From fdd514e16bb2531c0c61ae8a1f87740ce217f630 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 9 Jun 2011 20:43:59 +0200 Subject: block: make disk_block_events() properly wait for work cancellation disk_block_events() should guarantee that the event work is not in flight on return and once blocked it shouldn't issue further cancellations. Because there was no synchronization between the first blocker doing cancel_delayed_work_sync() and the following blockers, the following blockers could finish before cancellation was complete, which broke both guarantees - event work could be in flight and cancellation could happen after return. This bug triggered WARN_ON_ONCE() in disk_clear_events() reported in bug#34662. https://bugzilla.kernel.org/show_bug.cgi?id=34662 Fix it by adding an outer mutex which protects both block count manipulation and work cancellation. -v2: Use outer mutex instead of bit waitqueue per Linus. Signed-off-by: Tejun Heo Tested-by: Sitsofe Wheeler Reported-by: Sitsofe Wheeler Reported-by: Borislav Petkov Reported-by: Meelis Roos Reported-by: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Kay Sievers Signed-off-by: Jens Axboe --- block/genhd.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'block') diff --git a/block/genhd.c b/block/genhd.c index ab0731d8976d..3608289c8ecd 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1371,6 +1371,7 @@ struct disk_events { struct gendisk *disk; /* the associated disk */ spinlock_t lock; + struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ @@ -1438,12 +1439,20 @@ void disk_block_events(struct gendisk *disk) if (!ev) return; + /* + * Outer mutex ensures that the first blocker completes canceling + * the event work before further blockers are allowed to finish. + */ + mutex_lock(&ev->block_mutex); + spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); if (cancel) cancel_delayed_work_sync(&disk->ev->dwork); + + mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) @@ -1751,6 +1760,7 @@ static void disk_add_events(struct gendisk *disk) INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); + mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); -- cgit v1.2.3