[PATCH] speedup flush_workqueue for singlethread_workqueue

From: "Anil" <anil.s.keshavamurthy@intel.com>

In flush_workqueue() for a single_threaded_worqueue case the code flushes the
same cpu_workqueue_struct for each online_cpu.

Change things so that we only perform the flush once in this case.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

kernel/workqueue.c

@@ -218,6 +218,33 @@ static int worker_thread(void *__cwq)
 	return 0;
 }
 
+static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
+{
+	if (cwq->thread == current) {
+		/*
+		 * Probably keventd trying to flush its own queue. So simply run
+		 * it by hand rather than deadlocking.
+		 */
+		run_workqueue(cwq);
+	} else {
+		DEFINE_WAIT(wait);
+		long sequence_needed;
+
+		spin_lock_irq(&cwq->lock);
+		sequence_needed = cwq->insert_sequence;
+
+		while (sequence_needed - cwq->remove_sequence > 0) {
+			prepare_to_wait(&cwq->work_done, &wait,
+					TASK_UNINTERRUPTIBLE);
+			spin_unlock_irq(&cwq->lock);
+			schedule();
+			spin_lock_irq(&cwq->lock);
+		}
+		finish_wait(&cwq->work_done, &wait);
+		spin_unlock_irq(&cwq->lock);
+	}
+}
+
 /*
  * flush_workqueue - ensure that any scheduled work has run to completion.
  *
@@ -234,42 +261,19 @@ static int worker_thread(void *__cwq)
  */
 void fastcall flush_workqueue(struct workqueue_struct *wq)
 {
-	struct cpu_workqueue_struct *cwq;
-	int cpu;
-
 	might_sleep();
-
 	lock_cpu_hotplug();
-	for_each_online_cpu(cpu) {
-		DEFINE_WAIT(wait);
-		long sequence_needed;
 
-		if (is_single_threaded(wq))
-			cwq = wq->cpu_wq + 0; /* Always use cpu 0's area. */
-		else
-			cwq = wq->cpu_wq + cpu;
+	if (is_single_threaded(wq)) {
+		/* Always use cpu 0's area. */
+		flush_cpu_workqueue(wq->cpu_wq + 0);
+	} else {
+		int cpu;
 
-		if (cwq->thread == current) {
-			/*
-			 * Probably keventd trying to flush its own queue.
-			 * So simply run it by hand rather than deadlocking.
-			 */
-			run_workqueue(cwq);
-			continue;
+		for_each_online_cpu(cpu)
+			flush_cpu_workqueue(wq->cpu_wq + cpu);
 	}
-		spin_lock_irq(&cwq->lock);
-		sequence_needed = cwq->insert_sequence;
 
-		while (sequence_needed - cwq->remove_sequence > 0) {
-			prepare_to_wait(&cwq->work_done, &wait,
-					TASK_UNINTERRUPTIBLE);
-			spin_unlock_irq(&cwq->lock);
-			schedule();
-			spin_lock_irq(&cwq->lock);
-		}
-		finish_wait(&cwq->work_done, &wait);
-		spin_unlock_irq(&cwq->lock);
-	}
 	unlock_cpu_hotplug();
 }