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

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (37 commits)
  Improve slave/cyclic DMA engine documentation
  dmaengine: pl08x: handle the rest of enums in pl08x_width
  DMA: PL08x: cleanup selection of burst size
  DMA: PL08x: avoid recalculating cctl at each prepare
  DMA: PL08x: cleanup selection of buswidth
  DMA: PL08x: constify plchan->cd and plat->slave_channels
  DMA: PL08x: separately store source/destination cctl
  DMA: PL08x: separately store source/destination slave address
  DMA: PL08x: clean up LLI debugging
  DMA: PL08x: select LLI bus only once per LLI setup
  DMA: PL08x: remove unused constants
  ARM: mxs-dma: reset after disable channel
  dma: intel_mid_dma: remove redundant pci_set_drvdata calls
  dma: mxs-dma: fix unterminated platform_device_id table
  dmaengine: pl330: make platform data optional
  dmaengine: imx-sdma: return proper error if kzalloc fails
  pch_dma: Fix CTL register access issue
  dmaengine: mxs-dma: skip request_irq for NO_IRQ
  dmaengine/coh901318: fix slave submission semantics
  dmaengine/ste_dma40: allow memory buswidth/burst to be configured
  ...

Fix trivial whitespace conflict in drivers/dma/mv_xor.c

15 files changed, 442 insertions, 326 deletions

diff --git a/drivers/dma/TODO b/drivers/dma/TODO
index a4af8589330..734ed0206cd 100644
--- a/drivers/dma/TODO
+++ b/drivers/dma/TODO
@@ -9,6 +9,5 @@ TODO for slave dma
 	- mxs-dma.c
 	- dw_dmac
 	- intel_mid_dma
-	- ste_dma40
 4. Check other subsystems for dma drivers and merge/move to dmaengine
 5. Remove dma_slave_config's dma direction.
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index e6d7228b147..196a7378d33 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -156,14 +156,10 @@ struct pl08x_driver_data {
 #define PL08X_BOUNDARY_SHIFT		(10)	/* 1KB 0x400 */
 #define PL08X_BOUNDARY_SIZE		(1 << PL08X_BOUNDARY_SHIFT)
 
-/* Minimum period between work queue runs */
-#define PL08X_WQ_PERIODMIN	20
-
 /* Size (bytes) of each LLI buffer allocated for one transfer */
 # define PL08X_LLI_TSFR_SIZE	0x2000
 
 /* Maximum times we call dma_pool_alloc on this pool without freeing */
-#define PL08X_MAX_ALLOCS	0x40
 #define MAX_NUM_TSFR_LLIS	(PL08X_LLI_TSFR_SIZE/sizeof(struct pl08x_lli))
 #define PL08X_ALIGN		8
 
@@ -495,10 +491,10 @@ static inline u32 pl08x_cctl_bits(u32 cctl, u8 srcwidth, u8 dstwidth,
 
 struct pl08x_lli_build_data {
 	struct pl08x_txd *txd;
-	struct pl08x_driver_data *pl08x;
 	struct pl08x_bus_data srcbus;
 	struct pl08x_bus_data dstbus;
 	size_t remainder;
+	u32 lli_bus;
 };
 
 /*
@@ -551,8 +547,7 @@ static void pl08x_fill_lli_for_desc(struct pl08x_lli_build_data *bd,
 	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);
-	if (bd->pl08x->lli_buses & PL08X_AHB2)
-		llis_va[num_llis].lli |= PL080_LLI_LM_AHB2;
+	llis_va[num_llis].lli |= bd->lli_bus;
 
 	if (cctl & PL080_CONTROL_SRC_INCR)
 		bd->srcbus.addr += len;
@@ -605,9 +600,9 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	cctl = txd->cctl;
 
 	bd.txd = txd;
-	bd.pl08x = pl08x;
 	bd.srcbus.addr = txd->src_addr;
 	bd.dstbus.addr = txd->dst_addr;
+	bd.lli_bus = (pl08x->lli_buses & PL08X_AHB2) ? PL080_LLI_LM_AHB2 : 0;
 
 	/* Find maximum width of the source bus */
 	bd.srcbus.maxwidth =
@@ -622,25 +617,15 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	/* Set up the bus widths to the maximum */
 	bd.srcbus.buswidth = bd.srcbus.maxwidth;
 	bd.dstbus.buswidth = bd.dstbus.maxwidth;
-	dev_vdbg(&pl08x->adev->dev,
-		 "%s source bus is %d bytes wide, dest bus is %d bytes wide\n",
-		 __func__, bd.srcbus.buswidth, bd.dstbus.buswidth);
-
 
 	/*
 	 * Bytes transferred == tsize * MIN(buswidths), not max(buswidths)
 	 */
 	max_bytes_per_lli = min(bd.srcbus.buswidth, bd.dstbus.buswidth) *
 		PL080_CONTROL_TRANSFER_SIZE_MASK;
-	dev_vdbg(&pl08x->adev->dev,
-		 "%s max bytes per lli = %zu\n",
-		 __func__, max_bytes_per_lli);
 
 	/* We need to count this down to zero */
 	bd.remainder = txd->len;
-	dev_vdbg(&pl08x->adev->dev,
-		 "%s remainder = %zu\n",
-		 __func__, bd.remainder);
 
 	/*
 	 * Choose bus to align to
@@ -649,6 +634,16 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	 */
 	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",
+		 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);
+	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) {
@@ -840,15 +835,14 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	{
 		int i;
 
+		dev_vdbg(&pl08x->adev->dev,
+			 "%-3s %-9s  %-10s %-10s %-10s %s\n",
+			 "lli", "", "csrc", "cdst", "clli", "cctl");
 		for (i = 0; i < num_llis; i++) {
 			dev_vdbg(&pl08x->adev->dev,
-				 "lli %d @%p: csrc=0x%08x, cdst=0x%08x, cctl=0x%08x, clli=0x%08x\n",
-				 i,
-				 &llis_va[i],
-				 llis_va[i].src,
-				 llis_va[i].dst,
-				 llis_va[i].cctl,
-				 llis_va[i].lli
+				 "%3d @%p: 0x%08x 0x%08x 0x%08x 0x%08x\n",
+				 i, &llis_va[i], llis_va[i].src,
+				 llis_va[i].dst, llis_va[i].lli, llis_va[i].cctl
 				);
 		}
 	}
@@ -1054,64 +1048,105 @@ pl08x_dma_tx_status(struct dma_chan *chan,
 
 /* PrimeCell DMA extension */
 struct burst_table {
-	int burstwords;
+	u32 burstwords;
 	u32 reg;
 };
 
 static const struct burst_table burst_sizes[] = {
 	{
 		.burstwords = 256,
-		.reg = (PL080_BSIZE_256 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_256 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_256,
 	},
 	{
 		.burstwords = 128,
-		.reg = (PL080_BSIZE_128 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_128 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_128,
 	},
 	{
 		.burstwords = 64,
-		.reg = (PL080_BSIZE_64 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_64 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_64,
 	},
 	{
 		.burstwords = 32,
-		.reg = (PL080_BSIZE_32 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_32 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_32,
 	},
 	{
 		.burstwords = 16,
-		.reg = (PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_16,
 	},
 	{
 		.burstwords = 8,
-		.reg = (PL080_BSIZE_8 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_8 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_8,
 	},
 	{
 		.burstwords = 4,
-		.reg = (PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.reg = PL080_BSIZE_4,
 	},
 	{
-		.burstwords = 1,
-		.reg = (PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT),
+		.burstwords = 0,
+		.reg = PL080_BSIZE_1,
 	},
 };
 
+/*
+ * Given the source and destination available bus masks, select which
+ * will be routed to each port.  We try to have source and destination
+ * on separate ports, but always respect the allowable settings.
+ */
+static u32 pl08x_select_bus(u8 src, u8 dst)
+{
+	u32 cctl = 0;
+
+	if (!(dst & PL08X_AHB1) || ((dst & PL08X_AHB2) && (src & PL08X_AHB1)))
+		cctl |= PL080_CONTROL_DST_AHB2;
+	if (!(src & PL08X_AHB1) || ((src & PL08X_AHB2) && !(dst & PL08X_AHB2)))
+		cctl |= PL080_CONTROL_SRC_AHB2;
+
+	return cctl;
+}
+
+static u32 pl08x_cctl(u32 cctl)
+{
+	cctl &= ~(PL080_CONTROL_SRC_AHB2 | PL080_CONTROL_DST_AHB2 |
+		  PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR |
+		  PL080_CONTROL_PROT_MASK);
+
+	/* Access the cell in privileged mode, non-bufferable, non-cacheable */
+	return cctl | PL080_CONTROL_PROT_SYS;
+}
+
+static u32 pl08x_width(enum dma_slave_buswidth width)
+{
+	switch (width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		return PL080_WIDTH_8BIT;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		return PL080_WIDTH_16BIT;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		return PL080_WIDTH_32BIT;
+	default:
+		return ~0;
+	}
+}
+
+static u32 pl08x_burst(u32 maxburst)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(burst_sizes); i++)
+		if (burst_sizes[i].burstwords <= maxburst)
+			break;
+
+	return burst_sizes[i].reg;
+}
+
 static int dma_set_runtime_config(struct dma_chan *chan,
 				  struct dma_slave_config *config)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
-	struct pl08x_channel_data *cd = plchan->cd;
 	enum dma_slave_buswidth addr_width;
-	dma_addr_t addr;
-	u32 maxburst;
+	u32 width, burst, maxburst;
 	u32 cctl = 0;
-	int i;
 
 	if (!plchan->slave)
 		return -EINVAL;
@@ -1119,11 +1154,9 @@ static int dma_set_runtime_config(struct dma_chan *chan,
 	/* Transfer direction */
 	plchan->runtime_direction = config->direction;
 	if (config->direction == DMA_TO_DEVICE) {
-		addr = config->dst_addr;
 		addr_width = config->dst_addr_width;
 		maxburst = config->dst_maxburst;
 	} else if (config->direction == DMA_FROM_DEVICE) {
-		addr = config->src_addr;
 		addr_width = config->src_addr_width;
 		maxburst = config->src_maxburst;
 	} else {
@@ -1132,46 +1165,40 @@ static int dma_set_runtime_config(struct dma_chan *chan,
 		return -EINVAL;
 	}
 
-	switch (addr_width) {
-	case DMA_SLAVE_BUSWIDTH_1_BYTE:
-		cctl |= (PL080_WIDTH_8BIT << PL080_CONTROL_SWIDTH_SHIFT) |
-			(PL080_WIDTH_8BIT << PL080_CONTROL_DWIDTH_SHIFT);
-		break;
-	case DMA_SLAVE_BUSWIDTH_2_BYTES:
-		cctl |= (PL080_WIDTH_16BIT << PL080_CONTROL_SWIDTH_SHIFT) |
-			(PL080_WIDTH_16BIT << PL080_CONTROL_DWIDTH_SHIFT);
-		break;
-	case DMA_SLAVE_BUSWIDTH_4_BYTES:
-		cctl |= (PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT) |
-			(PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT);
-		break;
-	default:
+	width = pl08x_width(addr_width);
+	if (width == ~0) {
 		dev_err(&pl08x->adev->dev,
 			"bad runtime_config: alien address width\n");
 		return -EINVAL;
 	}
 
+	cctl |= width << PL080_CONTROL_SWIDTH_SHIFT;
+	cctl |= width << PL080_CONTROL_DWIDTH_SHIFT;
+
 	/*
-	 * Now decide on a maxburst:
 	 * If this channel will only request single transfers, set this
 	 * down to ONE element.  Also select one element if no maxburst
 	 * is specified.
 	 */
-	if (plchan->cd->single || maxburst == 0) {
-		cctl |= (PL080_BSIZE_1 << PL080_CONTROL_SB_SIZE_SHIFT) |
-			(PL080_BSIZE_1 << PL080_CONTROL_DB_SIZE_SHIFT);
+	if (plchan->cd->single)
+		maxburst = 1;
+
+	burst = pl08x_burst(maxburst);
+	cctl |= burst << PL080_CONTROL_SB_SIZE_SHIFT;
+	cctl |= burst << PL080_CONTROL_DB_SIZE_SHIFT;
+
+	if (plchan->runtime_direction == DMA_FROM_DEVICE) {
+		plchan->src_addr = config->src_addr;
+		plchan->src_cctl = pl08x_cctl(cctl) | PL080_CONTROL_DST_INCR |
+			pl08x_select_bus(plchan->cd->periph_buses,
+					 pl08x->mem_buses);
 	} else {
-		for (i = 0; i < ARRAY_SIZE(burst_sizes); i++)
-			if (burst_sizes[i].burstwords <= maxburst)
-				break;
-		cctl |= burst_sizes[i].reg;
+		plchan->dst_addr = config->dst_addr;
+		plchan->dst_cctl = pl08x_cctl(cctl) | PL080_CONTROL_SRC_INCR |
+			pl08x_select_bus(pl08x->mem_buses,
+					 plchan->cd->periph_buses);
 	}
 
-	plchan->runtime_addr = addr;
-
-	/* Modify the default channel data to fit PrimeCell request */
-	cd->cctl = cctl;
-
 	dev_dbg(&pl08x->adev->dev,
 		"configured channel %s (%s) for %s, data width %d, "
 		"maxburst %d words, LE, CCTL=0x%08x\n",
@@ -1270,23 +1297,6 @@ static int pl08x_prep_channel_resources(struct pl08x_dma_chan *plchan,
 	return 0;
 }
 
-/*
- * Given the source and destination available bus masks, select which
- * will be routed to each port.  We try to have source and destination
- * on separate ports, but always respect the allowable settings.
- */
-static u32 pl08x_select_bus(struct pl08x_driver_data *pl08x, u8 src, u8 dst)
-{
-	u32 cctl = 0;
-
-	if (!(dst & PL08X_AHB1) || ((dst & PL08X_AHB2) && (src & PL08X_AHB1)))
-		cctl |= PL080_CONTROL_DST_AHB2;
-	if (!(src & PL08X_AHB1) || ((src & PL08X_AHB2) && !(dst & PL08X_AHB2)))
-		cctl |= PL080_CONTROL_SRC_AHB2;
-
-	return cctl;
-}
-
 static struct pl08x_txd *pl08x_get_txd(struct pl08x_dma_chan *plchan,
 	unsigned long flags)
 {
@@ -1338,8 +1348,8 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_memcpy(
 	txd->cctl |= PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR;
 
 	if (pl08x->vd->dualmaster)
-		txd->cctl |= pl08x_select_bus(pl08x,
-					pl08x->mem_buses, pl08x->mem_buses);
+		txd->cctl |= pl08x_select_bus(pl08x->mem_buses,
+					      pl08x->mem_buses);
 
 	ret = pl08x_prep_channel_resources(plchan, txd);
 	if (ret)
@@ -1356,7 +1366,6 @@ 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;
-	u8 src_buses, dst_buses;
 	int ret;
 
 	/*
@@ -1390,42 +1399,22 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	txd->direction = direction;
 	txd->len = sgl->length;
 
-	txd->cctl = plchan->cd->cctl &
-			~(PL080_CONTROL_SRC_AHB2 | PL080_CONTROL_DST_AHB2 |
-			  PL080_CONTROL_SRC_INCR | PL080_CONTROL_DST_INCR |
-			  PL080_CONTROL_PROT_MASK);
-
-	/* Access the cell in privileged mode, non-bufferable, non-cacheable */
-	txd->cctl |= PL080_CONTROL_PROT_SYS;
-
 	if (direction == DMA_TO_DEVICE) {
 		txd->ccfg |= PL080_FLOW_MEM2PER << PL080_CONFIG_FLOW_CONTROL_SHIFT;
-		txd->cctl |= PL080_CONTROL_SRC_INCR;
+		txd->cctl = plchan->dst_cctl;
 		txd->src_addr = sgl->dma_address;
-		if (plchan->runtime_addr)
-			txd->dst_addr = plchan->runtime_addr;
-		else
-			txd->dst_addr = plchan->cd->addr;
-		src_buses = pl08x->mem_buses;
-		dst_buses = plchan->cd->periph_buses;
+		txd->dst_addr = plchan->dst_addr;
 	} else if (direction == DMA_FROM_DEVICE) {
 		txd->ccfg |= PL080_FLOW_PER2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT;
-		txd->cctl |= PL080_CONTROL_DST_INCR;
-		if (plchan->runtime_addr)
-			txd->src_addr = plchan->runtime_addr;
-		else
-			txd->src_addr = plchan->cd->addr;
+		txd->cctl = plchan->src_cctl;
+		txd->src_addr = plchan->src_addr;
 		txd->dst_addr = sgl->dma_address;
-		src_buses = plchan->cd->periph_buses;
-		dst_buses = pl08x->mem_buses;
 	} else {
 		dev_err(&pl08x->adev->dev,
 			"%s direction unsupported\n", __func__);
 		return NULL;
 	}
 
-	txd->cctl |= pl08x_select_bus(pl08x, src_buses, dst_buses);
-
 	ret = pl08x_prep_channel_resources(plchan, txd);
 	if (ret)
 		return NULL;
@@ -1676,6 +1665,20 @@ static irqreturn_t pl08x_irq(int irq, void *dev)
 	return mask ? IRQ_HANDLED : IRQ_NONE;
 }
 
+static void pl08x_dma_slave_init(struct pl08x_dma_chan *chan)
+{
+	u32 cctl = pl08x_cctl(chan->cd->cctl);
+
+	chan->slave = true;
+	chan->name = chan->cd->bus_id;
+	chan->src_addr = chan->cd->addr;
+	chan->dst_addr = chan->cd->addr;
+	chan->src_cctl = cctl | PL080_CONTROL_DST_INCR |
+		pl08x_select_bus(chan->cd->periph_buses, chan->host->mem_buses);
+	chan->dst_cctl = cctl | PL080_CONTROL_SRC_INCR |
+		pl08x_select_bus(chan->host->mem_buses, chan->cd->periph_buses);
+}
+
 /*
  * Initialise the DMAC memcpy/slave channels.
  * Make a local wrapper to hold required data
@@ -1707,9 +1710,8 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
 		chan->state = PL08X_CHAN_IDLE;
 
 		if (slave) {
-			chan->slave = true;
-			chan->name = pl08x->pd->slave_channels[i].bus_id;
 			chan->cd = &pl08x->pd->slave_channels[i];
+			pl08x_dma_slave_init(chan);
 		} else {
 			chan->cd = &pl08x->pd->memcpy_channel;
 			chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 36144f88d71..6a483eac7b3 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1216,7 +1216,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	atdma->dma_common.cap_mask = pdata->cap_mask;
 	atdma->all_chan_mask = (1 << pdata->nr_channels) - 1;
 
-	size = io->end - io->start + 1;
+	size = resource_size(io);
 	if (!request_mem_region(io->start, size, pdev->dev.driver->name)) {
 		err = -EBUSY;
 		goto err_kfree;
@@ -1362,7 +1362,7 @@ static int __exit at_dma_remove(struct platform_device *pdev)
 	atdma->regs = NULL;
 
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(io->start, io->end - io->start + 1);
+	release_mem_region(io->start, resource_size(io));
 
 	kfree(atdma);
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index a92d95eac86..4234f416ef1 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -41,6 +41,8 @@ struct coh901318_desc {
 	struct coh901318_lli *lli;
 	enum dma_data_direction dir;
 	unsigned long flags;
+	u32 head_config;
+	u32 head_ctrl;
 };
 
 struct coh901318_base {
@@ -661,6 +663,9 @@ static struct coh901318_desc *coh901318_queue_start(struct coh901318_chan *cohc)
 
 		coh901318_desc_submit(cohc, cohd);
 
+		/* Program the transaction head */
+		coh901318_set_conf(cohc, cohd->head_config);
+		coh901318_set_ctrl(cohc, cohd->head_ctrl);
 		coh901318_prep_linked_list(cohc, cohd->lli);
 
 		/* start dma job on this channel */
@@ -1091,8 +1096,6 @@ coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	} else
 		goto err_direction;
 
-	coh901318_set_conf(cohc, config);
-
 	/* The dma only supports transmitting packages up to
 	 * MAX_DMA_PACKET_SIZE. Calculate to total number of
 	 * dma elemts required to send the entire sg list
@@ -1129,16 +1132,18 @@ coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (ret)
 		goto err_lli_fill;
 
-	/*
-	 * Set the default ctrl for the channel to the one from the lli,
-	 * things may have changed due to odd buffer alignment etc.
-	 */
-	coh901318_set_ctrl(cohc, lli->control);
 
 	COH_DBG(coh901318_list_print(cohc, lli));
 
 	/* Pick a descriptor to handle this transfer */
 	cohd = coh901318_desc_get(cohc);
+	cohd->head_config = config;
+	/*
+	 * Set the default head ctrl for the channel to the one from the
+	 * lli, things may have changed due to odd buffer alignment
+	 * etc.
+	 */
+	cohd->head_ctrl = lli->control;
 	cohd->dir = direction;
 	cohd->flags = flags;
 	cohd->desc.tx_submit = coh901318_tx_submit;
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 48694c34d96..26374b2a55a 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -510,8 +510,8 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v
 					 dma_chan_name(chan));
 				list_del_rcu(&device->global_node);
 			} else if (err)
-				pr_err("dmaengine: failed to get %s: (%d)\n",
-				       dma_chan_name(chan), err);
+				pr_debug("dmaengine: failed to get %s: (%d)\n",
+					 dma_chan_name(chan), err);
 			else
 				break;
 			if (--device->privatecnt == 0)
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 0766c1e53b1..5d7a49bd7c2 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -902,7 +902,7 @@ static void ep93xx_dma_free_chan_resources(struct dma_chan *chan)
  *
  * Returns a valid DMA descriptor or %NULL in case of failure.
  */
-struct dma_async_tx_descriptor *
+static struct dma_async_tx_descriptor *
 ep93xx_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 			   dma_addr_t src, size_t len, unsigned long flags)
 {
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 1eb60ded2f0..7bd7e98548c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1305,8 +1305,10 @@ static int __init sdma_probe(struct platform_device *pdev)
 		goto err_request_irq;
 
 	sdma->script_addrs = kzalloc(sizeof(*sdma->script_addrs), GFP_KERNEL);
-	if (!sdma->script_addrs)
+	if (!sdma->script_addrs) {
+		ret = -ENOMEM;
 		goto err_alloc;
+	}
 
 	if (of_id)
 		pdev->id_entry = of_id->data;
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index f653517ef74..8a3fdd87db9 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -1351,7 +1351,6 @@ int dma_suspend(struct pci_dev *pci, pm_message_t state)
 			return -EAGAIN;
 	}
 	device->state = SUSPENDED;
-	pci_set_drvdata(pci, device);
 	pci_save_state(pci);
 	pci_disable_device(pci);
 	pci_set_power_state(pci, PCI_D3hot);
@@ -1380,7 +1379,6 @@ int dma_resume(struct pci_dev *pci)
 	}
 	device->state = RUNNING;
 	iowrite32(REG_BIT0, device->dma_base + DMA_CFG);
-	pci_set_drvdata(pci, device);
 	return 0;
 }
 
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index fd7d2b308cf..6815905a772 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1706,16 +1706,14 @@ static int __init ipu_probe(struct platform_device *pdev)
 		ipu_data.irq_fn, ipu_data.irq_err, ipu_data.irq_base);
 
 	/* Remap IPU common registers */
-	ipu_data.reg_ipu = ioremap(mem_ipu->start,
-				   mem_ipu->end - mem_ipu->start + 1);
+	ipu_data.reg_ipu = ioremap(mem_ipu->start, resource_size(mem_ipu));
 	if (!ipu_data.reg_ipu) {
 		ret = -ENOMEM;
 		goto err_ioremap_ipu;
 	}
 
 	/* Remap Image Converter and Image DMA Controller registers */
-	ipu_data.reg_ic = ioremap(mem_ic->start,
-				  mem_ic->end - mem_ic->start + 1);
+	ipu_data.reg_ic = ioremap(mem_ic->start, resource_size(mem_ic));
 	if (!ipu_data.reg_ic) {
 		ret = -ENOMEM;
 		goto err_ioremap_ic;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 06f9f27dbe7..9a353c2216d 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1304,7 +1304,8 @@ static int mv_xor_shared_probe(struct platform_device *pdev)
 	if (!res)
 		return -ENODEV;
 
-	msp->xor_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	msp->xor_base = devm_ioremap(&pdev->dev, res->start,
+				     resource_size(res));
 	if (!msp->xor_base)
 		return -EBUSY;
 
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 88aad4f5400..be641cbd36f 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -327,10 +327,12 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	memset(mxs_chan->ccw, 0, PAGE_SIZE);
 
-	ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
-				0, "mxs-dma", mxs_dma);
-	if (ret)
-		goto err_irq;
+	if (mxs_chan->chan_irq != NO_IRQ) {
+		ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
+					0, "mxs-dma", mxs_dma);
+		if (ret)
+			goto err_irq;
+	}
 
 	ret = clk_enable(mxs_dma->clk);
 	if (ret)
@@ -535,6 +537,7 @@ static int mxs_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
 		mxs_dma_disable_chan(mxs_chan);
+		mxs_dma_reset_chan(mxs_chan);
 		break;
 	case DMA_PAUSE:
 		mxs_dma_pause_chan(mxs_chan);
@@ -707,6 +710,8 @@ static struct platform_device_id mxs_dma_type[] = {
 	}, {
 		.name = "mxs-dma-apbx",
 		.driver_data = MXS_DMA_APBX,
+	}, {
+		/* end of list */
 	}
 };
 
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index ff5b38f9d45..1ac8d4b580b 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -45,7 +45,8 @@
 #define DMA_STATUS_MASK_BITS		0x3
 #define DMA_STATUS_SHIFT_BITS		16
 #define DMA_STATUS_IRQ(x)		(0x1 << (x))
-#define DMA_STATUS_ERR(x)		(0x1 << ((x) + 8))
+#define DMA_STATUS0_ERR(x)		(0x1 << ((x) + 8))
+#define DMA_STATUS2_ERR(x)		(0x1 << (x))
 
 #define DMA_DESC_WIDTH_SHIFT_BITS	12
 #define DMA_DESC_WIDTH_1_BYTE		(0x3 << DMA_DESC_WIDTH_SHIFT_BITS)
@@ -61,6 +62,9 @@
 
 #define MAX_CHAN_NR			8
 
+#define DMA_MASK_CTL0_MODE	0x33333333
+#define DMA_MASK_CTL2_MODE	0x00003333
+
 static unsigned int init_nr_desc_per_channel = 64;
 module_param(init_nr_desc_per_channel, uint, 0644);
 MODULE_PARM_DESC(init_nr_desc_per_channel,
@@ -133,6 +137,7 @@ struct pch_dma {
 #define PCH_DMA_CTL3	0x0C
 #define PCH_DMA_STS0	0x10
 #define PCH_DMA_STS1	0x14
+#define PCH_DMA_STS2	0x18
 
 #define dma_readl(pd, name) \
 	readl((pd)->membase + PCH_DMA_##name)
@@ -183,13 +188,19 @@ static void pdc_enable_irq(struct dma_chan *chan, int enable)
 {
 	struct pch_dma *pd = to_pd(chan->device);
 	u32 val;
+	int pos;
+
+	if (chan->chan_id < 8)
+		pos = chan->chan_id;
+	else
+		pos = chan->chan_id + 8;
 
 	val = dma_readl(pd, CTL2);
 
 	if (enable)
-		val |= 0x1 << chan->chan_id;
+		val |= 0x1 << pos;
 	else
-		val &= ~(0x1 << chan->chan_id);
+		val &= ~(0x1 << pos);
 
 	dma_writel(pd, CTL2, val);
 
@@ -202,10 +213,17 @@ static void pdc_set_dir(struct dma_chan *chan)
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
 	struct pch_dma *pd = to_pd(chan->device);
 	u32 val;
+	u32 mask_mode;
+	u32 mask_ctl;
 
 	if (chan->chan_id < 8) {
 		val = dma_readl(pd, CTL0);
 
+		mask_mode = DMA_CTL0_MODE_MASK_BITS <<
+					(DMA_CTL0_BITS_PER_CH * chan->chan_id);
+		mask_ctl = DMA_MASK_CTL0_MODE & ~(DMA_CTL0_MODE_MASK_BITS <<
+				       (DMA_CTL0_BITS_PER_CH * chan->chan_id));
+		val &= mask_mode;
 		if (pd_chan->dir == DMA_TO_DEVICE)
 			val |= 0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
 				       DMA_CTL0_DIR_SHIFT_BITS);
@@ -213,18 +231,24 @@ static void pdc_set_dir(struct dma_chan *chan)
 			val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
 					 DMA_CTL0_DIR_SHIFT_BITS));
 
+		val |= mask_ctl;
 		dma_writel(pd, CTL0, val);
 	} else {
 		int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
 		val = dma_readl(pd, CTL3);
 
+		mask_mode = DMA_CTL0_MODE_MASK_BITS <<
+						(DMA_CTL0_BITS_PER_CH * ch);
+		mask_ctl = DMA_MASK_CTL2_MODE & ~(DMA_CTL0_MODE_MASK_BITS <<
+						 (DMA_CTL0_BITS_PER_CH * ch));
+		val &= mask_mode;
 		if (pd_chan->dir == DMA_TO_DEVICE)
 			val |= 0x1 << (DMA_CTL0_BITS_PER_CH * ch +
 				       DMA_CTL0_DIR_SHIFT_BITS);
 		else
 			val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * ch +
 					 DMA_CTL0_DIR_SHIFT_BITS));
-
+		val |= mask_ctl;
 		dma_writel(pd, CTL3, val);
 	}
 
@@ -236,33 +260,37 @@ static void pdc_set_mode(struct dma_chan *chan, u32 mode)
 {
 	struct pch_dma *pd = to_pd(chan->device);
 	u32 val;
+	u32 mask_ctl;
+	u32 mask_dir;
 
 	if (chan->chan_id < 8) {
+		mask_ctl = DMA_MASK_CTL0_MODE & ~(DMA_CTL0_MODE_MASK_BITS <<
+			   (DMA_CTL0_BITS_PER_CH * chan->chan_id));
+		mask_dir = 1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +\
+				 DMA_CTL0_DIR_SHIFT_BITS);
 		val = dma_readl(pd, CTL0);
-
-		val &= ~(DMA_CTL0_MODE_MASK_BITS <<
-			(DMA_CTL0_BITS_PER_CH * chan->chan_id));
+		val &= mask_dir;
 		val |= mode << (DMA_CTL0_BITS_PER_CH * chan->chan_id);
-
+		val |= mask_ctl;
 		dma_writel(pd, CTL0, val);
 	} else {
 		int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
-
+		mask_ctl = DMA_MASK_CTL2_MODE & ~(DMA_CTL0_MODE_MASK_BITS <<
+						 (DMA_CTL0_BITS_PER_CH * ch));
+		mask_dir = 1 << (DMA_CTL0_BITS_PER_CH * ch +\
+				 DMA_CTL0_DIR_SHIFT_BITS);
 		val = dma_readl(pd, CTL3);
-
-		val &= ~(DMA_CTL0_MODE_MASK_BITS <<
-			(DMA_CTL0_BITS_PER_CH * ch));
+		val &= mask_dir;
 		val |= mode << (DMA_CTL0_BITS_PER_CH * ch);
-
+		val |= mask_ctl;
 		dma_writel(pd, CTL3, val);
-
 	}
 
 	dev_dbg(chan2dev(chan), "pdc_set_mode: chan %d -> %x\n",
 		chan->chan_id, val);
 }
 
-static u32 pdc_get_status(struct pch_dma_chan *pd_chan)
+static u32 pdc_get_status0(struct pch_dma_chan *pd_chan)
 {
 	struct pch_dma *pd = to_pd(pd_chan->chan.device);
 	u32 val;
@@ -272,9 +300,27 @@ static u32 pdc_get_status(struct pch_dma_chan *pd_chan)
 			DMA_STATUS_BITS_PER_CH * pd_chan->chan.chan_id));
 }
 
+static u32 pdc_get_status2(struct pch_dma_chan *pd_chan)
+{
+	struct pch_dma *pd = to_pd(pd_chan->chan.device);
+	u32 val;
+
+	val = dma_readl(pd, STS2);
+	return DMA_STATUS_MASK_BITS & (val >> (DMA_STATUS_SHIFT_BITS +
+			DMA_STATUS_BITS_PER_CH * (pd_chan->chan.chan_id - 8)));
+}
+
 static bool pdc_is_idle(struct pch_dma_chan *pd_chan)
 {
-	if (pdc_get_status(pd_chan) == DMA_STATUS_IDLE)
+	u32 sts;
+
+	if (pd_chan->chan.chan_id < 8)
+		sts = pdc_get_status0(pd_chan);
+	else
+		sts = pdc_get_status2(pd_chan);
+
+
+	if (sts == DMA_STATUS_IDLE)
 		return true;
 	else
 		return false;
@@ -495,11 +541,11 @@ static int pd_alloc_chan_resources(struct dma_chan *chan)
 		list_add_tail(&desc->desc_node, &tmp_list);
 	}
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irq(&pd_chan->lock);
 	list_splice(&tmp_list, &pd_chan->free_list);
 	pd_chan->descs_allocated = i;
 	pd_chan->completed_cookie = chan->cookie = 1;
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irq(&pd_chan->lock);
 
 	pdc_enable_irq(chan, 1);
 
@@ -517,10 +563,10 @@ static void pd_free_chan_resources(struct dma_chan *chan)
 	BUG_ON(!list_empty(&pd_chan->active_list));
 	BUG_ON(!list_empty(&pd_chan->queue));
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irq(&pd_chan->lock);
 	list_splice_init(&pd_chan->free_list, &tmp_list);
 	pd_chan->descs_allocated = 0;
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irq(&pd_chan->lock);
 
 	list_for_each_entry_safe(desc, _d, &tmp_list, desc_node)
 		pci_pool_free(pd->pool, desc, desc->txd.phys);
@@ -536,10 +582,10 @@ static enum dma_status pd_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	dma_cookie_t last_completed;
 	int ret;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irq(&pd_chan->lock);
 	last_completed = pd_chan->completed_cookie;
 	last_used = chan->cookie;
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irq(&pd_chan->lock);
 
 	ret = dma_async_is_complete(cookie, last_completed, last_used);
 
@@ -654,7 +700,7 @@ static int pd_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	if (cmd != DMA_TERMINATE_ALL)
 		return -ENXIO;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irq(&pd_chan->lock);
 
 	pdc_set_mode(&pd_chan->chan, DMA_CTL0_DISABLE);
 
@@ -664,7 +710,7 @@ static int pd_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	list_for_each_entry_safe(desc, _d, &list, desc_node)
 		pdc_chain_complete(pd_chan, desc);
 
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irq(&pd_chan->lock);
 
 	return 0;
 }
@@ -693,30 +739,45 @@ static irqreturn_t pd_irq(int irq, void *devid)
 	struct pch_dma *pd = (struct pch_dma *)devid;
 	struct pch_dma_chan *pd_chan;
 	u32 sts0;
+	u32 sts2;
 	int i;
-	int ret = IRQ_NONE;
+	int ret0 = IRQ_NONE;
+	int ret2 = IRQ_NONE;
 
 	sts0 = dma_readl(pd, STS0);
+	sts2 = dma_readl(pd, STS2);
 
 	dev_dbg(pd->dma.dev, "pd_irq sts0: %x\n", sts0);
 
 	for (i = 0; i < pd->dma.chancnt; i++) {
 		pd_chan = &pd->channels[i];
 
-		if (sts0 & DMA_STATUS_IRQ(i)) {
-			if (sts0 & DMA_STATUS_ERR(i))
-				set_bit(0, &pd_chan->err_status);
+		if (i < 8) {
+			if (sts0 & DMA_STATUS_IRQ(i)) {
+				if (sts0 & DMA_STATUS0_ERR(i))
+					set_bit(0, &pd_chan->err_status);
 
-			tasklet_schedule(&pd_chan->tasklet);
-			ret = IRQ_HANDLED;
-		}
+				tasklet_schedule(&pd_chan->tasklet);
+				ret0 = IRQ_HANDLED;
+			}
+		} else {
+			if (sts2 & DMA_STATUS_IRQ(i - 8)) {
+				if (sts2 & DMA_STATUS2_ERR(i))
+					set_bit(0, &pd_chan->err_status);
 
+				tasklet_schedule(&pd_chan->tasklet);
+				ret2 = IRQ_HANDLED;
+			}
+		}
 	}
 
 	/* clear interrupt bits in status register */
-	dma_writel(pd, STS0, sts0);
+	if (ret0)
+		dma_writel(pd, STS0, sts0);
+	if (ret2)
+		dma_writel(pd, STS2, sts2);
 
-	return ret;
+	return ret0 | ret2;
 }
 
 #ifdef	CONFIG_PM
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 6abe1ec1f2c..00eee59e8b3 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -82,7 +82,7 @@ struct dma_pl330_dmac {
 	spinlock_t pool_lock;
 
 	/* Peripheral channels connected to this DMAC */
-	struct dma_pl330_chan peripherals[0]; /* keep at end */
+	struct dma_pl330_chan *peripherals; /* keep at end */
 };
 
 struct dma_pl330_desc {
@@ -451,8 +451,13 @@ static struct dma_pl330_desc *pl330_get_desc(struct dma_pl330_chan *pch)
 	desc->txd.cookie = 0;
 	async_tx_ack(&desc->txd);
 
-	desc->req.rqtype = peri->rqtype;
-	desc->req.peri = peri->peri_id;
+	if (peri) {
+		desc->req.rqtype = peri->rqtype;
+		desc->req.peri = peri->peri_id;
+	} else {
+		desc->req.rqtype = MEMTOMEM;
+		desc->req.peri = 0;
+	}
 
 	dma_async_tx_descriptor_init(&desc->txd, &pch->chan);
 
@@ -529,10 +534,10 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	struct pl330_info *pi;
 	int burst;
 
-	if (unlikely(!pch || !len || !peri))
+	if (unlikely(!pch || !len))
 		return NULL;
 
-	if (peri->rqtype != MEMTOMEM)
+	if (peri && peri->rqtype != MEMTOMEM)
 		return NULL;
 
 	pi = &pch->dmac->pif;
@@ -577,7 +582,7 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	int i, burst_size;
 	dma_addr_t addr;
 
-	if (unlikely(!pch || !sgl || !sg_len))
+	if (unlikely(!pch || !sgl || !sg_len || !peri))
 		return NULL;
 
 	/* Make sure the direction is consistent */
@@ -666,17 +671,12 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	struct dma_device *pd;
 	struct resource *res;
 	int i, ret, irq;
+	int num_chan;
 
 	pdat = adev->dev.platform_data;
 
-	if (!pdat || !pdat->nr_valid_peri) {
-		dev_err(&adev->dev, "platform data missing\n");
-		return -ENODEV;
-	}
-
 	/* Allocate a new DMAC and its Channels */
-	pdmac = kzalloc(pdat->nr_valid_peri * sizeof(*pch)
-				+ sizeof(*pdmac), GFP_KERNEL);
+	pdmac = kzalloc(sizeof(*pdmac), GFP_KERNEL);
 	if (!pdmac) {
 		dev_err(&adev->dev, "unable to allocate mem\n");
 		return -ENOMEM;
@@ -685,7 +685,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pi = &pdmac->pif;
 	pi->dev = &adev->dev;
 	pi->pl330_data = NULL;
-	pi->mcbufsz = pdat->mcbuf_sz;
+	pi->mcbufsz = pdat ? pdat->mcbuf_sz : 0;
 
 	res = &adev->res;
 	request_mem_region(res->start, resource_size(res), "dma-pl330");
@@ -717,27 +717,35 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	INIT_LIST_HEAD(&pd->channels);
 
 	/* Initialize channel parameters */
-	for (i = 0; i < pdat->nr_valid_peri; i++) {
-		struct dma_pl330_peri *peri = &pdat->peri[i];
-		pch = &pdmac->peripherals[i];
+	num_chan = max(pdat ? pdat->nr_valid_peri : 0, (u8)pi->pcfg.num_chan);
+	pdmac->peripherals = kzalloc(num_chan * sizeof(*pch), GFP_KERNEL);
 
-		switch (peri->rqtype) {
-		case MEMTOMEM:
+	for (i = 0; i < num_chan; i++) {
+		pch = &pdmac->peripherals[i];
+		if (pdat) {
+			struct dma_pl330_peri *peri = &pdat->peri[i];
+
+			switch (peri->rqtype) {
+			case MEMTOMEM:
+				dma_cap_set(DMA_MEMCPY, pd->cap_mask);
+				break;
+			case MEMTODEV:
+			case DEVTOMEM:
+				dma_cap_set(DMA_SLAVE, pd->cap_mask);
+				break;
+			default:
+				dev_err(&adev->dev, "DEVTODEV Not Supported\n");
+				continue;
+			}
+			pch->chan.private = peri;
+		} else {
 			dma_cap_set(DMA_MEMCPY, pd->cap_mask);
-			break;
-		case MEMTODEV:
-		case DEVTOMEM:
-			dma_cap_set(DMA_SLAVE, pd->cap_mask);
-			break;
-		default:
-			dev_err(&adev->dev, "DEVTODEV Not Supported\n");
-			continue;
+			pch->chan.private = NULL;
 		}
 
 		INIT_LIST_HEAD(&pch->work_list);
 		spin_lock_init(&pch->lock);
 		pch->pl330_chid = NULL;
-		pch->chan.private = peri;
 		pch->chan.device = pd;
 		pch->chan.chan_id = i;
 		pch->dmac = pdmac;
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 29d1addbe0c..cd3a7c726bf 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -14,6 +14,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/amba/bus.h>
 
 #include <plat/ste_dma40.h>
 
@@ -45,9 +46,6 @@
 #define D40_ALLOC_PHY		(1 << 30)
 #define D40_ALLOC_LOG_FREE	0
 
-/* Hardware designer of the block */
-#define D40_HW_DESIGNER 0x8
-
 /**
  * enum 40_command - The different commands and/or statuses.
  *
@@ -186,6 +184,8 @@ struct d40_base;
  * @log_def: Default logical channel settings.
  * @lcla: Space for one dst src pair for logical channel transfers.
  * @lcpa: Pointer to dst and src lcpa settings.
+ * @runtime_addr: runtime configured address.
+ * @runtime_direction: runtime configured direction.
  *
  * This struct can either "be" a logical or a physical channel.
  */
@@ -200,6 +200,7 @@ struct d40_chan {
 	struct dma_chan			 chan;
 	struct tasklet_struct		 tasklet;
 	struct list_head		 client;
+	struct list_head		 pending_queue;
 	struct list_head		 active;
 	struct list_head		 queue;
 	struct stedma40_chan_cfg	 dma_cfg;
@@ -645,7 +646,20 @@ static struct d40_desc *d40_first_active_get(struct d40_chan *d40c)
 
 static void d40_desc_queue(struct d40_chan *d40c, struct d40_desc *desc)
 {
-	list_add_tail(&desc->node, &d40c->queue);
+	list_add_tail(&desc->node, &d40c->pending_queue);
+}
+
+static struct d40_desc *d40_first_pending(struct d40_chan *d40c)
+{
+	struct d40_desc *d;
+
+	if (list_empty(&d40c->pending_queue))
+		return NULL;
+
+	d = list_first_entry(&d40c->pending_queue,
+			     struct d40_desc,
+			     node);
+	return d;
 }
 
 static struct d40_desc *d40_first_queued(struct d40_chan *d40c)
@@ -802,6 +816,11 @@ static void d40_term_all(struct d40_chan *d40c)
 		d40_desc_free(d40c, d40d);
 	}
 
+	/* Release pending descriptors */
+	while ((d40d = d40_first_pending(d40c))) {
+		d40_desc_remove(d40d);
+		d40_desc_free(d40c, d40d);
+	}
 
 	d40c->pending_tx = 0;
 	d40c->busy = false;
@@ -2092,7 +2111,7 @@ dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 	struct scatterlist *sg;
 	int i;
 
-	sg = kcalloc(periods + 1, sizeof(struct scatterlist), GFP_KERNEL);
+	sg = kcalloc(periods + 1, sizeof(struct scatterlist), GFP_NOWAIT);
 	for (i = 0; i < periods; i++) {
 		sg_dma_address(&sg[i]) = dma_addr;
 		sg_dma_len(&sg[i]) = period_len;
@@ -2152,24 +2171,87 @@ static void d40_issue_pending(struct dma_chan *chan)
 
 	spin_lock_irqsave(&d40c->lock, flags);
 
-	/* Busy means that pending jobs are already being processed */
+	list_splice_tail_init(&d40c->pending_queue, &d40c->queue);
+
+	/* Busy means that queued jobs are already being processed */
 	if (!d40c->busy)
 		(void) d40_queue_start(d40c);
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 }
 
+static int
+dma40_config_to_halfchannel(struct d40_chan *d40c,
+			    struct stedma40_half_channel_info *info,
+			    enum dma_slave_buswidth width,
+			    u32 maxburst)
+{
+	enum stedma40_periph_data_width addr_width;
+	int psize;
+
+	switch (width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		addr_width = STEDMA40_BYTE_WIDTH;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		addr_width = STEDMA40_HALFWORD_WIDTH;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		addr_width = STEDMA40_WORD_WIDTH;
+		break;
+	case DMA_SLAVE_BUSWIDTH_8_BYTES:
+		addr_width = STEDMA40_DOUBLEWORD_WIDTH;
+		break;
+	default:
+		dev_err(d40c->base->dev,
+			"illegal peripheral address width "
+			"requested (%d)\n",
+			width);
+		return -EINVAL;
+	}
+
+	if (chan_is_logical(d40c)) {
+		if (maxburst >= 16)
+			psize = STEDMA40_PSIZE_LOG_16;
+		else if (maxburst >= 8)
+			psize = STEDMA40_PSIZE_LOG_8;
+		else if (maxburst >= 4)
+			psize = STEDMA40_PSIZE_LOG_4;
+		else
+			psize = STEDMA40_PSIZE_LOG_1;
+	} else {
+		if (maxburst >= 16)
+			psize = STEDMA40_PSIZE_PHY_16;
+		else if (maxburst >= 8)
+			psize = STEDMA40_PSIZE_PHY_8;
+		else if (maxburst >= 4)
+			psize = STEDMA40_PSIZE_PHY_4;
+		else
+			psize = STEDMA40_PSIZE_PHY_1;
+	}
+
+	info->data_width = addr_width;
+	info->psize = psize;
+	info->flow_ctrl = STEDMA40_NO_FLOW_CTRL;
+
+	return 0;
+}
+
 /* Runtime reconfiguration extension */
-static void d40_set_runtime_config(struct dma_chan *chan,
-			       struct dma_slave_config *config)
+static int d40_set_runtime_config(struct dma_chan *chan,
+				  struct dma_slave_config *config)
 {
 	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
 	struct stedma40_chan_cfg *cfg = &d40c->dma_cfg;
-	enum dma_slave_buswidth config_addr_width;
+	enum dma_slave_buswidth src_addr_width, dst_addr_width;
 	dma_addr_t config_addr;
-	u32 config_maxburst;
-	enum stedma40_periph_data_width addr_width;
-	int psize;
+	u32 src_maxburst, dst_maxburst;
+	int ret;
+
+	src_addr_width = config->src_addr_width;
+	src_maxburst = config->src_maxburst;
+	dst_addr_width = config->dst_addr_width;
+	dst_maxburst = config->dst_maxburst;
 
 	if (config->direction == DMA_FROM_DEVICE) {
 		dma_addr_t dev_addr_rx =
@@ -2188,8 +2270,11 @@ static void d40_set_runtime_config(struct dma_chan *chan,
 				cfg->dir);
 		cfg->dir = STEDMA40_PERIPH_TO_MEM;
 
-		config_addr_width = config->src_addr_width;
-		config_maxburst = config->src_maxburst;
+		/* Configure the memory side */
+		if (dst_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+			dst_addr_width = src_addr_width;
+		if (dst_maxburst == 0)
+			dst_maxburst = src_maxburst;
 
 	} else if (config->direction == DMA_TO_DEVICE) {
 		dma_addr_t dev_addr_tx =
@@ -2208,68 +2293,39 @@ static void d40_set_runtime_config(struct dma_chan *chan,
 				cfg->dir);
 		cfg->dir = STEDMA40_MEM_TO_PERIPH;
 
-		config_addr_width = config->dst_addr_width;
-		config_maxburst = config->dst_maxburst;
-
+		/* Configure the memory side */
+		if (src_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+			src_addr_width = dst_addr_width;
+		if (src_maxburst == 0)
+			src_maxburst = dst_maxburst;
 	} else {
 		dev_err(d40c->base->dev,
 			"unrecognized channel direction %d\n",
 			config->direction);
-		return;
+		return -EINVAL;
 	}
 
-	switch (config_addr_width) {
-	case DMA_SLAVE_BUSWIDTH_1_BYTE:
-		addr_width = STEDMA40_BYTE_WIDTH;
-		break;
-	case DMA_SLAVE_BUSWIDTH_2_BYTES:
-		addr_width = STEDMA40_HALFWORD_WIDTH;
-		break;
-	case DMA_SLAVE_BUSWIDTH_4_BYTES:
-		addr_width = STEDMA40_WORD_WIDTH;
-		break;
-	case DMA_SLAVE_BUSWIDTH_8_BYTES:
-		addr_width = STEDMA40_DOUBLEWORD_WIDTH;
-		break;
-	default:
+	if (src_maxburst * src_addr_width != dst_maxburst * dst_addr_width) {
 		dev_err(d40c->base->dev,
-			"illegal peripheral address width "
-			"requested (%d)\n",
-			config->src_addr_width);
-		return;
+			"src/dst width/maxburst mismatch: %d*%d != %d*%d\n",
+			src_maxburst,
+			src_addr_width,
+			dst_maxburst,
+			dst_addr_width);
+		return -EINVAL;
 	}
 
-	if (chan_is_logical(d40c)) {
-		if (config_maxburst >= 16)
-			psize = STEDMA40_PSIZE_LOG_16;
-		else if (config_maxburst >= 8)
-			psize = STEDMA40_PSIZE_LOG_8;
-		else if (config_maxburst >= 4)
-			psize = STEDMA40_PSIZE_LOG_4;
-		else
-			psize = STEDMA40_PSIZE_LOG_1;
-	} else {
-		if (config_maxburst >= 16)
-			psize = STEDMA40_PSIZE_PHY_16;
-		else if (config_maxburst >= 8)
-			psize = STEDMA40_PSIZE_PHY_8;
-		else if (config_maxburst >= 4)
-			psize = STEDMA40_PSIZE_PHY_4;
-		else if (config_maxburst >= 2)
-			psize = STEDMA40_PSIZE_PHY_2;
-		else
-			psize = STEDMA40_PSIZE_PHY_1;
-	}
+	ret = dma40_config_to_halfchannel(d40c, &cfg->src_info,
+					  src_addr_width,
+					  src_maxburst);
+	if (ret)
+		return ret;
 
-	/* Set up all the endpoint configs */
-	cfg->src_info.data_width = addr_width;
-	cfg->src_info.psize = psize;
-	cfg->src_info.big_endian = false;
-	cfg->src_info.flow_ctrl = STEDMA40_NO_FLOW_CTRL;
-	cfg->dst_info.data_width = addr_width;
-	cfg->dst_info.psize = psize;
-	cfg->dst_info.big_endian = false;
-	cfg->dst_info.flow_ctrl = STEDMA40_NO_FLOW_CTRL;
+	ret = dma40_config_to_halfchannel(d40c, &cfg->dst_info,
+					  dst_addr_width,
+					  dst_maxburst);
+	if (ret)
+		return ret;
 
 	/* Fill in register values */
 	if (chan_is_logical(d40c))
@@ -2282,12 +2338,14 @@ static void d40_set_runtime_config(struct dma_chan *chan,
 	d40c->runtime_addr = config_addr;
 	d40c->runtime_direction = config->direction;
 	dev_dbg(d40c->base->dev,
-		"configured channel %s for %s, data width %d, "
-		"maxburst %d bytes, LE, no flow control\n",
+		"configured channel %s for %s, data width %d/%d, "
+		"maxburst %d/%d elements, LE, no flow control\n",
 		dma_chan_name(chan),
 		(config->direction == DMA_FROM_DEVICE) ? "RX" : "TX",
-		config_addr_width,
-		config_maxburst);
+		src_addr_width, dst_addr_width,
+		src_maxburst, dst_maxburst);
+
+	return 0;
 }
 
 static int d40_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -2308,9 +2366,8 @@ static int d40_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	case DMA_RESUME:
 		return d40_resume(d40c);
 	case DMA_SLAVE_CONFIG:
-		d40_set_runtime_config(chan,
+		return d40_set_runtime_config(chan,
 			(struct dma_slave_config *) arg);
-		return 0;
 	default:
 		break;
 	}
@@ -2341,6 +2398,7 @@ static void __init d40_chan_init(struct d40_base *base, struct dma_device *dma,
 
 		INIT_LIST_HEAD(&d40c->active);
 		INIT_LIST_HEAD(&d40c->queue);
+		INIT_LIST_HEAD(&d40c->pending_queue);
 		INIT_LIST_HEAD(&d40c->client);
 
 		tasklet_init(&d40c->tasklet, dma_tasklet,
@@ -2502,25 +2560,6 @@ static int __init d40_phy_res_init(struct d40_base *base)
 
 static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 {
-	static const struct d40_reg_val dma_id_regs[] = {
-		/* Peripheral Id */
-		{ .reg = D40_DREG_PERIPHID0, .val = 0x0040},
-		{ .reg = D40_DREG_PERIPHID1, .val = 0x0000},
-		/*
-		 * D40_DREG_PERIPHID2 Depends on HW revision:
-		 *  DB8500ed has 0x0008,
-		 *  ? has 0x0018,
-		 *  DB8500v1 has 0x0028
-		 *  DB8500v2 has 0x0038
-		 */
-		{ .reg = D40_DREG_PERIPHID3, .val = 0x0000},
-
-		/* PCell Id */
-		{ .reg = D40_DREG_CELLID0, .val = 0x000d},
-		{ .reg = D40_DREG_CELLID1, .val = 0x00f0},
-		{ .reg = D40_DREG_CELLID2, .val = 0x0005},
-		{ .reg = D40_DREG_CELLID3, .val = 0x00b1}
-	};
 	struct stedma40_platform_data *plat_data;
 	struct clk *clk = NULL;
 	void __iomem *virtbase = NULL;
@@ -2529,8 +2568,9 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	int num_log_chans = 0;
 	int num_phy_chans;
 	int i;
-	u32 val;
-	u32 rev;
+	u32 pid;
+	u32 cid;
+	u8 rev;
 
 	clk = clk_get(&pdev->dev, NULL);
 
@@ -2554,32 +2594,32 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	if (!virtbase)
 		goto failure;
 
-	/* HW version check */
-	for (i = 0; i < ARRAY_SIZE(dma_id_regs); i++) {
-		if (dma_id_regs[i].val !=
-		    readl(virtbase + dma_id_regs[i].reg)) {
-			d40_err(&pdev->dev,
-				"Unknown hardware! Expected 0x%x at 0x%x but got 0x%x\n",
-				dma_id_regs[i].val,
-				dma_id_regs[i].reg,
-				readl(virtbase + dma_id_regs[i].reg));
-			goto failure;
-		}
-	}
+	/* This is just a regular AMBA PrimeCell ID actually */
+	for (pid = 0, i = 0; i < 4; i++)
+		pid |= (readl(virtbase + resource_size(res) - 0x20 + 4 * i)
+			& 255) << (i * 8);
+	for (cid = 0, i = 0; i < 4; i++)
+		cid |= (readl(virtbase + resource_size(res) - 0x10 + 4 * i)
+			& 255) << (i * 8);
 
-	/* Get silicon revision and designer */
-	val = readl(virtbase + D40_DREG_PERIPHID2);
-
-	if ((val & D40_DREG_PERIPHID2_DESIGNER_MASK) !=
-	    D40_HW_DESIGNER) {
+	if (cid != AMBA_CID) {
+		d40_err(&pdev->dev, "Unknown hardware! No PrimeCell ID\n");
+		goto failure;
+	}
+	if (AMBA_MANF_BITS(pid) != AMBA_VENDOR_ST) {
 		d40_err(&pdev->dev, "Unknown designer! Got %x wanted %x\n",
-			val & D40_DREG_PERIPHID2_DESIGNER_MASK,
-			D40_HW_DESIGNER);
+			AMBA_MANF_BITS(pid),
+			AMBA_VENDOR_ST);
 		goto failure;
 	}
-
-	rev = (val & D40_DREG_PERIPHID2_REV_MASK) >>
-		D40_DREG_PERIPHID2_REV_POS;
+	/*
+	 * HW revision:
+	 * DB8500ed has revision 0
+	 * ? has revision 1
+	 * DB8500v1 has revision 2
+	 * DB8500v2 has revision 3
+	 */
+	rev = AMBA_REV_BITS(pid);
 
 	/* The number of physical channels on this HW */
 	num_phy_chans = 4 * (readl(virtbase + D40_DREG_ICFG) & 0x7) + 4;
diff --git a/drivers/dma/ste_dma40_ll.h b/drivers/dma/ste_dma40_ll.h
index 195ee65ee7f..b44c455158d 100644
--- a/drivers/dma/ste_dma40_ll.h
+++ b/drivers/dma/ste_dma40_ll.h
@@ -184,9 +184,6 @@
 #define D40_DREG_PERIPHID0	0xFE0
 #define D40_DREG_PERIPHID1	0xFE4
 #define D40_DREG_PERIPHID2	0xFE8
-#define D40_DREG_PERIPHID2_REV_POS 4
-#define D40_DREG_PERIPHID2_REV_MASK (0xf << D40_DREG_PERIPHID2_REV_POS)
-#define D40_DREG_PERIPHID2_DESIGNER_MASK 0xf
 #define D40_DREG_PERIPHID3	0xFEC
 #define D40_DREG_CELLID0	0xFF0
 #define D40_DREG_CELLID1	0xFF4