Sched: fix skip_clock_update optimization

commit f26f9aff6aaf67e9a430d16c266f91b13a5bff64 upstream.

idle_balance() drops/retakes rq->lock, leaving the previous task
vulnerable to set_tsk_need_resched().  Clear it after we return
from balancing instead, and in setup_thread_stack() as well, so
no successfully descheduled or never scheduled task has it set.

Need resched confused the skip_clock_update logic, which assumes
that the next call to update_rq_clock() will come nearly immediately
after being set.  Make the optimization robust against the waking
a sleeper before it sucessfully deschedules case by checking that
the current task has not been dequeued before setting the flag,
since it is that useless clock update we're trying to save, and
clear unconditionally in schedule() proper instead of conditionally
in put_prev_task().

Signed-off-by: Mike Galbraith <efault@gmx.de>
Reported-by: Bjoern B. Brandenburg <bbb.lst@gmail.com>
Tested-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1291802742.1417.9.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/kernel/fork.c b/kernel/fork.c
index c445f8cc408d777dd7a94aec3fa78c07e1d98b98..a576b983652e37445348ebfe4f316f8bda56f403 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -272,6 +272,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
        setup_thread_stack(tsk, orig);
        clear_user_return_notifier(tsk);
+       clear_tsk_need_resched(tsk);
        stackend = end_of_stack(tsk);
        *stackend = STACK_END_MAGIC;    /* for overflow detection */
 

diff --git a/kernel/sched.c b/kernel/sched.c
index ac41c82174651b3ae1f933eab8353aa1a9c05200..92c5b60e357e4e91accc9629d2d40e096f6f2761 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -566,7 +566,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
         * A queue event has occurred, and we're going to schedule.  In
         * this case, we can save a useless back to back clock update.
         */
-       if (test_tsk_need_resched(p))
+       if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
                rq->skip_clock_update = 1;
 }
 
@@ -3821,7 +3821,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
        if (prev->se.on_rq)
                update_rq_clock(rq);
-       rq->skip_clock_update = 0;
        prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3883,7 +3882,6 @@ need_resched_nonpreemptible:
                hrtick_clear(rq);
 
        raw_spin_lock_irq(&rq->lock);
-       clear_tsk_need_resched(prev);
 
        switch_count = &prev->nivcsw;
        if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3915,6 +3913,8 @@ need_resched_nonpreemptible:
 
        put_prev_task(rq, prev);
        next = pick_next_task(rq);
+       clear_tsk_need_resched(prev);
+       rq->skip_clock_update = 0;
 
        if (likely(prev != next)) {
                sched_info_switch(prev, next);