cpufreq_conservative.c

来自「linux 内核源代码」· C语言 代码 · 共 612 行 · 第 1/2 页

/*
 *  drivers/cpufreq/cpufreq_conservative.c
 *
 *  Copyright (C)  2001 Russell King
 *            (C)  2003 Venkatesh Pallipadi <[e-mail]>.
 *                      Jun Nakajima <[e-mail]>
 *            (C)  2004 Alexander Clouter <[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/smp.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/ctype.h>
#include <linux/cpufreq.h>
#include <linux/sysctl.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/cpu.h>
#include <linux/kmod.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.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 DEF_FREQUENCY_DOWN_THRESHOLD		(20)

/*
 * 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 DEF_SAMPLING_DOWN_FACTOR		(1)
#define MAX_SAMPLING_DOWN_FACTOR		(10)
#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)

static void do_dbs_timer(struct work_struct *work);

struct cpu_dbs_info_s {
	struct cpufreq_policy *cur_policy;
	unsigned int prev_cpu_idle_up;
	unsigned int prev_cpu_idle_down;
	unsigned int enable;
	unsigned int down_skip;
	unsigned int requested_freq;
};
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 DECLARE_DELAYED_WORK(dbs_work, do_dbs_timer);

struct dbs_tuners {
	unsigned int sampling_rate;
	unsigned int sampling_down_factor;
	unsigned int up_threshold;
	unsigned int down_threshold;
	unsigned int ignore_nice;
	unsigned int freq_step;
};

static struct dbs_tuners dbs_tuners_ins = {
	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
	.down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD,
	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
	.ignore_nice = 0,
	.freq_step = 5,
};

static inline unsigned int get_cpu_idle_time(unsigned int cpu)
{
	unsigned int add_nice = 0, ret;

	if (dbs_tuners_ins.ignore_nice)
		add_nice = kstat_cpu(cpu).cpustat.nice;

	ret = kstat_cpu(cpu).cpustat.idle +
		kstat_cpu(cpu).cpustat.iowait +
		add_nice;

	return ret;
}

/* keep track of frequency transitions */
static int
dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
		     void *data)
{
	struct cpufreq_freqs *freq = data;
	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cpu_dbs_info,
							freq->cpu);

	if (!this_dbs_info->enable)
		return 0;

	this_dbs_info->requested_freq = freq->new;

	return 0;
}

static struct notifier_block dbs_cpufreq_notifier_block = {
	.notifier_call = dbs_cpufreq_notifier
};

/************************** 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_conservative 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(sampling_down_factor, sampling_down_factor);
show_one(up_threshold, up_threshold);
show_one(down_threshold, down_threshold);
show_one(ignore_nice_load, ignore_nice);
show_one(freq_step, freq_step);

static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);
	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
		return -EINVAL;

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.sampling_down_factor = input;
	mutex_unlock(&dbs_mutex);

	return count;
}

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 > 100 || input <= dbs_tuners_ins.down_threshold) {
		mutex_unlock(&dbs_mutex);
		return -EINVAL;
	}

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

	return count;
}

static ssize_t store_down_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 > 100 || input >= dbs_tuners_ins.up_threshold) {
		mutex_unlock(&dbs_mutex);
		return -EINVAL;
	}

	dbs_tuners_ins.down_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_up and prev_cpu_idle_down */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *j_dbs_info;
		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
	}
	mutex_unlock(&dbs_mutex);

	return count;
}

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

	ret = sscanf(buf, "%u", &input);

	if (ret != 1)
		return -EINVAL;

	if (input > 100)
		input = 100;

	/* no need to test here if freq_step is zero as the user might actually
	 * want this, they would be crazy though :) */
	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.freq_step = input;
	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);