android_kernel_xiaomi_sm8350/drivers/thermal/cpu_cooling.c
Zhuguangqing faa72d97c3 thermal/drivers/cpufreq_cooling: Update cpufreq_state only if state has changed
commit 236761f19a4f373354f1dcf399b57753f1f4b871 upstream.

If state has not changed successfully and we updated cpufreq_state,
next time when the new state is equal to cpufreq_state (not changed
successfully last time), we will return directly and miss a
freq_qos_update_request() that should have been.

Fixes: 5130802ddb ("thermal: cpu_cooling: Switch to QoS requests for freq limits")
Cc: v5.4+ <stable@vger.kernel.org> # v5.4+
Signed-off-by: Zhuguangqing <zhuguangqing@xiaomi.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20201106092243.15574-1-zhuguangqing83@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-01-06 14:48:35 +01:00

749 lines
21 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/drivers/thermal/cpu_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/module.h>
#include <linux/thermal.h>
#include <linux/cpufreq.h>
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/pm_opp.h>
#include <linux/pm_qos.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/cpu_cooling.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 freq_table - frequency table along with power entries
* @frequency: frequency in KHz
* @power: power in mW
*
* This structure is built when the cooling device registers and helps
* in translating frequency to power and vice versa.
*/
struct freq_table {
u32 frequency;
u32 power;
};
/**
* 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.
* @freq_table: Freq table in descending order of frequencies
* @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
*
* 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 freq_table *freq_table; /* In descending order */
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);
/* Below code defines functions to be used for cpufreq as cooling device */
/**
* 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)
{
struct freq_table *freq_table = cpufreq_cdev->freq_table;
unsigned long level;
for (level = 1; level <= cpufreq_cdev->max_level; level++)
if (freq > freq_table[level].frequency)
break;
return level - 1;
}
/**
* update_freq_table() - Update the freq table with power numbers
* @cpufreq_cdev: the cpufreq cooling device in which to update the table
* @capacitance: dynamic power coefficient for these cpus
*
* Update the freq table with power numbers. This table will be used in
* cpu_power_to_freq() and cpu_freq_to_power() to convert between power and
* frequency efficiently. Power is stored in mW, frequency in KHz. The
* resulting table is in descending order.
*
* Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
* or -ENOMEM if we run out of memory.
*/
static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev,
u32 capacitance)
{
struct freq_table *freq_table = cpufreq_cdev->freq_table;
struct dev_pm_opp *opp;
struct device *dev = NULL;
int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i;
dev = get_cpu_device(cpu);
if (unlikely(!dev)) {
pr_warn("No cpu device for cpu %d\n", cpu);
return -ENODEV;
}
num_opps = dev_pm_opp_get_opp_count(dev);
if (num_opps < 0)
return num_opps;
/*
* The cpufreq table is also built from the OPP table and so the count
* should match.
*/
if (num_opps != cpufreq_cdev->max_level + 1) {
dev_warn(dev, "Number of OPPs not matching with max_levels\n");
return -EINVAL;
}
for (i = 0; i <= cpufreq_cdev->max_level; i++) {
unsigned long freq = freq_table[i].frequency * 1000;
u32 freq_mhz = freq_table[i].frequency / 1000;
u64 power;
u32 voltage_mv;
/*
* Find ceil frequency as 'freq' may be slightly lower than OPP
* freq due to truncation while converting to kHz.
*/
opp = dev_pm_opp_find_freq_ceil(dev, &freq);
if (IS_ERR(opp)) {
dev_err(dev, "failed to get opp for %lu frequency\n",
freq);
return -EINVAL;
}
voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
dev_pm_opp_put(opp);
/*
* Do the multiplication with MHz and millivolt so as
* to not overflow.
*/
power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv;
do_div(power, 1000000000);
/* power is stored in mW */
freq_table[i].power = power;
}
return 0;
}
static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
u32 freq)
{
int i;
struct freq_table *freq_table = cpufreq_cdev->freq_table;
for (i = 1; i <= cpufreq_cdev->max_level; i++)
if (freq > freq_table[i].frequency)
break;
return freq_table[i - 1].power;
}
static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
u32 power)
{
int i;
struct freq_table *freq_table = cpufreq_cdev->freq_table;
for (i = 0; i < cpufreq_cdev->max_level; i++)
if (power >= freq_table[i].power)
break;
return freq_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 cooling device callback functions are defined below */
/**
* cpufreq_get_max_state - callback function to get the max cooling state.
* @cdev: thermal cooling device pointer.
* @state: fill this variable with the max cooling state.
*
* Callback for the thermal cooling device to return the cpufreq
* max cooling state.
*
* Return: 0 on success, an error code otherwise.
*/
static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
unsigned long *state)
{
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
*state = cpufreq_cdev->max_level;
return 0;
}
/**
* cpufreq_get_cur_state - callback function to get the current cooling state.
* @cdev: thermal cooling device pointer.
* @state: fill this variable with the current cooling state.
*
* Callback for the thermal cooling device to return the cpufreq
* current cooling state.
*
* Return: 0 on success, an error code otherwise.
*/
static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
unsigned long *state)
{
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
*state = cpufreq_cdev->cpufreq_state;
return 0;
}
/**
* cpufreq_set_cur_state - callback function to set the current cooling state.
* @cdev: thermal cooling device pointer.
* @state: set this variable to the current cooling state.
*
* Callback for the thermal cooling device to change the cpufreq
* current cooling state.
*
* Return: 0 on success, an error code otherwise.
*/
static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
unsigned long state)
{
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
int ret;
/* Request state should be less than max_level */
if (WARN_ON(state > cpufreq_cdev->max_level))
return -EINVAL;
/* Check if the old cooling action is same as new cooling action */
if (cpufreq_cdev->cpufreq_state == state)
return 0;
ret = freq_qos_update_request(&cpufreq_cdev->qos_req,
cpufreq_cdev->freq_table[state].frequency);
if (ret > 0)
cpufreq_cdev->cpufreq_state = state;
return ret;
}
/**
* cpufreq_get_requested_power() - get the current power
* @cdev: &thermal_cooling_device pointer
* @tz: a valid thermal zone 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,
struct thermal_zone_device *tz,
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
* @tz: a valid thermal zone 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,
struct thermal_zone_device *tz,
unsigned long state, u32 *power)
{
unsigned int freq, num_cpus;
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
/* Request state should be less than max_level */
if (WARN_ON(state > cpufreq_cdev->max_level))
return -EINVAL;
num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus);
freq = cpufreq_cdev->freq_table[state].frequency;
*power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus;
return 0;
}
/**
* cpufreq_power2state() - convert power to a cooling device state
* @cdev: &thermal_cooling_device pointer
* @tz: a valid thermal zone device pointer
* @power: power in milliwatts to be converted
* @state: pointer in which to store the resulting state
*
* Calculate a cooling device state for the cpus described by @cdev
* that would allow them to consume at most @power mW and store it in
* @state. Note that this calculation depends on external factors
* such as the cpu load or the current static power. Calling this
* function with the same power as input can yield different cooling
* device states depending on those external factors.
*
* Return: 0 on success, -ENODEV if no cpus are online or -EINVAL if
* the calculated frequency could not be converted to a valid state.
* The latter should not happen unless the frequencies available to
* cpufreq have changed since the initialization of the cpu cooling
* device.
*/
static int cpufreq_power2state(struct thermal_cooling_device *cdev,
struct thermal_zone_device *tz, u32 power,
unsigned long *state)
{
unsigned int target_freq;
u32 last_load, normalised_power;
struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
struct cpufreq_policy *policy = cpufreq_cdev->policy;
last_load = cpufreq_cdev->last_load ?: 1;
normalised_power = (power * 100) / last_load;
target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power);
*state = get_level(cpufreq_cdev, target_freq);
trace_thermal_power_cpu_limit(policy->related_cpus, target_freq, *state,
power);
return 0;
}
/* Bind cpufreq callbacks to thermal cooling device ops */
static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
.get_max_state = cpufreq_get_max_state,
.get_cur_state = cpufreq_get_cur_state,
.set_cur_state = cpufreq_set_cur_state,
};
static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
.get_max_state = cpufreq_get_max_state,
.get_cur_state = cpufreq_get_cur_state,
.set_cur_state = cpufreq_set_cur_state,
.get_requested_power = cpufreq_get_requested_power,
.state2power = cpufreq_state2power,
.power2state = cpufreq_power2state,
};
static unsigned int find_next_max(struct cpufreq_frequency_table *table,
unsigned int prev_max)
{
struct cpufreq_frequency_table *pos;
unsigned int max = 0;
cpufreq_for_each_valid_entry(pos, table) {
if (pos->frequency > max && pos->frequency < prev_max)
max = pos->frequency;
}
return max;
}
/**
* __cpufreq_cooling_register - helper function to create cpufreq cooling device
* @np: a valid struct device_node to the cooling device device tree node
* @policy: cpufreq policy
* Normally this should be same as cpufreq policy->related_cpus.
* @capacitance: dynamic power coefficient for these cpus
*
* This interface function registers the cpufreq cooling device with the name
* "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
* cooling devices. It also gives the opportunity to link the cooling device
* with a device tree node, in order to bind it via the thermal DT code.
*
* Return: a valid struct thermal_cooling_device pointer on success,
* on failure, it returns a corresponding ERR_PTR().
*/
static struct thermal_cooling_device *
__cpufreq_cooling_register(struct device_node *np,
struct cpufreq_policy *policy, u32 capacitance)
{
struct thermal_cooling_device *cdev;
struct cpufreq_cooling_device *cpufreq_cdev;
char dev_name[THERMAL_NAME_LENGTH];
unsigned int freq, i, num_cpus;
struct device *dev;
int ret;
struct thermal_cooling_device_ops *cooling_ops;
dev = get_cpu_device(policy->cpu);
if (unlikely(!dev)) {
pr_warn("No cpu device for cpu %d\n", policy->cpu);
return ERR_PTR(-ENODEV);
}
if (IS_ERR_OR_NULL(policy)) {
pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
return ERR_PTR(-EINVAL);
}
i = cpufreq_table_count_valid_entries(policy);
if (!i) {
pr_debug("%s: CPUFreq table not found or has no valid entries\n",
__func__);
return ERR_PTR(-ENODEV);
}
cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL);
if (!cpufreq_cdev)
return ERR_PTR(-ENOMEM);
cpufreq_cdev->policy = policy;
num_cpus = cpumask_weight(policy->related_cpus);
cpufreq_cdev->idle_time = kcalloc(num_cpus,
sizeof(*cpufreq_cdev->idle_time),
GFP_KERNEL);
if (!cpufreq_cdev->idle_time) {
cdev = ERR_PTR(-ENOMEM);
goto free_cdev;
}
/* max_level is an index, not a counter */
cpufreq_cdev->max_level = i - 1;
cpufreq_cdev->freq_table = kmalloc_array(i,
sizeof(*cpufreq_cdev->freq_table),
GFP_KERNEL);
if (!cpufreq_cdev->freq_table) {
cdev = ERR_PTR(-ENOMEM);
goto free_idle_time;
}
ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL);
if (ret < 0) {
cdev = ERR_PTR(ret);
goto free_table;
}
cpufreq_cdev->id = ret;
snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
cpufreq_cdev->id);
/* Fill freq-table in descending order of frequencies */
for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) {
freq = find_next_max(policy->freq_table, freq);
cpufreq_cdev->freq_table[i].frequency = freq;
/* Warn for duplicate entries */
if (!freq)
pr_warn("%s: table has duplicate entries\n", __func__);
else
pr_debug("%s: freq:%u KHz\n", __func__, freq);
}
if (capacitance) {
ret = update_freq_table(cpufreq_cdev, capacitance);
if (ret) {
cdev = ERR_PTR(ret);
goto remove_ida;
}
cooling_ops = &cpufreq_power_cooling_ops;
} else {
cooling_ops = &cpufreq_cooling_ops;
}
ret = freq_qos_add_request(&policy->constraints,
&cpufreq_cdev->qos_req, FREQ_QOS_MAX,
cpufreq_cdev->freq_table[0].frequency);
if (ret < 0) {
pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
ret);
cdev = ERR_PTR(ret);
goto remove_ida;
}
cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev,
cooling_ops);
if (IS_ERR(cdev))
goto remove_qos_req;
mutex_lock(&cooling_list_lock);
list_add(&cpufreq_cdev->node, &cpufreq_cdev_list);
mutex_unlock(&cooling_list_lock);
return cdev;
remove_qos_req:
freq_qos_remove_request(&cpufreq_cdev->qos_req);
remove_ida:
ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
free_table:
kfree(cpufreq_cdev->freq_table);
free_idle_time:
kfree(cpufreq_cdev->idle_time);
free_cdev:
kfree(cpufreq_cdev);
return cdev;
}
/**
* cpufreq_cooling_register - function to create cpufreq cooling device.
* @policy: cpufreq policy
*
* This interface function registers the cpufreq cooling device with the name
* "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
* cooling devices.
*
* Return: a valid struct thermal_cooling_device pointer on success,
* on failure, it returns a corresponding ERR_PTR().
*/
struct thermal_cooling_device *
cpufreq_cooling_register(struct cpufreq_policy *policy)
{
return __cpufreq_cooling_register(NULL, policy, 0);
}
EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
/**
* of_cpufreq_cooling_register - function to create cpufreq cooling device.
* @policy: cpufreq policy
*
* This interface function registers the cpufreq cooling device with the name
* "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
* cooling devices. Using this API, the cpufreq cooling device will be
* linked to the device tree node provided.
*
* Using this function, the cooling device will implement the power
* extensions by using a simple cpu power model. The cpus must have
* registered their OPPs using the OPP library.
*
* It also takes into account, if property present in policy CPU node, the
* static power consumed by the cpu.
*
* Return: a valid struct thermal_cooling_device pointer on success,
* and NULL on failure.
*/
struct thermal_cooling_device *
of_cpufreq_cooling_register(struct cpufreq_policy *policy)
{
struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
struct thermal_cooling_device *cdev = NULL;
u32 capacitance = 0;
if (!np) {
pr_err("cpu_cooling: OF node not available for cpu%d\n",
policy->cpu);
return NULL;
}
if (of_find_property(np, "#cooling-cells", NULL)) {
of_property_read_u32(np, "dynamic-power-coefficient",
&capacitance);
cdev = __cpufreq_cooling_register(np, policy, capacitance);
if (IS_ERR(cdev)) {
pr_err("cpu_cooling: cpu%d failed to register as cooling device: %ld\n",
policy->cpu, PTR_ERR(cdev));
cdev = NULL;
}
}
of_node_put(np);
return cdev;
}
EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
/**
* cpufreq_cooling_unregister - function to remove cpufreq cooling device.
* @cdev: thermal cooling device pointer.
*
* This interface function unregisters the "thermal-cpufreq-%x" cooling device.
*/
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{
struct cpufreq_cooling_device *cpufreq_cdev;
if (!cdev)
return;
cpufreq_cdev = cdev->devdata;
mutex_lock(&cooling_list_lock);
list_del(&cpufreq_cdev->node);
mutex_unlock(&cooling_list_lock);
thermal_cooling_device_unregister(cdev);
freq_qos_remove_request(&cpufreq_cdev->qos_req);
ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
kfree(cpufreq_cdev->idle_time);
kfree(cpufreq_cdev->freq_table);
kfree(cpufreq_cdev);
}
EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);