diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 135c24a5ba262b76529fa1c3dbe088d098de84a5..68c739b3fdf41b8b70dd09170661ae95f6c352dc 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_remap(cookie, size) ioremap_cache((cookie), (size))
 #define xen_unmap(cookie) iounmap((cookie))
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn);
+
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index ab700e1e59226696d96b9d21dc8241f2ebc285bb..28ebf3ecee4ee6a85e03b4821d7654a106bad085 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -100,6 +100,13 @@ void __xen_dma_sync_single_for_device(struct device *hwdev,
 	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
 }
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn)
+{
+	return ((pfn != mfn) && !is_device_dma_coherent(dev));
+}
+
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c949923a56685463465b9281b3b4d5cb1c28a7d6..f58ef6c0613b6739351e4366a3b869c9c2ecb72b 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr);
 #define xen_remap(cookie, size) ioremap((cookie), (size));
 #define xen_unmap(cookie) iounmap((cookie))
 
+static inline bool xen_arch_need_swiotlb(struct device *dev,
+					 unsigned long pfn,
+					 unsigned long mfn)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ad2c5eb8a9c79b7f64ce04dcf995b5422720d7b4..3725ee4ff43c0f2ed66391dd79f09b42e4a26e62 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -399,7 +399,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
-	    !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+	    !range_straddles_page_boundary(phys, size) &&
+		!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
+		!swiotlb_force) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
@@ -557,6 +559,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
 		if (swiotlb_force ||
+		    xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
 			phys_addr_t map = swiotlb_tbl_map_single(hwdev,