kbuild: rust: keep Rust objects out of Clang LTO with inline helpersgrafted

Under `CONFIG_LTO_CLANG` + `CONFIG_RUST_INLINE_HELPERS`, one may hit
`objtool` errors such as:

    vmlinux.o: error: objtool: _R..._3Gsp4boot+0xd6a:
    can't find jump dest instruction at .text._R..._3Gsp4boot+0x1dfd

The reason is that in such builds, the Clang invocation that compiles
the combined Rust plus helpers bitcode emits LLVM bitcode (again) --
the final code generation happens in the linker's LTO step, which the
`-mllvm` trap options passed to Clang do not reach.

This, in turn, means that unreachable traps are missing, and the
impossible paths do not merely fallthrough to the next symbol, but past
the end of their own section, since LTO builds place each function in
its own section.

Thus filter `CC_FLAGS_LTO` out of the Clang invocation, so that it always
emits machine code directly, with the traps in place.

Assisted-by: LLM
Cc: Gary Guo <gary@garyguo.net>
Cc: Boqun Feng <boqun@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Matthew Maurer <mmaurer@google.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Fixes: 3a2486cc1da5 ("kbuild: rust: provide an option to inline C helpers into Rust")
Acked-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260816133233.197500-2-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>

6 files changed, 7992 insertions, 0 deletions

diff --git a/drivers/dma/xilinx/Makefile b/drivers/dma/xilinx/Makefile
new file mode 100644
index 000000000..ebaa93644
--- /dev/null
+++ b/drivers/dma/xilinx/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_XILINX_DMA) += xilinx_dma.o
+obj-$(CONFIG_XILINX_XDMA) += xdma.o
+obj-$(CONFIG_XILINX_ZYNQMP_DMA) += zynqmp_dma.o
+obj-$(CONFIG_XILINX_ZYNQMP_DPDMA) += xilinx_dpdma.o
diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
new file mode 100644
index 000000000..70bca9262
--- /dev/null
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2017-2020 Xilinx, Inc. All rights reserved.
+ * Copyright (C) 2022, Advanced Micro Devices, Inc.
+ */
+
+#ifndef __DMA_XDMA_REGS_H
+#define __DMA_XDMA_REGS_H
+
+/* The length of register space exposed to host */
+#define XDMA_REG_SPACE_LEN	65536
+#define XDMA_MAX_REG_OFFSET	(XDMA_REG_SPACE_LEN - 4)
+
+/*
+ * maximum number of DMA channels for each direction:
+ * Host to Card (H2C) or Card to Host (C2H)
+ */
+#define XDMA_MAX_CHANNELS	4
+
+/*
+ * macros to define the number of descriptor blocks can be used in one
+ * DMA transfer request.
+ * the DMA engine uses a linked list of descriptor blocks that specify the
+ * source, destination, and length of the DMA transfers.
+ */
+#define XDMA_DESC_BLOCK_NUM		BIT(7)
+#define XDMA_DESC_BLOCK_MASK		(XDMA_DESC_BLOCK_NUM - 1)
+
+/* descriptor definitions */
+#define XDMA_DESC_ADJACENT		32
+#define XDMA_DESC_ADJACENT_MASK		(XDMA_DESC_ADJACENT - 1)
+#define XDMA_DESC_ADJACENT_BITS		GENMASK(13, 8)
+#define XDMA_DESC_MAGIC			0xad4bUL
+#define XDMA_DESC_MAGIC_BITS		GENMASK(31, 16)
+#define XDMA_DESC_FLAGS_BITS		GENMASK(7, 0)
+#define XDMA_DESC_STOPPED		BIT(0)
+#define XDMA_DESC_COMPLETED		BIT(1)
+#define XDMA_DESC_BLEN_BITS		28
+#define XDMA_DESC_BLEN_MAX		(BIT(XDMA_DESC_BLEN_BITS) - PAGE_SIZE)
+
+/* macros to construct the descriptor control word */
+#define XDMA_DESC_CONTROL(adjacent, flag)				\
+	(FIELD_PREP(XDMA_DESC_MAGIC_BITS, XDMA_DESC_MAGIC) |		\
+	 FIELD_PREP(XDMA_DESC_ADJACENT_BITS, (adjacent) - 1) |		\
+	 FIELD_PREP(XDMA_DESC_FLAGS_BITS, (flag)))
+#define XDMA_DESC_CONTROL_LAST						\
+	XDMA_DESC_CONTROL(1, XDMA_DESC_STOPPED | XDMA_DESC_COMPLETED)
+#define XDMA_DESC_CONTROL_CYCLIC					\
+	XDMA_DESC_CONTROL(1, XDMA_DESC_COMPLETED)
+
+/*
+ * Descriptor for a single contiguous memory block transfer.
+ *
+ * Multiple descriptors are linked by means of the next pointer. An additional
+ * extra adjacent number gives the amount of extra contiguous descriptors.
+ *
+ * The descriptors are in root complex memory, and the bytes in the 32-bit
+ * words must be in little-endian byte ordering.
+ */
+struct xdma_hw_desc {
+	__le32		control;
+	__le32		bytes;
+	__le64		src_addr;
+	__le64		dst_addr;
+	__le64		next_desc;
+};
+
+#define XDMA_DESC_SIZE			sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE		(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN		32
+#define XDMA_DESC_BLOCK_BOUNDARY	4096
+
+/*
+ * Channel registers
+ */
+#define XDMA_CHAN_IDENTIFIER		0x0
+#define XDMA_CHAN_CONTROL		0x4
+#define XDMA_CHAN_CONTROL_W1S		0x8
+#define XDMA_CHAN_CONTROL_W1C		0xc
+#define XDMA_CHAN_STATUS		0x40
+#define XDMA_CHAN_STATUS_RC		0x44
+#define XDMA_CHAN_COMPLETED_DESC	0x48
+#define XDMA_CHAN_ALIGNMENTS		0x4c
+#define XDMA_CHAN_INTR_ENABLE		0x90
+#define XDMA_CHAN_INTR_ENABLE_W1S	0x94
+#define XDMA_CHAN_INTR_ENABLE_W1C	0x9c
+
+#define XDMA_CHAN_STRIDE	0x100
+#define XDMA_CHAN_H2C_OFFSET	0x0
+#define XDMA_CHAN_C2H_OFFSET	0x1000
+#define XDMA_CHAN_H2C_TARGET	0x0
+#define XDMA_CHAN_C2H_TARGET	0x1
+
+/* macro to check if channel is available */
+#define XDMA_CHAN_MAGIC		0x1fc0
+#define XDMA_CHAN_CHECK_TARGET(id, target)		\
+	(((u32)(id) >> 16) == XDMA_CHAN_MAGIC + (target))
+
+/* bits of the channel control register */
+#define CHAN_CTRL_RUN_STOP			BIT(0)
+#define CHAN_CTRL_IE_DESC_STOPPED		BIT(1)
+#define CHAN_CTRL_IE_DESC_COMPLETED		BIT(2)
+#define CHAN_CTRL_IE_DESC_ALIGN_MISMATCH	BIT(3)
+#define CHAN_CTRL_IE_MAGIC_STOPPED		BIT(4)
+#define CHAN_CTRL_IE_IDLE_STOPPED		BIT(6)
+#define CHAN_CTRL_IE_READ_ERROR			GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR		GENMASK(18, 14)
+#define CHAN_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
+#define CHAN_CTRL_NON_INCR_ADDR			BIT(25)
+#define CHAN_CTRL_POLL_MODE_WB			BIT(26)
+
+#define CHAN_CTRL_START	(CHAN_CTRL_RUN_STOP |				\
+			 CHAN_CTRL_IE_DESC_STOPPED |			\
+			 CHAN_CTRL_IE_DESC_COMPLETED |			\
+			 CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |		\
+			 CHAN_CTRL_IE_MAGIC_STOPPED |			\
+			 CHAN_CTRL_IE_READ_ERROR |			\
+			 CHAN_CTRL_IE_WRITE_ERROR |			\
+			 CHAN_CTRL_IE_DESC_ERROR)
+
+/* bits of the channel status register */
+#define XDMA_CHAN_STATUS_BUSY			BIT(0)
+
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\
+			      CHAN_CTRL_IE_MAGIC_STOPPED |		\
+			      CHAN_CTRL_IE_READ_ERROR |			\
+			      CHAN_CTRL_IE_WRITE_ERROR |		\
+			      CHAN_CTRL_IE_DESC_ERROR)
+
+/* bits of the channel interrupt enable mask */
+#define CHAN_IM_DESC_ERROR			BIT(19)
+#define CHAN_IM_READ_ERROR			BIT(9)
+#define CHAN_IM_IDLE_STOPPED			BIT(6)
+#define CHAN_IM_MAGIC_STOPPED			BIT(4)
+#define CHAN_IM_DESC_COMPLETED			BIT(2)
+#define CHAN_IM_DESC_STOPPED			BIT(1)
+
+#define CHAN_IM_ALL	(CHAN_IM_DESC_ERROR | CHAN_IM_READ_ERROR |	\
+			 CHAN_IM_IDLE_STOPPED | CHAN_IM_MAGIC_STOPPED | \
+			 CHAN_IM_DESC_COMPLETED | CHAN_IM_DESC_STOPPED)
+
+/*
+ * Channel SGDMA registers
+ */
+#define XDMA_SGDMA_IDENTIFIER	0x4000
+#define XDMA_SGDMA_DESC_LO	0x4080
+#define XDMA_SGDMA_DESC_HI	0x4084
+#define XDMA_SGDMA_DESC_ADJ	0x4088
+#define XDMA_SGDMA_DESC_CREDIT	0x408c
+
+/*
+ * interrupt registers
+ */
+#define XDMA_IRQ_IDENTIFIER		0x2000
+#define XDMA_IRQ_USER_INT_EN		0x2004
+#define XDMA_IRQ_USER_INT_EN_W1S	0x2008
+#define XDMA_IRQ_USER_INT_EN_W1C	0x200c
+#define XDMA_IRQ_CHAN_INT_EN		0x2010
+#define XDMA_IRQ_CHAN_INT_EN_W1S	0x2014
+#define XDMA_IRQ_CHAN_INT_EN_W1C	0x2018
+#define XDMA_IRQ_USER_INT_REQ		0x2040
+#define XDMA_IRQ_CHAN_INT_REQ		0x2044
+#define XDMA_IRQ_USER_INT_PEND		0x2048
+#define XDMA_IRQ_CHAN_INT_PEND		0x204c
+#define XDMA_IRQ_USER_VEC_NUM		0x2080
+#define XDMA_IRQ_CHAN_VEC_NUM		0x20a0
+
+#define XDMA_IRQ_VEC_SHIFT		8
+
+#endif /* __DMA_XDMA_REGS_H */
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
new file mode 100644
index 000000000..8d4a5d14e
--- /dev/null
+++ b/drivers/dma/xilinx/xdma.c
@@ -0,0 +1,1320 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DMA driver for Xilinx DMA/Bridge Subsystem
+ *
+ * Copyright (C) 2017-2020 Xilinx, Inc. All rights reserved.
+ * Copyright (C) 2022, Advanced Micro Devices, Inc.
+ */
+
+/*
+ * The DMA/Bridge Subsystem for PCI Express allows for the movement of data
+ * between Host memory and the DMA subsystem. It does this by operating on
+ * 'descriptors' that contain information about the source, destination and
+ * amount of data to transfer. These direct memory transfers can be both in
+ * the Host to Card (H2C) and Card to Host (C2H) transfers. The DMA can be
+ * configured to have a single AXI4 Master interface shared by all channels
+ * or one AXI4-Stream interface for each channel enabled. Memory transfers are
+ * specified on a per-channel basis in descriptor linked lists, which the DMA
+ * fetches from host memory and processes. Events such as descriptor completion
+ * and errors are signaled using interrupts. The core also provides up to 16
+ * user interrupt wires that generate interrupts to the host.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dmapool.h>
+#include <linux/regmap.h>
+#include <linux/dmaengine.h>
+#include <linux/dma/amd_xdma.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/amd_xdma.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include "../virt-dma.h"
+#include "xdma-regs.h"
+
+/* mmio regmap config for all XDMA registers */
+static const struct regmap_config xdma_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = XDMA_MAX_REG_OFFSET,
+};
+
+/**
+ * struct xdma_desc_block - Descriptor block
+ * @virt_addr: Virtual address of block start
+ * @dma_addr: DMA address of block start
+ */
+struct xdma_desc_block {
+	void		*virt_addr;
+	dma_addr_t	dma_addr;
+};
+
+/**
+ * struct xdma_chan - Driver specific DMA channel structure
+ * @vchan: Virtual channel
+ * @xdev_hdl: Pointer to DMA device structure
+ * @base: Offset of channel registers
+ * @desc_pool: Descriptor pool
+ * @busy: Busy flag of the channel
+ * @dir: Transferring direction of the channel
+ * @cfg: Transferring config of the channel
+ * @irq: IRQ assigned to the channel
+ * @last_interrupt: task for comppleting last interrupt
+ * @stop_requested: stop request flag
+ */
+struct xdma_chan {
+	struct virt_dma_chan		vchan;
+	void				*xdev_hdl;
+	u32				base;
+	struct dma_pool			*desc_pool;
+	bool				busy;
+	enum dma_transfer_direction	dir;
+	struct dma_slave_config		cfg;
+	u32				irq;
+	struct completion		last_interrupt;
+	bool				stop_requested;
+};
+
+/**
+ * struct xdma_desc - DMA desc structure
+ * @vdesc: Virtual DMA descriptor
+ * @chan: DMA channel pointer
+ * @dir: Transferring direction of the request
+ * @desc_blocks: Hardware descriptor blocks
+ * @dblk_num: Number of hardware descriptor blocks
+ * @desc_num: Number of hardware descriptors
+ * @completed_desc_num: Completed hardware descriptors
+ * @cyclic: Cyclic transfer vs. scatter-gather
+ * @interleaved_dma: Interleaved DMA transfer
+ * @periods: Number of periods in the cyclic transfer
+ * @period_size: Size of a period in bytes in cyclic transfers
+ * @frames_left: Number of frames left in interleaved DMA transfer
+ * @error: tx error flag
+ */
+struct xdma_desc {
+	struct virt_dma_desc		vdesc;
+	struct xdma_chan		*chan;
+	enum dma_transfer_direction	dir;
+	struct xdma_desc_block		*desc_blocks;
+	u32				dblk_num;
+	u32				desc_num;
+	u32				completed_desc_num;
+	bool				cyclic;
+	bool				interleaved_dma;
+	u32				periods;
+	u32				period_size;
+	u32				frames_left;
+	bool				error;
+};
+
+#define XDMA_DEV_STATUS_REG_DMA		BIT(0)
+#define XDMA_DEV_STATUS_INIT_MSIX	BIT(1)
+
+/**
+ * struct xdma_device - DMA device structure
+ * @pdev: Platform device pointer
+ * @dma_dev: DMA device structure
+ * @rmap: MMIO regmap for DMA registers
+ * @h2c_chans: Host to Card channels
+ * @c2h_chans: Card to Host channels
+ * @h2c_chan_num: Number of H2C channels
+ * @c2h_chan_num: Number of C2H channels
+ * @irq_start: Start IRQ assigned to device
+ * @irq_num: Number of IRQ assigned to device
+ * @status: Initialization status
+ */
+struct xdma_device {
+	struct platform_device	*pdev;
+	struct dma_device	dma_dev;
+	struct regmap		*rmap;
+	struct xdma_chan	*h2c_chans;
+	struct xdma_chan	*c2h_chans;
+	u32			h2c_chan_num;
+	u32			c2h_chan_num;
+	u32			irq_start;
+	u32			irq_num;
+	u32			status;
+};
+
+#define xdma_err(xdev, fmt, args...)					\
+	dev_err(&(xdev)->pdev->dev, fmt, ##args)
+#define XDMA_CHAN_NUM(_xd) ({						\
+	typeof(_xd) (xd) = (_xd);					\
+	((xd)->h2c_chan_num + (xd)->c2h_chan_num); })
+
+/* Get the last desc in a desc block */
+static inline void *xdma_blk_last_desc(struct xdma_desc_block *block)
+{
+	return block->virt_addr + (XDMA_DESC_ADJACENT - 1) * XDMA_DESC_SIZE;
+}
+
+/**
+ * xdma_link_sg_desc_blocks - Link SG descriptor blocks for DMA transfer
+ * @sw_desc: Tx descriptor pointer
+ */
+static void xdma_link_sg_desc_blocks(struct xdma_desc *sw_desc)
+{
+	struct xdma_desc_block *block;
+	u32 last_blk_desc, desc_control;
+	struct xdma_hw_desc *desc;
+	int i;
+
+	desc_control = XDMA_DESC_CONTROL(XDMA_DESC_ADJACENT, 0);
+	for (i = 1; i < sw_desc->dblk_num; i++) {
+		block = &sw_desc->desc_blocks[i - 1];
+		desc = xdma_blk_last_desc(block);
+
+		if (!(i & XDMA_DESC_BLOCK_MASK)) {
+			desc->control = cpu_to_le32(XDMA_DESC_CONTROL_LAST);
+			continue;
+		}
+		desc->control = cpu_to_le32(desc_control);
+		desc->next_desc = cpu_to_le64(block[1].dma_addr);
+	}
+
+	/* update the last block */
+	last_blk_desc = (sw_desc->desc_num - 1) & XDMA_DESC_ADJACENT_MASK;
+	if (((sw_desc->dblk_num - 1) & XDMA_DESC_BLOCK_MASK) > 0) {
+		block = &sw_desc->desc_blocks[sw_desc->dblk_num - 2];
+		desc = xdma_blk_last_desc(block);
+		desc_control = XDMA_DESC_CONTROL(last_blk_desc + 1, 0);
+		desc->control = cpu_to_le32(desc_control);
+	}
+
+	block = &sw_desc->desc_blocks[sw_desc->dblk_num - 1];
+	desc = block->virt_addr + last_blk_desc * XDMA_DESC_SIZE;
+	desc->control = cpu_to_le32(XDMA_DESC_CONTROL_LAST);
+}
+
+/**
+ * xdma_link_cyclic_desc_blocks - Link cyclic descriptor blocks for DMA transfer
+ * @sw_desc: Tx descriptor pointer
+ */
+static void xdma_link_cyclic_desc_blocks(struct xdma_desc *sw_desc)
+{
+	struct xdma_desc_block *block;
+	struct xdma_hw_desc *desc;
+	int i;
+
+	block = sw_desc->desc_blocks;
+	for (i = 0; i < sw_desc->desc_num - 1; i++) {
+		desc = block->virt_addr + i * XDMA_DESC_SIZE;
+		desc->next_desc = cpu_to_le64(block->dma_addr + ((i + 1) * XDMA_DESC_SIZE));
+	}
+	desc = block->virt_addr + i * XDMA_DESC_SIZE;
+	desc->next_desc = cpu_to_le64(block->dma_addr);
+}
+
+static inline struct xdma_chan *to_xdma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct xdma_chan, vchan.chan);
+}
+
+static inline struct xdma_desc *to_xdma_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct xdma_desc, vdesc);
+}
+
+/**
+ * xdma_channel_init - Initialize DMA channel registers
+ * @chan: DMA channel pointer
+ */
+static int xdma_channel_init(struct xdma_chan *chan)
+{
+	struct xdma_device *xdev = chan->xdev_hdl;
+	int ret;
+
+	ret = regmap_write(xdev->rmap, chan->base + XDMA_CHAN_CONTROL_W1C,
+			   CHAN_CTRL_NON_INCR_ADDR);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(xdev->rmap, chan->base + XDMA_CHAN_INTR_ENABLE,
+			   CHAN_IM_ALL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * xdma_free_desc - Free descriptor
+ * @vdesc: Virtual DMA descriptor
+ */
+static void xdma_free_desc(struct virt_dma_desc *vdesc)
+{
+	struct xdma_desc *sw_desc;
+	int i;
+
+	sw_desc = to_xdma_desc(vdesc);
+	for (i = 0; i < sw_desc->dblk_num; i++) {
+		if (!sw_desc->desc_blocks[i].virt_addr)
+			break;
+		dma_pool_free(sw_desc->chan->desc_pool,
+			      sw_desc->desc_blocks[i].virt_addr,
+			      sw_desc->desc_blocks[i].dma_addr);
+	}
+	kfree(sw_desc->desc_blocks);
+	kfree(sw_desc);
+}
+
+/**
+ * xdma_alloc_desc - Allocate descriptor
+ * @chan: DMA channel pointer
+ * @desc_num: Number of hardware descriptors
+ * @cyclic: Whether this is a cyclic transfer
+ */
+static struct xdma_desc *
+xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num, bool cyclic)
+{
+	struct xdma_desc *sw_desc;
+	struct xdma_hw_desc *desc;
+	dma_addr_t dma_addr;
+	u32 dblk_num;
+	u32 control;
+	void *addr;
+	int i, j;
+
+	sw_desc = kzalloc_obj(*sw_desc, GFP_NOWAIT);
+	if (!sw_desc)
+		return NULL;
+
+	sw_desc->chan = chan;
+	sw_desc->desc_num = desc_num;
+	sw_desc->cyclic = cyclic;
+	sw_desc->error = false;
+	dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT);
+	sw_desc->desc_blocks = kzalloc_objs(*sw_desc->desc_blocks, dblk_num,
+					    GFP_NOWAIT);
+	if (!sw_desc->desc_blocks)
+		goto failed;
+
+	if (cyclic)
+		control = XDMA_DESC_CONTROL_CYCLIC;
+	else
+		control = XDMA_DESC_CONTROL(1, 0);
+
+	sw_desc->dblk_num = dblk_num;
+	for (i = 0; i < sw_desc->dblk_num; i++) {
+		addr = dma_pool_alloc(chan->desc_pool, GFP_NOWAIT, &dma_addr);
+		if (!addr)
+			goto failed;
+
+		sw_desc->desc_blocks[i].virt_addr = addr;
+		sw_desc->desc_blocks[i].dma_addr = dma_addr;
+		for (j = 0, desc = addr; j < XDMA_DESC_ADJACENT; j++)
+			desc[j].control = cpu_to_le32(control);
+	}
+
+	if (cyclic)
+		xdma_link_cyclic_desc_blocks(sw_desc);
+	else
+		xdma_link_sg_desc_blocks(sw_desc);
+
+	return sw_desc;
+
+failed:
+	xdma_free_desc(&sw_desc->vdesc);
+	return NULL;
+}
+
+/**
+ * xdma_xfer_start - Start DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_start(struct xdma_chan *xchan)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&xchan->vchan);
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	struct xdma_desc_block *block;
+	u32 val, completed_blocks;
+	struct xdma_desc *desc;
+	int ret;
+
+	/*
+	 * check if there is not any submitted descriptor or channel is busy.
+	 * vchan lock should be held where this function is called.
+	 */
+	if (!vd || xchan->busy)
+		return -EINVAL;
+
+	/* clear run stop bit to get ready for transfer */
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			   CHAN_CTRL_RUN_STOP);
+	if (ret)
+		return ret;
+
+	desc = to_xdma_desc(vd);
+	if (desc->dir != xchan->dir) {
+		xdma_err(xdev, "incorrect request direction");
+		return -EINVAL;
+	}
+
+	/* set DMA engine to the first descriptor block */
+	completed_blocks = desc->completed_desc_num / XDMA_DESC_ADJACENT;
+	block = &desc->desc_blocks[completed_blocks];
+	val = lower_32_bits(block->dma_addr);
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_LO, val);
+	if (ret)
+		return ret;
+
+	val = upper_32_bits(block->dma_addr);
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_HI, val);
+	if (ret)
+		return ret;
+
+	if (completed_blocks + 1 == desc->dblk_num)
+		val = (desc->desc_num - 1) & XDMA_DESC_ADJACENT_MASK;
+	else
+		val = XDMA_DESC_ADJACENT - 1;
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_SGDMA_DESC_ADJ, val);
+	if (ret)
+		return ret;
+
+	/* kick off DMA transfer */
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL,
+			   CHAN_CTRL_START);
+	if (ret)
+		return ret;
+
+	xchan->busy = true;
+	xchan->stop_requested = false;
+	reinit_completion(&xchan->last_interrupt);
+
+	return 0;
+}
+
+/**
+ * xdma_xfer_stop - Stop DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_stop(struct xdma_chan *xchan)
+{
+	struct xdma_device *xdev = xchan->xdev_hdl;
+
+	/* clear run stop bit to prevent any further auto-triggering */
+	return regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			    CHAN_CTRL_RUN_STOP);
+}
+
+/**
+ * xdma_alloc_channels - Detect and allocate DMA channels
+ * @xdev: DMA device pointer
+ * @dir: Channel direction
+ */
+static int xdma_alloc_channels(struct xdma_device *xdev,
+			       enum dma_transfer_direction dir)
+{
+	struct xdma_platdata *pdata = dev_get_platdata(&xdev->pdev->dev);
+	struct xdma_chan **chans, *xchan;
+	u32 base, identifier, target;
+	u32 *chan_num;
+	int i, j, ret;
+
+	if (dir == DMA_MEM_TO_DEV) {
+		base = XDMA_CHAN_H2C_OFFSET;
+		target = XDMA_CHAN_H2C_TARGET;
+		chans = &xdev->h2c_chans;
+		chan_num = &xdev->h2c_chan_num;
+	} else if (dir == DMA_DEV_TO_MEM) {
+		base = XDMA_CHAN_C2H_OFFSET;
+		target = XDMA_CHAN_C2H_TARGET;
+		chans = &xdev->c2h_chans;
+		chan_num = &xdev->c2h_chan_num;
+	} else {
+		xdma_err(xdev, "invalid direction specified");
+		return -EINVAL;
+	}
+
+	/* detect number of available DMA channels */
+	for (i = 0, *chan_num = 0; i < pdata->max_dma_channels; i++) {
+		ret = regmap_read(xdev->rmap, base + i * XDMA_CHAN_STRIDE,
+				  &identifier);
+		if (ret)
+			return ret;
+
+		/* check if it is available DMA channel */
+		if (XDMA_CHAN_CHECK_TARGET(identifier, target))
+			(*chan_num)++;
+	}
+
+	if (!*chan_num) {
+		xdma_err(xdev, "does not probe any channel");
+		return -EINVAL;
+	}
+
+	*chans = devm_kcalloc(&xdev->pdev->dev, *chan_num, sizeof(**chans),
+			      GFP_KERNEL);
+	if (!*chans)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < pdata->max_dma_channels; i++) {
+		ret = regmap_read(xdev->rmap, base + i * XDMA_CHAN_STRIDE,
+				  &identifier);
+		if (ret)
+			return ret;
+
+		if (!XDMA_CHAN_CHECK_TARGET(identifier, target))
+			continue;
+
+		if (j == *chan_num) {
+			xdma_err(xdev, "invalid channel number");
+			return -EIO;
+		}
+
+		/* init channel structure and hardware */
+		xchan = &(*chans)[j];
+		xchan->xdev_hdl = xdev;
+		xchan->base = base + i * XDMA_CHAN_STRIDE;
+		xchan->dir = dir;
+		xchan->stop_requested = false;
+		init_completion(&xchan->last_interrupt);
+
+		ret = xdma_channel_init(xchan);
+		if (ret)
+			return ret;
+		xchan->vchan.desc_free = xdma_free_desc;
+		vchan_init(&xchan->vchan, &xdev->dma_dev);
+
+		j++;
+	}
+
+	dev_info(&xdev->pdev->dev, "configured %d %s channels", j,
+		 (dir == DMA_MEM_TO_DEV) ? "H2C" : "C2H");
+
+	return 0;
+}
+
+/**
+ * xdma_issue_pending - Issue pending transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_issue_pending(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+	if (vchan_issue_pending(&xdma_chan->vchan))
+		xdma_xfer_start(xdma_chan);
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+}
+
+/**
+ * xdma_terminate_all - Terminate all transactions
+ * @chan: DMA channel pointer
+ */
+static int xdma_terminate_all(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	xdma_xfer_stop(xdma_chan);
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+	xdma_chan->busy = false;
+	xdma_chan->stop_requested = true;
+	vd = vchan_next_desc(&xdma_chan->vchan);
+	if (vd) {
+		list_del(&vd->node);
+		dma_cookie_complete(&vd->tx);
+		vchan_terminate_vdesc(vd);
+	}
+	vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+	list_splice_tail(&head, &xdma_chan->vchan.desc_terminated);
+
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+
+	return 0;
+}
+
+/**
+ * xdma_synchronize - Synchronize terminated transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_synchronize(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_device *xdev = xdma_chan->xdev_hdl;
+	int st = 0;
+
+	/* If the engine continues running, wait for the last interrupt */
+	regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st);
+	if (st & XDMA_CHAN_STATUS_BUSY)
+		wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000));
+
+	vchan_synchronize(&xdma_chan->vchan);
+}
+
+/**
+ * xdma_fill_descs() - Fill hardware descriptors for one contiguous memory chunk.
+ *		       More than one descriptor will be used if the size is bigger
+ *		       than XDMA_DESC_BLEN_MAX.
+ * @sw_desc: Descriptor container
+ * @src_addr: First value for the ->src_addr field
+ * @dst_addr: First value for the ->dst_addr field
+ * @size: Size of the contiguous memory block
+ * @filled_descs_num: Index of the first descriptor to take care of in @sw_desc
+ */
+static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
+				  u64 dst_addr, u32 size, u32 filled_descs_num)
+{
+	u32 left = size, len, desc_num = filled_descs_num;
+	struct xdma_desc_block *dblk;
+	struct xdma_hw_desc *desc;
+
+	dblk = sw_desc->desc_blocks + (desc_num / XDMA_DESC_ADJACENT);
+	desc = dblk->virt_addr;
+	desc += desc_num & XDMA_DESC_ADJACENT_MASK;
+	do {
+		len = min_t(u32, left, XDMA_DESC_BLEN_MAX);
+		/* set hardware descriptor */
+		desc->bytes = cpu_to_le32(len);
+		desc->src_addr = cpu_to_le64(src_addr);
+		desc->dst_addr = cpu_to_le64(dst_addr);
+		if (!(++desc_num & XDMA_DESC_ADJACENT_MASK))
+			desc = (++dblk)->virt_addr;
+		else
+			desc++;
+
+		src_addr += len;
+		dst_addr += len;
+		left -= len;
+	} while (left);
+
+	return desc_num - filled_descs_num;
+}
+
+/**
+ * xdma_prep_device_sg - prepare a descriptor for a DMA transaction
+ * @chan: DMA channel pointer
+ * @sgl: Transfer scatter gather list
+ * @sg_len: Length of scatter gather list
+ * @dir: Transfer direction
+ * @flags: transfer ack flags
+ * @context: APP words of the descriptor
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		    unsigned int sg_len, enum dma_transfer_direction dir,
+		    unsigned long flags, void *context)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_desc *sw_desc;
+	u64 addr, dev_addr, *src, *dst;
+	u32 desc_num, i;
+	struct scatterlist *sg;
+
+	desc_num = sg_nents_for_dma(sgl, sg_len, XDMA_DESC_BLEN_MAX);
+	sw_desc = xdma_alloc_desc(xdma_chan, desc_num, false);
+	if (!sw_desc)
+		return NULL;
+	sw_desc->dir = dir;
+	sw_desc->cyclic = false;
+	sw_desc->interleaved_dma = false;
+
+	if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = xdma_chan->cfg.dst_addr;
+		src = &addr;
+		dst = &dev_addr;
+	} else {
+		dev_addr = xdma_chan->cfg.src_addr;
+		src = &dev_addr;
+		dst = &addr;
+	}
+
+	desc_num = 0;
+	for_each_sg(sgl, sg, sg_len, i) {
+		addr = sg_dma_address(sg);
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, sg_dma_len(sg), desc_num);
+		dev_addr += sg_dma_len(sg);
+	}
+
+	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
+	if (!tx_desc)
+		goto failed;
+
+	return tx_desc;
+
+failed:
+	xdma_free_desc(&sw_desc->vdesc);
+
+	return NULL;
+}
+
+/**
+ * xdma_prep_dma_cyclic - prepare for cyclic DMA transactions
+ * @chan: DMA channel pointer
+ * @address: Device DMA address to access
+ * @size: Total length to transfer
+ * @period_size: Period size to use for each transfer
+ * @dir: Transfer direction
+ * @flags: Transfer ack flags
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
+		     size_t size, size_t period_size,
+		     enum dma_transfer_direction dir,
+		     unsigned long flags)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_device *xdev = xdma_chan->xdev_hdl;
+	unsigned int periods = size / period_size;
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_desc *sw_desc;
+	u64 addr, dev_addr, *src, *dst;
+	u32 desc_num;
+	unsigned int i;
+
+	/*
+	 * Simplify the whole logic by preventing an abnormally high number of
+	 * periods and periods size.
+	 */
+	if (period_size > XDMA_DESC_BLEN_MAX) {
+		xdma_err(xdev, "period size limited to %lu bytes\n", XDMA_DESC_BLEN_MAX);
+		return NULL;
+	}
+
+	if (periods > XDMA_DESC_ADJACENT) {
+		xdma_err(xdev, "number of periods limited to %u\n", XDMA_DESC_ADJACENT);
+		return NULL;
+	}
+
+	sw_desc = xdma_alloc_desc(xdma_chan, periods, true);
+	if (!sw_desc)
+		return NULL;
+
+	sw_desc->periods = periods;
+	sw_desc->period_size = period_size;
+	sw_desc->dir = dir;
+	sw_desc->interleaved_dma = false;
+
+	addr = address;
+	if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = xdma_chan->cfg.dst_addr;
+		src = &addr;
+		dst = &dev_addr;
+	} else {
+		dev_addr = xdma_chan->cfg.src_addr;
+		src = &dev_addr;
+		dst = &addr;
+	}
+
+	desc_num = 0;
+	for (i = 0; i < periods; i++) {
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
+		addr += period_size;
+	}
+
+	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
+	if (!tx_desc)
+		goto failed;
+
+	return tx_desc;
+
+failed:
+	xdma_free_desc(&sw_desc->vdesc);
+
+	return NULL;
+}
+
+/**
+ * xdma_prep_interleaved_dma - Prepare virtual descriptor for interleaved DMA transfers
+ * @chan: DMA channel
+ * @xt: DMA transfer template
+ * @flags: tx flags
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_interleaved_dma(struct dma_chan *chan,
+			  struct dma_interleaved_template *xt,
+			  unsigned long flags)
+{
+	int i;
+	u32 desc_num = 0, period_size = 0;
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_chan *xchan = to_xdma_chan(chan);
+	struct xdma_desc *sw_desc;
+	u64 src_addr, dst_addr;
+
+	for (i = 0; i < xt->frame_size; ++i)
+		desc_num += DIV_ROUND_UP(xt->sgl[i].size, XDMA_DESC_BLEN_MAX);
+
+	sw_desc = xdma_alloc_desc(xchan, desc_num, false);
+	if (!sw_desc)
+		return NULL;
+	sw_desc->dir = xt->dir;
+	sw_desc->interleaved_dma = true;
+	sw_desc->cyclic = flags & DMA_PREP_REPEAT;
+	sw_desc->frames_left = xt->numf;
+	sw_desc->periods = xt->numf;
+
+	desc_num = 0;
+	src_addr = xt->src_start;
+	dst_addr = xt->dst_start;
+	for (i = 0; i < xt->frame_size; ++i) {
+		desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
+		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + (xt->src_inc ?
+							      xt->sgl[i].size : 0);
+		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + (xt->dst_inc ?
+							      xt->sgl[i].size : 0);
+		period_size += xt->sgl[i].size;
+	}
+	sw_desc->period_size = period_size;
+
+	tx_desc = vchan_tx_prep(&xchan->vchan, &sw_desc->vdesc, flags);
+	if (tx_desc)
+		return tx_desc;
+
+	xdma_free_desc(&sw_desc->vdesc);
+	return NULL;
+}
+
+/**
+ * xdma_device_config - Configure the DMA channel
+ * @chan: DMA channel
+ * @cfg: channel configuration
+ */
+static int xdma_device_config(struct dma_chan *chan,
+			      struct dma_slave_config *cfg)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+
+	memcpy(&xdma_chan->cfg, cfg, sizeof(*cfg));
+
+	return 0;
+}
+
+/**
+ * xdma_free_chan_resources - Free channel resources
+ * @chan: DMA channel
+ */
+static void xdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+
+	vchan_free_chan_resources(&xdma_chan->vchan);
+	dma_pool_destroy(xdma_chan->desc_pool);
+	xdma_chan->desc_pool = NULL;
+}
+
+/**
+ * xdma_alloc_chan_resources - Allocate channel resources
+ * @chan: DMA channel
+ */
+static int xdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_device *xdev = xdma_chan->xdev_hdl;
+	struct device *dev = xdev->dma_dev.dev;
+
+	while (dev && !dev_is_pci(dev))
+		dev = dev->parent;
+	if (!dev) {
+		xdma_err(xdev, "unable to find pci device");
+		return -EINVAL;
+	}
+
+	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), dev, XDMA_DESC_BLOCK_SIZE,
+					       XDMA_DESC_BLOCK_ALIGN, XDMA_DESC_BLOCK_BOUNDARY);
+	if (!xdma_chan->desc_pool) {
+		xdma_err(xdev, "unable to allocate descriptor pool");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static enum dma_status xdma_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+				      struct dma_tx_state *state)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_desc *desc = NULL;
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+	unsigned int period_idx;
+	u32 residue = 0;
+
+	ret = dma_cookie_status(chan, cookie, state);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+	vd = vchan_find_desc(&xdma_chan->vchan, cookie);
+	if (!vd)
+		goto out;
+
+	desc = to_xdma_desc(vd);
+	if (desc->error) {
+		ret = DMA_ERROR;
+	} else if (desc->cyclic) {
+		period_idx = desc->completed_desc_num % desc->periods;
+		residue = (desc->periods - period_idx) * desc->period_size;
+		dma_set_residue(state, residue);
+	}
+out:
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+
+	return ret;
+}
+
+/**
+ * xdma_channel_isr - XDMA channel interrupt handler
+ * @irq: IRQ number
+ * @dev_id: Pointer to the DMA channel structure
+ */
+static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
+{
+	struct xdma_chan *xchan = dev_id;
+	u32 complete_desc_num = 0;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	struct virt_dma_desc *vd, *next_vd;
+	struct xdma_desc *desc;
+	int ret;
+	u32 st;
+	bool repeat_tx;
+
+	spin_lock(&xchan->vchan.lock);
+
+	if (xchan->stop_requested)
+		complete(&xchan->last_interrupt);
+
+	/* get submitted request */
+	vd = vchan_next_desc(&xchan->vchan);
+	if (!vd)
+		goto out;
+
+	/* Clear-on-read the status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
+	if (ret)
+		goto out;
+
+	desc = to_xdma_desc(vd);
+
+	st &= XDMA_CHAN_STATUS_MASK;
+	if ((st & XDMA_CHAN_ERROR_MASK) ||
+	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+		desc->error = true;
+		xdma_err(xdev, "channel error, status register value: 0x%x", st);
+		goto out;
+	}
+
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC,
+			  &complete_desc_num);
+	if (ret)
+		goto out;
+
+	if (desc->interleaved_dma) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+		if (complete_desc_num == XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) {
+			xdma_xfer_start(xchan);
+			goto out;
+		}
+
+		/* last desc of any frame */
+		desc->frames_left--;
+		if (desc->frames_left)
+			goto out;
+
+		/* last desc of the last frame  */
+		repeat_tx = vd->tx.flags & DMA_PREP_REPEAT;
+		next_vd = list_first_entry_or_null(&vd->node, struct virt_dma_desc, node);
+		if (next_vd)
+			repeat_tx = repeat_tx && !(next_vd->tx.flags & DMA_PREP_LOAD_EOT);
+		if (repeat_tx) {
+			desc->frames_left = desc->periods;
+			desc->completed_desc_num = 0;
+			vchan_cyclic_callback(vd);
+		} else {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+		}
+		/* start (or continue) the tx of a first desc on the vc.desc_issued list, if any */
+		xdma_xfer_start(xchan);
+	} else if (!desc->cyclic) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+
+		/* if all data blocks are transferred, remove and complete the request */
+		if (desc->completed_desc_num == desc->desc_num) {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+			goto out;
+		}
+
+		if (desc->completed_desc_num > desc->desc_num ||
+		    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
+			goto out;
+
+		/* transfer the rest of data */
+		xdma_xfer_start(xchan);
+	} else {
+		desc->completed_desc_num = complete_desc_num;
+		vchan_cyclic_callback(vd);
+	}
+
+out:
+	spin_unlock(&xchan->vchan.lock);
+	return IRQ_HANDLED;
+}
+
+/**
+ * xdma_irq_fini - Uninitialize IRQ
+ * @xdev: DMA device pointer
+ */
+static void xdma_irq_fini(struct xdma_device *xdev)
+{
+	int i;
+
+	/* disable interrupt */
+	regmap_write(xdev->rmap, XDMA_IRQ_CHAN_INT_EN_W1C, ~0);
+
+	/* free irq handler */
+	for (i = 0; i < xdev->h2c_chan_num; i++)
+		free_irq(xdev->h2c_chans[i].irq, &xdev->h2c_chans[i]);
+
+	for (i = 0; i < xdev->c2h_chan_num; i++)
+		free_irq(xdev->c2h_chans[i].irq, &xdev->c2h_chans[i]);
+}
+
+/**
+ * xdma_set_vector_reg - configure hardware IRQ registers
+ * @xdev: DMA device pointer
+ * @vec_tbl_start: Start of IRQ registers
+ * @irq_start: Start of IRQ
+ * @irq_num: Number of IRQ
+ */
+static int xdma_set_vector_reg(struct xdma_device *xdev, u32 vec_tbl_start,
+			       u32 irq_start, u32 irq_num)
+{
+	u32 shift, i, val = 0;
+	int ret;
+
+	/* Each IRQ register is 32 bit and contains 4 IRQs */
+	while (irq_num > 0) {
+		for (i = 0; i < 4; i++) {
+			shift = XDMA_IRQ_VEC_SHIFT * i;
+			val |= irq_start << shift;
+			irq_start++;
+			irq_num--;
+			if (!irq_num)
+				break;
+		}
+
+		/* write IRQ register */
+		ret = regmap_write(xdev->rmap, vec_tbl_start, val);
+		if (ret)
+			return ret;
+		vec_tbl_start += sizeof(u32);
+		val = 0;
+	}
+
+	return 0;
+}
+
+/**
+ * xdma_irq_init - initialize IRQs
+ * @xdev: DMA device pointer
+ */
+static int xdma_irq_init(struct xdma_device *xdev)
+{
+	u32 irq = xdev->irq_start;
+	u32 user_irq_start;
+	int i, j, ret;
+
+	/* return failure if there are not enough IRQs */
+	if (xdev->irq_num < XDMA_CHAN_NUM(xdev)) {
+		xdma_err(xdev, "not enough irq");
+		return -EINVAL;
+	}
+
+	/* setup H2C interrupt handler */
+	for (i = 0; i < xdev->h2c_chan_num; i++) {
+		ret = request_irq(irq, xdma_channel_isr, 0,
+				  "xdma-h2c-channel", &xdev->h2c_chans[i]);
+		if (ret) {
+			xdma_err(xdev, "H2C channel%d request irq%d failed: %d",
+				 i, irq, ret);
+			goto failed_init_h2c;
+		}
+		xdev->h2c_chans[i].irq = irq;
+		irq++;
+	}
+
+	/* setup C2H interrupt handler */
+	for (j = 0; j < xdev->c2h_chan_num; j++) {
+		ret = request_irq(irq, xdma_channel_isr, 0,
+				  "xdma-c2h-channel", &xdev->c2h_chans[j]);
+		if (ret) {
+			xdma_err(xdev, "C2H channel%d request irq%d failed: %d",
+				 j, irq, ret);
+			goto failed_init_c2h;
+		}
+		xdev->c2h_chans[j].irq = irq;
+		irq++;
+	}
+
+	/* config hardware IRQ registers */
+	ret = xdma_set_vector_reg(xdev, XDMA_IRQ_CHAN_VEC_NUM, 0,
+				  XDMA_CHAN_NUM(xdev));
+	if (ret) {
+		xdma_err(xdev, "failed to set channel vectors: %d", ret);
+		goto failed_init_c2h;
+	}
+
+	/* config user IRQ registers if needed */
+	user_irq_start = XDMA_CHAN_NUM(xdev);
+	if (xdev->irq_num > user_irq_start) {
+		ret = xdma_set_vector_reg(xdev, XDMA_IRQ_USER_VEC_NUM,
+					  user_irq_start,
+					  xdev->irq_num - user_irq_start);
+		if (ret) {
+			xdma_err(xdev, "failed to set user vectors: %d", ret);
+			goto failed_init_c2h;
+		}
+	}
+
+	/* enable interrupt */
+	ret = regmap_write(xdev->rmap, XDMA_IRQ_CHAN_INT_EN_W1S, ~0);
+	if (ret)
+		goto failed_init_c2h;
+
+	return 0;
+
+failed_init_c2h:
+	while (j--)
+		free_irq(xdev->c2h_chans[j].irq, &xdev->c2h_chans[j]);
+failed_init_h2c:
+	while (i--)
+		free_irq(xdev->h2c_chans[i].irq, &xdev->h2c_chans[i]);
+
+	return ret;
+}
+
+static bool xdma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_chan_info *chan_info = param;
+
+	return chan_info->dir == xdma_chan->dir;
+}
+
+/**
+ * xdma_disable_user_irq - Disable user interrupt
+ * @pdev: Pointer to the platform_device structure
+ * @irq_num: System IRQ number
+ */
+void xdma_disable_user_irq(struct platform_device *pdev, u32 irq_num)
+{
+	struct xdma_device *xdev = platform_get_drvdata(pdev);
+	u32 index;
+
+	index = irq_num - xdev->irq_start;
+	if (index < XDMA_CHAN_NUM(xdev) || index >= xdev->irq_num) {
+		xdma_err(xdev, "invalid user irq number");
+		return;
+	}
+	index -= XDMA_CHAN_NUM(xdev);
+
+	regmap_write(xdev->rmap, XDMA_IRQ_USER_INT_EN_W1C, 1 << index);
+}
+EXPORT_SYMBOL(xdma_disable_user_irq);
+
+/**
+ * xdma_enable_user_irq - Enable user logic interrupt
+ * @pdev: Pointer to the platform_device structure
+ * @irq_num: System IRQ number
+ */
+int xdma_enable_user_irq(struct platform_device *pdev, u32 irq_num)
+{
+	struct xdma_device *xdev = platform_get_drvdata(pdev);
+	u32 index;
+	int ret;
+
+	index = irq_num - xdev->irq_start;
+	if (index < XDMA_CHAN_NUM(xdev) || index >= xdev->irq_num) {
+		xdma_err(xdev, "invalid user irq number");
+		return -EINVAL;
+	}
+	index -= XDMA_CHAN_NUM(xdev);
+
+	ret = regmap_write(xdev->rmap, XDMA_IRQ_USER_INT_EN_W1S, 1 << index);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(xdma_enable_user_irq);
+
+/**
+ * xdma_get_user_irq - Get system IRQ number
+ * @pdev: Pointer to the platform_device structure
+ * @user_irq_index: User logic IRQ wire index
+ *
+ * Return: The system IRQ number allocated for the given wire index.
+ */
+int xdma_get_user_irq(struct platform_device *pdev, u32 user_irq_index)
+{
+	struct xdma_device *xdev = platform_get_drvdata(pdev);
+
+	if (XDMA_CHAN_NUM(xdev) + user_irq_index >= xdev->irq_num) {
+		xdma_err(xdev, "invalid user irq index");
+		return -EINVAL;
+	}
+
+	return xdev->irq_start + XDMA_CHAN_NUM(xdev) + user_irq_index;
+}
+EXPORT_SYMBOL(xdma_get_user_irq);
+
+/**
+ * xdma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void xdma_remove(struct platform_device *pdev)
+{
+	struct xdma_device *xdev = platform_get_drvdata(pdev);
+
+	if (xdev->status & XDMA_DEV_STATUS_INIT_MSIX)
+		xdma_irq_fini(xdev);
+
+	if (xdev->status & XDMA_DEV_STATUS_REG_DMA)
+		dma_async_device_unregister(&xdev->dma_dev);
+}
+
+/**
+ * xdma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ */
+static int xdma_probe(struct platform_device *pdev)
+{
+	struct xdma_platdata *pdata = dev_get_platdata(&pdev->dev);
+	struct xdma_device *xdev;
+	void __iomem *reg_base;
+	struct resource *res;
+	int ret = -ENODEV;
+
+	if (pdata->max_dma_channels > XDMA_MAX_CHANNELS) {
+		dev_err(&pdev->dev, "invalid max dma channels %d",
+			pdata->max_dma_channels);
+		return -EINVAL;
+	}
+
+	xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL);
+	if (!xdev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, xdev);
+	xdev->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		xdma_err(xdev, "failed to get irq resource");
+		goto failed;
+	}
+	xdev->irq_start = res->start;
+	xdev->irq_num = resource_size(res);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		xdma_err(xdev, "failed to get io resource");
+		goto failed;
+	}
+
+	reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(reg_base)) {
+		xdma_err(xdev, "ioremap failed");
+		goto failed;
+	}
+
+	xdev->rmap = devm_regmap_init_mmio(&pdev->dev, reg_base,
+					   &xdma_regmap_config);
+	if (IS_ERR(xdev->rmap)) {
+		xdma_err(xdev, "config regmap failed: %pe", xdev->rmap);
+		goto failed;
+	}
+	INIT_LIST_HEAD(&xdev->dma_dev.channels);
+
+	ret = xdma_alloc_channels(xdev, DMA_MEM_TO_DEV);
+	if (ret) {
+		xdma_err(xdev, "config H2C channels failed: %d", ret);
+		goto failed;
+	}
+
+	ret = xdma_alloc_channels(xdev, DMA_DEV_TO_MEM);
+	if (ret) {
+		xdma_err(xdev, "config C2H channels failed: %d", ret);
+		goto failed;
+	}
+
+	dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_REPEAT, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_LOAD_EOT, xdev->dma_dev.cap_mask);
+
+	xdev->dma_dev.dev = &pdev->dev;
+	xdev->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	xdev->dma_dev.device_free_chan_resources = xdma_free_chan_resources;
+	xdev->dma_dev.device_alloc_chan_resources = xdma_alloc_chan_resources;
+	xdev->dma_dev.device_tx_status = xdma_tx_status;
+	xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg;
+	xdev->dma_dev.device_config = xdma_device_config;
+	xdev->dma_dev.device_issue_pending = xdma_issue_pending;
+	xdev->dma_dev.device_terminate_all = xdma_terminate_all;
+	xdev->dma_dev.device_synchronize = xdma_synchronize;
+	xdev->dma_dev.filter.map = pdata->device_map;
+	xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
+	xdev->dma_dev.filter.fn = xdma_filter_fn;
+	xdev->dma_dev.device_prep_dma_cyclic = xdma_prep_dma_cyclic;
+	xdev->dma_dev.device_prep_interleaved_dma = xdma_prep_interleaved_dma;
+
+	ret = dma_async_device_register(&xdev->dma_dev);
+	if (ret) {
+		xdma_err(xdev, "failed to register Xilinx XDMA: %d", ret);
+		goto failed;
+	}
+	xdev->status |= XDMA_DEV_STATUS_REG_DMA;
+
+	ret = xdma_irq_init(xdev);
+	if (ret) {
+		xdma_err(xdev, "failed to init msix: %d", ret);
+		goto failed;
+	}
+	xdev->status |= XDMA_DEV_STATUS_INIT_MSIX;
+
+	return 0;
+
+failed:
+	xdma_remove(pdev);
+
+	return ret;
+}
+
+static const struct platform_device_id xdma_id_table[] = {
+	{ "xdma", 0},
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, xdma_id_table);
+
+static struct platform_driver xdma_driver = {
+	.driver		= {
+		.name = "xdma",
+	},
+	.id_table	= xdma_id_table,
+	.probe		= xdma_probe,
+	.remove		= xdma_remove,
+};
+
+module_platform_driver(xdma_driver);
+
+MODULE_DESCRIPTION("AMD XDMA driver");
+MODULE_AUTHOR("XRT Team <runtimeca39d@amd.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
new file mode 100644
index 000000000..404235c17
--- /dev/null
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -0,0 +1,3418 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DMA driver for Xilinx Video DMA Engine
+ *
+ * Copyright (C) 2010-2014 Xilinx, Inc. All rights reserved.
+ *
+ * Based on the Freescale DMA driver.
+ *
+ * Description:
+ * The AXI Video Direct Memory Access (AXI VDMA) core is a soft Xilinx IP
+ * core that provides high-bandwidth direct memory access between memory
+ * and AXI4-Stream type video target peripherals. The core provides efficient
+ * two dimensional DMA operations with independent asynchronous read (S2MM)
+ * and write (MM2S) channel operation. It can be configured to have either
+ * one channel or two channels. If configured as two channels, one is to
+ * transmit to the video device (MM2S) and another is to receive from the
+ * video device (S2MM). Initialization, status, interrupt and management
+ * registers are accessed through an AXI4-Lite slave interface.
+ *
+ * The AXI Direct Memory Access (AXI DMA) core is a soft Xilinx IP core that
+ * provides high-bandwidth one dimensional direct memory access between memory
+ * and AXI4-Stream target peripherals. It supports one receive and one
+ * transmit channel, both of them optional at synthesis time.
+ *
+ * The AXI CDMA, is a soft IP, which provides high-bandwidth Direct Memory
+ * Access (DMA) between a memory-mapped source address and a memory-mapped
+ * destination address.
+ *
+ * The AXI Multichannel Direct Memory Access (AXI MCDMA) core is a soft
+ * Xilinx IP that provides high-bandwidth direct memory access between
+ * memory and AXI4-Stream target peripherals. It provides scatter gather
+ * (SG) interface with multiple channels independent configuration support.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/dmapool.h>
+#include <linux/dma/xilinx_dma.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string_choices.h>
+#include <linux/clk.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include "../dmaengine.h"
+
+/* Register/Descriptor Offsets */
+#define XILINX_DMA_MM2S_CTRL_OFFSET		0x0000
+#define XILINX_DMA_S2MM_CTRL_OFFSET		0x0030
+#define XILINX_VDMA_MM2S_DESC_OFFSET		0x0050
+#define XILINX_VDMA_S2MM_DESC_OFFSET		0x00a0
+
+/* Control Registers */
+#define XILINX_DMA_REG_DMACR			0x0000
+#define XILINX_DMA_DMACR_DELAY_MAX		0xff
+#define XILINX_DMA_DMACR_DELAY_SHIFT		24
+#define XILINX_DMA_DMACR_FRAME_COUNT_MAX	0xff
+#define XILINX_DMA_DMACR_FRAME_COUNT_SHIFT	16
+#define XILINX_DMA_DMACR_ERR_IRQ		BIT(14)
+#define XILINX_DMA_DMACR_DLY_CNT_IRQ		BIT(13)
+#define XILINX_DMA_DMACR_FRM_CNT_IRQ		BIT(12)
+#define XILINX_DMA_DMACR_MASTER_SHIFT		8
+#define XILINX_DMA_DMACR_FSYNCSRC_SHIFT	5
+#define XILINX_DMA_DMACR_FRAMECNT_EN		BIT(4)
+#define XILINX_DMA_DMACR_GENLOCK_EN		BIT(3)
+#define XILINX_DMA_DMACR_RESET			BIT(2)
+#define XILINX_DMA_DMACR_CIRC_EN		BIT(1)
+#define XILINX_DMA_DMACR_RUNSTOP		BIT(0)
+#define XILINX_DMA_DMACR_FSYNCSRC_MASK		GENMASK(6, 5)
+#define XILINX_DMA_DMACR_DELAY_MASK		GENMASK(31, 24)
+#define XILINX_DMA_DMACR_FRAME_COUNT_MASK	GENMASK(23, 16)
+#define XILINX_DMA_DMACR_MASTER_MASK		GENMASK(11, 8)
+
+#define XILINX_DMA_REG_DMASR			0x0004
+#define XILINX_DMA_DMASR_EOL_LATE_ERR		BIT(15)
+#define XILINX_DMA_DMASR_ERR_IRQ		BIT(14)
+#define XILINX_DMA_DMASR_DLY_CNT_IRQ		BIT(13)
+#define XILINX_DMA_DMASR_FRM_CNT_IRQ		BIT(12)
+#define XILINX_DMA_DMASR_SOF_LATE_ERR		BIT(11)
+#define XILINX_DMA_DMASR_SG_DEC_ERR		BIT(10)
+#define XILINX_DMA_DMASR_SG_SLV_ERR		BIT(9)
+#define XILINX_DMA_DMASR_EOF_EARLY_ERR		BIT(8)
+#define XILINX_DMA_DMASR_SOF_EARLY_ERR		BIT(7)
+#define XILINX_DMA_DMASR_DMA_DEC_ERR		BIT(6)
+#define XILINX_DMA_DMASR_DMA_SLAVE_ERR		BIT(5)
+#define XILINX_DMA_DMASR_DMA_INT_ERR		BIT(4)
+#define XILINX_DMA_DMASR_SG_MASK		BIT(3)
+#define XILINX_DMA_DMASR_IDLE			BIT(1)
+#define XILINX_DMA_DMASR_HALTED		BIT(0)
+#define XILINX_DMA_DMASR_DELAY_MASK		GENMASK(31, 24)
+#define XILINX_DMA_DMASR_FRAME_COUNT_MASK	GENMASK(23, 16)
+
+#define XILINX_DMA_REG_CURDESC			0x0008
+#define XILINX_DMA_REG_TAILDESC		0x0010
+#define XILINX_DMA_REG_REG_INDEX		0x0014
+#define XILINX_DMA_REG_FRMSTORE		0x0018
+#define XILINX_DMA_REG_THRESHOLD		0x001c
+#define XILINX_DMA_REG_FRMPTR_STS		0x0024
+#define XILINX_DMA_REG_PARK_PTR		0x0028
+#define XILINX_DMA_PARK_PTR_WR_REF_SHIFT	8
+#define XILINX_DMA_PARK_PTR_WR_REF_MASK		GENMASK(12, 8)
+#define XILINX_DMA_PARK_PTR_RD_REF_SHIFT	0
+#define XILINX_DMA_PARK_PTR_RD_REF_MASK		GENMASK(4, 0)
+#define XILINX_DMA_REG_VDMA_VERSION		0x002c
+
+/* Register Direct Mode Registers */
+#define XILINX_DMA_REG_VSIZE			0x0000
+#define XILINX_DMA_VSIZE_MASK			GENMASK(12, 0)
+#define XILINX_DMA_REG_HSIZE			0x0004
+#define XILINX_DMA_HSIZE_MASK			GENMASK(15, 0)
+
+#define XILINX_DMA_REG_FRMDLY_STRIDE		0x0008
+#define XILINX_DMA_FRMDLY_STRIDE_FRMDLY_SHIFT	24
+#define XILINX_DMA_FRMDLY_STRIDE_STRIDE_SHIFT	0
+
+#define XILINX_VDMA_REG_START_ADDRESS(n)	(0x000c + 4 * (n))
+#define XILINX_VDMA_REG_START_ADDRESS_64(n)	(0x000c + 8 * (n))
+
+#define XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP	0x00ec
+#define XILINX_VDMA_ENABLE_VERTICAL_FLIP	BIT(0)
+
+/* HW specific definitions */
+#define XILINX_MCDMA_MAX_CHANS_PER_DEVICE	0x20
+#define XILINX_DMA_MAX_CHANS_PER_DEVICE		0x2
+#define XILINX_CDMA_MAX_CHANS_PER_DEVICE	0x1
+#define XILINX_DMA_DFAULT_ADDRWIDTH		0x20
+
+#define XILINX_DMA_DMAXR_ALL_IRQ_MASK	\
+		(XILINX_DMA_DMASR_FRM_CNT_IRQ | \
+		 XILINX_DMA_DMASR_DLY_CNT_IRQ | \
+		 XILINX_DMA_DMASR_ERR_IRQ)
+
+#define XILINX_DMA_DMASR_ALL_ERR_MASK	\
+		(XILINX_DMA_DMASR_EOL_LATE_ERR | \
+		 XILINX_DMA_DMASR_SOF_LATE_ERR | \
+		 XILINX_DMA_DMASR_SG_DEC_ERR | \
+		 XILINX_DMA_DMASR_SG_SLV_ERR | \
+		 XILINX_DMA_DMASR_EOF_EARLY_ERR | \
+		 XILINX_DMA_DMASR_SOF_EARLY_ERR | \
+		 XILINX_DMA_DMASR_DMA_DEC_ERR | \
+		 XILINX_DMA_DMASR_DMA_SLAVE_ERR | \
+		 XILINX_DMA_DMASR_DMA_INT_ERR)
+
+/*
+ * Recoverable errors are DMA Internal error, SOF Early, EOF Early
+ * and SOF Late. They are only recoverable when C_FLUSH_ON_FSYNC
+ * is enabled in the h/w system.
+ */
+#define XILINX_DMA_DMASR_ERR_RECOVER_MASK	\
+		(XILINX_DMA_DMASR_SOF_LATE_ERR | \
+		 XILINX_DMA_DMASR_EOF_EARLY_ERR | \
+		 XILINX_DMA_DMASR_SOF_EARLY_ERR | \
+		 XILINX_DMA_DMASR_DMA_INT_ERR)
+
+/* Axi VDMA Flush on Fsync bits */
+#define XILINX_DMA_FLUSH_S2MM		3
+#define XILINX_DMA_FLUSH_MM2S		2
+#define XILINX_DMA_FLUSH_BOTH		1
+
+/* Delay loop counter to prevent hardware failure */
+#define XILINX_DMA_LOOP_COUNT		1000000
+
+/* AXI DMA Specific Registers/Offsets */
+#define XILINX_DMA_REG_SRCDSTADDR	0x18
+#define XILINX_DMA_REG_BTT		0x28
+
+/* AXI DMA Specific Masks/Bit fields */
+#define XILINX_DMA_MAX_TRANS_LEN_MIN	8
+#define XILINX_DMA_MAX_TRANS_LEN_MAX	23
+#define XILINX_DMA_V2_MAX_TRANS_LEN_MAX	26
+#define XILINX_DMA_CR_COALESCE_MAX	GENMASK(23, 16)
+#define XILINX_DMA_CR_DELAY_MAX		GENMASK(31, 24)
+#define XILINX_DMA_CR_CYCLIC_BD_EN_MASK	BIT(4)
+#define XILINX_DMA_CR_COALESCE_SHIFT	16
+#define XILINX_DMA_CR_DELAY_SHIFT	24
+#define XILINX_DMA_BD_SOP		BIT(27)
+#define XILINX_DMA_BD_EOP		BIT(26)
+#define XILINX_DMA_BD_COMP_MASK		BIT(31)
+#define XILINX_DMA_COALESCE_MAX		255
+#define XILINX_DMA_NUM_DESCS		512
+#define XILINX_DMA_NUM_APP_WORDS	5
+
+/* AXI CDMA Specific Registers/Offsets */
+#define XILINX_CDMA_REG_SRCADDR		0x18
+#define XILINX_CDMA_REG_DSTADDR		0x20
+
+/* AXI CDMA Specific Masks */
+#define XILINX_CDMA_CR_SGMODE          BIT(3)
+
+#define xilinx_prep_dma_addr_t(addr)	\
+	((dma_addr_t)((u64)addr##_##msb << 32 | (addr)))
+
+/* AXI MCDMA Specific Registers/Offsets */
+#define XILINX_MCDMA_MM2S_CTRL_OFFSET		0x0000
+#define XILINX_MCDMA_S2MM_CTRL_OFFSET		0x0500
+#define XILINX_MCDMA_CHEN_OFFSET		0x0008
+#define XILINX_MCDMA_CH_ERR_OFFSET		0x0010
+#define XILINX_MCDMA_RXINT_SER_OFFSET		0x0020
+#define XILINX_MCDMA_TXINT_SER_OFFSET		0x0028
+#define XILINX_MCDMA_CHAN_CR_OFFSET(x)		(0x40 + (x) * 0x40)
+#define XILINX_MCDMA_CHAN_SR_OFFSET(x)		(0x44 + (x) * 0x40)
+#define XILINX_MCDMA_CHAN_CDESC_OFFSET(x)	(0x48 + (x) * 0x40)
+#define XILINX_MCDMA_CHAN_TDESC_OFFSET(x)	(0x50 + (x) * 0x40)
+
+/* AXI MCDMA Specific Masks/Shifts */
+#define XILINX_MCDMA_COALESCE_SHIFT		16
+#define XILINX_MCDMA_COALESCE_MAX		24
+#define XILINX_MCDMA_IRQ_ALL_MASK		GENMASK(7, 5)
+#define XILINX_MCDMA_COALESCE_MASK		GENMASK(23, 16)
+#define XILINX_MCDMA_CR_RUNSTOP_MASK		BIT(0)
+#define XILINX_MCDMA_IRQ_IOC_MASK		BIT(5)
+#define XILINX_MCDMA_IRQ_DELAY_MASK		BIT(6)
+#define XILINX_MCDMA_IRQ_ERR_MASK		BIT(7)
+#define XILINX_MCDMA_BD_EOP			BIT(30)
+#define XILINX_MCDMA_BD_SOP			BIT(31)
+
+/**
+ * struct xilinx_vdma_desc_hw - Hardware Descriptor
+ * @next_desc: Next Descriptor Pointer @0x00
+ * @pad1: Reserved @0x04
+ * @buf_addr: Buffer address @0x08
+ * @buf_addr_msb: MSB of Buffer address @0x0C
+ * @vsize: Vertical Size @0x10
+ * @hsize: Horizontal Size @0x14
+ * @stride: Number of bytes between the first
+ *	    pixels of each horizontal line @0x18
+ */
+struct xilinx_vdma_desc_hw {
+	u32 next_desc;
+	u32 pad1;
+	u32 buf_addr;
+	u32 buf_addr_msb;
+	u32 vsize;
+	u32 hsize;
+	u32 stride;
+} __aligned(64);
+
+/**
+ * struct xilinx_axidma_desc_hw - Hardware Descriptor for AXI DMA
+ * @next_desc: Next Descriptor Pointer @0x00
+ * @next_desc_msb: MSB of Next Descriptor Pointer @0x04
+ * @buf_addr: Buffer address @0x08
+ * @buf_addr_msb: MSB of Buffer address @0x0C
+ * @reserved1: Reserved @0x10
+ * @reserved2: Reserved @0x14
+ * @control: Control field @0x18
+ * @status: Status field @0x1C
+ * @app: APP Fields @0x20 - 0x30
+ */
+struct xilinx_axidma_desc_hw {
+	u32 next_desc;
+	u32 next_desc_msb;
+	u32 buf_addr;
+	u32 buf_addr_msb;
+	u32 reserved1;
+	u32 reserved2;
+	u32 control;
+	u32 status;
+	u32 app[XILINX_DMA_NUM_APP_WORDS];
+} __aligned(64);
+
+/**
+ * struct xilinx_aximcdma_desc_hw - Hardware Descriptor for AXI MCDMA
+ * @next_desc: Next Descriptor Pointer @0x00
+ * @next_desc_msb: MSB of Next Descriptor Pointer @0x04
+ * @buf_addr: Buffer address @0x08
+ * @buf_addr_msb: MSB of Buffer address @0x0C
+ * @rsvd: Reserved field @0x10
+ * @control: Control Information field @0x14
+ * @status: Status field @0x18
+ * @sideband_status: Status of sideband signals @0x1C
+ * @app: APP Fields @0x20 - 0x30
+ */
+struct xilinx_aximcdma_desc_hw {
+	u32 next_desc;
+	u32 next_desc_msb;
+	u32 buf_addr;
+	u32 buf_addr_msb;
+	u32 rsvd;
+	u32 control;
+	u32 status;
+	u32 sideband_status;
+	u32 app[XILINX_DMA_NUM_APP_WORDS];
+} __aligned(64);
+
+/**
+ * struct xilinx_cdma_desc_hw - Hardware Descriptor
+ * @next_desc: Next Descriptor Pointer @0x00
+ * @next_desc_msb: Next Descriptor Pointer MSB @0x04
+ * @src_addr: Source address @0x08
+ * @src_addr_msb: Source address MSB @0x0C
+ * @dest_addr: Destination address @0x10
+ * @dest_addr_msb: Destination address MSB @0x14
+ * @control: Control field @0x18
+ * @status: Status field @0x1C
+ */
+struct xilinx_cdma_desc_hw {
+	u32 next_desc;
+	u32 next_desc_msb;
+	u32 src_addr;
+	u32 src_addr_msb;
+	u32 dest_addr;
+	u32 dest_addr_msb;
+	u32 control;
+	u32 status;
+} __aligned(64);
+
+/**
+ * struct xilinx_vdma_tx_segment - Descriptor segment
+ * @hw: Hardware descriptor
+ * @node: Node in the descriptor segments list
+ * @phys: Physical address of segment
+ */
+struct xilinx_vdma_tx_segment {
+	struct xilinx_vdma_desc_hw hw;
+	struct list_head node;
+	dma_addr_t phys;
+} __aligned(64);
+
+/**
+ * struct xilinx_axidma_tx_segment - Descriptor segment
+ * @hw: Hardware descriptor
+ * @node: Node in the descriptor segments list
+ * @phys: Physical address of segment
+ */
+struct xilinx_axidma_tx_segment {
+	struct xilinx_axidma_desc_hw hw;
+	struct list_head node;
+	dma_addr_t phys;
+} __aligned(64);
+
+/**
+ * struct xilinx_aximcdma_tx_segment - Descriptor segment
+ * @hw: Hardware descriptor
+ * @node: Node in the descriptor segments list
+ * @phys: Physical address of segment
+ */
+struct xilinx_aximcdma_tx_segment {
+	struct xilinx_aximcdma_desc_hw hw;
+	struct list_head node;
+	dma_addr_t phys;
+} __aligned(64);
+
+/**
+ * struct xilinx_cdma_tx_segment - Descriptor segment
+ * @hw: Hardware descriptor
+ * @node: Node in the descriptor segments list
+ * @phys: Physical address of segment
+ */
+struct xilinx_cdma_tx_segment {
+	struct xilinx_cdma_desc_hw hw;
+	struct list_head node;
+	dma_addr_t phys;
+} __aligned(64);
+
+/**
+ * struct xilinx_dma_tx_descriptor - Per Transaction structure
+ * @async_tx: Async transaction descriptor
+ * @segments: TX segments list
+ * @node: Node in the channel descriptors list
+ * @cyclic: Check for cyclic transfers.
+ * @err: Whether the descriptor has an error.
+ * @residue: Residue of the completed descriptor
+ */
+struct xilinx_dma_tx_descriptor {
+	struct dma_async_tx_descriptor async_tx;
+	struct list_head segments;
+	struct list_head node;
+	bool cyclic;
+	bool err;
+	u32 residue;
+};
+
+/**
+ * struct xilinx_dma_chan - Driver specific DMA channel structure
+ * @xdev: Driver specific device structure
+ * @ctrl_offset: Control registers offset
+ * @desc_offset: TX descriptor registers offset
+ * @lock: Descriptor operation lock
+ * @pending_list: Descriptors waiting
+ * @active_list: Descriptors ready to submit
+ * @done_list: Complete descriptors
+ * @free_seg_list: Free descriptors
+ * @common: DMA common channel
+ * @desc_pool: Descriptors pool
+ * @dev: The dma device
+ * @irq: Channel IRQ
+ * @id: Channel ID
+ * @direction: Transfer direction
+ * @num_frms: Number of frames
+ * @has_sg: Support scatter transfers
+ * @cyclic: Check for cyclic transfers.
+ * @genlock: Support genlock mode
+ * @err: Channel has errors
+ * @idle: Check for channel idle
+ * @terminating: Check for channel being synchronized by user
+ * @tasklet: Cleanup work after irq
+ * @config: Device configuration info
+ * @flush_on_fsync: Flush on Frame sync
+ * @desc_pendingcount: Descriptor pending count
+ * @ext_addr: Indicates 64 bit addressing is supported by dma channel
+ * @desc_submitcount: Descriptor h/w submitted count
+ * @seg_v: Statically allocated segments base
+ * @seg_mv: Statically allocated segments base for MCDMA
+ * @seg_p: Physical allocated segments base
+ * @cyclic_seg_v: Statically allocated segment base for cyclic transfers
+ * @cyclic_seg_p: Physical allocated segments base for cyclic dma
+ * @start_transfer: Differentiate b/w DMA IP's transfer
+ * @stop_transfer: Differentiate b/w DMA IP's quiesce
+ * @tdest: TDEST value for mcdma
+ * @has_vflip: S2MM vertical flip
+ * @irq_delay: Interrupt delay timeout
+ */
+struct xilinx_dma_chan {
+	struct xilinx_dma_device *xdev;
+	u32 ctrl_offset;
+	u32 desc_offset;
+	spinlock_t lock;
+	struct list_head pending_list;
+	struct list_head active_list;
+	struct list_head done_list;
+	struct list_head free_seg_list;
+	struct dma_chan common;
+	struct dma_pool *desc_pool;
+	struct device *dev;
+	int irq;
+	int id;
+	enum dma_transfer_direction direction;
+	int num_frms;
+	bool has_sg;
+	bool cyclic;
+	bool genlock;
+	bool err;
+	bool idle;
+	bool terminating;
+	struct tasklet_struct tasklet;
+	struct xilinx_vdma_config config;
+	bool flush_on_fsync;
+	u32 desc_pendingcount;
+	bool ext_addr;
+	u32 desc_submitcount;
+	struct xilinx_axidma_tx_segment *seg_v;
+	struct xilinx_aximcdma_tx_segment *seg_mv;
+	dma_addr_t seg_p;
+	struct xilinx_axidma_tx_segment *cyclic_seg_v;
+	dma_addr_t cyclic_seg_p;
+	void (*start_transfer)(struct xilinx_dma_chan *chan);
+	int (*stop_transfer)(struct xilinx_dma_chan *chan);
+	u16 tdest;
+	bool has_vflip;
+	u8 irq_delay;
+};
+
+/**
+ * enum xdma_ip_type - DMA IP type.
+ *
+ * @XDMA_TYPE_AXIDMA: Axi dma ip.
+ * @XDMA_TYPE_CDMA: Axi cdma ip.
+ * @XDMA_TYPE_VDMA: Axi vdma ip.
+ * @XDMA_TYPE_AXIMCDMA: Axi MCDMA ip.
+ *
+ */
+enum xdma_ip_type {
+	XDMA_TYPE_AXIDMA = 0,
+	XDMA_TYPE_CDMA,
+	XDMA_TYPE_VDMA,
+	XDMA_TYPE_AXIMCDMA
+};
+
+struct xilinx_dma_config {
+	enum xdma_ip_type dmatype;
+	int (*clk_init)(struct platform_device *pdev, struct clk **axi_clk,
+			struct clk **tx_clk, struct clk **txs_clk,
+			struct clk **rx_clk, struct clk **rxs_clk);
+	irqreturn_t (*irq_handler)(int irq, void *data);
+	const int max_channels;
+};
+
+/**
+ * struct xilinx_dma_device - DMA device structure
+ * @regs: I/O mapped base address
+ * @dev: Device Structure
+ * @common: DMA device structure
+ * @chan: Driver specific DMA channel
+ * @flush_on_fsync: Flush on frame sync
+ * @ext_addr: Indicates 64 bit addressing is supported by dma device
+ * @pdev: Platform device structure pointer
+ * @dma_config: DMA config structure
+ * @axi_clk: DMA Axi4-lite interace clock
+ * @tx_clk: DMA mm2s clock
+ * @txs_clk: DMA mm2s stream clock
+ * @rx_clk: DMA s2mm clock
+ * @rxs_clk: DMA s2mm stream clock
+ * @s2mm_chan_id: DMA s2mm channel identifier
+ * @mm2s_chan_id: DMA mm2s channel identifier
+ * @max_buffer_len: Max buffer length
+ * @has_axistream_connected: AXI DMA connected to AXI Stream IP
+ */
+struct xilinx_dma_device {
+	void __iomem *regs;
+	struct device *dev;
+	struct dma_device common;
+	struct xilinx_dma_chan *chan[XILINX_MCDMA_MAX_CHANS_PER_DEVICE];
+	u32 flush_on_fsync;
+	bool ext_addr;
+	struct platform_device  *pdev;
+	const struct xilinx_dma_config *dma_config;
+	struct clk *axi_clk;
+	struct clk *tx_clk;
+	struct clk *txs_clk;
+	struct clk *rx_clk;
+	struct clk *rxs_clk;
+	u32 s2mm_chan_id;
+	u32 mm2s_chan_id;
+	u32 max_buffer_len;
+	bool has_axistream_connected;
+};
+
+/* Macros */
+#define to_xilinx_chan(chan) \
+	container_of(chan, struct xilinx_dma_chan, common)
+#define to_dma_tx_descriptor(tx) \
+	container_of(tx, struct xilinx_dma_tx_descriptor, async_tx)
+#define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \
+	readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \
+				  val, cond, delay_us, timeout_us)
+
+/* IO accessors */
+static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg)
+{
+	return ioread32(chan->xdev->regs + reg);
+}
+
+static inline void dma_write(struct xilinx_dma_chan *chan, u32 reg, u32 value)
+{
+	iowrite32(value, chan->xdev->regs + reg);
+}
+
+static inline void vdma_desc_write(struct xilinx_dma_chan *chan, u32 reg,
+				   u32 value)
+{
+	dma_write(chan, chan->desc_offset + reg, value);
+}
+
+static inline u32 dma_ctrl_read(struct xilinx_dma_chan *chan, u32 reg)
+{
+	return dma_read(chan, chan->ctrl_offset + reg);
+}
+
+static inline void dma_ctrl_write(struct xilinx_dma_chan *chan, u32 reg,
+				   u32 value)
+{
+	dma_write(chan, chan->ctrl_offset + reg, value);
+}
+
+static inline void dma_ctrl_clr(struct xilinx_dma_chan *chan, u32 reg,
+				 u32 clr)
+{
+	dma_ctrl_write(chan, reg, dma_ctrl_read(chan, reg) & ~clr);
+}
+
+static inline void dma_ctrl_set(struct xilinx_dma_chan *chan, u32 reg,
+				 u32 set)
+{
+	dma_ctrl_write(chan, reg, dma_ctrl_read(chan, reg) | set);
+}
+
+/**
+ * vdma_desc_write_64 - 64-bit descriptor write
+ * @chan: Driver specific VDMA channel
+ * @reg: Register to write
+ * @value_lsb: lower address of the descriptor.
+ * @value_msb: upper address of the descriptor.
+ *
+ * Since vdma driver is trying to write to a register offset which is not a
+ * multiple of 64 bits(ex : 0x5c), we are writing as two separate 32 bits
+ * instead of a single 64 bit register write.
+ */
+static inline void vdma_desc_write_64(struct xilinx_dma_chan *chan, u32 reg,
+				      u32 value_lsb, u32 value_msb)
+{
+	/* Write the lsb 32 bits*/
+	writel(value_lsb, chan->xdev->regs + chan->desc_offset + reg);
+
+	/* Write the msb 32 bits */
+	writel(value_msb, chan->xdev->regs + chan->desc_offset + reg + 4);
+}
+
+static inline void dma_writeq(struct xilinx_dma_chan *chan, u32 reg, u64 value)
+{
+	lo_hi_writeq(value, chan->xdev->regs + chan->ctrl_offset + reg);
+}
+
+static inline void xilinx_write(struct xilinx_dma_chan *chan, u32 reg,
+				dma_addr_t addr)
+{
+	if (chan->ext_addr)
+		dma_writeq(chan, reg, addr);
+	else
+		dma_ctrl_write(chan, reg, addr);
+}
+
+static inline void xilinx_axidma_buf(struct xilinx_dma_chan *chan,
+				     struct xilinx_axidma_desc_hw *hw,
+				     dma_addr_t buf_addr, size_t sg_used,
+				     size_t period_len)
+{
+	if (chan->ext_addr) {
+		hw->buf_addr = lower_32_bits(buf_addr + sg_used + period_len);
+		hw->buf_addr_msb = upper_32_bits(buf_addr + sg_used +
+						 period_len);
+	} else {
+		hw->buf_addr = buf_addr + sg_used + period_len;
+	}
+}
+
+static inline void xilinx_aximcdma_buf(struct xilinx_dma_chan *chan,
+				       struct xilinx_aximcdma_desc_hw *hw,
+				       dma_addr_t buf_addr, size_t sg_used)
+{
+	if (chan->ext_addr) {
+		hw->buf_addr = lower_32_bits(buf_addr + sg_used);
+		hw->buf_addr_msb = upper_32_bits(buf_addr + sg_used);
+	} else {
+		hw->buf_addr = buf_addr + sg_used;
+	}
+}
+
+/**
+ * xilinx_dma_get_metadata_ptr- Populate metadata pointer and payload length
+ * @tx: async transaction descriptor
+ * @payload_len: metadata payload length
+ * @max_len: metadata max length
+ * Return: The app field pointer.
+ */
+static void *xilinx_dma_get_metadata_ptr(struct dma_async_tx_descriptor *tx,
+					 size_t *payload_len, size_t *max_len)
+{
+	struct xilinx_dma_tx_descriptor *desc = to_dma_tx_descriptor(tx);
+	struct xilinx_axidma_tx_segment *seg;
+
+	*max_len = *payload_len = sizeof(u32) * XILINX_DMA_NUM_APP_WORDS;
+	seg = list_first_entry(&desc->segments,
+			       struct xilinx_axidma_tx_segment, node);
+	return seg->hw.app;
+}
+
+static struct dma_descriptor_metadata_ops xilinx_dma_metadata_ops = {
+	.get_ptr = xilinx_dma_get_metadata_ptr,
+};
+
+/* -----------------------------------------------------------------------------
+ * Descriptors and segments alloc and free
+ */
+
+/**
+ * xilinx_vdma_alloc_tx_segment - Allocate transaction segment
+ * @chan: Driver specific DMA channel
+ *
+ * Return: The allocated segment on success and NULL on failure.
+ */
+static struct xilinx_vdma_tx_segment *
+xilinx_vdma_alloc_tx_segment(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_vdma_tx_segment *segment;
+	dma_addr_t phys;
+
+	segment = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &phys);
+	if (!segment)
+		return NULL;
+
+	segment->phys = phys;
+
+	return segment;
+}
+
+/**
+ * xilinx_cdma_alloc_tx_segment - Allocate transaction segment
+ * @chan: Driver specific DMA channel
+ *
+ * Return: The allocated segment on success and NULL on failure.
+ */
+static struct xilinx_cdma_tx_segment *
+xilinx_cdma_alloc_tx_segment(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_cdma_tx_segment *segment;
+	dma_addr_t phys;
+
+	segment = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &phys);
+	if (!segment)
+		return NULL;
+
+	segment->phys = phys;
+
+	return segment;
+}
+
+/**
+ * xilinx_axidma_alloc_tx_segment - Allocate transaction segment
+ * @chan: Driver specific DMA channel
+ *
+ * Return: The allocated segment on success and NULL on failure.
+ */
+static struct xilinx_axidma_tx_segment *
+xilinx_axidma_alloc_tx_segment(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_axidma_tx_segment *segment = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (!list_empty(&chan->free_seg_list)) {
+		segment = list_first_entry(&chan->free_seg_list,
+					   struct xilinx_axidma_tx_segment,
+					   node);
+		list_del(&segment->node);
+	}
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	if (!segment)
+		dev_dbg(chan->dev, "Could not find free tx segment\n");
+
+	return segment;
+}
+
+/**
+ * xilinx_aximcdma_alloc_tx_segment - Allocate transaction segment
+ * @chan: Driver specific DMA channel
+ *
+ * Return: The allocated segment on success and NULL on failure.
+ */
+static struct xilinx_aximcdma_tx_segment *
+xilinx_aximcdma_alloc_tx_segment(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_aximcdma_tx_segment *segment = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (!list_empty(&chan->free_seg_list)) {
+		segment = list_first_entry(&chan->free_seg_list,
+					   struct xilinx_aximcdma_tx_segment,
+					   node);
+		list_del(&segment->node);
+	}
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return segment;
+}
+
+static void xilinx_dma_clean_hw_desc(struct xilinx_axidma_desc_hw *hw)
+{
+	u32 next_desc = hw->next_desc;
+	u32 next_desc_msb = hw->next_desc_msb;
+
+	memset(hw, 0, sizeof(struct xilinx_axidma_desc_hw));
+
+	hw->next_desc = next_desc;
+	hw->next_desc_msb = next_desc_msb;
+}
+
+static void xilinx_mcdma_clean_hw_desc(struct xilinx_aximcdma_desc_hw *hw)
+{
+	u32 next_desc = hw->next_desc;
+	u32 next_desc_msb = hw->next_desc_msb;
+
+	memset(hw, 0, sizeof(struct xilinx_aximcdma_desc_hw));
+
+	hw->next_desc = next_desc;
+	hw->next_desc_msb = next_desc_msb;
+}
+
+/**
+ * xilinx_dma_free_tx_segment - Free transaction segment
+ * @chan: Driver specific DMA channel
+ * @segment: DMA transaction segment
+ */
+static void xilinx_dma_free_tx_segment(struct xilinx_dma_chan *chan,
+				struct xilinx_axidma_tx_segment *segment)
+{
+	xilinx_dma_clean_hw_desc(&segment->hw);
+
+	list_add_tail(&segment->node, &chan->free_seg_list);
+}
+
+/**
+ * xilinx_mcdma_free_tx_segment - Free transaction segment
+ * @chan: Driver specific DMA channel
+ * @segment: DMA transaction segment
+ */
+static void xilinx_mcdma_free_tx_segment(struct xilinx_dma_chan *chan,
+					 struct xilinx_aximcdma_tx_segment *
+					 segment)
+{
+	xilinx_mcdma_clean_hw_desc(&segment->hw);
+
+	list_add_tail(&segment->node, &chan->free_seg_list);
+}
+
+/**
+ * xilinx_cdma_free_tx_segment - Free transaction segment
+ * @chan: Driver specific DMA channel
+ * @segment: DMA transaction segment
+ */
+static void xilinx_cdma_free_tx_segment(struct xilinx_dma_chan *chan,
+				struct xilinx_cdma_tx_segment *segment)
+{
+	dma_pool_free(chan->desc_pool, segment, segment->phys);
+}
+
+/**
+ * xilinx_vdma_free_tx_segment - Free transaction segment
+ * @chan: Driver specific DMA channel
+ * @segment: DMA transaction segment
+ */
+static void xilinx_vdma_free_tx_segment(struct xilinx_dma_chan *chan,
+					struct xilinx_vdma_tx_segment *segment)
+{
+	dma_pool_free(chan->desc_pool, segment, segment->phys);
+}
+
+/**
+ * xilinx_dma_alloc_tx_descriptor - Allocate transaction descriptor
+ * @chan: Driver specific DMA channel
+ *
+ * Return: The allocated descriptor on success and NULL on failure.
+ */
+static struct xilinx_dma_tx_descriptor *
+xilinx_dma_alloc_tx_descriptor(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *desc;
+
+	desc = kzalloc_obj(*desc, GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	INIT_LIST_HEAD(&desc->segments);
+
+	return desc;
+}
+
+/**
+ * xilinx_dma_free_tx_descriptor - Free transaction descriptor
+ * @chan: Driver specific DMA channel
+ * @desc: DMA transaction descriptor
+ */
+static void
+xilinx_dma_free_tx_descriptor(struct xilinx_dma_chan *chan,
+			       struct xilinx_dma_tx_descriptor *desc)
+{
+	struct xilinx_vdma_tx_segment *segment, *next;
+	struct xilinx_cdma_tx_segment *cdma_segment, *cdma_next;
+	struct xilinx_axidma_tx_segment *axidma_segment, *axidma_next;
+	struct xilinx_aximcdma_tx_segment *aximcdma_segment, *aximcdma_next;
+
+	if (!desc)
+		return;
+
+	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+		list_for_each_entry_safe(segment, next, &desc->segments, node) {
+			list_del(&segment->node);
+			xilinx_vdma_free_tx_segment(chan, segment);
+		}
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+		list_for_each_entry_safe(cdma_segment, cdma_next,
+					 &desc->segments, node) {
+			list_del(&cdma_segment->node);
+			xilinx_cdma_free_tx_segment(chan, cdma_segment);
+		}
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		list_for_each_entry_safe(axidma_segment, axidma_next,
+					 &desc->segments, node) {
+			list_del(&axidma_segment->node);
+			xilinx_dma_free_tx_segment(chan, axidma_segment);
+		}
+	} else {
+		list_for_each_entry_safe(aximcdma_segment, aximcdma_next,
+					 &desc->segments, node) {
+			list_del(&aximcdma_segment->node);
+			xilinx_mcdma_free_tx_segment(chan, aximcdma_segment);
+		}
+	}
+
+	kfree(desc);
+}
+
+/* Required functions */
+
+/**
+ * xilinx_dma_free_desc_list - Free descriptors list
+ * @chan: Driver specific DMA channel
+ * @list: List to parse and delete the descriptor
+ */
+static void xilinx_dma_free_desc_list(struct xilinx_dma_chan *chan,
+					struct list_head *list)
+{
+	struct xilinx_dma_tx_descriptor *desc, *next;
+
+	list_for_each_entry_safe(desc, next, list, node) {
+		list_del(&desc->node);
+		xilinx_dma_free_tx_descriptor(chan, desc);
+	}
+}
+
+/**
+ * xilinx_dma_free_descriptors - Free channel descriptors
+ * @chan: Driver specific DMA channel
+ */
+static void xilinx_dma_free_descriptors(struct xilinx_dma_chan *chan)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	xilinx_dma_free_desc_list(chan, &chan->pending_list);
+	xilinx_dma_free_desc_list(chan, &chan->done_list);
+	xilinx_dma_free_desc_list(chan, &chan->active_list);
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_dma_free_chan_resources - Free channel resources
+ * @dchan: DMA channel
+ */
+static void xilinx_dma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
+
+	dev_dbg(chan->dev, "Free all channel resources.\n");
+
+	xilinx_dma_free_descriptors(chan);
+
+	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		spin_lock_irqsave(&chan->lock, flags);
+		INIT_LIST_HEAD(&chan->free_seg_list);
+		spin_unlock_irqrestore(&chan->lock, flags);
+
+		/* Free memory that is allocated for BD */
+		dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				  XILINX_DMA_NUM_DESCS, chan->seg_v,
+				  chan->seg_p);
+
+		/* Free Memory that is allocated for cyclic DMA Mode */
+		dma_free_coherent(chan->dev, sizeof(*chan->cyclic_seg_v),
+				  chan->cyclic_seg_v, chan->cyclic_seg_p);
+	}
+
+	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA) {
+		spin_lock_irqsave(&chan->lock, flags);
+		INIT_LIST_HEAD(&chan->free_seg_list);
+		spin_unlock_irqrestore(&chan->lock, flags);
+
+		/* Free memory that is allocated for BD */
+		dma_free_coherent(chan->dev, sizeof(*chan->seg_mv) *
+				  XILINX_DMA_NUM_DESCS, chan->seg_mv,
+				  chan->seg_p);
+	}
+
+	if (chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA &&
+	    chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIMCDMA) {
+		dma_pool_destroy(chan->desc_pool);
+		chan->desc_pool = NULL;
+	}
+
+}
+
+/**
+ * xilinx_dma_get_residue - Compute residue for a given descriptor
+ * @chan: Driver specific dma channel
+ * @desc: dma transaction descriptor
+ *
+ * Return: The number of residue bytes for the descriptor.
+ */
+static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan,
+				  struct xilinx_dma_tx_descriptor *desc)
+{
+	struct xilinx_cdma_tx_segment *cdma_seg;
+	struct xilinx_axidma_tx_segment *axidma_seg;
+	struct xilinx_aximcdma_tx_segment *aximcdma_seg;
+	struct xilinx_cdma_desc_hw *cdma_hw;
+	struct xilinx_axidma_desc_hw *axidma_hw;
+	struct xilinx_aximcdma_desc_hw *aximcdma_hw;
+	struct list_head *entry;
+	u32 residue = 0;
+
+	list_for_each(entry, &desc->segments) {
+		if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+			cdma_seg = list_entry(entry,
+					      struct xilinx_cdma_tx_segment,
+					      node);
+			cdma_hw = &cdma_seg->hw;
+			residue += (cdma_hw->control & chan->xdev->max_buffer_len) -
+			           (cdma_hw->status & chan->xdev->max_buffer_len);
+		} else if (chan->xdev->dma_config->dmatype ==
+			   XDMA_TYPE_AXIDMA) {
+			axidma_seg = list_entry(entry,
+						struct xilinx_axidma_tx_segment,
+						node);
+			axidma_hw = &axidma_seg->hw;
+			residue += (axidma_hw->control & chan->xdev->max_buffer_len) -
+			           (axidma_hw->status & chan->xdev->max_buffer_len);
+		} else {
+			aximcdma_seg =
+				list_entry(entry,
+					   struct xilinx_aximcdma_tx_segment,
+					   node);
+			aximcdma_hw = &aximcdma_seg->hw;
+			residue +=
+				(aximcdma_hw->control & chan->xdev->max_buffer_len) -
+				(aximcdma_hw->status & chan->xdev->max_buffer_len);
+		}
+	}
+
+	return residue;
+}
+
+static u32
+xilinx_dma_get_residue_axidma_direct_s2mm(struct xilinx_dma_chan *chan,
+					  struct xilinx_dma_tx_descriptor *desc)
+{
+	struct xilinx_axidma_tx_segment *seg;
+	struct xilinx_axidma_desc_hw *hw;
+	u32 finished_len;
+
+	finished_len = dma_ctrl_read(chan, XILINX_DMA_REG_BTT);
+
+	seg = list_first_entry(&desc->segments, struct xilinx_axidma_tx_segment,
+			       node);
+
+	hw = &seg->hw;
+
+	return hw->control - finished_len;
+}
+
+/**
+ * xilinx_dma_chan_handle_cyclic - Cyclic dma callback
+ * @chan: Driver specific dma channel
+ * @desc: dma transaction descriptor
+ * @flags: flags for spin lock
+ */
+static void xilinx_dma_chan_handle_cyclic(struct xilinx_dma_chan *chan,
+					  struct xilinx_dma_tx_descriptor *desc,
+					  unsigned long *flags)
+{
+	struct dmaengine_desc_callback cb;
+
+	dmaengine_desc_get_callback(&desc->async_tx, &cb);
+	if (dmaengine_desc_callback_valid(&cb)) {
+		spin_unlock_irqrestore(&chan->lock, *flags);
+		dmaengine_desc_callback_invoke(&cb, NULL);
+		spin_lock_irqsave(&chan->lock, *flags);
+	}
+}
+
+/**
+ * xilinx_dma_chan_desc_cleanup - Clean channel descriptors
+ * @chan: Driver specific DMA channel
+ */
+static void xilinx_dma_chan_desc_cleanup(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *desc, *next;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	list_for_each_entry_safe(desc, next, &chan->done_list, node) {
+		struct dmaengine_result result;
+
+		if (desc->cyclic) {
+			xilinx_dma_chan_handle_cyclic(chan, desc, &flags);
+			break;
+		}
+
+		/* Remove from the list of running transactions */
+		list_del(&desc->node);
+
+		if (unlikely(desc->err)) {
+			if (chan->direction == DMA_DEV_TO_MEM)
+				result.result = DMA_TRANS_READ_FAILED;
+			else
+				result.result = DMA_TRANS_WRITE_FAILED;
+		} else {
+			result.result = DMA_TRANS_NOERROR;
+		}
+
+		result.residue = desc->residue;
+
+		/* Run the link descriptor callback function */
+		spin_unlock_irqrestore(&chan->lock, flags);
+		dmaengine_desc_get_callback_invoke(&desc->async_tx, &result);
+		spin_lock_irqsave(&chan->lock, flags);
+
+		/* Run any dependencies, then free the descriptor */
+		dma_run_dependencies(&desc->async_tx);
+		xilinx_dma_free_tx_descriptor(chan, desc);
+
+		/*
+		 * While we ran a callback the user called a terminate function,
+		 * which takes care of cleaning up any remaining descriptors
+		 */
+		if (chan->terminating)
+			break;
+	}
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_dma_do_tasklet - Schedule completion tasklet
+ * @t: Pointer to the Xilinx DMA channel structure
+ */
+static void xilinx_dma_do_tasklet(struct tasklet_struct *t)
+{
+	struct xilinx_dma_chan *chan = from_tasklet(chan, t, tasklet);
+
+	xilinx_dma_chan_desc_cleanup(chan);
+}
+
+/**
+ * xilinx_dma_alloc_chan_resources - Allocate channel resources
+ * @dchan: DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	int i;
+
+	/* Has this channel already been allocated? */
+	if (chan->desc_pool)
+		return 0;
+
+	/*
+	 * We need the descriptor to be aligned to 64bytes
+	 * for meeting Xilinx VDMA specification requirement.
+	 */
+	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		/* Allocate the buffer descriptors. */
+		chan->seg_v = dma_alloc_coherent(chan->dev,
+						 sizeof(*chan->seg_v) * XILINX_DMA_NUM_DESCS,
+						 &chan->seg_p, GFP_KERNEL);
+		if (!chan->seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate channel %d descriptors\n",
+				chan->id);
+			return -ENOMEM;
+		}
+		/*
+		 * For cyclic DMA mode we need to program the tail Descriptor
+		 * register with a value which is not a part of the BD chain
+		 * so allocating a desc segment during channel allocation for
+		 * programming tail descriptor.
+		 */
+		chan->cyclic_seg_v = dma_alloc_coherent(chan->dev,
+							sizeof(*chan->cyclic_seg_v),
+							&chan->cyclic_seg_p,
+							GFP_KERNEL);
+		if (!chan->cyclic_seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate desc segment for cyclic DMA\n");
+			dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				XILINX_DMA_NUM_DESCS, chan->seg_v,
+				chan->seg_p);
+			return -ENOMEM;
+		}
+		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
+
+		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
+			chan->seg_v[i].hw.next_desc =
+			lower_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].hw.next_desc_msb =
+			upper_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].phys = chan->seg_p +
+				sizeof(*chan->seg_v) * i;
+			list_add_tail(&chan->seg_v[i].node,
+				      &chan->free_seg_list);
+		}
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA) {
+		/* Allocate the buffer descriptors. */
+		chan->seg_mv = dma_alloc_coherent(chan->dev,
+						  sizeof(*chan->seg_mv) *
+						  XILINX_DMA_NUM_DESCS,
+						  &chan->seg_p, GFP_KERNEL);
+		if (!chan->seg_mv) {
+			dev_err(chan->dev,
+				"unable to allocate channel %d descriptors\n",
+				chan->id);
+			return -ENOMEM;
+		}
+		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
+			chan->seg_mv[i].hw.next_desc =
+			lower_32_bits(chan->seg_p + sizeof(*chan->seg_mv) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_mv[i].hw.next_desc_msb =
+			upper_32_bits(chan->seg_p + sizeof(*chan->seg_mv) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_mv[i].phys = chan->seg_p +
+				sizeof(*chan->seg_mv) * i;
+			list_add_tail(&chan->seg_mv[i].node,
+				      &chan->free_seg_list);
+		}
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+		chan->desc_pool = dma_pool_create("xilinx_cdma_desc_pool",
+				   chan->dev,
+				   sizeof(struct xilinx_cdma_tx_segment),
+				   __alignof__(struct xilinx_cdma_tx_segment),
+				   0);
+	} else {
+		chan->desc_pool = dma_pool_create("xilinx_vdma_desc_pool",
+				     chan->dev,
+				     sizeof(struct xilinx_vdma_tx_segment),
+				     __alignof__(struct xilinx_vdma_tx_segment),
+				     0);
+	}
+
+	if (!chan->desc_pool &&
+	    ((chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA) &&
+		chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIMCDMA)) {
+		dev_err(chan->dev,
+			"unable to allocate channel %d descriptor pool\n",
+			chan->id);
+		return -ENOMEM;
+	}
+
+	dma_cookie_init(dchan);
+
+	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
+		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+	return 0;
+}
+
+/**
+ * xilinx_dma_calc_copysize - Calculate the amount of data to copy
+ * @chan: Driver specific DMA channel
+ * @size: Total data that needs to be copied
+ * @done: Amount of data that has been already copied
+ *
+ * Return: Amount of data that has to be copied
+ */
+static int xilinx_dma_calc_copysize(struct xilinx_dma_chan *chan,
+				    int size, int done)
+{
+	size_t copy;
+
+	copy = min_t(size_t, size - done,
+		     chan->xdev->max_buffer_len);
+
+	if ((copy + done < size) &&
+	    chan->xdev->common.copy_align) {
+		/*
+		 * If this is not the last descriptor, make sure
+		 * the next one will be properly aligned
+		 */
+		copy = rounddown(copy,
+				 (1 << chan->xdev->common.copy_align));
+	}
+	return copy;
+}
+
+/**
+ * xilinx_dma_tx_status - Get DMA transaction status
+ * @dchan: DMA channel
+ * @cookie: Transaction identifier
+ * @txstate: Transaction state
+ *
+ * Return: DMA transaction status
+ */
+static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *txstate)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	enum dma_status ret;
+	unsigned long flags;
+	u32 residue = 0;
+
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (!list_empty(&chan->active_list)) {
+		desc = list_last_entry(&chan->active_list,
+				       struct xilinx_dma_tx_descriptor, node);
+		/*
+		 * VDMA and simple mode do not support residue reporting, so the
+		 * residue field will always be 0.
+		 */
+		if (chan->has_sg && chan->xdev->dma_config->dmatype != XDMA_TYPE_VDMA)
+			residue = xilinx_dma_get_residue(chan, desc);
+	}
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	dma_set_residue(txstate, residue);
+
+	return ret;
+}
+
+/**
+ * xilinx_dma_stop_transfer - Halt DMA channel
+ * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
+{
+	u32 val;
+
+	dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR, XILINX_DMA_DMACR_RUNSTOP);
+
+	/* Wait for the hardware to halt */
+	return xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
+				       val & XILINX_DMA_DMASR_HALTED, 0,
+				       XILINX_DMA_LOOP_COUNT);
+}
+
+/**
+ * xilinx_cdma_stop_transfer - Wait for the current transfer to complete
+ * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_cdma_stop_transfer(struct xilinx_dma_chan *chan)
+{
+	u32 val;
+
+	return xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
+				       val & XILINX_DMA_DMASR_IDLE, 0,
+				       XILINX_DMA_LOOP_COUNT);
+}
+
+/**
+ * xilinx_dma_start - Start DMA channel
+ * @chan: Driver specific DMA channel
+ */
+static void xilinx_dma_start(struct xilinx_dma_chan *chan)
+{
+	int err;
+	u32 val;
+
+	dma_ctrl_set(chan, XILINX_DMA_REG_DMACR, XILINX_DMA_DMACR_RUNSTOP);
+
+	/* Wait for the hardware to start */
+	err = xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
+				      !(val & XILINX_DMA_DMASR_HALTED), 0,
+				      XILINX_DMA_LOOP_COUNT);
+
+	if (err) {
+		dev_err(chan->dev, "Cannot start channel %p: %x\n",
+			chan, dma_ctrl_read(chan, XILINX_DMA_REG_DMASR));
+
+		chan->err = true;
+	}
+}
+
+/**
+ * xilinx_vdma_start_transfer - Starts VDMA transfer
+ * @chan: Driver specific channel struct pointer
+ */
+static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_vdma_config *config = &chan->config;
+	struct xilinx_dma_tx_descriptor *desc;
+	u32 reg, j;
+	struct xilinx_vdma_tx_segment *segment, *last = NULL;
+	int i = 0;
+
+	/* This function was invoked with lock held */
+	if (chan->err)
+		return;
+
+	if (!chan->idle)
+		return;
+
+	if (list_empty(&chan->pending_list))
+		return;
+
+	desc = list_first_entry(&chan->pending_list,
+				struct xilinx_dma_tx_descriptor, node);
+
+	/* Configure the hardware using info in the config structure */
+	if (chan->has_vflip) {
+		reg = dma_read(chan, XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP);
+		reg &= ~XILINX_VDMA_ENABLE_VERTICAL_FLIP;
+		reg |= config->vflip_en;
+		dma_write(chan, XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP,
+			  reg);
+	}
+
+	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
+
+	if (config->frm_cnt_en)
+		reg |= XILINX_DMA_DMACR_FRAMECNT_EN;
+	else
+		reg &= ~XILINX_DMA_DMACR_FRAMECNT_EN;
+
+	/* If not parking, enable circular mode */
+	if (config->park)
+		reg &= ~XILINX_DMA_DMACR_CIRC_EN;
+	else
+		reg |= XILINX_DMA_DMACR_CIRC_EN;
+
+	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
+
+	if (config->park) {
+		j = chan->desc_submitcount;
+		reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR);
+		if (chan->direction == DMA_MEM_TO_DEV) {
+			reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK;
+			reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT;
+		} else {
+			reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK;
+			reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT;
+		}
+		dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg);
+	}
+
+	/* Start the hardware */
+	xilinx_dma_start(chan);
+
+	if (chan->err)
+		return;
+
+	/* Start the transfer */
+	if (chan->desc_submitcount < chan->num_frms)
+		i = chan->desc_submitcount;
+
+	list_for_each_entry(segment, &desc->segments, node) {
+		if (chan->ext_addr)
+			vdma_desc_write_64(chan,
+				   XILINX_VDMA_REG_START_ADDRESS_64(i++),
+				   segment->hw.buf_addr,
+				   segment->hw.buf_addr_msb);
+		else
+			vdma_desc_write(chan,
+					XILINX_VDMA_REG_START_ADDRESS(i++),
+					segment->hw.buf_addr);
+
+		last = segment;
+	}
+
+	if (!last)
+		return;
+
+	/* HW expects these parameters to be same for one transaction */
+	vdma_desc_write(chan, XILINX_DMA_REG_HSIZE, last->hw.hsize);
+	vdma_desc_write(chan, XILINX_DMA_REG_FRMDLY_STRIDE,
+			last->hw.stride);
+	vdma_desc_write(chan, XILINX_DMA_REG_VSIZE, last->hw.vsize);
+
+	chan->desc_submitcount++;
+	chan->desc_pendingcount--;
+	list_move_tail(&desc->node, &chan->active_list);
+	if (chan->desc_submitcount == chan->num_frms)
+		chan->desc_submitcount = 0;
+
+	chan->idle = false;
+}
+
+/**
+ * xilinx_cdma_start_transfer - Starts cdma transfer
+ * @chan: Driver specific channel struct pointer
+ */
+static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
+	struct xilinx_cdma_tx_segment *tail_segment;
+	u32 ctrl_reg = dma_read(chan, XILINX_DMA_REG_DMACR);
+
+	if (chan->err)
+		return;
+
+	if (!chan->idle)
+		return;
+
+	if (list_empty(&chan->pending_list))
+		return;
+
+	head_desc = list_first_entry(&chan->pending_list,
+				     struct xilinx_dma_tx_descriptor, node);
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_dma_tx_descriptor, node);
+	tail_segment = list_last_entry(&tail_desc->segments,
+				       struct xilinx_cdma_tx_segment, node);
+
+	if (chan->desc_pendingcount <= XILINX_DMA_COALESCE_MAX) {
+		ctrl_reg &= ~XILINX_DMA_CR_COALESCE_MAX;
+		ctrl_reg |= chan->desc_pendingcount <<
+				XILINX_DMA_CR_COALESCE_SHIFT;
+		dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, ctrl_reg);
+	}
+
+	if (chan->has_sg) {
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+		xilinx_write(chan, XILINX_DMA_REG_CURDESC,
+			     head_desc->async_tx.phys);
+
+		/* Update tail ptr register which will start the transfer */
+		xilinx_write(chan, XILINX_DMA_REG_TAILDESC,
+			     tail_segment->phys);
+	} else {
+		/* In simple mode */
+		struct xilinx_cdma_tx_segment *segment;
+		struct xilinx_cdma_desc_hw *hw;
+
+		segment = list_first_entry(&head_desc->segments,
+					   struct xilinx_cdma_tx_segment,
+					   node);
+
+		hw = &segment->hw;
+
+		xilinx_write(chan, XILINX_CDMA_REG_SRCADDR,
+			     xilinx_prep_dma_addr_t(hw->src_addr));
+		xilinx_write(chan, XILINX_CDMA_REG_DSTADDR,
+			     xilinx_prep_dma_addr_t(hw->dest_addr));
+
+		/* Start the transfer */
+		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
+				hw->control & chan->xdev->max_buffer_len);
+	}
+
+	list_splice_tail_init(&chan->pending_list, &chan->active_list);
+	chan->desc_pendingcount = 0;
+	chan->idle = false;
+}
+
+/**
+ * xilinx_dma_start_transfer - Starts DMA transfer
+ * @chan: Driver specific channel struct pointer
+ */
+static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
+	struct xilinx_axidma_tx_segment *tail_segment;
+	u32 reg;
+
+	if (chan->err)
+		return;
+
+	if (list_empty(&chan->pending_list)) {
+		if (chan->cyclic) {
+			struct xilinx_dma_tx_descriptor *desc;
+			struct list_head *entry;
+
+			desc = list_last_entry(&chan->done_list,
+					       struct xilinx_dma_tx_descriptor, node);
+			list_for_each(entry, &desc->segments) {
+				struct xilinx_axidma_tx_segment *axidma_seg;
+				struct xilinx_axidma_desc_hw *axidma_hw;
+				axidma_seg = list_entry(entry,
+							struct xilinx_axidma_tx_segment,
+							node);
+				axidma_hw = &axidma_seg->hw;
+				axidma_hw->status = 0;
+			}
+
+			list_splice_tail_init(&chan->done_list, &chan->active_list);
+			chan->desc_pendingcount = 0;
+			chan->idle = false;
+		}
+		return;
+	}
+
+	if (!chan->idle)
+		return;
+
+	head_desc = list_first_entry(&chan->pending_list,
+				     struct xilinx_dma_tx_descriptor, node);
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_dma_tx_descriptor, node);
+	tail_segment = list_last_entry(&tail_desc->segments,
+				       struct xilinx_axidma_tx_segment, node);
+
+	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
+
+	if (chan->desc_pendingcount <= XILINX_DMA_COALESCE_MAX) {
+		reg &= ~XILINX_DMA_CR_COALESCE_MAX;
+		reg |= chan->desc_pendingcount <<
+				  XILINX_DMA_CR_COALESCE_SHIFT;
+		dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
+	}
+
+	if (chan->has_sg)
+		xilinx_write(chan, XILINX_DMA_REG_CURDESC,
+			     head_desc->async_tx.phys);
+	reg  &= ~XILINX_DMA_CR_DELAY_MAX;
+	reg  |= chan->irq_delay << XILINX_DMA_CR_DELAY_SHIFT;
+	reg |= XILINX_DMA_DMAXR_ALL_IRQ_MASK;
+	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
+
+	xilinx_dma_start(chan);
+
+	if (chan->err)
+		return;
+
+	/* Start the transfer */
+	if (chan->has_sg) {
+		if (chan->cyclic)
+			xilinx_write(chan, XILINX_DMA_REG_TAILDESC,
+				     chan->cyclic_seg_v->phys);
+		else
+			xilinx_write(chan, XILINX_DMA_REG_TAILDESC,
+				     tail_segment->phys);
+	} else {
+		struct xilinx_axidma_tx_segment *segment;
+		struct xilinx_axidma_desc_hw *hw;
+
+		segment = list_first_entry(&head_desc->segments,
+					   struct xilinx_axidma_tx_segment,
+					   node);
+		hw = &segment->hw;
+
+		xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR,
+			     xilinx_prep_dma_addr_t(hw->buf_addr));
+
+		/* Start the transfer */
+		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
+			       hw->control & chan->xdev->max_buffer_len);
+	}
+
+	list_splice_tail_init(&chan->pending_list, &chan->active_list);
+	chan->desc_pendingcount = 0;
+	chan->idle = false;
+}
+
+/**
+ * xilinx_mcdma_start_transfer - Starts MCDMA transfer
+ * @chan: Driver specific channel struct pointer
+ */
+static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
+	struct xilinx_aximcdma_tx_segment *tail_segment;
+	u32 reg;
+
+	/*
+	 * lock has been held by calling functions, so we don't need it
+	 * to take it here again.
+	 */
+
+	if (chan->err)
+		return;
+
+	if (!chan->idle)
+		return;
+
+	if (list_empty(&chan->pending_list))
+		return;
+
+	head_desc = list_first_entry(&chan->pending_list,
+				     struct xilinx_dma_tx_descriptor, node);
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_dma_tx_descriptor, node);
+	tail_segment = list_last_entry(&tail_desc->segments,
+				       struct xilinx_aximcdma_tx_segment, node);
+
+	reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest));
+
+	if (chan->desc_pendingcount <= XILINX_MCDMA_COALESCE_MAX) {
+		reg &= ~XILINX_MCDMA_COALESCE_MASK;
+		reg |= chan->desc_pendingcount <<
+			XILINX_MCDMA_COALESCE_SHIFT;
+	}
+
+	reg |= XILINX_MCDMA_IRQ_ALL_MASK;
+	dma_ctrl_write(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest), reg);
+
+	/* Program current descriptor */
+	xilinx_write(chan, XILINX_MCDMA_CHAN_CDESC_OFFSET(chan->tdest),
+		     head_desc->async_tx.phys);
+
+	/* Program channel enable register */
+	reg = dma_ctrl_read(chan, XILINX_MCDMA_CHEN_OFFSET);
+	reg |= BIT(chan->tdest);
+	dma_ctrl_write(chan, XILINX_MCDMA_CHEN_OFFSET, reg);
+
+	/* Start the fetch of BDs for the channel */
+	reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest));
+	reg |= XILINX_MCDMA_CR_RUNSTOP_MASK;
+	dma_ctrl_write(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest), reg);
+
+	xilinx_dma_start(chan);
+
+	if (chan->err)
+		return;
+
+	/* Start the transfer */
+	xilinx_write(chan, XILINX_MCDMA_CHAN_TDESC_OFFSET(chan->tdest),
+		     tail_segment->phys);
+
+	list_splice_tail_init(&chan->pending_list, &chan->active_list);
+	chan->desc_pendingcount = 0;
+	chan->idle = false;
+}
+
+/**
+ * xilinx_dma_issue_pending - Issue pending transactions
+ * @dchan: DMA channel
+ */
+static void xilinx_dma_issue_pending(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->start_transfer(chan);
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_dma_device_config - Configure the DMA channel
+ * @dchan: DMA channel
+ * @config: channel configuration
+ *
+ * Return: 0 always.
+ */
+static int xilinx_dma_device_config(struct dma_chan *dchan,
+				    struct dma_slave_config *config)
+{
+	return 0;
+}
+
+/**
+ * xilinx_dma_complete_descriptor - Mark the active descriptor as complete
+ * @chan : xilinx DMA channel
+ *
+ * CONTEXT: hardirq
+ */
+static void xilinx_dma_complete_descriptor(struct xilinx_dma_chan *chan)
+{
+	struct xilinx_dma_tx_descriptor *desc, *next;
+
+	/* This function was invoked with lock held */
+	if (list_empty(&chan->active_list))
+		return;
+
+	list_for_each_entry_safe(desc, next, &chan->active_list, node) {
+		if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+			struct xilinx_axidma_tx_segment *seg;
+
+			seg = list_last_entry(&desc->segments,
+					      struct xilinx_axidma_tx_segment, node);
+			if (!(seg->hw.status & XILINX_DMA_BD_COMP_MASK) && chan->has_sg)
+				break;
+		}
+		if (chan->has_sg && chan->xdev->dma_config->dmatype !=
+		    XDMA_TYPE_VDMA)
+			desc->residue = xilinx_dma_get_residue(chan, desc);
+		else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA &&
+			 chan->direction == DMA_DEV_TO_MEM && !chan->has_sg)
+			desc->residue = xilinx_dma_get_residue_axidma_direct_s2mm(chan, desc);
+		else
+			desc->residue = 0;
+		desc->err = chan->err;
+
+		list_del(&desc->node);
+		if (!desc->cyclic)
+			dma_cookie_complete(&desc->async_tx);
+		list_add_tail(&desc->node, &chan->done_list);
+	}
+}
+
+/**
+ * xilinx_dma_reset - Reset DMA channel
+ * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_reset(struct xilinx_dma_chan *chan)
+{
+	int err;
+	u32 tmp;
+
+	dma_ctrl_set(chan, XILINX_DMA_REG_DMACR, XILINX_DMA_DMACR_RESET);
+
+	/* Wait for the hardware to finish reset */
+	err = xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMACR, tmp,
+				      !(tmp & XILINX_DMA_DMACR_RESET), 0,
+				      XILINX_DMA_LOOP_COUNT);
+
+	if (err) {
+		dev_err(chan->dev, "reset timeout, cr %x, sr %x\n",
+			dma_ctrl_read(chan, XILINX_DMA_REG_DMACR),
+			dma_ctrl_read(chan, XILINX_DMA_REG_DMASR));
+		return -ETIMEDOUT;
+	}
+
+	chan->err = false;
+	chan->idle = true;
+	chan->desc_pendingcount = 0;
+	chan->desc_submitcount = 0;
+
+	return err;
+}
+
+/**
+ * xilinx_dma_chan_reset - Reset DMA channel and enable interrupts
+ * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_chan_reset(struct xilinx_dma_chan *chan)
+{
+	int err;
+
+	/* Reset VDMA */
+	err = xilinx_dma_reset(chan);
+	if (err)
+		return err;
+
+	/* Enable interrupts */
+	dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
+		      XILINX_DMA_DMAXR_ALL_IRQ_MASK);
+
+	return 0;
+}
+
+/**
+ * xilinx_mcdma_irq_handler - MCDMA Interrupt handler
+ * @irq: IRQ number
+ * @data: Pointer to the Xilinx MCDMA channel structure
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t xilinx_mcdma_irq_handler(int irq, void *data)
+{
+	struct xilinx_dma_chan *chan = data;
+	u32 status, ser_offset, chan_sermask, chan_offset = 0, chan_id;
+
+	if (chan->direction == DMA_DEV_TO_MEM)
+		ser_offset = XILINX_MCDMA_RXINT_SER_OFFSET;
+	else
+		ser_offset = XILINX_MCDMA_TXINT_SER_OFFSET;
+
+	/* Read the channel id raising the interrupt*/
+	chan_sermask = dma_ctrl_read(chan, ser_offset);
+	chan_id = ffs(chan_sermask);
+
+	if (!chan_id)
+		return IRQ_NONE;
+
+	if (chan->direction == DMA_DEV_TO_MEM)
+		chan_offset = chan->xdev->dma_config->max_channels / 2;
+
+	chan_offset = chan_offset + (chan_id - 1);
+	chan = chan->xdev->chan[chan_offset];
+	/* Read the status and ack the interrupts. */
+	status = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_SR_OFFSET(chan->tdest));
+	if (!(status & XILINX_MCDMA_IRQ_ALL_MASK))
+		return IRQ_NONE;
+
+	dma_ctrl_write(chan, XILINX_MCDMA_CHAN_SR_OFFSET(chan->tdest),
+		       status & XILINX_MCDMA_IRQ_ALL_MASK);
+
+	if (status & XILINX_MCDMA_IRQ_ERR_MASK) {
+		dev_err(chan->dev, "Channel %p has errors %x cdr %x tdr %x\n",
+			chan,
+			dma_ctrl_read(chan, XILINX_MCDMA_CH_ERR_OFFSET),
+			dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CDESC_OFFSET
+				      (chan->tdest)),
+			dma_ctrl_read(chan, XILINX_MCDMA_CHAN_TDESC_OFFSET
+				      (chan->tdest)));
+		chan->err = true;
+	}
+
+	if (status & XILINX_MCDMA_IRQ_DELAY_MASK) {
+		/*
+		 * Device takes too long to do the transfer when user requires
+		 * responsiveness.
+		 */
+		dev_dbg(chan->dev, "Inter-packet latency too long\n");
+	}
+
+	if (status & XILINX_MCDMA_IRQ_IOC_MASK) {
+		spin_lock(&chan->lock);
+		xilinx_dma_complete_descriptor(chan);
+		chan->idle = true;
+		chan->start_transfer(chan);
+		spin_unlock(&chan->lock);
+	}
+
+	tasklet_hi_schedule(&chan->tasklet);
+	return IRQ_HANDLED;
+}
+
+/**
+ * xilinx_dma_irq_handler - DMA Interrupt handler
+ * @irq: IRQ number
+ * @data: Pointer to the Xilinx DMA channel structure
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t xilinx_dma_irq_handler(int irq, void *data)
+{
+	struct xilinx_dma_chan *chan = data;
+	u32 status;
+
+	/* Read the status and ack the interrupts. */
+	status = dma_ctrl_read(chan, XILINX_DMA_REG_DMASR);
+	if (!(status & XILINX_DMA_DMAXR_ALL_IRQ_MASK))
+		return IRQ_NONE;
+
+	dma_ctrl_write(chan, XILINX_DMA_REG_DMASR,
+			status & XILINX_DMA_DMAXR_ALL_IRQ_MASK);
+
+	if (status & XILINX_DMA_DMASR_ERR_IRQ) {
+		/*
+		 * An error occurred. If C_FLUSH_ON_FSYNC is enabled and the
+		 * error is recoverable, ignore it. Otherwise flag the error.
+		 *
+		 * Only recoverable errors can be cleared in the DMASR register,
+		 * make sure not to write to other error bits to 1.
+		 */
+		u32 errors = status & XILINX_DMA_DMASR_ALL_ERR_MASK;
+
+		dma_ctrl_write(chan, XILINX_DMA_REG_DMASR,
+				errors & XILINX_DMA_DMASR_ERR_RECOVER_MASK);
+
+		if (!chan->flush_on_fsync ||
+		    (errors & ~XILINX_DMA_DMASR_ERR_RECOVER_MASK)) {
+			dev_err(chan->dev,
+				"Channel %p has errors %x, cdr %x tdr %x\n",
+				chan, errors,
+				dma_ctrl_read(chan, XILINX_DMA_REG_CURDESC),
+				dma_ctrl_read(chan, XILINX_DMA_REG_TAILDESC));
+			chan->err = true;
+		}
+	}
+
+	if (status & (XILINX_DMA_DMASR_FRM_CNT_IRQ |
+		      XILINX_DMA_DMASR_DLY_CNT_IRQ)) {
+		spin_lock(&chan->lock);
+		xilinx_dma_complete_descriptor(chan);
+		chan->idle = true;
+		chan->start_transfer(chan);
+		spin_unlock(&chan->lock);
+	}
+
+	tasklet_schedule(&chan->tasklet);
+	return IRQ_HANDLED;
+}
+
+/**
+ * append_desc_queue - Queuing descriptor
+ * @chan: Driver specific dma channel
+ * @desc: dma transaction descriptor
+ */
+static void append_desc_queue(struct xilinx_dma_chan *chan,
+			      struct xilinx_dma_tx_descriptor *desc)
+{
+	struct xilinx_vdma_tx_segment *tail_segment;
+	struct xilinx_dma_tx_descriptor *tail_desc;
+	struct xilinx_axidma_tx_segment *axidma_tail_segment;
+	struct xilinx_aximcdma_tx_segment *aximcdma_tail_segment;
+	struct xilinx_cdma_tx_segment *cdma_tail_segment;
+
+	if (list_empty(&chan->pending_list))
+		goto append;
+
+	/*
+	 * Add the hardware descriptor to the chain of hardware descriptors
+	 * that already exists in memory.
+	 */
+	tail_desc = list_last_entry(&chan->pending_list,
+				    struct xilinx_dma_tx_descriptor, node);
+	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+		tail_segment = list_last_entry(&tail_desc->segments,
+					       struct xilinx_vdma_tx_segment,
+					       node);
+		tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+		cdma_tail_segment = list_last_entry(&tail_desc->segments,
+						struct xilinx_cdma_tx_segment,
+						node);
+		cdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		axidma_tail_segment = list_last_entry(&tail_desc->segments,
+					       struct xilinx_axidma_tx_segment,
+					       node);
+		axidma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+	} else {
+		aximcdma_tail_segment =
+			list_last_entry(&tail_desc->segments,
+					struct xilinx_aximcdma_tx_segment,
+					node);
+		aximcdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+	}
+
+	/*
+	 * Add the software descriptor and all children to the list
+	 * of pending transactions
+	 */
+append:
+	list_add_tail(&desc->node, &chan->pending_list);
+	chan->desc_pendingcount++;
+
+	if (chan->has_sg && (chan->xdev->dma_config->dmatype == XDMA_TYPE_VDMA)
+	    && unlikely(chan->desc_pendingcount > chan->num_frms)) {
+		dev_dbg(chan->dev, "desc pendingcount is too high\n");
+		chan->desc_pendingcount = chan->num_frms;
+	}
+}
+
+/**
+ * xilinx_dma_tx_submit - Submit DMA transaction
+ * @tx: Async transaction descriptor
+ *
+ * Return: cookie value on success and failure value on error
+ */
+static dma_cookie_t xilinx_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct xilinx_dma_tx_descriptor *desc = to_dma_tx_descriptor(tx);
+	struct xilinx_dma_chan *chan = to_xilinx_chan(tx->chan);
+	dma_cookie_t cookie;
+	unsigned long flags;
+	int err;
+
+	if (chan->cyclic) {
+		xilinx_dma_free_tx_descriptor(chan, desc);
+		return -EBUSY;
+	}
+
+	if (chan->err) {
+		/*
+		 * If reset fails, need to hard reset the system.
+		 * Channel is no longer functional
+		 */
+		err = xilinx_dma_chan_reset(chan);
+		if (err < 0)
+			return err;
+	}
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	cookie = dma_cookie_assign(tx);
+
+	/* Put this transaction onto the tail of the pending queue */
+	append_desc_queue(chan, desc);
+
+	if (desc->cyclic)
+		chan->cyclic = true;
+
+	chan->terminating = false;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return cookie;
+}
+
+/**
+ * xilinx_vdma_dma_prep_interleaved - prepare a descriptor for a
+ *	DMA_SLAVE transaction
+ * @dchan: DMA channel
+ * @xt: Interleaved template pointer
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
+				 struct dma_interleaved_template *xt,
+				 unsigned long flags)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_vdma_tx_segment *segment;
+	struct xilinx_vdma_desc_hw *hw;
+
+	if (!is_slave_direction(xt->dir))
+		return NULL;
+
+	if (!xt->numf || !xt->sgl[0].size)
+		return NULL;
+
+	if (xt->numf & ~XILINX_DMA_VSIZE_MASK ||
+	    xt->sgl[0].size & ~XILINX_DMA_HSIZE_MASK)
+		return NULL;
+
+	if (xt->frame_size != 1)
+		return NULL;
+
+	/* Allocate a transaction descriptor. */
+	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;
+	async_tx_ack(&desc->async_tx);
+
+	/* Allocate the link descriptor from DMA pool */
+	segment = xilinx_vdma_alloc_tx_segment(chan);
+	if (!segment)
+		goto error;
+
+	/* Fill in the hardware descriptor */
+	hw = &segment->hw;
+	hw->vsize = xt->numf;
+	hw->hsize = xt->sgl[0].size;
+	hw->stride = (xt->sgl[0].icg + xt->sgl[0].size) <<
+			XILINX_DMA_FRMDLY_STRIDE_STRIDE_SHIFT;
+	hw->stride |= chan->config.frm_dly <<
+			XILINX_DMA_FRMDLY_STRIDE_FRMDLY_SHIFT;
+
+	if (xt->dir != DMA_MEM_TO_DEV) {
+		if (chan->ext_addr) {
+			hw->buf_addr = lower_32_bits(xt->dst_start);
+			hw->buf_addr_msb = upper_32_bits(xt->dst_start);
+		} else {
+			hw->buf_addr = xt->dst_start;
+		}
+	} else {
+		if (chan->ext_addr) {
+			hw->buf_addr = lower_32_bits(xt->src_start);
+			hw->buf_addr_msb = upper_32_bits(xt->src_start);
+		} else {
+			hw->buf_addr = xt->src_start;
+		}
+	}
+
+	/* Insert the segment into the descriptor segments list. */
+	list_add_tail(&segment->node, &desc->segments);
+
+	/* Link the last hardware descriptor with the first. */
+	segment = list_first_entry(&desc->segments,
+				   struct xilinx_vdma_tx_segment, node);
+	desc->async_tx.phys = segment->phys;
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
+/**
+ * xilinx_cdma_prep_memcpy - prepare descriptors for a memcpy transaction
+ * @dchan: DMA channel
+ * @dma_dst: destination address
+ * @dma_src: source address
+ * @len: transfer length
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+xilinx_cdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst,
+			dma_addr_t dma_src, size_t len, unsigned long flags)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_cdma_tx_segment *segment;
+	struct xilinx_cdma_desc_hw *hw;
+
+	if (!len || len > chan->xdev->max_buffer_len)
+		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;
+
+	/* Allocate the link descriptor from DMA pool */
+	segment = xilinx_cdma_alloc_tx_segment(chan);
+	if (!segment)
+		goto error;
+
+	hw = &segment->hw;
+	hw->control = len;
+	hw->src_addr = dma_src;
+	hw->dest_addr = dma_dst;
+	if (chan->ext_addr) {
+		hw->src_addr_msb = upper_32_bits(dma_src);
+		hw->dest_addr_msb = upper_32_bits(dma_dst);
+	}
+
+	/* Insert the segment into the descriptor segments list. */
+	list_add_tail(&segment->node, &desc->segments);
+
+	desc->async_tx.phys = segment->phys;
+	hw->next_desc = segment->phys;
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
+/**
+ * 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
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: transfer ack flags
+ * @context: APP words of the descriptor
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
+	struct dma_chan *dchan, struct scatterlist *sgl, unsigned int sg_len,
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_axidma_tx_segment *segment = NULL;
+	u32 *app_w = (u32 *)context;
+	struct scatterlist *sg;
+	size_t copy;
+	size_t sg_used;
+	unsigned int i;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	/* Allocate a transaction descriptor. */
+	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 in the scatter gather list */
+	for_each_sg(sgl, sg, sg_len, i) {
+		sg_used = 0;
+
+		/* Loop until the entire scatterlist entry is used */
+		while (sg_used < sg_dma_len(sg)) {
+			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, sg_dma_len(sg),
+							sg_used);
+			hw = &segment->hw;
+
+			/* Fill in the descriptor */
+			xilinx_axidma_buf(chan, hw, sg_dma_address(sg),
+					  sg_used, 0);
+
+			hw->control = copy;
+
+			if (chan->direction == DMA_MEM_TO_DEV) {
+				if (app_w)
+					memcpy(hw->app, app_w, sizeof(u32) *
+					       XILINX_DMA_NUM_APP_WORDS);
+			}
+
+			sg_used += copy;
+
+			/*
+			 * Insert the segment into the descriptor segments
+			 * list.
+			 */
+			list_add_tail(&segment->node, &desc->segments);
+		}
+	}
+
+	segment = list_first_entry(&desc->segments,
+				   struct xilinx_axidma_tx_segment, node);
+	desc->async_tx.phys = segment->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_dma_cyclic - prepare descriptors for a DMA_SLAVE transaction
+ * @dchan: DMA channel
+ * @buf_addr: Physical address of the buffer
+ * @buf_len: Total length of the cyclic buffers
+ * @period_len: length of individual cyclic buffer
+ * @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_dma_cyclic(
+	struct dma_chan *dchan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, 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_segment, *prev = NULL;
+	size_t copy, sg_used;
+	unsigned int num_periods;
+	int i;
+	u32 reg;
+
+	if (!period_len)
+		return NULL;
+
+	num_periods = buf_len / period_len;
+
+	if (!num_periods)
+		return NULL;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	/* Allocate a transaction descriptor. */
+	desc = xilinx_dma_alloc_tx_descriptor(chan);
+	if (!desc)
+		return NULL;
+
+	chan->direction = direction;
+	dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+	desc->async_tx.tx_submit = xilinx_dma_tx_submit;
+
+	for (i = 0; i < num_periods; ++i) {
+		sg_used = 0;
+
+		while (sg_used < period_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, period_len,
+							sg_used);
+			hw = &segment->hw;
+			xilinx_axidma_buf(chan, hw, buf_addr, sg_used,
+					  period_len * i);
+			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_segment = list_first_entry(&desc->segments,
+				   struct xilinx_axidma_tx_segment, node);
+	desc->async_tx.phys = head_segment->phys;
+
+	desc->cyclic = true;
+	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
+	reg |= XILINX_DMA_CR_CYCLIC_BD_EN_MASK;
+	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
+
+	segment = list_last_entry(&desc->segments,
+				  struct xilinx_axidma_tx_segment,
+				  node);
+	segment->hw.next_desc = (u32) head_segment->phys;
+
+	/* For the last DMA_MEM_TO_DEV transfer, set EOP */
+	if (direction == DMA_MEM_TO_DEV) {
+		head_segment->hw.control |= XILINX_DMA_BD_SOP;
+		segment->hw.control |= XILINX_DMA_BD_EOP;
+	}
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
+/**
+ * xilinx_mcdma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @dchan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: transfer ack flags
+ * @context: APP words of the descriptor
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+xilinx_mcdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
+			   unsigned int sg_len,
+			   enum dma_transfer_direction direction,
+			   unsigned long flags, void *context)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_aximcdma_tx_segment *segment = NULL;
+	u32 *app_w = (u32 *)context;
+	struct scatterlist *sg;
+	size_t copy;
+	size_t sg_used;
+	unsigned int i;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	/* Allocate a transaction descriptor. */
+	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 in the scatter gather list */
+	for_each_sg(sgl, sg, sg_len, i) {
+		sg_used = 0;
+
+		/* Loop until the entire scatterlist entry is used */
+		while (sg_used < sg_dma_len(sg)) {
+			struct xilinx_aximcdma_desc_hw *hw;
+
+			/* Get a free segment */
+			segment = xilinx_aximcdma_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 = min_t(size_t, sg_dma_len(sg) - sg_used,
+				     chan->xdev->max_buffer_len);
+			hw = &segment->hw;
+
+			/* Fill in the descriptor */
+			xilinx_aximcdma_buf(chan, hw, sg_dma_address(sg),
+					    sg_used);
+			hw->control = copy;
+
+			if (chan->direction == DMA_MEM_TO_DEV && app_w) {
+				memcpy(hw->app, app_w, sizeof(u32) *
+				       XILINX_DMA_NUM_APP_WORDS);
+			}
+
+			sg_used += copy;
+			/*
+			 * Insert the segment into the descriptor segments
+			 * list.
+			 */
+			list_add_tail(&segment->node, &desc->segments);
+		}
+	}
+
+	segment = list_first_entry(&desc->segments,
+				   struct xilinx_aximcdma_tx_segment, node);
+	desc->async_tx.phys = segment->phys;
+
+	/* For the last DMA_MEM_TO_DEV transfer, set EOP */
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		segment->hw.control |= XILINX_MCDMA_BD_SOP;
+		segment = list_last_entry(&desc->segments,
+					  struct xilinx_aximcdma_tx_segment,
+					  node);
+		segment->hw.control |= XILINX_MCDMA_BD_EOP;
+	}
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+
+	return NULL;
+}
+
+/**
+ * xilinx_dma_terminate_all - Halt the channel and free descriptors
+ * @dchan: Driver specific DMA Channel pointer
+ *
+ * Return: '0' always.
+ */
+static int xilinx_dma_terminate_all(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	u32 reg;
+	int err;
+
+	if (!chan->cyclic) {
+		err = chan->stop_transfer(chan);
+		if (err) {
+			dev_err(chan->dev, "Cannot stop channel %p: %x\n",
+				chan, dma_ctrl_read(chan,
+				XILINX_DMA_REG_DMASR));
+			chan->err = true;
+		}
+	}
+
+	xilinx_dma_chan_reset(chan);
+	/* Remove and free all of the descriptors in the lists */
+	chan->terminating = true;
+	xilinx_dma_free_descriptors(chan);
+	chan->idle = true;
+
+	if (chan->cyclic) {
+		reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
+		reg &= ~XILINX_DMA_CR_CYCLIC_BD_EN_MASK;
+		dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
+		chan->cyclic = false;
+	}
+
+	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+	return 0;
+}
+
+static void xilinx_dma_synchronize(struct dma_chan *dchan)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+
+	tasklet_kill(&chan->tasklet);
+}
+
+/**
+ * xilinx_vdma_channel_set_config - Configure VDMA channel
+ * Run-time configuration for Axi VDMA, supports:
+ * . halt the channel
+ * . configure interrupt coalescing and inter-packet delay threshold
+ * . start/stop parking
+ * . enable genlock
+ *
+ * @dchan: DMA channel
+ * @cfg: VDMA device configuration pointer
+ *
+ * Return: '0' on success and failure value on error
+ */
+int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
+					struct xilinx_vdma_config *cfg)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	u32 dmacr;
+
+	if (cfg->reset)
+		return xilinx_dma_chan_reset(chan);
+
+	dmacr = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
+
+	chan->config.frm_dly = cfg->frm_dly;
+	chan->config.park = cfg->park;
+
+	/* genlock settings */
+	chan->config.gen_lock = cfg->gen_lock;
+	chan->config.master = cfg->master;
+
+	dmacr &= ~XILINX_DMA_DMACR_GENLOCK_EN;
+	if (cfg->gen_lock && chan->genlock) {
+		dmacr |= XILINX_DMA_DMACR_GENLOCK_EN;
+		dmacr &= ~XILINX_DMA_DMACR_MASTER_MASK;
+		dmacr |= cfg->master << XILINX_DMA_DMACR_MASTER_SHIFT;
+	}
+
+	chan->config.frm_cnt_en = cfg->frm_cnt_en;
+	chan->config.vflip_en = cfg->vflip_en;
+
+	if (cfg->park)
+		chan->config.park_frm = cfg->park_frm;
+	else
+		chan->config.park_frm = -1;
+
+	chan->config.coalesc = cfg->coalesc;
+	chan->config.delay = cfg->delay;
+
+	if (cfg->coalesc <= XILINX_DMA_DMACR_FRAME_COUNT_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_FRAME_COUNT_MASK;
+		dmacr |= cfg->coalesc << XILINX_DMA_DMACR_FRAME_COUNT_SHIFT;
+		chan->config.coalesc = cfg->coalesc;
+	}
+
+	if (cfg->delay <= XILINX_DMA_DMACR_DELAY_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_DELAY_MASK;
+		dmacr |= cfg->delay << XILINX_DMA_DMACR_DELAY_SHIFT;
+		chan->config.delay = cfg->delay;
+	}
+
+	/* FSync Source selection */
+	dmacr &= ~XILINX_DMA_DMACR_FSYNCSRC_MASK;
+	dmacr |= cfg->ext_fsync << XILINX_DMA_DMACR_FSYNCSRC_SHIFT;
+
+	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, dmacr);
+
+	return 0;
+}
+EXPORT_SYMBOL(xilinx_vdma_channel_set_config);
+
+/* -----------------------------------------------------------------------------
+ * Probe and remove
+ */
+
+/**
+ * xilinx_dma_chan_remove - Per Channel remove function
+ * @chan: Driver specific DMA channel
+ */
+static void xilinx_dma_chan_remove(struct xilinx_dma_chan *chan)
+{
+	/* Disable all interrupts */
+	dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+		      XILINX_DMA_DMAXR_ALL_IRQ_MASK);
+
+	if (chan->irq > 0)
+		free_irq(chan->irq, chan);
+
+	tasklet_kill(&chan->tasklet);
+
+	list_del(&chan->common.device_node);
+}
+
+static int axidma_clk_init(struct platform_device *pdev, struct clk **axi_clk,
+			    struct clk **tx_clk, struct clk **rx_clk,
+			    struct clk **sg_clk, struct clk **tmp_clk)
+{
+	int err;
+
+	*tmp_clk = NULL;
+
+	*axi_clk = devm_clk_get(&pdev->dev, "s_axi_lite_aclk");
+	if (IS_ERR(*axi_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(*axi_clk), "failed to get axi_aclk\n");
+
+	*tx_clk = devm_clk_get(&pdev->dev, "m_axi_mm2s_aclk");
+	if (IS_ERR(*tx_clk))
+		*tx_clk = NULL;
+
+	*rx_clk = devm_clk_get(&pdev->dev, "m_axi_s2mm_aclk");
+	if (IS_ERR(*rx_clk))
+		*rx_clk = NULL;
+
+	*sg_clk = devm_clk_get(&pdev->dev, "m_axi_sg_aclk");
+	if (IS_ERR(*sg_clk))
+		*sg_clk = NULL;
+
+	err = clk_prepare_enable(*axi_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable axi_clk (%d)\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(*tx_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable tx_clk (%d)\n", err);
+		goto err_disable_axiclk;
+	}
+
+	err = clk_prepare_enable(*rx_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable rx_clk (%d)\n", err);
+		goto err_disable_txclk;
+	}
+
+	err = clk_prepare_enable(*sg_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable sg_clk (%d)\n", err);
+		goto err_disable_rxclk;
+	}
+
+	return 0;
+
+err_disable_rxclk:
+	clk_disable_unprepare(*rx_clk);
+err_disable_txclk:
+	clk_disable_unprepare(*tx_clk);
+err_disable_axiclk:
+	clk_disable_unprepare(*axi_clk);
+
+	return err;
+}
+
+static int axicdma_clk_init(struct platform_device *pdev, struct clk **axi_clk,
+			    struct clk **dev_clk, struct clk **tmp_clk,
+			    struct clk **tmp1_clk, struct clk **tmp2_clk)
+{
+	int err;
+
+	*tmp_clk = NULL;
+	*tmp1_clk = NULL;
+	*tmp2_clk = NULL;
+
+	*axi_clk = devm_clk_get(&pdev->dev, "s_axi_lite_aclk");
+	if (IS_ERR(*axi_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(*axi_clk), "failed to get axi_aclk\n");
+
+	*dev_clk = devm_clk_get(&pdev->dev, "m_axi_aclk");
+	if (IS_ERR(*dev_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(*dev_clk), "failed to get dev_clk\n");
+
+	err = clk_prepare_enable(*axi_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable axi_clk (%d)\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(*dev_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable dev_clk (%d)\n", err);
+		goto err_disable_axiclk;
+	}
+
+	return 0;
+
+err_disable_axiclk:
+	clk_disable_unprepare(*axi_clk);
+
+	return err;
+}
+
+static int axivdma_clk_init(struct platform_device *pdev, struct clk **axi_clk,
+			    struct clk **tx_clk, struct clk **txs_clk,
+			    struct clk **rx_clk, struct clk **rxs_clk)
+{
+	int err;
+
+	*axi_clk = devm_clk_get(&pdev->dev, "s_axi_lite_aclk");
+	if (IS_ERR(*axi_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(*axi_clk), "failed to get axi_aclk\n");
+
+	*tx_clk = devm_clk_get(&pdev->dev, "m_axi_mm2s_aclk");
+	if (IS_ERR(*tx_clk))
+		*tx_clk = NULL;
+
+	*txs_clk = devm_clk_get(&pdev->dev, "m_axis_mm2s_aclk");
+	if (IS_ERR(*txs_clk))
+		*txs_clk = NULL;
+
+	*rx_clk = devm_clk_get(&pdev->dev, "m_axi_s2mm_aclk");
+	if (IS_ERR(*rx_clk))
+		*rx_clk = NULL;
+
+	*rxs_clk = devm_clk_get(&pdev->dev, "s_axis_s2mm_aclk");
+	if (IS_ERR(*rxs_clk))
+		*rxs_clk = NULL;
+
+	err = clk_prepare_enable(*axi_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable axi_clk (%d)\n",
+			err);
+		return err;
+	}
+
+	err = clk_prepare_enable(*tx_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable tx_clk (%d)\n", err);
+		goto err_disable_axiclk;
+	}
+
+	err = clk_prepare_enable(*txs_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable txs_clk (%d)\n", err);
+		goto err_disable_txclk;
+	}
+
+	err = clk_prepare_enable(*rx_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable rx_clk (%d)\n", err);
+		goto err_disable_txsclk;
+	}
+
+	err = clk_prepare_enable(*rxs_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable rxs_clk (%d)\n", err);
+		goto err_disable_rxclk;
+	}
+
+	return 0;
+
+err_disable_rxclk:
+	clk_disable_unprepare(*rx_clk);
+err_disable_txsclk:
+	clk_disable_unprepare(*txs_clk);
+err_disable_txclk:
+	clk_disable_unprepare(*tx_clk);
+err_disable_axiclk:
+	clk_disable_unprepare(*axi_clk);
+
+	return err;
+}
+
+static void xdma_disable_allclks(struct xilinx_dma_device *xdev)
+{
+	clk_disable_unprepare(xdev->rxs_clk);
+	clk_disable_unprepare(xdev->rx_clk);
+	clk_disable_unprepare(xdev->txs_clk);
+	clk_disable_unprepare(xdev->tx_clk);
+	clk_disable_unprepare(xdev->axi_clk);
+}
+
+/**
+ * xilinx_dma_chan_probe - Per Channel Probing
+ * It get channel features from the device tree entry and
+ * initialize special channel handling routines
+ *
+ * @xdev: Driver specific device structure
+ * @node: Device node
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
+				  struct device_node *node)
+{
+	struct xilinx_dma_chan *chan;
+	bool has_dre = false;
+	u32 value, width;
+	int err;
+
+	/* Allocate and initialize the channel structure */
+	chan = devm_kzalloc(xdev->dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+
+	chan->dev = xdev->dev;
+	chan->xdev = xdev;
+	chan->desc_pendingcount = 0x0;
+	chan->ext_addr = xdev->ext_addr;
+	/* This variable ensures that descriptors are not
+	 * Submitted when dma engine is in progress. This variable is
+	 * Added to avoid polling for a bit in the status register to
+	 * Know dma state in the driver hot path.
+	 */
+	chan->idle = true;
+
+	spin_lock_init(&chan->lock);
+	INIT_LIST_HEAD(&chan->pending_list);
+	INIT_LIST_HEAD(&chan->done_list);
+	INIT_LIST_HEAD(&chan->active_list);
+	INIT_LIST_HEAD(&chan->free_seg_list);
+
+	/* Retrieve the channel properties from the device tree */
+	has_dre = of_property_read_bool(node, "xlnx,include-dre");
+
+	of_property_read_u8(node, "xlnx,irq-delay", &chan->irq_delay);
+
+	chan->genlock = of_property_read_bool(node, "xlnx,genlock-mode");
+
+	err = of_property_read_u32(node, "xlnx,datawidth", &value);
+	if (err) {
+		dev_err(xdev->dev, "missing xlnx,datawidth property\n");
+		return err;
+	}
+	width = value >> 3; /* Convert bits to bytes */
+
+	/* If data width is greater than 8 bytes, DRE is not in hw */
+	if (width > 8)
+		has_dre = false;
+
+	if (!has_dre)
+		xdev->common.copy_align = (enum dmaengine_alignment)fls(width - 1);
+
+	if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel") ||
+	    of_device_is_compatible(node, "xlnx,axi-dma-mm2s-channel") ||
+	    of_device_is_compatible(node, "xlnx,axi-cdma-channel")) {
+		chan->direction = DMA_MEM_TO_DEV;
+		chan->id = xdev->mm2s_chan_id++;
+		chan->tdest = chan->id;
+
+		chan->ctrl_offset = XILINX_DMA_MM2S_CTRL_OFFSET;
+		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+			chan->desc_offset = XILINX_VDMA_MM2S_DESC_OFFSET;
+			chan->config.park = 1;
+
+			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
+			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_MM2S)
+				chan->flush_on_fsync = true;
+		}
+	} else if (of_device_is_compatible(node,
+					   "xlnx,axi-vdma-s2mm-channel") ||
+		   of_device_is_compatible(node,
+					   "xlnx,axi-dma-s2mm-channel")) {
+		chan->direction = DMA_DEV_TO_MEM;
+		chan->id = xdev->s2mm_chan_id++;
+		chan->tdest = chan->id - xdev->dma_config->max_channels / 2;
+		chan->has_vflip = of_property_read_bool(node,
+					"xlnx,enable-vert-flip");
+		if (chan->has_vflip) {
+			chan->config.vflip_en = dma_read(chan,
+				XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP) &
+				XILINX_VDMA_ENABLE_VERTICAL_FLIP;
+		}
+
+		if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA)
+			chan->ctrl_offset = XILINX_MCDMA_S2MM_CTRL_OFFSET;
+		else
+			chan->ctrl_offset = XILINX_DMA_S2MM_CTRL_OFFSET;
+
+		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+			chan->desc_offset = XILINX_VDMA_S2MM_DESC_OFFSET;
+			chan->config.park = 1;
+
+			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
+			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_S2MM)
+				chan->flush_on_fsync = true;
+		}
+	} else {
+		dev_err(xdev->dev, "Invalid channel compatible node\n");
+		return -EINVAL;
+	}
+
+	xdev->common.directions |= BIT(chan->direction);
+
+	/* Request the interrupt */
+	chan->irq = of_irq_get(node, chan->tdest);
+	if (chan->irq < 0)
+		return dev_err_probe(xdev->dev, chan->irq, "failed to get irq\n");
+	err = request_irq(chan->irq, xdev->dma_config->irq_handler,
+			  IRQF_SHARED, "xilinx-dma-controller", chan);
+	if (err) {
+		dev_err(xdev->dev, "unable to request IRQ %d\n", chan->irq);
+		return err;
+	}
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		chan->start_transfer = xilinx_dma_start_transfer;
+		chan->stop_transfer = xilinx_dma_stop_transfer;
+	} else if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA) {
+		chan->start_transfer = xilinx_mcdma_start_transfer;
+		chan->stop_transfer = xilinx_dma_stop_transfer;
+	} else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+		chan->start_transfer = xilinx_cdma_start_transfer;
+		chan->stop_transfer = xilinx_cdma_stop_transfer;
+	} else {
+		chan->start_transfer = xilinx_vdma_start_transfer;
+		chan->stop_transfer = xilinx_dma_stop_transfer;
+	}
+
+	/* check if SG is enabled (only for AXIDMA, AXIMCDMA, and CDMA) */
+	if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) {
+		if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA ||
+		    dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
+			    XILINX_DMA_DMASR_SG_MASK)
+			chan->has_sg = true;
+		dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id,
+			str_enabled_disabled(chan->has_sg));
+	}
+
+	/* Initialize the tasklet */
+	tasklet_setup(&chan->tasklet, xilinx_dma_do_tasklet);
+
+	/*
+	 * Initialize the DMA channel and add it to the DMA engine channels
+	 * list.
+	 */
+	chan->common.device = &xdev->common;
+
+	list_add_tail(&chan->common.device_node, &xdev->common.channels);
+	xdev->chan[chan->id] = chan;
+
+	/* Reset the channel */
+	err = xilinx_dma_chan_reset(chan);
+	if (err < 0) {
+		dev_err(xdev->dev, "Reset channel failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * xilinx_dma_child_probe - Per child node probe
+ * It get number of dma-channels per child node from
+ * device-tree and initializes all the channels.
+ *
+ * @xdev: Driver specific device structure
+ * @node: Device node
+ *
+ * Return: '0' on success and failure value on error.
+ */
+static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
+				    struct device_node *node)
+{
+	int ret, i;
+	u32 nr_channels = 1;
+
+	ret = of_property_read_u32(node, "dma-channels", &nr_channels);
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0)
+		dev_warn(xdev->dev, "missing dma-channels property\n");
+
+	for (i = 0; i < nr_channels; i++) {
+		ret = xilinx_dma_chan_probe(xdev, node);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * of_dma_xilinx_xlate - Translation function
+ * @dma_spec: Pointer to DMA specifier as found in the device tree
+ * @ofdma: Pointer to DMA controller data
+ *
+ * Return: DMA channel pointer on success and NULL on error
+ */
+static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec,
+						struct of_dma *ofdma)
+{
+	struct xilinx_dma_device *xdev = ofdma->of_dma_data;
+	int chan_id = dma_spec->args[0];
+
+	if (chan_id >= xdev->dma_config->max_channels || !xdev->chan[chan_id])
+		return NULL;
+
+	return dma_get_slave_channel(&xdev->chan[chan_id]->common);
+}
+
+static const struct xilinx_dma_config axidma_config = {
+	.dmatype = XDMA_TYPE_AXIDMA,
+	.clk_init = axidma_clk_init,
+	.irq_handler = xilinx_dma_irq_handler,
+	.max_channels = XILINX_DMA_MAX_CHANS_PER_DEVICE,
+};
+
+static const struct xilinx_dma_config aximcdma_config = {
+	.dmatype = XDMA_TYPE_AXIMCDMA,
+	.clk_init = axidma_clk_init,
+	.irq_handler = xilinx_mcdma_irq_handler,
+	.max_channels = XILINX_MCDMA_MAX_CHANS_PER_DEVICE,
+};
+static const struct xilinx_dma_config axicdma_config = {
+	.dmatype = XDMA_TYPE_CDMA,
+	.clk_init = axicdma_clk_init,
+	.irq_handler = xilinx_dma_irq_handler,
+	.max_channels = XILINX_CDMA_MAX_CHANS_PER_DEVICE,
+};
+
+static const struct xilinx_dma_config axivdma_config = {
+	.dmatype = XDMA_TYPE_VDMA,
+	.clk_init = axivdma_clk_init,
+	.irq_handler = xilinx_dma_irq_handler,
+	.max_channels = XILINX_DMA_MAX_CHANS_PER_DEVICE,
+};
+
+static const struct of_device_id xilinx_dma_of_ids[] = {
+	{ .compatible = "xlnx,axi-dma-1.00.a", .data = &axidma_config },
+	{ .compatible = "xlnx,axi-cdma-1.00.a", .data = &axicdma_config },
+	{ .compatible = "xlnx,axi-vdma-1.00.a", .data = &axivdma_config },
+	{ .compatible = "xlnx,axi-mcdma-1.00.a", .data = &aximcdma_config },
+	{}
+};
+MODULE_DEVICE_TABLE(of, xilinx_dma_of_ids);
+
+/**
+ * xilinx_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_dma_probe(struct platform_device *pdev)
+{
+	int (*clk_init)(struct platform_device *, struct clk **, struct clk **,
+			struct clk **, struct clk **, struct clk **)
+					= axivdma_clk_init;
+	struct device_node *node = pdev->dev.of_node;
+	struct xilinx_dma_device *xdev;
+	struct device_node *np = pdev->dev.of_node;
+	u32 num_frames, addr_width = XILINX_DMA_DFAULT_ADDRWIDTH, len_width;
+	int i, err;
+
+	/* Allocate and initialize the DMA engine structure */
+	xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL);
+	if (!xdev)
+		return -ENOMEM;
+
+	xdev->dev = &pdev->dev;
+	if (np) {
+		const struct of_device_id *match;
+
+		match = of_match_node(xilinx_dma_of_ids, np);
+		if (match && match->data) {
+			xdev->dma_config = match->data;
+			clk_init = xdev->dma_config->clk_init;
+		}
+	}
+
+	err = clk_init(pdev, &xdev->axi_clk, &xdev->tx_clk, &xdev->txs_clk,
+		       &xdev->rx_clk, &xdev->rxs_clk);
+	if (err)
+		return err;
+
+	/* Request and map I/O memory */
+	xdev->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(xdev->regs)) {
+		err = PTR_ERR(xdev->regs);
+		goto disable_clks;
+	}
+	/* Retrieve the DMA engine properties from the device tree */
+	xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0);
+	xdev->s2mm_chan_id = xdev->dma_config->max_channels / 2;
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA ||
+	    xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA) {
+		if (!of_property_read_u32(node, "xlnx,sg-length-width",
+					  &len_width)) {
+			if (len_width < XILINX_DMA_MAX_TRANS_LEN_MIN ||
+			    len_width > XILINX_DMA_V2_MAX_TRANS_LEN_MAX) {
+				dev_warn(xdev->dev,
+					 "invalid xlnx,sg-length-width property value. Using default width\n");
+			} else {
+				if (len_width > XILINX_DMA_MAX_TRANS_LEN_MAX)
+					dev_warn(xdev->dev, "Please ensure that IP supports buffer length > 23 bits\n");
+				xdev->max_buffer_len =
+					GENMASK(len_width - 1, 0);
+			}
+		}
+	}
+
+	dma_set_max_seg_size(xdev->dev, xdev->max_buffer_len);
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
+		xdev->has_axistream_connected =
+			of_property_read_bool(node, "xlnx,axistream-connected");
+	}
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+		err = of_property_read_u32(node, "xlnx,num-fstores",
+					   &num_frames);
+		if (err < 0) {
+			dev_err(xdev->dev,
+				"missing xlnx,num-fstores property\n");
+			goto disable_clks;
+		}
+
+		err = of_property_read_u32(node, "xlnx,flush-fsync",
+					   &xdev->flush_on_fsync);
+		if (err < 0)
+			dev_warn(xdev->dev,
+				 "missing xlnx,flush-fsync property\n");
+	}
+
+	err = of_property_read_u32(node, "xlnx,addrwidth", &addr_width);
+	if (err < 0)
+		dev_warn(xdev->dev,
+			 "missing xlnx,addrwidth property, using default value %d\n",
+			 XILINX_DMA_DFAULT_ADDRWIDTH);
+
+	if (addr_width > 32)
+		xdev->ext_addr = true;
+	else
+		xdev->ext_addr = false;
+
+	/* Set metadata mode */
+	if (xdev->has_axistream_connected)
+		xdev->common.desc_metadata_modes = DESC_METADATA_ENGINE;
+
+	/* Set the dma mask bits */
+	err = dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width));
+	if (err < 0) {
+		dev_err(xdev->dev, "DMA mask error %d\n", err);
+		goto disable_clks;
+	}
+
+	/* Initialize the DMA engine */
+	xdev->common.dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&xdev->common.channels);
+	if (!(xdev->dma_config->dmatype == XDMA_TYPE_CDMA)) {
+		dma_cap_set(DMA_SLAVE, xdev->common.cap_mask);
+		dma_cap_set(DMA_PRIVATE, xdev->common.cap_mask);
+	}
+
+	xdev->common.device_alloc_chan_resources =
+				xilinx_dma_alloc_chan_resources;
+	xdev->common.device_free_chan_resources =
+				xilinx_dma_free_chan_resources;
+	xdev->common.device_terminate_all = xilinx_dma_terminate_all;
+	xdev->common.device_synchronize = xilinx_dma_synchronize;
+	xdev->common.device_tx_status = xilinx_dma_tx_status;
+	xdev->common.device_issue_pending = xilinx_dma_issue_pending;
+	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;
+		/* Residue calculation is supported by only AXI DMA and CDMA */
+		xdev->common.residue_granularity =
+					  DMA_RESIDUE_GRANULARITY_SEGMENT;
+	} else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
+		dma_cap_set(DMA_MEMCPY, xdev->common.cap_mask);
+		xdev->common.device_prep_dma_memcpy = xilinx_cdma_prep_memcpy;
+		/* Residue calculation is supported by only AXI DMA and CDMA */
+		xdev->common.residue_granularity =
+					  DMA_RESIDUE_GRANULARITY_SEGMENT;
+	} else if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA) {
+		xdev->common.device_prep_slave_sg = xilinx_mcdma_prep_slave_sg;
+	} else {
+		xdev->common.device_prep_interleaved_dma =
+				xilinx_vdma_dma_prep_interleaved;
+	}
+
+	platform_set_drvdata(pdev, xdev);
+
+	/* Initialize the channels */
+	for_each_child_of_node_scoped(node, child) {
+		err = xilinx_dma_child_probe(xdev, child);
+		if (err < 0)
+			goto error;
+	}
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
+		for (i = 0; i < xdev->dma_config->max_channels; i++)
+			if (xdev->chan[i])
+				xdev->chan[i]->num_frms = num_frames;
+	}
+
+	/* Register the DMA engine with the core */
+	err = dma_async_device_register(&xdev->common);
+	if (err) {
+		dev_err(xdev->dev, "failed to register the dma device\n");
+		goto error;
+	}
+
+	err = of_dma_controller_register(node, of_dma_xilinx_xlate,
+					 xdev);
+	if (err < 0) {
+		dev_err(&pdev->dev, "Unable to register DMA to DT\n");
+		dma_async_device_unregister(&xdev->common);
+		goto error;
+	}
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA)
+		dev_info(&pdev->dev, "Xilinx AXI DMA Engine Driver Probed!!\n");
+	else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA)
+		dev_info(&pdev->dev, "Xilinx AXI CDMA Engine Driver Probed!!\n");
+	else if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA)
+		dev_info(&pdev->dev, "Xilinx AXI MCDMA Engine Driver Probed!!\n");
+	else
+		dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
+
+	return 0;
+
+error:
+	for (i = 0; i < xdev->dma_config->max_channels; i++)
+		if (xdev->chan[i])
+			xilinx_dma_chan_remove(xdev->chan[i]);
+disable_clks:
+	xdma_disable_allclks(xdev);
+
+	return err;
+}
+
+/**
+ * xilinx_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void xilinx_dma_remove(struct platform_device *pdev)
+{
+	struct xilinx_dma_device *xdev = platform_get_drvdata(pdev);
+	int i;
+
+	of_dma_controller_free(pdev->dev.of_node);
+
+	dma_async_device_unregister(&xdev->common);
+
+	for (i = 0; i < xdev->dma_config->max_channels; i++)
+		if (xdev->chan[i])
+			xilinx_dma_chan_remove(xdev->chan[i]);
+
+	xdma_disable_allclks(xdev);
+}
+
+static struct platform_driver xilinx_vdma_driver = {
+	.driver = {
+		.name = "xilinx-vdma",
+		.of_match_table = xilinx_dma_of_ids,
+	},
+	.probe = xilinx_dma_probe,
+	.remove = xilinx_dma_remove,
+};
+
+module_platform_driver(xilinx_vdma_driver);
+
+MODULE_AUTHOR("Xilinx, Inc.");
+MODULE_DESCRIPTION("Xilinx VDMA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
new file mode 100644
index 000000000..d9a3542c4
--- /dev/null
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -0,0 +1,1877 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Xilinx ZynqMP DPDMA Engine driver
+ *
+ * Copyright (C) 2015 - 2020 Xilinx, Inc.
+ *
+ * Author: Hyun Woo Kwon <hyun.kwon@xilinx.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/dma/xilinx_dpdma.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+
+#include <dt-bindings/dma/xlnx-zynqmp-dpdma.h>
+
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+/* DPDMA registers */
+#define XILINX_DPDMA_ERR_CTRL				0x000
+#define XILINX_DPDMA_ISR				0x004
+#define XILINX_DPDMA_IMR				0x008
+#define XILINX_DPDMA_IEN				0x00c
+#define XILINX_DPDMA_IDS				0x010
+#define XILINX_DPDMA_INTR_DESC_DONE(n)			BIT((n) + 0)
+#define XILINX_DPDMA_INTR_DESC_DONE_MASK		GENMASK(5, 0)
+#define XILINX_DPDMA_INTR_NO_OSTAND(n)			BIT((n) + 6)
+#define XILINX_DPDMA_INTR_NO_OSTAND_MASK		GENMASK(11, 6)
+#define XILINX_DPDMA_INTR_AXI_ERR(n)			BIT((n) + 12)
+#define XILINX_DPDMA_INTR_AXI_ERR_MASK			GENMASK(17, 12)
+#define XILINX_DPDMA_INTR_DESC_ERR(n)			BIT((n) + 16)
+#define XILINX_DPDMA_INTR_DESC_ERR_MASK			GENMASK(23, 18)
+#define XILINX_DPDMA_INTR_WR_CMD_FIFO_FULL		BIT(24)
+#define XILINX_DPDMA_INTR_WR_DATA_FIFO_FULL		BIT(25)
+#define XILINX_DPDMA_INTR_AXI_4K_CROSS			BIT(26)
+#define XILINX_DPDMA_INTR_VSYNC				BIT(27)
+#define XILINX_DPDMA_INTR_CHAN_ERR_MASK			0x00041000
+#define XILINX_DPDMA_INTR_CHAN_ERR			0x00fff000
+#define XILINX_DPDMA_INTR_GLOBAL_ERR			0x07000000
+#define XILINX_DPDMA_INTR_ERR_ALL			0x07fff000
+#define XILINX_DPDMA_INTR_CHAN_MASK			0x00041041
+#define XILINX_DPDMA_INTR_GLOBAL_MASK			0x0f000000
+#define XILINX_DPDMA_INTR_ALL				0x0fffffff
+#define XILINX_DPDMA_EISR				0x014
+#define XILINX_DPDMA_EIMR				0x018
+#define XILINX_DPDMA_EIEN				0x01c
+#define XILINX_DPDMA_EIDS				0x020
+#define XILINX_DPDMA_EINTR_INV_APB			BIT(0)
+#define XILINX_DPDMA_EINTR_RD_AXI_ERR(n)		BIT((n) + 1)
+#define XILINX_DPDMA_EINTR_RD_AXI_ERR_MASK		GENMASK(6, 1)
+#define XILINX_DPDMA_EINTR_PRE_ERR(n)			BIT((n) + 7)
+#define XILINX_DPDMA_EINTR_PRE_ERR_MASK			GENMASK(12, 7)
+#define XILINX_DPDMA_EINTR_CRC_ERR(n)			BIT((n) + 13)
+#define XILINX_DPDMA_EINTR_CRC_ERR_MASK			GENMASK(18, 13)
+#define XILINX_DPDMA_EINTR_WR_AXI_ERR(n)		BIT((n) + 19)
+#define XILINX_DPDMA_EINTR_WR_AXI_ERR_MASK		GENMASK(24, 19)
+#define XILINX_DPDMA_EINTR_DESC_DONE_ERR(n)		BIT((n) + 25)
+#define XILINX_DPDMA_EINTR_DESC_DONE_ERR_MASK		GENMASK(30, 25)
+#define XILINX_DPDMA_EINTR_RD_CMD_FIFO_FULL		BIT(32)
+#define XILINX_DPDMA_EINTR_CHAN_ERR_MASK		0x02082082
+#define XILINX_DPDMA_EINTR_CHAN_ERR			0x7ffffffe
+#define XILINX_DPDMA_EINTR_GLOBAL_ERR			0x80000001
+#define XILINX_DPDMA_EINTR_ALL				0xffffffff
+#define XILINX_DPDMA_CNTL				0x100
+#define XILINX_DPDMA_GBL				0x104
+#define XILINX_DPDMA_GBL_TRIG_MASK(n)			((n) << 0)
+#define XILINX_DPDMA_GBL_RETRIG_MASK(n)			((n) << 6)
+#define XILINX_DPDMA_ALC0_CNTL				0x108
+#define XILINX_DPDMA_ALC0_STATUS			0x10c
+#define XILINX_DPDMA_ALC0_MAX				0x110
+#define XILINX_DPDMA_ALC0_MIN				0x114
+#define XILINX_DPDMA_ALC0_ACC				0x118
+#define XILINX_DPDMA_ALC0_ACC_TRAN			0x11c
+#define XILINX_DPDMA_ALC1_CNTL				0x120
+#define XILINX_DPDMA_ALC1_STATUS			0x124
+#define XILINX_DPDMA_ALC1_MAX				0x128
+#define XILINX_DPDMA_ALC1_MIN				0x12c
+#define XILINX_DPDMA_ALC1_ACC				0x130
+#define XILINX_DPDMA_ALC1_ACC_TRAN			0x134
+
+/* Channel register */
+#define XILINX_DPDMA_CH_BASE				0x200
+#define XILINX_DPDMA_CH_OFFSET				0x100
+#define XILINX_DPDMA_CH_DESC_START_ADDRE		0x000
+#define XILINX_DPDMA_CH_DESC_START_ADDRE_MASK		GENMASK(15, 0)
+#define XILINX_DPDMA_CH_DESC_START_ADDR			0x004
+#define XILINX_DPDMA_CH_DESC_NEXT_ADDRE			0x008
+#define XILINX_DPDMA_CH_DESC_NEXT_ADDR			0x00c
+#define XILINX_DPDMA_CH_PYLD_CUR_ADDRE			0x010
+#define XILINX_DPDMA_CH_PYLD_CUR_ADDR			0x014
+#define XILINX_DPDMA_CH_CNTL				0x018
+#define XILINX_DPDMA_CH_CNTL_ENABLE			BIT(0)
+#define XILINX_DPDMA_CH_CNTL_PAUSE			BIT(1)
+#define XILINX_DPDMA_CH_CNTL_QOS_DSCR_WR_MASK		GENMASK(5, 2)
+#define XILINX_DPDMA_CH_CNTL_QOS_DSCR_RD_MASK		GENMASK(9, 6)
+#define XILINX_DPDMA_CH_CNTL_QOS_DATA_RD_MASK		GENMASK(13, 10)
+#define XILINX_DPDMA_CH_CNTL_QOS_VID_CLASS		11
+#define XILINX_DPDMA_CH_STATUS				0x01c
+#define XILINX_DPDMA_CH_STATUS_OTRAN_CNT_MASK		GENMASK(24, 21)
+#define XILINX_DPDMA_CH_VDO				0x020
+#define XILINX_DPDMA_CH_PYLD_SZ				0x024
+#define XILINX_DPDMA_CH_DESC_ID				0x028
+#define XILINX_DPDMA_CH_DESC_ID_MASK			GENMASK(15, 0)
+
+/* DPDMA descriptor fields */
+#define XILINX_DPDMA_DESC_CONTROL_PREEMBLE		0xa5
+#define XILINX_DPDMA_DESC_CONTROL_COMPLETE_INTR		BIT(8)
+#define XILINX_DPDMA_DESC_CONTROL_DESC_UPDATE		BIT(9)
+#define XILINX_DPDMA_DESC_CONTROL_IGNORE_DONE		BIT(10)
+#define XILINX_DPDMA_DESC_CONTROL_FRAG_MODE		BIT(18)
+#define XILINX_DPDMA_DESC_CONTROL_LAST			BIT(19)
+#define XILINX_DPDMA_DESC_CONTROL_ENABLE_CRC		BIT(20)
+#define XILINX_DPDMA_DESC_CONTROL_LAST_OF_FRAME		BIT(21)
+#define XILINX_DPDMA_DESC_ID_MASK			GENMASK(15, 0)
+#define XILINX_DPDMA_DESC_HSIZE_STRIDE_HSIZE_MASK	GENMASK(17, 0)
+#define XILINX_DPDMA_DESC_HSIZE_STRIDE_STRIDE_MASK	GENMASK(31, 18)
+#define XILINX_DPDMA_DESC_ADDR_EXT_NEXT_ADDR_MASK	GENMASK(15, 0)
+#define XILINX_DPDMA_DESC_ADDR_EXT_SRC_ADDR_MASK	GENMASK(31, 16)
+
+#define XILINX_DPDMA_ALIGN_BYTES			256
+#define XILINX_DPDMA_LINESIZE_ALIGN_BITS		128
+
+#define XILINX_DPDMA_NUM_CHAN				6
+
+struct xilinx_dpdma_chan;
+
+/**
+ * struct xilinx_dpdma_hw_desc - DPDMA hardware descriptor
+ * @control: control configuration field
+ * @desc_id: descriptor ID
+ * @xfer_size: transfer size
+ * @hsize_stride: horizontal size and stride
+ * @timestamp_lsb: LSB of time stamp
+ * @timestamp_msb: MSB of time stamp
+ * @addr_ext: upper 16 bit of 48 bit address (next_desc and src_addr)
+ * @next_desc: next descriptor 32 bit address
+ * @src_addr: payload source address (1st page, 32 LSB)
+ * @addr_ext_23: payload source address (2nd and 3rd pages, 16 LSBs)
+ * @addr_ext_45: payload source address (4th and 5th pages, 16 LSBs)
+ * @src_addr2: payload source address (2nd page, 32 LSB)
+ * @src_addr3: payload source address (3rd page, 32 LSB)
+ * @src_addr4: payload source address (4th page, 32 LSB)
+ * @src_addr5: payload source address (5th page, 32 LSB)
+ * @crc: descriptor CRC
+ */
+struct xilinx_dpdma_hw_desc {
+	u32 control;
+	u32 desc_id;
+	u32 xfer_size;
+	u32 hsize_stride;
+	u32 timestamp_lsb;
+	u32 timestamp_msb;
+	u32 addr_ext;
+	u32 next_desc;
+	u32 src_addr;
+	u32 addr_ext_23;
+	u32 addr_ext_45;
+	u32 src_addr2;
+	u32 src_addr3;
+	u32 src_addr4;
+	u32 src_addr5;
+	u32 crc;
+} __aligned(XILINX_DPDMA_ALIGN_BYTES);
+
+/**
+ * struct xilinx_dpdma_sw_desc - DPDMA software descriptor
+ * @hw: DPDMA hardware descriptor
+ * @node: list node for software descriptors
+ * @dma_addr: DMA address of the software descriptor
+ */
+struct xilinx_dpdma_sw_desc {
+	struct xilinx_dpdma_hw_desc hw;
+	struct list_head node;
+	dma_addr_t dma_addr;
+};
+
+/**
+ * struct xilinx_dpdma_tx_desc - DPDMA transaction descriptor
+ * @vdesc: virtual DMA descriptor
+ * @chan: DMA channel
+ * @descriptors: list of software descriptors
+ * @error: an error has been detected with this descriptor
+ */
+struct xilinx_dpdma_tx_desc {
+	struct virt_dma_desc vdesc;
+	struct xilinx_dpdma_chan *chan;
+	struct list_head descriptors;
+	bool error;
+};
+
+#define to_dpdma_tx_desc(_desc) \
+	container_of(_desc, struct xilinx_dpdma_tx_desc, vdesc)
+
+/**
+ * struct xilinx_dpdma_chan - DPDMA channel
+ * @vchan: virtual DMA channel
+ * @reg: register base address
+ * @id: channel ID
+ * @wait_to_stop: queue to wait for outstanding transactions before stopping
+ * @running: true if the channel is running
+ * @first_frame: flag for the first frame of stream
+ * @video_group: flag if multi-channel operation is needed for video channels
+ * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before
+ *        @vchan.lock, if both are to be held.
+ * @desc_pool: descriptor allocation pool
+ * @err_task: error IRQ bottom half handler
+ * @desc: References to descriptors being processed
+ * @desc.pending: Descriptor schedule to the hardware, pending execution
+ * @desc.active: Descriptor being executed by the hardware
+ * @xdev: DPDMA device
+ */
+struct xilinx_dpdma_chan {
+	struct virt_dma_chan vchan;
+	void __iomem *reg;
+	unsigned int id;
+
+	wait_queue_head_t wait_to_stop;
+	bool running;
+	bool first_frame;
+	bool video_group;
+
+	spinlock_t lock; /* lock to access struct xilinx_dpdma_chan */
+	struct dma_pool *desc_pool;
+	struct tasklet_struct err_task;
+
+	struct {
+		struct xilinx_dpdma_tx_desc *pending;
+		struct xilinx_dpdma_tx_desc *active;
+	} desc;
+
+	struct xilinx_dpdma_device *xdev;
+};
+
+#define to_xilinx_chan(_chan) \
+	container_of(_chan, struct xilinx_dpdma_chan, vchan.chan)
+
+/**
+ * struct xilinx_dpdma_device - DPDMA device
+ * @common: generic dma device structure
+ * @reg: register base address
+ * @dev: generic device structure
+ * @irq: the interrupt number
+ * @axi_clk: axi clock
+ * @chan: DPDMA channels
+ * @ext_addr: flag for 64 bit system (48 bit addressing)
+ */
+struct xilinx_dpdma_device {
+	struct dma_device common;
+	void __iomem *reg;
+	struct device *dev;
+	int irq;
+
+	struct clk *axi_clk;
+	struct xilinx_dpdma_chan *chan[XILINX_DPDMA_NUM_CHAN];
+
+	bool ext_addr;
+};
+
+/* -----------------------------------------------------------------------------
+ * DebugFS
+ */
+#define XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE	32
+#define XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR	"65535"
+
+/* Match xilinx_dpdma_testcases vs dpdma_debugfs_reqs[] entry */
+enum xilinx_dpdma_testcases {
+	DPDMA_TC_INTR_DONE,
+	DPDMA_TC_NONE
+};
+
+struct xilinx_dpdma_debugfs {
+	enum xilinx_dpdma_testcases testcase;
+	u16 xilinx_dpdma_irq_done_count;
+	unsigned int chan_id;
+};
+
+static struct xilinx_dpdma_debugfs dpdma_debugfs;
+struct xilinx_dpdma_debugfs_request {
+	const char *name;
+	enum xilinx_dpdma_testcases tc;
+	ssize_t (*read)(char *buf);
+	int (*write)(char *args);
+};
+
+static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_FS) && chan->id == dpdma_debugfs.chan_id)
+		dpdma_debugfs.xilinx_dpdma_irq_done_count++;
+}
+
+static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
+{
+	size_t out_str_len;
+
+	dpdma_debugfs.testcase = DPDMA_TC_NONE;
+
+	out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
+	out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
+			    out_str_len + 1);
+	snprintf(buf, out_str_len, "%d",
+		 dpdma_debugfs.xilinx_dpdma_irq_done_count);
+
+	return 0;
+}
+
+static int xilinx_dpdma_debugfs_desc_done_irq_write(char *args)
+{
+	char *arg;
+	int ret;
+	u32 id;
+
+	arg = strsep(&args, " ");
+	if (!arg || strncasecmp(arg, "start", 5))
+		return -EINVAL;
+
+	arg = strsep(&args, " ");
+	if (!arg)
+		return -EINVAL;
+
+	ret = kstrtou32(arg, 0, &id);
+	if (ret < 0)
+		return ret;
+
+	if (id < ZYNQMP_DPDMA_VIDEO0 || id > ZYNQMP_DPDMA_AUDIO1)
+		return -EINVAL;
+
+	dpdma_debugfs.testcase = DPDMA_TC_INTR_DONE;
+	dpdma_debugfs.xilinx_dpdma_irq_done_count = 0;
+	dpdma_debugfs.chan_id = id;
+
+	return 0;
+}
+
+/* Match xilinx_dpdma_testcases vs dpdma_debugfs_reqs[] entry */
+static struct xilinx_dpdma_debugfs_request dpdma_debugfs_reqs[] = {
+	{
+		.name = "DESCRIPTOR_DONE_INTR",
+		.tc = DPDMA_TC_INTR_DONE,
+		.read = xilinx_dpdma_debugfs_desc_done_irq_read,
+		.write = xilinx_dpdma_debugfs_desc_done_irq_write,
+	},
+};
+
+static ssize_t xilinx_dpdma_debugfs_read(struct file *f, char __user *buf,
+					 size_t size, loff_t *pos)
+{
+	enum xilinx_dpdma_testcases testcase;
+	char *kern_buff;
+	int ret = 0;
+
+	if (*pos != 0 || size <= 0)
+		return -EINVAL;
+
+	kern_buff = kzalloc(XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE, GFP_KERNEL);
+	if (!kern_buff) {
+		dpdma_debugfs.testcase = DPDMA_TC_NONE;
+		return -ENOMEM;
+	}
+
+	testcase = READ_ONCE(dpdma_debugfs.testcase);
+	if (testcase != DPDMA_TC_NONE) {
+		ret = dpdma_debugfs_reqs[testcase].read(kern_buff);
+		if (ret < 0)
+			goto done;
+	} else {
+		strscpy(kern_buff, "No testcase executed",
+			XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE);
+	}
+
+	size = min(size, strlen(kern_buff));
+	if (copy_to_user(buf, kern_buff, size))
+		ret = -EFAULT;
+
+done:
+	kfree(kern_buff);
+	if (ret)
+		return ret;
+
+	*pos = size + 1;
+	return size;
+}
+
+static ssize_t xilinx_dpdma_debugfs_write(struct file *f,
+					  const char __user *buf, size_t size,
+					  loff_t *pos)
+{
+	char *kern_buff, *kern_buff_start;
+	char *testcase;
+	unsigned int i;
+	int ret;
+
+	if (*pos != 0 || size <= 0)
+		return -EINVAL;
+
+	/* Supporting single instance of test as of now. */
+	if (dpdma_debugfs.testcase != DPDMA_TC_NONE)
+		return -EBUSY;
+
+	kern_buff = kzalloc(size, GFP_KERNEL);
+	if (!kern_buff)
+		return -ENOMEM;
+	kern_buff_start = kern_buff;
+
+	ret = strncpy_from_user(kern_buff, buf, size);
+	if (ret < 0)
+		goto done;
+
+	/* Read the testcase name from a user request. */
+	testcase = strsep(&kern_buff, " ");
+
+	for (i = 0; i < ARRAY_SIZE(dpdma_debugfs_reqs); i++) {
+		if (!strcasecmp(testcase, dpdma_debugfs_reqs[i].name))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(dpdma_debugfs_reqs)) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	ret = dpdma_debugfs_reqs[i].write(kern_buff);
+	if (ret < 0)
+		goto done;
+
+	ret = size;
+
+done:
+	kfree(kern_buff_start);
+	return ret;
+}
+
+static const struct file_operations fops_xilinx_dpdma_dbgfs = {
+	.owner = THIS_MODULE,
+	.read = xilinx_dpdma_debugfs_read,
+	.write = xilinx_dpdma_debugfs_write,
+};
+
+static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev)
+{
+	struct dentry *dent;
+
+	dpdma_debugfs.testcase = DPDMA_TC_NONE;
+
+	dent = debugfs_create_file("testcase", 0444, xdev->common.dbg_dev_root,
+				   NULL, &fops_xilinx_dpdma_dbgfs);
+	if (IS_ERR(dent))
+		dev_err(xdev->dev, "Failed to create debugfs testcase file\n");
+}
+
+/* -----------------------------------------------------------------------------
+ * I/O Accessors
+ */
+
+static inline u32 dpdma_read(void __iomem *base, u32 offset)
+{
+	return ioread32(base + offset);
+}
+
+static inline void dpdma_write(void __iomem *base, u32 offset, u32 val)
+{
+	iowrite32(val, base + offset);
+}
+
+static inline void dpdma_clr(void __iomem *base, u32 offset, u32 clr)
+{
+	dpdma_write(base, offset, dpdma_read(base, offset) & ~clr);
+}
+
+static inline void dpdma_set(void __iomem *base, u32 offset, u32 set)
+{
+	dpdma_write(base, offset, dpdma_read(base, offset) | set);
+}
+
+/* -----------------------------------------------------------------------------
+ * Descriptor Operations
+ */
+
+/**
+ * xilinx_dpdma_sw_desc_set_dma_addrs - Set DMA addresses in the descriptor
+ * @xdev: DPDMA device
+ * @sw_desc: The software descriptor in which to set DMA addresses
+ * @prev: The previous descriptor
+ * @dma_addr: array of dma addresses
+ * @num_src_addr: number of addresses in @dma_addr
+ *
+ * Set all the DMA addresses in the hardware descriptor corresponding to @dev
+ * from @dma_addr. If a previous descriptor is specified in @prev, its next
+ * descriptor DMA address is set to the DMA address of @sw_desc. @prev may be
+ * identical to @sw_desc for cyclic transfers.
+ */
+static void xilinx_dpdma_sw_desc_set_dma_addrs(struct xilinx_dpdma_device *xdev,
+					       struct xilinx_dpdma_sw_desc *sw_desc,
+					       struct xilinx_dpdma_sw_desc *prev,
+					       dma_addr_t dma_addr[],
+					       unsigned int num_src_addr)
+{
+	struct xilinx_dpdma_hw_desc *hw_desc = &sw_desc->hw;
+	unsigned int i;
+
+	hw_desc->src_addr = lower_32_bits(dma_addr[0]);
+	if (xdev->ext_addr)
+		hw_desc->addr_ext |=
+			FIELD_PREP(XILINX_DPDMA_DESC_ADDR_EXT_SRC_ADDR_MASK,
+				   upper_32_bits(dma_addr[0]));
+
+	for (i = 1; i < num_src_addr; i++) {
+		u32 *addr = &hw_desc->src_addr2;
+
+		addr[i - 1] = lower_32_bits(dma_addr[i]);
+
+		if (xdev->ext_addr) {
+			u32 *addr_ext = &hw_desc->addr_ext_23;
+			u32 addr_msb;
+
+			addr_msb = upper_32_bits(dma_addr[i]) & GENMASK(15, 0);
+			addr_msb <<= 16 * ((i - 1) % 2);
+			addr_ext[(i - 1) / 2] |= addr_msb;
+		}
+	}
+
+	if (!prev)
+		return;
+
+	prev->hw.next_desc = lower_32_bits(sw_desc->dma_addr);
+	if (xdev->ext_addr)
+		prev->hw.addr_ext |=
+			FIELD_PREP(XILINX_DPDMA_DESC_ADDR_EXT_NEXT_ADDR_MASK,
+				   upper_32_bits(sw_desc->dma_addr));
+}
+
+/**
+ * xilinx_dpdma_chan_alloc_sw_desc - Allocate a software descriptor
+ * @chan: DPDMA channel
+ *
+ * Allocate a software descriptor from the channel's descriptor pool.
+ *
+ * Return: a software descriptor or NULL.
+ */
+static struct xilinx_dpdma_sw_desc *
+xilinx_dpdma_chan_alloc_sw_desc(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_sw_desc *sw_desc;
+	dma_addr_t dma_addr;
+
+	sw_desc = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &dma_addr);
+	if (!sw_desc)
+		return NULL;
+
+	sw_desc->dma_addr = dma_addr;
+
+	return sw_desc;
+}
+
+/**
+ * xilinx_dpdma_chan_free_sw_desc - Free a software descriptor
+ * @chan: DPDMA channel
+ * @sw_desc: software descriptor to free
+ *
+ * Free a software descriptor from the channel's descriptor pool.
+ */
+static void
+xilinx_dpdma_chan_free_sw_desc(struct xilinx_dpdma_chan *chan,
+			       struct xilinx_dpdma_sw_desc *sw_desc)
+{
+	dma_pool_free(chan->desc_pool, sw_desc, sw_desc->dma_addr);
+}
+
+/**
+ * xilinx_dpdma_chan_dump_tx_desc - Dump a tx descriptor
+ * @chan: DPDMA channel
+ * @tx_desc: tx descriptor to dump
+ *
+ * Dump contents of a tx descriptor
+ */
+static void xilinx_dpdma_chan_dump_tx_desc(struct xilinx_dpdma_chan *chan,
+					   struct xilinx_dpdma_tx_desc *tx_desc)
+{
+	struct xilinx_dpdma_sw_desc *sw_desc;
+	struct device *dev = chan->xdev->dev;
+	unsigned int i = 0;
+
+	dev_dbg(dev, "------- TX descriptor dump start -------\n");
+	dev_dbg(dev, "------- channel ID = %d -------\n", chan->id);
+
+	list_for_each_entry(sw_desc, &tx_desc->descriptors, node) {
+		struct xilinx_dpdma_hw_desc *hw_desc = &sw_desc->hw;
+
+		dev_dbg(dev, "------- HW descriptor %d -------\n", i++);
+		dev_dbg(dev, "descriptor DMA addr: %pad\n", &sw_desc->dma_addr);
+		dev_dbg(dev, "control: 0x%08x\n", hw_desc->control);
+		dev_dbg(dev, "desc_id: 0x%08x\n", hw_desc->desc_id);
+		dev_dbg(dev, "xfer_size: 0x%08x\n", hw_desc->xfer_size);
+		dev_dbg(dev, "hsize_stride: 0x%08x\n", hw_desc->hsize_stride);
+		dev_dbg(dev, "timestamp_lsb: 0x%08x\n", hw_desc->timestamp_lsb);
+		dev_dbg(dev, "timestamp_msb: 0x%08x\n", hw_desc->timestamp_msb);
+		dev_dbg(dev, "addr_ext: 0x%08x\n", hw_desc->addr_ext);
+		dev_dbg(dev, "next_desc: 0x%08x\n", hw_desc->next_desc);
+		dev_dbg(dev, "src_addr: 0x%08x\n", hw_desc->src_addr);
+		dev_dbg(dev, "addr_ext_23: 0x%08x\n", hw_desc->addr_ext_23);
+		dev_dbg(dev, "addr_ext_45: 0x%08x\n", hw_desc->addr_ext_45);
+		dev_dbg(dev, "src_addr2: 0x%08x\n", hw_desc->src_addr2);
+		dev_dbg(dev, "src_addr3: 0x%08x\n", hw_desc->src_addr3);
+		dev_dbg(dev, "src_addr4: 0x%08x\n", hw_desc->src_addr4);
+		dev_dbg(dev, "src_addr5: 0x%08x\n", hw_desc->src_addr5);
+		dev_dbg(dev, "crc: 0x%08x\n", hw_desc->crc);
+	}
+
+	dev_dbg(dev, "------- TX descriptor dump end -------\n");
+}
+
+/**
+ * xilinx_dpdma_chan_alloc_tx_desc - Allocate a transaction descriptor
+ * @chan: DPDMA channel
+ *
+ * Allocate a tx descriptor.
+ *
+ * Return: a tx descriptor or NULL.
+ */
+static struct xilinx_dpdma_tx_desc *
+xilinx_dpdma_chan_alloc_tx_desc(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_tx_desc *tx_desc;
+
+	tx_desc = kzalloc_obj(*tx_desc, GFP_NOWAIT);
+	if (!tx_desc)
+		return NULL;
+
+	INIT_LIST_HEAD(&tx_desc->descriptors);
+	tx_desc->chan = chan;
+	tx_desc->error = false;
+
+	return tx_desc;
+}
+
+/**
+ * xilinx_dpdma_chan_free_tx_desc - Free a virtual DMA descriptor
+ * @vdesc: virtual DMA descriptor
+ *
+ * Free the virtual DMA descriptor @vdesc including its software descriptors.
+ */
+static void xilinx_dpdma_chan_free_tx_desc(struct virt_dma_desc *vdesc)
+{
+	struct xilinx_dpdma_sw_desc *sw_desc, *next;
+	struct xilinx_dpdma_tx_desc *desc;
+
+	if (!vdesc)
+		return;
+
+	desc = to_dpdma_tx_desc(vdesc);
+
+	list_for_each_entry_safe(sw_desc, next, &desc->descriptors, node) {
+		list_del(&sw_desc->node);
+		xilinx_dpdma_chan_free_sw_desc(desc->chan, sw_desc);
+	}
+
+	kfree(desc);
+}
+
+/**
+ * xilinx_dpdma_chan_prep_cyclic - Prepare a cyclic dma descriptor
+ * @chan: DPDMA channel
+ * @buf_addr: buffer address
+ * @buf_len: buffer length
+ * @period_len: number of periods
+ * @flags: tx flags argument passed in to prepare function
+ *
+ * Prepare a tx descriptor incudling internal software/hardware descriptors
+ * for the given cyclic transaction.
+ *
+ * Return: A dma async tx descriptor on success, or NULL.
+ */
+static struct dma_async_tx_descriptor *
+xilinx_dpdma_chan_prep_cyclic(struct xilinx_dpdma_chan *chan,
+			      dma_addr_t buf_addr, size_t buf_len,
+			      size_t period_len, unsigned long flags)
+{
+	struct xilinx_dpdma_tx_desc *tx_desc;
+	struct xilinx_dpdma_sw_desc *sw_desc, *last = NULL;
+	unsigned int periods = buf_len / period_len;
+	unsigned int i;
+
+	tx_desc = xilinx_dpdma_chan_alloc_tx_desc(chan);
+	if (!tx_desc)
+		return NULL;
+
+	for (i = 0; i < periods; i++) {
+		struct xilinx_dpdma_hw_desc *hw_desc;
+
+		if (!IS_ALIGNED(buf_addr, XILINX_DPDMA_ALIGN_BYTES)) {
+			dev_err(chan->xdev->dev,
+				"buffer should be aligned at %d B\n",
+				XILINX_DPDMA_ALIGN_BYTES);
+			goto error;
+		}
+
+		sw_desc = xilinx_dpdma_chan_alloc_sw_desc(chan);
+		if (!sw_desc)
+			goto error;
+
+		xilinx_dpdma_sw_desc_set_dma_addrs(chan->xdev, sw_desc, last,
+						   &buf_addr, 1);
+		hw_desc = &sw_desc->hw;
+		hw_desc->xfer_size = period_len;
+		hw_desc->hsize_stride =
+			FIELD_PREP(XILINX_DPDMA_DESC_HSIZE_STRIDE_HSIZE_MASK,
+				   period_len) |
+			FIELD_PREP(XILINX_DPDMA_DESC_HSIZE_STRIDE_STRIDE_MASK,
+				   period_len);
+		hw_desc->control = XILINX_DPDMA_DESC_CONTROL_PREEMBLE |
+				   XILINX_DPDMA_DESC_CONTROL_IGNORE_DONE |
+				   XILINX_DPDMA_DESC_CONTROL_COMPLETE_INTR;
+
+		list_add_tail(&sw_desc->node, &tx_desc->descriptors);
+
+		buf_addr += period_len;
+		last = sw_desc;
+	}
+
+	sw_desc = list_first_entry(&tx_desc->descriptors,
+				   struct xilinx_dpdma_sw_desc, node);
+	last->hw.next_desc = lower_32_bits(sw_desc->dma_addr);
+	if (chan->xdev->ext_addr)
+		last->hw.addr_ext |=
+			FIELD_PREP(XILINX_DPDMA_DESC_ADDR_EXT_NEXT_ADDR_MASK,
+				   upper_32_bits(sw_desc->dma_addr));
+
+	last->hw.control |= XILINX_DPDMA_DESC_CONTROL_LAST_OF_FRAME;
+
+	return vchan_tx_prep(&chan->vchan, &tx_desc->vdesc, flags);
+
+error:
+	xilinx_dpdma_chan_free_tx_desc(&tx_desc->vdesc);
+
+	return NULL;
+}
+
+/**
+ * xilinx_dpdma_chan_prep_interleaved_dma - Prepare an interleaved dma
+ *					    descriptor
+ * @chan: DPDMA channel
+ * @xt: dma interleaved template
+ *
+ * Prepare a tx descriptor including internal software/hardware descriptors
+ * based on @xt.
+ *
+ * Return: A DPDMA TX descriptor on success, or NULL.
+ */
+static struct xilinx_dpdma_tx_desc *
+xilinx_dpdma_chan_prep_interleaved_dma(struct xilinx_dpdma_chan *chan,
+				       struct dma_interleaved_template *xt)
+{
+	struct xilinx_dpdma_tx_desc *tx_desc;
+	struct xilinx_dpdma_sw_desc *sw_desc;
+	struct xilinx_dpdma_hw_desc *hw_desc;
+	size_t hsize = xt->sgl[0].size;
+	size_t stride = hsize + xt->sgl[0].icg;
+
+	if (!IS_ALIGNED(xt->src_start, XILINX_DPDMA_ALIGN_BYTES)) {
+		dev_err(chan->xdev->dev,
+			"chan%u: buffer should be aligned at %d B\n",
+			chan->id, XILINX_DPDMA_ALIGN_BYTES);
+		return NULL;
+	}
+
+	tx_desc = xilinx_dpdma_chan_alloc_tx_desc(chan);
+	if (!tx_desc)
+		return NULL;
+
+	sw_desc = xilinx_dpdma_chan_alloc_sw_desc(chan);
+	if (!sw_desc) {
+		xilinx_dpdma_chan_free_tx_desc(&tx_desc->vdesc);
+		return NULL;
+	}
+
+	xilinx_dpdma_sw_desc_set_dma_addrs(chan->xdev, sw_desc, sw_desc,
+					   &xt->src_start, 1);
+
+	hw_desc = &sw_desc->hw;
+	hsize = ALIGN(hsize, XILINX_DPDMA_LINESIZE_ALIGN_BITS / 8);
+	hw_desc->xfer_size = hsize * xt->numf;
+	hw_desc->hsize_stride =
+		FIELD_PREP(XILINX_DPDMA_DESC_HSIZE_STRIDE_HSIZE_MASK, hsize) |
+		FIELD_PREP(XILINX_DPDMA_DESC_HSIZE_STRIDE_STRIDE_MASK,
+			   stride / 16);
+	hw_desc->control |= XILINX_DPDMA_DESC_CONTROL_PREEMBLE;
+	hw_desc->control |= XILINX_DPDMA_DESC_CONTROL_COMPLETE_INTR;
+	hw_desc->control |= XILINX_DPDMA_DESC_CONTROL_IGNORE_DONE;
+	hw_desc->control |= XILINX_DPDMA_DESC_CONTROL_LAST_OF_FRAME;
+
+	list_add_tail(&sw_desc->node, &tx_desc->descriptors);
+
+	return tx_desc;
+}
+
+/* -----------------------------------------------------------------------------
+ * DPDMA Channel Operations
+ */
+
+/**
+ * xilinx_dpdma_chan_enable - Enable the channel
+ * @chan: DPDMA channel
+ *
+ * Enable the channel and its interrupts. Set the QoS values for video class.
+ */
+static void xilinx_dpdma_chan_enable(struct xilinx_dpdma_chan *chan)
+{
+	u32 reg;
+
+	reg = (XILINX_DPDMA_INTR_CHAN_MASK << chan->id)
+	    | XILINX_DPDMA_INTR_GLOBAL_MASK;
+	dpdma_write(chan->xdev->reg, XILINX_DPDMA_IEN, reg);
+	reg = (XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id)
+	    | XILINX_DPDMA_INTR_GLOBAL_ERR;
+	dpdma_write(chan->xdev->reg, XILINX_DPDMA_EIEN, reg);
+
+	reg = XILINX_DPDMA_CH_CNTL_ENABLE
+	    | FIELD_PREP(XILINX_DPDMA_CH_CNTL_QOS_DSCR_WR_MASK,
+			 XILINX_DPDMA_CH_CNTL_QOS_VID_CLASS)
+	    | FIELD_PREP(XILINX_DPDMA_CH_CNTL_QOS_DSCR_RD_MASK,
+			 XILINX_DPDMA_CH_CNTL_QOS_VID_CLASS)
+	    | FIELD_PREP(XILINX_DPDMA_CH_CNTL_QOS_DATA_RD_MASK,
+			 XILINX_DPDMA_CH_CNTL_QOS_VID_CLASS);
+	dpdma_set(chan->reg, XILINX_DPDMA_CH_CNTL, reg);
+}
+
+/**
+ * xilinx_dpdma_chan_disable - Disable the channel
+ * @chan: DPDMA channel
+ *
+ * Disable the channel and its interrupts.
+ */
+static void xilinx_dpdma_chan_disable(struct xilinx_dpdma_chan *chan)
+{
+	u32 reg;
+
+	reg = XILINX_DPDMA_INTR_CHAN_MASK << chan->id;
+	dpdma_write(chan->xdev->reg, XILINX_DPDMA_IEN, reg);
+	reg = XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id;
+	dpdma_write(chan->xdev->reg, XILINX_DPDMA_EIEN, reg);
+
+	dpdma_clr(chan->reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE);
+}
+
+/**
+ * xilinx_dpdma_chan_pause - Pause the channel
+ * @chan: DPDMA channel
+ *
+ * Pause the channel.
+ */
+static void xilinx_dpdma_chan_pause(struct xilinx_dpdma_chan *chan)
+{
+	dpdma_set(chan->reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_PAUSE);
+}
+
+/**
+ * xilinx_dpdma_chan_unpause - Unpause the channel
+ * @chan: DPDMA channel
+ *
+ * Unpause the channel.
+ */
+static void xilinx_dpdma_chan_unpause(struct xilinx_dpdma_chan *chan)
+{
+	dpdma_clr(chan->reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_PAUSE);
+}
+
+static u32 xilinx_dpdma_chan_video_group_ready(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_device *xdev = chan->xdev;
+	u32 channels = 0;
+	unsigned int i;
+
+	for (i = ZYNQMP_DPDMA_VIDEO0; i <= ZYNQMP_DPDMA_VIDEO2; i++) {
+		if (xdev->chan[i]->video_group && !xdev->chan[i]->running)
+			return 0;
+
+		if (xdev->chan[i]->video_group)
+			channels |= BIT(i);
+	}
+
+	return channels;
+}
+
+/**
+ * xilinx_dpdma_chan_queue_transfer - Queue the next transfer
+ * @chan: DPDMA channel
+ *
+ * Queue the next descriptor, if any, to the hardware. If the channel is
+ * stopped, start it first. Otherwise retrigger it with the next descriptor.
+ */
+static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_device *xdev = chan->xdev;
+	struct xilinx_dpdma_sw_desc *sw_desc;
+	struct xilinx_dpdma_tx_desc *desc;
+	struct virt_dma_desc *vdesc;
+	u32 reg, channels;
+	bool first_frame;
+
+	lockdep_assert_held(&chan->lock);
+
+	if (chan->desc.pending)
+		return;
+
+	if (!chan->running) {
+		xilinx_dpdma_chan_unpause(chan);
+		xilinx_dpdma_chan_enable(chan);
+		chan->first_frame = true;
+		chan->running = true;
+	}
+
+	vdesc = vchan_next_desc(&chan->vchan);
+	if (!vdesc)
+		return;
+
+	desc = to_dpdma_tx_desc(vdesc);
+	chan->desc.pending = desc;
+	list_del(&desc->vdesc.node);
+
+	/*
+	 * Assign the cookie to descriptors in this transaction. Only 16 bit
+	 * will be used, but it should be enough.
+	 */
+	list_for_each_entry(sw_desc, &desc->descriptors, node)
+		sw_desc->hw.desc_id = desc->vdesc.tx.cookie
+				    & XILINX_DPDMA_CH_DESC_ID_MASK;
+
+	sw_desc = list_first_entry(&desc->descriptors,
+				   struct xilinx_dpdma_sw_desc, node);
+	dpdma_write(chan->reg, XILINX_DPDMA_CH_DESC_START_ADDR,
+		    lower_32_bits(sw_desc->dma_addr));
+	if (xdev->ext_addr)
+		dpdma_write(chan->reg, XILINX_DPDMA_CH_DESC_START_ADDRE,
+			    FIELD_PREP(XILINX_DPDMA_CH_DESC_START_ADDRE_MASK,
+				       upper_32_bits(sw_desc->dma_addr)));
+
+	first_frame = chan->first_frame;
+	chan->first_frame = false;
+
+	if (chan->video_group) {
+		channels = xilinx_dpdma_chan_video_group_ready(chan);
+		/*
+		 * Trigger the transfer only when all channels in the group are
+		 * ready.
+		 */
+		if (!channels)
+			return;
+	} else {
+		channels = BIT(chan->id);
+	}
+
+	if (first_frame)
+		reg = XILINX_DPDMA_GBL_TRIG_MASK(channels);
+	else
+		reg = XILINX_DPDMA_GBL_RETRIG_MASK(channels);
+
+	dpdma_write(xdev->reg, XILINX_DPDMA_GBL, reg);
+}
+
+/**
+ * xilinx_dpdma_chan_ostand - Number of outstanding transactions
+ * @chan: DPDMA channel
+ *
+ * Read and return the number of outstanding transactions from register.
+ *
+ * Return: Number of outstanding transactions from the status register.
+ */
+static u32 xilinx_dpdma_chan_ostand(struct xilinx_dpdma_chan *chan)
+{
+	return FIELD_GET(XILINX_DPDMA_CH_STATUS_OTRAN_CNT_MASK,
+			 dpdma_read(chan->reg, XILINX_DPDMA_CH_STATUS));
+}
+
+/**
+ * xilinx_dpdma_chan_notify_no_ostand - Notify no outstanding transaction event
+ * @chan: DPDMA channel
+ *
+ * Notify waiters for no outstanding event, so waiters can stop the channel
+ * safely. This function is supposed to be called when 'no outstanding'
+ * interrupt is generated. The 'no outstanding' interrupt is disabled and
+ * should be re-enabled when this event is handled. If the channel status
+ * register still shows some number of outstanding transactions, the interrupt
+ * remains enabled.
+ *
+ * Return: 0 on success. On failure, -EWOULDBLOCK if there's still outstanding
+ * transaction(s).
+ */
+static int xilinx_dpdma_chan_notify_no_ostand(struct xilinx_dpdma_chan *chan)
+{
+	u32 cnt;
+
+	cnt = xilinx_dpdma_chan_ostand(chan);
+	if (cnt) {
+		dev_dbg(chan->xdev->dev,
+			"chan%u: %d outstanding transactions\n",
+			chan->id, cnt);
+		return -EWOULDBLOCK;
+	}
+
+	/* Disable 'no outstanding' interrupt */
+	dpdma_write(chan->xdev->reg, XILINX_DPDMA_IDS,
+		    XILINX_DPDMA_INTR_NO_OSTAND(chan->id));
+	wake_up(&chan->wait_to_stop);
+
+	return 0;
+}
+
+/**
+ * xilinx_dpdma_chan_wait_no_ostand - Wait for the no outstanding irq
+ * @chan: DPDMA channel
+ *
+ * Wait for the no outstanding transaction interrupt. This functions can sleep
+ * for 50ms.
+ *
+ * Return: 0 on success. On failure, -ETIMEOUT for time out, or the error code
+ * from wait_event_interruptible_timeout().
+ */
+static int xilinx_dpdma_chan_wait_no_ostand(struct xilinx_dpdma_chan *chan)
+{
+	int ret;
+
+	/* Wait for a no outstanding transaction interrupt upto 50msec */
+	ret = wait_event_interruptible_timeout(chan->wait_to_stop,
+					       !xilinx_dpdma_chan_ostand(chan),
+					       msecs_to_jiffies(50));
+	if (ret > 0) {
+		dpdma_write(chan->xdev->reg, XILINX_DPDMA_IEN,
+			    XILINX_DPDMA_INTR_NO_OSTAND(chan->id));
+		return 0;
+	}
+
+	dev_err(chan->xdev->dev, "chan%u: not ready to stop: %d trans\n",
+		chan->id, xilinx_dpdma_chan_ostand(chan));
+
+	if (ret == 0)
+		return -ETIMEDOUT;
+
+	return ret;
+}
+
+/**
+ * xilinx_dpdma_chan_poll_no_ostand - Poll the outstanding transaction status
+ * @chan: DPDMA channel
+ *
+ * Poll the outstanding transaction status, and return when there's no
+ * outstanding transaction. This functions can be used in the interrupt context
+ * or where the atomicity is required. Calling thread may wait more than 50ms.
+ *
+ * Return: 0 on success, or -ETIMEDOUT.
+ */
+static int xilinx_dpdma_chan_poll_no_ostand(struct xilinx_dpdma_chan *chan)
+{
+	u32 cnt, loop = 50000;
+
+	/* Poll at least for 50ms (20 fps). */
+	do {
+		cnt = xilinx_dpdma_chan_ostand(chan);
+		udelay(1);
+	} while (loop-- > 0 && cnt);
+
+	if (loop) {
+		dpdma_write(chan->xdev->reg, XILINX_DPDMA_IEN,
+			    XILINX_DPDMA_INTR_NO_OSTAND(chan->id));
+		return 0;
+	}
+
+	dev_err(chan->xdev->dev, "chan%u: not ready to stop: %d trans\n",
+		chan->id, xilinx_dpdma_chan_ostand(chan));
+
+	return -ETIMEDOUT;
+}
+
+/**
+ * xilinx_dpdma_chan_stop - Stop the channel
+ * @chan: DPDMA channel
+ *
+ * Stop a previously paused channel by first waiting for completion of all
+ * outstanding transaction and then disabling the channel.
+ *
+ * Return: 0 on success, or -ETIMEDOUT if the channel failed to stop.
+ */
+static int xilinx_dpdma_chan_stop(struct xilinx_dpdma_chan *chan)
+{
+	unsigned long flags;
+	int ret;
+
+	ret = xilinx_dpdma_chan_wait_no_ostand(chan);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	xilinx_dpdma_chan_disable(chan);
+	chan->running = false;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return 0;
+}
+
+/**
+ * xilinx_dpdma_chan_done_irq - Handle hardware descriptor completion
+ * @chan: DPDMA channel
+ *
+ * Handle completion of the currently active descriptor (@chan->desc.active). As
+ * we currently support cyclic transfers only, this just invokes the cyclic
+ * callback. The descriptor will be completed at the VSYNC interrupt when a new
+ * descriptor replaces it.
+ */
+static void xilinx_dpdma_chan_done_irq(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_tx_desc *active;
+
+	spin_lock(&chan->lock);
+
+	xilinx_dpdma_debugfs_desc_done_irq(chan);
+
+	active = chan->desc.active;
+	if (active)
+		vchan_cyclic_callback(&active->vdesc);
+	else
+		dev_warn(chan->xdev->dev,
+			 "chan%u: DONE IRQ with no active descriptor!\n",
+			 chan->id);
+
+	spin_unlock(&chan->lock);
+}
+
+/**
+ * xilinx_dpdma_chan_vsync_irq - Handle hardware descriptor scheduling
+ * @chan: DPDMA channel
+ *
+ * At VSYNC the active descriptor may have been replaced by the pending
+ * descriptor. Detect this through the DESC_ID and perform appropriate
+ * bookkeeping.
+ */
+static void xilinx_dpdma_chan_vsync_irq(struct  xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_tx_desc *pending;
+	struct xilinx_dpdma_sw_desc *sw_desc;
+	u32 desc_id;
+
+	spin_lock(&chan->lock);
+
+	pending = chan->desc.pending;
+	if (!chan->running || !pending)
+		goto out;
+
+	desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID)
+		& XILINX_DPDMA_CH_DESC_ID_MASK;
+
+	/* If the retrigger raced with vsync, retry at the next frame. */
+	sw_desc = list_first_entry(&pending->descriptors,
+				   struct xilinx_dpdma_sw_desc, node);
+	if (sw_desc->hw.desc_id != desc_id) {
+		dev_dbg(chan->xdev->dev,
+			"chan%u: vsync race lost (%u != %u), retrying\n",
+			chan->id, sw_desc->hw.desc_id, desc_id);
+		goto out;
+	}
+
+	/*
+	 * Complete the active descriptor, if any, promote the pending
+	 * descriptor to active, and queue the next transfer, if any.
+	 */
+	spin_lock(&chan->vchan.lock);
+	if (chan->desc.active)
+		vchan_cookie_complete(&chan->desc.active->vdesc);
+	chan->desc.active = pending;
+	chan->desc.pending = NULL;
+
+	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
+
+out:
+	spin_unlock(&chan->lock);
+}
+
+/**
+ * xilinx_dpdma_chan_err - Detect any channel error
+ * @chan: DPDMA channel
+ * @isr: masked Interrupt Status Register
+ * @eisr: Error Interrupt Status Register
+ *
+ * Return: true if any channel error occurs, or false otherwise.
+ */
+static bool
+xilinx_dpdma_chan_err(struct xilinx_dpdma_chan *chan, u32 isr, u32 eisr)
+{
+	if (!chan)
+		return false;
+
+	if (chan->running &&
+	    ((isr & (XILINX_DPDMA_INTR_CHAN_ERR_MASK << chan->id)) ||
+	    (eisr & (XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id))))
+		return true;
+
+	return false;
+}
+
+/**
+ * xilinx_dpdma_chan_handle_err - DPDMA channel error handling
+ * @chan: DPDMA channel
+ *
+ * This function is called when any channel error or any global error occurs.
+ * The function disables the paused channel by errors and determines
+ * if the current active descriptor can be rescheduled depending on
+ * the descriptor status.
+ */
+static void xilinx_dpdma_chan_handle_err(struct xilinx_dpdma_chan *chan)
+{
+	struct xilinx_dpdma_device *xdev = chan->xdev;
+	struct xilinx_dpdma_tx_desc *active;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	dev_dbg(xdev->dev, "chan%u: cur desc addr = 0x%04x%08x\n",
+		chan->id,
+		dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_START_ADDRE),
+		dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_START_ADDR));
+	dev_dbg(xdev->dev, "chan%u: cur payload addr = 0x%04x%08x\n",
+		chan->id,
+		dpdma_read(chan->reg, XILINX_DPDMA_CH_PYLD_CUR_ADDRE),
+		dpdma_read(chan->reg, XILINX_DPDMA_CH_PYLD_CUR_ADDR));
+
+	xilinx_dpdma_chan_disable(chan);
+	chan->running = false;
+
+	if (!chan->desc.active)
+		goto out_unlock;
+
+	active = chan->desc.active;
+	chan->desc.active = NULL;
+
+	xilinx_dpdma_chan_dump_tx_desc(chan, active);
+
+	if (active->error)
+		dev_dbg(xdev->dev, "chan%u: repeated error on desc\n",
+			chan->id);
+
+	/* Reschedule if there's no new descriptor */
+	if (!chan->desc.pending &&
+	    list_empty(&chan->vchan.desc_issued)) {
+		active->error = true;
+		list_add_tail(&active->vdesc.node,
+			      &chan->vchan.desc_issued);
+	} else {
+		xilinx_dpdma_chan_free_tx_desc(&active->vdesc);
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/* -----------------------------------------------------------------------------
+ * DMA Engine Operations
+ */
+static struct dma_async_tx_descriptor *
+xilinx_dpdma_prep_dma_cyclic(struct dma_chan *dchan, dma_addr_t buf_addr,
+			     size_t buf_len, size_t period_len,
+			     enum dma_transfer_direction direction,
+			     unsigned long flags)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+
+	if (direction != DMA_MEM_TO_DEV)
+		return NULL;
+
+	if (buf_len % period_len)
+		return NULL;
+
+	return xilinx_dpdma_chan_prep_cyclic(chan, buf_addr, buf_len,
+					     period_len, flags);
+}
+
+static struct dma_async_tx_descriptor *
+xilinx_dpdma_prep_interleaved_dma(struct dma_chan *dchan,
+				  struct dma_interleaved_template *xt,
+				  unsigned long flags)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dpdma_tx_desc *desc;
+
+	if (xt->dir != DMA_MEM_TO_DEV)
+		return NULL;
+
+	if (!xt->numf || !xt->sgl[0].size)
+		return NULL;
+
+	if (!(flags & DMA_PREP_REPEAT) || !(flags & DMA_PREP_LOAD_EOT))
+		return NULL;
+
+	desc = xilinx_dpdma_chan_prep_interleaved_dma(chan, xt);
+	if (!desc)
+		return NULL;
+
+	vchan_tx_prep(&chan->vchan, &desc->vdesc, flags | DMA_CTRL_ACK);
+
+	return &desc->vdesc.tx;
+}
+
+/**
+ * xilinx_dpdma_alloc_chan_resources - Allocate resources for the channel
+ * @dchan: DMA channel
+ *
+ * Allocate a descriptor pool for the channel.
+ *
+ * Return: 0 on success, or -ENOMEM if failed to allocate a pool.
+ */
+static int xilinx_dpdma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	size_t align = __alignof__(struct xilinx_dpdma_sw_desc);
+
+	chan->desc_pool = dma_pool_create(dev_name(chan->xdev->dev),
+					  chan->xdev->dev,
+					  sizeof(struct xilinx_dpdma_sw_desc),
+					  align, 0);
+	if (!chan->desc_pool) {
+		dev_err(chan->xdev->dev,
+			"chan%u: failed to allocate a descriptor pool\n",
+			chan->id);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * xilinx_dpdma_free_chan_resources - Free all resources for the channel
+ * @dchan: DMA channel
+ *
+ * Free resources associated with the virtual DMA channel, and destroy the
+ * descriptor pool.
+ */
+static void xilinx_dpdma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+
+	vchan_free_chan_resources(&chan->vchan);
+
+	dma_pool_destroy(chan->desc_pool);
+	chan->desc_pool = NULL;
+}
+
+static void xilinx_dpdma_issue_pending(struct dma_chan *dchan)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
+	if (vchan_issue_pending(&chan->vchan))
+		xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+static int xilinx_dpdma_config(struct dma_chan *dchan,
+			       struct dma_slave_config *config)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dpdma_peripheral_config *pconfig;
+	unsigned long flags;
+
+	/*
+	 * The destination address doesn't need to be specified as the DPDMA is
+	 * hardwired to the destination (the DP controller). The transfer
+	 * width, burst size and port window size are thus meaningless, they're
+	 * fixed both on the DPDMA side and on the DP controller side.
+	 */
+
+	/*
+	 * Use the peripheral_config to indicate that the channel is part
+	 * of a video group. This requires matching use of the custom
+	 * structure in each driver.
+	 */
+	pconfig = config->peripheral_config;
+	if (WARN_ON(pconfig && config->peripheral_size != sizeof(*pconfig)))
+		return -EINVAL;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->id <= ZYNQMP_DPDMA_VIDEO2 && pconfig)
+		chan->video_group = pconfig->video_group;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return 0;
+}
+
+static int xilinx_dpdma_pause(struct dma_chan *dchan)
+{
+	xilinx_dpdma_chan_pause(to_xilinx_chan(dchan));
+
+	return 0;
+}
+
+static int xilinx_dpdma_resume(struct dma_chan *dchan)
+{
+	xilinx_dpdma_chan_unpause(to_xilinx_chan(dchan));
+
+	return 0;
+}
+
+/**
+ * xilinx_dpdma_terminate_all - Terminate the channel and descriptors
+ * @dchan: DMA channel
+ *
+ * Pause the channel without waiting for ongoing transfers to complete. Waiting
+ * for completion is performed by xilinx_dpdma_synchronize() that will disable
+ * the channel to complete the stop.
+ *
+ * All the descriptors associated with the channel that are guaranteed not to
+ * be touched by the hardware. The pending and active descriptor are not
+ * touched, and will be freed either upon completion, or by
+ * xilinx_dpdma_synchronize().
+ *
+ * Return: 0 on success, or -ETIMEDOUT if the channel failed to stop.
+ */
+static int xilinx_dpdma_terminate_all(struct dma_chan *dchan)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dpdma_device *xdev = chan->xdev;
+	LIST_HEAD(descriptors);
+	unsigned long flags;
+	unsigned int i;
+
+	/* Pause the channel (including the whole video group if applicable). */
+	if (chan->video_group) {
+		for (i = ZYNQMP_DPDMA_VIDEO0; i <= ZYNQMP_DPDMA_VIDEO2; i++) {
+			if (xdev->chan[i]->video_group &&
+			    xdev->chan[i]->running) {
+				xilinx_dpdma_chan_pause(xdev->chan[i]);
+				xdev->chan[i]->video_group = false;
+			}
+		}
+	} else {
+		xilinx_dpdma_chan_pause(chan);
+	}
+
+	/* Gather all the descriptors we can free and free them. */
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	vchan_get_all_descriptors(&chan->vchan, &descriptors);
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&chan->vchan, &descriptors);
+
+	return 0;
+}
+
+/**
+ * xilinx_dpdma_synchronize - Synchronize callback execution
+ * @dchan: DMA channel
+ *
+ * Synchronizing callback execution ensures that all previously issued
+ * transfers have completed and all associated callbacks have been called and
+ * have returned.
+ *
+ * This function waits for the DMA channel to stop. It assumes it has been
+ * paused by a previous call to dmaengine_terminate_async(), and that no new
+ * pending descriptors have been issued with dma_async_issue_pending(). The
+ * behaviour is undefined otherwise.
+ */
+static void xilinx_dpdma_synchronize(struct dma_chan *dchan)
+{
+	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
+
+	xilinx_dpdma_chan_stop(chan);
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	if (chan->desc.pending) {
+		vchan_terminate_vdesc(&chan->desc.pending->vdesc);
+		chan->desc.pending = NULL;
+	}
+	if (chan->desc.active) {
+		vchan_terminate_vdesc(&chan->desc.active->vdesc);
+		chan->desc.active = NULL;
+	}
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	vchan_synchronize(&chan->vchan);
+}
+
+/* -----------------------------------------------------------------------------
+ * Interrupt and Tasklet Handling
+ */
+
+/**
+ * xilinx_dpdma_err - Detect any global error
+ * @isr: Interrupt Status Register
+ * @eisr: Error Interrupt Status Register
+ *
+ * Return: True if any global error occurs, or false otherwise.
+ */
+static bool xilinx_dpdma_err(u32 isr, u32 eisr)
+{
+	if (isr & XILINX_DPDMA_INTR_GLOBAL_ERR ||
+	    eisr & XILINX_DPDMA_EINTR_GLOBAL_ERR)
+		return true;
+
+	return false;
+}
+
+/**
+ * xilinx_dpdma_handle_err_irq - Handle DPDMA error interrupt
+ * @xdev: DPDMA device
+ * @isr: masked Interrupt Status Register
+ * @eisr: Error Interrupt Status Register
+ *
+ * Handle if any error occurs based on @isr and @eisr. This function disables
+ * corresponding error interrupts, and those should be re-enabled once handling
+ * is done.
+ */
+static void xilinx_dpdma_handle_err_irq(struct xilinx_dpdma_device *xdev,
+					u32 isr, u32 eisr)
+{
+	bool err = xilinx_dpdma_err(isr, eisr);
+	unsigned int i;
+
+	dev_dbg_ratelimited(xdev->dev,
+			    "error irq: isr = 0x%08x, eisr = 0x%08x\n",
+			    isr, eisr);
+
+	/* Disable channel error interrupts until errors are handled. */
+	dpdma_write(xdev->reg, XILINX_DPDMA_IDS,
+		    isr & ~XILINX_DPDMA_INTR_GLOBAL_ERR);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EIDS,
+		    eisr & ~XILINX_DPDMA_EINTR_GLOBAL_ERR);
+
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); i++)
+		if (err || xilinx_dpdma_chan_err(xdev->chan[i], isr, eisr))
+			tasklet_schedule(&xdev->chan[i]->err_task);
+}
+
+/**
+ * xilinx_dpdma_enable_irq - Enable interrupts
+ * @xdev: DPDMA device
+ *
+ * Enable interrupts.
+ */
+static void xilinx_dpdma_enable_irq(struct xilinx_dpdma_device *xdev)
+{
+	dpdma_write(xdev->reg, XILINX_DPDMA_IEN, XILINX_DPDMA_INTR_ALL);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EIEN, XILINX_DPDMA_EINTR_ALL);
+}
+
+/**
+ * xilinx_dpdma_disable_irq - Disable interrupts
+ * @xdev: DPDMA device
+ *
+ * Disable interrupts.
+ */
+static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev)
+{
+	dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL);
+}
+
+/**
+ * xilinx_dpdma_chan_err_task - Per channel tasklet for error handling
+ * @t: pointer to the tasklet associated with this handler
+ *
+ * Per channel error handling tasklet. This function waits for the outstanding
+ * transaction to complete and triggers error handling. After error handling,
+ * re-enable channel error interrupts, and restart the channel if needed.
+ */
+static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t)
+{
+	struct xilinx_dpdma_chan *chan = from_tasklet(chan, t, err_task);
+	struct xilinx_dpdma_device *xdev = chan->xdev;
+	unsigned long flags;
+
+	/* Proceed error handling even when polling fails. */
+	xilinx_dpdma_chan_poll_no_ostand(chan);
+
+	xilinx_dpdma_chan_handle_err(chan);
+
+	dpdma_write(xdev->reg, XILINX_DPDMA_IEN,
+		    XILINX_DPDMA_INTR_CHAN_ERR_MASK << chan->id);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EIEN,
+		    XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id);
+
+	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
+	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+static irqreturn_t xilinx_dpdma_irq_handler(int irq, void *data)
+{
+	struct xilinx_dpdma_device *xdev = data;
+	unsigned long mask;
+	unsigned int i;
+	u32 status;
+	u32 error;
+
+	status = dpdma_read(xdev->reg, XILINX_DPDMA_ISR);
+	error = dpdma_read(xdev->reg, XILINX_DPDMA_EISR);
+	if (!status && !error)
+		return IRQ_NONE;
+
+	dpdma_write(xdev->reg, XILINX_DPDMA_ISR, status);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EISR, error);
+
+	if (status & XILINX_DPDMA_INTR_VSYNC) {
+		/*
+		 * There's a single VSYNC interrupt that needs to be processed
+		 * by each running channel to update the active descriptor.
+		 */
+		for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) {
+			struct xilinx_dpdma_chan *chan = xdev->chan[i];
+
+			if (chan)
+				xilinx_dpdma_chan_vsync_irq(chan);
+		}
+	}
+
+	mask = FIELD_GET(XILINX_DPDMA_INTR_DESC_DONE_MASK, status);
+	if (mask) {
+		for_each_set_bit(i, &mask, ARRAY_SIZE(xdev->chan))
+			xilinx_dpdma_chan_done_irq(xdev->chan[i]);
+	}
+
+	mask = FIELD_GET(XILINX_DPDMA_INTR_NO_OSTAND_MASK, status);
+	if (mask) {
+		for_each_set_bit(i, &mask, ARRAY_SIZE(xdev->chan))
+			xilinx_dpdma_chan_notify_no_ostand(xdev->chan[i]);
+	}
+
+	mask = status & XILINX_DPDMA_INTR_ERR_ALL;
+	if (mask || error)
+		xilinx_dpdma_handle_err_irq(xdev, mask, error);
+
+	return IRQ_HANDLED;
+}
+
+/* -----------------------------------------------------------------------------
+ * Initialization & Cleanup
+ */
+
+static int xilinx_dpdma_chan_init(struct xilinx_dpdma_device *xdev,
+				  unsigned int chan_id)
+{
+	struct xilinx_dpdma_chan *chan;
+
+	chan = devm_kzalloc(xdev->dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+
+	chan->id = chan_id;
+	chan->reg = xdev->reg + XILINX_DPDMA_CH_BASE
+		  + XILINX_DPDMA_CH_OFFSET * chan->id;
+	chan->running = false;
+	chan->xdev = xdev;
+
+	spin_lock_init(&chan->lock);
+	init_waitqueue_head(&chan->wait_to_stop);
+
+	tasklet_setup(&chan->err_task, xilinx_dpdma_chan_err_task);
+
+	chan->vchan.desc_free = xilinx_dpdma_chan_free_tx_desc;
+	vchan_init(&chan->vchan, &xdev->common);
+
+	xdev->chan[chan->id] = chan;
+
+	return 0;
+}
+
+static void xilinx_dpdma_chan_remove(struct xilinx_dpdma_chan *chan)
+{
+	if (!chan)
+		return;
+
+	tasklet_kill(&chan->err_task);
+	list_del(&chan->vchan.chan.device_node);
+}
+
+static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec,
+					    struct of_dma *ofdma)
+{
+	struct xilinx_dpdma_device *xdev = ofdma->of_dma_data;
+	u32 chan_id = dma_spec->args[0];
+
+	if (chan_id >= ARRAY_SIZE(xdev->chan))
+		return NULL;
+
+	if (!xdev->chan[chan_id])
+		return NULL;
+
+	return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan);
+}
+
+static void dpdma_hw_init(struct xilinx_dpdma_device *xdev)
+{
+	unsigned int i;
+	void __iomem *reg;
+
+	/* Disable all interrupts */
+	xilinx_dpdma_disable_irq(xdev);
+
+	/* Stop all channels */
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) {
+		reg = xdev->reg + XILINX_DPDMA_CH_BASE
+				+ XILINX_DPDMA_CH_OFFSET * i;
+		dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE);
+	}
+
+	/* Clear the interrupt status registers */
+	dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL);
+	dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL);
+}
+
+static int xilinx_dpdma_probe(struct platform_device *pdev)
+{
+	struct xilinx_dpdma_device *xdev;
+	struct dma_device *ddev;
+	unsigned int i;
+	int ret;
+
+	xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL);
+	if (!xdev)
+		return -ENOMEM;
+
+	xdev->dev = &pdev->dev;
+	xdev->ext_addr = sizeof(dma_addr_t) > 4;
+
+	INIT_LIST_HEAD(&xdev->common.channels);
+
+	platform_set_drvdata(pdev, xdev);
+
+	xdev->axi_clk = devm_clk_get(xdev->dev, "axi_clk");
+	if (IS_ERR(xdev->axi_clk))
+		return PTR_ERR(xdev->axi_clk);
+
+	xdev->reg = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(xdev->reg))
+		return PTR_ERR(xdev->reg);
+
+	dpdma_hw_init(xdev);
+
+	xdev->irq = platform_get_irq(pdev, 0);
+	if (xdev->irq < 0)
+		return xdev->irq;
+
+	ret = request_irq(xdev->irq, xilinx_dpdma_irq_handler, IRQF_SHARED,
+			  dev_name(xdev->dev), xdev);
+	if (ret) {
+		dev_err(xdev->dev, "failed to request IRQ\n");
+		return ret;
+	}
+
+	ddev = &xdev->common;
+	ddev->dev = &pdev->dev;
+
+	dma_cap_set(DMA_SLAVE, ddev->cap_mask);
+	dma_cap_set(DMA_PRIVATE, ddev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, ddev->cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, ddev->cap_mask);
+	dma_cap_set(DMA_REPEAT, ddev->cap_mask);
+	dma_cap_set(DMA_LOAD_EOT, ddev->cap_mask);
+	ddev->copy_align = fls(XILINX_DPDMA_ALIGN_BYTES - 1);
+
+	ddev->device_alloc_chan_resources = xilinx_dpdma_alloc_chan_resources;
+	ddev->device_free_chan_resources = xilinx_dpdma_free_chan_resources;
+	ddev->device_prep_dma_cyclic = xilinx_dpdma_prep_dma_cyclic;
+	ddev->device_prep_interleaved_dma = xilinx_dpdma_prep_interleaved_dma;
+	/* TODO: Can we achieve better granularity ? */
+	ddev->device_tx_status = dma_cookie_status;
+	ddev->device_issue_pending = xilinx_dpdma_issue_pending;
+	ddev->device_config = xilinx_dpdma_config;
+	ddev->device_pause = xilinx_dpdma_pause;
+	ddev->device_resume = xilinx_dpdma_resume;
+	ddev->device_terminate_all = xilinx_dpdma_terminate_all;
+	ddev->device_synchronize = xilinx_dpdma_synchronize;
+	ddev->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED);
+	ddev->directions = BIT(DMA_MEM_TO_DEV);
+	ddev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); ++i) {
+		ret = xilinx_dpdma_chan_init(xdev, i);
+		if (ret < 0) {
+			dev_err(xdev->dev, "failed to initialize channel %u\n",
+				i);
+			goto error;
+		}
+	}
+
+	ret = clk_prepare_enable(xdev->axi_clk);
+	if (ret) {
+		dev_err(xdev->dev, "failed to enable the axi clock\n");
+		goto error;
+	}
+
+	ret = dma_async_device_register(ddev);
+	if (ret) {
+		dev_err(xdev->dev, "failed to register the dma device\n");
+		goto error_dma_async;
+	}
+
+	ret = of_dma_controller_register(xdev->dev->of_node,
+					 of_dma_xilinx_xlate, ddev);
+	if (ret) {
+		dev_err(xdev->dev, "failed to register DMA to DT DMA helper\n");
+		goto error_of_dma;
+	}
+
+	xilinx_dpdma_enable_irq(xdev);
+
+	xilinx_dpdma_debugfs_init(xdev);
+
+	dev_info(&pdev->dev, "Xilinx DPDMA engine is probed\n");
+
+	return 0;
+
+error_of_dma:
+	dma_async_device_unregister(ddev);
+error_dma_async:
+	clk_disable_unprepare(xdev->axi_clk);
+error:
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); i++)
+		xilinx_dpdma_chan_remove(xdev->chan[i]);
+
+	free_irq(xdev->irq, xdev);
+
+	return ret;
+}
+
+static void xilinx_dpdma_remove(struct platform_device *pdev)
+{
+	struct xilinx_dpdma_device *xdev = platform_get_drvdata(pdev);
+	unsigned int i;
+
+	/* Start by disabling the IRQ to avoid races during cleanup. */
+	free_irq(xdev->irq, xdev);
+
+	xilinx_dpdma_disable_irq(xdev);
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&xdev->common);
+	clk_disable_unprepare(xdev->axi_clk);
+
+	for (i = 0; i < ARRAY_SIZE(xdev->chan); i++)
+		xilinx_dpdma_chan_remove(xdev->chan[i]);
+}
+
+static const struct of_device_id xilinx_dpdma_of_match[] = {
+	{ .compatible = "xlnx,zynqmp-dpdma",},
+	{ /* end of table */ },
+};
+MODULE_DEVICE_TABLE(of, xilinx_dpdma_of_match);
+
+static struct platform_driver xilinx_dpdma_driver = {
+	.probe			= xilinx_dpdma_probe,
+	.remove			= xilinx_dpdma_remove,
+	.driver			= {
+		.name		= "xilinx-zynqmp-dpdma",
+		.of_match_table	= xilinx_dpdma_of_match,
+	},
+};
+
+module_platform_driver(xilinx_dpdma_driver);
+
+MODULE_AUTHOR("Xilinx, Inc.");
+MODULE_DESCRIPTION("Xilinx ZynqMP DPDMA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
new file mode 100644
index 000000000..f6a812e49
--- /dev/null
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -0,0 +1,1200 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DMA driver for Xilinx ZynqMP DMA Engine
+ *
+ * Copyright (C) 2016 Xilinx, Inc. All rights reserved.
+ */
+
+#include <linux/bitops.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/pm_runtime.h>
+
+#include "../dmaengine.h"
+
+/* Register Offsets */
+#define ZYNQMP_DMA_ISR			(chan->irq_offset + 0x100)
+#define ZYNQMP_DMA_IMR			(chan->irq_offset + 0x104)
+#define ZYNQMP_DMA_IER			(chan->irq_offset + 0x108)
+#define ZYNQMP_DMA_IDS			(chan->irq_offset + 0x10c)
+#define ZYNQMP_DMA_CTRL0		0x110
+#define ZYNQMP_DMA_CTRL1		0x114
+#define ZYNQMP_DMA_DATA_ATTR		0x120
+#define ZYNQMP_DMA_DSCR_ATTR		0x124
+#define ZYNQMP_DMA_SRC_DSCR_WRD0	0x128
+#define ZYNQMP_DMA_SRC_DSCR_WRD1	0x12C
+#define ZYNQMP_DMA_SRC_DSCR_WRD2	0x130
+#define ZYNQMP_DMA_SRC_DSCR_WRD3	0x134
+#define ZYNQMP_DMA_DST_DSCR_WRD0	0x138
+#define ZYNQMP_DMA_DST_DSCR_WRD1	0x13C
+#define ZYNQMP_DMA_DST_DSCR_WRD2	0x140
+#define ZYNQMP_DMA_DST_DSCR_WRD3	0x144
+#define ZYNQMP_DMA_SRC_START_LSB	0x158
+#define ZYNQMP_DMA_SRC_START_MSB	0x15C
+#define ZYNQMP_DMA_DST_START_LSB	0x160
+#define ZYNQMP_DMA_DST_START_MSB	0x164
+#define ZYNQMP_DMA_TOTAL_BYTE		0x188
+#define ZYNQMP_DMA_RATE_CTRL		0x18C
+#define ZYNQMP_DMA_IRQ_SRC_ACCT		0x190
+#define ZYNQMP_DMA_IRQ_DST_ACCT		0x194
+#define ZYNQMP_DMA_CTRL2		0x200
+
+/* Interrupt registers bit field definitions */
+#define ZYNQMP_DMA_DONE			BIT(10)
+#define ZYNQMP_DMA_AXI_WR_DATA		BIT(9)
+#define ZYNQMP_DMA_AXI_RD_DATA		BIT(8)
+#define ZYNQMP_DMA_AXI_RD_DST_DSCR	BIT(7)
+#define ZYNQMP_DMA_AXI_RD_SRC_DSCR	BIT(6)
+#define ZYNQMP_DMA_IRQ_DST_ACCT_ERR	BIT(5)
+#define ZYNQMP_DMA_IRQ_SRC_ACCT_ERR	BIT(4)
+#define ZYNQMP_DMA_BYTE_CNT_OVRFL	BIT(3)
+#define ZYNQMP_DMA_DST_DSCR_DONE	BIT(2)
+#define ZYNQMP_DMA_INV_APB		BIT(0)
+
+/* Control 0 register bit field definitions */
+#define ZYNQMP_DMA_OVR_FETCH		BIT(7)
+#define ZYNQMP_DMA_POINT_TYPE_SG	BIT(6)
+#define ZYNQMP_DMA_RATE_CTRL_EN		BIT(3)
+
+/* Control 1 register bit field definitions */
+#define ZYNQMP_DMA_SRC_ISSUE		GENMASK(4, 0)
+
+/* Data Attribute register bit field definitions */
+#define ZYNQMP_DMA_ARBURST		GENMASK(27, 26)
+#define ZYNQMP_DMA_ARCACHE		GENMASK(25, 22)
+#define ZYNQMP_DMA_ARCACHE_OFST		22
+#define ZYNQMP_DMA_ARQOS		GENMASK(21, 18)
+#define ZYNQMP_DMA_ARQOS_OFST		18
+#define ZYNQMP_DMA_ARLEN		GENMASK(17, 14)
+#define ZYNQMP_DMA_ARLEN_OFST		14
+#define ZYNQMP_DMA_AWBURST		GENMASK(13, 12)
+#define ZYNQMP_DMA_AWCACHE		GENMASK(11, 8)
+#define ZYNQMP_DMA_AWCACHE_OFST		8
+#define ZYNQMP_DMA_AWQOS		GENMASK(7, 4)
+#define ZYNQMP_DMA_AWQOS_OFST		4
+#define ZYNQMP_DMA_AWLEN		GENMASK(3, 0)
+#define ZYNQMP_DMA_AWLEN_OFST		0
+
+/* Descriptor Attribute register bit field definitions */
+#define ZYNQMP_DMA_AXCOHRNT		BIT(8)
+#define ZYNQMP_DMA_AXCACHE		GENMASK(7, 4)
+#define ZYNQMP_DMA_AXCACHE_OFST		4
+#define ZYNQMP_DMA_AXQOS		GENMASK(3, 0)
+#define ZYNQMP_DMA_AXQOS_OFST		0
+
+/* Control register 2 bit field definitions */
+#define ZYNQMP_DMA_ENABLE		BIT(0)
+
+/* Buffer Descriptor definitions */
+#define ZYNQMP_DMA_DESC_CTRL_STOP	0x10
+#define ZYNQMP_DMA_DESC_CTRL_COMP_INT	0x4
+#define ZYNQMP_DMA_DESC_CTRL_SIZE_256	0x2
+#define ZYNQMP_DMA_DESC_CTRL_COHRNT	0x1
+
+/* Interrupt Mask specific definitions */
+#define ZYNQMP_DMA_INT_ERR	(ZYNQMP_DMA_AXI_RD_DATA | \
+				ZYNQMP_DMA_AXI_WR_DATA | \
+				ZYNQMP_DMA_AXI_RD_DST_DSCR | \
+				ZYNQMP_DMA_AXI_RD_SRC_DSCR | \
+				ZYNQMP_DMA_INV_APB)
+#define ZYNQMP_DMA_INT_OVRFL	(ZYNQMP_DMA_BYTE_CNT_OVRFL | \
+				ZYNQMP_DMA_IRQ_SRC_ACCT_ERR | \
+				ZYNQMP_DMA_IRQ_DST_ACCT_ERR)
+#define ZYNQMP_DMA_INT_DONE	(ZYNQMP_DMA_DONE | ZYNQMP_DMA_DST_DSCR_DONE)
+#define ZYNQMP_DMA_INT_EN_DEFAULT_MASK	(ZYNQMP_DMA_INT_DONE | \
+					ZYNQMP_DMA_INT_ERR | \
+					ZYNQMP_DMA_INT_OVRFL | \
+					ZYNQMP_DMA_DST_DSCR_DONE)
+
+/* Max number of descriptors per channel */
+#define ZYNQMP_DMA_NUM_DESCS	32
+
+/* Max transfer size per descriptor */
+#define ZYNQMP_DMA_MAX_TRANS_LEN	0x40000000
+
+/* Max burst lengths */
+#define ZYNQMP_DMA_MAX_DST_BURST_LEN    32768U
+#define ZYNQMP_DMA_MAX_SRC_BURST_LEN    32768U
+
+/* Reset values for data attributes */
+#define ZYNQMP_DMA_AXCACHE_VAL		0xF
+
+#define ZYNQMP_DMA_SRC_ISSUE_RST_VAL	0x1F
+
+#define ZYNQMP_DMA_IDS_DEFAULT_MASK	0xFFF
+
+/* Bus width in bits */
+#define ZYNQMP_DMA_BUS_WIDTH_64		64
+#define ZYNQMP_DMA_BUS_WIDTH_128	128
+
+#define ZDMA_PM_TIMEOUT			100
+
+#define ZYNQMP_DMA_DESC_SIZE(chan)	(chan->desc_size)
+
+#define to_chan(chan)		container_of(chan, struct zynqmp_dma_chan, \
+					     common)
+#define tx_to_desc(tx)		container_of(tx, struct zynqmp_dma_desc_sw, \
+					     async_tx)
+
+/* IRQ Register offset for Versal Gen 2 */
+#define IRQ_REG_OFFSET			0x308
+
+/**
+ * struct zynqmp_dma_desc_ll - Hw linked list descriptor
+ * @addr: Buffer address
+ * @size: Size of the buffer
+ * @ctrl: Control word
+ * @nxtdscraddr: Next descriptor base address
+ * @rsvd: Reserved field and for Hw internal use.
+ */
+struct zynqmp_dma_desc_ll {
+	u64 addr;
+	u32 size;
+	u32 ctrl;
+	u64 nxtdscraddr;
+	u64 rsvd;
+};
+
+/**
+ * struct zynqmp_dma_desc_sw - Per Transaction structure
+ * @src: Source address for simple mode dma
+ * @dst: Destination address for simple mode dma
+ * @len: Transfer length for simple mode dma
+ * @node: Node in the channel descriptor list
+ * @tx_list: List head for the current transfer
+ * @async_tx: Async transaction descriptor
+ * @src_v: Virtual address of the src descriptor
+ * @src_p: Physical address of the src descriptor
+ * @dst_v: Virtual address of the dst descriptor
+ * @dst_p: Physical address of the dst descriptor
+ */
+struct zynqmp_dma_desc_sw {
+	u64 src;
+	u64 dst;
+	u32 len;
+	struct list_head node;
+	struct list_head tx_list;
+	struct dma_async_tx_descriptor async_tx;
+	struct zynqmp_dma_desc_ll *src_v;
+	dma_addr_t src_p;
+	struct zynqmp_dma_desc_ll *dst_v;
+	dma_addr_t dst_p;
+};
+
+/**
+ * struct zynqmp_dma_chan - Driver specific DMA channel structure
+ * @zdev: Driver specific device structure
+ * @regs: Control registers offset
+ * @lock: Descriptor operation lock
+ * @pending_list: Descriptors waiting
+ * @free_list: Descriptors free
+ * @active_list: Descriptors active
+ * @sw_desc_pool: SW descriptor pool
+ * @done_list: Complete descriptors
+ * @common: DMA common channel
+ * @desc_pool_v: Statically allocated descriptor base
+ * @desc_pool_p: Physical allocated descriptor base
+ * @desc_free_cnt: Descriptor available count
+ * @dev: The dma device
+ * @irq: Channel IRQ
+ * @is_dmacoherent: Tells whether dma operations are coherent or not
+ * @tasklet: Cleanup work after irq
+ * @idle : Channel status;
+ * @desc_size: Size of the low level descriptor
+ * @err: Channel has errors
+ * @bus_width: Bus width
+ * @src_burst_len: Source burst length
+ * @dst_burst_len: Dest burst length
+ * @irq_offset: Irq register offset
+ */
+struct zynqmp_dma_chan {
+	struct zynqmp_dma_device *zdev;
+	void __iomem *regs;
+	spinlock_t lock;
+	struct list_head pending_list;
+	struct list_head free_list;
+	struct list_head active_list;
+	struct zynqmp_dma_desc_sw *sw_desc_pool;
+	struct list_head done_list;
+	struct dma_chan common;
+	void *desc_pool_v;
+	dma_addr_t desc_pool_p;
+	u32 desc_free_cnt;
+	struct device *dev;
+	int irq;
+	bool is_dmacoherent;
+	struct tasklet_struct tasklet;
+	bool idle;
+	size_t desc_size;
+	bool err;
+	u32 bus_width;
+	u32 src_burst_len;
+	u32 dst_burst_len;
+	u32 irq_offset;
+};
+
+/**
+ * struct zynqmp_dma_device - DMA device structure
+ * @dev: Device Structure
+ * @common: DMA device structure
+ * @chan: Driver specific DMA channel
+ * @clk_main: Pointer to main clock
+ * @clk_apb: Pointer to apb clock
+ */
+struct zynqmp_dma_device {
+	struct device *dev;
+	struct dma_device common;
+	struct zynqmp_dma_chan *chan;
+	struct clk *clk_main;
+	struct clk *clk_apb;
+};
+
+struct zynqmp_dma_config {
+	u32 offset;
+};
+
+static const struct zynqmp_dma_config versal2_dma_config = {
+	.offset = IRQ_REG_OFFSET,
+};
+
+static inline void zynqmp_dma_writeq(struct zynqmp_dma_chan *chan, u32 reg,
+				     u64 value)
+{
+	lo_hi_writeq(value, chan->regs + reg);
+}
+
+/**
+ * zynqmp_dma_update_desc_to_ctrlr - Updates descriptor to the controller
+ * @chan: ZynqMP DMA DMA channel pointer
+ * @desc: Transaction descriptor pointer
+ */
+static void zynqmp_dma_update_desc_to_ctrlr(struct zynqmp_dma_chan *chan,
+				      struct zynqmp_dma_desc_sw *desc)
+{
+	dma_addr_t addr;
+
+	addr = desc->src_p;
+	zynqmp_dma_writeq(chan, ZYNQMP_DMA_SRC_START_LSB, addr);
+	addr = desc->dst_p;
+	zynqmp_dma_writeq(chan, ZYNQMP_DMA_DST_START_LSB, addr);
+}
+
+/**
+ * zynqmp_dma_desc_config_eod - Mark the descriptor as end descriptor
+ * @chan: ZynqMP DMA channel pointer
+ * @desc: Hw descriptor pointer
+ */
+static void zynqmp_dma_desc_config_eod(struct zynqmp_dma_chan *chan,
+				       void *desc)
+{
+	struct zynqmp_dma_desc_ll *hw = (struct zynqmp_dma_desc_ll *)desc;
+
+	hw->ctrl |= ZYNQMP_DMA_DESC_CTRL_STOP;
+	hw++;
+	hw->ctrl |= ZYNQMP_DMA_DESC_CTRL_COMP_INT | ZYNQMP_DMA_DESC_CTRL_STOP;
+}
+
+/**
+ * zynqmp_dma_config_sg_ll_desc - Configure the linked list descriptor
+ * @chan: ZynqMP DMA channel pointer
+ * @sdesc: Hw descriptor pointer
+ * @src: Source buffer address
+ * @dst: Destination buffer address
+ * @len: Transfer length
+ * @prev: Previous hw descriptor pointer
+ */
+static void zynqmp_dma_config_sg_ll_desc(struct zynqmp_dma_chan *chan,
+				   struct zynqmp_dma_desc_ll *sdesc,
+				   dma_addr_t src, dma_addr_t dst, size_t len,
+				   struct zynqmp_dma_desc_ll *prev)
+{
+	struct zynqmp_dma_desc_ll *ddesc = sdesc + 1;
+
+	sdesc->size = ddesc->size = len;
+	sdesc->addr = src;
+	ddesc->addr = dst;
+
+	sdesc->ctrl = ddesc->ctrl = ZYNQMP_DMA_DESC_CTRL_SIZE_256;
+	if (chan->is_dmacoherent) {
+		sdesc->ctrl |= ZYNQMP_DMA_DESC_CTRL_COHRNT;
+		ddesc->ctrl |= ZYNQMP_DMA_DESC_CTRL_COHRNT;
+	}
+
+	if (prev) {
+		dma_addr_t addr = chan->desc_pool_p +
+			    ((uintptr_t)sdesc - (uintptr_t)chan->desc_pool_v);
+		ddesc = prev + 1;
+		prev->nxtdscraddr = addr;
+		ddesc->nxtdscraddr = addr + ZYNQMP_DMA_DESC_SIZE(chan);
+	}
+}
+
+/**
+ * zynqmp_dma_init - Initialize the channel
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_init(struct zynqmp_dma_chan *chan)
+{
+	u32 val;
+
+	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
+	val = readl(chan->regs + ZYNQMP_DMA_ISR);
+	writel(val, chan->regs + ZYNQMP_DMA_ISR);
+
+	if (chan->is_dmacoherent) {
+		val = ZYNQMP_DMA_AXCOHRNT;
+		val = (val & ~ZYNQMP_DMA_AXCACHE) |
+			(ZYNQMP_DMA_AXCACHE_VAL << ZYNQMP_DMA_AXCACHE_OFST);
+		writel(val, chan->regs + ZYNQMP_DMA_DSCR_ATTR);
+	}
+
+	val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR);
+	if (chan->is_dmacoherent) {
+		val = (val & ~ZYNQMP_DMA_ARCACHE) |
+			(ZYNQMP_DMA_AXCACHE_VAL << ZYNQMP_DMA_ARCACHE_OFST);
+		val = (val & ~ZYNQMP_DMA_AWCACHE) |
+			(ZYNQMP_DMA_AXCACHE_VAL << ZYNQMP_DMA_AWCACHE_OFST);
+	}
+	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
+
+	/* Clearing the interrupt account registers */
+	val = readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
+	val = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
+
+	chan->idle = true;
+}
+
+/**
+ * zynqmp_dma_tx_submit - Submit DMA transaction
+ * @tx: Async transaction descriptor pointer
+ *
+ * Return: cookie value
+ */
+static dma_cookie_t zynqmp_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct zynqmp_dma_chan *chan = to_chan(tx->chan);
+	struct zynqmp_dma_desc_sw *desc, *new;
+	dma_cookie_t cookie;
+	unsigned long irqflags;
+
+	new = tx_to_desc(tx);
+	spin_lock_irqsave(&chan->lock, irqflags);
+	cookie = dma_cookie_assign(tx);
+
+	if (!list_empty(&chan->pending_list)) {
+		desc = list_last_entry(&chan->pending_list,
+				     struct zynqmp_dma_desc_sw, node);
+		if (!list_empty(&desc->tx_list))
+			desc = list_last_entry(&desc->tx_list,
+					       struct zynqmp_dma_desc_sw, node);
+		desc->src_v->nxtdscraddr = new->src_p;
+		desc->src_v->ctrl &= ~ZYNQMP_DMA_DESC_CTRL_STOP;
+		desc->dst_v->nxtdscraddr = new->dst_p;
+		desc->dst_v->ctrl &= ~ZYNQMP_DMA_DESC_CTRL_STOP;
+	}
+
+	list_add_tail(&new->node, &chan->pending_list);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+
+	return cookie;
+}
+
+/**
+ * zynqmp_dma_get_descriptor - Get the sw descriptor from the pool
+ * @chan: ZynqMP DMA channel pointer
+ *
+ * Return: The sw descriptor
+ */
+static struct zynqmp_dma_desc_sw *
+zynqmp_dma_get_descriptor(struct zynqmp_dma_chan *chan)
+{
+	struct zynqmp_dma_desc_sw *desc;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	desc = list_first_entry(&chan->free_list,
+				struct zynqmp_dma_desc_sw, node);
+	list_del(&desc->node);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+
+	INIT_LIST_HEAD(&desc->tx_list);
+	/* Clear the src and dst descriptor memory */
+	memset((void *)desc->src_v, 0, ZYNQMP_DMA_DESC_SIZE(chan));
+	memset((void *)desc->dst_v, 0, ZYNQMP_DMA_DESC_SIZE(chan));
+
+	return desc;
+}
+
+/**
+ * zynqmp_dma_free_descriptor - Issue pending transactions
+ * @chan: ZynqMP DMA channel pointer
+ * @sdesc: Transaction descriptor pointer
+ */
+static void zynqmp_dma_free_descriptor(struct zynqmp_dma_chan *chan,
+				 struct zynqmp_dma_desc_sw *sdesc)
+{
+	struct zynqmp_dma_desc_sw *child, *next;
+
+	chan->desc_free_cnt++;
+	list_move_tail(&sdesc->node, &chan->free_list);
+	list_for_each_entry_safe(child, next, &sdesc->tx_list, node) {
+		chan->desc_free_cnt++;
+		list_move_tail(&child->node, &chan->free_list);
+	}
+}
+
+/**
+ * zynqmp_dma_free_desc_list - Free descriptors list
+ * @chan: ZynqMP DMA channel pointer
+ * @list: List to parse and delete the descriptor
+ */
+static void zynqmp_dma_free_desc_list(struct zynqmp_dma_chan *chan,
+				      struct list_head *list)
+{
+	struct zynqmp_dma_desc_sw *desc, *next;
+
+	list_for_each_entry_safe(desc, next, list, node)
+		zynqmp_dma_free_descriptor(chan, desc);
+}
+
+/**
+ * zynqmp_dma_alloc_chan_resources - Allocate channel resources
+ * @dchan: DMA channel
+ *
+ * Return: Number of descriptors on success and failure value on error
+ */
+static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	struct zynqmp_dma_desc_sw *desc;
+	int i, ret;
+
+	ret = pm_runtime_resume_and_get(chan->dev);
+	if (ret < 0)
+		return ret;
+
+	chan->sw_desc_pool = kzalloc_objs(*desc, ZYNQMP_DMA_NUM_DESCS);
+	if (!chan->sw_desc_pool)
+		return -ENOMEM;
+
+	chan->idle = true;
+	chan->desc_free_cnt = ZYNQMP_DMA_NUM_DESCS;
+
+	INIT_LIST_HEAD(&chan->free_list);
+
+	for (i = 0; i < ZYNQMP_DMA_NUM_DESCS; i++) {
+		desc = chan->sw_desc_pool + i;
+		dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+		desc->async_tx.tx_submit = zynqmp_dma_tx_submit;
+		list_add_tail(&desc->node, &chan->free_list);
+	}
+
+	chan->desc_pool_v = dma_alloc_coherent(chan->dev,
+					       (2 * ZYNQMP_DMA_DESC_SIZE(chan) *
+					       ZYNQMP_DMA_NUM_DESCS),
+					       &chan->desc_pool_p, GFP_KERNEL);
+	if (!chan->desc_pool_v)
+		return -ENOMEM;
+
+	for (i = 0; i < ZYNQMP_DMA_NUM_DESCS; i++) {
+		desc = chan->sw_desc_pool + i;
+		desc->src_v = (struct zynqmp_dma_desc_ll *) (chan->desc_pool_v +
+					(i * ZYNQMP_DMA_DESC_SIZE(chan) * 2));
+		desc->dst_v = (struct zynqmp_dma_desc_ll *) (desc->src_v + 1);
+		desc->src_p = chan->desc_pool_p +
+				(i * ZYNQMP_DMA_DESC_SIZE(chan) * 2);
+		desc->dst_p = desc->src_p + ZYNQMP_DMA_DESC_SIZE(chan);
+	}
+
+	return ZYNQMP_DMA_NUM_DESCS;
+}
+
+/**
+ * zynqmp_dma_start - Start DMA channel
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_start(struct zynqmp_dma_chan *chan)
+{
+	writel(ZYNQMP_DMA_INT_EN_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IER);
+	writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
+	chan->idle = false;
+	writel(ZYNQMP_DMA_ENABLE, chan->regs + ZYNQMP_DMA_CTRL2);
+}
+
+/**
+ * zynqmp_dma_handle_ovfl_int - Process the overflow interrupt
+ * @chan: ZynqMP DMA channel pointer
+ * @status: Interrupt status value
+ */
+static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)
+{
+	if (status & ZYNQMP_DMA_BYTE_CNT_OVRFL)
+		writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
+	if (status & ZYNQMP_DMA_IRQ_DST_ACCT_ERR)
+		readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
+	if (status & ZYNQMP_DMA_IRQ_SRC_ACCT_ERR)
+		readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
+}
+
+static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
+{
+	u32 val, burst_val;
+
+	val = readl(chan->regs + ZYNQMP_DMA_CTRL0);
+	val |= ZYNQMP_DMA_POINT_TYPE_SG;
+	writel(val, chan->regs + ZYNQMP_DMA_CTRL0);
+
+	val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR);
+	burst_val = __ilog2_u32(chan->src_burst_len);
+	val = (val & ~ZYNQMP_DMA_ARLEN) |
+		((burst_val << ZYNQMP_DMA_ARLEN_OFST) & ZYNQMP_DMA_ARLEN);
+	burst_val = __ilog2_u32(chan->dst_burst_len);
+	val = (val & ~ZYNQMP_DMA_AWLEN) |
+		((burst_val << ZYNQMP_DMA_AWLEN_OFST) & ZYNQMP_DMA_AWLEN);
+	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
+}
+
+/**
+ * zynqmp_dma_device_config - Zynqmp dma device configuration
+ * @dchan: DMA channel
+ * @config: DMA device config
+ *
+ * Return: 0 always
+ */
+static int zynqmp_dma_device_config(struct dma_chan *dchan,
+				    struct dma_slave_config *config)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+
+	chan->src_burst_len = clamp(config->src_maxburst, 1U,
+		ZYNQMP_DMA_MAX_SRC_BURST_LEN);
+	chan->dst_burst_len = clamp(config->dst_maxburst, 1U,
+		ZYNQMP_DMA_MAX_DST_BURST_LEN);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_start_transfer - Initiate the new transfer
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_start_transfer(struct zynqmp_dma_chan *chan)
+{
+	struct zynqmp_dma_desc_sw *desc;
+
+	if (!chan->idle)
+		return;
+
+	zynqmp_dma_config(chan);
+
+	desc = list_first_entry_or_null(&chan->pending_list,
+					struct zynqmp_dma_desc_sw, node);
+	if (!desc)
+		return;
+
+	list_splice_tail_init(&chan->pending_list, &chan->active_list);
+	zynqmp_dma_update_desc_to_ctrlr(chan, desc);
+	zynqmp_dma_start(chan);
+}
+
+
+/**
+ * zynqmp_dma_chan_desc_cleanup - Cleanup the completed descriptors
+ * @chan: ZynqMP DMA channel
+ */
+static void zynqmp_dma_chan_desc_cleanup(struct zynqmp_dma_chan *chan)
+{
+	struct zynqmp_dma_desc_sw *desc, *next;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+
+	list_for_each_entry_safe(desc, next, &chan->done_list, node) {
+		struct dmaengine_desc_callback cb;
+
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
+			spin_unlock_irqrestore(&chan->lock, irqflags);
+			dmaengine_desc_callback_invoke(&cb, NULL);
+			spin_lock_irqsave(&chan->lock, irqflags);
+		}
+
+		/* Run any dependencies, then free the descriptor */
+		zynqmp_dma_free_descriptor(chan, desc);
+	}
+
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+}
+
+/**
+ * zynqmp_dma_complete_descriptor - Mark the active descriptor as complete
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_complete_descriptor(struct zynqmp_dma_chan *chan)
+{
+	struct zynqmp_dma_desc_sw *desc;
+
+	desc = list_first_entry_or_null(&chan->active_list,
+					struct zynqmp_dma_desc_sw, node);
+	if (!desc)
+		return;
+	list_del(&desc->node);
+	dma_cookie_complete(&desc->async_tx);
+	list_add_tail(&desc->node, &chan->done_list);
+}
+
+/**
+ * zynqmp_dma_issue_pending - Issue pending transactions
+ * @dchan: DMA channel pointer
+ */
+static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	zynqmp_dma_start_transfer(chan);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+}
+
+/**
+ * zynqmp_dma_free_descriptors - Free channel descriptors
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	zynqmp_dma_free_desc_list(chan, &chan->active_list);
+	zynqmp_dma_free_desc_list(chan, &chan->pending_list);
+	zynqmp_dma_free_desc_list(chan, &chan->done_list);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+}
+
+/**
+ * zynqmp_dma_free_chan_resources - Free channel resources
+ * @dchan: DMA channel pointer
+ */
+static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+
+	zynqmp_dma_free_descriptors(chan);
+	dma_free_coherent(chan->dev,
+		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
+		chan->desc_pool_v, chan->desc_pool_p);
+	kfree(chan->sw_desc_pool);
+	pm_runtime_put_autosuspend(chan->dev);
+}
+
+/**
+ * zynqmp_dma_reset - Reset the channel
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_reset(struct zynqmp_dma_chan *chan)
+{
+	unsigned long irqflags;
+
+	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	zynqmp_dma_complete_descriptor(chan);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+	zynqmp_dma_chan_desc_cleanup(chan);
+	zynqmp_dma_free_descriptors(chan);
+
+	zynqmp_dma_init(chan);
+}
+
+/**
+ * zynqmp_dma_irq_handler - ZynqMP DMA Interrupt handler
+ * @irq: IRQ number
+ * @data: Pointer to the ZynqMP DMA channel structure
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t zynqmp_dma_irq_handler(int irq, void *data)
+{
+	struct zynqmp_dma_chan *chan = (struct zynqmp_dma_chan *)data;
+	u32 isr, imr, status;
+	irqreturn_t ret = IRQ_NONE;
+
+	isr = readl(chan->regs + ZYNQMP_DMA_ISR);
+	imr = readl(chan->regs + ZYNQMP_DMA_IMR);
+	status = isr & ~imr;
+
+	writel(isr, chan->regs + ZYNQMP_DMA_ISR);
+	if (status & ZYNQMP_DMA_INT_DONE) {
+		tasklet_schedule(&chan->tasklet);
+		ret = IRQ_HANDLED;
+	}
+
+	if (status & ZYNQMP_DMA_DONE)
+		chan->idle = true;
+
+	if (status & ZYNQMP_DMA_INT_ERR) {
+		chan->err = true;
+		tasklet_schedule(&chan->tasklet);
+		dev_err(chan->dev, "Channel %p has errors\n", chan);
+		ret = IRQ_HANDLED;
+	}
+
+	if (status & ZYNQMP_DMA_INT_OVRFL) {
+		zynqmp_dma_handle_ovfl_int(chan, status);
+		dev_dbg(chan->dev, "Channel %p overflow interrupt\n", chan);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+/**
+ * zynqmp_dma_do_tasklet - Schedule completion tasklet
+ * @t: Pointer to the ZynqMP DMA channel structure
+ */
+static void zynqmp_dma_do_tasklet(struct tasklet_struct *t)
+{
+	struct zynqmp_dma_chan *chan = from_tasklet(chan, t, tasklet);
+	u32 count;
+	unsigned long irqflags;
+
+	if (chan->err) {
+		zynqmp_dma_reset(chan);
+		chan->err = false;
+		return;
+	}
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	count = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
+	while (count) {
+		zynqmp_dma_complete_descriptor(chan);
+		count--;
+	}
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+
+	zynqmp_dma_chan_desc_cleanup(chan);
+
+	if (chan->idle) {
+		spin_lock_irqsave(&chan->lock, irqflags);
+		zynqmp_dma_start_transfer(chan);
+		spin_unlock_irqrestore(&chan->lock, irqflags);
+	}
+}
+
+/**
+ * zynqmp_dma_device_terminate_all - Aborts all transfers on a channel
+ * @dchan: DMA channel pointer
+ *
+ * Return: Always '0'
+ */
+static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+
+	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
+	zynqmp_dma_free_descriptors(chan);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_synchronize - Synchronizes the termination of a transfers to the current context.
+ * @dchan: DMA channel pointer
+ */
+static void zynqmp_dma_synchronize(struct dma_chan *dchan)
+{
+	struct zynqmp_dma_chan *chan = to_chan(dchan);
+
+	tasklet_kill(&chan->tasklet);
+}
+
+/**
+ * zynqmp_dma_prep_memcpy - prepare descriptors for memcpy transaction
+ * @dchan: DMA channel
+ * @dma_dst: Destination buffer address
+ * @dma_src: Source buffer address
+ * @len: Transfer length
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy(
+				struct dma_chan *dchan, dma_addr_t dma_dst,
+				dma_addr_t dma_src, size_t len, ulong flags)
+{
+	struct zynqmp_dma_chan *chan;
+	struct zynqmp_dma_desc_sw *new, *first = NULL;
+	void *desc = NULL, *prev = NULL;
+	size_t copy;
+	u32 desc_cnt;
+	unsigned long irqflags;
+
+	chan = to_chan(dchan);
+
+	desc_cnt = DIV_ROUND_UP(len, ZYNQMP_DMA_MAX_TRANS_LEN);
+
+	spin_lock_irqsave(&chan->lock, irqflags);
+	if (desc_cnt > chan->desc_free_cnt) {
+		spin_unlock_irqrestore(&chan->lock, irqflags);
+		dev_dbg(chan->dev, "chan %p descs are not available\n", chan);
+		return NULL;
+	}
+	chan->desc_free_cnt = chan->desc_free_cnt - desc_cnt;
+	spin_unlock_irqrestore(&chan->lock, irqflags);
+
+	do {
+		/* Allocate and populate the descriptor */
+		new = zynqmp_dma_get_descriptor(chan);
+
+		copy = min_t(size_t, len, ZYNQMP_DMA_MAX_TRANS_LEN);
+		desc = (struct zynqmp_dma_desc_ll *)new->src_v;
+		zynqmp_dma_config_sg_ll_desc(chan, desc, dma_src,
+					     dma_dst, copy, prev);
+		prev = desc;
+		len -= copy;
+		dma_src += copy;
+		dma_dst += copy;
+		if (!first)
+			first = new;
+		else
+			list_add_tail(&new->node, &first->tx_list);
+	} while (len);
+
+	zynqmp_dma_desc_config_eod(chan, desc);
+	async_tx_ack(&first->async_tx);
+	first->async_tx.flags = (enum dma_ctrl_flags)flags;
+	return &first->async_tx;
+}
+
+/**
+ * zynqmp_dma_chan_remove - Channel remove function
+ * @chan: ZynqMP DMA channel pointer
+ */
+static void zynqmp_dma_chan_remove(struct zynqmp_dma_chan *chan)
+{
+	if (!chan)
+		return;
+
+	if (chan->irq)
+		devm_free_irq(chan->zdev->dev, chan->irq, chan);
+	tasklet_kill(&chan->tasklet);
+	list_del(&chan->common.device_node);
+}
+
+/**
+ * zynqmp_dma_chan_probe - Per Channel Probing
+ * @zdev: Driver specific device structure
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,
+			   struct platform_device *pdev)
+{
+	struct zynqmp_dma_chan *chan;
+	struct device_node *node = pdev->dev.of_node;
+	const struct zynqmp_dma_config *match_data;
+	int err;
+
+	chan = devm_kzalloc(zdev->dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+	chan->dev = zdev->dev;
+	chan->zdev = zdev;
+
+	chan->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(chan->regs))
+		return PTR_ERR(chan->regs);
+
+	chan->bus_width = ZYNQMP_DMA_BUS_WIDTH_64;
+	chan->dst_burst_len = ZYNQMP_DMA_MAX_DST_BURST_LEN;
+	chan->src_burst_len = ZYNQMP_DMA_MAX_SRC_BURST_LEN;
+	err = of_property_read_u32(node, "xlnx,bus-width", &chan->bus_width);
+	if (err < 0) {
+		dev_err(&pdev->dev, "missing xlnx,bus-width property\n");
+		return err;
+	}
+
+	if (chan->bus_width != ZYNQMP_DMA_BUS_WIDTH_64 &&
+	    chan->bus_width != ZYNQMP_DMA_BUS_WIDTH_128) {
+		dev_err(zdev->dev, "invalid bus-width value");
+		return -EINVAL;
+	}
+
+	match_data = of_device_get_match_data(&pdev->dev);
+	if (match_data)
+		chan->irq_offset = match_data->offset;
+
+	chan->is_dmacoherent =  of_property_read_bool(node, "dma-coherent");
+	zdev->chan = chan;
+	tasklet_setup(&chan->tasklet, zynqmp_dma_do_tasklet);
+	spin_lock_init(&chan->lock);
+	INIT_LIST_HEAD(&chan->active_list);
+	INIT_LIST_HEAD(&chan->pending_list);
+	INIT_LIST_HEAD(&chan->done_list);
+	INIT_LIST_HEAD(&chan->free_list);
+
+	dma_cookie_init(&chan->common);
+	chan->common.device = &zdev->common;
+	list_add_tail(&chan->common.device_node, &zdev->common.channels);
+
+	zynqmp_dma_init(chan);
+	chan->irq = platform_get_irq(pdev, 0);
+	if (chan->irq < 0)
+		return -ENXIO;
+	err = devm_request_irq(&pdev->dev, chan->irq, zynqmp_dma_irq_handler, 0,
+			       "zynqmp-dma", chan);
+	if (err)
+		return err;
+
+	chan->desc_size = sizeof(struct zynqmp_dma_desc_ll);
+	chan->idle = true;
+	return 0;
+}
+
+/**
+ * of_zynqmp_dma_xlate - Translation function
+ * @dma_spec: Pointer to DMA specifier as found in the device tree
+ * @ofdma: Pointer to DMA controller data
+ *
+ * Return: DMA channel pointer on success and NULL on error
+ */
+static struct dma_chan *of_zynqmp_dma_xlate(struct of_phandle_args *dma_spec,
+					    struct of_dma *ofdma)
+{
+	struct zynqmp_dma_device *zdev = ofdma->of_dma_data;
+
+	return dma_get_slave_channel(&zdev->chan->common);
+}
+
+/**
+ * zynqmp_dma_suspend - Suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_suspend(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_suspend(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_resume - Resume from suspend
+ * @dev:	Address of the device structure
+ *
+ * Resume operation after suspend.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_resume(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_resume(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_suspend - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_suspend(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(zdev->clk_main);
+	clk_disable_unprepare(zdev->clk_apb);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_resume - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_resume(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(zdev->clk_main);
+	if (err) {
+		dev_err(dev, "Unable to enable main clock.\n");
+		return err;
+	}
+
+	err = clk_prepare_enable(zdev->clk_apb);
+	if (err) {
+		dev_err(dev, "Unable to enable apb clock.\n");
+		clk_disable_unprepare(zdev->clk_main);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops zynqmp_dma_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_dma_suspend, zynqmp_dma_resume)
+	SET_RUNTIME_PM_OPS(zynqmp_dma_runtime_suspend,
+			   zynqmp_dma_runtime_resume, NULL)
+};
+
+/**
+ * zynqmp_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int zynqmp_dma_probe(struct platform_device *pdev)
+{
+	struct zynqmp_dma_device *zdev;
+	struct dma_device *p;
+	int ret;
+
+	zdev = devm_kzalloc(&pdev->dev, sizeof(*zdev), GFP_KERNEL);
+	if (!zdev)
+		return -ENOMEM;
+
+	zdev->dev = &pdev->dev;
+	INIT_LIST_HEAD(&zdev->common.channels);
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44));
+	if (ret) {
+		dev_err(&pdev->dev, "DMA not available for address range\n");
+		return ret;
+	}
+	dma_cap_set(DMA_MEMCPY, zdev->common.cap_mask);
+
+	p = &zdev->common;
+	p->device_prep_dma_memcpy = zynqmp_dma_prep_memcpy;
+	p->device_terminate_all = zynqmp_dma_device_terminate_all;
+	p->device_synchronize = zynqmp_dma_synchronize;
+	p->device_issue_pending = zynqmp_dma_issue_pending;
+	p->device_alloc_chan_resources = zynqmp_dma_alloc_chan_resources;
+	p->device_free_chan_resources = zynqmp_dma_free_chan_resources;
+	p->device_tx_status = dma_cookie_status;
+	p->device_config = zynqmp_dma_device_config;
+	p->dev = &pdev->dev;
+
+	zdev->clk_main = devm_clk_get(&pdev->dev, "clk_main");
+	if (IS_ERR(zdev->clk_main))
+		return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_main),
+				     "main clock not found.\n");
+
+	zdev->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
+	if (IS_ERR(zdev->clk_apb))
+		return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_apb),
+				     "apb clock not found.\n");
+
+	platform_set_drvdata(pdev, zdev);
+	pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(zdev->dev);
+	pm_runtime_enable(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)
+			return ret;
+	}
+
+	ret = zynqmp_dma_chan_probe(zdev, pdev);
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "Probing channel failed\n");
+		goto err_disable_pm;
+	}
+
+	p->dst_addr_widths = BIT(zdev->chan->bus_width / 8);
+	p->src_addr_widths = BIT(zdev->chan->bus_width / 8);
+
+	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);
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "Unable to register DMA to DT\n");
+		dma_async_device_unregister(&zdev->common);
+		goto free_chan_resources;
+	}
+
+	pm_runtime_put_sync_autosuspend(zdev->dev);
+
+	return 0;
+
+free_chan_resources:
+	zynqmp_dma_chan_remove(zdev->chan);
+err_disable_pm:
+	if (!pm_runtime_enabled(zdev->dev))
+		zynqmp_dma_runtime_suspend(zdev->dev);
+	pm_runtime_disable(zdev->dev);
+	return ret;
+}
+
+/**
+ * zynqmp_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: Always '0'
+ */
+static void zynqmp_dma_remove(struct platform_device *pdev)
+{
+	struct zynqmp_dma_device *zdev = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&zdev->common);
+
+	zynqmp_dma_chan_remove(zdev->chan);
+	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[] = {
+	{ .compatible = "amd,versal2-dma-1.0", .data = &versal2_dma_config },
+	{ .compatible = "xlnx,zynqmp-dma-1.0", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, zynqmp_dma_of_match);
+
+static struct platform_driver zynqmp_dma_driver = {
+	.driver = {
+		.name = "xilinx-zynqmp-dma",
+		.of_match_table = zynqmp_dma_of_match,
+		.pm = &zynqmp_dma_dev_pm_ops,
+	},
+	.probe = zynqmp_dma_probe,
+	.remove = zynqmp_dma_remove,
+	.shutdown = zynqmp_dma_remove,
+};
+
+module_platform_driver(zynqmp_dma_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Xilinx, Inc.");
+MODULE_DESCRIPTION("Xilinx ZynqMP DMA driver");