
 void __init printk_sysctl_init(void);
-int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos);
 #else
 #define printk_sysctl_init() do { } while (0)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 7d91593..054c0e7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -197,7 +197,7 @@ __setup("printk.devkmsg=", control_devkmsg);
 
 char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
 #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
-int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char old_str[DEVKMSG_STR_MAX_SIZE];
@@ -4372,15 +4372,15 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
 EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
 
 /**
- * console_replay_all - replay kernel log on consoles
+ * console_try_replay_all - try to replay kernel log on consoles
  *
  * Try to obtain lock on console subsystem and replay all
  * available records in printk buffer on the consoles.
  * Does nothing if lock is not obtained.
  *
- * Context: Any context.
+ * Context: Any, except for NMI.
  */
-void console_replay_all(void)
+void console_try_replay_all(void)
 {
 	if (console_trylock()) {
 		__console_rewind_all();
diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c
index 3e47ded..f5072dc 100644
--- a/kernel/printk/sysctl.c
+++ b/kernel/printk/sysctl.c
@@ -11,7 +11,7 @@
 
 static const int ten_thousand = 10000;
 
-static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
+static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (write && !capable(CAP_SYS_ADMIN))
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ae5ef30..a9f6550 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1806,7 +1806,7 @@ static void uclamp_sync_util_min_rt_default(void)
 		uclamp_update_util_min_rt_default(p);
 }
 
-static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+static int sysctl_sched_uclamp_handler(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
@@ -4392,7 +4392,7 @@ static void reset_memory_tiering(void)
 	}
 }
 
-static int sysctl_numa_balancing(struct ctl_table *table, int write,
+static int sysctl_numa_balancing(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -4461,7 +4461,7 @@ static int __init setup_schedstats(char *str)
 __setup("schedstats=", setup_schedstats);
 
 #ifdef CONFIG_PROC_SYSCTL
-static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+static int sysctl_schedstats(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 63e49c8..310523c 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -26,9 +26,9 @@ int sysctl_sched_rt_runtime = 950000;
 
 #ifdef CONFIG_SYSCTL
 static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ;
-static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
 static struct ctl_table sched_rt_sysctls[] = {
 	{
@@ -2952,7 +2952,7 @@ static void sched_rt_do_global(void)
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
-static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
@@ -2991,7 +2991,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
-static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 784a0be..76504b7 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -285,7 +285,7 @@ void rebuild_sched_domains_energy(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-static int sched_energy_aware_handler(struct ctl_table *table, int write,
+static int sched_energy_aware_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index dc51e52..385d482 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -2431,7 +2431,7 @@ static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged,
 	return audit_seccomp_actions_logged(new, old, !ret);
 }
 
-static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
+static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int write,
 					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index 0f97125..39fd620 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -21,7 +21,7 @@
 static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
 
 #ifdef CONFIG_SYSCTL
-static int stack_erasing_sysctl(struct ctl_table *table, int write,
+static int stack_erasing_sysctl(const struct ctl_table *table, int write,
 			void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e442159..79e6cb1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -256,7 +256,7 @@ static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
  *
  * Returns 0 on success.
  */
-int proc_dostring(struct ctl_table *table, int write,
+int proc_dostring(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (write)
@@ -702,7 +702,7 @@ int do_proc_douintvec(const struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_dobool(struct ctl_table *table, int write, void *buffer,
+int proc_dobool(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table tmp;
@@ -739,7 +739,7 @@ int proc_dobool(struct ctl_table *table, int write, void *buffer,
  *
  * Returns 0 on success.
  */
-int proc_dointvec(struct ctl_table *table, int write, void *buffer,
+int proc_dointvec(const struct ctl_table *table, int write, void *buffer,
 		  size_t *lenp, loff_t *ppos)
 {
 	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
@@ -758,7 +758,7 @@ int proc_dointvec(struct ctl_table *table, int write, void *buffer,
  *
  * Returns 0 on success.
  */
-int proc_douintvec(struct ctl_table *table, int write, void *buffer,
+int proc_douintvec(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	return do_proc_douintvec(table, write, buffer, lenp, ppos,
@@ -769,7 +769,7 @@ int proc_douintvec(struct ctl_table *table, int write, void *buffer,
  * Taint values can only be increased
  * This means we can safely use a temporary.
  */
-static int proc_taint(struct ctl_table *table, int write,
+static int proc_taint(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -864,7 +864,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
  *
  * Returns 0 on success or -EINVAL on write when the range check fails.
  */
-int proc_dointvec_minmax(struct ctl_table *table, int write,
+int proc_dointvec_minmax(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct do_proc_dointvec_minmax_conv_param param = {
@@ -933,7 +933,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
  *
  * Returns 0 on success or -ERANGE on write when the range check fails.
  */
-int proc_douintvec_minmax(struct ctl_table *table, int write,
+int proc_douintvec_minmax(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct do_proc_douintvec_minmax_conv_param param = {
@@ -961,7 +961,7 @@ int proc_douintvec_minmax(struct ctl_table *table, int write,
  *
  * Returns 0 on success or an error on write when the range check fails.
  */
-int proc_dou8vec_minmax(struct ctl_table *table, int write,
+int proc_dou8vec_minmax(const struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table tmp;
@@ -998,7 +998,7 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write,
 EXPORT_SYMBOL_GPL(proc_dou8vec_minmax);
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static int sysrq_sysctl_handler(struct ctl_table *table, int write,
+static int sysrq_sysctl_handler(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int tmp, ret;
@@ -1115,7 +1115,7 @@ static int do_proc_doulongvec_minmax(const struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_doulongvec_minmax(struct ctl_table *table, int write,
+int proc_doulongvec_minmax(const struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
     return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
@@ -1138,7 +1138,7 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int write,
 				      void *buffer, size_t *lenp, loff_t *ppos)
 {
     return do_proc_doulongvec_minmax(table, write, buffer,
@@ -1259,14 +1259,14 @@ static int do_proc_dointvec_ms_jiffies_minmax_conv(bool *negp, unsigned long *lv
  *
  * Returns 0 on success.
  */
-int proc_dointvec_jiffies(struct ctl_table *table, int write,
+int proc_dointvec_jiffies(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
     return do_proc_dointvec(table,write,buffer,lenp,ppos,
 		    	    do_proc_dointvec_jiffies_conv,NULL);
 }
 
-int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct do_proc_dointvec_minmax_conv_param param = {
@@ -1292,7 +1292,7 @@ int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
+int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return do_proc_dointvec(table, write, buffer, lenp, ppos,
@@ -1315,14 +1315,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void *buffer,
+int proc_dointvec_ms_jiffies(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	return do_proc_dointvec(table, write, buffer, lenp, ppos,
 				do_proc_dointvec_ms_jiffies_conv, NULL);
 }
 
-static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer,
+static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct pid *new_pid;
@@ -1361,7 +1361,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer,
  *
  * Returns 0 on success.
  */
-int proc_do_large_bitmap(struct ctl_table *table, int write,
+int proc_do_large_bitmap(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err = 0;
@@ -1493,85 +1493,85 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 
 #else /* CONFIG_PROC_SYSCTL */
 
-int proc_dostring(struct ctl_table *table, int write,
+int proc_dostring(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dobool(struct ctl_table *table, int write,
+int proc_dobool(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec(struct ctl_table *table, int write,
+int proc_dointvec(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_douintvec(struct ctl_table *table, int write,
+int proc_douintvec(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_minmax(struct ctl_table *table, int write,
+int proc_dointvec_minmax(const struct ctl_table *table, int write,
 		    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_douintvec_minmax(struct ctl_table *table, int write,
+int proc_douintvec_minmax(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dou8vec_minmax(struct ctl_table *table, int write,
+int proc_dou8vec_minmax(const struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_jiffies(struct ctl_table *table, int write,
+int proc_dointvec_jiffies(const struct ctl_table *table, int write,
 		    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
+int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int write,
 		    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
+int proc_dointvec_ms_jiffies(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_doulongvec_minmax(struct ctl_table *table, int write,
+int proc_doulongvec_minmax(const struct ctl_table *table, int write,
 		    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int write,
 				      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
 }
 
-int proc_do_large_bitmap(struct ctl_table *table, int write,
+int proc_do_large_bitmap(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
@@ -1580,7 +1580,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 #endif /* CONFIG_PROC_SYSCTL */
 
 #if defined(CONFIG_SYSCTL)
-int proc_do_static_key(struct ctl_table *table, int write,
+int proc_do_static_key(const struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct static_key *key = (struct static_key *)table->data;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 48288dd..64b0d8a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -289,7 +289,7 @@ static void timers_update_migration(void)
 }
 
 #ifdef CONFIG_SYSCTL
-static int timer_migration_handler(struct ctl_table *table, int write,
+static int timer_migration_handler(const struct ctl_table *table, int write,
 			    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 8441311..8d57f76 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -475,9 +475,54 @@ static bool tmigr_check_lonely(struct tmigr_group *group)
 	return bitmap_weight(&active, BIT_CNT) <= 1;
 }
 
-typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *);
+/**
+ * struct tmigr_walk - data required for walking the hierarchy
+ * @nextexp:		Next CPU event expiry information which is handed into
+ *			the timer migration code by the timer code
+ *			(get_next_timer_interrupt())
+ * @firstexp:		Contains the first event expiry information when
+ *			hierarchy is completely idle.  When CPU itself was the
+ *			last going idle, information makes sure, that CPU will
+ *			be back in time. When using this value in the remote
+ *			expiry case, firstexp is stored in the per CPU tmigr_cpu
+ *			struct of CPU which expires remote timers. It is updated
+ *			in top level group only. Be aware, there could occur a
+ *			new top level of the hierarchy between the 'top level
+ *			call' in tmigr_update_events() and the check for the
+ *			parent group in walk_groups(). Then @firstexp might
+ *			contain a value != KTIME_MAX even if it was not the
+ *			final top level. This is not a problem, as the worst
+ *			outcome is a CPU which might wake up a little early.
+ * @evt:		Pointer to tmigr_event which needs to be queued (of idle
+ *			child group)
+ * @childmask:		groupmask of child group
+ * @remote:		Is set, when the new timer path is executed in
+ *			tmigr_handle_remote_cpu()
+ * @basej:		timer base in jiffies
+ * @now:		timer base monotonic
+ * @check:		is set if there is the need to handle remote timers;
+ *			required in tmigr_requires_handle_remote() only
+ * @tmc_active:		this flag indicates, whether the CPU which triggers
+ *			the hierarchy walk is !idle in the timer migration
+ *			hierarchy. When the CPU is idle and the whole hierarchy is
+ *			idle, only the first event of the top level has to be
+ *			considered.
+ */
+struct tmigr_walk {
+	u64			nextexp;
+	u64			firstexp;
+	struct tmigr_event	*evt;
+	u8			childmask;
+	bool			remote;
+	unsigned long		basej;
+	u64			now;
+	bool			check;
+	bool			tmc_active;
+};
 
-static void __walk_groups(up_f up, void *data,
+typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, struct tmigr_walk *);
+
+static void __walk_groups(up_f up, struct tmigr_walk *data,
 			  struct tmigr_cpu *tmc)
 {
 	struct tmigr_group *child = NULL, *group = tmc->tmgroup;
@@ -490,64 +535,17 @@ static void __walk_groups(up_f up, void *data,
 
 		child = group;
 		group = group->parent;
+		data->childmask = child->groupmask;
 	} while (group);
 }
 
-static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc)
+static void walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc)
 {
 	lockdep_assert_held(&tmc->lock);
 
 	__walk_groups(up, data, tmc);
 }
 
-/**
- * struct tmigr_walk - data required for walking the hierarchy
- * @nextexp:		Next CPU event expiry information which is handed into
- *			the timer migration code by the timer code
- *			(get_next_timer_interrupt())
- * @firstexp:		Contains the first event expiry information when last
- *			active CPU of hierarchy is on the way to idle to make
- *			sure CPU will be back in time.
- * @evt:		Pointer to tmigr_event which needs to be queued (of idle
- *			child group)
- * @childmask:		childmask of child group
- * @remote:		Is set, when the new timer path is executed in
- *			tmigr_handle_remote_cpu()
- */
-struct tmigr_walk {
-	u64			nextexp;
-	u64			firstexp;
-	struct tmigr_event	*evt;
-	u8			childmask;
-	bool			remote;
-};
-
-/**
- * struct tmigr_remote_data - data required for remote expiry hierarchy walk
- * @basej:		timer base in jiffies
- * @now:		timer base monotonic
- * @firstexp:		returns expiry of the first timer in the idle timer
- *			migration hierarchy to make sure the timer is handled in
- *			time; it is stored in the per CPU tmigr_cpu struct of
- *			CPU which expires remote timers
- * @childmask:		childmask of child group
- * @check:		is set if there is the need to handle remote timers;
- *			required in tmigr_requires_handle_remote() only
- * @tmc_active:		this flag indicates, whether the CPU which triggers
- *			the hierarchy walk is !idle in the timer migration
- *			hierarchy. When the CPU is idle and the whole hierarchy is
- *			idle, only the first event of the top level has to be
- *			considered.
- */
-struct tmigr_remote_data {
-	unsigned long	basej;
-	u64		now;
-	u64		firstexp;
-	u8		childmask;
-	bool		check;
-	bool		tmc_active;
-};
-
 /*
  * Returns the next event of the timerqueue @group->events
  *
@@ -618,10 +616,9 @@ static u64 tmigr_next_groupevt_expires(struct tmigr_group *group)
 
 static bool tmigr_active_up(struct tmigr_group *group,
 			    struct tmigr_group *child,
-			    void *ptr)
+			    struct tmigr_walk *data)
 {
 	union tmigr_state curstate, newstate;
-	struct tmigr_walk *data = ptr;
 	bool walk_done;
 	u8 childmask;
 
@@ -649,8 +646,7 @@ static bool tmigr_active_up(struct tmigr_group *group,
 
 	} while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state));
 
-	if ((walk_done == false) && group->parent)
-		data->childmask = group->childmask;
+	trace_tmigr_group_set_cpu_active(group, newstate, childmask);
 
 	/*
 	 * The group is active (again). The group event might be still queued
@@ -666,8 +662,6 @@ static bool tmigr_active_up(struct tmigr_group *group,
 	 */
 	group->groupevt.ignore = true;
 
-	trace_tmigr_group_set_cpu_active(group, newstate, childmask);
-
 	return walk_done;
 }
 
@@ -675,7 +669,7 @@ static void __tmigr_cpu_activate(struct tmigr_cpu *tmc)
 {
 	struct tmigr_walk data;
 
-	data.childmask = tmc->childmask;
+	data.childmask = tmc->groupmask;
 
 	trace_tmigr_cpu_active(tmc);
 
@@ -860,10 +854,8 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 
 static bool tmigr_new_timer_up(struct tmigr_group *group,
 			       struct tmigr_group *child,
-			       void *ptr)
+			       struct tmigr_walk *data)
 {
-	struct tmigr_walk *data = ptr;
-
 	return tmigr_update_events(group, child, data);
 }
 
@@ -995,9 +987,8 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now,
 
 static bool tmigr_handle_remote_up(struct tmigr_group *group,
 				   struct tmigr_group *child,
-				   void *ptr)
+				   struct tmigr_walk *data)
 {
-	struct tmigr_remote_data *data = ptr;
 	struct tmigr_event *evt;
 	unsigned long jif;
 	u8 childmask;
@@ -1034,12 +1025,10 @@ static bool tmigr_handle_remote_up(struct tmigr_group *group,
 	}
 
 	/*
-	 * Update of childmask for the next level and keep track of the expiry
-	 * of the first event that needs to be handled (group->next_expiry was
-	 * updated by tmigr_next_expired_groupevt(), next was set by
-	 * tmigr_handle_remote_cpu()).
+	 * Keep track of the expiry of the first event that needs to be handled
+	 * (group->next_expiry was updated by tmigr_next_expired_groupevt(),
+	 * next was set by tmigr_handle_remote_cpu()).
 	 */
-	data->childmask = group->childmask;
 	data->firstexp = group->next_expiry;
 
 	raw_spin_unlock_irq(&group->lock);
@@ -1055,12 +1044,12 @@ static bool tmigr_handle_remote_up(struct tmigr_group *group,
 void tmigr_handle_remote(void)
 {
 	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
-	struct tmigr_remote_data data;
+	struct tmigr_walk data;
 
 	if (tmigr_is_not_available(tmc))
 		return;
 
-	data.childmask = tmc->childmask;
+	data.childmask = tmc->groupmask;
 	data.firstexp = KTIME_MAX;
 
 	/*
@@ -1068,7 +1057,7 @@ void tmigr_handle_remote(void)
 	 * in tmigr_handle_remote_up() anyway. Keep this check to speed up the
 	 * return when nothing has to be done.
 	 */
-	if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) {
+	if (!tmigr_check_migrator(tmc->tmgroup, tmc->groupmask)) {
 		/*
 		 * If this CPU was an idle migrator, make sure to clear its wakeup
 		 * value so it won't chase timers that have already expired elsewhere.
@@ -1097,9 +1086,8 @@ void tmigr_handle_remote(void)
 
 static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
 					    struct tmigr_group *child,
-					    void *ptr)
+					    struct tmigr_walk *data)
 {
-	struct tmigr_remote_data *data = ptr;
 	u8 childmask;
 
 	childmask = data->childmask;
@@ -1118,7 +1106,7 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
 	 * group before reading the next_expiry value.
 	 */
 	if (group->parent && !data->tmc_active)
-		goto out;
+		return false;
 
 	/*
 	 * The lock is required on 32bit architectures to read the variable
@@ -1143,9 +1131,6 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
 		raw_spin_unlock(&group->lock);
 	}
 
-out:
-	/* Update of childmask for the next level */
-	data->childmask = group->childmask;
 	return false;
 }
 
@@ -1157,7 +1142,7 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
 bool tmigr_requires_handle_remote(void)
 {
 	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
-	struct tmigr_remote_data data;
+	struct tmigr_walk data;
 	unsigned long jif;
 	bool ret = false;
 
@@ -1165,7 +1150,7 @@ bool tmigr_requires_handle_remote(void)
 		return ret;
 
 	data.now = get_jiffies_update(&jif);
-	data.childmask = tmc->childmask;
+	data.childmask = tmc->groupmask;
 	data.firstexp = KTIME_MAX;
 	data.tmc_active = !tmc->idle;
 	data.check = false;
@@ -1230,14 +1215,13 @@ u64 tmigr_cpu_new_timer(u64 nextexp)
 		if (nextexp != tmc->cpuevt.nextevt.expires ||
 		    tmc->cpuevt.ignore) {
 			ret = tmigr_new_timer(tmc, nextexp);
+			/*
+			 * Make sure the reevaluation of timers in idle path
+			 * will not miss an event.
+			 */
+			WRITE_ONCE(tmc->wakeup, ret);
 		}
 	}
-	/*
-	 * Make sure the reevaluation of timers in idle path will not miss an
-	 * event.
-	 */
-	WRITE_ONCE(tmc->wakeup, ret);
-
 	trace_tmigr_cpu_new_timer_idle(tmc, nextexp);
 	raw_spin_unlock(&tmc->lock);
 	return ret;
@@ -1245,10 +1229,9 @@ u64 tmigr_cpu_new_timer(u64 nextexp)
 
 static bool tmigr_inactive_up(struct tmigr_group *group,
 			      struct tmigr_group *child,
-			      void *ptr)
+			      struct tmigr_walk *data)
 {
 	union tmigr_state curstate, newstate, childstate;
-	struct tmigr_walk *data = ptr;
 	bool walk_done;
 	u8 childmask;
 
@@ -1299,9 +1282,10 @@ static bool tmigr_inactive_up(struct tmigr_group *group,
 
 		WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active));
 
-		if (atomic_try_cmpxchg(&group->migr_state, &curstate.state,
-				       newstate.state))
+		if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)) {
+			trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
 			break;
+		}
 
 		/*
 		 * The memory barrier is paired with the cmpxchg() in
@@ -1317,22 +1301,6 @@ static bool tmigr_inactive_up(struct tmigr_group *group,
 	/* Event Handling */
 	tmigr_update_events(group, child, data);
 
-	if (group->parent && (walk_done == false))
-		data->childmask = group->childmask;
-
-	/*
-	 * data->firstexp was set by tmigr_update_events() and contains the
-	 * expiry of the first global event which needs to be handled. It
-	 * differs from KTIME_MAX if:
-	 * - group is the top level group and
-	 * - group is idle (which means CPU was the last active CPU in the
-	 *   hierarchy) and
-	 * - there is a pending event in the hierarchy
-	 */
-	WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent);
-
-	trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
-
 	return walk_done;
 }
 
@@ -1341,7 +1309,7 @@ static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp)
 	struct tmigr_walk data = { .nextexp = nextexp,
 				   .firstexp = KTIME_MAX,
 				   .evt = &tmc->cpuevt,
-				   .childmask = tmc->childmask };
+				   .childmask = tmc->groupmask };
 
 	/*
 	 * If nextexp is KTIME_MAX, the CPU event will be ignored because the
@@ -1400,7 +1368,7 @@ u64 tmigr_cpu_deactivate(u64 nextexp)
  *			  the only one in the level 0 group; and if it is the
  *			  only one in level 0 group, but there are more than a
  *			  single group active on the way to top level)
- * * nextevt		- when CPU is offline and has to handle timer on his own
+ * * nextevt		- when CPU is offline and has to handle timer on its own
  *			  or when on the way to top in every group only a single
  *			  child is active but @nextevt is before the lowest
  *			  next_expiry encountered while walking up to top level.
@@ -1419,7 +1387,7 @@ u64 tmigr_quick_check(u64 nextevt)
 	if (WARN_ON_ONCE(tmc->idle))
 		return nextevt;
 
-	if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask))
+	if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->groupmask))
 		return KTIME_MAX;
 
 	do {
@@ -1442,6 +1410,66 @@ u64 tmigr_quick_check(u64 nextevt)
 	return KTIME_MAX;
 }
 
+/*
+ * tmigr_trigger_active() - trigger a CPU to become active again
+ *
+ * This function is executed on a CPU which is part of cpu_online_mask, when the
+ * last active CPU in the hierarchy is offlining. With this, it is ensured that
+ * the other CPU is active and takes over the migrator duty.
+ */
+static long tmigr_trigger_active(void *unused)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+	WARN_ON_ONCE(!tmc->online || tmc->idle);
+
+	return 0;
+}
+
+static int tmigr_cpu_offline(unsigned int cpu)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	int migrator;
+	u64 firstexp;
+
+	raw_spin_lock_irq(&tmc->lock);
+	tmc->online = false;
+	WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+
+	/*
+	 * CPU has to handle the local events on his own, when on the way to
+	 * offline; Therefore nextevt value is set to KTIME_MAX
+	 */
+	firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
+	trace_tmigr_cpu_offline(tmc);
+	raw_spin_unlock_irq(&tmc->lock);
+
+	if (firstexp != KTIME_MAX) {
+		migrator = cpumask_any_but(cpu_online_mask, cpu);
+		work_on_cpu(migrator, tmigr_trigger_active, NULL);
+	}
+
+	return 0;
+}
+
+static int tmigr_cpu_online(unsigned int cpu)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+	/* Check whether CPU data was successfully initialized */
+	if (WARN_ON_ONCE(!tmc->tmgroup))
+		return -EINVAL;
+
+	raw_spin_lock_irq(&tmc->lock);
+	trace_tmigr_cpu_online(tmc);
+	tmc->idle = timer_base_is_idle();
+	if (!tmc->idle)
+		__tmigr_cpu_activate(tmc);
+	tmc->online = true;
+	raw_spin_unlock_irq(&tmc->lock);
+	return 0;
+}
+
 static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
 			     int node)
 {
@@ -1514,21 +1542,25 @@ static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node,
 }
 
 static void tmigr_connect_child_parent(struct tmigr_group *child,
-				       struct tmigr_group *parent)
+				       struct tmigr_group *parent,
+				       bool activate)
 {
-	union tmigr_state childstate;
+	struct tmigr_walk data;
 
 	raw_spin_lock_irq(&child->lock);
 	raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);
 
 	child->parent = parent;
-	child->childmask = BIT(parent->num_children++);
+	child->groupmask = BIT(parent->num_children++);
 
 	raw_spin_unlock(&parent->lock);
 	raw_spin_unlock_irq(&child->lock);
 
 	trace_tmigr_connect_child_parent(child);
 
+	if (!activate)
+		return;
+
 	/*
 	 * To prevent inconsistent states, active children need to be active in
 	 * the new parent as well. Inactive children are already marked inactive
@@ -1544,21 +1576,24 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
 	 *   child to the new parent. So tmigr_connect_child_parent() is
 	 *   executed with the formerly top level group (child) and the newly
 	 *   created group (parent).
+	 *
+	 * * It is ensured that the child is active, as this setup path is
+	 *   executed in hotplug prepare callback. This is exectued by an
+	 *   already connected and !idle CPU. Even if all other CPUs go idle,
+	 *   the CPU executing the setup will be responsible up to current top
+	 *   level group. And the next time it goes inactive, it will release
+	 *   the new childmask and parent to subsequent walkers through this
+	 *   @child. Therefore propagate active state unconditionally.
 	 */
-	childstate.state = atomic_read(&child->migr_state);
-	if (childstate.migrator != TMIGR_NONE) {
-		struct tmigr_walk data;
+	data.childmask = child->groupmask;
 
-		data.childmask = child->childmask;
-
-		/*
-		 * There is only one new level per time. When connecting the
-		 * child and the parent and set the child active when the parent
-		 * is inactive, the parent needs to be the uppermost
-		 * level. Otherwise there went something wrong!
-		 */
-		WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
-	}
+	/*
+	 * There is only one new level per time (which is protected by
+	 * tmigr_mutex). When connecting the child and the parent and set the
+	 * child active when the parent is inactive, the parent needs to be the
+	 * uppermost level. Otherwise there went something wrong!
+	 */
+	WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
 }
 
 static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
@@ -1611,12 +1646,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
 		 * Update tmc -> group / child -> group connection
 		 */
 		if (i == 0) {
-			struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+			struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu);
 
 			raw_spin_lock_irq(&group->lock);
 
 			tmc->tmgroup = group;
-			tmc->childmask = BIT(group->num_children++);
+			tmc->groupmask = BIT(group->num_children++);
 
 			raw_spin_unlock_irq(&group->lock);
 
@@ -1626,7 +1661,8 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
 			continue;
 		} else {
 			child = stack[i - 1];
-			tmigr_connect_child_parent(child, group);
+			/* Will be activated at online time */
+			tmigr_connect_child_parent(child, group, false);
 		}
 
 		/* check if uppermost level was newly created */
@@ -1637,12 +1673,21 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
 
 		lvllist = &tmigr_level_list[top];
 		if (group->num_children == 1 && list_is_singular(lvllist)) {
+			/*
+			 * The target CPU must never do the prepare work, except
+			 * on early boot when the boot CPU is the target. Otherwise
+			 * it may spuriously activate the old top level group inside
+			 * the new one (nevertheless whether old top level group is
+			 * active or not) and/or release an uninitialized childmask.
+			 */
+			WARN_ON_ONCE(cpu == raw_smp_processor_id());
+
 			lvllist = &tmigr_level_list[top - 1];
 			list_for_each_entry(child, lvllist, list) {
 				if (child->parent)
 					continue;
 
-				tmigr_connect_child_parent(child, group);
+				tmigr_connect_child_parent(child, group, true);
 			}
 		}
 	}
@@ -1664,80 +1709,31 @@ static int tmigr_add_cpu(unsigned int cpu)
 	return ret;
 }
 
-static int tmigr_cpu_online(unsigned int cpu)
+static int tmigr_cpu_prepare(unsigned int cpu)
 {
-	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
-	int ret;
+	struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu);
+	int ret = 0;
 
-	/* First online attempt? Initialize CPU data */
-	if (!tmc->tmgroup) {
-		raw_spin_lock_init(&tmc->lock);
+	/* Not first online attempt? */
+	if (tmc->tmgroup)
+		return ret;
 
-		ret = tmigr_add_cpu(cpu);
-		if (ret < 0)
-			return ret;
-
-		if (tmc->childmask == 0)
-			return -EINVAL;
-
-		timerqueue_init(&tmc->cpuevt.nextevt);
-		tmc->cpuevt.nextevt.expires = KTIME_MAX;
-		tmc->cpuevt.ignore = true;
-		tmc->cpuevt.cpu = cpu;
-
-		tmc->remote = false;
-		WRITE_ONCE(tmc->wakeup, KTIME_MAX);
-	}
-	raw_spin_lock_irq(&tmc->lock);
-	trace_tmigr_cpu_online(tmc);
-	tmc->idle = timer_base_is_idle();
-	if (!tmc->idle)
-		__tmigr_cpu_activate(tmc);
-	tmc->online = true;
-	raw_spin_unlock_irq(&tmc->lock);
-	return 0;
-}
-
-/*
- * tmigr_trigger_active() - trigger a CPU to become active again
- *
- * This function is executed on a CPU which is part of cpu_online_mask, when the
- * last active CPU in the hierarchy is offlining. With this, it is ensured that
- * the other CPU is active and takes over the migrator duty.
- */
-static long tmigr_trigger_active(void *unused)
-{
-	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
-
-	WARN_ON_ONCE(!tmc->online || tmc->idle);
-
-	return 0;
-}
-
-static int tmigr_cpu_offline(unsigned int cpu)
-{
-	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
-	int migrator;
-	u64 firstexp;
-
-	raw_spin_lock_irq(&tmc->lock);
-	tmc->online = false;
+	raw_spin_lock_init(&tmc->lock);
+	timerqueue_init(&tmc->cpuevt.nextevt);
+	tmc->cpuevt.nextevt.expires = KTIME_MAX;
+	tmc->cpuevt.ignore = true;
+	tmc->cpuevt.cpu = cpu;
+	tmc->remote = false;
 	WRITE_ONCE(tmc->wakeup, KTIME_MAX);
 
-	/*
-	 * CPU has to handle the local events on his own, when on the way to
-	 * offline; Therefore nextevt value is set to KTIME_MAX
-	 */
-	firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
-	trace_tmigr_cpu_offline(tmc);
-	raw_spin_unlock_irq(&tmc->lock);
+	ret = tmigr_add_cpu(cpu);
+	if (ret < 0)
+		return ret;
 
-	if (firstexp != KTIME_MAX) {
-		migrator = cpumask_any_but(cpu_online_mask, cpu);
-		work_on_cpu(migrator, tmigr_trigger_active, NULL);
-	}
+	if (tmc->groupmask == 0)
+		return -EINVAL;
 
-	return 0;
+	return ret;
 }
 
 static int __init tmigr_init(void)
@@ -1796,6 +1792,11 @@ static int __init tmigr_init(void)
 		tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
 		tmigr_crossnode_level);
 
+	ret = cpuhp_setup_state(CPUHP_TMIGR_PREPARE, "tmigr:prepare",
+				tmigr_cpu_prepare, NULL);
+	if (ret)
+		goto err;
+
 	ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online",
 				tmigr_cpu_online, tmigr_cpu_offline);
 	if (ret)
@@ -1807,4 +1808,4 @@ static int __init tmigr_init(void)
 	pr_err("Timer migration setup failed\n");
 	return ret;
 }
-late_initcall(tmigr_init);
+early_initcall(tmigr_init);
diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
index 6c37d94..154accc 100644
--- a/kernel/time/timer_migration.h
+++ b/kernel/time/timer_migration.h
@@ -22,7 +22,17 @@ struct tmigr_event {
  * struct tmigr_group - timer migration hierarchy group
  * @lock:		Lock protecting the event information and group hierarchy
  *			information during setup
- * @parent:		Pointer to the parent group
+ * @parent:		Pointer to the parent group. Pointer is updated when a
+ *			new hierarchy level is added because of a CPU coming
+ *			online the first time. Once it is set, the pointer will
+ *			not be removed or updated. When accessing parent pointer
+ *			lock less to decide whether to abort a propagation or
+ *			not, it is not a problem. The worst outcome is an
+ *			unnecessary/early CPU wake up. But do not access parent
+ *			pointer several times in the same 'action' (like
+ *			activation, deactivation, check for remote expiry,...)
+ *			without holding the lock as it is not ensured that value
+ *			will not change.
  * @groupevt:		Next event of the group which is only used when the
  *			group is !active. The group event is then queued into
  *			the parent timer queue.
@@ -41,9 +51,8 @@ struct tmigr_event {
  * @num_children:	Counter of group children to make sure the group is only
  *			filled with TMIGR_CHILDREN_PER_GROUP; Required for setup
  *			only
- * @childmask:		childmask of the group in the parent group; is set
- *			during setup and will never change; can be read
- *			lockless
+ * @groupmask:		mask of the group in the parent group; is set during
+ *			setup and will never change; can be read lockless
  * @list:		List head that is added to the per level
  *			tmigr_level_list; is required during setup when a
  *			new group needs to be connected to the existing
@@ -59,7 +68,7 @@ struct tmigr_group {
 	unsigned int		level;
 	int			numa_node;
 	unsigned int		num_children;
-	u8			childmask;
+	u8			groupmask;
 	struct list_head	list;
 };
 
@@ -79,7 +88,7 @@ struct tmigr_group {
  *			hierarchy
  * @remote:		Is set when timers of the CPU are expired remotely
  * @tmgroup:		Pointer to the parent group
- * @childmask:		childmask of tmigr_cpu in the parent group
+ * @groupmask:		mask of tmigr_cpu in the parent group
  * @wakeup:		Stores the first timer when the timer migration
  *			hierarchy is completely idle and remote expiry was done;
  *			is returned to timer code in the idle path and is only
@@ -92,7 +101,7 @@ struct tmigr_cpu {
 	bool			idle;
 	bool			remote;
 	struct tmigr_group	*tmgroup;
-	u8			childmask;
+	u8			groupmask;
 	u64			wakeup;
 	struct tmigr_event	cpuevt;
 };
@@ -108,8 +117,8 @@ union tmigr_state {
 	u32 state;
 	/**
 	 * struct - split state of tmigr_group
-	 * @active:	Contains each childmask bit of the active children
-	 * @migrator:	Contains childmask of the child which is migrator
+	 * @active:	Contains each mask bit of the active children
+	 * @migrator:	Contains mask of the child which is migrator
 	 * @seq:	Sequence counter needs to be increased when an update
 	 *		to the tmigr_state is done. It prevents a race when
 	 *		updates in the child groups are propagated in changed
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0f57943..4c28dd1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8735,7 +8735,7 @@ static bool is_permanent_ops_registered(void)
 }
 
 static int
-ftrace_enable_sysctl(struct ctl_table *table, int write,
+ftrace_enable_sysctl(const struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = -ENODEV;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 578a49f..10cd38b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2767,7 +2767,7 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 	raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
 }
 
-int tracepoint_printk_sysctl(struct ctl_table *table, int write,
+int tracepoint_printk_sysctl(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp,
 			     loff_t *ppos)
 {
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 3a2b468..42b0d99 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2885,7 +2885,7 @@ static int create_user_tracefs(void)
 	return -ENODEV;
 }
 
-static int set_max_user_events_sysctl(struct ctl_table *table, int write,
+static int set_max_user_events_sysctl(const struct ctl_table *table, int write,
 				      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 5a48dba..7f9572a 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -514,7 +514,7 @@ static const struct file_operations stack_trace_filter_fops = {
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 int
-stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
 		   size_t *lenp, loff_t *ppos)
 {
 	int was_enabled;
diff --git a/kernel/umh.c b/kernel/umh.c
index 598b3ff..ff1f13a 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -495,7 +495,7 @@ int call_usermodehelper(const char *path, char **argv, char **envp, int wait)
 EXPORT_SYMBOL(call_usermodehelper);
 
 #if defined(CONFIG_SYSCTL)
-static int proc_cap_handler(struct ctl_table *table, int write,
+static int proc_cap_handler(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 04e4513..7282f61 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -30,7 +30,7 @@ static void *get_uts(const struct ctl_table *table)
  *	Special case of dostring for the UTS structure. This has locks
  *	to observe. Should this be in kernel/sys.c ????
  */
-static int proc_do_uts_string(struct ctl_table *table, int write,
+static int proc_do_uts_string(const struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table uts_table;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51915b4..830a838 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -983,7 +983,7 @@ static void proc_watchdog_update(void)
  * -------------------|----------------------------------|-------------------------------
  * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED
  */
-static int proc_watchdog_common(int which, struct ctl_table *table, int write,
+static int proc_watchdog_common(int which, const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old, *param = table->data;
@@ -1010,7 +1010,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 /*
  * /proc/sys/kernel/watchdog
  */
-static int proc_watchdog(struct ctl_table *table, int write,
+static int proc_watchdog(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED |
@@ -1021,7 +1021,7 @@ static int proc_watchdog(struct ctl_table *table, int write,
 /*
  * /proc/sys/kernel/nmi_watchdog
  */
-static int proc_nmi_watchdog(struct ctl_table *table, int write,
+static int proc_nmi_watchdog(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!watchdog_hardlockup_available && write)
@@ -1034,7 +1034,7 @@ static int proc_nmi_watchdog(struct ctl_table *table, int write,
 /*
  * /proc/sys/kernel/soft_watchdog
  */
-static int proc_soft_watchdog(struct ctl_table *table, int write,
+static int proc_soft_watchdog(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED,
@@ -1045,7 +1045,7 @@ static int proc_soft_watchdog(struct ctl_table *table, int write,
 /*
  * /proc/sys/kernel/watchdog_thresh
  */
-static int proc_watchdog_thresh(struct ctl_table *table, int write,
+static int proc_watchdog_thresh(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old;
@@ -1068,7 +1068,7 @@ static int proc_watchdog_thresh(struct ctl_table *table, int write,
  * user to specify a mask that will include cpus that have not yet
  * been brought online, if desired.
  */
-static int proc_watchdog_cpumask(struct ctl_table *table, int write,
+static int proc_watchdog_cpumask(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err;
diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c
index a105e636..6b62a6b 100644
--- a/lib/cpumask_kunit.c
+++ b/lib/cpumask_kunit.c
@@ -152,4 +152,5 @@ static struct kunit_suite test_cpumask_suite = {
 };
 kunit_test_suite(test_cpumask_suite);
 
+MODULE_DESCRIPTION("KUnit tests for cpumask");
 MODULE_LICENSE("GPL");
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 3518e73..ca73616 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	   RUNB) */
 	symCount = symTotal+2;
 	for (j = 0; j < groupCount; j++) {
-		unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1];
+		unsigned char length[MAX_SYMBOLS];
+		unsigned short temp[MAX_HUFCODE_BITS+1];
 		int	minLen,	maxLen, pp;
 		/* Read Huffman code lengths for each symbol.  They're
 		   stored in a way similar to mtf; record a starting
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index d3fb09e..402e160 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -194,4 +194,5 @@ static int __init find_bit_test(void)
 }
 module_init(find_bit_test);
 
+MODULE_DESCRIPTION("Test for find_*_bit functions");
 MODULE_LICENSE("GPL");
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 03b427e..b7f2fa0 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env)
 		len = strlen(env->envp[i]) + 1;
 
 		if (i != env->envp_idx - 1) {
+			/* @env->envp[] contains pointers to @env->buf[]
+			 * with @env->buflen chars, and we are removing
+			 * variable MODALIAS here pointed by @env->envp[i]
+			 * with length @len as shown below:
+			 *
+			 * 0               @env->buf[]      @env->buflen
+			 * ---------------------------------------------
+			 * ^             ^              ^              ^
+			 * |             |->   @len   <-| target block |
+			 * @env->envp[0] @env->envp[i]  @env->envp[i + 1]
+			 *
+			 * so the "target block" indicated above is moved
+			 * backward by @len, and its right size is
+			 * @env->buflen - (@env->envp[i + 1] - @env->envp[0]).
+			 */
 			memmove(env->envp[i], env->envp[i + 1],
-				env->buflen - len);
+				env->buflen - (env->envp[i + 1] - env->envp[0]));
 
 			for (j = i; j < env->envp_idx - 1; j++)
 				env->envp[j] = env->envp[j + 1] - len;
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6dfb8d4..65a75d5 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -1486,4 +1486,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_bitmap);
 MODULE_AUTHOR("david decotigny <david.decotigny@googlers.com>");
+MODULE_DESCRIPTION("Test cases for bitmap API");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 69b6a5e..965cb6f 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -824,4 +824,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_printf);
 MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>");
+MODULE_DESCRIPTION("Test cases for printf facility");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_scanf.c b/lib/test_scanf.c
index a2707af..7257b176 100644
--- a/lib/test_scanf.c
+++ b/lib/test_scanf.c
@@ -810,4 +810,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_scanf);
 MODULE_AUTHOR("Richard Fitzgerald <rf@opensource.cirrus.com>");
+MODULE_DESCRIPTION("Test cases for sscanf facility");
 MODULE_LICENSE("GPL v2");
diff --git a/lib/usercopy.c b/lib/usercopy.c
index 499a7a7..7b17b83 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -12,40 +12,18 @@
 
 /* out-of-line parts */
 
-#ifndef INLINE_COPY_FROM_USER
+#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)
 unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long res = n;
-	might_fault();
-	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
-		/*
-		 * Ensure that bad access_ok() speculation will not
-		 * lead to nasty side effects *after* the copy is
-		 * finished:
-		 */
-		barrier_nospec();
-		instrument_copy_from_user_before(to, from, n);
-		res = raw_copy_from_user(to, from, n);
-		instrument_copy_from_user_after(to, from, n, res);
-	}
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
+	return _inline_copy_from_user(to, from, n);
 }
 EXPORT_SYMBOL(_copy_from_user);
 #endif
 
-#ifndef INLINE_COPY_TO_USER
+#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST)
 unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	might_fault();
-	if (should_fail_usercopy())
-		return n;
-	if (likely(access_ok(to, n))) {
-		instrument_copy_to_user(to, from, n);
-		n = raw_copy_to_user(to, from, n);
-	}
-	return n;
+	return _inline_copy_to_user(to, from, n);
 }
 EXPORT_SYMBOL(_copy_to_user);
 #endif
diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index c46c230..82fe827 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -38,3 +38,8 @@
 	  in the hotpath.
 
 endif
+
+config VDSO_GETRANDOM
+	bool
+	help
+	  Selected by architectures that support vDSO getrandom().
diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c
new file mode 100644
index 0000000..b230f0b
--- /dev/null
+++ b/lib/vdso/getrandom.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/cache.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+#include <vdso/datapage.h>
+#include <vdso/getrandom.h>
+#include <asm/vdso/getrandom.h>
+#include <asm/vdso/vsyscall.h>
+#include <asm/unaligned.h>
+#include <uapi/linux/mman.h>
+
+#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do {				\
+	while (len >= sizeof(type)) {						\
+		__put_unaligned_t(type, __get_unaligned_t(type, src), dst);	\
+		__put_unaligned_t(type, 0, src);				\
+		dst += sizeof(type);						\
+		src += sizeof(type);						\
+		len -= sizeof(type);						\
+	}									\
+} while (0)
+
+static void memcpy_and_zero_src(void *dst, void *src, size_t len)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		if (IS_ENABLED(CONFIG_64BIT))
+			MEMCPY_AND_ZERO_SRC(u64, dst, src, len);
+		MEMCPY_AND_ZERO_SRC(u32, dst, src, len);
+		MEMCPY_AND_ZERO_SRC(u16, dst, src, len);
+	}
+	MEMCPY_AND_ZERO_SRC(u8, dst, src, len);
+}
+
+/**
+ * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall.
+ * @rng_info:		Describes state of kernel RNG, memory shared with kernel.
+ * @buffer:		Destination buffer to fill with random bytes.
+ * @len:		Size of @buffer in bytes.
+ * @flags:		Zero or more GRND_* flags.
+ * @opaque_state:	Pointer to an opaque state area.
+ * @opaque_len:		Length of opaque state area.
+ *
+ * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's
+ * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same
+ * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always
+ * calls into the syscall.
+ *
+ * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated
+ * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0,
+ * this function should not be used.
+ *
+ * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields
+ * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external
+ * locking is used, one state must be allocated per thread, as it is not safe to call this function
+ * concurrently with the same @opaque_state. However, it is safe to call this using the same
+ * @opaque_state that is shared between main code and signal handling code, within the same thread.
+ *
+ * Returns:	The number of random bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t
+__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len,
+		       unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len);
+	struct vgetrandom_state *state = opaque_state;
+	size_t batch_len, nblocks, orig_len = len;
+	bool in_use, have_retried = false;
+	unsigned long current_generation;
+	void *orig_buffer = buffer;
+	u32 counter[2] = { 0 };
+
+	if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) {
+		*(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) {
+			.size_of_opaque_state = sizeof(*state),
+			.mmap_prot = PROT_READ | PROT_WRITE,
+			.mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS
+		};
+		return 0;
+	}
+
+	/* The state must not straddle a page, since pages can be zeroed at any time. */
+	if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE))
+		return -EFAULT;
+
+	/* If the caller passes the wrong size, which might happen due to CRIU, fallback. */
+	if (unlikely(opaque_len != sizeof(*state)))
+		goto fallback_syscall;
+
+	/*
+	 * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from
+	 * userspace, because A) the various @flags require this to block, or not, depending on
+	 * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is
+	 * ready is to reseed from the entropy pool at every invocation.
+	 */
+	if (unlikely(!READ_ONCE(rng_info->is_ready)))
+		goto fallback_syscall;
+
+	/*
+	 * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is
+	 * initialized, the @flags parameter may require this to block or return an error, even when
+	 * len is zero.
+	 */
+	if (unlikely(!len))
+		return 0;
+
+	/*
+	 * @state->in_use is basic reentrancy protection against this running in a signal handler
+	 * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one
+	 * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before
+	 * writing @state->in_use, there is still no race, because the signal handler will run to
+	 * its completion before returning execution.
+	 */
+	in_use = READ_ONCE(state->in_use);
+	if (unlikely(in_use))
+		/* The syscall simply fills the buffer and does not touch @state, so fallback. */
+		goto fallback_syscall;
+	WRITE_ONCE(state->in_use, true);
+
+retry_generation:
+	/*
+	 * @rng_info->generation must always be read here, as it serializes @state->key with the
+	 * kernel's RNG reseeding schedule.
+	 */
+	current_generation = READ_ONCE(rng_info->generation);
+
+	/*
+	 * If @state->generation doesn't match the kernel RNG's generation, then it means the
+	 * kernel's RNG has reseeded, and so @state->key is reseeded as well.
+	 */
+	if (unlikely(state->generation != current_generation)) {
+		/*
+		 * Write the generation before filling the key, in case of fork. If there is a fork
+		 * just after this line, the parent and child will get different random bytes from
+		 * the syscall, which is good. However, were this line to occur after the getrandom
+		 * syscall, then both child and parent could have the same bytes and the same
+		 * generation counter, so the fork would not be detected. Therefore, write
+		 * @state->generation before the call to the getrandom syscall.
+		 */
+		WRITE_ONCE(state->generation, current_generation);
+
+		/*
+		 * Prevent the syscall from being reordered wrt current_generation. Pairs with the
+		 * smp_store_release(&_vdso_rng_data.generation) in random.c.
+		 */
+		smp_rmb();
+
+		/* Reseed @state->key using fresh bytes from the kernel. */
+		if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) {
+			/*
+			 * If the syscall failed to refresh the key, then @state->key is now
+			 * invalid, so invalidate the generation so that it is not used again, and
+			 * fallback to using the syscall entirely.
+			 */
+			WRITE_ONCE(state->generation, 0);
+
+			/*
+			 * Set @state->in_use to false only after the last write to @state in the
+			 * line above.
+			 */
+			WRITE_ONCE(state->in_use, false);
+
+			goto fallback_syscall;
+		}
+
+		/*
+		 * Set @state->pos to beyond the end of the batch, so that the batch is refilled
+		 * using the new key.
+		 */
+		state->pos = sizeof(state->batch);
+	}
+
+	/* Set len to the total amount of bytes that this function is allowed to read, ret. */
+	len = ret;
+more_batch:
+	/*
+	 * First use bytes out of @state->batch, which may have been filled by the last call to this
+	 * function.
+	 */
+	batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len);
+	if (batch_len) {
+		/* Zeroing at the same time as memcpying helps preserve forward secrecy. */
+		memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len);
+		state->pos += batch_len;
+		buffer += batch_len;
+		len -= batch_len;
+	}
+
+	if (!len) {
+		/* Prevent the loop from being reordered wrt ->generation. */
+		barrier();
+
+		/*
+		 * Since @rng_info->generation will never be 0, re-read @state->generation, rather
+		 * than using the local current_generation variable, to learn whether a fork
+		 * occurred or if @state was zeroed due to memory pressure. Primarily, though, this
+		 * indicates whether the kernel's RNG has reseeded, in which case generate a new key
+		 * and start over.
+		 */
+		if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) {
+			/*
+			 * Prevent this from looping forever in case of low memory or racing with a
+			 * user force-reseeding the kernel's RNG using the ioctl.
+			 */
+			if (have_retried) {
+				WRITE_ONCE(state->in_use, false);
+				goto fallback_syscall;
+			}
+
+			have_retried = true;
+			buffer = orig_buffer;
+			goto retry_generation;
+		}
+
+		/*
+		 * Set @state->in_use to false only when there will be no more reads or writes of
+		 * @state.
+		 */
+		WRITE_ONCE(state->in_use, false);
+		return ret;
+	}
+
+	/* Generate blocks of RNG output directly into @buffer while there's enough room left. */
+	nblocks = len / CHACHA_BLOCK_SIZE;
+	if (nblocks) {
+		__arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks);
+		buffer += nblocks * CHACHA_BLOCK_SIZE;
+		len -= nblocks * CHACHA_BLOCK_SIZE;
+	}
+
+	BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0);
+
+	/* Refill the batch and overwrite the key, in order to preserve forward secrecy. */
+	__arch_chacha20_blocks_nostack(state->batch_key, state->key, counter,
+				       sizeof(state->batch_key) / CHACHA_BLOCK_SIZE);
+
+	/* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */
+	state->pos = 0;
+	goto more_batch;
+
+fallback_syscall:
+	return getrandom_syscall(orig_buffer, orig_len, flags);
+}
+
+static __always_inline ssize_t
+__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len);
+}
diff --git a/mm/compaction.c b/mm/compaction.c
index 6cb901b..eb95e9b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2962,7 +2962,7 @@ static int compact_nodes(void)
 	return 0;
 }
 
-static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
+static int compaction_proactiveness_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc, nid;
@@ -2992,7 +2992,7 @@ static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int
  * This is the entry point for compacting all nodes via
  * /proc/sys/vm/compact_memory
  */
-static int sysctl_compaction_handler(struct ctl_table *table, int write,
+static int sysctl_compaction_handler(const struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret;
@@ -3303,7 +3303,7 @@ static int kcompactd_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table,
 		int write, void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, old;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f9696c9..f4be468 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -89,9 +89,17 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 	bool smaps = tva_flags & TVA_SMAPS;
 	bool in_pf = tva_flags & TVA_IN_PF;
 	bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS;
+	unsigned long supported_orders;
+
 	/* Check the intersection of requested and supported orders. */
-	orders &= vma_is_anonymous(vma) ?
-			THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
+	if (vma_is_anonymous(vma))
+		supported_orders = THP_ORDERS_ALL_ANON;
+	else if (vma_is_dax(vma))
+		supported_orders = THP_ORDERS_ALL_FILE_DAX;
+	else
+		supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;
+
+	orders &= supported_orders;
 	if (!orders)
 		return 0;
 
@@ -877,7 +885,7 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	loff_t off_align = round_up(off, size);
 	unsigned long len_pad, ret, off_sub;
 
-	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+	if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
 		return 0;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0858a18..aaf508b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4925,7 +4925,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	return ret;
 }
 
-static int hugetlb_sysctl_handler(struct ctl_table *table, int write,
+static int hugetlb_sysctl_handler(const struct ctl_table *table, int write,
 			  void *buffer, size_t *length, loff_t *ppos)
 {
 
@@ -4934,7 +4934,7 @@ static int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_NUMA
-static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
+static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write,
 			  void *buffer, size_t *length, loff_t *ppos)
 {
 	return hugetlb_sysctl_handler_common(true, table, write,
@@ -4942,7 +4942,7 @@ static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
 }
 #endif /* CONFIG_NUMA */
 
-static int hugetlb_overcommit_handler(struct ctl_table *table, int write,
+static int hugetlb_overcommit_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
diff --git a/mm/ksm.c b/mm/ksm.c
index df6bae3..14d9e53 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -713,7 +713,7 @@ static bool vma_ksm_compatible(struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
 			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
-			     VM_MIXEDMAP))
+			     VM_MIXEDMAP| VM_DROPPABLE))
 		return false;		/* just ignore the advice */
 
 	if (vma_is_dax(vma))
diff --git a/mm/madvise.c b/mm/madvise.c
index 96c026f..89089d8 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1068,13 +1068,16 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_WIPEONFORK;
 		break;
 	case MADV_KEEPONFORK:
+		if (vma->vm_flags & VM_DROPPABLE)
+			return -EINVAL;
 		new_flags &= ~VM_WIPEONFORK;
 		break;
 	case MADV_DONTDUMP:
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL)
+		if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) ||
+		    (vma->vm_flags & VM_DROPPABLE))
 			return -EINVAL;
 		new_flags &= ~VM_DONTDUMP;
 		break;
diff --git a/mm/memory.c b/mm/memory.c
index 4bcd796..34f8402 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4780,7 +4780,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE);
+	bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE);
 	pte_t entry;
 
 	flush_icache_pages(vma, page, nr);
@@ -5801,6 +5801,7 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	/* If the fault handler drops the mmap_lock, vma may be freed */
 	struct mm_struct *mm = vma->vm_mm;
 	vm_fault_t ret;
+	bool is_droppable;
 
 	__set_current_state(TASK_RUNNING);
 
@@ -5815,6 +5816,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 
+	is_droppable = !!(vma->vm_flags & VM_DROPPABLE);
+
 	/*
 	 * Enable the memcg OOM handling for faults triggered in user
 	 * space.  Kernel faults are handled more gracefully.
@@ -5829,8 +5832,18 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	else
 		ret = __handle_mm_fault(vma, address, flags);
 
+	/*
+	 * Warning: It is no longer safe to dereference vma-> after this point,
+	 * because mmap_lock might have been dropped by __handle_mm_fault(), so
+	 * vma might be destroyed from underneath us.
+	 */
+
 	lru_gen_exit_fault();
 
+	/* If the mapping is droppable, then errors due to OOM aren't fatal. */
+	if (is_droppable)
+		ret &= ~VM_FAULT_OOM;
+
 	if (flags & FAULT_FLAG_USER) {
 		mem_cgroup_exit_user_fault();
 		/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 327a19b..b858e22 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2305,6 +2305,9 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct
 	pgoff_t ilx;
 	struct folio *folio;
 
+	if (vma->vm_flags & VM_DROPPABLE)
+		gfp |= __GFP_NOWARN;
+
 	pol = get_vma_policy(vma, addr, order, &ilx);
 	folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id());
 	mpol_cond_put(pol);
diff --git a/mm/mlock.c b/mm/mlock.c
index 52d6e40..e3e3dc2 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -474,7 +474,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma) || vma_is_secretmem(vma))
+	    vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index e42d89f..d0dfc85 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1410,6 +1410,36 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 			pgoff = 0;
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
 			break;
+		case MAP_DROPPABLE:
+			if (VM_DROPPABLE == VM_NONE)
+				return -ENOTSUPP;
+			/*
+			 * A locked or stack area makes no sense to be droppable.
+			 *
+			 * Also, since droppable pages can just go away at any time
+			 * it makes no sense to copy them on fork or dump them.
+			 *
+			 * And don't attempt to combine with hugetlb for now.
+			 */
+			if (flags & (MAP_LOCKED | MAP_HUGETLB))
+			        return -EINVAL;
+			if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP))
+			        return -EINVAL;
+
+			vm_flags |= VM_DROPPABLE;
+
+			/*
+			 * If the pages can be dropped, then it doesn't make
+			 * sense to reserve them.
+			 */
+			vm_flags |= VM_NORESERVE;
+
+			/*
+			 * Likewise, they're volatile enough that they
+			 * shouldn't survive forks or coredumps.
+			 */
+			vm_flags |= VM_WIPEONFORK | VM_DONTDUMP;
+			fallthrough;
 		case MAP_PRIVATE:
 			/*
 			 * Set pgoff according to addr for anon_vma.
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index acff24e..4430ac6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -506,7 +506,7 @@ bool node_dirty_ok(struct pglist_data *pgdat)
 }
 
 #ifdef CONFIG_SYSCTL
-static int dirty_background_ratio_handler(struct ctl_table *table, int write,
+static int dirty_background_ratio_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -517,7 +517,7 @@ static int dirty_background_ratio_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int dirty_background_bytes_handler(struct ctl_table *table, int write,
+static int dirty_background_bytes_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -535,7 +535,7 @@ static int dirty_background_bytes_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer,
+static int dirty_ratio_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_ratio = vm_dirty_ratio;
@@ -549,7 +549,7 @@ static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
-static int dirty_bytes_handler(struct ctl_table *table, int write,
+static int dirty_bytes_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned long old_bytes = vm_dirty_bytes;
@@ -2203,7 +2203,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 /*
  * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
  */
-static int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
+static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	unsigned int old_interval = dirty_writeback_interval;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3398d91..28f80da 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2343,16 +2343,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-	int count = READ_ONCE(pcp->count);
+	int count;
 
-	while (count) {
-		int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
-		count -= to_drain;
-
+	do {
 		spin_lock(&pcp->lock);
-		free_pcppages_bulk(zone, to_drain, pcp, 0);
+		count = pcp->count;
+		if (count) {
+			int to_drain = min(count,
+				pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+			free_pcppages_bulk(zone, to_drain, pcp, 0);
+			count -= to_drain;
+		}
 		spin_unlock(&pcp->lock);
-	}
+	} while (count);
 }
 
 /*
@@ -5127,7 +5131,7 @@ static char numa_zonelist_order[] = "Node";
 /*
  * sysctl handler for numa_zonelist_order
  */
-static int numa_zonelist_order_handler(struct ctl_table *table, int write,
+static int numa_zonelist_order_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
@@ -5815,6 +5819,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
+void free_reserved_page(struct page *page)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			set_codetag_empty(ref);
+			put_page_tag_ref(ref);
+		}
+	}
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL(free_reserved_page);
+
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
 	struct zone *zone;
@@ -6091,7 +6112,7 @@ postcore_initcall(init_per_zone_wmark_min)
  *	that we can call two helper functions whenever min_free_kbytes
  *	changes.
  */
-static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
+static int min_free_kbytes_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6107,7 +6128,7 @@ static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
+static int watermark_scale_factor_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6137,7 +6158,7 @@ static void setup_min_unmapped_ratio(void)
 }
 
 
-static int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_unmapped_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6164,7 +6185,7 @@ static void setup_min_slab_ratio(void)
 						     sysctl_min_slab_ratio) / 100;
 }
 
-static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6188,7 +6209,7 @@ static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int wri
  * minimum watermarks. The lowmem reserve ratio can only make sense
  * if in function of the boot time zone sizes.
  */
-static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
+static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	int i;
@@ -6209,7 +6230,7 @@ static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
  * cpu. It is the fraction of total pages in each zone that a hot per cpu
  * pagelist can have before it gets flushed back to buddy allocator.
  */
-static int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
+static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
diff --git a/mm/rmap.c b/mm/rmap.c
index 8616308..2490e72 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1412,7 +1412,11 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 	VM_BUG_ON_VMA(address < vma->vm_start ||
 			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
 
-	if (!folio_test_swapbacked(folio))
+	/*
+	 * VM_DROPPABLE mappings don't swap; instead they're just dropped when
+	 * under memory pressure.
+	 */
+	if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE))
 		__folio_set_swapbacked(folio);
 	__folio_set_anon(folio, vma, address, exclusive);
 
@@ -1848,7 +1852,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * plus the rmap(s) (dropped by discard:).
 				 */
 				if (ref_count == 1 + map_count &&
-				    !folio_test_dirty(folio)) {
+				    (!folio_test_dirty(folio) ||
+				     /*
+				      * Unlike MADV_FREE mappings, VM_DROPPABLE
+				      * ones can be dropped even if they've
+				      * been dirtied.
+				      */
+				     (vma->vm_flags & VM_DROPPABLE))) {
 					dec_mm_counter(mm, MM_ANONPAGES);
 					goto discard;
 				}
@@ -1858,7 +1868,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * discarded. Remap the page to page table.
 				 */
 				set_pte_at(mm, address, pvmw.pte, pteval);
-				folio_set_swapbacked(folio);
+				/*
+				 * Unlike MADV_FREE mappings, VM_DROPPABLE ones
+				 * never get swap backed on failure to drop.
+				 */
+				if (!(vma->vm_flags & VM_DROPPABLE))
+					folio_set_swapbacked(folio);
 				goto walk_abort;
 			}
 
diff --git a/mm/util.c b/mm/util.c
index bc488f0..bd283e2 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -868,7 +868,7 @@ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
 
-int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
+int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -884,7 +884,7 @@ static void sync_overcommit_as(struct work_struct *dummy)
 	percpu_counter_sync(&vm_committed_as);
 }
 
-int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
+int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -920,7 +920,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
-int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
+int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 525d3ff..cfa8392 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4301,15 +4301,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 		return true;
 	}
 
-	/* dirty lazyfree */
-	if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
-		success = lru_gen_del_folio(lruvec, folio, true);
-		VM_WARN_ON_ONCE_FOLIO(!success, folio);
-		folio_set_swapbacked(folio);
-		lruvec_add_folio_tail(lruvec, folio);
-		return true;
-	}
-
 	/* promoted */
 	if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 73d791d..04a1cb6 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -74,7 +74,7 @@ static void invalid_numa_statistics(void)
 
 static DEFINE_MUTEX(vm_numa_stat_lock);
 
-int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write,
+int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int ret, oldval;
@@ -1888,7 +1888,7 @@ static void refresh_vm_stats(struct work_struct *work)
 	refresh_cpu_vm_stats(true);
 }
 
-int vmstat_refresh(struct ctl_table *table, int write,
+int vmstat_refresh(const struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	long val;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 3c9f653..09f6a77 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -1189,7 +1189,7 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
 
 #ifdef CONFIG_SYSCTL
 static
-int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
+int brnf_sysctl_call_tables(const struct ctl_table *ctl, int write,
 			    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/net/core/filter.c b/net/core/filter.c
index 4cf1d34..f3c72cf8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3548,13 +3548,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		/* Due to header grow, MSS needs to be downgraded. */
-		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
-			skb_decrease_gso_size(shinfo, len_diff);
-
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= gso_type;
 		shinfo->gso_segs = 0;
+
+		/* Due to header growth, MSS needs to be downgraded.
+		 * There is a BUG_ON() when segmenting the frag_list with
+		 * head_frag true, so linearize the skb after downgrading
+		 * the MSS.
+		 */
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) {
+			skb_decrease_gso_size(shinfo, len_diff);
+			if (shinfo->frag_list)
+				return skb_linearize(skb);
+		}
 	}
 
 	return 0;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2777513..a6fe88e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3543,7 +3543,7 @@ EXPORT_SYMBOL(neigh_app_ns);
 #ifdef CONFIG_SYSCTL
 static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
 
-static int proc_unres_qlen(struct ctl_table *ctl, int write,
+static int proc_unres_qlen(const struct ctl_table *ctl, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int size, ret;
@@ -3595,7 +3595,7 @@ static void neigh_proc_update(const struct ctl_table *ctl, int write)
 		neigh_copy_dflt_parms(net, p, index);
 }
 
-static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
+static int neigh_proc_dointvec_zero_intmax(const struct ctl_table *ctl, int write,
 					   void *buffer, size_t *lenp,
 					   loff_t *ppos)
 {
@@ -3610,7 +3610,7 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int write,
+static int neigh_proc_dointvec_ms_jiffies_positive(const struct ctl_table *ctl, int write,
 						   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table tmp = *ctl;
@@ -3626,7 +3626,7 @@ static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int wr
 	return ret;
 }
 
-int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer,
+int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer,
 			size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
@@ -3636,7 +3636,7 @@ int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer,
 }
 EXPORT_SYMBOL(neigh_proc_dointvec);
 
-int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer,
+int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer,
 				size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3646,7 +3646,7 @@ int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer,
 }
 EXPORT_SYMBOL(neigh_proc_dointvec_jiffies);
 
-static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
+static int neigh_proc_dointvec_userhz_jiffies(const struct ctl_table *ctl, int write,
 					      void *buffer, size_t *lenp,
 					      loff_t *ppos)
 {
@@ -3656,7 +3656,7 @@ static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
+int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3666,7 +3666,7 @@ int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
 }
 EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies);
 
-static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
+static int neigh_proc_dointvec_unres_qlen(const struct ctl_table *ctl, int write,
 					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
@@ -3676,7 +3676,7 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
+static int neigh_proc_base_reachable_time(const struct ctl_table *ctl, int write,
 					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 2079000..86a2476 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -95,7 +95,7 @@ static struct cpumask *rps_default_mask_cow_alloc(struct net *net)
 	return rps_default_mask;
 }
 
-static int rps_default_mask_sysctl(struct ctl_table *table, int write,
+static int rps_default_mask_sysctl(const struct ctl_table *table, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = (struct net *)table->data;
@@ -126,7 +126,7 @@ static int rps_default_mask_sysctl(struct ctl_table *table, int write,
 	return err;
 }
 
-static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
+static int rps_sock_flow_sysctl(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int orig_size, size;
@@ -198,7 +198,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_NET_FLOW_LIMIT
 static DEFINE_MUTEX(flow_limit_update_mutex);
 
-static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
+static int flow_limit_cpu_sysctl(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct sd_flow_limit *cur;
@@ -255,7 +255,7 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
+static int flow_limit_table_len_sysctl(const struct ctl_table *table, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	unsigned int old, *ptr;
@@ -277,7 +277,7 @@ static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
 #endif /* CONFIG_NET_FLOW_LIMIT */
 
 #ifdef CONFIG_NET_SCHED
-static int set_default_qdisc(struct ctl_table *table, int write,
+static int set_default_qdisc(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char id[IFNAMSIZ];
@@ -296,7 +296,7 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 }
 #endif
 
-static int proc_do_dev_weight(struct ctl_table *table, int write,
+static int proc_do_dev_weight(const struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	static DEFINE_MUTEX(dev_weight_mutex);
@@ -314,7 +314,7 @@ static int proc_do_dev_weight(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int proc_do_rss_key(struct ctl_table *table, int write,
+static int proc_do_rss_key(const struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table fake_table;
@@ -327,7 +327,7 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_BPF_JIT
-static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
+static int proc_dointvec_minmax_bpf_enable(const struct ctl_table *table, int write,
 					   void *buffer, size_t *lenp,
 					   loff_t *ppos)
 {
@@ -360,7 +360,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 
 # ifdef CONFIG_HAVE_EBPF_JIT
 static int
-proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+proc_dointvec_minmax_bpf_restricted(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!capable(CAP_SYS_ADMIN))
@@ -371,7 +371,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
 # endif /* CONFIG_HAVE_EBPF_JIT */
 
 static int
-proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+proc_dolongvec_minmax_bpf_restricted(const struct ctl_table *table, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!capable(CAP_SYS_ADMIN))
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d09f557e..d96f3e4 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2390,7 +2390,7 @@ static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf)
 	}
 }
 
-static int devinet_conf_proc(struct ctl_table *ctl, int write,
+static int devinet_conf_proc(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int old_value = *(int *)ctl->data;
@@ -2442,7 +2442,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
+static int devinet_sysctl_forward(const struct ctl_table *ctl, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
@@ -2489,7 +2489,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int ipv4_doint_and_flush(struct ctl_table *ctl, int write,
+static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 535856b..6b9787e 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -888,9 +888,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 
 	p = nla_data(nla);
 	for (i = 0; i < nhg->num_nh; ++i) {
-		p->id = nhg->nh_entries[i].nh->id;
-		p->weight = nhg->nh_entries[i].weight - 1;
-		p += 1;
+		*p++ = (struct nexthop_grp) {
+			.id = nhg->nh_entries[i].nh->id,
+			.weight = nhg->nh_entries[i].weight - 1,
+		};
 	}
 
 	if (nhg->resilient && nla_put_nh_group_res(skb, nhg))
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 6c4664c..40053a02 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -44,7 +44,7 @@
 #include <net/sock.h>
 #include <net/raw.h>
 
-#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX)
+#define TCPUDP_MIB_MAX MAX_T(u32, UDP_MIB_MAX, TCP_MIB_MAX)
 
 /*
  *	Report socket allocation statistics [mea@utu.fi]
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5090912..13c0f1d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		struct flowi4 fl4 = {
 			.daddr = iph->daddr,
 			.saddr = iph->saddr,
-			.flowi4_tos = RT_TOS(iph->tos),
+			.flowi4_tos = iph->tos & IPTOS_RT_MASK,
 			.flowi4_oif = rt->dst.dev->ifindex,
 			.flowi4_iif = skb->dev->ifindex,
 			.flowi4_mark = skb->mark,
@@ -3388,7 +3388,7 @@ static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
 static int ip_min_valid_pmtu __read_mostly	= IPV4_MIN_MTU;
 
-static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write,
+static int ipv4_sysctl_rtcache_flush(const struct ctl_table *__ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = (struct net *)__ctl->extra1;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9140d20..4af0c23 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -62,7 +62,7 @@ static void set_local_port_range(struct net *net, unsigned int low, unsigned int
 }
 
 /* Validate changes from /proc interface. */
-static int ipv4_local_port_range(struct ctl_table *table, int write,
+static int ipv4_local_port_range(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = table->data;
@@ -96,7 +96,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 }
 
 /* Validate changes from /proc interface. */
-static int ipv4_privileged_ports(struct ctl_table *table, int write,
+static int ipv4_privileged_ports(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = container_of(table->data, struct net,
@@ -159,7 +159,7 @@ static void set_ping_group_range(const struct ctl_table *table,
 }
 
 /* Validate changes from /proc interface. */
-static int ipv4_ping_group_range(struct ctl_table *table, int write,
+static int ipv4_ping_group_range(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct user_namespace *user_ns = current_user_ns();
@@ -194,7 +194,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int ipv4_fwd_update_priority(struct ctl_table *table, int write,
+static int ipv4_fwd_update_priority(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net;
@@ -210,7 +210,7 @@ static int ipv4_fwd_update_priority(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
+static int proc_tcp_congestion_control(const struct ctl_table *ctl, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = container_of(ctl->data, struct net,
@@ -230,7 +230,7 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
+static int proc_tcp_available_congestion_control(const struct ctl_table *ctl,
 						 int write, void *buffer,
 						 size_t *lenp, loff_t *ppos)
 {
@@ -246,7 +246,7 @@ static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
 	return ret;
 }
 
-static int proc_allowed_congestion_control(struct ctl_table *ctl,
+static int proc_allowed_congestion_control(const struct ctl_table *ctl,
 					   int write, void *buffer,
 					   size_t *lenp, loff_t *ppos)
 {
@@ -283,7 +283,7 @@ static int sscanf_key(char *buf, __le32 *key)
 	return ret;
 }
 
-static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
+static int proc_tcp_fastopen_key(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = container_of(table->data, struct net,
@@ -354,7 +354,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
+static int proc_tfo_blackhole_detect_timeout(const struct ctl_table *table,
 					     int write, void *buffer,
 					     size_t *lenp, loff_t *ppos)
 {
@@ -369,7 +369,7 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
 	return ret;
 }
 
-static int proc_tcp_available_ulp(struct ctl_table *ctl,
+static int proc_tcp_available_ulp(const struct ctl_table *ctl,
 				  int write, void *buffer, size_t *lenp,
 				  loff_t *ppos)
 {
@@ -386,7 +386,7 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
 	return ret;
 }
 
-static int proc_tcp_ehash_entries(struct ctl_table *table, int write,
+static int proc_tcp_ehash_entries(const struct ctl_table *table, int write,
 				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = container_of(table->data, struct net,
@@ -410,7 +410,7 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write,
 	return proc_dointvec(&tbl, write, buffer, lenp, ppos);
 }
 
-static int proc_udp_hash_entries(struct ctl_table *table, int write,
+static int proc_udp_hash_entries(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = container_of(table->data, struct net,
@@ -434,7 +434,7 @@ static int proc_udp_hash_entries(struct ctl_table *table, int write,
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
+static int proc_fib_multipath_hash_policy(const struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
@@ -449,7 +449,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write,
+static int proc_fib_multipath_hash_fields(const struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
@@ -484,7 +484,7 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed)
 	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new);
 }
 
-static int proc_fib_multipath_hash_seed(struct ctl_table *table, int write,
+static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write,
 					void *buffer, size_t *lenp,
 					loff_t *ppos)
 {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ff9ab3d..454362e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6819,9 +6819,6 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		tcp_fast_path_on(tp);
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			tcp_shutdown(sk, SEND_SHUTDOWN);
-
-		if (sk->sk_socket)
-			goto consume;
 		break;
 
 	case TCP_FIN_WAIT1: {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 55a0fd5..f70d875 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6309,7 +6309,7 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 #ifdef CONFIG_SYSCTL
 
-static int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_forward(const struct ctl_table *ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
@@ -6334,7 +6334,7 @@ static int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int addrconf_sysctl_mtu(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_mtu(const struct ctl_table *ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct inet6_dev *idev = ctl->extra1;
@@ -6405,7 +6405,7 @@ static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf
 	return 0;
 }
 
-static int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
@@ -6430,7 +6430,7 @@ static int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
@@ -6471,7 +6471,7 @@ static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write,
 					 void *buffer, size_t *lenp,
 					 loff_t *ppos)
 {
@@ -6534,7 +6534,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write,
 					 void *buffer, size_t *lenp,
 					 loff_t *ppos)
 {
@@ -6602,7 +6602,7 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
 }
 
 static
-int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
+int addrconf_sysctl_ignore_routes_with_linkdown(const struct ctl_table *ctl,
 						int write, void *buffer,
 						size_t *lenp,
 						loff_t *ppos)
@@ -6702,7 +6702,7 @@ int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val)
 	return 0;
 }
 
-static int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
+static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 254b192..70a0b2a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1951,7 +1951,7 @@ static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl,
 	}
 }
 
-int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer,
+int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct net_device *dev = ctl->extra1;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 6d1d922..752327b 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -27,7 +27,7 @@
 #include <net/ipv6.h>
 
 #define MAX4(a, b, c, d) \
-	max_t(u32, max_t(u32, a, b), max_t(u32, c, d))
+	MAX_T(u32, MAX_T(u32, a, b), MAX_T(u32, c, d))
 #define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \
 			IPSTATS_MIB_MAX, ICMP_MIB_MAX)
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c752e9e..219701c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6334,7 +6334,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
 
 #ifdef CONFIG_SYSCTL
 
-static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
+static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index c060285..d2cd33e 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -30,7 +30,7 @@ static u32 rt6_multipath_hash_fields_all_mask =
 static u32 ioam6_id_max = IOAM6_DEFAULT_ID;
 static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE;
 
-static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
+static int proc_rt6_multipath_hash_policy(const struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net;
@@ -46,7 +46,7 @@ static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
 }
 
 static int
-proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer,
+proc_rt6_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer,
 			       size_t *lenp, loff_t *ppos)
 {
 	struct net *net;
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index b7bf34a..1e42e13 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -62,7 +62,7 @@
 #define IUCV_IPNORPY	0x10
 #define IUCV_IPALL	0x80
 
-static int iucv_bus_match(struct device *dev, struct device_driver *drv)
+static int iucv_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	return 0;
 }
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1c1decc..c80ab3f 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -441,14 +441,15 @@ int l2tp_session_register(struct l2tp_session *session,
 	int err;
 
 	spin_lock_bh(&tunnel->list_lock);
+	spin_lock_bh(&pn->l2tp_session_idr_lock);
+
 	if (!tunnel->acpt_newsess) {
 		err = -ENODEV;
-		goto err_tlock;
+		goto out;
 	}
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		session_key = session->session_id;
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL,
 				    &session_key, session_key, GFP_ATOMIC);
 		/* IP encap expects session IDs to be globally unique, while
@@ -462,43 +463,36 @@ int l2tp_session_register(struct l2tp_session *session,
 			err = l2tp_session_collision_add(pn, session,
 							 other_session);
 		}
-		spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	} else {
 		session_key = l2tp_v2_session_key(tunnel->tunnel_id,
 						  session->session_id);
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL,
 				    &session_key, session_key, GFP_ATOMIC);
-		spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	}
 
 	if (err) {
 		if (err == -ENOSPC)
 			err = -EEXIST;
-		goto err_tlock;
+		goto out;
 	}
 
 	l2tp_tunnel_inc_refcount(tunnel);
-
 	list_add(&session->list, &tunnel->session_list);
-	spin_unlock_bh(&tunnel->list_lock);
 
-	spin_lock_bh(&pn->l2tp_session_idr_lock);
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		if (!other_session)
 			idr_replace(&pn->l2tp_v3_session_idr, session, session_key);
 	} else {
 		idr_replace(&pn->l2tp_v2_session_idr, session, session_key);
 	}
+
+out:
 	spin_unlock_bh(&pn->l2tp_session_idr_lock);
-
-	trace_register_session(session);
-
-	return 0;
-
-err_tlock:
 	spin_unlock_bh(&tunnel->list_lock);
 
+	if (!err)
+		trace_register_session(session);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
@@ -1260,13 +1254,13 @@ static void l2tp_session_unhash(struct l2tp_session *session)
 		struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
 		struct l2tp_session *removed = session;
 
-		/* Remove from the per-tunnel list */
 		spin_lock_bh(&tunnel->list_lock);
+		spin_lock_bh(&pn->l2tp_session_idr_lock);
+
+		/* Remove from the per-tunnel list */
 		list_del_init(&session->list);
-		spin_unlock_bh(&tunnel->list_lock);
 
 		/* Remove from per-net IDR */
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		if (tunnel->version == L2TP_HDR_VER_3) {
 			if (hash_hashed(&session->hlist))
 				l2tp_session_collision_del(pn, session);
@@ -1280,7 +1274,9 @@ static void l2tp_session_unhash(struct l2tp_session *session)
 					     session_key);
 		}
 		WARN_ON_ONCE(removed && removed != session);
+
 		spin_unlock_bh(&pn->l2tp_session_idr_lock);
+		spin_unlock_bh(&tunnel->list_lock);
 
 		synchronize_rcu();
 	}
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 2dc7a90..0e6c94a 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1347,7 +1347,7 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb,
 #define MPLS_PERDEV_SYSCTL_OFFSET(field)	\
 	(&((struct mpls_dev *)0)->field)
 
-static int mpls_conf_proc(struct ctl_table *ctl, int write,
+static int mpls_conf_proc(const struct ctl_table *ctl, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int oval = *(int *)ctl->data;
@@ -2600,7 +2600,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	return -ENOMEM;
 }
 
-static int mpls_platform_labels(struct ctl_table *table, int write,
+static int mpls_platform_labels(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = table->data;
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 98b1dd4..99382c3 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -113,7 +113,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name)
 	return ret;
 }
 
-static int proc_scheduler(struct ctl_table *ctl, int write,
+static int proc_scheduler(const struct ctl_table *ctl, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	const struct net *net = current->nsproxy->net_ns;
@@ -133,7 +133,7 @@ static int proc_scheduler(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_available_schedulers(struct ctl_table *ctl,
+static int proc_available_schedulers(const struct ctl_table *ctl,
 				     int write, void *buffer,
 				     size_t *lenp, loff_t *ppos)
 {
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 706c2b5..dc6ddc4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1846,7 +1846,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs)
 #ifdef CONFIG_SYSCTL
 
 static int
-proc_do_defense_mode(struct ctl_table *table, int write,
+proc_do_defense_mode(const struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct netns_ipvs *ipvs = table->extra2;
@@ -1873,7 +1873,7 @@ proc_do_defense_mode(struct ctl_table *table, int write,
 }
 
 static int
-proc_do_sync_threshold(struct ctl_table *table, int write,
+proc_do_sync_threshold(const struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct netns_ipvs *ipvs = table->extra2;
@@ -1901,7 +1901,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write,
 }
 
 static int
-proc_do_sync_ports(struct ctl_table *table, int write,
+proc_do_sync_ports(const struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = table->data;
@@ -1984,7 +1984,7 @@ static int ipvs_proc_est_cpumask_get(const struct ctl_table *table,
 	return ret;
 }
 
-static int ipvs_proc_est_cpulist(struct ctl_table *table, int write,
+static int ipvs_proc_est_cpulist(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2011,7 +2011,7 @@ static int ipvs_proc_est_cpulist(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int ipvs_proc_est_nice(struct ctl_table *table, int write,
+static int ipvs_proc_est_nice(const struct ctl_table *table, int write,
 			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct netns_ipvs *ipvs = table->extra2;
@@ -2041,7 +2041,7 @@ static int ipvs_proc_est_nice(struct ctl_table *table, int write,
 	return ret;
 }
 
-static int ipvs_proc_run_estimation(struct ctl_table *table, int write,
+static int ipvs_proc_run_estimation(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct netns_ipvs *ipvs = table->extra2;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 6c40bdf..7d4f0fa 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -524,7 +524,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_count);
 static unsigned int nf_conntrack_htable_size_user __read_mostly;
 
 static int
-nf_conntrack_hash_sysctl(struct ctl_table *table, int write,
+nf_conntrack_hash_sysctl(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c
index d8ebebc..2d890dd 100644
--- a/net/netfilter/nf_hooks_lwtunnel.c
+++ b/net/netfilter/nf_hooks_lwtunnel.c
@@ -28,7 +28,7 @@ static inline int nf_hooks_lwtunnel_set(int enable)
 }
 
 #ifdef CONFIG_SYSCTL
-int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write,
+int nf_hooks_lwtunnel_sysctl_handler(const struct ctl_table *table, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int proc_nf_hooks_lwtunnel_enabled = 0;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 769fd76..6dd0de3 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -408,7 +408,7 @@ static struct ctl_table nf_log_sysctl_ftable[] = {
 	},
 };
 
-static int nf_log_proc_dostring(struct ctl_table *table, int write,
+static int nf_log_proc_dostring(const struct ctl_table *table, int write,
 			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	const struct nf_logger *logger;
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 8910a5a..b8d3c32 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1139,8 +1139,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	bool map_index;
 	int i, ret = 0;
 
-	if (unlikely(!irq_fpu_usable()))
-		return nft_pipapo_lookup(net, set, key, ext);
+	local_bh_disable();
+
+	if (unlikely(!irq_fpu_usable())) {
+		bool fallback_res = nft_pipapo_lookup(net, set, key, ext);
+
+		local_bh_enable();
+		return fallback_res;
+	}
 
 	m = rcu_dereference(priv->match);
 
@@ -1155,6 +1161,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	scratch = *raw_cpu_ptr(m->scratch);
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
+		local_bh_enable();
 		return false;
 	}
 
@@ -1235,6 +1242,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	if (i % 2)
 		scratch->map_index = !map_index;
 	kernel_fpu_end();
+	local_bh_enable();
 
 	return ret >= 0;
 }
diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c
index 82fc224..463a74a 100644
--- a/net/phonet/sysctl.c
+++ b/net/phonet/sysctl.c
@@ -48,7 +48,7 @@ void phonet_get_local_port_range(int *min, int *max)
 	} while (read_seqretry(&local_port_range_lock, seq));
 }
 
-static int proc_local_port_range(struct ctl_table *table, int write,
+static int proc_local_port_range(const struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 3dc6956..351ac17 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -61,7 +61,7 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0);
 
 static struct kmem_cache *rds_tcp_conn_slab;
 
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
+static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *fpos);
 
 static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
@@ -682,7 +682,7 @@ static void rds_tcp_sysctl_reset(struct net *net)
 	spin_unlock_irq(&rds_tcp_conn_lock);
 }
 
-static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
+static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *fpos)
 {
 	struct net *net = current->nsproxy->net_ns;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 61c6f30..e5a5af3 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -43,19 +43,19 @@ static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
 	? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
 
-static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
+static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
+static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer,
+static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer,
 				size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer,
+static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer,
 				 size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos);
-static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos);
 
 static struct ctl_table sctp_table[] = {
@@ -384,7 +384,7 @@ static struct ctl_table sctp_net_table[] = {
 	},
 };
 
-static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
+static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -429,7 +429,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
+static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -457,7 +457,7 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
+static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -485,7 +485,7 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (write)
@@ -495,7 +495,7 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
 	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
 }
 
-static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -524,7 +524,7 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
+static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -565,7 +565,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
 	return ret;
 }
 
-static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write,
+static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index 5f3170a..bdb587a 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(nlm_debug);
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 
-static int proc_do_xprt(struct ctl_table *table, int write,
+static int proc_do_xprt(const struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char tmpbuf[256];
@@ -62,7 +62,7 @@ static int proc_do_xprt(struct ctl_table *table, int write,
 }
 
 static int
-proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp,
+proc_dodebug(const struct ctl_table *table, int write, void *buffer, size_t *lenp,
 	     loff_t *ppos)
 {
 	char		tmpbuf[20], *s = NULL;
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 474f7a9..58ae6ec 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -74,7 +74,7 @@ enum {
 	SVCRDMA_COUNTER_BUFSIZ	= sizeof(unsigned long long),
 };
 
-static int svcrdma_counter_handler(struct ctl_table *table, int write,
+static int svcrdma_counter_handler(const struct ctl_table *table, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct percpu_counter *stat = (struct percpu_counter *)table->data;
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index b849a3d..439f755 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -135,8 +135,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
 		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
 	else if (ntohs(ua->proto) == ETH_P_IPV6)
 		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
-	else
+	else {
 		pr_err("Invalid UDP media address\n");
+		return 1;
+	}
+
 	return 0;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b0a4c6d..0be0dcb 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2721,10 +2721,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
+	struct unix_sock *u = unix_sk(sk);
+	struct sk_buff *skb;
+	int err;
+
 	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
-	return unix_read_skb(sk, recv_actor);
+	mutex_lock(&u->iolock);
+	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
+	mutex_unlock(&u->iolock);
+	if (!skb)
+		return err;
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (unlikely(skb == READ_ONCE(u->oob_skb))) {
+		bool drop = false;
+
+		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD)) {
+			unix_state_unlock(sk);
+			kfree_skb(skb);
+			return -ECONNRESET;
+		}
+
+		spin_lock(&sk->sk_receive_queue.lock);
+		if (likely(skb == u->oob_skb)) {
+			WRITE_ONCE(u->oob_skb, NULL);
+			drop = true;
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		unix_state_unlock(sk);
+
+		if (drop) {
+			WARN_ON_ONCE(skb_unref(skb));
+			kfree_skb(skb);
+			return -EAGAIN;
+		}
+	}
+#endif
+
+	return recv_actor(sk, skb);
 }
 
 static int unix_stream_read_generic(struct unix_stream_read_state *state,
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index bd84785..bca2d86 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 	struct sk_psock *psock;
 	int copied;
 
+	if (flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
 	if (!len)
 		return 0;
 
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index caa3401..9f76ca5 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 #define XDP_UMEM_FLAGS_VALID ( \
 		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
 		XDP_UMEM_TX_SW_CSUM | \
+		XDP_UMEM_TX_METADATA_LEN | \
 	0)
 
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
@@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
-	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
-		return -EINVAL;
+	if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
+		if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+			return -EINVAL;
+		umem->tx_metadata_len = mr->tx_metadata_len;
+	}
 
 	umem->size = size;
 	umem->headroom = headroom;
@@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
diff --git a/rust/Makefile b/rust/Makefile
index f70d5e2..1f10f92 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -44,17 +44,10 @@
 rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2)
 RUST_LIB_SRC ?= $(rustc_sysroot)/lib/rustlib/src/rust/library
 
-ifeq ($(quiet),silent_)
-cargo_quiet=-q
+ifneq ($(quiet),)
 rust_test_quiet=-q
 rustdoc_test_quiet=--test-args -q
 rustdoc_test_kernel_quiet=>/dev/null
-else ifeq ($(quiet),quiet_)
-rust_test_quiet=-q
-rustdoc_test_quiet=--test-args -q
-rustdoc_test_kernel_quiet=>/dev/null
-else
-cargo_quiet=--verbose
 endif
 
 core-cfgs = \
@@ -135,22 +128,21 @@
 		@$(objtree)/include/generated/rustc_cfg $(rustc_target_flags) \
 		--crate-type $(if $(rustc_test_library_proc),proc-macro,rlib) \
 		--out-dir $(objtree)/$(obj)/test --cfg testlib \
-		--sysroot $(objtree)/$(obj)/test/sysroot \
 		-L$(objtree)/$(obj)/test \
 		--crate-name $(subst rusttest-,,$(subst rusttestlib-,,$@)) $<
 
-rusttestlib-build_error: $(src)/build_error.rs rusttest-prepare FORCE
+rusttestlib-build_error: $(src)/build_error.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
 rusttestlib-macros: private rustc_target_flags = --extern proc_macro
 rusttestlib-macros: private rustc_test_library_proc = yes
-rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
+rusttestlib-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
-rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE
+rusttestlib-bindings: $(src)/bindings/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
-rusttestlib-uapi: $(src)/uapi/lib.rs rusttest-prepare FORCE
+rusttestlib-uapi: $(src)/uapi/lib.rs FORCE
 	+$(call if_changed,rustc_test_library)
 
 quiet_cmd_rustdoc_test = RUSTDOC T $<
@@ -159,7 +151,7 @@
 	$(RUSTDOC) --test $(rust_common_flags) \
 		@$(objtree)/include/generated/rustc_cfg \
 		$(rustc_target_flags) $(rustdoc_test_target_flags) \
-		--sysroot $(objtree)/$(obj)/test/sysroot $(rustdoc_test_quiet) \
+		$(rustdoc_test_quiet) \
 		-L$(objtree)/$(obj)/test --output $(rustdoc_output) \
 		--crate-name $(subst rusttest-,,$@) $<
 
@@ -192,7 +184,6 @@
 	$(RUSTC) --test $(rust_common_flags) \
 		@$(objtree)/include/generated/rustc_cfg \
 		$(rustc_target_flags) --out-dir $(objtree)/$(obj)/test \
-		--sysroot $(objtree)/$(obj)/test/sysroot \
 		-L$(objtree)/$(obj)/test \
 		--crate-name $(subst rusttest-,,$@) $<; \
 	$(objtree)/$(obj)/test/$(subst rusttest-,,$@) $(rust_test_quiet) \
@@ -200,60 +191,15 @@
 
 rusttest: rusttest-macros rusttest-kernel
 
-# This prepares a custom sysroot with our custom `alloc` instead of
-# the standard one.
-#
-# This requires several hacks:
-#   - Unlike `core` and `alloc`, `std` depends on more than a dozen crates,
-#     including third-party crates that need to be downloaded, plus custom
-#     `build.rs` steps. Thus hardcoding things here is not maintainable.
-#   - `cargo` knows how to build the standard library, but it is an unstable
-#     feature so far (`-Zbuild-std`).
-#   - `cargo` only considers the use case of building the standard library
-#     to use it in a given package. Thus we need to create a dummy package
-#     and pick the generated libraries from there.
-#   - The usual ways of modifying the dependency graph in `cargo` do not seem
-#     to apply for the `-Zbuild-std` steps, thus we have to mislead it
-#     by modifying the sources in the sysroot.
-#   - To avoid messing with the user's Rust installation, we create a clone
-#     of the sysroot. However, `cargo` ignores `RUSTFLAGS` in the `-Zbuild-std`
-#     steps, thus we use a wrapper binary passed via `RUSTC` to pass the flag.
-#
-# In the future, we hope to avoid the whole ordeal by either:
-#   - Making the `test` crate not depend on `std` (either improving upstream
-#     or having our own custom crate).
-#   - Making the tests run in kernel space (requires the previous point).
-#   - Making `std` and friends be more like a "normal" crate, so that
-#     `-Zbuild-std` and related hacks are not needed.
-quiet_cmd_rustsysroot = RUSTSYSROOT
-      cmd_rustsysroot = \
-	rm -rf $(objtree)/$(obj)/test; \
-	mkdir -p $(objtree)/$(obj)/test; \
-	cp -a $(rustc_sysroot) $(objtree)/$(obj)/test/sysroot; \
-	echo '\#!/bin/sh' > $(objtree)/$(obj)/test/rustc_sysroot; \
-	echo "$(RUSTC) --sysroot=$(abspath $(objtree)/$(obj)/test/sysroot) \"\$$@\"" \
-		>> $(objtree)/$(obj)/test/rustc_sysroot; \
-	chmod u+x $(objtree)/$(obj)/test/rustc_sysroot; \
-	$(CARGO) -q new $(objtree)/$(obj)/test/dummy; \
-	RUSTC=$(objtree)/$(obj)/test/rustc_sysroot $(CARGO) $(cargo_quiet) \
-		test -Zbuild-std --target $(rustc_host_target) \
-		--manifest-path $(objtree)/$(obj)/test/dummy/Cargo.toml; \
-	rm $(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib/*; \
-	cp $(objtree)/$(obj)/test/dummy/target/$(rustc_host_target)/debug/deps/* \
-		$(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib
-
-rusttest-prepare: FORCE
-	+$(call if_changed,rustsysroot)
-
 rusttest-macros: private rustc_target_flags = --extern proc_macro
 rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro
-rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
+rusttest-macros: $(src)/macros/lib.rs FORCE
 	+$(call if_changed,rustc_test)
 	+$(call if_changed,rustdoc_test)
 
 rusttest-kernel: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros --extern bindings --extern uapi
-rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \
+rusttest-kernel: $(src)/kernel/lib.rs \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
     rusttestlib-uapi FORCE
 	+$(call if_changed,rustc_test)
@@ -421,12 +367,12 @@
 endif
 
 $(obj)/core.o: private skip_clippy = 1
-$(obj)/core.o: private skip_flags = -Dunreachable_pub
+$(obj)/core.o: private skip_flags = -Wunreachable_pub
 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym))
 $(obj)/core.o: private rustc_target_flags = $(core-cfgs)
 $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
 	+$(call if_changed_dep,rustc_library)
-ifdef CONFIG_X86_64
+ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),)
 $(obj)/core.o: scripts/target.json
 endif
 
@@ -435,7 +381,7 @@
 	+$(call if_changed_dep,rustc_library)
 
 $(obj)/alloc.o: private skip_clippy = 1
-$(obj)/alloc.o: private skip_flags = -Dunreachable_pub
+$(obj)/alloc.o: private skip_flags = -Wunreachable_pub
 $(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs)
 $(obj)/alloc.o: $(RUST_LIB_SRC)/alloc/src/lib.rs $(obj)/compiler_builtins.o FORCE
 	+$(call if_changed_dep,rustc_library)
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 6deee85a..b940a57 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -12,6 +12,7 @@
 #include <linux/blkdev.h>
 #include <linux/errname.h>
 #include <linux/ethtool.h>
+#include <linux/firmware.h>
 #include <linux/jiffies.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
@@ -29,4 +30,5 @@ const gfp_t RUST_CONST_HELPER_GFP_KERNEL = GFP_KERNEL;
 const gfp_t RUST_CONST_HELPER_GFP_KERNEL_ACCOUNT = GFP_KERNEL_ACCOUNT;
 const gfp_t RUST_CONST_HELPER_GFP_NOWAIT = GFP_NOWAIT;
 const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO;
+const gfp_t RUST_CONST_HELPER___GFP_HIGHMEM = ___GFP_HIGHMEM;
 const blk_features_t RUST_CONST_HELPER_BLK_FEAT_ROTATIONAL = BLK_FEAT_ROTATIONAL;
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
index 40ddaee..93a1a3fc 100644
--- a/rust/bindings/lib.rs
+++ b/rust/bindings/lib.rs
@@ -24,6 +24,7 @@
     unsafe_op_in_unsafe_fn
 )]
 
+#[allow(dead_code)]
 mod bindings_raw {
     // Use glob import here to expose all helpers.
     // Symbols defined within the module will take precedence to the glob import.
diff --git a/rust/helpers.c b/rust/helpers.c
index 3df5217..92d3c03 100644
--- a/rust/helpers.c
+++ b/rust/helpers.c
@@ -23,8 +23,11 @@
 #include <kunit/test-bug.h>
 #include <linux/bug.h>
 #include <linux/build_bug.h>
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/errname.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
 #include <linux/mutex.h>
 #include <linux/refcount.h>
 #include <linux/sched/signal.h>
@@ -39,6 +42,20 @@ __noreturn void rust_helper_BUG(void)
 }
 EXPORT_SYMBOL_GPL(rust_helper_BUG);
 
+unsigned long rust_helper_copy_from_user(void *to, const void __user *from,
+					 unsigned long n)
+{
+	return copy_from_user(to, from, n);
+}
+EXPORT_SYMBOL_GPL(rust_helper_copy_from_user);
+
+unsigned long rust_helper_copy_to_user(void __user *to, const void *from,
+				       unsigned long n)
+{
+	return copy_to_user(to, from, n);
+}
+EXPORT_SYMBOL_GPL(rust_helper_copy_to_user);
+
 void rust_helper_mutex_lock(struct mutex *lock)
 {
 	mutex_lock(lock);
@@ -80,6 +97,24 @@ int rust_helper_signal_pending(struct task_struct *t)
 }
 EXPORT_SYMBOL_GPL(rust_helper_signal_pending);
 
+struct page *rust_helper_alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+	return alloc_pages(gfp_mask, order);
+}
+EXPORT_SYMBOL_GPL(rust_helper_alloc_pages);
+
+void *rust_helper_kmap_local_page(struct page *page)
+{
+	return kmap_local_page(page);
+}
+EXPORT_SYMBOL_GPL(rust_helper_kmap_local_page);
+
+void rust_helper_kunmap_local(const void *addr)
+{
+	kunmap_local(addr);
+}
+EXPORT_SYMBOL_GPL(rust_helper_kunmap_local);
+
 refcount_t rust_helper_REFCOUNT_INIT(int n)
 {
 	return (refcount_t)REFCOUNT_INIT(n);
diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index 531b5e4..1966bd4 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -20,6 +20,13 @@
 #[derive(Clone, Copy)]
 pub struct Flags(u32);
 
+impl Flags {
+    /// Get the raw representation of this flag.
+    pub(crate) fn as_raw(self) -> u32 {
+        self.0
+    }
+}
+
 impl core::ops::BitOr for Flags {
     type Output = Self;
     fn bitor(self, rhs: Self) -> Self::Output {
@@ -52,6 +59,14 @@ pub mod flags {
     /// This is normally or'd with other flags.
     pub const __GFP_ZERO: Flags = Flags(bindings::__GFP_ZERO);
 
+    /// Allow the allocation to be in high memory.
+    ///
+    /// Allocations in high memory may not be mapped into the kernel's address space, so this can't
+    /// be used with `kmalloc` and other similar methods.
+    ///
+    /// This is normally or'd with other flags.
+    pub const __GFP_HIGHMEM: Flags = Flags(bindings::__GFP_HIGHMEM);
+
     /// Users can not sleep and need the allocation to succeed.
     ///
     /// A lower watermark is applied to allow access to "atomic reserves". The current
@@ -66,7 +81,7 @@ pub mod flags {
     /// The same as [`GFP_KERNEL`], except the allocation is accounted to kmemcg.
     pub const GFP_KERNEL_ACCOUNT: Flags = Flags(bindings::GFP_KERNEL_ACCOUNT);
 
-    /// Ror kernel allocations that should not stall for direct reclaim, start physical IO or
+    /// For kernel allocations that should not stall for direct reclaim, start physical IO or
     /// use any filesystem callback.  It is very likely to fail to allocate memory, even for very
     /// small allocations.
     pub const GFP_NOWAIT: Flags = Flags(bindings::GFP_NOWAIT);
diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
new file mode 100644
index 0000000..851018e
--- /dev/null
+++ b/rust/kernel/device.rs
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Generic devices that are part of the kernel's driver model.
+//!
+//! C header: [`include/linux/device.h`](srctree/include/linux/device.h)
+
+use crate::{
+    bindings,
+    types::{ARef, Opaque},
+};
+use core::ptr;
+
+/// A reference-counted device.
+///
+/// This structure represents the Rust abstraction for a C `struct device`. This implementation
+/// abstracts the usage of an already existing C `struct device` within Rust code that we get
+/// passed from the C side.
+///
+/// An instance of this abstraction can be obtained temporarily or permanent.
+///
+/// A temporary one is bound to the lifetime of the C `struct device` pointer used for creation.
+/// A permanent instance is always reference-counted and hence not restricted by any lifetime
+/// boundaries.
+///
+/// For subsystems it is recommended to create a permanent instance to wrap into a subsystem
+/// specific device structure (e.g. `pci::Device`). This is useful for passing it to drivers in
+/// `T::probe()`, such that a driver can store the `ARef<Device>` (equivalent to storing a
+/// `struct device` pointer in a C driver) for arbitrary purposes, e.g. allocating DMA coherent
+/// memory.
+///
+/// # Invariants
+///
+/// A `Device` instance represents a valid `struct device` created by the C portion of the kernel.
+///
+/// Instances of this type are always reference-counted, that is, a call to `get_device` ensures
+/// that the allocation remains valid at least until the matching call to `put_device`.
+///
+/// `bindings::device::release` is valid to be called from any thread, hence `ARef<Device>` can be
+/// dropped from any thread.
+#[repr(transparent)]
+pub struct Device(Opaque<bindings::device>);
+
+impl Device {
+    /// Creates a new reference-counted abstraction instance of an existing `struct device` pointer.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that `ptr` is valid, non-null, and has a non-zero reference count,
+    /// i.e. it must be ensured that the reference count of the C `struct device` `ptr` points to
+    /// can't drop to zero, for the duration of this function call.
+    ///
+    /// It must also be ensured that `bindings::device::release` can be called from any thread.
+    /// While not officially documented, this should be the case for any `struct device`.
+    pub unsafe fn from_raw(ptr: *mut bindings::device) -> ARef<Self> {
+        // SAFETY: By the safety requirements, ptr is valid.
+        // Initially increase the reference count by one to compensate for the final decrement once
+        // this newly created `ARef<Device>` instance is dropped.
+        unsafe { bindings::get_device(ptr) };
+
+        // CAST: `Self` is a `repr(transparent)` wrapper around `bindings::device`.
+        let ptr = ptr.cast::<Self>();
+
+        // SAFETY: `ptr` is valid by the safety requirements of this function. By the above call to
+        // `bindings::get_device` we also own a reference to the underlying `struct device`.
+        unsafe { ARef::from_raw(ptr::NonNull::new_unchecked(ptr)) }
+    }
+
+    /// Obtain the raw `struct device *`.
+    pub(crate) fn as_raw(&self) -> *mut bindings::device {
+        self.0.get()
+    }
+
+    /// Convert a raw C `struct device` pointer to a `&'a Device`.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that `ptr` is valid, non-null, and has a non-zero reference count,
+    /// i.e. it must be ensured that the reference count of the C `struct device` `ptr` points to
+    /// can't drop to zero, for the duration of this function call and the entire duration when the
+    /// returned reference exists.
+    pub unsafe fn as_ref<'a>(ptr: *mut bindings::device) -> &'a Self {
+        // SAFETY: Guaranteed by the safety requirements of the function.
+        unsafe { &*ptr.cast() }
+    }
+}
+
+// SAFETY: Instances of `Device` are always reference-counted.
+unsafe impl crate::types::AlwaysRefCounted for Device {
+    fn inc_ref(&self) {
+        // SAFETY: The existence of a shared reference guarantees that the refcount is non-zero.
+        unsafe { bindings::get_device(self.as_raw()) };
+    }
+
+    unsafe fn dec_ref(obj: ptr::NonNull<Self>) {
+        // SAFETY: The safety requirements guarantee that the refcount is non-zero.
+        unsafe { bindings::put_device(obj.cast().as_ptr()) }
+    }
+}
+
+// SAFETY: As by the type invariant `Device` can be sent to any thread.
+unsafe impl Send for Device {}
+
+// SAFETY: `Device` can be shared among threads because all immutable methods are protected by the
+// synchronization in `struct device`.
+unsafe impl Sync for Device {}
diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs
new file mode 100644
index 0000000..2ba03af
--- /dev/null
+++ b/rust/kernel/firmware.rs
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Firmware abstraction
+//!
+//! C header: [`include/linux/firmware.h`](srctree/include/linux/firmware.h")
+
+use crate::{bindings, device::Device, error::Error, error::Result, str::CStr};
+use core::ptr::NonNull;
+
+/// # Invariants
+///
+/// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`,
+/// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`.
+struct FwFunc(
+    unsafe extern "C" fn(*mut *const bindings::firmware, *const i8, *mut bindings::device) -> i32,
+);
+
+impl FwFunc {
+    fn request() -> Self {
+        Self(bindings::request_firmware)
+    }
+
+    fn request_nowarn() -> Self {
+        Self(bindings::firmware_request_nowarn)
+    }
+}
+
+/// Abstraction around a C `struct firmware`.
+///
+/// This is a simple abstraction around the C firmware API. Just like with the C API, firmware can
+/// be requested. Once requested the abstraction provides direct access to the firmware buffer as
+/// `&[u8]`. The firmware is released once [`Firmware`] is dropped.
+///
+/// # Invariants
+///
+/// The pointer is valid, and has ownership over the instance of `struct firmware`.
+///
+/// The `Firmware`'s backing buffer is not modified.
+///
+/// # Examples
+///
+/// ```no_run
+/// # use kernel::{c_str, device::Device, firmware::Firmware};
+///
+/// # fn no_run() -> Result<(), Error> {
+/// # // SAFETY: *NOT* safe, just for the example to get an `ARef<Device>` instance
+/// # let dev = unsafe { Device::from_raw(core::ptr::null_mut()) };
+///
+/// let fw = Firmware::request(c_str!("path/to/firmware.bin"), &dev)?;
+/// let blob = fw.data();
+///
+/// # Ok(())
+/// # }
+/// ```
+pub struct Firmware(NonNull<bindings::firmware>);
+
+impl Firmware {
+    fn request_internal(name: &CStr, dev: &Device, func: FwFunc) -> Result<Self> {
+        let mut fw: *mut bindings::firmware = core::ptr::null_mut();
+        let pfw: *mut *mut bindings::firmware = &mut fw;
+
+        // SAFETY: `pfw` is a valid pointer to a NULL initialized `bindings::firmware` pointer.
+        // `name` and `dev` are valid as by their type invariants.
+        let ret = unsafe { func.0(pfw as _, name.as_char_ptr(), dev.as_raw()) };
+        if ret != 0 {
+            return Err(Error::from_errno(ret));
+        }
+
+        // SAFETY: `func` not bailing out with a non-zero error code, guarantees that `fw` is a
+        // valid pointer to `bindings::firmware`.
+        Ok(Firmware(unsafe { NonNull::new_unchecked(fw) }))
+    }
+
+    /// Send a firmware request and wait for it. See also `bindings::request_firmware`.
+    pub fn request(name: &CStr, dev: &Device) -> Result<Self> {
+        Self::request_internal(name, dev, FwFunc::request())
+    }
+
+    /// Send a request for an optional firmware module. See also
+    /// `bindings::firmware_request_nowarn`.
+    pub fn request_nowarn(name: &CStr, dev: &Device) -> Result<Self> {
+        Self::request_internal(name, dev, FwFunc::request_nowarn())
+    }
+
+    fn as_raw(&self) -> *mut bindings::firmware {
+        self.0.as_ptr()
+    }
+
+    /// Returns the size of the requested firmware in bytes.
+    pub fn size(&self) -> usize {
+        // SAFETY: `self.as_raw()` is valid by the type invariant.
+        unsafe { (*self.as_raw()).size }
+    }
+
+    /// Returns the requested firmware as `&[u8]`.
+    pub fn data(&self) -> &[u8] {
+        // SAFETY: `self.as_raw()` is valid by the type invariant. Additionally,
+        // `bindings::firmware` guarantees, if successfully requested, that
+        // `bindings::firmware::data` has a size of `bindings::firmware::size` bytes.
+        unsafe { core::slice::from_raw_parts((*self.as_raw()).data, self.size()) }
+    }
+}
+
+impl Drop for Firmware {
+    fn drop(&mut self) {
+        // SAFETY: `self.as_raw()` is valid by the type invariant.
+        unsafe { bindings::release_firmware(self.as_raw()) };
+    }
+}
+
+// SAFETY: `Firmware` only holds a pointer to a C `struct firmware`, which is safe to be used from
+// any thread.
+unsafe impl Send for Firmware {}
+
+// SAFETY: `Firmware` only holds a pointer to a C `struct firmware`, references to which are safe to
+// be used from any thread.
+unsafe impl Sync for Firmware {}
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 68605b6..495c09e 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -843,11 +843,8 @@ unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E> {
         let val = unsafe { &mut *slot };
         // SAFETY: `slot` is considered pinned.
         let val = unsafe { Pin::new_unchecked(val) };
-        (self.1)(val).map_err(|e| {
-            // SAFETY: `slot` was initialized above.
-            unsafe { core::ptr::drop_in_place(slot) };
-            e
-        })
+        // SAFETY: `slot` was initialized above.
+        (self.1)(val).inspect_err(|_| unsafe { core::ptr::drop_in_place(slot) })
     }
 }
 
@@ -941,11 +938,9 @@ unsafe fn __init(self, slot: *mut T) -> Result<(), E> {
         // SAFETY: All requirements fulfilled since this function is `__init`.
         unsafe { self.0.__pinned_init(slot)? };
         // SAFETY: The above call initialized `slot` and we still have unique access.
-        (self.1)(unsafe { &mut *slot }).map_err(|e| {
+        (self.1)(unsafe { &mut *slot }).inspect_err(|_|
             // SAFETY: `slot` was initialized above.
-            unsafe { core::ptr::drop_in_place(slot) };
-            e
-        })
+            unsafe { core::ptr::drop_in_place(slot) })
     }
 }
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 2cf7c6b..274bdc1 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -30,13 +30,17 @@
 #[cfg(CONFIG_BLOCK)]
 pub mod block;
 mod build_assert;
+pub mod device;
 pub mod error;
+#[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)]
+pub mod firmware;
 pub mod init;
 pub mod ioctl;
 #[cfg(CONFIG_KUNIT)]
 pub mod kunit;
 #[cfg(CONFIG_NET)]
 pub mod net;
+pub mod page;
 pub mod prelude;
 pub mod print;
 mod static_assert;
@@ -47,6 +51,7 @@
 pub mod task;
 pub mod time;
 pub mod types;
+pub mod uaccess;
 pub mod workqueue;
 
 #[doc(hidden)]
diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs
new file mode 100644
index 0000000..208a006
--- /dev/null
+++ b/rust/kernel/page.rs
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Kernel page allocation and management.
+
+use crate::{
+    alloc::{AllocError, Flags},
+    bindings,
+    error::code::*,
+    error::Result,
+    uaccess::UserSliceReader,
+};
+use core::ptr::{self, NonNull};
+
+/// A bitwise shift for the page size.
+pub const PAGE_SHIFT: usize = bindings::PAGE_SHIFT as usize;
+
+/// The number of bytes in a page.
+pub const PAGE_SIZE: usize = bindings::PAGE_SIZE;
+
+/// A bitmask that gives the page containing a given address.
+pub const PAGE_MASK: usize = !(PAGE_SIZE - 1);
+
+/// A pointer to a page that owns the page allocation.
+///
+/// # Invariants
+///
+/// The pointer is valid, and has ownership over the page.
+pub struct Page {
+    page: NonNull<bindings::page>,
+}
+
+// SAFETY: Pages have no logic that relies on them staying on a given thread, so moving them across
+// threads is safe.
+unsafe impl Send for Page {}
+
+// SAFETY: Pages have no logic that relies on them not being accessed concurrently, so accessing
+// them concurrently is safe.
+unsafe impl Sync for Page {}
+
+impl Page {
+    /// Allocates a new page.
+    ///
+    /// # Examples
+    ///
+    /// Allocate memory for a page.
+    ///
+    /// ```
+    /// use kernel::page::Page;
+    ///
+    /// # fn dox() -> Result<(), kernel::alloc::AllocError> {
+    /// let page = Page::alloc_page(GFP_KERNEL)?;
+    /// # Ok(()) }
+    /// ```
+    ///
+    /// Allocate memory for a page and zero its contents.
+    ///
+    /// ```
+    /// use kernel::page::Page;
+    ///
+    /// # fn dox() -> Result<(), kernel::alloc::AllocError> {
+    /// let page = Page::alloc_page(GFP_KERNEL | __GFP_ZERO)?;
+    /// # Ok(()) }
+    /// ```
+    pub fn alloc_page(flags: Flags) -> Result<Self, AllocError> {
+        // SAFETY: Depending on the value of `gfp_flags`, this call may sleep. Other than that, it
+        // is always safe to call this method.
+        let page = unsafe { bindings::alloc_pages(flags.as_raw(), 0) };
+        let page = NonNull::new(page).ok_or(AllocError)?;
+        // INVARIANT: We just successfully allocated a page, so we now have ownership of the newly
+        // allocated page. We transfer that ownership to the new `Page` object.
+        Ok(Self { page })
+    }
+
+    /// Returns a raw pointer to the page.
+    pub fn as_ptr(&self) -> *mut bindings::page {
+        self.page.as_ptr()
+    }
+
+    /// Runs a piece of code with this page mapped to an address.
+    ///
+    /// The page is unmapped when this call returns.
+    ///
+    /// # Using the raw pointer
+    ///
+    /// It is up to the caller to use the provided raw pointer correctly. The pointer is valid for
+    /// `PAGE_SIZE` bytes and for the duration in which the closure is called. The pointer might
+    /// only be mapped on the current thread, and when that is the case, dereferencing it on other
+    /// threads is UB. Other than that, the usual rules for dereferencing a raw pointer apply: don't
+    /// cause data races, the memory may be uninitialized, and so on.
+    ///
+    /// If multiple threads map the same page at the same time, then they may reference with
+    /// different addresses. However, even if the addresses are different, the underlying memory is
+    /// still the same for these purposes (e.g., it's still a data race if they both write to the
+    /// same underlying byte at the same time).
+    fn with_page_mapped<T>(&self, f: impl FnOnce(*mut u8) -> T) -> T {
+        // SAFETY: `page` is valid due to the type invariants on `Page`.
+        let mapped_addr = unsafe { bindings::kmap_local_page(self.as_ptr()) };
+
+        let res = f(mapped_addr.cast());
+
+        // This unmaps the page mapped above.
+        //
+        // SAFETY: Since this API takes the user code as a closure, it can only be used in a manner
+        // where the pages are unmapped in reverse order. This is as required by `kunmap_local`.
+        //
+        // In other words, if this call to `kunmap_local` happens when a different page should be
+        // unmapped first, then there must necessarily be a call to `kmap_local_page` other than the
+        // call just above in `with_page_mapped` that made that possible. In this case, it is the
+        // unsafe block that wraps that other call that is incorrect.
+        unsafe { bindings::kunmap_local(mapped_addr) };
+
+        res
+    }
+
+    /// Runs a piece of code with a raw pointer to a slice of this page, with bounds checking.
+    ///
+    /// If `f` is called, then it will be called with a pointer that points at `off` bytes into the
+    /// page, and the pointer will be valid for at least `len` bytes. The pointer is only valid on
+    /// this task, as this method uses a local mapping.
+    ///
+    /// If `off` and `len` refers to a region outside of this page, then this method returns
+    /// [`EINVAL`] and does not call `f`.
+    ///
+    /// # Using the raw pointer
+    ///
+    /// It is up to the caller to use the provided raw pointer correctly. The pointer is valid for
+    /// `len` bytes and for the duration in which the closure is called. The pointer might only be
+    /// mapped on the current thread, and when that is the case, dereferencing it on other threads
+    /// is UB. Other than that, the usual rules for dereferencing a raw pointer apply: don't cause
+    /// data races, the memory may be uninitialized, and so on.
+    ///
+    /// If multiple threads map the same page at the same time, then they may reference with
+    /// different addresses. However, even if the addresses are different, the underlying memory is
+    /// still the same for these purposes (e.g., it's still a data race if they both write to the
+    /// same underlying byte at the same time).
+    fn with_pointer_into_page<T>(
+        &self,
+        off: usize,
+        len: usize,
+        f: impl FnOnce(*mut u8) -> Result<T>,
+    ) -> Result<T> {
+        let bounds_ok = off <= PAGE_SIZE && len <= PAGE_SIZE && (off + len) <= PAGE_SIZE;
+
+        if bounds_ok {
+            self.with_page_mapped(move |page_addr| {
+                // SAFETY: The `off` integer is at most `PAGE_SIZE`, so this pointer offset will
+                // result in a pointer that is in bounds or one off the end of the page.
+                f(unsafe { page_addr.add(off) })
+            })
+        } else {
+            Err(EINVAL)
+        }
+    }
+
+    /// Maps the page and reads from it into the given buffer.
+    ///
+    /// This method will perform bounds checks on the page offset. If `offset .. offset+len` goes
+    /// outside of the page, then this call returns [`EINVAL`].
+    ///
+    /// # Safety
+    ///
+    /// * Callers must ensure that `dst` is valid for writing `len` bytes.
+    /// * Callers must ensure that this call does not race with a write to the same page that
+    ///   overlaps with this read.
+    pub unsafe fn read_raw(&self, dst: *mut u8, offset: usize, len: usize) -> Result {
+        self.with_pointer_into_page(offset, len, move |src| {
+            // SAFETY: If `with_pointer_into_page` calls into this closure, then
+            // it has performed a bounds check and guarantees that `src` is
+            // valid for `len` bytes.
+            //
+            // There caller guarantees that there is no data race.
+            unsafe { ptr::copy_nonoverlapping(src, dst, len) };
+            Ok(())
+        })
+    }
+
+    /// Maps the page and writes into it from the given buffer.
+    ///
+    /// This method will perform bounds checks on the page offset. If `offset .. offset+len` goes
+    /// outside of the page, then this call returns [`EINVAL`].
+    ///
+    /// # Safety
+    ///
+    /// * Callers must ensure that `src` is valid for reading `len` bytes.
+    /// * Callers must ensure that this call does not race with a read or write to the same page
+    ///   that overlaps with this write.
+    pub unsafe fn write_raw(&self, src: *const u8, offset: usize, len: usize) -> Result {
+        self.with_pointer_into_page(offset, len, move |dst| {
+            // SAFETY: If `with_pointer_into_page` calls into this closure, then it has performed a
+            // bounds check and guarantees that `dst` is valid for `len` bytes.
+            //
+            // There caller guarantees that there is no data race.
+            unsafe { ptr::copy_nonoverlapping(src, dst, len) };
+            Ok(())
+        })
+    }
+
+    /// Maps the page and zeroes the given slice.
+    ///
+    /// This method will perform bounds checks on the page offset. If `offset .. offset+len` goes
+    /// outside of the page, then this call returns [`EINVAL`].
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that this call does not race with a read or write to the same page that
+    /// overlaps with this write.
+    pub unsafe fn fill_zero_raw(&self, offset: usize, len: usize) -> Result {
+        self.with_pointer_into_page(offset, len, move |dst| {
+            // SAFETY: If `with_pointer_into_page` calls into this closure, then it has performed a
+            // bounds check and guarantees that `dst` is valid for `len` bytes.
+            //
+            // There caller guarantees that there is no data race.
+            unsafe { ptr::write_bytes(dst, 0u8, len) };
+            Ok(())
+        })
+    }
+
+    /// Copies data from userspace into this page.
+    ///
+    /// This method will perform bounds checks on the page offset. If `offset .. offset+len` goes
+    /// outside of the page, then this call returns [`EINVAL`].
+    ///
+    /// Like the other `UserSliceReader` methods, data races are allowed on the userspace address.
+    /// However, they are not allowed on the page you are copying into.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that this call does not race with a read or write to the same page that
+    /// overlaps with this write.
+    pub unsafe fn copy_from_user_slice_raw(
+        &self,
+        reader: &mut UserSliceReader,
+        offset: usize,
+        len: usize,
+    ) -> Result {
+        self.with_pointer_into_page(offset, len, move |dst| {
+            // SAFETY: If `with_pointer_into_page` calls into this closure, then it has performed a
+            // bounds check and guarantees that `dst` is valid for `len` bytes. Furthermore, we have
+            // exclusive access to the slice since the caller guarantees that there are no races.
+            reader.read_raw(unsafe { core::slice::from_raw_parts_mut(dst.cast(), len) })
+        })
+    }
+}
+
+impl Drop for Page {
+    fn drop(&mut self) {
+        // SAFETY: By the type invariants, we have ownership of the page and can free it.
+        unsafe { bindings::__free_pages(self.page.as_ptr(), 0) };
+    }
+}
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 2e7c900..bd189d6 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -409,3 +409,67 @@ pub enum Either<L, R> {
     /// Constructs an instance of [`Either`] containing a value of type `R`.
     Right(R),
 }
+
+/// Types for which any bit pattern is valid.
+///
+/// Not all types are valid for all values. For example, a `bool` must be either zero or one, so
+/// reading arbitrary bytes into something that contains a `bool` is not okay.
+///
+/// It's okay for the type to have padding, as initializing those bytes has no effect.
+///
+/// # Safety
+///
+/// All bit-patterns must be valid for this type. This type must not have interior mutability.
+pub unsafe trait FromBytes {}
+
+// SAFETY: All bit patterns are acceptable values of the types below.
+unsafe impl FromBytes for u8 {}
+unsafe impl FromBytes for u16 {}
+unsafe impl FromBytes for u32 {}
+unsafe impl FromBytes for u64 {}
+unsafe impl FromBytes for usize {}
+unsafe impl FromBytes for i8 {}
+unsafe impl FromBytes for i16 {}
+unsafe impl FromBytes for i32 {}
+unsafe impl FromBytes for i64 {}
+unsafe impl FromBytes for isize {}
+// SAFETY: If all bit patterns are acceptable for individual values in an array, then all bit
+// patterns are also acceptable for arrays of that type.
+unsafe impl<T: FromBytes> FromBytes for [T] {}
+unsafe impl<T: FromBytes, const N: usize> FromBytes for [T; N] {}
+
+/// Types that can be viewed as an immutable slice of initialized bytes.
+///
+/// If a struct implements this trait, then it is okay to copy it byte-for-byte to userspace. This
+/// means that it should not have any padding, as padding bytes are uninitialized. Reading
+/// uninitialized memory is not just undefined behavior, it may even lead to leaking sensitive
+/// information on the stack to userspace.
+///
+/// The struct should also not hold kernel pointers, as kernel pointer addresses are also considered
+/// sensitive. However, leaking kernel pointers is not considered undefined behavior by Rust, so
+/// this is a correctness requirement, but not a safety requirement.
+///
+/// # Safety
+///
+/// Values of this type may not contain any uninitialized bytes. This type must not have interior
+/// mutability.
+pub unsafe trait AsBytes {}
+
+// SAFETY: Instances of the following types have no uninitialized portions.
+unsafe impl AsBytes for u8 {}
+unsafe impl AsBytes for u16 {}
+unsafe impl AsBytes for u32 {}
+unsafe impl AsBytes for u64 {}
+unsafe impl AsBytes for usize {}
+unsafe impl AsBytes for i8 {}
+unsafe impl AsBytes for i16 {}
+unsafe impl AsBytes for i32 {}
+unsafe impl AsBytes for i64 {}
+unsafe impl AsBytes for isize {}
+unsafe impl AsBytes for bool {}
+unsafe impl AsBytes for char {}
+unsafe impl AsBytes for str {}
+// SAFETY: If individual values in an array have no uninitialized portions, then the array itself
+// does not have any uninitialized portions either.
+unsafe impl<T: AsBytes> AsBytes for [T] {}
+unsafe impl<T: AsBytes, const N: usize> AsBytes for [T; N] {}
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
new file mode 100644
index 0000000..e9347cf
--- /dev/null
+++ b/rust/kernel/uaccess.rs
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Slices to user space memory regions.
+//!
+//! C header: [`include/linux/uaccess.h`](srctree/include/linux/uaccess.h)
+
+use crate::{
+    alloc::Flags,
+    bindings,
+    error::Result,
+    prelude::*,
+    types::{AsBytes, FromBytes},
+};
+use alloc::vec::Vec;
+use core::ffi::{c_ulong, c_void};
+use core::mem::{size_of, MaybeUninit};
+
+/// The type used for userspace addresses.
+pub type UserPtr = usize;
+
+/// A pointer to an area in userspace memory, which can be either read-only or read-write.
+///
+/// All methods on this struct are safe: attempting to read or write on bad addresses (either out of
+/// the bound of the slice or unmapped addresses) will return [`EFAULT`]. Concurrent access,
+/// *including data races to/from userspace memory*, is permitted, because fundamentally another
+/// userspace thread/process could always be modifying memory at the same time (in the same way that
+/// userspace Rust's [`std::io`] permits data races with the contents of files on disk). In the
+/// presence of a race, the exact byte values read/written are unspecified but the operation is
+/// well-defined. Kernelspace code should validate its copy of data after completing a read, and not
+/// expect that multiple reads of the same address will return the same value.
+///
+/// These APIs are designed to make it difficult to accidentally write TOCTOU (time-of-check to
+/// time-of-use) bugs. Every time a memory location is read, the reader's position is advanced by
+/// the read length and the next read will start from there. This helps prevent accidentally reading
+/// the same location twice and causing a TOCTOU bug.
+///
+/// Creating a [`UserSliceReader`] and/or [`UserSliceWriter`] consumes the `UserSlice`, helping
+/// ensure that there aren't multiple readers or writers to the same location.
+///
+/// If double-fetching a memory location is necessary for some reason, then that is done by creating
+/// multiple readers to the same memory location, e.g. using [`clone_reader`].
+///
+/// # Examples
+///
+/// Takes a region of userspace memory from the current process, and modify it by adding one to
+/// every byte in the region.
+///
+/// ```no_run
+/// use alloc::vec::Vec;
+/// use core::ffi::c_void;
+/// use kernel::error::Result;
+/// use kernel::uaccess::{UserPtr, UserSlice};
+///
+/// fn bytes_add_one(uptr: UserPtr, len: usize) -> Result<()> {
+///     let (read, mut write) = UserSlice::new(uptr, len).reader_writer();
+///
+///     let mut buf = Vec::new();
+///     read.read_all(&mut buf, GFP_KERNEL)?;
+///
+///     for b in &mut buf {
+///         *b = b.wrapping_add(1);
+///     }
+///
+///     write.write_slice(&buf)?;
+///     Ok(())
+/// }
+/// ```
+///
+/// Example illustrating a TOCTOU (time-of-check to time-of-use) bug.
+///
+/// ```no_run
+/// use alloc::vec::Vec;
+/// use core::ffi::c_void;
+/// use kernel::error::{code::EINVAL, Result};
+/// use kernel::uaccess::{UserPtr, UserSlice};
+///
+/// /// Returns whether the data in this region is valid.
+/// fn is_valid(uptr: UserPtr, len: usize) -> Result<bool> {
+///     let read = UserSlice::new(uptr, len).reader();
+///
+///     let mut buf = Vec::new();
+///     read.read_all(&mut buf, GFP_KERNEL)?;
+///
+///     todo!()
+/// }
+///
+/// /// Returns the bytes behind this user pointer if they are valid.
+/// fn get_bytes_if_valid(uptr: UserPtr, len: usize) -> Result<Vec<u8>> {
+///     if !is_valid(uptr, len)? {
+///         return Err(EINVAL);
+///     }
+///
+///     let read = UserSlice::new(uptr, len).reader();
+///
+///     let mut buf = Vec::new();
+///     read.read_all(&mut buf, GFP_KERNEL)?;
+///
+///     // THIS IS A BUG! The bytes could have changed since we checked them.
+///     //
+///     // To avoid this kind of bug, don't call `UserSlice::new` multiple
+///     // times with the same address.
+///     Ok(buf)
+/// }
+/// ```
+///
+/// [`std::io`]: https://doc.rust-lang.org/std/io/index.html
+/// [`clone_reader`]: UserSliceReader::clone_reader
+pub struct UserSlice {
+    ptr: UserPtr,
+    length: usize,
+}
+
+impl UserSlice {
+    /// Constructs a user slice from a raw pointer and a length in bytes.
+    ///
+    /// Constructing a [`UserSlice`] performs no checks on the provided address and length, it can
+    /// safely be constructed inside a kernel thread with no current userspace process. Reads and
+    /// writes wrap the kernel APIs `copy_from_user` and `copy_to_user`, which check the memory map
+    /// of the current process and enforce that the address range is within the user range (no
+    /// additional calls to `access_ok` are needed). Validity of the pointer is checked when you
+    /// attempt to read or write, not in the call to `UserSlice::new`.
+    ///
+    /// Callers must be careful to avoid time-of-check-time-of-use (TOCTOU) issues. The simplest way
+    /// is to create a single instance of [`UserSlice`] per user memory block as it reads each byte
+    /// at most once.
+    pub fn new(ptr: UserPtr, length: usize) -> Self {
+        UserSlice { ptr, length }
+    }
+
+    /// Reads the entirety of the user slice, appending it to the end of the provided buffer.
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address.
+    pub fn read_all(self, buf: &mut Vec<u8>, flags: Flags) -> Result {
+        self.reader().read_all(buf, flags)
+    }
+
+    /// Constructs a [`UserSliceReader`].
+    pub fn reader(self) -> UserSliceReader {
+        UserSliceReader {
+            ptr: self.ptr,
+            length: self.length,
+        }
+    }
+
+    /// Constructs a [`UserSliceWriter`].
+    pub fn writer(self) -> UserSliceWriter {
+        UserSliceWriter {
+            ptr: self.ptr,
+            length: self.length,
+        }
+    }
+
+    /// Constructs both a [`UserSliceReader`] and a [`UserSliceWriter`].
+    ///
+    /// Usually when this is used, you will first read the data, and then overwrite it afterwards.
+    pub fn reader_writer(self) -> (UserSliceReader, UserSliceWriter) {
+        (
+            UserSliceReader {
+                ptr: self.ptr,
+                length: self.length,
+            },
+            UserSliceWriter {
+                ptr: self.ptr,
+                length: self.length,
+            },
+        )
+    }
+}
+
+/// A reader for [`UserSlice`].
+///
+/// Used to incrementally read from the user slice.
+pub struct UserSliceReader {
+    ptr: UserPtr,
+    length: usize,
+}
+
+impl UserSliceReader {
+    /// Skip the provided number of bytes.
+    ///
+    /// Returns an error if skipping more than the length of the buffer.
+    pub fn skip(&mut self, num_skip: usize) -> Result {
+        // Update `self.length` first since that's the fallible part of this operation.
+        self.length = self.length.checked_sub(num_skip).ok_or(EFAULT)?;
+        self.ptr = self.ptr.wrapping_add(num_skip);
+        Ok(())
+    }
+
+    /// Create a reader that can access the same range of data.
+    ///
+    /// Reading from the clone does not advance the current reader.
+    ///
+    /// The caller should take care to not introduce TOCTOU issues, as described in the
+    /// documentation for [`UserSlice`].
+    pub fn clone_reader(&self) -> UserSliceReader {
+        UserSliceReader {
+            ptr: self.ptr,
+            length: self.length,
+        }
+    }
+
+    /// Returns the number of bytes left to be read from this reader.
+    ///
+    /// Note that even reading less than this number of bytes may fail.
+    pub fn len(&self) -> usize {
+        self.length
+    }
+
+    /// Returns `true` if no data is available in the io buffer.
+    pub fn is_empty(&self) -> bool {
+        self.length == 0
+    }
+
+    /// Reads raw data from the user slice into a kernel buffer.
+    ///
+    /// For a version that uses `&mut [u8]`, please see [`UserSliceReader::read_slice`].
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address, or if the read goes out of
+    /// bounds of this [`UserSliceReader`]. This call may modify `out` even if it returns an error.
+    ///
+    /// # Guarantees
+    ///
+    /// After a successful call to this method, all bytes in `out` are initialized.
+    pub fn read_raw(&mut self, out: &mut [MaybeUninit<u8>]) -> Result {
+        let len = out.len();
+        let out_ptr = out.as_mut_ptr().cast::<c_void>();
+        if len > self.length {
+            return Err(EFAULT);
+        }
+        let Ok(len_ulong) = c_ulong::try_from(len) else {
+            return Err(EFAULT);
+        };
+        // SAFETY: `out_ptr` points into a mutable slice of length `len_ulong`, so we may write
+        // that many bytes to it.
+        let res =
+            unsafe { bindings::copy_from_user(out_ptr, self.ptr as *const c_void, len_ulong) };
+        if res != 0 {
+            return Err(EFAULT);
+        }
+        self.ptr = self.ptr.wrapping_add(len);
+        self.length -= len;
+        Ok(())
+    }
+
+    /// Reads raw data from the user slice into a kernel buffer.
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address, or if the read goes out of
+    /// bounds of this [`UserSliceReader`]. This call may modify `out` even if it returns an error.
+    pub fn read_slice(&mut self, out: &mut [u8]) -> Result {
+        // SAFETY: The types are compatible and `read_raw` doesn't write uninitialized bytes to
+        // `out`.
+        let out = unsafe { &mut *(out as *mut [u8] as *mut [MaybeUninit<u8>]) };
+        self.read_raw(out)
+    }
+
+    /// Reads a value of the specified type.
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address, or if the read goes out of
+    /// bounds of this [`UserSliceReader`].
+    pub fn read<T: FromBytes>(&mut self) -> Result<T> {
+        let len = size_of::<T>();
+        if len > self.length {
+            return Err(EFAULT);
+        }
+        let Ok(len_ulong) = c_ulong::try_from(len) else {
+            return Err(EFAULT);
+        };
+        let mut out: MaybeUninit<T> = MaybeUninit::uninit();
+        // SAFETY: The local variable `out` is valid for writing `size_of::<T>()` bytes.
+        //
+        // By using the _copy_from_user variant, we skip the check_object_size check that verifies
+        // the kernel pointer. This mirrors the logic on the C side that skips the check when the
+        // length is a compile-time constant.
+        let res = unsafe {
+            bindings::_copy_from_user(
+                out.as_mut_ptr().cast::<c_void>(),
+                self.ptr as *const c_void,
+                len_ulong,
+            )
+        };
+        if res != 0 {
+            return Err(EFAULT);
+        }
+        self.ptr = self.ptr.wrapping_add(len);
+        self.length -= len;
+        // SAFETY: The read above has initialized all bytes in `out`, and since `T` implements
+        // `FromBytes`, any bit-pattern is a valid value for this type.
+        Ok(unsafe { out.assume_init() })
+    }
+
+    /// Reads the entirety of the user slice, appending it to the end of the provided buffer.
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address.
+    pub fn read_all(mut self, buf: &mut Vec<u8>, flags: Flags) -> Result {
+        let len = self.length;
+        VecExt::<u8>::reserve(buf, len, flags)?;
+
+        // The call to `try_reserve` was successful, so the spare capacity is at least `len` bytes
+        // long.
+        self.read_raw(&mut buf.spare_capacity_mut()[..len])?;
+
+        // SAFETY: Since the call to `read_raw` was successful, so the next `len` bytes of the
+        // vector have been initialized.
+        unsafe { buf.set_len(buf.len() + len) };
+        Ok(())
+    }
+}
+
+/// A writer for [`UserSlice`].
+///
+/// Used to incrementally write into the user slice.
+pub struct UserSliceWriter {
+    ptr: UserPtr,
+    length: usize,
+}
+
+impl UserSliceWriter {
+    /// Returns the amount of space remaining in this buffer.
+    ///
+    /// Note that even writing less than this number of bytes may fail.
+    pub fn len(&self) -> usize {
+        self.length
+    }
+
+    /// Returns `true` if no more data can be written to this buffer.
+    pub fn is_empty(&self) -> bool {
+        self.length == 0
+    }
+
+    /// Writes raw data to this user pointer from a kernel buffer.
+    ///
+    /// Fails with [`EFAULT`] if the write happens on a bad address, or if the write goes out of
+    /// bounds of this [`UserSliceWriter`]. This call may modify the associated userspace slice even
+    /// if it returns an error.
+    pub fn write_slice(&mut self, data: &[u8]) -> Result {
+        let len = data.len();
+        let data_ptr = data.as_ptr().cast::<c_void>();
+        if len > self.length {
+            return Err(EFAULT);
+        }
+        let Ok(len_ulong) = c_ulong::try_from(len) else {
+            return Err(EFAULT);
+        };
+        // SAFETY: `data_ptr` points into an immutable slice of length `len_ulong`, so we may read
+        // that many bytes from it.
+        let res = unsafe { bindings::copy_to_user(self.ptr as *mut c_void, data_ptr, len_ulong) };
+        if res != 0 {
+            return Err(EFAULT);
+        }
+        self.ptr = self.ptr.wrapping_add(len);
+        self.length -= len;
+        Ok(())
+    }
+
+    /// Writes the provided Rust value to this userspace pointer.
+    ///
+    /// Fails with [`EFAULT`] if the write happens on a bad address, or if the write goes out of
+    /// bounds of this [`UserSliceWriter`]. This call may modify the associated userspace slice even
+    /// if it returns an error.
+    pub fn write<T: AsBytes>(&mut self, value: &T) -> Result {
+        let len = size_of::<T>();
+        if len > self.length {
+            return Err(EFAULT);
+        }
+        let Ok(len_ulong) = c_ulong::try_from(len) else {
+            return Err(EFAULT);
+        };
+        // SAFETY: The reference points to a value of type `T`, so it is valid for reading
+        // `size_of::<T>()` bytes.
+        //
+        // By using the _copy_to_user variant, we skip the check_object_size check that verifies the
+        // kernel pointer. This mirrors the logic on the C side that skips the check when the length
+        // is a compile-time constant.
+        let res = unsafe {
+            bindings::_copy_to_user(
+                self.ptr as *mut c_void,
+                (value as *const T).cast::<c_void>(),
+                len_ulong,
+            )
+        };
+        if res != 0 {
+            return Err(EFAULT);
+        }
+        self.ptr = self.ptr.wrapping_add(len);
+        self.length -= len;
+        Ok(())
+    }
+}
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 1cec63a..553a5cb 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -482,24 +482,26 @@ unsafe fn work_container_of(ptr: *mut Work<T, ID>) -> *mut Self
 /// use kernel::sync::Arc;
 /// use kernel::workqueue::{self, impl_has_work, Work};
 ///
-/// struct MyStruct {
-///     work_field: Work<MyStruct, 17>,
+/// struct MyStruct<'a, T, const N: usize> {
+///     work_field: Work<MyStruct<'a, T, N>, 17>,
+///     f: fn(&'a [T; N]),
 /// }
 ///
 /// impl_has_work! {
-///     impl HasWork<MyStruct, 17> for MyStruct { self.work_field }
+///     impl{'a, T, const N: usize} HasWork<MyStruct<'a, T, N>, 17>
+///     for MyStruct<'a, T, N> { self.work_field }
 /// }
 /// ```
 #[macro_export]
 macro_rules! impl_has_work {
-    ($(impl$(<$($implarg:ident),*>)?
+    ($(impl$({$($generics:tt)*})?
        HasWork<$work_type:ty $(, $id:tt)?>
-       for $self:ident $(<$($selfarg:ident),*>)?
+       for $self:ty
        { self.$field:ident }
     )*) => {$(
         // SAFETY: The implementation of `raw_get_work` only compiles if the field has the right
         // type.
-        unsafe impl$(<$($implarg),*>)? $crate::workqueue::HasWork<$work_type $(, $id)?> for $self $(<$($selfarg),*>)? {
+        unsafe impl$(<$($generics)+>)? $crate::workqueue::HasWork<$work_type $(, $id)?> for $self {
             const OFFSET: usize = ::core::mem::offset_of!(Self, $field) as usize;
 
             #[inline]
@@ -515,7 +517,7 @@ unsafe fn raw_get_work(ptr: *mut Self) -> *mut $crate::workqueue::Work<$work_typ
 pub use impl_has_work;
 
 impl_has_work! {
-    impl<T> HasWork<Self> for ClosureWork<T> { self.work }
+    impl{T} HasWork<Self> for ClosureWork<T> { self.work }
 }
 
 unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Arc<T>
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 520eae5..159e752 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -35,6 +35,7 @@
 ///     author: "Rust for Linux Contributors",
 ///     description: "My very own kernel module!",
 ///     license: "GPL",
+///     alias: ["alternate_module_name"],
 /// }
 ///
 /// struct MyModule;
@@ -55,13 +56,45 @@
 /// }
 /// ```
 ///
+/// ## Firmware
+///
+/// The following example shows how to declare a kernel module that needs
+/// to load binary firmware files. You need to specify the file names of
+/// the firmware in the `firmware` field. The information is embedded
+/// in the `modinfo` section of the kernel module. For example, a tool to
+/// build an initramfs uses this information to put the firmware files into
+/// the initramfs image.
+///
+/// ```ignore
+/// use kernel::prelude::*;
+///
+/// module!{
+///     type: MyDeviceDriverModule,
+///     name: "my_device_driver_module",
+///     author: "Rust for Linux Contributors",
+///     description: "My device driver requires firmware",
+///     license: "GPL",
+///     firmware: ["my_device_firmware1.bin", "my_device_firmware2.bin"],
+/// }
+///
+/// struct MyDeviceDriverModule;
+///
+/// impl kernel::Module for MyDeviceDriverModule {
+///     fn init() -> Result<Self> {
+///         Ok(Self)
+///     }
+/// }
+/// ```
+///
 /// # Supported argument types
 ///   - `type`: type which implements the [`Module`] trait (required).
-///   - `name`: byte array of the name of the kernel module (required).
-///   - `author`: byte array of the author of the kernel module.
-///   - `description`: byte array of the description of the kernel module.
-///   - `license`: byte array of the license of the kernel module (required).
-///   - `alias`: byte array of alias name of the kernel module.
+///   - `name`: ASCII string literal of the name of the kernel module (required).
+///   - `author`: string literal of the author of the kernel module.
+///   - `description`: string literal of the description of the kernel module.
+///   - `license`: ASCII string literal of the license of the kernel module (required).
+///   - `alias`: array of ASCII string literals of the alias names of the kernel module.
+///   - `firmware`: array of ASCII string literals of the firmware files of
+/// the kernel module.
 #[proc_macro]
 pub fn module(ts: TokenStream) -> TokenStream {
     module::module(ts)
@@ -312,7 +345,7 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 ///
 /// Currently supported modifiers are:
 /// * `span`: change the span of concatenated identifier to the span of the specified token. By
-/// default the span of the `[< >]` group is used.
+///   default the span of the `[< >]` group is used.
 /// * `lower`: change the identifier to lower case.
 /// * `upper`: change the identifier to upper case.
 ///
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index acd0393b..411dc10 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -97,14 +97,22 @@ struct ModuleInfo {
     author: Option<String>,
     description: Option<String>,
     alias: Option<Vec<String>>,
+    firmware: Option<Vec<String>>,
 }
 
 impl ModuleInfo {
     fn parse(it: &mut token_stream::IntoIter) -> Self {
         let mut info = ModuleInfo::default();
 
-        const EXPECTED_KEYS: &[&str] =
-            &["type", "name", "author", "description", "license", "alias"];
+        const EXPECTED_KEYS: &[&str] = &[
+            "type",
+            "name",
+            "author",
+            "description",
+            "license",
+            "alias",
+            "firmware",
+        ];
         const REQUIRED_KEYS: &[&str] = &["type", "name", "license"];
         let mut seen_keys = Vec::new();
 
@@ -131,6 +139,7 @@ fn parse(it: &mut token_stream::IntoIter) -> Self {
                 "description" => info.description = Some(expect_string(it)),
                 "license" => info.license = expect_string_ascii(it),
                 "alias" => info.alias = Some(expect_string_array(it)),
+                "firmware" => info.firmware = Some(expect_string_array(it)),
                 _ => panic!(
                     "Unknown key \"{}\". Valid keys are: {:?}.",
                     key, EXPECTED_KEYS
@@ -186,6 +195,11 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
             modinfo.emit("alias", &alias);
         }
     }
+    if let Some(firmware) = info.firmware {
+        for fw in firmware {
+            modinfo.emit("firmware", &fw);
+        }
+    }
 
     // Built-in modules also export the `file` modinfo string.
     let file =
diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs
index 0caad90..80a0026 100644
--- a/rust/uapi/lib.rs
+++ b/rust/uapi/lib.rs
@@ -14,6 +14,7 @@
 #![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))]
 #![allow(
     clippy::all,
+    dead_code,
     missing_docs,
     non_camel_case_types,
     non_upper_case_globals,
diff --git a/samples/kobject/kobject-example.c b/samples/kobject/kobject-example.c
index 96678ed..c9c3db1 100644
--- a/samples/kobject/kobject-example.c
+++ b/samples/kobject/kobject-example.c
@@ -140,5 +140,6 @@ static void __exit example_exit(void)
 
 module_init(example_init);
 module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kobject implementation");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>");
diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c
index 3424522..552d7e3 100644
--- a/samples/kobject/kset-example.c
+++ b/samples/kobject/kset-example.c
@@ -284,5 +284,6 @@ static void __exit example_exit(void)
 
 module_init(example_init);
 module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kset and ktype implementation");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>");
diff --git a/samples/qmi/qmi_sample_client.c b/samples/qmi/qmi_sample_client.c
index c045e3d..a428925 100644
--- a/samples/qmi/qmi_sample_client.c
+++ b/samples/qmi/qmi_sample_client.c
@@ -511,7 +511,7 @@ static int qmi_sample_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int qmi_sample_remove(struct platform_device *pdev)
+static void qmi_sample_remove(struct platform_device *pdev)
 {
 	struct qmi_sample *sample = platform_get_drvdata(pdev);
 
@@ -520,13 +520,11 @@ static int qmi_sample_remove(struct platform_device *pdev)
 	debugfs_remove(sample->de_dir);
 
 	qmi_handle_release(&sample->qmi);
-
-	return 0;
 }
 
 static struct platform_driver qmi_sample_driver = {
 	.probe = qmi_sample_probe,
-	.remove = qmi_sample_remove,
+	.remove_new = qmi_sample_remove,
 	.driver = {
 		.name = "qmi_sample_client",
 	},
diff --git a/scripts/Makefile b/scripts/Makefile
index fe56eee..dccef66 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -12,7 +12,7 @@
 hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS)		+= rustdoc_test_builder
 hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS)		+= rustdoc_test_gen
 
-ifdef CONFIG_X86_64
+ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),)
 always-$(CONFIG_RUST)					+= target.json
 filechk_rust_target = $< < include/config/auto.conf
 
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 641b713..87f3492 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -169,6 +169,23 @@ fn main() {
         ts.push("features", features);
         ts.push("llvm-target", "x86_64-linux-gnu");
         ts.push("target-pointer-width", "64");
+    } else if cfg.has("X86_32") {
+        // This only works on UML, as i386 otherwise needs regparm support in rustc
+        if !cfg.has("UML") {
+            panic!("32-bit x86 only works under UML");
+        }
+        ts.push("arch", "x86");
+        ts.push(
+            "data-layout",
+            "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128",
+        );
+        let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string();
+        if cfg.has("MITIGATION_RETPOLINE") {
+            features += ",+retpoline-external-thunk";
+        }
+        ts.push("features", features);
+        ts.push("llvm-target", "i386-unknown-linux-gnu");
+        ts.push("target-pointer-width", "32");
     } else if cfg.has("LOONGARCH") {
         panic!("loongarch uses the builtin rustc loongarch64-unknown-none-softfloat target");
     } else {
diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh
index 1170189..5262c56d 100755
--- a/scripts/rust_is_available.sh
+++ b/scripts/rust_is_available.sh
@@ -117,20 +117,16 @@
 	echo >&2 "***"
 	exit 1
 fi
-if [ "$rust_compiler_cversion" -gt "$rust_compiler_min_cversion" ]; then
-	echo >&2 "***"
-	echo >&2 "*** Rust compiler '$RUSTC' is too new. This may or may not work."
-	echo >&2 "***   Your version:     $rust_compiler_version"
-	echo >&2 "***   Expected version: $rust_compiler_min_version"
-	echo >&2 "***"
-	warning=1
-fi
 
 # Check that the Rust bindings generator is suitable.
 #
 # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`.
+#
+# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0
+# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when
+# the minimum version is upgraded past that (0.69.1 already fixed the issue).
 rust_bindings_generator_output=$( \
-	LC_ALL=C "$BINDGEN" --version 2>/dev/null
+	LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null
 ) || rust_bindings_generator_code=$?
 if [ -n "$rust_bindings_generator_code" ]; then
 	echo >&2 "***"
@@ -165,13 +161,18 @@
 	echo >&2 "***"
 	exit 1
 fi
-if [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cversion" ]; then
-	echo >&2 "***"
-	echo >&2 "*** Rust bindings generator '$BINDGEN' is too new. This may or may not work."
-	echo >&2 "***   Your version:     $rust_bindings_generator_version"
-	echo >&2 "***   Expected version: $rust_bindings_generator_min_version"
-	echo >&2 "***"
-	warning=1
+if [ "$rust_bindings_generator_cversion" -eq 6600 ] ||
+	[ "$rust_bindings_generator_cversion" -eq 6601 ]; then
+	# Distributions may have patched the issue (e.g. Debian did).
+	if ! "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_0_66.h >/dev/null; then
+		echo >&2 "***"
+		echo >&2 "*** Rust bindings generator '$BINDGEN' versions 0.66.0 and 0.66.1 may not"
+		echo >&2 "*** work due to a bug (https://github.com/rust-lang/rust-bindgen/pull/2567),"
+		echo >&2 "*** unless patched (like Debian's)."
+		echo >&2 "***   Your version:     $rust_bindings_generator_version"
+		echo >&2 "***"
+		warning=1
+	fi
 fi
 
 # Check that the `libclang` used by the Rust bindings generator is suitable.
diff --git a/scripts/rust_is_available_bindgen_0_66.h b/scripts/rust_is_available_bindgen_0_66.h
new file mode 100644
index 0000000..c043129
--- /dev/null
+++ b/scripts/rust_is_available_bindgen_0_66.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define A "\0"
diff --git a/scripts/rust_is_available_test.py b/scripts/rust_is_available_test.py
index 57613fe..4137410 100755
--- a/scripts/rust_is_available_test.py
+++ b/scripts/rust_is_available_test.py
@@ -54,18 +54,34 @@
 """)
 
     @classmethod
-    def generate_bindgen(cls, version_stdout, libclang_stderr):
+    def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=False):
+        if libclang_stderr is None:
+            libclang_case = f"raise SystemExit({cls.bindgen_default_bindgen_libclang_failure_exit_code})"
+        else:
+            libclang_case = f"print({repr(libclang_stderr)}, file=sys.stderr)"
+
+        if version_0_66_patched:
+            version_0_66_case = "pass"
+        else:
+            version_0_66_case = "raise SystemExit(1)"
+
         return cls.generate_executable(f"""#!/usr/bin/env python3
 import sys
 if "rust_is_available_bindgen_libclang.h" in " ".join(sys.argv):
-    print({repr(libclang_stderr)}, file=sys.stderr)
+    {libclang_case}
+elif "rust_is_available_bindgen_0_66.h" in " ".join(sys.argv):
+    {version_0_66_case}
 else:
     print({repr(version_stdout)})
 """)
 
     @classmethod
-    def generate_bindgen_version(cls, stdout):
-        return cls.generate_bindgen(stdout, cls.bindgen_default_bindgen_libclang_stderr)
+    def generate_bindgen_version(cls, stdout, version_0_66_patched=False):
+        return cls.generate_bindgen(stdout, cls.bindgen_default_bindgen_libclang_stderr, version_0_66_patched)
+
+    @classmethod
+    def generate_bindgen_libclang_failure(cls):
+        return cls.generate_bindgen(cls.bindgen_default_bindgen_version_stdout, None)
 
     @classmethod
     def generate_bindgen_libclang(cls, stderr):
@@ -89,6 +105,7 @@
         cls.rust_default_sysroot = subprocess.check_output(("rustc", "--print", "sysroot")).decode().strip()
 
         cls.bindgen_default_bindgen_version_stdout = f"bindgen {cls.bindgen_default_version}"
+        cls.bindgen_default_bindgen_libclang_failure_exit_code = 42
         cls.bindgen_default_bindgen_libclang_stderr = f"scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version {cls.llvm_default_version} [-W#pragma-messages], err: false"
 
         cls.default_rustc = cls.generate_rustc(f"rustc {cls.rustc_default_version}")
@@ -193,11 +210,6 @@
         result = self.run_script(self.Expected.FAILURE, { "RUSTC": rustc })
         self.assertIn(f"Rust compiler '{rustc}' is too old.", result.stderr)
 
-    def test_rustc_new_version(self):
-        rustc = self.generate_rustc("rustc 1.999.0 (a8314ef7d 2099-06-27)")
-        result = self.run_script(self.Expected.SUCCESS_WITH_WARNINGS, { "RUSTC": rustc })
-        self.assertIn(f"Rust compiler '{rustc}' is too new. This may or may not work.", result.stderr)
-
     def test_bindgen_nonexecutable(self):
         result = self.run_script(self.Expected.FAILURE, { "BINDGEN": self.nonexecutable })
         self.assertIn(f"Running '{self.nonexecutable}' to check the Rust bindings generator version failed with", result.stderr)
@@ -226,21 +238,24 @@
         result = self.run_script(self.Expected.FAILURE, { "BINDGEN": bindgen })
         self.assertIn(f"Rust bindings generator '{bindgen}' is too old.", result.stderr)
 
-    def test_bindgen_new_version(self):
-        bindgen = self.generate_bindgen_version("bindgen 0.999.0")
-        result = self.run_script(self.Expected.SUCCESS_WITH_WARNINGS, { "BINDGEN": bindgen })
-        self.assertIn(f"Rust bindings generator '{bindgen}' is too new. This may or may not work.", result.stderr)
+    def test_bindgen_bad_version_0_66_0_and_0_66_1(self):
+        for version in ("0.66.0", "0.66.1"):
+            with self.subTest(version=version):
+                bindgen = self.generate_bindgen_version(f"bindgen {version}")
+                result = self.run_script(self.Expected.SUCCESS_WITH_WARNINGS, { "BINDGEN": bindgen })
+                self.assertIn(f"Rust bindings generator '{bindgen}' versions 0.66.0 and 0.66.1 may not", result.stderr)
+
+    def test_bindgen_bad_version_0_66_0_and_0_66_1_patched(self):
+        for version in ("0.66.0", "0.66.1"):
+            with self.subTest(version=version):
+                bindgen = self.generate_bindgen_version(f"bindgen {version}", True)
+                result = self.run_script(self.Expected.SUCCESS, { "BINDGEN": bindgen })
 
     def test_bindgen_libclang_failure(self):
-        for env in (
-            { "LLVM_CONFIG_PATH": self.missing },
-            { "LIBCLANG_PATH": self.missing },
-            { "CLANG_PATH": self.missing },
-        ):
-            with self.subTest(env=env):
-                result = self.run_script(self.Expected.FAILURE, env | { "PATH": os.environ["PATH"], "BINDGEN": "bindgen" })
-                self.assertIn("Running 'bindgen' to check the libclang version (used by the Rust", result.stderr)
-                self.assertIn("bindings generator) failed with code ", result.stderr)
+        bindgen = self.generate_bindgen_libclang_failure()
+        result = self.run_script(self.Expected.FAILURE, { "BINDGEN": bindgen })
+        self.assertIn(f"Running '{bindgen}' to check the libclang version (used by the Rust", result.stderr)
+        self.assertIn(f"bindings generator) failed with code {self.bindgen_default_bindgen_libclang_failure_exit_code}. This may be caused by", result.stderr)
 
     def test_bindgen_libclang_unexpected_version(self):
         bindgen = self.generate_bindgen_libclang("scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version unexpected [-W#pragma-messages], err: false")
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index bcfea07..01b923d 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -1692,6 +1692,10 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 		struct aa_profile *p;
 		p = aa_deref_parent(profile);
 		dent = prof_dir(p);
+		if (!dent) {
+			error = -ENOENT;
+			goto fail2;
+		}
 		/* adding to parent that previously didn't have children */
 		dent = aafs_create_dir("profiles", dent);
 		if (IS_ERR(dent))
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
index c03eb7c..d52a5b1 100644
--- a/security/apparmor/file.c
+++ b/security/apparmor/file.c
@@ -144,19 +144,6 @@ int aa_audit_file(const struct cred *subj_cred,
 	return aa_audit(type, profile, &ad, file_audit_cb);
 }
 
-/**
- * is_deleted - test if a file has been completely unlinked
- * @dentry: dentry of file to test for deletion  (NOT NULL)
- *
- * Returns: true if deleted else false
- */
-static inline bool is_deleted(struct dentry *dentry)
-{
-	if (d_unlinked(dentry) && d_backing_inode(dentry)->i_nlink == 0)
-		return true;
-	return false;
-}
-
 static int path_name(const char *op, const struct cred *subj_cred,
 		     struct aa_label *label,
 		     const struct path *path, int flags, char *buffer,
diff --git a/security/apparmor/include/cred.h b/security/apparmor/include/cred.h
index 58fdc72..7265d2f 100644
--- a/security/apparmor/include/cred.h
+++ b/security/apparmor/include/cred.h
@@ -63,6 +63,26 @@ static inline struct aa_label *aa_get_newest_cred_label(const struct cred *cred)
 	return aa_get_newest_label(aa_cred_raw_label(cred));
 }
 
+static inline struct aa_label *aa_get_newest_cred_label_condref(const struct cred *cred,
+								bool *needput)
+{
+	struct aa_label *l = aa_cred_raw_label(cred);
+
+	if (unlikely(label_is_stale(l))) {
+		*needput = true;
+		return aa_get_newest_label(l);
+	}
+
+	*needput = false;
+	return l;
+}
+
+static inline void aa_put_label_condref(struct aa_label *l, bool needput)
+{
+	if (unlikely(needput))
+		aa_put_label(l);
+}
+
 /**
  * aa_current_raw_label - find the current tasks confining label
  *
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 6239777..808060f 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -461,6 +461,7 @@ static int apparmor_file_open(struct file *file)
 	struct aa_file_ctx *fctx = file_ctx(file);
 	struct aa_label *label;
 	int error = 0;
+	bool needput;
 
 	if (!path_mediated_fs(file->f_path.dentry))
 		return 0;
@@ -477,7 +478,7 @@ static int apparmor_file_open(struct file *file)
 		return 0;
 	}
 
-	label = aa_get_newest_cred_label(file->f_cred);
+	label = aa_get_newest_cred_label_condref(file->f_cred, &needput);
 	if (!unconfined(label)) {
 		struct mnt_idmap *idmap = file_mnt_idmap(file);
 		struct inode *inode = file_inode(file);
@@ -494,7 +495,7 @@ static int apparmor_file_open(struct file *file)
 		/* todo cache full allowed permissions set and state */
 		fctx->allow = aa_map_file_to_perms(file);
 	}
-	aa_put_label(label);
+	aa_put_label_condref(label, needput);
 
 	return error;
 }
@@ -1124,7 +1125,7 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern)
  * @sock: socket that is being setup
  * @family: family of socket being created
  * @type: type of the socket
- * @ptotocol: protocol of the socket
+ * @protocol: protocol of the socket
  * @kern: socket is a special kernel socket
  *
  * Note:
@@ -1304,6 +1305,13 @@ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (!skb->secmark)
 		return 0;
 
+	/*
+	 * If reach here before socket_post_create hook is called, in which
+	 * case label is null, drop the packet.
+	 */
+	if (!ctx->label)
+		return -EACCES;
+
 	return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE,
 				      skb->secmark, sk);
 }
@@ -2029,7 +2037,7 @@ static int __init alloc_buffers(void)
 }
 
 #ifdef CONFIG_SYSCTL
-static int apparmor_dointvec(struct ctl_table *table, int write,
+static int apparmor_dointvec(const struct ctl_table *table, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!aa_current_policy_admin_capable(NULL))
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
index 49fe8da..bf88632 100644
--- a/security/apparmor/mount.c
+++ b/security/apparmor/mount.c
@@ -44,6 +44,8 @@ static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags)
 		audit_log_format(ab, ", mand");
 	if (flags & MS_DIRSYNC)
 		audit_log_format(ab, ", dirsync");
+	if (flags & MS_NOSYMFOLLOW)
+		audit_log_format(ab, ", nosymfollow");
 	if (flags & MS_NOATIME)
 		audit_log_format(ab, ", noatime");
 	if (flags & MS_NODIRATIME)
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 957654d..14df15e3 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -225,7 +225,7 @@ static void aa_free_data(void *ptr, void *arg)
 {
 	struct aa_data *data = ptr;
 
-	kfree_sensitive(data->data);
+	kvfree_sensitive(data->data, data->size);
 	kfree_sensitive(data->key);
 	kfree_sensitive(data);
 }
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 5e578ef..5a57023 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -747,34 +747,42 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy,
 			*info = "missing required dfa";
 			goto fail;
 		}
-		goto out;
+	} else {
+		/*
+		 * only unpack the following if a dfa is present
+		 *
+		 * sadly start was given different names for file and policydb
+		 * but since it is optional we can try both
+		 */
+		if (!aa_unpack_u32(e, &pdb->start[0], "start"))
+			/* default start state */
+			pdb->start[0] = DFA_START;
+		if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
+			/* default start state for xmatch and file dfa */
+			pdb->start[AA_CLASS_FILE] = DFA_START;
+		}	/* setup class index */
+		for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
+			pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
+						    i);
+		}
 	}
 
 	/*
-	 * only unpack the following if a dfa is present
-	 *
-	 * sadly start was given different names for file and policydb
-	 * but since it is optional we can try both
+	 * Unfortunately due to a bug in earlier userspaces, a
+	 * transition table may be present even when the dfa is
+	 * not. For compatibility reasons unpack and discard.
 	 */
-	if (!aa_unpack_u32(e, &pdb->start[0], "start"))
-		/* default start state */
-		pdb->start[0] = DFA_START;
-	if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
-		/* default start state for xmatch and file dfa */
-		pdb->start[AA_CLASS_FILE] = DFA_START;
-	}	/* setup class index */
-	for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
-		pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
-					       i);
-	}
 	if (!unpack_trans_table(e, &pdb->trans) && required_trans) {
 		*info = "failed to unpack profile transition table";
 		goto fail;
 	}
 
+	if (!pdb->dfa && pdb->trans.table)
+		aa_free_str_table(&pdb->trans);
+
 	/* TODO: move compat mapping here, requires dfa merging first */
 	/* TODO: move verify here, it has to be done after compat mappings */
-out:
+
 	*policy = pdb;
 	return 0;
 
@@ -1071,6 +1079,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 
 			if (rhashtable_insert_fast(profile->data, &data->head,
 						   profile->data->p)) {
+				kvfree_sensitive(data->data, data->size);
 				kfree_sensitive(data->key);
 				kfree_sensitive(data);
 				info = "failed to insert data to table";
diff --git a/security/apparmor/policy_unpack_test.c b/security/apparmor/policy_unpack_test.c
index 5c9bde2..874fcf9 100644
--- a/security/apparmor/policy_unpack_test.c
+++ b/security/apparmor/policy_unpack_test.c
@@ -604,4 +604,5 @@ static struct kunit_suite apparmor_policy_unpack_test_module = {
 
 kunit_test_suite(apparmor_policy_unpack_test_module);
 
+MODULE_DESCRIPTION("KUnit tests for AppArmor's policy unpack");
 MODULE_LICENSE("GPL");
diff --git a/security/landlock/cred.c b/security/landlock/cred.c
index 786af18..db9fe7d 100644
--- a/security/landlock/cred.c
+++ b/security/landlock/cred.c
@@ -14,8 +14,8 @@
 #include "ruleset.h"
 #include "setup.h"
 
-static int hook_cred_prepare(struct cred *const new,
-			     const struct cred *const old, const gfp_t gfp)
+static void hook_cred_transfer(struct cred *const new,
+			       const struct cred *const old)
 {
 	struct landlock_ruleset *const old_dom = landlock_cred(old)->domain;
 
@@ -23,6 +23,12 @@ static int hook_cred_prepare(struct cred *const new,
 		landlock_get_ruleset(old_dom);
 		landlock_cred(new)->domain = old_dom;
 	}
+}
+
+static int hook_cred_prepare(struct cred *const new,
+			     const struct cred *const old, const gfp_t gfp)
+{
+	hook_cred_transfer(new, old);
 	return 0;
 }
 
@@ -36,6 +42,7 @@ static void hook_cred_free(struct cred *const cred)
 
 static struct security_hook_list landlock_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(cred_prepare, hook_cred_prepare),
+	LSM_HOOK_INIT(cred_transfer, hook_cred_transfer),
 	LSM_HOOK_INIT(cred_free, hook_cred_free),
 };
 
diff --git a/security/min_addr.c b/security/min_addr.c
index 88c9a6a..0ce267c 100644
--- a/security/min_addr.c
+++ b/security/min_addr.c
@@ -29,7 +29,7 @@ static void update_mmap_min_addr(void)
  * sysctl handler which just sets dac_mmap_min_addr = the new value and then
  * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly
  */
-int mmap_min_addr_handler(struct ctl_table *table, int write,
+int mmap_min_addr_handler(const struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 39944a8..e1a5e13 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -436,7 +436,7 @@ static struct security_hook_list yama_hooks[] __ro_after_init = {
 };
 
 #ifdef CONFIG_SYSCTL
-static int yama_dointvec_minmax(struct ctl_table *table, int write,
+static int yama_dointvec_minmax(const struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table table_copy;
diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c
index 40e88d7..96d4d7e 100644
--- a/sound/ac97/bus.c
+++ b/sound/ac97/bus.c
@@ -469,10 +469,10 @@ static struct attribute *ac97_dev_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ac97_dev);
 
-static int ac97_bus_match(struct device *dev, struct device_driver *drv)
+static int ac97_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct ac97_codec_device *adev = to_ac97_device(dev);
-	struct ac97_codec_driver *adrv = to_ac97_driver(drv);
+	const struct ac97_codec_driver *adrv = to_ac97_driver(drv);
 	const struct ac97_id *id = adrv->id_table;
 	int i = 0;
 
diff --git a/sound/core/seq_device.c b/sound/core/seq_device.c
index 654d620..4492be5d2 100644
--- a/sound/core/seq_device.c
+++ b/sound/core/seq_device.c
@@ -40,7 +40,7 @@ MODULE_LICENSE("GPL");
 /*
  * bus definition
  */
-static int snd_seq_bus_match(struct device *dev, struct device_driver *drv)
+static int snd_seq_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct snd_seq_device *sdev = to_seq_dev(dev);
 	struct snd_seq_driver *sdrv = to_seq_drv(drv);
@@ -234,7 +234,7 @@ int snd_seq_device_new(struct snd_card *card, int device, const char *id,
 		put_device(&dev->dev);
 		return err;
 	}
-	
+
 	if (result)
 		*result = dev;
 
diff --git a/sound/core/ump.c b/sound/core/ump.c
index 3f61220c..0f0d7e8 100644
--- a/sound/core/ump.c
+++ b/sound/core/ump.c
@@ -733,6 +733,12 @@ static void fill_fb_info(struct snd_ump_endpoint *ump,
 		info->block_id, info->direction, info->active,
 		info->first_group, info->num_groups, info->midi_ci_version,
 		info->sysex8_streams, info->flags);
+
+	if ((info->flags & SNDRV_UMP_BLOCK_IS_MIDI1) && info->num_groups != 1) {
+		info->num_groups = 1;
+		ump_dbg(ump, "FB %d: corrected groups to 1 for MIDI1\n",
+			info->block_id);
+	}
 }
 
 /* check whether the FB info gets updated by the current message */
@@ -806,6 +812,13 @@ static int ump_handle_fb_name_msg(struct snd_ump_endpoint *ump,
 	if (!fb)
 		return -ENODEV;
 
+	if (ump->parsed &&
+	    (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS)) {
+		ump_dbg(ump, "Skipping static FB name update (blk#%d)\n",
+			fb->info.block_id);
+		return 0;
+	}
+
 	ret = ump_append_string(ump, fb->info.name, sizeof(fb->info.name),
 				buf->raw, 3);
 	/* notify the FB name update to sequencer, too */
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index d35d0a4..1a163bb 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -1180,8 +1180,7 @@ static void process_rx_packets(struct fw_iso_context *context, u32 tstamp, size_
 		(void)fw_card_read_cycle_time(fw_parent_device(s->unit)->card, &curr_cycle_time);
 
 	for (i = 0; i < packets; ++i) {
-		DEFINE_FLEX(struct fw_iso_packet, template, header,
-			    header_length, CIP_HEADER_QUADLETS);
+		DEFINE_RAW_FLEX(struct fw_iso_packet, template, header, CIP_HEADER_QUADLETS);
 		bool sched_irq = false;
 
 		build_it_pkt_header(s, desc->cycle, template, pkt_header_length,
diff --git a/sound/hda/hda_bus_type.c b/sound/hda/hda_bus_type.c
index cce2c30..7545ace 100644
--- a/sound/hda/hda_bus_type.c
+++ b/sound/hda/hda_bus_type.c
@@ -46,7 +46,7 @@ static int hdac_codec_match(struct hdac_device *dev, struct hdac_driver *drv)
 		return 0;
 }
 
-static int hda_bus_match(struct device *dev, struct device_driver *drv)
+static int hda_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_driver *hdrv = drv_to_hdac_driver(drv);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c3a86a9..ba0ce87 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4800,6 +4800,8 @@ static void alc298_fixup_samsung_amp(struct hda_codec *codec,
 	}
 }
 
+#include "samsung_helper.c"
+
 #if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
@@ -7429,6 +7431,7 @@ enum {
 	ALC236_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
 	ALC298_FIXUP_SAMSUNG_AMP,
+	ALC298_FIXUP_SAMSUNG_AMP2,
 	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
@@ -9055,6 +9058,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET
 	},
+	[ALC298_FIXUP_SAMSUNG_AMP2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_samsung_amp2
+	},
 	[ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -10359,10 +10366,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
-	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
-	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
@@ -10406,6 +10413,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc868, "Samsung Galaxy Book2 Pro (NP930XED)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc1ca, "Samsung Galaxy Book3 Pro 360 (NP960QFG-KB1US)", ALC298_FIXUP_SAMSUNG_AMP2),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
@@ -10843,6 +10851,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"},
 	{.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"},
 	{.id = ALC298_FIXUP_SAMSUNG_AMP, .name = "alc298-samsung-amp"},
+	{.id = ALC298_FIXUP_SAMSUNG_AMP2, .name = "alc298-samsung-amp2"},
 	{.id = ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc256-samsung-headphone"},
 	{.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"},
 	{.id = ALC274_FIXUP_HP_MIC, .name = "alc274-hp-mic-detect"},
diff --git a/sound/pci/hda/samsung_helper.c b/sound/pci/hda/samsung_helper.c
new file mode 100644
index 0000000..a40175b
--- /dev/null
+++ b/sound/pci/hda/samsung_helper.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Helper functions for Samsung Galaxy Book3 audio initialization */
+
+struct alc298_samsung_coeff_fixup_desc {
+	unsigned char coeff_idx;
+	unsigned short coeff_value;
+};
+
+struct alc298_samsung_coeff_seq_desc {
+	unsigned short coeff_0x23;
+	unsigned short coeff_0x24;
+	unsigned short coeff_0x25;
+	unsigned short coeff_0x26;
+};
+
+
+static inline void alc298_samsung_write_coef_pack2(struct hda_codec *codec,
+						   const struct alc298_samsung_coeff_seq_desc *seq)
+{
+	int i;
+
+	for (i = 0; i < 100; i++) {
+		if ((alc_read_coef_idx(codec, 0x26) & 0x0010) == 0)
+			break;
+
+		usleep_range(500, 1000);
+	}
+
+	alc_write_coef_idx(codec, 0x23, seq->coeff_0x23);
+	alc_write_coef_idx(codec, 0x24, seq->coeff_0x24);
+	alc_write_coef_idx(codec, 0x25, seq->coeff_0x25);
+	alc_write_coef_idx(codec, 0x26, seq->coeff_0x26);
+}
+
+static inline void alc298_samsung_write_coef_pack_seq(
+						struct hda_codec *codec,
+						unsigned char target,
+						const struct alc298_samsung_coeff_seq_desc seq[],
+						int count)
+{
+	alc_write_coef_idx(codec, 0x22, target);
+	for (int i = 0; i < count; i++)
+		alc298_samsung_write_coef_pack2(codec, &seq[i]);
+}
+
+static void alc298_fixup_samsung_amp2(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	int i;
+	static const struct alc298_samsung_coeff_fixup_desc fixups1[] = {
+		{ 0x99, 0x8000 }, { 0x82, 0x4408 }, { 0x32, 0x3f00 }, { 0x0e, 0x6f80 },
+		{ 0x10, 0x0e21 }, { 0x55, 0x8000 }, { 0x08, 0x2fcf }, { 0x08, 0x2fcf },
+		{ 0x2d, 0xc020 }, { 0x19, 0x0017 }, { 0x50, 0x1000 }, { 0x0e, 0x6f80 },
+		{ 0x08, 0x2fcf }, { 0x80, 0x0011 }, { 0x2b, 0x0c10 }, { 0x2d, 0xc020 },
+		{ 0x03, 0x0042 }, { 0x0f, 0x0062 }, { 0x08, 0x2fcf },
+	};
+
+	static const struct alc298_samsung_coeff_seq_desc amp_0x38[] = {
+		{ 0x2000, 0x0000, 0x0001, 0xb011 }, { 0x23ff, 0x0000, 0x0000, 0xb011 },
+		{ 0x203a, 0x0000, 0x0080, 0xb011 }, { 0x23e1, 0x0000, 0x0000, 0xb011 },
+		{ 0x2012, 0x0000, 0x006f, 0xb011 }, { 0x2014, 0x0000, 0x0000, 0xb011 },
+		{ 0x201b, 0x0000, 0x0001, 0xb011 }, { 0x201d, 0x0000, 0x0001, 0xb011 },
+		{ 0x201f, 0x0000, 0x00fe, 0xb011 }, { 0x2021, 0x0000, 0x0000, 0xb011 },
+		{ 0x2022, 0x0000, 0x0010, 0xb011 }, { 0x203d, 0x0000, 0x0005, 0xb011 },
+		{ 0x203f, 0x0000, 0x0003, 0xb011 }, { 0x2050, 0x0000, 0x002c, 0xb011 },
+		{ 0x2076, 0x0000, 0x000e, 0xb011 }, { 0x207c, 0x0000, 0x004a, 0xb011 },
+		{ 0x2081, 0x0000, 0x0003, 0xb011 }, { 0x2399, 0x0000, 0x0003, 0xb011 },
+		{ 0x23a4, 0x0000, 0x00b5, 0xb011 }, { 0x23a5, 0x0000, 0x0001, 0xb011 },
+		{ 0x23ba, 0x0000, 0x0094, 0xb011 }, { 0x2100, 0x00d0, 0x950e, 0xb017 },
+		{ 0x2104, 0x0061, 0xd4e2, 0xb017 }, { 0x2108, 0x00d0, 0x950e, 0xb017 },
+		{ 0x210c, 0x0075, 0xf4e2, 0xb017 }, { 0x2110, 0x00b4, 0x4b0d, 0xb017 },
+		{ 0x2114, 0x000a, 0x1000, 0xb017 }, { 0x2118, 0x0015, 0x2000, 0xb017 },
+		{ 0x211c, 0x000a, 0x1000, 0xb017 }, { 0x2120, 0x0075, 0xf4e2, 0xb017 },
+		{ 0x2124, 0x00b4, 0x4b0d, 0xb017 }, { 0x2128, 0x0000, 0x0010, 0xb017 },
+		{ 0x212c, 0x0000, 0x0000, 0xb017 }, { 0x2130, 0x0000, 0x0000, 0xb017 },
+		{ 0x2134, 0x0000, 0x0000, 0xb017 }, { 0x2138, 0x0000, 0x0000, 0xb017 },
+		{ 0x213c, 0x0000, 0x0010, 0xb017 }, { 0x2140, 0x0000, 0x0000, 0xb017 },
+		{ 0x2144, 0x0000, 0x0000, 0xb017 }, { 0x2148, 0x0000, 0x0000, 0xb017 },
+		{ 0x214c, 0x0000, 0x0000, 0xb017 }, { 0x2150, 0x0000, 0x0010, 0xb017 },
+		{ 0x2154, 0x0000, 0x0000, 0xb017 }, { 0x2158, 0x0000, 0x0000, 0xb017 },
+		{ 0x215c, 0x0000, 0x0000, 0xb017 }, { 0x2160, 0x0000, 0x0000, 0xb017 },
+		{ 0x2164, 0x0000, 0x0010, 0xb017 }, { 0x2168, 0x0000, 0x0000, 0xb017 },
+		{ 0x216c, 0x0000, 0x0000, 0xb017 }, { 0x2170, 0x0000, 0x0000, 0xb017 },
+		{ 0x2174, 0x0000, 0x0000, 0xb017 }, { 0x2178, 0x0000, 0x0010, 0xb017 },
+		{ 0x217c, 0x0000, 0x0000, 0xb017 }, { 0x2180, 0x0000, 0x0000, 0xb017 },
+		{ 0x2184, 0x0000, 0x0000, 0xb017 }, { 0x2188, 0x0000, 0x0000, 0xb017 },
+		{ 0x218c, 0x0064, 0x5800, 0xb017 }, { 0x2190, 0x00c8, 0xb000, 0xb017 },
+		{ 0x2194, 0x0064, 0x5800, 0xb017 }, { 0x2198, 0x003d, 0x5be7, 0xb017 },
+		{ 0x219c, 0x0054, 0x060a, 0xb017 }, { 0x21a0, 0x00c8, 0xa310, 0xb017 },
+		{ 0x21a4, 0x0029, 0x4de5, 0xb017 }, { 0x21a8, 0x0032, 0x420c, 0xb017 },
+		{ 0x21ac, 0x0029, 0x4de5, 0xb017 }, { 0x21b0, 0x00fa, 0xe50c, 0xb017 },
+		{ 0x21b4, 0x0000, 0x0010, 0xb017 }, { 0x21b8, 0x0000, 0x0000, 0xb017 },
+		{ 0x21bc, 0x0000, 0x0000, 0xb017 }, { 0x21c0, 0x0000, 0x0000, 0xb017 },
+		{ 0x21c4, 0x0000, 0x0000, 0xb017 }, { 0x21c8, 0x0056, 0xc50f, 0xb017 },
+		{ 0x21cc, 0x007b, 0xd7e1, 0xb017 }, { 0x21d0, 0x0077, 0xa70e, 0xb017 },
+		{ 0x21d4, 0x00e0, 0xbde1, 0xb017 }, { 0x21d8, 0x0032, 0x530e, 0xb017 },
+		{ 0x2204, 0x00fb, 0x7e0f, 0xb017 }, { 0x2208, 0x000b, 0x02e1, 0xb017 },
+		{ 0x220c, 0x00fb, 0x7e0f, 0xb017 }, { 0x2210, 0x00d5, 0x17e1, 0xb017 },
+		{ 0x2214, 0x00c0, 0x130f, 0xb017 }, { 0x2218, 0x00e5, 0x0a00, 0xb017 },
+		{ 0x221c, 0x00cb, 0x1500, 0xb017 }, { 0x2220, 0x00e5, 0x0a00, 0xb017 },
+		{ 0x2224, 0x00d5, 0x17e1, 0xb017 }, { 0x2228, 0x00c0, 0x130f, 0xb017 },
+		{ 0x222c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2230, 0x0017, 0x48e2, 0xb017 },
+		{ 0x2234, 0x00f5, 0xdb0e, 0xb017 }, { 0x2238, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x223c, 0x00c1, 0xcc0d, 0xb017 }, { 0x2240, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x2244, 0x0017, 0x48e2, 0xb017 }, { 0x2248, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x224c, 0x00ef, 0x5ce2, 0xb017 }, { 0x2250, 0x00c1, 0xcc0d, 0xb017 },
+		{ 0x2254, 0x00f5, 0xdb0e, 0xb017 }, { 0x2258, 0x0017, 0x48e2, 0xb017 },
+		{ 0x225c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2260, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x2264, 0x00c1, 0xcc0d, 0xb017 }, { 0x2268, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x226c, 0x0017, 0x48e2, 0xb017 }, { 0x2270, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x2274, 0x00ef, 0x5ce2, 0xb017 }, { 0x2278, 0x00c1, 0xcc0d, 0xb017 },
+		{ 0x227c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2280, 0x0017, 0x48e2, 0xb017 },
+		{ 0x2284, 0x00f5, 0xdb0e, 0xb017 }, { 0x2288, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x228c, 0x00c1, 0xcc0d, 0xb017 }, { 0x22cc, 0x00e8, 0x8d00, 0xb017 },
+		{ 0x22d0, 0x0000, 0x0000, 0xb017 }, { 0x22d4, 0x0018, 0x72ff, 0xb017 },
+		{ 0x22d8, 0x00ce, 0x25e1, 0xb017 }, { 0x22dc, 0x002f, 0xe40e, 0xb017 },
+		{ 0x238e, 0x0000, 0x0099, 0xb011 }, { 0x238f, 0x0000, 0x0011, 0xb011 },
+		{ 0x2390, 0x0000, 0x0056, 0xb011 }, { 0x2391, 0x0000, 0x0004, 0xb011 },
+		{ 0x2392, 0x0000, 0x00bb, 0xb011 }, { 0x2393, 0x0000, 0x006d, 0xb011 },
+		{ 0x2394, 0x0000, 0x0010, 0xb011 }, { 0x2395, 0x0000, 0x0064, 0xb011 },
+		{ 0x2396, 0x0000, 0x00b6, 0xb011 }, { 0x2397, 0x0000, 0x0028, 0xb011 },
+		{ 0x2398, 0x0000, 0x000b, 0xb011 }, { 0x239a, 0x0000, 0x0099, 0xb011 },
+		{ 0x239b, 0x0000, 0x000d, 0xb011 }, { 0x23a6, 0x0000, 0x0064, 0xb011 },
+		{ 0x23a7, 0x0000, 0x0078, 0xb011 }, { 0x23b9, 0x0000, 0x0000, 0xb011 },
+		{ 0x23e0, 0x0000, 0x0021, 0xb011 }, { 0x23e1, 0x0000, 0x0001, 0xb011 },
+	};
+
+	static const struct alc298_samsung_coeff_seq_desc amp_0x39[] = {
+		{ 0x2000, 0x0000, 0x0001, 0xb011 }, { 0x23ff, 0x0000, 0x0000, 0xb011 },
+		{ 0x203a, 0x0000, 0x0080, 0xb011 }, { 0x23e1, 0x0000, 0x0000, 0xb011 },
+		{ 0x2012, 0x0000, 0x006f, 0xb011 }, { 0x2014, 0x0000, 0x0000, 0xb011 },
+		{ 0x201b, 0x0000, 0x0002, 0xb011 }, { 0x201d, 0x0000, 0x0002, 0xb011 },
+		{ 0x201f, 0x0000, 0x00fd, 0xb011 }, { 0x2021, 0x0000, 0x0001, 0xb011 },
+		{ 0x2022, 0x0000, 0x0010, 0xb011 }, { 0x203d, 0x0000, 0x0005, 0xb011 },
+		{ 0x203f, 0x0000, 0x0003, 0xb011 }, { 0x2050, 0x0000, 0x002c, 0xb011 },
+		{ 0x2076, 0x0000, 0x000e, 0xb011 }, { 0x207c, 0x0000, 0x004a, 0xb011 },
+		{ 0x2081, 0x0000, 0x0003, 0xb011 }, { 0x2399, 0x0000, 0x0003, 0xb011 },
+		{ 0x23a4, 0x0000, 0x00b5, 0xb011 }, { 0x23a5, 0x0000, 0x0001, 0xb011 },
+		{ 0x23ba, 0x0000, 0x0094, 0xb011 }, { 0x2100, 0x00d0, 0x950e, 0xb017 },
+		{ 0x2104, 0x0061, 0xd4e2, 0xb017 }, { 0x2108, 0x00d0, 0x950e, 0xb017 },
+		{ 0x210c, 0x0075, 0xf4e2, 0xb017 }, { 0x2110, 0x00b4, 0x4b0d, 0xb017 },
+		{ 0x2114, 0x000a, 0x1000, 0xb017 }, { 0x2118, 0x0015, 0x2000, 0xb017 },
+		{ 0x211c, 0x000a, 0x1000, 0xb017 }, { 0x2120, 0x0075, 0xf4e2, 0xb017 },
+		{ 0x2124, 0x00b4, 0x4b0d, 0xb017 }, { 0x2128, 0x0000, 0x0010, 0xb017 },
+		{ 0x212c, 0x0000, 0x0000, 0xb017 }, { 0x2130, 0x0000, 0x0000, 0xb017 },
+		{ 0x2134, 0x0000, 0x0000, 0xb017 }, { 0x2138, 0x0000, 0x0000, 0xb017 },
+		{ 0x213c, 0x0000, 0x0010, 0xb017 }, { 0x2140, 0x0000, 0x0000, 0xb017 },
+		{ 0x2144, 0x0000, 0x0000, 0xb017 }, { 0x2148, 0x0000, 0x0000, 0xb017 },
+		{ 0x214c, 0x0000, 0x0000, 0xb017 }, { 0x2150, 0x0000, 0x0010, 0xb017 },
+		{ 0x2154, 0x0000, 0x0000, 0xb017 }, { 0x2158, 0x0000, 0x0000, 0xb017 },
+		{ 0x215c, 0x0000, 0x0000, 0xb017 }, { 0x2160, 0x0000, 0x0000, 0xb017 },
+		{ 0x2164, 0x0000, 0x0010, 0xb017 }, { 0x2168, 0x0000, 0x0000, 0xb017 },
+		{ 0x216c, 0x0000, 0x0000, 0xb017 }, { 0x2170, 0x0000, 0x0000, 0xb017 },
+		{ 0x2174, 0x0000, 0x0000, 0xb017 }, { 0x2178, 0x0000, 0x0010, 0xb017 },
+		{ 0x217c, 0x0000, 0x0000, 0xb017 }, { 0x2180, 0x0000, 0x0000, 0xb017 },
+		{ 0x2184, 0x0000, 0x0000, 0xb017 }, { 0x2188, 0x0000, 0x0000, 0xb017 },
+		{ 0x218c, 0x0064, 0x5800, 0xb017 }, { 0x2190, 0x00c8, 0xb000, 0xb017 },
+		{ 0x2194, 0x0064, 0x5800, 0xb017 }, { 0x2198, 0x003d, 0x5be7, 0xb017 },
+		{ 0x219c, 0x0054, 0x060a, 0xb017 }, { 0x21a0, 0x00c8, 0xa310, 0xb017 },
+		{ 0x21a4, 0x0029, 0x4de5, 0xb017 }, { 0x21a8, 0x0032, 0x420c, 0xb017 },
+		{ 0x21ac, 0x0029, 0x4de5, 0xb017 }, { 0x21b0, 0x00fa, 0xe50c, 0xb017 },
+		{ 0x21b4, 0x0000, 0x0010, 0xb017 }, { 0x21b8, 0x0000, 0x0000, 0xb017 },
+		{ 0x21bc, 0x0000, 0x0000, 0xb017 }, { 0x21c0, 0x0000, 0x0000, 0xb017 },
+		{ 0x21c4, 0x0000, 0x0000, 0xb017 }, { 0x21c8, 0x0056, 0xc50f, 0xb017 },
+		{ 0x21cc, 0x007b, 0xd7e1, 0xb017 }, { 0x21d0, 0x0077, 0xa70e, 0xb017 },
+		{ 0x21d4, 0x00e0, 0xbde1, 0xb017 }, { 0x21d8, 0x0032, 0x530e, 0xb017 },
+		{ 0x2204, 0x00fb, 0x7e0f, 0xb017 }, { 0x2208, 0x000b, 0x02e1, 0xb017 },
+		{ 0x220c, 0x00fb, 0x7e0f, 0xb017 }, { 0x2210, 0x00d5, 0x17e1, 0xb017 },
+		{ 0x2214, 0x00c0, 0x130f, 0xb017 }, { 0x2218, 0x00e5, 0x0a00, 0xb017 },
+		{ 0x221c, 0x00cb, 0x1500, 0xb017 }, { 0x2220, 0x00e5, 0x0a00, 0xb017 },
+		{ 0x2224, 0x00d5, 0x17e1, 0xb017 }, { 0x2228, 0x00c0, 0x130f, 0xb017 },
+		{ 0x222c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2230, 0x0017, 0x48e2, 0xb017 },
+		{ 0x2234, 0x00f5, 0xdb0e, 0xb017 }, { 0x2238, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x223c, 0x00c1, 0xcc0d, 0xb017 }, { 0x2240, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x2244, 0x0017, 0x48e2, 0xb017 }, { 0x2248, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x224c, 0x00ef, 0x5ce2, 0xb017 }, { 0x2250, 0x00c1, 0xcc0d, 0xb017 },
+		{ 0x2254, 0x00f5, 0xdb0e, 0xb017 }, { 0x2258, 0x0017, 0x48e2, 0xb017 },
+		{ 0x225c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2260, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x2264, 0x00c1, 0xcc0d, 0xb017 }, { 0x2268, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x226c, 0x0017, 0x48e2, 0xb017 }, { 0x2270, 0x00f5, 0xdb0e, 0xb017 },
+		{ 0x2274, 0x00ef, 0x5ce2, 0xb017 }, { 0x2278, 0x00c1, 0xcc0d, 0xb017 },
+		{ 0x227c, 0x00f5, 0xdb0e, 0xb017 }, { 0x2280, 0x0017, 0x48e2, 0xb017 },
+		{ 0x2284, 0x00f5, 0xdb0e, 0xb017 }, { 0x2288, 0x00ef, 0x5ce2, 0xb017 },
+		{ 0x228c, 0x00c1, 0xcc0d, 0xb017 }, { 0x22cc, 0x00e8, 0x8d00, 0xb017 },
+		{ 0x22d0, 0x0000, 0x0000, 0xb017 }, { 0x22d4, 0x0018, 0x72ff, 0xb017 },
+		{ 0x22d8, 0x00ce, 0x25e1, 0xb017 }, { 0x22dc, 0x002f, 0xe40e, 0xb017 },
+		{ 0x238e, 0x0000, 0x0099, 0xb011 }, { 0x238f, 0x0000, 0x0011, 0xb011 },
+		{ 0x2390, 0x0000, 0x0056, 0xb011 }, { 0x2391, 0x0000, 0x0004, 0xb011 },
+		{ 0x2392, 0x0000, 0x00bb, 0xb011 }, { 0x2393, 0x0000, 0x006d, 0xb011 },
+		{ 0x2394, 0x0000, 0x0010, 0xb011 }, { 0x2395, 0x0000, 0x0064, 0xb011 },
+		{ 0x2396, 0x0000, 0x00b6, 0xb011 }, { 0x2397, 0x0000, 0x0028, 0xb011 },
+		{ 0x2398, 0x0000, 0x000b, 0xb011 }, { 0x239a, 0x0000, 0x0099, 0xb011 },
+		{ 0x239b, 0x0000, 0x000d, 0xb011 }, { 0x23a6, 0x0000, 0x0064, 0xb011 },
+		{ 0x23a7, 0x0000, 0x0078, 0xb011 }, { 0x23b9, 0x0000, 0x0000, 0xb011 },
+		{ 0x23e0, 0x0000, 0x0021, 0xb011 }, { 0x23e1, 0x0000, 0x0001, 0xb011 },
+	};
+
+	static const struct alc298_samsung_coeff_seq_desc amp_0x3c[] = {
+		{ 0x2000, 0x0000, 0x0001, 0xb011 }, { 0x23ff, 0x0000, 0x0000, 0xb011 },
+		{ 0x203a, 0x0000, 0x0080, 0xb011 }, { 0x23e1, 0x0000, 0x0000, 0xb011 },
+		{ 0x2012, 0x0000, 0x006f, 0xb011 }, { 0x2014, 0x0000, 0x0000, 0xb011 },
+		{ 0x201b, 0x0000, 0x0001, 0xb011 }, { 0x201d, 0x0000, 0x0001, 0xb011 },
+		{ 0x201f, 0x0000, 0x00fe, 0xb011 }, { 0x2021, 0x0000, 0x0000, 0xb011 },
+		{ 0x2022, 0x0000, 0x0010, 0xb011 }, { 0x203d, 0x0000, 0x0005, 0xb011 },
+		{ 0x203f, 0x0000, 0x0003, 0xb011 }, { 0x2050, 0x0000, 0x002c, 0xb011 },
+		{ 0x2076, 0x0000, 0x000e, 0xb011 }, { 0x207c, 0x0000, 0x004a, 0xb011 },
+		{ 0x2081, 0x0000, 0x0003, 0xb011 }, { 0x23ba, 0x0000, 0x008d, 0xb011 },
+		{ 0x2128, 0x0005, 0x460d, 0xb017 }, { 0x212c, 0x00f6, 0x73e5, 0xb017 },
+		{ 0x2130, 0x0005, 0x460d, 0xb017 }, { 0x2134, 0x00c0, 0xe9e5, 0xb017 },
+		{ 0x2138, 0x00d5, 0x010b, 0xb017 }, { 0x213c, 0x009d, 0x7809, 0xb017 },
+		{ 0x2140, 0x00c5, 0x0eed, 0xb017 }, { 0x2144, 0x009d, 0x7809, 0xb017 },
+		{ 0x2148, 0x00c4, 0x4ef0, 0xb017 }, { 0x214c, 0x003a, 0x3106, 0xb017 },
+		{ 0x2150, 0x00af, 0x750e, 0xb017 }, { 0x2154, 0x008c, 0x1ff1, 0xb017 },
+		{ 0x2158, 0x009e, 0x360c, 0xb017 }, { 0x215c, 0x008c, 0x1ff1, 0xb017 },
+		{ 0x2160, 0x004d, 0xac0a, 0xb017 }, { 0x2164, 0x007d, 0xa00f, 0xb017 },
+		{ 0x2168, 0x00e1, 0x9ce3, 0xb017 }, { 0x216c, 0x00e8, 0x590e, 0xb017 },
+		{ 0x2170, 0x00e1, 0x9ce3, 0xb017 }, { 0x2174, 0x0066, 0xfa0d, 0xb017 },
+		{ 0x2178, 0x0000, 0x0010, 0xb017 }, { 0x217c, 0x0000, 0x0000, 0xb017 },
+		{ 0x2180, 0x0000, 0x0000, 0xb017 }, { 0x2184, 0x0000, 0x0000, 0xb017 },
+		{ 0x2188, 0x0000, 0x0000, 0xb017 }, { 0x218c, 0x0000, 0x0010, 0xb017 },
+		{ 0x2190, 0x0000, 0x0000, 0xb017 }, { 0x2194, 0x0000, 0x0000, 0xb017 },
+		{ 0x2198, 0x0000, 0x0000, 0xb017 }, { 0x219c, 0x0000, 0x0000, 0xb017 },
+		{ 0x21a0, 0x0000, 0x0010, 0xb017 }, { 0x21a4, 0x0000, 0x0000, 0xb017 },
+		{ 0x21a8, 0x0000, 0x0000, 0xb017 }, { 0x21ac, 0x0000, 0x0000, 0xb017 },
+		{ 0x21b0, 0x0000, 0x0000, 0xb017 }, { 0x21b4, 0x0000, 0x0010, 0xb017 },
+		{ 0x21b8, 0x0000, 0x0000, 0xb017 }, { 0x21bc, 0x0000, 0x0000, 0xb017 },
+		{ 0x21c0, 0x0000, 0x0000, 0xb017 }, { 0x21c4, 0x0000, 0x0000, 0xb017 },
+		{ 0x23b9, 0x0000, 0x0000, 0xb011 }, { 0x23e0, 0x0000, 0x0020, 0xb011 },
+		{ 0x23e1, 0x0000, 0x0001, 0xb011 },
+	};
+
+	static const struct alc298_samsung_coeff_seq_desc amp_0x3d[] = {
+		{ 0x2000, 0x0000, 0x0001, 0xb011 }, { 0x23ff, 0x0000, 0x0000, 0xb011 },
+		{ 0x203a, 0x0000, 0x0080, 0xb011 }, { 0x23e1, 0x0000, 0x0000, 0xb011 },
+		{ 0x2012, 0x0000, 0x006f, 0xb011 }, { 0x2014, 0x0000, 0x0000, 0xb011 },
+		{ 0x201b, 0x0000, 0x0002, 0xb011 }, { 0x201d, 0x0000, 0x0002, 0xb011 },
+		{ 0x201f, 0x0000, 0x00fd, 0xb011 }, { 0x2021, 0x0000, 0x0001, 0xb011 },
+		{ 0x2022, 0x0000, 0x0010, 0xb011 }, { 0x203d, 0x0000, 0x0005, 0xb011 },
+		{ 0x203f, 0x0000, 0x0003, 0xb011 }, { 0x2050, 0x0000, 0x002c, 0xb011 },
+		{ 0x2076, 0x0000, 0x000e, 0xb011 }, { 0x207c, 0x0000, 0x004a, 0xb011 },
+		{ 0x2081, 0x0000, 0x0003, 0xb011 }, { 0x23ba, 0x0000, 0x008d, 0xb011 },
+		{ 0x2128, 0x0005, 0x460d, 0xb017 }, { 0x212c, 0x00f6, 0x73e5, 0xb017 },
+		{ 0x2130, 0x0005, 0x460d, 0xb017 }, { 0x2134, 0x00c0, 0xe9e5, 0xb017 },
+		{ 0x2138, 0x00d5, 0x010b, 0xb017 }, { 0x213c, 0x009d, 0x7809, 0xb017 },
+		{ 0x2140, 0x00c5, 0x0eed, 0xb017 }, { 0x2144, 0x009d, 0x7809, 0xb017 },
+		{ 0x2148, 0x00c4, 0x4ef0, 0xb017 }, { 0x214c, 0x003a, 0x3106, 0xb017 },
+		{ 0x2150, 0x00af, 0x750e, 0xb017 }, { 0x2154, 0x008c, 0x1ff1, 0xb017 },
+		{ 0x2158, 0x009e, 0x360c, 0xb017 }, { 0x215c, 0x008c, 0x1ff1, 0xb017 },
+		{ 0x2160, 0x004d, 0xac0a, 0xb017 }, { 0x2164, 0x007d, 0xa00f, 0xb017 },
+		{ 0x2168, 0x00e1, 0x9ce3, 0xb017 }, { 0x216c, 0x00e8, 0x590e, 0xb017 },
+		{ 0x2170, 0x00e1, 0x9ce3, 0xb017 }, { 0x2174, 0x0066, 0xfa0d, 0xb017 },
+		{ 0x2178, 0x0000, 0x0010, 0xb017 }, { 0x217c, 0x0000, 0x0000, 0xb017 },
+		{ 0x2180, 0x0000, 0x0000, 0xb017 }, { 0x2184, 0x0000, 0x0000, 0xb017 },
+		{ 0x2188, 0x0000, 0x0000, 0xb017 }, { 0x218c, 0x0000, 0x0010, 0xb017 },
+		{ 0x2190, 0x0000, 0x0000, 0xb017 }, { 0x2194, 0x0000, 0x0000, 0xb017 },
+		{ 0x2198, 0x0000, 0x0000, 0xb017 }, { 0x219c, 0x0000, 0x0000, 0xb017 },
+		{ 0x21a0, 0x0000, 0x0010, 0xb017 }, { 0x21a4, 0x0000, 0x0000, 0xb017 },
+		{ 0x21a8, 0x0000, 0x0000, 0xb017 }, { 0x21ac, 0x0000, 0x0000, 0xb017 },
+		{ 0x21b0, 0x0000, 0x0000, 0xb017 }, { 0x21b4, 0x0000, 0x0010, 0xb017 },
+		{ 0x21b8, 0x0000, 0x0000, 0xb017 }, { 0x21bc, 0x0000, 0x0000, 0xb017 },
+		{ 0x21c0, 0x0000, 0x0000, 0xb017 }, { 0x21c4, 0x0000, 0x0000, 0xb017 },
+		{ 0x23b9, 0x0000, 0x0000, 0xb011 }, { 0x23e0, 0x0000, 0x0020, 0xb011 },
+		{ 0x23e1, 0x0000, 0x0001, 0xb011 },
+	};
+
+	static const struct alc298_samsung_coeff_seq_desc amp_seq1[] = {
+		{ 0x23ff, 0x0000, 0x0000, 0xb011 }, { 0x203a, 0x0000, 0x0080, 0xb011 },
+	};
+
+	static const struct alc298_samsung_coeff_fixup_desc fixups2[] = {
+		{ 0x4f, 0xb029 }, { 0x05, 0x2be0 }, { 0x30, 0x2421 },
+	};
+
+
+	static const struct alc298_samsung_coeff_seq_desc amp_seq2[] = {
+		{ 0x203a, 0x0000, 0x0081, 0xb011 }, { 0x23ff, 0x0000, 0x0001, 0xb011 },
+	};
+
+	if (action != HDA_FIXUP_ACT_INIT)
+		return;
+
+	// First set of fixups
+	for (i = 0; i < ARRAY_SIZE(fixups1); i++)
+		alc_write_coef_idx(codec, fixups1[i].coeff_idx, fixups1[i].coeff_value);
+
+	// First set of writes
+	alc298_samsung_write_coef_pack_seq(codec, 0x38, amp_0x38, ARRAY_SIZE(amp_0x38));
+	alc298_samsung_write_coef_pack_seq(codec, 0x39, amp_0x39, ARRAY_SIZE(amp_0x39));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3c, amp_0x3c, ARRAY_SIZE(amp_0x3c));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3d, amp_0x3d, ARRAY_SIZE(amp_0x3d));
+
+	// Second set of writes
+	alc298_samsung_write_coef_pack_seq(codec, 0x38, amp_seq1, ARRAY_SIZE(amp_seq1));
+	alc298_samsung_write_coef_pack_seq(codec, 0x39, amp_seq1, ARRAY_SIZE(amp_seq1));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3c, amp_seq1, ARRAY_SIZE(amp_seq1));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3d, amp_seq1, ARRAY_SIZE(amp_seq1));
+
+	// Second set of fixups
+	for (i = 0; i < ARRAY_SIZE(fixups2); i++)
+		alc_write_coef_idx(codec, fixups2[i].coeff_idx, fixups2[i].coeff_value);
+
+	// Third set of writes
+	alc298_samsung_write_coef_pack_seq(codec, 0x38, amp_seq2, ARRAY_SIZE(amp_seq2));
+	alc298_samsung_write_coef_pack_seq(codec, 0x39, amp_seq2, ARRAY_SIZE(amp_seq2));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3c, amp_seq2, ARRAY_SIZE(amp_seq2));
+	alc298_samsung_write_coef_pack_seq(codec, 0x3d, amp_seq2, ARRAY_SIZE(amp_seq2));
+
+	// Final fixup
+	alc_write_coef_idx(codec, 0x10, 0x0F21);
+}
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index f54466e..1769e07 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -224,6 +224,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 		.driver_data = &acp6x_card,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21M5"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82QF"),
 		}
 	},
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 7434aee..402b9a2 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -2786,15 +2786,13 @@ int arizona_of_get_audio_pdata(struct arizona *arizona)
 {
 	struct arizona_pdata *pdata = &arizona->pdata;
 	struct device_node *np = arizona->dev->of_node;
-	struct property *prop;
-	const __be32 *cur;
 	u32 val;
 	u32 pdm_val[ARIZONA_MAX_PDM_SPK];
 	int ret;
 	int count = 0;
 
 	count = 0;
-	of_property_for_each_u32(np, "wlf,inmode", prop, cur, val) {
+	of_property_for_each_u32(np, "wlf,inmode", val) {
 		if (count == ARRAY_SIZE(pdata->inmode))
 			break;
 
@@ -2803,7 +2801,7 @@ int arizona_of_get_audio_pdata(struct arizona *arizona)
 	}
 
 	count = 0;
-	of_property_for_each_u32(np, "wlf,dmic-ref", prop, cur, val) {
+	of_property_for_each_u32(np, "wlf,dmic-ref", val) {
 		if (count == ARRAY_SIZE(pdata->dmic_ref))
 			break;
 
@@ -2812,7 +2810,7 @@ int arizona_of_get_audio_pdata(struct arizona *arizona)
 	}
 
 	count = 0;
-	of_property_for_each_u32(np, "wlf,out-mono", prop, cur, val) {
+	of_property_for_each_u32(np, "wlf,out-mono", val) {
 		if (count == ARRAY_SIZE(pdata->out_mono))
 			break;
 
@@ -2821,7 +2819,7 @@ int arizona_of_get_audio_pdata(struct arizona *arizona)
 	}
 
 	count = 0;
-	of_property_for_each_u32(np, "wlf,max-channels-clocked", prop, cur, val) {
+	of_property_for_each_u32(np, "wlf,max-channels-clocked", val) {
 		if (count == ARRAY_SIZE(pdata->max_channels_clocked))
 			break;
 
@@ -2830,7 +2828,7 @@ int arizona_of_get_audio_pdata(struct arizona *arizona)
 	}
 
 	count = 0;
-	of_property_for_each_u32(np, "wlf,out-volume-limit", prop, cur, val) {
+	of_property_for_each_u32(np, "wlf,out-volume-limit", val) {
 		if (count == ARRAY_SIZE(pdata->out_vol_limit))
 			break;
 
diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index 63626b9..8f9a3ae 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -2162,7 +2162,7 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 		return;
 
 	cal = cal_fmw->calibrations;
-	if (cal)
+	if (!cal)
 		return;
 
 	load_calib_data(priv, &cal->dev_data);
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 82df887..f6c3aef 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -306,27 +306,12 @@ static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 	return 0;
 }
 
-SND_SOC_DAILINK_DEFS(hifi,
-	DAILINK_COMP_ARRAY(COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_EMPTY(), COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_EMPTY()));
-
-SND_SOC_DAILINK_DEFS(hifi_fe,
-	DAILINK_COMP_ARRAY(COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_DUMMY()),
-	DAILINK_COMP_ARRAY(COMP_EMPTY()));
-
-SND_SOC_DAILINK_DEFS(hifi_be,
-	DAILINK_COMP_ARRAY(COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_EMPTY(), COMP_EMPTY()));
-
 static const struct snd_soc_dai_link fsl_asoc_card_dai[] = {
 	/* Default ASoC DAI Link*/
 	{
 		.name = "HiFi",
 		.stream_name = "HiFi",
 		.ops = &fsl_asoc_card_ops,
-		SND_SOC_DAILINK_REG(hifi),
 	},
 	/* DPCM Link between Front-End and Back-End (Optional) */
 	{
@@ -335,7 +320,6 @@ static const struct snd_soc_dai_link fsl_asoc_card_dai[] = {
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 		.dynamic = 1,
-		SND_SOC_DAILINK_REG(hifi_fe),
 	},
 	{
 		.name = "HiFi-ASRC-BE",
@@ -345,7 +329,6 @@ static const struct snd_soc_dai_link fsl_asoc_card_dai[] = {
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 		.no_pcm = 1,
-		SND_SOC_DAILINK_REG(hifi_be),
 	},
 };
 
@@ -637,6 +620,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 	struct platform_device *cpu_pdev;
 	struct fsl_asoc_card_priv *priv;
 	struct device *codec_dev[2] = { NULL, NULL };
+	struct snd_soc_dai_link_component *dlc;
 	const char *codec_dai_name[2];
 	const char *codec_dev_name[2];
 	u32 asrc_fmt = 0;
@@ -717,7 +701,35 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
 
 	memcpy(priv->dai_link, fsl_asoc_card_dai,
 	       sizeof(struct snd_soc_dai_link) * ARRAY_SIZE(priv->dai_link));
+	/*
+	 * "Default ASoC DAI Link": 1 cpus, 2 codecs, 1 platforms
+	 * "DPCM Link Front-End":  1 cpus, 1 codecs (dummy), 1 platforms
+	 * "DPCM Link Back-End": 1 cpus, 2 codecs
+	 * totally 10 components
+	 */
+	dlc = devm_kcalloc(&pdev->dev, 10, sizeof(*dlc), GFP_KERNEL);
+	if (!dlc) {
+		ret = -ENOMEM;
+		goto asrc_fail;
+	}
+
+	priv->dai_link[0].cpus = &dlc[0];
+	priv->dai_link[0].num_cpus = 1;
+	priv->dai_link[0].codecs = &dlc[1];
 	priv->dai_link[0].num_codecs = 1;
+	priv->dai_link[0].platforms = &dlc[3];
+	priv->dai_link[0].num_platforms = 1;
+
+	priv->dai_link[1].cpus = &dlc[4];
+	priv->dai_link[1].num_cpus = 1;
+	priv->dai_link[1].codecs = &dlc[5];
+	priv->dai_link[1].num_codecs = 0; /* dummy */
+	priv->dai_link[1].platforms = &dlc[6];
+	priv->dai_link[1].num_platforms = 1;
+
+	priv->dai_link[2].cpus = &dlc[7];
+	priv->dai_link[2].num_cpus = 1;
+	priv->dai_link[2].codecs = &dlc[8];
 	priv->dai_link[2].num_codecs = 1;
 
 	priv->card.dapm_routes = audio_map;
diff --git a/sound/soc/intel/common/soc-acpi-intel-ssp-common.c b/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
index 75d0b93..de7a3f7 100644
--- a/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
+++ b/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
@@ -64,6 +64,15 @@ static const struct codec_map amps[] = {
 	CODEC_MAP_ENTRY("RT1015P", "rt1015", RT1015P_ACPI_HID, CODEC_RT1015P),
 	CODEC_MAP_ENTRY("RT1019P", "rt1019", RT1019P_ACPI_HID, CODEC_RT1019P),
 	CODEC_MAP_ENTRY("RT1308", "rt1308", RT1308_ACPI_HID, CODEC_RT1308),
+
+	/*
+	 * Monolithic components
+	 *
+	 * Only put components that can serve as both the amp and the codec below this line.
+	 * This will ensure that if the part is used just as a codec and there is an amp as well
+	 * then the amp will be selected properly.
+	 */
+	CODEC_MAP_ENTRY("RT5650", "rt5650", RT5650_ACPI_HID, CODEC_RT5650),
 };
 
 enum snd_soc_acpi_intel_codec
diff --git a/sound/soc/intel/common/soc-intel-quirks.h b/sound/soc/intel/common/soc-intel-quirks.h
index de4e550..42bd514 100644
--- a/sound/soc/intel/common/soc-intel-quirks.h
+++ b/sound/soc/intel/common/soc-intel-quirks.h
@@ -11,7 +11,7 @@
 
 #include <linux/platform_data/x86/soc.h>
 
-#if IS_ENABLED(CONFIG_X86)
+#if IS_REACHABLE(CONFIG_IOSF_MBI)
 
 #include <linux/dmi.h>
 #include <asm/iosf_mbi.h>
diff --git a/sound/soc/sof/amd/pci-vangogh.c b/sound/soc/sof/amd/pci-vangogh.c
index 16eb299..eba5808 100644
--- a/sound/soc/sof/amd/pci-vangogh.c
+++ b/sound/soc/sof/amd/pci-vangogh.c
@@ -34,7 +34,6 @@ static const struct sof_amd_acp_desc vangogh_chip_info = {
 	.dsp_intr_base	= ACP5X_DSP_SW_INTR_BASE,
 	.sram_pte_offset = ACP5X_SRAM_PTE_OFFSET,
 	.hw_semaphore_offset = ACP5X_AXI2DAGB_SEM_0,
-	.acp_clkmux_sel = ACP5X_CLKMUX_SEL,
 	.probe_reg_offset = ACP5X_FUTURE_REG_ACLK_0,
 };
 
diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c
index 1c7019c..cdd1e79 100644
--- a/sound/soc/sof/imx/imx8m.c
+++ b/sound/soc/sof/imx/imx8m.c
@@ -234,7 +234,7 @@ static int imx8m_probe(struct snd_sof_dev *sdev)
 	/* set default mailbox offset for FW ready message */
 	sdev->dsp_box.offset = MBOX_OFFSET;
 
-	priv->regmap = syscon_regmap_lookup_by_compatible("fsl,dsp-ctrl");
+	priv->regmap = syscon_regmap_lookup_by_phandle(np, "fsl,dsp-ctrl");
 	if (IS_ERR(priv->regmap)) {
 		dev_err(sdev->dev, "cannot find dsp-ctrl registers");
 		ret = PTR_ERR(priv->regmap);
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index b8b914e..75f6240 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -310,15 +310,19 @@ int hda_cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *hext_stream
 		return ret;
 	}
 
-	/* Wait for completion of transfer */
-	time_left = wait_for_completion_timeout(&hda_stream->ioc,
-						msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
+	if (sdev->pdata->ipc_type == SOF_IPC_TYPE_4) {
+		/* Wait for completion of transfer */
+		time_left = wait_for_completion_timeout(&hda_stream->ioc,
+							msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
 
-	if (!time_left) {
-		dev_err(sdev->dev, "Code loader DMA did not complete\n");
-		return -ETIMEDOUT;
+		if (!time_left) {
+			dev_err(sdev->dev, "Code loader DMA did not complete\n");
+			return -ETIMEDOUT;
+		}
+		dev_dbg(sdev->dev, "Code loader DMA done\n");
 	}
-	dev_dbg(sdev->dev, "Code loader DMA done, waiting for FW_ENTERED status\n");
+
+	dev_dbg(sdev->dev, "waiting for FW_ENTERED status\n");
 
 	status = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
 					chip->rom_status_reg, reg,
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index daf364f..5a40b8f 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1307,9 +1307,10 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 	const struct sof_dev_desc *desc = sof_pdata->desc;
 	struct hdac_bus *bus = sof_to_bus(sdev);
 	struct snd_soc_acpi_mach *mach = NULL;
-	enum snd_soc_acpi_intel_codec codec_type;
+	enum snd_soc_acpi_intel_codec codec_type, amp_type;
 	const char *tplg_filename;
 	const char *tplg_suffix;
+	bool amp_name_valid;
 
 	/* Try I2S or DMIC if it is supported */
 	if (interface_mask & (BIT(SOF_DAI_INTEL_SSP) | BIT(SOF_DAI_INTEL_DMIC)))
@@ -1413,15 +1414,16 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 			}
 		}
 
-		codec_type = snd_soc_acpi_intel_detect_amp_type(sdev->dev);
+		amp_type = snd_soc_acpi_intel_detect_amp_type(sdev->dev);
+		codec_type = snd_soc_acpi_intel_detect_codec_type(sdev->dev);
+		amp_name_valid = amp_type != CODEC_NONE && amp_type != codec_type;
 
-		if (tplg_fixup &&
-		    mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_AMP_NAME &&
-		    codec_type != CODEC_NONE) {
-			tplg_suffix = snd_soc_acpi_intel_get_amp_tplg_suffix(codec_type);
+		if (tplg_fixup && amp_name_valid &&
+		    mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_AMP_NAME) {
+			tplg_suffix = snd_soc_acpi_intel_get_amp_tplg_suffix(amp_type);
 			if (!tplg_suffix) {
 				dev_err(sdev->dev, "no tplg suffix found, amp %d\n",
-					codec_type);
+					amp_type);
 				return NULL;
 			}
 
@@ -1436,7 +1438,6 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 			add_extension = true;
 		}
 
-		codec_type = snd_soc_acpi_intel_detect_codec_type(sdev->dev);
 
 		if (tplg_fixup &&
 		    mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_CODEC_NAME &&
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index 90f6856..87be7f1 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -1358,7 +1358,13 @@ static void sof_ipc4_unprepare_copier_module(struct snd_sof_widget *swidget)
 		ipc4_copier = dai->private;
 
 		if (pipeline->use_chain_dma) {
-			pipeline->msg.primary = 0;
+			/*
+			 * Preserve the DMA Link ID and clear other bits since
+			 * the DMA Link ID is only configured once during
+			 * dai_config, other fields are expected to be 0 for
+			 * re-configuration
+			 */
+			pipeline->msg.primary &= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
 			pipeline->msg.extension = 0;
 		}
 
@@ -3095,8 +3101,14 @@ static int sof_ipc4_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget *
 		return 0;
 
 	if (pipeline->use_chain_dma) {
-		pipeline->msg.primary &= ~SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
-		pipeline->msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID(data->dai_data);
+		/*
+		 * Only configure the DMA Link ID for ChainDMA when this op is
+		 * invoked with SOF_DAI_CONFIG_FLAGS_HW_PARAMS
+		 */
+		if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) {
+			pipeline->msg.primary &= ~SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
+			pipeline->msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID(data->dai_data);
+		}
 		return 0;
 	}
 
diff --git a/sound/soc/sof/sof-client.c b/sound/soc/sof/sof-client.c
index 99f74de..5d6005a 100644
--- a/sound/soc/sof/sof-client.c
+++ b/sound/soc/sof/sof-client.c
@@ -357,7 +357,7 @@ EXPORT_SYMBOL_NS_GPL(sof_client_ipc4_find_module, SND_SOC_SOF_CLIENT);
 
 int sof_suspend_clients(struct snd_sof_dev *sdev, pm_message_t state)
 {
-	struct auxiliary_driver *adrv;
+	const struct auxiliary_driver *adrv;
 	struct sof_client_dev *cdev;
 
 	mutex_lock(&sdev->ipc_client_mutex);
@@ -380,7 +380,7 @@ EXPORT_SYMBOL_NS_GPL(sof_suspend_clients, SND_SOC_SOF_CLIENT);
 
 int sof_resume_clients(struct snd_sof_dev *sdev)
 {
-	struct auxiliary_driver *adrv;
+	const struct auxiliary_driver *adrv;
 	struct sof_client_dev *cdev;
 
 	mutex_lock(&sdev->ipc_client_mutex);
diff --git a/sound/soc/tegra/Kconfig b/sound/soc/tegra/Kconfig
index 74effc5..2463c22 100644
--- a/sound/soc/tegra/Kconfig
+++ b/sound/soc/tegra/Kconfig
@@ -78,6 +78,7 @@
 
 config SND_SOC_TEGRA210_I2S
 	tristate "Tegra210 I2S module"
+	select SND_SIMPLE_CARD_UTILS
 	help
 	  Config to enable the Inter-IC Sound (I2S) Controller which
 	  implements full-duplex and bidirectional and single direction
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index c00009b..f7ce8e8c 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -1211,6 +1211,13 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 			cval->res = 16;
 		}
 		break;
+	case USB_ID(0x1bcf, 0x2281): /* HD Webcam */
+		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+			usb_audio_info(chip,
+				"set resolution quirk: cval->res = 16\n");
+			cval->res = 16;
+		}
+		break;
 	}
 }
 
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 58156fb..ea063a14 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2125,6 +2125,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
 		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
@@ -2167,6 +2169,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x1bcf, 0x2281, /* HD Webcam */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 40ea743..2ff949e 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -2489,7 +2489,7 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/connect_unix | cgroup/getpeername4 | cgroup/getpeername6 |\n"
 		"                 cgroup/getpeername_unix | cgroup/getsockname4 | cgroup/getsockname6 |\n"
 		"                 cgroup/getsockname_unix | cgroup/sendmsg4 | cgroup/sendmsg6 |\n"
-		"                 cgroup/sendmsg°unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n"
+		"                 cgroup/sendmsg_unix | cgroup/recvmsg4 | cgroup/recvmsg6 | cgroup/recvmsg_unix |\n"
 		"                 cgroup/getsockopt | cgroup/setsockopt | cgroup/sock_release |\n"
 		"                 struct_ops | fentry | fexit | freplace | sk_lookup }\n"
 		"       ATTACH_TYPE := { sk_msg_verdict | sk_skb_verdict | sk_skb_stream_verdict |\n"
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 936ef95..d54aaa0 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -704,7 +704,7 @@ static int sets_patch(struct object *obj)
 			 * Make sure id is at the beginning of the pairs
 			 * struct, otherwise the below qsort would not work.
 			 */
-			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
+			BUILD_BUG_ON((u32 *)set8->pairs != &set8->pairs[0].id);
 			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
 
 			/*
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 1e2ab14..e1900ab 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -149,6 +149,24 @@
 #
 FEATURE_GROUP_MEMBERS-libbfd = libbfd-liberty libbfd-liberty-z
 
+#
+# Declare list of feature dependency packages that provide pkg-config files.
+#
+FEATURE_PKG_CONFIG ?=           \
+         libtraceevent          \
+         libtracefs
+
+feature_pkg_config = $(eval $(feature_pkg_config_code))
+define feature_pkg_config_code
+  FEATURE_CHECK_CFLAGS-$(1) := $(shell $(PKG_CONFIG) --cflags $(1) 2>/dev/null)
+  FEATURE_CHECK_LDFLAGS-$(1) := $(shell $(PKG_CONFIG) --libs $(1) 2>/dev/null)
+endef
+
+# Set FEATURE_CHECK_(C|LD)FLAGS-$(package) for packages using pkg-config.
+ifneq ($(PKG_CONFIG),)
+  $(foreach package,$(FEATURE_PKG_CONFIG),$(call feature_pkg_config,$(package)))
+endif
+
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
 # mentioned in this list we need to refactor this ;-).
diff --git a/tools/include/asm/rwonce.h b/tools/include/asm/rwonce.h
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/tools/include/asm/rwonce.h
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 210c13b..2a7f260 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -19,7 +19,7 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
 bool __bitmap_equal(const unsigned long *bitmap1,
 		    const unsigned long *bitmap2, unsigned int bits);
-void bitmap_clear(unsigned long *map, unsigned int start, int len);
+void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 bool __bitmap_intersects(const unsigned long *bitmap1,
 			 const unsigned long *bitmap2, unsigned int bits);
 
@@ -150,4 +150,19 @@ static inline bool bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
+static inline void bitmap_clear(unsigned long *map, unsigned int start,
+			       unsigned int nbits)
+{
+	if (__builtin_constant_p(nbits) && nbits == 1)
+		__clear_bit(start, map);
+	else if (small_const_nbits(start + nbits))
+		*map &= ~GENMASK(start + nbits - 1, start);
+	else if (__builtin_constant_p(start & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) &&
+		 __builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
+		 IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
+		memset((char *)map + start / 8, 0, nbits / 8);
+	else
+		__bitmap_clear(map, start, nbits);
+}
 #endif /* _TOOLS_LINUX_BITMAP_H */
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 638c606..2f082b0 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index a246e11..e89d005 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -17,6 +17,7 @@
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
 #define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#define MAP_DROPPABLE	0x08		/* Zero memory under memory pressure. */
 
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index c3e4871..2178862 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -100,3 +100,23 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 			return true;
 	return false;
 }
+
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 5dbca76..8948601 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1559,10 +1559,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * Clang for BPF target generates func_proto with no
 			 * args as a func_proto with a single void arg (e.g.,
 			 * `int (*f)(void)` vs just `int (*f)()`). We are
-			 * going to pretend there are no args for such case.
+			 * going to emit valid empty args (void) syntax for
+			 * such case. Similarly and conveniently, valid
+			 * no args case can be special-cased here as well.
 			 */
-			if (vlen == 1 && p->type == 0) {
-				btf_dump_printf(d, ")");
+			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
+				btf_dump_printf(d, "void)");
 				return;
 			}
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index a4829b6..c896bab 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -182,20 +182,15 @@
 FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
 
+# for linking with debug library, run like:
+# make DEBUG=1 PKG_CONFIG_PATH=/opt/libtraceevent/(lib|lib64)/pkgconfig
+
 ifneq ($(NO_LIBTRACEEVENT),1)
   ifeq ($(call get-executable,$(PKG_CONFIG)),)
     $(error Error: $(PKG_CONFIG) needed by libtraceevent is missing on this system, please install it)
   endif
 endif
 
-# for linking with debug library, run like:
-# make DEBUG=1 PKG_CONFIG_PATH=/opt/libtraceevent/(lib|lib64)/pkgconfig
-FEATURE_CHECK_CFLAGS-libtraceevent := $(shell $(PKG_CONFIG) --cflags libtraceevent 2>/dev/null)
-FEATURE_CHECK_LDFLAGS-libtraceevent := $(shell $(PKG_CONFIG) --libs libtraceevent 2>/dev/null)
-
-FEATURE_CHECK_CFLAGS-libtracefs := $(shell $(PKG_CONFIG) --cflags libtracefs 2>/dev/null)
-FEATURE_CHECK_LDFLAGS-libtracefs := $(shell $(PKG_CONFIG) --libs libtracefs 2>/dev/null)
-
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -1206,6 +1201,8 @@
     LIBTRACEFS_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEFS_VERSION)))
     LIBTRACEFS_VERSION_CPP := $(shell expr $(LIBTRACEFS_VERSION_1) \* 255 \* 255 + $(LIBTRACEFS_VERSION_2) \* 255 + $(LIBTRACEFS_VERSION_3))
     CFLAGS += -DLIBTRACEFS_VERSION=$(LIBTRACEFS_VERSION_CPP)
+  else
+    $(warning libtracefs is missing. Please install libtracefs-dev/libtracefs-devel)
   endif
 endif
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 2340c4f..6741494 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1501,7 +1501,7 @@ void dso__delete(struct dso *dso)
 	auxtrace_cache__free(RC_CHK_ACCESS(dso)->auxtrace_cache);
 	dso_cache__free(dso);
 	dso__free_a2l(dso);
-	zfree(&RC_CHK_ACCESS(dso)->symsrc_filename);
+	dso__free_symsrc_filename(dso);
 	nsinfo__zput(RC_CHK_ACCESS(dso)->nsinfo);
 	mutex_destroy(dso__lock(dso));
 	RC_CHK_FREE(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 878c1f4..ed00682 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -602,6 +602,11 @@ static inline void dso__set_symsrc_filename(struct dso *dso, char *val)
 	RC_CHK_ACCESS(dso)->symsrc_filename = val;
 }
 
+static inline void dso__free_symsrc_filename(struct dso *dso)
+{
+	zfree(&RC_CHK_ACCESS(dso)->symsrc_filename);
+}
+
 static inline enum dso_binary_type dso__symtab_type(const struct dso *dso)
 {
 	return RC_CHK_ACCESS(dso)->symtab_type;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index f6a6f6a..16c2b03 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -413,7 +413,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 							__func__,
 							dso__symsrc_filename(dso),
 							debuglink);
-					zfree(&dso__symsrc_filename(dso));
+					dso__free_symsrc_filename(dso);
 				}
 				dso__set_symsrc_filename(dso, debuglink);
 			} else {
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index b1e6817..3946d52 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -46,6 +46,7 @@
 	@echo "#define GENMASK_ULL(h, l) (((~0ULL) << (l)) & (~0ULL >> (sizeof(long long) * 8 - 1 - (h))))" >> $(SNAPSHOT)/bits.h
 
 	@echo '#define BUILD_BUG_ON(cond) do { enum { compile_time_check ## __COUNTER__ = 1/(!(cond)) }; } while (0)' > $(SNAPSHOT)/build_bug.h
+	@echo '#define __must_be_array(arr) 0' >> $(SNAPSHOT)/build_bug.h
 
 	@echo PWD=. > $(SNAPSHOT)/Makefile
 	@echo "CFLAGS +=	-DMSRHEADER='\"msr-index.h\"'" >> $(SNAPSHOT)/Makefile
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 8d37acd..067717b 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -28,10 +28,13 @@
 .PP
 \fB--add attributes\fP add column with counter having specified 'attributes'.  The 'location' attribute is required, all others are optional.
 .nf
-	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP}
+	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP | \fBperf/<device>/<event>\fP}
 		msrDDD is a decimal offset, eg. msr16
 		msr0xXXX is a hex offset, eg. msr0x10
 		/sys/path... is an absolute path to a sysfs attribute
+		<device> is a perf device from /sys/bus/event_source/devices/<device> eg. cstate_core
+		<event> is a perf event for given device from /sys/bus/event_source/devices/<device>/events/<event> eg. c1-residency
+			perf/cstate_core/c1-residency would then use /sys/bus/event_source/devices/cstate_core/events/c1-residency
 
 	scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP}
 		sample and print the counter for every cpu, core, or package.
@@ -52,6 +55,39 @@
 		as the column header.
 .fi
 .PP
+\fB--add pmt,[attr_name=attr_value, ...]\fP add column with a PMT (Intel Platform Monitoring Technology) counter in a similar way to --add option above, but require PMT metadata to be supplied to correctly read and display the counter. The metadata can be found in the Intel PMT XML files, hosted at https://github.com/intel/Intel-PMT. For a complete example see "ADD PMT COUNTER EXAMPLE".
+.nf
+	name="name_string"
+		For column header.
+
+	type={\fBraw\fP}
+		'raw' shows the counter contents in hex.
+		default: raw
+
+	format={\fBraw\fP | \fBdelta\fP}
+		'raw' shows the counter contents in hex.
+		'delta' shows the difference in values during the measurement interval.
+		default: raw
+
+	domain={\fBcpu%u\fP | \fBcore%u\fP | \fBpackage%u\fP}
+		'cpu' per cpu/thread counter.
+		'core' per core counter.
+		'package' per package counter.
+		'%u' denotes id of the domain that the counter is associated with. For example core4 would mean that the counter is associated with core number 4.
+
+	offset=\fB%u\fP
+		'%u' offset within the PMT MMIO region.
+
+	lsb=\fB%u\fP
+		'%u' least significant bit within the 64 bit value read from 'offset'. Together with 'msb', used to form a read mask.
+
+	msb=\fB%u\fP
+		'%u' most significant bit within the 64 bit value read from 'offset'. Together with 'lsb', used to form a read mask.
+
+	guid=\fB%x\fP
+		'%x' hex identifier of the PMT MMIO region.
+.fi
+.PP
 \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
 .PP
 \fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.
@@ -67,10 +103,10 @@
 .PP
 \fB--quiet\fP Do not decode and print the system configuration header information.
 .PP
-+\fB--no-msr\fP Disable all the uses of the MSR driver.
-+.PP
-+\fB--no-perf\fP Disable all the uses of the perf API.
-+.PP
+\fB--no-msr\fP Disable all the uses of the MSR driver.
+.PP
+\fB--no-perf\fP Disable all the uses of the perf API.
+.PP
 \fB--interval seconds\fP overrides the default 5.0 second measurement interval.
 .PP
 \fB--num_iterations num\fP number of the measurement iterations.
@@ -320,7 +356,7 @@
 Here we limit turbostat to showing just the CPU number for cpu0 - cpu3.
 We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL),
 labeling it with the column header, "PRF_CTRL", and display it only once,
-afte the conclusion of a 0.1 second sleep.
+after the conclusion of a 0.1 second sleep.
 .nf
 sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1
 0.101604 sec
@@ -333,6 +369,56 @@
 
 .fi
 
+.SH ADD PERF COUNTER EXAMPLE
+Here we limit turbostat to showing just the CPU number for cpu0 - cpu3.
+We add a counter showing time spent in C1 core cstate,
+labeling it with the column header, "pCPU%c1", and display it only once,
+after the conclusion of 0.1 second sleep.
+We also show CPU%c1 built-in counter that should show similar values.
+.nf
+sudo ./turbostat --quiet --cpu 0-3 --show CPU,CPU%c1 --add perf/cstate_core/c1-residency,cpu,delta,percent,pCPU%c1 sleep .1
+0.102448 sec
+CPU     pCPU%c1 CPU%c1
+-       34.89   34.89
+0       45.99   45.99
+1       45.94   45.94
+2       23.83   23.83
+3       23.84   23.84
+
+.fi
+
+.SH ADD PMT COUNTER EXAMPLE
+Here we limit turbostat to showing just the CPU number 0.
+We add two counters, showing crystal clock count and the DC6 residency.
+All the parameters passed are based on the metadata found in the PMT XML files.
+
+For the crystal clock count, we
+label it with the column header, "XTAL",
+we set the type to 'raw', to read the number of clock ticks in hex,
+we set the format to 'delta', to display the difference in ticks during the measurement interval,
+we set the domain to 'package0', to collect it and associate it with the whole package number 0,
+we set the offset to '0', which is a offset of the counter within the PMT MMIO region,
+we set the lsb and msb to cover all 64 bits of the read 64 bit value,
+and finally we set the guid to '0x1a067102', that identifies the PMT MMIO region to which the 'offset' is applied to read the counter value.
+
+For the DC6 residency counter, we
+label it with the column header, "Die%c6",
+we set the type to 'txtal_time', to obtain the percent residency value
+we set the format to 'delta', to display the difference in ticks during the measurement interval,
+we set the domain to 'package0', to collect it and associate it with the whole package number 0,
+we set the offset to '0', which is a offset of the counter within the PMT MMIO region,
+we set the lsb and msb to cover all 64 bits of the read 64 bit value,
+and finally we set the guid to '0x1a067102', that identifies the PMT MMIO region to which the 'offset' is applied to read the counter value.
+
+.nf
+sudo ./turbostat --quiet --cpu 0 --show CPU --add pmt,name=XTAL,type=raw,format=delta,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102 --add pmt,name=Die%c6,type=txtal_time,format=delta,domain=package0,offset=120,lsb=0,msb=63,guid=0x1a067102
+0.104352 sec
+CPU                   XTAL      Die%c6
+-       0x0000006d4d957ca7      0.00
+0       0x0000006d4d957ca7      0.00
+0.102448 sec
+.fi
+
 .SH INPUT
 
 For interval-mode, turbostat will immediately end the current interval
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9f5d053..089220a 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -9,6 +9,30 @@
 
 #define _GNU_SOURCE
 #include MSRHEADER
+
+// copied from arch/x86/include/asm/cpu_device_id.h
+#define VFM_MODEL_BIT	0
+#define VFM_FAMILY_BIT	8
+#define VFM_VENDOR_BIT	16
+#define VFM_RSVD_BIT	24
+
+#define	VFM_MODEL_MASK	GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT)
+#define	VFM_FAMILY_MASK	GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT)
+#define	VFM_VENDOR_MASK	GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT)
+
+#define VFM_MODEL(vfm)	(((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT)
+#define VFM_FAMILY(vfm)	(((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT)
+#define VFM_VENDOR(vfm)	(((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT)
+
+#define	VFM_MAKE(_vendor, _family, _model) (	\
+	((_model) << VFM_MODEL_BIT) |		\
+	((_family) << VFM_FAMILY_BIT) |		\
+	((_vendor) << VFM_VENDOR_BIT)		\
+)
+// end copied section
+
+#define X86_VENDOR_INTEL	0
+
 #include INTEL_FAMILY_HEADER
 #include BUILD_BUG_HEADER
 #include <stdarg.h>
@@ -20,6 +44,7 @@
 #include <sys/stat.h>
 #include <sys/select.h>
 #include <sys/resource.h>
+#include <sys/mman.h>
 #include <fcntl.h>
 #include <signal.h>
 #include <sys/time.h>
@@ -55,15 +80,39 @@
  */
 #define	NAME_BYTES 20
 #define PATH_BYTES 128
+#define PERF_NAME_BYTES 128
 
 #define MAX_NOFILE 0x8000
 
+#define COUNTER_KIND_PERF_PREFIX "perf/"
+#define COUNTER_KIND_PERF_PREFIX_LEN strlen(COUNTER_KIND_PERF_PREFIX)
+#define PERF_DEV_NAME_BYTES 32
+#define PERF_EVT_NAME_BYTES 32
+
 enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
 enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M };
 enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE };
-enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR };
-enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR };
-enum cstate_source { CSTATE_SOURCE_NONE, CSTATE_SOURCE_PERF, CSTATE_SOURCE_MSR };
+enum counter_source { COUNTER_SOURCE_NONE, COUNTER_SOURCE_PERF, COUNTER_SOURCE_MSR };
+
+struct perf_counter_info {
+	struct perf_counter_info *next;
+
+	/* How to open the counter / What counter it is. */
+	char device[PERF_DEV_NAME_BYTES];
+	char event[PERF_EVT_NAME_BYTES];
+
+	/* How to show/format the counter. */
+	char name[PERF_NAME_BYTES];
+	unsigned int width;
+	enum counter_scope scope;
+	enum counter_type type;
+	enum counter_format format;
+	double scale;
+
+	/* For reading the counter. */
+	int *fd_perf_per_domain;
+	size_t num_domains;
+};
 
 struct sysfs_path {
 	char path[PATH_BYTES];
@@ -144,6 +193,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "SAM%mc6", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "SAMMHz", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "SAMAMHz", NULL, 0, 0, 0, NULL, 0 },
+	{ 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -205,11 +255,12 @@ struct msr_counter bic[] = {
 #define	BIC_SAM_mc6		(1ULL << 55)
 #define	BIC_SAMMHz		(1ULL << 56)
 #define	BIC_SAMACTMHz		(1ULL << 57)
+#define	BIC_Diec6		(1ULL << 58)
 
 #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
 #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
 #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6)
+#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6)
 #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
@@ -252,7 +303,6 @@ char *proc_stat = "/proc/stat";
 FILE *outf;
 int *fd_percpu;
 int *fd_instr_count_percpu;
-struct amperf_group_fd *fd_amperf_percpu;	/* File descriptors for perf group with APERF and MPERF counters. */
 struct timeval interval_tv = { 5, 0 };
 struct timespec interval_ts = { 5, 0 };
 
@@ -267,6 +317,7 @@ unsigned int summary_only;
 unsigned int list_header_only;
 unsigned int dump_only;
 unsigned int has_aperf;
+unsigned int has_aperf_access;
 unsigned int has_epb;
 unsigned int has_turbo;
 unsigned int is_hybrid;
@@ -307,7 +358,6 @@ unsigned int first_counter_read = 1;
 int ignore_stdin;
 bool no_msr;
 bool no_perf;
-enum amperf_source amperf_source;
 
 enum gfx_sysfs_idx {
 	GFX_rc6,
@@ -367,7 +417,7 @@ struct platform_features {
 };
 
 struct platform_data {
-	unsigned int model;
+	unsigned int vfm;
 	const struct platform_features *features;
 };
 
@@ -910,75 +960,75 @@ static const struct platform_features amd_features_with_rapl = {
 };
 
 static const struct platform_data turbostat_pdata[] = {
-	{ INTEL_FAM6_NEHALEM, &nhm_features },
-	{ INTEL_FAM6_NEHALEM_G, &nhm_features },
-	{ INTEL_FAM6_NEHALEM_EP, &nhm_features },
-	{ INTEL_FAM6_NEHALEM_EX, &nhx_features },
-	{ INTEL_FAM6_WESTMERE, &nhm_features },
-	{ INTEL_FAM6_WESTMERE_EP, &nhm_features },
-	{ INTEL_FAM6_WESTMERE_EX, &nhx_features },
-	{ INTEL_FAM6_SANDYBRIDGE, &snb_features },
-	{ INTEL_FAM6_SANDYBRIDGE_X, &snx_features },
-	{ INTEL_FAM6_IVYBRIDGE, &ivb_features },
-	{ INTEL_FAM6_IVYBRIDGE_X, &ivx_features },
-	{ INTEL_FAM6_HASWELL, &hsw_features },
-	{ INTEL_FAM6_HASWELL_X, &hsx_features },
-	{ INTEL_FAM6_HASWELL_L, &hswl_features },
-	{ INTEL_FAM6_HASWELL_G, &hswg_features },
-	{ INTEL_FAM6_BROADWELL, &bdw_features },
-	{ INTEL_FAM6_BROADWELL_G, &bdwg_features },
-	{ INTEL_FAM6_BROADWELL_X, &bdx_features },
-	{ INTEL_FAM6_BROADWELL_D, &bdx_features },
-	{ INTEL_FAM6_SKYLAKE_L, &skl_features },
-	{ INTEL_FAM6_SKYLAKE, &skl_features },
-	{ INTEL_FAM6_SKYLAKE_X, &skx_features },
-	{ INTEL_FAM6_KABYLAKE_L, &skl_features },
-	{ INTEL_FAM6_KABYLAKE, &skl_features },
-	{ INTEL_FAM6_COMETLAKE, &skl_features },
-	{ INTEL_FAM6_COMETLAKE_L, &skl_features },
-	{ INTEL_FAM6_CANNONLAKE_L, &cnl_features },
-	{ INTEL_FAM6_ICELAKE_X, &icx_features },
-	{ INTEL_FAM6_ICELAKE_D, &icx_features },
-	{ INTEL_FAM6_ICELAKE_L, &cnl_features },
-	{ INTEL_FAM6_ICELAKE_NNPI, &cnl_features },
-	{ INTEL_FAM6_ROCKETLAKE, &cnl_features },
-	{ INTEL_FAM6_TIGERLAKE_L, &cnl_features },
-	{ INTEL_FAM6_TIGERLAKE, &cnl_features },
-	{ INTEL_FAM6_SAPPHIRERAPIDS_X, &spr_features },
-	{ INTEL_FAM6_EMERALDRAPIDS_X, &spr_features },
-	{ INTEL_FAM6_GRANITERAPIDS_X, &spr_features },
-	{ INTEL_FAM6_LAKEFIELD, &cnl_features },
-	{ INTEL_FAM6_ALDERLAKE, &adl_features },
-	{ INTEL_FAM6_ALDERLAKE_L, &adl_features },
-	{ INTEL_FAM6_RAPTORLAKE, &adl_features },
-	{ INTEL_FAM6_RAPTORLAKE_P, &adl_features },
-	{ INTEL_FAM6_RAPTORLAKE_S, &adl_features },
-	{ INTEL_FAM6_METEORLAKE, &cnl_features },
-	{ INTEL_FAM6_METEORLAKE_L, &cnl_features },
-	{ INTEL_FAM6_ARROWLAKE_H, &arl_features },
-	{ INTEL_FAM6_ARROWLAKE_U, &arl_features },
-	{ INTEL_FAM6_ARROWLAKE, &arl_features },
-	{ INTEL_FAM6_LUNARLAKE_M, &arl_features },
-	{ INTEL_FAM6_ATOM_SILVERMONT, &slv_features },
-	{ INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features },
-	{ INTEL_FAM6_ATOM_AIRMONT, &amt_features },
-	{ INTEL_FAM6_ATOM_GOLDMONT, &gmt_features },
-	{ INTEL_FAM6_ATOM_GOLDMONT_D, &gmtd_features },
-	{ INTEL_FAM6_ATOM_GOLDMONT_PLUS, &gmtp_features },
-	{ INTEL_FAM6_ATOM_TREMONT_D, &tmtd_features },
-	{ INTEL_FAM6_ATOM_TREMONT, &tmt_features },
-	{ INTEL_FAM6_ATOM_TREMONT_L, &tmt_features },
-	{ INTEL_FAM6_ATOM_GRACEMONT, &adl_features },
-	{ INTEL_FAM6_ATOM_CRESTMONT_X, &srf_features },
-	{ INTEL_FAM6_ATOM_CRESTMONT, &grr_features },
-	{ INTEL_FAM6_XEON_PHI_KNL, &knl_features },
-	{ INTEL_FAM6_XEON_PHI_KNM, &knl_features },
+	{ INTEL_NEHALEM, &nhm_features },
+	{ INTEL_NEHALEM_G, &nhm_features },
+	{ INTEL_NEHALEM_EP, &nhm_features },
+	{ INTEL_NEHALEM_EX, &nhx_features },
+	{ INTEL_WESTMERE, &nhm_features },
+	{ INTEL_WESTMERE_EP, &nhm_features },
+	{ INTEL_WESTMERE_EX, &nhx_features },
+	{ INTEL_SANDYBRIDGE, &snb_features },
+	{ INTEL_SANDYBRIDGE_X, &snx_features },
+	{ INTEL_IVYBRIDGE, &ivb_features },
+	{ INTEL_IVYBRIDGE_X, &ivx_features },
+	{ INTEL_HASWELL, &hsw_features },
+	{ INTEL_HASWELL_X, &hsx_features },
+	{ INTEL_HASWELL_L, &hswl_features },
+	{ INTEL_HASWELL_G, &hswg_features },
+	{ INTEL_BROADWELL, &bdw_features },
+	{ INTEL_BROADWELL_G, &bdwg_features },
+	{ INTEL_BROADWELL_X, &bdx_features },
+	{ INTEL_BROADWELL_D, &bdx_features },
+	{ INTEL_SKYLAKE_L, &skl_features },
+	{ INTEL_SKYLAKE, &skl_features },
+	{ INTEL_SKYLAKE_X, &skx_features },
+	{ INTEL_KABYLAKE_L, &skl_features },
+	{ INTEL_KABYLAKE, &skl_features },
+	{ INTEL_COMETLAKE, &skl_features },
+	{ INTEL_COMETLAKE_L, &skl_features },
+	{ INTEL_CANNONLAKE_L, &cnl_features },
+	{ INTEL_ICELAKE_X, &icx_features },
+	{ INTEL_ICELAKE_D, &icx_features },
+	{ INTEL_ICELAKE_L, &cnl_features },
+	{ INTEL_ICELAKE_NNPI, &cnl_features },
+	{ INTEL_ROCKETLAKE, &cnl_features },
+	{ INTEL_TIGERLAKE_L, &cnl_features },
+	{ INTEL_TIGERLAKE, &cnl_features },
+	{ INTEL_SAPPHIRERAPIDS_X, &spr_features },
+	{ INTEL_EMERALDRAPIDS_X, &spr_features },
+	{ INTEL_GRANITERAPIDS_X, &spr_features },
+	{ INTEL_LAKEFIELD, &cnl_features },
+	{ INTEL_ALDERLAKE, &adl_features },
+	{ INTEL_ALDERLAKE_L, &adl_features },
+	{ INTEL_RAPTORLAKE, &adl_features },
+	{ INTEL_RAPTORLAKE_P, &adl_features },
+	{ INTEL_RAPTORLAKE_S, &adl_features },
+	{ INTEL_METEORLAKE, &cnl_features },
+	{ INTEL_METEORLAKE_L, &cnl_features },
+	{ INTEL_ARROWLAKE_H, &arl_features },
+	{ INTEL_ARROWLAKE_U, &arl_features },
+	{ INTEL_ARROWLAKE, &arl_features },
+	{ INTEL_LUNARLAKE_M, &arl_features },
+	{ INTEL_ATOM_SILVERMONT, &slv_features },
+	{ INTEL_ATOM_SILVERMONT_D, &slvd_features },
+	{ INTEL_ATOM_AIRMONT, &amt_features },
+	{ INTEL_ATOM_GOLDMONT, &gmt_features },
+	{ INTEL_ATOM_GOLDMONT_D, &gmtd_features },
+	{ INTEL_ATOM_GOLDMONT_PLUS, &gmtp_features },
+	{ INTEL_ATOM_TREMONT_D, &tmtd_features },
+	{ INTEL_ATOM_TREMONT, &tmt_features },
+	{ INTEL_ATOM_TREMONT_L, &tmt_features },
+	{ INTEL_ATOM_GRACEMONT, &adl_features },
+	{ INTEL_ATOM_CRESTMONT_X, &srf_features },
+	{ INTEL_ATOM_CRESTMONT, &grr_features },
+	{ INTEL_XEON_PHI_KNL, &knl_features },
+	{ INTEL_XEON_PHI_KNM, &knl_features },
 	/*
 	 * Missing support for
-	 * INTEL_FAM6_ICELAKE
-	 * INTEL_FAM6_ATOM_SILVERMONT_MID
-	 * INTEL_FAM6_ATOM_AIRMONT_MID
-	 * INTEL_FAM6_ATOM_AIRMONT_NP
+	 * INTEL_ICELAKE
+	 * INTEL_ATOM_SILVERMONT_MID
+	 * INTEL_ATOM_AIRMONT_MID
+	 * INTEL_ATOM_AIRMONT_NP
 	 */
 	{ 0, NULL },
 };
@@ -1003,11 +1053,11 @@ void probe_platform_features(unsigned int family, unsigned int model)
 		return;
 	}
 
-	if (!genuine_intel || family != 6)
+	if (!genuine_intel)
 		return;
 
 	for (i = 0; turbostat_pdata[i].features; i++) {
-		if (turbostat_pdata[i].model == model) {
+		if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) {
 			platform = turbostat_pdata[i].features;
 			return;
 		}
@@ -1034,8 +1084,13 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi
 #define MAX_ADDED_THREAD_COUNTERS 24
 #define MAX_ADDED_CORE_COUNTERS 8
 #define MAX_ADDED_PACKAGE_COUNTERS 16
+#define PMT_MAX_ADDED_THREAD_COUNTERS 24
+#define PMT_MAX_ADDED_CORE_COUNTERS 8
+#define PMT_MAX_ADDED_PACKAGE_COUNTERS 16
 #define BITMASK_SIZE 32
 
+#define ZERO_ARRAY(arr) (memset(arr, 0, sizeof(arr)) + __must_be_array(arr))
+
 /* Indexes used to map data read from perf and MSRs into global variables */
 enum rapl_rci_index {
 	RAPL_RCI_INDEX_ENERGY_PKG = 0,
@@ -1056,19 +1111,13 @@ enum rapl_unit {
 
 struct rapl_counter_info_t {
 	unsigned long long data[NUM_RAPL_COUNTERS];
-	enum rapl_source source[NUM_RAPL_COUNTERS];
+	enum counter_source source[NUM_RAPL_COUNTERS];
 	unsigned long long flags[NUM_RAPL_COUNTERS];
 	double scale[NUM_RAPL_COUNTERS];
 	enum rapl_unit unit[NUM_RAPL_COUNTERS];
-
-	union {
-		/* Active when source == RAPL_SOURCE_MSR */
-		struct {
-			unsigned long long msr[NUM_RAPL_COUNTERS];
-			unsigned long long msr_mask[NUM_RAPL_COUNTERS];
-			int msr_shift[NUM_RAPL_COUNTERS];
-		};
-	};
+	unsigned long long msr[NUM_RAPL_COUNTERS];
+	unsigned long long msr_mask[NUM_RAPL_COUNTERS];
+	int msr_shift[NUM_RAPL_COUNTERS];
 
 	int fd_perf;
 };
@@ -1224,7 +1273,7 @@ enum ccstate_rci_index {
 
 struct cstate_counter_info_t {
 	unsigned long long data[NUM_CSTATE_COUNTERS];
-	enum cstate_source source[NUM_CSTATE_COUNTERS];
+	enum counter_source source[NUM_CSTATE_COUNTERS];
 	unsigned long long msr[NUM_CSTATE_COUNTERS];
 	int fd_perf_core;
 	int fd_perf_pkg;
@@ -1361,6 +1410,167 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = {
 	  },
 };
 
+/* Indexes used to map data read from perf and MSRs into global variables */
+enum msr_rci_index {
+	MSR_RCI_INDEX_APERF = 0,
+	MSR_RCI_INDEX_MPERF = 1,
+	MSR_RCI_INDEX_SMI = 2,
+	NUM_MSR_COUNTERS,
+};
+
+struct msr_counter_info_t {
+	unsigned long long data[NUM_MSR_COUNTERS];
+	enum counter_source source[NUM_MSR_COUNTERS];
+	unsigned long long msr[NUM_MSR_COUNTERS];
+	unsigned long long msr_mask[NUM_MSR_COUNTERS];
+	int fd_perf;
+};
+
+struct msr_counter_info_t *msr_counter_info;
+unsigned int msr_counter_info_size;
+
+struct msr_counter_arch_info {
+	const char *perf_subsys;
+	const char *perf_name;
+	unsigned long long msr;
+	unsigned long long msr_mask;
+	unsigned int rci_index;	/* Maps data from perf counters to global variables */
+	bool needed;
+	bool present;
+};
+
+enum msr_arch_info_index {
+	MSR_ARCH_INFO_APERF_INDEX = 0,
+	MSR_ARCH_INFO_MPERF_INDEX = 1,
+	MSR_ARCH_INFO_SMI_INDEX = 2,
+};
+
+static struct msr_counter_arch_info msr_counter_arch_infos[] = {
+	[MSR_ARCH_INFO_APERF_INDEX] = {
+				       .perf_subsys = "msr",
+				       .perf_name = "aperf",
+				       .msr = MSR_IA32_APERF,
+				       .msr_mask = 0xFFFFFFFFFFFFFFFF,
+				       .rci_index = MSR_RCI_INDEX_APERF,
+				        },
+
+	[MSR_ARCH_INFO_MPERF_INDEX] = {
+				       .perf_subsys = "msr",
+				       .perf_name = "mperf",
+				       .msr = MSR_IA32_MPERF,
+				       .msr_mask = 0xFFFFFFFFFFFFFFFF,
+				       .rci_index = MSR_RCI_INDEX_MPERF,
+				        },
+
+	[MSR_ARCH_INFO_SMI_INDEX] = {
+				     .perf_subsys = "msr",
+				     .perf_name = "smi",
+				     .msr = MSR_SMI_COUNT,
+				     .msr_mask = 0xFFFFFFFF,
+				     .rci_index = MSR_RCI_INDEX_SMI,
+				      },
+};
+
+/* Can be redefined when compiling, useful for testing. */
+#ifndef SYSFS_TELEM_PATH
+#define SYSFS_TELEM_PATH "/sys/class/intel_pmt"
+#endif
+
+#define PMT_COUNTER_MTL_DC6_OFFSET 120
+#define PMT_COUNTER_MTL_DC6_LSB    0
+#define PMT_COUNTER_MTL_DC6_MSB    63
+#define PMT_MTL_DC6_GUID           0x1a067102
+
+#define PMT_COUNTER_NAME_SIZE_BYTES      16
+#define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32
+
+struct pmt_mmio {
+	struct pmt_mmio *next;
+
+	unsigned int guid;
+	unsigned int size;
+
+	/* Base pointer to the mmaped memory. */
+	void *mmio_base;
+
+	/*
+	 * Offset to be applied to the mmio_base
+	 * to get the beginning of the PMT counters for given GUID.
+	 */
+	unsigned long pmt_offset;
+} *pmt_mmios;
+
+enum pmt_datatype {
+	PMT_TYPE_RAW,
+	PMT_TYPE_XTAL_TIME,
+};
+
+struct pmt_domain_info {
+	/*
+	 * Pointer to the MMIO obtained by applying a counter offset
+	 * to the mmio_base of the mmaped region for the given GUID.
+	 *
+	 * This is where to read the raw value of the counter from.
+	 */
+	unsigned long *pcounter;
+};
+
+struct pmt_counter {
+	struct pmt_counter *next;
+
+	/* PMT metadata */
+	char name[PMT_COUNTER_NAME_SIZE_BYTES];
+	enum pmt_datatype type;
+	enum counter_scope scope;
+	unsigned int lsb;
+	unsigned int msb;
+
+	/* BIC-like metadata */
+	enum counter_format format;
+
+	unsigned int num_domains;
+	struct pmt_domain_info *domains;
+};
+
+unsigned int pmt_counter_get_width(const struct pmt_counter *p)
+{
+	return (p->msb - p->lsb) + 1;
+}
+
+void pmt_counter_resize_(struct pmt_counter *pcounter, unsigned int new_size)
+{
+	struct pmt_domain_info *new_mem;
+
+	new_mem = (struct pmt_domain_info *)reallocarray(pcounter->domains, new_size, sizeof(*pcounter->domains));
+	if (!new_mem) {
+		fprintf(stderr, "%s: failed to allocate memory for PMT counters\n", __func__);
+		exit(1);
+	}
+
+	/* Zero initialize just allocated memory. */
+	const size_t num_new_domains = new_size - pcounter->num_domains;
+
+	memset(&new_mem[pcounter->num_domains], 0, num_new_domains * sizeof(*pcounter->domains));
+
+	pcounter->num_domains = new_size;
+	pcounter->domains = new_mem;
+}
+
+void pmt_counter_resize(struct pmt_counter *pcounter, unsigned int new_size)
+{
+	/*
+	 * Allocate more memory ahead of time.
+	 *
+	 * Always allocate space for at least 8 elements
+	 * and double the size when growing.
+	 */
+	if (new_size < 8)
+		new_size = 8;
+	new_size = MAX(new_size, pcounter->num_domains * 2);
+
+	pmt_counter_resize_(pcounter, new_size);
+}
+
 struct thread_data {
 	struct timeval tv_begin;
 	struct timeval tv_end;
@@ -1378,6 +1588,8 @@ struct thread_data {
 	unsigned int flags;
 	bool is_atom;
 	unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
+	unsigned long long perf_counter[MAX_ADDED_THREAD_COUNTERS];
+	unsigned long long pmt_counter[PMT_MAX_ADDED_THREAD_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -1391,6 +1603,8 @@ struct core_data {
 	unsigned int core_id;
 	unsigned long long core_throt_cnt;
 	unsigned long long counter[MAX_ADDED_CORE_COUNTERS];
+	unsigned long long perf_counter[MAX_ADDED_CORE_COUNTERS];
+	unsigned long long pmt_counter[PMT_MAX_ADDED_CORE_COUNTERS];
 } *core_even, *core_odd;
 
 struct pkg_data {
@@ -1423,7 +1637,10 @@ struct pkg_data {
 	struct rapl_counter rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
 	unsigned int uncore_mhz;
+	unsigned long long die_c6;
 	unsigned long long counter[MAX_ADDED_PACKAGE_COUNTERS];
+	unsigned long long perf_counter[MAX_ADDED_PACKAGE_COUNTERS];
+	unsigned long long pmt_counter[PMT_MAX_ADDED_PACKAGE_COUNTERS];
 } *package_even, *package_odd;
 
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -1558,12 +1775,25 @@ int idx_valid(int idx)
 }
 
 struct sys_counters {
+	/* MSR added counters */
 	unsigned int added_thread_counters;
 	unsigned int added_core_counters;
 	unsigned int added_package_counters;
 	struct msr_counter *tp;
 	struct msr_counter *cp;
 	struct msr_counter *pp;
+
+	/* perf added counters */
+	unsigned int added_thread_perf_counters;
+	unsigned int added_core_perf_counters;
+	unsigned int added_package_perf_counters;
+	struct perf_counter_info *perf_tp;
+	struct perf_counter_info *perf_cp;
+	struct perf_counter_info *perf_pp;
+
+	struct pmt_counter *pmt_tp;
+	struct pmt_counter *pmt_cp;
+	struct pmt_counter *pmt_pp;
 } sys;
 
 static size_t free_msr_counters_(struct msr_counter **pp)
@@ -1747,7 +1977,7 @@ int get_msr_fd(int cpu)
 
 static void bic_disable_msr_access(void)
 {
-	const unsigned long bic_msrs = BIC_SMI | BIC_Mod_c6 | BIC_CoreTmp |
+	const unsigned long bic_msrs = BIC_Mod_c6 | BIC_CoreTmp |
 	    BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_PkgTmp;
 
 	bic_enabled &= ~bic_msrs;
@@ -1823,6 +2053,23 @@ int probe_msr(int cpu, off_t offset)
 	return 0;
 }
 
+/* Convert CPU ID to domain ID for given added perf counter. */
+unsigned int cpu_to_domain(const struct perf_counter_info *pc, int cpu)
+{
+	switch (pc->scope) {
+	case SCOPE_CPU:
+		return cpu;
+
+	case SCOPE_CORE:
+		return cpus[cpu].physical_core_id;
+
+	case SCOPE_PACKAGE:
+		return cpus[cpu].physical_package_id;
+	}
+
+	__builtin_unreachable();
+}
+
 #define MAX_DEFERRED 16
 char *deferred_add_names[MAX_DEFERRED];
 char *deferred_skip_names[MAX_DEFERRED];
@@ -1846,9 +2093,12 @@ void help(void)
 		"to print statistics, until interrupted.\n"
 		"  -a, --add	add a counter\n"
 		"		  eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
+		"		  eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n"
+		"		  eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n"
 		"  -c, --cpu	cpu-set	limit output to summary plus cpu-set:\n"
 		"		  {core | package | j,k,l..m,n-p }\n"
 		"  -d, --debug	displays usec, Time_Of_Day_Seconds and more debugging\n"
+		"		debug messages are printed to stderr\n"
 		"  -D, --Dump	displays the raw counter values\n"
 		"  -e, --enable	[all | column]\n"
 		"		shows all or the specified disabled column\n"
@@ -1955,6 +2205,8 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
 void print_header(char *delim)
 {
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 	int printed = 0;
 
 	if (DO_BIC(BIC_USEC))
@@ -2012,6 +2264,40 @@ void print_header(char *delim)
 		}
 	}
 
+	for (pp = sys.perf_tp; pp; pp = pp->next) {
+
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 64)
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name);
+		} else {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name);
+		}
+	}
+
+	ppmt = sys.pmt_tp;
+	while (ppmt) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name);
+			else
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			outp += sprintf(outp, "%s%s", delim, ppmt->name);
+			break;
+		}
+
+		ppmt = ppmt->next;
+	}
+
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c3))
@@ -2052,6 +2338,40 @@ void print_header(char *delim)
 		}
 	}
 
+	for (pp = sys.perf_cp; pp; pp = pp->next) {
+
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 64)
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name);
+		} else {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name);
+		}
+	}
+
+	ppmt = sys.pmt_cp;
+	while (ppmt) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name);
+			else
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			outp += sprintf(outp, "%s%s", delim, ppmt->name);
+			break;
+		}
+
+		ppmt = ppmt->next;
+	}
+
 	if (DO_BIC(BIC_PkgTmp))
 		outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : ""));
 
@@ -2096,6 +2416,8 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Diec6))
+		outp += sprintf(outp, "%sDie%%c6", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_LPI))
 		outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_SYS_LPI))
@@ -2147,6 +2469,40 @@ void print_header(char *delim)
 		}
 	}
 
+	for (pp = sys.perf_pp; pp; pp = pp->next) {
+
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 64)
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name);
+		} else {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name);
+			else
+				outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name);
+		}
+	}
+
+	ppmt = sys.pmt_pp;
+	while (ppmt) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name);
+			else
+				outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			outp += sprintf(outp, "%s%s", delim, ppmt->name);
+			break;
+		}
+
+		ppmt = ppmt->next;
+	}
+
 	outp += sprintf(outp, "\n");
 }
 
@@ -2267,6 +2623,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	char *fmt8;
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 	char *delim = "\t";
 	int printed = 0;
 
@@ -2404,6 +2762,51 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		}
 	}
 
+	/* Added perf counters */
+	for (i = 0, pp = sys.perf_tp; pp; ++i, pp = pp->next) {
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 32)
+				outp +=
+				    sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+					    (unsigned int)t->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->perf_counter[i]);
+		} else if (pp->format == FORMAT_DELTA) {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->perf_counter[i]);
+		} else if (pp->format == FORMAT_PERCENT) {
+			if (pp->type == COUNTER_USEC)
+				outp +=
+				    sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+					    t->perf_counter[i] / interval_float / 10000);
+			else
+				outp +=
+				    sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->perf_counter[i] / tsc);
+		}
+	}
+
+	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+						(unsigned int)t->pmt_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->pmt_counter[i]);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			const unsigned long value_raw = t->pmt_counter[i];
+			const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
+			break;
+		}
+	}
+
 	/* C1 */
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1 / tsc);
@@ -2447,6 +2850,44 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		}
 	}
 
+	for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 32)
+				outp +=
+				    sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+					    (unsigned int)c->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->perf_counter[i]);
+		} else if (pp->format == FORMAT_DELTA) {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->perf_counter[i]);
+		} else if (pp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->perf_counter[i] / tsc);
+		}
+	}
+
+	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+						(unsigned int)c->pmt_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->pmt_counter[i]);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			const unsigned long value_raw = c->pmt_counter[i];
+			const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
+			break;
+		}
+	}
+
 	fmt8 = "%s%.2f";
 
 	if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
@@ -2526,6 +2967,10 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	if (DO_BIC(BIC_Pkgpc10))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc);
 
+	if (DO_BIC(BIC_Diec6))
+		outp +=
+		    sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->die_c6 / crystal_hz / interval_float);
+
 	if (DO_BIC(BIC_CPU_LPI)) {
 		if (p->cpu_lpi >= 0)
 			outp +=
@@ -2601,6 +3046,47 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->counter[i] / 1000);
 	}
 
+	for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW) {
+			if (pp->width == 32)
+				outp +=
+				    sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+					    (unsigned int)p->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->perf_counter[i]);
+		} else if (pp->format == FORMAT_DELTA) {
+			if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns)
+				outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->perf_counter[i]);
+			else
+				outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->perf_counter[i]);
+		} else if (pp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->perf_counter[i] / tsc);
+		} else if (pp->type == COUNTER_K2M) {
+			outp +=
+			    sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->perf_counter[i] / 1000);
+		}
+	}
+
+	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
+		switch (ppmt->type) {
+		case PMT_TYPE_RAW:
+			if (pmt_counter_get_width(ppmt) <= 32)
+				outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""),
+						(unsigned int)p->pmt_counter[i]);
+			else
+				outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->pmt_counter[i]);
+
+			break;
+
+		case PMT_TYPE_XTAL_TIME:
+			const unsigned long value_raw = p->pmt_counter[i];
+			const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
+			break;
+		}
+	}
+
 done:
 	if (*(outp - 1) != '\n')
 		outp += sprintf(outp, "\n");
@@ -2654,6 +3140,8 @@ int delta_package(struct pkg_data *new, struct pkg_data *old)
 {
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 
 	if (DO_BIC(BIC_Totl_c0))
 		old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0;
@@ -2674,6 +3162,7 @@ int delta_package(struct pkg_data *new, struct pkg_data *old)
 	old->pc8 = new->pc8 - old->pc8;
 	old->pc9 = new->pc9 - old->pc9;
 	old->pc10 = new->pc10 - old->pc10;
+	old->die_c6 = new->die_c6 - old->die_c6;
 	old->cpu_lpi = new->cpu_lpi - old->cpu_lpi;
 	old->sys_lpi = new->sys_lpi - old->sys_lpi;
 	old->pkg_temp_c = new->pkg_temp_c;
@@ -2714,6 +3203,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old)
 			old->counter[i] = new->counter[i] - old->counter[i];
 	}
 
+	for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			old->perf_counter[i] = new->perf_counter[i];
+		else if (pp->format == FORMAT_AVERAGE)
+			old->perf_counter[i] = new->perf_counter[i];
+		else
+			old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
+		if (ppmt->format == FORMAT_RAW)
+			old->pmt_counter[i] = new->pmt_counter[i];
+		else
+			old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i];
+	}
+
 	return 0;
 }
 
@@ -2721,6 +3226,8 @@ void delta_core(struct core_data *new, struct core_data *old)
 {
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 
 	old->c3 = new->c3 - old->c3;
 	old->c6 = new->c6 - old->c6;
@@ -2737,6 +3244,20 @@ void delta_core(struct core_data *new, struct core_data *old)
 		else
 			old->counter[i] = new->counter[i] - old->counter[i];
 	}
+
+	for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			old->perf_counter[i] = new->perf_counter[i];
+		else
+			old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
+		if (ppmt->format == FORMAT_RAW)
+			old->pmt_counter[i] = new->pmt_counter[i];
+		else
+			old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i];
+	}
 }
 
 int soft_c1_residency_display(int bic)
@@ -2754,6 +3275,8 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 {
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 
 	/* we run cpuid just the 1st time, copy the results */
 	if (DO_BIC(BIC_APIC))
@@ -2832,6 +3355,21 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 		else
 			old->counter[i] = new->counter[i] - old->counter[i];
 	}
+
+	for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			old->perf_counter[i] = new->perf_counter[i];
+		else
+			old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
+		if (ppmt->format == FORMAT_RAW)
+			old->pmt_counter[i] = new->pmt_counter[i];
+		else
+			old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i];
+	}
+
 	return 0;
 }
 
@@ -2908,6 +3446,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->pc8 = 0;
 	p->pc9 = 0;
 	p->pc10 = 0;
+	p->die_c6 = 0;
 	p->cpu_lpi = 0;
 	p->sys_lpi = 0;
 
@@ -2934,6 +3473,14 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next)
 		p->counter[i] = 0;
+
+	memset(&t->perf_counter[0], 0, sizeof(t->perf_counter));
+	memset(&c->perf_counter[0], 0, sizeof(c->perf_counter));
+	memset(&p->perf_counter[0], 0, sizeof(p->perf_counter));
+
+	memset(&t->pmt_counter[0], 0, ARRAY_SIZE(t->pmt_counter));
+	memset(&c->pmt_counter[0], 0, ARRAY_SIZE(c->pmt_counter));
+	memset(&p->pmt_counter[0], 0, ARRAY_SIZE(p->pmt_counter));
 }
 
 void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src)
@@ -2954,6 +3501,8 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 
 	/* copy un-changing apic_id's */
 	if (DO_BIC(BIC_APIC))
@@ -2984,6 +3533,16 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		average.threads.counter[i] += t->counter[i];
 	}
 
+	for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			continue;
+		average.threads.perf_counter[i] += t->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
+		average.threads.pmt_counter[i] += t->pmt_counter[i];
+	}
+
 	/* sum per-core values only for 1st thread in core */
 	if (!is_cpu_first_thread_in_core(t, c, p))
 		return 0;
@@ -3004,6 +3563,16 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		average.cores.counter[i] += c->counter[i];
 	}
 
+	for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			continue;
+		average.cores.perf_counter[i] += c->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
+		average.cores.pmt_counter[i] += c->pmt_counter[i];
+	}
+
 	/* sum per-pkg values only for 1st core in pkg */
 	if (!is_cpu_first_core_in_package(t, c, p))
 		return 0;
@@ -3027,6 +3596,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	average.packages.pc8 += p->pc8;
 	average.packages.pc9 += p->pc9;
 	average.packages.pc10 += p->pc10;
+	average.packages.die_c6 += p->die_c6;
 
 	average.packages.cpu_lpi = p->cpu_lpi;
 	average.packages.sys_lpi = p->sys_lpi;
@@ -3055,6 +3625,18 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		else
 			average.packages.counter[i] += p->counter[i];
 	}
+
+	for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) {
+		if ((pp->format == FORMAT_RAW) && (topo.num_packages == 0))
+			average.packages.perf_counter[i] = p->perf_counter[i];
+		else
+			average.packages.perf_counter[i] += p->perf_counter[i];
+	}
+
+	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
+		average.packages.pmt_counter[i] += p->pmt_counter[i];
+	}
+
 	return 0;
 }
 
@@ -3066,6 +3648,8 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 {
 	int i;
 	struct msr_counter *mp;
+	struct perf_counter_info *pp;
+	struct pmt_counter *ppmt;
 
 	clear_counters(&average.threads, &average.cores, &average.packages);
 
@@ -3108,6 +3692,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 	average.packages.pc8 /= topo.allowed_packages;
 	average.packages.pc9 /= topo.allowed_packages;
 	average.packages.pc10 /= topo.allowed_packages;
+	average.packages.die_c6 /= topo.allowed_packages;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -3137,6 +3722,45 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 		}
 		average.packages.counter[i] /= topo.allowed_packages;
 	}
+
+	for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			continue;
+		if (pp->type == COUNTER_ITEMS) {
+			if (average.threads.perf_counter[i] > 9999999)
+				sums_need_wide_columns = 1;
+			continue;
+		}
+		average.threads.perf_counter[i] /= topo.allowed_cpus;
+	}
+	for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			continue;
+		if (pp->type == COUNTER_ITEMS) {
+			if (average.cores.perf_counter[i] > 9999999)
+				sums_need_wide_columns = 1;
+		}
+		average.cores.perf_counter[i] /= topo.allowed_cores;
+	}
+	for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) {
+		if (pp->format == FORMAT_RAW)
+			continue;
+		if (pp->type == COUNTER_ITEMS) {
+			if (average.packages.perf_counter[i] > 9999999)
+				sums_need_wide_columns = 1;
+		}
+		average.packages.perf_counter[i] /= topo.allowed_packages;
+	}
+
+	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
+		average.threads.pmt_counter[i] /= topo.allowed_cpus;
+	}
+	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
+		average.cores.pmt_counter[i] /= topo.allowed_cores;
+	}
+	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
+		average.packages.pmt_counter[i] /= topo.allowed_packages;
+	}
 }
 
 static unsigned long long rdtsc(void)
@@ -3382,30 +4006,6 @@ static unsigned int read_perf_counter_info_n(const char *const path, const char
 	return v;
 }
 
-static unsigned int read_msr_type(void)
-{
-	const char *const path = "/sys/bus/event_source/devices/msr/type";
-	const char *const format = "%u";
-
-	return read_perf_counter_info_n(path, format);
-}
-
-static unsigned int read_aperf_config(void)
-{
-	const char *const path = "/sys/bus/event_source/devices/msr/events/aperf";
-	const char *const format = "event=%x";
-
-	return read_perf_counter_info_n(path, format);
-}
-
-static unsigned int read_mperf_config(void)
-{
-	const char *const path = "/sys/bus/event_source/devices/msr/events/mperf";
-	const char *const format = "event=%x";
-
-	return read_perf_counter_info_n(path, format);
-}
-
 static unsigned int read_perf_type(const char *subsys)
 {
 	const char *const path_format = "/sys/bus/event_source/devices/%s/type";
@@ -3417,15 +4017,55 @@ static unsigned int read_perf_type(const char *subsys)
 	return read_perf_counter_info_n(path, format);
 }
 
-static unsigned int read_rapl_config(const char *subsys, const char *event_name)
+static unsigned int read_perf_config(const char *subsys, const char *event_name)
 {
 	const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s";
-	const char *const format = "event=%x";
+	FILE *fconfig = NULL;
 	char path[128];
+	char config_str[64];
+	unsigned int config;
+	unsigned int umask;
+	bool has_config = false;
+	bool has_umask = false;
+	unsigned int ret = -1;
 
 	snprintf(path, sizeof(path), path_format, subsys, event_name);
 
-	return read_perf_counter_info_n(path, format);
+	fconfig = fopen(path, "r");
+	if (!fconfig)
+		return -1;
+
+	if (fgets(config_str, ARRAY_SIZE(config_str), fconfig) != config_str)
+		goto cleanup_and_exit;
+
+	for (char *pconfig_str = &config_str[0]; pconfig_str;) {
+		if (sscanf(pconfig_str, "event=%x", &config) == 1) {
+			has_config = true;
+			goto next;
+		}
+
+		if (sscanf(pconfig_str, "umask=%x", &umask) == 1) {
+			has_umask = true;
+			goto next;
+		}
+
+next:
+		pconfig_str = strchr(pconfig_str, ',');
+		if (pconfig_str) {
+			*pconfig_str = '\0';
+			++pconfig_str;
+		}
+	}
+
+	if (!has_umask)
+		umask = 0;
+
+	if (has_config)
+		ret = (umask << 8) | config;
+
+cleanup_and_exit:
+	fclose(fconfig);
+	return ret;
 }
 
 static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name)
@@ -3444,7 +4084,7 @@ static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_na
 	return RAPL_UNIT_INVALID;
 }
 
-static double read_perf_rapl_scale(const char *subsys, const char *event_name)
+static double read_perf_scale(const char *subsys, const char *event_name)
 {
 	const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale";
 	const char *const format = "%lf";
@@ -3459,130 +4099,12 @@ static double read_perf_rapl_scale(const char *subsys, const char *event_name)
 	return scale;
 }
 
-static struct amperf_group_fd open_amperf_fd(int cpu)
-{
-	const unsigned int msr_type = read_msr_type();
-	const unsigned int aperf_config = read_aperf_config();
-	const unsigned int mperf_config = read_mperf_config();
-	struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 };
-
-	fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP);
-	fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP);
-
-	return fds;
-}
-
-static int get_amperf_fd(int cpu)
-{
-	assert(fd_amperf_percpu);
-
-	if (fd_amperf_percpu[cpu].aperf)
-		return fd_amperf_percpu[cpu].aperf;
-
-	fd_amperf_percpu[cpu] = open_amperf_fd(cpu);
-
-	return fd_amperf_percpu[cpu].aperf;
-}
-
-/* Read APERF, MPERF and TSC using the perf API. */
-static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu)
-{
-	union {
-		struct {
-			unsigned long nr_entries;
-			unsigned long aperf;
-			unsigned long mperf;
-		};
-
-		unsigned long as_array[3];
-	} cnt;
-
-	const int fd_amperf = get_amperf_fd(cpu);
-
-	/*
-	 * Read the TSC with rdtsc, because we want the absolute value and not
-	 * the offset from the start of the counter.
-	 */
-	t->tsc = rdtsc();
-
-	const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array));
-
-	if (n != sizeof(cnt.as_array))
-		return -2;
-
-	t->aperf = cnt.aperf * aperf_mperf_multiplier;
-	t->mperf = cnt.mperf * aperf_mperf_multiplier;
-
-	return 0;
-}
-
-/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */
-static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu)
-{
-	unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
-	int aperf_mperf_retry_count = 0;
-
-	/*
-	 * The TSC, APERF and MPERF must be read together for
-	 * APERF/MPERF and MPERF/TSC to give accurate results.
-	 *
-	 * Unfortunately, APERF and MPERF are read by
-	 * individual system call, so delays may occur
-	 * between them.  If the time to read them
-	 * varies by a large amount, we re-read them.
-	 */
-
-	/*
-	 * This initial dummy APERF read has been seen to
-	 * reduce jitter in the subsequent reads.
-	 */
-
-	if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
-		return -3;
-
-retry:
-	t->tsc = rdtsc();	/* re-read close to APERF */
-
-	tsc_before = t->tsc;
-
-	if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
-		return -3;
-
-	tsc_between = rdtsc();
-
-	if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
-		return -4;
-
-	tsc_after = rdtsc();
-
-	aperf_time = tsc_between - tsc_before;
-	mperf_time = tsc_after - tsc_between;
-
-	/*
-	 * If the system call latency to read APERF and MPERF
-	 * differ by more than 2x, then try again.
-	 */
-	if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
-		aperf_mperf_retry_count++;
-		if (aperf_mperf_retry_count < 5)
-			goto retry;
-		else
-			warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
-	}
-	aperf_mperf_retry_count = 0;
-
-	t->aperf = t->aperf * aperf_mperf_multiplier;
-	t->mperf = t->mperf * aperf_mperf_multiplier;
-
-	return 0;
-}
-
 size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci)
 {
 	size_t ret = 0;
 
 	for (int i = 0; i < NUM_RAPL_COUNTERS; ++i)
-		if (rci->source[i] == RAPL_SOURCE_PERF)
+		if (rci->source[i] == COUNTER_SOURCE_PERF)
 			++ret;
 
 	return ret;
@@ -3593,7 +4115,7 @@ static size_t cstate_counter_info_count_perf(const struct cstate_counter_info_t
 	size_t ret = 0;
 
 	for (int i = 0; i < NUM_CSTATE_COUNTERS; ++i)
-		if (cci->source[i] == CSTATE_SOURCE_PERF)
+		if (cci->source[i] == COUNTER_SOURCE_PERF)
 			++ret;
 
 	return ret;
@@ -3611,7 +4133,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct
 	unsigned long long perf_data[NUM_RAPL_COUNTERS + 1];
 	struct rapl_counter_info_t *rci;
 
-	if (debug)
+	if (debug >= 2)
 		fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain);
 
 	assert(rapl_counter_info_perdomain);
@@ -3634,14 +4156,14 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct
 
 	for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) {
 		switch (rci->source[i]) {
-		case RAPL_SOURCE_NONE:
+		case COUNTER_SOURCE_NONE:
 			break;
 
-		case RAPL_SOURCE_PERF:
+		case COUNTER_SOURCE_PERF:
 			assert(pi < ARRAY_SIZE(perf_data));
 			assert(rci->fd_perf != -1);
 
-			if (debug)
+			if (debug >= 2)
 				fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n",
 					i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]);
 
@@ -3650,8 +4172,8 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct
 			++pi;
 			break;
 
-		case RAPL_SOURCE_MSR:
-			if (debug)
+		case COUNTER_SOURCE_MSR:
+			if (debug >= 2)
 				fprintf(stderr, "Reading rapl counter via msr at %u\n", i);
 
 			assert(!no_msr);
@@ -3709,15 +4231,15 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat
 
 	struct cstate_counter_info_t *cci;
 
-	if (debug)
+	if (debug >= 2)
 		fprintf(stderr, "%s: cpu%d\n", __func__, cpu);
 
 	assert(ccstate_counter_info);
 	assert(cpu <= ccstate_counter_info_size);
 
-	memset(perf_data, 0, sizeof(perf_data));
-	memset(perf_data_core, 0, sizeof(perf_data_core));
-	memset(perf_data_pkg, 0, sizeof(perf_data_pkg));
+	ZERO_ARRAY(perf_data);
+	ZERO_ARRAY(perf_data_core);
+	ZERO_ARRAY(perf_data_pkg);
 
 	cci = &ccstate_counter_info[cpu];
 
@@ -3772,30 +4294,28 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat
 
 	for (unsigned int i = 0, pi = 0; i < NUM_CSTATE_COUNTERS; ++i) {
 		switch (cci->source[i]) {
-		case CSTATE_SOURCE_NONE:
+		case COUNTER_SOURCE_NONE:
 			break;
 
-		case CSTATE_SOURCE_PERF:
+		case COUNTER_SOURCE_PERF:
 			assert(pi < ARRAY_SIZE(perf_data));
 			assert(cci->fd_perf_core != -1 || cci->fd_perf_pkg != -1);
 
-			if (debug) {
+			if (debug >= 2)
 				fprintf(stderr, "cstate via %s %u: %llu\n", "perf", i, perf_data[pi]);
-			}
 
 			cci->data[i] = perf_data[pi];
 
 			++pi;
 			break;
 
-		case CSTATE_SOURCE_MSR:
+		case COUNTER_SOURCE_MSR:
 			assert(!no_msr);
 			if (get_msr(cpu, cci->msr[i], &cci->data[i]))
 				return -13 - i;
 
-			if (debug) {
+			if (debug >= 2)
 				fprintf(stderr, "cstate via %s0x%llx %u: %llu\n", "msr", cci->msr[i], i, cci->data[i]);
-			}
 
 			break;
 		}
@@ -3809,7 +4329,7 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat
 	 * when invoked for the thread sibling.
 	 */
 #define PERF_COUNTER_WRITE_DATA(out_counter, index) do {	\
-	if (cci->source[index] != CSTATE_SOURCE_NONE)		\
+	if (cci->source[index] != COUNTER_SOURCE_NONE)		\
 		out_counter = cci->data[index];			\
 } while (0)
 
@@ -3833,6 +4353,135 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat
 	return 0;
 }
 
+size_t msr_counter_info_count_perf(const struct msr_counter_info_t *mci)
+{
+	size_t ret = 0;
+
+	for (int i = 0; i < NUM_MSR_COUNTERS; ++i)
+		if (mci->source[i] == COUNTER_SOURCE_PERF)
+			++ret;
+
+	return ret;
+}
+
+int get_smi_aperf_mperf(unsigned int cpu, struct thread_data *t)
+{
+	unsigned long long perf_data[NUM_MSR_COUNTERS + 1];
+
+	struct msr_counter_info_t *mci;
+
+	if (debug >= 2)
+		fprintf(stderr, "%s: cpu%d\n", __func__, cpu);
+
+	assert(msr_counter_info);
+	assert(cpu <= msr_counter_info_size);
+
+	mci = &msr_counter_info[cpu];
+
+	ZERO_ARRAY(perf_data);
+	ZERO_ARRAY(mci->data);
+
+	if (mci->fd_perf != -1) {
+		const size_t num_perf_counters = msr_counter_info_count_perf(mci);
+		const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long);
+		const ssize_t actual_read_size = read(mci->fd_perf, &perf_data[0], sizeof(perf_data));
+
+		if (actual_read_size != expected_read_size)
+			err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size,
+			    actual_read_size);
+	}
+
+	for (unsigned int i = 0, pi = 1; i < NUM_MSR_COUNTERS; ++i) {
+		switch (mci->source[i]) {
+		case COUNTER_SOURCE_NONE:
+			break;
+
+		case COUNTER_SOURCE_PERF:
+			assert(pi < ARRAY_SIZE(perf_data));
+			assert(mci->fd_perf != -1);
+
+			if (debug >= 2)
+				fprintf(stderr, "Reading msr counter via perf at %u: %llu\n", i, perf_data[pi]);
+
+			mci->data[i] = perf_data[pi];
+
+			++pi;
+			break;
+
+		case COUNTER_SOURCE_MSR:
+			assert(!no_msr);
+
+			if (get_msr(cpu, mci->msr[i], &mci->data[i]))
+				return -2 - i;
+
+			mci->data[i] &= mci->msr_mask[i];
+
+			if (debug >= 2)
+				fprintf(stderr, "Reading msr counter via msr at %u: %llu\n", i, mci->data[i]);
+
+			break;
+		}
+	}
+
+	BUILD_BUG_ON(NUM_MSR_COUNTERS != 3);
+	t->aperf = mci->data[MSR_RCI_INDEX_APERF];
+	t->mperf = mci->data[MSR_RCI_INDEX_MPERF];
+	t->smi_count = mci->data[MSR_RCI_INDEX_SMI];
+
+	return 0;
+}
+
+int perf_counter_info_read_values(struct perf_counter_info *pp, int cpu, unsigned long long *out, size_t out_size)
+{
+	unsigned int domain;
+	unsigned long long value;
+	int fd_counter;
+
+	for (size_t i = 0; pp; ++i, pp = pp->next) {
+		domain = cpu_to_domain(pp, cpu);
+		assert(domain < pp->num_domains);
+
+		fd_counter = pp->fd_perf_per_domain[domain];
+
+		if (fd_counter == -1)
+			continue;
+
+		if (read(fd_counter, &value, sizeof(value)) != sizeof(value))
+			return 1;
+
+		assert(i < out_size);
+		out[i] = value * pp->scale;
+	}
+
+	return 0;
+}
+
+unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb)
+{
+	unsigned long mask;
+
+	if (msb == 63)
+		mask = 0xffffffffffffffff;
+	else
+		mask = ((1 << (msb + 1)) - 1);
+
+	mask -= (1 << lsb) - 1;
+
+	return mask;
+}
+
+unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id)
+{
+	assert(domain_id < ppmt->num_domains);
+
+	const unsigned long *pmmio = ppmt->domains[domain_id].pcounter;
+	const unsigned long value = pmmio ? *pmmio : 0;
+	const unsigned long value_mask = pmt_gen_value_mask(ppmt->lsb, ppmt->msb);
+	const unsigned long value_shift = ppmt->lsb;
+
+	return (value & value_mask) >> value_shift;
+}
+
 /*
  * get_counters(...)
  * migrate to cpu
@@ -3843,6 +4492,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	int cpu = t->cpu_id;
 	unsigned long long msr;
 	struct msr_counter *mp;
+	struct pmt_counter *pp;
 	int i;
 	int status;
 
@@ -3858,24 +4508,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
-	    || soft_c1_residency_display(BIC_Avg_MHz)) {
-		int status = -1;
-
-		assert(!no_perf || !no_msr);
-
-		switch (amperf_source) {
-		case AMPERF_SOURCE_PERF:
-			status = read_aperf_mperf_tsc_perf(t, cpu);
-			break;
-		case AMPERF_SOURCE_MSR:
-			status = read_aperf_mperf_tsc_msr(t, cpu);
-			break;
-		}
-
-		if (status != 0)
-			return status;
-	}
+	get_smi_aperf_mperf(cpu, t);
 
 	if (DO_BIC(BIC_IPC))
 		if (read(get_instr_count_fd(cpu), &t->instr_count, sizeof(long long)) != sizeof(long long))
@@ -3883,11 +4516,6 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	if (DO_BIC(BIC_IRQ))
 		t->irq_count = irqs_per_cpu[cpu];
-	if (DO_BIC(BIC_SMI)) {
-		if (get_msr(cpu, MSR_SMI_COUNT, &msr))
-			return -5;
-		t->smi_count = msr & 0xFFFFFFFF;
-	}
 
 	get_cstate_counters(cpu, t, c, p);
 
@@ -3896,6 +4524,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -10;
 	}
 
+	if (perf_counter_info_read_values(sys.perf_tp, cpu, t->perf_counter, MAX_ADDED_THREAD_COUNTERS))
+		return -10;
+
+	for (i = 0, pp = sys.pmt_tp; pp; i++, pp = pp->next)
+		t->pmt_counter[i] = pmt_read_counter(pp, t->cpu_id);
+
 	/* collect core counters only for 1st thread in core */
 	if (!is_cpu_first_thread_in_core(t, c, p))
 		goto done;
@@ -3934,6 +4568,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -10;
 	}
 
+	if (perf_counter_info_read_values(sys.perf_cp, cpu, c->perf_counter, MAX_ADDED_CORE_COUNTERS))
+		return -10;
+
+	for (i = 0, pp = sys.pmt_cp; pp; i++, pp = pp->next)
+		c->pmt_counter[i] = pmt_read_counter(pp, c->core_id);
+
 	/* collect package counters only for 1st core in package */
 	if (!is_cpu_first_core_in_package(t, c, p))
 		goto done;
@@ -4006,6 +4646,13 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_mp(cpu, mp, &p->counter[i], path))
 			return -10;
 	}
+
+	if (perf_counter_info_read_values(sys.perf_pp, cpu, p->perf_counter, MAX_ADDED_PACKAGE_COUNTERS))
+		return -10;
+
+	for (i = 0, pp = sys.pmt_pp; pp; i++, pp = pp->next)
+		p->pmt_counter[i] = pmt_read_counter(pp, p->package_id);
+
 done:
 	gettimeofday(&t->tv_end, (struct timezone *)NULL);
 
@@ -4469,25 +5116,6 @@ void free_fd_percpu(void)
 	fd_percpu = NULL;
 }
 
-void free_fd_amperf_percpu(void)
-{
-	int i;
-
-	if (!fd_amperf_percpu)
-		return;
-
-	for (i = 0; i < topo.max_cpu_num + 1; ++i) {
-		if (fd_amperf_percpu[i].mperf != 0)
-			close(fd_amperf_percpu[i].mperf);
-
-		if (fd_amperf_percpu[i].aperf != 0)
-			close(fd_amperf_percpu[i].aperf);
-	}
-
-	free(fd_amperf_percpu);
-	fd_amperf_percpu = NULL;
-}
-
 void free_fd_instr_count_percpu(void)
 {
 	if (!fd_instr_count_percpu)
@@ -4522,6 +5150,21 @@ void free_fd_cstate(void)
 	ccstate_counter_info_size = 0;
 }
 
+void free_fd_msr(void)
+{
+	if (!msr_counter_info)
+		return;
+
+	for (int cpu = 0; cpu < topo.max_cpu_num; ++cpu) {
+		if (msr_counter_info[cpu].fd_perf != -1)
+			close(msr_counter_info[cpu].fd_perf);
+	}
+
+	free(msr_counter_info);
+	msr_counter_info = NULL;
+	msr_counter_info_size = 0;
+}
+
 void free_fd_rapl_percpu(void)
 {
 	if (!rapl_counter_info_perdomain)
@@ -4539,6 +5182,36 @@ void free_fd_rapl_percpu(void)
 	rapl_counter_info_perdomain_size = 0;
 }
 
+void free_fd_added_perf_counters_(struct perf_counter_info *pp)
+{
+	if (!pp)
+		return;
+
+	if (!pp->fd_perf_per_domain)
+		return;
+
+	while (pp) {
+		for (size_t domain = 0; domain < pp->num_domains; ++domain) {
+			if (pp->fd_perf_per_domain[domain] != -1) {
+				close(pp->fd_perf_per_domain[domain]);
+				pp->fd_perf_per_domain[domain] = -1;
+			}
+		}
+
+		free(pp->fd_perf_per_domain);
+		pp->fd_perf_per_domain = NULL;
+
+		pp = pp->next;
+	}
+}
+
+void free_fd_added_perf_counters(void)
+{
+	free_fd_added_perf_counters_(sys.perf_tp);
+	free_fd_added_perf_counters_(sys.perf_cp);
+	free_fd_added_perf_counters_(sys.perf_pp);
+}
+
 void free_all_buffers(void)
 {
 	int i;
@@ -4581,9 +5254,10 @@ void free_all_buffers(void)
 
 	free_fd_percpu();
 	free_fd_instr_count_percpu();
-	free_fd_amperf_percpu();
+	free_fd_msr();
 	free_fd_rapl_percpu();
 	free_fd_cstate();
+	free_fd_added_perf_counters();
 
 	free(irq_column_2_cpu);
 	free(irqs_per_cpu);
@@ -4918,16 +5592,22 @@ static void update_effective_set(bool startup)
 }
 
 void linux_perf_init(void);
+void msr_perf_init(void);
 void rapl_perf_init(void);
 void cstate_perf_init(void);
+void added_perf_counters_init(void);
+void pmt_init(void);
 
 void re_initialize(void)
 {
 	free_all_buffers();
 	setup_all_buffers(false);
 	linux_perf_init();
+	msr_perf_init();
 	rapl_perf_init();
 	cstate_perf_init();
+	added_perf_counters_init();
+	pmt_init();
 	fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus,
 		topo.allowed_cpus);
 }
@@ -6779,22 +7459,13 @@ static int has_instr_count_access(void)
 	return has_access;
 }
 
-bool is_aperf_access_required(void)
-{
-	return BIC_IS_ENABLED(BIC_Avg_MHz)
-	    || BIC_IS_ENABLED(BIC_Busy)
-	    || BIC_IS_ENABLED(BIC_Bzy_MHz)
-	    || BIC_IS_ENABLED(BIC_IPC)
-	    || BIC_IS_ENABLED(BIC_CPU_c1);
-}
-
 int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
 			   double *scale_, enum rapl_unit *unit_)
 {
 	if (no_perf)
 		return -1;
 
-	const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name);
+	const double scale = read_perf_scale(cai->perf_subsys, cai->perf_name);
 
 	if (scale == 0.0)
 		return -1;
@@ -6805,7 +7476,7 @@ int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struc
 		return -1;
 
 	const unsigned int rapl_type = read_perf_type(cai->perf_subsys);
-	const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name);
+	const unsigned int rapl_energy_pkg_config = read_perf_config(cai->perf_subsys, cai->perf_name);
 
 	const int fd_counter =
 	    open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP);
@@ -6826,7 +7497,7 @@ int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct
 {
 	int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit);
 
-	if (debug)
+	if (debug >= 2)
 		fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu);
 
 	return ret;
@@ -6846,14 +7517,6 @@ void linux_perf_init(void)
 		if (fd_instr_count_percpu == NULL)
 			err(-1, "calloc fd_instr_count_percpu");
 	}
-
-	const bool aperf_required = is_aperf_access_required();
-
-	if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) {
-		fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu));
-		if (fd_amperf_percpu == NULL)
-			err(-1, "calloc fd_amperf_percpu");
-	}
 }
 
 void rapl_perf_init(void)
@@ -6875,7 +7538,7 @@ void rapl_perf_init(void)
 		rci->fd_perf = -1;
 		for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) {
 			rci->data[i] = 0;
-			rci->source[i] = RAPL_SOURCE_NONE;
+			rci->source[i] = COUNTER_SOURCE_NONE;
 		}
 	}
 
@@ -6917,14 +7580,14 @@ void rapl_perf_init(void)
 				/* Use perf API for this counter */
 				if (!no_perf && cai->perf_name
 				    && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) {
-					rci->source[cai->rci_index] = RAPL_SOURCE_PERF;
+					rci->source[cai->rci_index] = COUNTER_SOURCE_PERF;
 					rci->scale[cai->rci_index] = scale * cai->compat_scale;
 					rci->unit[cai->rci_index] = unit;
 					rci->flags[cai->rci_index] = cai->flags;
 
 					/* Use MSR for this counter */
 				} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
-					rci->source[cai->rci_index] = RAPL_SOURCE_MSR;
+					rci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
 					rci->msr[cai->rci_index] = cai->msr;
 					rci->msr_mask[cai->rci_index] = cai->msr_mask;
 					rci->msr_shift[cai->rci_index] = cai->msr_shift;
@@ -6934,7 +7597,7 @@ void rapl_perf_init(void)
 				}
 			}
 
-			if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE)
+			if (rci->source[cai->rci_index] != COUNTER_SOURCE_NONE)
 				has_counter = 1;
 		}
 
@@ -6946,75 +7609,11 @@ void rapl_perf_init(void)
 	free(domain_visited);
 }
 
-static int has_amperf_access_via_msr(void)
-{
-	if (no_msr)
-		return 0;
-
-	if (probe_msr(base_cpu, MSR_IA32_APERF))
-		return 0;
-
-	if (probe_msr(base_cpu, MSR_IA32_MPERF))
-		return 0;
-
-	return 1;
-}
-
-static int has_amperf_access_via_perf(void)
-{
-	struct amperf_group_fd fds;
-
-	/*
-	 * Cache the last result, so we don't warn the user multiple times
-	 *
-	 * Negative means cached, no access
-	 * Zero means not cached
-	 * Positive means cached, has access
-	 */
-	static int has_access_cached;
-
-	if (no_perf)
-		return 0;
-
-	if (has_access_cached != 0)
-		return has_access_cached > 0;
-
-	fds = open_amperf_fd(base_cpu);
-	has_access_cached = (fds.aperf != -1) && (fds.mperf != -1);
-
-	if (fds.aperf == -1)
-		warnx("Failed to access %s. Some of the counters may not be available\n"
-		      "\tRun as root to enable them or use %s to disable the access explicitly",
-		      "APERF perf counter", "--no-perf");
-	else
-		close(fds.aperf);
-
-	if (fds.mperf == -1)
-		warnx("Failed to access %s. Some of the counters may not be available\n"
-		      "\tRun as root to enable them or use %s to disable the access explicitly",
-		      "MPERF perf counter", "--no-perf");
-	else
-		close(fds.mperf);
-
-	if (has_access_cached == 0)
-		has_access_cached = -1;
-
-	return has_access_cached > 0;
-}
-
-/* Check if we can access APERF and MPERF */
+/* Assumes msr_counter_info is populated */
 static int has_amperf_access(void)
 {
-	if (!is_aperf_access_required())
-		return 0;
-
-	if (!no_msr && has_amperf_access_via_msr())
-		return 1;
-
-	if (!no_perf && has_amperf_access_via_perf())
-		return 1;
-
-	return 0;
+	return msr_counter_arch_infos[MSR_ARCH_INFO_APERF_INDEX].present &&
+	    msr_counter_arch_infos[MSR_ARCH_INFO_MPERF_INDEX].present;
 }
 
 int *get_cstate_perf_group_fd(struct cstate_counter_info_t *cci, const char *group_name)
@@ -7039,7 +7638,7 @@ int add_cstate_perf_counter_(int cpu, struct cstate_counter_info_t *cci, const s
 		return -1;
 
 	const unsigned int type = read_perf_type(cai->perf_subsys);
-	const unsigned int config = read_rapl_config(cai->perf_subsys, cai->perf_name);
+	const unsigned int config = read_perf_config(cai->perf_subsys, cai->perf_name);
 
 	const int fd_counter = open_perf_counter(cpu, type, config, *pfd_group, PERF_FORMAT_GROUP);
 
@@ -7057,12 +7656,120 @@ int add_cstate_perf_counter(int cpu, struct cstate_counter_info_t *cci, const st
 {
 	int ret = add_cstate_perf_counter_(cpu, cci, cai);
 
-	if (debug)
+	if (debug >= 2)
 		fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu);
 
 	return ret;
 }
 
+int add_msr_perf_counter_(int cpu, struct msr_counter_info_t *cci, const struct msr_counter_arch_info *cai)
+{
+	if (no_perf)
+		return -1;
+
+	const unsigned int type = read_perf_type(cai->perf_subsys);
+	const unsigned int config = read_perf_config(cai->perf_subsys, cai->perf_name);
+
+	const int fd_counter = open_perf_counter(cpu, type, config, cci->fd_perf, PERF_FORMAT_GROUP);
+
+	if (fd_counter == -1)
+		return -1;
+
+	/* If it's the first counter opened, make it a group descriptor */
+	if (cci->fd_perf == -1)
+		cci->fd_perf = fd_counter;
+
+	return fd_counter;
+}
+
+int add_msr_perf_counter(int cpu, struct msr_counter_info_t *cci, const struct msr_counter_arch_info *cai)
+{
+	int ret = add_msr_perf_counter_(cpu, cci, cai);
+
+	if (debug)
+		fprintf(stderr, "%s: %s/%s: %d (cpu: %d)\n", __func__, cai->perf_subsys, cai->perf_name, ret, cpu);
+
+	return ret;
+}
+
+void msr_perf_init_(void)
+{
+	const int mci_num = topo.max_cpu_num + 1;
+
+	msr_counter_info = calloc(mci_num, sizeof(*msr_counter_info));
+	if (!msr_counter_info)
+		err(1, "calloc msr_counter_info");
+	msr_counter_info_size = mci_num;
+
+	for (int cpu = 0; cpu < mci_num; ++cpu)
+		msr_counter_info[cpu].fd_perf = -1;
+
+	for (int cidx = 0; cidx < NUM_MSR_COUNTERS; ++cidx) {
+
+		struct msr_counter_arch_info *cai = &msr_counter_arch_infos[cidx];
+
+		cai->present = false;
+
+		for (int cpu = 0; cpu < mci_num; ++cpu) {
+
+			struct msr_counter_info_t *const cci = &msr_counter_info[cpu];
+
+			if (cpu_is_not_allowed(cpu))
+				continue;
+
+			if (cai->needed) {
+				/* Use perf API for this counter */
+				if (!no_perf && cai->perf_name && add_msr_perf_counter(cpu, cci, cai) != -1) {
+					cci->source[cai->rci_index] = COUNTER_SOURCE_PERF;
+					cai->present = true;
+
+					/* User MSR for this counter */
+				} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+					cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
+					cci->msr[cai->rci_index] = cai->msr;
+					cci->msr_mask[cai->rci_index] = cai->msr_mask;
+					cai->present = true;
+				}
+			}
+		}
+	}
+}
+
+/* Initialize data for reading perf counters from the MSR group. */
+void msr_perf_init(void)
+{
+	bool need_amperf = false, need_smi = false;
+	const bool need_soft_c1 = (!platform->has_msr_core_c1_res) && (platform->supported_cstates & CC1);
+
+	need_amperf = BIC_IS_ENABLED(BIC_Avg_MHz) || BIC_IS_ENABLED(BIC_Busy) || BIC_IS_ENABLED(BIC_Bzy_MHz)
+	    || BIC_IS_ENABLED(BIC_IPC) || need_soft_c1;
+
+	if (BIC_IS_ENABLED(BIC_SMI))
+		need_smi = true;
+
+	/* Enable needed counters */
+	msr_counter_arch_infos[MSR_ARCH_INFO_APERF_INDEX].needed = need_amperf;
+	msr_counter_arch_infos[MSR_ARCH_INFO_MPERF_INDEX].needed = need_amperf;
+	msr_counter_arch_infos[MSR_ARCH_INFO_SMI_INDEX].needed = need_smi;
+
+	msr_perf_init_();
+
+	const bool has_amperf = has_amperf_access();
+	const bool has_smi = msr_counter_arch_infos[MSR_ARCH_INFO_SMI_INDEX].present;
+
+	has_aperf_access = has_amperf;
+
+	if (has_amperf) {
+		BIC_PRESENT(BIC_Avg_MHz);
+		BIC_PRESENT(BIC_Busy);
+		BIC_PRESENT(BIC_Bzy_MHz);
+		BIC_PRESENT(BIC_SMI);
+	}
+
+	if (has_smi)
+		BIC_PRESENT(BIC_SMI);
+}
+
 void cstate_perf_init_(bool soft_c1)
 {
 	bool has_counter;
@@ -7127,17 +7834,17 @@ void cstate_perf_init_(bool soft_c1)
 				/* Use perf API for this counter */
 				if (!no_perf && cai->perf_name && add_cstate_perf_counter(cpu, cci, cai) != -1) {
 
-					cci->source[cai->rci_index] = CSTATE_SOURCE_PERF;
+					cci->source[cai->rci_index] = COUNTER_SOURCE_PERF;
 
 					/* User MSR for this counter */
 				} else if (!no_msr && cai->msr && pkg_cstate_limit >= cai->pkg_cstate_limit
 					   && probe_msr(cpu, cai->msr) == 0) {
-					cci->source[cai->rci_index] = CSTATE_SOURCE_MSR;
+					cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
 					cci->msr[cai->rci_index] = cai->msr;
 				}
 			}
 
-			if (cci->source[cai->rci_index] != CSTATE_SOURCE_NONE) {
+			if (cci->source[cai->rci_index] != COUNTER_SOURCE_NONE) {
 				has_counter = true;
 				cores_visited[core_id] = true;
 				pkg_visited[pkg_id] = true;
@@ -7320,12 +8027,6 @@ void process_cpuid()
 
 	__cpuid(0x6, eax, ebx, ecx, edx);
 	has_aperf = ecx & (1 << 0);
-	if (has_aperf && has_amperf_access()) {
-		BIC_PRESENT(BIC_Avg_MHz);
-		BIC_PRESENT(BIC_Busy);
-		BIC_PRESENT(BIC_Bzy_MHz);
-		BIC_PRESENT(BIC_IPC);
-	}
 	do_dts = eax & (1 << 0);
 	if (do_dts)
 		BIC_PRESENT(BIC_CoreTmp);
@@ -7442,6 +8143,11 @@ static void counter_info_init(void)
 		if (platform->has_msr_atom_pkg_c6_residency && cai->msr == MSR_PKG_C6_RESIDENCY)
 			cai->msr = MSR_ATOM_PKG_C6_RESIDENCY;
 	}
+
+	for (int i = 0; i < NUM_MSR_COUNTERS; ++i) {
+		msr_counter_arch_infos[i].present = false;
+		msr_counter_arch_infos[i].needed = false;
+	}
 }
 
 void probe_pm_features(void)
@@ -7817,21 +8523,6 @@ void set_base_cpu(void)
 	err(-ENODEV, "No valid cpus found");
 }
 
-static void set_amperf_source(void)
-{
-	amperf_source = AMPERF_SOURCE_PERF;
-
-	const bool aperf_required = is_aperf_access_required();
-
-	if (no_perf || !aperf_required || !has_amperf_access_via_perf())
-		amperf_source = AMPERF_SOURCE_MSR;
-
-	if (quiet || !debug)
-		return;
-
-	fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf");
-}
-
 bool has_added_counters(void)
 {
 	/*
@@ -7842,54 +8533,8 @@ bool has_added_counters(void)
 	return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters;
 }
 
-bool is_msr_access_required(void)
-{
-	if (no_msr)
-		return false;
-
-	if (has_added_counters())
-		return true;
-
-	return BIC_IS_ENABLED(BIC_SMI)
-	    || BIC_IS_ENABLED(BIC_CPU_c1)
-	    || BIC_IS_ENABLED(BIC_CPU_c3)
-	    || BIC_IS_ENABLED(BIC_CPU_c6)
-	    || BIC_IS_ENABLED(BIC_CPU_c7)
-	    || BIC_IS_ENABLED(BIC_Mod_c6)
-	    || BIC_IS_ENABLED(BIC_CoreTmp)
-	    || BIC_IS_ENABLED(BIC_Totl_c0)
-	    || BIC_IS_ENABLED(BIC_Any_c0)
-	    || BIC_IS_ENABLED(BIC_GFX_c0)
-	    || BIC_IS_ENABLED(BIC_CPUGFX)
-	    || BIC_IS_ENABLED(BIC_Pkgpc3)
-	    || BIC_IS_ENABLED(BIC_Pkgpc6)
-	    || BIC_IS_ENABLED(BIC_Pkgpc2)
-	    || BIC_IS_ENABLED(BIC_Pkgpc7)
-	    || BIC_IS_ENABLED(BIC_Pkgpc8)
-	    || BIC_IS_ENABLED(BIC_Pkgpc9)
-	    || BIC_IS_ENABLED(BIC_Pkgpc10)
-	    /* TODO: Multiplex access with perf */
-	    || BIC_IS_ENABLED(BIC_CorWatt)
-	    || BIC_IS_ENABLED(BIC_Cor_J)
-	    || BIC_IS_ENABLED(BIC_PkgWatt)
-	    || BIC_IS_ENABLED(BIC_CorWatt)
-	    || BIC_IS_ENABLED(BIC_GFXWatt)
-	    || BIC_IS_ENABLED(BIC_RAMWatt)
-	    || BIC_IS_ENABLED(BIC_Pkg_J)
-	    || BIC_IS_ENABLED(BIC_Cor_J)
-	    || BIC_IS_ENABLED(BIC_GFX_J)
-	    || BIC_IS_ENABLED(BIC_RAM_J)
-	    || BIC_IS_ENABLED(BIC_PKG__)
-	    || BIC_IS_ENABLED(BIC_RAM__)
-	    || BIC_IS_ENABLED(BIC_PkgTmp)
-	    || (is_aperf_access_required() && !has_amperf_access_via_perf());
-}
-
 void check_msr_access(void)
 {
-	if (!is_msr_access_required())
-		no_msr = 1;
-
 	check_dev_msr();
 	check_msr_permission();
 
@@ -7899,18 +8544,425 @@ void check_msr_access(void)
 
 void check_perf_access(void)
 {
-	const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC);
-
-	if (no_perf || !intrcount_required || !has_instr_count_access())
+	if (no_perf || !BIC_IS_ENABLED(BIC_IPC) || !has_instr_count_access())
 		bic_enabled &= ~BIC_IPC;
+}
 
-	const bool aperf_required = is_aperf_access_required();
+int added_perf_counters_init_(struct perf_counter_info *pinfo)
+{
+	size_t num_domains = 0;
+	unsigned int next_domain;
+	bool *domain_visited;
+	unsigned int perf_type, perf_config;
+	double perf_scale;
+	int fd_perf;
 
-	if (!aperf_required || !has_amperf_access()) {
-		bic_enabled &= ~BIC_Avg_MHz;
-		bic_enabled &= ~BIC_Busy;
-		bic_enabled &= ~BIC_Bzy_MHz;
-		bic_enabled &= ~BIC_IPC;
+	if (!pinfo)
+		return 0;
+
+	const size_t max_num_domains = MAX(topo.max_cpu_num + 1, MAX(topo.max_core_id + 1, topo.max_package_id + 1));
+
+	domain_visited = calloc(max_num_domains, sizeof(*domain_visited));
+
+	while (pinfo) {
+		switch (pinfo->scope) {
+		case SCOPE_CPU:
+			num_domains = topo.max_cpu_num + 1;
+			break;
+
+		case SCOPE_CORE:
+			num_domains = topo.max_core_id + 1;
+			break;
+
+		case SCOPE_PACKAGE:
+			num_domains = topo.max_package_id + 1;
+			break;
+		}
+
+		/* Allocate buffer for file descriptor for each domain. */
+		pinfo->fd_perf_per_domain = calloc(num_domains, sizeof(*pinfo->fd_perf_per_domain));
+		if (!pinfo->fd_perf_per_domain)
+			errx(1, "%s: alloc %s", __func__, "fd_perf_per_domain");
+
+		for (size_t i = 0; i < num_domains; ++i)
+			pinfo->fd_perf_per_domain[i] = -1;
+
+		pinfo->num_domains = num_domains;
+		pinfo->scale = 1.0;
+
+		memset(domain_visited, 0, max_num_domains * sizeof(*domain_visited));
+
+		for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) {
+
+			next_domain = cpu_to_domain(pinfo, cpu);
+
+			assert(next_domain < num_domains);
+
+			if (cpu_is_not_allowed(cpu))
+				continue;
+
+			if (domain_visited[next_domain])
+				continue;
+
+			perf_type = read_perf_type(pinfo->device);
+			if (perf_type == (unsigned int)-1) {
+				warnx("%s: perf/%s/%s: failed to read %s",
+				      __func__, pinfo->device, pinfo->event, "type");
+				continue;
+			}
+
+			perf_config = read_perf_config(pinfo->device, pinfo->event);
+			if (perf_config == (unsigned int)-1) {
+				warnx("%s: perf/%s/%s: failed to read %s",
+				      __func__, pinfo->device, pinfo->event, "config");
+				continue;
+			}
+
+			/* Scale is not required, some counters just don't have it. */
+			perf_scale = read_perf_scale(pinfo->device, pinfo->event);
+			if (perf_scale == 0.0)
+				perf_scale = 1.0;
+
+			fd_perf = open_perf_counter(cpu, perf_type, perf_config, -1, 0);
+			if (fd_perf == -1) {
+				warnx("%s: perf/%s/%s: failed to open counter on cpu%d",
+				      __func__, pinfo->device, pinfo->event, cpu);
+				continue;
+			}
+
+			domain_visited[next_domain] = 1;
+			pinfo->fd_perf_per_domain[next_domain] = fd_perf;
+			pinfo->scale = perf_scale;
+
+			if (debug)
+				fprintf(stderr, "Add perf/%s/%s cpu%d: %d\n",
+					pinfo->device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]);
+		}
+
+		pinfo = pinfo->next;
+	}
+
+	free(domain_visited);
+
+	return 0;
+}
+
+void added_perf_counters_init(void)
+{
+	if (added_perf_counters_init_(sys.perf_tp))
+		errx(1, "%s: %s", __func__, "thread");
+
+	if (added_perf_counters_init_(sys.perf_cp))
+		errx(1, "%s: %s", __func__, "core");
+
+	if (added_perf_counters_init_(sys.perf_pp))
+		errx(1, "%s: %s", __func__, "package");
+}
+
+int parse_telem_info_file(int fd_dir, const char *info_filename, const char *format, unsigned long *output)
+{
+	int fd_telem_info;
+	FILE *file_telem_info;
+	unsigned long value;
+
+	fd_telem_info = openat(fd_dir, info_filename, O_RDONLY);
+	if (fd_telem_info == -1)
+		return -1;
+
+	file_telem_info = fdopen(fd_telem_info, "r");
+	if (file_telem_info == NULL) {
+		close(fd_telem_info);
+		return -1;
+	}
+
+	if (fscanf(file_telem_info, format, &value) != 1) {
+		fclose(file_telem_info);
+		return -1;
+	}
+
+	fclose(file_telem_info);
+
+	*output = value;
+
+	return 0;
+}
+
+struct pmt_mmio *pmt_mmio_open(unsigned int target_guid)
+{
+	DIR *dirp;
+	struct dirent *entry;
+	struct stat st;
+	unsigned int telem_idx;
+	int fd_telem_dir, fd_pmt;
+	unsigned long guid, size, offset;
+	size_t mmap_size;
+	void *mmio;
+	struct pmt_mmio *ret = NULL;
+
+	if (stat(SYSFS_TELEM_PATH, &st) == -1)
+		return NULL;
+
+	dirp = opendir(SYSFS_TELEM_PATH);
+	if (dirp == NULL)
+		return NULL;
+
+	for (;;) {
+		entry = readdir(dirp);
+
+		if (entry == NULL)
+			break;
+
+		if (strcmp(entry->d_name, ".") == 0)
+			continue;
+
+		if (strcmp(entry->d_name, "..") == 0)
+			continue;
+
+		if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1)
+			continue;
+
+		if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) {
+			break;
+		}
+
+		if (!S_ISDIR(st.st_mode))
+			continue;
+
+		fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY);
+		if (fd_telem_dir == -1) {
+			break;
+		}
+
+		if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) {
+			close(fd_telem_dir);
+			break;
+		}
+
+		if (parse_telem_info_file(fd_telem_dir, "size", "%lu", &size)) {
+			close(fd_telem_dir);
+			break;
+		}
+
+		if (guid != target_guid) {
+			close(fd_telem_dir);
+			continue;
+		}
+
+		if (parse_telem_info_file(fd_telem_dir, "offset", "%lu", &offset)) {
+			close(fd_telem_dir);
+			break;
+		}
+
+		assert(offset == 0);
+
+		fd_pmt = openat(fd_telem_dir, "telem", O_RDONLY);
+		if (fd_pmt == -1)
+			goto loop_cleanup_and_break;
+
+		mmap_size = (size + 0x1000UL) & (~0x1000UL);
+		mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0);
+		if (mmio != MAP_FAILED) {
+
+			if (debug)
+				fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio);
+
+			ret = calloc(1, sizeof(*ret));
+
+			if (!ret) {
+				fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__);
+				exit(1);
+			}
+
+			ret->guid = guid;
+			ret->mmio_base = mmio;
+			ret->pmt_offset = offset;
+			ret->size = size;
+
+			ret->next = pmt_mmios;
+			pmt_mmios = ret;
+		}
+
+loop_cleanup_and_break:
+		close(fd_pmt);
+		close(fd_telem_dir);
+		break;
+	}
+
+	closedir(dirp);
+
+	return ret;
+}
+
+struct pmt_mmio *pmt_mmio_find(unsigned int guid)
+{
+	struct pmt_mmio *pmmio = pmt_mmios;
+
+	while (pmmio) {
+		if (pmmio->guid == guid)
+			return pmmio;
+
+		pmmio = pmmio->next;
+	}
+
+	return NULL;
+}
+
+void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offset)
+{
+	char *ret;
+
+	/* Get base of mmaped PMT file. */
+	ret = (char *)pmmio->mmio_base;
+
+	/*
+	 * Apply PMT MMIO offset to obtain beginning of the mmaped telemetry data.
+	 * It's not guaranteed that the mmaped memory begins with the telemetry data
+	 *      - we might have to apply the offset first.
+	 */
+	ret += pmmio->pmt_offset;
+
+	/* Apply the counter offset to get the address to the mmaped counter. */
+	ret += counter_offset;
+
+	return ret;
+}
+
+struct pmt_mmio *pmt_add_guid(unsigned int guid)
+{
+	struct pmt_mmio *ret;
+
+	ret = pmt_mmio_find(guid);
+	if (!ret)
+		ret = pmt_mmio_open(guid);
+
+	return ret;
+}
+
+enum pmt_open_mode {
+	PMT_OPEN_TRY,		/* Open failure is not an error. */
+	PMT_OPEN_REQUIRED,	/* Open failure is a fatal error. */
+};
+
+struct pmt_counter *pmt_find_counter(struct pmt_counter *pcounter, const char *name)
+{
+	while (pcounter) {
+		if (strcmp(pcounter->name, name) == 0)
+			break;
+
+		pcounter = pcounter->next;
+	}
+
+	return pcounter;
+}
+
+struct pmt_counter **pmt_get_scope_root(enum counter_scope scope)
+{
+	switch (scope) {
+	case SCOPE_CPU:
+		return &sys.pmt_tp;
+	case SCOPE_CORE:
+		return &sys.pmt_cp;
+	case SCOPE_PACKAGE:
+		return &sys.pmt_pp;
+	}
+
+	__builtin_unreachable();
+}
+
+void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio, unsigned int domain_id)
+{
+	/* Make sure the new domain fits. */
+	if (domain_id >= pcounter->num_domains)
+		pmt_counter_resize(pcounter, domain_id + 1);
+
+	assert(pcounter->domains);
+	assert(domain_id < pcounter->num_domains);
+
+	pcounter->domains[domain_id].pcounter = pmmio;
+}
+
+int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
+		    unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope,
+		    enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode)
+{
+	struct pmt_mmio *mmio;
+	struct pmt_counter *pcounter;
+	struct pmt_counter **const pmt_root = pmt_get_scope_root(scope);
+	bool new_counter = false;
+	int conflict = 0;
+
+	if (lsb > msb) {
+		fprintf(stderr, "%s: %s: `%s` must be satisfied\n", __func__, "lsb <= msb", name);
+		exit(1);
+	}
+
+	if (msb >= 64) {
+		fprintf(stderr, "%s: %s: `%s` must be satisfied\n", __func__, "msb < 64", name);
+		exit(1);
+	}
+
+	mmio = pmt_add_guid(guid);
+	if (!mmio) {
+		if (mode != PMT_OPEN_TRY) {
+			fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid);
+			exit(1);
+		}
+
+		return 1;
+	}
+
+	if (offset >= mmio->size) {
+		if (mode != PMT_OPEN_TRY) {
+			fprintf(stderr, "%s: offset %u outside of PMT MMIO size %u\n", __func__, offset, mmio->size);
+			exit(1);
+		}
+
+		return 1;
+	}
+
+	pcounter = pmt_find_counter(*pmt_root, name);
+	if (!pcounter) {
+		pcounter = calloc(1, sizeof(*pcounter));
+		new_counter = true;
+	}
+
+	if (new_counter) {
+		strncpy(pcounter->name, name, ARRAY_SIZE(pcounter->name) - 1);
+		pcounter->type = type;
+		pcounter->scope = scope;
+		pcounter->lsb = lsb;
+		pcounter->msb = msb;
+		pcounter->format = format;
+	} else {
+		conflict += pcounter->type != type;
+		conflict += pcounter->scope != scope;
+		conflict += pcounter->lsb != lsb;
+		conflict += pcounter->msb != msb;
+		conflict += pcounter->format != format;
+	}
+
+	if (conflict) {
+		fprintf(stderr, "%s: conflicting parameters for the PMT counter with the same name %s\n",
+			__func__, name);
+		exit(1);
+	}
+
+	pmt_counter_add_domain(pcounter, pmt_get_counter_pointer(mmio, offset), domain_id);
+
+	if (new_counter) {
+		pcounter->next = *pmt_root;
+		*pmt_root = pcounter;
+	}
+
+	return 0;
+}
+
+void pmt_init(void)
+{
+	if (BIC_IS_ENABLED(BIC_Diec6)) {
+		pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB,
+				PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA,
+				0, PMT_OPEN_TRY);
 	}
 }
 
@@ -7923,16 +8975,18 @@ void turbostat_init()
 	process_cpuid();
 	counter_info_init();
 	probe_pm_features();
-	set_amperf_source();
+	msr_perf_init();
 	linux_perf_init();
 	rapl_perf_init();
 	cstate_perf_init();
+	added_perf_counters_init();
+	pmt_init();
 
 	for_all_cpus(get_cpu_type, ODD_COUNTERS);
 	for_all_cpus(get_cpu_type, EVEN_COUNTERS);
 
-	if (DO_BIC(BIC_IPC))
-		(void)get_instr_count_fd(base_cpu);
+	if (BIC_IS_ENABLED(BIC_IPC) && has_aperf_access && get_instr_count_fd(base_cpu) != -1)
+		BIC_PRESENT(BIC_IPC);
 
 	/*
 	 * If TSC tweak is needed, but couldn't get it,
@@ -8017,7 +9071,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2024.05.10 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2024.07.26 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -8049,7 +9103,7 @@ struct msr_counter *find_msrp_by_name(struct msr_counter *head, char *name)
 
 	for (mp = head; mp; mp = mp->next) {
 		if (debug)
-			printf("%s: %s %s\n", __func__, name, mp->name);
+			fprintf(stderr, "%s: %s %s\n", __func__, name, mp->name);
 		if (!strncmp(name, mp->name, strlen(mp->name)))
 			return mp;
 	}
@@ -8066,8 +9120,8 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num);
 
 	if (debug)
-		printf("%s(msr%d, %s, %s, width%d, scope%d, type%d, format%d, flags%x, id%d)\n", __func__, msr_num,
-		       path, name, width, scope, type, format, flags, id);
+		fprintf(stderr, "%s(msr%d, %s, %s, width%d, scope%d, type%d, format%d, flags%x, id%d)\n",
+			__func__, msr_num, path, name, width, scope, type, format, flags, id);
 
 	switch (scope) {
 
@@ -8075,7 +9129,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		msrp = find_msrp_by_name(sys.tp, name);
 		if (msrp) {
 			if (debug)
-				printf("%s: %s FOUND\n", __func__, name);
+				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
 		if (sys.added_thread_counters++ >= MAX_ADDED_THREAD_COUNTERS) {
@@ -8087,7 +9141,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		msrp = find_msrp_by_name(sys.cp, name);
 		if (msrp) {
 			if (debug)
-				printf("%s: %s FOUND\n", __func__, name);
+				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
 		if (sys.added_core_counters++ >= MAX_ADDED_CORE_COUNTERS) {
@@ -8099,7 +9153,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		msrp = find_msrp_by_name(sys.pp, name);
 		if (msrp) {
 			if (debug)
-				printf("%s: %s FOUND\n", __func__, name);
+				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
 		if (sys.added_package_counters++ >= MAX_ADDED_PACKAGE_COUNTERS) {
@@ -8116,6 +9170,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 		msrp = calloc(1, sizeof(struct msr_counter));
 		if (msrp == NULL)
 			err(-1, "calloc msr_counter");
+
 		msrp->msr_num = msr_num;
 		strncpy(msrp->name, name, NAME_BYTES - 1);
 		msrp->width = width;
@@ -8156,11 +9211,106 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 	return 0;
 }
 
-void parse_add_command(char *add_command)
+/*
+ * Initialize the fields used for identifying and opening the counter.
+ *
+ * Defer the initialization of any runtime buffers for actually reading
+ * the counters for when we initialize all perf counters, so we can later
+ * easily call re_initialize().
+ */
+struct perf_counter_info *make_perf_counter_info(const char *perf_device,
+						 const char *perf_event,
+						 const char *name,
+						 unsigned int width,
+						 enum counter_scope scope,
+						 enum counter_type type, enum counter_format format)
+{
+	struct perf_counter_info *pinfo;
+
+	pinfo = calloc(1, sizeof(*pinfo));
+	if (!pinfo)
+		errx(1, "%s: Failed to allocate %s/%s\n", __func__, perf_device, perf_event);
+
+	strncpy(pinfo->device, perf_device, ARRAY_SIZE(pinfo->device) - 1);
+	strncpy(pinfo->event, perf_event, ARRAY_SIZE(pinfo->event) - 1);
+
+	strncpy(pinfo->name, name, ARRAY_SIZE(pinfo->name) - 1);
+	pinfo->width = width;
+	pinfo->scope = scope;
+	pinfo->type = type;
+	pinfo->format = format;
+
+	return pinfo;
+}
+
+int add_perf_counter(const char *perf_device, const char *perf_event, const char *name_buffer, unsigned int width,
+		     enum counter_scope scope, enum counter_type type, enum counter_format format)
+{
+	struct perf_counter_info *pinfo;
+
+	switch (scope) {
+	case SCOPE_CPU:
+		if (sys.added_thread_perf_counters >= MAX_ADDED_THREAD_COUNTERS) {
+			warnx("ignoring thread counter perf/%s/%s", perf_device, perf_event);
+			return -1;
+		}
+		break;
+
+	case SCOPE_CORE:
+		if (sys.added_core_perf_counters >= MAX_ADDED_CORE_COUNTERS) {
+			warnx("ignoring core counter perf/%s/%s", perf_device, perf_event);
+			return -1;
+		}
+		break;
+
+	case SCOPE_PACKAGE:
+		if (sys.added_package_perf_counters >= MAX_ADDED_PACKAGE_COUNTERS) {
+			warnx("ignoring package counter perf/%s/%s", perf_device, perf_event);
+			return -1;
+		}
+		break;
+	}
+
+	pinfo = make_perf_counter_info(perf_device, perf_event, name_buffer, width, scope, type, format);
+
+	if (!pinfo)
+		return -1;
+
+	switch (scope) {
+	case SCOPE_CPU:
+		pinfo->next = sys.perf_tp;
+		sys.perf_tp = pinfo;
+		++sys.added_thread_perf_counters;
+		break;
+
+	case SCOPE_CORE:
+		pinfo->next = sys.perf_cp;
+		sys.perf_cp = pinfo;
+		++sys.added_core_perf_counters;
+		break;
+
+	case SCOPE_PACKAGE:
+		pinfo->next = sys.perf_pp;
+		sys.perf_pp = pinfo;
+		++sys.added_package_perf_counters;
+		break;
+	}
+
+	// FIXME: we might not have debug here yet
+	if (debug)
+		fprintf(stderr, "%s: %s/%s, name: %s, scope%d\n",
+			__func__, pinfo->device, pinfo->event, pinfo->name, pinfo->scope);
+
+	return 0;
+}
+
+void parse_add_command_msr(char *add_command)
 {
 	int msr_num = 0;
 	char *path = NULL;
-	char name_buffer[NAME_BYTES] = "";
+	char perf_device[PERF_DEV_NAME_BYTES] = "";
+	char perf_event[PERF_EVT_NAME_BYTES] = "";
+	char name_buffer[PERF_NAME_BYTES] = "";
 	int width = 64;
 	int fail = 0;
 	enum counter_scope scope = SCOPE_CPU;
@@ -8175,6 +9325,11 @@ void parse_add_command(char *add_command)
 		if (sscanf(add_command, "msr%d", &msr_num) == 1)
 			goto next;
 
+		BUILD_BUG_ON(ARRAY_SIZE(perf_device) <= 31);
+		BUILD_BUG_ON(ARRAY_SIZE(perf_event) <= 31);
+		if (sscanf(add_command, "perf/%31[^/]/%31[^,]", &perf_device[0], &perf_event[0]) == 2)
+			goto next;
+
 		if (*add_command == '/') {
 			path = add_command;
 			goto next;
@@ -8222,7 +9377,8 @@ void parse_add_command(char *add_command)
 			goto next;
 		}
 
-		if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) {	/* 18 < NAME_BYTES */
+		BUILD_BUG_ON(ARRAY_SIZE(name_buffer) <= 18);
+		if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) {
 			char *eos;
 
 			eos = strchr(name_buffer, ',');
@@ -8239,21 +9395,33 @@ void parse_add_command(char *add_command)
 		}
 
 	}
-	if ((msr_num == 0) && (path == NULL)) {
-		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n");
+	if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) {
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n");
 		fail++;
 	}
 
+	/* Test for non-empty perf_device and perf_event */
+	const bool is_perf_counter = perf_device[0] && perf_event[0];
+
 	/* generate default column header */
 	if (*name_buffer == '\0') {
-		if (width == 32)
-			sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
-		else
-			sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
+		if (is_perf_counter) {
+			snprintf(name_buffer, ARRAY_SIZE(name_buffer), "perf/%s", perf_event);
+		} else {
+			if (width == 32)
+				sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
+			else
+				sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : "");
+		}
 	}
 
-	if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0, 0))
-		fail++;
+	if (is_perf_counter) {
+		if (add_perf_counter(perf_device, perf_event, name_buffer, width, scope, type, format))
+			fail++;
+	} else {
+		if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0, 0))
+			fail++;
+	}
 
 	if (fail) {
 		help();
@@ -8261,6 +9429,195 @@ void parse_add_command(char *add_command)
 	}
 }
 
+bool starts_with(const char *str, const char *prefix)
+{
+	return strncmp(prefix, str, strlen(prefix)) == 0;
+}
+
+void parse_add_command_pmt(char *add_command)
+{
+	char *name = NULL;
+	char *type_name = NULL;
+	char *format_name = NULL;
+	unsigned int offset;
+	unsigned int lsb;
+	unsigned int msb;
+	unsigned int guid;
+	unsigned int domain_id;
+	enum counter_scope scope = 0;
+	enum pmt_datatype type = PMT_TYPE_RAW;
+	enum counter_format format = FORMAT_RAW;
+	bool has_offset = false;
+	bool has_lsb = false;
+	bool has_msb = false;
+	bool has_format = true;	/* Format has a default value. */
+	bool has_guid = false;
+	bool has_scope = false;
+	bool has_type = true;	/* Type has a default value. */
+
+	/* Consume the "pmt," prefix. */
+	add_command = strchr(add_command, ',');
+	if (!add_command) {
+		help();
+		exit(1);
+	}
+	++add_command;
+
+	while (add_command) {
+		if (starts_with(add_command, "name=")) {
+			name = add_command + strlen("name=");
+			goto next;
+		}
+
+		if (starts_with(add_command, "type=")) {
+			type_name = add_command + strlen("type=");
+			goto next;
+		}
+
+		if (starts_with(add_command, "domain=")) {
+			const size_t prefix_len = strlen("domain=");
+
+			if (sscanf(add_command + prefix_len, "cpu%u", &domain_id) == 1) {
+				scope = SCOPE_CPU;
+				has_scope = true;
+			} else if (sscanf(add_command + prefix_len, "core%u", &domain_id) == 1) {
+				scope = SCOPE_CORE;
+				has_scope = true;
+			} else if (sscanf(add_command + prefix_len, "package%u", &domain_id) == 1) {
+				scope = SCOPE_PACKAGE;
+				has_scope = true;
+			}
+
+			if (!has_scope) {
+				printf("%s: invalid value for scope. Expected cpu%%u, core%%u or package%%u.\n",
+				       __func__);
+				exit(1);
+			}
+
+			goto next;
+		}
+
+		if (starts_with(add_command, "format=")) {
+			format_name = add_command + strlen("format=");
+			goto next;
+		}
+
+		if (sscanf(add_command, "offset=%u", &offset) == 1) {
+			has_offset = true;
+			goto next;
+		}
+
+		if (sscanf(add_command, "lsb=%u", &lsb) == 1) {
+			has_lsb = true;
+			goto next;
+		}
+
+		if (sscanf(add_command, "msb=%u", &msb) == 1) {
+			has_msb = true;
+			goto next;
+		}
+
+		if (sscanf(add_command, "guid=%x", &guid) == 1) {
+			has_guid = true;
+			goto next;
+		}
+
+next:
+		add_command = strchr(add_command, ',');
+		if (add_command) {
+			*add_command = '\0';
+			add_command++;
+		}
+	}
+
+	if (!name) {
+		printf("%s: missing %s\n", __func__, "name");
+		exit(1);
+	}
+
+	if (strlen(name) >= PMT_COUNTER_NAME_SIZE_BYTES) {
+		printf("%s: name has to be at most %d characters long\n", __func__, PMT_COUNTER_NAME_SIZE_BYTES);
+		exit(1);
+	}
+
+	if (format_name) {
+		has_format = false;
+
+		if (strcmp("raw", format_name) == 0) {
+			format = FORMAT_RAW;
+			has_format = true;
+		}
+
+		if (strcmp("delta", format_name) == 0) {
+			format = FORMAT_DELTA;
+			has_format = true;
+		}
+
+		if (!has_format) {
+			fprintf(stderr, "%s: Invalid format %s. Expected raw or delta\n", __func__, format_name);
+			exit(1);
+		}
+	}
+
+	if (type_name) {
+		has_type = false;
+
+		if (strcmp("raw", type_name) == 0) {
+			type = PMT_TYPE_RAW;
+			has_type = true;
+		}
+
+		if (strcmp("txtal_time", type_name) == 0) {
+			type = PMT_TYPE_XTAL_TIME;
+			has_type = true;
+		}
+
+		if (!has_type) {
+			printf("%s: invalid %s: %s\n", __func__, "type", type_name);
+			exit(1);
+		}
+	}
+
+	if (!has_offset) {
+		printf("%s : missing %s\n", __func__, "offset");
+		exit(1);
+	}
+
+	if (!has_lsb) {
+		printf("%s: missing %s\n", __func__, "lsb");
+		exit(1);
+	}
+
+	if (!has_msb) {
+		printf("%s: missing %s\n", __func__, "msb");
+		exit(1);
+	}
+
+	if (!has_guid) {
+		printf("%s: missing %s\n", __func__, "guid");
+		exit(1);
+	}
+
+	if (!has_scope) {
+		printf("%s: missing %s\n", __func__, "scope");
+		exit(1);
+	}
+
+	if (lsb > msb) {
+		printf("%s: lsb > msb doesn't make sense\n", __func__);
+		exit(1);
+	}
+
+	pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED);
+}
+
+void parse_add_command(char *add_command)
+{
+	if (strncmp(add_command, "pmt", strlen("pmt")) == 0)
+		return parse_add_command_pmt(add_command);
+	return parse_add_command_msr(add_command);
+}
+
 int is_deferred_add(char *name)
 {
 	int i;
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index eaf091a..129f179 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -385,19 +385,21 @@ struct cxl_test_gen_media {
 struct cxl_test_gen_media gen_media = {
 	.id = CXL_EVENT_GEN_MEDIA_UUID,
 	.rec = {
-		.hdr = {
-			.length = sizeof(struct cxl_test_gen_media),
-			.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
-			/* .handle = Set dynamically */
-			.related_handle = cpu_to_le16(0),
+		.media_hdr = {
+			.hdr = {
+				.length = sizeof(struct cxl_test_gen_media),
+				.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+				/* .handle = Set dynamically */
+				.related_handle = cpu_to_le16(0),
+			},
+			.phys_addr = cpu_to_le64(0x2000),
+			.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+			.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+			.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+			/* .validity_flags = <set below> */
+			.channel = 1,
+			.rank = 30,
 		},
-		.phys_addr = cpu_to_le64(0x2000),
-		.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
-		.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
-		.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
-		/* .validity_flags = <set below> */
-		.channel = 1,
-		.rank = 30
 	},
 };
 
@@ -409,18 +411,20 @@ struct cxl_test_dram {
 struct cxl_test_dram dram = {
 	.id = CXL_EVENT_DRAM_UUID,
 	.rec = {
-		.hdr = {
-			.length = sizeof(struct cxl_test_dram),
-			.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
-			/* .handle = Set dynamically */
-			.related_handle = cpu_to_le16(0),
+		.media_hdr = {
+			.hdr = {
+				.length = sizeof(struct cxl_test_dram),
+				.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+				/* .handle = Set dynamically */
+				.related_handle = cpu_to_le16(0),
+			},
+			.phys_addr = cpu_to_le64(0x8000),
+			.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+			.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+			.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+			/* .validity_flags = <set below> */
+			.channel = 1,
 		},
-		.phys_addr = cpu_to_le64(0x8000),
-		.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
-		.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
-		.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
-		/* .validity_flags = <set below> */
-		.channel = 1,
 		.bank_group = 5,
 		.bank = 2,
 		.column = {0xDE, 0xAD},
@@ -474,11 +478,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds,
 static void cxl_mock_add_event_logs(struct mock_event_store *mes)
 {
 	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
-			   &gen_media.rec.validity_flags);
+			   &gen_media.rec.media_hdr.validity_flags);
 
 	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
 			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
-			   &dram.rec.validity_flags);
+			   &dram.rec.media_hdr.validity_flags);
 
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
@@ -1131,27 +1135,28 @@ static bool mock_poison_dev_max_injected(struct cxl_dev_state *cxlds)
 	return (count >= poison_inject_dev_max);
 }
 
-static bool mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa)
+static int mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa)
 {
+	/* Return EBUSY to match the CXL driver handling */
 	if (mock_poison_dev_max_injected(cxlds)) {
 		dev_dbg(cxlds->dev,
 			"Device poison injection limit has been reached: %d\n",
-			MOCK_INJECT_DEV_MAX);
-		return false;
+			poison_inject_dev_max);
+		return -EBUSY;
 	}
 
 	for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) {
 		if (!mock_poison_list[i].cxlds) {
 			mock_poison_list[i].cxlds = cxlds;
 			mock_poison_list[i].dpa = dpa;
-			return true;
+			return 0;
 		}
 	}
 	dev_dbg(cxlds->dev,
 		"Mock test poison injection limit has been reached: %d\n",
 		MOCK_INJECT_TEST_MAX);
 
-	return false;
+	return -ENXIO;
 }
 
 static bool mock_poison_found(struct cxl_dev_state *cxlds, u64 dpa)
@@ -1175,10 +1180,8 @@ static int mock_inject_poison(struct cxl_dev_state *cxlds,
 		dev_dbg(cxlds->dev, "DPA: 0x%llx already poisoned\n", dpa);
 		return 0;
 	}
-	if (!mock_poison_add(cxlds, dpa))
-		return -ENXIO;
 
-	return 0;
+	return mock_poison_add(cxlds, dpa);
 }
 
 static bool mock_poison_del(struct cxl_dev_state *cxlds, u64 dpa)
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 7527f73..d1acd7d 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,8 +5,8 @@
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray maple
-CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o \
-			 slab.o maple.o
+LIBS := slab.o find_bit.o bitmap.o hweight.o vsprintf.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o maple.o $(LIBS)
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 regression4.o tag_check.o multiorder.o idr-test.o iteration_check.o \
 	 iteration_check_2.o benchmark.o
diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c
deleted file mode 100644
index 66ec4a2..0000000
--- a/tools/testing/radix-tree/bitmap.c
+++ /dev/null
@@ -1,23 +0,0 @@
-/* lib/bitmap.c pulls in at least two other files. */
-
-#include <linux/bitmap.h>
-
-void bitmap_clear(unsigned long *map, unsigned int start, int len)
-{
-	unsigned long *p = map + BIT_WORD(start);
-	const unsigned int size = start + len;
-	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
-	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
-
-	while (len - bits_to_clear >= 0) {
-		*p &= ~mask_to_clear;
-		len -= bits_to_clear;
-		bits_to_clear = BITS_PER_LONG;
-		mask_to_clear = ~0UL;
-		p++;
-	}
-	if (len) {
-		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
-		*p &= ~mask_to_clear;
-	}
-}
diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c
index 4c94127..e4fa507 100644
--- a/tools/testing/selftests/arm64/abi/ptrace.c
+++ b/tools/testing/selftests/arm64/abi/ptrace.c
@@ -156,7 +156,7 @@ static void test_hw_debug(pid_t child, int type, const char *type_name)
 		/* Zero is not currently architecturally valid */
 		ksft_test_result(arch, "%s_arch_set\n", type_name);
 	} else {
-		ksft_test_result_skip("%s_arch_set\n");
+		ksft_test_result_skip("%s_arch_set\n", type_name);
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 3c7c3e7..901349d 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -1,6 +1,5 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-fexit_sleep                                      # The test never returns. The remaining tests cannot start.
 kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
 kprobe_multi_test                                # needs CONFIG_FPROBE
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index f949647..552a087 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -21,13 +21,13 @@ static int do_sleep(void *skel)
 }
 
 #define STACK_SIZE (1024 * 1024)
-static char child_stack[STACK_SIZE];
 
 void test_fexit_sleep(void)
 {
 	struct fexit_sleep_lskel *fexit_skel = NULL;
 	int wstatus, duration = 0;
 	pid_t cpid;
+	char *child_stack = NULL;
 	int err, fexit_cnt;
 
 	fexit_skel = fexit_sleep_lskel__open_and_load();
@@ -38,6 +38,11 @@ void test_fexit_sleep(void)
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto cleanup;
 
+	child_stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+			   MAP_ANONYMOUS | MAP_STACK, -1, 0);
+	if (!ASSERT_NEQ(child_stack, MAP_FAILED, "mmap"))
+		goto cleanup;
+
 	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
 	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
 		goto cleanup;
@@ -78,5 +83,6 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 cleanup:
+	munmap(child_stack, STACK_SIZE);
 	fexit_sleep_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index e91b593..9ce0e0e 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -29,6 +29,8 @@
 
 #include "sockmap_helpers.h"
 
+#define NO_FLAGS 0
+
 static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
 				int family, int sotype, int mapfd)
 {
@@ -1376,7 +1378,8 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 
 static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 				     int sock_mapfd, int nop_mapfd,
-				     int verd_mapfd, enum redir_mode mode)
+				     int verd_mapfd, enum redir_mode mode,
+				     int send_flags)
 {
 	const char *log_prefix = redir_mode_str(mode);
 	unsigned int pass;
@@ -1396,12 +1399,11 @@ static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 			return;
 	}
 
-	n = write(cli1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
+	/* Last byte is OOB data when send_flags has MSG_OOB bit set */
+	n = xsend(cli1, "ab", 2, send_flags);
+	if (n >= 0 && n < 2)
+		FAIL("%s: incomplete send", log_prefix);
+	if (n < 2)
 		return;
 
 	key = SK_PASS;
@@ -1416,6 +1418,25 @@ static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
 		FAIL("%s: incomplete recv", log_prefix);
+
+	if (send_flags & MSG_OOB) {
+		/* Check that we can't read OOB while in sockmap */
+		errno = 0;
+		n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT);
+		if (n != -1 || errno != EOPNOTSUPP)
+			FAIL("%s: recv(MSG_OOB): expected EOPNOTSUPP: retval=%d errno=%d",
+			     log_prefix, n, errno);
+
+		/* Remove peer1 from sockmap */
+		xbpf_map_delete_elem(sock_mapfd, &(int){ 1 });
+
+		/* Check that OOB was dropped on redirect */
+		errno = 0;
+		n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT);
+		if (n != -1 || errno != EINVAL)
+			FAIL("%s: recv(MSG_OOB): expected EINVAL: retval=%d errno=%d",
+			     log_prefix, n, errno);
+	}
 }
 
 static void unix_redir_to_connected(int sotype, int sock_mapfd,
@@ -1432,7 +1453,8 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 		goto close0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
+				 mode, NO_FLAGS);
 
 	xclose(c1);
 	xclose(p1);
@@ -1722,7 +1744,8 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (err)
 		goto close_cli0;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
+				 mode, NO_FLAGS);
 
 	xclose(c1);
 	xclose(p1);
@@ -1780,7 +1803,8 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (err)
 		goto close;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
+				 mode, NO_FLAGS);
 
 	xclose(c1);
 	xclose(p1);
@@ -1815,10 +1839,9 @@ static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
 
-static void unix_inet_redir_to_connected(int family, int type,
-					int sock_mapfd, int nop_mapfd,
-					int verd_mapfd,
-					enum redir_mode mode)
+static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
+					 int nop_mapfd, int verd_mapfd,
+					 enum redir_mode mode, int send_flags)
 {
 	int c0, c1, p0, p1;
 	int sfd[2];
@@ -1828,19 +1851,18 @@ static void unix_inet_redir_to_connected(int family, int type,
 	if (err)
 		return;
 
-	if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
+	if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd))
 		goto close_cli0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1,
-				 sock_mapfd, nop_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, nop_mapfd,
+				 verd_mapfd, mode, send_flags);
 
 	xclose(c1);
 	xclose(p1);
 close_cli0:
 	xclose(c0);
 	xclose(p0);
-
 }
 
 static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
@@ -1859,31 +1881,42 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	skel->bss->test_ingress = false;
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, -1, verdict_map,
-				     REDIR_EGRESS);
+				     REDIR_EGRESS, NO_FLAGS);
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, -1, verdict_map,
-				     REDIR_EGRESS);
+				     REDIR_EGRESS, NO_FLAGS);
 
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, nop_map, verdict_map,
-				     REDIR_EGRESS);
+				     REDIR_EGRESS, NO_FLAGS);
 	unix_inet_redir_to_connected(family, SOCK_STREAM,
 				     sock_map, nop_map, verdict_map,
-				     REDIR_EGRESS);
+				     REDIR_EGRESS, NO_FLAGS);
+
+	/* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
+				     REDIR_EGRESS, MSG_OOB);
+
 	skel->bss->test_ingress = true;
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, -1, verdict_map,
-				     REDIR_INGRESS);
+				     REDIR_INGRESS, NO_FLAGS);
 	unix_inet_redir_to_connected(family, SOCK_STREAM,
 				     sock_map, -1, verdict_map,
-				     REDIR_INGRESS);
+				     REDIR_INGRESS, NO_FLAGS);
 
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, nop_map, verdict_map,
-				     REDIR_INGRESS);
+				     REDIR_INGRESS, NO_FLAGS);
 	unix_inet_redir_to_connected(family, SOCK_STREAM,
 				     sock_map, nop_map, verdict_map,
-				     REDIR_INGRESS);
+				     REDIR_INGRESS, NO_FLAGS);
+
+	/* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
+				     REDIR_INGRESS, MSG_OOB);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index f76b5d6..c87ee2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -68,7 +68,8 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM |
+			 XDP_UMEM_TX_METADATA_LEN,
 		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
index ba97165..a657651 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
@@ -14,9 +14,9 @@ typedef int *ptr_arr_t[6];
 
 typedef int *ptr_multiarr_t[7][8][9][10];
 
-typedef int * (*fn_ptr_arr_t[11])();
+typedef int * (*fn_ptr_arr_t[11])(void);
 
-typedef int * (*fn_ptr_multiarr_t[12][13])();
+typedef int * (*fn_ptr_multiarr_t[12][13])(void);
 
 struct root_struct {
 	arr_t _1;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index ad21ee8..29d01ff 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -100,7 +100,7 @@ typedef void (*printf_fn_t)(const char *, ...);
  *   `int -> char *` function and returns pointer to a char. Equivalent:
  *   typedef char * (*fn_input_t)(int);
  *   typedef char * (*fn_output_outer_t)(fn_input_t);
- *   typedef const fn_output_outer_t (* fn_output_inner_t)();
+ *   typedef const fn_output_outer_t (* fn_output_inner_t)(void);
  *   typedef const fn_output_inner_t fn_ptr_arr2_t[5];
  */
 /* ----- START-EXPECTED-OUTPUT ----- */
@@ -127,7 +127,7 @@ typedef void (* (*signal_t)(int, void (*)(int)))(int);
 
 typedef char * (*fn_ptr_arr1_t[10])(int **);
 
-typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int));
+typedef char * (* (* const fn_ptr_arr2_t[5])(void))(char * (*)(int));
 
 struct struct_w_typedefs {
 	int_t a;
diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c
index 3c1e9f3..3b26bf3 100644
--- a/tools/testing/selftests/landlock/base_test.c
+++ b/tools/testing/selftests/landlock/base_test.c
@@ -9,6 +9,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/keyctl.h>
 #include <linux/landlock.h>
 #include <string.h>
 #include <sys/prctl.h>
@@ -326,4 +327,77 @@ TEST(ruleset_fd_transfer)
 	ASSERT_EQ(EXIT_SUCCESS, WEXITSTATUS(status));
 }
 
+TEST(cred_transfer)
+{
+	struct landlock_ruleset_attr ruleset_attr = {
+		.handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR,
+	};
+	int ruleset_fd, dir_fd;
+	pid_t child;
+	int status;
+
+	drop_caps(_metadata);
+
+	dir_fd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	EXPECT_LE(0, dir_fd);
+	EXPECT_EQ(0, close(dir_fd));
+
+	/* Denies opening directories. */
+	ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, ruleset_fd);
+	EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+	ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+	EXPECT_EQ(0, close(ruleset_fd));
+
+	/* Checks ruleset enforcement. */
+	EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
+	EXPECT_EQ(EACCES, errno);
+
+	/* Needed for KEYCTL_SESSION_TO_PARENT permission checks */
+	EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING, NULL, 0,
+			      0, 0))
+	{
+		TH_LOG("Failed to join session keyring: %s", strerror(errno));
+	}
+
+	child = fork();
+	ASSERT_LE(0, child);
+	if (child == 0) {
+		/* Checks ruleset enforcement. */
+		EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
+		EXPECT_EQ(EACCES, errno);
+
+		/*
+		 * KEYCTL_SESSION_TO_PARENT is a no-op unless we have a
+		 * different session keyring in the child, so make that happen.
+		 */
+		EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING,
+				      NULL, 0, 0, 0));
+
+		/*
+		 * KEYCTL_SESSION_TO_PARENT installs credentials on the parent
+		 * that never go through the cred_prepare hook, this path uses
+		 * cred_transfer instead.
+		 */
+		EXPECT_EQ(0, syscall(__NR_keyctl, KEYCTL_SESSION_TO_PARENT, 0,
+				     0, 0, 0));
+
+		/* Re-checks ruleset enforcement. */
+		EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
+		EXPECT_EQ(EACCES, errno);
+
+		_exit(_metadata->exit_code);
+		return;
+	}
+
+	EXPECT_EQ(child, waitpid(child, &status, 0));
+	EXPECT_EQ(1, WIFEXITED(status));
+	EXPECT_EQ(EXIT_SUCCESS, WEXITSTATUS(status));
+
+	/* Re-checks ruleset enforcement. */
+	EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
+	EXPECT_EQ(EACCES, errno);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 0086efa..29af19c 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -2,6 +2,7 @@
 CONFIG_CGROUP_SCHED=y
 CONFIG_INET=y
 CONFIG_IPV6=y
+CONFIG_KEYS=y
 CONFIG_NET=y
 CONFIG_NET_NS=y
 CONFIG_OVERLAY_FS=y
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 064e7b1..da030b4 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -50,3 +50,4 @@
 hugetlb_madv_vs_map
 mseal_test
 seal_elf
+droppable
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index e1aa09d..901e0d0 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -76,6 +76,7 @@
 TEST_GEN_FILES += hugetlb_fault_after_madv
 TEST_GEN_FILES += hugetlb_madv_vs_map
 TEST_GEN_FILES += hugetlb_dio
+TEST_GEN_FILES += droppable
 
 ifneq ($(ARCH),arm64)
 TEST_GEN_FILES += soft-dirty
diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c
new file mode 100644
index 0000000..f3d9ecf
--- /dev/null
+++ b/tools/testing/selftests/mm/droppable.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/mman.h>
+
+#include "../kselftest.h"
+
+int main(int argc, char *argv[])
+{
+	size_t alloc_size = 134217728;
+	size_t page_size = getpagesize();
+	void *alloc;
+	pid_t child;
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0);
+	assert(alloc != MAP_FAILED);
+	memset(alloc, 'A', alloc_size);
+	for (size_t i = 0; i < alloc_size; i += page_size)
+		assert(*(uint8_t *)(alloc + i));
+
+	child = fork();
+	assert(child >= 0);
+	if (!child) {
+		for (;;)
+			*(char *)malloc(page_size) = 'B';
+	}
+
+	for (bool done = false; !done;) {
+		for (size_t i = 0; i < alloc_size; i += page_size) {
+			if (!*(uint8_t *)(alloc + i)) {
+				done = true;
+				break;
+			}
+		}
+	}
+	kill(child, SIGTERM);
+
+	ksft_test_result_pass("MAP_DROPPABLE: PASS\n");
+	exit(KSFT_PASS);
+}
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c
index fa7eabf..896b3f73 100644
--- a/tools/testing/selftests/mm/va_high_addr_switch.c
+++ b/tools/testing/selftests/mm/va_high_addr_switch.c
@@ -293,6 +293,20 @@ static int run_test(struct testcase *test, int count)
 	return ret;
 }
 
+#ifdef __aarch64__
+/* Check if userspace VA > 48 bits */
+static int high_address_present(void)
+{
+	void *ptr = mmap((void *)(1UL << 50), 1, PROT_READ | PROT_WRITE,
+			 MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+	if (ptr == MAP_FAILED)
+		return 0;
+
+	munmap(ptr, 1);
+	return 1;
+}
+#endif
+
 static int supported_arch(void)
 {
 #if defined(__powerpc64__)
@@ -300,7 +314,7 @@ static int supported_arch(void)
 #elif defined(__x86_64__)
 	return 1;
 #elif defined(__aarch64__)
-	return 1;
+	return high_address_present();
 #else
 	return 0;
 #endif
diff --git a/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
index 0760a34..a21b708 100755
--- a/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
@@ -178,6 +178,22 @@
 	check_err $? "Failed to remove a FDB entry of type ${type}"
 }
 
+check_fdb_n_learned_support()
+{
+	if ! ip link help bridge 2>&1 | grep -q "fdb_max_learned"; then
+		echo "SKIP: iproute2 too old, missing bridge max learned support"
+		exit $ksft_skip
+	fi
+
+	ip link add dev br0 type bridge
+	local learned=$(fdb_get_n_learned)
+	ip link del dev br0
+	if [ "$learned" == "null" ]; then
+		echo "SKIP: kernel too old; bridge fdb_n_learned feature not supported."
+		exit $ksft_skip
+	fi
+}
+
 check_accounting_one_type()
 {
 	local type=$1 is_counted=$2 overrides_learned=$3
@@ -274,6 +290,8 @@
 	done
 }
 
+check_fdb_n_learned_support
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
index 47746b0..7c2a434 100644
--- a/tools/testing/selftests/pidfd/pidfd_setns_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -16,11 +16,56 @@
 #include <unistd.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
+#include <linux/ioctl.h>
 
 #include "pidfd.h"
 #include "../clone3/clone3_selftests.h"
 #include "../kselftest_harness.h"
 
+#ifndef PIDFS_IOCTL_MAGIC
+#define PIDFS_IOCTL_MAGIC 0xFF
+#endif
+
+#ifndef PIDFD_GET_CGROUP_NAMESPACE
+#define PIDFD_GET_CGROUP_NAMESPACE            _IO(PIDFS_IOCTL_MAGIC, 1)
+#endif
+
+#ifndef PIDFD_GET_IPC_NAMESPACE
+#define PIDFD_GET_IPC_NAMESPACE               _IO(PIDFS_IOCTL_MAGIC, 2)
+#endif
+
+#ifndef PIDFD_GET_MNT_NAMESPACE
+#define PIDFD_GET_MNT_NAMESPACE               _IO(PIDFS_IOCTL_MAGIC, 3)
+#endif
+
+#ifndef PIDFD_GET_NET_NAMESPACE
+#define PIDFD_GET_NET_NAMESPACE               _IO(PIDFS_IOCTL_MAGIC, 4)
+#endif
+
+#ifndef PIDFD_GET_PID_NAMESPACE
+#define PIDFD_GET_PID_NAMESPACE               _IO(PIDFS_IOCTL_MAGIC, 5)
+#endif
+
+#ifndef PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE
+#define PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE  _IO(PIDFS_IOCTL_MAGIC, 6)
+#endif
+
+#ifndef PIDFD_GET_TIME_NAMESPACE
+#define PIDFD_GET_TIME_NAMESPACE              _IO(PIDFS_IOCTL_MAGIC, 7)
+#endif
+
+#ifndef PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE
+#define PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE _IO(PIDFS_IOCTL_MAGIC, 8)
+#endif
+
+#ifndef PIDFD_GET_USER_NAMESPACE
+#define PIDFD_GET_USER_NAMESPACE              _IO(PIDFS_IOCTL_MAGIC, 9)
+#endif
+
+#ifndef PIDFD_GET_UTS_NAMESPACE
+#define PIDFD_GET_UTS_NAMESPACE               _IO(PIDFS_IOCTL_MAGIC, 10)
+#endif
+
 enum {
 	PIDFD_NS_USER,
 	PIDFD_NS_MNT,
@@ -31,22 +76,25 @@ enum {
 	PIDFD_NS_CGROUP,
 	PIDFD_NS_PIDCLD,
 	PIDFD_NS_TIME,
+	PIDFD_NS_TIMECLD,
 	PIDFD_NS_MAX
 };
 
 const struct ns_info {
 	const char *name;
 	int flag;
+	unsigned int pidfd_ioctl;
 } ns_info[] = {
-	[PIDFD_NS_USER]   = { "user",             CLONE_NEWUSER,   },
-	[PIDFD_NS_MNT]    = { "mnt",              CLONE_NEWNS,     },
-	[PIDFD_NS_PID]    = { "pid",              CLONE_NEWPID,    },
-	[PIDFD_NS_UTS]    = { "uts",              CLONE_NEWUTS,    },
-	[PIDFD_NS_IPC]    = { "ipc",              CLONE_NEWIPC,    },
-	[PIDFD_NS_NET]    = { "net",              CLONE_NEWNET,    },
-	[PIDFD_NS_CGROUP] = { "cgroup",           CLONE_NEWCGROUP, },
-	[PIDFD_NS_PIDCLD] = { "pid_for_children", 0,               },
-	[PIDFD_NS_TIME]	  = { "time",             CLONE_NEWTIME,   },
+	[PIDFD_NS_USER]    = { "user",              CLONE_NEWUSER,   PIDFD_GET_USER_NAMESPACE,              },
+	[PIDFD_NS_MNT]     = { "mnt",               CLONE_NEWNS,     PIDFD_GET_MNT_NAMESPACE,               },
+	[PIDFD_NS_PID]     = { "pid",               CLONE_NEWPID,    PIDFD_GET_PID_NAMESPACE,               },
+	[PIDFD_NS_UTS]     = { "uts",               CLONE_NEWUTS,    PIDFD_GET_UTS_NAMESPACE,               },
+	[PIDFD_NS_IPC]     = { "ipc",               CLONE_NEWIPC,    PIDFD_GET_IPC_NAMESPACE,               },
+	[PIDFD_NS_NET]     = { "net",               CLONE_NEWNET,    PIDFD_GET_NET_NAMESPACE,               },
+	[PIDFD_NS_CGROUP]  = { "cgroup",            CLONE_NEWCGROUP, PIDFD_GET_CGROUP_NAMESPACE,            },
+	[PIDFD_NS_TIME]	   = { "time",              CLONE_NEWTIME,   PIDFD_GET_TIME_NAMESPACE,              },
+	[PIDFD_NS_PIDCLD]  = { "pid_for_children",  0,               PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE,  },
+	[PIDFD_NS_TIMECLD] = { "time_for_children", 0,               PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE, },
 };
 
 FIXTURE(current_nsset)
@@ -54,6 +102,7 @@ FIXTURE(current_nsset)
 	pid_t pid;
 	int pidfd;
 	int nsfds[PIDFD_NS_MAX];
+	int child_pidfd_derived_nsfds[PIDFD_NS_MAX];
 
 	pid_t child_pid_exited;
 	int child_pidfd_exited;
@@ -61,10 +110,12 @@ FIXTURE(current_nsset)
 	pid_t child_pid1;
 	int child_pidfd1;
 	int child_nsfds1[PIDFD_NS_MAX];
+	int child_pidfd_derived_nsfds1[PIDFD_NS_MAX];
 
 	pid_t child_pid2;
 	int child_pidfd2;
 	int child_nsfds2[PIDFD_NS_MAX];
+	int child_pidfd_derived_nsfds2[PIDFD_NS_MAX];
 };
 
 static int sys_waitid(int which, pid_t pid, int options)
@@ -128,9 +179,12 @@ FIXTURE_SETUP(current_nsset)
 	char c;
 
 	for (i = 0; i < PIDFD_NS_MAX; i++) {
-		self->nsfds[i]		= -EBADF;
-		self->child_nsfds1[i]	= -EBADF;
-		self->child_nsfds2[i]	= -EBADF;
+		self->nsfds[i]				= -EBADF;
+		self->child_nsfds1[i]			= -EBADF;
+		self->child_nsfds2[i]			= -EBADF;
+		self->child_pidfd_derived_nsfds[i]	= -EBADF;
+		self->child_pidfd_derived_nsfds1[i]	= -EBADF;
+		self->child_pidfd_derived_nsfds2[i]	= -EBADF;
 	}
 
 	proc_fd = open("/proc/self/ns", O_DIRECTORY | O_CLOEXEC);
@@ -139,6 +193,11 @@ FIXTURE_SETUP(current_nsset)
 	}
 
 	self->pid = getpid();
+	self->pidfd = sys_pidfd_open(self->pid, 0);
+	EXPECT_GT(self->pidfd, 0) {
+		TH_LOG("%m - Failed to open pidfd for process %d", self->pid);
+	}
+
 	for (i = 0; i < PIDFD_NS_MAX; i++) {
 		const struct ns_info *info = &ns_info[i];
 		self->nsfds[i] = openat(proc_fd, info->name, O_RDONLY | O_CLOEXEC);
@@ -148,20 +207,27 @@ FIXTURE_SETUP(current_nsset)
 				       info->name, self->pid);
 			}
 		}
-	}
 
-	self->pidfd = sys_pidfd_open(self->pid, 0);
-	EXPECT_GT(self->pidfd, 0) {
-		TH_LOG("%m - Failed to open pidfd for process %d", self->pid);
+		self->child_pidfd_derived_nsfds[i] = ioctl(self->pidfd, info->pidfd_ioctl, 0);
+		if (self->child_pidfd_derived_nsfds[i] < 0) {
+			EXPECT_EQ(errno, EOPNOTSUPP) {
+				TH_LOG("%m - Failed to derive %s namespace from pidfd of process %d",
+				       info->name, self->pid);
+			}
+		}
 	}
 
 	/* Create task that exits right away. */
-	self->child_pid_exited = create_child(&self->child_pidfd_exited,
-					      CLONE_NEWUSER | CLONE_NEWNET);
+	self->child_pid_exited = create_child(&self->child_pidfd_exited, 0);
 	EXPECT_GE(self->child_pid_exited, 0);
 
-	if (self->child_pid_exited == 0)
+	if (self->child_pid_exited == 0) {
+		if (self->nsfds[PIDFD_NS_USER] >= 0 && unshare(CLONE_NEWUSER) < 0)
+			_exit(EXIT_FAILURE);
+		if (self->nsfds[PIDFD_NS_NET] >= 0 && unshare(CLONE_NEWNET) < 0)
+			_exit(EXIT_FAILURE);
 		_exit(EXIT_SUCCESS);
+	}
 
 	ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED | WNOWAIT), 0);
 
@@ -174,18 +240,43 @@ FIXTURE_SETUP(current_nsset)
 	EXPECT_EQ(ret, 0);
 
 	/* Create tasks that will be stopped. */
-	self->child_pid1 = create_child(&self->child_pidfd1,
-					CLONE_NEWUSER | CLONE_NEWNS |
-					CLONE_NEWCGROUP | CLONE_NEWIPC |
-					CLONE_NEWUTS | CLONE_NEWPID |
-					CLONE_NEWNET);
+	if (self->nsfds[PIDFD_NS_USER] >= 0 && self->nsfds[PIDFD_NS_PID] >= 0)
+		self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER | CLONE_NEWPID);
+	else if (self->nsfds[PIDFD_NS_PID] >= 0)
+		self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWPID);
+	else if (self->nsfds[PIDFD_NS_USER] >= 0)
+		self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER);
+	else
+		self->child_pid1 = create_child(&self->child_pidfd1, 0);
 	EXPECT_GE(self->child_pid1, 0);
 
 	if (self->child_pid1 == 0) {
 		close(ipc_sockets[0]);
 
-		if (!switch_timens())
+		if (self->nsfds[PIDFD_NS_MNT] >= 0 && unshare(CLONE_NEWNS) < 0) {
+			TH_LOG("%m - Failed to unshare mount namespace for process %d", self->pid);
 			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_CGROUP] >= 0 && unshare(CLONE_NEWCGROUP) < 0) {
+			TH_LOG("%m - Failed to unshare cgroup namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_IPC] >= 0 && unshare(CLONE_NEWIPC) < 0) {
+			TH_LOG("%m - Failed to unshare ipc namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_UTS] >= 0 && unshare(CLONE_NEWUTS) < 0) {
+			TH_LOG("%m - Failed to unshare uts namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_NET] >= 0 && unshare(CLONE_NEWNET) < 0) {
+			TH_LOG("%m - Failed to unshare net namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_TIME] >= 0 && !switch_timens()) {
+			TH_LOG("%m - Failed to unshare time namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
 
 		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
 			_exit(EXIT_FAILURE);
@@ -203,18 +294,43 @@ FIXTURE_SETUP(current_nsset)
 	ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
 	EXPECT_EQ(ret, 0);
 
-	self->child_pid2 = create_child(&self->child_pidfd2,
-					CLONE_NEWUSER | CLONE_NEWNS |
-					CLONE_NEWCGROUP | CLONE_NEWIPC |
-					CLONE_NEWUTS | CLONE_NEWPID |
-					CLONE_NEWNET);
+	if (self->nsfds[PIDFD_NS_USER] >= 0 && self->nsfds[PIDFD_NS_PID] >= 0)
+		self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID);
+	else if (self->nsfds[PIDFD_NS_PID] >= 0)
+		self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWPID);
+	else if (self->nsfds[PIDFD_NS_USER] >= 0)
+		self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER);
+	else
+		self->child_pid2 = create_child(&self->child_pidfd2, 0);
 	EXPECT_GE(self->child_pid2, 0);
 
 	if (self->child_pid2 == 0) {
 		close(ipc_sockets[0]);
 
-		if (!switch_timens())
+		if (self->nsfds[PIDFD_NS_MNT] >= 0 && unshare(CLONE_NEWNS) < 0) {
+			TH_LOG("%m - Failed to unshare mount namespace for process %d", self->pid);
 			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_CGROUP] >= 0 && unshare(CLONE_NEWCGROUP) < 0) {
+			TH_LOG("%m - Failed to unshare cgroup namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_IPC] >= 0 && unshare(CLONE_NEWIPC) < 0) {
+			TH_LOG("%m - Failed to unshare ipc namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_UTS] >= 0 && unshare(CLONE_NEWUTS) < 0) {
+			TH_LOG("%m - Failed to unshare uts namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_NET] >= 0 && unshare(CLONE_NEWNET) < 0) {
+			TH_LOG("%m - Failed to unshare net namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
+		if (self->nsfds[PIDFD_NS_TIME] >= 0 && !switch_timens()) {
+			TH_LOG("%m - Failed to unshare time namespace for process %d", self->pid);
+			_exit(EXIT_FAILURE);
+		}
 
 		if (write_nointr(ipc_sockets[1], "1", 1) < 0)
 			_exit(EXIT_FAILURE);
@@ -267,6 +383,22 @@ FIXTURE_SETUP(current_nsset)
 				       info->name, self->child_pid1);
 			}
 		}
+
+		self->child_pidfd_derived_nsfds1[i] = ioctl(self->child_pidfd1, info->pidfd_ioctl, 0);
+		if (self->child_pidfd_derived_nsfds1[i] < 0) {
+			EXPECT_EQ(errno, EOPNOTSUPP) {
+				TH_LOG("%m - Failed to derive %s namespace from pidfd of process %d",
+				       info->name, self->child_pid1);
+			}
+		}
+
+		self->child_pidfd_derived_nsfds2[i] = ioctl(self->child_pidfd2, info->pidfd_ioctl, 0);
+		if (self->child_pidfd_derived_nsfds2[i] < 0) {
+			EXPECT_EQ(errno, EOPNOTSUPP) {
+				TH_LOG("%m - Failed to derive %s namespace from pidfd of process %d",
+				       info->name, self->child_pid2);
+			}
+		}
 	}
 
 	close(proc_fd);
@@ -288,6 +420,12 @@ FIXTURE_TEARDOWN(current_nsset)
 			close(self->child_nsfds1[i]);
 		if (self->child_nsfds2[i] >= 0)
 			close(self->child_nsfds2[i]);
+		if (self->child_pidfd_derived_nsfds[i] >= 0)
+			close(self->child_pidfd_derived_nsfds[i]);
+		if (self->child_pidfd_derived_nsfds1[i] >= 0)
+			close(self->child_pidfd_derived_nsfds1[i]);
+		if (self->child_pidfd_derived_nsfds2[i] >= 0)
+			close(self->child_pidfd_derived_nsfds2[i]);
 	}
 
 	if (self->child_pidfd1 >= 0)
@@ -446,6 +584,42 @@ TEST_F(current_nsset, nsfd_incremental_setns)
 	}
 }
 
+TEST_F(current_nsset, pidfd_derived_nsfd_incremental_setns)
+{
+	int i;
+	pid_t pid;
+
+	pid = getpid();
+	for (i = 0; i < PIDFD_NS_MAX; i++) {
+		const struct ns_info *info = &ns_info[i];
+		int nsfd;
+
+		if (self->child_pidfd_derived_nsfds1[i] < 0)
+			continue;
+
+		if (info->flag) {
+			ASSERT_EQ(setns(self->child_pidfd_derived_nsfds1[i], info->flag), 0) {
+				TH_LOG("%m - Failed to setns to %s namespace of %d via nsfd %d",
+				       info->name, self->child_pid1,
+				       self->child_pidfd_derived_nsfds1[i]);
+			}
+		}
+
+		/* Verify that we have changed to the correct namespaces. */
+		if (info->flag == CLONE_NEWPID)
+			nsfd = self->child_pidfd_derived_nsfds[i];
+		else
+			nsfd = self->child_pidfd_derived_nsfds1[i];
+		ASSERT_EQ(in_same_namespace(nsfd, pid, info->name), 1) {
+			TH_LOG("setns failed to place us correctly into %s namespace of %d via nsfd %d",
+			       info->name, self->child_pid1,
+			       self->child_pidfd_derived_nsfds1[i]);
+		}
+		TH_LOG("Managed to correctly setns to %s namespace of %d via nsfd %d",
+		       info->name, self->child_pid1, self->child_pidfd_derived_nsfds1[i]);
+	}
+}
+
 TEST_F(current_nsset, pidfd_one_shot_setns)
 {
 	unsigned flags = 0;
@@ -542,6 +716,28 @@ TEST_F(current_nsset, no_foul_play)
 		       info->name, self->child_pid2,
 		       self->child_nsfds2[i]);
 	}
+
+	/*
+	 * Can't setns to a user namespace outside of our hierarchy since we
+	 * don't have caps in there and didn't create it. That means that under
+	 * no circumstances should we be able to setns to any of the other
+	 * ones since they aren't owned by our user namespace.
+	 */
+	for (i = 0; i < PIDFD_NS_MAX; i++) {
+		const struct ns_info *info = &ns_info[i];
+
+		if (self->child_pidfd_derived_nsfds2[i] < 0 || !info->flag)
+			continue;
+
+		ASSERT_NE(setns(self->child_pidfd_derived_nsfds2[i], info->flag), 0) {
+			TH_LOG("Managed to setns to %s namespace of %d via nsfd %d",
+			       info->name, self->child_pid2,
+			       self->child_pidfd_derived_nsfds2[i]);
+		}
+		TH_LOG("%m - Correctly failed to setns to %s namespace of %d via nsfd %d",
+		       info->name, self->child_pid2,
+		       self->child_pidfd_derived_nsfds2[i]);
+	}
 }
 
 TEST(setns_einval)
diff --git a/tools/testing/selftests/turbostat/added_perf_counters.py b/tools/testing/selftests/turbostat/added_perf_counters.py
new file mode 100755
index 0000000..9ab4aaf
--- /dev/null
+++ b/tools/testing/selftests/turbostat/added_perf_counters.py
@@ -0,0 +1,178 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+from shutil import which
+from os import pread
+
+class PerfCounterInfo:
+	def __init__(self, subsys, event):
+		self.subsys = subsys
+		self.event = event
+
+	def get_perf_event_name(self):
+		return f'{self.subsys}/{self.event}/'
+
+	def get_turbostat_perf_id(self, counter_scope, counter_type, column_name):
+		return f'perf/{self.subsys}/{self.event},{counter_scope},{counter_type},{column_name}'
+
+PERF_COUNTERS_CANDIDATES = [
+	PerfCounterInfo('msr', 'mperf'),
+	PerfCounterInfo('msr', 'aperf'),
+	PerfCounterInfo('msr', 'tsc'),
+	PerfCounterInfo('cstate_core', 'c1-residency'),
+	PerfCounterInfo('cstate_core', 'c6-residency'),
+	PerfCounterInfo('cstate_core', 'c7-residency'),
+	PerfCounterInfo('cstate_pkg', 'c2-residency'),
+	PerfCounterInfo('cstate_pkg', 'c3-residency'),
+	PerfCounterInfo('cstate_pkg', 'c6-residency'),
+	PerfCounterInfo('cstate_pkg', 'c7-residency'),
+	PerfCounterInfo('cstate_pkg', 'c8-residency'),
+	PerfCounterInfo('cstate_pkg', 'c9-residency'),
+	PerfCounterInfo('cstate_pkg', 'c10-residency'),
+]
+present_perf_counters = []
+
+def check_perf_access():
+	perf = which('perf')
+	if perf is None:
+		print('SKIP: Could not find perf binary, thus could not determine perf access.')
+		return False
+
+	def has_perf_counter_access(counter_name):
+		proc_perf = subprocess.run([perf, 'stat', '-e', counter_name, '--timeout', '10'],
+							 capture_output = True)
+
+		if proc_perf.returncode != 0:
+			print(f'SKIP: Could not read {counter_name} perf counter.')
+			return False
+
+		if b'<not supported>' in proc_perf.stderr:
+			print(f'SKIP: Could not read {counter_name} perf counter.')
+			return False
+
+		return True
+
+	for counter in PERF_COUNTERS_CANDIDATES:
+		if has_perf_counter_access(counter.get_perf_event_name()):
+			present_perf_counters.append(counter)
+
+	if len(present_perf_counters) == 0:
+		print('SKIP: Could not read any perf counter.')
+		return False
+
+	if len(present_perf_counters) != len(PERF_COUNTERS_CANDIDATES):
+		print(f'WARN: Could not access all of the counters - some will be left untested')
+
+	return True
+
+if not check_perf_access():
+	exit(0)
+
+turbostat_counter_source_opts = ['']
+
+turbostat = which('turbostat')
+if turbostat is None:
+	print('Could not find turbostat binary')
+	exit(1)
+
+timeout = which('timeout')
+if timeout is None:
+	print('Could not find timeout binary')
+	exit(1)
+
+proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True)
+if proc_turbostat.returncode != 0:
+	print(f'turbostat failed with {proc_turbostat.returncode}')
+	exit(1)
+
+EXPECTED_COLUMNS_DEBUG_DEFAULT = [b'usec', b'Time_Of_Day_Seconds', b'APIC', b'X2APIC']
+
+expected_columns = [b'CPU']
+counters_argv = []
+for counter in present_perf_counters:
+	if counter.subsys == 'cstate_core':
+		counter_scope = 'core'
+	elif counter.subsys == 'cstate_pkg':
+		counter_scope = 'package'
+	else:
+		counter_scope = 'cpu'
+
+	counter_type = 'delta'
+	column_name = counter.event
+
+	cparams = counter.get_turbostat_perf_id(
+		counter_scope = counter_scope,
+		counter_type = counter_type,
+		column_name = column_name
+	)
+	expected_columns.append(column_name.encode())
+	counters_argv.extend(['--add', cparams])
+
+expected_columns_debug = EXPECTED_COLUMNS_DEBUG_DEFAULT + expected_columns
+
+def gen_user_friendly_cmdline(argv_):
+	argv = argv_[:]
+	ret = ''
+
+	while len(argv) != 0:
+		arg = argv.pop(0)
+		arg_next = ''
+
+		if arg in ('-i', '--show', '--add'):
+			arg_next = argv.pop(0) if len(argv) > 0 else ''
+
+		ret += f'{arg} {arg_next} \\\n\t'
+
+	# Remove the last separator and return
+	return ret[:-4]
+
+#
+# Run turbostat for some time and send SIGINT
+#
+timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '0.2s']
+turbostat_argv = [turbostat, '-i', '0.50', '--show', 'CPU'] + counters_argv
+
+def check_columns_or_fail(expected_columns: list, actual_columns: list):
+	if len(actual_columns) != len(expected_columns):
+		print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}')
+		exit(1)
+
+	failed = False
+	for expected_column in expected_columns:
+		if expected_column not in actual_columns:
+			print(f'turbostat column check failed: missing column {expected_column.decode()}')
+			failed = True
+
+	if failed:
+		exit(1)
+
+cmdline = gen_user_friendly_cmdline(turbostat_argv)
+print(f'Running turbostat with:\n\t{cmdline}\n... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+	print(f'turbostat failed with {proc_turbostat.returncode}')
+	exit(1)
+
+actual_columns = proc_turbostat.stdout.split(b'\n')[0].split(b'\t')
+check_columns_or_fail(expected_columns, actual_columns)
+print('OK')
+
+#
+# Same, but with --debug
+#
+# We explicitly specify '--show CPU' to make sure turbostat
+# don't show a bunch of default counters instead.
+#
+turbostat_argv.append('--debug')
+
+cmdline = gen_user_friendly_cmdline(turbostat_argv)
+print(f'Running turbostat (in debug mode) with:\n\t{cmdline}\n... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+	print(f'turbostat failed with {proc_turbostat.returncode}')
+	exit(1)
+
+actual_columns = proc_turbostat.stdout.split(b'\n')[0].split(b'\t')
+check_columns_or_fail(expected_columns_debug, actual_columns)
+print('OK')
diff --git a/tools/testing/selftests/turbostat/smi_aperf_mperf.py b/tools/testing/selftests/turbostat/smi_aperf_mperf.py
new file mode 100755
index 0000000..6289cc4
--- /dev/null
+++ b/tools/testing/selftests/turbostat/smi_aperf_mperf.py
@@ -0,0 +1,157 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+from shutil import which
+from os import pread
+
+# CDLL calls dlopen underneath.
+# Calling it with None (null), we get handle to the our own image (python interpreter).
+# We hope to find sched_getcpu() inside ;]
+# This is a bit ugly, but helps shipping working software, so..
+try:
+	import ctypes
+
+	this_image = ctypes.CDLL(None)
+	BASE_CPU = this_image.sched_getcpu()
+except:
+	BASE_CPU = 0 # If we fail, set to 0 and pray it's not offline.
+
+MSR_IA32_MPERF = 0x000000e7
+MSR_IA32_APERF = 0x000000e8
+
+def check_perf_access():
+	perf = which('perf')
+	if perf is None:
+		print('SKIP: Could not find perf binary, thus could not determine perf access.')
+		return False
+
+	def has_perf_counter_access(counter_name):
+		proc_perf = subprocess.run([perf, 'stat', '-e', counter_name, '--timeout', '10'],
+					    capture_output = True)
+
+		if proc_perf.returncode != 0:
+			print(f'SKIP: Could not read {counter_name} perf counter, assuming no access.')
+			return False
+
+		if b'<not supported>' in proc_perf.stderr:
+			print(f'SKIP: Could not read {counter_name} perf counter, assuming no access.')
+			return False
+
+		return True
+
+	if not has_perf_counter_access('msr/mperf/'):
+		return False
+	if not has_perf_counter_access('msr/aperf/'):
+		return False
+	if not has_perf_counter_access('msr/smi/'):
+		return False
+
+	return True
+
+def check_msr_access():
+	try:
+		file_msr = open(f'/dev/cpu/{BASE_CPU}/msr', 'rb')
+	except:
+		return False
+
+	if len(pread(file_msr.fileno(), 8, MSR_IA32_MPERF)) != 8:
+		return False
+
+	if len(pread(file_msr.fileno(), 8, MSR_IA32_APERF)) != 8:
+		return False
+
+	return True
+
+has_perf_access = check_perf_access()
+has_msr_access = check_msr_access()
+
+turbostat_counter_source_opts = ['']
+
+if has_msr_access:
+	turbostat_counter_source_opts.append('--no-perf')
+else:
+	print('SKIP: doesn\'t have MSR access, skipping run with --no-perf')
+
+if has_perf_access:
+	turbostat_counter_source_opts.append('--no-msr')
+else:
+	print('SKIP: doesn\'t have perf access, skipping run with --no-msr')
+
+if not has_msr_access and not has_perf_access:
+	print('SKIP: No MSR nor perf access detected. Skipping the tests entirely')
+	exit(0)
+
+turbostat = which('turbostat')
+if turbostat is None:
+	print('Could not find turbostat binary')
+	exit(1)
+
+timeout = which('timeout')
+if timeout is None:
+	print('Could not find timeout binary')
+	exit(1)
+
+proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True)
+if proc_turbostat.returncode != 0:
+	print(f'turbostat failed with {proc_turbostat.returncode}')
+	exit(1)
+
+EXPECTED_COLUMNS_DEBUG_DEFAULT = b'usec\tTime_Of_Day_Seconds\tAPIC\tX2APIC'
+
+SMI_APERF_MPERF_DEPENDENT_BICS = [
+	'SMI',
+	'Avg_MHz',
+	'Busy%',
+	'Bzy_MHz',
+]
+if has_perf_access:
+	SMI_APERF_MPERF_DEPENDENT_BICS.append('IPC')
+
+for bic in SMI_APERF_MPERF_DEPENDENT_BICS:
+	for counter_source_opt in turbostat_counter_source_opts:
+
+		# Ugly special case, but it is what it is..
+		if counter_source_opt == '--no-perf' and bic == 'IPC':
+			continue
+
+		expected_columns = bic.encode()
+		expected_columns_debug = EXPECTED_COLUMNS_DEBUG_DEFAULT + f'\t{bic}'.encode()
+
+		#
+		# Run turbostat for some time and send SIGINT
+		#
+		timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '0.2s']
+		turbostat_argv = [turbostat, '-i', '0.50', '--show', bic]
+
+		if counter_source_opt:
+			turbostat_argv.append(counter_source_opt)
+
+		print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+		proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+		if proc_turbostat.returncode != 0:
+			print(f'turbostat failed with {proc_turbostat.returncode}')
+			exit(1)
+
+		actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+		if expected_columns != actual_columns:
+			print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}')
+			exit(1)
+		print('OK')
+
+		#
+		# Same, but with --debug
+		#
+		turbostat_argv.append('--debug')
+
+		print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+		proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+		if proc_turbostat.returncode != 0:
+			print(f'turbostat failed with {proc_turbostat.returncode}')
+			exit(1)
+
+		actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+		if expected_columns_debug != actual_columns:
+			print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}')
+			exit(1)
+		print('OK')
diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
index a8dc51a..30d5c8f 100644
--- a/tools/testing/selftests/vDSO/.gitignore
+++ b/tools/testing/selftests/vDSO/.gitignore
@@ -6,3 +6,5 @@
 vdso_test_gettimeofday
 vdso_test_getcpu
 vdso_standalone_test_x86
+vdso_test_getrandom
+vdso_test_chacha
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 98d8ba2..3de8e7e 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+SODIUM := $(shell pkg-config --libs libsodium 2>/dev/null)
 
 TEST_GEN_PROGS := vdso_test_gettimeofday
 TEST_GEN_PROGS += vdso_test_getcpu
@@ -10,6 +11,12 @@
 TEST_GEN_PROGS += vdso_standalone_test_x86
 endif
 TEST_GEN_PROGS += vdso_test_correctness
+ifeq ($(uname_M),x86_64)
+TEST_GEN_PROGS += vdso_test_getrandom
+ifneq ($(SODIUM),)
+TEST_GEN_PROGS += vdso_test_chacha
+endif
+endif
 
 CFLAGS := -std=gnu99
 
@@ -28,3 +35,14 @@
 
 $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c
 $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl
+
+$(OUTPUT)/vdso_test_getrandom: parse_vdso.c
+$(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \
+                                         -isystem $(top_srcdir)/include/uapi
+
+$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrandom-chacha.S
+$(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \
+                                      -isystem $(top_srcdir)/arch/$(ARCH)/include \
+                                      -isystem $(top_srcdir)/include \
+                                      -D__ASSEMBLY__ -DBULID_VDSO -DCONFIG_FUNCTION_ALIGNMENT=0 \
+                                      -Wa,--noexecstack $(SODIUM)
diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c
new file mode 100644
index 0000000..e38f44e
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <sodium/crypto_stream_chacha20.h>
+#include <sys/random.h>
+#include <string.h>
+#include <stdint.h>
+#include "../kselftest.h"
+
+extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks);
+
+int main(int argc, char *argv[])
+{
+	enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 };
+	static const uint8_t nonce[8] = { 0 };
+	uint32_t counter[2];
+	uint8_t key[32];
+	uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS];
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	for (unsigned int trial = 0; trial < TRIALS; ++trial) {
+		if (getrandom(key, sizeof(key), 0) != sizeof(key)) {
+			printf("getrandom() failed!\n");
+			return KSFT_SKIP;
+		}
+		crypto_stream_chacha20(output1, sizeof(output1), nonce, key);
+		for (unsigned int split = 0; split < BLOCKS; ++split) {
+			memset(output2, 'X', sizeof(output2));
+			memset(counter, 0, sizeof(counter));
+			if (split)
+				__arch_chacha20_blocks_nostack(output2, key, counter, split);
+			__arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split);
+			if (memcmp(output1, output2, sizeof(output1)))
+				return KSFT_FAIL;
+		}
+	}
+	ksft_test_result_pass("chacha: PASS\n");
+	return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c
new file mode 100644
index 0000000..0512242
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <assert.h>
+#include <pthread.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/random.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/random.h>
+
+#include "../kselftest.h"
+#include "parse_vdso.h"
+
+#ifndef timespecsub
+#define	timespecsub(tsp, usp, vsp)					\
+	do {								\
+		(vsp)->tv_sec = (tsp)->tv_sec - (usp)->tv_sec;		\
+		(vsp)->tv_nsec = (tsp)->tv_nsec - (usp)->tv_nsec;	\
+		if ((vsp)->tv_nsec < 0) {				\
+			(vsp)->tv_sec--;				\
+			(vsp)->tv_nsec += 1000000000L;			\
+		}							\
+	} while (0)
+#endif
+
+static struct {
+	pthread_mutex_t lock;
+	void **states;
+	size_t len, cap;
+} grnd_allocator = {
+	.lock = PTHREAD_MUTEX_INITIALIZER
+};
+
+static struct {
+	ssize_t(*fn)(void *, size_t, unsigned long, void *, size_t);
+	pthread_key_t key;
+	pthread_once_t initialized;
+	struct vgetrandom_opaque_params params;
+} grnd_ctx = {
+	.initialized = PTHREAD_ONCE_INIT
+};
+
+static void *vgetrandom_get_state(void)
+{
+	void *state = NULL;
+
+	pthread_mutex_lock(&grnd_allocator.lock);
+	if (!grnd_allocator.len) {
+		size_t page_size = getpagesize();
+		size_t new_cap;
+		size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */
+		void *new_block, *new_states;
+
+		alloc_size = (num * grnd_ctx.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1));
+		num = (page_size / grnd_ctx.params.size_of_opaque_state) * (alloc_size / page_size);
+		new_block = mmap(0, alloc_size, grnd_ctx.params.mmap_prot, grnd_ctx.params.mmap_flags, -1, 0);
+		if (new_block == MAP_FAILED)
+			goto out;
+
+		new_cap = grnd_allocator.cap + num;
+		new_states = reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd_allocator.states));
+		if (!new_states)
+			goto unmap;
+		grnd_allocator.cap = new_cap;
+		grnd_allocator.states = new_states;
+
+		for (size_t i = 0; i < num; ++i) {
+			if (((uintptr_t)new_block & (page_size - 1)) + grnd_ctx.params.size_of_opaque_state > page_size)
+				new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1)));
+			grnd_allocator.states[i] = new_block;
+			new_block += grnd_ctx.params.size_of_opaque_state;
+		}
+		grnd_allocator.len = num;
+		goto success;
+
+	unmap:
+		munmap(new_block, alloc_size);
+		goto out;
+	}
+success:
+	state = grnd_allocator.states[--grnd_allocator.len];
+
+out:
+	pthread_mutex_unlock(&grnd_allocator.lock);
+	return state;
+}
+
+static void vgetrandom_put_state(void *state)
+{
+	if (!state)
+		return;
+	pthread_mutex_lock(&grnd_allocator.lock);
+	grnd_allocator.states[grnd_allocator.len++] = state;
+	pthread_mutex_unlock(&grnd_allocator.lock);
+}
+
+static void vgetrandom_init(void)
+{
+	if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) != 0)
+		return;
+	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	if (!sysinfo_ehdr) {
+		printf("AT_SYSINFO_EHDR is not present!\n");
+		exit(KSFT_SKIP);
+	}
+	vdso_init_from_sysinfo_ehdr(sysinfo_ehdr);
+	grnd_ctx.fn = (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_getrandom");
+	if (!grnd_ctx.fn) {
+		printf("__vdso_getrandom is missing!\n");
+		exit(KSFT_FAIL);
+	}
+	if (grnd_ctx.fn(NULL, 0, 0, &grnd_ctx.params, ~0UL) != 0) {
+		printf("failed to fetch vgetrandom params!\n");
+		exit(KSFT_FAIL);
+	}
+}
+
+static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags)
+{
+	void *state;
+
+	pthread_once(&grnd_ctx.initialized, vgetrandom_init);
+	state = pthread_getspecific(grnd_ctx.key);
+	if (!state) {
+		state = vgetrandom_get_state();
+		if (pthread_setspecific(grnd_ctx.key, state) != 0) {
+			vgetrandom_put_state(state);
+			state = NULL;
+		}
+		if (!state) {
+			printf("vgetrandom_get_state failed!\n");
+			exit(KSFT_FAIL);
+		}
+	}
+	return grnd_ctx.fn(buf, len, flags, state, grnd_ctx.params.size_of_opaque_state);
+}
+
+enum { TRIALS = 25000000, THREADS = 256 };
+
+static void *test_vdso_getrandom(void *)
+{
+	for (size_t i = 0; i < TRIALS; ++i) {
+		unsigned int val;
+		ssize_t ret = vgetrandom(&val, sizeof(val), 0);
+		assert(ret == sizeof(val));
+	}
+	return NULL;
+}
+
+static void *test_libc_getrandom(void *)
+{
+	for (size_t i = 0; i < TRIALS; ++i) {
+		unsigned int val;
+		ssize_t ret = getrandom(&val, sizeof(val), 0);
+		assert(ret == sizeof(val));
+	}
+	return NULL;
+}
+
+static void *test_syscall_getrandom(void *)
+{
+	for (size_t i = 0; i < TRIALS; ++i) {
+		unsigned int val;
+		ssize_t ret = syscall(__NR_getrandom, &val, sizeof(val), 0);
+		assert(ret == sizeof(val));
+	}
+	return NULL;
+}
+
+static void bench_single(void)
+{
+	struct timespec start, end, diff;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	test_vdso_getrandom(NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("   vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	test_libc_getrandom(NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("   libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	test_syscall_getrandom(NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec);
+}
+
+static void bench_multi(void)
+{
+	struct timespec start, end, diff;
+	pthread_t threads[THREADS];
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (size_t i = 0; i < THREADS; ++i)
+		assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0);
+	for (size_t i = 0; i < THREADS; ++i)
+		pthread_join(threads[i], NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("   vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (size_t i = 0; i < THREADS; ++i)
+		assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0);
+	for (size_t i = 0; i < THREADS; ++i)
+		pthread_join(threads[i], NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("   libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (size_t i = 0; i < THREADS; ++i)
+		assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0);
+	for (size_t i = 0; i < THREADS; ++i)
+		pthread_join(threads[i], NULL);
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	timespecsub(&end, &start, &diff);
+	printf("   syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec);
+}
+
+static void fill(void)
+{
+	uint8_t weird_size[323929];
+	for (;;)
+		vgetrandom(weird_size, sizeof(weird_size), 0);
+}
+
+static void kselftest(void)
+{
+	uint8_t weird_size[1263];
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	for (size_t i = 0; i < 1000; ++i) {
+		ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0);
+		if (ret != sizeof(weird_size))
+			exit(KSFT_FAIL);
+	}
+
+	ksft_test_result_pass("getrandom: PASS\n");
+	exit(KSFT_PASS);
+}
+
+static void usage(const char *argv0)
+{
+	fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill]\n", argv0);
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc == 1) {
+		kselftest();
+		return 0;
+	}
+
+	if (argc != 2) {
+		usage(argv[0]);
+		return 1;
+	}
+	if (!strcmp(argv[1], "bench-single"))
+		bench_single();
+	else if (!strcmp(argv[1], "bench-multi"))
+		bench_multi();
+	else if (!strcmp(argv[1], "fill"))
+		fill();
+	else {
+		usage(argv[0]);
+		return 1;
+	}
+	return 0;
+}
diff --git a/tools/tracing/latency/Makefile.config b/tools/tracing/latency/Makefile.config
index b25e531..0fe6b50 100644
--- a/tools/tracing/latency/Makefile.config
+++ b/tools/tracing/latency/Makefile.config
@@ -3,8 +3,9 @@
 STOP_ERROR :=
 
 define lib_setup
-  $(eval EXTLIBS += -l$(1))
   $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)"))
+  $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)"))
+  $(eval EXTLIBS += $(shell sh -c "$(PKG_CONFIG) --libs-only-l lib$(1)"))
 endef
 
 $(call feature_check,libtraceevent)
diff --git a/tools/tracing/rtla/Makefile.config b/tools/tracing/rtla/Makefile.config
index 0b7ecfb..5f8c286 100644
--- a/tools/tracing/rtla/Makefile.config
+++ b/tools/tracing/rtla/Makefile.config
@@ -7,7 +7,8 @@
 
 define lib_setup
   $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)"))
-  $(eval EXTLIBS += -l$(1))
+  $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)"))
+  $(eval EXTLIBS += $(shell sh -c "$(PKG_CONFIG) --libs-only-l lib$(1)"))
 endef
 
 $(call feature_check,libtraceevent)
diff --git a/tools/verification/rv/Makefile.config b/tools/verification/rv/Makefile.config
index 6d4ba77..0663022 100644
--- a/tools/verification/rv/Makefile.config
+++ b/tools/verification/rv/Makefile.config
@@ -7,7 +7,8 @@
 
 define lib_setup
   $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)"))
-  $(eval EXTLIBS += -l$(1))
+  $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)"))
+  $(eval EXTLIBS += $(shell sh -c "$(PKG_CONFIG) --libs-only-l lib$(1)"))
 endef
 
 $(call feature_check,libtraceevent)