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>