linux/drivers/thermal/thermal_core.c

2373 lines
61 KiB
C
Raw Normal View History

/*
* thermal.c - Generic Thermal Management Sysfs support.
*
* Copyright (C) 2008 Intel Corp
* Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
* Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* 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; version 2 of the License.
*
* 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.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/device.h>
#include <linux/err.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/kdev_t.h>
#include <linux/idr.h>
#include <linux/thermal.h>
#include <linux/reboot.h>
#include <linux/string.h>
#include <linux/of.h>
#include <net/netlink.h>
#include <net/genetlink.h>
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
#include <linux/suspend.h>
#define CREATE_TRACE_POINTS
#include <trace/events/thermal.h>
#include "thermal_core.h"
#include "thermal_hwmon.h"
MODULE_AUTHOR("Zhang Rui");
MODULE_DESCRIPTION("Generic thermal management sysfs support");
MODULE_LICENSE("GPL v2");
static DEFINE_IDR(thermal_tz_idr);
static DEFINE_IDR(thermal_cdev_idr);
static DEFINE_MUTEX(thermal_idr_lock);
static LIST_HEAD(thermal_tz_list);
static LIST_HEAD(thermal_cdev_list);
static LIST_HEAD(thermal_governor_list);
static DEFINE_MUTEX(thermal_list_lock);
static DEFINE_MUTEX(thermal_governor_lock);
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
static atomic_t in_suspend;
static struct thermal_governor *def_governor;
static struct thermal_governor *__find_governor(const char *name)
{
struct thermal_governor *pos;
if (!name || !name[0])
return def_governor;
list_for_each_entry(pos, &thermal_governor_list, governor_list)
if (!strncasecmp(name, pos->name, THERMAL_NAME_LENGTH))
return pos;
return NULL;
}
/**
* bind_previous_governor() - bind the previous governor of the thermal zone
* @tz: a valid pointer to a struct thermal_zone_device
* @failed_gov_name: the name of the governor that failed to register
*
* Register the previous governor of the thermal zone after a new
* governor has failed to be bound.
*/
static void bind_previous_governor(struct thermal_zone_device *tz,
const char *failed_gov_name)
{
if (tz->governor && tz->governor->bind_to_tz) {
if (tz->governor->bind_to_tz(tz)) {
dev_err(&tz->device,
"governor %s failed to bind and the previous one (%s) failed to bind again, thermal zone %s has no governor\n",
failed_gov_name, tz->governor->name, tz->type);
tz->governor = NULL;
}
}
}
/**
* thermal_set_governor() - Switch to another governor
* @tz: a valid pointer to a struct thermal_zone_device
* @new_gov: pointer to the new governor
*
* Change the governor of thermal zone @tz.
*
* Return: 0 on success, an error if the new governor's bind_to_tz() failed.
*/
static int thermal_set_governor(struct thermal_zone_device *tz,
struct thermal_governor *new_gov)
{
int ret = 0;
if (tz->governor && tz->governor->unbind_from_tz)
tz->governor->unbind_from_tz(tz);
if (new_gov && new_gov->bind_to_tz) {
ret = new_gov->bind_to_tz(tz);
if (ret) {
bind_previous_governor(tz, new_gov->name);
return ret;
}
}
tz->governor = new_gov;
return ret;
}
int thermal_register_governor(struct thermal_governor *governor)
{
int err;
const char *name;
struct thermal_zone_device *pos;
if (!governor)
return -EINVAL;
mutex_lock(&thermal_governor_lock);
err = -EBUSY;
if (__find_governor(governor->name) == NULL) {
err = 0;
list_add(&governor->governor_list, &thermal_governor_list);
if (!def_governor && !strncmp(governor->name,
DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
def_governor = governor;
}
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node) {
/*
* only thermal zones with specified tz->tzp->governor_name
* may run with tz->govenor unset
*/
if (pos->governor)
continue;
name = pos->tzp->governor_name;
if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
int ret;
ret = thermal_set_governor(pos, governor);
if (ret)
dev_err(&pos->device,
"Failed to set governor %s for thermal zone %s: %d\n",
governor->name, pos->type, ret);
}
}
mutex_unlock(&thermal_list_lock);
mutex_unlock(&thermal_governor_lock);
return err;
}
void thermal_unregister_governor(struct thermal_governor *governor)
{
struct thermal_zone_device *pos;
if (!governor)
return;
mutex_lock(&thermal_governor_lock);
if (__find_governor(governor->name) == NULL)
goto exit;
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node) {
if (!strncasecmp(pos->governor->name, governor->name,
THERMAL_NAME_LENGTH))
thermal_set_governor(pos, NULL);
}
mutex_unlock(&thermal_list_lock);
list_del(&governor->governor_list);
exit:
mutex_unlock(&thermal_governor_lock);
return;
}
static int get_idr(struct idr *idr, struct mutex *lock, int *id)
{
int ret;
if (lock)
mutex_lock(lock);
ret = idr_alloc(idr, NULL, 0, 0, GFP_KERNEL);
if (lock)
mutex_unlock(lock);
if (unlikely(ret < 0))
return ret;
*id = ret;
return 0;
}
static void release_idr(struct idr *idr, struct mutex *lock, int id)
{
if (lock)
mutex_lock(lock);
idr_remove(idr, id);
if (lock)
mutex_unlock(lock);
}
int get_tz_trend(struct thermal_zone_device *tz, int trip)
{
enum thermal_trend trend;
if (tz->emul_temperature || !tz->ops->get_trend ||
tz->ops->get_trend(tz, trip, &trend)) {
if (tz->temperature > tz->last_temperature)
trend = THERMAL_TREND_RAISING;
else if (tz->temperature < tz->last_temperature)
trend = THERMAL_TREND_DROPPING;
else
trend = THERMAL_TREND_STABLE;
}
return trend;
}
EXPORT_SYMBOL(get_tz_trend);
struct thermal_instance *get_thermal_instance(struct thermal_zone_device *tz,
struct thermal_cooling_device *cdev, int trip)
{
struct thermal_instance *pos = NULL;
struct thermal_instance *target_instance = NULL;
mutex_lock(&tz->lock);
mutex_lock(&cdev->lock);
list_for_each_entry(pos, &tz->thermal_instances, tz_node) {
if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
target_instance = pos;
break;
}
}
mutex_unlock(&cdev->lock);
mutex_unlock(&tz->lock);
return target_instance;
}
EXPORT_SYMBOL(get_thermal_instance);
static void print_bind_err_msg(struct thermal_zone_device *tz,
struct thermal_cooling_device *cdev, int ret)
{
dev_err(&tz->device, "binding zone %s with cdev %s failed:%d\n",
tz->type, cdev->type, ret);
}
static void __bind(struct thermal_zone_device *tz, int mask,
struct thermal_cooling_device *cdev,
unsigned long *limits,
unsigned int weight)
{
int i, ret;
for (i = 0; i < tz->trips; i++) {
if (mask & (1 << i)) {
unsigned long upper, lower;
upper = THERMAL_NO_LIMIT;
lower = THERMAL_NO_LIMIT;
if (limits) {
lower = limits[i * 2];
upper = limits[i * 2 + 1];
}
ret = thermal_zone_bind_cooling_device(tz, i, cdev,
upper, lower,
weight);
if (ret)
print_bind_err_msg(tz, cdev, ret);
}
}
}
static void __unbind(struct thermal_zone_device *tz, int mask,
struct thermal_cooling_device *cdev)
{
int i;
for (i = 0; i < tz->trips; i++)
if (mask & (1 << i))
thermal_zone_unbind_cooling_device(tz, i, cdev);
}
static void bind_cdev(struct thermal_cooling_device *cdev)
{
int i, ret;
const struct thermal_zone_params *tzp;
struct thermal_zone_device *pos = NULL;
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node) {
if (!pos->tzp && !pos->ops->bind)
continue;
if (pos->ops->bind) {
ret = pos->ops->bind(pos, cdev);
if (ret)
print_bind_err_msg(pos, cdev, ret);
continue;
}
tzp = pos->tzp;
if (!tzp || !tzp->tbp)
continue;
for (i = 0; i < tzp->num_tbps; i++) {
if (tzp->tbp[i].cdev || !tzp->tbp[i].match)
continue;
if (tzp->tbp[i].match(pos, cdev))
continue;
tzp->tbp[i].cdev = cdev;
__bind(pos, tzp->tbp[i].trip_mask, cdev,
tzp->tbp[i].binding_limits,
tzp->tbp[i].weight);
}
}
mutex_unlock(&thermal_list_lock);
}
static void bind_tz(struct thermal_zone_device *tz)
{
int i, ret;
struct thermal_cooling_device *pos = NULL;
const struct thermal_zone_params *tzp = tz->tzp;
if (!tzp && !tz->ops->bind)
return;
mutex_lock(&thermal_list_lock);
/* If there is ops->bind, try to use ops->bind */
if (tz->ops->bind) {
list_for_each_entry(pos, &thermal_cdev_list, node) {
ret = tz->ops->bind(tz, pos);
if (ret)
print_bind_err_msg(tz, pos, ret);
}
goto exit;
}
if (!tzp || !tzp->tbp)
goto exit;
list_for_each_entry(pos, &thermal_cdev_list, node) {
for (i = 0; i < tzp->num_tbps; i++) {
if (tzp->tbp[i].cdev || !tzp->tbp[i].match)
continue;
if (tzp->tbp[i].match(tz, pos))
continue;
tzp->tbp[i].cdev = pos;
__bind(tz, tzp->tbp[i].trip_mask, pos,
tzp->tbp[i].binding_limits,
tzp->tbp[i].weight);
}
}
exit:
mutex_unlock(&thermal_list_lock);
}
static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
int delay)
{
if (delay > 1000)
mod_delayed_work(system_freezable_wq, &tz->poll_queue,
round_jiffies(msecs_to_jiffies(delay)));
else if (delay)
mod_delayed_work(system_freezable_wq, &tz->poll_queue,
msecs_to_jiffies(delay));
else
cancel_delayed_work(&tz->poll_queue);
}
static void monitor_thermal_zone(struct thermal_zone_device *tz)
{
mutex_lock(&tz->lock);
if (tz->passive)
thermal_zone_device_set_polling(tz, tz->passive_delay);
else if (tz->polling_delay)
thermal_zone_device_set_polling(tz, tz->polling_delay);
else
thermal_zone_device_set_polling(tz, 0);
mutex_unlock(&tz->lock);
}
static void handle_non_critical_trips(struct thermal_zone_device *tz,
int trip, enum thermal_trip_type trip_type)
{
tz->governor ? tz->governor->throttle(tz, trip) :
def_governor->throttle(tz, trip);
}
static void handle_critical_trips(struct thermal_zone_device *tz,
int trip, enum thermal_trip_type trip_type)
{
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int trip_temp;
tz->ops->get_trip_temp(tz, trip, &trip_temp);
/* If we have not crossed the trip_temp, we do not care. */
if (trip_temp <= 0 || tz->temperature < trip_temp)
return;
trace_thermal_zone_trip(tz, trip, trip_type);
if (tz->ops->notify)
tz->ops->notify(tz, trip, trip_type);
if (trip_type == THERMAL_TRIP_CRITICAL) {
dev_emerg(&tz->device,
"critical temperature reached(%d C),shutting down\n",
tz->temperature / 1000);
orderly_poweroff(true);
}
}
static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
{
enum thermal_trip_type type;
2016-03-18 02:03:24 +00:00
/* Ignore disabled trip points */
if (test_bit(trip, &tz->trips_disabled))
return;
tz->ops->get_trip_type(tz, trip, &type);
if (type == THERMAL_TRIP_CRITICAL || type == THERMAL_TRIP_HOT)
handle_critical_trips(tz, trip, type);
else
handle_non_critical_trips(tz, trip, type);
/*
* Alright, we handled this trip successfully.
* So, start monitoring again.
*/
monitor_thermal_zone(tz);
}
/**
* thermal_zone_get_temp() - returns the temperature of a thermal zone
* @tz: a valid pointer to a struct thermal_zone_device
* @temp: a valid pointer to where to store the resulting temperature.
*
* When a valid thermal zone reference is passed, it will fetch its
* temperature and fill @temp.
*
* Return: On success returns 0, an error code otherwise
*/
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
{
int ret = -EINVAL;
int count;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int crit_temp = INT_MAX;
enum thermal_trip_type type;
if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
goto exit;
mutex_lock(&tz->lock);
ret = tz->ops->get_temp(tz, temp);
if (IS_ENABLED(CONFIG_THERMAL_EMULATION) && tz->emul_temperature) {
for (count = 0; count < tz->trips; count++) {
ret = tz->ops->get_trip_type(tz, count, &type);
if (!ret && type == THERMAL_TRIP_CRITICAL) {
ret = tz->ops->get_trip_temp(tz, count,
&crit_temp);
break;
}
}
/*
* Only allow emulating a temperature when the real temperature
* is below the critical temperature so that the emulation code
* cannot hide critical conditions.
*/
if (!ret && *temp < crit_temp)
*temp = tz->emul_temperature;
}
mutex_unlock(&tz->lock);
exit:
return ret;
}
EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
void thermal_zone_set_trips(struct thermal_zone_device *tz)
{
int low = -INT_MAX;
int high = INT_MAX;
int trip_temp, hysteresis;
int i, ret;
mutex_lock(&tz->lock);
if (!tz->ops->set_trips || !tz->ops->get_trip_hyst)
goto exit;
for (i = 0; i < tz->trips; i++) {
int trip_low;
tz->ops->get_trip_temp(tz, i, &trip_temp);
tz->ops->get_trip_hyst(tz, i, &hysteresis);
trip_low = trip_temp - hysteresis;
if (trip_low < tz->temperature && trip_low > low)
low = trip_low;
if (trip_temp > tz->temperature && trip_temp < high)
high = trip_temp;
}
/* No need to change trip points */
if (tz->prev_low_trip == low && tz->prev_high_trip == high)
goto exit;
tz->prev_low_trip = low;
tz->prev_high_trip = high;
dev_dbg(&tz->device,
"new temperature boundaries: %d < x < %d\n", low, high);
/*
* Set a temperature window. When this window is left the driver
* must inform the thermal core via thermal_zone_device_update.
*/
ret = tz->ops->set_trips(tz, low, high);
if (ret)
dev_err(&tz->device, "Failed to set trips: %d\n", ret);
exit:
mutex_unlock(&tz->lock);
}
EXPORT_SYMBOL_GPL(thermal_zone_set_trips);
static void update_temperature(struct thermal_zone_device *tz)
{
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int temp, ret;
ret = thermal_zone_get_temp(tz, &temp);
if (ret) {
if (ret != -EAGAIN)
dev_warn(&tz->device,
"failed to read out thermal zone (%d)\n",
ret);
return;
}
mutex_lock(&tz->lock);
tz->last_temperature = tz->temperature;
tz->temperature = temp;
mutex_unlock(&tz->lock);
thermal: debug: add debug statement for core and step_wise To ease debugging thermal problem, add these dynamic debug statements so that user do not need rebuild kernel to see these info. Based on a patch from Zhang Rui for debugging on bugzilla: https://bugzilla.kernel.org/attachment.cgi?id=98671 A sample output after we turn on dynamic debug with the following cmd: # echo 'module thermal_sys +fp' > /sys/kernel/debug/dynamic_debug/control is like: [ 355.147627] update_temperature: thermal thermal_zone0: last_temperature=52000, current_temperature=55000 [ 355.147636] thermal_zone_trip_update: thermal thermal_zone0: Trip1[type=1,temp=79000]:trend=2,throttle=0 [ 355.147644] get_target_state: thermal cooling_device8: cur_state=0 [ 355.147647] thermal_zone_trip_update: thermal cooling_device8: old_target=-1, target=-1 [ 355.147652] get_target_state: thermal cooling_device7: cur_state=0 [ 355.147655] thermal_zone_trip_update: thermal cooling_device7: old_target=-1, target=-1 [ 355.147660] get_target_state: thermal cooling_device6: cur_state=0 [ 355.147663] thermal_zone_trip_update: thermal cooling_device6: old_target=-1, target=-1 [ 355.147668] get_target_state: thermal cooling_device5: cur_state=0 [ 355.147671] thermal_zone_trip_update: thermal cooling_device5: old_target=-1, target=-1 [ 355.147678] thermal_zone_trip_update: thermal thermal_zone0: Trip2[type=0,temp=90000]:trend=1,throttle=0 [ 355.147776] get_target_state: thermal cooling_device0: cur_state=0 [ 355.147783] thermal_zone_trip_update: thermal cooling_device0: old_target=-1, target=-1 [ 355.147792] thermal_zone_trip_update: thermal thermal_zone0: Trip3[type=0,temp=80000]:trend=1,throttle=0 [ 355.147845] get_target_state: thermal cooling_device1: cur_state=0 [ 355.147849] thermal_zone_trip_update: thermal cooling_device1: old_target=-1, target=-1 [ 355.147856] thermal_zone_trip_update: thermal thermal_zone0: Trip4[type=0,temp=70000]:trend=1,throttle=0 [ 355.147904] get_target_state: thermal cooling_device2: cur_state=0 [ 355.147908] thermal_zone_trip_update: thermal cooling_device2: old_target=-1, target=-1 [ 355.147915] thermal_zone_trip_update: thermal thermal_zone0: Trip5[type=0,temp=60000]:trend=1,throttle=0 [ 355.147963] get_target_state: thermal cooling_device3: cur_state=0 [ 355.147967] thermal_zone_trip_update: thermal cooling_device3: old_target=-1, target=-1 [ 355.147973] thermal_zone_trip_update: thermal thermal_zone0: Trip6[type=0,temp=55000]:trend=1,throttle=1 [ 355.148022] get_target_state: thermal cooling_device4: cur_state=0 [ 355.148025] thermal_zone_trip_update: thermal cooling_device4: old_target=-1, target=1 [ 355.148036] thermal_cdev_update: thermal cooling_device4: zone0->target=1 [ 355.169279] thermal_cdev_update: thermal cooling_device4: set to state 1 Signed-off-by: Aaron Lu <aaron.lu@intel.com> Acked-by: Eduardo Valentin <eduardo.valentin@ti.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2013-12-02 05:54:26 +00:00
trace_thermal_temperature(tz);
if (tz->last_temperature == THERMAL_TEMP_INVALID)
dev_dbg(&tz->device, "last_temperature N/A, current_temperature=%d\n",
tz->temperature);
else
dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n",
tz->last_temperature, tz->temperature);
}
static void thermal_zone_device_reset(struct thermal_zone_device *tz)
{
struct thermal_instance *pos;
tz->temperature = THERMAL_TEMP_INVALID;
tz->passive = 0;
list_for_each_entry(pos, &tz->thermal_instances, tz_node)
pos->initialized = false;
}
void thermal_zone_device_update(struct thermal_zone_device *tz,
enum thermal_notify_event event)
{
int count;
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
if (atomic_read(&in_suspend))
return;
if (!tz->ops->get_temp)
return;
update_temperature(tz);
thermal_zone_set_trips(tz);
tz->notify_event = event;
for (count = 0; count < tz->trips; count++)
handle_thermal_trip(tz, count);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_update);
static void thermal_zone_device_check(struct work_struct *work)
{
struct thermal_zone_device *tz = container_of(work, struct
thermal_zone_device,
poll_queue.work);
thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
}
/* sys I/F for thermal zone */
#define to_thermal_zone(_dev) \
container_of(_dev, struct thermal_zone_device, device)
static ssize_t
type_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
return sprintf(buf, "%s\n", tz->type);
}
static ssize_t
temp_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int temperature, ret;
ret = thermal_zone_get_temp(tz, &temperature);
if (ret)
return ret;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
return sprintf(buf, "%d\n", temperature);
}
static ssize_t
mode_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
enum thermal_device_mode mode;
int result;
if (!tz->ops->get_mode)
return -EPERM;
result = tz->ops->get_mode(tz, &mode);
if (result)
return result;
return sprintf(buf, "%s\n", mode == THERMAL_DEVICE_ENABLED ? "enabled"
: "disabled");
}
static ssize_t
mode_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int result;
if (!tz->ops->set_mode)
return -EPERM;
if (!strncmp(buf, "enabled", sizeof("enabled") - 1))
result = tz->ops->set_mode(tz, THERMAL_DEVICE_ENABLED);
else if (!strncmp(buf, "disabled", sizeof("disabled") - 1))
result = tz->ops->set_mode(tz, THERMAL_DEVICE_DISABLED);
else
result = -EINVAL;
if (result)
return result;
return count;
}
static ssize_t
trip_point_type_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
enum thermal_trip_type type;
int trip, result;
if (!tz->ops->get_trip_type)
return -EPERM;
if (!sscanf(attr->attr.name, "trip_point_%d_type", &trip))
return -EINVAL;
result = tz->ops->get_trip_type(tz, trip, &type);
if (result)
return result;
switch (type) {
case THERMAL_TRIP_CRITICAL:
return sprintf(buf, "critical\n");
case THERMAL_TRIP_HOT:
return sprintf(buf, "hot\n");
case THERMAL_TRIP_PASSIVE:
return sprintf(buf, "passive\n");
case THERMAL_TRIP_ACTIVE:
return sprintf(buf, "active\n");
default:
return sprintf(buf, "unknown\n");
}
}
static ssize_t
trip_point_temp_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int trip, ret;
int temperature;
if (!tz->ops->set_trip_temp)
return -EPERM;
if (!sscanf(attr->attr.name, "trip_point_%d_temp", &trip))
return -EINVAL;
if (kstrtoint(buf, 10, &temperature))
return -EINVAL;
ret = tz->ops->set_trip_temp(tz, trip, temperature);
if (ret)
return ret;
thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
return count;
}
static ssize_t
trip_point_temp_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int trip, ret;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int temperature;
if (!tz->ops->get_trip_temp)
return -EPERM;
if (!sscanf(attr->attr.name, "trip_point_%d_temp", &trip))
return -EINVAL;
ret = tz->ops->get_trip_temp(tz, trip, &temperature);
if (ret)
return ret;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
return sprintf(buf, "%d\n", temperature);
}
static ssize_t
trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int trip, ret;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int temperature;
if (!tz->ops->set_trip_hyst)
return -EPERM;
if (!sscanf(attr->attr.name, "trip_point_%d_hyst", &trip))
return -EINVAL;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
if (kstrtoint(buf, 10, &temperature))
return -EINVAL;
/*
* We are not doing any check on the 'temperature' value
* here. The driver implementing 'set_trip_hyst' has to
* take care of this.
*/
ret = tz->ops->set_trip_hyst(tz, trip, temperature);
if (!ret)
thermal_zone_set_trips(tz);
return ret ? ret : count;
}
static ssize_t
trip_point_hyst_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int trip, ret;
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
int temperature;
if (!tz->ops->get_trip_hyst)
return -EPERM;
if (!sscanf(attr->attr.name, "trip_point_%d_hyst", &trip))
return -EINVAL;
ret = tz->ops->get_trip_hyst(tz, trip, &temperature);
thermal: consistently use int for temperatures The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Lukasz Majewski <l.majewski@samsung.com> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Peter Feuerer <peter@piie.net> Cc: Punit Agrawal <punit.agrawal@arm.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Eduardo Valentin <edubezval@gmail.com> Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare <jdelvare@suse.de> Cc: Peter Feuerer <peter@piie.net> Cc: Heiko Stuebner <heiko@sntech.de> Cc: Lukasz Majewski <l.majewski@samsung.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck <linux@roeck-us.net> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Maxime Ripard <maxime.ripard@free-electrons.com> Cc: Darren Hart <dvhart@infradead.org> Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2015-07-24 06:12:54 +00:00
return ret ? ret : sprintf(buf, "%d\n", temperature);
}
static ssize_t
passive_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
struct thermal_cooling_device *cdev = NULL;
int state;
if (!sscanf(buf, "%d\n", &state))
return -EINVAL;
/* sanity check: values below 1000 millicelcius don't make sense
* and can cause the system to go into a thermal heart attack
*/
if (state && state < 1000)
return -EINVAL;
if (state && !tz->forced_passive) {
mutex_lock(&thermal_list_lock);
list_for_each_entry(cdev, &thermal_cdev_list, node) {
if (!strncmp("Processor", cdev->type,
sizeof("Processor")))
thermal_zone_bind_cooling_device(tz,
THERMAL_TRIPS_NONE, cdev,
THERMAL_NO_LIMIT,
THERMAL_NO_LIMIT,
THERMAL_WEIGHT_DEFAULT);
}
mutex_unlock(&thermal_list_lock);
if (!tz->passive_delay)
tz->passive_delay = 1000;
} else if (!state && tz->forced_passive) {
mutex_lock(&thermal_list_lock);
list_for_each_entry(cdev, &thermal_cdev_list, node) {
if (!strncmp("Processor", cdev->type,
sizeof("Processor")))
thermal_zone_unbind_cooling_device(tz,
THERMAL_TRIPS_NONE,
cdev);
}
mutex_unlock(&thermal_list_lock);
tz->passive_delay = 0;
}
tz->forced_passive = state;
thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
return count;
}
static ssize_t
passive_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
return sprintf(buf, "%d\n", tz->forced_passive);
}
static ssize_t
policy_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int ret = -EINVAL;
struct thermal_zone_device *tz = to_thermal_zone(dev);
struct thermal_governor *gov;
char name[THERMAL_NAME_LENGTH];
snprintf(name, sizeof(name), "%s", buf);
mutex_lock(&thermal_governor_lock);
mutex_lock(&tz->lock);
gov = __find_governor(strim(name));
if (!gov)
goto exit;
ret = thermal_set_governor(tz, gov);
if (!ret)
ret = count;
exit:
mutex_unlock(&tz->lock);
mutex_unlock(&thermal_governor_lock);
return ret;
}
static ssize_t
policy_show(struct device *dev, struct device_attribute *devattr, char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
return sprintf(buf, "%s\n", tz->governor->name);
}
static ssize_t
available_policies_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
struct thermal_governor *pos;
ssize_t count = 0;
ssize_t size = PAGE_SIZE;
mutex_lock(&thermal_governor_lock);
list_for_each_entry(pos, &thermal_governor_list, governor_list) {
size = PAGE_SIZE - count;
count += scnprintf(buf + count, size, "%s ", pos->name);
}
count += scnprintf(buf + count, size, "\n");
mutex_unlock(&thermal_governor_lock);
return count;
}
static ssize_t
emul_temp_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
int ret = 0;
int temperature;
if (kstrtoint(buf, 10, &temperature))
return -EINVAL;
if (!tz->ops->set_emul_temp) {
mutex_lock(&tz->lock);
tz->emul_temperature = temperature;
mutex_unlock(&tz->lock);
} else {
ret = tz->ops->set_emul_temp(tz, temperature);
}
if (!ret)
thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
return ret ? ret : count;
}
static DEVICE_ATTR(emul_temp, S_IWUSR, NULL, emul_temp_store);
static ssize_t
sustainable_power_show(struct device *dev, struct device_attribute *devattr,
char *buf)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
if (tz->tzp)
return sprintf(buf, "%u\n", tz->tzp->sustainable_power);
else
return -EIO;
}
static ssize_t
sustainable_power_store(struct device *dev, struct device_attribute *devattr,
const char *buf, size_t count)
{
struct thermal_zone_device *tz = to_thermal_zone(dev);
u32 sustainable_power;
if (!tz->tzp)
return -EIO;
if (kstrtou32(buf, 10, &sustainable_power))
return -EINVAL;
tz->tzp->sustainable_power = sustainable_power;
return count;
}
static DEVICE_ATTR(sustainable_power, S_IWUSR | S_IRUGO, sustainable_power_show,
sustainable_power_store);
#define create_s32_tzp_attr(name) \
static ssize_t \
name##_show(struct device *dev, struct device_attribute *devattr, \
char *buf) \
{ \
struct thermal_zone_device *tz = to_thermal_zone(dev); \
\
if (tz->tzp) \
return sprintf(buf, "%d\n", tz->tzp->name); \
else \
return -EIO; \
} \
\
static ssize_t \
name##_store(struct device *dev, struct device_attribute *devattr, \
const char *buf, size_t count) \
{ \
struct thermal_zone_device *tz = to_thermal_zone(dev); \
s32 value; \
\
if (!tz->tzp) \
return -EIO; \
\
if (kstrtos32(buf, 10, &value)) \
return -EINVAL; \
\
tz->tzp->name = value; \
\
return count; \
} \
static DEVICE_ATTR(name, S_IWUSR | S_IRUGO, name##_show, name##_store)
create_s32_tzp_attr(k_po);
create_s32_tzp_attr(k_pu);
create_s32_tzp_attr(k_i);
create_s32_tzp_attr(k_d);
create_s32_tzp_attr(integral_cutoff);
create_s32_tzp_attr(slope);
create_s32_tzp_attr(offset);
#undef create_s32_tzp_attr
static struct device_attribute *dev_tzp_attrs[] = {
&dev_attr_sustainable_power,
&dev_attr_k_po,
&dev_attr_k_pu,
&dev_attr_k_i,
&dev_attr_k_d,
&dev_attr_integral_cutoff,
&dev_attr_slope,
&dev_attr_offset,
};
static int create_tzp_attrs(struct device *dev)
{
int i;
for (i = 0; i < ARRAY_SIZE(dev_tzp_attrs); i++) {
int ret;
struct device_attribute *dev_attr = dev_tzp_attrs[i];
ret = device_create_file(dev, dev_attr);
if (ret)
return ret;
}
return 0;
}
/**
* power_actor_get_max_power() - get the maximum power that a cdev can consume
* @cdev: pointer to &thermal_cooling_device
* @tz: a valid thermal zone device pointer
* @max_power: pointer in which to store the maximum power
*
* Calculate the maximum power consumption in milliwats that the
* cooling device can currently consume and store it in @max_power.
*
* Return: 0 on success, -EINVAL if @cdev doesn't support the
* power_actor API or -E* on other error.
*/
int power_actor_get_max_power(struct thermal_cooling_device *cdev,
struct thermal_zone_device *tz, u32 *max_power)
{
if (!cdev_is_power_actor(cdev))
return -EINVAL;
return cdev->ops->state2power(cdev, tz, 0, max_power);
}
/**
* power_actor_get_min_power() - get the mainimum power that a cdev can consume
* @cdev: pointer to &thermal_cooling_device
* @tz: a valid thermal zone device pointer
* @min_power: pointer in which to store the minimum power
*
* Calculate the minimum power consumption in milliwatts that the
* cooling device can currently consume and store it in @min_power.
*
* Return: 0 on success, -EINVAL if @cdev doesn't support the
* power_actor API or -E* on other error.
*/
int power_actor_get_min_power(struct thermal_cooling_device *cdev,
struct thermal_zone_device *tz, u32 *min_power)
{
unsigned long max_state;
int ret;
if (!cdev_is_power_actor(cdev))
return -EINVAL;
ret = cdev->ops->get_max_state(cdev, &max_state);
if (ret)
return ret;
return cdev->ops->state2power(cdev, tz, max_state, min_power);
}
/**
* power_actor_set_power() - limit the maximum power that a cooling device can consume
* @cdev: pointer to &thermal_cooling_device
* @instance: thermal instance to update
* @power: the power in milliwatts
*
* Set the cooling device to consume at most @power milliwatts.
*
* Return: 0 on success, -EINVAL if the cooling device does not
* implement the power actor API or -E* for other failures.
*/
int power_actor_set_power(struct thermal_cooling_device *cdev,
struct thermal_instance *instance, u32 power)
{
unsigned long state;
int ret;
if (!cdev_is_power_actor(cdev))
return -EINVAL;
ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
if (ret)
return ret;
instance->target = state;
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
mutex_lock(&cdev->lock);
cdev->updated = false;
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
mutex_unlock(&cdev->lock);
thermal_cdev_update(cdev);
return 0;
}
static DEVICE_ATTR(type, 0444, type_show, NULL);
static DEVICE_ATTR(temp, 0444, temp_show, NULL);
static DEVICE_ATTR(mode, 0644, mode_show, mode_store);
static DEVICE_ATTR(passive, S_IRUGO | S_IWUSR, passive_show, passive_store);
static DEVICE_ATTR(policy, S_IRUGO | S_IWUSR, policy_show, policy_store);
static DEVICE_ATTR(available_policies, S_IRUGO, available_policies_show, NULL);
/* sys I/F for cooling device */
#define to_cooling_device(_dev) \
container_of(_dev, struct thermal_cooling_device, device)
static ssize_t
thermal_cooling_device_type_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct thermal_cooling_device *cdev = to_cooling_device(dev);
return sprintf(buf, "%s\n", cdev->type);
}
static ssize_t
thermal_cooling_device_max_state_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct thermal_cooling_device *cdev = to_cooling_device(dev);
unsigned long state;
int ret;
ret = cdev->ops->get_max_state(cdev, &state);
if (ret)
return ret;
return sprintf(buf, "%ld\n", state);
}
static ssize_t
thermal_cooling_device_cur_state_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct thermal_cooling_device *cdev = to_cooling_device(dev);
unsigned long state;
int ret;
ret = cdev->ops->get_cur_state(cdev, &state);
if (ret)
return ret;
return sprintf(buf, "%ld\n", state);
}
static ssize_t
thermal_cooling_device_cur_state_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_cooling_device *cdev = to_cooling_device(dev);
unsigned long state;
int result;
if (!sscanf(buf, "%ld\n", &state))
return -EINVAL;
if ((long)state < 0)
return -EINVAL;
result = cdev->ops->set_cur_state(cdev, state);
if (result)
return result;
return count;
}
static struct device_attribute dev_attr_cdev_type =
__ATTR(type, 0444, thermal_cooling_device_type_show, NULL);
static DEVICE_ATTR(max_state, 0444,
thermal_cooling_device_max_state_show, NULL);
static DEVICE_ATTR(cur_state, 0644,
thermal_cooling_device_cur_state_show,
thermal_cooling_device_cur_state_store);
static ssize_t
thermal_cooling_device_trip_point_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct thermal_instance *instance;
instance =
container_of(attr, struct thermal_instance, attr);
if (instance->trip == THERMAL_TRIPS_NONE)
return sprintf(buf, "-1\n");
else
return sprintf(buf, "%d\n", instance->trip);
}
static struct attribute *cooling_device_attrs[] = {
&dev_attr_cdev_type.attr,
&dev_attr_max_state.attr,
&dev_attr_cur_state.attr,
NULL,
};
static const struct attribute_group cooling_device_attr_group = {
.attrs = cooling_device_attrs,
};
static const struct attribute_group *cooling_device_attr_groups[] = {
&cooling_device_attr_group,
NULL,
};
static ssize_t
thermal_cooling_device_weight_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct thermal_instance *instance;
instance = container_of(attr, struct thermal_instance, weight_attr);
return sprintf(buf, "%d\n", instance->weight);
}
static ssize_t
thermal_cooling_device_weight_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct thermal_instance *instance;
int ret, weight;
ret = kstrtoint(buf, 0, &weight);
if (ret)
return ret;
instance = container_of(attr, struct thermal_instance, weight_attr);
instance->weight = weight;
return count;
}
/* Device management */
/**
* thermal_zone_bind_cooling_device() - bind a cooling device to a thermal zone
* @tz: pointer to struct thermal_zone_device
* @trip: indicates which trip point the cooling devices is
* associated with in this thermal zone.
* @cdev: pointer to struct thermal_cooling_device
* @upper: the Maximum cooling state for this trip point.
* THERMAL_NO_LIMIT means no upper limit,
* and the cooling device can be in max_state.
* @lower: the Minimum cooling state can be used for this trip point.
* THERMAL_NO_LIMIT means no lower limit,
* and the cooling device can be in cooling state 0.
* @weight: The weight of the cooling device to be bound to the
* thermal zone. Use THERMAL_WEIGHT_DEFAULT for the
* default value
*
* This interface function bind a thermal cooling device to the certain trip
* point of a thermal zone device.
* This function is usually called in the thermal zone device .bind callback.
*
* Return: 0 on success, the proper error value otherwise.
*/
int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
int trip,
struct thermal_cooling_device *cdev,
unsigned long upper, unsigned long lower,
unsigned int weight)
{
struct thermal_instance *dev;
struct thermal_instance *pos;
struct thermal_zone_device *pos1;
struct thermal_cooling_device *pos2;
unsigned long max_state;
int result, ret;
if (trip >= tz->trips || (trip < 0 && trip != THERMAL_TRIPS_NONE))
return -EINVAL;
list_for_each_entry(pos1, &thermal_tz_list, node) {
if (pos1 == tz)
break;
}
list_for_each_entry(pos2, &thermal_cdev_list, node) {
if (pos2 == cdev)
break;
}
if (tz != pos1 || cdev != pos2)
return -EINVAL;
ret = cdev->ops->get_max_state(cdev, &max_state);
if (ret)
return ret;
/* lower default 0, upper default max_state */
lower = lower == THERMAL_NO_LIMIT ? 0 : lower;
upper = upper == THERMAL_NO_LIMIT ? max_state : upper;
if (lower > upper || upper > max_state)
return -EINVAL;
dev =
kzalloc(sizeof(struct thermal_instance), GFP_KERNEL);
if (!dev)
return -ENOMEM;
dev->tz = tz;
dev->cdev = cdev;
dev->trip = trip;
dev->upper = upper;
dev->lower = lower;
dev->target = THERMAL_NO_TARGET;
dev->weight = weight;
result = get_idr(&tz->idr, &tz->lock, &dev->id);
if (result)
goto free_mem;
sprintf(dev->name, "cdev%d", dev->id);
result =
sysfs_create_link(&tz->device.kobj, &cdev->device.kobj, dev->name);
if (result)
goto release_idr;
sprintf(dev->attr_name, "cdev%d_trip_point", dev->id);
sysfs_attr_init(&dev->attr.attr);
dev->attr.attr.name = dev->attr_name;
dev->attr.attr.mode = 0444;
dev->attr.show = thermal_cooling_device_trip_point_show;
result = device_create_file(&tz->device, &dev->attr);
if (result)
goto remove_symbol_link;
sprintf(dev->weight_attr_name, "cdev%d_weight", dev->id);
sysfs_attr_init(&dev->weight_attr.attr);
dev->weight_attr.attr.name = dev->weight_attr_name;
dev->weight_attr.attr.mode = S_IWUSR | S_IRUGO;
dev->weight_attr.show = thermal_cooling_device_weight_show;
dev->weight_attr.store = thermal_cooling_device_weight_store;
result = device_create_file(&tz->device, &dev->weight_attr);
if (result)
goto remove_trip_file;
mutex_lock(&tz->lock);
mutex_lock(&cdev->lock);
list_for_each_entry(pos, &tz->thermal_instances, tz_node)
if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
result = -EEXIST;
break;
}
if (!result) {
list_add_tail(&dev->tz_node, &tz->thermal_instances);
list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
atomic_set(&tz->need_update, 1);
}
mutex_unlock(&cdev->lock);
mutex_unlock(&tz->lock);
if (!result)
return 0;
device_remove_file(&tz->device, &dev->weight_attr);
remove_trip_file:
device_remove_file(&tz->device, &dev->attr);
remove_symbol_link:
sysfs_remove_link(&tz->device.kobj, dev->name);
release_idr:
release_idr(&tz->idr, &tz->lock, dev->id);
free_mem:
kfree(dev);
return result;
}
EXPORT_SYMBOL_GPL(thermal_zone_bind_cooling_device);
/**
* thermal_zone_unbind_cooling_device() - unbind a cooling device from a
* thermal zone.
* @tz: pointer to a struct thermal_zone_device.
* @trip: indicates which trip point the cooling devices is
* associated with in this thermal zone.
* @cdev: pointer to a struct thermal_cooling_device.
*
* This interface function unbind a thermal cooling device from the certain
* trip point of a thermal zone device.
* This function is usually called in the thermal zone device .unbind callback.
*
* Return: 0 on success, the proper error value otherwise.
*/
int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
int trip,
struct thermal_cooling_device *cdev)
{
struct thermal_instance *pos, *next;
mutex_lock(&tz->lock);
mutex_lock(&cdev->lock);
list_for_each_entry_safe(pos, next, &tz->thermal_instances, tz_node) {
if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
list_del(&pos->tz_node);
list_del(&pos->cdev_node);
mutex_unlock(&cdev->lock);
mutex_unlock(&tz->lock);
goto unbind;
}
}
mutex_unlock(&cdev->lock);
mutex_unlock(&tz->lock);
return -ENODEV;
unbind:
thermal: remove dangling 'weight_attr' device file This file isn't getting removed while we unbind a device from thermal zone. And this causes following messages when the device is registered again: WARNING: CPU: 0 PID: 2228 at /home/viresh/linux/fs/sysfs/dir.c:31 sysfs_warn_dup+0x60/0x70() sysfs: cannot create duplicate filename '/devices/virtual/thermal/thermal_zone0/cdev0_weight' Modules linked in: cpufreq_dt(+) [last unloaded: cpufreq_dt] CPU: 0 PID: 2228 Comm: insmod Not tainted 4.2.0-rc3-00059-g44fffd9473eb #272 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [<c00153e8>] (unwind_backtrace) from [<c0012368>] (show_stack+0x10/0x14) [<c0012368>] (show_stack) from [<c053a684>] (dump_stack+0x84/0xc4) [<c053a684>] (dump_stack) from [<c002284c>] (warn_slowpath_common+0x80/0xb0) [<c002284c>] (warn_slowpath_common) from [<c00228ac>] (warn_slowpath_fmt+0x30/0x40) [<c00228ac>] (warn_slowpath_fmt) from [<c012d524>] (sysfs_warn_dup+0x60/0x70) [<c012d524>] (sysfs_warn_dup) from [<c012d244>] (sysfs_add_file_mode_ns+0x13c/0x190) [<c012d244>] (sysfs_add_file_mode_ns) from [<c012d2d4>] (sysfs_create_file_ns+0x3c/0x48) [<c012d2d4>] (sysfs_create_file_ns) from [<c03c04a8>] (thermal_zone_bind_cooling_device+0x260/0x358) [<c03c04a8>] (thermal_zone_bind_cooling_device) from [<c03c2e70>] (of_thermal_bind+0x88/0xb4) [<c03c2e70>] (of_thermal_bind) from [<c03c10d0>] (__thermal_cooling_device_register+0x17c/0x2e0) [<c03c10d0>] (__thermal_cooling_device_register) from [<c03c3f50>] (__cpufreq_cooling_register+0x3a0/0x51c) [<c03c3f50>] (__cpufreq_cooling_register) from [<bf00505c>] (cpufreq_ready+0x44/0x88 [cpufreq_dt]) [<bf00505c>] (cpufreq_ready [cpufreq_dt]) from [<c03d6c30>] (cpufreq_add_dev+0x4a0/0x7dc) [<c03d6c30>] (cpufreq_add_dev) from [<c02cd3ec>] (subsys_interface_register+0x94/0xd8) [<c02cd3ec>] (subsys_interface_register) from [<c03d785c>] (cpufreq_register_driver+0x10c/0x1f0) [<c03d785c>] (cpufreq_register_driver) from [<bf0057d4>] (dt_cpufreq_probe+0x60/0x8c [cpufreq_dt]) [<bf0057d4>] (dt_cpufreq_probe [cpufreq_dt]) from [<c02d03e4>] (platform_drv_probe+0x44/0xa4) [<c02d03e4>] (platform_drv_probe) from [<c02cead8>] (driver_probe_device+0x174/0x2b4) [<c02cead8>] (driver_probe_device) from [<c02ceca4>] (__driver_attach+0x8c/0x90) [<c02ceca4>] (__driver_attach) from [<c02cd078>] (bus_for_each_dev+0x68/0x9c) [<c02cd078>] (bus_for_each_dev) from [<c02ce2f0>] (bus_add_driver+0x19c/0x214) [<c02ce2f0>] (bus_add_driver) from [<c02cf490>] (driver_register+0x78/0xf8) [<c02cf490>] (driver_register) from [<c0009710>] (do_one_initcall+0x8c/0x1d4) [<c0009710>] (do_one_initcall) from [<c05396b0>] (do_init_module+0x5c/0x1b8) [<c05396b0>] (do_init_module) from [<c0086490>] (load_module+0xd34/0xed8) [<c0086490>] (load_module) from [<c0086704>] (SyS_init_module+0xd0/0x120) [<c0086704>] (SyS_init_module) from [<c000f480>] (ret_fast_syscall+0x0/0x3c) ---[ end trace 3be0e7b7dc6e3c4f ]--- Fixes: db91651311c8 ("thermal: export weight to sysfs") Acked-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
2015-07-23 09:02:32 +00:00
device_remove_file(&tz->device, &pos->weight_attr);
device_remove_file(&tz->device, &pos->attr);
sysfs_remove_link(&tz->device.kobj, pos->name);
release_idr(&tz->idr, &tz->lock, pos->id);
kfree(pos);
return 0;
}
EXPORT_SYMBOL_GPL(thermal_zone_unbind_cooling_device);
static void thermal_release(struct device *dev)
{
struct thermal_zone_device *tz;
struct thermal_cooling_device *cdev;
if (!strncmp(dev_name(dev), "thermal_zone",
sizeof("thermal_zone") - 1)) {
tz = to_thermal_zone(dev);
kfree(tz);
} else if(!strncmp(dev_name(dev), "cooling_device",
sizeof("cooling_device") - 1)){
cdev = to_cooling_device(dev);
kfree(cdev);
}
}
static struct class thermal_class = {
.name = "thermal",
.dev_release = thermal_release,
};
/**
* __thermal_cooling_device_register() - register a new thermal cooling device
* @np: a pointer to a device tree node.
* @type: the thermal cooling device type.
* @devdata: device private data.
* @ops: standard thermal cooling devices callbacks.
*
* This interface function adds a new thermal cooling device (fan/processor/...)
* to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
* to all the thermal zone devices registered at the same time.
* It also gives the opportunity to link the cooling device to a device tree
* node, so that it can be bound to a thermal zone created out of device tree.
*
* Return: a pointer to the created struct thermal_cooling_device or an
* ERR_PTR. Caller must check return value with IS_ERR*() helpers.
*/
static struct thermal_cooling_device *
__thermal_cooling_device_register(struct device_node *np,
char *type, void *devdata,
const struct thermal_cooling_device_ops *ops)
{
struct thermal_cooling_device *cdev;
struct thermal_zone_device *pos = NULL;
int result;
if (type && strlen(type) >= THERMAL_NAME_LENGTH)
return ERR_PTR(-EINVAL);
if (!ops || !ops->get_max_state || !ops->get_cur_state ||
!ops->set_cur_state)
return ERR_PTR(-EINVAL);
cdev = kzalloc(sizeof(struct thermal_cooling_device), GFP_KERNEL);
if (!cdev)
return ERR_PTR(-ENOMEM);
result = get_idr(&thermal_cdev_idr, &thermal_idr_lock, &cdev->id);
if (result) {
kfree(cdev);
return ERR_PTR(result);
}
strlcpy(cdev->type, type ? : "", sizeof(cdev->type));
mutex_init(&cdev->lock);
INIT_LIST_HEAD(&cdev->thermal_instances);
cdev->np = np;
cdev->ops = ops;
cdev->updated = false;
cdev->device.class = &thermal_class;
cdev->device.groups = cooling_device_attr_groups;
cdev->devdata = devdata;
dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
result = device_register(&cdev->device);
if (result) {
release_idr(&thermal_cdev_idr, &thermal_idr_lock, cdev->id);
kfree(cdev);
return ERR_PTR(result);
}
/* Add 'this' new cdev to the global cdev list */
mutex_lock(&thermal_list_lock);
list_add(&cdev->node, &thermal_cdev_list);
mutex_unlock(&thermal_list_lock);
/* Update binding information for 'this' new cdev */
bind_cdev(cdev);
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node)
if (atomic_cmpxchg(&pos->need_update, 1, 0))
thermal_zone_device_update(pos,
THERMAL_EVENT_UNSPECIFIED);
mutex_unlock(&thermal_list_lock);
return cdev;
}
/**
* thermal_cooling_device_register() - register a new thermal cooling device
* @type: the thermal cooling device type.
* @devdata: device private data.
* @ops: standard thermal cooling devices callbacks.
*
* This interface function adds a new thermal cooling device (fan/processor/...)
* to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
* to all the thermal zone devices registered at the same time.
*
* Return: a pointer to the created struct thermal_cooling_device or an
* ERR_PTR. Caller must check return value with IS_ERR*() helpers.
*/
struct thermal_cooling_device *
thermal_cooling_device_register(char *type, void *devdata,
const struct thermal_cooling_device_ops *ops)
{
return __thermal_cooling_device_register(NULL, type, devdata, ops);
}
EXPORT_SYMBOL_GPL(thermal_cooling_device_register);
/**
* thermal_of_cooling_device_register() - register an OF thermal cooling device
* @np: a pointer to a device tree node.
* @type: the thermal cooling device type.
* @devdata: device private data.
* @ops: standard thermal cooling devices callbacks.
*
* This function will register a cooling device with device tree node reference.
* This interface function adds a new thermal cooling device (fan/processor/...)
* to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
* to all the thermal zone devices registered at the same time.
*
* Return: a pointer to the created struct thermal_cooling_device or an
* ERR_PTR. Caller must check return value with IS_ERR*() helpers.
*/
struct thermal_cooling_device *
thermal_of_cooling_device_register(struct device_node *np,
char *type, void *devdata,
const struct thermal_cooling_device_ops *ops)
{
return __thermal_cooling_device_register(np, type, devdata, ops);
}
EXPORT_SYMBOL_GPL(thermal_of_cooling_device_register);
/**
* thermal_cooling_device_unregister - removes the registered thermal cooling device
* @cdev: the thermal cooling device to remove.
*
* thermal_cooling_device_unregister() must be called when the device is no
* longer needed.
*/
void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
{
int i;
const struct thermal_zone_params *tzp;
struct thermal_zone_device *tz;
struct thermal_cooling_device *pos = NULL;
if (!cdev)
return;
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_cdev_list, node)
if (pos == cdev)
break;
if (pos != cdev) {
/* thermal cooling device not found */
mutex_unlock(&thermal_list_lock);
return;
}
list_del(&cdev->node);
/* Unbind all thermal zones associated with 'this' cdev */
list_for_each_entry(tz, &thermal_tz_list, node) {
if (tz->ops->unbind) {
tz->ops->unbind(tz, cdev);
continue;
}
if (!tz->tzp || !tz->tzp->tbp)
continue;
tzp = tz->tzp;
for (i = 0; i < tzp->num_tbps; i++) {
if (tzp->tbp[i].cdev == cdev) {
__unbind(tz, tzp->tbp[i].trip_mask, cdev);
tzp->tbp[i].cdev = NULL;
}
}
}
mutex_unlock(&thermal_list_lock);
if (cdev->type[0])
device_remove_file(&cdev->device, &dev_attr_cdev_type);
device_remove_file(&cdev->device, &dev_attr_max_state);
device_remove_file(&cdev->device, &dev_attr_cur_state);
release_idr(&thermal_cdev_idr, &thermal_idr_lock, cdev->id);
device_unregister(&cdev->device);
return;
}
EXPORT_SYMBOL_GPL(thermal_cooling_device_unregister);
void thermal_cdev_update(struct thermal_cooling_device *cdev)
{
struct thermal_instance *instance;
unsigned long target = 0;
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
mutex_lock(&cdev->lock);
/* cooling device is updated*/
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
if (cdev->updated) {
mutex_unlock(&cdev->lock);
return;
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
}
/* Make sure cdev enters the deepest cooling state */
list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) {
thermal: debug: add debug statement for core and step_wise To ease debugging thermal problem, add these dynamic debug statements so that user do not need rebuild kernel to see these info. Based on a patch from Zhang Rui for debugging on bugzilla: https://bugzilla.kernel.org/attachment.cgi?id=98671 A sample output after we turn on dynamic debug with the following cmd: # echo 'module thermal_sys +fp' > /sys/kernel/debug/dynamic_debug/control is like: [ 355.147627] update_temperature: thermal thermal_zone0: last_temperature=52000, current_temperature=55000 [ 355.147636] thermal_zone_trip_update: thermal thermal_zone0: Trip1[type=1,temp=79000]:trend=2,throttle=0 [ 355.147644] get_target_state: thermal cooling_device8: cur_state=0 [ 355.147647] thermal_zone_trip_update: thermal cooling_device8: old_target=-1, target=-1 [ 355.147652] get_target_state: thermal cooling_device7: cur_state=0 [ 355.147655] thermal_zone_trip_update: thermal cooling_device7: old_target=-1, target=-1 [ 355.147660] get_target_state: thermal cooling_device6: cur_state=0 [ 355.147663] thermal_zone_trip_update: thermal cooling_device6: old_target=-1, target=-1 [ 355.147668] get_target_state: thermal cooling_device5: cur_state=0 [ 355.147671] thermal_zone_trip_update: thermal cooling_device5: old_target=-1, target=-1 [ 355.147678] thermal_zone_trip_update: thermal thermal_zone0: Trip2[type=0,temp=90000]:trend=1,throttle=0 [ 355.147776] get_target_state: thermal cooling_device0: cur_state=0 [ 355.147783] thermal_zone_trip_update: thermal cooling_device0: old_target=-1, target=-1 [ 355.147792] thermal_zone_trip_update: thermal thermal_zone0: Trip3[type=0,temp=80000]:trend=1,throttle=0 [ 355.147845] get_target_state: thermal cooling_device1: cur_state=0 [ 355.147849] thermal_zone_trip_update: thermal cooling_device1: old_target=-1, target=-1 [ 355.147856] thermal_zone_trip_update: thermal thermal_zone0: Trip4[type=0,temp=70000]:trend=1,throttle=0 [ 355.147904] get_target_state: thermal cooling_device2: cur_state=0 [ 355.147908] thermal_zone_trip_update: thermal cooling_device2: old_target=-1, target=-1 [ 355.147915] thermal_zone_trip_update: thermal thermal_zone0: Trip5[type=0,temp=60000]:trend=1,throttle=0 [ 355.147963] get_target_state: thermal cooling_device3: cur_state=0 [ 355.147967] thermal_zone_trip_update: thermal cooling_device3: old_target=-1, target=-1 [ 355.147973] thermal_zone_trip_update: thermal thermal_zone0: Trip6[type=0,temp=55000]:trend=1,throttle=1 [ 355.148022] get_target_state: thermal cooling_device4: cur_state=0 [ 355.148025] thermal_zone_trip_update: thermal cooling_device4: old_target=-1, target=1 [ 355.148036] thermal_cdev_update: thermal cooling_device4: zone0->target=1 [ 355.169279] thermal_cdev_update: thermal cooling_device4: set to state 1 Signed-off-by: Aaron Lu <aaron.lu@intel.com> Acked-by: Eduardo Valentin <eduardo.valentin@ti.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2013-12-02 05:54:26 +00:00
dev_dbg(&cdev->device, "zone%d->target=%lu\n",
instance->tz->id, instance->target);
if (instance->target == THERMAL_NO_TARGET)
continue;
if (instance->target > target)
target = instance->target;
}
cdev->ops->set_cur_state(cdev, target);
cdev->updated = true;
thermal: fix race condition when updating cooling device When multiple thermal zones are bound to the same cooling device, multiple kernel threads may want to update the cooling device state by calling thermal_cdev_update(). Having cdev not protected by a mutex can lead to a race condition. Consider the following situation with two kernel threads k1 and k2: Thread k1 Thread k2 || || call thermal_cdev_update() || ... || set_cur_state(cdev, target); call power_actor_set_power() || ... || instance->target = state; || cdev->updated = false; || || cdev->updated = true; || // completes execution call thermal_cdev_update() || // cdev->updated == true || return; || \/ time k2 has already looped through the thermal instances looking for the deepest cooling device state and is preempted right before setting cdev->updated to true. Now, k1 runs, modifies the thermal instance state and sets cdev->updated to false. Then, k1 is preempted and k2 continues the execution by setting cdev->updated to true, therefore preventing k1 from performing the update. Notice that this is not an issue if k2 looks at the instance->target modified by k1 "after" it is assigned by k1. In fact, in this case the update will happen anyway and k1 can safely return immediately from thermal_cdev_update(). This may lead to a situation where a thermal governor never updates the cooling device. For example, this is the case for the step_wise governor: when calling the function thermal_zone_trip_update(), the governor may always get a new state equal to the old one (which, however, wasn't notified to the cooling device) and will therefore skip the update. CC: Zhang Rui <rui.zhang@intel.com> CC: Eduardo Valentin <edubezval@gmail.com> CC: Peter Feuerer <peter@piie.net> Reported-by: Toby Huang <toby.huang@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2016-06-02 14:25:31 +00:00
mutex_unlock(&cdev->lock);
trace_cdev_update(cdev, target);
thermal: debug: add debug statement for core and step_wise To ease debugging thermal problem, add these dynamic debug statements so that user do not need rebuild kernel to see these info. Based on a patch from Zhang Rui for debugging on bugzilla: https://bugzilla.kernel.org/attachment.cgi?id=98671 A sample output after we turn on dynamic debug with the following cmd: # echo 'module thermal_sys +fp' > /sys/kernel/debug/dynamic_debug/control is like: [ 355.147627] update_temperature: thermal thermal_zone0: last_temperature=52000, current_temperature=55000 [ 355.147636] thermal_zone_trip_update: thermal thermal_zone0: Trip1[type=1,temp=79000]:trend=2,throttle=0 [ 355.147644] get_target_state: thermal cooling_device8: cur_state=0 [ 355.147647] thermal_zone_trip_update: thermal cooling_device8: old_target=-1, target=-1 [ 355.147652] get_target_state: thermal cooling_device7: cur_state=0 [ 355.147655] thermal_zone_trip_update: thermal cooling_device7: old_target=-1, target=-1 [ 355.147660] get_target_state: thermal cooling_device6: cur_state=0 [ 355.147663] thermal_zone_trip_update: thermal cooling_device6: old_target=-1, target=-1 [ 355.147668] get_target_state: thermal cooling_device5: cur_state=0 [ 355.147671] thermal_zone_trip_update: thermal cooling_device5: old_target=-1, target=-1 [ 355.147678] thermal_zone_trip_update: thermal thermal_zone0: Trip2[type=0,temp=90000]:trend=1,throttle=0 [ 355.147776] get_target_state: thermal cooling_device0: cur_state=0 [ 355.147783] thermal_zone_trip_update: thermal cooling_device0: old_target=-1, target=-1 [ 355.147792] thermal_zone_trip_update: thermal thermal_zone0: Trip3[type=0,temp=80000]:trend=1,throttle=0 [ 355.147845] get_target_state: thermal cooling_device1: cur_state=0 [ 355.147849] thermal_zone_trip_update: thermal cooling_device1: old_target=-1, target=-1 [ 355.147856] thermal_zone_trip_update: thermal thermal_zone0: Trip4[type=0,temp=70000]:trend=1,throttle=0 [ 355.147904] get_target_state: thermal cooling_device2: cur_state=0 [ 355.147908] thermal_zone_trip_update: thermal cooling_device2: old_target=-1, target=-1 [ 355.147915] thermal_zone_trip_update: thermal thermal_zone0: Trip5[type=0,temp=60000]:trend=1,throttle=0 [ 355.147963] get_target_state: thermal cooling_device3: cur_state=0 [ 355.147967] thermal_zone_trip_update: thermal cooling_device3: old_target=-1, target=-1 [ 355.147973] thermal_zone_trip_update: thermal thermal_zone0: Trip6[type=0,temp=55000]:trend=1,throttle=1 [ 355.148022] get_target_state: thermal cooling_device4: cur_state=0 [ 355.148025] thermal_zone_trip_update: thermal cooling_device4: old_target=-1, target=1 [ 355.148036] thermal_cdev_update: thermal cooling_device4: zone0->target=1 [ 355.169279] thermal_cdev_update: thermal cooling_device4: set to state 1 Signed-off-by: Aaron Lu <aaron.lu@intel.com> Acked-by: Eduardo Valentin <eduardo.valentin@ti.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2013-12-02 05:54:26 +00:00
dev_dbg(&cdev->device, "set to state %lu\n", target);
}
EXPORT_SYMBOL(thermal_cdev_update);
/**
* thermal_notify_framework - Sensor drivers use this API to notify framework
* @tz: thermal zone device
* @trip: indicates which trip point has been crossed
*
* This function handles the trip events from sensor drivers. It starts
* throttling the cooling devices according to the policy configured.
* For CRITICAL and HOT trip points, this notifies the respective drivers,
* and does actual throttling for other trip points i.e ACTIVE and PASSIVE.
* The throttling policy is based on the configured platform data; if no
* platform data is provided, this uses the step_wise throttling policy.
*/
void thermal_notify_framework(struct thermal_zone_device *tz, int trip)
{
handle_thermal_trip(tz, trip);
}
EXPORT_SYMBOL_GPL(thermal_notify_framework);
/**
* create_trip_attrs() - create attributes for trip points
* @tz: the thermal zone device
* @mask: Writeable trip point bitmap.
*
* helper function to instantiate sysfs entries for every trip
* point and its properties of a struct thermal_zone_device.
*
* Return: 0 on success, the proper error value otherwise.
*/
static int create_trip_attrs(struct thermal_zone_device *tz, int mask)
{
int indx;
int size = sizeof(struct thermal_attr) * tz->trips;
tz->trip_type_attrs = kzalloc(size, GFP_KERNEL);
if (!tz->trip_type_attrs)
return -ENOMEM;
tz->trip_temp_attrs = kzalloc(size, GFP_KERNEL);
if (!tz->trip_temp_attrs) {
kfree(tz->trip_type_attrs);
return -ENOMEM;
}
if (tz->ops->get_trip_hyst) {
tz->trip_hyst_attrs = kzalloc(size, GFP_KERNEL);
if (!tz->trip_hyst_attrs) {
kfree(tz->trip_type_attrs);
kfree(tz->trip_temp_attrs);
return -ENOMEM;
}
}
for (indx = 0; indx < tz->trips; indx++) {
/* create trip type attribute */
snprintf(tz->trip_type_attrs[indx].name, THERMAL_NAME_LENGTH,
"trip_point_%d_type", indx);
sysfs_attr_init(&tz->trip_type_attrs[indx].attr.attr);
tz->trip_type_attrs[indx].attr.attr.name =
tz->trip_type_attrs[indx].name;
tz->trip_type_attrs[indx].attr.attr.mode = S_IRUGO;
tz->trip_type_attrs[indx].attr.show = trip_point_type_show;
device_create_file(&tz->device,
&tz->trip_type_attrs[indx].attr);
/* create trip temp attribute */
snprintf(tz->trip_temp_attrs[indx].name, THERMAL_NAME_LENGTH,
"trip_point_%d_temp", indx);
sysfs_attr_init(&tz->trip_temp_attrs[indx].attr.attr);
tz->trip_temp_attrs[indx].attr.attr.name =
tz->trip_temp_attrs[indx].name;
tz->trip_temp_attrs[indx].attr.attr.mode = S_IRUGO;
tz->trip_temp_attrs[indx].attr.show = trip_point_temp_show;
if (IS_ENABLED(CONFIG_THERMAL_WRITABLE_TRIPS) &&
mask & (1 << indx)) {
tz->trip_temp_attrs[indx].attr.attr.mode |= S_IWUSR;
tz->trip_temp_attrs[indx].attr.store =
trip_point_temp_store;
}
device_create_file(&tz->device,
&tz->trip_temp_attrs[indx].attr);
/* create Optional trip hyst attribute */
if (!tz->ops->get_trip_hyst)
continue;
snprintf(tz->trip_hyst_attrs[indx].name, THERMAL_NAME_LENGTH,
"trip_point_%d_hyst", indx);
sysfs_attr_init(&tz->trip_hyst_attrs[indx].attr.attr);
tz->trip_hyst_attrs[indx].attr.attr.name =
tz->trip_hyst_attrs[indx].name;
tz->trip_hyst_attrs[indx].attr.attr.mode = S_IRUGO;
tz->trip_hyst_attrs[indx].attr.show = trip_point_hyst_show;
if (tz->ops->set_trip_hyst) {
tz->trip_hyst_attrs[indx].attr.attr.mode |= S_IWUSR;
tz->trip_hyst_attrs[indx].attr.store =
trip_point_hyst_store;
}
device_create_file(&tz->device,
&tz->trip_hyst_attrs[indx].attr);
}
return 0;
}
static void remove_trip_attrs(struct thermal_zone_device *tz)
{
int indx;
for (indx = 0; indx < tz->trips; indx++) {
device_remove_file(&tz->device,
&tz->trip_type_attrs[indx].attr);
device_remove_file(&tz->device,
&tz->trip_temp_attrs[indx].attr);
if (tz->ops->get_trip_hyst)
device_remove_file(&tz->device,
&tz->trip_hyst_attrs[indx].attr);
}
kfree(tz->trip_type_attrs);
kfree(tz->trip_temp_attrs);
kfree(tz->trip_hyst_attrs);
}
/**
* thermal_zone_device_register() - register a new thermal zone device
* @type: the thermal zone device type
* @trips: the number of trip points the thermal zone support
* @mask: a bit string indicating the writeablility of trip points
* @devdata: private device data
* @ops: standard thermal zone device callbacks
* @tzp: thermal zone platform parameters
* @passive_delay: number of milliseconds to wait between polls when
* performing passive cooling
* @polling_delay: number of milliseconds to wait between polls when checking
* whether trip points have been crossed (0 for interrupt
* driven systems)
*
* This interface function adds a new thermal zone device (sensor) to
* /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
* thermal cooling devices registered at the same time.
* thermal_zone_device_unregister() must be called when the device is no
* longer needed. The passive cooling depends on the .get_trend() return value.
*
* Return: a pointer to the created struct thermal_zone_device or an
* in case of error, an ERR_PTR. Caller must check return value with
* IS_ERR*() helpers.
*/
struct thermal_zone_device *thermal_zone_device_register(const char *type,
int trips, int mask, void *devdata,
struct thermal_zone_device_ops *ops,
struct thermal_zone_params *tzp,
int passive_delay, int polling_delay)
{
struct thermal_zone_device *tz;
enum thermal_trip_type trip_type;
2016-03-18 02:03:24 +00:00
int trip_temp;
int result;
int count;
int passive = 0;
struct thermal_governor *governor;
if (type && strlen(type) >= THERMAL_NAME_LENGTH)
return ERR_PTR(-EINVAL);
if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips)
return ERR_PTR(-EINVAL);
if (!ops)
return ERR_PTR(-EINVAL);
if (trips > 0 && (!ops->get_trip_type || !ops->get_trip_temp))
return ERR_PTR(-EINVAL);
tz = kzalloc(sizeof(struct thermal_zone_device), GFP_KERNEL);
if (!tz)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&tz->thermal_instances);
idr_init(&tz->idr);
mutex_init(&tz->lock);
result = get_idr(&thermal_tz_idr, &thermal_idr_lock, &tz->id);
if (result) {
kfree(tz);
return ERR_PTR(result);
}
strlcpy(tz->type, type ? : "", sizeof(tz->type));
tz->ops = ops;
tz->tzp = tzp;
tz->device.class = &thermal_class;
tz->devdata = devdata;
tz->trips = trips;
tz->passive_delay = passive_delay;
tz->polling_delay = polling_delay;
/* A new thermal zone needs to be updated anyway. */
atomic_set(&tz->need_update, 1);
dev_set_name(&tz->device, "thermal_zone%d", tz->id);
result = device_register(&tz->device);
if (result) {
release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
kfree(tz);
return ERR_PTR(result);
}
/* sys I/F */
if (type) {
result = device_create_file(&tz->device, &dev_attr_type);
if (result)
goto unregister;
}
result = device_create_file(&tz->device, &dev_attr_temp);
if (result)
goto unregister;
if (ops->get_mode) {
result = device_create_file(&tz->device, &dev_attr_mode);
if (result)
goto unregister;
}
result = create_trip_attrs(tz, mask);
if (result)
goto unregister;
for (count = 0; count < trips; count++) {
2016-03-18 02:03:24 +00:00
if (tz->ops->get_trip_type(tz, count, &trip_type))
set_bit(count, &tz->trips_disabled);
if (trip_type == THERMAL_TRIP_PASSIVE)
passive = 1;
2016-03-18 02:03:24 +00:00
if (tz->ops->get_trip_temp(tz, count, &trip_temp))
set_bit(count, &tz->trips_disabled);
/* Check for bogus trip points */
if (trip_temp == 0)
set_bit(count, &tz->trips_disabled);
}
if (!passive) {
result = device_create_file(&tz->device, &dev_attr_passive);
if (result)
goto unregister;
}
if (IS_ENABLED(CONFIG_THERMAL_EMULATION)) {
result = device_create_file(&tz->device, &dev_attr_emul_temp);
if (result)
goto unregister;
}
/* Create policy attribute */
result = device_create_file(&tz->device, &dev_attr_policy);
if (result)
goto unregister;
/* Add thermal zone params */
result = create_tzp_attrs(&tz->device);
if (result)
goto unregister;
/* Create available_policies attribute */
result = device_create_file(&tz->device, &dev_attr_available_policies);
if (result)
goto unregister;
/* Update 'this' zone's governor information */
mutex_lock(&thermal_governor_lock);
if (tz->tzp)
governor = __find_governor(tz->tzp->governor_name);
else
governor = def_governor;
result = thermal_set_governor(tz, governor);
if (result) {
mutex_unlock(&thermal_governor_lock);
goto unregister;
}
mutex_unlock(&thermal_governor_lock);
if (!tz->tzp || !tz->tzp->no_hwmon) {
result = thermal_add_hwmon_sysfs(tz);
if (result)
goto unregister;
}
mutex_lock(&thermal_list_lock);
list_add_tail(&tz->node, &thermal_tz_list);
mutex_unlock(&thermal_list_lock);
/* Bind cooling devices for this zone */
bind_tz(tz);
INIT_DELAYED_WORK(&(tz->poll_queue), thermal_zone_device_check);
thermal_zone_device_reset(tz);
/* Update the new thermal zone and mark it as already updated. */
if (atomic_cmpxchg(&tz->need_update, 1, 0))
thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
return tz;
unregister:
release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
device_unregister(&tz->device);
return ERR_PTR(result);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_register);
/**
* thermal_device_unregister - removes the registered thermal zone device
* @tz: the thermal zone device to remove
*/
void thermal_zone_device_unregister(struct thermal_zone_device *tz)
{
int i;
const struct thermal_zone_params *tzp;
struct thermal_cooling_device *cdev;
struct thermal_zone_device *pos = NULL;
if (!tz)
return;
tzp = tz->tzp;
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node)
if (pos == tz)
break;
if (pos != tz) {
/* thermal zone device not found */
mutex_unlock(&thermal_list_lock);
return;
}
list_del(&tz->node);
/* Unbind all cdevs associated with 'this' thermal zone */
list_for_each_entry(cdev, &thermal_cdev_list, node) {
if (tz->ops->unbind) {
tz->ops->unbind(tz, cdev);
continue;
}
if (!tzp || !tzp->tbp)
break;
for (i = 0; i < tzp->num_tbps; i++) {
if (tzp->tbp[i].cdev == cdev) {
__unbind(tz, tzp->tbp[i].trip_mask, cdev);
tzp->tbp[i].cdev = NULL;
}
}
}
mutex_unlock(&thermal_list_lock);
thermal_zone_device_set_polling(tz, 0);
if (tz->type[0])
device_remove_file(&tz->device, &dev_attr_type);
device_remove_file(&tz->device, &dev_attr_temp);
if (tz->ops->get_mode)
device_remove_file(&tz->device, &dev_attr_mode);
device_remove_file(&tz->device, &dev_attr_policy);
device_remove_file(&tz->device, &dev_attr_available_policies);
remove_trip_attrs(tz);
thermal_set_governor(tz, NULL);
thermal_remove_hwmon_sysfs(tz);
release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
idr_destroy(&tz->idr);
mutex_destroy(&tz->lock);
device_unregister(&tz->device);
return;
}
EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
/**
* thermal_zone_get_zone_by_name() - search for a zone and returns its ref
* @name: thermal zone name to fetch the temperature
*
* When only one zone is found with the passed name, returns a reference to it.
*
* Return: On success returns a reference to an unique thermal zone with
* matching name equals to @name, an ERR_PTR otherwise (-EINVAL for invalid
* paramenters, -ENODEV for not found and -EEXIST for multiple matches).
*/
struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name)
{
struct thermal_zone_device *pos = NULL, *ref = ERR_PTR(-EINVAL);
unsigned int found = 0;
if (!name)
goto exit;
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node)
if (!strncasecmp(name, pos->type, THERMAL_NAME_LENGTH)) {
found++;
ref = pos;
}
mutex_unlock(&thermal_list_lock);
/* nothing has been found, thus an error code for it */
if (found == 0)
ref = ERR_PTR(-ENODEV);
else if (found > 1)
/* Success only when an unique zone is found */
ref = ERR_PTR(-EEXIST);
exit:
return ref;
}
EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);
/**
* thermal_zone_get_slope - return the slope attribute of the thermal zone
* @tz: thermal zone device with the slope attribute
*
* Return: If the thermal zone device has a slope attribute, return it, else
* return 1.
*/
int thermal_zone_get_slope(struct thermal_zone_device *tz)
{
if (tz && tz->tzp)
return tz->tzp->slope;
return 1;
}
EXPORT_SYMBOL_GPL(thermal_zone_get_slope);
/**
* thermal_zone_get_offset - return the offset attribute of the thermal zone
* @tz: thermal zone device with the offset attribute
*
* Return: If the thermal zone device has a offset attribute, return it, else
* return 0.
*/
int thermal_zone_get_offset(struct thermal_zone_device *tz)
{
if (tz && tz->tzp)
return tz->tzp->offset;
return 0;
}
EXPORT_SYMBOL_GPL(thermal_zone_get_offset);
#ifdef CONFIG_NET
static const struct genl_multicast_group thermal_event_mcgrps[] = {
{ .name = THERMAL_GENL_MCAST_GROUP_NAME, },
};
static struct genl_family thermal_event_genl_family __ro_after_init = {
.module = THIS_MODULE,
.name = THERMAL_GENL_FAMILY_NAME,
.version = THERMAL_GENL_VERSION,
.maxattr = THERMAL_GENL_ATTR_MAX,
.mcgrps = thermal_event_mcgrps,
.n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps),
};
int thermal_generate_netlink_event(struct thermal_zone_device *tz,
enum events event)
{
struct sk_buff *skb;
struct nlattr *attr;
struct thermal_genl_event *thermal_event;
void *msg_header;
int size;
int result;
static unsigned int thermal_event_seqnum;
if (!tz)
return -EINVAL;
/* allocate memory */
size = nla_total_size(sizeof(struct thermal_genl_event)) +
nla_total_size(0);
skb = genlmsg_new(size, GFP_ATOMIC);
if (!skb)
return -ENOMEM;
/* add the genetlink message header */
msg_header = genlmsg_put(skb, 0, thermal_event_seqnum++,
&thermal_event_genl_family, 0,
THERMAL_GENL_CMD_EVENT);
if (!msg_header) {
nlmsg_free(skb);
return -ENOMEM;
}
/* fill the data */
attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT,
sizeof(struct thermal_genl_event));
if (!attr) {
nlmsg_free(skb);
return -EINVAL;
}
thermal_event = nla_data(attr);
if (!thermal_event) {
nlmsg_free(skb);
return -EINVAL;
}
memset(thermal_event, 0, sizeof(struct thermal_genl_event));
thermal_event->orig = tz->id;
thermal_event->event = event;
/* send multicast genetlink message */
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
genlmsg_end(skb, msg_header);
result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
0, GFP_ATOMIC);
if (result)
dev_err(&tz->device, "Failed to send netlink event:%d", result);
return result;
}
EXPORT_SYMBOL_GPL(thermal_generate_netlink_event);
static int __init genetlink_init(void)
{
return genl_register_family(&thermal_event_genl_family);
}
static void genetlink_exit(void)
{
genl_unregister_family(&thermal_event_genl_family);
}
#else /* !CONFIG_NET */
static inline int genetlink_init(void) { return 0; }
static inline void genetlink_exit(void) {}
#endif /* !CONFIG_NET */
static int __init thermal_register_governors(void)
{
int result;
result = thermal_gov_step_wise_register();
if (result)
return result;
result = thermal_gov_fair_share_register();
if (result)
return result;
result = thermal_gov_bang_bang_register();
if (result)
return result;
result = thermal_gov_user_space_register();
if (result)
return result;
return thermal_gov_power_allocator_register();
}
static void thermal_unregister_governors(void)
{
thermal_gov_step_wise_unregister();
thermal_gov_fair_share_unregister();
thermal_gov_bang_bang_unregister();
thermal_gov_user_space_unregister();
thermal_gov_power_allocator_unregister();
}
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
static int thermal_pm_notify(struct notifier_block *nb,
unsigned long mode, void *_unused)
{
struct thermal_zone_device *tz;
switch (mode) {
case PM_HIBERNATION_PREPARE:
case PM_RESTORE_PREPARE:
case PM_SUSPEND_PREPARE:
atomic_set(&in_suspend, 1);
break;
case PM_POST_HIBERNATION:
case PM_POST_RESTORE:
case PM_POST_SUSPEND:
atomic_set(&in_suspend, 0);
list_for_each_entry(tz, &thermal_tz_list, node) {
thermal_zone_device_reset(tz);
thermal_zone_device_update(tz,
THERMAL_EVENT_UNSPECIFIED);
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
}
break;
default:
break;
}
return 0;
}
static struct notifier_block thermal_pm_nb = {
.notifier_call = thermal_pm_notify,
};
static int __init thermal_init(void)
{
int result;
result = thermal_register_governors();
if (result)
goto error;
result = class_register(&thermal_class);
if (result)
goto unregister_governors;
result = genetlink_init();
if (result)
goto unregister_class;
result = of_parse_thermal_zones();
if (result)
goto exit_netlink;
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
result = register_pm_notifier(&thermal_pm_nb);
if (result)
pr_warn("Thermal: Can not register suspend notifier, return %d\n",
result);
return 0;
exit_netlink:
genetlink_exit();
unregister_class:
class_unregister(&thermal_class);
unregister_governors:
thermal_unregister_governors();
error:
idr_destroy(&thermal_tz_idr);
idr_destroy(&thermal_cdev_idr);
mutex_destroy(&thermal_idr_lock);
mutex_destroy(&thermal_list_lock);
mutex_destroy(&thermal_governor_lock);
return result;
}
static void __exit thermal_exit(void)
{
Thermal: handle thermal zone device properly during system sleep Current thermal code does not handle system sleep well because 1. the cooling device cooling state may be changed during suspend 2. the previous temperature reading becomes invalid after resumed because it is got before system sleep 3. updating thermal zone device during suspending/resuming is wrong because some devices may have already been suspended or may have not been resumed. Thus, the proper way to do this is to cancel all thermal zone device update requirements during suspend/resume, and after all the devices have been resumed, reset and update every registered thermal zone devices. This also fixes a regression introduced by: Commit 19593a1fb1f6 ("ACPI / fan: convert to platform driver") Because, with above commit applied, all the fan devices are attached to the acpi_general_pm_domain, and they are turned on by the pm_domain automatically after resume, without the awareness of thermal core. CC: <stable@vger.kernel.org> #3.18+ Reference: https://bugzilla.kernel.org/show_bug.cgi?id=78201 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=91411 Tested-by: Manuel Krause <manuelkrause@netscape.net> Tested-by: szegad <szegadlo@poczta.onet.pl> Tested-by: prash <prash.n.rao@gmail.com> Tested-by: amish <ammdispose-arch@yahoo.com> Tested-by: Matthias <morpheusxyz123@yahoo.de> Reviewed-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com>
2015-10-30 08:31:58 +00:00
unregister_pm_notifier(&thermal_pm_nb);
of_thermal_destroy_zones();
genetlink_exit();
class_unregister(&thermal_class);
thermal_unregister_governors();
idr_destroy(&thermal_tz_idr);
idr_destroy(&thermal_cdev_idr);
mutex_destroy(&thermal_idr_lock);
mutex_destroy(&thermal_list_lock);
mutex_destroy(&thermal_governor_lock);
}
fs_initcall(thermal_init);
module_exit(thermal_exit);