[PATCH 1/2] sched: normalize sleeper's vruntime during group change

[Dima Zavin <dima@android.com>]

If you switch the cgroup of a sleeping thread, its vruntime does
not get adjusted correctly for the difference between the
min_vruntime values of the two groups.

The problem becomes most apparent when one has cgroups whose
cpu shares differ greatly, say group A.shares=1024 and group B.shares=52.
After some time, the vruntime of the group with the larger share (A)
will be way ahead of the group with the small share (B). Currently,
when a sleeping task is moved from group A to group B, it will retain its
larger vruntime value and thus will be way ahead of all the other tasks
in its new group. This will prevent this task from executing for an
extended period of time.

This patch adds a new callback, prep_move_task, to struct sched_class
to give sched_fair the opportunity to adjust the task's vruntime
just before setting its new group. This allows us to properly normalize
a sleeping task's vruntime when moving it between different cgroups.

Cc: Arve Hjønnevåg <arve@android.com>
Signed-off-by: Dima Zavin <dima@android.com>
---
 include/linux/sched.h |    1 +
 kernel/sched.c        |    5 +++++
 kernel/sched_fair.c   |   14 +++++++++++++-
 3 files changed, 19 insertions(+), 1 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e2a6db..ba3494e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1073,6 +1073,7 @@ struct sched_class {
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*moved_group) (struct task_struct *p, int on_rq);
+	void (*prep_move_group) (struct task_struct *p, int on_rq);
 #endif
 };
 
diff --git a/kernel/sched.c b/kernel/sched.c
index dc85ceb..fe4bb20 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8297,6 +8297,11 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (tsk->sched_class->prep_move_group)
+		tsk->sched_class->prep_move_group(tsk, on_rq);
+#endif
+
 	set_task_rq(tsk, task_cpu(tsk));
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index db3f674..6ded59f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3827,10 +3827,21 @@ static void set_curr_task_fair(struct rq *rq)
 static void moved_group_fair(struct task_struct *p, int on_rq)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	struct sched_entity *se = &p->se;
 
 	update_curr(cfs_rq);
 	if (!on_rq)
-		place_entity(cfs_rq, &p->se, 1);
+		se->vruntime += cfs_rq->min_vruntime;
+}
+
+static void prep_move_group_fair(struct task_struct *p, int on_rq)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	struct sched_entity *se = &p->se;
+
+	/* normalize the runtime of a sleeping task before moving it */
+	if (!on_rq)
+		se->vruntime -= cfs_rq->min_vruntime;
 }
 #endif
 
@@ -3883,6 +3894,7 @@ static const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	.moved_group		= moved_group_fair,
+	.prep_move_group	= prep_move_group_fair,
 #endif
 };
 
-- 
1.6.6