diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 31f114f486c4..9bf19b5bf755 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pgtable.h>
+#include <linux/slab.h>
 
 struct cma;
 
@@ -277,6 +278,66 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
+/*
+ * Check whether potential kmalloc() buffers are safe for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_safe(struct device *dev,
+				    enum dma_data_direction dir)
+{
+	/*
+	 * If DMA bouncing of kmalloc() buffers is disabled, the kmalloc()
+	 * caches have already been aligned to a DMA-safe size.
+	 */
+	if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+		return true;
+
+	/*
+	 * kmalloc() buffers are DMA-safe irrespective of size if the device
+	 * is coherent or the direction is DMA_TO_DEVICE (non-desctructive
+	 * cache maintenance and benign cache line evictions).
+	 */
+	if (dev_is_dma_coherent(dev) || dir == DMA_TO_DEVICE)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given size, assuming it is for a kmalloc()'ed buffer, is
+ * sufficiently aligned for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_size_aligned(size_t size)
+{
+	/*
+	 * Larger kmalloc() sizes are guaranteed to be aligned to
+	 * ARCH_DMA_MINALIGN.
+	 */
+	if (size >= 2 * ARCH_DMA_MINALIGN ||
+	    IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment()))
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given object size may have originated from a kmalloc()
+ * buffer with a slab alignment below the DMA-safe alignment and needs
+ * bouncing for non-coherent DMA. The pointer alignment is not considered and
+ * in-structure DMA-safe offsets are the responsibility of the caller. Such
+ * code should use the static ARCH_DMA_MINALIGN for compiler annotations.
+ *
+ * The heuristics can have false positives, bouncing unnecessarily, though the
+ * buffers would be small. False negatives are theoretically possible if, for
+ * example, multiple small kmalloc() buffers are coalesced into a larger
+ * buffer that passes the alignment check. There are no such known constructs
+ * in the kernel.
+ */
+static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size,
+					    enum dma_data_direction dir)
+{
+	return !dma_kmalloc_safe(dev, dir) && !dma_kmalloc_size_aligned(size);
+}
+
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index acc6f231259c..abea1823fe21 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -90,6 +90,10 @@ config SWIOTLB
 	bool
 	select NEED_DMA_MAP_STATE
 
+config DMA_BOUNCE_UNALIGNED_KMALLOC
+	bool
+	depends on SWIOTLB
+
 config DMA_RESTRICTED_POOL
 	bool "DMA Restricted Pool"
 	depends on OF && OF_RESERVED_MEM && SWIOTLB
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e38ffc5e6bdd..97ec892ea0b5 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -94,7 +94,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+	    dma_kmalloc_needs_bounce(dev, size, dir)) {
 		if (is_pci_p2pdma_page(page))
 			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))