mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 19:46:42 +07:00
d0b7306d20
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>
142 lines
4.0 KiB
C
142 lines
4.0 KiB
C
/*
|
|
* fair_share.c - A simple weight based Thermal governor
|
|
*
|
|
* Copyright (C) 2012 Intel Corp
|
|
* Copyright (C) 2012 Durgadoss R <durgadoss.r@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.
|
|
*
|
|
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
*/
|
|
|
|
#include <linux/thermal.h>
|
|
#include <trace/events/thermal.h>
|
|
|
|
#include "thermal_core.h"
|
|
|
|
/**
|
|
* get_trip_level: - obtains the current trip level for a zone
|
|
* @tz: thermal zone device
|
|
*/
|
|
static int get_trip_level(struct thermal_zone_device *tz)
|
|
{
|
|
int count = 0;
|
|
int trip_temp;
|
|
enum thermal_trip_type trip_type;
|
|
|
|
if (tz->trips == 0 || !tz->ops->get_trip_temp)
|
|
return 0;
|
|
|
|
for (count = 0; count < tz->trips; count++) {
|
|
tz->ops->get_trip_temp(tz, count, &trip_temp);
|
|
if (tz->temperature < trip_temp)
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* count > 0 only if temperature is greater than first trip
|
|
* point, in which case, trip_point = count - 1
|
|
*/
|
|
if (count > 0) {
|
|
tz->ops->get_trip_type(tz, count - 1, &trip_type);
|
|
trace_thermal_zone_trip(tz, count - 1, trip_type);
|
|
}
|
|
|
|
return count;
|
|
}
|
|
|
|
static long get_target_state(struct thermal_zone_device *tz,
|
|
struct thermal_cooling_device *cdev, int percentage, int level)
|
|
{
|
|
unsigned long max_state;
|
|
|
|
cdev->ops->get_max_state(cdev, &max_state);
|
|
|
|
return (long)(percentage * level * max_state) / (100 * tz->trips);
|
|
}
|
|
|
|
/**
|
|
* fair_share_throttle - throttles devices associated with the given zone
|
|
* @tz - thermal_zone_device
|
|
*
|
|
* Throttling Logic: This uses three parameters to calculate the new
|
|
* throttle state of the cooling devices associated with the given zone.
|
|
*
|
|
* Parameters used for Throttling:
|
|
* P1. max_state: Maximum throttle state exposed by the cooling device.
|
|
* P2. percentage[i]/100:
|
|
* How 'effective' the 'i'th device is, in cooling the given zone.
|
|
* P3. cur_trip_level/max_no_of_trips:
|
|
* This describes the extent to which the devices should be throttled.
|
|
* We do not want to throttle too much when we trip a lower temperature,
|
|
* whereas the throttling is at full swing if we trip critical levels.
|
|
* (Heavily assumes the trip points are in ascending order)
|
|
* new_state of cooling device = P3 * P2 * P1
|
|
*/
|
|
static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
|
|
{
|
|
struct thermal_instance *instance;
|
|
int total_weight = 0;
|
|
int total_instance = 0;
|
|
int cur_trip_level = get_trip_level(tz);
|
|
|
|
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
|
|
if (instance->trip != trip)
|
|
continue;
|
|
|
|
total_weight += instance->weight;
|
|
total_instance++;
|
|
}
|
|
|
|
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
|
|
int percentage;
|
|
struct thermal_cooling_device *cdev = instance->cdev;
|
|
|
|
if (instance->trip != trip)
|
|
continue;
|
|
|
|
if (!total_weight)
|
|
percentage = 100 / total_instance;
|
|
else
|
|
percentage = (instance->weight * 100) / total_weight;
|
|
|
|
instance->target = get_target_state(tz, cdev, percentage,
|
|
cur_trip_level);
|
|
|
|
mutex_lock(&instance->cdev->lock);
|
|
instance->cdev->updated = false;
|
|
mutex_unlock(&instance->cdev->lock);
|
|
thermal_cdev_update(cdev);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static struct thermal_governor thermal_gov_fair_share = {
|
|
.name = "fair_share",
|
|
.throttle = fair_share_throttle,
|
|
};
|
|
|
|
int thermal_gov_fair_share_register(void)
|
|
{
|
|
return thermal_register_governor(&thermal_gov_fair_share);
|
|
}
|
|
|
|
void thermal_gov_fair_share_unregister(void)
|
|
{
|
|
thermal_unregister_governor(&thermal_gov_fair_share);
|
|
}
|
|
|