[PATCH] sched: resched proper CPU on yield_to

[Venkatesh Pallipadi]

yield_to_task_fair() has code to resched the CPU of yielding task when the
intention is to resched the CPU of the task that is being yielded to.

Change here fixes the problem and also makes the resched conditional on
rq != p_rq.

I don't have a setup to test this code path. So, this is only compile tested
right now.

Signed-off-by: Venkatesh Pallipadi <venki@xxxxxxxxxx>
---
 kernel/sched.c      |    9 ++++++++-
 kernel/sched_fair.c |    4 ----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 5fb5aa2..afdbd09 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5495,8 +5495,15 @@ again:
 		goto out;
 
 	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
-	if (yielded)
+	if (yielded) {
 		schedstat_inc(rq, yld_count);
+		/*
+		 * Make p's CPU reschedule; pick_next_entity takes care of
+		 * fairness.
+		 */
+		if (preempt && rq != p_rq)
+			resched_task(p_rq->curr);
+	}
 
 out:
 	double_rq_unlock(rq, p_rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 36e8f02..1b1c780 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2001,10 +2001,6 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
 	/* Tell the scheduler that we'd really like pse to run next. */
 	set_next_buddy(se);
 
-	/* Make p's CPU reschedule; pick_next_entity takes care of fairness. */
-	if (preempt)
-		resched_task(rq->curr);
-
 	yield_task_fair(rq);
 
 	return true;
-- 
1.7.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/