Merge back earlier thermal control material for v6.10.

15 files changed, 415 insertions, 124 deletions

diff --git a/drivers/thermal/gov_fair_share.c b/drivers/thermal/gov_fair_share.c
index 4da25a0009d7..6ef8cfde7749 100644
--- a/drivers/thermal/gov_fair_share.c
+++ b/drivers/thermal/gov_fair_share.c
@@ -17,10 +17,13 @@
 
 static int get_trip_level(struct thermal_zone_device *tz)
 {
-	const struct thermal_trip *trip, *level_trip = NULL;
+	const struct thermal_trip *level_trip = NULL;
+	const struct thermal_trip_desc *td;
 	int trip_level = -1;
 
-	for_each_trip(tz, trip) {
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
+
 		if (trip->temperature >= tz->temperature)
 			continue;
 
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index e25e48d76aa7..ac1d02193a1b 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -496,9 +496,11 @@ static void get_governor_trips(struct thermal_zone_device *tz,
 	const struct thermal_trip *first_passive = NULL;
 	const struct thermal_trip *last_passive = NULL;
 	const struct thermal_trip *last_active = NULL;
-	const struct thermal_trip *trip;
+	const struct thermal_trip_desc *td;
+
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
 
-	for_each_trip(tz, trip) {
 		switch (trip->type) {
 		case THERMAL_TRIP_PASSIVE:
 			if (!first_passive) {
diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c
index 5436aa58d41e..ee2fb4e63d14 100644
--- a/drivers/thermal/gov_step_wise.c
+++ b/drivers/thermal/gov_step_wise.c
@@ -32,7 +32,6 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 {
 	struct thermal_cooling_device *cdev = instance->cdev;
 	unsigned long cur_state;
-	unsigned long next_target;
 
 	/*
 	 * We keep this instance the way it is by default.
@@ -40,32 +39,26 @@ static unsigned long get_target_state(struct thermal_instance *instance,
 	 * cdev in use to determine the next_target.
 	 */
 	cdev->ops->get_cur_state(cdev, &cur_state);
-	next_target = instance->target;
 	dev_dbg(&cdev->device, "cur_state=%ld\n", cur_state);
 
 	if (!instance->initialized) {
-		if (throttle) {
-			next_target = clamp((cur_state + 1), instance->lower, instance->upper);
-		} else {
-			next_target = THERMAL_NO_TARGET;
-		}
+		if (throttle)
+			return clamp(cur_state + 1, instance->lower, instance->upper);
 
-		return next_target;
+		return THERMAL_NO_TARGET;
 	}
 
 	if (throttle) {
 		if (trend == THERMAL_TREND_RAISING)
-			next_target = clamp((cur_state + 1), instance->lower, instance->upper);
-	} else {
-		if (trend == THERMAL_TREND_DROPPING) {
-			if (cur_state <= instance->lower)
-				next_target = THERMAL_NO_TARGET;
-			else
-				next_target = clamp((cur_state - 1), instance->lower, instance->upper);
-		}
+			return clamp(cur_state + 1, instance->lower, instance->upper);
+	} else if (trend == THERMAL_TREND_DROPPING) {
+		if (cur_state <= instance->lower)
+			return THERMAL_NO_TARGET;
+
+		return clamp(cur_state - 1, instance->lower, instance->upper);
 	}
 
-	return next_target;
+	return instance->target;
 }
 
 static void thermal_zone_trip_update(struct thermal_zone_device *tz,
@@ -99,15 +92,13 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz,
 		if (instance->initialized && old_target == instance->target)
 			continue;
 
-		if (old_target == THERMAL_NO_TARGET &&
-		    instance->target != THERMAL_NO_TARGET) {
-			/* Activate a passive thermal instance */
-			if (trip->type == THERMAL_TRIP_PASSIVE)
+		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) {
-			/* Deactivate a passive thermal instance */
-			if (trip->type == THERMAL_TRIP_PASSIVE)
+			else if (old_target != THERMAL_NO_TARGET &&
+				 instance->target == THERMAL_NO_TARGET)
 				tz->passive--;
 		}
 
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
index dc519a665c18..4b4a4d63e61f 100644
--- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -309,7 +309,7 @@ static int acpi_parse_psvt(acpi_handle handle, int *psvt_count, struct psvt **ps
 
 		if (knob->type == ACPI_TYPE_STRING) {
 			memset(&psvt->limit, 0, sizeof(u64));
-			strncpy(psvt->limit.string, psvt_ptr->limit.str_ptr, knob->string.length);
+			strscpy(psvt->limit.string, psvt_ptr->limit.str_ptr, ACPI_LIMIT_STR_MAX_LEN);
 		} else {
 			psvt->limit.integer = psvt_ptr->limit.integer;
 		}
@@ -468,7 +468,7 @@ static int fill_psvt(char __user *ubuf)
 		psvt_user[i].unlimit_coeff = psvts[i].unlimit_coeff;
 		psvt_user[i].control_knob_type = psvts[i].control_knob_type;
 		if (psvt_user[i].control_knob_type == ACPI_TYPE_STRING)
-			strncpy(psvt_user[i].limit.string, psvts[i].limit.string,
+			strscpy(psvt_user[i].limit.string, psvts[i].limit.string,
 				ACPI_LIMIT_STR_MAX_LEN);
 		else
 			psvt_user[i].limit.integer = psvts[i].limit.integer;
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 40d664a66cdc..fbc7f0cd83d7 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -159,6 +159,7 @@ struct hfi_cpu_info {
 static DEFINE_PER_CPU(struct hfi_cpu_info, hfi_cpu_info) = { .index = -1 };
 
 static int max_hfi_instances;
+static int hfi_clients_nr;
 static struct hfi_instance *hfi_instances;
 
 static struct hfi_features hfi_features;
@@ -477,8 +478,11 @@ void intel_hfi_online(unsigned int cpu)
 enable:
 	cpumask_set_cpu(cpu, hfi_instance->cpus);
 
-	/* Enable this HFI instance if this is its first online CPU. */
-	if (cpumask_weight(hfi_instance->cpus) == 1) {
+	/*
+	 * Enable this HFI instance if this is its first online CPU and
+	 * there are user-space clients of thermal events.
+	 */
+	if (cpumask_weight(hfi_instance->cpus) == 1 && hfi_clients_nr > 0) {
 		hfi_set_hw_table(hfi_instance);
 		hfi_enable();
 	}
@@ -573,18 +577,33 @@ static __init int hfi_parse_features(void)
 	return 0;
 }
 
-static void hfi_do_enable(void)
+/*
+ * If concurrency is not prevented by other means, the HFI enable/disable
+ * routines must be called under hfi_instance_lock."
+ */
+static void hfi_enable_instance(void *ptr)
+{
+	hfi_set_hw_table(ptr);
+	hfi_enable();
+}
+
+static void hfi_disable_instance(void *ptr)
+{
+	hfi_disable();
+}
+
+static void hfi_syscore_resume(void)
 {
 	/* This code runs only on the boot CPU. */
 	struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, 0);
 	struct hfi_instance *hfi_instance = info->hfi_instance;
 
 	/* No locking needed. There is no concurrency with CPU online. */
-	hfi_set_hw_table(hfi_instance);
-	hfi_enable();
+	if (hfi_clients_nr > 0)
+		hfi_enable_instance(hfi_instance);
 }
 
-static int hfi_do_disable(void)
+static int hfi_syscore_suspend(void)
 {
 	/* No locking needed. There is no concurrency with CPU offline. */
 	hfi_disable();
@@ -593,8 +612,58 @@ static int hfi_do_disable(void)
 }
 
 static struct syscore_ops hfi_pm_ops = {
-	.resume = hfi_do_enable,
-	.suspend = hfi_do_disable,
+	.resume = hfi_syscore_resume,
+	.suspend = hfi_syscore_suspend,
+};
+
+static int hfi_thermal_notify(struct notifier_block *nb, unsigned long state,
+			      void *_notify)
+{
+	struct thermal_genl_notify *notify = _notify;
+	struct hfi_instance *hfi_instance;
+	smp_call_func_t func = NULL;
+	unsigned int cpu;
+	int i;
+
+	if (notify->mcgrp != THERMAL_GENL_EVENT_GROUP)
+		return NOTIFY_DONE;
+
+	if (state != THERMAL_NOTIFY_BIND && state != THERMAL_NOTIFY_UNBIND)
+		return NOTIFY_DONE;
+
+	mutex_lock(&hfi_instance_lock);
+
+	switch (state) {
+	case THERMAL_NOTIFY_BIND:
+		if (++hfi_clients_nr == 1)
+			func = hfi_enable_instance;
+		break;
+	case THERMAL_NOTIFY_UNBIND:
+		if (--hfi_clients_nr == 0)
+			func = hfi_disable_instance;
+		break;
+	}
+
+	if (!func)
+		goto out;
+
+	for (i = 0; i < max_hfi_instances; i++) {
+		hfi_instance = &hfi_instances[i];
+		if (cpumask_empty(hfi_instance->cpus))
+			continue;
+
+		cpu = cpumask_any(hfi_instance->cpus);
+		smp_call_function_single(cpu, func, hfi_instance, true);
+	}
+
+out:
+	mutex_unlock(&hfi_instance_lock);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block hfi_thermal_nb = {
+	.notifier_call = hfi_thermal_notify,
 };
 
 void __init intel_hfi_init(void)
@@ -628,10 +697,22 @@ void __init intel_hfi_init(void)
 	if (!hfi_updates_wq)
 		goto err_nomem;
 
+	/*
+	 * Both thermal core and Intel HFI can not be build as modules.
+	 * As kernel build-in drivers they are initialized before user-space
+	 * starts, hence we can not miss BIND/UNBIND events when applications
+	 * add/remove thermal multicast group to/from a netlink socket.
+	 */
+	if (thermal_genl_register_notifier(&hfi_thermal_nb))
+		goto err_nl_notif;
+
 	register_syscore_ops(&hfi_pm_ops);
 
 	return;
 
+err_nl_notif:
+	destroy_workqueue(hfi_updates_wq);
+
 err_nomem:
 	for (j = 0; j < i; ++j) {
 		hfi_instance = &hfi_instances[j];
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 34a31bc72023..58e60bcdc0a5 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/kdev_t.h>
 #include <linux/idr.h>
+#include <linux/list_sort.h>
 #include <linux/thermal.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
@@ -361,49 +362,48 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 }
 
 static void handle_thermal_trip(struct thermal_zone_device *tz,
-				struct thermal_trip *trip)
+				struct thermal_trip_desc *td,
+				struct list_head *way_up_list,
+				struct list_head *way_down_list)
 {
+	const struct thermal_trip *trip = &td->trip;
+	int old_threshold;
+
 	if (trip->temperature == THERMAL_TEMP_INVALID)
 		return;
 
-	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) {
+	/*
+	 * If the trip temperature or hysteresis has been updated recently,
+	 * the threshold needs to be computed again using the new values.
+	 * However, its initial value still reflects the old ones and that
+	 * is what needs to be compared with the previous zone temperature
+	 * to decide which action to take.
+	 */
+	old_threshold = td->threshold;
+	td->threshold = trip->temperature;
+
+	if (tz->last_temperature >= old_threshold &&
+	    tz->last_temperature != THERMAL_TEMP_INVALID) {
 		/*
-		 * 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.
+		 * Mitigation is under way, so it needs to stop if the zone
+		 * temperature falls below the low temperature of the trip.
+		 * In that case, the trip temperature becomes the new threshold.
 		 */
-		if (tz->temperature >= trip->temperature) {
-			thermal_notify_tz_trip_up(tz, trip);
-			thermal_debug_tz_trip_up(tz, trip);
-			trip->threshold = trip->temperature - trip->hysteresis;
+		if (tz->temperature < trip->temperature - trip->hysteresis) {
+			list_add(&td->notify_list_node, way_down_list);
+			td->notify_temp = trip->temperature - trip->hysteresis;
 		} else {
-			trip->threshold = trip->temperature;
+			td->threshold -= trip->hysteresis;
 		}
-	} else {
+	} else if (tz->temperature >= trip->temperature) {
 		/*
-		 * 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.
+		 * There is no mitigation under way, so it needs to be started
+		 * if the zone temperature exceeds the trip one.  The new
+		 * threshold is then set to the low temperature of the trip.
 		 */
-		if (tz->temperature < trip->temperature - trip->hysteresis) {
-			thermal_notify_tz_trip_down(tz, trip);
-			thermal_debug_tz_trip_down(tz, trip);
-			trip->threshold = trip->temperature;
-		} else {
-			trip->threshold = trip->temperature - trip->hysteresis;
-		}
+		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)
@@ -455,10 +455,24 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 		pos->initialized = false;
 }
 
+static int thermal_trip_notify_cmp(void *ascending, const struct list_head *a,
+				   const struct list_head *b)
+{
+	struct thermal_trip_desc *tda = container_of(a, struct thermal_trip_desc,
+						     notify_list_node);
+	struct thermal_trip_desc *tdb = container_of(b, struct thermal_trip_desc,
+						     notify_list_node);
+	int ret = tdb->notify_temp - tda->notify_temp;
+
+	return ascending ? ret : -ret;
+}
+
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event)
 {
-	struct thermal_trip *trip;
+	struct thermal_trip_desc *td;
+	LIST_HEAD(way_down_list);
+	LIST_HEAD(way_up_list);
 
 	if (tz->suspended)
 		return;
@@ -472,8 +486,20 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 
 	tz->notify_event = event;
 
-	for_each_trip(tz, trip)
-		handle_thermal_trip(tz, trip);
+	for_each_trip_desc(tz, td)
+		handle_thermal_trip(tz, td, &way_up_list, &way_down_list);
+
+	list_sort(&way_up_list, &way_up_list, thermal_trip_notify_cmp);
+	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);
+	}
+
+	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);
+	}
 
 	monitor_thermal_zone(tz);
 }
@@ -766,7 +792,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	if (trip_index < 0 || trip_index >= tz->num_trips)
 		return -EINVAL;
 
-	return thermal_bind_cdev_to_trip(tz, &tz->trips[trip_index], cdev,
+	return thermal_bind_cdev_to_trip(tz, &tz->trips[trip_index].trip, cdev,
 					 upper, lower, weight);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_bind_cooling_device);
@@ -825,7 +851,7 @@ int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
 	if (trip_index < 0 || trip_index >= tz->num_trips)
 		return -EINVAL;
 
-	return thermal_unbind_cdev_from_trip(tz, &tz->trips[trip_index], cdev);
+	return thermal_unbind_cdev_from_trip(tz, &tz->trips[trip_index].trip, cdev);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_unbind_cooling_device);
 
@@ -1221,16 +1247,19 @@ static void thermal_set_delay_jiffies(unsigned long *delay_jiffies, int delay_ms
 
 int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp)
 {
-	int i, ret = -EINVAL;
+	const struct thermal_trip_desc *td;
+	int ret = -EINVAL;
 
 	if (tz->ops.get_crit_temp)
 		return tz->ops.get_crit_temp(tz, temp);
 
 	mutex_lock(&tz->lock);
 
-	for (i = 0; i < tz->num_trips; i++) {
-		if (tz->trips[i].type == THERMAL_TRIP_CRITICAL) {
-			*temp = tz->trips[i].temperature;
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
+
+		if (trip->type == THERMAL_TRIP_CRITICAL) {
+			*temp = trip->temperature;
 			ret = 0;
 			break;
 		}
@@ -1274,7 +1303,9 @@ thermal_zone_device_register_with_trips(const char *type,
 					const struct thermal_zone_params *tzp,
 					int passive_delay, int polling_delay)
 {
+	const struct thermal_trip *trip = trips;
 	struct thermal_zone_device *tz;
+	struct thermal_trip_desc *td;
 	int id;
 	int result;
 	struct thermal_governor *governor;
@@ -1339,7 +1370,8 @@ thermal_zone_device_register_with_trips(const char *type,
 	tz->device.class = thermal_class;
 	tz->devdata = devdata;
 	tz->num_trips = num_trips;
-	memcpy(tz->trips, trips, num_trips * sizeof(*trips));
+	for_each_trip_desc(tz, td)
+		td->trip = *trip++;
 
 	thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
 	thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 0d8a42bb7ce8..b461d9583834 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -15,6 +15,118 @@
 #include "thermal_netlink.h"
 #include "thermal_debugfs.h"
 
+struct thermal_trip_desc {
+	struct thermal_trip trip;
+	struct list_head notify_list_node;
+	int notify_temp;
+	int threshold;
+};
+
+/**
+ * struct thermal_governor - structure that holds thermal governor information
+ * @name:	name of the governor
+ * @bind_to_tz: callback called when binding to a thermal zone.  If it
+ *		returns 0, the governor is bound to the thermal zone,
+ *		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
+ * @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)
+ */
+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 (*update_tz)(struct thermal_zone_device *tz,
+			  enum thermal_notify_event reason);
+	struct list_head	governor_list;
+};
+
+/**
+ * struct thermal_zone_device - structure for a thermal zone
+ * @id:		unique id number for each thermal zone
+ * @type:	the thermal zone device type
+ * @device:	&struct device for this thermal zone
+ * @removal:	removal completion
+ * @trip_temp_attrs:	attributes for trip points for sysfs: trip temperature
+ * @trip_type_attrs:	attributes for trip points for sysfs: trip type
+ * @trip_hyst_attrs:	attributes for trip points for sysfs: trip hysteresis
+ * @mode:		current mode of this thermal zone
+ * @devdata:	private pointer for device private data
+ * @num_trips:	number of trip points the thermal zone supports
+ * @passive_delay_jiffies: number of jiffies to wait between polls when
+ *			performing passive cooling.
+ * @polling_delay_jiffies: number of jiffies to wait between polls when
+ *			checking whether trip points have been crossed (0 for
+ *			interrupt driven systems)
+ * @temperature:	current temperature.  This is only for core code,
+ *			drivers should use thermal_zone_get_temp() to get the
+ *			current temperature
+ * @last_temperature:	previous temperature read
+ * @emul_temperature:	emulated temperature when using CONFIG_THERMAL_EMULATION
+ * @passive:		1 if you've crossed a passive trip point, 0 otherwise.
+ * @prev_low_trip:	the low current temperature if you've crossed a passive
+			trip point.
+ * @prev_high_trip:	the above current temperature if you've crossed a
+			passive trip point.
+ * @need_update:	if equals 1, thermal_zone_device_update needs to be invoked.
+ * @ops:	operations this &thermal_zone_device supports
+ * @tzp:	thermal zone parameters
+ * @governor:	pointer to the governor for this thermal zone
+ * @governor_data:	private pointer for governor data
+ * @thermal_instances:	list of &struct thermal_instance of this thermal zone
+ * @ida:	&struct ida to generate unique id for this zone's cooling
+ *		devices
+ * @lock:	lock to protect thermal_instances list
+ * @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
+ * @trips:	array of struct thermal_trip objects
+ */
+struct thermal_zone_device {
+	int id;
+	char type[THERMAL_NAME_LENGTH];
+	struct device device;
+	struct completion removal;
+	struct attribute_group trips_attribute_group;
+	struct thermal_attr *trip_temp_attrs;
+	struct thermal_attr *trip_type_attrs;
+	struct thermal_attr *trip_hyst_attrs;
+	enum thermal_device_mode mode;
+	void *devdata;
+	int num_trips;
+	unsigned long passive_delay_jiffies;
+	unsigned long polling_delay_jiffies;
+	int temperature;
+	int last_temperature;
+	int emul_temperature;
+	int passive;
+	int prev_low_trip;
+	int prev_high_trip;
+	atomic_t need_update;
+	struct thermal_zone_device_ops ops;
+	struct thermal_zone_params *tzp;
+	struct thermal_governor *governor;
+	void *governor_data;
+	struct list_head thermal_instances;
+	struct ida ida;
+	struct mutex lock;
+	struct list_head node;
+	struct delayed_work poll_queue;
+	enum thermal_notify_event notify_event;
+	bool suspended;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
+	struct thermal_trip_desc trips[] __counted_by(num_trips);
+};
+
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
 #define DEFAULT_THERMAL_GOVERNOR       "step_wise"
@@ -120,8 +232,11 @@ void thermal_governor_update_tz(struct thermal_zone_device *tz,
 				enum thermal_notify_event reason);
 
 /* Helpers */
-#define for_each_trip(__tz, __trip)	\
-	for (__trip = __tz->trips; __trip - __tz->trips < __tz->num_trips; __trip++)
+#define for_each_trip_desc(__tz, __td)	\
+	for (__td = __tz->trips; __td - __tz->trips < __tz->num_trips; __td++)
+
+#define trip_to_trip_desc(__trip)	\
+	container_of(__trip, struct thermal_trip_desc, trip)
 
 void __thermal_zone_set_trips(struct thermal_zone_device *tz);
 int thermal_zone_trip_id(const struct thermal_zone_device *tz,
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index d78d54ae2605..40ea0071a691 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -745,7 +745,7 @@ static void tze_seq_stop(struct seq_file *s, void *v)
 static int tze_seq_show(struct seq_file *s, void *v)
 {
 	struct thermal_zone_device *tz = s->private;
-	struct thermal_trip *trip;
+	struct thermal_trip_desc *td;
 	struct tz_episode *tze;
 	const char *type;
 	int trip_id;
@@ -758,7 +758,9 @@ static int tze_seq_show(struct seq_file *s, void *v)
 
 	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
 
-	for_each_trip(tz, trip) {
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
+
 		/*
 		 * There is no possible mitigation happening at the
 		 * critical trip point, so the stats will be always
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index c5a057b59c42..d9f4e26ec125 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -50,7 +50,7 @@ get_thermal_instance(struct thermal_zone_device *tz,
 	mutex_lock(&tz->lock);
 	mutex_lock(&cdev->lock);
 
-	trip = &tz->trips[trip_index];
+	trip = &tz->trips[trip_index].trip;
 
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node) {
 		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
@@ -82,7 +82,7 @@ EXPORT_SYMBOL(get_thermal_instance);
  */
 int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	const struct thermal_trip *trip;
+	const struct thermal_trip_desc *td;
 	int crit_temp = INT_MAX;
 	int ret = -EINVAL;
 
@@ -91,7 +91,9 @@ int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 	ret = tz->ops.get_temp(tz, temp);
 
 	if (IS_ENABLED(CONFIG_THERMAL_EMULATION) && tz->emul_temperature) {
-		for_each_trip(tz, trip) {
+		for_each_trip_desc(tz, td) {
+			const struct thermal_trip *trip = &td->trip;
+
 			if (trip->type == THERMAL_TRIP_CRITICAL) {
 				crit_temp = trip->temperature;
 				break;
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 76a231a29654..97157c453630 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -7,17 +7,13 @@
  * Generic netlink for thermal management framework
  */
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/kernel.h>
 #include <net/genetlink.h>
 #include <uapi/linux/thermal.h>
 
 #include "thermal_core.h"
 
-enum thermal_genl_multicast_groups {
-	THERMAL_GENL_SAMPLING_GROUP = 0,
-	THERMAL_GENL_EVENT_GROUP = 1,
-};
-
 static const struct genl_multicast_group thermal_genl_mcgrps[] = {
 	[THERMAL_GENL_SAMPLING_GROUP] = { .name = THERMAL_GENL_SAMPLING_GROUP_NAME, },
 	[THERMAL_GENL_EVENT_GROUP]  = { .name = THERMAL_GENL_EVENT_GROUP_NAME,  },
@@ -74,11 +70,12 @@ struct param {
 
 typedef int (*cb_t)(struct param *);
 
-static struct genl_family thermal_gnl_family;
+static struct genl_family thermal_genl_family;
+static BLOCKING_NOTIFIER_HEAD(thermal_genl_chain);
 
 static int thermal_group_has_listeners(enum thermal_genl_multicast_groups group)
 {
-	return genl_has_listeners(&thermal_gnl_family, &init_net, group);
+	return genl_has_listeners(&thermal_genl_family, &init_net, group);
 }
 
 /************************** Sampling encoding *******************************/
@@ -95,7 +92,7 @@ int thermal_genl_sampling_temp(int id, int temp)
 	if (!skb)
 		return -ENOMEM;
 
-	hdr = genlmsg_put(skb, 0, 0, &thermal_gnl_family, 0,
+	hdr = genlmsg_put(skb, 0, 0, &thermal_genl_family, 0,
 			  THERMAL_GENL_SAMPLING_TEMP);
 	if (!hdr)
 		goto out_free;
@@ -108,7 +105,7 @@ int thermal_genl_sampling_temp(int id, int temp)
 
 	genlmsg_end(skb, hdr);
 
-	genlmsg_multicast(&thermal_gnl_family, skb, 0, THERMAL_GENL_SAMPLING_GROUP, GFP_KERNEL);
+	genlmsg_multicast(&thermal_genl_family, skb, 0, THERMAL_GENL_SAMPLING_GROUP, GFP_KERNEL);
 
 	return 0;
 out_cancel:
@@ -282,7 +279,7 @@ static int thermal_genl_send_event(enum thermal_genl_event event,
 		return -ENOMEM;
 	p->msg = msg;
 
-	hdr = genlmsg_put(msg, 0, 0, &thermal_gnl_family, 0, event);
+	hdr = genlmsg_put(msg, 0, 0, &thermal_genl_family, 0, event);
 	if (!hdr)
 		goto out_free_msg;
 
@@ -292,7 +289,7 @@ static int thermal_genl_send_event(enum thermal_genl_event event,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&thermal_gnl_family, msg, 0, THERMAL_GENL_EVENT_GROUP, GFP_KERNEL);
+	genlmsg_multicast(&thermal_genl_family, msg, 0, THERMAL_GENL_EVENT_GROUP, GFP_KERNEL);
 
 	return 0;
 
@@ -445,7 +442,7 @@ out_cancel_nest:
 static int thermal_genl_cmd_tz_get_trip(struct param *p)
 {
 	struct sk_buff *msg = p->msg;
-	const struct thermal_trip *trip;
+	const struct thermal_trip_desc *td;
 	struct thermal_zone_device *tz;
 	struct nlattr *start_trip;
 	int id;
@@ -465,7 +462,9 @@ static int thermal_genl_cmd_tz_get_trip(struct param *p)
 
 	mutex_lock(&tz->lock);
 
-	for_each_trip(tz, trip) {
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
+
 		if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID,
 				thermal_zone_trip_id(tz, trip)) ||
 		    nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, trip->type) ||
@@ -593,7 +592,7 @@ static int thermal_genl_cmd_dumpit(struct sk_buff *skb,
 	int ret;
 	void *hdr;
 
-	hdr = genlmsg_put(skb, 0, 0, &thermal_gnl_family, 0, cmd);
+	hdr = genlmsg_put(skb, 0, 0, &thermal_genl_family, 0, cmd);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -625,7 +624,7 @@ static int thermal_genl_cmd_doit(struct sk_buff *skb,
 		return -ENOMEM;
 	p.msg = msg;
 
-	hdr = genlmsg_put_reply(msg, info, &thermal_gnl_family, 0, cmd);
+	hdr = genlmsg_put_reply(msg, info, &thermal_genl_family, 0, cmd);
 	if (!hdr)
 		goto out_free_msg;
 
@@ -645,6 +644,27 @@ out_free_msg:
 	return ret;
 }
 
+static int thermal_genl_bind(int mcgrp)
+{
+	struct thermal_genl_notify n = { .mcgrp = mcgrp };
+
+	if (WARN_ON_ONCE(mcgrp > THERMAL_GENL_MAX_GROUP))
+		return -EINVAL;
+
+	blocking_notifier_call_chain(&thermal_genl_chain, THERMAL_NOTIFY_BIND, &n);
+	return 0;
+}
+
+static void thermal_genl_unbind(int mcgrp)
+{
+	struct thermal_genl_notify n = { .mcgrp = mcgrp };
+
+	if (WARN_ON_ONCE(mcgrp > THERMAL_GENL_MAX_GROUP))
+		return;
+
+	blocking_notifier_call_chain(&thermal_genl_chain, THERMAL_NOTIFY_UNBIND, &n);
+}
+
 static const struct genl_small_ops thermal_genl_ops[] = {
 	{
 		.cmd = THERMAL_GENL_CMD_TZ_GET_ID,
@@ -673,12 +693,14 @@ static const struct genl_small_ops thermal_genl_ops[] = {
 	},
 };
 
-static struct genl_family thermal_gnl_family __ro_after_init = {
+static struct genl_family thermal_genl_family __ro_after_init = {
 	.hdrsize	= 0,
 	.name		= THERMAL_GENL_FAMILY_NAME,
 	.version	= THERMAL_GENL_VERSION,
 	.maxattr	= THERMAL_GENL_ATTR_MAX,
 	.policy		= thermal_genl_policy,
+	.bind		= thermal_genl_bind,
+	.unbind		= thermal_genl_unbind,
 	.small_ops	= thermal_genl_ops,
 	.n_small_ops	= ARRAY_SIZE(thermal_genl_ops),
 	.resv_start_op	= THERMAL_GENL_CMD_CDEV_GET + 1,
@@ -686,12 +708,22 @@ static struct genl_family thermal_gnl_family __ro_after_init = {
 	.n_mcgrps	= ARRAY_SIZE(thermal_genl_mcgrps),
 };
 
+int thermal_genl_register_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&thermal_genl_chain, nb);
+}
+
+int thermal_genl_unregister_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&thermal_genl_chain, nb);
+}
+
 int __init thermal_netlink_init(void)
 {
-	return genl_register_family(&thermal_gnl_family);
+	return genl_register_family(&thermal_genl_family);
 }
 
 void __init thermal_netlink_exit(void)
 {
-	genl_unregister_family(&thermal_gnl_family);
+	genl_unregister_family(&thermal_genl_family);
 }
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index 93a927e144d5..e01221e8816b 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -10,6 +10,19 @@ struct thermal_genl_cpu_caps {
 	int efficiency;
 };
 
+enum thermal_genl_multicast_groups {
+	THERMAL_GENL_SAMPLING_GROUP = 0,
+	THERMAL_GENL_EVENT_GROUP = 1,
+	THERMAL_GENL_MAX_GROUP = THERMAL_GENL_EVENT_GROUP,
+};
+
+#define THERMAL_NOTIFY_BIND	0
+#define THERMAL_NOTIFY_UNBIND	1
+
+struct thermal_genl_notify {
+	int mcgrp;
+};
+
 struct thermal_zone_device;
 struct thermal_trip;
 struct thermal_cooling_device;
@@ -18,6 +31,9 @@ struct thermal_cooling_device;
 #ifdef CONFIG_THERMAL_NETLINK
 int __init thermal_netlink_init(void);
 void __init thermal_netlink_exit(void);
+int thermal_genl_register_notifier(struct notifier_block *nb);
+int thermal_genl_unregister_notifier(struct notifier_block *nb);
+
 int thermal_notify_tz_create(const struct thermal_zone_device *tz);
 int thermal_notify_tz_delete(const struct thermal_zone_device *tz);
 int thermal_notify_tz_enable(const struct thermal_zone_device *tz);
@@ -48,6 +64,16 @@ static inline int thermal_notify_tz_create(const struct thermal_zone_device *tz)
 	return 0;
 }
 
+static inline int thermal_genl_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int thermal_genl_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
 static inline int thermal_notify_tz_delete(const struct thermal_zone_device *tz)
 {
 	return 0;
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 5b533fa40437..88211ccdfbd6 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -88,7 +88,7 @@ trip_point_type_show(struct device *dev, struct device_attribute *attr,
 	if (sscanf(attr->attr.name, "trip_point_%d_type", &trip_id) != 1)
 		return -EINVAL;
 
-	switch (tz->trips[trip_id].type) {
+	switch (tz->trips[trip_id].trip.type) {
 	case THERMAL_TRIP_CRITICAL:
 		return sprintf(buf, "critical\n");
 	case THERMAL_TRIP_HOT:
@@ -120,7 +120,7 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&tz->lock);
 
-	trip = &tz->trips[trip_id];
+	trip = &tz->trips[trip_id].trip;
 
 	if (temp != trip->temperature) {
 		if (tz->ops.set_trip_temp) {
@@ -150,7 +150,7 @@ trip_point_temp_show(struct device *dev, struct device_attribute *attr,
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip_id) != 1)
 		return -EINVAL;
 
-	return sprintf(buf, "%d\n", tz->trips[trip_id].temperature);
+	return sprintf(buf, "%d\n", tz->trips[trip_id].trip.temperature);
 }
 
 static ssize_t
@@ -171,7 +171,7 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&tz->lock);
 
-	trip = &tz->trips[trip_id];
+	trip = &tz->trips[trip_id].trip;
 
 	if (hyst != trip->hysteresis) {
 		trip->hysteresis = hyst;
@@ -194,7 +194,7 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr,
 	if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1)
 		return -EINVAL;
 
-	return sprintf(buf, "%d\n", tz->trips[trip_id].hysteresis);
+	return sprintf(buf, "%d\n", tz->trips[trip_id].trip.hysteresis);
 }
 
 static ssize_t
@@ -393,7 +393,7 @@ static const struct attribute_group *thermal_zone_attribute_groups[] = {
  */
 static int create_trip_attrs(struct thermal_zone_device *tz)
 {
-	const struct thermal_trip *trip;
+	const struct thermal_trip_desc *td;
 	struct attribute **attrs;
 
 	/* This function works only for zones with at least one trip */
@@ -429,8 +429,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz)
 		return -ENOMEM;
 	}
 
-	for_each_trip(tz, trip) {
-		int indx = thermal_zone_trip_id(tz, trip);
+	for_each_trip_desc(tz, td) {
+		int indx = thermal_zone_trip_id(tz, &td->trip);
 
 		/* create trip type attribute */
 		snprintf(tz->trip_type_attrs[indx].name, THERMAL_NAME_LENGTH,
@@ -452,7 +452,7 @@ static int create_trip_attrs(struct thermal_zone_device *tz)
 						tz->trip_temp_attrs[indx].name;
 		tz->trip_temp_attrs[indx].attr.attr.mode = S_IRUGO;
 		tz->trip_temp_attrs[indx].attr.show = trip_point_temp_show;
-		if (trip->flags & THERMAL_TRIP_FLAG_RW_TEMP) {
+		if (td->trip.flags & THERMAL_TRIP_FLAG_RW_TEMP) {
 			tz->trip_temp_attrs[indx].attr.attr.mode |= S_IWUSR;
 			tz->trip_temp_attrs[indx].attr.store =
 							trip_point_temp_store;
@@ -467,7 +467,7 @@ static int create_trip_attrs(struct thermal_zone_device *tz)
 					tz->trip_hyst_attrs[indx].name;
 		tz->trip_hyst_attrs[indx].attr.attr.mode = S_IRUGO;
 		tz->trip_hyst_attrs[indx].attr.show = trip_point_hyst_show;
-		if (trip->flags & THERMAL_TRIP_FLAG_RW_HYST) {
+		if (td->trip.flags & THERMAL_TRIP_FLAG_RW_HYST) {
 			tz->trip_hyst_attrs[indx].attr.attr.mode |= S_IWUSR;
 			tz->trip_hyst_attrs[indx].attr.store =
 					trip_point_hyst_store;
diff --git a/drivers/thermal/thermal_trace.h b/drivers/thermal/thermal_trace.h
index 459c8ce6cf3b..88a962f560f2 100644
--- a/drivers/thermal/thermal_trace.h
+++ b/drivers/thermal/thermal_trace.h
@@ -9,6 +9,8 @@
 #include <linux/thermal.h>
 #include <linux/tracepoint.h>
 
+#include "thermal_core.h"
+
 TRACE_DEFINE_ENUM(THERMAL_TRIP_CRITICAL);
 TRACE_DEFINE_ENUM(THERMAL_TRIP_HOT);
 TRACE_DEFINE_ENUM(THERMAL_TRIP_PASSIVE);
diff --git a/drivers/thermal/thermal_trace_ipa.h b/drivers/thermal/thermal_trace_ipa.h
index b16b5dd863d9..a82821eebc88 100644
--- a/drivers/thermal/thermal_trace_ipa.h
+++ b/drivers/thermal/thermal_trace_ipa.h
@@ -7,6 +7,8 @@
 
 #include <linux/tracepoint.h>
 
+#include "thermal_core.h"
+
 TRACE_EVENT(thermal_power_allocator,
 	TP_PROTO(struct thermal_zone_device *tz, u32 total_req_power,
 		 u32 total_granted_power, int num_actors, u32 power_range,
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index 497abf0d47ca..7cf43b697272 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -13,11 +13,11 @@ int for_each_thermal_trip(struct thermal_zone_device *tz,
 			  int (*cb)(struct thermal_trip *, void *),
 			  void *data)
 {
-	struct thermal_trip *trip;
+	struct thermal_trip_desc *td;
 	int ret;
 
-	for_each_trip(tz, trip) {
-		ret = cb(trip, data);
+	for_each_trip_desc(tz, td) {
+		ret = cb(&td->trip, data);
 		if (ret)
 			return ret;
 	}
@@ -63,7 +63,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_get_num_trips);
  */
 void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 {
-	const struct thermal_trip *trip;
+	const struct thermal_trip_desc *td;
 	int low = -INT_MAX, high = INT_MAX;
 	int ret;
 
@@ -72,7 +72,8 @@ void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 	if (!tz->ops.set_trips)
 		return;
 
-	for_each_trip(tz, trip) {
+	for_each_trip_desc(tz, td) {
+		const struct thermal_trip *trip = &td->trip;
 		int trip_low;
 
 		trip_low = trip->temperature - trip->hysteresis;
@@ -110,7 +111,7 @@ int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 	if (!tz || trip_id < 0 || trip_id >= tz->num_trips || !trip)
 		return -EINVAL;
 
-	*trip = tz->trips[trip_id];
+	*trip = tz->trips[trip_id].trip;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__thermal_zone_get_trip);
@@ -135,7 +136,7 @@ int thermal_zone_trip_id(const struct thermal_zone_device *tz,
 	 * Assume the trip to be located within the bounds of the thermal
 	 * zone's trips[] table.
 	 */
-	return trip - tz->trips;
+	return trip_to_trip_desc(trip) - tz->trips;
 }
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip)