Merge tag 'dmaengine-5.2-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - Updates to stm32 dma residue calculations

 - Interleave dma capability to axi-dmac and support for ZynqMP arch

 - Rework of channel assignment for rcar dma

 - Debugfs for pl330 driver

 - Support for Tegra186/Tegra194, refactoring for new chips and support
   for pause/resume

 - Updates to axi-dmac, bcm2835, fsl-edma, idma64, imx-sdma, rcar-dmac,
   stm32-dma etc

 - dev_get_drvdata() updates on few drivers

* tag 'dmaengine-5.2-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (34 commits)
  dmaengine: tegra210-adma: restore channel status
  dmaengine: tegra210-dma: free dma controller in remove()
  dmaengine: tegra210-adma: add pause/resume support
  dmaengine: tegra210-adma: add support for Tegra186/Tegra194
  Documentation: DT: Add compatibility binding for Tegra186
  dmaengine: tegra210-adma: prepare for supporting newer Tegra chips
  dmaengine: at_xdmac: remove a stray bottom half unlock
  dmaengine: fsl-edma: Adjust indentation
  dmaengine: fsl-edma: Fix typo in Vybrid name
  dmaengine: stm32-dma: fix residue calculation in stm32-dma
  dmaengine: nbpfaxi: Use dev_get_drvdata()
  dmaengine: bcm-sba-raid: Use dev_get_drvdata()
  dmaengine: stm32-dma: Fix unsigned variable compared with zero
  dmaengine: stm32-dma: use platform_get_irq()
  dmaengine: rcar-dmac: Update copyright information
  dmaengine: imx-sdma: Only check ratio on parts that support 1:1
  dmaengine: xgene-dma: fix spelling mistake "descripto" -> "descriptor"
  dmaengine: idma64: Move driver name to the header
  dmaengine: bcm2835: Drop duplicate capability setting.
  dmaengine: pl330: _stop: clear interrupt status
  ...

17 files changed, 542 insertions, 156 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 0b1dfb5bf2d9..eaf78f4e07ce 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -99,7 +99,7 @@ config AT_XDMAC
 
 config AXI_DMAC
 	tristate "Analog Devices AXI-DMAC DMA support"
-	depends on MICROBLAZE || NIOS2 || ARCH_ZYNQ || ARCH_SOCFPGA || COMPILE_TEST
+	depends on MICROBLAZE || NIOS2 || ARCH_ZYNQ || ARCH_ZYNQMP || ARCH_SOCFPGA || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index fc8c2bab563c..8cfc753ad4b0 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -254,6 +254,7 @@ enum pl08x_dma_chan_state {
  * @slave: whether this channel is a device (slave) or for memcpy
  * @signal: the physical DMA request signal which this channel is using
  * @mux_use: count of descriptors using this DMA request signal setting
+ * @waiting_at: time in jiffies when this channel moved to waiting state
  */
 struct pl08x_dma_chan {
 	struct virt_dma_chan vc;
@@ -267,6 +268,7 @@ struct pl08x_dma_chan {
 	bool slave;
 	int signal;
 	unsigned mux_use;
+	unsigned long waiting_at;
 };
 
 /**
@@ -875,6 +877,7 @@ static void pl08x_phy_alloc_and_start(struct pl08x_dma_chan *plchan)
 	if (!ch) {
 		dev_dbg(&pl08x->adev->dev, "no physical channel available for xfer on %s\n", plchan->name);
 		plchan->state = PL08X_CHAN_WAITING;
+		plchan->waiting_at = jiffies;
 		return;
 	}
 
@@ -913,22 +916,29 @@ static void pl08x_phy_free(struct pl08x_dma_chan *plchan)
 {
 	struct pl08x_driver_data *pl08x = plchan->host;
 	struct pl08x_dma_chan *p, *next;
-
+	unsigned long waiting_at;
  retry:
 	next = NULL;
+	waiting_at = jiffies;
 
-	/* Find a waiting virtual channel for the next transfer. */
+	/*
+	 * Find a waiting virtual channel for the next transfer.
+	 * To be fair, time when each channel reached waiting state is compared
+	 * to select channel that is waiting for the longest time.
+	 */
 	list_for_each_entry(p, &pl08x->memcpy.channels, vc.chan.device_node)
-		if (p->state == PL08X_CHAN_WAITING) {
+		if (p->state == PL08X_CHAN_WAITING &&
+		    p->waiting_at <= waiting_at) {
 			next = p;
-			break;
+			waiting_at = p->waiting_at;
 		}
 
 	if (!next && pl08x->has_slave) {
 		list_for_each_entry(p, &pl08x->slave.channels, vc.chan.device_node)
-			if (p->state == PL08X_CHAN_WAITING) {
+			if (p->state == PL08X_CHAN_WAITING &&
+			    p->waiting_at <= waiting_at) {
 				next = p;
-				break;
+				waiting_at = p->waiting_at;
 			}
 	}
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index fe69dccfa0c0..e4ae2ee46d3f 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -308,6 +308,11 @@ static inline int at_xdmac_csize(u32 maxburst)
 	return csize;
 };
 
+static inline bool at_xdmac_chan_is_peripheral_xfer(u32 cfg)
+{
+	return cfg & AT_XDMAC_CC_TYPE_PER_TRAN;
+}
+
 static inline u8 at_xdmac_get_dwidth(u32 cfg)
 {
 	return (cfg & AT_XDMAC_CC_DWIDTH_MASK) >> AT_XDMAC_CC_DWIDTH_OFFSET;
@@ -389,7 +394,13 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 		 at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));
 
 	at_xdmac_chan_write(atchan, AT_XDMAC_CID, 0xffffffff);
-	reg = AT_XDMAC_CIE_RBEIE | AT_XDMAC_CIE_WBEIE | AT_XDMAC_CIE_ROIE;
+	reg = AT_XDMAC_CIE_RBEIE | AT_XDMAC_CIE_WBEIE;
+	/*
+	 * Request Overflow Error is only for peripheral synchronized transfers
+	 */
+	if (at_xdmac_chan_is_peripheral_xfer(first->lld.mbr_cfg))
+		reg |= AT_XDMAC_CIE_ROIE;
+
 	/*
 	 * There is no end of list when doing cyclic dma, we need to get
 	 * an interrupt after each periods.
@@ -1575,6 +1586,46 @@ static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
 		dmaengine_desc_get_callback_invoke(txd, NULL);
 }
 
+static void at_xdmac_handle_error(struct at_xdmac_chan *atchan)
+{
+	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	struct at_xdmac_desc	*bad_desc;
+
+	/*
+	 * The descriptor currently at the head of the active list is
+	 * broken. Since we don't have any way to report errors, we'll
+	 * just have to scream loudly and try to continue with other
+	 * descriptors queued (if any).
+	 */
+	if (atchan->irq_status & AT_XDMAC_CIS_RBEIS)
+		dev_err(chan2dev(&atchan->chan), "read bus error!!!");
+	if (atchan->irq_status & AT_XDMAC_CIS_WBEIS)
+		dev_err(chan2dev(&atchan->chan), "write bus error!!!");
+	if (atchan->irq_status & AT_XDMAC_CIS_ROIS)
+		dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
+
+	spin_lock_bh(&atchan->lock);
+
+	/* Channel must be disabled first as it's not done automatically */
+	at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
+	while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask)
+		cpu_relax();
+
+	bad_desc = list_first_entry(&atchan->xfers_list,
+				    struct at_xdmac_desc,
+				    xfer_node);
+
+	spin_unlock_bh(&atchan->lock);
+
+	/* Print bad descriptor's details if needed */
+	dev_dbg(chan2dev(&atchan->chan),
+		"%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
+		__func__, &bad_desc->lld.mbr_sa, &bad_desc->lld.mbr_da,
+		bad_desc->lld.mbr_ubc);
+
+	/* Then continue with usual descriptor management */
+}
+
 static void at_xdmac_tasklet(unsigned long data)
 {
 	struct at_xdmac_chan	*atchan = (struct at_xdmac_chan *)data;
@@ -1594,19 +1645,19 @@ static void at_xdmac_tasklet(unsigned long data)
 		   || (atchan->irq_status & error_mask)) {
 		struct dma_async_tx_descriptor  *txd;
 
-		if (atchan->irq_status & AT_XDMAC_CIS_RBEIS)
-			dev_err(chan2dev(&atchan->chan), "read bus error!!!");
-		if (atchan->irq_status & AT_XDMAC_CIS_WBEIS)
-			dev_err(chan2dev(&atchan->chan), "write bus error!!!");
-		if (atchan->irq_status & AT_XDMAC_CIS_ROIS)
-			dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
+		if (atchan->irq_status & error_mask)
+			at_xdmac_handle_error(atchan);
 
 		spin_lock(&atchan->lock);
 		desc = list_first_entry(&atchan->xfers_list,
 					struct at_xdmac_desc,
 					xfer_node);
 		dev_vdbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc);
-		BUG_ON(!desc->active_xfer);
+		if (!desc->active_xfer) {
+			dev_err(chan2dev(&atchan->chan), "Xfer not active: exiting");
+			spin_unlock(&atchan->lock);
+			return;
+		}
 
 		txd = &desc->tx_dma_desc;
 
diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c
index 72878ac5c78d..fa81d0177765 100644
--- a/drivers/dma/bcm-sba-raid.c
+++ b/drivers/dma/bcm-sba-raid.c
@@ -1459,8 +1459,7 @@ static void sba_receive_message(struct mbox_client *cl, void *msg)
 
 static int sba_debugfs_stats_show(struct seq_file *file, void *offset)
 {
-	struct platform_device *pdev = to_platform_device(file->private);
-	struct sba_device *sba = platform_get_drvdata(pdev);
+	struct sba_device *sba = dev_get_drvdata(file->private);
 
 	/* Write stats in file */
 	sba_write_stats_in_seqfile(sba, file);
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 54093ffd0aef..8101ff2f05c1 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -891,7 +891,6 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
 	dma_cap_set(DMA_PRIVATE, od->ddev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
-	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
 	dma_cap_set(DMA_MEMCPY, od->ddev.cap_mask);
 	od->ddev.device_alloc_chan_resources = bcm2835_dma_alloc_chan_resources;
 	od->ddev.device_free_chan_resources = bcm2835_dma_free_chan_resources;
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index ffc0adc2f6ce..f32fdf21edbd 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -166,7 +166,7 @@ static int axi_dmac_dest_is_mem(struct axi_dmac_chan *chan)
 
 static bool axi_dmac_check_len(struct axi_dmac_chan *chan, unsigned int len)
 {
-	if (len == 0 || len > chan->max_length)
+	if (len == 0)
 		return false;
 	if ((len & chan->align_mask) != 0) /* Not aligned */
 		return false;
@@ -379,6 +379,49 @@ static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
 	return desc;
 }
 
+static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
+	enum dma_transfer_direction direction, dma_addr_t addr,
+	unsigned int num_periods, unsigned int period_len,
+	struct axi_dmac_sg *sg)
+{
+	unsigned int num_segments, i;
+	unsigned int segment_size;
+	unsigned int len;
+
+	/* Split into multiple equally sized segments if necessary */
+	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
+	segment_size = DIV_ROUND_UP(period_len, num_segments);
+	/* Take care of alignment */
+	segment_size = ((segment_size - 1) | chan->align_mask) + 1;
+
+	for (i = 0; i < num_periods; i++) {
+		len = period_len;
+
+		while (len > segment_size) {
+			if (direction == DMA_DEV_TO_MEM)
+				sg->dest_addr = addr;
+			else
+				sg->src_addr = addr;
+			sg->x_len = segment_size;
+			sg->y_len = 1;
+			sg++;
+			addr += segment_size;
+			len -= segment_size;
+		}
+
+		if (direction == DMA_DEV_TO_MEM)
+			sg->dest_addr = addr;
+		else
+			sg->src_addr = addr;
+		sg->x_len = len;
+		sg->y_len = 1;
+		sg++;
+		addr += len;
+	}
+
+	return sg;
+}
+
 static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	struct dma_chan *c, struct scatterlist *sgl,
 	unsigned int sg_len, enum dma_transfer_direction direction,
@@ -386,16 +429,24 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac_desc *desc;
+	struct axi_dmac_sg *dsg;
 	struct scatterlist *sg;
+	unsigned int num_sgs;
 	unsigned int i;
 
 	if (direction != chan->direction)
 		return NULL;
 
-	desc = axi_dmac_alloc_desc(sg_len);
+	num_sgs = 0;
+	for_each_sg(sgl, sg, sg_len, i)
+		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), chan->max_length);
+
+	desc = axi_dmac_alloc_desc(num_sgs);
 	if (!desc)
 		return NULL;
 
+	dsg = desc->sg;
+
 	for_each_sg(sgl, sg, sg_len, i) {
 		if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
 		    !axi_dmac_check_len(chan, sg_dma_len(sg))) {
@@ -403,12 +454,8 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 			return NULL;
 		}
 
-		if (direction == DMA_DEV_TO_MEM)
-			desc->sg[i].dest_addr = sg_dma_address(sg);
-		else
-			desc->sg[i].src_addr = sg_dma_address(sg);
-		desc->sg[i].x_len = sg_dma_len(sg);
-		desc->sg[i].y_len = 1;
+		dsg = axi_dmac_fill_linear_sg(chan, direction, sg_dma_address(sg), 1,
+			sg_dma_len(sg), dsg);
 	}
 
 	desc->cyclic = false;
@@ -423,7 +470,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac_desc *desc;
-	unsigned int num_periods, i;
+	unsigned int num_periods, num_segments;
 
 	if (direction != chan->direction)
 		return NULL;
@@ -436,20 +483,14 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 		return NULL;
 
 	num_periods = buf_len / period_len;
+	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
 
-	desc = axi_dmac_alloc_desc(num_periods);
+	desc = axi_dmac_alloc_desc(num_periods * num_segments);
 	if (!desc)
 		return NULL;
 
-	for (i = 0; i < num_periods; i++) {
-		if (direction == DMA_DEV_TO_MEM)
-			desc->sg[i].dest_addr = buf_addr;
-		else
-			desc->sg[i].src_addr = buf_addr;
-		desc->sg[i].x_len = period_len;
-		desc->sg[i].y_len = 1;
-		buf_addr += period_len;
-	}
+	axi_dmac_fill_linear_sg(chan, direction, buf_addr, num_periods,
+		period_len, desc->sg);
 
 	desc->cyclic = true;
 
@@ -485,7 +526,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
 
 	if (chan->hw_2d) {
 		if (!axi_dmac_check_len(chan, xt->sgl[0].size) ||
-		    !axi_dmac_check_len(chan, xt->numf))
+		    xt->numf == 0)
 			return NULL;
 		if (xt->sgl[0].size + dst_icg > chan->max_length ||
 		    xt->sgl[0].size + src_icg > chan->max_length)
@@ -577,15 +618,6 @@ static int axi_dmac_parse_chan_dt(struct device_node *of_chan,
 		return ret;
 	chan->dest_width = val / 8;
 
-	ret = of_property_read_u32(of_chan, "adi,length-width", &val);
-	if (ret)
-		return ret;
-
-	if (val >= 32)
-		chan->max_length = UINT_MAX;
-	else
-		chan->max_length = (1ULL << val) - 1;
-
 	chan->align_mask = max(chan->dest_width, chan->src_width) - 1;
 
 	if (axi_dmac_dest_is_mem(chan) && axi_dmac_src_is_mem(chan))
@@ -597,12 +629,27 @@ static int axi_dmac_parse_chan_dt(struct device_node *of_chan,
 	else
 		chan->direction = DMA_DEV_TO_DEV;
 
-	chan->hw_cyclic = of_property_read_bool(of_chan, "adi,cyclic");
-	chan->hw_2d = of_property_read_bool(of_chan, "adi,2d");
-
 	return 0;
 }
 
+static void axi_dmac_detect_caps(struct axi_dmac *dmac)
+{
+	struct axi_dmac_chan *chan = &dmac->chan;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, AXI_DMAC_FLAG_CYCLIC);
+	if (axi_dmac_read(dmac, AXI_DMAC_REG_FLAGS) == AXI_DMAC_FLAG_CYCLIC)
+		chan->hw_cyclic = true;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, 1);
+	if (axi_dmac_read(dmac, AXI_DMAC_REG_Y_LENGTH) == 1)
+		chan->hw_2d = true;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, 0xffffffff);
+	chan->max_length = axi_dmac_read(dmac, AXI_DMAC_REG_X_LENGTH);
+	if (chan->max_length != UINT_MAX)
+		chan->max_length++;
+}
+
 static int axi_dmac_probe(struct platform_device *pdev)
 {
 	struct device_node *of_channels, *of_chan;
@@ -647,11 +694,12 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	of_node_put(of_channels);
 
 	pdev->dev.dma_parms = &dmac->dma_parms;
-	dma_set_max_seg_size(&pdev->dev, dmac->chan.max_length);
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
 	dma_dev = &dmac->dma_dev;
 	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
 	dma_cap_set(DMA_CYCLIC, dma_dev->cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, dma_dev->cap_mask);
 	dma_dev->device_free_chan_resources = axi_dmac_free_chan_resources;
 	dma_dev->device_tx_status = dma_cookie_status;
 	dma_dev->device_issue_pending = axi_dmac_issue_pending;
@@ -675,6 +723,8 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
+	axi_dmac_detect_caps(dmac);
+
 	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
 
 	ret = dma_async_device_register(dma_dev);
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index b435d8e1e3a1..c53f76eeb4d3 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -136,7 +136,7 @@ struct fsl_edma_desc {
 };
 
 enum edma_version {
-	v1, /* 32ch, Vybdir, mpc57x, etc */
+	v1, /* 32ch, Vybrid, mpc57x, etc */
 	v2, /* 64ch Coldfire */
 };
 
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 75e8a7ba3a22..d641ef85a634 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -144,21 +144,21 @@ fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma
 				fsl_edma_irq_handler, 0, "eDMA", fsl_edma);
 		if (ret) {
 			dev_err(&pdev->dev, "Can't register eDMA IRQ.\n");
-			 return  ret;
+			return ret;
 		}
 	} else {
 		ret = devm_request_irq(&pdev->dev, fsl_edma->txirq,
 				fsl_edma_tx_handler, 0, "eDMA tx", fsl_edma);
 		if (ret) {
 			dev_err(&pdev->dev, "Can't register eDMA tx IRQ.\n");
-			return  ret;
+			return ret;
 		}
 
 		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq,
 				fsl_edma_err_handler, 0, "eDMA err", fsl_edma);
 		if (ret) {
 			dev_err(&pdev->dev, "Can't register eDMA err IRQ.\n");
-			return  ret;
+			return ret;
 		}
 	}
 
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 0baf9797cc09..07fd4f25cdd8 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -19,10 +19,9 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
-#include "idma64.h"
+#include <linux/dma/idma64.h>
 
-/* Platform driver name */
-#define DRV_NAME		"idma64"
+#include "idma64.h"
 
 /* For now we support only two channels */
 #define IDMA64_NR_CHAN		2
@@ -592,7 +591,7 @@ static int idma64_probe(struct idma64_chip *chip)
 	idma64->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	idma64->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
-	idma64->dma.dev = chip->dev;
+	idma64->dma.dev = chip->sysdev;
 
 	dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK);
 
@@ -632,6 +631,7 @@ static int idma64_platform_probe(struct platform_device *pdev)
 {
 	struct idma64_chip *chip;
 	struct device *dev = &pdev->dev;
+	struct device *sysdev = dev->parent;
 	struct resource *mem;
 	int ret;
 
@@ -648,11 +648,12 @@ static int idma64_platform_probe(struct platform_device *pdev)
 	if (IS_ERR(chip->regs))
 		return PTR_ERR(chip->regs);
 
-	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	ret = dma_coerce_mask_and_coherent(sysdev, DMA_BIT_MASK(64));
 	if (ret)
 		return ret;
 
 	chip->dev = dev;
+	chip->sysdev = sysdev;
 
 	ret = idma64_probe(chip);
 	if (ret)
@@ -697,7 +698,7 @@ static struct platform_driver idma64_platform_driver = {
 	.probe		= idma64_platform_probe,
 	.remove		= idma64_platform_remove,
 	.driver = {
-		.name	= DRV_NAME,
+		.name	= LPSS_IDMA64_DRIVER_NAME,
 		.pm	= &idma64_dev_pm_ops,
 	},
 };
@@ -707,4 +708,4 @@ module_platform_driver(idma64_platform_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("iDMA64 core driver");
 MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
-MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_ALIAS("platform:" LPSS_IDMA64_DRIVER_NAME);
diff --git a/drivers/dma/idma64.h b/drivers/dma/idma64.h
index 6b816878e5e7..baa32e1425de 100644
--- a/drivers/dma/idma64.h
+++ b/drivers/dma/idma64.h
@@ -216,12 +216,14 @@ static inline void idma64_writel(struct idma64 *idma64, int offset, u32 value)
 /**
  * struct idma64_chip - representation of iDMA 64-bit controller hardware
  * @dev:		struct device of the DMA controller
+ * @sysdev:		struct device of the physical device that does DMA
  * @irq:		irq line
  * @regs:		memory mapped I/O space
  * @idma64:		struct idma64 that is filed by idma64_probe()
  */
 struct idma64_chip {
 	struct device	*dev;
+	struct device	*sysdev;
 	int		irq;
 	void __iomem	*regs;
 	struct idma64	*idma64;
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 5f3c1378b90e..99d9f431ae2c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -419,6 +419,7 @@ struct sdma_driver_data {
 	int chnenbl0;
 	int num_events;
 	struct sdma_script_start_addrs	*script_addrs;
+	bool check_ratio;
 };
 
 struct sdma_engine {
@@ -557,6 +558,13 @@ static struct sdma_driver_data sdma_imx7d = {
 	.script_addrs = &sdma_script_imx7d,
 };
 
+static struct sdma_driver_data sdma_imx8mq = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx7d,
+	.check_ratio = 1,
+};
+
 static const struct platform_device_id sdma_devtypes[] = {
 	{
 		.name = "imx25-sdma",
@@ -580,6 +588,9 @@ static const struct platform_device_id sdma_devtypes[] = {
 		.name = "imx7d-sdma",
 		.driver_data = (unsigned long)&sdma_imx7d,
 	}, {
+		.name = "imx8mq-sdma",
+		.driver_data = (unsigned long)&sdma_imx8mq,
+	}, {
 		/* sentinel */
 	}
 };
@@ -593,6 +604,7 @@ static const struct of_device_id sdma_dt_ids[] = {
 	{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
 	{ .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, },
 	{ .compatible = "fsl,imx7d-sdma", .data = &sdma_imx7d, },
+	{ .compatible = "fsl,imx8mq-sdma", .data = &sdma_imx8mq, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
@@ -1852,7 +1864,8 @@ static int sdma_init(struct sdma_engine *sdma)
 	if (ret)
 		goto disable_clk_ipg;
 
-	if (clk_get_rate(sdma->clk_ahb) == clk_get_rate(sdma->clk_ipg))
+	if (sdma->drvdata->check_ratio &&
+	    (clk_get_rate(sdma->clk_ahb) == clk_get_rate(sdma->clk_ipg)))
 		sdma->clk_ratio = 1;
 
 	/* Be sure SDMA has not started yet */
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index a67b292190f4..594409a6e975 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -1491,14 +1491,14 @@ MODULE_DEVICE_TABLE(platform, nbpf_ids);
 #ifdef CONFIG_PM
 static int nbpf_runtime_suspend(struct device *dev)
 {
-	struct nbpf_device *nbpf = platform_get_drvdata(to_platform_device(dev));
+	struct nbpf_device *nbpf = dev_get_drvdata(dev);
 	clk_disable_unprepare(nbpf->clk);
 	return 0;
 }
 
 static int nbpf_runtime_resume(struct device *dev)
 {
-	struct nbpf_device *nbpf = platform_get_drvdata(to_platform_device(dev));
+	struct nbpf_device *nbpf = dev_get_drvdata(dev);
 	return clk_prepare_enable(nbpf->clk);
 }
 #endif
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index eec79fdf27a5..6e6837214210 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -11,6 +11,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/init.h>
@@ -966,6 +967,7 @@ static void _stop(struct pl330_thread *thrd)
 {
 	void __iomem *regs = thrd->dmac->base;
 	u8 insn[6] = {0, 0, 0, 0, 0, 0};
+	u32 inten = readl(regs + INTEN);
 
 	if (_state(thrd) == PL330_STATE_FAULT_COMPLETING)
 		UNTIL(thrd, PL330_STATE_FAULTING | PL330_STATE_KILLING);
@@ -978,10 +980,13 @@ static void _stop(struct pl330_thread *thrd)
 
 	_emit_KILL(0, insn);
 
-	/* Stop generating interrupts for SEV */
-	writel(readl(regs + INTEN) & ~(1 << thrd->ev), regs + INTEN);
-
 	_execute_DBGINSN(thrd, insn, is_manager(thrd));
+
+	/* clear the event */
+	if (inten & (1 << thrd->ev))
+		writel(1 << thrd->ev, regs + INTCLR);
+	/* Stop generating interrupts for SEV */
+	writel(inten & ~(1 << thrd->ev), regs + INTEN);
 }
 
 /* Start doing req 'idx' of thread 'thrd' */
@@ -2896,6 +2901,55 @@ static irqreturn_t pl330_irq_handler(int irq, void *data)
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
 	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
 
+#ifdef CONFIG_DEBUG_FS
+static int pl330_debugfs_show(struct seq_file *s, void *data)
+{
+	struct pl330_dmac *pl330 = s->private;
+	int chans, pchs, ch, pr;
+
+	chans = pl330->pcfg.num_chan;
+	pchs = pl330->num_peripherals;
+
+	seq_puts(s, "PL330 physical channels:\n");
+	seq_puts(s, "THREAD:\t\tCHANNEL:\n");
+	seq_puts(s, "--------\t-----\n");
+	for (ch = 0; ch < chans; ch++) {
+		struct pl330_thread *thrd = &pl330->channels[ch];
+		int found = -1;
+
+		for (pr = 0; pr < pchs; pr++) {
+			struct dma_pl330_chan *pch = &pl330->peripherals[pr];
+
+			if (!pch->thread || thrd->id != pch->thread->id)
+				continue;
+
+			found = pr;
+		}
+
+		seq_printf(s, "%d\t\t", thrd->id);
+		if (found == -1)
+			seq_puts(s, "--\n");
+		else
+			seq_printf(s, "%d\n", found);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(pl330_debugfs);
+
+static inline void init_pl330_debugfs(struct pl330_dmac *pl330)
+{
+	debugfs_create_file(dev_name(pl330->ddma.dev),
+			    S_IFREG | 0444, NULL, pl330,
+			    &pl330_debugfs_fops);
+}
+#else
+static inline void init_pl330_debugfs(struct pl330_dmac *pl330)
+{
+}
+#endif
+
 /*
  * Runtime PM callbacks are provided by amba/bus.c driver.
  *
@@ -3082,6 +3136,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(&adev->dev, "unable to set the seg size\n");
 
 
+	init_pl330_debugfs(pl330);
 	dev_info(&adev->dev,
 		"Loaded driver for PL330 DMAC-%x\n", adev->periphid);
 	dev_info(&adev->dev,
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index e2a5398f89b5..33ab1b607e2b 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Renesas R-Car Gen2 DMA Controller Driver
+ * Renesas R-Car Gen2/Gen3 DMA Controller Driver
  *
- * Copyright (C) 2014 Renesas Electronics Inc.
+ * Copyright (C) 2014-2019 Renesas Electronics Inc.
  *
  * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
  */
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index ba239b529fa9..88d9c6c4389f 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -1042,33 +1042,97 @@ static u32 stm32_dma_get_remaining_bytes(struct stm32_dma_chan *chan)
 	return ndtr << width;
 }
 
+/**
+ * stm32_dma_is_current_sg - check that expected sg_req is currently transferred
+ * @chan: dma channel
+ *
+ * This function called when IRQ are disable, checks that the hardware has not
+ * switched on the next transfer in double buffer mode. The test is done by
+ * comparing the next_sg memory address with the hardware related register
+ * (based on CT bit value).
+ *
+ * Returns true if expected current transfer is still running or double
+ * buffer mode is not activated.
+ */
+static bool stm32_dma_is_current_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_smar, id;
+
+	id = chan->id;
+	dma_scr = stm32_dma_read(dmadev, STM32_DMA_SCR(id));
+
+	if (!(dma_scr & STM32_DMA_SCR_DBM))
+		return true;
+
+	sg_req = &chan->desc->sg_req[chan->next_sg];
+
+	if (dma_scr & STM32_DMA_SCR_CT) {
+		dma_smar = stm32_dma_read(dmadev, STM32_DMA_SM0AR(id));
+		return (dma_smar == sg_req->chan_reg.dma_sm0ar);
+	}
+
+	dma_smar = stm32_dma_read(dmadev, STM32_DMA_SM1AR(id));
+
+	return (dma_smar == sg_req->chan_reg.dma_sm1ar);
+}
+
 static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
 				     struct stm32_dma_desc *desc,
 				     u32 next_sg)
 {
 	u32 modulo, burst_size;
-	u32 residue = 0;
+	u32 residue;
+	u32 n_sg = next_sg;
+	struct stm32_dma_sg_req *sg_req = &chan->desc->sg_req[chan->next_sg];
 	int i;
 
 	/*
-	 * In cyclic mode, for the last period, residue = remaining bytes from
-	 * NDTR
+	 * Calculate the residue means compute the descriptors
+	 * information:
+	 * - the sg_req currently transferred
+	 * - the Hardware remaining position in this sg (NDTR bits field).
+	 *
+	 * A race condition may occur if DMA is running in cyclic or double
+	 * buffer mode, since the DMA register are automatically reloaded at end
+	 * of period transfer. The hardware may have switched to the next
+	 * transfer (CT bit updated) just before the position (SxNDTR reg) is
+	 * read.
+	 * In this case the SxNDTR reg could (or not) correspond to the new
+	 * transfer position, and not the expected one.
+	 * The strategy implemented in the stm32 driver is to:
+	 *  - read the SxNDTR register
+	 *  - crosscheck that hardware is still in current transfer.
+	 * In case of switch, we can assume that the DMA is at the beginning of
+	 * the next transfer. So we approximate the residue in consequence, by
+	 * pointing on the beginning of next transfer.
+	 *
+	 * This race condition doesn't apply for none cyclic mode, as double
+	 * buffer is not used. In such situation registers are updated by the
+	 * software.
 	 */
-	if (chan->desc->cyclic && next_sg == 0) {
-		residue = stm32_dma_get_remaining_bytes(chan);
-		goto end;
+
+	residue = stm32_dma_get_remaining_bytes(chan);
+
+	if (!stm32_dma_is_current_sg(chan)) {
+		n_sg++;
+		if (n_sg == chan->desc->num_sgs)
+			n_sg = 0;
+		residue = sg_req->len;
 	}
 
 	/*
-	 * For all other periods in cyclic mode, and in sg mode,
-	 * residue = remaining bytes from NDTR + remaining periods/sg to be
-	 * transferred
+	 * In cyclic mode, for the last period, residue = remaining bytes
+	 * from NDTR,
+	 * else for all other periods in cyclic mode, and in sg mode,
+	 * residue = remaining bytes from NDTR + remaining
+	 * periods/sg to be transferred
 	 */
-	for (i = next_sg; i < desc->num_sgs; i++)
-		residue += desc->sg_req[i].len;
-	residue += stm32_dma_get_remaining_bytes(chan);
+	if (!chan->desc->cyclic || n_sg != 0)
+		for (i = n_sg; i < desc->num_sgs; i++)
+			residue += desc->sg_req[i].len;
 
-end:
 	if (!chan->mem_burst)
 		return residue;
 
@@ -1302,13 +1366,16 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	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);
+		chan->irq = platform_get_irq(pdev, i);
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0)  {
+			if (ret != -EPROBE_DEFER)
+				dev_err(&pdev->dev,
+					"No irq resource for chan %d\n", i);
 			goto err_unregister;
 		}
-		chan->irq = res->start;
+		chan->irq = ret;
+
 		ret = devm_request_irq(&pdev->dev, chan->irq,
 				       stm32_dma_chan_irq, 0,
 				       dev_name(chan2dev(chan)), chan);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 5ec0dd97b397..21f6be16d013 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -22,7 +22,6 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/of_irq.h>
-#include <linux/pm_clock.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
@@ -31,35 +30,33 @@
 #define ADMA_CH_CMD					0x00
 #define ADMA_CH_STATUS					0x0c
 #define ADMA_CH_STATUS_XFER_EN				BIT(0)
+#define ADMA_CH_STATUS_XFER_PAUSED			BIT(1)
 
 #define ADMA_CH_INT_STATUS				0x10
 #define ADMA_CH_INT_STATUS_XFER_DONE			BIT(0)
 
 #define ADMA_CH_INT_CLEAR				0x1c
 #define ADMA_CH_CTRL					0x24
-#define ADMA_CH_CTRL_TX_REQ(val)			(((val) & 0xf) << 28)
-#define ADMA_CH_CTRL_TX_REQ_MAX				10
-#define ADMA_CH_CTRL_RX_REQ(val)			(((val) & 0xf) << 24)
-#define ADMA_CH_CTRL_RX_REQ_MAX				10
 #define ADMA_CH_CTRL_DIR(val)				(((val) & 0xf) << 12)
 #define ADMA_CH_CTRL_DIR_AHUB2MEM			2
 #define ADMA_CH_CTRL_DIR_MEM2AHUB			4
 #define ADMA_CH_CTRL_MODE_CONTINUOUS			(2 << 8)
 #define ADMA_CH_CTRL_FLOWCTRL_EN			BIT(1)
+#define ADMA_CH_CTRL_XFER_PAUSE_SHIFT			0
 
 #define ADMA_CH_CONFIG					0x28
 #define ADMA_CH_CONFIG_SRC_BUF(val)			(((val) & 0x7) << 28)
 #define ADMA_CH_CONFIG_TRG_BUF(val)			(((val) & 0x7) << 24)
-#define ADMA_CH_CONFIG_BURST_SIZE(val)			(((val) & 0x7) << 20)
-#define ADMA_CH_CONFIG_BURST_16				5
+#define ADMA_CH_CONFIG_BURST_SIZE_SHIFT			20
+#define ADMA_CH_CONFIG_MAX_BURST_SIZE                   16
 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val)		((val) & 0xf)
 #define ADMA_CH_CONFIG_MAX_BUFS				8
 
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define ADMA_CH_FIFO_CTRL_OVRFW_THRES(val)		(((val) & 0xf) << 24)
 #define ADMA_CH_FIFO_CTRL_STARV_THRES(val)		(((val) & 0xf) << 16)
-#define ADMA_CH_FIFO_CTRL_TX_SIZE(val)			(((val) & 0xf) << 8)
-#define ADMA_CH_FIFO_CTRL_RX_SIZE(val)			((val) & 0xf)
+#define ADMA_CH_FIFO_CTRL_TX_FIFO_SIZE_SHIFT		8
+#define ADMA_CH_FIFO_CTRL_RX_FIFO_SIZE_SHIFT		0
 
 #define ADMA_CH_LOWER_SRC_ADDR				0x34
 #define ADMA_CH_LOWER_TRG_ADDR				0x3c
@@ -69,25 +66,41 @@
 #define ADMA_CH_XFER_STATUS				0x54
 #define ADMA_CH_XFER_STATUS_COUNT_MASK			0xffff
 
-#define ADMA_GLOBAL_CMD					0xc00
-#define ADMA_GLOBAL_SOFT_RESET				0xc04
-#define ADMA_GLOBAL_INT_CLEAR				0xc20
-#define ADMA_GLOBAL_CTRL				0xc24
+#define ADMA_GLOBAL_CMD					0x00
+#define ADMA_GLOBAL_SOFT_RESET				0x04
 
-#define ADMA_CH_REG_OFFSET(a)				(a * 0x80)
+#define TEGRA_ADMA_BURST_COMPLETE_TIME			20
 
 #define ADMA_CH_FIFO_CTRL_DEFAULT	(ADMA_CH_FIFO_CTRL_OVRFW_THRES(1) | \
-					 ADMA_CH_FIFO_CTRL_STARV_THRES(1) | \
-					 ADMA_CH_FIFO_CTRL_TX_SIZE(3)     | \
-					 ADMA_CH_FIFO_CTRL_RX_SIZE(3))
+					 ADMA_CH_FIFO_CTRL_STARV_THRES(1))
+
+#define ADMA_CH_REG_FIELD_VAL(val, mask, shift)	(((val) & mask) << shift)
+
 struct tegra_adma;
 
 /*
  * struct tegra_adma_chip_data - Tegra chip specific data
+ * @global_reg_offset: Register offset of DMA global register.
+ * @global_int_clear: Register offset of DMA global interrupt clear.
+ * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
+ * @ch_req_rx_shift: Register offset for AHUB receive channel select.
+ * @ch_base_offset: Reister offset of DMA channel registers.
+ * @ch_req_mask: Mask for Tx or Rx channel select.
+ * @ch_req_max: Maximum number of Tx or Rx channels available.
+ * @ch_reg_size: Size of DMA channel register space.
  * @nr_channels: Number of DMA channels available.
  */
 struct tegra_adma_chip_data {
-	int nr_channels;
+	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
+	unsigned int global_reg_offset;
+	unsigned int global_int_clear;
+	unsigned int ch_req_tx_shift;
+	unsigned int ch_req_rx_shift;
+	unsigned int ch_base_offset;
+	unsigned int ch_req_mask;
+	unsigned int ch_req_max;
+	unsigned int ch_reg_size;
+	unsigned int nr_channels;
 };
 
 /*
@@ -99,6 +112,7 @@ struct tegra_adma_chan_regs {
 	unsigned int src_addr;
 	unsigned int trg_addr;
 	unsigned int fifo_ctrl;
+	unsigned int cmd;
 	unsigned int tc;
 };
 
@@ -128,6 +142,7 @@ struct tegra_adma_chan {
 	enum dma_transfer_direction	sreq_dir;
 	unsigned int			sreq_index;
 	bool				sreq_reserved;
+	struct tegra_adma_chan_regs	ch_regs;
 
 	/* Transfer count and position info */
 	unsigned int			tx_buf_count;
@@ -141,6 +156,7 @@ struct tegra_adma {
 	struct dma_device		dma_dev;
 	struct device			*dev;
 	void __iomem			*base_addr;
+	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
 	unsigned long			rx_requests_reserved;
 	unsigned long			tx_requests_reserved;
@@ -148,18 +164,20 @@ struct tegra_adma {
 	/* Used to store global command register state when suspending */
 	unsigned int			global_cmd;
 
+	const struct tegra_adma_chip_data *cdata;
+
 	/* Last member of the structure */
 	struct tegra_adma_chan		channels[0];
 };
 
 static inline void tdma_write(struct tegra_adma *tdma, u32 reg, u32 val)
 {
-	writel(val, tdma->base_addr + reg);
+	writel(val, tdma->base_addr + tdma->cdata->global_reg_offset + reg);
 }
 
 static inline u32 tdma_read(struct tegra_adma *tdma, u32 reg)
 {
-	return readl(tdma->base_addr + reg);
+	return readl(tdma->base_addr + tdma->cdata->global_reg_offset + reg);
 }
 
 static inline void tdma_ch_write(struct tegra_adma_chan *tdc, u32 reg, u32 val)
@@ -209,14 +227,16 @@ static int tegra_adma_init(struct tegra_adma *tdma)
 	int ret;
 
 	/* Clear any interrupts */
-	tdma_write(tdma, ADMA_GLOBAL_INT_CLEAR, 0x1);
+	tdma_write(tdma, tdma->cdata->global_int_clear, 0x1);
 
 	/* Assert soft reset */
 	tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1);
 
 	/* Wait for reset to clear */
 	ret = readx_poll_timeout(readl,
-				 tdma->base_addr + ADMA_GLOBAL_SOFT_RESET,
+				 tdma->base_addr +
+				 tdma->cdata->global_reg_offset +
+				 ADMA_GLOBAL_SOFT_RESET,
 				 status, status == 0, 20, 10000);
 	if (ret)
 		return ret;
@@ -236,13 +256,13 @@ static int tegra_adma_request_alloc(struct tegra_adma_chan *tdc,
 	if (tdc->sreq_reserved)
 		return tdc->sreq_dir == direction ? 0 : -EINVAL;
 
+	if (sreq_index > tdma->cdata->ch_req_max) {
+		dev_err(tdma->dev, "invalid DMA request\n");
+		return -EINVAL;
+	}
+
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
-		if (sreq_index > ADMA_CH_CTRL_TX_REQ_MAX) {
-			dev_err(tdma->dev, "invalid DMA request\n");
-			return -EINVAL;
-		}
-
 		if (test_and_set_bit(sreq_index, &tdma->tx_requests_reserved)) {
 			dev_err(tdma->dev, "DMA request reserved\n");
 			return -EINVAL;
@@ -250,11 +270,6 @@ static int tegra_adma_request_alloc(struct tegra_adma_chan *tdc,
 		break;
 
 	case DMA_DEV_TO_MEM:
-		if (sreq_index > ADMA_CH_CTRL_RX_REQ_MAX) {
-			dev_err(tdma->dev, "invalid DMA request\n");
-			return -EINVAL;
-		}
-
 		if (test_and_set_bit(sreq_index, &tdma->rx_requests_reserved)) {
 			dev_err(tdma->dev, "DMA request reserved\n");
 			return -EINVAL;
@@ -428,6 +443,51 @@ static void tegra_adma_issue_pending(struct dma_chan *dc)
 	spin_unlock_irqrestore(&tdc->vc.lock, flags);
 }
 
+static bool tegra_adma_is_paused(struct tegra_adma_chan *tdc)
+{
+	u32 csts;
+
+	csts = tdma_ch_read(tdc, ADMA_CH_STATUS);
+	csts &= ADMA_CH_STATUS_XFER_PAUSED;
+
+	return csts ? true : false;
+}
+
+static int tegra_adma_pause(struct dma_chan *dc)
+{
+	struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc);
+	struct tegra_adma_desc *desc = tdc->desc;
+	struct tegra_adma_chan_regs *ch_regs = &desc->ch_regs;
+	int dcnt = 10;
+
+	ch_regs->ctrl = tdma_ch_read(tdc, ADMA_CH_CTRL);
+	ch_regs->ctrl |= (1 << ADMA_CH_CTRL_XFER_PAUSE_SHIFT);
+	tdma_ch_write(tdc, ADMA_CH_CTRL, ch_regs->ctrl);
+
+	while (dcnt-- && !tegra_adma_is_paused(tdc))
+		udelay(TEGRA_ADMA_BURST_COMPLETE_TIME);
+
+	if (dcnt < 0) {
+		dev_err(tdc2dev(tdc), "unable to pause DMA channel\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int tegra_adma_resume(struct dma_chan *dc)
+{
+	struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc);
+	struct tegra_adma_desc *desc = tdc->desc;
+	struct tegra_adma_chan_regs *ch_regs = &desc->ch_regs;
+
+	ch_regs->ctrl = tdma_ch_read(tdc, ADMA_CH_CTRL);
+	ch_regs->ctrl &= ~(1 << ADMA_CH_CTRL_XFER_PAUSE_SHIFT);
+	tdma_ch_write(tdc, ADMA_CH_CTRL, ch_regs->ctrl);
+
+	return 0;
+}
+
 static int tegra_adma_terminate_all(struct dma_chan *dc)
 {
 	struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc);
@@ -481,12 +541,29 @@ static enum dma_status tegra_adma_tx_status(struct dma_chan *dc,
 	return ret;
 }
 
+static unsigned int tegra210_adma_get_burst_config(unsigned int burst_size)
+{
+	if (!burst_size || burst_size > ADMA_CH_CONFIG_MAX_BURST_SIZE)
+		burst_size = ADMA_CH_CONFIG_MAX_BURST_SIZE;
+
+	return fls(burst_size) << ADMA_CH_CONFIG_BURST_SIZE_SHIFT;
+}
+
+static unsigned int tegra186_adma_get_burst_config(unsigned int burst_size)
+{
+	if (!burst_size || burst_size > ADMA_CH_CONFIG_MAX_BURST_SIZE)
+		burst_size = ADMA_CH_CONFIG_MAX_BURST_SIZE;
+
+	return (burst_size - 1) << ADMA_CH_CONFIG_BURST_SIZE_SHIFT;
+}
+
 static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 				      struct tegra_adma_desc *desc,
 				      dma_addr_t buf_addr,
 				      enum dma_transfer_direction direction)
 {
 	struct tegra_adma_chan_regs *ch_regs = &desc->ch_regs;
+	const struct tegra_adma_chip_data *cdata = tdc->tdma->cdata;
 	unsigned int burst_size, adma_dir;
 
 	if (desc->num_periods > ADMA_CH_CONFIG_MAX_BUFS)
@@ -495,17 +572,21 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
 		adma_dir = ADMA_CH_CTRL_DIR_MEM2AHUB;
-		burst_size = fls(tdc->sconfig.dst_maxburst);
+		burst_size = tdc->sconfig.dst_maxburst;
 		ch_regs->config = ADMA_CH_CONFIG_SRC_BUF(desc->num_periods - 1);
-		ch_regs->ctrl = ADMA_CH_CTRL_TX_REQ(tdc->sreq_index);
+		ch_regs->ctrl = ADMA_CH_REG_FIELD_VAL(tdc->sreq_index,
+						      cdata->ch_req_mask,
+						      cdata->ch_req_tx_shift);
 		ch_regs->src_addr = buf_addr;
 		break;
 
 	case DMA_DEV_TO_MEM:
 		adma_dir = ADMA_CH_CTRL_DIR_AHUB2MEM;
-		burst_size = fls(tdc->sconfig.src_maxburst);
+		burst_size = tdc->sconfig.src_maxburst;
 		ch_regs->config = ADMA_CH_CONFIG_TRG_BUF(desc->num_periods - 1);
-		ch_regs->ctrl = ADMA_CH_CTRL_RX_REQ(tdc->sreq_index);
+		ch_regs->ctrl = ADMA_CH_REG_FIELD_VAL(tdc->sreq_index,
+						      cdata->ch_req_mask,
+						      cdata->ch_req_rx_shift);
 		ch_regs->trg_addr = buf_addr;
 		break;
 
@@ -514,13 +595,10 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 		return -EINVAL;
 	}
 
-	if (!burst_size || burst_size > ADMA_CH_CONFIG_BURST_16)
-		burst_size = ADMA_CH_CONFIG_BURST_16;
-
 	ch_regs->ctrl |= ADMA_CH_CTRL_DIR(adma_dir) |
 			 ADMA_CH_CTRL_MODE_CONTINUOUS |
 			 ADMA_CH_CTRL_FLOWCTRL_EN;
-	ch_regs->config |= ADMA_CH_CONFIG_BURST_SIZE(burst_size);
+	ch_regs->config |= cdata->adma_get_burst_config(burst_size);
 	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
 	ch_regs->fifo_ctrl = ADMA_CH_FIFO_CTRL_DEFAULT;
 	ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK;
@@ -635,32 +713,99 @@ static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec,
 static int tegra_adma_runtime_suspend(struct device *dev)
 {
 	struct tegra_adma *tdma = dev_get_drvdata(dev);
+	struct tegra_adma_chan_regs *ch_reg;
+	struct tegra_adma_chan *tdc;
+	int i;
 
 	tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD);
+	if (!tdma->global_cmd)
+		goto clk_disable;
+
+	for (i = 0; i < tdma->nr_channels; i++) {
+		tdc = &tdma->channels[i];
+		ch_reg = &tdc->ch_regs;
+		ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
+		/* skip if channel is not active */
+		if (!ch_reg->cmd)
+			continue;
+		ch_reg->tc = tdma_ch_read(tdc, ADMA_CH_TC);
+		ch_reg->src_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_SRC_ADDR);
+		ch_reg->trg_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_TRG_ADDR);
+		ch_reg->ctrl = tdma_ch_read(tdc, ADMA_CH_CTRL);
+		ch_reg->fifo_ctrl = tdma_ch_read(tdc, ADMA_CH_FIFO_CTRL);
+		ch_reg->config = tdma_ch_read(tdc, ADMA_CH_CONFIG);
+	}
+
+clk_disable:
+	clk_disable_unprepare(tdma->ahub_clk);
 
-	return pm_clk_suspend(dev);
+	return 0;
 }
 
 static int tegra_adma_runtime_resume(struct device *dev)
 {
 	struct tegra_adma *tdma = dev_get_drvdata(dev);
-	int ret;
+	struct tegra_adma_chan_regs *ch_reg;
+	struct tegra_adma_chan *tdc;
+	int ret, i;
 
-	ret = pm_clk_resume(dev);
-	if (ret)
+	ret = clk_prepare_enable(tdma->ahub_clk);
+	if (ret) {
+		dev_err(dev, "ahub clk_enable failed: %d\n", ret);
 		return ret;
-
+	}
 	tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd);
 
+	if (!tdma->global_cmd)
+		return 0;
+
+	for (i = 0; i < tdma->nr_channels; i++) {
+		tdc = &tdma->channels[i];
+		ch_reg = &tdc->ch_regs;
+		/* skip if channel was not active earlier */
+		if (!ch_reg->cmd)
+			continue;
+		tdma_ch_write(tdc, ADMA_CH_TC, ch_reg->tc);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR, ch_reg->src_addr);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR, ch_reg->trg_addr);
+		tdma_ch_write(tdc, ADMA_CH_CTRL, ch_reg->ctrl);
+		tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_reg->fifo_ctrl);
+		tdma_ch_write(tdc, ADMA_CH_CONFIG, ch_reg->config);
+		tdma_ch_write(tdc, ADMA_CH_CMD, ch_reg->cmd);
+	}
+
 	return 0;
 }
 
 static const struct tegra_adma_chip_data tegra210_chip_data = {
-	.nr_channels = 22,
+	.adma_get_burst_config  = tegra210_adma_get_burst_config,
+	.global_reg_offset	= 0xc00,
+	.global_int_clear	= 0x20,
+	.ch_req_tx_shift	= 28,
+	.ch_req_rx_shift	= 24,
+	.ch_base_offset		= 0,
+	.ch_req_mask		= 0xf,
+	.ch_req_max		= 10,
+	.ch_reg_size		= 0x80,
+	.nr_channels		= 22,
+};
+
+static const struct tegra_adma_chip_data tegra186_chip_data = {
+	.adma_get_burst_config  = tegra186_adma_get_burst_config,
+	.global_reg_offset	= 0,
+	.global_int_clear	= 0x402c,
+	.ch_req_tx_shift	= 27,
+	.ch_req_rx_shift	= 22,
+	.ch_base_offset		= 0x10000,
+	.ch_req_mask		= 0x1f,
+	.ch_req_max		= 20,
+	.ch_reg_size		= 0x100,
+	.nr_channels		= 32,
 };
 
 static const struct of_device_id tegra_adma_of_match[] = {
 	{ .compatible = "nvidia,tegra210-adma", .data = &tegra210_chip_data },
+	{ .compatible = "nvidia,tegra186-adma", .data = &tegra186_chip_data },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, tegra_adma_of_match);
@@ -685,6 +830,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	tdma->dev = &pdev->dev;
+	tdma->cdata = cdata;
 	tdma->nr_channels = cdata->nr_channels;
 	platform_set_drvdata(pdev, tdma);
 
@@ -693,13 +839,11 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	if (IS_ERR(tdma->base_addr))
 		return PTR_ERR(tdma->base_addr);
 
-	ret = pm_clk_create(&pdev->dev);
-	if (ret)
-		return ret;
-
-	ret = of_pm_clk_add_clk(&pdev->dev, "d_audio");
-	if (ret)
-		goto clk_destroy;
+	tdma->ahub_clk = devm_clk_get(&pdev->dev, "d_audio");
+	if (IS_ERR(tdma->ahub_clk)) {
+		dev_err(&pdev->dev, "Error: Missing ahub controller clock\n");
+		return PTR_ERR(tdma->ahub_clk);
+	}
 
 	pm_runtime_enable(&pdev->dev);
 
@@ -715,7 +859,8 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	for (i = 0; i < tdma->nr_channels; i++) {
 		struct tegra_adma_chan *tdc = &tdma->channels[i];
 
-		tdc->chan_addr = tdma->base_addr + ADMA_CH_REG_OFFSET(i);
+		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
+				 + (cdata->ch_reg_size * i);
 
 		tdc->irq = of_irq_get(pdev->dev.of_node, i);
 		if (tdc->irq <= 0) {
@@ -746,6 +891,8 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	tdma->dma_dev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	tdma->dma_dev.device_pause = tegra_adma_pause;
+	tdma->dma_dev.device_resume = tegra_adma_resume;
 
 	ret = dma_async_device_register(&tdma->dma_dev);
 	if (ret < 0) {
@@ -776,8 +923,6 @@ rpm_put:
 	pm_runtime_put_sync(&pdev->dev);
 rpm_disable:
 	pm_runtime_disable(&pdev->dev);
-clk_destroy:
-	pm_clk_destroy(&pdev->dev);
 
 	return ret;
 }
@@ -787,6 +932,7 @@ static int tegra_adma_remove(struct platform_device *pdev)
 	struct tegra_adma *tdma = platform_get_drvdata(pdev);
 	int i;
 
+	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&tdma->dma_dev);
 
 	for (i = 0; i < tdma->nr_channels; ++i)
@@ -794,22 +940,15 @@ static int tegra_adma_remove(struct platform_device *pdev)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	pm_clk_destroy(&pdev->dev);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int tegra_adma_pm_suspend(struct device *dev)
-{
-	return pm_runtime_suspended(dev) == false;
-}
-#endif
-
 static const struct dev_pm_ops tegra_adma_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra_adma_runtime_suspend,
 			   tegra_adma_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(tegra_adma_pm_suspend, NULL)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra_admac_driver = {
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index eafd6c4b90fe..8d174dc5dccd 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -703,7 +703,7 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 
 	INIT_LIST_HEAD(&ld_completed);
 
-	spin_lock_bh(&chan->lock);
+	spin_lock(&chan->lock);
 
 	/* Clean already completed and acked descriptors */
 	xgene_dma_clean_completed_descriptor(chan);
@@ -772,7 +772,7 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 	 */
 	xgene_chan_xfer_ld_pending(chan);
 
-	spin_unlock_bh(&chan->lock);
+	spin_unlock(&chan->lock);
 
 	/* Run the callback for each descriptor, in order */
 	list_for_each_entry_safe(desc_sw, _desc_sw, &ld_completed, node) {
@@ -797,7 +797,7 @@ static int xgene_dma_alloc_chan_resources(struct dma_chan *dchan)
 		return -ENOMEM;
 	}
 
-	chan_dbg(chan, "Allocate descripto pool\n");
+	chan_dbg(chan, "Allocate descriptor pool\n");
 
 	return 1;
 }