linux-stable/drivers/acpi/thermal.c

1148 lines
28 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 Based on 3 normalized pattern(s): 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 either version 2 of the license or at your option any later version 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 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 either version 2 of the license or at your option any later version [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] 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 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 either version 2 of the license or at your option any later version [author] [graeme] [gregory] [gg]@[slimlogic] [co] [uk] [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] [based] [on] [twl6030]_[usb] [c] [author] [hema] [hk] [hemahk]@[ti] [com] 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 extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 1105 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190527070033.202006027@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-27 06:55:06 +00:00
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* acpi_thermal.c - ACPI Thermal Zone Driver ($Revision: 41 $)
*
* Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
*
* This driver fully implements the ACPI thermal policy as described in the
* ACPI 2.0 Specification.
*
* TBD: 1. Implement passive cooling hysteresis.
* 2. Enhance passive cooling (CPU) states/limit interface to support
* concepts of 'multiple limiters', upper/lower limits, etc.
*/
#define pr_fmt(fmt) "ACPI: thermal: " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/dmi.h>
#include <linux/init.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/types.h>
#include <linux/jiffies.h>
#include <linux/kmod.h>
#include <linux/reboot.h>
#include <linux/device.h>
#include <linux/thermal.h>
ACPI: Clean up inclusions of ACPI header files Replace direct inclusions of <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h>, which are incorrect, with <linux/acpi.h> inclusions and remove some inclusions of those files that aren't necessary. First of all, <acpi/acpi.h>, <acpi/acpi_bus.h> and <acpi/acpi_drivers.h> should not be included directly from any files that are built for CONFIG_ACPI unset, because that generally leads to build warnings about undefined symbols in !CONFIG_ACPI builds. For CONFIG_ACPI set, <linux/acpi.h> includes those files and for CONFIG_ACPI unset it provides stub ACPI symbols to be used in that case. Second, there are ordering dependencies between those files that always have to be met. Namely, it is required that <acpi/acpi_bus.h> be included prior to <acpi/acpi_drivers.h> so that the acpi_pci_root declarations the latter depends on are always there. And <acpi/acpi.h> which provides basic ACPICA type declarations should always be included prior to any other ACPI headers in CONFIG_ACPI builds. That also is taken care of including <linux/acpi.h> as appropriate. Signed-off-by: Lv Zheng <lv.zheng@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Tony Luck <tony.luck@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> (drivers/pci stuff) Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> (Xen stuff) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-12-03 00:49:16 +00:00
#include <linux/acpi.h>
#include <linux/workqueue.h>
#include <linux/uaccess.h>
ACPI: thermal: switch to use <linux/units.h> helpers This switches the ACPI thermal zone driver to use celsius_to_deci_kelvin(), deci_kelvin_to_celsius(), and deci_kelvin_to_millicelsius_with_offset() in <linux/units.h> instead of helpers in <linux/thermal.h>. This is preparation for centralizing the kelvin to/from Celsius conversion helpers in <linux/units.h>. Link: http://lkml.kernel.org/r/1576386975-7941-3-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Sujith Thomas <sujith.thomas@intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Andy Shevchenko <andy@infradead.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@verdurent.com> Cc: Jean Delvare <jdelvare@suse.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Keith Busch <kbusch@kernel.org> Cc: Jens Axboe <axboe@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Cc: Hartmut Knaack <knaack.h@gmx.de> Cc: Johannes Berg <johannes.berg@intel.com> Cc: Jonathan Cameron <jic23@kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Kalle Valo <kvalo@codeaurora.org> Cc: Lars-Peter Clausen <lars@metafoo.de> Cc: Luca Coelho <luciano.coelho@intel.com> Cc: Peter Meerwald-Stadler <pmeerw@pmeerw.net> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-31 06:15:33 +00:00
#include <linux/units.h>
#include "internal.h"
#define ACPI_THERMAL_CLASS "thermal_zone"
#define ACPI_THERMAL_DEVICE_NAME "Thermal Zone"
#define ACPI_THERMAL_NOTIFY_TEMPERATURE 0x80
#define ACPI_THERMAL_NOTIFY_THRESHOLDS 0x81
#define ACPI_THERMAL_NOTIFY_DEVICES 0x82
#define ACPI_THERMAL_NOTIFY_CRITICAL 0xF0
#define ACPI_THERMAL_NOTIFY_HOT 0xF1
#define ACPI_THERMAL_MODE_ACTIVE 0x00
#define ACPI_THERMAL_MAX_ACTIVE 10
#define ACPI_THERMAL_MAX_LIMIT_STR_LEN 65
#define ACPI_THERMAL_TRIP_PASSIVE (-1)
/*
* This exception is thrown out in two cases:
* 1.An invalid trip point becomes invalid or a valid trip point becomes invalid
* when re-evaluating the AML code.
* 2.TODO: Devices listed in _PSL, _ALx, _TZD may change.
* We need to re-bind the cooling devices of a thermal zone when this occurs.
*/
#define ACPI_THERMAL_TRIPS_EXCEPTION(tz, str) \
do { \
acpi_handle_info(tz->device->handle, \
"ACPI thermal trip point %s changed\n" \
"Please report to linux-acpi@vger.kernel.org\n", str); \
} while (0)
static int act;
module_param(act, int, 0644);
MODULE_PARM_DESC(act, "Disable or override all lowest active trip points.");
static int crt;
module_param(crt, int, 0644);
MODULE_PARM_DESC(crt, "Disable or lower all critical trip points.");
static int tzp;
ACPI: thermal: expose "thermal.tzp=" to set global polling frequency Thermal Zone Polling frequency (_TZP) is an optional ACPI object recommending the rate that the OS should poll the associated thermal zone. If _TZP is 0, no polling should be used. If _TZP is non-zero, then the platform recommends that the OS poll the thermal zone at the specified rate. The minimum period is 30 seconds. The maximum period is 5 minutes. (note _TZP and thermal.tzp units are in deci-seconds, so _TZP = 300 corresponds to 30 seconds) If _TZP is not present, ACPI 3.0b recommends that the thermal zone be polled at an "OS provided default frequency". However, common industry practice is: 1. The BIOS never specifies any _TZP 2. High volume OS's from this century never poll any thermal zones Ie. The OS depends on the platform's ability to provoke thermal events when necessary, and the "OS provided default frequency" is "never":-) There is a proposal that ACPI 4.0 be updated to reflect common industry practice -- ie. no _TZP, no polling. The Linux kernel already follows this practice -- thermal zones are not polled unless _TZP is present and non-zero. But thermal zone polling is useful as a workaround for systems which have ACPI thermal control, but have an issue preventing thermal events. Indeed, some Linux distributions still set a non-zero thermal polling frequency for this reason. But rather than ask the user to write a polling frequency into all the /proc/acpi/thermal_zone/*/polling_frequency files, here we simply document and expose the already existing module parameter to do the same at system level, to simplify debugging those broken platforms. Note that thermal.tzp is a module-load time parameter only. Signed-off-by: Len Brown <len.brown@intel.com>
2007-08-12 04:12:26 +00:00
module_param(tzp, int, 0444);
MODULE_PARM_DESC(tzp, "Thermal zone polling frequency, in 1/10 seconds.");
static int off;
module_param(off, int, 0);
MODULE_PARM_DESC(off, "Set to disable ACPI thermal support.");
static int psv;
module_param(psv, int, 0644);
MODULE_PARM_DESC(psv, "Disable or override all passive trip points.");
static struct workqueue_struct *acpi_thermal_pm_queue;
struct acpi_thermal_trip {
unsigned long temp_dk;
struct acpi_handle_list devices;
};
struct acpi_thermal_passive {
struct acpi_thermal_trip trip;
unsigned long tc1;
unsigned long tc2;
unsigned long delay;
};
struct acpi_thermal_active {
struct acpi_thermal_trip trip;
};
struct acpi_thermal_trips {
struct acpi_thermal_passive passive;
struct acpi_thermal_active active[ACPI_THERMAL_MAX_ACTIVE];
};
struct acpi_thermal {
struct acpi_device *device;
acpi_bus_id name;
unsigned long temp_dk;
unsigned long last_temp_dk;
unsigned long polling_frequency;
volatile u8 zombie;
struct acpi_thermal_trips trips;
struct thermal_trip *trip_table;
struct thermal_zone_device *thermal_zone;
ACPI: thermal: switch to use <linux/units.h> helpers This switches the ACPI thermal zone driver to use celsius_to_deci_kelvin(), deci_kelvin_to_celsius(), and deci_kelvin_to_millicelsius_with_offset() in <linux/units.h> instead of helpers in <linux/thermal.h>. This is preparation for centralizing the kelvin to/from Celsius conversion helpers in <linux/units.h>. Link: http://lkml.kernel.org/r/1576386975-7941-3-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Sujith Thomas <sujith.thomas@intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Andy Shevchenko <andy@infradead.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@verdurent.com> Cc: Jean Delvare <jdelvare@suse.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Keith Busch <kbusch@kernel.org> Cc: Jens Axboe <axboe@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Cc: Hartmut Knaack <knaack.h@gmx.de> Cc: Johannes Berg <johannes.berg@intel.com> Cc: Jonathan Cameron <jic23@kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Kalle Valo <kvalo@codeaurora.org> Cc: Lars-Peter Clausen <lars@metafoo.de> Cc: Luca Coelho <luciano.coelho@intel.com> Cc: Peter Meerwald-Stadler <pmeerw@pmeerw.net> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-31 06:15:33 +00:00
int kelvin_offset; /* in millidegrees */
struct work_struct thermal_check_work;
ACPI: thermal: Do not call acpi_thermal_check() directly Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman <stephen.berman@gmx.net> Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Tested-by: Stephen Berman <stephen.berman@gmx.net> Cc: All applicable <stable@vger.kernel.org>
2021-01-14 18:34:22 +00:00
struct mutex thermal_check_lock;
refcount_t thermal_check_count;
};
/* --------------------------------------------------------------------------
Thermal Zone Management
-------------------------------------------------------------------------- */
static int acpi_thermal_get_temperature(struct acpi_thermal *tz)
{
acpi_status status = AE_OK;
unsigned long long tmp;
if (!tz)
return -EINVAL;
tz->last_temp_dk = tz->temp_dk;
status = acpi_evaluate_integer(tz->device->handle, "_TMP", NULL, &tmp);
if (ACPI_FAILURE(status))
return -ENODEV;
tz->temp_dk = tmp;
acpi_handle_debug(tz->device->handle, "Temperature is %lu dK\n",
tz->temp_dk);
return 0;
}
static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz)
{
acpi_status status = AE_OK;
unsigned long long tmp;
if (!tz)
return -EINVAL;
status = acpi_evaluate_integer(tz->device->handle, "_TZP", NULL, &tmp);
if (ACPI_FAILURE(status))
return -ENODEV;
tz->polling_frequency = tmp;
acpi_handle_debug(tz->device->handle, "Polling frequency is %lu dS\n",
tz->polling_frequency);
return 0;
}
static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k)
{
if (temp_deci_k == THERMAL_TEMP_INVALID)
return THERMAL_TEMP_INVALID;
return deci_kelvin_to_millicelsius_with_offset(temp_deci_k,
tz->kelvin_offset);
}
static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip)
{
return acpi_trip->temp_dk != THERMAL_TEMP_INVALID;
}
static int active_trip_index(struct acpi_thermal *tz,
struct acpi_thermal_trip *acpi_trip)
{
struct acpi_thermal_active *active;
active = container_of(acpi_trip, struct acpi_thermal_active, trip);
return active - tz->trips.active;
}
static long get_passive_temp(struct acpi_thermal *tz)
{
int temp;
if (acpi_passive_trip_temp(tz->device, &temp))
return THERMAL_TEMP_INVALID;
return temp;
}
static long get_active_temp(struct acpi_thermal *tz, int index)
{
int temp;
if (acpi_active_trip_temp(tz->device, index, &temp))
return THERMAL_TEMP_INVALID;
/*
* If an override has been provided, apply it so there are no active
* trips with thresholds greater than the override.
*/
if (act > 0) {
unsigned long long override = celsius_to_deci_kelvin(act);
if (temp > override)
return override;
}
return temp;
}
static void acpi_thermal_update_trip(struct acpi_thermal *tz,
const struct thermal_trip *trip)
{
struct acpi_thermal_trip *acpi_trip = trip->priv;
if (trip->type == THERMAL_TRIP_PASSIVE) {
if (psv > 0)
return;
acpi_trip->temp_dk = get_passive_temp(tz);
} else {
int index = active_trip_index(tz, acpi_trip);
acpi_trip->temp_dk = get_active_temp(tz, index);
}
if (!acpi_thermal_trip_valid(acpi_trip))
ACPI_THERMAL_TRIPS_EXCEPTION(tz, "state");
}
static bool update_trip_devices(struct acpi_thermal *tz,
struct acpi_thermal_trip *acpi_trip,
int index, bool compare)
{
struct acpi_handle_list devices = { 0 };
char method[] = "_PSL";
if (index != ACPI_THERMAL_TRIP_PASSIVE) {
method[1] = 'A';
method[2] = 'L';
method[3] = '0' + index;
}
if (!acpi_evaluate_reference(tz->device->handle, method, NULL, &devices)) {
acpi_handle_info(tz->device->handle, "%s evaluation failure\n", method);
return false;
}
if (acpi_handle_list_equal(&acpi_trip->devices, &devices)) {
acpi_handle_list_free(&devices);
return true;
}
if (compare)
ACPI_THERMAL_TRIPS_EXCEPTION(tz, "device");
acpi_handle_list_replace(&acpi_trip->devices, &devices);
return true;
}
static void acpi_thermal_update_trip_devices(struct acpi_thermal *tz,
const struct thermal_trip *trip)
{
struct acpi_thermal_trip *acpi_trip = trip->priv;
int index = trip->type == THERMAL_TRIP_PASSIVE ?
ACPI_THERMAL_TRIP_PASSIVE : active_trip_index(tz, acpi_trip);
if (update_trip_devices(tz, acpi_trip, index, true))
return;
acpi_trip->temp_dk = THERMAL_TEMP_INVALID;
ACPI_THERMAL_TRIPS_EXCEPTION(tz, "state");
}
struct adjust_trip_data {
struct acpi_thermal *tz;
u32 event;
};
static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
{
struct acpi_thermal_trip *acpi_trip = trip->priv;
struct adjust_trip_data *atd = data;
struct acpi_thermal *tz = atd->tz;
int temp;
if (!acpi_trip || !acpi_thermal_trip_valid(acpi_trip))
return 0;
if (atd->event == ACPI_THERMAL_NOTIFY_THRESHOLDS)
acpi_thermal_update_trip(tz, trip);
else
acpi_thermal_update_trip_devices(tz, trip);
if (acpi_thermal_trip_valid(acpi_trip))
temp = acpi_thermal_temp(tz, acpi_trip->temp_dk);
else
temp = THERMAL_TEMP_INVALID;
thermal_zone_set_trip_temp(tz->thermal_zone, trip, temp);
return 0;
}
static void acpi_queue_thermal_check(struct acpi_thermal *tz)
{
if (!work_pending(&tz->thermal_check_work))
queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work);
}
static void acpi_thermal_trips_update(struct acpi_thermal *tz, u32 event)
{
struct adjust_trip_data atd = { .tz = tz, .event = event };
struct acpi_device *adev = tz->device;
/*
* Use thermal_zone_for_each_trip() to carry out the trip points
* update, so as to protect thermal_get_trend() from getting stale
* trip point temperatures and to prevent thermal_zone_device_update()
* invoked from acpi_thermal_check_fn() from producing inconsistent
* results.
*/
thermal_zone_for_each_trip(tz->thermal_zone,
acpi_thermal_adjust_trip, &atd);
acpi_queue_thermal_check(tz);
acpi_bus_generate_netlink_event(adev->pnp.device_class,
dev_name(&adev->dev), event, 0);
}
static int acpi_thermal_get_critical_trip(struct acpi_thermal *tz)
{
int temp;
if (crt > 0) {
temp = celsius_to_deci_kelvin(crt);
goto set;
}
if (crt == -1) {
acpi_handle_debug(tz->device->handle, "Critical threshold disabled\n");
return THERMAL_TEMP_INVALID;
}
if (acpi_critical_trip_temp(tz->device, &temp))
return THERMAL_TEMP_INVALID;
if (temp <= 2732) {
/*
* Below zero (Celsius) values clearly aren't right for sure,
* so discard them as invalid.
*/
pr_info(FW_BUG "Invalid critical threshold (%d)\n", temp);
return THERMAL_TEMP_INVALID;
}
set:
acpi_handle_debug(tz->device->handle, "Critical threshold [%d]\n", temp);
return temp;
}
static int acpi_thermal_get_hot_trip(struct acpi_thermal *tz)
{
int temp;
if (acpi_hot_trip_temp(tz->device, &temp) || temp == THERMAL_TEMP_INVALID) {
acpi_handle_debug(tz->device->handle, "No hot threshold\n");
return THERMAL_TEMP_INVALID;
}
acpi_handle_debug(tz->device->handle, "Hot threshold [%d]\n", temp);
return temp;
}
static bool passive_trip_params_init(struct acpi_thermal *tz)
{
unsigned long long tmp;
acpi_status status;
status = acpi_evaluate_integer(tz->device->handle, "_TC1", NULL, &tmp);
if (ACPI_FAILURE(status))
return false;
tz->trips.passive.tc1 = tmp;
status = acpi_evaluate_integer(tz->device->handle, "_TC2", NULL, &tmp);
if (ACPI_FAILURE(status))
return false;
tz->trips.passive.tc2 = tmp;
status = acpi_evaluate_integer(tz->device->handle, "_TFP", NULL, &tmp);
if (ACPI_SUCCESS(status)) {
tz->trips.passive.delay = tmp;
return true;
}
status = acpi_evaluate_integer(tz->device->handle, "_TSP", NULL, &tmp);
if (ACPI_FAILURE(status))
return false;
tz->trips.passive.delay = tmp * 100;
return true;
}
static bool acpi_thermal_init_trip(struct acpi_thermal *tz, int index)
{
struct acpi_thermal_trip *acpi_trip;
long temp;
if (index == ACPI_THERMAL_TRIP_PASSIVE) {
acpi_trip = &tz->trips.passive.trip;
if (psv == -1)
goto fail;
if (!passive_trip_params_init(tz))
goto fail;
temp = psv > 0 ? celsius_to_deci_kelvin(psv) :
get_passive_temp(tz);
} else {
acpi_trip = &tz->trips.active[index].trip;
if (act == -1)
goto fail;
temp = get_active_temp(tz, index);
}
if (temp == THERMAL_TEMP_INVALID)
goto fail;
if (!update_trip_devices(tz, acpi_trip, index, false))
goto fail;
acpi_trip->temp_dk = temp;
return true;
fail:
acpi_trip->temp_dk = THERMAL_TEMP_INVALID;
return false;
}
static int acpi_thermal_get_trip_points(struct acpi_thermal *tz)
{
unsigned int count = 0;
int i;
if (acpi_thermal_init_trip(tz, ACPI_THERMAL_TRIP_PASSIVE))
count++;
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
if (acpi_thermal_init_trip(tz, i))
count++;
else
break;
}
while (++i < ACPI_THERMAL_MAX_ACTIVE)
tz->trips.active[i].trip.temp_dk = THERMAL_TEMP_INVALID;
return count;
}
/* sys I/F for generic thermal sysfs support */
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
static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
{
struct acpi_thermal *tz = thermal_zone_device_priv(thermal);
int result;
if (!tz)
return -EINVAL;
result = acpi_thermal_get_temperature(tz);
if (result)
return result;
*temp = deci_kelvin_to_millicelsius_with_offset(tz->temp_dk,
tz->kelvin_offset);
return 0;
}
static int thermal_get_trend(struct thermal_zone_device *thermal,
const struct thermal_trip *trip,
enum thermal_trend *trend)
{
struct acpi_thermal *tz = thermal_zone_device_priv(thermal);
struct acpi_thermal_trip *acpi_trip;
int t;
if (!tz || !trip)
return -EINVAL;
acpi_trip = trip->priv;
if (!acpi_trip || !acpi_thermal_trip_valid(acpi_trip))
return -EINVAL;
switch (trip->type) {
case THERMAL_TRIP_PASSIVE:
t = tz->trips.passive.tc1 * (tz->temp_dk -
tz->last_temp_dk) +
tz->trips.passive.tc2 * (tz->temp_dk -
acpi_trip->temp_dk);
if (t > 0)
*trend = THERMAL_TREND_RAISING;
else if (t < 0)
*trend = THERMAL_TREND_DROPPING;
else
*trend = THERMAL_TREND_STABLE;
return 0;
case THERMAL_TRIP_ACTIVE:
t = acpi_thermal_temp(tz, tz->temp_dk);
if (t <= trip->temperature)
break;
*trend = THERMAL_TREND_RAISING;
return 0;
default:
break;
}
return -EINVAL;
}
static void acpi_thermal_zone_device_hot(struct thermal_zone_device *thermal)
{
struct acpi_thermal *tz = thermal_zone_device_priv(thermal);
acpi_bus_generate_netlink_event(tz->device->pnp.device_class,
dev_name(&tz->device->dev),
ACPI_THERMAL_NOTIFY_HOT, 1);
}
static void acpi_thermal_zone_device_critical(struct thermal_zone_device *thermal)
{
struct acpi_thermal *tz = thermal_zone_device_priv(thermal);
acpi_bus_generate_netlink_event(tz->device->pnp.device_class,
dev_name(&tz->device->dev),
ACPI_THERMAL_NOTIFY_CRITICAL, 1);
thermal_zone_device_critical(thermal);
}
struct acpi_thermal_bind_data {
struct thermal_zone_device *thermal;
struct thermal_cooling_device *cdev;
bool bind;
};
static int bind_unbind_cdev_cb(struct thermal_trip *trip, void *arg)
{
struct acpi_thermal_trip *acpi_trip = trip->priv;
struct acpi_thermal_bind_data *bd = arg;
struct thermal_zone_device *thermal = bd->thermal;
struct thermal_cooling_device *cdev = bd->cdev;
struct acpi_device *cdev_adev = cdev->devdata;
int i;
/* Skip critical and hot trips. */
if (!acpi_trip)
return 0;
for (i = 0; i < acpi_trip->devices.count; i++) {
acpi_handle handle = acpi_trip->devices.handles[i];
struct acpi_device *adev = acpi_fetch_acpi_dev(handle);
if (adev != cdev_adev)
continue;
if (bd->bind) {
int ret;
ret = thermal_bind_cdev_to_trip(thermal, trip, cdev,
THERMAL_NO_LIMIT,
THERMAL_NO_LIMIT,
THERMAL_WEIGHT_DEFAULT);
if (ret)
return ret;
} else {
thermal_unbind_cdev_from_trip(thermal, trip, cdev);
}
}
return 0;
}
static int acpi_thermal_bind_unbind_cdev(struct thermal_zone_device *thermal,
struct thermal_cooling_device *cdev,
bool bind)
{
struct acpi_thermal_bind_data bd = {
.thermal = thermal, .cdev = cdev, .bind = bind
};
return for_each_thermal_trip(thermal, bind_unbind_cdev_cb, &bd);
}
static int
acpi_thermal_bind_cooling_device(struct thermal_zone_device *thermal,
struct thermal_cooling_device *cdev)
{
return acpi_thermal_bind_unbind_cdev(thermal, cdev, true);
}
static int
acpi_thermal_unbind_cooling_device(struct thermal_zone_device *thermal,
struct thermal_cooling_device *cdev)
{
return acpi_thermal_bind_unbind_cdev(thermal, cdev, false);
}
static struct thermal_zone_device_ops acpi_thermal_zone_ops = {
.bind = acpi_thermal_bind_cooling_device,
.unbind = acpi_thermal_unbind_cooling_device,
.get_temp = thermal_get_temp,
.get_trend = thermal_get_trend,
.hot = acpi_thermal_zone_device_hot,
.critical = acpi_thermal_zone_device_critical,
};
static int acpi_thermal_zone_sysfs_add(struct acpi_thermal *tz)
{
struct device *tzdev = thermal_zone_device(tz->thermal_zone);
int ret;
ret = sysfs_create_link(&tz->device->dev.kobj,
&tzdev->kobj, "thermal_zone");
if (ret)
return ret;
ret = sysfs_create_link(&tzdev->kobj,
&tz->device->dev.kobj, "device");
if (ret)
sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone");
return ret;
}
static void acpi_thermal_zone_sysfs_remove(struct acpi_thermal *tz)
{
struct device *tzdev = thermal_zone_device(tz->thermal_zone);
sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone");
sysfs_remove_link(&tzdev->kobj, "device");
}
static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz,
unsigned int trip_count,
int passive_delay)
{
int result;
tz->thermal_zone = thermal_zone_device_register_with_trips("acpitz",
tz->trip_table,
trip_count,
0, tz,
&acpi_thermal_zone_ops,
NULL,
passive_delay,
tz->polling_frequency * 100);
if (IS_ERR(tz->thermal_zone))
return PTR_ERR(tz->thermal_zone);
result = acpi_thermal_zone_sysfs_add(tz);
if (result)
goto unregister_tzd;
thermal: Use mode helpers in drivers Use thermal_zone_device_{en|dis}able() and thermal_zone_device_is_enabled(). Consequently, all set_mode() implementations in drivers: - can stop modifying tzd's "mode" member, - shall stop taking tzd's lock, as it is taken in the helpers - shall stop calling thermal_zone_device_update() as it is called in the helpers - can assume they are called when the mode truly changes, so checks to verify that can be dropped Not providing set_mode() by a driver no longer prevents the core from being able to set tzd's mode, so the relevant check in mode_store() is removed. Other comments: - acpi/thermal.c: tz->thermal_zone->mode will be updated only after we return from set_mode(), so use function parameter in thermal_set_mode() instead, no need to call acpi_thermal_check() in set_mode() - thermal/imx_thermal.c: regmap writes and mode assignment are done in thermal_zone_device_{en|dis}able() and set_mode() callback - thermal/intel/intel_quark_dts_thermal.c: soc_dts_{en|dis}able() are a part of set_mode() callback, so they don't need to modify tzd->mode, and don't need to fall back to the opposite mode if unsuccessful, as the return value will be propagated to thermal_zone_device_{en|dis}able() and ultimately tzd's member will not be changed in thermal_zone_device_set_mode(). - thermal/of-thermal.c: no need to set zone->mode to DISABLED in of_parse_thermal_zones() as a tzd is kzalloc'ed so mode is DISABLED anyway Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com> [for acerhdf] Acked-by: Peter Kaestle <peter@piie.net> Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org> Reviewed-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> Link: https://lore.kernel.org/r/20200629122925.21729-8-andrzej.p@collabora.com
2020-06-29 12:29:21 +00:00
result = thermal_zone_device_enable(tz->thermal_zone);
if (result)
goto remove_links;
dev_info(&tz->device->dev, "registered as thermal_zone%d\n",
thermal_zone_device_id(tz->thermal_zone));
return 0;
remove_links:
acpi_thermal_zone_sysfs_remove(tz);
unregister_tzd:
thermal_zone_device_unregister(tz->thermal_zone);
return result;
}
static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz)
{
thermal_zone_device_disable(tz->thermal_zone);
acpi_thermal_zone_sysfs_remove(tz);
thermal_zone_device_unregister(tz->thermal_zone);
tz->thermal_zone = NULL;
}
/* --------------------------------------------------------------------------
Driver Interface
-------------------------------------------------------------------------- */
static void acpi_thermal_notify(acpi_handle handle, u32 event, void *data)
{
struct acpi_device *device = data;
struct acpi_thermal *tz = acpi_driver_data(device);
if (!tz)
return;
switch (event) {
case ACPI_THERMAL_NOTIFY_TEMPERATURE:
ACPI: thermal: Do not call acpi_thermal_check() directly Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman <stephen.berman@gmx.net> Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Tested-by: Stephen Berman <stephen.berman@gmx.net> Cc: All applicable <stable@vger.kernel.org>
2021-01-14 18:34:22 +00:00
acpi_queue_thermal_check(tz);
break;
case ACPI_THERMAL_NOTIFY_THRESHOLDS:
case ACPI_THERMAL_NOTIFY_DEVICES:
acpi_thermal_trips_update(tz, event);
break;
default:
acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n",
event);
break;
}
}
/*
* On some platforms, the AML code has dependency about
* the evaluating order of _TMP and _CRT/_HOT/_PSV/_ACx.
* 1. On HP Pavilion G4-1016tx, _TMP must be invoked after
* /_CRT/_HOT/_PSV/_ACx, or else system will be power off.
* 2. On HP Compaq 6715b/6715s, the return value of _PSV is 0
* if _TMP has never been evaluated.
*
* As this dependency is totally transparent to OS, evaluate
* all of them once, in the order of _CRT/_HOT/_PSV/_ACx,
* _TMP, before they are actually used.
*/
static void acpi_thermal_aml_dependency_fix(struct acpi_thermal *tz)
{
acpi_handle handle = tz->device->handle;
unsigned long long value;
int i;
acpi_evaluate_integer(handle, "_CRT", NULL, &value);
acpi_evaluate_integer(handle, "_HOT", NULL, &value);
acpi_evaluate_integer(handle, "_PSV", NULL, &value);
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
char name[5] = { '_', 'A', 'C', ('0' + i), '\0' };
acpi_status status;
status = acpi_evaluate_integer(handle, name, NULL, &value);
if (status == AE_NOT_FOUND)
break;
}
acpi_evaluate_integer(handle, "_TMP", NULL, &value);
}
/*
* The exact offset between Kelvin and degree Celsius is 273.15. However ACPI
* handles temperature values with a single decimal place. As a consequence,
* some implementations use an offset of 273.1 and others use an offset of
* 273.2. Try to find out which one is being used, to present the most
* accurate and visually appealing number.
*
* The heuristic below should work for all ACPI thermal zones which have a
* critical trip point with a value being a multiple of 0.5 degree Celsius.
*/
static void acpi_thermal_guess_offset(struct acpi_thermal *tz, long crit_temp)
{
if (crit_temp != THERMAL_TEMP_INVALID && crit_temp % 5 == 1)
ACPI: thermal: switch to use <linux/units.h> helpers This switches the ACPI thermal zone driver to use celsius_to_deci_kelvin(), deci_kelvin_to_celsius(), and deci_kelvin_to_millicelsius_with_offset() in <linux/units.h> instead of helpers in <linux/thermal.h>. This is preparation for centralizing the kelvin to/from Celsius conversion helpers in <linux/units.h>. Link: http://lkml.kernel.org/r/1576386975-7941-3-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Sujith Thomas <sujith.thomas@intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Andy Shevchenko <andy@infradead.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@verdurent.com> Cc: Jean Delvare <jdelvare@suse.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Keith Busch <kbusch@kernel.org> Cc: Jens Axboe <axboe@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Cc: Hartmut Knaack <knaack.h@gmx.de> Cc: Johannes Berg <johannes.berg@intel.com> Cc: Jonathan Cameron <jic23@kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Kalle Valo <kvalo@codeaurora.org> Cc: Lars-Peter Clausen <lars@metafoo.de> Cc: Luca Coelho <luciano.coelho@intel.com> Cc: Peter Meerwald-Stadler <pmeerw@pmeerw.net> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-31 06:15:33 +00:00
tz->kelvin_offset = 273100;
else
ACPI: thermal: switch to use <linux/units.h> helpers This switches the ACPI thermal zone driver to use celsius_to_deci_kelvin(), deci_kelvin_to_celsius(), and deci_kelvin_to_millicelsius_with_offset() in <linux/units.h> instead of helpers in <linux/thermal.h>. This is preparation for centralizing the kelvin to/from Celsius conversion helpers in <linux/units.h>. Link: http://lkml.kernel.org/r/1576386975-7941-3-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Sujith Thomas <sujith.thomas@intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Andy Shevchenko <andy@infradead.org> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Amit Kucheria <amit.kucheria@verdurent.com> Cc: Jean Delvare <jdelvare@suse.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Keith Busch <kbusch@kernel.org> Cc: Jens Axboe <axboe@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Cc: Hartmut Knaack <knaack.h@gmx.de> Cc: Johannes Berg <johannes.berg@intel.com> Cc: Jonathan Cameron <jic23@kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Kalle Valo <kvalo@codeaurora.org> Cc: Lars-Peter Clausen <lars@metafoo.de> Cc: Luca Coelho <luciano.coelho@intel.com> Cc: Peter Meerwald-Stadler <pmeerw@pmeerw.net> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-31 06:15:33 +00:00
tz->kelvin_offset = 273200;
}
static void acpi_thermal_check_fn(struct work_struct *work)
{
struct acpi_thermal *tz = container_of(work, struct acpi_thermal,
thermal_check_work);
ACPI: thermal: Do not call acpi_thermal_check() directly Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman <stephen.berman@gmx.net> Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Tested-by: Stephen Berman <stephen.berman@gmx.net> Cc: All applicable <stable@vger.kernel.org>
2021-01-14 18:34:22 +00:00
/*
* In general, it is not sufficient to check the pending bit, because
* subsequent instances of this function may be queued after one of them
* has started running (e.g. if _TMP sleeps). Avoid bailing out if just
* one of them is running, though, because it may have done the actual
* check some time ago, so allow at least one of them to block on the
* mutex while another one is running the update.
*/
if (!refcount_dec_not_one(&tz->thermal_check_count))
return;
mutex_lock(&tz->thermal_check_lock);
thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED);
refcount_inc(&tz->thermal_check_count);
mutex_unlock(&tz->thermal_check_lock);
}
static void acpi_thermal_free_thermal_zone(struct acpi_thermal *tz)
{
int i;
acpi_handle_list_free(&tz->trips.passive.trip.devices);
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++)
acpi_handle_list_free(&tz->trips.active[i].trip.devices);
kfree(tz);
}
static int acpi_thermal_add(struct acpi_device *device)
{
struct acpi_thermal_trip *acpi_trip;
struct thermal_trip *trip;
struct acpi_thermal *tz;
unsigned int trip_count;
int crit_temp, hot_temp;
int passive_delay = 0;
int result;
int i;
if (!device)
return -EINVAL;
tz = kzalloc(sizeof(struct acpi_thermal), GFP_KERNEL);
if (!tz)
return -ENOMEM;
tz->device = device;
strcpy(tz->name, device->pnp.bus_id);
strcpy(acpi_device_name(device), ACPI_THERMAL_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_THERMAL_CLASS);
device->driver_data = tz;
acpi_thermal_aml_dependency_fix(tz);
/* Get trip points [_CRT, _PSV, etc.] (required). */
trip_count = acpi_thermal_get_trip_points(tz);
crit_temp = acpi_thermal_get_critical_trip(tz);
if (crit_temp != THERMAL_TEMP_INVALID)
trip_count++;
hot_temp = acpi_thermal_get_hot_trip(tz);
if (hot_temp != THERMAL_TEMP_INVALID)
trip_count++;
if (!trip_count) {
pr_warn(FW_BUG "No valid trip points!\n");
result = -ENODEV;
goto free_memory;
}
/* Get temperature [_TMP] (required). */
result = acpi_thermal_get_temperature(tz);
if (result)
goto free_memory;
/* Set the cooling mode [_SCP] to active cooling. */
acpi_execute_simple_method(tz->device->handle, "_SCP",
ACPI_THERMAL_MODE_ACTIVE);
/* Determine the default polling frequency [_TZP]. */
if (tzp)
tz->polling_frequency = tzp;
else
acpi_thermal_get_polling_frequency(tz);
acpi_thermal_guess_offset(tz, crit_temp);
trip = kcalloc(trip_count, sizeof(*trip), GFP_KERNEL);
if (!trip) {
result = -ENOMEM;
goto free_memory;
}
tz->trip_table = trip;
if (crit_temp != THERMAL_TEMP_INVALID) {
trip->type = THERMAL_TRIP_CRITICAL;
trip->temperature = acpi_thermal_temp(tz, crit_temp);
trip++;
}
if (hot_temp != THERMAL_TEMP_INVALID) {
trip->type = THERMAL_TRIP_HOT;
trip->temperature = acpi_thermal_temp(tz, hot_temp);
trip++;
}
acpi_trip = &tz->trips.passive.trip;
if (acpi_thermal_trip_valid(acpi_trip)) {
passive_delay = tz->trips.passive.delay;
trip->type = THERMAL_TRIP_PASSIVE;
trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
trip->priv = acpi_trip;
trip++;
}
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
acpi_trip = &tz->trips.active[i].trip;
if (!acpi_thermal_trip_valid(acpi_trip))
break;
trip->type = THERMAL_TRIP_ACTIVE;
trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
trip->priv = acpi_trip;
trip++;
}
result = acpi_thermal_register_thermal_zone(tz, trip_count, passive_delay);
if (result)
goto free_trips;
ACPI: thermal: Do not call acpi_thermal_check() directly Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman <stephen.berman@gmx.net> Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Tested-by: Stephen Berman <stephen.berman@gmx.net> Cc: All applicable <stable@vger.kernel.org>
2021-01-14 18:34:22 +00:00
refcount_set(&tz->thermal_check_count, 3);
mutex_init(&tz->thermal_check_lock);
INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
pr_info("%s [%s] (%ld C)\n", acpi_device_name(device),
acpi_device_bid(device), deci_kelvin_to_celsius(tz->temp_dk));
result = acpi_dev_install_notify_handler(device, ACPI_DEVICE_NOTIFY,
acpi_thermal_notify, device);
if (result)
goto flush_wq;
return 0;
flush_wq:
flush_workqueue(acpi_thermal_pm_queue);
acpi_thermal_unregister_thermal_zone(tz);
free_trips:
kfree(tz->trip_table);
free_memory:
acpi_thermal_free_thermal_zone(tz);
return result;
}
static void acpi_thermal_remove(struct acpi_device *device)
{
struct acpi_thermal *tz;
if (!device || !acpi_driver_data(device))
return;
tz = acpi_driver_data(device);
acpi_dev_remove_notify_handler(device, ACPI_DEVICE_NOTIFY,
acpi_thermal_notify);
flush_workqueue(acpi_thermal_pm_queue);
acpi_thermal_unregister_thermal_zone(tz);
kfree(tz->trip_table);
acpi_thermal_free_thermal_zone(tz);
}
#ifdef CONFIG_PM_SLEEP
static int acpi_thermal_suspend(struct device *dev)
{
/* Make sure the previously queued thermal check work has been done */
flush_workqueue(acpi_thermal_pm_queue);
return 0;
}
static int acpi_thermal_resume(struct device *dev)
{
struct acpi_thermal *tz;
int i, j, power_state;
if (!dev)
return -EINVAL;
tz = acpi_driver_data(to_acpi_device(dev));
if (!tz)
return -EINVAL;
for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) {
struct acpi_thermal_trip *acpi_trip = &tz->trips.active[i].trip;
if (!acpi_thermal_trip_valid(acpi_trip))
break;
for (j = 0; j < acpi_trip->devices.count; j++) {
acpi_bus_update_power(acpi_trip->devices.handles[j],
&power_state);
}
}
ACPI: thermal: Do not call acpi_thermal_check() directly Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman <stephen.berman@gmx.net> Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Tested-by: Stephen Berman <stephen.berman@gmx.net> Cc: All applicable <stable@vger.kernel.org>
2021-01-14 18:34:22 +00:00
acpi_queue_thermal_check(tz);
return AE_OK;
}
#else
#define acpi_thermal_suspend NULL
#define acpi_thermal_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_thermal_pm, acpi_thermal_suspend, acpi_thermal_resume);
static const struct acpi_device_id thermal_device_ids[] = {
{ACPI_THERMAL_HID, 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, thermal_device_ids);
static struct acpi_driver acpi_thermal_driver = {
.name = "thermal",
.class = ACPI_THERMAL_CLASS,
.ids = thermal_device_ids,
.ops = {
.add = acpi_thermal_add,
.remove = acpi_thermal_remove,
},
.drv.pm = &acpi_thermal_pm,
};
static int thermal_act(const struct dmi_system_id *d)
{
if (act == 0) {
pr_notice("%s detected: disabling all active thermal trip points\n",
d->ident);
act = -1;
}
return 0;
}
static int thermal_nocrt(const struct dmi_system_id *d)
{
pr_notice("%s detected: disabling all critical thermal trip point actions.\n",
d->ident);
crt = -1;
return 0;
}
static int thermal_tzp(const struct dmi_system_id *d)
{
if (tzp == 0) {
pr_notice("%s detected: enabling thermal zone polling\n",
d->ident);
tzp = 300; /* 300 dS = 30 Seconds */
}
return 0;
}
static int thermal_psv(const struct dmi_system_id *d)
{
if (psv == 0) {
pr_notice("%s detected: disabling all passive thermal trip points\n",
d->ident);
psv = -1;
}
return 0;
}
static const struct dmi_system_id thermal_dmi_table[] __initconst = {
/*
* Award BIOS on this AOpen makes thermal control almost worthless.
* http://bugzilla.kernel.org/show_bug.cgi?id=8842
*/
{
.callback = thermal_act,
.ident = "AOpen i915GMm-HFS",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"),
DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"),
},
},
{
.callback = thermal_psv,
.ident = "AOpen i915GMm-HFS",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"),
DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"),
},
},
{
.callback = thermal_tzp,
.ident = "AOpen i915GMm-HFS",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"),
DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"),
},
},
{
.callback = thermal_nocrt,
.ident = "Gigabyte GA-7ZX",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."),
DMI_MATCH(DMI_BOARD_NAME, "7ZX"),
},
},
{}
};
static int __init acpi_thermal_init(void)
{
int result;
dmi_check_system(thermal_dmi_table);
if (off) {
pr_notice("thermal control disabled\n");
return -ENODEV;
}
acpi_thermal_pm_queue = alloc_workqueue("acpi_thermal_pm",
WQ_HIGHPRI | WQ_MEM_RECLAIM, 0);
if (!acpi_thermal_pm_queue)
return -ENODEV;
result = acpi_bus_register_driver(&acpi_thermal_driver);
if (result < 0) {
destroy_workqueue(acpi_thermal_pm_queue);
return -ENODEV;
}
return 0;
}
static void __exit acpi_thermal_exit(void)
{
acpi_bus_unregister_driver(&acpi_thermal_driver);
destroy_workqueue(acpi_thermal_pm_queue);
}
module_init(acpi_thermal_init);
module_exit(acpi_thermal_exit);
MODULE_IMPORT_NS(ACPI_THERMAL);
MODULE_AUTHOR("Paul Diefenbaugh");
MODULE_DESCRIPTION("ACPI Thermal Zone Driver");
MODULE_LICENSE("GPL");