sched, cgroup: Fixup broken cgroup movement

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@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>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1ca5d041fccb956bf3379e0e6b8b3d180322ad49..4c9c4269d106c0942f41f7714ab5e03827da8d6e 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1113,7 +1113,7 @@ 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 c8272e7b40c80ce2e2a9ac9f6e0cf8b71ca743ee..d8a2155689d36a15f699168b67565b9ff2d027a0 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -10224,12 +10224,12 @@ 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 c07663eee1566db3204de312f538f35dceddffde..4e0aca002bb751fb9ecf8e28094e4d3da6aec33b 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2068,13 +2068,26 @@ 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
 
@@ -2128,7 +2141,7 @@ 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
 };