cpufreq_ondemand.c

linux 内核源代码

/*
 *  drivers/cpufreq/cpufreq_ondemand.c
 *
 *  Copyright (C)  2001 Russell King
 *            (C)  2003 Venkatesh Pallipadi <[e-mail]>.
 *                      Jun Nakajima <[e-mail]>
 *
 * 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>

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

#define DEF_FREQUENCY_UP_THRESHOLD		(80)
#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.
 */
static unsigned int def_sampling_rate;
#define MIN_SAMPLING_RATE_RATIO			(2)
/* for correct statistics, we need at least 10 ticks between each measure */
#define MIN_STAT_SAMPLING_RATE 			\
			(MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
#define MIN_SAMPLING_RATE			\
			(def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
#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;
	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
 */
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 ignore_nice;
	unsigned int powersave_bias;
} dbs_tuners_ins = {
	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
	.ignore_nice = 0,
	.powersave_bias = 0,
};

static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
{
	cputime64_t idle_time;
	cputime64_t cur_jiffies;
	cputime64_t busy_time;

	cur_jiffies = 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);

	if (!dbs_tuners_ins.ignore_nice) {
		busy_time = cputime64_add(busy_time,
				kstat_cpu(cpu).cpustat.nice);
	}

	idle_time = cputime64_sub(cur_jiffies, busy_time);
	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)
{
	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
}

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 || input > MAX_SAMPLING_RATE
		     || input < MIN_SAMPLING_RATE) {
		mutex_unlock(&dbs_mutex);
		return -EINVAL;
	}

	dbs_tuners_ins.sampling_rate = input;
	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 = get_jiffies_64();
	}
	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 = \