Merge branch 'for-3.9-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue fix from Tejun Heo:
 "Lai's patch to fix highly unlikely but still possible workqueue stall
  during CPU hotunplug."

* 'for-3.9-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: fix possible pool stall bug in wq_unbind_fn()

1 files changed, 25 insertions, 19 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 55fac5b..b48cd59 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3447,28 +3447,34 @@ static void wq_unbind_fn(struct work_struct *work)
 
 		spin_unlock_irq(&pool->lock);
 		mutex_unlock(&pool->assoc_mutex);
-	}
 
-	/*
-	 * Call schedule() so that we cross rq->lock and thus can guarantee
-	 * sched callbacks see the %WORKER_UNBOUND flag.  This is necessary
-	 * as scheduler callbacks may be invoked from other cpus.
-	 */
-	schedule();
+		/*
+		 * Call schedule() so that we cross rq->lock and thus can
+		 * guarantee sched callbacks see the %WORKER_UNBOUND flag.
+		 * This is necessary as scheduler callbacks may be invoked
+		 * from other cpus.
+		 */
+		schedule();
 
-	/*
-	 * Sched callbacks are disabled now.  Zap nr_running.  After this,
-	 * nr_running stays zero and need_more_worker() and keep_working()
-	 * are always true as long as the worklist is not empty.  Pools on
-	 * @cpu now behave as unbound (in terms of concurrency management)
-	 * pools which are served by workers tied to the CPU.
-	 *
-	 * On return from this function, the current worker would trigger
-	 * unbound chain execution of pending work items if other workers
-	 * didn't already.
-	 */
-	for_each_std_worker_pool(pool, cpu)
+		/*
+		 * Sched callbacks are disabled now.  Zap nr_running.
+		 * After this, nr_running stays zero and need_more_worker()
+		 * and keep_working() are always true as long as the
+		 * worklist is not empty.  This pool now behaves as an
+		 * unbound (in terms of concurrency management) pool which
+		 * are served by workers tied to the pool.
+		 */
 		atomic_set(&pool->nr_running, 0);
+
+		/*
+		 * With concurrency management just turned off, a busy
+		 * worker blocking could lead to lengthy stalls.  Kick off
+		 * unbound chain execution of currently pending work items.
+		 */
+		spin_lock_irq(&pool->lock);
+		wake_up_worker(pool);
+		spin_unlock_irq(&pool->lock);
+	}
 }
 
 /*