commit da07d2f9c153e457e845d4dcfdd13568d71d18a4 upstream.
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>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20230112122708.330667-3-qyousef@xxxxxxxxxxx
(cherry picked from commit da07d2f9c153e457e845d4dcfdd13568d71d18a4)
Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>
---
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 e3910f73ad65..b654c25a26cb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8363,16 +8363,23 @@ 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);
@@ -8397,6 +8404,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
break;
}
}
+
+ rcu_read_unlock();
}
trace_sched_cpu_capacity_tp(rq);
--
2.25.1
