diff --git a/arch/arm/include/asm/hardware/pl080.h b/arch/arm/include/asm/hardware/pl080.h
index e4a04e4e5627e998d7f3ff9a8fac4fb1ade84f95..33c78d7af2e15aaf2b7da93b708920fcefab9357 100644
--- a/arch/arm/include/asm/hardware/pl080.h
+++ b/arch/arm/include/asm/hardware/pl080.h
@@ -21,6 +21,9 @@
  * OneNAND features.
 */
 
+#ifndef ASM_PL080_H
+#define ASM_PL080_H
+
 #define PL080_INT_STATUS			(0x00)
 #define PL080_TC_STATUS				(0x04)
 #define PL080_TC_CLEAR				(0x08)
@@ -138,3 +141,4 @@ struct pl080s_lli {
 	u32	control1;
 };
 
+#endif /* ASM_PL080_H */
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index be21e3f138a88a6317da6e40318d3dc79d9bd5e1..3c2cad5b1165d7d458722bcdf714dc5e22c21c0b 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -66,28 +66,23 @@
  *    after the final transfer signalled by LBREQ or LSREQ.  The DMAC
  *    will then move to the next LLI entry.
  *
- * Only the former works sanely with scatter lists, so we only implement
- * the DMAC flow control method.  However, peripherals which use the LBREQ
- * and LSREQ signals (eg, MMCI) are unable to use this mode, which through
- * these hardware restrictions prevents them from using scatter DMA.
- *
  * Global TODO:
  * - Break out common code from arch/arm/mach-s3c64xx and share
  */
-#include <linux/device.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmapool.h>
-#include <linux/dmaengine.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/pl08x.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
-
+#include <linux/slab.h>
 #include <asm/hardware/pl080.h>
 
 #define DRIVER_NAME	"pl08xdmac"
@@ -126,7 +121,8 @@ struct pl08x_lli {
  * @phy_chans: array of data for the physical channels
  * @pool: a pool for the LLI descriptors
  * @pool_ctr: counter of LLIs in the pool
- * @lli_buses: bitmask to or in to LLI pointer selecting AHB port for LLI fetches
+ * @lli_buses: bitmask to or in to LLI pointer selecting AHB port for LLI
+ * fetches
  * @mem_buses: set to indicate memory transfers on AHB2.
  * @lock: a spinlock for this struct
  */
@@ -149,14 +145,6 @@ struct pl08x_driver_data {
  * PL08X specific defines
  */
 
-/*
- * Memory boundaries: the manual for PL08x says that the controller
- * cannot read past a 1KiB boundary, so these defines are used to
- * create transfer LLIs that do not cross such boundaries.
- */
-#define PL08X_BOUNDARY_SHIFT		(10)	/* 1KB 0x400 */
-#define PL08X_BOUNDARY_SIZE		(1 << PL08X_BOUNDARY_SHIFT)
-
 /* Size (bytes) of each LLI buffer allocated for one transfer */
 # define PL08X_LLI_TSFR_SIZE	0x2000
 
@@ -272,7 +260,6 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch)
 	writel(val, ch->base + PL080_CH_CONFIG);
 }
 
-
 /*
  * pl08x_terminate_phy_chan() stops the channel, clears the FIFO and
  * clears any pending interrupt status.  This should not be used for
@@ -407,6 +394,7 @@ pl08x_get_phy_channel(struct pl08x_driver_data *pl08x,
 		return NULL;
 	}
 
+	pm_runtime_get_sync(&pl08x->adev->dev);
 	return ch;
 }
 
@@ -420,6 +408,8 @@ static inline void pl08x_put_phy_channel(struct pl08x_driver_data *pl08x,
 	/* Stop the channel and clear its interrupts */
 	pl08x_terminate_phy_chan(pl08x, ch);
 
+	pm_runtime_put(&pl08x->adev->dev);
+
 	/* Mark it as free */
 	ch->serving = NULL;
 	spin_unlock_irqrestore(&ch->lock, flags);
@@ -499,36 +489,30 @@ struct pl08x_lli_build_data {
 };
 
 /*
- * Autoselect a master bus to use for the transfer this prefers the
- * destination bus if both available if fixed address on one bus the
- * other will be chosen
+ * Autoselect a master bus to use for the transfer. Slave will be the chosen as
+ * victim in case src & dest are not similarly aligned. i.e. If after aligning
+ * masters address with width requirements of transfer (by sending few byte by
+ * byte data), slave is still not aligned, then its width will be reduced to
+ * BYTE.
+ * - prefers the destination bus if both available
+ * - prefers bus with fixed address (i.e. peripheral)
  */
 static void pl08x_choose_master_bus(struct pl08x_lli_build_data *bd,
 	struct pl08x_bus_data **mbus, struct pl08x_bus_data **sbus, u32 cctl)
 {
 	if (!(cctl & PL080_CONTROL_DST_INCR)) {
-		*mbus = &bd->srcbus;
-		*sbus = &bd->dstbus;
-	} else if (!(cctl & PL080_CONTROL_SRC_INCR)) {
 		*mbus = &bd->dstbus;
 		*sbus = &bd->srcbus;
+	} else if (!(cctl & PL080_CONTROL_SRC_INCR)) {
+		*mbus = &bd->srcbus;
+		*sbus = &bd->dstbus;
 	} else {
-		if (bd->dstbus.buswidth == 4) {
+		if (bd->dstbus.buswidth >= bd->srcbus.buswidth) {
 			*mbus = &bd->dstbus;
 			*sbus = &bd->srcbus;
-		} else if (bd->srcbus.buswidth == 4) {
-			*mbus = &bd->srcbus;
-			*sbus = &bd->dstbus;
-		} else if (bd->dstbus.buswidth == 2) {
-			*mbus = &bd->dstbus;
-			*sbus = &bd->srcbus;
-		} else if (bd->srcbus.buswidth == 2) {
+		} else {
 			*mbus = &bd->srcbus;
 			*sbus = &bd->dstbus;
-		} else {
-			/* bd->srcbus.buswidth == 1 */
-			*mbus = &bd->dstbus;
-			*sbus = &bd->srcbus;
 		}
 	}
 }
@@ -547,7 +531,8 @@ static void pl08x_fill_lli_for_desc(struct pl08x_lli_build_data *bd,
 	llis_va[num_llis].cctl = cctl;
 	llis_va[num_llis].src = bd->srcbus.addr;
 	llis_va[num_llis].dst = bd->dstbus.addr;
-	llis_va[num_llis].lli = llis_bus + (num_llis + 1) * sizeof(struct pl08x_lli);
+	llis_va[num_llis].lli = llis_bus + (num_llis + 1) *
+		sizeof(struct pl08x_lli);
 	llis_va[num_llis].lli |= bd->lli_bus;
 
 	if (cctl & PL080_CONTROL_SRC_INCR)
@@ -560,16 +545,12 @@ static void pl08x_fill_lli_for_desc(struct pl08x_lli_build_data *bd,
 	bd->remainder -= len;
 }
 
-/*
- * Return number of bytes to fill to boundary, or len.
- * This calculation works for any value of addr.
- */
-static inline size_t pl08x_pre_boundary(u32 addr, size_t len)
+static inline void prep_byte_width_lli(struct pl08x_lli_build_data *bd,
+		u32 *cctl, u32 len, int num_llis, size_t *total_bytes)
 {
-	size_t boundary_len = PL08X_BOUNDARY_SIZE -
-			(addr & (PL08X_BOUNDARY_SIZE - 1));
-
-	return min(boundary_len, len);
+	*cctl = pl08x_cctl_bits(*cctl, 1, 1, len);
+	pl08x_fill_lli_for_desc(bd, num_llis, len, *cctl);
+	(*total_bytes) += len;
 }
 
 /*
@@ -583,13 +564,11 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	struct pl08x_bus_data *mbus, *sbus;
 	struct pl08x_lli_build_data bd;
 	int num_llis = 0;
-	u32 cctl;
-	size_t max_bytes_per_lli;
-	size_t total_bytes = 0;
+	u32 cctl, early_bytes = 0;
+	size_t max_bytes_per_lli, total_bytes = 0;
 	struct pl08x_lli *llis_va;
 
-	txd->llis_va = dma_pool_alloc(pl08x->pool, GFP_NOWAIT,
-				      &txd->llis_bus);
+	txd->llis_va = dma_pool_alloc(pl08x->pool, GFP_NOWAIT, &txd->llis_bus);
 	if (!txd->llis_va) {
 		dev_err(&pl08x->adev->dev, "%s no memory for llis\n", __func__);
 		return 0;
@@ -619,55 +598,85 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	bd.srcbus.buswidth = bd.srcbus.maxwidth;
 	bd.dstbus.buswidth = bd.dstbus.maxwidth;
 
-	/*
-	 * Bytes transferred == tsize * MIN(buswidths), not max(buswidths)
-	 */
-	max_bytes_per_lli = min(bd.srcbus.buswidth, bd.dstbus.buswidth) *
-		PL080_CONTROL_TRANSFER_SIZE_MASK;
-
 	/* We need to count this down to zero */
 	bd.remainder = txd->len;
 
-	/*
-	 * Choose bus to align to
-	 * - prefers destination bus if both available
-	 * - if fixed address on one bus chooses other
-	 */
 	pl08x_choose_master_bus(&bd, &mbus, &sbus, cctl);
 
-	dev_vdbg(&pl08x->adev->dev, "src=0x%08x%s/%u dst=0x%08x%s/%u len=%zu llimax=%zu\n",
+	dev_vdbg(&pl08x->adev->dev, "src=0x%08x%s/%u dst=0x%08x%s/%u len=%zu\n",
 		 bd.srcbus.addr, cctl & PL080_CONTROL_SRC_INCR ? "+" : "",
 		 bd.srcbus.buswidth,
 		 bd.dstbus.addr, cctl & PL080_CONTROL_DST_INCR ? "+" : "",
 		 bd.dstbus.buswidth,
-		 bd.remainder, max_bytes_per_lli);
+		 bd.remainder);
 	dev_vdbg(&pl08x->adev->dev, "mbus=%s sbus=%s\n",
 		 mbus == &bd.srcbus ? "src" : "dst",
 		 sbus == &bd.srcbus ? "src" : "dst");
 
-	if (txd->len < mbus->buswidth) {
-		/* Less than a bus width available - send as single bytes */
-		while (bd.remainder) {
-			dev_vdbg(&pl08x->adev->dev,
-				 "%s single byte LLIs for a transfer of "
-				 "less than a bus width (remain 0x%08x)\n",
-				 __func__, bd.remainder);
-			cctl = pl08x_cctl_bits(cctl, 1, 1, 1);
-			pl08x_fill_lli_for_desc(&bd, num_llis++, 1, cctl);
-			total_bytes++;
+	/*
+	 * Zero length is only allowed if all these requirements are met:
+	 * - flow controller is peripheral.
+	 * - src.addr is aligned to src.width
+	 * - dst.addr is aligned to dst.width
+	 *
+	 * sg_len == 1 should be true, as there can be two cases here:
+	 * - Memory addresses are contiguous and are not scattered. Here, Only
+	 * one sg will be passed by user driver, with memory address and zero
+	 * length. We pass this to controller and after the transfer it will
+	 * receive the last burst request from peripheral and so transfer
+	 * finishes.
+	 *
+	 * - Memory addresses are scattered and are not contiguous. Here,
+	 * Obviously as DMA controller doesn't know when a lli's transfer gets
+	 * over, it can't load next lli. So in this case, there has to be an
+	 * assumption that only one lli is supported. Thus, we can't have
+	 * scattered addresses.
+	 */
+	if (!bd.remainder) {
+		u32 fc = (txd->ccfg & PL080_CONFIG_FLOW_CONTROL_MASK) >>
+			PL080_CONFIG_FLOW_CONTROL_SHIFT;
+		if (!((fc >= PL080_FLOW_SRC2DST_DST) &&
+					(fc <= PL080_FLOW_SRC2DST_SRC))) {
+			dev_err(&pl08x->adev->dev, "%s sg len can't be zero",
+				__func__);
+			return 0;
 		}
-	} else {
-		/* Make one byte LLIs until master bus is aligned */
-		while ((mbus->addr) % (mbus->buswidth)) {
-			dev_vdbg(&pl08x->adev->dev,
-				"%s adjustment lli for less than bus width "
-				 "(remain 0x%08x)\n",
-				 __func__, bd.remainder);
-			cctl = pl08x_cctl_bits(cctl, 1, 1, 1);
-			pl08x_fill_lli_for_desc(&bd, num_llis++, 1, cctl);
-			total_bytes++;
+
+		if ((bd.srcbus.addr % bd.srcbus.buswidth) ||
+				(bd.srcbus.addr % bd.srcbus.buswidth)) {
+			dev_err(&pl08x->adev->dev,
+				"%s src & dst address must be aligned to src"
+				" & dst width if peripheral is flow controller",
+				__func__);
+			return 0;
 		}
 
+		cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth,
+				bd.dstbus.buswidth, 0);
+		pl08x_fill_lli_for_desc(&bd, num_llis++, 0, cctl);
+	}
+
+	/*
+	 * Send byte by byte for following cases
+	 * - Less than a bus width available
+	 * - until master bus is aligned
+	 */
+	if (bd.remainder < mbus->buswidth)
+		early_bytes = bd.remainder;
+	else if ((mbus->addr) % (mbus->buswidth)) {
+		early_bytes = mbus->buswidth - (mbus->addr) % (mbus->buswidth);
+		if ((bd.remainder - early_bytes) < mbus->buswidth)
+			early_bytes = bd.remainder;
+	}
+
+	if (early_bytes) {
+		dev_vdbg(&pl08x->adev->dev, "%s byte width LLIs "
+				"(remain 0x%08x)\n", __func__, bd.remainder);
+		prep_byte_width_lli(&bd, &cctl, early_bytes, num_llis++,
+				&total_bytes);
+	}
+
+	if (bd.remainder) {
 		/*
 		 * Master now aligned
 		 * - if slave is not then we must set its width down
@@ -680,138 +689,55 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 			sbus->buswidth = 1;
 		}
 
+		/* Bytes transferred = tsize * src width, not MIN(buswidths) */
+		max_bytes_per_lli = bd.srcbus.buswidth *
+			PL080_CONTROL_TRANSFER_SIZE_MASK;
+
 		/*
 		 * Make largest possible LLIs until less than one bus
 		 * width left
 		 */
 		while (bd.remainder > (mbus->buswidth - 1)) {
-			size_t lli_len, target_len, tsize, odd_bytes;
+			size_t lli_len, tsize, width;
 
 			/*
 			 * If enough left try to send max possible,
 			 * otherwise try to send the remainder
 			 */
-			target_len = min(bd.remainder, max_bytes_per_lli);
+			lli_len = min(bd.remainder, max_bytes_per_lli);
 
 			/*
-			 * Set bus lengths for incrementing buses to the
-			 * number of bytes which fill to next memory boundary,
-			 * limiting on the target length calculated above.
+			 * Check against maximum bus alignment: Calculate actual
+			 * transfer size in relation to bus width and get a
+			 * maximum remainder of the highest bus width - 1
 			 */
-			if (cctl & PL080_CONTROL_SRC_INCR)
-				bd.srcbus.fill_bytes =
-					pl08x_pre_boundary(bd.srcbus.addr,
-						target_len);
-			else
-				bd.srcbus.fill_bytes = target_len;
-
-			if (cctl & PL080_CONTROL_DST_INCR)
-				bd.dstbus.fill_bytes =
-					pl08x_pre_boundary(bd.dstbus.addr,
-						target_len);
-			else
-				bd.dstbus.fill_bytes = target_len;
-
-			/* Find the nearest */
-			lli_len	= min(bd.srcbus.fill_bytes,
-				      bd.dstbus.fill_bytes);
-
-			BUG_ON(lli_len > bd.remainder);
-
-			if (lli_len <= 0) {
-				dev_err(&pl08x->adev->dev,
-					"%s lli_len is %zu, <= 0\n",
-						__func__, lli_len);
-				return 0;
-			}
+			width = max(mbus->buswidth, sbus->buswidth);
+			lli_len = (lli_len / width) * width;
+			tsize = lli_len / bd.srcbus.buswidth;
 
-			if (lli_len == target_len) {
-				/*
-				 * Can send what we wanted.
-				 * Maintain alignment
-				 */
-				lli_len	= (lli_len/mbus->buswidth) *
-							mbus->buswidth;
-				odd_bytes = 0;
-			} else {
-				/*
-				 * So now we know how many bytes to transfer
-				 * to get to the nearest boundary.  The next
-				 * LLI will past the boundary.  However, we
-				 * may be working to a boundary on the slave
-				 * bus.  We need to ensure the master stays
-				 * aligned, and that we are working in
-				 * multiples of the bus widths.
-				 */
-				odd_bytes = lli_len % mbus->buswidth;
-				lli_len -= odd_bytes;
-
-			}
-
-			if (lli_len) {
-				/*
-				 * Check against minimum bus alignment:
-				 * Calculate actual transfer size in relation
-				 * to bus width an get a maximum remainder of
-				 * the smallest bus width - 1
-				 */
-				/* FIXME: use round_down()? */
-				tsize = lli_len / min(mbus->buswidth,
-						      sbus->buswidth);
-				lli_len	= tsize * min(mbus->buswidth,
-						      sbus->buswidth);
-
-				if (target_len != lli_len) {
-					dev_vdbg(&pl08x->adev->dev,
-					"%s can't send what we want. Desired 0x%08zx, lli of 0x%08zx bytes in txd of 0x%08zx\n",
-					__func__, target_len, lli_len, txd->len);
-				}
-
-				cctl = pl08x_cctl_bits(cctl,
-						       bd.srcbus.buswidth,
-						       bd.dstbus.buswidth,
-						       tsize);
-
-				dev_vdbg(&pl08x->adev->dev,
-					"%s fill lli with single lli chunk of size 0x%08zx (remainder 0x%08zx)\n",
-					__func__, lli_len, bd.remainder);
-				pl08x_fill_lli_for_desc(&bd, num_llis++,
-					lli_len, cctl);
-				total_bytes += lli_len;
-			}
-
-
-			if (odd_bytes) {
-				/*
-				 * Creep past the boundary, maintaining
-				 * master alignment
-				 */
-				int j;
-				for (j = 0; (j < mbus->buswidth)
-						&& (bd.remainder); j++) {
-					cctl = pl08x_cctl_bits(cctl, 1, 1, 1);
-					dev_vdbg(&pl08x->adev->dev,
-						"%s align with boundary, single byte (remain 0x%08zx)\n",
-						__func__, bd.remainder);
-					pl08x_fill_lli_for_desc(&bd,
-						num_llis++, 1, cctl);
-					total_bytes++;
-				}
-			}
+			dev_vdbg(&pl08x->adev->dev,
+				"%s fill lli with single lli chunk of "
+				"size 0x%08zx (remainder 0x%08zx)\n",
+				__func__, lli_len, bd.remainder);
+
+			cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth,
+					bd.dstbus.buswidth, tsize);
+			pl08x_fill_lli_for_desc(&bd, num_llis++, lli_len, cctl);
+			total_bytes += lli_len;
 		}
 
 		/*
 		 * Send any odd bytes
 		 */
-		while (bd.remainder) {
-			cctl = pl08x_cctl_bits(cctl, 1, 1, 1);
+		if (bd.remainder) {
 			dev_vdbg(&pl08x->adev->dev,
-				"%s align with boundary, single odd byte (remain %zu)\n",
+				"%s align with boundary, send odd bytes (remain %zu)\n",
 				__func__, bd.remainder);
-			pl08x_fill_lli_for_desc(&bd, num_llis++, 1, cctl);
-			total_bytes++;
+			prep_byte_width_lli(&bd, &cctl, bd.remainder,
+					num_llis++, &total_bytes);
 		}
 	}
+
 	if (total_bytes != txd->len) {
 		dev_err(&pl08x->adev->dev,
 			"%s size of encoded lli:s don't match total txd, transferred 0x%08zx from size 0x%08zx\n",
@@ -917,9 +843,7 @@ static int prep_phy_channel(struct pl08x_dma_chan *plchan,
 	 * need, but for slaves the physical signals may be muxed!
 	 * Can the platform allow us to use this channel?
 	 */
-	if (plchan->slave &&
-	    ch->signal < 0 &&
-	    pl08x->pd->get_signal) {
+	if (plchan->slave && pl08x->pd->get_signal) {
 		ret = pl08x->pd->get_signal(plchan);
 		if (ret < 0) {
 			dev_dbg(&pl08x->adev->dev,
@@ -1008,10 +932,8 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_interrupt(
  * If slaves are relying on interrupts to signal completion this function
  * must not be called with interrupts disabled.
  */
-static enum dma_status
-pl08x_dma_tx_status(struct dma_chan *chan,
-		    dma_cookie_t cookie,
-		    struct dma_tx_state *txstate)
+static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	dma_cookie_t last_used;
@@ -1253,7 +1175,9 @@ static int pl08x_prep_channel_resources(struct pl08x_dma_chan *plchan,
 
 	num_llis = pl08x_fill_llis_for_desc(pl08x, txd);
 	if (!num_llis) {
-		kfree(txd);
+		spin_lock_irqsave(&plchan->lock, flags);
+		pl08x_free_txd(pl08x, txd);
+		spin_unlock_irqrestore(&plchan->lock, flags);
 		return -EINVAL;
 	}
 
@@ -1301,7 +1225,7 @@ static int pl08x_prep_channel_resources(struct pl08x_dma_chan *plchan,
 static struct pl08x_txd *pl08x_get_txd(struct pl08x_dma_chan *plchan,
 	unsigned long flags)
 {
-	struct pl08x_txd *txd = kzalloc(sizeof(struct pl08x_txd), GFP_NOWAIT);
+	struct pl08x_txd *txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
 
 	if (txd) {
 		dma_async_tx_descriptor_init(&txd->tx, &plchan->chan);
@@ -1367,7 +1291,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
 	struct pl08x_txd *txd;
-	int ret;
+	int ret, tmp;
 
 	/*
 	 * Current implementation ASSUMES only one sg
@@ -1401,12 +1325,10 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	txd->len = sgl->length;
 
 	if (direction == DMA_TO_DEVICE) {
-		txd->ccfg |= PL080_FLOW_MEM2PER << PL080_CONFIG_FLOW_CONTROL_SHIFT;
 		txd->cctl = plchan->dst_cctl;
 		txd->src_addr = sgl->dma_address;
 		txd->dst_addr = plchan->dst_addr;
 	} else if (direction == DMA_FROM_DEVICE) {
-		txd->ccfg |= PL080_FLOW_PER2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT;
 		txd->cctl = plchan->src_cctl;
 		txd->src_addr = plchan->src_addr;
 		txd->dst_addr = sgl->dma_address;
@@ -1416,6 +1338,15 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 		return NULL;
 	}
 
+	if (plchan->cd->device_fc)
+		tmp = (direction == DMA_TO_DEVICE) ? PL080_FLOW_MEM2PER_PER :
+			PL080_FLOW_PER2MEM_PER;
+	else
+		tmp = (direction == DMA_TO_DEVICE) ? PL080_FLOW_MEM2PER :
+			PL080_FLOW_PER2MEM;
+
+	txd->ccfg |= tmp << PL080_CONFIG_FLOW_CONTROL_SHIFT;
+
 	ret = pl08x_prep_channel_resources(plchan, txd);
 	if (ret)
 		return NULL;
@@ -1507,13 +1438,7 @@ bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
  */
 static void pl08x_ensure_on(struct pl08x_driver_data *pl08x)
 {
-	u32 val;
-
-	val = readl(pl08x->base + PL080_CONFIG);
-	val &= ~(PL080_CONFIG_M2_BE | PL080_CONFIG_M1_BE | PL080_CONFIG_ENABLE);
-	/* We implicitly clear bit 1 and that means little-endian mode */
-	val |= PL080_CONFIG_ENABLE;
-	writel(val, pl08x->base + PL080_CONFIG);
+	writel(PL080_CONFIG_ENABLE, pl08x->base + PL080_CONFIG);
 }
 
 static void pl08x_unmap_buffers(struct pl08x_txd *txd)
@@ -1589,8 +1514,8 @@ static void pl08x_tasklet(unsigned long data)
 		 */
 		list_for_each_entry(waiting, &pl08x->memcpy.channels,
 				    chan.device_node) {
-		  if (waiting->state == PL08X_CHAN_WAITING &&
-			    waiting->waiting != NULL) {
+			if (waiting->state == PL08X_CHAN_WAITING &&
+				waiting->waiting != NULL) {
 				int ret;
 
 				/* This should REALLY not fail now */
@@ -1630,38 +1555,40 @@ static void pl08x_tasklet(unsigned long data)
 static irqreturn_t pl08x_irq(int irq, void *dev)
 {
 	struct pl08x_driver_data *pl08x = dev;
-	u32 mask = 0;
-	u32 val;
-	int i;
-
-	val = readl(pl08x->base + PL080_ERR_STATUS);
-	if (val) {
-		/* An error interrupt (on one or more channels) */
-		dev_err(&pl08x->adev->dev,
-			"%s error interrupt, register value 0x%08x\n",
-				__func__, val);
-		/*
-		 * Simply clear ALL PL08X error interrupts,
-		 * regardless of channel and cause
-		 * FIXME: should be 0x00000003 on PL081 really.
-		 */
-		writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR);
+	u32 mask = 0, err, tc, i;
+
+	/* check & clear - ERR & TC interrupts */
+	err = readl(pl08x->base + PL080_ERR_STATUS);
+	if (err) {
+		dev_err(&pl08x->adev->dev, "%s error interrupt, register value 0x%08x\n",
+			__func__, err);
+		writel(err, pl08x->base + PL080_ERR_CLEAR);
 	}
-	val = readl(pl08x->base + PL080_INT_STATUS);
+	tc = readl(pl08x->base + PL080_INT_STATUS);
+	if (tc)
+		writel(tc, pl08x->base + PL080_TC_CLEAR);
+
+	if (!err && !tc)
+		return IRQ_NONE;
+
 	for (i = 0; i < pl08x->vd->channels; i++) {
-		if ((1 << i) & val) {
+		if (((1 << i) & err) || ((1 << i) & tc)) {
 			/* Locate physical channel */
 			struct pl08x_phy_chan *phychan = &pl08x->phy_chans[i];
 			struct pl08x_dma_chan *plchan = phychan->serving;
 
+			if (!plchan) {
+				dev_err(&pl08x->adev->dev,
+					"%s Error TC interrupt on unused channel: 0x%08x\n",
+					__func__, i);
+				continue;
+			}
+
 			/* Schedule tasklet on this channel */
 			tasklet_schedule(&plchan->tasklet);
-
 			mask |= (1 << i);
 		}
 	}
-	/* Clear only the terminal interrupts on channels we processed */
-	writel(mask, pl08x->base + PL080_TC_CLEAR);
 
 	return mask ? IRQ_HANDLED : IRQ_NONE;
 }
@@ -1685,9 +1612,7 @@ static void pl08x_dma_slave_init(struct pl08x_dma_chan *chan)
  * Make a local wrapper to hold required data
  */
 static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
-					   struct dma_device *dmadev,
-					   unsigned int channels,
-					   bool slave)
+		struct dma_device *dmadev, unsigned int channels, bool slave)
 {
 	struct pl08x_dma_chan *chan;
 	int i;
@@ -1700,7 +1625,7 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
 	 * to cope with that situation.
 	 */
 	for (i = 0; i < channels; i++) {
-		chan = kzalloc(sizeof(struct pl08x_dma_chan), GFP_KERNEL);
+		chan = kzalloc(sizeof(*chan), GFP_KERNEL);
 		if (!chan) {
 			dev_err(&pl08x->adev->dev,
 				"%s no memory for channel\n", __func__);
@@ -1728,7 +1653,7 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
 			kfree(chan);
 			continue;
 		}
-		dev_info(&pl08x->adev->dev,
+		dev_dbg(&pl08x->adev->dev,
 			 "initialize virtual channel \"%s\"\n",
 			 chan->name);
 
@@ -1837,9 +1762,9 @@ static const struct file_operations pl08x_debugfs_operations = {
 static void init_pl08x_debugfs(struct pl08x_driver_data *pl08x)
 {
 	/* Expose a simple debugfs interface to view all clocks */
-	(void) debugfs_create_file(dev_name(&pl08x->adev->dev), S_IFREG | S_IRUGO,
-				   NULL, pl08x,
-				   &pl08x_debugfs_operations);
+	(void) debugfs_create_file(dev_name(&pl08x->adev->dev),
+			S_IFREG | S_IRUGO, NULL, pl08x,
+			&pl08x_debugfs_operations);
 }
 
 #else
@@ -1860,12 +1785,15 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		return ret;
 
 	/* Create the driver state holder */
-	pl08x = kzalloc(sizeof(struct pl08x_driver_data), GFP_KERNEL);
+	pl08x = kzalloc(sizeof(*pl08x), GFP_KERNEL);
 	if (!pl08x) {
 		ret = -ENOMEM;
 		goto out_no_pl08x;
 	}
 
+	pm_runtime_set_active(&adev->dev);
+	pm_runtime_enable(&adev->dev);
+
 	/* Initialize memcpy engine */
 	dma_cap_set(DMA_MEMCPY, pl08x->memcpy.cap_mask);
 	pl08x->memcpy.dev = &adev->dev;
@@ -1939,7 +1867,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	}
 
 	/* Initialize physical channels */
-	pl08x->phy_chans = kmalloc((vd->channels * sizeof(struct pl08x_phy_chan)),
+	pl08x->phy_chans = kmalloc((vd->channels * sizeof(*pl08x->phy_chans)),
 			GFP_KERNEL);
 	if (!pl08x->phy_chans) {
 		dev_err(&adev->dev, "%s failed to allocate "
@@ -1956,9 +1884,8 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		spin_lock_init(&ch->lock);
 		ch->serving = NULL;
 		ch->signal = -1;
-		dev_info(&adev->dev,
-			 "physical channel %d is %s\n", i,
-			 pl08x_phy_channel_busy(ch) ? "BUSY" : "FREE");
+		dev_dbg(&adev->dev, "physical channel %d is %s\n",
+			i, pl08x_phy_channel_busy(ch) ? "BUSY" : "FREE");
 	}
 
 	/* Register as many memcpy channels as there are physical channels */
@@ -1974,8 +1901,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 
 	/* Register slave channels */
 	ret = pl08x_dma_init_virtual_channels(pl08x, &pl08x->slave,
-					      pl08x->pd->num_slave_channels,
-					      true);
+			pl08x->pd->num_slave_channels, true);
 	if (ret <= 0) {
 		dev_warn(&pl08x->adev->dev,
 			"%s failed to enumerate slave channels - %d\n",
@@ -2005,6 +1931,8 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	dev_info(&pl08x->adev->dev, "DMA: PL%03x rev%u at 0x%08llx irq %d\n",
 		 amba_part(adev), amba_rev(adev),
 		 (unsigned long long)adev->res.start, adev->irq[0]);
+
+	pm_runtime_put(&adev->dev);
 	return 0;
 
 out_no_slave_reg:
@@ -2023,6 +1951,9 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	dma_pool_destroy(pl08x->pool);
 out_no_lli_pool:
 out_no_platdata:
+	pm_runtime_put(&adev->dev);
+	pm_runtime_disable(&adev->dev);
+
 	kfree(pl08x);
 out_no_pl08x:
 	amba_release_regions(adev);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 6a483eac7b3f2d971cabae0aceaf022a42866558..3b99dc62874b5640be9383a70657d593f9cc31e7 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -107,10 +107,11 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 {
 	struct at_desc *desc, *_desc;
 	struct at_desc *ret = NULL;
+	unsigned long flags;
 	unsigned int i = 0;
 	LIST_HEAD(tmp_list);
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
 		i++;
 		if (async_tx_test_ack(&desc->txd)) {
@@ -121,7 +122,7 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 		dev_dbg(chan2dev(&atchan->chan_common),
 				"desc %p not ACKed\n", desc);
 	}
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"scanned %u descriptors on freelist\n", i);
 
@@ -129,9 +130,9 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 	if (!ret) {
 		ret = atc_alloc_descriptor(&atchan->chan_common, GFP_ATOMIC);
 		if (ret) {
-			spin_lock_bh(&atchan->lock);
+			spin_lock_irqsave(&atchan->lock, flags);
 			atchan->descs_allocated++;
-			spin_unlock_bh(&atchan->lock);
+			spin_unlock_irqrestore(&atchan->lock, flags);
 		} else {
 			dev_err(chan2dev(&atchan->chan_common),
 					"not enough descriptors available\n");
@@ -150,8 +151,9 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 {
 	if (desc) {
 		struct at_desc *child;
+		unsigned long flags;
 
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, flags);
 		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&atchan->chan_common),
 					"moving child desc %p to freelist\n",
@@ -160,7 +162,7 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 		dev_vdbg(chan2dev(&atchan->chan_common),
 			 "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &atchan->free_list);
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, flags);
 	}
 }
 
@@ -299,7 +301,7 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 
 	/* for cyclic transfers,
 	 * no need to replay callback function while stopping */
-	if (!test_bit(ATC_IS_CYCLIC, &atchan->status)) {
+	if (!atc_chan_is_cyclic(atchan)) {
 		dma_async_tx_callback	callback = txd->callback;
 		void			*param = txd->callback_param;
 
@@ -471,16 +473,17 @@ static void atc_handle_cyclic(struct at_dma_chan *atchan)
 static void atc_tasklet(unsigned long data)
 {
 	struct at_dma_chan *atchan = (struct at_dma_chan *)data;
+	unsigned long flags;
 
-	spin_lock(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	if (test_and_clear_bit(ATC_IS_ERROR, &atchan->status))
 		atc_handle_error(atchan);
-	else if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+	else if (atc_chan_is_cyclic(atchan))
 		atc_handle_cyclic(atchan);
 	else
 		atc_advance_work(atchan);
 
-	spin_unlock(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
 static irqreturn_t at_dma_interrupt(int irq, void *dev_id)
@@ -539,8 +542,9 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct at_desc		*desc = txd_to_at_desc(tx);
 	struct at_dma_chan	*atchan = to_at_dma_chan(tx->chan);
 	dma_cookie_t		cookie;
+	unsigned long		flags;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	cookie = atc_assign_cookie(atchan, desc);
 
 	if (list_empty(&atchan->active_list)) {
@@ -554,7 +558,7 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 		list_add_tail(&desc->desc_node, &atchan->queue);
 	}
 
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return cookie;
 }
@@ -927,28 +931,29 @@ static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma		*atdma = to_at_dma(chan->device);
 	int			chan_id = atchan->chan_common.chan_id;
+	unsigned long		flags;
 
 	LIST_HEAD(list);
 
 	dev_vdbg(chan2dev(chan), "atc_control (%d)\n", cmd);
 
 	if (cmd == DMA_PAUSE) {
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, flags);
 
 		dma_writel(atdma, CHER, AT_DMA_SUSP(chan_id));
 		set_bit(ATC_IS_PAUSED, &atchan->status);
 
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, flags);
 	} else if (cmd == DMA_RESUME) {
-		if (!test_bit(ATC_IS_PAUSED, &atchan->status))
+		if (!atc_chan_is_paused(atchan))
 			return 0;
 
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, flags);
 
 		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id));
 		clear_bit(ATC_IS_PAUSED, &atchan->status);
 
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, flags);
 	} else if (cmd == DMA_TERMINATE_ALL) {
 		struct at_desc	*desc, *_desc;
 		/*
@@ -957,7 +962,7 @@ static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		 * channel. We still have to poll the channel enable bit due
 		 * to AHB/HSB limitations.
 		 */
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, flags);
 
 		/* disabling channel: must also remove suspend state */
 		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id) | atchan->mask);
@@ -978,7 +983,7 @@ static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		/* if channel dedicated to cyclic operations, free it */
 		clear_bit(ATC_IS_CYCLIC, &atchan->status);
 
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, flags);
 	} else {
 		return -ENXIO;
 	}
@@ -1004,9 +1009,10 @@ atc_tx_status(struct dma_chan *chan,
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	dma_cookie_t		last_used;
 	dma_cookie_t		last_complete;
+	unsigned long		flags;
 	enum dma_status		ret;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 
 	last_complete = atchan->completed_cookie;
 	last_used = chan->cookie;
@@ -1021,7 +1027,7 @@ atc_tx_status(struct dma_chan *chan,
 		ret = dma_async_is_complete(cookie, last_complete, last_used);
 	}
 
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	if (ret != DMA_SUCCESS)
 		dma_set_tx_state(txstate, last_complete, last_used,
@@ -1029,7 +1035,7 @@ atc_tx_status(struct dma_chan *chan,
 	else
 		dma_set_tx_state(txstate, last_complete, last_used, 0);
 
-	if (test_bit(ATC_IS_PAUSED, &atchan->status))
+	if (atc_chan_is_paused(atchan))
 		ret = DMA_PAUSED;
 
 	dev_vdbg(chan2dev(chan), "tx_status %d: cookie = %d (d%d, u%d)\n",
@@ -1046,18 +1052,19 @@ atc_tx_status(struct dma_chan *chan,
 static void atc_issue_pending(struct dma_chan *chan)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	unsigned long		flags;
 
 	dev_vdbg(chan2dev(chan), "issue_pending\n");
 
 	/* Not needed for cyclic transfers */
-	if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+	if (atc_chan_is_cyclic(atchan))
 		return;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	if (!atc_chan_is_enabled(atchan)) {
 		atc_advance_work(atchan);
 	}
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
 /**
@@ -1073,6 +1080,7 @@ static int atc_alloc_chan_resources(struct dma_chan *chan)
 	struct at_dma		*atdma = to_at_dma(chan->device);
 	struct at_desc		*desc;
 	struct at_dma_slave	*atslave;
+	unsigned long		flags;
 	int			i;
 	u32			cfg;
 	LIST_HEAD(tmp_list);
@@ -1116,11 +1124,11 @@ static int atc_alloc_chan_resources(struct dma_chan *chan)
 		list_add_tail(&desc->desc_node, &tmp_list);
 	}
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	atchan->descs_allocated = i;
 	list_splice(&tmp_list, &atchan->free_list);
 	atchan->completed_cookie = chan->cookie = 1;
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	/* channel parameters */
 	channel_writel(atchan, CFG, cfg);
@@ -1293,15 +1301,13 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
-	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask))
+	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
 		atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
-
-	if (dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
+		/* controller can do slave DMA: can trigger cyclic transfers */
+		dma_cap_set(DMA_CYCLIC, atdma->dma_common.cap_mask);
 		atdma->dma_common.device_prep_dma_cyclic = atc_prep_dma_cyclic;
-
-	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask) ||
-	    dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_control = atc_control;
+	}
 
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 
@@ -1377,27 +1383,112 @@ static void at_dma_shutdown(struct platform_device *pdev)
 	clk_disable(atdma->clk);
 }
 
+static int at_dma_prepare(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct at_dma *atdma = platform_get_drvdata(pdev);
+	struct dma_chan *chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan, &atdma->dma_common.channels,
+			device_node) {
+		struct at_dma_chan *atchan = to_at_dma_chan(chan);
+		/* wait for transaction completion (except in cyclic case) */
+		if (atc_chan_is_enabled(atchan) && !atc_chan_is_cyclic(atchan))
+			return -EAGAIN;
+	}
+	return 0;
+}
+
+static void atc_suspend_cyclic(struct at_dma_chan *atchan)
+{
+	struct dma_chan	*chan = &atchan->chan_common;
+
+	/* Channel should be paused by user
+	 * do it anyway even if it is not done already */
+	if (!atc_chan_is_paused(atchan)) {
+		dev_warn(chan2dev(chan),
+		"cyclic channel not paused, should be done by channel user\n");
+		atc_control(chan, DMA_PAUSE, 0);
+	}
+
+	/* now preserve additional data for cyclic operations */
+	/* next descriptor address in the cyclic list */
+	atchan->save_dscr = channel_readl(atchan, DSCR);
+
+	vdbg_dump_regs(atchan);
+}
+
 static int at_dma_suspend_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct at_dma *atdma = platform_get_drvdata(pdev);
+	struct dma_chan *chan, *_chan;
 
-	at_dma_off(platform_get_drvdata(pdev));
+	/* preserve data */
+	list_for_each_entry_safe(chan, _chan, &atdma->dma_common.channels,
+			device_node) {
+		struct at_dma_chan *atchan = to_at_dma_chan(chan);
+
+		if (atc_chan_is_cyclic(atchan))
+			atc_suspend_cyclic(atchan);
+		atchan->save_cfg = channel_readl(atchan, CFG);
+	}
+	atdma->save_imr = dma_readl(atdma, EBCIMR);
+
+	/* disable DMA controller */
+	at_dma_off(atdma);
 	clk_disable(atdma->clk);
 	return 0;
 }
 
+static void atc_resume_cyclic(struct at_dma_chan *atchan)
+{
+	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
+
+	/* restore channel status for cyclic descriptors list:
+	 * next descriptor in the cyclic list at the time of suspend */
+	channel_writel(atchan, SADDR, 0);
+	channel_writel(atchan, DADDR, 0);
+	channel_writel(atchan, CTRLA, 0);
+	channel_writel(atchan, CTRLB, 0);
+	channel_writel(atchan, DSCR, atchan->save_dscr);
+	dma_writel(atdma, CHER, atchan->mask);
+
+	/* channel pause status should be removed by channel user
+	 * We cannot take the initiative to do it here */
+
+	vdbg_dump_regs(atchan);
+}
+
 static int at_dma_resume_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct at_dma *atdma = platform_get_drvdata(pdev);
+	struct dma_chan *chan, *_chan;
 
+	/* bring back DMA controller */
 	clk_enable(atdma->clk);
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
+
+	/* clear any pending interrupt */
+	while (dma_readl(atdma, EBCISR))
+		cpu_relax();
+
+	/* restore saved data */
+	dma_writel(atdma, EBCIER, atdma->save_imr);
+	list_for_each_entry_safe(chan, _chan, &atdma->dma_common.channels,
+			device_node) {
+		struct at_dma_chan *atchan = to_at_dma_chan(chan);
+
+		channel_writel(atchan, CFG, atchan->save_cfg);
+		if (atc_chan_is_cyclic(atchan))
+			atc_resume_cyclic(atchan);
+	}
 	return 0;
 }
 
 static const struct dev_pm_ops at_dma_dev_pm_ops = {
+	.prepare = at_dma_prepare,
 	.suspend_noirq = at_dma_suspend_noirq,
 	.resume_noirq = at_dma_resume_noirq,
 };
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 087dbf1dd39cc0d87416e24e093ca7841a714b3f..aa4c9aebab7cedec68a42aececeb218aaea0208b 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -204,6 +204,9 @@ enum atc_status {
  * @status: transmit status information from irq/prep* functions
  *                to tasklet (use atomic operations)
  * @tasklet: bottom half to finish transaction work
+ * @save_cfg: configuration register that is saved on suspend/resume cycle
+ * @save_dscr: for cyclic operations, preserve next descriptor address in
+ *             the cyclic list on suspend/resume cycle
  * @lock: serializes enqueue/dequeue operations to descriptors lists
  * @completed_cookie: identifier for the most recently completed operation
  * @active_list: list of descriptors dmaengine is being running on
@@ -218,6 +221,8 @@ struct at_dma_chan {
 	u8			mask;
 	unsigned long		status;
 	struct tasklet_struct	tasklet;
+	u32			save_cfg;
+	u32			save_dscr;
 
 	spinlock_t		lock;
 
@@ -248,6 +253,7 @@ static inline struct at_dma_chan *to_at_dma_chan(struct dma_chan *dchan)
  * @chan_common: common dmaengine dma_device object members
  * @ch_regs: memory mapped register base
  * @clk: dma controller clock
+ * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
  * @dma_desc_pool: base of DMA descriptor region (DMA address)
  * @chan: channels table to store at_dma_chan structures
@@ -256,6 +262,7 @@ struct at_dma {
 	struct dma_device	dma_common;
 	void __iomem		*regs;
 	struct clk		*clk;
+	u32			save_imr;
 
 	u8			all_chan_mask;
 
@@ -355,6 +362,23 @@ static inline int atc_chan_is_enabled(struct at_dma_chan *atchan)
 	return !!(dma_readl(atdma, CHSR) & atchan->mask);
 }
 
+/**
+ * atc_chan_is_paused - test channel pause/resume status
+ * @atchan: channel we want to test status
+ */
+static inline int atc_chan_is_paused(struct at_dma_chan *atchan)
+{
+	return test_bit(ATC_IS_PAUSED, &atchan->status);
+}
+
+/**
+ * atc_chan_is_cyclic - test if given channel has cyclic property set
+ * @atchan: channel we want to test status
+ */
+static inline int atc_chan_is_cyclic(struct at_dma_chan *atchan)
+{
+	return test_bit(ATC_IS_CYCLIC, &atchan->status);
+}
 
 /**
  * set_desc_eol - set end-of-link to descriptor so it will end transfer
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 765f5ff22304348aa629b5857a02397f93dea8ce..eb1d8641cf5cc6b4bba303a68a9c79eb39f17dd0 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
+#include <linux/freezer.h>
 #include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
@@ -251,6 +252,7 @@ static int dmatest_func(void *data)
 	int			i;
 
 	thread_name = current->comm;
+	set_freezable_with_signal();
 
 	ret = -ENOMEM;
 
@@ -305,7 +307,8 @@ static int dmatest_func(void *data)
 		dma_addr_t dma_srcs[src_cnt];
 		dma_addr_t dma_dsts[dst_cnt];
 		struct completion cmp;
-		unsigned long tmo = msecs_to_jiffies(timeout);
+		unsigned long start, tmo, end = 0 /* compiler... */;
+		bool reload = true;
 		u8 align = 0;
 
 		total_tests++;
@@ -404,7 +407,17 @@ static int dmatest_func(void *data)
 		}
 		dma_async_issue_pending(chan);
 
-		tmo = wait_for_completion_timeout(&cmp, tmo);
+		do {
+			start = jiffies;
+			if (reload)
+				end = start + msecs_to_jiffies(timeout);
+			else if (end <= start)
+				end = start + 1;
+			tmo = wait_for_completion_interruptible_timeout(&cmp,
+								end - start);
+			reload = try_to_freeze();
+		} while (tmo == -ERESTARTSYS);
+
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
 		if (tmo == 0) {
@@ -477,6 +490,8 @@ static int dmatest_func(void *data)
 	pr_notice("%s: terminating after %u tests, %u failures (status %d)\n",
 			thread_name, total_tests, failed_tests, ret);
 
+	/* terminate all transfers on specified channels */
+	chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
 	if (iterations > 0)
 		while (!kthread_should_stop()) {
 			DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait_dmatest_exit);
@@ -499,6 +514,10 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 		list_del(&thread->node);
 		kfree(thread);
 	}
+
+	/* terminate all transfers on specified channels */
+	dtc->chan->device->device_control(dtc->chan, DMA_TERMINATE_ALL, 0);
+
 	kfree(dtc);
 }
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 7bd7e98548cd34e495910f093ee44e821c1de67b..b5cc27dc9a51d20c87b7648b093d6450e28fe00d 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -318,6 +318,7 @@ struct sdma_engine {
 	dma_addr_t			context_phys;
 	struct dma_device		dma_device;
 	struct clk			*clk;
+	struct mutex			channel_0_lock;
 	struct sdma_script_start_addrs	*script_addrs;
 };
 
@@ -415,11 +416,15 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 	dma_addr_t buf_phys;
 	int ret;
 
+	mutex_lock(&sdma->channel_0_lock);
+
 	buf_virt = dma_alloc_coherent(NULL,
 			size,
 			&buf_phys, GFP_KERNEL);
-	if (!buf_virt)
-		return -ENOMEM;
+	if (!buf_virt) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
 
 	bd0->mode.command = C0_SETPM;
 	bd0->mode.status = BD_DONE | BD_INTR | BD_WRAP | BD_EXTD;
@@ -433,6 +438,9 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 
 	dma_free_coherent(NULL, size, buf_virt, buf_phys);
 
+err_out:
+	mutex_unlock(&sdma->channel_0_lock);
+
 	return ret;
 }
 
@@ -656,6 +664,8 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 	dev_dbg(sdma->dev, "event_mask0 = 0x%08x\n", sdmac->event_mask0);
 	dev_dbg(sdma->dev, "event_mask1 = 0x%08x\n", sdmac->event_mask1);
 
+	mutex_lock(&sdma->channel_0_lock);
+
 	memset(context, 0, sizeof(*context));
 	context->channel_state.pc = load_address;
 
@@ -676,6 +686,8 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 
 	ret = sdma_run_channel(&sdma->channel[0]);
 
+	mutex_unlock(&sdma->channel_0_lock);
+
 	return ret;
 }
 
@@ -1131,18 +1143,17 @@ static void sdma_add_scripts(struct sdma_engine *sdma,
 			saddr_arr[i] = addr_arr[i];
 }
 
-static int __init sdma_get_firmware(struct sdma_engine *sdma,
-		const char *fw_name)
+static void sdma_load_firmware(const struct firmware *fw, void *context)
 {
-	const struct firmware *fw;
+	struct sdma_engine *sdma = context;
 	const struct sdma_firmware_header *header;
-	int ret;
 	const struct sdma_script_start_addrs *addr;
 	unsigned short *ram_code;
 
-	ret = request_firmware(&fw, fw_name, sdma->dev);
-	if (ret)
-		return ret;
+	if (!fw) {
+		dev_err(sdma->dev, "firmware not found\n");
+		return;
+	}
 
 	if (fw->size < sizeof(*header))
 		goto err_firmware;
@@ -1172,6 +1183,16 @@ static int __init sdma_get_firmware(struct sdma_engine *sdma,
 
 err_firmware:
 	release_firmware(fw);
+}
+
+static int __init sdma_get_firmware(struct sdma_engine *sdma,
+		const char *fw_name)
+{
+	int ret;
+
+	ret = request_firmware_nowait(THIS_MODULE,
+			FW_ACTION_HOTPLUG, fw_name, sdma->dev,
+			GFP_KERNEL, sdma, sdma_load_firmware);
 
 	return ret;
 }
@@ -1269,11 +1290,14 @@ static int __init sdma_probe(struct platform_device *pdev)
 	struct sdma_platform_data *pdata = pdev->dev.platform_data;
 	int i;
 	struct sdma_engine *sdma;
+	s32 *saddr_arr;
 
 	sdma = kzalloc(sizeof(*sdma), GFP_KERNEL);
 	if (!sdma)
 		return -ENOMEM;
 
+	mutex_init(&sdma->channel_0_lock);
+
 	sdma->dev = &pdev->dev;
 
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1310,6 +1334,11 @@ static int __init sdma_probe(struct platform_device *pdev)
 		goto err_alloc;
 	}
 
+	/* initially no scripts available */
+	saddr_arr = (s32 *)sdma->script_addrs;
+	for (i = 0; i < SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; i++)
+		saddr_arr[i] = -EINVAL;
+
 	if (of_id)
 		pdev->id_entry = of_id->data;
 	sdma->devtype = pdev->id_entry->driver_data;
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index be641cbd36fcb30c16aafaf25f279ecc0064b07a..b4588bdd98bb0f0f7dbd3ea5c570f760550ef14d 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -130,6 +130,23 @@ struct mxs_dma_engine {
 	struct mxs_dma_chan		mxs_chans[MXS_DMA_CHANNELS];
 };
 
+static inline void mxs_dma_clkgate(struct mxs_dma_chan *mxs_chan, int enable)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+	int set_clr = enable ? MXS_CLR_ADDR : MXS_SET_ADDR;
+
+	/* enable apbh channel clock */
+	if (dma_is_apbh()) {
+		if (apbh_is_old())
+			writel(1 << (chan_id + BP_APBH_CTRL0_CLKGATE_CHANNEL),
+				mxs_dma->base + HW_APBHX_CTRL0 + set_clr);
+		else
+			writel(1 << chan_id,
+				mxs_dma->base + HW_APBHX_CTRL0 + set_clr);
+	}
+}
+
 static void mxs_dma_reset_chan(struct mxs_dma_chan *mxs_chan)
 {
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -148,38 +165,21 @@ static void mxs_dma_enable_chan(struct mxs_dma_chan *mxs_chan)
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
 	int chan_id = mxs_chan->chan.chan_id;
 
+	/* clkgate needs to be enabled before writing other registers */
+	mxs_dma_clkgate(mxs_chan, 1);
+
 	/* set cmd_addr up */
 	writel(mxs_chan->ccw_phys,
 		mxs_dma->base + HW_APBHX_CHn_NXTCMDAR(chan_id));
 
-	/* enable apbh channel clock */
-	if (dma_is_apbh()) {
-		if (apbh_is_old())
-			writel(1 << (chan_id + BP_APBH_CTRL0_CLKGATE_CHANNEL),
-				mxs_dma->base + HW_APBHX_CTRL0 + MXS_CLR_ADDR);
-		else
-			writel(1 << chan_id,
-				mxs_dma->base + HW_APBHX_CTRL0 + MXS_CLR_ADDR);
-	}
-
 	/* write 1 to SEMA to kick off the channel */
 	writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(chan_id));
 }
 
 static void mxs_dma_disable_chan(struct mxs_dma_chan *mxs_chan)
 {
-	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
-	int chan_id = mxs_chan->chan.chan_id;
-
 	/* disable apbh channel clock */
-	if (dma_is_apbh()) {
-		if (apbh_is_old())
-			writel(1 << (chan_id + BP_APBH_CTRL0_CLKGATE_CHANNEL),
-				mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
-		else
-			writel(1 << chan_id,
-				mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
-	}
+	mxs_dma_clkgate(mxs_chan, 0);
 
 	mxs_chan->status = DMA_SUCCESS;
 }
@@ -338,7 +338,10 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 	if (ret)
 		goto err_clk;
 
+	/* clkgate needs to be enabled for reset to finish */
+	mxs_dma_clkgate(mxs_chan, 1);
 	mxs_dma_reset_chan(mxs_chan);
+	mxs_dma_clkgate(mxs_chan, 0);
 
 	dma_async_tx_descriptor_init(&mxs_chan->desc, chan);
 	mxs_chan->desc.tx_submit = mxs_dma_tx_submit;
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index e6e28f37d8ec472c9be9052039510fa4ce29a7cd..a22662c939812026cb29e775c2f7529264407016 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -47,6 +47,9 @@ enum {
  * @muxval: a number usually used to poke into some mux regiser to
  * mux in the signal to this channel
  * @cctl_opt: default options for the channel control register
+ * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
+ * channels. Fill with 'true' if peripheral should be flow controller. Direction
+ * will be selected at Runtime.
  * @addr: source/target address in physical memory for this DMA channel,
  * can be the address of a FIFO register for burst requests for example.
  * This can be left undefined if the PrimeCell API is used for configuring
@@ -65,6 +68,7 @@ struct pl08x_channel_data {
 	int max_signal;
 	u32 muxval;
 	u32 cctl;
+	bool device_fc;
 	dma_addr_t addr;
 	bool circular_buffer;
 	bool single;
@@ -77,13 +81,11 @@ struct pl08x_channel_data {
  * @addr: current address
  * @maxwidth: the maximum width of a transfer on this bus
  * @buswidth: the width of this bus in bytes: 1, 2 or 4
- * @fill_bytes: bytes required to fill to the next bus memory boundary
  */
 struct pl08x_bus_data {
 	dma_addr_t addr;
 	u8 maxwidth;
 	u8 buswidth;
-	size_t fill_bytes;
 };
 
 /**
@@ -105,8 +107,16 @@ struct pl08x_phy_chan {
 
 /**
  * struct pl08x_txd - wrapper for struct dma_async_tx_descriptor
+ * @tx: async tx descriptor
+ * @node: node for txd list for channels
+ * @src_addr: src address of txd
+ * @dst_addr: dst address of txd
+ * @len: transfer len in bytes
+ * @direction: direction of transfer
  * @llis_bus: DMA memory address (physical) start for the LLIs
  * @llis_va: virtual memory address start for the LLIs
+ * @cctl: control reg values for current txd
+ * @ccfg: config reg values for current txd
  */
 struct pl08x_txd {
 	struct dma_async_tx_descriptor tx;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 8fbf40e0713cfc9a4dd7ec64bc66010a42afc644..ace51af4369f668ea647f47c2d87f76d4478b121 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -24,8 +24,7 @@
 #include <linux/device.h>
 #include <linux/uio.h>
 #include <linux/dma-direction.h>
-
-struct scatterlist;
+#include <linux/scatterlist.h>
 
 /**
  * typedef dma_cookie_t - an opaque DMA cookie
@@ -519,6 +518,16 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 			(unsigned long)config);
 }
 
+static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
+	struct dma_chan *chan, void *buf, size_t len,
+	enum dma_data_direction dir, unsigned long flags)
+{
+	struct scatterlist sg;
+	sg_init_one(&sg, buf, len);
+
+	return chan->device->device_prep_slave_sg(chan, &sg, 1, dir, flags);
+}
+
 static inline int dmaengine_terminate_all(struct dma_chan *chan)
 {
 	return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0);