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 <morten.rasmussen@arm.com>
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: adharmap@codeaurora.org
Cc: chris.redpath@arm.com
Cc: currojerez@riseup.net
Cc: dietmar.eggemann@arm.com
Cc: edubezval@gmail.com
Cc: gregkh@linuxfoundation.org
Cc: javi.merino@kernel.org
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: patrick.bellasi@arm.com
Cc: pkondeti@codeaurora.org
Cc: rjw@rjwysocki.net
Cc: skannan@codeaurora.org
Cc: smuckle@google.com
Cc: srinivas.pandruvada@linux.intel.com
Cc: thara.gopinath@linaro.org
Cc: tkjos@google.com
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Cc: viresh.kumar@linaro.org
Link: https://lkml.kernel.org/r/20181203095628.11858-7-quentin.perret@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdc8356ea742928ec10798ac723157af40a2104c..a31a6d32590171ce89a30f5d46cafcbc94a1e0bc 100644 (file)
--- 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 808a565187b1de47dff2357f5478de09c08796db..75c40367470652f4caef9d6aa30ed8b90541d203 100644 (file)
--- 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 169d25cafab595602221b75427cd08263c7a8059..137ccfed9a43eac2592504f4a1ecf0a6e1d0ff2d 100644 (file)
--- 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);
 }
 
 /*