diff -up linux-3.0.30-rt50/kernel/workqueue.c.bak linux-3.0.30-rt50/kernel/workqueue.c
--- linux-3.0.30-rt50/kernel/workqueue.c.bak	2013-06-08 19:09:06.801059232 +0800
+++ linux-3.0.30-rt50/kernel/workqueue.c	2013-06-08 19:09:15.680069626 +0800
@@ -1922,6 +1922,7 @@ static int worker_thread(void *__worker)
 
 	/* tell the scheduler that this is a workqueue worker */
 	worker->task->flags |= PF_WQ_WORKER;
+	smp_mb();
 woke_up:
 	spin_lock_irq(&gcwq->lock);
 
@@ -2736,6 +2737,7 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
 int schedule_on_each_cpu(work_func_t func)
 {
 	int cpu;
+	int orig = -1;
 	struct work_struct __percpu *works;
 
 	works = alloc_percpu(struct work_struct);
@@ -2744,13 +2746,20 @@ int schedule_on_each_cpu(work_func_t fun
 
 	get_online_cpus();
 
+	if(current->flags & PF_WQ_WORKER)
+		orig = raw_smp_processor_id();
+
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
 		INIT_WORK(work, func);
-		schedule_work_on(cpu, work);
+		if(cpu != orig)
+			schedule_work_on(cpu, work);
 	}
 
+	if (orig >= 0)
+		func(per_cpu_ptr(works,orig));
+
 	for_each_online_cpu(cpu)
 		flush_work(per_cpu_ptr(works, cpu));