diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 8f8d97f65d7375a9fc87f4bad9f4a6c8033e8bba..34742fc00ec053f3087c2919de40066773f51970 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -156,3 +156,11 @@ accesses to DMA buffers in both privileged "supervisor" and unprivileged
 subsystem that the buffer is fully accessible at the elevated privilege
 level (and ideally inaccessible or at least read-only at the
 lesser-privileged levels).
+
+DMA_ATTR_OVERWRITE
+------------------
+
+This is a hint to the DMA-mapping subsystem that the device is expected to
+overwrite the entire mapped size, thus the caller does not require any of the
+previous buffer contents to be preserved. This allows bounce-buffering
+implementations to optimise DMA_FROM_DEVICE transfers.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 9d39d97e09f4dc82bf6418efb943e816ac5e3493..aa23cade6991fc69930169e7ce062a7483a4d4d4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -70,6 +70,14 @@
  */
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
+/*
+ * This is a hint to the DMA-mapping subsystem that the device is expected
+ * to overwrite the entire mapped size, thus the caller does not require any
+ * of the previous buffer contents to be preserved. This allows
+ * bounce-buffering implementations to optimise DMA_FROM_DEVICE transfers.
+ */
+#define DMA_ATTR_OVERWRITE		(1UL << 10)
+
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.
  * It can be given to a device to use as a DMA source or target.  A CPU cannot
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b6eee8ea867bcbcfd57ec7ebfb18432ad865238b..1624d12b60af5d16ac999bfe2a2ae41ddabee811 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -583,14 +583,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	 */
 	for (i = 0; i < nslots; i++)
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
-	/*
-	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
-	 * to the tlb buffer, if we knew for sure the device will
-	 * overwirte the entire current content. But we don't. Thus
-	 * unconditional bounce may prevent leaking swiotlb content (i.e.
-	 * kernel memory) to user-space.
-	 */
-	swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE ||
+	    dir == DMA_BIDIRECTIONAL))
+		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+
 	return tlb_addr;
 }
 
@@ -682,14 +679,11 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
-		/*
-		 * Unconditional bounce is necessary to avoid corruption on
-		 * sync_*_for_cpu or dma_ummap_* when the device didn't overwrite
-		 * the whole lengt of the bounce buffer.
-		 */
-		swiotlb_bounce(orig_addr, tlb_addr,
-			       size, DMA_TO_DEVICE);
-		BUG_ON(!valid_dma_direction(dir));
+		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+			swiotlb_bounce(orig_addr, tlb_addr,
+				       size, DMA_TO_DEVICE);
+		else
+			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
 	default:
 		BUG();