diff --git a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
index b3408cc57be6..1ae4748730a8 100644
--- a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
+++ b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
@@ -47,8 +47,8 @@ When the OS is not in control of the management interface (i.e. it's a guest),
 the channel nodes appear on their own, not under a management node.
 
 Required properties:
-- compatible: must contain "qcom,hidma-1.0" for initial HW or "qcom,hidma-1.1"
-for MSI capable HW.
+- compatible: must contain "qcom,hidma-1.0" for initial HW or
+  "qcom,hidma-1.1"/"qcom,hidma-1.2" for MSI capable HW.
 - reg: Addresses for the transfer and event channel
 - interrupts: Should contain the event interrupt
 - desc-count: Number of asynchronous requests this channel can handle
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 814acb4d2294..dfc4486b5743 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -111,40 +111,36 @@ The first thing you need to do in your driver is to allocate this
 structure. Any of the usual memory allocators will do, but you'll also
 need to initialize a few fields in there:
 
-- channels: should be initialized as a list using the
+- ``channels``: should be initialized as a list using the
   INIT_LIST_HEAD macro for example
 
-- src_addr_widths:
+- ``src_addr_widths``:
   should contain a bitmask of the supported source transfer width
 
-- dst_addr_widths:
+- ``dst_addr_widths``:
   should contain a bitmask of the supported destination transfer width
 
-- directions:
+- ``directions``:
   should contain a bitmask of the supported slave directions
   (i.e. excluding mem2mem transfers)
 
-- residue_granularity:
+- ``residue_granularity``:
+  granularity of the transfer residue reported to dma_set_residue.
+  This can be either:
 
-  - Granularity of the transfer residue reported to dma_set_residue.
-    This can be either:
+  - Descriptor:
+    your device doesn't support any kind of residue
+    reporting. The framework will only know that a particular
+    transaction descriptor is done.
 
-  - Descriptor
+  - Segment:
+    your device is able to report which chunks have been transferred
 
-    - Your device doesn't support any kind of residue
-      reporting. The framework will only know that a particular
-      transaction descriptor is done.
+  - Burst:
+    your device is able to report which burst have been transferred
 
-      - Segment
-
-        - Your device is able to report which chunks have been transferred
-
-      - Burst
-
-        - Your device is able to report which burst have been transferred
-
-  - dev: should hold the pointer to the ``struct device`` associated
-    to your current driver instance.
+- ``dev``: should hold the pointer to the ``struct device`` associated
+  to your current driver instance.
 
 Supported transaction types
 ---------------------------
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 4d0979e02a28..f87ed3be779a 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -785,6 +785,24 @@ const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 }
 EXPORT_SYMBOL_GPL(acpi_match_device);
 
+void *acpi_get_match_data(const struct device *dev)
+{
+	const struct acpi_device_id *match;
+
+	if (!dev->driver)
+		return NULL;
+
+	if (!dev->driver->acpi_match_table)
+		return NULL;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match)
+		return NULL;
+
+	return (void *)match->driver_data;
+}
+EXPORT_SYMBOL_GPL(acpi_get_match_data);
+
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids)
 {
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index e26ea209b63e..466d1503aba0 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1271,9 +1271,17 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static void *
+acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
+				  const struct device *dev)
+{
+	return acpi_get_match_data(dev);
+}
+
 #define DECLARE_ACPI_FWNODE_OPS(ops) \
 	const struct fwnode_operations ops = {				\
 		.device_is_available = acpi_fwnode_device_is_available, \
+		.device_get_match_data = acpi_fwnode_device_get_match_data, \
 		.property_present = acpi_fwnode_property_present,	\
 		.property_read_int_array =				\
 			acpi_fwnode_property_read_int_array,		\
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 851b1b6596a4..09eaac9400ed 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1340,3 +1340,10 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return fwnode_call_int_op(fwnode, graph_parse_endpoint, endpoint);
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
+
+void *device_get_match_data(struct device *dev)
+{
+	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data,
+				  dev);
+}
+EXPORT_SYMBOL_GPL(device_get_match_data);
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index b52b0d55247e..97483df1f82e 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -2182,7 +2182,7 @@ static int pl08x_terminate_all(struct dma_chan *chan)
 	}
 	/* Dequeue jobs and free LLIs */
 	if (plchan->at) {
-		pl08x_desc_free(&plchan->at->vd);
+		vchan_terminate_vdesc(&plchan->at->vd);
 		plchan->at = NULL;
 	}
 	/* Dequeue jobs not yet fired as well */
@@ -2193,6 +2193,13 @@ static int pl08x_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void pl08x_synchronize(struct dma_chan *chan)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+
+	vchan_synchronize(&plchan->vc);
+}
+
 static int pl08x_pause(struct dma_chan *chan)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
@@ -2773,6 +2780,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->memcpy.device_pause = pl08x_pause;
 	pl08x->memcpy.device_resume = pl08x_resume;
 	pl08x->memcpy.device_terminate_all = pl08x_terminate_all;
+	pl08x->memcpy.device_synchronize = pl08x_synchronize;
 	pl08x->memcpy.src_addr_widths = PL80X_DMA_BUSWIDTHS;
 	pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
 	pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM);
@@ -2802,6 +2810,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		pl08x->slave.device_pause = pl08x_pause;
 		pl08x->slave.device_resume = pl08x_resume;
 		pl08x->slave.device_terminate_all = pl08x_terminate_all;
+		pl08x->slave.device_synchronize = pl08x_synchronize;
 		pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS;
 		pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
 		pl08x->slave.directions =
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 6204cc32d09c..847f84a41a69 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -812,7 +812,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
-		bcm2835_dma_desc_free(&c->desc->vd);
+		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
 		bcm2835_dma_abort(c->chan_base);
 
@@ -836,6 +836,13 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void bcm2835_dma_synchronize(struct dma_chan *chan)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
 static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id,
 				 int irq, unsigned int irq_flags)
 {
@@ -942,6 +949,7 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 	od->ddev.device_prep_dma_memcpy = bcm2835_dma_prep_dma_memcpy;
 	od->ddev.device_config = bcm2835_dma_slave_config;
 	od->ddev.device_terminate_all = bcm2835_dma_terminate_all;
+	od->ddev.device_synchronize = bcm2835_dma_synchronize;
 	od->ddev.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	od->ddev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index f7e965f63274..d9bee65a18a4 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -934,7 +934,7 @@ static bool cpp41_dma_filter_fn(struct dma_chan *chan, void *param)
 
 	BUILD_BUG_ON(ARRAY_SIZE(am335x_usb_queues_rx) !=
 		     ARRAY_SIZE(am335x_usb_queues_tx));
-	if (WARN_ON(cchan->port_num > ARRAY_SIZE(am335x_usb_queues_rx)))
+	if (WARN_ON(cchan->port_num >= ARRAY_SIZE(am335x_usb_queues_rx)))
 		return false;
 
 	cchan->q_num = queues[cchan->port_num].submit;
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 7373b7a555ec..85820a2d69d4 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -511,7 +511,7 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 	/* Clear the DMA status and stop the transfer. */
 	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0);
 	if (jzchan->desc) {
-		jz4780_dma_desc_free(&jzchan->desc->vdesc);
+		vchan_terminate_vdesc(&jzchan->desc->vdesc);
 		jzchan->desc = NULL;
 	}
 
@@ -523,6 +523,13 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void jz4780_dma_synchronize(struct dma_chan *chan)
+{
+	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
+
+	vchan_synchronize(&jzchan->vchan);
+}
+
 static int jz4780_dma_config(struct dma_chan *chan,
 	struct dma_slave_config *config)
 {
@@ -813,6 +820,7 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	dd->device_prep_dma_memcpy = jz4780_dma_prep_dma_memcpy;
 	dd->device_config = jz4780_dma_config;
 	dd->device_terminate_all = jz4780_dma_terminate_all;
+	dd->device_synchronize = jz4780_dma_synchronize;
 	dd->device_tx_status = jz4780_dma_tx_status;
 	dd->device_issue_pending = jz4780_dma_issue_pending;
 	dd->src_addr_widths = JZ_DMA_BUSWIDTHS;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ec5f9d2bc820..80cc2be6483c 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -355,7 +355,7 @@ static void dmatest_callback(void *arg)
 {
 	struct dmatest_done *done = arg;
 	struct dmatest_thread *thread =
-		container_of(arg, struct dmatest_thread, done_wait);
+		container_of(done, struct dmatest_thread, test_done);
 	if (!thread->done) {
 		done->done = true;
 		wake_up_all(done->wait);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 9364a3ed345a..948df1ab5f1a 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -860,11 +860,8 @@ static int edma_terminate_all(struct dma_chan *chan)
 		/* Move the cyclic channel back to default queue */
 		if (!echan->tc && echan->edesc->cyclic)
 			edma_assign_channel_eventq(echan, EVENTQ_DEFAULT);
-		/*
-		 * free the running request descriptor
-		 * since it is not in any of the vdesc lists
-		 */
-		edma_desc_free(&echan->edesc->vdesc);
+
+		vchan_terminate_vdesc(&echan->edesc->vdesc);
 		echan->edesc = NULL;
 	}
 
diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c
index 0391f930aecc..25cec9c243e1 100644
--- a/drivers/dma/img-mdc-dma.c
+++ b/drivers/dma/img-mdc-dma.c
@@ -694,7 +694,6 @@ static unsigned int mdc_get_new_events(struct mdc_chan *mchan)
 static int mdc_terminate_all(struct dma_chan *chan)
 {
 	struct mdc_chan *mchan = to_mdc_chan(chan);
-	struct mdc_tx_desc *mdesc;
 	unsigned long flags;
 	LIST_HEAD(head);
 
@@ -703,21 +702,28 @@ static int mdc_terminate_all(struct dma_chan *chan)
 	mdc_chan_writel(mchan, MDC_CONTROL_AND_STATUS_CANCEL,
 			MDC_CONTROL_AND_STATUS);
 
-	mdesc = mchan->desc;
-	mchan->desc = NULL;
+	if (mchan->desc) {
+		vchan_terminate_vdesc(&mchan->desc->vd);
+		mchan->desc = NULL;
+	}
 	vchan_get_all_descriptors(&mchan->vc, &head);
 
 	mdc_get_new_events(mchan);
 
 	spin_unlock_irqrestore(&mchan->vc.lock, flags);
 
-	if (mdesc)
-		mdc_desc_free(&mdesc->vd);
 	vchan_dma_desc_free_list(&mchan->vc, &head);
 
 	return 0;
 }
 
+static void mdc_synchronize(struct dma_chan *chan)
+{
+	struct mdc_chan *mchan = to_mdc_chan(chan);
+
+	vchan_synchronize(&mchan->vc);
+}
+
 static int mdc_slave_config(struct dma_chan *chan,
 			    struct dma_slave_config *config)
 {
@@ -952,6 +958,7 @@ static int mdc_dma_probe(struct platform_device *pdev)
 	mdma->dma_dev.device_tx_status = mdc_tx_status;
 	mdma->dma_dev.device_issue_pending = mdc_issue_pending;
 	mdma->dma_dev.device_terminate_all = mdc_terminate_all;
+	mdma->dma_dev.device_synchronize = mdc_synchronize;
 	mdma->dma_dev.device_config = mdc_slave_config;
 
 	mdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 2184881afe76..e7db24c67030 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1939,4 +1939,10 @@ module_platform_driver(sdma_driver);
 
 MODULE_AUTHOR("Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>");
 MODULE_DESCRIPTION("i.MX SDMA driver");
+#if IS_ENABLED(CONFIG_SOC_IMX6Q)
+MODULE_FIRMWARE("imx/sdma/sdma-imx6q.bin");
+#endif
+#if IS_ENABLED(CONFIG_SOC_IMX7D)
+MODULE_FIRMWARE("imx/sdma/sdma-imx7d.bin");
+#endif
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 01d2a750a621..26b67455208f 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -719,7 +719,7 @@ static int k3_dma_terminate_all(struct dma_chan *chan)
 		c->phy = NULL;
 		p->vchan = NULL;
 		if (p->ds_run) {
-			k3_dma_free_desc(&p->ds_run->vd);
+			vchan_terminate_vdesc(&p->ds_run->vd);
 			p->ds_run = NULL;
 		}
 		p->ds_done = NULL;
@@ -730,6 +730,13 @@ static int k3_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void k3_dma_synchronize(struct dma_chan *chan)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
 static int k3_dma_transfer_pause(struct dma_chan *chan)
 {
 	struct k3_dma_chan *c = to_k3_chan(chan);
@@ -868,6 +875,7 @@ static int k3_dma_probe(struct platform_device *op)
 	d->slave.device_pause = k3_dma_transfer_pause;
 	d->slave.device_resume = k3_dma_transfer_resume;
 	d->slave.device_terminate_all = k3_dma_terminate_all;
+	d->slave.device_synchronize = k3_dma_synchronize;
 	d->slave.copy_align = DMAENGINE_ALIGN_8_BYTES;
 
 	/* init virtual channel */
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 5ba5714d0b7c..94d7bd7d2880 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -480,9 +480,7 @@ static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 		to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
 			mic_dma_intr_handler, mic_dma_thread_fn,
 			"mic dma_channel", ch, ch->ch_num);
-	if (IS_ERR(ch->cookie))
-		return PTR_ERR(ch->cookie);
-	return 0;
+	return PTR_ERR_OR_ZERO(ch->cookie);
 }
 
 static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index f6dd849159d8..d21c19822feb 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -1311,7 +1311,7 @@ static int omap_dma_terminate_all(struct dma_chan *chan)
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
-		omap_dma_desc_free(&c->desc->vd);
+		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
 		/* Avoid stopping the dma twice */
 		if (!c->paused)
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index e3669850aef4..963cc5228d05 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -50,6 +50,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/of_dma.h>
+#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/delay.h>
 #include <linux/acpi.h>
@@ -104,6 +105,10 @@ static unsigned int nr_desc_prm;
 module_param(nr_desc_prm, uint, 0644);
 MODULE_PARM_DESC(nr_desc_prm, "number of descriptors (default: 0)");
 
+enum hidma_cap {
+	HIDMA_MSI_CAP = 1,
+	HIDMA_IDENTITY_CAP,
+};
 
 /* process completed descriptors */
 static void hidma_process_completed(struct hidma_chan *mchan)
@@ -736,25 +741,12 @@ static int hidma_request_msi(struct hidma_dev *dmadev,
 #endif
 }
 
-static bool hidma_msi_capable(struct device *dev)
+static bool hidma_test_capability(struct device *dev, enum hidma_cap test_cap)
 {
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const char *of_compat;
-	int ret = -EINVAL;
+	enum hidma_cap cap;
 
-	if (!adev || acpi_disabled) {
-		ret = device_property_read_string(dev, "compatible",
-						  &of_compat);
-		if (ret)
-			return false;
-
-		ret = strcmp(of_compat, "qcom,hidma-1.1");
-	} else {
-#ifdef CONFIG_ACPI
-		ret = strcmp(acpi_device_hid(adev), "QCOM8062");
-#endif
-	}
-	return ret == 0;
+	cap = (enum hidma_cap) device_get_match_data(dev);
+	return cap ? ((cap & test_cap) > 0) : 0;
 }
 
 static int hidma_probe(struct platform_device *pdev)
@@ -834,8 +826,7 @@ static int hidma_probe(struct platform_device *pdev)
 	 * Determine the MSI capability of the platform. Old HW doesn't
 	 * support MSI.
 	 */
-	msi = hidma_msi_capable(&pdev->dev);
-
+	msi = hidma_test_capability(&pdev->dev, HIDMA_MSI_CAP);
 	device_property_read_u32(&pdev->dev, "desc-count",
 				 &dmadev->nr_descriptors);
 
@@ -848,7 +839,10 @@ static int hidma_probe(struct platform_device *pdev)
 	if (!dmadev->nr_descriptors)
 		dmadev->nr_descriptors = HIDMA_NR_DEFAULT_DESC;
 
-	dmadev->chidx = readl(dmadev->dev_trca + 0x28);
+	if (hidma_test_capability(&pdev->dev, HIDMA_IDENTITY_CAP))
+		dmadev->chidx = readl(dmadev->dev_trca + 0x40);
+	else
+		dmadev->chidx = readl(dmadev->dev_trca + 0x28);
 
 	/* Set DMA mask to 64 bits. */
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
@@ -953,7 +947,8 @@ static int hidma_remove(struct platform_device *pdev)
 #if IS_ENABLED(CONFIG_ACPI)
 static const struct acpi_device_id hidma_acpi_ids[] = {
 	{"QCOM8061"},
-	{"QCOM8062"},
+	{"QCOM8062", HIDMA_MSI_CAP},
+	{"QCOM8063", (HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP)},
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
@@ -961,7 +956,9 @@ MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
 
 static const struct of_device_id hidma_match[] = {
 	{.compatible = "qcom,hidma-1.0",},
-	{.compatible = "qcom,hidma-1.1",},
+	{.compatible = "qcom,hidma-1.1", .data = (void *)(HIDMA_MSI_CAP),},
+	{.compatible = "qcom,hidma-1.2",
+	 .data = (void *)(HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP),},
 	{},
 };
 MODULE_DEVICE_TABLE(of, hidma_match);
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index 4999e266b2de..7c6e2ff212a2 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -393,6 +393,8 @@ static int hidma_ll_reset(struct hidma_lldev *lldev)
  */
 static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 {
+	unsigned long irqflags;
+
 	if (cause & HIDMA_ERR_INT_MASK) {
 		dev_err(lldev->dev, "error 0x%x, disabling...\n",
 				cause);
@@ -410,6 +412,10 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 		return;
 	}
 
+	spin_lock_irqsave(&lldev->lock, irqflags);
+	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+	spin_unlock_irqrestore(&lldev->lock, irqflags);
+
 	/*
 	 * Fine tuned for this HW...
 	 *
@@ -421,9 +427,6 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 	 * Try to consume as many EVREs as possible.
 	 */
 	hidma_handle_tre_completion(lldev);
-
-	/* We consumed TREs or there are pending TREs or EVREs. */
-	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
 }
 
 irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 7335e2eb9b72..000c7019ca7d 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -17,6 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/property.h>
+#include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/module.h>
@@ -356,59 +357,29 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 {
 	struct platform_device *pdev_parent = of_find_device_by_node(np);
 	struct platform_device_info pdevinfo;
-	struct of_phandle_args out_irq;
 	struct device_node *child;
-	struct resource *res = NULL;
-	const __be32 *cell;
-	int ret = 0, size, i, num;
-	u64 addr, addr_size;
+	struct resource *res;
+	int ret = 0;
+
+	/* allocate a resource array */
+	res = kcalloc(3, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
 
 	for_each_available_child_of_node(np, child) {
-		struct resource *res_iter;
 		struct platform_device *new_pdev;
 
-		cell = of_get_property(child, "reg", &size);
-		if (!cell) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		size /= sizeof(*cell);
-		num = size /
-			(of_n_addr_cells(child) + of_n_size_cells(child)) + 1;
-
-		/* allocate a resource array */
-		res = kcalloc(num, sizeof(*res), GFP_KERNEL);
-		if (!res) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		/* read each reg value */
-		i = 0;
-		res_iter = res;
-		while (i < size) {
-			addr = of_read_number(&cell[i],
-					      of_n_addr_cells(child));
-			i += of_n_addr_cells(child);
-
-			addr_size = of_read_number(&cell[i],
-						   of_n_size_cells(child));
-			i += of_n_size_cells(child);
-
-			res_iter->start = addr;
-			res_iter->end = res_iter->start + addr_size - 1;
-			res_iter->flags = IORESOURCE_MEM;
-			res_iter++;
-		}
-
-		ret = of_irq_parse_one(child, 0, &out_irq);
-		if (ret)
+		ret = of_address_to_resource(child, 0, &res[0]);
+		if (!ret)
 			goto out;
 
-		res_iter->start = irq_create_of_mapping(&out_irq);
-		res_iter->name = "hidma event irq";
-		res_iter->flags = IORESOURCE_IRQ;
+		ret = of_address_to_resource(child, 1, &res[1]);
+		if (!ret)
+			goto out;
+
+		ret = of_irq_to_resource(child, 0, &res[2]);
+		if (ret <= 0)
+			goto out;
 
 		memset(&pdevinfo, 0, sizeof(pdevinfo));
 		pdevinfo.fwnode = &child->fwnode;
@@ -416,7 +387,7 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		pdevinfo.name = child->name;
 		pdevinfo.id = object_counter++;
 		pdevinfo.res = res;
-		pdevinfo.num_res = num;
+		pdevinfo.num_res = 3;
 		pdevinfo.data = NULL;
 		pdevinfo.size_data = 0;
 		pdevinfo.dma_mask = DMA_BIT_MASK(64);
@@ -434,8 +405,6 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		 */
 		of_msi_configure(&new_pdev->dev, child);
 		of_node_put(child);
-		kfree(res);
-		res = NULL;
 	}
 out:
 	kfree(res);
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index f04c4702d98b..cd92d696bcf9 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -732,7 +732,7 @@ static int s3c24xx_dma_terminate_all(struct dma_chan *chan)
 
 	/* Dequeue current job */
 	if (s3cchan->at) {
-		s3c24xx_dma_desc_free(&s3cchan->at->vd);
+		vchan_terminate_vdesc(&s3cchan->at->vd);
 		s3cchan->at = NULL;
 	}
 
@@ -744,6 +744,13 @@ unlock:
 	return ret;
 }
 
+static void s3c24xx_dma_synchronize(struct dma_chan *chan)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+
+	vchan_synchronize(&s3cchan->vc);
+}
+
 static void s3c24xx_dma_free_chan_resources(struct dma_chan *chan)
 {
 	/* Ensure all queued descriptors are freed */
@@ -1282,6 +1289,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->memcpy.device_issue_pending = s3c24xx_dma_issue_pending;
 	s3cdma->memcpy.device_config = s3c24xx_dma_set_runtime_config;
 	s3cdma->memcpy.device_terminate_all = s3c24xx_dma_terminate_all;
+	s3cdma->memcpy.device_synchronize = s3c24xx_dma_synchronize;
 
 	/* Initialize slave engine for SoC internal dedicated peripherals */
 	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
@@ -1296,6 +1304,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
 	s3cdma->slave.device_config = s3c24xx_dma_set_runtime_config;
 	s3cdma->slave.device_terminate_all = s3c24xx_dma_terminate_all;
+	s3cdma->slave.device_synchronize = s3c24xx_dma_synchronize;
 	s3cdma->slave.filter.map = pdata->slave_map;
 	s3cdma->slave.filter.mapcnt = pdata->slavecnt;
 	s3cdma->slave.filter.fn = s3c24xx_dma_filter;
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 35c3936edc45..e3ff162c03fc 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
@@ -741,6 +742,41 @@ static int rcar_dmac_fill_hwdesc(struct rcar_dmac_chan *chan,
 /* -----------------------------------------------------------------------------
  * Stop and reset
  */
+static void rcar_dmac_chcr_de_barrier(struct rcar_dmac_chan *chan)
+{
+	u32 chcr;
+	unsigned int i;
+
+	/*
+	 * Ensure that the setting of the DE bit is actually 0 after
+	 * clearing it.
+	 */
+	for (i = 0; i < 1024; i++) {
+		chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+		if (!(chcr & RCAR_DMACHCR_DE))
+			return;
+		udelay(1);
+	}
+
+	dev_err(chan->chan.device->dev, "CHCR DE check error\n");
+}
+
+static void rcar_dmac_sync_tcr(struct rcar_dmac_chan *chan)
+{
+	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+
+	if (!(chcr & RCAR_DMACHCR_DE))
+		return;
+
+	/* set DE=0 and flush remaining data */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, (chcr & ~RCAR_DMACHCR_DE));
+
+	/* make sure all remaining data was flushed */
+	rcar_dmac_chcr_de_barrier(chan);
+
+	/* back DE */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+}
 
 static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 {
@@ -749,6 +785,7 @@ static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 	chcr &= ~(RCAR_DMACHCR_DSE | RCAR_DMACHCR_DSIE | RCAR_DMACHCR_IE |
 		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE);
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+	rcar_dmac_chcr_de_barrier(chan);
 }
 
 static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
@@ -1309,8 +1346,11 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 		residue += chunk->size;
 	}
 
+	if (desc->direction == DMA_DEV_TO_MEM)
+		rcar_dmac_sync_tcr(chan);
+
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCR) << desc->xfer_shift;
+	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
 
 	return residue;
 }
@@ -1481,6 +1521,8 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 	if (chcr & RCAR_DMACHCR_TE)
 		mask |= RCAR_DMACHCR_DE;
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr & ~mask);
+	if (mask & RCAR_DMACHCR_DE)
+		rcar_dmac_chcr_de_barrier(chan);
 
 	if (chcr & RCAR_DMACHCR_DSE)
 		ret |= rcar_dmac_isr_desc_stage_end(chan);
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index b652071a2096..b106e8a60af6 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -710,7 +710,7 @@ static int sprd_dma_config(struct dma_chan *chan, struct sprd_dma_desc *sdesc,
 	return 0;
 }
 
-struct dma_async_tx_descriptor *
+static struct dma_async_tx_descriptor *
 sprd_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			 size_t len, unsigned long flags)
 {
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index d5db0f6e1ff8..4dbb30cf94ac 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -253,9 +253,6 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	iomem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(iomem))
 		return PTR_ERR(iomem);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index b9d75a54c896..9a558e30c461 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -353,7 +353,8 @@ static int tegra_dma_slave_config(struct dma_chan *dc,
 	}
 
 	memcpy(&tdc->dma_sconfig, sconfig, sizeof(*sconfig));
-	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID) {
+	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID &&
+	    sconfig->device_fc) {
 		if (sconfig->slave_id > TEGRA_APBDMA_CSR_REQ_SEL_MASK)
 			return -EINVAL;
 		tdc->slave_id = sconfig->slave_id;
@@ -970,8 +971,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_ONCE | TEGRA_APBDMA_CSR_FLOW;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	csr |= TEGRA_APBDMA_CSR_ONCE;
+
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
 
@@ -1110,10 +1116,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_FLOW;
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
 
 	apb_seq |= TEGRA_APBDMA_APBSEQ_WRAP_WORD_1;
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 7df910e7c348..9272b173c746 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -54,7 +54,15 @@ struct ti_am335x_xbar_map {
 
 static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u8 val)
 {
-	writeb_relaxed(val, iomem + event);
+	/*
+	 * TPCC_EVT_MUX_60_63 register layout is different than the
+	 * rest, in the sense, that event 63 is mapped to lowest byte
+	 * and event 60 is mapped to highest, handle it separately.
+	 */
+	if (event >= 60 && event <= 63)
+		writeb_relaxed(val, iomem + (63 - event % 4));
+	else
+		writeb_relaxed(val, iomem + event);
 }
 
 static void ti_am335x_xbar_free(struct device *dev, void *route_data)
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 896bafb7a532..395c698edb4d 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -422,7 +422,7 @@ static int td_alloc_chan_resources(struct dma_chan *chan)
 				break;
 			else {
 				dev_err(chan2dev(chan),
-					"Couldnt allocate any descriptors\n");
+					"Couldn't allocate any descriptors\n");
 				return -ENOMEM;
 			}
 		}
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 545e97279083..88ad8ed2a8d6 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -107,10 +107,7 @@ static void vchan_complete(unsigned long arg)
 		dmaengine_desc_get_callback(&vd->tx, &cb);
 
 		list_del(&vd->node);
-		if (dmaengine_desc_test_reuse(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+		vchan_vdesc_fini(vd);
 
 		dmaengine_desc_callback_invoke(&cb, NULL);
 	}
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 3f776a46a29c..b09b75ab0751 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -35,6 +35,7 @@ struct virt_dma_chan {
 	struct list_head desc_completed;
 
 	struct virt_dma_desc *cyclic;
+	struct virt_dma_desc *vd_terminated;
 };
 
 static inline struct virt_dma_chan *to_virt_chan(struct dma_chan *chan)
@@ -103,6 +104,20 @@ static inline void vchan_cookie_complete(struct virt_dma_desc *vd)
 	tasklet_schedule(&vc->task);
 }
 
+/**
+ * vchan_vdesc_fini - Free or reuse a descriptor
+ * @vd: virtual descriptor to free/reuse
+ */
+static inline void vchan_vdesc_fini(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	if (dmaengine_desc_test_reuse(&vd->tx))
+		list_add(&vd->node, &vc->desc_allocated);
+	else
+		vc->desc_free(vd);
+}
+
 /**
  * vchan_cyclic_callback - report the completion of a period
  * @vd: virtual descriptor
@@ -115,6 +130,25 @@ static inline void vchan_cyclic_callback(struct virt_dma_desc *vd)
 	tasklet_schedule(&vc->task);
 }
 
+/**
+ * vchan_terminate_vdesc - Disable pending cyclic callback
+ * @vd: virtual descriptor to be terminated
+ *
+ * vc.lock must be held by caller
+ */
+static inline void vchan_terminate_vdesc(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	/* free up stuck descriptor */
+	if (vc->vd_terminated)
+		vchan_vdesc_fini(vc->vd_terminated);
+
+	vc->vd_terminated = vd;
+	if (vc->cyclic == vd)
+		vc->cyclic = NULL;
+}
+
 /**
  * vchan_next_desc - peek at the next descriptor to be processed
  * @vc: virtual channel to obtain descriptor from
@@ -168,10 +202,20 @@ static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
  * Makes sure that all scheduled or active callbacks have finished running. For
  * proper operation the caller has to ensure that no new callbacks are scheduled
  * after the invocation of this function started.
+ * Free up the terminated cyclic descriptor to prevent memory leakage.
  */
 static inline void vchan_synchronize(struct virt_dma_chan *vc)
 {
+	unsigned long flags;
+
 	tasklet_kill(&vc->task);
+
+	spin_lock_irqsave(&vc->lock, flags);
+	if (vc->vd_terminated) {
+		vchan_vdesc_fini(vc->vd_terminated);
+		vc->vd_terminated = NULL;
+	}
+	spin_unlock_irqrestore(&vc->lock, flags);
 }
 
 #endif
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 5eef13380ca8..27b523530c4a 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -99,7 +99,9 @@
 #define XILINX_DMA_REG_FRMPTR_STS		0x0024
 #define XILINX_DMA_REG_PARK_PTR		0x0028
 #define XILINX_DMA_PARK_PTR_WR_REF_SHIFT	8
+#define XILINX_DMA_PARK_PTR_WR_REF_MASK		GENMASK(12, 8)
 #define XILINX_DMA_PARK_PTR_RD_REF_SHIFT	0
+#define XILINX_DMA_PARK_PTR_RD_REF_MASK		GENMASK(4, 0)
 #define XILINX_DMA_REG_VDMA_VERSION		0x002c
 
 /* Register Direct Mode Registers */
@@ -163,6 +165,7 @@
 #define XILINX_DMA_BD_SOP		BIT(27)
 #define XILINX_DMA_BD_EOP		BIT(26)
 #define XILINX_DMA_COALESCE_MAX		255
+#define XILINX_DMA_NUM_DESCS		255
 #define XILINX_DMA_NUM_APP_WORDS	5
 
 /* Multi-Channel DMA Descriptor offsets*/
@@ -211,8 +214,8 @@ struct xilinx_vdma_desc_hw {
  * @next_desc_msb: MSB of Next Descriptor Pointer @0x04
  * @buf_addr: Buffer address @0x08
  * @buf_addr_msb: MSB of Buffer address @0x0C
- * @pad1: Reserved @0x10
- * @pad2: Reserved @0x14
+ * @mcdma_control: Control field for mcdma @0x10
+ * @vsize_stride: Vsize and Stride field for mcdma @0x14
  * @control: Control field @0x18
  * @status: Status field @0x1C
  * @app: APP Fields @0x20 - 0x30
@@ -232,11 +235,11 @@ struct xilinx_axidma_desc_hw {
 /**
  * struct xilinx_cdma_desc_hw - Hardware Descriptor
  * @next_desc: Next Descriptor Pointer @0x00
- * @next_descmsb: Next Descriptor Pointer MSB @0x04
+ * @next_desc_msb: Next Descriptor Pointer MSB @0x04
  * @src_addr: Source address @0x08
- * @src_addrmsb: Source address MSB @0x0C
+ * @src_addr_msb: Source address MSB @0x0C
  * @dest_addr: Destination address @0x10
- * @dest_addrmsb: Destination address MSB @0x14
+ * @dest_addr_msb: Destination address MSB @0x14
  * @control: Control field @0x18
  * @status: Status field @0x1C
  */
@@ -310,6 +313,7 @@ struct xilinx_dma_tx_descriptor {
  * @pending_list: Descriptors waiting
  * @active_list: Descriptors ready to submit
  * @done_list: Complete descriptors
+ * @free_seg_list: Free descriptors
  * @common: DMA common channel
  * @desc_pool: Descriptors pool
  * @dev: The dma device
@@ -321,6 +325,7 @@ struct xilinx_dma_tx_descriptor {
  * @cyclic: Check for cyclic transfers.
  * @genlock: Support genlock mode
  * @err: Channel has errors
+ * @idle: Check for channel idle
  * @tasklet: Cleanup work after irq
  * @config: Device configuration info
  * @flush_on_fsync: Flush on Frame sync
@@ -329,9 +334,12 @@ struct xilinx_dma_tx_descriptor {
  * @desc_submitcount: Descriptor h/w submitted count
  * @residue: Residue for AXI DMA
  * @seg_v: Statically allocated segments base
+ * @seg_p: Physical allocated segments base
  * @cyclic_seg_v: Statically allocated segment base for cyclic transfers
+ * @cyclic_seg_p: Physical allocated segments base for cyclic dma
  * @start_transfer: Differentiate b/w DMA IP's transfer
  * @stop_transfer: Differentiate b/w DMA IP's quiesce
+ * @tdest: TDEST value for mcdma
  */
 struct xilinx_dma_chan {
 	struct xilinx_dma_device *xdev;
@@ -341,6 +349,7 @@ struct xilinx_dma_chan {
 	struct list_head pending_list;
 	struct list_head active_list;
 	struct list_head done_list;
+	struct list_head free_seg_list;
 	struct dma_chan common;
 	struct dma_pool *desc_pool;
 	struct device *dev;
@@ -352,6 +361,7 @@ struct xilinx_dma_chan {
 	bool cyclic;
 	bool genlock;
 	bool err;
+	bool idle;
 	struct tasklet_struct tasklet;
 	struct xilinx_vdma_config config;
 	bool flush_on_fsync;
@@ -360,18 +370,20 @@ struct xilinx_dma_chan {
 	u32 desc_submitcount;
 	u32 residue;
 	struct xilinx_axidma_tx_segment *seg_v;
+	dma_addr_t seg_p;
 	struct xilinx_axidma_tx_segment *cyclic_seg_v;
+	dma_addr_t cyclic_seg_p;
 	void (*start_transfer)(struct xilinx_dma_chan *chan);
 	int (*stop_transfer)(struct xilinx_dma_chan *chan);
 	u16 tdest;
 };
 
 /**
- * enum xdma_ip_type: DMA IP type.
+ * enum xdma_ip_type - DMA IP type.
  *
- * XDMA_TYPE_AXIDMA: Axi dma ip.
- * XDMA_TYPE_CDMA: Axi cdma ip.
- * XDMA_TYPE_VDMA: Axi vdma ip.
+ * @XDMA_TYPE_AXIDMA: Axi dma ip.
+ * @XDMA_TYPE_CDMA: Axi cdma ip.
+ * @XDMA_TYPE_VDMA: Axi vdma ip.
  *
  */
 enum xdma_ip_type {
@@ -580,18 +592,32 @@ xilinx_cdma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 static struct xilinx_axidma_tx_segment *
 xilinx_axidma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 {
-	struct xilinx_axidma_tx_segment *segment;
-	dma_addr_t phys;
+	struct xilinx_axidma_tx_segment *segment = NULL;
+	unsigned long flags;
 
-	segment = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &phys);
-	if (!segment)
-		return NULL;
-
-	segment->phys = phys;
+	spin_lock_irqsave(&chan->lock, flags);
+	if (!list_empty(&chan->free_seg_list)) {
+		segment = list_first_entry(&chan->free_seg_list,
+					   struct xilinx_axidma_tx_segment,
+					   node);
+		list_del(&segment->node);
+	}
+	spin_unlock_irqrestore(&chan->lock, flags);
 
 	return segment;
 }
 
+static void xilinx_dma_clean_hw_desc(struct xilinx_axidma_desc_hw *hw)
+{
+	u32 next_desc = hw->next_desc;
+	u32 next_desc_msb = hw->next_desc_msb;
+
+	memset(hw, 0, sizeof(struct xilinx_axidma_desc_hw));
+
+	hw->next_desc = next_desc;
+	hw->next_desc_msb = next_desc_msb;
+}
+
 /**
  * xilinx_dma_free_tx_segment - Free transaction segment
  * @chan: Driver specific DMA channel
@@ -600,7 +626,9 @@ xilinx_axidma_alloc_tx_segment(struct xilinx_dma_chan *chan)
 static void xilinx_dma_free_tx_segment(struct xilinx_dma_chan *chan,
 				struct xilinx_axidma_tx_segment *segment)
 {
-	dma_pool_free(chan->desc_pool, segment, segment->phys);
+	xilinx_dma_clean_hw_desc(&segment->hw);
+
+	list_add_tail(&segment->node, &chan->free_seg_list);
 }
 
 /**
@@ -725,16 +753,31 @@ static void xilinx_dma_free_descriptors(struct xilinx_dma_chan *chan)
 static void xilinx_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	unsigned long flags;
 
 	dev_dbg(chan->dev, "Free all channel resources.\n");
 
 	xilinx_dma_free_descriptors(chan);
+
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		xilinx_dma_free_tx_segment(chan, chan->cyclic_seg_v);
-		xilinx_dma_free_tx_segment(chan, chan->seg_v);
+		spin_lock_irqsave(&chan->lock, flags);
+		INIT_LIST_HEAD(&chan->free_seg_list);
+		spin_unlock_irqrestore(&chan->lock, flags);
+
+		/* Free memory that is allocated for BD */
+		dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				  XILINX_DMA_NUM_DESCS, chan->seg_v,
+				  chan->seg_p);
+
+		/* Free Memory that is allocated for cyclic DMA Mode */
+		dma_free_coherent(chan->dev, sizeof(*chan->cyclic_seg_v),
+				  chan->cyclic_seg_v, chan->cyclic_seg_p);
+	}
+
+	if (chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA) {
+		dma_pool_destroy(chan->desc_pool);
+		chan->desc_pool = NULL;
 	}
-	dma_pool_destroy(chan->desc_pool);
-	chan->desc_pool = NULL;
 }
 
 /**
@@ -817,6 +860,7 @@ static void xilinx_dma_do_tasklet(unsigned long data)
 static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	int i;
 
 	/* Has this channel already been allocated? */
 	if (chan->desc_pool)
@@ -827,11 +871,30 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 	 * for meeting Xilinx VDMA specification requirement.
 	 */
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		chan->desc_pool = dma_pool_create("xilinx_dma_desc_pool",
-				   chan->dev,
-				   sizeof(struct xilinx_axidma_tx_segment),
-				   __alignof__(struct xilinx_axidma_tx_segment),
-				   0);
+		/* 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);
+		if (!chan->seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate channel %d descriptors\n",
+				chan->id);
+			return -ENOMEM;
+		}
+
+		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
+			chan->seg_v[i].hw.next_desc =
+			lower_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].hw.next_desc_msb =
+			upper_32_bits(chan->seg_p + sizeof(*chan->seg_v) *
+				((i + 1) % XILINX_DMA_NUM_DESCS));
+			chan->seg_v[i].phys = chan->seg_p +
+				sizeof(*chan->seg_v) * i;
+			list_add_tail(&chan->seg_v[i].node,
+				      &chan->free_seg_list);
+		}
 	} else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
 		chan->desc_pool = dma_pool_create("xilinx_cdma_desc_pool",
 				   chan->dev,
@@ -846,7 +909,8 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 				     0);
 	}
 
-	if (!chan->desc_pool) {
+	if (!chan->desc_pool &&
+	    (chan->xdev->dma_config->dmatype != XDMA_TYPE_AXIDMA)) {
 		dev_err(chan->dev,
 			"unable to allocate channel %d descriptor pool\n",
 			chan->id);
@@ -854,23 +918,21 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 	}
 
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		/*
-		 * For AXI DMA case after submitting a pending_list, keep
-		 * an extra segment allocated so that the "next descriptor"
-		 * pointer on the tail descriptor always points to a
-		 * valid descriptor, even when paused after reaching taildesc.
-		 * This way, it is possible to issue additional
-		 * transfers without halting and restarting the channel.
-		 */
-		chan->seg_v = xilinx_axidma_alloc_tx_segment(chan);
-
 		/*
 		 * 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 = xilinx_axidma_alloc_tx_segment(chan);
+		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);
@@ -935,35 +997,11 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan,
 	return ret;
 }
 
-/**
- * xilinx_dma_is_running - Check if DMA channel is running
- * @chan: Driver specific DMA channel
- *
- * Return: '1' if running, '0' if not.
- */
-static bool xilinx_dma_is_running(struct xilinx_dma_chan *chan)
-{
-	return !(dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
-		 XILINX_DMA_DMASR_HALTED) &&
-		(dma_ctrl_read(chan, XILINX_DMA_REG_DMACR) &
-		 XILINX_DMA_DMACR_RUNSTOP);
-}
-
-/**
- * xilinx_dma_is_idle - Check if DMA channel is idle
- * @chan: Driver specific DMA channel
- *
- * Return: '1' if idle, '0' if not.
- */
-static bool xilinx_dma_is_idle(struct xilinx_dma_chan *chan)
-{
-	return dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
-		XILINX_DMA_DMASR_IDLE;
-}
-
 /**
  * xilinx_dma_stop_transfer - Halt DMA channel
  * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
  */
 static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
 {
@@ -980,6 +1018,8 @@ static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
 /**
  * xilinx_cdma_stop_transfer - Wait for the current transfer to complete
  * @chan: Driver specific DMA channel
+ *
+ * Return: '0' on success and failure value on error
  */
 static int xilinx_cdma_stop_transfer(struct xilinx_dma_chan *chan)
 {
@@ -1022,13 +1062,16 @@ 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;
+	u32 reg, j;
 	struct xilinx_vdma_tx_segment *tail_segment;
 
 	/* This function was invoked with lock held */
 	if (chan->err)
 		return;
 
+	if (!chan->idle)
+		return;
+
 	if (list_empty(&chan->pending_list))
 		return;
 
@@ -1040,13 +1083,6 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	tail_segment = list_last_entry(&tail_desc->segments,
 				       struct xilinx_vdma_tx_segment, node);
 
-	/* If it is SG mode and hardware is busy, cannot submit */
-	if (chan->has_sg && xilinx_dma_is_running(chan) &&
-	    !xilinx_dma_is_idle(chan)) {
-		dev_dbg(chan->dev, "DMA controller still busy\n");
-		return;
-	}
-
 	/*
 	 * If hardware is idle, then all descriptors on the running lists are
 	 * done, start new transfers
@@ -1063,10 +1099,6 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	else
 		reg &= ~XILINX_DMA_DMACR_FRAMECNT_EN;
 
-	/* Configure channel to allow number frame buffers */
-	dma_ctrl_write(chan, XILINX_DMA_REG_FRMSTORE,
-			chan->desc_pendingcount);
-
 	/*
 	 * With SG, start with circular mode, so that BDs can be fetched.
 	 * In direct register mode, if not parking, enable circular mode
@@ -1079,17 +1111,16 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
-	if (config->park && (config->park_frm >= 0) &&
-			(config->park_frm < chan->num_frms)) {
-		if (chan->direction == DMA_MEM_TO_DEV)
-			dma_write(chan, XILINX_DMA_REG_PARK_PTR,
-				config->park_frm <<
-					XILINX_DMA_PARK_PTR_RD_REF_SHIFT);
-		else
-			dma_write(chan, XILINX_DMA_REG_PARK_PTR,
-				config->park_frm <<
-					XILINX_DMA_PARK_PTR_WR_REF_SHIFT);
+	j = chan->desc_submitcount;
+	reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR);
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK;
+		reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT;
+	} else {
+		reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK;
+		reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT;
 	}
+	dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg);
 
 	/* Start the hardware */
 	xilinx_dma_start(chan);
@@ -1101,6 +1132,8 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 	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;
@@ -1130,19 +1163,16 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 		vdma_desc_write(chan, XILINX_DMA_REG_FRMDLY_STRIDE,
 				last->hw.stride);
 		vdma_desc_write(chan, XILINX_DMA_REG_VSIZE, last->hw.vsize);
-	}
 
-	if (!chan->has_sg) {
-		list_del(&desc->node);
-		list_add_tail(&desc->node, &chan->active_list);
 		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;
-	} else {
-		list_splice_tail_init(&chan->pending_list, &chan->active_list);
-		chan->desc_pendingcount = 0;
 	}
+
+	chan->idle = false;
 }
 
 /**
@@ -1158,6 +1188,9 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 	if (chan->err)
 		return;
 
+	if (!chan->idle)
+		return;
+
 	if (list_empty(&chan->pending_list))
 		return;
 
@@ -1176,6 +1209,12 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 	}
 
 	if (chan->has_sg) {
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
+		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
 		xilinx_write(chan, XILINX_DMA_REG_CURDESC,
 			     head_desc->async_tx.phys);
 
@@ -1203,6 +1242,7 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
 	chan->desc_pendingcount = 0;
+	chan->idle = false;
 }
 
 /**
@@ -1212,7 +1252,7 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 {
 	struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
-	struct xilinx_axidma_tx_segment *tail_segment, *old_head, *new_head;
+	struct xilinx_axidma_tx_segment *tail_segment;
 	u32 reg;
 
 	if (chan->err)
@@ -1221,12 +1261,8 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 	if (list_empty(&chan->pending_list))
 		return;
 
-	/* If it is SG mode and hardware is busy, cannot submit */
-	if (chan->has_sg && xilinx_dma_is_running(chan) &&
-	    !xilinx_dma_is_idle(chan)) {
-		dev_dbg(chan->dev, "DMA controller still busy\n");
+	if (!chan->idle)
 		return;
-	}
 
 	head_desc = list_first_entry(&chan->pending_list,
 				     struct xilinx_dma_tx_descriptor, node);
@@ -1235,21 +1271,6 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 	tail_segment = list_last_entry(&tail_desc->segments,
 				       struct xilinx_axidma_tx_segment, node);
 
-	if (chan->has_sg && !chan->xdev->mcdma) {
-		old_head = list_first_entry(&head_desc->segments,
-					struct xilinx_axidma_tx_segment, node);
-		new_head = chan->seg_v;
-		/* Copy Buffer Descriptor fields. */
-		new_head->hw = old_head->hw;
-
-		/* Swap and save new reserve */
-		list_replace_init(&old_head->node, &new_head->node);
-		chan->seg_v = old_head;
-
-		tail_segment->hw.next_desc = chan->seg_v->phys;
-		head_desc->async_tx.phys = new_head->phys;
-	}
-
 	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
 
 	if (chan->desc_pendingcount <= XILINX_DMA_COALESCE_MAX) {
@@ -1324,6 +1345,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 
 	list_splice_tail_init(&chan->pending_list, &chan->active_list);
 	chan->desc_pendingcount = 0;
+	chan->idle = false;
 }
 
 /**
@@ -1388,6 +1410,8 @@ static int xilinx_dma_reset(struct xilinx_dma_chan *chan)
 	}
 
 	chan->err = false;
+	chan->idle = true;
+	chan->desc_submitcount = 0;
 
 	return err;
 }
@@ -1469,6 +1493,7 @@ static irqreturn_t xilinx_dma_irq_handler(int irq, void *data)
 	if (status & XILINX_DMA_DMASR_FRM_CNT_IRQ) {
 		spin_lock(&chan->lock);
 		xilinx_dma_complete_descriptor(chan);
+		chan->idle = true;
 		chan->start_transfer(chan);
 		spin_unlock(&chan->lock);
 	}
@@ -1591,7 +1616,7 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
 	struct xilinx_dma_tx_descriptor *desc;
-	struct xilinx_vdma_tx_segment *segment, *prev = NULL;
+	struct xilinx_vdma_tx_segment *segment;
 	struct xilinx_vdma_desc_hw *hw;
 
 	if (!is_slave_direction(xt->dir))
@@ -1645,8 +1670,6 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	/* Insert the segment into the descriptor segments list. */
 	list_add_tail(&segment->node, &desc->segments);
 
-	prev = segment;
-
 	/* Link the last hardware descriptor with the first. */
 	segment = list_first_entry(&desc->segments,
 				   struct xilinx_vdma_tx_segment, node);
@@ -1733,7 +1756,7 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 {
 	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
 	struct xilinx_dma_tx_descriptor *desc;
-	struct xilinx_axidma_tx_segment *segment = NULL, *prev = NULL;
+	struct xilinx_axidma_tx_segment *segment = NULL;
 	u32 *app_w = (u32 *)context;
 	struct scatterlist *sg;
 	size_t copy;
@@ -1784,10 +1807,6 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 					       XILINX_DMA_NUM_APP_WORDS);
 			}
 
-			if (prev)
-				prev->hw.next_desc = segment->phys;
-
-			prev = segment;
 			sg_used += copy;
 
 			/*
@@ -1801,7 +1820,6 @@ static struct dma_async_tx_descriptor *xilinx_dma_prep_slave_sg(
 	segment = list_first_entry(&desc->segments,
 				   struct xilinx_axidma_tx_segment, node);
 	desc->async_tx.phys = segment->phys;
-	prev->hw.next_desc = segment->phys;
 
 	/* For the last DMA_MEM_TO_DEV transfer, set EOP */
 	if (chan->direction == DMA_MEM_TO_DEV) {
@@ -1821,11 +1839,14 @@ error:
 
 /**
  * xilinx_dma_prep_dma_cyclic - prepare descriptors for a DMA_SLAVE transaction
- * @chan: DMA channel
- * @sgl: scatterlist to transfer to/from
- * @sg_len: number of entries in @scatterlist
+ * @dchan: DMA channel
+ * @buf_addr: Physical address of the buffer
+ * @buf_len: Total length of the cyclic buffers
+ * @period_len: length of individual cyclic buffer
  * @direction: DMA direction
  * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
  */
 static struct dma_async_tx_descriptor *xilinx_dma_prep_dma_cyclic(
 	struct dma_chan *dchan, dma_addr_t buf_addr, size_t buf_len,
@@ -2009,7 +2030,9 @@ error:
 
 /**
  * xilinx_dma_terminate_all - Halt the channel and free descriptors
- * @chan: Driver specific DMA Channel pointer
+ * @dchan: Driver specific DMA Channel pointer
+ *
+ * Return: '0' always.
  */
 static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 {
@@ -2029,6 +2052,7 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 
 	/* Remove and free all of the descriptors in the lists */
 	xilinx_dma_free_descriptors(chan);
+	chan->idle = true;
 
 	if (chan->cyclic) {
 		reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
@@ -2037,6 +2061,10 @@ static int xilinx_dma_terminate_all(struct dma_chan *dchan)
 		chan->cyclic = false;
 	}
 
+	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
+		dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR,
+			     XILINX_CDMA_CR_SGMODE);
+
 	return 0;
 }
 
@@ -2323,6 +2351,7 @@ static void xdma_disable_allclks(struct xilinx_dma_device *xdev)
  *
  * @xdev: Driver specific device structure
  * @node: Device node
+ * @chan_id: DMA Channel id
  *
  * Return: '0' on success and failure value on error
  */
@@ -2344,11 +2373,18 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 	chan->has_sg = xdev->has_sg;
 	chan->desc_pendingcount = 0x0;
 	chan->ext_addr = xdev->ext_addr;
+	/* This variable ensures that descriptors are not
+	 * Submitted when dma engine is in progress. This variable is
+	 * Added to avoid polling for a bit in the status register to
+	 * Know dma state in the driver hot path.
+	 */
+	chan->idle = true;
 
 	spin_lock_init(&chan->lock);
 	INIT_LIST_HEAD(&chan->pending_list);
 	INIT_LIST_HEAD(&chan->done_list);
 	INIT_LIST_HEAD(&chan->active_list);
+	INIT_LIST_HEAD(&chan->free_seg_list);
 
 	/* Retrieve the channel properties from the device tree */
 	has_dre = of_property_read_bool(node, "xlnx,include-dre");
@@ -2379,6 +2415,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->ctrl_offset = XILINX_DMA_MM2S_CTRL_OFFSET;
 		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
 			chan->desc_offset = XILINX_VDMA_MM2S_DESC_OFFSET;
+			chan->config.park = 1;
 
 			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
 			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_MM2S)
@@ -2395,6 +2432,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->ctrl_offset = XILINX_DMA_S2MM_CTRL_OFFSET;
 		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
 			chan->desc_offset = XILINX_VDMA_S2MM_DESC_OFFSET;
+			chan->config.park = 1;
 
 			if (xdev->flush_on_fsync == XILINX_DMA_FLUSH_BOTH ||
 			    xdev->flush_on_fsync == XILINX_DMA_FLUSH_S2MM)
@@ -2459,7 +2497,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
  * Return: 0 always.
  */
 static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
-				    struct device_node *node) {
+				    struct device_node *node)
+{
 	int ret, i, nr_channels = 1;
 
 	ret = of_property_read_u32(node, "dma-channels", &nr_channels);
@@ -2654,7 +2693,12 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		goto error;
 	}
 
-	dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
+	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA)
+		dev_info(&pdev->dev, "Xilinx AXI DMA Engine Driver Probed!!\n");
+	else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA)
+		dev_info(&pdev->dev, "Xilinx AXI CDMA Engine Driver Probed!!\n");
+	else
+		dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
 
 	return 0;
 
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 1ee1241ca797..f14645817ed8 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/pm_runtime.h>
 
 #include "../dmaengine.h"
 
@@ -47,6 +48,7 @@
 #define ZYNQMP_DMA_SRC_START_MSB	0x15C
 #define ZYNQMP_DMA_DST_START_LSB	0x160
 #define ZYNQMP_DMA_DST_START_MSB	0x164
+#define ZYNQMP_DMA_TOTAL_BYTE		0x188
 #define ZYNQMP_DMA_RATE_CTRL		0x18C
 #define ZYNQMP_DMA_IRQ_SRC_ACCT		0x190
 #define ZYNQMP_DMA_IRQ_DST_ACCT		0x194
@@ -138,6 +140,8 @@
 #define ZYNQMP_DMA_BUS_WIDTH_64		64
 #define ZYNQMP_DMA_BUS_WIDTH_128	128
 
+#define ZDMA_PM_TIMEOUT			100
+
 #define ZYNQMP_DMA_DESC_SIZE(chan)	(chan->desc_size)
 
 #define to_chan(chan)		container_of(chan, struct zynqmp_dma_chan, \
@@ -211,8 +215,6 @@ struct zynqmp_dma_desc_sw {
  * @bus_width: Bus width
  * @src_burst_len: Source burst length
  * @dst_burst_len: Dest burst length
- * @clk_main: Pointer to main clock
- * @clk_apb: Pointer to apb clock
  */
 struct zynqmp_dma_chan {
 	struct zynqmp_dma_device *zdev;
@@ -237,8 +239,6 @@ struct zynqmp_dma_chan {
 	u32 bus_width;
 	u32 src_burst_len;
 	u32 dst_burst_len;
-	struct clk *clk_main;
-	struct clk *clk_apb;
 };
 
 /**
@@ -246,11 +246,15 @@ struct zynqmp_dma_chan {
  * @dev: Device Structure
  * @common: DMA device structure
  * @chan: Driver specific DMA channel
+ * @clk_main: Pointer to main clock
+ * @clk_apb: Pointer to apb clock
  */
 struct zynqmp_dma_device {
 	struct device *dev;
 	struct dma_device common;
 	struct zynqmp_dma_chan *chan;
+	struct clk *clk_main;
+	struct clk *clk_apb;
 };
 
 static inline void zynqmp_dma_writeq(struct zynqmp_dma_chan *chan, u32 reg,
@@ -461,7 +465,11 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
 	struct zynqmp_dma_desc_sw *desc;
-	int i;
+	int i, ret;
+
+	ret = pm_runtime_get_sync(chan->dev);
+	if (ret < 0)
+		return ret;
 
 	chan->sw_desc_pool = kzalloc(sizeof(*desc) * ZYNQMP_DMA_NUM_DESCS,
 				     GFP_KERNEL);
@@ -506,6 +514,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 static void zynqmp_dma_start(struct zynqmp_dma_chan *chan)
 {
 	writel(ZYNQMP_DMA_INT_EN_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IER);
+	writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
 	chan->idle = false;
 	writel(ZYNQMP_DMA_ENABLE, chan->regs + ZYNQMP_DMA_CTRL2);
 }
@@ -517,12 +526,12 @@ static void zynqmp_dma_start(struct zynqmp_dma_chan *chan)
  */
 static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)
 {
-	u32 val;
-
+	if (status & ZYNQMP_DMA_BYTE_CNT_OVRFL)
+		writel(0, chan->regs + ZYNQMP_DMA_TOTAL_BYTE);
 	if (status & ZYNQMP_DMA_IRQ_DST_ACCT_ERR)
-		val = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
+		readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
 	if (status & ZYNQMP_DMA_IRQ_SRC_ACCT_ERR)
-		val = readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
+		readl(chan->regs + ZYNQMP_DMA_IRQ_SRC_ACCT);
 }
 
 static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
@@ -545,6 +554,8 @@ static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
  * zynqmp_dma_device_config - Zynqmp dma device configuration
  * @dchan: DMA channel
  * @config: DMA device config
+ *
+ * Return: 0 always
  */
 static int zynqmp_dma_device_config(struct dma_chan *dchan,
 				    struct dma_slave_config *config)
@@ -640,7 +651,7 @@ static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
 
 /**
  * zynqmp_dma_free_descriptors - Free channel descriptors
- * @dchan: DMA channel pointer
+ * @chan: ZynqMP DMA channel pointer
  */
 static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 {
@@ -664,6 +675,8 @@ static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
 		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
 		chan->desc_pool_v, chan->desc_pool_p);
 	kfree(chan->sw_desc_pool);
+	pm_runtime_mark_last_busy(chan->dev);
+	pm_runtime_put_autosuspend(chan->dev);
 }
 
 /**
@@ -715,7 +728,7 @@ static irqreturn_t zynqmp_dma_irq_handler(int irq, void *data)
 
 	if (status & ZYNQMP_DMA_INT_OVRFL) {
 		zynqmp_dma_handle_ovfl_int(chan, status);
-		dev_info(chan->dev, "Channel %p overflow interrupt\n", chan);
+		dev_dbg(chan->dev, "Channel %p overflow interrupt\n", chan);
 		ret = IRQ_HANDLED;
 	}
 
@@ -838,11 +851,10 @@ static void zynqmp_dma_chan_remove(struct zynqmp_dma_chan *chan)
 	if (!chan)
 		return;
 
-	devm_free_irq(chan->zdev->dev, chan->irq, chan);
+	if (chan->irq)
+		devm_free_irq(chan->zdev->dev, chan->irq, chan);
 	tasklet_kill(&chan->tasklet);
 	list_del(&chan->common.device_node);
-	clk_disable_unprepare(chan->clk_apb);
-	clk_disable_unprepare(chan->clk_main);
 }
 
 /**
@@ -907,30 +919,6 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,
 			       "zynqmp-dma", chan);
 	if (err)
 		return err;
-	chan->clk_main = devm_clk_get(&pdev->dev, "clk_main");
-	if (IS_ERR(chan->clk_main)) {
-		dev_err(&pdev->dev, "main clock not found.\n");
-		return PTR_ERR(chan->clk_main);
-	}
-
-	chan->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
-	if (IS_ERR(chan->clk_apb)) {
-		dev_err(&pdev->dev, "apb clock not found.\n");
-		return PTR_ERR(chan->clk_apb);
-	}
-
-	err = clk_prepare_enable(chan->clk_main);
-	if (err) {
-		dev_err(&pdev->dev, "Unable to enable main clock.\n");
-		return err;
-	}
-
-	err = clk_prepare_enable(chan->clk_apb);
-	if (err) {
-		clk_disable_unprepare(chan->clk_main);
-		dev_err(&pdev->dev, "Unable to enable apb clock.\n");
-		return err;
-	}
 
 	chan->desc_size = sizeof(struct zynqmp_dma_desc_ll);
 	chan->idle = true;
@@ -952,6 +940,87 @@ static struct dma_chan *of_zynqmp_dma_xlate(struct of_phandle_args *dma_spec,
 	return dma_get_slave_channel(&zdev->chan->common);
 }
 
+/**
+ * zynqmp_dma_suspend - Suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_suspend(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_suspend(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_resume - Resume from suspend
+ * @dev:	Address of the device structure
+ *
+ * Resume operation after suspend.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused zynqmp_dma_resume(struct device *dev)
+{
+	if (!device_may_wakeup(dev))
+		return pm_runtime_force_resume(dev);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_suspend - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_suspend(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(zdev->clk_main);
+	clk_disable_unprepare(zdev->clk_apb);
+
+	return 0;
+}
+
+/**
+ * zynqmp_dma_runtime_resume - Runtime suspend method for the driver
+ * @dev:	Address of the device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused zynqmp_dma_runtime_resume(struct device *dev)
+{
+	struct zynqmp_dma_device *zdev = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(zdev->clk_main);
+	if (err) {
+		dev_err(dev, "Unable to enable main clock.\n");
+		return err;
+	}
+
+	err = clk_prepare_enable(zdev->clk_apb);
+	if (err) {
+		dev_err(dev, "Unable to enable apb clock.\n");
+		clk_disable_unprepare(zdev->clk_main);
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops zynqmp_dma_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(zynqmp_dma_suspend, zynqmp_dma_resume)
+	SET_RUNTIME_PM_OPS(zynqmp_dma_runtime_suspend,
+			   zynqmp_dma_runtime_resume, NULL)
+};
+
 /**
  * zynqmp_dma_probe - Driver probe function
  * @pdev: Pointer to the platform_device structure
@@ -984,12 +1053,33 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	p->device_config = zynqmp_dma_device_config;
 	p->dev = &pdev->dev;
 
+	zdev->clk_main = devm_clk_get(&pdev->dev, "clk_main");
+	if (IS_ERR(zdev->clk_main)) {
+		dev_err(&pdev->dev, "main clock not found.\n");
+		return PTR_ERR(zdev->clk_main);
+	}
+
+	zdev->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
+	if (IS_ERR(zdev->clk_apb)) {
+		dev_err(&pdev->dev, "apb clock not found.\n");
+		return PTR_ERR(zdev->clk_apb);
+	}
+
 	platform_set_drvdata(pdev, zdev);
+	pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(zdev->dev);
+	pm_runtime_enable(zdev->dev);
+	pm_runtime_get_sync(zdev->dev);
+	if (!pm_runtime_enabled(zdev->dev)) {
+		ret = zynqmp_dma_runtime_resume(zdev->dev);
+		if (ret)
+			return ret;
+	}
 
 	ret = zynqmp_dma_chan_probe(zdev, pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Probing channel failed\n");
-		goto free_chan_resources;
+		goto err_disable_pm;
 	}
 
 	p->dst_addr_widths = BIT(zdev->chan->bus_width / 8);
@@ -1005,12 +1095,19 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 		goto free_chan_resources;
 	}
 
+	pm_runtime_mark_last_busy(zdev->dev);
+	pm_runtime_put_sync_autosuspend(zdev->dev);
+
 	dev_info(&pdev->dev, "ZynqMP DMA driver Probe success\n");
 
 	return 0;
 
 free_chan_resources:
 	zynqmp_dma_chan_remove(zdev->chan);
+err_disable_pm:
+	if (!pm_runtime_enabled(zdev->dev))
+		zynqmp_dma_runtime_suspend(zdev->dev);
+	pm_runtime_disable(zdev->dev);
 	return ret;
 }
 
@@ -1028,6 +1125,9 @@ static int zynqmp_dma_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&zdev->common);
 
 	zynqmp_dma_chan_remove(zdev->chan);
+	pm_runtime_disable(zdev->dev);
+	if (!pm_runtime_enabled(zdev->dev))
+		zynqmp_dma_runtime_suspend(zdev->dev);
 
 	return 0;
 }
@@ -1042,6 +1142,7 @@ static struct platform_driver zynqmp_dma_driver = {
 	.driver = {
 		.name = "xilinx-zynqmp-dma",
 		.of_match_table = zynqmp_dma_of_match,
+		.pm = &zynqmp_dma_dev_pm_ops,
 	},
 	.probe = zynqmp_dma_probe,
 	.remove = zynqmp_dma_remove,
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 8ad33a44a7b8..f25d36358187 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -981,10 +981,18 @@ static int of_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static void *
+of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
+				const struct device *dev)
+{
+	return (void *)of_device_get_match_data(dev);
+}
+
 const struct fwnode_operations of_fwnode_ops = {
 	.get = of_fwnode_get,
 	.put = of_fwnode_put,
 	.device_is_available = of_fwnode_device_is_available,
+	.device_get_match_data = of_fwnode_device_get_match_data,
 	.property_present = of_fwnode_property_present,
 	.property_read_int_array = of_fwnode_property_read_int_array,
 	.property_read_string_array = of_fwnode_property_read_string_array,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index b8f4c3c776e5..a933f87ef98d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -585,6 +585,7 @@ extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev);
 
+void *acpi_get_match_data(const struct device *dev);
 extern bool acpi_driver_match_device(struct device *dev,
 				     const struct device_driver *drv);
 int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *);
@@ -762,6 +763,11 @@ static inline const struct acpi_device_id *acpi_match_device(
 	return NULL;
 }
 
+static inline void *acpi_get_match_data(const struct device *dev)
+{
+	return NULL;
+}
+
 static inline bool acpi_driver_match_device(struct device *dev,
 					    const struct device_driver *drv)
 {
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 411a84c6c400..4fa1a489efe4 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 
 struct fwnode_operations;
+struct device;
 
 struct fwnode_handle {
 	struct fwnode_handle *secondary;
@@ -51,6 +52,7 @@ struct fwnode_reference_args {
  * struct fwnode_operations - Operations for fwnode interface
  * @get: Get a reference to an fwnode.
  * @put: Put a reference to an fwnode.
+ * @device_get_match_data: Return the device driver match data.
  * @property_present: Return true if a property is present.
  * @property_read_integer_array: Read an array of integer properties. Return
  *				 zero on success, a negative error code
@@ -71,6 +73,8 @@ struct fwnode_operations {
 	struct fwnode_handle *(*get)(struct fwnode_handle *fwnode);
 	void (*put)(struct fwnode_handle *fwnode);
 	bool (*device_is_available)(const struct fwnode_handle *fwnode);
+	void *(*device_get_match_data)(const struct fwnode_handle *fwnode,
+				       const struct device *dev);
 	bool (*property_present)(const struct fwnode_handle *fwnode,
 				 const char *propname);
 	int (*property_read_int_array)(const struct fwnode_handle *fwnode,
diff --git a/include/linux/property.h b/include/linux/property.h
index f6189a3ac63c..6653ed4b99f9 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -275,6 +275,8 @@ bool device_dma_supported(struct device *dev);
 
 enum dev_dma_attr device_get_dma_attr(struct device *dev);
 
+void *device_get_match_data(struct device *dev);
+
 int device_get_phy_mode(struct device *dev);
 
 void *device_get_mac_address(struct device *dev, char *addr, int alen);