Btrfs: Check kthread_should_stop() before schedule() in worker_loop

In worker_loop(), the func should check whether it has been requested to stop
before it decides to schedule out.

Otherwise if the stop request(also the last wake_up()) sent by
btrfs_stop_workers() happens when worker_loop() running after the "while"
judgement and before schedule(), woker_loop() will schedule away and never be
woken up, which will also cause btrfs_stop_workers() wait forever.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index e1e49715459e..4229450b7596 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -171,7 +171,8 @@ static int worker_loop(void *arg)
                 } else {
                         set_current_state(TASK_INTERRUPTIBLE);
                         spin_unlock_irq(&worker->lock);
-                        schedule();
+                        if (!kthread_should_stop())
+                                schedule();
                         __set_current_state(TASK_RUNNING);
                 }
         } while (!kthread_should_stop());