workqueue: don't clear cwq->thread until it exits

Pointed out by Srivatsa Vaddagiri.

cleanup_workqueue_thread() sets cwq->thread = NULL and does kthread_stop().
This breaks the "if (cwq->thread == current)" logic in flush_cpu_workqueue()
and leads to deadlock.

Kill the thead first, then clear cwq->thread. workqueue_mutex protects us
from create_workqueue_thread() so we don't need cwq->lock.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>
Cc: Gautham shenoy <ego@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1d1933c..398c34f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -625,17 +625,12 @@
 
 static void cleanup_workqueue_thread(struct workqueue_struct *wq, int cpu)
 {
-	struct cpu_workqueue_struct *cwq;
-	unsigned long flags;
-	struct task_struct *p;
+	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
 
-	cwq = per_cpu_ptr(wq->cpu_wq, cpu);
-	spin_lock_irqsave(&cwq->lock, flags);
-	p = cwq->thread;
-	cwq->thread = NULL;
-	spin_unlock_irqrestore(&cwq->lock, flags);
-	if (p)
-		kthread_stop(p);
+	if (cwq->thread) {
+		kthread_stop(cwq->thread);
+		cwq->thread = NULL;
+	}
 }
 
 /**