diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 1887d92e8e92..17706dc91ec9 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -130,3 +130,11 @@ 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 dca2b1355bb1..6150d11a607e 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -61,6 +61,14 @@
  */
 #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.  It is specific to a
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 6db1c475ec82..bfc56cb21705 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -627,14 +627,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	for (i = 0; i < nr_slots(alloc_size + offset); i++)
 		mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(mem->start, index) + offset;
-	/*
-	 * 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(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE ||
+	    dir == DMA_BIDIRECTIONAL))
+		swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
 	return tlb_addr;
 }
 
@@ -701,13 +697,10 @@ void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr,
 void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr,
 		size_t size, enum dma_data_direction dir)
 {
-	/*
-	 * 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(dev, tlb_addr, size, DMA_TO_DEVICE);
-	BUG_ON(!valid_dma_direction(dir));
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE);
+	else
+		BUG_ON(dir != DMA_FROM_DEVICE);
 }
 
 void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr,