diff --git a/block/bio.c b/block/bio.c
index 8bfdea58159ba9ffd972dd95717e0eee99101e0a..9ef6cf3addb38cae822d0e5c5ef18ba9e98cd2d7 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -599,6 +599,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_disk = bio_src->bi_disk;
 	bio->bi_partno = bio_src->bi_partno;
 	bio_set_flag(bio, BIO_CLONED);
+	if (bio_flagged(bio_src, BIO_THROTTLED))
+		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 825bc29767e6699ac85675d319a9866b70cc9b84..d19f416d61012ac032c49608f0afe463c948e8bc 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2226,13 +2226,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out:
-	/*
-	 * As multiple blk-throtls may stack in the same issue path, we
-	 * don't want bios to leave with the flag set.  Clear the flag if
-	 * being issued.
-	 */
-	if (!throttled)
-		bio_clear_flag(bio, BIO_THROTTLED);
+	bio_set_flag(bio, BIO_THROTTLED);
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	if (throttled || !td->track_bio_latency)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 82f0c8fd7be8fd20951af806319f64f615f4ffc6..23d29b39f71e83e8a6a25540adc2e3f28702aec7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -492,6 +492,8 @@ extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 #define bio_set_dev(bio, bdev) 			\
 do {						\
+	if ((bio)->bi_disk != (bdev)->bd_disk)	\
+		bio_clear_flag(bio, BIO_THROTTLED);\
 	(bio)->bi_disk = (bdev)->bd_disk;	\
 	(bio)->bi_partno = (bdev)->bd_partno;	\
 } while (0)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index a1e628e032dad75bf1837a25e45b55a7f54ca2df..9e7d8bd776d227d2ba92b137af7230300f5b1d4a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -50,8 +50,6 @@ struct blk_issue_stat {
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct gendisk		*bi_disk;
-	u8			bi_partno;
-	blk_status_t		bi_status;
 	unsigned int		bi_opf;		/* bottom bits req flags,
 						 * top bits REQ_OP. Use
 						 * accessors.
@@ -59,8 +57,8 @@ struct bio {
 	unsigned short		bi_flags;	/* status, etc and bvec pool number */
 	unsigned short		bi_ioprio;
 	unsigned short		bi_write_hint;
-
-	struct bvec_iter	bi_iter;
+	blk_status_t		bi_status;
+	u8			bi_partno;
 
 	/* Number of segments in this BIO after
 	 * physical address coalescing is performed.
@@ -74,8 +72,9 @@ struct bio {
 	unsigned int		bi_seg_front_size;
 	unsigned int		bi_seg_back_size;
 
-	atomic_t		__bi_remaining;
+	struct bvec_iter	bi_iter;
 
+	atomic_t		__bi_remaining;
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;