[PATCH 2.6.32-rc6] sched, kvm: fix race condition involving sched_in_preempt_notifers

[Tejun Heo <tj@kernel.org>]

In finish_task_switch(), fire_sched_in_preempt_notifiers() is called
after finish_lock_switch().  However, depending on architecture,
preemption can be enabled after finish_lock_switch() which breaks the
semantics of preempt notifiers.  Move it before finish_arch_switch().
This also makes in notifiers symmetric to out notifiers in terms of
locking - now both are called under rq lock.

NOT_SIGNED_OFF_YET
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
---
Avi, I think kvm should be fine with this but I haven't tested it.
Does this look okay to you?  If so, can you please route this through
kvm tree with my signoff?

Thanks.

 kernel/sched.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Index: work/kernel/sched.c
===================================================================
--- work.orig/kernel/sched.c
+++ work/kernel/sched.c
@@ -2751,9 +2751,9 @@ static void finish_task_switch(struct rq
 	prev_state = prev->state;
 	finish_arch_switch(prev);
 	perf_event_task_sched_in(current, cpu_of(rq));
+	fire_sched_in_preempt_notifiers(current);
 	finish_lock_switch(rq, prev);
 
-	fire_sched_in_preempt_notifiers(current);
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {