diff --git a/block/bio.c b/block/bio.c
index bfd41e8b53a87a0df6121b6be2c1d5f656872a2d..748d7132f1728132225e3df63b24b4e5a1d96c13 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -2028,6 +2028,41 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
 	return 0;
 }
 
+/**
+ * bio_associate_create_blkg - associate a bio with a blkg from q
+ * @q: request_queue where bio is going
+ * @bio: target bio
+ *
+ * Associate @bio with the blkg found from the bio's css and the request_queue.
+ * If one is not found, bio_lookup_blkg creates the blkg.
+ */
+int bio_associate_create_blkg(struct request_queue *q, struct bio *bio)
+{
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	int ret = 0;
+
+	/* someone has already associated this bio with a blkg */
+	if (bio->bi_blkg)
+		return ret;
+
+	rcu_read_lock();
+
+	bio_associate_blkcg(bio, NULL);
+	blkcg = bio_blkcg(bio);
+
+	if (!blkcg->css.parent) {
+		ret = bio_associate_blkg(bio, q->root_blkg);
+	} else {
+		blkg = blkg_lookup_create(blkcg, q);
+
+		ret = bio_associate_blkg(bio, blkg);
+	}
+
+	rcu_read_unlock();
+	return ret;
+}
+
 /**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
@@ -2057,6 +2092,9 @@ void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
 {
 	if (src->bi_css)
 		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
+
+	if (src->bi_blkg)
+		bio_associate_blkg(dst, src->bi_blkg);
 }
 EXPORT_SYMBOL_GPL(bio_clone_blkcg_association);
 #endif /* CONFIG_BLK_CGROUP */
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index ffde3ab9f84cf435fb44ce9d933def278c2afdd2..7337fbc7f8507a49112512e47f7e78f34b9ad211 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -392,34 +392,14 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
 				     spinlock_t *lock)
 {
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	struct blkcg *blkcg;
-	struct blkcg_gq *blkg;
-	struct request_queue *q = rqos->q;
+	struct blkcg_gq *blkg = bio->bi_blkg;
 	bool issue_as_root = bio_issue_as_root_blkg(bio);
 
 	if (!blk_iolatency_enabled(blkiolat))
 		return;
 
-	rcu_read_lock();
-	bio_associate_blkcg(bio, NULL);
-	blkcg = bio_blkcg(bio);
-	blkg = blkg_lookup(blkcg, q);
-	if (unlikely(!blkg)) {
-		if (!lock)
-			spin_lock_irq(q->queue_lock);
-		blkg = __blkg_lookup_create(blkcg, q);
-		if (IS_ERR(blkg))
-			blkg = NULL;
-		if (!lock)
-			spin_unlock_irq(q->queue_lock);
-	}
-	if (!blkg)
-		goto out;
-
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
-	bio_associate_blkg(bio, blkg);
-out:
-	rcu_read_unlock();
+
 	while (blkg && blkg->parent) {
 		struct iolatency_grp *iolat = blkg_to_lat(blkg);
 		if (!iolat) {
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index db1a3a2ae00617fbe1e4804bbfd327e37ce55737..e62ae502891b02ddb9f8a04dab6dc77b89a6aa7e 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2118,9 +2118,6 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	/* fallback to root_blkg if we fail to get a blkg ref */
-	if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV))
-		bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg);
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }
@@ -2129,7 +2126,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 		    struct bio *bio)
 {
 	struct throtl_qnode *qn = NULL;
-	struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg);
+	struct throtl_grp *tg = blkg_to_tg(blkg);
 	struct throtl_service_queue *sq;
 	bool rw = bio_data_dir(bio);
 	bool throttled = false;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 14b4fa266357726dd8985bed2e49ae0b4ae2bc5b..829cd0bb407d466b4465ef95fcbdc32610797e6a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -542,11 +542,14 @@ static inline int bio_associate_blkcg_from_page(struct bio *bio,
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
+int bio_associate_create_blkg(struct request_queue *q, struct bio *bio);
 void bio_disassociate_task(struct bio *bio);
 void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
 static inline int bio_associate_blkcg(struct bio *bio,
 			struct cgroup_subsys_state *blkcg_css) { return 0; }
+static inline int bio_associate_create_blkg(struct request_queue *q,
+					    struct bio *bio) { return 0; }
 static inline void bio_disassociate_task(struct bio *bio) { }
 static inline void bio_clone_blkcg_association(struct bio *dst,
 			struct bio *src) { }
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 1fbff1bbb651dff9b24ee1d4d01b7634d5d9f748..6e33ad1d92b484858a5daaedc87df0e303a150ca 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -900,29 +900,17 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg
 static inline bool blkcg_bio_issue_check(struct request_queue *q,
 					 struct bio *bio)
 {
-	struct blkcg *blkcg;
 	struct blkcg_gq *blkg;
 	bool throtl = false;
 
 	rcu_read_lock();
 
-	/* associate blkcg if bio hasn't attached one */
-	bio_associate_blkcg(bio, NULL);
-	blkcg = bio_blkcg(bio);
-
-	blkg = blkg_lookup(blkcg, q);
-	if (unlikely(!blkg)) {
-		spin_lock_irq(q->queue_lock);
-		blkg = __blkg_lookup_create(blkcg, q);
-		if (IS_ERR(blkg))
-			blkg = NULL;
-		spin_unlock_irq(q->queue_lock);
-	}
+	bio_associate_create_blkg(q, bio);
+	blkg = bio->bi_blkg;
 
 	throtl = blk_throtl_bio(q, blkg, bio);
 
 	if (!throtl) {
-		blkg = blkg ?: q->root_blkg;
 		/*
 		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
 		 * is a split bio and we would have already accounted for the