LKML Archive on lore.kernel.org
 help / 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@quicinc.com, skannan@quicinc.com,
	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 v5 07/14] sched/topology: Introduce sched_energy_present static key
Date: Tue, 24 Jul 2018 13:25:14 +0100
Message-ID: <20180724122521.22109-8-quentin.perret@arm.com> (raw)
In-Reply-To: <20180724122521.22109-1-quentin.perret@arm.com>

In order to ensure a minimal performance impact on non-energy-aware
systems, introduce a static_key guarding the access to Energy-Aware
Scheduling (EAS) code.

The static key is set iff all the following conditions are met for at
least one root domain:
  1. all online CPUs of the root domain are covered by the Energy
     Model (EM);
  2. the complexity of the root domain's EM is low enough to keep
     scheduling overheads low;
  3. the root domain has an asymmetric CPU capacity topology (detected
     by looking for the SD_ASYM_CPUCAPACITY flag in the sched_domain
     hierarchy).

The static key is checked in the rd_freq_domain() function which returns
the frequency domains of a root domain when they are available. As EAS
cannot be enabled with CONFIG_ENERGY_MODEL=n, rd_freq_domain() is
stubbed to 'NULL' to let the compiler remove the unused EAS code by
constant propagation.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
---
 kernel/sched/sched.h    | 17 ++++++++++
 kernel/sched/topology.c | 73 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 25d64a0b6fe0..a317457804dd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2222,8 +2222,25 @@ static inline unsigned long cpu_util_irq(struct rq *rq)
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_ENERGY_MODEL
+extern struct static_key_false sched_energy_present;
+/**
+ * rd_freq_domain - Get the frequency domains of a root domain.
+ *
+ * Must be called from a RCU read-side critical section.
+ */
+static inline struct freq_domain *rd_freq_domain(struct root_domain *rd)
+{
+	if (!static_branch_unlikely(&sched_energy_present))
+		return NULL;
+
+	return rcu_dereference(rd->fd);
+}
 #define freq_domain_span(fd) (to_cpumask(((fd)->obj->cpus)))
 #else
+static inline struct freq_domain *rd_freq_domain(struct root_domain *rd)
+{
+	return NULL;
+}
 #define freq_domain_span(fd) NULL
 #endif
 #endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8f3f746b0d5e..483bb7bf7af6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -275,12 +275,32 @@ static void destroy_freq_domain_rcu(struct rcu_head *rp)
 	free_fd(fd);
 }
 
+/*
+ * The complexity of the Energy Model is defined as: nr_fd * (nr_cpus + nr_cs)
+ * with: 'nr_fd' the number of frequency domains; 'nr_cpus' the number of CPUs;
+ * and 'nr_cs' the sum of the capacity states numbers of all frequency domains.
+ *
+ * It is generally not a good idea to use such a model in the wake-up path on
+ * very complex platforms because of the associated scheduling overheads. The
+ * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
+ * with per-CPU DVFS and less than 8 capacity states each, for example.
+ */
+#define EM_MAX_COMPLEXITY 2048
+
+
 static void build_freq_domains(const struct cpumask *cpu_map)
 {
+	int i, nr_fd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct freq_domain *fd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
-	int i;
+
+	/* EAS is enabled for asymmetric CPU capacity topologies. */
+	if (!per_cpu(sd_ea, cpu)) {
+		if (sched_debug())
+			pr_info("rd %*pbl: !sd_ea\n", cpumask_pr_args(cpu_map));
+		goto free;
+	}
 
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
@@ -293,6 +313,18 @@ static void build_freq_domains(const struct cpumask *cpu_map)
 			goto free;
 		tmp->next = fd;
 		fd = tmp;
+
+		/* Count freq. doms and perf states for the complexity check. */
+		nr_fd++;
+		nr_cs += em_fd_nr_cap_states(fd->obj);
+	}
+
+	/* Bail out if the Energy Model complexity is too high. */
+	if (nr_fd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+		if (sched_debug())
+			pr_info("rd %*pbl: EM complexity is too high\n ",
+						cpumask_pr_args(cpu_map));
+		goto free;
 	}
 
 	freq_domain_debug(cpu_map, fd);
@@ -312,6 +344,44 @@ static void build_freq_domains(const struct cpumask *cpu_map)
 	if (tmp)
 		call_rcu(&tmp->rcu, destroy_freq_domain_rcu);
 }
+
+/*
+ * This static_key is set if at least one root domain meets all the following
+ * conditions:
+ *    1. all CPUs of the root domain are covered by the EM;
+ *    2. the EM complexity is low enough to keep scheduling overheads low;
+ *    3. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
+ */
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+
+static void sched_energy_start(int ndoms_new, cpumask_var_t doms_new[])
+{
+	/*
+	 * The conditions for EAS to start are checked during the creation of
+	 * root domains. If one of them meets all conditions, it will have a
+	 * non-null list of frequency domains.
+	 */
+	while (ndoms_new) {
+		if (cpu_rq(cpumask_first(doms_new[ndoms_new - 1]))->rd->fd)
+			goto enable;
+		ndoms_new--;
+	}
+
+	if (static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: stopping EAS\n", __func__);
+		static_branch_disable_cpuslocked(&sched_energy_present);
+	}
+
+	return;
+
+enable:
+	if (!static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: starting EAS\n", __func__);
+		static_branch_enable_cpuslocked(&sched_energy_present);
+	}
+}
 #else
 static void free_rd_fd(struct root_domain *rd) { }
 #endif
@@ -2046,6 +2116,7 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 match3:
 		;
 	}
+	sched_energy_start(ndoms_new, doms_new);
 #endif
 
 	/* Remember the new sched domains: */
-- 
2.18.0


  parent reply index

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-24 12:25 [PATCH v5 00/14] Energy Aware Scheduling Quentin Perret
2018-07-24 12:25 ` [PATCH v5 01/14] sched: Relocate arch_scale_cpu_capacity Quentin Perret
2018-07-24 12:25 ` [PATCH v5 02/14] sched/cpufreq: Factor out utilization to frequency mapping Quentin Perret
2018-07-24 12:25 ` [PATCH v5 03/14] PM: Introduce an Energy Model management framework Quentin Perret
2018-08-09 21:52   ` Rafael J. Wysocki
2018-08-10  8:15     ` Quentin Perret
2018-08-10  8:41       ` Rafael J. Wysocki
2018-08-10  9:12         ` Quentin Perret
2018-08-10 11:13           ` Rafael J. Wysocki
2018-08-10 12:30             ` Quentin Perret
2018-08-12  9:49               ` Rafael J. Wysocki
2018-07-24 12:25 ` [PATCH v5 04/14] PM / EM: Expose the Energy Model in sysfs Quentin Perret
2018-07-24 12:25 ` [PATCH v5 05/14] sched/topology: Reference the Energy Model of CPUs when available Quentin Perret
2018-07-24 12:25 ` [PATCH v5 06/14] sched/topology: Lowest energy aware balancing sched_domain level pointer Quentin Perret
2018-07-26 16:00   ` Valentin Schneider
2018-07-26 17:01     ` Quentin Perret
2018-07-24 12:25 ` Quentin Perret [this message]
2018-07-24 12:25 ` [PATCH v5 08/14] sched/fair: Clean-up update_sg_lb_stats parameters Quentin Perret
2018-07-24 12:25 ` [PATCH v5 09/14] sched: Add over-utilization/tipping point indicator Quentin Perret
2018-08-02 12:26   ` Peter Zijlstra
2018-08-02 13:03     ` Quentin Perret
2018-08-02 13:08       ` Peter Zijlstra
2018-08-02 13:18         ` Quentin Perret
2018-08-02 13:48           ` Vincent Guittot
2018-08-02 14:14             ` Quentin Perret
2018-08-02 15:14               ` Vincent Guittot
2018-08-02 15:30                 ` Quentin Perret
2018-08-02 15:55                   ` Vincent Guittot
2018-08-02 16:00                     ` Quentin Perret
2018-08-02 16:07                       ` Vincent Guittot
2018-08-02 16:10                         ` Quentin Perret
2018-08-02 16:38                           ` Vincent Guittot
2018-08-02 16:59                             ` Quentin Perret
2018-08-03  7:48                               ` Vincent Guittot
2018-08-03  8:18                                 ` Quentin Perret
2018-08-03 13:49                                   ` Vincent Guittot
2018-08-03 14:21                                     ` Vincent Guittot
2018-08-03 15:55                                     ` Quentin Perret
2018-08-06  8:40                                       ` Vincent Guittot
2018-08-06  9:43                                         ` Quentin Perret
2018-08-06 10:45                                           ` Vincent Guittot
2018-08-06 11:02                                             ` Quentin Perret
2018-08-06 10:08                                         ` Dietmar Eggemann
2018-08-06 10:33                                           ` Vincent Guittot
2018-08-06 12:29                                             ` Dietmar Eggemann
2018-08-06 12:37                                               ` Vincent Guittot
2018-08-06 13:20                                                 ` Dietmar Eggemann
2018-08-09  9:30   ` Vincent Guittot
2018-08-09  9:38     ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 10/14] sched/cpufreq: Refactor the utilization aggregation method Quentin Perret
2018-07-30 19:35   ` skannan
2018-07-31  7:59     ` Quentin Perret
2018-07-31 19:31       ` skannan
2018-08-01  7:32         ` Rafael J. Wysocki
2018-08-01  8:23           ` Quentin Perret
2018-08-01  8:35             ` Rafael J. Wysocki
2018-08-01  9:23               ` Quentin Perret
2018-08-01  9:40                 ` Rafael J. Wysocki
2018-08-02 13:04                 ` Peter Zijlstra
2018-08-02 15:39                   ` Quentin Perret
2018-08-03 13:04                     ` Quentin Perret
2018-08-02 12:33     ` Peter Zijlstra
2018-08-02 12:45       ` Peter Zijlstra
2018-08-02 15:21         ` Quentin Perret
2018-08-02 17:36           ` Peter Zijlstra
2018-08-03 12:42             ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 11/14] sched/fair: Introduce an energy estimation helper function Quentin Perret
2018-07-24 12:25 ` [PATCH v5 12/14] sched/fair: Select an energy-efficient CPU on task wake-up Quentin Perret
2018-08-02 13:54   ` Peter Zijlstra
2018-08-02 16:21     ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 13/14] OPTIONAL: arch_topology: Start Energy Aware Scheduling Quentin Perret
2018-07-24 12:25 ` [PATCH v5 14/14] OPTIONAL: cpufreq: dt: Register an Energy Model Quentin Perret

Reply instructions:

You may reply publically 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=20180724122521.22109-8-quentin.perret@arm.com \
    --to=quentin.perret@arm.com \
    --cc=adharmap@quicinc.com \
    --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@quicinc.com \
    --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 \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox