[tip:sched/core] sched: Fix cgroup movement of waking process

[tip-bot for Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>]

Commit-ID:  62af3783e4fd8ba9e28416e8e91cb3bdd9fb133e
Gitweb:     http://git.kernel.org/tip/62af3783e4fd8ba9e28416e8e91cb3bdd9fb133e
Author:     Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
AuthorDate: Thu, 15 Dec 2011 14:37:41 +0900
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Wed, 21 Dec 2011 10:34:52 +0100

sched: Fix cgroup movement of waking process

There is a small race between try_to_wake_up() and sched_move_task(),
which is trying to move the process being woken up.

    try_to_wake_up() on CPU0       sched_move_task() on CPU1
--------------------------------+---------------------------------
  raw_spin_lock_irqsave(p->pi_lock)
  task_waking_fair()
    ->p.se.vruntime -= cfs_rq->min_vruntime
  ttwu_queue()
    ->send reschedule IPI to CPU1
  raw_spin_unlock_irqsave(p->pi_lock)
                                   task_rq_lock()
                                     -> tring to aquire both p->pi_lock and
                                        rq->lock with IRQ disabled
                                   task_move_group_fair()
                                     -> p.se.vruntime
                                          -= (old)cfs_rq->min_vruntime
                                          += (new)cfs_rq->min_vruntime
                                   task_rq_unlock()

                                   (via IPI)
                                   sched_ttwu_pending()
                                     raw_spin_lock(rq->lock)
                                     ttwu_do_activate()
                                       ...
                                       enqueue_entity()
                                         child.se->vruntime += cfs_rq->min_vruntime
                                     raw_spin_unlock(rq->lock)

As a result, vruntime of the process 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_waking_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/20111215143741.df82dd50.nishimura@mxp.nes.nec.co.jp
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched/fair.c |    4 +++-
 1 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2d1ac6e..bdf1883 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5344,11 +5344,13 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
 	 *
 	 * - Moving a forked child which is waiting for being woken up by
 	 *   wake_up_new_task().
+	 * - Moving a task which has been woken up by try_to_wake_up() and
+	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 *
 	 * 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)
+	if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
 		on_rq = 1;
 
 	if (!on_rq)