sched: use the old min_vruntime when normalizing on dequeue

After pulling the thread off the run-queue during a cgroup change,
the cfs_rq.min_vruntime gets recalculated. The dequeued thread's vruntime
then gets normalized to this new value. This can then lead to the thread
getting an unfair boost in the new group if the vruntime of the next
task in the old run-queue was way further ahead.

Cc: Arve Hjønnevåg <arve@android.com>
Signed-off-by: Dima Zavin <dima@android.com>

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6ded59f453c0787d7f5ef7ac00bb9a65cf6d29a0..1bb8790131732ccd10af15b0f25f2e9fb91b34d3 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -802,6 +802,8 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+       u64 min_vruntime;
+
        /*
         * Update run-time statistics of the 'current'.
         */
@@ -826,6 +828,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
        if (se != cfs_rq->curr)
                __dequeue_entity(cfs_rq, se);
        account_entity_dequeue(cfs_rq, se);
+
+       min_vruntime = cfs_rq->min_vruntime;
        update_min_vruntime(cfs_rq);
 
        /*
@@ -834,7 +838,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
         * movement in our normalized position.
         */
        if (!(flags & DEQUEUE_SLEEP))
-               se->vruntime -= cfs_rq->min_vruntime;
+               se->vruntime -= min_vruntime;
 }
 
 /*