sched: Update the clock of runqueue select_task_rq() selected

In try_to_wake_up(), we update the runqueue clock, but
select_task_rq() may select a different runqueue than the one we
updated, leaving the new runqueue's clock stale for a bit.

This patch cures occasional huge latencies reported by latencytop
when coming out of idle on a mostly idle NO_HZ box.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1255070103.7639.30.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 76c0e96..e3f8f4f 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2311,7 +2311,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
        int cpu, orig_cpu, this_cpu, success = 0;
        unsigned long flags;
-       struct rq *rq;
+       struct rq *rq, *orig_rq;
 
        if (!sched_feat(SYNC_WAKEUPS))
                wake_flags &= ~WF_SYNC;
@@ -2319,7 +2319,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
        this_cpu = get_cpu();
 
        smp_wmb();
-       rq = task_rq_lock(p, &flags);
+       rq = orig_rq = task_rq_lock(p, &flags);
        update_rq_clock(rq);
        if (!(p->state & state))
                goto out;
@@ -2350,6 +2350,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
                set_task_cpu(p, cpu);
 
        rq = task_rq_lock(p, &flags);
+
+       if (rq != orig_rq)
+               update_rq_clock(rq);
+
        WARN_ON(p->state != TASK_WAKING);
        cpu = task_cpu(p);