From 34e2c555f3e13c90e9284e23d00f03be8a6e06c5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 15 Feb 2016 20:20:42 +0100 Subject: cpufreq: Add mechanism for registering utilization update callbacks Introduce a mechanism by which parts of the cpufreq subsystem ("setpolicy" drivers or the core) can register callbacks to be executed from cpufreq_update_util() which is invoked by the scheduler's update_load_avg() on CPU utilization changes. This allows the "setpolicy" drivers to dispense with their timers and do all of the computations they need and frequency/voltage adjustments in the update_load_avg() code path, among other things. The update_load_avg() changes were suggested by Peter Zijlstra. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- kernel/sched/deadline.c | 4 ++++ kernel/sched/fair.c | 26 +++++++++++++++++++++++++- kernel/sched/rt.c | 4 ++++ kernel/sched/sched.h | 1 + 4 files changed, 34 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..21a0aa6f810d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq) if (!dl_task(curr) || !on_dl_rq(dl_se)) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + /* * Consumed budget is computed considering the time as * observed by schedulable tasks (excluding time spent diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56b7d4b83947..e2987a7e489d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) { struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 now = cfs_rq_clock_task(cfs_rq); - int cpu = cpu_of(rq_of(cfs_rq)); + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); /* * Track task load average for carrying it to new CPU after migrated, and @@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg) update_tg_load_avg(cfs_rq, 0); + + if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { + unsigned long max = rq->cpu_capacity_orig; + + /* + * There are a few boundary cases this might miss but it should + * get called often enough that that should (hopefully) not be + * a real problem -- added to that it only calls on the local + * CPU, so if we enqueue remotely we'll miss an update, but + * the next tick/schedule should update. + * + * It will not get called when we go idle, because the idle + * thread is a different class (!fair), nor will the utilization + * number include things like RT tasks. + * + * As is, the util number is not freq-invariant (we'd have to + * implement arch_scale_freq_capacity() for that). + * + * See cpu_util(). + */ + cpufreq_update_util(rq_clock(rq), + min(cfs_rq->avg.util_avg, max), max); + } } static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea1..27f5b03cbdbe 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq) if (curr->sched_class != &rt_sched_class) return; + /* Kick cpufreq (see the comment in linux/cpufreq.h). */ + if (cpu_of(rq) == smp_processor_id()) + cpufreq_trigger_update(rq_clock(rq)); + delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 10f16374df7f..f042190c8002 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -9,6 +9,7 @@ #include #include #include +#include #include "cpupri.h" #include "cpudeadline.h" -- cgit v1.2.3 From adaf9fcd136970e480d7ca834c0cf25ce922ea74 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Mar 2016 20:44:47 +0100 Subject: cpufreq: Move scheduler-related code to the sched directory Create cpufreq.c under kernel/sched/ and move the cpufreq code related to the scheduler to that file and to sched.h. Redefine cpufreq_update_util() as a static inline function to avoid function calls at its call sites in the scheduler code (as suggested by Peter Zijlstra). Also move the definition of struct update_util_data and declaration of cpufreq_set_update_util_data() from include/linux/cpufreq.h to include/linux/sched.h. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- kernel/sched/Makefile | 1 + kernel/sched/cpufreq.c | 37 +++++++++++++++++++++++++++++++++++++ kernel/sched/sched.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 86 insertions(+), 1 deletion(-) create mode 100644 kernel/sched/cpufreq.c (limited to 'kernel') diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 67687973ce80..9507522164ac 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o +obj-$(CONFIG_CPU_FREQ) += cpufreq.o diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c new file mode 100644 index 000000000000..928c4ba32f68 --- /dev/null +++ b/kernel/sched/cpufreq.c @@ -0,0 +1,37 @@ +/* + * Scheduler code and data structures related to cpufreq. + * + * Copyright (C) 2016, Intel Corporation + * Author: Rafael J. Wysocki + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "sched.h" + +DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer. + * @cpu: The CPU to set the pointer for. + * @data: New pointer value. + * + * Set and publish the update_util_data pointer for the given CPU. That pointer + * points to a struct update_util_data object containing a callback function + * to call from cpufreq_update_util(). That function will be called from an RCU + * read-side critical section, so it must not sleep. + * + * Callers must use RCU-sched callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_sched() + * right after this function to avoid use-after-free. + */ +void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) +{ + if (WARN_ON(data && !data->func)) + return; + + rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); +} +EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f042190c8002..faf7e2758dd0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -9,7 +9,6 @@ #include #include #include -#include #include "cpupri.h" #include "cpudeadline.h" @@ -1739,3 +1738,51 @@ static inline u64 irq_time_read(int cpu) } #endif /* CONFIG_64BIT */ #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_CPU_FREQ +DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +/** + * cpufreq_update_util - Take a note about CPU utilization changes. + * @time: Current time. + * @util: Current utilization. + * @max: Utilization ceiling. + * + * This function is called by the scheduler on every invocation of + * update_load_avg() on the CPU whose utilization is being updated. + * + * It can only be called from RCU-sched read-side critical sections. + */ +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data) + data->func(data, time, util, max); +} + +/** + * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed. + * @time: Current time. + * + * The way cpufreq is currently arranged requires it to evaluate the CPU + * performance state (frequency/voltage) on a regular basis to prevent it from + * being stuck in a completely inadequate performance level for too long. + * That is not guaranteed to happen if the updates are only triggered from CFS, + * though, because they may not be coming in if RT or deadline tasks are active + * all the time (or there are RT and DL tasks only). + * + * As a workaround for that issue, this function is called by the RT and DL + * sched classes to trigger extra cpufreq updates to prevent it from stalling, + * but that really is a band-aid. Going forward it should be replaced with + * solutions targeted more specifically at RT and DL tasks. + */ +static inline void cpufreq_trigger_update(u64 time) +{ + cpufreq_update_util(time, ULONG_MAX, 0); +} +#else +static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {} +static inline void cpufreq_trigger_update(u64 time) {} +#endif /* CONFIG_CPU_FREQ */ -- cgit v1.2.3