Merge tag 'dmaengine-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "Nothing special, this includes a couple of new device support and new
  driver support and bunch of driver updates.

  New support:

   - Tegra gpcdma driver support

   - Qualcomm SM8350, Sm8450 and SC7280 device support

   - Renesas RZN1 dma and platform support

  Updates:

   - stm32 device pause/resume support and updates

   - DMA memset ops Documentation and usage clarification

   - deprecate '#dma-channels' & '#dma-requests' bindings

   - driver updates for stm32, ptdma idsx etc"

* tag 'dmaengine-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (87 commits)
  dmaengine: idxd: make idxd_wq_enable() return 0 if wq is already enabled
  dmaengine: sun6i: Add support for the D1 variant
  dmaengine: sun6i: Add support for 34-bit physical addresses
  dmaengine: sun6i: Do not use virt_to_phys
  dt-bindings: dma: sun50i-a64: Add compatible for D1
  dmaengine: tegra: Remove unused switch case
  dmaengine: tegra: Fix uninitialized variable usage
  dmaengine: stm32-dma: add device_pause/device_resume support
  dmaengine: stm32-dma: rename pm ops before dma pause/resume introduction
  dmaengine: stm32-dma: pass DMA_SxSCR value to stm32_dma_handle_chan_done()
  dmaengine: stm32-dma: introduce stm32_dma_sg_inc to manage chan->next_sg
  dmaengine: stm32-dmamux: avoid reset of dmamux if used by coprocessor
  dmaengine: qcom: gpi: Add support for sc7280
  dt-bindings: dma: pl330: Add power-domains
  dmaengine: stm32-mdma: use dev_dbg on non-busy channel spurious it
  dmaengine: stm32-mdma: fix chan initialization in stm32_mdma_irq_handler()
  dmaengine: stm32-mdma: remove GISR1 register
  dmaengine: ti: deprecate '#dma-channels'
  dmaengine: mmp: deprecate '#dma-channels'
  dmaengine: pxa: deprecate '#dma-channels' and '#dma-requests'
  ...

Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml

@@ -39,6 +39,17 @@ properties:
   '#power-domain-cells':
     const: 0
 
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 1
+
+patternProperties:
+  "^dma-router@[a-f0-9]+$":
+    type: object
+    $ref: "../dma/renesas,rzn1-dmamux.yaml#"
+
 required:
   - compatible
   - reg

Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml

@@ -20,9 +20,11 @@ properties:
 
   compatible:
     oneOf:
-      - const: allwinner,sun50i-a64-dma
-      - const: allwinner,sun50i-a100-dma
-      - const: allwinner,sun50i-h6-dma
+      - enum:
+          - allwinner,sun20i-d1-dma
+          - allwinner,sun50i-a64-dma
+          - allwinner,sun50i-a100-dma
+          - allwinner,sun50i-h6-dma
       - items:
           - const: allwinner,sun8i-r40-dma
           - const: allwinner,sun50i-a64-dma
@@ -58,6 +60,7 @@ if:
   properties:
     compatible:
       enum:
+        - allwinner,sun20i-d1-dma
         - allwinner,sun50i-a100-dma
         - allwinner,sun50i-h6-dma
 

Documentation/devicetree/bindings/dma/altr,msgdma.yaml

@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Altera mSGDMA IP core
 
 maintainers:
-  - Olivier Dautricourt <olivier.dautricourt@orolia.com>
+  - Olivier Dautricourt <olivierdautricourt@gmail.com>
 
 description: |
   Altera / Intel modular Scatter-Gather Direct Memory Access (mSGDMA)

Documentation/devicetree/bindings/dma/arm,pl330.yaml

@@ -55,6 +55,9 @@ properties:
 
   dma-coherent: true
 
+  power-domains:
+    maxItems: 1
+
   resets:
     minItems: 1
     maxItems: 2

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

@@ -10,10 +10,12 @@ Required properties:
 		or one irq for pdma device
 
 Optional properties:
-- #dma-channels: Number of DMA channels supported by the controller (defaults
+- dma-channels: Number of DMA channels supported by the controller (defaults
   to 32 when not specified)
-- #dma-requests: Number of DMA requestor lines supported by the controller
+- #dma-channels: deprecated
+- dma-requests: Number of DMA requestor lines supported by the controller
   (defaults to 32 when not specified)
+- #dma-requests: deprecated
 
 "marvell,pdma-1.0"
 Used platforms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
@@ -33,7 +35,7 @@ pdma: dma-controller@d4000000 {
 	      reg = <0xd4000000 0x10000>;
 	      interrupts = <0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15>;
 	      interrupt-parent = <&intcmux32>;
-	      #dma-channels = <16>;
+	      dma-channels = <16>;
       };
 
 /*
@@ -45,7 +47,7 @@ pdma: dma-controller@d4000000 {
 	      compatible = "marvell,pdma-1.0";
 	      reg = <0xd4000000 0x10000>;
 	      interrupts = <47>;
-	      #dma-channels = <16>;
+	      dma-channels = <16>;
       };
 
 

Documentation/devicetree/bindings/dma/nvidia,tegra186-gpc-dma.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/nvidia,tegra186-gpc-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NVIDIA Tegra GPC DMA Controller Device Tree Bindings
+
+description: |
+  The Tegra General Purpose Central (GPC) DMA controller is used for faster
+  data transfers between memory to memory, memory to device and device to
+  memory.
+
+maintainers:
+  - Jon Hunter <jonathanh@nvidia.com>
+  - Rajesh Gumasta <rgumasta@nvidia.com>
+
+allOf:
+  - $ref: "dma-controller.yaml#"
+
+properties:
+  compatible:
+    oneOf:
+      - const: nvidia,tegra186-gpcdma
+      - items:
+          - const: nvidia,tegra194-gpcdma
+          - const: nvidia,tegra186-gpcdma
+
+  "#dma-cells":
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description:
+      Should contain all of the per-channel DMA interrupts in
+      ascending order with respect to the DMA channel index.
+    minItems: 1
+    maxItems: 31
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: gpcdma
+
+  iommus:
+    maxItems: 1
+
+  dma-coherent: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - resets
+  - reset-names
+  - "#dma-cells"
+  - iommus
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/memory/tegra186-mc.h>
+    #include <dt-bindings/reset/tegra186-reset.h>
+
+    dma-controller@2600000 {
+        compatible = "nvidia,tegra186-gpcdma";
+        reg = <0x2600000 0x210000>;
+        resets = <&bpmp TEGRA186_RESET_GPCDMA>;
+        reset-names = "gpcdma";
+        interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
+        #dma-cells = <1>;
+        iommus = <&smmu TEGRA186_SID_GPCDMA_0>;
+        dma-coherent;
+    };
+...

Documentation/devicetree/bindings/dma/qcom,gpi.yaml

@@ -19,9 +19,12 @@ allOf:
 properties:
   compatible:
     enum:
+      - qcom,sc7280-gpi-dma
       - qcom,sdm845-gpi-dma
       - qcom,sm8150-gpi-dma
       - qcom,sm8250-gpi-dma
+      - qcom,sm8350-gpi-dma
+      - qcom,sm8450-gpi-dma
 
   reg:
     maxItems: 1

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

@@ -42,11 +42,10 @@ properties:
           - const: renesas,rcar-dmac
 
       - items:
-          - const: renesas,dmac-r8a779a0 # R-Car V3U
-
-      - items:
-          - const: renesas,dmac-r8a779f0 # R-Car S4-8
-          - const: renesas,rcar-gen4-dmac
+          - enum:
+              - renesas,dmac-r8a779a0     # R-Car V3U
+              - renesas,dmac-r8a779f0     # R-Car S4-8
+          - const: renesas,rcar-gen4-dmac # R-Car Gen4
 
   reg: true
 
@@ -121,7 +120,6 @@ if:
     compatible:
       contains:
         enum:
-          - renesas,dmac-r8a779a0
           - renesas,rcar-gen4-dmac
 then:
   properties:

Documentation/devicetree/bindings/dma/renesas,rzn1-dmamux.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/renesas,rzn1-dmamux.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas RZ/N1 DMA mux
+
+maintainers:
+  - Miquel Raynal <miquel.raynal@bootlin.com>
+
+allOf:
+  - $ref: "dma-router.yaml#"
+
+properties:
+  compatible:
+    const: renesas,rzn1-dmamux
+
+  reg:
+    maxItems: 1
+    description: DMA mux first register offset within the system control parent.
+
+  '#dma-cells':
+    const: 6
+    description:
+      The first four cells are dedicated to the master DMA controller. The fifth
+      cell gives the DMA mux bit index that must be set starting from 0. The
+      sixth cell gives the binary value that must be written there, ie. 0 or 1.
+
+  dma-masters:
+    minItems: 1
+    maxItems: 2
+
+  dma-requests:
+    const: 32
+
+required:
+  - reg
+  - dma-requests
+
+additionalProperties: false
+
+examples:
+  - |
+    dma-router@a0 {
+      compatible = "renesas,rzn1-dmamux";
+      reg = <0xa0 4>;
+      #dma-cells = <6>;
+      dma-masters = <&dma0 &dma1>;
+      dma-requests = <32>;
+    };

Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml

@@ -28,7 +28,15 @@ allOf:
 properties:
   compatible:
     items:
-      - const: sifive,fu540-c000-pdma
+      - enum:
+          - sifive,fu540-c000-pdma
+      - const: sifive,pdma0
+    description:
+      Should be "sifive,<chip>-pdma" and "sifive,pdma<version>".
+      Supported compatible strings are -
+      "sifive,fu540-c000-pdma" for the SiFive PDMA v0 as integrated onto the
+      SiFive FU540 chip resp and "sifive,pdma0" for the SiFive PDMA v0 IP block
+      with no chip integration tweaks.
 
   reg:
     maxItems: 1
@@ -37,6 +45,12 @@ properties:
     minItems: 1
     maxItems: 8
 
+  dma-channels:
+    description: For backwards-compatibility, the default value is 4
+    minimum: 1
+    maximum: 4
+    default: 4
+
   '#dma-cells':
     const: 1
 
@@ -50,8 +64,9 @@ unevaluatedProperties: false
 examples:
   - |
     dma-controller@3000000 {
-      compatible = "sifive,fu540-c000-pdma";
+      compatible = "sifive,fu540-c000-pdma", "sifive,pdma0";
       reg = <0x3000000 0x8000>;
+      dma-channels = <4>;
       interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>, <30>;
       #dma-cells = <1>;
     };

Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml

@@ -15,7 +15,13 @@ allOf:
 
 properties:
   compatible:
-    const: snps,dma-spear1340
+    oneOf:
+      - const: snps,dma-spear1340
+      - items:
+          - enum:
+              - renesas,r9a06g032-dma
+          - const: renesas,rzn1-dma
+
 
   "#dma-cells":
     minimum: 3

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

@@ -8,10 +8,13 @@ Required properties:
 - interrupts: Should contain one interrupt shared by all channel.
 - #dma-cells: must be <1>. Used to represent the number of integer
 	cells in the dmas property of client device.
-- #dma-channels : Number of DMA channels supported. Should be 32.
+- dma-channels : Number of DMA channels supported. Should be 32.
 - clock-names: Should contain the clock of the DMA controller.
 - clocks: Should contain a clock specifier for each entry in clock-names.
 
+Deprecated properties:
+- #dma-channels : Number of DMA channels supported. Should be 32.
+
 Example:
 
 Controller:
@@ -20,7 +23,7 @@ apdma: dma-controller@20100000 {
 	reg = <0x20100000 0x4000>;
 	interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
 	#dma-cells = <1>;
-	#dma-channels = <32>;
+	dma-channels = <32>;
 	clock-names = "enable";
 	clocks = <&clk_ap_ahb_gates 5>;
 };

Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt

@@ -110,7 +110,11 @@ axi_vdma_0: axivdma@40030000 {
 Required properties:
 - dmas: a list of <[Video DMA device phandle] [Channel ID]> pairs,
 	where Channel ID is '0' for write/tx and '1' for read/rx
-	channel.
+	channel. For MCMDA, MM2S channel(write/tx) ID start from
+	'0' and is in [0-15] range. S2MM channel(read/rx) ID start
+	from '16' and is in [16-31] range. These channels ID are
+	fixed irrespective of IP configuration.
+
 - dma-names: a list of DMA channel names, one per "dmas" entry
 
 Example:

Documentation/driver-api/dmaengine/provider.rst

@@ -206,6 +206,12 @@ Currently, the types available are:
   - The device is able to perform parity check using RAID6 P+Q
     algorithm against a memory buffer.
 
+- DMA_MEMSET
+
+  - The device is able to fill memory with the provided pattern
+
+  - The pattern is treated as a single byte signed value.
+
 - DMA_INTERRUPT
 
   - The device is able to trigger a dummy transfer that will
@@ -457,7 +463,7 @@ supported.
   - Should use dma_set_residue to report it
 
   - In the case of a cyclic transfer, it should only take into
-    account the current period.
+    account the total size of the cyclic buffer.
 
   - Should return DMA_OUT_OF_ORDER if the device does not support in order
     completion and is completing the operation out of order.

MAINTAINERS

@@ -820,7 +820,7 @@ S:	Maintained
 F:	drivers/mailbox/mailbox-altera.c
 
 ALTERA MSGDMA IP CORE DRIVER
-M:	Olivier Dautricourt <olivier.dautricourt@orolia.com>
+M:	Olivier Dautricourt <olivierdautricourt@gmail.com>
 R:	Stefan Roese <sr@denx.de>
 L:	dmaengine@vger.kernel.org
 S:	Odd Fixes
@@ -19202,6 +19202,7 @@ SYNOPSYS DESIGNWARE DMAC DRIVER
 M:	Viresh Kumar <vireshk@kernel.org>
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
+F:	Documentation/devicetree/bindings/dma/renesas,rzn1-dmamux.yaml
 F:	Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml
 F:	drivers/dma/dw/
 F:	include/dt-bindings/dma/dw-dmac.h

drivers/clk/renesas/r9a06g032-clocks.c

@@ -16,13 +16,17 @@
 #include <linux/math64.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_clock.h>
 #include <linux/pm_domain.h>
 #include <linux/slab.h>
+#include <linux/soc/renesas/r9a06g032-sysctrl.h>
 #include <linux/spinlock.h>
 #include <dt-bindings/clock/r9a06g032-sysctrl.h>
 
+#define R9A06G032_SYSCTRL_DMAMUX 0xA0
+
 struct r9a06g032_gate {
 	u16 gate, reset, ready, midle,
 		scon, mirack, mistat;
@@ -315,6 +319,30 @@ struct r9a06g032_priv {
 	void __iomem *reg;
 };
 
+static struct r9a06g032_priv *sysctrl_priv;
+
+/* Exported helper to access the DMAMUX register */
+int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val)
+{
+	unsigned long flags;
+	u32 dmamux;
+
+	if (!sysctrl_priv)
+		return -EPROBE_DEFER;
+
+	spin_lock_irqsave(&sysctrl_priv->lock, flags);
+
+	dmamux = readl(sysctrl_priv->reg + R9A06G032_SYSCTRL_DMAMUX);
+	dmamux &= ~mask;
+	dmamux |= val & mask;
+	writel(dmamux, sysctrl_priv->reg + R9A06G032_SYSCTRL_DMAMUX);
+
+	spin_unlock_irqrestore(&sysctrl_priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(r9a06g032_sysctrl_set_dmamux);
+
 /* register/bit pairs are encoded as an uint16_t */
 static void
 clk_rdesc_set(struct r9a06g032_priv *clocks,
@@ -963,7 +991,17 @@ static int __init r9a06g032_clocks_probe(struct platform_device *pdev)
 	if (error)
 		return error;
 
-	return r9a06g032_add_clk_domain(dev);
+	error = r9a06g032_add_clk_domain(dev);
+	if (error)
+		return error;
+
+	sysctrl_priv = clocks;
+
+	error = of_platform_populate(np, NULL, NULL, dev);
+	if (error)
+		dev_err(dev, "Failed to populate children (%d)\n", error);
+
+	return 0;
 }
 
 static const struct of_device_id r9a06g032_match[] = {

drivers/dma/Kconfig

@@ -163,7 +163,7 @@ config DMA_SUN4I
 
 config DMA_SUN6I
 	tristate "Allwinner A31 SoCs DMA support"
-	depends on MACH_SUN6I || MACH_SUN8I || (ARM64 && ARCH_SUNXI) || COMPILE_TEST
+	depends on ARCH_SUNXI || COMPILE_TEST
 	depends on RESET_CONTROLLER
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
@@ -629,6 +629,18 @@ config TXX9_DMAC
 	  Support the TXx9 SoC internal DMA controller.  This can be
 	  integrated in chips such as the Toshiba TX4927/38/39.
 
+config TEGRA186_GPC_DMA
+	tristate "NVIDIA Tegra GPC DMA support"
+	depends on (ARCH_TEGRA || COMPILE_TEST) && ARCH_DMA_ADDR_T_64BIT
+	depends on IOMMU_API
+	select DMA_ENGINE
+	help
+	  Support for the NVIDIA Tegra General Purpose Central DMA controller.
+	  The DMA controller has multiple DMA channels which can be configured
+	  for different peripherals like UART, SPI, etc which are on APB bus.
+	  This DMA controller transfers data from memory to peripheral FIFO
+	  or vice versa. It also supports memory to memory data transfer.
+
 config TEGRA20_APB_DMA
 	tristate "NVIDIA Tegra20 APB DMA support"
 	depends on ARCH_TEGRA || COMPILE_TEST

drivers/dma/Makefile

@@ -72,6 +72,7 @@ obj-$(CONFIG_STM32_MDMA) += stm32-mdma.o
 obj-$(CONFIG_SPRD_DMA) += sprd-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
+obj-$(CONFIG_TEGRA186_GPC_DMA) += tegra186-gpc-dma.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
 obj-$(CONFIG_TEGRA210_ADMA) += tegra210-adma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o

drivers/dma/amba-pl08x.c

@@ -1535,14 +1535,6 @@ static void pl08x_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(to_virt_chan(chan));
 }
 
-static struct dma_async_tx_descriptor *pl08x_prep_dma_interrupt(
-		struct dma_chan *chan, unsigned long flags)
-{
-	struct dma_async_tx_descriptor *retval = NULL;
-
-	return retval;
-}
-
 /*
  * Code accessing dma_async_is_complete() in a tight loop may give problems.
  * If slaves are relying on interrupts to signal completion this function
@@ -2760,7 +2752,6 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->memcpy.dev = &adev->dev;
 	pl08x->memcpy.device_free_chan_resources = pl08x_free_chan_resources;
 	pl08x->memcpy.device_prep_dma_memcpy = pl08x_prep_dma_memcpy;
-	pl08x->memcpy.device_prep_dma_interrupt = pl08x_prep_dma_interrupt;
 	pl08x->memcpy.device_tx_status = pl08x_dma_tx_status;
 	pl08x->memcpy.device_issue_pending = pl08x_issue_pending;
 	pl08x->memcpy.device_config = pl08x_config;
@@ -2787,8 +2778,6 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		pl08x->slave.dev = &adev->dev;
 		pl08x->slave.device_free_chan_resources =
 			pl08x_free_chan_resources;
-		pl08x->slave.device_prep_dma_interrupt =
-			pl08x_prep_dma_interrupt;
 		pl08x->slave.device_tx_status = pl08x_dma_tx_status;
 		pl08x->slave.device_issue_pending = pl08x_issue_pending;
 		pl08x->slave.device_prep_slave_sg = pl08x_prep_slave_sg;

drivers/dma/at_hdmac.c

@@ -942,6 +942,7 @@ atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	struct at_desc		*desc;
 	void __iomem		*vaddr;
 	dma_addr_t		paddr;
+	char			fill_pattern;
 
 	dev_vdbg(chan2dev(chan), "%s: d%pad v0x%x l0x%zx f0x%lx\n", __func__,
 		&dest, value, len, flags);
@@ -963,7 +964,14 @@ atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 			__func__);
 		return NULL;
 	}
-	*(u32*)vaddr = value;
+
+	/* Only the first byte of value is to be used according to dmaengine */
+	fill_pattern = (char)value;
+
+	*(u32*)vaddr = (fill_pattern << 24) |
+		       (fill_pattern << 16) |
+		       (fill_pattern << 8) |
+		       fill_pattern;
 
 	desc = atc_create_memset_desc(chan, paddr, dest, len);
 	if (!desc) {

drivers/dma/at_xdmac.c

@@ -1202,6 +1202,7 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	unsigned long		flags;
 	size_t			ublen;
 	u32			dwidth;
+	char			pattern;
 	/*
 	 * WARNING: The channel configuration is set here since there is no
 	 * dmaengine_slave_config call in this case. Moreover we don't know the
@@ -1244,10 +1245,16 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 
 	chan_cc |= AT_XDMAC_CC_DWIDTH(dwidth);
 
+	/* Only the first byte of value is to be used according to dmaengine */
+	pattern = (char)value;
+
 	ublen = len >> dwidth;
 
 	desc->lld.mbr_da = dst_addr;
-	desc->lld.mbr_ds = value;
+	desc->lld.mbr_ds = (pattern << 24) |
+			   (pattern << 16) |
+			   (pattern << 8) |
+			   pattern;
 	desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV3
 		| AT_XDMAC_MBR_UBC_NDEN
 		| AT_XDMAC_MBR_UBC_NSEN

drivers/dma/bestcomm/bestcomm.c

@@ -17,7 +17,9 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <asm/io.h>
 #include <asm/irq.h>

drivers/dma/dma-jz4780.c

@@ -8,6 +8,7 @@
 
 #include <linux/clk.h>
 #include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -911,6 +912,14 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 
 	dd = &jzdma->dma_device;
 
+	/*
+	 * The real segment size limit is dependent on the size unit selected
+	 * for the transfer. Because the size unit is selected automatically
+	 * and may be as small as 1 byte, use a safe limit of 2^24-1 bytes to
+	 * ensure the 24-bit transfer count in the descriptor cannot overflow.
+	 */
+	dma_set_max_seg_size(dev, 0xffffff);
+
 	dma_cap_set(DMA_MEMCPY, dd->cap_mask);
 	dma_cap_set(DMA_SLAVE, dd->cap_mask);
 	dma_cap_set(DMA_CYCLIC, dd->cap_mask);

drivers/dma/dmaengine.c

@@ -1053,9 +1053,7 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	 * When the chan_id is a negative value, we are dynamically adding
 	 * the channel. Otherwise we are static enumerating.
 	 */
-	mutex_lock(&device->chan_mutex);
 	chan->chan_id = ida_alloc(&device->chan_ida, GFP_KERNEL);
-	mutex_unlock(&device->chan_mutex);
 	if (chan->chan_id < 0) {
 		pr_err("%s: unable to alloc ida for chan: %d\n",
 		       __func__, chan->chan_id);
@@ -1078,9 +1076,7 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	return 0;
 
  err_out_ida:
-	mutex_lock(&device->chan_mutex);
 	ida_free(&device->chan_ida, chan->chan_id);
-	mutex_unlock(&device->chan_mutex);
  err_free_dev:
 	kfree(chan->dev);
  err_free_local:
@@ -1113,9 +1109,7 @@ static void __dma_async_device_channel_unregister(struct dma_device *device,
 	device->chancnt--;
 	chan->dev->chan = NULL;
 	mutex_unlock(&dma_list_mutex);
-	mutex_lock(&device->chan_mutex);
 	ida_free(&device->chan_ida, chan->chan_id);
-	mutex_unlock(&device->chan_mutex);
 	device_unregister(&chan->dev->device);
 	free_percpu(chan->local);
 }
@@ -1250,7 +1244,6 @@ int dma_async_device_register(struct dma_device *device)
 	if (rc != 0)
 		return rc;
 
-	mutex_init(&device->chan_mutex);
 	ida_init(&device->chan_ida);
 
 	/* represent channels in sysfs. Probably want devs too */

drivers/dma/dmatest.c

@@ -675,10 +675,16 @@ static int dmatest_func(void *data)
 	/*
 	 * src and dst buffers are freed by ourselves below
 	 */
-	if (params->polled)
+	if (params->polled) {
 		flags = DMA_CTRL_ACK;
-	else
-		flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
+	} else {
+		if (dma_has_cap(DMA_INTERRUPT, dev->cap_mask)) {
+			flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
+		} else {
+			pr_err("Channel does not support interrupt!\n");
+			goto err_pq_array;
+		}
+	}
 
 	ktime = ktime_get();
 	while (!(kthread_should_stop() ||
@@ -906,6 +912,7 @@ static int dmatest_func(void *data)
 	runtime = ktime_to_us(ktime);
 
 	ret = 0;
+err_pq_array:
 	kfree(dma_pq);
 err_srcs_array:
 	kfree(srcs);

drivers/dma/dw/Kconfig

@@ -16,6 +16,15 @@ config DW_DMAC
 	  Support the Synopsys DesignWare AHB DMA controller. This
 	  can be integrated in chips such as the Intel Cherrytrail.
 
+config RZN1_DMAMUX
+	tristate "Renesas RZ/N1 DMAMUX driver"
+	depends on DW_DMAC
+	depends on ARCH_RZN1 || COMPILE_TEST
+	help
+	  Support the Renesas RZ/N1 DMAMUX which is located in front of
+	  the Synopsys DesignWare AHB DMA controller located on Renesas
+	  SoCs.
+
 config DW_DMAC_PCI
 	tristate "Synopsys DesignWare AHB DMA PCI driver"
 	depends on PCI

drivers/dma/dw/Makefile

@@ -9,3 +9,5 @@ dw_dmac-$(CONFIG_OF)		+= of.o
 
 obj-$(CONFIG_DW_DMAC_PCI)	+= dw_dmac_pci.o
 dw_dmac_pci-y			:= pci.o
+
+obj-$(CONFIG_RZN1_DMAMUX)	+= rzn1-dmamux.o

drivers/dma/dw/platform.c

@@ -137,6 +137,7 @@ static void dw_shutdown(struct platform_device *pdev)
 #ifdef CONFIG_OF
 static const struct of_device_id dw_dma_of_id_table[] = {
 	{ .compatible = "snps,dma-spear1340", .data = &dw_dma_chip_pdata },
+	{ .compatible = "renesas,rzn1-dma", .data = &dw_dma_chip_pdata },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);

drivers/dma/dw/rzn1-dmamux.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 Schneider-Electric
+ * Author: Miquel Raynal <miquel.raynal@bootlin.com
+ * Based on TI crossbar driver written by Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+#include <linux/bitops.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/slab.h>
+#include <linux/soc/renesas/r9a06g032-sysctrl.h>
+#include <linux/types.h>
+
+#define RNZ1_DMAMUX_NCELLS 6
+#define RZN1_DMAMUX_MAX_LINES 64
+#define RZN1_DMAMUX_LINES_PER_CTLR 16
+
+struct rzn1_dmamux_data {
+	struct dma_router dmarouter;
+	DECLARE_BITMAP(used_chans, 2 * RZN1_DMAMUX_LINES_PER_CTLR);
+};
+
+struct rzn1_dmamux_map {
+	unsigned int req_idx;
+};
+
+static void rzn1_dmamux_free(struct device *dev, void *route_data)
+{
+	struct rzn1_dmamux_data *dmamux = dev_get_drvdata(dev);
+	struct rzn1_dmamux_map *map = route_data;
+
+	dev_dbg(dev, "Unmapping DMAMUX request %u\n", map->req_idx);
+
+	clear_bit(map->req_idx, dmamux->used_chans);
+
+	kfree(map);
+}
+
+static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec,
+					struct of_dma *ofdma)
+{
+	struct platform_device *pdev = of_find_device_by_node(ofdma->of_node);
+	struct rzn1_dmamux_data *dmamux = platform_get_drvdata(pdev);
+	struct rzn1_dmamux_map *map;
+	unsigned int dmac_idx, chan, val;
+	u32 mask;
+	int ret;
+
+	if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS)
+		return ERR_PTR(-EINVAL);
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	chan = dma_spec->args[0];
+	map->req_idx = dma_spec->args[4];
+	val = dma_spec->args[5];
+	dma_spec->args_count -= 2;
+
+	if (chan >= RZN1_DMAMUX_LINES_PER_CTLR) {
+		dev_err(&pdev->dev, "Invalid DMA request line: %u\n", chan);
+		ret = -EINVAL;
+		goto free_map;
+	}
+
+	if (map->req_idx >= RZN1_DMAMUX_MAX_LINES ||
+	    (map->req_idx % RZN1_DMAMUX_LINES_PER_CTLR) != chan) {
+		dev_err(&pdev->dev, "Invalid MUX request line: %u\n", map->req_idx);
+		ret = -EINVAL;
+		goto free_map;
+	}
+
+	dmac_idx = map->req_idx >= RZN1_DMAMUX_LINES_PER_CTLR ? 1 : 0;
+	dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", dmac_idx);
+	if (!dma_spec->np) {
+		dev_err(&pdev->dev, "Can't get DMA master\n");
+		ret = -EINVAL;
+		goto free_map;
+	}
+
+	dev_dbg(&pdev->dev, "Mapping DMAMUX request %u to DMAC%u request %u\n",
+		map->req_idx, dmac_idx, chan);
+
+	if (test_and_set_bit(map->req_idx, dmamux->used_chans)) {
+		ret = -EBUSY;
+		goto free_map;
+	}
+
+	mask = BIT(map->req_idx);
+	ret = r9a06g032_sysctrl_set_dmamux(mask, val ? mask : 0);
+	if (ret)
+		goto clear_bitmap;
+
+	return map;
+
+clear_bitmap:
+	clear_bit(map->req_idx, dmamux->used_chans);
+free_map:
+	kfree(map);
+
+	return ERR_PTR(ret);
+}
+
+static const struct of_device_id rzn1_dmac_match[] = {
+	{ .compatible = "renesas,rzn1-dma" },
+	{}
+};
+
+static int rzn1_dmamux_probe(struct platform_device *pdev)
+{
+	struct device_node *mux_node = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct device_node *dmac_node;
+	struct rzn1_dmamux_data *dmamux;
+
+	dmamux = devm_kzalloc(&pdev->dev, sizeof(*dmamux), GFP_KERNEL);
+	if (!dmamux)
+		return -ENOMEM;
+
+	dmac_node = of_parse_phandle(mux_node, "dma-masters", 0);
+	if (!dmac_node)
+		return dev_err_probe(&pdev->dev, -ENODEV, "Can't get DMA master node\n");
+
+	match = of_match_node(rzn1_dmac_match, dmac_node);
+	of_node_put(dmac_node);
+	if (!match)
+		return dev_err_probe(&pdev->dev, -EINVAL, "DMA master is not supported\n");
+
+	dmamux->dmarouter.dev = &pdev->dev;
+	dmamux->dmarouter.route_free = rzn1_dmamux_free;
+
+	platform_set_drvdata(pdev, dmamux);
+
+	return of_dma_router_register(mux_node, rzn1_dmamux_route_allocate,
+				      &dmamux->dmarouter);
+}
+
+static const struct of_device_id rzn1_dmamux_match[] = {
+	{ .compatible = "renesas,rzn1-dmamux" },
+	{}
+};
+
+static struct platform_driver rzn1_dmamux_driver = {
+	.driver = {
+		.name = "renesas,rzn1-dmamux",
+		.of_match_table = rzn1_dmamux_match,
+	},
+	.probe	= rzn1_dmamux_probe,
+};
+module_platform_driver(rzn1_dmamux_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com");
+MODULE_DESCRIPTION("Renesas RZ/N1 DMAMUX driver");

drivers/dma/ep93xx_dma.c

@@ -132,7 +132,7 @@ struct ep93xx_dma_desc {
 /**
  * struct ep93xx_dma_chan - an EP93xx DMA M2P/M2M channel
  * @chan: dmaengine API channel
- * @edma: pointer to to the engine device
+ * @edma: pointer to the engine device
  * @regs: memory mapped registers
  * @irq: interrupt number of the channel
  * @clk: clock used by this channel

drivers/dma/idxd/cdev.c

@@ -99,7 +99,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	ctx->wq = wq;
 	filp->private_data = ctx;
 
-	if (device_pasid_enabled(idxd)) {
+	if (device_user_pasid_enabled(idxd)) {
 		sva = iommu_sva_bind_device(dev, current->mm, NULL);
 		if (IS_ERR(sva)) {
 			rc = PTR_ERR(sva);
@@ -152,7 +152,7 @@ static int idxd_cdev_release(struct inode *node, struct file *filep)
 	if (wq_shared(wq)) {
 		idxd_device_drain_pasid(idxd, ctx->pasid);
 	} else {
-		if (device_pasid_enabled(idxd)) {
+		if (device_user_pasid_enabled(idxd)) {
 			/* The wq disable in the disable pasid function will drain the wq */
 			rc = idxd_wq_disable_pasid(wq);
 			if (rc < 0)
@@ -314,7 +314,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	wq->type = IDXD_WQT_USER;
-	rc = __drv_enable_wq(wq);
+	rc = drv_enable_wq(wq);
 	if (rc < 0)
 		goto err;
 
@@ -329,7 +329,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_cdev:
-	__drv_disable_wq(wq);
+	drv_disable_wq(wq);
 err:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
@@ -342,7 +342,7 @@ static void idxd_user_drv_remove(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_del_cdev(wq);
-	__drv_disable_wq(wq);
+	drv_disable_wq(wq);
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 }
@@ -369,10 +369,16 @@ int idxd_cdev_register(void)
 		rc = alloc_chrdev_region(&ictx[i].devt, 0, MINORMASK,
 					 ictx[i].name);
 		if (rc)
-			return rc;
+			goto err_free_chrdev_region;
 	}
 
 	return 0;
+
+err_free_chrdev_region:
+	for (i--; i >= 0; i--)
+		unregister_chrdev_region(ictx[i].devt, MINORMASK);
+
+	return rc;
 }
 
 void idxd_cdev_remove(void)

drivers/dma/idxd/device.c

@@ -184,7 +184,7 @@ int idxd_wq_enable(struct idxd_wq *wq)
 
 	if (wq->state == IDXD_WQ_ENABLED) {
 		dev_dbg(dev, "WQ %d already enabled\n", wq->id);
-		return -ENXIO;
+		return 0;
 	}
 
 	idxd_cmd_exec(idxd, IDXD_CMD_ENABLE_WQ, wq->id, &status);
@@ -299,24 +299,46 @@ void idxd_wqs_unmap_portal(struct idxd_device *idxd)
 	}
 }
 
-int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid)
+static void __idxd_wq_set_priv_locked(struct idxd_wq *wq, int priv)
 {
 	struct idxd_device *idxd = wq->idxd;
-	int rc;
 	union wqcfg wqcfg;
 	unsigned int offset;
 
-	rc = idxd_wq_disable(wq, false);
-	if (rc < 0)
-		return rc;
+	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PRIVL_IDX);
+	spin_lock(&idxd->dev_lock);
+	wqcfg.bits[WQCFG_PRIVL_IDX] = ioread32(idxd->reg_base + offset);
+	wqcfg.priv = priv;
+	wq->wqcfg->bits[WQCFG_PRIVL_IDX] = wqcfg.bits[WQCFG_PRIVL_IDX];
+	iowrite32(wqcfg.bits[WQCFG_PRIVL_IDX], idxd->reg_base + offset);
+	spin_unlock(&idxd->dev_lock);
+}
+
+static void __idxd_wq_set_pasid_locked(struct idxd_wq *wq, int pasid)
+{
+	struct idxd_device *idxd = wq->idxd;
+	union wqcfg wqcfg;
+	unsigned int offset;
 
 	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PASID_IDX);
 	spin_lock(&idxd->dev_lock);
 	wqcfg.bits[WQCFG_PASID_IDX] = ioread32(idxd->reg_base + offset);
 	wqcfg.pasid_en = 1;
 	wqcfg.pasid = pasid;
+	wq->wqcfg->bits[WQCFG_PASID_IDX] = wqcfg.bits[WQCFG_PASID_IDX];
 	iowrite32(wqcfg.bits[WQCFG_PASID_IDX], idxd->reg_base + offset);
 	spin_unlock(&idxd->dev_lock);
+}
+
+int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid)
+{
+	int rc;
+
+	rc = idxd_wq_disable(wq, false);
+	if (rc < 0)
+		return rc;
+
+	__idxd_wq_set_pasid_locked(wq, pasid);
 
 	rc = idxd_wq_enable(wq);
 	if (rc < 0)
@@ -555,19 +577,15 @@ int idxd_device_disable(struct idxd_device *idxd)
 		return -ENXIO;
 	}
 
-	spin_lock(&idxd->dev_lock);
 	idxd_device_clear_state(idxd);
-	idxd->state = IDXD_DEV_DISABLED;
-	spin_unlock(&idxd->dev_lock);
 	return 0;
 }
 
 void idxd_device_reset(struct idxd_device *idxd)
 {
 	idxd_cmd_exec(idxd, IDXD_CMD_RESET_DEVICE, 0, NULL);
-	spin_lock(&idxd->dev_lock);
 	idxd_device_clear_state(idxd);
-	idxd->state = IDXD_DEV_DISABLED;
+	spin_lock(&idxd->dev_lock);
 	idxd_unmask_error_interrupts(idxd);
 	spin_unlock(&idxd->dev_lock);
 }
@@ -694,15 +712,16 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
 {
 	int i;
 
-	lockdep_assert_held(&idxd->dev_lock);
 	for (i = 0; i < idxd->max_wqs; i++) {
 		struct idxd_wq *wq = idxd->wqs[i];
 
+		mutex_lock(&wq->wq_lock);
 		if (wq->state == IDXD_WQ_ENABLED) {
 			idxd_wq_disable_cleanup(wq);
 			wq->state = IDXD_WQ_DISABLED;
 		}
 		idxd_wq_device_reset_cleanup(wq);
+		mutex_unlock(&wq->wq_lock);
 	}
 }
 
@@ -711,9 +730,12 @@ void idxd_device_clear_state(struct idxd_device *idxd)
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
 		return;
 
+	idxd_device_wqs_clear_state(idxd);
+	spin_lock(&idxd->dev_lock);
 	idxd_groups_clear_state(idxd);
 	idxd_engines_clear_state(idxd);
-	idxd_device_wqs_clear_state(idxd);
+	idxd->state = IDXD_DEV_DISABLED;
+	spin_unlock(&idxd->dev_lock);
 }
 
 static void idxd_group_config_write(struct idxd_group *group)
@@ -799,7 +821,7 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 	 */
 	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
 		wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
-		wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
+		wq->wqcfg->bits[i] |= ioread32(idxd->reg_base + wq_offset);
 	}
 
 	if (wq->size == 0 && wq->type != IDXD_WQT_NONE)
@@ -815,14 +837,8 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 	if (wq_dedicated(wq))
 		wq->wqcfg->mode = 1;
 
-	if (device_pasid_enabled(idxd)) {
-		wq->wqcfg->pasid_en = 1;
-		if (wq->type == IDXD_WQT_KERNEL && wq_dedicated(wq))
-			wq->wqcfg->pasid = idxd->pasid;
-	}
-
 	/*
-	 * Here the priv bit is set depending on the WQ type. priv = 1 if the
+	 * The WQ priv bit is set depending on the WQ type. priv = 1 if the
 	 * WQ type is kernel to indicate privileged access. This setting only
 	 * matters for dedicated WQ. According to the DSA spec:
 	 * If the WQ is in dedicated mode, WQ PASID Enable is 1, and the
@@ -832,7 +848,6 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 	 * In the case of a dedicated kernel WQ that is not able to support
 	 * the PASID cap, then the configuration will be rejected.
 	 */
-	wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL);
 	if (wq_dedicated(wq) && wq->wqcfg->pasid_en &&
 	    !idxd_device_pasid_priv_enabled(idxd) &&
 	    wq->type == IDXD_WQT_KERNEL) {
@@ -953,7 +968,7 @@ static int idxd_wqs_setup(struct idxd_device *idxd)
 		if (!wq->group)
 			continue;
 
-		if (wq_shared(wq) && !device_swq_supported(idxd)) {
+		if (wq_shared(wq) && !wq_shared_supported(wq)) {
 			idxd->cmd_status = IDXD_SCMD_WQ_NO_SWQ_SUPPORT;
 			dev_warn(dev, "No shared wq support but configured.\n");
 			return -EINVAL;
@@ -1018,6 +1033,9 @@ static int idxd_wq_load_config(struct idxd_wq *wq)
 
 	wq->priority = wq->wqcfg->priority;
 
+	wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift;
+	wq->max_batch_size = 1ULL << wq->wqcfg->max_batch_shift;
+
 	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
 		wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);
 		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wqcfg_offset, wq->wqcfg->bits[i]);
@@ -1161,7 +1179,9 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
 	struct idxd_device *idxd = wq->idxd;
 	struct idxd_irq_entry *ie = &wq->ie;
 
-	synchronize_irq(ie->vector);
+	if (wq->type != IDXD_WQT_KERNEL)
+		return;
+
 	free_irq(ie->vector, ie);
 	idxd_flush_pending_descs(ie);
 	if (idxd->request_int_handles)
@@ -1180,6 +1200,9 @@ int idxd_wq_request_irq(struct idxd_wq *wq)
 	struct idxd_irq_entry *ie;
 	int rc;
 
+	if (wq->type != IDXD_WQT_KERNEL)
+		return 0;
+
 	ie = &wq->ie;
 	ie->vector = pci_irq_vector(pdev, ie->id);
 	ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID;
@@ -1211,7 +1234,7 @@ int idxd_wq_request_irq(struct idxd_wq *wq)
 	return rc;
 }
 
-int __drv_enable_wq(struct idxd_wq *wq)
+int drv_enable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1245,7 +1268,7 @@ int __drv_enable_wq(struct idxd_wq *wq)
 
 	/* Shared WQ checks */
 	if (wq_shared(wq)) {
-		if (!device_swq_supported(idxd)) {
+		if (!wq_shared_supported(wq)) {
 			idxd->cmd_status = IDXD_SCMD_WQ_NO_SVM;
 			dev_dbg(dev, "PASID not enabled and shared wq.\n");
 			goto err;
@@ -1265,6 +1288,29 @@ int __drv_enable_wq(struct idxd_wq *wq)
 		}
 	}
 
+	/*
+	 * In the event that the WQ is configurable for pasid and priv bits.
+	 * For kernel wq, the driver should setup the pasid, pasid_en, and priv bit.
+	 * However, for non-kernel wq, the driver should only set the pasid_en bit for
+	 * shared wq. A dedicated wq that is not 'kernel' type will configure pasid and
+	 * pasid_en later on so there is no need to setup.
+	 */
+	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
+		int priv = 0;
+
+		if (wq_pasid_enabled(wq)) {
+			if (is_idxd_wq_kernel(wq) || wq_shared(wq)) {
+				u32 pasid = wq_dedicated(wq) ? idxd->pasid : 0;
+
+				__idxd_wq_set_pasid_locked(wq, pasid);
+			}
+		}
+
+		if (is_idxd_wq_kernel(wq))
+			priv = 1;
+		__idxd_wq_set_priv_locked(wq, priv);
+	}
+
 	rc = 0;
 	spin_lock(&idxd->dev_lock);
 	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
@@ -1289,8 +1335,36 @@ int __drv_enable_wq(struct idxd_wq *wq)
 	}
 
 	wq->client_count = 0;
+
+	rc = idxd_wq_request_irq(wq);
+	if (rc < 0) {
+		idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR;
+		dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc);
+		goto err_irq;
+	}
+
+	rc = idxd_wq_alloc_resources(wq);
+	if (rc < 0) {
+		idxd->cmd_status = IDXD_SCMD_WQ_RES_ALLOC_ERR;
+		dev_dbg(dev, "WQ resource alloc failed\n");
+		goto err_res_alloc;
+	}
+
+	rc = idxd_wq_init_percpu_ref(wq);
+	if (rc < 0) {
+		idxd->cmd_status = IDXD_SCMD_PERCPU_ERR;
+		dev_dbg(dev, "percpu_ref setup failed\n");
+		goto err_ref;
+	}
+
 	return 0;
 
+err_ref:
+	idxd_wq_free_resources(wq);
+err_res_alloc:
+	idxd_wq_free_irq(wq);
+err_irq:
+	idxd_wq_unmap_portal(wq);
 err_map_portal:
 	rc = idxd_wq_disable(wq, false);
 	if (rc < 0)
@@ -1299,17 +1373,7 @@ int __drv_enable_wq(struct idxd_wq *wq)
 	return rc;
 }
 
-int drv_enable_wq(struct idxd_wq *wq)
-{
-	int rc;
-
-	mutex_lock(&wq->wq_lock);
-	rc = __drv_enable_wq(wq);
-	mutex_unlock(&wq->wq_lock);
-	return rc;
-}
-
-void __drv_disable_wq(struct idxd_wq *wq)
+void drv_disable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1320,21 +1384,16 @@ void __drv_disable_wq(struct idxd_wq *wq)
 		dev_warn(dev, "Clients has claim on wq %d: %d\n",
 			 wq->id, idxd_wq_refcount(wq));
 
+	idxd_wq_free_resources(wq);
 	idxd_wq_unmap_portal(wq);
-
 	idxd_wq_drain(wq);
+	idxd_wq_free_irq(wq);
 	idxd_wq_reset(wq);
-
+	percpu_ref_exit(&wq->wq_active);
+	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
 
-void drv_disable_wq(struct idxd_wq *wq)
-{
-	mutex_lock(&wq->wq_lock);
-	__drv_disable_wq(wq);
-	mutex_unlock(&wq->wq_lock);
-}
-
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
 {
 	struct idxd_device *idxd = idxd_dev_to_idxd(idxd_dev);

drivers/dma/idxd/dma.c

@@ -87,6 +87,27 @@ static inline void idxd_prep_desc_common(struct idxd_wq *wq,
 	hw->completion_addr = compl;
 }
 
+static struct dma_async_tx_descriptor *
+idxd_dma_prep_interrupt(struct dma_chan *c, unsigned long flags)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+	u32 desc_flags;
+	struct idxd_desc *desc;
+
+	if (wq->state != IDXD_WQ_ENABLED)
+		return NULL;
+
+	op_flag_setup(flags, &desc_flags);
+	desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(desc))
+		return NULL;
+
+	idxd_prep_desc_common(wq, desc->hw, DSA_OPCODE_NOOP,
+			      0, 0, 0, desc->compl_dma, desc_flags);
+	desc->txd.flags = flags;
+	return &desc->txd;
+}
+
 static struct dma_async_tx_descriptor *
 idxd_dma_submit_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 		       dma_addr_t dma_src, size_t len, unsigned long flags)
@@ -193,10 +214,12 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	INIT_LIST_HEAD(&dma->channels);
 	dma->dev = dev;
 
+	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
 	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
 	dma_cap_set(DMA_COMPLETION_NO_ORDER, dma->cap_mask);
 	dma->device_release = idxd_dma_release;
 
+	dma->device_prep_dma_interrupt = idxd_dma_prep_interrupt;
 	if (idxd->hw.opcap.bits[0] & IDXD_OPCAP_MEMMOVE) {
 		dma_cap_set(DMA_MEMCPY, dma->cap_mask);
 		dma->device_prep_dma_memcpy = idxd_dma_submit_memcpy;
@@ -227,7 +250,7 @@ void idxd_unregister_dma_device(struct idxd_device *idxd)
 	dma_async_device_unregister(&idxd->idxd_dma->dma);
 }
 
-int idxd_register_dma_channel(struct idxd_wq *wq)
+static int idxd_register_dma_channel(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct dma_device *dma = &idxd->idxd_dma->dma;
@@ -264,7 +287,7 @@ int idxd_register_dma_channel(struct idxd_wq *wq)
 	return 0;
 }
 
-void idxd_unregister_dma_channel(struct idxd_wq *wq)
+static void idxd_unregister_dma_channel(struct idxd_wq *wq)
 {
 	struct idxd_dma_chan *idxd_chan = wq->idxd_chan;
 	struct dma_chan *chan = &idxd_chan->chan;
@@ -290,34 +313,13 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 	mutex_lock(&wq->wq_lock);
 	wq->type = IDXD_WQT_KERNEL;
 
-	rc = idxd_wq_request_irq(wq);
-	if (rc < 0) {
-		idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR;
-		dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc);
-		goto err_irq;
-	}
-
-	rc = __drv_enable_wq(wq);
+	rc = drv_enable_wq(wq);
 	if (rc < 0) {
 		dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
 		rc = -ENXIO;
 		goto err;
 	}
 
-	rc = idxd_wq_alloc_resources(wq);
-	if (rc < 0) {
-		idxd->cmd_status = IDXD_SCMD_WQ_RES_ALLOC_ERR;
-		dev_dbg(dev, "WQ resource alloc failed\n");
-		goto err_res_alloc;
-	}
-
-	rc = idxd_wq_init_percpu_ref(wq);
-	if (rc < 0) {
-		idxd->cmd_status = IDXD_SCMD_PERCPU_ERR;
-		dev_dbg(dev, "percpu_ref setup failed\n");
-		goto err_ref;
-	}
-
 	rc = idxd_register_dma_channel(wq);
 	if (rc < 0) {
 		idxd->cmd_status = IDXD_SCMD_DMA_CHAN_ERR;
@@ -330,15 +332,8 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_dma:
-	__idxd_wq_quiesce(wq);
-	percpu_ref_exit(&wq->wq_active);
-err_ref:
-	idxd_wq_free_resources(wq);
-err_res_alloc:
-	__drv_disable_wq(wq);
+	drv_disable_wq(wq);
 err:
-	idxd_wq_free_irq(wq);
-err_irq:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 	return rc;
@@ -351,11 +346,7 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	mutex_lock(&wq->wq_lock);
 	__idxd_wq_quiesce(wq);
 	idxd_unregister_dma_channel(wq);
-	idxd_wq_free_resources(wq);
-	__drv_disable_wq(wq);
-	percpu_ref_exit(&wq->wq_active);
-	idxd_wq_free_irq(wq);
-	wq->type = IDXD_WQT_NONE;
+	drv_disable_wq(wq);
 	mutex_unlock(&wq->wq_lock);
 }
 

drivers/dma/idxd/idxd.h

@@ -239,6 +239,7 @@ enum idxd_device_flag {
 	IDXD_FLAG_CONFIGURABLE = 0,
 	IDXD_FLAG_CMD_RUNNING,
 	IDXD_FLAG_PASID_ENABLED,
+	IDXD_FLAG_USER_PASID_ENABLED,
 };
 
 struct idxd_dma_dev {
@@ -469,9 +470,20 @@ static inline bool device_pasid_enabled(struct idxd_device *idxd)
 	return test_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
 }
 
-static inline bool device_swq_supported(struct idxd_device *idxd)
+static inline bool device_user_pasid_enabled(struct idxd_device *idxd)
 {
-	return (support_enqcmd && device_pasid_enabled(idxd));
+	return test_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags);
+}
+
+static inline bool wq_pasid_enabled(struct idxd_wq *wq)
+{
+	return (is_idxd_wq_kernel(wq) && device_pasid_enabled(wq->idxd)) ||
+	       (is_idxd_wq_user(wq) && device_user_pasid_enabled(wq->idxd));
+}
+
+static inline bool wq_shared_supported(struct idxd_wq *wq)
+{
+	return (support_enqcmd && wq_pasid_enabled(wq));
 }
 
 enum idxd_portal_prot {
@@ -559,9 +571,7 @@ void idxd_unregister_idxd_drv(void);
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev);
 void idxd_device_drv_remove(struct idxd_dev *idxd_dev);
 int drv_enable_wq(struct idxd_wq *wq);
-int __drv_enable_wq(struct idxd_wq *wq);
 void drv_disable_wq(struct idxd_wq *wq);
-void __drv_disable_wq(struct idxd_wq *wq);
 int idxd_device_init_reset(struct idxd_device *idxd);
 int idxd_device_enable(struct idxd_device *idxd);
 int idxd_device_disable(struct idxd_device *idxd);
@@ -602,8 +612,6 @@ int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
 /* dmaengine */
 int idxd_register_dma_device(struct idxd_device *idxd);
 void idxd_unregister_dma_device(struct idxd_device *idxd);
-int idxd_register_dma_channel(struct idxd_wq *wq);
-void idxd_unregister_dma_channel(struct idxd_wq *wq);
 void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
 void idxd_dma_complete_txd(struct idxd_desc *desc,
 			   enum idxd_complete_type comp_type, bool free_desc);

drivers/dma/idxd/init.c

@@ -512,18 +512,15 @@ static int idxd_probe(struct idxd_device *idxd)
 	dev_dbg(dev, "IDXD reset complete\n");
 
 	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM) && sva) {
-		rc = iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA);
-		if (rc == 0) {
-			rc = idxd_enable_system_pasid(idxd);
-			if (rc < 0) {
-				iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
-				dev_warn(dev, "Failed to enable PASID. No SVA support: %d\n", rc);
-			} else {
-				set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
-			}
-		} else {
-			dev_warn(dev, "Unable to turn on SVA feature.\n");
-		}
+		if (iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA))
+			dev_warn(dev, "Unable to turn on user SVA feature.\n");
+		else
+			set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags);
+
+		if (idxd_enable_system_pasid(idxd))
+			dev_warn(dev, "No in-kernel DMA with PASID.\n");
+		else
+			set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
 	} else if (!sva) {
 		dev_warn(dev, "User forced SVA off via module param.\n");
 	}
@@ -561,7 +558,8 @@ static int idxd_probe(struct idxd_device *idxd)
  err:
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
+	if (device_user_pasid_enabled(idxd))
+		iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
 	return rc;
 }
 
@@ -574,7 +572,8 @@ static void idxd_cleanup(struct idxd_device *idxd)
 	idxd_cleanup_internals(idxd);
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
+	if (device_user_pasid_enabled(idxd))
+		iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA);
 }
 
 static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -691,7 +690,8 @@ static void idxd_remove(struct pci_dev *pdev)
 	free_irq(irq_entry->vector, irq_entry);
 	pci_free_irq_vectors(pdev);
 	pci_iounmap(pdev, idxd->reg_base);
-	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
+	if (device_user_pasid_enabled(idxd))
+		iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
 	pci_disable_device(pdev);
 	destroy_workqueue(idxd->wq);
 	perfmon_pmu_remove(idxd);

drivers/dma/idxd/registers.h

@@ -353,6 +353,7 @@ union wqcfg {
 } __packed;
 
 #define WQCFG_PASID_IDX                2
+#define WQCFG_PRIVL_IDX		2
 #define WQCFG_OCCUP_IDX		6
 
 #define WQCFG_OCCUP_MASK	0xffff

drivers/dma/idxd/sysfs.c

@@ -588,7 +588,7 @@ static ssize_t wq_mode_store(struct device *dev,
 	if (sysfs_streq(buf, "dedicated")) {
 		set_bit(WQ_FLAG_DEDICATED, &wq->flags);
 		wq->threshold = 0;
-	} else if (sysfs_streq(buf, "shared") && device_swq_supported(idxd)) {
+	} else if (sysfs_streq(buf, "shared")) {
 		clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	} else {
 		return -EINVAL;
@@ -832,6 +832,7 @@ static ssize_t wq_name_store(struct device *dev,
 			     size_t count)
 {
 	struct idxd_wq *wq = confdev_to_wq(dev);
+	char *input, *pos;
 
 	if (wq->state != IDXD_WQ_DISABLED)
 		return -EPERM;
@@ -846,9 +847,14 @@ static ssize_t wq_name_store(struct device *dev,
 	if (wq->type == IDXD_WQT_KERNEL && device_pasid_enabled(wq->idxd))
 		return -EOPNOTSUPP;
 
+	input = kstrndup(buf, count, GFP_KERNEL);
+	if (!input)
+		return -ENOMEM;
+
+	pos = strim(input);
 	memset(wq->name, 0, WQ_NAME_SIZE + 1);
-	strncpy(wq->name, buf, WQ_NAME_SIZE);
-	strreplace(wq->name, '\n', '\0');
+	sprintf(wq->name, "%s", pos);
+	kfree(input);
 	return count;
 }
 

drivers/dma/mediatek/mtk-cqdma.c

@@ -751,7 +751,6 @@ static int mtk_cqdma_probe(struct platform_device *pdev)
 	struct mtk_cqdma_device *cqdma;
 	struct mtk_cqdma_vchan *vc;
 	struct dma_device *dd;
-	struct resource *res;
 	int err;
 	u32 i;
 
@@ -824,13 +823,10 @@ static int mtk_cqdma_probe(struct platform_device *pdev)
 			return PTR_ERR(cqdma->pc[i]->base);
 
 		/* allocate IRQ resource */
-		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
-		if (!res) {
-			dev_err(&pdev->dev, "No irq resource for %s\n",
-				dev_name(&pdev->dev));
-			return -EINVAL;
-		}
-		cqdma->pc[i]->irq = res->start;
+		err = platform_get_irq(pdev, i);
+		if (err < 0)
+			return err;
+		cqdma->pc[i]->irq = err;
 
 		err = devm_request_irq(&pdev->dev, cqdma->pc[i]->irq,
 				       mtk_cqdma_irq, 0, dev_name(&pdev->dev),

drivers/dma/mediatek/mtk-hsdma.c

@@ -601,7 +601,7 @@ static void mtk_hsdma_free_rooms_in_ring(struct mtk_hsdma_device *hsdma)
 			cb->flag = 0;
 		}
 
-		cb->vd = 0;
+		cb->vd = NULL;
 
 		/*
 		 * Recycle the RXD with the helper WRITE_ONCE that can ensure
@@ -923,13 +923,10 @@ static int mtk_hsdma_probe(struct platform_device *pdev)
 		return PTR_ERR(hsdma->clk);
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "No irq resource for %s\n",
-			dev_name(&pdev->dev));
-		return -EINVAL;
-	}
-	hsdma->irq = res->start;
+	err = platform_get_irq(pdev, 0);
+	if (err < 0)
+		return err;
+	hsdma->irq = err;
 
 	refcount_set(&hsdma->pc_refcnt, 0);
 	spin_lock_init(&hsdma->lock);

drivers/dma/mmp_pdma.c

@@ -1043,13 +1043,17 @@ static int mmp_pdma_probe(struct platform_device *op)
 		return PTR_ERR(pdev->base);
 
 	of_id = of_match_device(mmp_pdma_dt_ids, pdev->dev);
-	if (of_id)
-		of_property_read_u32(pdev->dev->of_node, "#dma-channels",
-				     &dma_channels);
-	else if (pdata && pdata->dma_channels)
+	if (of_id) {
+		/* Parse new and deprecated dma-channels properties */
+		if (of_property_read_u32(pdev->dev->of_node, "dma-channels",
+					 &dma_channels))
+			of_property_read_u32(pdev->dev->of_node, "#dma-channels",
+					     &dma_channels);
+	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
-	else
+	} else {
 		dma_channels = 32;	/* default 32 channel */
+	}
 	pdev->dma_channels = dma_channels;
 
 	for (i = 0; i < dma_channels; i++) {

drivers/dma/mv_xor_v2.c

@@ -591,14 +591,14 @@ static void mv_xor_v2_tasklet(struct tasklet_struct *t)
 		dma_run_dependencies(&next_pending_sw_desc->async_tx);
 
 		/* Lock the channel */
-		spin_lock_bh(&xor_dev->lock);
+		spin_lock(&xor_dev->lock);
 
 		/* add the SW descriptor to the free descriptors list */
 		list_add(&next_pending_sw_desc->free_list,
 			 &xor_dev->free_sw_desc);
 
 		/* Release the channel */
-		spin_unlock_bh(&xor_dev->lock);
+		spin_unlock(&xor_dev->lock);
 
 		/* increment the next descriptor */
 		pending_ptr++;

drivers/dma/nbpfaxi.c

@@ -1294,7 +1294,7 @@ static int nbpf_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct nbpf_device *nbpf;
 	struct dma_device *dma_dev;
-	struct resource *iomem, *irq_res;
+	struct resource *iomem;
 	const struct nbpf_config *cfg;
 	int num_channels;
 	int ret, irq, eirq, i;
@@ -1335,13 +1335,11 @@ static int nbpf_probe(struct platform_device *pdev)
 	nbpf->config = cfg;
 
 	for (i = 0; irqs < ARRAY_SIZE(irqbuf); i++) {
-		irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
-		if (!irq_res)
-			break;
-
-		for (irq = irq_res->start; irq <= irq_res->end;
-		     irq++, irqs++)
-			irqbuf[irqs] = irq;
+		irq = platform_get_irq_optional(pdev, i);
+		if (irq < 0 && irq != -ENXIO)
+			return irq;
+		if (irq > 0)
+			irqbuf[irqs++] = irq;
 	}
 
 	/*

drivers/dma/plx_dma.c

@@ -137,7 +137,7 @@ static void plx_dma_process_desc(struct plx_dma_dev *plxdev)
 	struct plx_dma_desc *desc;
 	u32 flags;
 
-	spin_lock_bh(&plxdev->ring_lock);
+	spin_lock(&plxdev->ring_lock);
 
 	while (plxdev->tail != plxdev->head) {
 		desc = plx_dma_get_desc(plxdev, plxdev->tail);
@@ -165,7 +165,7 @@ static void plx_dma_process_desc(struct plx_dma_dev *plxdev)
 		plxdev->tail++;
 	}
 
-	spin_unlock_bh(&plxdev->ring_lock);
+	spin_unlock(&plxdev->ring_lock);
 }
 
 static void plx_dma_abort_desc(struct plx_dma_dev *plxdev)

drivers/dma/ptdma/ptdma-dev.c

@@ -100,6 +100,7 @@ int pt_core_perform_passthru(struct pt_cmd_queue *cmd_q,
 			     struct pt_passthru_engine *pt_engine)
 {
 	struct ptdma_desc desc;
+	struct pt_device *pt = container_of(cmd_q, struct pt_device, cmd_q);
 
 	cmd_q->cmd_error = 0;
 	cmd_q->total_pt_ops++;
@@ -111,17 +112,12 @@ int pt_core_perform_passthru(struct pt_cmd_queue *cmd_q,
 	desc.dst_lo = lower_32_bits(pt_engine->dst_dma);
 	desc.dw5.dst_hi = upper_32_bits(pt_engine->dst_dma);
 
-	return pt_core_execute_cmd(&desc, cmd_q);
-}
-
-static inline void pt_core_disable_queue_interrupts(struct pt_device *pt)
-{
-	iowrite32(0, pt->cmd_q.reg_control + 0x000C);
-}
+	if (cmd_q->int_en)
+		pt_core_enable_queue_interrupts(pt);
+	else
+		pt_core_disable_queue_interrupts(pt);
 
-static inline void pt_core_enable_queue_interrupts(struct pt_device *pt)
-{
-	iowrite32(SUPPORTED_INTERRUPTS, pt->cmd_q.reg_control + 0x000C);
+	return pt_core_execute_cmd(&desc, cmd_q);
 }
 
 static void pt_do_cmd_complete(unsigned long data)
@@ -144,14 +140,10 @@ static void pt_do_cmd_complete(unsigned long data)
 	cmd->pt_cmd_callback(cmd->data, cmd->ret);
 }
 
-static irqreturn_t pt_core_irq_handler(int irq, void *data)
+void pt_check_status_trans(struct pt_device *pt, struct pt_cmd_queue *cmd_q)
 {
-	struct pt_device *pt = data;
-	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
 	u32 status;
 
-	pt_core_disable_queue_interrupts(pt);
-	pt->total_interrupts++;
 	status = ioread32(cmd_q->reg_control + 0x0010);
 	if (status) {
 		cmd_q->int_status = status;
@@ -162,11 +154,21 @@ static irqreturn_t pt_core_irq_handler(int irq, void *data)
 		if ((status & INT_ERROR) && !cmd_q->cmd_error)
 			cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
 
-		/* Acknowledge the interrupt */
+		/* Acknowledge the completion */
 		iowrite32(status, cmd_q->reg_control + 0x0010);
-		pt_core_enable_queue_interrupts(pt);
 		pt_do_cmd_complete((ulong)&pt->tdata);
 	}
+}
+
+static irqreturn_t pt_core_irq_handler(int irq, void *data)
+{
+	struct pt_device *pt = data;
+	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+
+	pt_core_disable_queue_interrupts(pt);
+	pt->total_interrupts++;
+	pt_check_status_trans(pt, cmd_q);
+	pt_core_enable_queue_interrupts(pt);
 	return IRQ_HANDLED;
 }
 

drivers/dma/ptdma/ptdma-dmaengine.c

@@ -171,6 +171,7 @@ static struct pt_dma_desc *pt_alloc_dma_desc(struct pt_dma_chan *chan,
 	vchan_tx_prep(&chan->vc, &desc->vd, flags);
 
 	desc->pt = chan->pt;
+	desc->pt->cmd_q.int_en = !!(flags & DMA_PREP_INTERRUPT);
 	desc->issued_to_hw = 0;
 	desc->status = DMA_IN_PROGRESS;
 
@@ -257,6 +258,17 @@ static void pt_issue_pending(struct dma_chan *dma_chan)
 		pt_cmd_callback(desc, 0);
 }
 
+static enum dma_status
+pt_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+		struct dma_tx_state *txstate)
+{
+	struct pt_device *pt = to_pt_chan(c)->pt;
+	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+
+	pt_check_status_trans(pt, cmd_q);
+	return dma_cookie_status(c, cookie, txstate);
+}
+
 static int pt_pause(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
@@ -291,8 +303,10 @@ static int pt_terminate_all(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
 	unsigned long flags;
+	struct pt_cmd_queue *cmd_q = &chan->pt->cmd_q;
 	LIST_HEAD(head);
 
+	iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vchan_get_all_descriptors(&chan->vc, &head);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
@@ -362,7 +376,7 @@ int pt_dmaengine_register(struct pt_device *pt)
 	dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy;
 	dma_dev->device_prep_dma_interrupt = pt_prep_dma_interrupt;
 	dma_dev->device_issue_pending = pt_issue_pending;
-	dma_dev->device_tx_status = dma_cookie_status;
+	dma_dev->device_tx_status = pt_tx_status;
 	dma_dev->device_pause = pt_pause;
 	dma_dev->device_resume = pt_resume;
 	dma_dev->device_terminate_all = pt_terminate_all;

drivers/dma/ptdma/ptdma.h

@@ -206,6 +206,9 @@ struct pt_cmd_queue {
 	unsigned int active;
 	unsigned int suspended;
 
+	/* Interrupt flag */
+	bool int_en;
+
 	/* Register addresses for queue */
 	void __iomem *reg_control;
 	u32 qcontrol; /* Cached control register */
@@ -318,7 +321,17 @@ void pt_core_destroy(struct pt_device *pt);
 int pt_core_perform_passthru(struct pt_cmd_queue *cmd_q,
 			     struct pt_passthru_engine *pt_engine);
 
+void pt_check_status_trans(struct pt_device *pt, struct pt_cmd_queue *cmd_q);
 void pt_start_queue(struct pt_cmd_queue *cmd_q);
 void pt_stop_queue(struct pt_cmd_queue *cmd_q);
 
+static inline void pt_core_disable_queue_interrupts(struct pt_device *pt)
+{
+	iowrite32(0, pt->cmd_q.reg_control + 0x000C);
+}
+
+static inline void pt_core_enable_queue_interrupts(struct pt_device *pt)
+{
+	iowrite32(SUPPORTED_INTERRUPTS, pt->cmd_q.reg_control + 0x000C);
+}
 #endif

drivers/dma/pxa_dma.c

@@ -1365,10 +1365,17 @@ static int pxad_probe(struct platform_device *op)
 
 	of_id = of_match_device(pxad_dt_ids, &op->dev);
 	if (of_id) {
-		of_property_read_u32(op->dev.of_node, "#dma-channels",
-				     &dma_channels);
-		ret = of_property_read_u32(op->dev.of_node, "#dma-requests",
+		/* Parse new and deprecated dma-channels properties */
+		if (of_property_read_u32(op->dev.of_node, "dma-channels",
+					 &dma_channels))
+			of_property_read_u32(op->dev.of_node, "#dma-channels",
+					     &dma_channels);
+		/* Parse new and deprecated dma-requests properties */
+		ret = of_property_read_u32(op->dev.of_node, "dma-requests",
 					   &nb_requestors);
+		if (ret)
+			ret = of_property_read_u32(op->dev.of_node, "#dma-requests",
+						   &nb_requestors);
 		if (ret) {
 			dev_warn(pdev->slave.dev,
 				 "#dma-requests set to default 32 as missing in OF: %d",

drivers/dma/qcom/gpi.c

@@ -1754,10 +1754,14 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
 		tre->dword[2] = u32_encode_bits(spi->rx_len, TRE_RX_LEN);
 
 		tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
-		if (spi->cmd == SPI_RX)
+		if (spi->cmd == SPI_RX) {
 			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB);
-		else
+		} else if (spi->cmd == SPI_TX) {
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+		} else { /* SPI_DUPLEX */
 			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK);
+		}
 	}
 
 	/* create the dma tre */
@@ -2148,6 +2152,7 @@ static int gpi_probe(struct platform_device *pdev)
 {
 	struct gpi_dev *gpi_dev;
 	unsigned int i;
+	u32 ee_offset;
 	int ret;
 
 	gpi_dev = devm_kzalloc(&pdev->dev, sizeof(*gpi_dev), GFP_KERNEL);
@@ -2175,6 +2180,9 @@ static int gpi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ee_offset = (uintptr_t)device_get_match_data(gpi_dev->dev);
+	gpi_dev->ee_base = gpi_dev->ee_base - ee_offset;
+
 	gpi_dev->ev_factor = EV_FACTOR;
 
 	ret = dma_set_mask(gpi_dev->dev, DMA_BIT_MASK(64));
@@ -2278,9 +2286,12 @@ static int gpi_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id gpi_of_match[] = {
-	{ .compatible = "qcom,sdm845-gpi-dma" },
-	{ .compatible = "qcom,sm8150-gpi-dma" },
-	{ .compatible = "qcom,sm8250-gpi-dma" },
+	{ .compatible = "qcom,sc7280-gpi-dma", .data = (void *)0x10000 },
+	{ .compatible = "qcom,sdm845-gpi-dma", .data = (void *)0x0 },
+	{ .compatible = "qcom,sm8150-gpi-dma", .data = (void *)0x0 },
+	{ .compatible = "qcom,sm8250-gpi-dma", .data = (void *)0x0 },
+	{ .compatible = "qcom,sm8350-gpi-dma", .data = (void *)0x10000 },
+	{ .compatible = "qcom,sm8450-gpi-dma", .data = (void *)0x10000 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, gpi_of_match);

drivers/dma/qcom/hidma.c

@@ -431,6 +431,7 @@ hidma_prep_dma_memset(struct dma_chan *dmach, dma_addr_t dest, int value,
 	struct hidma_desc *mdesc = NULL;
 	struct hidma_dev *mdma = mchan->dmadev;
 	unsigned long irqflags;
+	u64 byte_pattern, fill_pattern;
 
 	/* Get free descriptor */
 	spin_lock_irqsave(&mchan->lock, irqflags);
@@ -443,9 +444,19 @@ hidma_prep_dma_memset(struct dma_chan *dmach, dma_addr_t dest, int value,
 	if (!mdesc)
 		return NULL;
 
+	byte_pattern = (char)value;
+	fill_pattern =	(byte_pattern << 56) |
+			(byte_pattern << 48) |
+			(byte_pattern << 40) |
+			(byte_pattern << 32) |
+			(byte_pattern << 24) |
+			(byte_pattern << 16) |
+			(byte_pattern << 8) |
+			byte_pattern;
+
 	mdesc->desc.flags = flags;
 	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
-				     value, dest, len, flags,
+				     fill_pattern, dest, len, flags,
 				     HIDMA_TRE_MEMSET);
 
 	/* Place descriptor in prepared list */

drivers/dma/sf-pdma/sf-pdma.c

@@ -482,23 +482,30 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
 static int sf_pdma_probe(struct platform_device *pdev)
 {
 	struct sf_pdma *pdma;
-	struct sf_pdma_chan *chan;
 	struct resource *res;
-	int len, chans;
-	int ret;
+	int ret, n_chans;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE | 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;
 
-	chans = PDMA_NR_CH;
-	len = sizeof(*pdma) + sizeof(*chan) * chans;
-	pdma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	ret = of_property_read_u32(pdev->dev.of_node, "dma-channels", &n_chans);
+	if (ret) {
+		/* backwards-compatibility for no dma-channels property */
+		dev_dbg(&pdev->dev, "set number of channels to default value: 4\n");
+		n_chans = PDMA_MAX_NR_CH;
+	} else if (n_chans > PDMA_MAX_NR_CH) {
+		dev_err(&pdev->dev, "the number of channels exceeds the maximum\n");
+		return -EINVAL;
+	}
+
+	pdma = devm_kzalloc(&pdev->dev, struct_size(pdma, chans, n_chans),
+			    GFP_KERNEL);
 	if (!pdma)
 		return -ENOMEM;
 
-	pdma->n_chans = chans;
+	pdma->n_chans = n_chans;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pdma->membase = devm_ioremap_resource(&pdev->dev, res);
@@ -556,7 +563,7 @@ static int sf_pdma_remove(struct platform_device *pdev)
 	struct sf_pdma_chan *ch;
 	int i;
 
-	for (i = 0; i < PDMA_NR_CH; i++) {
+	for (i = 0; i < pdma->n_chans; i++) {
 		ch = &pdma->chans[i];
 
 		devm_free_irq(&pdev->dev, ch->txirq, ch);
@@ -574,6 +581,7 @@ static int sf_pdma_remove(struct platform_device *pdev)
 
 static const struct of_device_id sf_pdma_dt_ids[] = {
 	{ .compatible = "sifive,fu540-c000-pdma" },
+	{ .compatible = "sifive,pdma0" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);

drivers/dma/sf-pdma/sf-pdma.h

@@ -22,11 +22,7 @@
 #include "../dmaengine.h"
 #include "../virt-dma.h"
 
-#define PDMA_NR_CH					4
-
-#if (PDMA_NR_CH != 4)
-#error "Please define PDMA_NR_CH to 4"
-#endif
+#define PDMA_MAX_NR_CH					4
 
 #define PDMA_BASE_ADDR					0x3000000
 #define PDMA_CHAN_OFFSET				0x1000
@@ -118,7 +114,7 @@ struct sf_pdma {
 	void __iomem            *membase;
 	void __iomem            *mappedbase;
 	u32			n_chans;
-	struct sf_pdma_chan	chans[PDMA_NR_CH];
+	struct sf_pdma_chan	chans[];
 };
 
 #endif /* _SF_PDMA_H */

drivers/dma/sh/Kconfig

@@ -50,7 +50,7 @@ config RENESAS_USB_DMAC
 
 config RZ_DMAC
 	tristate "Renesas RZ/{G2L,V2L} DMA Controller"
-	depends on ARCH_R9A07G044 || ARCH_R9A07G054 || COMPILE_TEST
+	depends on ARCH_RZG2L || COMPILE_TEST
 	select RENESAS_DMA
 	select DMA_VIRTUAL_CHANNELS
 	help

drivers/dma/sprd-dma.c

@@ -1117,7 +1117,11 @@ static int sprd_dma_probe(struct platform_device *pdev)
 	u32 chn_count;
 	int ret, i;
 
-	ret = device_property_read_u32(&pdev->dev, "#dma-channels", &chn_count);
+	/* Parse new and deprecated dma-channels properties */
+	ret = device_property_read_u32(&pdev->dev, "dma-channels", &chn_count);
+	if (ret)
+		ret = device_property_read_u32(&pdev->dev, "#dma-channels",
+					       &chn_count);
 	if (ret) {
 		dev_err(&pdev->dev, "get dma channels count failed\n");
 		return ret;

drivers/dma/stm32-dma.c

@@ -208,6 +208,7 @@ struct stm32_dma_chan {
 	u32 threshold;
 	u32 mem_burst;
 	u32 mem_width;
+	enum dma_status status;
 };
 
 struct stm32_dma_device {
@@ -485,6 +486,7 @@ static void stm32_dma_stop(struct stm32_dma_chan *chan)
 	}
 
 	chan->busy = false;
+	chan->status = DMA_COMPLETE;
 }
 
 static int stm32_dma_terminate_all(struct dma_chan *c)
@@ -535,6 +537,13 @@ static void stm32_dma_dump_reg(struct stm32_dma_chan *chan)
 	dev_dbg(chan2dev(chan), "SFCR:  0x%08x\n", sfcr);
 }
 
+static void stm32_dma_sg_inc(struct stm32_dma_chan *chan)
+{
+	chan->next_sg++;
+	if (chan->desc->cyclic && (chan->next_sg == chan->desc->num_sgs))
+		chan->next_sg = 0;
+}
+
 static void stm32_dma_configure_next_sg(struct stm32_dma_chan *chan);
 
 static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
@@ -575,7 +584,7 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
 	stm32_dma_write(dmadev, STM32_DMA_SM1AR(chan->id), reg->dma_sm1ar);
 	stm32_dma_write(dmadev, STM32_DMA_SNDTR(chan->id), reg->dma_sndtr);
 
-	chan->next_sg++;
+	stm32_dma_sg_inc(chan);
 
 	/* Clear interrupt status if it is there */
 	status = stm32_dma_irq_status(chan);
@@ -588,11 +597,11 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
 	stm32_dma_dump_reg(chan);
 
 	/* Start DMA */
+	chan->busy = true;
+	chan->status = DMA_IN_PROGRESS;
 	reg->dma_scr |= STM32_DMA_SCR_EN;
 	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), reg->dma_scr);
 
-	chan->busy = true;
-
 	dev_dbg(chan2dev(chan), "vchan %pK: started\n", &chan->vchan);
 }
 
@@ -605,41 +614,131 @@ static void stm32_dma_configure_next_sg(struct stm32_dma_chan *chan)
 	id = chan->id;
 	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
 
-	if (dma_scr & STM32_DMA_SCR_DBM) {
-		if (chan->next_sg == chan->desc->num_sgs)
-			chan->next_sg = 0;
+	sg_req = &chan->desc->sg_req[chan->next_sg];
 
-		sg_req = &chan->desc->sg_req[chan->next_sg];
+	if (dma_scr & STM32_DMA_SCR_CT) {
+		dma_sm0ar = sg_req->chan_reg.dma_sm0ar;
+		stm32_dma_write(dmadev, STM32_DMA_SM0AR(id), dma_sm0ar);
+		dev_dbg(chan2dev(chan), "CT=1 <=> SM0AR: 0x%08x\n",
+			stm32_dma_read(dmadev, STM32_DMA_SM0AR(id)));
+	} else {
+		dma_sm1ar = sg_req->chan_reg.dma_sm1ar;
+		stm32_dma_write(dmadev, STM32_DMA_SM1AR(id), dma_sm1ar);
+		dev_dbg(chan2dev(chan), "CT=0 <=> SM1AR: 0x%08x\n",
+			stm32_dma_read(dmadev, STM32_DMA_SM1AR(id)));
+	}
+}
 
-		if (dma_scr & STM32_DMA_SCR_CT) {
-			dma_sm0ar = sg_req->chan_reg.dma_sm0ar;
-			stm32_dma_write(dmadev, STM32_DMA_SM0AR(id), dma_sm0ar);
-			dev_dbg(chan2dev(chan), "CT=1 <=> SM0AR: 0x%08x\n",
-				stm32_dma_read(dmadev, STM32_DMA_SM0AR(id)));
-		} else {
-			dma_sm1ar = sg_req->chan_reg.dma_sm1ar;
-			stm32_dma_write(dmadev, STM32_DMA_SM1AR(id), dma_sm1ar);
-			dev_dbg(chan2dev(chan), "CT=0 <=> SM1AR: 0x%08x\n",
-				stm32_dma_read(dmadev, STM32_DMA_SM1AR(id)));
-		}
+static void stm32_dma_handle_chan_paused(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 dma_scr;
+
+	/*
+	 * Read and store current remaining data items and peripheral/memory addresses to be
+	 * updated on resume
+	 */
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+	/*
+	 * Transfer can be paused while between a previous resume and reconfiguration on transfer
+	 * complete. If transfer is cyclic and CIRC and DBM have been deactivated for resume, need
+	 * to set it here in SCR backup to ensure a good reconfiguration on transfer complete.
+	 */
+	if (chan->desc && chan->desc->cyclic) {
+		if (chan->desc->num_sgs == 1)
+			dma_scr |= STM32_DMA_SCR_CIRC;
+		else
+			dma_scr |= STM32_DMA_SCR_DBM;
+	}
+	chan->chan_reg.dma_scr = dma_scr;
+
+	/*
+	 * Need to temporarily deactivate CIRC/DBM until next Transfer Complete interrupt, otherwise
+	 * on resume NDTR autoreload value will be wrong (lower than the initial period length)
+	 */
+	if (chan->desc && chan->desc->cyclic) {
+		dma_scr &= ~(STM32_DMA_SCR_DBM | STM32_DMA_SCR_CIRC);
+		stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), dma_scr);
+	}
+
+	chan->chan_reg.dma_sndtr = stm32_dma_read(dmadev, STM32_DMA_SNDTR(chan->id));
+
+	dev_dbg(chan2dev(chan), "vchan %pK: paused\n", &chan->vchan);
+}
+
+static void stm32_dma_post_resume_reconfigure(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	struct stm32_dma_sg_req *sg_req;
+	u32 dma_scr, status, id;
+
+	id = chan->id;
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+
+	/* Clear interrupt status if it is there */
+	status = stm32_dma_irq_status(chan);
+	if (status)
+		stm32_dma_irq_clear(chan, status);
+
+	if (!chan->next_sg)
+		sg_req = &chan->desc->sg_req[chan->desc->num_sgs - 1];
+	else
+		sg_req = &chan->desc->sg_req[chan->next_sg - 1];
+
+	/* Reconfigure NDTR with the initial value */
+	stm32_dma_write(dmadev, STM32_DMA_SNDTR(chan->id), sg_req->chan_reg.dma_sndtr);
+
+	/* Restore SPAR */
+	stm32_dma_write(dmadev, STM32_DMA_SPAR(id), sg_req->chan_reg.dma_spar);
+
+	/* Restore SM0AR/SM1AR whatever DBM/CT as they may have been modified */
+	stm32_dma_write(dmadev, STM32_DMA_SM0AR(id), sg_req->chan_reg.dma_sm0ar);
+	stm32_dma_write(dmadev, STM32_DMA_SM1AR(id), sg_req->chan_reg.dma_sm1ar);
+
+	/* Reactivate CIRC/DBM if needed */
+	if (chan->chan_reg.dma_scr & STM32_DMA_SCR_DBM) {
+		dma_scr |= STM32_DMA_SCR_DBM;
+		/* Restore CT */
+		if (chan->chan_reg.dma_scr & STM32_DMA_SCR_CT)
+			dma_scr &= ~STM32_DMA_SCR_CT;
+		else
+			dma_scr |= STM32_DMA_SCR_CT;
+	} else if (chan->chan_reg.dma_scr & STM32_DMA_SCR_CIRC) {
+		dma_scr |= STM32_DMA_SCR_CIRC;
 	}
+	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), dma_scr);
+
+	stm32_dma_configure_next_sg(chan);
+
+	stm32_dma_dump_reg(chan);
+
+	dma_scr |= STM32_DMA_SCR_EN;
+	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), dma_scr);
+
+	dev_dbg(chan2dev(chan), "vchan %pK: reconfigured after pause/resume\n", &chan->vchan);
 }
 
-static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan)
+static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan, u32 scr)
 {
-	if (chan->desc) {
-		if (chan->desc->cyclic) {
-			vchan_cyclic_callback(&chan->desc->vdesc);
-			chan->next_sg++;
+	if (!chan->desc)
+		return;
+
+	if (chan->desc->cyclic) {
+		vchan_cyclic_callback(&chan->desc->vdesc);
+		stm32_dma_sg_inc(chan);
+		/* cyclic while CIRC/DBM disable => post resume reconfiguration needed */
+		if (!(scr & (STM32_DMA_SCR_CIRC | STM32_DMA_SCR_DBM)))
+			stm32_dma_post_resume_reconfigure(chan);
+		else if (scr & STM32_DMA_SCR_DBM)
 			stm32_dma_configure_next_sg(chan);
-		} else {
-			chan->busy = false;
-			if (chan->next_sg == chan->desc->num_sgs) {
-				vchan_cookie_complete(&chan->desc->vdesc);
-				chan->desc = NULL;
-			}
-			stm32_dma_start_transfer(chan);
+	} else {
+		chan->busy = false;
+		chan->status = DMA_COMPLETE;
+		if (chan->next_sg == chan->desc->num_sgs) {
+			vchan_cookie_complete(&chan->desc->vdesc);
+			chan->desc = NULL;
 		}
+		stm32_dma_start_transfer(chan);
 	}
 }
 
@@ -675,8 +774,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 
 	if (status & STM32_DMA_TCI) {
 		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
-		if (scr & STM32_DMA_SCR_TCIE)
-			stm32_dma_handle_chan_done(chan);
+		if (scr & STM32_DMA_SCR_TCIE) {
+			if (chan->status == DMA_PAUSED && !(scr & STM32_DMA_SCR_EN))
+				stm32_dma_handle_chan_paused(chan);
+			else
+				stm32_dma_handle_chan_done(chan, scr);
+		}
 		status &= ~STM32_DMA_TCI;
 	}
 
@@ -711,6 +814,107 @@ static void stm32_dma_issue_pending(struct dma_chan *c)
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
 
+static int stm32_dma_pause(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	unsigned long flags;
+	int ret;
+
+	if (chan->status != DMA_IN_PROGRESS)
+		return -EPERM;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	ret = stm32_dma_disable_chan(chan);
+	/*
+	 * A transfer complete flag is set to indicate the end of transfer due to the stream
+	 * interruption, so wait for interrupt
+	 */
+	if (!ret)
+		chan->status = DMA_PAUSED;
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	return ret;
+}
+
+static int stm32_dma_resume(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	struct stm32_dma_chan_reg chan_reg = chan->chan_reg;
+	u32 id = chan->id, scr, ndtr, offset, spar, sm0ar, sm1ar;
+	struct stm32_dma_sg_req *sg_req;
+	unsigned long flags;
+
+	if (chan->status != DMA_PAUSED)
+		return -EPERM;
+
+	scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+	if (WARN_ON(scr & STM32_DMA_SCR_EN))
+		return -EPERM;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+
+	/* sg_reg[prev_sg] contains original ndtr, sm0ar and sm1ar before pausing the transfer */
+	if (!chan->next_sg)
+		sg_req = &chan->desc->sg_req[chan->desc->num_sgs - 1];
+	else
+		sg_req = &chan->desc->sg_req[chan->next_sg - 1];
+
+	ndtr = sg_req->chan_reg.dma_sndtr;
+	offset = (ndtr - chan_reg.dma_sndtr) << STM32_DMA_SCR_PSIZE_GET(chan_reg.dma_scr);
+	spar = sg_req->chan_reg.dma_spar;
+	sm0ar = sg_req->chan_reg.dma_sm0ar;
+	sm1ar = sg_req->chan_reg.dma_sm1ar;
+
+	/*
+	 * The peripheral and/or memory addresses have to be updated in order to adjust the
+	 * address pointers. Need to check increment.
+	 */
+	if (chan_reg.dma_scr & STM32_DMA_SCR_PINC)
+		stm32_dma_write(dmadev, STM32_DMA_SPAR(id), spar + offset);
+	else
+		stm32_dma_write(dmadev, STM32_DMA_SPAR(id), spar);
+
+	if (!(chan_reg.dma_scr & STM32_DMA_SCR_MINC))
+		offset = 0;
+
+	/*
+	 * In case of DBM, the current target could be SM1AR.
+	 * Need to temporarily deactivate CIRC/DBM to finish the current transfer, so
+	 * SM0AR becomes the current target and must be updated with SM1AR + offset if CT=1.
+	 */
+	if ((chan_reg.dma_scr & STM32_DMA_SCR_DBM) && (chan_reg.dma_scr & STM32_DMA_SCR_CT))
+		stm32_dma_write(dmadev, STM32_DMA_SM1AR(id), sm1ar + offset);
+	else
+		stm32_dma_write(dmadev, STM32_DMA_SM0AR(id), sm0ar + offset);
+
+	/* NDTR must be restored otherwise internal HW counter won't be correctly reset */
+	stm32_dma_write(dmadev, STM32_DMA_SNDTR(id), chan_reg.dma_sndtr);
+
+	/*
+	 * Need to temporarily deactivate CIRC/DBM until next Transfer Complete interrupt,
+	 * otherwise NDTR autoreload value will be wrong (lower than the initial period length)
+	 */
+	if (chan_reg.dma_scr & (STM32_DMA_SCR_CIRC | STM32_DMA_SCR_DBM))
+		chan_reg.dma_scr &= ~(STM32_DMA_SCR_CIRC | STM32_DMA_SCR_DBM);
+
+	if (chan_reg.dma_scr & STM32_DMA_SCR_DBM)
+		stm32_dma_configure_next_sg(chan);
+
+	stm32_dma_dump_reg(chan);
+
+	/* The stream may then be re-enabled to restart transfer from the point it was stopped */
+	chan->status = DMA_IN_PROGRESS;
+	chan_reg.dma_scr |= STM32_DMA_SCR_EN;
+	stm32_dma_write(dmadev, STM32_DMA_SCR(id), chan_reg.dma_scr);
+
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	dev_dbg(chan2dev(chan), "vchan %pK: resumed\n", &chan->vchan);
+
+	return 0;
+}
+
 static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 				    enum dma_transfer_direction direction,
 				    enum dma_slave_buswidth *buswidth,
@@ -978,10 +1182,12 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_cyclic(
 	}
 
 	/*  Enable Circular mode or double buffer mode */
-	if (buf_len == period_len)
+	if (buf_len == period_len) {
 		chan->chan_reg.dma_scr |= STM32_DMA_SCR_CIRC;
-	else
+	} else {
 		chan->chan_reg.dma_scr |= STM32_DMA_SCR_DBM;
+		chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_CT;
+	}
 
 	/* Clear periph ctrl if client set it */
 	chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL;
@@ -1091,24 +1297,36 @@ static bool stm32_dma_is_current_sg(struct stm32_dma_chan *chan)
 {
 	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
 	struct stm32_dma_sg_req *sg_req;
-	u32 dma_scr, dma_smar, id;
+	u32 dma_scr, dma_smar, id, period_len;
 
 	id = chan->id;
 	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
 
+	/* In cyclic CIRC but not DBM, CT is not used */
 	if (!(dma_scr & STM32_DMA_SCR_DBM))
 		return true;
 
 	sg_req = &chan->desc->sg_req[chan->next_sg];
+	period_len = sg_req->len;
 
+	/* DBM - take care of a previous pause/resume not yet post reconfigured */
 	if (dma_scr & STM32_DMA_SCR_CT) {
 		dma_smar = stm32_dma_read(dmadev, STM32_DMA_SM0AR(id));
-		return (dma_smar == sg_req->chan_reg.dma_sm0ar);
+		/*
+		 * If transfer has been pause/resumed,
+		 * SM0AR is in the range of [SM0AR:SM0AR+period_len]
+		 */
+		return (dma_smar >= sg_req->chan_reg.dma_sm0ar &&
+			dma_smar < sg_req->chan_reg.dma_sm0ar + period_len);
 	}
 
 	dma_smar = stm32_dma_read(dmadev, STM32_DMA_SM1AR(id));
-
-	return (dma_smar == sg_req->chan_reg.dma_sm1ar);
+	/*
+	 * If transfer has been pause/resumed,
+	 * SM1AR is in the range of [SM1AR:SM1AR+period_len]
+	 */
+	return (dma_smar >= sg_req->chan_reg.dma_sm1ar &&
+		dma_smar < sg_req->chan_reg.dma_sm1ar + period_len);
 }
 
 static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
@@ -1148,7 +1366,7 @@ static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
 
 	residue = stm32_dma_get_remaining_bytes(chan);
 
-	if (!stm32_dma_is_current_sg(chan)) {
+	if (chan->desc->cyclic && !stm32_dma_is_current_sg(chan)) {
 		n_sg++;
 		if (n_sg == chan->desc->num_sgs)
 			n_sg = 0;
@@ -1188,7 +1406,12 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
 	u32 residue = 0;
 
 	status = dma_cookie_status(c, cookie, state);
-	if (status == DMA_COMPLETE || !state)
+	if (status == DMA_COMPLETE)
+		return status;
+
+	status = chan->status;
+
+	if (!state)
 		return status;
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
@@ -1377,6 +1600,8 @@ static int stm32_dma_probe(struct platform_device *pdev)
 	dd->device_prep_slave_sg = stm32_dma_prep_slave_sg;
 	dd->device_prep_dma_cyclic = stm32_dma_prep_dma_cyclic;
 	dd->device_config = stm32_dma_slave_config;
+	dd->device_pause = stm32_dma_pause;
+	dd->device_resume = stm32_dma_resume;
 	dd->device_terminate_all = stm32_dma_terminate_all;
 	dd->device_synchronize = stm32_dma_synchronize;
 	dd->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
@@ -1482,7 +1707,7 @@ static int stm32_dma_runtime_resume(struct device *dev)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
-static int stm32_dma_suspend(struct device *dev)
+static int stm32_dma_pm_suspend(struct device *dev)
 {
 	struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
 	int id, ret, scr;
@@ -1506,14 +1731,14 @@ static int stm32_dma_suspend(struct device *dev)
 	return 0;
 }
 
-static int stm32_dma_resume(struct device *dev)
+static int stm32_dma_pm_resume(struct device *dev)
 {
 	return pm_runtime_force_resume(dev);
 }
 #endif
 
 static const struct dev_pm_ops stm32_dma_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(stm32_dma_suspend, stm32_dma_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(stm32_dma_pm_suspend, stm32_dma_pm_resume)
 	SET_RUNTIME_PM_OPS(stm32_dma_runtime_suspend,
 			   stm32_dma_runtime_resume, NULL)
 };

drivers/dma/stm32-dmamux.c

@@ -267,7 +267,7 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 		ret = PTR_ERR(rst);
 		if (ret == -EPROBE_DEFER)
 			goto err_clk;
-	} else {
+	} else if (count > 1) { /* Don't reset if there is only one dma-master */
 		reset_control_assert(rst);
 		udelay(2);
 		reset_control_deassert(rst);

drivers/dma/stm32-mdma.c

@@ -34,7 +34,6 @@
 #include "virt-dma.h"
 
 #define STM32_MDMA_GISR0		0x0000 /* MDMA Int Status Reg 1 */
-#define STM32_MDMA_GISR1		0x0004 /* MDMA Int Status Reg 2 */
 
 /* MDMA Channel x interrupt/status register */
 #define STM32_MDMA_CISR(x)		(0x40 + 0x40 * (x)) /* x = 0..62 */
@@ -73,6 +72,7 @@
 #define STM32_MDMA_CCR_WEX		BIT(14)
 #define STM32_MDMA_CCR_HEX		BIT(13)
 #define STM32_MDMA_CCR_BEX		BIT(12)
+#define STM32_MDMA_CCR_SM		BIT(8)
 #define STM32_MDMA_CCR_PL_MASK		GENMASK(7, 6)
 #define STM32_MDMA_CCR_PL(n)		FIELD_PREP(STM32_MDMA_CCR_PL_MASK, (n))
 #define STM32_MDMA_CCR_TCIE		BIT(5)
@@ -168,7 +168,7 @@
 
 #define STM32_MDMA_MAX_BUF_LEN		128
 #define STM32_MDMA_MAX_BLOCK_LEN	65536
-#define STM32_MDMA_MAX_CHANNELS		63
+#define STM32_MDMA_MAX_CHANNELS		32
 #define STM32_MDMA_MAX_REQUESTS		256
 #define STM32_MDMA_MAX_BURST		128
 #define STM32_MDMA_VERY_HIGH_PRIORITY	0x3
@@ -248,6 +248,7 @@ struct stm32_mdma_device {
 	u32 nr_channels;
 	u32 nr_requests;
 	u32 nr_ahb_addr_masks;
+	u32 chan_reserved;
 	struct stm32_mdma_chan chan[STM32_MDMA_MAX_CHANNELS];
 	u32 ahb_addr_masks[];
 };
@@ -1317,26 +1318,16 @@ static void stm32_mdma_xfer_end(struct stm32_mdma_chan *chan)
 static irqreturn_t stm32_mdma_irq_handler(int irq, void *devid)
 {
 	struct stm32_mdma_device *dmadev = devid;
-	struct stm32_mdma_chan *chan = devid;
+	struct stm32_mdma_chan *chan;
 	u32 reg, id, ccr, ien, status;
 
 	/* Find out which channel generates the interrupt */
 	status = readl_relaxed(dmadev->base + STM32_MDMA_GISR0);
-	if (status) {
-		id = __ffs(status);
-	} else {
-		status = readl_relaxed(dmadev->base + STM32_MDMA_GISR1);
-		if (!status) {
-			dev_dbg(mdma2dev(dmadev), "spurious it\n");
-			return IRQ_NONE;
-		}
-		id = __ffs(status);
-		/*
-		 * As GISR0 provides status for channel id from 0 to 31,
-		 * so GISR1 provides status for channel id from 32 to 62
-		 */
-		id += 32;
+	if (!status) {
+		dev_dbg(mdma2dev(dmadev), "spurious it\n");
+		return IRQ_NONE;
 	}
+	id = __ffs(status);
 
 	chan = &dmadev->chan[id];
 	if (!chan) {
@@ -1354,9 +1345,12 @@ static irqreturn_t stm32_mdma_irq_handler(int irq, void *devid)
 
 	if (!(status & ien)) {
 		spin_unlock(&chan->vchan.lock);
-		dev_warn(chan2dev(chan),
-			 "spurious it (status=0x%04x, ien=0x%04x)\n",
-			 status, ien);
+		if (chan->busy)
+			dev_warn(chan2dev(chan),
+				 "spurious it (status=0x%04x, ien=0x%04x)\n", status, ien);
+		else
+			dev_dbg(chan2dev(chan),
+				"spurious it (status=0x%04x, ien=0x%04x)\n", status, ien);
 		return IRQ_NONE;
 	}
 
@@ -1456,10 +1450,23 @@ static void stm32_mdma_free_chan_resources(struct dma_chan *c)
 	chan->desc_pool = NULL;
 }
 
+static bool stm32_mdma_filter_fn(struct dma_chan *c, void *fn_param)
+{
+	struct stm32_mdma_chan *chan = to_stm32_mdma_chan(c);
+	struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
+
+	/* Check if chan is marked Secure */
+	if (dmadev->chan_reserved & BIT(chan->id))
+		return false;
+
+	return true;
+}
+
 static struct dma_chan *stm32_mdma_of_xlate(struct of_phandle_args *dma_spec,
 					    struct of_dma *ofdma)
 {
 	struct stm32_mdma_device *dmadev = ofdma->of_dma_data;
+	dma_cap_mask_t mask = dmadev->ddev.cap_mask;
 	struct stm32_mdma_chan *chan;
 	struct dma_chan *c;
 	struct stm32_mdma_chan_config config;
@@ -1485,7 +1492,7 @@ static struct dma_chan *stm32_mdma_of_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 	}
 
-	c = dma_get_any_slave_channel(&dmadev->ddev);
+	c = __dma_request_channel(&mask, stm32_mdma_filter_fn, &config, ofdma->of_node);
 	if (!c) {
 		dev_err(mdma2dev(dmadev), "No more channels available\n");
 		return NULL;
@@ -1615,6 +1622,10 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	for (i = 0; i < dmadev->nr_channels; i++) {
 		chan = &dmadev->chan[i];
 		chan->id = i;
+
+		if (stm32_mdma_read(dmadev, STM32_MDMA_CCR(i)) & STM32_MDMA_CCR_SM)
+			dmadev->chan_reserved |= BIT(i);
+
 		chan->vchan.desc_free = stm32_mdma_desc_free;
 		vchan_init(&chan->vchan, dd);
 	}

drivers/dma/sun6i-dma.c

@@ -90,6 +90,14 @@
 
 #define DMA_CHAN_CUR_PARA	0x1c
 
+/*
+ * LLI address mangling
+ *
+ * The LLI link physical address is also mangled, but we avoid dealing
+ * with that by allocating LLIs from the DMA32 zone.
+ */
+#define SRC_HIGH_ADDR(x)		(((x) & 0x3U) << 16)
+#define DST_HIGH_ADDR(x)		(((x) & 0x3U) << 18)
 
 /*
  * Various hardware related defines
@@ -132,6 +140,7 @@ struct sun6i_dma_config {
 	u32 dst_burst_lengths;
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
+	bool has_high_addr;
 	bool has_mbus_clk;
 };
 
@@ -241,9 +250,7 @@ static inline void sun6i_dma_dump_com_regs(struct sun6i_dma_dev *sdev)
 static inline void sun6i_dma_dump_chan_regs(struct sun6i_dma_dev *sdev,
 					    struct sun6i_pchan *pchan)
 {
-	phys_addr_t reg = virt_to_phys(pchan->base);
-
-	dev_dbg(sdev->slave.dev, "Chan %d reg: %pa\n"
+	dev_dbg(sdev->slave.dev, "Chan %d reg:\n"
 		"\t___en(%04x): \t0x%08x\n"
 		"\tpause(%04x): \t0x%08x\n"
 		"\tstart(%04x): \t0x%08x\n"
@@ -252,7 +259,7 @@ static inline void sun6i_dma_dump_chan_regs(struct sun6i_dma_dev *sdev,
 		"\t__dst(%04x): \t0x%08x\n"
 		"\tcount(%04x): \t0x%08x\n"
 		"\t_para(%04x): \t0x%08x\n\n",
-		pchan->idx, &reg,
+		pchan->idx,
 		DMA_CHAN_ENABLE,
 		readl(pchan->base + DMA_CHAN_ENABLE),
 		DMA_CHAN_PAUSE,
@@ -385,17 +392,16 @@ static void *sun6i_dma_lli_add(struct sun6i_dma_lli *prev,
 }
 
 static inline void sun6i_dma_dump_lli(struct sun6i_vchan *vchan,
-				      struct sun6i_dma_lli *lli)
+				      struct sun6i_dma_lli *v_lli,
+				      dma_addr_t p_lli)
 {
-	phys_addr_t p_lli = virt_to_phys(lli);
-
 	dev_dbg(chan2dev(&vchan->vc.chan),
-		"\n\tdesc:   p - %pa v - 0x%p\n"
+		"\n\tdesc:\tp - %pad v - 0x%p\n"
 		"\t\tc - 0x%08x s - 0x%08x d - 0x%08x\n"
 		"\t\tl - 0x%08x p - 0x%08x n - 0x%08x\n",
-		&p_lli, lli,
-		lli->cfg, lli->src, lli->dst,
-		lli->len, lli->para, lli->p_lli_next);
+		&p_lli, v_lli,
+		v_lli->cfg, v_lli->src, v_lli->dst,
+		v_lli->len, v_lli->para, v_lli->p_lli_next);
 }
 
 static void sun6i_dma_free_desc(struct virt_dma_desc *vd)
@@ -445,7 +451,7 @@ static int sun6i_dma_start_desc(struct sun6i_vchan *vchan)
 	pchan->desc = to_sun6i_desc(&desc->tx);
 	pchan->done = NULL;
 
-	sun6i_dma_dump_lli(vchan, pchan->desc->v_lli);
+	sun6i_dma_dump_lli(vchan, pchan->desc->v_lli, pchan->desc->p_lli);
 
 	irq_reg = pchan->idx / DMA_IRQ_CHAN_NR;
 	irq_offset = pchan->idx % DMA_IRQ_CHAN_NR;
@@ -626,6 +632,18 @@ static int set_config(struct sun6i_dma_dev *sdev,
 	return 0;
 }
 
+static inline void sun6i_dma_set_addr(struct sun6i_dma_dev *sdev,
+				      struct sun6i_dma_lli *v_lli,
+				      dma_addr_t src, dma_addr_t dst)
+{
+	v_lli->src = lower_32_bits(src);
+	v_lli->dst = lower_32_bits(dst);
+
+	if (sdev->cfg->has_high_addr)
+		v_lli->para |= SRC_HIGH_ADDR(upper_32_bits(src)) |
+			       DST_HIGH_ADDR(upper_32_bits(dst));
+}
+
 static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy(
 		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		size_t len, unsigned long flags)
@@ -648,16 +666,15 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy(
 	if (!txd)
 		return NULL;
 
-	v_lli = dma_pool_alloc(sdev->pool, GFP_NOWAIT, &p_lli);
+	v_lli = dma_pool_alloc(sdev->pool, GFP_DMA32 | GFP_NOWAIT, &p_lli);
 	if (!v_lli) {
 		dev_err(sdev->slave.dev, "Failed to alloc lli memory\n");
 		goto err_txd_free;
 	}
 
-	v_lli->src = src;
-	v_lli->dst = dest;
 	v_lli->len = len;
 	v_lli->para = NORMAL_WAIT;
+	sun6i_dma_set_addr(sdev, v_lli, src, dest);
 
 	burst = convert_burst(8);
 	width = convert_buswidth(DMA_SLAVE_BUSWIDTH_4_BYTES);
@@ -670,7 +687,7 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy(
 
 	sun6i_dma_lli_add(NULL, v_lli, p_lli, txd);
 
-	sun6i_dma_dump_lli(vchan, v_lli);
+	sun6i_dma_dump_lli(vchan, v_lli, p_lli);
 
 	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
 
@@ -708,7 +725,7 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_slave_sg(
 		return NULL;
 
 	for_each_sg(sgl, sg, sg_len, i) {
-		v_lli = dma_pool_alloc(sdev->pool, GFP_NOWAIT, &p_lli);
+		v_lli = dma_pool_alloc(sdev->pool, GFP_DMA32 | GFP_NOWAIT, &p_lli);
 		if (!v_lli)
 			goto err_lli_free;
 
@@ -716,8 +733,9 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_slave_sg(
 		v_lli->para = NORMAL_WAIT;
 
 		if (dir == DMA_MEM_TO_DEV) {
-			v_lli->src = sg_dma_address(sg);
-			v_lli->dst = sconfig->dst_addr;
+			sun6i_dma_set_addr(sdev, v_lli,
+					   sg_dma_address(sg),
+					   sconfig->dst_addr);
 			v_lli->cfg = lli_cfg;
 			sdev->cfg->set_drq(&v_lli->cfg, DRQ_SDRAM, vchan->port);
 			sdev->cfg->set_mode(&v_lli->cfg, LINEAR_MODE, IO_MODE);
@@ -729,8 +747,9 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_slave_sg(
 				sg_dma_len(sg), flags);
 
 		} else {
-			v_lli->src = sconfig->src_addr;
-			v_lli->dst = sg_dma_address(sg);
+			sun6i_dma_set_addr(sdev, v_lli,
+					   sconfig->src_addr,
+					   sg_dma_address(sg));
 			v_lli->cfg = lli_cfg;
 			sdev->cfg->set_drq(&v_lli->cfg, vchan->port, DRQ_SDRAM);
 			sdev->cfg->set_mode(&v_lli->cfg, IO_MODE, LINEAR_MODE);
@@ -746,14 +765,16 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_slave_sg(
 	}
 
 	dev_dbg(chan2dev(chan), "First: %pad\n", &txd->p_lli);
-	for (prev = txd->v_lli; prev; prev = prev->v_lli_next)
-		sun6i_dma_dump_lli(vchan, prev);
+	for (p_lli = txd->p_lli, v_lli = txd->v_lli; v_lli;
+	     p_lli = v_lli->p_lli_next, v_lli = v_lli->v_lli_next)
+		sun6i_dma_dump_lli(vchan, v_lli, p_lli);
 
 	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
 
 err_lli_free:
-	for (prev = txd->v_lli; prev; prev = prev->v_lli_next)
-		dma_pool_free(sdev->pool, prev, virt_to_phys(prev));
+	for (p_lli = txd->p_lli, v_lli = txd->v_lli; v_lli;
+	     p_lli = v_lli->p_lli_next, v_lli = v_lli->v_lli_next)
+		dma_pool_free(sdev->pool, v_lli, p_lli);
 	kfree(txd);
 	return NULL;
 }
@@ -787,7 +808,7 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_cyclic(
 		return NULL;
 
 	for (i = 0; i < periods; i++) {
-		v_lli = dma_pool_alloc(sdev->pool, GFP_NOWAIT, &p_lli);
+		v_lli = dma_pool_alloc(sdev->pool, GFP_DMA32 | GFP_NOWAIT, &p_lli);
 		if (!v_lli) {
 			dev_err(sdev->slave.dev, "Failed to alloc lli memory\n");
 			goto err_lli_free;
@@ -797,14 +818,16 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_cyclic(
 		v_lli->para = NORMAL_WAIT;
 
 		if (dir == DMA_MEM_TO_DEV) {
-			v_lli->src = buf_addr + period_len * i;
-			v_lli->dst = sconfig->dst_addr;
+			sun6i_dma_set_addr(sdev, v_lli,
+					   buf_addr + period_len * i,
+					   sconfig->dst_addr);
 			v_lli->cfg = lli_cfg;
 			sdev->cfg->set_drq(&v_lli->cfg, DRQ_SDRAM, vchan->port);
 			sdev->cfg->set_mode(&v_lli->cfg, LINEAR_MODE, IO_MODE);
 		} else {
-			v_lli->src = sconfig->src_addr;
-			v_lli->dst = buf_addr + period_len * i;
+			sun6i_dma_set_addr(sdev, v_lli,
+					   sconfig->src_addr,
+					   buf_addr + period_len * i);
 			v_lli->cfg = lli_cfg;
 			sdev->cfg->set_drq(&v_lli->cfg, vchan->port, DRQ_SDRAM);
 			sdev->cfg->set_mode(&v_lli->cfg, IO_MODE, LINEAR_MODE);
@@ -820,8 +843,9 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_cyclic(
 	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
 
 err_lli_free:
-	for (prev = txd->v_lli; prev; prev = prev->v_lli_next)
-		dma_pool_free(sdev->pool, prev, virt_to_phys(prev));
+	for (p_lli = txd->p_lli, v_lli = txd->v_lli; v_lli;
+	     p_lli = v_lli->p_lli_next, v_lli = v_lli->v_lli_next)
+		dma_pool_free(sdev->pool, v_lli, p_lli);
 	kfree(txd);
 	return NULL;
 }
@@ -1174,8 +1198,6 @@ static struct sun6i_dma_config sun50i_a64_dma_cfg = {
 };
 
 /*
- * TODO: Add support for more than 4g physical addressing.
- *
  * The A100 binding uses the number of dma channels from the
  * device tree node.
  */
@@ -1194,6 +1216,7 @@ static struct sun6i_dma_config sun50i_a100_dma_cfg = {
 			     BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
 			     BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
 			     BIT(DMA_SLAVE_BUSWIDTH_8_BYTES),
+	.has_high_addr = true,
 	.has_mbus_clk = true,
 };
 
@@ -1248,6 +1271,7 @@ static const struct of_device_id sun6i_dma_match[] = {
 	{ .compatible = "allwinner,sun8i-a83t-dma", .data = &sun8i_a83t_dma_cfg },
 	{ .compatible = "allwinner,sun8i-h3-dma", .data = &sun8i_h3_dma_cfg },
 	{ .compatible = "allwinner,sun8i-v3s-dma", .data = &sun8i_v3s_dma_cfg },
+	{ .compatible = "allwinner,sun20i-d1-dma", .data = &sun50i_a100_dma_cfg },
 	{ .compatible = "allwinner,sun50i-a64-dma", .data = &sun50i_a64_dma_cfg },
 	{ .compatible = "allwinner,sun50i-a100-dma", .data = &sun50i_a100_dma_cfg },
 	{ .compatible = "allwinner,sun50i-h6-dma", .data = &sun50i_h6_dma_cfg },

drivers/dma/tegra186-gpc-dma.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DMA driver for NVIDIA Tegra GPC DMA controller.
+ *
+ * Copyright (c) 2014-2022, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/minmax.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+#include <dt-bindings/memory/tegra186-mc.h>
+#include "virt-dma.h"
+
+/* CSR register */
+#define TEGRA_GPCDMA_CHAN_CSR			0x00
+#define TEGRA_GPCDMA_CSR_ENB			BIT(31)
+#define TEGRA_GPCDMA_CSR_IE_EOC			BIT(30)
+#define TEGRA_GPCDMA_CSR_ONCE			BIT(27)
+
+#define TEGRA_GPCDMA_CSR_FC_MODE		GENMASK(25, 24)
+#define TEGRA_GPCDMA_CSR_FC_MODE_NO_MMIO	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_FC_MODE, 0)
+#define TEGRA_GPCDMA_CSR_FC_MODE_ONE_MMIO	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_FC_MODE, 1)
+#define TEGRA_GPCDMA_CSR_FC_MODE_TWO_MMIO	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_FC_MODE, 2)
+#define TEGRA_GPCDMA_CSR_FC_MODE_FOUR_MMIO	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_FC_MODE, 3)
+
+#define TEGRA_GPCDMA_CSR_DMA			GENMASK(23, 21)
+#define TEGRA_GPCDMA_CSR_DMA_IO2MEM_NO_FC	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 0)
+#define TEGRA_GPCDMA_CSR_DMA_IO2MEM_FC		\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 1)
+#define TEGRA_GPCDMA_CSR_DMA_MEM2IO_NO_FC	\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 2)
+#define TEGRA_GPCDMA_CSR_DMA_MEM2IO_FC		\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 3)
+#define TEGRA_GPCDMA_CSR_DMA_MEM2MEM		\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 4)
+#define TEGRA_GPCDMA_CSR_DMA_FIXED_PAT		\
+		FIELD_PREP(TEGRA_GPCDMA_CSR_DMA, 6)
+
+#define TEGRA_GPCDMA_CSR_REQ_SEL_MASK		GENMASK(20, 16)
+#define TEGRA_GPCDMA_CSR_REQ_SEL_UNUSED		\
+					FIELD_PREP(TEGRA_GPCDMA_CSR_REQ_SEL_MASK, 4)
+#define TEGRA_GPCDMA_CSR_IRQ_MASK		BIT(15)
+#define TEGRA_GPCDMA_CSR_WEIGHT			GENMASK(13, 10)
+
+/* STATUS register */
+#define TEGRA_GPCDMA_CHAN_STATUS		0x004
+#define TEGRA_GPCDMA_STATUS_BUSY		BIT(31)
+#define TEGRA_GPCDMA_STATUS_ISE_EOC		BIT(30)
+#define TEGRA_GPCDMA_STATUS_PING_PONG		BIT(28)
+#define TEGRA_GPCDMA_STATUS_DMA_ACTIVITY	BIT(27)
+#define TEGRA_GPCDMA_STATUS_CHANNEL_PAUSE	BIT(26)
+#define TEGRA_GPCDMA_STATUS_CHANNEL_RX		BIT(25)
+#define TEGRA_GPCDMA_STATUS_CHANNEL_TX		BIT(24)
+#define TEGRA_GPCDMA_STATUS_IRQ_INTR_STA	BIT(23)
+#define TEGRA_GPCDMA_STATUS_IRQ_STA		BIT(21)
+#define TEGRA_GPCDMA_STATUS_IRQ_TRIG_STA	BIT(20)
+
+#define TEGRA_GPCDMA_CHAN_CSRE			0x008
+#define TEGRA_GPCDMA_CHAN_CSRE_PAUSE		BIT(31)
+
+/* Source address */
+#define TEGRA_GPCDMA_CHAN_SRC_PTR		0x00C
+
+/* Destination address */
+#define TEGRA_GPCDMA_CHAN_DST_PTR		0x010
+
+/* High address pointer */
+#define TEGRA_GPCDMA_CHAN_HIGH_ADDR_PTR		0x014
+#define TEGRA_GPCDMA_HIGH_ADDR_SRC_PTR		GENMASK(7, 0)
+#define TEGRA_GPCDMA_HIGH_ADDR_DST_PTR		GENMASK(23, 16)
+
+/* MC sequence register */
+#define TEGRA_GPCDMA_CHAN_MCSEQ			0x18
+#define TEGRA_GPCDMA_MCSEQ_DATA_SWAP		BIT(31)
+#define TEGRA_GPCDMA_MCSEQ_REQ_COUNT		GENMASK(30, 25)
+#define TEGRA_GPCDMA_MCSEQ_BURST		GENMASK(24, 23)
+#define TEGRA_GPCDMA_MCSEQ_BURST_2		\
+		FIELD_PREP(TEGRA_GPCDMA_MCSEQ_BURST, 0)
+#define TEGRA_GPCDMA_MCSEQ_BURST_16		\
+		FIELD_PREP(TEGRA_GPCDMA_MCSEQ_BURST, 3)
+#define TEGRA_GPCDMA_MCSEQ_WRAP1		GENMASK(22, 20)
+#define TEGRA_GPCDMA_MCSEQ_WRAP0		GENMASK(19, 17)
+#define TEGRA_GPCDMA_MCSEQ_WRAP_NONE		0
+
+#define TEGRA_GPCDMA_MCSEQ_STREAM_ID1_MASK	GENMASK(13, 7)
+#define TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK	GENMASK(6, 0)
+
+/* MMIO sequence register */
+#define TEGRA_GPCDMA_CHAN_MMIOSEQ			0x01c
+#define TEGRA_GPCDMA_MMIOSEQ_DBL_BUF		BIT(31)
+#define TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH		GENMASK(30, 28)
+#define TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_8	\
+		FIELD_PREP(TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH, 0)
+#define TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_16	\
+		FIELD_PREP(TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH, 1)
+#define TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_32	\
+		FIELD_PREP(TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH, 2)
+#define TEGRA_GPCDMA_MMIOSEQ_DATA_SWAP		BIT(27)
+#define TEGRA_GPCDMA_MMIOSEQ_BURST_SHIFT	23
+#define TEGRA_GPCDMA_MMIOSEQ_BURST_MIN		2U
+#define TEGRA_GPCDMA_MMIOSEQ_BURST_MAX		32U
+#define TEGRA_GPCDMA_MMIOSEQ_BURST(bs)	\
+		(GENMASK((fls(bs) - 2), 0) << TEGRA_GPCDMA_MMIOSEQ_BURST_SHIFT)
+#define TEGRA_GPCDMA_MMIOSEQ_MASTER_ID		GENMASK(22, 19)
+#define TEGRA_GPCDMA_MMIOSEQ_WRAP_WORD		GENMASK(18, 16)
+#define TEGRA_GPCDMA_MMIOSEQ_MMIO_PROT		GENMASK(8, 7)
+
+/* Channel WCOUNT */
+#define TEGRA_GPCDMA_CHAN_WCOUNT		0x20
+
+/* Transfer count */
+#define TEGRA_GPCDMA_CHAN_XFER_COUNT		0x24
+
+/* DMA byte count status */
+#define TEGRA_GPCDMA_CHAN_DMA_BYTE_STATUS	0x28
+
+/* Error Status Register */
+#define TEGRA_GPCDMA_CHAN_ERR_STATUS		0x30
+#define TEGRA_GPCDMA_CHAN_ERR_TYPE_SHIFT	8
+#define TEGRA_GPCDMA_CHAN_ERR_TYPE_MASK	0xF
+#define TEGRA_GPCDMA_CHAN_ERR_TYPE(err)	(			\
+		((err) >> TEGRA_GPCDMA_CHAN_ERR_TYPE_SHIFT) &	\
+		TEGRA_GPCDMA_CHAN_ERR_TYPE_MASK)
+#define TEGRA_DMA_BM_FIFO_FULL_ERR		0xF
+#define TEGRA_DMA_PERIPH_FIFO_FULL_ERR		0xE
+#define TEGRA_DMA_PERIPH_ID_ERR			0xD
+#define TEGRA_DMA_STREAM_ID_ERR			0xC
+#define TEGRA_DMA_MC_SLAVE_ERR			0xB
+#define TEGRA_DMA_MMIO_SLAVE_ERR		0xA
+
+/* Fixed Pattern */
+#define TEGRA_GPCDMA_CHAN_FIXED_PATTERN		0x34
+
+#define TEGRA_GPCDMA_CHAN_TZ			0x38
+#define TEGRA_GPCDMA_CHAN_TZ_MMIO_PROT_1	BIT(0)
+#define TEGRA_GPCDMA_CHAN_TZ_MC_PROT_1		BIT(1)
+
+#define TEGRA_GPCDMA_CHAN_SPARE			0x3c
+#define TEGRA_GPCDMA_CHAN_SPARE_EN_LEGACY_FC	BIT(16)
+
+/*
+ * If any burst is in flight and DMA paused then this is the time to complete
+ * on-flight burst and update DMA status register.
+ */
+#define TEGRA_GPCDMA_BURST_COMPLETE_TIME	20
+#define TEGRA_GPCDMA_BURST_COMPLETION_TIMEOUT	100
+
+/* Channel base address offset from GPCDMA base address */
+#define TEGRA_GPCDMA_CHANNEL_BASE_ADD_OFFSET	0x20000
+
+struct tegra_dma;
+struct tegra_dma_channel;
+
+/*
+ * tegra_dma_chip_data Tegra chip specific DMA data
+ * @nr_channels: Number of channels available in the controller.
+ * @channel_reg_size: Channel register size.
+ * @max_dma_count: Maximum DMA transfer count supported by DMA controller.
+ * @hw_support_pause: DMA HW engine support pause of the channel.
+ */
+struct tegra_dma_chip_data {
+	bool hw_support_pause;
+	unsigned int nr_channels;
+	unsigned int channel_reg_size;
+	unsigned int max_dma_count;
+	int (*terminate)(struct tegra_dma_channel *tdc);
+};
+
+/* DMA channel registers */
+struct tegra_dma_channel_regs {
+	u32 csr;
+	u32 src_ptr;
+	u32 dst_ptr;
+	u32 high_addr_ptr;
+	u32 mc_seq;
+	u32 mmio_seq;
+	u32 wcount;
+	u32 fixed_pattern;
+};
+
+/*
+ * tegra_dma_sg_req: DMA request details to configure hardware. This
+ * contains the details for one transfer to configure DMA hw.
+ * The client's request for data transfer can be broken into multiple
+ * sub-transfer as per requester details and hw support. This sub transfer
+ * get added as an array in Tegra DMA desc which manages the transfer details.
+ */
+struct tegra_dma_sg_req {
+	unsigned int len;
+	struct tegra_dma_channel_regs ch_regs;
+};
+
+/*
+ * tegra_dma_desc: Tegra DMA descriptors which uses virt_dma_desc to
+ * manage client request and keep track of transfer status, callbacks
+ * and request counts etc.
+ */
+struct tegra_dma_desc {
+	bool cyclic;
+	unsigned int bytes_req;
+	unsigned int bytes_xfer;
+	unsigned int sg_idx;
+	unsigned int sg_count;
+	struct virt_dma_desc vd;
+	struct tegra_dma_channel *tdc;
+	struct tegra_dma_sg_req sg_req[];
+};
+
+/*
+ * tegra_dma_channel: Channel specific information
+ */
+struct tegra_dma_channel {
+	bool config_init;
+	char name[30];
+	enum dma_transfer_direction sid_dir;
+	int id;
+	int irq;
+	int slave_id;
+	struct tegra_dma *tdma;
+	struct virt_dma_chan vc;
+	struct tegra_dma_desc *dma_desc;
+	struct dma_slave_config dma_sconfig;
+	unsigned int stream_id;
+	unsigned long chan_base_offset;
+};
+
+/*
+ * tegra_dma: Tegra DMA specific information
+ */
+struct tegra_dma {
+	const struct tegra_dma_chip_data *chip_data;
+	unsigned long sid_m2d_reserved;
+	unsigned long sid_d2m_reserved;
+	void __iomem *base_addr;
+	struct device *dev;
+	struct dma_device dma_dev;
+	struct reset_control *rst;
+	struct tegra_dma_channel channels[];
+};
+
+static inline void tdc_write(struct tegra_dma_channel *tdc,
+			     u32 reg, u32 val)
+{
+	writel_relaxed(val, tdc->tdma->base_addr + tdc->chan_base_offset + reg);
+}
+
+static inline u32 tdc_read(struct tegra_dma_channel *tdc, u32 reg)
+{
+	return readl_relaxed(tdc->tdma->base_addr + tdc->chan_base_offset + reg);
+}
+
+static inline struct tegra_dma_channel *to_tegra_dma_chan(struct dma_chan *dc)
+{
+	return container_of(dc, struct tegra_dma_channel, vc.chan);
+}
+
+static inline struct tegra_dma_desc *vd_to_tegra_dma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct tegra_dma_desc, vd);
+}
+
+static inline struct device *tdc2dev(struct tegra_dma_channel *tdc)
+{
+	return tdc->vc.chan.device->dev;
+}
+
+static void tegra_dma_dump_chan_regs(struct tegra_dma_channel *tdc)
+{
+	dev_dbg(tdc2dev(tdc), "DMA Channel %d name %s register dump:\n",
+		tdc->id, tdc->name);
+	dev_dbg(tdc2dev(tdc), "CSR %x STA %x CSRE %x SRC %x DST %x\n",
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSR),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_STATUS),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_SRC_PTR),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_DST_PTR)
+	);
+	dev_dbg(tdc2dev(tdc), "MCSEQ %x IOSEQ %x WCNT %x XFER %x BSTA %x\n",
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_MMIOSEQ),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_WCOUNT),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_XFER_COUNT),
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_DMA_BYTE_STATUS)
+	);
+	dev_dbg(tdc2dev(tdc), "DMA ERR_STA %x\n",
+		tdc_read(tdc, TEGRA_GPCDMA_CHAN_ERR_STATUS));
+}
+
+static int tegra_dma_sid_reserve(struct tegra_dma_channel *tdc,
+				 enum dma_transfer_direction direction)
+{
+	struct tegra_dma *tdma = tdc->tdma;
+	int sid = tdc->slave_id;
+
+	if (!is_slave_direction(direction))
+		return 0;
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		if (test_and_set_bit(sid, &tdma->sid_m2d_reserved)) {
+			dev_err(tdma->dev, "slave id already in use\n");
+			return -EINVAL;
+		}
+		break;
+	case DMA_DEV_TO_MEM:
+		if (test_and_set_bit(sid, &tdma->sid_d2m_reserved)) {
+			dev_err(tdma->dev, "slave id already in use\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		break;
+	}
+
+	tdc->sid_dir = direction;
+
+	return 0;
+}
+
+static void tegra_dma_sid_free(struct tegra_dma_channel *tdc)
+{
+	struct tegra_dma *tdma = tdc->tdma;
+	int sid = tdc->slave_id;
+
+	switch (tdc->sid_dir) {
+	case DMA_MEM_TO_DEV:
+		clear_bit(sid,  &tdma->sid_m2d_reserved);
+		break;
+	case DMA_DEV_TO_MEM:
+		clear_bit(sid,  &tdma->sid_d2m_reserved);
+		break;
+	default:
+		break;
+	}
+
+	tdc->sid_dir = DMA_TRANS_NONE;
+}
+
+static void tegra_dma_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(container_of(vd, struct tegra_dma_desc, vd));
+}
+
+static int tegra_dma_slave_config(struct dma_chan *dc,
+				  struct dma_slave_config *sconfig)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+
+	memcpy(&tdc->dma_sconfig, sconfig, sizeof(*sconfig));
+	tdc->config_init = true;
+
+	return 0;
+}
+
+static int tegra_dma_pause(struct tegra_dma_channel *tdc)
+{
+	int ret;
+	u32 val;
+
+	val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE);
+	val |= TEGRA_GPCDMA_CHAN_CSRE_PAUSE;
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val);
+
+	/* Wait until busy bit is de-asserted */
+	ret = readl_relaxed_poll_timeout_atomic(tdc->tdma->base_addr +
+			tdc->chan_base_offset + TEGRA_GPCDMA_CHAN_STATUS,
+			val,
+			!(val & TEGRA_GPCDMA_STATUS_BUSY),
+			TEGRA_GPCDMA_BURST_COMPLETE_TIME,
+			TEGRA_GPCDMA_BURST_COMPLETION_TIMEOUT);
+
+	if (ret) {
+		dev_err(tdc2dev(tdc), "DMA pause timed out\n");
+		tegra_dma_dump_chan_regs(tdc);
+	}
+
+	return ret;
+}
+
+static int tegra_dma_device_pause(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned long flags;
+	int ret;
+
+	if (!tdc->tdma->chip_data->hw_support_pause)
+		return -ENOSYS;
+
+	spin_lock_irqsave(&tdc->vc.lock, flags);
+	ret = tegra_dma_pause(tdc);
+	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+
+	return ret;
+}
+
+static void tegra_dma_resume(struct tegra_dma_channel *tdc)
+{
+	u32 val;
+
+	val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE);
+	val &= ~TEGRA_GPCDMA_CHAN_CSRE_PAUSE;
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val);
+}
+
+static int tegra_dma_device_resume(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned long flags;
+
+	if (!tdc->tdma->chip_data->hw_support_pause)
+		return -ENOSYS;
+
+	spin_lock_irqsave(&tdc->vc.lock, flags);
+	tegra_dma_resume(tdc);
+	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+
+	return 0;
+}
+
+static void tegra_dma_disable(struct tegra_dma_channel *tdc)
+{
+	u32 csr, status;
+
+	csr = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSR);
+
+	/* Disable interrupts */
+	csr &= ~TEGRA_GPCDMA_CSR_IE_EOC;
+
+	/* Disable DMA */
+	csr &= ~TEGRA_GPCDMA_CSR_ENB;
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR, csr);
+
+	/* Clear interrupt status if it is there */
+	status = tdc_read(tdc, TEGRA_GPCDMA_CHAN_STATUS);
+	if (status & TEGRA_GPCDMA_STATUS_ISE_EOC) {
+		dev_dbg(tdc2dev(tdc), "%s():clearing interrupt\n", __func__);
+		tdc_write(tdc, TEGRA_GPCDMA_CHAN_STATUS, status);
+	}
+}
+
+static void tegra_dma_configure_next_sg(struct tegra_dma_channel *tdc)
+{
+	struct tegra_dma_desc *dma_desc = tdc->dma_desc;
+	struct tegra_dma_channel_regs *ch_regs;
+	int ret;
+	u32 val;
+
+	dma_desc->sg_idx++;
+
+	/* Reset the sg index for cyclic transfers */
+	if (dma_desc->sg_idx == dma_desc->sg_count)
+		dma_desc->sg_idx = 0;
+
+	/* Configure next transfer immediately after DMA is busy */
+	ret = readl_relaxed_poll_timeout_atomic(tdc->tdma->base_addr +
+			tdc->chan_base_offset + TEGRA_GPCDMA_CHAN_STATUS,
+			val,
+			(val & TEGRA_GPCDMA_STATUS_BUSY), 0,
+			TEGRA_GPCDMA_BURST_COMPLETION_TIMEOUT);
+	if (ret)
+		return;
+
+	ch_regs = &dma_desc->sg_req[dma_desc->sg_idx].ch_regs;
+
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_WCOUNT, ch_regs->wcount);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_SRC_PTR, ch_regs->src_ptr);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_DST_PTR, ch_regs->dst_ptr);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_HIGH_ADDR_PTR, ch_regs->high_addr_ptr);
+
+	/* Start DMA */
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR,
+		  ch_regs->csr | TEGRA_GPCDMA_CSR_ENB);
+}
+
+static void tegra_dma_start(struct tegra_dma_channel *tdc)
+{
+	struct tegra_dma_desc *dma_desc = tdc->dma_desc;
+	struct tegra_dma_channel_regs *ch_regs;
+	struct virt_dma_desc *vdesc;
+
+	if (!dma_desc) {
+		vdesc = vchan_next_desc(&tdc->vc);
+		if (!vdesc)
+			return;
+
+		dma_desc = vd_to_tegra_dma_desc(vdesc);
+		list_del(&vdesc->node);
+		dma_desc->tdc = tdc;
+		tdc->dma_desc = dma_desc;
+
+		tegra_dma_resume(tdc);
+	}
+
+	ch_regs = &dma_desc->sg_req[dma_desc->sg_idx].ch_regs;
+
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_WCOUNT, ch_regs->wcount);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR, 0);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_SRC_PTR, ch_regs->src_ptr);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_DST_PTR, ch_regs->dst_ptr);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_HIGH_ADDR_PTR, ch_regs->high_addr_ptr);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_FIXED_PATTERN, ch_regs->fixed_pattern);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_MMIOSEQ, ch_regs->mmio_seq);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_MCSEQ, ch_regs->mc_seq);
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR, ch_regs->csr);
+
+	/* Start DMA */
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR,
+		  ch_regs->csr | TEGRA_GPCDMA_CSR_ENB);
+}
+
+static void tegra_dma_xfer_complete(struct tegra_dma_channel *tdc)
+{
+	vchan_cookie_complete(&tdc->dma_desc->vd);
+
+	tegra_dma_sid_free(tdc);
+	tdc->dma_desc = NULL;
+}
+
+static void tegra_dma_chan_decode_error(struct tegra_dma_channel *tdc,
+					unsigned int err_status)
+{
+	switch (TEGRA_GPCDMA_CHAN_ERR_TYPE(err_status)) {
+	case TEGRA_DMA_BM_FIFO_FULL_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d bm fifo full\n", tdc->id);
+		break;
+
+	case TEGRA_DMA_PERIPH_FIFO_FULL_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d peripheral fifo full\n", tdc->id);
+		break;
+
+	case TEGRA_DMA_PERIPH_ID_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d illegal peripheral id\n", tdc->id);
+		break;
+
+	case TEGRA_DMA_STREAM_ID_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d illegal stream id\n", tdc->id);
+		break;
+
+	case TEGRA_DMA_MC_SLAVE_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d mc slave error\n", tdc->id);
+		break;
+
+	case TEGRA_DMA_MMIO_SLAVE_ERR:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d mmio slave error\n", tdc->id);
+		break;
+
+	default:
+		dev_err(tdc->tdma->dev,
+			"GPCDMA CH%d security violation %x\n", tdc->id,
+			err_status);
+	}
+}
+
+static irqreturn_t tegra_dma_isr(int irq, void *dev_id)
+{
+	struct tegra_dma_channel *tdc = dev_id;
+	struct tegra_dma_desc *dma_desc = tdc->dma_desc;
+	struct tegra_dma_sg_req *sg_req;
+	u32 status;
+
+	/* Check channel error status register */
+	status = tdc_read(tdc, TEGRA_GPCDMA_CHAN_ERR_STATUS);
+	if (status) {
+		tegra_dma_chan_decode_error(tdc, status);
+		tegra_dma_dump_chan_regs(tdc);
+		tdc_write(tdc, TEGRA_GPCDMA_CHAN_ERR_STATUS, 0xFFFFFFFF);
+	}
+
+	spin_lock(&tdc->vc.lock);
+	status = tdc_read(tdc, TEGRA_GPCDMA_CHAN_STATUS);
+	if (!(status & TEGRA_GPCDMA_STATUS_ISE_EOC))
+		goto irq_done;
+
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_STATUS,
+		  TEGRA_GPCDMA_STATUS_ISE_EOC);
+
+	if (!dma_desc)
+		goto irq_done;
+
+	sg_req = dma_desc->sg_req;
+	dma_desc->bytes_xfer += sg_req[dma_desc->sg_idx].len;
+
+	if (dma_desc->cyclic) {
+		vchan_cyclic_callback(&dma_desc->vd);
+		tegra_dma_configure_next_sg(tdc);
+	} else {
+		dma_desc->sg_idx++;
+		if (dma_desc->sg_idx == dma_desc->sg_count)
+			tegra_dma_xfer_complete(tdc);
+		else
+			tegra_dma_start(tdc);
+	}
+
+irq_done:
+	spin_unlock(&tdc->vc.lock);
+	return IRQ_HANDLED;
+}
+
+static void tegra_dma_issue_pending(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned long flags;
+
+	if (tdc->dma_desc)
+		return;
+
+	spin_lock_irqsave(&tdc->vc.lock, flags);
+	if (vchan_issue_pending(&tdc->vc))
+		tegra_dma_start(tdc);
+
+	/*
+	 * For cyclic DMA transfers, program the second
+	 * transfer parameters as soon as the first DMA
+	 * transfer is started inorder for the DMA
+	 * controller to trigger the second transfer
+	 * with the correct parameters.
+	 */
+	if (tdc->dma_desc && tdc->dma_desc->cyclic)
+		tegra_dma_configure_next_sg(tdc);
+
+	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+}
+
+static int tegra_dma_stop_client(struct tegra_dma_channel *tdc)
+{
+	int ret;
+	u32 status, csr;
+
+	/*
+	 * Change the client associated with the DMA channel
+	 * to stop DMA engine from starting any more bursts for
+	 * the given client and wait for in flight bursts to complete
+	 */
+	csr = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSR);
+	csr &= ~(TEGRA_GPCDMA_CSR_REQ_SEL_MASK);
+	csr |= TEGRA_GPCDMA_CSR_REQ_SEL_UNUSED;
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSR, csr);
+
+	/* Wait for in flight data transfer to finish */
+	udelay(TEGRA_GPCDMA_BURST_COMPLETE_TIME);
+
+	/* If TX/RX path is still active wait till it becomes
+	 * inactive
+	 */
+
+	ret = readl_relaxed_poll_timeout_atomic(tdc->tdma->base_addr +
+				tdc->chan_base_offset +
+				TEGRA_GPCDMA_CHAN_STATUS,
+				status,
+				!(status & (TEGRA_GPCDMA_STATUS_CHANNEL_TX |
+				TEGRA_GPCDMA_STATUS_CHANNEL_RX)),
+				5,
+				TEGRA_GPCDMA_BURST_COMPLETION_TIMEOUT);
+	if (ret) {
+		dev_err(tdc2dev(tdc), "Timeout waiting for DMA burst completion!\n");
+		tegra_dma_dump_chan_regs(tdc);
+	}
+
+	return ret;
+}
+
+static int tegra_dma_terminate_all(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned long flags;
+	LIST_HEAD(head);
+	int err;
+
+	spin_lock_irqsave(&tdc->vc.lock, flags);
+
+	if (tdc->dma_desc) {
+		err = tdc->tdma->chip_data->terminate(tdc);
+		if (err) {
+			spin_unlock_irqrestore(&tdc->vc.lock, flags);
+			return err;
+		}
+
+		tegra_dma_disable(tdc);
+		tdc->dma_desc = NULL;
+	}
+
+	tegra_dma_sid_free(tdc);
+	vchan_get_all_descriptors(&tdc->vc, &head);
+	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+
+	vchan_dma_desc_free_list(&tdc->vc, &head);
+
+	return 0;
+}
+
+static int tegra_dma_get_residual(struct tegra_dma_channel *tdc)
+{
+	struct tegra_dma_desc *dma_desc = tdc->dma_desc;
+	struct tegra_dma_sg_req *sg_req = dma_desc->sg_req;
+	unsigned int bytes_xfer, residual;
+	u32 wcount = 0, status;
+
+	wcount = tdc_read(tdc, TEGRA_GPCDMA_CHAN_XFER_COUNT);
+
+	/*
+	 * Set wcount = 0 if EOC bit is set. The transfer would have
+	 * already completed and the CHAN_XFER_COUNT could have updated
+	 * for the next transfer, specifically in case of cyclic transfers.
+	 */
+	status = tdc_read(tdc, TEGRA_GPCDMA_CHAN_STATUS);
+	if (status & TEGRA_GPCDMA_STATUS_ISE_EOC)
+		wcount = 0;
+
+	bytes_xfer = dma_desc->bytes_xfer +
+		     sg_req[dma_desc->sg_idx].len - (wcount * 4);
+
+	residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req);
+
+	return residual;
+}
+
+static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
+					   dma_cookie_t cookie,
+					   struct dma_tx_state *txstate)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	struct tegra_dma_desc *dma_desc;
+	struct virt_dma_desc *vd;
+	unsigned int residual;
+	unsigned long flags;
+	enum dma_status ret;
+
+	ret = dma_cookie_status(dc, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	spin_lock_irqsave(&tdc->vc.lock, flags);
+	vd = vchan_find_desc(&tdc->vc, cookie);
+	if (vd) {
+		dma_desc = vd_to_tegra_dma_desc(vd);
+		residual = dma_desc->bytes_req;
+		dma_set_residue(txstate, residual);
+	} else if (tdc->dma_desc && tdc->dma_desc->vd.tx.cookie == cookie) {
+		residual =  tegra_dma_get_residual(tdc);
+		dma_set_residue(txstate, residual);
+	} else {
+		dev_err(tdc2dev(tdc), "cookie %d is not found\n", cookie);
+	}
+	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+
+	return ret;
+}
+
+static inline int get_bus_width(struct tegra_dma_channel *tdc,
+				enum dma_slave_buswidth slave_bw)
+{
+	switch (slave_bw) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		return TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_8;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		return TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_16;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		return TEGRA_GPCDMA_MMIOSEQ_BUS_WIDTH_32;
+	default:
+		dev_err(tdc2dev(tdc), "given slave bus width is not supported\n");
+		return -EINVAL;
+	}
+}
+
+static unsigned int get_burst_size(struct tegra_dma_channel *tdc,
+				   u32 burst_size, enum dma_slave_buswidth slave_bw,
+				   int len)
+{
+	unsigned int burst_mmio_width, burst_byte;
+
+	/*
+	 * burst_size from client is in terms of the bus_width.
+	 * convert that into words.
+	 * If burst_size is not specified from client, then use
+	 * len to calculate the optimum burst size
+	 */
+	burst_byte = burst_size ? burst_size * slave_bw : len;
+	burst_mmio_width = burst_byte / 4;
+
+	if (burst_mmio_width < TEGRA_GPCDMA_MMIOSEQ_BURST_MIN)
+		return 0;
+
+	burst_mmio_width = min(burst_mmio_width, TEGRA_GPCDMA_MMIOSEQ_BURST_MAX);
+
+	return TEGRA_GPCDMA_MMIOSEQ_BURST(burst_mmio_width);
+}
+
+static int get_transfer_param(struct tegra_dma_channel *tdc,
+			      enum dma_transfer_direction direction,
+			      u32 *apb_addr,
+			      u32 *mmio_seq,
+			      u32 *csr,
+			      unsigned int *burst_size,
+			      enum dma_slave_buswidth *slave_bw)
+{
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		*apb_addr = tdc->dma_sconfig.dst_addr;
+		*mmio_seq = get_bus_width(tdc, tdc->dma_sconfig.dst_addr_width);
+		*burst_size = tdc->dma_sconfig.dst_maxburst;
+		*slave_bw = tdc->dma_sconfig.dst_addr_width;
+		*csr = TEGRA_GPCDMA_CSR_DMA_MEM2IO_FC;
+		return 0;
+	case DMA_DEV_TO_MEM:
+		*apb_addr = tdc->dma_sconfig.src_addr;
+		*mmio_seq = get_bus_width(tdc, tdc->dma_sconfig.src_addr_width);
+		*burst_size = tdc->dma_sconfig.src_maxburst;
+		*slave_bw = tdc->dma_sconfig.src_addr_width;
+		*csr = TEGRA_GPCDMA_CSR_DMA_IO2MEM_FC;
+		return 0;
+	default:
+		dev_err(tdc2dev(tdc), "DMA direction is not supported\n");
+	}
+
+	return -EINVAL;
+}
+
+static struct dma_async_tx_descriptor *
+tegra_dma_prep_dma_memset(struct dma_chan *dc, dma_addr_t dest, int value,
+			  size_t len, unsigned long flags)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned int max_dma_count = tdc->tdma->chip_data->max_dma_count;
+	struct tegra_dma_sg_req *sg_req;
+	struct tegra_dma_desc *dma_desc;
+	u32 csr, mc_seq;
+
+	if ((len & 3) || (dest & 3) || len > max_dma_count) {
+		dev_err(tdc2dev(tdc),
+			"DMA length/memory address is not supported\n");
+		return NULL;
+	}
+
+	/* Set DMA mode to fixed pattern */
+	csr = TEGRA_GPCDMA_CSR_DMA_FIXED_PAT;
+	/* Enable once or continuous mode */
+	csr |= TEGRA_GPCDMA_CSR_ONCE;
+	/* Enable IRQ mask */
+	csr |= TEGRA_GPCDMA_CSR_IRQ_MASK;
+	/* Enable the DMA interrupt */
+	if (flags & DMA_PREP_INTERRUPT)
+		csr |= TEGRA_GPCDMA_CSR_IE_EOC;
+	/* Configure default priority weight for the channel */
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_WEIGHT, 1);
+
+	mc_seq =  tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ);
+	/* retain stream-id and clean rest */
+	mc_seq &= TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK;
+
+	/* Set the address wrapping */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP0,
+						TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP1,
+						TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+
+	/* Program outstanding MC requests */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_REQ_COUNT, 1);
+	/* Set burst size */
+	mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_16;
+
+	dma_desc = kzalloc(struct_size(dma_desc, sg_req, 1), GFP_NOWAIT);
+	if (!dma_desc)
+		return NULL;
+
+	dma_desc->bytes_req = len;
+	dma_desc->sg_count = 1;
+	sg_req = dma_desc->sg_req;
+
+	sg_req[0].ch_regs.src_ptr = 0;
+	sg_req[0].ch_regs.dst_ptr = dest;
+	sg_req[0].ch_regs.high_addr_ptr =
+			FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_DST_PTR, (dest >> 32));
+	sg_req[0].ch_regs.fixed_pattern = value;
+	/* Word count reg takes value as (N +1) words */
+	sg_req[0].ch_regs.wcount = ((len - 4) >> 2);
+	sg_req[0].ch_regs.csr = csr;
+	sg_req[0].ch_regs.mmio_seq = 0;
+	sg_req[0].ch_regs.mc_seq = mc_seq;
+	sg_req[0].len = len;
+
+	dma_desc->cyclic = false;
+	return vchan_tx_prep(&tdc->vc, &dma_desc->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+tegra_dma_prep_dma_memcpy(struct dma_chan *dc, dma_addr_t dest,
+			  dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	struct tegra_dma_sg_req *sg_req;
+	struct tegra_dma_desc *dma_desc;
+	unsigned int max_dma_count;
+	u32 csr, mc_seq;
+
+	max_dma_count = tdc->tdma->chip_data->max_dma_count;
+	if ((len & 3) || (src & 3) || (dest & 3) || len > max_dma_count) {
+		dev_err(tdc2dev(tdc),
+			"DMA length/memory address is not supported\n");
+		return NULL;
+	}
+
+	/* Set DMA mode to memory to memory transfer */
+	csr = TEGRA_GPCDMA_CSR_DMA_MEM2MEM;
+	/* Enable once or continuous mode */
+	csr |= TEGRA_GPCDMA_CSR_ONCE;
+	/* Enable IRQ mask */
+	csr |= TEGRA_GPCDMA_CSR_IRQ_MASK;
+	/* Enable the DMA interrupt */
+	if (flags & DMA_PREP_INTERRUPT)
+		csr |= TEGRA_GPCDMA_CSR_IE_EOC;
+	/* Configure default priority weight for the channel */
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_WEIGHT, 1);
+
+	mc_seq =  tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ);
+	/* retain stream-id and clean rest */
+	mc_seq &= (TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK) |
+		  (TEGRA_GPCDMA_MCSEQ_STREAM_ID1_MASK);
+
+	/* Set the address wrapping */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP0,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP1,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+
+	/* Program outstanding MC requests */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_REQ_COUNT, 1);
+	/* Set burst size */
+	mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_16;
+
+	dma_desc = kzalloc(struct_size(dma_desc, sg_req, 1), GFP_NOWAIT);
+	if (!dma_desc)
+		return NULL;
+
+	dma_desc->bytes_req = len;
+	dma_desc->sg_count = 1;
+	sg_req = dma_desc->sg_req;
+
+	sg_req[0].ch_regs.src_ptr = src;
+	sg_req[0].ch_regs.dst_ptr = dest;
+	sg_req[0].ch_regs.high_addr_ptr =
+		FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_SRC_PTR, (src >> 32));
+	sg_req[0].ch_regs.high_addr_ptr |=
+		FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_DST_PTR, (dest >> 32));
+	/* Word count reg takes value as (N +1) words */
+	sg_req[0].ch_regs.wcount = ((len - 4) >> 2);
+	sg_req[0].ch_regs.csr = csr;
+	sg_req[0].ch_regs.mmio_seq = 0;
+	sg_req[0].ch_regs.mc_seq = mc_seq;
+	sg_req[0].len = len;
+
+	dma_desc->cyclic = false;
+	return vchan_tx_prep(&tdc->vc, &dma_desc->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+tegra_dma_prep_slave_sg(struct dma_chan *dc, struct scatterlist *sgl,
+			unsigned int sg_len, enum dma_transfer_direction direction,
+			unsigned long flags, void *context)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	unsigned int max_dma_count = tdc->tdma->chip_data->max_dma_count;
+	enum dma_slave_buswidth slave_bw = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	u32 csr, mc_seq, apb_ptr = 0, mmio_seq = 0;
+	struct tegra_dma_sg_req *sg_req;
+	struct tegra_dma_desc *dma_desc;
+	struct scatterlist *sg;
+	u32 burst_size;
+	unsigned int i;
+	int ret;
+
+	if (!tdc->config_init) {
+		dev_err(tdc2dev(tdc), "DMA channel is not configured\n");
+		return NULL;
+	}
+	if (sg_len < 1) {
+		dev_err(tdc2dev(tdc), "Invalid segment length %d\n", sg_len);
+		return NULL;
+	}
+
+	ret = tegra_dma_sid_reserve(tdc, direction);
+	if (ret)
+		return NULL;
+
+	ret = get_transfer_param(tdc, direction, &apb_ptr, &mmio_seq, &csr,
+				 &burst_size, &slave_bw);
+	if (ret < 0)
+		return NULL;
+
+	/* Enable once or continuous mode */
+	csr |= TEGRA_GPCDMA_CSR_ONCE;
+	/* Program the slave id in requestor select */
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_REQ_SEL_MASK, tdc->slave_id);
+	/* Enable IRQ mask */
+	csr |= TEGRA_GPCDMA_CSR_IRQ_MASK;
+	/* Configure default priority weight for the channel*/
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_WEIGHT, 1);
+
+	/* Enable the DMA interrupt */
+	if (flags & DMA_PREP_INTERRUPT)
+		csr |= TEGRA_GPCDMA_CSR_IE_EOC;
+
+	mc_seq =  tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ);
+	/* retain stream-id and clean rest */
+	mc_seq &= TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK;
+
+	/* Set the address wrapping on both MC and MMIO side */
+
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP0,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP1,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+	mmio_seq |= FIELD_PREP(TEGRA_GPCDMA_MMIOSEQ_WRAP_WORD, 1);
+
+	/* Program 2 MC outstanding requests by default. */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_REQ_COUNT, 1);
+
+	/* Setting MC burst size depending on MMIO burst size */
+	if (burst_size == 64)
+		mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_16;
+	else
+		mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_2;
+
+	dma_desc = kzalloc(struct_size(dma_desc, sg_req, sg_len), GFP_NOWAIT);
+	if (!dma_desc)
+		return NULL;
+
+	dma_desc->sg_count = sg_len;
+	sg_req = dma_desc->sg_req;
+
+	/* Make transfer requests */
+	for_each_sg(sgl, sg, sg_len, i) {
+		u32 len;
+		dma_addr_t mem;
+
+		mem = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+
+		if ((len & 3) || (mem & 3) || len > max_dma_count) {
+			dev_err(tdc2dev(tdc),
+				"DMA length/memory address is not supported\n");
+			kfree(dma_desc);
+			return NULL;
+		}
+
+		mmio_seq |= get_burst_size(tdc, burst_size, slave_bw, len);
+		dma_desc->bytes_req += len;
+
+		if (direction == DMA_MEM_TO_DEV) {
+			sg_req[i].ch_regs.src_ptr = mem;
+			sg_req[i].ch_regs.dst_ptr = apb_ptr;
+			sg_req[i].ch_regs.high_addr_ptr =
+				FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_SRC_PTR, (mem >> 32));
+		} else if (direction == DMA_DEV_TO_MEM) {
+			sg_req[i].ch_regs.src_ptr = apb_ptr;
+			sg_req[i].ch_regs.dst_ptr = mem;
+			sg_req[i].ch_regs.high_addr_ptr =
+				FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_DST_PTR, (mem >> 32));
+		}
+
+		/*
+		 * Word count register takes input in words. Writing a value
+		 * of N into word count register means a req of (N+1) words.
+		 */
+		sg_req[i].ch_regs.wcount = ((len - 4) >> 2);
+		sg_req[i].ch_regs.csr = csr;
+		sg_req[i].ch_regs.mmio_seq = mmio_seq;
+		sg_req[i].ch_regs.mc_seq = mc_seq;
+		sg_req[i].len = len;
+	}
+
+	dma_desc->cyclic = false;
+	return vchan_tx_prep(&tdc->vc, &dma_desc->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+tegra_dma_prep_dma_cyclic(struct dma_chan *dc, dma_addr_t buf_addr, size_t buf_len,
+			  size_t period_len, enum dma_transfer_direction direction,
+			  unsigned long flags)
+{
+	enum dma_slave_buswidth slave_bw = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	u32 csr, mc_seq, apb_ptr = 0, mmio_seq = 0, burst_size;
+	unsigned int max_dma_count, len, period_count, i;
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	struct tegra_dma_desc *dma_desc;
+	struct tegra_dma_sg_req *sg_req;
+	dma_addr_t mem = buf_addr;
+	int ret;
+
+	if (!buf_len || !period_len) {
+		dev_err(tdc2dev(tdc), "Invalid buffer/period len\n");
+		return NULL;
+	}
+
+	if (!tdc->config_init) {
+		dev_err(tdc2dev(tdc), "DMA slave is not configured\n");
+		return NULL;
+	}
+
+	ret = tegra_dma_sid_reserve(tdc, direction);
+	if (ret)
+		return NULL;
+
+	/*
+	 * We only support cycle transfer when buf_len is multiple of
+	 * period_len.
+	 */
+	if (buf_len % period_len) {
+		dev_err(tdc2dev(tdc), "buf_len is not multiple of period_len\n");
+		return NULL;
+	}
+
+	len = period_len;
+	max_dma_count = tdc->tdma->chip_data->max_dma_count;
+	if ((len & 3) || (buf_addr & 3) || len > max_dma_count) {
+		dev_err(tdc2dev(tdc), "Req len/mem address is not correct\n");
+		return NULL;
+	}
+
+	ret = get_transfer_param(tdc, direction, &apb_ptr, &mmio_seq, &csr,
+				 &burst_size, &slave_bw);
+	if (ret < 0)
+		return NULL;
+
+	/* Enable once or continuous mode */
+	csr &= ~TEGRA_GPCDMA_CSR_ONCE;
+	/* Program the slave id in requestor select */
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_REQ_SEL_MASK, tdc->slave_id);
+	/* Enable IRQ mask */
+	csr |= TEGRA_GPCDMA_CSR_IRQ_MASK;
+	/* Configure default priority weight for the channel*/
+	csr |= FIELD_PREP(TEGRA_GPCDMA_CSR_WEIGHT, 1);
+
+	/* Enable the DMA interrupt */
+	if (flags & DMA_PREP_INTERRUPT)
+		csr |= TEGRA_GPCDMA_CSR_IE_EOC;
+
+	mmio_seq |= FIELD_PREP(TEGRA_GPCDMA_MMIOSEQ_WRAP_WORD, 1);
+
+	mc_seq =  tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ);
+	/* retain stream-id and clean rest */
+	mc_seq &= TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK;
+
+	/* Set the address wrapping on both MC and MMIO side */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP0,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_WRAP1,
+			     TEGRA_GPCDMA_MCSEQ_WRAP_NONE);
+
+	/* Program 2 MC outstanding requests by default. */
+	mc_seq |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_REQ_COUNT, 1);
+	/* Setting MC burst size depending on MMIO burst size */
+	if (burst_size == 64)
+		mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_16;
+	else
+		mc_seq |= TEGRA_GPCDMA_MCSEQ_BURST_2;
+
+	period_count = buf_len / period_len;
+	dma_desc = kzalloc(struct_size(dma_desc, sg_req, period_count),
+			   GFP_NOWAIT);
+	if (!dma_desc)
+		return NULL;
+
+	dma_desc->bytes_req = buf_len;
+	dma_desc->sg_count = period_count;
+	sg_req = dma_desc->sg_req;
+
+	/* Split transfer equal to period size */
+	for (i = 0; i < period_count; i++) {
+		mmio_seq |= get_burst_size(tdc, burst_size, slave_bw, len);
+		if (direction == DMA_MEM_TO_DEV) {
+			sg_req[i].ch_regs.src_ptr = mem;
+			sg_req[i].ch_regs.dst_ptr = apb_ptr;
+			sg_req[i].ch_regs.high_addr_ptr =
+				FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_SRC_PTR, (mem >> 32));
+		} else if (direction == DMA_DEV_TO_MEM) {
+			sg_req[i].ch_regs.src_ptr = apb_ptr;
+			sg_req[i].ch_regs.dst_ptr = mem;
+			sg_req[i].ch_regs.high_addr_ptr =
+				FIELD_PREP(TEGRA_GPCDMA_HIGH_ADDR_DST_PTR, (mem >> 32));
+		}
+		/*
+		 * Word count register takes input in words. Writing a value
+		 * of N into word count register means a req of (N+1) words.
+		 */
+		sg_req[i].ch_regs.wcount = ((len - 4) >> 2);
+		sg_req[i].ch_regs.csr = csr;
+		sg_req[i].ch_regs.mmio_seq = mmio_seq;
+		sg_req[i].ch_regs.mc_seq = mc_seq;
+		sg_req[i].len = len;
+
+		mem += len;
+	}
+
+	dma_desc->cyclic = true;
+
+	return vchan_tx_prep(&tdc->vc, &dma_desc->vd, flags);
+}
+
+static int tegra_dma_alloc_chan_resources(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	int ret;
+
+	ret = request_irq(tdc->irq, tegra_dma_isr, 0, tdc->name, tdc);
+	if (ret) {
+		dev_err(tdc2dev(tdc), "request_irq failed for %s\n", tdc->name);
+		return ret;
+	}
+
+	dma_cookie_init(&tdc->vc.chan);
+	tdc->config_init = false;
+	return 0;
+}
+
+static void tegra_dma_chan_synchronize(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+
+	synchronize_irq(tdc->irq);
+	vchan_synchronize(&tdc->vc);
+}
+
+static void tegra_dma_free_chan_resources(struct dma_chan *dc)
+{
+	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+
+	dev_dbg(tdc2dev(tdc), "Freeing channel %d\n", tdc->id);
+
+	tegra_dma_terminate_all(dc);
+	synchronize_irq(tdc->irq);
+
+	tasklet_kill(&tdc->vc.task);
+	tdc->config_init = false;
+	tdc->slave_id = -1;
+	tdc->sid_dir = DMA_TRANS_NONE;
+	free_irq(tdc->irq, tdc);
+
+	vchan_free_chan_resources(&tdc->vc);
+}
+
+static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec,
+					   struct of_dma *ofdma)
+{
+	struct tegra_dma *tdma = ofdma->of_dma_data;
+	struct tegra_dma_channel *tdc;
+	struct dma_chan *chan;
+
+	chan = dma_get_any_slave_channel(&tdma->dma_dev);
+	if (!chan)
+		return NULL;
+
+	tdc = to_tegra_dma_chan(chan);
+	tdc->slave_id = dma_spec->args[0];
+
+	return chan;
+}
+
+static const struct tegra_dma_chip_data tegra186_dma_chip_data = {
+	.nr_channels = 31,
+	.channel_reg_size = SZ_64K,
+	.max_dma_count = SZ_1G,
+	.hw_support_pause = false,
+	.terminate = tegra_dma_stop_client,
+};
+
+static const struct tegra_dma_chip_data tegra194_dma_chip_data = {
+	.nr_channels = 31,
+	.channel_reg_size = SZ_64K,
+	.max_dma_count = SZ_1G,
+	.hw_support_pause = true,
+	.terminate = tegra_dma_pause,
+};
+
+static const struct of_device_id tegra_dma_of_match[] = {
+	{
+		.compatible = "nvidia,tegra186-gpcdma",
+		.data = &tegra186_dma_chip_data,
+	}, {
+		.compatible = "nvidia,tegra194-gpcdma",
+		.data = &tegra194_dma_chip_data,
+	}, {
+	},
+};
+MODULE_DEVICE_TABLE(of, tegra_dma_of_match);
+
+static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
+{
+	unsigned int reg_val =  tdc_read(tdc, TEGRA_GPCDMA_CHAN_MCSEQ);
+
+	reg_val &= ~(TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK);
+	reg_val &= ~(TEGRA_GPCDMA_MCSEQ_STREAM_ID1_MASK);
+
+	reg_val |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_STREAM_ID0_MASK, stream_id);
+	reg_val |= FIELD_PREP(TEGRA_GPCDMA_MCSEQ_STREAM_ID1_MASK, stream_id);
+
+	tdc_write(tdc, TEGRA_GPCDMA_CHAN_MCSEQ, reg_val);
+	return 0;
+}
+
+static int tegra_dma_probe(struct platform_device *pdev)
+{
+	const struct tegra_dma_chip_data *cdata = NULL;
+	struct iommu_fwspec *iommu_spec;
+	unsigned int stream_id, i;
+	struct tegra_dma *tdma;
+	int ret;
+
+	cdata = of_device_get_match_data(&pdev->dev);
+
+	tdma = devm_kzalloc(&pdev->dev,
+			    struct_size(tdma, channels, cdata->nr_channels),
+			    GFP_KERNEL);
+	if (!tdma)
+		return -ENOMEM;
+
+	tdma->dev = &pdev->dev;
+	tdma->chip_data = cdata;
+	platform_set_drvdata(pdev, tdma);
+
+	tdma->base_addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(tdma->base_addr))
+		return PTR_ERR(tdma->base_addr);
+
+	tdma->rst = devm_reset_control_get_exclusive(&pdev->dev, "gpcdma");
+	if (IS_ERR(tdma->rst)) {
+		return dev_err_probe(&pdev->dev, PTR_ERR(tdma->rst),
+			      "Missing controller reset\n");
+	}
+	reset_control_reset(tdma->rst);
+
+	tdma->dma_dev.dev = &pdev->dev;
+
+	iommu_spec = dev_iommu_fwspec_get(&pdev->dev);
+	if (!iommu_spec) {
+		dev_err(&pdev->dev, "Missing iommu stream-id\n");
+		return -EINVAL;
+	}
+	stream_id = iommu_spec->ids[0] & 0xffff;
+
+	INIT_LIST_HEAD(&tdma->dma_dev.channels);
+	for (i = 0; i < cdata->nr_channels; i++) {
+		struct tegra_dma_channel *tdc = &tdma->channels[i];
+
+		tdc->irq = platform_get_irq(pdev, i);
+		if (tdc->irq < 0)
+			return tdc->irq;
+
+		tdc->chan_base_offset = TEGRA_GPCDMA_CHANNEL_BASE_ADD_OFFSET +
+					i * cdata->channel_reg_size;
+		snprintf(tdc->name, sizeof(tdc->name), "gpcdma.%d", i);
+		tdc->tdma = tdma;
+		tdc->id = i;
+		tdc->slave_id = -1;
+
+		vchan_init(&tdc->vc, &tdma->dma_dev);
+		tdc->vc.desc_free = tegra_dma_desc_free;
+
+		/* program stream-id for this channel */
+		tegra_dma_program_sid(tdc, stream_id);
+		tdc->stream_id = stream_id;
+	}
+
+	dma_cap_set(DMA_SLAVE, tdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_PRIVATE, tdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_MEMCPY, tdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_MEMSET, tdma->dma_dev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, tdma->dma_dev.cap_mask);
+
+	/*
+	 * Only word aligned transfers are supported. Set the copy
+	 * alignment shift.
+	 */
+	tdma->dma_dev.copy_align = 2;
+	tdma->dma_dev.fill_align = 2;
+	tdma->dma_dev.device_alloc_chan_resources =
+					tegra_dma_alloc_chan_resources;
+	tdma->dma_dev.device_free_chan_resources =
+					tegra_dma_free_chan_resources;
+	tdma->dma_dev.device_prep_slave_sg = tegra_dma_prep_slave_sg;
+	tdma->dma_dev.device_prep_dma_memcpy = tegra_dma_prep_dma_memcpy;
+	tdma->dma_dev.device_prep_dma_memset = tegra_dma_prep_dma_memset;
+	tdma->dma_dev.device_prep_dma_cyclic = tegra_dma_prep_dma_cyclic;
+	tdma->dma_dev.device_config = tegra_dma_slave_config;
+	tdma->dma_dev.device_terminate_all = tegra_dma_terminate_all;
+	tdma->dma_dev.device_tx_status = tegra_dma_tx_status;
+	tdma->dma_dev.device_issue_pending = tegra_dma_issue_pending;
+	tdma->dma_dev.device_pause = tegra_dma_device_pause;
+	tdma->dma_dev.device_resume = tegra_dma_device_resume;
+	tdma->dma_dev.device_synchronize = tegra_dma_chan_synchronize;
+	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	ret = dma_async_device_register(&tdma->dma_dev);
+	if (ret < 0) {
+		dev_err_probe(&pdev->dev, ret,
+			      "GPC DMA driver registration failed\n");
+		return ret;
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 tegra_dma_of_xlate, tdma);
+	if (ret < 0) {
+		dev_err_probe(&pdev->dev, ret,
+			      "GPC DMA OF registration failed\n");
+
+		dma_async_device_unregister(&tdma->dma_dev);
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "GPC DMA driver register %d channels\n",
+		 cdata->nr_channels);
+
+	return 0;
+}
+
+static int tegra_dma_remove(struct platform_device *pdev)
+{
+	struct tegra_dma *tdma = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&tdma->dma_dev);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_dma_pm_suspend(struct device *dev)
+{
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
+	unsigned int i;
+
+	for (i = 0; i < tdma->chip_data->nr_channels; i++) {
+		struct tegra_dma_channel *tdc = &tdma->channels[i];
+
+		if (tdc->dma_desc) {
+			dev_err(tdma->dev, "channel %u busy\n", i);
+			return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_dma_pm_resume(struct device *dev)
+{
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
+	unsigned int i;
+
+	reset_control_reset(tdma->rst);
+
+	for (i = 0; i < tdma->chip_data->nr_channels; i++) {
+		struct tegra_dma_channel *tdc = &tdma->channels[i];
+
+		tegra_dma_program_sid(tdc, tdc->stream_id);
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops tegra_dma_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_dma_pm_suspend, tegra_dma_pm_resume)
+};
+
+static struct platform_driver tegra_dma_driver = {
+	.driver = {
+		.name	= "tegra-gpcdma",
+		.pm	= &tegra_dma_dev_pm_ops,
+		.of_match_table = tegra_dma_of_match,
+	},
+	.probe		= tegra_dma_probe,
+	.remove		= tegra_dma_remove,
+};
+
+module_platform_driver(tegra_dma_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra GPC DMA Controller driver");
+MODULE_AUTHOR("Pavan Kunapuli <pkunapuli@nvidia.com>");
+MODULE_AUTHOR("Rajesh Gumasta <rgumasta@nvidia.com>");
+MODULE_LICENSE("GPL");

drivers/dma/ti/cppi41.c

@@ -1105,8 +1105,12 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	cdd->qmgr_num_pend = glue_info->qmgr_num_pend;
 	cdd->first_completion_queue = glue_info->first_completion_queue;
 
+	/* Parse new and deprecated dma-channels properties */
 	ret = of_property_read_u32(dev->of_node,
-				   "#dma-channels", &cdd->n_chans);
+				   "dma-channels", &cdd->n_chans);
+	if (ret)
+		ret = of_property_read_u32(dev->of_node,
+					   "#dma-channels", &cdd->n_chans);
 	if (ret)
 		goto err_get_n_chans;
 

drivers/dma/ti/k3-psil-am62.c

@@ -70,10 +70,10 @@
 /* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
 static struct psil_ep am62_src_ep_map[] = {
 	/* SAUL */
-	PSIL_SAUL(0x7500, 20, 35, 8, 35, 0),
-	PSIL_SAUL(0x7501, 21, 35, 8, 36, 0),
-	PSIL_SAUL(0x7502, 22, 43, 8, 43, 0),
-	PSIL_SAUL(0x7503, 23, 43, 8, 44, 0),
+	PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
 	/* PDMA_MAIN0 - SPI0-3 */
 	PSIL_PDMA_XY_PKT(0x4302),
 	PSIL_PDMA_XY_PKT(0x4303),

drivers/dma/xilinx/zynqmp_dma.c

@@ -229,7 +229,7 @@ struct zynqmp_dma_chan {
 	bool is_dmacoherent;
 	struct tasklet_struct tasklet;
 	bool idle;
-	u32 desc_size;
+	size_t desc_size;
 	bool err;
 	u32 bus_width;
 	u32 src_burst_len;
@@ -486,7 +486,8 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 	}
 
 	chan->desc_pool_v = dma_alloc_coherent(chan->dev,
-					       (2 * chan->desc_size * ZYNQMP_DMA_NUM_DESCS),
+					       (2 * ZYNQMP_DMA_DESC_SIZE(chan) *
+					       ZYNQMP_DMA_NUM_DESCS),
 					       &chan->desc_pool_p, GFP_KERNEL);
 	if (!chan->desc_pool_v)
 		return -ENOMEM;
@@ -1077,7 +1078,11 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT);
 	pm_runtime_use_autosuspend(zdev->dev);
 	pm_runtime_enable(zdev->dev);
-	pm_runtime_get_sync(zdev->dev);
+	ret = pm_runtime_resume_and_get(zdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "device wakeup failed.\n");
+		pm_runtime_disable(zdev->dev);
+	}
 	if (!pm_runtime_enabled(zdev->dev)) {
 		ret = zynqmp_dma_runtime_resume(zdev->dev);
 		if (ret)
@@ -1093,7 +1098,11 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	p->dst_addr_widths = BIT(zdev->chan->bus_width / 8);
 	p->src_addr_widths = BIT(zdev->chan->bus_width / 8);
 
-	dma_async_device_register(&zdev->common);
+	ret = dma_async_device_register(&zdev->common);
+	if (ret) {
+		dev_err(zdev->dev, "failed to register the dma device\n");
+		goto free_chan_resources;
+	}
 
 	ret = of_dma_controller_register(pdev->dev.of_node,
 					 of_zynqmp_dma_xlate, zdev);

include/linux/dmaengine.h

@@ -870,7 +870,6 @@ struct dma_device {
 	struct device *dev;
 	struct module *owner;
 	struct ida chan_ida;
-	struct mutex chan_mutex;	/* to protect chan_ida */
 
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
@@ -1031,6 +1030,14 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
 	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
 }
 
+/**
+ * dmaengine_prep_dma_memset() - Prepare a DMA memset descriptor.
+ * @chan: The channel to be used for this descriptor
+ * @dest: Address of buffer to be set
+ * @value: Treated as a single byte value that fills the destination buffer
+ * @len: The total size of dest
+ * @flags: DMA engine flags
+ */
 static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset(
 		struct dma_chan *chan, dma_addr_t dest, int value, size_t len,
 		unsigned long flags)

include/linux/soc/renesas/r9a06g032-sysctrl.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__
+#define __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__
+
+#ifdef CONFIG_CLK_R9A06G032
+int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val);
+#else
+static inline int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) { return -ENODEV; }
+#endif
+
+#endif /* __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ */

include/uapi/linux/idxd.h

@@ -53,6 +53,11 @@ enum idxd_scmd_stat {
 
 /* IAX */
 #define IDXD_OP_FLAG_RD_SRC2_AECS	0x010000
+#define IDXD_OP_FLAG_RD_SRC2_2ND	0x020000
+#define IDXD_OP_FLAG_WR_SRC2_AECS_COMP	0x040000
+#define IDXD_OP_FLAG_WR_SRC2_AECS_OVFL	0x080000
+#define IDXD_OP_FLAG_SRC2_STS		0x100000
+#define IDXD_OP_FLAG_CRC_RFC3720	0x200000
 
 /* Opcode */
 enum dsa_opcode {
@@ -81,6 +86,18 @@ enum iax_opcode {
 	IAX_OPCODE_MEMMOVE,
 	IAX_OPCODE_DECOMPRESS = 0x42,
 	IAX_OPCODE_COMPRESS,
+	IAX_OPCODE_CRC64,
+	IAX_OPCODE_ZERO_DECOMP_32 = 0x48,
+	IAX_OPCODE_ZERO_DECOMP_16,
+	IAX_OPCODE_DECOMP_32 = 0x4c,
+	IAX_OPCODE_DECOMP_16,
+	IAX_OPCODE_SCAN = 0x50,
+	IAX_OPCODE_SET_MEMBER,
+	IAX_OPCODE_EXTRACT,
+	IAX_OPCODE_SELECT,
+	IAX_OPCODE_RLE_BURST,
+	IAX_OPCDE_FIND_UNIQUE,
+	IAX_OPCODE_EXPAND,
 };
 
 /* Completion record status */
@@ -120,6 +137,7 @@ enum iax_completion_status {
 	IAX_COMP_NONE = 0,
 	IAX_COMP_SUCCESS,
 	IAX_COMP_PAGE_FAULT_IR = 0x04,
+	IAX_COMP_ANALYTICS_ERROR = 0x0a,
 	IAX_COMP_OUTBUF_OVERFLOW,
 	IAX_COMP_BAD_OPCODE = 0x10,
 	IAX_COMP_INVALID_FLAGS,
@@ -140,7 +158,10 @@ enum iax_completion_status {
 	IAX_COMP_WATCHDOG,
 	IAX_COMP_INVALID_COMP_FLAG = 0x30,
 	IAX_COMP_INVALID_FILTER_FLAG,
-	IAX_COMP_INVALID_NUM_ELEMS = 0x33,
+	IAX_COMP_INVALID_INPUT_SIZE,
+	IAX_COMP_INVALID_NUM_ELEMS,
+	IAX_COMP_INVALID_SRC1_WIDTH,
+	IAX_COMP_INVALID_INVERT_OUT,
 };
 
 #define DSA_COMP_STATUS_MASK		0x7f
@@ -319,8 +340,12 @@ struct iax_completion_record {
 	uint32_t                output_size;
 	uint8_t                 output_bits;
 	uint8_t                 rsvd3;
-	uint16_t                rsvd4;
-	uint64_t                rsvd5[4];
+	uint16_t                xor_csum;
+	uint32_t                crc;
+	uint32_t                min;
+	uint32_t                max;
+	uint32_t                sum;
+	uint64_t                rsvd4[2];
 } __attribute__((packed));
 
 struct iax_raw_completion_record {