Merge tag 'dmaengine-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
"A couple of new device support and small driver updates for this
round.

New support:
- Intel idxd Wildcat Lake family support
- SpacemiT K1 PDMA controller support
- Renesas RZ/G3E family support

Updates:
- Xilinx shutdown support and dma client properties update
- Designware edma callback_result support"

* tag 'dmaengine-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine:
dt-bindings: dma: rz-dmac: Document RZ/G3E family of SoCs
dmaengine: dw-edma: Set status for callback_result
dmaengine: mv_xor: match alloc_wc and free_wc
dmaengine: mmp_pdma: Add SpacemiT K1 PDMA support with 64-bit addressing
dmaengine: mmp_pdma: Add operations structure for controller abstraction
dmaengine: mmp_pdma: Add reset controller support
dmaengine: mmp_pdma: Add clock support
dt-bindings: dma: Add SpacemiT K1 PDMA controller
dt-bindings: dmaengine: xilinx_dma: Remove DMA client properties
dmaengine: Fix dma_async_tx_descriptor->tx_submit documentation
dmaengine: xilinx_dma: Support descriptor setup from dma_vecs
dmaengine: sh: setup_xref error handling
dmaengine: Replace zero-length array with flexible-array
dmaengine: ppc4xx: Remove space before newline
dmaengine: idxd: Add a new IAA device ID for Wildcat Lake family platforms
dmaengine: idxd: Replace memset(0) + strscpy() with strscpy_pad()
dt-bindings: dma: nvidia,tegra20-apbdma: Add undocumented compatibles and "clock-names"
dmaengine: zynqmp_dma: Add shutdown operation support

Documentation/devicetree/bindings/dma/nvidia,tegra20-apbdma.yaml

···
 properties:
   compatible:
     oneOf:
-      - const: nvidia,tegra20-apbdma
+      - enum:
+          - nvidia,tegra114-apbdma
+          - nvidia,tegra20-apbdma
       - items:
           - const: nvidia,tegra30-apbdma
           - const: nvidia,tegra20-apbdma
+      - items:
+          - enum:
+              - nvidia,tegra124-apbdma
+              - nvidia,tegra210-apbdma
+          - const: nvidia,tegra148-apbdma
 
   reg:
     maxItems: 1
···
 
   clocks:
     maxItems: 1
+
+  clock-names:
+    const: dma
 
   interrupts:
     description:

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

···
               - renesas,r9a08g045-dmac # RZ/G3S
           - const: renesas,rz-dmac
 
+      - items:
+          - enum:
+              - renesas,r9a09g047-dmac # RZ/G3E
+          - const: renesas,r9a09g057-dmac
+
       - const: renesas,r9a09g057-dmac # RZ/V2H(P)
 
   reg:

Documentation/devicetree/bindings/dma/spacemit,k1-pdma.yaml

···
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/spacemit,k1-pdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SpacemiT K1 PDMA Controller
+
+maintainers:
+  - Guodong Xu <[e-mail]>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    const: spacemit,k1-pdma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description: Shared interrupt for all DMA channels
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  dma-channels:
+    maximum: 16
+
+  '#dma-cells':
+    const: 1
+    description:
+      The DMA request number for the peripheral device.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - resets
+  - dma-channels
+  - '#dma-cells'
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/spacemit,k1-syscon.h>
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        dma-controller@d4000000 {
+            compatible = "spacemit,k1-pdma";
+            reg = <0x0 0xd4000000 0x0 0x4000>;
+            interrupts = <72>;
+            clocks = <&syscon_apmu CLK_DMA>;
+            resets = <&syscon_apmu RESET_DMA>;
+            dma-channels = <16>;
+            #dma-cells = <1>;
+        };
+    };

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

···
 		xlnx,datawidth = <0x40>;
 	} ;
 } ;
-
-
-* DMA client
-
-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. 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:
-++++++++
-
-vdmatest_0: vdmatest@0 {
-	compatible ="xlnx,axi-vdma-test-1.00.a";
-	dmas = <&axi_vdma_0 0
-		&axi_vdma_0 1>;
-	dma-names = "vdma0", "vdma1";
-} ;

drivers/dma/Kconfig

···
 
 config MMP_PDMA
 	tristate "MMP PDMA support"
-	depends on ARCH_MMP || ARCH_PXA || COMPILE_TEST
+	depends on ARCH_MMP || ARCH_PXA || ARCH_SPACEMIT || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Support the MMP PDMA engine for PXA and MMP platform.

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

···
 	return dw_edma_device_transfer(&xfer);
 }
 
+static void dw_hdma_set_callback_result(struct virt_dma_desc *vd,
+					enum dmaengine_tx_result result)
+{
+	u32 residue = 0;
+	struct dw_edma_desc *desc;
+	struct dmaengine_result *res;
+
+	if (!vd->tx.callback_result)
+		return;
+
+	desc = vd2dw_edma_desc(vd);
+	if (desc)
+		residue = desc->alloc_sz - desc->xfer_sz;
+
+	res = &vd->tx_result;
+	res->result = result;
+	res->residue = residue;
+}
+
 static void dw_edma_done_interrupt(struct dw_edma_chan *chan)
 {
 	struct dw_edma_desc *desc;
···
 		case EDMA_REQ_NONE:
 			desc = vd2dw_edma_desc(vd);
 			if (!desc->chunks_alloc) {
+				dw_hdma_set_callback_result(vd,
+							    DMA_TRANS_NOERROR);
 				list_del(&vd->node);
 				vchan_cookie_complete(vd);
 			}
···
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vd = vchan_next_desc(&chan->vc);
 	if (vd) {
+		dw_hdma_set_callback_result(vd, DMA_TRANS_ABORTED);
 		list_del(&vd->node);
 		vchan_cookie_complete(vd);
 	}

drivers/dma/idxd/defaults.c

···
 	group->num_wqs++;
 
 	/* set name to "iaa_crypto" */
-	memset(wq->name, 0, WQ_NAME_SIZE + 1);
-	strscpy(wq->name, "iaa_crypto", WQ_NAME_SIZE + 1);
+	strscpy_pad(wq->name, "iaa_crypto");
 
 	/* set driver_name to "crypto" */
-	memset(wq->driver_name, 0, DRIVER_NAME_SIZE + 1);
-	strscpy(wq->driver_name, "crypto", DRIVER_NAME_SIZE + 1);
+	strscpy_pad(wq->driver_name, "crypto");
 
 	engine = idxd->engines[0];
 

drivers/dma/idxd/init.c

···
 	{ PCI_DEVICE_DATA(INTEL, IAA_DMR, &idxd_driver_data[IDXD_TYPE_IAX]) },
 	/* IAA PTL platforms */
 	{ PCI_DEVICE_DATA(INTEL, IAA_PTL, &idxd_driver_data[IDXD_TYPE_IAX]) },
+	/* IAA WCL platforms */
+	{ PCI_DEVICE_DATA(INTEL, IAA_WCL, &idxd_driver_data[IDXD_TYPE_IAX]) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);

drivers/dma/idxd/registers.h

···
 #define PCI_DEVICE_ID_INTEL_DSA_DMR	0x1212
 #define PCI_DEVICE_ID_INTEL_IAA_DMR	0x1216
 #define PCI_DEVICE_ID_INTEL_IAA_PTL	0xb02d
+#define PCI_DEVICE_ID_INTEL_IAA_WCL	0xfd2d
 
 #define DEVICE_VERSION_1		0x100
 #define DEVICE_VERSION_2		0x200

drivers/dma/imx-sdma.c

···
 	/* End of v3 array */
 	union { s32 v3_end; s32 mcu_2_zqspi_addr; };
 	/* End of v4 array */
-	s32 v4_end[0];
+	s32 v4_end[];
 };
 
 /*

drivers/dma/mmp_pdma.c

···
 #include <linux/device.h>
 #include <linux/platform_data/mmp_dma.h>
 #include <linux/dmapool.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
 #include <linux/of_dma.h>
 #include <linux/of.h>
 
···
 #define DCSR		0x0000
 #define DALGN		0x00a0
 #define DINT		0x00f0
-#define DDADR		0x0200
+#define DDADR(n)	(0x0200 + ((n) << 4))
 #define DSADR(n)	(0x0204 + ((n) << 4))
 #define DTADR(n)	(0x0208 + ((n) << 4))
+#define DDADRH(n)	(0x0300 + ((n) << 4))
+#define DSADRH(n)	(0x0304 + ((n) << 4))
+#define DTADRH(n)	(0x0308 + ((n) << 4))
 #define DCMD		0x020c
 
 #define DCSR_RUN	BIT(31)	/* Run Bit (read / write) */
···
 #define DCSR_EORSTOPEN	BIT(26)	/* STOP on an EOR */
 #define DCSR_SETCMPST	BIT(25)	/* Set Descriptor Compare Status */
 #define DCSR_CLRCMPST	BIT(24)	/* Clear Descriptor Compare Status */
+#define DCSR_LPAEEN	BIT(21)	/* Long Physical Address Extension Enable */
 #define DCSR_CMPST	BIT(10)	/* The Descriptor Compare Status */
 #define DCSR_EORINTR	BIT(9)	/* The end of Receive */
 
···
 	u32 dsadr;	/* DSADR value for the current transfer */
 	u32 dtadr;	/* DTADR value for the current transfer */
 	u32 dcmd;	/* DCMD value for the current transfer */
+	/*
+	 * The following 32-bit words are only used in the 64-bit, ie.
+	 * LPAE (Long Physical Address Extension) mode.
+	 * They are used to specify the high 32 bits of the descriptor's
+	 * addresses.
+	 */
+	u32 ddadrh;	/* High 32-bit of DDADR */
+	u32 dsadrh;	/* High 32-bit of DSADR */
+	u32 dtadrh;	/* High 32-bit of DTADR */
+	u32 rsvd;	/* reserved */
 } __aligned(32);
 
 struct mmp_pdma_desc_sw {
···
 	struct mmp_pdma_chan *vchan;
 };
 
+/**
+ * struct mmp_pdma_ops - Operations for the MMP PDMA controller
+ *
+ * Hardware Register Operations (read/write hardware registers):
+ * @write_next_addr: Function to program address of next descriptor into
+ *                   DDADR/DDADRH
+ * @read_src_addr: Function to read the source address from DSADR/DSADRH
+ * @read_dst_addr: Function to read the destination address from DTADR/DTADRH
+ *
+ * Descriptor Memory Operations (manipulate descriptor structs in memory):
+ * @set_desc_next_addr: Function to set next descriptor address in descriptor
+ * @set_desc_src_addr: Function to set the source address in descriptor
+ * @set_desc_dst_addr: Function to set the destination address in descriptor
+ * @get_desc_src_addr: Function to get the source address from descriptor
+ * @get_desc_dst_addr: Function to get the destination address from descriptor
+ *
+ * Controller Configuration:
+ * @run_bits:   Control bits in DCSR register for channel start/stop
+ * @dma_mask:   DMA addressing capability of controller. 0 to use OF/platform
+ *              settings, or explicit mask like DMA_BIT_MASK(32/64)
+ */
+struct mmp_pdma_ops {
+	/* Hardware Register Operations */
+	void (*write_next_addr)(struct mmp_pdma_phy *phy, dma_addr_t addr);
+	u64 (*read_src_addr)(struct mmp_pdma_phy *phy);
+	u64 (*read_dst_addr)(struct mmp_pdma_phy *phy);
+
+	/* Descriptor Memory Operations */
+	void (*set_desc_next_addr)(struct mmp_pdma_desc_hw *desc,
+				   dma_addr_t addr);
+	void (*set_desc_src_addr)(struct mmp_pdma_desc_hw *desc,
+				  dma_addr_t addr);
+	void (*set_desc_dst_addr)(struct mmp_pdma_desc_hw *desc,
+				  dma_addr_t addr);
+	u64 (*get_desc_src_addr)(const struct mmp_pdma_desc_hw *desc);
+	u64 (*get_desc_dst_addr)(const struct mmp_pdma_desc_hw *desc);
+
+	/* Controller Configuration */
+	u32 run_bits;
+	u64 dma_mask;
+};
+
 struct mmp_pdma_device {
 	int				dma_channels;
 	void __iomem			*base;
 	struct device			*dev;
 	struct dma_device		device;
 	struct mmp_pdma_phy		*phy;
+	const struct mmp_pdma_ops	*ops;
 	spinlock_t phy_lock; /* protect alloc/free phy channels */
 };
 
···
 #define to_mmp_pdma_dev(dmadev)					\
 	container_of(dmadev, struct mmp_pdma_device, device)
 
-static int mmp_pdma_config_write(struct dma_chan *dchan,
-			   struct dma_slave_config *cfg,
-			   enum dma_transfer_direction direction);
-
-static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
+/* For 32-bit PDMA */
+static void write_next_addr_32(struct mmp_pdma_phy *phy, dma_addr_t addr)
 {
-	u32 reg = (phy->idx << 4) + DDADR;
-
-	writel(addr, phy->base + reg);
+	writel(addr, phy->base + DDADR(phy->idx));
 }
+
+static u64 read_src_addr_32(struct mmp_pdma_phy *phy)
+{
+	return readl(phy->base + DSADR(phy->idx));
+}
+
+static u64 read_dst_addr_32(struct mmp_pdma_phy *phy)
+{
+	return readl(phy->base + DTADR(phy->idx));
+}
+
+static void set_desc_next_addr_32(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->ddadr = addr;
+}
+
+static void set_desc_src_addr_32(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->dsadr = addr;
+}
+
+static void set_desc_dst_addr_32(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->dtadr = addr;
+}
+
+static u64 get_desc_src_addr_32(const struct mmp_pdma_desc_hw *desc)
+{
+	return desc->dsadr;
+}
+
+static u64 get_desc_dst_addr_32(const struct mmp_pdma_desc_hw *desc)
+{
+	return desc->dtadr;
+}
+
+/* For 64-bit PDMA */
+static void write_next_addr_64(struct mmp_pdma_phy *phy, dma_addr_t addr)
+{
+	writel(lower_32_bits(addr), phy->base + DDADR(phy->idx));
+	writel(upper_32_bits(addr), phy->base + DDADRH(phy->idx));
+}
+
+static u64 read_src_addr_64(struct mmp_pdma_phy *phy)
+{
+	u32 low = readl(phy->base + DSADR(phy->idx));
+	u32 high = readl(phy->base + DSADRH(phy->idx));
+
+	return ((u64)high << 32) | low;
+}
+
+static u64 read_dst_addr_64(struct mmp_pdma_phy *phy)
+{
+	u32 low = readl(phy->base + DTADR(phy->idx));
+	u32 high = readl(phy->base + DTADRH(phy->idx));
+
+	return ((u64)high << 32) | low;
+}
+
+static void set_desc_next_addr_64(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->ddadr = lower_32_bits(addr);
+	desc->ddadrh = upper_32_bits(addr);
+}
+
+static void set_desc_src_addr_64(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->dsadr = lower_32_bits(addr);
+	desc->dsadrh = upper_32_bits(addr);
+}
+
+static void set_desc_dst_addr_64(struct mmp_pdma_desc_hw *desc, dma_addr_t addr)
+{
+	desc->dtadr = lower_32_bits(addr);
+	desc->dtadrh = upper_32_bits(addr);
+}
+
+static u64 get_desc_src_addr_64(const struct mmp_pdma_desc_hw *desc)
+{
+	return ((u64)desc->dsadrh << 32) | desc->dsadr;
+}
+
+static u64 get_desc_dst_addr_64(const struct mmp_pdma_desc_hw *desc)
+{
+	return ((u64)desc->dtadrh << 32) | desc->dtadr;
+}
+
+static int mmp_pdma_config_write(struct dma_chan *dchan,
+				 struct dma_slave_config *cfg,
+				 enum dma_transfer_direction direction);
 
 static void enable_chan(struct mmp_pdma_phy *phy)
 {
 	u32 reg, dalgn;
+	struct mmp_pdma_device *pdev;
 
 	if (!phy->vchan)
 		return;
+
+	pdev = to_mmp_pdma_dev(phy->vchan->chan.device);
 
 	reg = DRCMR(phy->vchan->drcmr);
 	writel(DRCMR_MAPVLD | phy->idx, phy->base + reg);
···
 	writel(dalgn, phy->base + DALGN);
 
 	reg = (phy->idx << 2) + DCSR;
-	writel(readl(phy->base + reg) | DCSR_RUN, phy->base + reg);
+	writel(readl(phy->base + reg) | pdev->ops->run_bits,
+	       phy->base + reg);
 }
 
 static void disable_chan(struct mmp_pdma_phy *phy)
 {
-	u32 reg;
+	u32 reg, dcsr;
 
 	if (!phy)
 		return;
 
 	reg = (phy->idx << 2) + DCSR;
-	writel(readl(phy->base + reg) & ~DCSR_RUN, phy->base + reg);
+	dcsr = readl(phy->base + reg);
+
+	if (phy->vchan) {
+		struct mmp_pdma_device *pdev;
+
+		pdev = to_mmp_pdma_dev(phy->vchan->chan.device);
+		writel(dcsr & ~pdev->ops->run_bits, phy->base + reg);
+	} else {
+		/* If no vchan, just clear the RUN bit */
+		writel(dcsr & ~DCSR_RUN, phy->base + reg);
+	}
 }
 
 static int clear_chan_irq(struct mmp_pdma_phy *phy)
···
 static void start_pending_queue(struct mmp_pdma_chan *chan)
 {
 	struct mmp_pdma_desc_sw *desc;
+	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(chan->chan.device);
 
 	/* still in running, irq will start the pending list */
 	if (!chan->idle) {
···
 	 * Program the descriptor's address into the DMA controller,
 	 * then start the DMA transaction
 	 */
-	set_desc(chan->phy, desc->async_tx.phys);
+	pdev->ops->write_next_addr(chan->phy, desc->async_tx.phys);
 	enable_chan(chan->phy);
 	chan->idle = false;
 }
···
 		     size_t len, unsigned long flags)
 {
 	struct mmp_pdma_chan *chan;
+	struct mmp_pdma_device *pdev;
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
 	size_t copy = 0;
 
-	if (!dchan)
+	if (!dchan || !len)
 		return NULL;
 
-	if (!len)
-		return NULL;
-
+	pdev = to_mmp_pdma_dev(dchan->device);
 	chan = to_mmp_pdma_chan(dchan);
 	chan->byte_align = false;
 
···
 			chan->byte_align = true;
 
 		new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & copy);
-		new->desc.dsadr = dma_src;
-		new->desc.dtadr = dma_dst;
+		pdev->ops->set_desc_src_addr(&new->desc, dma_src);
+		pdev->ops->set_desc_dst_addr(&new->desc, dma_dst);
 
 		if (!first)
 			first = new;
 		else
-			prev->desc.ddadr = new->async_tx.phys;
+			pdev->ops->set_desc_next_addr(&prev->desc,
+						      new->async_tx.phys);
 
 		new->async_tx.cookie = 0;
 		async_tx_ack(&new->async_tx);
···
 		       unsigned long flags, void *context)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(dchan->device);
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new = NULL;
 	size_t len, avail;
 	struct scatterlist *sg;
···
 
 			new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & len);
 			if (dir == DMA_MEM_TO_DEV) {
-				new->desc.dsadr = addr;
+				pdev->ops->set_desc_src_addr(&new->desc, addr);
 				new->desc.dtadr = chan->dev_addr;
 			} else {
 				new->desc.dsadr = chan->dev_addr;
-				new->desc.dtadr = addr;
+				pdev->ops->set_desc_dst_addr(&new->desc, addr);
 			}
 
 			if (!first)
 				first = new;
 			else
-				prev->desc.ddadr = new->async_tx.phys;
+				pdev->ops->set_desc_next_addr(&prev->desc,
+							   new->async_tx.phys);
 
 			new->async_tx.cookie = 0;
 			async_tx_ack(&new->async_tx);
···
 			 unsigned long flags)
 {
 	struct mmp_pdma_chan *chan;
+	struct mmp_pdma_device *pdev;
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
 	dma_addr_t dma_src, dma_dst;
 
 	if (!dchan || !len || !period_len)
 		return NULL;
+
+	pdev = to_mmp_pdma_dev(dchan->device);
 
 	/* the buffer length must be a multiple of period_len */
 	if (len % period_len != 0)
···
 
 		new->desc.dcmd = (chan->dcmd | DCMD_ENDIRQEN |
 				  (DCMD_LENGTH & period_len));
-		new->desc.dsadr = dma_src;
-		new->desc.dtadr = dma_dst;
+		pdev->ops->set_desc_src_addr(&new->desc, dma_src);
+		pdev->ops->set_desc_dst_addr(&new->desc, dma_dst);
 
 		if (!first)
 			first = new;
 		else
-			prev->desc.ddadr = new->async_tx.phys;
+			pdev->ops->set_desc_next_addr(&prev->desc,
+						      new->async_tx.phys);
 
 		new->async_tx.cookie = 0;
 		async_tx_ack(&new->async_tx);
···
 	first->async_tx.cookie = -EBUSY;
 
 	/* make the cyclic link */
-	new->desc.ddadr = first->async_tx.phys;
+	pdev->ops->set_desc_next_addr(&new->desc, first->async_tx.phys);
 	chan->cyclic_first = first;
 
 	return &first->async_tx;
···
 				     dma_cookie_t cookie)
 {
 	struct mmp_pdma_desc_sw *sw;
-	u32 curr, residue = 0;
+	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(chan->chan.device);
+	u64 curr;
+	u32 residue = 0;
 	bool passed = false;
 	bool cyclic = chan->cyclic_first != NULL;
 
···
 		return 0;
 
 	if (chan->dir == DMA_DEV_TO_MEM)
-		curr = readl(chan->phy->base + DTADR(chan->phy->idx));
+		curr = pdev->ops->read_dst_addr(chan->phy);
 	else
-		curr = readl(chan->phy->base + DSADR(chan->phy->idx));
+		curr = pdev->ops->read_src_addr(chan->phy);
 
 	list_for_each_entry(sw, &chan->chain_running, node) {
-		u32 start, end, len;
+		u64 start, end;
+		u32 len;
 
 		if (chan->dir == DMA_DEV_TO_MEM)
-			start = sw->desc.dtadr;
+			start = pdev->ops->get_desc_dst_addr(&sw->desc);
 		else
-			start = sw->desc.dsadr;
+			start = pdev->ops->get_desc_src_addr(&sw->desc);
 
 		len = sw->desc.dcmd & DCMD_LENGTH;
 		end = start + len;
···
 		if (passed) {
 			residue += len;
 		} else if (curr >= start && curr <= end) {
-			residue += end - curr;
+			residue += (u32)(end - curr);
 			passed = true;
 		}
 
···
 	return 0;
 }
 
+static const struct mmp_pdma_ops marvell_pdma_v1_ops = {
+	.write_next_addr = write_next_addr_32,
+	.read_src_addr = read_src_addr_32,
+	.read_dst_addr = read_dst_addr_32,
+	.set_desc_next_addr = set_desc_next_addr_32,
+	.set_desc_src_addr = set_desc_src_addr_32,
+	.set_desc_dst_addr = set_desc_dst_addr_32,
+	.get_desc_src_addr = get_desc_src_addr_32,
+	.get_desc_dst_addr = get_desc_dst_addr_32,
+	.run_bits = (DCSR_RUN),
+	.dma_mask = 0,			/* let OF/platform set DMA mask */
+};
+
+static const struct mmp_pdma_ops spacemit_k1_pdma_ops = {
+	.write_next_addr = write_next_addr_64,
+	.read_src_addr = read_src_addr_64,
+	.read_dst_addr = read_dst_addr_64,
+	.set_desc_next_addr = set_desc_next_addr_64,
+	.set_desc_src_addr = set_desc_src_addr_64,
+	.set_desc_dst_addr = set_desc_dst_addr_64,
+	.get_desc_src_addr = get_desc_src_addr_64,
+	.get_desc_dst_addr = get_desc_dst_addr_64,
+	.run_bits = (DCSR_RUN | DCSR_LPAEEN),
+	.dma_mask = DMA_BIT_MASK(64),	/* force 64-bit DMA addr capability */
+};
+
 static const struct of_device_id mmp_pdma_dt_ids[] = {
-	{ .compatible = "marvell,pdma-1.0", },
-	{}
+	{
+		.compatible = "marvell,pdma-1.0",
+		.data = &marvell_pdma_v1_ops
+	}, {
+		.compatible = "spacemit,k1-pdma",
+		.data = &spacemit_k1_pdma_ops
+	}, {
+		/* sentinel */
+	}
 };
 MODULE_DEVICE_TABLE(of, mmp_pdma_dt_ids);
 
···
 {
 	struct mmp_pdma_device *pdev;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
+	struct clk *clk;
+	struct reset_control *rst;
 	int i, ret, irq = 0;
 	int dma_channels = 0, irq_num = 0;
 	const enum dma_slave_buswidth widths =
···
 	pdev->base = devm_platform_ioremap_resource(op, 0);
 	if (IS_ERR(pdev->base))
 		return PTR_ERR(pdev->base);
+
+	clk = devm_clk_get_optional_enabled(pdev->dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	rst = devm_reset_control_get_optional_exclusive_deasserted(pdev->dev,
+								   NULL);
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	pdev->ops = of_device_get_match_data(&op->dev);
+	if (!pdev->ops)
+		return -ENODEV;
 
 	if (pdev->dev->of_node) {
 		/* Parse new and deprecated dma-channels properties */
···
 	pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
 	pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
-	if (pdev->dev->coherent_dma_mask)
+	/* Set DMA mask based on ops->dma_mask, or OF/platform */
+	if (pdev->ops->dma_mask)
+		dma_set_mask(pdev->dev, pdev->ops->dma_mask);
+	else if (pdev->dev->coherent_dma_mask)
 		dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask);
 	else
 		dma_set_mask(pdev->dev, DMA_BIT_MASK(64));

drivers/dma/mv_xor.c

···
 
 	dma_async_device_unregister(&mv_chan->dmadev);
 
-	dma_free_coherent(dev, MV_XOR_POOL_SIZE,
+	dma_free_wc(dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
 	dma_unmap_single(dev, mv_chan->dummy_src_addr,
 			 MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
···
 err_free_irq:
 	free_irq(mv_chan->irq, mv_chan);
 err_free_dma:
-	dma_free_coherent(&pdev->dev, MV_XOR_POOL_SIZE,
+	dma_free_wc(&pdev->dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
 err_unmap_dst:
 	dma_unmap_single(dma_dev->dev, mv_chan->dummy_dst_addr,

drivers/dma/ppc4xx/adma.c

···
 		pr_err("%s: src_cnt=%d, state=%d, addr_count=%d, order=%lld\n",
 			__func__, src_cnt, state, addr_count, order);
 		for (i = 0; i < src_cnt; i++)
-			pr_err("\t[%d] 0x%llx \n", i, srcs[i]);
+			pr_err("\t[%d] 0x%llx\n", i, srcs[i]);
 		BUG();
 	}
 
···
 
 	ppc440spe_chan = to_ppc440spe_adma_chan(chan);
 	dev_dbg(ppc440spe_chan->device->common.dev,
-		"ppc440spe adma%d: %s %d \n", ppc440spe_chan->device->id,
+		"ppc440spe adma%d: %s %d\n", ppc440spe_chan->device->id,
 		__func__, ppc440spe_chan->pending);
 
 	if (ppc440spe_chan->pending) {

drivers/dma/sh/shdma-base.c

···
 			const struct shdma_ops *ops = sdev->ops;
 			dev_dbg(schan->dev, "Bring up channel %d\n",
 				schan->id);
-			/*
-			 * TODO: .xfer_setup() might fail on some platforms.
-			 * Make it int then, on error remove chunks from the
-			 * queue again
-			 */
-			ops->setup_xfer(schan, schan->slave_id);
+
+			ret = ops->setup_xfer(schan, schan->slave_id);
+			if (ret < 0) {
+				dev_err(schan->dev, "setup_xfer failed: %d\n", ret);
+
+				/* Remove chunks from the queue and mark them as idle */
+				list_for_each_entry_safe(chunk, c, &schan->ld_queue, node) {
+					if (chunk->cookie == cookie) {
+						chunk->mark = DESC_IDLE;
+						list_move(&chunk->node, &schan->ld_free);
+					}
+				}
+
+				schan->pm_state = SHDMA_PM_ESTABLISHED;
+				ret = pm_runtime_put(schan->dev);
+
+				spin_unlock_irq(&schan->chan_lock);
+				return ret;
+			}
 
 			if (schan->pm_state == SHDMA_PM_PENDING)
 				shdma_chan_xfer_ld_queue(schan);

drivers/dma/sh/shdmac.c

···
 	return dmae_is_busy(sh_chan);
 }
 
-static void sh_dmae_setup_xfer(struct shdma_chan *schan,
-			       int slave_id)
+static int sh_dmae_setup_xfer(struct shdma_chan *schan, int slave_id)
 {
 	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
 						    shdma_chan);
 
+	int ret = 0;
 	if (slave_id >= 0) {
 		const struct sh_dmae_slave_config *cfg =
 			sh_chan->config;
 
-		dmae_set_dmars(sh_chan, cfg->mid_rid);
-		dmae_set_chcr(sh_chan, cfg->chcr);
+		ret = dmae_set_dmars(sh_chan, cfg->mid_rid);
+		if (ret < 0)
+			goto END;
+
+		ret = dmae_set_chcr(sh_chan, cfg->chcr);
+		if (ret < 0)
+			goto END;
+
 	} else {
 		dmae_init(sh_chan);
 	}
+
+END:
+	return ret;
 }
 
 /*

drivers/dma/xilinx/xilinx_dma.c

···
 }
 
 /**
+ * xilinx_dma_prep_peripheral_dma_vec - prepare descriptors for a DMA_SLAVE
+ *	transaction from DMA vectors
+ * @dchan: DMA channel
+ * @vecs: Array of DMA vectors that should be transferred
+ * @nb: number of entries in @vecs
+ * @direction: DMA direction
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *xilinx_dma_prep_peripheral_dma_vec(
+	struct dma_chan *dchan, const struct dma_vec *vecs, size_t nb,
+	enum dma_transfer_direction direction, unsigned long flags)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_axidma_tx_segment *segment, *head, *prev = NULL;
+	size_t copy;
+	size_t sg_used;
+	unsigned int i;
+
+	if (!is_slave_direction(direction) || direction != chan->direction)
+		return NULL;
+
+	desc = xilinx_dma_alloc_tx_descriptor(chan);
+	if (!desc)
+		return NULL;
+
+	dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+	desc->async_tx.tx_submit = xilinx_dma_tx_submit;
+
+	/* Build transactions using information from DMA vectors */
+	for (i = 0; i < nb; i++) {
+		sg_used = 0;
+
+		/* Loop until the entire dma_vec entry is used */
+		while (sg_used < vecs[i].len) {
+			struct xilinx_axidma_desc_hw *hw;
+
+			/* Get a free segment */
+			segment = xilinx_axidma_alloc_tx_segment(chan);
+			if (!segment)
+				goto error;
+
+			/*
+			 * Calculate the maximum number of bytes to transfer,
+			 * making sure it is less than the hw limit
+			 */
+			copy = xilinx_dma_calc_copysize(chan, vecs[i].len,
+					sg_used);
+			hw = &segment->hw;
+
+			/* Fill in the descriptor */
+			xilinx_axidma_buf(chan, hw, vecs[i].addr, sg_used, 0);
+			hw->control = copy;
+
+			if (prev)
+				prev->hw.next_desc = segment->phys;
+
+			prev = segment;
+			sg_used += copy;
+
+			/*
+			 * Insert the segment into the descriptor segments
+			 * list.
+			 */
+			list_add_tail(&segment->node, &desc->segments);
+		}
+	}
+
+	head = list_first_entry(&desc->segments, struct xilinx_axidma_tx_segment, node);
+	desc->async_tx.phys = head->phys;
+
+	/* For the last DMA_MEM_TO_DEV transfer, set EOP */
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		segment->hw.control |= XILINX_DMA_BD_SOP;
+		segment = list_last_entry(&desc->segments,
+					  struct xilinx_axidma_tx_segment,
+					  node);
+		segment->hw.control |= XILINX_DMA_BD_EOP;
+	}
+
+	if (chan->xdev->has_axistream_connected)
+		desc->async_tx.metadata_ops = &xilinx_dma_metadata_ops;
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
+/**
  * xilinx_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
  * @dchan: DMA channel
  * @sgl: scatterlist to transfer to/from
···
 	xdev->common.device_config = xilinx_dma_device_config;
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		dma_cap_set(DMA_CYCLIC, xdev->common.cap_mask);
+		xdev->common.device_prep_peripheral_dma_vec = xilinx_dma_prep_peripheral_dma_vec;
 		xdev->common.device_prep_slave_sg = xilinx_dma_prep_slave_sg;
 		xdev->common.device_prep_dma_cyclic =
 					  xilinx_dma_prep_dma_cyclic;

drivers/dma/xilinx/zynqmp_dma.c

···
 	dma_async_device_unregister(&zdev->common);
 
 	zynqmp_dma_chan_remove(zdev->chan);
-	pm_runtime_disable(zdev->dev);
-	if (!pm_runtime_enabled(zdev->dev))
+	if (pm_runtime_active(zdev->dev))
 		zynqmp_dma_runtime_suspend(zdev->dev);
+	pm_runtime_disable(zdev->dev);
 }
 
 static const struct of_device_id zynqmp_dma_of_match[] = {
···
 	},
 	.probe = zynqmp_dma_probe,
 	.remove = zynqmp_dma_remove,
+	.shutdown = zynqmp_dma_remove,
 };
 
 module_platform_driver(zynqmp_dma_driver);

include/linux/dmaengine.h

···
  * @phys: physical address of the descriptor
  * @chan: target channel for this operation
  * @tx_submit: accept the descriptor, assign ordered cookie and mark the
+ *	descriptor pending. To be pushed on .issue_pending() call
  * @desc_free: driver's callback function to free a resusable descriptor
  *	after completion
- * descriptor pending. To be pushed on .issue_pending() call
  * @callback: routine to call after this operation is complete
  * @callback_result: error result from a DMA transaction
  * @callback_param: general parameter to pass to the callback routine

include/linux/shdma-base.h

···
 	int (*desc_setup)(struct shdma_chan *, struct shdma_desc *,
 			  dma_addr_t, dma_addr_t, size_t *);
 	int (*set_slave)(struct shdma_chan *, int, dma_addr_t, bool);
-	void (*setup_xfer)(struct shdma_chan *, int);
+	int (*setup_xfer)(struct shdma_chan *, int);
 	void (*start_xfer)(struct shdma_chan *, struct shdma_desc *);
 	struct shdma_desc *(*embedded_desc)(void *, int);
 	bool (*chan_irq)(struct shdma_chan *, int);