Re: [PATCH v3 2/2] sched/fair: Fixes for capacity inversion detection

From: Vincent Guittot
Date: Fri Jan 13 2023 - 03:16:17 EST


On Thu, 12 Jan 2023 at 13:27, Qais Yousef <qyousef@xxxxxxxxxxx> wrote:
>
> Traversing the Perf Domains requires rcu_read_lock() to be held and is
> conditional on sched_energy_enabled(). Ensure right protections applied.
>
> Also skip capacity inversion detection for our own pd; which was an
> error.
>
> Fixes: 44c7b80bffc3 ("sched/fair: Detect capacity inversion")
> Reported-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
> Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>

Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>

> ---
> kernel/sched/fair.c | 13 +++++++++++--
> 1 file changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 5a8e75d4a17b..34239d3118f0 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -8992,16 +8992,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
> * * Thermal pressure will impact all cpus in this perf domain
> * equally.
> */
> - if (static_branch_unlikely(&sched_asym_cpucapacity)) {
> + if (sched_energy_enabled()) {
> unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
> - struct perf_domain *pd = rcu_dereference(rq->rd->pd);
> + struct perf_domain *pd;
> +
> + rcu_read_lock();
>
> + pd = rcu_dereference(rq->rd->pd);
> rq->cpu_capacity_inverted = 0;
>
> for (; pd; pd = pd->next) {
> struct cpumask *pd_span = perf_domain_span(pd);
> unsigned long pd_cap_orig, pd_cap;
>
> + /* We can't be inverted against our own pd */
> + if (cpumask_test_cpu(cpu_of(rq), pd_span))
> + continue;
> +
> cpu = cpumask_any(pd_span);
> pd_cap_orig = arch_scale_cpu_capacity(cpu);
>
> @@ -9026,6 +9033,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
> break;
> }
> }
> +
> + rcu_read_unlock();
> }
>
> trace_sched_cpu_capacity_tp(rq);
> --
> 2.25.1
>