diff --git a/block/blk-merge.c b/block/blk-merge.c
index b3ac40aef46b317c5a432a92ba9b40c8e1942504..89b97b5e0881853054c0807c5607c20d91d90762 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -97,19 +97,22 @@ void blk_recalc_rq_segments(struct request *rq)
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
-			&q->queue_flags);
-	bool merge_not_need = bio->bi_vcnt < queue_max_segments(q);
+	unsigned short seg_cnt;
+
+	/* estimate segment number by bi_vcnt for non-cloned bio */
+	if (bio_flagged(bio, BIO_CLONED))
+		seg_cnt = bio_segments(bio);
+	else
+		seg_cnt = bio->bi_vcnt;
 
-	if (no_sg_merge && !bio_flagged(bio, BIO_CLONED) &&
-			merge_not_need)
-		bio->bi_phys_segments = bio->bi_vcnt;
+	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
+			(seg_cnt < queue_max_segments(q)))
+		bio->bi_phys_segments = seg_cnt;
 	else {
 		struct bio *nxt = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio,
-				no_sg_merge && merge_not_need);
+		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
 		bio->bi_next = nxt;
 	}
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 68929bad9a6a4048151f485cc1e44db2d655fc0f..1d016fc9a8b640c54ce7e06e9f1ce1f293b694e6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -107,11 +107,7 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
-/*
- * Guarantee no request is in use, so we can change any data structure of
- * the queue afterward.
- */
-void blk_mq_freeze_queue(struct request_queue *q)
+static void blk_mq_freeze_queue_start(struct request_queue *q)
 {
 	bool freeze;
 
@@ -123,9 +119,23 @@ void blk_mq_freeze_queue(struct request_queue *q)
 		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_queues(q, false);
 	}
+}
+
+static void blk_mq_freeze_queue_wait(struct request_queue *q)
+{
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
 }
 
+/*
+ * Guarantee no request is in use, so we can change any data structure of
+ * the queue afterward.
+ */
+void blk_mq_freeze_queue(struct request_queue *q)
+{
+	blk_mq_freeze_queue_start(q);
+	blk_mq_freeze_queue_wait(q);
+}
+
 static void blk_mq_unfreeze_queue(struct request_queue *q)
 {
 	bool wake;
@@ -1921,7 +1931,7 @@ void blk_mq_free_queue(struct request_queue *q)
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
 {
-	blk_mq_freeze_queue(q);
+	WARN_ON_ONCE(!q->mq_freeze_depth);
 
 	blk_mq_sysfs_unregister(q);
 
@@ -1936,8 +1946,6 @@ static void blk_mq_queue_reinit(struct request_queue *q)
 	blk_mq_map_swqueue(q);
 
 	blk_mq_sysfs_register(q);
-
-	blk_mq_unfreeze_queue(q);
 }
 
 static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
@@ -1956,8 +1964,25 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 		return NOTIFY_OK;
 
 	mutex_lock(&all_q_mutex);
+
+	/*
+	 * We need to freeze and reinit all existing queues.  Freezing
+	 * involves synchronous wait for an RCU grace period and doing it
+	 * one by one may take a long time.  Start freezing all queues in
+	 * one swoop and then wait for the completions so that freezing can
+	 * take place in parallel.
+	 */
+	list_for_each_entry(q, &all_q_list, all_q_node)
+		blk_mq_freeze_queue_start(q);
+	list_for_each_entry(q, &all_q_list, all_q_node)
+		blk_mq_freeze_queue_wait(q);
+
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_queue_reinit(q);
+
+	list_for_each_entry(q, &all_q_list, all_q_node)
+		blk_mq_unfreeze_queue(q);
+
 	mutex_unlock(&all_q_mutex);
 	return NOTIFY_OK;
 }
diff --git a/block/ioprio.c b/block/ioprio.c
index e50170ca7c33f446acc16e29a0d0097828919c30..31666c92b46af29919f42ea3e1093caed7127d71 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -157,14 +157,16 @@ static int get_task_ioprio(struct task_struct *p)
 
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
-	unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+	unsigned short aclass;
+	unsigned short bclass;
 
-	if (aclass == IOPRIO_CLASS_NONE)
-		aclass = IOPRIO_CLASS_BE;
-	if (bclass == IOPRIO_CLASS_NONE)
-		bclass = IOPRIO_CLASS_BE;
+	if (!ioprio_valid(aprio))
+		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+	if (!ioprio_valid(bprio))
+		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 
+	aclass = IOPRIO_PRIO_CLASS(aprio);
+	bclass = IOPRIO_PRIO_CLASS(bprio);
 	if (aclass == bclass)
 		return min(aprio, bprio);
 	if (aclass > bclass)
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 1e053d911240b577df324912bb68af13e6174bcc..b0c2a616c8f9b859191c075526c473ea1df796bc 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -458,7 +458,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
-		goto error;
+		goto error_free_buffer;
 	}
 	blk_rq_set_block_pc(rq);
 
@@ -531,9 +531,11 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	}
 	
 error:
+	blk_put_request(rq);
+
+error_free_buffer:
 	kfree(buffer);
-	if (rq)
-		blk_put_request(rq);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(sg_scsi_ioctl);