kthread: initial support for delayed kthread work

We are going to use kthread_worker more widely and delayed works
will be pretty useful.

The implementation is inspired by workqueues.  It uses a timer to queue
the work after the requested delay.  If the delay is zero, the work is
queued immediately.

In compare with workqueues, each work is associated with a single worker
(kthread).  Therefore the implementation could be much easier.  In
particular, we use the worker->lock to synchronize all the operations with
the work.  We do not need any atomic operation with a flags variable.

In fact, we do not need any state variable at all.  Instead, we add a list
of delayed works into the worker.  Then the pending work is listed either
in the list of queued or delayed works.  And the existing check of pending
works is the same even for the delayed ones.

A work must not be assigned to another worker unless reinitialized.
Therefore the timer handler might expect that dwork->work->worker is valid
and it could simply take the lock.  We just add some sanity checks to help
with debugging a potential misuse.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Petr Mladek <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Josh Triplett <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Jiri Kosina <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/kthread.h

@@ -63,10 +63,12 @@ extern int tsk_fork_get_node(struct task_struct *tsk);
  */
 struct kthread_work;
 typedef void (*kthread_work_func_t)(struct kthread_work *work);
+void kthread_delayed_work_timer_fn(unsigned long __data);
 
 struct kthread_worker {
 	spinlock_t		lock;
 	struct list_head	work_list;
+	struct list_head	delayed_work_list;
 	struct task_struct	*task;
 	struct kthread_work	*current_work;
 };
@@ -77,22 +79,39 @@ struct kthread_work {
 	struct kthread_worker	*worker;
 };
 
+struct kthread_delayed_work {
+	struct kthread_work work;
+	struct timer_list timer;
+};
+
 #define KTHREAD_WORKER_INIT(worker)	{				\
 	.lock = __SPIN_LOCK_UNLOCKED((worker).lock),			\
 	.work_list = LIST_HEAD_INIT((worker).work_list),		\
+	.delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\
 	}
 
 #define KTHREAD_WORK_INIT(work, fn)	{				\
 	.node = LIST_HEAD_INIT((work).node),				\
 	.func = (fn),							\
 	}
 
+#define KTHREAD_DELAYED_WORK_INIT(dwork, fn) {				\
+	.work = KTHREAD_WORK_INIT((dwork).work, (fn)),			\
+	.timer = __TIMER_INITIALIZER(kthread_delayed_work_timer_fn,	\
+				     0, (unsigned long)&(dwork),	\
+				     TIMER_IRQSAFE),			\
+	}
+
 #define DEFINE_KTHREAD_WORKER(worker)					\
 	struct kthread_worker worker = KTHREAD_WORKER_INIT(worker)
 
 #define DEFINE_KTHREAD_WORK(work, fn)					\
 	struct kthread_work work = KTHREAD_WORK_INIT(work, fn)
 
+#define DEFINE_KTHREAD_DELAYED_WORK(dwork, fn)				\
+	struct kthread_delayed_work dwork =				\
+		KTHREAD_DELAYED_WORK_INIT(dwork, fn)
+
 /*
  * kthread_worker.lock needs its own lockdep class key when defined on
  * stack with lockdep enabled.  Use the following macros in such cases.
@@ -122,6 +141,15 @@ extern void __kthread_init_worker(struct kthread_worker *worker,
 		(work)->func = (fn);					\
 	} while (0)
 
+#define kthread_init_delayed_work(dwork, fn)				\
+	do {								\
+		kthread_init_work(&(dwork)->work, (fn));		\
+		__setup_timer(&(dwork)->timer,				\
+			      kthread_delayed_work_timer_fn,		\
+			      (unsigned long)(dwork),			\
+			      TIMER_IRQSAFE);				\
+	} while (0)
+
 int kthread_worker_fn(void *worker_ptr);
 
 __printf(1, 2)
@@ -133,6 +161,11 @@ kthread_create_worker_on_cpu(int cpu, const char namefmt[], ...);
 
 bool kthread_queue_work(struct kthread_worker *worker,
 			struct kthread_work *work);
+
+bool kthread_queue_delayed_work(struct kthread_worker *worker,
+				struct kthread_delayed_work *dwork,
+				unsigned long delay);
+
 void kthread_flush_work(struct kthread_work *work);
 void kthread_flush_worker(struct kthread_worker *worker);
 

kernel/kthread.c

@@ -563,6 +563,7 @@ void __kthread_init_worker(struct kthread_worker *worker,
 	spin_lock_init(&worker->lock);
 	lockdep_set_class_and_name(&worker->lock, key, name);
 	INIT_LIST_HEAD(&worker->work_list);
+	INIT_LIST_HEAD(&worker->delayed_work_list);
 	worker->task = NULL;
 }
 EXPORT_SYMBOL_GPL(__kthread_init_worker);
@@ -767,6 +768,107 @@ bool kthread_queue_work(struct kthread_worker *worker,
 }
 EXPORT_SYMBOL_GPL(kthread_queue_work);
 
+/**
+ * kthread_delayed_work_timer_fn - callback that queues the associated kthread
+ *	delayed work when the timer expires.
+ * @__data: pointer to the data associated with the timer
+ *
+ * The format of the function is defined by struct timer_list.
+ * It should have been called from irqsafe timer with irq already off.
+ */
+void kthread_delayed_work_timer_fn(unsigned long __data)
+{
+	struct kthread_delayed_work *dwork =
+		(struct kthread_delayed_work *)__data;
+	struct kthread_work *work = &dwork->work;
+	struct kthread_worker *worker = work->worker;
+
+	/*
+	 * This might happen when a pending work is reinitialized.
+	 * It means that it is used a wrong way.
+	 */
+	if (WARN_ON_ONCE(!worker))
+		return;
+
+	spin_lock(&worker->lock);
+	/* Work must not be used with >1 worker, see kthread_queue_work(). */
+	WARN_ON_ONCE(work->worker != worker);
+
+	/* Move the work from worker->delayed_work_list. */
+	WARN_ON_ONCE(list_empty(&work->node));
+	list_del_init(&work->node);
+	kthread_insert_work(worker, work, &worker->work_list);
+
+	spin_unlock(&worker->lock);
+}
+EXPORT_SYMBOL(kthread_delayed_work_timer_fn);
+
+void __kthread_queue_delayed_work(struct kthread_worker *worker,
+				  struct kthread_delayed_work *dwork,
+				  unsigned long delay)
+{
+	struct timer_list *timer = &dwork->timer;
+	struct kthread_work *work = &dwork->work;
+
+	WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn ||
+		     timer->data != (unsigned long)dwork);
+
+	/*
+	 * If @delay is 0, queue @dwork->work immediately.  This is for
+	 * both optimization and correctness.  The earliest @timer can
+	 * expire is on the closest next tick and delayed_work users depend
+	 * on that there's no such delay when @delay is 0.
+	 */
+	if (!delay) {
+		kthread_insert_work(worker, work, &worker->work_list);
+		return;
+	}
+
+	/* Be paranoid and try to detect possible races already now. */
+	kthread_insert_work_sanity_check(worker, work);
+
+	list_add(&work->node, &worker->delayed_work_list);
+	work->worker = worker;
+	timer_stats_timer_set_start_info(&dwork->timer);
+	timer->expires = jiffies + delay;
+	add_timer(timer);
+}
+
+/**
+ * kthread_queue_delayed_work - queue the associated kthread work
+ *	after a delay.
+ * @worker: target kthread_worker
+ * @dwork: kthread_delayed_work to queue
+ * @delay: number of jiffies to wait before queuing
+ *
+ * If the work has not been pending it starts a timer that will queue
+ * the work after the given @delay. If @delay is zero, it queues the
+ * work immediately.
+ *
+ * Return: %false if the @work has already been pending. It means that
+ * either the timer was running or the work was queued. It returns %true
+ * otherwise.
+ */
+bool kthread_queue_delayed_work(struct kthread_worker *worker,
+				struct kthread_delayed_work *dwork,
+				unsigned long delay)
+{
+	struct kthread_work *work = &dwork->work;
+	unsigned long flags;
+	bool ret = false;
+
+	spin_lock_irqsave(&worker->lock, flags);
+
+	if (list_empty(&work->node)) {
+		__kthread_queue_delayed_work(worker, dwork, delay);
+		ret = true;
+	}
+
+	spin_unlock_irqrestore(&worker->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kthread_queue_delayed_work);
+
 struct kthread_flush_work {
 	struct kthread_work	work;
 	struct completion	done;