ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

15 files changed, 4284 insertions, 0 deletions

diff --git a/drivers/dma/dw-edma/Kconfig b/drivers/dma/dw-edma/Kconfig
new file mode 100644
index 000000000..2b6f26795
--- /dev/null
+++ b/drivers/dma/dw-edma/Kconfig
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config DW_EDMA
+	tristate "Synopsys DesignWare eDMA controller driver"
+	depends on PCI && PCI_MSI
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the Synopsys DesignWare eDMA controller, normally
+	  implemented on endpoints SoCs.
+
+if DW_EDMA
+
+config DW_EDMA_PCIE
+	tristate "Synopsys DesignWare eDMA PCIe driver"
+	depends on PCI && PCI_MSI
+	help
+	  Provides a glue-logic between the Synopsys DesignWare
+	  eDMA controller and an endpoint PCIe device. This also serves
+	  as a reference design to whom desires to use this IP.
+
+endif # DW_EDMA
diff --git a/drivers/dma/dw-edma/Makefile b/drivers/dma/dw-edma/Makefile
new file mode 100644
index 000000000..83ab58f87
--- /dev/null
+++ b/drivers/dma/dw-edma/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_DW_EDMA)		+= dw-edma.o
+dw-edma-$(CONFIG_DEBUG_FS)	:= dw-edma-v0-debugfs.o	\
+				   dw-hdma-v0-debugfs.o
+dw-edma-objs			:= dw-edma-core.o	\
+				   dw-edma-v0-core.o	\
+				   dw-hdma-v0-core.o $(dw-edma-y)
+obj-$(CONFIG_DW_EDMA_PCIE)	+= dw-edma-pcie.o
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
new file mode 100644
index 000000000..03b2c2188
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -0,0 +1,1308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA core driver
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/dmaengine.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/dma/edma.h>
+#include <linux/dma-mapping.h>
+#include <linux/string_choices.h>
+
+#include "dw-edma-core.h"
+#include "dw-edma-v0-core.h"
+#include "dw-hdma-v0-core.h"
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+static inline
+struct dw_edma_desc *vd2dw_edma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct dw_edma_desc, vd);
+}
+
+enum dw_edma_irq_event {
+	DW_EDMA_IRQ_DONE	= BIT(0),
+	DW_EDMA_IRQ_ABORT	= BIT(1),
+};
+
+static inline
+u64 dw_edma_get_pci_address(struct dw_edma_chan *chan, phys_addr_t cpu_addr)
+{
+	struct dw_edma_chip *chip = chan->dw->chip;
+
+	if (chip->ops->pci_address)
+		return chip->ops->pci_address(chip->dev, cpu_addr);
+
+	return cpu_addr;
+}
+
+static struct dw_edma_desc *
+dw_edma_alloc_desc(struct dw_edma_chan *chan, size_t nburst)
+{
+	struct dw_edma_desc *desc;
+
+	desc = kzalloc_flex(*desc, burst, nburst, GFP_NOWAIT);
+	if (unlikely(!desc))
+		return NULL;
+
+	desc->chan = chan;
+	desc->nburst = nburst;
+	desc->cb = true;
+
+	return desc;
+}
+
+static void vchan_free_desc(struct virt_dma_desc *vdesc)
+{
+	kfree(vd2dw_edma_desc(vdesc));
+}
+
+static void dw_edma_core_start(struct dw_edma_desc *desc, bool first)
+{
+	struct dw_edma_chan *chan = desc->chan;
+	size_t i = 0;
+
+	if (chan->non_ll) {
+		chan->dw->core->non_ll_start(chan, &desc->burst[desc->start_burst]);
+		desc->done_burst = desc->start_burst;
+		desc->start_burst += 1;
+		return;
+	}
+
+	for (i = 0; i + desc->start_burst < desc->nburst; i++) {
+		u32 idx = i + desc->start_burst;
+
+		if (i == chan->ll_max)
+			break;
+
+		dw_edma_core_ll_data(chan, &desc->burst[idx],
+				     i, desc->cb,
+				     idx == desc->nburst - 1 || i == chan->ll_max - 1);
+	}
+
+	desc->done_burst = desc->start_burst;
+	desc->start_burst += i;
+
+	dw_edma_core_ll_link(chan, i, desc->cb, chan->ll_region.paddr);
+
+	if (first)
+		dw_edma_core_ch_enable(chan);
+
+	dw_edma_core_ch_doorbell(chan);
+}
+
+static int dw_edma_start_transfer(struct dw_edma_chan *chan)
+{
+	struct dw_edma_desc *desc;
+	struct virt_dma_desc *vd;
+
+	vd = vchan_next_desc(&chan->vc);
+	if (!vd)
+		return 0;
+
+	desc = vd2dw_edma_desc(vd);
+	if (!desc)
+		return 0;
+
+	dw_edma_core_start(desc, !desc->start_burst);
+
+	desc->cb = !desc->cb;
+
+	return 1;
+}
+
+static void dw_edma_terminate_vdesc(struct virt_dma_desc *vd)
+{
+	list_del(&vd->node);
+	dma_cookie_complete(&vd->tx);
+	vchan_terminate_vdesc(vd);
+}
+
+static void dw_edma_terminate_vdesc_list(struct list_head *head)
+{
+	struct virt_dma_desc *vd, *_vd;
+
+	list_for_each_entry_safe(vd, _vd, head, node)
+		dw_edma_terminate_vdesc(vd);
+}
+
+/* Must be called with vc.lock held. */
+static void dw_edma_terminate_all_descs(struct dw_edma_chan *chan)
+{
+	/*
+	 * This order must not be reversed. Cookies are assigned when
+	 * descriptors are submitted, so desc_issued contains older cookies
+	 * than desc_submitted. Completing desc_submitted first could move
+	 * chan->vc.chan.completed_cookie backwards when desc_issued is
+	 * terminated afterwards.
+	 */
+	dw_edma_terminate_vdesc_list(&chan->vc.desc_issued);
+	dw_edma_terminate_vdesc_list(&chan->vc.desc_submitted);
+}
+
+static void dw_edma_device_caps(struct dma_chan *dchan,
+				struct dma_slave_caps *caps)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		if (chan->dir == EDMA_DIR_READ)
+			caps->directions = BIT(DMA_DEV_TO_MEM);
+		else
+			caps->directions = BIT(DMA_MEM_TO_DEV);
+	} else {
+		if (chan->dir == EDMA_DIR_WRITE)
+			caps->directions = BIT(DMA_DEV_TO_MEM);
+		else
+			caps->directions = BIT(DMA_MEM_TO_DEV);
+	}
+}
+
+static enum dw_edma_ch_irq_mode
+dw_edma_get_default_irq_mode(struct dw_edma_chan *chan)
+{
+	struct dw_edma_chip *chip = chan->dw->chip;
+
+	return chip->flags & DW_EDMA_CHIP_LOCAL ? DW_EDMA_CH_IRQ_LOCAL :
+						  DW_EDMA_CH_IRQ_REMOTE;
+}
+
+static int dw_edma_device_config(struct dma_chan *dchan,
+				 struct dma_slave_config *config)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	bool cfg_non_ll;
+	int non_ll = 0;
+
+	chan->non_ll = false;
+	if (chan->dw->chip->mf == EDMA_MF_HDMA_NATIVE) {
+		if (config->peripheral_config &&
+		    config->peripheral_size != sizeof(int)) {
+			dev_err(dchan->device->dev,
+				"config param peripheral size mismatch\n");
+			return -EINVAL;
+		}
+
+		/*
+		 * When there is no valid LLP base address available then the
+		 * default DMA ops will use the non-LL mode.
+		 *
+		 * Cases where LL mode is enabled and client wants to use the
+		 * non-LL mode then also client can do so via providing the
+		 * peripheral_config param.
+		 */
+		cfg_non_ll = chan->dw->chip->cfg_non_ll;
+		if (config->peripheral_config) {
+			non_ll = *(int *)config->peripheral_config;
+
+			if (cfg_non_ll && !non_ll) {
+				dev_err(dchan->device->dev, "invalid configuration\n");
+				return -EINVAL;
+			}
+		}
+
+		if (cfg_non_ll || non_ll)
+			chan->non_ll = true;
+	} else if (config->peripheral_config) {
+		dev_err(dchan->device->dev,
+			"peripheral config param applicable only for HDMA\n");
+		return -EINVAL;
+	}
+
+	memcpy(&chan->config, config, sizeof(*config));
+	chan->configured = true;
+
+	return 0;
+}
+
+static struct dma_slave_config *
+dw_edma_device_get_config(struct dma_chan *dchan,
+			  struct dma_slave_config *config)
+{
+	struct dw_edma_chan *chan;
+
+	if (config)
+		return config;
+
+	chan = dchan2dw_edma_chan(dchan);
+
+	return &chan->config;
+}
+
+static int dw_edma_device_pause(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	int err = 0;
+
+	guard(spinlock_irqsave)(&chan->vc.lock);
+
+	if (!chan->configured)
+		err = -EPERM;
+	else if (chan->status != EDMA_ST_BUSY)
+		err = -EPERM;
+	else if (chan->request != EDMA_REQ_NONE)
+		err = -EPERM;
+	else
+		chan->request = EDMA_REQ_PAUSE;
+
+	return err;
+}
+
+static int dw_edma_device_resume(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	int err = 0;
+
+	guard(spinlock_irqsave)(&chan->vc.lock);
+
+	if (!chan->configured) {
+		err = -EPERM;
+	} else if (chan->status != EDMA_ST_PAUSE) {
+		err = -EPERM;
+	} else if (chan->request != EDMA_REQ_NONE) {
+		err = -EPERM;
+	} else {
+		chan->status = EDMA_ST_BUSY;
+		if (!dw_edma_start_transfer(chan))
+			chan->status = EDMA_ST_IDLE;
+	}
+
+	return err;
+}
+
+static int dw_edma_device_terminate_all(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	int err = 0;
+
+	guard(spinlock_irqsave)(&chan->vc.lock);
+
+	if (!chan->configured) {
+		dw_edma_terminate_all_descs(chan);
+	} else if (chan->status == EDMA_ST_PAUSE) {
+		dw_edma_terminate_all_descs(chan);
+		chan->status = EDMA_ST_IDLE;
+	} else if (chan->status == EDMA_ST_IDLE) {
+		dw_edma_terminate_all_descs(chan);
+	} else if (dw_edma_core_ch_status(chan) == DMA_COMPLETE) {
+		/*
+		 * The channel is in a false BUSY state, probably didn't
+		 * receive or lost an interrupt
+		 */
+		dw_edma_terminate_all_descs(chan);
+		chan->status = EDMA_ST_IDLE;
+	} else if (chan->request > EDMA_REQ_PAUSE) {
+		err = -EPERM;
+	} else {
+		chan->request = EDMA_REQ_STOP;
+	}
+	if (chan->status == EDMA_ST_IDLE)
+		chan->request = EDMA_REQ_NONE;
+
+	return err;
+}
+
+static void dw_edma_device_issue_pending(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	if (chan->configured && vchan_issue_pending(&chan->vc) &&
+	    chan->request == EDMA_REQ_NONE &&
+	    chan->status == EDMA_ST_IDLE) {
+		chan->status = EDMA_ST_BUSY;
+		dw_edma_start_transfer(chan);
+	}
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+}
+
+static enum dma_status
+dw_edma_device_tx_status(struct dma_chan *dchan, dma_cookie_t cookie,
+			 struct dma_tx_state *txstate)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	struct dw_edma_desc *desc;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	enum dma_status ret;
+	u32 residue = 0;
+
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	if (ret == DMA_IN_PROGRESS && chan->status == EDMA_ST_PAUSE)
+		ret = DMA_PAUSED;
+
+	if (!txstate)
+		goto ret_residue;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	vd = vchan_find_desc(&chan->vc, cookie);
+	if (vd) {
+		desc = vd2dw_edma_desc(vd);
+
+		residue = desc->alloc_sz;
+		if (desc && desc->done_burst)
+			residue -= desc->burst[desc->done_burst - 1].xfer_sz;
+	}
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+ret_residue:
+	dma_set_residue(txstate, residue);
+
+	return ret;
+}
+
+static struct dma_async_tx_descriptor *
+dw_edma_device_transfer(struct dw_edma_transfer *xfer,
+			struct dma_slave_config *config)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
+	enum dma_transfer_direction dir = xfer->direction;
+	struct scatterlist *sg = NULL;
+	struct dw_edma_burst *burst;
+	struct dw_edma_desc *desc;
+	u64 src_addr, dst_addr;
+	size_t fsz = 0;
+	size_t cnt = 0;
+	u32 i;
+
+	if (!chan->configured)
+		return NULL;
+
+	/*
+	 * Local Root Port/End-point              Remote End-point
+	 * +-----------------------+ PCIe bus +----------------------+
+	 * |                       |    +-+   |                      |
+	 * |    DEV_TO_MEM   Rx Ch <----+ +---+ Tx Ch  DEV_TO_MEM    |
+	 * |                       |    | |   |                      |
+	 * |    MEM_TO_DEV   Tx Ch +----+ +---> Rx Ch  MEM_TO_DEV    |
+	 * |                       |    +-+   |                      |
+	 * +-----------------------+          +----------------------+
+	 *
+	 * 1. Normal logic:
+	 * If eDMA is embedded into the DW PCIe RP/EP and controlled from the
+	 * CPU/Application side, the Rx channel (EDMA_DIR_READ) will be used
+	 * for the device read operations (DEV_TO_MEM) and the Tx channel
+	 * (EDMA_DIR_WRITE) - for the write operations (MEM_TO_DEV).
+	 *
+	 * 2. Inverted logic:
+	 * If eDMA is embedded into a Remote PCIe EP and is controlled by the
+	 * MWr/MRd TLPs sent from the CPU's PCIe host controller, the Tx
+	 * channel (EDMA_DIR_WRITE) will be used for the device read operations
+	 * (DEV_TO_MEM) and the Rx channel (EDMA_DIR_READ) - for the write
+	 * operations (MEM_TO_DEV).
+	 *
+	 * It is the client driver responsibility to choose a proper channel
+	 * for the DMA transfers.
+	 */
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		if ((chan->dir == EDMA_DIR_READ && dir != DMA_DEV_TO_MEM) ||
+		    (chan->dir == EDMA_DIR_WRITE && dir != DMA_MEM_TO_DEV))
+			return NULL;
+	} else {
+		if ((chan->dir == EDMA_DIR_WRITE && dir != DMA_DEV_TO_MEM) ||
+		    (chan->dir == EDMA_DIR_READ && dir != DMA_MEM_TO_DEV))
+			return NULL;
+	}
+
+	if (xfer->type == EDMA_XFER_CYCLIC) {
+		if (!xfer->xfer.cyclic.len || !xfer->xfer.cyclic.cnt)
+			return NULL;
+	} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+		if (xfer->xfer.sg.len < 1)
+			return NULL;
+	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		if (!xfer->xfer.il->numf || xfer->xfer.il->frame_size < 1)
+			return NULL;
+		if (!xfer->xfer.il->src_inc || !xfer->xfer.il->dst_inc)
+			return NULL;
+	} else {
+		return NULL;
+	}
+
+	if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		src_addr = xfer->xfer.il->src_start;
+		dst_addr = xfer->xfer.il->dst_start;
+	} else {
+		src_addr = config->src_addr;
+		dst_addr = config->dst_addr;
+	}
+
+	if (dir == DMA_DEV_TO_MEM)
+		src_addr = dw_edma_get_pci_address(chan, (phys_addr_t)src_addr);
+	else
+		dst_addr = dw_edma_get_pci_address(chan, (phys_addr_t)dst_addr);
+
+	if (xfer->type == EDMA_XFER_CYCLIC) {
+		cnt = xfer->xfer.cyclic.cnt;
+	} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+		cnt = xfer->xfer.sg.len;
+		sg = xfer->xfer.sg.sgl;
+	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+		cnt = xfer->xfer.il->numf * xfer->xfer.il->frame_size;
+		fsz = xfer->xfer.il->frame_size;
+	}
+
+	desc = dw_edma_alloc_desc(chan, cnt);
+	if (unlikely(!desc))
+		return NULL;
+
+	for (i = 0; i < cnt; i++) {
+		if (xfer->type == EDMA_XFER_SCATTER_GATHER && !sg)
+			break;
+
+		burst = desc->burst + i;
+
+		if (xfer->type == EDMA_XFER_CYCLIC)
+			burst->sz = xfer->xfer.cyclic.len;
+		else if (xfer->type == EDMA_XFER_SCATTER_GATHER)
+			burst->sz = sg_dma_len(sg);
+		else if (xfer->type == EDMA_XFER_INTERLEAVED)
+			burst->sz = xfer->xfer.il->sgl[i % fsz].size;
+
+		desc->alloc_sz += burst->sz;
+		burst->xfer_sz = desc->alloc_sz;
+
+		if (dir == DMA_DEV_TO_MEM) {
+			burst->sar = src_addr;
+			if (xfer->type == EDMA_XFER_CYCLIC) {
+				burst->dar = xfer->xfer.cyclic.paddr;
+			} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+				src_addr += sg_dma_len(sg);
+				burst->dar = sg_dma_address(sg);
+				/* Unlike the typical assumption by other
+				 * drivers/IPs the peripheral memory isn't
+				 * a FIFO memory, in this case, it's a
+				 * linear memory and that why the source
+				 * and destination addresses are increased
+				 * by the same portion (data length)
+				 */
+			} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+				burst->dar = dst_addr;
+			}
+		} else {
+			burst->dar = dst_addr;
+			if (xfer->type == EDMA_XFER_CYCLIC) {
+				burst->sar = xfer->xfer.cyclic.paddr;
+			} else if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+				dst_addr += sg_dma_len(sg);
+				burst->sar = sg_dma_address(sg);
+				/* Unlike the typical assumption by other
+				 * drivers/IPs the peripheral memory isn't
+				 * a FIFO memory, in this case, it's a
+				 * linear memory and that why the source
+				 * and destination addresses are increased
+				 * by the same portion (data length)
+				 */
+			}  else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+				burst->sar = src_addr;
+			}
+		}
+
+		if (xfer->type == EDMA_XFER_SCATTER_GATHER) {
+			sg = sg_next(sg);
+		} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
+			struct dma_interleaved_template *il = xfer->xfer.il;
+			struct data_chunk *dc = &il->sgl[i % fsz];
+
+			src_addr += burst->sz;
+			if (il->src_sgl)
+				src_addr += dmaengine_get_src_icg(il, dc);
+
+			dst_addr += burst->sz;
+			if (il->dst_sgl)
+				dst_addr += dmaengine_get_dst_icg(il, dc);
+		}
+	}
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, xfer->flags);
+}
+
+static struct dma_async_tx_descriptor *
+dw_edma_device_prep_config_sg(struct dma_chan *dchan, struct scatterlist *sgl,
+			      unsigned int len,
+			      enum dma_transfer_direction direction,
+			      unsigned long flags,
+			      struct dma_slave_config *config)
+{
+	struct dw_edma_transfer xfer;
+
+	xfer.dchan = dchan;
+	xfer.direction = direction;
+	xfer.xfer.sg.sgl = sgl;
+	xfer.xfer.sg.len = len;
+	xfer.flags = flags;
+	xfer.type = EDMA_XFER_SCATTER_GATHER;
+
+	if (config && dw_edma_device_config(dchan, config))
+		return NULL;
+
+	return dw_edma_device_transfer(&xfer, dw_edma_device_get_config(dchan, config));
+}
+
+static struct dma_async_tx_descriptor *
+dw_edma_device_prep_dma_cyclic(struct dma_chan *dchan, dma_addr_t paddr,
+			       size_t len, size_t count,
+			       enum dma_transfer_direction direction,
+			       unsigned long flags)
+{
+	struct dw_edma_transfer xfer;
+
+	xfer.dchan = dchan;
+	xfer.direction = direction;
+	xfer.xfer.cyclic.paddr = paddr;
+	xfer.xfer.cyclic.len = len;
+	xfer.xfer.cyclic.cnt = count;
+	xfer.flags = flags;
+	xfer.type = EDMA_XFER_CYCLIC;
+
+	return dw_edma_device_transfer(&xfer, dw_edma_device_get_config(dchan, NULL));
+}
+
+static struct dma_async_tx_descriptor *
+dw_edma_device_prep_interleaved_dma(struct dma_chan *dchan,
+				    struct dma_interleaved_template *ilt,
+				    unsigned long flags)
+{
+	struct dw_edma_transfer xfer;
+
+	xfer.dchan = dchan;
+	xfer.direction = ilt->dir;
+	xfer.xfer.il = ilt;
+	xfer.flags = flags;
+	xfer.type = EDMA_XFER_INTERLEAVED;
+
+	return dw_edma_device_transfer(&xfer, dw_edma_device_get_config(dchan, NULL));
+}
+
+static void dw_hdma_set_callback_result(struct virt_dma_desc *vd,
+					enum dmaengine_tx_result result)
+{
+	u32 residue = 0;
+	struct dw_edma_desc *desc;
+	struct dmaengine_result *res;
+
+	if (!vd->tx.callback_result)
+		return;
+
+	desc = vd2dw_edma_desc(vd);
+	if (desc) {
+		residue = desc->alloc_sz;
+
+		if (result == DMA_TRANS_NOERROR)
+			residue -= desc->burst[desc->start_burst - 1].xfer_sz;
+		else if (desc->done_burst)
+			residue -= desc->burst[desc->done_burst - 1].xfer_sz;
+	}
+
+	res = &vd->tx_result;
+	res->result = result;
+	res->residue = residue;
+}
+
+static void dw_edma_done_interrupt(struct dw_edma_chan *chan)
+{
+	struct dw_edma_desc *desc;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	if (chan->status == EDMA_ST_PAUSE) {
+		spin_unlock_irqrestore(&chan->vc.lock, flags);
+		return;
+	}
+
+	vd = vchan_next_desc(&chan->vc);
+	if (vd) {
+		switch (chan->request) {
+		case EDMA_REQ_NONE:
+		case EDMA_REQ_PAUSE:
+			desc = vd2dw_edma_desc(vd);
+			if (desc->start_burst >= desc->nburst) {
+				dw_hdma_set_callback_result(vd,
+							    DMA_TRANS_NOERROR);
+				list_del(&vd->node);
+				vchan_cookie_complete(vd);
+			}
+
+			if (chan->request == EDMA_REQ_PAUSE) {
+				chan->request = EDMA_REQ_NONE;
+				chan->status = EDMA_ST_PAUSE;
+				break;
+			}
+
+			/* Continue transferring if there are remaining chunks or issued requests.
+			 */
+			chan->status = dw_edma_start_transfer(chan) ? EDMA_ST_BUSY : EDMA_ST_IDLE;
+			break;
+
+		case EDMA_REQ_STOP:
+			dw_edma_terminate_all_descs(chan);
+			chan->request = EDMA_REQ_NONE;
+			chan->status = EDMA_ST_IDLE;
+			break;
+
+		default:
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+}
+
+static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
+{
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+	vd = vchan_next_desc(&chan->vc);
+	if (vd && chan->request == EDMA_REQ_STOP) {
+		dw_edma_terminate_all_descs(chan);
+	} else if (vd) {
+		dw_hdma_set_callback_result(vd, DMA_TRANS_ABORTED);
+		list_del(&vd->node);
+		vchan_cookie_complete(vd);
+	}
+	chan->request = EDMA_REQ_NONE;
+	chan->status = EDMA_ST_IDLE;
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+}
+
+static void dw_edma_irq_work(struct work_struct *work)
+{
+	struct dw_edma_chan *chan = container_of(work, struct dw_edma_chan,
+						 irq_work);
+	unsigned int events;
+
+	do {
+		events = atomic_xchg(&chan->irq_pending, 0);
+
+		if (events & DW_EDMA_IRQ_DONE)
+			dw_edma_done_interrupt(chan);
+		if (events & DW_EDMA_IRQ_ABORT)
+			dw_edma_abort_interrupt(chan);
+	} while (atomic_read(&chan->irq_pending));
+}
+
+static void dw_edma_queue_irq_work(struct dw_edma_chan *chan,
+				   enum dw_edma_irq_event event)
+{
+	atomic_or(event, &chan->irq_pending);
+	queue_work(chan->dw->wq, &chan->irq_work);
+}
+
+static void dw_edma_done_interrupt_deferred(struct dw_edma_chan *chan)
+{
+	dw_edma_queue_irq_work(chan, DW_EDMA_IRQ_DONE);
+}
+
+static void dw_edma_abort_interrupt_deferred(struct dw_edma_chan *chan)
+{
+	dw_edma_queue_irq_work(chan, DW_EDMA_IRQ_ABORT);
+}
+
+static void dw_edma_emul_irq_ack(struct irq_data *d)
+{
+	struct dw_edma *dw = irq_data_get_irq_chip_data(d);
+
+	dw_edma_core_ack_emulated_irq(dw);
+}
+
+/*
+ * irq_chip implementation for interrupt-emulation doorbells.
+ *
+ * The emulated source has no mask/unmask mechanism. With handle_level_irq(),
+ * the flow is therefore:
+ *   1) .irq_ack() deasserts the source
+ *   2) registered handlers (if any) are dispatched
+ * Since deassertion is already done in .irq_ack(), handlers do not need to take
+ * care of it, hence IRQCHIP_ONESHOT_SAFE.
+ */
+static struct irq_chip dw_edma_emul_irqchip = {
+	.name		= "dw-edma-emul",
+	.irq_ack	= dw_edma_emul_irq_ack,
+	.flags		= IRQCHIP_ONESHOT_SAFE | IRQCHIP_SKIP_SET_WAKE,
+};
+
+static int dw_edma_emul_irq_alloc(struct dw_edma *dw)
+{
+	struct dw_edma_chip *chip = dw->chip;
+	int virq;
+
+	chip->db_irq = 0;
+	chip->db_offset = ~0;
+
+	if (chip->flags & DW_EDMA_CHIP_PARTIAL)
+		return 0;
+
+	/*
+	 * Only meaningful when the core provides the deassert sequence
+	 * for interrupt emulation.
+	 */
+	if (!dw->core->ack_emulated_irq)
+		return 0;
+
+	/*
+	 * Allocate a single, requestable Linux virtual IRQ number.
+	 * Use >= 1 so that 0 can remain a "not available" sentinel.
+	 */
+	virq = irq_alloc_desc(NUMA_NO_NODE);
+	if (virq < 0)
+		return virq;
+
+	irq_set_chip_and_handler(virq, &dw_edma_emul_irqchip, handle_level_irq);
+	irq_set_status_flags(virq, IRQ_LEVEL);
+	irq_set_chip_data(virq, dw);
+	irq_set_noprobe(virq);
+
+	chip->db_irq = virq;
+	chip->db_offset = dw_edma_core_db_offset(dw);
+
+	return 0;
+}
+
+static void dw_edma_emul_irq_free(struct dw_edma *dw)
+{
+	struct dw_edma_chip *chip = dw->chip;
+
+	if (!chip)
+		return;
+	if (chip->db_irq <= 0)
+		return;
+
+	irq_free_descs(chip->db_irq, 1);
+	chip->db_irq = 0;
+	chip->db_offset = ~0;
+}
+
+static inline irqreturn_t dw_edma_interrupt_emulated(void *data)
+{
+	struct dw_edma_irq *dw_irq = data;
+	struct dw_edma *dw = dw_irq->dw;
+	int db_irq = dw->chip->db_irq;
+
+	if (db_irq > 0) {
+		/*
+		 * Interrupt emulation may assert the IRQ line without updating the
+		 * normal DONE/ABORT status bits. With a shared IRQ handler we
+		 * cannot reliably detect such events by status registers alone, so
+		 * always perform the core-specific deassert sequence.
+		 */
+		generic_handle_irq(db_irq);
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
+
+static inline irqreturn_t dw_edma_interrupt_write_inner(int irq, void *data)
+{
+	struct dw_edma_irq *dw_irq = data;
+
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_WRITE,
+				       dw_edma_done_interrupt_deferred,
+				       dw_edma_abort_interrupt_deferred);
+}
+
+static inline irqreturn_t dw_edma_interrupt_read_inner(int irq, void *data)
+{
+	struct dw_edma_irq *dw_irq = data;
+
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_READ,
+				       dw_edma_done_interrupt_deferred,
+				       dw_edma_abort_interrupt_deferred);
+}
+
+static inline irqreturn_t dw_edma_interrupt_write(int irq, void *data)
+{
+	irqreturn_t ret = IRQ_NONE;
+
+	ret |= dw_edma_interrupt_write_inner(irq, data);
+	ret |= dw_edma_interrupt_emulated(data);
+
+	return ret;
+}
+
+static inline irqreturn_t dw_edma_interrupt_read(int irq, void *data)
+{
+	irqreturn_t ret = IRQ_NONE;
+
+	ret |= dw_edma_interrupt_read_inner(irq, data);
+	ret |= dw_edma_interrupt_emulated(data);
+
+	return ret;
+}
+
+static inline irqreturn_t dw_edma_interrupt_common(int irq, void *data)
+{
+	irqreturn_t ret = IRQ_NONE;
+
+	ret |= dw_edma_interrupt_write_inner(irq, data);
+	ret |= dw_edma_interrupt_read_inner(irq, data);
+	ret |= dw_edma_interrupt_emulated(data);
+
+	return ret;
+}
+
+static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+
+	if (chan->status != EDMA_ST_IDLE)
+		return -EBUSY;
+
+	return 0;
+}
+
+static void dw_edma_wait_termination(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	unsigned long timeout = jiffies + msecs_to_jiffies(5000);
+	bool stopping;
+
+	/*
+	 * A STOP may be deferred to a later interrupt while the channel is still
+	 * running. Wait until that handler completes the termination.
+	 */
+	while (time_before(jiffies, timeout)) {
+		scoped_guard(spinlock_irqsave, &chan->vc.lock)
+			stopping = chan->request == EDMA_REQ_STOP;
+
+		if (!stopping)
+			return;
+
+		fsleep(1000);
+	}
+
+	dev_warn(chan->dw->chip->dev,
+		 "timeout waiting for channel termination\n");
+}
+
+static void dw_edma_device_synchronize(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+
+	dw_edma_wait_termination(dchan);
+	cancel_work_sync(&chan->irq_work);
+	atomic_set(&chan->irq_pending, 0);
+	vchan_synchronize(&chan->vc);
+}
+
+static void dw_edma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+
+	dw_edma_device_terminate_all(dchan);
+	dw_edma_device_synchronize(dchan);
+
+	scoped_guard(spinlock_irqsave, &chan->vc.lock)
+		chan->configured = false;
+
+	vchan_free_chan_resources(&chan->vc);
+}
+
+static int dw_edma_channel_setup(struct dw_edma *dw, u32 wr_alloc, u32 rd_alloc)
+{
+	struct dw_edma_chip *chip = dw->chip;
+	struct device *dev = chip->dev;
+	struct dw_edma_chan *chan;
+	struct dw_edma_irq *irq;
+	struct dma_device *dma;
+	u32 i, ch_cnt;
+	u32 pos;
+
+	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
+	dma = &dw->dma;
+
+	INIT_LIST_HEAD(&dma->channels);
+
+	for (i = 0; i < ch_cnt; i++) {
+		chan = &dw->chan[i];
+
+		chan->dw = dw;
+		chan->func_no = chip->func_no;
+
+		if (i < dw->wr_ch_cnt) {
+			chan->id = i;
+			chan->dir = EDMA_DIR_WRITE;
+		} else {
+			chan->id = i - dw->wr_ch_cnt;
+			chan->dir = EDMA_DIR_READ;
+		}
+
+		chan->configured = false;
+		chan->request = EDMA_REQ_NONE;
+		chan->status = EDMA_ST_IDLE;
+		chan->irq_mode = dw_edma_get_default_irq_mode(chan);
+		INIT_WORK(&chan->irq_work, dw_edma_irq_work);
+		atomic_set(&chan->irq_pending, 0);
+
+		if (chan->dir == EDMA_DIR_WRITE)
+			chan->ll_region = chip->ll_region_wr[chan->id];
+		else
+			chan->ll_region = chip->ll_region_rd[chan->id];
+
+		chan->ll_max = chan->ll_region.sz / EDMA_LL_SZ - 1;
+
+		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
+			 str_write_read(chan->dir == EDMA_DIR_WRITE),
+			 chan->id, chan->ll_max);
+
+		if (dw->nr_irqs == 1)
+			pos = 0;
+		else if (chan->dir == EDMA_DIR_WRITE)
+			pos = chan->id % wr_alloc;
+		else
+			pos = wr_alloc + chan->id % rd_alloc;
+
+		irq = &dw->irq[pos];
+
+		if (chan->dir == EDMA_DIR_WRITE)
+			bitmap_set(irq->wr_mask, chan->id, 1);
+		else
+			bitmap_set(irq->rd_mask, chan->id, 1);
+
+		memcpy(&chan->msi, &irq->msi, sizeof(chan->msi));
+
+		dev_vdbg(dev, "MSI:\t\tChannel %s[%u] addr=0x%.8x%.8x, data=0x%.8x\n",
+			 str_write_read(chan->dir == EDMA_DIR_WRITE),
+			 chan->id,
+			 chan->msi.address_hi, chan->msi.address_lo,
+			 chan->msi.data);
+
+		chan->vc.desc_free = vchan_free_desc;
+		chan->vc.chan.private = chan->dir == EDMA_DIR_WRITE ?
+					&dw->chip->dt_region_wr[chan->id] :
+					&dw->chip->dt_region_rd[chan->id];
+
+		vchan_init(&chan->vc, dma);
+
+		dw_edma_core_ch_config(chan);
+	}
+
+	/* Set DMA channel capabilities */
+	dma_cap_zero(dma->cap_mask);
+	dma_cap_set(DMA_SLAVE, dma->cap_mask);
+	dma_cap_set(DMA_CYCLIC, dma->cap_mask);
+	dma_cap_set(DMA_PRIVATE, dma->cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, dma->cap_mask);
+	dma->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	dma->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+
+	/* Set DMA channel callbacks */
+	dma->dev = chip->dev;
+	dma->device_alloc_chan_resources = dw_edma_alloc_chan_resources;
+	dma->device_free_chan_resources = dw_edma_free_chan_resources;
+	dma->device_caps = dw_edma_device_caps;
+	dma->device_config = dw_edma_device_config;
+	dma->device_pause = dw_edma_device_pause;
+	dma->device_resume = dw_edma_device_resume;
+	dma->device_terminate_all = dw_edma_device_terminate_all;
+	dma->device_synchronize = dw_edma_device_synchronize;
+	dma->device_issue_pending = dw_edma_device_issue_pending;
+	dma->device_tx_status = dw_edma_device_tx_status;
+	dma->device_prep_config_sg = dw_edma_device_prep_config_sg;
+	dma->device_prep_dma_cyclic = dw_edma_device_prep_dma_cyclic;
+	dma->device_prep_interleaved_dma = dw_edma_device_prep_interleaved_dma;
+
+	dma_set_max_seg_size(dma->dev, U32_MAX);
+
+	/* Register DMA device */
+	return dma_async_device_register(dma);
+}
+
+static inline void dw_edma_dec_irq_alloc(int *nr_irqs, u32 *alloc, u16 cnt)
+{
+	if (*nr_irqs && *alloc < cnt) {
+		(*alloc)++;
+		(*nr_irqs)--;
+	}
+}
+
+static int dw_edma_irq_request(struct dw_edma *dw,
+			       u32 *wr_alloc, u32 *rd_alloc)
+{
+	struct dw_edma_chip *chip = dw->chip;
+	struct device *dev = dw->chip->dev;
+	struct msi_desc *msi_desc;
+	int i, err = 0;
+	u32 ch_cnt;
+	int irq;
+
+	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
+
+	if (chip->nr_irqs < 1 || !chip->ops->irq_vector)
+		return -EINVAL;
+
+	dw->irq = devm_kcalloc(dev, chip->nr_irqs, sizeof(*dw->irq), GFP_KERNEL);
+	if (!dw->irq)
+		return -ENOMEM;
+
+	if (chip->nr_irqs == 1) {
+		/* Common IRQ shared among all channels */
+		irq = chip->ops->irq_vector(dev, 0);
+		dw->irq[0].dw = dw;
+		err = request_irq(irq, dw_edma_interrupt_common,
+				  IRQF_SHARED, dw->name, &dw->irq[0]);
+		if (err) {
+			dw->nr_irqs = 0;
+			return err;
+		}
+
+		if (irq_get_msi_desc(irq))
+			get_cached_msi_msg(irq, &dw->irq[0].msi);
+
+		dw->nr_irqs = 1;
+	} else {
+		/* Distribute IRQs equally among all channels */
+		int tmp = chip->nr_irqs;
+
+		while (tmp && (*wr_alloc + *rd_alloc) < ch_cnt) {
+			dw_edma_dec_irq_alloc(&tmp, wr_alloc, dw->wr_ch_cnt);
+			dw_edma_dec_irq_alloc(&tmp, rd_alloc, dw->rd_ch_cnt);
+		}
+
+		for (i = 0; i < (*wr_alloc + *rd_alloc); i++) {
+			irq = chip->ops->irq_vector(dev, i);
+			dw->irq[i].dw = dw;
+			err = request_irq(irq,
+					  i < *wr_alloc ?
+						dw_edma_interrupt_write :
+						dw_edma_interrupt_read,
+					  IRQF_SHARED, dw->name,
+					  &dw->irq[i]);
+			if (err)
+				goto err_irq_free;
+			msi_desc = irq_get_msi_desc(irq);
+			if (msi_desc) {
+				get_cached_msi_msg(irq, &dw->irq[i].msi);
+				if (!msi_desc->pci.msi_attrib.is_msix)
+					dw->irq[i].msi.data = dw->irq[0].msi.data + i;
+			}
+		}
+
+		dw->nr_irqs = i;
+	}
+
+	return 0;
+
+err_irq_free:
+	for  (i--; i >= 0; i--) {
+		irq = chip->ops->irq_vector(dev, i);
+		free_irq(irq, &dw->irq[i]);
+	}
+
+	return err;
+}
+
+static int dw_edma_check_partial(struct dw_edma_chip *chip,
+				 u16 hw_wr_ch_cnt, u16 hw_rd_ch_cnt)
+{
+	if (!(chip->flags & DW_EDMA_CHIP_PARTIAL))
+		return 0;
+
+	if (chip->mf != EDMA_MF_EDMA_UNROLL &&
+	    chip->mf != EDMA_MF_HDMA_COMPAT)
+		return 0;
+
+	/*
+	 * Direction-wide registers are shared by all channels in that
+	 * direction, so a direction must have a single owner.
+	 */
+	if ((chip->ll_wr_cnt && chip->ll_wr_cnt != hw_wr_ch_cnt) ||
+	    (chip->ll_rd_cnt && chip->ll_rd_cnt != hw_rd_ch_cnt))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+int dw_edma_probe(struct dw_edma_chip *chip)
+{
+	struct device *dev;
+	struct dw_edma *dw;
+	u16 hw_wr_ch_cnt;
+	u16 hw_rd_ch_cnt;
+	u32 wr_alloc = 0;
+	u32 rd_alloc = 0;
+	u16 max_wr_cnt;
+	u16 max_rd_cnt;
+	int i, err;
+
+	if (!chip)
+		return -EINVAL;
+
+	dev = chip->dev;
+	if (!dev || !chip->ops)
+		return -EINVAL;
+
+	if (chip->flags & DW_EDMA_CHIP_PARTIAL) {
+		switch (chip->mf) {
+		case EDMA_MF_EDMA_UNROLL:
+		case EDMA_MF_HDMA_COMPAT:
+		case EDMA_MF_HDMA_NATIVE:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	dw = devm_kzalloc(dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	dw->chip = chip;
+
+	if (dw->chip->mf == EDMA_MF_HDMA_NATIVE) {
+		dw_hdma_v0_core_register(dw);
+		max_wr_cnt = HDMA_MAX_WR_CH;
+		max_rd_cnt = HDMA_MAX_RD_CH;
+	} else {
+		dw_edma_v0_core_register(dw);
+		max_wr_cnt = EDMA_MAX_WR_CH;
+		max_rd_cnt = EDMA_MAX_RD_CH;
+	}
+
+	raw_spin_lock_init(&dw->lock);
+
+	/*
+	 * chip->ll_*_cnt describes the channels exposed by this instance. Keep
+	 * the usable hardware counts separate for partial ownership checks.
+	 */
+	hw_wr_ch_cnt = min(dw_edma_core_ch_count(dw, EDMA_DIR_WRITE),
+			   max_wr_cnt);
+	hw_rd_ch_cnt = min(dw_edma_core_ch_count(dw, EDMA_DIR_READ),
+			   max_rd_cnt);
+
+	err = dw_edma_check_partial(chip, hw_wr_ch_cnt, hw_rd_ch_cnt);
+	if (err)
+		return err;
+
+	dw->wr_ch_cnt = min(chip->ll_wr_cnt, hw_wr_ch_cnt);
+	dw->rd_ch_cnt = min(chip->ll_rd_cnt, hw_rd_ch_cnt);
+
+	if (!dw->wr_ch_cnt && !dw->rd_ch_cnt)
+		return -EINVAL;
+
+	dev_vdbg(dev, "Channels:\twrite=%d, read=%d\n",
+		 dw->wr_ch_cnt, dw->rd_ch_cnt);
+
+	/* Allocate channels */
+	dw->chan = devm_kcalloc(dev, dw->wr_ch_cnt + dw->rd_ch_cnt,
+				sizeof(*dw->chan), GFP_KERNEL);
+	if (!dw->chan)
+		return -ENOMEM;
+
+	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%s",
+		 dev_name(chip->dev));
+
+	if (chip->flags & DW_EDMA_CHIP_PARTIAL) {
+		/*
+		 * Do not reset the shared controller, but drain stale state
+		 * from resources represented by this instance.
+		 */
+		err = dw_edma_core_quiesce(dw);
+		if (err)
+			return err;
+	} else {
+		/* Disable eDMA only when this instance owns the controller. */
+		dw_edma_core_off(dw);
+	}
+
+	/*
+	 * Deferred IRQ works are queued from the hard IRQ handlers, so the
+	 * workqueue must exist before any IRQ is requested.
+	 */
+	dw->wq = alloc_workqueue("dw-edma:%s", WQ_UNBOUND | WQ_HIGHPRI, 0,
+				 dev_name(chip->dev));
+	if (!dw->wq)
+		return -ENOMEM;
+
+	/* Request IRQs */
+	err = dw_edma_irq_request(dw, &wr_alloc, &rd_alloc);
+	if (err) {
+		destroy_workqueue(dw->wq);
+		return err;
+	}
+
+	/* Allocate a dedicated virtual IRQ for interrupt-emulation doorbells */
+	err = dw_edma_emul_irq_alloc(dw);
+	if (err)
+		dev_warn(dev, "Failed to allocate emulation IRQ: %d\n", err);
+
+	/* Setup write/read channels */
+	err = dw_edma_channel_setup(dw, wr_alloc, rd_alloc);
+	if (err)
+		goto err_irq_free;
+
+	/* Turn debugfs on */
+	dw_edma_core_debugfs_on(dw);
+
+	chip->dw = dw;
+
+	return 0;
+
+err_irq_free:
+	for (i = (dw->nr_irqs - 1); i >= 0; i--)
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
+	dw_edma_emul_irq_free(dw);
+	destroy_workqueue(dw->wq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dw_edma_probe);
+
+int dw_edma_remove(struct dw_edma_chip *chip)
+{
+	struct dw_edma_chan *chan, *_chan;
+	struct device *dev = chip->dev;
+	struct dw_edma *dw = chip->dw;
+	int i, err = 0;
+
+	/* Skip removal if no private data found */
+	if (!dw)
+		return -ENODEV;
+
+	if (chip->flags & DW_EDMA_CHIP_PARTIAL)
+		err = dw_edma_core_quiesce(dw);
+	else
+		dw_edma_core_off(dw);
+
+	/* Free irqs */
+	for (i = (dw->nr_irqs - 1); i >= 0; i--)
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
+	dw_edma_emul_irq_free(dw);
+
+	for (i = 0; i < dw->wr_ch_cnt + dw->rd_ch_cnt; i++)
+		cancel_work_sync(&dw->chan[i].irq_work);
+
+	destroy_workqueue(dw->wq);
+
+	/* Deregister eDMA device */
+	dma_async_device_unregister(&dw->dma);
+	list_for_each_entry_safe(chan, _chan, &dw->dma.channels,
+				 vc.chan.device_node) {
+		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dw_edma_remove);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare eDMA controller core driver");
+MODULE_AUTHOR("Gustavo Pimentel <gustavo.pimentel@synopsys.com>");
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
new file mode 100644
index 000000000..f6a5ad317
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -0,0 +1,290 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA core driver
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#ifndef _DW_EDMA_CORE_H
+#define _DW_EDMA_CORE_H
+
+#include <linux/atomic.h>
+#include <linux/msi.h>
+#include <linux/dma/edma.h>
+#include <linux/workqueue.h>
+
+#include "../virt-dma.h"
+
+#define EDMA_LL_SZ					24
+
+enum dw_edma_dir {
+	EDMA_DIR_WRITE = 0,
+	EDMA_DIR_READ
+};
+
+enum dw_edma_request {
+	EDMA_REQ_NONE = 0,
+	EDMA_REQ_STOP,
+	EDMA_REQ_PAUSE
+};
+
+enum dw_edma_status {
+	EDMA_ST_IDLE = 0,
+	EDMA_ST_PAUSE,
+	EDMA_ST_BUSY
+};
+
+enum dw_edma_xfer_type {
+	EDMA_XFER_SCATTER_GATHER = 0,
+	EDMA_XFER_CYCLIC,
+	EDMA_XFER_INTERLEAVED
+};
+
+struct dw_edma_chan;
+struct dw_edma_chunk;
+
+struct dw_edma_burst {
+	u64				sar;
+	u64				dar;
+	u32				sz;
+	/* precalulate summary of previous burst total size */
+	u32				xfer_sz;
+};
+
+struct dw_edma_desc {
+	struct virt_dma_desc		vd;
+	struct dw_edma_chan		*chan;
+
+	u32				alloc_sz;
+
+	size_t				done_burst;
+	size_t				start_burst;
+	u8				cb;
+	size_t				nburst;
+	struct dw_edma_burst            burst[] __counted_by(nburst);
+};
+
+struct dw_edma_chan {
+	struct virt_dma_chan		vc;
+	struct dw_edma			*dw;
+	int				id;
+	enum dw_edma_dir		dir;
+	u8				func_no;
+
+	u32				ll_max;
+	struct dw_edma_region		ll_region;	/* Linked list */
+
+	struct msi_msg			msi;
+
+	enum dw_edma_ch_irq_mode	irq_mode;
+
+	enum dw_edma_request		request;
+	enum dw_edma_status		status;
+	u8				configured;
+
+	struct dma_slave_config		config;
+	bool				non_ll;
+
+	struct work_struct		irq_work;
+	atomic_t			irq_pending;
+};
+
+struct dw_edma_irq {
+	struct msi_msg                  msi;
+	struct dw_edma			*dw;
+
+	DECLARE_BITMAP(wr_mask, HDMA_MAX_WR_CH);
+	DECLARE_BITMAP(rd_mask, HDMA_MAX_RD_CH);
+};
+
+struct dw_edma {
+	char				name[32];
+
+	struct dma_device		dma;
+
+	u16				wr_ch_cnt;
+	u16				rd_ch_cnt;
+
+	struct dw_edma_irq		*irq;
+	int				nr_irqs;
+
+	struct dw_edma_chan		*chan;
+
+	/*
+	 * WQ_HIGHPRI keeps completion processing responsive under heavy load;
+	 * WQ_UNBOUND lets different channels run on different CPUs.
+	 */
+	struct workqueue_struct		*wq;
+
+	raw_spinlock_t			lock;		/* Protect v0 shared registers */
+
+	struct dw_edma_chip             *chip;
+
+	const struct dw_edma_core_ops	*core;
+};
+
+typedef void (*dw_edma_handler_t)(struct dw_edma_chan *);
+
+struct dw_edma_core_ops {
+	void (*off)(struct dw_edma *dw);
+	int (*quiesce)(struct dw_edma *dw);
+	int (*ch_quiesce)(struct dw_edma_chan *chan);
+	u16 (*ch_count)(struct dw_edma *dw, enum dw_edma_dir dir);
+	enum dma_status (*ch_status)(struct dw_edma_chan *chan);
+	irqreturn_t (*handle_int)(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+				  dw_edma_handler_t done, dw_edma_handler_t abort);
+	void (*non_ll_start)(struct dw_edma_chan *chan, struct dw_edma_burst *child);
+	void (*ll_data)(struct dw_edma_chan *chan, struct dw_edma_burst *burst,
+			u32 idx, bool cb, bool irq);
+	void (*ll_link)(struct dw_edma_chan *chan, u32 idx, bool cb, u64 addr);
+	void (*ch_doorbell)(struct dw_edma_chan *chan);
+	void (*ch_enable)(struct dw_edma_chan *chan);
+	void (*ch_config)(struct dw_edma_chan *chan);
+	void (*debugfs_on)(struct dw_edma *dw);
+	void (*ack_emulated_irq)(struct dw_edma *dw);
+	resource_size_t (*db_offset)(struct dw_edma *dw);
+};
+
+struct dw_edma_sg {
+	struct scatterlist		*sgl;
+	unsigned int			len;
+};
+
+struct dw_edma_cyclic {
+	dma_addr_t			paddr;
+	size_t				len;
+	size_t				cnt;
+};
+
+struct dw_edma_transfer {
+	struct dma_chan			*dchan;
+	union dw_edma_xfer {
+		struct dw_edma_sg		sg;
+		struct dw_edma_cyclic		cyclic;
+		struct dma_interleaved_template *il;
+	} xfer;
+	enum dma_transfer_direction	direction;
+	unsigned long			flags;
+	enum dw_edma_xfer_type		type;
+};
+
+static inline
+struct dw_edma_chan *vc2dw_edma_chan(struct virt_dma_chan *vc)
+{
+	return container_of(vc, struct dw_edma_chan, vc);
+}
+
+static inline
+struct dw_edma_chan *dchan2dw_edma_chan(struct dma_chan *dchan)
+{
+	return vc2dw_edma_chan(to_virt_chan(dchan));
+}
+
+static inline u64 dw_edma_core_get_ll_paddr(struct dw_edma_chan *chan)
+{
+	if (chan->dir == EDMA_DIR_WRITE)
+		return chan->dw->chip->ll_region_wr[chan->id].paddr;
+
+	return chan->dw->chip->ll_region_rd[chan->id].paddr;
+}
+
+static inline
+void dw_edma_core_off(struct dw_edma *dw)
+{
+	dw->core->off(dw);
+}
+
+static inline
+int dw_edma_core_quiesce(struct dw_edma *dw)
+{
+	return dw->core->quiesce(dw);
+}
+
+static inline
+int dw_edma_core_ch_quiesce(struct dw_edma_chan *chan)
+{
+	return chan->dw->core->ch_quiesce(chan);
+}
+
+static inline
+u16 dw_edma_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	return dw->core->ch_count(dw, dir);
+}
+
+static inline
+enum dma_status dw_edma_core_ch_status(struct dw_edma_chan *chan)
+{
+	return chan->dw->core->ch_status(chan);
+}
+
+static inline irqreturn_t
+dw_edma_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	return dw_irq->dw->core->handle_int(dw_irq, dir, done, abort);
+}
+
+static inline
+void dw_edma_core_ch_config(struct dw_edma_chan *chan)
+{
+	chan->dw->core->ch_config(chan);
+}
+
+static inline void
+dw_edma_core_ll_data(struct dw_edma_chan *chan, struct dw_edma_burst *burst,
+		     u32 idx, bool cb, bool irq)
+{
+	chan->dw->core->ll_data(chan, burst, idx, cb, irq);
+}
+
+static inline void
+dw_edma_core_ll_link(struct dw_edma_chan *chan, u32 idx, bool cb, u64 addr)
+{
+	chan->dw->core->ll_link(chan, idx, cb, addr);
+}
+
+static inline void dw_edma_core_ch_doorbell(struct dw_edma_chan *chan)
+{
+	chan->dw->core->ch_doorbell(chan);
+}
+
+static inline void dw_edma_core_ch_enable(struct dw_edma_chan *chan)
+{
+	chan->dw->core->ch_enable(chan);
+}
+
+static inline
+void dw_edma_core_debugfs_on(struct dw_edma *dw)
+{
+	dw->core->debugfs_on(dw);
+}
+
+static inline int dw_edma_core_ack_emulated_irq(struct dw_edma *dw)
+{
+	if (!dw->core->ack_emulated_irq)
+		return -EOPNOTSUPP;
+
+	dw->core->ack_emulated_irq(dw);
+	return 0;
+}
+
+static inline resource_size_t
+dw_edma_core_db_offset(struct dw_edma *dw)
+{
+	return dw->core->db_offset(dw);
+}
+
+static inline bool
+dw_edma_core_ch_ignore_irq(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	if (dw->chip->flags & DW_EDMA_CHIP_LOCAL)
+		return chan->irq_mode == DW_EDMA_CH_IRQ_REMOTE;
+	else
+		return chan->irq_mode == DW_EDMA_CH_IRQ_LOCAL;
+}
+
+#endif /* _DW_EDMA_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
new file mode 100644
index 000000000..9f237ba91
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -0,0 +1,668 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA PCIe driver
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/dma/edma.h>
+#include <linux/pci-epf.h>
+#include <linux/msi.h>
+#include <linux/bitfield.h>
+#include <linux/sizes.h>
+
+#include "dw-edma-core.h"
+
+/* Synopsys */
+#define DW_PCIE_SYNOPSYS_VSEC_DMA_ID		0x6
+#define DW_PCIE_SYNOPSYS_VSEC_DMA_BAR		GENMASK(10, 8)
+#define DW_PCIE_SYNOPSYS_VSEC_DMA_MAP		GENMASK(2, 0)
+#define DW_PCIE_SYNOPSYS_VSEC_DMA_WR_CH		GENMASK(9, 0)
+#define DW_PCIE_SYNOPSYS_VSEC_DMA_RD_CH		GENMASK(25, 16)
+
+/* AMD MDB (Xilinx) specific defines */
+#define PCI_DEVICE_ID_XILINX_B054		0xb054
+#define PCI_DEVICE_ID_XILINX_B00F		0xb00f
+
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_ID		0x6
+#define DW_PCIE_XILINX_MDB_VSEC_ID		0x20
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_BAR		GENMASK(10, 8)
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_MAP		GENMASK(2, 0)
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_WR_CH	GENMASK(9, 0)
+#define DW_PCIE_XILINX_MDB_VSEC_DMA_RD_CH	GENMASK(25, 16)
+
+#define DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_HIGH	0xc
+#define DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_LOW	0x8
+#define DW_PCIE_XILINX_MDB_INVALID_ADDR		(~0ULL)
+
+#define DW_PCIE_XILINX_MDB_LL_OFF_GAP		0x200000
+#define DW_PCIE_XILINX_MDB_LL_SIZE		0x800
+#define DW_PCIE_XILINX_MDB_DT_OFF_GAP		0x100000
+#define DW_PCIE_XILINX_MDB_DT_SIZE		0x800
+
+#define DW_BLOCK(a, b, c) \
+	{ \
+		.bar = a, \
+		.off = b, \
+		.sz = c, \
+	},
+
+struct dw_edma_block {
+	enum pci_barno			bar;
+	off_t				off;
+	u64				paddr;
+	bool				paddr_valid;
+	size_t				sz;
+};
+
+struct dw_edma_pcie_data {
+	/* eDMA registers location */
+	struct dw_edma_block		rg;
+	/* eDMA memory linked list location */
+	struct dw_edma_block		ll_wr[HDMA_MAX_WR_CH];
+	struct dw_edma_block		ll_rd[HDMA_MAX_RD_CH];
+	/* eDMA memory data location */
+	struct dw_edma_block		dt_wr[HDMA_MAX_WR_CH];
+	struct dw_edma_block		dt_rd[HDMA_MAX_RD_CH];
+	/* Other */
+	enum dw_edma_map_format		mf;
+	u8				irqs;
+	u16				wr_ch_cnt;
+	u16				rd_ch_cnt;
+	u64				devmem_phys_off;
+	bool				cfg_non_ll;
+};
+
+struct dw_edma_pcie_match_data {
+	const struct dw_edma_pcie_data *data;
+	const struct dw_edma_plat_ops *plat_ops;
+	/*
+	 * Mandatory callback. It may leave @pdata unchanged when the static
+	 * template already describes the device.
+	 */
+	int (*parse_caps)(struct pci_dev *pdev,
+			  struct dw_edma_pcie_data *pdata);
+	unsigned long flags;
+	u32 chip_flags;
+};
+
+#define DW_EDMA_PCIE_F_DEVMEM_PHYS_OFF	BIT(0)
+#define DW_EDMA_PCIE_F_REG_OFFSET	BIT(1)
+
+static const struct dw_edma_pcie_data snps_edda_data = {
+	/* eDMA registers location */
+	.rg.bar				= BAR_0,
+	.rg.off				= 0x00001000,	/*  4 Kbytes */
+	.rg.sz				= 0x00002000,	/*  8 Kbytes */
+	/* eDMA memory linked list location */
+	.ll_wr = {
+		/* Channel 0 - BAR 2, offset 0 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00000000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 2 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00200000, 0x00000800)
+	},
+	.ll_rd = {
+		/* Channel 0 - BAR 2, offset 4 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00400000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 6 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00600000, 0x00000800)
+	},
+	/* eDMA memory data location */
+	.dt_wr = {
+		/* Channel 0 - BAR 2, offset 8 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00800000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 9 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00900000, 0x00000800)
+	},
+	.dt_rd = {
+		/* Channel 0 - BAR 2, offset 10 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00a00000, 0x00000800)
+		/* Channel 1 - BAR 2, offset 11 Mbytes, size 2 Kbytes */
+		DW_BLOCK(BAR_2, 0x00b00000, 0x00000800)
+	},
+	/* Other */
+	.mf				= EDMA_MF_EDMA_UNROLL,
+	.irqs				= 1,
+	.wr_ch_cnt			= 2,
+	.rd_ch_cnt			= 2,
+};
+
+static const struct dw_edma_pcie_data xilinx_mdb_data = {
+	/* MDB registers location */
+	.rg.bar				= BAR_0,
+	.rg.off				= SZ_4K,	/*  4 Kbytes */
+	.rg.sz				= SZ_8K,	/*  8 Kbytes */
+
+	/* Other */
+	.mf				= EDMA_MF_HDMA_NATIVE,
+	.irqs				= 1,
+	.wr_ch_cnt			= 8,
+	.rd_ch_cnt			= 8,
+};
+
+static const struct dw_edma_pcie_data xilinx_cpm6_dma_data = {
+	/* MDB registers location */
+	.rg.bar				= BAR_0,
+	.rg.off				= SZ_4K,	/*  4 Kbytes */
+	.rg.sz				= SZ_8K,	/*  8 Kbytes */
+
+	/* Other */
+	.mf				= EDMA_MF_HDMA_NATIVE,
+	.irqs				= 1,
+	.wr_ch_cnt			= 8,
+	.rd_ch_cnt			= 8,
+};
+
+static void dw_edma_set_chan_region_offset(struct dw_edma_pcie_data *pdata,
+					   enum pci_barno bar, off_t start_off,
+					   off_t ll_off_gap, size_t ll_size,
+					   off_t dt_off_gap, size_t dt_size)
+{
+	u16 wr_ch = pdata->wr_ch_cnt;
+	u16 rd_ch = pdata->rd_ch_cnt;
+	off_t off;
+	u16 i;
+
+	off = start_off;
+
+	/* Write channel LL region */
+	for (i = 0; i < wr_ch; i++) {
+		pdata->ll_wr[i].bar = bar;
+		pdata->ll_wr[i].off = off;
+		pdata->ll_wr[i].sz = ll_size;
+		off += ll_off_gap;
+	}
+
+	/* Read channel LL region */
+	for (i = 0; i < rd_ch; i++) {
+		pdata->ll_rd[i].bar = bar;
+		pdata->ll_rd[i].off = off;
+		pdata->ll_rd[i].sz = ll_size;
+		off += ll_off_gap;
+	}
+
+	/* Write channel data region */
+	for (i = 0; i < wr_ch; i++) {
+		pdata->dt_wr[i].bar = bar;
+		pdata->dt_wr[i].off = off;
+		pdata->dt_wr[i].sz = dt_size;
+		off += dt_off_gap;
+	}
+
+	/* Read channel data region */
+	for (i = 0; i < rd_ch; i++) {
+		pdata->dt_rd[i].bar = bar;
+		pdata->dt_rd[i].off = off;
+		pdata->dt_rd[i].sz = dt_size;
+		off += dt_off_gap;
+	}
+}
+
+static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
+{
+	return pci_irq_vector(to_pci_dev(dev), nr);
+}
+
+static u64 dw_edma_pcie_address(struct device *dev, phys_addr_t cpu_addr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus_region region;
+	struct resource res = {
+		.flags = IORESOURCE_MEM,
+		.start = cpu_addr,
+		.end = cpu_addr,
+	};
+
+	pcibios_resource_to_bus(pdev->bus, &region, &res);
+	return region.start;
+}
+
+static const struct dw_edma_plat_ops dw_edma_pcie_plat_ops = {
+	.irq_vector = dw_edma_pcie_irq_vector,
+	.pci_address = dw_edma_pcie_address,
+};
+
+static void dw_edma_pcie_get_synopsys_dma_data(struct pci_dev *pdev,
+					       struct dw_edma_pcie_data *pdata)
+{
+	u32 val, map;
+	u16 vsec;
+	u64 off;
+
+	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_SYNOPSYS,
+					DW_PCIE_SYNOPSYS_VSEC_DMA_ID);
+	if (!vsec)
+		return;
+
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	if (PCI_VNDR_HEADER_REV(val) != 0x00 ||
+	    PCI_VNDR_HEADER_LEN(val) != 0x18)
+		return;
+
+	pci_dbg(pdev, "Detected Synopsys PCIe Vendor-Specific Extended Capability DMA\n");
+	pci_read_config_dword(pdev, vsec + 0x8, &val);
+	map = FIELD_GET(DW_PCIE_SYNOPSYS_VSEC_DMA_MAP, val);
+	if (map != EDMA_MF_EDMA_LEGACY &&
+	    map != EDMA_MF_EDMA_UNROLL &&
+	    map != EDMA_MF_HDMA_COMPAT &&
+	    map != EDMA_MF_HDMA_NATIVE)
+		return;
+
+	pdata->mf = map;
+	pdata->rg.bar = FIELD_GET(DW_PCIE_SYNOPSYS_VSEC_DMA_BAR, val);
+
+	pci_read_config_dword(pdev, vsec + 0xc, &val);
+	pdata->wr_ch_cnt = min_t(u16, pdata->wr_ch_cnt,
+				 FIELD_GET(DW_PCIE_SYNOPSYS_VSEC_DMA_WR_CH, val));
+	pdata->rd_ch_cnt = min_t(u16, pdata->rd_ch_cnt,
+				 FIELD_GET(DW_PCIE_SYNOPSYS_VSEC_DMA_RD_CH, val));
+
+	pci_read_config_dword(pdev, vsec + 0x14, &val);
+	off = val;
+	pci_read_config_dword(pdev, vsec + 0x10, &val);
+	off <<= 32;
+	off |= val;
+	pdata->rg.off = off;
+}
+
+static void dw_edma_pcie_get_xilinx_dma_data(struct pci_dev *pdev,
+					     struct dw_edma_pcie_data *pdata)
+{
+	u32 val, map;
+	u16 vsec;
+	u64 off;
+
+	pdata->devmem_phys_off = DW_PCIE_XILINX_MDB_INVALID_ADDR;
+
+	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_XILINX,
+					DW_PCIE_XILINX_MDB_VSEC_DMA_ID);
+	if (!vsec)
+		return;
+
+	pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+	if (PCI_VNDR_HEADER_REV(val) != 0x00 ||
+	    PCI_VNDR_HEADER_LEN(val) != 0x18)
+		return;
+
+	pci_dbg(pdev, "Detected Xilinx PCIe Vendor-Specific Extended Capability DMA\n");
+	pci_read_config_dword(pdev, vsec + 0x8, &val);
+	map = FIELD_GET(DW_PCIE_XILINX_MDB_VSEC_DMA_MAP, val);
+	if (map != EDMA_MF_HDMA_NATIVE)
+		return;
+
+	pdata->mf = map;
+	pdata->rg.bar = FIELD_GET(DW_PCIE_XILINX_MDB_VSEC_DMA_BAR, val);
+
+	pci_read_config_dword(pdev, vsec + 0xc, &val);
+	pdata->wr_ch_cnt = min(pdata->wr_ch_cnt,
+			       FIELD_GET(DW_PCIE_XILINX_MDB_VSEC_DMA_WR_CH, val));
+	pdata->rd_ch_cnt = min(pdata->rd_ch_cnt,
+			       FIELD_GET(DW_PCIE_XILINX_MDB_VSEC_DMA_RD_CH, val));
+
+	pci_read_config_dword(pdev, vsec + 0x14, &val);
+	off = val;
+	pci_read_config_dword(pdev, vsec + 0x10, &val);
+	off <<= 32;
+	off |= val;
+	pdata->rg.off = off;
+
+	vsec = pci_find_vsec_capability(pdev, PCI_VENDOR_ID_XILINX,
+					DW_PCIE_XILINX_MDB_VSEC_ID);
+	if (!vsec)
+		return;
+
+	pci_read_config_dword(pdev,
+			      vsec + DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_HIGH,
+			      &val);
+	off = val;
+	pci_read_config_dword(pdev,
+			      vsec + DW_PCIE_XILINX_MDB_DEVMEM_OFF_REG_LOW,
+			      &val);
+	off <<= 32;
+	off |= val;
+	pdata->devmem_phys_off = off;
+}
+
+static int
+dw_edma_pcie_parse_synopsys_caps(struct pci_dev *pdev,
+				 struct dw_edma_pcie_data *pdata)
+{
+	dw_edma_pcie_get_synopsys_dma_data(pdev, pdata);
+
+	return 0;
+}
+
+static int
+dw_edma_pcie_parse_xilinx_caps(struct pci_dev *pdev,
+			       struct dw_edma_pcie_data *pdata)
+{
+	dw_edma_pcie_get_xilinx_dma_data(pdev, pdata);
+
+	/*
+	 * There is no valid address found for the LL memory space on the
+	 * device side. In the absence of LL base address use the non-LL mode or
+	 * simple mode supported by the HDMA IP.
+	 */
+	if (pdata->devmem_phys_off == DW_PCIE_XILINX_MDB_INVALID_ADDR) {
+		pdata->cfg_non_ll = true;
+		return 0;
+	}
+
+	/*
+	 * Configure the channel LL and data blocks if number of channels
+	 * enabled in VSEC capability are more than the channels configured in
+	 * xilinx_mdb_data.
+	 */
+	dw_edma_set_chan_region_offset(pdata, BAR_2, 0,
+				       DW_PCIE_XILINX_MDB_LL_OFF_GAP,
+				       DW_PCIE_XILINX_MDB_LL_SIZE,
+				       DW_PCIE_XILINX_MDB_DT_OFF_GAP,
+				       DW_PCIE_XILINX_MDB_DT_SIZE);
+
+	return 0;
+}
+
+static u64 dw_edma_get_phys_addr(struct pci_dev *pdev,
+				 const struct dw_edma_pcie_match_data *match,
+				 struct dw_edma_pcie_data *pdata,
+				 enum pci_barno bar)
+{
+	if (match->flags & DW_EDMA_PCIE_F_DEVMEM_PHYS_OFF)
+		return pdata->devmem_phys_off;
+
+	return pci_bus_address(pdev, bar);
+}
+
+static u64 dw_edma_get_block_addr(struct pci_dev *pdev,
+				  const struct dw_edma_pcie_match_data *match,
+				  struct dw_edma_pcie_data *pdata,
+				  const struct dw_edma_block *block)
+{
+	if (block->paddr_valid)
+		return block->paddr;
+
+	return dw_edma_get_phys_addr(pdev, match, pdata, block->bar) +
+	       block->off;
+}
+
+static int dw_edma_pcie_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *pid)
+{
+	const struct dw_edma_pcie_match_data *match = (void *)pid->driver_data;
+	const struct dw_edma_pcie_data *pdata;
+	struct device *dev = &pdev->dev;
+	struct dw_edma_chip *chip;
+	int err, nr_irqs;
+	int i, mask;
+
+	if (!match)
+		return -ENODEV;
+	pdata = match->data;
+
+	if (!pdata)
+		return -ENODEV;
+
+	struct dw_edma_pcie_data *dma_data __free(kfree) =
+		kmemdup(pdata, sizeof(*dma_data), GFP_KERNEL);
+	if (!dma_data)
+		return -ENOMEM;
+
+	/* Enable PCI device */
+	err = pcim_enable_device(pdev);
+	if (err) {
+		pci_err(pdev, "enabling device failed\n");
+		return err;
+	}
+
+	/* Let device-specific discovery override the static template data. */
+	if (!match->parse_caps || !match->plat_ops)
+		return -EINVAL;
+
+	err = match->parse_caps(pdev, dma_data);
+	if (err)
+		return err;
+
+	/* Mapping PCI BAR regions */
+	mask = BIT(dma_data->rg.bar);
+	for (i = 0; i < dma_data->wr_ch_cnt; i++) {
+		mask |= BIT(dma_data->ll_wr[i].bar);
+		if (dma_data->dt_wr[i].sz)
+			mask |= BIT(dma_data->dt_wr[i].bar);
+	}
+	for (i = 0; i < dma_data->rd_ch_cnt; i++) {
+		mask |= BIT(dma_data->ll_rd[i].bar);
+		if (dma_data->dt_rd[i].sz)
+			mask |= BIT(dma_data->dt_rd[i].bar);
+	}
+	err = pcim_iomap_regions(pdev, mask, pci_name(pdev));
+	if (err) {
+		pci_err(pdev, "eDMA BAR I/O remapping failed\n");
+		return err;
+	}
+
+	pci_set_master(pdev);
+
+	/* DMA configuration */
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		pci_err(pdev, "DMA mask 64 set failed\n");
+		return err;
+	}
+
+	/* Data structure allocation */
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	/* IRQs allocation */
+	nr_irqs = pci_alloc_irq_vectors(pdev, 1, dma_data->irqs,
+					PCI_IRQ_MSI | PCI_IRQ_MSIX);
+	if (nr_irqs < 1) {
+		pci_err(pdev, "fail to alloc IRQ vector (number of IRQs=%u)\n",
+			nr_irqs);
+		return -EPERM;
+	}
+
+	/* Data structure initialization */
+	chip->dev = dev;
+
+	chip->mf = dma_data->mf;
+	chip->flags = match->chip_flags;
+	chip->func_no = PCI_FUNC(pdev->devfn);
+	chip->nr_irqs = nr_irqs;
+	chip->ops = match->plat_ops;
+	chip->cfg_non_ll = dma_data->cfg_non_ll;
+
+	chip->ll_wr_cnt = dma_data->wr_ch_cnt;
+	chip->ll_rd_cnt = dma_data->rd_ch_cnt;
+
+	chip->reg_base = pcim_iomap_table(pdev)[dma_data->rg.bar];
+	if (!chip->reg_base)
+		return -ENOMEM;
+	if (match->flags & DW_EDMA_PCIE_F_REG_OFFSET)
+		chip->reg_base += dma_data->rg.off;
+
+	for (i = 0; i < chip->ll_wr_cnt && !dma_data->cfg_non_ll; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_wr[i];
+		struct dw_edma_region *dt_region = &chip->dt_region_wr[i];
+		struct dw_edma_block *ll_block = &dma_data->ll_wr[i];
+		struct dw_edma_block *dt_block = &dma_data->dt_wr[i];
+
+		ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr.io)
+			return -ENOMEM;
+
+		ll_region->vaddr.io += ll_block->off;
+		ll_region->paddr = dw_edma_get_block_addr(pdev, match, dma_data,
+							  ll_block);
+		ll_region->sz = ll_block->sz;
+
+		if (!dt_block->sz)
+			continue;
+
+		dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr.io)
+			return -ENOMEM;
+
+		dt_region->vaddr.io += dt_block->off;
+		dt_region->paddr = dw_edma_get_block_addr(pdev, match, dma_data,
+							  dt_block);
+		dt_region->sz = dt_block->sz;
+	}
+
+	for (i = 0; i < chip->ll_rd_cnt && !dma_data->cfg_non_ll; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_rd[i];
+		struct dw_edma_region *dt_region = &chip->dt_region_rd[i];
+		struct dw_edma_block *ll_block = &dma_data->ll_rd[i];
+		struct dw_edma_block *dt_block = &dma_data->dt_rd[i];
+
+		ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar];
+		if (!ll_region->vaddr.io)
+			return -ENOMEM;
+
+		ll_region->vaddr.io += ll_block->off;
+		ll_region->paddr = dw_edma_get_block_addr(pdev, match, dma_data,
+							  ll_block);
+		ll_region->sz = ll_block->sz;
+
+		if (!dt_block->sz)
+			continue;
+
+		dt_region->vaddr.io = pcim_iomap_table(pdev)[dt_block->bar];
+		if (!dt_region->vaddr.io)
+			return -ENOMEM;
+
+		dt_region->vaddr.io += dt_block->off;
+		dt_region->paddr = dw_edma_get_block_addr(pdev, match, dma_data,
+							  dt_block);
+		dt_region->sz = dt_block->sz;
+	}
+
+	/* Debug info */
+	if (chip->mf == EDMA_MF_EDMA_LEGACY)
+		pci_dbg(pdev, "Version:\teDMA Port Logic (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_EDMA_UNROLL)
+		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_COMPAT)
+		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_NATIVE)
+		pci_dbg(pdev, "Version:\tHDMA Native (0x%x)\n", chip->mf);
+	else
+		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf);
+
+	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p)\n",
+		dma_data->rg.bar, dma_data->rg.off, dma_data->rg.sz,
+		chip->reg_base);
+
+
+	for (i = 0; i < chip->ll_wr_cnt; i++) {
+		pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, dma_data->ll_wr[i].bar,
+			dma_data->ll_wr[i].off, chip->ll_region_wr[i].sz,
+			chip->ll_region_wr[i].vaddr.io, &chip->ll_region_wr[i].paddr);
+
+		if (!dma_data->dt_wr[i].sz)
+			continue;
+
+		pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, dma_data->dt_wr[i].bar,
+			dma_data->dt_wr[i].off, chip->dt_region_wr[i].sz,
+			chip->dt_region_wr[i].vaddr.io,
+			&chip->dt_region_wr[i].paddr);
+	}
+
+	for (i = 0; i < chip->ll_rd_cnt; i++) {
+		pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, dma_data->ll_rd[i].bar,
+			dma_data->ll_rd[i].off, chip->ll_region_rd[i].sz,
+			chip->ll_region_rd[i].vaddr.io, &chip->ll_region_rd[i].paddr);
+
+		if (!dma_data->dt_rd[i].sz)
+			continue;
+
+		pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+			i, dma_data->dt_rd[i].bar,
+			dma_data->dt_rd[i].off, chip->dt_region_rd[i].sz,
+			chip->dt_region_rd[i].vaddr.io,
+			&chip->dt_region_rd[i].paddr);
+	}
+
+	pci_dbg(pdev, "Nr. IRQs:\t%u\n", chip->nr_irqs);
+
+	/* Validating if PCI interrupts were enabled */
+	if (!pci_dev_msi_enabled(pdev)) {
+		pci_err(pdev, "enable interrupt failed\n");
+		return -EPERM;
+	}
+
+	/* Starting eDMA driver */
+	err = dw_edma_probe(chip);
+	if (err) {
+		pci_err(pdev, "eDMA probe failed\n");
+		return err;
+	}
+
+	/* Saving data structure reference */
+	pci_set_drvdata(pdev, chip);
+
+	return 0;
+}
+
+static void dw_edma_pcie_remove(struct pci_dev *pdev)
+{
+	struct dw_edma_chip *chip = pci_get_drvdata(pdev);
+	int err;
+
+	/* Stopping eDMA driver */
+	err = dw_edma_remove(chip);
+	if (err)
+		pci_warn(pdev, "can't remove device properly: %d\n", err);
+}
+
+static const struct dw_edma_pcie_match_data snps_edda_match_data = {
+	.data = &snps_edda_data,
+	.plat_ops = &dw_edma_pcie_plat_ops,
+	.parse_caps = dw_edma_pcie_parse_synopsys_caps,
+};
+
+static const struct dw_edma_pcie_match_data xilinx_mdb_match_data = {
+	.data = &xilinx_mdb_data,
+	.plat_ops = &dw_edma_pcie_plat_ops,
+	.parse_caps = dw_edma_pcie_parse_xilinx_caps,
+	.flags = DW_EDMA_PCIE_F_DEVMEM_PHYS_OFF,
+};
+
+static const struct dw_edma_pcie_match_data xilinx_cpm6_dma_match_data = {
+	.data = &xilinx_cpm6_dma_data,
+	.plat_ops = &dw_edma_pcie_plat_ops,
+	.parse_caps = dw_edma_pcie_parse_xilinx_caps,
+	.flags = DW_EDMA_PCIE_F_DEVMEM_PHYS_OFF,
+};
+
+static const struct pci_device_id dw_edma_pcie_id_table[] = {
+	{ PCI_DEVICE_DATA(SYNOPSYS, EDDA, &snps_edda_match_data) },
+	{ PCI_VDEVICE(XILINX, PCI_DEVICE_ID_XILINX_B054),
+	  .driver_data = (kernel_ulong_t)&xilinx_mdb_match_data },
+	{ PCI_VDEVICE(XILINX, PCI_DEVICE_ID_XILINX_B00F),
+	  .driver_data = (kernel_ulong_t)&xilinx_cpm6_dma_match_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, dw_edma_pcie_id_table);
+
+static struct pci_driver dw_edma_pcie_driver = {
+	.name		= "dw-edma-pcie",
+	.id_table	= dw_edma_pcie_id_table,
+	.probe		= dw_edma_pcie_probe,
+	.remove		= dw_edma_pcie_remove,
+};
+
+module_pci_driver(dw_edma_pcie_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare eDMA PCIe driver");
+MODULE_AUTHOR("Gustavo Pimentel <gustavo.pimentel@synopsys.com>");
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
new file mode 100644
index 000000000..abc1bd4c0
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -0,0 +1,664 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA v0 core
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/iopoll.h>
+#include <linux/irqreturn.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include "dw-edma-core.h"
+#include "dw-edma-v0-core.h"
+#include "dw-edma-v0-regs.h"
+#include "dw-edma-v0-debugfs.h"
+
+enum dw_edma_control {
+	DW_EDMA_V0_CB					= BIT(0),
+	DW_EDMA_V0_TCB					= BIT(1),
+	DW_EDMA_V0_LLP					= BIT(2),
+	DW_EDMA_V0_LIE					= BIT(3),
+	DW_EDMA_V0_RIE					= BIT(4),
+	DW_EDMA_V0_CCS					= BIT(8),
+	DW_EDMA_V0_LLE					= BIT(9),
+};
+
+#define EDMA_V0_FUNC_NUM_MASK				GENMASK(16, 12)
+
+static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
+{
+	return dw->chip->reg_base;
+}
+
+#define SET_32(dw, name, value)				\
+	writel(value, &(__dw_regs(dw)->name))
+
+#define GET_32(dw, name)				\
+	readl(&(__dw_regs(dw)->name))
+
+#define SET_RW_32(dw, dir, name, value)			\
+	do {						\
+		if ((dir) == EDMA_DIR_WRITE)		\
+			SET_32(dw, wr_##name, value);	\
+		else					\
+			SET_32(dw, rd_##name, value);	\
+	} while (0)
+
+#define GET_RW_32(dw, dir, name)			\
+	((dir) == EDMA_DIR_WRITE			\
+	  ? GET_32(dw, wr_##name)			\
+	  : GET_32(dw, rd_##name))
+
+#define SET_BOTH_32(dw, name, value)			\
+	do {						\
+		SET_32(dw, wr_##name, value);		\
+		SET_32(dw, rd_##name, value);		\
+	} while (0)
+
+#define SET_64(dw, name, value)				\
+	writeq(value, &(__dw_regs(dw)->name))
+
+#define GET_64(dw, name)				\
+	readq(&(__dw_regs(dw)->name))
+
+#define SET_RW_64(dw, dir, name, value)			\
+	do {						\
+		if ((dir) == EDMA_DIR_WRITE)		\
+			SET_64(dw, wr_##name, value);	\
+		else					\
+			SET_64(dw, rd_##name, value);	\
+	} while (0)
+
+#define GET_RW_64(dw, dir, name)			\
+	((dir) == EDMA_DIR_WRITE			\
+	  ? GET_64(dw, wr_##name)			\
+	  : GET_64(dw, rd_##name))
+
+#define SET_BOTH_64(dw, name, value)			\
+	do {						\
+		SET_64(dw, wr_##name, value);		\
+		SET_64(dw, rd_##name, value);		\
+	} while (0)
+
+#define SET_COMPAT(dw, name, value)			\
+	writel(value, &(__dw_regs(dw)->type.unroll.name))
+
+#define SET_RW_COMPAT(dw, dir, name, value)		\
+	do {						\
+		if ((dir) == EDMA_DIR_WRITE)		\
+			SET_COMPAT(dw, wr_##name, value); \
+		else					\
+			SET_COMPAT(dw, rd_##name, value); \
+	} while (0)
+
+static inline struct dw_edma_v0_ch_regs __iomem *
+__dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
+{
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY)
+		return &(__dw_regs(dw)->type.legacy.ch);
+
+	if (dir == EDMA_DIR_WRITE)
+		return &__dw_regs(dw)->type.unroll.ch[ch].wr;
+
+	return &__dw_regs(dw)->type.unroll.ch[ch].rd;
+}
+
+static inline void writel_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
+			     u32 value, void __iomem *addr)
+{
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
+		u32 viewport_sel;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&dw->lock, flags);
+
+		viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch);
+		if (dir == EDMA_DIR_READ)
+			viewport_sel |= BIT(31);
+
+		writel(viewport_sel,
+		       &(__dw_regs(dw)->type.legacy.viewport_sel));
+		writel(value, addr);
+
+		raw_spin_unlock_irqrestore(&dw->lock, flags);
+	} else {
+		writel(value, addr);
+	}
+}
+
+static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
+			   const void __iomem *addr)
+{
+	u32 value;
+
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
+		u32 viewport_sel;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&dw->lock, flags);
+
+		viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch);
+		if (dir == EDMA_DIR_READ)
+			viewport_sel |= BIT(31);
+
+		writel(viewport_sel,
+		       &(__dw_regs(dw)->type.legacy.viewport_sel));
+		value = readl(addr);
+
+		raw_spin_unlock_irqrestore(&dw->lock, flags);
+	} else {
+		value = readl(addr);
+	}
+
+	return value;
+}
+
+#define SET_CH_32(dw, dir, ch, name, value) \
+	writel_ch(dw, dir, ch, value, &(__dw_ch_regs(dw, dir, ch)->name))
+
+#define GET_CH_32(dw, dir, ch, name) \
+	readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
+
+static u32 dw_edma_v0_func_num(struct dw_edma_chan *chan)
+{
+	return FIELD_PREP(EDMA_V0_FUNC_NUM_MASK, chan->func_no);
+}
+
+/* eDMA management callbacks */
+static void dw_edma_v0_core_ch_power(struct dw_edma *dw,
+				     enum dw_edma_dir dir, u16 id, bool enable)
+{
+	u32 value = enable ? BIT(0) : 0;
+
+	if (WARN_ON_ONCE(id >= EDMA_V0_MAX_NR_CH))
+		return;
+
+	switch (id) {
+	case 0:
+		SET_RW_COMPAT(dw, dir, ch0_pwr_en, value);
+		break;
+	case 1:
+		SET_RW_COMPAT(dw, dir, ch1_pwr_en, value);
+		break;
+	case 2:
+		SET_RW_COMPAT(dw, dir, ch2_pwr_en, value);
+		break;
+	case 3:
+		SET_RW_COMPAT(dw, dir, ch3_pwr_en, value);
+		break;
+	case 4:
+		SET_RW_COMPAT(dw, dir, ch4_pwr_en, value);
+		break;
+	case 5:
+		SET_RW_COMPAT(dw, dir, ch5_pwr_en, value);
+		break;
+	case 6:
+		SET_RW_COMPAT(dw, dir, ch6_pwr_en, value);
+		break;
+	case 7:
+		SET_RW_COMPAT(dw, dir, ch7_pwr_en, value);
+		break;
+	}
+}
+
+static int dw_edma_v0_core_engine_disable(struct dw_edma *dw,
+					  enum dw_edma_dir dir)
+{
+	u32 value;
+	int ret;
+
+	SET_RW_32(dw, dir, engine_en, 0);
+	ret = read_poll_timeout(GET_RW_32, value, !(value & BIT(0)), 100,
+				200000, false, dw, dir, engine_en);
+	if (ret)
+		dev_warn(dw->chip->dev, "%s engine did not stop within 200ms\n",
+			 dir == EDMA_DIR_WRITE ? "write" : "read");
+
+	return ret;
+}
+
+static int dw_edma_v0_core_dir_off(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	u16 count, id;
+	int ret = 0;
+
+	scoped_guard(raw_spinlock_irqsave, &dw->lock)
+		SET_RW_32(dw, dir, int_mask,
+			  EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
+		/*
+		 * DWC PCIe Controller Databook 6.10a-lca06, "Legacy DMA
+		 * and HDMA Software Compatibility": HDMA compatibility mode
+		 * does not implement ENGINE_EN, but retains CHi_PWR_EN for
+		 * per-channel enable and disable.
+		 */
+		count = dir == EDMA_DIR_WRITE ? dw->wr_ch_cnt : dw->rd_ch_cnt;
+		for (id = 0; id < count; id++)
+			dw_edma_v0_core_ch_power(dw, dir, id, false);
+	} else {
+		ret = dw_edma_v0_core_engine_disable(dw, dir);
+	}
+
+	SET_RW_32(dw, dir, int_clear,
+		  EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+
+	return ret;
+}
+
+static void dw_edma_v0_core_off(struct dw_edma *dw)
+{
+	SET_BOTH_32(dw, int_mask,
+		    EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+	SET_BOTH_32(dw, int_clear,
+		    EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
+	SET_BOTH_32(dw, engine_en, 0);
+}
+
+static int dw_edma_v0_core_quiesce(struct dw_edma *dw)
+{
+	int ret = 0;
+	int err;
+
+	if (dw->wr_ch_cnt)
+		ret = dw_edma_v0_core_dir_off(dw, EDMA_DIR_WRITE);
+	if (dw->rd_ch_cnt) {
+		err = dw_edma_v0_core_dir_off(dw, EDMA_DIR_READ);
+		if (!ret)
+			ret = err;
+	}
+
+	return ret;
+}
+
+/*
+ * The unrolled eDMA and HDMA compatibility register maps share interrupt
+ * control per direction, so the whole direction is quiesced. Callers must
+ * own the direction entirely and prevent the peer from programming it after
+ * this point. Partial ownership mode validates direction granularity.
+ */
+static int dw_edma_v0_core_ch_quiesce(struct dw_edma_chan *chan)
+{
+	return dw_edma_v0_core_dir_off(chan->dw, chan->dir);
+}
+
+static u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	u32 num_ch;
+
+	if (dir == EDMA_DIR_WRITE)
+		num_ch = FIELD_GET(EDMA_V0_WRITE_CH_COUNT_MASK,
+				   GET_32(dw, ctrl));
+	else
+		num_ch = FIELD_GET(EDMA_V0_READ_CH_COUNT_MASK,
+				   GET_32(dw, ctrl));
+
+	if (num_ch > EDMA_V0_MAX_NR_CH)
+		num_ch = EDMA_V0_MAX_NR_CH;
+
+	return (u16)num_ch;
+}
+
+static enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 tmp;
+
+	tmp = FIELD_GET(EDMA_V0_CH_STATUS_MASK,
+			GET_CH_32(dw, chan->dir, chan->id, ch_control1));
+
+	if (tmp == 1)
+		return DMA_IN_PROGRESS;
+	else if (tmp == 3)
+		return DMA_COMPLETE;
+	else
+		return DMA_ERROR;
+}
+
+static void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_RW_32(dw, chan->dir, int_clear,
+		  FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id)));
+}
+
+static void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_RW_32(dw, chan->dir, int_clear,
+		  FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id)));
+}
+
+static irqreturn_t
+dw_edma_v0_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			   dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	struct dw_edma *dw = dw_irq->dw;
+	unsigned long total, pos, val;
+	irqreturn_t ret = IRQ_NONE;
+	struct dw_edma_chan *chan;
+	unsigned long off;
+	unsigned long *mask;
+	u32 sts;
+
+	if (dir == EDMA_DIR_WRITE) {
+		total = dw->wr_ch_cnt;
+		off = 0;
+		mask = dw_irq->wr_mask;
+	} else {
+		total = dw->rd_ch_cnt;
+		off = dw->wr_ch_cnt;
+		mask = dw_irq->rd_mask;
+	}
+
+	/*
+	 * DONE and ABORT status share one register, and on remote setups
+	 * every read is a non-posted round trip across the PCIe link. Take
+	 * one snapshot and derive both views from it. An abort raised
+	 * after the snapshot is deferred, not lost: only bits observed in
+	 * the snapshot are ever cleared below, so its status remains set and
+	 * triggers another handler pass.
+	 */
+	sts = GET_RW_32(dw, dir, int_status);
+
+	val = FIELD_GET(EDMA_V0_DONE_INT_MASK, sts);
+	val &= *mask;
+	for_each_set_bit(pos, &val, total) {
+		chan = &dw->chan[pos + off];
+
+		if (unlikely(dw_edma_core_ch_ignore_irq(chan)))
+			continue;
+
+		dw_edma_v0_core_clear_done_int(chan);
+		done(chan);
+
+		ret = IRQ_HANDLED;
+	}
+
+	val = FIELD_GET(EDMA_V0_ABORT_INT_MASK, sts);
+	val &= *mask;
+	for_each_set_bit(pos, &val, total) {
+		chan = &dw->chan[pos + off];
+
+		if (unlikely(dw_edma_core_ch_ignore_irq(chan)))
+			continue;
+
+		dw_edma_v0_core_clear_abort_int(chan);
+		abort(chan);
+
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void dw_edma_v0_write_ll_data(struct dw_edma_chan *chan, int i,
+				     u32 control, u32 size, u64 sar, u64 dar)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_edma_v0_lli *lli = chan->ll_region.vaddr.mem + ofs;
+
+		lli->transfer_size = size;
+		lli->sar.reg = sar;
+		lli->dar.reg = dar;
+		dma_wmb();
+		lli->control = control;
+	} else {
+		struct dw_edma_v0_lli __iomem *lli = chan->ll_region.vaddr.io + ofs;
+
+		writel(size, &lli->transfer_size);
+		writeq(sar, &lli->sar.reg);
+		writeq(dar, &lli->dar.reg);
+		writel(control, &lli->control);
+	}
+}
+
+static void dw_edma_v0_write_ll_link(struct dw_edma_chan *chan,
+				     int i, u32 control, u64 pointer)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_edma_v0_lli);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_edma_v0_llp *llp = chan->ll_region.vaddr.mem + ofs;
+
+		llp->llp.reg = pointer;
+		dma_wmb();
+		llp->control = control;
+	} else {
+		struct dw_edma_v0_llp __iomem *llp = chan->ll_region.vaddr.io + ofs;
+
+		writeq(pointer, &llp->llp.reg);
+		writel(control, &llp->control);
+	}
+}
+
+static void dw_edma_v0_core_ch_enable(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	unsigned long flags;
+	u32 tmp;
+
+	 /* Enable engine */
+	SET_RW_32(dw, chan->dir, engine_en, BIT(0));
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT)
+		dw_edma_v0_core_ch_power(dw, chan->dir, chan->id, true);
+	/* Interrupt mask/unmask - done, abort */
+	raw_spin_lock_irqsave(&dw->lock, flags);
+
+	tmp = GET_RW_32(dw, chan->dir, int_mask);
+	if (chan->irq_mode == DW_EDMA_CH_IRQ_REMOTE) {
+		tmp |= FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id));
+		tmp |= FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id));
+	} else {
+		tmp &= ~FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id));
+		tmp &= ~FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id));
+	}
+	SET_RW_32(dw, chan->dir, int_mask, tmp);
+	/* Linked list error */
+	tmp = GET_RW_32(dw, chan->dir, linked_list_err_en);
+	tmp |= FIELD_PREP(EDMA_V0_LINKED_LIST_ERR_MASK, BIT(chan->id));
+	SET_RW_32(dw, chan->dir, linked_list_err_en, tmp);
+
+	raw_spin_unlock_irqrestore(&dw->lock, flags);
+
+	/* Channel control */
+	SET_CH_32(dw, chan->dir, chan->id, ch_control1,
+		  DW_EDMA_V0_CCS | DW_EDMA_V0_LLE |
+		  dw_edma_v0_func_num(chan));
+	/* Linked list */
+	/* llp is not aligned on 64bit -> keep 32bit accesses */
+	SET_CH_32(dw, chan->dir, chan->id, llp.lsb,
+		  lower_32_bits(chan->ll_region.paddr));
+	SET_CH_32(dw, chan->dir, chan->id, llp.msb,
+		  upper_32_bits(chan->ll_region.paddr));
+}
+
+static void dw_edma_v0_sync_ll_data(struct dw_edma_chan *chan)
+{
+	/*
+	 * In case of remote eDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chan->ll_region.vaddr.io);
+}
+
+static void dw_edma_v0_core_ch_config(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 tmp = 0;
+
+	/* MSI done addr - low, high */
+	SET_RW_32(dw, chan->dir, done_imwr.lsb, chan->msi.address_lo);
+	SET_RW_32(dw, chan->dir, done_imwr.msb, chan->msi.address_hi);
+	/* MSI abort addr - low, high */
+	SET_RW_32(dw, chan->dir, abort_imwr.lsb, chan->msi.address_lo);
+	SET_RW_32(dw, chan->dir, abort_imwr.msb, chan->msi.address_hi);
+	/* MSI data - low, high */
+	switch (chan->id) {
+	case 0:
+	case 1:
+		tmp = GET_RW_32(dw, chan->dir, ch01_imwr_data);
+		break;
+
+	case 2:
+	case 3:
+		tmp = GET_RW_32(dw, chan->dir, ch23_imwr_data);
+		break;
+
+	case 4:
+	case 5:
+		tmp = GET_RW_32(dw, chan->dir, ch45_imwr_data);
+		break;
+
+	case 6:
+	case 7:
+		tmp = GET_RW_32(dw, chan->dir, ch67_imwr_data);
+		break;
+	}
+
+	if (chan->id & BIT(0)) {
+		/* Channel odd {1, 3, 5, 7} */
+		tmp &= EDMA_V0_CH_EVEN_MSI_DATA_MASK;
+		tmp |= FIELD_PREP(EDMA_V0_CH_ODD_MSI_DATA_MASK,
+				  chan->msi.data);
+	} else {
+		/* Channel even {0, 2, 4, 6} */
+		tmp &= EDMA_V0_CH_ODD_MSI_DATA_MASK;
+		tmp |= FIELD_PREP(EDMA_V0_CH_EVEN_MSI_DATA_MASK,
+				  chan->msi.data);
+	}
+
+	switch (chan->id) {
+	case 0:
+	case 1:
+		SET_RW_32(dw, chan->dir, ch01_imwr_data, tmp);
+		break;
+
+	case 2:
+	case 3:
+		SET_RW_32(dw, chan->dir, ch23_imwr_data, tmp);
+		break;
+
+	case 4:
+	case 5:
+		SET_RW_32(dw, chan->dir, ch45_imwr_data, tmp);
+		break;
+
+	case 6:
+	case 7:
+		SET_RW_32(dw, chan->dir, ch67_imwr_data, tmp);
+		break;
+	}
+}
+
+static void
+dw_edma_v0_core_ll_data(struct dw_edma_chan *chan, struct dw_edma_burst *burst,
+			u32 idx, bool cb, bool irq)
+{
+	u32 control = 0;
+
+	if (cb)
+		control |= DW_EDMA_V0_CB;
+
+	if (irq) {
+		control |= DW_EDMA_V0_LIE;
+
+		/*
+		 * A local instance never issues transfers on a remote-routed
+		 * channel: on CHIP_LOCAL instances, REMOTE routing denotes a
+		 * channel handed over to the remote side, which programs the
+		 * linked list through its own instance. The remote-only
+		 * recipe (LIE|RIE with the local interrupt masked) is thus
+		 * applied by the instance that owns the transfer, and the
+		 * LIE-only write below never executes for a remote-routed
+		 * channel.
+		 */
+		if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) &&
+		    chan->irq_mode == DW_EDMA_CH_IRQ_REMOTE)
+			control |= DW_EDMA_V0_RIE;
+	}
+
+	dw_edma_v0_write_ll_data(chan, idx, control, burst->sz, burst->sar,
+				 burst->dar);
+}
+
+static void
+dw_edma_v0_core_ll_link(struct dw_edma_chan *chan, u32 idx, bool cb, u64 addr)
+{
+	u32 control = DW_EDMA_V0_LLP | DW_EDMA_V0_TCB;
+
+	if (!cb)
+		control |= DW_EDMA_V0_CB;
+
+	dw_edma_v0_write_ll_link(chan, idx, control, addr);
+}
+
+static void dw_edma_v0_core_ch_doorbell(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	dw_edma_v0_sync_ll_data(chan);
+
+	/* Doorbell */
+	SET_RW_32(dw, chan->dir, doorbell,
+		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
+}
+
+/* eDMA debugfs callbacks */
+static void dw_edma_v0_core_debugfs_on(struct dw_edma *dw)
+{
+	dw_edma_v0_debugfs_on(dw);
+}
+
+static void dw_edma_v0_core_ack_emulated_irq(struct dw_edma *dw)
+{
+	/*
+	 * Interrupt emulation may assert the IRQ without setting
+	 * DONE/ABORT status bits. A zero write to INT_CLEAR deasserts the
+	 * emulated IRQ, while being a no-op for real interrupts.
+	 */
+	SET_BOTH_32(dw, int_clear, 0);
+}
+
+static resource_size_t dw_edma_v0_core_db_offset(struct dw_edma *dw)
+{
+	/*
+	 * rd_int_status is chosen arbitrarily, but wr_int_status would be
+	 * equally suitable.
+	 */
+	return offsetof(struct dw_edma_v0_regs, rd_int_status);
+}
+
+static const struct dw_edma_core_ops dw_edma_v0_core = {
+	.off = dw_edma_v0_core_off,
+	.quiesce = dw_edma_v0_core_quiesce,
+	.ch_quiesce = dw_edma_v0_core_ch_quiesce,
+	.ch_count = dw_edma_v0_core_ch_count,
+	.ch_status = dw_edma_v0_core_ch_status,
+	.handle_int = dw_edma_v0_core_handle_int,
+	.ll_data = dw_edma_v0_core_ll_data,
+	.ll_link = dw_edma_v0_core_ll_link,
+	.ch_doorbell = dw_edma_v0_core_ch_doorbell,
+	.ch_enable = dw_edma_v0_core_ch_enable,
+	.ch_config = dw_edma_v0_core_ch_config,
+	.debugfs_on = dw_edma_v0_core_debugfs_on,
+	.ack_emulated_irq = dw_edma_v0_core_ack_emulated_irq,
+	.db_offset = dw_edma_v0_core_db_offset,
+};
+
+void dw_edma_v0_core_register(struct dw_edma *dw)
+{
+	dw->core = &dw_edma_v0_core;
+}
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.h b/drivers/dma/dw-edma/dw-edma-v0-core.h
new file mode 100644
index 000000000..04a882222
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA v0 core
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#ifndef _DW_EDMA_V0_CORE_H
+#define _DW_EDMA_V0_CORE_H
+
+#include <linux/dma/edma.h>
+
+/* eDMA core register */
+void dw_edma_v0_core_register(struct dw_edma *dw);
+
+#endif /* _DW_EDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
new file mode 100644
index 000000000..406f169b0
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA v0 core
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/bitfield.h>
+
+#include "dw-edma-v0-debugfs.h"
+#include "dw-edma-v0-regs.h"
+#include "dw-edma-core.h"
+
+#define REGS_ADDR(dw, name)						       \
+	({								       \
+		struct dw_edma_v0_regs __iomem *__regs = (dw)->chip->reg_base; \
+									       \
+		(void __iomem *)&__regs->name;				       \
+	})
+
+#define REGS_CH_ADDR(dw, name, _dir, _ch)				       \
+	({								       \
+		struct dw_edma_v0_ch_regs __iomem *__ch_regs;		       \
+									       \
+		if ((dw)->chip->mf == EDMA_MF_EDMA_LEGACY)		       \
+			__ch_regs = REGS_ADDR(dw, type.legacy.ch);	       \
+		else if (_dir == EDMA_DIR_READ)				       \
+			__ch_regs = REGS_ADDR(dw, type.unroll.ch[_ch].rd);     \
+		else							       \
+			__ch_regs = REGS_ADDR(dw, type.unroll.ch[_ch].wr);     \
+									       \
+		(void __iomem *)&__ch_regs->name;			       \
+	})
+
+#define REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, name) }
+
+#define CTX_REGISTER(dw, name, dir, ch) \
+	{ dw, #name, REGS_CH_ADDR(dw, name, dir, ch), dir, ch }
+
+#define WR_REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, wr_##name) }
+#define RD_REGISTER(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, rd_##name) }
+
+#define WR_REGISTER_LEGACY(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.legacy.wr_##name) }
+#define RD_REGISTER_LEGACY(name) \
+	{ dw, #name, REGS_ADDR(dw, type.legacy.rd_##name) }
+
+#define WR_REGISTER_UNROLL(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.unroll.wr_##name) }
+#define RD_REGISTER_UNROLL(dw, name) \
+	{ dw, #name, REGS_ADDR(dw, type.unroll.rd_##name) }
+
+#define WRITE_STR				"write"
+#define READ_STR				"read"
+#define CHANNEL_STR				"channel"
+#define REGISTERS_STR				"registers"
+
+struct dw_edma_debugfs_entry {
+	struct dw_edma				*dw;
+	const char				*name;
+	void __iomem				*reg;
+	enum dw_edma_dir			dir;
+	u16					ch;
+};
+
+static int dw_edma_debugfs_u32_get(void *data, u64 *val)
+{
+	struct dw_edma_debugfs_entry *entry = data;
+	struct dw_edma *dw = entry->dw;
+	void __iomem *reg = entry->reg;
+
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY &&
+	    reg >= REGS_ADDR(dw, type.legacy.ch)) {
+		unsigned long flags;
+		u32 viewport_sel;
+
+		viewport_sel = entry->dir == EDMA_DIR_READ ? BIT(31) : 0;
+		viewport_sel |= FIELD_PREP(EDMA_V0_VIEWPORT_MASK, entry->ch);
+
+		raw_spin_lock_irqsave(&dw->lock, flags);
+
+		writel(viewport_sel, REGS_ADDR(dw, type.legacy.viewport_sel));
+		*val = readl(reg);
+
+		raw_spin_unlock_irqrestore(&dw->lock, flags);
+	} else {
+		*val = readl(reg);
+	}
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, dw_edma_debugfs_u32_get, NULL, "0x%08llx\n");
+
+static void dw_edma_debugfs_create_x32(struct dw_edma *dw,
+				       const struct dw_edma_debugfs_entry ini[],
+				       int nr_entries, struct dentry *dent)
+{
+	struct dw_edma_debugfs_entry *entries;
+	int i;
+
+	entries = devm_kcalloc(dw->chip->dev, nr_entries, sizeof(*entries),
+			       GFP_KERNEL);
+	if (!entries)
+		return;
+
+	for (i = 0; i < nr_entries; i++) {
+		entries[i] = ini[i];
+
+		debugfs_create_file_unsafe(entries[i].name, 0444, dent,
+					   &entries[i], &fops_x32);
+	}
+}
+
+static void dw_edma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
+				    u16 ch, struct dentry *dent)
+{
+	struct dw_edma_debugfs_entry debugfs_regs[] = {
+		CTX_REGISTER(dw, ch_control1, dir, ch),
+		CTX_REGISTER(dw, ch_control2, dir, ch),
+		CTX_REGISTER(dw, transfer_size, dir, ch),
+		CTX_REGISTER(dw, sar.lsb, dir, ch),
+		CTX_REGISTER(dw, sar.msb, dir, ch),
+		CTX_REGISTER(dw, dar.lsb, dir, ch),
+		CTX_REGISTER(dw, dar.msb, dir, ch),
+		CTX_REGISTER(dw, llp.lsb, dir, ch),
+		CTX_REGISTER(dw, llp.msb, dir, ch),
+	};
+	int nr_entries;
+
+	nr_entries = ARRAY_SIZE(debugfs_regs);
+	dw_edma_debugfs_create_x32(dw, debugfs_regs, nr_entries, dent);
+}
+
+static noinline_for_stack void
+dw_edma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
+{
+	const struct dw_edma_debugfs_entry debugfs_regs[] = {
+		/* eDMA global registers */
+		WR_REGISTER(dw, engine_en),
+		WR_REGISTER(dw, doorbell),
+		WR_REGISTER(dw, ch_arb_weight.lsb),
+		WR_REGISTER(dw, ch_arb_weight.msb),
+		/* eDMA interrupts registers */
+		WR_REGISTER(dw, int_status),
+		WR_REGISTER(dw, int_mask),
+		WR_REGISTER(dw, int_clear),
+		WR_REGISTER(dw, err_status),
+		WR_REGISTER(dw, done_imwr.lsb),
+		WR_REGISTER(dw, done_imwr.msb),
+		WR_REGISTER(dw, abort_imwr.lsb),
+		WR_REGISTER(dw, abort_imwr.msb),
+		WR_REGISTER(dw, ch01_imwr_data),
+		WR_REGISTER(dw, ch23_imwr_data),
+		WR_REGISTER(dw, ch45_imwr_data),
+		WR_REGISTER(dw, ch67_imwr_data),
+		WR_REGISTER(dw, linked_list_err_en),
+	};
+	const struct dw_edma_debugfs_entry debugfs_unroll_regs[] = {
+		/* eDMA channel context grouping */
+		WR_REGISTER_UNROLL(dw, engine_chgroup),
+		WR_REGISTER_UNROLL(dw, engine_hshake_cnt.lsb),
+		WR_REGISTER_UNROLL(dw, engine_hshake_cnt.msb),
+		WR_REGISTER_UNROLL(dw, ch0_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch1_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch2_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch3_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch4_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch5_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch6_pwr_en),
+		WR_REGISTER_UNROLL(dw, ch7_pwr_en),
+	};
+	struct dentry *regs_dent, *ch_dent;
+	int nr_entries, i;
+	char name[32];
+
+	regs_dent = debugfs_create_dir(WRITE_STR, dent);
+
+	nr_entries = ARRAY_SIZE(debugfs_regs);
+	dw_edma_debugfs_create_x32(dw, debugfs_regs, nr_entries, regs_dent);
+
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
+		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
+		dw_edma_debugfs_create_x32(dw, debugfs_unroll_regs, nr_entries,
+					   regs_dent);
+	}
+
+	for (i = 0; i < dw->wr_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_edma_debugfs_regs_ch(dw, EDMA_DIR_WRITE, i, ch_dent);
+	}
+}
+
+static noinline_for_stack void dw_edma_debugfs_regs_rd(struct dw_edma *dw,
+						       struct dentry *dent)
+{
+	const struct dw_edma_debugfs_entry debugfs_regs[] = {
+		/* eDMA global registers */
+		RD_REGISTER(dw, engine_en),
+		RD_REGISTER(dw, doorbell),
+		RD_REGISTER(dw, ch_arb_weight.lsb),
+		RD_REGISTER(dw, ch_arb_weight.msb),
+		/* eDMA interrupts registers */
+		RD_REGISTER(dw, int_status),
+		RD_REGISTER(dw, int_mask),
+		RD_REGISTER(dw, int_clear),
+		RD_REGISTER(dw, err_status.lsb),
+		RD_REGISTER(dw, err_status.msb),
+		RD_REGISTER(dw, linked_list_err_en),
+		RD_REGISTER(dw, done_imwr.lsb),
+		RD_REGISTER(dw, done_imwr.msb),
+		RD_REGISTER(dw, abort_imwr.lsb),
+		RD_REGISTER(dw, abort_imwr.msb),
+		RD_REGISTER(dw, ch01_imwr_data),
+		RD_REGISTER(dw, ch23_imwr_data),
+		RD_REGISTER(dw, ch45_imwr_data),
+		RD_REGISTER(dw, ch67_imwr_data),
+	};
+	const struct dw_edma_debugfs_entry debugfs_unroll_regs[] = {
+		/* eDMA channel context grouping */
+		RD_REGISTER_UNROLL(dw, engine_chgroup),
+		RD_REGISTER_UNROLL(dw, engine_hshake_cnt.lsb),
+		RD_REGISTER_UNROLL(dw, engine_hshake_cnt.msb),
+		RD_REGISTER_UNROLL(dw, ch0_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch1_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch2_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch3_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch4_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch5_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch6_pwr_en),
+		RD_REGISTER_UNROLL(dw, ch7_pwr_en),
+	};
+	struct dentry *regs_dent, *ch_dent;
+	int nr_entries, i;
+	char name[32];
+
+	regs_dent = debugfs_create_dir(READ_STR, dent);
+
+	nr_entries = ARRAY_SIZE(debugfs_regs);
+	dw_edma_debugfs_create_x32(dw, debugfs_regs, nr_entries, regs_dent);
+
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
+		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
+		dw_edma_debugfs_create_x32(dw, debugfs_unroll_regs, nr_entries,
+					   regs_dent);
+	}
+
+	for (i = 0; i < dw->rd_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_edma_debugfs_regs_ch(dw, EDMA_DIR_READ, i, ch_dent);
+	}
+}
+
+static void dw_edma_debugfs_regs(struct dw_edma *dw)
+{
+	const struct dw_edma_debugfs_entry debugfs_regs[] = {
+		REGISTER(dw, ctrl_data_arb_prior),
+		REGISTER(dw, ctrl),
+	};
+	struct dentry *regs_dent;
+	int nr_entries;
+
+	regs_dent = debugfs_create_dir(REGISTERS_STR, dw->dma.dbg_dev_root);
+
+	nr_entries = ARRAY_SIZE(debugfs_regs);
+	dw_edma_debugfs_create_x32(dw, debugfs_regs, nr_entries, regs_dent);
+
+	dw_edma_debugfs_regs_wr(dw, regs_dent);
+	dw_edma_debugfs_regs_rd(dw, regs_dent);
+}
+
+void dw_edma_v0_debugfs_on(struct dw_edma *dw)
+{
+	if (!debugfs_initialized())
+		return;
+
+	debugfs_create_u32("mf", 0444, dw->dma.dbg_dev_root, &dw->chip->mf);
+	debugfs_create_u16("wr_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->wr_ch_cnt);
+	debugfs_create_u16("rd_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->rd_ch_cnt);
+
+	dw_edma_debugfs_regs(dw);
+}
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.h b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
new file mode 100644
index 000000000..fb3342d97
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA v0 core
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#ifndef _DW_EDMA_V0_DEBUG_FS_H
+#define _DW_EDMA_V0_DEBUG_FS_H
+
+#include <linux/dma/edma.h>
+
+#ifdef CONFIG_DEBUG_FS
+void dw_edma_v0_debugfs_on(struct dw_edma *dw);
+#else
+static inline void dw_edma_v0_debugfs_on(struct dw_edma *dw)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _DW_EDMA_V0_DEBUG_FS_H */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-regs.h b/drivers/dma/dw-edma/dw-edma-v0-regs.h
new file mode 100644
index 000000000..e175f7b20
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-edma-v0-regs.h
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare eDMA v0 core
+ *
+ * Author: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+ */
+
+#ifndef _DW_EDMA_V0_REGS_H
+#define _DW_EDMA_V0_REGS_H
+
+#include <linux/dmaengine.h>
+
+#define EDMA_V0_MAX_NR_CH				8
+#define EDMA_V0_VIEWPORT_MASK				GENMASK(2, 0)
+#define EDMA_V0_DONE_INT_MASK				GENMASK(7, 0)
+#define EDMA_V0_ABORT_INT_MASK				GENMASK(23, 16)
+#define EDMA_V0_WRITE_CH_COUNT_MASK			GENMASK(3, 0)
+#define EDMA_V0_READ_CH_COUNT_MASK			GENMASK(19, 16)
+#define EDMA_V0_CH_STATUS_MASK				GENMASK(6, 5)
+#define EDMA_V0_DOORBELL_CH_MASK			GENMASK(2, 0)
+#define EDMA_V0_LINKED_LIST_ERR_MASK			GENMASK(7, 0)
+
+#define EDMA_V0_CH_ODD_MSI_DATA_MASK			GENMASK(31, 16)
+#define EDMA_V0_CH_EVEN_MSI_DATA_MASK			GENMASK(15, 0)
+
+struct dw_edma_v0_ch_regs {
+	u32 ch_control1;				/* 0x0000 */
+	u32 ch_control2;				/* 0x0004 */
+	u32 transfer_size;				/* 0x0008 */
+	union {
+		u64 reg;				/* 0x000c..0x0010 */
+		struct {
+			u32 lsb;			/* 0x000c */
+			u32 msb;			/* 0x0010 */
+		};
+	} sar;
+	union {
+		u64 reg;				/* 0x0014..0x0018 */
+		struct {
+			u32 lsb;			/* 0x0014 */
+			u32 msb;			/* 0x0018 */
+		};
+	} dar;
+	union {
+		u64 reg;				/* 0x001c..0x0020 */
+		struct {
+			u32 lsb;			/* 0x001c */
+			u32 msb;			/* 0x0020 */
+		};
+	} llp;
+} __packed;
+
+struct dw_edma_v0_ch {
+	struct dw_edma_v0_ch_regs wr;			/* 0x0200 */
+	u32 padding_1[55];				/* 0x0224..0x02fc */
+	struct dw_edma_v0_ch_regs rd;			/* 0x0300 */
+	u32 padding_2[55];				/* 0x0324..0x03fc */
+} __packed;
+
+struct dw_edma_v0_unroll {
+	u32 padding_1;					/* 0x00f8 */
+	u32 wr_engine_chgroup;				/* 0x0100 */
+	u32 rd_engine_chgroup;				/* 0x0104 */
+	union {
+		u64 reg;				/* 0x0108..0x010c */
+		struct {
+			u32 lsb;			/* 0x0108 */
+			u32 msb;			/* 0x010c */
+		};
+	} wr_engine_hshake_cnt;
+	u32 padding_2[2];				/* 0x0110..0x0114 */
+	union {
+		u64 reg;				/* 0x0120..0x0124 */
+		struct {
+			u32 lsb;			/* 0x0120 */
+			u32 msb;			/* 0x0124 */
+		};
+	} rd_engine_hshake_cnt;
+	u32 padding_3[2];				/* 0x0120..0x0124 */
+	u32 wr_ch0_pwr_en;				/* 0x0128 */
+	u32 wr_ch1_pwr_en;				/* 0x012c */
+	u32 wr_ch2_pwr_en;				/* 0x0130 */
+	u32 wr_ch3_pwr_en;				/* 0x0134 */
+	u32 wr_ch4_pwr_en;				/* 0x0138 */
+	u32 wr_ch5_pwr_en;				/* 0x013c */
+	u32 wr_ch6_pwr_en;				/* 0x0140 */
+	u32 wr_ch7_pwr_en;				/* 0x0144 */
+	u32 padding_4[8];				/* 0x0148..0x0164 */
+	u32 rd_ch0_pwr_en;				/* 0x0168 */
+	u32 rd_ch1_pwr_en;				/* 0x016c */
+	u32 rd_ch2_pwr_en;				/* 0x0170 */
+	u32 rd_ch3_pwr_en;				/* 0x0174 */
+	u32 rd_ch4_pwr_en;				/* 0x0178 */
+	u32 rd_ch5_pwr_en;				/* 0x018c */
+	u32 rd_ch6_pwr_en;				/* 0x0180 */
+	u32 rd_ch7_pwr_en;				/* 0x0184 */
+	u32 padding_5[30];				/* 0x0188..0x01fc */
+	struct dw_edma_v0_ch ch[EDMA_V0_MAX_NR_CH];	/* 0x0200..0x1120 */
+} __packed;
+
+struct dw_edma_v0_legacy {
+	u32 viewport_sel;				/* 0x00f8 */
+	struct dw_edma_v0_ch_regs ch;			/* 0x0100..0x0120 */
+} __packed;
+
+struct dw_edma_v0_regs {
+	/* eDMA global registers */
+	u32 ctrl_data_arb_prior;			/* 0x0000 */
+	u32 padding_1;					/* 0x0004 */
+	u32 ctrl;					/* 0x0008 */
+	u32 wr_engine_en;				/* 0x000c */
+	u32 wr_doorbell;				/* 0x0010 */
+	u32 padding_2;					/* 0x0014 */
+	union {
+		u64 reg;				/* 0x0018..0x001c */
+		struct {
+			u32 lsb;			/* 0x0018 */
+			u32 msb;			/* 0x001c */
+		};
+	} wr_ch_arb_weight;
+	u32 padding_3[3];				/* 0x0020..0x0028 */
+	u32 rd_engine_en;				/* 0x002c */
+	u32 rd_doorbell;				/* 0x0030 */
+	u32 padding_4;					/* 0x0034 */
+	union {
+		u64 reg;				/* 0x0038..0x003c */
+		struct {
+			u32 lsb;			/* 0x0038 */
+			u32 msb;			/* 0x003c */
+		};
+	} rd_ch_arb_weight;
+	u32 padding_5[3];				/* 0x0040..0x0048 */
+	/* eDMA interrupts registers */
+	u32 wr_int_status;				/* 0x004c */
+	u32 padding_6;					/* 0x0050 */
+	u32 wr_int_mask;				/* 0x0054 */
+	u32 wr_int_clear;				/* 0x0058 */
+	u32 wr_err_status;				/* 0x005c */
+	union {
+		u64 reg;				/* 0x0060..0x0064 */
+		struct {
+			u32 lsb;			/* 0x0060 */
+			u32 msb;			/* 0x0064 */
+		};
+	} wr_done_imwr;
+	union {
+		u64 reg;				/* 0x0068..0x006c */
+		struct {
+			u32 lsb;			/* 0x0068 */
+			u32 msb;			/* 0x006c */
+		};
+	} wr_abort_imwr;
+	u32 wr_ch01_imwr_data;				/* 0x0070 */
+	u32 wr_ch23_imwr_data;				/* 0x0074 */
+	u32 wr_ch45_imwr_data;				/* 0x0078 */
+	u32 wr_ch67_imwr_data;				/* 0x007c */
+	u32 padding_7[4];				/* 0x0080..0x008c */
+	u32 wr_linked_list_err_en;			/* 0x0090 */
+	u32 padding_8[3];				/* 0x0094..0x009c */
+	u32 rd_int_status;				/* 0x00a0 */
+	u32 padding_9;					/* 0x00a4 */
+	u32 rd_int_mask;				/* 0x00a8 */
+	u32 rd_int_clear;				/* 0x00ac */
+	u32 padding_10;					/* 0x00b0 */
+	union {
+		u64 reg;				/* 0x00b4..0x00b8 */
+		struct {
+			u32 lsb;			/* 0x00b4 */
+			u32 msb;			/* 0x00b8 */
+		};
+	} rd_err_status;
+	u32 padding_11[2];				/* 0x00bc..0x00c0 */
+	u32 rd_linked_list_err_en;			/* 0x00c4 */
+	u32 padding_12;					/* 0x00c8 */
+	union {
+		u64 reg;				/* 0x00cc..0x00d0 */
+		struct {
+			u32 lsb;			/* 0x00cc */
+			u32 msb;			/* 0x00d0 */
+		};
+	} rd_done_imwr;
+	union {
+		u64 reg;				/* 0x00d4..0x00d8 */
+		struct {
+			u32 lsb;			/* 0x00d4 */
+			u32 msb;			/* 0x00d8 */
+		};
+	} rd_abort_imwr;
+	u32 rd_ch01_imwr_data;				/* 0x00dc */
+	u32 rd_ch23_imwr_data;				/* 0x00e0 */
+	u32 rd_ch45_imwr_data;				/* 0x00e4 */
+	u32 rd_ch67_imwr_data;				/* 0x00e8 */
+	u32 padding_13[4];				/* 0x00ec..0x00f8 */
+	/* eDMA channel context grouping */
+	union dw_edma_v0_type {
+		struct dw_edma_v0_legacy legacy;	/* 0x00f8..0x0120 */
+		struct dw_edma_v0_unroll unroll;	/* 0x00f8..0x1120 */
+	} type;
+} __packed;
+
+struct dw_edma_v0_lli {
+	u32 control;
+	u32 transfer_size;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} sar;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} dar;
+} __packed;
+
+struct dw_edma_v0_llp {
+	u32 control;
+	u32 reserved;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} llp;
+} __packed;
+
+#endif /* _DW_EDMA_V0_REGS_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
new file mode 100644
index 000000000..36ee72efc
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 core
+ */
+
+#include <linux/bitfield.h>
+#include <linux/irqreturn.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include "dw-edma-core.h"
+#include "dw-hdma-v0-core.h"
+#include "dw-hdma-v0-regs.h"
+#include "dw-hdma-v0-debugfs.h"
+
+enum dw_hdma_control {
+	DW_HDMA_V0_CB					= BIT(0),
+	DW_HDMA_V0_TCB					= BIT(1),
+	DW_HDMA_V0_LLP					= BIT(2),
+	DW_HDMA_V0_LWIE					= BIT(3),
+	DW_HDMA_V0_RWIE					= BIT(4),
+	DW_HDMA_V0_CCS					= BIT(8),
+	DW_HDMA_V0_LLE					= BIT(9),
+};
+
+static inline struct dw_hdma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
+{
+	return dw->chip->reg_base;
+}
+
+static inline struct dw_hdma_v0_ch_regs __iomem *
+__dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
+{
+	if (dir == EDMA_DIR_WRITE)
+		return &(__dw_regs(dw)->ch[ch].wr);
+	else
+		return &(__dw_regs(dw)->ch[ch].rd);
+}
+
+#define SET_CH_32(dw, dir, ch, name, value) \
+	writel(value, &(__dw_ch_regs(dw, dir, ch)->name))
+
+#define GET_CH_32(dw, dir, ch, name) \
+	readl(&(__dw_ch_regs(dw, dir, ch)->name))
+
+#define SET_BOTH_CH_32(dw, ch, name, value) \
+	do {					\
+		writel(value, &(__dw_ch_regs(dw, EDMA_DIR_WRITE, ch)->name));	\
+		writel(value, &(__dw_ch_regs(dw, EDMA_DIR_READ, ch)->name));	\
+	} while (0)
+
+static u32 dw_hdma_v0_core_int_setup(struct dw_edma_chan *chan, u32 val)
+{
+	val &= ~(HDMA_V0_LOCAL_ABORT_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN |
+		 HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_REMOTE_STOP_INT_EN |
+		 HDMA_V0_ABORT_INT_MASK | HDMA_V0_STOP_INT_MASK);
+
+	/*
+	 * HDMA_INT_STATUS.STOP and .ABORT are latched only when LSIE and
+	 * LAIE are enabled. A remote handler needs those status bits to
+	 * identify the source of the IMWr, so keep local generation enabled
+	 * and mask the local interrupt pins instead.
+	 */
+	val |= HDMA_V0_LOCAL_ABORT_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN;
+
+	if (chan->irq_mode == DW_EDMA_CH_IRQ_REMOTE)
+		val |= HDMA_V0_REMOTE_ABORT_INT_EN |
+		       HDMA_V0_REMOTE_STOP_INT_EN |
+		       HDMA_V0_ABORT_INT_MASK | HDMA_V0_STOP_INT_MASK;
+
+	return val;
+}
+
+/* HDMA management callbacks */
+static void dw_hdma_v0_core_ch_off(struct dw_edma *dw, enum dw_edma_dir dir,
+				   u16 id)
+{
+	SET_CH_32(dw, dir, id, int_setup,
+		  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+	SET_CH_32(dw, dir, id, ch_en, 0);
+	SET_CH_32(dw, dir, id, int_clear,
+		  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+}
+
+static void dw_hdma_v0_core_off(struct dw_edma *dw)
+{
+	int id;
+	enum dw_edma_dir dir;
+
+	dir = EDMA_DIR_WRITE;
+	for (id = 0; id < dw->wr_ch_cnt; id++) {
+		SET_CH_32(dw, dir, id, int_setup,
+			  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_CH_32(dw, dir, id, int_clear,
+			  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_CH_32(dw, dir, id, ch_en, 0);
+	}
+
+	dir = EDMA_DIR_READ;
+	for (id = 0; id < dw->rd_ch_cnt; id++) {
+		SET_CH_32(dw, dir, id, int_setup,
+			  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_CH_32(dw, dir, id, int_clear,
+			  HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_CH_32(dw, dir, id, ch_en, 0);
+	}
+}
+
+static int dw_hdma_v0_core_quiesce(struct dw_edma *dw)
+{
+	int id;
+
+	for (id = 0; id < dw->wr_ch_cnt; id++)
+		dw_hdma_v0_core_ch_off(dw, EDMA_DIR_WRITE, id);
+	for (id = 0; id < dw->rd_ch_cnt; id++)
+		dw_hdma_v0_core_ch_off(dw, EDMA_DIR_READ, id);
+
+	return 0;
+}
+
+static int dw_hdma_v0_core_ch_quiesce(struct dw_edma_chan *chan)
+{
+	dw_hdma_v0_core_ch_off(chan->dw, chan->dir, chan->id);
+
+	return 0;
+}
+
+static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	/*
+	 * The HDMA IP have no way to know the number of hardware channels
+	 * available, we set it to maximum channels and let the platform
+	 * set the right number of channels.
+	 */
+	return HDMA_V0_MAX_NR_CH;
+}
+
+static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 tmp;
+
+	tmp = FIELD_GET(HDMA_V0_CH_STATUS_MASK,
+			GET_CH_32(dw, chan->dir, chan->id, ch_stat));
+
+	if (tmp == 1)
+		return DMA_IN_PROGRESS;
+	else if (tmp == 3)
+		return DMA_COMPLETE;
+	else
+		return DMA_ERROR;
+}
+
+static void dw_hdma_v0_core_clear_done_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_CH_32(dw, chan->dir, chan->id, int_clear, HDMA_V0_STOP_INT_MASK);
+}
+
+static void dw_hdma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_CH_32(dw, chan->dir, chan->id, int_clear, HDMA_V0_ABORT_INT_MASK);
+}
+
+static u32 dw_hdma_v0_core_status_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	return GET_CH_32(dw, chan->dir, chan->id, int_stat);
+}
+
+static irqreturn_t
+dw_hdma_v0_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			   dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	struct dw_edma *dw = dw_irq->dw;
+	unsigned long total, pos, val;
+	irqreturn_t ret = IRQ_NONE;
+	struct dw_edma_chan *chan;
+	unsigned long off, *mask;
+
+	if (dir == EDMA_DIR_WRITE) {
+		total = dw->wr_ch_cnt;
+		off = 0;
+		mask = dw_irq->wr_mask;
+	} else {
+		total = dw->rd_ch_cnt;
+		off = dw->wr_ch_cnt;
+		mask = dw_irq->rd_mask;
+	}
+
+	for_each_set_bit(pos, mask, total) {
+		chan = &dw->chan[pos + off];
+		if (unlikely(dw_edma_core_ch_ignore_irq(chan)))
+			continue;
+
+		val = dw_hdma_v0_core_status_int(chan);
+		if (FIELD_GET(HDMA_V0_STOP_INT_MASK, val)) {
+			dw_hdma_v0_core_clear_done_int(chan);
+			done(chan);
+
+			ret = IRQ_HANDLED;
+		}
+
+		if (FIELD_GET(HDMA_V0_ABORT_INT_MASK, val)) {
+			dw_hdma_v0_core_clear_abort_int(chan);
+			abort(chan);
+
+			ret = IRQ_HANDLED;
+		}
+	}
+
+	return ret;
+}
+
+static void dw_hdma_v0_write_ll_data(struct dw_edma_chan *chan, int i,
+				     u32 control, u32 size, u64 sar, u64 dar)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_hdma_v0_lli);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_hdma_v0_lli *lli = chan->ll_region.vaddr.mem + ofs;
+
+		lli->transfer_size = size;
+		lli->sar.reg = sar;
+		lli->dar.reg = dar;
+		dma_wmb();
+		lli->control = control;
+	} else {
+		struct dw_hdma_v0_lli __iomem *lli = chan->ll_region.vaddr.io + ofs;
+
+		writel(size, &lli->transfer_size);
+		writeq(sar, &lli->sar.reg);
+		writeq(dar, &lli->dar.reg);
+		writel(control, &lli->control);
+	}
+}
+
+static void dw_hdma_v0_write_ll_link(struct dw_edma_chan *chan,
+				     int i, u32 control, u64 pointer)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_hdma_v0_lli);
+
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_hdma_v0_llp *llp = chan->ll_region.vaddr.mem + ofs;
+
+		llp->llp.reg = pointer;
+		dma_wmb();
+		llp->control = control;
+	} else {
+		struct dw_hdma_v0_llp __iomem *llp = chan->ll_region.vaddr.io + ofs;
+
+		writeq(pointer, &llp->llp.reg);
+		writel(control, &llp->control);
+	}
+}
+
+static void dw_hdma_v0_core_ch_enable(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 tmp;
+
+	/* Enable engine */
+	SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0));
+	/* Interrupt unmask - stop, abort */
+	tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup);
+	tmp = dw_hdma_v0_core_int_setup(chan, tmp);
+	SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
+	/* Channel control */
+	SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN);
+	/* Linked list */
+	/* llp is not aligned on 64bit -> keep 32bit accesses */
+	SET_CH_32(dw, chan->dir, chan->id, llp.lsb,
+		  lower_32_bits(chan->ll_region.paddr));
+	SET_CH_32(dw, chan->dir, chan->id, llp.msb,
+		  upper_32_bits(chan->ll_region.paddr));
+	/* Set consumer cycle */
+	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
+		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
+}
+
+static void dw_hdma_v0_sync_ll_data(struct dw_edma_chan *chan)
+{
+	/*
+	 * In case of remote HDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chan->ll_region.vaddr.io);
+}
+
+static void dw_hdma_v0_core_non_ll_start(struct dw_edma_chan *chan,
+					 struct dw_edma_burst *child)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 val;
+
+	SET_CH_32(dw, chan->dir, chan->id, ch_en, HDMA_V0_CH_EN);
+
+	/* Source address */
+	SET_CH_32(dw, chan->dir, chan->id, sar.lsb,
+		  lower_32_bits(child->sar));
+	SET_CH_32(dw, chan->dir, chan->id, sar.msb,
+		  upper_32_bits(child->sar));
+
+	/* Destination address */
+	SET_CH_32(dw, chan->dir, chan->id, dar.lsb,
+		  lower_32_bits(child->dar));
+	SET_CH_32(dw, chan->dir, chan->id, dar.msb,
+		  upper_32_bits(child->dar));
+
+	/* Transfer size */
+	SET_CH_32(dw, chan->dir, chan->id, transfer_size, child->sz);
+
+	/* Interrupt setup */
+	val = GET_CH_32(dw, chan->dir, chan->id, int_setup);
+	val = dw_hdma_v0_core_int_setup(chan, val);
+	SET_CH_32(dw, chan->dir, chan->id, int_setup, val);
+
+	/* Channel control setup */
+	val = GET_CH_32(dw, chan->dir, chan->id, control1);
+	val &= ~HDMA_V0_LINKLIST_EN;
+	SET_CH_32(dw, chan->dir, chan->id, control1, val);
+
+	SET_CH_32(dw, chan->dir, chan->id, doorbell,
+		  HDMA_V0_DOORBELL_START);
+}
+
+static void dw_hdma_v0_core_ch_config(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	/* MSI done addr - low, high */
+	SET_CH_32(dw, chan->dir, chan->id, msi_stop.lsb, chan->msi.address_lo);
+	SET_CH_32(dw, chan->dir, chan->id, msi_stop.msb, chan->msi.address_hi);
+	/* MSI abort addr - low, high */
+	SET_CH_32(dw, chan->dir, chan->id, msi_abort.lsb, chan->msi.address_lo);
+	SET_CH_32(dw, chan->dir, chan->id, msi_abort.msb, chan->msi.address_hi);
+	/* config MSI data */
+	SET_CH_32(dw, chan->dir, chan->id, msi_msgdata, chan->msi.data);
+	/* Configure the requester function number used by outbound TLPs. */
+	SET_CH_32(dw, chan->dir, chan->id, func_num,
+		  FIELD_PREP(HDMA_V0_FUNC_NUM_PF_MASK, chan->func_no));
+}
+
+static void
+dw_hdma_v0_core_ll_data(struct dw_edma_chan *chan, struct dw_edma_burst *burst,
+			u32 idx, bool cb, bool irq)
+{
+	u32 control = 0;
+
+	if (cb)
+		control |= DW_HDMA_V0_CB;
+
+	dw_hdma_v0_write_ll_data(chan, idx, control, burst->sz, burst->sar,
+				 burst->dar);
+}
+
+static void
+dw_hdma_v0_core_ll_link(struct dw_edma_chan *chan, u32 idx, bool cb, u64 addr)
+{
+	u32 control = DW_HDMA_V0_LLP | DW_HDMA_V0_TCB;
+
+	if (!cb)
+		control |= DW_HDMA_V0_CB;
+
+	dw_hdma_v0_write_ll_link(chan, idx, control, addr);
+}
+
+static void dw_hdma_v0_core_ch_doorbell(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	dw_hdma_v0_sync_ll_data(chan);
+
+	/* Doorbell */
+	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
+}
+
+/* HDMA debugfs callbacks */
+static void dw_hdma_v0_core_debugfs_on(struct dw_edma *dw)
+{
+	dw_hdma_v0_debugfs_on(dw);
+}
+
+static resource_size_t dw_hdma_v0_core_db_offset(struct dw_edma *dw)
+{
+	/* Implement once the correct offset is known. */
+	return ~0;
+}
+
+static const struct dw_edma_core_ops dw_hdma_v0_core = {
+	.off = dw_hdma_v0_core_off,
+	.quiesce = dw_hdma_v0_core_quiesce,
+	.ch_quiesce = dw_hdma_v0_core_ch_quiesce,
+	.ch_count = dw_hdma_v0_core_ch_count,
+	.ch_status = dw_hdma_v0_core_ch_status,
+	.handle_int = dw_hdma_v0_core_handle_int,
+	.non_ll_start = dw_hdma_v0_core_non_ll_start,
+	.ll_data = dw_hdma_v0_core_ll_data,
+	.ll_link = dw_hdma_v0_core_ll_link,
+	.ch_doorbell = dw_hdma_v0_core_ch_doorbell,
+	.ch_enable = dw_hdma_v0_core_ch_enable,
+	.ch_config = dw_hdma_v0_core_ch_config,
+	.debugfs_on = dw_hdma_v0_core_debugfs_on,
+	.db_offset = dw_hdma_v0_core_db_offset,
+};
+
+void dw_hdma_v0_core_register(struct dw_edma *dw)
+{
+	dw->core = &dw_hdma_v0_core;
+}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.h b/drivers/dma/dw-edma/dw-hdma-v0-core.h
new file mode 100644
index 000000000..c373b4f0b
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 core
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_CORE_H
+#define _DW_HDMA_V0_CORE_H
+
+#include <linux/dma/edma.h>
+
+/* HDMA core register */
+void dw_hdma_v0_core_register(struct dw_edma *dw);
+
+#endif /* _DW_HDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
new file mode 100644
index 000000000..dcdc57fe9
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 debugfs
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/bitfield.h>
+
+#include "dw-hdma-v0-debugfs.h"
+#include "dw-hdma-v0-regs.h"
+#include "dw-edma-core.h"
+
+#define REGS_ADDR(dw, name)						       \
+	({								       \
+		struct dw_hdma_v0_regs __iomem *__regs = (dw)->chip->reg_base; \
+									       \
+		(void __iomem *)&__regs->name;				       \
+	})
+
+#define REGS_CH_ADDR(dw, name, _dir, _ch)				       \
+	({								       \
+		struct dw_hdma_v0_ch_regs __iomem *__ch_regs;		       \
+									       \
+		if (_dir == EDMA_DIR_READ)				       \
+			__ch_regs = REGS_ADDR(dw, ch[_ch].rd);		       \
+		else							       \
+			__ch_regs = REGS_ADDR(dw, ch[_ch].wr);		       \
+									       \
+		(void __iomem *)&__ch_regs->name;			       \
+	})
+
+#define CTX_REGISTER(dw, name, dir, ch) \
+	{#name, REGS_CH_ADDR(dw, name, dir, ch)}
+
+#define WRITE_STR				"write"
+#define READ_STR				"read"
+#define CHANNEL_STR				"channel"
+#define REGISTERS_STR				"registers"
+
+struct dw_hdma_debugfs_entry {
+	const char				*name;
+	void __iomem				*reg;
+};
+
+static int dw_hdma_debugfs_u32_get(void *data, u64 *val)
+{
+	struct dw_hdma_debugfs_entry *entry = data;
+	void __iomem *reg = entry->reg;
+
+	*val = readl(reg);
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, dw_hdma_debugfs_u32_get, NULL, "0x%08llx\n");
+
+static void dw_hdma_debugfs_create_x32(struct dw_edma *dw,
+				       const struct dw_hdma_debugfs_entry ini[],
+				       int nr_entries, struct dentry *dent)
+{
+	struct dw_hdma_debugfs_entry *entries;
+	int i;
+
+	entries = devm_kcalloc(dw->chip->dev, nr_entries, sizeof(*entries),
+			       GFP_KERNEL);
+	if (!entries)
+		return;
+
+	for (i = 0; i < nr_entries; i++) {
+		entries[i] = ini[i];
+
+		debugfs_create_file_unsafe(entries[i].name, 0444, dent,
+					   &entries[i], &fops_x32);
+	}
+}
+
+static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
+				    u16 ch, struct dentry *dent)
+{
+	const struct dw_hdma_debugfs_entry debugfs_regs[] = {
+		CTX_REGISTER(dw, ch_en, dir, ch),
+		CTX_REGISTER(dw, doorbell, dir, ch),
+		CTX_REGISTER(dw, prefetch, dir, ch),
+		CTX_REGISTER(dw, handshake, dir, ch),
+		CTX_REGISTER(dw, llp.lsb, dir, ch),
+		CTX_REGISTER(dw, llp.msb, dir, ch),
+		CTX_REGISTER(dw, cycle_sync, dir, ch),
+		CTX_REGISTER(dw, transfer_size, dir, ch),
+		CTX_REGISTER(dw, sar.lsb, dir, ch),
+		CTX_REGISTER(dw, sar.msb, dir, ch),
+		CTX_REGISTER(dw, dar.lsb, dir, ch),
+		CTX_REGISTER(dw, dar.msb, dir, ch),
+		CTX_REGISTER(dw, watermark_en, dir, ch),
+		CTX_REGISTER(dw, control1, dir, ch),
+		CTX_REGISTER(dw, func_num, dir, ch),
+		CTX_REGISTER(dw, qos, dir, ch),
+		CTX_REGISTER(dw, ch_stat, dir, ch),
+		CTX_REGISTER(dw, int_stat, dir, ch),
+		CTX_REGISTER(dw, int_setup, dir, ch),
+		CTX_REGISTER(dw, int_clear, dir, ch),
+		CTX_REGISTER(dw, msi_stop.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_stop.msb, dir, ch),
+		CTX_REGISTER(dw, msi_watermark.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_watermark.msb, dir, ch),
+		CTX_REGISTER(dw, msi_abort.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_abort.msb, dir, ch),
+		CTX_REGISTER(dw, msi_msgdata, dir, ch),
+	};
+	int nr_entries = ARRAY_SIZE(debugfs_regs);
+
+	dw_hdma_debugfs_create_x32(dw, debugfs_regs, nr_entries, dent);
+}
+
+static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
+{
+	struct dentry *regs_dent, *ch_dent;
+	char name[32];
+	int i;
+
+	regs_dent = debugfs_create_dir(WRITE_STR, dent);
+
+	for (i = 0; i < dw->wr_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_hdma_debugfs_regs_ch(dw, EDMA_DIR_WRITE, i, ch_dent);
+	}
+}
+
+static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent)
+{
+	struct dentry *regs_dent, *ch_dent;
+	char name[32];
+	int i;
+
+	regs_dent = debugfs_create_dir(READ_STR, dent);
+
+	for (i = 0; i < dw->rd_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_hdma_debugfs_regs_ch(dw, EDMA_DIR_READ, i, ch_dent);
+	}
+}
+
+static void dw_hdma_debugfs_regs(struct dw_edma *dw)
+{
+	struct dentry *regs_dent;
+
+	regs_dent = debugfs_create_dir(REGISTERS_STR, dw->dma.dbg_dev_root);
+
+	dw_hdma_debugfs_regs_wr(dw, regs_dent);
+	dw_hdma_debugfs_regs_rd(dw, regs_dent);
+}
+
+void dw_hdma_v0_debugfs_on(struct dw_edma *dw)
+{
+	if (!debugfs_initialized())
+		return;
+
+	debugfs_create_u32("mf", 0444, dw->dma.dbg_dev_root, &dw->chip->mf);
+	debugfs_create_u16("wr_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->wr_ch_cnt);
+	debugfs_create_u16("rd_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->rd_ch_cnt);
+
+	dw_hdma_debugfs_regs(dw);
+}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h
new file mode 100644
index 000000000..e6842c837
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 debugfs
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_DEBUG_FS_H
+#define _DW_HDMA_V0_DEBUG_FS_H
+
+#include <linux/dma/edma.h>
+
+#ifdef CONFIG_DEBUG_FS
+void dw_hdma_v0_debugfs_on(struct dw_edma *dw);
+#else
+static inline void dw_hdma_v0_debugfs_on(struct dw_edma *dw)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _DW_HDMA_V0_DEBUG_FS_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
new file mode 100644
index 000000000..2124c162a
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 reg
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_REGS_H
+#define _DW_HDMA_V0_REGS_H
+
+#include <linux/dmaengine.h>
+
+#define HDMA_V0_MAX_NR_CH			64
+#define HDMA_V0_CH_EN				BIT(0)
+#define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
+#define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
+#define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
+#define HDMA_V0_REMOTE_STOP_INT_EN		BIT(3)
+#define HDMA_V0_ABORT_INT_MASK			BIT(2)
+#define HDMA_V0_STOP_INT_MASK			BIT(0)
+#define HDMA_V0_LINKLIST_EN			BIT(0)
+#define HDMA_V0_CONSUMER_CYCLE_STAT		BIT(1)
+#define HDMA_V0_CONSUMER_CYCLE_BIT		BIT(0)
+#define HDMA_V0_DOORBELL_START			BIT(0)
+#define HDMA_V0_CH_STATUS_MASK			GENMASK(1, 0)
+#define HDMA_V0_FUNC_NUM_PF_MASK		GENMASK(7, 0)
+
+struct dw_hdma_v0_ch_regs {
+	u32 ch_en;				/* 0x0000 */
+	u32 doorbell;				/* 0x0004 */
+	u32 prefetch;				/* 0x0008 */
+	u32 handshake;				/* 0x000c */
+	union {
+		u64 reg;			/* 0x0010..0x0014 */
+		struct {
+			u32 lsb;		/* 0x0010 */
+			u32 msb;		/* 0x0014 */
+		};
+	} llp;
+	u32 cycle_sync;				/* 0x0018 */
+	u32 transfer_size;			/* 0x001c */
+	union {
+		u64 reg;			/* 0x0020..0x0024 */
+		struct {
+			u32 lsb;		/* 0x0020 */
+			u32 msb;		/* 0x0024 */
+		};
+	} sar;
+	union {
+		u64 reg;			/* 0x0028..0x002c */
+		struct {
+			u32 lsb;		/* 0x0028 */
+			u32 msb;		/* 0x002c */
+		};
+	} dar;
+	u32 watermark_en;			/* 0x0030 */
+	u32 control1;				/* 0x0034 */
+	u32 func_num;				/* 0x0038 */
+	u32 qos;				/* 0x003c */
+	u32 padding_1[16];			/* 0x0040..0x007c */
+	u32 ch_stat;				/* 0x0080 */
+	u32 int_stat;				/* 0x0084 */
+	u32 int_setup;				/* 0x0088 */
+	u32 int_clear;				/* 0x008c */
+	union {
+		u64 reg;			/* 0x0090..0x0094 */
+		struct {
+			u32 lsb;		/* 0x0090 */
+			u32 msb;		/* 0x0094 */
+		};
+	} msi_stop;
+	union {
+		u64 reg;			/* 0x0098..0x009c */
+		struct {
+			u32 lsb;		/* 0x0098 */
+			u32 msb;		/* 0x009c */
+		};
+	} msi_watermark;
+	union {
+		u64 reg;			/* 0x00a0..0x00a4 */
+		struct {
+			u32 lsb;		/* 0x00a0 */
+			u32 msb;		/* 0x00a4 */
+		};
+	} msi_abort;
+	u32 msi_msgdata;			/* 0x00a8 */
+	u32 padding_2[21];			/* 0x00ac..0x00fc */
+} __packed;
+
+struct dw_hdma_v0_ch {
+	struct dw_hdma_v0_ch_regs wr;		/* 0x0000 */
+	struct dw_hdma_v0_ch_regs rd;		/* 0x0100 */
+} __packed;
+
+struct dw_hdma_v0_regs {
+	struct dw_hdma_v0_ch ch[HDMA_V0_MAX_NR_CH];	/* 0x0000..0x0fa8 */
+} __packed;
+
+struct dw_hdma_v0_lli {
+	u32 control;
+	u32 transfer_size;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} sar;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} dar;
+} __packed;
+
+struct dw_hdma_v0_llp {
+	u32 control;
+	u32 reserved;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} llp;
+} __packed;
+
+#endif /* _DW_HDMA_V0_REGS_H */