From: Vincent Guittot <vincent.guittot@xxxxxxxxxx> commit fe61468b2cbc2b7ce5f8d3bf32ae5001d4c434e9 upstream. When a cfs rq is throttled, the latter and its child are removed from the leaf list but their nr_running is not changed which includes staying higher than 1. When a task is enqueued in this throttled branch, the cfs rqs must be added back in order to ensure correct ordering in the list but this can only happens if nr_running == 1. When cfs bandwidth is used, we call unconditionnaly list_add_leaf_cfs_rq() when enqueuing an entity to make sure that the complete branch will be added. Similarly unthrottle_cfs_rq() can stop adding cfs in the list when a parent is throttled. Iterate the remaining entity to ensure that the complete branch will be added in the list. Reported-by: Christian Borntraeger <borntraeger@xxxxxxxxxx> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx> Tested-by: Christian Borntraeger <borntraeger@xxxxxxxxxx> Tested-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx> Cc: stable@xxxxxxxxxxxxxxx Cc: stable@xxxxxxxxxxxxxxx #v5.1+ Link: https://lkml.kernel.org/r/20200306135257.25044-1-vincent.guittot@xxxxxxxxxx Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- kernel/sched/fair.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3927,6 +3927,7 @@ static inline void check_schedstat_requi #endif } +static inline bool cfs_bandwidth_used(void); /* * MIGRATION @@ -4005,10 +4006,16 @@ enqueue_entity(struct cfs_rq *cfs_rq, st __enqueue_entity(cfs_rq, se); se->on_rq = 1; - if (cfs_rq->nr_running == 1) { + /* + * When bandwidth control is enabled, cfs might have been removed + * because of a parent been throttled but cfs->nr_running > 1. Try to + * add it unconditionnally. + */ + if (cfs_rq->nr_running == 1 || cfs_bandwidth_used()) list_add_leaf_cfs_rq(cfs_rq); + + if (cfs_rq->nr_running == 1) check_enqueue_throttle(cfs_rq); - } } static void __clear_buddies_last(struct sched_entity *se) @@ -4589,11 +4596,22 @@ void unthrottle_cfs_rq(struct cfs_rq *cf break; } - assert_list_leaf_cfs_rq(rq); - if (!se) add_nr_running(rq, task_delta); + /* + * The cfs_rq_throttled() breaks in the above iteration can result in + * incomplete leaf list maintenance, resulting in triggering the + * assertion below. + */ + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + list_add_leaf_cfs_rq(cfs_rq); + } + + assert_list_leaf_cfs_rq(rq); + /* Determine whether we need to wake up potentially idle CPU: */ if (rq->curr == rq->idle && rq->cfs.nr_running) resched_curr(rq);
