Merge branch 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This update brings:

   - the big cleanup up by Maxime for device control and slave
     capabilities.  This makes the API much cleaner.

   - new IMG MDC driver by Andrew

   - new Renesas R-Car Gen2 DMA Controller driver by Laurent along with
     bunch of fixes on rcar drivers

   - odd fixes and updates spread over driver"

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (130 commits)
  dmaengine: pl330: add DMA_PAUSE feature
  dmaengine: pl330: improve pl330_tx_status() function
  dmaengine: rcar-dmac: Disable channel 0 when using IOMMU
  dmaengine: rcar-dmac: Work around descriptor mode IOMMU errata
  dmaengine: rcar-dmac: Allocate hardware descriptors with DMAC device
  dmaengine: rcar-dmac: Fix oops due to unintialized list in error ISR
  dmaengine: rcar-dmac: Fix spinlock issues in interrupt
  dmaenegine: edma: fix sparse warnings
  dmaengine: rcar-dmac: Fix uninitialized variable usage
  dmaengine: shdmac: extend PM methods
  dmaengine: shdmac: use SET_RUNTIME_PM_OPS()
  dmaengine: pl330: fix bug that cause start the same descs in cyclic
  dmaengine: at_xdmac: allow muliple dwidths when doing slave transfers
  dmaengine: at_xdmac: simplify channel configuration stuff
  dmaengine: at_xdmac: introduce save_cc field
  dmaengine: at_xdmac: wait for in-progress transaction to complete after pausing a channel
  ioat: fail self-test if wait_for_completion times out
  dmaengine: dw: define DW_DMA_MAX_NR_MASTERS
  dmaengine: dw: amend description of dma_dev field
  dmatest: move src_off, dst_off, len inside loop
  ...

56 files changed, 4543 insertions, 1787 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index faf30a4e642b..a874b6ec6650 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -416,6 +416,15 @@ config NBPFAXI_DMA
 	help
 	  Support for "Type-AXI" NBPF DMA IPs from Renesas
 
+config IMG_MDC_DMA
+	tristate "IMG MDC support"
+	depends on MIPS || COMPILE_TEST
+	depends on MFD_SYSCON
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the IMG multi-threaded DMA controller (MDC).
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 2022b5451377..f915f61ec574 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -19,7 +19,7 @@ obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
-obj-$(CONFIG_SH_DMAE_BASE) += sh/
+obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
@@ -50,3 +50,4 @@ obj-y += xilinx/
 obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
 obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
 obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o
+obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 1364d00881dd..4a5fd245014e 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1386,32 +1386,6 @@ static u32 pl08x_get_cctl(struct pl08x_dma_chan *plchan,
 	return pl08x_cctl(cctl);
 }
 
-static int dma_set_runtime_config(struct dma_chan *chan,
-				  struct dma_slave_config *config)
-{
-	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
-	struct pl08x_driver_data *pl08x = plchan->host;
-
-	if (!plchan->slave)
-		return -EINVAL;
-
-	/* 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;
-
-	if (config->device_fc && pl08x->vd->pl080s) {
-		dev_err(&pl08x->adev->dev,
-			"%s: PL080S does not support peripheral flow control\n",
-			__func__);
-		return -EINVAL;
-	}
-
-	plchan->cfg = *config;
-
-	return 0;
-}
-
 /*
  * Slave transactions callback to the slave device to allow
  * synchronization of slave DMA signals with the DMAC enable
@@ -1693,20 +1667,71 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic(
 	return vchan_tx_prep(&plchan->vc, &txd->vd, flags);
 }
 
-static int pl08x_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
-			 unsigned long arg)
+static int pl08x_config(struct dma_chan *chan,
+			struct dma_slave_config *config)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	struct pl08x_driver_data *pl08x = plchan->host;
+
+	if (!plchan->slave)
+		return -EINVAL;
+
+	/* 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;
+
+	if (config->device_fc && pl08x->vd->pl080s) {
+		dev_err(&pl08x->adev->dev,
+			"%s: PL080S does not support peripheral flow control\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	plchan->cfg = *config;
+
+	return 0;
+}
+
+static int pl08x_terminate_all(struct dma_chan *chan)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
 	unsigned long flags;
-	int ret = 0;
 
-	/* Controls applicable to inactive channels */
-	if (cmd == DMA_SLAVE_CONFIG) {
-		return dma_set_runtime_config(chan,
-					      (struct dma_slave_config *)arg);
+	spin_lock_irqsave(&plchan->vc.lock, flags);
+	if (!plchan->phychan && !plchan->at) {
+		spin_unlock_irqrestore(&plchan->vc.lock, flags);
+		return 0;
 	}
 
+	plchan->state = PL08X_CHAN_IDLE;
+
+	if (plchan->phychan) {
+		/*
+		 * Mark physical channel as free and free any slave
+		 * signal
+		 */
+		pl08x_phy_free(plchan);
+	}
+	/* Dequeue jobs and free LLIs */
+	if (plchan->at) {
+		pl08x_desc_free(&plchan->at->vd);
+		plchan->at = NULL;
+	}
+	/* Dequeue jobs not yet fired as well */
+	pl08x_free_txd_list(pl08x, plchan);
+
+	spin_unlock_irqrestore(&plchan->vc.lock, flags);
+
+	return 0;
+}
+
+static int pl08x_pause(struct dma_chan *chan)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	unsigned long flags;
+
 	/*
 	 * Anything succeeds on channels with no physical allocation and
 	 * no queued transfers.
@@ -1717,42 +1742,35 @@ static int pl08x_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		return 0;
 	}
 
-	switch (cmd) {
-	case DMA_TERMINATE_ALL:
-		plchan->state = PL08X_CHAN_IDLE;
+	pl08x_pause_phy_chan(plchan->phychan);
+	plchan->state = PL08X_CHAN_PAUSED;
 
-		if (plchan->phychan) {
-			/*
-			 * Mark physical channel as free and free any slave
-			 * signal
-			 */
-			pl08x_phy_free(plchan);
-		}
-		/* Dequeue jobs and free LLIs */
-		if (plchan->at) {
-			pl08x_desc_free(&plchan->at->vd);
-			plchan->at = NULL;
-		}
-		/* Dequeue jobs not yet fired as well */
-		pl08x_free_txd_list(pl08x, plchan);
-		break;
-	case DMA_PAUSE:
-		pl08x_pause_phy_chan(plchan->phychan);
-		plchan->state = PL08X_CHAN_PAUSED;
-		break;
-	case DMA_RESUME:
-		pl08x_resume_phy_chan(plchan->phychan);
-		plchan->state = PL08X_CHAN_RUNNING;
-		break;
-	default:
-		/* Unknown command */
-		ret = -ENXIO;
-		break;
+	spin_unlock_irqrestore(&plchan->vc.lock, flags);
+
+	return 0;
+}
+
+static int pl08x_resume(struct dma_chan *chan)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	unsigned long flags;
+
+	/*
+	 * Anything succeeds on channels with no physical allocation and
+	 * no queued transfers.
+	 */
+	spin_lock_irqsave(&plchan->vc.lock, flags);
+	if (!plchan->phychan && !plchan->at) {
+		spin_unlock_irqrestore(&plchan->vc.lock, flags);
+		return 0;
 	}
 
+	pl08x_resume_phy_chan(plchan->phychan);
+	plchan->state = PL08X_CHAN_RUNNING;
+
 	spin_unlock_irqrestore(&plchan->vc.lock, flags);
 
-	return ret;
+	return 0;
 }
 
 bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
@@ -2048,7 +2066,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->memcpy.device_prep_dma_interrupt = pl08x_prep_dma_interrupt;
 	pl08x->memcpy.device_tx_status = pl08x_dma_tx_status;
 	pl08x->memcpy.device_issue_pending = pl08x_issue_pending;
-	pl08x->memcpy.device_control = pl08x_control;
+	pl08x->memcpy.device_config = pl08x_config;
+	pl08x->memcpy.device_pause = pl08x_pause;
+	pl08x->memcpy.device_resume = pl08x_resume;
+	pl08x->memcpy.device_terminate_all = pl08x_terminate_all;
 
 	/* Initialize slave engine */
 	dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask);
@@ -2061,7 +2082,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->slave.device_issue_pending = pl08x_issue_pending;
 	pl08x->slave.device_prep_slave_sg = pl08x_prep_slave_sg;
 	pl08x->slave.device_prep_dma_cyclic = pl08x_prep_dma_cyclic;
-	pl08x->slave.device_control = pl08x_control;
+	pl08x->slave.device_config = pl08x_config;
+	pl08x->slave.device_pause = pl08x_pause;
+	pl08x->slave.device_resume = pl08x_resume;
+	pl08x->slave.device_terminate_all = pl08x_terminate_all;
 
 	/* Get the platform data */
 	pl08x->pd = dev_get_platdata(&adev->dev);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index ca9dd2613283..1e1a4c567542 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -42,6 +42,11 @@
 #define	ATC_DEFAULT_CFG		(ATC_FIFOCFG_HALFFIFO)
 #define	ATC_DEFAULT_CTRLB	(ATC_SIF(AT_DMA_MEM_IF) \
 				|ATC_DIF(AT_DMA_MEM_IF))
+#define ATC_DMA_BUSWIDTHS\
+	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |\
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
 /*
  * Initial number of descriptors to allocate for each channel. This could
@@ -972,11 +977,13 @@ err_out:
 	return NULL;
 }
 
-static int set_runtime_config(struct dma_chan *chan,
-			      struct dma_slave_config *sconfig)
+static int atc_config(struct dma_chan *chan,
+		      struct dma_slave_config *sconfig)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
+
 	/* Check if it is chan is configured for slave transfers */
 	if (!chan->private)
 		return -EINVAL;
@@ -989,9 +996,28 @@ static int set_runtime_config(struct dma_chan *chan,
 	return 0;
 }
 
+static int atc_pause(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	int			chan_id = atchan->chan_common.chan_id;
+	unsigned long		flags;
 
-static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
-		       unsigned long arg)
+	LIST_HEAD(list);
+
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
+
+	spin_lock_irqsave(&atchan->lock, flags);
+
+	dma_writel(atdma, CHER, AT_DMA_SUSP(chan_id));
+	set_bit(ATC_IS_PAUSED, &atchan->status);
+
+	spin_unlock_irqrestore(&atchan->lock, flags);
+
+	return 0;
+}
+
+static int atc_resume(struct dma_chan *chan)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma		*atdma = to_at_dma(chan->device);
@@ -1000,60 +1026,61 @@ static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 
 	LIST_HEAD(list);
 
-	dev_vdbg(chan2dev(chan), "atc_control (%d)\n", cmd);
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
-	if (cmd == DMA_PAUSE) {
-		spin_lock_irqsave(&atchan->lock, flags);
+	if (!atc_chan_is_paused(atchan))
+		return 0;
 
-		dma_writel(atdma, CHER, AT_DMA_SUSP(chan_id));
-		set_bit(ATC_IS_PAUSED, &atchan->status);
+	spin_lock_irqsave(&atchan->lock, flags);
 
-		spin_unlock_irqrestore(&atchan->lock, flags);
-	} else if (cmd == DMA_RESUME) {
-		if (!atc_chan_is_paused(atchan))
-			return 0;
+	dma_writel(atdma, CHDR, AT_DMA_RES(chan_id));
+	clear_bit(ATC_IS_PAUSED, &atchan->status);
 
-		spin_lock_irqsave(&atchan->lock, flags);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
-		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id));
-		clear_bit(ATC_IS_PAUSED, &atchan->status);
+	return 0;
+}
 
-		spin_unlock_irqrestore(&atchan->lock, flags);
-	} else if (cmd == DMA_TERMINATE_ALL) {
-		struct at_desc	*desc, *_desc;
-		/*
-		 * This is only called when something went wrong elsewhere, so
-		 * we don't really care about the data. Just disable the
-		 * channel. We still have to poll the channel enable bit due
-		 * to AHB/HSB limitations.
-		 */
-		spin_lock_irqsave(&atchan->lock, flags);
+static int atc_terminate_all(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	int			chan_id = atchan->chan_common.chan_id;
+	struct at_desc		*desc, *_desc;
+	unsigned long		flags;
 
-		/* disabling channel: must also remove suspend state */
-		dma_writel(atdma, CHDR, AT_DMA_RES(chan_id) | atchan->mask);
+	LIST_HEAD(list);
 
-		/* confirm that this channel is disabled */
-		while (dma_readl(atdma, CHSR) & atchan->mask)
-			cpu_relax();
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
-		/* active_list entries will end up before queued entries */
-		list_splice_init(&atchan->queue, &list);
-		list_splice_init(&atchan->active_list, &list);
+	/*
+	 * This is only called when something went wrong elsewhere, so
+	 * we don't really care about the data. Just disable the
+	 * channel. We still have to poll the channel enable bit due
+	 * to AHB/HSB limitations.
+	 */
+	spin_lock_irqsave(&atchan->lock, flags);
 
-		/* Flush all pending and queued descriptors */
-		list_for_each_entry_safe(desc, _desc, &list, desc_node)
-			atc_chain_complete(atchan, desc);
+	/* disabling channel: must also remove suspend state */
+	dma_writel(atdma, CHDR, AT_DMA_RES(chan_id) | atchan->mask);
 
-		clear_bit(ATC_IS_PAUSED, &atchan->status);
-		/* if channel dedicated to cyclic operations, free it */
-		clear_bit(ATC_IS_CYCLIC, &atchan->status);
+	/* confirm that this channel is disabled */
+	while (dma_readl(atdma, CHSR) & atchan->mask)
+		cpu_relax();
 
-		spin_unlock_irqrestore(&atchan->lock, flags);
-	} else if (cmd == DMA_SLAVE_CONFIG) {
-		return set_runtime_config(chan, (struct dma_slave_config *)arg);
-	} else {
-		return -ENXIO;
-	}
+	/* active_list entries will end up before queued entries */
+	list_splice_init(&atchan->queue, &list);
+	list_splice_init(&atchan->active_list, &list);
+
+	/* Flush all pending and queued descriptors */
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		atc_chain_complete(atchan, desc);
+
+	clear_bit(ATC_IS_PAUSED, &atchan->status);
+	/* if channel dedicated to cyclic operations, free it */
+	clear_bit(ATC_IS_CYCLIC, &atchan->status);
+
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return 0;
 }
@@ -1505,7 +1532,14 @@ static int __init at_dma_probe(struct platform_device *pdev)
 		/* controller can do slave DMA: can trigger cyclic transfers */
 		dma_cap_set(DMA_CYCLIC, atdma->dma_common.cap_mask);
 		atdma->dma_common.device_prep_dma_cyclic = atc_prep_dma_cyclic;
-		atdma->dma_common.device_control = atc_control;
+		atdma->dma_common.device_config = atc_config;
+		atdma->dma_common.device_pause = atc_pause;
+		atdma->dma_common.device_resume = atc_resume;
+		atdma->dma_common.device_terminate_all = atc_terminate_all;
+		atdma->dma_common.src_addr_widths = ATC_DMA_BUSWIDTHS;
+		atdma->dma_common.dst_addr_widths = ATC_DMA_BUSWIDTHS;
+		atdma->dma_common.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+		atdma->dma_common.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	}
 
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
@@ -1622,7 +1656,7 @@ static void atc_suspend_cyclic(struct at_dma_chan *atchan)
 	if (!atc_chan_is_paused(atchan)) {
 		dev_warn(chan2dev(chan),
 		"cyclic channel not paused, should be done by channel user\n");
-		atc_control(chan, DMA_PAUSE, 0);
+		atc_pause(chan);
 	}
 
 	/* now preserve additional data for cyclic operations */
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 2787aba60c6b..d6bba6c636c2 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -232,7 +232,8 @@ enum atc_status {
  * @save_dscr: for cyclic operations, preserve next descriptor address in
  *             the cyclic list on suspend/resume cycle
  * @remain_desc: to save remain desc length
- * @dma_sconfig: configuration for slave transfers, passed via DMA_SLAVE_CONFIG
+ * @dma_sconfig: configuration for slave transfers, passed via
+ * .device_config
  * @lock: serializes enqueue/dequeue operations to descriptors lists
  * @active_list: list of descriptors dmaengine is being running on
  * @queue: list of descriptors ready to be submitted to engine
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b60d77a22df6..09e2825a547a 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -25,6 +25,7 @@
 #include <linux/dmapool.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of_dma.h>
@@ -174,6 +175,13 @@
 
 #define AT_XDMAC_MAX_CHAN	0x20
 
+#define AT_XDMAC_DMA_BUSWIDTHS\
+	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
+	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 atc_status {
 	AT_XDMAC_CHAN_IS_CYCLIC = 0,
 	AT_XDMAC_CHAN_IS_PAUSED,
@@ -184,15 +192,15 @@ struct at_xdmac_chan {
 	struct dma_chan			chan;
 	void __iomem			*ch_regs;
 	u32				mask;		/* Channel Mask */
-	u32				cfg[3];		/* Channel Configuration Register */
-	#define	AT_XDMAC_CUR_CFG	0		/* Current channel conf */
-	#define	AT_XDMAC_DEV_TO_MEM_CFG	1		/* Predifined dev to mem channel conf */
-	#define	AT_XDMAC_MEM_TO_DEV_CFG	2		/* Predifined mem to dev channel conf */
+	u32				cfg[2];		/* Channel Configuration Register */
+	#define	AT_XDMAC_DEV_TO_MEM_CFG	0		/* Predifined dev to mem channel conf */
+	#define	AT_XDMAC_MEM_TO_DEV_CFG	1		/* Predifined mem to dev channel conf */
 	u8				perid;		/* Peripheral ID */
 	u8				perif;		/* Peripheral Interface */
 	u8				memif;		/* Memory Interface */
 	u32				per_src_addr;
 	u32				per_dst_addr;
+	u32				save_cc;
 	u32				save_cim;
 	u32				save_cnda;
 	u32				save_cndc;
@@ -344,20 +352,13 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 	at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, reg);
 
 	/*
-	 * When doing memory to memory transfer we need to use the next
+	 * When doing non cyclic transfer we need to use the next
 	 * descriptor view 2 since some fields of the configuration register
 	 * depend on transfer size and src/dest addresses.
 	 */
-	if (is_slave_direction(first->direction)) {
+	if (at_xdmac_chan_is_cyclic(atchan)) {
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
-		if (first->direction == DMA_MEM_TO_DEV)
-			atchan->cfg[AT_XDMAC_CUR_CFG] =
-				atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
-		else
-			atchan->cfg[AT_XDMAC_CUR_CFG] =
-				atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
-		at_xdmac_chan_write(atchan, AT_XDMAC_CC,
-				    atchan->cfg[AT_XDMAC_CUR_CFG]);
+		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
 	} else {
 		/*
 		 * No need to write AT_XDMAC_CC reg, it will be done when the
@@ -561,7 +562,6 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct at_xdmac_desc	*first = NULL, *prev = NULL;
 	struct scatterlist	*sg;
 	int			i;
-	u32			cfg;
 	unsigned int		xfer_size = 0;
 
 	if (!sgl)
@@ -583,7 +583,7 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	/* Prepare descriptors. */
 	for_each_sg(sgl, sg, sg_len, i) {
 		struct at_xdmac_desc	*desc = NULL;
-		u32			len, mem;
+		u32			len, mem, dwidth, fixed_dwidth;
 
 		len = sg_dma_len(sg);
 		mem = sg_dma_address(sg);
@@ -608,17 +608,21 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		if (direction == DMA_DEV_TO_MEM) {
 			desc->lld.mbr_sa = atchan->per_src_addr;
 			desc->lld.mbr_da = mem;
-			cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
+			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
 		} else {
 			desc->lld.mbr_sa = mem;
 			desc->lld.mbr_da = atchan->per_dst_addr;
-			cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
 		}
-		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1		/* next descriptor view */
-			| AT_XDMAC_MBR_UBC_NDEN				/* next descriptor dst parameter update */
-			| AT_XDMAC_MBR_UBC_NSEN				/* next descriptor src parameter update */
-			| (i == sg_len - 1 ? 0 : AT_XDMAC_MBR_UBC_NDE)	/* descriptor fetch */
-			| len / (1 << at_xdmac_get_dwidth(cfg));	/* microblock length */
+		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
+		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
+			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
+			       : AT_XDMAC_CC_DWIDTH_BYTE;
+		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2			/* next descriptor view */
+			| AT_XDMAC_MBR_UBC_NDEN					/* next descriptor dst parameter update */
+			| AT_XDMAC_MBR_UBC_NSEN					/* next descriptor src parameter update */
+			| (i == sg_len - 1 ? 0 : AT_XDMAC_MBR_UBC_NDE)		/* descriptor fetch */
+			| (len >> fixed_dwidth);				/* microblock length */
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
 			 __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc);
@@ -882,7 +886,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	enum dma_status		ret;
 	int			residue;
 	u32			cur_nda, mask, value;
-	u8			dwidth = at_xdmac_get_dwidth(atchan->cfg[AT_XDMAC_CUR_CFG]);
+	u8			dwidth = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -912,7 +916,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	 */
 	mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
 	value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
-	if ((atchan->cfg[AT_XDMAC_CUR_CFG] & mask) == value) {
+	if ((desc->lld.mbr_cfg & mask) == value) {
 		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
 		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
 			cpu_relax();
@@ -926,6 +930,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	 */
 	descs_list = &desc->descs_list;
 	list_for_each_entry_safe(desc, _desc, descs_list, desc_node) {
+		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
 		residue -= (desc->lld.mbr_ubc & 0xffffff) << dwidth;
 		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
 			break;