sched: Fix rq->nr_uninterruptible update race

KOSAKI Motohiro noticed the following race:

 > CPU0                    CPU1
 > --------------------------------------------------------
 > deactivate_task()
 >                         task->state = TASK_UNINTERRUPTIBLE;
 > activate_task()
 >    rq->nr_uninterruptible--;
 >
 >                         schedule()
 >                           deactivate_task()
 >                             rq->nr_uninterruptible++;
 >

Kosaki-San's scenario is possible when CPU0 runs
__sched_setscheduler() against CPU1's current @task.

__sched_setscheduler() does a dequeue/enqueue in order to move
the task to its new queue (position) to reflect the newly provided
scheduling parameters. However it should be completely invariant to
nr_uninterruptible accounting, sched_setscheduler() doesn't affect
readyness to run, merely policy on when to run.

So convert the inappropriate activate/deactivate_task usage to
enqueue/dequeue_task, which avoids the nr_uninterruptible accounting.

Also convert the two other sites: __migrate_task() and
normalize_task() that still use activate/deactivate_task. These sites
aren't really a problem since __migrate_task() will only be called on
non-running task (and therefore are immume to the described problem)
and normalize_task() isn't ever used on regular systems.

Also remove the comments from activate/deactivate_task since they're
misleading at best.

Reported-by: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1327486224.2614.45.camel@laptop
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df00cb09263e093b2c0a9c73a20e16b6602a70ea..e067df1fd01a3cbafad173dbb240a6ba2701146f 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -723,9 +723,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
        p->sched_class->dequeue_task(rq, p, flags);
 }
 
-/*
- * activate_task - move a task to the runqueue.
- */
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
        if (task_contributes_to_load(p))
@@ -734,9 +731,6 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
        enqueue_task(rq, p, flags);
 }
 
-/*
- * deactivate_task - remove a task from the runqueue.
- */
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
        if (task_contributes_to_load(p))
@@ -4134,7 +4128,7 @@ recheck:
        on_rq = p->on_rq;
        running = task_current(rq, p);
        if (on_rq)
-               deactivate_task(rq, p, 0);
+               dequeue_task(rq, p, 0);
        if (running)
                p->sched_class->put_prev_task(rq, p);
 
@@ -4147,7 +4141,7 @@ recheck:
        if (running)
                p->sched_class->set_curr_task(rq);
        if (on_rq)
-               activate_task(rq, p, 0);
+               enqueue_task(rq, p, 0);
 
        check_class_changed(rq, p, prev_class, oldprio);
        task_rq_unlock(rq, p, &flags);
@@ -4998,9 +4992,9 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         * placed properly.
         */
        if (p->on_rq) {
-               deactivate_task(rq_src, p, 0);
+               dequeue_task(rq_src, p, 0);
                set_task_cpu(p, dest_cpu);
-               activate_task(rq_dest, p, 0);
+               enqueue_task(rq_dest, p, 0);
                check_preempt_curr(rq_dest, p, 0);
        }
 done:
@@ -7032,10 +7026,10 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 
        on_rq = p->on_rq;
        if (on_rq)
-               deactivate_task(rq, p, 0);
+               dequeue_task(rq, p, 0);
        __setscheduler(rq, p, SCHED_NORMAL, 0);
        if (on_rq) {
-               activate_task(rq, p, 0);
+               enqueue_task(rq, p, 0);
                resched_task(rq->curr);
        }