mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Morten Rasmussen <morten.rasmussen@arm.com>
To: peterz@infradead.org, mingo@redhat.com
Cc: valentin.schneider@arm.com, dietmar.eggemann@arm.com,
	vincent.guittot@linaro.org, linux-kernel@vger.kernel.org,
	Morten Rasmussen <morten.rasmussen@arm.com>
Subject: [PATCH 1/7] sched: Add static_key for asymmetric cpu capacity optimizations
Date: Thu, 15 Feb 2018 16:20:48 +0000	[thread overview]
Message-ID: <1518711654-23503-2-git-send-email-morten.rasmussen@arm.com> (raw)
In-Reply-To: <1518711654-23503-1-git-send-email-morten.rasmussen@arm.com>

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 <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
---
 kernel/sched/fair.c     |  3 +++
 kernel/sched/sched.h    |  1 +
 kernel/sched/topology.c | 10 ++++++++++
 3 files changed, 14 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1070803cb423..452ad2e6f1a0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6291,6 +6291,9 @@ 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 2e95505e23c6..a06184906640 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1095,6 +1095,7 @@ 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 034cbed7f88b..517c57d312df 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -393,6 +393,7 @@ 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)
 {
@@ -420,6 +421,13 @@ static void update_top_cache_domain(int cpu)
 	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
 }
 
+static void update_asym_cpucapacity(int cpu)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+	    lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY))
+		static_branch_enable(&sched_asym_cpucapacity);
+}
+
 /*
  * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
  * hold the hotplug lock.
@@ -1697,6 +1705,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 
 		cpu_attach_domain(sd, d.rd, i);
 	}
+
+	update_asym_cpucapacity(cpumask_first(cpu_map));
 	rcu_read_unlock();
 
 	if (rq && sched_debug_enabled) {
-- 
2.7.4

  reply	other threads:[~2018-02-15 16:23 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-15 16:20 [PATCH 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems Morten Rasmussen
2018-02-15 16:20 ` Morten Rasmussen [this message]
2018-02-16 13:47   ` [PATCH 1/7] sched: Add static_key for asymmetric cpu capacity optimizations Peter Zijlstra
2018-02-16 15:41     ` Morten Rasmussen
2018-02-16 16:51       ` Peter Zijlstra
2018-02-19 11:49         ` Morten Rasmussen
2018-02-16 17:39       ` Quentin Perret
2018-02-16 17:43         ` Peter Zijlstra
2018-02-15 16:20 ` [PATCH 2/7] sched/fair: Add group_misfit_task load-balance type Morten Rasmussen
2018-02-19 13:56   ` Peter Zijlstra
2018-02-19 13:58     ` Peter Zijlstra
2018-02-20 16:01       ` Morten Rasmussen
2018-02-15 16:20 ` [PATCH 3/7] sched/fair: Consider misfit tasks when load-balancing Morten Rasmussen
2018-02-15 16:20 ` [PATCH 4/7] sched/fair: Avoid unnecessary balancing of asymmetric capacity groups Morten Rasmussen
2018-02-19 14:50   ` Peter Zijlstra
2018-02-19 14:53     ` Peter Zijlstra
2018-02-20 16:22       ` Morten Rasmussen
2018-02-19 15:10   ` Peter Zijlstra
2018-02-20 16:33     ` Morten Rasmussen
2018-02-20 18:26       ` Peter Zijlstra
2018-02-23 16:38         ` Morten Rasmussen
2018-02-23 16:47           ` Peter Zijlstra
2018-02-26 15:06             ` Morten Rasmussen
2018-02-15 16:20 ` [PATCH 5/7] sched/fair: Kick nohz balance if rq->misfit_task Morten Rasmussen
2018-02-15 16:20 ` [PATCH 6/7] sched: Rename root_domain->overload to should_idle_balance Morten Rasmussen
2018-02-16  9:14   ` Juri Lelli
2018-02-16  9:49     ` Peter Zijlstra
2018-02-16 11:59       ` Valentin Schneider
2018-02-15 16:20 ` [PATCH 7/7] sched/fair: Set sd->should_idle_balance when misfit Morten Rasmussen
2018-02-28  7:46 ` [PATCH 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems Gaku Inami
2018-03-01 11:59   ` Valentin Schneider

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1518711654-23503-2-git-send-email-morten.rasmussen@arm.com \
    --to=morten.rasmussen@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®