diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7dfe681acc3d..761c1b251c1e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2283,9 +2283,9 @@ static int
 __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 unsigned long phys_pfn, unsigned long nr_pages, int prot)
 {
-	struct dma_pte *first_pte = NULL, *pte = NULL;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
+	struct dma_pte *pte = NULL;
 	phys_addr_t pteval;
 	u64 attr;
 
@@ -2314,7 +2314,7 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			largepage_lvl = hardware_largepage_caps(domain, iov_pfn,
 					phys_pfn, nr_pages);
 
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
+			pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
 			/* It is large page*/
@@ -2375,34 +2375,14 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 * recalculate 'pte' and switch back to smaller pages for the
 		 * end of the mapping, if the trailing size is not enough to
 		 * use another superpage (i.e. nr_pages < lvl_pages).
+		 *
+		 * We leave clflush for the leaf pte changes to iotlb_sync_map()
+		 * callback.
 		 */
 		pte++;
 		if (!nr_pages || first_pte_in_page(pte) ||
-		    (largepage_lvl > 1 && nr_pages < lvl_pages)) {
-			domain_flush_cache(domain, first_pte,
-					   (void *)pte - (void *)first_pte);
+		    (largepage_lvl > 1 && nr_pages < lvl_pages))
 			pte = NULL;
-		}
-	}
-
-	return 0;
-}
-
-static int
-domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
-	       unsigned long phys_pfn, unsigned long nr_pages, int prot)
-{
-	int iommu_id, ret;
-	struct intel_iommu *iommu;
-
-	/* Do the real mapping first */
-	ret = __domain_mapping(domain, iov_pfn, phys_pfn, nr_pages, prot);
-	if (ret)
-		return ret;
-
-	for_each_domain_iommu(iommu_id, domain) {
-		iommu = g_iommus[iommu_id];
-		__mapping_notify_one(iommu, domain, iov_pfn, nr_pages);
 	}
 
 	return 0;
@@ -4943,7 +4923,6 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;
 	int prot = 0;
-	int ret;
 
 	if (iommu_prot & IOMMU_READ)
 		prot |= DMA_PTE_READ;
@@ -4969,9 +4948,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	/* Round up size to next multiple of PAGE_SIZE, if it and
 	   the low bits of hpa would take us onto the next page */
 	size = aligned_nrpages(hpa, size);
-	ret = domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
-			     hpa >> VTD_PAGE_SHIFT, size, prot);
-	return ret;
+	return __domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
+				hpa >> VTD_PAGE_SHIFT, size, prot);
 }
 
 static size_t intel_iommu_unmap(struct iommu_domain *domain,
@@ -5424,6 +5402,57 @@ static bool risky_device(struct pci_dev *pdev)
 	return false;
 }
 
+static void clflush_sync_map(struct dmar_domain *domain, unsigned long clf_pfn,
+			     unsigned long clf_pages)
+{
+	struct dma_pte *first_pte = NULL, *pte = NULL;
+	unsigned long lvl_pages = 0;
+	int level = 0;
+
+	while (clf_pages > 0) {
+		if (!pte) {
+			level = 0;
+			pte = pfn_to_dma_pte(domain, clf_pfn, &level);
+			if (WARN_ON(!pte))
+				return;
+			first_pte = pte;
+			lvl_pages = lvl_to_nr_pages(level);
+		}
+
+		if (WARN_ON(!lvl_pages || clf_pages < lvl_pages))
+			return;
+
+		clf_pages -= lvl_pages;
+		clf_pfn += lvl_pages;
+		pte++;
+
+		if (!clf_pages || first_pte_in_page(pte) ||
+		    (level > 1 && clf_pages < lvl_pages)) {
+			domain_flush_cache(domain, first_pte,
+					   (void *)pte - (void *)first_pte);
+			pte = NULL;
+		}
+	}
+}
+
+static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
+				       unsigned long iova, size_t size)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long pages = aligned_nrpages(iova, size);
+	unsigned long pfn = iova >> VTD_PAGE_SHIFT;
+	struct intel_iommu *iommu;
+	int iommu_id;
+
+	if (!dmar_domain->iommu_coherency)
+		clflush_sync_map(dmar_domain, pfn, pages);
+
+	for_each_domain_iommu(iommu_id, dmar_domain) {
+		iommu = g_iommus[iommu_id];
+		__mapping_notify_one(iommu, dmar_domain, pfn, pages);
+	}
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
@@ -5436,6 +5465,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.aux_detach_dev		= intel_iommu_aux_detach_device,
 	.aux_get_pasid		= intel_iommu_aux_get_pasid,
 	.map			= intel_iommu_map,
+	.iotlb_sync_map		= intel_iommu_iotlb_sync_map,
 	.unmap			= intel_iommu_unmap,
 	.flush_iotlb_all        = intel_flush_iotlb_all,
 	.iotlb_sync		= intel_iommu_tlb_sync,