sched: move_task_off_dead_cpu(): Take rq->lock around select_fallback_rq()

move_task_off_dead_cpu()->select_fallback_rq() reads/updates ->cpus_allowed
lockless. We can race with set_cpus_allowed() running in parallel.

Change it to take rq->lock around select_fallback_rq(). Note that it is not
trivial to move this spin_lock() into select_fallback_rq(), we must recheck
the task was not migrated after we take the lock and other callers do not
need this lock.

To avoid the races with other callers of select_fallback_rq() which rely on
TASK_WAKING, we also check p->state != TASK_WAKING and do nothing otherwise.
The owner of TASK_WAKING must update ->cpus_allowed and choose the correct
CPU anyway, and the subsequent __migrate_task() is just meaningless because
p->se.on_rq must be false.

Alternatively, we could change select_task_rq() to take rq->lock right
after it calls sched_class->select_task_rq(), but this looks a bit ugly.

Also, change it to not assume irqs are disabled and absorb __migrate_task_irq().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100315091010.GA9131@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index c0b3ebc..27774b5 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5448,29 +5448,29 @@ static int migration_thread(void *data)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

-
-static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
-{
-       int ret;
-
-       local_irq_disable();
-       ret = __migrate_task(p, src_cpu, dest_cpu);
-       local_irq_enable();
-       return ret;
-}
-

 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
 static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
 static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {

-       int dest_cpu;
-
+       struct rq *rq = cpu_rq(dead_cpu);
+       int needs_cpu, uninitialized_var(dest_cpu);
+       unsigned long flags;

 again:
 again:

-       dest_cpu = select_fallback_rq(dead_cpu, p);
+       local_irq_save(flags);
+
+       raw_spin_lock(&rq->lock);
+       needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
+       if (needs_cpu)
+               dest_cpu = select_fallback_rq(dead_cpu, p);
+       raw_spin_unlock(&rq->lock);

 
        /* It can have affinity changed while we were choosing. */
 
        /* It can have affinity changed while we were choosing. */

-       if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
+       if (needs_cpu)
+               needs_cpu = !__migrate_task(p, dead_cpu, dest_cpu);
+       local_irq_restore(flags);
+
+       if (unlikely(needs_cpu))

                goto again;
 }
 
                goto again;
 }