workqueue: UNBOUND -> REBIND morphing in rebind_workers() should be atomic
commit 96e65306b81351b656835c15931d1d237b252f27 upstream.
The compiler may compile the following code into TWO write/modify
instructions.
worker->flags &= ~WORKER_UNBOUND;
worker->flags |= WORKER_REBIND;
so the other CPU may temporarily see worker->flags which doesn't have
either WORKER_UNBOUND or WORKER_REBIND set and perform local wakeup
prematurely.
Fix it by using single explicit assignment via ACCESS_ONCE().
Because idle workers have another WORKER_NOT_RUNNING flag, this bug
doesn't exist for them; however, update it to use the same pattern for
consistency.
tj: Applied the change to idle workers too and updated comments and
patch description a bit.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f483dd0..7584322 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3433,14 +3433,17 @@
for_each_busy_worker(worker, i, pos, gcwq) {
struct work_struct *rebind_work = &worker->rebind_work;
+ unsigned long worker_flags = worker->flags;
/*
* Rebind_work may race with future cpu hotplug
* operations. Use a separate flag to mark that
- * rebinding is scheduled.
+ * rebinding is scheduled. The morphing should
+ * be atomic.
*/
- worker->flags |= WORKER_REBIND;
- worker->flags &= ~WORKER_ROGUE;
+ worker_flags |= WORKER_REBIND;
+ worker_flags &= ~WORKER_ROGUE;
+ ACCESS_ONCE(worker->flags) = worker_flags;
/* queue rebind_work, wq doesn't matter, use the default one */
if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,