Linux-libre 4.5-gnu

35 files changed, 1898 insertions, 1079 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e6cd1a320..79b1390f2 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -431,8 +431,20 @@ config STE_DMA40
 	help
 	  Support for ST-Ericsson DMA40 controller
 
+config STM32_DMA
+	bool "STMicroelectronics STM32 DMA support"
+	depends on ARCH_STM32
+	select DMA_ENGINE
+	select DMA_OF
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip DMA controller on STMicroelectronics
+	  STM32 MCUs.
+	  If you have a board based on such a MCU and wish to use DMA say Y or M
+	  here.
+
 config S3C24XX_DMAC
-	tristate "Samsung S3C24XX DMA support"
+	bool "Samsung S3C24XX DMA support"
 	depends on ARCH_S3C24XX
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index ef9c099bd..2dd0a067a 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
+obj-$(CONFIG_STM32_DMA) += stm32-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 16d0daa05..eed6bda01 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -15,6 +15,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -72,7 +73,9 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	si = (const struct acpi_csrt_shared_info *)&grp[1];
 
 	/* Match device by MMIO and IRQ */
-	if (si->mmio_base_low != mem || si->gsi_interrupt != irq)
+	if (si->mmio_base_low != lower_32_bits(mem) ||
+	    si->mmio_base_high != upper_32_bits(mem) ||
+	    si->gsi_interrupt != irq)
 		return 0;
 
 	dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n",
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index fa00f3a18..8e304b1be 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -176,6 +176,7 @@
 #define AT_XDMAC_MAX_CHAN	0x20
 #define AT_XDMAC_MAX_CSIZE	16	/* 16 data */
 #define AT_XDMAC_MAX_DWIDTH	8	/* 64 bits */
+#define AT_XDMAC_RESIDUE_MAX_RETRIES	5
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
 	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -863,8 +864,12 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DIF(0)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
@@ -1041,8 +1046,12 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * access DDR through both ports (at least on SAMA5D4x), so we can use
 	 * the same interface for source and dest, that solves the fact we
 	 * don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_INCREMENTED_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1143,8 +1152,12 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_UBS_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1383,8 +1396,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	struct at_xdmac_desc	*desc, *_desc;
 	struct list_head	*descs_list;
 	enum dma_status		ret;
-	int			residue;
-	u32			cur_nda, mask, value;
+	int			residue, retry;
+	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
 
@@ -1421,7 +1434,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 			cpu_relax();
 	}
 
+	/*
+	 * When processing the residue, we need to read two registers but we
+	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
+	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
+	 * to know how many data are remaining for the current descriptor.
+	 * Since the dma channel is not paused to not loose data, between the
+	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
+	 * descriptor.
+	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
+	 * still using the same descriptor by reading a second time
+	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
+	 * read again AT_XDMAC_CUBC.
+	 * Memory barriers are used to ensure the read order of the registers.
+	 * A max number of retries is set because unlikely it can never ends if
+	 * we are transferring a lot of data with small buffers.
+	 */
 	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+	rmb();
+	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
+		rmb();
+		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+
+		if (likely(cur_nda == check_nda))
+			break;
+
+		cur_nda = check_nda;
+		rmb();
+		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	}
+
+	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
+		ret = DMA_ERROR;
+		goto spin_unlock;
+	}
+
 	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
@@ -1434,7 +1482,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
 			break;
 	}
-	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+	residue += cur_ubc << dwidth;
 
 	dma_set_residue(txstate, residue);
 
@@ -2001,8 +2049,6 @@ static int at_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&atxdmac->dma);
 	clk_disable_unprepare(atxdmac->clk);
 
-	synchronize_irq(atxdmac->irq);
-
 	free_irq(atxdmac->irq, atxdmac->dma.dev);
 
 	for (i = 0; i < atxdmac->dma.chancnt; i++) {
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 5b2395e7e..c34680943 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -307,6 +307,13 @@ static int axi_dmac_terminate_all(struct dma_chan *c)
 	return 0;
 }
 
+static void axi_dmac_synchronize(struct dma_chan *c)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+
+	vchan_synchronize(&chan->vchan);
+}
+
 static void axi_dmac_issue_pending(struct dma_chan *c)
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
@@ -613,6 +620,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->device_prep_dma_cyclic = axi_dmac_prep_dma_cyclic;
 	dma_dev->device_prep_interleaved_dma = axi_dmac_prep_interleaved;
 	dma_dev->device_terminate_all = axi_dmac_terminate_all;
+	dma_dev->device_synchronize = axi_dmac_synchronize;
 	dma_dev->dev = &pdev->dev;
 	dma_dev->chancnt = 1;
 	dma_dev->src_addr_widths = BIT(dmac->chan.src_width);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 3ecec1445..c50a247be 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -43,6 +43,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -265,8 +266,11 @@ static void dma_chan_put(struct dma_chan *chan)
 	module_put(dma_chan_to_owner(chan));
 
 	/* This channel is not in use anymore, free it */
-	if (!chan->client_count && chan->device->device_free_chan_resources)
+	if (!chan->client_count && chan->device->device_free_chan_resources) {
+		/* Make sure all operations have completed */
+		dmaengine_synchronize(chan);
 		chan->device->device_free_chan_resources(chan);
+	}
 
 	/* If the channel is used via a DMA request router, free the mapping */
 	if (chan->router && chan->router->route_free) {
@@ -493,6 +497,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
 	caps->residue_granularity = device->residue_granularity;
+	caps->descriptor_reuse = device->descriptor_reuse;
 
 	/*
 	 * Some devices implement only pause (e.g. to get residuum) but no
@@ -511,7 +516,7 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 {
 	struct dma_chan *chan;
 
-	if (!__dma_device_satisfies_mask(dev, mask)) {
+	if (mask && !__dma_device_satisfies_mask(dev, mask)) {
 		pr_debug("%s: wrong capabilities\n", __func__);
 		return NULL;
 	}
@@ -542,6 +547,42 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 	return NULL;
 }
 
+static struct dma_chan *find_candidate(struct dma_device *device,
+				       const dma_cap_mask_t *mask,
+				       dma_filter_fn fn, void *fn_param)
+{
+	struct dma_chan *chan = private_candidate(mask, device, fn, fn_param);
+	int err;
+
+	if (chan) {
+		/* Found a suitable channel, try to grab, prep, and return it.
+		 * We first set DMA_PRIVATE to disable balance_ref_count as this
+		 * channel will not be published in the general-purpose
+		 * allocator
+		 */
+		dma_cap_set(DMA_PRIVATE, device->cap_mask);
+		device->privatecnt++;
+		err = dma_chan_get(chan);
+
+		if (err) {
+			if (err == -ENODEV) {
+				pr_debug("%s: %s module removed\n", __func__,
+					 dma_chan_name(chan));
+				list_del_rcu(&device->global_node);
+			} else
+				pr_debug("%s: failed to get %s: (%d)\n",
+					 __func__, dma_chan_name(chan), err);
+
+			if (--device->privatecnt == 0)
+				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+
+			chan = ERR_PTR(err);
+		}
+	}
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
+}
+
 /**
  * dma_get_slave_channel - try to get specific channel exclusively
  * @chan: target channel
@@ -580,7 +621,6 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 {
 	dma_cap_mask_t mask;
 	struct dma_chan *chan;
-	int err;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -588,23 +628,11 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 	/* lock against __dma_request_channel */
 	mutex_lock(&dma_list_mutex);
 
-	chan = private_candidate(&mask, device, NULL, NULL);
-	if (chan) {
-		dma_cap_set(DMA_PRIVATE, device->cap_mask);
-		device->privatecnt++;
-		err = dma_chan_get(chan);
-		if (err) {
-			pr_debug("%s: failed to get %s: (%d)\n",
-				__func__, dma_chan_name(chan), err);
-			chan = NULL;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-		}
-	}
+	chan = find_candidate(device, &mask, NULL, NULL);
 
 	mutex_unlock(&dma_list_mutex);
 
-	return chan;
+	return IS_ERR(chan) ? NULL : chan;
 }
 EXPORT_SYMBOL_GPL(dma_get_any_slave_channel);
 
@@ -621,35 +649,15 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	struct dma_device *device, *_d;
 	struct dma_chan *chan = NULL;
-	int err;
 
 	/* Find a channel */
 	mutex_lock(&dma_list_mutex);
 	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
-		chan = private_candidate(mask, device, fn, fn_param);
-		if (chan) {
-			/* Found a suitable channel, try to grab, prep, and
-			 * return it.  We first set DMA_PRIVATE to disable
-			 * balance_ref_count as this channel will not be
-			 * published in the general-purpose allocator
-			 */
-			dma_cap_set(DMA_PRIVATE, device->cap_mask);
-			device->privatecnt++;
-			err = dma_chan_get(chan);
+		chan = find_candidate(device, mask, fn, fn_param);
+		if (!IS_ERR(chan))
+			break;
 
-			if (err == -ENODEV) {
-				pr_debug("%s: %s module removed\n",
-					 __func__, dma_chan_name(chan));
-				list_del_rcu(&device->global_node);
-			} else if (err)
-				pr_debug("%s: failed to get %s: (%d)\n",
-					 __func__, dma_chan_name(chan), err);
-			else
-				break;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-			chan = NULL;
-		}
+		chan = NULL;
 	}
 	mutex_unlock(&dma_list_mutex);
 
@@ -662,27 +670,73 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 }
 EXPORT_SYMBOL_GPL(__dma_request_channel);
 
+static const struct dma_slave_map *dma_filter_match(struct dma_device *device,
+						    const char *name,
+						    struct device *dev)
+{
+	int i;
+
+	if (!device->filter.mapcnt)
+		return NULL;
+
+	for (i = 0; i < device->filter.mapcnt; i++) {
+		const struct dma_slave_map *map = &device->filter.map[i];
+
+		if (!strcmp(map->devname, dev_name(dev)) &&
+		    !strcmp(map->slave, name))
+			return map;
+	}
+
+	return NULL;
+}
+
 /**
- * dma_request_slave_channel_reason - try to allocate an exclusive slave channel
+ * dma_request_chan - try to allocate an exclusive slave channel
  * @dev:	pointer to client device structure
  * @name:	slave channel name
  *
  * Returns pointer to appropriate DMA channel on success or an error pointer.
  */
-struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
-						  const char *name)
+struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 {
+	struct dma_device *d, *_d;
+	struct dma_chan *chan = NULL;
+
 	/* If device-tree is present get slave info from here */
 	if (dev->of_node)
-		return of_dma_request_slave_channel(dev->of_node, name);
+		chan = of_dma_request_slave_channel(dev->of_node, name);
 
 	/* If device was enumerated by ACPI get slave info from here */
-	if (ACPI_HANDLE(dev))
-		return acpi_dma_request_slave_chan_by_name(dev, name);
+	if (has_acpi_companion(dev) && !chan)
+		chan = acpi_dma_request_slave_chan_by_name(dev, name);
+
+	if (chan) {
+		/* Valid channel found or requester need to be deferred */
+		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
+			return chan;
+	}
 
-	return ERR_PTR(-ENODEV);
+	/* Try to find the channel via the DMA filter map(s) */
+	mutex_lock(&dma_list_mutex);
+	list_for_each_entry_safe(d, _d, &dma_device_list, global_node) {
+		dma_cap_mask_t mask;
+		const struct dma_slave_map *map = dma_filter_match(d, name, dev);
+
+		if (!map)
+			continue;
+
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+
+		chan = find_candidate(d, &mask, d->filter.fn, map->param);
+		if (!IS_ERR(chan))
+			break;
+	}
+	mutex_unlock(&dma_list_mutex);
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 }
-EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
+EXPORT_SYMBOL_GPL(dma_request_chan);
 
 /**
  * dma_request_slave_channel - try to allocate an exclusive slave channel
@@ -694,17 +748,35 @@ EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
 struct dma_chan *dma_request_slave_channel(struct device *dev,
 					   const char *name)
 {
-	struct dma_chan *ch = dma_request_slave_channel_reason(dev, name);
+	struct dma_chan *ch = dma_request_chan(dev, name);
 	if (IS_ERR(ch))
 		return NULL;
 
-	dma_cap_set(DMA_PRIVATE, ch->device->cap_mask);
-	ch->device->privatecnt++;
-
 	return ch;
 }
 EXPORT_SYMBOL_GPL(dma_request_slave_channel);
 
+/**
+ * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
+ * @mask: capabilities that the channel must satisfy
+ *
+ * Returns pointer to appropriate DMA channel on success or an error pointer.
+ */
+struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
+{
+	struct dma_chan *chan;
+
+	if (!mask)
+		return ERR_PTR(-ENODEV);
+
+	chan = __dma_request_channel(mask, NULL, NULL);
+	if (!chan)
+		chan = ERR_PTR(-ENODEV);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(dma_request_chan_by_mask);
+
 void dma_release_channel(struct dma_chan *chan)
 {
 	mutex_lock(&dma_list_mutex);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 4f099ea29..5ad0ec1f0 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -628,12 +628,17 @@ static void dw_dma_tasklet(unsigned long data)
 static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 {
 	struct dw_dma *dw = dev_id;
-	u32 status = dma_readl(dw, STATUS_INT);
+	u32 status;
 
+	/* Check if we have any interrupt from the DMAC which is not in use */
+	if (!dw->in_use)
+		return IRQ_NONE;
+
+	status = dma_readl(dw, STATUS_INT);
 	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status);
 
 	/* Check if we have any interrupt from the DMAC */
-	if (!status || !dw->in_use)
+	if (!status)
 		return IRQ_NONE;
 
 	/*
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 4c30fdd09..358f9689a 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -108,6 +108,10 @@ static const struct pci_device_id dw_pci_id_table[] = {
 
 	/* Haswell */
 	{ PCI_VDEVICE(INTEL, 0x9c60) },
+
+	/* Broadwell */
+	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, dw_pci_id_table);
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 68a481575..26edbe3a2 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -103,18 +103,21 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct dw_dma_platform_data *pdata;
 	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 nr_channels;
 
 	if (!np) {
 		dev_err(&pdev->dev, "Missing DT data\n");
 		return NULL;
 	}
 
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	if (of_property_read_u32(np, "dma-channels", &pdata->nr_channels))
-		return NULL;
+	pdata->nr_channels = nr_channels;
 
 	if (of_property_read_bool(np, "is_private"))
 		pdata->is_private = true;
@@ -155,7 +158,6 @@ static int dw_probe(struct platform_device *pdev)
 	struct dw_dma_chip *chip;
 	struct device *dev = &pdev->dev;
 	struct resource *mem;
-	const struct acpi_device_id *id;
 	struct dw_dma_platform_data *pdata;
 	int err;
 
@@ -179,11 +181,6 @@ static int dw_probe(struct platform_device *pdev)
 	pdata = dev_get_platdata(dev);
 	if (!pdata)
 		pdata = dw_dma_parse_dt(pdev);
-	if (!pdata && has_acpi_companion(dev)) {
-		id = acpi_match_device(dev->driver->acpi_match_table, dev);
-		if (id)
-			pdata = (struct dw_dma_platform_data *)id->driver_data;
-	}
 
 	chip->dev = dev;
 
@@ -239,7 +236,19 @@ static void dw_shutdown(struct platform_device *pdev)
 {
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
 
+	/*
+	 * We have to call dw_dma_disable() to stop any ongoing transfer. On
+	 * some platforms we can't do that since DMA device is powered off.
+	 * Moreover we have no possibility to check if the platform is affected
+	 * or not. That's why we call pm_runtime_get_sync() / pm_runtime_put()
+	 * unconditionally. On the other hand we can't use
+	 * pm_runtime_suspended() because runtime PM framework is not fully
+	 * used by the driver.
+	 */
+	pm_runtime_get_sync(chip->dev);
 	dw_dma_disable(chip);
+	pm_runtime_put_sync_suspend(chip->dev);
+
 	clk_disable_unprepare(chip->clk);
 }
 
@@ -252,17 +261,8 @@ MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);
 #endif
 
 #ifdef CONFIG_ACPI
-static struct dw_dma_platform_data dw_dma_acpi_pdata = {
-	.nr_channels = 8,
-	.is_private = true,
-	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
-	.chan_priority = CHAN_PRIORITY_ASCENDING,
-	.block_size = 4095,
-	.nr_masters = 2,
-};
-
 static const struct acpi_device_id dw_dma_acpi_id_table[] = {
-	{ "INTL9C60", (kernel_ulong_t)&dw_dma_acpi_pdata },
+	{ "INTL9C60", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 16fe773fb..e3d7fcb69 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -113,6 +113,9 @@
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
 #define CHMAP_EXIST		BIT(24)
 
+/* CCSTAT register */
+#define EDMA_CCSTAT_ACTV	BIT(4)
+
 /*
  * Max of 20 segments per channel to conserve PaRAM slots
  * Also note that MAX_NR_SG should be atleast the no.of periods
@@ -484,7 +487,7 @@ static void edma_read_slot(struct edma_cc *ecc, unsigned slot,
  */
 static int edma_alloc_slot(struct edma_cc *ecc, int slot)
 {
-	if (slot > 0) {
+	if (slot >= 0) {
 		slot = EDMA_CHAN_SLOT(slot);
 		/* Requesting entry paRAM slot for a HW triggered channel. */
 		if (ecc->chmap_exist && slot < ecc->num_channels)
@@ -1680,9 +1683,20 @@ static void edma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 }
 
+/*
+ * This limit exists to avoid a possible infinite loop when waiting for proof
+ * that a particular transfer is completed. This limit can be hit if there
+ * are large bursts to/from slow devices or the CPU is never able to catch
+ * the DMA hardware idle. On an AM335x transfering 48 bytes from the UART
+ * RX-FIFO, as many as 55 loops have been seen.
+ */
+#define EDMA_MAX_TR_WAIT_LOOPS 1000
+
 static u32 edma_residue(struct edma_desc *edesc)
 {
 	bool dst = edesc->direction == DMA_DEV_TO_MEM;
+	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
+	struct edma_chan *echan = edesc->echan;
 	struct edma_pset *pset = edesc->pset;
 	dma_addr_t done, pos;
 	int i;
@@ -1691,7 +1705,32 @@ static u32 edma_residue(struct edma_desc *edesc)
 	 * We always read the dst/src position from the first RamPar
 	 * pset. That's the one which is active now.
 	 */
-	pos = edma_get_position(edesc->echan->ecc, edesc->echan->slot[0], dst);
+	pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+
+	/*
+	 * "pos" may represent a transfer request that is still being
+	 * processed by the EDMACC or EDMATC. We will busy wait until
+	 * any one of the situations occurs:
+	 *   1. the DMA hardware is idle
+	 *   2. a new transfer request is setup
+	 *   3. we hit the loop limit
+	 */
+	while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) {
+		/* check if a new transfer request is setup */
+		if (edma_get_position(echan->ecc,
+				      echan->slot[0], dst) != pos) {
+			break;
+		}
+
+		if (!--loop_count) {
+			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
+				"%s: timeout waiting for PaRAM update\n",
+				__func__);
+			break;
+		}
+
+		cpu_relax();
+	}
 
 	/*
 	 * Cyclic is simple. Just subtract pset[0].addr from pos.
@@ -2314,6 +2353,10 @@ static int edma_probe(struct platform_device *pdev)
 		edma_set_chmap(&ecc->slave_chans[i], ecc->dummy_slot);
 	}
 
+	ecc->dma_slave.filter.map = info->slave_map;
+	ecc->dma_slave.filter.mapcnt = info->slavecnt;
+	ecc->dma_slave.filter.fn = edma_filter_fn;
+
 	ret = dma_async_device_register(&ecc->dma_slave);
 	if (ret) {
 		dev_err(dev, "slave ddev registration failed (%d)\n", ret);
@@ -2421,7 +2464,13 @@ static struct platform_driver edma_driver = {
 	},
 };
 
+static int edma_tptc_probe(struct platform_device *pdev)
+{
+	return 0;
+}
+
 static struct platform_driver edma_tptc_driver = {
+	.probe		= edma_tptc_probe,
 	.driver = {
 		.name	= "edma3-tptc",
 		.of_match_table = edma_tptc_of_ids,
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 915eec3cc..be2e62b87 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -116,6 +116,10 @@
 				BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
+enum fsl_edma_pm_state {
+	RUNNING = 0,
+	SUSPENDED,
+};
 
 struct fsl_edma_hw_tcd {
 	__le32	saddr;
@@ -147,6 +151,9 @@ struct fsl_edma_slave_config {
 struct fsl_edma_chan {
 	struct virt_dma_chan		vchan;
 	enum dma_status			status;
+	enum fsl_edma_pm_state		pm_state;
+	bool				idle;
+	u32				slave_id;
 	struct fsl_edma_engine		*edma;
 	struct fsl_edma_desc		*edesc;
 	struct fsl_edma_slave_config	fsc;
@@ -298,6 +305,7 @@ static int fsl_edma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 	fsl_edma_disable_request(fsl_chan);
 	fsl_chan->edesc = NULL;
+	fsl_chan->idle = true;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
@@ -313,6 +321,7 @@ static int fsl_edma_pause(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_disable_request(fsl_chan);
 		fsl_chan->status = DMA_PAUSED;
+		fsl_chan->idle = true;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -327,6 +336,7 @@ static int fsl_edma_resume(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_enable_request(fsl_chan);
 		fsl_chan->status = DMA_IN_PROGRESS;
+		fsl_chan->idle = false;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -648,6 +658,7 @@ static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
 	fsl_edma_enable_request(fsl_chan);
 	fsl_chan->status = DMA_IN_PROGRESS;
+	fsl_chan->idle = false;
 }
 
 static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
@@ -676,6 +687,7 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
 				fsl_chan->edesc = NULL;
 				fsl_chan->status = DMA_COMPLETE;
+				fsl_chan->idle = true;
 			} else {
 				vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
 			}
@@ -704,6 +716,7 @@ static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch),
 				fsl_edma->membase + EDMA_CERR);
 			fsl_edma->chans[ch].status = DMA_ERROR;
+			fsl_edma->chans[ch].idle = true;
 		}
 	}
 	return IRQ_HANDLED;
@@ -724,6 +737,12 @@ static void fsl_edma_issue_pending(struct dma_chan *chan)
 
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 
+	if (unlikely(fsl_chan->pm_state != RUNNING)) {
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		/* cannot submit due to suspend */
+		return;
+	}
+
 	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
 		fsl_edma_xfer_desc(fsl_chan);
 
@@ -735,6 +754,7 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data;
 	struct dma_chan *chan, *_chan;
+	struct fsl_edma_chan *fsl_chan;
 	unsigned long chans_per_mux = fsl_edma->n_chans / DMAMUX_NR;
 
 	if (dma_spec->args_count != 2)
@@ -748,8 +768,10 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 			chan = dma_get_slave_channel(chan);
 			if (chan) {
 				chan->device->privatecnt++;
-				fsl_edma_chan_mux(to_fsl_edma_chan(chan),
-					dma_spec->args[1], true);
+				fsl_chan = to_fsl_edma_chan(chan);
+				fsl_chan->slave_id = dma_spec->args[1];
+				fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id,
+						true);
 				mutex_unlock(&fsl_edma->fsl_edma_mutex);
 				return chan;
 			}
@@ -888,7 +910,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
 
 		fsl_chan->edma = fsl_edma;
-
+		fsl_chan->pm_state = RUNNING;
+		fsl_chan->slave_id = 0;
+		fsl_chan->idle = true;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
@@ -959,6 +983,60 @@ static int fsl_edma_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int fsl_edma_suspend_late(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		/* Make sure chan is idle or will force disable. */
+		if (unlikely(!fsl_chan->idle)) {
+			dev_warn(dev, "WARN: There is non-idle channel.");
+			fsl_edma_disable_request(fsl_chan);
+			fsl_edma_chan_mux(fsl_chan, 0, false);
+		}
+
+		fsl_chan->pm_state = SUSPENDED;
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	}
+
+	return 0;
+}
+
+static int fsl_edma_resume_early(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		fsl_chan->pm_state = RUNNING;
+		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		if (fsl_chan->slave_id != 0)
+			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
+	}
+
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA,
+			fsl_edma->membase + EDMA_CR);
+
+	return 0;
+}
+
+/*
+ * eDMA provides the service to others, so it should be suspend late
+ * and resume early. When eDMA suspend, all of the clients should stop
+ * the DMA data transmission and let the channel idle.
+ */
+static const struct dev_pm_ops fsl_edma_pm_ops = {
+	.suspend_late   = fsl_edma_suspend_late,
+	.resume_early   = fsl_edma_resume_early,
+};
+
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", },
 	{ /* sentinel */ }
@@ -969,6 +1047,7 @@ static struct platform_driver fsl_edma_driver = {
 	.driver		= {
 		.name	= "fsl-edma",
 		.of_match_table = fsl_edma_dt_ids,
+		.pm     = &fsl_edma_pm_ops,
 	},
 	.probe          = fsl_edma_probe,
 	.remove		= fsl_edma_remove,
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 2209f75fd..aac85c30c 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -522,6 +522,8 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan,
 			chan_dbg(chan, "LD %p callback\n", desc);
 			txd->callback(txd->callback_param);
 		}
+
+		dma_descriptor_unmap(txd);
 	}
 
 	/* Run any dependencies */
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 823ad728a..eef145edb 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -228,6 +228,8 @@ static struct dma_async_tx_descriptor *hsu_dma_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		desc->sg[i].addr = sg_dma_address(sg);
 		desc->sg[i].len = sg_dma_len(sg);
+
+		desc->length += sg_dma_len(sg);
 	}
 
 	desc->nents = sg_len;
@@ -249,21 +251,10 @@ static void hsu_dma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 }
 
-static size_t hsu_dma_desc_size(struct hsu_dma_desc *desc)
-{
-	size_t bytes = 0;
-	unsigned int i;
-
-	for (i = desc->active; i < desc->nents; i++)
-		bytes += desc->sg[i].len;
-
-	return bytes;
-}
-
 static size_t hsu_dma_active_desc_size(struct hsu_dma_chan *hsuc)
 {
 	struct hsu_dma_desc *desc = hsuc->desc;
-	size_t bytes = hsu_dma_desc_size(desc);
+	size_t bytes = desc->length;
 	int i;
 
 	i = desc->active % HSU_DMA_CHAN_NR_DESC;
@@ -294,7 +285,7 @@ static enum dma_status hsu_dma_tx_status(struct dma_chan *chan,
 		dma_set_residue(state, bytes);
 		status = hsuc->desc->status;
 	} else if (vdesc) {
-		bytes = hsu_dma_desc_size(to_hsu_dma_desc(vdesc));
+		bytes = to_hsu_dma_desc(vdesc)->length;
 		dma_set_residue(state, bytes);
 	}
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index f06579c6d..578a8ee8c 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -65,6 +65,7 @@ struct hsu_dma_desc {
 	enum dma_transfer_direction direction;
 	struct hsu_dma_sg *sg;
 	unsigned int nents;
+	size_t length;
 	unsigned int active;
 	enum dma_status status;
 };
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 7d56b47e4..3cb7b2c78 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -178,20 +178,12 @@ static irqreturn_t idma64_irq(int irq, void *dev)
 	if (!status)
 		return IRQ_NONE;
 
-	/* Disable interrupts */
-	channel_clear_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_clear_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	status_xfer = dma_readl(idma64, RAW(XFER));
 	status_err = dma_readl(idma64, RAW(ERROR));
 
 	for (i = 0; i < idma64->dma.chancnt; i++)
 		idma64_chan_irq(idma64, i, status_err, status_xfer);
 
-	/* Re-enable interrupts */
-	channel_set_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_set_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	return IRQ_HANDLED;
 }
 
@@ -239,7 +231,7 @@ static void idma64_vdesc_free(struct virt_dma_desc *vdesc)
 	idma64_desc_free(idma64c, to_idma64_desc(vdesc));
 }
 
-static u64 idma64_hw_desc_fill(struct idma64_hw_desc *hw,
+static void idma64_hw_desc_fill(struct idma64_hw_desc *hw,
 		struct dma_slave_config *config,
 		enum dma_transfer_direction direction, u64 llp)
 {
@@ -276,26 +268,26 @@ static u64 idma64_hw_desc_fill(struct idma64_hw_desc *hw,
 		     IDMA64C_CTLL_SRC_WIDTH(src_width);
 
 	lli->llp = llp;
-	return hw->llp;
 }
 
 static void idma64_desc_fill(struct idma64_chan *idma64c,
 		struct idma64_desc *desc)
 {
 	struct dma_slave_config *config = &idma64c->config;
-	struct idma64_hw_desc *hw = &desc->hw[desc->ndesc - 1];
+	unsigned int i = desc->ndesc;
+	struct idma64_hw_desc *hw = &desc->hw[i - 1];
 	struct idma64_lli *lli = hw->lli;
 	u64 llp = 0;
-	unsigned int i = desc->ndesc;
 
 	/* Fill the hardware descriptors and link them to a list */
 	do {
 		hw = &desc->hw[--i];
-		llp = idma64_hw_desc_fill(hw, config, desc->direction, llp);
+		idma64_hw_desc_fill(hw, config, desc->direction, llp);
+		llp = hw->llp;
 		desc->length += hw->len;
 	} while (i);
 
-	/* Trigger interrupt after last block */
+	/* Trigger an interrupt after the last block is transfered */
 	lli->ctllo |= IDMA64C_CTLL_INT_EN;
 }
 
@@ -596,6 +588,8 @@ static int idma64_probe(struct idma64_chip *chip)
 
 	idma64->dma.dev = chip->dev;
 
+	dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK);
+
 	ret = dma_async_device_register(&idma64->dma);
 	if (ret)
 		return ret;
diff --git a/drivers/dma/idma64.h b/drivers/dma/idma64.h
index f6aeff0af..8423f13ed 100644
--- a/drivers/dma/idma64.h
+++ b/drivers/dma/idma64.h
@@ -54,7 +54,8 @@
 #define IDMA64C_CTLL_LLP_S_EN		(1 << 28)	/* src block chain */
 
 /* Bitfields in CTL_HI */
-#define IDMA64C_CTLH_BLOCK_TS(x)	((x) & ((1 << 17) - 1))
+#define IDMA64C_CTLH_BLOCK_TS_MASK	((1 << 17) - 1)
+#define IDMA64C_CTLH_BLOCK_TS(x)	((x) & IDMA64C_CTLH_BLOCK_TS_MASK)
 #define IDMA64C_CTLH_DONE		(1 << 17)
 
 /* Bitfields in CFG_LO */
diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c
index 9ca56830c..a4c53be48 100644
--- a/drivers/dma/img-mdc-dma.c
+++ b/drivers/dma/img-mdc-dma.c
@@ -651,6 +651,48 @@ static enum dma_status mdc_tx_status(struct dma_chan *chan,
 	return ret;
 }
 
+static unsigned int mdc_get_new_events(struct mdc_chan *mchan)
+{
+	u32 val, processed, done1, done2;
+	unsigned int ret;
+
+	val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+	processed = (val >> MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) &
+				MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK;
+	/*
+	 * CMDS_DONE may have incremented between reading CMDS_PROCESSED
+	 * and clearing INT_ACTIVE.  Re-read CMDS_PROCESSED to ensure we
+	 * didn't miss a command completion.
+	 */
+	do {
+		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+
+		done1 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
+			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
+
+		val &= ~((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK <<
+			  MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) |
+			 MDC_CMDS_PROCESSED_INT_ACTIVE);
+
+		val |= done1 << MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT;
+
+		mdc_chan_writel(mchan, val, MDC_CMDS_PROCESSED);
+
+		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+
+		done2 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
+			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
+	} while (done1 != done2);
+
+	if (done1 >= processed)
+		ret = done1 - processed;
+	else
+		ret = ((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK + 1) -
+			processed) + done1;
+
+	return ret;
+}
+
 static int mdc_terminate_all(struct dma_chan *chan)
 {
 	struct mdc_chan *mchan = to_mdc_chan(chan);
@@ -667,6 +709,8 @@ static int mdc_terminate_all(struct dma_chan *chan)
 	mchan->desc = NULL;
 	vchan_get_all_descriptors(&mchan->vc, &head);
 
+	mdc_get_new_events(mchan);
+
 	spin_unlock_irqrestore(&mchan->vc.lock, flags);
 
 	if (mdesc)
@@ -703,35 +747,17 @@ static irqreturn_t mdc_chan_irq(int irq, void *dev_id)
 {
 	struct mdc_chan *mchan = (struct mdc_chan *)dev_id;
 	struct mdc_tx_desc *mdesc;
-	u32 val, processed, done1, done2;
-	unsigned int i;
+	unsigned int i, new_events;
 
 	spin_lock(&mchan->vc.lock);
 
-	val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-	processed = (val >> MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) &
-		MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK;
-	/*
-	 * CMDS_DONE may have incremented between reading CMDS_PROCESSED
-	 * and clearing INT_ACTIVE.  Re-read CMDS_PROCESSED to ensure we
-	 * didn't miss a command completion.
-	 */
-	do {
-		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-		done1 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
-			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
-		val &= ~((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK <<
-			  MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) |
-			 MDC_CMDS_PROCESSED_INT_ACTIVE);
-		val |= done1 << MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT;
-		mdc_chan_writel(mchan, val, MDC_CMDS_PROCESSED);
-		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-		done2 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
-			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
-	} while (done1 != done2);
-
 	dev_dbg(mdma2dev(mchan->mdma), "IRQ on channel %d\n", mchan->chan_nr);
 
+	new_events = mdc_get_new_events(mchan);
+
+	if (!new_events)
+		goto out;
+
 	mdesc = mchan->desc;
 	if (!mdesc) {
 		dev_warn(mdma2dev(mchan->mdma),
@@ -740,8 +766,7 @@ static irqreturn_t mdc_chan_irq(int irq, void *dev_id)
 		goto out;
 	}
 
-	for (i = processed; i != done1;
-	     i = (i + 1) % (MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK + 1)) {
+	for (i = 0; i < new_events; i++) {
 		/*
 		 * The first interrupt in a transfer indicates that the
 		 * command list has been loaded, not that a command has
@@ -979,7 +1004,6 @@ static int mdc_dma_remove(struct platform_device *pdev)
 				 vc.chan.device_node) {
 		list_del(&mchan->vc.chan.device_node);
 
-		synchronize_irq(mchan->irq);
 		devm_free_irq(&pdev->dev, mchan->irq, mchan);
 
 		tasklet_kill(&mchan->vc.task);
diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c
index 2cb7c308d..0b9b6b07d 100644
--- a/drivers/dma/ioat/dca.c
+++ b/drivers/dma/ioat/dca.c
@@ -224,7 +224,7 @@ static u8 ioat_dca_get_tag(struct dca_provider *dca,
 	return tag;
 }
 
-static struct dca_ops ioat_dca_ops = {
+static const struct dca_ops ioat_dca_ops = {
 	.add_requester		= ioat_dca_add_requester,
 	.remove_requester	= ioat_dca_remove_requester,
 	.get_tag		= ioat_dca_get_tag,
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1d5df2ef1..21539d5c5 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -861,32 +861,42 @@ void ioat_timer_event(unsigned long data)
 			return;
 	}
 
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+
+	/* handle the no-actives case */
+	if (!ioat_ring_active(ioat_chan)) {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		check_active(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+		spin_unlock_bh(&ioat_chan->cleanup_lock);
+		return;
+	}
+
 	/* if we haven't made progress and we have already
 	 * acknowledged a pending completion once, then be more
 	 * forceful with a restart
 	 */
-	spin_lock_bh(&ioat_chan->cleanup_lock);
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
 		__cleanup(ioat_chan, phys_complete);
 	else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
+		u32 chanerr;
+
+		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
+		dev_warn(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n",
+			 status, chanerr);
+		dev_warn(to_dev(ioat_chan), "Active descriptors: %d\n",
+			 ioat_ring_active(ioat_chan));
+
 		spin_lock_bh(&ioat_chan->prep_lock);
 		ioat_restart_channel(ioat_chan);
 		spin_unlock_bh(&ioat_chan->prep_lock);
 		spin_unlock_bh(&ioat_chan->cleanup_lock);
 		return;
-	} else {
+	} else
 		set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	}
-
 
-	if (ioat_ring_active(ioat_chan))
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	else {
-		spin_lock_bh(&ioat_chan->prep_lock);
-		check_active(ioat_chan);
-		spin_unlock_bh(&ioat_chan->prep_lock);
-	}
+	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 8f4e607d5..b8f480747 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -235,43 +235,11 @@ ioat_chan_by_index(struct ioatdma_device *ioat_dma, int index)
 	return ioat_dma->idx[index];
 }
 
-static inline u64 ioat_chansts_32(struct ioatdma_chan *ioat_chan)
-{
-	u8 ver = ioat_chan->ioat_dma->version;
-	u64 status;
-	u32 status_lo;
-
-	/* We need to read the low address first as this causes the
-	 * chipset to latch the upper bits for the subsequent read
-	 */
-	status_lo = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_LOW(ver));
-	status = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_HIGH(ver));
-	status <<= 32;
-	status |= status_lo;
-
-	return status;
-}
-
-#if BITS_PER_LONG == 64
-
 static inline u64 ioat_chansts(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = ioat_chan->ioat_dma->version;
-	u64 status;
-
-	 /* With IOAT v3.3 the status register is 64bit.  */
-	if (ver >= IOAT_VER_3_3)
-		status = readq(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET(ver));
-	else
-		status = ioat_chansts_32(ioat_chan);
-
-	return status;
+	return readq(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET);
 }
 
-#else
-#define ioat_chansts ioat_chansts_32
-#endif
-
 static inline u64 ioat_chansts_to_addr(u64 status)
 {
 	return status & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h
index 909352f74..4994a3623 100644
--- a/drivers/dma/ioat/registers.h
+++ b/drivers/dma/ioat/registers.h
@@ -99,19 +99,9 @@
 #define IOAT_DMA_COMP_V1			0x0001	/* Compatibility with DMA version 1 */
 #define IOAT_DMA_COMP_V2			0x0002	/* Compatibility with DMA version 2 */
 
-
-#define IOAT1_CHANSTS_OFFSET		0x04	/* 64-bit Channel Status Register */
-#define IOAT2_CHANSTS_OFFSET		0x08	/* 64-bit Channel Status Register */
-#define IOAT_CHANSTS_OFFSET(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET : IOAT2_CHANSTS_OFFSET)
-#define IOAT1_CHANSTS_OFFSET_LOW	0x04
-#define IOAT2_CHANSTS_OFFSET_LOW	0x08
-#define IOAT_CHANSTS_OFFSET_LOW(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET_LOW : IOAT2_CHANSTS_OFFSET_LOW)
-#define IOAT1_CHANSTS_OFFSET_HIGH	0x08
-#define IOAT2_CHANSTS_OFFSET_HIGH	0x0C
-#define IOAT_CHANSTS_OFFSET_HIGH(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET_HIGH : IOAT2_CHANSTS_OFFSET_HIGH)
+/* IOAT1 define left for i7300_idle driver to not fail compiling */
+#define IOAT1_CHANSTS_OFFSET		0x04
+#define IOAT_CHANSTS_OFFSET		0x08	/* 64-bit Channel Status Register */
 #define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR	(~0x3fULL)
 #define IOAT_CHANSTS_SOFT_ERR			0x10ULL
 #define IOAT_CHANSTS_UNAFFILIATED_ERR		0x8ULL
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 1c2de9a83..14091f878 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -139,46 +139,10 @@ static void mv_chan_clear_err_status(struct mv_xor_chan *chan)
 }
 
 static void mv_chan_set_mode(struct mv_xor_chan *chan,
-			     enum dma_transaction_type type)
+			     u32 op_mode)
 {
-	u32 op_mode;
 	u32 config = readl_relaxed(XOR_CONFIG(chan));
 
-	switch (type) {
-	case DMA_XOR:
-		op_mode = XOR_OPERATION_MODE_XOR;
-		break;
-	case DMA_MEMCPY:
-		op_mode = XOR_OPERATION_MODE_MEMCPY;
-		break;
-	default:
-		dev_err(mv_chan_to_devp(chan),
-			"error: unsupported operation %d\n",
-			type);
-		BUG();
-		return;
-	}
-
-	config &= ~0x7;
-	config |= op_mode;
-
-#if defined(__BIG_ENDIAN)
-	config |= XOR_DESCRIPTOR_SWAP;
-#else
-	config &= ~XOR_DESCRIPTOR_SWAP;
-#endif
-
-	writel_relaxed(config, XOR_CONFIG(chan));
-	chan->current_type = type;
-}
-
-static void mv_chan_set_mode_to_desc(struct mv_xor_chan *chan)
-{
-	u32 op_mode;
-	u32 config = readl_relaxed(XOR_CONFIG(chan));
-
-	op_mode = XOR_OPERATION_MODE_IN_DESC;
-
 	config &= ~0x7;
 	config |= op_mode;
 
@@ -1043,9 +1007,9 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	mv_chan_unmask_interrupts(mv_chan);
 
 	if (mv_chan->op_in_desc == XOR_MODE_IN_DESC)
-		mv_chan_set_mode_to_desc(mv_chan);
+		mv_chan_set_mode(mv_chan, XOR_OPERATION_MODE_IN_DESC);
 	else
-		mv_chan_set_mode(mv_chan, DMA_XOR);
+		mv_chan_set_mode(mv_chan, XOR_OPERATION_MODE_XOR);
 
 	spin_lock_init(&mv_chan->lock);
 	INIT_LIST_HEAD(&mv_chan->chain);
@@ -1121,6 +1085,57 @@ mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 	writel(0, base + WINDOW_OVERRIDE_CTRL(1));
 }
 
+/*
+ * Since this XOR driver is basically used only for RAID5, we don't
+ * need to care about synchronizing ->suspend with DMA activity,
+ * because the DMA engine will naturally be quiet due to the block
+ * devices being suspended.
+ */
+static int mv_xor_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct mv_xor_device *xordev = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		struct mv_xor_chan *mv_chan = xordev->channels[i];
+
+		if (!mv_chan)
+			continue;
+
+		mv_chan->saved_config_reg =
+			readl_relaxed(XOR_CONFIG(mv_chan));
+		mv_chan->saved_int_mask_reg =
+			readl_relaxed(XOR_INTR_MASK(mv_chan));
+	}
+
+	return 0;
+}
+
+static int mv_xor_resume(struct platform_device *dev)
+{
+	struct mv_xor_device *xordev = platform_get_drvdata(dev);
+	const struct mbus_dram_target_info *dram;
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		struct mv_xor_chan *mv_chan = xordev->channels[i];
+
+		if (!mv_chan)
+			continue;
+
+		writel_relaxed(mv_chan->saved_config_reg,
+			       XOR_CONFIG(mv_chan));
+		writel_relaxed(mv_chan->saved_int_mask_reg,
+			       XOR_INTR_MASK(mv_chan));
+	}
+
+	dram = mv_mbus_dram_info();
+	if (dram)
+		mv_xor_conf_mbus_windows(xordev, dram);
+
+	return 0;
+}
+
 static const struct of_device_id mv_xor_dt_ids[] = {
 	{ .compatible = "marvell,orion-xor", .data = (void *)XOR_MODE_IN_REG },
 	{ .compatible = "marvell,armada-380-xor", .data = (void *)XOR_MODE_IN_DESC },
@@ -1282,6 +1297,8 @@ err_channel_add:
 
 static struct platform_driver mv_xor_driver = {
 	.probe		= mv_xor_probe,
+	.suspend        = mv_xor_suspend,
+	.resume         = mv_xor_resume,
 	.driver		= {
 		.name	        = MV_XOR_NAME,
 		.of_match_table = of_match_ptr(mv_xor_dt_ids),
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index b7455b421..c19fe30e5 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -110,7 +110,6 @@ struct mv_xor_chan {
 	void __iomem		*mmr_high_base;
 	unsigned int		idx;
 	int                     irq;
-	enum dma_transaction_type	current_type;
 	struct list_head	chain;
 	struct list_head	free_slots;
 	struct list_head	allocated_slots;
@@ -126,6 +125,7 @@ struct mv_xor_chan {
 	char			dummy_src[MV_XOR_MIN_BYTE_COUNT];
 	char			dummy_dst[MV_XOR_MIN_BYTE_COUNT];
 	dma_addr_t		dummy_src_addr, dummy_dst_addr;
+	u32                     saved_config_reg, saved_int_mask_reg;
 };
 
 /**
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 1dfc71c90..9794b073d 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -28,8 +28,6 @@
 struct omap_dmadev {
 	struct dma_device ddev;
 	spinlock_t lock;
-	struct tasklet_struct task;
-	struct list_head pending;
 	void __iomem *base;
 	const struct omap_dma_reg *reg_map;
 	struct omap_system_dma_plat_info *plat;
@@ -42,7 +40,6 @@ struct omap_dmadev {
 
 struct omap_chan {
 	struct virt_dma_chan vc;
-	struct list_head node;
 	void __iomem *channel_base;
 	const struct omap_dma_reg *reg_map;
 	uint32_t ccr;
@@ -454,33 +451,6 @@ static void omap_dma_callback(int ch, u16 status, void *data)
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 }
 
-/*
- * This callback schedules all pending channels.  We could be more
- * clever here by postponing allocation of the real DMA channels to
- * this point, and freeing them when our virtual channel becomes idle.
- *
- * We would then need to deal with 'all channels in-use'
- */
-static void omap_dma_sched(unsigned long data)
-{
-	struct omap_dmadev *d = (struct omap_dmadev *)data;
-	LIST_HEAD(head);
-
-	spin_lock_irq(&d->lock);
-	list_splice_tail_init(&d->pending, &head);
-	spin_unlock_irq(&d->lock);
-
-	while (!list_empty(&head)) {
-		struct omap_chan *c = list_first_entry(&head,
-			struct omap_chan, node);
-
-		spin_lock_irq(&c->vc.lock);
-		list_del_init(&c->node);
-		omap_dma_start_desc(c);
-		spin_unlock_irq(&c->vc.lock);
-	}
-}
-
 static irqreturn_t omap_dma_irq(int irq, void *devid)
 {
 	struct omap_dmadev *od = devid;
@@ -703,8 +673,14 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	struct omap_chan *c = to_omap_dma_chan(chan);
 	struct virt_dma_desc *vd;
 	enum dma_status ret;
+	uint32_t ccr;
 	unsigned long flags;
 
+	ccr = omap_dma_chan_read(c, CCR);
+	/* The channel is no longer active, handle the completion right away */
+	if (!(ccr & CCR_ENABLE))
+		omap_dma_callback(c->dma_ch, 0, c);
+
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
@@ -719,7 +695,7 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 
 		if (d->dir == DMA_MEM_TO_DEV)
 			pos = omap_dma_get_src_pos(c);
-		else if (d->dir == DMA_DEV_TO_MEM)
+		else if (d->dir == DMA_DEV_TO_MEM  || d->dir == DMA_MEM_TO_MEM)
 			pos = omap_dma_get_dst_pos(c);
 		else
 			pos = 0;
@@ -739,22 +715,8 @@ static void omap_dma_issue_pending(struct dma_chan *chan)
 	unsigned long flags;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	if (vchan_issue_pending(&c->vc) && !c->desc) {
-		/*
-		 * c->cyclic is used only by audio and in this case the DMA need
-		 * to be started without delay.
-		 */
-		if (!c->cyclic) {
-			struct omap_dmadev *d = to_omap_dma_dev(chan->device);
-			spin_lock(&d->lock);
-			if (list_empty(&c->node))
-				list_add_tail(&c->node, &d->pending);
-			spin_unlock(&d->lock);
-			tasklet_schedule(&d->task);
-		} else {
-			omap_dma_start_desc(c);
-		}
-	}
+	if (vchan_issue_pending(&c->vc) && !c->desc)
+		omap_dma_start_desc(c);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 }
 
@@ -768,7 +730,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	struct scatterlist *sgent;
 	struct omap_desc *d;
 	dma_addr_t dev_addr;
-	unsigned i, j = 0, es, en, frame_bytes;
+	unsigned i, es, en, frame_bytes;
 	u32 burst;
 
 	if (dir == DMA_DEV_TO_MEM) {
@@ -845,13 +807,12 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	en = burst;
 	frame_bytes = es_bytes[es] * en;
 	for_each_sg(sgl, sgent, sglen, i) {
-		d->sg[j].addr = sg_dma_address(sgent);
-		d->sg[j].en = en;
-		d->sg[j].fn = sg_dma_len(sgent) / frame_bytes;
-		j++;
+		d->sg[i].addr = sg_dma_address(sgent);
+		d->sg[i].en = en;
+		d->sg[i].fn = sg_dma_len(sgent) / frame_bytes;
 	}
 
-	d->sglen = j;
+	d->sglen = sglen;
 
 	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
 }
@@ -1018,17 +979,11 @@ static int omap_dma_slave_config(struct dma_chan *chan, struct dma_slave_config
 static int omap_dma_terminate_all(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
-	struct omap_dmadev *d = to_omap_dma_dev(c->vc.chan.device);
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 
-	/* Prevent this channel being scheduled */
-	spin_lock(&d->lock);
-	list_del_init(&c->node);
-	spin_unlock(&d->lock);
-
 	/*
 	 * Stop DMA activity: we assume the callback will not be called
 	 * after omap_dma_stop() returns (even if it does, it will see
@@ -1102,14 +1057,12 @@ static int omap_dma_chan_init(struct omap_dmadev *od)
 	c->reg_map = od->reg_map;
 	c->vc.desc_free = omap_dma_desc_free;
 	vchan_init(&c->vc, &od->ddev);
-	INIT_LIST_HEAD(&c->node);
 
 	return 0;
 }
 
 static void omap_dma_free(struct omap_dmadev *od)
 {
-	tasklet_kill(&od->task);
 	while (!list_empty(&od->ddev.channels)) {
 		struct omap_chan *c = list_first_entry(&od->ddev.channels,
 			struct omap_chan, vc.chan.device_node);
@@ -1165,12 +1118,9 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
-	INIT_LIST_HEAD(&od->pending);
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
-	tasklet_init(&od->task, omap_dma_sched, (unsigned long)od);
-
 	od->dma_requests = OMAP_SDMA_REQUESTS;
 	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
 						      "dma-requests",
@@ -1203,6 +1153,10 @@ static int omap_dma_probe(struct platform_device *pdev)
 			return rc;
 	}
 
+	od->ddev.filter.map = od->plat->slave_map;
+	od->ddev.filter.mapcnt = od->plat->slavecnt;
+	od->ddev.filter.fn = omap_dma_filter_fn;
+
 	rc = dma_async_device_register(&od->ddev);
 	if (rc) {
 		pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n",
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index a59061e42..debca824b 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -1420,6 +1420,7 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.dst_addr_widths = widths;
 	pdev->slave.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
 	pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	pdev->slave.descriptor_reuse = true;
 
 	pdev->slave.dev = &op->dev;
 	ret = pxad_init_dmadev(op, pdev, dma_channels);
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index 9fda65af8..f32c430eb 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -47,12 +47,6 @@ config RCAR_DMAC
 	  This driver supports the general purpose DMA controller found in the
 	  Renesas R-Car second generation SoCs.
 
-config RCAR_HPB_DMAE
-	tristate "Renesas R-Car HPB DMAC support"
-	depends on SH_DMAE_BASE
-	help
-	  Enable support for the Renesas R-Car series DMA controllers.
-
 config RENESAS_USB_DMAC
 	tristate "Renesas USB-DMA Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index 0133e4658..f1e2fd64f 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -14,6 +14,5 @@ shdma-objs := $(shdma-y)
 obj-$(CONFIG_SH_DMAE) += shdma.o
 
 obj-$(CONFIG_RCAR_DMAC) += rcar-dmac.o
-obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
 obj-$(CONFIG_RENESAS_USB_DMAC) += usb-dmac.o
 obj-$(CONFIG_SUDMAC) += sudmac.o
diff --git a/drivers/dma/sh/rcar-hpbdma.c b/drivers/dma/sh/rcar-hpbdma.c
deleted file mode 100644
index 749f26ecd..000000000
--- a/drivers/dma/sh/rcar-hpbdma.c
+++ /dev/null
@@ -1,669 +0,0 @@
-/*
- * Copyright (C) 2011-2013 Renesas Electronics Corporation
- * Copyright (C) 2013 Cogent Embedded, Inc.
- *
- * This file is based on the drivers/dma/sh/shdma.c
- *
- * Renesas SuperH DMA Engine support
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * - DMA of SuperH does not have Hardware DMA chain mode.
- * - max DMA size is 16MB.
- *
- */
-
-#include <linux/dmaengine.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/platform_data/dma-rcar-hpbdma.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include <linux/shdma-base.h>
-#include <linux/slab.h>
-
-/* DMA channel registers */
-#define HPB_DMAE_DSAR0	0x00
-#define HPB_DMAE_DDAR0	0x04
-#define HPB_DMAE_DTCR0	0x08
-#define HPB_DMAE_DSAR1	0x0C
-#define HPB_DMAE_DDAR1	0x10
-#define HPB_DMAE_DTCR1	0x14
-#define HPB_DMAE_DSASR	0x18
-#define HPB_DMAE_DDASR	0x1C
-#define HPB_DMAE_DTCSR	0x20
-#define HPB_DMAE_DPTR	0x24
-#define HPB_DMAE_DCR	0x28
-#define HPB_DMAE_DCMDR	0x2C
-#define HPB_DMAE_DSTPR	0x30
-#define HPB_DMAE_DSTSR	0x34
-#define HPB_DMAE_DDBGR	0x38
-#define HPB_DMAE_DDBGR2	0x3C
-#define HPB_DMAE_CHAN(n)	(0x40 * (n))
-
-/* DMA command register (DCMDR) bits */
-#define HPB_DMAE_DCMDR_BDOUT	BIT(7)
-#define HPB_DMAE_DCMDR_DQSPD	BIT(6)
-#define HPB_DMAE_DCMDR_DQSPC	BIT(5)
-#define HPB_DMAE_DCMDR_DMSPD	BIT(4)
-#define HPB_DMAE_DCMDR_DMSPC	BIT(3)
-#define HPB_DMAE_DCMDR_DQEND	BIT(2)
-#define HPB_DMAE_DCMDR_DNXT	BIT(1)
-#define HPB_DMAE_DCMDR_DMEN	BIT(0)
-
-/* DMA forced stop register (DSTPR) bits */
-#define HPB_DMAE_DSTPR_DMSTP	BIT(0)
-
-/* DMA status register (DSTSR) bits */
-#define HPB_DMAE_DSTSR_DQSTS	BIT(2)
-#define HPB_DMAE_DSTSR_DMSTS	BIT(0)
-
-/* DMA common registers */
-#define HPB_DMAE_DTIMR		0x00
-#define HPB_DMAE_DINTSR0		0x0C
-#define HPB_DMAE_DINTSR1		0x10
-#define HPB_DMAE_DINTCR0		0x14
-#define HPB_DMAE_DINTCR1		0x18
-#define HPB_DMAE_DINTMR0		0x1C
-#define HPB_DMAE_DINTMR1		0x20
-#define HPB_DMAE_DACTSR0		0x24
-#define HPB_DMAE_DACTSR1		0x28
-#define HPB_DMAE_HSRSTR(n)	(0x40 + (n) * 4)
-#define HPB_DMAE_HPB_DMASPR(n)	(0x140 + (n) * 4)
-#define HPB_DMAE_HPB_DMLVLR0	0x160
-#define HPB_DMAE_HPB_DMLVLR1	0x164
-#define HPB_DMAE_HPB_DMSHPT0	0x168
-#define HPB_DMAE_HPB_DMSHPT1	0x16C
-
-#define HPB_DMA_SLAVE_NUMBER 256
-#define HPB_DMA_TCR_MAX 0x01000000	/* 16 MiB */
-
-struct hpb_dmae_chan {
-	struct shdma_chan shdma_chan;
-	int xfer_mode;			/* DMA transfer mode */
-#define XFER_SINGLE	1
-#define XFER_DOUBLE	2
-	unsigned plane_idx;		/* current DMA information set */
-	bool first_desc;		/* first/next transfer */
-	int xmit_shift;			/* log_2(bytes_per_xfer) */
-	void __iomem *base;
-	const struct hpb_dmae_slave_config *cfg;
-	char dev_id[16];		/* unique name per DMAC of channel */
-	dma_addr_t slave_addr;
-};
-
-struct hpb_dmae_device {
-	struct shdma_dev shdma_dev;
-	spinlock_t reg_lock;		/* comm_reg operation lock */
-	struct hpb_dmae_pdata *pdata;
-	void __iomem *chan_reg;
-	void __iomem *comm_reg;
-	void __iomem *reset_reg;
-	void __iomem *mode_reg;
-};
-
-struct hpb_dmae_regs {
-	u32 sar; /* SAR / source address */
-	u32 dar; /* DAR / destination address */
-	u32 tcr; /* TCR / transfer count */
-};
-
-struct hpb_desc {
-	struct shdma_desc shdma_desc;
-	struct hpb_dmae_regs hw;
-	unsigned plane_idx;
-};
-
-#define to_chan(schan) container_of(schan, struct hpb_dmae_chan, shdma_chan)
-#define to_desc(sdesc) container_of(sdesc, struct hpb_desc, shdma_desc)
-#define to_dev(sc) container_of(sc->shdma_chan.dma_chan.device, \
-				struct hpb_dmae_device, shdma_dev.dma_dev)
-
-static void ch_reg_write(struct hpb_dmae_chan *hpb_dc, u32 data, u32 reg)
-{
-	iowrite32(data, hpb_dc->base + reg);
-}
-
-static u32 ch_reg_read(struct hpb_dmae_chan *hpb_dc, u32 reg)
-{
-	return ioread32(hpb_dc->base + reg);
-}
-
-static void dcmdr_write(struct hpb_dmae_device *hpbdev, u32 data)
-{
-	iowrite32(data, hpbdev->chan_reg + HPB_DMAE_DCMDR);
-}
-
-static void hsrstr_write(struct hpb_dmae_device *hpbdev, u32 ch)
-{
-	iowrite32(0x1, hpbdev->comm_reg + HPB_DMAE_HSRSTR(ch));
-}
-
-static u32 dintsr_read(struct hpb_dmae_device *hpbdev, u32 ch)
-{
-	u32 v;
-
-	if (ch < 32)
-		v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR0) >> ch;
-	else
-		v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR1) >> (ch - 32);
-	return v & 0x1;
-}
-
-static void dintcr_write(struct hpb_dmae_device *hpbdev, u32 ch)
-{
-	if (ch < 32)
-		iowrite32((0x1 << ch), hpbdev->comm_reg + HPB_DMAE_DINTCR0);
-	else
-		iowrite32((0x1 << (ch - 32)),
-			  hpbdev->comm_reg + HPB_DMAE_DINTCR1);
-}
-
-static void asyncmdr_write(struct hpb_dmae_device *hpbdev, u32 data)
-{
-	iowrite32(data, hpbdev->mode_reg);
-}
-
-static u32 asyncmdr_read(struct hpb_dmae_device *hpbdev)
-{
-	return ioread32(hpbdev->mode_reg);
-}
-
-static void hpb_dmae_enable_int(struct hpb_dmae_device *hpbdev, u32 ch)
-{
-	u32 intreg;
-
-	spin_lock_irq(&hpbdev->reg_lock);
-	if (ch < 32) {
-		intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR0);
-		iowrite32(BIT(ch) | intreg,
-			  hpbdev->comm_reg + HPB_DMAE_DINTMR0);
-	} else {
-		intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR1);
-		iowrite32(BIT(ch - 32) | intreg,
-			  hpbdev->comm_reg + HPB_DMAE_DINTMR1);
-	}
-	spin_unlock_irq(&hpbdev->reg_lock);
-}
-
-static void hpb_dmae_async_reset(struct hpb_dmae_device *hpbdev, u32 data)
-{
-	u32 rstr;
-	int timeout = 10000;	/* 100 ms */
-
-	spin_lock(&hpbdev->reg_lock);
-	rstr = ioread32(hpbdev->reset_reg);
-	rstr |= data;
-	iowrite32(rstr, hpbdev->reset_reg);
-	do {
-		rstr = ioread32(hpbdev->reset_reg);
-		if ((rstr & data) == data)
-			break;
-		udelay(10);
-	} while (timeout--);
-
-	if (timeout < 0)
-		dev_err(hpbdev->shdma_dev.dma_dev.dev,
-			"%s timeout\n", __func__);
-
-	rstr &= ~data;
-	iowrite32(rstr, hpbdev->reset_reg);
-	spin_unlock(&hpbdev->reg_lock);
-}
-
-static void hpb_dmae_set_async_mode(struct hpb_dmae_device *hpbdev,
-				    u32 mask, u32 data)
-{
-	u32 mode;
-
-	spin_lock_irq(&hpbdev->reg_lock);
-	mode = asyncmdr_read(hpbdev);
-	mode &= ~mask;
-	mode |= data;
-	asyncmdr_write(hpbdev, mode);
-	spin_unlock_irq(&hpbdev->reg_lock);
-}
-
-static void hpb_dmae_ctl_stop(struct hpb_dmae_device *hpbdev)
-{
-	dcmdr_write(hpbdev, HPB_DMAE_DCMDR_DQSPD);
-}
-
-static void hpb_dmae_reset(struct hpb_dmae_device *hpbdev)
-{
-	u32 ch;
-
-	for (ch = 0; ch < hpbdev->pdata->num_hw_channels; ch++)
-		hsrstr_write(hpbdev, ch);
-}
-
-static unsigned int calc_xmit_shift(struct hpb_dmae_chan *hpb_chan)
-{
-	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
-	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
-	int width = ch_reg_read(hpb_chan, HPB_DMAE_DCR);
-	int i;
-
-	switch (width & (HPB_DMAE_DCR_SPDS_MASK | HPB_DMAE_DCR_DPDS_MASK)) {
-	case HPB_DMAE_DCR_SPDS_8BIT | HPB_DMAE_DCR_DPDS_8BIT:
-	default:
-		i = XMIT_SZ_8BIT;
-		break;
-	case HPB_DMAE_DCR_SPDS_16BIT | HPB_DMAE_DCR_DPDS_16BIT:
-		i = XMIT_SZ_16BIT;
-		break;
-	case HPB_DMAE_DCR_SPDS_32BIT | HPB_DMAE_DCR_DPDS_32BIT:
-		i = XMIT_SZ_32BIT;
-		break;
-	}
-	return pdata->ts_shift[i];
-}
-
-static void hpb_dmae_set_reg(struct hpb_dmae_chan *hpb_chan,
-			     struct hpb_dmae_regs *hw, unsigned plane)
-{
-	ch_reg_write(hpb_chan, hw->sar,
-		     plane ? HPB_DMAE_DSAR1 : HPB_DMAE_DSAR0);
-	ch_reg_write(hpb_chan, hw->dar,
-		     plane ? HPB_DMAE_DDAR1 : HPB_DMAE_DDAR0);
-	ch_reg_write(hpb_chan, hw->tcr >> hpb_chan->xmit_shift,
-		     plane ? HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0);
-}
-
-static void hpb_dmae_start(struct hpb_dmae_chan *hpb_chan, bool next)
-{
-	ch_reg_write(hpb_chan, (next ? HPB_DMAE_DCMDR_DNXT : 0) |
-		     HPB_DMAE_DCMDR_DMEN, HPB_DMAE_DCMDR);
-}
-
-static void hpb_dmae_halt(struct shdma_chan *schan)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-
-	ch_reg_write(chan, HPB_DMAE_DCMDR_DQEND, HPB_DMAE_DCMDR);
-	ch_reg_write(chan, HPB_DMAE_DSTPR_DMSTP, HPB_DMAE_DSTPR);
-
-	chan->plane_idx = 0;
-	chan->first_desc = true;
-}
-
-static const struct hpb_dmae_slave_config *
-hpb_dmae_find_slave(struct hpb_dmae_chan *hpb_chan, int slave_id)
-{
-	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
-	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
-	int i;
-
-	if (slave_id >= HPB_DMA_SLAVE_NUMBER)
-		return NULL;
-
-	for (i = 0; i < pdata->num_slaves; i++)
-		if (pdata->slaves[i].id == slave_id)
-			return pdata->slaves + i;
-
-	return NULL;
-}
-
-static void hpb_dmae_start_xfer(struct shdma_chan *schan,
-				struct shdma_desc *sdesc)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-	struct hpb_dmae_device *hpbdev = to_dev(chan);
-	struct hpb_desc *desc = to_desc(sdesc);
-
-	if (chan->cfg->flags & HPB_DMAE_SET_ASYNC_RESET)
-		hpb_dmae_async_reset(hpbdev, chan->cfg->rstr);
-
-	desc->plane_idx = chan->plane_idx;
-	hpb_dmae_set_reg(chan, &desc->hw, chan->plane_idx);
-	hpb_dmae_start(chan, !chan->first_desc);
-
-	if (chan->xfer_mode == XFER_DOUBLE) {
-		chan->plane_idx ^= 1;
-		chan->first_desc = false;
-	}
-}
-
-static bool hpb_dmae_desc_completed(struct shdma_chan *schan,
-				    struct shdma_desc *sdesc)
-{
-	/*
-	 * This is correct since we always have at most single
-	 * outstanding DMA transfer per channel, and by the time
-	 * we get completion interrupt the transfer is completed.
-	 * This will change if we ever use alternating DMA
-	 * information sets and submit two descriptors at once.
-	 */
-	return true;
-}
-
-static bool hpb_dmae_chan_irq(struct shdma_chan *schan, int irq)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-	struct hpb_dmae_device *hpbdev = to_dev(chan);
-	int ch = chan->cfg->dma_ch;
-
-	/* Check Complete DMA Transfer */
-	if (dintsr_read(hpbdev, ch)) {
-		/* Clear Interrupt status */
-		dintcr_write(hpbdev, ch);
-		return true;
-	}
-	return false;
-}
-
-static int hpb_dmae_desc_setup(struct shdma_chan *schan,
-			       struct shdma_desc *sdesc,
-			       dma_addr_t src, dma_addr_t dst, size_t *len)
-{
-	struct hpb_desc *desc = to_desc(sdesc);
-
-	if (*len > (size_t)HPB_DMA_TCR_MAX)
-		*len = (size_t)HPB_DMA_TCR_MAX;
-
-	desc->hw.sar = src;
-	desc->hw.dar = dst;
-	desc->hw.tcr = *len;
-
-	return 0;
-}
-
-static size_t hpb_dmae_get_partial(struct shdma_chan *schan,
-				   struct shdma_desc *sdesc)
-{
-	struct hpb_desc *desc = to_desc(sdesc);
-	struct hpb_dmae_chan *chan = to_chan(schan);
-	u32 tcr = ch_reg_read(chan, desc->plane_idx ?
-			      HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0);
-
-	return (desc->hw.tcr - tcr) << chan->xmit_shift;
-}
-
-static bool hpb_dmae_channel_busy(struct shdma_chan *schan)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-	u32 dstsr = ch_reg_read(chan, HPB_DMAE_DSTSR);
-
-	if (chan->xfer_mode == XFER_DOUBLE)
-		return dstsr & HPB_DMAE_DSTSR_DQSTS;
-	else
-		return dstsr & HPB_DMAE_DSTSR_DMSTS;
-}
-
-static int
-hpb_dmae_alloc_chan_resources(struct hpb_dmae_chan *hpb_chan,
-			      const struct hpb_dmae_slave_config *cfg)
-{
-	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
-	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
-	const struct hpb_dmae_channel *channel = pdata->channels;
-	int slave_id = cfg->id;
-	int i, err;
-
-	for (i = 0; i < pdata->num_channels; i++, channel++) {
-		if (channel->s_id == slave_id) {
-			struct device *dev = hpb_chan->shdma_chan.dev;
-
-			hpb_chan->base = hpbdev->chan_reg +
-				HPB_DMAE_CHAN(cfg->dma_ch);
-
-			dev_dbg(dev, "Detected Slave device\n");
-			dev_dbg(dev, " -- slave_id       : 0x%x\n", slave_id);
-			dev_dbg(dev, " -- cfg->dma_ch    : %d\n", cfg->dma_ch);
-			dev_dbg(dev, " -- channel->ch_irq: %d\n",
-				channel->ch_irq);
-			break;
-		}
-	}
-
-	err = shdma_request_irq(&hpb_chan->shdma_chan, channel->ch_irq,
-				IRQF_SHARED, hpb_chan->dev_id);
-	if (err) {
-		dev_err(hpb_chan->shdma_chan.dev,
-			"DMA channel request_irq %d failed with error %d\n",
-			channel->ch_irq, err);
-		return err;
-	}
-
-	hpb_chan->plane_idx = 0;
-	hpb_chan->first_desc = true;
-
-	if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) == 0) {
-		hpb_chan->xfer_mode = XFER_SINGLE;
-	} else if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) ==
-		   (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) {
-		hpb_chan->xfer_mode = XFER_DOUBLE;
-	} else {
-		dev_err(hpb_chan->shdma_chan.dev, "DCR setting error");
-		return -EINVAL;
-	}
-
-	if (cfg->flags & HPB_DMAE_SET_ASYNC_MODE)
-		hpb_dmae_set_async_mode(hpbdev, cfg->mdm, cfg->mdr);
-	ch_reg_write(hpb_chan, cfg->dcr, HPB_DMAE_DCR);
-	ch_reg_write(hpb_chan, cfg->port, HPB_DMAE_DPTR);
-	hpb_chan->xmit_shift = calc_xmit_shift(hpb_chan);
-	hpb_dmae_enable_int(hpbdev, cfg->dma_ch);
-
-	return 0;
-}
-
-static int hpb_dmae_set_slave(struct shdma_chan *schan, int slave_id,
-			      dma_addr_t slave_addr, bool try)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-	const struct hpb_dmae_slave_config *sc =
-		hpb_dmae_find_slave(chan, slave_id);
-
-	if (!sc)
-		return -ENODEV;
-	if (try)
-		return 0;
-	chan->cfg = sc;
-	chan->slave_addr = slave_addr ? : sc->addr;
-	return hpb_dmae_alloc_chan_resources(chan, sc);
-}
-
-static void hpb_dmae_setup_xfer(struct shdma_chan *schan, int slave_id)
-{
-}
-
-static dma_addr_t hpb_dmae_slave_addr(struct shdma_chan *schan)
-{
-	struct hpb_dmae_chan *chan = to_chan(schan);
-
-	return chan->slave_addr;
-}
-
-static struct shdma_desc *hpb_dmae_embedded_desc(void *buf, int i)
-{
-	return &((struct hpb_desc *)buf)[i].shdma_desc;
-}
-
-static const struct shdma_ops hpb_dmae_ops = {
-	.desc_completed = hpb_dmae_desc_completed,
-	.halt_channel = hpb_dmae_halt,
-	.channel_busy = hpb_dmae_channel_busy,
-	.slave_addr = hpb_dmae_slave_addr,
-	.desc_setup = hpb_dmae_desc_setup,
-	.set_slave = hpb_dmae_set_slave,
-	.setup_xfer = hpb_dmae_setup_xfer,
-	.start_xfer = hpb_dmae_start_xfer,
-	.embedded_desc = hpb_dmae_embedded_desc,
-	.chan_irq = hpb_dmae_chan_irq,
-	.get_partial = hpb_dmae_get_partial,
-};
-
-static int hpb_dmae_chan_probe(struct hpb_dmae_device *hpbdev, int id)
-{
-	struct shdma_dev *sdev = &hpbdev->shdma_dev;
-	struct platform_device *pdev =
-		to_platform_device(hpbdev->shdma_dev.dma_dev.dev);
-	struct hpb_dmae_chan *new_hpb_chan;
-	struct shdma_chan *schan;
-
-	/* Alloc channel */
-	new_hpb_chan = devm_kzalloc(&pdev->dev,
-				    sizeof(struct hpb_dmae_chan), GFP_KERNEL);
-	if (!new_hpb_chan) {
-		dev_err(hpbdev->shdma_dev.dma_dev.dev,
-			"No free memory for allocating DMA channels!\n");
-		return -ENOMEM;
-	}
-
-	schan = &new_hpb_chan->shdma_chan;
-	schan->max_xfer_len = HPB_DMA_TCR_MAX;
-
-	shdma_chan_probe(sdev, schan, id);
-
-	if (pdev->id >= 0)
-		snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id),
-			 "hpb-dmae%d.%d", pdev->id, id);
-	else
-		snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id),
-			 "hpb-dma.%d", id);
-
-	return 0;
-}
-
-static int hpb_dmae_probe(struct platform_device *pdev)
-{
-	const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE |
-		DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES;
-	struct hpb_dmae_pdata *pdata = pdev->dev.platform_data;
-	struct hpb_dmae_device *hpbdev;
-	struct dma_device *dma_dev;
-	struct resource *chan, *comm, *rest, *mode, *irq_res;
-	int err, i;
-
-	/* Get platform data */
-	if (!pdata || !pdata->num_channels)
-		return -ENODEV;
-
-	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	comm = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	rest = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-	mode = platform_get_resource(pdev, IORESOURCE_MEM, 3);
-
-	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq_res)
-		return -ENODEV;
-
-	hpbdev = devm_kzalloc(&pdev->dev, sizeof(struct hpb_dmae_device),
-			      GFP_KERNEL);
-	if (!hpbdev) {
-		dev_err(&pdev->dev, "Not enough memory\n");
-		return -ENOMEM;
-	}
-
-	hpbdev->chan_reg = devm_ioremap_resource(&pdev->dev, chan);
-	if (IS_ERR(hpbdev->chan_reg))
-		return PTR_ERR(hpbdev->chan_reg);
-
-	hpbdev->comm_reg = devm_ioremap_resource(&pdev->dev, comm);
-	if (IS_ERR(hpbdev->comm_reg))
-		return PTR_ERR(hpbdev->comm_reg);
-
-	hpbdev->reset_reg = devm_ioremap_resource(&pdev->dev, rest);
-	if (IS_ERR(hpbdev->reset_reg))
-		return PTR_ERR(hpbdev->reset_reg);
-
-	hpbdev->mode_reg = devm_ioremap_resource(&pdev->dev, mode);
-	if (IS_ERR(hpbdev->mode_reg))
-		return PTR_ERR(hpbdev->mode_reg);
-
-	dma_dev = &hpbdev->shdma_dev.dma_dev;
-
-	spin_lock_init(&hpbdev->reg_lock);
-
-	/* Platform data */
-	hpbdev->pdata = pdata;
-
-	pm_runtime_enable(&pdev->dev);
-	err = pm_runtime_get_sync(&pdev->dev);
-	if (err < 0)
-		dev_err(&pdev->dev, "%s(): GET = %d\n", __func__, err);
-
-	/* Reset DMA controller */
-	hpb_dmae_reset(hpbdev);
-
-	pm_runtime_put(&pdev->dev);
-
-	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
-	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
-	dma_dev->src_addr_widths = widths;
-	dma_dev->dst_addr_widths = widths;
-	dma_dev->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
-	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
-
-	hpbdev->shdma_dev.ops = &hpb_dmae_ops;
-	hpbdev->shdma_dev.desc_size = sizeof(struct hpb_desc);
-	err = shdma_init(&pdev->dev, &hpbdev->shdma_dev, pdata->num_channels);
-	if (err < 0)
-		goto error;
-
-	/* Create DMA channels */
-	for (i = 0; i < pdata->num_channels; i++)
-		hpb_dmae_chan_probe(hpbdev, i);
-
-	platform_set_drvdata(pdev, hpbdev);
-	err = dma_async_device_register(dma_dev);
-	if (!err)
-		return 0;
-
-	shdma_cleanup(&hpbdev->shdma_dev);
-error:
-	pm_runtime_disable(&pdev->dev);
-	return err;
-}
-
-static void hpb_dmae_chan_remove(struct hpb_dmae_device *hpbdev)
-{
-	struct shdma_chan *schan;
-	int i;
-
-	shdma_for_each_chan(schan, &hpbdev->shdma_dev, i) {
-		BUG_ON(!schan);
-
-		shdma_chan_remove(schan);
-	}
-}
-
-static int hpb_dmae_remove(struct platform_device *pdev)
-{
-	struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev);
-
-	dma_async_device_unregister(&hpbdev->shdma_dev.dma_dev);
-
-	pm_runtime_disable(&pdev->dev);
-
-	hpb_dmae_chan_remove(hpbdev);
-
-	return 0;
-}
-
-static void hpb_dmae_shutdown(struct platform_device *pdev)
-{
-	struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev);
-	hpb_dmae_ctl_stop(hpbdev);
-}
-
-static struct platform_driver hpb_dmae_driver = {
-	.probe		= hpb_dmae_probe,
-	.remove		= hpb_dmae_remove,
-	.shutdown	= hpb_dmae_shutdown,
-	.driver = {
-		.name	= "hpb-dma-engine",
-	},
-};
-module_platform_driver(hpb_dmae_driver);
-
-MODULE_AUTHOR("Max Filippov <max.filippov@cogentembedded.com>");
-MODULE_DESCRIPTION("Renesas HPB DMA Engine driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index f1bcc2a16..749f1bd5d 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -448,7 +448,7 @@ usb_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 static int usb_dmac_chan_terminate_all(struct dma_chan *chan)
 {
 	struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan);
-	struct usb_dmac_desc *desc;
+	struct usb_dmac_desc *desc, *_desc;
 	unsigned long flags;
 	LIST_HEAD(head);
 	LIST_HEAD(list);
@@ -459,7 +459,7 @@ static int usb_dmac_chan_terminate_all(struct dma_chan *chan)
 	if (uchan->desc)
 		uchan->desc = NULL;
 	list_splice_init(&uchan->desc_got, &list);
-	list_for_each_entry(desc, &list, node)
+	list_for_each_entry_safe(desc, _desc, &list, node)
 		list_move_tail(&desc->node, &uchan->desc_freed);
 	spin_unlock_irqrestore(&uchan->vc.lock, flags);
 	vchan_dma_desc_free_list(&uchan->vc, &head);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index dd3e7ba27..6fb830746 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3543,8 +3543,8 @@ static int __init d40_probe(struct platform_device *pdev)
 	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	int ret = -ENOENT;
-	struct d40_base *base = NULL;
-	struct resource *res = NULL;
+	struct d40_base *base;
+	struct resource *res;
 	int num_reserved_chans;
 	u32 val;
 
@@ -3552,17 +3552,17 @@ static int __init d40_probe(struct platform_device *pdev)
 		if (np) {
 			if (d40_of_probe(pdev, np)) {
 				ret = -ENOMEM;
-				goto failure;
+				goto report_failure;
 			}
 		} else {
 			d40_err(&pdev->dev, "No pdata or Device Tree provided\n");
-			goto failure;
+			goto report_failure;
 		}
 	}
 
 	base = d40_hw_detect_init(pdev);
 	if (!base)
-		goto failure;
+		goto report_failure;
 
 	num_reserved_chans = d40_phy_res_init(base);
 
@@ -3693,51 +3693,48 @@ static int __init d40_probe(struct platform_device *pdev)
 	return 0;
 
 failure:
-	if (base) {
-		if (base->desc_slab)
-			kmem_cache_destroy(base->desc_slab);
-		if (base->virtbase)
-			iounmap(base->virtbase);
-
-		if (base->lcla_pool.base && base->plat_data->use_esram_lcla) {
-			iounmap(base->lcla_pool.base);
-			base->lcla_pool.base = NULL;
-		}
+	kmem_cache_destroy(base->desc_slab);
+	if (base->virtbase)
+		iounmap(base->virtbase);
 
-		if (base->lcla_pool.dma_addr)
-			dma_unmap_single(base->dev, base->lcla_pool.dma_addr,
-					 SZ_1K * base->num_phy_chans,
-					 DMA_TO_DEVICE);
-
-		if (!base->lcla_pool.base_unaligned && base->lcla_pool.base)
-			free_pages((unsigned long)base->lcla_pool.base,
-				   base->lcla_pool.pages);
-
-		kfree(base->lcla_pool.base_unaligned);
-
-		if (base->phy_lcpa)
-			release_mem_region(base->phy_lcpa,
-					   base->lcpa_size);
-		if (base->phy_start)
-			release_mem_region(base->phy_start,
-					   base->phy_size);
-		if (base->clk) {
-			clk_disable_unprepare(base->clk);
-			clk_put(base->clk);
-		}
+	if (base->lcla_pool.base && base->plat_data->use_esram_lcla) {
+		iounmap(base->lcla_pool.base);
+		base->lcla_pool.base = NULL;
+	}
 
-		if (base->lcpa_regulator) {
-			regulator_disable(base->lcpa_regulator);
-			regulator_put(base->lcpa_regulator);
-		}
+	if (base->lcla_pool.dma_addr)
+		dma_unmap_single(base->dev, base->lcla_pool.dma_addr,
+				 SZ_1K * base->num_phy_chans,
+				 DMA_TO_DEVICE);
 
-		kfree(base->lcla_pool.alloc_map);
-		kfree(base->lookup_log_chans);
-		kfree(base->lookup_phy_chans);
-		kfree(base->phy_res);
-		kfree(base);
+	if (!base->lcla_pool.base_unaligned && base->lcla_pool.base)
+		free_pages((unsigned long)base->lcla_pool.base,
+			   base->lcla_pool.pages);
+
+	kfree(base->lcla_pool.base_unaligned);
+
+	if (base->phy_lcpa)
+		release_mem_region(base->phy_lcpa,
+				   base->lcpa_size);
+	if (base->phy_start)
+		release_mem_region(base->phy_start,
+				   base->phy_size);
+	if (base->clk) {
+		clk_disable_unprepare(base->clk);
+		clk_put(base->clk);
+	}
+
+	if (base->lcpa_regulator) {
+		regulator_disable(base->lcpa_regulator);
+		regulator_put(base->lcpa_regulator);
 	}
 
+	kfree(base->lcla_pool.alloc_map);
+	kfree(base->lookup_log_chans);
+	kfree(base->lookup_phy_chans);
+	kfree(base->phy_res);
+	kfree(base);
+report_failure:
 	d40_err(&pdev->dev, "probe failed\n");
 	return ret;
 }
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
new file mode 100644
index 000000000..047476a13
--- /dev/null
+++ b/drivers/dma/stm32-dma.c
@@ -0,0 +1,1141 @@
+/*
+ * Driver for STM32 DMA controller
+ *
+ * Inspired by dma-jz4740.c and tegra20-apb-dma.c
+ *
+ * Copyright (C) M'boumba Cedric Madianga 2015
+ * Author: M'boumba Cedric Madianga <cedric.madianga@gmail.com>
+ *
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "virt-dma.h"
+
+#define STM32_DMA_LISR			0x0000 /* DMA Low Int Status Reg */
+#define STM32_DMA_HISR			0x0004 /* DMA High Int Status Reg */
+#define STM32_DMA_LIFCR			0x0008 /* DMA Low Int Flag Clear Reg */
+#define STM32_DMA_HIFCR			0x000c /* DMA High Int Flag Clear Reg */
+#define STM32_DMA_TCI			BIT(5) /* Transfer Complete Interrupt */
+#define STM32_DMA_TEI			BIT(3) /* Transfer Error Interrupt */
+#define STM32_DMA_DMEI			BIT(2) /* Direct Mode Error Interrupt */
+#define STM32_DMA_FEI			BIT(0) /* FIFO Error Interrupt */
+
+/* DMA Stream x Configuration Register */
+#define STM32_DMA_SCR(x)		(0x0010 + 0x18 * (x)) /* x = 0..7 */
+#define STM32_DMA_SCR_REQ(n)		((n & 0x7) << 25)
+#define STM32_DMA_SCR_MBURST_MASK	GENMASK(24, 23)
+#define STM32_DMA_SCR_MBURST(n)	        ((n & 0x3) << 23)
+#define STM32_DMA_SCR_PBURST_MASK	GENMASK(22, 21)
+#define STM32_DMA_SCR_PBURST(n)	        ((n & 0x3) << 21)
+#define STM32_DMA_SCR_PL_MASK		GENMASK(17, 16)
+#define STM32_DMA_SCR_PL(n)		((n & 0x3) << 16)
+#define STM32_DMA_SCR_MSIZE_MASK	GENMASK(14, 13)
+#define STM32_DMA_SCR_MSIZE(n)		((n & 0x3) << 13)
+#define STM32_DMA_SCR_PSIZE_MASK	GENMASK(12, 11)
+#define STM32_DMA_SCR_PSIZE(n)		((n & 0x3) << 11)
+#define STM32_DMA_SCR_PSIZE_GET(n)	((n & STM32_DMA_SCR_PSIZE_MASK) >> 11)
+#define STM32_DMA_SCR_DIR_MASK		GENMASK(7, 6)
+#define STM32_DMA_SCR_DIR(n)		((n & 0x3) << 6)
+#define STM32_DMA_SCR_CT		BIT(19) /* Target in double buffer */
+#define STM32_DMA_SCR_DBM		BIT(18) /* Double Buffer Mode */
+#define STM32_DMA_SCR_PINCOS		BIT(15) /* Peripheral inc offset size */
+#define STM32_DMA_SCR_MINC		BIT(10) /* Memory increment mode */
+#define STM32_DMA_SCR_PINC		BIT(9) /* Peripheral increment mode */
+#define STM32_DMA_SCR_CIRC		BIT(8) /* Circular mode */
+#define STM32_DMA_SCR_PFCTRL		BIT(5) /* Peripheral Flow Controller */
+#define STM32_DMA_SCR_TCIE		BIT(4) /* Transfer Cplete Int Enable*/
+#define STM32_DMA_SCR_TEIE		BIT(2) /* Transfer Error Int Enable */
+#define STM32_DMA_SCR_DMEIE		BIT(1) /* Direct Mode Err Int Enable */
+#define STM32_DMA_SCR_EN		BIT(0) /* Stream Enable */
+#define STM32_DMA_SCR_CFG_MASK		(STM32_DMA_SCR_PINC \
+					| STM32_DMA_SCR_MINC \
+					| STM32_DMA_SCR_PINCOS \
+					| STM32_DMA_SCR_PL_MASK)
+#define STM32_DMA_SCR_IRQ_MASK		(STM32_DMA_SCR_TCIE \
+					| STM32_DMA_SCR_TEIE \
+					| STM32_DMA_SCR_DMEIE)
+
+/* DMA Stream x number of data register */
+#define STM32_DMA_SNDTR(x)		(0x0014 + 0x18 * (x))
+
+/* DMA stream peripheral address register */
+#define STM32_DMA_SPAR(x)		(0x0018 + 0x18 * (x))
+
+/* DMA stream x memory 0 address register */
+#define STM32_DMA_SM0AR(x)		(0x001c + 0x18 * (x))
+
+/* DMA stream x memory 1 address register */
+#define STM32_DMA_SM1AR(x)		(0x0020 + 0x18 * (x))
+
+/* DMA stream x FIFO control register */
+#define STM32_DMA_SFCR(x)		(0x0024 + 0x18 * (x))
+#define STM32_DMA_SFCR_FTH_MASK		GENMASK(1, 0)
+#define STM32_DMA_SFCR_FTH(n)		(n & STM32_DMA_SFCR_FTH_MASK)
+#define STM32_DMA_SFCR_FEIE		BIT(7) /* FIFO error interrupt enable */
+#define STM32_DMA_SFCR_DMDIS		BIT(2) /* Direct mode disable */
+#define STM32_DMA_SFCR_MASK		(STM32_DMA_SFCR_FEIE \
+					| STM32_DMA_SFCR_DMDIS)
+
+/* DMA direction */
+#define STM32_DMA_DEV_TO_MEM		0x00
+#define	STM32_DMA_MEM_TO_DEV		0x01
+#define	STM32_DMA_MEM_TO_MEM		0x02
+
+/* DMA priority level */
+#define STM32_DMA_PRIORITY_LOW		0x00
+#define STM32_DMA_PRIORITY_MEDIUM	0x01
+#define STM32_DMA_PRIORITY_HIGH		0x02
+#define STM32_DMA_PRIORITY_VERY_HIGH	0x03
+
+/* DMA FIFO threshold selection */
+#define STM32_DMA_FIFO_THRESHOLD_1QUARTERFULL		0x00
+#define STM32_DMA_FIFO_THRESHOLD_HALFFULL		0x01
+#define STM32_DMA_FIFO_THRESHOLD_3QUARTERSFULL		0x02
+#define STM32_DMA_FIFO_THRESHOLD_FULL			0x03
+
+#define STM32_DMA_MAX_DATA_ITEMS	0xffff
+#define STM32_DMA_MAX_CHANNELS		0x08
+#define STM32_DMA_MAX_REQUEST_ID	0x08
+#define STM32_DMA_MAX_DATA_PARAM	0x03
+
+enum stm32_dma_width {
+	STM32_DMA_BYTE,
+	STM32_DMA_HALF_WORD,
+	STM32_DMA_WORD,
+};
+
+enum stm32_dma_burst_size {
+	STM32_DMA_BURST_SINGLE,
+	STM32_DMA_BURST_INCR4,
+	STM32_DMA_BURST_INCR8,
+	STM32_DMA_BURST_INCR16,
+};
+
+struct stm32_dma_cfg {
+	u32 channel_id;
+	u32 request_line;
+	u32 stream_config;
+	u32 threshold;
+};
+
+struct stm32_dma_chan_reg {
+	u32 dma_lisr;
+	u32 dma_hisr;
+	u32 dma_lifcr;
+	u32 dma_hifcr;
+	u32 dma_scr;
+	u32 dma_sndtr;
+	u32 dma_spar;
+	u32 dma_sm0ar;
+	u32 dma_sm1ar;
+	u32 dma_sfcr;
+};
+
+struct stm32_dma_sg_req {
+	u32 len;
+	struct stm32_dma_chan_reg chan_reg;
+};
+
+struct stm32_dma_desc {
+	struct virt_dma_desc vdesc;
+	bool cyclic;
+	u32 num_sgs;
+	struct stm32_dma_sg_req sg_req[];
+};
+
+struct stm32_dma_chan {
+	struct virt_dma_chan vchan;
+	bool config_init;
+	bool busy;
+	u32 id;
+	u32 irq;
+	struct stm32_dma_desc *desc;
+	u32 next_sg;
+	struct dma_slave_config	dma_sconfig;
+	struct stm32_dma_chan_reg chan_reg;
+};
+
+struct stm32_dma_device {
+	struct dma_device ddev;
+	void __iomem *base;
+	struct clk *clk;
+	struct reset_control *rst;
+	bool mem2mem;
+	struct stm32_dma_chan chan[STM32_DMA_MAX_CHANNELS];
+};
+
+static struct stm32_dma_device *stm32_dma_get_dev(struct stm32_dma_chan *chan)
+{
+	return container_of(chan->vchan.chan.device, struct stm32_dma_device,
+			    ddev);
+}
+
+static struct stm32_dma_chan *to_stm32_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct stm32_dma_chan, vchan.chan);
+}
+
+static struct stm32_dma_desc *to_stm32_dma_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct stm32_dma_desc, vdesc);
+}
+
+static struct device *chan2dev(struct stm32_dma_chan *chan)
+{
+	return &chan->vchan.chan.dev->device;
+}
+
+static u32 stm32_dma_read(struct stm32_dma_device *dmadev, u32 reg)
+{
+	return readl_relaxed(dmadev->base + reg);
+}
+
+static void stm32_dma_write(struct stm32_dma_device *dmadev, u32 reg, u32 val)
+{
+	writel_relaxed(val, dmadev->base + reg);
+}
+
+static struct stm32_dma_desc *stm32_dma_alloc_desc(u32 num_sgs)
+{
+	return kzalloc(sizeof(struct stm32_dma_desc) +
+		       sizeof(struct stm32_dma_sg_req) * num_sgs, GFP_NOWAIT);
+}
+
+static int stm32_dma_get_width(struct stm32_dma_chan *chan,
+			       enum dma_slave_buswidth width)
+{
+	switch (width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		return STM32_DMA_BYTE;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		return STM32_DMA_HALF_WORD;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		return STM32_DMA_WORD;
+	default:
+		dev_err(chan2dev(chan), "Dma bus width not supported\n");
+		return -EINVAL;
+	}
+}
+
+static int stm32_dma_get_burst(struct stm32_dma_chan *chan, u32 maxburst)
+{
+	switch (maxburst) {
+	case 0:
+	case 1:
+		return STM32_DMA_BURST_SINGLE;
+	case 4:
+		return STM32_DMA_BURST_INCR4;
+	case 8:
+		return STM32_DMA_BURST_INCR8;
+	case 16:
+		return STM32_DMA_BURST_INCR16;
+	default:
+		dev_err(chan2dev(chan), "Dma burst size not supported\n");
+		return -EINVAL;
+	}
+}
+
+static void stm32_dma_set_fifo_config(struct stm32_dma_chan *chan,
+				      u32 src_maxburst, u32 dst_maxburst)
+{
+	chan->chan_reg.dma_sfcr &= ~STM32_DMA_SFCR_MASK;
+	chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_DMEIE;
+
+	if ((!src_maxburst) && (!dst_maxburst)) {
+		/* Using direct mode */
+		chan->chan_reg.dma_scr |= STM32_DMA_SCR_DMEIE;
+	} else {
+		/* Using FIFO mode */
+		chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_MASK;
+	}
+}
+
+static int stm32_dma_slave_config(struct dma_chan *c,
+				  struct dma_slave_config *config)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+
+	memcpy(&chan->dma_sconfig, config, sizeof(*config));
+
+	chan->config_init = true;
+
+	return 0;
+}
+
+static u32 stm32_dma_irq_status(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 flags, dma_isr;
+
+	/*
+	 * Read "flags" from DMA_xISR register corresponding to the selected
+	 * DMA channel at the correct bit offset inside that register.
+	 *
+	 * If (ch % 4) is 2 or 3, left shift the mask by 16 bits.
+	 * If (ch % 4) is 1 or 3, additionally left shift the mask by 6 bits.
+	 */
+
+	if (chan->id & 4)
+		dma_isr = stm32_dma_read(dmadev, STM32_DMA_HISR);
+	else
+		dma_isr = stm32_dma_read(dmadev, STM32_DMA_LISR);
+
+	flags = dma_isr >> (((chan->id & 2) << 3) | ((chan->id & 1) * 6));
+
+	return flags;
+}
+
+static void stm32_dma_irq_clear(struct stm32_dma_chan *chan, u32 flags)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 dma_ifcr;
+
+	/*
+	 * Write "flags" to the DMA_xIFCR register corresponding to the selected
+	 * DMA channel at the correct bit offset inside that register.
+	 *
+	 * If (ch % 4) is 2 or 3, left shift the mask by 16 bits.
+	 * If (ch % 4) is 1 or 3, additionally left shift the mask by 6 bits.
+	 */
+	dma_ifcr = flags << (((chan->id & 2) << 3) | ((chan->id & 1) * 6));
+
+	if (chan->id & 4)
+		stm32_dma_write(dmadev, STM32_DMA_HIFCR, dma_ifcr);
+	else
+		stm32_dma_write(dmadev, STM32_DMA_LIFCR, dma_ifcr);
+}
+
+static int stm32_dma_disable_chan(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	unsigned long timeout = jiffies + msecs_to_jiffies(5000);
+	u32 dma_scr, id;
+
+	id = chan->id;
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+
+	if (dma_scr & STM32_DMA_SCR_EN) {
+		dma_scr &= ~STM32_DMA_SCR_EN;
+		stm32_dma_write(dmadev, STM32_DMA_SCR(id), dma_scr);
+
+		do {
+			dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+			dma_scr &= STM32_DMA_SCR_EN;
+			if (!dma_scr)
+				break;
+
+			if (time_after_eq(jiffies, timeout)) {
+				dev_err(chan2dev(chan), "%s: timeout!\n",
+					__func__);
+				return -EBUSY;
+			}
+			cond_resched();
+		} while (1);
+	}
+
+	return 0;
+}
+
+static void stm32_dma_stop(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 dma_scr, dma_sfcr, status;
+	int ret;
+
+	/* Disable interrupts */
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+	dma_scr &= ~STM32_DMA_SCR_IRQ_MASK;
+	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), dma_scr);
+	dma_sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
+	dma_sfcr &= ~STM32_DMA_SFCR_FEIE;
+	stm32_dma_write(dmadev, STM32_DMA_SFCR(chan->id), dma_sfcr);
+
+	/* Disable DMA */
+	ret = stm32_dma_disable_chan(chan);
+	if (ret < 0)
+		return;
+
+	/* Clear interrupt status if it is there */
+	status = stm32_dma_irq_status(chan);
+	if (status) {
+		dev_dbg(chan2dev(chan), "%s(): clearing interrupt: 0x%08x\n",
+			__func__, status);
+		stm32_dma_irq_clear(chan, status);
+	}
+
+	chan->busy = false;
+}
+
+static int stm32_dma_terminate_all(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+
+	if (chan->busy) {
+		stm32_dma_stop(chan);
+		chan->desc = NULL;
+	}
+
+	vchan_get_all_descriptors(&chan->vchan, &head);
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&chan->vchan, &head);
+
+	return 0;
+}
+
+static void stm32_dma_dump_reg(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+	u32 ndtr = stm32_dma_read(dmadev, STM32_DMA_SNDTR(chan->id));
+	u32 spar = stm32_dma_read(dmadev, STM32_DMA_SPAR(chan->id));
+	u32 sm0ar = stm32_dma_read(dmadev, STM32_DMA_SM0AR(chan->id));
+	u32 sm1ar = stm32_dma_read(dmadev, STM32_DMA_SM1AR(chan->id));
+	u32 sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
+
+	dev_dbg(chan2dev(chan), "SCR:   0x%08x\n", scr);
+	dev_dbg(chan2dev(chan), "NDTR:  0x%08x\n", ndtr);
+	dev_dbg(chan2dev(chan), "SPAR:  0x%08x\n", spar);
+	dev_dbg(chan2dev(chan), "SM0AR: 0x%08x\n", sm0ar);
+	dev_dbg(chan2dev(chan), "SM1AR: 0x%08x\n", sm1ar);
+	dev_dbg(chan2dev(chan), "SFCR:  0x%08x\n", sfcr);
+}
+
+static int stm32_dma_start_transfer(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	struct virt_dma_desc *vdesc;
+	struct stm32_dma_sg_req *sg_req;
+	struct stm32_dma_chan_reg *reg;
+	u32 status;
+	int ret;
+
+	ret = stm32_dma_disable_chan(chan);
+	if (ret < 0)
+		return ret;
+
+	if (!chan->desc) {
+		vdesc = vchan_next_desc(&chan->vchan);
+		if (!vdesc)
+			return -EPERM;
+
+		chan->desc = to_stm32_dma_desc(vdesc);
+		chan->next_sg = 0;
+	}
+
+	if (chan->next_sg == chan->desc->num_sgs)
+		chan->next_sg = 0;
+
+	sg_req = &chan->desc->sg_req[chan->next_sg];
+	reg = &sg_req->chan_reg;
+
+	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), reg->dma_scr);
+	stm32_dma_write(dmadev, STM32_DMA_SPAR(chan->id), reg->dma_spar);
+	stm32_dma_write(dmadev, STM32_DMA_SM0AR(chan->id), reg->dma_sm0ar);
+	stm32_dma_write(dmadev, STM32_DMA_SFCR(chan->id), reg->dma_sfcr);
+	stm32_dma_write(dmadev, STM32_DMA_SM1AR(chan->id), reg->dma_sm1ar);
+	stm32_dma_write(dmadev, STM32_DMA_SNDTR(chan->id), reg->dma_sndtr);
+
+	chan->next_sg++;
+
+	/* Clear interrupt status if it is there */
+	status = stm32_dma_irq_status(chan);
+	if (status)
+		stm32_dma_irq_clear(chan, status);
+
+	stm32_dma_dump_reg(chan);
+
+	/* Start DMA */
+	reg->dma_scr |= STM32_DMA_SCR_EN;
+	stm32_dma_write(dmadev, STM32_DMA_SCR(chan->id), reg->dma_scr);
+
+	chan->busy = true;
+
+	return 0;
+}
+
+static void stm32_dma_configure_next_sg(struct stm32_dma_chan *chan)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	struct stm32_dma_sg_req *sg_req;
+	u32 dma_scr, dma_sm0ar, dma_sm1ar, id;
+
+	id = chan->id;
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+
+	if (dma_scr & STM32_DMA_SCR_DBM) {
+		if (chan->next_sg == chan->desc->num_sgs)
+			chan->next_sg = 0;
+
+		sg_req = &chan->desc->sg_req[chan->next_sg];
+
+		if (dma_scr & STM32_DMA_SCR_CT) {
+			dma_sm0ar = sg_req->chan_reg.dma_sm0ar;
+			stm32_dma_write(dmadev, STM32_DMA_SM0AR(id), dma_sm0ar);
+			dev_dbg(chan2dev(chan), "CT=1 <=> SM0AR: 0x%08x\n",
+				stm32_dma_read(dmadev, STM32_DMA_SM0AR(id)));
+		} else {
+			dma_sm1ar = sg_req->chan_reg.dma_sm1ar;
+			stm32_dma_write(dmadev, STM32_DMA_SM1AR(id), dma_sm1ar);
+			dev_dbg(chan2dev(chan), "CT=0 <=> SM1AR: 0x%08x\n",
+				stm32_dma_read(dmadev, STM32_DMA_SM1AR(id)));
+		}
+
+		chan->next_sg++;
+	}
+}
+
+static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan)
+{
+	if (chan->desc) {
+		if (chan->desc->cyclic) {
+			vchan_cyclic_callback(&chan->desc->vdesc);
+			stm32_dma_configure_next_sg(chan);
+		} else {
+			chan->busy = false;
+			if (chan->next_sg == chan->desc->num_sgs) {
+				list_del(&chan->desc->vdesc.node);
+				vchan_cookie_complete(&chan->desc->vdesc);
+				chan->desc = NULL;
+			}
+			stm32_dma_start_transfer(chan);
+		}
+	}
+}
+
+static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
+{
+	struct stm32_dma_chan *chan = devid;
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 status, scr, sfcr;
+
+	spin_lock(&chan->vchan.lock);
+
+	status = stm32_dma_irq_status(chan);
+	scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+	sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
+
+	if ((status & STM32_DMA_TCI) && (scr & STM32_DMA_SCR_TCIE)) {
+		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
+		stm32_dma_handle_chan_done(chan);
+
+	} else {
+		stm32_dma_irq_clear(chan, status);
+		dev_err(chan2dev(chan), "DMA error: status=0x%08x\n", status);
+	}
+
+	spin_unlock(&chan->vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static void stm32_dma_issue_pending(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	if (!chan->busy) {
+		if (vchan_issue_pending(&chan->vchan) && !chan->desc) {
+			ret = stm32_dma_start_transfer(chan);
+			if ((!ret) && (chan->desc->cyclic))
+				stm32_dma_configure_next_sg(chan);
+		}
+	}
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+}
+
+static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
+				    enum dma_transfer_direction direction,
+				    enum dma_slave_buswidth *buswidth)
+{
+	enum dma_slave_buswidth src_addr_width, dst_addr_width;
+	int src_bus_width, dst_bus_width;
+	int src_burst_size, dst_burst_size;
+	u32 src_maxburst, dst_maxburst;
+	dma_addr_t src_addr, dst_addr;
+	u32 dma_scr = 0;
+
+	src_addr_width = chan->dma_sconfig.src_addr_width;
+	dst_addr_width = chan->dma_sconfig.dst_addr_width;
+	src_maxburst = chan->dma_sconfig.src_maxburst;
+	dst_maxburst = chan->dma_sconfig.dst_maxburst;
+	src_addr = chan->dma_sconfig.src_addr;
+	dst_addr = chan->dma_sconfig.dst_addr;
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		dst_bus_width = stm32_dma_get_width(chan, dst_addr_width);
+		if (dst_bus_width < 0)
+			return dst_bus_width;
+
+		dst_burst_size = stm32_dma_get_burst(chan, dst_maxburst);
+		if (dst_burst_size < 0)
+			return dst_burst_size;
+
+		if (!src_addr_width)
+			src_addr_width = dst_addr_width;
+
+		src_bus_width = stm32_dma_get_width(chan, src_addr_width);
+		if (src_bus_width < 0)
+			return src_bus_width;
+
+		src_burst_size = stm32_dma_get_burst(chan, src_maxburst);
+		if (src_burst_size < 0)
+			return src_burst_size;
+
+		dma_scr = STM32_DMA_SCR_DIR(STM32_DMA_MEM_TO_DEV) |
+			STM32_DMA_SCR_PSIZE(dst_bus_width) |
+			STM32_DMA_SCR_MSIZE(src_bus_width) |
+			STM32_DMA_SCR_PBURST(dst_burst_size) |
+			STM32_DMA_SCR_MBURST(src_burst_size);
+
+		chan->chan_reg.dma_spar = chan->dma_sconfig.dst_addr;
+		*buswidth = dst_addr_width;
+		break;
+
+	case DMA_DEV_TO_MEM:
+		src_bus_width = stm32_dma_get_width(chan, src_addr_width);
+		if (src_bus_width < 0)
+			return src_bus_width;
+
+		src_burst_size = stm32_dma_get_burst(chan, src_maxburst);
+		if (src_burst_size < 0)
+			return src_burst_size;
+
+		if (!dst_addr_width)
+			dst_addr_width = src_addr_width;
+
+		dst_bus_width = stm32_dma_get_width(chan, dst_addr_width);
+		if (dst_bus_width < 0)
+			return dst_bus_width;
+
+		dst_burst_size = stm32_dma_get_burst(chan, dst_maxburst);
+		if (dst_burst_size < 0)
+			return dst_burst_size;
+
+		dma_scr = STM32_DMA_SCR_DIR(STM32_DMA_DEV_TO_MEM) |
+			STM32_DMA_SCR_PSIZE(src_bus_width) |
+			STM32_DMA_SCR_MSIZE(dst_bus_width) |
+			STM32_DMA_SCR_PBURST(src_burst_size) |
+			STM32_DMA_SCR_MBURST(dst_burst_size);
+
+		chan->chan_reg.dma_spar = chan->dma_sconfig.src_addr;
+		*buswidth = chan->dma_sconfig.src_addr_width;
+		break;
+
+	default:
+		dev_err(chan2dev(chan), "Dma direction is not supported\n");
+		return -EINVAL;
+	}
+
+	stm32_dma_set_fifo_config(chan, src_maxburst, dst_maxburst);
+
+	chan->chan_reg.dma_scr &= ~(STM32_DMA_SCR_DIR_MASK |
+			STM32_DMA_SCR_PSIZE_MASK | STM32_DMA_SCR_MSIZE_MASK |
+			STM32_DMA_SCR_PBURST_MASK | STM32_DMA_SCR_MBURST_MASK);
+	chan->chan_reg.dma_scr |= dma_scr;
+
+	return 0;
+}
+
+static void stm32_dma_clear_reg(struct stm32_dma_chan_reg *regs)
+{
+	memset(regs, 0, sizeof(struct stm32_dma_chan_reg));
+}
+
+static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
+	struct dma_chan *c, struct scatterlist *sgl,
+	u32 sg_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct stm32_dma_desc *desc;
+	struct scatterlist *sg;
+	enum dma_slave_buswidth buswidth;
+	u32 nb_data_items;
+	int i, ret;
+
+	if (!chan->config_init) {
+		dev_err(chan2dev(chan), "dma channel is not configured\n");
+		return NULL;
+	}
+
+	if (sg_len < 1) {
+		dev_err(chan2dev(chan), "Invalid segment length %d\n", sg_len);
+		return NULL;
+	}
+
+	desc = stm32_dma_alloc_desc(sg_len);
+	if (!desc)
+		return NULL;
+
+	ret = stm32_dma_set_xfer_param(chan, direction, &buswidth);
+	if (ret < 0)
+		goto err;
+
+	/* Set peripheral flow controller */
+	if (chan->dma_sconfig.device_fc)
+		chan->chan_reg.dma_scr |= STM32_DMA_SCR_PFCTRL;
+	else
+		chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		desc->sg_req[i].len = sg_dma_len(sg);
+
+		nb_data_items = desc->sg_req[i].len / buswidth;
+		if (nb_data_items > STM32_DMA_MAX_DATA_ITEMS) {
+			dev_err(chan2dev(chan), "nb items not supported\n");
+			goto err;
+		}
+
+		stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
+		desc->sg_req[i].chan_reg.dma_scr = chan->chan_reg.dma_scr;
+		desc->sg_req[i].chan_reg.dma_sfcr = chan->chan_reg.dma_sfcr;
+		desc->sg_req[i].chan_reg.dma_spar = chan->chan_reg.dma_spar;
+		desc->sg_req[i].chan_reg.dma_sm0ar = sg_dma_address(sg);
+		desc->sg_req[i].chan_reg.dma_sm1ar = sg_dma_address(sg);
+		desc->sg_req[i].chan_reg.dma_sndtr = nb_data_items;
+	}
+
+	desc->num_sgs = sg_len;
+	desc->cyclic = false;
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+
+err:
+	kfree(desc);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *stm32_dma_prep_dma_cyclic(
+	struct dma_chan *c, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct stm32_dma_desc *desc;
+	enum dma_slave_buswidth buswidth;
+	u32 num_periods, nb_data_items;
+	int i, ret;
+
+	if (!buf_len || !period_len) {
+		dev_err(chan2dev(chan), "Invalid buffer/period len\n");
+		return NULL;
+	}
+
+	if (!chan->config_init) {
+		dev_err(chan2dev(chan), "dma channel is not configured\n");
+		return NULL;
+	}
+
+	if (buf_len % period_len) {
+		dev_err(chan2dev(chan), "buf_len not multiple of period_len\n");
+		return NULL;
+	}
+
+	/*
+	 * We allow to take more number of requests till DMA is
+	 * not started. The driver will loop over all requests.
+	 * Once DMA is started then new requests can be queued only after
+	 * terminating the DMA.
+	 */
+	if (chan->busy) {
+		dev_err(chan2dev(chan), "Request not allowed when dma busy\n");
+		return NULL;
+	}
+
+	ret = stm32_dma_set_xfer_param(chan, direction, &buswidth);
+	if (ret < 0)
+		return NULL;
+
+	nb_data_items = period_len / buswidth;
+	if (nb_data_items > STM32_DMA_MAX_DATA_ITEMS) {
+		dev_err(chan2dev(chan), "number of items not supported\n");
+		return NULL;
+	}
+
+	/*  Enable Circular mode or double buffer mode */
+	if (buf_len == period_len)
+		chan->chan_reg.dma_scr |= STM32_DMA_SCR_CIRC;
+	else
+		chan->chan_reg.dma_scr |= STM32_DMA_SCR_DBM;
+
+	/* Clear periph ctrl if client set it */
+	chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL;
+
+	num_periods = buf_len / period_len;
+
+	desc = stm32_dma_alloc_desc(num_periods);
+	if (!desc)
+		return NULL;
+
+	for (i = 0; i < num_periods; i++) {
+		desc->sg_req[i].len = period_len;
+
+		stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
+		desc->sg_req[i].chan_reg.dma_scr = chan->chan_reg.dma_scr;
+		desc->sg_req[i].chan_reg.dma_sfcr = chan->chan_reg.dma_sfcr;
+		desc->sg_req[i].chan_reg.dma_spar = chan->chan_reg.dma_spar;
+		desc->sg_req[i].chan_reg.dma_sm0ar = buf_addr;
+		desc->sg_req[i].chan_reg.dma_sm1ar = buf_addr;
+		desc->sg_req[i].chan_reg.dma_sndtr = nb_data_items;
+		buf_addr += period_len;
+	}
+
+	desc->num_sgs = num_periods;
+	desc->cyclic = true;
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
+	struct dma_chan *c, dma_addr_t dest,
+	dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	u32 num_sgs;
+	struct stm32_dma_desc *desc;
+	size_t xfer_count, offset;
+	int i;
+
+	num_sgs = DIV_ROUND_UP(len, STM32_DMA_MAX_DATA_ITEMS);
+	desc = stm32_dma_alloc_desc(num_sgs);
+	if (!desc)
+		return NULL;
+
+	for (offset = 0, i = 0; offset < len; offset += xfer_count, i++) {
+		xfer_count = min_t(size_t, len - offset,
+				   STM32_DMA_MAX_DATA_ITEMS);
+
+		desc->sg_req[i].len = xfer_count;
+
+		stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
+		desc->sg_req[i].chan_reg.dma_scr =
+			STM32_DMA_SCR_DIR(STM32_DMA_MEM_TO_MEM) |
+			STM32_DMA_SCR_MINC |
+			STM32_DMA_SCR_PINC |
+			STM32_DMA_SCR_TCIE |
+			STM32_DMA_SCR_TEIE;
+		desc->sg_req[i].chan_reg.dma_sfcr = STM32_DMA_SFCR_DMDIS |
+			STM32_DMA_SFCR_FTH(STM32_DMA_FIFO_THRESHOLD_FULL) |
+			STM32_DMA_SFCR_FEIE;
+		desc->sg_req[i].chan_reg.dma_spar = src + offset;
+		desc->sg_req[i].chan_reg.dma_sm0ar = dest + offset;
+		desc->sg_req[i].chan_reg.dma_sndtr = xfer_count;
+	}
+
+	desc->num_sgs = num_sgs;
+	desc->cyclic = false;
+
+	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
+}
+
+static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
+				     struct stm32_dma_desc *desc,
+				     u32 next_sg)
+{
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	u32 dma_scr, width, residue, count;
+	int i;
+
+	residue = 0;
+
+	for (i = next_sg; i < desc->num_sgs; i++)
+		residue += desc->sg_req[i].len;
+
+	if (next_sg != 0) {
+		dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+		width = STM32_DMA_SCR_PSIZE_GET(dma_scr);
+		count = stm32_dma_read(dmadev, STM32_DMA_SNDTR(chan->id));
+
+		residue += count << width;
+	}
+
+	return residue;
+}
+
+static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
+					   dma_cookie_t cookie,
+					   struct dma_tx_state *state)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	unsigned long flags;
+	u32 residue;
+
+	status = dma_cookie_status(c, cookie, state);
+	if ((status == DMA_COMPLETE) || (!state))
+		return status;
+
+	spin_lock_irqsave(&chan->vchan.lock, flags);
+	vdesc = vchan_find_desc(&chan->vchan, cookie);
+	if (cookie == chan->desc->vdesc.tx.cookie) {
+		residue = stm32_dma_desc_residue(chan, chan->desc,
+						 chan->next_sg);
+	} else if (vdesc) {
+		residue = stm32_dma_desc_residue(chan,
+						 to_stm32_dma_desc(vdesc), 0);
+	} else {
+		residue = 0;
+	}
+
+	dma_set_residue(state, residue);
+
+	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+
+	return status;
+}
+
+static int stm32_dma_alloc_chan_resources(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	int ret;
+
+	chan->config_init = false;
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret < 0) {
+		dev_err(chan2dev(chan), "clk_prepare_enable failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = stm32_dma_disable_chan(chan);
+	if (ret < 0)
+		clk_disable_unprepare(dmadev->clk);
+
+	return ret;
+}
+
+static void stm32_dma_free_chan_resources(struct dma_chan *c)
+{
+	struct stm32_dma_chan *chan = to_stm32_dma_chan(c);
+	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
+	unsigned long flags;
+
+	dev_dbg(chan2dev(chan), "Freeing channel %d\n", chan->id);
+
+	if (chan->busy) {
+		spin_lock_irqsave(&chan->vchan.lock, flags);
+		stm32_dma_stop(chan);
+		chan->desc = NULL;
+		spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	}
+
+	clk_disable_unprepare(dmadev->clk);
+
+	vchan_free_chan_resources(to_virt_chan(c));
+}
+
+static void stm32_dma_desc_free(struct virt_dma_desc *vdesc)
+{
+	kfree(container_of(vdesc, struct stm32_dma_desc, vdesc));
+}
+
+void stm32_dma_set_config(struct stm32_dma_chan *chan,
+			  struct stm32_dma_cfg *cfg)
+{
+	stm32_dma_clear_reg(&chan->chan_reg);
+
+	chan->chan_reg.dma_scr = cfg->stream_config & STM32_DMA_SCR_CFG_MASK;
+	chan->chan_reg.dma_scr |= STM32_DMA_SCR_REQ(cfg->request_line);
+
+	/* Enable Interrupts  */
+	chan->chan_reg.dma_scr |= STM32_DMA_SCR_TEIE | STM32_DMA_SCR_TCIE;
+
+	chan->chan_reg.dma_sfcr = cfg->threshold & STM32_DMA_SFCR_FTH_MASK;
+}
+
+static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec,
+					   struct of_dma *ofdma)
+{
+	struct stm32_dma_device *dmadev = ofdma->of_dma_data;
+	struct stm32_dma_cfg cfg;
+	struct stm32_dma_chan *chan;
+	struct dma_chan *c;
+
+	if (dma_spec->args_count < 3)
+		return NULL;
+
+	cfg.channel_id = dma_spec->args[0];
+	cfg.request_line = dma_spec->args[1];
+	cfg.stream_config = dma_spec->args[2];
+	cfg.threshold = 0;
+
+	if ((cfg.channel_id >= STM32_DMA_MAX_CHANNELS) || (cfg.request_line >=
+				STM32_DMA_MAX_REQUEST_ID))
+		return NULL;
+
+	if (dma_spec->args_count > 3)
+		cfg.threshold = dma_spec->args[3];
+
+	chan = &dmadev->chan[cfg.channel_id];
+
+	c = dma_get_slave_channel(&chan->vchan.chan);
+	if (c)
+		stm32_dma_set_config(chan, &cfg);
+
+	return c;
+}
+
+static const struct of_device_id stm32_dma_of_match[] = {
+	{ .compatible = "st,stm32-dma", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, stm32_dma_of_match);
+
+static int stm32_dma_probe(struct platform_device *pdev)
+{
+	struct stm32_dma_chan *chan;
+	struct stm32_dma_device *dmadev;
+	struct dma_device *dd;
+	const struct of_device_id *match;
+	struct resource *res;
+	int i, ret;
+
+	match = of_match_device(stm32_dma_of_match, &pdev->dev);
+	if (!match) {
+		dev_err(&pdev->dev, "Error: No device match found\n");
+		return -ENODEV;
+	}
+
+	dmadev = devm_kzalloc(&pdev->dev, sizeof(*dmadev), GFP_KERNEL);
+	if (!dmadev)
+		return -ENOMEM;
+
+	dd = &dmadev->ddev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dmadev->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dmadev->base))
+		return PTR_ERR(dmadev->base);
+
+	dmadev->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dmadev->clk)) {
+		dev_err(&pdev->dev, "Error: Missing controller clock\n");
+		return PTR_ERR(dmadev->clk);
+	}
+
+	dmadev->mem2mem = of_property_read_bool(pdev->dev.of_node,
+						"st,mem2mem");
+
+	dmadev->rst = devm_reset_control_get(&pdev->dev, NULL);
+	if (!IS_ERR(dmadev->rst)) {
+		reset_control_assert(dmadev->rst);
+		udelay(2);
+		reset_control_deassert(dmadev->rst);
+	}
+
+	dma_cap_set(DMA_SLAVE, dd->cap_mask);
+	dma_cap_set(DMA_PRIVATE, dd->cap_mask);
+	dma_cap_set(DMA_CYCLIC, dd->cap_mask);
+	dd->device_alloc_chan_resources = stm32_dma_alloc_chan_resources;
+	dd->device_free_chan_resources = stm32_dma_free_chan_resources;
+	dd->device_tx_status = stm32_dma_tx_status;
+	dd->device_issue_pending = stm32_dma_issue_pending;
+	dd->device_prep_slave_sg = stm32_dma_prep_slave_sg;
+	dd->device_prep_dma_cyclic = stm32_dma_prep_dma_cyclic;
+	dd->device_config = stm32_dma_slave_config;
+	dd->device_terminate_all = stm32_dma_terminate_all;
+	dd->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+		BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	dd->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+		BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	dd->dev = &pdev->dev;
+	INIT_LIST_HEAD(&dd->channels);
+
+	if (dmadev->mem2mem) {
+		dma_cap_set(DMA_MEMCPY, dd->cap_mask);
+		dd->device_prep_dma_memcpy = stm32_dma_prep_dma_memcpy;
+		dd->directions |= BIT(DMA_MEM_TO_MEM);
+	}
+
+	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
+		chan = &dmadev->chan[i];
+		chan->id = i;
+		chan->vchan.desc_free = stm32_dma_desc_free;
+		vchan_init(&chan->vchan, dd);
+	}
+
+	ret = dma_async_device_register(dd);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
+		chan = &dmadev->chan[i];
+		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
+		if (!res) {
+			ret = -EINVAL;
+			dev_err(&pdev->dev, "No irq resource for chan %d\n", i);
+			goto err_unregister;
+		}
+		chan->irq = res->start;
+		ret = devm_request_irq(&pdev->dev, chan->irq,
+				       stm32_dma_chan_irq, 0,
+				       dev_name(chan2dev(chan)), chan);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"request_irq failed with err %d channel %d\n",
+				ret, i);
+			goto err_unregister;
+		}
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 stm32_dma_of_xlate, dmadev);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"STM32 DMA DMA OF registration failed %d\n", ret);
+		goto err_unregister;
+	}
+
+	platform_set_drvdata(pdev, dmadev);
+
+	dev_info(&pdev->dev, "STM32 DMA driver registered\n");
+
+	return 0;
+
+err_unregister:
+	dma_async_device_unregister(dd);
+
+	return ret;
+}
+
+static struct platform_driver stm32_dma_driver = {
+	.driver = {
+		.name = "stm32-dma",
+		.of_match_table = stm32_dma_of_match,
+	},
+};
+
+static int __init stm32_dma_init(void)
+{
+	return platform_driver_probe(&stm32_dma_driver, stm32_dma_probe);
+}
+subsys_initcall(stm32_dma_init);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index c8f79dcaa..935da8192 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -296,7 +296,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get(
 	spin_unlock_irqrestore(&tdc->lock, flags);
 
 	/* Allocate DMA desc */
-	dma_desc = kzalloc(sizeof(*dma_desc), GFP_ATOMIC);
+	dma_desc = kzalloc(sizeof(*dma_desc), GFP_NOWAIT);
 	if (!dma_desc) {
 		dev_err(tdc2dev(tdc), "dma_desc alloc failed\n");
 		return NULL;
@@ -336,7 +336,7 @@ static struct tegra_dma_sg_req *tegra_dma_sg_req_get(
 	}
 	spin_unlock_irqrestore(&tdc->lock, flags);
 
-	sg_req = kzalloc(sizeof(struct tegra_dma_sg_req), GFP_ATOMIC);
+	sg_req = kzalloc(sizeof(struct tegra_dma_sg_req), GFP_NOWAIT);
 	if (!sg_req)
 		dev_err(tdc2dev(tdc), "sg_req alloc failed\n");
 	return sg_req;
@@ -1186,10 +1186,12 @@ static int tegra_dma_alloc_chan_resources(struct dma_chan *dc)
 
 	dma_cookie_init(&tdc->dma_chan);
 	tdc->config_init = false;
-	ret = clk_prepare_enable(tdma->dma_clk);
+
+	ret = pm_runtime_get_sync(tdma->dev);
 	if (ret < 0)
-		dev_err(tdc2dev(tdc), "clk_prepare_enable failed: %d\n", ret);
-	return ret;
+		return ret;
+
+	return 0;
 }
 
 static void tegra_dma_free_chan_resources(struct dma_chan *dc)
@@ -1232,7 +1234,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)
 		list_del(&sg_req->node);
 		kfree(sg_req);
 	}
-	clk_disable_unprepare(tdma->dma_clk);
+	pm_runtime_put(tdma->dev);
 
 	tdc->slave_id = 0;
 }
@@ -1356,20 +1358,14 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&tdma->global_lock);
 
 	pm_runtime_enable(&pdev->dev);
-	if (!pm_runtime_enabled(&pdev->dev)) {
+	if (!pm_runtime_enabled(&pdev->dev))
 		ret = tegra_dma_runtime_resume(&pdev->dev);
-		if (ret) {
-			dev_err(&pdev->dev, "dma_runtime_resume failed %d\n",
-				ret);
-			goto err_pm_disable;
-		}
-	}
+	else
+		ret = pm_runtime_get_sync(&pdev->dev);
 
-	/* Enable clock before accessing registers */
-	ret = clk_prepare_enable(tdma->dma_clk);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "clk_prepare_enable failed: %d\n", ret);
-		goto err_pm_disable;
+		pm_runtime_disable(&pdev->dev);
+		return ret;
 	}
 
 	/* Reset DMA controller */
@@ -1382,7 +1378,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	tdma_write(tdma, TEGRA_APBDMA_CONTROL, 0);
 	tdma_write(tdma, TEGRA_APBDMA_IRQ_MASK_SET, 0xFFFFFFFFul);
 
-	clk_disable_unprepare(tdma->dma_clk);
+	pm_runtime_put(&pdev->dev);
 
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < cdata->nr_channels; i++) {
@@ -1400,8 +1396,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		}
 		tdc->irq = res->start;
 		snprintf(tdc->name, sizeof(tdc->name), "apbdma.%d", i);
-		ret = devm_request_irq(&pdev->dev, tdc->irq,
-				tegra_dma_isr, 0, tdc->name, tdc);
+		ret = request_irq(tdc->irq, tegra_dma_isr, 0, tdc->name, tdc);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"request_irq failed with err %d channel %d\n",
@@ -1482,10 +1477,11 @@ err_unregister_dma_dev:
 err_irq:
 	while (--i >= 0) {
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
+
+		free_irq(tdc->irq, tdc);
 		tasklet_kill(&tdc->tasklet);
 	}
 
-err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		tegra_dma_runtime_suspend(&pdev->dev);
@@ -1502,6 +1498,7 @@ static int tegra_dma_remove(struct platform_device *pdev)
 
 	for (i = 0; i < tdma->chip_data->nr_channels; ++i) {
 		tdc = &tdma->channels[i];
+		free_irq(tdc->irq, tdc);
 		tasklet_kill(&tdc->tasklet);
 	}
 
@@ -1514,8 +1511,7 @@ static int tegra_dma_remove(struct platform_device *pdev)
 
 static int tegra_dma_runtime_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct tegra_dma *tdma = platform_get_drvdata(pdev);
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
 
 	clk_disable_unprepare(tdma->dma_clk);
 	return 0;
@@ -1523,8 +1519,7 @@ static int tegra_dma_runtime_suspend(struct device *dev)
 
 static int tegra_dma_runtime_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct tegra_dma *tdma = platform_get_drvdata(pdev);
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
 	int ret;
 
 	ret = clk_prepare_enable(tdma->dma_clk);
@@ -1543,7 +1538,7 @@ static int tegra_dma_pm_suspend(struct device *dev)
 	int ret;
 
 	/* Enable clock before accessing register */
-	ret = tegra_dma_runtime_resume(dev);
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		return ret;
 
@@ -1552,15 +1547,22 @@ static int tegra_dma_pm_suspend(struct device *dev)
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 		struct tegra_dma_channel_regs *ch_reg = &tdc->channel_reg;
 
+		/* Only save the state of DMA channels that are in use */
+		if (!tdc->config_init)
+			continue;
+
 		ch_reg->csr = tdc_read(tdc, TEGRA_APBDMA_CHAN_CSR);
 		ch_reg->ahb_ptr = tdc_read(tdc, TEGRA_APBDMA_CHAN_AHBPTR);
 		ch_reg->apb_ptr = tdc_read(tdc, TEGRA_APBDMA_CHAN_APBPTR);
 		ch_reg->ahb_seq = tdc_read(tdc, TEGRA_APBDMA_CHAN_AHBSEQ);
 		ch_reg->apb_seq = tdc_read(tdc, TEGRA_APBDMA_CHAN_APBSEQ);
+		if (tdma->chip_data->support_separate_wcount_reg)
+			ch_reg->wcount = tdc_read(tdc,
+						  TEGRA_APBDMA_CHAN_WCOUNT);
 	}
 
 	/* Disable clock */
-	tegra_dma_runtime_suspend(dev);
+	pm_runtime_put(dev);
 	return 0;
 }
 
@@ -1571,7 +1573,7 @@ static int tegra_dma_pm_resume(struct device *dev)
 	int ret;
 
 	/* Enable clock before accessing register */
-	ret = tegra_dma_runtime_resume(dev);
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		return ret;
 
@@ -1583,6 +1585,13 @@ static int tegra_dma_pm_resume(struct device *dev)
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 		struct tegra_dma_channel_regs *ch_reg = &tdc->channel_reg;
 
+		/* Only restore the state of DMA channels that are in use */
+		if (!tdc->config_init)
+			continue;
+
+		if (tdma->chip_data->support_separate_wcount_reg)
+			tdc_write(tdc, TEGRA_APBDMA_CHAN_WCOUNT,
+				  ch_reg->wcount);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_APBSEQ, ch_reg->apb_seq);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_APBPTR, ch_reg->apb_ptr);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_AHBSEQ, ch_reg->ahb_seq);
@@ -1592,16 +1601,14 @@ static int tegra_dma_pm_resume(struct device *dev)
 	}
 
 	/* Disable clock */
-	tegra_dma_runtime_suspend(dev);
+	pm_runtime_put(dev);
 	return 0;
 }
 #endif
 
 static const struct dev_pm_ops tegra_dma_dev_pm_ops = {
-#ifdef CONFIG_PM
-	.runtime_suspend = tegra_dma_runtime_suspend,
-	.runtime_resume = tegra_dma_runtime_resume,
-#endif
+	SET_RUNTIME_PM_OPS(tegra_dma_runtime_suspend, tegra_dma_runtime_resume,
+			   NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_dma_pm_suspend, tegra_dma_pm_resume)
 };
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index a415edbe6..e107779b1 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/io.h>
-#include <linux/idr.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
@@ -198,7 +197,8 @@ struct ti_dra7_xbar_data {
 	void __iomem *iomem;
 
 	struct dma_router dmarouter;
-	struct idr map_idr;
+	struct mutex mutex;
+	unsigned long *dma_inuse;
 
 	u16 safe_val; /* Value to rest the crossbar lines */
 	u32 xbar_requests; /* number of DMA requests connected to XBAR */
@@ -225,7 +225,9 @@ static void ti_dra7_xbar_free(struct device *dev, void *route_data)
 		map->xbar_in, map->xbar_out);
 
 	ti_dra7_xbar_write(xbar->iomem, map->xbar_out, xbar->safe_val);
-	idr_remove(&xbar->map_idr, map->xbar_out);
+	mutex_lock(&xbar->mutex);
+	clear_bit(map->xbar_out, xbar->dma_inuse);
+	mutex_unlock(&xbar->mutex);
 	kfree(map);
 }
 
@@ -255,8 +257,17 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	map->xbar_out = idr_alloc(&xbar->map_idr, NULL, 0, xbar->dma_requests,
-				  GFP_KERNEL);
+	mutex_lock(&xbar->mutex);
+	map->xbar_out = find_first_zero_bit(xbar->dma_inuse,
+					    xbar->dma_requests);
+	mutex_unlock(&xbar->mutex);
+	if (map->xbar_out == xbar->dma_requests) {
+		dev_err(&pdev->dev, "Run out of free DMA requests\n");
+		kfree(map);
+		return ERR_PTR(-ENOMEM);
+	}
+	set_bit(map->xbar_out, xbar->dma_inuse);
+
 	map->xbar_in = (u16)dma_spec->args[0];
 
 	dma_spec->args[0] = map->xbar_out + xbar->dma_offset;
@@ -278,17 +289,29 @@ static const struct of_device_id ti_dra7_master_match[] = {
 		.compatible = "ti,edma3",
 		.data = (void *)TI_XBAR_EDMA_OFFSET,
 	},
+	{
+		.compatible = "ti,edma3-tpcc",
+		.data = (void *)TI_XBAR_EDMA_OFFSET,
+	},
 	{},
 };
 
+static inline void ti_dra7_xbar_reserve(int offset, int len, unsigned long *p)
+{
+	for (; len > 0; len--)
+		clear_bit(offset + (len - 1), p);
+}
+
 static int ti_dra7_xbar_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
 	const struct of_device_id *match;
 	struct device_node *dma_node;
 	struct ti_dra7_xbar_data *xbar;
+	struct property *prop;
 	struct resource *res;
 	u32 safe_val;
+	size_t sz;
 	void __iomem *iomem;
 	int i, ret;
 
@@ -299,8 +322,6 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	if (!xbar)
 		return -ENOMEM;
 
-	idr_init(&xbar->map_idr);
-
 	dma_node = of_parse_phandle(node, "dma-masters", 0);
 	if (!dma_node) {
 		dev_err(&pdev->dev, "Can't get DMA master node\n");
@@ -322,6 +343,12 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	}
 	of_node_put(dma_node);
 
+	xbar->dma_inuse = devm_kcalloc(&pdev->dev,
+				       BITS_TO_LONGS(xbar->dma_requests),
+				       sizeof(unsigned long), GFP_KERNEL);
+	if (!xbar->dma_inuse)
+		return -ENOMEM;
+
 	if (of_property_read_u32(node, "dma-requests", &xbar->xbar_requests)) {
 		dev_info(&pdev->dev,
 			 "Missing XBAR input information, using %u.\n",
@@ -332,6 +359,33 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	if (!of_property_read_u32(node, "ti,dma-safe-map", &safe_val))
 		xbar->safe_val = (u16)safe_val;
 
+
+	prop = of_find_property(node, "ti,reserved-dma-request-ranges", &sz);
+	if (prop) {
+		const char pname[] = "ti,reserved-dma-request-ranges";
+		u32 (*rsv_events)[2];
+		size_t nelm = sz / sizeof(*rsv_events);
+		int i;
+
+		if (!nelm)
+			return -EINVAL;
+
+		rsv_events = kcalloc(nelm, sizeof(*rsv_events), GFP_KERNEL);
+		if (!rsv_events)
+			return -ENOMEM;
+
+		ret = of_property_read_u32_array(node, pname, (u32 *)rsv_events,
+						 nelm * 2);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < nelm; i++) {
+			ti_dra7_xbar_reserve(rsv_events[i][0], rsv_events[i][1],
+					     xbar->dma_inuse);
+		}
+		kfree(rsv_events);
+	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iomem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(iomem))
@@ -343,18 +397,23 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	xbar->dmarouter.route_free = ti_dra7_xbar_free;
 	xbar->dma_offset = (u32)match->data;
 
+	mutex_init(&xbar->mutex);
 	platform_set_drvdata(pdev, xbar);
 
 	/* Reset the crossbar */
-	for (i = 0; i < xbar->dma_requests; i++)
-		ti_dra7_xbar_write(xbar->iomem, i, xbar->safe_val);
+	for (i = 0; i < xbar->dma_requests; i++) {
+		if (!test_bit(i, xbar->dma_inuse))
+			ti_dra7_xbar_write(xbar->iomem, i, xbar->safe_val);
+	}
 
 	ret = of_dma_router_register(node, ti_dra7_xbar_route_allocate,
 				     &xbar->dmarouter);
 	if (ret) {
 		/* Restore the defaults for the crossbar */
-		for (i = 0; i < xbar->dma_requests; i++)
-			ti_dra7_xbar_write(xbar->iomem, i, i);
+		for (i = 0; i < xbar->dma_requests; i++) {
+			if (!test_bit(i, xbar->dma_inuse))
+				ti_dra7_xbar_write(xbar->iomem, i, i);
+		}
 	}
 
 	return ret;
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 6f80432a3..a35c21185 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -29,7 +29,7 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_add_tail(&vd->node, &vc->desc_submitted);
+	list_move_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -39,6 +39,33 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 }
 EXPORT_SYMBOL_GPL(vchan_tx_submit);
 
+/**
+ * vchan_tx_desc_free - free a reusable descriptor
+ * @tx: the transfer
+ *
+ * This function frees a previously allocated reusable descriptor. The only
+ * other way is to clear the DMA_CTRL_REUSE flag and submit one last time the
+ * transfer.
+ *
+ * Returns 0 upon success
+ */
+int vchan_tx_desc_free(struct dma_async_tx_descriptor *tx)
+{
+	struct virt_dma_chan *vc = to_virt_chan(tx->chan);
+	struct virt_dma_desc *vd = to_virt_desc(tx);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: freeing\n",
+		vc, vd, vd->tx.cookie);
+	vc->desc_free(vd);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vchan_tx_desc_free);
+
 struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *vc,
 	dma_cookie_t cookie)
 {
@@ -83,8 +110,10 @@ static void vchan_complete(unsigned long arg)
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-
-		vc->desc_free(vd);
+		if (dmaengine_desc_test_reuse(&vd->tx))
+			list_add(&vd->node, &vc->desc_allocated);
+		else
+			vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -96,9 +125,13 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		list_del(&vd->node);
-		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-		vc->desc_free(vd);
+		if (dmaengine_desc_test_reuse(&vd->tx)) {
+			list_move_tail(&vd->node, &vc->desc_allocated);
+		} else {
+			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+			list_del(&vd->node);
+			vc->desc_free(vd);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -108,6 +141,7 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
+	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 2fa47745a..d9731ca5e 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -29,6 +29,7 @@ struct virt_dma_chan {
 	spinlock_t lock;
 
 	/* protected by vc.lock */
+	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -55,10 +56,17 @@ static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
+	extern int vchan_tx_desc_free(struct dma_async_tx_descriptor *);
+	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
+	vd->tx.desc_free = vchan_tx_desc_free;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_add_tail(&vd->node, &vc->desc_allocated);
+	spin_unlock_irqrestore(&vc->lock, flags);
 
 	return &vd->tx;
 }
@@ -134,6 +142,7 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
+	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -141,14 +150,30 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
+	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
+	list_for_each_entry(vd, &head, node)
+		dmaengine_desc_clear_reuse(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
 }
 
+/**
+ * vchan_synchronize() - synchronize callback execution to the current context
+ * @vc: virtual channel to synchronize
+ *
+ * Makes sure that all scheduled or active callbacks have finished running. For
+ * proper operation the caller has to ensure that no new callbacks are scheduled
+ * after the invocation of this function started.
+ */
+static inline void vchan_synchronize(struct virt_dma_chan *vc)
+{
+	tasklet_kill(&vc->task);
+}
+
 #endif