Merge tag 'thermal-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more thermal control updates from Rafael Wysocki:
 "These add support for debugfs-based diagnostics to the thermal core,
  simplify the thermal netlink API, fix system-wide PM support in the
  Intel HFI driver and clean up some code.

  Specifics:

   - Add debugfs-based diagnostics support to the thermal core (Daniel
     Lezcano, Dan Carpenter)

   - Fix a power allocator thermal governor issue preventing it from
     resetting cooling devices sometimes (Di Shen)

   - Simplify the thermal netlink API and clean up related code (Rafael
     J. Wysocki)

   - Make the Intel HFI driver support hibernation and deep suspend
     properly (Ricardo Neri)"

* tag 'thermal-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  thermal/debugfs: Unlock on error path in thermal_debug_tz_trip_up()
  thermal: intel: hfi: Add syscore callbacks for system-wide PM
  thermal: gov_power_allocator: avoid inability to reset a cdev
  thermal: helpers: Rearrange thermal_cdev_set_cur_state()
  thermal: netlink: Rework notify API for cooling devices
  thermal: core: Use kstrdup_const() during cooling device registration
  thermal/debugfs: Add thermal debugfs information for mitigation episodes
  thermal/debugfs: Add thermal cooling device debugfs information
  thermal: netlink: Pass thermal zone pointer to notify routines
  thermal: netlink: Drop thermal_notify_tz_trip_add/delete()
  thermal: netlink: Pass pointers to thermal_notify_tz_trip_up/down()
  thermal: netlink: Pass pointers to thermal_notify_tz_trip_change()

Author: torvalds

drivers/thermal/Kconfig

@@ -33,6 +33,13 @@ config THERMAL_STATISTICS
 
 	  If in doubt, say N.
 
+config THERMAL_DEBUGFS
+	bool "Thermal subsystem debug support"
+	depends on DEBUG_FS
+	help
+	  Say Y to allow the thermal subsystem to collect diagnostic
+	  information that can be accessed via debugfs.
+
 config THERMAL_EMERGENCY_POWEROFF_DELAY_MS
 	int "Emergency poweroff delay in milli-seconds"
 	default 0

drivers/thermal/Makefile

@@ -10,6 +10,8 @@ thermal_sys-y			+= thermal_trip.o thermal_helpers.o
 # netlink interface to manage the thermal framework
 thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 
+thermal_sys-$(CONFIG_THERMAL_DEBUGFS)	+= thermal_debugfs.o
+
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o

drivers/thermal/gov_power_allocator.c

@@ -762,7 +762,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz,
 
 	trip = params->trip_switch_on;
 	if (trip && tz->temperature < trip->temperature) {
-		update = tz->last_temperature >= trip->temperature;
+		update = tz->passive;
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz, update);

drivers/thermal/intel/intel_hfi.c

@@ -35,7 +35,9 @@
 #include <linux/processor.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/suspend.h>
 #include <linux/string.h>
+#include <linux/syscore_ops.h>
 #include <linux/topology.h>
 #include <linux/workqueue.h>
 
@@ -571,6 +573,30 @@ static __init int hfi_parse_features(void)
 	return 0;
 }
 
+static void hfi_do_enable(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();
+}
+
+static int hfi_do_disable(void)
+{
+	/* No locking needed. There is no concurrency with CPU offline. */
+	hfi_disable();
+
+	return 0;
+}
+
+static struct syscore_ops hfi_pm_ops = {
+	.resume = hfi_do_enable,
+	.suspend = hfi_do_disable,
+};
+
 void __init intel_hfi_init(void)
 {
 	struct hfi_instance *hfi_instance;
@@ -602,6 +628,8 @@ void __init intel_hfi_init(void)
 	if (!hfi_updates_wq)
 		goto err_nomem;
 
+	register_syscore_ops(&hfi_pm_ops);
+
 	return;
 
 err_nomem:

drivers/thermal/thermal_core.c

@@ -211,7 +211,7 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *tz,
 	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_governor_lock);
 
-	thermal_notify_tz_gov_change(tz->id, policy);
+	thermal_notify_tz_gov_change(tz, policy);
 
 	return ret;
 }
@@ -381,9 +381,8 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * 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);
+			thermal_notify_tz_trip_up(tz, trip);
+			thermal_debug_tz_trip_up(tz, trip);
 			trip->threshold = trip->temperature - trip->hysteresis;
 		} else {
 			trip->threshold = trip->temperature;
@@ -400,9 +399,8 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 		 * the trip.
 		 */
 		if (tz->temperature < trip->temperature - trip->hysteresis) {
-			thermal_notify_tz_trip_down(tz->id,
-						    thermal_zone_trip_id(tz, trip),
-						    tz->temperature);
+			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;
@@ -434,6 +432,7 @@ 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)
@@ -505,9 +504,9 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	mutex_unlock(&tz->lock);
 
 	if (mode == THERMAL_DEVICE_ENABLED)
-		thermal_notify_tz_enable(tz->id);
+		thermal_notify_tz_enable(tz);
 	else
-		thermal_notify_tz_disable(tz->id);
+		thermal_notify_tz_disable(tz);
 
 	return ret;
 }
@@ -846,7 +845,7 @@ static void thermal_release(struct device *dev)
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
 		thermal_cooling_device_destroy_sysfs(cdev);
-		kfree(cdev->type);
+		kfree_const(cdev->type);
 		ida_free(&thermal_cdev_ida, cdev->id);
 		kfree(cdev);
 	}
@@ -918,7 +917,7 @@ __thermal_cooling_device_register(struct device_node *np,
 	cdev->id = ret;
 	id = ret;
 
-	cdev->type = kstrdup(type ? type : "", GFP_KERNEL);
+	cdev->type = kstrdup_const(type ? type : "", GFP_KERNEL);
 	if (!cdev->type) {
 		ret = -ENOMEM;
 		goto out_ida_remove;
@@ -964,12 +963,14 @@ __thermal_cooling_device_register(struct device_node *np,
 
 	mutex_unlock(&thermal_list_lock);
 
+	thermal_debug_cdev_add(cdev);
+
 	return cdev;
 
 out_cooling_dev:
 	thermal_cooling_device_destroy_sysfs(cdev);
 out_cdev_type:
-	kfree(cdev->type);
+	kfree_const(cdev->type);
 out_ida_remove:
 	ida_free(&thermal_cdev_ida, id);
 out_kfree_cdev:
@@ -1170,6 +1171,8 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 	if (!cdev)
 		return;
 
+	thermal_debug_cdev_remove(cdev);
+
 	mutex_lock(&thermal_list_lock);
 
 	if (!thermal_cooling_device_present(cdev)) {
@@ -1411,7 +1414,9 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	if (atomic_cmpxchg(&tz->need_update, 1, 0))
 		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
-	thermal_notify_tz_create(tz->id, tz->type);
+	thermal_notify_tz_create(tz);
+
+	thermal_debug_tz_add(tz);
 
 	return tz;
 
@@ -1470,14 +1475,13 @@ EXPORT_SYMBOL_GPL(thermal_zone_device);
  */
 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 {
-	int tz_id;
 	struct thermal_cooling_device *cdev;
 	struct thermal_zone_device *pos = NULL;
 
 	if (!tz)
 		return;
 
-	tz_id = tz->id;
+	thermal_debug_tz_remove(tz);
 
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
@@ -1514,7 +1518,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
 	put_device(&tz->device);
 
-	thermal_notify_tz_delete(tz_id);
+	thermal_notify_tz_delete(tz);
 
 	wait_for_completion(&tz->removal);
 	kfree(tz);
@@ -1636,6 +1640,8 @@ static int __init thermal_init(void)
 {
 	int result;
 
+	thermal_debug_init();
+
 	result = thermal_netlink_init();
 	if (result)
 		goto error;

drivers/thermal/thermal_core.h

@@ -13,6 +13,7 @@
 #include <linux/thermal.h>
 
 #include "thermal_netlink.h"
+#include "thermal_debugfs.h"
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)