diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 92438e9dacc3..5a87384ea4ff 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -804,11 +804,14 @@ dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
 	int cpu;
+	unsigned long flags;
 
 	dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
 	dma_dest = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE);
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len,
-					 DMA_CTRL_ACK);
+	flags = DMA_CTRL_ACK |
+		DMA_COMPL_SRC_UNMAP_SINGLE |
+		DMA_COMPL_DEST_UNMAP_SINGLE;
+	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
 
 	if (!tx) {
 		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
@@ -850,11 +853,12 @@ dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
 	int cpu;
+	unsigned long flags;
 
 	dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
 	dma_dest = dma_map_page(dev->dev, page, offset, len, DMA_FROM_DEVICE);
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len,
-					 DMA_CTRL_ACK);
+	flags = DMA_CTRL_ACK | DMA_COMPL_SRC_UNMAP_SINGLE;
+	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
 
 	if (!tx) {
 		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
@@ -898,12 +902,13 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
 	int cpu;
+	unsigned long flags;
 
 	dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
 	dma_dest = dma_map_page(dev->dev, dest_pg, dest_off, len,
 				DMA_FROM_DEVICE);
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len,
-					 DMA_CTRL_ACK);
+	flags = DMA_CTRL_ACK;
+	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
 
 	if (!tx) {
 		dma_unmap_page(dev->dev, dma_src, len, DMA_TO_DEVICE);
diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c
index e4fc33c1c32f..1955ee8d6d20 100644
--- a/drivers/dma/ioat_dma.c
+++ b/drivers/dma/ioat_dma.c
@@ -1063,22 +1063,31 @@ static void ioat_dma_cleanup_tasklet(unsigned long data)
 static void
 ioat_dma_unmap(struct ioat_dma_chan *ioat_chan, struct ioat_desc_sw *desc)
 {
-	/*
-	 * yes we are unmapping both _page and _single
-	 * alloc'd regions with unmap_page. Is this
-	 * *really* that bad?
-	 */
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		pci_unmap_page(ioat_chan->device->pdev,
-				pci_unmap_addr(desc, dst),
-				pci_unmap_len(desc, len),
-				PCI_DMA_FROMDEVICE);
+	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+		if (desc->async_tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+			pci_unmap_single(ioat_chan->device->pdev,
+					 pci_unmap_addr(desc, dst),
+					 pci_unmap_len(desc, len),
+					 PCI_DMA_FROMDEVICE);
+		else
+			pci_unmap_page(ioat_chan->device->pdev,
+				       pci_unmap_addr(desc, dst),
+				       pci_unmap_len(desc, len),
+				       PCI_DMA_FROMDEVICE);
+	}
 
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		pci_unmap_page(ioat_chan->device->pdev,
-				pci_unmap_addr(desc, src),
-				pci_unmap_len(desc, len),
-				PCI_DMA_TODEVICE);
+	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		if (desc->async_tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+			pci_unmap_single(ioat_chan->device->pdev,
+					 pci_unmap_addr(desc, src),
+					 pci_unmap_len(desc, len),
+					 PCI_DMA_TODEVICE);
+		else
+			pci_unmap_page(ioat_chan->device->pdev,
+				       pci_unmap_addr(desc, src),
+				       pci_unmap_len(desc, len),
+				       PCI_DMA_TODEVICE);
+	}
 }
 
 /**
@@ -1363,6 +1372,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	int err = 0;
 	struct completion cmp;
 	unsigned long tmo;
+	unsigned long flags;
 
 	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
 	if (!src)
@@ -1392,8 +1402,9 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 				 DMA_TO_DEVICE);
 	dma_dest = dma_map_single(dma_chan->device->dev, dest, IOAT_TEST_SIZE,
 				  DMA_FROM_DEVICE);
+	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_DEST_UNMAP_SINGLE;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
-						   IOAT_TEST_SIZE, 0);
+						   IOAT_TEST_SIZE, flags);
 	if (!tx) {
 		dev_err(&device->pdev->dev,
 			"Self-test prep failed, disabling\n");
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 2e2aa3df170c..ffefba81c818 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -78,12 +78,18 @@ enum dma_transaction_type {
  * 	dependency chains
  * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
  * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
+ * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single
+ * 	(if not set, do the source dma-unmapping as page)
+ * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single
+ * 	(if not set, do the destination dma-unmapping as page)
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
 	DMA_CTRL_ACK = (1 << 1),
 	DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2),
 	DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
+	DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4),
+	DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5),
 };
 
 /**