From b89f625e28d44552083f43752f62d8621ded0a04 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 23 Sep 2019 23:12:09 +0800 Subject: block: don't release queue's sysfs lock during switching elevator cecf5d87ff20 ("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 cecf5d87ff20 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: cecf5d87ff20 ("block: split .sysfs_lock into two locks") Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Greg KH Cc: Mike Snitzer Reviewed-by: Bart Van Assche Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'block/blk-sysfs.c') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b82736c781c5..962fc0c44381 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -989,13 +989,11 @@ 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->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); @@ -1005,7 +1003,6 @@ 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); @@ -1062,12 +1059,10 @@ void blk_unregister_queue(struct gendisk *disk) kobject_del(&q->kobj); 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->elevator) elv_unregister_queue(q); + mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); kobject_put(&disk_to_dev(disk)->kobj); -- cgit v1.2.3