block: move wbt_enable_default() out of queue freezing from sched ->exit()

scheduler's ->exit() is called with queue frozen and elevator lock is held, and
wbt_enable_default() can't be called with queue frozen, otherwise the
following lockdep warning is triggered:

	#6 (&q->rq_qos_mutex){+.+.}-{4:4}:
	#5 (&eq->sysfs_lock){+.+.}-{4:4}:
	#4 (&q->elevator_lock){+.+.}-{4:4}:
	#3 (&q->q_usage_counter(io)#3){++++}-{0:0}:
	#2 (fs_reclaim){+.+.}-{0:0}:
	#1 (&sb->s_type->i_mutex_key#3){+.+.}-{4:4}:
	#0 (&q->debugfs_mutex){+.+.}-{4:4}:

Fix the issue by moving wbt_enable_default() out of bfq's exit(), and
call it from elevator_change_done().

Meantime add disk->rqos_state_mutex for covering wbt state change, which
matches the purpose more than ->elevator_lock.

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/20250505141805.2751237-26-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/bfq-iosched.c

@@ -7211,7 +7211,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	blk_stat_disable_accounting(bfqd->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_DISABLE_WBT_DEF, bfqd->queue);
-	wbt_enable_default(bfqd->queue->disk);
+	set_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, &e->flags);
 
 	kfree(bfqd);
 }

block/blk-sysfs.c

@@ -560,7 +560,7 @@ static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
 	ssize_t ret;
 	struct request_queue *q = disk->queue;
 
-	mutex_lock(&q->elevator_lock);
+	mutex_lock(&disk->rqos_state_mutex);
 	if (!wbt_rq_qos(q)) {
 		ret = -EINVAL;
 		goto out;
@@ -573,7 +573,7 @@ static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
 
 	ret = sysfs_emit(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 out:
-	mutex_unlock(&q->elevator_lock);
+	mutex_unlock(&disk->rqos_state_mutex);
 	return ret;
 }
 
@@ -593,7 +593,6 @@ static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
 		return -EINVAL;
 
 	memflags = blk_mq_freeze_queue(q);
-	mutex_lock(&q->elevator_lock);
 
 	rqos = wbt_rq_qos(q);
 	if (!rqos) {
@@ -618,11 +617,12 @@ static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
 	 */
 	blk_mq_quiesce_queue(q);
 
+	mutex_lock(&disk->rqos_state_mutex);
 	wbt_set_min_lat(q, val);
+	mutex_unlock(&disk->rqos_state_mutex);
 
 	blk_mq_unquiesce_queue(q);
 out:
-	mutex_unlock(&q->elevator_lock);
 	blk_mq_unfreeze_queue(q, memflags);
 
 	return ret;
@@ -871,9 +871,7 @@ int blk_register_queue(struct gendisk *disk)
 
 	if (queue_is_mq(q))
 		elevator_set_default(q);
-	mutex_lock(&q->elevator_lock);
 	wbt_enable_default(disk);
-	mutex_unlock(&q->elevator_lock);
 
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 

block/blk-wbt.c

@@ -704,6 +704,8 @@ void wbt_enable_default(struct gendisk *disk)
 	struct rq_qos *rqos;
 	bool enable = IS_ENABLED(CONFIG_BLK_WBT_MQ);
 
+	mutex_lock(&disk->rqos_state_mutex);
+
 	if (blk_queue_disable_wbt(q))
 		enable = false;
 
@@ -712,8 +714,10 @@ void wbt_enable_default(struct gendisk *disk)
 	if (rqos) {
 		if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT)
 			RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT;
+		mutex_unlock(&disk->rqos_state_mutex);
 		return;
 	}
+	mutex_unlock(&disk->rqos_state_mutex);
 
 	/* Queue not registered? Maybe shutting down... */
 	if (!blk_queue_registered(q))
@@ -773,11 +777,13 @@ void wbt_disable_default(struct gendisk *disk)
 	struct rq_wb *rwb;
 	if (!rqos)
 		return;
+	mutex_lock(&disk->rqos_state_mutex);
 	rwb = RQWB(rqos);
 	if (rwb->enable_state == WBT_STATE_ON_DEFAULT) {
 		blk_stat_deactivate(rwb->cb);
 		rwb->enable_state = WBT_STATE_OFF_DEFAULT;
 	}
+	mutex_unlock(&disk->rqos_state_mutex);
 }
 EXPORT_SYMBOL_GPL(wbt_disable_default);
 

block/elevator.c

@@ -637,8 +637,13 @@ static int elevator_change_done(struct request_queue *q,
 	int ret = 0;
 
 	if (ctx->old) {
+		bool enable_wbt = test_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT,
+				&ctx->old->flags);
+
 		elv_unregister_queue(q, ctx->old);
 		kobject_put(&ctx->old->kobj);
+		if (enable_wbt)
+			wbt_enable_default(q->disk);
 	}
 	if (ctx->new) {
 		ret = elv_register_queue(q, ctx->new, !ctx->no_uevent);

block/elevator.h

@@ -122,6 +122,7 @@ struct elevator_queue
 
 #define ELEVATOR_FLAG_REGISTERED	0
 #define ELEVATOR_FLAG_DYING		1
+#define ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT	2
 
 /*
  * block elevator interface

block/genhd.c

@@ -1470,6 +1470,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
 	INIT_LIST_HEAD(&disk->slave_bdevs);
 #endif
+	mutex_init(&disk->rqos_state_mutex);
 	return disk;
 
 out_erase_part0:

include/linux/blkdev.h

@@ -218,6 +218,8 @@ struct gendisk {
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
+
+	struct mutex rqos_state_mutex;	/* rqos state change mutex */
 };
 
 /**