@@ -40,6 +40,21 @@ config THERMAL_DEBUGFS
Say Y to allow the thermal subsystem to collect diagnostic
information that can be accessed via debugfs.
+config THERMAL_THRESHOLDS
+ bool "Thermal thresholds notification mechanism"
+ depends on THERMAL_NETLINK
+ help
+ The userspace implements thermal engines which needs to get
+ notified when temperature thresholds are crossed the way up
+ and down. These notification allow them to analyze the
+ thermal situation of the platform and take decision to
+ fulfill specific thermal profile like 'balanced',
+ 'performance' or 'power saving'. In addition, the
+ temperature of the skin sensor is very important in this
+ case and must be monitored as well.
+
+ If in doubt, say Y
+
config THERMAL_EMERGENCY_POWEROFF_DELAY_MS
int "Emergency poweroff delay in milli-seconds"
default 0
@@ -7,6 +7,9 @@ obj-$(CONFIG_THERMAL) += thermal_sys.o
thermal_sys-y += thermal_core.o thermal_sysfs.o
thermal_sys-y += thermal_trip.o thermal_helpers.o
+# thermal thresholds
+thermal_sys-$(CONFIG_THERMAL_THRESHOLDS) += thermal_thresholds.o
+
# netlink interface to manage the thermal framework
thermal_sys-$(CONFIG_THERMAL_NETLINK) += thermal_netlink.o
@@ -13,6 +13,7 @@
#include <linux/thermal.h>
#include "thermal_netlink.h"
+#include "thermal_thresholds.h"
#include "thermal_debugfs.h"
struct thermal_trip_desc {
@@ -132,6 +133,9 @@ struct thermal_zone_device {
bool resuming;
#ifdef CONFIG_THERMAL_DEBUGFS
struct thermal_debugfs *debugfs;
+#endif
+#ifdef CONFIG_THERMAL_THRESHOLDS
+ struct thresholds *thresholds;
#endif
struct thermal_trip_desc trips[] __counted_by(num_trips);
};
new file mode 100644
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2024 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Thermal thresholds
+ */
+#include <linux/list.h>
+#include <linux/list_sort.h>
+
+#include "thermal_core.h"
+
+struct thresholds {
+ struct list_head list;
+};
+
+int thermal_thresholds_init(struct thermal_zone_device *tz)
+{
+ struct thresholds *thresholds;
+
+ thresholds = kmalloc(sizeof(*thresholds), GFP_KERNEL);
+ if (!thresholds)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&thresholds->list);
+ tz->thresholds = thresholds;
+
+ return 0;
+}
+
+void thermal_thresholds_exit(struct thermal_zone_device *tz)
+{
+ thermal_thresholds_flush(tz);
+ kfree(tz->thresholds);
+ tz->thresholds = NULL;
+}
+
+static int __thermal_thresholds_cmp(void *data,
+ const struct list_head *l1,
+ const struct list_head *l2)
+{
+ struct threshold *t1 = container_of(l1, struct threshold, list);
+ struct threshold *t2 = container_of(l2, struct threshold, list);
+
+ return t1->temperature - t2->temperature;
+}
+
+static struct threshold *__thermal_thresholds_find(const struct thresholds *thresholds, int temperature)
+{
+ struct threshold *t;
+
+ list_for_each_entry(t, &thresholds->list, list)
+ if (t->temperature == temperature)
+ return t;
+
+ return NULL;
+}
+
+static bool __thermal_threshold_is_crossed(struct threshold *threshold, int temperature,
+ int last_temperature, int direction,
+ int *low, int *high)
+{
+ if (temperature > threshold->temperature && threshold->temperature > *low &&
+ (THERMAL_THRESHOLD_WAY_DOWN & threshold->direction))
+ *low = threshold->temperature;
+
+ if (temperature < threshold->temperature && threshold->temperature < *high &&
+ (THERMAL_THRESHOLD_WAY_UP & threshold->direction))
+ *high = threshold->temperature;
+
+ if (temperature < threshold->temperature &&
+ last_temperature >= threshold->temperature &&
+ (threshold->direction & direction))
+ return true;
+
+ if (temperature >= threshold->temperature &&
+ last_temperature < threshold->temperature &&
+ (threshold->direction & direction))
+ return true;
+
+ return false;
+}
+
+static bool thermal_thresholds_handle_raising(struct thresholds *thresholds, int temperature,
+ int last_temperature, int *low, int *high)
+{
+ struct threshold *t;
+
+ list_for_each_entry(t, &thresholds->list, list) {
+ if (__thermal_threshold_is_crossed(t, temperature, last_temperature,
+ THERMAL_THRESHOLD_WAY_UP, low, high))
+ return true;
+ }
+
+ return false;
+}
+
+static bool thermal_thresholds_handle_dropping(struct thresholds *thresholds, int temperature,
+ int last_temperature, int *low, int *high)
+{
+ struct threshold *t;
+
+ list_for_each_entry_reverse(t, &thresholds->list, list) {
+ if (__thermal_threshold_is_crossed(t, temperature, last_temperature,
+ THERMAL_THRESHOLD_WAY_DOWN, low, high))
+ return true;
+ }
+
+ return false;
+}
+
+void thermal_thresholds_flush(struct thermal_zone_device *tz)
+{
+ struct thresholds *thresholds = tz->thresholds;
+ struct threshold *entry, *tmp;
+
+ lockdep_assert_held(&tz->lock);
+
+ list_for_each_entry_safe(entry, tmp, &thresholds->list, list) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+
+ __thermal_zone_device_update(tz, THERMAL_THRESHOLD_FLUSHED);
+}
+
+int thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high)
+{
+ struct thresholds *thresholds = tz->thresholds;
+
+ int temperature = tz->temperature;
+ int last_temperature = tz->last_temperature;
+ bool notify;
+
+ lockdep_assert_held(&tz->lock);
+
+ /*
+ * We need a second update in order to detect a threshold being crossed
+ */
+ if (last_temperature == THERMAL_TEMP_INVALID)
+ return 0;
+
+ /*
+ * The temperature is stable, so obviously we can not have
+ * crossed a threshold.
+ */
+ if (last_temperature == temperature)
+ return 0;
+
+ /*
+ * Since last update the temperature:
+ * - increased : thresholds are crossed the way up
+ * - decreased : thresholds are crossed the way down
+ */
+ if (temperature > last_temperature)
+ notify = thermal_thresholds_handle_raising(thresholds, temperature,
+ last_temperature, low, high);
+ else
+ notify = thermal_thresholds_handle_dropping(thresholds, temperature,
+ last_temperature, low, high);
+
+ if (notify)
+ pr_debug("A threshold has been crossed the way %s, with a temperature=%d, last_temperature=%d\n",
+ temperature > last_temperature ? "up" : "down", temperature, last_temperature);
+
+ return 0;
+}
+
+int thermal_thresholds_add(struct thermal_zone_device *tz, int temperature, int direction)
+{
+ struct thresholds *thresholds = tz->thresholds;
+ struct threshold *t;
+
+ lockdep_assert_held(&tz->lock);
+
+ t = __thermal_thresholds_find(thresholds, temperature);
+ if (t) {
+ if (t->direction == direction)
+ return -EEXIST;
+
+ t->direction |= direction;
+ } else {
+
+ t = kmalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&t->list);
+ t->temperature = temperature;
+ t->direction = direction;
+ list_add(&t->list, &thresholds->list);
+ list_sort(NULL, &thresholds->list, __thermal_thresholds_cmp);
+ }
+
+ __thermal_zone_device_update(tz, THERMAL_THRESHOLD_ADDED);
+
+ return 0;
+}
+
+int thermal_thresholds_delete(struct thermal_zone_device *tz, int temperature, int direction)
+{
+ struct thresholds *thresholds = tz->thresholds;
+ struct threshold *t;
+
+ lockdep_assert_held(&tz->lock);
+
+ t = __thermal_thresholds_find(thresholds, temperature);
+ if (!t)
+ return -ENOENT;
+
+ if (t->direction == direction) {
+ list_del(&t->list);
+ kfree(t);
+ } else {
+ t->direction &= ~direction;
+ }
+
+ __thermal_zone_device_update(tz, THERMAL_THRESHOLD_DELETED);
+
+ return 0;
+}
+
+int thermal_thresholds_for_each(struct thermal_zone_device *tz,
+ int (*cb)(struct threshold *, void *arg), void *arg)
+{
+ struct thresholds *thresholds = tz->thresholds;
+ struct threshold *entry;
+ int ret;
+
+ lockdep_assert_held(&tz->lock);
+
+ list_for_each_entry(entry, &thresholds->list, list) {
+ ret = cb(entry, arg);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define THERMAL_THRESHOLD_WAY_UP BIT(0)
+#define THERMAL_THRESHOLD_WAY_DOWN BIT(1)
+
+struct threshold {
+ int temperature;
+ int direction;
+ struct list_head list;
+};
+
+#ifdef CONFIG_THERMAL_THRESHOLDS
+int thermal_thresholds_init(struct thermal_zone_device *tz);
+void thermal_thresholds_exit(struct thermal_zone_device *tz);
+void thermal_thresholds_flush(struct thermal_zone_device *tz);
+int thermal_thresholds_add(struct thermal_zone_device *tz, int temperature, int direction);
+int thermal_thresholds_delete(struct thermal_zone_device *tz, int temperature, int direction);
+int thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high);
+int thermal_thresholds_for_each(struct thermal_zone_device *tz,
+ int (*cb)(struct threshold *, void *arg), void *arg);
+#else
+static inline int thermal_thresholds_init(struct thermal_zone_device *tz)
+{
+ return 0;
+}
+
+static inline void thermal_thresholds_exit(struct thermal_zone_device *tz)
+{
+ ;
+}
+
+static inline void thermal_thresholds_flush(struct thermal_zone_device *tz)
+{
+ ;
+}
+
+static inline int thermal_thresholds_add(struct thermal_zone_device *tz, int temperature, int direction)
+{
+ return 0;
+}
+
+static inline int thermal_thresholds_delete(struct thermal_zone_device *tz, int temperature, int direction)
+{
+ return 0;
+}
+
+static inline int thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high)
+{
+ return 0;
+}
+
+static inline int thermal_thresholds_for_each(struct thermal_zone_device *tz,
+ int (*cb)(struct threshold *, void *arg), void *arg)
+{
+ return 0;
+}
+#endif
@@ -55,6 +55,9 @@ enum thermal_notify_event {
THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
+ THERMAL_THRESHOLD_ADDED, /* Threshold added */
+ THERMAL_THRESHOLD_DELETED, /* Threshold deleted */
+ THERMAL_THRESHOLD_FLUSHED, /* All thresholds deleted */
};
/**
The trip points are a firmware description of the temperature limits of a specific thermal zone where we associate an action which is done by the kernel. The time resolution is low. The userspace has to deal with a more complex thermal management based on heuristics from different information coming from different places. The logic is much more complex but based on a bigger time resolution, usually one second based. The purpose of the userspace is to monitor the temperatures from different places and take actions. However, it can not be constantly reading the temperature to detect when a temperature threshold has been reached. This is especially bad for mobile or embedded system as that will lead to an unacceptable number of wakeup to check the temperature with nothing to do. On the other side, the sensors are now most of the time interrupt driven. That means the thermal framework will use the temperature trip points to program the sensor to trigger an interrupt when a temperature limit is crossed. Unfortunately, the userspace can not benefit this feature and current solutions found here and there, iow out-of-tree, are to add fake trip points in the firmware and enable the writable trip points. This is bad for different reasons, the trip points are for in-kernel actions, the semantic of their types is used by the thermal framework and by adding trip points in the device tree is a way to overcome the current limitation but tampering with how the thermal framework is supposed to work. The writable trip points is a way to adjust a temperature limit given a specific platform if the firmware is not accurate enough and TBH it is more a debug feature from my POV. The thresholds mechanism is a way to have the userspace to tell thermal framework to send a notification when a temperature limit is crossed. There is no id, no hysteresis, just the temperature and the direction of the limit crossing. That means we can be notified when a threshold is crossed the way up only, or the way down only or both ways. That allows to create hysteresis values if it is needed. A threshold can be added, deleted or flushed. The latter means all thresholds belonging to a thermal zone will be deleted. When a threshold is added: - if the same threshold (temperature and direction) exists, an error is returned - if a threshold is specified with the same temperature but a different direction, the specified direction is added - if there is no threshold with the same temperature then it is created When a threshold is deleted: - if the same threshold (temperature and direction) exists, it is deleted - if a threshold is specified with the same temperature but a different direction, the specified direction is removed - if there is no threshold with the same temperature, then an error is returned When the threshold are flushed: - All thresholds related to a thermal zone are deleted When a threshold is crossed: - the userspace does not need to know which threshold(s) have been crossed, it will be notified with the current temperature and the previous temperature - if multiple thresholds have been crossed between two updates only one notification will be send to the userspace, it is pointless to send a notification per thresholds crossed as the userspace can handle that easily when it has the temperature delta information Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> --- drivers/thermal/Kconfig | 15 ++ drivers/thermal/Makefile | 3 + drivers/thermal/thermal_core.h | 4 + drivers/thermal/thermal_thresholds.c | 240 +++++++++++++++++++++++++++ drivers/thermal/thermal_thresholds.h | 57 +++++++ include/linux/thermal.h | 3 + 6 files changed, 322 insertions(+) create mode 100644 drivers/thermal/thermal_thresholds.c create mode 100644 drivers/thermal/thermal_thresholds.h