Linux内核Thermal框架详解六、Thermal Core（5）

接前一篇文章Linux内核Thermal框架详解五、Thermal Core（4）

三、相关源码及分析

2. thermal_register_governors

（2）thermal_register_governor

上一回说到了thermal_register_governors中的thermal_register_governor函数，本篇文章继续解析此函数的后半段，即与thermal zones相关的代码。

先再贴一下完整的函数代码。在drivers/thermal/thermal_core.c中：

int thermal_register_governor(struct thermal_governor *governor)
{
	int err;
	const char *name;
	struct thermal_zone_device *pos;

	if (!governor)
		return -EINVAL;

	mutex_lock(&thermal_governor_lock);

	err = -EBUSY;
	if (!__find_governor(governor->name)) {
		bool match_default;

		err = 0;
		list_add(&governor->governor_list, &thermal_governor_list);
		match_default = !strncmp(governor->name,
					 DEFAULT_THERMAL_GOVERNOR,
					 THERMAL_NAME_LENGTH);

		if (!def_governor && match_default)
			def_governor = governor;
	}

	mutex_lock(&thermal_list_lock);

	list_for_each_entry(pos, &thermal_tz_list, node) {
		/*
		 * only thermal zones with specified tz->tzp->governor_name
		 * may run with tz->govenor unset
		 */
		if (pos->governor)
			continue;

		name = pos->tzp->governor_name;

		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
			int ret;

			ret = thermal_set_governor(pos, governor);
			if (ret)
				dev_err(&pos->device,
					"Failed to set governor %s for thermal zone %s: %d\n",
					governor->name, pos->type, ret);
		}
	}

	mutex_unlock(&thermal_list_lock);
	mutex_unlock(&thermal_governor_lock);

	return err;
}

thermal_list_lock在同文件（drivers/thermal/thermal_core.c）中定义并初始化，代码如下：

static DEFINE_MUTEX(thermal_list_lock);

接下来，list_for_each_entry在上一篇文章中已经给出了详尽的分析，可以参考前一篇文章，本文不再赘述。

thermal_tz_list同样在drivers/thermal/thermal_core.c文件中定义并初始化：

static LIST_HEAD(thermal_tz_list);

可以看到，thermal_tz_list与前篇文章的thermal_governor_list类似，也是初始的时候是一个空链表，而后往链表中添加项。那么，是在哪里添加的各个项？又添加了哪些项？是在drivers/thermal/thermal_core.c的thermal_zone_device_register函数中。代码如下：

/**
 * thermal_zone_device_register() - register a new thermal zone device
 * @type:	the thermal zone device type
 * @trips:	the number of trip points the thermal zone support
 * @mask:	a bit string indicating the writeablility of trip points
 * @devdata:	private device data
 * @ops:	standard thermal zone device callbacks
 * @tzp:	thermal zone platform parameters
 * @passive_delay: number of milliseconds to wait between polls when
 *		   performing passive cooling
 * @polling_delay: number of milliseconds to wait between polls when checking
 *		   whether trip points have been crossed (0 for interrupt
 *		   driven systems)
 *
 * This interface function adds a new thermal zone device (sensor) to
 * /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
 * thermal cooling devices registered at the same time.
 * thermal_zone_device_unregister() must be called when the device is no
 * longer needed. The passive cooling depends on the .get_trend() return value.
 *
 * Return: a pointer to the created struct thermal_zone_device or an
 * in case of error, an ERR_PTR. Caller must check return value with
 * IS_ERR*() helpers.
 */
struct thermal_zone_device *
thermal_zone_device_register(const char *type, int trips, int mask,
			     void *devdata, struct thermal_zone_device_ops *ops,
			     struct thermal_zone_params *tzp, int passive_delay,
			     int polling_delay)
{
	struct thermal_zone_device *tz;
	enum thermal_trip_type trip_type;
	int trip_temp;
	int id;
	int result;
	int count;
	struct thermal_governor *governor;

	if (!type || strlen(type) == 0) {
		pr_err("Error: No thermal zone type defined\n");
		return ERR_PTR(-EINVAL);
	}

	if (type && strlen(type) >= THERMAL_NAME_LENGTH) {
		pr_err("Error: Thermal zone name (%s) too long, should be under %d chars\n",
		       type, THERMAL_NAME_LENGTH);
		return ERR_PTR(-EINVAL);
	}

	if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips) {
		pr_err("Error: Incorrect number of thermal trips\n");
		return ERR_PTR(-EINVAL);
	}

	if (!ops) {
		pr_err("Error: Thermal zone device ops not defined\n");
		return ERR_PTR(-EINVAL);
	}

	if (trips > 0 && (!ops->get_trip_type || !ops->get_trip_temp))
		return ERR_PTR(-EINVAL);

	tz = kzalloc(sizeof(*tz), GFP_KERNEL);
	if (!tz)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&tz->thermal_instances);
	ida_init(&tz->ida);
	mutex_init(&tz->lock);
	id = ida_simple_get(&thermal_tz_ida, 0, 0, GFP_KERNEL);
	if (id < 0) {
		result = id;
		goto free_tz;
	}

	tz->id = id;
	strlcpy(tz->type, type, sizeof(tz->type));

	result = dev_set_name(&tz->device, "thermal_zone%d", tz->id);
	if (result)
		goto remove_id;

	if (!ops->critical)
		ops->critical = thermal_zone_device_critical;

	tz->ops = ops;
	tz->tzp = tzp;
	tz->device.class = &thermal_class;
	tz->devdata = devdata;
	tz->trips = trips;

	thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
	thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);

	/* sys I/F */
	/* Add nodes that are always present via .groups */
	result = thermal_zone_create_device_groups(tz, mask);
	if (result)
		goto remove_id;

	/* A new thermal zone needs to be updated anyway. */
	atomic_set(&tz->need_update, 1);

	result = device_register(&tz->device);
	if (result)
		goto release_device;

	for (count = 0; count < trips; count++) {
		if (tz->ops->get_trip_type(tz, count, &trip_type) ||
		    tz->ops->get_trip_temp(tz, count, &trip_temp) ||
		    !trip_temp)
			set_bit(count, &tz->trips_disabled);
	}

	/* Update 'this' zone's governor information */
	mutex_lock(&thermal_governor_lock);

	if (tz->tzp)
		governor = __find_governor(tz->tzp->governor_name);
	else
		governor = def_governor;

	result = thermal_set_governor(tz, governor);
	if (result) {
		mutex_unlock(&thermal_governor_lock);
		goto unregister;
	}

	mutex_unlock(&thermal_governor_lock);

	if (!tz->tzp || !tz->tzp->no_hwmon) {
		result = thermal_add_hwmon_sysfs(tz);
		if (result)
			goto unregister;
	}

	mutex_lock(&thermal_list_lock);
	list_add_tail(&tz->node, &thermal_tz_list);
	mutex_unlock(&thermal_list_lock);

	/* Bind cooling devices for this zone */
	bind_tz(tz);

	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);

	thermal_zone_device_init(tz);
	/* Update the new thermal zone and mark it as already updated. */
	if (atomic_cmpxchg(&tz->need_update, 1, 0))
		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);

	thermal_notify_tz_create(tz->id, tz->type);

	return tz;

unregister:
	device_del(&tz->device);
release_device:
	put_device(&tz->device);
	tz = NULL;
remove_id:
	ida_simple_remove(&thermal_tz_ida, id);
free_tz:
	kfree(tz);
	return ERR_PTR(result);
}
EXPORT_SYMBOL_GPL(thermal_zone_device_register);

thermal_zone_device_register函数实现的功能是：注册一个新的thermal zone设备。

thermal_zone_device_register函数在内核源码中有很多处调用，例如：drivers/thermal/thermal_of.c中的of_parse_thermal_zones函数、drivers/acpi/thermal.c中的acpi_thermal_register_thermal_zone函数等等。针对于thermal_zone_device_register函数的详细解析，将放到thermal zone章节中进行。

注意：这里有一个问题。由于thermal_register_governors函数先于of_parse_thermal_zones函数被调用，因此在目前调用thermal_register_governors中的thermal_register_governor函数时，还没到调用of_parse_thermal_zones函数，故drivers/thermal/下的thermal zone此时还没有放到thermal_tz_list链表中来。那么当前thermal_tz_list链表中是否有数据，是由哪个在之前执行的函数添加进来的、何时添加进来的，尚有待进一步分析。

接着往下看，先要弄清楚termal_zone_device结构。struct thermal_zone_device在include/linux/thermal.h中定义，代码如下：

/**
 * 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
 * @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
 * @trips:	number of trip points the thermal zone supports
 * @trips_disabled;	bitmap for disabled trips
 * @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
 */
struct thermal_zone_device {
	int id;
	char type[THERMAL_NAME_LENGTH];
	struct device device;
	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 trips;
	unsigned long trips_disabled;	/* bitmap for disabled 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;
};

其中重点关注struct thermal_zone_params *tzp成员。struct thermal_zone_params也在include/linux/thermal.h中定义，代码如下：

/* Structure to define Thermal Zone parameters */
struct thermal_zone_params {
	char governor_name[THERMAL_NAME_LENGTH];

	/*
	 * a boolean to indicate if the thermal to hwmon sysfs interface
	 * is required. when no_hwmon == false, a hwmon sysfs interface
	 * will be created. when no_hwmon == true, nothing will be done
	 */
	bool no_hwmon;

	int num_tbps;	/* Number of tbp entries */
	struct thermal_bind_params *tbp;

	/*
	 * Sustainable power (heat) that this thermal zone can dissipate in
	 * mW
	 */
	u32 sustainable_power;

	/*
	 * Proportional parameter of the PID controller when
	 * overshooting (i.e., when temperature is below the target)
	 */
	s32 k_po;

	/*
	 * Proportional parameter of the PID controller when
	 * undershooting
	 */
	s32 k_pu;

	/* Integral parameter of the PID controller */
	s32 k_i;

	/* Derivative parameter of the PID controller */
	s32 k_d;

	/* threshold below which the error is no longer accumulated */
	s32 integral_cutoff;

	/*
	 * @slope:	slope of a linear temperature adjustment curve.
	 * 		Used by thermal zone drivers.
	 */
	int slope;
	/*
	 * @offset:	offset of a linear temperature adjustment curve.
	 * 		Used by thermal zone drivers (default 0).
	 */
	int offset;
};

因此，thermal_register_governor函数中以下代码段的意思就比较清楚了：

int thermal_register_governor(struct thermal_governor *governor)
{
	int err;
	const char *name;
	struct thermal_zone_device *pos;

	……

	mutex_lock(&thermal_list_lock);

	list_for_each_entry(pos, &thermal_tz_list, node) {
		/*
		 * only thermal zones with specified tz->tzp->governor_name
		 * may run with tz->govenor unset
		 */
		if (pos->governor)
			continue;

		name = pos->tzp->governor_name;

		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
			int ret;

			ret = thermal_set_governor(pos, governor);
			if (ret)
				dev_err(&pos->device,
					"Failed to set governor %s for thermal zone %s: %d\n",
					governor->name, pos->type, ret);
		}
	}

	mutex_unlock(&thermal_list_lock);
	mutex_unlock(&thermal_governor_lock);

	return err;
}

遍历thermal_tz_list链表，将struct thermal_zone_device中的struct thermal_zone_params *tzp中的governor_name与函数入参struct thermal_governor *governor指向的温控策略的名称做忽略大小写的字符串比较。如果名称相同，则调用thermal_set_governor函数。

thermal_set_governor函数同样在drivers/thermal/thermal_core.c中，代码如下：

/**
 * thermal_set_governor() - Switch to another governor
 * @tz:		a valid pointer to a struct thermal_zone_device
 * @new_gov:	pointer to the new governor
 *
 * Change the governor of thermal zone @tz.
 *
 * Return: 0 on success, an error if the new governor's bind_to_tz() failed.
 */
static int thermal_set_governor(struct thermal_zone_device *tz,
				struct thermal_governor *new_gov)
{
	int ret = 0;

	if (tz->governor && tz->governor->unbind_from_tz)
		tz->governor->unbind_from_tz(tz);

	if (new_gov && new_gov->bind_to_tz) {
		ret = new_gov->bind_to_tz(tz);
		if (ret) {
			bind_previous_governor(tz, new_gov->name);

			return ret;
		}
	}

	tz->governor = new_gov;

	return ret;
}

函数的功能是切换到另一个governor中。连通前边的分析，如果在初始化调用thermal_register_governor函数的时候，thermal_tz_list中已经与同名的governor相绑定了，那么先与之前的governor解绑（如果提供了解绑函数），之后将新的governor与此thermal zone相绑定，并且设置该thermal zone的governor为新的governor，即：tz->governor = new_gov。

从这个角度来说，也许之前thermal_tz_list确实没有任何项，因为即使有也要重新设置、重新绑定。

至此，thermal_register_governor函数就全部分析完了。