HWPOISON: Allow schedule_on_each_cpu() from keventd

Right now when calling schedule_on_each_cpu() from keventd there
is a deadlock because it tries to schedule a work item on the current CPU
too. This happens via lru_add_drain_all() in hwpoison.

Just call the function for the current CPU in this case. This is actually
faster too.

Debugging with Fengguang Wu & Max Asbock
Signed-off-by: NAndi Kleen <ak@linux.intel.com>

kernel/workqueue.c

@@ -667,21 +667,38 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
 int schedule_on_each_cpu(work_func_t func)
 {
 	int cpu;
+	int orig = -1;
 	struct work_struct *works;
 
 	works = alloc_percpu(struct work_struct);
 	if (!works)
 		return -ENOMEM;
 
+	/*
+	 * when running in keventd don't schedule a work item on itself.
+	 * Can just call directly because the work queue is already bound.
+	 * This also is faster.
+	 * Make this a generic parameter for other workqueues?
+	 */
+	if (current_is_keventd()) {
+		orig = raw_smp_processor_id();
+		INIT_WORK(per_cpu_ptr(works, orig), func);
+		func(per_cpu_ptr(works, orig));
+	}
+
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
+		if (cpu == orig)
+			continue;
 		INIT_WORK(work, func);
 		schedule_work_on(cpu, work);
 	}
-	for_each_online_cpu(cpu)
-		flush_work(per_cpu_ptr(works, cpu));
+	for_each_online_cpu(cpu) {
+		if (cpu != orig)
+			flush_work(per_cpu_ptr(works, cpu));
+	}
 	put_online_cpus();
 	free_percpu(works);
 	return 0;