2019-05-27 06:55:15 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2012-09-21 06:36:04 +00:00
|
|
|
/*
|
|
|
|
* 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>
|
2022-06-29 15:10:11 +00:00
|
|
|
#include <linux/minmax.h>
|
2023-03-07 13:37:25 +00:00
|
|
|
#include "thermal_trace.h"
|
2012-09-21 06:36:04 +00:00
|
|
|
|
|
|
|
#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
|
2012-11-19 08:10:20 +00:00
|
|
|
* 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
|
2012-09-21 06:36:04 +00:00
|
|
|
*/
|
|
|
|
static unsigned long get_target_state(struct thermal_instance *instance,
|
2012-11-19 08:10:20 +00:00
|
|
|
enum thermal_trend trend, bool throttle)
|
2012-09-21 06:36:04 +00:00
|
|
|
{
|
|
|
|
struct thermal_cooling_device *cdev = instance->cdev;
|
|
|
|
unsigned long cur_state;
|
|
|
|
|
2013-06-17 13:24:24 +00:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2012-09-21 06:36:04 +00:00
|
|
|
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);
|
2012-09-21 06:36:04 +00:00
|
|
|
|
2015-10-30 08:31:47 +00:00
|
|
|
if (!instance->initialized) {
|
2024-04-03 18:11:10 +00:00
|
|
|
if (throttle)
|
|
|
|
return clamp(cur_state + 1, instance->lower, instance->upper);
|
2015-10-30 08:31:47 +00:00
|
|
|
|
2024-04-03 18:11:10 +00:00
|
|
|
return THERMAL_NO_TARGET;
|
2015-10-30 08:31:47 +00:00
|
|
|
}
|
|
|
|
|
2023-03-21 05:47:14 +00:00
|
|
|
if (throttle) {
|
|
|
|
if (trend == THERMAL_TREND_RAISING)
|
2024-04-03 18:11:10 +00:00
|
|
|
return clamp(cur_state + 1, instance->lower, instance->upper);
|
|
|
|
} else if (trend == THERMAL_TREND_DROPPING) {
|
|
|
|
if (cur_state <= instance->lower)
|
|
|
|
return THERMAL_NO_TARGET;
|
|
|
|
|
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;
|
2012-09-21 06:36:04 +00:00
|
|
|
}
|
|
|
|
|
2024-04-03 18:11:10 +00:00
|
|
|
return instance->target;
|
2012-09-21 06:36:04 +00:00
|
|
|
}
|
|
|
|
|
2023-10-12 18:34:50 +00:00
|
|
|
static void thermal_zone_trip_update(struct thermal_zone_device *tz,
|
2024-10-04 19:39:19 +00:00
|
|
|
const struct thermal_trip_desc *td,
|
2024-04-10 16:43:07 +00:00
|
|
|
int trip_threshold)
|
2012-09-21 06:36:04 +00:00
|
|
|
{
|
2024-10-04 19:39:19 +00:00
|
|
|
const struct thermal_trip *trip = &td->trip;
|
2024-04-10 16:44:14 +00:00
|
|
|
enum thermal_trend trend = get_tz_trend(tz, trip);
|
2023-10-12 18:34:50 +00:00
|
|
|
int trip_id = thermal_zone_trip_id(tz, trip);
|
2012-11-22 07:45:02 +00:00
|
|
|
struct thermal_instance *instance;
|
|
|
|
bool throttle = false;
|
2012-09-21 06:36:04 +00:00
|
|
|
|
2024-04-10 16:43:07 +00:00
|
|
|
if (tz->temperature >= trip_threshold) {
|
2012-11-22 07:45:02 +00:00
|
|
|
throttle = true;
|
2023-09-21 17:52:44 +00:00
|
|
|
trace_thermal_zone_trip(tz, trip_id, trip->type);
|
2014-07-29 10:50:50 +00:00
|
|
|
}
|
2012-11-22 07:45:02 +00:00
|
|
|
|
2015-07-24 06:12:54 +00:00
|
|
|
dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
|
2024-04-10 16:43:07 +00:00
|
|
|
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
|
|
|
|
2024-10-04 19:39:19 +00:00
|
|
|
list_for_each_entry(instance, &td->thermal_instances, trip_node) {
|
2024-04-10 16:44:14 +00:00
|
|
|
int old_target;
|
|
|
|
|
2012-11-22 07:45:02 +00:00
|
|
|
old_target = instance->target;
|
|
|
|
instance->target = get_target_state(instance, trend, throttle);
|
2024-04-10 16:44:14 +00:00
|
|
|
|
|
|
|
dev_dbg(&instance->cdev->device, "old_target=%d, target=%ld\n",
|
|
|
|
old_target, instance->target);
|
2012-11-22 07:45:02 +00:00
|
|
|
|
2015-10-30 08:31:47 +00:00
|
|
|
if (instance->initialized && old_target == instance->target)
|
2013-06-17 13:24:23 +00:00
|
|
|
continue;
|
|
|
|
|
2015-10-30 08:31:47 +00:00
|
|
|
instance->initialized = true;
|
2024-04-10 16:44:14 +00:00
|
|
|
|
2024-10-14 14:59:46 +00:00
|
|
|
scoped_guard(cooling_dev, instance->cdev) {
|
|
|
|
instance->cdev->updated = false; /* cdev needs update */
|
|
|
|
}
|
2012-11-22 07:45:02 +00:00
|
|
|
}
|
2012-09-21 06:36:04 +00:00
|
|
|
}
|
|
|
|
|
2024-04-10 16:13:55 +00:00
|
|
|
static void step_wise_manage(struct thermal_zone_device *tz)
|
2012-09-21 06:36:04 +00:00
|
|
|
{
|
2024-04-10 16:13:55 +00:00
|
|
|
const struct thermal_trip_desc *td;
|
2012-09-21 06:36:04 +00:00
|
|
|
struct thermal_instance *instance;
|
|
|
|
|
2022-08-05 15:38:33 +00:00
|
|
|
lockdep_assert_held(&tz->lock);
|
2012-09-21 06:36:04 +00:00
|
|
|
|
2024-04-10 16:13:55 +00:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2024-10-04 19:39:19 +00:00
|
|
|
thermal_zone_trip_update(tz, td, td->threshold);
|
2024-04-10 16:13:55 +00:00
|
|
|
}
|
2022-08-05 15:38:32 +00:00
|
|
|
|
2024-10-04 19:39:19 +00:00
|
|
|
for_each_trip_desc(tz, td) {
|
|
|
|
list_for_each_entry(instance, &td->thermal_instances, trip_node)
|
|
|
|
thermal_cdev_update(instance->cdev);
|
|
|
|
}
|
2012-09-21 06:36:04 +00:00
|
|
|
}
|
|
|
|
|
2012-09-27 10:58:12 +00:00
|
|
|
static struct thermal_governor thermal_gov_step_wise = {
|
2024-04-10 16:13:55 +00:00
|
|
|
.name = "step_wise",
|
|
|
|
.manage = step_wise_manage,
|
2012-09-21 06:36:04 +00:00
|
|
|
};
|
2019-06-12 20:13:25 +00:00
|
|
|
THERMAL_GOVERNOR_DECLARE(thermal_gov_step_wise);
|