Merge branch 'thermal-core'

This includes a major rework of thermal governors and part of the
thermal core interacting with them as well as some fixes and cleanups
of the thermal debug code:

 - Redesign the thermal governor interface to allow the governors to
   work in a more straightforward way.

 - Make thermal governors take the current trip point thresholds into
   account in their computations which allows trip hysteresis to be
   observed more accurately.

 - Clean up thermal governors.

 - Make the thermal core manage passive polling for thermal zones and
   remove passive polling management from thermal governors.

 - Improve the handling of cooling device states and thermal mitigation
   episodes in progress in the thermal debug code.

 - Avoid excessive updates of trip point statistics and clean up the
   printing of thermal mitigation episode information.

* thermal-core: (27 commits)
  thermal: core: Move passive polling management to the core
  thermal: core: Do not call handle_thermal_trip() if zone temperature is invalid
  thermal: trip: Add missing empty code line
  thermal/debugfs: Avoid printing zero duration for mitigation events in progress
  thermal/debugfs: Pass cooling device state to thermal_debug_cdev_add()
  thermal/debugfs: Create records for cdev states as they get used
  thermal: core: Introduce thermal_governor_trip_crossed()
  thermal/debugfs: Make tze_seq_show() skip invalid trips and trips with no stats
  thermal/debugfs: Rename thermal_debug_update_temp() to thermal_debug_update_trip_stats()
  thermal/debugfs: Clean up thermal_debug_update_temp()
  thermal/debugfs: Avoid excessive updates of trip point statistics
  thermal: core: Relocate critical and hot trip handling
  thermal: core: Drop the .throttle() governor callback
  thermal: gov_user_space: Use .trip_crossed() instead of .throttle()
  thermal: gov_fair_share: Eliminate unnecessary integer divisions
  thermal: gov_fair_share: Use trip thresholds instead of trip temperatures
  thermal: gov_fair_share: Use .manage() callback instead of .throttle()
  thermal: gov_step_wise: Clean up thermal_zone_trip_update()
  thermal: gov_step_wise: Use trip thresholds instead of trip temperatures
  thermal: gov_step_wise: Use .manage() callback instead of .throttle()
  ...

drivers/thermal/gov_bang_bang.c

@@ -13,60 +13,11 @@
 
 #include "thermal_core.h"
 
-static int thermal_zone_trip_update(struct thermal_zone_device *tz,
-				    const struct thermal_trip *trip)
-{
-	int trip_index = thermal_zone_trip_id(tz, trip);
-	struct thermal_instance *instance;
-
-	if (!trip->hysteresis)
-		dev_info_once(&tz->device,
-			      "Zero hysteresis value for thermal zone %s\n", tz->type);
-
-	dev_dbg(&tz->device, "Trip%d[temp=%d]:temp=%d:hyst=%d\n",
-				trip_index, trip->temperature, tz->temperature,
-				trip->hysteresis);
-
-	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		if (instance->trip != trip)
-			continue;
-
-		/* in case fan is in initial state, switch the fan off */
-		if (instance->target == THERMAL_NO_TARGET)
-			instance->target = 0;
-
-		/* in case fan is neither on nor off set the fan to active */
-		if (instance->target != 0 && instance->target != 1) {
-			pr_warn("Thermal instance %s controlled by bang-bang has unexpected state: %ld\n",
-					instance->name, instance->target);
-			instance->target = 1;
-		}
-
-		/*
-		 * enable fan when temperature exceeds trip_temp and disable
-		 * the fan in case it falls below trip_temp minus hysteresis
-		 */
-		if (instance->target == 0 && tz->temperature >= trip->temperature)
-			instance->target = 1;
-		else if (instance->target == 1 &&
-			 tz->temperature < trip->temperature - trip->hysteresis)
-			instance->target = 0;
-
-		dev_dbg(&instance->cdev->device, "target=%d\n",
-					(int)instance->target);
-
-		mutex_lock(&instance->cdev->lock);
-		instance->cdev->updated = false; /* cdev needs update */
-		mutex_unlock(&instance->cdev->lock);
-	}
-
-	return 0;
-}
-
 /**
  * bang_bang_control - controls devices associated with the given zone
  * @tz: thermal_zone_device
  * @trip: the trip point
+ * @crossed_up: whether or not the trip has been crossed on the way up
  *
  * Regulation Logic: a two point regulation, deliver cooling state depending
  * on the previous state shown in this diagram:
@@ -90,26 +41,54 @@ static int thermal_zone_trip_update(struct thermal_zone_device *tz,
  *     (trip_temp - hyst) so that the fan gets turned off again.
  *
  */
-static int bang_bang_control(struct thermal_zone_device *tz,
-			     const struct thermal_trip *trip)
+static void bang_bang_control(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip,
+			      bool crossed_up)
 {
 	struct thermal_instance *instance;
-	int ret;
 
 	lockdep_assert_held(&tz->lock);
 
-	ret = thermal_zone_trip_update(tz, trip);
-	if (ret)
-		return ret;
+	dev_dbg(&tz->device, "Trip%d[temp=%d]:temp=%d:hyst=%d\n",
+		thermal_zone_trip_id(tz, trip), trip->temperature,
+		tz->temperature, trip->hysteresis);
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != trip)
+			continue;
+
+		if (instance->target == THERMAL_NO_TARGET)
+			instance->target = 0;
+
+		if (instance->target != 0 && instance->target != 1) {
+			pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n",
+				 instance->target, instance->name);
+
+			instance->target = 1;
+		}
+
+		/*
+		 * Enable the fan when the trip is crossed on the way up and
+		 * disable it when the trip is crossed on the way down.
+		 */
+		if (instance->target == 0 && crossed_up)
+			instance->target = 1;
+		else if (instance->target == 1 && !crossed_up)
+			instance->target = 0;
+
+		dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target);
+
+		mutex_lock(&instance->cdev->lock);
+		instance->cdev->updated = false; /* cdev needs update */
+		mutex_unlock(&instance->cdev->lock);
+	}
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
-
-	return 0;
 }
 
 static struct thermal_governor thermal_gov_bang_bang = {
 	.name		= "bang_bang",
-	.throttle	= bang_bang_control,
+	.trip_crossed	= bang_bang_control,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang);

drivers/thermal/gov_fair_share.c

@@ -17,100 +17,111 @@
 
 static int get_trip_level(struct thermal_zone_device *tz)
 {
-	const struct thermal_trip *level_trip = NULL;
+	const struct thermal_trip_desc *level_td = NULL;
 	const struct thermal_trip_desc *td;
 	int trip_level = -1;
 
 	for_each_trip_desc(tz, td) {
-		const struct thermal_trip *trip = &td->trip;
-
-		if (trip->temperature >= tz->temperature)
+		if (td->threshold > tz->temperature)
 			continue;
 
 		trip_level++;
 
-		if (!level_trip || trip->temperature > level_trip->temperature)
-			level_trip = trip;
+		if (!level_td || td->threshold > level_td->threshold)
+			level_td = td;
 	}
 
 	/*  Bail out if the temperature is not greater than any trips. */
 	if (trip_level < 0)
 		return 0;
 
-	trace_thermal_zone_trip(tz, thermal_zone_trip_id(tz, level_trip),
-				level_trip->type);
+	trace_thermal_zone_trip(tz, thermal_zone_trip_id(tz, &level_td->trip),
+				level_td->trip.type);
 
 	return trip_level;
 }
 
-static long get_target_state(struct thermal_zone_device *tz,
-		struct thermal_cooling_device *cdev, int percentage, int level)
-{
-	return (long)(percentage * level * cdev->max_state) / (100 * tz->num_trips);
-}
-
 /**
  * fair_share_throttle - throttles devices associated with the given zone
  * @tz: thermal_zone_device
  * @trip: trip point
+ * @trip_level: number of trips crossed by the zone temperature
  *
  * Throttling Logic: This uses three parameters to calculate the new
  * throttle state of the cooling devices associated with the given zone.
  *
  * Parameters used for Throttling:
  * P1. max_state: Maximum throttle state exposed by the cooling device.
- * P2. percentage[i]/100:
+ * P2. weight[i]/total_weight:
  *	How 'effective' the 'i'th device is, in cooling the given zone.
- * P3. cur_trip_level/max_no_of_trips:
+ * P3. trip_level/max_no_of_trips:
  *	This describes the extent to which the devices should be throttled.
  *	We do not want to throttle too much when we trip a lower temperature,
  *	whereas the throttling is at full swing if we trip critical levels.
- *	(Heavily assumes the trip points are in ascending order)
  * new_state of cooling device = P3 * P2 * P1
  */
-static int fair_share_throttle(struct thermal_zone_device *tz,
-			       const struct thermal_trip *trip)
+static void fair_share_throttle(struct thermal_zone_device *tz,
+				const struct thermal_trip *trip,
+				int trip_level)
 {
 	struct thermal_instance *instance;
 	int total_weight = 0;
-	int total_instance = 0;
-	int cur_trip_level = get_trip_level(tz);
-
-	lockdep_assert_held(&tz->lock);
+	int nr_instances = 0;
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
 			continue;
 
 		total_weight += instance->weight;
-		total_instance++;
+		nr_instances++;
 	}
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
-		int percentage;
 		struct thermal_cooling_device *cdev = instance->cdev;
+		u64 dividend;
+		u32 divisor;
 
 		if (instance->trip != trip)
 			continue;
 
-		if (!total_weight)
-			percentage = 100 / total_instance;
-		else
-			percentage = (instance->weight * 100) / total_weight;
-
-		instance->target = get_target_state(tz, cdev, percentage,
-						    cur_trip_level);
+		dividend = trip_level;
+		dividend *= cdev->max_state;
+		divisor = tz->num_trips;
+		if (total_weight) {
+			dividend *= instance->weight;
+			divisor *= total_weight;
+		} else {
+			divisor *= nr_instances;
+		}
+		instance->target = div_u64(dividend, divisor);
 
 		mutex_lock(&cdev->lock);
 		__thermal_cdev_update(cdev);
 		mutex_unlock(&cdev->lock);
 	}
+}
+
+static void fair_share_manage(struct thermal_zone_device *tz)
+{
+	int trip_level = get_trip_level(tz);
+	const struct thermal_trip_desc *td;
+
+	lockdep_assert_held(&tz->lock);
+
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
 
-	return 0;
+		if (trip->temperature == THERMAL_TEMP_INVALID ||
+		    trip->type == THERMAL_TRIP_CRITICAL ||
+		    trip->type == THERMAL_TRIP_HOT)
+			continue;
+
+		fair_share_throttle(tz, trip, trip_level);
+	}
 }
 
 static struct thermal_governor thermal_gov_fair_share = {
-	.name		= "fair_share",
-	.throttle	= fair_share_throttle,
+	.name	= "fair_share",
+	.manage	= fair_share_manage,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_fair_share);

drivers/thermal/gov_power_allocator.c

@@ -66,6 +66,7 @@ struct power_actor {
  * struct power_allocator_params - parameters for the power allocator governor
  * @allocated_tzp:	whether we have allocated tzp for this thermal zone and
  *			it needs to be freed on unbind
+ * @update_cdevs:	whether or not update cdevs on the next run
  * @err_integral:	accumulated error in the PID controller.
  * @prev_err:	error in the previous iteration of the PID controller.
  *		Used to calculate the derivative term.
@@ -84,6 +85,7 @@ struct power_actor {
  */
 struct power_allocator_params {
 	bool allocated_tzp;
+	bool update_cdevs;
 	s64 err_integral;
 	s32 prev_err;
 	u32 sustainable_power;
@@ -395,7 +397,7 @@ static void divvy_up_power(struct power_actor *power, int num_actors,
 	}
 }
 
-static int allocate_power(struct thermal_zone_device *tz, int control_temp)
+static void allocate_power(struct thermal_zone_device *tz, int control_temp)
 {
 	struct power_allocator_params *params = tz->governor_data;
 	unsigned int num_actors = params->num_actors;
@@ -410,7 +412,7 @@ static int allocate_power(struct thermal_zone_device *tz, int control_temp)
 	int i = 0, ret;
 
 	if (!num_actors)
-		return -ENODEV;
+		return;
 
 	/* Clean all buffers for new power estimations */
 	memset(power, 0, params->buffer_size);
@@ -471,8 +473,6 @@ static int allocate_power(struct thermal_zone_device *tz, int control_temp)
 				      num_actors, power_range,
 				      max_allocatable_power, tz->temperature,
 				      control_temp - tz->temperature);
-
-	return 0;
 }
 
 /**
@@ -535,7 +535,7 @@ static void reset_pid_controller(struct power_allocator_params *params)
 	params->prev_err = 0;
 }
 
-static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
+static void allow_maximum_power(struct thermal_zone_device *tz)
 {
 	struct power_allocator_params *params = tz->governor_data;
 	struct thermal_cooling_device *cdev;
@@ -557,7 +557,7 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 		 */
 		cdev->ops->get_requested_power(cdev, &req_power);
 
-		if (update)
+		if (params->update_cdevs)
 			__thermal_cdev_update(cdev);
 
 		mutex_unlock(&cdev->lock);
@@ -745,40 +745,29 @@ static void power_allocator_unbind(struct thermal_zone_device *tz)
 	tz->governor_data = NULL;
 }
 
-static int power_allocator_throttle(struct thermal_zone_device *tz,
-				    const struct thermal_trip *trip)
+static void power_allocator_manage(struct thermal_zone_device *tz)
 {
 	struct power_allocator_params *params = tz->governor_data;
-	bool update;
+	const struct thermal_trip *trip = params->trip_switch_on;
 
 	lockdep_assert_held(&tz->lock);
 
-	/*
-	 * We get called for every trip point but we only need to do
-	 * our calculations once
-	 */
-	if (trip != params->trip_max)
-		return 0;
-
-	trip = params->trip_switch_on;
 	if (trip && tz->temperature < trip->temperature) {
-		update = tz->passive;
-		tz->passive = 0;
 		reset_pid_controller(params);
-		allow_maximum_power(tz, update);
-		return 0;
+		allow_maximum_power(tz);
+		params->update_cdevs = false;
+		return;
 	}
 
-	tz->passive = 1;
-
-	return allocate_power(tz, params->trip_max->temperature);
+	allocate_power(tz, params->trip_max->temperature);
+	params->update_cdevs = true;
 }
 
 static struct thermal_governor thermal_gov_power_allocator = {
 	.name		= "power_allocator",
 	.bind_to_tz	= power_allocator_bind,
 	.unbind_from_tz	= power_allocator_unbind,
-	.throttle	= power_allocator_throttle,
+	.manage		= power_allocator_manage,
 	.update_tz	= power_allocator_update_tz,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_power_allocator);

drivers/thermal/gov_step_wise.c

@@ -62,81 +62,76 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 }
 
 static void thermal_zone_trip_update(struct thermal_zone_device *tz,
-				     const struct thermal_trip *trip)
+				     const struct thermal_trip *trip,
+				     int trip_threshold)
 {
+	enum thermal_trend trend = get_tz_trend(tz, trip);
 	int trip_id = thermal_zone_trip_id(tz, trip);
-	enum thermal_trend trend;
 	struct thermal_instance *instance;
 	bool throttle = false;
-	int old_target;
 
-	trend = get_tz_trend(tz, trip);
-
-	if (tz->temperature >= trip->temperature) {
+	if (tz->temperature >= trip_threshold) {
 		throttle = true;
 		trace_thermal_zone_trip(tz, trip_id, trip->type);
 	}
 
 	dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
-		trip_id, trip->type, trip->temperature, trend, throttle);
+		trip_id, trip->type, trip_threshold, trend, throttle);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		int old_target;
+
 		if (instance->trip != trip)
 			continue;
 
 		old_target = instance->target;
 		instance->target = get_target_state(instance, trend, throttle);
-		dev_dbg(&instance->cdev->device, "old_target=%d, target=%d\n",
-					old_target, (int)instance->target);
+
+		dev_dbg(&instance->cdev->device, "old_target=%d, target=%ld\n",
+			old_target, instance->target);
 
 		if (instance->initialized && old_target == instance->target)
 			continue;
 
-		if (trip->type == THERMAL_TRIP_PASSIVE) {
-			/* If needed, update the status of passive polling. */
-			if (old_target == THERMAL_NO_TARGET &&
-			    instance->target != THERMAL_NO_TARGET)
-				tz->passive++;
-			else if (old_target != THERMAL_NO_TARGET &&
-				 instance->target == THERMAL_NO_TARGET)
-				tz->passive--;
-		}
-
 		instance->initialized = true;
+
 		mutex_lock(&instance->cdev->lock);
 		instance->cdev->updated = false; /* cdev needs update */
 		mutex_unlock(&instance->cdev->lock);
 	}
 }
 
-/**
- * step_wise_throttle - throttles devices associated with the given zone
- * @tz: thermal_zone_device
- * @trip: trip point
- *
- * Throttling Logic: This uses the trend of the thermal zone to throttle.
- * If the thermal zone is 'heating up' this throttles all the cooling
- * devices associated with the zone and its particular trip point, by one
- * step. If the zone is 'cooling down' it brings back the performance of
- * the devices by one step.
- */
-static int step_wise_throttle(struct thermal_zone_device *tz,
-			      const struct thermal_trip *trip)
+static void step_wise_manage(struct thermal_zone_device *tz)
 {
+	const struct thermal_trip_desc *td;
 	struct thermal_instance *instance;
 
 	lockdep_assert_held(&tz->lock);
 
-	thermal_zone_trip_update(tz, trip);
+	/*
+	 * 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;
+
+		thermal_zone_trip_update(tz, trip, td->threshold);
+	}
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
-
-	return 0;
 }
 
 static struct thermal_governor thermal_gov_step_wise = {
-	.name		= "step_wise",
-	.throttle	= step_wise_throttle,
+	.name	= "step_wise",
+	.manage	= step_wise_manage,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_step_wise);

drivers/thermal/gov_user_space.c

@@ -26,11 +26,13 @@ static int user_space_bind(struct thermal_zone_device *tz)
  * notify_user_space - Notifies user space about thermal events
  * @tz: thermal_zone_device
  * @trip: trip point
+ * @crossed_up: whether or not the trip has been crossed on the way up
  *
  * This function notifies the user space through UEvents.
  */
-static int notify_user_space(struct thermal_zone_device *tz,
-			     const struct thermal_trip *trip)
+static void notify_user_space(struct thermal_zone_device *tz,
+			      const struct thermal_trip *trip,
+			      bool crossed_up)
 {
 	char *thermal_prop[5];
 	int i;
@@ -46,13 +48,11 @@ static int notify_user_space(struct thermal_zone_device *tz,
 	kobject_uevent_env(&tz->device.kobj, KOBJ_CHANGE, thermal_prop);
 	for (i = 0; i < 4; ++i)
 		kfree(thermal_prop[i]);
-
-	return 0;
 }
 
 static struct thermal_governor thermal_gov_user_space = {
 	.name		= "user_space",
-	.throttle	= notify_user_space,
+	.trip_crossed	= notify_user_space,
 	.bind_to_tz	= user_space_bind,
 };
 THERMAL_GOVERNOR_DECLARE(thermal_gov_user_space);

drivers/thermal/thermal_core.c

@@ -296,17 +296,18 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz)
 {
 	if (tz->mode != THERMAL_DEVICE_ENABLED)
 		thermal_zone_device_set_polling(tz, 0);
-	else if (tz->passive)
+	else if (tz->passive > 0)
 		thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
 	else if (tz->polling_delay_jiffies)
 		thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
 }
 
-static void handle_non_critical_trips(struct thermal_zone_device *tz,
-				      const struct thermal_trip *trip)
+static struct thermal_governor *thermal_get_tz_governor(struct thermal_zone_device *tz)
 {
-	tz->governor ? tz->governor->throttle(tz, trip) :
-		       def_governor->throttle(tz, trip);
+	if (tz->governor)
+		return tz->governor;
+
+	return def_governor;
 }
 
 void thermal_governor_update_tz(struct thermal_zone_device *tz,
@@ -349,10 +350,6 @@ void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip)
 {
-	/* If we have not crossed the trip_temp, we do not care. */
-	if (trip->temperature <= 0 || tz->temperature < trip->temperature)
-		return;
-
 	trace_thermal_zone_trip(tz, thermal_zone_trip_id(tz, trip), trip->type);
 
 	if (trip->type == THERMAL_TRIP_CRITICAL)
@@ -392,6 +389,11 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		if (tz->temperature < trip->temperature - trip->hysteresis) {
 			list_add(&td->notify_list_node, way_down_list);
 			td->notify_temp = trip->temperature - trip->hysteresis;
+
+			if (trip->type == THERMAL_TRIP_PASSIVE) {
+				tz->passive--;
+				WARN_ON(tz->passive < 0);
+			}
 		} else {
 			td->threshold -= trip->hysteresis;
 		}
@@ -404,12 +406,13 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		list_add_tail(&td->notify_list_node, way_up_list);
 		td->notify_temp = trip->temperature;
 		td->threshold -= trip->hysteresis;
-	}
 
-	if (trip->type == THERMAL_TRIP_CRITICAL || trip->type == THERMAL_TRIP_HOT)
-		handle_critical_trips(tz, trip);
-	else
-		handle_non_critical_trips(tz, trip);
+		if (trip->type == THERMAL_TRIP_PASSIVE)
+			tz->passive++;
+		else if (trip->type == THERMAL_TRIP_CRITICAL ||
+			 trip->type == THERMAL_TRIP_HOT)
+			handle_critical_trips(tz, trip);
+	}
 }
 
 static void update_temperature(struct thermal_zone_device *tz)
@@ -431,7 +434,6 @@ static void update_temperature(struct thermal_zone_device *tz)
 	trace_thermal_temperature(tz);
 
 	thermal_genl_sampling_temp(tz->id, temp);
-	thermal_debug_update_temp(tz);
 }
 
 static void thermal_zone_device_check(struct work_struct *work)
@@ -449,12 +451,22 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
 
 	tz->temperature = THERMAL_TEMP_INVALID;
+	tz->passive = 0;
 	tz->prev_low_trip = -INT_MAX;
 	tz->prev_high_trip = INT_MAX;
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
 		pos->initialized = false;
 }
 
+static void thermal_governor_trip_crossed(struct thermal_governor *governor,
+					  struct thermal_zone_device *tz,
+					  const struct thermal_trip *trip,
+					  bool crossed_up)
+{
+	if (governor->trip_crossed)
+		governor->trip_crossed(tz, trip, crossed_up);
+}
+
 static int thermal_trip_notify_cmp(void *ascending, const struct list_head *a,
 				   const struct list_head *b)
 {
@@ -470,6 +482,7 @@ static int thermal_trip_notify_cmp(void *ascending, const struct list_head *a,
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event)
 {
+	struct thermal_governor *governor = thermal_get_tz_governor(tz);
 	struct thermal_trip_desc *td;
 	LIST_HEAD(way_down_list);
 	LIST_HEAD(way_up_list);
@@ -482,6 +495,9 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 
 	update_temperature(tz);
 
+	if (tz->temperature == THERMAL_TEMP_INVALID)
+		return;
+
 	__thermal_zone_set_trips(tz);
 
 	tz->notify_event = event;
@@ -493,14 +509,21 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 	list_for_each_entry(td, &way_up_list, notify_list_node) {
 		thermal_notify_tz_trip_up(tz, &td->trip);
 		thermal_debug_tz_trip_up(tz, &td->trip);
+		thermal_governor_trip_crossed(governor, tz, &td->trip, true);
 	}
 
 	list_sort(NULL, &way_down_list, thermal_trip_notify_cmp);
 	list_for_each_entry(td, &way_down_list, notify_list_node) {
 		thermal_notify_tz_trip_down(tz, &td->trip);
 		thermal_debug_tz_trip_down(tz, &td->trip);
+		thermal_governor_trip_crossed(governor, tz, &td->trip, false);
 	}
 
+	if (governor->manage)
+		governor->manage(tz);
+
+	thermal_debug_update_trip_stats(tz);
+
 	monitor_thermal_zone(tz);
 }
 
@@ -923,6 +946,7 @@ __thermal_cooling_device_register(struct device_node *np,
 {
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos = NULL;
+	unsigned long current_state;
 	int id, ret;
 
 	if (!ops || !ops->get_max_state || !ops->get_cur_state ||
@@ -960,6 +984,10 @@ __thermal_cooling_device_register(struct device_node *np,
 	if (ret)
 		goto out_cdev_type;
 
+	ret = cdev->ops->get_cur_state(cdev, &current_state);
+	if (ret)
+		goto out_cdev_type;
+
 	thermal_cooling_device_setup_sysfs(cdev);
 
 	ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -973,6 +1001,8 @@ __thermal_cooling_device_register(struct device_node *np,
 		return ERR_PTR(ret);
 	}
 
+	thermal_debug_cdev_add(cdev, current_state);
+
 	/* Add 'this' new cdev to the global cdev list */
 	mutex_lock(&thermal_list_lock);
 
@@ -988,8 +1018,6 @@ __thermal_cooling_device_register(struct device_node *np,
 
 	mutex_unlock(&thermal_list_lock);
 
-	thermal_debug_cdev_add(cdev);
-
 	return cdev;
 
 out_cooling_dev:

drivers/thermal/thermal_core.h

@@ -30,8 +30,8 @@ struct thermal_trip_desc {
  *		otherwise it fails.
  * @unbind_from_tz:	callback called when a governor is unbound from a
  *			thermal zone.
- * @throttle:	callback called for every trip point even if temperature is
- *		below the trip point temperature
+ * @trip_crossed:	called for trip points that have just been crossed
+ * @manage:	called on thermal zone temperature updates
  * @update_tz:	callback called when thermal zone internals have changed, e.g.
  *		thermal cooling instance was added/removed
  * @governor_list:	node in thermal_governor_list (in thermal_core.c)
@@ -40,8 +40,10 @@ struct thermal_governor {
 	const char *name;
 	int (*bind_to_tz)(struct thermal_zone_device *tz);
 	void (*unbind_from_tz)(struct thermal_zone_device *tz);
-	int (*throttle)(struct thermal_zone_device *tz,
-			const struct thermal_trip *trip);
+	void (*trip_crossed)(struct thermal_zone_device *tz,
+			     const struct thermal_trip *trip,
+			     bool crossed_up);
+	void (*manage)(struct thermal_zone_device *tz);
 	void (*update_tz)(struct thermal_zone_device *tz,
 			  enum thermal_notify_event reason);
 	struct list_head	governor_list;

drivers/thermal/thermal_debugfs.c

@@ -435,6 +435,14 @@ void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
 	}
 
 	cdev_dbg->current_state = new_state;
+
+	/*
+	 * Create a record for the new state if it is not there, so its
+	 * duration will be printed by cdev_dt_seq_show() as expected if it
+	 * runs before the next state transition.
+	 */
+	thermal_debugfs_cdev_record_get(thermal_dbg, cdev_dbg->durations, new_state);
+
 	transition = (old_state << 16) | new_state;
 
 	/*
@@ -460,8 +468,9 @@ void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
  * Allocates a cooling device object for debug, initializes the
  * statistics and create the entries in sysfs.
  * @cdev: a pointer to a cooling device
+ * @state: current state of the cooling device
  */
-void thermal_debug_cdev_add(struct thermal_cooling_device *cdev)
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state)
 {
 	struct thermal_debugfs *thermal_dbg;
 	struct cdev_debugfs *cdev_dbg;
@@ -478,9 +487,16 @@ void thermal_debug_cdev_add(struct thermal_cooling_device *cdev)
 		INIT_LIST_HEAD(&cdev_dbg->durations[i]);
 	}
 
-	cdev_dbg->current_state = 0;
+	cdev_dbg->current_state = state;
 	cdev_dbg->timestamp = ktime_get();
 
+	/*
+	 * Create a record for the initial cooling device state, so its
+	 * duration will be printed by cdev_dt_seq_show() as expected if it
+	 * runs before the first state transition.
+	 */
+	thermal_debugfs_cdev_record_get(thermal_dbg, cdev_dbg->durations, state);
+
 	debugfs_create_file("trans_table", 0400, thermal_dbg->d_top,
 			    thermal_dbg, &tt_fops);
 
@@ -540,6 +556,7 @@ static struct tz_episode *thermal_debugfs_tz_event_alloc(struct thermal_zone_dev
 
 	INIT_LIST_HEAD(&tze->node);
 	tze->timestamp = now;
+	tze->duration = KTIME_MIN;
 
 	for (i = 0; i < tz->num_trips; i++) {
 		tze->trip_stats[i].min = INT_MAX;
@@ -555,7 +572,6 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 	struct tz_episode *tze;
 	struct tz_debugfs *tz_dbg;
 	struct thermal_debugfs *thermal_dbg = tz->debugfs;
-	int temperature = tz->temperature;
 	int trip_id = thermal_zone_trip_id(tz, trip);
 	ktime_t now = ktime_get();
 
@@ -624,12 +640,6 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 
 	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
 	tze->trip_stats[trip_id].timestamp = now;
-	tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature);
-	tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature);
-	tze->trip_stats[trip_id].count++;
-	tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
-		(temperature - tze->trip_stats[trip_id].avg) /
-		tze->trip_stats[trip_id].count;
 
 unlock:
 	mutex_unlock(&thermal_dbg->lock);
@@ -682,6 +692,9 @@ void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
 	tze->trip_stats[trip_id].duration =
 		ktime_add(delta, tze->trip_stats[trip_id].duration);
 
+	/* Mark the end of mitigation for this trip point. */
+	tze->trip_stats[trip_id].timestamp = KTIME_MAX;
+
 	/*
 	 * This event closes the mitigation as we are crossing the
 	 * last trip point the way down.
@@ -693,12 +706,12 @@ void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
 	mutex_unlock(&thermal_dbg->lock);
 }
 
-void thermal_debug_update_temp(struct thermal_zone_device *tz)
+void thermal_debug_update_trip_stats(struct thermal_zone_device *tz)
 {
 	struct thermal_debugfs *thermal_dbg = tz->debugfs;
-	struct tz_episode *tze;
 	struct tz_debugfs *tz_dbg;
-	int trip_id, i;
+	struct tz_episode *tze;
+	int i;
 
 	if (!thermal_dbg)
 		return;
@@ -710,15 +723,16 @@ void thermal_debug_update_temp(struct thermal_zone_device *tz)
 	if (!tz_dbg->nr_trips)
 		goto out;
 
+	tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
+
 	for (i = 0; i < tz_dbg->nr_trips; i++) {
-		trip_id = tz_dbg->trips_crossed[i];
-		tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node);
-		tze->trip_stats[trip_id].count++;
-		tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, tz->temperature);
-		tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, tz->temperature);
-		tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
-			(tz->temperature - tze->trip_stats[trip_id].avg) /
-			tze->trip_stats[trip_id].count;
+		int trip_id = tz_dbg->trips_crossed[i];
+		struct trip_stats *trip_stats = &tze->trip_stats[trip_id];
+
+		trip_stats->max = max(trip_stats->max, tz->temperature);
+		trip_stats->min = min(trip_stats->min, tz->temperature);
+		trip_stats->avg += (tz->temperature - trip_stats->avg) /
+					++trip_stats->count;
 	}
 out:
 	mutex_unlock(&thermal_dbg->lock);
@@ -756,18 +770,33 @@ static int tze_seq_show(struct seq_file *s, void *v)
 	struct thermal_trip_desc *td;
 	struct tz_episode *tze;
 	const char *type;
+	u64 duration_ms;
 	int trip_id;
+	char c;
 
 	tze = list_entry((struct list_head *)v, struct tz_episode, node);
 
-	seq_printf(s, ",-Mitigation at %lluus, duration=%llums\n",
-		   ktime_to_us(tze->timestamp),
-		   ktime_to_ms(tze->duration));
+	if (tze->duration == KTIME_MIN) {
+		/* Mitigation in progress. */
+		duration_ms = ktime_to_ms(ktime_sub(ktime_get(), tze->timestamp));
+		c = '>';
+	} else {
+		duration_ms = ktime_to_ms(tze->duration);
+		c = '=';
+	}
+
+	seq_printf(s, ",-Mitigation at %lluus, duration%c%llums\n",
+		   ktime_to_us(tze->timestamp), c, duration_ms);
 
-	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
+	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration   |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
 
 	for_each_trip_desc(tz, td) {
 		const struct thermal_trip *trip = &td->trip;
+		struct trip_stats *trip_stats;
+
+		/* Skip invalid trips. */
+		if (trip->temperature == THERMAL_TEMP_INVALID)
+			continue;
 
 		/*
 		 * There is no possible mitigation happening at the
@@ -777,6 +806,13 @@ static int tze_seq_show(struct seq_file *s, void *v)
 		if (trip->type == THERMAL_TRIP_CRITICAL)
 			continue;
 
+		trip_id = thermal_zone_trip_id(tz, trip);
+		trip_stats = &tze->trip_stats[trip_id];
+
+		/* Skip trips without any stats. */
+		if (trip_stats->min > trip_stats->max)
+			continue;
+
 		if (trip->type == THERMAL_TRIP_PASSIVE)
 			type = "passive";
 		else if (trip->type == THERMAL_TRIP_ACTIVE)
@@ -784,17 +820,28 @@ static int tze_seq_show(struct seq_file *s, void *v)
 		else
 			type = "hot";
 
-		trip_id = thermal_zone_trip_id(tz, trip);
+		if (trip_stats->timestamp != KTIME_MAX) {
+			/* Mitigation in progress. */
+			ktime_t delta = ktime_sub(ktime_get(),
+						  trip_stats->timestamp);
+
+			delta = ktime_add(delta, trip_stats->duration);
+			duration_ms = ktime_to_ms(delta);
+			c = '>';
+		} else {
+			duration_ms = ktime_to_ms(trip_stats->duration);
+			c = ' ';
+		}
 
-		seq_printf(s, "| %*d | %*s | %*d | %*d | %*lld | %*d | %*d | %*d |\n",
+		seq_printf(s, "| %*d | %*s | %*d | %*d | %c%*lld | %*d | %*d | %*d |\n",
 			   4 , trip_id,
 			   8, type,
 			   9, trip->temperature,
 			   9, trip->hysteresis,
-			   10, ktime_to_ms(tze->trip_stats[trip_id].duration),
-			   9, tze->trip_stats[trip_id].avg,
-			   9, tze->trip_stats[trip_id].min,
-			   9, tze->trip_stats[trip_id].max);
+			   c, 10, duration_ms,
+			   9, trip_stats->avg,
+			   9, trip_stats->min,
+			   9, trip_stats->max);
 	}
 
 	return 0;

drivers/thermal/thermal_debugfs.h

@@ -2,7 +2,7 @@
 
 #ifdef CONFIG_THERMAL_DEBUGFS
 void thermal_debug_init(void);
-void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state);
 void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
 void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state);
 void thermal_debug_tz_add(struct thermal_zone_device *tz);
@@ -11,10 +11,10 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 			      const struct thermal_trip *trip);
 void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
 				const struct thermal_trip *trip);
-void thermal_debug_update_temp(struct thermal_zone_device *tz);
+void thermal_debug_update_trip_stats(struct thermal_zone_device *tz);
 #else
 static inline void thermal_debug_init(void) {}
-static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state) {}
 static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {}
 static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
 						   int state) {}
@@ -24,5 +24,5 @@ static inline void thermal_debug_tz_trip_up(struct thermal_zone_device *tz,
 					    const struct thermal_trip *trip) {};
 static inline void thermal_debug_tz_trip_down(struct thermal_zone_device *tz,
 					      const struct thermal_trip *trip) {}
-static inline void thermal_debug_update_temp(struct thermal_zone_device *tz) {}
+static inline void thermal_debug_update_trip_stats(struct thermal_zone_device *tz) {}
 #endif /* CONFIG_THERMAL_DEBUGFS */

drivers/thermal/thermal_trip.c

@@ -138,6 +138,7 @@ int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 	 */
 	return trip_to_trip_desc(trip) - tz->trips;
 }
+
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip)
 {