sched, cgroup: Fixup broken cgroup movement

Dima noticed that we fail to correct the ->vruntime of sleeping tasks
when we move them between cgroups.

Reported-by: Dima Zavin <dima@android.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1287150604.29097.1513.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 24 insertions, 11 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2cca9a92f5e5..be312c129787 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1073,7 +1073,7 @@ struct sched_class {
 					 struct task_struct *task);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*moved_group) (struct task_struct *p, int on_rq);
+	void (*task_move_group) (struct task_struct *p, int on_rq);
 #endif
 };
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 5998222f901c..3fe253e6a6e9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8498,12 +8498,12 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
-	set_task_rq(tsk, task_cpu(tsk));
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	if (tsk->sched_class->moved_group)
-		tsk->sched_class->moved_group(tsk, on_rq);
+	if (tsk->sched_class->task_move_group)
+		tsk->sched_class->task_move_group(tsk, on_rq);
+	else
 #endif
+		set_task_rq(tsk, task_cpu(tsk));
 
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 74cccfae87a8..3acc2a487c18 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3866,13 +3866,26 @@ static void set_curr_task_fair(struct rq *rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void moved_group_fair(struct task_struct *p, int on_rq)
+static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
-	struct cfs_rq *cfs_rq = task_cfs_rq(p);
-
-	update_curr(cfs_rq);
+	/*
+	 * If the task was not on the rq at the time of this cgroup movement
+	 * it must have been asleep, sleeping tasks keep their ->vruntime
+	 * absolute on their old rq until wakeup (needed for the fair sleeper
+	 * bonus in place_entity()).
+	 *
+	 * If it was on the rq, we've just 'preempted' it, which does convert
+	 * ->vruntime to a relative base.
+	 *
+	 * Make sure both cases convert their relative position when migrating
+	 * to another cgroup's rq. This does somewhat interfere with the
+	 * fair sleeper stuff for the first placement, but who cares.
+	 */
+	if (!on_rq)
+		p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+	set_task_rq(p, task_cpu(p));
 	if (!on_rq)
-		place_entity(cfs_rq, &p->se, 1);
+		p->se.vruntime += cfs_rq_of(&p->se)->min_vruntime;
 }
 #endif
 
@@ -3924,7 +3937,7 @@ static const struct sched_class fair_sched_class = {
 	.get_rr_interval	= get_rr_interval_fair,
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	.moved_group		= moved_group_fair,
+	.task_move_group	= task_move_group_fair,
 #endif
 };