workqueue: change value of lcpu in __queue_delayed_work_on()

We assign cpu id into work struct's data field in __queue_delayed_work_on().
In current implementation, when work is come in first time,
current running cpu id is assigned.
If we do __queue_delayed_work_on() with CPU A on CPU B,
__queue_work() invoked in delayed_work_timer_fn() go into
the following sub-optimal path in case of WQ_NON_REENTRANT.

	gcwq = get_gcwq(cpu);
	if (wq->flags & WQ_NON_REENTRANT &&
		(last_gcwq = get_work_gcwq(work)) && last_gcwq != gcwq) {

Change lcpu to @cpu and rechange lcpu to local cpu if lcpu is WORK_CPU_UNBOUND.
It is sufficient to prevent to go into sub-optimal path.

tj: Slightly rephrased the comment.

Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 8 insertions, 2 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c29f2dc0f4fc..99ee9b939264 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1356,9 +1356,15 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
         if (!(wq->flags & WQ_UNBOUND)) {
                 struct global_cwq *gcwq = get_work_gcwq(work);
 
-                if (gcwq && gcwq->cpu != WORK_CPU_UNBOUND)
+                /*
+                 * If we cannot get the last gcwq from @work directly,
+                 * select the last CPU such that it avoids unnecessarily
+                 * triggering non-reentrancy check in __queue_work().
+                 */
+                lcpu = cpu;
+                if (gcwq)
                         lcpu = gcwq->cpu;
-                else
+                if (lcpu == WORK_CPU_UNBOUND)
                         lcpu = raw_smp_processor_id();
         } else {
                 lcpu = WORK_CPU_UNBOUND;