[PATCH] [107/275] sched, cgroup: Fixup broken cgroup movement

[Andi Kleen]

2.6.35-longterm review patch.  If anyone has any objections, please let me know.

------------------
Commit: b2b5ce022acf5e9f52f7b78c5579994fdde191d4 upstream

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

Reported-by: Dima Zavin <dima@xxxxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Tested-by: Mike Galbraith <efault@xxxxxx>
LKML-Reference: <1287150604.29097.1513.camel@twins>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Mike Galbraith <efault@xxxxxx>
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
 include/linux/sched.h |    2 +-
 kernel/sched.c        |    8 ++++----
 kernel/sched_fair.c   |   25 +++++++++++++++++++------
 3 files changed, 24 insertions(+), 11 deletions(-)

Index: linux-2.6.35.y/include/linux/sched.h
===================================================================
--- linux-2.6.35.y.orig/include/linux/sched.h	2011-03-29 23:03:00.269293279 -0700
+++ linux-2.6.35.y/include/linux/sched.h	2011-03-29 23:54:57.628527856 -0700
@@ -1076,7 +1076,7 @@
 					 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
 };
 
Index: linux-2.6.35.y/kernel/sched.c
===================================================================
--- linux-2.6.35.y.orig/kernel/sched.c	2011-03-29 23:03:00.391290158 -0700
+++ linux-2.6.35.y/kernel/sched.c	2011-03-29 23:54:57.628527856 -0700
@@ -8332,12 +8332,12 @@
 	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);
Index: linux-2.6.35.y/kernel/sched_fair.c
===================================================================
--- linux-2.6.35.y.orig/kernel/sched_fair.c	2011-03-29 23:03:00.347291285 -0700
+++ linux-2.6.35.y/kernel/sched_fair.c	2011-03-29 23:54:57.628527856 -0700
@@ -3657,13 +3657,26 @@
 }
 
 #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
 
@@ -3715,7 +3728,7 @@
 	.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
 };
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/