Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dmaengine updates from Vinod Koul:
 "This is fairly big pull by my standards as I had missed last merge
  window.  So we have the support for device tree for slave-dmaengine,
  large updates to dw_dmac driver from Andy for reusing on different
  architectures.  Along with this we have fixes on bunch of the drivers"

Fix up trivial conflicts, usually due to #include line movement next to
each other.

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (111 commits)
  Revert "ARM: SPEAr13xx: Pass DW DMAC platform data from DT"
  ARM: dts: pl330: Add #dma-cells for generic dma binding support
  DMA: PL330: Register the DMA controller with the generic DMA helpers
  DMA: PL330: Add xlate function
  DMA: PL330: Add new pl330 filter for DT case.
  dma: tegra20-apb-dma: remove unnecessary assignment
  edma: do not waste memory for dma_mask
  dma: coh901318: set residue only if dma is in progress
  dma: coh901318: avoid unbalanced locking
  dmaengine.h: remove redundant else keyword
  dma: of-dma: protect list write operation by spin_lock
  dmaengine: ste_dma40: do not remove descriptors for cyclic transfers
  dma: of-dma.c: fix memory leakage
  dw_dmac: apply default dma_mask if needed
  dmaengine: ioat - fix spare sparse complain
  dmaengine: move drivers/of/dma.c -> drivers/dma/of-dma.c
  ioatdma: fix race between updating ioat->head and IOAT_COMPLETION_PENDING
  dw_dmac: add support for Lynxpoint DMA controllers
  dw_dmac: return proper residue value
  dw_dmac: fill individual length of descriptor
  ...

35 files changed, 1701 insertions, 632 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 40179e7..80b6997 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -51,7 +51,7 @@ config ASYNC_TX_ENABLE_CHANNEL_SWITCH
 
 config AMBA_PL08X
 	bool "ARM PrimeCell PL080 or PL081 support"
-	depends on ARM_AMBA && EXPERIMENTAL
+	depends on ARM_AMBA
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -83,7 +83,6 @@ config INTEL_IOP_ADMA
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA support"
-	depends on HAVE_CLK
 	select DMA_ENGINE
 	default y if CPU_AT32AP7000
 	help
@@ -215,8 +214,8 @@ config TIMB_DMA
 	  Enable support for the Timberdale FPGA DMA engine.
 
 config SIRF_DMA
-	tristate "CSR SiRFprimaII DMA support"
-	depends on ARCH_PRIMA2
+	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
+	depends on ARCH_SIRF
 	select DMA_ENGINE
 	help
 	  Enable support for the CSR SiRFprimaII DMA engine.
@@ -328,6 +327,10 @@ config DMA_ENGINE
 config DMA_VIRTUAL_CHANNELS
 	tristate
 
+config DMA_OF
+	def_bool y
+	depends on OF
+
 comment "DMA Clients"
 	depends on DMA_ENGINE
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 642d967..488e3ff 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -3,6 +3,8 @@ ccflags-$(CONFIG_DMADEVICES_VDEBUG) += -DVERBOSE_DEBUG
 
 obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
 obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
+obj-$(CONFIG_DMA_OF) += of-dma.o
+
 obj-$(CONFIG_NET_DMA) += iovlock.o
 obj-$(CONFIG_INTEL_MID_DMAC) += intel_mid_dma.o
 obj-$(CONFIG_DMATEST) += dmatest.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index d1cc579..8bad254 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -83,7 +83,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <asm/hardware/pl080.h>
+#include <linux/amba/pl080.h>
 
 #include "dmaengine.h"
 #include "virt-dma.h"
@@ -1096,15 +1096,9 @@ static void pl08x_free_txd_list(struct pl08x_driver_data *pl08x,
 				struct pl08x_dma_chan *plchan)
 {
 	LIST_HEAD(head);
-	struct pl08x_txd *txd;
 
 	vchan_get_all_descriptors(&plchan->vc, &head);
-
-	while (!list_empty(&head)) {
-		txd = list_first_entry(&head, struct pl08x_txd, vd.node);
-		list_del(&txd->vd.node);
-		pl08x_desc_free(&txd->vd);
-	}
+	vchan_dma_desc_free_list(&plchan->vc, &head);
 }
 
 /*
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 13a02f4..6e13f26 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -778,7 +778,7 @@ err:
  */
 static int
 atc_dma_cyclic_check_values(unsigned int reg_width, dma_addr_t buf_addr,
-		size_t period_len, enum dma_transfer_direction direction)
+		size_t period_len)
 {
 	if (period_len > (ATC_BTSIZE_MAX << reg_width))
 		goto err_out;
@@ -786,8 +786,6 @@ atc_dma_cyclic_check_values(unsigned int reg_width, dma_addr_t buf_addr,
 		goto err_out;
 	if (unlikely(buf_addr & ((1 << reg_width) - 1)))
 		goto err_out;
-	if (unlikely(!(direction & (DMA_DEV_TO_MEM | DMA_MEM_TO_DEV))))
-		goto err_out;
 
 	return 0;
 
@@ -886,14 +884,16 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 		return NULL;
 	}
 
+	if (unlikely(!is_slave_direction(direction)))
+		goto err_out;
+
 	if (sconfig->direction == DMA_MEM_TO_DEV)
 		reg_width = convert_buswidth(sconfig->dst_addr_width);
 	else
 		reg_width = convert_buswidth(sconfig->src_addr_width);
 
 	/* Check for too big/unaligned periods and unaligned DMA buffer */
-	if (atc_dma_cyclic_check_values(reg_width, buf_addr,
-					period_len, direction))
+	if (atc_dma_cyclic_check_values(reg_width, buf_addr, period_len))
 		goto err_out;
 
 	/* build cyclic linked list */
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 116e4ad..0eb3c13 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -369,10 +369,10 @@ static void vdbg_dump_regs(struct at_dma_chan *atchan) {}
 
 static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
 {
-	dev_printk(KERN_CRIT, chan2dev(&atchan->chan_common),
-			"  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
-			lli->saddr, lli->daddr,
-			lli->ctrla, lli->ctrlb, lli->dscr);
+	dev_crit(chan2dev(&atchan->chan_common),
+		 "  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
+		 lli->saddr, lli->daddr,
+		 lli->ctrla, lli->ctrlb, lli->dscr);
 }
 
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index a2f079a..797940e 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2355,7 +2355,9 @@ coh901318_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	/* FIXME: should be conditional on ret != DMA_SUCCESS? */
+	if (ret == DMA_SUCCESS)
+		return ret;
+
 	dma_set_residue(txstate, coh901318_get_bytes_left(chan));
 
 	if (ret == DMA_IN_PROGRESS && cohc->stopped)
diff --git a/drivers/dma/coh901318_lli.c b/drivers/dma/coh901318_lli.c
index 3e96610..702112d 100644
--- a/drivers/dma/coh901318_lli.c
+++ b/drivers/dma/coh901318_lli.c
@@ -61,7 +61,7 @@ coh901318_lli_alloc(struct coh901318_pool *pool, unsigned int len)
 	dma_addr_t phy;
 
 	if (len == 0)
-		goto err;
+		return NULL;
 
 	spin_lock(&pool->lock);
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a815d44..242b8c0 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -62,6 +62,7 @@
 #include <linux/rculist.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
+#include <linux/of_dma.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDR(dma_idr);
@@ -266,7 +267,10 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 			pr_err("%s: timeout!\n", __func__);
 			return DMA_ERROR;
 		}
-	} while (status == DMA_IN_PROGRESS);
+		if (status != DMA_IN_PROGRESS)
+			break;
+		cpu_relax();
+	} while (1);
 
 	return status;
 }
@@ -546,6 +550,21 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v
 }
 EXPORT_SYMBOL_GPL(__dma_request_channel);
 
+/**
+ * dma_request_slave_channel - try to allocate an exclusive slave channel
+ * @dev:	pointer to client device structure
+ * @name:	slave channel name
+ */
+struct dma_chan *dma_request_slave_channel(struct device *dev, char *name)
+{
+	/* If device-tree is present get slave info from here */
+	if (dev->of_node)
+		return of_dma_request_slave_channel(dev->of_node, name);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(dma_request_slave_channel);
+
 void dma_release_channel(struct dma_chan *chan)
 {
 	mutex_lock(&dma_list_mutex);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 64b048d..a2c8904 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -242,6 +242,13 @@ static inline void unmap_dst(struct device *dev, dma_addr_t *addr, size_t len,
 		dma_unmap_single(dev, addr[count], len, DMA_BIDIRECTIONAL);
 }
 
+static unsigned int min_odd(unsigned int x, unsigned int y)
+{
+	unsigned int val = min(x, y);
+
+	return val % 2 ? val : val - 1;
+}
+
 /*
  * This function repeatedly tests DMA transfers of various lengths and
  * offsets for a given operation type until it is told to exit by
@@ -262,6 +269,7 @@ static int dmatest_func(void *data)
 	struct dmatest_thread	*thread = data;
 	struct dmatest_done	done = { .wait = &done_wait };
 	struct dma_chan		*chan;
+	struct dma_device	*dev;
 	const char		*thread_name;
 	unsigned int		src_off, dst_off, len;
 	unsigned int		error_count;
@@ -283,13 +291,16 @@ static int dmatest_func(void *data)
 
 	smp_rmb();
 	chan = thread->chan;
+	dev = chan->device;
 	if (thread->type == DMA_MEMCPY)
 		src_cnt = dst_cnt = 1;
 	else if (thread->type == DMA_XOR) {
-		src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
+		/* force odd to ensure dst = src */
+		src_cnt = min_odd(xor_sources | 1, dev->max_xor);
 		dst_cnt = 1;
 	} else if (thread->type == DMA_PQ) {
-		src_cnt = pq_sources | 1; /* force odd to ensure dst = src */
+		/* force odd to ensure dst = src */
+		src_cnt = min_odd(pq_sources | 1, dma_maxpq(dev, 0));
 		dst_cnt = 2;
 		for (i = 0; i < src_cnt; i++)
 			pq_coefs[i] = 1;
@@ -327,7 +338,6 @@ static int dmatest_func(void *data)
 
 	while (!kthread_should_stop()
 	       && !(iterations && total_tests >= iterations)) {
-		struct dma_device *dev = chan->device;
 		struct dma_async_tx_descriptor *tx = NULL;
 		dma_addr_t dma_srcs[src_cnt];
 		dma_addr_t dma_dsts[dst_cnt];
@@ -526,7 +536,9 @@ err_srcs:
 			thread_name, total_tests, failed_tests, ret);
 
 	/* terminate all transfers on specified channels */
-	chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+	if (ret)
+		dmaengine_terminate_all(chan);
+
 	if (iterations > 0)
 		while (!kthread_should_stop()) {
 			DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait_dmatest_exit);
@@ -551,7 +563,7 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 	}
 
 	/* terminate all transfers on specified channels */
-	dtc->chan->device->device_control(dtc->chan, DMA_TERMINATE_ALL, 0);
+	dmaengine_terminate_all(dtc->chan);
 
 	kfree(dtc);
 }
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index b33d1f6..51c3ea2 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -1,6 +1,5 @@
 /*
- * Driver for the Synopsys DesignWare DMA Controller (aka DMACA on
- * AVR32 systems.)
+ * Core driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007-2008 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
@@ -9,11 +8,13 @@
  * 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>
+#include <linux/dmapool.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -47,15 +48,32 @@ static inline unsigned int dwc_get_sms(struct dw_dma_slave *slave)
 	return slave ? slave->src_master : 1;
 }
 
+#define SRC_MASTER	0
+#define DST_MASTER	1
+
+static inline unsigned int dwc_get_master(struct dma_chan *chan, int master)
+{
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	struct dw_dma_slave *dws = chan->private;
+	unsigned int m;
+
+	if (master == SRC_MASTER)
+		m = dwc_get_sms(dws);
+	else
+		m = dwc_get_dms(dws);
+
+	return min_t(unsigned int, dw->nr_masters - 1, m);
+}
+
 #define DWC_DEFAULT_CTLLO(_chan) ({				\
-		struct dw_dma_slave *__slave = (_chan->private);	\
 		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
 		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
-		int _dms = dwc_get_dms(__slave);		\
-		int _sms = dwc_get_sms(__slave);		\
-		u8 _smsize = __slave ? _sconfig->src_maxburst :	\
+		bool _is_slave = is_slave_direction(_dwc->direction);	\
+		int _dms = dwc_get_master(_chan, DST_MASTER);		\
+		int _sms = dwc_get_master(_chan, SRC_MASTER);		\
+		u8 _smsize = _is_slave ? _sconfig->src_maxburst :	\
 			DW_DMA_MSIZE_16;			\
-		u8 _dmsize = __slave ? _sconfig->dst_maxburst :	\
+		u8 _dmsize = _is_slave ? _sconfig->dst_maxburst :	\
 			DW_DMA_MSIZE_16;			\
 								\
 		(DWC_CTLL_DST_MSIZE(_dmsize)			\
@@ -73,15 +91,14 @@ static inline unsigned int dwc_get_sms(struct dw_dma_slave *slave)
  */
 #define NR_DESCS_PER_CHANNEL	64
 
-/*----------------------------------------------------------------------*/
+static inline unsigned int dwc_get_data_width(struct dma_chan *chan, int master)
+{
+	struct dw_dma *dw = to_dw_dma(chan->device);
 
-/*
- * Because we're not relying on writeback from the controller (it may not
- * even be configured into the core!) we don't need to use dma_pool.  These
- * descriptors -- and associated data -- are cacheable.  We do need to make
- * sure their dcache entries are written back before handing them off to
- * the controller, though.
- */
+	return dw->data_width[dwc_get_master(chan, master)];
+}
+
+/*----------------------------------------------------------------------*/
 
 static struct device *chan2dev(struct dma_chan *chan)
 {
@@ -94,7 +111,7 @@ static struct device *chan2parent(struct dma_chan *chan)
 
 static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 {
-	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
+	return to_dw_desc(dwc->active_list.next);
 }
 
 static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
@@ -121,19 +138,6 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 	return ret;
 }
 
-static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
-{
-	struct dw_desc	*child;
-
-	list_for_each_entry(child, &desc->tx_list, desc_node)
-		dma_sync_single_for_cpu(chan2parent(&dwc->chan),
-				child->txd.phys, sizeof(child->lli),
-				DMA_TO_DEVICE);
-	dma_sync_single_for_cpu(chan2parent(&dwc->chan),
-			desc->txd.phys, sizeof(desc->lli),
-			DMA_TO_DEVICE);
-}
-
 /*
  * Move a descriptor, including any children, to the free list.
  * `desc' must not be on any lists.
@@ -145,8 +149,6 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	if (desc) {
 		struct dw_desc *child;
 
-		dwc_sync_desc_for_cpu(dwc, desc);
-
 		spin_lock_irqsave(&dwc->lock, flags);
 		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dwc->chan),
@@ -179,9 +181,9 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 		cfghi = dws->cfg_hi;
 		cfglo |= dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
 	} else {
-		if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+		if (dwc->direction == DMA_MEM_TO_DEV)
 			cfghi = DWC_CFGH_DST_PER(dwc->dma_sconfig.slave_id);
-		else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM)
+		else if (dwc->direction == DMA_DEV_TO_MEM)
 			cfghi = DWC_CFGH_SRC_PER(dwc->dma_sconfig.slave_id);
 	}
 
@@ -223,7 +225,6 @@ static inline void dwc_dump_chan_regs(struct dw_dma_chan *dwc)
 		channel_readl(dwc, CTL_LO));
 }
 
-
 static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
 	channel_clear_bit(dw, CH_EN, dwc->mask);
@@ -249,6 +250,9 @@ static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
 	channel_writel(dwc, CTL_LO, ctllo);
 	channel_writel(dwc, CTL_HI, desc->lli.ctlhi);
 	channel_set_bit(dw, CH_EN, dwc->mask);
+
+	/* Move pointer to next descriptor */
+	dwc->tx_node_active = dwc->tx_node_active->next;
 }
 
 /* Called with dwc->lock held and bh disabled */
@@ -279,9 +283,10 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 
 		dwc_initialize(dwc);
 
-		dwc->tx_list = &first->tx_list;
-		dwc->tx_node_active = first->tx_list.next;
+		dwc->residue = first->total_len;
+		dwc->tx_node_active = &first->tx_list;
 
+		/* Submit first block */
 		dwc_do_single_block(dwc, first);
 
 		return;
@@ -317,8 +322,6 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 		param = txd->callback_param;
 	}
 
-	dwc_sync_desc_for_cpu(dwc, desc);
-
 	/* async_tx_ack */
 	list_for_each_entry(child, &desc->tx_list, desc_node)
 		async_tx_ack(&child->txd);
@@ -327,29 +330,29 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
-	if (!dwc->chan.private) {
+	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->len, DMA_FROM_DEVICE);
+					desc->total_len, DMA_FROM_DEVICE);
 			else
 				dma_unmap_page(parent, desc->lli.dar,
-						desc->len, DMA_FROM_DEVICE);
+					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->len, DMA_TO_DEVICE);
+					desc->total_len, DMA_TO_DEVICE);
 			else
 				dma_unmap_page(parent, desc->lli.sar,
-						desc->len, DMA_TO_DEVICE);
+					desc->total_len, DMA_TO_DEVICE);
 		}
 	}
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
-	if (callback_required && callback)
+	if (callback)
 		callback(param);
 }
 
@@ -384,6 +387,15 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		dwc_descriptor_complete(dwc, desc, true);
 }
 
+/* Returns how many bytes were already received from source */
+static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
+{
+	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));
+}
+
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
 	dma_addr_t llp;
@@ -399,6 +411,39 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	if (status_xfer & dwc->mask) {
 		/* Everything we've submitted is done */
 		dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+		if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+			struct list_head *head, *active = dwc->tx_node_active;
+
+			/*
+			 * We are inside first active descriptor.
+			 * Otherwise something is really wrong.
+			 */
+			desc = dwc_first_active(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;
+
+				child = to_dw_desc(active);
+
+				/* Submit next block */
+				dwc_do_single_block(dwc, child);
+
+				spin_unlock_irqrestore(&dwc->lock, flags);
+				return;
+			}
+
+			/* We are done here */
+			clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+		}
+
+		dwc->residue = 0;
+
 		spin_unlock_irqrestore(&dwc->lock, flags);
 
 		dwc_complete_all(dw, dwc);
@@ -406,6 +451,13 @@ 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;
+	}
+
+	if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+		dev_vdbg(chan2dev(&dwc->chan), "%s: soft LLP mode\n", __func__);
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		return;
 	}
@@ -414,6 +466,9 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 			(unsigned long long)llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
+		/* initial residue value */
+		dwc->residue = desc->total_len;
+
 		/* check first descriptors addr */
 		if (desc->txd.phys == llp) {
 			spin_unlock_irqrestore(&dwc->lock, flags);
@@ -423,16 +478,21 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		/* check first descriptors llp */
 		if (desc->lli.llp == llp) {
 			/* This one is currently in progress */
+			dwc->residue -= dwc_get_sent(dwc);
 			spin_unlock_irqrestore(&dwc->lock, flags);
 			return;
 		}
 
-		list_for_each_entry(child, &desc->tx_list, desc_node)
+		dwc->residue -= desc->len;
+		list_for_each_entry(child, &desc->tx_list, desc_node) {
 			if (child->lli.llp == llp) {
 				/* Currently in progress */
+				dwc->residue -= dwc_get_sent(dwc);
 				spin_unlock_irqrestore(&dwc->lock, flags);
 				return;
 			}
+			dwc->residue -= child->len;
+		}
 
 		/*
 		 * No descriptors so far seem to be in progress, i.e.
@@ -458,9 +518,8 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 
 static inline void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
 {
-	dev_printk(KERN_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);
+	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);
 }
 
 static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -488,16 +547,14 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		dwc_dostart(dwc, dwc_first_active(dwc));
 
 	/*
-	 * KERN_CRITICAL may seem harsh, but since this only happens
+	 * WARN may seem harsh, but since this only happens
 	 * when someone submits a bad physical address in a
 	 * descriptor, we should consider ourselves lucky that the
 	 * controller flagged an error instead of scribbling over
 	 * random memory locations.
 	 */
-	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
-			"Bad descriptor submitted for DMA!\n");
-	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
-			"  cookie: %d\n", bad_desc->txd.cookie);
+	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);
 	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		dwc_dump_lli(dwc, &child->lli);
@@ -598,36 +655,8 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_handle_cyclic(dw, dwc, status_err, status_xfer);
 		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
-		else if (status_xfer & (1 << i)) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&dwc->lock, flags);
-			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
-				if (dwc->tx_node_active != dwc->tx_list) {
-					struct dw_desc *desc =
-						list_entry(dwc->tx_node_active,
-							   struct dw_desc,
-							   desc_node);
-
-					dma_writel(dw, CLEAR.XFER, dwc->mask);
-
-					/* move pointer to next descriptor */
-					dwc->tx_node_active =
-						dwc->tx_node_active->next;
-
-					dwc_do_single_block(dwc, desc);
-
-					spin_unlock_irqrestore(&dwc->lock, flags);
-					continue;
-				} else {
-					/* we are done here */
-					clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
-				}
-			}
-			spin_unlock_irqrestore(&dwc->lock, flags);
-
+		else if (status_xfer & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
-		}
 	}
 
 	/*
@@ -709,7 +738,6 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		size_t len, unsigned long flags)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	struct dw_dma_slave	*dws = chan->private;
 	struct dw_desc		*desc;
 	struct dw_desc		*first;
 	struct dw_desc		*prev;
@@ -730,8 +758,10 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		return NULL;
 	}
 
-	data_width = min_t(unsigned int, dwc->dw->data_width[dwc_get_sms(dws)],
-					 dwc->dw->data_width[dwc_get_dms(dws)]);
+	dwc->direction = DMA_MEM_TO_MEM;
+
+	data_width = min_t(unsigned int, dwc_get_data_width(chan, SRC_MASTER),
+			   dwc_get_data_width(chan, DST_MASTER));
 
 	src_width = dst_width = min_t(unsigned int, data_width,
 				      dwc_fast_fls(src | dest | len));
@@ -756,32 +786,25 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		desc->lli.dar = dest + offset;
 		desc->lli.ctllo = ctllo;
 		desc->lli.ctlhi = xfer_count;
+		desc->len = xfer_count << src_width;
 
 		if (!first) {
 			first = desc;
 		} else {
 			prev->lli.llp = desc->txd.phys;
-			dma_sync_single_for_device(chan2parent(chan),
-					prev->txd.phys, sizeof(prev->lli),
-					DMA_TO_DEVICE);
 			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;
 
 	prev->lli.llp = 0;
-	dma_sync_single_for_device(chan2parent(chan),
-			prev->txd.phys, sizeof(prev->lli),
-			DMA_TO_DEVICE);
-
 	first->txd.flags = flags;
-	first->len = len;
+	first->total_len = len;
 
 	return &first->txd;
 
@@ -796,7 +819,6 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned long flags, void *context)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	struct dw_dma_slave	*dws = chan->private;
 	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
 	struct dw_desc		*prev;
 	struct dw_desc		*first;
@@ -811,9 +833,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
-	if (unlikely(!dws || !sg_len))
+	if (unlikely(!is_slave_direction(direction) || !sg_len))
 		return NULL;
 
+	dwc->direction = direction;
+
 	prev = first = NULL;
 
 	switch (direction) {
@@ -828,7 +852,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
 			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
 
-		data_width = dwc->dw->data_width[dwc_get_sms(dws)];
+		data_width = dwc_get_data_width(chan, SRC_MASTER);
 
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
@@ -861,15 +885,12 @@ slave_sg_todev_fill_desc:
 			}
 
 			desc->lli.ctlhi = dlen >> mem_width;
+			desc->len = dlen;
 
 			if (!first) {
 				first = desc;
 			} else {
 				prev->lli.llp = desc->txd.phys;
-				dma_sync_single_for_device(chan2parent(chan),
-						prev->txd.phys,
-						sizeof(prev->lli),
-						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
 						&first->tx_list);
 			}
@@ -891,7 +912,7 @@ slave_sg_todev_fill_desc:
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
 			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
 
-		data_width = dwc->dw->data_width[dwc_get_dms(dws)];
+		data_width = dwc_get_data_width(chan, DST_MASTER);
 
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
@@ -923,15 +944,12 @@ slave_sg_fromdev_fill_desc:
 				len = 0;
 			}
 			desc->lli.ctlhi = dlen >> reg_width;
+			desc->len = dlen;
 
 			if (!first) {
 				first = desc;
 			} else {
 				prev->lli.llp = desc->txd.phys;
-				dma_sync_single_for_device(chan2parent(chan),
-						prev->txd.phys,
-						sizeof(prev->lli),
-						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
 						&first->tx_list);
 			}
@@ -951,11 +969,7 @@ slave_sg_fromdev_fill_desc:
 		prev->lli.ctllo |= DWC_CTLL_INT_EN;
 
 	prev->lli.llp = 0;
-	dma_sync_single_for_device(chan2parent(chan),
-			prev->txd.phys, sizeof(prev->lli),
-			DMA_TO_DEVICE);
-
-	first->len = total_len;
+	first->total_len = total_len;
 
 	return &first->txd;
 
@@ -985,11 +999,12 @@ set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 {
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 
-	/* Check if it is chan is configured for slave transfers */
-	if (!chan->private)
+	/* Check if chan will be configured for slave transfers */
+	if (!is_slave_direction(sconfig->direction))
 		return -EINVAL;
 
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
+	dwc->direction = sconfig->direction;
 
 	convert_burst(&dwc->dma_sconfig.src_maxburst);
 	convert_burst(&dwc->dma_sconfig.dst_maxburst);
@@ -997,6 +1012,26 @@ set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 	return 0;
 }
 
+static inline void dwc_chan_pause(struct dw_dma_chan *dwc)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+	while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY))
+		cpu_relax();
+
+	dwc->paused = true;
+}
+
+static inline void dwc_chan_resume(struct dw_dma_chan *dwc)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+
+	dwc->paused = false;
+}
+
 static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		       unsigned long arg)
 {
@@ -1004,18 +1039,13 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	struct dw_dma		*dw = to_dw_dma(chan->device);
 	struct dw_desc		*desc, *_desc;
 	unsigned long		flags;
-	u32			cfglo;
 	LIST_HEAD(list);
 
 	if (cmd == DMA_PAUSE) {
 		spin_lock_irqsave(&dwc->lock, flags);
 
-		cfglo = channel_readl(dwc, CFG_LO);
-		channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
-		while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY))
-			cpu_relax();
+		dwc_chan_pause(dwc);
 
-		dwc->paused = true;
 		spin_unlock_irqrestore(&dwc->lock, flags);
 	} else if (cmd == DMA_RESUME) {
 		if (!dwc->paused)
@@ -1023,9 +1053,7 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 
 		spin_lock_irqsave(&dwc->lock, flags);
 
-		cfglo = channel_readl(dwc, CFG_LO);
-		channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
-		dwc->paused = false;
+		dwc_chan_resume(dwc);
 
 		spin_unlock_irqrestore(&dwc->lock, flags);
 	} else if (cmd == DMA_TERMINATE_ALL) {
@@ -1035,7 +1063,7 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 
 		dwc_chan_disable(dw, dwc);
 
-		dwc->paused = false;
+		dwc_chan_resume(dwc);
 
 		/* active_list entries will end up before queued entries */
 		list_splice_init(&dwc->queue, &list);
@@ -1055,6 +1083,21 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	return 0;
 }
 
+static inline u32 dwc_get_residue(struct dw_dma_chan *dwc)
+{
+	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);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+	return residue;
+}
+
 static enum dma_status
 dwc_tx_status(struct dma_chan *chan,
 	      dma_cookie_t cookie,
@@ -1071,7 +1114,7 @@ dwc_tx_status(struct dma_chan *chan,
 	}
 
 	if (ret != DMA_SUCCESS)
-		dma_set_residue(txstate, dwc_first_active(dwc)->len);
+		dma_set_residue(txstate, dwc_get_residue(dwc));
 
 	if (dwc->paused)
 		return DMA_PAUSED;
@@ -1114,22 +1157,22 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	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 = kzalloc(sizeof(struct dw_desc), GFP_KERNEL);
-		if (!desc) {
-			dev_info(chan2dev(chan),
-				"only allocated %d descriptors\n", i);
-			spin_lock_irqsave(&dwc->lock, flags);
-			break;
-		}
+		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 = dma_map_single(chan2parent(chan), &desc->lli,
-				sizeof(desc->lli), DMA_TO_DEVICE);
+		desc->txd.phys = phys;
+
 		dwc_desc_put(dwc, desc);
 
 		spin_lock_irqsave(&dwc->lock, flags);
@@ -1141,6 +1184,11 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	dev_dbg(chan2dev(chan), "%s: allocated %d descriptors\n", __func__, i);
 
 	return i;
+
+err_desc_alloc:
+	dev_info(chan2dev(chan), "only allocated %d descriptors\n", i);
+
+	return i;
 }
 
 static void dwc_free_chan_resources(struct dma_chan *chan)
@@ -1172,14 +1220,56 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
 		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
-		dma_unmap_single(chan2parent(chan), desc->txd.phys,
-				sizeof(desc->lli), DMA_TO_DEVICE);
-		kfree(desc);
+		dma_pool_free(dw->desc_pool, desc, desc->txd.phys);
 	}
 
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
+bool dw_dma_generic_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	static struct dw_dma *last_dw;
+	static char *last_bus_id;
+	int i = -1;
+
+	/*
+	 * dmaengine framework calls this routine for all channels of all dma
+	 * controller, until true is returned. If 'param' bus_id is not
+	 * registered with a dma controller (dw), then there is no need of
+	 * running below function for all channels of dw.
+	 *
+	 * This block of code does this by saving the parameters of last
+	 * failure. If dw and param are same, i.e. trying on same dw with
+	 * different channel, return false.
+	 */
+	if ((last_dw == dw) && (last_bus_id == param))
+		return false;
+	/*
+	 * Return true:
+	 * - If dw_dma's platform data is not filled with slave info, then all
+	 *   dma controllers are fine for transfer.
+	 * - Or if param is NULL
+	 */
+	if (!dw->sd || !param)
+		return true;
+
+	while (++i < dw->sd_count) {
+		if (!strcmp(dw->sd[i].bus_id, param)) {
+			chan->private = &dw->sd[i];
+			last_dw = NULL;
+			last_bus_id = NULL;
+
+			return true;
+		}
+	}
+
+	last_dw = dw;
+	last_bus_id = param;
+	return false;
+}
+EXPORT_SYMBOL(dw_dma_generic_filter);
+
 /* --------------------- Cyclic DMA API extensions -------------------- */
 
 /**
@@ -1299,6 +1389,11 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 
 	retval = ERR_PTR(-EINVAL);
 
+	if (unlikely(!is_slave_direction(direction)))
+		goto out_err;
+
+	dwc->direction = direction;
+
 	if (direction == DMA_MEM_TO_DEV)
 		reg_width = __ffs(sconfig->dst_addr_width);
 	else
@@ -1313,8 +1408,6 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 		goto out_err;
 	if (unlikely(buf_addr & ((1 << reg_width) - 1)))
 		goto out_err;
-	if (unlikely(!(direction & (DMA_MEM_TO_DEV | DMA_DEV_TO_MEM))))
-		goto out_err;
 
 	retval = ERR_PTR(-ENOMEM);
 
@@ -1372,20 +1465,14 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 		desc->lli.ctlhi = (period_len >> reg_width);
 		cdesc->desc[i] = desc;
 
-		if (last) {
+		if (last)
 			last->lli.llp = desc->txd.phys;
-			dma_sync_single_for_device(chan2parent(chan),
-					last->txd.phys, sizeof(last->lli),
-					DMA_TO_DEVICE);
-		}
 
 		last = desc;
 	}
 
 	/* lets make a cyclic list */
 	last->lli.llp = cdesc->desc[0]->txd.phys;
-	dma_sync_single_for_device(chan2parent(chan), last->txd.phys,
-			sizeof(last->lli), DMA_TO_DEVICE);
 
 	dev_dbg(chan2dev(&dwc->chan), "cyclic prepared buf 0x%llx len %zu "
 			"period %zu periods %d\n", (unsigned long long)buf_addr,
@@ -1463,6 +1550,91 @@ static void dw_dma_off(struct dw_dma *dw)
 		dw->chan[i].initialized = false;
 }
 
+#ifdef CONFIG_OF
+static struct dw_dma_platform_data *
+dw_dma_parse_dt(struct platform_device *pdev)
+{
+	struct device_node *sn, *cn, *np = pdev->dev.of_node;
+	struct dw_dma_platform_data *pdata;
+	struct dw_dma_slave *sd;
+	u32 tmp, arr[4];
+
+	if (!np) {
+		dev_err(&pdev->dev, "Missing DT data\n");
+		return NULL;
+	}
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	if (of_property_read_u32(np, "nr_channels", &pdata->nr_channels))
+		return NULL;
+
+	if (of_property_read_bool(np, "is_private"))
+		pdata->is_private = true;
+
+	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
+		pdata->chan_allocation_order = (unsigned char)tmp;
+
+	if (!of_property_read_u32(np, "chan_priority", &tmp))
+		pdata->chan_priority = tmp;
+
+	if (!of_property_read_u32(np, "block_size", &tmp))
+		pdata->block_size = tmp;
+
+	if (!of_property_read_u32(np, "nr_masters", &tmp)) {
+		if (tmp > 4)
+			return NULL;
+
+		pdata->nr_masters = tmp;
+	}
+
+	if (!of_property_read_u32_array(np, "data_width", arr,
+				pdata->nr_masters))
+		for (tmp = 0; tmp < pdata->nr_masters; tmp++)
+			pdata->data_width[tmp] = arr[tmp];
+
+	/* parse slave data */
+	sn = of_find_node_by_name(np, "slave_info");
+	if (!sn)
+		return pdata;
+
+	/* calculate number of slaves */
+	tmp = of_get_child_count(sn);
+	if (!tmp)
+		return NULL;
+
+	sd = devm_kzalloc(&pdev->dev, sizeof(*sd) * tmp, GFP_KERNEL);
+	if (!sd)
+		return NULL;
+
+	pdata->sd = sd;
+	pdata->sd_count = tmp;
+
+	for_each_child_of_node(sn, cn) {
+		sd->dma_dev = &pdev->dev;
+		of_property_read_string(cn, "bus_id", &sd->bus_id);
+		of_property_read_u32(cn, "cfg_hi", &sd->cfg_hi);
+		of_property_read_u32(cn, "cfg_lo", &sd->cfg_lo);
+		if (!of_property_read_u32(cn, "src_master", &tmp))
+			sd->src_master = tmp;
+
+		if (!of_property_read_u32(cn, "dst_master", &tmp))
+			sd->dst_master = tmp;
+		sd++;
+	}
+
+	return pdata;
+}
+#else
+static inline struct dw_dma_platform_data *
+dw_dma_parse_dt(struct platform_device *pdev)
+{
+	return NULL;
+}
+#endif
+
 static int dw_probe(struct platform_device *pdev)
 {
 	struct dw_dma_platform_data *pdata;
@@ -1478,10 +1650,6 @@ static int dw_probe(struct platform_device *pdev)
 	int			err;
 	int			i;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
-		return -EINVAL;
-
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!io)
 		return -EINVAL;
@@ -1494,9 +1662,33 @@ static int dw_probe(struct platform_device *pdev)
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
+	/* Apply default dma_mask if needed */
+	if (!pdev->dev.dma_mask) {
+		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	}
+
 	dw_params = dma_read_byaddr(regs, DW_PARAMS);
 	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
 
+	dev_dbg(&pdev->dev, "DW_PARAMS: 0x%08x\n", dw_params);
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata)
+		pdata = dw_dma_parse_dt(pdev);
+
+	if (!pdata && autocfg) {
+		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+
+		/* 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
@@ -1513,6 +1705,8 @@ static int dw_probe(struct platform_device *pdev)
 	clk_prepare_enable(dw->clk);
 
 	dw->regs = regs;
+	dw->sd = pdata->sd;
+	dw->sd_count = pdata->sd_count;
 
 	/* get hardware configuration parameters */
 	if (autocfg) {
@@ -1544,6 +1738,14 @@ static int dw_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dw);
 
+	/* create a pool of consistent memory blocks for hardware descriptors */
+	dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", &pdev->dev,
+					 sizeof(struct dw_desc), 4, 0);
+	if (!dw->desc_pool) {
+		dev_err(&pdev->dev, "No memory for descriptors dma pool\n");
+		return -ENOMEM;
+	}
+
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
 
 	INIT_LIST_HEAD(&dw->dma.channels);
@@ -1575,7 +1777,7 @@ static int dw_probe(struct platform_device *pdev)
 
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 
-		dwc->dw = dw;
+		dwc->direction = DMA_TRANS_NONE;
 
 		/* hardware configuration */
 		if (autocfg) {
@@ -1584,6 +1786,9 @@ static int dw_probe(struct platform_device *pdev)
 			dwc_params = dma_read_byaddr(regs + r * sizeof(u32),
 						     DWC_PARAMS);
 
+			dev_dbg(&pdev->dev, "DWC_PARAMS[%d]: 0x%08x\n", i,
+					    dwc_params);
+
 			/* Decode maximum block size for given channel. The
 			 * stored 4 bit value represents blocks from 0x00 for 3
 			 * up to 0x0a for 4095. */
@@ -1627,8 +1832,8 @@ static int dw_probe(struct platform_device *pdev)
 
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 
-	printk(KERN_INFO "%s: DesignWare DMA Controller, %d channels\n",
-			dev_name(&pdev->dev), nr_channels);
+	dev_info(&pdev->dev, "DesignWare DMA Controller, %d channels\n",
+		 nr_channels);
 
 	dma_async_device_register(&dw->dma);
 
@@ -1658,7 +1863,7 @@ static void dw_shutdown(struct platform_device *pdev)
 {
 	struct dw_dma	*dw = platform_get_drvdata(pdev);
 
-	dw_dma_off(platform_get_drvdata(pdev));
+	dw_dma_off(dw);
 	clk_disable_unprepare(dw->clk);
 }
 
@@ -1667,7 +1872,7 @@ static int dw_suspend_noirq(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma	*dw = platform_get_drvdata(pdev);
 
-	dw_dma_off(platform_get_drvdata(pdev));
+	dw_dma_off(dw);
 	clk_disable_unprepare(dw->clk);
 
 	return 0;
@@ -1680,6 +1885,7 @@ static int dw_resume_noirq(struct device *dev)
 
 	clk_prepare_enable(dw->clk);
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+
 	return 0;
 }
 
@@ -1700,7 +1906,13 @@ static const struct of_device_id dw_dma_id_table[] = {
 MODULE_DEVICE_TABLE(of, dw_dma_id_table);
 #endif
 
+static const struct platform_device_id dw_dma_ids[] = {
+	{ "INTL9C60", 0 },
+	{ }
+};
+
 static struct platform_driver dw_driver = {
+	.probe		= dw_probe,
 	.remove		= dw_remove,
 	.shutdown	= dw_shutdown,
 	.driver = {
@@ -1708,11 +1920,12 @@ static struct platform_driver dw_driver = {
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_id_table),
 	},
+	.id_table	= dw_dma_ids,
 };
 
 static int __init dw_init(void)
 {
-	return platform_driver_probe(&dw_driver, dw_probe);
+	return platform_driver_register(&dw_driver);
 }
 subsys_initcall(dw_init);
 
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 8896559..88dd8eb 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/dmaengine.h>
 #include <linux/dw_dmac.h>
 
 #define DW_DMA_MAX_NR_CHANNELS	8
@@ -184,15 +185,15 @@ enum dw_dmac_flags {
 };
 
 struct dw_dma_chan {
-	struct dma_chan		chan;
-	void __iomem		*ch_regs;
-	u8			mask;
-	u8			priority;
-	bool			paused;
-	bool			initialized;
+	struct dma_chan			chan;
+	void __iomem			*ch_regs;
+	u8				mask;
+	u8				priority;
+	enum dma_transfer_direction	direction;
+	bool				paused;
+	bool				initialized;
 
 	/* software emulation of the LLP transfers */
-	struct list_head	*tx_list;
 	struct list_head	*tx_node_active;
 
 	spinlock_t		lock;
@@ -202,6 +203,7 @@ struct dw_dma_chan {
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
+	u32			residue;
 	struct dw_cyclic_desc	*cdesc;
 
 	unsigned int		descs_allocated;
@@ -212,9 +214,6 @@ struct dw_dma_chan {
 
 	/* configuration passed via DMA_SLAVE_CONFIG */
 	struct dma_slave_config dma_sconfig;
-
-	/* backlink to dw_dma */
-	struct dw_dma		*dw;
 };
 
 static inline struct dw_dma_chan_regs __iomem *
@@ -236,9 +235,14 @@ static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 struct dw_dma {
 	struct dma_device	dma;
 	void __iomem		*regs;
+	struct dma_pool		*desc_pool;
 	struct tasklet_struct	tasklet;
 	struct clk		*clk;
 
+	/* slave information */
+	struct dw_dma_slave	*sd;
+	unsigned int		sd_count;
+
 	u8			all_chan_mask;
 
 	/* hardware configuration */
@@ -293,8 +297,11 @@ struct dw_desc {
 	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	size_t				len;
+	size_t				total_len;
 };
 
+#define to_dw_desc(h)	list_entry(h, struct dw_desc, desc_node)
+
 static inline struct dw_desc *
 txd_to_dw_desc(struct dma_async_tx_descriptor *txd)
 {
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index f424298..cd7e328 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -69,9 +69,7 @@ struct edma_chan {
 	int				ch_num;
 	bool				alloced;
 	int				slot[EDMA_MAX_SLOTS];
-	dma_addr_t			addr;
-	int				addr_width;
-	int				maxburst;
+	struct dma_slave_config		cfg;
 };
 
 struct edma_cc {
@@ -178,29 +176,14 @@ static int edma_terminate_all(struct edma_chan *echan)
 	return 0;
 }
 
-
 static int edma_slave_config(struct edma_chan *echan,
-	struct dma_slave_config *config)
+	struct dma_slave_config *cfg)
 {
-	if ((config->src_addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES) ||
-	    (config->dst_addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES))
+	if (cfg->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    cfg->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
 		return -EINVAL;
 
-	if (config->direction == DMA_MEM_TO_DEV) {
-		if (config->dst_addr)
-			echan->addr = config->dst_addr;
-		if (config->dst_addr_width)
-			echan->addr_width = config->dst_addr_width;
-		if (config->dst_maxburst)
-			echan->maxburst = config->dst_maxburst;
-	} else if (config->direction == DMA_DEV_TO_MEM) {
-		if (config->src_addr)
-			echan->addr = config->src_addr;
-		if (config->src_addr_width)
-			echan->addr_width = config->src_addr_width;
-		if (config->src_maxburst)
-			echan->maxburst = config->src_maxburst;
-	}
+	memcpy(&echan->cfg, cfg, sizeof(echan->cfg));
 
 	return 0;
 }
@@ -235,6 +218,9 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 	struct edma_chan *echan = to_edma_chan(chan);
 	struct device *dev = chan->device->dev;
 	struct edma_desc *edesc;
+	dma_addr_t dev_addr;
+	enum dma_slave_buswidth dev_width;
+	u32 burst;
 	struct scatterlist *sg;
 	int i;
 	int acnt, bcnt, ccnt, src, dst, cidx;
@@ -243,7 +229,20 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 	if (unlikely(!echan || !sgl || !sg_len))
 		return NULL;
 
-	if (echan->addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+	if (direction == DMA_DEV_TO_MEM) {
+		dev_addr = echan->cfg.src_addr;
+		dev_width = echan->cfg.src_addr_width;
+		burst = echan->cfg.src_maxburst;
+	} else if (direction == DMA_MEM_TO_DEV) {
+		dev_addr = echan->cfg.dst_addr;
+		dev_width = echan->cfg.dst_addr_width;
+		burst = echan->cfg.dst_maxburst;
+	} else {
+		dev_err(dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
 		dev_err(dev, "Undefined slave buswidth\n");
 		return NULL;
 	}
@@ -275,14 +274,14 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 			}
 		}
 
-		acnt = echan->addr_width;
+		acnt = dev_width;
 
 		/*
 		 * If the maxburst is equal to the fifo width, use
 		 * A-synced transfers. This allows for large contiguous
 		 * buffer transfers using only one PaRAM set.
 		 */
-		if (echan->maxburst == 1) {
+		if (burst == 1) {
 			edesc->absync = false;
 			ccnt = sg_dma_len(sg) / acnt / (SZ_64K - 1);
 			bcnt = sg_dma_len(sg) / acnt - ccnt * (SZ_64K - 1);
@@ -302,7 +301,7 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 		 */
 		} else {
 			edesc->absync = true;
-			bcnt = echan->maxburst;
+			bcnt = burst;
 			ccnt = sg_dma_len(sg) / (acnt * bcnt);
 			if (ccnt > (SZ_64K - 1)) {
 				dev_err(dev, "Exceeded max SG segment size\n");
@@ -313,13 +312,13 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 
 		if (direction == DMA_MEM_TO_DEV) {
 			src = sg_dma_address(sg);
-			dst = echan->addr;
+			dst = dev_addr;
 			src_bidx = acnt;
 			src_cidx = cidx;
 			dst_bidx = 0;
 			dst_cidx = 0;
 		} else {
-			src = echan->addr;
+			src = dev_addr;
 			dst = sg_dma_address(sg);
 			src_bidx = 0;
 			src_cidx = 0;
@@ -621,13 +620,11 @@ static struct platform_device *pdev0, *pdev1;
 static const struct platform_device_info edma_dev_info0 = {
 	.name = "edma-dma-engine",
 	.id = 0,
-	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static const struct platform_device_info edma_dev_info1 = {
 	.name = "edma-dma-engine",
 	.id = 1,
-	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static int edma_init(void)
@@ -641,6 +638,8 @@ static int edma_init(void)
 			ret = PTR_ERR(pdev0);
 			goto out;
 		}
+		pdev0->dev.dma_mask = &pdev0->dev.coherent_dma_mask;
+		pdev0->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	}
 
 	if (EDMA_CTLRS == 2) {
@@ -650,6 +649,8 @@ static int edma_init(void)
 			platform_device_unregister(pdev0);
 			ret = PTR_ERR(pdev1);
 		}
+		pdev1->dev.dma_mask = &pdev1->dev.coherent_dma_mask;
+		pdev1->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	}
 
 out:
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index bcfde40..f2bf8c0 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -903,8 +903,7 @@ static int ep93xx_dma_alloc_chan_resources(struct dma_chan *chan)
 			switch (data->port) {
 			case EP93XX_DMA_SSP:
 			case EP93XX_DMA_IDE:
-				if (data->direction != DMA_MEM_TO_DEV &&
-				    data->direction != DMA_DEV_TO_MEM)
+				if (!is_slave_direction(data->direction))
 					return -EINVAL;
 				break;
 			default:
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a68a8b..1879a59 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -833,14 +833,14 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_DEST_UNMAP_SINGLE |
+	flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
 		DMA_PREP_INTERRUPT;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
 						   IOAT_TEST_SIZE, flags);
 	if (!tx) {
 		dev_err(dev, "Self-test prep failed, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 
 	async_tx_ack(tx);
@@ -851,7 +851,7 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test setup failed, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -862,7 +862,7 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 					!= DMA_SUCCESS) {
 		dev_err(dev, "Self-test copy timed out, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
 		dev_err(dev, "Self-test copy failed compare, disabling\n");
@@ -870,6 +870,9 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 		goto free_resources;
 	}
 
+unmap_dma:
+	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+	dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
 free_resources:
 	dma->device_free_chan_resources(dma_chan);
 out:
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 087935f..53a4cbb 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -97,6 +97,7 @@ struct ioat_chan_common {
 	#define IOAT_KOBJ_INIT_FAIL 3
 	#define IOAT_RESHAPE_PENDING 4
 	#define IOAT_RUN 5
+	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
 	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
 	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 82d4e30..b925e1b 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -269,61 +269,22 @@ static void ioat2_restart_channel(struct ioat2_dma_chan *ioat)
 	__ioat2_restart_chan(ioat);
 }
 
-void ioat2_timer_event(unsigned long data)
+static void check_active(struct ioat2_dma_chan *ioat)
 {
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
 	struct ioat_chan_common *chan = &ioat->base;
 
-	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		dma_addr_t phys_complete;
-		u64 status;
-
-		status = ioat_chansts(chan);
-
-		/* when halted due to errors check for channel
-		 * programming errors before advancing the completion state
-		 */
-		if (is_ioat_halted(status)) {
-			u32 chanerr;
-
-			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-			dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
-				__func__, chanerr);
-			if (test_bit(IOAT_RUN, &chan->state))
-				BUG_ON(is_ioat_bug(chanerr));
-			else /* we never got off the ground */
-				return;
-		}
-
-		/* if we haven't made progress and we have already
-		 * acknowledged a pending completion once, then be more
-		 * forceful with a restart
-		 */
-		spin_lock_bh(&chan->cleanup_lock);
-		if (ioat_cleanup_preamble(chan, &phys_complete)) {
-			__cleanup(ioat, phys_complete);
-		} else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
-			spin_lock_bh(&ioat->prep_lock);
-			ioat2_restart_channel(ioat);
-			spin_unlock_bh(&ioat->prep_lock);
-		} else {
-			set_bit(IOAT_COMPLETION_ACK, &chan->state);
-			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		}
-		spin_unlock_bh(&chan->cleanup_lock);
-	} else {
-		u16 active;
+	if (ioat2_ring_active(ioat)) {
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		return;
+	}
 
+	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &chan->state))
+		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	else if (ioat->alloc_order > ioat_get_alloc_order()) {
 		/* if the ring is idle, empty, and oversized try to step
 		 * down the size
 		 */
-		spin_lock_bh(&chan->cleanup_lock);
-		spin_lock_bh(&ioat->prep_lock);
-		active = ioat2_ring_active(ioat);
-		if (active == 0 && ioat->alloc_order > ioat_get_alloc_order())
-			reshape_ring(ioat, ioat->alloc_order-1);
-		spin_unlock_bh(&ioat->prep_lock);
-		spin_unlock_bh(&chan->cleanup_lock);
+		reshape_ring(ioat, ioat->alloc_order - 1);
 
 		/* keep shrinking until we get back to our minimum
 		 * default size
@@ -331,6 +292,60 @@ void ioat2_timer_event(unsigned long data)
 		if (ioat->alloc_order > ioat_get_alloc_order())
 			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
 	}
+
+}
+
+void ioat2_timer_event(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
+	dma_addr_t phys_complete;
+	u64 status;
+
+	status = ioat_chansts(chan);
+
+	/* when halted due to errors check for channel
+	 * programming errors before advancing the completion state
+	 */
+	if (is_ioat_halted(status)) {
+		u32 chanerr;
+
+		chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
+			__func__, chanerr);
+		if (test_bit(IOAT_RUN, &chan->state))
+			BUG_ON(is_ioat_bug(chanerr));
+		else /* we never got off the ground */
+			return;
+	}
+
+	/* if we haven't made progress and we have already
+	 * acknowledged a pending completion once, then be more
+	 * forceful with a restart
+	 */
+	spin_lock_bh(&chan->cleanup_lock);
+	if (ioat_cleanup_preamble(chan, &phys_complete))
+		__cleanup(ioat, phys_complete);
+	else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
+		spin_lock_bh(&ioat->prep_lock);
+		ioat2_restart_channel(ioat);
+		spin_unlock_bh(&ioat->prep_lock);
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	} else {
+		set_bit(IOAT_COMPLETION_ACK, &chan->state);
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	}
+
+
+	if (ioat2_ring_active(ioat))
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	else {
+		spin_lock_bh(&ioat->prep_lock);
+		check_active(ioat);
+		spin_unlock_bh(&ioat->prep_lock);
+	}
+	spin_unlock_bh(&chan->cleanup_lock);
 }
 
 static int ioat2_reset_hw(struct ioat_chan_common *chan)
@@ -404,7 +419,7 @@ static dma_cookie_t ioat2_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
 	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
-	if (!test_and_set_bit(IOAT_COMPLETION_PENDING, &chan->state))
+	if (!test_and_set_bit(IOAT_CHAN_ACTIVE, &chan->state))
 		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
 
 	/* make descriptor updates visible before advancing ioat->head,
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 3e9d669..e8336cc 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -342,61 +342,22 @@ static void ioat3_restart_channel(struct ioat2_dma_chan *ioat)
 	__ioat2_restart_chan(ioat);
 }
 
-static void ioat3_timer_event(unsigned long data)
+static void check_active(struct ioat2_dma_chan *ioat)
 {
-	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
 	struct ioat_chan_common *chan = &ioat->base;
 
-	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		dma_addr_t phys_complete;
-		u64 status;
-
-		status = ioat_chansts(chan);
-
-		/* when halted due to errors check for channel
-		 * programming errors before advancing the completion state
-		 */
-		if (is_ioat_halted(status)) {
-			u32 chanerr;
-
-			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
-			dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
-				__func__, chanerr);
-			if (test_bit(IOAT_RUN, &chan->state))
-				BUG_ON(is_ioat_bug(chanerr));
-			else /* we never got off the ground */
-				return;
-		}
-
-		/* if we haven't made progress and we have already
-		 * acknowledged a pending completion once, then be more
-		 * forceful with a restart
-		 */
-		spin_lock_bh(&chan->cleanup_lock);
-		if (ioat_cleanup_preamble(chan, &phys_complete))
-			__cleanup(ioat, phys_complete);
-		else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
-			spin_lock_bh(&ioat->prep_lock);
-			ioat3_restart_channel(ioat);
-			spin_unlock_bh(&ioat->prep_lock);
-		} else {
-			set_bit(IOAT_COMPLETION_ACK, &chan->state);
-			mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
-		}
-		spin_unlock_bh(&chan->cleanup_lock);
-	} else {
-		u16 active;
+	if (ioat2_ring_active(ioat)) {
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+		return;
+	}
 
+	if (test_and_clear_bit(IOAT_CHAN_ACTIVE, &chan->state))
+		mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
+	else if (ioat->alloc_order > ioat_get_alloc_order()) {
 		/* if the ring is idle, empty, and oversized try to step
 		 * down the size
 		 */
-		spin_lock_bh(&chan->cleanup_lock);
-		spin_lock_bh(&ioat->prep_lock);
-		active = ioat2_ring_active(ioat);
-		if (active == 0 && ioat->alloc_order > ioat_get_alloc_order())
-			reshape_ring(ioat, ioat->alloc_order-1);
-		spin_unlock_bh(&ioat->prep_lock);
-		spin_unlock_bh(&chan->cleanup_lock);
+		reshape_ring(ioat, ioat->alloc_order - 1);
 
 		/* keep shrinking until we get back to our minimum
 		 * default size
@@ -404,6 +365,60 @@ static void ioat3_timer_event(unsigned long data)
 		if (ioat->alloc_order > ioat_get_alloc_order())
 			mod_timer(&chan->timer, jiffies + IDLE_TIMEOUT);
 	}
+
+}
+
+static void ioat3_timer_event(unsigned long data)
+{
+	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
+	dma_addr_t phys_complete;
+	u64 status;
+
+	status = ioat_chansts(chan);
+
+	/* when halted due to errors check for channel
+	 * programming errors before advancing the completion state
+	 */
+	if (is_ioat_halted(status)) {
+		u32 chanerr;
+
+		chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
+			__func__, chanerr);
+		if (test_bit(IOAT_RUN, &chan->state))
+			BUG_ON(is_ioat_bug(chanerr));
+		else /* we never got off the ground */
+			return;
+	}
+
+	/* if we haven't made progress and we have already
+	 * acknowledged a pending completion once, then be more
+	 * forceful with a restart
+	 */
+	spin_lock_bh(&chan->cleanup_lock);
+	if (ioat_cleanup_preamble(chan, &phys_complete))
+		__cleanup(ioat, phys_complete);
+	else if (test_bit(IOAT_COMPLETION_ACK, &chan->state)) {
+		spin_lock_bh(&ioat->prep_lock);
+		ioat3_restart_channel(ioat);
+		spin_unlock_bh(&ioat->prep_lock);
+		spin_unlock_bh(&chan->cleanup_lock);
+		return;
+	} else {
+		set_bit(IOAT_COMPLETION_ACK, &chan->state);
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	}
+
+
+	if (ioat2_ring_active(ioat))
+		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
+	else {
+		spin_lock_bh(&ioat->prep_lock);
+		check_active(ioat);
+		spin_unlock_bh(&ioat->prep_lock);
+	}
+	spin_unlock_bh(&chan->cleanup_lock);
 }
 
 static enum dma_status
@@ -863,6 +878,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	unsigned long tmo;
 	struct device *dev = &device->pdev->dev;
 	struct dma_device *dma = &device->common;
+	u8 op = 0;
 
 	dev_dbg(dev, "%s\n", __func__);
 
@@ -908,18 +924,22 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	}
 
 	/* test xor */
+	op = IOAT_OP_XOR;
+
 	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
 		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
 				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
-				      DMA_PREP_INTERRUPT);
+				      DMA_PREP_INTERRUPT |
+				      DMA_COMPL_SKIP_SRC_UNMAP |
+				      DMA_COMPL_SKIP_DEST_UNMAP);
 
 	if (!tx) {
 		dev_err(dev, "Self-test xor prep failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
 	async_tx_ack(tx);
@@ -930,7 +950,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test xor setup failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -939,9 +959,13 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
 		dev_err(dev, "Self-test xor timed out\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
+	dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
 	dma_sync_single_for_cpu(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
 	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
 		u32 *ptr = page_address(dest);
@@ -957,6 +981,8 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
 		goto free_resources;
 
+	op = IOAT_OP_XOR_VAL;
+
 	/* validate the sources with the destintation page */
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
 		xor_val_srcs[i] = xor_srcs[i];
@@ -969,11 +995,13 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT);
+					  &xor_val_result, DMA_PREP_INTERRUPT |
+					  DMA_COMPL_SKIP_SRC_UNMAP |
+					  DMA_COMPL_SKIP_DEST_UNMAP);
 	if (!tx) {
 		dev_err(dev, "Self-test zero prep failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
 	async_tx_ack(tx);
@@ -984,7 +1012,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test zero setup failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -993,9 +1021,12 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
 		dev_err(dev, "Self-test validate timed out\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
 	if (xor_val_result != 0) {
 		dev_err(dev, "Self-test validate failed compare\n");
 		err = -ENODEV;
@@ -1007,14 +1038,18 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 		goto free_resources;
 
 	/* test memset */
+	op = IOAT_OP_FILL;
+
 	dma_addr = dma_map_page(dev, dest, 0,
 			PAGE_SIZE, DMA_FROM_DEVICE);
 	tx = dma->device_prep_dma_memset(dma_chan, dma_addr, 0, PAGE_SIZE,
-					 DMA_PREP_INTERRUPT);
+					 DMA_PREP_INTERRUPT |
+					 DMA_COMPL_SKIP_SRC_UNMAP |
+					 DMA_COMPL_SKIP_DEST_UNMAP);
 	if (!tx) {
 		dev_err(dev, "Self-test memset prep failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
 	async_tx_ack(tx);
@@ -1025,7 +1060,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test memset setup failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -1034,9 +1069,11 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
 		dev_err(dev, "Self-test memset timed out\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
+	dma_unmap_page(dev, dma_addr, PAGE_SIZE, DMA_FROM_DEVICE);
+
 	for (i = 0; i < PAGE_SIZE/sizeof(u32); i++) {
 		u32 *ptr = page_address(dest);
 		if (ptr[i]) {
@@ -1047,17 +1084,21 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	}
 
 	/* test for non-zero parity sum */
+	op = IOAT_OP_XOR_VAL;
+
 	xor_val_result = 0;
 	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
 		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT);
+					  &xor_val_result, DMA_PREP_INTERRUPT |
+					  DMA_COMPL_SKIP_SRC_UNMAP |
+					  DMA_COMPL_SKIP_DEST_UNMAP);
 	if (!tx) {
 		dev_err(dev, "Self-test 2nd zero prep failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
 	async_tx_ack(tx);
@@ -1068,7 +1109,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test  2nd zero setup failed\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -1077,15 +1118,31 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
 		dev_err(dev, "Self-test 2nd validate timed out\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
 	if (xor_val_result != SUM_CHECK_P_RESULT) {
 		dev_err(dev, "Self-test validate failed compare\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto dma_unmap;
 	}
 
+	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+		dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE);
+
+	goto free_resources;
+dma_unmap:
+	if (op == IOAT_OP_XOR) {
+		dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
+			dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+				       DMA_TO_DEVICE);
+	} else if (op == IOAT_OP_XOR_VAL) {
+		for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++)
+			dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE,
+				       DMA_TO_DEVICE);
+	} else if (op == IOAT_OP_FILL)
+		dma_unmap_page(dev, dma_addr, PAGE_SIZE, DMA_FROM_DEVICE);
 free_resources:
 	dma->device_free_chan_resources(dma_chan);
 out:
@@ -1126,12 +1183,7 @@ static int ioat3_reset_hw(struct ioat_chan_common *chan)
 	chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
 	writel(chanerr, chan->reg_base + IOAT_CHANERR_OFFSET);
 
-	/* -= IOAT ver.3 workarounds =- */
-	/* Write CHANERRMSK_INT with 3E07h to mask out the errors
-	 * that can cause stability issues for IOAT ver.3, and clear any
-	 * pending errors
-	 */
-	pci_write_config_dword(pdev, IOAT_PCI_CHANERRMASK_INT_OFFSET, 0x3e07);
+	/* clear any pending errors */
 	err = pci_read_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, &chanerr);
 	if (err) {
 		dev_err(&pdev->dev, "channel error register unreachable\n");
@@ -1187,6 +1239,26 @@ static bool is_snb_ioat(struct pci_dev *pdev)
 	}
 }
 
+static bool is_ivb_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB0:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB1:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB2:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB3:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB4:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB5:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB6:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB7:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB8:
+	case PCI_DEVICE_ID_INTEL_IOAT_IVB9:
+		return true;
+	default:
+		return false;
+	}
+
+}
+
 int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 {
 	struct pci_dev *pdev = device->pdev;
@@ -1207,7 +1279,7 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
 	dma->device_free_chan_resources = ioat2_free_chan_resources;
 
-	if (is_jf_ioat(pdev) || is_snb_ioat(pdev))
+	if (is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev))
 		dma->copy_align = 6;
 
 	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index d2ff3fd..7cb74c6 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -35,6 +35,17 @@
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */
 #define IOAT_VER_3_2            0x32    /* Version 3.2 */
 
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB0	0x0e20
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB1	0x0e21
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB2	0x0e22
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB3	0x0e23
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB4	0x0e24
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB5	0x0e25
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB6	0x0e26
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB7	0x0e27
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB8	0x0e2e
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB9	0x0e2f
+
 int system_has_dca_enabled(struct pci_dev *pdev);
 
 struct ioat_dma_descriptor {
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
index 4f686c5..71c7ecd 100644
--- a/drivers/dma/ioat/pci.c
+++ b/drivers/dma/ioat/pci.c
@@ -40,17 +40,6 @@ MODULE_VERSION(IOAT_DMA_VERSION);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel Corporation");
 
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB0	0x0e20
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB1	0x0e21
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB2	0x0e22
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB3	0x0e23
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB4	0x0e24
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB5	0x0e25
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB6	0x0e26
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB7	0x0e27
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB8	0x0e2e
-#define PCI_DEVICE_ID_INTEL_IOAT_IVB9	0x0e2f
-
 static struct pci_device_id ioat_pci_tbl[] = {
 	/* I/OAT v1 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT) },
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index eacb8be..7dafb9f 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -936,7 +936,7 @@ static irqreturn_t iop_adma_err_handler(int irq, void *data)
 	struct iop_adma_chan *chan = data;
 	unsigned long status = iop_chan_get_status(chan);
 
-	dev_printk(KERN_ERR, chan->device->common.dev,
+	dev_err(chan->device->common.dev,
 		"error ( %s%s%s%s%s%s%s)\n",
 		iop_is_err_int_parity(status, chan) ? "int_parity " : "",
 		iop_is_err_mcu_abort(status, chan) ? "mcu_abort " : "",
@@ -1017,7 +1017,7 @@ static int iop_adma_memcpy_self_test(struct iop_adma_device *device)
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
 			DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test copy timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1027,7 +1027,7 @@ static int iop_adma_memcpy_self_test(struct iop_adma_device *device)
 	dma_sync_single_for_cpu(&iop_chan->device->pdev->dev, dest_dma,
 		IOP_ADMA_TEST_SIZE, DMA_FROM_DEVICE);
 	if (memcmp(src, dest, IOP_ADMA_TEST_SIZE)) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test copy failed compare, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1117,7 +1117,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
 		DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test xor timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1129,7 +1129,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 	for (i = 0; i < (PAGE_SIZE / sizeof(u32)); i++) {
 		u32 *ptr = page_address(dest);
 		if (ptr[i] != cmp_word) {
-			dev_printk(KERN_ERR, dma_chan->device->dev,
+			dev_err(dma_chan->device->dev,
 				"Self-test xor failed compare, disabling\n");
 			err = -ENODEV;
 			goto free_resources;
@@ -1163,14 +1163,14 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test zero sum timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
 	}
 
 	if (zero_sum_result != 0) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test zero sum failed compare, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1187,7 +1187,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test memset timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1196,7 +1196,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 	for (i = 0; i < PAGE_SIZE/sizeof(u32); i++) {
 		u32 *ptr = page_address(dest);
 		if (ptr[i]) {
-			dev_printk(KERN_ERR, dma_chan->device->dev,
+			dev_err(dma_chan->device->dev,
 				"Self-test memset failed compare, disabling\n");
 			err = -ENODEV;
 			goto free_resources;
@@ -1219,14 +1219,14 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test non-zero sum timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
 	}
 
 	if (zero_sum_result != 1) {
-		dev_printk(KERN_ERR, dma_chan->device->dev,
+		dev_err(dma_chan->device->dev,
 			"Self-test non-zero sum failed compare, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1579,15 +1579,14 @@ static int iop_adma_probe(struct platform_device *pdev)
 			goto err_free_iop_chan;
 	}
 
-	dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: "
-	  "( %s%s%s%s%s%s%s)\n",
-	  dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
-	  dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
-	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
-	  dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "",
-	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
-	  dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
-	  dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
+	dev_info(&pdev->dev, "Intel(R) IOP: ( %s%s%s%s%s%s%s)\n",
+		 dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
+		 dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
+		 dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
+		 dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "",
+		 dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
+		 dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
+		 dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
 	dma_async_device_register(dma_dev);
 	goto out;
@@ -1651,8 +1650,8 @@ static void iop_chan_start_null_memcpy(struct iop_adma_chan *iop_chan)
 		/* run the descriptor */
 		iop_chan_enable(iop_chan);
 	} else
-		dev_printk(KERN_ERR, iop_chan->device->common.dev,
-			 "failed to allocate null descriptor\n");
+		dev_err(iop_chan->device->common.dev,
+			"failed to allocate null descriptor\n");
 	spin_unlock_bh(&iop_chan->lock);
 }
 
@@ -1704,7 +1703,7 @@ static void iop_chan_start_null_xor(struct iop_adma_chan *iop_chan)
 		/* run the descriptor */
 		iop_chan_enable(iop_chan);
 	} else
-		dev_printk(KERN_ERR, iop_chan->device->common.dev,
+		dev_err(iop_chan->device->common.dev,
 			"failed to allocate null descriptor\n");
 	spin_unlock_bh(&iop_chan->lock);
 }
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index 6585537..8c61d17 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1347,7 +1347,7 @@ static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan
 	    chan->chan_id != IDMAC_IC_7)
 		return NULL;
 
-	if (direction != DMA_DEV_TO_MEM && direction != DMA_MEM_TO_DEV) {
+	if (!is_slave_direction(direction)) {
 		dev_err(chan->device->dev, "Invalid DMA direction %d!\n", direction);
 		return NULL;
 	}
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index a5ee37d..2e284a4 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -44,7 +44,6 @@ static void ipu_write_reg(struct ipu *ipu, u32 value, unsigned long reg)
 struct ipu_irq_bank {
 	unsigned int	control;
 	unsigned int	status;
-	spinlock_t	lock;
 	struct ipu	*ipu;
 };
 
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index dc74665..c26699f 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -618,10 +618,8 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 		else if (maxburst == 32)
 			chan->dcmd |= DCMD_BURST32;
 
-		if (cfg) {
-			chan->dir = cfg->direction;
-			chan->drcmr = cfg->slave_id;
-		}
+		chan->dir = cfg->direction;
+		chan->drcmr = cfg->slave_id;
 		chan->dev_addr = addr;
 		break;
 	default:
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index e17fad0..d64ae14 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -210,7 +210,7 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 		break;
 	default:
 		dev_err(mv_chan_to_devp(chan),
-			"error: unsupported operation %d.\n",
+			"error: unsupported operation %d\n",
 			type);
 		BUG();
 		return;
@@ -828,28 +828,22 @@ static void mv_dump_xor_regs(struct mv_xor_chan *chan)
 	u32 val;
 
 	val = __raw_readl(XOR_CONFIG(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"config       0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "config       0x%08x\n", val);
 
 	val = __raw_readl(XOR_ACTIVATION(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"activation   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "activation   0x%08x\n", val);
 
 	val = __raw_readl(XOR_INTR_CAUSE(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"intr cause   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "intr cause   0x%08x\n", val);
 
 	val = __raw_readl(XOR_INTR_MASK(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"intr mask    0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "intr mask    0x%08x\n", val);
 
 	val = __raw_readl(XOR_ERROR_CAUSE(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"error cause  0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "error cause  0x%08x\n", val);
 
 	val = __raw_readl(XOR_ERROR_ADDR(chan));
-	dev_err(mv_chan_to_devp(chan),
-		"error addr   0x%08x.\n", val);
+	dev_err(mv_chan_to_devp(chan), "error addr   0x%08x\n", val);
 }
 
 static void mv_xor_err_interrupt_handler(struct mv_xor_chan *chan,
@@ -862,7 +856,7 @@ static void mv_xor_err_interrupt_handler(struct mv_xor_chan *chan,
 	}
 
 	dev_err(mv_chan_to_devp(chan),
-		"error on chan %d. intr cause 0x%08x.\n",
+		"error on chan %d. intr cause 0x%08x\n",
 		chan->idx, intr_cause);
 
 	mv_dump_xor_regs(chan);
@@ -1052,9 +1046,8 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 		u32 *ptr = page_address(dest);
 		if (ptr[i] != cmp_word) {
 			dev_err(dma_chan->device->dev,
-				"Self-test xor failed compare, disabling."
-				" index %d, data %x, expected %x\n", i,
-				ptr[i], cmp_word);
+				"Self-test xor failed compare, disabling. index %d, data %x, expected %x\n",
+				i, ptr[i], cmp_word);
 			err = -ENODEV;
 			goto free_resources;
 		}
@@ -1194,12 +1187,11 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 			goto err_free_irq;
 	}
 
-	dev_info(&pdev->dev, "Marvell XOR: "
-	  "( %s%s%s%s)\n",
-	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
-	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
-	  dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
-	  dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
+	dev_info(&pdev->dev, "Marvell XOR: ( %s%s%s%s)\n",
+		 dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
+		 dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
+		 dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
+		 dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
 	dma_async_device_register(dma_dev);
 	return mv_chan;
@@ -1253,7 +1245,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 	struct resource *res;
 	int i, ret;
 
-	dev_notice(&pdev->dev, "Marvell XOR driver\n");
+	dev_notice(&pdev->dev, "Marvell shared XOR driver\n");
 
 	xordev = devm_kzalloc(&pdev->dev, sizeof(*xordev), GFP_KERNEL);
 	if (!xordev)
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 9f02e79..8f6d30d3 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -109,7 +109,7 @@ struct mxs_dma_chan {
 	struct dma_chan			chan;
 	struct dma_async_tx_descriptor	desc;
 	struct tasklet_struct		tasklet;
-	int				chan_irq;
+	unsigned int			chan_irq;
 	struct mxs_dma_ccw		*ccw;
 	dma_addr_t			ccw_phys;
 	int				desc_count;
@@ -441,7 +441,7 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
 	struct mxs_dma_ccw *ccw;
 	struct scatterlist *sg;
-	int i, j;
+	u32 i, j;
 	u32 *pio;
 	bool append = flags & DMA_PREP_INTERRUPT;
 	int idx = append ? mxs_chan->desc_count : 0;
@@ -537,8 +537,8 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
-	int num_periods = buf_len / period_len;
-	int i = 0, buf = 0;
+	u32 num_periods = buf_len / period_len;
+	u32 i = 0, buf = 0;
 
 	if (mxs_chan->status == DMA_IN_PROGRESS)
 		return NULL;
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
new file mode 100644
index 0000000..69d04d2
--- /dev/null
+++ b/drivers/dma/of-dma.c
@@ -0,0 +1,267 @@
+/*
+ * Device tree helpers for DMA request / controller
+ *
+ * Based on of_gpio.c
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * 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/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+
+static LIST_HEAD(of_dma_list);
+static DEFINE_SPINLOCK(of_dma_lock);
+
+/**
+ * of_dma_get_controller - Get a DMA controller in DT DMA helpers list
+ * @dma_spec:	pointer to DMA specifier as found in the device tree
+ *
+ * Finds a DMA controller with matching device node and number for dma cells
+ * in a list of registered DMA controllers. If a match is found the use_count
+ * variable is increased and a valid pointer to the DMA data stored is retuned.
+ * A NULL pointer is returned if no match is found.
+ */
+static struct of_dma *of_dma_get_controller(struct of_phandle_args *dma_spec)
+{
+	struct of_dma *ofdma;
+
+	spin_lock(&of_dma_lock);
+
+	if (list_empty(&of_dma_list)) {
+		spin_unlock(&of_dma_lock);
+		return NULL;
+	}
+
+	list_for_each_entry(ofdma, &of_dma_list, of_dma_controllers)
+		if ((ofdma->of_node == dma_spec->np) &&
+		    (ofdma->of_dma_nbcells == dma_spec->args_count)) {
+			ofdma->use_count++;
+			spin_unlock(&of_dma_lock);
+			return ofdma;
+		}
+
+	spin_unlock(&of_dma_lock);
+
+	pr_debug("%s: can't find DMA controller %s\n", __func__,
+		 dma_spec->np->full_name);
+
+	return NULL;
+}
+
+/**
+ * of_dma_put_controller - Decrement use count for a registered DMA controller
+ * @of_dma:	pointer to DMA controller data
+ *
+ * Decrements the use_count variable in the DMA data structure. This function
+ * should be called only when a valid pointer is returned from
+ * of_dma_get_controller() and no further accesses to data referenced by that
+ * pointer are needed.
+ */
+static void of_dma_put_controller(struct of_dma *ofdma)
+{
+	spin_lock(&of_dma_lock);
+	ofdma->use_count--;
+	spin_unlock(&of_dma_lock);
+}
+
+/**
+ * of_dma_controller_register - Register a DMA controller to DT DMA helpers
+ * @np:			device node of DMA controller
+ * @of_dma_xlate:	translation function which converts a phandle
+ *			arguments list into a dma_chan structure
+ * @data		pointer to controller specific data to be used by
+ *			translation function
+ *
+ * Returns 0 on success or appropriate errno value on error.
+ *
+ * Allocated memory should be freed with appropriate of_dma_controller_free()
+ * call.
+ */
+int of_dma_controller_register(struct device_node *np,
+				struct dma_chan *(*of_dma_xlate)
+				(struct of_phandle_args *, struct of_dma *),
+				void *data)
+{
+	struct of_dma	*ofdma;
+	int		nbcells;
+
+	if (!np || !of_dma_xlate) {
+		pr_err("%s: not enough information provided\n", __func__);
+		return -EINVAL;
+	}
+
+	ofdma = kzalloc(sizeof(*ofdma), GFP_KERNEL);
+	if (!ofdma)
+		return -ENOMEM;
+
+	nbcells = be32_to_cpup(of_get_property(np, "#dma-cells", NULL));
+	if (!nbcells) {
+		pr_err("%s: #dma-cells property is missing or invalid\n",
+		       __func__);
+		kfree(ofdma);
+		return -EINVAL;
+	}
+
+	ofdma->of_node = np;
+	ofdma->of_dma_nbcells = nbcells;
+	ofdma->of_dma_xlate = of_dma_xlate;
+	ofdma->of_dma_data = data;
+	ofdma->use_count = 0;
+
+	/* Now queue of_dma controller structure in list */
+	spin_lock(&of_dma_lock);
+	list_add_tail(&ofdma->of_dma_controllers, &of_dma_list);
+	spin_unlock(&of_dma_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_dma_controller_register);
+
+/**
+ * of_dma_controller_free - Remove a DMA controller from DT DMA helpers list
+ * @np:		device node of DMA controller
+ *
+ * Memory allocated by of_dma_controller_register() is freed here.
+ */
+int of_dma_controller_free(struct device_node *np)
+{
+	struct of_dma *ofdma;
+
+	spin_lock(&of_dma_lock);
+
+	if (list_empty(&of_dma_list)) {
+		spin_unlock(&of_dma_lock);
+		return -ENODEV;
+	}
+
+	list_for_each_entry(ofdma, &of_dma_list, of_dma_controllers)
+		if (ofdma->of_node == np) {
+			if (ofdma->use_count) {
+				spin_unlock(&of_dma_lock);
+				return -EBUSY;
+			}
+
+			list_del(&ofdma->of_dma_controllers);
+			spin_unlock(&of_dma_lock);
+			kfree(ofdma);
+			return 0;
+		}
+
+	spin_unlock(&of_dma_lock);
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(of_dma_controller_free);
+
+/**
+ * of_dma_match_channel - Check if a DMA specifier matches name
+ * @np:		device node to look for DMA channels
+ * @name:	channel name to be matched
+ * @index:	index of DMA specifier in list of DMA specifiers
+ * @dma_spec:	pointer to DMA specifier as found in the device tree
+ *
+ * Check if the DMA specifier pointed to by the index in a list of DMA
+ * specifiers, matches the name provided. Returns 0 if the name matches and
+ * a valid pointer to the DMA specifier is found. Otherwise returns -ENODEV.
+ */
+static int of_dma_match_channel(struct device_node *np, char *name, int index,
+				struct of_phandle_args *dma_spec)
+{
+	const char *s;
+
+	if (of_property_read_string_index(np, "dma-names", index, &s))
+		return -ENODEV;
+
+	if (strcmp(name, s))
+		return -ENODEV;
+
+	if (of_parse_phandle_with_args(np, "dmas", "#dma-cells", index,
+				       dma_spec))
+		return -ENODEV;
+
+	return 0;
+}
+
+/**
+ * of_dma_request_slave_channel - Get the DMA slave channel
+ * @np:		device node to get DMA request from
+ * @name:	name of desired channel
+ *
+ * Returns pointer to appropriate dma channel on success or NULL on error.
+ */
+struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
+					      char *name)
+{
+	struct of_phandle_args	dma_spec;
+	struct of_dma		*ofdma;
+	struct dma_chan		*chan;
+	int			count, i;
+
+	if (!np || !name) {
+		pr_err("%s: not enough information provided\n", __func__);
+		return NULL;
+	}
+
+	count = of_property_count_strings(np, "dma-names");
+	if (count < 0) {
+		pr_err("%s: dma-names property missing or empty\n", __func__);
+		return NULL;
+	}
+
+	for (i = 0; i < count; i++) {
+		if (of_dma_match_channel(np, name, i, &dma_spec))
+			continue;
+
+		ofdma = of_dma_get_controller(&dma_spec);
+
+		if (!ofdma)
+			continue;
+
+		chan = ofdma->of_dma_xlate(&dma_spec, ofdma);
+
+		of_dma_put_controller(ofdma);
+
+		of_node_put(dma_spec.np);
+
+		if (chan)
+			return chan;
+	}
+
+	return NULL;
+}
+
+/**
+ * of_dma_simple_xlate - Simple DMA engine translation function
+ * @dma_spec:	pointer to DMA specifier as found in the device tree
+ * @of_dma:	pointer to DMA controller data
+ *
+ * A simple translation function for devices that use a 32-bit value for the
+ * filter_param when calling the DMA engine dma_request_channel() function.
+ * Note that this translation function requires that #dma-cells is equal to 1
+ * and the argument of the dma specifier is the 32-bit filter_param. Returns
+ * pointer to appropriate dma channel on success or NULL on error.
+ */
+struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec,
+						struct of_dma *ofdma)
+{
+	int count = dma_spec->args_count;
+	struct of_dma_filter_info *info = ofdma->of_dma_data;
+
+	if (!info || !info->filter_fn)
+		return NULL;
+
+	if (count != 1)
+		return NULL;
+
+	return dma_request_channel(info->dma_cap, info->filter_fn,
+			&dma_spec->args[0]);
+}
+EXPORT_SYMBOL_GPL(of_dma_simple_xlate);
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 3f26172..d01faeb 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -1029,18 +1029,7 @@ static struct pci_driver pch_dma_driver = {
 #endif
 };
 
-static int __init pch_dma_init(void)
-{
-	return pci_register_driver(&pch_dma_driver);
-}
-
-static void __exit pch_dma_exit(void)
-{
-	pci_unregister_driver(&pch_dma_driver);
-}
-
-module_init(pch_dma_init);
-module_exit(pch_dma_exit);
+module_pci_driver(pch_dma_driver);
 
 MODULE_DESCRIPTION("Intel EG20T PCH / LAPIS Semicon ML7213/ML7223/ML7831 IOH "
 		   "DMA controller driver");
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 80680ee..7181531 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -25,6 +25,7 @@
 #include <linux/amba/pl330.h>
 #include <linux/scatterlist.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 
 #include "dmaengine.h"
 #define PL330_MAX_CHAN		8
@@ -606,6 +607,11 @@ struct dma_pl330_desc {
 	struct dma_pl330_chan *pchan;
 };
 
+struct dma_pl330_filter_args {
+	struct dma_pl330_dmac *pdmac;
+	unsigned int chan_id;
+};
+
 static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
 {
 	if (r && r->xfer_cb)
@@ -2352,6 +2358,16 @@ static void dma_pl330_rqcb(void *token, enum pl330_op_err err)
 	tasklet_schedule(&pch->task);
 }
 
+static bool pl330_dt_filter(struct dma_chan *chan, void *param)
+{
+	struct dma_pl330_filter_args *fargs = param;
+
+	if (chan->device != &fargs->pdmac->ddma)
+		return false;
+
+	return (chan->chan_id == fargs->chan_id);
+}
+
 bool pl330_filter(struct dma_chan *chan, void *param)
 {
 	u8 *peri_id;
@@ -2359,25 +2375,35 @@ bool pl330_filter(struct dma_chan *chan, void *param)
 	if (chan->device->dev->driver != &pl330_driver.drv)
 		return false;
 
-#ifdef CONFIG_OF
-	if (chan->device->dev->of_node) {
-		const __be32 *prop_value;
-		phandle phandle;
-		struct device_node *node;
-
-		prop_value = ((struct property *)param)->value;
-		phandle = be32_to_cpup(prop_value++);
-		node = of_find_node_by_phandle(phandle);
-		return ((chan->private == node) &&
-				(chan->chan_id == be32_to_cpup(prop_value)));
-	}
-#endif
-
 	peri_id = chan->private;
 	return *peri_id == (unsigned)param;
 }
 EXPORT_SYMBOL(pl330_filter);
 
+static struct dma_chan *of_dma_pl330_xlate(struct of_phandle_args *dma_spec,
+						struct of_dma *ofdma)
+{
+	int count = dma_spec->args_count;
+	struct dma_pl330_dmac *pdmac = ofdma->of_dma_data;
+	struct dma_pl330_filter_args fargs;
+	dma_cap_mask_t cap;
+
+	if (!pdmac)
+		return NULL;
+
+	if (count != 1)
+		return NULL;
+
+	fargs.pdmac = pdmac;
+	fargs.chan_id = dma_spec->args[0];
+
+	dma_cap_zero(cap);
+	dma_cap_set(DMA_SLAVE, cap);
+	dma_cap_set(DMA_CYCLIC, cap);
+
+	return dma_request_channel(cap, pl330_dt_filter, &fargs);
+}
+
 static int pl330_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -2866,7 +2892,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pdat = adev->dev.platform_data;
 
 	/* Allocate a new DMAC and its Channels */
-	pdmac = kzalloc(sizeof(*pdmac), GFP_KERNEL);
+	pdmac = devm_kzalloc(&adev->dev, sizeof(*pdmac), GFP_KERNEL);
 	if (!pdmac) {
 		dev_err(&adev->dev, "unable to allocate mem\n");
 		return -ENOMEM;
@@ -2878,13 +2904,9 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pi->mcbufsz = pdat ? pdat->mcbuf_sz : 0;
 
 	res = &adev->res;
-	request_mem_region(res->start, resource_size(res), "dma-pl330");
-
-	pi->base = ioremap(res->start, resource_size(res));
-	if (!pi->base) {
-		ret = -ENXIO;
-		goto probe_err1;
-	}
+	pi->base = devm_request_and_ioremap(&adev->dev, res);
+	if (!pi->base)
+		return -ENXIO;
 
 	amba_set_drvdata(adev, pdmac);
 
@@ -2892,11 +2914,11 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = request_irq(irq, pl330_irq_handler, 0,
 			dev_name(&adev->dev), pi);
 	if (ret)
-		goto probe_err2;
+		return ret;
 
 	ret = pl330_add(pi);
 	if (ret)
-		goto probe_err3;
+		goto probe_err1;
 
 	INIT_LIST_HEAD(&pdmac->desc_pool);
 	spin_lock_init(&pdmac->pool_lock);
@@ -2918,7 +2940,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!pdmac->peripherals) {
 		ret = -ENOMEM;
 		dev_err(&adev->dev, "unable to allocate pdmac->peripherals\n");
-		goto probe_err4;
+		goto probe_err2;
 	}
 
 	for (i = 0; i < num_chan; i++) {
@@ -2962,7 +2984,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = dma_async_device_register(pd);
 	if (ret) {
 		dev_err(&adev->dev, "unable to register DMAC\n");
-		goto probe_err4;
+		goto probe_err2;
 	}
 
 	dev_info(&adev->dev,
@@ -2973,17 +2995,20 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 		pi->pcfg.data_bus_width / 8, pi->pcfg.num_chan,
 		pi->pcfg.num_peri, pi->pcfg.num_events);
 
+	ret = of_dma_controller_register(adev->dev.of_node,
+					 of_dma_pl330_xlate, pdmac);
+	if (ret) {
+		dev_err(&adev->dev,
+		"unable to register DMA to the generic DT DMA helpers\n");
+		goto probe_err2;
+	}
+
 	return 0;
 
-probe_err4:
-	pl330_del(pi);
-probe_err3:
-	free_irq(irq, pi);
 probe_err2:
-	iounmap(pi->base);
+	pl330_del(pi);
 probe_err1:
-	release_mem_region(res->start, resource_size(res));
-	kfree(pdmac);
+	free_irq(irq, pi);
 
 	return ret;
 }
@@ -2993,12 +3018,13 @@ static int pl330_remove(struct amba_device *adev)
 	struct dma_pl330_dmac *pdmac = amba_get_drvdata(adev);
 	struct dma_pl330_chan *pch, *_p;
 	struct pl330_info *pi;
-	struct resource *res;
 	int irq;
 
 	if (!pdmac)
 		return 0;
 
+	of_dma_controller_free(adev->dev.of_node);
+
 	amba_set_drvdata(adev, NULL);
 
 	/* Idle the DMAC */
@@ -3020,13 +3046,6 @@ static int pl330_remove(struct amba_device *adev)
 	irq = adev->irq[0];
 	free_irq(irq, pi);
 
-	iounmap(pi->base);
-
-	res = &adev->res;
-	release_mem_region(res->start, resource_size(res));
-
-	kfree(pdmac);
-
 	return 0;
 }
 
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index f4cd946..4acb85a 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -638,9 +638,6 @@ static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	unsigned long flags;
 	int ret;
 
-	if (!chan)
-		return -EINVAL;
-
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
 		spin_lock_irqsave(&schan->chan_lock, flags);
diff --git a/drivers/dma/sh/shdma.c b/drivers/dma/sh/shdma.c
index 3315e4b..b70709b 100644
--- a/drivers/dma/sh/shdma.c
+++ b/drivers/dma/sh/shdma.c
@@ -326,7 +326,7 @@ static int sh_dmae_set_slave(struct shdma_chan *schan,
 						    shdma_chan);
 	const struct sh_dmae_slave_config *cfg = dmae_find_slave(sh_chan, slave_id);
 	if (!cfg)
-		return -ENODEV;
+		return -ENXIO;
 
 	if (!try)
 		sh_chan->config = cfg;
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 94674a9..1d627e2 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -32,7 +32,9 @@
 #define SIRFSOC_DMA_CH_VALID                    0x140
 #define SIRFSOC_DMA_CH_INT                      0x144
 #define SIRFSOC_DMA_INT_EN                      0x148
+#define SIRFSOC_DMA_INT_EN_CLR			0x14C
 #define SIRFSOC_DMA_CH_LOOP_CTRL                0x150
+#define SIRFSOC_DMA_CH_LOOP_CTRL_CLR            0x15C
 
 #define SIRFSOC_DMA_MODE_CTRL_BIT               4
 #define SIRFSOC_DMA_DIR_CTRL_BIT                5
@@ -76,6 +78,7 @@ struct sirfsoc_dma {
 	struct sirfsoc_dma_chan		channels[SIRFSOC_DMA_CHANNELS];
 	void __iomem			*base;
 	int				irq;
+	bool				is_marco;
 };
 
 #define DRV_NAME	"sirfsoc_dma"
@@ -288,17 +291,67 @@ static int sirfsoc_dma_terminate_all(struct sirfsoc_dma_chan *schan)
 	int cid = schan->chan.chan_id;
 	unsigned long flags;
 
-	writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_INT_EN) &
-		~(1 << cid), sdma->base + SIRFSOC_DMA_INT_EN);
-	writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_VALID);
+	spin_lock_irqsave(&schan->lock, flags);
 
-	writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL)
-		& ~((1 << cid) | 1 << (cid + 16)),
+	if (!sdma->is_marco) {
+		writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_INT_EN) &
+			~(1 << cid), sdma->base + SIRFSOC_DMA_INT_EN);
+		writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL)
+			& ~((1 << cid) | 1 << (cid + 16)),
 			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL);
+	} else {
+		writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_INT_EN_CLR);
+		writel_relaxed((1 << cid) | 1 << (cid + 16),
+			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL_CLR);
+	}
+
+	writel_relaxed(1 << cid, sdma->base + SIRFSOC_DMA_CH_VALID);
 
-	spin_lock_irqsave(&schan->lock, flags);
 	list_splice_tail_init(&schan->active, &schan->free);
 	list_splice_tail_init(&schan->queued, &schan->free);
+
+	spin_unlock_irqrestore(&schan->lock, flags);
+
+	return 0;
+}
+
+static int sirfsoc_dma_pause_chan(struct sirfsoc_dma_chan *schan)
+{
+	struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan);
+	int cid = schan->chan.chan_id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&schan->lock, flags);
+
+	if (!sdma->is_marco)
+		writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL)
+			& ~((1 << cid) | 1 << (cid + 16)),
+			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL);
+	else
+		writel_relaxed((1 << cid) | 1 << (cid + 16),
+			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL_CLR);
+
+	spin_unlock_irqrestore(&schan->lock, flags);
+
+	return 0;
+}
+
+static int sirfsoc_dma_resume_chan(struct sirfsoc_dma_chan *schan)
+{
+	struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(&schan->chan);
+	int cid = schan->chan.chan_id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&schan->lock, flags);
+
+	if (!sdma->is_marco)
+		writel_relaxed(readl_relaxed(sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL)
+			| ((1 << cid) | 1 << (cid + 16)),
+			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL);
+	else
+		writel_relaxed((1 << cid) | 1 << (cid + 16),
+			sdma->base + SIRFSOC_DMA_CH_LOOP_CTRL);
+
 	spin_unlock_irqrestore(&schan->lock, flags);
 
 	return 0;
@@ -311,6 +364,10 @@ static int sirfsoc_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
 
 	switch (cmd) {
+	case DMA_PAUSE:
+		return sirfsoc_dma_pause_chan(schan);
+	case DMA_RESUME:
+		return sirfsoc_dma_resume_chan(schan);
 	case DMA_TERMINATE_ALL:
 		return sirfsoc_dma_terminate_all(schan);
 	case DMA_SLAVE_CONFIG:
@@ -568,6 +625,9 @@ static int sirfsoc_dma_probe(struct platform_device *op)
 		return -ENOMEM;
 	}
 
+	if (of_device_is_compatible(dn, "sirf,marco-dmac"))
+		sdma->is_marco = true;
+
 	if (of_property_read_u32(dn, "cell-index", &id)) {
 		dev_err(dev, "Fail to get DMAC index\n");
 		return -ENODEV;
@@ -668,6 +728,7 @@ static int sirfsoc_dma_remove(struct platform_device *op)
 
 static struct of_device_id sirfsoc_dma_match[] = {
 	{ .compatible = "sirf,prima2-dmac", },
+	{ .compatible = "sirf,marco-dmac", },
 	{},
 };
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 23c5573..1734fee 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -53,6 +53,8 @@
 #define D40_ALLOC_PHY		(1 << 30)
 #define D40_ALLOC_LOG_FREE	0
 
+#define MAX(a, b) (((a) < (b)) ? (b) : (a))
+
 /**
  * enum 40_command - The different commands and/or statuses.
  *
@@ -100,8 +102,19 @@ static u32 d40_backup_regs[] = {
 
 #define BACKUP_REGS_SZ ARRAY_SIZE(d40_backup_regs)
 
-/* TODO: Check if all these registers have to be saved/restored on dma40 v3 */
-static u32 d40_backup_regs_v3[] = {
+/*
+ * since 9540 and 8540 has the same HW revision
+ * use v4a for 9540 or ealier
+ * use v4b for 8540 or later
+ * HW revision:
+ * DB8500ed has revision 0
+ * DB8500v1 has revision 2
+ * DB8500v2 has revision 3
+ * AP9540v1 has revision 4
+ * DB8540v1 has revision 4
+ * TODO: Check if all these registers have to be saved/restored on dma40 v4a
+ */
+static u32 d40_backup_regs_v4a[] = {
 	D40_DREG_PSEG1,
 	D40_DREG_PSEG2,
 	D40_DREG_PSEG3,
@@ -120,7 +133,32 @@ static u32 d40_backup_regs_v3[] = {
 	D40_DREG_RCEG4,
 };
 
-#define BACKUP_REGS_SZ_V3 ARRAY_SIZE(d40_backup_regs_v3)
+#define BACKUP_REGS_SZ_V4A ARRAY_SIZE(d40_backup_regs_v4a)
+
+static u32 d40_backup_regs_v4b[] = {
+	D40_DREG_CPSEG1,
+	D40_DREG_CPSEG2,
+	D40_DREG_CPSEG3,
+	D40_DREG_CPSEG4,
+	D40_DREG_CPSEG5,
+	D40_DREG_CPCEG1,
+	D40_DREG_CPCEG2,
+	D40_DREG_CPCEG3,
+	D40_DREG_CPCEG4,
+	D40_DREG_CPCEG5,
+	D40_DREG_CRSEG1,
+	D40_DREG_CRSEG2,
+	D40_DREG_CRSEG3,
+	D40_DREG_CRSEG4,
+	D40_DREG_CRSEG5,
+	D40_DREG_CRCEG1,
+	D40_DREG_CRCEG2,
+	D40_DREG_CRCEG3,
+	D40_DREG_CRCEG4,
+	D40_DREG_CRCEG5,
+};
+
+#define BACKUP_REGS_SZ_V4B ARRAY_SIZE(d40_backup_regs_v4b)
 
 static u32 d40_backup_regs_chan[] = {
 	D40_CHAN_REG_SSCFG,
@@ -134,6 +172,102 @@ static u32 d40_backup_regs_chan[] = {
 };
 
 /**
+ * struct d40_interrupt_lookup - lookup table for interrupt handler
+ *
+ * @src: Interrupt mask register.
+ * @clr: Interrupt clear register.
+ * @is_error: true if this is an error interrupt.
+ * @offset: start delta in the lookup_log_chans in d40_base. If equals to
+ * D40_PHY_CHAN, the lookup_phy_chans shall be used instead.
+ */
+struct d40_interrupt_lookup {
+	u32 src;
+	u32 clr;
+	bool is_error;
+	int offset;
+};
+
+
+static struct d40_interrupt_lookup il_v4a[] = {
+	{D40_DREG_LCTIS0, D40_DREG_LCICR0, false,  0},
+	{D40_DREG_LCTIS1, D40_DREG_LCICR1, false, 32},
+	{D40_DREG_LCTIS2, D40_DREG_LCICR2, false, 64},
+	{D40_DREG_LCTIS3, D40_DREG_LCICR3, false, 96},
+	{D40_DREG_LCEIS0, D40_DREG_LCICR0, true,   0},
+	{D40_DREG_LCEIS1, D40_DREG_LCICR1, true,  32},
+	{D40_DREG_LCEIS2, D40_DREG_LCICR2, true,  64},
+	{D40_DREG_LCEIS3, D40_DREG_LCICR3, true,  96},
+	{D40_DREG_PCTIS,  D40_DREG_PCICR,  false, D40_PHY_CHAN},
+	{D40_DREG_PCEIS,  D40_DREG_PCICR,  true,  D40_PHY_CHAN},
+};
+
+static struct d40_interrupt_lookup il_v4b[] = {
+	{D40_DREG_CLCTIS1, D40_DREG_CLCICR1, false,  0},
+	{D40_DREG_CLCTIS2, D40_DREG_CLCICR2, false, 32},
+	{D40_DREG_CLCTIS3, D40_DREG_CLCICR3, false, 64},
+	{D40_DREG_CLCTIS4, D40_DREG_CLCICR4, false, 96},
+	{D40_DREG_CLCTIS5, D40_DREG_CLCICR5, false, 128},
+	{D40_DREG_CLCEIS1, D40_DREG_CLCICR1, true,   0},
+	{D40_DREG_CLCEIS2, D40_DREG_CLCICR2, true,  32},
+	{D40_DREG_CLCEIS3, D40_DREG_CLCICR3, true,  64},
+	{D40_DREG_CLCEIS4, D40_DREG_CLCICR4, true,  96},
+	{D40_DREG_CLCEIS5, D40_DREG_CLCICR5, true,  128},
+	{D40_DREG_CPCTIS,  D40_DREG_CPCICR,  false, D40_PHY_CHAN},
+	{D40_DREG_CPCEIS,  D40_DREG_CPCICR,  true,  D40_PHY_CHAN},
+};
+
+/**
+ * struct d40_reg_val - simple lookup struct
+ *
+ * @reg: The register.
+ * @val: The value that belongs to the register in reg.
+ */
+struct d40_reg_val {
+	unsigned int reg;
+	unsigned int val;
+};
+
+static __initdata struct d40_reg_val dma_init_reg_v4a[] = {
+	/* Clock every part of the DMA block from start */
+	{ .reg = D40_DREG_GCC,    .val = D40_DREG_GCC_ENABLE_ALL},
+
+	/* Interrupts on all logical channels */
+	{ .reg = D40_DREG_LCMIS0, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCMIS1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCMIS2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCMIS3, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCICR0, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCICR1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCICR2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCICR3, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCTIS0, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCTIS1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCTIS2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_LCTIS3, .val = 0xFFFFFFFF}
+};
+static __initdata struct d40_reg_val dma_init_reg_v4b[] = {
+	/* Clock every part of the DMA block from start */
+	{ .reg = D40_DREG_GCC,    .val = D40_DREG_GCC_ENABLE_ALL},
+
+	/* Interrupts on all logical channels */
+	{ .reg = D40_DREG_CLCMIS1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCMIS2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCMIS3, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCMIS4, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCMIS5, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCICR1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCICR2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCICR3, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCICR4, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCICR5, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCTIS1, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCTIS2, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCTIS3, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCTIS4, .val = 0xFFFFFFFF},
+	{ .reg = D40_DREG_CLCTIS5, .val = 0xFFFFFFFF}
+};
+
+/**
  * struct d40_lli_pool - Structure for keeping LLIs in memory
  *
  * @base: Pointer to memory area when the pre_alloc_lli's are not large
@@ -221,6 +355,7 @@ struct d40_lcla_pool {
  * @allocated_dst: Same as for src but is dst.
  * allocated_dst and allocated_src uses the D40_ALLOC* defines as well as
  * event line number.
+ * @use_soft_lli: To mark if the linked lists of channel are managed by SW.
  */
 struct d40_phy_res {
 	spinlock_t lock;
@@ -228,6 +363,7 @@ struct d40_phy_res {
 	int	   num;
 	u32	   allocated_src;
 	u32	   allocated_dst;
+	bool	   use_soft_lli;
 };
 
 struct d40_base;
@@ -248,6 +384,7 @@ struct d40_base;
  * @client: Cliented owned descriptor list.
  * @pending_queue: Submitted jobs, to be issued by issue_pending()
  * @active: Active descriptor.
+ * @done: Completed jobs
  * @queue: Queued jobs.
  * @prepare_queue: Prepared jobs.
  * @dma_cfg: The client configuration of this dma channel.
@@ -273,6 +410,7 @@ struct d40_chan {
 	struct list_head		 client;
 	struct list_head		 pending_queue;
 	struct list_head		 active;
+	struct list_head		 done;
 	struct list_head		 queue;
 	struct list_head		 prepare_queue;
 	struct stedma40_chan_cfg	 dma_cfg;
@@ -289,6 +427,38 @@ struct d40_chan {
 };
 
 /**
+ * struct d40_gen_dmac - generic values to represent u8500/u8540 DMA
+ * controller
+ *
+ * @backup: the pointer to the registers address array for backup
+ * @backup_size: the size of the registers address array for backup
+ * @realtime_en: the realtime enable register
+ * @realtime_clear: the realtime clear register
+ * @high_prio_en: the high priority enable register
+ * @high_prio_clear: the high priority clear register
+ * @interrupt_en: the interrupt enable register
+ * @interrupt_clear: the interrupt clear register
+ * @il: the pointer to struct d40_interrupt_lookup
+ * @il_size: the size of d40_interrupt_lookup array
+ * @init_reg: the pointer to the struct d40_reg_val
+ * @init_reg_size: the size of d40_reg_val array
+ */
+struct d40_gen_dmac {
+	u32				*backup;
+	u32				 backup_size;
+	u32				 realtime_en;
+	u32				 realtime_clear;
+	u32				 high_prio_en;
+	u32				 high_prio_clear;
+	u32				 interrupt_en;
+	u32				 interrupt_clear;
+	struct d40_interrupt_lookup	*il;
+	u32				 il_size;
+	struct d40_reg_val		*init_reg;
+	u32				 init_reg_size;
+};
+
+/**
  * struct d40_base - The big global struct, one for each probe'd instance.
  *
  * @interrupt_lock: Lock used to make sure one interrupt is handle a time.
@@ -326,11 +496,13 @@ struct d40_chan {
  * @desc_slab: cache for descriptors.
  * @reg_val_backup: Here the values of some hardware registers are stored
  * before the DMA is powered off. They are restored when the power is back on.
- * @reg_val_backup_v3: Backup of registers that only exits on dma40 v3 and
- * later.
+ * @reg_val_backup_v4: Backup of registers that only exits on dma40 v3 and
+ * later
  * @reg_val_backup_chan: Backup data for standard channel parameter registers.
  * @gcc_pwr_off_mask: Mask to maintain the channels that can be turned off.
  * @initialized: true if the dma has been initialized
+ * @gen_dmac: the struct for generic registers values to represent u8500/8540
+ * DMA controller
  */
 struct d40_base {
 	spinlock_t			 interrupt_lock;
@@ -344,6 +516,7 @@ struct d40_base {
 	int				  irq;
 	int				  num_phy_chans;
 	int				  num_log_chans;
+	struct device_dma_parameters	  dma_parms;
 	struct dma_device		  dma_both;
 	struct dma_device		  dma_slave;
 	struct dma_device		  dma_memcpy;
@@ -361,37 +534,11 @@ struct d40_base {
 	resource_size_t			  lcpa_size;
 	struct kmem_cache		 *desc_slab;
 	u32				  reg_val_backup[BACKUP_REGS_SZ];
-	u32				  reg_val_backup_v3[BACKUP_REGS_SZ_V3];
+	u32				  reg_val_backup_v4[MAX(BACKUP_REGS_SZ_V4A, BACKUP_REGS_SZ_V4B)];
 	u32				 *reg_val_backup_chan;
 	u16				  gcc_pwr_off_mask;
 	bool				  initialized;
-};
-
-/**
- * struct d40_interrupt_lookup - lookup table for interrupt handler
- *
- * @src: Interrupt mask register.
- * @clr: Interrupt clear register.
- * @is_error: true if this is an error interrupt.
- * @offset: start delta in the lookup_log_chans in d40_base. If equals to
- * D40_PHY_CHAN, the lookup_phy_chans shall be used instead.
- */
-struct d40_interrupt_lookup {
-	u32 src;
-	u32 clr;
-	bool is_error;
-	int offset;
-};
-
-/**
- * struct d40_reg_val - simple lookup struct
- *
- * @reg: The register.
- * @val: The value that belongs to the register in reg.
- */
-struct d40_reg_val {
-	unsigned int reg;
-	unsigned int val;
+	struct d40_gen_dmac		  gen_dmac;
 };
 
 static struct device *chan2dev(struct d40_chan *d40c)
@@ -494,19 +641,18 @@ static int d40_lcla_alloc_one(struct d40_chan *d40c,
 	unsigned long flags;
 	int i;
 	int ret = -EINVAL;
-	int p;
 
 	spin_lock_irqsave(&d40c->base->lcla_pool.lock, flags);
 
-	p = d40c->phy_chan->num * D40_LCLA_LINK_PER_EVENT_GRP;
-
 	/*
 	 * Allocate both src and dst at the same time, therefore the half
 	 * start on 1 since 0 can't be used since zero is used as end marker.
 	 */
 	for (i = 1 ; i < D40_LCLA_LINK_PER_EVENT_GRP / 2; i++) {
-		if (!d40c->base->lcla_pool.alloc_map[p + i]) {
-			d40c->base->lcla_pool.alloc_map[p + i] = d40d;
+		int idx = d40c->phy_chan->num * D40_LCLA_LINK_PER_EVENT_GRP + i;
+
+		if (!d40c->base->lcla_pool.alloc_map[idx]) {
+			d40c->base->lcla_pool.alloc_map[idx] = d40d;
 			d40d->lcla_alloc++;
 			ret = i;
 			break;
@@ -531,10 +677,10 @@ static int d40_lcla_free_all(struct d40_chan *d40c,
 	spin_lock_irqsave(&d40c->base->lcla_pool.lock, flags);
 
 	for (i = 1 ; i < D40_LCLA_LINK_PER_EVENT_GRP / 2; i++) {
-		if (d40c->base->lcla_pool.alloc_map[d40c->phy_chan->num *
-						    D40_LCLA_LINK_PER_EVENT_GRP + i] == d40d) {
-			d40c->base->lcla_pool.alloc_map[d40c->phy_chan->num *
-							D40_LCLA_LINK_PER_EVENT_GRP + i] = NULL;
+		int idx = d40c->phy_chan->num * D40_LCLA_LINK_PER_EVENT_GRP + i;
+
+		if (d40c->base->lcla_pool.alloc_map[idx] == d40d) {
+			d40c->base->lcla_pool.alloc_map[idx] = NULL;
 			d40d->lcla_alloc--;
 			if (d40d->lcla_alloc == 0) {
 				ret = 0;
@@ -611,6 +757,11 @@ static void d40_phy_lli_load(struct d40_chan *chan, struct d40_desc *desc)
 	writel(lli_dst->reg_lnk, base + D40_CHAN_REG_SDLNK);
 }
 
+static void d40_desc_done(struct d40_chan *d40c, struct d40_desc *desc)
+{
+	list_add_tail(&desc->node, &d40c->done);
+}
+
 static void d40_log_lli_to_lcxa(struct d40_chan *chan, struct d40_desc *desc)
 {
 	struct d40_lcla_pool *pool = &chan->base->lcla_pool;
@@ -634,7 +785,16 @@ static void d40_log_lli_to_lcxa(struct d40_chan *chan, struct d40_desc *desc)
 	 * can't link back to the one in LCPA space
 	 */
 	if (linkback || (lli_len - lli_current > 1)) {
-		curr_lcla = d40_lcla_alloc_one(chan, desc);
+		/*
+		 * If the channel is expected to use only soft_lli don't
+		 * allocate a lcla. This is to avoid a HW issue that exists
+		 * in some controller during a peripheral to memory transfer
+		 * that uses linked lists.
+		 */
+		if (!(chan->phy_chan->use_soft_lli &&
+			chan->dma_cfg.dir == STEDMA40_PERIPH_TO_MEM))
+			curr_lcla = d40_lcla_alloc_one(chan, desc);
+
 		first_lcla = curr_lcla;
 	}
 
@@ -771,6 +931,14 @@ static struct d40_desc *d40_first_queued(struct d40_chan *d40c)
 	return d;
 }
 
+static struct d40_desc *d40_first_done(struct d40_chan *d40c)
+{
+	if (list_empty(&d40c->done))
+		return NULL;
+
+	return list_first_entry(&d40c->done, struct d40_desc, node);
+}
+
 static int d40_psize_2_burst_size(bool is_log, int psize)
 {
 	if (is_log) {
@@ -874,11 +1042,11 @@ static void d40_save_restore_registers(struct d40_base *base, bool save)
 		     save);
 
 	/* Save/Restore registers only existing on dma40 v3 and later */
-	if (base->rev >= 3)
-		dma40_backup(base->virtbase, base->reg_val_backup_v3,
-			     d40_backup_regs_v3,
-			     ARRAY_SIZE(d40_backup_regs_v3),
-			     save);
+	if (base->gen_dmac.backup)
+		dma40_backup(base->virtbase, base->reg_val_backup_v4,
+			     base->gen_dmac.backup,
+			base->gen_dmac.backup_size,
+			save);
 }
 #else
 static void d40_save_restore_registers(struct d40_base *base, bool save)
@@ -961,6 +1129,12 @@ static void d40_term_all(struct d40_chan *d40c)
 	struct d40_desc *d40d;
 	struct d40_desc *_d;
 
+	/* Release completed descriptors */
+	while ((d40d = d40_first_done(d40c))) {
+		d40_desc_remove(d40d);
+		d40_desc_free(d40c, d40d);
+	}
+
 	/* Release active descriptors */
 	while ((d40d = d40_first_active_get(d40c))) {
 		d40_desc_remove(d40d);
@@ -1396,6 +1570,9 @@ static void dma_tc_handle(struct d40_chan *d40c)
 			d40c->busy = false;
 		pm_runtime_mark_last_busy(d40c->base->dev);
 		pm_runtime_put_autosuspend(d40c->base->dev);
+
+		d40_desc_remove(d40d);
+		d40_desc_done(d40c, d40d);
 	}
 
 	d40c->pending_tx++;
@@ -1413,10 +1590,14 @@ static void dma_tasklet(unsigned long data)
 
 	spin_lock_irqsave(&d40c->lock, flags);
 
-	/* Get first active entry from list */
-	d40d = d40_first_active_get(d40c);
-	if (d40d == NULL)
-		goto err;
+	/* Get first entry from the done list */
+	d40d = d40_first_done(d40c);
+	if (d40d == NULL) {
+		/* Check if we have reached here for cyclic job */
+		d40d = d40_first_active_get(d40c);
+		if (d40d == NULL || !d40d->cyclic)
+			goto err;
+	}
 
 	if (!d40d->cyclic)
 		dma_cookie_complete(&d40d->txd);
@@ -1438,13 +1619,11 @@ static void dma_tasklet(unsigned long data)
 		if (async_tx_test_ack(&d40d->txd)) {
 			d40_desc_remove(d40d);
 			d40_desc_free(d40c, d40d);
-		} else {
-			if (!d40d->is_in_client_list) {
-				d40_desc_remove(d40d);
-				d40_lcla_free_all(d40c, d40d);
-				list_add_tail(&d40d->node, &d40c->client);
-				d40d->is_in_client_list = true;
-			}
+		} else if (!d40d->is_in_client_list) {
+			d40_desc_remove(d40d);
+			d40_lcla_free_all(d40c, d40d);
+			list_add_tail(&d40d->node, &d40c->client);
+			d40d->is_in_client_list = true;
 		}
 	}
 
@@ -1469,53 +1648,51 @@ err:
 
 static irqreturn_t d40_handle_interrupt(int irq, void *data)
 {
-	static const struct d40_interrupt_lookup il[] = {
-		{D40_DREG_LCTIS0, D40_DREG_LCICR0, false,  0},
-		{D40_DREG_LCTIS1, D40_DREG_LCICR1, false, 32},
-		{D40_DREG_LCTIS2, D40_DREG_LCICR2, false, 64},
-		{D40_DREG_LCTIS3, D40_DREG_LCICR3, false, 96},
-		{D40_DREG_LCEIS0, D40_DREG_LCICR0, true,   0},
-		{D40_DREG_LCEIS1, D40_DREG_LCICR1, true,  32},
-		{D40_DREG_LCEIS2, D40_DREG_LCICR2, true,  64},
-		{D40_DREG_LCEIS3, D40_DREG_LCICR3, true,  96},
-		{D40_DREG_PCTIS,  D40_DREG_PCICR,  false, D40_PHY_CHAN},
-		{D40_DREG_PCEIS,  D40_DREG_PCICR,  true,  D40_PHY_CHAN},
-	};
-
 	int i;
-	u32 regs[ARRAY_SIZE(il)];
 	u32 idx;
 	u32 row;
 	long chan = -1;
 	struct d40_chan *d40c;
 	unsigned long flags;
 	struct d40_base *base = data;
+	u32 regs[base->gen_dmac.il_size];
+	struct d40_interrupt_lookup *il = base->gen_dmac.il;
+	u32 il_size = base->gen_dmac.il_size;
 
 	spin_lock_irqsave(&base->interrupt_lock, flags);
 
 	/* Read interrupt status of both logical and physical channels */
-	for (i = 0; i < ARRAY_SIZE(il); i++)
+	for (i = 0; i < il_size; i++)
 		regs[i] = readl(base->virtbase + il[i].src);
 
 	for (;;) {
 
 		chan = find_next_bit((unsigned long *)regs,
-				     BITS_PER_LONG * ARRAY_SIZE(il), chan + 1);
+				     BITS_PER_LONG * il_size, chan + 1);
 
 		/* No more set bits found? */
-		if (chan == BITS_PER_LONG * ARRAY_SIZE(il))
+		if (chan == BITS_PER_LONG * il_size)
 			break;
 
 		row = chan / BITS_PER_LONG;
 		idx = chan & (BITS_PER_LONG - 1);
 
-		/* ACK interrupt */
-		writel(1 << idx, base->virtbase + il[row].clr);
-
 		if (il[row].offset == D40_PHY_CHAN)
 			d40c = base->lookup_phy_chans[idx];
 		else
 			d40c = base->lookup_log_chans[il[row].offset + idx];
+
+		if (!d40c) {
+			/*
+			 * No error because this can happen if something else
+			 * in the system is using the channel.
+			 */
+			continue;
+		}
+
+		/* ACK interrupt */
+		writel(1 << idx, base->virtbase + il[row].clr);
+
 		spin_lock(&d40c->lock);
 
 		if (!il[row].is_error)
@@ -1710,10 +1887,12 @@ static int d40_allocate_channel(struct d40_chan *d40c, bool *first_phy_user)
 	int i;
 	int j;
 	int log_num;
+	int num_phy_chans;
 	bool is_src;
 	bool is_log = d40c->dma_cfg.mode == STEDMA40_MODE_LOGICAL;
 
 	phys = d40c->base->phy_res;
+	num_phy_chans = d40c->base->num_phy_chans;
 
 	if (d40c->dma_cfg.dir == STEDMA40_PERIPH_TO_MEM) {
 		dev_type = d40c->dma_cfg.src_dev_type;
@@ -1734,12 +1913,19 @@ static int d40_allocate_channel(struct d40_chan *d40c, bool *first_phy_user)
 	if (!is_log) {
 		if (d40c->dma_cfg.dir == STEDMA40_MEM_TO_MEM) {
 			/* Find physical half channel */
-			for (i = 0; i < d40c->base->num_phy_chans; i++) {
-
+			if (d40c->dma_cfg.use_fixed_channel) {
+				i = d40c->dma_cfg.phy_channel;
 				if (d40_alloc_mask_set(&phys[i], is_src,
 						       0, is_log,
 						       first_phy_user))
 					goto found_phy;
+			} else {
+				for (i = 0; i < num_phy_chans; i++) {
+					if (d40_alloc_mask_set(&phys[i], is_src,
+						       0, is_log,
+						       first_phy_user))
+						goto found_phy;
+				}
 			}
 		} else
 			for (j = 0; j < d40c->base->num_phy_chans; j += 8) {
@@ -1954,7 +2140,6 @@ _exit:
 
 }
 
-
 static u32 stedma40_residue(struct dma_chan *chan)
 {
 	struct d40_chan *d40c =
@@ -2030,7 +2215,6 @@ d40_prep_sg_phy(struct d40_chan *chan, struct d40_desc *desc,
 	return ret < 0 ? ret : 0;
 }
 
-
 static struct d40_desc *
 d40_prep_desc(struct d40_chan *chan, struct scatterlist *sg,
 	      unsigned int sg_len, unsigned long dma_flags)
@@ -2056,7 +2240,6 @@ d40_prep_desc(struct d40_chan *chan, struct scatterlist *sg,
 		goto err;
 	}
 
-
 	desc->lli_current = 0;
 	desc->txd.flags = dma_flags;
 	desc->txd.tx_submit = d40_tx_submit;
@@ -2105,7 +2288,6 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 		return NULL;
 	}
 
-
 	spin_lock_irqsave(&chan->lock, flags);
 
 	desc = d40_prep_desc(chan, sg_src, sg_len, dma_flags);
@@ -2179,11 +2361,26 @@ static void __d40_set_prio_rt(struct d40_chan *d40c, int dev_type, bool src)
 {
 	bool realtime = d40c->dma_cfg.realtime;
 	bool highprio = d40c->dma_cfg.high_priority;
-	u32 prioreg = highprio ? D40_DREG_PSEG1 : D40_DREG_PCEG1;
-	u32 rtreg = realtime ? D40_DREG_RSEG1 : D40_DREG_RCEG1;
+	u32 rtreg;
 	u32 event = D40_TYPE_TO_EVENT(dev_type);
 	u32 group = D40_TYPE_TO_GROUP(dev_type);
 	u32 bit = 1 << event;
+	u32 prioreg;
+	struct d40_gen_dmac *dmac = &d40c->base->gen_dmac;
+
+	rtreg = realtime ? dmac->realtime_en : dmac->realtime_clear;
+	/*
+	 * Due to a hardware bug, in some cases a logical channel triggered by
+	 * a high priority destination event line can generate extra packet
+	 * transactions.
+	 *
+	 * The workaround is to not set the high priority level for the
+	 * destination event lines that trigger logical channels.
+	 */
+	if (!src && chan_is_logical(d40c))
+		highprio = false;
+
+	prioreg = highprio ? dmac->high_prio_en : dmac->high_prio_clear;
 
 	/* Destination event lines are stored in the upper halfword */
 	if (!src)
@@ -2248,11 +2445,11 @@ static int d40_alloc_chan_resources(struct dma_chan *chan)
 
 		if (d40c->dma_cfg.dir == STEDMA40_PERIPH_TO_MEM)
 			d40c->lcpa = d40c->base->lcpa_base +
-			  d40c->dma_cfg.src_dev_type * D40_LCPA_CHAN_SIZE;
+				d40c->dma_cfg.src_dev_type * D40_LCPA_CHAN_SIZE;
 		else
 			d40c->lcpa = d40c->base->lcpa_base +
-			  d40c->dma_cfg.dst_dev_type *
-			  D40_LCPA_CHAN_SIZE + D40_LCPA_CHAN_DST_DELTA;
+				d40c->dma_cfg.dst_dev_type *
+				D40_LCPA_CHAN_SIZE + D40_LCPA_CHAN_DST_DELTA;
 	}
 
 	dev_dbg(chan2dev(d40c), "allocated %s channel (phy %d%s)\n",
@@ -2287,7 +2484,6 @@ static void d40_free_chan_resources(struct dma_chan *chan)
 		return;
 	}
 
-
 	spin_lock_irqsave(&d40c->lock, flags);
 
 	err = d40_free_dma(d40c);
@@ -2330,14 +2526,12 @@ d40_prep_memcpy_sg(struct dma_chan *chan,
 	return d40_prep_sg(chan, src_sg, dst_sg, src_nents, DMA_NONE, dma_flags);
 }
 
-static struct dma_async_tx_descriptor *d40_prep_slave_sg(struct dma_chan *chan,
-							 struct scatterlist *sgl,
-							 unsigned int sg_len,
-							 enum dma_transfer_direction direction,
-							 unsigned long dma_flags,
-							 void *context)
+static struct dma_async_tx_descriptor *
+d40_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		  unsigned int sg_len, enum dma_transfer_direction direction,
+		  unsigned long dma_flags, void *context)
 {
-	if (direction != DMA_DEV_TO_MEM && direction != DMA_MEM_TO_DEV)
+	if (!is_slave_direction(direction))
 		return NULL;
 
 	return d40_prep_sg(chan, sgl, sgl, sg_len, direction, dma_flags);
@@ -2577,6 +2771,14 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 		return -EINVAL;
 	}
 
+	if (src_maxburst > 16) {
+		src_maxburst = 16;
+		dst_maxburst = src_maxburst * src_addr_width / dst_addr_width;
+	} else if (dst_maxburst > 16) {
+		dst_maxburst = 16;
+		src_maxburst = dst_maxburst * dst_addr_width / src_addr_width;
+	}
+
 	ret = dma40_config_to_halfchannel(d40c, &cfg->src_info,
 					  src_addr_width,
 					  src_maxburst);
@@ -2659,6 +2861,7 @@ static void __init d40_chan_init(struct d40_base *base, struct dma_device *dma,
 
 		d40c->log_num = D40_PHY_CHAN;
 
+		INIT_LIST_HEAD(&d40c->done);
 		INIT_LIST_HEAD(&d40c->active);
 		INIT_LIST_HEAD(&d40c->queue);
 		INIT_LIST_HEAD(&d40c->pending_queue);
@@ -2773,8 +2976,6 @@ static int dma40_pm_suspend(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct d40_base *base = platform_get_drvdata(pdev);
 	int ret = 0;
-	if (!pm_runtime_suspended(dev))
-		return -EBUSY;
 
 	if (base->lcpa_regulator)
 		ret = regulator_disable(base->lcpa_regulator);
@@ -2882,6 +3083,13 @@ static int __init d40_phy_res_init(struct d40_base *base)
 		num_phy_chans_avail--;
 	}
 
+	/* Mark soft_lli channels */
+	for (i = 0; i < base->plat_data->num_of_soft_lli_chans; i++) {
+		int chan = base->plat_data->soft_lli_chans[i];
+
+		base->phy_res[chan].use_soft_lli = true;
+	}
+
 	dev_info(base->dev, "%d of %d physical DMA channels available\n",
 		 num_phy_chans_avail, base->num_phy_chans);
 
@@ -2975,14 +3183,21 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	 * ? has revision 1
 	 * DB8500v1 has revision 2
 	 * DB8500v2 has revision 3
+	 * AP9540v1 has revision 4
+	 * DB8540v1 has revision 4
 	 */
 	rev = AMBA_REV_BITS(pid);
 
+	plat_data = pdev->dev.platform_data;
+
 	/* The number of physical channels on this HW */
-	num_phy_chans = 4 * (readl(virtbase + D40_DREG_ICFG) & 0x7) + 4;
+	if (plat_data->num_of_phy_chans)
+		num_phy_chans = plat_data->num_of_phy_chans;
+	else
+		num_phy_chans = 4 * (readl(virtbase + D40_DREG_ICFG) & 0x7) + 4;
 
-	dev_info(&pdev->dev, "hardware revision: %d @ 0x%x\n",
-		 rev, res->start);
+	dev_info(&pdev->dev, "hardware revision: %d @ 0x%x with %d physical channels\n",
+		 rev, res->start, num_phy_chans);
 
 	if (rev < 2) {
 		d40_err(&pdev->dev, "hardware revision: %d is not supported",
@@ -2990,8 +3205,6 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 		goto failure;
 	}
 
-	plat_data = pdev->dev.platform_data;
-
 	/* Count the number of logical channels in use */
 	for (i = 0; i < plat_data->dev_len; i++)
 		if (plat_data->dev_rx[i] != 0)
@@ -3022,6 +3235,36 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	base->phy_chans = ((void *)base) + ALIGN(sizeof(struct d40_base), 4);
 	base->log_chans = &base->phy_chans[num_phy_chans];
 
+	if (base->plat_data->num_of_phy_chans == 14) {
+		base->gen_dmac.backup = d40_backup_regs_v4b;
+		base->gen_dmac.backup_size = BACKUP_REGS_SZ_V4B;
+		base->gen_dmac.interrupt_en = D40_DREG_CPCMIS;
+		base->gen_dmac.interrupt_clear = D40_DREG_CPCICR;
+		base->gen_dmac.realtime_en = D40_DREG_CRSEG1;
+		base->gen_dmac.realtime_clear = D40_DREG_CRCEG1;
+		base->gen_dmac.high_prio_en = D40_DREG_CPSEG1;
+		base->gen_dmac.high_prio_clear = D40_DREG_CPCEG1;
+		base->gen_dmac.il = il_v4b;
+		base->gen_dmac.il_size = ARRAY_SIZE(il_v4b);
+		base->gen_dmac.init_reg = dma_init_reg_v4b;
+		base->gen_dmac.init_reg_size = ARRAY_SIZE(dma_init_reg_v4b);
+	} else {
+		if (base->rev >= 3) {
+			base->gen_dmac.backup = d40_backup_regs_v4a;
+			base->gen_dmac.backup_size = BACKUP_REGS_SZ_V4A;
+		}
+		base->gen_dmac.interrupt_en = D40_DREG_PCMIS;
+		base->gen_dmac.interrupt_clear = D40_DREG_PCICR;
+		base->gen_dmac.realtime_en = D40_DREG_RSEG1;
+		base->gen_dmac.realtime_clear = D40_DREG_RCEG1;
+		base->gen_dmac.high_prio_en = D40_DREG_PSEG1;
+		base->gen_dmac.high_prio_clear = D40_DREG_PCEG1;
+		base->gen_dmac.il = il_v4a;
+		base->gen_dmac.il_size = ARRAY_SIZE(il_v4a);
+		base->gen_dmac.init_reg = dma_init_reg_v4a;
+		base->gen_dmac.init_reg_size = ARRAY_SIZE(dma_init_reg_v4a);
+	}
+
 	base->phy_res = kzalloc(num_phy_chans * sizeof(struct d40_phy_res),
 				GFP_KERNEL);
 	if (!base->phy_res)
@@ -3093,31 +3336,15 @@ failure:
 static void __init d40_hw_init(struct d40_base *base)
 {
 
-	static struct d40_reg_val dma_init_reg[] = {
-		/* Clock every part of the DMA block from start */
-		{ .reg = D40_DREG_GCC,    .val = D40_DREG_GCC_ENABLE_ALL},
-
-		/* Interrupts on all logical channels */
-		{ .reg = D40_DREG_LCMIS0, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCMIS1, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCMIS2, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCMIS3, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCICR0, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCICR1, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCICR2, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCICR3, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCTIS0, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCTIS1, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCTIS2, .val = 0xFFFFFFFF},
-		{ .reg = D40_DREG_LCTIS3, .val = 0xFFFFFFFF}
-	};
 	int i;
 	u32 prmseo[2] = {0, 0};
 	u32 activeo[2] = {0xFFFFFFFF, 0xFFFFFFFF};
 	u32 pcmis = 0;
 	u32 pcicr = 0;
+	struct d40_reg_val *dma_init_reg = base->gen_dmac.init_reg;
+	u32 reg_size = base->gen_dmac.init_reg_size;
 
-	for (i = 0; i < ARRAY_SIZE(dma_init_reg); i++)
+	for (i = 0; i < reg_size; i++)
 		writel(dma_init_reg[i].val,
 		       base->virtbase + dma_init_reg[i].reg);
 
@@ -3150,11 +3377,14 @@ static void __init d40_hw_init(struct d40_base *base)
 	writel(activeo[0], base->virtbase + D40_DREG_ACTIVO);
 
 	/* Write which interrupt to enable */
-	writel(pcmis, base->virtbase + D40_DREG_PCMIS);
+	writel(pcmis, base->virtbase + base->gen_dmac.interrupt_en);
 
 	/* Write which interrupt to clear */
-	writel(pcicr, base->virtbase + D40_DREG_PCICR);
+	writel(pcicr, base->virtbase + base->gen_dmac.interrupt_clear);
 
+	/* These are __initdata and cannot be accessed after init */
+	base->gen_dmac.init_reg = NULL;
+	base->gen_dmac.init_reg_size = 0;
 }
 
 static int __init d40_lcla_allocate(struct d40_base *base)
@@ -3362,6 +3592,13 @@ static int __init d40_probe(struct platform_device *pdev)
 	if (err)
 		goto failure;
 
+	base->dev->dma_parms = &base->dma_parms;
+	err = dma_set_max_seg_size(base->dev, STEDMA40_MAX_SEG_SIZE);
+	if (err) {
+		d40_err(&pdev->dev, "Failed to set dma max seg size\n");
+		goto failure;
+	}
+
 	d40_hw_init(base);
 
 	dev_info(base->dev, "initialized\n");
@@ -3397,7 +3634,7 @@ failure:
 			release_mem_region(base->phy_start,
 					   base->phy_size);
 		if (base->clk) {
-			clk_disable(base->clk);
+			clk_disable_unprepare(base->clk);
 			clk_put(base->clk);
 		}
 
diff --git a/drivers/dma/ste_dma40_ll.c b/drivers/dma/ste_dma40_ll.c
index 851ad56..7180e0d 100644
--- a/drivers/dma/ste_dma40_ll.c
+++ b/drivers/dma/ste_dma40_ll.c
@@ -102,17 +102,18 @@ void d40_phy_cfg(struct stedma40_chan_cfg *cfg,
 		src |= cfg->src_info.data_width << D40_SREG_CFG_ESIZE_POS;
 		dst |= cfg->dst_info.data_width << D40_SREG_CFG_ESIZE_POS;
 
+		/* Set the priority bit to high for the physical channel */
+		if (cfg->high_priority) {
+			src |= 1 << D40_SREG_CFG_PRI_POS;
+			dst |= 1 << D40_SREG_CFG_PRI_POS;
+		}
+
 	} else {
 		/* Logical channel */
 		dst |= 1 << D40_SREG_CFG_LOG_GIM_POS;
 		src |= 1 << D40_SREG_CFG_LOG_GIM_POS;
 	}
 
-	if (cfg->high_priority) {
-		src |= 1 << D40_SREG_CFG_PRI_POS;
-		dst |= 1 << D40_SREG_CFG_PRI_POS;
-	}
-
 	if (cfg->src_info.big_endian)
 		src |= 1 << D40_SREG_CFG_LBE_POS;
 	if (cfg->dst_info.big_endian)
@@ -250,7 +251,7 @@ d40_phy_buf_to_lli(struct d40_phy_lli *lli, dma_addr_t addr, u32 size,
 
 	return lli;
 
- err:
+err:
 	return NULL;
 }
 
@@ -331,10 +332,10 @@ void d40_log_lli_lcpa_write(struct d40_log_lli_full *lcpa,
 {
 	d40_log_lli_link(lli_dst, lli_src, next, flags);
 
-	writel(lli_src->lcsp02, &lcpa[0].lcsp0);
-	writel(lli_src->lcsp13, &lcpa[0].lcsp1);
-	writel(lli_dst->lcsp02, &lcpa[0].lcsp2);
-	writel(lli_dst->lcsp13, &lcpa[0].lcsp3);
+	writel_relaxed(lli_src->lcsp02, &lcpa[0].lcsp0);
+	writel_relaxed(lli_src->lcsp13, &lcpa[0].lcsp1);
+	writel_relaxed(lli_dst->lcsp02, &lcpa[0].lcsp2);
+	writel_relaxed(lli_dst->lcsp13, &lcpa[0].lcsp3);
 }
 
 void d40_log_lli_lcla_write(struct d40_log_lli *lcla,
@@ -344,10 +345,10 @@ void d40_log_lli_lcla_write(struct d40_log_lli *lcla,
 {
 	d40_log_lli_link(lli_dst, lli_src, next, flags);
 
-	writel(lli_src->lcsp02, &lcla[0].lcsp02);
-	writel(lli_src->lcsp13, &lcla[0].lcsp13);
-	writel(lli_dst->lcsp02, &lcla[1].lcsp02);
-	writel(lli_dst->lcsp13, &lcla[1].lcsp13);
+	writel_relaxed(lli_src->lcsp02, &lcla[0].lcsp02);
+	writel_relaxed(lli_src->lcsp13, &lcla[0].lcsp13);
+	writel_relaxed(lli_dst->lcsp02, &lcla[1].lcsp02);
+	writel_relaxed(lli_dst->lcsp13, &lcla[1].lcsp13);
 }
 
 static void d40_log_fill_lli(struct d40_log_lli *lli,
diff --git a/drivers/dma/ste_dma40_ll.h b/drivers/dma/ste_dma40_ll.h
index 6d47373..fdde8ef 100644
--- a/drivers/dma/ste_dma40_ll.h
+++ b/drivers/dma/ste_dma40_ll.h
@@ -125,7 +125,7 @@
 #define D40_DREG_GCC		0x000
 #define D40_DREG_GCC_ENA	0x1
 /* This assumes that there are only 4 event groups */
-#define D40_DREG_GCC_ENABLE_ALL	0xff01
+#define D40_DREG_GCC_ENABLE_ALL	0x3ff01
 #define D40_DREG_GCC_EVTGRP_POS 8
 #define D40_DREG_GCC_SRC 0
 #define D40_DREG_GCC_DST 1
@@ -148,14 +148,31 @@
 
 #define D40_DREG_LCPA		0x020
 #define D40_DREG_LCLA		0x024
+
+#define D40_DREG_SSEG1		0x030
+#define D40_DREG_SSEG2		0x034
+#define D40_DREG_SSEG3		0x038
+#define D40_DREG_SSEG4		0x03C
+
+#define D40_DREG_SCEG1		0x040
+#define D40_DREG_SCEG2		0x044
+#define D40_DREG_SCEG3		0x048
+#define D40_DREG_SCEG4		0x04C
+
 #define D40_DREG_ACTIVE		0x050
 #define D40_DREG_ACTIVO		0x054
-#define D40_DREG_FSEB1		0x058
-#define D40_DREG_FSEB2		0x05C
+#define D40_DREG_CIDMOD		0x058
+#define D40_DREG_TCIDV		0x05C
 #define D40_DREG_PCMIS		0x060
 #define D40_DREG_PCICR		0x064
 #define D40_DREG_PCTIS		0x068
 #define D40_DREG_PCEIS		0x06C
+
+#define D40_DREG_SPCMIS		0x070
+#define D40_DREG_SPCICR		0x074
+#define D40_DREG_SPCTIS		0x078
+#define D40_DREG_SPCEIS		0x07C
+
 #define D40_DREG_LCMIS0		0x080
 #define D40_DREG_LCMIS1		0x084
 #define D40_DREG_LCMIS2		0x088
@@ -172,6 +189,33 @@
 #define D40_DREG_LCEIS1		0x0B4
 #define D40_DREG_LCEIS2		0x0B8
 #define D40_DREG_LCEIS3		0x0BC
+
+#define D40_DREG_SLCMIS1	0x0C0
+#define D40_DREG_SLCMIS2	0x0C4
+#define D40_DREG_SLCMIS3	0x0C8
+#define D40_DREG_SLCMIS4	0x0CC
+
+#define D40_DREG_SLCICR1	0x0D0
+#define D40_DREG_SLCICR2	0x0D4
+#define D40_DREG_SLCICR3	0x0D8
+#define D40_DREG_SLCICR4	0x0DC
+
+#define D40_DREG_SLCTIS1	0x0E0
+#define D40_DREG_SLCTIS2	0x0E4
+#define D40_DREG_SLCTIS3	0x0E8
+#define D40_DREG_SLCTIS4	0x0EC
+
+#define D40_DREG_SLCEIS1	0x0F0
+#define D40_DREG_SLCEIS2	0x0F4
+#define D40_DREG_SLCEIS3	0x0F8
+#define D40_DREG_SLCEIS4	0x0FC
+
+#define D40_DREG_FSESS1		0x100
+#define D40_DREG_FSESS2		0x104
+
+#define D40_DREG_FSEBS1		0x108
+#define D40_DREG_FSEBS2		0x10C
+
 #define D40_DREG_PSEG1		0x110
 #define D40_DREG_PSEG2		0x114
 #define D40_DREG_PSEG3		0x118
@@ -188,6 +232,86 @@
 #define D40_DREG_RCEG2		0x144
 #define D40_DREG_RCEG3		0x148
 #define D40_DREG_RCEG4		0x14C
+
+#define D40_DREG_PREFOT		0x15C
+#define D40_DREG_EXTCFG		0x160
+
+#define D40_DREG_CPSEG1		0x200
+#define D40_DREG_CPSEG2		0x204
+#define D40_DREG_CPSEG3		0x208
+#define D40_DREG_CPSEG4		0x20C
+#define D40_DREG_CPSEG5		0x210
+
+#define D40_DREG_CPCEG1		0x220
+#define D40_DREG_CPCEG2		0x224
+#define D40_DREG_CPCEG3		0x228
+#define D40_DREG_CPCEG4		0x22C
+#define D40_DREG_CPCEG5		0x230
+
+#define D40_DREG_CRSEG1		0x240
+#define D40_DREG_CRSEG2		0x244
+#define D40_DREG_CRSEG3		0x248
+#define D40_DREG_CRSEG4		0x24C
+#define D40_DREG_CRSEG5		0x250
+
+#define D40_DREG_CRCEG1		0x260
+#define D40_DREG_CRCEG2		0x264
+#define D40_DREG_CRCEG3		0x268
+#define D40_DREG_CRCEG4		0x26C
+#define D40_DREG_CRCEG5		0x270
+
+#define D40_DREG_CFSESS1	0x280
+#define D40_DREG_CFSESS2	0x284
+#define D40_DREG_CFSESS3	0x288
+
+#define D40_DREG_CFSEBS1	0x290
+#define D40_DREG_CFSEBS2	0x294
+#define D40_DREG_CFSEBS3	0x298
+
+#define D40_DREG_CLCMIS1	0x300
+#define D40_DREG_CLCMIS2	0x304
+#define D40_DREG_CLCMIS3	0x308
+#define D40_DREG_CLCMIS4	0x30C
+#define D40_DREG_CLCMIS5	0x310
+
+#define D40_DREG_CLCICR1	0x320
+#define D40_DREG_CLCICR2	0x324
+#define D40_DREG_CLCICR3	0x328
+#define D40_DREG_CLCICR4	0x32C
+#define D40_DREG_CLCICR5	0x330
+
+#define D40_DREG_CLCTIS1	0x340
+#define D40_DREG_CLCTIS2	0x344
+#define D40_DREG_CLCTIS3	0x348
+#define D40_DREG_CLCTIS4	0x34C
+#define D40_DREG_CLCTIS5	0x350
+
+#define D40_DREG_CLCEIS1	0x360
+#define D40_DREG_CLCEIS2	0x364
+#define D40_DREG_CLCEIS3	0x368
+#define D40_DREG_CLCEIS4	0x36C
+#define D40_DREG_CLCEIS5	0x370
+
+#define D40_DREG_CPCMIS		0x380
+#define D40_DREG_CPCICR		0x384
+#define D40_DREG_CPCTIS		0x388
+#define D40_DREG_CPCEIS		0x38C
+
+#define D40_DREG_SCCIDA1	0xE80
+#define D40_DREG_SCCIDA2	0xE90
+#define D40_DREG_SCCIDA3	0xEA0
+#define D40_DREG_SCCIDA4	0xEB0
+#define D40_DREG_SCCIDA5	0xEC0
+
+#define D40_DREG_SCCIDB1	0xE84
+#define D40_DREG_SCCIDB2	0xE94
+#define D40_DREG_SCCIDB3	0xEA4
+#define D40_DREG_SCCIDB4	0xEB4
+#define D40_DREG_SCCIDB5	0xEC4
+
+#define D40_DREG_PRSCCIDA	0xF80
+#define D40_DREG_PRSCCIDB	0xF84
+
 #define D40_DREG_STFU		0xFC8
 #define D40_DREG_ICFG		0xFCC
 #define D40_DREG_PERIPHID0	0xFE0
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index f6c018f..fcee27e 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -63,6 +63,9 @@
 #define TEGRA_APBDMA_STATUS_COUNT_SHIFT		2
 #define TEGRA_APBDMA_STATUS_COUNT_MASK		0xFFFC
 
+#define TEGRA_APBDMA_CHAN_CSRE			0x00C
+#define TEGRA_APBDMA_CHAN_CSRE_PAUSE		(1 << 31)
+
 /* AHB memory address */
 #define TEGRA_APBDMA_CHAN_AHBPTR		0x010
 
@@ -113,10 +116,12 @@ struct tegra_dma;
  * tegra_dma_chip_data Tegra chip specific DMA data
  * @nr_channels: Number of channels available in the controller.
  * @max_dma_count: Maximum DMA transfer count supported by DMA controller.
+ * @support_channel_pause: Support channel wise pause of dma.
  */
 struct tegra_dma_chip_data {
 	int nr_channels;
 	int max_dma_count;
+	bool support_channel_pause;
 };
 
 /* DMA channel registers */
@@ -355,6 +360,32 @@ static void tegra_dma_global_resume(struct tegra_dma_channel *tdc)
 	spin_unlock(&tdma->global_lock);
 }
 
+static void tegra_dma_pause(struct tegra_dma_channel *tdc,
+	bool wait_for_burst_complete)
+{
+	struct tegra_dma *tdma = tdc->tdma;
+
+	if (tdma->chip_data->support_channel_pause) {
+		tdc_write(tdc, TEGRA_APBDMA_CHAN_CSRE,
+				TEGRA_APBDMA_CHAN_CSRE_PAUSE);
+		if (wait_for_burst_complete)
+			udelay(TEGRA_APBDMA_BURST_COMPLETE_TIME);
+	} else {
+		tegra_dma_global_pause(tdc, wait_for_burst_complete);
+	}
+}
+
+static void tegra_dma_resume(struct tegra_dma_channel *tdc)
+{
+	struct tegra_dma *tdma = tdc->tdma;
+
+	if (tdma->chip_data->support_channel_pause) {
+		tdc_write(tdc, TEGRA_APBDMA_CHAN_CSRE, 0);
+	} else {
+		tegra_dma_global_resume(tdc);
+	}
+}
+
 static void tegra_dma_stop(struct tegra_dma_channel *tdc)
 {
 	u32 csr;
@@ -410,7 +441,7 @@ static void tegra_dma_configure_for_next(struct tegra_dma_channel *tdc,
 	 * If there is already IEC status then interrupt handler need to
 	 * load new configuration.
 	 */
-	tegra_dma_global_pause(tdc, false);
+	tegra_dma_pause(tdc, false);
 	status  = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
 
 	/*
@@ -420,7 +451,7 @@ static void tegra_dma_configure_for_next(struct tegra_dma_channel *tdc,
 	if (status & TEGRA_APBDMA_STATUS_ISE_EOC) {
 		dev_err(tdc2dev(tdc),
 			"Skipping new configuration as interrupt is pending\n");
-		tegra_dma_global_resume(tdc);
+		tegra_dma_resume(tdc);
 		return;
 	}
 
@@ -431,7 +462,7 @@ static void tegra_dma_configure_for_next(struct tegra_dma_channel *tdc,
 				nsg_req->ch_regs.csr | TEGRA_APBDMA_CSR_ENB);
 	nsg_req->configured = true;
 
-	tegra_dma_global_resume(tdc);
+	tegra_dma_resume(tdc);
 }
 
 static void tdc_start_head_req(struct tegra_dma_channel *tdc)
@@ -692,7 +723,7 @@ static void tegra_dma_terminate_all(struct dma_chan *dc)
 		goto skip_dma_stop;
 
 	/* Pause DMA before checking the queue status */
-	tegra_dma_global_pause(tdc, true);
+	tegra_dma_pause(tdc, true);
 
 	status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
 	if (status & TEGRA_APBDMA_STATUS_ISE_EOC) {
@@ -710,7 +741,7 @@ static void tegra_dma_terminate_all(struct dma_chan *dc)
 		sgreq->dma_desc->bytes_transferred +=
 				get_current_xferred_count(tdc, sgreq, status);
 	}
-	tegra_dma_global_resume(tdc);
+	tegra_dma_resume(tdc);
 
 skip_dma_stop:
 	tegra_dma_abort_all(tdc);
@@ -738,7 +769,6 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 
 	ret = dma_cookie_status(dc, cookie, txstate);
 	if (ret == DMA_SUCCESS) {
-		dma_set_residue(txstate, 0);
 		spin_unlock_irqrestore(&tdc->lock, flags);
 		return ret;
 	}
@@ -1180,6 +1210,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)
 static const struct tegra_dma_chip_data tegra20_dma_chip_data = {
 	.nr_channels		= 16,
 	.max_dma_count		= 1024UL * 64,
+	.support_channel_pause	= false,
 };
 
 #if defined(CONFIG_OF)
@@ -1187,10 +1218,22 @@ static const struct tegra_dma_chip_data tegra20_dma_chip_data = {
 static const struct tegra_dma_chip_data tegra30_dma_chip_data = {
 	.nr_channels		= 32,
 	.max_dma_count		= 1024UL * 64,
+	.support_channel_pause	= false,
 };
 
+/* Tegra114 specific DMA controller information */
+static const struct tegra_dma_chip_data tegra114_dma_chip_data = {
+	.nr_channels		= 32,
+	.max_dma_count		= 1024UL * 64,
+	.support_channel_pause	= true,
+};
+
+
 static const struct of_device_id tegra_dma_of_match[] = {
 	{
+		.compatible = "nvidia,tegra114-apbdma",
+		.data = &tegra114_dma_chip_data,
+	}, {
 		.compatible = "nvidia,tegra30-apbdma",
 		.data = &tegra30_dma_chip_data,
 	}, {