diff --git a/block/bio.c b/block/bio.c
index 117da319afb62c7a33d59479bf997a6245943440..c2ff8a88aef15f34c75d8e1caca57e6cd745e3ad 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -271,7 +271,7 @@ void bio_init(struct bio *bio)
 	memset(bio, 0, sizeof(*bio));
 	bio->bi_flags = 1 << BIO_UPTODATE;
 	atomic_set(&bio->__bi_remaining, 1);
-	atomic_set(&bio->bi_cnt, 1);
+	atomic_set(&bio->__bi_cnt, 1);
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -524,13 +524,17 @@ EXPORT_SYMBOL(zero_fill_bio);
  **/
 void bio_put(struct bio *bio)
 {
-	BIO_BUG_ON(!atomic_read(&bio->bi_cnt));
-
-	/*
-	 * last put frees it
-	 */
-	if (atomic_dec_and_test(&bio->bi_cnt))
+	if (!bio_flagged(bio, BIO_REFFED))
 		bio_free(bio);
+	else {
+		BIO_BUG_ON(!atomic_read(&bio->__bi_cnt));
+
+		/*
+		 * last put frees it
+		 */
+		if (atomic_dec_and_test(&bio->__bi_cnt))
+			bio_free(bio);
+	}
 }
 EXPORT_SYMBOL(bio_put);
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ab43faddb447e365f85fdfddb53ca4accddb0f17..1616f668a4cb043741520d724b2f3602da0e07be 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -619,7 +619,7 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio)
 	bio->bi_end_io		= request_endio;
 	bio->bi_private		= &s->cl;
 
-	atomic_set(&bio->bi_cnt, 3);
+	bio_cnt_set(bio, 3);
 }
 
 static void search_free(struct closure *cl)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 96aebf3bcd5b37d35604c76ec584d29686ad34e2..8e8d1d1e28a52cad010416887b8613b48e30c113 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -345,7 +345,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device)
 		    waitqueue_active(&fs_info->async_submit_wait))
 			wake_up(&fs_info->async_submit_wait);
 
-		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
+		BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
 
 		/*
 		 * if we're doing the sync list, record that our
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index a56960dd16847bccd3fea619f28aedad0f744f31..095f94c2d8b564a46d3c48636fb0532e6b10a658 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -356,7 +356,6 @@ xfs_end_bio(
 {
 	xfs_ioend_t		*ioend = bio->bi_private;
 
-	ASSERT(atomic_read(&bio->bi_cnt) >= 1);
 	ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error;
 
 	/* Toss bio and pass work off to an xfsdatad thread */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8bfe9eee6d1a0ef8d1ebc4a397f98a628c7c5364..7486ea103f6e3c719437f9c75a4573880447dcd7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -290,7 +290,21 @@ static inline unsigned bio_segments(struct bio *bio)
  * returns. and then bio would be freed memory when if (bio->bi_flags ...)
  * runs
  */
-#define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
+static inline void bio_get(struct bio *bio)
+{
+	bio->bi_flags |= (1 << BIO_REFFED);
+	smp_mb__before_atomic();
+	atomic_inc(&bio->__bi_cnt);
+}
+
+static inline void bio_cnt_set(struct bio *bio, unsigned int count)
+{
+	if (count != 1) {
+		bio->bi_flags |= (1 << BIO_REFFED);
+		smp_mb__before_atomic();
+	}
+	atomic_set(&bio->__bi_cnt, count);
+}
 
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 8b07e06038871bd3a0bdd09a8fd9313ab688d6ea..93d2e715381695baaf6fde81ad5937efffc94d4b 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -92,7 +92,7 @@ struct bio {
 
 	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */
 
-	atomic_t		bi_cnt;		/* pin count */
+	atomic_t		__bi_cnt;	/* pin count */
 
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
 
@@ -123,6 +123,7 @@ struct bio {
 #define BIO_QUIET	9	/* Make BIO Quiet */
 #define BIO_SNAP_STABLE	10	/* bio data must be snapshotted during write */
 #define BIO_CHAIN	11	/* chained bio, ->bi_remaining in effect */
+#define BIO_REFFED	12	/* bio has elevated ->bi_cnt */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes