Merge commit 'dmaengine-3.13-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/dmaengine

Pull dmaengine changes from Dan

1/ Bartlomiej and Dan finalized a rework of the dma address unmap
   implementation.

2/ In the course of testing 1/ a collection of enhancements to dmatest
   fell out.  Notably basic performance statistics, and fixed / enhanced
   test control through new module parameters 'run', 'wait', 'noverify',
   and 'verbose'.  Thanks to Andriy and Linus for their review.

3/ Testing the raid related corner cases of 1/ triggered bugs in the
   recently added 16-source operation support in the ioatdma driver.

4/ Some minor fixes / cleanups to mv_xor and ioatdma.

Conflicts:
	drivers/dma/dmatest.c

Signed-off-by: Vinod Koul <vinod.koul@intel.com>

5 files changed, 238 insertions, 167 deletions

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 9e62feffb37..f8c0b8dbeb7 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -50,33 +50,36 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 						      &dest, 1, &src, 1, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
-	if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
-		dma_addr_t dma_dest, dma_src;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+
+	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		unsigned long dma_prep_flags = 0;
 
 		if (submit->cb_fn)
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_prep_flags |= DMA_PREP_FENCE;
-		dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
-					DMA_FROM_DEVICE);
-
-		dma_src = dma_map_page(device->dev, src, src_offset, len,
-				       DMA_TO_DEVICE);
-
-		tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
-						    len, dma_prep_flags);
-		if (!tx) {
-			dma_unmap_page(device->dev, dma_dest, len,
-				       DMA_FROM_DEVICE);
-			dma_unmap_page(device->dev, dma_src, len,
-				       DMA_TO_DEVICE);
-		}
+
+		unmap->to_cnt = 1;
+		unmap->addr[0] = dma_map_page(device->dev, src, src_offset, len,
+					      DMA_TO_DEVICE);
+		unmap->from_cnt = 1;
+		unmap->addr[1] = dma_map_page(device->dev, dest, dest_offset, len,
+					      DMA_FROM_DEVICE);
+		unmap->len = len;
+
+		tx = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+						    unmap->addr[0], len,
+						    dma_prep_flags);
 	}
 
 	if (tx) {
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
+
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 	} else {
 		void *dest_buf, *src_buf;
@@ -96,6 +99,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 		async_tx_sync_epilog(submit);
 	}
 
+	dmaengine_unmap_put(unmap);
+
 	return tx;
 }
 EXPORT_SYMBOL_GPL(async_memcpy);
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 91d5d385899..d05327caf69 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -46,49 +46,24 @@ static struct page *pq_scribble_page;
  * do_async_gen_syndrome - asynchronously calculate P and/or Q
  */
 static __async_inline struct dma_async_tx_descriptor *
-do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
-		      const unsigned char *scfs, unsigned int offset, int disks,
-		      size_t len, dma_addr_t *dma_src,
+do_async_gen_syndrome(struct dma_chan *chan,
+		      const unsigned char *scfs, int disks,
+		      struct dmaengine_unmap_data *unmap,
+		      enum dma_ctrl_flags dma_flags,
 		      struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct dma_device *dma = chan->device;
-	enum dma_ctrl_flags dma_flags = 0;
 	enum async_tx_flags flags_orig = submit->flags;
 	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 	dma_async_tx_callback cb_param_orig = submit->cb_param;
 	int src_cnt = disks - 2;
-	unsigned char coefs[src_cnt];
 	unsigned short pq_src_cnt;
 	dma_addr_t dma_dest[2];
 	int src_off = 0;
-	int idx;
-	int i;
 
-	/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
-	if (P(blocks, disks))
-		dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
-					   len, DMA_BIDIRECTIONAL);
-	else
-		dma_flags |= DMA_PREP_PQ_DISABLE_P;
-	if (Q(blocks, disks))
-		dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
-					   len, DMA_BIDIRECTIONAL);
-	else
-		dma_flags |= DMA_PREP_PQ_DISABLE_Q;
-
-	/* convert source addresses being careful to collapse 'empty'
-	 * sources and update the coefficients accordingly
-	 */
-	for (i = 0, idx = 0; i < src_cnt; i++) {
-		if (blocks[i] == NULL)
-			continue;
-		dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
-					    DMA_TO_DEVICE);
-		coefs[idx] = scfs[i];
-		idx++;
-	}
-	src_cnt = idx;
+	if (submit->flags & ASYNC_TX_FENCE)
+		dma_flags |= DMA_PREP_FENCE;
 
 	while (src_cnt > 0) {
 		submit->flags = flags_orig;
@@ -100,28 +75,25 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
 		if (src_cnt > pq_src_cnt) {
 			submit->flags &= ~ASYNC_TX_ACK;
 			submit->flags |= ASYNC_TX_FENCE;
-			dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = NULL;
 			submit->cb_param = NULL;
 		} else {
-			dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = cb_fn_orig;
 			submit->cb_param = cb_param_orig;
 			if (cb_fn_orig)
 				dma_flags |= DMA_PREP_INTERRUPT;
 		}
-		if (submit->flags & ASYNC_TX_FENCE)
-			dma_flags |= DMA_PREP_FENCE;
 
-		/* Since we have clobbered the src_list we are committed
-		 * to doing this asynchronously.  Drivers force forward
-		 * progress in case they can not provide a descriptor
+		/* Drivers force forward progress in case they can not provide
+		 * a descriptor
 		 */
 		for (;;) {
+			dma_dest[0] = unmap->addr[disks - 2];
+			dma_dest[1] = unmap->addr[disks - 1];
 			tx = dma->device_prep_dma_pq(chan, dma_dest,
-						     &dma_src[src_off],
+						     &unmap->addr[src_off],
 						     pq_src_cnt,
-						     &coefs[src_off], len,
+						     &scfs[src_off], unmap->len,
 						     dma_flags);
 			if (likely(tx))
 				break;
@@ -129,6 +101,7 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
 			dma_async_issue_pending(chan);
 		}
 
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 		submit->depend_tx = tx;
 
@@ -188,10 +161,6 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
  * set to NULL those buffers will be replaced with the raid6_zero_page
  * in the synchronous path and omitted in the hardware-asynchronous
  * path.
- *
- * 'blocks' note: if submit->scribble is NULL then the contents of
- * 'blocks' may be overwritten to perform address conversions
- * (dma_map_page() or page_address()).
  */
 struct dma_async_tx_descriptor *
 async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
@@ -202,26 +171,69 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 						      &P(blocks, disks), 2,
 						      blocks, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
-	dma_addr_t *dma_src = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) blocks;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
 
-	if (dma_src && device &&
+	if (unmap &&
 	    (src_cnt <= dma_maxpq(device, 0) ||
 	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {
+		struct dma_async_tx_descriptor *tx;
+		enum dma_ctrl_flags dma_flags = 0;
+		unsigned char coefs[src_cnt];
+		int i, j;
+
 		/* run the p+q asynchronously */
 		pr_debug("%s: (async) disks: %d len: %zu\n",
 			 __func__, disks, len);
-		return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
-					     disks, len, dma_src, submit);
+
+		/* convert source addresses being careful to collapse 'empty'
+		 * sources and update the coefficients accordingly
+		 */
+		unmap->len = len;
+		for (i = 0, j = 0; i < src_cnt; i++) {
+			if (blocks[i] == NULL)
+				continue;
+			unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
+						      len, DMA_TO_DEVICE);
+			coefs[j] = raid6_gfexp[i];
+			unmap->to_cnt++;
+			j++;
+		}
+
+		/*
+		 * DMAs use destinations as sources,
+		 * so use BIDIRECTIONAL mapping
+		 */
+		unmap->bidi_cnt++;
+		if (P(blocks, disks))
+			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
+							offset, len, DMA_BIDIRECTIONAL);
+		else {
+			unmap->addr[j++] = 0;
+			dma_flags |= DMA_PREP_PQ_DISABLE_P;
+		}
+
+		unmap->bidi_cnt++;
+		if (Q(blocks, disks))
+			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
+						       offset, len, DMA_BIDIRECTIONAL);
+		else {
+			unmap->addr[j++] = 0;
+			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
+		}
+
+		tx = do_async_gen_syndrome(chan, coefs, j, unmap, dma_flags, submit);
+		dmaengine_unmap_put(unmap);
+		return tx;
 	}
 
+	dmaengine_unmap_put(unmap);
+
 	/* run the pq synchronously */
 	pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
 
@@ -277,50 +289,60 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 	struct dma_async_tx_descriptor *tx;
 	unsigned char coefs[disks-2];
 	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
-	dma_addr_t *dma_src = NULL;
-	int src_cnt = 0;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(disks < 4);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) blocks;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
 
-	if (dma_src && device && disks <= dma_maxpq(device, 0) &&
+	if (unmap && disks <= dma_maxpq(device, 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {
 		struct device *dev = device->dev;
-		dma_addr_t *pq = &dma_src[disks-2];
-		int i;
+		dma_addr_t pq[2];
+		int i, j = 0, src_cnt = 0;
 
 		pr_debug("%s: (async) disks: %d len: %zu\n",
 			 __func__, disks, len);
-		if (!P(blocks, disks))
+
+		unmap->len = len;
+		for (i = 0; i < disks-2; i++)
+			if (likely(blocks[i])) {
+				unmap->addr[j] = dma_map_page(dev, blocks[i],
+							      offset, len,
+							      DMA_TO_DEVICE);
+				coefs[j] = raid6_gfexp[i];
+				unmap->to_cnt++;
+				src_cnt++;
+				j++;
+			}
+
+		if (!P(blocks, disks)) {
+			pq[0] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
-		else
+		} else {
 			pq[0] = dma_map_page(dev, P(blocks, disks),
 					     offset, len,
 					     DMA_TO_DEVICE);
-		if (!Q(blocks, disks))
+			unmap->addr[j++] = pq[0];
+			unmap->to_cnt++;
+		}
+		if (!Q(blocks, disks)) {
+			pq[1] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
-		else
+		} else {
 			pq[1] = dma_map_page(dev, Q(blocks, disks),
 					     offset, len,
 					     DMA_TO_DEVICE);
+			unmap->addr[j++] = pq[1];
+			unmap->to_cnt++;
+		}
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		for (i = 0; i < disks-2; i++)
-			if (likely(blocks[i])) {
-				dma_src[src_cnt] = dma_map_page(dev, blocks[i],
-								offset, len,
-								DMA_TO_DEVICE);
-				coefs[src_cnt] = raid6_gfexp[i];
-				src_cnt++;
-			}
-
 		for (;;) {
-			tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
+			tx = device->device_prep_dma_pq_val(chan, pq,
+							    unmap->addr,
 							    src_cnt,
 							    coefs,
 							    len, pqres,
@@ -330,6 +352,8 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			async_tx_quiesce(&submit->depend_tx);
 			dma_async_issue_pending(chan);
 		}
+
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 
 		return tx;
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index a9f08a6a582..934a8498149 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -26,6 +26,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
+#include <linux/dmaengine.h>
 
 static struct dma_async_tx_descriptor *
 async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
@@ -34,35 +35,45 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, srcs, 2, len);
 	struct dma_device *dma = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 	const u8 *amul, *bmul;
 	u8 ax, bx;
 	u8 *a, *b, *c;
 
-	if (dma) {
-		dma_addr_t dma_dest[2];
-		dma_addr_t dma_src[2];
+	if (dma)
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+
+	if (unmap) {
 		struct device *dev = dma->dev;
+		dma_addr_t pq[2];
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
-		dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
-		dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
-		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef,
+		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
+		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		unmap->to_cnt = 2;
+
+		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->bidi_cnt = 1;
+		/* engine only looks at Q, but expects it to follow P */
+		pq[1] = unmap->addr[2];
+
+		unmap->len = len;
+		tx = dma->device_prep_dma_pq(chan, pq, unmap->addr, 2, coef,
 					     len, dma_flags);
 		if (tx) {
+			dma_set_unmap(tx, unmap);
 			async_tx_submit(chan, tx, submit);
+			dmaengine_unmap_put(unmap);
 			return tx;
 		}
 
 		/* could not get a descriptor, unmap and fall through to
 		 * the synchronous path
 		 */
-		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
-		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
-		dma_unmap_page(dev, dma_src[1], len, DMA_TO_DEVICE);
+		dmaengine_unmap_put(unmap);
 	}
 
 	/* run the operation synchronously */
@@ -89,23 +100,38 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, &src, 1, len);
 	struct dma_device *dma = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 	const u8 *qmul; /* Q multiplier table */
 	u8 *d, *s;
 
-	if (dma) {
+	if (dma)
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+
+	if (unmap) {
 		dma_addr_t dma_dest[2];
-		dma_addr_t dma_src[1];
 		struct device *dev = dma->dev;
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
-		dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
-		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef,
-					     len, dma_flags);
+		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		unmap->to_cnt++;
+		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		dma_dest[1] = unmap->addr[1];
+		unmap->bidi_cnt++;
+		unmap->len = len;
+
+		/* this looks funny, but the engine looks for Q at
+		 * dma_dest[1] and ignores dma_dest[0] as a dest
+		 * due to DMA_PREP_PQ_DISABLE_P
+		 */
+		tx = dma->device_prep_dma_pq(chan, dma_dest, unmap->addr,
+					     1, &coef, len, dma_flags);
+
 		if (tx) {
+			dma_set_unmap(tx, unmap);
+			dmaengine_unmap_put(unmap);
 			async_tx_submit(chan, tx, submit);
 			return tx;
 		}
@@ -113,8 +139,7 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 		/* could not get a descriptor, unmap and fall through to
 		 * the synchronous path
 		 */
-		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
-		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
+		dmaengine_unmap_put(unmap);
 	}
 
 	/* no channel available, or failed to allocate a descriptor, so
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 8ade0a0481c..3c562f5a60b 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -33,48 +33,31 @@
 
 /* do_async_xor - dma map the pages and perform the xor with an engine */
 static __async_inline struct dma_async_tx_descriptor *
-do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
-	     unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
+do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 	     struct async_submit_ctl *submit)
 {
 	struct dma_device *dma = chan->device;
 	struct dma_async_tx_descriptor *tx = NULL;
-	int src_off = 0;
-	int i;
 	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 	void *cb_param_orig = submit->cb_param;
 	enum async_tx_flags flags_orig = submit->flags;
-	enum dma_ctrl_flags dma_flags;
-	int xor_src_cnt = 0;
-	dma_addr_t dma_dest;
-
-	/* map the dest bidrectional in case it is re-used as a source */
-	dma_dest = dma_map_page(dma->dev, dest, offset, len, DMA_BIDIRECTIONAL);
-	for (i = 0; i < src_cnt; i++) {
-		/* only map the dest once */
-		if (!src_list[i])
-			continue;
-		if (unlikely(src_list[i] == dest)) {
-			dma_src[xor_src_cnt++] = dma_dest;
-			continue;
-		}
-		dma_src[xor_src_cnt++] = dma_map_page(dma->dev, src_list[i], offset,
-						      len, DMA_TO_DEVICE);
-	}
-	src_cnt = xor_src_cnt;
+	enum dma_ctrl_flags dma_flags = 0;
+	int src_cnt = unmap->to_cnt;
+	int xor_src_cnt;
+	dma_addr_t dma_dest = unmap->addr[unmap->to_cnt];
+	dma_addr_t *src_list = unmap->addr;
 
 	while (src_cnt) {
+		dma_addr_t tmp;
+
 		submit->flags = flags_orig;
-		dma_flags = 0;
 		xor_src_cnt = min(src_cnt, (int)dma->max_xor);
-		/* if we are submitting additional xors, leave the chain open,
-		 * clear the callback parameters, and leave the destination
-		 * buffer mapped
+		/* if we are submitting additional xors, leave the chain open
+		 * and clear the callback parameters
 		 */
 		if (src_cnt > xor_src_cnt) {
 			submit->flags &= ~ASYNC_TX_ACK;
 			submit->flags |= ASYNC_TX_FENCE;
-			dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = NULL;
 			submit->cb_param = NULL;
 		} else {
@@ -85,12 +68,18 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 			dma_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		/* Since we have clobbered the src_list we are committed
-		 * to doing this asynchronously.  Drivers force forward progress
-		 * in case they can not provide a descriptor
+
+		/* Drivers force forward progress in case they can not provide a
+		 * descriptor
 		 */
-		tx = dma->device_prep_dma_xor(chan, dma_dest, &dma_src[src_off],
-					      xor_src_cnt, len, dma_flags);
+		tmp = src_list[0];
+		if (src_list > unmap->addr)
+			src_list[0] = dma_dest;
+		tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
+					      xor_src_cnt, unmap->len,
+					      dma_flags);
+		src_list[0] = tmp;
+
 
 		if (unlikely(!tx))
 			async_tx_quiesce(&submit->depend_tx);
@@ -99,22 +88,21 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 		while (unlikely(!tx)) {
 			dma_async_issue_pending(chan);
 			tx = dma->device_prep_dma_xor(chan, dma_dest,
-						      &dma_src[src_off],
-						      xor_src_cnt, len,
+						      src_list,
+						      xor_src_cnt, unmap->len,
 						      dma_flags);
 		}
 
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 		submit->depend_tx = tx;
 
 		if (src_cnt > xor_src_cnt) {
 			/* drop completed sources */
 			src_cnt -= xor_src_cnt;
-			src_off += xor_src_cnt;
-
 			/* use the intermediate result a source */
-			dma_src[--src_off] = dma_dest;
 			src_cnt++;
+			src_list += xor_src_cnt - 1;
 		} else
 			break;
 	}
@@ -189,22 +177,40 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
 						      &dest, 1, src_list,
 						      src_cnt, len);
-	dma_addr_t *dma_src = NULL;
+	struct dma_device *device = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(src_cnt <= 1);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) src_list;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO);
+
+	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+		struct dma_async_tx_descriptor *tx;
+		int i, j;
 
-	if (dma_src && chan && is_dma_xor_aligned(chan->device, offset, 0, len)) {
 		/* run the xor asynchronously */
 		pr_debug("%s (async): len: %zu\n", __func__, len);
 
-		return do_async_xor(chan, dest, src_list, offset, src_cnt, len,
-				    dma_src, submit);
+		unmap->len = len;
+		for (i = 0, j = 0; i < src_cnt; i++) {
+			if (!src_list[i])
+				continue;
+			unmap->to_cnt++;
+			unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
+							offset, len, DMA_TO_DEVICE);
+		}
+
+		/* map it bidirectional as it may be re-used as a source */
+		unmap->addr[j] = dma_map_page(device->dev, dest, offset, len,
+					      DMA_BIDIRECTIONAL);
+		unmap->bidi_cnt = 1;
+
+		tx = do_async_xor(chan, unmap, submit);
+		dmaengine_unmap_put(unmap);
+		return tx;
 	} else {
+		dmaengine_unmap_put(unmap);
 		/* run the xor synchronously */
 		pr_debug("%s (sync): len: %zu\n", __func__, len);
 		WARN_ONCE(chan, "%s: no space for dma address conversion\n",
@@ -268,16 +274,14 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 	struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
-	dma_addr_t *dma_src = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(src_cnt <= 1);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) src_list;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO);
 
-	if (dma_src && device && src_cnt <= device->max_xor &&
+	if (unmap && src_cnt <= device->max_xor &&
 	    is_dma_xor_aligned(device, offset, 0, len)) {
 		unsigned long dma_prep_flags = 0;
 		int i;
@@ -288,11 +292,15 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_prep_flags |= DMA_PREP_FENCE;
-		for (i = 0; i < src_cnt; i++)
-			dma_src[i] = dma_map_page(device->dev, src_list[i],
-						  offset, len, DMA_TO_DEVICE);
 
-		tx = device->device_prep_dma_xor_val(chan, dma_src, src_cnt,
+		for (i = 0; i < src_cnt; i++) {
+			unmap->addr[i] = dma_map_page(device->dev, src_list[i],
+						      offset, len, DMA_TO_DEVICE);
+			unmap->to_cnt++;
+		}
+		unmap->len = len;
+
+		tx = device->device_prep_dma_xor_val(chan, unmap->addr, src_cnt,
 						     len, result,
 						     dma_prep_flags);
 		if (unlikely(!tx)) {
@@ -301,11 +309,11 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 			while (!tx) {
 				dma_async_issue_pending(chan);
 				tx = device->device_prep_dma_xor_val(chan,
-					dma_src, src_cnt, len, result,
+					unmap->addr, src_cnt, len, result,
 					dma_prep_flags);
 			}
 		}
-
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 	} else {
 		enum async_tx_flags flags_orig = submit->flags;
@@ -327,6 +335,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		async_tx_sync_epilog(submit);
 		submit->flags = flags_orig;
 	}
+	dmaengine_unmap_put(unmap);
 
 	return tx;
 }
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index 4a92bac744d..dad95f45b88 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -28,7 +28,7 @@
 #undef pr
 #define pr(fmt, args...) pr_info("raid6test: " fmt, ##args)
 
-#define NDISKS 16 /* Including P and Q */
+#define NDISKS 64 /* Including P and Q */
 
 static struct page *dataptrs[NDISKS];
 static addr_conv_t addr_conv[NDISKS];
@@ -219,6 +219,14 @@ static int raid6_test(void)
 		err += test(11, &tests);
 		err += test(12, &tests);
 	}
+
+	/* the 24 disk case is special for ioatdma as it is the boudary point
+	 * at which it needs to switch from 8-source ops to 16-source
+	 * ops for continuation (assumes DMA_HAS_PQ_CONTINUE is not set)
+	 */
+	if (NDISKS > 24)
+		err += test(24, &tests);
+
 	err += test(NDISKS, &tests);
 
 	pr("\n");