diff --git a/mm/mremap.c b/mm/mremap.c
index fbb4861964f6..e2b65a17148e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -489,6 +489,53 @@ static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma,
 	return moved;
 }
 
+/*
+ * A helper to check if a previous mapping exists. Required for
+ * move_page_tables() and realign_addr() to determine if a previous mapping
+ * exists before we can do realignment optimizations.
+ */
+static bool can_align_down(struct vm_area_struct *vma, unsigned long addr_to_align,
+			       unsigned long mask)
+{
+	unsigned long addr_masked = addr_to_align & mask;
+
+	/*
+	 * If @addr_to_align of either source or destination is not the beginning
+	 * of the corresponding VMA, we can't align down or we will destroy part
+	 * of the current mapping.
+	 */
+	if (vma->vm_start != addr_to_align)
+		return false;
+
+	/*
+	 * Make sure the realignment doesn't cause the address to fall on an
+	 * existing mapping.
+	 */
+	return find_vma_intersection(vma->vm_mm, addr_masked, vma->vm_start) == NULL;
+}
+
+/* Opportunistically realign to specified boundary for faster copy. */
+static void try_realign_addr(unsigned long *old_addr, struct vm_area_struct *old_vma,
+			     unsigned long *new_addr, struct vm_area_struct *new_vma,
+			     unsigned long mask)
+{
+	/* Skip if the addresses are already aligned. */
+	if ((*old_addr & ~mask) == 0)
+		return;
+
+	/* Only realign if the new and old addresses are mutually aligned. */
+	if ((*old_addr & ~mask) != (*new_addr & ~mask))
+		return;
+
+	/* Ensure realignment doesn't cause overlap with existing mappings. */
+	if (!can_align_down(old_vma, *old_addr, mask) ||
+	    !can_align_down(new_vma, *new_addr, mask))
+		return;
+
+	*old_addr = *old_addr & mask;
+	*new_addr = *new_addr & mask;
+}
+
 unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
@@ -508,6 +555,14 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		return move_hugetlb_page_tables(vma, new_vma, old_addr,
 						new_addr, len);
 
+	/*
+	 * If possible, realign addresses to PMD boundary for faster copy.
+	 * Only realign if the mremap copying hits a PMD boundary.
+	 */
+	if ((vma != new_vma)
+		&& (len >= PMD_SIZE - (old_addr & ~PMD_MASK)))
+		try_realign_addr(&old_addr, vma, &new_addr, new_vma, PMD_MASK);
+
 	flush_cache_range(vma, old_addr, old_end);
 	mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm,
 				old_addr, old_end);
@@ -577,6 +632,13 @@ again:
 
 	mmu_notifier_invalidate_range_end(&range);
 
+	/*
+	 * Prevent negative return values when {old,new}_addr was realigned
+	 * but we broke out of the above loop for the first PMD itself.
+	 */
+	if (len + old_addr < old_end)
+		return 0;
+
 	return len + old_addr - old_end;	/* how much done */
 }