Merge branch 'next' into for-linus

Prepare input updates for 5.3 merge window.

73 files changed, 4603 insertions, 1064 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index de511db021cc..0b1dfb5bf2d9 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -218,6 +218,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config FSL_QDMA
+       tristate "NXP Layerscape qDMA engine support"
+       depends on ARM || ARM64
+       select DMA_ENGINE
+       select DMA_VIRTUAL_CHANNELS
+       select DMA_ENGINE_RAID
+       select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+       help
+         Support the NXP Layerscape qDMA engine with command queue and legacy mode.
+         Channel virtualization is supported through enqueuing of DMA jobs to,
+         or dequeuing DMA jobs from, different work queues.
+         This module can be found on NXP Layerscape SoCs.
+	  The qdma driver only work on  SoCs with a DPAA hardware block.
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH
@@ -587,6 +601,17 @@ config TIMB_DMA
 	help
 	  Enable support for the Timberdale FPGA DMA engine.
 
+config UNIPHIER_MDMAC
+	tristate "UniPhier MIO DMAC"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the MIO DMAC (Media I/O DMA controller) on the
+	  UniPhier platform.  This DMA controller is used as the external
+	  DMA engine of the SD/eMMC controllers of the LD4, Pro4, sLD8 SoCs.
+
 config XGENE_DMA
 	tristate "APM X-Gene DMA support"
 	depends on ARCH_XGENE || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 7fcc4d8e336d..6126e1c3a875 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
 obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
@@ -70,6 +71,7 @@ obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
 obj-$(CONFIG_TEGRA210_ADMA) += tegra210-adma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
+obj-$(CONFIG_UNIPHIER_MDMAC) += uniphier-mdmac.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx_dma.o
 obj-$(CONFIG_ST_FDMA) += st_fdma.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 97483df1f82e..fc8c2bab563c 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -2505,24 +2505,14 @@ static int pl08x_debugfs_show(struct seq_file *s, void *data)
 	return 0;
 }
 
-static int pl08x_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, pl08x_debugfs_show, inode->i_private);
-}
-
-static const struct file_operations pl08x_debugfs_operations = {
-	.open		= pl08x_debugfs_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(pl08x_debugfs);
 
 static void init_pl08x_debugfs(struct pl08x_driver_data *pl08x)
 {
 	/* Expose a simple debugfs interface to view all clocks */
 	(void) debugfs_create_file(dev_name(&pl08x->adev->dev),
 			S_IFREG | S_IRUGO, NULL, pl08x,
-			&pl08x_debugfs_operations);
+			&pl08x_debugfs_fops);
 }
 
 #else
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 01d936c9fe89..a0a9cd76c1d4 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -134,7 +134,6 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 	struct at_desc *ret = NULL;
 	unsigned long flags;
 	unsigned int i = 0;
-	LIST_HEAD(tmp_list);
 
 	spin_lock_irqsave(&atchan->lock, flags);
 	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
@@ -1387,8 +1386,6 @@ static int atc_pause(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	spin_lock_irqsave(&atchan->lock, flags);
@@ -1408,8 +1405,6 @@ static int atc_resume(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	if (!atc_chan_is_paused(atchan))
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 4e557684f792..fe69dccfa0c0 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -203,6 +203,7 @@ struct at_xdmac_chan {
 	u32				save_cim;
 	u32				save_cnda;
 	u32				save_cndc;
+	u32				irq_status;
 	unsigned long			status;
 	struct tasklet_struct		tasklet;
 	struct dma_slave_config		sconfig;
@@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data)
 	struct at_xdmac_desc	*desc;
 	u32			error_mask;
 
-	dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n",
-		 __func__, atchan->status);
+	dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n",
+		__func__, atchan->irq_status);
 
 	error_mask = AT_XDMAC_CIS_RBEIS
 		     | AT_XDMAC_CIS_WBEIS
@@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data)
 
 	if (at_xdmac_chan_is_cyclic(atchan)) {
 		at_xdmac_handle_cyclic(atchan);
-	} else if ((atchan->status & AT_XDMAC_CIS_LIS)
-		   || (atchan->status & error_mask)) {
+	} else if ((atchan->irq_status & AT_XDMAC_CIS_LIS)
+		   || (atchan->irq_status & error_mask)) {
 		struct dma_async_tx_descriptor  *txd;
 
-		if (atchan->status & AT_XDMAC_CIS_RBEIS)
+		if (atchan->irq_status & AT_XDMAC_CIS_RBEIS)
 			dev_err(chan2dev(&atchan->chan), "read bus error!!!");
-		if (atchan->status & AT_XDMAC_CIS_WBEIS)
+		if (atchan->irq_status & AT_XDMAC_CIS_WBEIS)
 			dev_err(chan2dev(&atchan->chan), "write bus error!!!");
-		if (atchan->status & AT_XDMAC_CIS_ROIS)
+		if (atchan->irq_status & AT_XDMAC_CIS_ROIS)
 			dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
 
 		spin_lock(&atchan->lock);
@@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
 			atchan = &atxdmac->chan[i];
 			chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM);
 			chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS);
-			atchan->status = chan_status & chan_imr;
+			atchan->irq_status = chan_status & chan_imr;
 			dev_vdbg(atxdmac->dma.dev,
 				 "%s: chan%d: imr=0x%x, status=0x%x\n",
 				 __func__, i, chan_imr, chan_status);
@@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
 				 at_xdmac_chan_read(atchan, AT_XDMAC_CDA),
 				 at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));
 
-			if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS))
+			if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS))
 				at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
 
 			tasklet_schedule(&atchan->tasklet);
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index cad55ab80d41..54093ffd0aef 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -1,9 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * BCM2835 DMA engine support
  *
- * This driver only supports cyclic DMA transfers
- * as needed for the I2S module.
- *
  * Author:      Florian Meier <florian.meier@koalo.de>
  *              Copyright 2013
  *
@@ -18,16 +16,6 @@
  *
  *	MARVELL MMP Peripheral DMA Driver
  *	Copyright 2012 Marvell International Ltd.
- *
- * This program 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
@@ -51,7 +39,6 @@
 
 struct bcm2835_dmadev {
 	struct dma_device ddev;
-	spinlock_t lock;
 	void __iomem *base;
 	struct device_dma_parameters dma_parms;
 };
@@ -73,7 +60,6 @@ struct bcm2835_cb_entry {
 
 struct bcm2835_chan {
 	struct virt_dma_chan vc;
-	struct list_head node;
 
 	struct dma_slave_config	cfg;
 	unsigned int dreq;
@@ -321,8 +307,7 @@ static struct bcm2835_desc *bcm2835_dma_create_cb_chain(
 		return NULL;
 
 	/* allocate and setup the descriptor. */
-	d = kzalloc(sizeof(*d) + frames * sizeof(struct bcm2835_cb_entry),
-		    gfp);
+	d = kzalloc(struct_size(d, cb_list, frames), gfp);
 	if (!d)
 		return NULL;
 
@@ -415,39 +400,32 @@ static void bcm2835_dma_fill_cb_chain_with_sg(
 	}
 }
 
-static int bcm2835_dma_abort(void __iomem *chan_base)
+static void bcm2835_dma_abort(struct bcm2835_chan *c)
 {
-	unsigned long cs;
+	void __iomem *chan_base = c->chan_base;
 	long int timeout = 10000;
 
-	cs = readl(chan_base + BCM2835_DMA_CS);
-	if (!(cs & BCM2835_DMA_ACTIVE))
-		return 0;
+	/*
+	 * A zero control block address means the channel is idle.
+	 * (The ACTIVE flag in the CS register is not a reliable indicator.)
+	 */
+	if (!readl(chan_base + BCM2835_DMA_ADDR))
+		return;
 
 	/* Write 0 to the active bit - Pause the DMA */
 	writel(0, chan_base + BCM2835_DMA_CS);
 
 	/* Wait for any current AXI transfer to complete */
-	while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) {
+	while ((readl(chan_base + BCM2835_DMA_CS) &
+		BCM2835_DMA_WAITING_FOR_WRITES) && --timeout)
 		cpu_relax();
-		cs = readl(chan_base + BCM2835_DMA_CS);
-	}
 
-	/* We'll un-pause when we set of our next DMA */
+	/* Peripheral might be stuck and fail to signal AXI write responses */
 	if (!timeout)
-		return -ETIMEDOUT;
-
-	if (!(cs & BCM2835_DMA_ACTIVE))
-		return 0;
-
-	/* Terminate the control block chain */
-	writel(0, chan_base + BCM2835_DMA_NEXTCB);
+		dev_err(c->vc.chan.device->dev,
+			"failed to complete outstanding writes\n");
 
-	/* Abort the whole DMA */
-	writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE,
-	       chan_base + BCM2835_DMA_CS);
-
-	return 0;
+	writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS);
 }
 
 static void bcm2835_dma_start_desc(struct bcm2835_chan *c)
@@ -485,8 +463,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data)
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 
-	/* Acknowledge interrupt */
-	writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS);
+	/*
+	 * Clear the INT flag to receive further interrupts. Keep the channel
+	 * active in case the descriptor is cyclic or in case the client has
+	 * already terminated the descriptor and issued a new one. (May happen
+	 * if this IRQ handler is threaded.) If the channel is finished, it
+	 * will remain idle despite the ACTIVE flag being set.
+	 */
+	writel(BCM2835_DMA_INT | BCM2835_DMA_ACTIVE,
+	       c->chan_base + BCM2835_DMA_CS);
 
 	d = c->desc;
 
@@ -494,11 +479,7 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data)
 		if (d->cyclic) {
 			/* call the cyclic callback */
 			vchan_cyclic_callback(&d->vd);
-
-			/* Keep the DMA engine running */
-			writel(BCM2835_DMA_ACTIVE,
-			       c->chan_base + BCM2835_DMA_CS);
-		} else {
+		} else if (!readl(c->chan_base + BCM2835_DMA_ADDR)) {
 			vchan_cookie_complete(&c->desc->vd);
 			bcm2835_dma_start_desc(c);
 		}
@@ -516,8 +497,12 @@ static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	dev_dbg(dev, "Allocating DMA channel %d\n", c->ch);
 
+	/*
+	 * Control blocks are 256 bit in length and must start at a 256 bit
+	 * (32 byte) aligned address (BCM2835 ARM Peripherals, sec. 4.2.1.1).
+	 */
 	c->cb_pool = dma_pool_create(dev_name(dev), dev,
-				     sizeof(struct bcm2835_dma_cb), 0, 0);
+				     sizeof(struct bcm2835_dma_cb), 32, 0);
 	if (!c->cb_pool) {
 		dev_err(dev, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
@@ -686,7 +671,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_slave_sg(
 	d = bcm2835_dma_create_cb_chain(chan, direction, false,
 					info, extra,
 					frames, src, dst, 0, 0,
-					GFP_KERNEL);
+					GFP_NOWAIT);
 	if (!d)
 		return NULL;
 
@@ -786,39 +771,16 @@ static int bcm2835_dma_slave_config(struct dma_chan *chan,
 static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
-	struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device);
 	unsigned long flags;
-	int timeout = 10000;
 	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 bcm_dma_abort() returns (even if it does, it will see
-	 * c->desc is NULL and exit.)
-	 */
+	/* stop DMA activity */
 	if (c->desc) {
 		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
-		bcm2835_dma_abort(c->chan_base);
-
-		/* Wait for stopping */
-		while (--timeout) {
-			if (!(readl(c->chan_base + BCM2835_DMA_CS) &
-						BCM2835_DMA_ACTIVE))
-				break;
-
-			cpu_relax();
-		}
-
-		if (!timeout)
-			dev_err(d->ddev.dev, "DMA transfer could not be terminated\n");
+		bcm2835_dma_abort(c);
 	}
 
 	vchan_get_all_descriptors(&c->vc, &head);
@@ -846,7 +808,6 @@ static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id,
 
 	c->vc.desc_free = bcm2835_dma_desc_free;
 	vchan_init(&c->vc, &d->ddev);
-	INIT_LIST_HEAD(&c->node);
 
 	c->chan_base = BCM2835_DMA_CHANIO(d->base, chan_id);
 	c->ch = chan_id;
@@ -949,7 +910,6 @@ static int bcm2835_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);
-	spin_lock_init(&od->lock);
 
 	platform_set_drvdata(pdev, od);
 
@@ -1056,4 +1016,4 @@ module_platform_driver(bcm2835_dma_driver);
 MODULE_ALIAS("platform:bcm2835-dma");
 MODULE_DESCRIPTION("BCM2835 DMA engine driver");
 MODULE_AUTHOR("Florian Meier <florian.meier@koalo.de>");
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index eebaba3d9e78..b69d66e44052 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1802,13 +1802,10 @@ static struct dma_chan *coh901318_xlate(struct of_phandle_args *dma_spec,
 static int coh901318_config(struct coh901318_chan *cohc,
 			    struct coh901318_params *param)
 {
-	unsigned long flags;
 	const struct coh901318_params *p;
 	int channel = cohc->id;
 	void __iomem *virtbase = cohc->base->virtbase;
 
-	spin_lock_irqsave(&cohc->lock, flags);
-
 	if (param)
 		p = param;
 	else
@@ -1828,8 +1825,6 @@ static int coh901318_config(struct coh901318_chan *cohc,
 	coh901318_set_conf(cohc, p->config);
 	coh901318_set_ctrl(cohc, p->ctrl_lli_last);
 
-	spin_unlock_irqrestore(&cohc->lock, flags);
-
 	return 0;
 }
 
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 15b2453d2647..ffc0adc2f6ce 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -367,8 +367,7 @@ static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
 	struct axi_dmac_desc *desc;
 	unsigned int i;
 
-	desc = kzalloc(sizeof(struct axi_dmac_desc) +
-		sizeof(struct axi_dmac_sg) * num_sgs, GFP_NOWAIT);
+	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index a8b6225faa12..9ce0a386225b 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -838,9 +838,8 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	if (!soc_data)
 		return -EINVAL;
 
-	jzdma = devm_kzalloc(dev, sizeof(*jzdma)
-				+ sizeof(*jzdma->chan) * soc_data->nb_channels,
-				GFP_KERNEL);
+	jzdma = devm_kzalloc(dev, struct_size(jzdma, chan,
+			     soc_data->nb_channels), GFP_KERNEL);
 	if (!jzdma)
 		return -ENOMEM;
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index f1a441ab395d..3a11b1092e80 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -63,6 +63,7 @@
 #include <linux/acpi_dma.h>
 #include <linux/of_dma.h>
 #include <linux/mempool.h>
+#include <linux/numa.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDA(dma_ida);
@@ -386,7 +387,8 @@ EXPORT_SYMBOL(dma_issue_pending_all);
 static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
 {
 	int node = dev_to_node(chan->device->dev);
-	return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node));
+	return node == NUMA_NO_NODE ||
+		cpumask_test_cpu(cpu, cpumask_of_node(node));
 }
 
 /**
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index aa1712beb0cc..b96814a7dceb 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -27,11 +27,6 @@ static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
 
-static char test_channel[20];
-module_param_string(channel, test_channel, sizeof(test_channel),
-		S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(channel, "Bus ID of the channel to test (default: any)");
-
 static char test_device[32];
 module_param_string(device, test_device, sizeof(test_device),
 		S_IRUGO | S_IWUSR);
@@ -84,6 +79,14 @@ static bool verbose;
 module_param(verbose, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
 
+static int alignment = -1;
+module_param(alignment, int, 0644);
+MODULE_PARM_DESC(alignment, "Custom data address alignment taken as 2^(alignment) (default: not used (-1))");
+
+static unsigned int transfer_size;
+module_param(transfer_size, uint, 0644);
+MODULE_PARM_DESC(transfer_size, "Optional custom transfer size in bytes (default: not used (0))");
+
 /**
  * struct dmatest_params - test parameters.
  * @buf_size:		size of the memcpy test buffer
@@ -108,6 +111,8 @@ struct dmatest_params {
 	int		timeout;
 	bool		noverify;
 	bool		norandom;
+	int		alignment;
+	unsigned int	transfer_size;
 };
 
 /**
@@ -139,6 +144,28 @@ static bool dmatest_run;
 module_param_cb(run, &run_ops, &dmatest_run, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(run, "Run the test (default: false)");
 
+static int dmatest_chan_set(const char *val, const struct kernel_param *kp);
+static int dmatest_chan_get(char *val, const struct kernel_param *kp);
+static const struct kernel_param_ops multi_chan_ops = {
+	.set = dmatest_chan_set,
+	.get = dmatest_chan_get,
+};
+
+static char test_channel[20];
+static struct kparam_string newchan_kps = {
+	.string = test_channel,
+	.maxlen = 20,
+};
+module_param_cb(channel, &multi_chan_ops, &newchan_kps, 0644);
+MODULE_PARM_DESC(channel, "Bus ID of the channel to test (default: any)");
+
+static int dmatest_test_list_get(char *val, const struct kernel_param *kp);
+static const struct kernel_param_ops test_list_ops = {
+	.get = dmatest_test_list_get,
+};
+module_param_cb(test_list, &test_list_ops, NULL, 0444);
+MODULE_PARM_DESC(test_list, "Print current test list");
+
 /* Maximum amount of mismatched bytes in buffer to print */
 #define MAX_ERROR_COUNT		32
 
@@ -160,25 +187,38 @@ MODULE_PARM_DESC(run, "Run the test (default: false)");
 #define PATTERN_COUNT_MASK	0x1f
 #define PATTERN_MEMSET_IDX	0x01
 
+/* Fixed point arithmetic ops */
+#define FIXPT_SHIFT		8
+#define FIXPNT_MASK		0xFF
+#define FIXPT_TO_INT(a)	((a) >> FIXPT_SHIFT)
+#define INT_TO_FIXPT(a)	((a) << FIXPT_SHIFT)
+#define FIXPT_GET_FRAC(a)	((((a) & FIXPNT_MASK) * 100) >> FIXPT_SHIFT)
+
 /* poor man's completion - we want to use wait_event_freezable() on it */
 struct dmatest_done {
 	bool			done;
 	wait_queue_head_t	*wait;
 };
 
+struct dmatest_data {
+	u8		**raw;
+	u8		**aligned;
+	unsigned int	cnt;
+	unsigned int	off;
+};
+
 struct dmatest_thread {
 	struct list_head	node;
 	struct dmatest_info	*info;
 	struct task_struct	*task;
 	struct dma_chan		*chan;
-	u8			**srcs;
-	u8			**usrcs;
-	u8			**dsts;
-	u8			**udsts;
+	struct dmatest_data	src;
+	struct dmatest_data	dst;
 	enum dma_transaction_type type;
 	wait_queue_head_t done_wait;
 	struct dmatest_done test_done;
 	bool			done;
+	bool			pending;
 };
 
 struct dmatest_chan {
@@ -206,6 +246,22 @@ static bool is_threaded_test_run(struct dmatest_info *info)
 	return false;
 }
 
+static bool is_threaded_test_pending(struct dmatest_info *info)
+{
+	struct dmatest_chan *dtc;
+
+	list_for_each_entry(dtc, &info->channels, node) {
+		struct dmatest_thread *thread;
+
+		list_for_each_entry(thread, &dtc->threads, node) {
+			if (thread->pending)
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static int dmatest_wait_get(char *val, const struct kernel_param *kp)
 {
 	struct dmatest_info *info = &test_info;
@@ -419,13 +475,62 @@ static unsigned long long dmatest_persec(s64 runtime, unsigned int val)
 	}
 
 	per_sec *= val;
+	per_sec = INT_TO_FIXPT(per_sec);
 	do_div(per_sec, runtime);
+
 	return per_sec;
 }
 
 static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
 {
-	return dmatest_persec(runtime, len >> 10);
+	return FIXPT_TO_INT(dmatest_persec(runtime, len >> 10));
+}
+
+static void __dmatest_free_test_data(struct dmatest_data *d, unsigned int cnt)
+{
+	unsigned int i;
+
+	for (i = 0; i < cnt; i++)
+		kfree(d->raw[i]);
+
+	kfree(d->aligned);
+	kfree(d->raw);
+}
+
+static void dmatest_free_test_data(struct dmatest_data *d)
+{
+	__dmatest_free_test_data(d, d->cnt);
+}
+
+static int dmatest_alloc_test_data(struct dmatest_data *d,
+		unsigned int buf_size, u8 align)
+{
+	unsigned int i = 0;
+
+	d->raw = kcalloc(d->cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!d->raw)
+		return -ENOMEM;
+
+	d->aligned = kcalloc(d->cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!d->aligned)
+		goto err;
+
+	for (i = 0; i < d->cnt; i++) {
+		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		if (!d->raw[i])
+			goto err;
+
+		/* align to alignment restriction */
+		if (align)
+			d->aligned[i] = PTR_ALIGN(d->raw[i], align);
+		else
+			d->aligned[i] = d->raw[i];
+	}
+
+	return 0;
+err:
+	__dmatest_free_test_data(d, i);
+	return -ENOMEM;
 }
 
 /*
@@ -458,14 +563,16 @@ static int dmatest_func(void *data)
 	enum dma_ctrl_flags 	flags;
 	u8			*pq_coefs = NULL;
 	int			ret;
-	int			src_cnt;
-	int			dst_cnt;
+	unsigned int 		buf_size;
+	struct dmatest_data	*src;
+	struct dmatest_data	*dst;
 	int			i;
 	ktime_t			ktime, start, diff;
 	ktime_t			filltime = 0;
 	ktime_t			comparetime = 0;
 	s64			runtime = 0;
 	unsigned long long	total_len = 0;
+	unsigned long long	iops = 0;
 	u8			align = 0;
 	bool			is_memset = false;
 	dma_addr_t		*srcs;
@@ -476,88 +583,71 @@ static int dmatest_func(void *data)
 	ret = -ENOMEM;
 
 	smp_rmb();
+	thread->pending = false;
 	info = thread->info;
 	params = &info->params;
 	chan = thread->chan;
 	dev = chan->device;
+	src = &thread->src;
+	dst = &thread->dst;
 	if (thread->type == DMA_MEMCPY) {
-		align = dev->copy_align;
-		src_cnt = dst_cnt = 1;
+		align = params->alignment < 0 ? dev->copy_align :
+						params->alignment;
+		src->cnt = dst->cnt = 1;
 	} else if (thread->type == DMA_MEMSET) {
-		align = dev->fill_align;
-		src_cnt = dst_cnt = 1;
+		align = params->alignment < 0 ? dev->fill_align :
+						params->alignment;
+		src->cnt = dst->cnt = 1;
 		is_memset = true;
 	} else if (thread->type == DMA_XOR) {
 		/* force odd to ensure dst = src */
-		src_cnt = min_odd(params->xor_sources | 1, dev->max_xor);
-		dst_cnt = 1;
-		align = dev->xor_align;
+		src->cnt = min_odd(params->xor_sources | 1, dev->max_xor);
+		dst->cnt = 1;
+		align = params->alignment < 0 ? dev->xor_align :
+						params->alignment;
 	} else if (thread->type == DMA_PQ) {
 		/* force odd to ensure dst = src */
-		src_cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
-		dst_cnt = 2;
-		align = dev->pq_align;
+		src->cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
+		dst->cnt = 2;
+		align = params->alignment < 0 ? dev->pq_align :
+						params->alignment;
 
 		pq_coefs = kmalloc(params->pq_sources + 1, GFP_KERNEL);
 		if (!pq_coefs)
 			goto err_thread_type;
 
-		for (i = 0; i < src_cnt; i++)
+		for (i = 0; i < src->cnt; i++)
 			pq_coefs[i] = 1;
 	} else
 		goto err_thread_type;
 
-	thread->srcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->srcs)
-		goto err_srcs;
-
-	thread->usrcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->usrcs)
-		goto err_usrcs;
-
-	for (i = 0; i < src_cnt; i++) {
-		thread->usrcs[i] = kmalloc(params->buf_size + align,
-					   GFP_KERNEL);
-		if (!thread->usrcs[i])
-			goto err_srcbuf;
-
-		/* align srcs to alignment restriction */
-		if (align)
-			thread->srcs[i] = PTR_ALIGN(thread->usrcs[i], align);
-		else
-			thread->srcs[i] = thread->usrcs[i];
+	/* Check if buffer count fits into map count variable (u8) */
+	if ((src->cnt + dst->cnt) >= 255) {
+		pr_err("too many buffers (%d of 255 supported)\n",
+		       src->cnt + dst->cnt);
+		goto err_free_coefs;
 	}
-	thread->srcs[i] = NULL;
 
-	thread->dsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->dsts)
-		goto err_dsts;
-
-	thread->udsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->udsts)
-		goto err_udsts;
+	buf_size = params->buf_size;
+	if (1 << align > buf_size) {
+		pr_err("%u-byte buffer too small for %d-byte alignment\n",
+		       buf_size, 1 << align);
+		goto err_free_coefs;
+	}
 
-	for (i = 0; i < dst_cnt; i++) {
-		thread->udsts[i] = kmalloc(params->buf_size + align,
-					   GFP_KERNEL);
-		if (!thread->udsts[i])
-			goto err_dstbuf;
+	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
+		goto err_free_coefs;
 
-		/* align dsts to alignment restriction */
-		if (align)
-			thread->dsts[i] = PTR_ALIGN(thread->udsts[i], align);
-		else
-			thread->dsts[i] = thread->udsts[i];
-	}
-	thread->dsts[i] = NULL;
+	if (dmatest_alloc_test_data(dst, buf_size, align) < 0)
+		goto err_src;
 
 	set_user_nice(current, 10);
 
-	srcs = kcalloc(src_cnt, sizeof(dma_addr_t), GFP_KERNEL);
+	srcs = kcalloc(src->cnt, sizeof(dma_addr_t), GFP_KERNEL);
 	if (!srcs)
-		goto err_dstbuf;
+		goto err_dst;
 
-	dma_pq = kcalloc(dst_cnt, sizeof(dma_addr_t), GFP_KERNEL);
+	dma_pq = kcalloc(dst->cnt, sizeof(dma_addr_t), GFP_KERNEL);
 	if (!dma_pq)
 		goto err_srcs_array;
 
@@ -572,88 +662,83 @@ static int dmatest_func(void *data)
 		struct dma_async_tx_descriptor *tx = NULL;
 		struct dmaengine_unmap_data *um;
 		dma_addr_t *dsts;
-		unsigned int src_off, dst_off, len;
+		unsigned int len;
 
 		total_tests++;
 
-		/* Check if buffer count fits into map count variable (u8) */
-		if ((src_cnt + dst_cnt) >= 255) {
-			pr_err("too many buffers (%d of 255 supported)\n",
-			       src_cnt + dst_cnt);
-			break;
+		if (params->transfer_size) {
+			if (params->transfer_size >= buf_size) {
+				pr_err("%u-byte transfer size must be lower than %u-buffer size\n",
+				       params->transfer_size, buf_size);
+				break;
+			}
+			len = params->transfer_size;
+		} else if (params->norandom) {
+			len = buf_size;
+		} else {
+			len = dmatest_random() % buf_size + 1;
 		}
 
-		if (1 << align > params->buf_size) {
-			pr_err("%u-byte buffer too small for %d-byte alignment\n",
-			       params->buf_size, 1 << align);
-			break;
+		/* Do not alter transfer size explicitly defined by user */
+		if (!params->transfer_size) {
+			len = (len >> align) << align;
+			if (!len)
+				len = 1 << align;
 		}
-
-		if (params->norandom)
-			len = params->buf_size;
-		else
-			len = dmatest_random() % params->buf_size + 1;
-
-		len = (len >> align) << align;
-		if (!len)
-			len = 1 << align;
-
 		total_len += len;
 
 		if (params->norandom) {
-			src_off = 0;
-			dst_off = 0;
+			src->off = 0;
+			dst->off = 0;
 		} else {
-			src_off = dmatest_random() % (params->buf_size - len + 1);
-			dst_off = dmatest_random() % (params->buf_size - len + 1);
+			src->off = dmatest_random() % (buf_size - len + 1);
+			dst->off = dmatest_random() % (buf_size - len + 1);
 
-			src_off = (src_off >> align) << align;
-			dst_off = (dst_off >> align) << align;
+			src->off = (src->off >> align) << align;
+			dst->off = (dst->off >> align) << align;
 		}
 
 		if (!params->noverify) {
 			start = ktime_get();
-			dmatest_init_srcs(thread->srcs, src_off, len,
-					  params->buf_size, is_memset);
-			dmatest_init_dsts(thread->dsts, dst_off, len,
-					  params->buf_size, is_memset);
+			dmatest_init_srcs(src->aligned, src->off, len,
+					  buf_size, is_memset);
+			dmatest_init_dsts(dst->aligned, dst->off, len,
+					  buf_size, is_memset);
 
 			diff = ktime_sub(ktime_get(), start);
 			filltime = ktime_add(filltime, diff);
 		}
 
-		um = dmaengine_get_unmap_data(dev->dev, src_cnt + dst_cnt,
+		um = dmaengine_get_unmap_data(dev->dev, src->cnt + dst->cnt,
 					      GFP_KERNEL);
 		if (!um) {
 			failed_tests++;
 			result("unmap data NULL", total_tests,
-			       src_off, dst_off, len, ret);
+			       src->off, dst->off, len, ret);
 			continue;
 		}
 
-		um->len = params->buf_size;
-		for (i = 0; i < src_cnt; i++) {
-			void *buf = thread->srcs[i];
+		um->len = buf_size;
+		for (i = 0; i < src->cnt; i++) {
+			void *buf = src->aligned[i];
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
 			um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
 						   um->len, DMA_TO_DEVICE);
-			srcs[i] = um->addr[i] + src_off;
+			srcs[i] = um->addr[i] + src->off;
 			ret = dma_mapping_error(dev->dev, um->addr[i]);
 			if (ret) {
-				dmaengine_unmap_put(um);
 				result("src mapping error", total_tests,
-				       src_off, dst_off, len, ret);
-				failed_tests++;
-				continue;
+				       src->off, dst->off, len, ret);
+				goto error_unmap_continue;
 			}
 			um->to_cnt++;
 		}
 		/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
-		dsts = &um->addr[src_cnt];
-		for (i = 0; i < dst_cnt; i++) {
-			void *buf = thread->dsts[i];
+		dsts = &um->addr[src->cnt];
+		for (i = 0; i < dst->cnt; i++) {
+			void *buf = dst->aligned[i];
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
@@ -661,44 +746,40 @@ static int dmatest_func(void *data)
 					       DMA_BIDIRECTIONAL);
 			ret = dma_mapping_error(dev->dev, dsts[i]);
 			if (ret) {
-				dmaengine_unmap_put(um);
 				result("dst mapping error", total_tests,
-				       src_off, dst_off, len, ret);
-				failed_tests++;
-				continue;
+				       src->off, dst->off, len, ret);
+				goto error_unmap_continue;
 			}
 			um->bidi_cnt++;
 		}
 
 		if (thread->type == DMA_MEMCPY)
 			tx = dev->device_prep_dma_memcpy(chan,
-							 dsts[0] + dst_off,
+							 dsts[0] + dst->off,
 							 srcs[0], len, flags);
 		else if (thread->type == DMA_MEMSET)
 			tx = dev->device_prep_dma_memset(chan,
-						dsts[0] + dst_off,
-						*(thread->srcs[0] + src_off),
+						dsts[0] + dst->off,
+						*(src->aligned[0] + src->off),
 						len, flags);
 		else if (thread->type == DMA_XOR)
 			tx = dev->device_prep_dma_xor(chan,
-						      dsts[0] + dst_off,
-						      srcs, src_cnt,
+						      dsts[0] + dst->off,
+						      srcs, src->cnt,
 						      len, flags);
 		else if (thread->type == DMA_PQ) {
-			for (i = 0; i < dst_cnt; i++)
-				dma_pq[i] = dsts[i] + dst_off;
+			for (i = 0; i < dst->cnt; i++)
+				dma_pq[i] = dsts[i] + dst->off;
 			tx = dev->device_prep_dma_pq(chan, dma_pq, srcs,
-						     src_cnt, pq_coefs,
+						     src->cnt, pq_coefs,
 						     len, flags);
 		}
 
 		if (!tx) {
-			dmaengine_unmap_put(um);
-			result("prep error", total_tests, src_off,
-			       dst_off, len, ret);
+			result("prep error", total_tests, src->off,
+			       dst->off, len, ret);
 			msleep(100);
-			failed_tests++;
-			continue;
+			goto error_unmap_continue;
 		}
 
 		done->done = false;
@@ -707,12 +788,10 @@ static int dmatest_func(void *data)
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
-			dmaengine_unmap_put(um);
-			result("submit error", total_tests, src_off,
-			       dst_off, len, ret);
+			result("submit error", total_tests, src->off,
+			       dst->off, len, ret);
 			msleep(100);
-			failed_tests++;
-			continue;
+			goto error_unmap_continue;
 		}
 		dma_async_issue_pending(chan);
 
@@ -722,63 +801,65 @@ static int dmatest_func(void *data)
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
 		if (!done->done) {
-			dmaengine_unmap_put(um);
-			result("test timed out", total_tests, src_off, dst_off,
+			result("test timed out", total_tests, src->off, dst->off,
 			       len, 0);
-			failed_tests++;
-			continue;
+			goto error_unmap_continue;
 		} else if (status != DMA_COMPLETE) {
-			dmaengine_unmap_put(um);
 			result(status == DMA_ERROR ?
 			       "completion error status" :
-			       "completion busy status", total_tests, src_off,
-			       dst_off, len, ret);
-			failed_tests++;
-			continue;
+			       "completion busy status", total_tests, src->off,
+			       dst->off, len, ret);
+			goto error_unmap_continue;
 		}
 
 		dmaengine_unmap_put(um);
 
 		if (params->noverify) {
-			verbose_result("test passed", total_tests, src_off,
-				       dst_off, len, 0);
+			verbose_result("test passed", total_tests, src->off,
+				       dst->off, len, 0);
 			continue;
 		}
 
 		start = ktime_get();
 		pr_debug("%s: verifying source buffer...\n", current->comm);
-		error_count = dmatest_verify(thread->srcs, 0, src_off,
+		error_count = dmatest_verify(src->aligned, 0, src->off,
 				0, PATTERN_SRC, true, is_memset);
-		error_count += dmatest_verify(thread->srcs, src_off,
-				src_off + len, src_off,
+		error_count += dmatest_verify(src->aligned, src->off,
+				src->off + len, src->off,
 				PATTERN_SRC | PATTERN_COPY, true, is_memset);
-		error_count += dmatest_verify(thread->srcs, src_off + len,
-				params->buf_size, src_off + len,
+		error_count += dmatest_verify(src->aligned, src->off + len,
+				buf_size, src->off + len,
 				PATTERN_SRC, true, is_memset);
 
 		pr_debug("%s: verifying dest buffer...\n", current->comm);
-		error_count += dmatest_verify(thread->dsts, 0, dst_off,
+		error_count += dmatest_verify(dst->aligned, 0, dst->off,
 				0, PATTERN_DST, false, is_memset);
 
-		error_count += dmatest_verify(thread->dsts, dst_off,
-				dst_off + len, src_off,
+		error_count += dmatest_verify(dst->aligned, dst->off,
+				dst->off + len, src->off,
 				PATTERN_SRC | PATTERN_COPY, false, is_memset);
 
-		error_count += dmatest_verify(thread->dsts, dst_off + len,
-				params->buf_size, dst_off + len,
+		error_count += dmatest_verify(dst->aligned, dst->off + len,
+				buf_size, dst->off + len,
 				PATTERN_DST, false, is_memset);
 
 		diff = ktime_sub(ktime_get(), start);
 		comparetime = ktime_add(comparetime, diff);
 
 		if (error_count) {
-			result("data error", total_tests, src_off, dst_off,
+			result("data error", total_tests, src->off, dst->off,
 			       len, error_count);
 			failed_tests++;
 		} else {
-			verbose_result("test passed", total_tests, src_off,
-				       dst_off, len, 0);
+			verbose_result("test passed", total_tests, src->off,
+				       dst->off, len, 0);
 		}
+
+		continue;
+
+error_unmap_continue:
+		dmaengine_unmap_put(um);
+		failed_tests++;
 	}
 	ktime = ktime_sub(ktime_get(), ktime);
 	ktime = ktime_sub(ktime, comparetime);
@@ -789,30 +870,22 @@ static int dmatest_func(void *data)
 	kfree(dma_pq);
 err_srcs_array:
 	kfree(srcs);
-err_dstbuf:
-	for (i = 0; thread->udsts[i]; i++)
-		kfree(thread->udsts[i]);
-	kfree(thread->udsts);
-err_udsts:
-	kfree(thread->dsts);
-err_dsts:
-err_srcbuf:
-	for (i = 0; thread->usrcs[i]; i++)
-		kfree(thread->usrcs[i]);
-	kfree(thread->usrcs);
-err_usrcs:
-	kfree(thread->srcs);
-err_srcs:
+err_dst:
+	dmatest_free_test_data(dst);
+err_src:
+	dmatest_free_test_data(src);
+err_free_coefs:
 	kfree(pq_coefs);
 err_thread_type:
-	pr_info("%s: summary %u tests, %u failures %llu iops %llu KB/s (%d)\n",
+	iops = dmatest_persec(runtime, total_tests);
+	pr_info("%s: summary %u tests, %u failures %llu.%02llu iops %llu KB/s (%d)\n",
 		current->comm, total_tests, failed_tests,
-		dmatest_persec(runtime, total_tests),
+		FIXPT_TO_INT(iops), FIXPT_GET_FRAC(iops),
 		dmatest_KBs(runtime, total_len), ret);
 
 	/* terminate all transfers on specified channels */
 	if (ret || failed_tests)
-		dmaengine_terminate_all(chan);
+		dmaengine_terminate_sync(chan);
 
 	thread->done = true;
 	wake_up(&thread_wait);
@@ -836,7 +909,7 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 	}
 
 	/* terminate all transfers on specified channels */
-	dmaengine_terminate_all(dtc->chan);
+	dmaengine_terminate_sync(dtc->chan);
 
 	kfree(dtc);
 }
@@ -886,7 +959,7 @@ static int dmatest_add_threads(struct dmatest_info *info,
 		/* srcbuf and dstbuf are allocated by the thread itself */
 		get_task_struct(thread->task);
 		list_add_tail(&thread->node, &dtc->threads);
-		wake_up_process(thread->task);
+		thread->pending = true;
 	}
 
 	return i;
@@ -932,7 +1005,7 @@ static int dmatest_add_channel(struct dmatest_info *info,
 		thread_count += cnt > 0 ? cnt : 0;
 	}
 
-	pr_info("Started %u threads using %s\n",
+	pr_info("Added %u threads using %s\n",
 		thread_count, dma_chan_name(chan));
 
 	list_add_tail(&dtc->node, &info->channels);
@@ -977,7 +1050,7 @@ static void request_channels(struct dmatest_info *info,
 	}
 }
 
-static void run_threaded_test(struct dmatest_info *info)
+static void add_threaded_test(struct dmatest_info *info)
 {
 	struct dmatest_params *params = &info->params;
 
@@ -993,6 +1066,8 @@ static void run_threaded_test(struct dmatest_info *info)
 	params->timeout = timeout;
 	params->noverify = noverify;
 	params->norandom = norandom;
+	params->alignment = alignment;
+	params->transfer_size = transfer_size;
 
 	request_channels(info, DMA_MEMCPY);
 	request_channels(info, DMA_MEMSET);
@@ -1000,6 +1075,24 @@ static void run_threaded_test(struct dmatest_info *info)
 	request_channels(info, DMA_PQ);
 }
 
+static void run_pending_tests(struct dmatest_info *info)
+{
+	struct dmatest_chan *dtc;
+	unsigned int thread_count = 0;
+
+	list_for_each_entry(dtc, &info->channels, node) {
+		struct dmatest_thread *thread;
+
+		thread_count = 0;
+		list_for_each_entry(thread, &dtc->threads, node) {
+			wake_up_process(thread->task);
+			thread_count++;
+		}
+		pr_info("Started %u threads using %s\n",
+			thread_count, dma_chan_name(dtc->chan));
+	}
+}
+
 static void stop_threaded_test(struct dmatest_info *info)
 {
 	struct dmatest_chan *dtc, *_dtc;
@@ -1016,7 +1109,7 @@ static void stop_threaded_test(struct dmatest_info *info)
 	info->nr_channels = 0;
 }
 
-static void restart_threaded_test(struct dmatest_info *info, bool run)
+static void start_threaded_tests(struct dmatest_info *info)
 {
 	/* we might be called early to set run=, defer running until all
 	 * parameters have been evaluated
@@ -1024,11 +1117,7 @@ static void restart_threaded_test(struct dmatest_info *info, bool run)
 	if (!info->did_init)
 		return;
 
-	/* Stop any running test first */
-	stop_threaded_test(info);
-
-	/* Run test with new parameters */
-	run_threaded_test(info);
+	run_pending_tests(info);
 }
 
 static int dmatest_run_get(char *val, const struct kernel_param *kp)
@@ -1039,7 +1128,8 @@ static int dmatest_run_get(char *val, const struct kernel_param *kp)
 	if (is_threaded_test_run(info)) {
 		dmatest_run = true;
 	} else {
-		stop_threaded_test(info);
+		if (!is_threaded_test_pending(info))
+			stop_threaded_test(info);
 		dmatest_run = false;
 	}
 	mutex_unlock(&info->lock);
@@ -1057,16 +1147,123 @@ static int dmatest_run_set(const char *val, const struct kernel_param *kp)
 	if (ret) {
 		mutex_unlock(&info->lock);
 		return ret;
+	} else if (dmatest_run) {
+		if (is_threaded_test_pending(info))
+			start_threaded_tests(info);
+		else
+			pr_info("Could not start test, no channels configured\n");
+	} else {
+		stop_threaded_test(info);
 	}
 
-	if (is_threaded_test_run(info))
+	mutex_unlock(&info->lock);
+
+	return ret;
+}
+
+static int dmatest_chan_set(const char *val, const struct kernel_param *kp)
+{
+	struct dmatest_info *info = &test_info;
+	struct dmatest_chan *dtc;
+	char chan_reset_val[20];
+	int ret = 0;
+
+	mutex_lock(&info->lock);
+	ret = param_set_copystring(val, kp);
+	if (ret) {
+		mutex_unlock(&info->lock);
+		return ret;
+	}
+	/*Clear any previously run threads */
+	if (!is_threaded_test_run(info) && !is_threaded_test_pending(info))
+		stop_threaded_test(info);
+	/* Reject channels that are already registered */
+	if (is_threaded_test_pending(info)) {
+		list_for_each_entry(dtc, &info->channels, node) {
+			if (strcmp(dma_chan_name(dtc->chan),
+				   strim(test_channel)) == 0) {
+				dtc = list_last_entry(&info->channels,
+						      struct dmatest_chan,
+						      node);
+				strlcpy(chan_reset_val,
+					dma_chan_name(dtc->chan),
+					sizeof(chan_reset_val));
+				ret = -EBUSY;
+				goto add_chan_err;
+			}
+		}
+	}
+
+	add_threaded_test(info);
+
+	/* Check if channel was added successfully */
+	dtc = list_last_entry(&info->channels, struct dmatest_chan, node);
+
+	if (dtc->chan) {
+		/*
+		 * if new channel was not successfully added, revert the
+		 * "test_channel" string to the name of the last successfully
+		 * added channel. exception for when users issues empty string
+		 * to channel parameter.
+		 */
+		if ((strcmp(dma_chan_name(dtc->chan), strim(test_channel)) != 0)
+		    && (strcmp("", strim(test_channel)) != 0)) {
+			ret = -EINVAL;
+			strlcpy(chan_reset_val, dma_chan_name(dtc->chan),
+				sizeof(chan_reset_val));
+			goto add_chan_err;
+		}
+
+	} else {
+		/* Clear test_channel if no channels were added successfully */
+		strlcpy(chan_reset_val, "", sizeof(chan_reset_val));
 		ret = -EBUSY;
-	else if (dmatest_run)
-		restart_threaded_test(info, dmatest_run);
+		goto add_chan_err;
+	}
 
 	mutex_unlock(&info->lock);
 
 	return ret;
+
+add_chan_err:
+	param_set_copystring(chan_reset_val, kp);
+	mutex_unlock(&info->lock);
+
+	return ret;
+}
+
+static int dmatest_chan_get(char *val, const struct kernel_param *kp)
+{
+	struct dmatest_info *info = &test_info;
+
+	mutex_lock(&info->lock);
+	if (!is_threaded_test_run(info) && !is_threaded_test_pending(info)) {
+		stop_threaded_test(info);
+		strlcpy(test_channel, "", sizeof(test_channel));
+	}
+	mutex_unlock(&info->lock);
+
+	return param_get_string(val, kp);
+}
+
+static int dmatest_test_list_get(char *val, const struct kernel_param *kp)
+{
+	struct dmatest_info *info = &test_info;
+	struct dmatest_chan *dtc;
+	unsigned int thread_count = 0;
+
+	list_for_each_entry(dtc, &info->channels, node) {
+		struct dmatest_thread *thread;
+
+		thread_count = 0;
+		list_for_each_entry(thread, &dtc->threads, node) {
+			thread_count++;
+		}
+		pr_info("%u threads using %s\n",
+			thread_count, dma_chan_name(dtc->chan));
+	}
+
+	return 0;
 }
 
 static int __init dmatest_init(void)
@@ -1076,7 +1273,8 @@ static int __init dmatest_init(void)
 
 	if (dmatest_run) {
 		mutex_lock(&info->lock);
-		run_threaded_test(info);
+		add_threaded_test(info);
+		run_pending_tests(info);
 		mutex_unlock(&info->lock);
 	}
 
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
index f8888dc0b8dc..18b6014cf9b4 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
@@ -75,7 +75,7 @@ struct __packed axi_dma_lli {
 	__le32		sstat;
 	__le32		dstat;
 	__le32		status_lo;
-	__le32		ststus_hi;
+	__le32		status_hi;
 	__le32		reserved_lo;
 	__le32		reserved_hi;
 };
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index 04b9728c1d26..e5162690de8f 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
 #
 # DMA engine configuration for dw
 #
diff --git a/drivers/dma/dw/Makefile b/drivers/dma/dw/Makefile
index 2b949c2e4504..63ed895c09aa 100644
--- a/drivers/dma/dw/Makefile
+++ b/drivers/dma/dw/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DW_DMAC_CORE)	+= dw_dmac_core.o
-dw_dmac_core-objs	:= core.o
+dw_dmac_core-objs	:= core.o dw.o idma32.o
 
 obj-$(CONFIG_DW_DMAC)		+= dw_dmac.o
 dw_dmac-objs		:= platform.o
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1fc488e90f36..21cb2a58dbd2 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Core driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007-2008 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
  * Copyright (C) 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
@@ -37,27 +34,6 @@
  * support descriptor writeback.
  */
 
-#define DWC_DEFAULT_CTLLO(_chan) ({				\
-		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
-		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
-		bool _is_slave = is_slave_direction(_dwc->direction);	\
-		u8 _smsize = _is_slave ? _sconfig->src_maxburst :	\
-			DW_DMA_MSIZE_16;			\
-		u8 _dmsize = _is_slave ? _sconfig->dst_maxburst :	\
-			DW_DMA_MSIZE_16;			\
-		u8 _dms = (_dwc->direction == DMA_MEM_TO_DEV) ?		\
-			_dwc->dws.p_master : _dwc->dws.m_master;	\
-		u8 _sms = (_dwc->direction == DMA_DEV_TO_MEM) ?		\
-			_dwc->dws.p_master : _dwc->dws.m_master;	\
-								\
-		(DWC_CTLL_DST_MSIZE(_dmsize)			\
-		 | DWC_CTLL_SRC_MSIZE(_smsize)			\
-		 | DWC_CTLL_LLP_D_EN				\
-		 | DWC_CTLL_LLP_S_EN				\
-		 | DWC_CTLL_DMS(_dms)				\
-		 | DWC_CTLL_SMS(_sms));				\
-	})
-
 /* The set of bus widths supported by the DMA controller */
 #define DW_DMA_BUSWIDTHS			  \
 	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED)	| \
@@ -138,42 +114,6 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	dwc->descs_allocated--;
 }
 
-static void dwc_initialize_chan_idma32(struct dw_dma_chan *dwc)
-{
-	u32 cfghi = 0;
-	u32 cfglo = 0;
-
-	/* Set default burst alignment */
-	cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN;
-
-	/* Low 4 bits of the request lines */
-	cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf);
-	cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf);
-
-	/* Request line extension (2 bits) */
-	cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3);
-	cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3);
-
-	channel_writel(dwc, CFG_LO, cfglo);
-	channel_writel(dwc, CFG_HI, cfghi);
-}
-
-static void dwc_initialize_chan_dw(struct dw_dma_chan *dwc)
-{
-	u32 cfghi = DWC_CFGH_FIFO_MODE;
-	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
-	bool hs_polarity = dwc->dws.hs_polarity;
-
-	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
-	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
-
-	/* Set polarity of handshake interface */
-	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
-
-	channel_writel(dwc, CFG_LO, cfglo);
-	channel_writel(dwc, CFG_HI, cfghi);
-}
-
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
@@ -181,10 +121,7 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
 		return;
 
-	if (dw->pdata->is_idma32)
-		dwc_initialize_chan_idma32(dwc);
-	else
-		dwc_initialize_chan_dw(dwc);
+	dw->initialize_chan(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
@@ -213,37 +150,6 @@ static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		cpu_relax();
 }
 
-static u32 bytes2block(struct dw_dma_chan *dwc, size_t bytes,
-			  unsigned int width, size_t *len)
-{
-	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	u32 block;
-
-	/* Always in bytes for iDMA 32-bit */
-	if (dw->pdata->is_idma32)
-		width = 0;
-
-	if ((bytes >> width) > dwc->block_size) {
-		block = dwc->block_size;
-		*len = block << width;
-	} else {
-		block = bytes >> width;
-		*len = bytes;
-	}
-
-	return block;
-}
-
-static size_t block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
-{
-	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-
-	if (dw->pdata->is_idma32)
-		return IDMA32C_CTLH_BLOCK_TS(block);
-
-	return DWC_CTLH_BLOCK_TS(block) << width;
-}
-
 /*----------------------------------------------------------------------*/
 
 /* Perform single block transfer */
@@ -389,10 +295,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 /* Returns how many bytes were already received from source */
 static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
 {
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	u32 ctlhi = channel_readl(dwc, CTL_HI);
 	u32 ctllo = channel_readl(dwc, CTL_LO);
 
-	return block2bytes(dwc, ctlhi, ctllo >> 4 & 7);
+	return dw->block2bytes(dwc, ctlhi, ctllo >> 4 & 7);
 }
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -649,7 +556,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	unsigned int		src_width;
 	unsigned int		dst_width;
 	unsigned int		data_width = dw->pdata->data_width[m_master];
-	u32			ctllo;
+	u32			ctllo, ctlhi;
 	u8			lms = DWC_LLP_LMS(m_master);
 
 	dev_vdbg(chan2dev(chan),
@@ -665,7 +572,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 	src_width = dst_width = __ffs(data_width | src | dest | len);
 
-	ctllo = DWC_DEFAULT_CTLLO(chan)
+	ctllo = dw->prepare_ctllo(dwc)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -678,10 +585,12 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		if (!desc)
 			goto err_desc_get;
 
+		ctlhi = dw->bytes2block(dwc, len - offset, src_width, &xfer_count);
+
 		lli_write(desc, sar, src + offset);
 		lli_write(desc, dar, dest + offset);
 		lli_write(desc, ctllo, ctllo);
-		lli_write(desc, ctlhi, bytes2block(dwc, len - offset, src_width, &xfer_count));
+		lli_write(desc, ctlhi, ctlhi);
 		desc->len = xfer_count;
 
 		if (!first) {
@@ -719,7 +628,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
 	struct dw_desc		*prev;
 	struct dw_desc		*first;
-	u32			ctllo;
+	u32			ctllo, ctlhi;
 	u8			m_master = dwc->dws.m_master;
 	u8			lms = DWC_LLP_LMS(m_master);
 	dma_addr_t		reg;
@@ -743,10 +652,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	case DMA_MEM_TO_DEV:
 		reg_width = __ffs(sconfig->dst_addr_width);
 		reg = sconfig->dst_addr;
-		ctllo = (DWC_DEFAULT_CTLLO(chan)
+		ctllo = dw->prepare_ctllo(dwc)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
-				| DWC_CTLL_SRC_INC);
+				| DWC_CTLL_SRC_INC;
 
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
 			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
@@ -766,9 +675,11 @@ slave_sg_todev_fill_desc:
 			if (!desc)
 				goto err_desc_get;
 
+			ctlhi = dw->bytes2block(dwc, len, mem_width, &dlen);
+
 			lli_write(desc, sar, mem);
 			lli_write(desc, dar, reg);
-			lli_write(desc, ctlhi, bytes2block(dwc, len, mem_width, &dlen));
+			lli_write(desc, ctlhi, ctlhi);
 			lli_write(desc, ctllo, ctllo | DWC_CTLL_SRC_WIDTH(mem_width));
 			desc->len = dlen;
 
@@ -791,10 +702,10 @@ slave_sg_todev_fill_desc:
 	case DMA_DEV_TO_MEM:
 		reg_width = __ffs(sconfig->src_addr_width);
 		reg = sconfig->src_addr;
-		ctllo = (DWC_DEFAULT_CTLLO(chan)
+		ctllo = dw->prepare_ctllo(dwc)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
-				| DWC_CTLL_SRC_FIX);
+				| DWC_CTLL_SRC_FIX;
 
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
 			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
@@ -812,9 +723,11 @@ slave_sg_fromdev_fill_desc:
 			if (!desc)
 				goto err_desc_get;
 
+			ctlhi = dw->bytes2block(dwc, len, reg_width, &dlen);
+
 			lli_write(desc, sar, reg);
 			lli_write(desc, dar, mem);
-			lli_write(desc, ctlhi, bytes2block(dwc, len, reg_width, &dlen));
+			lli_write(desc, ctlhi, ctlhi);
 			mem_width = __ffs(data_width | mem | dlen);
 			lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
 			desc->len = dlen;
@@ -874,22 +787,12 @@ EXPORT_SYMBOL_GPL(dw_dma_filter);
 static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 {
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
-	struct dma_slave_config *sc = &dwc->dma_sconfig;
 	struct dw_dma *dw = to_dw_dma(chan->device);
-	/*
-	 * Fix sconfig's burst size according to dw_dmac. We need to convert
-	 * them as:
-	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
-	 *
-	 * NOTE: burst size 2 is not supported by DesignWare controller.
-	 *       iDMA 32-bit supports it.
-	 */
-	u32 s = dw->pdata->is_idma32 ? 1 : 2;
 
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
 
-	sc->src_maxburst = sc->src_maxburst > 1 ? fls(sc->src_maxburst) - s : 0;
-	sc->dst_maxburst = sc->dst_maxburst > 1 ? fls(sc->dst_maxburst) - s : 0;
+	dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst);
+	dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst);
 
 	return 0;
 }
@@ -898,16 +801,9 @@ static void dwc_chan_pause(struct dw_dma_chan *dwc, bool drain)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	unsigned int		count = 20;	/* timeout iterations */
-	u32			cfglo;
 
-	cfglo = channel_readl(dwc, CFG_LO);
-	if (dw->pdata->is_idma32) {
-		if (drain)
-			cfglo |= IDMA32C_CFGL_CH_DRAIN;
-		else
-			cfglo &= ~IDMA32C_CFGL_CH_DRAIN;
-	}
-	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+	dw->suspend_chan(dwc, drain);
+
 	while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY) && count--)
 		udelay(2);
 
@@ -926,11 +822,11 @@ static int dwc_pause(struct dma_chan *chan)
 	return 0;
 }
 
-static inline void dwc_chan_resume(struct dw_dma_chan *dwc)
+static inline void dwc_chan_resume(struct dw_dma_chan *dwc, bool drain)
 {
-	u32 cfglo = channel_readl(dwc, CFG_LO);
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 
-	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+	dw->resume_chan(dwc, drain);
 
 	clear_bit(DW_DMA_IS_PAUSED, &dwc->flags);
 }
@@ -943,7 +839,7 @@ static int dwc_resume(struct dma_chan *chan)
 	spin_lock_irqsave(&dwc->lock, flags);
 
 	if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags))
-		dwc_chan_resume(dwc);
+		dwc_chan_resume(dwc, false);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -966,7 +862,7 @@ static int dwc_terminate_all(struct dma_chan *chan)
 
 	dwc_chan_disable(dw, dwc);
 
-	dwc_chan_resume(dwc);
+	dwc_chan_resume(dwc, true);
 
 	/* active_list entries will end up before queued entries */
 	list_splice_init(&dwc->queue, &list);
@@ -1056,33 +952,7 @@ static void dwc_issue_pending(struct dma_chan *chan)
 
 /*----------------------------------------------------------------------*/
 
-/*
- * Program FIFO size of channels.
- *
- * By default full FIFO (512 bytes) is assigned to channel 0. Here we
- * slice FIFO on equal parts between channels.
- */
-static void idma32_fifo_partition(struct dw_dma *dw)
-{
-	u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) |
-		    IDMA32C_FP_UPDATE;
-	u64 fifo_partition = 0;
-
-	if (!dw->pdata->is_idma32)
-		return;
-
-	/* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */
-	fifo_partition |= value << 0;
-
-	/* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */
-	fifo_partition |= value << 32;
-
-	/* Program FIFO Partition registers - 64 bytes per channel */
-	idma32_writeq(dw, FIFO_PARTITION1, fifo_partition);
-	idma32_writeq(dw, FIFO_PARTITION0, fifo_partition);
-}
-
-static void dw_dma_off(struct dw_dma *dw)
+void do_dw_dma_off(struct dw_dma *dw)
 {
 	unsigned int i;
 
@@ -1101,7 +971,7 @@ static void dw_dma_off(struct dw_dma *dw)
 		clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags);
 }
 
-static void dw_dma_on(struct dw_dma *dw)
+void do_dw_dma_on(struct dw_dma *dw)
 {
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 }
@@ -1137,7 +1007,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 
 	/* Enable controller here if needed */
 	if (!dw->in_use)
-		dw_dma_on(dw);
+		do_dw_dma_on(dw);
 	dw->in_use |= dwc->mask;
 
 	return 0;
@@ -1148,7 +1018,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
 	unsigned long		flags;
-	LIST_HEAD(list);
 
 	dev_dbg(chan2dev(chan), "%s: descs allocated=%u\n", __func__,
 			dwc->descs_allocated);
@@ -1175,30 +1044,25 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	/* Disable controller in case it was a last user */
 	dw->in_use &= ~dwc->mask;
 	if (!dw->in_use)
-		dw_dma_off(dw);
+		do_dw_dma_off(dw);
 
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
-int dw_dma_probe(struct dw_dma_chip *chip)
+int do_dma_probe(struct dw_dma_chip *chip)
 {
+	struct dw_dma *dw = chip->dw;
 	struct dw_dma_platform_data *pdata;
-	struct dw_dma		*dw;
 	bool			autocfg = false;
 	unsigned int		dw_params;
 	unsigned int		i;
 	int			err;
 
-	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
-	if (!dw)
-		return -ENOMEM;
-
 	dw->pdata = devm_kzalloc(chip->dev, sizeof(*dw->pdata), GFP_KERNEL);
 	if (!dw->pdata)
 		return -ENOMEM;
 
 	dw->regs = chip->regs;
-	chip->dw = dw;
 
 	pm_runtime_get_sync(chip->dev);
 
@@ -1225,8 +1089,6 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 		pdata->block_size = dma_readl(dw, MAX_BLK_SIZE);
 
 		/* Fill platform data with the default values */
-		pdata->is_private = true;
-		pdata->is_memcpy = true;
 		pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
 		pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
 	} else if (chip->pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
@@ -1250,15 +1112,10 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 	dw->all_chan_mask = (1 << pdata->nr_channels) - 1;
 
 	/* Force dma off, just in case */
-	dw_dma_off(dw);
-
-	idma32_fifo_partition(dw);
+	dw->disable(dw);
 
 	/* Device and instance ID for IRQ and DMA pool */
-	if (pdata->is_idma32)
-		snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", chip->id);
-	else
-		snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", chip->id);
+	dw->set_device_name(dw, chip->id);
 
 	/* Create a pool of consistent memory blocks for hardware descriptors */
 	dw->desc_pool = dmam_pool_create(dw->name, chip->dev,
@@ -1338,10 +1195,8 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 
 	/* Set capabilities */
 	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
-	if (pdata->is_private)
-		dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
-	if (pdata->is_memcpy)
-		dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+	dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
+	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
 
 	dw->dma.dev = chip->dev;
 	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
@@ -1382,16 +1237,15 @@ err_pdata:
 	pm_runtime_put_sync_suspend(chip->dev);
 	return err;
 }
-EXPORT_SYMBOL_GPL(dw_dma_probe);
 
-int dw_dma_remove(struct dw_dma_chip *chip)
+int do_dma_remove(struct dw_dma_chip *chip)
 {
 	struct dw_dma		*dw = chip->dw;
 	struct dw_dma_chan	*dwc, *_dwc;
 
 	pm_runtime_get_sync(chip->dev);
 
-	dw_dma_off(dw);
+	do_dw_dma_off(dw);
 	dma_async_device_unregister(&dw->dma);
 
 	free_irq(chip->irq, dw);
@@ -1406,27 +1260,24 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 	pm_runtime_put_sync_suspend(chip->dev);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_remove);
 
-int dw_dma_disable(struct dw_dma_chip *chip)
+int do_dw_dma_disable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
-	dw_dma_off(dw);
+	dw->disable(dw);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_disable);
+EXPORT_SYMBOL_GPL(do_dw_dma_disable);
 
-int dw_dma_enable(struct dw_dma_chip *chip)
+int do_dw_dma_enable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
-	idma32_fifo_partition(dw);
-
-	dw_dma_on(dw);
+	dw->enable(dw);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_enable);
+EXPORT_SYMBOL_GPL(do_dw_dma_enable);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c
new file mode 100644
index 000000000000..7a085b3c1854
--- /dev/null
+++ b/drivers/dma/dw/dw.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2007-2008 Atmel Corporation
+// Copyright (C) 2010-2011 ST Microelectronics
+// Copyright (C) 2013,2018 Intel Corporation
+
+#include <linux/bitops.h>
+#include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "internal.h"
+
+static void dw_dma_initialize_chan(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 cfghi = DWC_CFGH_FIFO_MODE;
+	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
+	bool hs_polarity = dwc->dws.hs_polarity;
+
+	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
+	cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl);
+
+	/* Set polarity of handshake interface */
+	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dw_dma_suspend_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+}
+
+static void dw_dma_resume_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+}
+
+static u32 dw_dma_bytes2block(struct dw_dma_chan *dwc,
+			      size_t bytes, unsigned int width, size_t *len)
+{
+	u32 block;
+
+	if ((bytes >> width) > dwc->block_size) {
+		block = dwc->block_size;
+		*len = dwc->block_size << width;
+	} else {
+		block = bytes >> width;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t dw_dma_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	return DWC_CTLH_BLOCK_TS(block) << width;
+}
+
+static u32 dw_dma_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	bool is_slave = is_slave_direction(dwc->direction);
+	u8 smsize = is_slave ? sconfig->src_maxburst : DW_DMA_MSIZE_16;
+	u8 dmsize = is_slave ? sconfig->dst_maxburst : DW_DMA_MSIZE_16;
+	u8 p_master = dwc->dws.p_master;
+	u8 m_master = dwc->dws.m_master;
+	u8 dms = (dwc->direction == DMA_MEM_TO_DEV) ? p_master : m_master;
+	u8 sms = (dwc->direction == DMA_DEV_TO_MEM) ? p_master : m_master;
+
+	return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+	       DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize) |
+	       DWC_CTLL_DMS(dms) | DWC_CTLL_SMS(sms);
+}
+
+static void dw_dma_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
+{
+	/*
+	 * Fix burst size according to dw_dmac. We need to convert them as:
+	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+	 */
+	*maxburst = *maxburst > 1 ? fls(*maxburst) - 2 : 0;
+}
+
+static void dw_dma_set_device_name(struct dw_dma *dw, int id)
+{
+	snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", id);
+}
+
+static void dw_dma_disable(struct dw_dma *dw)
+{
+	do_dw_dma_off(dw);
+}
+
+static void dw_dma_enable(struct dw_dma *dw)
+{
+	do_dw_dma_on(dw);
+}
+
+int dw_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	/* Channel operations */
+	dw->initialize_chan = dw_dma_initialize_chan;
+	dw->suspend_chan = dw_dma_suspend_chan;
+	dw->resume_chan = dw_dma_resume_chan;
+	dw->prepare_ctllo = dw_dma_prepare_ctllo;
+	dw->encode_maxburst = dw_dma_encode_maxburst;
+	dw->bytes2block = dw_dma_bytes2block;
+	dw->block2bytes = dw_dma_block2bytes;
+
+	/* Device operations */
+	dw->set_device_name = dw_dma_set_device_name;
+	dw->disable = dw_dma_disable;
+	dw->enable = dw_dma_enable;
+
+	chip->dw = dw;
+	return do_dma_probe(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_probe);
+
+int dw_dma_remove(struct dw_dma_chip *chip)
+{
+	return do_dma_remove(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_remove);
diff --git a/drivers/dma/dw/idma32.c b/drivers/dma/dw/idma32.c
new file mode 100644
index 000000000000..f00657308811
--- /dev/null
+++ b/drivers/dma/dw/idma32.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2013,2018 Intel Corporation
+
+#include <linux/bitops.h>
+#include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "internal.h"
+
+static void idma32_initialize_chan(struct dw_dma_chan *dwc)
+{
+	u32 cfghi = 0;
+	u32 cfglo = 0;
+
+	/* Set default burst alignment */
+	cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN;
+
+	/* Low 4 bits of the request lines */
+	cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf);
+	cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf);
+
+	/* Request line extension (2 bits) */
+	cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3);
+	cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3);
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void idma32_suspend_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	if (drain)
+		cfglo |= IDMA32C_CFGL_CH_DRAIN;
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+}
+
+static void idma32_resume_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	if (drain)
+		cfglo &= ~IDMA32C_CFGL_CH_DRAIN;
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+}
+
+static u32 idma32_bytes2block(struct dw_dma_chan *dwc,
+			      size_t bytes, unsigned int width, size_t *len)
+{
+	u32 block;
+
+	if (bytes > dwc->block_size) {
+		block = dwc->block_size;
+		*len = dwc->block_size;
+	} else {
+		block = bytes;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t idma32_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	return IDMA32C_CTLH_BLOCK_TS(block);
+}
+
+static u32 idma32_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	bool is_slave = is_slave_direction(dwc->direction);
+	u8 smsize = is_slave ? sconfig->src_maxburst : IDMA32_MSIZE_8;
+	u8 dmsize = is_slave ? sconfig->dst_maxburst : IDMA32_MSIZE_8;
+
+	return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+	       DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize);
+}
+
+static void idma32_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
+{
+	*maxburst = *maxburst > 1 ? fls(*maxburst) - 1 : 0;
+}
+
+static void idma32_set_device_name(struct dw_dma *dw, int id)
+{
+	snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", id);
+}
+
+/*
+ * Program FIFO size of channels.
+ *
+ * By default full FIFO (512 bytes) is assigned to channel 0. Here we
+ * slice FIFO on equal parts between channels.
+ */
+static void idma32_fifo_partition(struct dw_dma *dw)
+{
+	u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) |
+		    IDMA32C_FP_UPDATE;
+	u64 fifo_partition = 0;
+
+	/* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */
+	fifo_partition |= value << 0;
+
+	/* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */
+	fifo_partition |= value << 32;
+
+	/* Program FIFO Partition registers - 64 bytes per channel */
+	idma32_writeq(dw, FIFO_PARTITION1, fifo_partition);
+	idma32_writeq(dw, FIFO_PARTITION0, fifo_partition);
+}
+
+static void idma32_disable(struct dw_dma *dw)
+{
+	do_dw_dma_off(dw);
+	idma32_fifo_partition(dw);
+}
+
+static void idma32_enable(struct dw_dma *dw)
+{
+	idma32_fifo_partition(dw);
+	do_dw_dma_on(dw);
+}
+
+int idma32_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	/* Channel operations */
+	dw->initialize_chan = idma32_initialize_chan;
+	dw->suspend_chan = idma32_suspend_chan;
+	dw->resume_chan = idma32_resume_chan;
+	dw->prepare_ctllo = idma32_prepare_ctllo;
+	dw->encode_maxburst = idma32_encode_maxburst;
+	dw->bytes2block = idma32_bytes2block;
+	dw->block2bytes = idma32_block2bytes;
+
+	/* Device operations */
+	dw->set_device_name = idma32_set_device_name;
+	dw->disable = idma32_disable;
+	dw->enable = idma32_enable;
+
+	chip->dw = dw;
+	return do_dma_probe(chip);
+}
+EXPORT_SYMBOL_GPL(idma32_dma_probe);
+
+int idma32_dma_remove(struct dw_dma_chip *chip)
+{
+	return do_dma_remove(chip);
+}
+EXPORT_SYMBOL_GPL(idma32_dma_remove);
diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index 41439732ff6b..1dd7a4e6dd23 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _DMA_DW_INTERNAL_H
@@ -15,8 +12,14 @@
 
 #include "regs.h"
 
-int dw_dma_disable(struct dw_dma_chip *chip);
-int dw_dma_enable(struct dw_dma_chip *chip);
+int do_dma_probe(struct dw_dma_chip *chip);
+int do_dma_remove(struct dw_dma_chip *chip);
+
+void do_dw_dma_on(struct dw_dma *dw);
+void do_dw_dma_off(struct dw_dma *dw);
+
+int do_dw_dma_disable(struct dw_dma_chip *chip);
+int do_dw_dma_enable(struct dw_dma_chip *chip);
 
 extern bool dw_dma_filter(struct dma_chan *chan, void *param);
 
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 7778ed705a1a..e79a75db0852 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * PCI driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2013 Intel Corporation
  * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -15,21 +12,33 @@
 
 #include "internal.h"
 
-static struct dw_dma_platform_data mrfld_pdata = {
+struct dw_dma_pci_data {
+	const struct dw_dma_platform_data *pdata;
+	int (*probe)(struct dw_dma_chip *chip);
+};
+
+static const struct dw_dma_pci_data dw_pci_data = {
+	.probe = dw_dma_probe,
+};
+
+static const struct dw_dma_platform_data idma32_pdata = {
 	.nr_channels = 8,
-	.is_private = true,
-	.is_memcpy = true,
-	.is_idma32 = true,
 	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
 	.chan_priority = CHAN_PRIORITY_ASCENDING,
 	.block_size = 131071,
 	.nr_masters = 1,
 	.data_width = {4},
+	.multi_block = {1, 1, 1, 1, 1, 1, 1, 1},
+};
+
+static const struct dw_dma_pci_data idma32_pci_data = {
+	.pdata = &idma32_pdata,
+	.probe = idma32_dma_probe,
 };
 
 static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 {
-	const struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
+	const struct dw_dma_pci_data *data = (void *)pid->driver_data;
 	struct dw_dma_chip *chip;
 	int ret;
 
@@ -62,9 +71,9 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 	chip->id = pdev->devfn;
 	chip->regs = pcim_iomap_table(pdev)[0];
 	chip->irq = pdev->irq;
-	chip->pdata = pdata;
+	chip->pdata = data->pdata;
 
-	ret = dw_dma_probe(chip);
+	ret = data->probe(chip);
 	if (ret)
 		return ret;
 
@@ -90,7 +99,7 @@ static int dw_pci_suspend_late(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_disable(chip);
+	return do_dw_dma_disable(chip);
 };
 
 static int dw_pci_resume_early(struct device *dev)
@@ -98,7 +107,7 @@ static int dw_pci_resume_early(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_enable(chip);
+	return do_dw_dma_enable(chip);
 };
 
 #endif /* CONFIG_PM_SLEEP */
@@ -109,24 +118,24 @@ static const struct dev_pm_ops dw_pci_dev_pm_ops = {
 
 static const struct pci_device_id dw_pci_id_table[] = {
 	/* Medfield (GPDMA) */
-	{ PCI_VDEVICE(INTEL, 0x0827) },
+	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_data },
 
 	/* BayTrail */
-	{ PCI_VDEVICE(INTEL, 0x0f06) },
-	{ PCI_VDEVICE(INTEL, 0x0f40) },
+	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_data },
 
-	/* Merrifield iDMA 32-bit (GPDMA) */
-	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&mrfld_pdata },
+	/* Merrifield */
+	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&idma32_pci_data },
 
 	/* Braswell */
-	{ PCI_VDEVICE(INTEL, 0x2286) },
-	{ PCI_VDEVICE(INTEL, 0x22c0) },
+	{ PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_pci_data },
 
 	/* Haswell */
-	{ PCI_VDEVICE(INTEL, 0x9c60) },
+	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_data },
 
 	/* Broadwell */
-	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+	{ PCI_VDEVICE(INTEL, 0x9ce0), (kernel_ulong_t)&dw_pci_data },
 
 	{ }
 };
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index f01b2c173fa6..382dfd9e9600 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Platform driver for the Synopsys DesignWare DMA Controller
  *
@@ -6,10 +7,6 @@
  * Copyright (C) 2013 Intel Corporation
  *
  * Some parts of this driver are derived from the original dw_dmac.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -128,15 +125,6 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	pdata->nr_masters = nr_masters;
 	pdata->nr_channels = nr_channels;
 
-	if (of_property_read_bool(np, "is_private"))
-		pdata->is_private = true;
-
-	/*
-	 * All known devices, which use DT for configuration, support
-	 * memory-to-memory transfers. So enable it by default.
-	 */
-	pdata->is_memcpy = true;
-
 	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
 		pdata->chan_allocation_order = (unsigned char)tmp;
 
@@ -162,6 +150,12 @@ dw_dma_parse_dt(struct platform_device *pdev)
 			pdata->multi_block[tmp] = 1;
 	}
 
+	if (!of_property_read_u32(np, "snps,dma-protection-control", &tmp)) {
+		if (tmp > CHAN_PROTCTL_MASK)
+			return NULL;
+		pdata->protctl = tmp;
+	}
+
 	return pdata;
 }
 #else
@@ -258,7 +252,7 @@ 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
+	 * We have to call do_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()
@@ -267,7 +261,7 @@ static void dw_shutdown(struct platform_device *pdev)
 	 * used by the driver.
 	 */
 	pm_runtime_get_sync(chip->dev);
-	dw_dma_disable(chip);
+	do_dw_dma_disable(chip);
 	pm_runtime_put_sync_suspend(chip->dev);
 
 	clk_disable_unprepare(chip->clk);
@@ -297,7 +291,7 @@ static int dw_suspend_late(struct device *dev)
 {
 	struct dw_dma_chip *chip = dev_get_drvdata(dev);
 
-	dw_dma_disable(chip);
+	do_dw_dma_disable(chip);
 	clk_disable_unprepare(chip->clk);
 
 	return 0;
@@ -312,7 +306,7 @@ static int dw_resume_early(struct device *dev)
 	if (ret)
 		return ret;
 
-	return dw_dma_enable(chip);
+	return do_dw_dma_enable(chip);
 }
 
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 09e7dfdbb790..3fce66ecee7a 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare AHB DMA Controller
  *
  * Copyright (C) 2005-2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
  * Copyright (C) 2016 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
@@ -200,6 +197,10 @@ enum dw_dma_msize {
 #define DWC_CFGH_FCMODE		(1 << 0)
 #define DWC_CFGH_FIFO_MODE	(1 << 1)
 #define DWC_CFGH_PROTCTL(x)	((x) << 2)
+#define DWC_CFGH_PROTCTL_DATA	(0 << 2)	/* data access - always set */
+#define DWC_CFGH_PROTCTL_PRIV	(1 << 2)	/* privileged -> AHB HPROT[1] */
+#define DWC_CFGH_PROTCTL_BUFFER	(2 << 2)	/* bufferable -> AHB HPROT[2] */
+#define DWC_CFGH_PROTCTL_CACHE	(4 << 2)	/* cacheable  -> AHB HPROT[3] */
 #define DWC_CFGH_DS_UPD_EN	(1 << 5)
 #define DWC_CFGH_SS_UPD_EN	(1 << 6)
 #define DWC_CFGH_SRC_PER(x)	((x) << 7)
@@ -218,6 +219,16 @@ enum dw_dma_msize {
 
 /* iDMA 32-bit support */
 
+/* bursts size */
+enum idma32_msize {
+	IDMA32_MSIZE_1,
+	IDMA32_MSIZE_2,
+	IDMA32_MSIZE_4,
+	IDMA32_MSIZE_8,
+	IDMA32_MSIZE_16,
+	IDMA32_MSIZE_32,
+};
+
 /* Bitfields in CTL_HI */
 #define IDMA32C_CTLH_BLOCK_TS_MASK	GENMASK(16, 0)
 #define IDMA32C_CTLH_BLOCK_TS(x)	((x) & IDMA32C_CTLH_BLOCK_TS_MASK)
@@ -308,6 +319,21 @@ struct dw_dma {
 	u8			all_chan_mask;
 	u8			in_use;
 
+	/* Channel operations */
+	void	(*initialize_chan)(struct dw_dma_chan *dwc);
+	void	(*suspend_chan)(struct dw_dma_chan *dwc, bool drain);
+	void	(*resume_chan)(struct dw_dma_chan *dwc, bool drain);
+	u32	(*prepare_ctllo)(struct dw_dma_chan *dwc);
+	void	(*encode_maxburst)(struct dw_dma_chan *dwc, u32 *maxburst);
+	u32	(*bytes2block)(struct dw_dma_chan *dwc, size_t bytes,
+			       unsigned int width, size_t *len);
+	size_t	(*block2bytes)(struct dw_dma_chan *dwc, u32 block, u32 width);
+
+	/* Device operations */
+	void (*set_device_name)(struct dw_dma *dw, int id);
+	void (*disable)(struct dw_dma *dw);
+	void (*enable)(struct dw_dma *dw);
+
 	/* platform data */
 	struct dw_dma_platform_data	*pdata;
 };
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index f674eb5fbbef..594a88f4f99c 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -997,7 +997,7 @@ ep93xx_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 	for (offset = 0; offset < len; offset += bytes) {
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
@@ -1069,7 +1069,7 @@ ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
@@ -1149,7 +1149,7 @@ ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 	for (offset = 0; offset < buf_len; offset += period_len) {
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 8876c4c1bb2c..680b2a00a953 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -6,6 +6,7 @@
 #include <linux/dmapool.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #include "fsl-edma-common.h"
 
@@ -173,12 +174,62 @@ int fsl_edma_resume(struct dma_chan *chan)
 }
 EXPORT_SYMBOL_GPL(fsl_edma_resume);
 
+static void fsl_edma_unprep_slave_dma(struct fsl_edma_chan *fsl_chan)
+{
+	if (fsl_chan->dma_dir != DMA_NONE)
+		dma_unmap_resource(fsl_chan->vchan.chan.device->dev,
+				   fsl_chan->dma_dev_addr,
+				   fsl_chan->dma_dev_size,
+				   fsl_chan->dma_dir, 0);
+	fsl_chan->dma_dir = DMA_NONE;
+}
+
+static bool fsl_edma_prep_slave_dma(struct fsl_edma_chan *fsl_chan,
+				    enum dma_transfer_direction dir)
+{
+	struct device *dev = fsl_chan->vchan.chan.device->dev;
+	enum dma_data_direction dma_dir;
+	phys_addr_t addr = 0;
+	u32 size = 0;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		dma_dir = DMA_FROM_DEVICE;
+		addr = fsl_chan->cfg.dst_addr;
+		size = fsl_chan->cfg.dst_maxburst;
+		break;
+	case DMA_DEV_TO_MEM:
+		dma_dir = DMA_TO_DEVICE;
+		addr = fsl_chan->cfg.src_addr;
+		size = fsl_chan->cfg.src_maxburst;
+		break;
+	default:
+		dma_dir = DMA_NONE;
+		break;
+	}
+
+	/* Already mapped for this config? */
+	if (fsl_chan->dma_dir == dma_dir)
+		return true;
+
+	fsl_edma_unprep_slave_dma(fsl_chan);
+
+	fsl_chan->dma_dev_addr = dma_map_resource(dev, addr, size, dma_dir, 0);
+	if (dma_mapping_error(dev, fsl_chan->dma_dev_addr))
+		return false;
+	fsl_chan->dma_dev_size = size;
+	fsl_chan->dma_dir = dma_dir;
+
+	return true;
+}
+
 int fsl_edma_slave_config(struct dma_chan *chan,
 				 struct dma_slave_config *cfg)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 
 	memcpy(&fsl_chan->cfg, cfg, sizeof(*cfg));
+	fsl_edma_unprep_slave_dma(fsl_chan);
 
 	return 0;
 }
@@ -339,9 +390,7 @@ static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
 	struct fsl_edma_desc *fsl_desc;
 	int i;
 
-	fsl_desc = kzalloc(sizeof(*fsl_desc) +
-			   sizeof(struct fsl_edma_sw_tcd) *
-			   sg_len, GFP_NOWAIT);
+	fsl_desc = kzalloc(struct_size(fsl_desc, tcd, sg_len), GFP_NOWAIT);
 	if (!fsl_desc)
 		return NULL;
 
@@ -378,6 +427,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 	if (!is_slave_direction(direction))
 		return NULL;
 
+	if (!fsl_edma_prep_slave_dma(fsl_chan, direction))
+		return NULL;
+
 	sg_len = buf_len / period_len;
 	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
 	if (!fsl_desc)
@@ -409,11 +461,11 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 
 		if (direction == DMA_MEM_TO_DEV) {
 			src_addr = dma_buf_next;
-			dst_addr = fsl_chan->cfg.dst_addr;
+			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = 0;
 		} else {
-			src_addr = fsl_chan->cfg.src_addr;
+			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = dma_buf_next;
 			soff = 0;
 			doff = fsl_chan->cfg.src_addr_width;
@@ -444,6 +496,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 	if (!is_slave_direction(direction))
 		return NULL;
 
+	if (!fsl_edma_prep_slave_dma(fsl_chan, direction))
+		return NULL;
+
 	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
 	if (!fsl_desc)
 		return NULL;
@@ -468,11 +523,11 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 
 		if (direction == DMA_MEM_TO_DEV) {
 			src_addr = sg_dma_address(sg);
-			dst_addr = fsl_chan->cfg.dst_addr;
+			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = 0;
 		} else {
-			src_addr = fsl_chan->cfg.src_addr;
+			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = sg_dma_address(sg);
 			soff = 0;
 			doff = fsl_chan->cfg.src_addr_width;
@@ -555,6 +610,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	fsl_edma_chan_mux(fsl_chan, 0, false);
 	fsl_chan->edesc = NULL;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	fsl_edma_unprep_slave_dma(fsl_chan);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 8917e8865959..b435d8e1e3a1 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -6,6 +6,7 @@
 #ifndef _FSL_EDMA_COMMON_H_
 #define _FSL_EDMA_COMMON_H_
 
+#include <linux/dma-direction.h>
 #include "virt-dma.h"
 
 #define EDMA_CR_EDBG		BIT(1)
@@ -120,6 +121,9 @@ struct fsl_edma_chan {
 	struct dma_slave_config		cfg;
 	u32				attr;
 	struct dma_pool			*tcd_pool;
+	dma_addr_t			dma_dev_addr;
+	u32				dma_dev_size;
+	enum dma_data_direction		dma_dir;
 };
 
 struct fsl_edma_desc {
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 34d70112fcc9..75e8a7ba3a22 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -254,6 +254,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		fsl_chan->pm_state = RUNNING;
 		fsl_chan->slave_id = 0;
 		fsl_chan->idle = true;
+		fsl_chan->dma_dir = DMA_NONE;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
new file mode 100644
index 000000000000..aa1d0ae3d207
--- /dev/null
+++ b/drivers/dma/fsl-qdma.c
@@ -0,0 +1,1259 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright 2014-2015 Freescale
+// Copyright 2018 NXP
+
+/*
+ * Driver for NXP Layerscape Queue Direct Memory Access Controller
+ *
+ * Author:
+ *  Wen He <wen.he_1@nxp.com>
+ *  Jiaheng Fan <jiaheng.fan@nxp.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/of_dma.h>
+#include <linux/dma-mapping.h>
+
+#include "virt-dma.h"
+#include "fsldma.h"
+
+/* Register related definition */
+#define FSL_QDMA_DMR			0x0
+#define FSL_QDMA_DSR			0x4
+#define FSL_QDMA_DEIER			0xe00
+#define FSL_QDMA_DEDR			0xe04
+#define FSL_QDMA_DECFDW0R		0xe10
+#define FSL_QDMA_DECFDW1R		0xe14
+#define FSL_QDMA_DECFDW2R		0xe18
+#define FSL_QDMA_DECFDW3R		0xe1c
+#define FSL_QDMA_DECFQIDR		0xe30
+#define FSL_QDMA_DECBR			0xe34
+
+#define FSL_QDMA_BCQMR(x)		(0xc0 + 0x100 * (x))
+#define FSL_QDMA_BCQSR(x)		(0xc4 + 0x100 * (x))
+#define FSL_QDMA_BCQEDPA_SADDR(x)	(0xc8 + 0x100 * (x))
+#define FSL_QDMA_BCQDPA_SADDR(x)	(0xcc + 0x100 * (x))
+#define FSL_QDMA_BCQEEPA_SADDR(x)	(0xd0 + 0x100 * (x))
+#define FSL_QDMA_BCQEPA_SADDR(x)	(0xd4 + 0x100 * (x))
+#define FSL_QDMA_BCQIER(x)		(0xe0 + 0x100 * (x))
+#define FSL_QDMA_BCQIDR(x)		(0xe4 + 0x100 * (x))
+
+#define FSL_QDMA_SQDPAR			0x80c
+#define FSL_QDMA_SQEPAR			0x814
+#define FSL_QDMA_BSQMR			0x800
+#define FSL_QDMA_BSQSR			0x804
+#define FSL_QDMA_BSQICR			0x828
+#define FSL_QDMA_CQMR			0xa00
+#define FSL_QDMA_CQDSCR1		0xa08
+#define FSL_QDMA_CQDSCR2                0xa0c
+#define FSL_QDMA_CQIER			0xa10
+#define FSL_QDMA_CQEDR			0xa14
+#define FSL_QDMA_SQCCMR			0xa20
+
+/* Registers for bit and genmask */
+#define FSL_QDMA_CQIDR_SQT		BIT(15)
+#define QDMA_CCDF_FOTMAT		BIT(29)
+#define QDMA_CCDF_SER			BIT(30)
+#define QDMA_SG_FIN			BIT(30)
+#define QDMA_SG_LEN_MASK		GENMASK(29, 0)
+#define QDMA_CCDF_MASK			GENMASK(28, 20)
+
+#define FSL_QDMA_DEDR_CLEAR		GENMASK(31, 0)
+#define FSL_QDMA_BCQIDR_CLEAR		GENMASK(31, 0)
+#define FSL_QDMA_DEIER_CLEAR		GENMASK(31, 0)
+
+#define FSL_QDMA_BCQIER_CQTIE		BIT(15)
+#define FSL_QDMA_BCQIER_CQPEIE		BIT(23)
+#define FSL_QDMA_BSQICR_ICEN		BIT(31)
+
+#define FSL_QDMA_BSQICR_ICST(x)		((x) << 16)
+#define FSL_QDMA_CQIER_MEIE		BIT(31)
+#define FSL_QDMA_CQIER_TEIE		BIT(0)
+#define FSL_QDMA_SQCCMR_ENTER_WM	BIT(21)
+
+#define FSL_QDMA_BCQMR_EN		BIT(31)
+#define FSL_QDMA_BCQMR_EI		BIT(30)
+#define FSL_QDMA_BCQMR_CD_THLD(x)	((x) << 20)
+#define FSL_QDMA_BCQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BCQSR_QF		BIT(16)
+#define FSL_QDMA_BCQSR_XOFF		BIT(0)
+
+#define FSL_QDMA_BSQMR_EN		BIT(31)
+#define FSL_QDMA_BSQMR_DI		BIT(30)
+#define FSL_QDMA_BSQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BSQSR_QE		BIT(17)
+
+#define FSL_QDMA_DMR_DQD		BIT(30)
+#define FSL_QDMA_DSR_DB		BIT(31)
+
+/* Size related definition */
+#define FSL_QDMA_QUEUE_MAX		8
+#define FSL_QDMA_COMMAND_BUFFER_SIZE	64
+#define FSL_QDMA_DESCRIPTOR_BUFFER_SIZE 32
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MIN	64
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MAX	16384
+#define FSL_QDMA_QUEUE_NUM_MAX		8
+
+/* Field definition for CMD */
+#define FSL_QDMA_CMD_RWTTYPE		0x4
+#define FSL_QDMA_CMD_LWC                0x2
+#define FSL_QDMA_CMD_RWTTYPE_OFFSET	28
+#define FSL_QDMA_CMD_NS_OFFSET		27
+#define FSL_QDMA_CMD_DQOS_OFFSET	24
+#define FSL_QDMA_CMD_WTHROTL_OFFSET	20
+#define FSL_QDMA_CMD_DSEN_OFFSET	19
+#define FSL_QDMA_CMD_LWC_OFFSET		16
+
+/* Field definition for Descriptor offset */
+#define QDMA_CCDF_STATUS		20
+#define QDMA_CCDF_OFFSET		20
+
+/* Field definition for safe loop count*/
+#define FSL_QDMA_HALT_COUNT		1500
+#define FSL_QDMA_MAX_SIZE		16385
+#define	FSL_QDMA_COMP_TIMEOUT		1000
+#define FSL_COMMAND_QUEUE_OVERFLLOW	10
+
+#define FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma_engine, x)			\
+	(((fsl_qdma_engine)->block_offset) * (x))
+
+/**
+ * struct fsl_qdma_format - This is the struct holding describing compound
+ *			    descriptor format with qDMA.
+ * @status:		    Command status and enqueue status notification.
+ * @cfg:		    Frame offset and frame format.
+ * @addr_lo:		    Holding the compound descriptor of the lower
+ *			    32-bits address in memory 40-bit address.
+ * @addr_hi:		    Same as above member, but point high 8-bits in
+ *			    memory 40-bit address.
+ * @__reserved1:	    Reserved field.
+ * @cfg8b_w1:		    Compound descriptor command queue origin produced
+ *			    by qDMA and dynamic debug field.
+ * @data		    Pointer to the memory 40-bit address, describes DMA
+ *			    source information and DMA destination information.
+ */
+struct fsl_qdma_format {
+	__le32 status;
+	__le32 cfg;
+	union {
+		struct {
+			__le32 addr_lo;
+			u8 addr_hi;
+			u8 __reserved1[2];
+			u8 cfg8b_w1;
+		} __packed;
+		__le64 data;
+	};
+} __packed;
+
+/* qDMA status notification pre information */
+struct fsl_pre_status {
+	u64 addr;
+	u8 queue;
+};
+
+static DEFINE_PER_CPU(struct fsl_pre_status, pre);
+
+struct fsl_qdma_chan {
+	struct virt_dma_chan		vchan;
+	struct virt_dma_desc		vdesc;
+	enum dma_status			status;
+	struct fsl_qdma_engine		*qdma;
+	struct fsl_qdma_queue		*queue;
+};
+
+struct fsl_qdma_queue {
+	struct fsl_qdma_format	*virt_head;
+	struct fsl_qdma_format	*virt_tail;
+	struct list_head	comp_used;
+	struct list_head	comp_free;
+	struct dma_pool		*comp_pool;
+	struct dma_pool		*desc_pool;
+	spinlock_t		queue_lock;
+	dma_addr_t		bus_addr;
+	u32                     n_cq;
+	u32			id;
+	struct fsl_qdma_format	*cq;
+	void __iomem		*block_base;
+};
+
+struct fsl_qdma_comp {
+	dma_addr_t              bus_addr;
+	dma_addr_t              desc_bus_addr;
+	struct fsl_qdma_format	*virt_addr;
+	struct fsl_qdma_format	*desc_virt_addr;
+	struct fsl_qdma_chan	*qchan;
+	struct virt_dma_desc    vdesc;
+	struct list_head	list;
+};
+
+struct fsl_qdma_engine {
+	struct dma_device	dma_dev;
+	void __iomem		*ctrl_base;
+	void __iomem            *status_base;
+	void __iomem		*block_base;
+	u32			n_chans;
+	u32			n_queues;
+	struct mutex            fsl_qdma_mutex;
+	int			error_irq;
+	int			*queue_irq;
+	u32			feature;
+	struct fsl_qdma_queue	*queue;
+	struct fsl_qdma_queue	**status;
+	struct fsl_qdma_chan	*chans;
+	int			block_number;
+	int			block_offset;
+	int			irq_base;
+	int			desc_allocated;
+
+};
+
+static inline u64
+qdma_ccdf_addr_get64(const struct fsl_qdma_format *ccdf)
+{
+	return le64_to_cpu(ccdf->data) & (U64_MAX >> 24);
+}
+
+static inline void
+qdma_desc_addr_set64(struct fsl_qdma_format *ccdf, u64 addr)
+{
+	ccdf->addr_hi = upper_32_bits(addr);
+	ccdf->addr_lo = cpu_to_le32(lower_32_bits(addr));
+}
+
+static inline u8
+qdma_ccdf_get_queue(const struct fsl_qdma_format *ccdf)
+{
+	return ccdf->cfg8b_w1 & U8_MAX;
+}
+
+static inline int
+qdma_ccdf_get_offset(const struct fsl_qdma_format *ccdf)
+{
+	return (le32_to_cpu(ccdf->cfg) & QDMA_CCDF_MASK) >> QDMA_CCDF_OFFSET;
+}
+
+static inline void
+qdma_ccdf_set_format(struct fsl_qdma_format *ccdf, int offset)
+{
+	ccdf->cfg = cpu_to_le32(QDMA_CCDF_FOTMAT | offset);
+}
+
+static inline int
+qdma_ccdf_get_status(const struct fsl_qdma_format *ccdf)
+{
+	return (le32_to_cpu(ccdf->status) & QDMA_CCDF_MASK) >> QDMA_CCDF_STATUS;
+}
+
+static inline void
+qdma_ccdf_set_ser(struct fsl_qdma_format *ccdf, int status)
+{
+	ccdf->status = cpu_to_le32(QDMA_CCDF_SER | status);
+}
+
+static inline void qdma_csgf_set_len(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = cpu_to_le32(len & QDMA_SG_LEN_MASK);
+}
+
+static inline void qdma_csgf_set_f(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = cpu_to_le32(QDMA_SG_FIN | (len & QDMA_SG_LEN_MASK));
+}
+
+static u32 qdma_readl(struct fsl_qdma_engine *qdma, void __iomem *addr)
+{
+	return FSL_DMA_IN(qdma, addr, 32);
+}
+
+static void qdma_writel(struct fsl_qdma_engine *qdma, u32 val,
+			void __iomem *addr)
+{
+	FSL_DMA_OUT(qdma, addr, val, 32);
+}
+
+static struct fsl_qdma_chan *to_fsl_qdma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct fsl_qdma_chan, vchan.chan);
+}
+
+static struct fsl_qdma_comp *to_fsl_qdma_comp(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct fsl_qdma_comp, vdesc);
+}
+
+static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	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);
+
+	if (!fsl_queue->comp_pool && !fsl_queue->comp_pool)
+		return;
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_used,	list) {
+		dma_pool_free(fsl_queue->comp_pool,
+			      comp_temp->virt_addr,
+			      comp_temp->bus_addr);
+		dma_pool_free(fsl_queue->desc_pool,
+			      comp_temp->desc_virt_addr,
+			      comp_temp->desc_bus_addr);
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_free, list) {
+		dma_pool_free(fsl_queue->comp_pool,
+			      comp_temp->virt_addr,
+			      comp_temp->bus_addr);
+		dma_pool_free(fsl_queue->desc_pool,
+			      comp_temp->desc_virt_addr,
+			      comp_temp->desc_bus_addr);
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	dma_pool_destroy(fsl_queue->comp_pool);
+	dma_pool_destroy(fsl_queue->desc_pool);
+
+	fsl_qdma->desc_allocated--;
+	fsl_queue->comp_pool = NULL;
+	fsl_queue->desc_pool = NULL;
+}
+
+static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
+				      dma_addr_t dst, dma_addr_t src, u32 len)
+{
+	struct fsl_qdma_format *sdf, *ddf;
+	struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
+
+	ccdf = fsl_comp->virt_addr;
+	csgf_desc = fsl_comp->virt_addr + 1;
+	csgf_src = fsl_comp->virt_addr + 2;
+	csgf_dest = fsl_comp->virt_addr + 3;
+	sdf = fsl_comp->desc_virt_addr;
+	ddf = fsl_comp->desc_virt_addr + 1;
+
+	memset(fsl_comp->virt_addr, 0, FSL_QDMA_COMMAND_BUFFER_SIZE);
+	memset(fsl_comp->desc_virt_addr, 0, FSL_QDMA_DESCRIPTOR_BUFFER_SIZE);
+	/* Head Command Descriptor(Frame Descriptor) */
+	qdma_desc_addr_set64(ccdf, fsl_comp->bus_addr + 16);
+	qdma_ccdf_set_format(ccdf, qdma_ccdf_get_offset(ccdf));
+	qdma_ccdf_set_ser(ccdf, qdma_ccdf_get_status(ccdf));
+	/* Status notification is enqueued to status queue. */
+	/* Compound Command Descriptor(Frame List Table) */
+	qdma_desc_addr_set64(csgf_desc, fsl_comp->desc_bus_addr);
+	/* It must be 32 as Compound S/G Descriptor */
+	qdma_csgf_set_len(csgf_desc, 32);
+	qdma_desc_addr_set64(csgf_src, src);
+	qdma_csgf_set_len(csgf_src, len);
+	qdma_desc_addr_set64(csgf_dest, dst);
+	qdma_csgf_set_len(csgf_dest, len);
+	/* This entry is the last entry. */
+	qdma_csgf_set_f(csgf_dest, len);
+	/* Descriptor Buffer */
+	sdf->data =
+		cpu_to_le64(FSL_QDMA_CMD_RWTTYPE <<
+			    FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->data =
+		cpu_to_le64(FSL_QDMA_CMD_RWTTYPE <<
+			    FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->data |=
+		cpu_to_le64(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET);
+}
+
+/*
+ * Pre-request full command descriptor for enqueue.
+ */
+static int fsl_qdma_pre_request_enqueue_desc(struct fsl_qdma_queue *queue)
+{
+	int i;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+
+	for (i = 0; i < queue->n_cq + FSL_COMMAND_QUEUE_OVERFLLOW; i++) {
+		comp_temp = kzalloc(sizeof(*comp_temp), GFP_KERNEL);
+		if (!comp_temp)
+			goto err_alloc;
+		comp_temp->virt_addr =
+			dma_pool_alloc(queue->comp_pool, GFP_KERNEL,
+				       &comp_temp->bus_addr);
+		if (!comp_temp->virt_addr)
+			goto err_dma_alloc;
+
+		comp_temp->desc_virt_addr =
+			dma_pool_alloc(queue->desc_pool, GFP_KERNEL,
+				       &comp_temp->desc_bus_addr);
+		if (!comp_temp->desc_virt_addr)
+			goto err_desc_dma_alloc;
+
+		list_add_tail(&comp_temp->list, &queue->comp_free);
+	}
+
+	return 0;
+
+err_desc_dma_alloc:
+	dma_pool_free(queue->comp_pool, comp_temp->virt_addr,
+		      comp_temp->bus_addr);
+
+err_dma_alloc:
+	kfree(comp_temp);
+
+err_alloc:
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &queue->comp_free, list) {
+		if (comp_temp->virt_addr)
+			dma_pool_free(queue->comp_pool,
+				      comp_temp->virt_addr,
+				      comp_temp->bus_addr);
+		if (comp_temp->desc_virt_addr)
+			dma_pool_free(queue->desc_pool,
+				      comp_temp->desc_virt_addr,
+				      comp_temp->desc_bus_addr);
+
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	return -ENOMEM;
+}
+
+/*
+ * Request a command descriptor for enqueue.
+ */
+static struct fsl_qdma_comp
+*fsl_qdma_request_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	unsigned long flags;
+	struct fsl_qdma_comp *comp_temp;
+	int timeout = FSL_QDMA_COMP_TIMEOUT;
+	struct fsl_qdma_queue *queue = fsl_chan->queue;
+
+	while (timeout--) {
+		spin_lock_irqsave(&queue->queue_lock, flags);
+		if (!list_empty(&queue->comp_free)) {
+			comp_temp = list_first_entry(&queue->comp_free,
+						     struct fsl_qdma_comp,
+						     list);
+			list_del(&comp_temp->list);
+
+			spin_unlock_irqrestore(&queue->queue_lock, flags);
+			comp_temp->qchan = fsl_chan;
+			return comp_temp;
+		}
+		spin_unlock_irqrestore(&queue->queue_lock, flags);
+		udelay(1);
+	}
+
+	return NULL;
+}
+
+static struct fsl_qdma_queue
+*fsl_qdma_alloc_queue_resources(struct platform_device *pdev,
+				struct fsl_qdma_engine *fsl_qdma)
+{
+	int ret, len, i, j;
+	int queue_num, block_number;
+	unsigned int queue_size[FSL_QDMA_QUEUE_MAX];
+	struct fsl_qdma_queue *queue_head, *queue_temp;
+
+	queue_num = fsl_qdma->n_queues;
+	block_number = fsl_qdma->block_number;
+
+	if (queue_num > FSL_QDMA_QUEUE_MAX)
+		queue_num = FSL_QDMA_QUEUE_MAX;
+	len = sizeof(*queue_head) * queue_num * block_number;
+	queue_head = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!queue_head)
+		return NULL;
+
+	ret = device_property_read_u32_array(&pdev->dev, "queue-sizes",
+					     queue_size, queue_num);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queue-sizes.\n");
+		return NULL;
+	}
+	for (j = 0; j < block_number; j++) {
+		for (i = 0; i < queue_num; i++) {
+			if (queue_size[i] > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX ||
+			    queue_size[i] < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+				dev_err(&pdev->dev,
+					"Get wrong queue-sizes.\n");
+				return NULL;
+			}
+			queue_temp = queue_head + i + (j * queue_num);
+
+			queue_temp->cq =
+			dma_alloc_coherent(&pdev->dev,
+					   sizeof(struct fsl_qdma_format) *
+					   queue_size[i],
+					   &queue_temp->bus_addr,
+					   GFP_KERNEL);
+			if (!queue_temp->cq)
+				return NULL;
+			queue_temp->block_base = fsl_qdma->block_base +
+				FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+			queue_temp->n_cq = queue_size[i];
+			queue_temp->id = i;
+			queue_temp->virt_head = queue_temp->cq;
+			queue_temp->virt_tail = queue_temp->cq;
+			/*
+			 * List for queue command buffer
+			 */
+			INIT_LIST_HEAD(&queue_temp->comp_used);
+			spin_lock_init(&queue_temp->queue_lock);
+		}
+	}
+	return queue_head;
+}
+
+static struct fsl_qdma_queue
+*fsl_qdma_prep_status_queue(struct platform_device *pdev)
+{
+	int ret;
+	unsigned int status_size;
+	struct fsl_qdma_queue *status_head;
+	struct device_node *np = pdev->dev.of_node;
+
+	ret = of_property_read_u32(np, "status-sizes", &status_size);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get status-sizes.\n");
+		return NULL;
+	}
+	if (status_size > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX ||
+	    status_size < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+		dev_err(&pdev->dev, "Get wrong status_size.\n");
+		return NULL;
+	}
+	status_head = devm_kzalloc(&pdev->dev,
+				   sizeof(*status_head), GFP_KERNEL);
+	if (!status_head)
+		return NULL;
+
+	/*
+	 * Buffer for queue command
+	 */
+	status_head->cq = dma_alloc_coherent(&pdev->dev,
+					     sizeof(struct fsl_qdma_format) *
+					     status_size,
+					     &status_head->bus_addr,
+					     GFP_KERNEL);
+	if (!status_head->cq) {
+		devm_kfree(&pdev->dev, status_head);
+		return NULL;
+	}
+	status_head->n_cq = status_size;
+	status_head->virt_head = status_head->cq;
+	status_head->virt_tail = status_head->cq;
+	status_head->comp_pool = NULL;
+
+	return status_head;
+}
+
+static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
+{
+	u32 reg;
+	int i, j, count = FSL_QDMA_HALT_COUNT;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+
+	/* Disable the command queue and wait for idle state. */
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg |= FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < FSL_QDMA_QUEUE_NUM_MAX; i++)
+			qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQMR(i));
+	}
+	while (1) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DSR);
+		if (!(reg & FSL_QDMA_DSR_DB))
+			break;
+		if (count-- < 0)
+			return -EBUSY;
+		udelay(100);
+	}
+
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+
+		/* Disable status queue. */
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BSQMR);
+
+		/*
+		 * clear the command queue interrupt detect register for
+		 * all queues.
+		 */
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+			    block + FSL_QDMA_BCQIDR(0));
+	}
+
+	return 0;
+}
+
+static int
+fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
+				 void *block,
+				 int id)
+{
+	bool duplicate;
+	u32 reg, i, count;
+	struct fsl_qdma_queue *temp_queue;
+	struct fsl_qdma_format *status_addr;
+	struct fsl_qdma_comp *fsl_comp = NULL;
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+	struct fsl_qdma_queue *fsl_status = fsl_qdma->status[id];
+
+	count = FSL_QDMA_MAX_SIZE;
+
+	while (count--) {
+		duplicate = 0;
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQSR);
+		if (reg & FSL_QDMA_BSQSR_QE)
+			return 0;
+
+		status_addr = fsl_status->virt_head;
+
+		if (qdma_ccdf_get_queue(status_addr) ==
+		   __this_cpu_read(pre.queue) &&
+			qdma_ccdf_addr_get64(status_addr) ==
+			__this_cpu_read(pre.addr))
+			duplicate = 1;
+		i = qdma_ccdf_get_queue(status_addr) +
+			id * fsl_qdma->n_queues;
+		__this_cpu_write(pre.addr, qdma_ccdf_addr_get64(status_addr));
+		__this_cpu_write(pre.queue, qdma_ccdf_get_queue(status_addr));
+		temp_queue = fsl_queue + i;
+
+		spin_lock(&temp_queue->queue_lock);
+		if (list_empty(&temp_queue->comp_used)) {
+			if (!duplicate) {
+				spin_unlock(&temp_queue->queue_lock);
+				return -EAGAIN;
+			}
+		} else {
+			fsl_comp = list_first_entry(&temp_queue->comp_used,
+						    struct fsl_qdma_comp, list);
+			if (fsl_comp->bus_addr + 16 !=
+				__this_cpu_read(pre.addr)) {
+				if (!duplicate) {
+					spin_unlock(&temp_queue->queue_lock);
+					return -EAGAIN;
+				}
+			}
+		}
+
+		if (duplicate) {
+			reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+			reg |= FSL_QDMA_BSQMR_DI;
+			qdma_desc_addr_set64(status_addr, 0x0);
+			fsl_status->virt_head++;
+			if (fsl_status->virt_head == fsl_status->cq
+						   + fsl_status->n_cq)
+				fsl_status->virt_head = fsl_status->cq;
+			qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+			spin_unlock(&temp_queue->queue_lock);
+			continue;
+		}
+		list_del(&fsl_comp->list);
+
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+		reg |= FSL_QDMA_BSQMR_DI;
+		qdma_desc_addr_set64(status_addr, 0x0);
+		fsl_status->virt_head++;
+		if (fsl_status->virt_head == fsl_status->cq + fsl_status->n_cq)
+			fsl_status->virt_head = fsl_status->cq;
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+		spin_unlock(&temp_queue->queue_lock);
+
+		spin_lock(&fsl_comp->qchan->vchan.lock);
+		vchan_cookie_complete(&fsl_comp->vdesc);
+		fsl_comp->qchan->status = DMA_COMPLETE;
+		spin_unlock(&fsl_comp->qchan->vchan.lock);
+	}
+
+	return 0;
+}
+
+static irqreturn_t fsl_qdma_error_handler(int irq, void *dev_id)
+{
+	unsigned int intr;
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	void __iomem *status = fsl_qdma->status_base;
+
+	intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
+
+	if (intr) {
+		dev_err(fsl_qdma->dma_dev.dev, "DMA transaction error!\n");
+		return IRQ_NONE;
+	}
+
+	qdma_writel(fsl_qdma, FSL_QDMA_DEDR_CLEAR, status + FSL_QDMA_DEDR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_qdma_queue_handler(int irq, void *dev_id)
+{
+	int id;
+	unsigned int intr, reg;
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+
+	id = irq - fsl_qdma->irq_base;
+	if (id < 0 && id > fsl_qdma->block_number) {
+		dev_err(fsl_qdma->dma_dev.dev,
+			"irq %d is wrong irq_base is %d\n",
+			irq, fsl_qdma->irq_base);
+	}
+
+	block = fsl_qdma->block_base +
+		FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, id);
+
+	intr = qdma_readl(fsl_qdma, block + FSL_QDMA_BCQIDR(0));
+
+	if ((intr & FSL_QDMA_CQIDR_SQT) != 0)
+		intr = fsl_qdma_queue_transfer_complete(fsl_qdma, block, id);
+
+	if (intr != 0) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+		reg |= FSL_QDMA_DMR_DQD;
+		qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQIER(0));
+		dev_err(fsl_qdma->dma_dev.dev, "QDMA: status err!\n");
+	}
+
+	/* Clear all detected events and interrupts. */
+	qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+		    block + FSL_QDMA_BCQIDR(0));
+
+	return IRQ_HANDLED;
+}
+
+static int
+fsl_qdma_irq_init(struct platform_device *pdev,
+		  struct fsl_qdma_engine *fsl_qdma)
+{
+	int i;
+	int cpu;
+	int ret;
+	char irq_name[20];
+
+	fsl_qdma->error_irq =
+		platform_get_irq_byname(pdev, "qdma-error");
+	if (fsl_qdma->error_irq < 0) {
+		dev_err(&pdev->dev, "Can't get qdma controller irq.\n");
+		return fsl_qdma->error_irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, fsl_qdma->error_irq,
+			       fsl_qdma_error_handler, 0,
+			       "qDMA error", fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register qDMA controller IRQ.\n");
+		return  ret;
+	}
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		sprintf(irq_name, "qdma-queue%d", i);
+		fsl_qdma->queue_irq[i] =
+				platform_get_irq_byname(pdev, irq_name);
+
+		if (fsl_qdma->queue_irq[i] < 0) {
+			dev_err(&pdev->dev,
+				"Can't get qdma queue %d irq.\n", i);
+			return fsl_qdma->queue_irq[i];
+		}
+
+		ret = devm_request_irq(&pdev->dev,
+				       fsl_qdma->queue_irq[i],
+				       fsl_qdma_queue_handler,
+				       0,
+				       "qDMA queue",
+				       fsl_qdma);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Can't register qDMA queue IRQ.\n");
+			return  ret;
+		}
+
+		cpu = i % num_online_cpus();
+		ret = irq_set_affinity_hint(fsl_qdma->queue_irq[i],
+					    get_cpu_mask(cpu));
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Can't set cpu %d affinity to IRQ %d.\n",
+				cpu,
+				fsl_qdma->queue_irq[i]);
+			return  ret;
+		}
+	}
+
+	return 0;
+}
+
+static void fsl_qdma_irq_exit(struct platform_device *pdev,
+			      struct fsl_qdma_engine *fsl_qdma)
+{
+	int i;
+
+	devm_free_irq(&pdev->dev, fsl_qdma->error_irq, fsl_qdma);
+	for (i = 0; i < fsl_qdma->block_number; i++)
+		devm_free_irq(&pdev->dev, fsl_qdma->queue_irq[i], fsl_qdma);
+}
+
+static int fsl_qdma_reg_init(struct fsl_qdma_engine *fsl_qdma)
+{
+	u32 reg;
+	int i, j, ret;
+	struct fsl_qdma_queue *temp;
+	void __iomem *status = fsl_qdma->status_base;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+
+	/* Try to halt the qDMA engine first. */
+	ret = fsl_qdma_halt(fsl_qdma);
+	if (ret) {
+		dev_err(fsl_qdma->dma_dev.dev, "DMA halt failed!");
+		return ret;
+	}
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		/*
+		 * Clear the command queue interrupt detect register for
+		 * all queues.
+		 */
+
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, i);
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+			    block + FSL_QDMA_BCQIDR(0));
+	}
+
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < fsl_qdma->n_queues; i++) {
+			temp = fsl_queue + i + (j * fsl_qdma->n_queues);
+			/*
+			 * Initialize Command Queue registers to
+			 * point to the first
+			 * command descriptor in memory.
+			 * Dequeue Pointer Address Registers
+			 * Enqueue Pointer Address Registers
+			 */
+
+			qdma_writel(fsl_qdma, temp->bus_addr,
+				    block + FSL_QDMA_BCQDPA_SADDR(i));
+			qdma_writel(fsl_qdma, temp->bus_addr,
+				    block + FSL_QDMA_BCQEPA_SADDR(i));
+
+			/* Initialize the queue mode. */
+			reg = FSL_QDMA_BCQMR_EN;
+			reg |= FSL_QDMA_BCQMR_CD_THLD(ilog2(temp->n_cq) - 4);
+			reg |= FSL_QDMA_BCQMR_CQ_SIZE(ilog2(temp->n_cq) - 6);
+			qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BCQMR(i));
+		}
+
+		/*
+		 * Workaround for erratum: ERR010812.
+		 * We must enable XOFF to avoid the enqueue rejection occurs.
+		 * Setting SQCCMR ENTER_WM to 0x20.
+		 */
+
+		qdma_writel(fsl_qdma, FSL_QDMA_SQCCMR_ENTER_WM,
+			    block + FSL_QDMA_SQCCMR);
+
+		/*
+		 * Initialize status queue registers to point to the first
+		 * command descriptor in memory.
+		 * Dequeue Pointer Address Registers
+		 * Enqueue Pointer Address Registers
+		 */
+
+		qdma_writel(fsl_qdma, fsl_qdma->status[j]->bus_addr,
+			    block + FSL_QDMA_SQEPAR);
+		qdma_writel(fsl_qdma, fsl_qdma->status[j]->bus_addr,
+			    block + FSL_QDMA_SQDPAR);
+		/* Initialize status queue interrupt. */
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIER_CQTIE,
+			    block + FSL_QDMA_BCQIER(0));
+		qdma_writel(fsl_qdma, FSL_QDMA_BSQICR_ICEN |
+				   FSL_QDMA_BSQICR_ICST(5) | 0x8000,
+				   block + FSL_QDMA_BSQICR);
+		qdma_writel(fsl_qdma, FSL_QDMA_CQIER_MEIE |
+				   FSL_QDMA_CQIER_TEIE,
+				   block + FSL_QDMA_CQIER);
+
+		/* Initialize the status queue mode. */
+		reg = FSL_QDMA_BSQMR_EN;
+		reg |= FSL_QDMA_BSQMR_CQ_SIZE(ilog2
+			(fsl_qdma->status[j]->n_cq) - 6);
+
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+	}
+
+	/* Initialize controller interrupt register. */
+	qdma_writel(fsl_qdma, FSL_QDMA_DEDR_CLEAR, status + FSL_QDMA_DEDR);
+	qdma_writel(fsl_qdma, FSL_QDMA_DEIER_CLEAR, status + FSL_QDMA_DEIER);
+
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg &= ~FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *
+fsl_qdma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst,
+		     dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	fsl_comp = fsl_qdma_request_enqueue_desc(fsl_chan);
+
+	if (!fsl_comp)
+		return NULL;
+
+	fsl_qdma_comp_fill_memcpy(fsl_comp, dst, src, len);
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_comp->vdesc, flags);
+}
+
+static void fsl_qdma_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	u32 reg;
+	struct virt_dma_desc *vdesc;
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	void __iomem *block = fsl_queue->block_base;
+
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQSR(fsl_queue->id));
+	if (reg & (FSL_QDMA_BCQSR_QF | FSL_QDMA_BCQSR_XOFF))
+		return;
+	vdesc = vchan_next_desc(&fsl_chan->vchan);
+	if (!vdesc)
+		return;
+	list_del(&vdesc->node);
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+
+	memcpy(fsl_queue->virt_head++,
+	       fsl_comp->virt_addr, sizeof(struct fsl_qdma_format));
+	if (fsl_queue->virt_head == fsl_queue->cq + fsl_queue->n_cq)
+		fsl_queue->virt_head = fsl_queue->cq;
+
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_used);
+	barrier();
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	reg |= FSL_QDMA_BCQMR_EI;
+	qdma_writel(fsl_chan->qdma, reg, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	fsl_chan->status = DMA_IN_PROGRESS;
+}
+
+static void fsl_qdma_free_desc(struct virt_dma_desc *vdesc)
+{
+	unsigned long flags;
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_queue *fsl_queue;
+
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+	fsl_queue = fsl_comp->qchan->queue;
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_free);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static void fsl_qdma_issue_pending(struct dma_chan *chan)
+{
+	unsigned long flags;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	spin_lock(&fsl_chan->vchan.lock);
+	if (vchan_issue_pending(&fsl_chan->vchan))
+		fsl_qdma_enqueue_desc(fsl_chan);
+	spin_unlock(&fsl_chan->vchan.lock);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static void fsl_qdma_synchronize(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	vchan_synchronize(&fsl_chan->vchan);
+}
+
+static int fsl_qdma_terminate_all(struct dma_chan *chan)
+{
+	LIST_HEAD(head);
+	unsigned long flags;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	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);
+	return 0;
+}
+
+static int fsl_qdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	int ret;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+
+	if (fsl_queue->comp_pool && fsl_queue->desc_pool)
+		return fsl_qdma->desc_allocated;
+
+	INIT_LIST_HEAD(&fsl_queue->comp_free);
+
+	/*
+	 * The dma pool for queue command buffer
+	 */
+	fsl_queue->comp_pool =
+	dma_pool_create("comp_pool",
+			chan->device->dev,
+			FSL_QDMA_COMMAND_BUFFER_SIZE,
+			64, 0);
+	if (!fsl_queue->comp_pool)
+		return -ENOMEM;
+
+	/*
+	 * The dma pool for Descriptor(SD/DD) buffer
+	 */
+	fsl_queue->desc_pool =
+	dma_pool_create("desc_pool",
+			chan->device->dev,
+			FSL_QDMA_DESCRIPTOR_BUFFER_SIZE,
+			32, 0);
+	if (!fsl_queue->desc_pool)
+		goto err_desc_pool;
+
+	ret = fsl_qdma_pre_request_enqueue_desc(fsl_queue);
+	if (ret) {
+		dev_err(chan->device->dev,
+			"failed to alloc dma buffer for S/G descriptor\n");
+		goto err_mem;
+	}
+
+	fsl_qdma->desc_allocated++;
+	return fsl_qdma->desc_allocated;
+
+err_mem:
+	dma_pool_destroy(fsl_queue->desc_pool);
+err_desc_pool:
+	dma_pool_destroy(fsl_queue->comp_pool);
+	return -ENOMEM;
+}
+
+static int fsl_qdma_probe(struct platform_device *pdev)
+{
+	int ret, i;
+	int blk_num, blk_off;
+	u32 len, chans, queues;
+	struct resource *res;
+	struct fsl_qdma_chan *fsl_chan;
+	struct fsl_qdma_engine *fsl_qdma;
+	struct device_node *np = pdev->dev.of_node;
+
+	ret = of_property_read_u32(np, "dma-channels", &chans);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get dma-channels.\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "block-offset", &blk_off);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get block-offset.\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "block-number", &blk_num);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get block-number.\n");
+		return ret;
+	}
+
+	blk_num = min_t(int, blk_num, num_online_cpus());
+
+	len = sizeof(*fsl_qdma);
+	fsl_qdma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma)
+		return -ENOMEM;
+
+	len = sizeof(*fsl_chan) * chans;
+	fsl_qdma->chans = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->chans)
+		return -ENOMEM;
+
+	len = sizeof(struct fsl_qdma_queue *) * blk_num;
+	fsl_qdma->status = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->status)
+		return -ENOMEM;
+
+	len = sizeof(int) * blk_num;
+	fsl_qdma->queue_irq = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->queue_irq)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(np, "fsl,dma-queues", &queues);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queues.\n");
+		return ret;
+	}
+
+	fsl_qdma->desc_allocated = 0;
+	fsl_qdma->n_chans = chans;
+	fsl_qdma->n_queues = queues;
+	fsl_qdma->block_number = blk_num;
+	fsl_qdma->block_offset = blk_off;
+
+	mutex_init(&fsl_qdma->fsl_qdma_mutex);
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		fsl_qdma->status[i] = fsl_qdma_prep_status_queue(pdev);
+		if (!fsl_qdma->status[i])
+			return -ENOMEM;
+	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	fsl_qdma->ctrl_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->ctrl_base))
+		return PTR_ERR(fsl_qdma->ctrl_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	fsl_qdma->status_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->status_base))
+		return PTR_ERR(fsl_qdma->status_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	fsl_qdma->block_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->block_base))
+		return PTR_ERR(fsl_qdma->block_base);
+	fsl_qdma->queue = fsl_qdma_alloc_queue_resources(pdev, fsl_qdma);
+	if (!fsl_qdma->queue)
+		return -ENOMEM;
+
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
+	fsl_qdma->feature = of_property_read_bool(np, "big-endian");
+	INIT_LIST_HEAD(&fsl_qdma->dma_dev.channels);
+
+	for (i = 0; i < fsl_qdma->n_chans; i++) {
+		struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[i];
+
+		fsl_chan->qdma = fsl_qdma;
+		fsl_chan->queue = fsl_qdma->queue + i % (fsl_qdma->n_queues *
+							fsl_qdma->block_number);
+		fsl_chan->vchan.desc_free = fsl_qdma_free_desc;
+		vchan_init(&fsl_chan->vchan, &fsl_qdma->dma_dev);
+	}
+
+	dma_cap_set(DMA_MEMCPY, fsl_qdma->dma_dev.cap_mask);
+
+	fsl_qdma->dma_dev.dev = &pdev->dev;
+	fsl_qdma->dma_dev.device_free_chan_resources =
+		fsl_qdma_free_chan_resources;
+	fsl_qdma->dma_dev.device_alloc_chan_resources =
+		fsl_qdma_alloc_chan_resources;
+	fsl_qdma->dma_dev.device_tx_status = dma_cookie_status;
+	fsl_qdma->dma_dev.device_prep_dma_memcpy = fsl_qdma_prep_memcpy;
+	fsl_qdma->dma_dev.device_issue_pending = fsl_qdma_issue_pending;
+	fsl_qdma->dma_dev.device_synchronize = fsl_qdma_synchronize;
+	fsl_qdma->dma_dev.device_terminate_all = fsl_qdma_terminate_all;
+
+	dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+
+	platform_set_drvdata(pdev, fsl_qdma);
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Can't register NXP Layerscape qDMA engine.\n");
+		return ret;
+	}
+
+	ret = fsl_qdma_reg_init(fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev)
+{
+	struct fsl_qdma_chan *chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan,
+				 &dmadev->channels, vchan.chan.device_node) {
+		list_del(&chan->vchan.chan.device_node);
+		tasklet_kill(&chan->vchan.task);
+	}
+}
+
+static int fsl_qdma_remove(struct platform_device *pdev)
+{
+	int i;
+	struct fsl_qdma_queue *status;
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
+
+	fsl_qdma_irq_exit(pdev, fsl_qdma);
+	fsl_qdma_cleanup_vchan(&fsl_qdma->dma_dev);
+	of_dma_controller_free(np);
+	dma_async_device_unregister(&fsl_qdma->dma_dev);
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		status = fsl_qdma->status[i];
+		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) *
+				status->n_cq, status->cq, status->bus_addr);
+	}
+	return 0;
+}
+
+static const struct of_device_id fsl_qdma_dt_ids[] = {
+	{ .compatible = "fsl,ls1021a-qdma", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_qdma_dt_ids);
+
+static struct platform_driver fsl_qdma_driver = {
+	.driver		= {
+		.name	= "fsl-qdma",
+		.of_match_table = fsl_qdma_dt_ids,
+	},
+	.probe          = fsl_qdma_probe,
+	.remove		= fsl_qdma_remove,
+};
+
+module_platform_driver(fsl_qdma_driver);
+
+MODULE_ALIAS("platform:fsl-qdma");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("NXP Layerscape qDMA engine driver");
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 9d360a3fbae3..1e38e6b94006 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -53,42 +53,42 @@ static const char msg_ld_oom[] = "No free memory for link descriptor";
 
 static void set_sr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->sr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->sr, val, 32);
 }
 
 static u32 get_sr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->sr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->sr, 32);
 }
 
 static void set_mr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->mr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->mr, val, 32);
 }
 
 static u32 get_mr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->mr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->mr, 32);
 }
 
 static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
 {
-	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
+	FSL_DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
 }
 
 static dma_addr_t get_cdar(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
+	return FSL_DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
 }
 
 static void set_bcr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->bcr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->bcr, val, 32);
 }
 
 static u32 get_bcr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->bcr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->bcr, 32);
 }
 
 /*
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 4787d485dd76..a9b12f82b5c3 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -196,39 +196,67 @@ struct fsldma_chan {
 #define to_fsl_desc(lh) container_of(lh, struct fsl_desc_sw, node)
 #define tx_to_fsl_desc(tx) container_of(tx, struct fsl_desc_sw, async_tx)
 
-#ifndef __powerpc64__
-static u64 in_be64(const u64 __iomem *addr)
+#ifdef	CONFIG_PPC
+#define fsl_ioread32(p)		in_le32(p)
+#define fsl_ioread32be(p)	in_be32(p)
+#define fsl_iowrite32(v, p)	out_le32(p, v)
+#define fsl_iowrite32be(v, p)	out_be32(p, v)
+
+#ifdef __powerpc64__
+#define fsl_ioread64(p)		in_le64(p)
+#define fsl_ioread64be(p)	in_be64(p)
+#define fsl_iowrite64(v, p)	out_le64(p, v)
+#define fsl_iowrite64be(v, p)	out_be64(p, v)
+#else
+static u64 fsl_ioread64(const u64 __iomem *addr)
 {
-	return ((u64)in_be32((u32 __iomem *)addr) << 32) |
-		(in_be32((u32 __iomem *)addr + 1));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32;
+
+	return fsl_addr_hi | in_le32((u32 *)fsl_addr);
 }
 
-static void out_be64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64(u64 val, u64 __iomem *addr)
 {
-	out_be32((u32 __iomem *)addr, val >> 32);
-	out_be32((u32 __iomem *)addr + 1, (u32)val);
+	out_le32((u32 __iomem *)addr + 1, val >> 32);
+	out_le32((u32 __iomem *)addr, (u32)val);
 }
 
-/* There is no asm instructions for 64 bits reverse loads and stores */
-static u64 in_le64(const u64 __iomem *addr)
+static u64 fsl_ioread64be(const u64 __iomem *addr)
 {
-	return ((u64)in_le32((u32 __iomem *)addr + 1) << 32) |
-		(in_le32((u32 __iomem *)addr));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32;
+
+	return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1));
 }
 
-static void out_le64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64be(u64 val, u64 __iomem *addr)
 {
-	out_le32((u32 __iomem *)addr + 1, val >> 32);
-	out_le32((u32 __iomem *)addr, (u32)val);
+	out_be32((u32 __iomem *)addr, val >> 32);
+	out_be32((u32 __iomem *)addr + 1, (u32)val);
 }
 #endif
+#endif
 
-#define DMA_IN(fsl_chan, addr, width)					\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			in_be##width(addr) : in_le##width(addr))
-#define DMA_OUT(fsl_chan, addr, val, width)				\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			out_be##width(addr, val) : out_le##width(addr, val))
+#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
+#define fsl_ioread32(p)		ioread32(p)
+#define fsl_ioread32be(p)	ioread32be(p)
+#define fsl_iowrite32(v, p)	iowrite32(v, p)
+#define fsl_iowrite32be(v, p)	iowrite32be(v, p)
+#define fsl_ioread64(p)		ioread64(p)
+#define fsl_ioread64be(p)	ioread64be(p)
+#define fsl_iowrite64(v, p)	iowrite64(v, p)
+#define fsl_iowrite64be(v, p)	iowrite64be(v, p)
+#endif
+
+#define FSL_DMA_IN(fsl_dma, addr, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_ioread##width##be(addr) : fsl_ioread##width(addr))
+
+#define FSL_DMA_OUT(fsl_dma, addr, val, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_iowrite##width##be(val, addr) : fsl_iowrite	\
+		##width(val, addr))
 
 #define DMA_TO_CPU(fsl_chan, d, width)					\
 		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index c2fff3f6c9ca..00a089e24150 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -278,14 +278,14 @@ static int imxdma_hw_chain(struct imxdma_channel *imxdmac)
 /*
  * imxdma_sg_next - prepare next chunk for scatter-gather DMA emulation
  */
-static inline int imxdma_sg_next(struct imxdma_desc *d)
+static inline void imxdma_sg_next(struct imxdma_desc *d)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct scatterlist *sg = d->sg;
-	unsigned long now;
+	size_t now;
 
-	now = min(d->len, sg_dma_len(sg));
+	now = min_t(size_t, d->len, sg_dma_len(sg));
 	if (d->len != IMX_DMA_LENGTH_LOOP)
 		d->len -= now;
 
@@ -303,8 +303,6 @@ static inline int imxdma_sg_next(struct imxdma_desc *d)
 		 imx_dmav1_readl(imxdma, DMA_DAR(imxdmac->channel)),
 		 imx_dmav1_readl(imxdma, DMA_SAR(imxdmac->channel)),
 		 imx_dmav1_readl(imxdma, DMA_CNTR(imxdmac->channel)));
-
-	return now;
 }
 
 static void imxdma_enable_hw(struct imxdma_desc *d)
@@ -618,7 +616,7 @@ static void imxdma_tasklet(unsigned long data)
 {
 	struct imxdma_channel *imxdmac = (void *)data;
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
-	struct imxdma_desc *desc;
+	struct imxdma_desc *desc, *next_desc;
 	unsigned long flags;
 
 	spin_lock_irqsave(&imxdma->lock, flags);
@@ -648,10 +646,10 @@ static void imxdma_tasklet(unsigned long data)
 	list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free);
 
 	if (!list_empty(&imxdmac->ld_queue)) {
-		desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc,
-					node);
+		next_desc = list_first_entry(&imxdmac->ld_queue,
+					     struct imxdma_desc, node);
 		list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active);
-		if (imxdma_xfer_desc(desc) < 0)
+		if (imxdma_xfer_desc(next_desc) < 0)
 			dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n",
 				 __func__, imxdmac->channel);
 	}
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index cb1b44d78a1f..5f3c1378b90e 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -335,6 +335,7 @@ struct sdma_desc {
  * @sdma:		pointer to the SDMA engine for this channel
  * @channel:		the channel number, matches dmaengine chan_id + 1
  * @direction:		transfer type. Needed for setting SDMA script
+ * @slave_config	Slave configuration
  * @peripheral_type:	Peripheral type. Needed for setting SDMA script
  * @event_id0:		aka dma request line
  * @event_id1:		for channels that use 2 events
@@ -362,6 +363,7 @@ struct sdma_channel {
 	struct sdma_engine		*sdma;
 	unsigned int			channel;
 	enum dma_transfer_direction		direction;
+	struct dma_slave_config		slave_config;
 	enum sdma_peripheral_type	peripheral_type;
 	unsigned int			event_id0;
 	unsigned int			event_id1;
@@ -375,6 +377,7 @@ struct sdma_channel {
 	unsigned long			watermark_level;
 	u32				shp_addr, per_addr;
 	enum dma_status			status;
+	bool				context_loaded;
 	struct imx_dma_data		data;
 	struct work_struct		terminate_worker;
 };
@@ -438,8 +441,14 @@ struct sdma_engine {
 	unsigned int			irq;
 	dma_addr_t			bd0_phys;
 	struct sdma_buffer_descriptor	*bd0;
+	/* clock ratio for AHB:SDMA core. 1:1 is 1, 2:1 is 0*/
+	bool				clk_ratio;
 };
 
+static int sdma_config_write(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg,
+		       enum dma_transfer_direction direction);
+
 static struct sdma_driver_data sdma_imx31 = {
 	.chnenbl0 = SDMA_CHNENBL0_IMX31,
 	.num_events = 32,
@@ -656,8 +665,11 @@ static int sdma_run_channel0(struct sdma_engine *sdma)
 		dev_err(sdma->dev, "Timeout waiting for CH0 ready\n");
 
 	/* Set bits of CONFIG register with dynamic context switching */
-	if (readl(sdma->regs + SDMA_H_CONFIG) == 0)
-		writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+	reg = readl(sdma->regs + SDMA_H_CONFIG);
+	if ((reg & SDMA_H_CONFIG_CSM) == 0) {
+		reg |= SDMA_H_CONFIG_CSM;
+		writel_relaxed(reg, sdma->regs + SDMA_H_CONFIG);
+	}
 
 	return ret;
 }
@@ -671,9 +683,7 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 	int ret;
 	unsigned long flags;
 
-	buf_virt = dma_alloc_coherent(NULL,
-			size,
-			&buf_phys, GFP_KERNEL);
+	buf_virt = dma_alloc_coherent(sdma->dev, size, &buf_phys, GFP_KERNEL);
 	if (!buf_virt) {
 		return -ENOMEM;
 	}
@@ -692,7 +702,7 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 
 	spin_unlock_irqrestore(&sdma->channel_0_lock, flags);
 
-	dma_free_coherent(NULL, size, buf_virt, buf_phys);
+	dma_free_coherent(sdma->dev, size, buf_virt, buf_phys);
 
 	return ret;
 }
@@ -966,6 +976,9 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 	int ret;
 	unsigned long flags;
 
+	if (sdmac->context_loaded)
+		return 0;
+
 	if (sdmac->direction == DMA_DEV_TO_MEM)
 		load_address = sdmac->pc_from_device;
 	else if (sdmac->direction == DMA_DEV_TO_DEV)
@@ -1008,6 +1021,8 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 
 	spin_unlock_irqrestore(&sdma->channel_0_lock, flags);
 
+	sdmac->context_loaded = true;
+
 	return ret;
 }
 
@@ -1047,6 +1062,7 @@ static void sdma_channel_terminate_work(struct work_struct *work)
 	sdmac->desc = NULL;
 	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 	vchan_dma_desc_free_list(&sdmac->vc, &head);
+	sdmac->context_loaded = false;
 }
 
 static int sdma_disable_channel_async(struct dma_chan *chan)
@@ -1122,18 +1138,6 @@ static int sdma_config_channel(struct dma_chan *chan)
 	sdmac->shp_addr = 0;
 	sdmac->per_addr = 0;
 
-	if (sdmac->event_id0) {
-		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id0);
-	}
-
-	if (sdmac->event_id1) {
-		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id1);
-	}
-
 	switch (sdmac->peripheral_type) {
 	case IMX_DMATYPE_DSP:
 		sdma_config_ownership(sdmac, false, true, true);
@@ -1190,7 +1194,7 @@ static int sdma_request_channel0(struct sdma_engine *sdma)
 {
 	int ret = -EBUSY;
 
-	sdma->bd0 = dma_zalloc_coherent(NULL, PAGE_SIZE, &sdma->bd0_phys,
+	sdma->bd0 = dma_alloc_coherent(sdma->dev, PAGE_SIZE, &sdma->bd0_phys,
 					GFP_NOWAIT);
 	if (!sdma->bd0) {
 		ret = -ENOMEM;
@@ -1213,8 +1217,8 @@ static int sdma_alloc_bd(struct sdma_desc *desc)
 	u32 bd_size = desc->num_bd * sizeof(struct sdma_buffer_descriptor);
 	int ret = 0;
 
-	desc->bd = dma_zalloc_coherent(NULL, bd_size, &desc->bd_phys,
-					GFP_NOWAIT);
+	desc->bd = dma_alloc_coherent(desc->sdmac->sdma->dev, bd_size,
+				       &desc->bd_phys, GFP_NOWAIT);
 	if (!desc->bd) {
 		ret = -ENOMEM;
 		goto out;
@@ -1227,7 +1231,8 @@ static void sdma_free_bd(struct sdma_desc *desc)
 {
 	u32 bd_size = desc->num_bd * sizeof(struct sdma_buffer_descriptor);
 
-	dma_free_coherent(NULL, bd_size, desc->bd, desc->bd_phys);
+	dma_free_coherent(desc->sdmac->sdma->dev, bd_size, desc->bd,
+			  desc->bd_phys);
 }
 
 static void sdma_desc_free(struct virt_dma_desc *vd)
@@ -1431,6 +1436,8 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
 	struct scatterlist *sg;
 	struct sdma_desc *desc;
 
+	sdma_config_write(chan, &sdmac->slave_config, direction);
+
 	desc = sdma_transfer_init(sdmac, direction, sg_len);
 	if (!desc)
 		goto err_out;
@@ -1515,6 +1522,8 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 
 	dev_dbg(sdma->dev, "%s channel: %d\n", __func__, channel);
 
+	sdma_config_write(chan, &sdmac->slave_config, direction);
+
 	desc = sdma_transfer_init(sdmac, direction, num_periods);
 	if (!desc)
 		goto err_out;
@@ -1570,17 +1579,18 @@ err_out:
 	return NULL;
 }
 
-static int sdma_config(struct dma_chan *chan,
-		       struct dma_slave_config *dmaengine_cfg)
+static int sdma_config_write(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg,
+		       enum dma_transfer_direction direction)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 
-	if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		sdmac->per_address = dmaengine_cfg->src_addr;
 		sdmac->watermark_level = dmaengine_cfg->src_maxburst *
 			dmaengine_cfg->src_addr_width;
 		sdmac->word_size = dmaengine_cfg->src_addr_width;
-	} else if (dmaengine_cfg->direction == DMA_DEV_TO_DEV) {
+	} else if (direction == DMA_DEV_TO_DEV) {
 		sdmac->per_address2 = dmaengine_cfg->src_addr;
 		sdmac->per_address = dmaengine_cfg->dst_addr;
 		sdmac->watermark_level = dmaengine_cfg->src_maxburst &
@@ -1594,10 +1604,33 @@ static int sdma_config(struct dma_chan *chan,
 			dmaengine_cfg->dst_addr_width;
 		sdmac->word_size = dmaengine_cfg->dst_addr_width;
 	}
-	sdmac->direction = dmaengine_cfg->direction;
+	sdmac->direction = direction;
 	return sdma_config_channel(chan);
 }
 
+static int sdma_config(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg)
+{
+	struct sdma_channel *sdmac = to_sdma_chan(chan);
+
+	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
+
+	/* Set ENBLn earlier to make sure dma request triggered after that */
+	if (sdmac->event_id0) {
+		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
+			return -EINVAL;
+		sdma_event_enable(sdmac, sdmac->event_id0);
+	}
+
+	if (sdmac->event_id1) {
+		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
+			return -EINVAL;
+		sdma_event_enable(sdmac, sdmac->event_id1);
+	}
+
+	return 0;
+}
+
 static enum dma_status sdma_tx_status(struct dma_chan *chan,
 				      dma_cookie_t cookie,
 				      struct dma_tx_state *txstate)
@@ -1819,10 +1852,13 @@ 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))
+		sdma->clk_ratio = 1;
+
 	/* Be sure SDMA has not started yet */
 	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
 
-	sdma->channel_control = dma_alloc_coherent(NULL,
+	sdma->channel_control = dma_alloc_coherent(sdma->dev,
 			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) +
 			sizeof(struct sdma_context_data),
 			&ccb_phys, GFP_KERNEL);
@@ -1859,8 +1895,10 @@ static int sdma_init(struct sdma_engine *sdma)
 	writel_relaxed(0x4050, sdma->regs + SDMA_CHN0ADDR);
 
 	/* Set bits of CONFIG register but with static context switching */
-	/* FIXME: Check whether to set ACR bit depending on clock ratios */
-	writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
+	if (sdma->clk_ratio)
+		writel_relaxed(SDMA_H_CONFIG_ACR, sdma->regs + SDMA_H_CONFIG);
+	else
+		writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
 
 	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
@@ -1883,11 +1921,16 @@ disable_clk_ipg:
 static bool sdma_filter_fn(struct dma_chan *chan, void *fn_param)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	struct sdma_engine *sdma = sdmac->sdma;
 	struct imx_dma_data *data = fn_param;
 
 	if (!imx_dma_is_general_purpose(chan))
 		return false;
 
+	/* return false if it's not the right device */
+	if (sdma->dev->of_node != data->of_node)
+		return false;
+
 	sdmac->data = *data;
 	chan->private = &sdmac->data;
 
@@ -1915,6 +1958,7 @@ static struct dma_chan *sdma_xlate(struct of_phandle_args *dma_spec,
 	 * be set to sdmac->event_id1.
 	 */
 	data.dma_request2 = 0;
+	data.of_node = ofdma->of_node;
 
 	return dma_request_channel(mask, sdma_filter_fn, &data);
 }
@@ -2077,6 +2121,7 @@ static int sdma_probe(struct platform_device *pdev)
 	sdma->dma_device.device_prep_dma_memcpy = sdma_prep_memcpy;
 	sdma->dma_device.device_issue_pending = sdma_issue_pending;
 	sdma->dma_device.dev->dma_parms = &sdma->dma_parms;
+	sdma->dma_device.copy_align = 2;
 	dma_set_max_seg_size(sdma->dma_device.dev, SDMA_BD_MAX_CNT);
 
 	platform_set_drvdata(pdev, sdma);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 23fb2fa04000..f373a139e0c3 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -372,6 +372,7 @@ struct ioat_ring_ent **
 ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 {
 	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
 	struct ioat_ring_ent **ring;
 	int total_descs = 1 << order;
 	int i, chunks;
@@ -437,6 +438,17 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 	}
 	ring[i]->hw->next = ring[0]->txd.phys;
 
+	/* setup descriptor pre-fetching for v3.4 */
+	if (ioat_dma->cap & IOAT_CAP_DPS) {
+		u16 drsctl = IOAT_CHAN_DRSZ_2MB | IOAT_CHAN_DRS_EN;
+
+		if (chunks == 1)
+			drsctl |= IOAT_CHAN_DRS_AUTOWRAP;
+
+		writew(drsctl, ioat_chan->reg_base + IOAT_CHAN_DRSCTL_OFFSET);
+
+	}
+
 	return ring;
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 1ab42ec2b7ff..aaafd0e882b5 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -27,7 +27,7 @@
 #include "registers.h"
 #include "hw.h"
 
-#define IOAT_DMA_VERSION  "4.00"
+#define IOAT_DMA_VERSION  "5.00"
 
 #define IOAT_DMA_DCA_ANY_CPU		~0
 
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index abcc51b343ce..781c94de8e81 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -66,11 +66,14 @@
 
 #define PCI_DEVICE_ID_INTEL_IOAT_SKX	0x2021
 
+#define PCI_DEVICE_ID_INTEL_IOAT_ICX	0x0b00
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */
 #define IOAT_VER_3_2            0x32    /* Version 3.2 */
 #define IOAT_VER_3_3            0x33    /* Version 3.3 */
+#define IOAT_VER_3_4		0x34	/* Version 3.4 */
 
 
 int system_has_dca_enabled(struct pci_dev *pdev);
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 2d810dfcdc48..d41dc9a9ff68 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -119,6 +119,9 @@ static const struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE2) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE3) },
 
+	/* I/OAT v3.4 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_ICX) },
+
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
@@ -135,10 +138,10 @@ static int ioat3_dma_self_test(struct ioatdma_device *ioat_dma);
 static int ioat_dca_enabled = 1;
 module_param(ioat_dca_enabled, int, 0644);
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
-int ioat_pending_level = 4;
+int ioat_pending_level = 7;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
-		 "high-water mark for pushing ioat descriptors (default: 4)");
+		 "high-water mark for pushing ioat descriptors (default: 7)");
 static char ioat_interrupt_style[32] = "msix";
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
 		    sizeof(ioat_interrupt_style), 0644);
@@ -635,6 +638,11 @@ static void ioat_free_chan_resources(struct dma_chan *c)
 	ioat_stop(ioat_chan);
 	ioat_reset_hw(ioat_chan);
 
+	/* Put LTR to idle */
+	if (ioat_dma->version >= IOAT_VER_3_4)
+		writeb(IOAT_CHAN_LTR_SWSEL_IDLE,
+			ioat_chan->reg_base + IOAT_CHAN_LTR_SWSEL_OFFSET);
+
 	spin_lock_bh(&ioat_chan->cleanup_lock);
 	spin_lock_bh(&ioat_chan->prep_lock);
 	descs = ioat_ring_space(ioat_chan);
@@ -724,6 +732,28 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	spin_unlock_bh(&ioat_chan->prep_lock);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 
+	/* Setting up LTR values for 3.4 or later */
+	if (ioat_chan->ioat_dma->version >= IOAT_VER_3_4) {
+		u32 lat_val;
+
+		lat_val = IOAT_CHAN_LTR_ACTIVE_SNVAL |
+			IOAT_CHAN_LTR_ACTIVE_SNLATSCALE |
+			IOAT_CHAN_LTR_ACTIVE_SNREQMNT;
+		writel(lat_val, ioat_chan->reg_base +
+				IOAT_CHAN_LTR_ACTIVE_OFFSET);
+
+		lat_val = IOAT_CHAN_LTR_IDLE_SNVAL |
+			  IOAT_CHAN_LTR_IDLE_SNLATSCALE |
+			  IOAT_CHAN_LTR_IDLE_SNREQMNT;
+		writel(lat_val, ioat_chan->reg_base +
+				IOAT_CHAN_LTR_IDLE_OFFSET);
+
+		/* Select to active */
+		writeb(IOAT_CHAN_LTR_SWSEL_ACTIVE,
+		       ioat_chan->reg_base +
+		       IOAT_CHAN_LTR_SWSEL_OFFSET);
+	}
+
 	ioat_start_null_desc(ioat_chan);
 
 	/* check that we got off the ground */
@@ -1185,6 +1215,10 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	if (err)
 		return err;
 
+	if (ioat_dma->cap & IOAT_CAP_DPS)
+		writeb(ioat_pending_level + 1,
+		       ioat_dma->reg_base + IOAT_PREFETCH_LIMIT_OFFSET);
+
 	return 0;
 }
 
@@ -1350,6 +1384,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_set_drvdata(pdev, device);
 
 	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
+	if (device->version >= IOAT_VER_3_4)
+		ioat_dca_enabled = 0;
 	if (device->version >= IOAT_VER_3_0) {
 		if (is_skx_ioat(pdev))
 			device->version = IOAT_VER_3_2;
diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h
index 2f3bbc88ff2a..99c1c24d465d 100644
--- a/drivers/dma/ioat/registers.h
+++ b/drivers/dma/ioat/registers.h
@@ -84,6 +84,9 @@
 #define IOAT_CAP_PQ				0x00000200
 #define IOAT_CAP_DWBES				0x00002000
 #define IOAT_CAP_RAID16SS			0x00020000
+#define IOAT_CAP_DPS				0x00800000
+
+#define IOAT_PREFETCH_LIMIT_OFFSET		0x4C	/* CHWPREFLMT */
 
 #define IOAT_CHANNEL_MMIO_SIZE			0x80	/* Each Channel MMIO space is this size */
 
@@ -243,4 +246,25 @@
 
 #define IOAT_CHANERR_MASK_OFFSET		0x2C	/* 32-bit Channel Error Register */
 
+#define IOAT_CHAN_DRSCTL_OFFSET			0xB6
+#define IOAT_CHAN_DRSZ_4KB			0x0000
+#define IOAT_CHAN_DRSZ_8KB			0x0001
+#define IOAT_CHAN_DRSZ_2MB			0x0009
+#define IOAT_CHAN_DRS_EN			0x0100
+#define IOAT_CHAN_DRS_AUTOWRAP			0x0200
+
+#define IOAT_CHAN_LTR_SWSEL_OFFSET		0xBC
+#define IOAT_CHAN_LTR_SWSEL_ACTIVE		0x0
+#define IOAT_CHAN_LTR_SWSEL_IDLE		0x1
+
+#define IOAT_CHAN_LTR_ACTIVE_OFFSET		0xC0
+#define IOAT_CHAN_LTR_ACTIVE_SNVAL		0x0000	/* 0 us */
+#define IOAT_CHAN_LTR_ACTIVE_SNLATSCALE		0x0800	/* 1us scale */
+#define IOAT_CHAN_LTR_ACTIVE_SNREQMNT		0x8000	/* snoop req enable */
+
+#define IOAT_CHAN_LTR_IDLE_OFFSET		0xC4
+#define IOAT_CHAN_LTR_IDLE_SNVAL		0x0258	/* 600 us */
+#define IOAT_CHAN_LTR_IDLE_SNLATSCALE		0x0800	/* 1us scale */
+#define IOAT_CHAN_LTR_IDLE_SNREQMNT		0x8000	/* snoop req enable */
+
 #endif /* _IOAT_REGISTERS_H_ */
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index fdec2b6cfbb0..5737d92eaeeb 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -52,8 +52,6 @@
 #define CX_SRC			0x814
 #define CX_DST			0x818
 #define CX_CFG			0x81c
-#define AXI_CFG			0x820
-#define AXI_CFG_DEFAULT		0x201201
 
 #define CX_LLI_CHAIN_EN		0x2
 #define CX_CFG_EN		0x1
@@ -113,9 +111,18 @@ struct k3_dma_dev {
 	struct dma_pool		*pool;
 	u32			dma_channels;
 	u32			dma_requests;
+	u32			dma_channel_mask;
 	unsigned int		irq;
 };
 
+
+#define K3_FLAG_NOCLK	BIT(1)
+
+struct k3dma_soc_data {
+	unsigned long flags;
+};
+
+
 #define to_k3_dma(dmadev) container_of(dmadev, struct k3_dma_dev, slave)
 
 static int k3_dma_config_write(struct dma_chan *chan,
@@ -161,7 +168,6 @@ static void k3_dma_set_desc(struct k3_dma_phy *phy, struct k3_desc_hw *hw)
 	writel_relaxed(hw->count, phy->base + CX_CNT0);
 	writel_relaxed(hw->saddr, phy->base + CX_SRC);
 	writel_relaxed(hw->daddr, phy->base + CX_DST);
-	writel_relaxed(AXI_CFG_DEFAULT, phy->base + AXI_CFG);
 	writel_relaxed(hw->config, phy->base + CX_CFG);
 }
 
@@ -314,6 +320,9 @@ static void k3_dma_tasklet(unsigned long arg)
 	/* check new channel request in d->chan_pending */
 	spin_lock_irq(&d->lock);
 	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (!(d->dma_channel_mask & (1 << pch)))
+			continue;
+
 		p = &d->phy[pch];
 
 		if (p->vchan == NULL && !list_empty(&d->chan_pending)) {
@@ -331,6 +340,9 @@ static void k3_dma_tasklet(unsigned long arg)
 	spin_unlock_irq(&d->lock);
 
 	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (!(d->dma_channel_mask & (1 << pch)))
+			continue;
+
 		if (pch_alloc & (1 << pch)) {
 			p = &d->phy[pch];
 			c = p->vchan;
@@ -790,8 +802,21 @@ static int k3_dma_transfer_resume(struct dma_chan *chan)
 	return 0;
 }
 
+static const struct k3dma_soc_data k3_v1_dma_data = {
+	.flags = 0,
+};
+
+static const struct k3dma_soc_data asp_v1_dma_data = {
+	.flags = K3_FLAG_NOCLK,
+};
+
 static const struct of_device_id k3_pdma_dt_ids[] = {
-	{ .compatible = "hisilicon,k3-dma-1.0", },
+	{ .compatible = "hisilicon,k3-dma-1.0",
+	  .data = &k3_v1_dma_data
+	},
+	{ .compatible = "hisilicon,hisi-pcm-asp-dma-1.0",
+	  .data = &asp_v1_dma_data
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, k3_pdma_dt_ids);
@@ -810,6 +835,7 @@ static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
 
 static int k3_dma_probe(struct platform_device *op)
 {
+	const struct k3dma_soc_data *soc_data;
 	struct k3_dma_dev *d;
 	const struct of_device_id *of_id;
 	struct resource *iores;
@@ -823,6 +849,10 @@ static int k3_dma_probe(struct platform_device *op)
 	if (!d)
 		return -ENOMEM;
 
+	soc_data = device_get_match_data(&op->dev);
+	if (!soc_data)
+		return -EINVAL;
+
 	d->base = devm_ioremap_resource(&op->dev, iores);
 	if (IS_ERR(d->base))
 		return PTR_ERR(d->base);
@@ -833,12 +863,21 @@ static int k3_dma_probe(struct platform_device *op)
 				"dma-channels", &d->dma_channels);
 		of_property_read_u32((&op->dev)->of_node,
 				"dma-requests", &d->dma_requests);
+		ret = of_property_read_u32((&op->dev)->of_node,
+				"dma-channel-mask", &d->dma_channel_mask);
+		if (ret) {
+			dev_warn(&op->dev,
+				 "dma-channel-mask doesn't exist, considering all as available.\n");
+			d->dma_channel_mask = (u32)~0UL;
+		}
 	}
 
-	d->clk = devm_clk_get(&op->dev, NULL);
-	if (IS_ERR(d->clk)) {
-		dev_err(&op->dev, "no dma clk\n");
-		return PTR_ERR(d->clk);
+	if (!(soc_data->flags & K3_FLAG_NOCLK)) {
+		d->clk = devm_clk_get(&op->dev, NULL);
+		if (IS_ERR(d->clk)) {
+			dev_err(&op->dev, "no dma clk\n");
+			return PTR_ERR(d->clk);
+		}
 	}
 
 	irq = platform_get_irq(op, 0);
@@ -862,8 +901,12 @@ static int k3_dma_probe(struct platform_device *op)
 		return -ENOMEM;
 
 	for (i = 0; i < d->dma_channels; i++) {
-		struct k3_dma_phy *p = &d->phy[i];
+		struct k3_dma_phy *p;
+
+		if (!(d->dma_channel_mask & BIT(i)))
+			continue;
 
+		p = &d->phy[i];
 		p->idx = i;
 		p->base = d->base + i * 0x40;
 	}
diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c
index 5de1b07eddff..7de54b2fafdb 100644
--- a/drivers/dma/mcf-edma.c
+++ b/drivers/dma/mcf-edma.c
@@ -214,6 +214,7 @@ static int mcf_edma_probe(struct platform_device *pdev)
 		mcf_chan->edma = mcf_edma;
 		mcf_chan->slave_id = i;
 		mcf_chan->idle = true;
+		mcf_chan->dma_dir = DMA_NONE;
 		mcf_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
 		iowrite32(0x0, &regs->tcd[i].csr);
diff --git a/drivers/dma/mediatek/Kconfig b/drivers/dma/mediatek/Kconfig
index 27bac0bba09e..680fc0572d87 100644
--- a/drivers/dma/mediatek/Kconfig
+++ b/drivers/dma/mediatek/Kconfig
@@ -11,3 +11,16 @@ config MTK_HSDMA
 	  This controller provides the channels which is dedicated to
 	  memory-to-memory transfer to offload from CPU through ring-
 	  based descriptor management.
+
+config MTK_CQDMA
+	tristate "MediaTek Command-Queue DMA controller support"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	help
+	  Enable support for Command-Queue DMA controller on MediaTek
+	  SoCs.
+
+	  This controller provides the channels which is dedicated to
+	  memory-to-memory transfer to offload from CPU.
diff --git a/drivers/dma/mediatek/Makefile b/drivers/dma/mediatek/Makefile
index 6e778f842f01..41bb3815f636 100644
--- a/drivers/dma/mediatek/Makefile
+++ b/drivers/dma/mediatek/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_MTK_HSDMA) += mtk-hsdma.o
+obj-$(CONFIG_MTK_CQDMA) += mtk-cqdma.o
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
new file mode 100644
index 000000000000..814853842e29
--- /dev/null
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -0,0 +1,951 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-2019 MediaTek Inc.
+
+/*
+ * Driver for MediaTek Command-Queue DMA Controller
+ *
+ * Author: Shun-Chih Yu <shun-chih.yu@mediatek.com>
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/iopoll.h>
+#include <linux/interrupt.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/pm_runtime.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+
+#include "../virt-dma.h"
+
+#define MTK_CQDMA_USEC_POLL		10
+#define MTK_CQDMA_TIMEOUT_POLL		1000
+#define MTK_CQDMA_DMA_BUSWIDTHS		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+#define MTK_CQDMA_ALIGN_SIZE		1
+
+/* The default number of virtual channel */
+#define MTK_CQDMA_NR_VCHANS		32
+
+/* The default number of physical channel */
+#define MTK_CQDMA_NR_PCHANS		3
+
+/* Registers for underlying dma manipulation */
+#define MTK_CQDMA_INT_FLAG		0x0
+#define MTK_CQDMA_INT_EN		0x4
+#define MTK_CQDMA_EN			0x8
+#define MTK_CQDMA_RESET			0xc
+#define MTK_CQDMA_FLUSH			0x14
+#define MTK_CQDMA_SRC			0x1c
+#define MTK_CQDMA_DST			0x20
+#define MTK_CQDMA_LEN1			0x24
+#define MTK_CQDMA_LEN2			0x28
+#define MTK_CQDMA_SRC2			0x60
+#define MTK_CQDMA_DST2			0x64
+
+/* Registers setting */
+#define MTK_CQDMA_EN_BIT		BIT(0)
+#define MTK_CQDMA_INT_FLAG_BIT		BIT(0)
+#define MTK_CQDMA_INT_EN_BIT		BIT(0)
+#define MTK_CQDMA_FLUSH_BIT		BIT(0)
+
+#define MTK_CQDMA_WARM_RST_BIT		BIT(0)
+#define MTK_CQDMA_HARD_RST_BIT		BIT(1)
+
+#define MTK_CQDMA_MAX_LEN		GENMASK(27, 0)
+#define MTK_CQDMA_ADDR_LIMIT		GENMASK(31, 0)
+#define MTK_CQDMA_ADDR2_SHFIT		(32)
+
+/**
+ * struct mtk_cqdma_vdesc - The struct holding info describing virtual
+ *                         descriptor (CVD)
+ * @vd:                    An instance for struct virt_dma_desc
+ * @len:                   The total data size device wants to move
+ * @residue:               The remaining data size device will move
+ * @dest:                  The destination address device wants to move to
+ * @src:                   The source address device wants to move from
+ * @ch:                    The pointer to the corresponding dma channel
+ * @node:                  The lise_head struct to build link-list for VDs
+ * @parent:                The pointer to the parent CVD
+ */
+struct mtk_cqdma_vdesc {
+	struct virt_dma_desc vd;
+	size_t len;
+	size_t residue;
+	dma_addr_t dest;
+	dma_addr_t src;
+	struct dma_chan *ch;
+
+	struct list_head node;
+	struct mtk_cqdma_vdesc *parent;
+};
+
+/**
+ * struct mtk_cqdma_pchan - The struct holding info describing physical
+ *                         channel (PC)
+ * @queue:                 Queue for the PDs issued to this PC
+ * @base:                  The mapped register I/O base of this PC
+ * @irq:                   The IRQ that this PC are using
+ * @refcnt:                Track how many VCs are using this PC
+ * @tasklet:               Tasklet for this PC
+ * @lock:                  Lock protect agaisting multiple VCs access PC
+ */
+struct mtk_cqdma_pchan {
+	struct list_head queue;
+	void __iomem *base;
+	u32 irq;
+
+	refcount_t refcnt;
+
+	struct tasklet_struct tasklet;
+
+	/* lock to protect PC */
+	spinlock_t lock;
+};
+
+/**
+ * struct mtk_cqdma_vchan - The struct holding info describing virtual
+ *                         channel (VC)
+ * @vc:                    An instance for struct virt_dma_chan
+ * @pc:                    The pointer to the underlying PC
+ * @issue_completion:	   The wait for all issued descriptors completited
+ * @issue_synchronize:	   Bool indicating channel synchronization starts
+ */
+struct mtk_cqdma_vchan {
+	struct virt_dma_chan vc;
+	struct mtk_cqdma_pchan *pc;
+	struct completion issue_completion;
+	bool issue_synchronize;
+};
+
+/**
+ * struct mtk_cqdma_device - The struct holding info describing CQDMA
+ *                          device
+ * @ddev:                   An instance for struct dma_device
+ * @clk:                    The clock that device internal is using
+ * @dma_requests:           The number of VCs the device supports to
+ * @dma_channels:           The number of PCs the device supports to
+ * @vc:                     The pointer to all available VCs
+ * @pc:                     The pointer to all the underlying PCs
+ */
+struct mtk_cqdma_device {
+	struct dma_device ddev;
+	struct clk *clk;
+
+	u32 dma_requests;
+	u32 dma_channels;
+	struct mtk_cqdma_vchan *vc;
+	struct mtk_cqdma_pchan **pc;
+};
+
+static struct mtk_cqdma_device *to_cqdma_dev(struct dma_chan *chan)
+{
+	return container_of(chan->device, struct mtk_cqdma_device, ddev);
+}
+
+static struct mtk_cqdma_vchan *to_cqdma_vchan(struct dma_chan *chan)
+{
+	return container_of(chan, struct mtk_cqdma_vchan, vc.chan);
+}
+
+static struct mtk_cqdma_vdesc *to_cqdma_vdesc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct mtk_cqdma_vdesc, vd);
+}
+
+static struct device *cqdma2dev(struct mtk_cqdma_device *cqdma)
+{
+	return cqdma->ddev.dev;
+}
+
+static u32 mtk_dma_read(struct mtk_cqdma_pchan *pc, u32 reg)
+{
+	return readl(pc->base + reg);
+}
+
+static void mtk_dma_write(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	writel_relaxed(val, pc->base + reg);
+}
+
+static void mtk_dma_rmw(struct mtk_cqdma_pchan *pc, u32 reg,
+			u32 mask, u32 set)
+{
+	u32 val;
+
+	val = mtk_dma_read(pc, reg);
+	val &= ~mask;
+	val |= set;
+	mtk_dma_write(pc, reg, val);
+}
+
+static void mtk_dma_set(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	mtk_dma_rmw(pc, reg, 0, val);
+}
+
+static void mtk_dma_clr(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	mtk_dma_rmw(pc, reg, val, 0);
+}
+
+static void mtk_cqdma_vdesc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_cqdma_vdesc(vd));
+}
+
+static int mtk_cqdma_poll_engine_done(struct mtk_cqdma_pchan *pc, bool atomic)
+{
+	u32 status = 0;
+
+	if (!atomic)
+		return readl_poll_timeout(pc->base + MTK_CQDMA_EN,
+					  status,
+					  !(status & MTK_CQDMA_EN_BIT),
+					  MTK_CQDMA_USEC_POLL,
+					  MTK_CQDMA_TIMEOUT_POLL);
+
+	return readl_poll_timeout_atomic(pc->base + MTK_CQDMA_EN,
+					 status,
+					 !(status & MTK_CQDMA_EN_BIT),
+					 MTK_CQDMA_USEC_POLL,
+					 MTK_CQDMA_TIMEOUT_POLL);
+}
+
+static int mtk_cqdma_hard_reset(struct mtk_cqdma_pchan *pc)
+{
+	mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT);
+	mtk_dma_clr(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT);
+
+	return mtk_cqdma_poll_engine_done(pc, false);
+}
+
+static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc,
+			    struct mtk_cqdma_vdesc *cvd)
+{
+	/* wait for the previous transaction done */
+	if (mtk_cqdma_poll_engine_done(pc, true) < 0)
+		dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), "cqdma wait transaction timeout\n");
+
+	/* warm reset the dma engine for the new transaction */
+	mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_WARM_RST_BIT);
+	if (mtk_cqdma_poll_engine_done(pc, true) < 0)
+		dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), "cqdma warm reset timeout\n");
+
+	/* setup the source */
+	mtk_dma_set(pc, MTK_CQDMA_SRC, cvd->src & MTK_CQDMA_ADDR_LIMIT);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	mtk_dma_set(pc, MTK_CQDMA_SRC2, cvd->src >> MTK_CQDMA_ADDR2_SHFIT);
+#else
+	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+#endif
+
+	/* setup the destination */
+	mtk_dma_set(pc, MTK_CQDMA_DST, cvd->dest & MTK_CQDMA_ADDR_LIMIT);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
+#else
+	mtk_dma_set(pc, MTK_CQDMA_DST2, 0);
+#endif
+
+	/* setup the length */
+	mtk_dma_set(pc, MTK_CQDMA_LEN1, cvd->len);
+
+	/* start dma engine */
+	mtk_dma_set(pc, MTK_CQDMA_EN, MTK_CQDMA_EN_BIT);
+}
+
+static void mtk_cqdma_issue_vchan_pending(struct mtk_cqdma_vchan *cvc)
+{
+	struct virt_dma_desc *vd, *vd2;
+	struct mtk_cqdma_pchan *pc = cvc->pc;
+	struct mtk_cqdma_vdesc *cvd;
+	bool trigger_engine = false;
+
+	lockdep_assert_held(&cvc->vc.lock);
+	lockdep_assert_held(&pc->lock);
+
+	list_for_each_entry_safe(vd, vd2, &cvc->vc.desc_issued, node) {
+		/* need to trigger dma engine if PC's queue is empty */
+		if (list_empty(&pc->queue))
+			trigger_engine = true;
+
+		cvd = to_cqdma_vdesc(vd);
+
+		/* add VD into PC's queue */
+		list_add_tail(&cvd->node, &pc->queue);
+
+		/* start the dma engine */
+		if (trigger_engine)
+			mtk_cqdma_start(pc, cvd);
+
+		/* remove VD from list desc_issued */
+		list_del(&vd->node);
+	}
+}
+
+/*
+ * return true if this VC is active,
+ * meaning that there are VDs under processing by the PC
+ */
+static bool mtk_cqdma_is_vchan_active(struct mtk_cqdma_vchan *cvc)
+{
+	struct mtk_cqdma_vdesc *cvd;
+
+	list_for_each_entry(cvd, &cvc->pc->queue, node)
+		if (cvc == to_cqdma_vchan(cvd->ch))
+			return true;
+
+	return false;
+}
+
+/*
+ * return the pointer of the CVD that is just consumed by the PC
+ */
+static struct mtk_cqdma_vdesc
+*mtk_cqdma_consume_work_queue(struct mtk_cqdma_pchan *pc)
+{
+	struct mtk_cqdma_vchan *cvc;
+	struct mtk_cqdma_vdesc *cvd, *ret = NULL;
+
+	/* consume a CVD from PC's queue */
+	cvd = list_first_entry_or_null(&pc->queue,
+				       struct mtk_cqdma_vdesc, node);
+	if (unlikely(!cvd || !cvd->parent))
+		return NULL;
+
+	cvc = to_cqdma_vchan(cvd->ch);
+	ret = cvd;
+
+	/* update residue of the parent CVD */
+	cvd->parent->residue -= cvd->len;
+
+	/* delete CVD from PC's queue */
+	list_del(&cvd->node);
+
+	spin_lock(&cvc->vc.lock);
+
+	/* check whether all the child CVDs completed */
+	if (!cvd->parent->residue) {
+		/* add the parent VD into list desc_completed */
+		vchan_cookie_complete(&cvd->parent->vd);
+
+		/* setup completion if this VC is under synchronization */
+		if (cvc->issue_synchronize && !mtk_cqdma_is_vchan_active(cvc)) {
+			complete(&cvc->issue_completion);
+			cvc->issue_synchronize = false;
+		}
+	}
+
+	spin_unlock(&cvc->vc.lock);
+
+	/* start transaction for next CVD in the queue */
+	cvd = list_first_entry_or_null(&pc->queue,
+				       struct mtk_cqdma_vdesc, node);
+	if (cvd)
+		mtk_cqdma_start(pc, cvd);
+
+	return ret;
+}
+
+static void mtk_cqdma_tasklet_cb(unsigned long data)
+{
+	struct mtk_cqdma_pchan *pc = (struct mtk_cqdma_pchan *)data;
+	struct mtk_cqdma_vdesc *cvd = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pc->lock, flags);
+	/* consume the queue */
+	cvd = mtk_cqdma_consume_work_queue(pc);
+	spin_unlock_irqrestore(&pc->lock, flags);
+
+	/* submit the next CVD */
+	if (cvd) {
+		dma_run_dependencies(&cvd->vd.tx);
+
+		/*
+		 * free child CVD after completion.
+		 * the parent CVD would be freeed with desc_free by user.
+		 */
+		if (cvd->parent != cvd)
+			kfree(cvd);
+	}
+
+	/* re-enable interrupt before leaving tasklet */
+	enable_irq(pc->irq);
+}
+
+static irqreturn_t mtk_cqdma_irq(int irq, void *devid)
+{
+	struct mtk_cqdma_device *cqdma = devid;
+	irqreturn_t ret = IRQ_NONE;
+	bool schedule_tasklet = false;
+	u32 i;
+
+	/* clear interrupt flags for each PC */
+	for (i = 0; i < cqdma->dma_channels; ++i, schedule_tasklet = false) {
+		spin_lock(&cqdma->pc[i]->lock);
+		if (mtk_dma_read(cqdma->pc[i],
+				 MTK_CQDMA_INT_FLAG) & MTK_CQDMA_INT_FLAG_BIT) {
+			/* clear interrupt */
+			mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_FLAG,
+				    MTK_CQDMA_INT_FLAG_BIT);
+
+			schedule_tasklet = true;
+			ret = IRQ_HANDLED;
+		}
+		spin_unlock(&cqdma->pc[i]->lock);
+
+		if (schedule_tasklet) {
+			/* disable interrupt */
+			disable_irq_nosync(cqdma->pc[i]->irq);
+
+			/* schedule the tasklet to handle the transactions */
+			tasklet_schedule(&cqdma->pc[i]->tasklet);
+		}
+	}
+
+	return ret;
+}
+
+static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c,
+							dma_cookie_t cookie)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cvc->pc->lock, flags);
+	list_for_each_entry(vd, &cvc->pc->queue, node)
+		if (vd->tx.cookie == cookie) {
+			spin_unlock_irqrestore(&cvc->pc->lock, flags);
+			return vd;
+		}
+	spin_unlock_irqrestore(&cvc->pc->lock, flags);
+
+	list_for_each_entry(vd, &cvc->vc.desc_issued, node)
+		if (vd->tx.cookie == cookie)
+			return vd;
+
+	return NULL;
+}
+
+static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c,
+					   dma_cookie_t cookie,
+					   struct dma_tx_state *txstate)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	struct mtk_cqdma_vdesc *cvd;
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&cvc->vc.lock, flags);
+	vd = mtk_cqdma_find_active_desc(c, cookie);
+	spin_unlock_irqrestore(&cvc->vc.lock, flags);
+
+	if (vd) {
+		cvd = to_cqdma_vdesc(vd);
+		bytes = cvd->residue;
+	}
+
+	dma_set_residue(txstate, bytes);
+
+	return ret;
+}
+
+static void mtk_cqdma_issue_pending(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	unsigned long pc_flags;
+	unsigned long vc_flags;
+
+	/* acquire PC's lock before VS's lock for lock dependency in tasklet */
+	spin_lock_irqsave(&cvc->pc->lock, pc_flags);
+	spin_lock_irqsave(&cvc->vc.lock, vc_flags);
+
+	if (vchan_issue_pending(&cvc->vc))
+		mtk_cqdma_issue_vchan_pending(cvc);
+
+	spin_unlock_irqrestore(&cvc->vc.lock, vc_flags);
+	spin_unlock_irqrestore(&cvc->pc->lock, pc_flags);
+}
+
+static struct dma_async_tx_descriptor *
+mtk_cqdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest,
+			  dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct mtk_cqdma_vdesc **cvd;
+	struct dma_async_tx_descriptor *tx = NULL, *prev_tx = NULL;
+	size_t i, tlen, nr_vd;
+
+	/*
+	 * In the case that trsanction length is larger than the
+	 * DMA engine supports, a single memcpy transaction needs
+	 * to be separated into several DMA transactions.
+	 * Each DMA transaction would be described by a CVD,
+	 * and the first one is referred as the parent CVD,
+	 * while the others are child CVDs.
+	 * The parent CVD's tx descriptor is the only tx descriptor
+	 * returned to the DMA user, and it should not be completed
+	 * until all the child CVDs completed.
+	 */
+	nr_vd = DIV_ROUND_UP(len, MTK_CQDMA_MAX_LEN);
+	cvd = kcalloc(nr_vd, sizeof(*cvd), GFP_NOWAIT);
+	if (!cvd)
+		return NULL;
+
+	for (i = 0; i < nr_vd; ++i) {
+		cvd[i] = kzalloc(sizeof(*cvd[i]), GFP_NOWAIT);
+		if (!cvd[i]) {
+			for (; i > 0; --i)
+				kfree(cvd[i - 1]);
+			return NULL;
+		}
+
+		/* setup dma channel */
+		cvd[i]->ch = c;
+
+		/* setup sourece, destination, and length */
+		tlen = (len > MTK_CQDMA_MAX_LEN) ? MTK_CQDMA_MAX_LEN : len;
+		cvd[i]->len = tlen;
+		cvd[i]->src = src;
+		cvd[i]->dest = dest;
+
+		/* setup tx descriptor */
+		tx = vchan_tx_prep(to_virt_chan(c), &cvd[i]->vd, flags);
+		tx->next = NULL;
+
+		if (!i) {
+			cvd[0]->residue = len;
+		} else {
+			prev_tx->next = tx;
+			cvd[i]->residue = tlen;
+		}
+
+		cvd[i]->parent = cvd[0];
+
+		/* update the src, dest, len, prev_tx for the next CVD */
+		src += tlen;
+		dest += tlen;
+		len -= tlen;
+		prev_tx = tx;
+	}
+
+	return &cvd[0]->vd.tx;
+}
+
+static void mtk_cqdma_free_inactive_desc(struct dma_chan *c)
+{
+	struct virt_dma_chan *vc = to_virt_chan(c);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	/*
+	 * set desc_allocated, desc_submitted,
+	 * and desc_issued as the candicates to be freed
+	 */
+	spin_lock_irqsave(&vc->lock, flags);
+	list_splice_tail_init(&vc->desc_allocated, &head);
+	list_splice_tail_init(&vc->desc_submitted, &head);
+	list_splice_tail_init(&vc->desc_issued, &head);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	/* free descriptor lists */
+	vchan_dma_desc_free_list(vc, &head);
+}
+
+static void mtk_cqdma_free_active_desc(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	bool sync_needed = false;
+	unsigned long pc_flags;
+	unsigned long vc_flags;
+
+	/* acquire PC's lock first due to lock dependency in dma ISR */
+	spin_lock_irqsave(&cvc->pc->lock, pc_flags);
+	spin_lock_irqsave(&cvc->vc.lock, vc_flags);
+
+	/* synchronization is required if this VC is active */
+	if (mtk_cqdma_is_vchan_active(cvc)) {
+		cvc->issue_synchronize = true;
+		sync_needed = true;
+	}
+
+	spin_unlock_irqrestore(&cvc->vc.lock, vc_flags);
+	spin_unlock_irqrestore(&cvc->pc->lock, pc_flags);
+
+	/* waiting for the completion of this VC */
+	if (sync_needed)
+		wait_for_completion(&cvc->issue_completion);
+
+	/* free all descriptors in list desc_completed */
+	vchan_synchronize(&cvc->vc);
+
+	WARN_ONCE(!list_empty(&cvc->vc.desc_completed),
+		  "Desc pending still in list desc_completed\n");
+}
+
+static int mtk_cqdma_terminate_all(struct dma_chan *c)
+{
+	/* free descriptors not processed yet by hardware */
+	mtk_cqdma_free_inactive_desc(c);
+
+	/* free descriptors being processed by hardware */
+	mtk_cqdma_free_active_desc(c);
+
+	return 0;
+}
+
+static int mtk_cqdma_alloc_chan_resources(struct dma_chan *c)
+{
+	struct mtk_cqdma_device *cqdma = to_cqdma_dev(c);
+	struct mtk_cqdma_vchan *vc = to_cqdma_vchan(c);
+	struct mtk_cqdma_pchan *pc = NULL;
+	u32 i, min_refcnt = U32_MAX, refcnt;
+	unsigned long flags;
+
+	/* allocate PC with the minimun refcount */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		refcnt = refcount_read(&cqdma->pc[i]->refcnt);
+		if (refcnt < min_refcnt) {
+			pc = cqdma->pc[i];
+			min_refcnt = refcnt;
+		}
+	}
+
+	if (!pc)
+		return -ENOSPC;
+
+	spin_lock_irqsave(&pc->lock, flags);
+
+	if (!refcount_read(&pc->refcnt)) {
+		/* allocate PC when the refcount is zero */
+		mtk_cqdma_hard_reset(pc);
+
+		/* enable interrupt for this PC */
+		mtk_dma_set(pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT);
+
+		/*
+		 * refcount_inc would complain increment on 0; use-after-free.
+		 * Thus, we need to explicitly set it as 1 initially.
+		 */
+		refcount_set(&pc->refcnt, 1);
+	} else {
+		refcount_inc(&pc->refcnt);
+	}
+
+	spin_unlock_irqrestore(&pc->lock, flags);
+
+	vc->pc = pc;
+
+	return 0;
+}
+
+static void mtk_cqdma_free_chan_resources(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	unsigned long flags;
+
+	/* free all descriptors in all lists on the VC */
+	mtk_cqdma_terminate_all(c);
+
+	spin_lock_irqsave(&cvc->pc->lock, flags);
+
+	/* PC is not freed until there is no VC mapped to it */
+	if (refcount_dec_and_test(&cvc->pc->refcnt)) {
+		/* start the flush operation and stop the engine */
+		mtk_dma_set(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT);
+
+		/* wait for the completion of flush operation */
+		if (mtk_cqdma_poll_engine_done(cvc->pc, false) < 0)
+			dev_err(cqdma2dev(to_cqdma_dev(c)), "cqdma flush timeout\n");
+
+		/* clear the flush bit and interrupt flag */
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT);
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_FLAG,
+			    MTK_CQDMA_INT_FLAG_BIT);
+
+		/* disable interrupt for this PC */
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT);
+	}
+
+	spin_unlock_irqrestore(&cvc->pc->lock, flags);
+}
+
+static int mtk_cqdma_hw_init(struct mtk_cqdma_device *cqdma)
+{
+	unsigned long flags;
+	int err;
+	u32 i;
+
+	pm_runtime_enable(cqdma2dev(cqdma));
+	pm_runtime_get_sync(cqdma2dev(cqdma));
+
+	err = clk_prepare_enable(cqdma->clk);
+
+	if (err) {
+		pm_runtime_put_sync(cqdma2dev(cqdma));
+		pm_runtime_disable(cqdma2dev(cqdma));
+		return err;
+	}
+
+	/* reset all PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0) {
+			dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n");
+			spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+
+			clk_disable_unprepare(cqdma->clk);
+			pm_runtime_put_sync(cqdma2dev(cqdma));
+			pm_runtime_disable(cqdma2dev(cqdma));
+			return -EINVAL;
+		}
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+	}
+
+	return 0;
+}
+
+static void mtk_cqdma_hw_deinit(struct mtk_cqdma_device *cqdma)
+{
+	unsigned long flags;
+	u32 i;
+
+	/* reset all PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0)
+			dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n");
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+	}
+
+	clk_disable_unprepare(cqdma->clk);
+
+	pm_runtime_put_sync(cqdma2dev(cqdma));
+	pm_runtime_disable(cqdma2dev(cqdma));
+}
+
+static const struct of_device_id mtk_cqdma_match[] = {
+	{ .compatible = "mediatek,mt6765-cqdma" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mtk_cqdma_match);
+
+static int mtk_cqdma_probe(struct platform_device *pdev)
+{
+	struct mtk_cqdma_device *cqdma;
+	struct mtk_cqdma_vchan *vc;
+	struct dma_device *dd;
+	struct resource *res;
+	int err;
+	u32 i;
+
+	cqdma = devm_kzalloc(&pdev->dev, sizeof(*cqdma), GFP_KERNEL);
+	if (!cqdma)
+		return -ENOMEM;
+
+	dd = &cqdma->ddev;
+
+	cqdma->clk = devm_clk_get(&pdev->dev, "cqdma");
+	if (IS_ERR(cqdma->clk)) {
+		dev_err(&pdev->dev, "No clock for %s\n",
+			dev_name(&pdev->dev));
+		return PTR_ERR(cqdma->clk);
+	}
+
+	dma_cap_set(DMA_MEMCPY, dd->cap_mask);
+
+	dd->copy_align = MTK_CQDMA_ALIGN_SIZE;
+	dd->device_alloc_chan_resources = mtk_cqdma_alloc_chan_resources;
+	dd->device_free_chan_resources = mtk_cqdma_free_chan_resources;
+	dd->device_tx_status = mtk_cqdma_tx_status;
+	dd->device_issue_pending = mtk_cqdma_issue_pending;
+	dd->device_prep_dma_memcpy = mtk_cqdma_prep_dma_memcpy;
+	dd->device_terminate_all = mtk_cqdma_terminate_all;
+	dd->src_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS;
+	dd->dst_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS;
+	dd->directions = BIT(DMA_MEM_TO_MEM);
+	dd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	dd->dev = &pdev->dev;
+	INIT_LIST_HEAD(&dd->channels);
+
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-requests",
+						      &cqdma->dma_requests)) {
+		dev_info(&pdev->dev,
+			 "Using %u as missing dma-requests property\n",
+			 MTK_CQDMA_NR_VCHANS);
+
+		cqdma->dma_requests = MTK_CQDMA_NR_VCHANS;
+	}
+
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-channels",
+						      &cqdma->dma_channels)) {
+		dev_info(&pdev->dev,
+			 "Using %u as missing dma-channels property\n",
+			 MTK_CQDMA_NR_PCHANS);
+
+		cqdma->dma_channels = MTK_CQDMA_NR_PCHANS;
+	}
+
+	cqdma->pc = devm_kcalloc(&pdev->dev, cqdma->dma_channels,
+				 sizeof(*cqdma->pc), GFP_KERNEL);
+	if (!cqdma->pc)
+		return -ENOMEM;
+
+	/* initialization for PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		cqdma->pc[i] = devm_kcalloc(&pdev->dev, 1,
+					    sizeof(**cqdma->pc), GFP_KERNEL);
+		if (!cqdma->pc[i])
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&cqdma->pc[i]->queue);
+		spin_lock_init(&cqdma->pc[i]->lock);
+		refcount_set(&cqdma->pc[i]->refcnt, 0);
+
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res) {
+			dev_err(&pdev->dev, "No mem resource for %s\n",
+				dev_name(&pdev->dev));
+			return -EINVAL;
+		}
+
+		cqdma->pc[i]->base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(cqdma->pc[i]->base))
+			return PTR_ERR(cqdma->pc[i]->base);
+
+		/* allocate IRQ resource */
+		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
+		if (!res) {
+			dev_err(&pdev->dev, "No irq resource for %s\n",
+				dev_name(&pdev->dev));
+			return -EINVAL;
+		}
+		cqdma->pc[i]->irq = res->start;
+
+		err = devm_request_irq(&pdev->dev, cqdma->pc[i]->irq,
+				       mtk_cqdma_irq, 0, dev_name(&pdev->dev),
+				       cqdma);
+		if (err) {
+			dev_err(&pdev->dev,
+				"request_irq failed with err %d\n", err);
+			return -EINVAL;
+		}
+	}
+
+	/* allocate resource for VCs */
+	cqdma->vc = devm_kcalloc(&pdev->dev, cqdma->dma_requests,
+				 sizeof(*cqdma->vc), GFP_KERNEL);
+	if (!cqdma->vc)
+		return -ENOMEM;
+
+	for (i = 0; i < cqdma->dma_requests; i++) {
+		vc = &cqdma->vc[i];
+		vc->vc.desc_free = mtk_cqdma_vdesc_free;
+		vchan_init(&vc->vc, dd);
+		init_completion(&vc->issue_completion);
+	}
+
+	err = dma_async_device_register(dd);
+	if (err)
+		return err;
+
+	err = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, cqdma);
+	if (err) {
+		dev_err(&pdev->dev,
+			"MediaTek CQDMA OF registration failed %d\n", err);
+		goto err_unregister;
+	}
+
+	err = mtk_cqdma_hw_init(cqdma);
+	if (err) {
+		dev_err(&pdev->dev,
+			"MediaTek CQDMA HW initialization failed %d\n", err);
+		goto err_unregister;
+	}
+
+	platform_set_drvdata(pdev, cqdma);
+
+	/* initialize tasklet for each PC */
+	for (i = 0; i < cqdma->dma_channels; ++i)
+		tasklet_init(&cqdma->pc[i]->tasklet, mtk_cqdma_tasklet_cb,
+			     (unsigned long)cqdma->pc[i]);
+
+	dev_info(&pdev->dev, "MediaTek CQDMA driver registered\n");
+
+	return 0;
+
+err_unregister:
+	dma_async_device_unregister(dd);
+
+	return err;
+}
+
+static int mtk_cqdma_remove(struct platform_device *pdev)
+{
+	struct mtk_cqdma_device *cqdma = platform_get_drvdata(pdev);
+	struct mtk_cqdma_vchan *vc;
+	unsigned long flags;
+	int i;
+
+	/* kill VC task */
+	for (i = 0; i < cqdma->dma_requests; i++) {
+		vc = &cqdma->vc[i];
+
+		list_del(&vc->vc.chan.device_node);
+		tasklet_kill(&vc->vc.task);
+	}
+
+	/* disable interrupt */
+	for (i = 0; i < cqdma->dma_channels; i++) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_EN,
+			    MTK_CQDMA_INT_EN_BIT);
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+
+		/* Waits for any pending IRQ handlers to complete */
+		synchronize_irq(cqdma->pc[i]->irq);
+
+		tasklet_kill(&cqdma->pc[i]->tasklet);
+	}
+
+	/* disable hardware */
+	mtk_cqdma_hw_deinit(cqdma);
+
+	dma_async_device_unregister(&cqdma->ddev);
+	of_dma_controller_free(pdev->dev.of_node);
+
+	return 0;
+}
+
+static struct platform_driver mtk_cqdma_driver = {
+	.probe = mtk_cqdma_probe,
+	.remove = mtk_cqdma_remove,
+	.driver = {
+		.name           = KBUILD_MODNAME,
+		.of_match_table = mtk_cqdma_match,
+	},
+};
+module_platform_driver(mtk_cqdma_driver);
+
+MODULE_DESCRIPTION("MediaTek CQDMA Controller Driver");
+MODULE_AUTHOR("Shun-Chih Yu <shun-chih.yu@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c
index b7ec56ae02a6..1a2028e1c29e 100644
--- a/drivers/dma/mediatek/mtk-hsdma.c
+++ b/drivers/dma/mediatek/mtk-hsdma.c
@@ -325,8 +325,8 @@ static int mtk_hsdma_alloc_pchan(struct mtk_hsdma_device *hsdma,
 	 * and [MTK_DMA_SIZE ... 2 * MTK_DMA_SIZE - 1] is for RX ring.
 	 */
 	pc->sz_ring = 2 * MTK_DMA_SIZE * sizeof(*ring->txd);
-	ring->txd = dma_zalloc_coherent(hsdma2dev(hsdma), pc->sz_ring,
-					&ring->tphys, GFP_NOWAIT);
+	ring->txd = dma_alloc_coherent(hsdma2dev(hsdma), pc->sz_ring,
+				       &ring->tphys, GFP_NOWAIT);
 	if (!ring->txd)
 		return -ENOMEM;
 
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index adfd316db1a8..6a91e28d537d 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -676,7 +676,7 @@ static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
 }
 
 /* DEBUGFS CODE */
-static int mic_dma_reg_seq_show(struct seq_file *s, void *pos)
+static int mic_dma_reg_show(struct seq_file *s, void *pos)
 {
 	struct mic_dma_device *mic_dma_dev = s->private;
 	int i, chan_num, first_chan = mic_dma_dev->start_ch;
@@ -707,23 +707,7 @@ static int mic_dma_reg_seq_show(struct seq_file *s, void *pos)
 	return 0;
 }
 
-static int mic_dma_reg_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mic_dma_reg_seq_show, inode->i_private);
-}
-
-static int mic_dma_reg_debug_release(struct inode *inode, struct file *file)
-{
-	return single_release(inode, file);
-}
-
-static const struct file_operations mic_dma_reg_ops = {
-	.owner   = THIS_MODULE,
-	.open    = mic_dma_reg_debug_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = mic_dma_reg_debug_release
-};
+DEFINE_SHOW_ATTRIBUTE(mic_dma_reg);
 
 /* Debugfs parent dir */
 static struct dentry *mic_dma_dbg;
@@ -747,7 +731,7 @@ static int mic_dma_driver_probe(struct mbus_device *mbdev)
 		if (mic_dma_dev->dbg_dir)
 			debugfs_create_file("mic_dma_reg", 0444,
 					    mic_dma_dev->dbg_dir, mic_dma_dev,
-					    &mic_dma_reg_ops);
+					    &mic_dma_reg_fops);
 	}
 	return 0;
 }
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index eb3a1f42ab06..334bab92d26d 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -96,6 +96,7 @@ struct mmp_pdma_chan {
 	struct dma_async_tx_descriptor desc;
 	struct mmp_pdma_phy *phy;
 	enum dma_transfer_direction dir;
+	struct dma_slave_config slave_config;
 
 	struct mmp_pdma_desc_sw *cyclic_first;	/* first desc_sw if channel
 						 * is in cyclic mode */
@@ -140,6 +141,10 @@ struct mmp_pdma_device {
 #define to_mmp_pdma_dev(dmadev)					\
 	container_of(dmadev, struct mmp_pdma_device, device)
 
+static int mmp_pdma_config_write(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg,
+			   enum dma_transfer_direction direction);
+
 static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
 {
 	u32 reg = (phy->idx << 4) + DDADR;
@@ -537,6 +542,8 @@ mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 
 	chan->byte_align = false;
 
+	mmp_pdma_config_write(dchan, &chan->slave_config, dir);
+
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
 		avail = sg_dma_len(sgl);
@@ -619,6 +626,7 @@ mmp_pdma_prep_dma_cyclic(struct dma_chan *dchan,
 		return NULL;
 
 	chan = to_mmp_pdma_chan(dchan);
+	mmp_pdma_config_write(dchan, &chan->slave_config, direction);
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
@@ -684,8 +692,9 @@ fail:
 	return NULL;
 }
 
-static int mmp_pdma_config(struct dma_chan *dchan,
-			   struct dma_slave_config *cfg)
+static int mmp_pdma_config_write(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg,
+			   enum dma_transfer_direction direction)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
 	u32 maxburst = 0, addr = 0;
@@ -694,12 +703,12 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	if (!dchan)
 		return -EINVAL;
 
-	if (cfg->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		chan->dcmd = DCMD_INCTRGADDR | DCMD_FLOWSRC;
 		maxburst = cfg->src_maxburst;
 		width = cfg->src_addr_width;
 		addr = cfg->src_addr;
-	} else if (cfg->direction == DMA_MEM_TO_DEV) {
+	} else if (direction == DMA_MEM_TO_DEV) {
 		chan->dcmd = DCMD_INCSRCADDR | DCMD_FLOWTRG;
 		maxburst = cfg->dst_maxburst;
 		width = cfg->dst_addr_width;
@@ -720,7 +729,7 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	else if (maxburst == 32)
 		chan->dcmd |= DCMD_BURST32;
 
-	chan->dir = cfg->direction;
+	chan->dir = direction;
 	chan->dev_addr = addr;
 	/* FIXME: drivers should be ported over to use the filter
 	 * function. Once that's done, the following two lines can
@@ -732,6 +741,15 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	return 0;
 }
 
+static int mmp_pdma_config(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+
+	memcpy(&chan->slave_config, cfg, sizeof(*cfg));
+	return 0;
+}
+
 static int mmp_pdma_terminate_all(struct dma_chan *dchan)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 7f595355fb79..65af2e7fcb2c 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1059,6 +1059,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		mv_chan->op_in_desc = XOR_MODE_IN_DESC;
 
 	dma_dev = &mv_chan->dmadev;
+	dma_dev->dev = &pdev->dev;
 	mv_chan->xordev = xordev;
 
 	/*
@@ -1091,7 +1092,6 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	dma_dev->device_free_chan_resources = mv_xor_free_chan_resources;
 	dma_dev->device_tx_status = mv_xor_status;
 	dma_dev->device_issue_pending = mv_xor_issue_pending;
-	dma_dev->dev = &pdev->dev;
 
 	/* set prep routines based on capability */
 	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
@@ -1153,7 +1153,10 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		 dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
 		 dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
-	dma_async_device_register(dma_dev);
+	ret = dma_async_device_register(dma_dev);
+	if (ret)
+		goto err_free_irq;
+
 	return mv_chan;
 
 err_free_irq:
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 35193b31a9e0..22cc7f68ef6e 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -416,9 +416,9 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
 	int ret;
 
-	mxs_chan->ccw = dma_zalloc_coherent(mxs_dma->dma_device.dev,
-					    CCW_BLOCK_SIZE,
-					    &mxs_chan->ccw_phys, GFP_KERNEL);
+	mxs_chan->ccw = dma_alloc_coherent(mxs_dma->dma_device.dev,
+					   CCW_BLOCK_SIZE,
+					   &mxs_chan->ccw_phys, GFP_KERNEL);
 	if (!mxs_chan->ccw) {
 		ret = -ENOMEM;
 		goto err_alloc;
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index afd8f27bda96..538b6e0e17bb 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -972,7 +972,6 @@ static void pch_dma_remove(struct pci_dev *pdev)
 }
 
 /* PCI Device ID of DMA device */
-#define PCI_VENDOR_ID_ROHM             0x10DB
 #define PCI_DEVICE_ID_EG20T_PCH_DMA_8CH        0x8810
 #define PCI_DEVICE_ID_EG20T_PCH_DMA_4CH        0x8815
 #define PCI_DEVICE_ID_ML7213_DMA1_8CH	0x8026
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 88750a34e859..eec79fdf27a5 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -448,6 +448,7 @@ struct dma_pl330_chan {
 	/* DMA-mapped view of the FIFO; may differ if an IOMMU is present */
 	dma_addr_t fifo_dma;
 	enum dma_data_direction dir;
+	struct dma_slave_config slave_config;
 
 	/* for cyclic capability */
 	bool cyclic;
@@ -542,6 +543,10 @@ struct _xfer_spec {
 	struct dma_pl330_desc *desc;
 };
 
+static int pl330_config_write(struct dma_chan *chan,
+			struct dma_slave_config *slave_config,
+			enum dma_transfer_direction direction);
+
 static inline bool _queue_full(struct pl330_thread *thrd)
 {
 	return thrd->req[0].desc != NULL && thrd->req[1].desc != NULL;
@@ -2220,20 +2225,21 @@ static int fixup_burst_len(int max_burst_len, int quirks)
 		return max_burst_len;
 }
 
-static int pl330_config(struct dma_chan *chan,
-			struct dma_slave_config *slave_config)
+static int pl330_config_write(struct dma_chan *chan,
+			struct dma_slave_config *slave_config,
+			enum dma_transfer_direction direction)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
 
 	pl330_unprep_slave_fifo(pch);
-	if (slave_config->direction == DMA_MEM_TO_DEV) {
+	if (direction == DMA_MEM_TO_DEV) {
 		if (slave_config->dst_addr)
 			pch->fifo_addr = slave_config->dst_addr;
 		if (slave_config->dst_addr_width)
 			pch->burst_sz = __ffs(slave_config->dst_addr_width);
 		pch->burst_len = fixup_burst_len(slave_config->dst_maxburst,
 			pch->dmac->quirks);
-	} else if (slave_config->direction == DMA_DEV_TO_MEM) {
+	} else if (direction == DMA_DEV_TO_MEM) {
 		if (slave_config->src_addr)
 			pch->fifo_addr = slave_config->src_addr;
 		if (slave_config->src_addr_width)
@@ -2245,13 +2251,22 @@ static int pl330_config(struct dma_chan *chan,
 	return 0;
 }
 
+static int pl330_config(struct dma_chan *chan,
+			struct dma_slave_config *slave_config)
+{
+	struct dma_pl330_chan *pch = to_pchan(chan);
+
+	memcpy(&pch->slave_config, slave_config, sizeof(*slave_config));
+
+	return 0;
+}
+
 static int pl330_terminate_all(struct dma_chan *chan)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
 	struct dma_pl330_desc *desc;
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
-	LIST_HEAD(list);
 	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
@@ -2661,6 +2676,8 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 		return NULL;
 	}
 
+	pl330_config_write(chan, &pch->slave_config, direction);
+
 	if (!pl330_prep_slave_fifo(pch, direction))
 		return NULL;
 
@@ -2815,6 +2832,8 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (unlikely(!pch || !sgl || !sg_len))
 		return NULL;
 
+	pl330_config_write(chan, &pch->slave_config, direction);
+
 	if (!pl330_prep_slave_fifo(pch, direction))
 		return NULL;
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 825725057e00..b429642f3e7a 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -179,7 +179,7 @@ static unsigned int pxad_drcmr(unsigned int line)
 	return 0x1000 + line * 4;
 }
 
-bool pxad_filter_fn(struct dma_chan *chan, void *param);
+static bool pxad_filter_fn(struct dma_chan *chan, void *param);
 
 /*
  * Debug fs
@@ -189,7 +189,7 @@ bool pxad_filter_fn(struct dma_chan *chan, void *param);
 #include <linux/uaccess.h>
 #include <linux/seq_file.h>
 
-static int dbg_show_requester_chan(struct seq_file *s, void *p)
+static int requester_chan_show(struct seq_file *s, void *p)
 {
 	struct pxad_phy *phy = s->private;
 	int i;
@@ -220,7 +220,7 @@ static int is_phys_valid(unsigned long addr)
 #define PXA_DCSR_STR(flag) (dcsr & PXA_DCSR_##flag ? #flag" " : "")
 #define PXA_DCMD_STR(flag) (dcmd & PXA_DCMD_##flag ? #flag" " : "")
 
-static int dbg_show_descriptors(struct seq_file *s, void *p)
+static int descriptors_show(struct seq_file *s, void *p)
 {
 	struct pxad_phy *phy = s->private;
 	int i, max_show = 20, burst, width;
@@ -263,7 +263,7 @@ static int dbg_show_descriptors(struct seq_file *s, void *p)
 	return 0;
 }
 
-static int dbg_show_chan_state(struct seq_file *s, void *p)
+static int chan_state_show(struct seq_file *s, void *p)
 {
 	struct pxad_phy *phy = s->private;
 	u32 dcsr, dcmd;
@@ -306,7 +306,7 @@ static int dbg_show_chan_state(struct seq_file *s, void *p)
 	return 0;
 }
 
-static int dbg_show_state(struct seq_file *s, void *p)
+static int state_show(struct seq_file *s, void *p)
 {
 	struct pxad_device *pdev = s->private;
 
@@ -317,22 +317,10 @@ static int dbg_show_state(struct seq_file *s, void *p)
 	return 0;
 }
 
-#define DBGFS_FUNC_DECL(name) \
-static int dbg_open_##name(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, dbg_show_##name, inode->i_private); \
-} \
-static const struct file_operations dbg_fops_##name = { \
-	.open		= dbg_open_##name, \
-	.llseek		= seq_lseek, \
-	.read		= seq_read, \
-	.release	= single_release, \
-}
-
-DBGFS_FUNC_DECL(state);
-DBGFS_FUNC_DECL(chan_state);
-DBGFS_FUNC_DECL(descriptors);
-DBGFS_FUNC_DECL(requester_chan);
+DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(chan_state);
+DEFINE_SHOW_ATTRIBUTE(descriptors);
+DEFINE_SHOW_ATTRIBUTE(requester_chan);
 
 static struct dentry *pxad_dbg_alloc_chan(struct pxad_device *pdev,
 					     int ch, struct dentry *chandir)
@@ -348,13 +336,13 @@ static struct dentry *pxad_dbg_alloc_chan(struct pxad_device *pdev,
 
 	if (chan)
 		chan_state = debugfs_create_file("state", 0400, chan, dt,
-						 &dbg_fops_chan_state);
+						 &chan_state_fops);
 	if (chan_state)
 		chan_descr = debugfs_create_file("descriptors", 0400, chan, dt,
-						 &dbg_fops_descriptors);
+						 &descriptors_fops);
 	if (chan_descr)
 		chan_reqs = debugfs_create_file("requesters", 0400, chan, dt,
-						&dbg_fops_requester_chan);
+						&requester_chan_fops);
 	if (!chan_reqs)
 		goto err_state;
 
@@ -375,7 +363,7 @@ static void pxad_init_debugfs(struct pxad_device *pdev)
 		goto err_root;
 
 	pdev->dbgfs_state = debugfs_create_file("state", 0400, pdev->dbgfs_root,
-						pdev, &dbg_fops_state);
+						pdev, &state_fops);
 	if (!pdev->dbgfs_state)
 		goto err_state;
 
@@ -1500,7 +1488,7 @@ static struct platform_driver pxad_driver = {
 	.remove		= pxad_remove,
 };
 
-bool pxad_filter_fn(struct dma_chan *chan, void *param)
+static bool pxad_filter_fn(struct dma_chan *chan, void *param)
 {
 	struct pxad_chan *c = to_pxad_chan(chan);
 	struct pxad_param *p = param;
@@ -1513,7 +1501,6 @@ bool pxad_filter_fn(struct dma_chan *chan, void *param)
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(pxad_filter_fn);
 
 module_platform_driver(pxad_driver);
 
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 1617715aa6e0..cb860cb53c27 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -636,8 +636,8 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 		num_alloc += DIV_ROUND_UP(sg_dma_len(sg), BAM_FIFO_SIZE);
 
 	/* allocate enough room to accomodate the number of entries */
-	async_desc = kzalloc(sizeof(*async_desc) +
-			(num_alloc * sizeof(struct bam_desc_hw)), GFP_NOWAIT);
+	async_desc = kzalloc(struct_size(async_desc, desc, num_alloc),
+			     GFP_NOWAIT);
 
 	if (!async_desc)
 		goto err_out;
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 43d4b00b8138..411f91fde734 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -138,24 +138,25 @@ static void hidma_process_completed(struct hidma_chan *mchan)
 		desc = &mdesc->desc;
 		last_cookie = desc->cookie;
 
+		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
+
 		spin_lock_irqsave(&mchan->lock, irqflags);
+		if (llstat == DMA_COMPLETE) {
+			mchan->last_success = last_cookie;
+			result.result = DMA_TRANS_NOERROR;
+		} else {
+			result.result = DMA_TRANS_ABORTED;
+		}
+
 		dma_cookie_complete(desc);
 		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
-		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
 		dmaengine_desc_get_callback(desc, &cb);
 
 		dma_run_dependencies(desc);
 
 		spin_lock_irqsave(&mchan->lock, irqflags);
 		list_move(&mdesc->node, &mchan->free);
-
-		if (llstat == DMA_COMPLETE) {
-			mchan->last_success = last_cookie;
-			result.result = DMA_TRANS_NOERROR;
-		} else
-			result.result = DMA_TRANS_ABORTED;
-
 		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
 		dmaengine_desc_callback_invoke(&cb, &result);
@@ -415,6 +416,7 @@ hidma_prep_dma_memcpy(struct dma_chan *dmach, dma_addr_t dest, dma_addr_t src,
 	if (!mdesc)
 		return NULL;
 
+	mdesc->desc.flags = flags;
 	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
 				     src, dest, len, flags,
 				     HIDMA_TRE_MEMCPY);
@@ -447,6 +449,7 @@ hidma_prep_dma_memset(struct dma_chan *dmach, dma_addr_t dest, int value,
 	if (!mdesc)
 		return NULL;
 
+	mdesc->desc.flags = flags;
 	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
 				     value, dest, len, flags,
 				     HIDMA_TRE_MEMSET);
diff --git a/drivers/dma/qcom/hidma_dbg.c b/drivers/dma/qcom/hidma_dbg.c
index 3bdcb8056a36..9523faf7acdc 100644
--- a/drivers/dma/qcom/hidma_dbg.c
+++ b/drivers/dma/qcom/hidma_dbg.c
@@ -85,11 +85,11 @@ static void hidma_ll_devstats(struct seq_file *s, void *llhndl)
 }
 
 /*
- * hidma_chan_stats: display HIDMA channel statistics
+ * hidma_chan_show: display HIDMA channel statistics
  *
  * Display the statistics for the current HIDMA virtual channel device.
  */
-static int hidma_chan_stats(struct seq_file *s, void *unused)
+static int hidma_chan_show(struct seq_file *s, void *unused)
 {
 	struct hidma_chan *mchan = s->private;
 	struct hidma_desc *mdesc;
@@ -117,11 +117,11 @@ static int hidma_chan_stats(struct seq_file *s, void *unused)
 }
 
 /*
- * hidma_dma_info: display HIDMA device info
+ * hidma_dma_show: display HIDMA device info
  *
  * Display the info for the current HIDMA device.
  */
-static int hidma_dma_info(struct seq_file *s, void *unused)
+static int hidma_dma_show(struct seq_file *s, void *unused)
 {
 	struct hidma_dev *dmadev = s->private;
 	resource_size_t sz;
@@ -138,29 +138,8 @@ static int hidma_dma_info(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int hidma_chan_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hidma_chan_stats, inode->i_private);
-}
-
-static int hidma_dma_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hidma_dma_info, inode->i_private);
-}
-
-static const struct file_operations hidma_chan_fops = {
-	.open = hidma_chan_stats_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static const struct file_operations hidma_dma_fops = {
-	.open = hidma_dma_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(hidma_chan);
+DEFINE_SHOW_ATTRIBUTE(hidma_dma);
 
 void hidma_debug_uninit(struct hidma_dev *dmadev)
 {
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index d64edeb6771a..681de12f4c67 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -423,9 +423,8 @@ static int __init hidma_mgmt_init(void)
 		hidma_mgmt_of_populate_channels(child);
 	}
 #endif
-	platform_driver_register(&hidma_mgmt_driver);
+	return platform_driver_register(&hidma_mgmt_driver);
 
-	return 0;
 }
 module_init(hidma_mgmt_init);
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index b31d07c7d93c..3fae23768b47 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/sa11x0-dma.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -706,7 +705,6 @@ static int sa11x0_dma_device_pause(struct dma_chan *chan)
 	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
 	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
 	struct sa11x0_dma_phy *p;
-	LIST_HEAD(head);
 	unsigned long flags;
 
 	dev_dbg(d->slave.dev, "vchan %p: pause\n", &c->vc);
@@ -733,7 +731,6 @@ static int sa11x0_dma_device_resume(struct dma_chan *chan)
 	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
 	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
 	struct sa11x0_dma_phy *p;
-	LIST_HEAD(head);
 	unsigned long flags;
 
 	dev_dbg(d->slave.dev, "vchan %p: resume\n", &c->vc);
@@ -830,6 +827,14 @@ static const struct dma_slave_map sa11x0_dma_map[] = {
 	{ "sa11x0-ssp", "rx", "Ser4SSPRc" },
 };
 
+static bool sa11x0_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	const char *p = param;
+
+	return !strcmp(c->name, p);
+}
+
 static int sa11x0_dma_init_dmadev(struct dma_device *dmadev,
 	struct device *dev)
 {
@@ -1087,18 +1092,6 @@ static struct platform_driver sa11x0_dma_driver = {
 	.remove		= sa11x0_dma_remove,
 };
 
-bool sa11x0_dma_filter_fn(struct dma_chan *chan, void *param)
-{
-	if (chan->device->dev->driver == &sa11x0_dma_driver.driver) {
-		struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
-		const char *p = param;
-
-		return !strcmp(c->name, p);
-	}
-	return false;
-}
-EXPORT_SYMBOL(sa11x0_dma_filter_fn);
-
 static int __init sa11x0_dma_init(void)
 {
 	return platform_driver_register(&sa11x0_dma_driver);
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index 6e0685f1a838..4d6b02b3b1f1 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # DMA engine configuration for sh
 #
@@ -12,7 +13,7 @@ config RENESAS_DMA
 
 config SH_DMAE_BASE
 	bool "Renesas SuperH DMA Engine support"
-	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
+	depends on SUPERH || COMPILE_TEST
 	depends on !SUPERH || SH_DMA
 	depends on !SH_DMA_API
 	default y
@@ -30,15 +31,6 @@ config SH_DMAE
 	help
 	  Enable support for the Renesas SuperH DMA controllers.
 
-if SH_DMAE
-
-config SH_DMAE_R8A73A4
-	def_bool y
-	depends on ARCH_R8A73A4
-	depends on OF
-
-endif
-
 config RCAR_DMAC
 	tristate "Renesas R-Car Gen2 DMA Controller"
 	depends on ARCH_RENESAS || COMPILE_TEST
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index 7d7c9491ade1..42110dd57a56 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_SH_DMAE_BASE) += shdma-base.o shdma-of.o
 #
 
 shdma-y := shdmac.o
-shdma-$(CONFIG_SH_DMAE_R8A73A4) += shdma-r8a73a4.o
 shdma-objs := $(shdma-y)
 obj-$(CONFIG_SH_DMAE) += shdma.o
 
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 74fa2b1a6a86..e2a5398f89b5 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1282,6 +1282,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	enum dma_status status;
 	unsigned int residue = 0;
 	unsigned int dptr = 0;
+	unsigned int chcrb;
+	unsigned int tcrb;
+	unsigned int i;
 
 	if (!desc)
 		return 0;
@@ -1330,14 +1333,31 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/*
+	 * We need to read two registers.
+	 * Make sure the control register does not skip to next chunk
+	 * while reading the counter.
+	 * Trying it 3 times should be enough: Initial read, retry, retry
+	 * for the paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+					    RCAR_DMACHCRB_DPTR_MASK;
+		tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+		/* Still the same? */
+		if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+			      RCAR_DMACHCRB_DPTR_MASK))
+			break;
+	}
+	WARN_ONCE(i >= 3, "residue might be not continuous!");
+
+	/*
 	 * In descriptor mode the descriptor running pointer is not maintained
 	 * by the interrupt handler, find the running descriptor from the
 	 * descriptor pointer field in the CHCRB register. In non-descriptor
 	 * mode just use the running descriptor pointer.
 	 */
 	if (desc->hwdescs.use) {
-		dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
-			RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+		dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
 		if (dptr == 0)
 			dptr = desc->nchunks;
 		dptr--;
@@ -1355,7 +1375,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+	residue += tcrb << desc->xfer_shift;
 
 	return residue;
 }
@@ -1368,6 +1388,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 	enum dma_status status;
 	unsigned long flags;
 	unsigned int residue;
+	bool cyclic;
 
 	status = dma_cookie_status(chan, cookie, txstate);
 	if (status == DMA_COMPLETE || !txstate)
@@ -1375,10 +1396,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&rchan->lock, flags);
 	residue = rcar_dmac_chan_get_residue(rchan, cookie);
+	cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
 	spin_unlock_irqrestore(&rchan->lock, flags);
 
 	/* if there's no residue, the cookie is complete */
-	if (!residue)
+	if (!residue && !cyclic)
 		return DMA_COMPLETE;
 
 	dma_set_residue(txstate, residue);
@@ -1809,7 +1831,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	 * level we can't disable it selectively, so ignore channel 0 for now if
 	 * the device is part of an IOMMU group.
 	 */
-	if (pdev->dev.iommu_group) {
+	if (device_iommu_mapped(&pdev->dev)) {
 		dmac->n_channels--;
 		channels_offset = 1;
 	}
diff --git a/drivers/dma/sh/shdma-r8a73a4.c b/drivers/dma/sh/shdma-r8a73a4.c
deleted file mode 100644
index ddc9a3578353..000000000000
--- a/drivers/dma/sh/shdma-r8a73a4.c
+++ /dev/null
@@ -1,74 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Renesas SuperH DMA Engine support for r8a73a4 (APE6) SoCs
- *
- * Copyright (C) 2013 Renesas Electronics, Inc.
- */
-#include <linux/sh_dma.h>
-
-#include "shdma-arm.h"
-
-static const unsigned int dma_ts_shift[] = SH_DMAE_TS_SHIFT;
-
-static const struct sh_dmae_slave_config dma_slaves[] = {
-	{
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd1,		/* MMC0 Tx */
-	}, {
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd2,		/* MMC0 Rx */
-	}, {
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xe1,		/* MMC1 Tx */
-	}, {
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xe2,		/* MMC1 Rx */
-	},
-};
-
-#define DMAE_CHANNEL(a, b)				\
-	{						\
-		.offset         = (a) - 0x20,		\
-		.dmars          = (a) - 0x20 + 0x40,	\
-		.chclr_bit	= (b),			\
-		.chclr_offset	= 0x80 - 0x20,		\
-	}
-
-static const struct sh_dmae_channel dma_channels[] = {
-	DMAE_CHANNEL(0x8000, 0),
-	DMAE_CHANNEL(0x8080, 1),
-	DMAE_CHANNEL(0x8100, 2),
-	DMAE_CHANNEL(0x8180, 3),
-	DMAE_CHANNEL(0x8200, 4),
-	DMAE_CHANNEL(0x8280, 5),
-	DMAE_CHANNEL(0x8300, 6),
-	DMAE_CHANNEL(0x8380, 7),
-	DMAE_CHANNEL(0x8400, 8),
-	DMAE_CHANNEL(0x8480, 9),
-	DMAE_CHANNEL(0x8500, 10),
-	DMAE_CHANNEL(0x8580, 11),
-	DMAE_CHANNEL(0x8600, 12),
-	DMAE_CHANNEL(0x8680, 13),
-	DMAE_CHANNEL(0x8700, 14),
-	DMAE_CHANNEL(0x8780, 15),
-	DMAE_CHANNEL(0x8800, 16),
-	DMAE_CHANNEL(0x8880, 17),
-	DMAE_CHANNEL(0x8900, 18),
-	DMAE_CHANNEL(0x8980, 19),
-};
-
-const struct sh_dmae_pdata r8a73a4_dma_pdata = {
-	.slave		= dma_slaves,
-	.slave_num	= ARRAY_SIZE(dma_slaves),
-	.channel	= dma_channels,
-	.channel_num	= ARRAY_SIZE(dma_channels),
-	.ts_low_shift	= TS_LOW_SHIFT,
-	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
-	.ts_high_shift	= TS_HI_SHIFT,
-	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
-	.ts_shift	= dma_ts_shift,
-	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
-	.dmaor_init     = DMAOR_DME,
-	.chclr_present	= 1,
-	.chclr_bitwise	= 1,
-};
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index bfb69909bd19..9c121a4b33ad 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -58,11 +58,4 @@ struct sh_dmae_desc {
 #define to_sh_dev(chan) container_of(chan->shdma_chan.dma_chan.device,\
 				     struct sh_dmae_device, shdma_dev.dma_dev)
 
-#ifdef CONFIG_SH_DMAE_R8A73A4
-extern const struct sh_dmae_pdata r8a73a4_dma_pdata;
-#define r8a73a4_shdma_devid (&r8a73a4_dma_pdata)
-#else
-#define r8a73a4_shdma_devid NULL
-#endif
-
 #endif	/* __DMA_SHDMA_H */
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 7971ea275387..5aafe548ca5f 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -665,12 +665,6 @@ static const struct shdma_ops sh_dmae_shdma_ops = {
 	.get_partial = sh_dmae_get_partial,
 };
 
-static const struct of_device_id sh_dmae_of_match[] = {
-	{.compatible = "renesas,shdma-r8a73a4", .data = r8a73a4_shdma_devid,},
-	{}
-};
-MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
-
 static int sh_dmae_probe(struct platform_device *pdev)
 {
 	const enum dma_slave_buswidth widths =
@@ -915,7 +909,6 @@ static struct platform_driver sh_dmae_driver = {
 	.driver		= {
 		.pm	= &sh_dmae_pm,
 		.name	= SH_DMAE_DRV_NAME,
-		.of_match_table = sh_dmae_of_match,
 	},
 	.remove		= sh_dmae_remove,
 };
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index 7f7184c3cf95..59403f6d008a 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -694,6 +694,8 @@ static int usb_dmac_runtime_resume(struct device *dev)
 #endif /* CONFIG_PM */
 
 static const struct dev_pm_ops usb_dmac_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				      pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(usb_dmac_runtime_suspend, usb_dmac_runtime_resume,
 			   NULL)
 };
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 38d4e4f07c66..48431e2da987 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -36,6 +36,8 @@
 #define SPRD_DMA_GLB_CHN_EN_STS		0x1c
 #define SPRD_DMA_GLB_DEBUG_STS		0x20
 #define SPRD_DMA_GLB_ARB_SEL_STS	0x24
+#define SPRD_DMA_GLB_2STAGE_GRP1	0x28
+#define SPRD_DMA_GLB_2STAGE_GRP2	0x2c
 #define SPRD_DMA_GLB_REQ_UID(uid)	(0x4 * ((uid) - 1))
 #define SPRD_DMA_GLB_REQ_UID_OFFSET	0x2000
 
@@ -57,6 +59,18 @@
 #define SPRD_DMA_CHN_SRC_BLK_STEP	0x38
 #define SPRD_DMA_CHN_DES_BLK_STEP	0x3c
 
+/* SPRD_DMA_GLB_2STAGE_GRP register definition */
+#define SPRD_DMA_GLB_2STAGE_EN		BIT(24)
+#define SPRD_DMA_GLB_CHN_INT_MASK	GENMASK(23, 20)
+#define SPRD_DMA_GLB_LIST_DONE_TRG	BIT(19)
+#define SPRD_DMA_GLB_TRANS_DONE_TRG	BIT(18)
+#define SPRD_DMA_GLB_BLOCK_DONE_TRG	BIT(17)
+#define SPRD_DMA_GLB_FRAG_DONE_TRG	BIT(16)
+#define SPRD_DMA_GLB_TRG_OFFSET		16
+#define SPRD_DMA_GLB_DEST_CHN_MASK	GENMASK(13, 8)
+#define SPRD_DMA_GLB_DEST_CHN_OFFSET	8
+#define SPRD_DMA_GLB_SRC_CHN_MASK	GENMASK(5, 0)
+
 /* SPRD_DMA_CHN_INTC register definition */
 #define SPRD_DMA_INT_MASK		GENMASK(4, 0)
 #define SPRD_DMA_INT_CLR_OFFSET		24
@@ -118,6 +132,10 @@
 #define SPRD_DMA_SRC_TRSF_STEP_OFFSET	0
 #define SPRD_DMA_TRSF_STEP_MASK		GENMASK(15, 0)
 
+/* define DMA channel mode & trigger mode mask */
+#define SPRD_DMA_CHN_MODE_MASK		GENMASK(7, 0)
+#define SPRD_DMA_TRG_MODE_MASK		GENMASK(7, 0)
+
 /* define the DMA transfer step type */
 #define SPRD_DMA_NONE_STEP		0
 #define SPRD_DMA_BYTE_STEP		1
@@ -159,6 +177,7 @@ struct sprd_dma_chn_hw {
 struct sprd_dma_desc {
 	struct virt_dma_desc	vd;
 	struct sprd_dma_chn_hw	chn_hw;
+	enum dma_transfer_direction dir;
 };
 
 /* dma channel description */
@@ -169,6 +188,8 @@ struct sprd_dma_chn {
 	struct dma_slave_config	slave_cfg;
 	u32			chn_num;
 	u32			dev_id;
+	enum sprd_dma_chn_mode	chn_mode;
+	enum sprd_dma_trg_mode	trg_mode;
 	struct sprd_dma_desc	*cur_desc;
 };
 
@@ -205,6 +226,16 @@ static inline struct sprd_dma_desc *to_sprd_dma_desc(struct virt_dma_desc *vd)
 	return container_of(vd, struct sprd_dma_desc, vd);
 }
 
+static void sprd_dma_glb_update(struct sprd_dma_dev *sdev, u32 reg,
+				u32 mask, u32 val)
+{
+	u32 orig = readl(sdev->glb_base + reg);
+	u32 tmp;
+
+	tmp = (orig & ~mask) | val;
+	writel(tmp, sdev->glb_base + reg);
+}
+
 static void sprd_dma_chn_update(struct sprd_dma_chn *schan, u32 reg,
 				u32 mask, u32 val)
 {
@@ -331,6 +362,17 @@ static void sprd_dma_stop_and_disable(struct sprd_dma_chn *schan)
 	sprd_dma_disable_chn(schan);
 }
 
+static unsigned long sprd_dma_get_src_addr(struct sprd_dma_chn *schan)
+{
+	unsigned long addr, addr_high;
+
+	addr = readl(schan->chn_base + SPRD_DMA_CHN_SRC_ADDR);
+	addr_high = readl(schan->chn_base + SPRD_DMA_CHN_WARP_PTR) &
+		    SPRD_DMA_HIGH_ADDR_MASK;
+
+	return addr | (addr_high << SPRD_DMA_HIGH_ADDR_OFFSET);
+}
+
 static unsigned long sprd_dma_get_dst_addr(struct sprd_dma_chn *schan)
 {
 	unsigned long addr, addr_high;
@@ -377,6 +419,49 @@ static enum sprd_dma_req_mode sprd_dma_get_req_type(struct sprd_dma_chn *schan)
 	return (frag_reg >> SPRD_DMA_REQ_MODE_OFFSET) & SPRD_DMA_REQ_MODE_MASK;
 }
 
+static int sprd_dma_set_2stage_config(struct sprd_dma_chn *schan)
+{
+	struct sprd_dma_dev *sdev = to_sprd_dma_dev(&schan->vc.chan);
+	u32 val, chn = schan->chn_num + 1;
+
+	switch (schan->chn_mode) {
+	case SPRD_DMA_SRC_CHN0:
+		val = chn & SPRD_DMA_GLB_SRC_CHN_MASK;
+		val |= BIT(schan->trg_mode - 1) << SPRD_DMA_GLB_TRG_OFFSET;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP1, val, val);
+		break;
+
+	case SPRD_DMA_SRC_CHN1:
+		val = chn & SPRD_DMA_GLB_SRC_CHN_MASK;
+		val |= BIT(schan->trg_mode - 1) << SPRD_DMA_GLB_TRG_OFFSET;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP2, val, val);
+		break;
+
+	case SPRD_DMA_DST_CHN0:
+		val = (chn << SPRD_DMA_GLB_DEST_CHN_OFFSET) &
+			SPRD_DMA_GLB_DEST_CHN_MASK;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP1, val, val);
+		break;
+
+	case SPRD_DMA_DST_CHN1:
+		val = (chn << SPRD_DMA_GLB_DEST_CHN_OFFSET) &
+			SPRD_DMA_GLB_DEST_CHN_MASK;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP2, val, val);
+		break;
+
+	default:
+		dev_err(sdev->dma_dev.dev, "invalid channel mode setting %d\n",
+			schan->chn_mode);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void sprd_dma_set_chn_config(struct sprd_dma_chn *schan,
 				    struct sprd_dma_desc *sdesc)
 {
@@ -411,6 +496,13 @@ static void sprd_dma_start(struct sprd_dma_chn *schan)
 	schan->cur_desc = to_sprd_dma_desc(vd);
 
 	/*
+	 * Set 2-stage configuration if the channel starts one 2-stage
+	 * transfer.
+	 */
+	if (schan->chn_mode && sprd_dma_set_2stage_config(schan))
+		return;
+
+	/*
 	 * Copy the DMA configuration from DMA descriptor to this hardware
 	 * channel.
 	 */
@@ -427,6 +519,7 @@ static void sprd_dma_stop(struct sprd_dma_chn *schan)
 	sprd_dma_stop_and_disable(schan);
 	sprd_dma_unset_uid(schan);
 	sprd_dma_clear_int(schan);
+	schan->cur_desc = NULL;
 }
 
 static bool sprd_dma_check_trans_done(struct sprd_dma_desc *sdesc,
@@ -450,7 +543,7 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 	struct sprd_dma_desc *sdesc;
 	enum sprd_dma_req_mode req_type;
 	enum sprd_dma_int_type int_type;
-	bool trans_done = false;
+	bool trans_done = false, cyclic = false;
 	u32 i;
 
 	while (irq_status) {
@@ -465,13 +558,19 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 
 		sdesc = schan->cur_desc;
 
-		/* Check if the dma request descriptor is done. */
-		trans_done = sprd_dma_check_trans_done(sdesc, int_type,
-						       req_type);
-		if (trans_done == true) {
-			vchan_cookie_complete(&sdesc->vd);
-			schan->cur_desc = NULL;
-			sprd_dma_start(schan);
+		/* cyclic mode schedule callback */
+		cyclic = schan->linklist.phy_addr ? true : false;
+		if (cyclic == true) {
+			vchan_cyclic_callback(&sdesc->vd);
+		} else {
+			/* Check if the dma request descriptor is done. */
+			trans_done = sprd_dma_check_trans_done(sdesc, int_type,
+							       req_type);
+			if (trans_done == true) {
+				vchan_cookie_complete(&sdesc->vd);
+				schan->cur_desc = NULL;
+				sprd_dma_start(schan);
+			}
 		}
 		spin_unlock(&schan->vc.lock);
 	}
@@ -481,15 +580,7 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 
 static int sprd_dma_alloc_chan_resources(struct dma_chan *chan)
 {
-	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
-	int ret;
-
-	ret = pm_runtime_get_sync(chan->device->dev);
-	if (ret < 0)
-		return ret;
-
-	schan->dev_id = SPRD_DMA_SOFTWARE_UID;
-	return 0;
+	return pm_runtime_get_sync(chan->device->dev);
 }
 
 static void sprd_dma_free_chan_resources(struct dma_chan *chan)
@@ -534,7 +625,12 @@ static enum dma_status sprd_dma_tx_status(struct dma_chan *chan,
 		else
 			pos = 0;
 	} else if (schan->cur_desc && schan->cur_desc->vd.tx.cookie == cookie) {
-		pos = sprd_dma_get_dst_addr(schan);
+		struct sprd_dma_desc *sdesc = to_sprd_dma_desc(vd);
+
+		if (sdesc->dir == DMA_DEV_TO_MEM)
+			pos = sprd_dma_get_dst_addr(schan);
+		else
+			pos = sprd_dma_get_src_addr(schan);
 	} else {
 		pos = 0;
 	}
@@ -593,6 +689,7 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 {
 	struct sprd_dma_dev *sdev = to_sprd_dma_dev(chan);
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	enum sprd_dma_chn_mode chn_mode = schan->chn_mode;
 	u32 req_mode = (flags >> SPRD_DMA_REQ_SHIFT) & SPRD_DMA_REQ_MODE_MASK;
 	u32 int_mode = flags & SPRD_DMA_INT_MASK;
 	int src_datawidth, dst_datawidth, src_step, dst_step;
@@ -604,7 +701,16 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 			dev_err(sdev->dma_dev.dev, "invalid source step\n");
 			return src_step;
 		}
-		dst_step = SPRD_DMA_NONE_STEP;
+
+		/*
+		 * For 2-stage transfer, destination channel step can not be 0,
+		 * since destination device is AON IRAM.
+		 */
+		if (chn_mode == SPRD_DMA_DST_CHN0 ||
+		    chn_mode == SPRD_DMA_DST_CHN1)
+			dst_step = src_step;
+		else
+			dst_step = SPRD_DMA_NONE_STEP;
 	} else {
 		dst_step = sprd_dma_get_step(slave_cfg->dst_addr_width);
 		if (dst_step < 0) {
@@ -674,13 +780,11 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 
 	/* link-list configuration */
 	if (schan->linklist.phy_addr) {
-		if (sg_index == sglen - 1)
-			hw->frg_len |= SPRD_DMA_LLIST_END;
-
 		hw->cfg |= SPRD_DMA_LINKLIST_EN;
 
 		/* link-list index */
-		temp = (sg_index + 1) % sglen;
+		temp = sglen ? (sg_index + 1) % sglen : 0;
+
 		/* Next link-list configuration's physical address offset */
 		temp = temp * sizeof(*hw) + SPRD_DMA_CHN_SRC_ADDR;
 		/*
@@ -804,6 +908,8 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!sdesc)
 		return NULL;
 
+	sdesc->dir = dir;
+
 	for_each_sg(sgl, sg, sglen, i) {
 		len = sg_dma_len(sg);
 
@@ -831,6 +937,12 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		}
 	}
 
+	/* Set channel mode and trigger mode for 2-stage transfer */
+	schan->chn_mode =
+		(flags >> SPRD_DMA_CHN_MODE_SHIFT) & SPRD_DMA_CHN_MODE_MASK;
+	schan->trg_mode =
+		(flags >> SPRD_DMA_TRG_MODE_SHIFT) & SPRD_DMA_TRG_MODE_MASK;
+
 	ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, src, dst, len,
 				 dir, flags, slave_cfg);
 	if (ret) {
@@ -847,9 +959,6 @@ static int sprd_dma_slave_config(struct dma_chan *chan,
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
 	struct dma_slave_config *slave_cfg = &schan->slave_cfg;
 
-	if (!is_slave_direction(config->direction))
-		return -EINVAL;
-
 	memcpy(slave_cfg, config, sizeof(*config));
 	return 0;
 }
@@ -904,13 +1013,10 @@ static void sprd_dma_free_desc(struct virt_dma_desc *vd)
 static bool sprd_dma_filter_fn(struct dma_chan *chan, void *param)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
-	struct sprd_dma_dev *sdev = to_sprd_dma_dev(&schan->vc.chan);
-	u32 req = *(u32 *)param;
+	u32 slave_id = *(u32 *)param;
 
-	if (req < sdev->total_chns)
-		return req == schan->chn_num + 1;
-	else
-		return false;
+	schan->dev_id = slave_id;
+	return true;
 }
 
 static int sprd_dma_probe(struct platform_device *pdev)
@@ -1109,4 +1215,5 @@ module_platform_driver(sprd_dma_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("DMA driver for Spreadtrum");
 MODULE_AUTHOR("Baolin Wang <baolin.wang@spreadtrum.com>");
+MODULE_AUTHOR("Eric Long <eric.long@spreadtrum.com>");
 MODULE_ALIAS("platform:sprd-dma");
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index 07c20aa2e955..bc7a1de3f29b 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -243,8 +243,7 @@ static struct st_fdma_desc *st_fdma_alloc_desc(struct st_fdma_chan *fchan,
 	struct st_fdma_desc *fdesc;
 	int i;
 
-	fdesc = kzalloc(sizeof(*fdesc) +
-			sizeof(struct st_fdma_sw_node) * sg_len, GFP_NOWAIT);
+	fdesc = kzalloc(struct_size(fdesc, node, sg_len), GFP_NOWAIT);
 	if (!fdesc)
 		return NULL;
 
@@ -294,8 +293,6 @@ static void st_fdma_free_chan_res(struct dma_chan *chan)
 	struct rproc *rproc = fchan->fdev->slim_rproc->rproc;
 	unsigned long flags;
 
-	LIST_HEAD(head);
-
 	dev_dbg(fchan->fdev->dev, "%s: freeing chan:%d\n",
 		__func__, fchan->vchan.chan.chan_id);
 
@@ -626,7 +623,6 @@ static void st_fdma_issue_pending(struct dma_chan *chan)
 static int st_fdma_pause(struct dma_chan *chan)
 {
 	unsigned long flags;
-	LIST_HEAD(head);
 	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
 	int ch_id = fchan->vchan.chan.chan_id;
 	unsigned long cmd = FDMA_CMD_PAUSE(ch_id);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 5e328bd10c27..907ae97a3ef4 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -442,6 +442,7 @@ struct d40_base;
  * @queue: Queued jobs.
  * @prepare_queue: Prepared jobs.
  * @dma_cfg: The client configuration of this dma channel.
+ * @slave_config: DMA slave configuration.
  * @configured: whether the dma_cfg configuration is valid
  * @base: Pointer to the device instance struct.
  * @src_def_cfg: Default cfg register setting for src.
@@ -468,6 +469,7 @@ struct d40_chan {
 	struct list_head		 queue;
 	struct list_head		 prepare_queue;
 	struct stedma40_chan_cfg	 dma_cfg;
+	struct dma_slave_config		 slave_config;
 	bool				 configured;
 	struct d40_base			*base;
 	/* Default register configurations */
@@ -625,6 +627,10 @@ static void __iomem *chan_base(struct d40_chan *chan)
 #define chan_err(d40c, format, arg...)		\
 	d40_err(chan2dev(d40c), format, ## arg)
 
+static int d40_set_runtime_config_write(struct dma_chan *chan,
+				  struct dma_slave_config *config,
+				  enum dma_transfer_direction direction);
+
 static int d40_pool_lli_alloc(struct d40_chan *d40c, struct d40_desc *d40d,
 			      int lli_len)
 {
@@ -2216,6 +2222,8 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 		return NULL;
 	}
 
+	d40_set_runtime_config_write(dchan, &chan->slave_config, direction);
+
 	spin_lock_irqsave(&chan->lock, flags);
 
 	desc = d40_prep_desc(chan, sg_src, sg_len, dma_flags);
@@ -2634,11 +2642,22 @@ dma40_config_to_halfchannel(struct d40_chan *d40c,
 	return 0;
 }
 
-/* Runtime reconfiguration extension */
 static int d40_set_runtime_config(struct dma_chan *chan,
 				  struct dma_slave_config *config)
 {
 	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
+
+	memcpy(&d40c->slave_config, config, sizeof(*config));
+
+	return 0;
+}
+
+/* Runtime reconfiguration extension */
+static int d40_set_runtime_config_write(struct dma_chan *chan,
+				  struct dma_slave_config *config,
+				  enum dma_transfer_direction direction)
+{
+	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
 	struct stedma40_chan_cfg *cfg = &d40c->dma_cfg;
 	enum dma_slave_buswidth src_addr_width, dst_addr_width;
 	dma_addr_t config_addr;
@@ -2655,7 +2674,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 	dst_addr_width = config->dst_addr_width;
 	dst_maxburst = config->dst_maxburst;
 
-	if (config->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		config_addr = config->src_addr;
 
 		if (cfg->dir != DMA_DEV_TO_MEM)
@@ -2671,7 +2690,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 		if (dst_maxburst == 0)
 			dst_maxburst = src_maxburst;
 
-	} else if (config->direction == DMA_MEM_TO_DEV) {
+	} else if (direction == DMA_MEM_TO_DEV) {
 		config_addr = config->dst_addr;
 
 		if (cfg->dir != DMA_MEM_TO_DEV)
@@ -2689,7 +2708,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 	} else {
 		dev_err(d40c->base->dev,
 			"unrecognized channel direction %d\n",
-			config->direction);
+			direction);
 		return -EINVAL;
 	}
 
@@ -2746,12 +2765,12 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 
 	/* These settings will take precedence later */
 	d40c->runtime_addr = config_addr;
-	d40c->runtime_direction = config->direction;
+	d40c->runtime_direction = direction;
 	dev_dbg(d40c->base->dev,
 		"configured channel %s for %s, data width %d/%d, "
 		"maxburst %d/%d elements, LE, no flow control\n",
 		dma_chan_name(chan),
-		(config->direction == DMA_DEV_TO_MEM) ? "RX" : "TX",
+		(direction == DMA_DEV_TO_MEM) ? "RX" : "TX",
 		src_addr_width, dst_addr_width,
 		src_maxburst, dst_maxburst);
 
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 4903a408fc14..ba239b529fa9 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -23,6 +23,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -641,12 +642,13 @@ 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;
+	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) {
 		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
@@ -661,10 +663,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 	if (status & STM32_DMA_FEI) {
 		stm32_dma_irq_clear(chan, STM32_DMA_FEI);
 		status &= ~STM32_DMA_FEI;
-		if (!(scr & STM32_DMA_SCR_EN))
-			dev_err(chan2dev(chan), "FIFO Error\n");
-		else
-			dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
+		if (sfcr & STM32_DMA_SFCR_FEIE) {
+			if (!(scr & STM32_DMA_SCR_EN))
+				dev_err(chan2dev(chan), "FIFO Error\n");
+			else
+				dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
+		}
 	}
 	if (status) {
 		stm32_dma_irq_clear(chan, status);
@@ -1112,15 +1116,14 @@ static int stm32_dma_alloc_chan_resources(struct dma_chan *c)
 	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);
+
+	ret = pm_runtime_get_sync(dmadev->ddev.dev);
+	if (ret < 0)
 		return ret;
-	}
 
 	ret = stm32_dma_disable_chan(chan);
 	if (ret < 0)
-		clk_disable_unprepare(dmadev->clk);
+		pm_runtime_put(dmadev->ddev.dev);
 
 	return ret;
 }
@@ -1140,7 +1143,7 @@ static void stm32_dma_free_chan_resources(struct dma_chan *c)
 		spin_unlock_irqrestore(&chan->vchan.lock, flags);
 	}
 
-	clk_disable_unprepare(dmadev->clk);
+	pm_runtime_put(dmadev->ddev.dev);
 
 	vchan_free_chan_resources(to_virt_chan(c));
 }
@@ -1240,6 +1243,12 @@ static int stm32_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(dmadev->clk);
 	}
 
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "clk_prep_enable error: %d\n", ret);
+		return ret;
+	}
+
 	dmadev->mem2mem = of_property_read_bool(pdev->dev.of_node,
 						"st,mem2mem");
 
@@ -1289,7 +1298,7 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	ret = dma_async_device_register(dd);
 	if (ret)
-		return ret;
+		goto clk_free;
 
 	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
 		chan = &dmadev->chan[i];
@@ -1321,20 +1330,58 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dmadev);
 
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
+
 	dev_info(&pdev->dev, "STM32 DMA driver registered\n");
 
 	return 0;
 
 err_unregister:
 	dma_async_device_unregister(dd);
+clk_free:
+	clk_disable_unprepare(dmadev->clk);
 
 	return ret;
 }
 
+#ifdef CONFIG_PM
+static int stm32_dma_runtime_suspend(struct device *dev)
+{
+	struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dmadev->clk);
+
+	return 0;
+}
+
+static int stm32_dma_runtime_resume(struct device *dev)
+{
+	struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret) {
+		dev_err(dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_dma_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_dma_runtime_suspend,
+			   stm32_dma_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_dma_driver = {
 	.driver = {
 		.name = "stm32-dma",
 		.of_match_table = stm32_dma_of_match,
+		.pm = &stm32_dma_pm_ops,
 	},
 };
 
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index b922db90939a..a67119199c45 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -79,8 +80,7 @@ static void stm32_dmamux_free(struct device *dev, void *route_data)
 	stm32_dmamux_write(dmamux->iomem, STM32_DMAMUX_CCR(mux->chan_id), 0);
 	clear_bit(mux->chan_id, dmamux->dma_inuse);
 
-	if (!IS_ERR(dmamux->clk))
-		clk_disable(dmamux->clk);
+	pm_runtime_put_sync(dev);
 
 	spin_unlock_irqrestore(&dmamux->lock, flags);
 
@@ -146,13 +146,10 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec,
 
 	/* Set dma request */
 	spin_lock_irqsave(&dmamux->lock, flags);
-	if (!IS_ERR(dmamux->clk)) {
-		ret = clk_enable(dmamux->clk);
-		if (ret < 0) {
-			spin_unlock_irqrestore(&dmamux->lock, flags);
-			dev_err(&pdev->dev, "clk_prep_enable issue: %d\n", ret);
-			goto error;
-		}
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		spin_unlock_irqrestore(&dmamux->lock, flags);
+		goto error;
 	}
 	spin_unlock_irqrestore(&dmamux->lock, flags);
 
@@ -254,6 +251,7 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "DMAMUX defaulting on %u requests\n",
 			 stm32_dmamux->dmamux_requests);
 	}
+	pm_runtime_get_noresume(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iomem = devm_ioremap_resource(&pdev->dev, res);
@@ -282,6 +280,8 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	stm32_dmamux->dmarouter.route_free = stm32_dmamux_free;
 
 	platform_set_drvdata(pdev, stm32_dmamux);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 
 	if (!IS_ERR(stm32_dmamux->clk)) {
 		ret = clk_prepare_enable(stm32_dmamux->clk);
@@ -291,17 +291,52 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 		}
 	}
 
+	pm_runtime_get_noresume(&pdev->dev);
+
 	/* Reset the dmamux */
 	for (i = 0; i < stm32_dmamux->dma_requests; i++)
 		stm32_dmamux_write(stm32_dmamux->iomem, STM32_DMAMUX_CCR(i), 0);
 
-	if (!IS_ERR(stm32_dmamux->clk))
-		clk_disable(stm32_dmamux->clk);
+	pm_runtime_put(&pdev->dev);
 
 	return of_dma_router_register(node, stm32_dmamux_route_allocate,
 				     &stm32_dmamux->dmarouter);
 }
 
+#ifdef CONFIG_PM
+static int stm32_dmamux_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev =
+		container_of(dev, struct platform_device, dev);
+	struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(stm32_dmamux->clk);
+
+	return 0;
+}
+
+static int stm32_dmamux_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev =
+		container_of(dev, struct platform_device, dev);
+	struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = clk_prepare_enable(stm32_dmamux->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_dmamux_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_dmamux_runtime_suspend,
+			   stm32_dmamux_runtime_resume, NULL)
+};
+
 static const struct of_device_id stm32_dmamux_match[] = {
 	{ .compatible = "st,stm32h7-dmamux" },
 	{},
@@ -312,6 +347,7 @@ static struct platform_driver stm32_dmamux_driver = {
 	.driver = {
 		.name = "stm32-dmamux",
 		.of_match_table = stm32_dmamux_match,
+		.pm = &stm32_dmamux_pm_ops,
 	},
 };
 
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 390e4cae0e1a..ac0301b69593 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -37,6 +37,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
 
@@ -1456,15 +1457,13 @@ static int stm32_mdma_alloc_chan_resources(struct dma_chan *c)
 		return -ENOMEM;
 	}
 
-	ret = clk_prepare_enable(dmadev->clk);
-	if (ret < 0) {
-		dev_err(chan2dev(chan), "clk_prepare_enable failed: %d\n", ret);
+	ret = pm_runtime_get_sync(dmadev->ddev.dev);
+	if (ret < 0)
 		return ret;
-	}
 
 	ret = stm32_mdma_disable_chan(chan);
 	if (ret < 0)
-		clk_disable_unprepare(dmadev->clk);
+		pm_runtime_put(dmadev->ddev.dev);
 
 	return ret;
 }
@@ -1484,7 +1483,7 @@ static void stm32_mdma_free_chan_resources(struct dma_chan *c)
 		spin_unlock_irqrestore(&chan->vchan.lock, flags);
 	}
 
-	clk_disable_unprepare(dmadev->clk);
+	pm_runtime_put(dmadev->ddev.dev);
 	vchan_free_chan_resources(to_virt_chan(c));
 	dmam_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
@@ -1597,6 +1596,12 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "clk_prep_enable error: %d\n", ret);
+		return ret;
+	}
+
 	dmadev->rst = devm_reset_control_get(&pdev->dev, NULL);
 	if (!IS_ERR(dmadev->rst)) {
 		reset_control_assert(dmadev->rst);
@@ -1668,6 +1673,10 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, dmadev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
 
 	dev_info(&pdev->dev, "STM32 MDMA driver registered\n");
 
@@ -1677,11 +1686,42 @@ err_unregister:
 	return ret;
 }
 
+#ifdef CONFIG_PM
+static int stm32_mdma_runtime_suspend(struct device *dev)
+{
+	struct stm32_mdma_device *dmadev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dmadev->clk);
+
+	return 0;
+}
+
+static int stm32_mdma_runtime_resume(struct device *dev)
+{
+	struct stm32_mdma_device *dmadev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret) {
+		dev_err(dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_mdma_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_mdma_runtime_suspend,
+			   stm32_mdma_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_mdma_driver = {
 	.probe = stm32_mdma_probe,
 	.driver = {
 		.name = "stm32-mdma",
 		.of_match_table = stm32_mdma_of_match,
+		.pm = &stm32_mdma_pm_ops,
 	},
 };
 
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 9a558e30c461..cf462b1abc0b 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -38,6 +38,9 @@
 
 #include "dmaengine.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/tegra_apb_dma.h>
+
 #define TEGRA_APBDMA_GENERAL			0x0
 #define TEGRA_APBDMA_GENERAL_ENABLE		BIT(31)
 
@@ -146,7 +149,7 @@ struct tegra_dma_channel_regs {
 };
 
 /*
- * tegra_dma_sg_req: Dma request details to configure hardware. This
+ * tegra_dma_sg_req: DMA request details to configure hardware. This
  * contains the details for one transfer to configure DMA hw.
  * The client's request for data transfer can be broken into multiple
  * sub-transfer as per requester details and hw support.
@@ -155,7 +158,7 @@ struct tegra_dma_channel_regs {
  */
 struct tegra_dma_sg_req {
 	struct tegra_dma_channel_regs	ch_regs;
-	int				req_len;
+	unsigned int			req_len;
 	bool				configured;
 	bool				last_sg;
 	struct list_head		node;
@@ -169,8 +172,8 @@ struct tegra_dma_sg_req {
  */
 struct tegra_dma_desc {
 	struct dma_async_tx_descriptor	txd;
-	int				bytes_requested;
-	int				bytes_transferred;
+	unsigned int			bytes_requested;
+	unsigned int			bytes_transferred;
 	enum dma_status			dma_status;
 	struct list_head		node;
 	struct list_head		tx_list;
@@ -186,7 +189,7 @@ typedef void (*dma_isr_handler)(struct tegra_dma_channel *tdc,
 /* tegra_dma_channel: Channel specific information */
 struct tegra_dma_channel {
 	struct dma_chan		dma_chan;
-	char			name[30];
+	char			name[12];
 	bool			config_init;
 	int			id;
 	int			irq;
@@ -574,7 +577,7 @@ static bool handle_continuous_head_request(struct tegra_dma_channel *tdc,
 	struct tegra_dma_sg_req *hsgreq = NULL;
 
 	if (list_empty(&tdc->pending_sg_req)) {
-		dev_err(tdc2dev(tdc), "Dma is running without req\n");
+		dev_err(tdc2dev(tdc), "DMA is running without req\n");
 		tegra_dma_stop(tdc);
 		return false;
 	}
@@ -587,7 +590,7 @@ static bool handle_continuous_head_request(struct tegra_dma_channel *tdc,
 	hsgreq = list_first_entry(&tdc->pending_sg_req, typeof(*hsgreq), node);
 	if (!hsgreq->configured) {
 		tegra_dma_stop(tdc);
-		dev_err(tdc2dev(tdc), "Error in dma transfer, aborting dma\n");
+		dev_err(tdc2dev(tdc), "Error in DMA transfer, aborting DMA\n");
 		tegra_dma_abort_all(tdc);
 		return false;
 	}
@@ -636,7 +639,10 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 
 	sgreq = list_first_entry(&tdc->pending_sg_req, typeof(*sgreq), node);
 	dma_desc = sgreq->dma_desc;
-	dma_desc->bytes_transferred += sgreq->req_len;
+	/* if we dma for long enough the transfer count will wrap */
+	dma_desc->bytes_transferred =
+		(dma_desc->bytes_transferred + sgreq->req_len) %
+		dma_desc->bytes_requested;
 
 	/* Callback need to be call */
 	if (!dma_desc->cb_count)
@@ -669,6 +675,8 @@ static void tegra_dma_tasklet(unsigned long data)
 		dmaengine_desc_get_callback(&dma_desc->txd, &cb);
 		cb_count = dma_desc->cb_count;
 		dma_desc->cb_count = 0;
+		trace_tegra_dma_complete_cb(&tdc->dma_chan, cb_count,
+					    cb.callback);
 		spin_unlock_irqrestore(&tdc->lock, flags);
 		while (cb_count--)
 			dmaengine_desc_callback_invoke(&cb, NULL);
@@ -685,6 +693,7 @@ static irqreturn_t tegra_dma_isr(int irq, void *dev_id)
 
 	spin_lock_irqsave(&tdc->lock, flags);
 
+	trace_tegra_dma_isr(&tdc->dma_chan, irq);
 	status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
 	if (status & TEGRA_APBDMA_STATUS_ISE_EOC) {
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_STATUS, status);
@@ -843,6 +852,7 @@ found:
 		dma_set_residue(txstate, residual);
 	}
 
+	trace_tegra_dma_tx_status(&tdc->dma_chan, cookie, txstate);
 	spin_unlock_irqrestore(&tdc->lock, flags);
 	return ret;
 }
@@ -919,7 +929,7 @@ static int get_transfer_param(struct tegra_dma_channel *tdc,
 		return 0;
 
 	default:
-		dev_err(tdc2dev(tdc), "Dma direction is not supported\n");
+		dev_err(tdc2dev(tdc), "DMA direction is not supported\n");
 		return -EINVAL;
 	}
 	return -EINVAL;
@@ -952,7 +962,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 	enum dma_slave_buswidth slave_bw;
 
 	if (!tdc->config_init) {
-		dev_err(tdc2dev(tdc), "dma channel is not configured\n");
+		dev_err(tdc2dev(tdc), "DMA channel is not configured\n");
 		return NULL;
 	}
 	if (sg_len < 1) {
@@ -985,7 +995,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 
 	dma_desc = tegra_dma_desc_get(tdc);
 	if (!dma_desc) {
-		dev_err(tdc2dev(tdc), "Dma descriptors not available\n");
+		dev_err(tdc2dev(tdc), "DMA descriptors not available\n");
 		return NULL;
 	}
 	INIT_LIST_HEAD(&dma_desc->tx_list);
@@ -1005,14 +1015,14 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 		if ((len & 3) || (mem & 3) ||
 				(len > tdc->tdma->chip_data->max_dma_count)) {
 			dev_err(tdc2dev(tdc),
-				"Dma length/memory address is not supported\n");
+				"DMA length/memory address is not supported\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
 
 		sg_req = tegra_dma_sg_req_get(tdc);
 		if (!sg_req) {
-			dev_err(tdc2dev(tdc), "Dma sg-req not available\n");
+			dev_err(tdc2dev(tdc), "DMA sg-req not available\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
@@ -1087,7 +1097,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	 * terminating the DMA.
 	 */
 	if (tdc->busy) {
-		dev_err(tdc2dev(tdc), "Request not allowed when dma running\n");
+		dev_err(tdc2dev(tdc), "Request not allowed when DMA running\n");
 		return NULL;
 	}
 
@@ -1144,7 +1154,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	while (remain_len) {
 		sg_req = tegra_dma_sg_req_get(tdc);
 		if (!sg_req) {
-			dev_err(tdc2dev(tdc), "Dma sg-req not available\n");
+			dev_err(tdc2dev(tdc), "DMA sg-req not available\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
@@ -1319,8 +1329,9 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	tdma = devm_kzalloc(&pdev->dev, sizeof(*tdma) + cdata->nr_channels *
-			sizeof(struct tegra_dma_channel), GFP_KERNEL);
+	tdma = devm_kzalloc(&pdev->dev,
+			    struct_size(tdma, channels, cdata->nr_channels),
+			    GFP_KERNEL);
 	if (!tdma)
 		return -ENOMEM;
 
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index b26256f23d67..5ec0dd97b397 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -678,8 +678,9 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	tdma = devm_kzalloc(&pdev->dev, sizeof(*tdma) + cdata->nr_channels *
-			    sizeof(struct tegra_adma_chan), GFP_KERNEL);
+	tdma = devm_kzalloc(&pdev->dev,
+			    struct_size(tdma, channels, cdata->nr_channels),
+			    GFP_KERNEL);
 	if (!tdma)
 		return -ENOMEM;
 
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index fc0f9c8766a8..afbb1c95b721 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -643,8 +643,8 @@ static int td_probe(struct platform_device *pdev)
 		DRIVER_NAME))
 		return -EBUSY;
 
-	td  = kzalloc(sizeof(struct timb_dma) +
-		sizeof(struct timb_dma_chan) * pdata->nr_channels, GFP_KERNEL);
+	td  = kzalloc(struct_size(td, channels, pdata->nr_channels),
+		      GFP_KERNEL);
 	if (!td) {
 		err = -ENOMEM;
 		goto err_release_region;
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
new file mode 100644
index 000000000000..ec65a7430dc4
--- /dev/null
+++ b/drivers/dma/uniphier-mdmac.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2018 Socionext Inc.
+//   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "virt-dma.h"
+
+/* registers common for all channels */
+#define UNIPHIER_MDMAC_CMD		0x000	/* issue DMA start/abort */
+#define   UNIPHIER_MDMAC_CMD_ABORT		BIT(31) /* 1: abort, 0: start */
+
+/* per-channel registers */
+#define UNIPHIER_MDMAC_CH_OFFSET	0x100
+#define UNIPHIER_MDMAC_CH_STRIDE	0x040
+
+#define UNIPHIER_MDMAC_CH_IRQ_STAT	0x010	/* current hw status (RO) */
+#define UNIPHIER_MDMAC_CH_IRQ_REQ	0x014	/* latched STAT (WOC) */
+#define UNIPHIER_MDMAC_CH_IRQ_EN	0x018	/* IRQ enable mask */
+#define UNIPHIER_MDMAC_CH_IRQ_DET	0x01c	/* REQ & EN (RO) */
+#define   UNIPHIER_MDMAC_CH_IRQ__ABORT		BIT(13)
+#define   UNIPHIER_MDMAC_CH_IRQ__DONE		BIT(1)
+#define UNIPHIER_MDMAC_CH_SRC_MODE	0x020	/* mode of source */
+#define UNIPHIER_MDMAC_CH_DEST_MODE	0x024	/* mode of destination */
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_INC	(0 << 4)
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_DEC	(1 << 4)
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED	(2 << 4)
+#define UNIPHIER_MDMAC_CH_SRC_ADDR	0x028	/* source address */
+#define UNIPHIER_MDMAC_CH_DEST_ADDR	0x02c	/* destination address */
+#define UNIPHIER_MDMAC_CH_SIZE		0x030	/* transfer bytes */
+
+#define UNIPHIER_MDMAC_SLAVE_BUSWIDTHS \
+	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
+
+struct uniphier_mdmac_desc {
+	struct virt_dma_desc vd;
+	struct scatterlist *sgl;
+	unsigned int sg_len;
+	unsigned int sg_cur;
+	enum dma_transfer_direction dir;
+};
+
+struct uniphier_mdmac_chan {
+	struct virt_dma_chan vc;
+	struct uniphier_mdmac_device *mdev;
+	struct uniphier_mdmac_desc *md;
+	void __iomem *reg_ch_base;
+	unsigned int chan_id;
+};
+
+struct uniphier_mdmac_device {
+	struct dma_device ddev;
+	struct clk *clk;
+	void __iomem *reg_base;
+	struct uniphier_mdmac_chan channels[0];
+};
+
+static struct uniphier_mdmac_chan *
+to_uniphier_mdmac_chan(struct virt_dma_chan *vc)
+{
+	return container_of(vc, struct uniphier_mdmac_chan, vc);
+}
+
+static struct uniphier_mdmac_desc *
+to_uniphier_mdmac_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct uniphier_mdmac_desc, vd);
+}
+
+/* mc->vc.lock must be held by caller */
+static struct uniphier_mdmac_desc *
+uniphier_mdmac_next_desc(struct uniphier_mdmac_chan *mc)
+{
+	struct virt_dma_desc *vd;
+
+	vd = vchan_next_desc(&mc->vc);
+	if (!vd) {
+		mc->md = NULL;
+		return NULL;
+	}
+
+	list_del(&vd->node);
+
+	mc->md = to_uniphier_mdmac_desc(vd);
+
+	return mc->md;
+}
+
+/* mc->vc.lock must be held by caller */
+static void uniphier_mdmac_handle(struct uniphier_mdmac_chan *mc,
+				  struct uniphier_mdmac_desc *md)
+{
+	struct uniphier_mdmac_device *mdev = mc->mdev;
+	struct scatterlist *sg;
+	u32 irq_flag = UNIPHIER_MDMAC_CH_IRQ__DONE;
+	u32 src_mode, src_addr, dest_mode, dest_addr, chunk_size;
+
+	sg = &md->sgl[md->sg_cur];
+
+	if (md->dir == DMA_MEM_TO_DEV) {
+		src_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_INC;
+		src_addr = sg_dma_address(sg);
+		dest_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED;
+		dest_addr = 0;
+	} else {
+		src_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED;
+		src_addr = 0;
+		dest_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_INC;
+		dest_addr = sg_dma_address(sg);
+	}
+
+	chunk_size = sg_dma_len(sg);
+
+	writel(src_mode, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SRC_MODE);
+	writel(dest_mode, mc->reg_ch_base + UNIPHIER_MDMAC_CH_DEST_MODE);
+	writel(src_addr, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SRC_ADDR);
+	writel(dest_addr, mc->reg_ch_base + UNIPHIER_MDMAC_CH_DEST_ADDR);
+	writel(chunk_size, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SIZE);
+
+	/* write 1 to clear */
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_EN);
+
+	writel(BIT(mc->chan_id), mdev->reg_base + UNIPHIER_MDMAC_CMD);
+}
+
+/* mc->vc.lock must be held by caller */
+static void uniphier_mdmac_start(struct uniphier_mdmac_chan *mc)
+{
+	struct uniphier_mdmac_desc *md;
+
+	md = uniphier_mdmac_next_desc(mc);
+	if (md)
+		uniphier_mdmac_handle(mc, md);
+}
+
+/* mc->vc.lock must be held by caller */
+static int uniphier_mdmac_abort(struct uniphier_mdmac_chan *mc)
+{
+	struct uniphier_mdmac_device *mdev = mc->mdev;
+	u32 irq_flag = UNIPHIER_MDMAC_CH_IRQ__ABORT;
+	u32 val;
+
+	/* write 1 to clear */
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	writel(UNIPHIER_MDMAC_CMD_ABORT | BIT(mc->chan_id),
+	       mdev->reg_base + UNIPHIER_MDMAC_CMD);
+
+	/*
+	 * Abort should be accepted soon. We poll the bit here instead of
+	 * waiting for the interrupt.
+	 */
+	return readl_poll_timeout(mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ,
+				  val, val & irq_flag, 0, 20);
+}
+
+static irqreturn_t uniphier_mdmac_interrupt(int irq, void *dev_id)
+{
+	struct uniphier_mdmac_chan *mc = dev_id;
+	struct uniphier_mdmac_desc *md;
+	irqreturn_t ret = IRQ_HANDLED;
+	u32 irq_stat;
+
+	spin_lock(&mc->vc.lock);
+
+	irq_stat = readl(mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_DET);
+
+	/*
+	 * Some channels share a single interrupt line. If the IRQ status is 0,
+	 * this is probably triggered by a different channel.
+	 */
+	if (!irq_stat) {
+		ret = IRQ_NONE;
+		goto out;
+	}
+
+	/* write 1 to clear */
+	writel(irq_stat, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	/*
+	 * UNIPHIER_MDMAC_CH_IRQ__DONE interrupt is asserted even when the DMA
+	 * is aborted. To distinguish the normal completion and the abort,
+	 * check mc->md. If it is NULL, we are aborting.
+	 */
+	md = mc->md;
+	if (!md)
+		goto out;
+
+	md->sg_cur++;
+
+	if (md->sg_cur >= md->sg_len) {
+		vchan_cookie_complete(&md->vd);
+		md = uniphier_mdmac_next_desc(mc);
+		if (!md)
+			goto out;
+	}
+
+	uniphier_mdmac_handle(mc, md);
+
+out:
+	spin_unlock(&mc->vc.lock);
+
+	return ret;
+}
+
+static void uniphier_mdmac_free_chan_resources(struct dma_chan *chan)
+{
+	vchan_free_chan_resources(to_virt_chan(chan));
+}
+
+static struct dma_async_tx_descriptor *
+uniphier_mdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+			     unsigned int sg_len,
+			     enum dma_transfer_direction direction,
+			     unsigned long flags, void *context)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_desc *md;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	md = kzalloc(sizeof(*md), GFP_NOWAIT);
+	if (!md)
+		return NULL;
+
+	md->sgl = sgl;
+	md->sg_len = sg_len;
+	md->dir = direction;
+
+	return vchan_tx_prep(vc, &md->vd, flags);
+}
+
+static int uniphier_mdmac_terminate_all(struct dma_chan *chan)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_chan *mc = to_uniphier_mdmac_chan(vc);
+	unsigned long flags;
+	int ret = 0;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	if (mc->md) {
+		vchan_terminate_vdesc(&mc->md->vd);
+		mc->md = NULL;
+		ret = uniphier_mdmac_abort(mc);
+	}
+	vchan_get_all_descriptors(vc, &head);
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	vchan_dma_desc_free_list(vc, &head);
+
+	return ret;
+}
+
+static void uniphier_mdmac_synchronize(struct dma_chan *chan)
+{
+	vchan_synchronize(to_virt_chan(chan));
+}
+
+static enum dma_status uniphier_mdmac_tx_status(struct dma_chan *chan,
+						dma_cookie_t cookie,
+						struct dma_tx_state *txstate)
+{
+	struct virt_dma_chan *vc;
+	struct virt_dma_desc *vd;
+	struct uniphier_mdmac_chan *mc;
+	struct uniphier_mdmac_desc *md = NULL;
+	enum dma_status stat;
+	unsigned long flags;
+	int i;
+
+	stat = dma_cookie_status(chan, cookie, txstate);
+	/* Return immediately if we do not need to compute the residue. */
+	if (stat == DMA_COMPLETE || !txstate)
+		return stat;
+
+	vc = to_virt_chan(chan);
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	mc = to_uniphier_mdmac_chan(vc);
+
+	if (mc->md && mc->md->vd.tx.cookie == cookie) {
+		/* residue from the on-flight chunk */
+		txstate->residue = readl(mc->reg_ch_base +
+					 UNIPHIER_MDMAC_CH_SIZE);
+		md = mc->md;
+	}
+
+	if (!md) {
+		vd = vchan_find_desc(vc, cookie);
+		if (vd)
+			md = to_uniphier_mdmac_desc(vd);
+	}
+
+	if (md) {
+		/* residue from the queued chunks */
+		for (i = md->sg_cur; i < md->sg_len; i++)
+			txstate->residue += sg_dma_len(&md->sgl[i]);
+	}
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	return stat;
+}
+
+static void uniphier_mdmac_issue_pending(struct dma_chan *chan)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_chan *mc = to_uniphier_mdmac_chan(vc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	if (vchan_issue_pending(vc) && !mc->md)
+		uniphier_mdmac_start(mc);
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+}
+
+static void uniphier_mdmac_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_uniphier_mdmac_desc(vd));
+}
+
+static int uniphier_mdmac_chan_init(struct platform_device *pdev,
+				    struct uniphier_mdmac_device *mdev,
+				    int chan_id)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_mdmac_chan *mc = &mdev->channels[chan_id];
+	char *irq_name;
+	int irq, ret;
+
+	irq = platform_get_irq(pdev, chan_id);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ number for ch%d\n",
+			chan_id);
+		return irq;
+	}
+
+	irq_name = devm_kasprintf(dev, GFP_KERNEL, "uniphier-mio-dmac-ch%d",
+				  chan_id);
+	if (!irq_name)
+		return -ENOMEM;
+
+	ret = devm_request_irq(dev, irq, uniphier_mdmac_interrupt,
+			       IRQF_SHARED, irq_name, mc);
+	if (ret)
+		return ret;
+
+	mc->mdev = mdev;
+	mc->reg_ch_base = mdev->reg_base + UNIPHIER_MDMAC_CH_OFFSET +
+					UNIPHIER_MDMAC_CH_STRIDE * chan_id;
+	mc->chan_id = chan_id;
+	mc->vc.desc_free = uniphier_mdmac_desc_free;
+	vchan_init(&mc->vc, &mdev->ddev);
+
+	return 0;
+}
+
+static int uniphier_mdmac_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_mdmac_device *mdev;
+	struct dma_device *ddev;
+	struct resource *res;
+	int nr_chans, ret, i;
+
+	nr_chans = platform_irq_count(pdev);
+	if (nr_chans < 0)
+		return nr_chans;
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	mdev = devm_kzalloc(dev, struct_size(mdev, channels, nr_chans),
+			    GFP_KERNEL);
+	if (!mdev)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mdev->reg_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(mdev->reg_base))
+		return PTR_ERR(mdev->reg_base);
+
+	mdev->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(mdev->clk)) {
+		dev_err(dev, "failed to get clock\n");
+		return PTR_ERR(mdev->clk);
+	}
+
+	ret = clk_prepare_enable(mdev->clk);
+	if (ret)
+		return ret;
+
+	ddev = &mdev->ddev;
+	ddev->dev = dev;
+	dma_cap_set(DMA_PRIVATE, ddev->cap_mask);
+	ddev->src_addr_widths = UNIPHIER_MDMAC_SLAVE_BUSWIDTHS;
+	ddev->dst_addr_widths = UNIPHIER_MDMAC_SLAVE_BUSWIDTHS;
+	ddev->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
+	ddev->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	ddev->device_free_chan_resources = uniphier_mdmac_free_chan_resources;
+	ddev->device_prep_slave_sg = uniphier_mdmac_prep_slave_sg;
+	ddev->device_terminate_all = uniphier_mdmac_terminate_all;
+	ddev->device_synchronize = uniphier_mdmac_synchronize;
+	ddev->device_tx_status = uniphier_mdmac_tx_status;
+	ddev->device_issue_pending = uniphier_mdmac_issue_pending;
+	INIT_LIST_HEAD(&ddev->channels);
+
+	for (i = 0; i < nr_chans; i++) {
+		ret = uniphier_mdmac_chan_init(pdev, mdev, i);
+		if (ret)
+			goto disable_clk;
+	}
+
+	ret = dma_async_device_register(ddev);
+	if (ret)
+		goto disable_clk;
+
+	ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id,
+					 ddev);
+	if (ret)
+		goto unregister_dmac;
+
+	platform_set_drvdata(pdev, mdev);
+
+	return 0;
+
+unregister_dmac:
+	dma_async_device_unregister(ddev);
+disable_clk:
+	clk_disable_unprepare(mdev->clk);
+
+	return ret;
+}
+
+static int uniphier_mdmac_remove(struct platform_device *pdev)
+{
+	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
+	struct dma_chan *chan;
+	int ret;
+
+	/*
+	 * Before reaching here, almost all descriptors have been freed by the
+	 * ->device_free_chan_resources() hook. However, each channel might
+	 * be still holding one descriptor that was on-flight at that moment.
+	 * Terminate it to make sure this hardware is no longer running. Then,
+	 * free the channel resources once again to avoid memory leak.
+	 */
+	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
+		ret = dmaengine_terminate_sync(chan);
+		if (ret)
+			return ret;
+		uniphier_mdmac_free_chan_resources(chan);
+	}
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&mdev->ddev);
+	clk_disable_unprepare(mdev->clk);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_mdmac_match[] = {
+	{ .compatible = "socionext,uniphier-mio-dmac" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
+
+static struct platform_driver uniphier_mdmac_driver = {
+	.probe = uniphier_mdmac_probe,
+	.remove = uniphier_mdmac_remove,
+	.driver = {
+		.name = "uniphier-mio-dmac",
+		.of_match_table = uniphier_mdmac_match,
+	},
+};
+module_platform_driver(uniphier_mdmac_driver);
+
+MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
+MODULE_DESCRIPTION("UniPhier MIO DMAC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 1d5988849aa6..eafd6c4b90fe 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -1208,8 +1208,8 @@ static int xgene_dma_create_ring_one(struct xgene_dma_chan *chan,
 	ring->size = ret;
 
 	/* Allocate memory for DMA ring descriptor */
-	ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size,
-					       &ring->desc_paddr, GFP_KERNEL);
+	ring->desc_vaddr = dma_alloc_coherent(chan->dev, ring->size,
+					      &ring->desc_paddr, GFP_KERNEL);
 	if (!ring->desc_vaddr) {
 		chan_err(chan, "Failed to allocate ring desc\n");
 		return -ENOMEM;
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index c12442312595..c43c1a154604 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -86,6 +86,7 @@
 #define XILINX_DMA_DMASR_DMA_DEC_ERR		BIT(6)
 #define XILINX_DMA_DMASR_DMA_SLAVE_ERR		BIT(5)
 #define XILINX_DMA_DMASR_DMA_INT_ERR		BIT(4)
+#define XILINX_DMA_DMASR_SG_MASK		BIT(3)
 #define XILINX_DMA_DMASR_IDLE			BIT(1)
 #define XILINX_DMA_DMASR_HALTED		BIT(0)
 #define XILINX_DMA_DMASR_DELAY_MASK		GENMASK(31, 24)
@@ -161,7 +162,9 @@
 #define XILINX_DMA_REG_BTT		0x28
 
 /* AXI DMA Specific Masks/Bit fields */
-#define XILINX_DMA_MAX_TRANS_LEN	GENMASK(22, 0)
+#define XILINX_DMA_MAX_TRANS_LEN_MIN	8
+#define XILINX_DMA_MAX_TRANS_LEN_MAX	23
+#define XILINX_DMA_V2_MAX_TRANS_LEN_MAX	26
 #define XILINX_DMA_CR_COALESCE_MAX	GENMASK(23, 16)
 #define XILINX_DMA_CR_CYCLIC_BD_EN_MASK	BIT(4)
 #define XILINX_DMA_CR_COALESCE_SHIFT	16
@@ -190,6 +193,8 @@
 /* AXI CDMA Specific Masks */
 #define XILINX_CDMA_CR_SGMODE          BIT(3)
 
+#define xilinx_prep_dma_addr_t(addr)	\
+	((dma_addr_t)((u64)addr##_##msb << 32 | (addr)))
 /**
  * struct xilinx_vdma_desc_hw - Hardware Descriptor
  * @next_desc: Next Descriptor Pointer @0x00
@@ -410,7 +415,6 @@ struct xilinx_dma_config {
  * @dev: Device Structure
  * @common: DMA device structure
  * @chan: Driver specific DMA channel
- * @has_sg: Specifies whether Scatter-Gather is present or not
  * @mcdma: Specifies whether Multi-Channel is present or not
  * @flush_on_fsync: Flush on frame sync
  * @ext_addr: Indicates 64 bit addressing is supported by dma device
@@ -423,13 +427,13 @@ struct xilinx_dma_config {
  * @rxs_clk: DMA s2mm stream clock
  * @nr_channels: Number of channels DMA device supports
  * @chan_id: DMA channel identifier
+ * @max_buffer_len: Max buffer length
  */
 struct xilinx_dma_device {
 	void __iomem *regs;
 	struct device *dev;
 	struct dma_device common;
 	struct xilinx_dma_chan *chan[XILINX_DMA_MAX_CHANS_PER_DEVICE];
-	bool has_sg;
 	bool mcdma;
 	u32 flush_on_fsync;
 	bool ext_addr;
@@ -442,6 +446,7 @@ struct xilinx_dma_device {
 	struct clk *rxs_clk;
 	u32 nr_channels;
 	u32 chan_id;
+	u32 max_buffer_len;
 };
 
 /* Macros */
@@ -877,16 +882,34 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 	 */
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		/* Allocate the buffer descriptors. */
-		chan->seg_v = dma_zalloc_coherent(chan->dev,
-						  sizeof(*chan->seg_v) *
-						  XILINX_DMA_NUM_DESCS,
-						  &chan->seg_p, GFP_KERNEL);
+		chan->seg_v = dma_alloc_coherent(chan->dev,
+						 sizeof(*chan->seg_v) * XILINX_DMA_NUM_DESCS,
+						 &chan->seg_p, GFP_KERNEL);
 		if (!chan->seg_v) {
 			dev_err(chan->dev,
 				"unable to allocate channel %d descriptors\n",
 				chan->id);
 			return -ENOMEM;
 		}
+		/*
+		 * For cyclic DMA mode we need to program the tail Descriptor
+		 * register with a value which is not a part of the BD chain
+		 * so allocating a desc segment during channel allocation for
+		 * programming tail descriptor.
+		 */
+		chan->cyclic_seg_v = dma_alloc_coherent(chan->dev,
+							sizeof(*chan->cyclic_seg_v),
+							&chan->cyclic_seg_p,
+							GFP_KERNEL);
+		if (!chan->cyclic_seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate desc segment for cyclic DMA\n");
+			dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				XILINX_DMA_NUM_DESCS, chan->seg_v,
+				chan->seg_p);
+			return -ENOMEM;
+		}
+		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
 
 		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
 			chan->seg_v[i].hw.next_desc =
@@ -922,24 +945,6 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 		return -ENOMEM;
 	}
 
-	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		/*
-		 * For cyclic DMA mode we need to program the tail Descriptor
-		 * register with a value which is not a part of the BD chain
-		 * so allocating a desc segment during channel allocation for
-		 * programming tail descriptor.
-		 */
-		chan->cyclic_seg_v = dma_zalloc_coherent(chan->dev,
-					sizeof(*chan->cyclic_seg_v),
-					&chan->cyclic_seg_p, GFP_KERNEL);
-		if (!chan->cyclic_seg_v) {
-			dev_err(chan->dev,
-				"unable to allocate desc segment for cyclic DMA\n");
-			return -ENOMEM;
-		}
-		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
-	}
-
 	dma_cookie_init(dchan);
 
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
@@ -958,6 +963,34 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 }
 
 /**
+ * xilinx_dma_calc_copysize - Calculate the amount of data to copy
+ * @chan: Driver specific DMA channel
+ * @size: Total data that needs to be copied
+ * @done: Amount of data that has been already copied
+ *
+ * Return: Amount of data that has to be copied
+ */
+static int xilinx_dma_calc_copysize(struct xilinx_dma_chan *chan,
+				    int size, int done)
+{
+	size_t copy;
+
+	copy = min_t(size_t, size - done,
+		     chan->xdev->max_buffer_len);
+
+	if ((copy + done < size) &&
+	    chan->xdev->common.copy_align) {
+		/*
+		 * If this is not the last descriptor, make sure
+		 * the next one will be properly aligned
+		 */
+		copy = rounddown(copy,
+				 (1 << chan->xdev->common.copy_align));
+	}
+	return copy;
+}
+
+/**
  * xilinx_dma_tx_status - Get DMA transaction status
  * @dchan: DMA channel
  * @cookie: Transaction identifier
@@ -990,7 +1023,7 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan,
 			list_for_each_entry(segment, &desc->segments, node) {
 				hw = &segment->hw;
 				residue += (hw->control - hw->status) &
-					   XILINX_DMA_MAX_TRANS_LEN;
+					   chan->xdev->max_buffer_len;
 			}
 		}
 		spin_unlock_irqrestore(&chan->lock, flags);
@@ -1068,7 +1101,8 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	struct xilinx_vdma_config *config = &chan->config;
 	struct xilinx_dma_tx_descriptor *desc, *tail_desc;
 	u32 reg, j;
-	struct xilinx_vdma_tx_segment *tail_segment;
+	struct xilinx_vdma_tx_segment *segment, *last = NULL;
+	int i = 0;
 
 	/* This function was invoked with lock held */
 	if (chan->err)
@@ -1085,17 +1119,6 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	tail_desc = list_last_entry(&chan->pending_list,
 				    struct xilinx_dma_tx_descriptor, node);
 
-	tail_segment = list_last_entry(&tail_desc->segments,
-				       struct xilinx_vdma_tx_segment, node);
-
-	/*
-	 * If hardware is idle, then all descriptors on the running lists are
-	 * done, start new transfers
-	 */
-	if (chan->has_sg)
-		dma_ctrl_write(chan, XILINX_DMA_REG_CURDESC,
-				desc->async_tx.phys);
-
 	/* Configure the hardware using info in the config structure */
 	if (chan->has_vflip) {
 		reg = dma_read(chan, XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP);
@@ -1112,15 +1135,11 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	else
 		reg &= ~XILINX_DMA_DMACR_FRAMECNT_EN;
 
-	/*
-	 * With SG, start with circular mode, so that BDs can be fetched.
-	 * In direct register mode, if not parking, enable circular mode
-	 */
-	if (chan->has_sg || !config->park)
-		reg |= XILINX_DMA_DMACR_CIRC_EN;
-
+	/* If not parking, enable circular mode */
 	if (config->park)
 		reg &= ~XILINX_DMA_DMACR_CIRC_EN;
+	else
+		reg |= XILINX_DMA_DMACR_CIRC_EN;
 
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
@@ -1142,48 +1161,38 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 		return;
 
 	/* Start the transfer */
-	if (chan->has_sg) {
-		dma_ctrl_write(chan, XILINX_DMA_REG_TAILDESC,
-				tail_segment->phys);
-		list_splice_tail_init(&chan->pending_list, &chan->active_list);
-		chan->desc_pendingcount = 0;
-	} else {
-		struct xilinx_vdma_tx_segment *segment, *last = NULL;
-		int i = 0;
-
-		if (chan->desc_submitcount < chan->num_frms)
-			i = chan->desc_submitcount;
-
-		list_for_each_entry(segment, &desc->segments, node) {
-			if (chan->ext_addr)
-				vdma_desc_write_64(chan,
-					XILINX_VDMA_REG_START_ADDRESS_64(i++),
-					segment->hw.buf_addr,
-					segment->hw.buf_addr_msb);
-			else
-				vdma_desc_write(chan,
+	if (chan->desc_submitcount < chan->num_frms)
+		i = chan->desc_submitcount;
+
+	list_for_each_entry(segment, &desc->segments, node) {
+		if (chan->ext_addr)
+			vdma_desc_write_64(chan,
+				   XILINX_VDMA_REG_START_ADDRESS_64(i++),
+				   segment->hw.buf_addr,
+				   segment->hw.buf_addr_msb);
+		else
+			vdma_desc_write(chan,
 					XILINX_VDMA_REG_START_ADDRESS(i++),
 					segment->hw.buf_addr);
 
-			last = segment;
-		}
+		last = segment;
+	}
 
-		if (!last)
-			return;
+	if (!last)
+		return;
 
-		/* HW expects these parameters to be same for one transaction */
-		vdma_desc_write(chan, XILINX_DMA_REG_HSIZE, last->hw.hsize);
-		vdma_desc_write(chan, XILINX_DMA_REG_FRMDLY_STRIDE,
-				last->hw.stride);
-		vdma_desc_write(chan, XILINX_DMA_REG_VSIZE, last->hw.vsize);
+	/* HW expects these parameters to be same for one transaction */
+	vdma_desc_write(chan, XILINX_DMA_REG_HSIZE, last->hw.hsize);
+	vdma_desc_write(chan, XILINX_DMA_REG_FRMDLY_STRIDE,
+			last->hw.stride);
+	vdma_desc_write(chan, XILINX_DMA_REG_VSIZE, last->hw.vsize);
 
-		chan->desc_submitcount++;
-		chan->desc_pendingcount--;
-		list_del(&desc->node);
-		list_add_tail(&desc->node, &chan->active_list);
-		if (chan->desc_submitcount == chan->num_frms)
-			chan->desc_submitcount = 0;
-	}
+	chan->desc_submitcount++;
+	chan->desc_pendingcount--;
+	list_del(&desc->node);
+	list_add_tail(&desc->node, &chan->active_list);
+	if (chan->desc_submitcount == chan->num_frms)
+		chan->desc_submitcount = 0;
 
 	chan->idle = false;
 }
@@ -1245,12 +1254,14 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 
 		hw = &segment->hw;
 
-		xilinx_write(chan, XILINX_CDMA_REG_SRCADDR, hw->src_addr);
-		xilinx_write(chan, XILINX_CDMA_REG_DSTADDR, hw->dest_addr);
+		xilinx_write(chan, XILINX_CDMA_REG_SRCADDR,
+			     xilinx_prep_dma_addr_t(hw->src_addr));
+		xilinx_write(chan, XILINX_CDMA_REG_DSTADDR,
+			     xilinx_prep_dma_addr_t(hw->dest_addr));
 
 		/* Start the transfer */
 		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
-				hw->control & XILINX_DMA_MAX_TRANS_LEN);
+				hw->control & chan->xdev->max_buffer_len);
 	}
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
@@ -1353,7 +1364,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 
 		/* Start the transfer */
 		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
-			       hw->control & XILINX_DMA_MAX_TRANS_LEN);
+			       hw->control & chan->xdev->max_buffer_len);
 	}
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
@@ -1714,7 +1725,7 @@ xilinx_cdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst,
 	struct xilinx_cdma_tx_segment *segment;
 	struct xilinx_cdma_desc_hw *hw;
 
-	if (!len || len > XILINX_DMA_MAX_TRANS_LEN)
+	if (!len || len > chan->xdev->max_buffer_len)
 		return NULL;
 
 	desc = xilinx_dma_alloc_tx_descriptor(chan);
@@ -1804,8 +1815,8 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 			 * Calculate the maximum number of bytes to transfer,
 			 * making sure it is less than the hw limit
 			 */
-			copy = min_t(size_t, sg_dma_len(sg) - sg_used,
-				     XILINX_DMA_MAX_TRANS_LEN);
+			copy = xilinx_dma_calc_copysize(chan, sg_dma_len(sg),
+							sg_used);
 			hw = &segment->hw;
 
 			/* Fill in the descriptor */
@@ -1909,8 +1920,8 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_dma_cyclic(
 			 * Calculate the maximum number of bytes to transfer,
 			 * making sure it is less than the hw limit
 			 */
-			copy = min_t(size_t, period_len - sg_used,
-				     XILINX_DMA_MAX_TRANS_LEN);
+			copy = xilinx_dma_calc_copysize(chan, period_len,
+							sg_used);
 			hw = &segment->hw;
 			xilinx_axidma_buf(chan, hw, buf_addr, sg_used,
 					  period_len * i);
@@ -2385,7 +2396,6 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 
 	chan->dev = xdev->dev;
 	chan->xdev = xdev;
-	chan->has_sg = xdev->has_sg;
 	chan->desc_pendingcount = 0x0;
 	chan->ext_addr = xdev->ext_addr;
 	/* This variable ensures that descriptors are not
@@ -2485,6 +2495,15 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->stop_transfer = xilinx_dma_stop_transfer;
 	}
 
+	/* check if SG is enabled (only for AXIDMA and CDMA) */
+	if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) {
+		if (dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
+		    XILINX_DMA_DMASR_SG_MASK)
+			chan->has_sg = true;
+		dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id,
+			chan->has_sg ? "enabled" : "disabled");
+	}
+
 	/* Initialize the tasklet */
 	tasklet_init(&chan->tasklet, xilinx_dma_do_tasklet,
 			(unsigned long)chan);
@@ -2592,7 +2611,7 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 	struct xilinx_dma_device *xdev;
 	struct device_node *child, *np = pdev->dev.of_node;
 	struct resource *io;
-	u32 num_frames, addr_width;
+	u32 num_frames, addr_width, len_width;
 	int i, err;
 
 	/* Allocate and initialize the DMA engine structure */
@@ -2623,9 +2642,24 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(xdev->regs);
 
 	/* Retrieve the DMA engine properties from the device tree */
-	xdev->has_sg = of_property_read_bool(node, "xlnx,include-sg");
-	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA)
+	xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0);
+
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		xdev->mcdma = of_property_read_bool(node, "xlnx,mcdma");
+		if (!of_property_read_u32(node, "xlnx,sg-length-width",
+					  &len_width)) {
+			if (len_width < XILINX_DMA_MAX_TRANS_LEN_MIN ||
+			    len_width > XILINX_DMA_V2_MAX_TRANS_LEN_MAX) {
+				dev_warn(xdev->dev,
+					 "invalid xlnx,sg-length-width property value. Using default width\n");
+			} else {
+				if (len_width > XILINX_DMA_MAX_TRANS_LEN_MAX)
+					dev_warn(xdev->dev, "Please ensure that IP supports buffer length > 23 bits\n");
+				xdev->max_buffer_len =
+					GENMASK(len_width - 1, 0);
+			}
+		}
+	}
 
 	if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
 		err = of_property_read_u32(node, "xlnx,num-fstores",
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index c74a88b65039..4478787a247f 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -163,7 +163,7 @@ struct zynqmp_dma_desc_ll {
 	u32 ctrl;
 	u64 nxtdscraddr;
 	u64 rsvd;
-}; __aligned(64)
+};
 
 /**
  * struct zynqmp_dma_desc_sw - Per Transaction structure
@@ -375,9 +375,10 @@ static dma_cookie_t zynqmp_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct zynqmp_dma_chan *chan = to_chan(tx->chan);
 	struct zynqmp_dma_desc_sw *desc, *new;
 	dma_cookie_t cookie;
+	unsigned long irqflags;
 
 	new = tx_to_desc(tx);
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	cookie = dma_cookie_assign(tx);
 
 	if (!list_empty(&chan->pending_list)) {
@@ -393,7 +394,7 @@ static dma_cookie_t zynqmp_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	}
 
 	list_add_tail(&new->node, &chan->pending_list);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	return cookie;
 }
@@ -408,12 +409,13 @@ static struct zynqmp_dma_desc_sw *
 zynqmp_dma_get_descriptor(struct zynqmp_dma_chan *chan)
 {
 	struct zynqmp_dma_desc_sw *desc;
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	desc = list_first_entry(&chan->free_list,
 				struct zynqmp_dma_desc_sw, node);
 	list_del(&desc->node);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	INIT_LIST_HEAD(&desc->tx_list);
 	/* Clear the src and dst descriptor memory */
@@ -488,9 +490,9 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 		list_add_tail(&desc->node, &chan->free_list);
 	}
 
-	chan->desc_pool_v = dma_zalloc_coherent(chan->dev,
-				(2 * chan->desc_size * ZYNQMP_DMA_NUM_DESCS),
-				&chan->desc_pool_p, GFP_KERNEL);
+	chan->desc_pool_v = dma_alloc_coherent(chan->dev,
+					       (2 * chan->desc_size * ZYNQMP_DMA_NUM_DESCS),
+					       &chan->desc_pool_p, GFP_KERNEL);
 	if (!chan->desc_pool_v)
 		return -ENOMEM;
 
@@ -643,10 +645,11 @@ static void zynqmp_dma_complete_descriptor(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_start_transfer(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -667,10 +670,11 @@ static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 	dma_free_coherent(chan->dev,
 		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
 		chan->desc_pool_v, chan->desc_pool_p);
@@ -743,8 +747,9 @@ static void zynqmp_dma_do_tasklet(unsigned long data)
 {
 	struct zynqmp_dma_chan *chan = (struct zynqmp_dma_chan *)data;
 	u32 count;
+	unsigned long irqflags;
 
-	spin_lock(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 
 	if (chan->err) {
 		zynqmp_dma_reset(chan);
@@ -764,7 +769,7 @@ static void zynqmp_dma_do_tasklet(unsigned long data)
 		zynqmp_dma_start_transfer(chan);
 
 unlock:
-	spin_unlock(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -776,11 +781,12 @@ unlock:
 static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	return 0;
 }
@@ -804,19 +810,20 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy(
 	void *desc = NULL, *prev = NULL;
 	size_t copy;
 	u32 desc_cnt;
+	unsigned long irqflags;
 
 	chan = to_chan(dchan);
 
 	desc_cnt = DIV_ROUND_UP(len, ZYNQMP_DMA_MAX_TRANS_LEN);
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	if (desc_cnt > chan->desc_free_cnt) {
-		spin_unlock_bh(&chan->lock);
+		spin_unlock_irqrestore(&chan->lock, irqflags);
 		dev_dbg(chan->dev, "chan %p descs are not available\n", chan);
 		return NULL;
 	}
 	chan->desc_free_cnt = chan->desc_free_cnt - desc_cnt;
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	do {
 		/* Allocate and populate the descriptor */