From: Dietmar Eggemann <dietmar.eggemann@arm.com>
To: Quentin Perret <quentin.perret@arm.com>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <peterz@infradead.org>,
Thara Gopinath <thara.gopinath@linaro.org>,
linux-pm@vger.kernel.org,
Morten Rasmussen <morten.rasmussen@arm.com>,
Chris Redpath <chris.redpath@arm.com>,
Patrick Bellasi <patrick.bellasi@arm.com>,
Valentin Schneider <valentin.schneider@arm.com>,
"Rafael J . Wysocki" <rjw@rjwysocki.net>,
Vincent Guittot <vincent.guittot@linaro.org>,
Viresh Kumar <viresh.kumar@linaro.org>,
Todd Kjos <tkjos@google.com>, Joel Fernandes <joelaf@google.com>
Subject: Re: [RFC PATCH 2/6] sched: Introduce energy models of CPUs
Date: Tue, 27 Mar 2018 00:26:43 +0200 [thread overview]
Message-ID: <ab194f83-85eb-4bec-feea-5fbe5d5b20f5@arm.com> (raw)
In-Reply-To: <20180325134548.GA1344@queper01-VirtualBox>
On 03/25/2018 03:48 PM, Quentin Perret wrote:
> On Tuesday 20 Mar 2018 at 10:52:15 (+0100), Greg Kroah-Hartman wrote:
>> On Tue, Mar 20, 2018 at 09:43:08AM +0000, Dietmar Eggemann wrote:
>>> From: Quentin Perret <quentin.perret@arm.com>
>
> [...]
>
>>> +#ifdef CONFIG_PM_OPP
>>
>> #ifdefs go in .h files, not .c files, right?
>>
>
> So, after looking into this, my suggestion would be to: 1) remove the
> #ifdef CONFIG_PM_OPP from energy.c entirely; 2) make sure
> init_sched_energy() is stubbed properly for !CONFIG_SMP and
> !CONFIG_PM_OPP in include/linux/sched/energy.h; 3) relocate the global
> variables (energy_model, freq_domains, ...) to fair.c; and 4) modify
> kernel/sched/Makefile with something like:
>
> ifeq ($(CONFIG_PM_OPP),y)
> obj-$(CONFIG_SMP) += energy.o
> endif
>
> That way, energy.c is not compiled if not needed by the arch, and the
> ifdef are kept within header files and Makefiles.
>
> Would that work ?
Could we extend this idea a little bit further and leave the global
variables in energy.c? Normally, all energy interfaces could be
declared or stubbed in energy.h.
We could hide the access to energy_model, sched_energy_present and
freq_domains behind functions.
It would be nice to provide also find_energy_efficient_cpu() in energy.c
but it uses itself a lot of fair.c stuff and we do want to avoid function
calls in the wakeup path, right?
Boot-tested on juno r0 (CONFIG_SMP=y and CONFIG_PM_OPP=y). Build-tested on
i386 (CONFIG_SMP and CONFIG_PM_OPP not set), arm multi_v5_defconfig (CONFIG_SMP
not set and CONFIG_PM_OPP=y).
in energy.h:
#ifdef CONFIG_SMP
#ifdef CONFIG_PM_OPP
static inline struct capacity_state *find_cap_state(int cpu, unsigned long util)
{
...
}
static inline bool sched_energy_enabled(void)
{
...
}
static inline struct list_head *get_freq_domains(void)
{
...
}
#endif
#endif
#if !defined(CONFIG_SMP) || !defined(CONFIG_PM_OPP)
static inline struct capacity_state *find_cap_state(int cpu, unsigned long util) { return false; }
static inline struct list_head *get_freq_domains(void) { return NULL; }
static inline struct capacity_state *
find_cap_state(int cpu, unsigned long util) { return NULL; }
static inline void init_sched_energy(void) { }
#endif
#define for_each_freq_domain(fdom) \
list_for_each_entry(fdom, get_freq_domains(), next)
--->8---
diff --git a/include/linux/sched/energy.h b/include/linux/sched/energy.h
index b4f43564ffe4..5aad03ec5b30 100644
--- a/include/linux/sched/energy.h
+++ b/include/linux/sched/energy.h
@@ -20,12 +20,49 @@ struct freq_domain {
extern struct sched_energy_model ** __percpu energy_model;
extern struct static_key_false sched_energy_present;
extern struct list_head freq_domains;
-#define for_each_freq_domain(fdom) \
- list_for_each_entry(fdom, &freq_domains, next)
-void init_sched_energy(void);
-#else
-static inline void init_sched_energy(void) { }
+#ifdef CONFIG_PM_OPP
+static inline bool sched_energy_enabled(void)
+{
+ return static_branch_unlikely(&sched_energy_present);
+}
+
+static inline struct list_head *get_freq_domains(void)
+{
+ return &freq_domains;
+}
+
+static inline
+struct capacity_state *find_cap_state(int cpu, unsigned long util)
+{
+ struct sched_energy_model *em = *per_cpu_ptr(energy_model, cpu);
+ struct capacity_state *cs = NULL;
+ int i;
+
+ util += util >> 2;
+
+ for (i = 0; i < em->nr_cap_states; i++) {
+ cs = &em->cap_states[i];
+ if (cs->cap >= util)
+ break;
+ }
+
+ return cs;
+}
+
+extern void init_sched_energy(void);
#endif
+#endif /* CONFIG_SMP */
+#if !defined(CONFIG_SMP) || !defined(CONFIG_PM_OPP)
+static inline bool sched_energy_enabled(void) { return false; }
+static inline struct list_head *get_freq_domains(void) { return NULL; }
+static inline struct capacity_state *
+find_cap_state(int cpu, unsigned long util) { return NULL; }
+static inline void init_sched_energy(void) { }
#endif
+
+#define for_each_freq_domain(fdom) \
+ list_for_each_entry(fdom, get_freq_domains(), next)
+
+#endif /* _LINUX_SCHED_ENERGY_H */
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 912972ad4dbc..e34bec3ae353 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle.o fair.o rt.o deadline.o
obj-y += wait.o wait_bit.o swait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o energy.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
@@ -29,3 +29,6 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
obj-$(CONFIG_MEMBARRIER) += membarrier.o
obj-$(CONFIG_CPU_ISOLATION) += isolation.o
+ifeq ($(CONFIG_PM_OPP),y)
+ obj-$(CONFIG_SMP) += energy.o
+endif
diff --git a/kernel/sched/energy.c b/kernel/sched/energy.c
index 4662c993e096..1de8226943b9 100644
--- a/kernel/sched/energy.c
+++ b/kernel/sched/energy.c
@@ -30,7 +30,6 @@ struct sched_energy_model ** __percpu energy_model;
*/
LIST_HEAD(freq_domains);
-#ifdef CONFIG_PM_OPP
static struct sched_energy_model *build_energy_model(int cpu)
{
unsigned long cap_scale = arch_scale_cpu_capacity(NULL, cpu);
@@ -185,6 +184,3 @@ void init_sched_energy(void)
exit_fail:
pr_err("Energy Aware Scheduling initialization failed.\n");
}
-#else
-void init_sched_energy(void) {}
-#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 65a1bead0773..b3e6a2656b68 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6456,27 +6456,6 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
return !util_fits_capacity(task_util(p), min_cap);
}
-static struct capacity_state *find_cap_state(int cpu, unsigned long util)
-{
- struct sched_energy_model *em = *per_cpu_ptr(energy_model, cpu);
- struct capacity_state *cs = NULL;
- int i;
-
- /*
- * As the goal is to estimate the OPP reached for a specific util
- * value, mimic the behaviour of schedutil with a 1.25 coefficient
- */
- util += util >> 2;
-
- for (i = 0; i < em->nr_cap_states; i++) {
- cs = &em->cap_states[i];
- if (cs->cap >= util)
- break;
- }
-
- return cs;
-}
-
static unsigned long compute_energy(struct task_struct *p, int dst_cpu)
{
unsigned long util, fdom_max_util;
@@ -6557,7 +6536,7 @@ static inline bool wake_energy(struct task_struct *p, int prev_cpu)
{
struct sched_domain *sd;
- if (!static_branch_unlikely(&sched_energy_present))
+ if (!sched_energy_enabled())
return false;
sd = rcu_dereference_sched(cpu_rq(prev_cpu)->sd);
@@ -9252,8 +9231,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
}
max_cost += sd->max_newidle_lb_cost;
- if (static_branch_unlikely(&sched_energy_present) &&
- !sd_overutilized(sd))
+ if (sched_energy_enabled() && !sd_overutilized(sd))
continue;
if (!(sd->flags & SD_LOAD_BALANCE))
@@ -9823,8 +9801,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
break;
}
- if (static_branch_unlikely(&sched_energy_present) &&
- !sd_overutilized(sd))
+ if (sched_energy_enabled() && !sd_overutilized(sd))
continue;
if (sd->flags & SD_BALANCE_NEWIDLE) {
next prev parent reply other threads:[~2018-03-26 22:26 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-20 9:43 [RFC PATCH 0/6] Energy Aware Scheduling Dietmar Eggemann
2018-03-20 9:43 ` [RFC PATCH 1/6] sched/fair: Create util_fits_capacity() Dietmar Eggemann
2018-03-20 9:43 ` [RFC PATCH 2/6] sched: Introduce energy models of CPUs Dietmar Eggemann
2018-03-20 9:52 ` Greg Kroah-Hartman
2018-03-21 0:45 ` Quentin Perret
2018-03-25 13:48 ` Quentin Perret
2018-03-26 22:26 ` Dietmar Eggemann [this message]
2018-04-09 12:01 ` Peter Zijlstra
2018-04-09 13:45 ` Quentin Perret
2018-04-09 15:32 ` Peter Zijlstra
2018-04-09 16:42 ` Quentin Perret
2018-04-10 6:55 ` Rafael J. Wysocki
2018-04-10 9:31 ` Quentin Perret
2018-04-10 10:20 ` Rafael J. Wysocki
2018-03-20 9:43 ` [RFC PATCH 3/6] sched: Add over-utilization/tipping point indicator Dietmar Eggemann
2018-04-09 9:40 ` Peter Zijlstra
2018-04-09 9:47 ` Peter Zijlstra
2018-04-09 9:53 ` Dietmar Eggemann
2018-04-09 11:49 ` Peter Zijlstra
2018-03-20 9:43 ` [RFC PATCH 4/6] sched/fair: Introduce an energy estimation helper function Dietmar Eggemann
2018-03-21 9:04 ` Juri Lelli
2018-03-21 12:26 ` Patrick Bellasi
2018-03-21 12:59 ` Juri Lelli
2018-03-21 13:55 ` Quentin Perret
2018-03-21 15:15 ` Juri Lelli
2018-03-21 16:26 ` Morten Rasmussen
2018-03-21 17:02 ` Juri Lelli
2018-03-21 14:02 ` Quentin Perret
2018-03-21 21:15 ` Dietmar Eggemann
2018-03-21 12:39 ` Patrick Bellasi
2018-03-21 14:26 ` Quentin Perret
2018-03-21 14:50 ` Juri Lelli
2018-03-21 15:54 ` Patrick Bellasi
2018-03-22 5:05 ` Quentin Perret
2018-03-20 9:43 ` [RFC PATCH 5/6] sched/fair: Select an energy-efficient CPU on task wake-up Dietmar Eggemann
2018-03-21 15:35 ` Patrick Bellasi
2018-03-22 20:10 ` Joel Fernandes
2018-03-23 15:47 ` Morten Rasmussen
2018-03-24 1:13 ` Joel Fernandes
2018-03-24 1:34 ` Quentin Perret
2018-03-24 6:06 ` Joel Fernandes
2018-03-24 1:22 ` Quentin Perret
2018-03-25 1:52 ` Quentin Perret
2018-03-22 16:27 ` Joel Fernandes
2018-03-22 18:06 ` Patrick Bellasi
2018-03-22 20:19 ` Joel Fernandes
2018-03-24 1:47 ` Quentin Perret
2018-03-25 0:12 ` Joel Fernandes
2018-03-23 16:00 ` Morten Rasmussen
2018-03-24 0:36 ` Joel Fernandes
2018-03-25 1:38 ` Quentin Perret
2018-03-20 9:43 ` [RFC PATCH 6/6] drivers: base: arch_topology.c: Enable EAS for arm/arm64 platforms Dietmar Eggemann
2018-03-20 9:49 ` Greg Kroah-Hartman
2018-03-20 15:20 ` Dietmar Eggemann
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=ab194f83-85eb-4bec-feea-5fbe5d5b20f5@arm.com \
--to=dietmar.eggemann@arm.com \
--cc=chris.redpath@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=joelaf@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=morten.rasmussen@arm.com \
--cc=patrick.bellasi@arm.com \
--cc=peterz@infradead.org \
--cc=quentin.perret@arm.com \
--cc=rjw@rjwysocki.net \
--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
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;
as well as URLs for NNTP newsgroup(s).