sched/fair: Reorder cgroup creation code

A future patch needs rq->lock held _after_ we link the task_group into
the hierarchy. In order to avoid taking every rq->lock twice, reorder
things a little and create online_fair_sched_group() to be called
after we link the task_group.

All this code is still ran from css_alloc() so css_online() isn't in
fact used for this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 781788d..62d5e7d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8624,10 +8624,6 @@
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
-
-		raw_spin_lock_irq(&rq->lock);
-		post_init_entity_util_avg(se);
-		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
@@ -8638,6 +8634,22 @@
 	return 0;
 }
 
+void online_fair_sched_group(struct task_group *tg)
+{
+	struct sched_entity *se;
+	struct rq *rq;
+	int i;
+
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+		se = tg->se[i];
+
+		raw_spin_lock_irq(&rq->lock);
+		post_init_entity_util_avg(se);
+		raw_spin_unlock_irq(&rq->lock);
+	}
+}
+
 void unregister_fair_sched_group(struct task_group *tg)
 {
 	unsigned long flags;
@@ -8742,6 +8754,8 @@
 	return 1;
 }
 
+void online_fair_sched_group(struct task_group *tg) { }
+
 void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */