cpufreq_ondemand.c

linux 内核源代码

__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 idle_ticks, total_ticks;
	unsigned int load = 0;
	cputime64_t cur_jiffies;

	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;
	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
	total_ticks = (unsigned int) cputime64_sub(cur_jiffies,
			this_dbs_info->prev_cpu_wall);
	this_dbs_info->prev_cpu_wall = get_jiffies_64();

	if (!total_ticks)
		return;
	/*
	 * 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 Idle Time */
	idle_ticks = UINT_MAX;
	for_each_cpu_mask(j, policy->cpus) {
		cputime64_t total_idle_ticks;
		unsigned int tmp_idle_ticks;
		struct cpu_dbs_info_s *j_dbs_info;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		total_idle_ticks = get_cpu_idle_time(j);
		tmp_idle_ticks = (unsigned int) cputime64_sub(total_idle_ticks,
				j_dbs_info->prev_cpu_idle);
		j_dbs_info->prev_cpu_idle = total_idle_ticks;

		if (tmp_idle_ticks < idle_ticks)
			idle_ticks = tmp_idle_ticks;
	}
	if (likely(total_ticks > idle_ticks))
		load = (100 * (total_ticks - idle_ticks)) / total_ticks;

	/* Check for frequency increase */
	if (load > dbs_tuners_ins.up_threshold) {
		/* 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 (load < (dbs_tuners_ins.up_threshold - 10)) {
		unsigned int freq_next, freq_cur;

		freq_cur = __cpufreq_driver_getavg(policy);
		if (!freq_cur)
			freq_cur = policy->cur;

		freq_next = (freq_cur * load) /
			(dbs_tuners_ins.up_threshold - 10);

		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(&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_mask(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 = get_jiffies_64();
		}
		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;

			def_sampling_rate = latency *
					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;

			if (def_sampling_rate < MIN_STAT_SAMPLING_RATE)
				def_sampling_rate = MIN_STAT_SAMPLING_RATE;

			dbs_tuners_ins.sampling_rate = def_sampling_rate;
		}
		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;
}

struct cpufreq_governor cpufreq_gov_ondemand = {
	.name			= "ondemand",
	.governor		= cpufreq_governor_dbs,
	.max_transition_latency = TRANSITION_LATENCY_LIMIT,
	.owner			= THIS_MODULE,
};
EXPORT_SYMBOL(cpufreq_gov_ondemand);

static int __init cpufreq_gov_dbs_init(void)
{
	kondemand_wq = create_workqueue("kondemand");
	if (!kondemand_wq) {
		printk(KERN_ERR "Creation of kondemand failed\n");
		return -EFAULT;
	}
	return cpufreq_register_governor(&cpufreq_gov_ondemand);
}

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


MODULE_AUTHOR("Venkatesh Pallipadi <[e-mail]>");
MODULE_AUTHOR("Alexey Starikovskiy <[e-mail]>");
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);