1 files changed, 60 insertions, 3 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0f32acb05055..4c4ea474fdc2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8824,16 +8824,73 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
+	unsigned long capacity_orig = arch_scale_cpu_capacity(cpu);
 	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
+	struct rq *rq = cpu_rq(cpu);
 
-	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
+	rq->cpu_capacity_orig = capacity_orig;
 
 	if (!capacity)
 		capacity = 1;
 
-	cpu_rq(cpu)->cpu_capacity = capacity;
-	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+	rq->cpu_capacity = capacity;
+
+	/*
+	 * Detect if the performance domain is in capacity inversion state.
+	 *
+	 * Capacity inversion happens when another perf domain with equal or
+	 * lower capacity_orig_of() ends up having higher capacity than this
+	 * domain after subtracting thermal pressure.
+	 *
+	 * We only take into account thermal pressure in this detection as it's
+	 * the only metric that actually results in *real* reduction of
+	 * capacity due to performance points (OPPs) being dropped/become
+	 * unreachable due to thermal throttling.
+	 *
+	 * We assume:
+	 *   * That all cpus in a perf domain have the same capacity_orig
+	 *     (same uArch).
+	 *   * Thermal pressure will impact all cpus in this perf domain
+	 *     equally.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
+		struct perf_domain *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;
+
+			cpu = cpumask_any(pd_span);
+			pd_cap_orig = arch_scale_cpu_capacity(cpu);
+
+			if (capacity_orig < pd_cap_orig)
+				continue;
+
+			/*
+			 * handle the case of multiple perf domains have the
+			 * same capacity_orig but one of them is under higher
+			 * thermal pressure. We record it as capacity
+			 * inversion.
+			 */
+			if (capacity_orig == pd_cap_orig) {
+				pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu));
+
+				if (pd_cap > inv_cap) {
+					rq->cpu_capacity_inverted = inv_cap;
+					break;
+				}
+			} else if (pd_cap_orig > inv_cap) {
+				rq->cpu_capacity_inverted = inv_cap;
+				break;
+			}
+		}
+	}
+
+	trace_sched_cpu_capacity_tp(rq);
 
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;