diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 003f7bc..07ae73f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1189,8 +1189,15 @@
 		goto out_free_pages;
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
+	/*
+	 * Leave pmd empty until pte is filled note we must notify here as
+	 * concurrent CPU thread might write to new page before the call to
+	 * mmu_notifier_invalidate_range_end() happens which can lead to a
+	 * device seeing memory write in different order than CPU.
+	 *
+	 * See Documentation/vm/mmu_notifier.txt
+	 */
 	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
-	/* leave pmd empty until pte is filled */
 
 	pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, vmf->pmd);
 	pmd_populate(vma->vm_mm, &_pmd, pgtable);
@@ -2029,8 +2036,15 @@
 	pmd_t _pmd;
 	int i;
 
-	/* leave pmd empty until pte is filled */
-	pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+	/*
+	 * Leave pmd empty until pte is filled note that it is fine to delay
+	 * notification until mmu_notifier_invalidate_range_end() as we are
+	 * replacing a zero pmd write protected page with a zero pte write
+	 * protected page.
+	 *
+	 * See Documentation/vm/mmu_notifier.txt
+	 */
+	pmdp_huge_clear_flush(vma, haddr, pmd);
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);