diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index cca64b8..7aece56 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -4698,7 +4698,7 @@ long arch_memory_op(int op, XEN_GUEST_HANDLE(void) arg)
     {
     case XENMEM_add_to_physmap:
     {
-        struct xen_add_to_physmap xatp;
+        struct xen_add_to_physmap xatp, start_xatp;
         struct domain *d;
 
         if ( copy_from_guest(&xatp, arg, 1) )
@@ -4716,7 +4716,13 @@ long arch_memory_op(int op, XEN_GUEST_HANDLE(void) arg)
 
         if ( xatp.space != XENMAPSPACE_gmfn_range )
             xatp.size = 1;
+        else
+        {
+            if ( need_iommu(d) )
+                this_cpu(iommu_dont_flush_iotlb) = 1;
+        }
 
+        start_xatp = xatp;
         for ( ; xatp.size > 0; xatp.size-- )
         {
             if ( hypercall_preempt_check() )
@@ -4729,6 +4735,13 @@ long arch_memory_op(int op, XEN_GUEST_HANDLE(void) arg)
             xatp.gpfn++;
         }
 
+        if ( xatp.space == XENMAPSPACE_gmfn_range && need_iommu(d) )
+        {
+            this_cpu(iommu_dont_flush_iotlb) = 0;
+            iommu_iotlb_flush(d, start_xatp.idx, start_xatp.size - xatp.size);
+            iommu_iotlb_flush(d, start_xatp.gpfn, start_xatp.size - xatp.size);
+        }
+
         rcu_unlock_domain(d);
         if ( rc == -EAGAIN )
         {
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 9c62861..a06c94a 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -52,6 +52,8 @@ bool_t __read_mostly iommu_hap_pt_share = 1;
 bool_t __read_mostly iommu_debug;
 bool_t __read_mostly amd_iommu_perdev_intremap;
 
+DEFINE_PER_CPU(bool_t, iommu_dont_flush_iotlb);
+
 static void __init parse_iommu_param(char *s)
 {
     char *ss;
@@ -227,6 +229,7 @@ static int iommu_populate_page_table(struct domain *d)
 
     spin_lock(&d->page_alloc_lock);
 
+    this_cpu(iommu_dont_flush_iotlb) = 1;
     page_list_for_each ( page, &d->page_list )
     {
         if ( is_hvm_domain(d) ||
@@ -244,6 +247,8 @@ static int iommu_populate_page_table(struct domain *d)
             }
         }
     }
+    this_cpu(iommu_dont_flush_iotlb) = 0;
+    iommu_iotlb_flush_all(d);
     spin_unlock(&d->page_alloc_lock);
     return 0;
 }
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 7ec9541..a3dd018 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -660,7 +660,8 @@ static void dma_pte_clear_one(struct domain *domain, u64 addr)
     spin_unlock(&hd->mapping_lock);
     iommu_flush_cache_entry(pte, sizeof(struct dma_pte));
 
-    __intel_iommu_iotlb_flush(domain, addr >> PAGE_SHIFT_4K , 0, 1);
+    if ( !this_cpu(iommu_dont_flush_iotlb) )
+        __intel_iommu_iotlb_flush(domain, addr >> PAGE_SHIFT_4K , 0, 1);
 
     unmap_vtd_domain_page(page);
 
@@ -1753,7 +1754,8 @@ static int intel_iommu_map_page(
     spin_unlock(&hd->mapping_lock);
     unmap_vtd_domain_page(page);
 
-    __intel_iommu_iotlb_flush(d, gfn, dma_pte_present(old), 1);
+    if ( !this_cpu(iommu_dont_flush_iotlb) )
+        __intel_iommu_iotlb_flush(d, gfn, dma_pte_present(old), 1);
 
     return 0;
 }
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index a1034df..c757a78 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -160,4 +160,6 @@ int iommu_do_domctl(struct xen_domctl *, XEN_GUEST_HANDLE(xen_domctl_t));
 void iommu_iotlb_flush(struct domain *d, unsigned long gfn, unsigned int page_count);
 void iommu_iotlb_flush_all(struct domain *d);
 
+DECLARE_PER_CPU(bool_t, iommu_dont_flush_iotlb);
+
 #endif /* _IOMMU_H_ */