On 09/22, Peter Zijlstra wrote:

+static void wait_task_inactive_sched_in(struct preempt_notifier *n, int cpu)
+{
+	struct task_struct *p;
+	struct wait_task_inactive_blocked *blocked =
+		container_of(n, struct wait_task_inactive_blocked, notifier);
+
+	hlist_del(&n->link);
+
+	p = ACCESS_ONCE(blocked->waiter);
+	blocked->waiter = NULL;
+	wake_up_process(p);
+}
...
+static void
+wait_task_inactive_sched_out(struct preempt_notifier *n, struct task_struct *next)
+{
+	if (current->on_rq) /* we're not inactive yet */
+		return;
+
+	hlist_del(&n->link);
+	n->ops = &wait_task_inactive_ops_post;
+	hlist_add_head(&n->link, &next->preempt_notifiers);
+}

Tricky ;) Yes, the first ->sched_out() is not enough.

 unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
...
+	rq = task_rq_lock(p, &flags);
+	trace_sched_wait_task(p);
+	if (!p->on_rq) /* we're already blocked */
+		goto done;

This doesn't look right. schedule() clears ->on_rq a long before
__switch_to/etc.

And it seems that we check ->on_cpu above, this is not UP friendly.

-			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
-			continue;
-		}
+	hlist_add_head(&blocked.notifier.link, &p->preempt_notifiers);
+	task_rq_unlock(rq, p, &flags);

I thought about reimplementing wait_task_inactive() too, but afaics there
is a problem: why we can't race with p doing register_preempt_notifier() ?
I guess register_ needs rq->lock too.

Oleg.