Merge tag 'dmaengine-5.1-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - dmatest updates for modularizing common struct and code

 - remove SG support for VDMA xilinx IP and updates to driver

 - Update to dw driver to support Intel iDMA controllers multi-block
   support

 - tegra updates for proper reporting of residue

 - Add Snow Ridge ioatdma device id and support for IOATDMA v3.4

 - struct_size() usage and useless LIST_HEAD cleanups in subsystem.

 - qDMA controller driver for Layerscape SoCs

 - stm32-dma PM Runtime support

 - And usual updates to imx-sdma, sprd, Documentation, fsl-edma,
   bcm2835, qcom_hidma etc

* tag 'dmaengine-5.1-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (81 commits)
  dmaengine: imx-sdma: fix consistent dma test failures
  dmaengine: imx-sdma: add a test for imx8mq multi sdma devices
  dmaengine: imx-sdma: add clock ratio 1:1 check
  dmaengine: dmatest: move test data alloc & free into functions
  dmaengine: dmatest: add short-hand `buf_size` var in dmatest_func()
  dmaengine: dmatest: wrap src & dst data into a struct
  dmaengine: ioatdma: support latency tolerance report (LTR) for v3.4
  dmaengine: ioatdma: add descriptor pre-fetch support for v3.4
  dmaengine: ioatdma: disable DCA enabling on IOATDMA v3.4
  dmaengine: ioatdma: Add Snow Ridge ioatdma device id
  dmaengine: sprd: Change channel id to slave id for DMA cell specifier
  dt-bindings: dmaengine: sprd: Change channel id to slave id for DMA cell specifier
  dmaengine: mv_xor: Use correct device for DMA API
  Documentation :dmaengine: clarify DMA desc. pointer after submission
  Documentation: dmaengine: fix dmatest.rst warning
  dmaengine: k3dma: Add support for dma-channel-mask
  dmaengine: k3dma: Delete axi_config
  dmaengine: k3dma: Upgrade k3dma driver to support hisi_asp_dma hardware
  Documentation: bindings: dma: Add binding for dma-channel-mask
  Documentation: bindings: k3dma: Extend the k3dma driver binding to support hisi-asp
  ...

48 files changed, 2453 insertions, 630 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index d2286c7f7222..0b1dfb5bf2d9 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -218,6 +218,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config FSL_QDMA
+       tristate "NXP Layerscape qDMA engine support"
+       depends on ARM || ARM64
+       select DMA_ENGINE
+       select DMA_VIRTUAL_CHANNELS
+       select DMA_ENGINE_RAID
+       select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+       help
+         Support the NXP Layerscape qDMA engine with command queue and legacy mode.
+         Channel virtualization is supported through enqueuing of DMA jobs to,
+         or dequeuing DMA jobs from, different work queues.
+         This module can be found on NXP Layerscape SoCs.
+	  The qdma driver only work on  SoCs with a DPAA hardware block.
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 09571a81353d..6126e1c3a875 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
 obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
 obj-$(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 01d936c9fe89..a0a9cd76c1d4 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -134,7 +134,6 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 	struct at_desc *ret = NULL;
 	unsigned long flags;
 	unsigned int i = 0;
-	LIST_HEAD(tmp_list);
 
 	spin_lock_irqsave(&atchan->lock, flags);
 	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
@@ -1387,8 +1386,6 @@ static int atc_pause(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	spin_lock_irqsave(&atchan->lock, flags);
@@ -1408,8 +1405,6 @@ static int atc_resume(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	if (!atc_chan_is_paused(atchan))
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index ae10f5614f95..ec8a291d62ba 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -2,9 +2,6 @@
 /*
  * BCM2835 DMA engine support
  *
- * This driver only supports cyclic DMA transfers
- * as needed for the I2S module.
- *
  * Author:      Florian Meier <florian.meier@koalo.de>
  *              Copyright 2013
  *
@@ -42,7 +39,6 @@
 
 struct bcm2835_dmadev {
 	struct dma_device ddev;
-	spinlock_t lock;
 	void __iomem *base;
 	struct device_dma_parameters dma_parms;
 };
@@ -64,7 +60,6 @@ struct bcm2835_cb_entry {
 
 struct bcm2835_chan {
 	struct virt_dma_chan vc;
-	struct list_head node;
 
 	struct dma_slave_config	cfg;
 	unsigned int dreq;
@@ -312,8 +307,7 @@ static struct bcm2835_desc *bcm2835_dma_create_cb_chain(
 		return NULL;
 
 	/* allocate and setup the descriptor. */
-	d = kzalloc(sizeof(*d) + frames * sizeof(struct bcm2835_cb_entry),
-		    gfp);
+	d = kzalloc(struct_size(d, cb_list, frames), gfp);
 	if (!d)
 		return NULL;
 
@@ -406,7 +400,7 @@ static void bcm2835_dma_fill_cb_chain_with_sg(
 	}
 }
 
-static int bcm2835_dma_abort(struct bcm2835_chan *c)
+static void bcm2835_dma_abort(struct bcm2835_chan *c)
 {
 	void __iomem *chan_base = c->chan_base;
 	long int timeout = 10000;
@@ -416,7 +410,7 @@ static int bcm2835_dma_abort(struct bcm2835_chan *c)
 	 * (The ACTIVE flag in the CS register is not a reliable indicator.)
 	 */
 	if (!readl(chan_base + BCM2835_DMA_ADDR))
-		return 0;
+		return;
 
 	/* Write 0 to the active bit - Pause the DMA */
 	writel(0, chan_base + BCM2835_DMA_CS);
@@ -432,7 +426,6 @@ static int bcm2835_dma_abort(struct bcm2835_chan *c)
 			"failed to complete outstanding writes\n");
 
 	writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS);
-	return 0;
 }
 
 static void bcm2835_dma_start_desc(struct bcm2835_chan *c)
@@ -504,8 +497,12 @@ static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	dev_dbg(dev, "Allocating DMA channel %d\n", c->ch);
 
+	/*
+	 * Control blocks are 256 bit in length and must start at a 256 bit
+	 * (32 byte) aligned address (BCM2835 ARM Peripherals, sec. 4.2.1.1).
+	 */
 	c->cb_pool = dma_pool_create(dev_name(dev), dev,
-				     sizeof(struct bcm2835_dma_cb), 0, 0);
+				     sizeof(struct bcm2835_dma_cb), 32, 0);
 	if (!c->cb_pool) {
 		dev_err(dev, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
@@ -774,17 +771,11 @@ static int bcm2835_dma_slave_config(struct dma_chan *chan,
 static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
-	struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device);
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 
-	/* Prevent this channel being scheduled */
-	spin_lock(&d->lock);
-	list_del_init(&c->node);
-	spin_unlock(&d->lock);
-
 	/* stop DMA activity */
 	if (c->desc) {
 		vchan_terminate_vdesc(&c->desc->vd);
@@ -817,7 +808,6 @@ static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id,
 
 	c->vc.desc_free = bcm2835_dma_desc_free;
 	vchan_init(&c->vc, &d->ddev);
-	INIT_LIST_HEAD(&c->node);
 
 	c->chan_base = BCM2835_DMA_CHANIO(d->base, chan_id);
 	c->ch = chan_id;
@@ -920,7 +910,6 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
-	spin_lock_init(&od->lock);
 
 	platform_set_drvdata(pdev, od);
 
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 15b2453d2647..ffc0adc2f6ce 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -367,8 +367,7 @@ static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
 	struct axi_dmac_desc *desc;
 	unsigned int i;
 
-	desc = kzalloc(sizeof(struct axi_dmac_desc) +
-		sizeof(struct axi_dmac_sg) * num_sgs, GFP_NOWAIT);
+	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index a8b6225faa12..9ce0a386225b 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -838,9 +838,8 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	if (!soc_data)
 		return -EINVAL;
 
-	jzdma = devm_kzalloc(dev, sizeof(*jzdma)
-				+ sizeof(*jzdma->chan) * soc_data->nb_channels,
-				GFP_KERNEL);
+	jzdma = devm_kzalloc(dev, struct_size(jzdma, chan,
+			     soc_data->nb_channels), GFP_KERNEL);
 	if (!jzdma)
 		return -ENOMEM;
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 6511928b4cdf..b96814a7dceb 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -200,15 +200,20 @@ struct dmatest_done {
 	wait_queue_head_t	*wait;
 };
 
+struct dmatest_data {
+	u8		**raw;
+	u8		**aligned;
+	unsigned int	cnt;
+	unsigned int	off;
+};
+
 struct dmatest_thread {
 	struct list_head	node;
 	struct dmatest_info	*info;
 	struct task_struct	*task;
 	struct dma_chan		*chan;
-	u8			**srcs;
-	u8			**usrcs;
-	u8			**dsts;
-	u8			**udsts;
+	struct dmatest_data	src;
+	struct dmatest_data	dst;
 	enum dma_transaction_type type;
 	wait_queue_head_t done_wait;
 	struct dmatest_done test_done;
@@ -481,6 +486,53 @@ static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
 	return FIXPT_TO_INT(dmatest_persec(runtime, len >> 10));
 }
 
+static void __dmatest_free_test_data(struct dmatest_data *d, unsigned int cnt)
+{
+	unsigned int i;
+
+	for (i = 0; i < cnt; i++)
+		kfree(d->raw[i]);
+
+	kfree(d->aligned);
+	kfree(d->raw);
+}
+
+static void dmatest_free_test_data(struct dmatest_data *d)
+{
+	__dmatest_free_test_data(d, d->cnt);
+}
+
+static int dmatest_alloc_test_data(struct dmatest_data *d,
+		unsigned int buf_size, u8 align)
+{
+	unsigned int i = 0;
+
+	d->raw = kcalloc(d->cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!d->raw)
+		return -ENOMEM;
+
+	d->aligned = kcalloc(d->cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!d->aligned)
+		goto err;
+
+	for (i = 0; i < d->cnt; i++) {
+		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		if (!d->raw[i])
+			goto err;
+
+		/* align to alignment restriction */
+		if (align)
+			d->aligned[i] = PTR_ALIGN(d->raw[i], align);
+		else
+			d->aligned[i] = d->raw[i];
+	}
+
+	return 0;
+err:
+	__dmatest_free_test_data(d, i);
+	return -ENOMEM;
+}
+
 /*
  * This function repeatedly tests DMA transfers of various lengths and
  * offsets for a given operation type until it is told to exit by
@@ -511,8 +563,9 @@ static int dmatest_func(void *data)
 	enum dma_ctrl_flags 	flags;
 	u8			*pq_coefs = NULL;
 	int			ret;
-	int			src_cnt;
-	int			dst_cnt;
+	unsigned int 		buf_size;
+	struct dmatest_data	*src;
+	struct dmatest_data	*dst;
 	int			i;
 	ktime_t			ktime, start, diff;
 	ktime_t			filltime = 0;
@@ -535,25 +588,27 @@ static int dmatest_func(void *data)
 	params = &info->params;
 	chan = thread->chan;
 	dev = chan->device;
+	src = &thread->src;
+	dst = &thread->dst;
 	if (thread->type == DMA_MEMCPY) {
 		align = params->alignment < 0 ? dev->copy_align :
 						params->alignment;
-		src_cnt = dst_cnt = 1;
+		src->cnt = dst->cnt = 1;
 	} else if (thread->type == DMA_MEMSET) {
 		align = params->alignment < 0 ? dev->fill_align :
 						params->alignment;
-		src_cnt = dst_cnt = 1;
+		src->cnt = dst->cnt = 1;
 		is_memset = true;
 	} else if (thread->type == DMA_XOR) {
 		/* force odd to ensure dst = src */
-		src_cnt = min_odd(params->xor_sources | 1, dev->max_xor);
-		dst_cnt = 1;
+		src->cnt = min_odd(params->xor_sources | 1, dev->max_xor);
+		dst->cnt = 1;
 		align = params->alignment < 0 ? dev->xor_align :
 						params->alignment;
 	} else if (thread->type == DMA_PQ) {
 		/* force odd to ensure dst = src */
-		src_cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
-		dst_cnt = 2;
+		src->cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
+		dst->cnt = 2;
 		align = params->alignment < 0 ? dev->pq_align :
 						params->alignment;
 
@@ -561,75 +616,38 @@ static int dmatest_func(void *data)
 		if (!pq_coefs)
 			goto err_thread_type;
 
-		for (i = 0; i < src_cnt; i++)
+		for (i = 0; i < src->cnt; i++)
 			pq_coefs[i] = 1;
 	} else
 		goto err_thread_type;
 
 	/* Check if buffer count fits into map count variable (u8) */
-	if ((src_cnt + dst_cnt) >= 255) {
+	if ((src->cnt + dst->cnt) >= 255) {
 		pr_err("too many buffers (%d of 255 supported)\n",
-		       src_cnt + dst_cnt);
+		       src->cnt + dst->cnt);
 		goto err_free_coefs;
 	}
 
-	if (1 << align > params->buf_size) {
+	buf_size = params->buf_size;
+	if (1 << align > buf_size) {
 		pr_err("%u-byte buffer too small for %d-byte alignment\n",
-		       params->buf_size, 1 << align);
+		       buf_size, 1 << align);
 		goto err_free_coefs;
 	}
 
-	thread->srcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->srcs)
+	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
 		goto err_free_coefs;
 
-	thread->usrcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->usrcs)
-		goto err_usrcs;
-
-	for (i = 0; i < src_cnt; i++) {
-		thread->usrcs[i] = kmalloc(params->buf_size + align,
-					   GFP_KERNEL);
-		if (!thread->usrcs[i])
-			goto err_srcbuf;
-
-		/* align srcs to alignment restriction */
-		if (align)
-			thread->srcs[i] = PTR_ALIGN(thread->usrcs[i], align);
-		else
-			thread->srcs[i] = thread->usrcs[i];
-	}
-	thread->srcs[i] = NULL;
-
-	thread->dsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->dsts)
-		goto err_dsts;
-
-	thread->udsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
-	if (!thread->udsts)
-		goto err_udsts;
-
-	for (i = 0; i < dst_cnt; i++) {
-		thread->udsts[i] = kmalloc(params->buf_size + align,
-					   GFP_KERNEL);
-		if (!thread->udsts[i])
-			goto err_dstbuf;
-
-		/* align dsts to alignment restriction */
-		if (align)
-			thread->dsts[i] = PTR_ALIGN(thread->udsts[i], align);
-		else
-			thread->dsts[i] = thread->udsts[i];
-	}
-	thread->dsts[i] = NULL;
+	if (dmatest_alloc_test_data(dst, buf_size, align) < 0)
+		goto err_src;
 
 	set_user_nice(current, 10);
 
-	srcs = kcalloc(src_cnt, sizeof(dma_addr_t), GFP_KERNEL);
+	srcs = kcalloc(src->cnt, sizeof(dma_addr_t), GFP_KERNEL);
 	if (!srcs)
-		goto err_dstbuf;
+		goto err_dst;
 
-	dma_pq = kcalloc(dst_cnt, sizeof(dma_addr_t), GFP_KERNEL);
+	dma_pq = kcalloc(dst->cnt, sizeof(dma_addr_t), GFP_KERNEL);
 	if (!dma_pq)
 		goto err_srcs_array;
 
@@ -644,21 +662,21 @@ static int dmatest_func(void *data)
 		struct dma_async_tx_descriptor *tx = NULL;
 		struct dmaengine_unmap_data *um;
 		dma_addr_t *dsts;
-		unsigned int src_off, dst_off, len;
+		unsigned int len;
 
 		total_tests++;
 
 		if (params->transfer_size) {
-			if (params->transfer_size >= params->buf_size) {
+			if (params->transfer_size >= buf_size) {
 				pr_err("%u-byte transfer size must be lower than %u-buffer size\n",
-				       params->transfer_size, params->buf_size);
+				       params->transfer_size, buf_size);
 				break;
 			}
 			len = params->transfer_size;
 		} else if (params->norandom) {
-			len = params->buf_size;
+			len = buf_size;
 		} else {
-			len = dmatest_random() % params->buf_size + 1;
+			len = dmatest_random() % buf_size + 1;
 		}
 
 		/* Do not alter transfer size explicitly defined by user */
@@ -670,57 +688,57 @@ static int dmatest_func(void *data)
 		total_len += len;
 
 		if (params->norandom) {
-			src_off = 0;
-			dst_off = 0;
+			src->off = 0;
+			dst->off = 0;
 		} else {
-			src_off = dmatest_random() % (params->buf_size - len + 1);
-			dst_off = dmatest_random() % (params->buf_size - len + 1);
+			src->off = dmatest_random() % (buf_size - len + 1);
+			dst->off = dmatest_random() % (buf_size - len + 1);
 
-			src_off = (src_off >> align) << align;
-			dst_off = (dst_off >> align) << align;
+			src->off = (src->off >> align) << align;
+			dst->off = (dst->off >> align) << align;
 		}
 
 		if (!params->noverify) {
 			start = ktime_get();
-			dmatest_init_srcs(thread->srcs, src_off, len,
-					  params->buf_size, is_memset);
-			dmatest_init_dsts(thread->dsts, dst_off, len,
-					  params->buf_size, is_memset);
+			dmatest_init_srcs(src->aligned, src->off, len,
+					  buf_size, is_memset);
+			dmatest_init_dsts(dst->aligned, dst->off, len,
+					  buf_size, is_memset);
 
 			diff = ktime_sub(ktime_get(), start);
 			filltime = ktime_add(filltime, diff);
 		}
 
-		um = dmaengine_get_unmap_data(dev->dev, src_cnt + dst_cnt,
+		um = dmaengine_get_unmap_data(dev->dev, src->cnt + dst->cnt,
 					      GFP_KERNEL);
 		if (!um) {
 			failed_tests++;
 			result("unmap data NULL", total_tests,
-			       src_off, dst_off, len, ret);
+			       src->off, dst->off, len, ret);
 			continue;
 		}
 
-		um->len = params->buf_size;
-		for (i = 0; i < src_cnt; i++) {
-			void *buf = thread->srcs[i];
+		um->len = buf_size;
+		for (i = 0; i < src->cnt; i++) {
+			void *buf = src->aligned[i];
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
 			um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
 						   um->len, DMA_TO_DEVICE);
-			srcs[i] = um->addr[i] + src_off;
+			srcs[i] = um->addr[i] + src->off;
 			ret = dma_mapping_error(dev->dev, um->addr[i]);
 			if (ret) {
 				result("src mapping error", total_tests,
-				       src_off, dst_off, len, ret);
+				       src->off, dst->off, len, ret);
 				goto error_unmap_continue;
 			}
 			um->to_cnt++;
 		}
 		/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
-		dsts = &um->addr[src_cnt];
-		for (i = 0; i < dst_cnt; i++) {
-			void *buf = thread->dsts[i];
+		dsts = &um->addr[src->cnt];
+		for (i = 0; i < dst->cnt; i++) {
+			void *buf = dst->aligned[i];
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
@@ -729,7 +747,7 @@ static int dmatest_func(void *data)
 			ret = dma_mapping_error(dev->dev, dsts[i]);
 			if (ret) {
 				result("dst mapping error", total_tests,
-				       src_off, dst_off, len, ret);
+				       src->off, dst->off, len, ret);
 				goto error_unmap_continue;
 			}
 			um->bidi_cnt++;
@@ -737,29 +755,29 @@ static int dmatest_func(void *data)
 
 		if (thread->type == DMA_MEMCPY)
 			tx = dev->device_prep_dma_memcpy(chan,
-							 dsts[0] + dst_off,
+							 dsts[0] + dst->off,
 							 srcs[0], len, flags);
 		else if (thread->type == DMA_MEMSET)
 			tx = dev->device_prep_dma_memset(chan,
-						dsts[0] + dst_off,
-						*(thread->srcs[0] + src_off),
+						dsts[0] + dst->off,
+						*(src->aligned[0] + src->off),
 						len, flags);
 		else if (thread->type == DMA_XOR)
 			tx = dev->device_prep_dma_xor(chan,
-						      dsts[0] + dst_off,
-						      srcs, src_cnt,
+						      dsts[0] + dst->off,
+						      srcs, src->cnt,
 						      len, flags);
 		else if (thread->type == DMA_PQ) {
-			for (i = 0; i < dst_cnt; i++)
-				dma_pq[i] = dsts[i] + dst_off;
+			for (i = 0; i < dst->cnt; i++)
+				dma_pq[i] = dsts[i] + dst->off;
 			tx = dev->device_prep_dma_pq(chan, dma_pq, srcs,
-						     src_cnt, pq_coefs,
+						     src->cnt, pq_coefs,
 						     len, flags);
 		}
 
 		if (!tx) {
-			result("prep error", total_tests, src_off,
-			       dst_off, len, ret);
+			result("prep error", total_tests, src->off,
+			       dst->off, len, ret);
 			msleep(100);
 			goto error_unmap_continue;
 		}
@@ -770,8 +788,8 @@ static int dmatest_func(void *data)
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
-			result("submit error", total_tests, src_off,
-			       dst_off, len, ret);
+			result("submit error", total_tests, src->off,
+			       dst->off, len, ret);
 			msleep(100);
 			goto error_unmap_continue;
 		}
@@ -783,58 +801,58 @@ static int dmatest_func(void *data)
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
 		if (!done->done) {
-			result("test timed out", total_tests, src_off, dst_off,
+			result("test timed out", total_tests, src->off, dst->off,
 			       len, 0);
 			goto error_unmap_continue;
 		} else if (status != DMA_COMPLETE) {
 			result(status == DMA_ERROR ?
 			       "completion error status" :
-			       "completion busy status", total_tests, src_off,
-			       dst_off, len, ret);
+			       "completion busy status", total_tests, src->off,
+			       dst->off, len, ret);
 			goto error_unmap_continue;
 		}
 
 		dmaengine_unmap_put(um);
 
 		if (params->noverify) {
-			verbose_result("test passed", total_tests, src_off,
-				       dst_off, len, 0);
+			verbose_result("test passed", total_tests, src->off,
+				       dst->off, len, 0);
 			continue;
 		}
 
 		start = ktime_get();
 		pr_debug("%s: verifying source buffer...\n", current->comm);
-		error_count = dmatest_verify(thread->srcs, 0, src_off,
+		error_count = dmatest_verify(src->aligned, 0, src->off,
 				0, PATTERN_SRC, true, is_memset);
-		error_count += dmatest_verify(thread->srcs, src_off,
-				src_off + len, src_off,
+		error_count += dmatest_verify(src->aligned, src->off,
+				src->off + len, src->off,
 				PATTERN_SRC | PATTERN_COPY, true, is_memset);
-		error_count += dmatest_verify(thread->srcs, src_off + len,
-				params->buf_size, src_off + len,
+		error_count += dmatest_verify(src->aligned, src->off + len,
+				buf_size, src->off + len,
 				PATTERN_SRC, true, is_memset);
 
 		pr_debug("%s: verifying dest buffer...\n", current->comm);
-		error_count += dmatest_verify(thread->dsts, 0, dst_off,
+		error_count += dmatest_verify