mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Rafael J. Wysocki](/assets/img/avatar_default.png)
When a cpufreq policy appears or goes away, the CPU cooling devices for the CPUs covered by that policy need to be updated so that the new processor_get_max_state() value is stored as max_state and the statistics in sysfs are rearranged for each of them. Do that accordingly in acpi_thermal_cpufreq_init() and acpi_thermal_cpufreq_exit(). Fixes: a365105c685c("thermal: sysfs: Reuse cdev->max_state") Reported-by: Wang, Quanxian <quanxian.wang@intel.com> Link: https://lore.kernel.org/linux-pm/53ec1f06f61c984100868926f282647e57ecfb2d.camel@intel.com Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Tested-by: Zhang Rui <rui.zhang@intel.com> Reviewed-by: Zhang Rui <rui.zhang@intel.com>
330 lines
7.3 KiB
C
330 lines
7.3 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* processor_thermal.c - Passive cooling submodule of the ACPI processor driver
|
|
*
|
|
* Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
|
|
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
|
|
* Copyright (C) 2004 Dominik Brodowski <linux@brodo.de>
|
|
* Copyright (C) 2004 Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
|
|
* - Added processor hotplug support
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/cpufreq.h>
|
|
#include <linux/acpi.h>
|
|
#include <acpi/processor.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#ifdef CONFIG_CPU_FREQ
|
|
|
|
/* If a passive cooling situation is detected, primarily CPUfreq is used, as it
|
|
* offers (in most cases) voltage scaling in addition to frequency scaling, and
|
|
* thus a cubic (instead of linear) reduction of energy. Also, we allow for
|
|
* _any_ cpufreq driver and not only the acpi-cpufreq driver.
|
|
*/
|
|
|
|
#define CPUFREQ_THERMAL_MIN_STEP 0
|
|
#define CPUFREQ_THERMAL_MAX_STEP 3
|
|
|
|
static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
|
|
|
|
#define reduction_pctg(cpu) \
|
|
per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
|
|
|
|
/*
|
|
* Emulate "per package data" using per cpu data (which should really be
|
|
* provided elsewhere)
|
|
*
|
|
* Note we can lose a CPU on cpu hotunplug, in this case we forget the state
|
|
* temporarily. Fortunately that's not a big issue here (I hope)
|
|
*/
|
|
static int phys_package_first_cpu(int cpu)
|
|
{
|
|
int i;
|
|
int id = topology_physical_package_id(cpu);
|
|
|
|
for_each_online_cpu(i)
|
|
if (topology_physical_package_id(i) == id)
|
|
return i;
|
|
return 0;
|
|
}
|
|
|
|
static int cpu_has_cpufreq(unsigned int cpu)
|
|
{
|
|
struct cpufreq_policy *policy;
|
|
|
|
if (!acpi_processor_cpufreq_init)
|
|
return 0;
|
|
|
|
policy = cpufreq_cpu_get(cpu);
|
|
if (policy) {
|
|
cpufreq_cpu_put(policy);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int cpufreq_get_max_state(unsigned int cpu)
|
|
{
|
|
if (!cpu_has_cpufreq(cpu))
|
|
return 0;
|
|
|
|
return CPUFREQ_THERMAL_MAX_STEP;
|
|
}
|
|
|
|
static int cpufreq_get_cur_state(unsigned int cpu)
|
|
{
|
|
if (!cpu_has_cpufreq(cpu))
|
|
return 0;
|
|
|
|
return reduction_pctg(cpu);
|
|
}
|
|
|
|
static int cpufreq_set_cur_state(unsigned int cpu, int state)
|
|
{
|
|
struct cpufreq_policy *policy;
|
|
struct acpi_processor *pr;
|
|
unsigned long max_freq;
|
|
int i, ret;
|
|
|
|
if (!cpu_has_cpufreq(cpu))
|
|
return 0;
|
|
|
|
reduction_pctg(cpu) = state;
|
|
|
|
/*
|
|
* Update all the CPUs in the same package because they all
|
|
* contribute to the temperature and often share the same
|
|
* frequency.
|
|
*/
|
|
for_each_online_cpu(i) {
|
|
if (topology_physical_package_id(i) !=
|
|
topology_physical_package_id(cpu))
|
|
continue;
|
|
|
|
pr = per_cpu(processors, i);
|
|
|
|
if (unlikely(!freq_qos_request_active(&pr->thermal_req)))
|
|
continue;
|
|
|
|
policy = cpufreq_cpu_get(i);
|
|
if (!policy)
|
|
return -EINVAL;
|
|
|
|
max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
|
|
|
|
cpufreq_cpu_put(policy);
|
|
|
|
ret = freq_qos_update_request(&pr->thermal_req, max_freq);
|
|
if (ret < 0) {
|
|
pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
|
|
pr->id, ret);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
|
|
{
|
|
unsigned int cpu;
|
|
|
|
for_each_cpu(cpu, policy->related_cpus) {
|
|
struct acpi_processor *pr = per_cpu(processors, cpu);
|
|
int ret;
|
|
|
|
if (!pr)
|
|
continue;
|
|
|
|
ret = freq_qos_add_request(&policy->constraints,
|
|
&pr->thermal_req,
|
|
FREQ_QOS_MAX, INT_MAX);
|
|
if (ret < 0) {
|
|
pr_err("Failed to add freq constraint for CPU%d (%d)\n",
|
|
cpu, ret);
|
|
continue;
|
|
}
|
|
|
|
thermal_cooling_device_update(pr->cdev);
|
|
}
|
|
}
|
|
|
|
void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
|
|
{
|
|
unsigned int cpu;
|
|
|
|
for_each_cpu(cpu, policy->related_cpus) {
|
|
struct acpi_processor *pr = per_cpu(processors, cpu);
|
|
|
|
if (!pr)
|
|
continue;
|
|
|
|
freq_qos_remove_request(&pr->thermal_req);
|
|
|
|
thermal_cooling_device_update(pr->cdev);
|
|
}
|
|
}
|
|
#else /* ! CONFIG_CPU_FREQ */
|
|
static int cpufreq_get_max_state(unsigned int cpu)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static int cpufreq_get_cur_state(unsigned int cpu)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static int cpufreq_set_cur_state(unsigned int cpu, int state)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
|
|
/* thermal cooling device callbacks */
|
|
static int acpi_processor_max_state(struct acpi_processor *pr)
|
|
{
|
|
int max_state = 0;
|
|
|
|
/*
|
|
* There exists four states according to
|
|
* cpufreq_thermal_reduction_pctg. 0, 1, 2, 3
|
|
*/
|
|
max_state += cpufreq_get_max_state(pr->id);
|
|
if (pr->flags.throttling)
|
|
max_state += (pr->throttling.state_count -1);
|
|
|
|
return max_state;
|
|
}
|
|
static int
|
|
processor_get_max_state(struct thermal_cooling_device *cdev,
|
|
unsigned long *state)
|
|
{
|
|
struct acpi_device *device = cdev->devdata;
|
|
struct acpi_processor *pr;
|
|
|
|
if (!device)
|
|
return -EINVAL;
|
|
|
|
pr = acpi_driver_data(device);
|
|
if (!pr)
|
|
return -EINVAL;
|
|
|
|
*state = acpi_processor_max_state(pr);
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
processor_get_cur_state(struct thermal_cooling_device *cdev,
|
|
unsigned long *cur_state)
|
|
{
|
|
struct acpi_device *device = cdev->devdata;
|
|
struct acpi_processor *pr;
|
|
|
|
if (!device)
|
|
return -EINVAL;
|
|
|
|
pr = acpi_driver_data(device);
|
|
if (!pr)
|
|
return -EINVAL;
|
|
|
|
*cur_state = cpufreq_get_cur_state(pr->id);
|
|
if (pr->flags.throttling)
|
|
*cur_state += pr->throttling.state;
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
processor_set_cur_state(struct thermal_cooling_device *cdev,
|
|
unsigned long state)
|
|
{
|
|
struct acpi_device *device = cdev->devdata;
|
|
struct acpi_processor *pr;
|
|
int result = 0;
|
|
int max_pstate;
|
|
|
|
if (!device)
|
|
return -EINVAL;
|
|
|
|
pr = acpi_driver_data(device);
|
|
if (!pr)
|
|
return -EINVAL;
|
|
|
|
max_pstate = cpufreq_get_max_state(pr->id);
|
|
|
|
if (state > acpi_processor_max_state(pr))
|
|
return -EINVAL;
|
|
|
|
if (state <= max_pstate) {
|
|
if (pr->flags.throttling && pr->throttling.state)
|
|
result = acpi_processor_set_throttling(pr, 0, false);
|
|
cpufreq_set_cur_state(pr->id, state);
|
|
} else {
|
|
cpufreq_set_cur_state(pr->id, max_pstate);
|
|
result = acpi_processor_set_throttling(pr,
|
|
state - max_pstate, false);
|
|
}
|
|
return result;
|
|
}
|
|
|
|
const struct thermal_cooling_device_ops processor_cooling_ops = {
|
|
.get_max_state = processor_get_max_state,
|
|
.get_cur_state = processor_get_cur_state,
|
|
.set_cur_state = processor_set_cur_state,
|
|
};
|
|
|
|
int acpi_processor_thermal_init(struct acpi_processor *pr,
|
|
struct acpi_device *device)
|
|
{
|
|
int result = 0;
|
|
|
|
pr->cdev = thermal_cooling_device_register("Processor", device,
|
|
&processor_cooling_ops);
|
|
if (IS_ERR(pr->cdev)) {
|
|
result = PTR_ERR(pr->cdev);
|
|
return result;
|
|
}
|
|
|
|
dev_dbg(&device->dev, "registered as cooling_device%d\n",
|
|
pr->cdev->id);
|
|
|
|
result = sysfs_create_link(&device->dev.kobj,
|
|
&pr->cdev->device.kobj,
|
|
"thermal_cooling");
|
|
if (result) {
|
|
dev_err(&device->dev,
|
|
"Failed to create sysfs link 'thermal_cooling'\n");
|
|
goto err_thermal_unregister;
|
|
}
|
|
|
|
result = sysfs_create_link(&pr->cdev->device.kobj,
|
|
&device->dev.kobj,
|
|
"device");
|
|
if (result) {
|
|
dev_err(&pr->cdev->device,
|
|
"Failed to create sysfs link 'device'\n");
|
|
goto err_remove_sysfs_thermal;
|
|
}
|
|
|
|
return 0;
|
|
|
|
err_remove_sysfs_thermal:
|
|
sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
|
|
err_thermal_unregister:
|
|
thermal_cooling_device_unregister(pr->cdev);
|
|
|
|
return result;
|
|
}
|
|
|
|
void acpi_processor_thermal_exit(struct acpi_processor *pr,
|
|
struct acpi_device *device)
|
|
{
|
|
if (pr->cdev) {
|
|
sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
|
|
sysfs_remove_link(&pr->cdev->device.kobj, "device");
|
|
thermal_cooling_device_unregister(pr->cdev);
|
|
pr->cdev = NULL;
|
|
}
|
|
}
|