The existing asymmetric cpu capacity code should cause minimal overhead
for others. Putting it behind a static_key, it has been done for SMT
optimizations, would make it easier to extend and improve without
causing harm to others moving forward.

cc: Ingo Molnar <[email protected]>
cc: Peter Zijlstra <[email protected]>

Signed-off-by: Morten Rasmussen <[email protected]>
---
 kernel/sched/fair.c     |  3 +++
 kernel/sched/sched.h    |  1 +
 kernel/sched/topology.c | 18 ++++++++++++++++++
 3 files changed, 22 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e497c05aab7f..6116d1b7e441 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6585,6 +6585,9 @@ static int wake_cap(struct task_struct *p, int cpu, int 
prev_cpu)
 {
        long min_cap, max_cap;
 
+       if (!static_branch_unlikely(&sched_asym_cpucapacity))
+               return 0;
+
        min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
        max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 67702b4d9ac7..0fbfbcf5c551 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1153,6 +1153,7 @@ DECLARE_PER_CPU(int, sd_llc_id);
 DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
        atomic_t                ref;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 61a1125c1ae4..edc87e35fc75 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -398,6 +398,7 @@ DEFINE_PER_CPU(int, sd_llc_id);
 DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -425,6 +426,21 @@ static void update_top_cache_domain(int cpu)
        rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
 }
 
+static void update_asym_cpucapacity(int cpu)
+{
+       int enable = false;
+
+       rcu_read_lock();
+       if (lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY))
+               enable = true;
+       rcu_read_unlock();
+
+       if (enable) {
+               /* This expects to be hotplug-safe */
+               static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
+       }
+}
+
 /*
  * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
  * hold the hotplug lock.
@@ -1707,6 +1723,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct 
sched_domain_attr *att
        }
        rcu_read_unlock();
 
+       update_asym_cpucapacity(cpumask_first(cpu_map));
+
        if (rq && sched_debug_enabled) {
                pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
                        cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
-- 
2.7.4

Reply via email to