1 files changed, 576 insertions, 900 deletions

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index eea479c12173..dd75f97a33b3 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1,17 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Core driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007-2008 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
  * Copyright (C) 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
-#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
@@ -20,9 +16,11 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 
 #include "../dmaengine.h"
 #include "internal.h"
@@ -32,46 +30,14 @@
  * (DW_ahb_dmac) which is used with various AMBA 2.0 systems (not all
  * of which use ARM any more).  See the "Databook" from Synopsys for
  * information beyond what licensees probably provide.
- *
- * The driver has currently been tested only with the Atmel AT32AP7000,
- * which does not support descriptor writeback.
  */
 
-static inline void dwc_set_masters(struct dw_dma_chan *dwc)
-{
-	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
-	unsigned char mmax = dw->nr_masters - 1;
-
-	if (dwc->request_line == ~0) {
-		dwc->src_master = min_t(unsigned char, mmax, dwc_get_sms(dws));
-		dwc->dst_master = min_t(unsigned char, mmax, dwc_get_dms(dws));
-	}
-}
-
-#define DWC_DEFAULT_CTLLO(_chan) ({				\
-		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
-		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
-		bool _is_slave = is_slave_direction(_dwc->direction);	\
-		u8 _smsize = _is_slave ? _sconfig->src_maxburst :	\
-			DW_DMA_MSIZE_16;			\
-		u8 _dmsize = _is_slave ? _sconfig->dst_maxburst :	\
-			DW_DMA_MSIZE_16;			\
-								\
-		(DWC_CTLL_DST_MSIZE(_dmsize)			\
-		 | DWC_CTLL_SRC_MSIZE(_smsize)			\
-		 | DWC_CTLL_LLP_D_EN				\
-		 | DWC_CTLL_LLP_S_EN				\
-		 | DWC_CTLL_DMS(_dwc->dst_master)		\
-		 | DWC_CTLL_SMS(_dwc->src_master));		\
-	})
-
-/*
- * Number of descriptors to allocate for each channel. This should be
- * made configurable somehow; preferably, the clients (at least the
- * ones using slave transfers) should be able to give us a hint.
- */
-#define NR_DESCS_PER_CHANNEL	64
+/* The set of bus widths supported by the DMA controller */
+#define DW_DMA_BUSWIDTHS			  \
+	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED)	| \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE)		| \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES)		| \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
 
 /*----------------------------------------------------------------------*/
 
@@ -79,116 +45,86 @@ static struct device *chan2dev(struct dma_chan *chan)
 {
 	return &chan->dev->device;
 }
-static struct device *chan2parent(struct dma_chan *chan)
-{
-	return chan->dev->device.parent;
-}
 
 static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 {
 	return to_dw_desc(dwc->active_list.next);
 }
 
-static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
+static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 {
-	struct dw_desc *desc, *_desc;
-	struct dw_desc *ret = NULL;
-	unsigned int i = 0;
-	unsigned long flags;
+	struct dw_desc		*desc = txd_to_dw_desc(tx);
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(tx->chan);
+	dma_cookie_t		cookie;
+	unsigned long		flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	list_for_each_entry_safe(desc, _desc, &dwc->free_list, desc_node) {
-		i++;
-		if (async_tx_test_ack(&desc->txd)) {
-			list_del(&desc->desc_node);
-			ret = desc;
-			break;
-		}
-		dev_dbg(chan2dev(&dwc->chan), "desc %p not ACKed\n", desc);
-	}
-	spin_unlock_irqrestore(&dwc->lock, flags);
+	cookie = dma_cookie_assign(tx);
+
+	/*
+	 * REVISIT: We should attempt to chain as many descriptors as
+	 * possible, perhaps even appending to those already submitted
+	 * for DMA. But this is hard to do in a race-free manner.
+	 */
 
-	dev_vdbg(chan2dev(&dwc->chan), "scanned %u descriptors on freelist\n", i);
+	list_add_tail(&desc->desc_node, &dwc->queue);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+	dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n",
+		 __func__, desc->txd.cookie);
 
-	return ret;
+	return cookie;
 }
 
-/*
- * Move a descriptor, including any children, to the free list.
- * `desc' must not be on any lists.
- */
-static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
+static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 {
-	unsigned long flags;
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	struct dw_desc *desc;
+	dma_addr_t phys;
 
-	if (desc) {
-		struct dw_desc *child;
+	desc = dma_pool_zalloc(dw->desc_pool, GFP_ATOMIC, &phys);
+	if (!desc)
+		return NULL;
 
-		spin_lock_irqsave(&dwc->lock, flags);
-		list_for_each_entry(child, &desc->tx_list, desc_node)
-			dev_vdbg(chan2dev(&dwc->chan),
-					"moving child desc %p to freelist\n",
-					child);
-		list_splice_init(&desc->tx_list, &dwc->free_list);
-		dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
-		list_add(&desc->desc_node, &dwc->free_list);
-		spin_unlock_irqrestore(&dwc->lock, flags);
-	}
+	dwc->descs_allocated++;
+	INIT_LIST_HEAD(&desc->tx_list);
+	dma_async_tx_descriptor_init(&desc->txd, &dwc->chan);
+	desc->txd.tx_submit = dwc_tx_submit;
+	desc->txd.flags = DMA_CTRL_ACK;
+	desc->txd.phys = phys;
+	return desc;
 }
 
-static void dwc_initialize(struct dw_dma_chan *dwc)
+static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
-	u32 cfghi = DWC_CFGH_FIFO_MODE;
-	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
+	struct dw_desc *child, *_next;
 
-	if (dwc->initialized == true)
+	if (unlikely(!desc))
 		return;
 
-	if (dws) {
-		/*
-		 * We need controller-specific data to set up slave
-		 * transfers.
-		 */
-		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
-
-		cfghi = dws->cfg_hi;
-		cfglo |= dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
-	} else {
-		if (dwc->direction == DMA_MEM_TO_DEV)
-			cfghi = DWC_CFGH_DST_PER(dwc->request_line);
-		else if (dwc->direction == DMA_DEV_TO_MEM)
-			cfghi = DWC_CFGH_SRC_PER(dwc->request_line);
+	list_for_each_entry_safe(child, _next, &desc->tx_list, desc_node) {
+		list_del(&child->desc_node);
+		dma_pool_free(dw->desc_pool, child, child->txd.phys);
+		dwc->descs_allocated--;
 	}
 
-	channel_writel(dwc, CFG_LO, cfglo);
-	channel_writel(dwc, CFG_HI, cfghi);
+	dma_pool_free(dw->desc_pool, desc, desc->txd.phys);
+	dwc->descs_allocated--;
+}
+
+static void dwc_initialize(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	dw->initialize_chan(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
-
-	dwc->initialized = true;
 }
 
 /*----------------------------------------------------------------------*/
 
-static inline unsigned int dwc_fast_fls(unsigned long long v)
-{
-	/*
-	 * We can be a lot more clever here, but this should take care
-	 * of the most common optimization.
-	 */
-	if (!(v & 7))
-		return 3;
-	else if (!(v & 3))
-		return 2;
-	else if (!(v & 1))
-		return 1;
-	return 0;
-}
-
 static inline void dwc_dump_chan_regs(struct dw_dma_chan *dwc)
 {
 	dev_err(chan2dev(&dwc->chan),
@@ -216,14 +152,16 @@ static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
 	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
 	u32		ctllo;
 
-	/* Software emulation of LLP mode relies on interrupts to continue
-	 * multi block transfer. */
-	ctllo = desc->lli.ctllo | DWC_CTLL_INT_EN;
+	/*
+	 * Software emulation of LLP mode relies on interrupts to continue
+	 * multi block transfer.
+	 */
+	ctllo = lli_read(desc, ctllo) | DWC_CTLL_INT_EN;
 
-	channel_writel(dwc, SAR, desc->lli.sar);
-	channel_writel(dwc, DAR, desc->lli.dar);
+	channel_writel(dwc, SAR, lli_read(desc, sar));
+	channel_writel(dwc, DAR, lli_read(desc, dar));
 	channel_writel(dwc, CTL_LO, ctllo);
-	channel_writel(dwc, CTL_HI, desc->lli.ctlhi);
+	channel_writel(dwc, CTL_HI, lli_read(desc, ctlhi));
 	channel_set_bit(dw, CH_EN, dwc->mask);
 
 	/* Move pointer to next descriptor */
@@ -234,12 +172,14 @@ static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
 static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 {
 	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+	u8		lms = DWC_LLP_LMS(dwc->dws.m_master);
 	unsigned long	was_soft_llp;
 
 	/* ASSERT:  channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
 		dev_err(chan2dev(&dwc->chan),
-			"BUG: Attempted to start non-idle channel\n");
+			"%s: BUG: Attempted to start non-idle channel\n",
+			__func__);
 		dwc_dump_chan_regs(dwc);
 
 		/* The tasklet will hopefully advance the queue... */
@@ -251,14 +191,13 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 						&dwc->flags);
 		if (was_soft_llp) {
 			dev_err(chan2dev(&dwc->chan),
-				"BUG: Attempted to start new LLP transfer "
-				"inside ongoing one\n");
+				"BUG: Attempted to start new LLP transfer inside ongoing one\n");
 			return;
 		}
 
 		dwc_initialize(dwc);
 
-		dwc->residue = first->total_len;
+		first->residue = first->total_len;
 		dwc->tx_node_active = &first->tx_list;
 
 		/* Submit first block */
@@ -269,66 +208,53 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 
 	dwc_initialize(dwc);
 
-	channel_writel(dwc, LLP, first->txd.phys);
-	channel_writel(dwc, CTL_LO,
-			DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	channel_writel(dwc, LLP, first->txd.phys | lms);
+	channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
 	channel_writel(dwc, CTL_HI, 0);
 	channel_set_bit(dw, CH_EN, dwc->mask);
 }
 
+static void dwc_dostart_first_queued(struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc;
+
+	if (list_empty(&dwc->queue))
+		return;
+
+	list_move(dwc->queue.next, &dwc->active_list);
+	desc = dwc_first_active(dwc);
+	dev_vdbg(chan2dev(&dwc->chan), "%s: started %u\n", __func__, desc->txd.cookie);
+	dwc_dostart(dwc, desc);
+}
+
 /*----------------------------------------------------------------------*/
 
 static void
 dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 		bool callback_required)
 {
-	dma_async_tx_callback		callback = NULL;
-	void				*param = NULL;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 	struct dw_desc			*child;
 	unsigned long			flags;
+	struct dmaengine_desc_callback	cb;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
 	spin_lock_irqsave(&dwc->lock, flags);
 	dma_cookie_complete(txd);
-	if (callback_required) {
-		callback = txd->callback;
-		param = txd->callback_param;
-	}
+	if (callback_required)
+		dmaengine_desc_get_callback(txd, &cb);
+	else
+		memset(&cb, 0, sizeof(cb));
 
 	/* async_tx_ack */
 	list_for_each_entry(child, &desc->tx_list, desc_node)
 		async_tx_ack(&child->txd);
 	async_tx_ack(&desc->txd);
-
-	list_splice_init(&desc->tx_list, &dwc->free_list);
-	list_move(&desc->desc_node, &dwc->free_list);
-
-	if (!is_slave_direction(dwc->direction)) {
-		struct device *parent = chan2parent(&dwc->chan);
-		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-				dma_unmap_single(parent, desc->lli.dar,
-					desc->total_len, DMA_FROM_DEVICE);
-			else
-				dma_unmap_page(parent, desc->lli.dar,
-					desc->total_len, DMA_FROM_DEVICE);
-		}
-		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-				dma_unmap_single(parent, desc->lli.sar,
-					desc->total_len, DMA_TO_DEVICE);
-			else
-				dma_unmap_page(parent, desc->lli.sar,
-					desc->total_len, DMA_TO_DEVICE);
-		}
-	}
-
+	dwc_desc_put(dwc, desc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
 static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -351,10 +277,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * the completed ones.
 	 */
 	list_splice_init(&dwc->active_list, &list);
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -365,10 +288,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 /* Returns how many bytes were already received from source */
 static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
 {
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	u32 ctlhi = channel_readl(dwc, CTL_HI);
 	u32 ctllo = channel_readl(dwc, CTL_LO);
 
-	return (ctlhi & DWC_CTLH_BLOCK_TS_MASK) * (1 << (ctllo >> 4 & 7));
+	return dw->block2bytes(dwc, ctlhi, ctllo >> 4 & 7);
 }
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -398,11 +322,11 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 
 			head = &desc->tx_list;
 			if (active != head) {
-				/* Update desc to reflect last sent one */
-				if (active != head->next)
-					desc = to_dw_desc(active->prev);
-
-				dwc->residue -= desc->len;
+				/* Update residue to reflect last sent descriptor */
+				if (active == head->next)
+					desc->residue -= desc->len;
+				else
+					desc->residue -= to_dw_desc(active->prev)->len;
 
 				child = to_dw_desc(active);
 
@@ -417,8 +341,6 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 			clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
 		}
 
-		dwc->residue = 0;
-
 		spin_unlock_irqrestore(&dwc->lock, flags);
 
 		dwc_complete_all(dw, dwc);
@@ -426,7 +348,6 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	}
 
 	if (list_empty(&dwc->active_list)) {
-		dwc->residue = 0;
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		return;
 	}
@@ -437,36 +358,35 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		return;
 	}
 
-	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=0x%llx\n", __func__,
-			(unsigned long long)llp);
+	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=%pad\n", __func__, &llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
 		/* Initial residue value */
-		dwc->residue = desc->total_len;
+		desc->residue = desc->total_len;
 
 		/* Check first descriptors addr */
-		if (desc->txd.phys == llp) {
+		if (desc->txd.phys == DWC_LLP_LOC(llp)) {
 			spin_unlock_irqrestore(&dwc->lock, flags);
 			return;
 		}
 
 		/* Check first descriptors llp */
-		if (desc->lli.llp == llp) {
+		if (lli_read(desc, llp) == llp) {
 			/* This one is currently in progress */
-			dwc->residue -= dwc_get_sent(dwc);
+			desc->residue -= dwc_get_sent(dwc);
 			spin_unlock_irqrestore(&dwc->lock, flags);
 			return;
 		}
 
-		dwc->residue -= desc->len;
+		desc->residue -= desc->len;
 		list_for_each_entry(child, &desc->tx_list, desc_node) {
-			if (child->lli.llp == llp) {
+			if (lli_read(child, llp) == llp) {
 				/* Currently in progress */
-				dwc->residue -= dwc_get_sent(dwc);
+				desc->residue -= dwc_get_sent(dwc);
 				spin_unlock_irqrestore(&dwc->lock, flags);
 				return;
 			}
-			dwc->residue -= child->len;
+			desc->residue -= child->len;
 		}
 
 		/*
@@ -484,17 +404,18 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	/* Try to continue after resetting the channel... */
 	dwc_chan_disable(dw, dwc);
 
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
-static inline void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
+static inline void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
 	dev_crit(chan2dev(&dwc->chan), "  desc: s0x%x d0x%x l0x%x c0x%x:%x\n",
-		 lli->sar, lli->dar, lli->llp, lli->ctlhi, lli->ctllo);
+		 lli_read(desc, sar),
+		 lli_read(desc, dar),
+		 lli_read(desc, llp),
+		 lli_read(desc, ctlhi),
+		 lli_read(desc, ctllo));
 }
 
 static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -530,9 +451,9 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 */
 	dev_WARN(chan2dev(&dwc->chan), "Bad descriptor submitted for DMA!\n"
 				       "  cookie: %d\n", bad_desc->txd.cookie);
-	dwc_dump_lli(dwc, &bad_desc->lli);
+	dwc_dump_lli(dwc, bad_desc);
 	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
-		dwc_dump_lli(dwc, &child->lli);
+		dwc_dump_lli(dwc, child);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -540,84 +461,13 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	dwc_descriptor_complete(dwc, bad_desc, true);
 }
 
-/* --------------------- Cyclic DMA API extensions -------------------- */
-
-dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan)
-{
-	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
-	return channel_readl(dwc, SAR);
-}
-EXPORT_SYMBOL(dw_dma_get_src_addr);
-
-dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan)
-{
-	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
-	return channel_readl(dwc, DAR);
-}
-EXPORT_SYMBOL(dw_dma_get_dst_addr);
-
-/* Called with dwc->lock held and all DMAC interrupts disabled */
-static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
-		u32 status_err, u32 status_xfer)
-{
-	unsigned long flags;
-
-	if (dwc->mask) {
-		void (*callback)(void *param);
-		void *callback_param;
-
-		dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n",
-				channel_readl(dwc, LLP));
-
-		callback = dwc->cdesc->period_callback;
-		callback_param = dwc->cdesc->period_callback_param;
-
-		if (callback)
-			callback(callback_param);
-	}
-
-	/*
-	 * Error and transfer complete are highly unlikely, and will most
-	 * likely be due to a configuration error by the user.
-	 */
-	if (unlikely(status_err & dwc->mask) ||
-			unlikely(status_xfer & dwc->mask)) {
-		int i;
-
-		dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s "
-				"interrupt, stopping DMA transfer\n",
-				status_xfer ? "xfer" : "error");
-
-		spin_lock_irqsave(&dwc->lock, flags);
-
-		dwc_dump_chan_regs(dwc);
-
-		dwc_chan_disable(dw, dwc);
-
-		/* Make sure DMA does not restart by loading a new list */
-		channel_writel(dwc, LLP, 0);
-		channel_writel(dwc, CTL_LO, 0);
-		channel_writel(dwc, CTL_HI, 0);
-
-		dma_writel(dw, CLEAR.ERROR, dwc->mask);
-		dma_writel(dw, CLEAR.XFER, dwc->mask);
-
-		for (i = 0; i < dwc->cdesc->periods; i++)
-			dwc_dump_lli(dwc, &dwc->cdesc->desc[i]->lli);
-
-		spin_unlock_irqrestore(&dwc->lock, flags);
-	}
-}
-
-/* ------------------------------------------------------------------------- */
-
-static void dw_dma_tasklet(unsigned long data)
+static void dw_dma_tasklet(struct tasklet_struct *t)
 {
-	struct dw_dma *dw = (struct dw_dma *)data;
+	struct dw_dma *dw = from_tasklet(dw, t, tasklet);
 	struct dw_dma_chan *dwc;
 	u32 status_xfer;
 	u32 status_err;
-	int i;
+	unsigned int i;
 
 	status_xfer = dma_readl(dw, RAW.XFER);
 	status_err = dma_readl(dw, RAW.ERROR);
@@ -627,16 +477,14 @@ static void dw_dma_tasklet(unsigned long data)
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
 		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
-			dwc_handle_cyclic(dw, dwc, status_err, status_xfer);
+			dev_vdbg(dw->dma.dev, "Cyclic xfer is not implemented\n");
 		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
 		else if (status_xfer & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
 	}
 
-	/*
-	 * Re-enable interrupts.
-	 */
+	/* Re-enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
@@ -646,14 +494,23 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 	struct dw_dma *dw = dev_id;
 	u32 status;
 
-	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__,
-			dma_readl(dw, STATUS_INT));
+	/* Check if we have any interrupt from the DMAC which is not in use */
+	if (!dw->in_use)
+		return IRQ_NONE;
+
+	status = dma_readl(dw, STATUS_INT);
+	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status);
+
+	/* Check if we have any interrupt from the DMAC */
+	if (!status)
+		return IRQ_NONE;
 
 	/*
 	 * Just disable the interrupts. We'll turn them back on in the
 	 * softirq handler.
 	 */
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
 
 	status = dma_readl(dw, STATUS_INT);
@@ -664,6 +521,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 
 		/* Try to recover */
 		channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1);
 		channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1);
@@ -676,38 +534,6 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 
 /*----------------------------------------------------------------------*/
 
-static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
-{
-	struct dw_desc		*desc = txd_to_dw_desc(tx);
-	struct dw_dma_chan	*dwc = to_dw_dma_chan(tx->chan);
-	dma_cookie_t		cookie;
-	unsigned long		flags;
-
-	spin_lock_irqsave(&dwc->lock, flags);
-	cookie = dma_cookie_assign(tx);
-
-	/*
-	 * REVISIT: We should attempt to chain as many descriptors as
-	 * possible, perhaps even appending to those already submitted
-	 * for DMA. But this is hard to do in a race-free manner.
-	 */
-	if (list_empty(&dwc->active_list)) {
-		dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__,
-				desc->txd.cookie);
-		list_add_tail(&desc->desc_node, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	} else {
-		dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__,
-				desc->txd.cookie);
-
-		list_add_tail(&desc->desc_node, &dwc->queue);
-	}
-
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
-	return cookie;
-}
-
 static struct dma_async_tx_descriptor *
 dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		size_t len, unsigned long flags)
@@ -719,15 +545,16 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	struct dw_desc		*prev;
 	size_t			xfer_count;
 	size_t			offset;
+	u8			m_master = dwc->dws.m_master;
 	unsigned int		src_width;
 	unsigned int		dst_width;
-	unsigned int		data_width;
-	u32			ctllo;
+	unsigned int		data_width = dw->pdata->data_width[m_master];
+	u32			ctllo, ctlhi;
+	u8			lms = DWC_LLP_LMS(m_master);
 
 	dev_vdbg(chan2dev(chan),
-			"%s: d0x%llx s0x%llx l0x%zx f0x%lx\n", __func__,
-			(unsigned long long)dest, (unsigned long long)src,
-			len, flags);
+			"%s: d%pad s%pad l0x%zx f0x%lx\n", __func__,
+			&dest, &src, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
@@ -736,13 +563,9 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 	dwc->direction = DMA_MEM_TO_MEM;
 
-	data_width = min_t(unsigned int, dw->data_width[dwc->src_master],
-			   dw->data_width[dwc->dst_master]);
-
-	src_width = dst_width = min_t(unsigned int, data_width,
-				      dwc_fast_fls(src | dest | len));
+	src_width = dst_width = __ffs(data_width | src | dest | len);
 
-	ctllo = DWC_DEFAULT_CTLLO(chan)
+	ctllo = dw->prepare_ctllo(dwc)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -750,35 +573,34 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			| DWC_CTLL_FC_M2M;
 	prev = first = NULL;
 
-	for (offset = 0; offset < len; offset += xfer_count << src_width) {
-		xfer_count = min_t(size_t, (len - offset) >> src_width,
-					   dwc->block_size);
-
+	for (offset = 0; offset < len; offset += xfer_count) {
 		desc = dwc_desc_get(dwc);
 		if (!desc)
 			goto err_desc_get;
 
-		desc->lli.sar = src + offset;
-		desc->lli.dar = dest + offset;
-		desc->lli.ctllo = ctllo;
-		desc->lli.ctlhi = xfer_count;
-		desc->len = xfer_count << src_width;
+		ctlhi = dw->bytes2block(dwc, len - offset, src_width, &xfer_count);
+
+		lli_write(desc, sar, src + offset);
+		lli_write(desc, dar, dest + offset);
+		lli_write(desc, ctllo, ctllo);
+		lli_write(desc, ctlhi, ctlhi);
+		desc->len = xfer_count;
 
 		if (!first) {
 			first = desc;
 		} else {
-			prev->lli.llp = desc->txd.phys;
-			list_add_tail(&desc->desc_node,
-					&first->tx_list);
+			lli_write(prev, llp, desc->txd.phys | lms);
+			list_add_tail(&desc->desc_node, &first->tx_list);
 		}
 		prev = desc;
 	}
 
 	if (flags & DMA_PREP_INTERRUPT)
 		/* Trigger interrupt after last block */
-		prev->lli.ctllo |= DWC_CTLL_INT_EN;
+		lli_set(prev, ctllo, DWC_CTLL_INT_EN);
 
 	prev->lli.llp = 0;
+	lli_clear(prev, ctllo, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
 	first->txd.flags = flags;
 	first->total_len = len;
 
@@ -799,11 +621,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
 	struct dw_desc		*prev;
 	struct dw_desc		*first;
-	u32			ctllo;
+	u32			ctllo, ctlhi;
+	u8			lms = DWC_LLP_LMS(dwc->dws.m_master);
 	dma_addr_t		reg;
 	unsigned int		reg_width;
 	unsigned int		mem_width;
-	unsigned int		data_width;
 	unsigned int		i;
 	struct scatterlist	*sg;
 	size_t			total_len = 0;
@@ -819,59 +641,49 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
-		reg_width = __fls(sconfig->dst_addr_width);
+		reg_width = __ffs(sconfig->dst_addr_width);
 		reg = sconfig->dst_addr;
-		ctllo = (DWC_DEFAULT_CTLLO(chan)
+		ctllo = dw->prepare_ctllo(dwc)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
-				| DWC_CTLL_SRC_INC);
+				| DWC_CTLL_SRC_INC;
 
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
 			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
 
-		data_width = dw->data_width[dwc->src_master];
-
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len, dlen, mem;
+			u32		len, mem;
+			size_t		dlen;
 
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
 
-			mem_width = min_t(unsigned int,
-					  data_width, dwc_fast_fls(mem | len));
+			mem_width = __ffs(sconfig->src_addr_width | mem | len);
 
 slave_sg_todev_fill_desc:
 			desc = dwc_desc_get(dwc);
-			if (!desc) {
-				dev_err(chan2dev(chan),
-					"not enough descriptors available\n");
+			if (!desc)
 				goto err_desc_get;
-			}
 
-			desc->lli.sar = mem;
-			desc->lli.dar = reg;
-			desc->lli.ctllo = ctllo | DWC_CTLL_SRC_WIDTH(mem_width);
-			if ((len >> mem_width) > dwc->block_size) {
-				dlen = dwc->block_size << mem_width;
-				mem += dlen;
-				len -= dlen;
-			} else {
-				dlen = len;
-				len = 0;
-			}
+			ctlhi = dw->bytes2block(dwc, len, mem_width, &dlen);
 
-			desc->lli.ctlhi = dlen >> mem_width;
+			lli_write(desc, sar, mem);
+			lli_write(desc, dar, reg);
+			lli_write(desc, ctlhi, ctlhi);
+			lli_write(desc, ctllo, ctllo | DWC_CTLL_SRC_WIDTH(mem_width));
 			desc->len = dlen;
 
 			if (!first) {
 				first = desc;
 			} else {
-				prev->lli.llp = desc->txd.phys;
-				list_add_tail(&desc->desc_node,
-						&first->tx_list);
+				lli_write(prev, llp, desc->txd.phys | lms);
+				list_add_tail(&desc->desc_node, &first->tx_list);
 			}
 			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
 			total_len += dlen;
 
 			if (len)
@@ -879,58 +691,48 @@ slave_sg_todev_fill_desc:
 		}
 		break;
 	case DMA_DEV_TO_MEM:
-		reg_width = __fls(sconfig->src_addr_width);
+		reg_width = __ffs(sconfig->src_addr_width);
 		reg = sconfig->src_addr;
-		ctllo = (DWC_DEFAULT_CTLLO(chan)
+		ctllo = dw->prepare_ctllo(dwc)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
-				| DWC_CTLL_SRC_FIX);
+				| DWC_CTLL_SRC_FIX;
 
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
 			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
 
-		data_width = dw->data_width[dwc->dst_master];
-
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len, dlen, mem;
+			u32		len, mem;
+			size_t		dlen;
 
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
 
-			mem_width = min_t(unsigned int,
-					  data_width, dwc_fast_fls(mem | len));
-
 slave_sg_fromdev_fill_desc:
 			desc = dwc_desc_get(dwc);
-			if (!desc) {
-				dev_err(chan2dev(chan),
-						"not enough descriptors available\n");
+			if (!desc)
 				goto err_desc_get;
-			}
 
-			desc->lli.sar = reg;
-			desc->lli.dar = mem;
-			desc->lli.ctllo = ctllo | DWC_CTLL_DST_WIDTH(mem_width);
-			if ((len >> reg_width) > dwc->block_size) {
-				dlen = dwc->block_size << reg_width;
-				mem += dlen;
-				len -= dlen;
-			} else {
-				dlen = len;
-				len = 0;
-			}
-			desc->lli.ctlhi = dlen >> reg_width;
+			ctlhi = dw->bytes2block(dwc, len, reg_width, &dlen);
+
+			lli_write(desc, sar, reg);
+			lli_write(desc, dar, mem);
+			lli_write(desc, ctlhi, ctlhi);
+			mem_width = __ffs(sconfig->dst_addr_width | mem);
+			lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
 			desc->len = dlen;
 
 			if (!first) {
 				first = desc;
 			} else {
-				prev->lli.llp = desc->txd.phys;
-				list_add_tail(&desc->desc_node,
-						&first->tx_list);
+				lli_write(prev, llp, desc->txd.phys | lms);
+				list_add_tail(&desc->desc_node, &first->tx_list);
 			}
 			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
 			total_len += dlen;
 
 			if (len)
@@ -943,79 +745,196 @@ slave_sg_fromdev_fill_desc:
 
 	if (flags & DMA_PREP_INTERRUPT)
 		/* Trigger interrupt after last block */
-		prev->lli.ctllo |= DWC_CTLL_INT_EN;
+		lli_set(prev, ctllo, DWC_CTLL_INT_EN);
 
 	prev->lli.llp = 0;
+	lli_clear(prev, ctllo, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
 	first->total_len = total_len;
 
 	return &first->txd;
 
 err_desc_get:
+	dev_err(chan2dev(chan),
+		"not enough descriptors available. Direction %d\n", direction);
 	dwc_desc_put(dwc, first);
 	return NULL;
 }
 
-/*
- * Fix sconfig's burst size according to dw_dmac. We need to convert them as:
- * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
- *
- * NOTE: burst size 2 is not supported by controller.
- *
- * This can be done by finding least significant bit set: n & (n - 1)
- */
-static inline void convert_burst(u32 *maxburst)
+bool dw_dma_filter(struct dma_chan *chan, void *param)
 {
-	if (*maxburst > 1)
-		*maxburst = fls(*maxburst) - 2;
-	else
-		*maxburst = 0;
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dw_dma_slave *dws = param;
+
+	if (dws->dma_dev != chan->device->dev)
+		return false;
+
+	/* permit channels in accordance with the channels mask */
+	if (dws->channels && !(dws->channels & dwc->mask))
+		return false;
+
+	/* We have to copy data since dws can be temporary storage */
+	memcpy(&dwc->dws, dws, sizeof(struct dw_dma_slave));
+
+	return true;
 }
+EXPORT_SYMBOL_GPL(dw_dma_filter);
 
-static int
-set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+static int dwc_verify_maxburst(struct dma_chan *chan)
 {
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 
-	/* Check if chan will be configured for slave transfers */
-	if (!is_slave_direction(sconfig->direction))
+	dwc->dma_sconfig.src_maxburst =
+		clamp(dwc->dma_sconfig.src_maxburst, 1U, dwc->max_burst);
+	dwc->dma_sconfig.dst_maxburst =
+		clamp(dwc->dma_sconfig.dst_maxburst, 1U, dwc->max_burst);
+
+	dwc->dma_sconfig.src_maxburst =
+		rounddown_pow_of_two(dwc->dma_sconfig.src_maxburst);
+	dwc->dma_sconfig.dst_maxburst =
+		rounddown_pow_of_two(dwc->dma_sconfig.dst_maxburst);
+
+	return 0;
+}
+
+static int dwc_verify_p_buswidth(struct dma_chan *chan)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	u32 reg_width, max_width;
+
+	if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+		reg_width = dwc->dma_sconfig.dst_addr_width;
+	else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM)
+		reg_width = dwc->dma_sconfig.src_addr_width;
+	else /* DMA_MEM_TO_MEM */
+		return 0;
+
+	max_width = dw->pdata->data_width[dwc->dws.p_master];
+
+	/* Fall-back to 1-byte transfer width if undefined */
+	if (reg_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+		reg_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	else if (!is_power_of_2(reg_width) || reg_width > max_width)
 		return -EINVAL;
+	else /* bus width is valid */
+		return 0;
+
+	/* Update undefined addr width value */
+	if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+		dwc->dma_sconfig.dst_addr_width = reg_width;
+	else /* DMA_DEV_TO_MEM */
+		dwc->dma_sconfig.src_addr_width = reg_width;
+
+	return 0;
+}
+
+static int dwc_verify_m_buswidth(struct dma_chan *chan)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	u32 reg_width, reg_burst, mem_width;
+
+	mem_width = dw->pdata->data_width[dwc->dws.m_master];
+
+	/*
+	 * It's possible to have a data portion locked in the DMA FIFO in case
+	 * of the channel suspension. Subsequent channel disabling will cause
+	 * that data silent loss. In order to prevent that maintain the src and
+	 * dst transfer widths coherency by means of the relation:
+	 * (CTLx.SRC_TR_WIDTH * CTLx.SRC_MSIZE >= CTLx.DST_TR_WIDTH)
+	 * Look for the details in the commit message that brings this change.
+	 *
+	 * Note the DMA configs utilized in the calculations below must have
+	 * been verified to have correct values by this method call.
+	 */
+	if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) {
+		reg_width = dwc->dma_sconfig.dst_addr_width;
+		if (mem_width < reg_width)
+			return -EINVAL;
+
+		dwc->dma_sconfig.src_addr_width = mem_width;
+	} else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) {
+		reg_width = dwc->dma_sconfig.src_addr_width;
+		reg_burst = dwc->dma_sconfig.src_maxburst;
+
+		dwc->dma_sconfig.dst_addr_width = min(mem_width, reg_width * reg_burst);
+	}
+
+	return 0;
+}
+
+static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	int ret;
 
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
-	dwc->direction = sconfig->direction;
 
-	/* Take the request line from slave_id member */
-	if (dwc->request_line == ~0)
-		dwc->request_line = sconfig->slave_id;
+	ret = dwc_verify_maxburst(chan);
+	if (ret)
+		return ret;
+
+	ret = dwc_verify_p_buswidth(chan);
+	if (ret)
+		return ret;
 
-	convert_burst(&dwc->dma_sconfig.src_maxburst);
-	convert_burst(&dwc->dma_sconfig.dst_maxburst);
+	ret = dwc_verify_m_buswidth(chan);
+	if (ret)
+		return ret;
 
 	return 0;
 }
 
-static inline void dwc_chan_pause(struct dw_dma_chan *dwc)
+static void dwc_chan_pause(struct dw_dma_chan *dwc, bool drain)
 {
-	u32 cfglo = channel_readl(dwc, CFG_LO);
-	unsigned int count = 20;	/* timeout iterations */
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	unsigned int		count = 20;	/* timeout iterations */
+
+	dw->suspend_chan(dwc, drain);
 
-	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
 	while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY) && count--)
 		udelay(2);
 
-	dwc->paused = true;
+	set_bit(DW_DMA_IS_PAUSED, &dwc->flags);
+}
+
+static int dwc_pause(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	dwc_chan_pause(dwc, false);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	return 0;
+}
+
+static inline void dwc_chan_resume(struct dw_dma_chan *dwc, bool drain)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	dw->resume_chan(dwc, drain);
+
+	clear_bit(DW_DMA_IS_PAUSED, &dwc->flags);
 }
 
-static inline void dwc_chan_resume(struct dw_dma_chan *dwc)
+static int dwc_resume(struct dma_chan *chan)
 {
-	u32 cfglo = channel_readl(dwc, CFG_LO);
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
 
-	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+	if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags))
+		dwc_chan_resume(dwc, false);
 
-	dwc->paused = false;
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	return 0;
 }
 
-static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
-		       unsigned long arg)
+static int dwc_terminate_all(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
@@ -1023,58 +942,63 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	unsigned long		flags;
 	LIST_HEAD(list);
 
-	if (cmd == DMA_PAUSE) {
-		spin_lock_irqsave(&dwc->lock, flags);
-
-		dwc_chan_pause(dwc);
+	spin_lock_irqsave(&dwc->lock, flags);
 
-		spin_unlock_irqrestore(&dwc->lock, flags);
-	} else if (cmd == DMA_RESUME) {
-		if (!dwc->paused)
-			return 0;
+	clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
 
-		spin_lock_irqsave(&dwc->lock, flags);
+	dwc_chan_pause(dwc, true);
 
-		dwc_chan_resume(dwc);
+	dwc_chan_disable(dw, dwc);
 
-		spin_unlock_irqrestore(&dwc->lock, flags);
-	} else if (cmd == DMA_TERMINATE_ALL) {
-		spin_lock_irqsave(&dwc->lock, flags);
+	dwc_chan_resume(dwc, true);
 
-		clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+	/* active_list entries will end up before queued entries */
+	list_splice_init(&dwc->queue, &list);
+	list_splice_init(&dwc->active_list, &list);
 
-		dwc_chan_disable(dw, dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 
-		dwc_chan_resume(dwc);
+	/* Flush all pending and queued descriptors */
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		dwc_descriptor_complete(dwc, desc, false);
 
-		/* active_list entries will end up before queued entries */
-		list_splice_init(&dwc->queue, &list);
-		list_splice_init(&dwc->active_list, &list);
+	return 0;
+}
 
-		spin_unlock_irqrestore(&dwc->lock, flags);
+static struct dw_desc *dwc_find_desc(struct dw_dma_chan *dwc, dma_cookie_t c)
+{
+	struct dw_desc *desc;
 
-		/* Flush all pending and queued descriptors */
-		list_for_each_entry_safe(desc, _desc, &list, desc_node)
-			dwc_descriptor_complete(dwc, desc, false);
-	} else if (cmd == DMA_SLAVE_CONFIG) {
-		return set_runtime_config(chan, (struct dma_slave_config *)arg);
-	} else {
-		return -ENXIO;
-	}
+	list_for_each_entry(desc, &dwc->active_list, desc_node)
+		if (desc->txd.cookie == c)
+			return desc;
 
-	return 0;
+	return NULL;
 }
 
-static inline u32 dwc_get_residue(struct dw_dma_chan *dwc)
+static u32 dwc_get_residue_and_status(struct dw_dma_chan *dwc, dma_cookie_t cookie,
+				      enum dma_status *status)
 {
+	struct dw_desc *desc;
 	unsigned long flags;
 	u32 residue;
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
-	residue = dwc->residue;
-	if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags) && residue)
-		residue -= dwc_get_sent(dwc);
+	desc = dwc_find_desc(dwc, cookie);
+	if (desc) {
+		if (desc == dwc_first_active(dwc)) {
+			residue = desc->residue;
+			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags) && residue)
+				residue -= dwc_get_sent(dwc);
+			if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags))
+				*status = DMA_PAUSED;
+		} else {
+			residue = desc->total_len;
+		}
+	} else {
+		residue = 0;
+	}
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 	return residue;
@@ -1089,36 +1013,55 @@ dwc_tx_status(struct dma_chan *chan,
 	enum dma_status		ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
-		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
-
-		ret = dma_cookie_status(chan, cookie, txstate);
-	}
+	if (ret == DMA_COMPLETE)
+		return ret;
 
-	if (ret != DMA_SUCCESS)
-		dma_set_residue(txstate, dwc_get_residue(dwc));
+	dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
 
-	if (dwc->paused)
-		return DMA_PAUSED;
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
 
+	dma_set_residue(txstate, dwc_get_residue_and_status(dwc, cookie, &ret));
 	return ret;
 }
 
 static void dwc_issue_pending(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (list_empty(&dwc->active_list))
+		dwc_dostart_first_queued(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
+/*----------------------------------------------------------------------*/
 
-	if (!list_empty(&dwc->queue))
-		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+void do_dw_dma_off(struct dw_dma *dw)
+{
+	dma_writel(dw, CFG, 0);
+
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
+		cpu_relax();
+}
+
+void do_dw_dma_on(struct dw_dma *dw)
+{
+	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 }
 
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
-	struct dw_desc		*desc;
-	int			i;
-	unsigned long		flags;
 
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
@@ -1136,52 +1079,27 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
-	dwc_set_masters(dwc);
-
-	spin_lock_irqsave(&dwc->lock, flags);
-	i = dwc->descs_allocated;
-	while (dwc->descs_allocated < NR_DESCS_PER_CHANNEL) {
-		dma_addr_t phys;
-
-		spin_unlock_irqrestore(&dwc->lock, flags);
-
-		desc = dma_pool_alloc(dw->desc_pool, GFP_ATOMIC, &phys);
-		if (!desc)
-			goto err_desc_alloc;
-
-		memset(desc, 0, sizeof(struct dw_desc));
-
-		INIT_LIST_HEAD(&desc->tx_list);
-		dma_async_tx_descriptor_init(&desc->txd, chan);
-		desc->txd.tx_submit = dwc_tx_submit;
-		desc->txd.flags = DMA_CTRL_ACK;
-		desc->txd.phys = phys;
-
-		dwc_desc_put(dwc, desc);
-
-		spin_lock_irqsave(&dwc->lock, flags);
-		i = ++dwc->descs_allocated;
+	/*
+	 * We need controller-specific data to set up slave transfers.
+	 */
+	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
+		return -EINVAL;
 	}
 
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
-	dev_dbg(chan2dev(chan), "%s: allocated %d descriptors\n", __func__, i);
-
-	return i;
+	/* Enable controller here if needed */
+	if (!dw->in_use)
+		do_dw_dma_on(dw);
+	dw->in_use |= dwc->mask;
 
-err_desc_alloc:
-	dev_info(chan2dev(chan), "only allocated %d descriptors\n", i);
-
-	return i;
+	return 0;
 }
 
 static void dwc_free_chan_resources(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
-	struct dw_desc		*desc, *_desc;
 	unsigned long		flags;
-	LIST_HEAD(list);
 
 	dev_dbg(chan2dev(chan), "%s: descs allocated=%u\n", __func__,
 			dwc->descs_allocated);
@@ -1192,393 +1110,131 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	list_splice_init(&dwc->free_list, &list);
-	dwc->descs_allocated = 0;
-	dwc->initialized = false;
-	dwc->request_line = ~0;
+
+	/* Clear custom channel configuration */
+	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
 
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
+	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
-	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
-		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
-		dma_pool_free(dw->desc_pool, desc, desc->txd.phys);
-	}
+	/* Disable controller in case it was a last user */
+	dw->in_use &= ~dwc->mask;
+	if (!dw->in_use)
+		do_dw_dma_off(dw);
 
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
-/* --------------------- Cyclic DMA API extensions -------------------- */
-
-/**
- * dw_dma_cyclic_start - start the cyclic DMA transfer
- * @chan: the DMA channel to start
- *
- * Must be called with soft interrupts disabled. Returns zero on success or
- * -errno on failure.
- */
-int dw_dma_cyclic_start(struct dma_chan *chan)
-{
-	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
-	unsigned long		flags;
-
-	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
-		dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n");
-		return -ENODEV;
-	}
-
-	spin_lock_irqsave(&dwc->lock, flags);
-
-	/* Assert channel is idle */
-	if (dma_readl(dw, CH_EN) & dwc->mask) {
-		dev_err(chan2dev(&dwc->chan),
-			"BUG: Attempted to start non-idle channel\n");
-		dwc_dump_chan_regs(dwc);
-		spin_unlock_irqrestore(&dwc->lock, flags);
-		return -EBUSY;
-	}
-
-	dma_writel(dw, CLEAR.ERROR, dwc->mask);
-	dma_writel(dw, CLEAR.XFER, dwc->mask);
-
-	/* Setup DMAC channel registers */
-	channel_writel(dwc, LLP, dwc->cdesc->desc[0]->txd.phys);
-	channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
-	channel_writel(dwc, CTL_HI, 0);
-
-	channel_set_bit(dw, CH_EN, dwc->mask);
-
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
-	return 0;
-}
-EXPORT_SYMBOL(dw_dma_cyclic_start);
-
-/**
- * dw_dma_cyclic_stop - stop the cyclic DMA transfer
- * @chan: the DMA channel to stop
- *
- * Must be called with soft interrupts disabled.
- */
-void dw_dma_cyclic_stop(struct dma_chan *chan)
-{
-	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
-	unsigned long		flags;
-
-	spin_lock_irqsave(&dwc->lock, flags);
-
-	dwc_chan_disable(dw, dwc);
-
-	spin_unlock_irqrestore(&dwc->lock, flags);
-}
-EXPORT_SYMBOL(dw_dma_cyclic_stop);
-
-/**
- * dw_dma_cyclic_prep - prepare the cyclic DMA transfer
- * @chan: the DMA channel to prepare
- * @buf_addr: physical DMA address where the buffer starts
- * @buf_len: total number of bytes for the entire buffer
- * @period_len: number of bytes for each period
- * @direction: transfer direction, to or from device
- *
- * Must be called before trying to start the transfer. Returns a valid struct
- * dw_cyclic_desc if successful or an ERR_PTR(-errno) if not successful.
- */
-struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
-		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
-		enum dma_transfer_direction direction)
+static void dwc_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 {
-	struct dw_dma_chan		*dwc = to_dw_dma_chan(chan);
-	struct dma_slave_config		*sconfig = &dwc->dma_sconfig;
-	struct dw_cyclic_desc		*cdesc;
-	struct dw_cyclic_desc		*retval = NULL;
-	struct dw_desc			*desc;
-	struct dw_desc			*last = NULL;
-	unsigned long			was_cyclic;
-	unsigned int			reg_width;
-	unsigned int			periods;
-	unsigned int			i;
-	unsigned long			flags;
-
-	spin_lock_irqsave(&dwc->lock, flags);
-	if (dwc->nollp) {
-		spin_unlock_irqrestore(&dwc->lock, flags);
-		dev_dbg(chan2dev(&dwc->chan),
-				"channel doesn't support LLP transfers\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) {
-		spin_unlock_irqrestore(&dwc->lock, flags);
-		dev_dbg(chan2dev(&dwc->chan),
-				"queue and/or active list are not empty\n");
-		return ERR_PTR(-EBUSY);
-	}
-
-	was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
-	spin_unlock_irqrestore(&dwc->lock, flags);
-	if (was_cyclic) {
-		dev_dbg(chan2dev(&dwc->chan),
-				"channel already prepared for cyclic DMA\n");
-		return ERR_PTR(-EBUSY);
-	}
-
-	retval = ERR_PTR(-EINVAL);
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 
-	if (unlikely(!is_slave_direction(direction)))
-		goto out_err;
+	caps->max_burst = dwc->max_burst;
 
-	dwc->direction = direction;
-
-	if (direction == DMA_MEM_TO_DEV)
-		reg_width = __ffs(sconfig->dst_addr_width);
+	/*
+	 * It might be crucial for some devices to have the hardware
+	 * accelerated multi-block transfers supported, aka LLPs in DW DMAC
+	 * notation. So if LLPs are supported then max_sg_burst is set to
+	 * zero which means unlimited number of SG entries can be handled in a
+	 * single DMA transaction, otherwise it's just one SG entry.
+	 */
+	if (dwc->nollp)
+		caps->max_sg_burst = 1;
 	else
-		reg_width = __ffs(sconfig->src_addr_width);
-
-	periods = buf_len / period_len;
-
-	/* Check for too big/unaligned periods and unaligned DMA buffer. */
-	if (period_len > (dwc->block_size << reg_width))
-		goto out_err;
-	if (unlikely(period_len & ((1 << reg_width) - 1)))
-		goto out_err;
-	if (unlikely(buf_addr & ((1 << reg_width) - 1)))
-		goto out_err;
-
-	retval = ERR_PTR(-ENOMEM);
-
-	if (periods > NR_DESCS_PER_CHANNEL)
-		goto out_err;
-
-	cdesc = kzalloc(sizeof(struct dw_cyclic_desc), GFP_KERNEL);
-	if (!cdesc)
-		goto out_err;
-
-	cdesc->desc = kzalloc(sizeof(struct dw_desc *) * periods, GFP_KERNEL);
-	if (!cdesc->desc)
-		goto out_err_alloc;
-
-	for (i = 0; i < periods; i++) {
-		desc = dwc_desc_get(dwc);
-		if (!desc)
-			goto out_err_desc_get;
-
-		switch (direction) {
-		case DMA_MEM_TO_DEV:
-			desc->lli.dar = sconfig->dst_addr;
-			desc->lli.sar = buf_addr + (period_len * i);
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
-					| DWC_CTLL_DST_WIDTH(reg_width)
-					| DWC_CTLL_SRC_WIDTH(reg_width)
-					| DWC_CTLL_DST_FIX
-					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_INT_EN);
-
-			desc->lli.ctllo |= sconfig->device_fc ?
-				DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
-				DWC_CTLL_FC(DW_DMA_FC_D_M2P);
-
-			break;
-		case DMA_DEV_TO_MEM:
-			desc->lli.dar = buf_addr + (period_len * i);
-			desc->lli.sar = sconfig->src_addr;
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan)
-					| DWC_CTLL_SRC_WIDTH(reg_width)
-					| DWC_CTLL_DST_WIDTH(reg_width)
-					| DWC_CTLL_DST_INC
-					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_INT_EN);
-
-			desc->lli.ctllo |= sconfig->device_fc ?
-				DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
-				DWC_CTLL_FC(DW_DMA_FC_D_P2M);
-
-			break;
-		default:
-			break;
-		}
-
-		desc->lli.ctlhi = (period_len >> reg_width);
-		cdesc->desc[i] = desc;
-
-		if (last)
-			last->lli.llp = desc->txd.phys;
-
-		last = desc;
-	}
-
-	/* Let's make a cyclic list */
-	last->lli.llp = cdesc->desc[0]->txd.phys;
-
-	dev_dbg(chan2dev(&dwc->chan), "cyclic prepared buf 0x%llx len %zu "
-			"period %zu periods %d\n", (unsigned long long)buf_addr,
-			buf_len, period_len, periods);
-
-	cdesc->periods = periods;
-	dwc->cdesc = cdesc;
-
-	return cdesc;
-
-out_err_desc_get:
-	while (i--)
-		dwc_desc_put(dwc, cdesc->desc[i]);
-out_err_alloc:
-	kfree(cdesc);
-out_err:
-	clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
-	return (struct dw_cyclic_desc *)retval;
-}
-EXPORT_SYMBOL(dw_dma_cyclic_prep);
-
-/**
- * dw_dma_cyclic_free - free a prepared cyclic DMA transfer
- * @chan: the DMA channel to free
- */
-void dw_dma_cyclic_free(struct dma_chan *chan)
-{
-	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
-	struct dw_cyclic_desc	*cdesc = dwc->cdesc;
-	int			i;
-	unsigned long		flags;
-
-	dev_dbg(chan2dev(&dwc->chan), "%s\n", __func__);
-
-	if (!cdesc)
-		return;
-
-	spin_lock_irqsave(&dwc->lock, flags);
-
-	dwc_chan_disable(dw, dwc);
-
-	dma_writel(dw, CLEAR.ERROR, dwc->mask);
-	dma_writel(dw, CLEAR.XFER, dwc->mask);
-
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
-	for (i = 0; i < cdesc->periods; i++)
-		dwc_desc_put(dwc, cdesc->desc[i]);
-
-	kfree(cdesc->desc);
-	kfree(cdesc);
-
-	clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
+		caps->max_sg_burst = 0;
 }
-EXPORT_SYMBOL(dw_dma_cyclic_free);
 
-/*----------------------------------------------------------------------*/
-
-static void dw_dma_off(struct dw_dma *dw)
+int do_dma_probe(struct dw_dma_chip *chip)
 {
-	int i;
-
-	dma_writel(dw, CFG, 0);
+	struct dw_dma *dw = chip->dw;
+	struct dw_dma_platform_data *pdata;
+	bool			autocfg = false;
+	unsigned int		dw_params;
+	unsigned int		i;
+	int			ret;
 
-	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+	dw->pdata = devm_kzalloc(chip->dev, sizeof(*dw->pdata), GFP_KERNEL);
+	if (!dw->pdata)
+		return -ENOMEM;
 
-	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
-		cpu_relax();
+	dw->regs = chip->regs;
 
-	for (i = 0; i < dw->dma.chancnt; i++)
-		dw->chan[i].initialized = false;
-}
+	pm_runtime_get_sync(chip->dev);
 
-int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
-{
-	struct dw_dma		*dw;
-	size_t			size;
-	bool			autocfg;
-	unsigned int		dw_params;
-	unsigned int		nr_channels;
-	unsigned int		max_blk_size = 0;
-	int			err;
-	int			i;
+	if (!chip->pdata) {
+		dw_params = dma_readl(dw, DW_PARAMS);
+		dev_dbg(chip->dev, "DW_PARAMS: 0x%08x\n", dw_params);
 
-	dw_params = dma_read_byaddr(chip->regs, DW_PARAMS);
-	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
+		autocfg = dw_params >> DW_PARAMS_EN & 1;
+		if (!autocfg) {
+			ret = -EINVAL;
+			goto err_pdata;
+		}
 
-	dev_dbg(chip->dev, "DW_PARAMS: 0x%08x\n", dw_params);
+		/* Reassign the platform data pointer */
+		pdata = dw->pdata;
 
-	if (!pdata && autocfg) {
-		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
+		/* Get hardware configuration parameters */
+		pdata->nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 7) + 1;
+		pdata->nr_masters = (dw_params >> DW_PARAMS_NR_MASTER & 3) + 1;
+		for (i = 0; i < pdata->nr_masters; i++) {
+			pdata->data_width[i] =
+				4 << (dw_params >> DW_PARAMS_DATA_WIDTH(i) & 3);
+		}
+		pdata->block_size = dma_readl(dw, MAX_BLK_SIZE);
 
 		/* Fill platform data with the default values */
-		pdata->is_private = true;
 		pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
 		pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
-	} else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
-		return -EINVAL;
-
-	if (autocfg)
-		nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 0x7) + 1;
-	else
-		nr_channels = pdata->nr_channels;
-
-	size = sizeof(struct dw_dma) + nr_channels * sizeof(struct dw_dma_chan);
-	dw = devm_kzalloc(chip->dev, size, GFP_KERNEL);
-	if (!dw)
-		return -ENOMEM;
-
-	dw->clk = devm_clk_get(chip->dev, "hclk");
-	if (IS_ERR(dw->clk))
-		return PTR_ERR(dw->clk);
-	clk_prepare_enable(dw->clk);
-
-	dw->regs = chip->regs;
-	chip->dw = dw;
+	} else if (chip->pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
+		ret = -EINVAL;
+		goto err_pdata;
+	} else {
+		memcpy(dw->pdata, chip->pdata, sizeof(*dw->pdata));
 
-	/* Get hardware configuration parameters */
-	if (autocfg) {
-		max_blk_size = dma_readl(dw, MAX_BLK_SIZE);
+		/* Reassign the platform data pointer */
+		pdata = dw->pdata;
+	}
 
-		dw->nr_masters = (dw_params >> DW_PARAMS_NR_MASTER & 3) + 1;
-		for (i = 0; i < dw->nr_masters; i++) {
-			dw->data_width[i] =
-				(dw_params >> DW_PARAMS_DATA_WIDTH(i) & 3) + 2;
-		}
-	} else {
-		dw->nr_masters = pdata->nr_masters;
-		memcpy(dw->data_width, pdata->data_width, 4);
+	dw->chan = devm_kcalloc(chip->dev, pdata->nr_channels, sizeof(*dw->chan),
+				GFP_KERNEL);
+	if (!dw->chan) {
+		ret = -ENOMEM;
+		goto err_pdata;
 	}
 
 	/* Calculate all channel mask before DMA setup */
-	dw->all_chan_mask = (1 << nr_channels) - 1;
+	dw->all_chan_mask = (1 << pdata->nr_channels) - 1;
 
 	/* Force dma off, just in case */
-	dw_dma_off(dw);
-
-	/* Disable BLOCK interrupts as well */
-	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	dw->disable(dw);
 
-	err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt, 0,
-			       "dw_dmac", dw);
-	if (err)
-		return err;
+	/* Device and instance ID for IRQ and DMA pool */
+	dw->set_device_name(dw, chip->id);
 
 	/* Create a pool of consistent memory blocks for hardware descriptors */
-	dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev,
+	dw->desc_pool = dmam_pool_create(dw->name, chip->dev,
 					 sizeof(struct dw_desc), 4, 0);
 	if (!dw->desc_pool) {
 		dev_err(chip->dev, "No memory for descriptors dma pool\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_pdata;
 	}
 
-	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
+	tasklet_setup(&dw->tasklet, dw_dma_tasklet);
+
+	ret = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
+			  dw->name, dw);
+	if (ret)
+		goto err_pdata;
 
 	INIT_LIST_HEAD(&dw->dma.channels);
-	for (i = 0; i < nr_channels; i++) {
+	for (i = 0; i < pdata->nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
-		int			r = nr_channels - i - 1;
 
 		dwc->chan.device = &dw->dma;
 		dma_cookie_init(&dwc->chan);
@@ -1590,7 +1246,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = r;
+			dwc->priority = pdata->nr_channels - i - 1;
 		else
 			dwc->priority = i;
 
@@ -1600,38 +1256,44 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 		INIT_LIST_HEAD(&dwc->active_list);
 		INIT_LIST_HEAD(&dwc->queue);
-		INIT_LIST_HEAD(&dwc->free_list);
 
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 
 		dwc->direction = DMA_TRANS_NONE;
-		dwc->request_line = ~0;
 
 		/* Hardware configuration */
 		if (autocfg) {
-			unsigned int dwc_params;
-			void __iomem *addr = chip->regs + r * sizeof(u32);
-
-			dwc_params = dma_read_byaddr(addr, DWC_PARAMS);
+			unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
+			void __iomem *addr = &__dw_regs(dw)->DWC_PARAMS[r];
+			unsigned int dwc_params = readl(addr);
 
 			dev_dbg(chip->dev, "DWC_PARAMS[%d]: 0x%08x\n", i,
 					   dwc_params);
 
-			/* Decode maximum block size for given channel. The
+			/*
+			 * Decode maximum block size for given channel. The
 			 * stored 4 bit value represents blocks from 0x00 for 3
-			 * up to 0x0a for 4095. */
+			 * up to 0x0a for 4095.
+			 */
 			dwc->block_size =
-				(4 << ((max_blk_size >> 4 * i) & 0xf)) - 1;
+				(4 << ((pdata->block_size >> 4 * i) & 0xf)) - 1;
+
+			/*
+			 * According to the DW DMA databook the true scatter-
+			 * gether LLPs aren't available if either multi-block
+			 * config is disabled (CHx_MULTI_BLK_EN == 0) or the
+			 * LLP register is hard-coded to zeros
+			 * (CHx_HC_LLP == 1).
+			 */
 			dwc->nollp =
-				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0;
+				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0 ||
+				(dwc_params >> DWC_PARAMS_HC_LLP & 0x1) == 1;
+			dwc->max_burst =
+				(0x4 << (dwc_params >> DWC_PARAMS_MSIZE & 0x7));
 		} else {
 			dwc->block_size = pdata->block_size;
-
-			/* Check if channel supports multi block transfer */
-			channel_writel(dwc, LLP, 0xfffffffc);
-			dwc->nollp =
-				(channel_readl(dwc, LLP) & 0xfffffffc) == 0;
-			channel_writel(dwc, LLP, 0);
+			dwc->nollp = !pdata->multi_block[i];
+			dwc->max_burst = pdata->max_burst[i] ?: DW_DMA_MAX_BURST;
 		}
 	}
 
@@ -1642,41 +1304,72 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	dma_writel(dw, CLEAR.DST_TRAN, dw->all_chan_mask);
 	dma_writel(dw, CLEAR.ERROR, dw->all_chan_mask);
 
-	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+	/* Set capabilities */
 	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
-	if (pdata->is_private)
-		dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
+	dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
+	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+
 	dw->dma.dev = chip->dev;
 	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
 	dw->dma.device_free_chan_resources = dwc_free_chan_resources;
 
 	dw->dma.device_prep_dma_memcpy = dwc_prep_dma_memcpy;
-
 	dw->dma.device_prep_slave_sg = dwc_prep_slave_sg;
-	dw->dma.device_control = dwc_control;
+
+	dw->dma.device_caps = dwc_caps;
+	dw->dma.device_config = dwc_config;
+	dw->dma.device_pause = dwc_pause;
+	dw->dma.device_resume = dwc_resume;
+	dw->dma.device_terminate_all = dwc_terminate_all;
 
 	dw->dma.device_tx_status = dwc_tx_status;
 	dw->dma.device_issue_pending = dwc_issue_pending;
 
-	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+	/* DMA capabilities */
+	dw->dma.min_burst = DW_DMA_MIN_BURST;
+	dw->dma.max_burst = DW_DMA_MAX_BURST;
+	dw->dma.src_addr_widths = DW_DMA_BUSWIDTHS;
+	dw->dma.dst_addr_widths = DW_DMA_BUSWIDTHS;
+	dw->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
+			     BIT(DMA_MEM_TO_MEM);
+	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	/*
+	 * For now there is no hardware with non uniform maximum block size
+	 * across all of the device channels, so we set the maximum segment
+	 * size as the block size found for the very first channel.
+	 */
+	dma_set_max_seg_size(dw->dma.dev, dw->chan[0].block_size);
+
+	ret = dma_async_device_register(&dw->dma);
+	if (ret)
+		goto err_dma_register;
 
 	dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n",
-		 nr_channels);
+		 pdata->nr_channels);
 
-	dma_async_device_register(&dw->dma);
+	pm_runtime_put_sync_suspend(chip->dev);
 
 	return 0;
+
+err_dma_register:
+	free_irq(chip->irq, dw);
+err_pdata:
+	pm_runtime_put_sync_suspend(chip->dev);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dw_dma_probe);
 
-int dw_dma_remove(struct dw_dma_chip *chip)
+int do_dma_remove(struct dw_dma_chip *chip)
 {
 	struct dw_dma		*dw = chip->dw;
 	struct dw_dma_chan	*dwc, *_dwc;
 
-	dw_dma_off(dw);
+	pm_runtime_get_sync(chip->dev);
+
+	do_dw_dma_off(dw);
 	dma_async_device_unregister(&dw->dma);
 
+	free_irq(chip->irq, dw);
 	tasklet_kill(&dw->tasklet);
 
 	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
@@ -1685,46 +1378,29 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 	}
 
+	pm_runtime_put_sync_suspend(chip->dev);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_remove);
-
-void dw_dma_shutdown(struct dw_dma_chip *chip)
-{
-	struct dw_dma *dw = chip->dw;
-
-	dw_dma_off(dw);
-	clk_disable_unprepare(dw->clk);
-}
-EXPORT_SYMBOL_GPL(dw_dma_shutdown);
 
-#ifdef CONFIG_PM_SLEEP
-
-int dw_dma_suspend(struct dw_dma_chip *chip)
+int do_dw_dma_disable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
-	dw_dma_off(dw);
-	clk_disable_unprepare(dw->clk);
-
+	dw->disable(dw);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_suspend);
+EXPORT_SYMBOL_GPL(do_dw_dma_disable);
 
-int dw_dma_resume(struct dw_dma_chip *chip)
+int do_dw_dma_enable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
-	clk_prepare_enable(dw->clk);
-	dma_writel(dw, CFG, DW_CFG_DMA_EN);
-
+	dw->enable(dw);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_resume);
-
-#endif /* CONFIG_PM_SLEEP */
+EXPORT_SYMBOL_GPL(do_dw_dma_enable);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");