workqueues: implement flush_work()

Most of users of flush_workqueue() can be changed to use cancel_work_sync(),
but sometimes we really need to wait for the completion and cancelling is not
an option. schedule_on_each_cpu() is good example.

Add the new helper, flush_work(work), which waits for the completion of the
specific work_struct. More precisely, it "flushes" the result of of the last
queue_work() which is visible to the caller.

For example, this code

	queue_work(wq, work);
	/* WINDOW */
	queue_work(wq, work);

	flush_work(work);

doesn't necessary work "as expected". What can happen in the WINDOW above is

	- wq starts the execution of work->func()

	- the caller migrates to another CPU

now, after the 2nd queue_work() this work is active on the previous CPU, and
at the same time it is queued on another. In this case flush_work(work) may
return before the first work->func() completes.

It is trivial to add another helper

	int flush_work_sync(struct work_struct *work)
	{
		return flush_work(work) || wait_on_work(work);
	}

which works "more correctly", but it has to iterate over all CPUs and thus
it much slower than flush_work().
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Acked-by: Jarek Poplawski <jarkao2@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/workqueue.h

@@ -201,6 +201,8 @@ extern int keventd_up(void);
 extern void init_workqueues(void);
 int execute_in_process_context(work_func_t fn, struct execute_work *);
 
+extern int flush_work(struct work_struct *work);
+
 extern int cancel_work_sync(struct work_struct *work);
 
 /*

kernel/workqueue.c

@@ -423,6 +423,52 @@ void flush_workqueue(struct workqueue_struct *wq)
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
+/**
+ * flush_work - block until a work_struct's callback has terminated
+ * @work: the work which is to be flushed
+ *
+ * It is expected that, prior to calling flush_work(), the caller has
+ * arranged for the work to not be requeued, otherwise it doesn't make
+ * sense to use this function.
+ */
+int flush_work(struct work_struct *work)
+{
+	struct cpu_workqueue_struct *cwq;
+	struct list_head *prev;
+	struct wq_barrier barr;
+
+	might_sleep();
+	cwq = get_wq_data(work);
+	if (!cwq)
+		return 0;
+
+	prev = NULL;
+	spin_lock_irq(&cwq->lock);
+	if (!list_empty(&work->entry)) {
+		/*
+		 * See the comment near try_to_grab_pending()->smp_rmb().
+		 * If it was re-queued under us we are not going to wait.
+		 */
+		smp_rmb();
+		if (unlikely(cwq != get_wq_data(work)))
+			goto out;
+		prev = &work->entry;
+	} else {
+		if (cwq->current_work != work)
+			goto out;
+		prev = &cwq->worklist;
+	}
+	insert_wq_barrier(cwq, &barr, prev->next);
+out:
+	spin_unlock_irq(&cwq->lock);
+	if (!prev)
+		return 0;
+
+	wait_for_completion(&barr.done);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(flush_work);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.