[lkml]   [2009]   [Nov]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[PATCH 02/21] sched, kvm: fix race condition involving sched_in_preempt_notifers
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.

Signed-off-by: Tejun Heo <>
Cc: Avi Kivity <>
kernel/sched.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 3c11ae0..de8a765 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2751,9 +2751,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
prev_state = prev->state;
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)
if (unlikely(prev_state == TASK_DEAD)) {

 \ /
  Last update: 2009-11-16 18:23    [from the cache]
©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site