Gh0st
/
linux
mirror of https://github.com/torvalds/linux.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

thermal: core: Fix thermal zone suspend-resume synchronization 

There are 3 synchronization issues with thermal zone suspend-resume
during system-wide transitions:

 1. The resume code runs in a PM notifier which is invoked after user
    space has been thawed, so it can run concurrently with user space
    which can trigger a thermal zone device removal.  If that happens,
    the thermal zone resume code may use a stale pointer to the next
    list element and crash, because it does not hold thermal_list_lock
    while walking thermal_tz_list.

 2. The thermal zone resume code calls thermal_zone_device_init()
    outside the zone lock, so user space or an update triggered by
    the platform firmware may see an inconsistent state of a
    thermal zone leading to unexpected behavior.

 3. Clearing the in_suspend global variable in thermal_pm_notify()
    allows __thermal_zone_device_update() to continue for all thermal
    zones and it may as well run before the thermal_tz_list walk (or
    at any point during the list walk for that matter) and attempt to
    operate on a thermal zone that has not been resumed yet.  It may
    also race destructively with thermal_zone_device_init().

To address these issues, add thermal_list_lock locking to
thermal_pm_notify(), especially arount the thermal_tz_list,
make it call thermal_zone_device_init() back-to-back with
__thermal_zone_device_update() under the zone lock and replace
in_suspend with per-zone bool "suspend" indicators set and unset
under the given zone's lock.

Link: https://lore.kernel.org/linux-pm/20231218162348.69101-1-bo.ye@mediatek.com/
Reported-by: Bo Ye <bo.ye@mediatek.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This commit is contained in:
Rafael J. Wysocki 2023-12-18 20:25:02 +01:00
parent 5f70413a85
commit 4e814173a8
2 changed files with 25 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
drivers/thermal/thermal_core.c
View File

@ -37,8 +37,6 @@ static LIST_HEAD(thermal_governor_list);
static DEFINE_MUTEX(thermal_list_lock);
static DEFINE_MUTEX(thermal_governor_lock);
static atomic_t in_suspend;
static struct thermal_governor *def_governor;
/*
@ -431,7 +429,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
{
struct thermal_trip *trip;
if (atomic_read(&in_suspend))
if (tz->suspended)
return;
if (!thermal_zone_device_is_enabled(tz))
@ -1542,17 +1540,35 @@ static int thermal_pm_notify(struct notifier_block *nb,
case PM_HIBERNATION_PREPARE:
case PM_RESTORE_PREPARE:
case PM_SUSPEND_PREPARE:
atomic_set(&in_suspend, 1);
mutex_lock(&thermal_list_lock);
list_for_each_entry(tz, &thermal_tz_list, node) {
mutex_lock(&tz->lock);
tz->suspended = true;
mutex_unlock(&tz->lock);
}
mutex_unlock(&thermal_list_lock);
break;
case PM_POST_HIBERNATION:
case PM_POST_RESTORE:
case PM_POST_SUSPEND:
atomic_set(&in_suspend, 0);
mutex_lock(&thermal_list_lock);
list_for_each_entry(tz, &thermal_tz_list, node) {
mutex_lock(&tz->lock);
tz->suspended = false;
thermal_zone_device_init(tz);
thermal_zone_device_update(tz,
THERMAL_EVENT_UNSPECIFIED);
__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
mutex_unlock(&tz->lock);
}
mutex_unlock(&thermal_list_lock);
break;
default:
break;

2
include/linux/thermal.h
View File

@ -152,6 +152,7 @@ struct thermal_cooling_device {
* @node: node in thermal_tz_list (in thermal_core.c)
* @poll_queue: delayed work for polling
* @notify_event: Last notification event
* @suspended: thermal zone suspend indicator
*/
struct thermal_zone_device {
int id;
@ -185,6 +186,7 @@ struct thermal_zone_device {
struct list_head node;
struct delayed_work poll_queue;
enum thermal_notify_event notify_event;
bool suspended;
};
/**