/*
 * 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/kthread.h>
#include <uapi/linux/sched/types.h>
#include <linux/slab.h>
#include <trace/events/power.h>

#include "sched.h"

#define SUGOV_KTHREAD_PRIORITY	50

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;
	unsigned int cached_raw_freq;

	/* The next fields are only needed if fast switch cannot be used. */
	struct irq_work irq_work;
	struct kthread_work work;
	struct mutex work_lock;
	struct kthread_worker worker;
	struct task_struct *thread;
	bool work_in_progress;

	bool need_freq_update;
};

struct sugov_cpu {
	struct update_util_data update_util;
	struct sugov_policy *sg_policy;
	unsigned int cpu;

	bool iowait_boost_pending;
	unsigned int iowait_boost;
	unsigned int iowait_boost_max;
	u64 last_update;

	/* The fields below are only needed when sharing a policy. */
	unsigned long util_cfs;
	unsigned long util_dl;
	unsigned long max;
	unsigned int flags;

	/* The field below is for single-CPU policies only. */
#ifdef CONFIG_NO_HZ_COMMON
	unsigned long saved_idle_calls;
#endif
};

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;

	/*
	 * Since cpufreq_update_util() is called with rq->lock held for
	 * the @target_cpu, our per-cpu data is fully serialized.
	 *
	 * However, drivers cannot in general deal with cross-cpu
	 * requests, so while get_next_freq() will work, our
	 * sugov_update_commit() call may not for the fast switching platforms.
	 *
	 * Hence stop here for remote requests if they aren't supported
	 * by the hardware, as calculating the frequency is pointless if
	 * we cannot in fact act on it.
	 *
	 * For the slow switching platforms, the kthread is always scheduled on
	 * the right set of CPUs and any CPU can find the next frequency and
	 * schedule the kthread.
	 */
	if (sg_policy->policy->fast_switch_enabled &&
	    !cpufreq_can_do_remote_dvfs(sg_policy->policy))
		return false;

	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;

	if (sg_policy->next_freq == next_freq)
		return;

	sg_policy->next_freq = next_freq;
	sg_policy->last_freq_update_time = time;

	if (policy->fast_switch_enabled) {
		next_freq = cpufreq_driver_fast_switch(policy, next_freq);
		if (!next_freq)
			return;

		policy->cur = next_freq;
		trace_cpu_frequency(next_freq, smp_processor_id());
	} else {
		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_policy: schedutil policy 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_policy *sg_policy,
				  unsigned long util, unsigned long max)
{
	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_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
		return sg_policy->next_freq;
	sg_policy->cached_raw_freq = freq;
	return cpufreq_driver_resolve_freq(policy, freq);
}

static void sugov_get_util(struct sugov_cpu *sg_cpu)
{
	struct rq *rq = cpu_rq(sg_cpu->cpu);

	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
	sg_cpu->util_cfs = cpu_util_cfs(rq);
	sg_cpu->util_dl  = cpu_util_dl(rq);
}

static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
{
	/*
	 * Ideally we would like to set util_dl as min/guaranteed freq and
	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
	 * ready for such an interface. So, we only do the latter for now.
	 */
	return min(sg_cpu->util_cfs + sg_cpu->util_dl, sg_cpu->max);
}

static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time)
{
	if (sg_cpu->flags & SCHED_CPUFREQ_IOWAIT) {
		if (sg_cpu->iowait_boost_pending)
			return;

		sg_cpu->iowait_boost_pending = true;

		if (sg_cpu->iowait_boost) {
			sg_cpu->iowait_boost <<= 1;
			if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
				sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
		} else {
			sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
		}
	} 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;
			sg_cpu->iowait_boost_pending = false;
		}
	}
}

static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
			       unsigned long *max)
{
	unsigned int boost_util, boost_max;

	if (!sg_cpu->iowait_boost)
		return;

	if (sg_cpu->iowait_boost_pending) {
		sg_cpu->iowait_boost_pending = false;
	} else {
		sg_cpu->iowait_boost >>= 1;
		if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
			sg_cpu->iowait_boost = 0;
			return;
		}
	}

	boost_util = sg_cpu->iowait_boost;
	boost_max = sg_cpu->iowait_boost_max;

	if (*util * boost_max < *max * boost_util) {
		*util = boost_util;
		*max = boost_max;
	}
}

#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
	unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
	bool ret = idle_calls == sg_cpu->saved_idle_calls;

	sg_cpu->saved_idle_calls = idle_calls;
	return ret;
}
#else
static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
#endif /* CONFIG_NO_HZ_COMMON */

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;
	bool busy;

	sugov_set_iowait_boost(sg_cpu, time);
	sg_cpu->last_update = time;

	if (!sugov_should_update_freq(sg_policy, time))
		return;

	busy = sugov_cpu_is_busy(sg_cpu);

	if (flags & SCHED_CPUFREQ_RT) {
		next_f = policy->cpuinfo.max_freq;
	} else {
		sugov_get_util(sg_cpu);
		max = sg_cpu->max;
		util = sugov_aggregate_util(sg_cpu);
		sugov_iowait_boost(sg_cpu, &util, &max);
		next_f = get_next_freq(sg_policy, util, max);
		/*
		 * Do not reduce the frequency if the CPU has not been idle
		 * recently, as the reduction is likely to be premature then.
		 */
		if (busy && next_f < sg_policy->next_freq) {
			next_f = sg_policy->next_freq;

			/* Reset cached freq as next_freq has changed */
			sg_policy->cached_raw_freq = 0;
		}
	}
	sugov_update_commit(sg_policy, time, next_f);
}

static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
{
	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
	struct cpufreq_policy *policy = sg_policy->policy;
	unsigned long util = 0, max = 1;
	unsigned int j;

	for_each_cpu(j, policy->cpus) {
		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
		unsigned long j_util, j_max;
		s64 delta_ns;

		/*
		 * If the CFS 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, reset iowait_boost and util_cfs, as
		 * they are now probably stale. However, still consider the
		 * CPU contribution if it has some DEADLINE utilization
		 * (util_dl).
		 */
		delta_ns = time - j_sg_cpu->last_update;
		if (delta_ns > TICK_NSEC) {
			j_sg_cpu->iowait_boost = 0;
			j_sg_cpu->iowait_boost_pending = false;
			j_sg_cpu->util_cfs = 0;
			if (j_sg_cpu->util_dl == 0)
				continue;
		}
		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT)
			return policy->cpuinfo.max_freq;

		j_max = j_sg_cpu->max;
		j_util = sugov_aggregate_util(j_sg_cpu);
		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_policy, 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 int next_f;

	raw_spin_lock(&sg_policy->update_lock);

	sugov_get_util(sg_cpu);
	sg_cpu->flags = flags;

	sugov_set_iowait_boost(sg_cpu, time);
	sg_cpu->last_update = time;

	if (sugov_should_update_freq(sg_policy, time)) {
		if (flags & SCHED_CPUFREQ_RT)
			next_f = sg_policy->policy->cpuinfo.max_freq;
		else
			next_f = sugov_next_freq_shared(sg_cpu, time);

		sugov_update_commit(sg_policy, time, next_f);
	}

	raw_spin_unlock(&sg_policy->update_lock);
}

static void sugov_work(struct kthread_work *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);

	/*
	 * For RT tasks, the schedutil governor shoots the frequency to maximum.
	 * Special care must be taken to ensure that this kthread doesn't result
	 * in the same behavior.
	 *
	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
	 * updated only at the end of the sugov_work() function and before that
	 * the schedutil governor rejects all other frequency scaling requests.
	 *
	 * There is a very rare case though, where the RT thread yields right
	 * after the work_in_progress flag is cleared. The effects of that are
	 * neglected for now.
	 */
	kthread_queue_work(&sg_policy->worker, &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 *********************/

static struct cpufreq_governor schedutil_gov;

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;
	raw_spin_lock_init(&sg_policy->update_lock);
	return sg_policy;
}

static void sugov_policy_free(struct sugov_policy *sg_policy)
{
	kfree(sg_policy);
}

static int sugov_kthread_create(struct sugov_policy *sg_policy)
{
	struct task_struct *thread;
	struct sched_attr attr = {
		.size = sizeof(struct sched_attr),
		.sched_policy = SCHED_DEADLINE,
		.sched_flags = SCHED_FLAG_SUGOV,
		.sched_nice = 0,
		.sched_priority = 0,
		/*
		 * Fake (unused) bandwidth; workaround to "fix"
		 * priority inheritance.
		 */
		.sched_runtime	=  1000000,
		.sched_deadline = 10000000,
		.sched_period	= 10000000,
	};
	struct cpufreq_policy *policy = sg_policy->policy;
	int ret;

	/* kthread only required for slow path */
	if (policy->fast_switch_enabled)
		return 0;

	kthread_init_work(&sg_policy->work, sugov_work);
	kthread_init_worker(&sg_policy->worker);
	thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
				"sugov:%d",
				cpumask_first(policy->related_cpus));
	if (IS_ERR(thread)) {
		pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
		return PTR_ERR(thread);
	}

	ret = sched_setattr_nocheck(thread, &attr);
	if (ret) {
		kthread_stop(thread);
		pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
		return ret;
	}

	sg_policy->thread = thread;

	/* Kthread is bound to all CPUs by default */
	if (!policy->dvfs_possible_from_any_cpu)
		kthread_bind_mask(thread, policy->related_cpus);

	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
	mutex_init(&sg_policy->work_lock);

	wake_up_process(thread);

	return 0;
}

static void sugov_kthread_stop(struct sugov_policy *sg_policy)
{
	/* kthread only required for slow path */
	if (sg_policy->policy->fast_switch_enabled)
		return;

	kthread_flush_worker(&sg_policy->worker);
	kthread_stop(sg_policy->thread);
	mutex_destroy(&sg_policy->work_lock);
}

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;
	int ret = 0;

	/* State should be equivalent to EXIT */
	if (policy->governor_data)
		return -EBUSY;

	cpufreq_enable_fast_switch(policy);

	sg_policy = sugov_policy_alloc(policy);
	if (!sg_policy) {
		ret = -ENOMEM;
		goto disable_fast_switch;
	}

	ret = sugov_kthread_create(sg_policy);
	if (ret)
		goto free_sg_policy;

	mutex_lock(&global_tunables_lock);

	if (global_tunables) {
		if (WARN_ON(have_governor_per_policy())) {
			ret = -EINVAL;
			goto stop_kthread;
		}
		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 stop_kthread;
	}

	tunables->rate_limit_us = cpufreq_policy_transition_delay_us(policy);

	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",
				   schedutil_gov.name);
	if (ret)
		goto fail;

out:
	mutex_unlock(&global_tunables_lock);
	return 0;

fail:
	policy->governor_data = NULL;
	sugov_tunables_free(tunables);

stop_kthread:
	sugov_kthread_stop(sg_policy);

free_sg_policy:
	mutex_unlock(&global_tunables_lock);

	sugov_policy_free(sg_policy);

disable_fast_switch:
	cpufreq_disable_fast_switch(policy);

	pr_err("initialization failed (error %d)\n", ret);
	return ret;
}

static void sugov_exit(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy = policy->governor_data;
	struct sugov_tunables *tunables = sg_policy->tunables;
	unsigned int count;

	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_kthread_stop(sg_policy);
	sugov_policy_free(sg_policy);
	cpufreq_disable_fast_switch(policy);
}

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;
	sg_policy->cached_raw_freq = 0;

	for_each_cpu(cpu, policy->cpus) {
		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);

		memset(sg_cpu, 0, sizeof(*sg_cpu));
		sg_cpu->cpu = cpu;
		sg_cpu->sg_policy = sg_policy;
		sg_cpu->flags = 0;
		sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
	}

	for_each_cpu(cpu, policy->cpus) {
		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);

		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
					     policy_is_shared(policy) ?
							sugov_update_shared :
							sugov_update_single);
	}
	return 0;
}

static void 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();

	if (!policy->fast_switch_enabled) {
		irq_work_sync(&sg_policy->irq_work);
		kthread_cancel_work_sync(&sg_policy->work);
	}
}

static void 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;
}

static struct cpufreq_governor schedutil_gov = {
	.name = "schedutil",
	.owner = THIS_MODULE,
	.dynamic_switching = true,
	.init = sugov_init,
	.exit = sugov_exit,
	.start = sugov_start,
	.stop = sugov_stop,
	.limits = sugov_limits,
};

#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
struct cpufreq_governor *cpufreq_default_governor(void)
{
	return &schedutil_gov;
}
#endif

static int __init sugov_register(void)
{
	return cpufreq_register_governor(&schedutil_gov);
}
fs_initcall(sugov_register);