block: don't release queue's sysfs lock during switching elevator

mainline inclusion
from mainline-5.4-rc1
commit b89f625e
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I6HOKY
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h=v6.2&id=b89f625e28d44552083f43752f62d8621ded0a04

---------------------------

cecf5d87 ("block: split .sysfs_lock into two locks") starts to
release & acquire sysfs_lock before registering/un-registering elevator
queue during switching elevator for avoiding potential deadlock from
showing & storing 'queue/iosched' attributes and removing elevator's
kobject.

Turns out there isn't such deadlock because 'q->sysfs_lock' isn't
required in .show & .store of queue/iosched's attributes, and just
elevator's sysfs lock is acquired in elv_iosched_store() and
elv_iosched_show(). So it is safe to hold queue's sysfs lock when
registering/un-registering elevator queue.

The biggest issue is that commit cecf5d87 assumes that concurrent
write on 'queue/scheduler' can't happen. However, this assumption isn't
true, because kernfs_fop_write() only guarantees that concurrent write
aren't called on the same open file, but the write could be from
different open on the file. So we can't release & re-acquire queue's
sysfs lock during switching elevator, otherwise use-after-free on
elevator could be triggered.

Fixes the issue by not releasing queue's sysfs lock during switching
elevator.

Fixes: cecf5d87 ("block: split .sysfs_lock into two locks")
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Conflict:
  block/blk-sysfs.c
  block/elevator.c
Signed-off-by: NLi Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: NHou Tao <houtao1@huawei.com>
Signed-off-by: NYongqiang Liu <liuyongqiang13@huawei.com>

block/blk-sysfs.c

@@ -959,13 +959,11 @@ int blk_register_queue(struct gendisk *disk)
 		blk_mq_debugfs_register(q);
 	}
 
-	/*
-	 * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
-	 * switch won't happen at all.
-	 */
+	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator)) {
 		ret = elv_register_queue(q, false);
 		if (ret) {
+			mutex_unlock(&q->sysfs_lock);
 			mutex_unlock(&q->sysfs_dir_lock);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
@@ -975,7 +973,6 @@ int blk_register_queue(struct gendisk *disk)
 		has_elevator = true;
 	}
 
-	mutex_lock(&q->sysfs_lock);
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 	wbt_enable_default(q);
 	blk_throtl_register_queue(q);
@@ -1049,12 +1046,10 @@ void blk_unregister_queue(struct gendisk *disk)
 
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	/*
-	 * q->kobj has been removed, so it is safe to check if elevator
-	 * exists without holding q->sysfs_lock.
-	 */
+	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))
 		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);
 
 	/* Now that we've deleted all child objects, we can delete the queue. */

block/elevator.c

@@ -864,11 +864,9 @@ int elv_register_queue(struct request_queue *q, bool uevent)
 		if (uevent)
 			kobject_uevent(&e->kobj, KOBJ_ADD);
 
-		mutex_lock(&q->sysfs_lock);
 		e->registered = 1;
 		if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
 			e->type->ops.sq.elevator_registered_fn(q);
-		mutex_unlock(&q->sysfs_lock);
 	}
 	return error;
 }
@@ -886,9 +884,7 @@ void elv_unregister_queue(struct request_queue *q)
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
 
-		mutex_lock(&q->sysfs_lock);
 		e->registered = 0;
-		mutex_unlock(&q->sysfs_lock);
 	}
 }
 
@@ -959,32 +955,11 @@ int elevator_switch_mq(struct request_queue *q,
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (q->elevator) {
-		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.
-			 */
+		if (q->elevator->registered)
 			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 (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
-			return 0;
 	}
 
 	ret = blk_mq_init_sched(q, new_e);
@@ -992,11 +967,7 @@ int elevator_switch_mq(struct request_queue *q,
 		goto out;
 
 	if (new_e) {
-		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;