1 files changed, 238 insertions, 222 deletions

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 468d1097a1ec..8e5f7defa6b6 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -9,35 +9,35 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/pm_runtime.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 device *dchan2dev(struct dma_chan *dchan)
+struct dw_edma_desc *vd2dw_edma_desc(struct virt_dma_desc *vd)
 {
-	return &dchan->dev->device;
+	return container_of(vd, struct dw_edma_desc, vd);
 }
 
 static inline
-struct device *chan2dev(struct dw_edma_chan *chan)
+u64 dw_edma_get_pci_address(struct dw_edma_chan *chan, phys_addr_t cpu_addr)
 {
-	return &chan->vc.chan.dev->device;
-}
+	struct dw_edma_chip *chip = chan->dw->chip;
 
-static inline
-struct dw_edma_desc *vd2dw_edma_desc(struct virt_dma_desc *vd)
-{
-	return container_of(vd, struct dw_edma_desc, vd);
+	if (chip->ops->pci_address)
+		return chip->ops->pci_address(chip->dev, cpu_addr);
+
+	return cpu_addr;
 }
 
 static struct dw_edma_burst *dw_edma_alloc_burst(struct dw_edma_chunk *chunk)
@@ -64,8 +64,8 @@ static struct dw_edma_burst *dw_edma_alloc_burst(struct dw_edma_chunk *chunk)
 
 static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 {
+	struct dw_edma_chip *chip = desc->chan->dw->chip;
 	struct dw_edma_chan *chan = desc->chan;
-	struct dw_edma *dw = chan->chip->dw;
 	struct dw_edma_chunk *chunk;
 
 	chunk = kzalloc(sizeof(*chunk), GFP_NOWAIT);
@@ -82,11 +82,11 @@ static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 	 */
 	chunk->cb = !(desc->chunks_alloc % 2);
 	if (chan->dir == EDMA_DIR_WRITE) {
-		chunk->ll_region.paddr = dw->ll_region_wr[chan->id].paddr;
-		chunk->ll_region.vaddr = dw->ll_region_wr[chan->id].vaddr;
+		chunk->ll_region.paddr = chip->ll_region_wr[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->ll_region_wr[chan->id].vaddr;
 	} else {
-		chunk->ll_region.paddr = dw->ll_region_rd[chan->id].paddr;
-		chunk->ll_region.vaddr = dw->ll_region_rd[chan->id].vaddr;
+		chunk->ll_region.paddr = chip->ll_region_rd[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->ll_region_rd[chan->id].vaddr;
 	}
 
 	if (desc->chunk) {
@@ -171,31 +171,52 @@ static void vchan_free_desc(struct virt_dma_desc *vdesc)
 	dw_edma_free_desc(vd2dw_edma_desc(vdesc));
 }
 
-static void dw_edma_start_transfer(struct dw_edma_chan *chan)
+static int dw_edma_start_transfer(struct dw_edma_chan *chan)
 {
+	struct dw_edma *dw = chan->dw;
 	struct dw_edma_chunk *child;
 	struct dw_edma_desc *desc;
 	struct virt_dma_desc *vd;
 
 	vd = vchan_next_desc(&chan->vc);
 	if (!vd)
-		return;
+		return 0;
 
 	desc = vd2dw_edma_desc(vd);
 	if (!desc)
-		return;
+		return 0;
 
 	child = list_first_entry_or_null(&desc->chunk->list,
 					 struct dw_edma_chunk, list);
 	if (!child)
-		return;
+		return 0;
 
-	dw_edma_v0_core_start(child, !desc->xfer_sz);
+	dw_edma_core_start(dw, child, !desc->xfer_sz);
 	desc->xfer_sz += child->ll_region.sz;
 	dw_edma_free_burst(child);
 	list_del(&child->list);
 	kfree(child);
 	desc->chunks_alloc--;
+
+	return 1;
+}
+
+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 int dw_edma_device_config(struct dma_chan *dchan,
@@ -257,7 +278,7 @@ static int dw_edma_device_terminate_all(struct dma_chan *dchan)
 		chan->configured = false;
 	} else if (chan->status == EDMA_ST_IDLE) {
 		chan->configured = false;
-	} else if (dw_edma_v0_core_ch_status(chan) == DMA_COMPLETE) {
+	} 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
@@ -278,9 +299,12 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan)
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
 	unsigned long flags;
 
+	if (!chan->configured)
+		return;
+
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	if (chan->configured && chan->request == EDMA_REQ_NONE &&
-	    chan->status == EDMA_ST_IDLE && vchan_issue_pending(&chan->vc)) {
+	if (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);
 	}
@@ -328,32 +352,52 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
 	enum dma_transfer_direction dir = xfer->direction;
-	phys_addr_t src_addr, dst_addr;
 	struct scatterlist *sg = NULL;
 	struct dw_edma_chunk *chunk;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
+	u64 src_addr, dst_addr;
+	size_t fsz = 0;
 	u32 cnt = 0;
 	int i;
 
 	if (!chan->configured)
 		return NULL;
 
-	switch (chan->config.direction) {
-	case DMA_DEV_TO_MEM: /* local DMA */
-		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ)
-			break;
-		return NULL;
-	case DMA_MEM_TO_DEV: /* local DMA */
-		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE)
-			break;
-		return NULL;
-	default: /* remote DMA */
-		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_READ)
-			break;
-		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_WRITE)
-			break;
-		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) {
@@ -363,9 +407,9 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		if (xfer->xfer.sg.len < 1)
 			return NULL;
 	} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
-		if (!xfer->xfer.il->numf)
+		if (!xfer->xfer.il->numf || xfer->xfer.il->frame_size < 1)
 			return NULL;
-		if (xfer->xfer.il->numf > 0 && xfer->xfer.il->frame_size > 0)
+		if (!xfer->xfer.il->src_inc || !xfer->xfer.il->dst_inc)
 			return NULL;
 	} else {
 		return NULL;
@@ -387,16 +431,19 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		dst_addr = chan->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) {
-		if (xfer->xfer.il->numf > 0)
-			cnt = xfer->xfer.il->numf;
-		else
-			cnt = xfer->xfer.il->frame_size;
+		cnt = xfer->xfer.il->numf * xfer->xfer.il->frame_size;
+		fsz = xfer->xfer.il->frame_size;
 	}
 
 	for (i = 0; i < cnt; i++) {
@@ -418,12 +465,12 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		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].size;
+			burst->sz = xfer->xfer.il->sgl[i % fsz].size;
 
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
-		if (chan->dir == EDMA_DIR_WRITE) {
+		if (dir == DMA_DEV_TO_MEM) {
 			burst->sar = src_addr;
 			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->dar = xfer->xfer.cyclic.paddr;
@@ -437,6 +484,8 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * 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;
@@ -452,25 +501,24 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 				 * 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 &&
-			   xfer->xfer.il->frame_size > 0) {
+		} else if (xfer->type == EDMA_XFER_INTERLEAVED) {
 			struct dma_interleaved_template *il = xfer->xfer.il;
-			struct data_chunk *dc = &il->sgl[i];
+			struct data_chunk *dc = &il->sgl[i % fsz];
 
-			if (il->src_sgl) {
-				src_addr += burst->sz;
+			src_addr += burst->sz;
+			if (il->src_sgl)
 				src_addr += dmaengine_get_src_icg(il, dc);
-			}
 
-			if (il->dst_sgl) {
-				dst_addr += burst->sz;
+			dst_addr += burst->sz;
+			if (il->dst_sgl)
 				dst_addr += dmaengine_get_dst_icg(il, dc);
-			}
 		}
 	}
 
@@ -536,28 +584,47 @@ dw_edma_device_prep_interleaved_dma(struct dma_chan *dchan,
 	return dw_edma_device_transfer(&xfer);
 }
 
+static void dw_hdma_set_callback_result(struct virt_dma_desc *vd,
+					enum dmaengine_tx_result result)
+{
+	u32 residue = 0;
+	struct dw_edma_desc *desc;
+	struct dmaengine_result *res;
+
+	if (!vd->tx.callback_result)
+		return;
+
+	desc = vd2dw_edma_desc(vd);
+	if (desc)
+		residue = desc->alloc_sz - desc->xfer_sz;
+
+	res = &vd->tx_result;
+	res->result = result;
+	res->residue = residue;
+}
+
 static void dw_edma_done_interrupt(struct dw_edma_chan *chan)
 {
 	struct dw_edma_desc *desc;
 	struct virt_dma_desc *vd;
 	unsigned long flags;
 
-	dw_edma_v0_core_clear_done_int(chan);
-
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vd = vchan_next_desc(&chan->vc);
 	if (vd) {
 		switch (chan->request) {
 		case EDMA_REQ_NONE:
 			desc = vd2dw_edma_desc(vd);
-			if (desc->chunks_alloc) {
-				chan->status = EDMA_ST_BUSY;
-				dw_edma_start_transfer(chan);
-			} else {
+			if (!desc->chunks_alloc) {
+				dw_hdma_set_callback_result(vd,
+							    DMA_TRANS_NOERROR);
 				list_del(&vd->node);
 				vchan_cookie_complete(vd);
-				chan->status = EDMA_ST_IDLE;
 			}
+
+			/* 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:
@@ -584,11 +651,10 @@ static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
 	struct virt_dma_desc *vd;
 	unsigned long flags;
 
-	dw_edma_v0_core_clear_abort_int(chan);
-
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vd = vchan_next_desc(&chan->vc);
 	if (vd) {
+		dw_hdma_set_callback_result(vd, DMA_TRANS_ABORTED);
 		list_del(&vd->node);
 		vchan_cookie_complete(vd);
 	}
@@ -597,63 +663,32 @@ static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
 	chan->status = EDMA_ST_IDLE;
 }
 
-static irqreturn_t dw_edma_interrupt(int irq, void *data, bool write)
+static inline irqreturn_t dw_edma_interrupt_write(int irq, void *data)
 {
 	struct dw_edma_irq *dw_irq = data;
-	struct dw_edma *dw = dw_irq->dw;
-	unsigned long total, pos, val;
-	unsigned long off;
-	u32 mask;
-
-	if (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;
-	}
-
-	val = dw_edma_v0_core_status_done_int(dw, write ?
-							  EDMA_DIR_WRITE :
-							  EDMA_DIR_READ);
-	val &= mask;
-	for_each_set_bit(pos, &val, total) {
-		struct dw_edma_chan *chan = &dw->chan[pos + off];
-
-		dw_edma_done_interrupt(chan);
-	}
-
-	val = dw_edma_v0_core_status_abort_int(dw, write ?
-							   EDMA_DIR_WRITE :
-							   EDMA_DIR_READ);
-	val &= mask;
-	for_each_set_bit(pos, &val, total) {
-		struct dw_edma_chan *chan = &dw->chan[pos + off];
-
-		dw_edma_abort_interrupt(chan);
-	}
 
-	return IRQ_HANDLED;
-}
-
-static inline irqreturn_t dw_edma_interrupt_write(int irq, void *data)
-{
-	return dw_edma_interrupt(irq, data, true);
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_WRITE,
+				       dw_edma_done_interrupt,
+				       dw_edma_abort_interrupt);
 }
 
 static inline irqreturn_t dw_edma_interrupt_read(int irq, void *data)
 {
-	return dw_edma_interrupt(irq, data, false);
+	struct dw_edma_irq *dw_irq = data;
+
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_READ,
+				       dw_edma_done_interrupt,
+				       dw_edma_abort_interrupt);
 }
 
 static irqreturn_t dw_edma_interrupt_common(int irq, void *data)
 {
-	dw_edma_interrupt(irq, data, true);
-	dw_edma_interrupt(irq, data, false);
+	irqreturn_t ret = IRQ_NONE;
 
-	return IRQ_HANDLED;
+	ret |= dw_edma_interrupt_write(irq, data);
+	ret |= dw_edma_interrupt_read(irq, data);
+
+	return ret;
 }
 
 static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
@@ -663,15 +698,12 @@ static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
 	if (chan->status != EDMA_ST_IDLE)
 		return -EBUSY;
 
-	pm_runtime_get(chan->chip->dev);
-
 	return 0;
 }
 
 static void dw_edma_free_chan_resources(struct dma_chan *dchan)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(5000);
-	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
 	int ret;
 
 	while (time_before(jiffies, timeout)) {
@@ -684,98 +716,81 @@ static void dw_edma_free_chan_resources(struct dma_chan *dchan)
 
 		cpu_relax();
 	}
-
-	pm_runtime_put(chan->chip->dev);
 }
 
-static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
-				 u32 wr_alloc, u32 rd_alloc)
+static int dw_edma_channel_setup(struct dw_edma *dw, u32 wr_alloc, u32 rd_alloc)
 {
-	struct dw_edma_region *dt_region;
+	struct dw_edma_chip *chip = dw->chip;
 	struct device *dev = chip->dev;
-	struct dw_edma *dw = chip->dw;
 	struct dw_edma_chan *chan;
 	struct dw_edma_irq *irq;
 	struct dma_device *dma;
-	u32 alloc, off_alloc;
-	u32 i, j, cnt;
-	int err = 0;
+	u32 i, ch_cnt;
 	u32 pos;
 
-	if (write) {
-		i = 0;
-		cnt = dw->wr_ch_cnt;
-		dma = &dw->wr_edma;
-		alloc = wr_alloc;
-		off_alloc = 0;
-	} else {
-		i = dw->wr_ch_cnt;
-		cnt = dw->rd_ch_cnt;
-		dma = &dw->rd_edma;
-		alloc = rd_alloc;
-		off_alloc = wr_alloc;
-	}
+	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
+	dma = &dw->dma;
 
 	INIT_LIST_HEAD(&dma->channels);
-	for (j = 0; (alloc || dw->nr_irqs == 1) && j < cnt; j++, i++) {
+
+	for (i = 0; i < ch_cnt; i++) {
 		chan = &dw->chan[i];
 
-		dt_region = devm_kzalloc(dev, sizeof(*dt_region), GFP_KERNEL);
-		if (!dt_region)
-			return -ENOMEM;
+		chan->dw = dw;
 
-		chan->vc.chan.private = dt_region;
+		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->chip = chip;
-		chan->id = j;
-		chan->dir = write ? EDMA_DIR_WRITE : EDMA_DIR_READ;
 		chan->configured = false;
 		chan->request = EDMA_REQ_NONE;
 		chan->status = EDMA_ST_IDLE;
 
-		if (write)
-			chan->ll_max = (dw->ll_region_wr[j].sz / EDMA_LL_SZ);
+		if (chan->dir == EDMA_DIR_WRITE)
+			chan->ll_max = (chip->ll_region_wr[chan->id].sz / EDMA_LL_SZ);
 		else
-			chan->ll_max = (dw->ll_region_rd[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_rd[chan->id].sz / EDMA_LL_SZ);
 		chan->ll_max -= 1;
 
 		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
-			 write ? "write" : "read", j, chan->ll_max);
+			 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 = off_alloc + (j % alloc);
+			pos = wr_alloc + chan->id % rd_alloc;
 
 		irq = &dw->irq[pos];
 
-		if (write)
-			irq->wr_mask |= BIT(j);
+		if (chan->dir == EDMA_DIR_WRITE)
+			irq->wr_mask |= BIT(chan->id);
 		else
-			irq->rd_mask |= BIT(j);
+			irq->rd_mask |= BIT(chan->id);
 
 		irq->dw = dw;
 		memcpy(&chan->msi, &irq->msi, sizeof(chan->msi));
 
 		dev_vdbg(dev, "MSI:\t\tChannel %s[%u] addr=0x%.8x%.8x, data=0x%.8x\n",
-			 write ? "write" : "read", j,
+			 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;
-		vchan_init(&chan->vc, dma);
+		chan->vc.chan.private = chan->dir == EDMA_DIR_WRITE ?
+					&dw->chip->dt_region_wr[chan->id] :
+					&dw->chip->dt_region_rd[chan->id];
 
-		if (write) {
-			dt_region->paddr = dw->dt_region_wr[j].paddr;
-			dt_region->vaddr = dw->dt_region_wr[j].vaddr;
-			dt_region->sz = dw->dt_region_wr[j].sz;
-		} else {
-			dt_region->paddr = dw->dt_region_rd[j].paddr;
-			dt_region->vaddr = dw->dt_region_rd[j].vaddr;
-			dt_region->sz = dw->dt_region_rd[j].sz;
-		}
+		vchan_init(&chan->vc, dma);
 
-		dw_edma_v0_core_device_config(chan);
+		dw_edma_core_ch_config(chan);
 	}
 
 	/* Set DMA channel capabilities */
@@ -784,16 +799,16 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	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(write ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV);
+	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;
-	dma->chancnt = cnt;
 
 	/* 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;
@@ -807,9 +822,7 @@ static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
 	dma_set_max_seg_size(dma->dev, U32_MAX);
 
 	/* Register DMA device */
-	err = dma_async_device_register(dma);
-
-	return err;
+	return dma_async_device_register(dma);
 }
 
 static inline void dw_edma_dec_irq_alloc(int *nr_irqs, u32 *alloc, u16 cnt)
@@ -826,11 +839,11 @@ static inline void dw_edma_add_irq_mask(u32 *mask, u32 alloc, u16 cnt)
 		(*mask)++;
 }
 
-static int dw_edma_irq_request(struct dw_edma_chip *chip,
+static int dw_edma_irq_request(struct dw_edma *dw,
 			       u32 *wr_alloc, u32 *rd_alloc)
 {
-	struct device *dev = chip->dev;
-	struct dw_edma *dw = chip->dw;
+	struct dw_edma_chip *chip = dw->chip;
+	struct device *dev = dw->chip->dev;
 	u32 wr_mask = 1;
 	u32 rd_mask = 1;
 	int i, err = 0;
@@ -839,12 +852,16 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 
 	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
 
-	if (dw->nr_irqs < 1)
+	if (chip->nr_irqs < 1 || !chip->ops->irq_vector)
 		return -EINVAL;
 
-	if (dw->nr_irqs == 1) {
+	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 = dw->ops->irq_vector(dev, 0);
+		irq = chip->ops->irq_vector(dev, 0);
 		err = request_irq(irq, dw_edma_interrupt_common,
 				  IRQF_SHARED, dw->name, &dw->irq[0]);
 		if (err) {
@@ -854,9 +871,11 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 
 		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 = dw->nr_irqs;
+		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);
@@ -867,17 +886,15 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 		dw_edma_add_irq_mask(&rd_mask, *rd_alloc, dw->rd_ch_cnt);
 
 		for (i = 0; i < (*wr_alloc + *rd_alloc); i++) {
-			irq = dw->ops->irq_vector(dev, i);
+			irq = chip->ops->irq_vector(dev, i);
 			err = request_irq(irq,
 					  i < *wr_alloc ?
 						dw_edma_interrupt_write :
 						dw_edma_interrupt_read,
 					  IRQF_SHARED, dw->name,
 					  &dw->irq[i]);
-			if (err) {
-				dw->nr_irqs = i;
-				return err;
-			}
+			if (err)
+				goto err_irq_free;
 
 			if (irq_get_msi_desc(irq))
 				get_cached_msi_msg(irq, &dw->irq[i].msi);
@@ -886,6 +903,14 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 		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;
 }
 
@@ -901,21 +926,28 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 		return -EINVAL;
 
 	dev = chip->dev;
-	if (!dev)
+	if (!dev || !chip->ops)
 		return -EINVAL;
 
-	dw = chip->dw;
-	if (!dw || !dw->irq || !dw->ops || !dw->ops->irq_vector)
-		return -EINVAL;
+	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);
+	else
+		dw_edma_v0_core_register(dw);
 
 	raw_spin_lock_init(&dw->lock);
 
-	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt,
-			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_WRITE));
+	dw->wr_ch_cnt = min_t(u16, chip->ll_wr_cnt,
+			      dw_edma_core_ch_count(dw, EDMA_DIR_WRITE));
 	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt, EDMA_MAX_WR_CH);
 
-	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt,
-			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_READ));
+	dw->rd_ch_cnt = min_t(u16, chip->ll_rd_cnt,
+			      dw_edma_core_ch_count(dw, EDMA_DIR_READ));
 	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt, EDMA_MAX_RD_CH);
 
 	if (!dw->wr_ch_cnt && !dw->rd_ch_cnt)
@@ -930,39 +962,32 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 	if (!dw->chan)
 		return -ENOMEM;
 
-	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%d", chip->id);
+	snprintf(dw->name, sizeof(dw->name), "dw-edma-core:%s",
+		 dev_name(chip->dev));
 
 	/* Disable eDMA, only to establish the ideal initial conditions */
-	dw_edma_v0_core_off(dw);
+	dw_edma_core_off(dw);
 
 	/* Request IRQs */
-	err = dw_edma_irq_request(chip, &wr_alloc, &rd_alloc);
+	err = dw_edma_irq_request(dw, &wr_alloc, &rd_alloc);
 	if (err)
 		return err;
 
-	/* Setup write channels */
-	err = dw_edma_channel_setup(chip, true, wr_alloc, rd_alloc);
+	/* Setup write/read channels */
+	err = dw_edma_channel_setup(dw, wr_alloc, rd_alloc);
 	if (err)
 		goto err_irq_free;
 
-	/* Setup read channels */
-	err = dw_edma_channel_setup(chip, false, wr_alloc, rd_alloc);
-	if (err)
-		goto err_irq_free;
-
-	/* Power management */
-	pm_runtime_enable(dev);
-
 	/* Turn debugfs on */
-	dw_edma_v0_core_debugfs_on(chip);
+	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(dw->ops->irq_vector(dev, i), &dw->irq[i]);
-
-	dw->nr_irqs = 0;
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	return err;
 }
@@ -975,34 +1000,25 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	struct dw_edma *dw = chip->dw;
 	int i;
 
+	/* Skip removal if no private data found */
+	if (!dw)
+		return -ENODEV;
+
 	/* Disable eDMA */
-	dw_edma_v0_core_off(dw);
+	dw_edma_core_off(dw);
 
 	/* Free irqs */
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
-
-	/* Power management */
-	pm_runtime_disable(dev);
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	/* Deregister eDMA device */
-	dma_async_device_unregister(&dw->wr_edma);
-	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
+	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);
 	}
 
-	dma_async_device_unregister(&dw->rd_edma);
-	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
-				 vc.chan.device_node) {
-		tasklet_kill(&chan->vc.task);
-		list_del(&chan->vc.chan.device_node);
-	}
-
-	/* Turn debugfs off */
-	dw_edma_v0_core_debugfs_off(chip);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_edma_remove);