block: don't acquire ->elevator_lock in blk_mq_map_swqueue and blk_mq_realloc_hw_ctxs

JIRA: https://issues.redhat.com/browse/RHEL-106845

commit 0a47d2b
Author: Ming Lei <ming.lei@redhat.com>
Date:   Mon May 5 22:18:01 2025 +0800

    block: don't acquire ->elevator_lock in blk_mq_map_swqueue and blk_mq_realloc_hw_ctxs

    Both blk_mq_map_swqueue() and blk_mq_realloc_hw_ctxs() are called before
    the request queue is added to tagset list, so the two won't run concurrently
    with blk_mq_update_nr_hw_queues().

    When the two functions are only called from queue initialization or
    blk_mq_update_nr_hw_queues(), elevator switch can't happen.

    So remove ->elevator_lock uses from the two functions.

    Reviewed-by: Hannes Reinecke <hare@suse.de>
    Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
    Signed-off-by: Ming Lei <ming.lei@redhat.com>
    Reviewed-by: Christoph Hellwig <hch@lst.de>
    Link: https://lore.kernel.org/r/20250505141805.2751237-24-ming.lei@redhat.com
    Signed-off-by: Jens Axboe <axboe@kernel.dk>

Signed-off-by: Ming Lei <ming.lei@redhat.com>

Author: Ming Lei

block/blk-mq.c

@@ -4156,8 +4156,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
 
-	mutex_lock(&q->elevator_lock);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
 		hctx->nr_ctx = 0;
@@ -4262,8 +4260,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
-
-	mutex_unlock(&q->elevator_lock);
 }
 
 /*
@@ -4567,16 +4563,9 @@ static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 }
 
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
-				   struct request_queue *q, bool lock)
+				   struct request_queue *q)
 {
-	if (lock) {
-		/* protect against switching io scheduler  */
-		mutex_lock(&q->elevator_lock);
-		__blk_mq_realloc_hw_ctxs(set, q);
-		mutex_unlock(&q->elevator_lock);
-	} else {
-		__blk_mq_realloc_hw_ctxs(set, q);
-	}
+	__blk_mq_realloc_hw_ctxs(set, q);
 
 	/* unregister cpuhp callbacks for exited hctxs */
 	blk_mq_remove_hw_queues_cpuhp(q);
@@ -4608,7 +4597,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	xa_init(&q->hctx_table);
 
-	blk_mq_realloc_hw_ctxs(set, q, false);
+	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
 
@@ -5019,7 +5008,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 fallback:
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
-		blk_mq_realloc_hw_ctxs(set, q, true);
+		blk_mq_realloc_hw_ctxs(set, q);
 
 		if (q->nr_hw_queues != set->nr_hw_queues) {
 			int i = prev_nr_hw_queues;