Merge tag 'dmaengine-4.20-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - Support for ColdFire mcf5441x edma controller

 - Support for link list mode in sprd dma

 - More users of managed dmaenginem_async_device_register API

 - Cyclic mode support in owl dma driver

 - DT updates for renesas drivers, dma-jz4780 updates and support for
   JZ4770, JZ4740 and JZ4725B controllers

 - Removal of deprecated dma_slave_config direction in dmaengine
   drivers, few more users will be removed in next cycle and eventually
   removed.

 - Minor updates to idma64, ioat, pxa, ppc drivers

* tag 'dmaengine-4.20-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (66 commits)
  dmaengine: ppc4xx: fix off-by-one build failure
  dmaengine: owl: Fix warnings generated during build
  dmaengine: fsl-edma: remove dma_slave_config direction usage
  dmaengine: rcar-dmac: set scatter/gather max segment size
  dmaengine: mmp_tdma: remove dma_slave_config direction usage
  dmaengine: ep93xx_dma: remove dma_slave_config direction usage
  dmaengine: k3dma: remove dma_slave_config direction usage
  dmaengine: k3dma: dont use direction for memcpy
  dmaengine: imx-dma: remove dma_slave_config direction usage
  dmaengine: idma: remove dma_slave_config direction usage
  dmaengine: hsu: remove dma_slave_config direction usage
  dmaengine: dw: remove dma_slave_config direction usage
  dmaengine: jz4740: remove dma_slave_config direction usage
  dmaengine: coh901318: remove dma_slave_config direction usage
  dmaengine: bcm2835: remove dma_slave_config direction usage
  dmaengine: at_hdmac: remove dma_slave_config direction usage
  dmaengine: owl: Add Slave and Cyclic mode support for Actions Semi Owl S900 SoC
  dmaengine: ioat: fix prototype of ioat_enumerate_channels
  dmaengine: stm32-dma: check whether length is aligned on FIFO threshold
  dt-bindings: dmaengine: usb-dmac: Add binding for r8a7744
  ...

44 files changed, 1941 insertions, 961 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index dacf3f42426d..de511db021cc 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -143,7 +143,7 @@ config DMA_JZ4740
 
 config DMA_JZ4780
 	tristate "JZ4780 DMA support"
-	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on MIPS || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -321,6 +321,17 @@ config LPC18XX_DMAMUX
 	  Enable support for DMA on NXP LPC18xx/43xx platforms
 	  with PL080 and multiplexed DMA request lines.
 
+config MCF_EDMA
+	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
+	depends on M5441x || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the Freescale ColdFire eDMA engine, 64-channel
+	  implementation that performs complex data transfers with
+	  minimal intervention from a host processor.
+	  This module can be found on Freescale ColdFire mcf5441x SoCs.
+
 config MMP_PDMA
 	bool "MMP PDMA support"
 	depends on ARCH_MMP || ARCH_PXA || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index c91702d88b95..7fcc4d8e336d 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -31,7 +31,8 @@ obj-$(CONFIG_DW_AXI_DMAC) += dw-axi-dmac/
 obj-$(CONFIG_DW_DMAC_CORE) += dw/
 obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
-obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
+obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
+obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 75f38d19fcbe..7cbac6e8c113 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1320,7 +1320,7 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	if (unlikely(!is_slave_direction(direction)))
 		goto err_out;
 
-	if (sconfig->direction == DMA_MEM_TO_DEV)
+	if (direction == DMA_MEM_TO_DEV)
 		reg_width = convert_buswidth(sconfig->dst_addr_width);
 	else
 		reg_width = convert_buswidth(sconfig->src_addr_width);
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 4bf72561667c..4e557684f792 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -1600,7 +1600,7 @@ static void at_xdmac_tasklet(unsigned long data)
 		if (atchan->status & AT_XDMAC_CIS_ROIS)
 			dev_err(chan2dev(&atchan->chan), "request overflow error!!!");
 
-		spin_lock_bh(&atchan->lock);
+		spin_lock(&atchan->lock);
 		desc = list_first_entry(&atchan->xfers_list,
 					struct at_xdmac_desc,
 					xfer_node);
@@ -1610,7 +1610,7 @@ static void at_xdmac_tasklet(unsigned long data)
 		txd = &desc->tx_dma_desc;
 
 		at_xdmac_remove_xfer(atchan, desc);
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock(&atchan->lock);
 
 		if (!at_xdmac_chan_is_cyclic(atchan)) {
 			dma_cookie_complete(txd);
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 847f84a41a69..cad55ab80d41 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -778,14 +778,6 @@ static int bcm2835_dma_slave_config(struct dma_chan *chan,
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
 
-	if ((cfg->direction == DMA_DEV_TO_MEM &&
-	     cfg->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES) ||
-	    (cfg->direction == DMA_MEM_TO_DEV &&
-	     cfg->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES) ||
-	    !is_slave_direction(cfg->direction)) {
-		return -EINVAL;
-	}
-
 	c->cfg = *cfg;
 
 	return 0;
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index da74fd74636b..eebaba3d9e78 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1306,6 +1306,7 @@ struct coh901318_chan {
 	unsigned long nbr_active_done;
 	unsigned long busy;
 
+	struct dma_slave_config config;
 	u32 addr;
 	u32 ctrl;
 
@@ -1402,6 +1403,10 @@ static inline struct coh901318_chan *to_coh901318_chan(struct dma_chan *chan)
 	return container_of(chan, struct coh901318_chan, chan);
 }
 
+static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan,
+					   struct dma_slave_config *config,
+					   enum dma_transfer_direction direction);
+
 static inline const struct coh901318_params *
 cohc_chan_param(struct coh901318_chan *cohc)
 {
@@ -2360,6 +2365,8 @@ coh901318_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (lli == NULL)
 		goto err_dma_alloc;
 
+	coh901318_dma_set_runtimeconfig(chan, &cohc->config, direction);
+
 	/* initiate allocated lli list */
 	ret = coh901318_lli_fill_sg(&cohc->base->pool, lli, sgl, sg_len,
 				    cohc->addr,
@@ -2499,7 +2506,8 @@ static const struct burst_table burst_sizes[] = {
 };
 
 static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan,
-					   struct dma_slave_config *config)
+					   struct dma_slave_config *config,
+					   enum dma_transfer_direction direction)
 {
 	struct coh901318_chan *cohc = to_coh901318_chan(chan);
 	dma_addr_t addr;
@@ -2509,11 +2517,11 @@ static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan,
 	int i = 0;
 
 	/* We only support mem to per or per to mem transfers */
-	if (config->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		addr = config->src_addr;
 		addr_width = config->src_addr_width;
 		maxburst = config->src_maxburst;
-	} else if (config->direction == DMA_MEM_TO_DEV) {
+	} else if (direction == DMA_MEM_TO_DEV) {
 		addr = config->dst_addr;
 		addr_width = config->dst_addr_width;
 		maxburst = config->dst_maxburst;
@@ -2579,6 +2587,16 @@ static int coh901318_dma_set_runtimeconfig(struct dma_chan *chan,
 	return 0;
 }
 
+static int coh901318_dma_slave_config(struct dma_chan *chan,
+					   struct dma_slave_config *config)
+{
+	struct coh901318_chan *cohc = to_coh901318_chan(chan);
+
+	memcpy(&cohc->config, config, sizeof(*config));
+
+	return 0;
+}
+
 static void coh901318_base_init(struct dma_device *dma, const int *pick_chans,
 				struct coh901318_base *base)
 {
@@ -2684,7 +2702,7 @@ static int __init coh901318_probe(struct platform_device *pdev)
 	base->dma_slave.device_prep_slave_sg = coh901318_prep_slave_sg;
 	base->dma_slave.device_tx_status = coh901318_tx_status;
 	base->dma_slave.device_issue_pending = coh901318_issue_pending;
-	base->dma_slave.device_config = coh901318_dma_set_runtimeconfig;
+	base->dma_slave.device_config = coh901318_dma_slave_config;
 	base->dma_slave.device_pause = coh901318_pause;
 	base->dma_slave.device_resume = coh901318_resume;
 	base->dma_slave.device_terminate_all = coh901318_terminate_all;
@@ -2707,7 +2725,7 @@ static int __init coh901318_probe(struct platform_device *pdev)
 	base->dma_memcpy.device_prep_dma_memcpy = coh901318_prep_memcpy;
 	base->dma_memcpy.device_tx_status = coh901318_tx_status;
 	base->dma_memcpy.device_issue_pending = coh901318_issue_pending;
-	base->dma_memcpy.device_config = coh901318_dma_set_runtimeconfig;
+	base->dma_memcpy.device_config = coh901318_dma_slave_config;
 	base->dma_memcpy.device_pause = coh901318_pause;
 	base->dma_memcpy.device_resume = coh901318_resume;
 	base->dma_memcpy.device_terminate_all = coh901318_terminate_all;
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index afd5e10f8927..5253e3c0dc04 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -113,6 +113,7 @@ struct jz4740_dma_desc {
 struct jz4740_dmaengine_chan {
 	struct virt_dma_chan vchan;
 	unsigned int id;
+	struct dma_slave_config config;
 
 	dma_addr_t fifo_addr;
 	unsigned int transfer_shift;
@@ -203,8 +204,9 @@ static enum jz4740_dma_transfer_size jz4740_dma_maxburst(u32 maxburst)
 	return JZ4740_DMA_TRANSFER_SIZE_32BYTE;
 }
 
-static int jz4740_dma_slave_config(struct dma_chan *c,
-				   struct dma_slave_config *config)
+static int jz4740_dma_slave_config_write(struct dma_chan *c,
+				   struct dma_slave_config *config,
+				   enum dma_transfer_direction direction)
 {
 	struct jz4740_dmaengine_chan *chan = to_jz4740_dma_chan(c);
 	struct jz4740_dma_dev *dmadev = jz4740_dma_chan_get_dev(chan);
@@ -214,7 +216,7 @@ static int jz4740_dma_slave_config(struct dma_chan *c,
 	enum jz4740_dma_flags flags;
 	uint32_t cmd;
 
-	switch (config->direction) {
+	switch (direction) {
 	case DMA_MEM_TO_DEV:
 		flags = JZ4740_DMA_SRC_AUTOINC;
 		transfer_size = jz4740_dma_maxburst(config->dst_maxburst);
@@ -265,6 +267,15 @@ static int jz4740_dma_slave_config(struct dma_chan *c,
 	return 0;
 }
 
+static int jz4740_dma_slave_config(struct dma_chan *c,
+				   struct dma_slave_config *config)
+{
+	struct jz4740_dmaengine_chan *chan = to_jz4740_dma_chan(c);
+
+	memcpy(&chan->config, config, sizeof(*config));
+	return 0;
+}
+
 static int jz4740_dma_terminate_all(struct dma_chan *c)
 {
 	struct jz4740_dmaengine_chan *chan = to_jz4740_dma_chan(c);
@@ -407,6 +418,8 @@ static struct dma_async_tx_descriptor *jz4740_dma_prep_slave_sg(
 	desc->direction = direction;
 	desc->cyclic = false;
 
+	jz4740_dma_slave_config_write(c, &chan->config, direction);
+
 	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
 }
 
@@ -438,6 +451,8 @@ static struct dma_async_tx_descriptor *jz4740_dma_prep_dma_cyclic(
 	desc->direction = direction;
 	desc->cyclic = true;
 
+	jz4740_dma_slave_config_write(c, &chan->config, direction);
+
 	return vchan_tx_prep(&chan->vchan, &desc->vdesc, flags);
 }
 
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 85820a2d69d4..a8b6225faa12 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -23,33 +24,35 @@
 #include "dmaengine.h"
 #include "virt-dma.h"
 
-#define JZ_DMA_NR_CHANNELS	32
-
 /* Global registers. */
-#define JZ_DMA_REG_DMAC		0x1000
-#define JZ_DMA_REG_DIRQP	0x1004
-#define JZ_DMA_REG_DDR		0x1008
-#define JZ_DMA_REG_DDRS		0x100c
-#define JZ_DMA_REG_DMACP	0x101c
-#define JZ_DMA_REG_DSIRQP	0x1020
-#define JZ_DMA_REG_DSIRQM	0x1024
-#define JZ_DMA_REG_DCIRQP	0x1028
-#define JZ_DMA_REG_DCIRQM	0x102c
+#define JZ_DMA_REG_DMAC		0x00
+#define JZ_DMA_REG_DIRQP	0x04
+#define JZ_DMA_REG_DDR		0x08
+#define JZ_DMA_REG_DDRS		0x0c
+#define JZ_DMA_REG_DCKE		0x10
+#define JZ_DMA_REG_DCKES	0x14
+#define JZ_DMA_REG_DCKEC	0x18
+#define JZ_DMA_REG_DMACP	0x1c
+#define JZ_DMA_REG_DSIRQP	0x20
+#define JZ_DMA_REG_DSIRQM	0x24
+#define JZ_DMA_REG_DCIRQP	0x28
+#define JZ_DMA_REG_DCIRQM	0x2c
 
 /* Per-channel registers. */
 #define JZ_DMA_REG_CHAN(n)	(n * 0x20)
-#define JZ_DMA_REG_DSA(n)	(0x00 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DTA(n)	(0x04 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DTC(n)	(0x08 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DRT(n)	(0x0c + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DCS(n)	(0x10 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DCM(n)	(0x14 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DDA(n)	(0x18 + JZ_DMA_REG_CHAN(n))
-#define JZ_DMA_REG_DSD(n)	(0x1c + JZ_DMA_REG_CHAN(n))
+#define JZ_DMA_REG_DSA		0x00
+#define JZ_DMA_REG_DTA		0x04
+#define JZ_DMA_REG_DTC		0x08
+#define JZ_DMA_REG_DRT		0x0c
+#define JZ_DMA_REG_DCS		0x10
+#define JZ_DMA_REG_DCM		0x14
+#define JZ_DMA_REG_DDA		0x18
+#define JZ_DMA_REG_DSD		0x1c
 
 #define JZ_DMA_DMAC_DMAE	BIT(0)
 #define JZ_DMA_DMAC_AR		BIT(2)
 #define JZ_DMA_DMAC_HLT		BIT(3)
+#define JZ_DMA_DMAC_FAIC	BIT(27)
 #define JZ_DMA_DMAC_FMSC	BIT(31)
 
 #define JZ_DMA_DRT_AUTO		0x8
@@ -86,6 +89,14 @@
 				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define JZ4780_DMA_CTRL_OFFSET	0x1000
+
+/* macros for use with jz4780_dma_soc_data.flags */
+#define JZ_SOC_DATA_ALLOW_LEGACY_DT	BIT(0)
+#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)
+
 /**
  * struct jz4780_dma_hwdesc - descriptor structure read by the DMA controller.
  * @dcm: value for the DCM (channel command) register
@@ -94,17 +105,12 @@
  * @dtc: transfer count (number of blocks of the transfer size specified in DCM
  * to transfer) in the low 24 bits, offset of the next descriptor from the
  * descriptor base address in the upper 8 bits.
- * @sd: target/source stride difference (in stride transfer mode).
- * @drt: request type
  */
 struct jz4780_dma_hwdesc {
 	uint32_t dcm;
 	uint32_t dsa;
 	uint32_t dta;
 	uint32_t dtc;
-	uint32_t sd;
-	uint32_t drt;
-	uint32_t reserved[2];
 };
 
 /* Size of allocations for hardware descriptor blocks. */
@@ -135,14 +141,22 @@ struct jz4780_dma_chan {
 	unsigned int curr_hwdesc;
 };
 
+struct jz4780_dma_soc_data {
+	unsigned int nb_channels;
+	unsigned int transfer_ord_max;
+	unsigned long flags;
+};
+
 struct jz4780_dma_dev {
 	struct dma_device dma_device;
-	void __iomem *base;
+	void __iomem *chn_base;
+	void __iomem *ctrl_base;
 	struct clk *clk;
 	unsigned int irq;
+	const struct jz4780_dma_soc_data *soc_data;
 
 	uint32_t chan_reserved;
-	struct jz4780_dma_chan chan[JZ_DMA_NR_CHANNELS];
+	struct jz4780_dma_chan chan[];
 };
 
 struct jz4780_dma_filter_data {
@@ -169,16 +183,51 @@ static inline struct jz4780_dma_dev *jz4780_dma_chan_parent(
 			    dma_device);
 }
 
-static inline uint32_t jz4780_dma_readl(struct jz4780_dma_dev *jzdma,
+static inline uint32_t jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma,
+	unsigned int chn, unsigned int reg)
+{
+	return readl(jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
+}
+
+static inline void jz4780_dma_chn_writel(struct jz4780_dma_dev *jzdma,
+	unsigned int chn, unsigned int reg, uint32_t val)
+{
+	writel(val, jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
+}
+
+static inline uint32_t jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma,
 	unsigned int reg)
 {
-	return readl(jzdma->base + reg);
+	return readl(jzdma->ctrl_base + reg);
 }
 
-static inline void jz4780_dma_writel(struct jz4780_dma_dev *jzdma,
+static inline void jz4780_dma_ctrl_writel(struct jz4780_dma_dev *jzdma,
 	unsigned int reg, uint32_t val)
 {
-	writel(val, jzdma->base + reg);
+	writel(val, jzdma->ctrl_base + reg);
+}
+
+static inline void jz4780_dma_chan_enable(struct jz4780_dma_dev *jzdma,
+	unsigned int chn)
+{
+	if (jzdma->soc_data->flags & JZ_SOC_DATA_PER_CHAN_PM) {
+		unsigned int reg;
+
+		if (jzdma->soc_data->flags & JZ_SOC_DATA_NO_DCKES_DCKEC)
+			reg = JZ_DMA_REG_DCKE;
+		else
+			reg = JZ_DMA_REG_DCKES;
+
+		jz4780_dma_ctrl_writel(jzdma, reg, BIT(chn));
+	}
+}
+
+static inline void jz4780_dma_chan_disable(struct jz4780_dma_dev *jzdma,
+	unsigned int chn)
+{
+	if ((jzdma->soc_data->flags & JZ_SOC_DATA_PER_CHAN_PM) &&
+			!(jzdma->soc_data->flags & JZ_SOC_DATA_NO_DCKES_DCKEC))
+		jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DCKEC, BIT(chn));
 }
 
 static struct jz4780_dma_desc *jz4780_dma_desc_alloc(
@@ -215,8 +264,10 @@ static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc)
 	kfree(desc);
 }
 
-static uint32_t jz4780_dma_transfer_size(unsigned long val, uint32_t *shift)
+static uint32_t jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan,
+	unsigned long val, uint32_t *shift)
 {
+	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
 	int ord = ffs(val) - 1;
 
 	/*
@@ -228,8 +279,8 @@ static uint32_t jz4780_dma_transfer_size(unsigned long val, uint32_t *shift)
 	 */
 	if (ord == 3)
 		ord = 2;
-	else if (ord > 7)
-		ord = 7;
+	else if (ord > jzdma->soc_data->transfer_ord_max)
+		ord = jzdma->soc_data->transfer_ord_max;
 
 	*shift = ord;
 
@@ -262,7 +313,6 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 		desc->dcm = JZ_DMA_DCM_SAI;
 		desc->dsa = addr;
 		desc->dta = config->dst_addr;
-		desc->drt = jzchan->transfer_type;
 
 		width = config->dst_addr_width;
 		maxburst = config->dst_maxburst;
@@ -270,7 +320,6 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 		desc->dcm = JZ_DMA_DCM_DAI;
 		desc->dsa = config->src_addr;
 		desc->dta = addr;
-		desc->drt = jzchan->transfer_type;
 
 		width = config->src_addr_width;
 		maxburst = config->src_maxburst;
@@ -283,7 +332,7 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 	 * divisible by the transfer size, and we must not use more than the
 	 * maximum burst specified by the user.
 	 */
-	tsz = jz4780_dma_transfer_size(addr | len | (width * maxburst),
+	tsz = jz4780_dma_transfer_size(jzchan, addr | len | (width * maxburst),
 				       &jzchan->transfer_shift);
 
 	switch (width) {
@@ -412,12 +461,13 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
 	if (!desc)
 		return NULL;
 
-	tsz = jz4780_dma_transfer_size(dest | src | len,
+	tsz = jz4780_dma_transfer_size(jzchan, dest | src | len,
 				       &jzchan->transfer_shift);
 
+	jzchan->transfer_type = JZ_DMA_DRT_AUTO;
+
 	desc->desc[0].dsa = src;
 	desc->desc[0].dta = dest;
-	desc->desc[0].drt = JZ_DMA_DRT_AUTO;
 	desc->desc[0].dcm = JZ_DMA_DCM_TIE | JZ_DMA_DCM_SAI | JZ_DMA_DCM_DAI |
 			    tsz << JZ_DMA_DCM_TSZ_SHIFT |
 			    JZ_DMA_WIDTH_32_BIT << JZ_DMA_DCM_SP_SHIFT |
@@ -472,18 +522,34 @@ static void jz4780_dma_begin(struct jz4780_dma_chan *jzchan)
 			(jzchan->curr_hwdesc + 1) % jzchan->desc->count;
 	}
 
-	/* Use 8-word descriptors. */
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), JZ_DMA_DCS_DES8);
+	/* Enable the channel's clock. */
+	jz4780_dma_chan_enable(jzdma, jzchan->id);
+
+	/* Use 4-word descriptors. */
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DCS, 0);
+
+	/* Set transfer type. */
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DRT,
+			      jzchan->transfer_type);
+
+	/*
+	 * Set the transfer count. This is redundant for a descriptor-driven
+	 * transfer. However, there can be a delay between the transfer start
+	 * time and when DTCn reg contains the new transfer count. Setting
+	 * it explicitly ensures residue is computed correctly at all times.
+	 */
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DTC,
+				jzchan->desc->desc[jzchan->curr_hwdesc].dtc);
 
 	/* Write descriptor address and initiate descriptor fetch. */
 	desc_phys = jzchan->desc->desc_phys +
 		    (jzchan->curr_hwdesc * sizeof(*jzchan->desc->desc));
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DDA(jzchan->id), desc_phys);
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DDRS, BIT(jzchan->id));
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DDA, desc_phys);
+	jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DDRS, BIT(jzchan->id));
 
 	/* Enable the channel. */
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id),
-			  JZ_DMA_DCS_DES8 | JZ_DMA_DCS_CTE);
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DCS,
+			      JZ_DMA_DCS_CTE);
 }
 
 static void jz4780_dma_issue_pending(struct dma_chan *chan)
@@ -509,12 +575,14 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&jzchan->vchan.lock, flags);
 
 	/* Clear the DMA status and stop the transfer. */
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0);
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DCS, 0);
 	if (jzchan->desc) {
 		vchan_terminate_vdesc(&jzchan->desc->vdesc);
 		jzchan->desc = NULL;
 	}
 
+	jz4780_dma_chan_disable(jzdma, jzchan->id);
+
 	vchan_get_all_descriptors(&jzchan->vchan, &head);
 
 	spin_unlock_irqrestore(&jzchan->vchan.lock, flags);
@@ -526,8 +594,10 @@ static int jz4780_dma_terminate_all(struct dma_chan *chan)
 static void jz4780_dma_synchronize(struct dma_chan *chan)
 {
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
+	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
 
 	vchan_synchronize(&jzchan->vchan);
+	jz4780_dma_chan_disable(jzdma, jzchan->id);
 }
 
 static int jz4780_dma_config(struct dma_chan *chan,
@@ -549,21 +619,17 @@ static size_t jz4780_dma_desc_residue(struct jz4780_dma_chan *jzchan,
 	struct jz4780_dma_desc *desc, unsigned int next_sg)
 {
 	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
-	unsigned int residue, count;
+	unsigned int count = 0;
 	unsigned int i;
 
-	residue = 0;
-
 	for (i = next_sg; i < desc->count; i++)
-		residue += desc->desc[i].dtc << jzchan->transfer_shift;
+		count += desc->desc[i].dtc & GENMASK(23, 0);
 
-	if (next_sg != 0) {
-		count = jz4780_dma_readl(jzdma,
-					 JZ_DMA_REG_DTC(jzchan->id));
-		residue += count << jzchan->transfer_shift;
-	}
+	if (next_sg != 0)
+		count += jz4780_dma_chn_readl(jzdma, jzchan->id,
+					 JZ_DMA_REG_DTC);
 
-	return residue;
+	return count << jzchan->transfer_shift;
 }
 
 static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan,
@@ -573,6 +639,7 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan,
 	struct virt_dma_desc *vdesc;
 	enum dma_status status;
 	unsigned long flags;
+	unsigned long residue = 0;
 
 	status = dma_cookie_status(chan, cookie, txstate);
 	if ((status == DMA_COMPLETE) || (txstate == NULL))
@@ -583,13 +650,13 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan,
 	vdesc = vchan_find_desc(&jzchan->vchan, cookie);
 	if (vdesc) {
 		/* On the issued list, so hasn't been processed yet */
-		txstate->residue = jz4780_dma_desc_residue(jzchan,
+		residue = jz4780_dma_desc_residue(jzchan,
 					to_jz4780_dma_desc(vdesc), 0);
 	} else if (cookie == jzchan->desc->vdesc.tx.cookie) {
-		txstate->residue = jz4780_dma_desc_residue(jzchan, jzchan->desc,
-			  (jzchan->curr_hwdesc + 1) % jzchan->desc->count);
-	} else
-		txstate->residue = 0;
+		residue = jz4780_dma_desc_residue(jzchan, jzchan->desc,
+					jzchan->curr_hwdesc + 1);
+	}
+	dma_set_residue(txstate, residue);
 
 	if (vdesc && jzchan->desc && vdesc == &jzchan->desc->vdesc
 	    && jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT))
@@ -606,8 +673,8 @@ static void jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma,
 
 	spin_lock(&jzchan->vchan.lock);
 
-	dcs = jz4780_dma_readl(jzdma, JZ_DMA_REG_DCS(jzchan->id));
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0);
+	dcs = jz4780_dma_chn_readl(jzdma, jzchan->id, JZ_DMA_REG_DCS);
+	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DCS, 0);
 
 	if (dcs & JZ_DMA_DCS_AR) {
 		dev_warn(&jzchan->vchan.chan.dev->device,
@@ -646,9 +713,9 @@ static irqreturn_t jz4780_dma_irq_handler(int irq, void *data)
 	uint32_t pending, dmac;
 	int i;
 
-	pending = jz4780_dma_readl(jzdma, JZ_DMA_REG_DIRQP);
+	pending = jz4780_dma_ctrl_readl(jzdma, JZ_DMA_REG_DIRQP);
 
-	for (i = 0; i < JZ_DMA_NR_CHANNELS; i++) {
+	for (i = 0; i < jzdma->soc_data->nb_channels; i++) {
 		if (!(pending & (1<<i)))
 			continue;
 
@@ -656,12 +723,12 @@ static irqreturn_t jz4780_dma_irq_handler(int irq, void *data)
 	}
 
 	/* Clear halt and address error status of all channels. */
-	dmac = jz4780_dma_readl(jzdma, JZ_DMA_REG_DMAC);
+	dmac = jz4780_dma_ctrl_readl(jzdma, JZ_DMA_REG_DMAC);
 	dmac &= ~(JZ_DMA_DMAC_HLT | JZ_DMA_DMAC_AR);
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DMAC, dmac);
+	jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DMAC, dmac);
 
 	/* Clear interrupt pending status. */
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DIRQP, 0);
+	jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DIRQP, 0);
 
 	return IRQ_HANDLED;
 }
@@ -728,7 +795,7 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 	data.channel = dma_spec->args[1];
 
 	if (data.channel > -1) {
-		if (data.channel >= JZ_DMA_NR_CHANNELS) {
+		if (data.channel >= jzdma->soc_data->nb_channels) {
 			dev_err(jzdma->dma_device.dev,
 				"device requested non-existent channel %u\n",
 				data.channel);
@@ -755,16 +822,29 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 static int jz4780_dma_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	const struct jz4780_dma_soc_data *soc_data;
 	struct jz4780_dma_dev *jzdma;
 	struct jz4780_dma_chan *jzchan;
 	struct dma_device *dd;
 	struct resource *res;
 	int i, ret;
 
-	jzdma = devm_kzalloc(dev, sizeof(*jzdma), GFP_KERNEL);
+	if (!dev->of_node) {
+		dev_err(dev, "This driver must be probed from devicetree\n");
+		return -EINVAL;
+	}
+
+	soc_data = device_get_match_data(dev);
+	if (!soc_data)
+		return -EINVAL;
+
+	jzdma = devm_kzalloc(dev, sizeof(*jzdma)
+				+ sizeof(*jzdma->chan) * soc_data->nb_channels,
+				GFP_KERNEL);
 	if (!jzdma)
 		return -ENOMEM;
 
+	jzdma->soc_data = soc_data;
 	platform_set_drvdata(pdev, jzdma);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -773,9 +853,26 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	jzdma->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(jzdma->base))
-		return PTR_ERR(jzdma->base);
+	jzdma->chn_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(jzdma->chn_base))
+		return PTR_ERR(jzdma->chn_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (res) {
+		jzdma->ctrl_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(jzdma->ctrl_base))
+			return PTR_ERR(jzdma->ctrl_base);
+	} else if (soc_data->flags & JZ_SOC_DATA_ALLOW_LEGACY_DT) {
+		/*
+		 * On JZ4780, if the second memory resource was not supplied,
+		 * assume we're using an old devicetree, and calculate the
+		 * offset to the control registers.
+		 */
+		jzdma->ctrl_base = jzdma->chn_base + JZ4780_DMA_CTRL_OFFSET;
+	} else {
+		dev_err(dev, "failed to get I/O memory\n");
+		return -EINVAL;
+	}
 
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0) {
@@ -833,13 +930,15 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	 * Also set the FMSC bit - it increases MSC performance, so it makes
 	 * little sense not to enable it.
 	 */
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DMAC,
-			  JZ_DMA_DMAC_DMAE | JZ_DMA_DMAC_FMSC);
-	jz4780_dma_writel(jzdma, JZ_DMA_REG_DMACP, 0);
+	jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DMAC, JZ_DMA_DMAC_DMAE |
+			       JZ_DMA_DMAC_FAIC | JZ_DMA_DMAC_FMSC);
+
+	if (soc_data->flags & JZ_SOC_DATA_PROGRAMMABLE_DMA)
+		jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DMACP, 0);
 
 	INIT_LIST_HEAD(&dd->channels);
 
-	for (i = 0; i < JZ_DMA_NR_CHANNELS; i++) {
+	for (i = 0; i < soc_data->nb_channels; i++) {
 		jzchan = &jzdma->chan[i];
 		jzchan->id = i;
 
@@ -847,7 +946,7 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 		jzchan->vchan.desc_free = jz4780_dma_desc_free;
 	}
 
-	ret = dma_async_device_register(dd);
+	ret = dmaenginem_async_device_register(dd);
 	if (ret) {
 		dev_err(dev, "failed to register device\n");
 		goto err_disable_clk;
@@ -858,15 +957,12 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 					 jzdma);
 	if (ret) {
 		dev_err(dev, "failed to register OF DMA controller\n");
-		goto err_unregister_dev;
+		goto err_disable_clk;
 	}
 
 	dev_info(dev, "JZ4780 DMA controller initialised\n");
 	return 0;
 
-err_unregister_dev:
-	dma_async_device_unregister(dd);
-
 err_disable_clk:
 	clk_disable_unprepare(jzdma->clk);
 
@@ -884,15 +980,40 @@ static int jz4780_dma_remove(struct platform_device *pdev)
 
 	free_irq(jzdma->irq, jzdma);
 
-	for (i = 0; i < JZ_DMA_NR_CHANNELS; i++)
+	for (i = 0; i < jzdma->soc_data->nb_channels; i++)
 		tasklet_kill(&jzdma->chan[i].vchan.task);
 
-	dma_async_device_unregister(&jzdma->dma_device);
 	return 0;
 }
 
+static const struct jz4780_dma_soc_data jz4740_dma_soc_data = {
+	.nb_channels = 6,
+	.transfer_ord_max = 5,
+};
+
+static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = {
+	.nb_channels = 6,
+	.transfer_ord_max = 5,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
+static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
+	.nb_channels = 6,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
+static const struct jz4780_dma_soc_data jz4780_dma_soc_data = {
+	.nb_channels = 32,
+	.transfer_ord_max = 7,
+	.flags = JZ_SOC_DATA_ALLOW_LEGACY_DT | JZ_SOC_DATA_PROGRAMMABLE_DMA,
+};
+
 static const struct of_device_id jz4780_dma_dt_match[] = {
-	{ .compatible = "ingenic,jz4780-dma", .data = NULL },
+	{ .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data },
+	{ .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data },
+	{ .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data },
+	{ .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data },
 	{},
 };
 MODULE_DEVICE_TABLE(of, jz4780_dma_dt_match);
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index c4eb55e3011c..b2ac1d2c5b86 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -934,7 +934,7 @@ static int dw_probe(struct platform_device *pdev)
 
 	pm_runtime_put(chip->dev);
 
-	ret = dma_async_device_register(&dw->dma);
+	ret = dmaenginem_async_device_register(&dw->dma);
 	if (ret)
 		goto err_pm_disable;
 
@@ -977,8 +977,6 @@ static int dw_remove(struct platform_device *pdev)
 		tasklet_kill(&chan->vc.task);
 	}
 
-	dma_async_device_unregister(&dw->dma);
-
 	return 0;
 }
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index f43e6dafe446..d0c3e50b39fb 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -886,12 +886,7 @@ static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 	 */
 	u32 s = dw->pdata->is_idma32 ? 1 : 2;
 
-	/* Check if chan will be configured for slave transfers */
-	if (!is_slave_direction(sconfig->direction))
-		return -EINVAL;
-
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
-	dwc->direction = sconfig->direction;
 
 	sc->src_maxburst = sc->src_maxburst > 1 ? fls(sc->src_maxburst) - s : 0;
 	sc->dst_maxburst = sc->dst_maxburst > 1 ? fls(sc->dst_maxburst) - s : 0;
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index f62dd0944908..f01b2c173fa6 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -284,6 +284,8 @@ 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 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index a15592383d4e..f674eb5fbbef 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -109,6 +109,9 @@
 #define DMA_MAX_CHAN_DESCRIPTORS	32
 
 struct ep93xx_dma_engine;
+static int ep93xx_dma_slave_config_write(struct dma_chan *chan,
+					 enum dma_transfer_direction dir,
+					 struct dma_slave_config *config);
 
 /**
  * struct ep93xx_dma_desc - EP93xx specific transaction descriptor
@@ -180,6 +183,7 @@ struct ep93xx_dma_chan {
 	struct list_head		free_list;
 	u32				runtime_addr;
 	u32				runtime_ctrl;
+	struct dma_slave_config		slave_config;
 };
 
 /**
@@ -1051,6 +1055,8 @@ ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		return NULL;
 	}
 
+	ep93xx_dma_slave_config_write(chan, dir, &edmac->slave_config);
+
 	first = NULL;
 	for_each_sg(sgl, sg, sg_len, i) {
 		size_t len = sg_dma_len(sg);
@@ -1136,6 +1142,8 @@ ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 		return NULL;
 	}
 
+	ep93xx_dma_slave_config_write(chan, dir, &edmac->slave_config);
+
 	/* Split the buffer into period size chunks */
 	first = NULL;
 	for (offset = 0; offset < buf_len; offset += period_len) {
@@ -1227,6 +1235,17 @@ static int ep93xx_dma_slave_config(struct dma_chan *chan,
 				   struct dma_slave_config *config)
 {
 	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
+
+	memcpy(&edmac->slave_config, config, sizeof(*config));
+
+	return 0;
+}
+
+static int ep93xx_dma_slave_config_write(struct dma_chan *chan,
+					 enum dma_transfer_direction dir,
+					 struct dma_slave_config *config)
+{
+	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
 	enum dma_slave_buswidth width;
 	unsigned long flags;
 	u32 addr, ctrl;
@@ -1234,7 +1253,7 @@ static int ep93xx_dma_slave_config(struct dma_chan *chan,
 	if (!edmac->edma->m2m)
 		return -EINVAL;
 
-	switch (config->direction) {
+	switch (dir) {
 	case DMA_DEV_TO_MEM:
 		width = config->src_addr_width;
 		addr = config->src_addr;
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
new file mode 100644
index 000000000000..8876c4c1bb2c
--- /dev/null
+++ b/drivers/dma/fsl-edma-common.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2013-2014 Freescale Semiconductor, Inc
+// Copyright (c) 2017 Sysam, Angelo Dureghello  <angelo@sysam.it>
+
+#include <linux/dmapool.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "fsl-edma-common.h"
+
+#define EDMA_CR			0x00
+#define EDMA_ES			0x04
+#define EDMA_ERQ		0x0C
+#define EDMA_EEI		0x14
+#define EDMA_SERQ		0x1B
+#define EDMA_CERQ		0x1A
+#define EDMA_SEEI		0x19
+#define EDMA_CEEI		0x18
+#define EDMA_CINT		0x1F
+#define EDMA_CERR		0x1E
+#define EDMA_SSRT		0x1D
+#define EDMA_CDNE		0x1C
+#define EDMA_INTR		0x24
+#define EDMA_ERR		0x2C
+
+#define EDMA64_ERQH		0x08
+#define EDMA64_EEIH		0x10
+#define EDMA64_SERQ		0x18
+#define EDMA64_CERQ		0x19
+#define EDMA64_SEEI		0x1a
+#define EDMA64_CEEI		0x1b
+#define EDMA64_CINT		0x1c
+#define EDMA64_CERR		0x1d
+#define EDMA64_SSRT		0x1e
+#define EDMA64_CDNE		0x1f
+#define EDMA64_INTH		0x20
+#define EDMA64_INTL		0x24
+#define EDMA64_ERRH		0x28
+#define EDMA64_ERRL		0x2c
+
+#define EDMA_TCD		0x1000
+
+static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan)
+{
+	struct edma_regs *regs = &fsl_chan->edma->regs;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	if (fsl_chan->edma->version == v1) {
+		edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), regs->seei);
+		edma_writeb(fsl_chan->edma, ch, regs->serq);
+	} else {
+		/* ColdFire is big endian, and accesses natively
+		 * big endian I/O peripherals
+		 */
+		iowrite8(EDMA_SEEI_SEEI(ch), regs->seei);
+		iowrite8(ch, regs->serq);
+	}
+}
+
+void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan)
+{
+	struct edma_regs *regs = &fsl_chan->edma->regs;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	if (fsl_chan->edma->version == v1) {
+		edma_writeb(fsl_chan->edma, ch, regs->cerq);
+		edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), regs->ceei);
+	} else {
+		/* ColdFire is big endian, and accesses natively
+		 * big endian I/O peripherals
+		 */
+		iowrite8(ch, regs->cerq);
+		iowrite8(EDMA_CEEI_CEEI(ch), regs->ceei);
+	}
+}
+EXPORT_SYMBOL_GPL(fsl_edma_disable_request);
+
+void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
+			unsigned int slot, bool enable)
+{
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+	void __iomem *muxaddr;
+	unsigned int chans_per_mux, ch_off;
+
+	chans_per_mux = fsl_chan->edma->n_chans / DMAMUX_NR;
+	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
+	muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux];
+	slot = EDMAMUX_CHCFG_SOURCE(slot);
+
+	if (enable)
+		iowrite8(EDMAMUX_CHCFG_ENBL | slot, muxaddr + ch_off);
+	else
+		iowrite8(EDMAMUX_CHCFG_DIS, muxaddr + ch_off);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_chan_mux);
+
+static unsigned int fsl_edma_get_tcd_attr(enum dma_slave_buswidth addr_width)
+{
+	switch (addr_width) {
+	case 1:
+		return EDMA_TCD_ATTR_SSIZE_8BIT | EDMA_TCD_ATTR_DSIZE_8BIT;
+	case 2:
+		return EDMA_TCD_ATTR_SSIZE_16BIT | EDMA_TCD_ATTR_DSIZE_16BIT;
+	case 4:
+		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
+	case 8:
+		return EDMA_TCD_ATTR_SSIZE_64BIT | EDMA_TCD_ATTR_DSIZE_64BIT;
+	default:
+		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
+	}
+}
+
+void fsl_edma_free_desc(struct virt_dma_desc *vdesc)
+{
+	struct fsl_edma_desc *fsl_desc;
+	int i;
+
+	fsl_desc = to_fsl_edma_desc(vdesc);
+	for (i = 0; i < fsl_desc->n_tcds; i++)
+		dma_pool_free(fsl_desc->echan->tcd_pool, fsl_desc->tcd[i].vtcd,
+			      fsl_desc->tcd[i].ptcd);
+	kfree(fsl_desc);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_free_desc);
+
+int fsl_edma_terminate_all(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	fsl_edma_disable_request(fsl_chan);
+	fsl_chan->edesc = NULL;
+	fsl_chan->idle = true;
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_terminate_all);
+
+int fsl_edma_pause(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	if (fsl_chan->edesc) {
+		fsl_edma_disable_request(fsl_chan);
+		fsl_chan->status = DMA_PAUSED;
+		fsl_chan->idle = true;
+	}
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_pause);
+
+int fsl_edma_resume(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	if (fsl_chan->edesc) {
+		fsl_edma_enable_request(fsl_chan);
+		fsl_chan->status = DMA_IN_PROGRESS;
+		fsl_chan->idle = false;
+	}
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_resume);
+
+int fsl_edma_slave_config(struct dma_chan *chan,
+				 struct dma_slave_config *cfg)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+
+	memcpy(&fsl_chan->cfg, cfg, sizeof(*cfg));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_slave_config);
+
+static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
+		struct virt_dma_desc *vdesc, bool in_progress)
+{
+	struct fsl_edma_desc *edesc = fsl_chan->edesc;
+	struct edma_regs *regs = &fsl_chan->edma->regs;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+	enum dma_transfer_direction dir = edesc->dirn;
+	dma_addr_t cur_addr, dma_addr;
+	size_t len, size;
+	int i;
+
+	/* calculate the total size in this desc */
+	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++)
+		len += le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
+			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
+
+	if (!in_progress)
+		return len;
+
+	if (dir == DMA_MEM_TO_DEV)
+		cur_addr = edma_readl(fsl_chan->edma, &regs->tcd[ch].saddr);
+	else
+		cur_addr = edma_readl(fsl_chan->edma, &regs->tcd[ch].daddr);
+
+	/* figure out the finished and calculate the residue */
+	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
+		size = le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
+			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		if (dir == DMA_MEM_TO_DEV)
+			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->saddr);
+		else
+			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->daddr);
+
+		len -= size;
+		if (cur_addr >= dma_addr && cur_addr < dma_addr + size) {
+			len += dma_addr + size - cur_addr;
+			break;
+		}
+	}
+
+	return len;
+}
+
+enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	unsigned long flags;
+
+	status = dma_cookie_status(chan, cookie, txstate);
+	if (status == DMA_COMPLETE)
+		return status;
+
+	if (!txstate)
+		return fsl_chan->status;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	vdesc = vchan_find_desc(&fsl_chan->vchan, cookie);
+	if (fsl_chan->edesc && cookie == fsl_chan->edesc->vdesc.tx.cookie)
+		txstate->residue =
+			fsl_edma_desc_residue(fsl_chan, vdesc, true);
+	else if (vdesc)
+		txstate->residue =
+			fsl_edma_desc_residue(fsl_chan, vdesc, false);
+	else
+		txstate->residue = 0;
+
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	return fsl_chan->status;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_tx_status);
+
+static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
+				  struct fsl_edma_hw_tcd *tcd)
+{
+	struct fsl_edma_engine *edma = fsl_chan->edma;
+	struct edma_regs *regs = &fsl_chan->edma->regs;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	/*
+	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
+	 * endian format. However, we need to load the TCD registers in
+	 * big- or little-endian obeying the eDMA engine model endian.
+	 */
+	edma_writew(edma, 0,  &regs->tcd[ch].csr);
+	edma_writel(edma, le32_to_cpu(tcd->saddr), &regs->tcd[ch].saddr);
+	edma_writel(edma, le32_to_cpu(tcd->daddr), &regs->tcd[ch].daddr);
+
+	edma_writew(edma, le16_to_cpu(tcd->attr), &regs->tcd[ch].attr);
+	edma_writew(edma, le16_to_cpu(tcd->soff), &regs->tcd[ch].soff);
+
+	edma_writel(edma, le32_to_cpu(tcd->nbytes), &regs->tcd[ch].nbytes);
+	edma_writel(edma, le32_to_cpu(tcd->slast), &regs->tcd[ch].slast);
+
+	edma_writew(edma, le16_to_cpu(tcd->citer), &regs->tcd[ch].citer);
+	edma_writew(edma, le16_to_cpu(tcd->biter), &regs->tcd[ch].biter);
+	edma_writew(edma, le16_to_cpu(tcd->doff), &regs->tcd[ch].doff);
+
+	edma_writel(edma, le32_to_cpu(tcd->dlast_sga),
+			&regs->tcd[ch].dlast_sga);
+
+	edma_writew(edma, le16_to_cpu(tcd->csr), &regs->tcd[ch].csr);
+}
+
+static inline
+void fsl_edma_fill_tcd(struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
+		       u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
+		       u16 biter, u16 doff, u32 dlast_sga, bool major_int,
+		       bool disable_req, bool enable_sg)
+{
+	u16 csr = 0;
+
+	/*
+	 * eDMA hardware SGs require the TCDs to be stored in little
+	 * endian format irrespective of the register endian model.
+	 * So we put the value in little endian in memory, waiting
+	 * for fsl_edma_set_tcd_regs doing the swap.
+	 */
+	tcd->saddr = cpu_to_le32(src);
+	tcd->daddr = cpu_to_le32(dst);
+
+	tcd->attr = cpu_to_le16(attr);
+
+	tcd->soff = cpu_to_le16(soff);
+
+	tcd->nbytes = cpu_to_le32(nbytes);
+	tcd->slast = cpu_to_le32(slast);
+
+	tcd->citer = cpu_to_le16(EDMA_TCD_CITER_CITER(citer));
+	tcd->doff = cpu_to_le16(doff);
+
+	tcd->dlast_sga = cpu_to_le32(dlast_sga);
+
+	tcd->biter = cpu_to_le16(EDMA_TCD_BITER_BITER(biter));
+	if (major_int)
+		csr |= EDMA_TCD_CSR_INT_MAJOR;
+
+	if (disable_req)
+		csr |= EDMA_TCD_CSR_D_REQ;
+
+	if (enable_sg)
+		csr |= EDMA_TCD_CSR_E_SG;
+
+	tcd->csr = cpu_to_le16(csr);
+}
+
+static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
+		int sg_len)
+{
+	struct fsl_edma_desc *fsl_desc;
+	int i;
+
+	fsl_desc = kzalloc(sizeof(*fsl_desc) +
+			   sizeof(struct fsl_edma_sw_tcd) *
+			   sg_len, GFP_NOWAIT);
+	if (!fsl_desc)
+		return NULL;
+
+	fsl_desc->echan = fsl_chan;
+	fsl_desc->n_tcds = sg_len;
+	for (i = 0; i < sg_len; i++) {
+		fsl_desc->tcd[i].vtcd = dma_pool_alloc(fsl_chan->tcd_pool,
+					GFP_NOWAIT, &fsl_desc->tcd[i].ptcd);
+		if (!fsl_desc->tcd[i].vtcd)
+			goto err;
+	}
+	return fsl_desc;
+
+err:
+	while (--i >= 0)
+		dma_pool_free(fsl_chan->tcd_pool, fsl_desc->tcd[i].vtcd,
+				fsl_desc->tcd[i].ptcd);
+	kfree(fsl_desc);
+	return NULL;
+}
+
+struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction direction,
+		unsigned long flags)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_desc *fsl_desc;
+	dma_addr_t dma_buf_next;
+	int sg_len, i;
+	u32 src_addr, dst_addr, last_sg, nbytes;
+	u16 soff, doff, iter;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	sg_len = buf_len / period_len;
+	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
+	if (!fsl_desc)
+		return NULL;
+	fsl_desc->iscyclic = true;
+	fsl_desc->dirn = direction;
+
+	dma_buf_next = dma_addr;
+	if (direction == DMA_MEM_TO_DEV) {
+		fsl_chan->attr =
+			fsl_edma_get_tcd_attr(fsl_chan->cfg.dst_addr_width);
+		nbytes = fsl_chan->cfg.dst_addr_width *
+			fsl_chan->cfg.dst_maxburst;
+	} else {
+		fsl_chan->attr =
+			fsl_edma_get_tcd_attr(fsl_chan->cfg.src_addr_width);
+		nbytes = fsl_chan->cfg.src_addr_width *
+			fsl_chan->cfg.src_maxburst;
+	}
+
+	iter = period_len / nbytes;
+
+	for (i = 0; i < sg_len; i++) {
+		if (dma_buf_next >= dma_addr + buf_len)
+			dma_buf_next = dma_addr;
+
+		/* get next sg's physical address */
+		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
+
+		if (direction == DMA_MEM_TO_DEV) {
+			src_addr = dma_buf_next;
+			dst_addr = fsl_chan->cfg.dst_addr;
+			soff = fsl_chan->cfg.dst_addr_width;
+			doff = 0;
+		} else {
+			src_addr = fsl_chan->cfg.src_addr;
+			dst_addr = dma_buf_next;
+			soff = 0;
+			doff = fsl_chan->cfg.src_addr_width;
+		}
+
+		fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr, dst_addr,
+				  fsl_chan->attr, soff, nbytes, 0, iter,
+				  iter, doff, last_sg, true, false, true);
+		dma_buf_next += period_len;
+	}
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_prep_dma_cyclic);
+
+struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_desc *fsl_desc;
+	struct scatterlist *sg;
+	u32 src_addr, dst_addr, last_sg, nbytes;
+	u16 soff, doff, iter;
+	int i;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
+	if (!fsl_desc)
+		return NULL;
+	fsl_desc->iscyclic = false;
+	fsl_desc->dirn = direction;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		fsl_chan->attr =
+			fsl_edma_get_tcd_attr(fsl_chan->cfg.dst_addr_width);
+		nbytes = fsl_chan->cfg.dst_addr_width *
+			fsl_chan->cfg.dst_maxburst;
+	} else {
+		fsl_chan->attr =
+			fsl_edma_get_tcd_attr(fsl_chan->cfg.src_addr_width);
+		nbytes = fsl_chan->cfg.src_addr_width *
+			fsl_chan->cfg.src_maxburst;
+	}
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		/* get next sg's physical address */
+		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
+
+		if (direction == DMA_MEM_TO_DEV) {
+			src_addr = sg_dma_address(sg);
+			dst_addr = fsl_chan->cfg.dst_addr;
+			soff = fsl_chan->cfg.dst_addr_width;
+			doff = 0;
+		} else {
+			src_addr = fsl_chan->cfg.src_addr;
+			dst_addr = sg_dma_address(sg);
+			soff = 0;
+			doff = fsl_chan->cfg.src_addr_width;
+		}
+
+		iter = sg_dma_len(sg) / nbytes;
+		if (i < sg_len - 1) {
+			last_sg = fsl_desc->tcd[(i + 1)].ptcd;
+			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
+					  dst_addr, fsl_chan->attr, soff,
+					  nbytes, 0, iter, iter, doff, last_sg,
+					  false, false, true);
+		} else {
+			last_sg = 0;
+			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
+					  dst_addr, fsl_chan->attr, soff,
+					  nbytes, 0, iter, iter, doff, last_sg,
+					  true, true, false);
+		}
+	}
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_prep_slave_sg);
+
+void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
+{
+	struct virt_dma_desc *vdesc;
+
+	vdesc = vchan_next_desc(&fsl_chan->vchan);
+	if (!vdesc)
+		return;
+	fsl_chan->edesc = to_fsl_edma_desc(vdesc);
+	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
+	fsl_edma_enable_request(fsl_chan);
+	fsl_chan->status = DMA_IN_PROGRESS;
+	fsl_chan->idle = false;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_xfer_desc);
+
+void fsl_edma_issue_pending(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+
+	if (unlikely(fsl_chan->pm_state != RUNNING)) {
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		/* cannot submit due to suspend */
+		return;
+	}
+
+	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
+		fsl_edma_xfer_desc(fsl_chan);
+
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_issue_pending);
+
+int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+
+	fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev,
+				sizeof(struct fsl_edma_hw_tcd),
+				32, 0);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_alloc_chan_resources);
+
+void fsl_edma_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	fsl_edma_disable_request(fsl_chan);
+	fsl_edma_chan_mux(fsl_chan, 0, false);
+	fsl_chan->edesc = NULL;
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+	dma_pool_destroy(fsl_chan->tcd_pool);
+	fsl_chan->tcd_pool = NULL;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_free_chan_resources);
+
+void fsl_edma_cleanup_vchan(struct dma_device *dmadev)
+{
+	struct fsl_edma_chan *chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan,
+				&dmadev->channels, vchan.chan.device_node) {
+		list_del(&chan->vchan.chan.device_node);
+		tasklet_kill(&chan->vchan.task);
+	}
+}
+EXPORT_SYMBOL_GPL(fsl_edma_cleanup_vchan);
+
+/*
+ * On the 32 channels Vybrid/mpc577x edma version (here called "v1"),
+ * register offsets are different compared to ColdFire mcf5441x 64 channels
+ * edma (here called "v2").
+ *
+ * This function sets up register offsets as per proper declared version
+ * so must be called in xxx_edma_probe() just after setting the
+ * edma "version" and "membase" appropriately.
+ */
+void fsl_edma_setup_regs(struct fsl_edma_engine *edma)
+{
+	edma->regs.cr = edma->membase + EDMA_CR;
+	edma->regs.es = edma->membase + EDMA_ES;
+	edma->regs.erql = edma->membase + EDMA_ERQ;
+	edma->regs.eeil = edma->membase + EDMA_EEI;
+
+	edma->regs.serq = edma->membase + ((edma->version == v1) ?
+			EDMA_SERQ : EDMA64_SERQ);
+	edma->regs.cerq = edma->membase + ((edma->version == v1) ?
+			EDMA_CERQ : EDMA64_CERQ);
+	edma->regs.seei = edma->membase + ((edma->version == v1) ?
+			EDMA_SEEI : EDMA64_SEEI);
+	edma->regs.ceei = edma->membase + ((edma->version == v1) ?
+			EDMA_CEEI : EDMA64_CEEI);
+	edma->regs.cint = edma->membase + ((edma->version == v1) ?
+			EDMA_CINT : EDMA64_CINT);
+	edma->regs.cerr = edma->membase + ((edma->version == v1) ?
+			EDMA_CERR : EDMA64_CERR);
+	edma->regs.ssrt = edma->membase + ((edma->version == v1) ?
+			EDMA_SSRT : EDMA64_SSRT);
+	edma->regs.cdne = edma->membase + ((edma->version == v1) ?
+			EDMA_CDNE : EDMA64_CDNE);
+	edma->regs.intl = edma->membase + ((edma->version == v1) ?
+			EDMA_INTR : EDMA64_INTL);
+	edma->regs.errl = edma->membase + ((edma->version == v1) ?
+			EDMA_ERR : EDMA64_ERRL);
+
+	if (edma->version == v2) {
+		edma->regs.erqh = edma->membase + EDMA64_ERQH;
+		edma->regs.eeih = edma->membase + EDMA64_EEIH;
+		edma->regs.errh = edma->membase + EDMA64_ERRH;
+		edma->regs.inth = edma->membase + EDMA64_INTH;
+	}
+
+	edma->regs.tcd = edma->membase + EDMA_TCD;
+}
+EXPORT_SYMBOL_GPL(fsl_edma_setup_regs);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
new file mode 100644
index 000000000000..8917e8865959
--- /dev/null
+++ b/drivers/dma/fsl-edma-common.h
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2013-2014 Freescale Semiconductor, Inc.
+ * Copyright 2018 Angelo Dureghello <angelo@sysam.it>
+ */
+#ifndef _FSL_EDMA_COMMON_H_
+#define _FSL_EDMA_COMMON_H_
+
+#include "virt-dma.h"
+
+#define EDMA_CR_EDBG		BIT(1)
+#define EDMA_CR_ERCA		BIT(2)
+#define EDMA_CR_ERGA		BIT(3)
+#define EDMA_CR_HOE		BIT(4)
+#define EDMA_CR_HALT		BIT(5)
+#define EDMA_CR_CLM		BIT(6)
+#define EDMA_CR_EMLM		BIT(7)
+#define EDMA_CR_ECX		BIT(16)
+#define EDMA_CR_CX		BIT(17)
+
+#define EDMA_SEEI_SEEI(x)	((x) & GENMASK(4, 0))
+#define EDMA_CEEI_CEEI(x)	((x) & GENMASK(4, 0))
+#define EDMA_CINT_CINT(x)	((x) & GENMASK(4, 0))
+#define EDMA_CERR_CERR(x)	((x) & GENMASK(4, 0))
+
+#define EDMA_TCD_ATTR_DSIZE(x)		(((x) & GENMASK(2, 0)))
+#define EDMA_TCD_ATTR_DMOD(x)		(((x) & GENMASK(4, 0)) << 3)
+#define EDMA_TCD_ATTR_SSIZE(x)		(((x) & GENMASK(2, 0)) << 8)
+#define EDMA_TCD_ATTR_SMOD(x)		(((x) & GENMASK(4, 0)) << 11)
+#define EDMA_TCD_ATTR_DSIZE_8BIT	0
+#define EDMA_TCD_ATTR_DSIZE_16BIT	BIT(0)
+#define EDMA_TCD_ATTR_DSIZE_32BIT	BIT(1)
+#define EDMA_TCD_ATTR_DSIZE_64BIT	(BIT(0) | BIT(1))
+#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(3) | BIT(0))
+#define EDMA_TCD_ATTR_SSIZE_8BIT	0
+#define EDMA_TCD_ATTR_SSIZE_16BIT	(EDMA_TCD_ATTR_DSIZE_16BIT << 8)
+#define EDMA_TCD_ATTR_SSIZE_32BIT	(EDMA_TCD_ATTR_DSIZE_32BIT << 8)
+#define EDMA_TCD_ATTR_SSIZE_64BIT	(EDMA_TCD_ATTR_DSIZE_64BIT << 8)
+#define EDMA_TCD_ATTR_SSIZE_32BYTE	(EDMA_TCD_ATTR_DSIZE_32BYTE << 8)
+
+#define EDMA_TCD_CITER_CITER(x)		((x) & GENMASK(14, 0))
+#define EDMA_TCD_BITER_BITER(x)		((x) & GENMASK(14, 0))
+
+#define EDMA_TCD_CSR_START		BIT(0)
+#define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
+#define EDMA_TCD_CSR_INT_HALF		BIT(2)
+#define EDMA_TCD_CSR_D_REQ		BIT(3)
+#define EDMA_TCD_CSR_E_SG		BIT(4)
+#define EDMA_TCD_CSR_E_LINK		BIT(5)
+#define EDMA_TCD_CSR_ACTIVE		BIT(6)
+#define EDMA_TCD_CSR_DONE		BIT(7)
+
+#define EDMAMUX_CHCFG_DIS		0x0
+#define EDMAMUX_CHCFG_ENBL		0x80
+#define EDMAMUX_CHCFG_SOURCE(n)		((n) & 0x3F)
+
+#define DMAMUX_NR	2
+
+#define FSL_EDMA_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+enum fsl_edma_pm_state {
+	RUNNING = 0,
+	SUSPENDED,
+};
+
+struct fsl_edma_hw_tcd {
+	__le32	saddr;
+	__le16	soff;
+	__le16	attr;
+	__le32	nbytes;
+	__le32	slast;
+	__le32	daddr;
+	__le16	doff;
+	__le16	citer;
+	__le32	dlast_sga;
+	__le16	csr;
+	__le16	biter;
+};
+
+/*
+ * These are iomem pointers, for both v32 and v64.
+ */
+struct edma_regs {
+	void __iomem *cr;
+	void __iomem *es;
+	void __iomem *erqh;
+	void __iomem *erql;	/* aka erq on v32 */
+	void __iomem *eeih;
+	void __iomem *eeil;	/* aka eei on v32 */
+	void __iomem *seei;
+	void __iomem *ceei;
+	void __iomem *serq;
+	void __iomem *cerq;
+	void __iomem *cint;
+	void __iomem *cerr;
+	void __iomem *ssrt;
+	void __iomem *cdne;
+	void __iomem *inth;
+	void __iomem *intl;
+	void __iomem *errh;
+	void __iomem *errl;
+	struct fsl_edma_hw_tcd __iomem *tcd;
+};
+
+struct fsl_edma_sw_tcd {
+	dma_addr_t			ptcd;
+	struct fsl_edma_hw_tcd		*vtcd;
+};
+
+struct fsl_edma_chan {
+	struct virt_dma_chan		vchan;
+	enum dma_status			status;
+	enum fsl_edma_pm_state		pm_state;
+	bool				idle;
+	u32				slave_id;
+	struct fsl_edma_engine		*edma;
+	struct fsl_edma_desc		*edesc;
+	struct dma_slave_config		cfg;
+	u32				attr;
+	struct dma_pool			*tcd_pool;
+};
+
+struct fsl_edma_desc {
+	struct virt_dma_desc		vdesc;
+	struct fsl_edma_chan		*echan;
+	bool				iscyclic;
+	enum dma_transfer_direction	dirn;
+	unsigned int			n_tcds;
+	struct fsl_edma_sw_tcd		tcd[];
+};
+
+enum edma_version {
+	v1, /* 32ch, Vybdir, mpc57x, etc */
+	v2, /* 64ch Coldfire */
+};
+
+struct fsl_edma_engine {
+	struct dma_device	dma_dev;
+	void __iomem		*membase;
+	void __iomem		*muxbase[DMAMUX_NR];
+	struct clk		*muxclk[DMAMUX_NR];
+	struct mutex		fsl_edma_mutex;
+	u32			n_chans;
+	int			txirq;
+	int			errirq;
+	bool			big_endian;
+	enum edma_version	version;
+	struct edma_regs	regs;
+	struct fsl_edma_chan	chans[];
+};
+
+/*
+ * R/W functions for big- or little-endian registers:
+ * The eDMA controller's endian is independent of the CPU core's endian.
+ * For the big-endian IP module, the offset for 8-bit or 16-bit registers
+ * should also be swapped opposite to that in little-endian IP.
+ */
+static inline u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr)
+{
+	if (edma->big_endian)
+		return ioread32be(addr);
+	else
+		return ioread32(addr);
+}
+
+static inline void edma_writeb(struct fsl_edma_engine *edma,
+			       u8 val, void __iomem *addr)
+{
+	/* swap the reg offset for these in big-endian mode */
+	if (edma->big_endian)
+		iowrite8(val, (void __iomem *)((unsigned long)addr ^ 0x3));
+	else
+		iowrite8(val, addr);
+}
+
+static inline void edma_writew(struct fsl_edma_engine *edma,
+			       u16 val, void __iomem *addr)
+{
+	/* swap the reg offset for these in big-endian mode */
+	if (edma->big_endian)
+		iowrite16be(val, (void __iomem *)((unsigned long)addr ^ 0x2));
+	else
+		iowrite16(val, addr);
+}
+
+static inline void edma_writel(struct fsl_edma_engine *edma,
+			       u32 val, void __iomem *addr)
+{
+	if (edma->big_endian)
+		iowrite32be(val, addr);
+	else
+		iowrite32(val, addr);
+}
+
+static inline struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct fsl_edma_chan, vchan.chan);
+}
+
+static inline struct fsl_edma_desc *to_fsl_edma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct fsl_edma_desc, vdesc);
+}
+
+void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan);
+void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
+			unsigned int slot, bool enable);
+void fsl_edma_free_desc(struct virt_dma_desc *vdesc);
+int fsl_edma_terminate_all(struct dma_chan *chan);
+int fsl_edma_pause(struct dma_chan *chan);
+int fsl_edma_resume(struct dma_chan *chan);
+int fsl_edma_slave_config(struct dma_chan *chan,
+				 struct dma_slave_config *cfg);
+enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate);
+struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction direction,
+		unsigned long flags);
+struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context);
+void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan);
+void fsl_edma_issue_pending(struct dma_chan *chan);
+int fsl_edma_alloc_chan_resources(struct dma_chan *chan);
+void fsl_edma_free_chan_resources(struct dma_chan *chan);
+void fsl_edma_cleanup_vchan(struct dma_device *dmadev);
+void fsl_edma_setup_regs(struct fsl_edma_engine *edma);
+
+#endif /* _FSL_EDMA_COMMON_H_ */
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index c7568869284e..34d70112fcc9 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -13,671 +13,31 @@
  * option) any later version.
  */
 
-#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmapool.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_dma.h>
 
-#include "virt-dma.h"
-
-#define EDMA_CR			0x00
-#define EDMA_ES			0x04
-#define EDMA_ERQ		0x0C
-#define EDMA_EEI		0x14
-#define EDMA_SERQ		0x1B
-#define EDMA_CERQ		0x1A
-#define EDMA_SEEI		0x19
-#define EDMA_CEEI		0x18
-#define EDMA_CINT		0x1F
-#define EDMA_CERR		0x1E
-#define EDMA_SSRT		0x1D
-#define EDMA_CDNE		0x1C
-#define EDMA_INTR		0x24
-#define EDMA_ERR		0x2C
-
-#define EDMA_TCD_SADDR(x)	(0x1000 + 32 * (x))
-#define EDMA_TCD_SOFF(x)	(0x1004 + 32 * (x))
-#define EDMA_TCD_ATTR(x)	(0x1006 + 32 * (x))
-#define EDMA_TCD_NBYTES(x)	(0x1008 + 32 * (x))
-#define EDMA_TCD_SLAST(x)	(0x100C + 32 * (x))
-#define EDMA_TCD_DADDR(x)	(0x1010 + 32 * (x))
-#define EDMA_TCD_DOFF(x)	(0x1014 + 32 * (x))
-#define EDMA_TCD_CITER_ELINK(x)	(0x1016 + 32 * (x))
-#define EDMA_TCD_CITER(x)	(0x1016 + 32 * (x))
-#define EDMA_TCD_DLAST_SGA(x)	(0x1018 + 32 * (x))
-#define EDMA_TCD_CSR(x)		(0x101C + 32 * (x))
-#define EDMA_TCD_BITER_ELINK(x)	(0x101E + 32 * (x))
-#define EDMA_TCD_BITER(x)	(0x101E + 32 * (x))
-
-#define EDMA_CR_EDBG		BIT(1)
-#define EDMA_CR_ERCA		BIT(2)
-#define EDMA_CR_ERGA		BIT(3)
-#define EDMA_CR_HOE		BIT(4)
-#define EDMA_CR_HALT		BIT(5)
-#define EDMA_CR_CLM		BIT(6)
-#define EDMA_CR_EMLM		BIT(7)
-#define EDMA_CR_ECX		BIT(16)
-#define EDMA_CR_CX		BIT(17)
-
-#define EDMA_SEEI_SEEI(x)	((x) & 0x1F)
-#define EDMA_CEEI_CEEI(x)	((x) & 0x1F)
-#define EDMA_CINT_CINT(x)	((x) & 0x1F)
-#define EDMA_CERR_CERR(x)	((x) & 0x1F)
-
-#define EDMA_TCD_ATTR_DSIZE(x)		(((x) & 0x0007))
-#define EDMA_TCD_ATTR_DMOD(x)		(((x) & 0x001F) << 3)
-#define EDMA_TCD_ATTR_SSIZE(x)		(((x) & 0x0007) << 8)
-#define EDMA_TCD_ATTR_SMOD(x)		(((x) & 0x001F) << 11)
-#define EDMA_TCD_ATTR_SSIZE_8BIT	(0x0000)
-#define EDMA_TCD_ATTR_SSIZE_16BIT	(0x0100)
-#define EDMA_TCD_ATTR_SSIZE_32BIT	(0x0200)
-#define EDMA_TCD_ATTR_SSIZE_64BIT	(0x0300)
-#define EDMA_TCD_ATTR_SSIZE_32BYTE	(0x0500)
-#define EDMA_TCD_ATTR_DSIZE_8BIT	(0x0000)
-#define EDMA_TCD_ATTR_DSIZE_16BIT	(0x0001)
-#define EDMA_TCD_ATTR_DSIZE_32BIT	(0x0002)
-#define EDMA_TCD_ATTR_DSIZE_64BIT	(0x0003)
-#define EDMA_TCD_ATTR_DSIZE_32BYTE	(0x0005)
-
-#define EDMA_TCD_SOFF_SOFF(x)		(x)
-#define EDMA_TCD_NBYTES_NBYTES(x)	(x)
-#define EDMA_TCD_SLAST_SLAST(x)		(x)
-#define EDMA_TCD_DADDR_DADDR(x)		(x)
-#define EDMA_TCD_CITER_CITER(x)		((x) & 0x7FFF)
-#define EDMA_TCD_DOFF_DOFF(x)		(x)
-#define EDMA_TCD_DLAST_SGA_DLAST_SGA(x)	(x)
-#define EDMA_TCD_BITER_BITER(x)		((x) & 0x7FFF)
-
-#define EDMA_TCD_CSR_START		BIT(0)
-#define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
-#define EDMA_TCD_CSR_INT_HALF		BIT(2)
-#define EDMA_TCD_CSR_D_REQ		BIT(3)
-#define EDMA_TCD_CSR_E_SG		BIT(4)
-#define EDMA_TCD_CSR_E_LINK		BIT(5)
-#define EDMA_TCD_CSR_ACTIVE		BIT(6)
-#define EDMA_TCD_CSR_DONE		BIT(7)
-
-#define EDMAMUX_CHCFG_DIS		0x0
-#define EDMAMUX_CHCFG_ENBL		0x80
-#define EDMAMUX_CHCFG_SOURCE(n)		((n) & 0x3F)
-
-#define DMAMUX_NR	2
-
-#define FSL_EDMA_BUSWIDTHS	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
-				BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
-				BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
-				BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
-enum fsl_edma_pm_state {
-	RUNNING = 0,
-	SUSPENDED,
-};
-
-struct fsl_edma_hw_tcd {
-	__le32	saddr;
-	__le16	soff;
-	__le16	attr;
-	__le32	nbytes;
-	__le32	slast;
-	__le32	daddr;
-	__le16	doff;
-	__le16	citer;
-	__le32	dlast_sga;
-	__le16	csr;
-	__le16	biter;
-};
-
-struct fsl_edma_sw_tcd {
-	dma_addr_t			ptcd;
-	struct fsl_edma_hw_tcd		*vtcd;
-};
-
-struct fsl_edma_slave_config {
-	enum dma_transfer_direction	dir;
-	enum dma_slave_buswidth		addr_width;
-	u32				dev_addr;
-	u32				burst;
-	u32				attr;
-};
-
-struct fsl_edma_chan {
-	struct virt_dma_chan		vchan;
-	enum dma_status			status;
-	enum fsl_edma_pm_state		pm_state;
-	bool				idle;
-	u32				slave_id;
-	struct fsl_edma_engine		*edma;
-	struct fsl_edma_desc		*edesc;
-	struct fsl_edma_slave_config	fsc;
-	struct dma_pool			*tcd_pool;
-};
-
-struct fsl_edma_desc {
-	struct virt_dma_desc		vdesc;
-	struct fsl_edma_chan		*echan;
-	bool				iscyclic;
-	unsigned int			n_tcds;
-	struct fsl_edma_sw_tcd		tcd[];
-};
-
-struct fsl_edma_engine {
-	struct dma_device	dma_dev;
-	void __iomem		*membase;
-	void __iomem		*muxbase[DMAMUX_NR];
-	struct clk		*muxclk[DMAMUX_NR];
-	struct mutex		fsl_edma_mutex;
-	u32			n_chans;
-	int			txirq;
-	int			errirq;
-	bool			big_endian;
-	struct fsl_edma_chan	chans[];
-};
-
-/*
- * R/W functions for big- or little-endian registers:
- * The eDMA controller's endian is independent of the CPU core's endian.
- * For the big-endian IP module, the offset for 8-bit or 16-bit registers
- * should also be swapped opposite to that in little-endian IP.
- */
-
-static u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr)
-{
-	if (edma->big_endian)
-		return ioread32be(addr);
-	else
-		return ioread32(addr);
-}
-
-static void edma_writeb(struct fsl_edma_engine *edma, u8 val, void __iomem *addr)
-{
-	/* swap the reg offset for these in big-endian mode */
-	if (edma->big_endian)
-		iowrite8(val, (void __iomem *)((unsigned long)addr ^ 0x3));
-	else
-		iowrite8(val, addr);
-}
-
-static void edma_writew(struct fsl_edma_engine *edma, u16 val, void __iomem *addr)
-{
-	/* swap the reg offset for these in big-endian mode */
-	if (edma->big_endian)
-		iowrite16be(val, (void __iomem *)((unsigned long)addr ^ 0x2));
-	else
-		iowrite16(val, addr);
-}
-
-static void edma_writel(struct fsl_edma_engine *edma, u32 val, void __iomem *addr)
-{
-	if (edma->big_endian)
-		iowrite32be(val, addr);
-	else
-		iowrite32(val, addr);
-}
-
-static struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan)
-{
-	return container_of(chan, struct fsl_edma_chan, vchan.chan);
-}
-
-static struct fsl_edma_desc *to_fsl_edma_desc(struct virt_dma_desc *vd)
-{
-	return container_of(vd, struct fsl_edma_desc, vdesc);
-}
-
-static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan)
-{
-	void __iomem *addr = fsl_chan->edma->membase;
-	u32 ch = fsl_chan->vchan.chan.chan_id;
-
-	edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), addr + EDMA_SEEI);
-	edma_writeb(fsl_chan->edma, ch, addr + EDMA_SERQ);
-}
-
-static void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan)
-{
-	void __iomem *addr = fsl_chan->edma->membase;
-	u32 ch = fsl_chan->vchan.chan.chan_id;
-
-	edma_writeb(fsl_chan->edma, ch, addr + EDMA_CERQ);
-	edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), addr + EDMA_CEEI);
-}
-
-static void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
-			unsigned int slot, bool enable)
-{
-	u32 ch = fsl_chan->vchan.chan.chan_id;
-	void __iomem *muxaddr;
-	unsigned chans_per_mux, ch_off;
-
-	chans_per_mux = fsl_chan->edma->n_chans / DMAMUX_NR;
-	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
-	muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux];
-	slot = EDMAMUX_CHCFG_SOURCE(slot);
-
-	if (enable)
-		iowrite8(EDMAMUX_CHCFG_ENBL | slot, muxaddr + ch_off);
-	else
-		iowrite8(EDMAMUX_CHCFG_DIS, muxaddr + ch_off);
-}
-
-static unsigned int fsl_edma_get_tcd_attr(enum dma_slave_buswidth addr_width)
-{
-	switch (addr_width) {
-	case 1:
-		return EDMA_TCD_ATTR_SSIZE_8BIT | EDMA_TCD_ATTR_DSIZE_8BIT;
-	case 2:
-		return EDMA_TCD_ATTR_SSIZE_16BIT | EDMA_TCD_ATTR_DSIZE_16BIT;
-	case 4:
-		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
-	case 8:
-		return EDMA_TCD_ATTR_SSIZE_64BIT | EDMA_TCD_ATTR_DSIZE_64BIT;
-	default:
-		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
-	}
-}
-
-static void fsl_edma_free_desc(struct virt_dma_desc *vdesc)
-{
-	struct fsl_edma_desc *fsl_desc;
-	int i;
-
-	fsl_desc = to_fsl_edma_desc(vdesc);
-	for (i = 0; i < fsl_desc->n_tcds; i++)
-		dma_pool_free(fsl_desc->echan->tcd_pool, fsl_desc->tcd[i].vtcd,
-			      fsl_desc->tcd[i].ptcd);
-	kfree(fsl_desc);
-}
-
-static int fsl_edma_terminate_all(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	unsigned long flags;
-	LIST_HEAD(head);
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-	fsl_edma_disable_request(fsl_chan);
-	fsl_chan->edesc = NULL;
-	fsl_chan->idle = true;
-	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
-	return 0;
-}
-
-static int fsl_edma_pause(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-	if (fsl_chan->edesc) {
-		fsl_edma_disable_request(fsl_chan);
-		fsl_chan->status = DMA_PAUSED;
-		fsl_chan->idle = true;
-	}
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-	return 0;
-}
-
-static int fsl_edma_resume(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-	if (fsl_chan->edesc) {
-		fsl_edma_enable_request(fsl_chan);
-		fsl_chan->status = DMA_IN_PROGRESS;
-		fsl_chan->idle = false;
-	}
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-	return 0;
-}
-
-static int fsl_edma_slave_config(struct dma_chan *chan,
-				 struct dma_slave_config *cfg)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-
-	fsl_chan->fsc.dir = cfg->direction;
-	if (cfg->direction == DMA_DEV_TO_MEM) {
-		fsl_chan->fsc.dev_addr = cfg->src_addr;
-		fsl_chan->fsc.addr_width = cfg->src_addr_width;
-		fsl_chan->fsc.burst = cfg->src_maxburst;
-		fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->src_addr_width);
-	} else if (cfg->direction == DMA_MEM_TO_DEV) {
-		fsl_chan->fsc.dev_addr = cfg->dst_addr;
-		fsl_chan->fsc.addr_width = cfg->dst_addr_width;
-		fsl_chan->fsc.burst = cfg->dst_maxburst;
-		fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->dst_addr_width);
-	} else {
-			return -EINVAL;
-	}
-	return 0;
-}
-
-static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
-		struct virt_dma_desc *vdesc, bool in_progress)
-{
-	struct fsl_edma_desc *edesc = fsl_chan->edesc;
-	void __iomem *addr = fsl_chan->edma->membase;
-	u32 ch = fsl_chan->vchan.chan.chan_id;
-	enum dma_transfer_direction dir = fsl_chan->fsc.dir;
-	dma_addr_t cur_addr, dma_addr;
-	size_t len, size;
-	int i;
-
-	/* calculate the total size in this desc */
-	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++)
-		len += le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
-			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
-
-	if (!in_progress)
-		return len;
-
-	if (dir == DMA_MEM_TO_DEV)
-		cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_SADDR(ch));
-	else
-		cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_DADDR(ch));
-
-	/* figure out the finished and calculate the residue */
-	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		size = le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
-			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
-		if (dir == DMA_MEM_TO_DEV)
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->saddr);
-		else
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->daddr);
-
-		len -= size;
-		if (cur_addr >= dma_addr && cur_addr < dma_addr + size) {
-			len += dma_addr + size - cur_addr;
-			break;
-		}
-	}
-
-	return len;
-}
-
-static enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
-		dma_cookie_t cookie, struct dma_tx_state *txstate)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	struct virt_dma_desc *vdesc;
-	enum dma_status status;
-	unsigned long flags;
-
-	status = dma_cookie_status(chan, cookie, txstate);
-	if (status == DMA_COMPLETE)
-		return status;
-
-	if (!txstate)
-		return fsl_chan->status;
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-	vdesc = vchan_find_desc(&fsl_chan->vchan, cookie);
-	if (fsl_chan->edesc && cookie == fsl_chan->edesc->vdesc.tx.cookie)
-		txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, true);
-	else if (vdesc)
-		txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, false);
-	else
-		txstate->residue = 0;
-
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-
-	return fsl_chan->status;
-}
-
-static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
-				  struct fsl_edma_hw_tcd *tcd)
-{
-	struct fsl_edma_engine *edma = fsl_chan->edma;
-	void __iomem *addr = fsl_chan->edma->membase;
-	u32 ch = fsl_chan->vchan.chan.chan_id;
-
-	/*
-	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
-	 * endian format. However, we need to load the TCD registers in
-	 * big- or little-endian obeying the eDMA engine model endian.
-	 */
-	edma_writew(edma, 0, addr + EDMA_TCD_CSR(ch));
-	edma_writel(edma, le32_to_cpu(tcd->saddr), addr + EDMA_TCD_SADDR(ch));
-	edma_writel(edma, le32_to_cpu(tcd->daddr), addr + EDMA_TCD_DADDR(ch));
-
-	edma_writew(edma, le16_to_cpu(tcd->attr), addr + EDMA_TCD_ATTR(ch));
-	edma_writew(edma, le16_to_cpu(tcd->soff), addr + EDMA_TCD_SOFF(ch));
-
-	edma_writel(edma, le32_to_cpu(tcd->nbytes), addr + EDMA_TCD_NBYTES(ch));
-	edma_writel(edma, le32_to_cpu(tcd->slast), addr + EDMA_TCD_SLAST(ch));
-
-	edma_writew(edma, le16_to_cpu(tcd->citer), addr + EDMA_TCD_CITER(ch));
-	edma_writew(edma, le16_to_cpu(tcd->biter), addr + EDMA_TCD_BITER(ch));
-	edma_writew(edma, le16_to_cpu(tcd->doff), addr + EDMA_TCD_DOFF(ch));
-
-	edma_writel(edma, le32_to_cpu(tcd->dlast_sga), addr + EDMA_TCD_DLAST_SGA(ch));
-
-	edma_writew(edma, le16_to_cpu(tcd->csr), addr + EDMA_TCD_CSR(ch));
-}
-
-static inline
-void fsl_edma_fill_tcd(struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
-		       u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
-		       u16 biter, u16 doff, u32 dlast_sga, bool major_int,
-		       bool disable_req, bool enable_sg)
-{
-	u16 csr = 0;
-
-	/*
-	 * eDMA hardware SGs require the TCDs to be stored in little
-	 * endian format irrespective of the register endian model.
-	 * So we put the value in little endian in memory, waiting
-	 * for fsl_edma_set_tcd_regs doing the swap.
-	 */
-	tcd->saddr = cpu_to_le32(src);
-	tcd->daddr = cpu_to_le32(dst);
-
-	tcd->attr = cpu_to_le16(attr);
-
-	tcd->soff = cpu_to_le16(EDMA_TCD_SOFF_SOFF(soff));
-
-	tcd->nbytes = cpu_to_le32(EDMA_TCD_NBYTES_NBYTES(nbytes));
-	tcd->slast = cpu_to_le32(EDMA_TCD_SLAST_SLAST(slast));
-
-	tcd->citer = cpu_to_le16(EDMA_TCD_CITER_CITER(citer));
-	tcd->doff = cpu_to_le16(EDMA_TCD_DOFF_DOFF(doff));
-
-	tcd->dlast_sga = cpu_to_le32(EDMA_TCD_DLAST_SGA_DLAST_SGA(dlast_sga));
-
-	tcd->biter = cpu_to_le16(EDMA_TCD_BITER_BITER(biter));
-	if (major_int)
-		csr |= EDMA_TCD_CSR_INT_MAJOR;
-
-	if (disable_req)
-		csr |= EDMA_TCD_CSR_D_REQ;
-
-	if (enable_sg)
-		csr |= EDMA_TCD_CSR_E_SG;
-
-	tcd->csr = cpu_to_le16(csr);
-}
-
-static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
-		int sg_len)
-{
-	struct fsl_edma_desc *fsl_desc;
-	int i;
-
-	fsl_desc = kzalloc(sizeof(*fsl_desc) + sizeof(struct fsl_edma_sw_tcd) * sg_len,
-				GFP_NOWAIT);
-	if (!fsl_desc)
-		return NULL;
-
-	fsl_desc->echan = fsl_chan;
-	fsl_desc->n_tcds = sg_len;
-	for (i = 0; i < sg_len; i++) {
-		fsl_desc->tcd[i].vtcd = dma_pool_alloc(fsl_chan->tcd_pool,
-					GFP_NOWAIT, &fsl_desc->tcd[i].ptcd);
-		if (!fsl_desc->tcd[i].vtcd)
-			goto err;
-	}
-	return fsl_desc;
-
-err:
-	while (--i >= 0)
-		dma_pool_free(fsl_chan->tcd_pool, fsl_desc->tcd[i].vtcd,
-				fsl_desc->tcd[i].ptcd);
-	kfree(fsl_desc);
-	return NULL;
-}
-
-static struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
-		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
-		size_t period_len, enum dma_transfer_direction direction,
-		unsigned long flags)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	struct fsl_edma_desc *fsl_desc;
-	dma_addr_t dma_buf_next;
-	int sg_len, i;
-	u32 src_addr, dst_addr, last_sg, nbytes;
-	u16 soff, doff, iter;
-
-	if (!is_slave_direction(fsl_chan->fsc.dir))
-		return NULL;
-
-	sg_len = buf_len / period_len;
-	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
-	if (!fsl_desc)
-		return NULL;
-	fsl_desc->iscyclic = true;
-
-	dma_buf_next = dma_addr;
-	nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst;
-	iter = period_len / nbytes;
-
-	for (i = 0; i < sg_len; i++) {
-		if (dma_buf_next >= dma_addr + buf_len)
-			dma_buf_next = dma_addr;
-
-		/* get next sg's physical address */
-		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
-
-		if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) {
-			src_addr = dma_buf_next;
-			dst_addr = fsl_chan->fsc.dev_addr;
-			soff = fsl_chan->fsc.addr_width;
-			doff = 0;
-		} else {
-			src_addr = fsl_chan->fsc.dev_addr;
-			dst_addr = dma_buf_next;
-			soff = 0;
-			doff = fsl_chan->fsc.addr_width;
-		}
-
-		fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr, dst_addr,
-				  fsl_chan->fsc.attr, soff, nbytes, 0, iter,
-				  iter, doff, last_sg, true, false, true);
-		dma_buf_next += period_len;
-	}
-
-	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
-}
-
-static struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
-		struct dma_chan *chan, struct scatterlist *sgl,
-		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags, void *context)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	struct fsl_edma_desc *fsl_desc;
-	struct scatterlist *sg;
-	u32 src_addr, dst_addr, last_sg, nbytes;
-	u16 soff, doff, iter;
-	int i;
-
-	if (!is_slave_direction(fsl_chan->fsc.dir))
-		return NULL;
-
-	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
-	if (!fsl_desc)
-		return NULL;
-	fsl_desc->iscyclic = false;
-
-	nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst;
-	for_each_sg(sgl, sg, sg_len, i) {
-		/* get next sg's physical address */
-		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
-
-		if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) {
-			src_addr = sg_dma_address(sg);
-			dst_addr = fsl_chan->fsc.dev_addr;
-			soff = fsl_chan->fsc.addr_width;
-			doff = 0;
-		} else {
-			src_addr = fsl_chan->fsc.dev_addr;
-			dst_addr = sg_dma_address(sg);
-			soff = 0;
-			doff = fsl_chan->fsc.addr_width;
-		}
-
-		iter = sg_dma_len(sg) / nbytes;
-		if (i < sg_len - 1) {
-			last_sg = fsl_desc->tcd[(i + 1)].ptcd;
-			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
-					  dst_addr, fsl_chan->fsc.attr, soff,
-					  nbytes, 0, iter, iter, doff, last_sg,
-					  false, false, true);
-		} else {
-			last_sg = 0;
-			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
-					  dst_addr, fsl_chan->fsc.attr, soff,
-					  nbytes, 0, iter, iter, doff, last_sg,
-					  true, true, false);
-		}
-	}
-
-	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
-}
-
-static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
-{
-	struct virt_dma_desc *vdesc;
-
-	vdesc = vchan_next_desc(&fsl_chan->vchan);
-	if (!vdesc)
-		return;
-	fsl_chan->edesc = to_fsl_edma_desc(vdesc);
-	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
-	fsl_edma_enable_request(fsl_chan);
-	fsl_chan->status = DMA_IN_PROGRESS;
-	fsl_chan->idle = false;
-}
+#include "fsl-edma-common.h"
 
 static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_engine *fsl_edma = dev_id;
 	unsigned int intr, ch;
-	void __iomem *base_addr;
+	struct edma_regs *regs = &fsl_edma->regs;
 	struct fsl_edma_chan *fsl_chan;
 
-	base_addr = fsl_edma->membase;
-
-	intr = edma_readl(fsl_edma, base_addr + EDMA_INTR);
+	intr = edma_readl(fsl_edma, regs->intl);
 	if (!intr)
 		return IRQ_NONE;
 
 	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
 		if (intr & (0x1 << ch)) {
-			edma_writeb(fsl_edma, EDMA_CINT_CINT(ch),
-				base_addr + EDMA_CINT);
+			edma_writeb(fsl_edma, EDMA_CINT_CINT(ch), regs->cint);
 
 			fsl_chan = &fsl_edma->chans[ch];
 
@@ -705,16 +65,16 @@ static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_engine *fsl_edma = dev_id;
 	unsigned int err, ch;
+	struct edma_regs *regs = &fsl_edma->regs;
 
-	err = edma_readl(fsl_edma, fsl_edma->membase + EDMA_ERR);
+	err = edma_readl(fsl_edma, regs->errl);
 	if (!err)
 		return IRQ_NONE;
 
 	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
 		if (err & (0x1 << ch)) {
 			fsl_edma_disable_request(&fsl_edma->chans[ch]);
-			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch),
-				fsl_edma->membase + EDMA_CERR);
+			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch), regs->cerr);
 			fsl_edma->chans[ch].status = DMA_ERROR;
 			fsl_edma->chans[ch].idle = true;
 		}
@@ -730,25 +90,6 @@ static irqreturn_t fsl_edma_irq_handler(int irq, void *dev_id)
 	return fsl_edma_err_handler(irq, dev_id);
 }
 
-static void fsl_edma_issue_pending(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-
-	if (unlikely(fsl_chan->pm_state != RUNNING)) {
-		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-		/* cannot submit due to suspend */
-		return;
-	}
-
-	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
-		fsl_edma_xfer_desc(fsl_chan);
-
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-}
-
 static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 		struct of_dma *ofdma)
 {
@@ -781,34 +122,6 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 	return NULL;
 }
 
-static int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-
-	fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev,
-				sizeof(struct fsl_edma_hw_tcd),
-				32, 0);
-	return 0;
-}
-
-static void fsl_edma_free_chan_resources(struct dma_chan *chan)
-{
-	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	unsigned long flags;
-	LIST_HEAD(head);
-
-	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
-	fsl_edma_disable_request(fsl_chan);
-	fsl_edma_chan_mux(fsl_chan, 0, false);
-	fsl_chan->edesc = NULL;
-	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
-	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
-
-	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
-	dma_pool_destroy(fsl_chan->tcd_pool);
-	fsl_chan->tcd_pool = NULL;
-}
-
 static int
 fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
 {
@@ -876,6 +189,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct fsl_edma_engine *fsl_edma;
 	struct fsl_edma_chan *fsl_chan;
+	struct edma_regs *regs;
 	struct resource *res;
 	int len, chans;
 	int ret, i;
@@ -891,6 +205,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	if (!fsl_edma)
 		return -ENOMEM;
 
+	fsl_edma->version = v1;
 	fsl_edma->n_chans = chans;
 	mutex_init(&fsl_edma->fsl_edma_mutex);
 
@@ -899,6 +214,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	if (IS_ERR(fsl_edma->membase))
 		return PTR_ERR(fsl_edma->membase);
 
+	fsl_edma_setup_regs(fsl_edma);
+	regs = &fsl_edma->regs;
+
 	for (i = 0; i < DMAMUX_NR; i++) {
 		char clkname[32];
 
@@ -939,11 +257,11 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
-		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		edma_writew(fsl_edma, 0x0, &regs->tcd[i].csr);
 		fsl_edma_chan_mux(fsl_chan, 0, false);
 	}
 
-	edma_writel(fsl_edma, ~0, fsl_edma->membase + EDMA_INTR);
+	edma_writel(fsl_edma, ~0, regs->intl);
 	ret = fsl_edma_irq_init(pdev, fsl_edma);
 	if (ret)
 		return ret;
@@ -990,22 +308,11 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	}
 
 	/* enable round robin arbitration */
-	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, fsl_edma->membase + EDMA_CR);
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
 
 	return 0;
 }
 
-static void fsl_edma_cleanup_vchan(struct dma_device *dmadev)
-{
-	struct fsl_edma_chan *chan, *_chan;
-
-	list_for_each_entry_safe(chan, _chan,
-				&dmadev->channels, vchan.chan.device_node) {
-		list_del(&chan->vchan.chan.device_node);
-		tasklet_kill(&chan->vchan.task);
-	}
-}
-
 static int fsl_edma_remove(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -1048,18 +355,18 @@ static int fsl_edma_resume_early(struct device *dev)
 {
 	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
 	struct fsl_edma_chan *fsl_chan;
+	struct edma_regs *regs = &fsl_edma->regs;
 	int i;
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		fsl_chan = &fsl_edma->chans[i];
 		fsl_chan->pm_state = RUNNING;
-		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		edma_writew(fsl_edma, 0x0, &regs->tcd[i].csr);
 		if (fsl_chan->slave_id != 0)
 			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
 	}
 
-	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA,
-			fsl_edma->membase + EDMA_CR);
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
 
 	return 0;
 }
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 1117b5123a6f..9d360a3fbae3 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -987,7 +987,7 @@ static void dma_do_tasklet(unsigned long data)
 
 	chan_dbg(chan, "tasklet entry\n");
 
-	spin_lock_bh(&chan->desc_lock);
+	spin_lock(&chan->desc_lock);
 
 	/* the hardware is now idle and ready for more */
 	chan->idle = true;
@@ -995,7 +995,7 @@ static void dma_do_tasklet(unsigned long data)
 	/* Run all cleanup for descriptors which have been completed */
 	fsldma_cleanup_descriptors(chan);
 
-	spin_unlock_bh(&chan->desc_lock);
+	spin_unlock(&chan->desc_lock);
 
 	chan_dbg(chan, "tasklet exit\n");
 }
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 202ffa9f7611..e06f20272fd7 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -348,10 +348,6 @@ static int hsu_dma_slave_config(struct dma_chan *chan,
 {
 	struct hsu_dma_chan *hsuc = to_hsu_dma_chan(chan);
 
-	/* Check if chan will be configured for slave transfers */
-	if (!is_slave_direction(config->direction))
-		return -EINVAL;
-
 	memcpy(&hsuc->config, config, sizeof(hsuc->config));
 
 	return 0;
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 1fbf9cb9b742..0baf9797cc09 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -142,9 +142,8 @@ static void idma64_chan_irq(struct idma64 *idma64, unsigned short c,
 {
 	struct idma64_chan *idma64c = &idma64->chan[c];
 	struct idma64_desc *desc;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idma64c->vchan.lock, flags);
+	spin_lock(&idma64c->vchan.lock);
 	desc = idma64c->desc;
 	if (desc) {
 		if (status_err & (1 << c)) {
@@ -161,7 +160,7 @@ static void idma64_chan_irq(struct idma64 *idma64, unsigned short c,
 		if (idma64c->desc == NULL || desc->status == DMA_ERROR)
 			idma64_stop_transfer(idma64c);
 	}
-	spin_unlock_irqrestore(&idma64c->vchan.lock, flags);
+	spin_unlock(&idma64c->vchan.lock);
 }
 
 static irqreturn_t idma64_irq(int irq, void *dev)
@@ -408,10 +407,6 @@ static int idma64_slave_config(struct dma_chan *chan,
 {
 	struct idma64_chan *idma64c = to_idma64_chan(chan);
 
-	/* Check if chan will be configured for slave transfers */
-	if (!is_slave_direction(config->direction))
-		return -EINVAL;
-
 	memcpy(&idma64c->config, config, sizeof(idma64c->config));
 
 	convert_burst(&idma64c->config.src_maxburst);
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 75b6ff0415ee..c2fff3f6c9ca 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -162,6 +162,7 @@ struct imxdma_channel {
 	bool				enabled_2d;
 	int				slot_2d;
 	unsigned int			irq;
+	struct dma_slave_config		config;
 };
 
 enum imx_dma_type {
@@ -675,14 +676,15 @@ static int imxdma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
-static int imxdma_config(struct dma_chan *chan,
-			 struct dma_slave_config *dmaengine_cfg)
+static int imxdma_config_write(struct dma_chan *chan,
+			       struct dma_slave_config *dmaengine_cfg,
+			       enum dma_transfer_direction direction)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	unsigned int mode = 0;
 
-	if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		imxdmac->per_address = dmaengine_cfg->src_addr;
 		imxdmac->watermark_level = dmaengine_cfg->src_maxburst;
 		imxdmac->word_size = dmaengine_cfg->src_addr_width;
@@ -723,6 +725,16 @@ static int imxdma_config(struct dma_chan *chan,
 	return 0;
 }
 
+static int imxdma_config(struct dma_chan *chan,
+			 struct dma_slave_config *dmaengine_cfg)
+{
+	struct imxdma_channel *imxdmac = to_imxdma_chan(chan);
+
+	memcpy(&imxdmac->config, dmaengine_cfg, sizeof(*dmaengine_cfg));
+
+	return 0;
+}
+
 static enum dma_status imxdma_tx_status(struct dma_chan *chan,
 					    dma_cookie_t cookie,
 					    struct dma_tx_state *txstate)
@@ -905,6 +917,8 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	desc->desc.callback = NULL;
 	desc->desc.callback_param = NULL;
 
+	imxdma_config_write(chan, &imxdmac->config, direction);
+
 	return &desc->desc;
 }
 
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 4fa4c06c9edb..0fec3c554fe3 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -129,7 +129,7 @@ static void
 ioat_init_channel(struct ioatdma_device *ioat_dma,
 		  struct ioatdma_chan *ioat_chan, int idx);
 static void ioat_intr_quirk(struct ioatdma_device *ioat_dma);
-static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma);
+static void ioat_enumerate_channels(struct ioatdma_device *ioat_dma);
 static int ioat3_dma_self_test(struct ioatdma_device *ioat_dma);
 
 static int ioat_dca_enabled = 1;
@@ -575,7 +575,7 @@ static void ioat_dma_remove(struct ioatdma_device *ioat_dma)
  * ioat_enumerate_channels - find and initialize the device's channels
  * @ioat_dma: the ioat dma device to be enumerated
  */
-static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
+static void ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
 {
 	struct ioatdma_chan *ioat_chan;
 	struct device *dev = &ioat_dma->pdev->dev;
@@ -594,7 +594,7 @@ static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
 	xfercap_log = readb(ioat_dma->reg_base + IOAT_XFERCAP_OFFSET);
 	xfercap_log &= 0x1f; /* bits [4:0] valid */
 	if (xfercap_log == 0)
-		return 0;
+		return;
 	dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
 
 	for (i = 0; i < dma->chancnt; i++) {
@@ -611,7 +611,6 @@ static int ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
 		}
 	}
 	dma->chancnt = i;
-	return i;
 }
 
 /**
@@ -1205,8 +1204,15 @@ static void ioat_shutdown(struct pci_dev *pdev)
 
 		spin_lock_bh(&ioat_chan->prep_lock);
 		set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
-		del_timer_sync(&ioat_chan->timer);
 		spin_unlock_bh(&ioat_chan->prep_lock);
+		/*
+		 * Synchronization rule for del_timer_sync():
+		 *  - The caller must not hold locks which would prevent
+		 *    completion of the timer's handler.
+		 * So prep_lock cannot be held before calling it.
+		 */
+		del_timer_sync(&ioat_chan->timer);
+
 		/* this should quiesce then reset */
 		ioat_reset_hw(ioat_chan);
 	}
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 6bfa217ed6d0..fdec2b6cfbb0 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -87,10 +87,10 @@ struct k3_dma_chan {
 	struct virt_dma_chan	vc;
 	struct k3_dma_phy	*phy;
 	struct list_head	node;
-	enum dma_transfer_direction dir;
 	dma_addr_t		dev_addr;
 	enum dma_status		status;
 	bool			cyclic;
+	struct dma_slave_config	slave_config;
 };
 
 struct k3_dma_phy {
@@ -118,6 +118,10 @@ struct k3_dma_dev {
 
 #define to_k3_dma(dmadev) container_of(dmadev, struct k3_dma_dev, slave)
 
+static int k3_dma_config_write(struct dma_chan *chan,
+			       enum dma_transfer_direction dir,
+			       struct dma_slave_config *cfg);
+
 static struct k3_dma_chan *to_k3_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct k3_dma_chan, vc.chan);
@@ -501,14 +505,8 @@ static struct dma_async_tx_descriptor *k3_dma_prep_memcpy(
 		copy = min_t(size_t, len, DMA_MAX_SIZE);
 		k3_dma_fill_desc(ds, dst, src, copy, num++, c->ccfg);
 
-		if (c->dir == DMA_MEM_TO_DEV) {
-			src += copy;
-		} else if (c->dir == DMA_DEV_TO_MEM) {
-			dst += copy;
-		} else {
-			src += copy;
-			dst += copy;
-		}
+		src += copy;
+		dst += copy;
 		len -= copy;
 	} while (len);
 
@@ -542,6 +540,7 @@ static struct dma_async_tx_descriptor *k3_dma_prep_slave_sg(
 	if (!ds)
 		return NULL;
 	num = 0;
+	k3_dma_config_write(chan, dir, &c->slave_config);
 
 	for_each_sg(sgl, sg, sglen, i) {
 		addr = sg_dma_address(sg);
@@ -602,6 +601,7 @@ k3_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 	avail = buf_len;
 	total = avail;
 	num = 0;
+	k3_dma_config_write(chan, dir, &c->slave_config);
 
 	if (period_len < modulo)
 		modulo = period_len;
@@ -642,18 +642,26 @@ static int k3_dma_config(struct dma_chan *chan,
 			 struct dma_slave_config *cfg)
 {
 	struct k3_dma_chan *c = to_k3_chan(chan);
+
+	memcpy(&c->slave_config, cfg, sizeof(*cfg));
+
+	return 0;
+}
+
+static int k3_dma_config_write(struct dma_chan *chan,
+			       enum dma_transfer_direction dir,
+			       struct dma_slave_config *cfg)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
 	u32 maxburst = 0, val = 0;
 	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
 
-	if (cfg == NULL)
-		return -EINVAL;
-	c->dir = cfg->direction;
-	if (c->dir == DMA_DEV_TO_MEM) {
+	if (dir == DMA_DEV_TO_MEM) {
 		c->ccfg = CX_CFG_DSTINCR;
 		c->dev_addr = cfg->src_addr;
 		maxburst = cfg->src_maxburst;
 		width = cfg->src_addr_width;
-	} else if (c->dir == DMA_MEM_TO_DEV) {
+	} else if (dir == DMA_MEM_TO_DEV) {
 		c->ccfg = CX_CFG_SRCINCR;
 		c->dev_addr = cfg->dst_addr;
 		maxburst = cfg->dst_maxburst;
diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c
new file mode 100644
index 000000000000..5de1b07eddff
--- /dev/null
+++ b/drivers/dma/mcf-edma.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2013-2014 Freescale Semiconductor, Inc
+// Copyright (c) 2017 Sysam, Angelo Dureghello  <angelo@sysam.it>
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/dma-mcf-edma.h>
+
+#include "fsl-edma-common.h"
+
+#define EDMA_CHANNELS		64
+#define EDMA_MASK_CH(x)		((x) & GENMASK(5, 0))
+
+static irqreturn_t mcf_edma_tx_handler(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *mcf_edma = dev_id;
+	struct edma_regs *regs = &mcf_edma->regs;
+	unsigned int ch;
+	struct fsl_edma_chan *mcf_chan;
+	u64 intmap;
+
+	intmap = ioread32(regs->inth);
+	intmap <<= 32;
+	intmap |= ioread32(regs->intl);
+	if (!intmap)
+		return IRQ_NONE;
+
+	for (ch = 0; ch < mcf_edma->n_chans; ch++) {
+		if (intmap & BIT(ch)) {
+			iowrite8(EDMA_MASK_CH(ch), regs->cint);
+
+			mcf_chan = &mcf_edma->chans[ch];
+
+			spin_lock(&mcf_chan->vchan.lock);
+			if (!mcf_chan->edesc->iscyclic) {
+				list_del(&mcf_chan->edesc->vdesc.node);
+				vchan_cookie_complete(&mcf_chan->edesc->vdesc);
+				mcf_chan->edesc = NULL;
+				mcf_chan->status = DMA_COMPLETE;
+				mcf_chan->idle = true;
+			} else {
+				vchan_cyclic_callback(&mcf_chan->edesc->vdesc);
+			}
+
+			if (!mcf_chan->edesc)
+				fsl_edma_xfer_desc(mcf_chan);
+
+			spin_unlock(&mcf_chan->vchan.lock);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mcf_edma_err_handler(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *mcf_edma = dev_id;
+	struct edma_regs *regs = &mcf_edma->regs;
+	unsigned int err, ch;
+
+	err = ioread32(regs->errl);
+	if (!err)
+		return IRQ_NONE;
+
+	for (ch = 0; ch < (EDMA_CHANNELS / 2); ch++) {
+		if (err & BIT(ch)) {
+			fsl_edma_disable_request(&mcf_edma->chans[ch]);
+			iowrite8(EDMA_CERR_CERR(ch), regs->cerr);
+			mcf_edma->chans[ch].status = DMA_ERROR;
+			mcf_edma->chans[ch].idle = true;
+		}
+	}
+
+	err = ioread32(regs->errh);
+	if (!err)
+		return IRQ_NONE;
+
+	for (ch = (EDMA_CHANNELS / 2); ch < EDMA_CHANNELS; ch++) {
+		if (err & (BIT(ch - (EDMA_CHANNELS / 2)))) {
+			fsl_edma_disable_request(&mcf_edma->chans[ch]);
+			iowrite8(EDMA_CERR_CERR(ch), regs->cerr);
+			mcf_edma->chans[ch].status = DMA_ERROR;
+			mcf_edma->chans[ch].idle = true;
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int mcf_edma_irq_init(struct platform_device *pdev,
+				struct fsl_edma_engine *mcf_edma)
+{
+	int ret = 0, i;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev,
+				IORESOURCE_IRQ, "edma-tx-00-15");
+	if (!res)
+		return -1;
+
+	for (ret = 0, i = res->start; i <= res->end; ++i)
+		ret |= request_irq(i, mcf_edma_tx_handler, 0, "eDMA", mcf_edma);
+	if (ret)
+		return ret;
+
+	res = platform_get_resource_byname(pdev,
+			IORESOURCE_IRQ, "edma-tx-16-55");
+	if (!res)
+		return -1;
+
+	for (ret = 0, i = res->start; i <= res->end; ++i)
+		ret |= request_irq(i, mcf_edma_tx_handler, 0, "eDMA", mcf_edma);
+	if (ret)
+		return ret;
+
+	ret = platform_get_irq_byname(pdev, "edma-tx-56-63");
+	if (ret != -ENXIO) {
+		ret = request_irq(ret, mcf_edma_tx_handler,
+				  0, "eDMA", mcf_edma);
+		if (ret)
+			return ret;
+	}
+
+	ret = platform_get_irq_byname(pdev, "edma-err");
+	if (ret != -ENXIO) {
+		ret = request_irq(ret, mcf_edma_err_handler,
+				  0, "eDMA", mcf_edma);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void mcf_edma_irq_free(struct platform_device *pdev,
+				struct fsl_edma_engine *mcf_edma)
+{
+	int irq;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev,
+			IORESOURCE_IRQ, "edma-tx-00-15");
+	if (res) {
+		for (irq = res->start; irq <= res->end; irq++)
+			free_irq(irq, mcf_edma);
+	}
+
+	res = platform_get_resource_byname(pdev,
+			IORESOURCE_IRQ, "edma-tx-16-55");
+	if (res) {
+		for (irq = res->start; irq <= res->end; irq++)
+			free_irq(irq, mcf_edma);
+	}
+
+	irq = platform_get_irq_byname(pdev, "edma-tx-56-63");
+	if (irq != -ENXIO)
+		free_irq(irq, mcf_edma);
+
+	irq = platform_get_irq_byname(pdev, "edma-err");
+	if (irq != -ENXIO)
+		free_irq(irq, mcf_edma);
+}
+
+static int mcf_edma_probe(struct platform_device *pdev)
+{
+	struct mcf_edma_platform_data *pdata;
+	struct fsl_edma_engine *mcf_edma;
+	struct fsl_edma_chan *mcf_chan;
+	struct edma_regs *regs;
+	struct resource *res;
+	int ret, i, len, chans;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "no platform data supplied\n");
+		return -EINVAL;
+	}
+
+	chans = pdata->dma_channels;
+	len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans;
+	mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!mcf_edma)
+		return -ENOMEM;
+
+	mcf_edma->n_chans = chans;
+
+	/* Set up version for ColdFire edma */
+	mcf_edma->version = v2;
+	mcf_edma->big_endian = 1;
+
+	if (!mcf_edma->n_chans) {
+		dev_info(&pdev->dev, "setting default channel number to 64");
+		mcf_edma->n_chans = 64;
+	}
+
+	mutex_init(&mcf_edma->fsl_edma_mutex);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	mcf_edma->membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mcf_edma->membase))
+		return PTR_ERR(mcf_edma->membase);
+
+	fsl_edma_setup_regs(mcf_edma);
+	regs = &mcf_edma->regs;
+
+	INIT_LIST_HEAD(&mcf_edma->dma_dev.channels);
+	for (i = 0; i < mcf_edma->n_chans; i++) {
+		struct fsl_edma_chan *mcf_chan = &mcf_edma->chans[i];
+
+		mcf_chan->edma = mcf_edma;
+		mcf_chan->slave_id = i;
+		mcf_chan->idle = true;
+		mcf_chan->vchan.desc_free = fsl_edma_free_desc;
+		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
+		iowrite32(0x0, &regs->tcd[i].csr);
+	}
+
+	iowrite32(~0, regs->inth);
+	iowrite32(~0, regs->intl);
+
+	ret = mcf_edma_irq_init(pdev, mcf_edma);
+	if (ret)
+		return ret;
+
+	dma_cap_set(DMA_PRIVATE, mcf_edma->dma_dev.cap_mask);
+	dma_cap_set(DMA_SLAVE, mcf_edma->dma_dev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, mcf_edma->dma_dev.cap_mask);
+
+	mcf_edma->dma_dev.dev = &pdev->dev;
+	mcf_edma->dma_dev.device_alloc_chan_resources =
+			fsl_edma_alloc_chan_resources;
+	mcf_edma->dma_dev.device_free_chan_resources =
+			fsl_edma_free_chan_resources;
+	mcf_edma->dma_dev.device_config = fsl_edma_slave_config;
+	mcf_edma->dma_dev.device_prep_dma_cyclic =
+			fsl_edma_prep_dma_cyclic;
+	mcf_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg;
+	mcf_edma->dma_dev.device_tx_status = fsl_edma_tx_status;
+	mcf_edma->dma_dev.device_pause = fsl_edma_pause;
+	mcf_edma->dma_dev.device_resume = fsl_edma_resume;
+	mcf_edma->dma_dev.device_terminate_all = fsl_edma_terminate_all;
+	mcf_edma->dma_dev.device_issue_pending = fsl_edma_issue_pending;
+
+	mcf_edma->dma_dev.src_addr_widths = FSL_EDMA_BUSWIDTHS;
+	mcf_edma->dma_dev.dst_addr_widths = FSL_EDMA_BUSWIDTHS;
+	mcf_edma->dma_dev.directions =
+			BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+
+	mcf_edma->dma_dev.filter.fn = mcf_edma_filter_fn;
+	mcf_edma->dma_dev.filter.map = pdata->slave_map;
+	mcf_edma->dma_dev.filter.mapcnt = pdata->slavecnt;
+
+	platform_set_drvdata(pdev, mcf_edma);
+
+	ret = dma_async_device_register(&mcf_edma->dma_dev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Can't register Freescale eDMA engine. (%d)\n", ret);
+		return ret;
+	}
+
+	/* Enable round robin arbitration */
+	iowrite32(EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
+
+	return 0;
+}
+
+static int mcf_edma_remove(struct platform_device *pdev)
+{
+	struct fsl_edma_engine *mcf_edma = platform_get_drvdata(pdev);
+
+	mcf_edma_irq_free(pdev, mcf_edma);
+	fsl_edma_cleanup_vchan(&mcf_edma->dma_dev);
+	dma_async_device_unregister(&mcf_edma->dma_dev);
+
+	return 0;
+}
+
+static struct platform_driver mcf_edma_driver = {
+	.driver		= {
+		.name	= "mcf-edma",
+	},
+	.probe		= mcf_edma_probe,
+	.remove		= mcf_edma_remove,
+};
+
+bool mcf_edma_filter_fn(struct dma_chan *chan, void *param)
+{
+	if (chan->device->dev->driver == &mcf_edma_driver.driver) {
+		struct fsl_edma_chan *mcf_chan = to_fsl_edma_chan(chan);
+
+		return (mcf_chan->slave_id == (uintptr_t)param);
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(mcf_edma_filter_fn);
+
+static int __init mcf_edma_init(void)
+{
+	return platform_driver_register(&mcf_edma_driver);
+}
+subsys_initcall(mcf_edma_init);
+
+static void __exit mcf_edma_exit(void)
+{
+	platform_driver_unregister(&mcf_edma_driver);
+}
+module_exit(mcf_edma_exit);
+
+MODULE_ALIAS("platform:mcf-edma");
+MODULE_DESCRIPTION("Freescale eDMA engine driver, ColdFire family");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 13c68b6434ce..0c56faa03e9a 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -116,6 +116,7 @@ struct mmp_tdma_chan {
 	u32				burst_sz;
 	enum dma_slave_buswidth		buswidth;
 	enum dma_status			status;
+	struct dma_slave_config		slave_config;
 
 	int				idx;
 	enum mmp_tdma_type		type;
@@ -139,6 +140,10 @@ struct mmp_tdma_device {
 
 #define to_mmp_tdma_chan(dchan) container_of(dchan, struct mmp_tdma_chan, chan)
 
+static int mmp_tdma_config_write(struct dma_chan *chan,
+				 enum dma_transfer_direction dir,
+				 struct dma_slave_config *dmaengine_cfg);
+
 static void mmp_tdma_chan_set_desc(struct mmp_tdma_chan *tdmac, dma_addr_t phys)
 {
 	writel(phys, tdmac->reg_base + TDNDPR);
@@ -442,6 +447,8 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 	if (!desc)
 		goto err_out;
 
+	mmp_tdma_config_write(chan, direction, &tdmac->slave_config);
+
 	while (buf < buf_len) {
 		desc = &tdmac->desc_arr[i];
 
@@ -495,7 +502,18 @@ static int mmp_tdma_config(struct dma_chan *chan,
 {
 	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
 
-	if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
+	memcpy(&tdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
+
+	return 0;
+}
+
+static int mmp_tdma_config_write(struct dma_chan *chan,
+				 enum dma_transfer_direction dir,
+				 struct dma_slave_config *dmaengine_cfg)
+{
+	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
+
+	if (dir == DMA_DEV_TO_MEM) {
 		tdmac->dev_addr = dmaengine_cfg->src_addr;
 		tdmac->burst_sz = dmaengine_cfg->src_maxburst;
 		tdmac->buswidth = dmaengine_cfg->src_addr_width;
@@ -504,7 +522,7 @@ static int mmp_tdma_config(struct dma_chan *chan,
 		tdmac->burst_sz = dmaengine_cfg->dst_maxburst;
 		tdmac->buswidth = dmaengine_cfg->dst_addr_width;
 	}
-	tdmac->dir = dmaengine_cfg->direction;
+	tdmac->dir = dir;
 
 	return mmp_tdma_config_chan(chan);
 }
@@ -530,9 +548,6 @@ static void mmp_tdma_issue_pending(struct dma_chan *chan)
 
 static int mmp_tdma_remove(struct platform_device *pdev)
 {
-	struct mmp_tdma_device *tdev = platform_get_drvdata(pdev);
-
-	dma_async_device_unregister(&tdev->device);
 	return 0;
 }
 
@@ -696,7 +711,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	platform_set_drvdata(pdev, tdev);
 
-	ret = dma_async_device_register(&tdev->device);
+	ret = dmaenginem_async_device_register(&tdev->device);
 	if (ret) {
 		dev_err(tdev->device.dev, "unable to register\n");
 		return ret;
@@ -708,7 +723,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(tdev->device.dev,
 				"failed to register controller\n");
-			dma_async_device_unregister(&tdev->device);
+			return ret;
 		}
 	}
 
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 969534c1a6c6..7f595355fb79 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -348,9 +348,9 @@ static void mv_xor_tasklet(unsigned long data)
 {
 	struct mv_xor_chan *chan = (struct mv_xor_chan *) data;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock(&chan->lock);
 	mv_chan_slot_cleanup(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock(&chan->lock);
 }
 
 static struct mv_xor_desc_slot *
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index ae5182ff0128..35193b31a9e0 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -847,7 +847,7 @@ static int __init mxs_dma_probe(struct platform_device *pdev)
 	mxs_dma->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	mxs_dma->dma_device.device_issue_pending = mxs_dma_enable_chan;
 
-	ret = dma_async_device_register(&mxs_dma->dma_device);
+	ret = dmaenginem_async_device_register(&mxs_dma->dma_device);
 	if (ret) {
 		dev_err(mxs_dma->dma_device.dev, "unable to register\n");
 		return ret;
@@ -857,7 +857,6 @@ static int __init mxs_dma_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(mxs_dma->dma_device.dev,
 			"failed to register controller\n");
-		dma_async_device_unregister(&mxs_dma->dma_device);
 	}
 
 	dev_info(mxs_dma->dma_device.dev, "initialized\n");
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 8c7b2e8703da..a67b292190f4 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013-2014 Renesas Electronics Europe Ltd.
  * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitmap.h>
@@ -1095,8 +1092,8 @@ static struct dma_chan *nbpf_of_xlate(struct of_phandle_args *dma_spec,
 	if (!dchan)
 		return NULL;
 
-	dev_dbg(dchan->device->dev, "Entry %s(%s)\n", __func__,
-		dma_spec->np->name);
+	dev_dbg(dchan->device->dev, "Entry %s(%pOFn)\n", __func__,
+		dma_spec->np);
 
 	chan = nbpf_to_chan(dchan);
 
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 7812a6338acd..90bbcef99ef8 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/of_dma.h>
 #include <linux/slab.h>
 #include "virt-dma.h"
 
@@ -161,10 +162,12 @@ struct owl_dma_lli {
  * struct owl_dma_txd - Wrapper for struct dma_async_tx_descriptor
  * @vd: virtual DMA descriptor
  * @lli_list: link list of lli nodes
+ * @cyclic: flag to indicate cyclic transfers
  */
 struct owl_dma_txd {
 	struct virt_dma_desc	vd;
 	struct list_head	lli_list;
+	bool			cyclic;
 };
 
 /**
@@ -186,11 +189,15 @@ struct owl_dma_pchan {
  * @vc: wrappped virtual channel
  * @pchan: the physical channel utilized by this channel
  * @txd: active transaction on this channel
+ * @cfg: slave configuration for this channel
+ * @drq: physical DMA request ID for this channel
  */
 struct owl_dma_vchan {
 	struct virt_dma_chan	vc;
 	struct owl_dma_pchan	*pchan;
 	struct owl_dma_txd	*txd;
+	struct dma_slave_config cfg;
+	u8			drq;
 };
 
 /**
@@ -200,6 +207,7 @@ struct owl_dma_vchan {
  * @clk: clock for the DMA controller
  * @lock: a lock to use when change DMA controller global register
  * @lli_pool: a pool for the LLI descriptors
+ * @irq: interrupt ID for the DMA controller
  * @nr_pchans: the number of physical channels
  * @pchans: array of data for the physical channels
  * @nr_vchans: the number of physical channels
@@ -336,9 +344,11 @@ static struct owl_dma_lli *owl_dma_alloc_lli(struct owl_dma *od)
 
 static struct owl_dma_lli *owl_dma_add_lli(struct owl_dma_txd *txd,
 					   struct owl_dma_lli *prev,
-					   struct owl_dma_lli *next)
+					   struct owl_dma_lli *next,
+					   bool is_cyclic)
 {
-	list_add_tail(&next->node, &txd->lli_list);
+	if (!is_cyclic)
+		list_add_tail(&next->node, &txd->lli_list);
 
 	if (prev) {
 		prev->hw.next_lli = next->phys;
@@ -351,7 +361,9 @@ static struct owl_dma_lli *owl_dma_add_lli(struct owl_dma_txd *txd,
 static inline int owl_dma_cfg_lli(struct owl_dma_vchan *vchan,
 				  struct owl_dma_lli *lli,
 				  dma_addr_t src, dma_addr_t dst,
-				  u32 len, enum dma_transfer_direction dir)
+				  u32 len, enum dma_transfer_direction dir,
+				  struct dma_slave_config *sconfig,
+				  bool is_cyclic)
 {
 	struct owl_dma_lli_hw *hw = &lli->hw;
 	u32 mode;
@@ -365,6 +377,32 @@ static inline int owl_dma_cfg_lli(struct owl_dma_vchan *vchan,
 			OWL_DMA_MODE_DAM_INC;
 
 		break;
+	case DMA_MEM_TO_DEV:
+		mode |= OWL_DMA_MODE_TS(vchan->drq)
+			| OWL_DMA_MODE_ST_DCU | OWL_DMA_MODE_DT_DEV
+			| OWL_DMA_MODE_SAM_INC | OWL_DMA_MODE_DAM_CONST;
+
+		/*
+		 * Hardware only supports 32bit and 8bit buswidth. Since the
+		 * default is 32bit, select 8bit only when requested.
+		 */
+		if (sconfig->dst_addr_width == DMA_SLAVE_BUSWIDTH_1_BYTE)
+			mode |= OWL_DMA_MODE_NDDBW_8BIT;
+
+		break;
+	case DMA_DEV_TO_MEM:
+		 mode |= OWL_DMA_MODE_TS(vchan->drq)
+			| OWL_DMA_MODE_ST_DEV | OWL_DMA_MODE_DT_DCU
+			| OWL_DMA_MODE_SAM_CONST | OWL_DMA_MODE_DAM_INC;
+
+		/*
+		 * Hardware only supports 32bit and 8bit buswidth. Since the
+		 * default is 32bit, select 8bit only when requested.
+		 */
+		if (sconfig->src_addr_width == DMA_SLAVE_BUSWIDTH_1_BYTE)
+			mode |= OWL_DMA_MODE_NDDBW_8BIT;
+
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -381,7 +419,10 @@ static inline int owl_dma_cfg_lli(struct owl_dma_vchan *vchan,
 				 OWL_DMA_LLC_SAV_LOAD_NEXT |
 				 OWL_DMA_LLC_DAV_LOAD_NEXT);
 
-	hw->ctrlb = llc_hw_ctrlb(OWL_DMA_INTCTL_SUPER_BLOCK);
+	if (is_cyclic)
+		hw->ctrlb = llc_hw_ctrlb(OWL_DMA_INTCTL_BLOCK);
+	else
+		hw->ctrlb = llc_hw_ctrlb(OWL_DMA_INTCTL_SUPER_BLOCK);
 
 	return 0;
 }
@@ -443,6 +484,16 @@ static void owl_dma_terminate_pchan(struct owl_dma *od,
 	spin_unlock_irqrestore(&od->lock, flags);
 }
 
+static void owl_dma_pause_pchan(struct owl_dma_pchan *pchan)
+{
+	pchan_writel(pchan, 1, OWL_DMAX_PAUSE);
+}
+
+static void owl_dma_resume_pchan(struct owl_dma_pchan *pchan)
+{
+	pchan_writel(pchan, 0, OWL_DMAX_PAUSE);
+}
+
 static int owl_dma_start_next_txd(struct owl_dma_vchan *vchan)
 {
 	struct owl_dma *od = to_owl_dma(vchan->vc.chan.device);
@@ -464,7 +515,10 @@ static int owl_dma_start_next_txd(struct owl_dma_vchan *vchan)
 	lli = list_first_entry(&txd->lli_list,
 			       struct owl_dma_lli, node);
 
-	int_ctl = OWL_DMA_INTCTL_SUPER_BLOCK;
+	if (txd->cyclic)
+		int_ctl = OWL_DMA_INTCTL_BLOCK;
+	else
+		int_ctl = OWL_DMA_INTCTL_SUPER_BLOCK;
 
 	pchan_writel(pchan, OWL_DMAX_MODE, OWL_DMA_MODE_LME);
 	pchan_writel(pchan, OWL_DMAX_LINKLIST_CTL,
@@ -627,6 +681,54 @@ static int owl_dma_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static int owl_dma_config(struct dma_chan *chan,
+			  struct dma_slave_config *config)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+
+	/* Reject definitely invalid configurations */
+	if (config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	memcpy(&vchan->cfg, config, sizeof(struct dma_slave_config));
+
+	return 0;
+}
+
+static int owl_dma_pause(struct dma_chan *chan)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+
+	owl_dma_pause_pchan(vchan->pchan);
+
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	return 0;
+}
+
+static int owl_dma_resume(struct dma_chan *chan)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	unsigned long flags;
+
+	if (!vchan->pchan && !vchan->txd)
+		return 0;
+
+	dev_dbg(chan2dev(chan), "vchan %p: resume\n", &vchan->vc);
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+
+	owl_dma_resume_pchan(vchan->pchan);
+
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	return 0;
+}
+
 static u32 owl_dma_getbytes_chan(struct owl_dma_vchan *vchan)
 {
 	struct owl_dma_pchan *pchan;
@@ -754,13 +856,14 @@ static struct dma_async_tx_descriptor
 		bytes = min_t(size_t, (len - offset), OWL_DMA_FRAME_MAX_LENGTH);
 
 		ret = owl_dma_cfg_lli(vchan, lli, src + offset, dst + offset,
-				      bytes, DMA_MEM_TO_MEM);
+				      bytes, DMA_MEM_TO_MEM,
+				      &vchan->cfg, txd->cyclic);
 		if (ret) {
 			dev_warn(chan2dev(chan), "failed to config lli\n");
 			goto err_txd_free;
 		}
 
-		prev = owl_dma_add_lli(txd, prev, lli);
+		prev = owl_dma_add_lli(txd, prev, lli, false);
 	}
 
 	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
@@ -770,6 +873,133 @@ err_txd_free:
 	return NULL;
 }
 
+static struct dma_async_tx_descriptor
+		*owl_dma_prep_slave_sg(struct dma_chan *chan,
+				       struct scatterlist *sgl,
+				       unsigned int sg_len,
+				       enum dma_transfer_direction dir,
+				       unsigned long flags, void *context)
+{
+	struct owl_dma *od = to_owl_dma(chan->device);
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	struct dma_slave_config *sconfig = &vchan->cfg;
+	struct owl_dma_txd *txd;
+	struct owl_dma_lli *lli, *prev = NULL;
+	struct scatterlist *sg;
+	dma_addr_t addr, src = 0, dst = 0;
+	size_t len;
+	int ret, i;
+
+	txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
+	if (!txd)
+		return NULL;
+
+	INIT_LIST_HEAD(&txd->lli_list);
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+
+		if (len > OWL_DMA_FRAME_MAX_LENGTH) {
+			dev_err(od->dma.dev,
+				"frame length exceeds max supported length");
+			goto err_txd_free;
+		}
+
+		lli = owl_dma_alloc_lli(od);
+		if (!lli) {
+			dev_err(chan2dev(chan), "failed to allocate lli");
+			goto err_txd_free;
+		}
+
+		if (dir == DMA_MEM_TO_DEV) {
+			src = addr;
+			dst = sconfig->dst_addr;
+		} else {
+			src = sconfig->src_addr;
+			dst = addr;
+		}
+
+		ret = owl_dma_cfg_lli(vchan, lli, src, dst, len, dir, sconfig,
+				      txd->cyclic);
+		if (ret) {
+			dev_warn(chan2dev(chan), "failed to config lli");
+			goto err_txd_free;
+		}
+
+		prev = owl_dma_add_lli(txd, prev, lli, false);
+	}
+
+	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
+
+err_txd_free:
+	owl_dma_free_txd(od, txd);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor
+		*owl_prep_dma_cyclic(struct dma_chan *chan,
+				     dma_addr_t buf_addr, size_t buf_len,
+				     size_t period_len,
+				     enum dma_transfer_direction dir,
+				     unsigned long flags)
+{
+	struct owl_dma *od = to_owl_dma(chan->device);
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	struct dma_slave_config *sconfig = &vchan->cfg;
+	struct owl_dma_txd *txd;
+	struct owl_dma_lli *lli, *prev = NULL, *first = NULL;
+	dma_addr_t src = 0, dst = 0;
+	unsigned int periods = buf_len / period_len;
+	int ret, i;
+
+	txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
+	if (!txd)
+		return NULL;
+
+	INIT_LIST_HEAD(&txd->lli_list);
+	txd->cyclic = true;
+
+	for (i = 0; i < periods; i++) {
+		lli = owl_dma_alloc_lli(od);
+		if (!lli) {
+			dev_warn(chan2dev(chan), "failed to allocate lli");
+			goto err_txd_free;
+		}
+
+		if (dir == DMA_MEM_TO_DEV) {
+			src = buf_addr + (period_len * i);
+			dst = sconfig->dst_addr;
+		} else if (dir == DMA_DEV_TO_MEM) {
+			src = sconfig->src_addr;
+			dst = buf_addr + (period_len * i);
+		}
+
+		ret = owl_dma_cfg_lli(vchan, lli, src, dst, period_len,
+				      dir, sconfig, txd->cyclic);
+		if (ret) {
+			dev_warn(chan2dev(chan), "failed to config lli");
+			goto err_txd_free;
+		}
+
+		if (!first)
+			first = lli;
+
+		prev = owl_dma_add_lli(txd, prev, lli, false);
+	}
+
+	/* close the cyclic list */
+	owl_dma_add_lli(txd, prev, first, true);
+
+	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
+
+err_txd_free:
+	owl_dma_free_txd(od, txd);
+
+	return NULL;
+}
+
 static void owl_dma_free_chan_resources(struct dma_chan *chan)
 {
 	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
@@ -790,6 +1020,27 @@ static inline void owl_dma_free(struct owl_dma *od)
 	}
 }
 
+static struct dma_chan *owl_dma_of_xlate(struct of_phandle_args *dma_spec,
+					 struct of_dma *ofdma)
+{
+	struct owl_dma *od = ofdma->of_dma_data;
+	struct owl_dma_vchan *vchan;
+	struct dma_chan *chan;
+	u8 drq = dma_spec->args[0];
+
+	if (drq > od->nr_vchans)
+		return NULL;
+
+	chan = dma_get_any_slave_channel(&od->dma);
+	if (!chan)
+		return NULL;
+
+	vchan = to_owl_vchan(chan);
+	vchan->drq = drq;
+
+	return chan;
+}
+
 static int owl_dma_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -833,12 +1084,19 @@ static int owl_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&od->lock);
 
 	dma_cap_set(DMA_MEMCPY, od->dma.cap_mask);
+	dma_cap_set(DMA_SLAVE, od->dma.cap_mask);
+	dma_cap_set(DMA_CYCLIC, od->dma.cap_mask);
 
 	od->dma.dev = &pdev->dev;
 	od->dma.device_free_chan_resources = owl_dma_free_chan_resources;
 	od->dma.device_tx_status = owl_dma_tx_status;
 	od->dma.device_issue_pending = owl_dma_issue_pending;
 	od->dma.device_prep_dma_memcpy = owl_dma_prep_memcpy;
+	od->dma.device_prep_slave_sg = owl_dma_prep_slave_sg;
+	od->dma.device_prep_dma_cyclic = owl_prep_dma_cyclic;
+	od->dma.device_config = owl_dma_config;
+	od->dma.device_pause = owl_dma_pause;
+	od->dma.device_resume = owl_dma_resume;
 	od->dma.device_terminate_all = owl_dma_terminate_all;
 	od->dma.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
 	od->dma.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
@@ -910,8 +1168,18 @@ static int owl_dma_probe(struct platform_device *pdev)
 		goto err_pool_free;
 	}
 
+	/* Device-tree DMA controller registration */
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 owl_dma_of_xlate, od);
+	if (ret) {
+		dev_err(&pdev->dev, "of_dma_controller_register failed\n");
+		goto err_dma_unregister;
+	}
+
 	return 0;
 
+err_dma_unregister:
+	dma_async_device_unregister(&od->dma);
 err_pool_free:
 	clk_disable_unprepare(od->clk);
 	dma_pool_destroy(od->lli_pool);
@@ -923,6 +1191,7 @@ static int owl_dma_remove(struct platform_device *pdev)
 {
 	struct owl_dma *od = platform_get_drvdata(pdev);
 
+	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&od->dma);
 
 	/* Mask all interrupts for this execution environment */
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 4cf0d4d0cecf..25610286979f 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -4360,7 +4360,7 @@ static ssize_t enable_store(struct device_driver *dev, const char *buf,
 }
 static DRIVER_ATTR_RW(enable);
 
-static ssize_t poly_store(struct device_driver *dev, char *buf)
+static ssize_t poly_show(struct device_driver *dev, char *buf)
 {
 	ssize_t size = 0;
 	u32 reg;
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index b31c28b67ad3..825725057e00 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -1285,7 +1285,6 @@ static int pxad_remove(struct platform_device *op)
 
 	pxad_cleanup_debugfs(pdev);
 	pxad_free_channels(&pdev->slave);
-	dma_async_device_unregister(&pdev->slave);
 	return 0;
 }
 
@@ -1396,7 +1395,7 @@ static int pxad_init_dmadev(struct platform_device *op,
 		init_waitqueue_head(&c->wq_state);
 	}
 
-	return dma_async_device_register(&pdev->slave);
+	return dmaenginem_async_device_register(&pdev->slave);
 }
 
 static int pxad_probe(struct platform_device *op)
@@ -1433,7 +1432,7 @@ static int pxad_probe(struct platform_device *op)
 				 "#dma-requests set to default 32 as missing in OF: %d",
 				 ret);
 			nb_requestors = 32;
-		};
+		}
 	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
 		nb_requestors = pdata->nb_requestors;
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 48ee35e2bce6..74fa2b1a6a86 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -198,6 +198,7 @@ struct rcar_dmac {
 	struct dma_device engine;
 	struct device *dev;
 	void __iomem *iomem;
+	struct device_dma_parameters parms;
 
 	unsigned int n_channels;
 	struct rcar_dmac_chan *channels;
@@ -1792,6 +1793,8 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 
 	dmac->dev = &pdev->dev;
 	platform_set_drvdata(pdev, dmac);
+	dmac->dev->dma_parms = &dmac->parms;
+	dma_set_max_seg_size(dmac->dev, RCAR_DMATCR_MASK);
 	dma_set_mask_and_coherent(dmac->dev, DMA_BIT_MASK(40));
 
 	ret = rcar_dmac_parse_of(&pdev->dev, dmac);
diff --git a/drivers/dma/sh/shdma-arm.h b/drivers/dma/sh/shdma-arm.h
index a1b0ef45d6a2..7459f9a13b5b 100644
--- a/drivers/dma/sh/shdma-arm.h
+++ b/drivers/dma/sh/shdma-arm.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Renesas SuperH DMA Engine support
  *
  * Copyright (C) 2013 Renesas Electronics, Inc.
- *
- * This is free software; you can redistribute it and/or modify it under the
- * terms of version 2 the GNU General Public License as published by the Free
- * Software Foundation.
  */
 
 #ifndef SHDMA_ARM_H
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 6b5626e299b2..c51de498b5b4 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Dmaengine driver base library for DMA controllers, found on SH-based SoCs
  *
@@ -7,10 +8,6 @@
  * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
  * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/dma/sh/shdma-of.c b/drivers/dma/sh/shdma-of.c
index f999f9b0d314..be89dd894328 100644
--- a/drivers/dma/sh/shdma-of.c
+++ b/drivers/dma/sh/shdma-of.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SHDMA Device Tree glue
  *
  * Copyright (C) 2013 Renesas Electronics Inc.
  * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dmaengine.h>
diff --git a/drivers/dma/sh/shdma-r8a73a4.c b/drivers/dma/sh/shdma-r8a73a4.c
index 96ea3828c3eb..ddc9a3578353 100644
--- a/drivers/dma/sh/shdma-r8a73a4.c
+++ b/drivers/dma/sh/shdma-r8a73a4.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Renesas SuperH DMA Engine support for r8a73a4 (APE6) SoCs
  *
  * Copyright (C) 2013 Renesas Electronics, Inc.
- *
- * This is free software; you can redistribute it and/or modify it under the
- * terms of version 2 the GNU General Public License as published by the Free
- * Software Foundation.
  */
 #include <linux/sh_dma.h>
 
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index 2c0a969adc9f..bfb69909bd19 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Renesas SuperH DMA Engine support
  *
  * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
  * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
  *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 #ifndef __DMA_SHDMA_H
 #define __DMA_SHDMA_H
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 04a74e0a95b7..7971ea275387 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Renesas SuperH DMA Engine support
  *
@@ -8,11 +9,6 @@
  * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * - DMA of SuperH does not have Hardware DMA chain mode.
  * - MAX DMA size is 16MB.
  *
diff --git a/drivers/dma/sh/sudmac.c b/drivers/dma/sh/sudmac.c
index 69b9564dc9d9..30cc3553cb8b 100644
--- a/drivers/dma/sh/sudmac.c
+++ b/drivers/dma/sh/sudmac.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Renesas SUDMAC support
  *
@@ -8,10 +9,6 @@
  * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
  * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dmaengine.h>
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index 1bb1a8e09025..7f7184c3cf95 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Renesas USB DMA Controller Driver
  *
@@ -6,10 +7,6 @@
  * based on rcar-dmac.c
  * Copyright (C) 2014 Renesas Electronics Inc.
  * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 55df0d41355b..38d4e4f07c66 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -68,6 +68,7 @@
 
 /* SPRD_DMA_CHN_CFG register definition */
 #define SPRD_DMA_CHN_EN			BIT(0)
+#define SPRD_DMA_LINKLIST_EN		BIT(4)
 #define SPRD_DMA_WAIT_BDONE_OFFSET	24
 #define SPRD_DMA_DONOT_WAIT_BDONE	1
 
@@ -103,7 +104,7 @@
 #define SPRD_DMA_REQ_MODE_MASK		GENMASK(1, 0)
 #define SPRD_DMA_FIX_SEL_OFFSET		21
 #define SPRD_DMA_FIX_EN_OFFSET		20
-#define SPRD_DMA_LLIST_END_OFFSET	19
+#define SPRD_DMA_LLIST_END		BIT(19)
 #define SPRD_DMA_FRG_LEN_MASK		GENMASK(16, 0)
 
 /* SPRD_DMA_CHN_BLK_LEN register definition */
@@ -164,6 +165,7 @@ struct sprd_dma_desc {
 struct sprd_dma_chn {
 	struct virt_dma_chan	vc;
 	void __iomem		*chn_base;
+	struct sprd_dma_linklist	linklist;
 	struct dma_slave_config	slave_cfg;
 	u32			chn_num;
 	u32			dev_id;
@@ -582,7 +584,8 @@ static int sprd_dma_get_step(enum dma_slave_buswidth buswidth)
 }
 
 static int sprd_dma_fill_desc(struct dma_chan *chan,
-			      struct sprd_dma_desc *sdesc,
+			      struct sprd_dma_chn_hw *hw,
+			      unsigned int sglen, int sg_index,
 			      dma_addr_t src, dma_addr_t dst, u32 len,
 			      enum dma_transfer_direction dir,
 			      unsigned long flags,
@@ -590,7 +593,6 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 {
 	struct sprd_dma_dev *sdev = to_sprd_dma_dev(chan);
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
-	struct sprd_dma_chn_hw *hw = &sdesc->chn_hw;
 	u32 req_mode = (flags >> SPRD_DMA_REQ_SHIFT) & SPRD_DMA_REQ_MODE_MASK;
 	u32 int_mode = flags & SPRD_DMA_INT_MASK;
 	int src_datawidth, dst_datawidth, src_step, dst_step;
@@ -670,12 +672,52 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 	temp |= (src_step & SPRD_DMA_TRSF_STEP_MASK) << SPRD_DMA_SRC_TRSF_STEP_OFFSET;
 	hw->trsf_step = temp;
 
+	/* link-list configuration */
+	if (schan->linklist.phy_addr) {
+		if (sg_index == sglen - 1)
+			hw->frg_len |= SPRD_DMA_LLIST_END;
+
+		hw->cfg |= SPRD_DMA_LINKLIST_EN;
+
+		/* link-list index */
+		temp = (sg_index + 1) % sglen;
+		/* Next link-list configuration's physical address offset */
+		temp = temp * sizeof(*hw) + SPRD_DMA_CHN_SRC_ADDR;
+		/*
+		 * Set the link-list pointer point to next link-list
+		 * configuration's physical address.
+		 */
+		hw->llist_ptr = schan->linklist.phy_addr + temp;
+	} else {
+		hw->llist_ptr = 0;
+	}
+
 	hw->frg_step = 0;
 	hw->src_blk_step = 0;
 	hw->des_blk_step = 0;
 	return 0;
 }
 
+static int sprd_dma_fill_linklist_desc(struct dma_chan *chan,
+				       unsigned int sglen, int sg_index,
+				       dma_addr_t src, dma_addr_t dst, u32 len,
+				       enum dma_transfer_direction dir,
+				       unsigned long flags,
+				       struct dma_slave_config *slave_cfg)
+{
+	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	struct sprd_dma_chn_hw *hw;
+
+	if (!schan->linklist.virt_addr)
+		return -EINVAL;
+
+	hw = (struct sprd_dma_chn_hw *)(schan->linklist.virt_addr +
+					sg_index * sizeof(*hw));
+
+	return sprd_dma_fill_desc(chan, hw, sglen, sg_index, src, dst, len,
+				  dir, flags, slave_cfg);
+}
+
 static struct dma_async_tx_descriptor *
 sprd_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			 size_t len, unsigned long flags)
@@ -744,10 +786,20 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	u32 len = 0;
 	int ret, i;
 
-	/* TODO: now we only support one sg for each DMA configuration. */
-	if (!is_slave_direction(dir) || sglen > 1)
+	if (!is_slave_direction(dir))
 		return NULL;
 
+	if (context) {
+		struct sprd_dma_linklist *ll_cfg =
+			(struct sprd_dma_linklist *)context;
+
+		schan->linklist.phy_addr = ll_cfg->phy_addr;
+		schan->linklist.virt_addr = ll_cfg->virt_addr;
+	} else {
+		schan->linklist.phy_addr = 0;
+		schan->linklist.virt_addr = 0;
+	}
+
 	sdesc = kzalloc(sizeof(*sdesc), GFP_NOWAIT);
 	if (!sdesc)
 		return NULL;
@@ -762,10 +814,25 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			src = slave_cfg->src_addr;
 			dst = sg_dma_address(sg);
 		}
+
+		/*
+		 * The link-list mode needs at least 2 link-list
+		 * configurations. If there is only one sg, it doesn't
+		 * need to fill the link-list configuration.
+		 */
+		if (sglen < 2)
+			break;
+
+		ret = sprd_dma_fill_linklist_desc(chan, sglen, i, src, dst, len,
+						  dir, flags, slave_cfg);
+		if (ret) {
+			kfree(sdesc);
+			return NULL;
+		}
 	}
 
-	ret = sprd_dma_fill_desc(chan, sdesc, src, dst, len, dir, flags,
-				 slave_cfg);
+	ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, src, dst, len,
+				 dir, flags, slave_cfg);
 	if (ret) {
 		kfree(sdesc);
 		return NULL;
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index bfb79bd0c6de..07c20aa2e955 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -833,7 +833,7 @@ static int st_fdma_probe(struct platform_device *pdev)
 	fdev->dma_device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	fdev->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
-	ret = dma_async_device_register(&fdev->dma_device);
+	ret = dmaenginem_async_device_register(&fdev->dma_device);
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Failed to register DMA device (%d)\n", ret);
@@ -844,15 +844,13 @@ static int st_fdma_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Failed to register controller (%d)\n", ret);
-		goto err_dma_dev;
+		goto err_rproc;
 	}
 
 	dev_info(&pdev->dev, "ST FDMA engine driver, irq:%d\n", fdev->irq);
 
 	return 0;
 
-err_dma_dev:
-	dma_async_device_unregister(&fdev->dma_device);
 err_rproc:
 	st_fdma_free(fdev);
 	st_slim_rproc_put(fdev->slim_rproc);
@@ -867,7 +865,6 @@ static int st_fdma_remove(struct platform_device *pdev)
 	devm_free_irq(&pdev->dev, fdev->irq, fdev);
 	st_slim_rproc_put(fdev->slim_rproc);
 	of_dma_controller_free(pdev->dev.of_node);
-	dma_async_device_unregister(&fdev->dma_device);
 
 	return 0;
 }
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index f4edfc56f34e..5e328bd10c27 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -2839,7 +2839,7 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 
 	d40_ops_init(base, &base->dma_slave);
 
-	err = dma_async_device_register(&base->dma_slave);
+	err = dmaenginem_async_device_register(&base->dma_slave);
 
 	if (err) {
 		d40_err(base->dev, "Failed to register slave channels\n");
@@ -2854,12 +2854,12 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 
 	d40_ops_init(base, &base->dma_memcpy);
 
-	err = dma_async_device_register(&base->dma_memcpy);
+	err = dmaenginem_async_device_register(&base->dma_memcpy);
 
 	if (err) {
 		d40_err(base->dev,
 			"Failed to register memcpy only channels\n");
-		goto unregister_slave;
+		goto exit;
 	}
 
 	d40_chan_init(base, &base->dma_both, base->phy_chans,
@@ -2871,18 +2871,14 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 	dma_cap_set(DMA_CYCLIC, base->dma_slave.cap_mask);
 
 	d40_ops_init(base, &base->dma_both);
-	err = dma_async_device_register(&base->dma_both);
+	err = dmaenginem_async_device_register(&base->dma_both);
 
 	if (err) {
 		d40_err(base->dev,
 			"Failed to register logical and physical capable channels\n");
-		goto unregister_memcpy;
+		goto exit;
 	}
 	return 0;
- unregister_memcpy:
-	dma_async_device_unregister(&base->dma_memcpy);
- unregister_slave:
-	dma_async_device_unregister(&base->dma_slave);
  exit:
 	return err;
 }
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 379e8d534e61..4903a408fc14 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -308,20 +308,12 @@ static bool stm32_dma_fifo_threshold_is_allowed(u32 burst, u32 threshold,
 
 static bool stm32_dma_is_burst_possible(u32 buf_len, u32 threshold)
 {
-	switch (threshold) {
-	case STM32_DMA_FIFO_THRESHOLD_FULL:
-		if (buf_len >= STM32_DMA_MAX_BURST)
-			return true;
-		else
-			return false;
-	case STM32_DMA_FIFO_THRESHOLD_HALFFULL:
-		if (buf_len >= STM32_DMA_MAX_BURST / 2)
-			return true;
-		else
-			return false;
-	default:
-		return false;
-	}
+	/*
+	 * Buffer or period length has to be aligned on FIFO depth.
+	 * Otherwise bytes may be stuck within FIFO at buffer or period
+	 * length.
+	 */
+	return ((buf_len % ((threshold + 1) * 4)) == 0);
 }
 
 static u32 stm32_dma_get_best_burst(u32 buf_len, u32 max_burst, u32 threshold,
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 06dd1725375e..390e4cae0e1a 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1656,7 +1656,7 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = dma_async_device_register(dd);
+	ret = dmaenginem_async_device_register(dd);
 	if (ret)
 		return ret;
 
@@ -1674,8 +1674,6 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	return 0;
 
 err_unregister:
-	dma_async_device_unregister(dd);
-
 	return ret;
 }
 
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 395c698edb4d..fc0f9c8766a8 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -545,7 +545,7 @@ static struct dma_async_tx_descriptor *td_prep_slave_sg(struct dma_chan *chan,
 	}
 
 	dma_sync_single_for_device(chan2dmadev(chan), td_desc->txd.phys,
-		td_desc->desc_list_len, DMA_MEM_TO_DEV);
+		td_desc->desc_list_len, DMA_TO_DEVICE);
 
 	return &td_desc->txd;
 }