/*
 *  drivers/cpufreq/cpufreq_ondemand.c
 *
 *  Copyright (C)  2001 Russell King
 *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
 *                      Jun Nakajima <jun.nakajima@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.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/cpu.h>
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/mutex.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/ktime.h>
#include <linux/sched.h>

/*
 * dbs is used in this file as a shortform for demandbased switching
 * It helps to keep variable names smaller, simpler
 */

#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
#define DEF_FREQUENCY_UP_THRESHOLD		(80)
#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
#define MICRO_FREQUENCY_UP_THRESHOLD		(95)
#define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
#define MIN_FREQUENCY_UP_THRESHOLD		(11)
#define MAX_FREQUENCY_UP_THRESHOLD		(100)

/*
 * The polling frequency of this governor depends on the capability of
 * the processor. Default polling frequency is 1000 times the transition
 * latency of the processor. The governor will work on any processor with
 * transition latency <= 10mS, using appropriate sampling
 * rate.
 * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
 * this governor will not work.
 * All times here are in uS.
 */
#define MIN_SAMPLING_RATE_RATIO			(2)

static unsigned int min_sampling_rate;

#define LATENCY_MULTIPLIER			(1000)
#define MIN_LATENCY_MULTIPLIER			(100)
#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)

static void do_dbs_timer(struct work_struct *work);

/* Sampling types */
enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};

struct cpu_dbs_info_s {
	cputime64_t prev_cpu_idle;
	cputime64_t prev_cpu_wall;
	cputime64_t prev_cpu_nice;
	struct cpufreq_policy *cur_policy;
	struct delayed_work work;
	struct cpufreq_frequency_table *freq_table;
	unsigned int freq_lo;
	unsigned int freq_lo_jiffies;
	unsigned int freq_hi_jiffies;
	int cpu;
	unsigned int enable:1,
		sample_type:1;
};
static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);

static unsigned int dbs_enable;	/* number of CPUs using this policy */

/*
 * DEADLOCK ALERT! There is a ordering requirement between cpu_hotplug
 * lock and dbs_mutex. cpu_hotplug lock should always be held before
 * dbs_mutex. If any function that can potentially take cpu_hotplug lock
 * (like __cpufreq_driver_target()) is being called with dbs_mutex taken, then
 * cpu_hotplug lock should be taken before that. Note that cpu_hotplug lock
 * is recursive for the same process. -Venki
 * DEADLOCK ALERT! (2) : do_dbs_timer() must not take the dbs_mutex, because it
 * would deadlock with cancel_delayed_work_sync(), which is needed for proper
 * raceless workqueue teardown.
 */
static DEFINE_MUTEX(dbs_mutex);

static struct workqueue_struct	*kondemand_wq;

static struct dbs_tuners {
	unsigned int sampling_rate;
	unsigned int up_threshold;
	unsigned int down_differential;
	unsigned int ignore_nice;
	unsigned int powersave_bias;
} dbs_tuners_ins = {
	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
	.ignore_nice = 0,
	.powersave_bias = 0,
};

static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
							cputime64_t *wall)
{
	cputime64_t idle_time;
	cputime64_t cur_wall_time;
	cputime64_t busy_time;

	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
	busy_time = cputime64_add(kstat_cpu(cpu).cpustat.user,
			kstat_cpu(cpu).cpustat.system);

	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.nice);

	idle_time = cputime64_sub(cur_wall_time, busy_time);
	if (wall)
		*wall = cur_wall_time;

	return idle_time;
}

static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
{
	u64 idle_time = get_cpu_idle_time_us(cpu, wall);

	if (idle_time == -1ULL)
		return get_cpu_idle_time_jiffy(cpu, wall);

	return idle_time;
}

/*
 * Find right freq to be set now with powersave_bias on.
 * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
 * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
 */
static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
					  unsigned int freq_next,
					  unsigned int relation)
{
	unsigned int freq_req, freq_reduc, freq_avg;
	unsigned int freq_hi, freq_lo;
	unsigned int index = 0;
	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
	struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, policy->cpu);

	if (!dbs_info->freq_table) {
		dbs_info->freq_lo = 0;
		dbs_info->freq_lo_jiffies = 0;
		return freq_next;
	}

	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
			relation, &index);
	freq_req = dbs_info->freq_table[index].frequency;
	freq_reduc = freq_req * dbs_tuners_ins.powersave_bias / 1000;
	freq_avg = freq_req - freq_reduc;

	/* Find freq bounds for freq_avg in freq_table */
	index = 0;
	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
			CPUFREQ_RELATION_H, &index);
	freq_lo = dbs_info->freq_table[index].frequency;
	index = 0;
	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
			CPUFREQ_RELATION_L, &index);
	freq_hi = dbs_info->freq_table[index].frequency;

	/* Find out how long we have to be in hi and lo freqs */
	if (freq_hi == freq_lo) {
		dbs_info->freq_lo = 0;
		dbs_info->freq_lo_jiffies = 0;
		return freq_lo;
	}
	jiffies_total = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
	jiffies_hi += ((freq_hi - freq_lo) / 2);
	jiffies_hi /= (freq_hi - freq_lo);
	jiffies_lo = jiffies_total - jiffies_hi;
	dbs_info->freq_lo = freq_lo;
	dbs_info->freq_lo_jiffies = jiffies_lo;
	dbs_info->freq_hi_jiffies = jiffies_hi;
	return freq_hi;
}

static void ondemand_powersave_bias_init(void)
{
	int i;
	for_each_online_cpu(i) {
		struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, i);
		dbs_info->freq_table = cpufreq_frequency_get_table(i);
		dbs_info->freq_lo = 0;
	}
}

/************************** sysfs interface ************************/
static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
{
	printk_once(KERN_INFO "CPUFREQ: ondemand sampling_rate_max "
	       "sysfs file is deprecated - used by: %s\n", current->comm);
	return sprintf(buf, "%u\n", -1U);
}

static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
{
	return sprintf(buf, "%u\n", min_sampling_rate);
}

#define define_one_ro(_name)		\
static struct freq_attr _name =		\
__ATTR(_name, 0444, show_##_name, NULL)

define_one_ro(sampling_rate_max);
define_one_ro(sampling_rate_min);

/* cpufreq_ondemand Governor Tunables */
#define show_one(file_name, object)					\
static ssize_t show_##file_name						\
(struct cpufreq_policy *unused, char *buf)				\
{									\
	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
}
show_one(sampling_rate, sampling_rate);
show_one(up_threshold, up_threshold);
show_one(ignore_nice_load, ignore_nice);
show_one(powersave_bias, powersave_bias);

static ssize_t store_sampling_rate(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);

	mutex_lock(&dbs_mutex);
	if (ret != 1) {
		mutex_unlock(&dbs_mutex);
		return -EINVAL;
	}
	dbs_tuners_ins.sampling_rate = max(input, min_sampling_rate);
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_up_threshold(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);

	mutex_lock(&dbs_mutex);
	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD ||
			input < MIN_FREQUENCY_UP_THRESHOLD) {
		mutex_unlock(&dbs_mutex);
		return -EINVAL;
	}

	dbs_tuners_ins.up_threshold = input;
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	unsigned int j;

	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;

	if (input > 1)
		input = 1;

	mutex_lock(&dbs_mutex);
	if (input == dbs_tuners_ins.ignore_nice) { /* nothing to do */
		mutex_unlock(&dbs_mutex);
		return count;
	}
	dbs_tuners_ins.ignore_nice = input;

	/* we need to re-evaluate prev_cpu_idle */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *dbs_info;
		dbs_info = &per_cpu(cpu_dbs_info, j);
		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
						&dbs_info->prev_cpu_wall);
		if (dbs_tuners_ins.ignore_nice)
			dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;

	}
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_powersave_bias(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);

	if (ret != 1)
		return -EINVAL;

	if (input > 1000)
		input = 1000;

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.powersave_bias = input;
	ondemand_powersave_bias_init();
	mutex_unlock(&dbs_mutex);

	return count;
}

#define define_one_rw(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)

define_one_rw(sampling_rate);
define_one_rw(up_threshold);
define_one_rw(ignore_nice_load);
define_one_rw(powersave_bias);

static struct attribute *dbs_attributes[] = {
	&sampling_rate_max.attr,
	&sampling_rate_min.attr,
	&sampling_rate.attr,
	&up_threshold.attr,
	&ignore_nice_load.attr,
	&powersave_bias.attr,
	NULL
};

static struct attribute_group dbs_attr_group = {
	.attrs = dbs_attributes,
	.name = "ondemand",
};

/************************** sysfs end ************************/

static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
{
	unsigned int max_load_freq;

	struct cpufreq_policy *policy;
	unsigned int j;

	if (!this_dbs_info->enable)
		return;

	this_dbs_info->freq_lo = 0;
	policy = this_dbs_info->cur_policy;

	/*
	 * Every sampling_rate, we check, if current idle time is less
	 * than 20% (default), then we try to increase frequency
	 * Every sampling_rate, we look for a the lowest
	 * frequency which can sustain the load while keeping idle time over
	 * 30%. If such a frequency exist, we try to decrease to this frequency.
	 *
	 * Any frequency increase takes it to the maximum frequency.
	 * Frequency reduction happens at minimum steps of
	 * 5% (default) of current frequency
	 */

	/* Get Absolute Load - in terms of freq */
	max_load_freq = 0;

	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info_s *j_dbs_info;
		cputime64_t cur_wall_time, cur_idle_time;
		unsigned int idle_time, wall_time;
		unsigned int load, load_freq;
		int freq_avg;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);

		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);

		wall_time = (unsigned int) cputime64_sub(cur_wall_time,
				j_dbs_info->prev_cpu_wall);
		j_dbs_info->prev_cpu_wall = cur_wall_time;

		idle_time = (unsigned int) cputime64_sub(cur_idle_time,
				j_dbs_info->prev_cpu_idle);
		j_dbs_info->prev_cpu_idle = cur_idle_time;

		if (dbs_tuners_ins.ignore_nice) {
			cputime64_t cur_nice;
			unsigned long cur_nice_jiffies;

			cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice,
					 j_dbs_info->prev_cpu_nice);
			/*
			 * Assumption: nice time between sampling periods will
			 * be less than 2^32 jiffies for 32 bit sys
			 */
			cur_nice_jiffies = (unsigned long)
					cputime64_to_jiffies64(cur_nice);

			j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
			idle_time += jiffies_to_usecs(cur_nice_jiffies);
		}

		if (unlikely(!wall_time || wall_time < idle_time))
			continue;

		load = 100 * (wall_time - idle_time) / wall_time;

		freq_avg = __cpufreq_driver_getavg(policy, j);
		if (freq_avg <= 0)
			freq_avg = policy->cur;

		load_freq = load * freq_avg;
		if (load_freq > max_load_freq)
			max_load_freq = load_freq;
	}

	/* Check for frequency increase */
	if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
		/* if we are already at full speed then break out early */
		if (!dbs_tuners_ins.powersave_bias) {
			if (policy->cur == policy->max)
				return;

			__cpufreq_driver_target(policy, policy->max,
				CPUFREQ_RELATION_H);
		} else {
			int freq = powersave_bias_target(policy, policy->max,
					CPUFREQ_RELATION_H);
			__cpufreq_driver_target(policy, freq,
				CPUFREQ_RELATION_L);
		}
		return;
	}

	/* Check for frequency decrease */
	/* if we cannot reduce the frequency anymore, break out early */
	if (policy->cur == policy->min)
		return;

	/*
	 * The optimal frequency is the frequency that is the lowest that
	 * can support the current CPU usage without triggering the up
	 * policy. To be safe, we focus 10 points under the threshold.
	 */
	if (max_load_freq <
	    (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential) *
	     policy->cur) {
		unsigned int freq_next;
		freq_next = max_load_freq /
				(dbs_tuners_ins.up_threshold -
				 dbs_tuners_ins.down_differential);

		if (!dbs_tuners_ins.powersave_bias) {
			__cpufreq_driver_target(policy, freq_next,
					CPUFREQ_RELATION_L);
		} else {
			int freq = powersave_bias_target(policy, freq_next,
					CPUFREQ_RELATION_L);
			__cpufreq_driver_target(policy, freq,
				CPUFREQ_RELATION_L);
		}
	}
}

static void do_dbs_timer(struct work_struct *work)
{
	struct cpu_dbs_info_s *dbs_info =
		container_of(work, struct cpu_dbs_info_s, work.work);
	unsigned int cpu = dbs_info->cpu;
	int sample_type = dbs_info->sample_type;

	/* We want all CPUs to do sampling nearly on same jiffy */
	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);

	delay -= jiffies % delay;

	if (lock_policy_rwsem_write(cpu) < 0)
		return;

	if (!dbs_info->enable) {
		unlock_policy_rwsem_write(cpu);
		return;
	}

	/* Common NORMAL_SAMPLE setup */
	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
	if (!dbs_tuners_ins.powersave_bias ||
	    sample_type == DBS_NORMAL_SAMPLE) {
		dbs_check_cpu(dbs_info);
		if (dbs_info->freq_lo) {
			/* Setup timer for SUB_SAMPLE */
			dbs_info->sample_type = DBS_SUB_SAMPLE;
			delay = dbs_info->freq_hi_jiffies;
		}
	} else {
		__cpufreq_driver_target(dbs_info->cur_policy,
			dbs_info->freq_lo, CPUFREQ_RELATION_H);
	}
	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
	unlock_policy_rwsem_write(cpu);
}

static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
{
	/* We want all CPUs to do sampling nearly on same jiffy */
	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
	delay -= jiffies % delay;

	dbs_info->enable = 1;
	ondemand_powersave_bias_init();
	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
	INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer);
	queue_delayed_work_on(dbs_info->cpu, kondemand_wq, &dbs_info->work,
		delay);
}

static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
{
	dbs_info->enable = 0;
	cancel_delayed_work_sync(&dbs_info->work);
}

static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
				   unsigned int event)
{
	unsigned int cpu = policy->cpu;
	struct cpu_dbs_info_s *this_dbs_info;
	unsigned int j;
	int rc;

	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);

	switch (event) {
	case CPUFREQ_GOV_START:
		if ((!cpu_online(cpu)) || (!policy->cur))
			return -EINVAL;

		if (this_dbs_info->enable) /* Already enabled */
			break;

		mutex_lock(&dbs_mutex);
		dbs_enable++;

		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group);
		if (rc) {
			dbs_enable--;
			mutex_unlock(&dbs_mutex);
			return rc;
		}

		for_each_cpu(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;
			j_dbs_info = &per_cpu(cpu_dbs_info, j);
			j_dbs_info->cur_policy = policy;

			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
						&j_dbs_info->prev_cpu_wall);
			if (dbs_tuners_ins.ignore_nice) {
				j_dbs_info->prev_cpu_nice =
						kstat_cpu(j).cpustat.nice;
			}
		}
		this_dbs_info->cpu = cpu;
		/*
		 * Start the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 1) {
			unsigned int latency;
			/* policy latency is in nS. Convert it to uS first */
			latency = policy->cpuinfo.transition_latency / 1000;
			if (latency == 0)
				latency = 1;
			/* Bring kernel and HW constraints together */
			min_sampling_rate = max(min_sampling_rate,
					MIN_LATENCY_MULTIPLIER * latency);
			dbs_tuners_ins.sampling_rate =
				max(min_sampling_rate,
				    latency * LATENCY_MULTIPLIER);
		}
		dbs_timer_init(this_dbs_info);

		mutex_unlock(&dbs_mutex);
		break;

	case CPUFREQ_GOV_STOP:
		mutex_lock(&dbs_mutex);
		dbs_timer_exit(this_dbs_info);
		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
		dbs_enable--;
		mutex_unlock(&dbs_mutex);

		break;

	case CPUFREQ_GOV_LIMITS:
		mutex_lock(&dbs_mutex);
		if (policy->max < this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(this_dbs_info->cur_policy,
				policy->max, CPUFREQ_RELATION_H);
		else if (policy->min > this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(this_dbs_info->cur_policy,
				policy->min, CPUFREQ_RELATION_L);
		mutex_unlock(&dbs_mutex);
		break;
	}
	return 0;
}

#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
static
#endif
struct cpufreq_governor cpufreq_gov_ondemand = {
	.name			= "ondemand",
	.governor		= cpufreq_governor_dbs,
	.max_transition_latency = TRANSITION_LATENCY_LIMIT,
	.owner			= THIS_MODULE,
};

static int __init cpufreq_gov_dbs_init(void)
{
	int err;
	cputime64_t wall;
	u64 idle_time;
	int cpu = get_cpu();

	idle_time = get_cpu_idle_time_us(cpu, &wall);
	put_cpu();
	if (idle_time != -1ULL) {
		/* Idle micro accounting is supported. Use finer thresholds */
		dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
		dbs_tuners_ins.down_differential =
					MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
		/*
		 * In no_hz/micro accounting case we set the minimum frequency
		 * not depending on HZ, but fixed (very low). The deferred
		 * timer might skip some samples if idle/sleeping as needed.
		*/
		min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
	} else {
		/* For correct statistics, we need 10 ticks for each measure */
		min_sampling_rate =
			MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
	}

	kondemand_wq = create_workqueue("kondemand");
	if (!kondemand_wq) {
		printk(KERN_ERR "Creation of kondemand failed\n");
		return -EFAULT;
	}
	err = cpufreq_register_governor(&cpufreq_gov_ondemand);
	if (err)
		destroy_workqueue(kondemand_wq);

	return err;
}

static void __exit cpufreq_gov_dbs_exit(void)
{
	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
	destroy_workqueue(kondemand_wq);
}


MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
	"Low Latency Frequency Transition capable processors");
MODULE_LICENSE("GPL");

#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
fs_initcall(cpufreq_gov_dbs_init);
#else
module_init(cpufreq_gov_dbs_init);
#endif
module_exit(cpufreq_gov_dbs_exit);