thermal: core: Resume thermal zones asynchronously

The resume of thermal zones in thermal_pm_notify() is carried out
sequentially, which may be a problem if __thermal_zone_device_update()
takes a significant time to run for some thermal zones, because some
other thermal zones may need to wait for them to resume then and if
any other PM notifiers are going to be invoked after the thermal one,
they will need to wait for it either.

To address this, make thermal_pm_notify() switch the poll_queue delayed
work over to a one-shot thermal_zone_device_resume() work function that
will restore the original one during the thermal zone resume and queue
up poll_queue without a delay for each thermal zone.

Link: https://lore.kernel.org/linux-pm/20231120234015.3273143-1-radusolea@google.com/
Reported-by: Radu Solea <radusolea@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 94e5e353b40e9ae39098a41562d29c5fa16cb2ff..3ffccd73b19e3c91d84a8d226f2cc279597278eb 100644 (file)
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1532,6 +1532,22 @@ exit:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);
 
+static void thermal_zone_device_resume(struct work_struct *work)
+{
+       struct thermal_zone_device *tz;
+
+       tz = container_of(work, struct thermal_zone_device, poll_queue.work);
+
+       mutex_lock(&tz->lock);
+
+       tz->suspended = false;
+
+       thermal_zone_device_init(tz);
+       __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+
+       mutex_unlock(&tz->lock);
+}
+
 static int thermal_pm_notify(struct notifier_block *nb,
                             unsigned long mode, void *_unused)
 {
@@ -1563,10 +1579,16 @@ static int thermal_pm_notify(struct notifier_block *nb,
 
                        cancel_delayed_work(&tz->poll_queue);
 
-                       tz->suspended = false;
-
-                       thermal_zone_device_init(tz);
-                       __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+                       /*
+                        * Replace the work function with the resume one, which
+                        * will restore the original work function and schedule
+                        * the polling work if needed.
+                        */
+                       INIT_DELAYED_WORK(&tz->poll_queue,
+                                         thermal_zone_device_resume);
+                       /* Queue up the work without a delay. */
+                       mod_delayed_work(system_freezable_power_efficient_wq,
+                                        &tz->poll_queue, 0);
 
                        mutex_unlock(&tz->lock);
                }