BACKPORT: cpufreq: schedutil: New governor based on scheduler utilization data

Add a new cpufreq scaling governor, called "schedutil", that uses
scheduler-provided CPU utilization information as input for making
its decisions.

Doing that is possible after commit 34e2c55 (cpufreq: Add
mechanism for registering utilization update callbacks) that
introduced cpufreq_update_util() called by the scheduler on
utilization changes (from CFS) and RT/DL task status updates.
In particular, CPU frequency scaling decisions may be based on
the the utilization data passed to cpufreq_update_util() by CFS.

The new governor is relatively simple.

The frequency selection formula used by it depends on whether or not
the utilization is frequency-invariant.  In the frequency-invariant
case the new CPU frequency is given by

	next_freq = 1.25 * max_freq * util / max

where util and max are the last two arguments of cpufreq_update_util().
In turn, if util is not frequency-invariant, the maximum frequency in
the above formula is replaced with the current frequency of the CPU:

	next_freq = 1.25 * curr_freq * util / max

The coefficient 1.25 corresponds to the frequency tipping point at
(util / max) = 0.8.

All of the computations are carried out in the utilization update
handlers provided by the new governor.  One of those handlers is
used for cpufreq policies shared between multiple CPUs and the other
one is for policies with one CPU only (and therefore it doesn't need
to use any extra synchronization means).

The governor supports fast frequency switching if that is supported
by the cpufreq driver in use and possible for the given policy.
In the fast switching case, all operations of the governor take
place in its utilization update handlers.  If fast switching cannot
be used, the frequency switch operations are carried out with the
help of a work item which only calls __cpufreq_driver_target()
(under a mutex) to trigger a frequency update (to a value already
computed beforehand in one of the utilization update handlers).

Currently, the governor treats all of the RT and DL tasks as
"unknown utilization" and sets the frequency to the allowed
maximum when updated from the RT or DL sched classes.  That
heavy-handed approach should be replaced with something more
subtle and specifically targeted at RT and DL tasks.

The governor shares some tunables management code with the
"ondemand" and "conservative" governors and uses some common
definitions from cpufreq_governor.h, but apart from that it
is stand-alone.

Change-Id: I03876e622768e4b3ee4dc28682af7cce771f2f4c
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
(cherry-picked from 9bdcb44e391da5c41b98573bf0305a0e0b1c9569)
[ Backport the schedutil cpufreq governor from 4.9. Some cpufreq
  tunable infrastructure as well as the resolve_freq API is also
  backported as those are dependencies]
Signed-off-by: Steve Muckle <smuckle@linaro.org>
[trivial cherry-picking fixes]
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
[fixed default governor machinery]
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

1 files changed, 601 insertions, 0 deletions

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
new file mode 100644
index 000000000000..7e42a1d6d88d
--- /dev/null
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -0,0 +1,601 @@
+/*
+ * CPUFreq governor based on scheduler-provided CPU utilization data.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/slab.h>
+#include <trace/events/power.h>
+
+#include "sched.h"
+
+/* Stub out fast switch routines present on mainline to reduce the backport
+ * overhead. */
+#define cpufreq_driver_fast_switch(x, y) 0
+#define cpufreq_enable_fast_switch(x)
+#define cpufreq_disable_fast_switch(x)
+
+struct sugov_tunables {
+	struct gov_attr_set attr_set;
+	unsigned int rate_limit_us;
+};
+
+struct sugov_policy {
+	struct cpufreq_policy *policy;
+
+	struct sugov_tunables *tunables;
+	struct list_head tunables_hook;
+
+	raw_spinlock_t update_lock;  /* For shared policies */
+	u64 last_freq_update_time;
+	s64 freq_update_delay_ns;
+	unsigned int next_freq;
+
+	/* The next fields are only needed if fast switch cannot be used. */
+	struct irq_work irq_work;
+	struct work_struct work;
+	struct mutex work_lock;
+	bool work_in_progress;
+
+	bool need_freq_update;
+};
+
+struct sugov_cpu {
+	struct update_util_data update_util;
+	struct sugov_policy *sg_policy;
+
+	unsigned int cached_raw_freq;
+	unsigned long iowait_boost;
+	unsigned long iowait_boost_max;
+	u64 last_update;
+
+	/* The fields below are only needed when sharing a policy. */
+	unsigned long util;
+	unsigned long max;
+	unsigned int flags;
+};
+
+static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
+
+/************************ Governor internals ***********************/
+
+static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
+{
+	s64 delta_ns;
+
+	if (sg_policy->work_in_progress)
+		return false;
+
+	if (unlikely(sg_policy->need_freq_update)) {
+		sg_policy->need_freq_update = false;
+		/*
+		 * This happens when limits change, so forget the previous
+		 * next_freq value and force an update.
+		 */
+		sg_policy->next_freq = UINT_MAX;
+		return true;
+	}
+
+	delta_ns = time - sg_policy->last_freq_update_time;
+	return delta_ns >= sg_policy->freq_update_delay_ns;
+}
+
+static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
+				unsigned int next_freq)
+{
+	struct cpufreq_policy *policy = sg_policy->policy;
+
+	sg_policy->last_freq_update_time = time;
+
+	if (policy->fast_switch_enabled) {
+		if (sg_policy->next_freq == next_freq) {
+			trace_cpu_frequency(policy->cur, smp_processor_id());
+			return;
+		}
+		sg_policy->next_freq = next_freq;
+		next_freq = cpufreq_driver_fast_switch(policy, next_freq);
+		if (next_freq == CPUFREQ_ENTRY_INVALID)
+			return;
+
+		policy->cur = next_freq;
+		trace_cpu_frequency(next_freq, smp_processor_id());
+	} else if (sg_policy->next_freq != next_freq) {
+		sg_policy->next_freq = next_freq;
+		sg_policy->work_in_progress = true;
+		irq_work_queue(&sg_policy->irq_work);
+	}
+}
+
+/**
+ * get_next_freq - Compute a new frequency for a given cpufreq policy.
+ * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @util: Current CPU utilization.
+ * @max: CPU capacity.
+ *
+ * If the utilization is frequency-invariant, choose the new frequency to be
+ * proportional to it, that is
+ *
+ * next_freq = C * max_freq * util / max
+ *
+ * Otherwise, approximate the would-be frequency-invariant utilization by
+ * util_raw * (curr_freq / max_freq) which leads to
+ *
+ * next_freq = C * curr_freq * util_raw / max
+ *
+ * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
+ *
+ * The lowest driver-supported frequency which is equal or greater than the raw
+ * next_freq (as calculated above) is returned, subject to policy min/max and
+ * cpufreq driver limitations.
+ */
+static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
+				  unsigned long max)
+{
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	struct cpufreq_policy *policy = sg_policy->policy;
+	unsigned int freq = arch_scale_freq_invariant() ?
+				policy->cpuinfo.max_freq : policy->cur;
+
+	freq = (freq + (freq >> 2)) * util / max;
+
+	if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+		return sg_policy->next_freq;
+	sg_cpu->cached_raw_freq = freq;
+	return cpufreq_driver_resolve_freq(policy, freq);
+}
+
+static void sugov_get_util(unsigned long *util, unsigned long *max)
+{
+	struct rq *rq = this_rq();
+	unsigned long cfs_max;
+
+	cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+
+	*util = min(rq->cfs.avg.util_avg, cfs_max);
+	*max = cfs_max;
+}
+
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+				   unsigned int flags)
+{
+	if (flags & SCHED_CPUFREQ_IOWAIT) {
+		sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+	} else if (sg_cpu->iowait_boost) {
+		s64 delta_ns = time - sg_cpu->last_update;
+
+		/* Clear iowait_boost if the CPU apprears to have been idle. */
+		if (delta_ns > TICK_NSEC)
+			sg_cpu->iowait_boost = 0;
+	}
+}
+
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
+			       unsigned long *max)
+{
+	unsigned long boost_util = sg_cpu->iowait_boost;
+	unsigned long boost_max = sg_cpu->iowait_boost_max;
+
+	if (!boost_util)
+		return;
+
+	if (*util * boost_max < *max * boost_util) {
+		*util = boost_util;
+		*max = boost_max;
+	}
+	sg_cpu->iowait_boost >>= 1;
+}
+
+static void sugov_update_single(struct update_util_data *hook, u64 time,
+				unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	struct cpufreq_policy *policy = sg_policy->policy;
+	unsigned long util, max;
+	unsigned int next_f;
+
+	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sg_cpu->last_update = time;
+
+	if (!sugov_should_update_freq(sg_policy, time))
+		return;
+
+	if (flags & SCHED_CPUFREQ_RT_DL) {
+		next_f = policy->cpuinfo.max_freq;
+	} else {
+		sugov_get_util(&util, &max);
+		sugov_iowait_boost(sg_cpu, &util, &max);
+		next_f = get_next_freq(sg_cpu, util, max);
+	}
+	sugov_update_commit(sg_policy, time, next_f);
+}
+
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
+					   unsigned long util, unsigned long max,
+					   unsigned int flags)
+{
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	struct cpufreq_policy *policy = sg_policy->policy;
+	unsigned int max_f = policy->cpuinfo.max_freq;
+	u64 last_freq_update_time = sg_policy->last_freq_update_time;
+	unsigned int j;
+
+	if (flags & SCHED_CPUFREQ_RT_DL)
+		return max_f;
+
+	sugov_iowait_boost(sg_cpu, &util, &max);
+
+	for_each_cpu(j, policy->cpus) {
+		struct sugov_cpu *j_sg_cpu;
+		unsigned long j_util, j_max;
+		s64 delta_ns;
+
+		if (j == smp_processor_id())
+			continue;
+
+		j_sg_cpu = &per_cpu(sugov_cpu, j);
+		/*
+		 * If the CPU utilization was last updated before the previous
+		 * frequency update and the time elapsed between the last update
+		 * of the CPU utilization and the last frequency update is long
+		 * enough, don't take the CPU into account as it probably is
+		 * idle now (and clear iowait_boost for it).
+		 */
+		delta_ns = last_freq_update_time - j_sg_cpu->last_update;
+		if (delta_ns > TICK_NSEC) {
+			j_sg_cpu->iowait_boost = 0;
+			continue;
+		}
+		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
+			return max_f;
+
+		j_util = j_sg_cpu->util;
+		j_max = j_sg_cpu->max;
+		if (j_util * max > j_max * util) {
+			util = j_util;
+			max = j_max;
+		}
+
+		sugov_iowait_boost(j_sg_cpu, &util, &max);
+	}
+
+	return get_next_freq(sg_cpu, util, max);
+}
+
+static void sugov_update_shared(struct update_util_data *hook, u64 time,
+				unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned long util, max;
+	unsigned int next_f;
+
+	sugov_get_util(&util, &max);
+
+	raw_spin_lock(&sg_policy->update_lock);
+
+	sg_cpu->util = util;
+	sg_cpu->max = max;
+	sg_cpu->flags = flags;
+
+	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sg_cpu->last_update = time;
+
+	if (sugov_should_update_freq(sg_policy, time)) {
+		next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
+		sugov_update_commit(sg_policy, time, next_f);
+	}
+
+	raw_spin_unlock(&sg_policy->update_lock);
+}
+
+static void sugov_work(struct work_struct *work)
+{
+	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
+
+	mutex_lock(&sg_policy->work_lock);
+	__cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
+				CPUFREQ_RELATION_L);
+	mutex_unlock(&sg_policy->work_lock);
+
+	sg_policy->work_in_progress = false;
+}
+
+static void sugov_irq_work(struct irq_work *irq_work)
+{
+	struct sugov_policy *sg_policy;
+
+	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
+	schedule_work_on(smp_processor_id(), &sg_policy->work);
+}
+
+/************************** sysfs interface ************************/
+
+static struct sugov_tunables *global_tunables;
+static DEFINE_MUTEX(global_tunables_lock);
+
+static inline struct sugov_tunables *to_sugov_tunables(struct gov_attr_set *attr_set)
+{
+	return container_of(attr_set, struct sugov_tunables, attr_set);
+}
+
+static ssize_t rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
+{
+	struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+
+	return sprintf(buf, "%u\n", tunables->rate_limit_us);
+}
+
+static ssize_t rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf,
+				   size_t count)
+{
+	struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+	struct sugov_policy *sg_policy;
+	unsigned int rate_limit_us;
+
+	if (kstrtouint(buf, 10, &rate_limit_us))
+		return -EINVAL;
+
+	tunables->rate_limit_us = rate_limit_us;
+
+	list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook)
+		sg_policy->freq_update_delay_ns = rate_limit_us * NSEC_PER_USEC;
+
+	return count;
+}
+
+static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us);
+
+static struct attribute *sugov_attributes[] = {
+	&rate_limit_us.attr,
+	NULL
+};
+
+static struct kobj_type sugov_tunables_ktype = {
+	.default_attrs = sugov_attributes,
+	.sysfs_ops = &governor_sysfs_ops,
+};
+
+/********************** cpufreq governor interface *********************/
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+static
+#endif
+struct cpufreq_governor cpufreq_gov_schedutil;
+
+static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy;
+
+	sg_policy = kzalloc(sizeof(*sg_policy), GFP_KERNEL);
+	if (!sg_policy)
+		return NULL;
+
+	sg_policy->policy = policy;
+	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
+	INIT_WORK(&sg_policy->work, sugov_work);
+	mutex_init(&sg_policy->work_lock);
+	raw_spin_lock_init(&sg_policy->update_lock);
+	return sg_policy;
+}
+
+static void sugov_policy_free(struct sugov_policy *sg_policy)
+{
+	mutex_destroy(&sg_policy->work_lock);
+	kfree(sg_policy);
+}
+
+static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
+{
+	struct sugov_tunables *tunables;
+
+	tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
+	if (tunables) {
+		gov_attr_set_init(&tunables->attr_set, &sg_policy->tunables_hook);
+		if (!have_governor_per_policy())
+			global_tunables = tunables;
+	}
+	return tunables;
+}
+
+static void sugov_tunables_free(struct sugov_tunables *tunables)
+{
+	if (!have_governor_per_policy())
+		global_tunables = NULL;
+
+	kfree(tunables);
+}
+
+static int sugov_init(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy;
+	struct sugov_tunables *tunables;
+	unsigned int lat;
+	int ret = 0;
+
+	/* State should be equivalent to EXIT */
+	if (policy->governor_data)
+		return -EBUSY;
+
+	sg_policy = sugov_policy_alloc(policy);
+	if (!sg_policy)
+		return -ENOMEM;
+
+	mutex_lock(&global_tunables_lock);
+
+	if (global_tunables) {
+		if (WARN_ON(have_governor_per_policy())) {
+			ret = -EINVAL;
+			goto free_sg_policy;
+		}
+		policy->governor_data = sg_policy;
+		sg_policy->tunables = global_tunables;
+
+		gov_attr_set_get(&global_tunables->attr_set, &sg_policy->tunables_hook);
+		goto out;
+	}
+
+	tunables = sugov_tunables_alloc(sg_policy);
+	if (!tunables) {
+		ret = -ENOMEM;
+		goto free_sg_policy;
+	}
+
+	tunables->rate_limit_us = 20 * USEC_PER_MSEC;
+	lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+	if (lat)
+		tunables->rate_limit_us *= lat;
+
+	policy->governor_data = sg_policy;
+	sg_policy->tunables = tunables;
+
+	ret = kobject_init_and_add(&tunables->attr_set.kobj, &sugov_tunables_ktype,
+				   get_governor_parent_kobj(policy), "%s",
+				   cpufreq_gov_schedutil.name);
+	if (ret)
+		goto fail;
+
+ out:
+	mutex_unlock(&global_tunables_lock);
+
+	cpufreq_enable_fast_switch(policy);
+	return 0;
+
+ fail:
+	policy->governor_data = NULL;
+	sugov_tunables_free(tunables);
+
+ free_sg_policy:
+	mutex_unlock(&global_tunables_lock);
+
+	sugov_policy_free(sg_policy);
+	pr_err("initialization failed (error %d)\n", ret);
+	return ret;
+}
+
+static int sugov_exit(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy = policy->governor_data;
+	struct sugov_tunables *tunables = sg_policy->tunables;
+	unsigned int count;
+
+	cpufreq_disable_fast_switch(policy);
+
+	mutex_lock(&global_tunables_lock);
+
+	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
+	policy->governor_data = NULL;
+	if (!count)
+		sugov_tunables_free(tunables);
+
+	mutex_unlock(&global_tunables_lock);
+
+	sugov_policy_free(sg_policy);
+
+	return 0;
+}
+
+static int sugov_start(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy = policy->governor_data;
+	unsigned int cpu;
+
+	sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
+	sg_policy->last_freq_update_time = 0;
+	sg_policy->next_freq = UINT_MAX;
+	sg_policy->work_in_progress = false;
+	sg_policy->need_freq_update = false;
+
+	for_each_cpu(cpu, policy->cpus) {
+		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
+
+		sg_cpu->sg_policy = sg_policy;
+		if (policy_is_shared(policy)) {
+			sg_cpu->util = 0;
+			sg_cpu->max = 0;
+			sg_cpu->flags = SCHED_CPUFREQ_RT;
+			sg_cpu->last_update = 0;
+			sg_cpu->cached_raw_freq = 0;
+			sg_cpu->iowait_boost = 0;
+			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+						     sugov_update_shared);
+		} else {
+			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+						     sugov_update_single);
+		}
+	}
+	return 0;
+}
+
+static int sugov_stop(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy = policy->governor_data;
+	unsigned int cpu;
+
+	for_each_cpu(cpu, policy->cpus)
+		cpufreq_remove_update_util_hook(cpu);
+
+	synchronize_sched();
+
+	irq_work_sync(&sg_policy->irq_work);
+	cancel_work_sync(&sg_policy->work);
+
+	return 0;
+}
+
+static int sugov_limits(struct cpufreq_policy *policy)
+{
+	struct sugov_policy *sg_policy = policy->governor_data;
+
+	if (!policy->fast_switch_enabled) {
+		mutex_lock(&sg_policy->work_lock);
+		cpufreq_policy_apply_limits(policy);
+		mutex_unlock(&sg_policy->work_lock);
+	}
+
+	sg_policy->need_freq_update = true;
+
+	return 0;
+}
+
+static int cpufreq_schedutil_cb(struct cpufreq_policy *policy,
+				unsigned int event)
+{
+	switch(event) {
+	case CPUFREQ_GOV_POLICY_INIT:
+		return sugov_init(policy);
+	case CPUFREQ_GOV_POLICY_EXIT:
+		return sugov_exit(policy);
+	case CPUFREQ_GOV_START:
+		return sugov_start(policy);
+	case CPUFREQ_GOV_STOP:
+		return sugov_stop(policy);
+	case CPUFREQ_GOV_LIMITS:
+		return sugov_limits(policy);
+	default:
+		BUG();
+	}
+}
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+static
+#endif
+struct cpufreq_governor cpufreq_gov_schedutil = {
+	.name = "schedutil",
+	.governor = cpufreq_schedutil_cb,
+	.owner = THIS_MODULE,
+};
+
+static int __init sugov_register(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_schedutil);
+}
+fs_initcall(sugov_register);