Re: [PATCH 5/8] sched,cfs: use explicit cfs_rq of parent se helper

[Dietmar Eggemann]

On 6/12/19 9:32 PM, Rik van Riel wrote:
> Use an explicit "cfs_rq of parent sched_entity" helper in a few
> strategic places, where cfs_rq_of(se) may no longer point at the
> right runqueue once we flatten the hierarchical cgroup runqueues.
> 
> No functional change.
> 
> Signed-off-by: Rik van Riel <r...@surriel.com>
> ---
>  kernel/sched/fair.c | 17 +++++++++++++----
>  1 file changed, 13 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index dcc521d251e3..c6ede2ecc935 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -275,6 +275,15 @@ static inline struct cfs_rq *group_cfs_rq(struct 
> sched_entity *grp)
>       return grp->my_q;
>  }
>  
> +/* runqueue owned by the parent entity */
> +static inline struct cfs_rq *group_cfs_rq_of_parent(struct sched_entity *se)
> +{
> +     if (se->parent)
> +             return group_cfs_rq(se->parent);
> +
> +     return &cfs_rq_of(se)->rq->cfs;
> +}
> +
>  static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
>  {
>       struct rq *rq = rq_of(cfs_rq);
> @@ -3298,7 +3307,7 @@ static inline int propagate_entity_load_avg(struct 
> sched_entity *se)
>  
>       gcfs_rq->propagate = 0;
>  
> -     cfs_rq = cfs_rq_of(se);
> +     cfs_rq = group_cfs_rq_of_parent(se);
>  
>       add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum);
>  
> @@ -7779,7 +7788,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
>  
>       WRITE_ONCE(cfs_rq->h_load_next, NULL);
>       for_each_sched_entity(se) {
> -             cfs_rq = cfs_rq_of(se);
> +             cfs_rq = group_cfs_rq_of_parent(se);

Why do you change this here? task_se_h_load() calls
update_cfs_rq_h_load() with cfs_rq = group_cfs_rq_of_parent(se) because
the task might not be on the cfs_rq yet.

But inside update_cfs_rq_h_load() the first se is derived from
cfs_rq->tg->se[cpu_of(rq)] so in the first for_each_sched_entity() loop
we should still start with group_cfs_rq() (se->my_q) ?

The system doesn't barf with these two WARN_ON's in.

@@ -7663,12 +7673,17 @@ static void update_cfs_rq_h_load(struct cfs_rq
*cfs_rq)
        unsigned long now = jiffies;
        unsigned long load;

+       WARN_ON(se && (se != group_cfs_rq(se)->tg->se[cpu_of(rq)]));
+
        if (cfs_rq->last_h_load_update == now)
                return;

        WRITE_ONCE(cfs_rq->h_load_next, NULL);
        for_each_sched_entity(se) {
                cfs_rq = group_cfs_rq_of_parent(se);
+
+               WARN_ON(se != group_cfs_rq(se)->tg->se[cpu_of(rq)]);
+
                WRITE_ONCE(cfs_rq->h_load_next, se);
                if (cfs_rq->last_h_load_update == now)
                        break;


[...]