In case that CONFIG_HOTPLUG_CPU and CONFIG_CFS_BANDWIDTH is turned on
and tasks in bandwidth controlled task group run on hotplug core,
the tasks are not controlled by cfs_b->quota when hotplug core is offline
and then online. The remaining tasks in task group consume all of
cfs_b->quota on other cores.
The cause of this problem is described as below:
1. When hotplug core is offline while tasks in task group run
on hotplug core, unregister_fair_sched_group() deletes
leaf_cfs_rq_list of tg->cfs_rq[cpu] from &rq_of(cfs_rq)->leaf_cfs_rq_list.
2. Then, when hotplug core is online, update_runtime_enabled()
registers cfs_b->quota on cfs_rq->runtime_enabled of all leaf cfs_rq
on runqueue. However, because this is before enqueue_entity() adds
&cfs_rq->leaf_cfs_rq_list on &rq_of(cfs_rq)->leaf_cfs_rq_list,
cfs->quota is not register on cfs_rq->runtime_enabled.
To resolve this problem, this patch makes update_runtime_enabled()
registers cfs_b->quota by using walk_tg_tree_from().
Signed-off-by: Jeehong Kim <jhez.kim@xxxxxxxxxxx>
---
V2: update_runtime_enabled() walks the whole tg tree,
instead of register quota on every enqueue.
kernel/sched/fair.c | 32 +++++++++++++++++++++-----------
1 file changed, 21 insertions(+), 11 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6488815..63b376d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4373,17 +4373,27 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
hrtimer_cancel(&cfs_b->slack_timer);
}
-static void __maybe_unused update_runtime_enabled(struct rq *rq)
+static int __maybe_unused __update_runtime_enabled(struct task_group *tg, void *data)
{
- struct cfs_rq *cfs_rq;
+ struct rq *rq = data;
+ struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+ struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
- for_each_leaf_cfs_rq(rq, cfs_rq) {
- struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+ raw_spin_lock(&cfs_b->lock);
+ cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
+ raw_spin_unlock(&cfs_b->lock);
- raw_spin_lock(&cfs_b->lock);
- cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
- raw_spin_unlock(&cfs_b->lock);
- }
+ return 0;
+}
+
+static void __maybe_unused update_runtime_enabled(struct rq *rq)
+{
+ struct cfs_rq *cfs_rq = &rq->cfs;
+
+ /* register cfs_b->quota on the whole tg tree */
+ rcu_read_lock();
+ walk_tg_tree_from(cfs_rq->tg, __update_runtime_enabled, tg_nop, (void *)rq);
+ rcu_read_unlock();
}
--
--
To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
