Merge tag 'davinci-for-v3.16/edma' of git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci into next/drivers

Merge "DaVinci EDMA clean-up for v3.16" from Sekhar Nori:

This series makes edma use configuration information available within
the IP instead of reading it from platform data or DT. Some other useful
clean-ups are included too.

* tag 'davinci-for-v3.16/edma' of git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci: (34 commits)
  ARM: edma: Remove redundant/unused parameters from edma_soc_info
  ARM: davinci: Remove redundant/unused parameters for edma
  ARM: dts: am4372: Remove obsolete properties from edma node
  ARM: dts: am33xx: Remove obsolete properties from edma node
  dt/bindings: ti,edma: Remove redundant properties from documentation
  ARM: edma: Get IP configuration from HW (number of channels, tc, etc)
  ARM: edma: Save number of regions from pdata to struct edma
  ARM: edma: Remove num_cc member from struct edma
  ARM: edma: Remove queue_tc_mapping data from edma_soc_info
  ARM: davinci: Remove eDMA3 queue_tc_mapping data from edma_soc_info
  ARM: edma: Do not change TC -> Queue mapping, leave it to default.
  ARM: edma: Take the number of tc from edma_soc_info (pdata)
  ARM: edma: No need to clean the pdata in edma_of_parse_dt()
  ARM: edma: Clean up and simplify the code around irq request
  dmaengine: edma: update DMA memcpy to use new param element
  dmaengine: edma: Document variables used for residue accounting
  dmaengine: edma: Provide granular accounting
  dmaengine: edma: Make reading the position of active channels work
  dmaengine: edma: Store transfer data in edma_desc and edma_pset
  dmaengine: edma: Create private pset struct
  ...

Signed-off-by: Olof Johansson <olof@lixom.net>

11 files changed, 373 insertions, 297 deletions

diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 68ff2137bae7..5ba525a10035 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -2,11 +2,8 @@ TI EDMA
 
 Required properties:
 - compatible : "ti,edma3"
-- ti,edma-regions: Number of regions
-- ti,edma-slots: Number of slots
 - #dma-cells: Should be set to <1>
               Clients should use a single channel number per DMA request.
-- dma-channels: Specify total DMA channels per CC
 - reg: Memory map for accessing module
 - interrupt-parent: Interrupt controller the interrupt is routed through
 - interrupts: Exactly 3 interrupts need to be specified in the order:
@@ -17,6 +14,13 @@ Optional properties:
 - ti,hwmods: Name of the hwmods associated to the EDMA
 - ti,edma-xbar-event-map: Crossbar event to channel map
 
+Deprecated properties:
+Listed here in case one wants to boot an old kernel with new DTB. These
+properties might need to be added to the new DTS files.
+- ti,edma-regions: Number of regions
+- ti,edma-slots: Number of slots
+- dma-channels: Specify total DMA channels per CC
+
 Example:
 
 edma: edma@49000000 {
@@ -26,9 +30,6 @@ edma: edma@49000000 {
 	compatible = "ti,edma3";
 	ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
 	#dma-cells = <1>;
-	dma-channels = <64>;
-	ti,edma-regions = <4>;
-	ti,edma-slots = <256>;
 	ti,edma-xbar-event-map = /bits/ 16 <1 12
 					    2 13>;
 };
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 7ad75b4e0663..99e572c45244 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -147,9 +147,6 @@
 				<0x44e10f90 0x40>;
 			interrupts = <12 13 14>;
 			#dma-cells = <1>;
-			dma-channels = <64>;
-			ti,edma-regions = <4>;
-			ti,edma-slots = <256>;
 		};
 
 		gpio0: gpio@44e07000 {
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index d1f8707ff1df..befb680e5719 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -108,9 +108,6 @@
 					<GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
 					<GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 			#dma-cells = <1>;
-			dma-channels = <64>;
-			ti,edma-regions = <4>;
-			ti,edma-slots = <256>;
 		};
 
 		uart0: serial@44e09000 {
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 5339009b3c0c..485be42519b9 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -102,7 +102,13 @@
 #define PARM_OFFSET(param_no)	(EDMA_PARM + ((param_no) << 5))
 
 #define EDMA_DCHMAP	0x0100  /* 64 registers */
-#define CHMAP_EXIST	BIT(24)
+
+/* CCCFG register */
+#define GET_NUM_DMACH(x)	(x & 0x7) /* bits 0-2 */
+#define GET_NUM_PAENTRY(x)	((x & 0x7000) >> 12) /* bits 12-14 */
+#define GET_NUM_EVQUE(x)	((x & 0x70000) >> 16) /* bits 16-18 */
+#define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
+#define CHMAP_EXIST		BIT(24)
 
 #define EDMA_MAX_DMACH           64
 #define EDMA_MAX_PARAMENTRY     512
@@ -233,7 +239,6 @@ struct edma {
 	unsigned	num_region;
 	unsigned	num_slots;
 	unsigned	num_tc;
-	unsigned	num_cc;
 	enum dma_event_q 	default_queue;
 
 	/* list of channels with no even trigger; terminated by "-1" */
@@ -290,12 +295,6 @@ static void map_dmach_queue(unsigned ctlr, unsigned ch_no,
 			~(0x7 << bit), queue_no << bit);
 }
 
-static void __init map_queue_tc(unsigned ctlr, int queue_no, int tc_no)
-{
-	int bit = queue_no * 4;
-	edma_modify(ctlr, EDMA_QUETCMAP, ~(0x7 << bit), ((tc_no & 0x7) << bit));
-}
-
 static void __init assign_priority_to_queue(unsigned ctlr, int queue_no,
 		int priority)
 {
@@ -994,29 +993,23 @@ void edma_set_dest(unsigned slot, dma_addr_t dest_port,
 EXPORT_SYMBOL(edma_set_dest);
 
 /**
- * edma_get_position - returns the current transfer points
+ * edma_get_position - returns the current transfer point
  * @slot: parameter RAM slot being examined
- * @src: pointer to source port position
- * @dst: pointer to destination port position
+ * @dst:  true selects the dest position, false the source
  *
- * Returns current source and destination addresses for a particular
- * parameter RAM slot.  Its channel should not be active when this is called.
+ * Returns the position of the current active slot
  */
-void edma_get_position(unsigned slot, dma_addr_t *src, dma_addr_t *dst)
+dma_addr_t edma_get_position(unsigned slot, bool dst)
 {
-	struct edmacc_param temp;
-	unsigned ctlr;
+	u32 offs, ctlr = EDMA_CTLR(slot);
 
-	ctlr = EDMA_CTLR(slot);
 	slot = EDMA_CHAN_SLOT(slot);
 
-	edma_read_slot(EDMA_CTLR_CHAN(ctlr, slot), &temp);
-	if (src != NULL)
-		*src = temp.src;
-	if (dst != NULL)
-		*dst = temp.dst;
+	offs = PARM_OFFSET(slot);
+	offs += dst ? PARM_DST : PARM_SRC;
+
+	return edma_read(ctlr, offs);
 }
-EXPORT_SYMBOL(edma_get_position);
 
 /**
  * edma_set_src_index - configure DMA source address indexing
@@ -1421,6 +1414,67 @@ void edma_clear_event(unsigned channel)
 }
 EXPORT_SYMBOL(edma_clear_event);
 
+static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
+			      struct edma *edma_cc)
+{
+	int i;
+	u32 value, cccfg;
+	s8 (*queue_priority_map)[2];
+
+	/* Decode the eDMA3 configuration from CCCFG register */
+	cccfg = edma_read(0, EDMA_CCCFG);
+
+	value = GET_NUM_REGN(cccfg);
+	edma_cc->num_region = BIT(value);
+
+	value = GET_NUM_DMACH(cccfg);
+	edma_cc->num_channels = BIT(value + 1);
+
+	value = GET_NUM_PAENTRY(cccfg);
+	edma_cc->num_slots = BIT(value + 4);
+
+	value = GET_NUM_EVQUE(cccfg);
+	edma_cc->num_tc = value + 1;
+
+	dev_dbg(dev, "eDMA3 HW configuration (cccfg: 0x%08x):\n", cccfg);
+	dev_dbg(dev, "num_region: %u\n", edma_cc->num_region);
+	dev_dbg(dev, "num_channel: %u\n", edma_cc->num_channels);
+	dev_dbg(dev, "num_slot: %u\n", edma_cc->num_slots);
+	dev_dbg(dev, "num_tc: %u\n", edma_cc->num_tc);
+
+	/* Nothing need to be done if queue priority is provided */
+	if (pdata->queue_priority_mapping)
+		return 0;
+
+	/*
+	 * Configure TC/queue priority as follows:
+	 * Q0 - priority 0
+	 * Q1 - priority 1
+	 * Q2 - priority 2
+	 * ...
+	 * The meaning of priority numbers: 0 highest priority, 7 lowest
+	 * priority. So Q0 is the highest priority queue and the last queue has
+	 * the lowest priority.
+	 */
+	queue_priority_map = devm_kzalloc(dev,
+					  (edma_cc->num_tc + 1) * sizeof(s8),
+					  GFP_KERNEL);
+	if (!queue_priority_map)
+		return -ENOMEM;
+
+	for (i = 0; i < edma_cc->num_tc; i++) {
+		queue_priority_map[i][0] = i;
+		queue_priority_map[i][1] = i;
+	}
+	queue_priority_map[i][0] = -1;
+	queue_priority_map[i][1] = -1;
+
+	pdata->queue_priority_mapping = queue_priority_map;
+	pdata->default_queue = 0;
+
+	return 0;
+}
+
 #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_DMADEVICES)
 
 static int edma_xbar_event_map(struct device *dev, struct device_node *node,
@@ -1471,65 +1525,16 @@ static int edma_of_parse_dt(struct device *dev,
 			    struct device_node *node,
 			    struct edma_soc_info *pdata)
 {
-	int ret = 0, i;
-	u32 value;
+	int ret = 0;
 	struct property *prop;
 	size_t sz;
 	struct edma_rsv_info *rsv_info;
-	s8 (*queue_tc_map)[2], (*queue_priority_map)[2];
-
-	memset(pdata, 0, sizeof(struct edma_soc_info));
-
-	ret = of_property_read_u32(node, "dma-channels", &value);
-	if (ret < 0)
-		return ret;
-	pdata->n_channel = value;
-
-	ret = of_property_read_u32(node, "ti,edma-regions", &value);
-	if (ret < 0)
-		return ret;
-	pdata->n_region = value;
-
-	ret = of_property_read_u32(node, "ti,edma-slots", &value);
-	if (ret < 0)
-		return ret;
-	pdata->n_slot = value;
-
-	pdata->n_cc = 1;
 
 	rsv_info = devm_kzalloc(dev, sizeof(struct edma_rsv_info), GFP_KERNEL);
 	if (!rsv_info)
 		return -ENOMEM;
 	pdata->rsv = rsv_info;
 
-	queue_tc_map = devm_kzalloc(dev, 8*sizeof(s8), GFP_KERNEL);
-	if (!queue_tc_map)
-		return -ENOMEM;
-
-	for (i = 0; i < 3; i++) {
-		queue_tc_map[i][0] = i;
-		queue_tc_map[i][1] = i;
-	}
-	queue_tc_map[i][0] = -1;
-	queue_tc_map[i][1] = -1;
-
-	pdata->queue_tc_mapping = queue_tc_map;
-
-	queue_priority_map = devm_kzalloc(dev, 8*sizeof(s8), GFP_KERNEL);
-	if (!queue_priority_map)
-		return -ENOMEM;
-
-	for (i = 0; i < 3; i++) {
-		queue_priority_map[i][0] = i;
-		queue_priority_map[i][1] = i;
-	}
-	queue_priority_map[i][0] = -1;
-	queue_priority_map[i][1] = -1;
-
-	pdata->queue_priority_mapping = queue_priority_map;
-
-	pdata->default_queue = 0;
-
 	prop = of_find_property(node, "ti,edma-xbar-event-map", &sz);
 	if (prop)
 		ret = edma_xbar_event_map(dev, node, pdata, sz);
@@ -1556,6 +1561,7 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev,
 		return ERR_PTR(ret);
 
 	dma_cap_set(DMA_SLAVE, edma_filter_info.dma_cap);
+	dma_cap_set(DMA_CYCLIC, edma_filter_info.dma_cap);
 	of_dma_controller_register(dev->of_node, of_dma_simple_xlate,
 				   &edma_filter_info);
 
@@ -1574,7 +1580,6 @@ static int edma_probe(struct platform_device *pdev)
 	struct edma_soc_info	**info = pdev->dev.platform_data;
 	struct edma_soc_info    *ninfo[EDMA_MAX_CC] = {NULL};
 	s8		(*queue_priority_mapping)[2];
-	s8		(*queue_tc_mapping)[2];
 	int			i, j, off, ln, found = 0;
 	int			status = -1;
 	const s16		(*rsv_chans)[2];
@@ -1585,7 +1590,6 @@ static int edma_probe(struct platform_device *pdev)
 	struct resource		*r[EDMA_MAX_CC] = {NULL};
 	struct resource		res[EDMA_MAX_CC];
 	char			res_name[10];
-	char			irq_name[10];
 	struct device_node	*node = pdev->dev.of_node;
 	struct device		*dev = &pdev->dev;
 	int			ret;
@@ -1650,12 +1654,10 @@ static int edma_probe(struct platform_device *pdev)
 		if (!edma_cc[j])
 			return -ENOMEM;
 
-		edma_cc[j]->num_channels = min_t(unsigned, info[j]->n_channel,
-							EDMA_MAX_DMACH);
-		edma_cc[j]->num_slots = min_t(unsigned, info[j]->n_slot,
-							EDMA_MAX_PARAMENTRY);
-		edma_cc[j]->num_cc = min_t(unsigned, info[j]->n_cc,
-							EDMA_MAX_CC);
+		/* Get eDMA3 configuration from IP */
+		ret = edma_setup_from_hw(dev, info[j], edma_cc[j]);
+		if (ret)
+			return ret;
 
 		edma_cc[j]->default_queue = info[j]->default_queue;
 
@@ -1707,14 +1709,21 @@ static int edma_probe(struct platform_device *pdev)
 
 		if (node) {
 			irq[j] = irq_of_parse_and_map(node, 0);
+			err_irq[j] = irq_of_parse_and_map(node, 2);
 		} else {
+			char irq_name[10];
+
 			sprintf(irq_name, "edma%d", j);
 			irq[j] = platform_get_irq_byname(pdev, irq_name);
+
+			sprintf(irq_name, "edma%d_err", j);
+			err_irq[j] = platform_get_irq_byname(pdev, irq_name);
 		}
 		edma_cc[j]->irq_res_start = irq[j];
-		status = devm_request_irq(&pdev->dev, irq[j],
-					  dma_irq_handler, 0, "edma",
-					  &pdev->dev);
+		edma_cc[j]->irq_res_end = err_irq[j];
+
+		status = devm_request_irq(dev, irq[j], dma_irq_handler, 0,
+					  "edma", dev);
 		if (status < 0) {
 			dev_dbg(&pdev->dev,
 				"devm_request_irq %d failed --> %d\n",
@@ -1722,16 +1731,8 @@ static int edma_probe(struct platform_device *pdev)
 			return status;
 		}
 
-		if (node) {
-			err_irq[j] = irq_of_parse_and_map(node, 2);
-		} else {
-			sprintf(irq_name, "edma%d_err", j);
-			err_irq[j] = platform_get_irq_byname(pdev, irq_name);
-		}
-		edma_cc[j]->irq_res_end = err_irq[j];
-		status = devm_request_irq(&pdev->dev, err_irq[j],
-					  dma_ccerr_handler, 0,
-					  "edma_error", &pdev->dev);
+		status = devm_request_irq(dev, err_irq[j], dma_ccerr_handler, 0,
+					  "edma_error", dev);
 		if (status < 0) {
 			dev_dbg(&pdev->dev,
 				"devm_request_irq %d failed --> %d\n",
@@ -1742,14 +1743,8 @@ static int edma_probe(struct platform_device *pdev)
 		for (i = 0; i < edma_cc[j]->num_channels; i++)
 			map_dmach_queue(j, i, info[j]->default_queue);
 
-		queue_tc_mapping = info[j]->queue_tc_mapping;
 		queue_priority_mapping = info[j]->queue_priority_mapping;
 
-		/* Event queue to TC mapping */
-		for (i = 0; queue_tc_mapping[i][0] != -1; i++)
-			map_queue_tc(j, queue_tc_mapping[i][0],
-					queue_tc_mapping[i][1]);
-
 		/* Event queue priority mapping */
 		for (i = 0; queue_priority_mapping[i][0] != -1; i++)
 			assign_priority_to_queue(j,
@@ -1762,7 +1757,7 @@ static int edma_probe(struct platform_device *pdev)
 		if (edma_read(j, EDMA_CCCFG) & CHMAP_EXIST)
 			map_dmach_param(j);
 
-		for (i = 0; i < info[j]->n_region; i++) {
+		for (i = 0; i < edma_cc[j]->num_region; i++) {
 			edma_write_array2(j, EDMA_DRAE, i, 0, 0x0);
 			edma_write_array2(j, EDMA_DRAE, i, 1, 0x0);
 			edma_write_array(j, EDMA_QRAE, i, 0x0);
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 56ea41d5f849..b85b781b05fd 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -134,13 +134,6 @@ struct platform_device da8xx_serial_device[] = {
 	}
 };
 
-static s8 da8xx_queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{1, 1},
-	{-1, -1}
-};
-
 static s8 da8xx_queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 3},
@@ -148,12 +141,6 @@ static s8 da8xx_queue_priority_mapping[][2] = {
 	{-1, -1}
 };
 
-static s8 da850_queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{-1, -1}
-};
-
 static s8 da850_queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 3},
@@ -161,12 +148,6 @@ static s8 da850_queue_priority_mapping[][2] = {
 };
 
 static struct edma_soc_info da830_edma_cc0_info = {
-	.n_channel		= 32,
-	.n_region		= 4,
-	.n_slot			= 128,
-	.n_tc			= 2,
-	.n_cc			= 1,
-	.queue_tc_mapping	= da8xx_queue_tc_mapping,
 	.queue_priority_mapping	= da8xx_queue_priority_mapping,
 	.default_queue		= EVENTQ_1,
 };
@@ -177,22 +158,10 @@ static struct edma_soc_info *da830_edma_info[EDMA_MAX_CC] = {
 
 static struct edma_soc_info da850_edma_cc_info[] = {
 	{
-		.n_channel		= 32,
-		.n_region		= 4,
-		.n_slot			= 128,
-		.n_tc			= 2,
-		.n_cc			= 1,
-		.queue_tc_mapping	= da8xx_queue_tc_mapping,
 		.queue_priority_mapping	= da8xx_queue_priority_mapping,
 		.default_queue		= EVENTQ_1,
 	},
 	{
-		.n_channel		= 32,
-		.n_region		= 4,
-		.n_slot			= 128,
-		.n_tc			= 1,
-		.n_cc			= 1,
-		.queue_tc_mapping	= da850_queue_tc_mapping,
 		.queue_priority_mapping	= da850_queue_priority_mapping,
 		.default_queue		= EVENTQ_0,
 	},
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 07381d8cea62..2f3ed3a58d57 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -569,14 +569,6 @@ static u8 dm355_default_priorities[DAVINCI_N_AINTC_IRQ] = {
 /*----------------------------------------------------------------------*/
 
 static s8
-queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{1, 1},
-	{-1, -1},
-};
-
-static s8
 queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 3},
@@ -585,12 +577,6 @@ queue_priority_mapping[][2] = {
 };
 
 static struct edma_soc_info edma_cc0_info = {
-	.n_channel		= 64,
-	.n_region		= 4,
-	.n_slot			= 128,
-	.n_tc			= 2,
-	.n_cc			= 1,
-	.queue_tc_mapping	= queue_tc_mapping,
 	.queue_priority_mapping	= queue_priority_mapping,
 	.default_queue		= EVENTQ_1,
 };
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 08a61b938333..0ae8114f5cc9 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -853,16 +853,6 @@ static u8 dm365_default_priorities[DAVINCI_N_AINTC_IRQ] = {
 
 /* Four Transfer Controllers on DM365 */
 static s8
-dm365_queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{1, 1},
-	{2, 2},
-	{3, 3},
-	{-1, -1},
-};
-
-static s8
 dm365_queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 7},
@@ -873,12 +863,6 @@ dm365_queue_priority_mapping[][2] = {
 };
 
 static struct edma_soc_info edma_cc0_info = {
-	.n_channel		= 64,
-	.n_region		= 4,
-	.n_slot			= 256,
-	.n_tc			= 4,
-	.n_cc			= 1,
-	.queue_tc_mapping	= dm365_queue_tc_mapping,
 	.queue_priority_mapping	= dm365_queue_priority_mapping,
 	.default_queue		= EVENTQ_3,
 };
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 5debffba4b24..dc52657909c4 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -499,14 +499,6 @@ static u8 dm644x_default_priorities[DAVINCI_N_AINTC_IRQ] = {
 /*----------------------------------------------------------------------*/
 
 static s8
-queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{1, 1},
-	{-1, -1},
-};
-
-static s8
 queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 3},
@@ -515,12 +507,6 @@ queue_priority_mapping[][2] = {
 };
 
 static struct edma_soc_info edma_cc0_info = {
-	.n_channel		= 64,
-	.n_region		= 4,
-	.n_slot			= 128,
-	.n_tc			= 2,
-	.n_cc			= 1,
-	.queue_tc_mapping	= queue_tc_mapping,
 	.queue_priority_mapping	= queue_priority_mapping,
 	.default_queue		= EVENTQ_1,
 };
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index 332d00d24dc2..6c3bbea7d77d 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -533,16 +533,6 @@ static u8 dm646x_default_priorities[DAVINCI_N_AINTC_IRQ] = {
 
 /* Four Transfer Controllers on DM646x */
 static s8
-dm646x_queue_tc_mapping[][2] = {
-	/* {event queue no, TC no} */
-	{0, 0},
-	{1, 1},
-	{2, 2},
-	{3, 3},
-	{-1, -1},
-};
-
-static s8
 dm646x_queue_priority_mapping[][2] = {
 	/* {event queue no, Priority} */
 	{0, 4},
@@ -553,12 +543,6 @@ dm646x_queue_priority_mapping[][2] = {
 };
 
 static struct edma_soc_info edma_cc0_info = {
-	.n_channel		= 64,
-	.n_region		= 6,	/* 0-1, 4-7 */
-	.n_slot			= 512,
-	.n_tc			= 4,
-	.n_cc			= 1,
-	.queue_tc_mapping	= dm646x_queue_tc_mapping,
 	.queue_priority_mapping	= dm646x_queue_priority_mapping,
 	.default_queue		= EVENTQ_1,
 };
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 926360c2db6a..d08c4dedef35 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -57,14 +57,48 @@
 #define EDMA_MAX_SLOTS		MAX_NR_SG
 #define EDMA_DESCRIPTORS	16
 
+struct edma_pset {
+	u32				len;
+	dma_addr_t			addr;
+	struct edmacc_param		param;
+};
+
 struct edma_desc {
 	struct virt_dma_desc		vdesc;
 	struct list_head		node;
+	enum dma_transfer_direction	direction;
 	int				cyclic;
 	int				absync;
 	int				pset_nr;
+	struct edma_chan		*echan;
 	int				processed;
-	struct edmacc_param		pset[0];
+
+	/*
+	 * The following 4 elements are used for residue accounting.
+	 *
+	 * - processed_stat: the number of SG elements we have traversed
+	 * so far to cover accounting. This is updated directly to processed
+	 * during edma_callback and is always <= processed, because processed
+	 * refers to the number of pending transfer (programmed to EDMA
+	 * controller), where as processed_stat tracks number of transfers
+	 * accounted for so far.
+	 *
+	 * - residue: The amount of bytes we have left to transfer for this desc
+	 *
+	 * - residue_stat: The residue in bytes of data we have covered
+	 * so far for accounting. This is updated directly to residue
+	 * during callbacks to keep it current.
+	 *
+	 * - sg_len: Tracks the length of the current intermediate transfer,
+	 * this is required to update the residue during intermediate transfer
+	 * completion callback.
+	 */
+	int				processed_stat;
+	u32				sg_len;
+	u32				residue;
+	u32				residue_stat;
+
+	struct edma_pset		pset[0];
 };
 
 struct edma_cc;
@@ -136,12 +170,14 @@ static void edma_execute(struct edma_chan *echan)
 	/* Find out how many left */
 	left = edesc->pset_nr - edesc->processed;
 	nslots = min(MAX_NR_SG, left);
+	edesc->sg_len = 0;
 
 	/* Write descriptor PaRAM set(s) */
 	for (i = 0; i < nslots; i++) {
 		j = i + edesc->processed;
-		edma_write_slot(echan->slot[i], &edesc->pset[j]);
-		dev_dbg(echan->vchan.chan.device->dev,
+		edma_write_slot(echan->slot[i], &edesc->pset[j].param);
+		edesc->sg_len += edesc->pset[j].len;
+		dev_vdbg(echan->vchan.chan.device->dev,
 			"\n pset[%d]:\n"
 			"  chnum\t%d\n"
 			"  slot\t%d\n"
@@ -154,14 +190,14 @@ static void edma_execute(struct edma_chan *echan)
 			"  cidx\t%08x\n"
 			"  lkrld\t%08x\n",
 			j, echan->ch_num, echan->slot[i],
-			edesc->pset[j].opt,
-			edesc->pset[j].src,
-			edesc->pset[j].dst,
-			edesc->pset[j].a_b_cnt,
-			edesc->pset[j].ccnt,
-			edesc->pset[j].src_dst_bidx,
-			edesc->pset[j].src_dst_cidx,
-			edesc->pset[j].link_bcntrld);
+			edesc->pset[j].param.opt,
+			edesc->pset[j].param.src,
+			edesc->pset[j].param.dst,
+			edesc->pset[j].param.a_b_cnt,
+			edesc->pset[j].param.ccnt,
+			edesc->pset[j].param.src_dst_bidx,
+			edesc->pset[j].param.src_dst_cidx,
+			edesc->pset[j].param.link_bcntrld);
 		/* Link to the previous slot if not the last set */
 		if (i != (nslots - 1))
 			edma_link(echan->slot[i], echan->slot[i+1]);
@@ -183,7 +219,8 @@ static void edma_execute(struct edma_chan *echan)
 	}
 
 	if (edesc->processed <= MAX_NR_SG) {
-		dev_dbg(dev, "first transfer starting %d\n", echan->ch_num);
+		dev_dbg(dev, "first transfer starting on channel %d\n",
+			echan->ch_num);
 		edma_start(echan->ch_num);
 	} else {
 		dev_dbg(dev, "chan: %d: completed %d elements, resuming\n",
@@ -197,7 +234,7 @@ static void edma_execute(struct edma_chan *echan)
 	 * MAX_NR_SG
 	 */
 	if (echan->missed) {
-		dev_dbg(dev, "missed event in execute detected\n");
+		dev_dbg(dev, "missed event on channel %d\n", echan->ch_num);
 		edma_clean_channel(echan->ch_num);
 		edma_stop(echan->ch_num);
 		edma_start(echan->ch_num);
@@ -242,6 +279,26 @@ static int edma_slave_config(struct edma_chan *echan,
 	return 0;
 }
 
+static int edma_dma_pause(struct edma_chan *echan)
+{
+	/* Pause/Resume only allowed with cyclic mode */
+	if (!echan->edesc->cyclic)
+		return -EINVAL;
+
+	edma_pause(echan->ch_num);
+	return 0;
+}
+
+static int edma_dma_resume(struct edma_chan *echan)
+{
+	/* Pause/Resume only allowed with cyclic mode */
+	if (!echan->edesc->cyclic)
+		return -EINVAL;
+
+	edma_resume(echan->ch_num);
+	return 0;
+}
+
 static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 			unsigned long arg)
 {
@@ -257,6 +314,14 @@ static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		config = (struct dma_slave_config *)arg;
 		ret = edma_slave_config(echan, config);
 		break;
+	case DMA_PAUSE:
+		ret = edma_dma_pause(echan);
+		break;
+
+	case DMA_RESUME:
+		ret = edma_dma_resume(echan);
+		break;
+
 	default:
 		ret = -ENOSYS;
 	}
@@ -275,18 +340,23 @@ static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
  * @dma_length: Total length of the DMA transfer
  * @direction: Direction of the transfer
  */
-static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset,
+static int edma_config_pset(struct dma_chan *chan, struct edma_pset *epset,
 	dma_addr_t src_addr, dma_addr_t dst_addr, u32 burst,
 	enum dma_slave_buswidth dev_width, unsigned int dma_length,
 	enum dma_transfer_direction direction)
 {
 	struct edma_chan *echan = to_edma_chan(chan);
 	struct device *dev = chan->device->dev;
+	struct edmacc_param *param = &epset->param;
 	int acnt, bcnt, ccnt, cidx;
 	int src_bidx, dst_bidx, src_cidx, dst_cidx;
 	int absync;
 
 	acnt = dev_width;
+
+	/* src/dst_maxburst == 0 is the same case as src/dst_maxburst == 1 */
+	if (!burst)
+		burst = 1;
 	/*
 	 * If the maxburst is equal to the fifo width, use
 	 * A-synced transfers. This allows for large contiguous
@@ -337,41 +407,50 @@ static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset,
 		cidx = acnt * bcnt;
 	}
 
+	epset->len = dma_length;
+
 	if (direction == DMA_MEM_TO_DEV) {
 		src_bidx = acnt;
 		src_cidx = cidx;
 		dst_bidx = 0;
 		dst_cidx = 0;
+		epset->addr = src_addr;
 	} else if (direction == DMA_DEV_TO_MEM)  {
 		src_bidx = 0;
 		src_cidx = 0;
 		dst_bidx = acnt;
 		dst_cidx = cidx;
+		epset->addr = dst_addr;
+	} else if (direction == DMA_MEM_TO_MEM)  {
+		src_bidx = acnt;
+		src_cidx = cidx;
+		dst_bidx = acnt;
+		dst_cidx = cidx;
 	} else {
 		dev_err(dev, "%s: direction not implemented yet\n", __func__);
 		return -EINVAL;
 	}
 
-	pset->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+	param->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
 	/* Configure A or AB synchronized transfers */
 	if (absync)
-		pset->opt |= SYNCDIM;
+		param->opt |= SYNCDIM;
 
-	pset->src = src_addr;
-	pset->dst = dst_addr;
+	param->src = src_addr;
+	param->dst = dst_addr;
 
-	pset->src_dst_bidx = (dst_bidx << 16) | src_bidx;
-	pset->src_dst_cidx = (dst_cidx << 16) | src_cidx;
+	param->src_dst_bidx = (dst_bidx << 16) | src_bidx;
+	param->src_dst_cidx = (dst_cidx << 16) | src_cidx;
 
-	pset->a_b_cnt = bcnt << 16 | acnt;
-	pset->ccnt = ccnt;
+	param->a_b_cnt = bcnt << 16 | acnt;
+	param->ccnt = ccnt;
 	/*
 	 * Only time when (bcntrld) auto reload is required is for
 	 * A-sync case, and in this case, a requirement of reload value
 	 * of SZ_64K-1 only is assured. 'link' is initially set to NULL
 	 * and then later will be populated by edma_execute.
 	 */
-	pset->link_bcntrld = 0xffffffff;
+	param->link_bcntrld = 0xffffffff;
 	return absync;
 }
 
@@ -401,23 +480,26 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 		dev_width = echan->cfg.dst_addr_width;
 		burst = echan->cfg.dst_maxburst;
 	} else {
-		dev_err(dev, "%s: bad direction?\n", __func__);
+		dev_err(dev, "%s: bad direction: %d\n", __func__, direction);
 		return NULL;
 	}
 
 	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
-		dev_err(dev, "Undefined slave buswidth\n");
+		dev_err(dev, "%s: Undefined slave buswidth\n", __func__);
 		return NULL;
 	}
 
 	edesc = kzalloc(sizeof(*edesc) + sg_len *
 		sizeof(edesc->pset[0]), GFP_ATOMIC);
 	if (!edesc) {
-		dev_dbg(dev, "Failed to allocate a descriptor\n");
+		dev_err(dev, "%s: Failed to allocate a descriptor\n", __func__);
 		return NULL;
 	}
 
 	edesc->pset_nr = sg_len;
+	edesc->residue = 0;
+	edesc->direction = direction;
+	edesc->echan = echan;
 
 	/* Allocate a PaRAM slot, if needed */
 	nslots = min_t(unsigned, MAX_NR_SG, sg_len);
@@ -429,7 +511,8 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 						EDMA_SLOT_ANY);
 			if (echan->slot[i] < 0) {
 				kfree(edesc);
-				dev_err(dev, "Failed to allocate slot\n");
+				dev_err(dev, "%s: Failed to allocate slot\n",
+					__func__);
 				return NULL;
 			}
 		}
@@ -452,16 +535,56 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 		}
 
 		edesc->absync = ret;
+		edesc->residue += sg_dma_len(sg);
 
 		/* If this is the last in a current SG set of transactions,
 		   enable interrupts so that next set is processed */
 		if (!((i+1) % MAX_NR_SG))
-			edesc->pset[i].opt |= TCINTEN;
+			edesc->pset[i].param.opt |= TCINTEN;
 
 		/* If this is the last set, enable completion interrupt flag */
 		if (i == sg_len - 1)
-			edesc->pset[i].opt |= TCINTEN;
+			edesc->pset[i].param.opt |= TCINTEN;
 	}
+	edesc->residue_stat = edesc->residue;
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+	size_t len, unsigned long tx_flags)
+{
+	int ret;
+	struct edma_desc *edesc;
+	struct device *dev = chan->device->dev;
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	if (unlikely(!echan || !len))
+		return NULL;
+
+	edesc = kzalloc(sizeof(*edesc) + sizeof(edesc->pset[0]), GFP_ATOMIC);
+	if (!edesc) {
+		dev_dbg(dev, "Failed to allocate a descriptor\n");
+		return NULL;
+	}
+
+	edesc->pset_nr = 1;
+
+	ret = edma_config_pset(chan, &edesc->pset[0], src, dest, 1,
+			       DMA_SLAVE_BUSWIDTH_4_BYTES, len, DMA_MEM_TO_MEM);
+	if (ret < 0)
+		return NULL;
+
+	edesc->absync = ret;
+
+	/*
+	 * Enable intermediate transfer chaining to re-trigger channel
+	 * on completion of every TR, and enable transfer-completion
+	 * interrupt on completion of the whole transfer.
+	 */
+	edesc->pset[0].param.opt |= ITCCHEN;
+	edesc->pset[0].param.opt |= TCINTEN;
 
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
 }
@@ -493,12 +616,12 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		dev_width = echan->cfg.dst_addr_width;
 		burst = echan->cfg.dst_maxburst;
 	} else {
-		dev_err(dev, "%s: bad direction?\n", __func__);
+		dev_err(dev, "%s: bad direction: %d\n", __func__, direction);
 		return NULL;
 	}
 
 	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
-		dev_err(dev, "Undefined slave buswidth\n");
+		dev_err(dev, "%s: Undefined slave buswidth\n", __func__);
 		return NULL;
 	}
 
@@ -523,16 +646,18 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 	edesc = kzalloc(sizeof(*edesc) + nslots *
 		sizeof(edesc->pset[0]), GFP_ATOMIC);
 	if (!edesc) {
-		dev_dbg(dev, "Failed to allocate a descriptor\n");
+		dev_err(dev, "%s: Failed to allocate a descriptor\n", __func__);
 		return NULL;
 	}
 
 	edesc->cyclic = 1;
 	edesc->pset_nr = nslots;
+	edesc->residue = edesc->residue_stat = buf_len;
+	edesc->direction = direction;
+	edesc->echan = echan;
 
-	dev_dbg(dev, "%s: nslots=%d\n", __func__, nslots);
-	dev_dbg(dev, "%s: period_len=%d\n", __func__, period_len);
-	dev_dbg(dev, "%s: buf_len=%d\n", __func__, buf_len);
+	dev_dbg(dev, "%s: channel=%d nslots=%d period_len=%zu buf_len=%zu\n",
+		__func__, echan->ch_num, nslots, period_len, buf_len);
 
 	for (i = 0; i < nslots; i++) {
 		/* Allocate a PaRAM slot, if needed */
@@ -542,7 +667,8 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 						EDMA_SLOT_ANY);
 			if (echan->slot[i] < 0) {
 				kfree(edesc);
-				dev_err(dev, "Failed to allocate slot\n");
+				dev_err(dev, "%s: Failed to allocate slot\n",
+					__func__);
 				return NULL;
 			}
 		}
@@ -566,8 +692,8 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		else
 			src_addr += period_len;
 
-		dev_dbg(dev, "%s: Configure period %d of buf:\n", __func__, i);
-		dev_dbg(dev,
+		dev_vdbg(dev, "%s: Configure period %d of buf:\n", __func__, i);
+		dev_vdbg(dev,
 			"\n pset[%d]:\n"
 			"  chnum\t%d\n"
 			"  slot\t%d\n"
@@ -580,14 +706,14 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 			"  cidx\t%08x\n"
 			"  lkrld\t%08x\n",
 			i, echan->ch_num, echan->slot[i],
-			edesc->pset[i].opt,
-			edesc->pset[i].src,
-			edesc->pset[i].dst,
-			edesc->pset[i].a_b_cnt,
-			edesc->pset[i].ccnt,
-			edesc->pset[i].src_dst_bidx,
-			edesc->pset[i].src_dst_cidx,
-			edesc->pset[i].link_bcntrld);
+			edesc->pset[i].param.opt,
+			edesc->pset[i].param.src,
+			edesc->pset[i].param.dst,
+			edesc->pset[i].param.a_b_cnt,
+			edesc->pset[i].param.ccnt,
+			edesc->pset[i].param.src_dst_bidx,
+			edesc->pset[i].param.src_dst_cidx,
+			edesc->pset[i].param.link_bcntrld);
 
 		edesc->absync = ret;
 
@@ -595,7 +721,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		 * Enable interrupts for every period because callback
 		 * has to be called for every period.
 		 */
-		edesc->pset[i].opt |= TCINTEN;
+		edesc->pset[i].param.opt |= TCINTEN;
 	}
 
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
@@ -606,7 +732,6 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 	struct edma_chan *echan = data;
 	struct device *dev = echan->vchan.chan.device->dev;
 	struct edma_desc *edesc;
-	unsigned long flags;
 	struct edmacc_param p;
 
 	edesc = echan->edesc;
@@ -617,27 +742,34 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 
 	switch (ch_status) {
 	case EDMA_DMA_COMPLETE:
-		spin_lock_irqsave(&echan->vchan.lock, flags);
+		spin_lock(&echan->vchan.lock);
 
 		if (edesc) {
 			if (edesc->cyclic) {
 				vchan_cyclic_callback(&edesc->vdesc);
 			} else if (edesc->processed == edesc->pset_nr) {
 				dev_dbg(dev, "Transfer complete, stopping channel %d\n", ch_num);
+				edesc->residue = 0;
 				edma_stop(echan->ch_num);
 				vchan_cookie_complete(&edesc->vdesc);
 				edma_execute(echan);
 			} else {
 				dev_dbg(dev, "Intermediate transfer complete on channel %d\n", ch_num);
+
+				/* Update statistics for tx_status */
+				edesc->residue -= edesc->sg_len;
+				edesc->residue_stat = edesc->residue;
+				edesc->processed_stat = edesc->processed;
+
 				edma_execute(echan);
 			}
 		}
 
-		spin_unlock_irqrestore(&echan->vchan.lock, flags);
+		spin_unlock(&echan->vchan.lock);
 
 		break;
 	case EDMA_DMA_CC_ERROR:
-		spin_lock_irqsave(&echan->vchan.lock, flags);
+		spin_lock(&echan->vchan.lock);
 
 		edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p);
 
@@ -668,7 +800,7 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 			edma_trigger_channel(echan->ch_num);
 		}
 
-		spin_unlock_irqrestore(&echan->vchan.lock, flags);
+		spin_unlock(&echan->vchan.lock);
 
 		break;
 	default:
@@ -704,7 +836,7 @@ static int edma_alloc_chan_resources(struct dma_chan *chan)
 	echan->alloced = true;
 	echan->slot[0] = echan->ch_num;
 
-	dev_dbg(dev, "allocated channel for %u:%u\n",
+	dev_dbg(dev, "allocated channel %d for %u:%u\n", echan->ch_num,
 		EDMA_CTLR(echan->ch_num), EDMA_CHAN_SLOT(echan->ch_num));
 
 	return 0;
@@ -756,23 +888,52 @@ static void edma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 }
 
-static size_t edma_desc_size(struct edma_desc *edesc)
+static u32 edma_residue(struct edma_desc *edesc)
 {
+	bool dst = edesc->direction == DMA_DEV_TO_MEM;
+	struct edma_pset *pset = edesc->pset;
+	dma_addr_t done, pos;
 	int i;
-	size_t size;
-
-	if (edesc->absync)
-		for (size = i = 0; i < edesc->pset_nr; i++)
-			size += (edesc->pset[i].a_b_cnt & 0xffff) *
-				(edesc->pset[i].a_b_cnt >> 16) *
-				 edesc->pset[i].ccnt;
-	else
-		size = (edesc->pset[0].a_b_cnt & 0xffff) *
-			(edesc->pset[0].a_b_cnt >> 16) +
-			(edesc->pset[0].a_b_cnt & 0xffff) *
-			(SZ_64K - 1) * edesc->pset[0].ccnt;
-
-	return size;
+
+	/*
+	 * We always read the dst/src position from the first RamPar
+	 * pset. That's the one which is active now.
+	 */
+	pos = edma_get_position(edesc->echan->slot[0], dst);
+
+	/*
+	 * Cyclic is simple. Just subtract pset[0].addr from pos.
+	 *
+	 * We never update edesc->residue in the cyclic case, so we
+	 * can tell the remaining room to the end of the circular
+	 * buffer.
+	 */
+	if (edesc->cyclic) {
+		done = pos - pset->addr;
+		edesc->residue_stat = edesc->residue - done;
+		return edesc->residue_stat;
+	}
+
+	/*
+	 * For SG operation we catch up with the last processed
+	 * status.
+	 */
+	pset += edesc->processed_stat;
+
+	for (i = edesc->processed_stat; i < edesc->processed; i++, pset++) {
+		/*
+		 * If we are inside this pset address range, we know
+		 * this is the active one. Get the current delta and
+		 * stop walking the psets.
+		 */
+		if (pos >= pset->addr && pos < pset->addr + pset->len)
+			return edesc->residue_stat - (pos - pset->addr);
+
+		/* Otherwise mark it done and update residue_stat. */
+		edesc->processed_stat++;
+		edesc->residue_stat -= pset->len;
+	}
+	return edesc->residue_stat;
 }
 
 /* Check request completion status */
@@ -790,13 +951,10 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
 		return ret;
 
 	spin_lock_irqsave(&echan->vchan.lock, flags);
-	vdesc = vchan_find_desc(&echan->vchan, cookie);
-	if (vdesc) {
-		txstate->residue = edma_desc_size(to_edma_desc(&vdesc->tx));
-	} else if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
-		struct edma_desc *edesc = echan->edesc;
-		txstate->residue = edma_desc_size(edesc);
-	}
+	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;
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 	return ret;
@@ -822,18 +980,43 @@ static void __init edma_chan_init(struct edma_cc *ecc,
 	}
 }
 
+#define EDMA_DMA_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
+
+static int edma_dma_device_slave_caps(struct dma_chan *dchan,
+				      struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = EDMA_DMA_BUSWIDTHS;
+	caps->dstn_addr_widths = EDMA_DMA_BUSWIDTHS;
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = true;
+	caps->cmd_terminate = true;
+	caps->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+
+	return 0;
+}
+
 static void edma_dma_init(struct edma_cc *ecc, struct dma_device *dma,
 			  struct device *dev)
 {
 	dma->device_prep_slave_sg = edma_prep_slave_sg;
 	dma->device_prep_dma_cyclic = edma_prep_dma_cyclic;
+	dma->device_prep_dma_memcpy = edma_prep_dma_memcpy;
 	dma->device_alloc_chan_resources = edma_alloc_chan_resources;
 	dma->device_free_chan_resources = edma_free_chan_resources;
 	dma->device_issue_pending = edma_issue_pending;
 	dma->device_tx_status = edma_tx_status;
 	dma->device_control = edma_control;
+	dma->device_slave_caps = edma_dma_device_slave_caps;
 	dma->dev = dev;
 
+	/*
+	 * code using dma memcpy must make sure alignment of
+	 * length is at dma->copy_align boundary.
+	 */
+	dma->copy_align = DMA_SLAVE_BUSWIDTH_4_BYTES;
+
 	INIT_LIST_HEAD(&dma->channels);
 }
 
@@ -861,6 +1044,8 @@ static int edma_probe(struct platform_device *pdev)
 
 	dma_cap_zero(ecc->dma_slave.cap_mask);
 	dma_cap_set(DMA_SLAVE, ecc->dma_slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, ecc->dma_slave.cap_mask);
+	dma_cap_set(DMA_MEMCPY, ecc->dma_slave.cap_mask);
 
 	edma_dma_init(ecc, &ecc->dma_slave, &pdev->dev);
 
diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h
index f50821cb64be..eb8d5627d080 100644
--- a/include/linux/platform_data/edma.h
+++ b/include/linux/platform_data/edma.h
@@ -43,15 +43,15 @@
 
 /* PaRAM slots are laid out like this */
 struct edmacc_param {
-	unsigned int opt;
-	unsigned int src;
-	unsigned int a_b_cnt;
-	unsigned int dst;
-	unsigned int src_dst_bidx;
-	unsigned int link_bcntrld;
-	unsigned int src_dst_cidx;
-	unsigned int ccnt;
-};
+	u32 opt;
+	u32 src;
+	u32 a_b_cnt;
+	u32 dst;
+	u32 src_dst_bidx;
+	u32 link_bcntrld;
+	u32 src_dst_cidx;
+	u32 ccnt;
+} __packed;
 
 /* fields in edmacc_param.opt */
 #define SAM		BIT(0)
@@ -130,7 +130,7 @@ void edma_set_src(unsigned slot, dma_addr_t src_port,
 				enum address_mode mode, enum fifo_width);
 void edma_set_dest(unsigned slot, dma_addr_t dest_port,
 				 enum address_mode mode, enum fifo_width);
-void edma_get_position(unsigned slot, dma_addr_t *src, dma_addr_t *dst);
+dma_addr_t edma_get_position(unsigned slot, bool dst);
 void edma_set_src_index(unsigned slot, s16 src_bidx, s16 src_cidx);
 void edma_set_dest_index(unsigned slot, s16 dest_bidx, s16 dest_cidx);
 void edma_set_transfer_params(unsigned slot, u16 acnt, u16 bcnt, u16 ccnt,
@@ -158,13 +158,6 @@ struct edma_rsv_info {
 
 /* platform_data for EDMA driver */
 struct edma_soc_info {
-
-	/* how many dma resources of each type */
-	unsigned	n_channel;
-	unsigned	n_region;
-	unsigned	n_slot;
-	unsigned	n_tc;
-	unsigned	n_cc;
 	/*
 	 * Default queue is expected to be a low-priority queue.
 	 * This way, long transfers on the default queue started
@@ -175,7 +168,6 @@ struct edma_soc_info {
 	/* Resource reservation for other cores */
 	struct edma_rsv_info	*rsv;
 
-	s8	(*queue_tc_mapping)[2];
 	s8	(*queue_priority_mapping)[2];
 	const s16	(*xbar_chans)[2];
 };