path: root/drivers/thermal/cpufreq_cooling.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/drivers/thermal/cpufreq_cooling.c
 *
 *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
 *
 *  Copyright (C) 2012-2018 Linaro Limited.
 *
 *  Authors:	Amit Daniel <amit.kachhap@linaro.org>
 *		Viresh Kumar <viresh.kumar@linaro.org>
 *
 */
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/cpu_cooling.h>
#include <linux/energy_model.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/idr.h>
#include <linux/pm_opp.h>
#include <linux/pm_qos.h>
#include <linux/slab.h>
#include <linux/thermal.h>

#include <trace/events/thermal.h>

/*
 * Cooling state <-> CPUFreq frequency
 *
 * Cooling states are translated to frequencies throughout this driver and this
 * is the relation between them.
 *
 * Highest cooling state corresponds to lowest possible frequency.
 *
 * i.e.
 *	level 0 --> 1st Max Freq
 *	level 1 --> 2nd Max Freq
 *	...
 */

/**
 * struct time_in_idle - Idle time stats
 * @time: previous reading of the absolute time that this cpu was idle
 * @timestamp: wall time of the last invocation of get_cpu_idle_time_us()
 */
struct time_in_idle {
	u64 time;
	u64 timestamp;
};

/**
 * struct cpufreq_cooling_device - data for cooling device with cpufreq
 * @id: unique integer value corresponding to each cpufreq_cooling_device
 *	registered.
 * @last_load: load measured by the latest call to cpufreq_get_requested_power()
 * @cpufreq_state: integer value representing the current state of cpufreq
 *	cooling	devices.
 * @max_level: maximum cooling level. One less than total number of valid
 *	cpufreq frequencies.
 * @em: Reference on the Energy Model of the device
 * @cdev: thermal_cooling_device pointer to keep track of the
 *	registered cooling device.
 * @policy: cpufreq policy.
 * @node: list_head to link all cpufreq_cooling_device together.
 * @idle_time: idle time stats
 * @qos_req: PM QoS contraint to apply
 *
 * This structure is required for keeping information of each registered
 * cpufreq_cooling_device.
 */
struct cpufreq_cooling_device {
	int id;
	u32 last_load;
	unsigned int cpufreq_state;
	unsigned int max_level;
	struct em_perf_domain *em;
	struct cpufreq_policy *policy;
	struct list_head node;
	struct time_in_idle *idle_time;
	struct freq_qos_request qos_req;
};

static DEFINE_IDA(cpufreq_ida);
static DEFINE_MUTEX(cooling_list_lock);
static LIST_HEAD(cpufreq_cdev_list);

#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
/**
 * get_level: Find the level for a particular frequency
 * @cpufreq_cdev: cpufreq_cdev for which the property is required
 * @freq: Frequency
 *
 * Return: level corresponding to the frequency.
 */
static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
			       unsigned int freq)
{
	int i;

	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
		if (freq > cpufreq_cdev->em->table[i].frequency)
			break;
	}

	return cpufreq_cdev->max_level - i - 1;
}

static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
			     u32 freq)
{
	int i;

	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
		if (freq > cpufreq_cdev->em->table[i].frequency)
			break;
	}

	return cpufreq_cdev->em->table[i + 1].power;
}

static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
			     u32 power)
{
	int i;

	for (i = cpufreq_cdev->max_level; i >= 0; i--) {
		if (power >= cpufreq_cdev->em->table[i].power)
			break;
	}

	return cpufreq_cdev->em->table[i].frequency;
}

/**
 * get_load() - get load for a cpu since last updated
 * @cpufreq_cdev:	&struct cpufreq_cooling_device for this cpu
 * @cpu:	cpu number
 * @cpu_idx:	index of the cpu in time_in_idle*
 *
 * Return: The average load of cpu @cpu in percentage since this
 * function was last called.
 */
static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
		    int cpu_idx)
{
	u32 load;
	u64 now, now_idle, delta_time, delta_idle;
	struct time_in_idle *idle_time = &cpufreq_cdev->idle_time[cpu_idx];

	now_idle = get_cpu_idle_time(cpu, &now, 0);
	delta_idle = now_idle - idle_time->time;
	delta_time = now - idle_time->timestamp;

	if (delta_time <= delta_idle)
		load = 0;
	else
		load = div64_u64(100 * (delta_time - delta_idle), delta_time);

	idle_time->time = now_idle;
	idle_time->timestamp = now;

	return load;
}

/**
 * get_dynamic_power() - calculate the dynamic power
 * @cpufreq_cdev:	&cpufreq_cooling_device for this cdev
 * @freq:	current frequency
 *
 * Return: the dynamic power consumed by the cpus described by
 * @cpufreq_cdev.
 */
static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
			     unsigned long freq)
{
	u32 raw_cpu_power;

	raw_cpu_power = cpu_freq_to_power(cpufreq_cdev, freq);
	return (raw_cpu_power * cpufreq_cdev->last_load) / 100;
}

/**
 * cpufreq_get_requested_power() - get the current power
 * @cdev:	&thermal_cooling_device pointer
 * @power:	pointer in which to store the resulting power
 *
 * Calculate the current power consumption of the cpus in milliwatts
 * and store it in @power.  This function should actually calculate
 * the requested power, but it's hard to get the frequency that
 * cpufreq would have assigned if there were no thermal limits.
 * Instead, we calculate the current power on the assumption that the
 * immediate future will look like the immediate past.
 *
 * We use the current frequency and the average load since this
 * function was last called.  In reality, there could have been
 * multiple opps since this function was last called and that affects
 * the load calculation.  While it's not perfectly accurate, this
 * simplification is good enough and works.  REVISIT this, as more
 * complex code may be needed if experiments show that it's not
 * accurate enough.
 *
 * Return: 0 on success, -E* if getting the static power failed.
 */
static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
				       u32 *power)
{
	unsigned long freq;
	int i = 0, cpu;
	u32 total_load = 0;
	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
	struct cpufreq_policy *policy = cpufreq_cdev->policy;
	u32 *load_cpu = NULL;

	freq = cpufreq_quick_get(policy->cpu);

	if (trace_thermal_power_cpu_get_power_enabled()) {
		u32 ncpus = cpumask_weight(policy->related_cpus);

		load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL);
	}

	for_each_cpu(cpu, policy->related_cpus) {
		u32 load;

		if (cpu_online(cpu))
			load = get_load(cpufreq_cdev, cpu, i);
		else
			load = 0;

		total_load += load;
		if (load_cpu)
			load_cpu[i] = load;

		i++;
	}

	cpufreq_cdev->last_load = total_load;

	*power = get_dynamic_power(cpufreq_cdev, freq);

	if (load_cpu) {
		trace_thermal_power_cpu_get_power(policy->related_cpus, freq,
						  load_cpu, i, *power);

		kfree(load_cpu);
	}

	return 0;
}

/**
 * cpufreq_state2power() - convert a cpu cdev state to power consumed
 * @cdev:	&thermal_cooling_device pointer
 * @state:	cooling device state to be converted
 * @power:	pointer in which to store the resulting power
 *
 * Convert cooling device state @state into power consumption in
 * milliwatts assuming 100% load.  Store the calculated power in
 * @power.
 *
 * Return: 0 on success, -EINVAL if the cooling device state could not
 * be converted into a frequency or other -E* if there was an error
 * when calculating the static power.
 */
static int cpufreq_state2power(struct thermal_cooling_device *cdev,
			       unsigned long state, u32 *power)
{
	unsigned int freq, num_cpus, idx;
	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;

	/* Request state should be less than max_level */
	if (state > cpufreq_cdev->max_level)
		return -EINVAL;

	num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus);

	idx =