Android中Linux suspend/resume流程

Android中Linux suspend/resume流程

首先我们从linux kernel 的suspend说起，不管你是使用echo mem > /sys/power/state 或者使用你的开发板已经拥有的power key 都可以实现系统进入suspend的功能，这是suspend的基础，即控制系统使suspend得到执行的机会，这里相信大家都可以理解，不再过多说明。

那么suspend得到了执行的机会又是怎么一步一步开始往下执行的呢？现在就开始我们的系统的电源管理之旅：

我们就通过echo mem > /sys/power/state这种方式来看，这样更容易被理解，位于/sys/power下面的这个state，做driver不知道那可说不过去，我们就看看这个state是在哪个地方创建的吧

kernel/kernel/power/suspend.c

static int __init pm_init(void)
{
	int error = pm_start_workqueue();
	if (error)
		return error;
	hibernate_image_size_init();
	hibernate_reserved_size_init();
	power_kobj = kobject_create_and_add("power", NULL);
	if (!power_kobj)
		return -ENOMEM;
	return sysfs_create_group(power_kobj, &attr_group);
}

core_initcall(pm_init);

这段代码很少却很重要，我关心的是他确实为我们在sys目录下先建了一个power目录，然后，return时创建了很多接口，其中一个就是state，以下是接口定义

static struct attribute * g[] = {
	&state_attr.attr,
#ifdef CONFIG_PM_TRACE
	&pm_trace_attr.attr,
	&pm_trace_dev_match_attr.attr,
#endif
#ifdef CONFIG_PM_SLEEP
	&pm_async_attr.attr,
	&wakeup_count_attr.attr,
#ifdef CONFIG_PM_DEBUG
	&pm_test_attr.attr,
#endif
#ifdef CONFIG_USER_WAKELOCK
	&wake_lock_attr.attr,
	&wake_unlock_attr.attr,
#endif
#endif
	NULL,
};

static struct attribute_group attr_group = {
	.attrs = g,
};

上面你可以看到了这些接口了

我们在echo mem > /sys/power/state，或调用的我们的接口函数state_store，suspend也就才真正开始走出第一步

static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
			   const char *buf, size_t n)
{
#ifdef CONFIG_SUSPEND
#ifdef CONFIG_EARLYSUSPEND
	suspend_state_t state = PM_SUSPEND_ON;
#else
	suspend_state_t state = PM_SUSPEND_STANDBY;
#endif
	const char * const *s;
#endif
	char *p;
	int len;
	int error = -EINVAL;

	p = memchr(buf, '
', n);
	len = p ? p - buf : n;

	/* First, check if we are requested to hibernate */
	if (len == 4 && !strncmp(buf, "disk", len)) {
		error = hibernate();
                goto Exit;
	}

#ifdef CONFIG_SUSPEND
	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
			break;
	}
	if (state < PM_SUSPEND_MAX && *s)
#ifdef CONFIG_EARLYSUSPEND
		if (state == PM_SUSPEND_ON || valid_state(state)) {
			error = 0;
			request_suspend_state(state);
		}
#else
		error = enter_state(state);
#endif
#endif

 Exit:
	return error ? error : n;
}

这里我们echo mem > /sys/power/state， 还有一种echo on > /sys/power/state，接着state_store进入reauest_suspend_state(state)，然后如果是on的话进入late_resume_work（在执行late_resume_work之前会向系统申请main_wake_lock），如果是mem进入early_suspend_work。

reauest_suspend_state函数路径：kernel/kernel/power/earlysuspend.c

void request_suspend_state(suspend_state_t new_state)
{
	unsigned long irqflags;
	int old_sleep;

	spin_lock_irqsave(&state_lock, irqflags);
	old_sleep = state & SUSPEND_REQUESTED;
	if (debug_mask & DEBUG_USER_STATE) {
		struct timespec ts;
		struct rtc_time tm;
		getnstimeofday(&ts);
		rtc_time_to_tm(ts.tv_sec, &tm);
		pr_info("request_suspend_state: %s (%d->%d) at %lld "
			"(%d-%02d-%02d %02d:%02d:%02d.%09lu UTC)
",
			new_state != PM_SUSPEND_ON ? "sleep" : "wakeup",
			requested_suspend_state, new_state,
			ktime_to_ns(ktime_get()),
			tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
			tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
	}
	if (!old_sleep && new_state != PM_SUSPEND_ON) {
		state |= SUSPEND_REQUESTED;
		queue_work(suspend_work_queue, &early_suspend_work);
	} else if (old_sleep && new_state == PM_SUSPEND_ON) {
		state &= ~SUSPEND_REQUESTED;
		wake_lock(&main_wake_lock);
		queue_work(suspend_work_queue, &late_resume_work);
	}
	requested_suspend_state = new_state;
	spin_unlock_irqrestore(&state_lock, irqflags);
}

这里做的最重要的是就在最下面那两个分支中，决定了我们执行early_suspend_work，还是late_resume_work。这里我们走early_suspend_work这个分支接着往下看。先看看early_suspend_work怎么被调用

queue_work(suspend_work_queue, &early_suspend_work);

这是一个工作队列的调用方法，找到early_suspend_work的定义

static DECLARE_WORK(early_suspend_work, early_suspend);

这里有关于工作队列的方法，不知道就要自己去看看了，所以这里最终调用的其实是early_suspend这个方法

static void early_suspend(struct work_struct *work)
{
	struct early_suspend *pos;
	unsigned long irqflags;
	int abort = 0;

	mutex_lock(&early_suspend_lock);
	spin_lock_irqsave(&state_lock, irqflags);
	if (state == SUSPEND_REQUESTED)
		state |= SUSPENDED;
	else
		abort = 1;
	spin_unlock_irqrestore(&state_lock, irqflags);

	if (abort) {
		if (debug_mask & DEBUG_SUSPEND)
			pr_info("early_suspend: abort, state %d
", state);
		mutex_unlock(&early_suspend_lock);
		goto abort;
	}

	if (debug_mask & DEBUG_SUSPEND)
		pr_info("early_suspend: call handlers
");
	list_for_each_entry(pos, &early_suspend_handlers, link) {
		if (pos->suspend != NULL) {
			if (debug_mask & DEBUG_VERBOSE)
				pr_info("early_suspend: calling %pf
", pos->suspend);
			pos->suspend(pos);
		}
	}
	mutex_unlock(&early_suspend_lock);

	if (debug_mask & DEBUG_SUSPEND)
		pr_info("early_suspend: sync
");

	sys_sync();
abort:
	spin_lock_irqsave(&state_lock, irqflags);
	if (state == SUSPEND_REQUESTED_AND_SUSPENDED)
		wake_unlock(&main_wake_lock);
	spin_unlock_irqrestore(&state_lock, irqflags);
}

early_suspend()这个函数里会遍历early_suspend_handlers，依次执行里面的early_suspend函数,执行完所有的early_suspend后，释放main_wake_lock，进入wake_unlock函数。

wake_unlock(&main_wake_lock);

这里还是说一下吧，这个main_wake_lock是个什么东西，路径：kernel/kernel/power/wakelock.c

struct wake_lock main_wake_lock;

看他的初始化

wake_lock_init(&main_wake_lock, WAKE_LOCK_SUSPEND, "main");

wake_lock(&main_wake_lock);

首先初始化，然后lock，等待unlock

对于一个lock进入wake_unlock，首先会将lock从原链表中删除(active_wake_locks)，然后加入inactive_locks链表中。

void wake_unlock(struct wake_lock *lock)
{
	int type;
	unsigned long irqflags;
	spin_lock_irqsave(&list_lock, irqflags);
	type = lock->flags & WAKE_LOCK_TYPE_MASK;
#ifdef CONFIG_WAKELOCK_STAT
	wake_unlock_stat_locked(lock, 0);
#endif
	if (debug_mask & DEBUG_WAKE_LOCK)
		pr_info("wake_unlock: %s
", lock->name);
	lock->flags &= ~(WAKE_LOCK_ACTIVE | WAKE_LOCK_AUTO_EXPIRE);
	list_del(&lock->link);
	list_add(&lock->link, &inactive_locks);
	if (type == WAKE_LOCK_SUSPEND) {
		long has_lock = has_wake_lock_locked(type);
		if (has_lock > 0) {
			if (debug_mask & DEBUG_EXPIRE)
				pr_info("wake_unlock: %s, start expire timer, "
					"%ld
", lock->name, has_lock);
			mod_timer(&expire_timer, jiffies + has_lock);
		} else {
			if (del_timer(&expire_timer))
				if (debug_mask & DEBUG_EXPIRE)
					pr_info("wake_unlock: %s, stop expire "
						"timer
", lock->name);
			if (has_lock == 0)
				queue_work(suspend_work_queue, &suspend_work);
		}
		if (lock == &main_wake_lock) {
			if (debug_mask & DEBUG_SUSPEND)
				print_active_locks(WAKE_LOCK_SUSPEND);
#ifdef CONFIG_WAKELOCK_STAT
			update_sleep_wait_stats_locked(0);
#endif
		}
	}
	spin_unlock_irqrestore(&list_lock, irqflags);
}

对于释放锁，上面两个过程就结束了，但是如果这个锁的类型是WAKE_LOCK_SUSPEND，那么还需要执行一些操作，判断是否可以进入睡眠。首先调has_wake_lock_locked(type)去查找是否还有这种类型的锁,会遍历active_wake_locks[type]链表，如果在这个链表中一检测中有锁，而且该锁不是超时锁，那么就返回-1。如果是超时锁，且已经超时了，那就去释放这个锁，如果没超时就得到一个max_timeout，然后返回max_timeout。接着就会回到wake_unlock函数中,调用mod_timer(&expire_timer,jiffies +has_lock);has_lock就是前面返回的max_timeout，这句话的意思就是向系统中再添加定时器,定时时间就是最大的超时时间.expire_timer的操作函数是expire_wake_locks,这里会去检测还有没有锁，没有的话就进入suspend_work，执行suspend，进入睡眠流程。上面wake_unlock中如果没有检测到锁，也会执行suspend。在suspend函数中又会通过has_wake_lock去检测有没有锁，有锁就直接返回。

queue_work(suspend_work_queue, &suspend_work);

又是一个工作队列，看看他的定义，找到他的处理过程

static DECLARE_WORK(suspend_work, suspend);

所以他真正执行的是suspend这个方法

static void suspend(struct work_struct *work)
{
	int ret;
	int entry_event_num;
	struct timespec ts_entry, ts_exit;

	if (has_wake_lock(WAKE_LOCK_SUSPEND)) {
		if (debug_mask & DEBUG_SUSPEND)
			pr_info("suspend: abort suspend
");
		return;
	}

	entry_event_num = current_event_num;
	sys_sync();
	if (debug_mask & DEBUG_SUSPEND)
		pr_info("suspend: enter suspend
");
	getnstimeofday(&ts_entry);
	ret = pm_suspend(requested_suspend_state);
	getnstimeofday(&ts_exit);

	if (debug_mask & DEBUG_EXIT_SUSPEND) {
		struct rtc_time tm;
		rtc_time_to_tm(ts_exit.tv_sec, &tm);
		pr_info("suspend: exit suspend, ret = %d "
			"(%d-%02d-%02d %02d:%02d:%02d.%09lu UTC)
", ret,
			tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
			tm.tm_hour, tm.tm_min, tm.tm_sec, ts_exit.tv_nsec);
	}

	if (ts_exit.tv_sec - ts_entry.tv_sec <= 1) {
		++suspend_short_count;

		if (suspend_short_count == SUSPEND_BACKOFF_THRESHOLD) {
			suspend_backoff();
			suspend_short_count = 0;
		}
	} else {
		suspend_short_count = 0;
	}

	if (current_event_num == entry_event_num) {
		if (debug_mask & DEBUG_SUSPEND)
			pr_info("suspend: pm_suspend returned with no event
");
		wake_lock_timeout(&unknown_wakeup, HZ / 2);
	}
}

suspend函数中，通过pm_suspend(requested_suspend_state)进入suspend操作。这个里面也有唤醒操作，只有等唤醒后才会跳出pm_suspend，跳出后会打印log：suspend:exit suspend, ret =pm_suspend就是判断传入的state是否符合suspend,符合就调用enter_state(state)，到现在开始才进入了linux标准的suspend流程。

pm_suspend的路径：kernel/kernel/power/suspend.c

int pm_suspend(suspend_state_t state)
{
	if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX)
		return enter_state(state);
	return -EINVAL;
}
EXPORT_SYMBOL(pm_suspend);

enter_state这个函数主要有三个函数调用，分别是suspend_prepare,suspend_devices_and_enter,suspend_finish。

/**
 *	enter_state - Do common work of entering low-power state.
 *	@state:		pm_state structure for state we're entering.
 *
 *	Make sure we're the only ones trying to enter a sleep state. Fail
 *	if someone has beat us to it, since we don't want anything weird to
 *	happen when we wake up.
 *	Then, do the setup for suspend, enter the state, and cleaup (after
 *	we've woken up).
 */
int enter_state(suspend_state_t state)
{
	int error;

	if (!valid_state(state))
		return -ENODEV;

	if (!mutex_trylock(&pm_mutex))
		return -EBUSY;

	printk(KERN_INFO "PM: Syncing filesystems ... ");
	sys_sync();
	printk("done.
");

	pr_debug("PM: Preparing system for %s sleep
", pm_states[state]);
	error = suspend_prepare();
	if (error)
		goto Unlock;

	if (suspend_test(TEST_FREEZER))
		goto Finish;

	pr_debug("PM: Entering %s sleep
", pm_states[state]);
	pm_restrict_gfp_mask();
	error = suspend_devices_and_enter(state);
	pm_restore_gfp_mask();

 Finish:
	pr_debug("PM: Finishing wakeup.
");
	suspend_finish();
 Unlock:
	mutex_unlock(&pm_mutex);
	return error;
}

suspend_prepare做一些睡眠的准备工作

suspend_devices_and_enter就是真正的设备进入睡眠

suspend_finish唤醒后进行的操作。

下面来一个一个分析：

suspend_prepare中首先通过pm_prepare_console，给suspend分配一个虚拟终端来输出信息；接着通过pm_notifier_call_chain来广播一个系统进入suspend的通报；关闭用户态的helper进程；最后通过suspend_freeze_processes来冻结用户态进程，最后会尝试释放一些内存。在suspend_freeze_processes()函数中调用了freeze_processes()函数，而freeze_processes()函数中又调用了try_to_freeze_tasks()来完成冻结任务。在冻结过程中,会判断当前进程是否有wake_lock,若有,则冻结失败，函数会放弃冻结。

执行完上面的操作后再次回到enter_state函数中，下面开始调用suspend_devices_and_enter()函数让外设进入休眠。在suspend_devices_and_enter()中首先调用关于平台的suspend_ops->begin，接着通过suspend_console来关闭console，也可以通过改变一个flag来使这个函数无效。接着调用dpm_suspend_start。dpm_suspend_start中会执行device_prepare和device_suspend,这两个函数都是调用pm接口里的prepare和suspend函数(其实这里就开始通过总线的接口来执行驱动的suspend函数了，通过bus->pm->suspend)。接着回到suspend_devices_and_enter中调用suspend_enter(state);在suspend_enter中，首先调用平台相关的suspend_ops->prepare，接着执行dpm_suspend_noirq()调用pm接口里的pm->suspend_noirq，回到suspend_enter，接着调用suspend_ops->prepare_late，接下来多cpu中非启动的cpu通过函数disable_nonboot_cpus()被关闭，然后通过调用arch_suspend_disable_irqs()关闭本地中断。再后来才到睡眠设备的操作，sysdev_suspend(PMSG_SUSPEND)，这样就会进入sysdev_driver.suspend阶段。最后调用suspend_ops->enter()，这里就开始执行到睡眠的最后一步了，执行平台相关的睡眠。在平台睡眠的代码中主要是通过suspend_in_iram(suspend_param1)来执行一段汇编代码，最终在汇编中睡死。唤醒的步骤与睡眠的步骤相反，cpu有电后会首先从汇编中起来，接着回到suspend_enter函数中，执行suspend_ops->enter()返回后的一些唤醒代码，这边就不再去说了，基本是按照上面的逆序来操作的。

上面的过程在我看来还是很复杂的，power management 要好好研究一下了

resume的过程

唤醒的时候，程序从suspend_devices_and_enter函数中出来后，开始执行suspend_finish，接着就会从enter_state中退出来，返回pm_suspend，然后又从pm_suspend返回到wakelock.c中的suspend()，在这里接下来就会打印出”suspend:exit suspend, ret“这些log。

下面是网上大牛画的一张睡眠唤醒的流程图，总结的很是到位，非常感谢，分享链接：http://blog.csdn.net/android_huber/article/details/7399476