block: Fix a blk_exit_rl() regression

Avoid that the following complaint is reported:

BUG: sleeping function called from invalid context at kernel/workqueue.c:2790
in_atomic(): 1, irqs_disabled(): 0, pid: 41, name: rcuop/3
1 lock held by rcuop/3/41:
#0: (rcu_callback){......}, at: [<ffffffff8111f9a2>] rcu_nocb_kthread+0x282/0x500
Call Trace:
dump_stack+0x86/0xcf
___might_sleep+0x174/0x260
__might_sleep+0x4a/0x80
flush_work+0x7e/0x2e0
__cancel_work_timer+0x143/0x1c0
cancel_work_sync+0x10/0x20
blk_throtl_exit+0x25/0x60
blkcg_exit_queue+0x35/0x40
blk_release_queue+0x42/0x130
kobject_put+0xa9/0x190

This happens since we invoke callbacks that need to block from the
queue release handler. Fix this by pushing the final release to
a workqueue.

Reported-by: Ross Zwisler <[e-mail]>
Fixes: commit b425e5049258 ("block: Avoid that blk_exit_rl() triggers a use-after-free")
Signed-off-by: Bart Van Assche <[e-mail]>
Tested-by: Ross Zwisler <[e-mail]>

Updated changelog
Signed-off-by: Jens Axboe <[e-mail]>

block/blk-sysfs.c

···
 }
 
 /**
- * blk_release_queue: - release a &struct request_queue when it is no longer needed
- * @kobj:    the kobj belonging to the request queue to be released
+ * __blk_release_queue - release a request queue when it is no longer needed
+ * @work: pointer to the release_work member of the request queue to be released
  *
  * Description:
- *     blk_release_queue is the pair to blk_init_queue() or
- *     blk_queue_make_request().  It should be called when a request queue is
- *     being released; typically when a block device is being de-registered.
- *     Currently, its primary task it to free all the &struct request
- *     structures that were allocated to the queue and the queue itself.
+ *     blk_release_queue is the counterpart of blk_init_queue(). It should be
+ *     called when a request queue is being released; typically when a block
+ *     device is being de-registered. Its primary task it to free the queue
+ *     itself.
  *
- * Note:
+ * Notes:
  *     The low level driver must have finished any outstanding requests first
  *     via blk_cleanup_queue().
- **/
-static void blk_release_queue(struct kobject *kobj)
+ *
+ *     Although blk_release_queue() may be called with preemption disabled,
+ *     __blk_release_queue() may sleep.
+ */
+static void __blk_release_queue(struct work_struct *work)
 {
-	struct request_queue *q =
-		container_of(kobj, struct request_queue, kobj);
+	struct request_queue *q = container_of(work, typeof(*q), release_work);
 
 	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
 		blk_stat_remove_callback(q, q->poll_cb);
···
 
 	ida_simple_remove(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
+}
+
+static void blk_release_queue(struct kobject *kobj)
+{
+	struct request_queue *q =
+		container_of(kobj, struct request_queue, kobj);
+
+	INIT_WORK(&q->release_work, __blk_release_queue);
+	schedule_work(&q->release_work);
 }
 
 static const struct sysfs_ops queue_sysfs_ops = {

include/linux/blkdev.h

···
 
 	size_t			cmd_size;
 	void			*rq_alloc_data;
+
+	struct work_struct	release_work;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */