linux/drivers/acpi/processor_thermal.c

362 lines
8.2 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 Based on 3 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [graeme] [gregory] [gg]@[slimlogic] [co] [uk] [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] [based] [on] [twl6030]_[usb] [c] [author] [hema] [hk] [hemahk]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 1105 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190527070033.202006027@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-27 09:55:06 +03:00
// 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>
ACPI: Clean up inclusions of ACPI header files Replace direct inclusions of <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h>, which are incorrect, with <linux/acpi.h> inclusions and remove some inclusions of those files that aren't necessary. First of all, <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h> should not be included directly from any files that are built for CONFIG_ACPI unset, because that generally leads to build warnings about undefined symbols in !CONFIG_ACPI builds. For CONFIG_ACPI set, <linux/acpi.h> includes those files and for CONFIG_ACPI unset it provides stub ACPI symbols to be used in that case. Second, there are ordering dependencies between those files that always have to be met. Namely, it is required that <acpi/acpi_bus.h> be included prior to <acpi/acpi_drivers.h> so that the acpi_pci_root declarations the latter depends on are always there. And <acpi/acpi.h> which provides basic ACPICA type declarations should always be included prior to any other ACPI headers in CONFIG_ACPI builds. That also is taken care of including <linux/acpi.h> as appropriate. Signed-off-by: Lv Zheng <lv.zheng@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Tony Luck <tony.luck@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> (drivers/pci stuff) Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> (Xen stuff) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-12-03 04:49:16 +04:00
#include <linux/acpi.h>
#include <acpi/processor.h>
#include <linux/uaccess.h>
#include "internal.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
static int cpufreq_thermal_max_step __read_mostly = 3;
/*
* Minimum throttle percentage for processor_thermal cooling device.
* The processor_thermal driver uses it to calculate the percentage amount by
* which cpu frequency must be reduced for each cooling state. This is also used
* to calculate the maximum number of throttling steps or cooling states.
*/
static int cpufreq_thermal_reduction_pctg __read_mostly = 20;
static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_step);
#define reduction_step(cpu) \
per_cpu(cpufreq_thermal_reduction_step, 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_step(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_step(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);
cpufreq: Use per-policy frequency QoS Replace the CPU device PM QoS used for the management of min and max frequency constraints in cpufreq (and its users) with per-policy frequency QoS to avoid problems with cpufreq policies covering more then one CPU. Namely, a cpufreq driver is registered with the subsys interface which calls cpufreq_add_dev() for each CPU, starting from CPU0, so currently the PM QoS notifiers are added to the first CPU in the policy (i.e. CPU0 in the majority of cases). In turn, when the cpufreq driver is unregistered, the subsys interface doing that calls cpufreq_remove_dev() for each CPU, starting from CPU0, and the PM QoS notifiers are only removed when cpufreq_remove_dev() is called for the last CPU in the policy, say CPUx, which as a rule is not CPU0 if the policy covers more than one CPU. Then, the PM QoS notifiers cannot be removed, because CPUx does not have them, and they are still there in the device PM QoS notifiers list of CPU0, which prevents new PM QoS notifiers from being registered for CPU0 on the next attempt to register the cpufreq driver. The same issue occurs when the first CPU in the policy goes offline before unregistering the driver. After this change it does not matter which CPU is the policy CPU at the driver registration time and whether or not it is online all the time, because the frequency QoS is per policy and not per CPU. Fixes: 67d874c3b2c6 ("cpufreq: Register notifiers with the PM QoS framework") Reported-by: Dmitry Osipenko <digetx@gmail.com> Tested-by: Dmitry Osipenko <digetx@gmail.com> Reported-by: Sudeep Holla <sudeep.holla@arm.com> Tested-by: Sudeep Holla <sudeep.holla@arm.com> Diagnosed-by: Viresh Kumar <viresh.kumar@linaro.org> Link: https://lore.kernel.org/linux-pm/5ad2624194baa2f53acc1f1e627eb7684c577a19.1562210705.git.viresh.kumar@linaro.org/T/#md2d89e95906b8c91c15f582146173dce2e86e99f Link: https://lore.kernel.org/linux-pm/20191017094612.6tbkwoq4harsjcqv@vireshk-i7/T/#m30d48cc23b9a80467fbaa16e30f90b3828a5a29b Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2019-10-16 13:47:06 +03:00
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_step(i) * cpufreq_thermal_reduction_pctg)) / 100;
cpufreq_cpu_put(policy);
cpufreq: Use per-policy frequency QoS Replace the CPU device PM QoS used for the management of min and max frequency constraints in cpufreq (and its users) with per-policy frequency QoS to avoid problems with cpufreq policies covering more then one CPU. Namely, a cpufreq driver is registered with the subsys interface which calls cpufreq_add_dev() for each CPU, starting from CPU0, so currently the PM QoS notifiers are added to the first CPU in the policy (i.e. CPU0 in the majority of cases). In turn, when the cpufreq driver is unregistered, the subsys interface doing that calls cpufreq_remove_dev() for each CPU, starting from CPU0, and the PM QoS notifiers are only removed when cpufreq_remove_dev() is called for the last CPU in the policy, say CPUx, which as a rule is not CPU0 if the policy covers more than one CPU. Then, the PM QoS notifiers cannot be removed, because CPUx does not have them, and they are still there in the device PM QoS notifiers list of CPU0, which prevents new PM QoS notifiers from being registered for CPU0 on the next attempt to register the cpufreq driver. The same issue occurs when the first CPU in the policy goes offline before unregistering the driver. After this change it does not matter which CPU is the policy CPU at the driver registration time and whether or not it is online all the time, because the frequency QoS is per policy and not per CPU. Fixes: 67d874c3b2c6 ("cpufreq: Register notifiers with the PM QoS framework") Reported-by: Dmitry Osipenko <digetx@gmail.com> Tested-by: Dmitry Osipenko <digetx@gmail.com> Reported-by: Sudeep Holla <sudeep.holla@arm.com> Tested-by: Sudeep Holla <sudeep.holla@arm.com> Diagnosed-by: Viresh Kumar <viresh.kumar@linaro.org> Link: https://lore.kernel.org/linux-pm/5ad2624194baa2f53acc1f1e627eb7684c577a19.1562210705.git.viresh.kumar@linaro.org/T/#md2d89e95906b8c91c15f582146173dce2e86e99f Link: https://lore.kernel.org/linux-pm/20191017094612.6tbkwoq4harsjcqv@vireshk-i7/T/#m30d48cc23b9a80467fbaa16e30f90b3828a5a29b Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2019-10-16 13:47:06 +03:00
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;
}
static void acpi_thermal_cpufreq_config(void)
{
int cpufreq_pctg = acpi_arch_thermal_cpufreq_pctg();
if (!cpufreq_pctg)
return;
cpufreq_thermal_reduction_pctg = cpufreq_pctg;
/*
* Derive the MAX_STEP from minimum throttle percentage so that the reduction
* percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
* the CPU performance doesn't become 0.
*/
cpufreq_thermal_max_step = (100 / cpufreq_pctg) - 2;
}
cpufreq: Use per-policy frequency QoS Replace the CPU device PM QoS used for the management of min and max frequency constraints in cpufreq (and its users) with per-policy frequency QoS to avoid problems with cpufreq policies covering more then one CPU. Namely, a cpufreq driver is registered with the subsys interface which calls cpufreq_add_dev() for each CPU, starting from CPU0, so currently the PM QoS notifiers are added to the first CPU in the policy (i.e. CPU0 in the majority of cases). In turn, when the cpufreq driver is unregistered, the subsys interface doing that calls cpufreq_remove_dev() for each CPU, starting from CPU0, and the PM QoS notifiers are only removed when cpufreq_remove_dev() is called for the last CPU in the policy, say CPUx, which as a rule is not CPU0 if the policy covers more than one CPU. Then, the PM QoS notifiers cannot be removed, because CPUx does not have them, and they are still there in the device PM QoS notifiers list of CPU0, which prevents new PM QoS notifiers from being registered for CPU0 on the next attempt to register the cpufreq driver. The same issue occurs when the first CPU in the policy goes offline before unregistering the driver. After this change it does not matter which CPU is the policy CPU at the driver registration time and whether or not it is online all the time, because the frequency QoS is per policy and not per CPU. Fixes: 67d874c3b2c6 ("cpufreq: Register notifiers with the PM QoS framework") Reported-by: Dmitry Osipenko <digetx@gmail.com> Tested-by: Dmitry Osipenko <digetx@gmail.com> Reported-by: Sudeep Holla <sudeep.holla@arm.com> Tested-by: Sudeep Holla <sudeep.holla@arm.com> Diagnosed-by: Viresh Kumar <viresh.kumar@linaro.org> Link: https://lore.kernel.org/linux-pm/5ad2624194baa2f53acc1f1e627eb7684c577a19.1562210705.git.viresh.kumar@linaro.org/T/#md2d89e95906b8c91c15f582146173dce2e86e99f Link: https://lore.kernel.org/linux-pm/20191017094612.6tbkwoq4harsjcqv@vireshk-i7/T/#m30d48cc23b9a80467fbaa16e30f90b3828a5a29b Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2019-10-16 13:47:06 +03:00
void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
{
unsigned int cpu;
acpi_thermal_cpufreq_config();
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);
}
}
cpufreq: Use per-policy frequency QoS Replace the CPU device PM QoS used for the management of min and max frequency constraints in cpufreq (and its users) with per-policy frequency QoS to avoid problems with cpufreq policies covering more then one CPU. Namely, a cpufreq driver is registered with the subsys interface which calls cpufreq_add_dev() for each CPU, starting from CPU0, so currently the PM QoS notifiers are added to the first CPU in the policy (i.e. CPU0 in the majority of cases). In turn, when the cpufreq driver is unregistered, the subsys interface doing that calls cpufreq_remove_dev() for each CPU, starting from CPU0, and the PM QoS notifiers are only removed when cpufreq_remove_dev() is called for the last CPU in the policy, say CPUx, which as a rule is not CPU0 if the policy covers more than one CPU. Then, the PM QoS notifiers cannot be removed, because CPUx does not have them, and they are still there in the device PM QoS notifiers list of CPU0, which prevents new PM QoS notifiers from being registered for CPU0 on the next attempt to register the cpufreq driver. The same issue occurs when the first CPU in the policy goes offline before unregistering the driver. After this change it does not matter which CPU is the policy CPU at the driver registration time and whether or not it is online all the time, because the frequency QoS is per policy and not per CPU. Fixes: 67d874c3b2c6 ("cpufreq: Register notifiers with the PM QoS framework") Reported-by: Dmitry Osipenko <digetx@gmail.com> Tested-by: Dmitry Osipenko <digetx@gmail.com> Reported-by: Sudeep Holla <sudeep.holla@arm.com> Tested-by: Sudeep Holla <sudeep.holla@arm.com> Diagnosed-by: Viresh Kumar <viresh.kumar@linaro.org> Link: https://lore.kernel.org/linux-pm/5ad2624194baa2f53acc1f1e627eb7684c577a19.1562210705.git.viresh.kumar@linaro.org/T/#md2d89e95906b8c91c15f582146173dce2e86e99f Link: https://lore.kernel.org/linux-pm/20191017094612.6tbkwoq4harsjcqv@vireshk-i7/T/#m30d48cc23b9a80467fbaa16e30f90b3828a5a29b Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2019-10-16 13:47:06 +03:00
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_step. 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)
2009-08-27 01:29:29 +04:00
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,
2009-08-27 01:29:29 +04:00
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;
}
}