sched: Fix cgroup movement of newly created process

There is a small race between do_fork() and sched_move_task(), which is
trying to move the child.

            do_fork()                 sched_move_task()
--------------------------------+---------------------------------
  copy_process()
    sched_fork()
      task_fork_fair()
        -> vruntime of the child is initialized
           based on that of the parent.
  -> we can see the child in "tasks" file now.
                                    task_rq_lock()
                                    task_move_group_fair()
                                      -> child.se.vruntime
                                           -= (old)cfs_rq->min_vruntime
                                           += (new)cfs_rq->min_vruntime
                                    task_rq_unlock()
  wake_up_new_task()
    ...
    enqueue_entity()
      child.se.vruntime += cfs_rq->min_vruntime

As a result, vruntime of the child becomes far bigger than min_vruntime,
if (new)cfs_rq->min_vruntime >> (old)cfs_rq->min_vruntime.

This patch fixes this problem by just ignoring such process in
task_move_group_fair(), because the vruntime has already been normalized in
task_fork_fair().

Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20111215143607.2ee12c5d.nishimura@mxp.nes.nec.co.jp
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 525d69e5fb789ab95e17a31c2a69375f5e7f99df..2d1ac6e2386d84cafcd099de5d2902fd22a56d77 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5338,6 +5338,19 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
         * to another cgroup's rq. This does somewhat interfere with the
         * fair sleeper stuff for the first placement, but who cares.
         */
+       /*
+        * When !on_rq, vruntime of the task has usually NOT been normalized.
+        * But there are some cases where it has already been normalized:
+        *
+        * - Moving a forked child which is waiting for being woken up by
+        *   wake_up_new_task().
+        *
+        * To prevent boost or penalty in the new cfs_rq caused by delta
+        * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
+        */
+       if (!on_rq && !p->se.sum_exec_runtime)
+               on_rq = 1;
+
        if (!on_rq)
                p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
        set_task_rq(p, task_cpu(p));