linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Quentin Perret <quentin.perret@arm.com>
To: peterz@infradead.org, rjw@rjwysocki.net,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org
Cc: gregkh@linuxfoundation.org, mingo@redhat.com,
	dietmar.eggemann@arm.com, morten.rasmussen@arm.com,
	chris.redpath@arm.com, patrick.bellasi@arm.com,
	valentin.schneider@arm.com, vincent.guittot@linaro.org,
	thara.gopinath@linaro.org, viresh.kumar@linaro.org,
	tkjos@google.com, joel@joelfernandes.org, smuckle@google.com,
	adharmap@codeaurora.org, skannan@codeaurora.org,
	pkondeti@codeaurora.org, juri.lelli@redhat.com,
	edubezval@gmail.com, srinivas.pandruvada@linux.intel.com,
	currojerez@riseup.net, javi.merino@kernel.org,
	quentin.perret@arm.com
Subject: [PATCH v10 08/15] sched/topology: Make Energy Aware Scheduling depend on schedutil
Date: Mon,  3 Dec 2018 09:56:21 +0000	[thread overview]
Message-ID: <20181203095628.11858-9-quentin.perret@arm.com> (raw)
In-Reply-To: <20181203095628.11858-1-quentin.perret@arm.com>

Energy Aware Scheduling (EAS) is designed with the assumption that
frequencies of CPUs follow their utilization value. When using a CPUFreq
governor other than schedutil, the chances of this assumption being true
are small, if any. When schedutil is being used, EAS' predictions are at
least consistent with the frequency requests. Although those requests
have no guarantees to be honored by the hardware, they should at least
guide DVFS in the right direction and provide some hope in regards to the
EAS model being accurate.

To make sure EAS is only used in a sane configuration, create a strong
dependency on schedutil being used. Since having sugov compiled-in does
not provide that guarantee, make CPUFreq call a scheduler function on
governor changes hence letting it rebuild the scheduling domains, check
the governors of the online CPUs, and enable/disable EAS accordingly.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
---
 drivers/cpufreq/cpufreq.c        |  1 +
 include/linux/cpufreq.h          |  8 +++++++
 kernel/sched/cpufreq_schedutil.c | 37 ++++++++++++++++++++++++++++++--
 kernel/sched/sched.h             |  4 +---
 kernel/sched/topology.c          | 28 ++++++++++++++++++++----
 5 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7aa3dcad2175..6f23ebb395f1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2277,6 +2277,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
 			pr_debug("cpufreq: governor change\n");
+			sched_cpufreq_governor_change(policy, old_gov);
 			return 0;
 		}
 		cpufreq_exit_governor(policy);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 882a9b9e34bc..c86d6d8bdfed 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -950,6 +950,14 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 }
 #endif
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+			struct cpufreq_governor *old_gov);
+#else
+static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+			struct cpufreq_governor *old_gov) { }
+#endif
+
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 90128be27712..c2e53d1a3143 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -624,7 +624,7 @@ static struct kobj_type sugov_tunables_ktype = {
 
 /********************** cpufreq governor interface *********************/
 
-static struct cpufreq_governor schedutil_gov;
+struct cpufreq_governor schedutil_gov;
 
 static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
 {
@@ -883,7 +883,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 	sg_policy->need_freq_update = true;
 }
 
-static struct cpufreq_governor schedutil_gov = {
+struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
 	.dynamic_switching	= true,
@@ -906,3 +906,36 @@ static int __init sugov_register(void)
 	return cpufreq_register_governor(&schedutil_gov);
 }
 fs_initcall(sugov_register);
+
+#ifdef CONFIG_ENERGY_MODEL
+extern bool sched_energy_update;
+extern struct mutex sched_energy_mutex;
+
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+				  struct cpufreq_governor *old_gov)
+{
+	if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
+		/*
+		 * When called from the cpufreq_register_driver() path, the
+		 * cpu_hotplug_lock is already held, so use a work item to
+		 * avoid nested locking in rebuild_sched_domains().
+		 */
+		schedule_work(&rebuild_sd_work);
+	}
+
+}
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ae4fb3e88c35..6236081d68bf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2293,10 +2293,8 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned
 }
 #endif
 
-#ifdef CONFIG_SMP
-#ifdef CONFIG_ENERGY_MODEL
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 #define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus)))
 #else
 #define perf_domain_span(pd) NULL
 #endif
-#endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 992a2a893df1..70492d4bfed6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -201,7 +201,10 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
-#ifdef CONFIG_ENERGY_MODEL
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+DEFINE_MUTEX(sched_energy_mutex);
+bool sched_energy_update;
+
 static void free_pd(struct perf_domain *pd)
 {
 	struct perf_domain *tmp;
@@ -275,6 +278,7 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp)
  *    1. an Energy Model (EM) is available;
  *    2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
  *    3. the EM complexity is low enough to keep scheduling overheads low;
+ *    4. schedutil is driving the frequency of all CPUs of the rd;
  *
  * The complexity of the Energy Model is defined as:
  *
@@ -294,12 +298,15 @@ static void destroy_perf_domain_rcu(struct rcu_head *rp)
  */
 #define EM_MAX_COMPLEXITY 2048
 
+extern struct cpufreq_governor schedutil_gov;
 static void build_perf_domains(const struct cpumask *cpu_map)
 {
 	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
+	struct cpufreq_policy *policy;
+	struct cpufreq_governor *gov;
 
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
 	if (!per_cpu(sd_asym_cpucapacity, cpu)) {
@@ -315,6 +322,19 @@ static void build_perf_domains(const struct cpumask *cpu_map)
 		if (find_pd(pd, i))
 			continue;
 
+		/* Do not attempt EAS if schedutil is not being used. */
+		policy = cpufreq_cpu_get(i);
+		if (!policy)
+			goto free;
+		gov = policy->governor;
+		cpufreq_cpu_put(policy);
+		if (gov != &schedutil_gov) {
+			if (rd->pd)
+				pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
+						cpumask_pr_args(cpu_map));
+			goto free;
+		}
+
 		/* Create the new pd and add it to the local list. */
 		tmp = pd_init(i);
 		if (!tmp)
@@ -356,7 +376,7 @@ static void build_perf_domains(const struct cpumask *cpu_map)
 }
 #else
 static void free_pd(struct perf_domain *pd) { }
-#endif /* CONFIG_ENERGY_MODEL */
+#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
 
 static void free_rootdomain(struct rcu_head *rcu)
 {
@@ -2154,10 +2174,10 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 		;
 	}
 
-#ifdef CONFIG_ENERGY_MODEL
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 	/* Build perf. domains: */
 	for (i = 0; i < ndoms_new; i++) {
-		for (j = 0; j < n; j++) {
+		for (j = 0; j < n && !sched_energy_update; j++) {
 			if (cpumask_equal(doms_new[i], doms_cur[j]) &&
 			    cpu_rq(cpumask_first(doms_cur[j]))->rd->pd)
 				goto match3;
-- 
2.19.2


  parent reply	other threads:[~2018-12-03  9:57 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-03  9:56 [PATCH v10 00/15] Energy Aware Scheduling Quentin Perret
2018-12-03  9:56 ` [PATCH v10 01/15] sched: Relocate arch_scale_cpu_capacity Quentin Perret
2018-12-11 15:32   ` [tip:sched/core] sched/topology: Relocate arch_scale_cpu_capacity() to the internal header tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 02/15] sched/cpufreq: Prepare schedutil for Energy Aware Scheduling Quentin Perret
2018-12-11 12:01   ` Rafael J. Wysocki
2018-12-11 12:17     ` Quentin Perret
2018-12-11 12:22       ` Rafael J. Wysocki
2018-12-11 12:24         ` Quentin Perret
2018-12-11 15:33   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 03/15] PM: Introduce an Energy Model management framework Quentin Perret
2018-12-11 15:33   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 04/15] PM / EM: Expose the Energy Model in sysfs Quentin Perret
2018-12-11 14:18   ` Ingo Molnar
2018-12-11 15:04     ` Quentin Perret
2018-12-03  9:56 ` [PATCH v10 05/15] sched/topology: Reference the Energy Model of CPUs when available Quentin Perret
2018-12-11 15:34   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 06/15] sched/topology: Lowest CPU asymmetry sched_domain level pointer Quentin Perret
2018-12-11 15:34   ` [tip:sched/core] sched/topology: Add lowest " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 07/15] sched/topology: Disable EAS on inappropriate platforms Quentin Perret
2018-12-11 15:35   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` Quentin Perret [this message]
2018-12-11 15:36   ` [tip:sched/core] sched/topology: Make Energy Aware Scheduling depend on schedutil tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 09/15] sched: Introduce sched_energy_present static key Quentin Perret
2018-12-11 15:36   ` [tip:sched/core] sched/toplogy: Introduce the 'sched_energy_present' " tip-bot for Quentin Perret
2018-12-13 13:56     ` Quentin Perret
2018-12-03  9:56 ` [PATCH v10 10/15] sched: Introduce a sysctl for Energy Aware Scheduling Quentin Perret
2018-12-11 14:15   ` Ingo Molnar
2018-12-11 14:49     ` Quentin Perret
2018-12-13 14:03       ` Peter Zijlstra
2019-01-21 11:35   ` [tip:sched/core] sched/topology: " tip-bot for Quentin Perret
2019-01-21 13:51   ` tip-bot for Quentin Perret
2019-01-27 11:34   ` tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 11/15] sched/fair: Clean-up update_sg_lb_stats parameters Quentin Perret
2018-12-11 15:37   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 12/15] sched: Add over-utilization/tipping point indicator Quentin Perret
2018-12-11 15:37   ` [tip:sched/core] sched/fair: " tip-bot for Morten Rasmussen
2018-12-03  9:56 ` [PATCH v10 13/15] sched/fair: Introduce an energy estimation helper function Quentin Perret
2018-12-11 15:38   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 14/15] sched/fair: Select an energy-efficient CPU on task wake-up Quentin Perret
2018-12-11 15:39   ` [tip:sched/core] " tip-bot for Quentin Perret
2018-12-03  9:56 ` [PATCH v10 15/15] OPTIONAL: cpufreq: dt: Register an Energy Model Quentin Perret
2019-01-08 20:38   ` Matthias Kaehlcke
2019-01-09 10:57     ` Quentin Perret
2019-01-09 18:14       ` Matthias Kaehlcke
2019-01-10  9:08         ` Quentin Perret

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=20181203095628.11858-9-quentin.perret@arm.com \
    --to=quentin.perret@arm.com \
    --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=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=patrick.bellasi@arm.com \
    --cc=peterz@infradead.org \
    --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 \
    --subject='Re: [PATCH v10 08/15] sched/topology: Make Energy Aware Scheduling depend on schedutil' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).