Merge tag 'thermal-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull thermal control updates from Rafael Wysocki:
 "These add support for the D1/T113s THS controller to the sun8i driver
  and a DT-based mechanism for platforms to indicate a preference to
  reboot (instead of shutting down) on crossing a critical trip point,
  fix issues, make other improvements (in the IPA governor, the Intel
  HFI driver, the exynos driver and the thermal netlink interface among
  other places) and clean up code.

  One long-standing issue addressed here is that trip point crossing
  notifications sent to user space might be unreliable due to the
  incorrect handling of trip point hysteresis in the thermal core:
  multiple notifications might be sent for the same event or there might
  be events without any notification at all.

  Specifics:

   - Add dynamic thresholds for trip point crossing detection to prevent
     trip point crossing notifications from being sent at incorrect
     times or not at all in some cases (Rafael J. Wysocki)

   - Fix synchronization issues related to the resume of thermal zones
     during a system-wide resume and allow thermal zones to be resumed
     concurrently (Rafael J. Wysocki)

   - Modify the thermal zone unregistration to wait for the given zone
     to go away completely before returning to the caller and rework the
     sysfs interface for trip points on top of that (Rafael J. Wysocki)

   - Fix a possible NULL pointer dereference in thermal zone
     registration error path (Rafael J. Wysocki)

   - Clean up the IPA thermal governor and modify it (with the help of a
     new governor callback) to avoid allocating and freeing memory every
     time its throttling callback is invoked (Lukasz Luba)

   - Make the IPA thermal governor handle thermal instance weight
     changes via sysfs correctly (Lukasz Luba)

   - Update the thermal netlink code to avoid sending messages if there
     are no recipients (Stanislaw Gruszka)

   - Convert Mediatek Thermal to the json-schema (Rafał Miłecki)

   - Fix thermal DT bindings issue on Loongson (Binbin Zhou)

   - Fix returning NULL instead of -ENODEV during thermal probe on
     Loogsoon (Binbin Zhou)

   - Add thermal DT binding for tsens on the SM8650 platform (Neil
     Armstrong)

   - Add reboot on the critical trip point crossing option feature
     (Fabio Estevam)

   - Use DEFINE_SIMPLE_DEV_PM_OPS do define PM functions for thermal
     suspend/resume on AmLogic (Uwe Kleine-König)

   - Add D1/T113s THS controller support to the Sun8i thermal control
     driver (Maxim Kiselev)

   - Fix example in the thermal DT binding for QCom SPMI (Johan Hovold)

   - Fix compilation warning in the tmon utility (Florian Eckert)

   - Add support for interrupt-based thermal configuration on Exynos
     along with a set of related cleanups (Mateusz Majewski)

   - Make the Intel HFI thermal driver enable an HFI instance (eg.
     processor package) from its first online CPU and disable it when
     the last CPU in it goes offline (Ricardo Neri)

   - Fix a kernel-doc warning and a spello in the cpuidle_cooling
     thermal driver (Randy Dunlap)

   - Move the .get_temp() thermal zone callback presence check to the
     thermal zone registration code (Daniel Lezcano)

   - Use the for_each_trip() macro for trip points table walks in a few
     places in the thermal core (Rafael J. Wysocki)

   - Make all trip point updates (via sysfs as well as from the platform
     firmware) trigger trip change notifications (Rafael J. Wysocki)

   - Drop redundant code from the thermal core and make one function in
     it take a const pointer argument (Rafael J. Wysocki)"

* tag 'thermal-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (64 commits)
  thermal: trip: Constify thermal zone argument of thermal_zone_trip_id()
  thermal: intel: hfi: Disable an HFI instance when all its CPUs go offline
  thermal: intel: hfi: Enable an HFI instance from its first online CPU
  thermal: intel: hfi: Refactor enabling code into helper functions
  thermal/drivers/exynos: Use set_trips ops
  thermal/drivers/exynos: Use BIT wherever possible
  thermal/drivers/exynos: Split initialization of TMU and the thermal zone
  thermal/drivers/exynos: Stop using the threshold mechanism on Exynos 4210
  thermal/drivers/exynos: Simplify regulator (de)initialization
  thermal/drivers/exynos: Handle devm_regulator_get_optional return value correctly
  thermal/drivers/exynos: Wwitch from workqueue-driven interrupt handling to threaded interrupts
  thermal/drivers/exynos: Drop id field
  thermal/drivers/exynos: Remove an unnecessary field description
  tools/thermal/tmon: Fix compilation warning for wrong format
  dt-bindings: thermal: qcom-spmi-adc-tm5/hc: Clean up examples
  dt-bindings: thermal: qcom-spmi-adc-tm5/hc: Fix example node names
  thermal/drivers/sun8i: Add D1/T113s THS controller support
  dt-bindings: thermal: sun8i: Add binding for D1/T113s THS controller
  thermal: amlogic: Use DEFINE_SIMPLE_DEV_PM_OPS for PM functions
  thermal: amlogic: Make amlogic_thermal_disable() return void
  ...

1 files changed, 144 insertions, 49 deletions

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 9c17d35ccbbd..fa88d8707241 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -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;
 
 /*
@@ -203,9 +201,6 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *tz,
 	mutex_lock(&thermal_governor_lock);
 	mutex_lock(&tz->lock);
 
-	if (!device_is_registered(&tz->device))
-		goto exit;
-
 	gov = __find_governor(strim(policy));
 	if (!gov)
 		goto exit;
@@ -314,21 +309,43 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz,
 		       def_governor->throttle(tz, trip);
 }
 
-void thermal_zone_device_critical(struct thermal_zone_device *tz)
+void thermal_governor_update_tz(struct thermal_zone_device *tz,
+				enum thermal_notify_event reason)
+{
+	if (!tz->governor || !tz->governor->update_tz)
+		return;
+
+	tz->governor->update_tz(tz, reason);
+}
+
+static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdown)
 {
 	/*
 	 * poweroff_delay_ms must be a carefully profiled positive value.
 	 * Its a must for forced_emergency_poweroff_work to be scheduled.
 	 */
 	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
+	const char *msg = "Temperature too high";
 
-	dev_emerg(&tz->device, "%s: critical temperature reached, "
-		  "shutting down\n", tz->type);
+	dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type);
+
+	if (shutdown)
+		hw_protection_shutdown(msg, poweroff_delay_ms);
+	else
+		hw_protection_reboot(msg, poweroff_delay_ms);
+}
 
-	hw_protection_shutdown("Temperature too high", poweroff_delay_ms);
+void thermal_zone_device_critical(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, true);
 }
 EXPORT_SYMBOL(thermal_zone_device_critical);
 
+void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, false);
+}
+
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip)
 {
@@ -345,22 +362,51 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 }
 
 static void handle_thermal_trip(struct thermal_zone_device *tz,
-				const struct thermal_trip *trip)
+				struct thermal_trip *trip)
 {
 	if (trip->temperature == THERMAL_TEMP_INVALID)
 		return;
 
-	if (tz->last_temperature != THERMAL_TEMP_INVALID) {
-		if (tz->last_temperature < trip->temperature &&
-		    tz->temperature >= trip->temperature)
+	if (tz->last_temperature == THERMAL_TEMP_INVALID) {
+		/* Initialization. */
+		trip->threshold = trip->temperature;
+		if (tz->temperature >= trip->threshold)
+			trip->threshold -= trip->hysteresis;
+	} else if (tz->last_temperature < trip->threshold) {
+		/*
+		 * The trip threshold is equal to the trip temperature, unless
+		 * the latter has changed in the meantime.  In either case,
+		 * the trip is crossed if the current zone temperature is at
+		 * least equal to its temperature, but otherwise ensure that
+		 * the threshold and the trip temperature will be equal.
+		 */
+		if (tz->temperature >= trip->temperature) {
 			thermal_notify_tz_trip_up(tz->id,
 						  thermal_zone_trip_id(tz, trip),
 						  tz->temperature);
-		if (tz->last_temperature >= trip->temperature &&
-		    tz->temperature < trip->temperature - trip->hysteresis)
+			trip->threshold = trip->temperature - trip->hysteresis;
+		} else {
+			trip->threshold = trip->temperature;
+		}
+	} else {
+		/*
+		 * The previous zone temperature was above or equal to the trip
+		 * threshold, which would be equal to the "low temperature" of
+		 * the trip (its temperature minus its hysteresis), unless the
+		 * trip temperature or hysteresis had changed.  In either case,
+		 * the trip is crossed if the current zone temperature is below
+		 * the low temperature of the trip, but otherwise ensure that
+		 * the trip threshold will be equal to the low temperature of
+		 * the trip.
+		 */
+		if (tz->temperature < trip->temperature - trip->hysteresis) {
 			thermal_notify_tz_trip_down(tz->id,
 						    thermal_zone_trip_id(tz, trip),
 						    tz->temperature);
+			trip->threshold = trip->temperature;
+		} else {
+			trip->threshold = trip->temperature - trip->hysteresis;
+		}
 	}
 
 	if (trip->type == THERMAL_TRIP_CRITICAL || trip->type == THERMAL_TRIP_HOT)
@@ -390,9 +436,20 @@ static void update_temperature(struct thermal_zone_device *tz)
 	thermal_genl_sampling_temp(tz->id, temp);
 }
 
+static void thermal_zone_device_check(struct work_struct *work)
+{
+	struct thermal_zone_device *tz = container_of(work, struct
+						      thermal_zone_device,
+						      poll_queue.work);
+	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+}
+
 static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *pos;
+
+	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
+
 	tz->temperature = THERMAL_TEMP_INVALID;
 	tz->prev_low_trip = -INT_MAX;
 	tz->prev_high_trip = INT_MAX;
@@ -403,14 +460,9 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event)
 {
-	const struct thermal_trip *trip;
-
-	if (atomic_read(&in_suspend))
-		return;
+	struct thermal_trip *trip;
 
-	if (WARN_ONCE(!tz->ops->get_temp,
-		      "'%s' must not be called without 'get_temp' ops set\n",
-		      __func__))
+	if (tz->suspended)
 		return;
 
 	if (!thermal_zone_device_is_enabled(tz))
@@ -442,12 +494,6 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 		return ret;
 	}
 
-	if (!device_is_registered(&tz->device)) {
-		mutex_unlock(&tz->lock);
-
-		return -ENODEV;
-	}
-
 	if (tz->ops->change_mode)
 		ret = tz->ops->change_mode(tz, mode);
 
@@ -485,24 +531,21 @@ int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
 	return tz->mode == THERMAL_DEVICE_ENABLED;
 }
 
+static bool thermal_zone_is_present(struct thermal_zone_device *tz)
+{
+	return !list_empty(&tz->node);
+}
+
 void thermal_zone_device_update(struct thermal_zone_device *tz,
 				enum thermal_notify_event event)
 {
 	mutex_lock(&tz->lock);
-	if (device_is_registered(&tz->device))
+	if (thermal_zone_is_present(tz))
 		__thermal_zone_device_update(tz, event);
 	mutex_unlock(&tz->lock);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_update);
 
-static void thermal_zone_device_check(struct work_struct *work)
-{
-	struct thermal_zone_device *tz = container_of(work, struct
-						      thermal_zone_device,
-						      poll_queue.work);
-	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
-}
-
 int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *),
 			      void *data)
 {
@@ -694,6 +737,8 @@ int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz,
 		list_add_tail(&dev->tz_node, &tz->thermal_instances);
 		list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
 		atomic_set(&tz->need_update, 1);
+
+		thermal_governor_update_tz(tz, THERMAL_TZ_BIND_CDEV);
 	}
 	mutex_unlock(&cdev->lock);
 	mutex_unlock(&tz->lock);
@@ -752,6 +797,9 @@ int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz,
 		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
 			list_del(&pos->tz_node);
 			list_del(&pos->cdev_node);
+
+			thermal_governor_update_tz(tz, THERMAL_TZ_UNBIND_CDEV);
+
 			mutex_unlock(&cdev->lock);
 			mutex_unlock(&tz->lock);
 			goto unbind;
@@ -793,7 +841,7 @@ static void thermal_release(struct device *dev)
 		tz = to_thermal_zone(dev);
 		thermal_zone_destroy_device_groups(tz);
 		mutex_destroy(&tz->lock);
-		kfree(tz);
+		complete(&tz->removal);
 	} else if (!strncmp(dev_name(dev), "cooling_device",
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
@@ -1260,7 +1308,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (!ops) {
+	if (!ops || !ops->get_temp) {
 		pr_err("Thermal zone device ops not defined\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1284,8 +1332,10 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	}
 
 	INIT_LIST_HEAD(&tz->thermal_instances);
+	INIT_LIST_HEAD(&tz->node);
 	ida_init(&tz->ida);
 	mutex_init(&tz->lock);
+	init_completion(&tz->removal);
 	id = ida_alloc(&thermal_tz_ida, GFP_KERNEL);
 	if (id < 0) {
 		result = id;
@@ -1348,14 +1398,14 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	}
 
 	mutex_lock(&thermal_list_lock);
+	mutex_lock(&tz->lock);
 	list_add_tail(&tz->node, &thermal_tz_list);
+	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_list_lock);
 
 	/* Bind cooling devices for this zone */
 	bind_tz(tz);
 
-	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
-
 	thermal_zone_device_init(tz);
 	/* Update the new thermal zone and mark it as already updated. */
 	if (atomic_cmpxchg(&tz->need_update, 1, 0))
@@ -1369,7 +1419,6 @@ unregister:
 	device_del(&tz->device);
 release_device:
 	put_device(&tz->device);
-	tz = NULL;
 remove_id:
 	ida_free(&thermal_tz_ida, id);
 free_tzp:
@@ -1439,7 +1488,10 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 		mutex_unlock(&thermal_list_lock);
 		return;
 	}
+
+	mutex_lock(&tz->lock);
 	list_del(&tz->node);
+	mutex_unlock(&tz->lock);
 
 	/* Unbind all cdevs associated with 'this' thermal zone */
 	list_for_each_entry(cdev, &thermal_cdev_list, node)
@@ -1456,15 +1508,16 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	ida_free(&thermal_tz_ida, tz->id);
 	ida_destroy(&tz->ida);
 
-	mutex_lock(&tz->lock);
 	device_del(&tz->device);
-	mutex_unlock(&tz->lock);
 
 	kfree(tz->tzp);
 
 	put_device(&tz->device);
 
 	thermal_notify_tz_delete(tz_id);
+
+	wait_for_completion(&tz->removal);
+	kfree(tz);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
 
@@ -1506,6 +1559,22 @@ 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)
 {
@@ -1515,17 +1584,43 @@ 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) {
-			thermal_zone_device_init(tz);
-			thermal_zone_device_update(tz,
-						   THERMAL_EVENT_UNSPECIFIED);
+			mutex_lock(&tz->lock);
+
+			cancel_delayed_work(&tz->poll_queue);
+
+			/*
+			 * 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);
 		}
+
+		mutex_unlock(&thermal_list_lock);
 		break;
 	default:
 		break;