diff --git a/fs/buffer.c b/fs/buffer.c
index 98196327ddf0dddc2b3a911441bd4ff493026abf..39ff14403d137be85dcd11161584abeabd9d7577 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1181,7 +1181,20 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
 void mark_buffer_dirty(struct buffer_head *bh)
 {
 	WARN_ON_ONCE(!buffer_uptodate(bh));
-	if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh))
+
+	/*
+	 * Very *carefully* optimize the it-is-already-dirty case.
+	 *
+	 * Don't let the final "is it dirty" escape to before we
+	 * perhaps modified the buffer.
+	 */
+	if (buffer_dirty(bh)) {
+		smp_mb();
+		if (buffer_dirty(bh))
+			return;
+	}
+
+	if (!test_set_buffer_dirty(bh))
 		__set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
 }