1 files changed, 47 insertions, 8 deletions

diff --git a/block/elevator.c b/block/elevator.c
index 03d923196569..4781c4205a5d 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -470,13 +470,16 @@ static struct kobj_type elv_ktype = {
 	.release	= elevator_release,
 };
 
-int elv_register_queue(struct request_queue *q)
+/*
+ * elv_register_queue is called from either blk_register_queue or
+ * elevator_switch, elevator switch is prevented from being happen
+ * in the two paths, so it is safe to not hold q->sysfs_lock.
+ */
+int elv_register_queue(struct request_queue *q, bool uevent)
 {
 	struct elevator_queue *e = q->elevator;
 	int error;
 
-	lockdep_assert_held(&q->sysfs_lock);
-
 	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
 	if (!error) {
 		struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -487,24 +490,34 @@ int elv_register_queue(struct request_queue *q)
 				attr++;
 			}
 		}
-		kobject_uevent(&e->kobj, KOBJ_ADD);
+		if (uevent)
+			kobject_uevent(&e->kobj, KOBJ_ADD);
+
+		mutex_lock(&q->sysfs_lock);
 		e->registered = 1;
+		mutex_unlock(&q->sysfs_lock);
 	}
 	return error;
 }
 
+/*
+ * elv_unregister_queue is called from either blk_unregister_queue or
+ * elevator_switch, elevator switch is prevented from being happen
+ * in the two paths, so it is safe to not hold q->sysfs_lock.
+ */
 void elv_unregister_queue(struct request_queue *q)
 {
-	lockdep_assert_held(&q->sysfs_lock);
-
 	if (q) {
 		struct elevator_queue *e = q->elevator;
 
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
+
+		mutex_lock(&q->sysfs_lock);
 		e->registered = 0;
 		/* Re-enable throttling in case elevator disabled it */
 		wbt_enable_default(q);
+		mutex_unlock(&q->sysfs_lock);
 	}
 }
 
@@ -567,10 +580,32 @@ int elevator_switch_mq(struct request_queue *q,
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (q->elevator) {
-		if (q->elevator->registered)
+		if (q->elevator->registered) {
+			mutex_unlock(&q->sysfs_lock);
+
+			/*
+			 * Concurrent elevator switch can't happen becasue
+			 * sysfs write is always exclusively on same file.
+			 *
+			 * Also the elevator queue won't be freed after
+			 * sysfs_lock is released becasue kobject_del() in
+			 * blk_unregister_queue() waits for completion of
+			 * .store & .show on its attributes.
+			 */
 			elv_unregister_queue(q);
+
+			mutex_lock(&q->sysfs_lock);
+		}
 		ioc_clear_queue(q);
 		elevator_exit(q, q->elevator);
+
+		/*
+		 * sysfs_lock may be dropped, so re-check if queue is
+		 * unregistered. If yes, don't switch to new elevator
+		 * any more
+		 */
+		if (!blk_queue_registered(q))
+			return 0;
 	}
 
 	ret = blk_mq_init_sched(q, new_e);
@@ -578,7 +613,11 @@ int elevator_switch_mq(struct request_queue *q,
 		goto out;
 
 	if (new_e) {
-		ret = elv_register_queue(q);
+		mutex_unlock(&q->sysfs_lock);
+
+		ret = elv_register_queue(q, true);
+
+		mutex_lock(&q->sysfs_lock);
 		if (ret) {
 			elevator_exit(q, q->elevator);
 			goto out;