dmaengine updates for v6.16

New support:
   - Renesas RZ/V2H(P) dma support for r9a09g057
   - Arm DMA-350 driver
   - Tegra Tegra264 ADMA support
 
  Updates:
   - AMD ptdma driver code removal and optimizations
   - Freescale edma error interrupt handler support
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE+vs47OPLdNbVcHzyfBQHDyUjg0cFAmhBO1YACgkQfBQHDyUj
 g0cuMxAAqscuPU17PjJPDy9Fzaq+B3nsZ9JR+Y/M7ifxFJSedJqdaZc7w4OsfGy2
 VZIWiSbpK2WrQHLTh/KlE2AeycO0zX5H1vQmYc4GNQn+18cprxj68YHLb05ZskJq
 sNVpEI0zZCxrFUgz8TrwdNcDzTC71TdtD2VLqZ6dCYcoi8lWiHPdbzxR/cSpbENb
 ysSrAoJy6v92ES2McH3wLAcwuchlC1wFMof9kVVhe3ueZnrtvuBML/fZldKE85qc
 dgcm9r1XOdcU3rOBxKQkQq2b0PzeRcUhUNRErqMQVTNs8Vg3N02x2jM214XKNLGt
 G/aFac9neun6iJ3H8rXzHEFhO8bInNddCjfv1SBdV0UR2LZHnzHQHz+0Og/HdyGD
 kkr3QsU+JzUQe29cHRwDKUR63l5dd+6PgwkWgcxYuauhFNRFpxdlosepmWZWZ+GE
 OVy4D/tWu1acXvorm9ZnIbkg/9anzQJEj78+Y9Tlgh5C59nBINfBtVjTVw9BWDTo
 1P9YS3YGdkT49uZu1sust9ug4H9/yifcXY4uXzBdTIYZTt3kNZfncVr3kMkMgAdU
 bcm5PvnklIRo+JWd8WftiLQDyF4OWUcf5CG3VVFthIR4Fla+1Wpg41NjQVLvRNzk
 Ji/WzLj0Wnzx+QuPyUC3NFKE11IJdB+7hGktfVBHcuQ/W6Vc7bY=
 =cu98
 -----END PGP SIGNATURE-----

Merge tag 'dmaengine-6.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "A fairly small update for the dmaengine subsystem. This has a new ARM
  dmaengine driver and couple of new device support and few driver
  changes:

  New support:
   - Renesas RZ/V2H(P) dma support for r9a09g057
   - Arm DMA-350 driver
   - Tegra Tegra264 ADMA support

  Updates:
   - AMD ptdma driver code removal and optimizations
   - Freescale edma error interrupt handler support"

* tag 'dmaengine-6.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (27 commits)
  dmaengine: idxd: Remove unused pointer and macro
  arm64: dts: renesas: r9a09g057: Add DMAC nodes
  dmaengine: sh: rz-dmac: Add RZ/V2H(P) support
  dmaengine: sh: rz-dmac: Allow for multiple DMACs
  irqchip/renesas-rzv2h: Add rzv2h_icu_register_dma_req()
  dt-bindings: dma: rz-dmac: Document RZ/V2H(P) family of SoCs
  dt-bindings: dma: rz-dmac: Restrict properties for RZ/A1H
  dmaengine: idxd: Narrow the restriction on BATCH to ver. 1 only
  dmaengine: ti: Add NULL check in udma_probe()
  fsldma: Set correct dma_mask based on hw capability
  dmaengine: idxd: Check availability of workqueue allocated by idxd wq driver before using
  dmaengine: xilinx_dma: Set dma_device directions
  dmaengine: tegra210-adma: Add Tegra264 support
  dt-bindings: Document Tegra264 ADMA support
  dmaengine: dw-edma: Add HDMA NATIVE map check
  dmaegnine: fsl-edma: add edma error interrupt handler
  dt-bindings: dma: fsl-edma: increase maxItems of interrupts and interrupt-names
  dmaengine: ARM_DMA350 should depend on ARM/ARM64
  dt-bindings: dma: qcom,bam: Document dma-coherent property
  dmaengine: Add Arm DMA-350 driver
  ...

Documentation/devicetree/bindings/dma/arm,dma-350.yaml

@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/arm,dma-350.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm CoreLink DMA-350 Controller
+
+maintainers:
+  - Robin Murphy <robin.murphy@arm.com>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    const: arm,dma-350
+
+  reg:
+    items:
+      - description: Base and size of the full register map
+
+  interrupts:
+    minItems: 1
+    items:
+      - description: Channel 0 interrupt
+      - description: Channel 1 interrupt
+      - description: Channel 2 interrupt
+      - description: Channel 3 interrupt
+      - description: Channel 4 interrupt
+      - description: Channel 5 interrupt
+      - description: Channel 6 interrupt
+      - description: Channel 7 interrupt
+
+  "#dma-cells":
+    const: 1
+    description: The cell is the trigger input number
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+unevaluatedProperties: false

Documentation/devicetree/bindings/dma/fsl,edma.yaml

@@ -48,11 +48,11 @@ properties:
 
   interrupts:
     minItems: 1
-    maxItems: 64
+    maxItems: 65
 
   interrupt-names:
     minItems: 1
-    maxItems: 64
+    maxItems: 65
 
   "#dma-cells":
     description: |

Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml

@@ -19,6 +19,7 @@ properties:
       - enum:
           - nvidia,tegra210-adma
           - nvidia,tegra186-adma
+          - nvidia,tegra264-adma
       - items:
           - enum:
               - nvidia,tegra234-adma
@@ -92,6 +93,7 @@ allOf:
           contains:
             enum:
               - nvidia,tegra186-adma
+              - nvidia,tegra264-adma
     then:
       anyOf:
         - properties:

Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml

@@ -42,6 +42,8 @@ properties:
   interrupts:
     maxItems: 1
 
+  dma-coherent: true
+
   iommus:
     minItems: 1
     maxItems: 6

Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml

@@ -11,19 +11,23 @@ maintainers:
 
 properties:
   compatible:
-    items:
+    oneOf:
-      - enum:
+      - items:
-          - renesas,r7s72100-dmac # RZ/A1H
+          - enum:
-          - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
+              - renesas,r7s72100-dmac # RZ/A1H
-          - renesas,r9a07g044-dmac # RZ/G2{L,LC}
+              - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
-          - renesas,r9a07g054-dmac # RZ/V2L
+              - renesas,r9a07g044-dmac # RZ/G2{L,LC}
-          - renesas,r9a08g045-dmac # RZ/G3S
+              - renesas,r9a07g054-dmac # RZ/V2L
-      - const: renesas,rz-dmac
+              - renesas,r9a08g045-dmac # RZ/G3S
+          - const: renesas,rz-dmac
+
+      - const: renesas,r9a09g057-dmac # RZ/V2H(P)
 
   reg:
     items:
       - description: Control and channel register block
       - description: DMA extended resource selector block
+    minItems: 1
 
   interrupts:
     maxItems: 17
@@ -52,6 +56,7 @@ properties:
     items:
       - description: DMA main clock
       - description: DMA register access clock
+    minItems: 1
 
   clock-names:
     items:
@@ -61,10 +66,10 @@ properties:
   '#dma-cells':
     const: 1
     description:
-      The cell specifies the encoded MID/RID values of the DMAC port
+      The cell specifies the encoded MID/RID or the REQ No values of
-      connected to the DMA client and the slave channel configuration
+      the DMAC port connected to the DMA client and the slave channel
-      parameters.
+      configuration parameters.
-      bits[0:9] - Specifies MID/RID value
+      bits[0:9] - Specifies the MID/RID or the REQ No value
       bit[10] - Specifies DMA request high enable (HIEN)
       bit[11] - Specifies DMA request detection type (LVL)
       bits[12:14] - Specifies DMAACK output mode (AM)
@@ -80,12 +85,26 @@ properties:
     items:
       - description: Reset for DMA ARESETN reset terminal
       - description: Reset for DMA RST_ASYNC reset terminal
+    minItems: 1
 
   reset-names:
     items:
       - const: arst
       - const: rst_async
 
+  renesas,icu:
+    description:
+      It must contain the phandle to the ICU and the index of the DMAC as seen
+      from the ICU.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - items:
+          - description: Phandle to the ICU node.
+          - description:
+              The number of the DMAC as seen from the ICU, i.e. parameter k from
+              register ICU_DMkSELy. This may differ from the actual DMAC instance
+              number.
+
 required:
   - compatible
   - reg
@@ -98,13 +117,25 @@ allOf:
   - $ref: dma-controller.yaml#
 
   - if:
-      not:
+      properties:
-        properties:
+        compatible:
-          compatible:
+          contains:
-            contains:
+            enum:
-              enum:
+              - renesas,r9a07g043-dmac
-                - renesas,r7s72100-dmac
+              - renesas,r9a07g044-dmac
+              - renesas,r9a07g054-dmac
+              - renesas,r9a08g045-dmac
     then:
+      properties:
+        reg:
+          minItems: 2
+        clocks:
+          minItems: 2
+        resets:
+          minItems: 2
+
+        renesas,icu: false
+
       required:
         - clocks
         - clock-names
@@ -112,6 +143,46 @@ allOf:
         - resets
         - reset-names
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r7s72100-dmac
+    then:
+      properties:
+        reg:
+          minItems: 2
+
+        clocks: false
+        clock-names: false
+        power-domains: false
+        resets: false
+        reset-names: false
+        renesas,icu: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r9a09g057-dmac
+    then:
+      properties:
+        reg:
+          maxItems: 1
+        clocks:
+          maxItems: 1
+        resets:
+          maxItems: 1
+
+        clock-names: false
+        reset-names: false
+
+      required:
+        - clocks
+        - power-domains
+        - renesas,icu
+        - resets
+
 additionalProperties: false
 
 examples:

Documentation/driver-api/dmaengine/provider.rst

@@ -172,8 +172,8 @@ Currently, the types available are:
   - It's usually used for copying pixel data between host memory and
     memory-mapped GPU device memory, such as found on modern PCI video graphics
     cards. The most immediate example is the OpenGL API function
-    ``glReadPielx()``, which might require a verbatim copy of a huge framebuffer
+    ``glReadPixels()``, which might require a verbatim copy of a huge
-    from local device memory onto host memory.
+    framebuffer from local device memory onto host memory.
 
 - DMA_XOR
 

MAINTAINERS

@@ -10781,7 +10781,7 @@ F:	net/dsa/tag_hellcreek.c
 
 HISILICON DMA DRIVER
 M:	Zhou Wang <wangzhou1@hisilicon.com>
-M:	Jie Hai <haijie1@huawei.com>
+M:	Longfang Liu <liulongfang@huawei.com>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	drivers/dma/hisi_dma.c

arch/arm64/boot/dts/renesas/r9a09g057.dtsi

@@ -280,6 +280,171 @@
 			resets = <&cpg 0x30>;
 		};
 
+		dmac0: dma-controller@11400000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x11400000 0 0x10000>;
+			interrupts = <GIC_SPI 499 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 89  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 90  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 91  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 92  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 93  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 94  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 95  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 96  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 97  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 98  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 99  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 100 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 101 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 102 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 103 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 104 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x0>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x31>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 4>;
+		};
+
+		dmac1: dma-controller@14830000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x14830000 0 0x10000>;
+			interrupts = <GIC_SPI 495 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 25  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 26  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 27  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 28  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 29  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 30  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 31  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 32  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 33  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 34  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 35  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 36  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 37  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 38  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 39  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 40  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x1>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x32>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 0>;
+		};
+
+		dmac2: dma-controller@14840000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x14840000 0 0x10000>;
+			interrupts = <GIC_SPI 496 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 41  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 42  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 43  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 44  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 45  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 46  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 47  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 48  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 49  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 50  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 51  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 52  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 53  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 54  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 55  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 56  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x2>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x33>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 1>;
+		};
+
+		dmac3: dma-controller@12000000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x12000000 0 0x10000>;
+			interrupts = <GIC_SPI 497 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 57  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 58  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 59  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 60  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 61  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 62  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 63  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 64  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 65  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 66  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 67  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 68  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 69  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 70  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 71  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 72  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x3>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x34>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 2>;
+		};
+
+		dmac4: dma-controller@12010000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x12010000 0 0x10000>;
+			interrupts = <GIC_SPI 498 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 73  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 74  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 75  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 76  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 77  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 78  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 79  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 80  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 81  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 82  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 83  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 84  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 85  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 86  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 87  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 88  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x4>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x35>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 3>;
+		};
+
 		ostm0: timer@11800000 {
 			compatible = "renesas,r9a09g057-ostm", "renesas,ostm";
 			reg = <0x0 0x11800000 0x0 0x1000>;

drivers/dma/Kconfig

@@ -93,6 +93,14 @@ config APPLE_ADMAC
 	help
 	  Enable support for Audio DMA Controller found on Apple Silicon SoCs.
 
+config ARM_DMA350
+	tristate "Arm DMA-350 support"
+	depends on ARM || ARM64 || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Arm DMA-350 controller.
+
 config AT_HDMAC
 	tristate "Atmel AHB DMA support"
 	depends on ARCH_AT91

drivers/dma/Makefile

@@ -17,6 +17,7 @@ obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o
+obj-$(CONFIG_ARM_DMA350) += arm-dma350.o
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o

drivers/dma/amd/ptdma/ptdma-dmaengine.c

@@ -566,7 +566,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 	struct ae4_device *ae4 = NULL;
 	struct pt_dma_chan *chan;
 	char *desc_cache_name;
-	char *cmd_cache_name;
 	int ret, i;
 
 	if (pt->ver == AE4_DMA_VERSION)
@@ -582,27 +581,17 @@ int pt_dmaengine_register(struct pt_device *pt)
 	if (!pt->pt_dma_chan)
 		return -ENOMEM;
 
-	cmd_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
-					"%s-dmaengine-cmd-cache",
-					dev_name(pt->dev));
-	if (!cmd_cache_name)
-		return -ENOMEM;
-
 	desc_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
 					 "%s-dmaengine-desc-cache",
 					 dev_name(pt->dev));
-	if (!desc_cache_name) {
+	if (!desc_cache_name)
-		ret = -ENOMEM;
+		return -ENOMEM;
-		goto err_cache;
-	}
 
 	pt->dma_desc_cache = kmem_cache_create(desc_cache_name,
 					       sizeof(struct pt_dma_desc), 0,
 					       SLAB_HWCACHE_ALIGN, NULL);
-	if (!pt->dma_desc_cache) {
+	if (!pt->dma_desc_cache)
-		ret = -ENOMEM;
+		return -ENOMEM;
-		goto err_cache;
-	}
 
 	dma_dev->dev = pt->dev;
 	dma_dev->src_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
@@ -656,9 +645,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 err_reg:
 	kmem_cache_destroy(pt->dma_desc_cache);
 
-err_cache:
-	kmem_cache_destroy(pt->dma_cmd_cache);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pt_dmaengine_register);
@@ -670,5 +656,4 @@ void pt_dmaengine_unregister(struct pt_device *pt)
 	dma_async_device_unregister(dma_dev);
 
 	kmem_cache_destroy(pt->dma_desc_cache);
-	kmem_cache_destroy(pt->dma_cmd_cache);
 }

drivers/dma/amd/ptdma/ptdma.h

@@ -254,7 +254,6 @@ struct pt_device {
 	/* Support for the DMA Engine capabilities */
 	struct dma_device dma_dev;
 	struct pt_dma_chan *pt_dma_chan;
-	struct kmem_cache *dma_cmd_cache;
 	struct kmem_cache *dma_desc_cache;
 
 	wait_queue_head_t lsb_queue;

drivers/dma/arm-dma350.c

@@ -0,0 +1,660 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2024-2025 Arm Limited
+// Arm DMA-350 driver
+
+#include <linux/bitfield.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+#define DMAINFO			0x0f00
+
+#define DMA_BUILDCFG0		0xb0
+#define DMA_CFG_DATA_WIDTH	GENMASK(18, 16)
+#define DMA_CFG_ADDR_WIDTH	GENMASK(15, 10)
+#define DMA_CFG_NUM_CHANNELS	GENMASK(9, 4)
+
+#define DMA_BUILDCFG1		0xb4
+#define DMA_CFG_NUM_TRIGGER_IN	GENMASK(8, 0)
+
+#define IIDR			0xc8
+#define IIDR_PRODUCTID		GENMASK(31, 20)
+#define IIDR_VARIANT		GENMASK(19, 16)
+#define IIDR_REVISION		GENMASK(15, 12)
+#define IIDR_IMPLEMENTER	GENMASK(11, 0)
+
+#define PRODUCTID_DMA350	0x3a0
+#define IMPLEMENTER_ARM		0x43b
+
+#define DMACH(n)		(0x1000 + 0x0100 * (n))
+
+#define CH_CMD			0x00
+#define CH_CMD_RESUME		BIT(5)
+#define CH_CMD_PAUSE		BIT(4)
+#define CH_CMD_STOP		BIT(3)
+#define CH_CMD_DISABLE		BIT(2)
+#define CH_CMD_CLEAR		BIT(1)
+#define CH_CMD_ENABLE		BIT(0)
+
+#define CH_STATUS		0x04
+#define CH_STAT_RESUMEWAIT	BIT(21)
+#define CH_STAT_PAUSED		BIT(20)
+#define CH_STAT_STOPPED		BIT(19)
+#define CH_STAT_DISABLED	BIT(18)
+#define CH_STAT_ERR		BIT(17)
+#define CH_STAT_DONE		BIT(16)
+#define CH_STAT_INTR_ERR	BIT(1)
+#define CH_STAT_INTR_DONE	BIT(0)
+
+#define CH_INTREN		0x08
+#define CH_INTREN_ERR		BIT(1)
+#define CH_INTREN_DONE		BIT(0)
+
+#define CH_CTRL			0x0c
+#define CH_CTRL_USEDESTRIGIN	BIT(26)
+#define CH_CTRL_USESRCTRIGIN	BIT(26)
+#define CH_CTRL_DONETYPE	GENMASK(23, 21)
+#define CH_CTRL_REGRELOADTYPE	GENMASK(20, 18)
+#define CH_CTRL_XTYPE		GENMASK(11, 9)
+#define CH_CTRL_TRANSIZE	GENMASK(2, 0)
+
+#define CH_SRCADDR		0x10
+#define CH_SRCADDRHI		0x14
+#define CH_DESADDR		0x18
+#define CH_DESADDRHI		0x1c
+#define CH_XSIZE		0x20
+#define CH_XSIZEHI		0x24
+#define CH_SRCTRANSCFG		0x28
+#define CH_DESTRANSCFG		0x2c
+#define CH_CFG_MAXBURSTLEN	GENMASK(19, 16)
+#define CH_CFG_PRIVATTR		BIT(11)
+#define CH_CFG_SHAREATTR	GENMASK(9, 8)
+#define CH_CFG_MEMATTR		GENMASK(7, 0)
+
+#define TRANSCFG_DEVICE					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_OSH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_DEVICE)
+#define TRANSCFG_NC					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_OSH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_NC)
+#define TRANSCFG_WB					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_ISH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_WB)
+
+#define CH_XADDRINC		0x30
+#define CH_XY_DES		GENMASK(31, 16)
+#define CH_XY_SRC		GENMASK(15, 0)
+
+#define CH_FILLVAL		0x38
+#define CH_SRCTRIGINCFG		0x4c
+#define CH_DESTRIGINCFG		0x50
+#define CH_LINKATTR		0x70
+#define CH_LINK_SHAREATTR	GENMASK(9, 8)
+#define CH_LINK_MEMATTR		GENMASK(7, 0)
+
+#define CH_AUTOCFG		0x74
+#define CH_LINKADDR		0x78
+#define CH_LINKADDR_EN		BIT(0)
+
+#define CH_LINKADDRHI		0x7c
+#define CH_ERRINFO		0x90
+#define CH_ERRINFO_AXIRDPOISERR BIT(18)
+#define CH_ERRINFO_AXIWRRESPERR BIT(17)
+#define CH_ERRINFO_AXIRDRESPERR BIT(16)
+
+#define CH_BUILDCFG0		0xf8
+#define CH_CFG_INC_WIDTH	GENMASK(29, 26)
+#define CH_CFG_DATA_WIDTH	GENMASK(24, 22)
+#define CH_CFG_DATA_BUF_SIZE	GENMASK(7, 0)
+
+#define CH_BUILDCFG1		0xfc
+#define CH_CFG_HAS_CMDLINK	BIT(8)
+#define CH_CFG_HAS_TRIGSEL	BIT(7)
+#define CH_CFG_HAS_TRIGIN	BIT(5)
+#define CH_CFG_HAS_WRAP		BIT(1)
+
+
+#define LINK_REGCLEAR		BIT(0)
+#define LINK_INTREN		BIT(2)
+#define LINK_CTRL		BIT(3)
+#define LINK_SRCADDR		BIT(4)
+#define LINK_SRCADDRHI		BIT(5)
+#define LINK_DESADDR		BIT(6)
+#define LINK_DESADDRHI		BIT(7)
+#define LINK_XSIZE		BIT(8)
+#define LINK_XSIZEHI		BIT(9)
+#define LINK_SRCTRANSCFG	BIT(10)
+#define LINK_DESTRANSCFG	BIT(11)
+#define LINK_XADDRINC		BIT(12)
+#define LINK_FILLVAL		BIT(14)
+#define LINK_SRCTRIGINCFG	BIT(19)
+#define LINK_DESTRIGINCFG	BIT(20)
+#define LINK_AUTOCFG		BIT(29)
+#define LINK_LINKADDR		BIT(30)
+#define LINK_LINKADDRHI		BIT(31)
+
+
+enum ch_ctrl_donetype {
+	CH_CTRL_DONETYPE_NONE = 0,
+	CH_CTRL_DONETYPE_CMD = 1,
+	CH_CTRL_DONETYPE_CYCLE = 3
+};
+
+enum ch_ctrl_xtype {
+	CH_CTRL_XTYPE_DISABLE = 0,
+	CH_CTRL_XTYPE_CONTINUE = 1,
+	CH_CTRL_XTYPE_WRAP = 2,
+	CH_CTRL_XTYPE_FILL = 3
+};
+
+enum ch_cfg_shareattr {
+	SHAREATTR_NSH = 0,
+	SHAREATTR_OSH = 2,
+	SHAREATTR_ISH = 3
+};
+
+enum ch_cfg_memattr {
+	MEMATTR_DEVICE = 0x00,
+	MEMATTR_NC = 0x44,
+	MEMATTR_WB = 0xff
+};
+
+struct d350_desc {
+	struct virt_dma_desc vd;
+	u32 command[16];
+	u16 xsize;
+	u16 xsizehi;
+	u8 tsz;
+};
+
+struct d350_chan {
+	struct virt_dma_chan vc;
+	struct d350_desc *desc;
+	void __iomem *base;
+	int irq;
+	enum dma_status status;
+	dma_cookie_t cookie;
+	u32 residue;
+	u8 tsz;
+	bool has_trig;
+	bool has_wrap;
+	bool coherent;
+};
+
+struct d350 {
+	struct dma_device dma;
+	int nchan;
+	int nreq;
+	struct d350_chan channels[] __counted_by(nchan);
+};
+
+static inline struct d350_chan *to_d350_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct d350_chan, vc.chan);
+}
+
+static inline struct d350_desc *to_d350_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct d350_desc, vd);
+}
+
+static void d350_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_d350_desc(vd));
+}
+
+static struct dma_async_tx_descriptor *d350_prep_memcpy(struct dma_chan *chan,
+		dma_addr_t dest, dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct d350_desc *desc;
+	u32 *cmd;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->tsz = __ffs(len | dest | src | (1 << dch->tsz));
+	desc->xsize = lower_16_bits(len >> desc->tsz);
+	desc->xsizehi = upper_16_bits(len >> desc->tsz);
+
+	cmd = desc->command;
+	cmd[0] = LINK_CTRL | LINK_SRCADDR | LINK_SRCADDRHI | LINK_DESADDR |
+		 LINK_DESADDRHI | LINK_XSIZE | LINK_XSIZEHI | LINK_SRCTRANSCFG |
+		 LINK_DESTRANSCFG | LINK_XADDRINC | LINK_LINKADDR;
+
+	cmd[1] = FIELD_PREP(CH_CTRL_TRANSIZE, desc->tsz) |
+		 FIELD_PREP(CH_CTRL_XTYPE, CH_CTRL_XTYPE_CONTINUE) |
+		 FIELD_PREP(CH_CTRL_DONETYPE, CH_CTRL_DONETYPE_CMD);
+
+	cmd[2] = lower_32_bits(src);
+	cmd[3] = upper_32_bits(src);
+	cmd[4] = lower_32_bits(dest);
+	cmd[5] = upper_32_bits(dest);
+	cmd[6] = FIELD_PREP(CH_XY_SRC, desc->xsize) | FIELD_PREP(CH_XY_DES, desc->xsize);
+	cmd[7] = FIELD_PREP(CH_XY_SRC, desc->xsizehi) | FIELD_PREP(CH_XY_DES, desc->xsizehi);
+	cmd[8] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[9] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[10] = FIELD_PREP(CH_XY_SRC, 1) | FIELD_PREP(CH_XY_DES, 1);
+	cmd[11] = 0;
+
+	return vchan_tx_prep(&dch->vc, &desc->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *d350_prep_memset(struct dma_chan *chan,
+		dma_addr_t dest, int value, size_t len, unsigned long flags)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct d350_desc *desc;
+	u32 *cmd;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->tsz = __ffs(len | dest | (1 << dch->tsz));
+	desc->xsize = lower_16_bits(len >> desc->tsz);
+	desc->xsizehi = upper_16_bits(len >> desc->tsz);
+
+	cmd = desc->command;
+	cmd[0] = LINK_CTRL | LINK_DESADDR | LINK_DESADDRHI |
+		 LINK_XSIZE | LINK_XSIZEHI | LINK_DESTRANSCFG |
+		 LINK_XADDRINC | LINK_FILLVAL | LINK_LINKADDR;
+
+	cmd[1] = FIELD_PREP(CH_CTRL_TRANSIZE, desc->tsz) |
+		 FIELD_PREP(CH_CTRL_XTYPE, CH_CTRL_XTYPE_FILL) |
+		 FIELD_PREP(CH_CTRL_DONETYPE, CH_CTRL_DONETYPE_CMD);
+
+	cmd[2] = lower_32_bits(dest);
+	cmd[3] = upper_32_bits(dest);
+	cmd[4] = FIELD_PREP(CH_XY_DES, desc->xsize);
+	cmd[5] = FIELD_PREP(CH_XY_DES, desc->xsizehi);
+	cmd[6] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[7] = FIELD_PREP(CH_XY_DES, 1);
+	cmd[8] = (u8)value * 0x01010101;
+	cmd[9] = 0;
+
+	return vchan_tx_prep(&dch->vc, &desc->vd, flags);
+}
+
+static int d350_pause(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (dch->status == DMA_IN_PROGRESS) {
+		writel_relaxed(CH_CMD_PAUSE, dch->base + CH_CMD);
+		dch->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static int d350_resume(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (dch->status == DMA_PAUSED) {
+		writel_relaxed(CH_CMD_RESUME, dch->base + CH_CMD);
+		dch->status = DMA_IN_PROGRESS;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static u32 d350_get_residue(struct d350_chan *dch)
+{
+	u32 res, xsize, xsizehi, hi_new;
+	int retries = 3; /* 1st time unlucky, 2nd improbable, 3rd just broken */
+
+	hi_new = readl_relaxed(dch->base + CH_XSIZEHI);
+	do {
+		xsizehi = hi_new;
+		xsize = readl_relaxed(dch->base + CH_XSIZE);
+		hi_new = readl_relaxed(dch->base + CH_XSIZEHI);
+	} while (xsizehi != hi_new && --retries);
+
+	res = FIELD_GET(CH_XY_DES, xsize);
+	res |= FIELD_GET(CH_XY_DES, xsizehi) << 16;
+
+	return res << dch->desc->tsz;
+}
+
+static int d350_terminate_all(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	writel_relaxed(CH_CMD_STOP, dch->base + CH_CMD);
+	if (dch->desc) {
+		if (dch->status != DMA_ERROR)
+			vchan_terminate_vdesc(&dch->desc->vd);
+		dch->desc = NULL;
+		dch->status = DMA_COMPLETE;
+	}
+	vchan_get_all_descriptors(&dch->vc, &list);
+	list_splice_tail(&list, &dch->vc.desc_terminated);
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static void d350_synchronize(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+
+	vchan_synchronize(&dch->vc);
+}
+
+static u32 d350_desc_bytes(struct d350_desc *desc)
+{
+	return ((u32)desc->xsizehi << 16 | desc->xsize) << desc->tsz;
+}
+
+static enum dma_status d350_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+				      struct dma_tx_state *state)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status status;
+	unsigned long flags;
+	u32 residue = 0;
+
+	status = dma_cookie_status(chan, cookie, state);
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (cookie == dch->cookie) {
+		status = dch->status;
+		if (status == DMA_IN_PROGRESS || status == DMA_PAUSED)
+			dch->residue = d350_get_residue(dch);
+		residue = dch->residue;
+	} else if ((vd = vchan_find_desc(&dch->vc, cookie))) {
+		residue = d350_desc_bytes(to_d350_desc(vd));
+	} else if (status == DMA_IN_PROGRESS) {
+		/* Somebody else terminated it? */
+		status = DMA_ERROR;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	dma_set_residue(state, residue);
+	return status;
+}
+
+static void d350_start_next(struct d350_chan *dch)
+{
+	u32 hdr, *reg;
+
+	dch->desc = to_d350_desc(vchan_next_desc(&dch->vc));
+	if (!dch->desc)
+		return;
+
+	list_del(&dch->desc->vd.node);
+	dch->status = DMA_IN_PROGRESS;
+	dch->cookie = dch->desc->vd.tx.cookie;
+	dch->residue = d350_desc_bytes(dch->desc);
+
+	hdr = dch->desc->command[0];
+	reg = &dch->desc->command[1];
+
+	if (hdr & LINK_INTREN)
+		writel_relaxed(*reg++, dch->base + CH_INTREN);
+	if (hdr & LINK_CTRL)
+		writel_relaxed(*reg++, dch->base + CH_CTRL);
+	if (hdr & LINK_SRCADDR)
+		writel_relaxed(*reg++, dch->base + CH_SRCADDR);
+	if (hdr & LINK_SRCADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_SRCADDRHI);
+	if (hdr & LINK_DESADDR)
+		writel_relaxed(*reg++, dch->base + CH_DESADDR);
+	if (hdr & LINK_DESADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_DESADDRHI);
+	if (hdr & LINK_XSIZE)
+		writel_relaxed(*reg++, dch->base + CH_XSIZE);
+	if (hdr & LINK_XSIZEHI)
+		writel_relaxed(*reg++, dch->base + CH_XSIZEHI);
+	if (hdr & LINK_SRCTRANSCFG)
+		writel_relaxed(*reg++, dch->base + CH_SRCTRANSCFG);
+	if (hdr & LINK_DESTRANSCFG)
+		writel_relaxed(*reg++, dch->base + CH_DESTRANSCFG);
+	if (hdr & LINK_XADDRINC)
+		writel_relaxed(*reg++, dch->base + CH_XADDRINC);
+	if (hdr & LINK_FILLVAL)
+		writel_relaxed(*reg++, dch->base + CH_FILLVAL);
+	if (hdr & LINK_SRCTRIGINCFG)
+		writel_relaxed(*reg++, dch->base + CH_SRCTRIGINCFG);
+	if (hdr & LINK_DESTRIGINCFG)
+		writel_relaxed(*reg++, dch->base + CH_DESTRIGINCFG);
+	if (hdr & LINK_AUTOCFG)
+		writel_relaxed(*reg++, dch->base + CH_AUTOCFG);
+	if (hdr & LINK_LINKADDR)
+		writel_relaxed(*reg++, dch->base + CH_LINKADDR);
+	if (hdr & LINK_LINKADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_LINKADDRHI);
+
+	writel(CH_CMD_ENABLE, dch->base + CH_CMD);
+}
+
+static void d350_issue_pending(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (vchan_issue_pending(&dch->vc) && !dch->desc)
+		d350_start_next(dch);
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+}
+
+static irqreturn_t d350_irq(int irq, void *data)
+{
+	struct d350_chan *dch = data;
+	struct device *dev = dch->vc.chan.device->dev;
+	struct virt_dma_desc *vd = &dch->desc->vd;
+	u32 ch_status;
+
+	ch_status = readl(dch->base + CH_STATUS);
+	if (!ch_status)
+		return IRQ_NONE;
+
+	if (ch_status & CH_STAT_INTR_ERR) {
+		u32 errinfo = readl_relaxed(dch->base + CH_ERRINFO);
+
+		if (errinfo & (CH_ERRINFO_AXIRDPOISERR | CH_ERRINFO_AXIRDRESPERR))
+			vd->tx_result.result = DMA_TRANS_READ_FAILED;
+		else if (errinfo & CH_ERRINFO_AXIWRRESPERR)
+			vd->tx_result.result = DMA_TRANS_WRITE_FAILED;
+		else
+			vd->tx_result.result = DMA_TRANS_ABORTED;
+
+		vd->tx_result.residue = d350_get_residue(dch);
+	} else if (!(ch_status & CH_STAT_INTR_DONE)) {
+		dev_warn(dev, "Unexpected IRQ source? 0x%08x\n", ch_status);
+	}
+	writel_relaxed(ch_status, dch->base + CH_STATUS);
+
+	spin_lock(&dch->vc.lock);
+	vchan_cookie_complete(vd);
+	if (ch_status & CH_STAT_INTR_DONE) {
+		dch->status = DMA_COMPLETE;
+		dch->residue = 0;
+		d350_start_next(dch);
+	} else {
+		dch->status = DMA_ERROR;
+		dch->residue = vd->tx_result.residue;
+	}
+	spin_unlock(&dch->vc.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int d350_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	int ret = request_irq(dch->irq, d350_irq, IRQF_SHARED,
+			      dev_name(&dch->vc.chan.dev->device), dch);
+	if (!ret)
+		writel_relaxed(CH_INTREN_DONE | CH_INTREN_ERR, dch->base + CH_INTREN);
+
+	return ret;
+}
+
+static void d350_free_chan_resources(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+
+	writel_relaxed(0, dch->base + CH_INTREN);
+	free_irq(dch->irq, dch);
+	vchan_free_chan_resources(&dch->vc);
+}
+
+static int d350_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct d350 *dmac;
+	void __iomem *base;
+	u32 reg;
+	int ret, nchan, dw, aw, r, p;
+	bool coherent, memset;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	reg = readl_relaxed(base + DMAINFO + IIDR);
+	r = FIELD_GET(IIDR_VARIANT, reg);
+	p = FIELD_GET(IIDR_REVISION, reg);
+	if (FIELD_GET(IIDR_IMPLEMENTER, reg) != IMPLEMENTER_ARM ||
+	    FIELD_GET(IIDR_PRODUCTID, reg) != PRODUCTID_DMA350)
+		return dev_err_probe(dev, -ENODEV, "Not a DMA-350!");
+
+	reg = readl_relaxed(base + DMAINFO + DMA_BUILDCFG0);
+	nchan = FIELD_GET(DMA_CFG_NUM_CHANNELS, reg) + 1;
+	dw = 1 << FIELD_GET(DMA_CFG_DATA_WIDTH, reg);
+	aw = FIELD_GET(DMA_CFG_ADDR_WIDTH, reg) + 1;
+
+	dma_set_mask_and_coherent(dev, DMA_BIT_MASK(aw));
+	coherent = device_get_dma_attr(dev) == DEV_DMA_COHERENT;
+
+	dmac = devm_kzalloc(dev, struct_size(dmac, channels, nchan), GFP_KERNEL);
+	if (!dmac)
+		return -ENOMEM;
+
+	dmac->nchan = nchan;
+
+	reg = readl_relaxed(base + DMAINFO + DMA_BUILDCFG1);
+	dmac->nreq = FIELD_GET(DMA_CFG_NUM_TRIGGER_IN, reg);
+
+	dev_dbg(dev, "DMA-350 r%dp%d with %d channels, %d requests\n", r, p, dmac->nchan, dmac->nreq);
+
+	dmac->dma.dev = dev;
+	for (int i = min(dw, 16); i > 0; i /= 2) {
+		dmac->dma.src_addr_widths |= BIT(i);
+		dmac->dma.dst_addr_widths |= BIT(i);
+	}
+	dmac->dma.directions = BIT(DMA_MEM_TO_MEM);
+	dmac->dma.descriptor_reuse = true;
+	dmac->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	dmac->dma.device_alloc_chan_resources = d350_alloc_chan_resources;
+	dmac->dma.device_free_chan_resources = d350_free_chan_resources;
+	dma_cap_set(DMA_MEMCPY, dmac->dma.cap_mask);
+	dmac->dma.device_prep_dma_memcpy = d350_prep_memcpy;
+	dmac->dma.device_pause = d350_pause;
+	dmac->dma.device_resume = d350_resume;
+	dmac->dma.device_terminate_all = d350_terminate_all;
+	dmac->dma.device_synchronize = d350_synchronize;
+	dmac->dma.device_tx_status = d350_tx_status;
+	dmac->dma.device_issue_pending = d350_issue_pending;
+	INIT_LIST_HEAD(&dmac->dma.channels);
+
+	/* Would be nice to have per-channel caps for this... */
+	memset = true;
+	for (int i = 0; i < nchan; i++) {
+		struct d350_chan *dch = &dmac->channels[i];
+
+		dch->base = base + DMACH(i);
+		writel_relaxed(CH_CMD_CLEAR, dch->base + CH_CMD);
+
+		reg = readl_relaxed(dch->base + CH_BUILDCFG1);
+		if (!(FIELD_GET(CH_CFG_HAS_CMDLINK, reg))) {
+			dev_warn(dev, "No command link support on channel %d\n", i);
+			continue;
+		}
+		dch->irq = platform_get_irq(pdev, i);
+		if (dch->irq < 0)
+			return dev_err_probe(dev, dch->irq,
+					     "Failed to get IRQ for channel %d\n", i);
+
+		dch->has_wrap = FIELD_GET(CH_CFG_HAS_WRAP, reg);
+		dch->has_trig = FIELD_GET(CH_CFG_HAS_TRIGIN, reg) &
+				FIELD_GET(CH_CFG_HAS_TRIGSEL, reg);
+
+		/* Fill is a special case of Wrap */
+		memset &= dch->has_wrap;
+
+		reg = readl_relaxed(dch->base + CH_BUILDCFG0);
+		dch->tsz = FIELD_GET(CH_CFG_DATA_WIDTH, reg);
+
+		reg = FIELD_PREP(CH_LINK_SHAREATTR, coherent ? SHAREATTR_ISH : SHAREATTR_OSH);
+		reg |= FIELD_PREP(CH_LINK_MEMATTR, coherent ? MEMATTR_WB : MEMATTR_NC);
+		writel_relaxed(reg, dch->base + CH_LINKATTR);
+
+		dch->vc.desc_free = d350_desc_free;
+		vchan_init(&dch->vc, &dmac->dma);
+	}
+
+	if (memset) {
+		dma_cap_set(DMA_MEMSET, dmac->dma.cap_mask);
+		dmac->dma.device_prep_dma_memset = d350_prep_memset;
+	}
+
+	platform_set_drvdata(pdev, dmac);
+
+	ret = dma_async_device_register(&dmac->dma);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register DMA device\n");
+
+	return 0;
+}
+
+static void d350_remove(struct platform_device *pdev)
+{
+	struct d350 *dmac = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&dmac->dma);
+}
+
+static const struct of_device_id d350_of_match[] __maybe_unused = {
+	{ .compatible = "arm,dma-350" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, d350_of_match);
+
+static struct platform_driver d350_driver = {
+	.driver = {
+		.name = "arm-dma350",
+		.of_match_table = of_match_ptr(d350_of_match),
+	},
+	.probe = d350_probe,
+	.remove = d350_remove,
+};
+module_platform_driver(d350_driver);
+
+MODULE_AUTHOR("Robin Murphy <robin.murphy@arm.com>");
+MODULE_DESCRIPTION("Arm DMA-350 driver");
+MODULE_LICENSE("GPL v2");

drivers/dma/at_xdmac.c

@@ -2033,10 +2033,8 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan)
 		 * at_xdmac_start_xfer() for this descriptor. Now it's time
 		 * to release it.
 		 */
-		if (desc->active_xfer) {
+		if (desc->active_xfer)
-			pm_runtime_put_autosuspend(atxdmac->dev);
+			pm_runtime_put_noidle(atxdmac->dev);
-			pm_runtime_mark_last_busy(atxdmac->dev);
-		}
 	}
 
 	clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);

drivers/dma/dw-edma/dw-edma-pcie.c

@@ -136,7 +136,8 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	map = FIELD_GET(DW_PCIE_VSEC_DMA_MAP, val);
 	if (map != EDMA_MF_EDMA_LEGACY &&
 	    map != EDMA_MF_EDMA_UNROLL &&
-	    map != EDMA_MF_HDMA_COMPAT)
+	    map != EDMA_MF_HDMA_COMPAT &&
+	    map != EDMA_MF_HDMA_NATIVE)
 		return;
 
 	pdata->mf = map;
@@ -291,6 +292,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", chip->mf);
 	else if (chip->mf == EDMA_MF_HDMA_COMPAT)
 		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_NATIVE)
+		pci_dbg(pdev, "Version:\tHDMA Native (0x%x)\n", chip->mf);
 	else
 		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf);
 

drivers/dma/fsl-edma-common.c

@@ -95,7 +95,7 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
 	}
 
 	val = edma_readl_chreg(fsl_chan, ch_csr);
-	val |= EDMA_V3_CH_CSR_ERQ;
+	val |= EDMA_V3_CH_CSR_ERQ | EDMA_V3_CH_CSR_EEI;
 	edma_writel_chreg(fsl_chan, val, ch_csr);
 }
 
@@ -821,7 +821,7 @@ 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;
+	int ret = 0;
 
 	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK)
 		clk_prepare_enable(fsl_chan->clk);
@@ -831,17 +831,29 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 				sizeof(struct fsl_edma_hw_tcd64) : sizeof(struct fsl_edma_hw_tcd),
 				32, 0);
 
-	if (fsl_chan->txirq) {
+	if (fsl_chan->txirq)
 		ret = request_irq(fsl_chan->txirq, fsl_chan->irq_handler, IRQF_SHARED,
 				 fsl_chan->chan_name, fsl_chan);
 
-		if (ret) {
+	if (ret)
-			dma_pool_destroy(fsl_chan->tcd_pool);
+		goto err_txirq;
-			return ret;
+
-		}
+	if (fsl_chan->errirq > 0)
-	}
+		ret = request_irq(fsl_chan->errirq, fsl_chan->errirq_handler, IRQF_SHARED,
+				  fsl_chan->errirq_name, fsl_chan);
+
+	if (ret)
+		goto err_errirq;
 
 	return 0;
+
+err_errirq:
+	if (fsl_chan->txirq)
+		free_irq(fsl_chan->txirq, fsl_chan);
+err_txirq:
+	dma_pool_destroy(fsl_chan->tcd_pool);
+
+	return ret;
 }
 
 void fsl_edma_free_chan_resources(struct dma_chan *chan)
@@ -862,6 +874,8 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 
 	if (fsl_chan->txirq)
 		free_irq(fsl_chan->txirq, fsl_chan);
+	if (fsl_chan->errirq)
+		free_irq(fsl_chan->errirq, fsl_chan);
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 	dma_pool_destroy(fsl_chan->tcd_pool);

drivers/dma/fsl-edma-common.h

@@ -71,6 +71,18 @@
 #define EDMA_V3_CH_ES_ERR          BIT(31)
 #define EDMA_V3_MP_ES_VLD          BIT(31)
 
+#define EDMA_V3_CH_ERR_DBE	BIT(0)
+#define EDMA_V3_CH_ERR_SBE	BIT(1)
+#define EDMA_V3_CH_ERR_SGE	BIT(2)
+#define EDMA_V3_CH_ERR_NCE	BIT(3)
+#define EDMA_V3_CH_ERR_DOE	BIT(4)
+#define EDMA_V3_CH_ERR_DAE	BIT(5)
+#define EDMA_V3_CH_ERR_SOE	BIT(6)
+#define EDMA_V3_CH_ERR_SAE	BIT(7)
+#define EDMA_V3_CH_ERR_ECX	BIT(8)
+#define EDMA_V3_CH_ERR_UCE	BIT(9)
+#define EDMA_V3_CH_ERR		BIT(31)
+
 enum fsl_edma_pm_state {
 	RUNNING = 0,
 	SUSPENDED,
@@ -162,6 +174,7 @@ struct fsl_edma_chan {
 	u32				dma_dev_size;
 	enum dma_data_direction		dma_dir;
 	char				chan_name[32];
+	char				errirq_name[36];
 	void __iomem			*tcd;
 	void __iomem			*mux_addr;
 	u32				real_count;
@@ -174,7 +187,9 @@ struct fsl_edma_chan {
 	int                             priority;
 	int				hw_chanid;
 	int				txirq;
+	int				errirq;
 	irqreturn_t			(*irq_handler)(int irq, void *dev_id);
+	irqreturn_t			(*errirq_handler)(int irq, void *dev_id);
 	bool				is_rxchan;
 	bool				is_remote;
 	bool				is_multi_fifo;
@@ -208,6 +223,9 @@ struct fsl_edma_desc {
 /* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */
 #define FSL_EDMA_DRV_CLEAR_DONE_E_LINK	BIT(14)
 #define FSL_EDMA_DRV_TCD64		BIT(15)
+/* All channel ERR IRQ share one IRQ line */
+#define FSL_EDMA_DRV_ERRIRQ_SHARE       BIT(16)
+
 
 #define FSL_EDMA_DRV_EDMA3	(FSL_EDMA_DRV_SPLIT_REG |	\
 				 FSL_EDMA_DRV_BUS_8BYTE |	\

drivers/dma/fsl-edma-main.c

@@ -50,6 +50,83 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void fsl_edma3_err_check(struct fsl_edma_chan *fsl_chan)
+{
+	unsigned int ch_err;
+	u32 val;
+
+	scoped_guard(spinlock, &fsl_chan->vchan.lock) {
+		ch_err = edma_readl_chreg(fsl_chan, ch_es);
+		if (!(ch_err & EDMA_V3_CH_ERR))
+			return;
+
+		edma_writel_chreg(fsl_chan, EDMA_V3_CH_ERR, ch_es);
+		val = edma_readl_chreg(fsl_chan, ch_csr);
+		val &= ~EDMA_V3_CH_CSR_ERQ;
+		edma_writel_chreg(fsl_chan, val, ch_csr);
+	}
+
+	/* Ignore this interrupt since channel has been disabled already */
+	if (!fsl_chan->edesc)
+		return;
+
+	if (ch_err & EDMA_V3_CH_ERR_DBE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Bus Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SBE)
+		dev_err(&fsl_chan->pdev->dev, "Source Bus Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SGE)
+		dev_err(&fsl_chan->pdev->dev, "Scatter/Gather Configuration Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_NCE)
+		dev_err(&fsl_chan->pdev->dev, "NBYTES/CITER Configuration Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_DOE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Offset Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_DAE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Address Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SOE)
+		dev_err(&fsl_chan->pdev->dev, "Source Offset Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SAE)
+		dev_err(&fsl_chan->pdev->dev, "Source Address Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_ECX)
+		dev_err(&fsl_chan->pdev->dev, "Transfer Canceled interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_UCE)
+		dev_err(&fsl_chan->pdev->dev, "Uncorrectable TCD error during channel execution interrupt.\n");
+
+	fsl_chan->status = DMA_ERROR;
+}
+
+static irqreturn_t fsl_edma3_err_handler_per_chan(int irq, void *dev_id)
+{
+	struct fsl_edma_chan *fsl_chan = dev_id;
+
+	fsl_edma3_err_check(fsl_chan);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_edma3_err_handler_shared(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	unsigned int ch;
+
+	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
+		if (fsl_edma->chan_masked & BIT(ch))
+			continue;
+
+		fsl_edma3_err_check(&fsl_edma->chans[ch]);
+	}
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_chan *fsl_chan = dev_id;
@@ -309,7 +386,8 @@ 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 i;
+	char *errirq_name;
+	int i, ret;
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 
@@ -324,6 +402,27 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
 			return  -EINVAL;
 
 		fsl_chan->irq_handler = fsl_edma3_tx_handler;
+
+		if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_ERRIRQ_SHARE)) {
+			fsl_chan->errirq = fsl_chan->txirq;
+			fsl_chan->errirq_handler = fsl_edma3_err_handler_per_chan;
+		}
+	}
+
+	/* All channel err use one irq number */
+	if (fsl_edma->drvdata->flags & FSL_EDMA_DRV_ERRIRQ_SHARE) {
+		/* last one is error irq */
+		fsl_edma->errirq = platform_get_irq_optional(pdev, fsl_edma->n_chans);
+		if (fsl_edma->errirq < 0)
+			return 0; /* dts miss err irq, treat as no err irq case */
+
+		errirq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-err",
+					     dev_name(&pdev->dev));
+
+		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, fsl_edma3_err_handler_shared,
+				       0, errirq_name, fsl_edma);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "Can't register eDMA err IRQ.\n");
 	}
 
 	return 0;
@@ -464,7 +563,8 @@ static struct fsl_edma_drvdata imx7ulp_data = {
 };
 
 static struct fsl_edma_drvdata imx8qm_data = {
-	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE,
+	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE
+		 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x10000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
@@ -481,14 +581,15 @@ static struct fsl_edma_drvdata imx8ulp_data = {
 };
 
 static struct fsl_edma_drvdata imx93_data3 = {
-	.flags = FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3,
+	.flags = FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x10000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
 };
 
 static struct fsl_edma_drvdata imx93_data4 = {
-	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4,
+	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4
+		 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
 	.mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux),
@@ -498,7 +599,7 @@ static struct fsl_edma_drvdata imx93_data4 = {
 
 static struct fsl_edma_drvdata imx95_data5 = {
 	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4 |
-		 FSL_EDMA_DRV_TCD64,
+		 FSL_EDMA_DRV_TCD64 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
 	.mux_off = 0x200,
@@ -700,6 +801,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		snprintf(fsl_chan->chan_name, sizeof(fsl_chan->chan_name), "%s-CH%02d",
 							   dev_name(&pdev->dev), i);
 
+		snprintf(fsl_chan->errirq_name, sizeof(fsl_chan->errirq_name),
+			 "%s-CH%02d-err", dev_name(&pdev->dev), i);
+
 		fsl_chan->edma = fsl_edma;
 		fsl_chan->pm_state = RUNNING;
 		fsl_chan->srcid = 0;

drivers/dma/fsldma.c

@@ -1226,6 +1226,8 @@ static int fsldma_of_probe(struct platform_device *op)
 
 	fdev->dev = &op->dev;
 	INIT_LIST_HEAD(&fdev->common.channels);
+	/* The DMA address bits supported for this device. */
+	fdev->addr_bits = (long)device_get_match_data(fdev->dev);
 
 	/* ioremap the registers for use */
 	fdev->regs = of_iomap(op->dev.of_node, 0);
@@ -1254,7 +1256,7 @@ static int fsldma_of_probe(struct platform_device *op)
 	fdev->common.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	fdev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
-	dma_set_mask(&(op->dev), DMA_BIT_MASK(36));
+	dma_set_mask(&(op->dev), DMA_BIT_MASK(fdev->addr_bits));
 
 	platform_set_drvdata(op, fdev);
 
@@ -1387,10 +1389,20 @@ static const struct dev_pm_ops fsldma_pm_ops = {
 };
 #endif
 
+/* The .data field is used for dma-bit-mask. */
 static const struct of_device_id fsldma_of_ids[] = {
-	{ .compatible = "fsl,elo3-dma", },
+	{
-	{ .compatible = "fsl,eloplus-dma", },
+		.compatible = "fsl,elo3-dma",
-	{ .compatible = "fsl,elo-dma", },
+		.data = (void *)40,
+	},
+	{
+		.compatible = "fsl,eloplus-dma",
+		.data = (void *)36,
+	},
+	{
+		.compatible = "fsl,elo-dma",
+		.data = (void *)32,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, fsldma_of_ids);

drivers/dma/fsldma.h

@@ -124,6 +124,7 @@ struct fsldma_device {
 	struct fsldma_chan *chan[FSL_DMA_MAX_CHANS_PER_DEVICE];
 	u32 feature;		/* The same as DMA channels */
 	int irq;		/* Channel IRQ */
+	int addr_bits;		/* DMA addressing bits supported */
 };
 
 /* Define macros for fsldma_chan->feature property */

drivers/dma/idxd/cdev.c

@@ -349,7 +349,9 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 			set_bit(h, evl->bmap);
 		h = (h + 1) % size;
 	}
-	drain_workqueue(wq->wq);
+	if (wq->wq)
+		drain_workqueue(wq->wq);
+
 	mutex_unlock(&evl->lock);
 }
 
@@ -442,10 +444,12 @@ static int idxd_submit_user_descriptor(struct idxd_user_context *ctx,
 	 * DSA devices are capable of indirect ("batch") command submission.
 	 * On devices where direct user submissions are not safe, we cannot
 	 * allow this since there is no good way for us to verify these
-	 * indirect commands.
+	 * indirect commands. Narrow the restriction of operations with the
+	 * BATCH opcode to only DSA version 1 devices.
 	 */
 	if (is_dsa_dev(idxd_dev) && descriptor.opcode == DSA_OPCODE_BATCH &&
-		!wq->idxd->user_submission_safe)
+	    wq->idxd->hw.version == DEVICE_VERSION_1 &&
+	    !wq->idxd->user_submission_safe)
 		return -EINVAL;
 	/*
 	 * As per the programming specification, the completion address must be

drivers/dma/idxd/idxd.h

@@ -19,7 +19,6 @@
 
 #define IDXD_DRIVER_VERSION	"1.00"
 
-extern struct kmem_cache *idxd_desc_pool;
 extern bool tc_override;
 
 struct idxd_wq;
@@ -171,7 +170,6 @@ struct idxd_cdev {
 
 #define DRIVER_NAME_SIZE		128
 
-#define IDXD_ALLOCATED_BATCH_SIZE	128U
 #define WQ_NAME_SIZE   1024
 #define WQ_TYPE_SIZE   10
 

drivers/dma/idxd/sysfs.c

@@ -1208,9 +1208,11 @@ static ssize_t op_cap_show_common(struct device *dev, char *buf, unsigned long *
 
 		/* On systems where direct user submissions are not safe, we need to clear out
 		 * the BATCH capability from the capability mask in sysfs since we cannot support
-		 * that command on such systems.
+		 * that command on such systems. Narrow the restriction of operations with the
+		 * BATCH opcode to only DSA version 1 devices.
 		 */
-		if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe)
+		if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe &&
+		    confdev_to_idxd(dev)->hw.version == DEVICE_VERSION_1)
 			clear_bit(DSA_OPCODE_BATCH % 64, &val);
 
 		pos += sysfs_emit_at(buf, pos, "%*pb", 64, &val);

drivers/dma/sh/rz-dmac.c

@@ -14,6 +14,7 @@
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/irqchip/irq-renesas-rzv2h.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -89,8 +90,14 @@ struct rz_dmac_chan {
 
 #define to_rz_dmac_chan(c)	container_of(c, struct rz_dmac_chan, vc.chan)
 
+struct rz_dmac_icu {
+	struct platform_device *pdev;
+	u8 dmac_index;
+};
+
 struct rz_dmac {
 	struct dma_device engine;
+	struct rz_dmac_icu icu;
 	struct device *dev;
 	struct reset_control *rstc;
 	void __iomem *base;
@@ -99,6 +106,8 @@ struct rz_dmac {
 	unsigned int n_channels;
 	struct rz_dmac_chan *channels;
 
+	bool has_icu;
+
 	DECLARE_BITMAP(modules, 1024);
 };
 
@@ -167,6 +176,9 @@ struct rz_dmac {
 #define RZ_DMAC_MAX_CHANNELS		16
 #define DMAC_NR_LMDESC			64
 
+/* RZ/V2H ICU related */
+#define RZV2H_MAX_DMAC_INDEX		4
+
 /*
  * -----------------------------------------------------------------------------
  * Device access
@@ -324,7 +336,13 @@ static void rz_dmac_prepare_desc_for_memcpy(struct rz_dmac_chan *channel)
 	lmdesc->chext = 0;
 	lmdesc->header = HEADER_LV;
 
-	rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index,
+					   RZV2H_ICU_DMAC_REQ_NO_DEFAULT);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	}
 
 	channel->chcfg = chcfg;
 	channel->chctrl = CHCTRL_STG | CHCTRL_SETEN;
@@ -375,7 +393,13 @@ static void rz_dmac_prepare_descs_for_slave_sg(struct rz_dmac_chan *channel)
 
 	channel->lmdesc.tail = lmdesc;
 
-	rz_dmac_set_dmars_register(dmac, channel->index, channel->mid_rid);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index, channel->mid_rid);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, channel->mid_rid);
+	}
+
 	channel->chctrl = CHCTRL_SETEN;
 }
 
@@ -647,7 +671,13 @@ static void rz_dmac_device_synchronize(struct dma_chan *chan)
 	if (ret < 0)
 		dev_warn(dmac->dev, "DMA Timeout");
 
-	rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index,
+					   RZV2H_ICU_DMAC_REQ_NO_DEFAULT);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	}
 }
 
 /*
@@ -748,7 +778,8 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	return dma_request_channel(mask, rz_dmac_chan_filter, dma_spec);
+	return __dma_request_channel(&mask, rz_dmac_chan_filter, dma_spec,
+				     ofdma->of_node);
 }
 
 /*
@@ -823,6 +854,38 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 	return 0;
 }
 
+static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac)
+{
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	uint32_t dmac_index;
+	int ret;
+
+	ret = of_parse_phandle_with_fixed_args(np, "renesas,icu", 1, 0, &args);
+	if (ret == -ENOENT)
+		return 0;
+	if (ret)
+		return ret;
+
+	dmac->has_icu = true;
+
+	dmac->icu.pdev = of_find_device_by_node(args.np);
+	of_node_put(args.np);
+	if (!dmac->icu.pdev) {
+		dev_err(dev, "ICU device not found.\n");
+		return -ENODEV;
+	}
+
+	dmac_index = args.args[0];
+	if (dmac_index > RZV2H_MAX_DMAC_INDEX) {
+		dev_err(dev, "DMAC index %u invalid.\n", dmac_index);
+		return -EINVAL;
+	}
+	dmac->icu.dmac_index = dmac_index;
+
+	return 0;
+}
+
 static int rz_dmac_parse_of(struct device *dev, struct rz_dmac *dmac)
 {
 	struct device_node *np = dev->of_node;
@@ -839,7 +902,7 @@ static int rz_dmac_parse_of(struct device *dev, struct rz_dmac *dmac)
 		return -EINVAL;
 	}
 
-	return 0;
+	return rz_dmac_parse_of_icu(dev, dmac);
 }
 
 static int rz_dmac_probe(struct platform_device *pdev)
@@ -873,9 +936,11 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	if (IS_ERR(dmac->base))
 		return PTR_ERR(dmac->base);
 
-	dmac->ext_base = devm_platform_ioremap_resource(pdev, 1);
+	if (!dmac->has_icu) {
-	if (IS_ERR(dmac->ext_base))
+		dmac->ext_base = devm_platform_ioremap_resource(pdev, 1);
-		return PTR_ERR(dmac->ext_base);
+		if (IS_ERR(dmac->ext_base))
+			return PTR_ERR(dmac->ext_base);
+	}
 
 	/* Register interrupt handler for error */
 	irq = platform_get_irq_byname(pdev, irqname);
@@ -990,9 +1055,12 @@ static void rz_dmac_remove(struct platform_device *pdev)
 	reset_control_assert(dmac->rstc);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+
+	platform_device_put(dmac->icu.pdev);
 }
 
 static const struct of_device_id of_rz_dmac_match[] = {
+	{ .compatible = "renesas,r9a09g057-dmac", },
 	{ .compatible = "renesas,rz-dmac", },
 	{ /* Sentinel */ }
 };

drivers/dma/tegra210-adma.c

@@ -27,10 +27,10 @@
 
 #define ADMA_CH_INT_CLEAR				0x1c
 #define ADMA_CH_CTRL					0x24
-#define ADMA_CH_CTRL_DIR(val)				(((val) & 0xf) << 12)
+#define ADMA_CH_CTRL_DIR(val, mask, shift)		(((val) & (mask)) << (shift))
 #define ADMA_CH_CTRL_DIR_AHUB2MEM			2
 #define ADMA_CH_CTRL_DIR_MEM2AHUB			4
-#define ADMA_CH_CTRL_MODE_CONTINUOUS			(2 << 8)
+#define ADMA_CH_CTRL_MODE_CONTINUOUS(shift)		(2 << (shift))
 #define ADMA_CH_CTRL_FLOWCTRL_EN			BIT(1)
 #define ADMA_CH_CTRL_XFER_PAUSE_SHIFT			0
 
@@ -41,15 +41,27 @@
 #define ADMA_CH_CONFIG_MAX_BURST_SIZE                   16
 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val)		((val) & 0xf)
 #define ADMA_CH_CONFIG_MAX_BUFS				8
-#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
+#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	((reqs) << 4)
+
+#define ADMA_GLOBAL_CH_CONFIG				0x400
+#define ADMA_GLOBAL_CH_CONFIG_WEIGHT_FOR_WRR(val)	((val) & 0x7)
+#define ADMA_GLOBAL_CH_CONFIG_OUTSTANDING_REQS(reqs)	((reqs) << 8)
 
 #define TEGRA186_ADMA_GLOBAL_PAGE_CHGRP			0x30
 #define TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ		0x70
 #define TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ		0x84
+#define TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0		0x44
+#define TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1		0x48
+#define TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0		0x100
+#define TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1		0x104
+#define TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0		0x180
+#define TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1		0x184
+#define TEGRA264_ADMA_GLOBAL_PAGE_OFFSET		0x8
 
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define ADMA_CH_TX_FIFO_SIZE_SHIFT			8
 #define ADMA_CH_RX_FIFO_SIZE_SHIFT			0
+#define ADMA_GLOBAL_CH_FIFO_CTRL			0x300
 
 #define ADMA_CH_LOWER_SRC_ADDR				0x34
 #define ADMA_CH_LOWER_TRG_ADDR				0x3c
@@ -73,36 +85,48 @@ struct tegra_adma;
  * @adma_get_burst_config: Function callback used to set DMA burst size.
  * @global_reg_offset: Register offset of DMA global register.
  * @global_int_clear: Register offset of DMA global interrupt clear.
+ * @global_ch_fifo_base: Global channel fifo ctrl base offset
+ * @global_ch_config_base: Global channel config base offset
  * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
  * @ch_req_rx_shift: Register offset for AHUB receive channel select.
+ * @ch_dir_shift: Channel direction bit position.
+ * @ch_mode_shift: Channel mode bit position.
  * @ch_base_offset: Register offset of DMA channel registers.
+ * @ch_tc_offset_diff: From TC register onwards offset differs for Tegra264
  * @ch_fifo_ctrl: Default value for channel FIFO CTRL register.
+ * @ch_config: Outstanding and WRR config values
  * @ch_req_mask: Mask for Tx or Rx channel select.
+ * @ch_dir_mask: Mask for channel direction.
  * @ch_req_max: Maximum number of Tx or Rx channels available.
  * @ch_reg_size: Size of DMA channel register space.
  * @nr_channels: Number of DMA channels available.
  * @ch_fifo_size_mask: Mask for FIFO size field.
  * @sreq_index_offset: Slave channel index offset.
  * @max_page: Maximum ADMA Channel Page.
- * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  * @set_global_pg_config: Global page programming.
  */
 struct tegra_adma_chip_data {
 	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
 	unsigned int global_reg_offset;
 	unsigned int global_int_clear;
+	unsigned int global_ch_fifo_base;
+	unsigned int global_ch_config_base;
 	unsigned int ch_req_tx_shift;
 	unsigned int ch_req_rx_shift;
+	unsigned int ch_dir_shift;
+	unsigned int ch_mode_shift;
 	unsigned int ch_base_offset;
+	unsigned int ch_tc_offset_diff;
 	unsigned int ch_fifo_ctrl;
+	unsigned int ch_config;
 	unsigned int ch_req_mask;
+	unsigned int ch_dir_mask;
 	unsigned int ch_req_max;
 	unsigned int ch_reg_size;
 	unsigned int nr_channels;
 	unsigned int ch_fifo_size_mask;
 	unsigned int sreq_index_offset;
 	unsigned int max_page;
-	bool has_outstanding_reqs;
 	void (*set_global_pg_config)(struct tegra_adma *tdma);
 };
 
@@ -112,6 +136,7 @@ struct tegra_adma_chip_data {
 struct tegra_adma_chan_regs {
 	unsigned int ctrl;
 	unsigned int config;
+	unsigned int global_config;
 	unsigned int src_addr;
 	unsigned int trg_addr;
 	unsigned int fifo_ctrl;
@@ -150,6 +175,9 @@ struct tegra_adma_chan {
 	/* Transfer count and position info */
 	unsigned int			tx_buf_count;
 	unsigned int			tx_buf_pos;
+
+	unsigned int			global_ch_fifo_offset;
+	unsigned int			global_ch_config_offset;
 };
 
 /*
@@ -246,6 +274,29 @@ static void tegra186_adma_global_page_config(struct tegra_adma *tdma)
 	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ + (tdma->ch_page_no * 0x4), 0xffffff);
 }
 
+static void tegra264_adma_global_page_config(struct tegra_adma *tdma)
+{
+	u32 global_page_offset = tdma->ch_page_no * TEGRA264_ADMA_GLOBAL_PAGE_OFFSET;
+
+	/* If the default page (page1) is not used, then clear page1 registers */
+	if (tdma->ch_page_no) {
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1, 0);
+	}
+
+	/* Program global registers for selected page */
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1 + global_page_offset, 0x1);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1 + global_page_offset, 0x1);
+}
+
 static int tegra_adma_init(struct tegra_adma *tdma)
 {
 	u32 status;
@@ -404,11 +455,21 @@ static void tegra_adma_start(struct tegra_adma_chan *tdc)
 
 	tdc->tx_buf_pos = 0;
 	tdc->tx_buf_count = 0;
-	tdma_ch_write(tdc, ADMA_CH_TC, ch_regs->tc);
+	tdma_ch_write(tdc, ADMA_CH_TC - tdc->tdma->cdata->ch_tc_offset_diff, ch_regs->tc);
 	tdma_ch_write(tdc, ADMA_CH_CTRL, ch_regs->ctrl);
-	tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR, ch_regs->src_addr);
+	tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR - tdc->tdma->cdata->ch_tc_offset_diff,
-	tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR, ch_regs->trg_addr);
+		      ch_regs->src_addr);
-	tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_regs->fifo_ctrl);
+	tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR - tdc->tdma->cdata->ch_tc_offset_diff,
+		      ch_regs->trg_addr);
+
+	if (!tdc->tdma->cdata->global_ch_fifo_base)
+		tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_regs->fifo_ctrl);
+	else if (tdc->global_ch_fifo_offset)
+		tdma_write(tdc->tdma, tdc->global_ch_fifo_offset, ch_regs->fifo_ctrl);
+
+	if (tdc->global_ch_config_offset)
+		tdma_write(tdc->tdma, tdc->global_ch_config_offset, ch_regs->global_config);
+
 	tdma_ch_write(tdc, ADMA_CH_CONFIG, ch_regs->config);
 
 	/* Start ADMA */
@@ -421,7 +482,8 @@ static unsigned int tegra_adma_get_residue(struct tegra_adma_chan *tdc)
 {
 	struct tegra_adma_desc *desc = tdc->desc;
 	unsigned int max = ADMA_CH_XFER_STATUS_COUNT_MASK + 1;
-	unsigned int pos = tdma_ch_read(tdc, ADMA_CH_XFER_STATUS);
+	unsigned int pos = tdma_ch_read(tdc, ADMA_CH_XFER_STATUS -
+			tdc->tdma->cdata->ch_tc_offset_diff);
 	unsigned int periods_remaining;
 
 	/*
@@ -627,13 +689,16 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 		return -EINVAL;
 	}
 
-	ch_regs->ctrl |= ADMA_CH_CTRL_DIR(adma_dir) |
+	ch_regs->ctrl |= ADMA_CH_CTRL_DIR(adma_dir, cdata->ch_dir_mask,
-			 ADMA_CH_CTRL_MODE_CONTINUOUS |
+			cdata->ch_dir_shift) |
+			 ADMA_CH_CTRL_MODE_CONTINUOUS(cdata->ch_mode_shift) |
 			 ADMA_CH_CTRL_FLOWCTRL_EN;
 	ch_regs->config |= cdata->adma_get_burst_config(burst_size);
-	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
+
-	if (cdata->has_outstanding_reqs)
+	if (cdata->global_ch_config_base)
-		ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8);
+		ch_regs->global_config |= cdata->ch_config;
+	else
+		ch_regs->config |= cdata->ch_config;
 
 	/*
 	 * 'sreq_index' represents the current ADMAIF channel number and as per
@@ -788,12 +853,23 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 		/* skip if channel is not active */
 		if (!ch_reg->cmd)
 			continue;
-		ch_reg->tc = tdma_ch_read(tdc, ADMA_CH_TC);
+		ch_reg->tc = tdma_ch_read(tdc, ADMA_CH_TC - tdma->cdata->ch_tc_offset_diff);
-		ch_reg->src_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_SRC_ADDR);
+		ch_reg->src_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_SRC_ADDR -
-		ch_reg->trg_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_TRG_ADDR);
+						tdma->cdata->ch_tc_offset_diff);
+		ch_reg->trg_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_TRG_ADDR -
+						tdma->cdata->ch_tc_offset_diff);
 		ch_reg->ctrl = tdma_ch_read(tdc, ADMA_CH_CTRL);
-		ch_reg->fifo_ctrl = tdma_ch_read(tdc, ADMA_CH_FIFO_CTRL);
+
+		if (tdc->global_ch_config_offset)
+			ch_reg->global_config = tdma_read(tdc->tdma, tdc->global_ch_config_offset);
+
+		if (!tdc->tdma->cdata->global_ch_fifo_base)
+			ch_reg->fifo_ctrl = tdma_ch_read(tdc, ADMA_CH_FIFO_CTRL);
+		else if (tdc->global_ch_fifo_offset)
+			ch_reg->fifo_ctrl = tdma_read(tdc->tdma, tdc->global_ch_fifo_offset);
+
 		ch_reg->config = tdma_ch_read(tdc, ADMA_CH_CONFIG);
+
 	}
 
 clk_disable:
@@ -832,12 +908,23 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
 			continue;
-		tdma_ch_write(tdc, ADMA_CH_TC, ch_reg->tc);
+		tdma_ch_write(tdc, ADMA_CH_TC - tdma->cdata->ch_tc_offset_diff, ch_reg->tc);
-		tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR, ch_reg->src_addr);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR - tdma->cdata->ch_tc_offset_diff,
-		tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR, ch_reg->trg_addr);
+			      ch_reg->src_addr);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR - tdma->cdata->ch_tc_offset_diff,
+			      ch_reg->trg_addr);
 		tdma_ch_write(tdc, ADMA_CH_CTRL, ch_reg->ctrl);
-		tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_reg->fifo_ctrl);
+
+		if (!tdc->tdma->cdata->global_ch_fifo_base)
+			tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_reg->fifo_ctrl);
+		else if (tdc->global_ch_fifo_offset)
+			tdma_write(tdc->tdma, tdc->global_ch_fifo_offset, ch_reg->fifo_ctrl);
+
+		if (tdc->global_ch_config_offset)
+			tdma_write(tdc->tdma, tdc->global_ch_config_offset, ch_reg->global_config);
+
 		tdma_ch_write(tdc, ADMA_CH_CONFIG, ch_reg->config);
+
 		tdma_ch_write(tdc, ADMA_CH_CMD, ch_reg->cmd);
 	}
 
@@ -848,17 +935,23 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.adma_get_burst_config  = tegra210_adma_get_burst_config,
 	.global_reg_offset	= 0xc00,
 	.global_int_clear	= 0x20,
+	.global_ch_fifo_base	= 0,
+	.global_ch_config_base	= 0,
 	.ch_req_tx_shift	= 28,
 	.ch_req_rx_shift	= 24,
+	.ch_dir_shift		= 12,
+	.ch_mode_shift		= 8,
 	.ch_base_offset		= 0,
+	.ch_tc_offset_diff	= 0,
+	.ch_config		= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1),
 	.ch_req_mask		= 0xf,
+	.ch_dir_mask		= 0xf,
 	.ch_req_max		= 10,
 	.ch_reg_size		= 0x80,
 	.nr_channels		= 22,
 	.ch_fifo_size_mask	= 0xf,
 	.sreq_index_offset	= 2,
 	.max_page		= 0,
-	.has_outstanding_reqs	= false,
 	.set_global_pg_config	= NULL,
 };
 
@@ -866,23 +959,56 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.adma_get_burst_config  = tegra186_adma_get_burst_config,
 	.global_reg_offset	= 0,
 	.global_int_clear	= 0x402c,
+	.global_ch_fifo_base	= 0,
+	.global_ch_config_base	= 0,
 	.ch_req_tx_shift	= 27,
 	.ch_req_rx_shift	= 22,
+	.ch_dir_shift		= 12,
+	.ch_mode_shift		= 8,
 	.ch_base_offset		= 0x10000,
+	.ch_tc_offset_diff	= 0,
+	.ch_config		= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1) |
+				  TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8),
 	.ch_req_mask		= 0x1f,
+	.ch_dir_mask		= 0xf,
 	.ch_req_max		= 20,
 	.ch_reg_size		= 0x100,
 	.nr_channels		= 32,
 	.ch_fifo_size_mask	= 0x1f,
 	.sreq_index_offset	= 4,
 	.max_page		= 4,
-	.has_outstanding_reqs	= true,
 	.set_global_pg_config	= tegra186_adma_global_page_config,
 };
 
+static const struct tegra_adma_chip_data tegra264_chip_data = {
+	.adma_get_burst_config  = tegra186_adma_get_burst_config,
+	.global_reg_offset	= 0,
+	.global_int_clear	= 0x800c,
+	.global_ch_fifo_base	= ADMA_GLOBAL_CH_FIFO_CTRL,
+	.global_ch_config_base	= ADMA_GLOBAL_CH_CONFIG,
+	.ch_req_tx_shift	= 26,
+	.ch_req_rx_shift	= 20,
+	.ch_dir_shift		= 10,
+	.ch_mode_shift		= 7,
+	.ch_base_offset		= 0x10000,
+	.ch_tc_offset_diff	= 4,
+	.ch_config		= ADMA_GLOBAL_CH_CONFIG_WEIGHT_FOR_WRR(1) |
+				  ADMA_GLOBAL_CH_CONFIG_OUTSTANDING_REQS(8),
+	.ch_req_mask		= 0x3f,
+	.ch_dir_mask		= 7,
+	.ch_req_max		= 32,
+	.ch_reg_size		= 0x100,
+	.nr_channels		= 64,
+	.ch_fifo_size_mask	= 0x7f,
+	.sreq_index_offset	= 0,
+	.max_page		= 10,
+	.set_global_pg_config	= tegra264_adma_global_page_config,
+};
+
 static const struct of_device_id tegra_adma_of_match[] = {
 	{ .compatible = "nvidia,tegra210-adma", .data = &tegra210_chip_data },
 	{ .compatible = "nvidia,tegra186-adma", .data = &tegra186_chip_data },
+	{ .compatible = "nvidia,tegra264-adma", .data = &tegra264_chip_data },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, tegra_adma_of_match);
@@ -985,6 +1111,15 @@ static int tegra_adma_probe(struct platform_device *pdev)
 
 		tdc->chan_addr = tdma->ch_base_addr + (cdata->ch_reg_size * i);
 
+		if (tdma->base_addr) {
+			if (cdata->global_ch_fifo_base)
+				tdc->global_ch_fifo_offset = cdata->global_ch_fifo_base + (4 * i);
+
+			if (cdata->global_ch_config_base)
+				tdc->global_ch_config_offset =
+					cdata->global_ch_config_base + (4 * i);
+		}
+
 		tdc->irq = of_irq_get(pdev->dev.of_node, i);
 		if (tdc->irq <= 0) {
 			ret = tdc->irq ?: -ENXIO;

drivers/dma/ti/k3-udma.c

@@ -5624,7 +5624,8 @@ static int udma_probe(struct platform_device *pdev)
 		uc->config.dir = DMA_MEM_TO_MEM;
 		uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d",
 					  dev_name(dev), i);
-
+		if (!uc->name)
+			return -ENOMEM;
 		vchan_init(&uc->vc, &ud->ddev);
 		/* Use custom vchan completion handling */
 		tasklet_setup(&uc->vc.task, udma_vchan_complete);

drivers/dma/xilinx/xilinx_dma.c

@@ -2909,6 +2909,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		return -EINVAL;
 	}
 
+	xdev->common.directions |= chan->direction;
+
 	/* Request the interrupt */
 	chan->irq = of_irq_get(node, chan->tdest);
 	if (chan->irq < 0)
@@ -3115,6 +3117,8 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		}
 	}
 
+	dma_set_max_seg_size(xdev->dev, xdev->max_buffer_len);
+
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		xdev->has_axistream_connected =
 			of_property_read_bool(node, "xlnx,axistream-connected");

drivers/irqchip/irq-renesas-rzv2h.c

@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/irq-renesas-rzv2h.h>
 #include <linux/irqdomain.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -41,6 +42,8 @@
 #define ICU_TSCLR				0x24
 #define ICU_TITSR(k)				(0x28 + (k) * 4)
 #define ICU_TSSR(k)				(0x30 + (k) * 4)
+#define ICU_DMkSELy(k, y)			(0x420 + (k) * 0x20 + (y) * 4)
+#define ICU_DMACKSELk(k)			(0x500 + (k) * 4)
 
 /* NMI */
 #define ICU_NMI_EDGE_FALLING			0
@@ -103,6 +106,15 @@ struct rzv2h_hw_info {
 	u8		field_width;
 };
 
+/* DMAC */
+#define ICU_DMAC_DkRQ_SEL_MASK			GENMASK(9, 0)
+
+#define ICU_DMAC_DMAREQ_SHIFT(up)		((up) * 16)
+#define ICU_DMAC_DMAREQ_MASK(up)		(ICU_DMAC_DkRQ_SEL_MASK \
+						 << ICU_DMAC_DMAREQ_SHIFT(up))
+#define ICU_DMAC_PREP_DMAREQ(sel, up)		(FIELD_PREP(ICU_DMAC_DkRQ_SEL_MASK, (sel)) \
+						 << ICU_DMAC_DMAREQ_SHIFT(up))
+
 /**
  * struct rzv2h_icu_priv - Interrupt Control Unit controller private data structure.
  * @base:	Controller's base address
@@ -117,6 +129,27 @@ struct rzv2h_icu_priv {
 	const struct rzv2h_hw_info	*info;
 };
 
+void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index, u8 dmac_channel,
+				u16 req_no)
+{
+	struct rzv2h_icu_priv *priv = platform_get_drvdata(icu_dev);
+	u32 icu_dmksely, dmareq, dmareq_mask;
+	u8 y, upper;
+
+	y = dmac_channel / 2;
+	upper = dmac_channel % 2;
+
+	dmareq = ICU_DMAC_PREP_DMAREQ(req_no, upper);
+	dmareq_mask = ICU_DMAC_DMAREQ_MASK(upper);
+
+	guard(raw_spinlock_irqsave)(&priv->lock);
+
+	icu_dmksely = readl(priv->base + ICU_DMkSELy(dmac_index, y));
+	icu_dmksely = (icu_dmksely & ~dmareq_mask) | dmareq;
+	writel(icu_dmksely, priv->base + ICU_DMkSELy(dmac_index, y));
+}
+EXPORT_SYMBOL_GPL(rzv2h_icu_register_dma_req);
+
 static inline struct rzv2h_icu_priv *irq_data_to_priv(struct irq_data *data)
 {
 	return data->domain->host_data;
@@ -491,6 +524,8 @@ static int rzv2h_icu_init_common(struct device_node *node, struct device_node *p
 	if (!rzv2h_icu_data)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, rzv2h_icu_data);
+
 	rzv2h_icu_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
 	if (IS_ERR(rzv2h_icu_data->base))
 		return PTR_ERR(rzv2h_icu_data->base);

include/linux/irqchip/irq-renesas-rzv2h.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Renesas RZ/V2H(P) Interrupt Control Unit (ICU)
+ *
+ * Copyright (C) 2025 Renesas Electronics Corporation.
+ */
+
+#ifndef __LINUX_IRQ_RENESAS_RZV2H
+#define __LINUX_IRQ_RENESAS_RZV2H
+
+#include <linux/platform_device.h>
+
+#define RZV2H_ICU_DMAC_REQ_NO_DEFAULT		0x3ff
+
+#ifdef CONFIG_RENESAS_RZV2H_ICU
+void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index, u8 dmac_channel,
+				u16 req_no);
+#else
+static inline void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index,
+					      u8 dmac_channel, u16 req_no) { }
+#endif
+
+#endif /* __LINUX_IRQ_RENESAS_RZV2H */