dmaengine updates for v5.12-rc1

New drivers/devices
  - Intel LGM SoC DMA driver
  - Actions Semi S500 DMA controller
  - Renesas r8a779a0 dma controller
  - Ingenic JZ4760(B) dma controller
  - Intel KeemBay AxiDMA controller
 
 Removed
  - Coh901318 dma driver
  - Zte zx dma driver
  - Sirfsoc dma driver
 
 Updates:
  - mmp_pdma, mmp_tdma gained module support
  - imx-sdma become modern and dropped platform data support
  - dw-axi driver gained slave and cyclic dma support
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE+vs47OPLdNbVcHzyfBQHDyUjg0cFAmA0gIEACgkQfBQHDyUj
 g0fLyw//bfIBqmyvN01QNmYV0qrud0nZGRAGHSEwZ1Nrw2CvK37+XphYzVYy/PGk
 Cg6ca+QXGJdIfqmQV/rnIEwrNx/GeNUAulVT5hxdHQw/HDPoZexU5S+Lyetr4g7l
 FaE2C5se4RBp07eGhcOWkneHE/fhC9fX23VdNGNM6Nzb1F0j4MTmzcJAlsdCq2Q+
 1UlJ2O4w/t/mdqgec4J+JGTsfb+BXxs0nWnuwVSy1SEkac3Gj0kqHlIHsQqLCiST
 /D2rs1I0Chscu+ChrPNaVXDEobQipxIEdkzO6623t8C5KqfSf5i8rLvZvRP5YKf1
 U5ZAi3p0c/t5VgXvA6WD79pN6ZLPsEMFDxyKQAazGPgrEP4gmI4dteETiJyr6Ag6
 j6WqiDJwkmdVyuTiFDJsN3pTOqvT+TeHlLbnygAiuyMeNaF9skc7kxtq0XtXQigT
 vLcwtGavFnmF7TZGjEVv4JTMdMFPfczE8y+fhM7ET/uF36gTrPHaoD3KIwgimwIt
 Cmfpe+Ij8R3tBwV80454hp4+Gb+cR83OUgwy+EcBCw9P0/Pf4t0NyTgim+wN02Kt
 X7tkkgxGkvziIkfbXQa4zdVqAbT6+WcRUjEDZY3/Lp7EFyVyM8APEVSAie9b/TWN
 UgQo3TDuB6SU7XQ3Ahj6Swra0+UoVztHtwOmgIqiVz5on6780lg=
 =0AE9
 -----END PGP SIGNATURE-----

Merge tag 'dmaengine-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "We have couple of drivers removed a new driver and bunch of new device
  support and few updates to drivers for this round.

  New drivers/devices:
   - Intel LGM SoC DMA driver
   - Actions Semi S500 DMA controller
   - Renesas r8a779a0 dma controller
   - Ingenic JZ4760(B) dma controller
   - Intel KeemBay AxiDMA controller

  Removed:
   - Coh901318 dma driver
   - Zte zx dma driver
   - Sirfsoc dma driver

  Updates:
   - mmp_pdma, mmp_tdma gained module support
   - imx-sdma become modern and dropped platform data support
   - dw-axi driver gained slave and cyclic dma support"

* tag 'dmaengine-5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (58 commits)
  dmaengine: dw-axi-dmac: remove redundant null check on desc
  dmaengine: xilinx_dma: Alloc tx descriptors GFP_NOWAIT
  dmaengine: dw-axi-dmac: Virtually split the linked-list
  dmaengine: dw-axi-dmac: Set constraint to the Max segment size
  dmaengine: dw-axi-dmac: Add Intel KeemBay AxiDMA BYTE and HALFWORD registers
  dmaengine: dw-axi-dmac: Add Intel KeemBay AxiDMA handshake
  dmaengine: dw-axi-dmac: Add Intel KeemBay AxiDMA support
  dmaengine: drivers: Kconfig: add HAS_IOMEM dependency to DW_AXI_DMAC
  dmaengine: dw-axi-dmac: Add Intel KeemBay DMA register fields
  dt-binding: dma: dw-axi-dmac: Add support for Intel KeemBay AxiDMA
  dmaengine: dw-axi-dmac: Support burst residue granularity
  dmaengine: dw-axi-dmac: Support of_dma_controller_register()
  dmaegine: dw-axi-dmac: Support device_prep_dma_cyclic()
  dmaengine: dw-axi-dmac: Support device_prep_slave_sg
  dmaengine: dw-axi-dmac: Add device_config operation
  dmaengine: dw-axi-dmac: Add device_synchronize() callback
  dmaengine: dw-axi-dmac: move dma_pool_create() to alloc_chan_resources()
  dmaengine: dw-axi-dmac: simplify descriptor management
  dt-bindings: dma: Add YAML schemas for dw-axi-dmac
  dmaengine: ti: k3-psil: optimize struct psil_endpoint_config for size
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1674,6 +1674,12 @@
 			In such case C2/C3 won't be used again.
 			idle=nomwait: Disable mwait for CPU C-states
 
+	idxd.sva=	[HW]
+			Format: <bool>
+			Allow force disabling of Shared Virtual Memory (SVA)
+			support for the idxd driver. By default it is set to
+			true (1).
+
 	ieee754=	[MIPS] Select IEEE Std 754 conformance mode
 			Format: { strict | legacy | 2008 | relaxed }
 			Default: strict

Documentation/devicetree/bindings/dma/ingenic,dma.yaml

@@ -17,6 +17,8 @@ properties:
     enum:
       - ingenic,jz4740-dma
       - ingenic,jz4725b-dma
+      - ingenic,jz4760-dma
+      - ingenic,jz4760b-dma
       - ingenic,jz4770-dma
       - ingenic,jz4780-dma
       - ingenic,x1000-dma

Documentation/devicetree/bindings/dma/intel,ldma.yaml

@@ -0,0 +1,116 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/intel,ldma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Lightning Mountain centralized DMA controllers.
+
+maintainers:
+  - chuanhua.lei@intel.com
+  - mallikarjunax.reddy@intel.com
+
+allOf:
+  - $ref: "dma-controller.yaml#"
+
+properties:
+  compatible:
+    enum:
+      - intel,lgm-cdma
+      - intel,lgm-dma2tx
+      - intel,lgm-dma1rx
+      - intel,lgm-dma1tx
+      - intel,lgm-dma0tx
+      - intel,lgm-dma3
+      - intel,lgm-toe-dma30
+      - intel,lgm-toe-dma31
+
+  reg:
+    maxItems: 1
+
+  "#dma-cells":
+    const: 3
+    description:
+      The first cell is the peripheral's DMA request line.
+      The second cell is the peripheral's (port) number corresponding to the channel.
+      The third cell is the burst length of the channel.
+
+  dma-channels:
+    minimum: 1
+    maximum: 16
+
+  dma-channel-mask:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    items:
+      - const: ctrl
+
+  interrupts:
+    maxItems: 1
+
+  intel,dma-poll-cnt:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      DMA descriptor polling counter is used to control the poling mechanism
+      for the descriptor fetching for all channels.
+
+  intel,dma-byte-en:
+    type: boolean
+    description:
+      DMA byte enable is only valid for DMA write(RX).
+      Byte enable(1) means DMA write will be based on the number of dwords
+      instead of the whole burst.
+
+  intel,dma-drb:
+    type: boolean
+    description:
+      DMA descriptor read back to make sure data and desc synchronization.
+
+  intel,dma-dburst-wr:
+    type: boolean
+    description:
+      Enable RX dynamic burst write. When it is enabled, the DMA does RX dynamic burst;
+      if it is disabled, the DMA RX will still support programmable fixed burst size of 2,4,8,16.
+      It only applies to RX DMA and memcopy DMA.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    dma0: dma-controller@e0e00000 {
+      compatible = "intel,lgm-cdma";
+      reg = <0xe0e00000 0x1000>;
+      #dma-cells = <3>;
+      dma-channels = <16>;
+      dma-channel-mask = <0xFFFF>;
+      interrupt-parent = <&ioapic1>;
+      interrupts = <82 1>;
+      resets = <&rcu0 0x30 0>;
+      reset-names = "ctrl";
+      clocks = <&cgu0 80>;
+      intel,dma-poll-cnt = <4>;
+      intel,dma-byte-en;
+      intel,dma-drb;
+    };
+  - |
+    dma3: dma-controller@ec800000 {
+      compatible = "intel,lgm-dma3";
+      reg = <0xec800000 0x1000>;
+      clocks = <&cgu0 71>;
+      resets = <&rcu0 0x10 9>;
+      #dma-cells = <3>;
+      intel,dma-poll-cnt = <16>;
+      intel,dma-byte-en;
+      intel,dma-dburst-wr;
+    };

Documentation/devicetree/bindings/dma/owl-dma.yaml

@@ -8,8 +8,8 @@ title: Actions Semi Owl SoCs DMA controller
 
 description: |
   The OWL DMA is a general-purpose direct memory access controller capable of
-  supporting 10 and 12 independent DMA channels for S700 and S900 SoCs
-  respectively.
+  supporting 10 independent DMA channels for the Actions Semi S700 SoC and 12
+  independent DMA channels for the S500 and S900 SoC variants.
 
 maintainers:
   - Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -20,8 +20,9 @@ allOf:
 properties:
   compatible:
     enum:
-      - actions,s900-dma
+      - actions,s500-dma
       - actions,s700-dma
+      - actions,s900-dma
 
   reg:
     maxItems: 1

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

@@ -14,34 +14,37 @@ allOf:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - renesas,dmac-r8a7742  # RZ/G1H
-          - renesas,dmac-r8a7743  # RZ/G1M
-          - renesas,dmac-r8a7744  # RZ/G1N
-          - renesas,dmac-r8a7745  # RZ/G1E
-          - renesas,dmac-r8a77470 # RZ/G1C
-          - renesas,dmac-r8a774a1 # RZ/G2M
-          - renesas,dmac-r8a774b1 # RZ/G2N
-          - renesas,dmac-r8a774c0 # RZ/G2E
-          - renesas,dmac-r8a774e1 # RZ/G2H
-          - renesas,dmac-r8a7790  # R-Car H2
-          - renesas,dmac-r8a7791  # R-Car M2-W
-          - renesas,dmac-r8a7792  # R-Car V2H
-          - renesas,dmac-r8a7793  # R-Car M2-N
-          - renesas,dmac-r8a7794  # R-Car E2
-          - renesas,dmac-r8a7795  # R-Car H3
-          - renesas,dmac-r8a7796  # R-Car M3-W
-          - renesas,dmac-r8a77961 # R-Car M3-W+
-          - renesas,dmac-r8a77965 # R-Car M3-N
-          - renesas,dmac-r8a77970 # R-Car V3M
-          - renesas,dmac-r8a77980 # R-Car V3H
-          - renesas,dmac-r8a77990 # R-Car E3
-          - renesas,dmac-r8a77995 # R-Car D3
-      - const: renesas,rcar-dmac
+    oneOf:
+      - items:
+          - enum:
+              - renesas,dmac-r8a7742  # RZ/G1H
+              - renesas,dmac-r8a7743  # RZ/G1M
+              - renesas,dmac-r8a7744  # RZ/G1N
+              - renesas,dmac-r8a7745  # RZ/G1E
+              - renesas,dmac-r8a77470 # RZ/G1C
+              - renesas,dmac-r8a774a1 # RZ/G2M
+              - renesas,dmac-r8a774b1 # RZ/G2N
+              - renesas,dmac-r8a774c0 # RZ/G2E
+              - renesas,dmac-r8a774e1 # RZ/G2H
+              - renesas,dmac-r8a7790  # R-Car H2
+              - renesas,dmac-r8a7791  # R-Car M2-W
+              - renesas,dmac-r8a7792  # R-Car V2H
+              - renesas,dmac-r8a7793  # R-Car M2-N
+              - renesas,dmac-r8a7794  # R-Car E2
+              - renesas,dmac-r8a7795  # R-Car H3
+              - renesas,dmac-r8a7796  # R-Car M3-W
+              - renesas,dmac-r8a77961 # R-Car M3-W+
+              - renesas,dmac-r8a77965 # R-Car M3-N
+              - renesas,dmac-r8a77970 # R-Car V3M
+              - renesas,dmac-r8a77980 # R-Car V3H
+              - renesas,dmac-r8a77990 # R-Car E3
+              - renesas,dmac-r8a77995 # R-Car D3
+          - const: renesas,rcar-dmac
 
-  reg:
-    maxItems: 1
+      - items:
+          - const: renesas,dmac-r8a779a0 # R-Car V3U
+
+  reg: true
 
   interrupts:
     minItems: 9
@@ -110,6 +113,23 @@ required:
   - power-domains
   - resets
 
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - renesas,dmac-r8a779a0
+then:
+  properties:
+    reg:
+      items:
+        - description: Base register block
+        - description: Channel register block
+else:
+  properties:
+    reg:
+      maxItems: 1
+
 additionalProperties: false
 
 examples:

Documentation/devicetree/bindings/dma/sirfsoc-dma.txt

@@ -1,44 +0,0 @@
-* CSR SiRFSoC DMA controller
-
-See dma.txt first
-
-Required properties:
-- compatible: Should be "sirf,prima2-dmac", "sirf,atlas7-dmac" or
-  "sirf,atlas7-dmac-v2"
-- 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.
-- clocks: clock required
-
-Example:
-
-Controller:
-dmac0: dma-controller@b00b0000 {
-	compatible = "sirf,prima2-dmac";
-	reg = <0xb00b0000 0x10000>;
-	interrupts = <12>;
-	clocks = <&clks 24>;
-	#dma-cells = <1>;
-};
-
-
-Client:
-Fill the specific dma request line in dmas. In the below example, spi0 read
-channel request line is 9 of the 2nd dma controller, while write channel uses
-4 of the 2nd dma controller; spi1 read channel request line is 12 of the 1st
-dma controller, while write channel uses 13 of the 1st dma controller:
-
-spi0: spi@b00d0000 {
-	compatible = "sirf,prima2-spi";
-	dmas = <&dmac1 9>,
-		<&dmac1 4>;
-	dma-names = "rx", "tx";
-};
-
-spi1: spi@b0170000 {
-	compatible = "sirf,prima2-spi";
-	dmas = <&dmac0 12>,
-		<&dmac0 13>;
-	dma-names = "rx", "tx";
-};

Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt

@@ -1,39 +0,0 @@
-Synopsys DesignWare AXI DMA Controller
-
-Required properties:
-- compatible: "snps,axi-dma-1.01a"
-- reg: Address range of the DMAC registers. This should include
-  all of the per-channel registers.
-- interrupt: Should contain the DMAC interrupt number.
-- dma-channels: Number of channels supported by hardware.
-- snps,dma-masters: Number of AXI masters supported by the hardware.
-- snps,data-width: Maximum AXI data width supported by hardware.
-  (0 - 8bits, 1 - 16bits, 2 - 32bits, ..., 6 - 512bits)
-- snps,priority: Priority of channel. Array size is equal to the number of
-  dma-channels. Priority value must be programmed within [0:dma-channels-1]
-  range. (0 - minimum priority)
-- snps,block-size: Maximum block size supported by the controller channel.
-  Array size is equal to the number of dma-channels.
-
-Optional properties:
-- snps,axi-max-burst-len: Restrict master AXI burst length by value specified
-  in this property. If this property is missing the maximum AXI burst length
-  supported by DMAC is used. [1:256]
-
-Example:
-
-dmac: dma-controller@80000 {
-	compatible = "snps,axi-dma-1.01a";
-	reg = <0x80000 0x400>;
-	clocks = <&core_clk>, <&cfgr_clk>;
-	clock-names = "core-clk", "cfgr-clk";
-	interrupt-parent = <&intc>;
-	interrupts = <27>;
-
-	dma-channels = <4>;
-	snps,dma-masters = <2>;
-	snps,data-width = <3>;
-	snps,block-size = <4096 4096 4096 4096>;
-	snps,priority = <0 1 2 3>;
-	snps,axi-max-burst-len = <16>;
-};

Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml

@@ -0,0 +1,126 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/snps,dw-axi-dmac.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Synopsys DesignWare AXI DMA Controller
+
+maintainers:
+  - Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+  - Jee Heng Sia <jee.heng.sia@intel.com>
+
+description:
+  Synopsys DesignWare AXI DMA Controller DT Binding
+
+allOf:
+  - $ref: "dma-controller.yaml#"
+
+properties:
+  compatible:
+    enum:
+      - snps,axi-dma-1.01a
+      - intel,kmb-axi-dma
+
+  reg:
+    minItems: 1
+    items:
+      - description: Address range of the DMAC registers
+      - description: Address range of the DMAC APB registers
+
+  reg-names:
+    items:
+      - const: axidma_ctrl_regs
+      - const: axidma_apb_regs
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+
+  clock-names:
+    items:
+      - const: core-clk
+      - const: cfgr-clk
+
+  '#dma-cells':
+    const: 1
+
+  dma-channels:
+    minimum: 1
+    maximum: 8
+
+  snps,dma-masters:
+    description: |
+      Number of AXI masters supported by the hardware.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [1, 2]
+
+  snps,data-width:
+    description: |
+      AXI data width supported by hardware.
+      (0 - 8bits, 1 - 16bits, 2 - 32bits, ..., 6 - 512bits)
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [0, 1, 2, 3, 4, 5, 6]
+
+  snps,priority:
+    description: |
+      Channel priority specifier associated with the DMA channels.
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 1
+    maxItems: 8
+
+  snps,block-size:
+    description: |
+      Channel block size specifier associated with the DMA channels.
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 1
+    maxItems: 8
+
+  snps,axi-max-burst-len:
+    description: |
+      Restrict master AXI burst length by value specified in this property.
+      If this property is missing the maximum AXI burst length supported by
+      DMAC is used.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 1
+    maximum: 256
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - interrupts
+  - '#dma-cells'
+  - dma-channels
+  - snps,dma-masters
+  - snps,data-width
+  - snps,priority
+  - snps,block-size
+
+additionalProperties: false
+
+examples:
+  - |
+     #include <dt-bindings/interrupt-controller/arm-gic.h>
+     #include <dt-bindings/interrupt-controller/irq.h>
+     /* example with snps,dw-axi-dmac */
+     dmac: dma-controller@80000 {
+         compatible = "snps,axi-dma-1.01a";
+         reg = <0x80000 0x400>;
+         clocks = <&core_clk>, <&cfgr_clk>;
+         clock-names = "core-clk", "cfgr-clk";
+         interrupt-parent = <&intc>;
+         interrupts = <27>;
+         #dma-cells = <1>;
+         dma-channels = <4>;
+         snps,dma-masters = <2>;
+         snps,data-width = <3>;
+         snps,block-size = <4096 4096 4096 4096>;
+         snps,priority = <0 1 2 3>;
+         snps,axi-max-burst-len = <16>;
+     };

Documentation/devicetree/bindings/dma/ste-coh901318.txt

@@ -1,32 +0,0 @@
-ST-Ericsson COH 901 318 DMA Controller
-
-This is a DMA controller which has begun as a fork of the
-ARM PL08x PrimeCell VHDL code.
-
-Required properties:
-- compatible: should be "stericsson,coh901318"
-- reg: register locations and length
-- interrupts: the single DMA IRQ
-- #dma-cells: must be set to <1>, as the channels on the
-  COH 901 318 are simple and identified by a single number
-- dma-channels: the number of DMA channels handled
-
-Example:
-
-dmac: dma-controller@c00020000 {
-	compatible = "stericsson,coh901318";
-	reg = <0xc0020000 0x1000>;
-	interrupt-parent = <&vica>;
-	interrupts = <2>;
-	#dma-cells = <1>;
-	dma-channels = <40>;
-};
-
-Consumers example:
-
-uart0: serial@c0013000 {
-	compatible = "...";
-	(...)
-	dmas = <&dmac 17 &dmac 18>;
-	dma-names = "tx", "rx";
-};

Documentation/devicetree/bindings/dma/zxdma.txt

@@ -1,38 +0,0 @@
-* ZTE ZX296702 DMA controller
-
-Required properties:
-- compatible: Should be "zte,zx296702-dma"
-- reg: Should contain DMA registers location and length.
-- interrupts: Should contain one interrupt shared by all channel
-- #dma-cells: see dma.txt, should be 1, para number
-- dma-channels: physical channels supported
-- dma-requests: virtual channels supported, each virtual channel
-		have specific request line
-- clocks: clock required
-
-Example:
-
-Controller:
-	dma: dma-controller@09c00000{
-		compatible = "zte,zx296702-dma";
-		reg = <0x09c00000 0x1000>;
-		clocks = <&topclk ZX296702_DMA_ACLK>;
-		interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>;
-		#dma-cells = <1>;
-		dma-channels = <24>;
-		dma-requests = <24>;
-	};
-
-Client:
-Use specific request line passing from dmax
-For example, spdif0 tx channel request line is 4
-	spdif0: spdif0@b004000 {
-		#sound-dai-cells = <0>;
-		compatible = "zte,zx296702-spdif";
-		reg = <0x0b004000 0x1000>;
-		clocks = <&lsp0clk ZX296702_SPDIF0_DIV>;
-		clock-names = "tx";
-		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
-		dmas = <&dma 4>;
-		dma-names = "tx";
-	}

MAINTAINERS

@@ -2828,9 +2828,7 @@ S:	Odd fixes
 W:	http://sourceforge.net/projects/xscaleiop
 F:	Documentation/crypto/async-tx-api.rst
 F:	crypto/async_tx/
-F:	drivers/dma/
 F:	include/linux/async_tx.h
-F:	include/linux/dmaengine.h
 
 AT24 EEPROM DRIVER
 M:	Bartosz Golaszewski <bgolaszewski@baylibre.com>
@@ -5271,6 +5269,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine.git
 F:	Documentation/devicetree/bindings/dma/
 F:	Documentation/driver-api/dmaengine/
 F:	drivers/dma/
+F:	include/linux/dma/
 F:	include/linux/dmaengine.h
 F:	include/linux/of_dma.h
 
@@ -11614,7 +11613,6 @@ F:	drivers/dma/at_hdmac.c
 F:	drivers/dma/at_hdmac_regs.h
 F:	drivers/dma/at_xdmac.c
 F:	include/dt-bindings/dma/at91.h
-F:	include/linux/platform_data/dma-atmel.h
 
 MICROCHIP AT91 SERIAL DRIVER
 M:	Richard Genoud <richard.genoud@gmail.com>

drivers/dma/Kconfig

@@ -124,13 +124,6 @@ config BCM_SBA_RAID
 	  has the capability to offload memcpy, xor and pq computation
 	  for raid5/6.
 
-config COH901318
-	bool "ST-Ericsson COH901318 DMA support"
-	select DMA_ENGINE
-	depends on ARCH_U300 || COMPILE_TEST
-	help
-	  Enable support for ST-Ericsson COH 901 318 DMA.
-
 config DMA_BCM2835
 	tristate "BCM2835 DMA engine support"
 	depends on ARCH_BCM2835
@@ -179,6 +172,7 @@ config DMA_SUN6I
 config DW_AXI_DMAC
 	tristate "Synopsys DesignWare AXI DMA support"
 	depends on OF || COMPILE_TEST
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -378,14 +372,14 @@ config MILBEAUT_XDMAC
 	  XDMAC device.
 
 config MMP_PDMA
-	bool "MMP PDMA support"
+	tristate "MMP PDMA support"
 	depends on ARCH_MMP || ARCH_PXA || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Support the MMP PDMA engine for PXA and MMP platform.
 
 config MMP_TDMA
-	bool "MMP Two-Channel DMA support"
+	tristate "MMP Two-Channel DMA support"
 	depends on ARCH_MMP || COMPILE_TEST
 	select DMA_ENGINE
 	select GENERIC_ALLOCATOR
@@ -519,13 +513,6 @@ config PLX_DMA
 	  These are exposed via extra functions on the switch's
 	  upstream port. Each function exposes one DMA channel.
 
-config SIRF_DMA
-	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
-	depends on ARCH_SIRF
-	select DMA_ENGINE
-	help
-	  Enable support for the CSR SiRFprimaII DMA engine.
-
 config STE_DMA40
 	bool "ST-Ericsson DMA40 support"
 	depends on ARCH_U8500
@@ -710,15 +697,6 @@ config XILINX_ZYNQMP_DPDMA
 	  driver provides the dmaengine required by the DisplayPort subsystem
 	  display driver.
 
-config ZX_DMA
-	tristate "ZTE ZX DMA support"
-	depends on ARCH_ZX || COMPILE_TEST
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Support the DMA engine for ZTE ZX family platform devices.
-
-
 # driver files
 source "drivers/dma/bestcomm/Kconfig"
 
@@ -740,6 +718,8 @@ source "drivers/dma/ti/Kconfig"
 
 source "drivers/dma/fsl-dpaa2-qdma/Kconfig"
 
+source "drivers/dma/lgm/Kconfig"
+
 # clients
 comment "DMA Clients"
 	depends on DMA_ENGINE

drivers/dma/Makefile

@@ -20,7 +20,6 @@ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
 obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o
-obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
 obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
@@ -65,7 +64,6 @@ obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
 obj-$(CONFIG_PXA_DMA) += pxa_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SF_PDMA) += sf-pdma/
-obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_STM32_DMA) += stm32-dma.o
 obj-$(CONFIG_STM32_DMAMUX) += stm32-dmamux.o
@@ -79,9 +77,9 @@ obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_UNIPHIER_MDMAC) += uniphier-mdmac.o
 obj-$(CONFIG_UNIPHIER_XDMAC) += uniphier-xdmac.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
-obj-$(CONFIG_ZX_DMA) += zx_dma.o
 obj-$(CONFIG_ST_FDMA) += st_fdma.o
 obj-$(CONFIG_FSL_DPAA2_QDMA) += fsl-dpaa2-qdma/
+obj-$(CONFIG_INTEL_LDMA) += lgm/
 
 obj-y += mediatek/
 obj-y += qcom/

drivers/dma/at_hdmac.c

@@ -54,6 +54,25 @@ module_param(init_nr_desc_per_channel, uint, 0644);
 MODULE_PARM_DESC(init_nr_desc_per_channel,
 		 "initial descriptors per channel (default: 64)");
 
+/**
+ * struct at_dma_platform_data - Controller configuration parameters
+ * @nr_channels: Number of channels supported by hardware (max 8)
+ * @cap_mask: dma_capability flags supported by the platform
+ */
+struct at_dma_platform_data {
+	unsigned int	nr_channels;
+	dma_cap_mask_t  cap_mask;
+};
+
+/**
+ * struct at_dma_slave - Controller-specific information about a slave
+ * @dma_dev: required DMA master device
+ * @cfg: Platform-specific initializer for the CFG register
+ */
+struct at_dma_slave {
+	struct device		*dma_dev;
+	u32			cfg;
+};
 
 /* prototypes */
 static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx);

drivers/dma/at_hdmac_regs.h

@@ -7,8 +7,6 @@
 #ifndef AT_HDMAC_REGS_H
 #define	AT_HDMAC_REGS_H
 
-#include <linux/platform_data/dma-atmel.h>
-
 #define	AT_DMA_MAX_NR_CHANNELS	8
 
 
@@ -148,7 +146,31 @@
 #define	ATC_AUTO		(0x1 << 31)	/* Auto multiple buffer tx enable */
 
 /* Bitfields in CFG */
-/* are in at_hdmac.h */
+#define ATC_PER_MSB(h)	((0x30U & (h)) >> 4)	/* Extract most significant bits of a handshaking identifier */
+
+#define	ATC_SRC_PER(h)		(0xFU & (h))	/* Channel src rq associated with periph handshaking ifc h */
+#define	ATC_DST_PER(h)		((0xFU & (h)) <<  4)	/* Channel dst rq associated with periph handshaking ifc h */
+#define	ATC_SRC_REP		(0x1 <<  8)	/* Source Replay Mod */
+#define	ATC_SRC_H2SEL		(0x1 <<  9)	/* Source Handshaking Mod */
+#define		ATC_SRC_H2SEL_SW	(0x0 <<  9)
+#define		ATC_SRC_H2SEL_HW	(0x1 <<  9)
+#define	ATC_SRC_PER_MSB(h)	(ATC_PER_MSB(h) << 10)	/* Channel src rq (most significant bits) */
+#define	ATC_DST_REP		(0x1 << 12)	/* Destination Replay Mod */
+#define	ATC_DST_H2SEL		(0x1 << 13)	/* Destination Handshaking Mod */
+#define		ATC_DST_H2SEL_SW	(0x0 << 13)
+#define		ATC_DST_H2SEL_HW	(0x1 << 13)
+#define	ATC_DST_PER_MSB(h)	(ATC_PER_MSB(h) << 14)	/* Channel dst rq (most significant bits) */
+#define	ATC_SOD			(0x1 << 16)	/* Stop On Done */
+#define	ATC_LOCK_IF		(0x1 << 20)	/* Interface Lock */
+#define	ATC_LOCK_B		(0x1 << 21)	/* AHB Bus Lock */
+#define	ATC_LOCK_IF_L		(0x1 << 22)	/* Master Interface Arbiter Lock */
+#define		ATC_LOCK_IF_L_CHUNK	(0x0 << 22)
+#define		ATC_LOCK_IF_L_BUFFER	(0x1 << 22)
+#define	ATC_AHB_PROT_MASK	(0x7 << 24)	/* AHB Protection */
+#define	ATC_FIFOCFG_MASK	(0x3 << 28)	/* FIFO Request Configuration */
+#define		ATC_FIFOCFG_LARGESTBURST	(0x0 << 28)
+#define		ATC_FIFOCFG_HALFFIFO		(0x1 << 28)
+#define		ATC_FIFOCFG_ENOUGHSPACE		(0x2 << 28)
 
 /* Bitfields in SPIP */
 #define	ATC_SPIP_HOLE(x)	(0xFFFFU & (x))

drivers/dma/coh901318.h

@@ -1,141 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2007-2013 ST-Ericsson
- * DMA driver for COH 901 318
- * Author: Per Friden <per.friden@stericsson.com>
- */
-
-#ifndef COH901318_H
-#define COH901318_H
-
-#define MAX_DMA_PACKET_SIZE_SHIFT 11
-#define MAX_DMA_PACKET_SIZE (1 << MAX_DMA_PACKET_SIZE_SHIFT)
-
-struct device;
-
-struct coh901318_pool {
-	spinlock_t lock;
-	struct dma_pool *dmapool;
-	struct device *dev;
-
-#ifdef CONFIG_DEBUG_FS
-	int debugfs_pool_counter;
-#endif
-};
-
-/**
- * struct coh901318_lli - linked list item for DMAC
- * @control: control settings for DMAC
- * @src_addr: transfer source address
- * @dst_addr: transfer destination address
- * @link_addr:  physical address to next lli
- * @virt_link_addr: virtual address of next lli (only used by pool_free)
- * @phy_this: physical address of current lli (only used by pool_free)
- */
-struct coh901318_lli {
-	u32 control;
-	dma_addr_t src_addr;
-	dma_addr_t dst_addr;
-	dma_addr_t link_addr;
-
-	void *virt_link_addr;
-	dma_addr_t phy_this;
-};
-
-/**
- * coh901318_pool_create() - Creates an dma pool for lli:s
- * @pool: pool handle
- * @dev: dma device
- * @lli_nbr: number of lli:s in the pool
- * @algin: address alignemtn of lli:s
- * returns 0 on success otherwise none zero
- */
-int coh901318_pool_create(struct coh901318_pool *pool,
-			  struct device *dev,
-			  size_t lli_nbr, size_t align);
-
-/**
- * coh901318_pool_destroy() - Destroys the dma pool
- * @pool: pool handle
- * returns 0 on success otherwise none zero
- */
-int coh901318_pool_destroy(struct coh901318_pool *pool);
-
-/**
- * coh901318_lli_alloc() - Allocates a linked list
- *
- * @pool: pool handle
- * @len: length to list
- * return: none NULL if success otherwise NULL
- */
-struct coh901318_lli *
-coh901318_lli_alloc(struct coh901318_pool *pool,
-		    unsigned int len);
-
-/**
- * coh901318_lli_free() - Returns the linked list items to the pool
- * @pool: pool handle
- * @lli: reference to lli pointer to be freed
- */
-void coh901318_lli_free(struct coh901318_pool *pool,
-			struct coh901318_lli **lli);
-
-/**
- * coh901318_lli_fill_memcpy() - Prepares the lli:s for dma memcpy
- * @pool: pool handle
- * @lli: allocated lli
- * @src: src address
- * @size: transfer size
- * @dst: destination address
- * @ctrl_chained: ctrl for chained lli
- * @ctrl_last: ctrl for the last lli
- * returns number of CPU interrupts for the lli, negative on error.
- */
-int
-coh901318_lli_fill_memcpy(struct coh901318_pool *pool,
-			  struct coh901318_lli *lli,
-			  dma_addr_t src, unsigned int size,
-			  dma_addr_t dst, u32 ctrl_chained, u32 ctrl_last);
-
-/**
- * coh901318_lli_fill_single() - Prepares the lli:s for dma single transfer
- * @pool: pool handle
- * @lli: allocated lli
- * @buf: transfer buffer
- * @size: transfer size
- * @dev_addr: address of periphal
- * @ctrl_chained: ctrl for chained lli
- * @ctrl_last: ctrl for the last lli
- * @dir: direction of transfer (to or from device)
- * returns number of CPU interrupts for the lli, negative on error.
- */
-int
-coh901318_lli_fill_single(struct coh901318_pool *pool,
-			  struct coh901318_lli *lli,
-			  dma_addr_t buf, unsigned int size,
-			  dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl_last,
-			  enum dma_transfer_direction dir);
-
-/**
- * coh901318_lli_fill_single() - Prepares the lli:s for dma scatter list transfer
- * @pool: pool handle
- * @lli: allocated lli
- * @sg: scatter gather list
- * @nents: number of entries in sg
- * @dev_addr: address of periphal
- * @ctrl_chained: ctrl for chained lli
- * @ctrl: ctrl of middle lli
- * @ctrl_last: ctrl for the last lli
- * @dir: direction of transfer (to or from device)
- * @ctrl_irq_mask: ctrl mask for CPU interrupt
- * returns number of CPU interrupts for the lli, negative on error.
- */
-int
-coh901318_lli_fill_sg(struct coh901318_pool *pool,
-		      struct coh901318_lli *lli,
-		      struct scatterlist *sg, unsigned int nents,
-		      dma_addr_t dev_addr, u32 ctrl_chained,
-		      u32 ctrl, u32 ctrl_last,
-		      enum dma_transfer_direction dir, u32 ctrl_irq_mask);
-
-#endif /* COH901318_H */

drivers/dma/coh901318_lli.c

@@ -1,313 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * driver/dma/coh901318_lli.c
- *
- * Copyright (C) 2007-2009 ST-Ericsson
- * Support functions for handling lli for dma
- * Author: Per Friden <per.friden@stericsson.com>
- */
-
-#include <linux/spinlock.h>
-#include <linux/memory.h>
-#include <linux/gfp.h>
-#include <linux/dmapool.h>
-#include <linux/dmaengine.h>
-
-#include "coh901318.h"
-
-#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_U300_DEBUG))
-#define DEBUGFS_POOL_COUNTER_RESET(pool) (pool->debugfs_pool_counter = 0)
-#define DEBUGFS_POOL_COUNTER_ADD(pool, add) (pool->debugfs_pool_counter += add)
-#else
-#define DEBUGFS_POOL_COUNTER_RESET(pool)
-#define DEBUGFS_POOL_COUNTER_ADD(pool, add)
-#endif
-
-static struct coh901318_lli *
-coh901318_lli_next(struct coh901318_lli *data)
-{
-	if (data == NULL || data->link_addr == 0)
-		return NULL;
-
-	return (struct coh901318_lli *) data->virt_link_addr;
-}
-
-int coh901318_pool_create(struct coh901318_pool *pool,
-			  struct device *dev,
-			  size_t size, size_t align)
-{
-	spin_lock_init(&pool->lock);
-	pool->dev = dev;
-	pool->dmapool = dma_pool_create("lli_pool", dev, size, align, 0);
-
-	DEBUGFS_POOL_COUNTER_RESET(pool);
-	return 0;
-}
-
-int coh901318_pool_destroy(struct coh901318_pool *pool)
-{
-
-	dma_pool_destroy(pool->dmapool);
-	return 0;
-}
-
-struct coh901318_lli *
-coh901318_lli_alloc(struct coh901318_pool *pool, unsigned int len)
-{
-	int i;
-	struct coh901318_lli *head;
-	struct coh901318_lli *lli;
-	struct coh901318_lli *lli_prev;
-	dma_addr_t phy;
-
-	if (len == 0)
-		return NULL;
-
-	spin_lock(&pool->lock);
-
-	head = dma_pool_alloc(pool->dmapool, GFP_NOWAIT, &phy);
-
-	if (head == NULL)
-		goto err;
-
-	DEBUGFS_POOL_COUNTER_ADD(pool, 1);
-
-	lli = head;
-	lli->phy_this = phy;
-	lli->link_addr = 0x00000000;
-	lli->virt_link_addr = NULL;
-
-	for (i = 1; i < len; i++) {
-		lli_prev = lli;
-
-		lli = dma_pool_alloc(pool->dmapool, GFP_NOWAIT, &phy);
-
-		if (lli == NULL)
-			goto err_clean_up;
-
-		DEBUGFS_POOL_COUNTER_ADD(pool, 1);
-		lli->phy_this = phy;
-		lli->link_addr = 0x00000000;
-		lli->virt_link_addr = NULL;
-
-		lli_prev->link_addr = phy;
-		lli_prev->virt_link_addr = lli;
-	}
-
-	spin_unlock(&pool->lock);
-
-	return head;
-
- err:
-	spin_unlock(&pool->lock);
-	return NULL;
-
- err_clean_up:
-	lli_prev->link_addr = 0x00000000U;
-	spin_unlock(&pool->lock);
-	coh901318_lli_free(pool, &head);
-	return NULL;
-}
-
-void coh901318_lli_free(struct coh901318_pool *pool,
-			struct coh901318_lli **lli)
-{
-	struct coh901318_lli *l;
-	struct coh901318_lli *next;
-
-	if (lli == NULL)
-		return;
-
-	l = *lli;
-
-	if (l == NULL)
-		return;
-
-	spin_lock(&pool->lock);
-
-	while (l->link_addr) {
-		next = l->virt_link_addr;
-		dma_pool_free(pool->dmapool, l, l->phy_this);
-		DEBUGFS_POOL_COUNTER_ADD(pool, -1);
-		l = next;
-	}
-	dma_pool_free(pool->dmapool, l, l->phy_this);
-	DEBUGFS_POOL_COUNTER_ADD(pool, -1);
-
-	spin_unlock(&pool->lock);
-	*lli = NULL;
-}
-
-int
-coh901318_lli_fill_memcpy(struct coh901318_pool *pool,
-			  struct coh901318_lli *lli,
-			  dma_addr_t source, unsigned int size,
-			  dma_addr_t destination, u32 ctrl_chained,
-			  u32 ctrl_eom)
-{
-	int s = size;
-	dma_addr_t src = source;
-	dma_addr_t dst = destination;
-
-	lli->src_addr = src;
-	lli->dst_addr = dst;
-
-	while (lli->link_addr) {
-		lli->control = ctrl_chained | MAX_DMA_PACKET_SIZE;
-		lli->src_addr = src;
-		lli->dst_addr = dst;
-
-		s -= MAX_DMA_PACKET_SIZE;
-		lli = coh901318_lli_next(lli);
-
-		src += MAX_DMA_PACKET_SIZE;
-		dst += MAX_DMA_PACKET_SIZE;
-	}
-
-	lli->control = ctrl_eom | s;
-	lli->src_addr = src;
-	lli->dst_addr = dst;
-
-	return 0;
-}
-
-int
-coh901318_lli_fill_single(struct coh901318_pool *pool,
-			  struct coh901318_lli *lli,
-			  dma_addr_t buf, unsigned int size,
-			  dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl_eom,
-			  enum dma_transfer_direction dir)
-{
-	int s = size;
-	dma_addr_t src;
-	dma_addr_t dst;
-
-
-	if (dir == DMA_MEM_TO_DEV) {
-		src = buf;
-		dst = dev_addr;
-
-	} else if (dir == DMA_DEV_TO_MEM) {
-
-		src = dev_addr;
-		dst = buf;
-	} else {
-		return -EINVAL;
-	}
-
-	while (lli->link_addr) {
-		size_t block_size = MAX_DMA_PACKET_SIZE;
-		lli->control = ctrl_chained | MAX_DMA_PACKET_SIZE;
-
-		/* If we are on the next-to-final block and there will
-		 * be less than half a DMA packet left for the last
-		 * block, then we want to make this block a little
-		 * smaller to balance the sizes. This is meant to
-		 * avoid too small transfers if the buffer size is
-		 * (MAX_DMA_PACKET_SIZE*N + 1) */
-		if (s < (MAX_DMA_PACKET_SIZE + MAX_DMA_PACKET_SIZE/2))
-			block_size = MAX_DMA_PACKET_SIZE/2;
-
-		s -= block_size;
-		lli->src_addr = src;
-		lli->dst_addr = dst;
-
-		lli = coh901318_lli_next(lli);
-
-		if (dir == DMA_MEM_TO_DEV)
-			src += block_size;
-		else if (dir == DMA_DEV_TO_MEM)
-			dst += block_size;
-	}
-
-	lli->control = ctrl_eom | s;
-	lli->src_addr = src;
-	lli->dst_addr = dst;
-
-	return 0;
-}
-
-int
-coh901318_lli_fill_sg(struct coh901318_pool *pool,
-		      struct coh901318_lli *lli,
-		      struct scatterlist *sgl, unsigned int nents,
-		      dma_addr_t dev_addr, u32 ctrl_chained, u32 ctrl,
-		      u32 ctrl_last,
-		      enum dma_transfer_direction dir, u32 ctrl_irq_mask)
-{
-	int i;
-	struct scatterlist *sg;
-	u32 ctrl_sg;
-	dma_addr_t src = 0;
-	dma_addr_t dst = 0;
-	u32 bytes_to_transfer;
-	u32 elem_size;
-
-	if (lli == NULL)
-		goto err;
-
-	spin_lock(&pool->lock);
-
-	if (dir == DMA_MEM_TO_DEV)
-		dst = dev_addr;
-	else if (dir == DMA_DEV_TO_MEM)
-		src = dev_addr;
-	else
-		goto err;
-
-	for_each_sg(sgl, sg, nents, i) {
-		if (sg_is_chain(sg)) {
-			/* sg continues to the next sg-element don't
-			 * send ctrl_finish until the last
-			 * sg-element in the chain
-			 */
-			ctrl_sg = ctrl_chained;
-		} else if (i == nents - 1)
-			ctrl_sg = ctrl_last;
-		else
-			ctrl_sg = ctrl ? ctrl : ctrl_last;
-
-
-		if (dir == DMA_MEM_TO_DEV)
-			/* increment source address */
-			src = sg_dma_address(sg);
-		else
-			/* increment destination address */
-			dst = sg_dma_address(sg);
-
-		bytes_to_transfer = sg_dma_len(sg);
-
-		while (bytes_to_transfer) {
-			u32 val;
-
-			if (bytes_to_transfer > MAX_DMA_PACKET_SIZE) {
-				elem_size = MAX_DMA_PACKET_SIZE;
-				val = ctrl_chained;
-			} else {
-				elem_size = bytes_to_transfer;
-				val = ctrl_sg;
-			}
-
-			lli->control = val | elem_size;
-			lli->src_addr = src;
-			lli->dst_addr = dst;
-
-			if (dir == DMA_DEV_TO_MEM)
-				dst += elem_size;
-			else
-				src += elem_size;
-
-			BUG_ON(lli->link_addr & 3);
-
-			bytes_to_transfer -= elem_size;
-			lli = coh901318_lli_next(lli);
-		}
-
-	}
-	spin_unlock(&pool->lock);
-
-	return 0;
- err:
-	spin_unlock(&pool->lock);
-	return -EINVAL;
-}

drivers/dma/dma-jz4780.c

@@ -1004,6 +1004,18 @@ static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = {
 		 JZ_SOC_DATA_BREAK_LINKS,
 };
 
+static const struct jz4780_dma_soc_data jz4760_dma_soc_data = {
+	.nb_channels = 5,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
+static const struct jz4780_dma_soc_data jz4760b_dma_soc_data = {
+	.nb_channels = 5,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
 static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
 	.nb_channels = 6,
 	.transfer_ord_max = 6,
@@ -1031,6 +1043,8 @@ static const struct jz4780_dma_soc_data x1830_dma_soc_data = {
 static const struct of_device_id jz4780_dma_dt_match[] = {
 	{ .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data },
 	{ .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data },
+	{ .compatible = "ingenic,jz4760-dma", .data = &jz4760_dma_soc_data },
+	{ .compatible = "ingenic,jz4760b-dma", .data = &jz4760b_dma_soc_data },
 	{ .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data },
 	{ .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data },
 	{ .compatible = "ingenic,x1000-dma", .data = &x1000_dma_soc_data },

drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c

@@ -12,15 +12,20 @@
 #include <linux/device.h>
 #include <linux/dmaengine.h>
 #include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #include "dw-axi-dmac.h"
@@ -195,43 +200,56 @@ static inline const char *axi_chan_name(struct axi_dma_chan *chan)
 	return dma_chan_name(&chan->vc.chan);
 }
 
-static struct axi_dma_desc *axi_desc_get(struct axi_dma_chan *chan)
+static struct axi_dma_desc *axi_desc_alloc(u32 num)
 {
-	struct dw_axi_dma *dw = chan->chip->dw;
 	struct axi_dma_desc *desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->hw_desc = kcalloc(num, sizeof(*desc->hw_desc), GFP_NOWAIT);
+	if (!desc->hw_desc) {
+		kfree(desc);
+		return NULL;
+	}
+
+	return desc;
+}
+
+static struct axi_dma_lli *axi_desc_get(struct axi_dma_chan *chan,
+					dma_addr_t *addr)
+{
+	struct axi_dma_lli *lli;
 	dma_addr_t phys;
 
-	desc = dma_pool_zalloc(dw->desc_pool, GFP_NOWAIT, &phys);
-	if (unlikely(!desc)) {
+	lli = dma_pool_zalloc(chan->desc_pool, GFP_NOWAIT, &phys);
+	if (unlikely(!lli)) {
 		dev_err(chan2dev(chan), "%s: not enough descriptors available\n",
 			axi_chan_name(chan));
 		return NULL;
 	}
 
 	atomic_inc(&chan->descs_allocated);
-	INIT_LIST_HEAD(&desc->xfer_list);
-	desc->vd.tx.phys = phys;
-	desc->chan = chan;
+	*addr = phys;
 
-	return desc;
+	return lli;
 }
 
 static void axi_desc_put(struct axi_dma_desc *desc)
 {
 	struct axi_dma_chan *chan = desc->chan;
-	struct dw_axi_dma *dw = chan->chip->dw;
-	struct axi_dma_desc *child, *_next;
-	unsigned int descs_put = 0;
+	int count = atomic_read(&chan->descs_allocated);
+	struct axi_dma_hw_desc *hw_desc;
+	int descs_put;
 
-	list_for_each_entry_safe(child, _next, &desc->xfer_list, xfer_list) {
-		list_del(&child->xfer_list);
-		dma_pool_free(dw->desc_pool, child, child->vd.tx.phys);
-		descs_put++;
+	for (descs_put = 0; descs_put < count; descs_put++) {
+		hw_desc = &desc->hw_desc[descs_put];
+		dma_pool_free(chan->desc_pool, hw_desc->lli, hw_desc->llp);
 	}
 
-	dma_pool_free(dw->desc_pool, desc, desc->vd.tx.phys);
-	descs_put++;
-
+	kfree(desc->hw_desc);
+	kfree(desc);
 	atomic_sub(descs_put, &chan->descs_allocated);
 	dev_vdbg(chan2dev(chan), "%s: %d descs put, %d still allocated\n",
 		axi_chan_name(chan), descs_put,
@@ -248,19 +266,41 @@ dma_chan_tx_status(struct dma_chan *dchan, dma_cookie_t cookie,
 		  struct dma_tx_state *txstate)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
-	enum dma_status ret;
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	u32 completed_length;
+	unsigned long flags;
+	u32 completed_blocks;
+	size_t bytes = 0;
+	u32 length;
+	u32 len;
 
-	ret = dma_cookie_status(dchan, cookie, txstate);
+	status = dma_cookie_status(dchan, cookie, txstate);
+	if (status == DMA_COMPLETE || !txstate)
+		return status;
 
-	if (chan->is_paused && ret == DMA_IN_PROGRESS)
-		ret = DMA_PAUSED;
+	spin_lock_irqsave(&chan->vc.lock, flags);
 
-	return ret;
+	vdesc = vchan_find_desc(&chan->vc, cookie);
+	if (vdesc) {
+		length = vd_to_axi_desc(vdesc)->length;
+		completed_blocks = vd_to_axi_desc(vdesc)->completed_blocks;
+		len = vd_to_axi_desc(vdesc)->hw_desc[0].len;
+		completed_length = completed_blocks * len;
+		bytes = length - completed_length;
+	} else {
+		bytes = vd_to_axi_desc(vdesc)->length;
+	}
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+	dma_set_residue(txstate, bytes);
+
+	return status;
 }
 
-static void write_desc_llp(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_llp(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.llp = cpu_to_le64(adr);
+	desc->lli->llp = cpu_to_le64(adr);
 }
 
 static void write_chan_llp(struct axi_dma_chan *chan, dma_addr_t adr)
@@ -268,6 +308,29 @@ static void write_chan_llp(struct axi_dma_chan *chan, dma_addr_t adr)
 	axi_chan_iowrite64(chan, CH_LLP, adr);
 }
 
+static void dw_axi_dma_set_byte_halfword(struct axi_dma_chan *chan, bool set)
+{
+	u32 offset = DMAC_APB_BYTE_WR_CH_EN;
+	u32 reg_width, val;
+
+	if (!chan->chip->apb_regs) {
+		dev_dbg(chan->chip->dev, "apb_regs not initialized\n");
+		return;
+	}
+
+	reg_width = __ffs(chan->config.dst_addr_width);
+	if (reg_width == DWAXIDMAC_TRANS_WIDTH_16)
+		offset = DMAC_APB_HALFWORD_WR_CH_EN;
+
+	val = ioread32(chan->chip->apb_regs + offset);
+
+	if (set)
+		val |= BIT(chan->id);
+	else
+		val &= ~BIT(chan->id);
+
+	iowrite32(val, chan->chip->apb_regs + offset);
+}
 /* Called in chan locked context */
 static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 				      struct axi_dma_desc *first)
@@ -293,9 +356,26 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 	       priority << CH_CFG_H_PRIORITY_POS |
 	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_DST_POS |
 	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_SRC_POS);
+	switch (chan->direction) {
+	case DMA_MEM_TO_DEV:
+		dw_axi_dma_set_byte_halfword(chan, true);
+		reg |= (chan->config.device_fc ?
+			DWAXIDMAC_TT_FC_MEM_TO_PER_DST :
+			DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC)
+			<< CH_CFG_H_TT_FC_POS;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg |= (chan->config.device_fc ?
+			DWAXIDMAC_TT_FC_PER_TO_MEM_SRC :
+			DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC)
+			<< CH_CFG_H_TT_FC_POS;
+		break;
+	default:
+		break;
+	}
 	axi_chan_iowrite32(chan, CH_CFG_H, reg);
 
-	write_chan_llp(chan, first->vd.tx.phys | lms);
+	write_chan_llp(chan, first->hw_desc[0].llp | lms);
 
 	irq_mask = DWAXIDMAC_IRQ_DMA_TRF | DWAXIDMAC_IRQ_ALL_ERR;
 	axi_chan_irq_sig_set(chan, irq_mask);
@@ -333,6 +413,13 @@ static void dma_chan_issue_pending(struct dma_chan *dchan)
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 }
 
+static void dw_axi_dma_synchronize(struct dma_chan *dchan)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+
+	vchan_synchronize(&chan->vc);
+}
+
 static int dma_chan_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
@@ -344,6 +431,15 @@ static int dma_chan_alloc_chan_resources(struct dma_chan *dchan)
 		return -EBUSY;
 	}
 
+	/* LLI address must be aligned to a 64-byte boundary */
+	chan->desc_pool = dma_pool_create(dev_name(chan2dev(chan)),
+					  chan->chip->dev,
+					  sizeof(struct axi_dma_lli),
+					  64, 0);
+	if (!chan->desc_pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
 	dev_vdbg(dchan2dev(dchan), "%s: allocating\n", axi_chan_name(chan));
 
 	pm_runtime_get(chan->chip->dev);
@@ -365,6 +461,8 @@ static void dma_chan_free_chan_resources(struct dma_chan *dchan)
 
 	vchan_free_chan_resources(&chan->vc);
 
+	dma_pool_destroy(chan->desc_pool);
+	chan->desc_pool = NULL;
 	dev_vdbg(dchan2dev(dchan),
 		 "%s: free resources, descriptor still allocated: %u\n",
 		 axi_chan_name(chan), atomic_read(&chan->descs_allocated));
@@ -372,73 +470,398 @@ static void dma_chan_free_chan_resources(struct dma_chan *dchan)
 	pm_runtime_put(chan->chip->dev);
 }
 
+static void dw_axi_dma_set_hw_channel(struct axi_dma_chip *chip,
+				      u32 handshake_num, bool set)
+{
+	unsigned long start = 0;
+	unsigned long reg_value;
+	unsigned long reg_mask;
+	unsigned long reg_set;
+	unsigned long mask;
+	unsigned long val;
+
+	if (!chip->apb_regs) {
+		dev_dbg(chip->dev, "apb_regs not initialized\n");
+		return;
+	}
+
+	/*
+	 * An unused DMA channel has a default value of 0x3F.
+	 * Lock the DMA channel by assign a handshake number to the channel.
+	 * Unlock the DMA channel by assign 0x3F to the channel.
+	 */
+	if (set) {
+		reg_set = UNUSED_CHANNEL;
+		val = handshake_num;
+	} else {
+		reg_set = handshake_num;
+		val = UNUSED_CHANNEL;
+	}
+
+	reg_value = lo_hi_readq(chip->apb_regs + DMAC_APB_HW_HS_SEL_0);
+
+	for_each_set_clump8(start, reg_mask, &reg_value, 64) {
+		if (reg_mask == reg_set) {
+			mask = GENMASK_ULL(start + 7, start);
+			reg_value &= ~mask;
+			reg_value |= rol64(val, start);
+			lo_hi_writeq(reg_value,
+				     chip->apb_regs + DMAC_APB_HW_HS_SEL_0);
+			break;
+		}
+	}
+}
+
 /*
  * If DW_axi_dmac sees CHx_CTL.ShadowReg_Or_LLI_Last bit of the fetched LLI
  * as 1, it understands that the current block is the final block in the
  * transfer and completes the DMA transfer operation at the end of current
  * block transfer.
  */
-static void set_desc_last(struct axi_dma_desc *desc)
+static void set_desc_last(struct axi_dma_hw_desc *desc)
 {
 	u32 val;
 
-	val = le32_to_cpu(desc->lli.ctl_hi);
+	val = le32_to_cpu(desc->lli->ctl_hi);
 	val |= CH_CTL_H_LLI_LAST;
-	desc->lli.ctl_hi = cpu_to_le32(val);
+	desc->lli->ctl_hi = cpu_to_le32(val);
 }
 
-static void write_desc_sar(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_sar(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.sar = cpu_to_le64(adr);
+	desc->lli->sar = cpu_to_le64(adr);
 }
 
-static void write_desc_dar(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_dar(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.dar = cpu_to_le64(adr);
+	desc->lli->dar = cpu_to_le64(adr);
 }
 
-static void set_desc_src_master(struct axi_dma_desc *desc)
+static void set_desc_src_master(struct axi_dma_hw_desc *desc)
 {
 	u32 val;
 
 	/* Select AXI0 for source master */
-	val = le32_to_cpu(desc->lli.ctl_lo);
+	val = le32_to_cpu(desc->lli->ctl_lo);
 	val &= ~CH_CTL_L_SRC_MAST;
-	desc->lli.ctl_lo = cpu_to_le32(val);
+	desc->lli->ctl_lo = cpu_to_le32(val);
 }
 
-static void set_desc_dest_master(struct axi_dma_desc *desc)
+static void set_desc_dest_master(struct axi_dma_hw_desc *hw_desc,
+				 struct axi_dma_desc *desc)
 {
 	u32 val;
 
 	/* Select AXI1 for source master if available */
-	val = le32_to_cpu(desc->lli.ctl_lo);
+	val = le32_to_cpu(hw_desc->lli->ctl_lo);
 	if (desc->chan->chip->dw->hdata->nr_masters > 1)
 		val |= CH_CTL_L_DST_MAST;
 	else
 		val &= ~CH_CTL_L_DST_MAST;
 
-	desc->lli.ctl_lo = cpu_to_le32(val);
+	hw_desc->lli->ctl_lo = cpu_to_le32(val);
+}
+
+static int dw_axi_dma_set_hw_desc(struct axi_dma_chan *chan,
+				  struct axi_dma_hw_desc *hw_desc,
+				  dma_addr_t mem_addr, size_t len)
+{
+	unsigned int data_width = BIT(chan->chip->dw->hdata->m_data_width);
+	unsigned int reg_width;
+	unsigned int mem_width;
+	dma_addr_t device_addr;
+	size_t axi_block_ts;
+	size_t block_ts;
+	u32 ctllo, ctlhi;
+	u32 burst_len;
+
+	axi_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+
+	mem_width = __ffs(data_width | mem_addr | len);
+	if (mem_width > DWAXIDMAC_TRANS_WIDTH_32)
+		mem_width = DWAXIDMAC_TRANS_WIDTH_32;
+
+	if (!IS_ALIGNED(mem_addr, 4)) {
+		dev_err(chan->chip->dev, "invalid buffer alignment\n");
+		return -EINVAL;
+	}
+
+	switch (chan->direction) {
+	case DMA_MEM_TO_DEV:
+		reg_width = __ffs(chan->config.dst_addr_width);
+		device_addr = chan->config.dst_addr;
+		ctllo = reg_width << CH_CTL_L_DST_WIDTH_POS |
+			mem_width << CH_CTL_L_SRC_WIDTH_POS |
+			DWAXIDMAC_CH_CTL_L_NOINC << CH_CTL_L_DST_INC_POS |
+			DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_SRC_INC_POS;
+		block_ts = len >> mem_width;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg_width = __ffs(chan->config.src_addr_width);
+		device_addr = chan->config.src_addr;
+		ctllo = reg_width << CH_CTL_L_SRC_WIDTH_POS |
+			mem_width << CH_CTL_L_DST_WIDTH_POS |
+			DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_DST_INC_POS |
+			DWAXIDMAC_CH_CTL_L_NOINC << CH_CTL_L_SRC_INC_POS;
+		block_ts = len >> reg_width;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (block_ts > axi_block_ts)
+		return -EINVAL;
+
+	hw_desc->lli = axi_desc_get(chan, &hw_desc->llp);
+	if (unlikely(!hw_desc->lli))
+		return -ENOMEM;
+
+	ctlhi = CH_CTL_H_LLI_VALID;
+
+	if (chan->chip->dw->hdata->restrict_axi_burst_len) {
+		burst_len = chan->chip->dw->hdata->axi_rw_burst_len;
+		ctlhi |= CH_CTL_H_ARLEN_EN | CH_CTL_H_AWLEN_EN |
+			 burst_len << CH_CTL_H_ARLEN_POS |
+			 burst_len << CH_CTL_H_AWLEN_POS;
+	}
+
+	hw_desc->lli->ctl_hi = cpu_to_le32(ctlhi);
+
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		write_desc_sar(hw_desc, mem_addr);
+		write_desc_dar(hw_desc, device_addr);
+	} else {
+		write_desc_sar(hw_desc, device_addr);
+		write_desc_dar(hw_desc, mem_addr);
+	}
+
+	hw_desc->lli->block_ts_lo = cpu_to_le32(block_ts - 1);
+
+	ctllo |= DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_DST_MSIZE_POS |
+		 DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_SRC_MSIZE_POS;
+	hw_desc->lli->ctl_lo = cpu_to_le32(ctllo);
+
+	set_desc_src_master(hw_desc);
+
+	hw_desc->len = len;
+	return 0;
+}
+
+static size_t calculate_block_len(struct axi_dma_chan *chan,
+				  dma_addr_t dma_addr, size_t buf_len,
+				  enum dma_transfer_direction direction)
+{
+	u32 data_width, reg_width, mem_width;
+	size_t axi_block_ts, block_len;
+
+	axi_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		data_width = BIT(chan->chip->dw->hdata->m_data_width);
+		mem_width = __ffs(data_width | dma_addr | buf_len);
+		if (mem_width > DWAXIDMAC_TRANS_WIDTH_32)
+			mem_width = DWAXIDMAC_TRANS_WIDTH_32;
+
+		block_len = axi_block_ts << mem_width;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg_width = __ffs(chan->config.src_addr_width);
+		block_len = axi_block_ts << reg_width;
+		break;
+	default:
+		block_len = 0;
+	}
+
+	return block_len;
+}
+
+static struct dma_async_tx_descriptor *
+dw_axi_dma_chan_prep_cyclic(struct dma_chan *dchan, dma_addr_t dma_addr,
+			    size_t buf_len, size_t period_len,
+			    enum dma_transfer_direction direction,
+			    unsigned long flags)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	dma_addr_t src_addr = dma_addr;
+	u32 num_periods, num_segments;
+	size_t axi_block_len;
+	u32 total_segments;
+	u32 segment_len;
+	unsigned int i;
+	int status;
+	u64 llp = 0;
+	u8 lms = 0; /* Select AXI0 master for LLI fetching */
+
+	num_periods = buf_len / period_len;
+
+	axi_block_len = calculate_block_len(chan, dma_addr, buf_len, direction);
+	if (axi_block_len == 0)
+		return NULL;
+
+	num_segments = DIV_ROUND_UP(period_len, axi_block_len);
+	segment_len = DIV_ROUND_UP(period_len, num_segments);
+
+	total_segments = num_periods * num_segments;
+
+	desc = axi_desc_alloc(total_segments);
+	if (unlikely(!desc))
+		goto err_desc_get;
+
+	chan->direction = direction;
+	desc->chan = chan;
+	chan->cyclic = true;
+	desc->length = 0;
+	desc->period_len = period_len;
+
+	for (i = 0; i < total_segments; i++) {
+		hw_desc = &desc->hw_desc[i];
+
+		status = dw_axi_dma_set_hw_desc(chan, hw_desc, src_addr,
+						segment_len);
+		if (status < 0)
+			goto err_desc_get;
+
+		desc->length += hw_desc->len;
+		/* Set end-of-link to the linked descriptor, so that cyclic
+		 * callback function can be triggered during interrupt.
+		 */
+		set_desc_last(hw_desc);
+
+		src_addr += segment_len;
+	}
+
+	llp = desc->hw_desc[0].llp;
+
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--total_segments];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (total_segments);
+
+	dw_axi_dma_set_hw_channel(chan->chip, chan->hw_handshake_num, true);
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
+
+err_desc_get:
+	if (desc)
+		axi_desc_put(desc);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+dw_axi_dma_chan_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
+			      unsigned int sg_len,
+			      enum dma_transfer_direction direction,
+			      unsigned long flags, void *context)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	u32 num_segments, segment_len;
+	unsigned int loop = 0;
+	struct scatterlist *sg;
+	size_t axi_block_len;
+	u32 len, num_sgs = 0;
+	unsigned int i;
+	dma_addr_t mem;
+	int status;
+	u64 llp = 0;
+	u8 lms = 0; /* Select AXI0 master for LLI fetching */
+
+	if (unlikely(!is_slave_direction(direction) || !sg_len))
+		return NULL;
+
+	mem = sg_dma_address(sgl);
+	len = sg_dma_len(sgl);
+
+	axi_block_len = calculate_block_len(chan, mem, len, direction);
+	if (axi_block_len == 0)
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i)
+		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), axi_block_len);
+
+	desc = axi_desc_alloc(num_sgs);
+	if (unlikely(!desc))
+		goto err_desc_get;
+
+	desc->chan = chan;
+	desc->length = 0;
+	chan->direction = direction;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		mem = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		num_segments = DIV_ROUND_UP(sg_dma_len(sg), axi_block_len);
+		segment_len = DIV_ROUND_UP(sg_dma_len(sg), num_segments);
+
+		do {
+			hw_desc = &desc->hw_desc[loop++];
+			status = dw_axi_dma_set_hw_desc(chan, hw_desc, mem, segment_len);
+			if (status < 0)
+				goto err_desc_get;
+
+			desc->length += hw_desc->len;
+			len -= segment_len;
+			mem += segment_len;
+		} while (len >= segment_len);
+	}
+
+	/* Set end-of-link to the last link descriptor of list */
+	set_desc_last(&desc->hw_desc[num_sgs - 1]);
+
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--num_sgs];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (num_sgs);
+
+	dw_axi_dma_set_hw_channel(chan->chip, chan->hw_handshake_num, true);
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
+
+err_desc_get:
+	if (desc)
+		axi_desc_put(desc);
+
+	return NULL;
 }
 
 static struct dma_async_tx_descriptor *
 dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 			 dma_addr_t src_adr, size_t len, unsigned long flags)
 {
-	struct axi_dma_desc *first = NULL, *desc = NULL, *prev = NULL;
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
 	size_t block_ts, max_block_ts, xfer_len;
-	u32 xfer_width, reg;
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	u32 xfer_width, reg, num;
+	u64 llp = 0;
 	u8 lms = 0; /* Select AXI0 master for LLI fetching */
 
 	dev_dbg(chan2dev(chan), "%s: memcpy: src: %pad dst: %pad length: %zd flags: %#lx",
 		axi_chan_name(chan), &src_adr, &dst_adr, len, flags);
 
 	max_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+	xfer_width = axi_chan_get_xfer_width(chan, src_adr, dst_adr, len);
+	num = DIV_ROUND_UP(len, max_block_ts << xfer_width);
+	desc = axi_desc_alloc(num);
+	if (unlikely(!desc))
+		goto err_desc_get;
 
+	desc->chan = chan;
+	num = 0;
+	desc->length = 0;
 	while (len) {
 		xfer_len = len;
 
+		hw_desc = &desc->hw_desc[num];
 		/*
 		 * Take care for the alignment.
 		 * Actually source and destination widths can be different, but
@@ -457,13 +880,13 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 			xfer_len = max_block_ts << xfer_width;
 		}
 
-		desc = axi_desc_get(chan);
-		if (unlikely(!desc))
+		hw_desc->lli = axi_desc_get(chan, &hw_desc->llp);
+		if (unlikely(!hw_desc->lli))
 			goto err_desc_get;
 
-		write_desc_sar(desc, src_adr);
-		write_desc_dar(desc, dst_adr);
-		desc->lli.block_ts_lo = cpu_to_le32(block_ts - 1);
+		write_desc_sar(hw_desc, src_adr);
+		write_desc_dar(hw_desc, dst_adr);
+		hw_desc->lli->block_ts_lo = cpu_to_le32(block_ts - 1);
 
 		reg = CH_CTL_H_LLI_VALID;
 		if (chan->chip->dw->hdata->restrict_axi_burst_len) {
@@ -474,7 +897,7 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 				CH_CTL_H_AWLEN_EN |
 				burst_len << CH_CTL_H_AWLEN_POS);
 		}
-		desc->lli.ctl_hi = cpu_to_le32(reg);
+		hw_desc->lli->ctl_hi = cpu_to_le32(reg);
 
 		reg = (DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_DST_MSIZE_POS |
 		       DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_SRC_MSIZE_POS |
@@ -482,62 +905,68 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 		       xfer_width << CH_CTL_L_SRC_WIDTH_POS |
 		       DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_DST_INC_POS |
 		       DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_SRC_INC_POS);
-		desc->lli.ctl_lo = cpu_to_le32(reg);
+		hw_desc->lli->ctl_lo = cpu_to_le32(reg);
 
-		set_desc_src_master(desc);
-		set_desc_dest_master(desc);
-
-		/* Manage transfer list (xfer_list) */
-		if (!first) {
-			first = desc;
-		} else {
-			list_add_tail(&desc->xfer_list, &first->xfer_list);
-			write_desc_llp(prev, desc->vd.tx.phys | lms);
-		}
-		prev = desc;
+		set_desc_src_master(hw_desc);
+		set_desc_dest_master(hw_desc, desc);
 
+		hw_desc->len = xfer_len;
+		desc->length += hw_desc->len;
 		/* update the length and addresses for the next loop cycle */
 		len -= xfer_len;
 		dst_adr += xfer_len;
 		src_adr += xfer_len;
+		num++;
 	}
 
-	/* Total len of src/dest sg == 0, so no descriptor were allocated */
-	if (unlikely(!first))
-		return NULL;
-
 	/* Set end-of-link to the last link descriptor of list */
-	set_desc_last(desc);
+	set_desc_last(&desc->hw_desc[num - 1]);
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--num];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (num);
 
-	return vchan_tx_prep(&chan->vc, &first->vd, flags);
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
 
 err_desc_get:
-	if (first)
-		axi_desc_put(first);
+	if (desc)
+		axi_desc_put(desc);
 	return NULL;
 }
 
+static int dw_axi_dma_chan_slave_config(struct dma_chan *dchan,
+					struct dma_slave_config *config)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+
+	memcpy(&chan->config, config, sizeof(*config));
+
+	return 0;
+}
+
 static void axi_chan_dump_lli(struct axi_dma_chan *chan,
-			      struct axi_dma_desc *desc)
+			      struct axi_dma_hw_desc *desc)
 {
 	dev_err(dchan2dev(&chan->vc.chan),
 		"SAR: 0x%llx DAR: 0x%llx LLP: 0x%llx BTS 0x%x CTL: 0x%x:%08x",
-		le64_to_cpu(desc->lli.sar),
-		le64_to_cpu(desc->lli.dar),
-		le64_to_cpu(desc->lli.llp),
-		le32_to_cpu(desc->lli.block_ts_lo),
-		le32_to_cpu(desc->lli.ctl_hi),
-		le32_to_cpu(desc->lli.ctl_lo));
+		le64_to_cpu(desc->lli->sar),
+		le64_to_cpu(desc->lli->dar),
+		le64_to_cpu(desc->lli->llp),
+		le32_to_cpu(desc->lli->block_ts_lo),
+		le32_to_cpu(desc->lli->ctl_hi),
+		le32_to_cpu(desc->lli->ctl_lo));
 }
 
 static void axi_chan_list_dump_lli(struct axi_dma_chan *chan,
 				   struct axi_dma_desc *desc_head)
 {
-	struct axi_dma_desc *desc;
+	int count = atomic_read(&chan->descs_allocated);
+	int i;
 
-	axi_chan_dump_lli(chan, desc_head);
-	list_for_each_entry(desc, &desc_head->xfer_list, xfer_list)
-		axi_chan_dump_lli(chan, desc);
+	for (i = 0; i < count; i++)
+		axi_chan_dump_lli(chan, &desc_head->hw_desc[i]);
 }
 
 static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
@@ -570,8 +999,13 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
 
 static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 {
+	int count = atomic_read(&chan->descs_allocated);
+	struct axi_dma_hw_desc *hw_desc;
+	struct axi_dma_desc *desc;
 	struct virt_dma_desc *vd;
 	unsigned long flags;
+	u64 llp;
+	int i;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	if (unlikely(axi_chan_is_hw_enable(chan))) {
@@ -582,12 +1016,34 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 
 	/* The completed descriptor currently is in the head of vc list */
 	vd = vchan_next_desc(&chan->vc);
-	/* Remove the completed descriptor from issued list before completing */
-	list_del(&vd->node);
-	vchan_cookie_complete(vd);
 
-	/* Submit queued descriptors after processing the completed ones */
-	axi_chan_start_first_queued(chan);
+	if (chan->cyclic) {
+		desc = vd_to_axi_desc(vd);
+		if (desc) {
+			llp = lo_hi_readq(chan->chan_regs + CH_LLP);
+			for (i = 0; i < count; i++) {
+				hw_desc = &desc->hw_desc[i];
+				if (hw_desc->llp == llp) {
+					axi_chan_irq_clear(chan, hw_desc->lli->status_lo);
+					hw_desc->lli->ctl_hi |= CH_CTL_H_LLI_VALID;
+					desc->completed_blocks = i;
+
+					if (((hw_desc->len * (i + 1)) % desc->period_len) == 0)
+						vchan_cyclic_callback(vd);
+					break;
+				}
+			}
+
+			axi_chan_enable(chan);
+		}
+	} else {
+		/* Remove the completed descriptor from issued list before completing */
+		list_del(&vd->node);
+		vchan_cookie_complete(vd);
+
+		/* Submit queued descriptors after processing the completed ones */
+		axi_chan_start_first_queued(chan);
+	}
 
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 }
@@ -627,15 +1083,31 @@ static irqreturn_t dw_axi_dma_interrupt(int irq, void *dev_id)
 static int dma_chan_terminate_all(struct dma_chan *dchan)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	u32 chan_active = BIT(chan->id) << DMAC_CHAN_EN_SHIFT;
 	unsigned long flags;
+	u32 val;
+	int ret;
 	LIST_HEAD(head);
 
-	spin_lock_irqsave(&chan->vc.lock, flags);
-
 	axi_chan_disable(chan);
 
+	ret = readl_poll_timeout_atomic(chan->chip->regs + DMAC_CHEN, val,
+					!(val & chan_active), 1000, 10000);
+	if (ret == -ETIMEDOUT)
+		dev_warn(dchan2dev(dchan),
+			 "%s failed to stop\n", axi_chan_name(chan));
+
+	if (chan->direction != DMA_MEM_TO_MEM)
+		dw_axi_dma_set_hw_channel(chan->chip,
+					  chan->hw_handshake_num, false);
+	if (chan->direction == DMA_MEM_TO_DEV)
+		dw_axi_dma_set_byte_halfword(chan, false);
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
 	vchan_get_all_descriptors(&chan->vc, &head);
 
+	chan->cyclic = false;
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
 	vchan_dma_desc_free_list(&chan->vc, &head);
@@ -746,6 +1218,22 @@ static int __maybe_unused axi_dma_runtime_resume(struct device *dev)
 	return axi_dma_resume(chip);
 }
 
+static struct dma_chan *dw_axi_dma_of_xlate(struct of_phandle_args *dma_spec,
+					    struct of_dma *ofdma)
+{
+	struct dw_axi_dma *dw = ofdma->of_dma_data;
+	struct axi_dma_chan *chan;
+	struct dma_chan *dchan;
+
+	dchan = dma_get_any_slave_channel(&dw->dma);
+	if (!dchan)
+		return NULL;
+
+	chan = dchan_to_axi_dma_chan(dchan);
+	chan->hw_handshake_num = dma_spec->args[0];
+	return dchan;
+}
+
 static int parse_device_properties(struct axi_dma_chip *chip)
 {
 	struct device *dev = chip->dev;
@@ -816,6 +1304,7 @@ static int parse_device_properties(struct axi_dma_chip *chip)
 
 static int dw_probe(struct platform_device *pdev)
 {
+	struct device_node *node = pdev->dev.of_node;
 	struct axi_dma_chip *chip;
 	struct resource *mem;
 	struct dw_axi_dma *dw;
@@ -848,6 +1337,12 @@ static int dw_probe(struct platform_device *pdev)
 	if (IS_ERR(chip->regs))
 		return PTR_ERR(chip->regs);
 
+	if (of_device_is_compatible(node, "intel,kmb-axi-dma")) {
+		chip->apb_regs = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(chip->apb_regs))
+			return PTR_ERR(chip->apb_regs);
+	}
+
 	chip->core_clk = devm_clk_get(chip->dev, "core-clk");
 	if (IS_ERR(chip->core_clk))
 		return PTR_ERR(chip->core_clk);
@@ -870,13 +1365,6 @@ static int dw_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	/* Lli address must be aligned to a 64-byte boundary */
-	dw->desc_pool = dmam_pool_create(KBUILD_MODNAME, chip->dev,
-					 sizeof(struct axi_dma_desc), 64, 0);
-	if (!dw->desc_pool) {
-		dev_err(chip->dev, "No memory for descriptors dma pool\n");
-		return -ENOMEM;
-	}
 
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < hdata->nr_channels; i++) {
@@ -893,13 +1381,16 @@ static int dw_probe(struct platform_device *pdev)
 
 	/* Set capabilities */
 	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	dma_cap_set(DMA_CYCLIC, dw->dma.cap_mask);
 
 	/* DMA capabilities */
 	dw->dma.chancnt = hdata->nr_channels;
 	dw->dma.src_addr_widths = AXI_DMA_BUSWIDTHS;
 	dw->dma.dst_addr_widths = AXI_DMA_BUSWIDTHS;
 	dw->dma.directions = BIT(DMA_MEM_TO_MEM);
-	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dw->dma.directions |= BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
+	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
 	dw->dma.dev = chip->dev;
 	dw->dma.device_tx_status = dma_chan_tx_status;
@@ -912,7 +1403,18 @@ static int dw_probe(struct platform_device *pdev)
 	dw->dma.device_free_chan_resources = dma_chan_free_chan_resources;
 
 	dw->dma.device_prep_dma_memcpy = dma_chan_prep_dma_memcpy;
+	dw->dma.device_synchronize = dw_axi_dma_synchronize;
+	dw->dma.device_config = dw_axi_dma_chan_slave_config;
+	dw->dma.device_prep_slave_sg = dw_axi_dma_chan_prep_slave_sg;
+	dw->dma.device_prep_dma_cyclic = dw_axi_dma_chan_prep_cyclic;
 
+	/*
+	 * Synopsis DesignWare AxiDMA datasheet mentioned Maximum
+	 * supported blocks is 1024. Device register width is 4 bytes.
+	 * Therefore, set constraint to 1024 * 4.
+	 */
+	dw->dma.dev->dma_parms = &dw->dma_parms;
+	dma_set_max_seg_size(&pdev->dev, MAX_BLOCK_SIZE);
 	platform_set_drvdata(pdev, chip);
 
 	pm_runtime_enable(chip->dev);
@@ -935,6 +1437,13 @@ static int dw_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_pm_disable;
 
+	/* Register with OF helpers for DMA lookups */
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 dw_axi_dma_of_xlate, dw);
+	if (ret < 0)
+		dev_warn(&pdev->dev,
+			 "Failed to register OF DMA controller, fallback to MEM_TO_MEM mode\n");
+
 	dev_info(chip->dev, "DesignWare AXI DMA Controller, %d channels\n",
 		 dw->hdata->nr_channels);
 
@@ -968,6 +1477,8 @@ static int dw_remove(struct platform_device *pdev)
 
 	devm_free_irq(chip->dev, chip->irq, chip);
 
+	of_dma_controller_free(chip->dev->of_node);
+
 	list_for_each_entry_safe(chan, _chan, &dw->dma.channels,
 			vc.chan.device_node) {
 		list_del(&chan->vc.chan.device_node);
@@ -983,6 +1494,7 @@ static const struct dev_pm_ops dw_axi_dma_pm_ops = {
 
 static const struct of_device_id dw_dma_of_id_table[] = {
 	{ .compatible = "snps,axi-dma-1.01a" },
+	{ .compatible = "intel,kmb-axi-dma" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);

drivers/dma/dw-axi-dmac/dw-axi-dmac.h

@@ -37,10 +37,16 @@ struct axi_dma_chan {
 	struct axi_dma_chip		*chip;
 	void __iomem			*chan_regs;
 	u8				id;
+	u8				hw_handshake_num;
 	atomic_t			descs_allocated;
 
+	struct dma_pool			*desc_pool;
 	struct virt_dma_chan		vc;
 
+	struct axi_dma_desc		*desc;
+	struct dma_slave_config		config;
+	enum dma_transfer_direction	direction;
+	bool				cyclic;
 	/* these other elements are all protected by vc.lock */
 	bool				is_paused;
 };
@@ -48,7 +54,7 @@ struct axi_dma_chan {
 struct dw_axi_dma {
 	struct dma_device	dma;
 	struct dw_axi_dma_hcfg	*hdata;
-	struct dma_pool		*desc_pool;
+	struct device_dma_parameters	dma_parms;
 
 	/* channels */
 	struct axi_dma_chan	*chan;
@@ -58,6 +64,7 @@ struct axi_dma_chip {
 	struct device		*dev;
 	int			irq;
 	void __iomem		*regs;
+	void __iomem		*apb_regs;
 	struct clk		*core_clk;
 	struct clk		*cfgr_clk;
 	struct dw_axi_dma	*dw;
@@ -80,12 +87,20 @@ struct __packed axi_dma_lli {
 	__le32		reserved_hi;
 };
 
+struct axi_dma_hw_desc {
+	struct axi_dma_lli	*lli;
+	dma_addr_t		llp;
+	u32			len;
+};
+
 struct axi_dma_desc {
-	struct axi_dma_lli		lli;
+	struct axi_dma_hw_desc	*hw_desc;
 
 	struct virt_dma_desc		vd;
 	struct axi_dma_chan		*chan;
-	struct list_head		xfer_list;
+	u32				completed_blocks;
+	u32				length;
+	u32				period_len;
 };
 
 static inline struct device *dchan2dev(struct dma_chan *dchan)
@@ -157,6 +172,19 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan)
 #define CH_INTSIGNAL_ENA	0x090 /* R/W Chan Interrupt Signal Enable */
 #define CH_INTCLEAR		0x098 /* W Chan Interrupt Clear */
 
+/* These Apb registers are used by Intel KeemBay SoC */
+#define DMAC_APB_CFG		0x000 /* DMAC Apb Configuration Register */
+#define DMAC_APB_STAT		0x004 /* DMAC Apb Status Register */
+#define DMAC_APB_DEBUG_STAT_0	0x008 /* DMAC Apb Debug Status Register 0 */
+#define DMAC_APB_DEBUG_STAT_1	0x00C /* DMAC Apb Debug Status Register 1 */
+#define DMAC_APB_HW_HS_SEL_0	0x010 /* DMAC Apb HW HS register 0 */
+#define DMAC_APB_HW_HS_SEL_1	0x014 /* DMAC Apb HW HS register 1 */
+#define DMAC_APB_LPI		0x018 /* DMAC Apb Low Power Interface Reg */
+#define DMAC_APB_BYTE_WR_CH_EN	0x01C /* DMAC Apb Byte Write Enable */
+#define DMAC_APB_HALFWORD_WR_CH_EN	0x020 /* DMAC Halfword write enables */
+
+#define UNUSED_CHANNEL		0x3F /* Set unused DMA channel to 0x3F */
+#define MAX_BLOCK_SIZE		0x1000 /* 1024 blocks * 4 bytes data width */
 
 /* DMAC_CFG */
 #define DMAC_EN_POS			0

drivers/dma/fsldma.c

@@ -1214,6 +1214,7 @@ static int fsldma_of_probe(struct platform_device *op)
 {
 	struct fsldma_device *fdev;
 	struct device_node *child;
+	unsigned int i;
 	int err;
 
 	fdev = kzalloc(sizeof(*fdev), GFP_KERNEL);
@@ -1292,6 +1293,10 @@ static int fsldma_of_probe(struct platform_device *op)
 	return 0;
 
 out_free_fdev:
+	for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) {
+		if (fdev->chan[i])
+			fsl_dma_chan_remove(fdev->chan[i]);
+	}
 	irq_dispose_mapping(fdev->irq);
 	iounmap(fdev->regs);
 out_free:
@@ -1314,6 +1319,7 @@ static int fsldma_of_remove(struct platform_device *op)
 		if (fdev->chan[i])
 			fsl_dma_chan_remove(fdev->chan[i]);
 	}
+	irq_dispose_mapping(fdev->irq);
 
 	iounmap(fdev->regs);
 	kfree(fdev);

drivers/dma/hsu/pci.c

@@ -26,22 +26,12 @@
 static irqreturn_t hsu_pci_irq(int irq, void *dev)
 {
 	struct hsu_dma_chip *chip = dev;
-	struct pci_dev *pdev = to_pci_dev(chip->dev);
 	u32 dmaisr;
 	u32 status;
 	unsigned short i;
 	int ret = 0;
 	int err;
 
-	/*
-	 * On Intel Tangier B0 and Anniedale the interrupt line, disregarding
-	 * to have different numbers, is shared between HSU DMA and UART IPs.
-	 * Thus on such SoCs we are expecting that IRQ handler is called in
-	 * UART driver only.
-	 */
-	if (pdev->device == PCI_DEVICE_ID_INTEL_MRFLD_HSU_DMA)
-		return IRQ_HANDLED;
-
 	dmaisr = readl(chip->regs + HSU_PCI_DMAISR);
 	for (i = 0; i < chip->hsu->nr_channels; i++) {
 		if (dmaisr & 0x1) {
@@ -105,6 +95,17 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_register_irq;
 
+	/*
+	 * On Intel Tangier B0 and Anniedale the interrupt line, disregarding
+	 * to have different numbers, is shared between HSU DMA and UART IPs.
+	 * Thus on such SoCs we are expecting that IRQ handler is called in
+	 * UART driver only. Instead of handling the spurious interrupt
+	 * from HSU DMA here and waste CPU time and delay HSU UART interrupt
+	 * handling, disable the interrupt entirely.
+	 */
+	if (pdev->device == PCI_DEVICE_ID_INTEL_MRFLD_HSU_DMA)
+		disable_irq_nosync(chip->irq);
+
 	pci_set_drvdata(pdev, chip);
 
 	return 0;

drivers/dma/idxd/dma.c

@@ -165,6 +165,7 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	INIT_LIST_HEAD(&dma->channels);
 	dma->dev = &idxd->pdev->dev;
 
+	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
 	dma_cap_set(DMA_COMPLETION_NO_ORDER, dma->cap_mask);
 	dma->device_release = idxd_dma_release;
 

drivers/dma/idxd/init.c

@@ -26,12 +26,16 @@ MODULE_VERSION(IDXD_DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Intel Corporation");
 
+static bool sva = true;
+module_param(sva, bool, 0644);
+MODULE_PARM_DESC(sva, "Toggle SVA support on/off");
+
 #define DRV_NAME "idxd"
 
 bool support_enqcmd;
 
 static struct idr idxd_idrs[IDXD_TYPE_MAX];
-static struct mutex idxd_idr_lock;
+static DEFINE_MUTEX(idxd_idr_lock);
 
 static struct pci_device_id idxd_pci_tbl[] = {
 	/* DSA ver 1.0 platforms */
@@ -341,12 +345,14 @@ static int idxd_probe(struct idxd_device *idxd)
 
 	dev_dbg(dev, "IDXD reset complete\n");
 
-	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM)) {
+	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM) && sva) {
 		rc = idxd_enable_system_pasid(idxd);
 		if (rc < 0)
 			dev_warn(dev, "Failed to enable PASID. No SVA support: %d\n", rc);
 		else
 			set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
+	} else if (!sva) {
+		dev_warn(dev, "User forced SVA off via module param.\n");
 	}
 
 	idxd_read_caps(idxd);
@@ -547,7 +553,6 @@ static int __init idxd_init_module(void)
 	else
 		support_enqcmd = true;
 
-	mutex_init(&idxd_idr_lock);
 	for (i = 0; i < IDXD_TYPE_MAX; i++)
 		idr_init(&idxd_idrs[i]);
 

drivers/dma/imx-sdma.c

@@ -1952,8 +1952,6 @@ static struct dma_chan *sdma_xlate(struct of_phandle_args *dma_spec,
 
 static int sdma_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-			of_match_device(sdma_dt_ids, &pdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	struct device_node *spba_bus;
 	const char *fw_name;
@@ -1961,17 +1959,9 @@ static int sdma_probe(struct platform_device *pdev)
 	int irq;
 	struct resource *iores;
 	struct resource spba_res;
-	struct sdma_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int i;
 	struct sdma_engine *sdma;
 	s32 *saddr_arr;
-	const struct sdma_driver_data *drvdata = NULL;
-
-	drvdata = of_id->data;
-	if (!drvdata) {
-		dev_err(&pdev->dev, "unable to find driver data\n");
-		return -EINVAL;
-	}
 
 	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret)
@@ -1984,7 +1974,7 @@ static int sdma_probe(struct platform_device *pdev)
 	spin_lock_init(&sdma->channel_0_lock);
 
 	sdma->dev = &pdev->dev;
-	sdma->drvdata = drvdata;
+	sdma->drvdata = of_device_get_match_data(sdma->dev);
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -2063,8 +2053,6 @@ static int sdma_probe(struct platform_device *pdev)
 
 	if (sdma->drvdata->script_addrs)
 		sdma_add_scripts(sdma, sdma->drvdata->script_addrs);
-	if (pdata && pdata->script_addrs)
-		sdma_add_scripts(sdma, pdata->script_addrs);
 
 	sdma->dma_device.dev = &pdev->dev;
 
@@ -2110,30 +2098,18 @@ static int sdma_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * Kick off firmware loading as the very last step:
-	 * attempt to load firmware only if we're not on the error path, because
-	 * the firmware callback requires a fully functional and allocated sdma
-	 * instance.
+	 * Because that device tree does not encode ROM script address,
+	 * the RAM script in firmware is mandatory for device tree
+	 * probe, otherwise it fails.
 	 */
-	if (pdata) {
-		ret = sdma_get_firmware(sdma, pdata->fw_name);
-		if (ret)
-			dev_warn(&pdev->dev, "failed to get firmware from platform data\n");
+	ret = of_property_read_string(np, "fsl,sdma-ram-script-name",
+				      &fw_name);
+	if (ret) {
+		dev_warn(&pdev->dev, "failed to get firmware name\n");
 	} else {
-		/*
-		 * Because that device tree does not encode ROM script address,
-		 * the RAM script in firmware is mandatory for device tree
-		 * probe, otherwise it fails.
-		 */
-		ret = of_property_read_string(np, "fsl,sdma-ram-script-name",
-					      &fw_name);
-		if (ret) {
-			dev_warn(&pdev->dev, "failed to get firmware name\n");
-		} else {
-			ret = sdma_get_firmware(sdma, fw_name);
-			if (ret)
-				dev_warn(&pdev->dev, "failed to get firmware from device tree\n");
-		}
+		ret = sdma_get_firmware(sdma, fw_name);
+		if (ret)
+			dev_warn(&pdev->dev, "failed to get firmware from device tree\n");
 	}
 
 	return 0;

drivers/dma/lgm/Kconfig

@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config INTEL_LDMA
+	bool "Lightning Mountain centralized DMA controllers"
+	depends on X86 || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for Intel Lightning Mountain SOC DMA controllers.
+	  These controllers provide DMA capabilities for a variety of on-chip
+	  devices such as HSNAND and GSWIP (Gigabit Switch IP).

drivers/dma/lgm/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_INTEL_LDMA)	+= lgm-dma.o

drivers/dma/mmp_pdma.c

@@ -18,7 +18,6 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/of.h>
-#include <linux/dma/mmp-pdma.h>
 
 #include "dmaengine.h"
 
@@ -1148,19 +1147,6 @@ static struct platform_driver mmp_pdma_driver = {
 	.remove		= mmp_pdma_remove,
 };
 
-bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param)
-{
-	struct mmp_pdma_chan *c = to_mmp_pdma_chan(chan);
-
-	if (chan->device->dev->driver != &mmp_pdma_driver.driver)
-		return false;
-
-	c->drcmr = *(unsigned int *)param;
-
-	return true;
-}
-EXPORT_SYMBOL_GPL(mmp_pdma_filter_fn);
-
 module_platform_driver(mmp_pdma_driver);
 
 MODULE_DESCRIPTION("MARVELL MMP Peripheral DMA Driver");

drivers/dma/owl-dma.c

@@ -1080,8 +1080,9 @@ static struct dma_chan *owl_dma_of_xlate(struct of_phandle_args *dma_spec,
 }
 
 static const struct of_device_id owl_dma_match[] = {
-	{ .compatible = "actions,s900-dma", .data = (void *)S900_DMA,},
+	{ .compatible = "actions,s500-dma", .data = (void *)S900_DMA,},
 	{ .compatible = "actions,s700-dma", .data = (void *)S700_DMA,},
+	{ .compatible = "actions,s900-dma", .data = (void *)S900_DMA,},
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, owl_dma_match);
@@ -1245,6 +1246,7 @@ static int owl_dma_remove(struct platform_device *pdev)
 	owl_dma_free(od);
 
 	clk_disable_unprepare(od->clk);
+	dma_pool_destroy(od->lli_pool);
 
 	return 0;
 }

drivers/dma/qcom/bam_dma.c

@@ -1270,13 +1270,13 @@ static int bam_dma_probe(struct platform_device *pdev)
 			dev_err(bdev->dev, "num-ees unspecified in dt\n");
 	}
 
-	bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
-	if (IS_ERR(bdev->bamclk)) {
-		if (!bdev->controlled_remotely)
-			return PTR_ERR(bdev->bamclk);
+	if (bdev->controlled_remotely)
+		bdev->bamclk = devm_clk_get_optional(bdev->dev, "bam_clk");
+	else
+		bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
 
-		bdev->bamclk = NULL;
-	}
+	if (IS_ERR(bdev->bamclk))
+		return PTR_ERR(bdev->bamclk);
 
 	ret = clk_prepare_enable(bdev->bamclk);
 	if (ret) {
@@ -1350,7 +1350,7 @@ static int bam_dma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unregister_dma;
 
-	if (bdev->controlled_remotely) {
+	if (!bdev->bamclk) {
 		pm_runtime_disable(&pdev->dev);
 		return 0;
 	}
@@ -1438,10 +1438,10 @@ static int __maybe_unused bam_dma_suspend(struct device *dev)
 {
 	struct bam_device *bdev = dev_get_drvdata(dev);
 
-	if (!bdev->controlled_remotely)
+	if (bdev->bamclk) {
 		pm_runtime_force_suspend(dev);
-
-	clk_unprepare(bdev->bamclk);
+		clk_unprepare(bdev->bamclk);
+	}
 
 	return 0;
 }
@@ -1451,12 +1451,13 @@ static int __maybe_unused bam_dma_resume(struct device *dev)
 	struct bam_device *bdev = dev_get_drvdata(dev);
 	int ret;
 
-	ret = clk_prepare(bdev->bamclk);
-	if (ret)
-		return ret;
+	if (bdev->bamclk) {
+		ret = clk_prepare(bdev->bamclk);
+		if (ret)
+			return ret;
 
-	if (!bdev->controlled_remotely)
 		pm_runtime_force_resume(dev);
+	}
 
 	return 0;
 }

drivers/dma/qcom/gpi.c

@@ -584,7 +584,7 @@ static inline void gpi_write_reg_field(struct gpii *gpii, void __iomem *addr,
 	gpi_write_reg(gpii, addr, val);
 }
 
-static inline void
+static __always_inline void
 gpi_update_reg(struct gpii *gpii, u32 offset, u32 mask, u32 val)
 {
 	void __iomem *addr = gpii->regs + offset;
@@ -1700,7 +1700,7 @@ static int gpi_create_i2c_tre(struct gchan *chan, struct gpi_desc *desc,
 
 		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
 		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
-	};
+	}
 
 	for (i = 0; i < tre_idx; i++)
 		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],

drivers/dma/sh/rcar-dmac.c

@@ -189,7 +189,8 @@ struct rcar_dmac_chan {
  * struct rcar_dmac - R-Car Gen2 DMA Controller
  * @engine: base DMA engine object
  * @dev: the hardware device
- * @iomem: remapped I/O memory base
+ * @dmac_base: remapped base register block
+ * @chan_base: remapped channel register block (optional)
  * @n_channels: number of available channels
  * @channels: array of DMAC channels
  * @channels_mask: bitfield of which DMA channels are managed by this driver
@@ -198,7 +199,8 @@ struct rcar_dmac_chan {
 struct rcar_dmac {
 	struct dma_device engine;
 	struct device *dev;
-	void __iomem *iomem;
+	void __iomem *dmac_base;
+	void __iomem *chan_base;
 
 	unsigned int n_channels;
 	struct rcar_dmac_chan *channels;
@@ -209,6 +211,10 @@ struct rcar_dmac {
 
 #define to_rcar_dmac(d)		container_of(d, struct rcar_dmac, engine)
 
+#define for_each_rcar_dmac_chan(i, dmac, chan)						\
+	for (i = 0, chan = &(dmac)->channels[0]; i < (dmac)->n_channels; i++, chan++)	\
+		if (!((dmac)->channels_mask & BIT(i))) continue; else
+
 /*
  * struct rcar_dmac_of_data - This driver's OF data
  * @chan_offset_base: DMAC channels base offset
@@ -230,7 +236,7 @@ struct rcar_dmac_of_data {
 #define RCAR_DMAOR_PRI_ROUND_ROBIN	(3 << 8)
 #define RCAR_DMAOR_AE			(1 << 2)
 #define RCAR_DMAOR_DME			(1 << 0)
-#define RCAR_DMACHCLR			0x0080
+#define RCAR_DMACHCLR			0x0080	/* Not on R-Car V3U */
 #define RCAR_DMADPSEC			0x00a0
 
 #define RCAR_DMASAR			0x0000
@@ -293,6 +299,9 @@ struct rcar_dmac_of_data {
 #define RCAR_DMAFIXDAR			0x0014
 #define RCAR_DMAFIXDPBASE		0x0060
 
+/* For R-Car V3U */
+#define RCAR_V3U_DMACHCLR		0x0100
+
 /* Hardcode the MEMCPY transfer size to 4 bytes. */
 #define RCAR_DMAC_MEMCPY_XFER_SIZE	4
 
@@ -303,17 +312,17 @@ struct rcar_dmac_of_data {
 static void rcar_dmac_write(struct rcar_dmac *dmac, u32 reg, u32 data)
 {
 	if (reg == RCAR_DMAOR)
-		writew(data, dmac->iomem + reg);
+		writew(data, dmac->dmac_base + reg);
 	else
-		writel(data, dmac->iomem + reg);
+		writel(data, dmac->dmac_base + reg);
 }
 
 static u32 rcar_dmac_read(struct rcar_dmac *dmac, u32 reg)
 {
 	if (reg == RCAR_DMAOR)
-		return readw(dmac->iomem + reg);
+		return readw(dmac->dmac_base + reg);
 	else
-		return readl(dmac->iomem + reg);
+		return readl(dmac->dmac_base + reg);
 }
 
 static u32 rcar_dmac_chan_read(struct rcar_dmac_chan *chan, u32 reg)
@@ -332,6 +341,28 @@ static void rcar_dmac_chan_write(struct rcar_dmac_chan *chan, u32 reg, u32 data)
 		writel(data, chan->iomem + reg);
 }
 
+static void rcar_dmac_chan_clear(struct rcar_dmac *dmac,
+				 struct rcar_dmac_chan *chan)
+{
+	if (dmac->chan_base)
+		rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+	else
+		rcar_dmac_write(dmac, RCAR_DMACHCLR, BIT(chan->index));
+}
+
+static void rcar_dmac_chan_clear_all(struct rcar_dmac *dmac)
+{
+	struct rcar_dmac_chan *chan;
+	unsigned int i;
+
+	if (dmac->chan_base) {
+		for_each_rcar_dmac_chan(i, dmac, chan)
+			rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+	} else {
+		rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
+	}
+}
+
 /* -----------------------------------------------------------------------------
  * Initialization and configuration
  */
@@ -447,7 +478,7 @@ static int rcar_dmac_init(struct rcar_dmac *dmac)
 	u16 dmaor;
 
 	/* Clear all channels and enable the DMAC globally. */
-	rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
+	rcar_dmac_chan_clear_all(dmac);
 	rcar_dmac_write(dmac, RCAR_DMAOR,
 			RCAR_DMAOR_PRI_FIXED | RCAR_DMAOR_DME);
 
@@ -817,15 +848,11 @@ static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
 
 static void rcar_dmac_stop_all_chan(struct rcar_dmac *dmac)
 {
+	struct rcar_dmac_chan *chan;
 	unsigned int i;
 
 	/* Stop all channels. */
-	for (i = 0; i < dmac->n_channels; ++i) {
-		struct rcar_dmac_chan *chan = &dmac->channels[i];
-
-		if (!(dmac->channels_mask & BIT(i)))
-			continue;
-
+	for_each_rcar_dmac_chan(i, dmac, chan) {
 		/* Stop and reinitialize the channel. */
 		spin_lock_irq(&chan->lock);
 		rcar_dmac_chan_halt(chan);
@@ -1566,7 +1593,7 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 		 * because channel is already stopped in error case.
 		 * We need to clear register and check DE bit as recovery.
 		 */
-		rcar_dmac_write(dmac, RCAR_DMACHCLR, 1 << chan->index);
+		rcar_dmac_chan_clear(dmac, chan);
 		rcar_dmac_chcr_de_barrier(chan);
 		reinit = true;
 		goto spin_lock_end;
@@ -1732,9 +1759,7 @@ static const struct dev_pm_ops rcar_dmac_pm = {
  */
 
 static int rcar_dmac_chan_probe(struct rcar_dmac *dmac,
-				struct rcar_dmac_chan *rchan,
-				const struct rcar_dmac_of_data *data,
-				unsigned int index)
+				struct rcar_dmac_chan *rchan)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
 	struct dma_chan *chan = &rchan->chan;
@@ -1742,9 +1767,6 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac,
 	char *irqname;
 	int ret;
 
-	rchan->index = index;
-	rchan->iomem = dmac->iomem + data->chan_offset_base +
-		       data->chan_offset_stride * index;
 	rchan->mid_rid = -EINVAL;
 
 	spin_lock_init(&rchan->lock);
@@ -1756,13 +1778,13 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac,
 	INIT_LIST_HEAD(&rchan->desc.wait);
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	sprintf(pdev_irqname, "ch%u", rchan->index);
 	rchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (rchan->irq < 0)
 		return -ENODEV;
 
 	irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:%u",
-				 dev_name(dmac->dev), index);
+				 dev_name(dmac->dev), rchan->index);
 	if (!irqname)
 		return -ENOMEM;
 
@@ -1828,9 +1850,11 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 		DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES |
 		DMA_SLAVE_BUSWIDTH_8_BYTES | DMA_SLAVE_BUSWIDTH_16_BYTES |
 		DMA_SLAVE_BUSWIDTH_32_BYTES | DMA_SLAVE_BUSWIDTH_64_BYTES;
-	struct dma_device *engine;
-	struct rcar_dmac *dmac;
 	const struct rcar_dmac_of_data *data;
+	struct rcar_dmac_chan *chan;
+	struct dma_device *engine;
+	void __iomem *chan_base;
+	struct rcar_dmac *dmac;
 	unsigned int i;
 	int ret;
 
@@ -1868,9 +1892,24 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	/* Request resources. */
-	dmac->iomem = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(dmac->iomem))
-		return PTR_ERR(dmac->iomem);
+	dmac->dmac_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(dmac->dmac_base))
+		return PTR_ERR(dmac->dmac_base);
+
+	if (!data->chan_offset_base) {
+		dmac->chan_base = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(dmac->chan_base))
+			return PTR_ERR(dmac->chan_base);
+
+		chan_base = dmac->chan_base;
+	} else {
+		chan_base = dmac->dmac_base + data->chan_offset_base;
+	}
+
+	for_each_rcar_dmac_chan(i, dmac, chan) {
+		chan->index = i;
+		chan->iomem = chan_base + i * data->chan_offset_stride;
+	}
 
 	/* Enable runtime PM and initialize the device. */
 	pm_runtime_enable(&pdev->dev);
@@ -1916,11 +1955,8 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 
 	INIT_LIST_HEAD(&engine->channels);
 
-	for (i = 0; i < dmac->n_channels; ++i) {
-		if (!(dmac->channels_mask & BIT(i)))
-			continue;
-
-		ret = rcar_dmac_chan_probe(dmac, &dmac->channels[i], data, i);
+	for_each_rcar_dmac_chan(i, dmac, chan) {
+		ret = rcar_dmac_chan_probe(dmac, chan);
 		if (ret < 0)
 			goto error;
 	}
@@ -1968,14 +2004,22 @@ static void rcar_dmac_shutdown(struct platform_device *pdev)
 }
 
 static const struct rcar_dmac_of_data rcar_dmac_data = {
-	.chan_offset_base = 0x8000,
-	.chan_offset_stride = 0x80,
+	.chan_offset_base	= 0x8000,
+	.chan_offset_stride	= 0x80,
+};
+
+static const struct rcar_dmac_of_data rcar_v3u_dmac_data = {
+	.chan_offset_base	= 0x0,
+	.chan_offset_stride	= 0x1000,
 };
 
 static const struct of_device_id rcar_dmac_of_ids[] = {
 	{
 		.compatible = "renesas,rcar-dmac",
 		.data = &rcar_dmac_data,
+	}, {
+		.compatible = "renesas,dmac-r8a779a0",
+		.data = &rcar_v3u_dmac_data,
 	},
 	{ /* Sentinel */ }
 };

drivers/dma/ste_dma40.c

@@ -78,7 +78,7 @@ static int dma40_memcpy_channels[] = {
 	DB8500_DMA_MEMCPY_EV_5,
 };
 
-/* Default configuration for physcial memcpy */
+/* Default configuration for physical memcpy */
 static const struct stedma40_chan_cfg dma40_memcpy_conf_phy = {
 	.mode = STEDMA40_MODE_PHYSICAL,
 	.dir = DMA_MEM_TO_MEM,

drivers/dma/ti/k3-udma.c

@@ -121,6 +121,11 @@ struct udma_oes_offsets {
 #define UDMA_FLAG_PDMA_ACC32		BIT(0)
 #define UDMA_FLAG_PDMA_BURST		BIT(1)
 #define UDMA_FLAG_TDTYPE		BIT(2)
+#define UDMA_FLAG_BURST_SIZE		BIT(3)
+#define UDMA_FLAGS_J7_CLASS		(UDMA_FLAG_PDMA_ACC32 | \
+					 UDMA_FLAG_PDMA_BURST | \
+					 UDMA_FLAG_TDTYPE | \
+					 UDMA_FLAG_BURST_SIZE)
 
 struct udma_match_data {
 	enum k3_dma_type type;
@@ -128,6 +133,7 @@ struct udma_match_data {
 	bool enable_memcpy_support;
 	u32 flags;
 	u32 statictr_z_mask;
+	u8 burst_size[3];
 };
 
 struct udma_soc_data {
@@ -436,6 +442,18 @@ static void k3_configure_chan_coherency(struct dma_chan *chan, u32 asel)
 	}
 }
 
+static u8 udma_get_chan_tpl_index(struct udma_tpl *tpl_map, int chan_id)
+{
+	int i;
+
+	for (i = 0; i < tpl_map->levels; i++) {
+		if (chan_id >= tpl_map->start_idx[i])
+			return i;
+	}
+
+	return 0;
+}
+
 static void udma_reset_uchan(struct udma_chan *uc)
 {
 	memset(&uc->config, 0, sizeof(uc->config));
@@ -1811,13 +1829,21 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
 	struct udma_tchan *tchan = uc->tchan;
 	struct udma_rchan *rchan = uc->rchan;
-	int ret = 0;
+	u8 burst_size = 0;
+	int ret;
+	u8 tpl;
 
 	/* Non synchronized - mem to mem type of transfer */
 	int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring);
 	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
 	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
 
+	if (ud->match_data->flags & UDMA_FLAG_BURST_SIZE) {
+		tpl = udma_get_chan_tpl_index(&ud->tchan_tpl, tchan->id);
+
+		burst_size = ud->match_data->burst_size[tpl];
+	}
+
 	req_tx.valid_params = TISCI_UDMA_TCHAN_VALID_PARAMS;
 	req_tx.nav_id = tisci_rm->tisci_dev_id;
 	req_tx.index = tchan->id;
@@ -1825,6 +1851,10 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 	req_tx.tx_fetch_size = sizeof(struct cppi5_desc_hdr_t) >> 2;
 	req_tx.txcq_qnum = tc_ring;
 	req_tx.tx_atype = ud->atype;
+	if (burst_size) {
+		req_tx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
+		req_tx.tx_burst_size = burst_size;
+	}
 
 	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
 	if (ret) {
@@ -1839,6 +1869,10 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 	req_rx.rxcq_qnum = tc_ring;
 	req_rx.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR;
 	req_rx.rx_atype = ud->atype;
+	if (burst_size) {
+		req_rx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
+		req_rx.rx_burst_size = burst_size;
+	}
 
 	ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx);
 	if (ret)
@@ -1854,12 +1888,24 @@ static int bcdma_tisci_m2m_channel_config(struct udma_chan *uc)
 	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
 	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
 	struct udma_bchan *bchan = uc->bchan;
-	int ret = 0;
+	u8 burst_size = 0;
+	int ret;
+	u8 tpl;
+
+	if (ud->match_data->flags & UDMA_FLAG_BURST_SIZE) {
+		tpl = udma_get_chan_tpl_index(&ud->bchan_tpl, bchan->id);
+
+		burst_size = ud->match_data->burst_size[tpl];
+	}
 
 	req_tx.valid_params = TISCI_BCDMA_BCHAN_VALID_PARAMS;
 	req_tx.nav_id = tisci_rm->tisci_dev_id;
 	req_tx.extended_ch_type = TI_SCI_RM_BCDMA_EXTENDED_CH_TYPE_BCHAN;
 	req_tx.index = bchan->id;
+	if (burst_size) {
+		req_tx.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID;
+		req_tx.tx_burst_size = burst_size;
+	}
 
 	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
 	if (ret)
@@ -1877,7 +1923,7 @@ static int udma_tisci_tx_channel_config(struct udma_chan *uc)
 	int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring);
 	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
 	u32 mode, fetch_size;
-	int ret = 0;
+	int ret;
 
 	if (uc->config.pkt_mode) {
 		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
@@ -1918,7 +1964,7 @@ static int bcdma_tisci_tx_channel_config(struct udma_chan *uc)
 	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
 	struct udma_tchan *tchan = uc->tchan;
 	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
-	int ret = 0;
+	int ret;
 
 	req_tx.valid_params = TISCI_BCDMA_TCHAN_VALID_PARAMS;
 	req_tx.nav_id = tisci_rm->tisci_dev_id;
@@ -1951,7 +1997,7 @@ static int udma_tisci_rx_channel_config(struct udma_chan *uc)
 	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
 	struct ti_sci_msg_rm_udmap_flow_cfg flow_req = { 0 };
 	u32 mode, fetch_size;
-	int ret = 0;
+	int ret;
 
 	if (uc->config.pkt_mode) {
 		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
@@ -2028,7 +2074,7 @@ static int bcdma_tisci_rx_channel_config(struct udma_chan *uc)
 	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
 	struct udma_rchan *rchan = uc->rchan;
 	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
-	int ret = 0;
+	int ret;
 
 	req_rx.valid_params = TISCI_BCDMA_RCHAN_VALID_PARAMS;
 	req_rx.nav_id = tisci_rm->tisci_dev_id;
@@ -2048,7 +2094,7 @@ static int pktdma_tisci_rx_channel_config(struct udma_chan *uc)
 	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
 	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
 	struct ti_sci_msg_rm_udmap_flow_cfg flow_req = { 0 };
-	int ret = 0;
+	int ret;
 
 	req_rx.valid_params = TISCI_BCDMA_RCHAN_VALID_PARAMS;
 	req_rx.nav_id = tisci_rm->tisci_dev_id;
@@ -4168,6 +4214,11 @@ static struct udma_match_data am654_main_data = {
 	.psil_base = 0x1000,
 	.enable_memcpy_support = true,
 	.statictr_z_mask = GENMASK(11, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* H Channels */
+		0, /* No UH Channels */
+	},
 };
 
 static struct udma_match_data am654_mcu_data = {
@@ -4175,38 +4226,63 @@ static struct udma_match_data am654_mcu_data = {
 	.psil_base = 0x6000,
 	.enable_memcpy_support = false,
 	.statictr_z_mask = GENMASK(11, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* H Channels */
+		0, /* No UH Channels */
+	},
 };
 
 static struct udma_match_data j721e_main_data = {
 	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x1000,
 	.enable_memcpy_support = true,
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.flags = UDMA_FLAGS_J7_CLASS,
 	.statictr_z_mask = GENMASK(23, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES, /* H Channels */
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES, /* UH Channels */
+	},
 };
 
 static struct udma_match_data j721e_mcu_data = {
 	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x6000,
 	.enable_memcpy_support = false, /* MEM_TO_MEM is slow via MCU UDMA */
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.flags = UDMA_FLAGS_J7_CLASS,
 	.statictr_z_mask = GENMASK(23, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES, /* H Channels */
+		0, /* No UH Channels */
+	},
 };
 
 static struct udma_match_data am64_bcdma_data = {
 	.type = DMA_TYPE_BCDMA,
 	.psil_base = 0x2000, /* for tchan and rchan, not applicable to bchan */
 	.enable_memcpy_support = true, /* Supported via bchan */
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.flags = UDMA_FLAGS_J7_CLASS,
 	.statictr_z_mask = GENMASK(23, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		0, /* No H Channels */
+		0, /* No UH Channels */
+	},
 };
 
 static struct udma_match_data am64_pktdma_data = {
 	.type = DMA_TYPE_PKTDMA,
 	.psil_base = 0x1000,
 	.enable_memcpy_support = false, /* PKTDMA does not support MEM_TO_MEM */
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.flags = UDMA_FLAGS_J7_CLASS,
 	.statictr_z_mask = GENMASK(23, 0),
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		0, /* No H Channels */
+		0, /* No UH Channels */
+	},
 };
 
 static const struct of_device_id udma_of_match[] = {
@@ -4306,6 +4382,7 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
 		ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2);
 		ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2);
 		ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2);
+		ud->rflow_cnt = ud->rchan_cnt;
 		break;
 	case DMA_TYPE_PKTDMA:
 		cap4 = udma_read(ud->mmrs[MMR_GCFG], 0x30);
@@ -5046,6 +5123,34 @@ static void udma_dbg_summary_show(struct seq_file *s,
 }
 #endif /* CONFIG_DEBUG_FS */
 
+static enum dmaengine_alignment udma_get_copy_align(struct udma_dev *ud)
+{
+	const struct udma_match_data *match_data = ud->match_data;
+	u8 tpl;
+
+	if (!match_data->enable_memcpy_support)
+		return DMAENGINE_ALIGN_8_BYTES;
+
+	/* Get the highest TPL level the device supports for memcpy */
+	if (ud->bchan_cnt)
+		tpl = udma_get_chan_tpl_index(&ud->bchan_tpl, 0);
+	else if (ud->tchan_cnt)
+		tpl = udma_get_chan_tpl_index(&ud->tchan_tpl, 0);
+	else
+		return DMAENGINE_ALIGN_8_BYTES;
+
+	switch (match_data->burst_size[tpl]) {
+	case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES:
+		return DMAENGINE_ALIGN_256_BYTES;
+	case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES:
+		return DMAENGINE_ALIGN_128_BYTES;
+	case TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES:
+	fallthrough;
+	default:
+		return DMAENGINE_ALIGN_64_BYTES;
+	}
+}
+
 #define TI_UDMAC_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
 				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				 BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
@@ -5202,7 +5307,6 @@ static int udma_probe(struct platform_device *pdev)
 	ud->ddev.dst_addr_widths = TI_UDMAC_BUSWIDTHS;
 	ud->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	ud->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
-	ud->ddev.copy_align = DMAENGINE_ALIGN_8_BYTES;
 	ud->ddev.desc_metadata_modes = DESC_METADATA_CLIENT |
 				       DESC_METADATA_ENGINE;
 	if (ud->match_data->enable_memcpy_support &&
@@ -5284,6 +5388,9 @@ static int udma_probe(struct platform_device *pdev)
 		INIT_DELAYED_WORK(&uc->tx_drain.work, udma_check_tx_completion);
 	}
 
+	/* Configure the copy_align to the maximum burst size the device supports */
+	ud->ddev.copy_align = udma_get_copy_align(ud);
+
 	ret = dma_async_device_register(&ud->ddev);
 	if (ret) {
 		dev_err(dev, "failed to register slave DMA engine: %d\n", ret);

drivers/dma/xilinx/xilinx_dma.c

@@ -800,7 +800,7 @@ xilinx_dma_alloc_tx_descriptor(struct xilinx_dma_chan *chan)
 {
 	struct xilinx_dma_tx_descriptor *desc;
 
-	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 

drivers/dma/zx_dma.c

@@ -1,941 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2015 Linaro.
- */
-#include <linux/sched.h>
-#include <linux/device.h>
-#include <linux/dmaengine.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmapool.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/of_device.h>
-#include <linux/of.h>
-#include <linux/clk.h>
-#include <linux/of_dma.h>
-
-#include "virt-dma.h"
-
-#define DRIVER_NAME		"zx-dma"
-#define DMA_ALIGN		4
-#define DMA_MAX_SIZE		(0x10000 - 512)
-#define LLI_BLOCK_SIZE		(4 * PAGE_SIZE)
-
-#define REG_ZX_SRC_ADDR			0x00
-#define REG_ZX_DST_ADDR			0x04
-#define REG_ZX_TX_X_COUNT		0x08
-#define REG_ZX_TX_ZY_COUNT		0x0c
-#define REG_ZX_SRC_ZY_STEP		0x10
-#define REG_ZX_DST_ZY_STEP		0x14
-#define REG_ZX_LLI_ADDR			0x1c
-#define REG_ZX_CTRL			0x20
-#define REG_ZX_TC_IRQ			0x800
-#define REG_ZX_SRC_ERR_IRQ		0x804
-#define REG_ZX_DST_ERR_IRQ		0x808
-#define REG_ZX_CFG_ERR_IRQ		0x80c
-#define REG_ZX_TC_IRQ_RAW		0x810
-#define REG_ZX_SRC_ERR_IRQ_RAW		0x814
-#define REG_ZX_DST_ERR_IRQ_RAW		0x818
-#define REG_ZX_CFG_ERR_IRQ_RAW		0x81c
-#define REG_ZX_STATUS			0x820
-#define REG_ZX_DMA_GRP_PRIO		0x824
-#define REG_ZX_DMA_ARB			0x828
-
-#define ZX_FORCE_CLOSE			BIT(31)
-#define ZX_DST_BURST_WIDTH(x)		(((x) & 0x7) << 13)
-#define ZX_MAX_BURST_LEN		16
-#define ZX_SRC_BURST_LEN(x)		(((x) & 0xf) << 9)
-#define ZX_SRC_BURST_WIDTH(x)		(((x) & 0x7) << 6)
-#define ZX_IRQ_ENABLE_ALL		(3 << 4)
-#define ZX_DST_FIFO_MODE		BIT(3)
-#define ZX_SRC_FIFO_MODE		BIT(2)
-#define ZX_SOFT_REQ			BIT(1)
-#define ZX_CH_ENABLE			BIT(0)
-
-#define ZX_DMA_BUSWIDTHS \
-	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
-	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
-	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
-	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
-	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
-
-enum zx_dma_burst_width {
-	ZX_DMA_WIDTH_8BIT	= 0,
-	ZX_DMA_WIDTH_16BIT	= 1,
-	ZX_DMA_WIDTH_32BIT	= 2,
-	ZX_DMA_WIDTH_64BIT	= 3,
-};
-
-struct zx_desc_hw {
-	u32 saddr;
-	u32 daddr;
-	u32 src_x;
-	u32 src_zy;
-	u32 src_zy_step;
-	u32 dst_zy_step;
-	u32 reserved1;
-	u32 lli;
-	u32 ctr;
-	u32 reserved[7]; /* pack as hardware registers region size */
-} __aligned(32);
-
-struct zx_dma_desc_sw {
-	struct virt_dma_desc	vd;
-	dma_addr_t		desc_hw_lli;
-	size_t			desc_num;
-	size_t			size;
-	struct zx_desc_hw	*desc_hw;
-};
-
-struct zx_dma_phy;
-
-struct zx_dma_chan {
-	struct dma_slave_config slave_cfg;
-	int			id; /* Request phy chan id */
-	u32			ccfg;
-	u32			cyclic;
-	struct virt_dma_chan	vc;
-	struct zx_dma_phy	*phy;
-	struct list_head	node;
-	dma_addr_t		dev_addr;
-	enum dma_status		status;
-};
-
-struct zx_dma_phy {
-	u32			idx;
-	void __iomem		*base;
-	struct zx_dma_chan	*vchan;
-	struct zx_dma_desc_sw	*ds_run;
-	struct zx_dma_desc_sw	*ds_done;
-};
-
-struct zx_dma_dev {
-	struct dma_device	slave;
-	void __iomem		*base;
-	spinlock_t		lock; /* lock for ch and phy */
-	struct list_head	chan_pending;
-	struct zx_dma_phy	*phy;
-	struct zx_dma_chan	*chans;
-	struct clk		*clk;
-	struct dma_pool		*pool;
-	u32			dma_channels;
-	u32			dma_requests;
-	int 			irq;
-};
-
-#define to_zx_dma(dmadev) container_of(dmadev, struct zx_dma_dev, slave)
-
-static struct zx_dma_chan *to_zx_chan(struct dma_chan *chan)
-{
-	return container_of(chan, struct zx_dma_chan, vc.chan);
-}
-
-static void zx_dma_terminate_chan(struct zx_dma_phy *phy, struct zx_dma_dev *d)
-{
-	u32 val = 0;
-
-	val = readl_relaxed(phy->base + REG_ZX_CTRL);
-	val &= ~ZX_CH_ENABLE;
-	val |= ZX_FORCE_CLOSE;
-	writel_relaxed(val, phy->base + REG_ZX_CTRL);
-
-	val = 0x1 << phy->idx;
-	writel_relaxed(val, d->base + REG_ZX_TC_IRQ_RAW);
-	writel_relaxed(val, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
-	writel_relaxed(val, d->base + REG_ZX_DST_ERR_IRQ_RAW);
-	writel_relaxed(val, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
-}
-
-static void zx_dma_set_desc(struct zx_dma_phy *phy, struct zx_desc_hw *hw)
-{
-	writel_relaxed(hw->saddr, phy->base + REG_ZX_SRC_ADDR);
-	writel_relaxed(hw->daddr, phy->base + REG_ZX_DST_ADDR);
-	writel_relaxed(hw->src_x, phy->base + REG_ZX_TX_X_COUNT);
-	writel_relaxed(0, phy->base + REG_ZX_TX_ZY_COUNT);
-	writel_relaxed(0, phy->base + REG_ZX_SRC_ZY_STEP);
-	writel_relaxed(0, phy->base + REG_ZX_DST_ZY_STEP);
-	writel_relaxed(hw->lli, phy->base + REG_ZX_LLI_ADDR);
-	writel_relaxed(hw->ctr, phy->base + REG_ZX_CTRL);
-}
-
-static u32 zx_dma_get_curr_lli(struct zx_dma_phy *phy)
-{
-	return readl_relaxed(phy->base + REG_ZX_LLI_ADDR);
-}
-
-static u32 zx_dma_get_chan_stat(struct zx_dma_dev *d)
-{
-	return readl_relaxed(d->base + REG_ZX_STATUS);
-}
-
-static void zx_dma_init_state(struct zx_dma_dev *d)
-{
-	/* set same priority */
-	writel_relaxed(0x0, d->base + REG_ZX_DMA_ARB);
-	/* clear all irq */
-	writel_relaxed(0xffffffff, d->base + REG_ZX_TC_IRQ_RAW);
-	writel_relaxed(0xffffffff, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
-	writel_relaxed(0xffffffff, d->base + REG_ZX_DST_ERR_IRQ_RAW);
-	writel_relaxed(0xffffffff, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
-}
-
-static int zx_dma_start_txd(struct zx_dma_chan *c)
-{
-	struct zx_dma_dev *d = to_zx_dma(c->vc.chan.device);
-	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
-
-	if (!c->phy)
-		return -EAGAIN;
-
-	if (BIT(c->phy->idx) & zx_dma_get_chan_stat(d))
-		return -EAGAIN;
-
-	if (vd) {
-		struct zx_dma_desc_sw *ds =
-			container_of(vd, struct zx_dma_desc_sw, vd);
-		/*
-		 * fetch and remove request from vc->desc_issued
-		 * so vc->desc_issued only contains desc pending
-		 */
-		list_del(&ds->vd.node);
-		c->phy->ds_run = ds;
-		c->phy->ds_done = NULL;
-		/* start dma */
-		zx_dma_set_desc(c->phy, ds->desc_hw);
-		return 0;
-	}
-	c->phy->ds_done = NULL;
-	c->phy->ds_run = NULL;
-	return -EAGAIN;
-}
-
-static void zx_dma_task(struct zx_dma_dev *d)
-{
-	struct zx_dma_phy *p;
-	struct zx_dma_chan *c, *cn;
-	unsigned pch, pch_alloc = 0;
-	unsigned long flags;
-
-	/* check new dma request of running channel in vc->desc_issued */
-	list_for_each_entry_safe(c, cn, &d->slave.channels,
-				 vc.chan.device_node) {
-		spin_lock_irqsave(&c->vc.lock, flags);
-		p = c->phy;
-		if (p && p->ds_done && zx_dma_start_txd(c)) {
-			/* No current txd associated with this channel */
-			dev_dbg(d->slave.dev, "pchan %u: free\n", p->idx);
-			/* Mark this channel free */
-			c->phy = NULL;
-			p->vchan = NULL;
-		}
-		spin_unlock_irqrestore(&c->vc.lock, flags);
-	}
-
-	/* check new channel request in d->chan_pending */
-	spin_lock_irqsave(&d->lock, flags);
-	while (!list_empty(&d->chan_pending)) {
-		c = list_first_entry(&d->chan_pending,
-				     struct zx_dma_chan, node);
-		p = &d->phy[c->id];
-		if (!p->vchan) {
-			/* remove from d->chan_pending */
-			list_del_init(&c->node);
-			pch_alloc |= 1 << c->id;
-			/* Mark this channel allocated */
-			p->vchan = c;
-			c->phy = p;
-		} else {
-			dev_dbg(d->slave.dev, "pchan %u: busy!\n", c->id);
-		}
-	}
-	spin_unlock_irqrestore(&d->lock, flags);
-
-	for (pch = 0; pch < d->dma_channels; pch++) {
-		if (pch_alloc & (1 << pch)) {
-			p = &d->phy[pch];
-			c = p->vchan;
-			if (c) {
-				spin_lock_irqsave(&c->vc.lock, flags);
-				zx_dma_start_txd(c);
-				spin_unlock_irqrestore(&c->vc.lock, flags);
-			}
-		}
-	}
-}
-
-static irqreturn_t zx_dma_int_handler(int irq, void *dev_id)
-{
-	struct zx_dma_dev *d = (struct zx_dma_dev *)dev_id;
-	struct zx_dma_phy *p;
-	struct zx_dma_chan *c;
-	u32 tc = readl_relaxed(d->base + REG_ZX_TC_IRQ);
-	u32 serr = readl_relaxed(d->base + REG_ZX_SRC_ERR_IRQ);
-	u32 derr = readl_relaxed(d->base + REG_ZX_DST_ERR_IRQ);
-	u32 cfg = readl_relaxed(d->base + REG_ZX_CFG_ERR_IRQ);
-	u32 i, irq_chan = 0, task = 0;
-
-	while (tc) {
-		i = __ffs(tc);
-		tc &= ~BIT(i);
-		p = &d->phy[i];
-		c = p->vchan;
-		if (c) {
-			spin_lock(&c->vc.lock);
-			if (c->cyclic) {
-				vchan_cyclic_callback(&p->ds_run->vd);
-			} else {
-				vchan_cookie_complete(&p->ds_run->vd);
-				p->ds_done = p->ds_run;
-				task = 1;
-			}
-			spin_unlock(&c->vc.lock);
-			irq_chan |= BIT(i);
-		}
-	}
-
-	if (serr || derr || cfg)
-		dev_warn(d->slave.dev, "DMA ERR src 0x%x, dst 0x%x, cfg 0x%x\n",
-			 serr, derr, cfg);
-
-	writel_relaxed(irq_chan, d->base + REG_ZX_TC_IRQ_RAW);
-	writel_relaxed(serr, d->base + REG_ZX_SRC_ERR_IRQ_RAW);
-	writel_relaxed(derr, d->base + REG_ZX_DST_ERR_IRQ_RAW);
-	writel_relaxed(cfg, d->base + REG_ZX_CFG_ERR_IRQ_RAW);
-
-	if (task)
-		zx_dma_task(d);
-	return IRQ_HANDLED;
-}
-
-static void zx_dma_free_chan_resources(struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_dev *d = to_zx_dma(chan->device);
-	unsigned long flags;
-
-	spin_lock_irqsave(&d->lock, flags);
-	list_del_init(&c->node);
-	spin_unlock_irqrestore(&d->lock, flags);
-
-	vchan_free_chan_resources(&c->vc);
-	c->ccfg = 0;
-}
-
-static enum dma_status zx_dma_tx_status(struct dma_chan *chan,
-					dma_cookie_t cookie,
-					struct dma_tx_state *state)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_phy *p;
-	struct virt_dma_desc *vd;
-	unsigned long flags;
-	enum dma_status ret;
-	size_t bytes = 0;
-
-	ret = dma_cookie_status(&c->vc.chan, cookie, state);
-	if (ret == DMA_COMPLETE || !state)
-		return ret;
-
-	spin_lock_irqsave(&c->vc.lock, flags);
-	p = c->phy;
-	ret = c->status;
-
-	/*
-	 * If the cookie is on our issue queue, then the residue is
-	 * its total size.
-	 */
-	vd = vchan_find_desc(&c->vc, cookie);
-	if (vd) {
-		bytes = container_of(vd, struct zx_dma_desc_sw, vd)->size;
-	} else if ((!p) || (!p->ds_run)) {
-		bytes = 0;
-	} else {
-		struct zx_dma_desc_sw *ds = p->ds_run;
-		u32 clli = 0, index = 0;
-
-		bytes = 0;
-		clli = zx_dma_get_curr_lli(p);
-		index = (clli - ds->desc_hw_lli) /
-				sizeof(struct zx_desc_hw) + 1;
-		for (; index < ds->desc_num; index++) {
-			bytes += ds->desc_hw[index].src_x;
-			/* end of lli */
-			if (!ds->desc_hw[index].lli)
-				break;
-		}
-	}
-	spin_unlock_irqrestore(&c->vc.lock, flags);
-	dma_set_residue(state, bytes);
-	return ret;
-}
-
-static void zx_dma_issue_pending(struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_dev *d = to_zx_dma(chan->device);
-	unsigned long flags;
-	int issue = 0;
-
-	spin_lock_irqsave(&c->vc.lock, flags);
-	/* add request to vc->desc_issued */
-	if (vchan_issue_pending(&c->vc)) {
-		spin_lock(&d->lock);
-		if (!c->phy && list_empty(&c->node)) {
-			/* if new channel, add chan_pending */
-			list_add_tail(&c->node, &d->chan_pending);
-			issue = 1;
-			dev_dbg(d->slave.dev, "vchan %p: issued\n", &c->vc);
-		}
-		spin_unlock(&d->lock);
-	} else {
-		dev_dbg(d->slave.dev, "vchan %p: nothing to issue\n", &c->vc);
-	}
-	spin_unlock_irqrestore(&c->vc.lock, flags);
-
-	if (issue)
-		zx_dma_task(d);
-}
-
-static void zx_dma_fill_desc(struct zx_dma_desc_sw *ds, dma_addr_t dst,
-			     dma_addr_t src, size_t len, u32 num, u32 ccfg)
-{
-	if ((num + 1) < ds->desc_num)
-		ds->desc_hw[num].lli = ds->desc_hw_lli + (num + 1) *
-			sizeof(struct zx_desc_hw);
-	ds->desc_hw[num].saddr = src;
-	ds->desc_hw[num].daddr = dst;
-	ds->desc_hw[num].src_x = len;
-	ds->desc_hw[num].ctr = ccfg;
-}
-
-static struct zx_dma_desc_sw *zx_alloc_desc_resource(int num,
-						     struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_desc_sw *ds;
-	struct zx_dma_dev *d = to_zx_dma(chan->device);
-	int lli_limit = LLI_BLOCK_SIZE / sizeof(struct zx_desc_hw);
-
-	if (num > lli_limit) {
-		dev_dbg(chan->device->dev, "vch %p: sg num %d exceed max %d\n",
-			&c->vc, num, lli_limit);
-		return NULL;
-	}
-
-	ds = kzalloc(sizeof(*ds), GFP_ATOMIC);
-	if (!ds)
-		return NULL;
-
-	ds->desc_hw = dma_pool_zalloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
-	if (!ds->desc_hw) {
-		dev_dbg(chan->device->dev, "vch %p: dma alloc fail\n", &c->vc);
-		kfree(ds);
-		return NULL;
-	}
-	ds->desc_num = num;
-	return ds;
-}
-
-static enum zx_dma_burst_width zx_dma_burst_width(enum dma_slave_buswidth width)
-{
-	switch (width) {
-	case DMA_SLAVE_BUSWIDTH_1_BYTE:
-	case DMA_SLAVE_BUSWIDTH_2_BYTES:
-	case DMA_SLAVE_BUSWIDTH_4_BYTES:
-	case DMA_SLAVE_BUSWIDTH_8_BYTES:
-		return ffs(width) - 1;
-	default:
-		return ZX_DMA_WIDTH_32BIT;
-	}
-}
-
-static int zx_pre_config(struct zx_dma_chan *c, enum dma_transfer_direction dir)
-{
-	struct dma_slave_config *cfg = &c->slave_cfg;
-	enum zx_dma_burst_width src_width;
-	enum zx_dma_burst_width dst_width;
-	u32 maxburst = 0;
-
-	switch (dir) {
-	case DMA_MEM_TO_MEM:
-		c->ccfg = ZX_CH_ENABLE | ZX_SOFT_REQ
-			| ZX_SRC_BURST_LEN(ZX_MAX_BURST_LEN - 1)
-			| ZX_SRC_BURST_WIDTH(ZX_DMA_WIDTH_32BIT)
-			| ZX_DST_BURST_WIDTH(ZX_DMA_WIDTH_32BIT);
-		break;
-	case DMA_MEM_TO_DEV:
-		c->dev_addr = cfg->dst_addr;
-		/* dst len is calculated from src width, len and dst width.
-		 * We need make sure dst len not exceed MAX LEN.
-		 * Trailing single transaction that does not fill a full
-		 * burst also require identical src/dst data width.
-		 */
-		dst_width = zx_dma_burst_width(cfg->dst_addr_width);
-		maxburst = cfg->dst_maxburst;
-		maxburst = maxburst < ZX_MAX_BURST_LEN ?
-				maxburst : ZX_MAX_BURST_LEN;
-		c->ccfg = ZX_DST_FIFO_MODE | ZX_CH_ENABLE
-			| ZX_SRC_BURST_LEN(maxburst - 1)
-			| ZX_SRC_BURST_WIDTH(dst_width)
-			| ZX_DST_BURST_WIDTH(dst_width);
-		break;
-	case DMA_DEV_TO_MEM:
-		c->dev_addr = cfg->src_addr;
-		src_width = zx_dma_burst_width(cfg->src_addr_width);
-		maxburst = cfg->src_maxburst;
-		maxburst = maxburst < ZX_MAX_BURST_LEN ?
-				maxburst : ZX_MAX_BURST_LEN;
-		c->ccfg = ZX_SRC_FIFO_MODE | ZX_CH_ENABLE
-			| ZX_SRC_BURST_LEN(maxburst - 1)
-			| ZX_SRC_BURST_WIDTH(src_width)
-			| ZX_DST_BURST_WIDTH(src_width);
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static struct dma_async_tx_descriptor *zx_dma_prep_memcpy(
-	struct dma_chan *chan,	dma_addr_t dst, dma_addr_t src,
-	size_t len, unsigned long flags)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_desc_sw *ds;
-	size_t copy = 0;
-	int num = 0;
-
-	if (!len)
-		return NULL;
-
-	if (zx_pre_config(c, DMA_MEM_TO_MEM))
-		return NULL;
-
-	num = DIV_ROUND_UP(len, DMA_MAX_SIZE);
-
-	ds = zx_alloc_desc_resource(num, chan);
-	if (!ds)
-		return NULL;
-
-	ds->size = len;
-	num = 0;
-
-	do {
-		copy = min_t(size_t, len, DMA_MAX_SIZE);
-		zx_dma_fill_desc(ds, dst, src, copy, num++, c->ccfg);
-
-		src += copy;
-		dst += copy;
-		len -= copy;
-	} while (len);
-
-	c->cyclic = 0;
-	ds->desc_hw[num - 1].lli = 0;	/* end of link */
-	ds->desc_hw[num - 1].ctr |= ZX_IRQ_ENABLE_ALL;
-	return vchan_tx_prep(&c->vc, &ds->vd, flags);
-}
-
-static struct dma_async_tx_descriptor *zx_dma_prep_slave_sg(
-	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sglen,
-	enum dma_transfer_direction dir, unsigned long flags, void *context)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_desc_sw *ds;
-	size_t len, avail, total = 0;
-	struct scatterlist *sg;
-	dma_addr_t addr, src = 0, dst = 0;
-	int num = sglen, i;
-
-	if (!sgl)
-		return NULL;
-
-	if (zx_pre_config(c, dir))
-		return NULL;
-
-	for_each_sg(sgl, sg, sglen, i) {
-		avail = sg_dma_len(sg);
-		if (avail > DMA_MAX_SIZE)
-			num += DIV_ROUND_UP(avail, DMA_MAX_SIZE) - 1;
-	}
-
-	ds = zx_alloc_desc_resource(num, chan);
-	if (!ds)
-		return NULL;
-
-	c->cyclic = 0;
-	num = 0;
-	for_each_sg(sgl, sg, sglen, i) {
-		addr = sg_dma_address(sg);
-		avail = sg_dma_len(sg);
-		total += avail;
-
-		do {
-			len = min_t(size_t, avail, DMA_MAX_SIZE);
-
-			if (dir == DMA_MEM_TO_DEV) {
-				src = addr;
-				dst = c->dev_addr;
-			} else if (dir == DMA_DEV_TO_MEM) {
-				src = c->dev_addr;
-				dst = addr;
-			}
-
-			zx_dma_fill_desc(ds, dst, src, len, num++, c->ccfg);
-
-			addr += len;
-			avail -= len;
-		} while (avail);
-	}
-
-	ds->desc_hw[num - 1].lli = 0;	/* end of link */
-	ds->desc_hw[num - 1].ctr |= ZX_IRQ_ENABLE_ALL;
-	ds->size = total;
-	return vchan_tx_prep(&c->vc, &ds->vd, flags);
-}
-
-static struct dma_async_tx_descriptor *zx_dma_prep_dma_cyclic(
-		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction dir,
-		unsigned long flags)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_desc_sw *ds;
-	dma_addr_t src = 0, dst = 0;
-	int num_periods = buf_len / period_len;
-	int buf = 0, num = 0;
-
-	if (period_len > DMA_MAX_SIZE) {
-		dev_err(chan->device->dev, "maximum period size exceeded\n");
-		return NULL;
-	}
-
-	if (zx_pre_config(c, dir))
-		return NULL;
-
-	ds = zx_alloc_desc_resource(num_periods, chan);
-	if (!ds)
-		return NULL;
-	c->cyclic = 1;
-
-	while (buf < buf_len) {
-		if (dir == DMA_MEM_TO_DEV) {
-			src = dma_addr;
-			dst = c->dev_addr;
-		} else if (dir == DMA_DEV_TO_MEM) {
-			src = c->dev_addr;
-			dst = dma_addr;
-		}
-		zx_dma_fill_desc(ds, dst, src, period_len, num++,
-				 c->ccfg | ZX_IRQ_ENABLE_ALL);
-		dma_addr += period_len;
-		buf += period_len;
-	}
-
-	ds->desc_hw[num - 1].lli = ds->desc_hw_lli;
-	ds->size = buf_len;
-	return vchan_tx_prep(&c->vc, &ds->vd, flags);
-}
-
-static int zx_dma_config(struct dma_chan *chan,
-			 struct dma_slave_config *cfg)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-
-	if (!cfg)
-		return -EINVAL;
-
-	memcpy(&c->slave_cfg, cfg, sizeof(*cfg));
-
-	return 0;
-}
-
-static int zx_dma_terminate_all(struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	struct zx_dma_dev *d = to_zx_dma(chan->device);
-	struct zx_dma_phy *p = c->phy;
-	unsigned long flags;
-	LIST_HEAD(head);
-
-	dev_dbg(d->slave.dev, "vchan %p: terminate all\n", &c->vc);
-
-	/* Prevent this channel being scheduled */
-	spin_lock(&d->lock);
-	list_del_init(&c->node);
-	spin_unlock(&d->lock);
-
-	/* Clear the tx descriptor lists */
-	spin_lock_irqsave(&c->vc.lock, flags);
-	vchan_get_all_descriptors(&c->vc, &head);
-	if (p) {
-		/* vchan is assigned to a pchan - stop the channel */
-		zx_dma_terminate_chan(p, d);
-		c->phy = NULL;
-		p->vchan = NULL;
-		p->ds_run = NULL;
-		p->ds_done = NULL;
-	}
-	spin_unlock_irqrestore(&c->vc.lock, flags);
-	vchan_dma_desc_free_list(&c->vc, &head);
-
-	return 0;
-}
-
-static int zx_dma_transfer_pause(struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	u32 val = 0;
-
-	val = readl_relaxed(c->phy->base + REG_ZX_CTRL);
-	val &= ~ZX_CH_ENABLE;
-	writel_relaxed(val, c->phy->base + REG_ZX_CTRL);
-
-	return 0;
-}
-
-static int zx_dma_transfer_resume(struct dma_chan *chan)
-{
-	struct zx_dma_chan *c = to_zx_chan(chan);
-	u32 val = 0;
-
-	val = readl_relaxed(c->phy->base + REG_ZX_CTRL);
-	val |= ZX_CH_ENABLE;
-	writel_relaxed(val, c->phy->base + REG_ZX_CTRL);
-
-	return 0;
-}
-
-static void zx_dma_free_desc(struct virt_dma_desc *vd)
-{
-	struct zx_dma_desc_sw *ds =
-		container_of(vd, struct zx_dma_desc_sw, vd);
-	struct zx_dma_dev *d = to_zx_dma(vd->tx.chan->device);
-
-	dma_pool_free(d->pool, ds->desc_hw, ds->desc_hw_lli);
-	kfree(ds);
-}
-
-static const struct of_device_id zx6702_dma_dt_ids[] = {
-	{ .compatible = "zte,zx296702-dma", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, zx6702_dma_dt_ids);
-
-static struct dma_chan *zx_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
-					       struct of_dma *ofdma)
-{
-	struct zx_dma_dev *d = ofdma->of_dma_data;
-	unsigned int request = dma_spec->args[0];
-	struct dma_chan *chan;
-	struct zx_dma_chan *c;
-
-	if (request >= d->dma_requests)
-		return NULL;
-
-	chan = dma_get_any_slave_channel(&d->slave);
-	if (!chan) {
-		dev_err(d->slave.dev, "get channel fail in %s.\n", __func__);
-		return NULL;
-	}
-	c = to_zx_chan(chan);
-	c->id = request;
-	dev_info(d->slave.dev, "zx_dma: pchan %u: alloc vchan %p\n",
-		 c->id, &c->vc);
-	return chan;
-}
-
-static int zx_dma_probe(struct platform_device *op)
-{
-	struct zx_dma_dev *d;
-	int i, ret = 0;
-
-	d = devm_kzalloc(&op->dev, sizeof(*d), GFP_KERNEL);
-	if (!d)
-		return -ENOMEM;
-
-	d->base = devm_platform_ioremap_resource(op, 0);
-	if (IS_ERR(d->base))
-		return PTR_ERR(d->base);
-
-	of_property_read_u32((&op->dev)->of_node,
-			     "dma-channels", &d->dma_channels);
-	of_property_read_u32((&op->dev)->of_node,
-			     "dma-requests", &d->dma_requests);
-	if (!d->dma_requests || !d->dma_channels)
-		return -EINVAL;
-
-	d->clk = devm_clk_get(&op->dev, NULL);
-	if (IS_ERR(d->clk)) {
-		dev_err(&op->dev, "no dma clk\n");
-		return PTR_ERR(d->clk);
-	}
-
-	d->irq = platform_get_irq(op, 0);
-	ret = devm_request_irq(&op->dev, d->irq, zx_dma_int_handler,
-			       0, DRIVER_NAME, d);
-	if (ret)
-		return ret;
-
-	/* A DMA memory pool for LLIs, align on 32-byte boundary */
-	d->pool = dmam_pool_create(DRIVER_NAME, &op->dev,
-			LLI_BLOCK_SIZE, 32, 0);
-	if (!d->pool)
-		return -ENOMEM;
-
-	/* init phy channel */
-	d->phy = devm_kcalloc(&op->dev,
-		d->dma_channels, sizeof(struct zx_dma_phy), GFP_KERNEL);
-	if (!d->phy)
-		return -ENOMEM;
-
-	for (i = 0; i < d->dma_channels; i++) {
-		struct zx_dma_phy *p = &d->phy[i];
-
-		p->idx = i;
-		p->base = d->base + i * 0x40;
-	}
-
-	INIT_LIST_HEAD(&d->slave.channels);
-	dma_cap_set(DMA_SLAVE, d->slave.cap_mask);
-	dma_cap_set(DMA_MEMCPY, d->slave.cap_mask);
-	dma_cap_set(DMA_CYCLIC, d->slave.cap_mask);
-	dma_cap_set(DMA_PRIVATE, d->slave.cap_mask);
-	d->slave.dev = &op->dev;
-	d->slave.device_free_chan_resources = zx_dma_free_chan_resources;
-	d->slave.device_tx_status = zx_dma_tx_status;
-	d->slave.device_prep_dma_memcpy = zx_dma_prep_memcpy;
-	d->slave.device_prep_slave_sg = zx_dma_prep_slave_sg;
-	d->slave.device_prep_dma_cyclic = zx_dma_prep_dma_cyclic;
-	d->slave.device_issue_pending = zx_dma_issue_pending;
-	d->slave.device_config = zx_dma_config;
-	d->slave.device_terminate_all = zx_dma_terminate_all;
-	d->slave.device_pause = zx_dma_transfer_pause;
-	d->slave.device_resume = zx_dma_transfer_resume;
-	d->slave.copy_align = DMA_ALIGN;
-	d->slave.src_addr_widths = ZX_DMA_BUSWIDTHS;
-	d->slave.dst_addr_widths = ZX_DMA_BUSWIDTHS;
-	d->slave.directions = BIT(DMA_MEM_TO_MEM) | BIT(DMA_MEM_TO_DEV)
-			| BIT(DMA_DEV_TO_MEM);
-	d->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
-
-	/* init virtual channel */
-	d->chans = devm_kcalloc(&op->dev,
-		d->dma_requests, sizeof(struct zx_dma_chan), GFP_KERNEL);
-	if (!d->chans)
-		return -ENOMEM;
-
-	for (i = 0; i < d->dma_requests; i++) {
-		struct zx_dma_chan *c = &d->chans[i];
-
-		c->status = DMA_IN_PROGRESS;
-		INIT_LIST_HEAD(&c->node);
-		c->vc.desc_free = zx_dma_free_desc;
-		vchan_init(&c->vc, &d->slave);
-	}
-
-	/* Enable clock before accessing registers */
-	ret = clk_prepare_enable(d->clk);
-	if (ret < 0) {
-		dev_err(&op->dev, "clk_prepare_enable failed: %d\n", ret);
-		goto zx_dma_out;
-	}
-
-	zx_dma_init_state(d);
-
-	spin_lock_init(&d->lock);
-	INIT_LIST_HEAD(&d->chan_pending);
-	platform_set_drvdata(op, d);
-
-	ret = dma_async_device_register(&d->slave);
-	if (ret)
-		goto clk_dis;
-
-	ret = of_dma_controller_register((&op->dev)->of_node,
-					 zx_of_dma_simple_xlate, d);
-	if (ret)
-		goto of_dma_register_fail;
-
-	dev_info(&op->dev, "initialized\n");
-	return 0;
-
-of_dma_register_fail:
-	dma_async_device_unregister(&d->slave);
-clk_dis:
-	clk_disable_unprepare(d->clk);
-zx_dma_out:
-	return ret;
-}
-
-static int zx_dma_remove(struct platform_device *op)
-{
-	struct zx_dma_chan *c, *cn;
-	struct zx_dma_dev *d = platform_get_drvdata(op);
-
-	/* explictly free the irq */
-	devm_free_irq(&op->dev, d->irq, d);
-
-	dma_async_device_unregister(&d->slave);
-	of_dma_controller_free((&op->dev)->of_node);
-
-	list_for_each_entry_safe(c, cn, &d->slave.channels,
-				 vc.chan.device_node) {
-		list_del(&c->vc.chan.device_node);
-	}
-	clk_disable_unprepare(d->clk);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int zx_dma_suspend_dev(struct device *dev)
-{
-	struct zx_dma_dev *d = dev_get_drvdata(dev);
-	u32 stat = 0;
-
-	stat = zx_dma_get_chan_stat(d);
-	if (stat) {
-		dev_warn(d->slave.dev,
-			 "chan %d is running fail to suspend\n", stat);
-		return -1;
-	}
-	clk_disable_unprepare(d->clk);
-	return 0;
-}
-
-static int zx_dma_resume_dev(struct device *dev)
-{
-	struct zx_dma_dev *d = dev_get_drvdata(dev);
-	int ret = 0;
-
-	ret = clk_prepare_enable(d->clk);
-	if (ret < 0) {
-		dev_err(d->slave.dev, "clk_prepare_enable failed: %d\n", ret);
-		return ret;
-	}
-	zx_dma_init_state(d);
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(zx_dma_pmops, zx_dma_suspend_dev, zx_dma_resume_dev);
-
-static struct platform_driver zx_pdma_driver = {
-	.driver		= {
-		.name	= DRIVER_NAME,
-		.pm	= &zx_dma_pmops,
-		.of_match_table = zx6702_dma_dt_ids,
-	},
-	.probe		= zx_dma_probe,
-	.remove		= zx_dma_remove,
-};
-
-module_platform_driver(zx_pdma_driver);
-
-MODULE_DESCRIPTION("ZTE ZX296702 DMA Driver");
-MODULE_AUTHOR("Jun Nie jun.nie@linaro.org");
-MODULE_LICENSE("GPL v2");

include/linux/dma/k3-psil.h

@@ -42,14 +42,14 @@ enum psil_endpoint_type {
 /**
  * struct psil_endpoint_config - PSI-L Endpoint configuration
  * @ep_type:		PSI-L endpoint type
+ * @channel_tpl:	Desired throughput level for the channel
  * @pkt_mode:		If set, the channel must be in Packet mode, otherwise in
  *			TR mode
  * @notdpkt:		TDCM must be suppressed on the TX channel
  * @needs_epib:		Endpoint needs EPIB
- * @psd_size:		If set, PSdata is used by the endpoint
- * @channel_tpl:	Desired throughput level for the channel
  * @pdma_acc32:		ACC32 must be enabled on the PDMA side
  * @pdma_burst:		BURST must be enabled on the PDMA side
+ * @psd_size:		If set, PSdata is used by the endpoint
  * @mapped_channel_id:	PKTDMA thread to channel mapping for mapped channels.
  *			The thread must be serviced by the specified channel if
  *			mapped_channel_id is >= 0 in case of PKTDMA
@@ -62,23 +62,22 @@ enum psil_endpoint_type {
  */
 struct psil_endpoint_config {
 	enum psil_endpoint_type ep_type;
+	enum udma_tp_level channel_tpl;
 
 	unsigned pkt_mode:1;
 	unsigned notdpkt:1;
 	unsigned needs_epib:1;
-	u32 psd_size;
-	enum udma_tp_level channel_tpl;
-
 	/* PDMA properties, valid for PSIL_EP_PDMA_* */
 	unsigned pdma_acc32:1;
 	unsigned pdma_burst:1;
 
+	u32 psd_size;
 	/* PKDMA mapped channel */
-	int mapped_channel_id;
+	s16 mapped_channel_id;
 	/* PKTDMA tflow and rflow ranges for mapped channel */
 	u16 flow_start;
 	u16 flow_num;
-	u16 default_flow_id;
+	s16 default_flow_id;
 };
 
 int psil_set_new_ep_config(struct device *dev, const char *name,

include/linux/dma/mmp-pdma.h

@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MMP_PDMA_H_
-#define _MMP_PDMA_H_
-
-struct dma_chan;
-
-#ifdef CONFIG_MMP_PDMA
-bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param);
-#else
-static inline bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param)
-{
-	return false;
-}
-#endif
-
-#endif /* _MMP_PDMA_H_ */

include/linux/dmaengine.h

@@ -745,6 +745,8 @@ enum dmaengine_alignment {
 	DMAENGINE_ALIGN_16_BYTES = 4,
 	DMAENGINE_ALIGN_32_BYTES = 5,
 	DMAENGINE_ALIGN_64_BYTES = 6,
+	DMAENGINE_ALIGN_128_BYTES = 7,
+	DMAENGINE_ALIGN_256_BYTES = 8,
 };
 
 /**

include/linux/platform_data/dma-atmel.h

@@ -1,61 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Header file for the Atmel AHB DMA Controller driver
- *
- * Copyright (C) 2008 Atmel Corporation
- */
-#ifndef AT_HDMAC_H
-#define AT_HDMAC_H
-
-#include <linux/dmaengine.h>
-
-/**
- * struct at_dma_platform_data - Controller configuration parameters
- * @nr_channels: Number of channels supported by hardware (max 8)
- * @cap_mask: dma_capability flags supported by the platform
- */
-struct at_dma_platform_data {
-	unsigned int	nr_channels;
-	dma_cap_mask_t  cap_mask;
-};
-
-/**
- * struct at_dma_slave - Controller-specific information about a slave
- * @dma_dev: required DMA master device
- * @cfg: Platform-specific initializer for the CFG register
- */
-struct at_dma_slave {
-	struct device		*dma_dev;
-	u32			cfg;
-};
-
-
-/* Platform-configurable bits in CFG */
-#define ATC_PER_MSB(h)	((0x30U & (h)) >> 4)	/* Extract most significant bits of a handshaking identifier */
-
-#define	ATC_SRC_PER(h)		(0xFU & (h))	/* Channel src rq associated with periph handshaking ifc h */
-#define	ATC_DST_PER(h)		((0xFU & (h)) <<  4)	/* Channel dst rq associated with periph handshaking ifc h */
-#define	ATC_SRC_REP		(0x1 <<  8)	/* Source Replay Mod */
-#define	ATC_SRC_H2SEL		(0x1 <<  9)	/* Source Handshaking Mod */
-#define		ATC_SRC_H2SEL_SW	(0x0 <<  9)
-#define		ATC_SRC_H2SEL_HW	(0x1 <<  9)
-#define	ATC_SRC_PER_MSB(h)	(ATC_PER_MSB(h) << 10)	/* Channel src rq (most significant bits) */
-#define	ATC_DST_REP		(0x1 << 12)	/* Destination Replay Mod */
-#define	ATC_DST_H2SEL		(0x1 << 13)	/* Destination Handshaking Mod */
-#define		ATC_DST_H2SEL_SW	(0x0 << 13)
-#define		ATC_DST_H2SEL_HW	(0x1 << 13)
-#define	ATC_DST_PER_MSB(h)	(ATC_PER_MSB(h) << 14)	/* Channel dst rq (most significant bits) */
-#define	ATC_SOD			(0x1 << 16)	/* Stop On Done */
-#define	ATC_LOCK_IF		(0x1 << 20)	/* Interface Lock */
-#define	ATC_LOCK_B		(0x1 << 21)	/* AHB Bus Lock */
-#define	ATC_LOCK_IF_L		(0x1 << 22)	/* Master Interface Arbiter Lock */
-#define		ATC_LOCK_IF_L_CHUNK	(0x0 << 22)
-#define		ATC_LOCK_IF_L_BUFFER	(0x1 << 22)
-#define	ATC_AHB_PROT_MASK	(0x7 << 24)	/* AHB Protection */
-#define	ATC_FIFOCFG_MASK	(0x3 << 28)	/* FIFO Request Configuration */
-#define		ATC_FIFOCFG_LARGESTBURST	(0x0 << 28)
-#define		ATC_FIFOCFG_HALFFIFO		(0x1 << 28)
-#define		ATC_FIFOCFG_ENOUGHSPACE		(0x2 << 28)
-
-
-#endif /* AT_HDMAC_H */

include/linux/platform_data/dma-coh901318.h

@@ -1,72 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Platform data for the COH901318 DMA controller
- * Copyright (C) 2007-2013 ST-Ericsson
- */
-
-#ifndef PLAT_COH901318_H
-#define PLAT_COH901318_H
-
-#ifdef CONFIG_COH901318
-
-/* We only support the U300 DMA channels */
-#define U300_DMA_MSL_TX_0		0
-#define U300_DMA_MSL_TX_1		1
-#define U300_DMA_MSL_TX_2		2
-#define U300_DMA_MSL_TX_3		3
-#define U300_DMA_MSL_TX_4		4
-#define U300_DMA_MSL_TX_5		5
-#define U300_DMA_MSL_TX_6		6
-#define U300_DMA_MSL_RX_0		7
-#define U300_DMA_MSL_RX_1		8
-#define U300_DMA_MSL_RX_2		9
-#define U300_DMA_MSL_RX_3		10
-#define U300_DMA_MSL_RX_4		11
-#define U300_DMA_MSL_RX_5		12
-#define U300_DMA_MSL_RX_6		13
-#define U300_DMA_MMCSD_RX_TX		14
-#define U300_DMA_MSPRO_TX		15
-#define U300_DMA_MSPRO_RX		16
-#define U300_DMA_UART0_TX		17
-#define U300_DMA_UART0_RX		18
-#define U300_DMA_APEX_TX		19
-#define U300_DMA_APEX_RX		20
-#define U300_DMA_PCM_I2S0_TX		21
-#define U300_DMA_PCM_I2S0_RX		22
-#define U300_DMA_PCM_I2S1_TX		23
-#define U300_DMA_PCM_I2S1_RX		24
-#define U300_DMA_XGAM_CDI		25
-#define U300_DMA_XGAM_PDI		26
-#define U300_DMA_SPI_TX			27
-#define U300_DMA_SPI_RX			28
-#define U300_DMA_GENERAL_PURPOSE_0	29
-#define U300_DMA_GENERAL_PURPOSE_1	30
-#define U300_DMA_GENERAL_PURPOSE_2	31
-#define U300_DMA_GENERAL_PURPOSE_3	32
-#define U300_DMA_GENERAL_PURPOSE_4	33
-#define U300_DMA_GENERAL_PURPOSE_5	34
-#define U300_DMA_GENERAL_PURPOSE_6	35
-#define U300_DMA_GENERAL_PURPOSE_7	36
-#define U300_DMA_GENERAL_PURPOSE_8	37
-#define U300_DMA_UART1_TX		38
-#define U300_DMA_UART1_RX		39
-
-#define U300_DMA_DEVICE_CHANNELS	32
-#define U300_DMA_CHANNELS		40
-
-/**
- * coh901318_filter_id() - DMA channel filter function
- * @chan: dma channel handle
- * @chan_id: id of dma channel to be filter out
- *
- * In dma_request_channel() it specifies what channel id to be requested
- */
-bool coh901318_filter_id(struct dma_chan *chan, void *chan_id);
-#else
-static inline bool coh901318_filter_id(struct dma_chan *chan, void *chan_id)
-{
-	return false;
-}
-#endif
-
-#endif /* PLAT_COH901318_H */

include/linux/platform_data/dma-imx-sdma.h

@@ -57,15 +57,4 @@ struct sdma_script_start_addrs {
 	/* End of v4 array */
 };
 
-/**
- * struct sdma_platform_data - platform specific data for SDMA engine
- *
- * @fw_name		The firmware name
- * @script_addrs	SDMA scripts addresses in SDMA ROM
- */
-struct sdma_platform_data {
-	char *fw_name;
-	struct sdma_script_start_addrs *script_addrs;
-};
-
 #endif /* __MACH_MXC_SDMA_H__ */

include/linux/sirfsoc_dma.h

@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _SIRFSOC_DMA_H_
-#define _SIRFSOC_DMA_H_
-
-bool sirfsoc_dma_filter_id(struct dma_chan *chan, void *chan_id);
-
-#endif