sched/topology: Add lowest CPU asymmetry sched_domain level pointer

Add another member to the family of per-cpu sched_domain shortcut
pointers. This one, sd_asym_cpucapacity, points to the lowest level
at which the SD_ASYM_CPUCAPACITY flag is set. While at it, rename the
sd_asym shortcut to sd_asym_packing to avoid confusions.

Generally speaking, the largest opportunity to save energy via
scheduling comes from a smarter exploitation of heterogeneous platforms
(i.e. big.LITTLE). Consequently, the sd_asym_cpucapacity shortcut will
be used at first as the lowest domain where Energy-Aware Scheduling
(EAS) should be applied. For example, it is possible to apply EAS within
a socket on a multi-socket system, as long as each socket has an
asymmetric topology. Energy-aware cross-sockets wake-up balancing will
only happen when the system is over-utilized, or this_cpu and prev_cpu
are in different sockets.

Suggested-by: Morten Rasmussen <[email protected]>
Signed-off-by: Quentin Perret <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

3 files changed, 9 insertions, 4 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdc8356ea742..a31a6d325901 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9299,7 +9299,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		}
 	}
 
-	sd = rcu_dereference(per_cpu(sd_asym, cpu));
+	sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
 	if (sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
 			if (i == cpu ||
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 808a565187b1..75c403674706 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1303,7 +1303,8 @@ DECLARE_PER_CPU(int, sd_llc_size);
 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);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 169d25cafab5..137ccfed9a43 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -508,7 +508,8 @@ DEFINE_PER_CPU(int, sd_llc_size);
 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_PER_CPU(struct sched_domain *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
@@ -534,7 +535,10 @@ static void update_top_cache_domain(int cpu)
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
 
 	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
-	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+	rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
+
+	sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY);
+	rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
 }
 
 /*