> On Nov 13, 2024, at 9:57 PM, Juri Lelli <juri.lelli@xxxxxxxxxx> wrote:
>
> When root domain non-destructive changes (e.g., only modifying one of
> the existing root domains while the rest is not touched) happen we still
> need to clear DEADLINE bandwidth accounting so that it's then properly
> restore taking into account DEADLINE tasks associated to each cpuset
> (associated to each root domain). After the introduction of dl_servers,
> we fail to restore such servers contribution after non-destructive
> changes (as they are only considered on destructive changes when
> runqueues are attached to the new domains).
>
> Fix this by making sure we iterate over the dl_server attached to
> domains that have not been destroyed and add them bandwidth contribution
> back correctly.
>
> Signed-off-by: Juri Lelli <juri.lelli@xxxxxxxxxx>
Reviewed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Thanks,
- Joel
> ---
> include/linux/sched/deadline.h | 2 +-
> kernel/cgroup/cpuset.c | 2 +-
> kernel/sched/deadline.c | 18 +++++++++++++-----
> kernel/sched/topology.c | 10 ++++++----
> 4 files changed, 21 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
> index 3a912ab42bb5..82c966a55856 100644
> --- a/include/linux/sched/deadline.h
> +++ b/include/linux/sched/deadline.h
> @@ -33,7 +33,7 @@ static inline bool dl_time_before(u64 a, u64 b)
>
> struct root_domain;
> extern void dl_add_task_root_domain(struct task_struct *p);
> -extern void dl_clear_root_domain(struct root_domain *rd);
> +extern void dl_clear_root_domain(struct root_domain *rd, bool restore);
>
> #endif /* CONFIG_SMP */
>
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 142303abb055..4d3603a99db3 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -954,7 +954,7 @@ static void dl_rebuild_rd_accounting(void)
> * Clear default root domain DL accounting, it will be computed again
> * if a task belongs to it.
> */
> - dl_clear_root_domain(&def_root_domain);
> + dl_clear_root_domain(&def_root_domain, false);
>
> cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 9ce93d0bf452..e53208a50279 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -2968,13 +2968,21 @@ void dl_add_task_root_domain(struct task_struct *p)
> task_rq_unlock(rq, p, &rf);
> }
>
> -void dl_clear_root_domain(struct root_domain *rd)
> +void dl_clear_root_domain(struct root_domain *rd, bool restore)
> {
> - unsigned long flags;
> -
> - raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
> + guard(raw_spinlock_irqsave)(&rd->dl_bw.lock);
> rd->dl_bw.total_bw = 0;
> - raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
> +
> + if (restore) {
> + int i;
> +
> + for_each_cpu(i, rd->span) {
> + struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server;
> +
> + if (dl_server(dl_se))
> + rd->dl_bw.total_bw += dl_se->dl_bw;
> + }
> + }
> }
>
> #endif /* CONFIG_SMP */
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 9748a4c8d668..e9e7a7c43dd6 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -2721,12 +2721,14 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
>
> /*
> * This domain won't be destroyed and as such
> - * its dl_bw->total_bw needs to be cleared. It
> - * will be recomputed in function
> - * update_tasks_root_domain().
> + * its dl_bw->total_bw needs to be cleared.
> + * Tasks contribution will be then recomputed
> + * in function dl_update_tasks_root_domain(),
> + * dl_servers contribution in function
> + * dl_restore_server_root_domain().
> */
> rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
> - dl_clear_root_domain(rd);
> + dl_clear_root_domain(rd, true);
> goto match1;
> }
> }
> --
> 2.47.0
>
