sched: Prevent buddy interactions with throttled entities

Buddies allow us to select "on-rq" entities without actually selecting them
from a cfs_rq's rb_tree.  As a result we must ensure that throttled entities
are not falsely nominated as buddies.  The fact that entities are dequeued
within throttle_entity is not sufficient for clearing buddy status as the
nomination may occur after throttling.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.886850167@google.comSigned-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched_fair.c

@@ -2348,6 +2348,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(se == pse))
 		return;
 
+	/*
+	 * This is possible from callers such as pull_task(), in which we
+	 * unconditionally check_prempt_curr() after an enqueue (which may have
+	 * lead to a throttle).  This both saves work and prevents false
+	 * next-buddy nomination below.
+	 */
+	if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
+		return;
+
 	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
 		set_next_buddy(pse);
 		next_buddy_marked = 1;
@@ -2356,6 +2365,12 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
 	 * wake up path.
+	 *
+	 * Note: this also catches the edge-case of curr being in a throttled
+	 * group (e.g. via set_curr_task), since update_curr() (in the
+	 * enqueue of curr) will have resulted in resched being set.  This
+	 * prevents us from potentially nominating it as a false LAST_BUDDY
+	 * below.
 	 */
 	if (test_tsk_need_resched(curr))
 		return;
@@ -2474,7 +2489,8 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
 {
 	struct sched_entity *se = &p->se;
 
-	if (!se->on_rq)
+	/* throttled hierarchies are not runnable */
+	if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se)))
 		return false;
 
 	/* Tell the scheduler that we'd really like pse to run next. */