1 files changed, 18 insertions, 22 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e9bf950983c7..93d9d60980fb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -579,6 +579,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
 	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+	if (cpu >= nr_cpu_ids)
+		goto out_queue_exit;
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	if (!q->elevator)
@@ -2141,20 +2143,6 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
 /*
- * Is the request queue handled by an IO scheduler that does not respect
- * hardware queues when dispatching?
- */
-static bool blk_mq_has_sqsched(struct request_queue *q)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (e && e->type->ops.dispatch_request &&
-	    !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
-		return true;
-	return false;
-}
-
-/*
  * Return prefered queue to dispatch from (if any) for non-mq aware IO
  * scheduler.
  */
@@ -2186,7 +2174,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 	unsigned long i;
 
 	sq_hctx = NULL;
-	if (blk_mq_has_sqsched(q))
+	if (blk_queue_sq_sched(q))
 		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
@@ -2214,7 +2202,7 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 	unsigned long i;
 
 	sq_hctx = NULL;
-	if (blk_mq_has_sqsched(q))
+	if (blk_queue_sq_sched(q))
 		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
@@ -2777,15 +2765,20 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		return NULL;
 	}
 
-	rq_qos_throttle(q, *bio);
-
 	if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
 		return NULL;
 	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
 		return NULL;
 
-	rq->cmd_flags = (*bio)->bi_opf;
+	/*
+	 * If any qos ->throttle() end up blocking, we will have flushed the
+	 * plug and hence killed the cached_rq list as well. Pop this entry
+	 * before we throttle.
+	 */
 	plug->cached_rq = rq_list_next(rq);
+	rq_qos_throttle(q, *bio);
+
+	rq->cmd_flags = (*bio)->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 	return rq;
 }
@@ -3443,8 +3436,9 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (blk_mq_hw_queue_mapped(hctx))
 		blk_mq_tag_idle(hctx);
 
-	blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
-			set->queue_depth, flush_rq);
+	if (blk_queue_init_done(q))
+		blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+				set->queue_depth, flush_rq);
 	if (set->ops->exit_request)
 		set->ops->exit_request(set, flush_rq, hctx_idx);
 
@@ -4438,12 +4432,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	if (!qe)
 		return false;
 
+	/* q->elevator needs protection from ->sysfs_lock */
+	mutex_lock(&q->sysfs_lock);
+
 	INIT_LIST_HEAD(&qe->node);
 	qe->q = q;
 	qe->type = q->elevator->type;
 	list_add(&qe->node, head);
 
-	mutex_lock(&q->sysfs_lock);
 	/*
 	 * After elevator_switch_mq, the previous elevator_queue will be
 	 * released by elevator_release. The reference of the io scheduler