linux/drivers/thermal/gov_step_wise.c

142 lines
4.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* step_wise.c - A step-by-step Thermal throttling governor
*
* Copyright (C) 2012 Intel Corp
* Copyright (C) 2012 Durgadoss R <durgadoss.r@intel.com>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#include <linux/thermal.h>
#include <linux/minmax.h>
#include "thermal_trace.h"
#include "thermal_core.h"
/*
* If the temperature is higher than a trip point,
* a. if the trend is THERMAL_TREND_RAISING, use higher cooling
* state for this trip point
thermal/drivers/step_wise: Fix temperature regulation misbehavior There is a particular situation when the cooling device is cpufreq and the heat dissipation is not efficient enough where the temperature increases little by little until reaching the critical threshold and leading to a SoC reset. The behavior is reproducible on a hikey6220 with bad heat dissipation (eg. stacked with other boards). Running a simple C program doing while(1); for each CPU of the SoC makes the temperature to reach the passive regulation trip point and ends up to the maximum allowed temperature followed by a reset. This issue has been also reported by running the libhugetlbfs test suite. What is observed is a ping pong between two cpu frequencies, 1.2GHz and 900MHz while the temperature continues to grow. It appears the step wise governor calls get_target_state() the first time with the throttle set to true and the trend to 'raising'. The code selects logically the next state, so the cpu frequency decreases from 1.2GHz to 900MHz, so far so good. The temperature decreases immediately but still stays greater than the trip point, then get_target_state() is called again, this time with the throttle set to true *and* the trend to 'dropping'. From there the algorithm assumes we have to step down the state and the cpu frequency jumps back to 1.2GHz. But the temperature is still higher than the trip point, so get_target_state() is called with throttle=1 and trend='raising' again, we jump to 900MHz, then get_target_state() is called with throttle=1 and trend='dropping', we jump to 1.2GHz, etc ... but the temperature does not stabilizes and continues to increase. [ 237.922654] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 237.922678] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 237.922690] thermal cooling_device0: cur_state=0 [ 237.922701] thermal cooling_device0: old_target=0, target=1 [ 238.026656] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 238.026680] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=1 [ 238.026694] thermal cooling_device0: cur_state=1 [ 238.026707] thermal cooling_device0: old_target=1, target=0 [ 238.134647] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 238.134667] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 238.134679] thermal cooling_device0: cur_state=0 [ 238.134690] thermal cooling_device0: old_target=0, target=1 In this situation the temperature continues to increase while the trend is oscillating between 'dropping' and 'raising'. We need to keep the current state untouched if the throttle is set, so the temperature can decrease or a higher state could be selected, thus preventing this oscillation. Keeping the next_target untouched when 'throttle' is true at 'dropping' time fixes the issue. The following traces show the governor does not change the next state if trend==2 (dropping) and throttle==1. [ 2306.127987] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2306.128009] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 2306.128021] thermal cooling_device0: cur_state=0 [ 2306.128031] thermal cooling_device0: old_target=0, target=1 [ 2306.231991] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2306.232016] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=1 [ 2306.232030] thermal cooling_device0: cur_state=1 [ 2306.232042] thermal cooling_device0: old_target=1, target=1 [ 2306.335982] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2306.336006] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=1 [ 2306.336021] thermal cooling_device0: cur_state=1 [ 2306.336034] thermal cooling_device0: old_target=1, target=1 [ 2306.439984] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2306.440008] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=0 [ 2306.440022] thermal cooling_device0: cur_state=1 [ 2306.440034] thermal cooling_device0: old_target=1, target=0 [ ... ] After a while, if the temperature continues to increase, the next state becomes 2 which is 720MHz on the hikey. That results in the temperature stabilizing around the trip point. [ 2455.831982] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2455.832006] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=0 [ 2455.832019] thermal cooling_device0: cur_state=1 [ 2455.832032] thermal cooling_device0: old_target=1, target=1 [ 2455.935985] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2455.936013] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=0 [ 2455.936027] thermal cooling_device0: cur_state=1 [ 2455.936040] thermal cooling_device0: old_target=1, target=1 [ 2456.043984] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2456.044009] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=0 [ 2456.044023] thermal cooling_device0: cur_state=1 [ 2456.044036] thermal cooling_device0: old_target=1, target=1 [ 2456.148001] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2456.148028] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 2456.148042] thermal cooling_device0: cur_state=1 [ 2456.148055] thermal cooling_device0: old_target=1, target=2 [ 2456.252009] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2456.252041] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=0 [ 2456.252058] thermal cooling_device0: cur_state=2 [ 2456.252075] thermal cooling_device0: old_target=2, target=1 IOW, this change is needed to keep the state for a cooling device if the temperature trend is oscillating while the temperature increases slightly. Without this change, the situation above leads to a catastrophic crash by a hardware reset on hikey. This issue has been reported to happen on an OMAP dra7xx also. Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Keerthy <j-keerthy@ti.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Leo Yan <leo.yan@linaro.org> Tested-by: Keerthy <j-keerthy@ti.com> Reviewed-by: Keerthy <j-keerthy@ti.com> Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
2017-10-19 17:05:58 +00:00
* b. if the trend is THERMAL_TREND_DROPPING, do nothing
* If the temperature is lower than a trip point,
* a. if the trend is THERMAL_TREND_RAISING, do nothing
* b. if the trend is THERMAL_TREND_DROPPING, use lower cooling
* state for this trip point, if the cooling state already
* equals lower limit, deactivate the thermal instance
*/
static unsigned long get_target_state(struct thermal_instance *instance,
enum thermal_trend trend, bool throttle)
{
struct thermal_cooling_device *cdev = instance->cdev;
unsigned long cur_state;
/*
* We keep this instance the way it is by default.
* Otherwise, we use the current state of the
* cdev in use to determine the next_target.
*/
cdev->ops->get_cur_state(cdev, &cur_state);
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, "cur_state=%ld\n", cur_state);
if (!instance->initialized) {
if (throttle)
return clamp(cur_state + 1, instance->lower, instance->upper);
return THERMAL_NO_TARGET;
}
if (throttle) {
if (trend == THERMAL_TREND_RAISING)
return clamp(cur_state + 1, instance->lower, instance->upper);
} else if (trend == THERMAL_TREND_DROPPING) {
if (cur_state <= instance->lower)
return THERMAL_NO_TARGET;
thermal: gov_step_wise: Go straight to instance->lower when mitigation is over Commit b6846826982b ("thermal: gov_step_wise: Restore passive polling management") attempted to fix a Step-Wise thermal governor issue introduced by commit 042a3d80f118 ("thermal: core: Move passive polling management to the core"), which caused the governor to leave cooling devices in high states, by partially reverting that commit. However, this turns out to be insufficient on some systems due to interactions between the governor code restored by commit b6846826982b and the passive polling management in the thermal core. For this reason, revert commit b6846826982b and make the governor set the target cooling device state to the "lower" one as soon as the zone temperature falls below the threshold of the trip point corresponding to the given thermal instance, which means that thermal mitigation is not necessary any more. Before this change the "lower" cooling device state would be reached in steps through the passive polling mechanism which was questionable for three reasons: (1) cooling device were kept in high states when that was not necessary (and it could adversely impact performance), (2) it only worked for thermal zones with nonzero passive_delay_jiffies value, and (3) passive polling belongs to the core and should not be hijacked by governors for their internal purposes. Fixes: b6846826982b ("thermal: gov_step_wise: Restore passive polling management") Closes: https://lore.kernel.org/linux-pm/6759ce9f-281d-4fcd-bb4c-b784a1cc5f6e@oldschoolsolutions.biz Reported-by: Jens Glathe <jens.glathe@oldschoolsolutions.biz> Tested-by: Jens Glathe <jens.glathe@oldschoolsolutions.biz> Link: https://patch.msgid.link/12464461.O9o76ZdvQC@rjwysocki.net Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Tested-by: Steev Klimaszewski <steev@kali.org> Tested-by: Johan Hovold <johan+linaro@kernel.org>
2024-06-22 12:26:33 +00:00
/*
* If 'throttle' is false, no mitigation is necessary, so
* request the lower state for this instance.
*/
return instance->lower;
}
return instance->target;
}
static void thermal_zone_trip_update(struct thermal_zone_device *tz,
const struct thermal_trip_desc *td,
int trip_threshold)
{
const struct thermal_trip *trip = &td->trip;
enum thermal_trend trend = get_tz_trend(tz, trip);
int trip_id = thermal_zone_trip_id(tz, trip);
struct thermal_instance *instance;
bool throttle = false;
if (tz->temperature >= trip_threshold) {
throttle = true;
trace_thermal_zone_trip(tz, trip_id, 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
dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
trip_id, trip->type, trip_threshold, trend, throttle);
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
list_for_each_entry(instance, &td->thermal_instances, trip_node) {
int old_target;
old_target = instance->target;
instance->target = get_target_state(instance, trend, throttle);
dev_dbg(&instance->cdev->device, "old_target=%d, target=%ld\n",
old_target, instance->target);
if (instance->initialized && old_target == instance->target)
continue;
instance->initialized = true;
scoped_guard(cooling_dev, instance->cdev) {
instance->cdev->updated = false; /* cdev needs update */
}
}
}
static void step_wise_manage(struct thermal_zone_device *tz)
{
const struct thermal_trip_desc *td;
struct thermal_instance *instance;
lockdep_assert_held(&tz->lock);
/*
* Throttling Logic: Use the trend of the thermal zone to throttle.
* If the thermal zone is 'heating up', throttle all of the cooling
* devices associated with each trip point by one step. If the zone
* is 'cooling down', it brings back the performance of the devices
* by one step.
*/
for_each_trip_desc(tz, td) {
const struct thermal_trip *trip = &td->trip;
if (trip->temperature == THERMAL_TEMP_INVALID ||
trip->type == THERMAL_TRIP_CRITICAL ||
trip->type == THERMAL_TRIP_HOT)
continue;
thermal_zone_trip_update(tz, td, td->threshold);
}
for_each_trip_desc(tz, td) {
list_for_each_entry(instance, &td->thermal_instances, trip_node)
thermal_cdev_update(instance->cdev);
}
}
static struct thermal_governor thermal_gov_step_wise = {
.name = "step_wise",
.manage = step_wise_manage,
};
THERMAL_GOVERNOR_DECLARE(thermal_gov_step_wise);