linux-sg2042/drivers/thermal/power_allocator.c

664 lines
19 KiB
C
Raw Normal View History

/*
* A power allocator to manage temperature
*
* Copyright (C) 2014 ARM Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed "as is" WITHOUT ANY WARRANTY of any
* kind, whether express or implied; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#define pr_fmt(fmt) "Power allocator: " fmt
#include <linux/rculist.h>
#include <linux/slab.h>
#include <linux/thermal.h>
#define CREATE_TRACE_POINTS
#include <trace/events/thermal_power_allocator.h>
#include "thermal_core.h"
#define INVALID_TRIP -1
#define FRAC_BITS 10
#define int_to_frac(x) ((x) << FRAC_BITS)
#define frac_to_int(x) ((x) >> FRAC_BITS)
/**
* mul_frac() - multiply two fixed-point numbers
* @x: first multiplicand
* @y: second multiplicand
*
* Return: the result of multiplying two fixed-point numbers. The
* result is also a fixed-point number.
*/
static inline s64 mul_frac(s64 x, s64 y)
{
return (x * y) >> FRAC_BITS;
}
/**
* div_frac() - divide two fixed-point numbers
* @x: the dividend
* @y: the divisor
*
* Return: the result of dividing two fixed-point numbers. The
* result is also a fixed-point number.
*/
static inline s64 div_frac(s64 x, s64 y)
{
return div_s64(x << FRAC_BITS, y);
}
/**
* struct power_allocator_params - parameters for the power allocator governor
* @allocated_tzp: whether we have allocated tzp for this thermal zone and
* it needs to be freed on unbind
* @err_integral: accumulated error in the PID controller.
* @prev_err: error in the previous iteration of the PID controller.
* Used to calculate the derivative term.
* @trip_switch_on: first passive trip point of the thermal zone. The
* governor switches on when this trip point is crossed.
* If the thermal zone only has one passive trip point,
* @trip_switch_on should be INVALID_TRIP.
* @trip_max_desired_temperature: last passive trip point of the thermal
* zone. The temperature we are
* controlling for.
*/
struct power_allocator_params {
bool allocated_tzp;
s64 err_integral;
s32 prev_err;
int trip_switch_on;
int trip_max_desired_temperature;
};
/**
* estimate_sustainable_power() - Estimate the sustainable power of a thermal zone
* @tz: thermal zone we are operating in
*
* For thermal zones that don't provide a sustainable_power in their
* thermal_zone_params, estimate one. Calculate it using the minimum
* power of all the cooling devices as that gives a valid value that
* can give some degree of functionality. For optimal performance of
* this governor, provide a sustainable_power in the thermal zone's
* thermal_zone_params.
*/
static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
{
u32 sustainable_power = 0;
struct thermal_instance *instance;
struct power_allocator_params *params = tz->governor_data;
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
struct thermal_cooling_device *cdev = instance->cdev;
u32 min_power;
if (instance->trip != params->trip_max_desired_temperature)
continue;
if (power_actor_get_min_power(cdev, tz, &min_power))
continue;
sustainable_power += min_power;
}
return sustainable_power;
}
/**
* estimate_pid_constants() - Estimate the constants for the PID controller
* @tz: thermal zone for which to estimate the constants
* @sustainable_power: sustainable power for the thermal zone
* @trip_switch_on: trip point number for the switch on temperature
* @control_temp: target temperature for the power allocator governor
* @force: whether to force the update of the constants
*
* This function is used to update the estimation of the PID
* controller constants in struct thermal_zone_parameters.
* Sustainable power is provided in case it was estimated. The
* estimated sustainable_power should not be stored in the
* thermal_zone_parameters so it has to be passed explicitly to this
* function.
*
* If @force is not set, the values in the thermal zone's parameters
* are preserved if they are not zero. If @force is set, the values
* in thermal zone's parameters are overwritten.
*/
static void estimate_pid_constants(struct thermal_zone_device *tz,
u32 sustainable_power, int trip_switch_on,
int control_temp, bool force)
{
int ret;
int switch_on_temp;
u32 temperature_threshold;
ret = tz->ops->get_trip_temp(tz, trip_switch_on, &switch_on_temp);
if (ret)
switch_on_temp = 0;
temperature_threshold = control_temp - switch_on_temp;
/*
* estimate_pid_constants() tries to find appropriate default
* values for thermal zones that don't provide them. If a
* system integrator has configured a thermal zone with two
* passive trip points at the same temperature, that person
* hasn't put any effort to set up the thermal zone properly
* so just give up.
*/
if (!temperature_threshold)
return;
if (!tz->tzp->k_po || force)
tz->tzp->k_po = int_to_frac(sustainable_power) /
temperature_threshold;
if (!tz->tzp->k_pu || force)
tz->tzp->k_pu = int_to_frac(2 * sustainable_power) /
temperature_threshold;
if (!tz->tzp->k_i || force)
tz->tzp->k_i = int_to_frac(10) / 1000;
/*
* The default for k_d and integral_cutoff is 0, so we can
* leave them as they are.
*/
}
/**
* pid_controller() - PID controller
* @tz: thermal zone we are operating in
* @control_temp: the target temperature in millicelsius
* @max_allocatable_power: maximum allocatable power for this thermal zone
*
* This PID controller increases the available power budget so that the
* temperature of the thermal zone gets as close as possible to
* @control_temp and limits the power if it exceeds it. k_po is the
* proportional term when we are overshooting, k_pu is the
* proportional term when we are undershooting. integral_cutoff is a
* threshold below which we stop accumulating the error. The
* accumulated error is only valid if the requested power will make
* the system warmer. If the system is mostly idle, there's no point
* in accumulating positive error.
*
* Return: The power budget for the next period.
*/
static u32 pid_controller(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 14:12:54 +08:00
int control_temp,
u32 max_allocatable_power)
{
s64 p, i, d, power_range;
s32 err, max_power_frac;
u32 sustainable_power;
struct power_allocator_params *params = tz->governor_data;
max_power_frac = int_to_frac(max_allocatable_power);
if (tz->tzp->sustainable_power) {
sustainable_power = tz->tzp->sustainable_power;
} else {
sustainable_power = estimate_sustainable_power(tz);
estimate_pid_constants(tz, sustainable_power,
params->trip_switch_on, control_temp,
true);
}
err = control_temp - tz->temperature;
err = int_to_frac(err);
/* Calculate the proportional term */
p = mul_frac(err < 0 ? tz->tzp->k_po : tz->tzp->k_pu, err);
/*
* Calculate the integral term
*
* if the error is less than cut off allow integration (but
* the integral is limited to max power)
*/
i = mul_frac(tz->tzp->k_i, params->err_integral);
if (err < int_to_frac(tz->tzp->integral_cutoff)) {
s64 i_next = i + mul_frac(tz->tzp->k_i, err);
if (abs(i_next) < max_power_frac) {
i = i_next;
params->err_integral += err;
}
}
/*
* Calculate the derivative term
*
* We do err - prev_err, so with a positive k_d, a decreasing
* error (i.e. driving closer to the line) results in less
* power being applied, slowing down the controller)
*/
d = mul_frac(tz->tzp->k_d, err - params->prev_err);
d = div_frac(d, tz->passive_delay);
params->prev_err = err;
power_range = p + i + d;
/* feed-forward the known sustainable dissipatable power */
power_range = sustainable_power + frac_to_int(power_range);
power_range = clamp(power_range, (s64)0, (s64)max_allocatable_power);
trace_thermal_power_allocator_pid(tz, frac_to_int(err),
frac_to_int(params->err_integral),
frac_to_int(p), frac_to_int(i),
frac_to_int(d), power_range);
return power_range;
}
/**
* divvy_up_power() - divvy the allocated power between the actors
* @req_power: each actor's requested power
* @max_power: each actor's maximum available power
* @num_actors: size of the @req_power, @max_power and @granted_power's array
* @total_req_power: sum of @req_power
* @power_range: total allocated power
* @granted_power: output array: each actor's granted power
* @extra_actor_power: an appropriately sized array to be used in the
* function as temporary storage of the extra power given
* to the actors
*
* This function divides the total allocated power (@power_range)
* fairly between the actors. It first tries to give each actor a
* share of the @power_range according to how much power it requested
* compared to the rest of the actors. For example, if only one actor
* requests power, then it receives all the @power_range. If
* three actors each requests 1mW, each receives a third of the
* @power_range.
*
* If any actor received more than their maximum power, then that
* surplus is re-divvied among the actors based on how far they are
* from their respective maximums.
*
* Granted power for each actor is written to @granted_power, which
* should've been allocated by the calling function.
*/
static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
u32 total_req_power, u32 power_range,
u32 *granted_power, u32 *extra_actor_power)
{
u32 extra_power, capped_extra_power;
int i;
/*
* Prevent division by 0 if none of the actors request power.
*/
if (!total_req_power)
total_req_power = 1;
capped_extra_power = 0;
extra_power = 0;
for (i = 0; i < num_actors; i++) {
u64 req_range = (u64)req_power[i] * power_range;
granted_power[i] = DIV_ROUND_CLOSEST_ULL(req_range,
total_req_power);
if (granted_power[i] > max_power[i]) {
extra_power += granted_power[i] - max_power[i];
granted_power[i] = max_power[i];
}
extra_actor_power[i] = max_power[i] - granted_power[i];
capped_extra_power += extra_actor_power[i];
}
if (!extra_power)
return;
/*
* Re-divvy the reclaimed extra among actors based on
* how far they are from the max
*/
extra_power = min(extra_power, capped_extra_power);
if (capped_extra_power > 0)
for (i = 0; i < num_actors; i++)
granted_power[i] += (extra_actor_power[i] *
extra_power) / capped_extra_power;
}
static int allocate_power(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 14:12:54 +08:00
int control_temp)
{
struct thermal_instance *instance;
struct power_allocator_params *params = tz->governor_data;
u32 *req_power, *max_power, *granted_power, *extra_actor_power;
u32 *weighted_req_power;
u32 total_req_power, max_allocatable_power, total_weighted_req_power;
u32 total_granted_power, power_range;
int i, num_actors, total_weight, ret = 0;
int trip_max_desired_temperature = params->trip_max_desired_temperature;
mutex_lock(&tz->lock);
num_actors = 0;
total_weight = 0;
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
if ((instance->trip == trip_max_desired_temperature) &&
cdev_is_power_actor(instance->cdev)) {
num_actors++;
total_weight += instance->weight;
}
}
if (!num_actors) {
ret = -ENODEV;
goto unlock;
}
/*
* We need to allocate five arrays of the same size:
* req_power, max_power, granted_power, extra_actor_power and
* weighted_req_power. They are going to be needed until this
* function returns. Allocate them all in one go to simplify
* the allocation and deallocation logic.
*/
BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power));
BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power));
BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
req_power = kcalloc(num_actors * 5, sizeof(*req_power), GFP_KERNEL);
if (!req_power) {
ret = -ENOMEM;
goto unlock;
}
max_power = &req_power[num_actors];
granted_power = &req_power[2 * num_actors];
extra_actor_power = &req_power[3 * num_actors];
weighted_req_power = &req_power[4 * num_actors];
i = 0;
total_weighted_req_power = 0;
total_req_power = 0;
max_allocatable_power = 0;
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
int weight;
struct thermal_cooling_device *cdev = instance->cdev;
if (instance->trip != trip_max_desired_temperature)
continue;
if (!cdev_is_power_actor(cdev))
continue;
if (cdev->ops->get_requested_power(cdev, tz, &req_power[i]))
continue;
if (!total_weight)
weight = 1 << FRAC_BITS;
else
weight = instance->weight;
weighted_req_power[i] = frac_to_int(weight * req_power[i]);
if (power_actor_get_max_power(cdev, tz, &max_power[i]))
continue;
total_req_power += req_power[i];
max_allocatable_power += max_power[i];
total_weighted_req_power += weighted_req_power[i];
i++;
}
power_range = pid_controller(tz, control_temp, max_allocatable_power);
divvy_up_power(weighted_req_power, max_power, num_actors,
total_weighted_req_power, power_range, granted_power,
extra_actor_power);
total_granted_power = 0;
i = 0;
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
if (instance->trip != trip_max_desired_temperature)
continue;
if (!cdev_is_power_actor(instance->cdev))
continue;
power_actor_set_power(instance->cdev, instance,
granted_power[i]);
total_granted_power += granted_power[i];
i++;
}
trace_thermal_power_allocator(tz, req_power, total_req_power,
granted_power, total_granted_power,
num_actors, power_range,
max_allocatable_power, tz->temperature,
control_temp - tz->temperature);
kfree(req_power);
unlock:
mutex_unlock(&tz->lock);
return ret;
}
/**
* get_governor_trips() - get the number of the two trip points that are key for this governor
* @tz: thermal zone to operate on
* @params: pointer to private data for this governor
*
* The power allocator governor works optimally with two trips points:
* a "switch on" trip point and a "maximum desired temperature". These
* are defined as the first and last passive trip points.
*
* If there is only one trip point, then that's considered to be the
* "maximum desired temperature" trip point and the governor is always
* on. If there are no passive or active trip points, then the
* governor won't do anything. In fact, its throttle function
* won't be called at all.
*/
static void get_governor_trips(struct thermal_zone_device *tz,
struct power_allocator_params *params)
{
int i, last_active, last_passive;
bool found_first_passive;
found_first_passive = false;
last_active = INVALID_TRIP;
last_passive = INVALID_TRIP;
for (i = 0; i < tz->trips; i++) {
enum thermal_trip_type type;
int ret;
ret = tz->ops->get_trip_type(tz, i, &type);
if (ret) {
dev_warn(&tz->device,
"Failed to get trip point %d type: %d\n", i,
ret);
continue;
}
if (type == THERMAL_TRIP_PASSIVE) {
if (!found_first_passive) {
params->trip_switch_on = i;
found_first_passive = true;
} else {
last_passive = i;
}
} else if (type == THERMAL_TRIP_ACTIVE) {
last_active = i;
} else {
break;
}
}
if (last_passive != INVALID_TRIP) {
params->trip_max_desired_temperature = last_passive;
} else if (found_first_passive) {
params->trip_max_desired_temperature = params->trip_switch_on;
params->trip_switch_on = INVALID_TRIP;
} else {
params->trip_switch_on = INVALID_TRIP;
params->trip_max_desired_temperature = last_active;
}
}
static void reset_pid_controller(struct power_allocator_params *params)
{
params->err_integral = 0;
params->prev_err = 0;
}
static void allow_maximum_power(struct thermal_zone_device *tz)
{
struct thermal_instance *instance;
struct power_allocator_params *params = tz->governor_data;
thermal: power_allocator: fix one race condition issue for thermal_instances list When invoking allow_maximum_power and traverse tz->thermal_instances, we should grab thermal_zone_device->lock to avoid race condition. For example, during the system reboot, if the mali GPU device implements device shutdown callback and unregister GPU devfreq cooling device, the deleted list head may be accessed to cause panic, as the following log shows: [ 33.551070] c3 25 (kworker/3:0) Unable to handle kernel paging request at virtual address dead000000000070 [ 33.566708] c3 25 (kworker/3:0) pgd = ffffffc0ed290000 [ 33.572071] c3 25 (kworker/3:0) [dead000000000070] *pgd=00000001ed292003, *pud=00000001ed292003, *pmd=0000000000000000 [ 33.581515] c3 25 (kworker/3:0) Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 33.599761] c3 25 (kworker/3:0) CPU: 3 PID: 25 Comm: kworker/3:0 Not tainted 4.4.35+ #912 [ 33.614137] c3 25 (kworker/3:0) Workqueue: events_freezable thermal_zone_device_check [ 33.620245] c3 25 (kworker/3:0) task: ffffffc0f32e4200 ti: ffffffc0f32f0000 task.ti: ffffffc0f32f0000 [ 33.629466] c3 25 (kworker/3:0) PC is at power_allocator_throttle+0x7c8/0x8a4 [ 33.636609] c3 25 (kworker/3:0) LR is at power_allocator_throttle+0x808/0x8a4 [ 33.643742] c3 25 (kworker/3:0) pc : [<ffffff8008683dd0>] lr : [<ffffff8008683e10>] pstate: 20000145 [ 33.652874] c3 25 (kworker/3:0) sp : ffffffc0f32f3bb0 [ 34.468519] c3 25 (kworker/3:0) Process kworker/3:0 (pid: 25, stack limit = 0xffffffc0f32f0020) [ 34.477220] c3 25 (kworker/3:0) Stack: (0xffffffc0f32f3bb0 to 0xffffffc0f32f4000) [ 34.819822] c3 25 (kworker/3:0) Call trace: [ 34.824021] c3 25 (kworker/3:0) Exception stack(0xffffffc0f32f39c0 to 0xffffffc0f32f3af0) [ 34.924993] c3 25 (kworker/3:0) [<ffffff8008683dd0>] power_allocator_throttle+0x7c8/0x8a4 [ 34.933184] c3 25 (kworker/3:0) [<ffffff80086807f4>] handle_thermal_trip.part.25+0x70/0x224 [ 34.941545] c3 25 (kworker/3:0) [<ffffff8008680a68>] thermal_zone_device_update+0xc0/0x20c [ 34.949818] c3 25 (kworker/3:0) [<ffffff8008680bd4>] thermal_zone_device_check+0x20/0x2c [ 34.957924] c3 25 (kworker/3:0) [<ffffff80080b93a4>] process_one_work+0x168/0x458 [ 34.965414] c3 25 (kworker/3:0) [<ffffff80080ba068>] worker_thread+0x13c/0x4b4 [ 34.972650] c3 25 (kworker/3:0) [<ffffff80080c0a4c>] kthread+0xe8/0xfc [ 34.979187] c3 25 (kworker/3:0) [<ffffff8008084e90>] ret_from_fork+0x10/0x40 [ 34.986244] c3 25 (kworker/3:0) Code: f9405e73 eb1302bf d102e273 54ffc460 (b9402a61) [ 34.994339] c3 25 (kworker/3:0) ---[ end trace 32057901e3b7e1db ]--- Signed-off-by: Yi Zeng <yizeng@asrmicro.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2017-12-26 19:22:26 +08:00
mutex_lock(&tz->lock);
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
if ((instance->trip != params->trip_max_desired_temperature) ||
(!cdev_is_power_actor(instance->cdev)))
continue;
instance->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 22:25:31 +08:00
mutex_lock(&instance->cdev->lock);
instance->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 22:25:31 +08:00
mutex_unlock(&instance->cdev->lock);
thermal_cdev_update(instance->cdev);
}
thermal: power_allocator: fix one race condition issue for thermal_instances list When invoking allow_maximum_power and traverse tz->thermal_instances, we should grab thermal_zone_device->lock to avoid race condition. For example, during the system reboot, if the mali GPU device implements device shutdown callback and unregister GPU devfreq cooling device, the deleted list head may be accessed to cause panic, as the following log shows: [ 33.551070] c3 25 (kworker/3:0) Unable to handle kernel paging request at virtual address dead000000000070 [ 33.566708] c3 25 (kworker/3:0) pgd = ffffffc0ed290000 [ 33.572071] c3 25 (kworker/3:0) [dead000000000070] *pgd=00000001ed292003, *pud=00000001ed292003, *pmd=0000000000000000 [ 33.581515] c3 25 (kworker/3:0) Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 33.599761] c3 25 (kworker/3:0) CPU: 3 PID: 25 Comm: kworker/3:0 Not tainted 4.4.35+ #912 [ 33.614137] c3 25 (kworker/3:0) Workqueue: events_freezable thermal_zone_device_check [ 33.620245] c3 25 (kworker/3:0) task: ffffffc0f32e4200 ti: ffffffc0f32f0000 task.ti: ffffffc0f32f0000 [ 33.629466] c3 25 (kworker/3:0) PC is at power_allocator_throttle+0x7c8/0x8a4 [ 33.636609] c3 25 (kworker/3:0) LR is at power_allocator_throttle+0x808/0x8a4 [ 33.643742] c3 25 (kworker/3:0) pc : [<ffffff8008683dd0>] lr : [<ffffff8008683e10>] pstate: 20000145 [ 33.652874] c3 25 (kworker/3:0) sp : ffffffc0f32f3bb0 [ 34.468519] c3 25 (kworker/3:0) Process kworker/3:0 (pid: 25, stack limit = 0xffffffc0f32f0020) [ 34.477220] c3 25 (kworker/3:0) Stack: (0xffffffc0f32f3bb0 to 0xffffffc0f32f4000) [ 34.819822] c3 25 (kworker/3:0) Call trace: [ 34.824021] c3 25 (kworker/3:0) Exception stack(0xffffffc0f32f39c0 to 0xffffffc0f32f3af0) [ 34.924993] c3 25 (kworker/3:0) [<ffffff8008683dd0>] power_allocator_throttle+0x7c8/0x8a4 [ 34.933184] c3 25 (kworker/3:0) [<ffffff80086807f4>] handle_thermal_trip.part.25+0x70/0x224 [ 34.941545] c3 25 (kworker/3:0) [<ffffff8008680a68>] thermal_zone_device_update+0xc0/0x20c [ 34.949818] c3 25 (kworker/3:0) [<ffffff8008680bd4>] thermal_zone_device_check+0x20/0x2c [ 34.957924] c3 25 (kworker/3:0) [<ffffff80080b93a4>] process_one_work+0x168/0x458 [ 34.965414] c3 25 (kworker/3:0) [<ffffff80080ba068>] worker_thread+0x13c/0x4b4 [ 34.972650] c3 25 (kworker/3:0) [<ffffff80080c0a4c>] kthread+0xe8/0xfc [ 34.979187] c3 25 (kworker/3:0) [<ffffff8008084e90>] ret_from_fork+0x10/0x40 [ 34.986244] c3 25 (kworker/3:0) Code: f9405e73 eb1302bf d102e273 54ffc460 (b9402a61) [ 34.994339] c3 25 (kworker/3:0) ---[ end trace 32057901e3b7e1db ]--- Signed-off-by: Yi Zeng <yizeng@asrmicro.com> Signed-off-by: Zhang Rui <rui.zhang@intel.com>
2017-12-26 19:22:26 +08:00
mutex_unlock(&tz->lock);
}
/**
* power_allocator_bind() - bind the power_allocator governor to a thermal zone
* @tz: thermal zone to bind it to
*
* Initialize the PID controller parameters and bind it to the thermal
* zone.
*
* Return: 0 on success, or -ENOMEM if we ran out of memory.
*/
static int power_allocator_bind(struct thermal_zone_device *tz)
{
int ret;
struct power_allocator_params *params;
int control_temp;
params = kzalloc(sizeof(*params), GFP_KERNEL);
if (!params)
return -ENOMEM;
if (!tz->tzp) {
tz->tzp = kzalloc(sizeof(*tz->tzp), GFP_KERNEL);
if (!tz->tzp) {
ret = -ENOMEM;
goto free_params;
}
params->allocated_tzp = true;
}
if (!tz->tzp->sustainable_power)
dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
get_governor_trips(tz, params);
if (tz->trips > 0) {
ret = tz->ops->get_trip_temp(tz,
params->trip_max_desired_temperature,
&control_temp);
if (!ret)
estimate_pid_constants(tz, tz->tzp->sustainable_power,
params->trip_switch_on,
control_temp, false);
}
reset_pid_controller(params);
tz->governor_data = params;
return 0;
free_params:
kfree(params);
return ret;
}
static void power_allocator_unbind(struct thermal_zone_device *tz)
{
struct power_allocator_params *params = tz->governor_data;
dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
if (params->allocated_tzp) {
kfree(tz->tzp);
tz->tzp = NULL;
}
kfree(tz->governor_data);
tz->governor_data = NULL;
}
static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
{
int ret;
int switch_on_temp, control_temp;
struct power_allocator_params *params = tz->governor_data;
/*
* We get called for every trip point but we only need to do
* our calculations once
*/
if (trip != params->trip_max_desired_temperature)
return 0;
ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
&switch_on_temp);
if (!ret && (tz->temperature < switch_on_temp)) {
tz->passive = 0;
reset_pid_controller(params);
allow_maximum_power(tz);
return 0;
}
tz->passive = 1;
ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
&control_temp);
if (ret) {
dev_warn(&tz->device,
"Failed to get the maximum desired temperature: %d\n",
ret);
return ret;
}
return allocate_power(tz, control_temp);
}
static struct thermal_governor thermal_gov_power_allocator = {
.name = "power_allocator",
.bind_to_tz = power_allocator_bind,
.unbind_from_tz = power_allocator_unbind,
.throttle = power_allocator_throttle,
};
int thermal_gov_power_allocator_register(void)
{
return thermal_register_governor(&thermal_gov_power_allocator);
}
void thermal_gov_power_allocator_unregister(void)
{
thermal_unregister_governor(&thermal_gov_power_allocator);
}