Merge tag 'dmaengine-5.4-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - Move Dmaengine DT bindings to YAML and convert Allwinner to schema.

 - FSL dma device_synchronize implementation

 - DW split acpi and of helpers and updates to driver and support for
   Elkhart Lake

 - Move filter fn as private for omap-dma and edma drivers and
   improvements to these drivers

 - Mark expected switch fall-through in couple of drivers

 - Renames of shdma and nbpfaxi binding document

 - Minor updates to bunch of drivers

* tag 'dmaengine-5.4-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (55 commits)
  dmaengine: ti: edma: Use bitmap_set() instead of open coded edma_set_bits()
  dmaengine: ti: edma: Only reset region0 access registers
  dmaengine: ti: edma: Do not reset reserved paRAM slots
  dmaengine: iop-adma.c: fix printk format warning
  dmaengine: stm32-dma: Use struct_size() helper
  dt-bindings: dmaengine: dma-common: Fix the dma-channel-mask property
  dmanegine: ioat/dca: Use struct_size() helper
  dmaengine: iop-adma: remove set but not used variable 'slots_per_op'
  dmaengine: dmatest: Add support for completion polling
  dmaengine: ti: omap-dma: Remove variable override in omap_dma_tx_status()
  dmaengine: ti: omap-dma: Remove 'Assignment in if condition'
  dmaengine: ti: edma: Remove 'Assignment in if condition'
  dmaengine: dw: platform: Split OF helpers to separate module
  dmaengine: dw: platform: Split ACPI helpers to separate module
  dmaengine: dw: platform: Move handle check to dw_dma_acpi_controller_register()
  dmaengine: dw: platform: Switch to acpi_dma_controller_register()
  dmaengine: dw: platform: Use devm_platform_ioremap_resource()
  dmaengine: dw: platform: Enable iDMA 32-bit on Intel Elkhart Lake
  dmaengine: dw: platform: Use struct dw_dma_chip_pdata
  dmaengine: dw: Export struct dw_dma_chip_pdata for wider use
  ...

39 files changed, 746 insertions, 454 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 413efef5fbb6..7c511e3db4c8 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -295,7 +295,7 @@ config INTEL_IOATDMA
 
 config INTEL_IOP_ADMA
 	tristate "Intel IOP32x ADMA support"
-	depends on ARCH_IOP32X
+	depends on ARCH_IOP32X || COMPILE_TEST
 	select DMA_ENGINE
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	help
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 30243f5c0710..8a05db3343d3 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -82,6 +83,12 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	if (si->base_request_line == 0 && si->num_handshake_signals == 0)
 		return 0;
 
+	/* Set up DMA mask based on value from CSRT */
+	ret = dma_coerce_mask_and_coherent(&adev->dev,
+					   DMA_BIT_MASK(si->dma_address_width));
+	if (ret)
+		return 0;
+
 	adma->base_request_line = si->base_request_line;
 	adma->end_request_line = si->base_request_line +
 				 si->num_handshake_signals - 1;
@@ -140,7 +147,7 @@ static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
  * @dev:		struct device of DMA controller
  * @acpi_dma_xlate:	translation function which converts a dma specifier
  *			into a dma_chan structure
- * @data		pointer to controller specific data to be used by
+ * @data:		pointer to controller specific data to be used by
  *			translation function
  *
  * Allocated memory should be freed with appropriate acpi_dma_controller_free()
@@ -224,7 +231,7 @@ static void devm_acpi_dma_release(struct device *dev, void *res)
  * devm_acpi_dma_controller_register - resource managed acpi_dma_controller_register()
  * @dev:		device that is registering this DMA controller
  * @acpi_dma_xlate:	translation function
- * @data		pointer to controller specific data
+ * @data:		pointer to controller specific data
  *
  * Managed acpi_dma_controller_register(). DMA controller registered by this
  * function are automatically freed on driver detach. See
@@ -257,6 +264,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_register);
 
 /**
  * devm_acpi_dma_controller_free - resource managed acpi_dma_controller_free()
+ * @dev:	device that is unregistering as DMA controller
  *
  * Unregister a DMA controller registered with
  * devm_acpi_dma_controller_register(). Normally this function will not need to
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 67100e4e1083..e4c593f48575 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -896,8 +896,10 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
 
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
-	if (rc)
+	if (rc) {
+		dev_err(&pdev->dev, "Unable to set DMA mask\n");
 		return rc;
+	}
 
 	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
 	if (!od)
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 7fe9309a876b..cafb1cc065bb 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -92,6 +92,7 @@
 #define JZ_SOC_DATA_PROGRAMMABLE_DMA	BIT(1)
 #define JZ_SOC_DATA_PER_CHAN_PM		BIT(2)
 #define JZ_SOC_DATA_NO_DCKES_DCKEC	BIT(3)
+#define JZ_SOC_DATA_BREAK_LINKS		BIT(4)
 
 /**
  * struct jz4780_dma_hwdesc - descriptor structure read by the DMA controller.
@@ -355,6 +356,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 	void *context)
 {
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
+	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
 	struct jz4780_dma_desc *desc;
 	unsigned int i;
 	int err;
@@ -375,7 +377,8 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 
 		desc->desc[i].dcm |= JZ_DMA_DCM_TIE;
 
-		if (i != (sg_len - 1)) {
+		if (i != (sg_len - 1) &&
+		    !(jzdma->soc_data->flags & JZ_SOC_DATA_BREAK_LINKS)) {
 			/* Automatically proceeed to the next descriptor. */
 			desc->desc[i].dcm |= JZ_DMA_DCM_LINK;
 
@@ -664,6 +667,8 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan,
 static bool jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma,
 				struct jz4780_dma_chan *jzchan)
 {
+	const unsigned int soc_flags = jzdma->soc_data->flags;
+	struct jz4780_dma_desc *desc = jzchan->desc;
 	uint32_t dcs;
 	bool ack = true;
 
@@ -691,8 +696,11 @@ static bool jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma,
 
 				jz4780_dma_begin(jzchan);
 			} else if (dcs & JZ_DMA_DCS_TT) {
-				vchan_cookie_complete(&jzchan->desc->vdesc);
-				jzchan->desc = NULL;
+				if (!(soc_flags & JZ_SOC_DATA_BREAK_LINKS) ||
+				    (jzchan->curr_hwdesc + 1 == desc->count)) {
+					vchan_cookie_complete(&desc->vdesc);
+					jzchan->desc = NULL;
+				}
 
 				jz4780_dma_begin(jzchan);
 			} else {
@@ -878,10 +886,8 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	}
 
 	ret = platform_get_irq(pdev, 0);
-	if (ret < 0) {
-		dev_err(dev, "failed to get IRQ: %d\n", ret);
+	if (ret < 0)
 		return ret;
-	}
 
 	jzdma->irq = ret;
 
@@ -992,6 +998,7 @@ static int jz4780_dma_remove(struct platform_device *pdev)
 static const struct jz4780_dma_soc_data jz4740_dma_soc_data = {
 	.nb_channels = 6,
 	.transfer_ord_max = 5,
+	.flags = JZ_SOC_DATA_BREAK_LINKS,
 };
 
 static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = {
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 3d22ae8dca72..a2cadfa2e6d7 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -72,6 +72,10 @@ static bool norandom;
 module_param(norandom, bool, 0644);
 MODULE_PARM_DESC(norandom, "Disable random offset setup (default: random)");
 
+static bool polled;
+module_param(polled, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
+
 static bool verbose;
 module_param(verbose, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
@@ -110,6 +114,7 @@ struct dmatest_params {
 	bool		norandom;
 	int		alignment;
 	unsigned int	transfer_size;
+	bool		polled;
 };
 
 /**
@@ -651,7 +656,10 @@ static int dmatest_func(void *data)
 	/*
 	 * src and dst buffers are freed by ourselves below
 	 */
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
+	if (params->polled)
+		flags = DMA_CTRL_ACK;
+	else
+		flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	ktime = ktime_get();
 	while (!kthread_should_stop()
@@ -780,8 +788,10 @@ static int dmatest_func(void *data)
 		}
 
 		done->done = false;
-		tx->callback = dmatest_callback;
-		tx->callback_param = done;
+		if (!params->polled) {
+			tx->callback = dmatest_callback;
+			tx->callback_param = done;
+		}
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
@@ -790,12 +800,22 @@ static int dmatest_func(void *data)
 			msleep(100);
 			goto error_unmap_continue;
 		}
-		dma_async_issue_pending(chan);
 
-		wait_event_freezable_timeout(thread->done_wait, done->done,
-					     msecs_to_jiffies(params->timeout));
+		if (params->polled) {
+			status = dma_sync_wait(chan, cookie);
+			dmaengine_terminate_sync(chan);
+			if (status == DMA_COMPLETE)
+				done->done = true;
+		} else {
+			dma_async_issue_pending(chan);
+
+			wait_event_freezable_timeout(thread->done_wait,
+					done->done,
+					msecs_to_jiffies(params->timeout));
 
-		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
+			status = dma_async_is_tx_complete(chan, cookie, NULL,
+							  NULL);
+		}
 
 		if (!done->done) {
 			result("test timed out", total_tests, src->off, dst->off,
@@ -1065,6 +1085,7 @@ static void add_threaded_test(struct dmatest_info *info)
 	params->norandom = norandom;
 	params->alignment = alignment;
 	params->transfer_size = transfer_size;
+	params->polled = polled;
 
 	request_channels(info, DMA_MEMCPY);
 	request_channels(info, DMA_MEMSET);
diff --git a/drivers/dma/dw/Makefile b/drivers/dma/dw/Makefile
index 63ed895c09aa..b6f06699e91a 100644
--- a/drivers/dma/dw/Makefile
+++ b/drivers/dma/dw/Makefile
@@ -3,7 +3,9 @@ obj-$(CONFIG_DW_DMAC_CORE)	+= dw_dmac_core.o
 dw_dmac_core-objs	:= core.o dw.o idma32.o
 
 obj-$(CONFIG_DW_DMAC)		+= dw_dmac.o
-dw_dmac-objs		:= platform.o
+dw_dmac-y			:= platform.o
+dw_dmac-$(CONFIG_ACPI)		+= acpi.o
+dw_dmac-$(CONFIG_OF)		+= of.o
 
 obj-$(CONFIG_DW_DMAC_PCI)	+= dw_dmac_pci.o
 dw_dmac_pci-objs	:= pci.o
diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c
new file mode 100644
index 000000000000..f6e8d55b4f6e
--- /dev/null
+++ b/drivers/dma/dw/acpi.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2013,2019 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/acpi_dma.h>
+
+#include "internal.h"
+
+static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param)
+{
+	struct acpi_dma_spec *dma_spec = param;
+	struct dw_dma_slave slave = {
+		.dma_dev = dma_spec->dev,
+		.src_id = dma_spec->slave_id,
+		.dst_id = dma_spec->slave_id,
+		.m_master = 0,
+		.p_master = 1,
+	};
+
+	return dw_dma_filter(chan, &slave);
+}
+
+void dw_dma_acpi_controller_register(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+	struct acpi_dma_filter_info *info;
+	int ret;
+
+	if (!has_acpi_companion(dev))
+		return;
+
+	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return;
+
+	dma_cap_zero(info->dma_cap);
+	dma_cap_set(DMA_SLAVE, info->dma_cap);
+	info->filter_fn = dw_dma_acpi_filter;
+
+	ret = acpi_dma_controller_register(dev, acpi_dma_simple_xlate, info);
+	if (ret)
+		dev_err(dev, "could not register acpi_dma_controller\n");
+}
+
+void dw_dma_acpi_controller_free(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+
+	if (!has_acpi_companion(dev))
+		return;
+
+	acpi_dma_controller_free(dev);
+}
diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index 1dd7a4e6dd23..2e1c52eefdeb 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -23,4 +23,55 @@ int do_dw_dma_enable(struct dw_dma_chip *chip);
 
 extern bool dw_dma_filter(struct dma_chan *chan, void *param);
 
+#ifdef CONFIG_ACPI
+void dw_dma_acpi_controller_register(struct dw_dma *dw);
+void dw_dma_acpi_controller_free(struct dw_dma *dw);
+#else /* !CONFIG_ACPI */
+static inline void dw_dma_acpi_controller_register(struct dw_dma *dw) {}
+static inline void dw_dma_acpi_controller_free(struct dw_dma *dw) {}
+#endif /* !CONFIG_ACPI */
+
+struct platform_device;
+
+#ifdef CONFIG_OF
+struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev);
+void dw_dma_of_controller_register(struct dw_dma *dw);
+void dw_dma_of_controller_free(struct dw_dma *dw);
+#else
+static inline struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
+{
+	return NULL;
+}
+static inline void dw_dma_of_controller_register(struct dw_dma *dw) {}
+static inline void dw_dma_of_controller_free(struct dw_dma *dw) {}
+#endif
+
+struct dw_dma_chip_pdata {
+	const struct dw_dma_platform_data *pdata;
+	int (*probe)(struct dw_dma_chip *chip);
+	int (*remove)(struct dw_dma_chip *chip);
+	struct dw_dma_chip *chip;
+};
+
+static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = {
+	.probe = dw_dma_probe,
+	.remove = dw_dma_remove,
+};
+
+static const struct dw_dma_platform_data idma32_pdata = {
+	.nr_channels = 8,
+	.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 __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = {
+	.pdata = &idma32_pdata,
+	.probe = idma32_dma_probe,
+	.remove = idma32_dma_remove,
+};
+
 #endif /* _DMA_DW_INTERNAL_H */
diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
new file mode 100644
index 000000000000..9e27831dee32
--- /dev/null
+++ b/drivers/dma/dw/of.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Platform driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2013 Intel Corporation
+ */
+
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+
+#include "internal.h"
+
+static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
+					struct of_dma *ofdma)
+{
+	struct dw_dma *dw = ofdma->of_dma_data;
+	struct dw_dma_slave slave = {
+		.dma_dev = dw->dma.dev,
+	};
+	dma_cap_mask_t cap;
+
+	if (dma_spec->args_count != 3)
+		return NULL;
+
+	slave.src_id = dma_spec->args[0];
+	slave.dst_id = dma_spec->args[0];
+	slave.m_master = dma_spec->args[1];
+	slave.p_master = dma_spec->args[2];
+
+	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.m_master >= dw->pdata->nr_masters ||
+		    slave.p_master >= dw->pdata->nr_masters))
+		return NULL;
+
+	dma_cap_zero(cap);
+	dma_cap_set(DMA_SLAVE, cap);
+
+	/* TODO: there should be a simpler way to do this */
+	return dma_request_channel(cap, dw_dma_filter, &slave);
+}
+
+struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct dw_dma_platform_data *pdata;
+	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS], mb[DW_DMA_MAX_NR_CHANNELS];
+	u32 nr_masters;
+	u32 nr_channels;
+
+	if (!np) {
+		dev_err(&pdev->dev, "Missing DT data\n");
+		return NULL;
+	}
+
+	if (of_property_read_u32(np, "dma-masters", &nr_masters))
+		return NULL;
+	if (nr_masters < 1 || nr_masters > DW_DMA_MAX_NR_MASTERS)
+		return NULL;
+
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+	if (nr_channels > DW_DMA_MAX_NR_CHANNELS)
+		return NULL;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	pdata->nr_masters = nr_masters;
+	pdata->nr_channels = nr_channels;
+
+	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
+		pdata->chan_allocation_order = (unsigned char)tmp;
+
+	if (!of_property_read_u32(np, "chan_priority", &tmp))
+		pdata->chan_priority = tmp;
+
+	if (!of_property_read_u32(np, "block_size", &tmp))
+		pdata->block_size = tmp;
+
+	if (!of_property_read_u32_array(np, "data-width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = arr[tmp];
+	} else if (!of_property_read_u32_array(np, "data_width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
+	}
+
+	if (!of_property_read_u32_array(np, "multi-block", mb, nr_channels)) {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			pdata->multi_block[tmp] = mb[tmp];
+	} else {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			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;
+}
+
+void dw_dma_of_controller_register(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+	int ret;
+
+	if (!dev->of_node)
+		return;
+
+	ret = of_dma_controller_register(dev->of_node, dw_dma_of_xlate, dw);
+	if (ret)
+		dev_err(dev, "could not register of_dma_controller\n");
+}
+
+void dw_dma_of_controller_free(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+
+	if (!dev->of_node)
+		return;
+
+	of_dma_controller_free(dev->of_node);
+}
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 8de87b15a988..cf6e8ec4c0ff 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -12,38 +12,10 @@
 
 #include "internal.h"
 
-struct dw_dma_pci_data {
-	const struct dw_dma_platform_data *pdata;
-	int (*probe)(struct dw_dma_chip *chip);
-	int (*remove)(struct dw_dma_chip *chip);
-	struct dw_dma_chip *chip;
-};
-
-static const struct dw_dma_pci_data dw_pci_data = {
-	.probe = dw_dma_probe,
-	.remove = dw_dma_remove,
-};
-
-static const struct dw_dma_platform_data idma32_pdata = {
-	.nr_channels = 8,
-	.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,
-	.remove = idma32_dma_remove,
-};
-
 static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 {
-	const struct dw_dma_pci_data *drv_data = (void *)pid->driver_data;
-	struct dw_dma_pci_data *data;
+	const struct dw_dma_chip_pdata *drv_data = (void *)pid->driver_data;
+	struct dw_dma_chip_pdata *data;
 	struct dw_dma_chip *chip;
 	int ret;
 
@@ -95,7 +67,7 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 
 static void dw_pci_remove(struct pci_dev *pdev)
 {
-	struct dw_dma_pci_data *data = pci_get_drvdata(pdev);
+	struct dw_dma_chip_pdata *data = pci_get_drvdata(pdev);
 	struct dw_dma_chip *chip = data->chip;
 	int ret;
 
@@ -108,7 +80,7 @@ static void dw_pci_remove(struct pci_dev *pdev)
 
 static int dw_pci_suspend_late(struct device *dev)
 {
-	struct dw_dma_pci_data *data = dev_get_drvdata(dev);
+	struct dw_dma_chip_pdata *data = dev_get_drvdata(dev);
 	struct dw_dma_chip *chip = data->chip;
 
 	return do_dw_dma_disable(chip);
@@ -116,7 +88,7 @@ static int dw_pci_suspend_late(struct device *dev)
 
 static int dw_pci_resume_early(struct device *dev)
 {
-	struct dw_dma_pci_data *data = dev_get_drvdata(dev);
+	struct dw_dma_chip_pdata *data = dev_get_drvdata(dev);
 	struct dw_dma_chip *chip = data->chip;
 
 	return do_dw_dma_enable(chip);
@@ -130,29 +102,29 @@ 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), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_dma_chip_pdata },
 
 	/* BayTrail */
-	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_data },
-	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_dma_chip_pdata },
+	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_dma_chip_pdata },
 
 	/* Merrifield */
-	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&idma32_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&idma32_chip_pdata },
 
 	/* Braswell */
-	{ PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_pci_data },
-	{ PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_dma_chip_pdata },
+	{ PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_dma_chip_pdata },
 
-	/* Elkhart Lake iDMA 32-bit (OSE DMA) */
-	{ PCI_VDEVICE(INTEL, 0x4bb4), (kernel_ulong_t)&idma32_pci_data },
-	{ PCI_VDEVICE(INTEL, 0x4bb5), (kernel_ulong_t)&idma32_pci_data },
-	{ PCI_VDEVICE(INTEL, 0x4bb6), (kernel_ulong_t)&idma32_pci_data },
+	/* Elkhart Lake iDMA 32-bit (PSE DMA) */
+	{ PCI_VDEVICE(INTEL, 0x4bb4), (kernel_ulong_t)&idma32_chip_pdata },
+	{ PCI_VDEVICE(INTEL, 0x4bb5), (kernel_ulong_t)&idma32_chip_pdata },
+	{ PCI_VDEVICE(INTEL, 0x4bb6), (kernel_ulong_t)&idma32_chip_pdata },
 
 	/* Haswell */
-	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_dma_chip_pdata },
 
 	/* Broadwell */
-	{ PCI_VDEVICE(INTEL, 0x9ce0), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x9ce0), (kernel_ulong_t)&dw_dma_chip_pdata },
 
 	{ }
 };
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 382dfd9e9600..c90c798e5ec3 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -17,163 +17,28 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
-#include <linux/of_dma.h>
 #include <linux/acpi.h>
-#include <linux/acpi_dma.h>
 
 #include "internal.h"
 
 #define DRV_NAME	"dw_dmac"
 
-static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
-					struct of_dma *ofdma)
-{
-	struct dw_dma *dw = ofdma->of_dma_data;
-	struct dw_dma_slave slave = {
-		.dma_dev = dw->dma.dev,
-	};
-	dma_cap_mask_t cap;
-
-	if (dma_spec->args_count != 3)
-		return NULL;
-
-	slave.src_id = dma_spec->args[0];
-	slave.dst_id = dma_spec->args[0];
-	slave.m_master = dma_spec->args[1];
-	slave.p_master = dma_spec->args[2];
-
-	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
-		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
-		    slave.m_master >= dw->pdata->nr_masters ||
-		    slave.p_master >= dw->pdata->nr_masters))
-		return NULL;
-
-	dma_cap_zero(cap);
-	dma_cap_set(DMA_SLAVE, cap);
-
-	/* TODO: there should be a simpler way to do this */
-	return dma_request_channel(cap, dw_dma_filter, &slave);
-}
-
-#ifdef CONFIG_ACPI
-static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param)
-{
-	struct acpi_dma_spec *dma_spec = param;
-	struct dw_dma_slave slave = {
-		.dma_dev = dma_spec->dev,
-		.src_id = dma_spec->slave_id,
-		.dst_id = dma_spec->slave_id,
-		.m_master = 0,
-		.p_master = 1,
-	};
-
-	return dw_dma_filter(chan, &slave);
-}
-
-static void dw_dma_acpi_controller_register(struct dw_dma *dw)
-{
-	struct device *dev = dw->dma.dev;
-	struct acpi_dma_filter_info *info;
-	int ret;
-
-	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return;
-
-	dma_cap_zero(info->dma_cap);
-	dma_cap_set(DMA_SLAVE, info->dma_cap);
-	info->filter_fn = dw_dma_acpi_filter;
-
-	ret = devm_acpi_dma_controller_register(dev, acpi_dma_simple_xlate,
-						info);
-	if (ret)
-		dev_err(dev, "could not register acpi_dma_controller\n");
-}
-#else /* !CONFIG_ACPI */
-static inline void dw_dma_acpi_controller_register(struct dw_dma *dw) {}
-#endif /* !CONFIG_ACPI */
-
-#ifdef CONFIG_OF
-static struct dw_dma_platform_data *
-dw_dma_parse_dt(struct platform_device *pdev)
-{
-	struct device_node *np = pdev->dev.of_node;
-	struct dw_dma_platform_data *pdata;
-	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS], mb[DW_DMA_MAX_NR_CHANNELS];
-	u32 nr_masters;
-	u32 nr_channels;
-
-	if (!np) {
-		dev_err(&pdev->dev, "Missing DT data\n");
-		return NULL;
-	}
-
-	if (of_property_read_u32(np, "dma-masters", &nr_masters))
-		return NULL;
-	if (nr_masters < 1 || nr_masters > DW_DMA_MAX_NR_MASTERS)
-		return NULL;
-
-	if (of_property_read_u32(np, "dma-channels", &nr_channels))
-		return NULL;
-	if (nr_channels > DW_DMA_MAX_NR_CHANNELS)
-		return NULL;
-
-	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
-		return NULL;
-
-	pdata->nr_masters = nr_masters;
-	pdata->nr_channels = nr_channels;
-
-	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
-		pdata->chan_allocation_order = (unsigned char)tmp;
-
-	if (!of_property_read_u32(np, "chan_priority", &tmp))
-		pdata->chan_priority = tmp;
-
-	if (!of_property_read_u32(np, "block_size", &tmp))
-		pdata->block_size = tmp;
-
-	if (!of_property_read_u32_array(np, "data-width", arr, nr_masters)) {
-		for (tmp = 0; tmp < nr_masters; tmp++)
-			pdata->data_width[tmp] = arr[tmp];
-	} else if (!of_property_read_u32_array(np, "data_width", arr, nr_masters)) {
-		for (tmp = 0; tmp < nr_masters; tmp++)
-			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
-	}
-
-	if (!of_property_read_u32_array(np, "multi-block", mb, nr_channels)) {
-		for (tmp = 0; tmp < nr_channels; tmp++)
-			pdata->multi_block[tmp] = mb[tmp];
-	} else {
-		for (tmp = 0; tmp < nr_channels; tmp++)
-			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
-static inline struct dw_dma_platform_data *
-dw_dma_parse_dt(struct platform_device *pdev)
-{
-	return NULL;
-}
-#endif
-
 static int dw_probe(struct platform_device *pdev)
 {
+	const struct dw_dma_chip_pdata *match;
+	struct dw_dma_chip_pdata *data;
 	struct dw_dma_chip *chip;
 	struct device *dev = &pdev->dev;
-	struct resource *mem;
-	const struct dw_dma_platform_data *pdata;
 	int err;
 
+	match = device_get_match_data(dev);
+	if (!match)
+		return -ENODEV;
+
+	data = devm_kmemdup(&pdev->dev, match, sizeof(*match), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
 	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
@@ -182,8 +47,7 @@ static int dw_probe(struct platform_device *pdev)
 	if (chip->irq < 0)
 		return chip->irq;
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	chip->regs = devm_ioremap_resource(dev, mem);
+	chip->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(chip->regs))
 		return PTR_ERR(chip->regs);
 
@@ -191,13 +55,16 @@ static int dw_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	pdata = dev_get_platdata(dev);
-	if (!pdata)
-		pdata = dw_dma_parse_dt(pdev);
+	if (!data->pdata)
+		data->pdata = dev_get_platdata(dev);
+	if (!data->pdata)
+		data->pdata = dw_dma_parse_dt(pdev);
 
 	chip->dev = dev;
 	chip->id = pdev->id;
-	chip->pdata = pdata;
+	chip->pdata = data->pdata;
+
+	data->chip = chip;
 
 	chip->clk = devm_clk_get(chip->dev, "hclk");
 	if (IS_ERR(chip->clk))
@@ -208,22 +75,15 @@ static int dw_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(&pdev->dev);
 
-	err = dw_dma_probe(chip);
+	err = data->probe(chip);
 	if (err)
 		goto err_dw_dma_probe;
 
-	platform_set_drvdata(pdev, chip);
+	platform_set_drvdata(pdev, data);
 
-	if (pdev->dev.of_node) {
-		err = of_dma_controller_register(pdev->dev.of_node,
-						 dw_dma_of_xlate, chip->dw);
-		if (err)
-			dev_err(&pdev->dev,
-				"could not register of_dma_controller\n");
-	}
+	dw_dma_of_controller_register(chip->dw);
 
-	if (ACPI_HANDLE(&pdev->dev))
-		dw_dma_acpi_controller_register(chip->dw);
+	dw_dma_acpi_controller_register(chip->dw);
 
 	return 0;
 
@@ -235,12 +95,18 @@ err_dw_dma_probe:
 
 static int dw_remove(struct platform_device *pdev)
 {
-	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
+	struct dw_dma_chip_pdata *data = platform_get_drvdata(pdev);
+	struct dw_dma_chip *chip = data->chip;
+	int ret;
+
+	dw_dma_acpi_controller_free(chip->dw);
 
-	if (pdev->dev.of_node)
-		of_dma_controller_free(pdev->dev.of_node);
+	dw_dma_of_controller_free(chip->dw);
+
+	ret = data->remove(chip);
+	if (ret)
+		dev_warn(chip->dev, "can't remove device properly: %d\n", ret);
 
-	dw_dma_remove(chip);
 	pm_runtime_disable(&pdev->dev);
 	clk_disable_unprepare(chip->clk);
 
@@ -249,7 +115,8 @@ static int dw_remove(struct platform_device *pdev)
 
 static void dw_shutdown(struct platform_device *pdev)
 {
-	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
+	struct dw_dma_chip_pdata *data = platform_get_drvdata(pdev);
+	struct dw_dma_chip *chip = data->chip;
 
 	/*
 	 * We have to call do_dw_dma_disable() to stop any ongoing transfer. On
@@ -269,7 +136,7 @@ static void dw_shutdown(struct platform_device *pdev)
 
 #ifdef CONFIG_OF
 static const struct of_device_id dw_dma_of_id_table[] = {
-	{ .compatible = "snps,dma-spear1340" },
+	{ .compatible = "snps,dma-spear1340", .data = &dw_dma_chip_pdata },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);
@@ -277,9 +144,15 @@ MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id dw_dma_acpi_id_table[] = {
-	{ "INTL9C60", 0 },
-	{ "80862286", 0 },
-	{ "808622C0", 0 },
+	{ "INTL9C60", (kernel_ulong_t)&dw_dma_chip_pdata },
+	{ "80862286", (kernel_ulong_t)&dw_dma_chip_pdata },
+	{ "808622C0", (kernel_ulong_t)&dw_dma_chip_pdata },
+
+	/* Elkhart Lake iDMA 32-bit (PSE DMA) */
+	{ "80864BB4", (kernel_ulong_t)&idma32_chip_pdata },
+	{ "80864BB5", (kernel_ulong_t)&idma32_chip_pdata },
+	{ "80864BB6", (kernel_ulong_t)&idma32_chip_pdata },
+
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
@@ -289,7 +162,8 @@ MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
 
 static int dw_suspend_late(struct device *dev)
 {
-	struct dw_dma_chip *chip = dev_get_drvdata(dev);
+	struct dw_dma_chip_pdata *data = dev_get_drvdata(dev);
+	struct dw_dma_chip *chip = data->chip;
 
 	do_dw_dma_disable(chip);
 	clk_disable_unprepare(chip->clk);
@@ -299,7 +173,8 @@ static int dw_suspend_late(struct device *dev)
 
 static int dw_resume_early(struct device *dev)
 {
-	struct dw_dma_chip *chip = dev_get_drvdata(dev);
+	struct dw_dma_chip_pdata *data = dev_get_drvdata(dev);
+	struct dw_dma_chip *chip = data->chip;
 	int ret;
 
 	ret = clk_prepare_enable(chip->clk);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 44d92c34dec3..b1a7ca91701a 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -90,8 +90,21 @@ static void mux_configure8(struct fsl_edma_chan *fsl_chan, void __iomem *addr,
 	iowrite8(val8, addr + off);
 }
 
+static void mux_configure32(struct fsl_edma_chan *fsl_chan, void __iomem *addr,
+			    u32 off, u32 slot, bool enable)
+{
+	u32 val;
+
+	if (enable)
+		val = EDMAMUX_CHCFG_ENBL << 24 | slot;
+	else
+		val = EDMAMUX_CHCFG_DIS;
+
+	iowrite32(val, addr + off * 4);
+}
+
 void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
-			unsigned int slot, bool enable)
+		       unsigned int slot, bool enable)
 {
 	u32 ch = fsl_chan->vchan.chan.chan_id;
 	void __iomem *muxaddr;
@@ -103,7 +116,10 @@ void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
 	muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux];
 	slot = EDMAMUX_CHCFG_SOURCE(slot);
 
-	mux_configure8(fsl_chan, muxaddr, ch_off, slot, enable);
+	if (fsl_chan->edma->drvdata->version == v3)
+		mux_configure32(fsl_chan, muxaddr, ch_off, slot, enable);
+	else
+		mux_configure8(fsl_chan, muxaddr, ch_off, slot, enable);
 }
 EXPORT_SYMBOL_GPL(fsl_edma_chan_mux);
 
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 4e175560292c..5eaa2902ed39 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -125,6 +125,7 @@ struct fsl_edma_chan {
 	dma_addr_t			dma_dev_addr;
 	u32				dma_dev_size;
 	enum dma_data_direction		dma_dir;
+	char				chan_name[16];
 };
 
 struct fsl_edma_desc {
@@ -139,11 +140,13 @@ struct fsl_edma_desc {
 enum edma_version {
 	v1, /* 32ch, Vybrid, mpc57x, etc */
 	v2, /* 64ch Coldfire */
+	v3, /* 32ch, i.mx7ulp */
 };
 
 struct fsl_edma_drvdata {
 	enum edma_version	version;
 	u32			dmamuxs;
+	bool			has_dmaclk;
 	int			(*setup_irq)(struct platform_device *pdev,
 					     struct fsl_edma_engine *fsl_edma);
 };
@@ -153,6 +156,7 @@ struct fsl_edma_engine {
 	void __iomem		*membase;
 	void __iomem		*muxbase[DMAMUX_NR];
 	struct clk		*muxclk[DMAMUX_NR];
+	struct clk		*dmaclk;
 	struct mutex		fsl_edma_mutex;
 	const struct fsl_edma_drvdata *drvdata;
 	u32			n_chans;
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index fcbad6ae954a..b626c06ac2e0 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -20,6 +20,13 @@
 
 #include "fsl-edma-common.h"
 
+static void fsl_edma_synchronize(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+
+	vchan_synchronize(&fsl_chan->vchan);
+}
+
 static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_engine *fsl_edma = dev_id;
@@ -125,16 +132,12 @@ fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma
 	int ret;
 
 	fsl_edma->txirq = platform_get_irq_byname(pdev, "edma-tx");
-	if (fsl_edma->txirq < 0) {
-		dev_err(&pdev->dev, "Can't get edma-tx irq.\n");
+	if (fsl_edma->txirq < 0)
 		return fsl_edma->txirq;
-	}
 
 	fsl_edma->errirq = platform_get_irq_byname(pdev, "edma-err");
-	if (fsl_edma->errirq < 0) {
-		dev_err(&pdev->dev, "Can't get edma-err irq.\n");
+	if (fsl_edma->errirq < 0)
 		return fsl_edma->errirq;
-	}
 
 	if (fsl_edma->txirq == fsl_edma->errirq) {
 		ret = devm_request_irq(&pdev->dev, fsl_edma->txirq,
@@ -162,6 +165,49 @@ fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma
 	return 0;
 }
 
+static int
+fsl_edma2_irq_init(struct platform_device *pdev,
+		   struct fsl_edma_engine *fsl_edma)
+{
+	int i, ret, irq;
+	int count;
+
+	count = platform_irq_count(pdev);
+	dev_dbg(&pdev->dev, "%s Found %d interrupts\r\n", __func__, count);
+	if (count <= 2) {
+		dev_err(&pdev->dev, "Interrupts in DTS not correct.\n");
+		return -EINVAL;
+	}
+	/*
+	 * 16 channel independent interrupts + 1 error interrupt on i.mx7ulp.
+	 * 2 channel share one interrupt, for example, ch0/ch16, ch1/ch17...
+	 * For now, just simply request irq without IRQF_SHARED flag, since 16
+	 * channels are enough on i.mx7ulp whose M4 domain own some peripherals.
+	 */
+	for (i = 0; i < count; i++) {
+		irq = platform_get_irq(pdev, i);
+		if (irq < 0)
+			return -ENXIO;
+
+		sprintf(fsl_edma->chans[i].chan_name, "eDMA2-CH%02d", i);
+
+		/* The last IRQ is for eDMA err */
+		if (i == count - 1)
+			ret = devm_request_irq(&pdev->dev, irq,
+						fsl_edma_err_handler,
+						0, "eDMA2-ERR", fsl_edma);
+		else
+			ret = devm_request_irq(&pdev->dev, irq,
+						fsl_edma_tx_handler, 0,
+						fsl_edma->chans[i].chan_name,
+						fsl_edma);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static void fsl_edma_irq_exit(
 		struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
 {
@@ -187,8 +233,16 @@ static struct fsl_edma_drvdata vf610_data = {
 	.setup_irq = fsl_edma_irq_init,
 };
 
+static struct fsl_edma_drvdata imx7ulp_data = {
+	.version = v3,
+	.dmamuxs = 1,
+	.has_dmaclk = true,
+	.setup_irq = fsl_edma2_irq_init,
+};
+
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", .data = &vf610_data},
+	{ .compatible = "fsl,imx7ulp-edma", .data = &imx7ulp_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids);
@@ -236,6 +290,20 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	fsl_edma_setup_regs(fsl_edma);
 	regs = &fsl_edma->regs;
 
+	if (drvdata->has_dmaclk) {
+		fsl_edma->dmaclk = devm_clk_get(&pdev->dev, "dma");
+		if (IS_ERR(fsl_edma->dmaclk)) {
+			dev_err(&pdev->dev, "Missing DMA block clock.\n");
+			return PTR_ERR(fsl_edma->dmaclk);
+		}
+
+		ret = clk_prepare_enable(fsl_edma->dmaclk);
+		if (ret) {
+			dev_err(&pdev->dev, "DMA clk block failed.\n");
+			return ret;
+		}
+	}
+
 	for (i = 0; i < fsl_edma->drvdata->dmamuxs; i++) {
 		char clkname[32];
 
@@ -302,6 +370,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	fsl_edma->dma_dev.device_pause = fsl_edma_pause;
 	fsl_edma->dma_dev.device_resume = fsl_edma_resume;
 	fsl_edma->dma_dev.device_terminate_all = fsl_edma_terminate_all;
+	fsl_edma->dma_dev.device_synchronize = fsl_edma_synchronize;
 	fsl_edma->dma_dev.device_issue_pending = fsl_edma_issue_pending;
 
 	fsl_edma->dma_dev.src_addr_widths = FSL_EDMA_BUSWIDTHS;
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 8e341c0c13bc..06664fbd2d91 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -758,10 +758,8 @@ fsl_qdma_irq_init(struct platform_device *pdev,
 
 	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");
+	if (fsl_qdma->error_irq < 0)
 		return fsl_qdma->error_irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, fsl_qdma->error_irq,
 			       fsl_qdma_error_handler, 0,
@@ -776,11 +774,8 @@ fsl_qdma_irq_init(struct platform_device *pdev,
 		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);
+		if (fsl_qdma->queue_irq[i] < 0)
 			return fsl_qdma->queue_irq[i];
-		}
 
 		ret = devm_request_irq(&pdev->dev,
 				       fsl_qdma->queue_irq[i],
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 00a089e24150..5c0fb3134825 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -556,6 +556,7 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 		 * We fall-through here intentionally, since a 2D transfer is
 		 * similar to MEMCPY just adding the 2D slot configuration.
 		 */
+		/* Fall through */
 	case IMXDMA_DESC_MEMCPY:
 		imx_dmav1_writel(imxdma, d->src, DMA_SAR(imxdmac->channel));
 		imx_dmav1_writel(imxdma, d->dest, DMA_DAR(imxdmac->channel));
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index a01f4b5d793c..9ba74ab7e912 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1886,10 +1886,6 @@ static int sdma_init(struct sdma_engine *sdma)
 	sdma->context_phys = ccb_phys +
 		MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control);
 
-	/* Zero-out the CCB structures array just allocated */
-	memset(sdma->channel_control, 0,
-			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control));
-
 	/* disable all channels */
 	for (i = 0; i < sdma->drvdata->num_events; i++)
 		writel_relaxed(0, sdma->regs + chnenbl_ofs(sdma, i));
diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c
index 70fd8454d002..be61c32a876f 100644
--- a/drivers/dma/ioat/dca.c
+++ b/drivers/dma/ioat/dca.c
@@ -286,8 +286,7 @@ struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 		return NULL;
 
 	dca = alloc_dca_provider(&ioat_dca_ops,
-				 sizeof(*ioatdca)
-				      + (sizeof(struct ioat_dca_slot) * slots));
+				 struct_size(ioatdca, req_slots, slots));
 	if (!dca)
 		return NULL;
 
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 03f4a588cf7f..a3f942a6a946 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -116,9 +116,9 @@ static void __iop_adma_slot_cleanup(struct iop_adma_chan *iop_chan)
 	list_for_each_entry_safe(iter, _iter, &iop_chan->chain,
 					chain_node) {
 		pr_debug("\tcookie: %d slot: %d busy: %d "
-			"this_desc: %#x next_desc: %#llx ack: %d\n",
+			"this_desc: %pad next_desc: %#llx ack: %d\n",
 			iter->async_tx.cookie, iter->idx, busy,
-			iter->async_tx.phys, (u64)iop_desc_get_next_desc(iter),
+			&iter->async_tx.phys, (u64)iop_desc_get_next_desc(iter),
 			async_tx_test_ack(&iter->async_tx));
 		prefetch(_iter);
 		prefetch(&_iter->async_tx);
@@ -364,13 +364,11 @@ iop_adma_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(tx->chan);
 	struct iop_adma_desc_slot *grp_start, *old_chain_tail;
 	int slot_cnt;
-	int slots_per_op;
 	dma_cookie_t cookie;
 	dma_addr_t next_dma;
 
 	grp_start = sw_desc->group_head;
 	slot_cnt = grp_start->slot_cnt;
-	slots_per_op = grp_start->slots_per_op;
 
 	spin_lock_bh(&iop_chan->lock);
 	cookie = dma_cookie_assign(tx);
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index 546995c20876..f40051d6aecb 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -547,10 +547,8 @@ static int mtk_uart_apdma_probe(struct platform_device *pdev)
 		vchan_init(&c->vc, &mtkd->ddev);
 
 		rc = platform_get_irq(pdev, i);
-		if (rc < 0) {
-			dev_err(&pdev->dev, "failed to get IRQ[%d]\n", i);
+		if (rc < 0)
 			goto err_no_dma;
-		}
 		c->irq = rc;
 	}
 
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index fa5dab481203..e3850f04f676 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -33,7 +33,6 @@
 #define MV_XOR_V2_DMA_IMSG_CDAT_OFF			0x014
 #define MV_XOR_V2_DMA_IMSG_THRD_OFF			0x018
 #define   MV_XOR_V2_DMA_IMSG_THRD_MASK			0x7FFF
-#define   MV_XOR_V2_DMA_IMSG_THRD_SHIFT			0x0
 #define   MV_XOR_V2_DMA_IMSG_TIMER_EN			BIT(18)
 #define MV_XOR_V2_DMA_DESQ_AWATTR_OFF			0x01C
   /* Same flags as MV_XOR_V2_DMA_DESQ_ARATTR_OFF */
@@ -50,7 +49,6 @@
 #define MV_XOR_V2_DMA_DESQ_ADD_OFF			0x808
 #define MV_XOR_V2_DMA_IMSG_TMOT				0x810
 #define   MV_XOR_V2_DMA_IMSG_TIMER_THRD_MASK		0x1FFF
-#define   MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT		0
 
 /* XOR Global registers */
 #define MV_XOR_V2_GLOB_BW_CTRL				0x4
@@ -261,16 +259,15 @@ void mv_xor_v2_enable_imsg_thrd(struct mv_xor_v2_device *xor_dev)
 
 	/* Configure threshold of number of descriptors, and enable timer */
 	reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
-	reg &= (~MV_XOR_V2_DMA_IMSG_THRD_MASK << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
-	reg |= (MV_XOR_V2_DONE_IMSG_THRD << MV_XOR_V2_DMA_IMSG_THRD_SHIFT);
+	reg &= ~MV_XOR_V2_DMA_IMSG_THRD_MASK;
+	reg |= MV_XOR_V2_DONE_IMSG_THRD;
 	reg |= MV_XOR_V2_DMA_IMSG_TIMER_EN;
 	writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_THRD_OFF);
 
 	/* Configure Timer Threshold */
 	reg = readl(xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_TMOT);
-	reg &= (~MV_XOR_V2_DMA_IMSG_TIMER_THRD_MASK <<
-		MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT);
-	reg |= (MV_XOR_V2_TIMER_THRD << MV_XOR_V2_DMA_IMSG_TIMER_THRD_SHIFT);
+	reg &= ~MV_XOR_V2_DMA_IMSG_TIMER_THRD_MASK;
+	reg |= MV_XOR_V2_TIMER_THRD;
 	writel(reg, xor_dev->dma_base + MV_XOR_V2_DMA_IMSG_TMOT);
 }
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 1163af2ba4a3..6cce9ef61b29 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1922,9 +1922,10 @@ static int dmac_alloc_resources(struct pl330_dmac *pl330)
 	if (ret) {
 		dev_err(pl330->ddma.dev, "%s:%d Can't to create channels for DMAC!\n",
 			__func__, __LINE__);
-		dma_free_coherent(pl330->ddma.dev,
+		dma_free_attrs(pl330->ddma.dev,
 				chans * pl330->mcbufsz,
-				pl330->mcode_cpu, pl330->mcode_bus);
+				pl330->mcode_cpu, pl330->mcode_bus,
+				DMA_ATTR_PRIVILEGED);
 		return ret;
 	}
 
@@ -2003,9 +2004,9 @@ static void pl330_del(struct pl330_dmac *pl330)
 	/* Free DMAC resources */
 	dmac_free_threads(pl330);
 
-	dma_free_coherent(pl330->ddma.dev,
+	dma_free_attrs(pl330->ddma.dev,
 		pl330->pcfg.num_chan * pl330->mcbufsz, pl330->mcode_cpu,
-		pl330->mcode_bus);
+		pl330->mcode_bus, DMA_ATTR_PRIVILEGED);
 }
 
 /* forward declaration */
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index 5bf8b145c427..bb4471e84e48 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -749,7 +749,6 @@ struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres,
 	if (!lldev->tre_ring)
 		return NULL;
 
-	memset(lldev->tre_ring, 0, (HIDMA_TRE_SIZE + 1) * nr_tres);
 	lldev->tre_ring_size = HIDMA_TRE_SIZE * nr_tres;
 	lldev->nr_tres = nr_tres;
 
@@ -769,7 +768,6 @@ struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres,
 	if (!lldev->evre_ring)
 		return NULL;
 
-	memset(lldev->evre_ring, 0, (HIDMA_EVRE_SIZE + 1) * nr_tres);
 	lldev->evre_ring_size = HIDMA_EVRE_SIZE * nr_tres;
 
 	/* the EVRE ring has to be EVRE_SIZE aligned */
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 3022d66e7a33..806ca02c52d7 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -183,7 +183,6 @@ static int hidma_mgmt_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "irq resources not found\n");
 		rc = irq;
 		goto out;
 	}
@@ -388,7 +387,6 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 			ret = PTR_ERR(new_pdev);
 			goto out;
 		}
-		of_node_get(child);
 		new_pdev->dev.of_node = child;
 		of_dma_configure(&new_pdev->dev, child, true);
 		/*
@@ -396,9 +394,14 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		 * platforms with or without MSI support.
 		 */
 		of_msi_configure(&new_pdev->dev, child);
-		of_node_put(child);
 	}
+
+	kfree(res);
+
+	return ret;
+
 out:
+	of_node_put(child);
 	kfree(res);
 
 	return ret;
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index ad30f3d2c7f6..43da8eeb18ef 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -1237,11 +1237,8 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 		phy->host = s3cdma;
 
 		phy->irq = platform_get_irq(pdev, i);
-		if (phy->irq < 0) {
-			dev_err(&pdev->dev, "failed to get irq %d, err %d\n",
-				i, phy->irq);
+		if (phy->irq < 0)
 			continue;
-		}
 
 		ret = devm_request_irq(&pdev->dev, phy->irq, s3c24xx_dma_irq,
 				       0, pdev->name, phy);
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 1072c450c37a..3993ab65c62c 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1749,10 +1749,8 @@ static int rcar_dmac_chan_probe(struct rcar_dmac *dmac,
 	/* Request the channel interrupt. */
 	sprintf(pdev_irqname, "ch%u", index);
 	rchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
-	if (rchan->irq < 0) {
-		dev_err(dmac->dev, "no IRQ specified for channel %u\n", index);
+	if (rchan->irq < 0)
 		return -ENODEV;
-	}
 
 	irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:%u",
 				 dev_name(dmac->dev), index);
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index 17063aaf51bc..b218a013c260 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -717,10 +717,8 @@ static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 	/* Request the channel interrupt. */
 	sprintf(pdev_irqname, "ch%u", index);
 	uchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
-	if (uchan->irq < 0) {
-		dev_err(dmac->dev, "no IRQ specified for channel %u\n", index);
+	if (uchan->irq < 0)
 		return -ENODEV;
-	}
 
 	irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:%u",
 				 dev_name(dmac->dev), index);
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index a3ee0f6bb664..67087dbe2f9f 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -771,10 +771,8 @@ static int st_fdma_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, fdev);
 
 	fdev->irq = platform_get_irq(pdev, 0);
-	if (fdev->irq < 0) {
-		dev_err(&pdev->dev, "Failed to get irq resource\n");
+	if (fdev->irq < 0)
 		return -EINVAL;
-	}
 
 	ret = devm_request_irq(&pdev->dev, fdev->irq, st_fdma_irq_handler, 0,
 			       dev_name(&pdev->dev), fdev);
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index ef4d109e7189..5989b0893521 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -243,12 +243,6 @@ static void stm32_dma_write(struct stm32_dma_device *dmadev, u32 reg, u32 val)
 	writel_relaxed(val, dmadev->base + reg);
 }
 
-static struct stm32_dma_desc *stm32_dma_alloc_desc(u32 num_sgs)
-{
-	return kzalloc(sizeof(struct stm32_dma_desc) +
-		       sizeof(struct stm32_dma_sg_req) * num_sgs, GFP_NOWAIT);
-}
-
 static int stm32_dma_get_width(struct stm32_dma_chan *chan,
 			       enum dma_slave_buswidth width)
 {
@@ -853,7 +847,7 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
 		return NULL;
 	}
 
-	desc = stm32_dma_alloc_desc(sg_len);
+	desc = kzalloc(struct_size(desc, sg_req, sg_len), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
@@ -954,7 +948,7 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_cyclic(
 
 	num_periods = buf_len / period_len;
 
-	desc = stm32_dma_alloc_desc(num_periods);
+	desc = kzalloc(struct_size(desc, sg_req, num_periods), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
@@ -989,7 +983,7 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
 	int i;
 
 	num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS);
-	desc = stm32_dma_alloc_desc(num_sgs);
+	desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
@@ -1366,12 +1360,8 @@ static int stm32_dma_probe(struct platform_device *pdev)
 	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
 		chan = &dmadev->chan[i];
 		ret = platform_get_irq(pdev, i);
-		if (ret < 0)  {
-			if (ret != -EPROBE_DEFER)
-				dev_err(&pdev->dev,
-					"No irq resource for chan %d\n", i);
+		if (ret < 0)
 			goto err_unregister;
-		}
 		chan->irq = ret;
 
 		ret = devm_request_irq(&pdev->dev, chan->irq,
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index b552949da14b..3c89bd39e096 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -185,8 +185,7 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	if (!node)
 		return -ENODEV;
 
-	count = device_property_read_u32_array(&pdev->dev, "dma-masters",
-					       NULL, 0);
+	count = device_property_count_u32(&pdev->dev, "dma-masters");
 	if (count < 0) {
 		dev_err(&pdev->dev, "Can't get DMA master(s) node\n");
 		return -ENODEV;
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 1311de74bfdd..5838311cf990 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1555,8 +1555,7 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 			 nr_requests);
 	}
 
-	count = device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
-					       NULL, 0);
+	count = device_property_count_u32(&pdev->dev, "st,ahb-addr-masks");
 	if (count < 0)
 		count = 0;
 
@@ -1638,10 +1637,8 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	}
 
 	dmadev->irq = platform_get_irq(pdev, 0);
-	if (dmadev->irq < 0) {
-		dev_err(&pdev->dev, "failed to get IRQ\n");
+	if (dmadev->irq < 0)
 		return dmadev->irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, dmadev->irq, stm32_mdma_irq_handler,
 			       0, dev_name(&pdev->dev), dmadev);
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index 1f80568b2613..e397a50058c8 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -1132,10 +1132,8 @@ static int sun4i_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->base);
 
 	priv->irq = platform_get_irq(pdev, 0);
-	if (priv->irq < 0) {
-		dev_err(&pdev->dev, "Cannot claim IRQ\n");
+	if (priv->irq < 0)
 		return priv->irq;
-	}
 
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(priv->clk)) {
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index ed5b68dcfe50..06cd7f867f7c 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -1251,10 +1251,8 @@ static int sun6i_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(sdc->base);
 
 	sdc->irq = platform_get_irq(pdev, 0);
-	if (sdc->irq < 0) {
-		dev_err(&pdev->dev, "Cannot claim IRQ\n");
+	if (sdc->irq < 0)
 		return sdc->irq;
-	}
 
 	sdc->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(sdc->clk)) {
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 79e9593815f1..3a45079d11ec 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -152,6 +152,7 @@ struct tegra_dma_sg_req {
 	bool				last_sg;
 	struct list_head		node;
 	struct tegra_dma_desc		*dma_desc;
+	unsigned int			words_xferred;
 };
 
 /*
@@ -496,6 +497,7 @@ static void tegra_dma_configure_for_next(struct tegra_dma_channel *tdc,
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_CSR,
 				nsg_req->ch_regs.csr | TEGRA_APBDMA_CSR_ENB);
 	nsg_req->configured = true;
+	nsg_req->words_xferred = 0;
 
 	tegra_dma_resume(tdc);
 }
@@ -511,6 +513,7 @@ static void tdc_start_head_req(struct tegra_dma_channel *tdc)
 					typeof(*sg_req), node);
 	tegra_dma_start(tdc, sg_req);
 	sg_req->configured = true;
+	sg_req->words_xferred = 0;
 	tdc->busy = true;
 }
 
@@ -638,6 +641,8 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 		list_add_tail(&dma_desc->cb_node, &tdc->cb_desc);
 	dma_desc->cb_count++;
 
+	sgreq->words_xferred = 0;
+
 	/* If not last req then put at end of pending list */
 	if (!list_is_last(&sgreq->node, &tdc->pending_sg_req)) {
 		list_move_tail(&sgreq->node, &tdc->pending_sg_req);
@@ -797,6 +802,65 @@ skip_dma_stop:
 	return 0;
 }
 
+static unsigned int tegra_dma_sg_bytes_xferred(struct tegra_dma_channel *tdc,
+					       struct tegra_dma_sg_req *sg_req)
+{
+	unsigned long status, wcount = 0;
+
+	if (!list_is_first(&sg_req->node, &tdc->pending_sg_req))
+		return 0;
+
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		wcount = tdc_read(tdc, TEGRA_APBDMA_CHAN_WORD_TRANSFER);
+
+	status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
+
+	if (!tdc->tdma->chip_data->support_separate_wcount_reg)
+		wcount = status;
+
+	if (status & TEGRA_APBDMA_STATUS_ISE_EOC)
+		return sg_req->req_len;
+
+	wcount = get_current_xferred_count(tdc, sg_req, wcount);
+
+	if (!wcount) {
+		/*
+		 * If wcount wasn't ever polled for this SG before, then
+		 * simply assume that transfer hasn't started yet.
+		 *
+		 * Otherwise it's the end of the transfer.
+		 *
+		 * The alternative would be to poll the status register
+		 * until EOC bit is set or wcount goes UP. That's so
+		 * because EOC bit is getting set only after the last
+		 * burst's completion and counter is less than the actual
+		 * transfer size by 4 bytes. The counter value wraps around
+		 * in a cyclic mode before EOC is set(!), so we can't easily
+		 * distinguish start of transfer from its end.
+		 */
+		if (sg_req->words_xferred)
+			wcount = sg_req->req_len - 4;
+
+	} else if (wcount < sg_req->words_xferred) {
+		/*
+		 * This case will never happen for a non-cyclic transfer.
+		 *
+		 * For a cyclic transfer, although it is possible for the
+		 * next transfer to have already started (resetting the word
+		 * count), this case should still not happen because we should
+		 * have detected that the EOC bit is set and hence the transfer
+		 * was completed.
+		 */
+		WARN_ON_ONCE(1);
+
+		wcount = sg_req->req_len - 4;
+	} else {
+		sg_req->words_xferred = wcount;
+	}
+
+	return wcount;
+}
+
 static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
@@ -806,6 +870,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	enum dma_status ret;
 	unsigned long flags;
 	unsigned int residual;
+	unsigned int bytes = 0;
 
 	ret = dma_cookie_status(dc, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -825,6 +890,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	list_for_each_entry(sg_req, &tdc->pending_sg_req, node) {
 		dma_desc = sg_req->dma_desc;
 		if (dma_desc->txd.cookie == cookie) {
+			bytes = tegra_dma_sg_bytes_xferred(tdc, sg_req);
 			ret = dma_desc->dma_status;
 			goto found;
 		}
@@ -836,7 +902,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 found:
 	if (dma_desc && txstate) {
 		residual = dma_desc->bytes_requested -
-			   (dma_desc->bytes_transferred %
+			   ((dma_desc->bytes_transferred + bytes) %
 			    dma_desc->bytes_requested);
 		dma_set_residue(txstate, residual);
 	}
@@ -1441,12 +1507,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
 		BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
 	tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	/*
-	 * XXX The hardware appears to support
-	 * DMA_RESIDUE_GRANULARITY_BURST-level reporting, but it's
-	 * only used by this driver during tegra_dma_terminate_all()
-	 */
-	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	tdma->dma_dev.device_config = tegra_dma_slave_config;
 	tdma->dma_dev.device_terminate_all = tegra_dma_terminate_all;
 	tdma->dma_dev.device_tx_status = tegra_dma_tx_status;
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index b33cf6e8ab8e..5f8adf5c1f20 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -42,12 +42,8 @@
 #define ADMA_CH_CONFIG_MAX_BUFS				8
 
 #define ADMA_CH_FIFO_CTRL				0x2c
-#define TEGRA210_ADMA_CH_FIFO_CTRL_OFLWTHRES(val)	(((val) & 0xf) << 24)
-#define TEGRA210_ADMA_CH_FIFO_CTRL_STRVTHRES(val)	(((val) & 0xf) << 16)
 #define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0xf) << 8)
 #define TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(val)		((val) & 0xf)
-#define TEGRA186_ADMA_CH_FIFO_CTRL_OFLWTHRES(val)	(((val) & 0x1f) << 24)
-#define TEGRA186_ADMA_CH_FIFO_CTRL_STRVTHRES(val)	(((val) & 0x1f) << 16)
 #define TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0x1f) << 8)
 #define TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(val)		((val) & 0x1f)
 
@@ -64,14 +60,10 @@
 
 #define TEGRA_ADMA_BURST_COMPLETE_TIME			20
 
-#define TEGRA210_FIFO_CTRL_DEFAULT (TEGRA210_ADMA_CH_FIFO_CTRL_OFLWTHRES(1) | \
-				    TEGRA210_ADMA_CH_FIFO_CTRL_STRVTHRES(1) | \
-				    TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(3)    | \
+#define TEGRA210_FIFO_CTRL_DEFAULT (TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \
 				    TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(3))
 
-#define TEGRA186_FIFO_CTRL_DEFAULT (TEGRA186_ADMA_CH_FIFO_CTRL_OFLWTHRES(1) | \
-				    TEGRA186_ADMA_CH_FIFO_CTRL_STRVTHRES(1) | \
-				    TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(3)    | \
+#define TEGRA186_FIFO_CTRL_DEFAULT (TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \
 				    TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(3))
 
 #define ADMA_CH_REG_FIELD_VAL(val, mask, shift)	(((val) & mask) << shift)
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index ceabdea40ae0..ba7c4f07fcd6 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -15,7 +15,7 @@
 
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
-#include <linux/edma.h>
+#include <linux/bitmap.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -133,6 +133,17 @@
 #define EDMA_CONT_PARAMS_FIXED_EXACT	 1002
 #define EDMA_CONT_PARAMS_FIXED_NOT_EXACT 1003
 
+/*
+ * 64bit array registers are split into two 32bit registers:
+ * reg0: channel/event 0-31
+ * reg1: channel/event 32-63
+ *
+ * bit 5 in the channel number tells the array index (0/1)
+ * bit 0-4 (0x1f) is the bit offset within the register
+ */
+#define EDMA_REG_ARRAY_INDEX(channel)	((channel) >> 5)
+#define EDMA_CHANNEL_BIT(channel)	(BIT((channel) & 0x1f))
+
 /* PaRAM slots are laid out like this */
 struct edmacc_param {
 	u32 opt;
@@ -169,6 +180,7 @@ struct edma_desc {
 	struct list_head		node;
 	enum dma_transfer_direction	direction;
 	int				cyclic;
+	bool				polled;
 	int				absync;
 	int				pset_nr;
 	struct edma_chan		*echan;
@@ -412,12 +424,6 @@ static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
 	edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
 }
 
-static inline void edma_set_bits(int offset, int len, unsigned long *p)
-{
-	for (; len > 0; len--)
-		set_bit(offset + (len - 1), p);
-}
-
 static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
 					  int priority)
 {
@@ -441,15 +447,14 @@ static void edma_setup_interrupt(struct edma_chan *echan, bool enable)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
 	if (enable) {
-		edma_shadow0_write_array(ecc, SH_ICR, channel >> 5,
-					 BIT(channel & 0x1f));
-		edma_shadow0_write_array(ecc, SH_IESR, channel >> 5,
-					 BIT(channel & 0x1f));
+		edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_IESR, idx, ch_bit);
 	} else {
-		edma_shadow0_write_array(ecc, SH_IECR, channel >> 5,
-					 BIT(channel & 0x1f));
+		edma_shadow0_write_array(ecc, SH_IECR, idx, ch_bit);
 	}
 }
 
@@ -587,26 +592,26 @@ static void edma_start(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
 	if (!echan->hw_triggered) {
 		/* EDMA channels without event association */
-		dev_dbg(ecc->dev, "ESR%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_ESR, j));
-		edma_shadow0_write_array(ecc, SH_ESR, j, mask);
+		dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ESR, idx));
+		edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
 	} else {
 		/* EDMA channel with event association */
-		dev_dbg(ecc->dev, "ER%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_ER, j));
+		dev_dbg(ecc->dev, "ER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ER, idx));
 		/* Clear any pending event or error */
-		edma_write_array(ecc, EDMA_ECR, j, mask);
-		edma_write_array(ecc, EDMA_EMCR, j, mask);
+		edma_write_array(ecc, EDMA_ECR, idx, ch_bit);
+		edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 		/* Clear any SER */
-		edma_shadow0_write_array(ecc, SH_SECR, j, mask);
-		edma_shadow0_write_array(ecc, SH_EESR, j, mask);
-		dev_dbg(ecc->dev, "EER%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_EER, j));
+		edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_EESR, idx, ch_bit);
+		dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_EER, idx));
 	}
 }
 
@@ -614,19 +619,19 @@ static void edma_stop(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	edma_shadow0_write_array(ecc, SH_EECR, j, mask);
-	edma_shadow0_write_array(ecc, SH_ECR, j, mask);
-	edma_shadow0_write_array(ecc, SH_SECR, j, mask);
-	edma_write_array(ecc, EDMA_EMCR, j, mask);
+	edma_shadow0_write_array(ecc, SH_EECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 
 	/* clear possibly pending completion interrupt */
-	edma_shadow0_write_array(ecc, SH_ICR, j, mask);
+	edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
 
-	dev_dbg(ecc->dev, "EER%d %08x\n", j,
-		edma_shadow0_read_array(ecc, SH_EER, j));
+	dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_EER, idx));
 
 	/* REVISIT:  consider guarding against inappropriate event
 	 * chaining by overwriting with dummy_paramset.
@@ -640,45 +645,49 @@ static void edma_stop(struct edma_chan *echan)
 static void edma_pause(struct edma_chan *echan)
 {
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
 
-	edma_shadow0_write_array(echan->ecc, SH_EECR, channel >> 5, mask);
+	edma_shadow0_write_array(echan->ecc, SH_EECR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
 }
 
 /* Re-enable EDMA hardware events on the specified channel.  */
 static void edma_resume(struct edma_chan *echan)
 {
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
 
-	edma_shadow0_write_array(echan->ecc, SH_EESR, channel >> 5, mask);
+	edma_shadow0_write_array(echan->ecc, SH_EESR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
 }
 
 static void edma_trigger_channel(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	edma_shadow0_write_array(ecc, SH_ESR, (channel >> 5), mask);
+	edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
 
-	dev_dbg(ecc->dev, "ESR%d %08x\n", (channel >> 5),
-		edma_shadow0_read_array(ecc, SH_ESR, (channel >> 5)));
+	dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_ESR, idx));
 }
 
 static void edma_clean_channel(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	dev_dbg(ecc->dev, "EMR%d %08x\n", j, edma_read_array(ecc, EDMA_EMR, j));
-	edma_shadow0_write_array(ecc, SH_ECR, j, mask);
+	dev_dbg(ecc->dev, "EMR%d %08x\n", idx,
+		edma_read_array(ecc, EDMA_EMR, idx));
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
 	/* Clear the corresponding EMR bits */
-	edma_write_array(ecc, EDMA_EMCR, j, mask);
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 	/* Clear any SER */
-	edma_shadow0_write_array(ecc, SH_SECR, j, mask);
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
 	edma_write(ecc, EDMA_CCERRCLR, BIT(16) | BIT(1) | BIT(0));
 }
 
@@ -708,7 +717,8 @@ static int edma_alloc_channel(struct edma_chan *echan,
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
 
 	/* ensure access through shadow region 0 */
-	edma_or_array2(ecc, EDMA_DRAE, 0, channel >> 5, BIT(channel & 0x1f));
+	edma_or_array2(ecc, EDMA_DRAE, 0, EDMA_REG_ARRAY_INDEX(channel),
+		       EDMA_CHANNEL_BIT(channel));
 
 	/* ensure no events are pending */
 	edma_stop(echan);
@@ -1011,6 +1021,7 @@ static int edma_config_pset(struct dma_chan *chan, struct edma_pset *epset,
 		src_cidx = cidx;
 		dst_bidx = acnt;
 		dst_cidx = cidx;
+		epset->addr = src_addr;
 	} else {
 		dev_err(dev, "%s: direction not implemented yet\n", __func__);
 		return -EINVAL;
@@ -1211,8 +1222,9 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 
 	edesc->pset[0].param.opt |= ITCCHEN;
 	if (nslots == 1) {
-		/* Enable transfer complete interrupt */
-		edesc->pset[0].param.opt |= TCINTEN;
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[0].param.opt |= TCINTEN;
 	} else {
 		/* Enable transfer complete chaining for the first slot */
 		edesc->pset[0].param.opt |= TCCHEN;
@@ -1239,9 +1251,14 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 		}
 
 		edesc->pset[1].param.opt |= ITCCHEN;
-		edesc->pset[1].param.opt |= TCINTEN;
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[1].param.opt |= TCINTEN;
 	}
 
+	if (!(tx_flags & DMA_PREP_INTERRUPT))
+		edesc->polled = true;
+
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
 }
 
@@ -1721,7 +1738,11 @@ static u32 edma_residue(struct edma_desc *edesc)
 	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
 	struct edma_chan *echan = edesc->echan;
 	struct edma_pset *pset = edesc->pset;
-	dma_addr_t done, pos;
+	dma_addr_t done, pos, pos_old;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+	int event_reg;
 	int i;
 
 	/*
@@ -1734,16 +1755,20 @@ static u32 edma_residue(struct edma_desc *edesc)
 	 * "pos" may represent a transfer request that is still being
 	 * processed by the EDMACC or EDMATC. We will busy wait until
 	 * any one of the situations occurs:
-	 *   1. the DMA hardware is idle
-	 *   2. a new transfer request is setup
+	 *   1. while and event is pending for the channel
+	 *   2. a position updated
 	 *   3. we hit the loop limit
 	 */
-	while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) {
-		/* check if a new transfer request is setup */
-		if (edma_get_position(echan->ecc,
-				      echan->slot[0], dst) != pos) {
+	if (is_slave_direction(edesc->direction))
+		event_reg = SH_ER;
+	else
+		event_reg = SH_ESR;
+
+	pos_old = pos;
+	while (edma_shadow0_read_array(echan->ecc, event_reg, idx) & ch_bit) {
+		pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+		if (pos != pos_old)
 			break;
-		}
 
 		if (!--loop_count) {
 			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
@@ -1769,6 +1794,12 @@ static u32 edma_residue(struct edma_desc *edesc)
 	}
 
 	/*
+	 * If the position is 0, then EDMA loaded the closing dummy slot, the
+	 * transfer is completed
+	 */
+	if (!pos)
+		return 0;
+	/*
 	 * For SG operation we catch up with the last processed
 	 * status.
 	 */
@@ -1796,19 +1827,46 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
 				      struct dma_tx_state *txstate)
 {
 	struct edma_chan *echan = to_edma_chan(chan);
-	struct virt_dma_desc *vdesc;
+	struct dma_tx_state txstate_tmp;
 	enum dma_status ret;
 	unsigned long flags;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_COMPLETE || !txstate)
+
+	if (ret == DMA_COMPLETE)
 		return ret;
 
+	/* Provide a dummy dma_tx_state for completion checking */
+	if (!txstate)
+		txstate = &txstate_tmp;
+
 	spin_lock_irqsave(&echan->vchan.lock, flags);
-	if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie)
+	if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
 		txstate->residue = edma_residue(echan->edesc);
-	else if ((vdesc = vchan_find_desc(&echan->vchan, cookie)))
-		txstate->residue = to_edma_desc(&vdesc->tx)->residue;
+	} else {
+		struct virt_dma_desc *vdesc = vchan_find_desc(&echan->vchan,
+							      cookie);
+
+		if (vdesc)
+			txstate->residue = to_edma_desc(&vdesc->tx)->residue;
+		else
+			txstate->residue = 0;
+	}
+
+	/*
+	 * Mark the cookie completed if the residue is 0 for non cyclic
+	 * transfers
+	 */
+	if (ret != DMA_COMPLETE && !txstate->residue &&
+	    echan->edesc && echan->edesc->polled &&
+	    echan->edesc->vdesc.tx.cookie == cookie) {
+		edma_stop(echan);
+		vchan_cookie_complete(&echan->edesc->vdesc);
+		echan->edesc = NULL;
+		edma_execute(echan);
+		ret = DMA_COMPLETE;
+	}
+
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 	return ret;
@@ -2185,11 +2243,13 @@ static struct dma_chan *of_edma_xlate(struct of_phandle_args *dma_spec,
 }
 #endif
 
+static bool edma_filter_fn(struct dma_chan *chan, void *param);
+
 static int edma_probe(struct platform_device *pdev)
 {
 	struct edma_soc_info	*info = pdev->dev.platform_data;
 	s8			(*queue_priority_mapping)[2];
-	int			i, off, ln;
+	int			i, off;
 	const s16		(*rsv_slots)[2];
 	const s16		(*xbar_chans)[2];
 	int			irq;
@@ -2273,21 +2333,22 @@ static int edma_probe(struct platform_device *pdev)
 
 	ecc->default_queue = info->default_queue;
 
-	for (i = 0; i < ecc->num_slots; i++)
-		edma_write_slot(ecc, i, &dummy_paramset);
-
 	if (info->rsv) {
 		/* Set the reserved slots in inuse list */
 		rsv_slots = info->rsv->rsv_slots;
 		if (rsv_slots) {
-			for (i = 0; rsv_slots[i][0] != -1; i++) {
-				off = rsv_slots[i][0];
-				ln = rsv_slots[i][1];
-				edma_set_bits(off, ln, ecc->slot_inuse);
-			}
+			for (i = 0; rsv_slots[i][0] != -1; i++)
+				bitmap_set(ecc->slot_inuse, rsv_slots[i][0],
+					   rsv_slots[i][1]);
 		}
 	}
 
+	for (i = 0; i < ecc->num_slots; i++) {
+		/* Reset only unused - not reserved - paRAM slots */
+		if (!test_bit(i, ecc->slot_inuse))
+			edma_write_slot(ecc, i, &dummy_paramset);
+	}
+
 	/* Clear the xbar mapped channels in unused list */
 	xbar_chans = info->xbar_chans;
 	if (xbar_chans) {
@@ -2366,11 +2427,10 @@ static int edma_probe(struct platform_device *pdev)
 		edma_assign_priority_to_queue(ecc, queue_priority_mapping[i][0],
 					      queue_priority_mapping[i][1]);
 
-	for (i = 0; i < ecc->num_region; i++) {
-		edma_write_array2(ecc, EDMA_DRAE, i, 0, 0x0);
-		edma_write_array2(ecc, EDMA_DRAE, i, 1, 0x0);
-		edma_write_array(ecc, EDMA_QRAE, i, 0x0);
-	}
+	edma_write_array2(ecc, EDMA_DRAE, 0, 0, 0x0);
+	edma_write_array2(ecc, EDMA_DRAE, 0, 1, 0x0);
+	edma_write_array(ecc, EDMA_QRAE, 0, 0x0);
+
 	ecc->info = info;
 
 	/* Init the dma device and channels */
@@ -2482,8 +2542,9 @@ static int edma_pm_resume(struct device *dev)
 	for (i = 0; i < ecc->num_channels; i++) {
 		if (echan[i].alloced) {
 			/* ensure access through shadow region 0 */
-			edma_or_array2(ecc, EDMA_DRAE, 0, i >> 5,
-				       BIT(i & 0x1f));
+			edma_or_array2(ecc, EDMA_DRAE, 0,
+				       EDMA_REG_ARRAY_INDEX(i),
+				       EDMA_CHANNEL_BIT(i));
 
 			edma_setup_interrupt(&echan[i], true);
 
@@ -2524,7 +2585,7 @@ static struct platform_driver edma_tptc_driver = {
 	},
 };
 
-bool edma_filter_fn(struct dma_chan *chan, void *param)
+static bool edma_filter_fn(struct dma_chan *chan, void *param)
 {
 	bool match = false;
 
@@ -2539,7 +2600,6 @@ bool edma_filter_fn(struct dma_chan *chan, void *param)
 	}
 	return match;
 }
-EXPORT_SYMBOL(edma_filter_fn);
 
 static int edma_init(void)
 {
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index d07c0d5de7a2..6b6ba238b81a 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -91,6 +91,7 @@ struct omap_desc {
 	bool using_ll;
 	enum dma_transfer_direction dir;
 	dma_addr_t dev_addr;
+	bool polled;
 
 	int32_t fi;		/* for OMAP_DMA_SYNC_PACKET / double indexing */
 	int16_t ei;		/* for double indexing */
@@ -202,6 +203,7 @@ static const unsigned es_bytes[] = {
 	[CSDP_DATA_TYPE_32] = 4,
 };
 
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param);
 static struct of_dma_filter_info omap_dma_info = {
 	.filter_fn = omap_dma_filter_fn,
 };
@@ -812,31 +814,22 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
-	struct virt_dma_desc *vd;
 	enum dma_status ret;
 	unsigned long flags;
+	struct omap_desc *d = NULL;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-
-	if (!c->paused && c->running) {
-		uint32_t ccr = omap_dma_chan_read(c, CCR);
-		/*
-		 * The channel is no longer active, set the return value
-		 * accordingly
-		 */
-		if (!(ccr & CCR_ENABLE))
-			ret = DMA_COMPLETE;
-	}
-
-	if (ret == DMA_COMPLETE || !txstate)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	vd = vchan_find_desc(&c->vc, cookie);
-	if (vd) {
-		txstate->residue = omap_dma_desc_size(to_omap_dma_desc(&vd->tx));
-	} else if (c->desc && c->desc->vd.tx.cookie == cookie) {
-		struct omap_desc *d = c->desc;
+	if (c->desc && c->desc->vd.tx.cookie == cookie)
+		d = c->desc;
+
+	if (!txstate)
+		goto out;
+
+	if (d) {
 		dma_addr_t pos;
 
 		if (d->dir == DMA_MEM_TO_DEV)
@@ -848,10 +841,31 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 
 		txstate->residue = omap_dma_desc_size_pos(d, pos);
 	} else {
-		txstate->residue = 0;
+		struct virt_dma_desc *vd = vchan_find_desc(&c->vc, cookie);
+
+		if (vd)
+			txstate->residue = omap_dma_desc_size(
+						to_omap_dma_desc(&vd->tx));
+		else
+			txstate->residue = 0;
 	}
-	if (ret == DMA_IN_PROGRESS && c->paused)
+
+out:
+	if (ret == DMA_IN_PROGRESS && c->paused) {
 		ret = DMA_PAUSED;
+	} else if (d && d->polled && c->running) {
+		uint32_t ccr = omap_dma_chan_read(c, CCR);
+		/*
+		 * The channel is no longer active, set the return value
+		 * accordingly and mark it as completed
+		 */
+		if (!(ccr & CCR_ENABLE)) {
+			ret = DMA_COMPLETE;
+			omap_dma_start_desc(c);
+			vchan_cookie_complete(&d->vd);
+		}
+	}
+
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
 	return ret;
@@ -1178,7 +1192,10 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_memcpy(
 	d->ccr = c->ccr;
 	d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_POSTINC;
 
-	d->cicr = CICR_DROP_IE | CICR_FRAME_IE;
+	if (tx_flags & DMA_PREP_INTERRUPT)
+		d->cicr |= CICR_FRAME_IE;
+	else
+		d->polled = true;
 
 	d->csdp = data_type;
 
@@ -1639,7 +1656,7 @@ static struct platform_driver omap_dma_driver = {
 	},
 };
 
-bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
 {
 	if (chan->device->dev->driver == &omap_dma_driver.driver) {
 		struct omap_dmadev *od = to_omap_dma_dev(chan->device);
@@ -1653,7 +1670,6 @@ bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(omap_dma_filter_fn);
 
 static int omap_dma_init(void)
 {
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index ec65a7430dc4..fde54687856b 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -354,11 +354,8 @@ static int uniphier_mdmac_chan_init(struct platform_device *pdev,
 	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);
+	if (irq < 0)
 		return irq;
-	}
 
 	irq_name = devm_kasprintf(dev, GFP_KERNEL, "uniphier-mio-dmac-ch%d",
 				  chan_id);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 957c269ce1fd..cd60fa6d6750 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -1678,20 +1678,16 @@ static int xgene_dma_get_resources(struct platform_device *pdev,
 
 	/* Get DMA error interrupt */
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		dev_err(&pdev->dev, "Failed to get Error IRQ\n");
+	if (irq <= 0)
 		return -ENXIO;
-	}
 
 	pdma->err_irq = irq;
 
 	/* Get DMA Rx ring descriptor interrupts for all DMA channels */
 	for (i = 1; i <= XGENE_DMA_MAX_CHANNEL; i++) {
 		irq = platform_get_irq(pdev, i);
-		if (irq <= 0) {
-			dev_err(&pdev->dev, "Failed to get Rx IRQ\n");
+		if (irq <= 0)
 			return -ENXIO;
-		}
 
 		pdma->chan[i - 1].rx_irq = irq;
 	}