在pm_suspend()函数中,enter_state()函数被调用,从而进入标准linux休眠过程。
int pm_suspend(suspend_state_t state)
{
if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
return enter_state(state);
return -EINVAL;
}
在enter_state()函数中,首先检查一些状态参数,再同步文件系统,然后调用suspend_prepare()来冻结进程,最后调用suspend_devices_and_enter()让外设进入休眠。
static 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.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare();
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state);
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
在suspend_prepare()函数中,先通过pm_prepare_console();给suspend分配一个虚拟终端来输出信息,再广播一个系统进入suspend的通报,关闭用户态的helper进程,然后调用suspend_freeze_processes()来冻结进程,最后会尝试释放一些内存。
static int suspend_prepare(void)
{
int error;
unsigned int free_pages;
if (!suspend_ops || !suspend_ops->enter)
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
if (error)
goto Finish;
error = usermodehelper_disable();
if (error)
goto Finish;
if (suspend_freeze_processes()) {
error = -EAGAIN;
goto Thaw;
}
free_pages = global_page_state(NR_FREE_PAGES);
if (free_pages < FREE_PAGE_NUMBER) {
pr_debug("PM: free some memory\n");
shrink_all_memory(FREE_PAGE_NUMBER - free_pages);
if (nr_free_pages() < FREE_PAGE_NUMBER) {
error = -ENOMEM;
printk(KERN_ERR "PM: No enough memory\n");
}
}
if (!error)
return 0;
Thaw:
suspend_thaw_processes();
usermodehelper_enable();
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
return error;
}
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。
static int try_to_freeze_tasks(bool sig_only)
{
struct task_struct *g, *p;
unsigned long end_time;
unsigned int todo;
struct timeval start, end;
u64 elapsed_csecs64;
unsigned int elapsed_csecs;
unsigned int wakeup = 0;
do_gettimeofday(&start);
end_time = jiffies + TIMEOUT;
do {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
if (frozen(p) || !freezeable(p))
continue;
if (!freeze_task(p, sig_only))
continue;
/*
* Now that we've done set_freeze_flag, don't
* perturb a task in TASK_STOPPED or TASK_TRACED.
* It is "frozen enough". If the task does wake
* up, it will immediately call try_to_freeze.
*/
if (!task_is_stopped_or_traced(p) &&
!freezer_should_skip(p))
todo++;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
yield();/* Yield is okay here */
if (todo && has_wake_lock(WAKE_LOCK_SUSPEND)) {
wakeup = 1;
break;
}
if (time_after(jiffies, end_time))
break;
} while (todo);
do_gettimeofday(&end);
elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
do_div(elapsed_csecs64, NSEC_PER_SEC / 100);
elapsed_csecs = elapsed_csecs64;
if (todo) {
/* This does not unfreeze processes that are already frozen
* (we have slightly ugly calling convention in that respect,
* and caller must call thaw_processes() if something fails),
* but it cleans up leftover PF_FREEZE requests.
*/
if(wakeup) {
printk("\n");
printk(KERN_ERR "Freezing of %s aborted\n",
sig_only ? "user space " : "tasks ");
}
else {
printk("\n");
printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
"(%d tasks refusing to freeze):\n",
elapsed_csecs / 100, elapsed_csecs % 100, todo);
show_state();
}
read_lock(&tasklist_lock);
do_each_thread(g, p) {
task_lock(p);
if (freezing(p) && !freezer_should_skip(p))
printk(KERN_ERR " %s\n", p->comm);
cancel_freezing(p);
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
} else {
printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100,
elapsed_csecs % 100);
}
return todo ? -EBUSY : 0;
}
到现在,所有的进程(也包括workqueue/kthread) 都已经停止了,内核态进程有可能在停止的时候握有一些信号量,所以如果这时候在外设里面去解锁这个信号量有可能会发生死锁, 所以在外设suspend()函数里面作lock/unlock锁要非常小心,建议不要在外设的suspend()里面等待锁。而且suspend的过程中,有一些log是无法输出的,所以一旦出现问题,非常难调试。
回到enter_state()函数中,再冻结进程完成后,调用suspend_devices_and_enter()函数让外设进入休眠。该函数中,首先休眠串口(之后不能再显示log,解决方法为在kernel配置选项的cmd_line中,添加”no_console_suspend”选项),再通过device_suspend()函数调用各驱动的suspend函数。
当外设进入休眠后,suspend_ops->prepare()被调用,suspend_ops是板级的PM操作(本文中粉红色的函数,依赖于具体的平台),以s3c6410为例,其注册在linux_source/arch/arm/plat-s3c64xx/pm.c中,只定义了suspend_ops->enter()函数。
static struct platform_suspend_ops s3c6410_pm_ops = {
.enter= s3c6410_pm_enter,
.valid= suspend_valid_only_mem,
};
接下来,多CPU中的非启动CPU被关闭。
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
if (!suspend_ops)
return -ENOSYS;
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
suspend_test_start();
error = device_suspend(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
goto Resume_devices;
}
if (suspend_test(TEST_PLATFORM))
goto Finish;
error = disable_nonboot_cpus();
if (!error && !suspend_test(TEST_CPUS))
suspend_enter(state);
enable_nonboot_cpus();
Finish:
if (suspend_ops->finish)
suspend_ops->finish();
Resume_devices:
suspend_test_start();
device_resume(PMSG_RESUME);
suspend_test_finish("resume devices");
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
return error;
Recover_platform:
if (suspend_ops->recover)
suspend_ops->recover();
goto Resume_devices;
}
接下来suspend_enter()被调用,该函数首先关闭IRQ,然后调用device_power_down(), 它会调用suspend_late()函数, 这个函数是系统真正进入休眠最后调用的函数, 通常会在这个函数中作最后的检查,接下来休眠所有的系统设备和总线。最后调用 suspend_pos->enter() 来使CPU进入省电状态。这时候,整个休眠过程完成,代码的执行也就停在这里了。
static int suspend_enter(suspend_state_t state)
{
int error = 0;
device_pm_lock();
#ifdef CONFIG_CPU_FREQ
cpufreq_get_cpufreq_name(0);
strcpy(governor_name, cpufreq_governor_name);
if(strnicmp(governor_name, userspace_governor, CPUFREQ_NAME_LEN)) {
cpufreq_set_policy(0, "performance");
}
#endif /* CONFIG_CPU_FREQ */
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
if ((error = device_power_down(PMSG_SUSPEND))) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
goto Done;
}
error = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
if (!suspend_test(TEST_CORE))
error = suspend_ops->enter(state);
sysdev_resume();
}
device_power_up(PMSG_RESUME);
Done:
arch_suspend_enable_irqs();
#ifdef CONFIG_CPU_FREQ
if(strnicmp(governor_name, userspace_governor, CPUFREQ_NAME_LEN)) {
cpufreq_set_policy(0, governor_name);
}
#endif /* CONFIG_CPU_FREQ */
BUG_ON(irqs_disabled());
device_pm_unlock();
return error;
}
在suspend_pos->enter()所对应的函数中,代码最终停止在pm_cpu_sleep();处。
static int s3c6410_pm_enter(suspend_state_t state)
{
……
s3c6410_pm_do_save(gpio_save, ARRAY_SIZE(gpio_save));
s3c6410_pm_do_save(irq_save, ARRAY_SIZE(irq_save));
s3c6410_pm_do_save(core_save, ARRAY_SIZE(core_save));
s3c6410_pm_do_save(sromc_save, ARRAY_SIZE(sromc_save));
/* Clear WAKEUP_STAT register for next wakeup -jc.lee */
/* If this register do not be cleared, Wakeup will be failed */
__raw_writel(__raw_readl(S3C_WAKEUP_STAT), S3C_WAKEUP_STAT);
#ifdef CONFIG_MACH_SMDK6410
/* ALL sub block "ON" before enterring sleep mode - EVT0 bug*/
__raw_writel(0xffffff00, S3C_NORMAL_CFG);
/* Open all clock gate to enter sleep mode - EVT0 bug*/
__raw_writel(0xffffffff, S3C_HCLK_GATE);
__raw_writel(0xffffffff, S3C_PCLK_GATE);
__raw_writel(0xffffffff, S3C_SCLK_GATE);
……
/* s3c6410_cpu_save will also act as our return point from when
* we resume as it saves its own register state, so use the return
* code to differentiate return from save and return from sleep */
if (s3c6410_cpu_save(regs_save) == 0) {
flush_cache_all();
pm_cpu_sleep();
}
/* restore the cpu state */
cpu_init();
__raw_writel(s3c_eint_mask_val, S3C_EINT_MASK);
/* restore the system state */
s3c6410_pm_do_restore_core(core_save, ARRAY_SIZE(core_save));
s3c6410_pm_do_restore(sromc_save, ARRAY_SIZE(sromc_save));
……
}
Android 唤醒过程如下:
如果在休眠中系统被中断或者其他事件唤醒,接下来的代码就从suspend完成的地方开始执行,以s3c6410为例,即pm.c中的s3c6410_pm_enter()中的cpu_init(),然后执行suspend_enter()的sysdev_resume()函数,唤醒系统设备和总线,使能系统中断。
static int suspend_enter(suspend_state_t state)
{
int error = 0;
device_pm_lock();
#ifdef CONFIG_CPU_FREQ
cpufreq_get_cpufreq_name(0);
strcpy(governor_name, cpufreq_governor_name);
if(strnicmp(governor_name, userspace_governor, CPUFREQ_NAME_LEN)) {
cpufreq_set_policy(0, "performance");
}
#endif /* CONFIG_CPU_FREQ */
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
if ((error = device_power_down(PMSG_SUSPEND))) {
printk(KERN_ERR "PM: Some devices failed to power down\n");
goto Done;
}
error = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
if (!suspend_test(TEST_CORE))
error = suspend_ops->enter(state); //suspend过程完成处
sysdev_resume();
}
device_power_up(PMSG_RESUME);
Done:
arch_suspend_enable_irqs();
#ifdef CONFIG_CPU_FREQ
if(strnicmp(governor_name, userspace_governor, CPUFREQ_NAME_LEN)) {
cpufreq_set_policy(0, governor_name);
}
#endif /* CONFIG_CPU_FREQ */
BUG_ON(irqs_disabled());
device_pm_unlock();
return error;
}
然后回到suspend_devices_and_enter()函数中,使能休眠时候停止掉的非启动CPU,继续唤醒每个设备,使能终端。
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
if (!suspend_ops)
return -ENOSYS;
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
suspend_test_start();
error = device_suspend(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "PM: Some devices failed to suspend\n");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
if (suspend_ops->prepare) {
error = suspend_ops->prepare();
if (error)
goto Resume_devices;
}
if (suspend_test(TEST_PLATFORM))
goto Finish;
error = disable_nonboot_cpus();
if (!error && !suspend_test(TEST_CPUS))
suspend_enter(state); //suspend过程完成处
enable_nonboot_cpus();
Finish:
if (suspend_ops->finish)
suspend_ops->finish();
Resume_devices:
suspend_test_start();
device_resume(PMSG_RESUME);
suspend_test_finish("resume devices");
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
return error;
Recover_platform:
if (suspend_ops->recover)
suspend_ops->recover();
goto Resume_devices;
}
当suspend_devices_and_enter()执行完成后,系统外设已经唤醒,但进程依然是冻结的状态,返回到enter_state函数中,调用suspend_finish()函数。
static 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.\n");
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare();
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
error = suspend_devices_and_enter(state); //suspend过程完成处
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
在suspend_finish()函数中,解冻进程和任务,使能用户空间helper进程,广播一个系统从suspend状态退出的notify,唤醒终端。
static void suspend_finish(void)
{
suspend_thaw_processes();
usermodehelper_enable();
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
}
当所有的唤醒已经结束以后,用户进程都已经开始运行了,但没点亮屏幕,唤醒通常会是以下的几种原因:
如果是来电,那么Modem会通过发送命令给rild来让rild通知WindowManager有来电响应,这样就会远程调用PowerManagerService来写”on”到 /sys/power/state 来调用late resume(),执行点亮屏幕等操作。
用户按键事件会送到WindowManager中,WindowManager会处理这些按键事件,按键分为几种情况,如果按键不是唤醒键,那么WindowManager会主动放弃wakeLock来使系统进入再次休眠;如果按键是唤醒键,那么WindowManger就会调用PowerManagerService中的接口来执行late Resume。
当”on”被写入到/sys/power/state之后,同early_suspend过程,request_suspend_state()被调用,只是执行的工作队列变为late_resume_work。在late_resume函数中,唤醒调用了early_suspend的设备。
static DECLARE_WORK(late_resume_work, late_resume);
static void late_resume(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 == SUSPENDED)
state &= ~SUSPENDED;
else
abort = 1;
spin_unlock_irqrestore(&state_lock, irqflags);
if (abort) {
if (debug_mask & DEBUG_SUSPEND)
pr_info("late_resume: abort, state %d\n", state);
goto abort;
}
if (debug_mask & DEBUG_SUSPEND)
pr_info("late_resume: call handlers\n");
list_for_each_entry_reverse(pos, &early_suspend_handlers, link)
if (pos->resume != NULL)
pos->resume(pos);
if (debug_mask & DEBUG_SUSPEND)
pr_info("late_resume: done\n");
abort:
mutex_unlock(&early_suspend_lock);
}
关于wake_lock
在上文中,已经介绍了wakelock机制,下面从代码的角度进行介绍。
wakelock有3种类型,常用为WAKE_LOCK_SUSPEND,作用是防止系统进入睡眠。其他类型不是很清楚。
enum {
WAKE_LOCK_SUSPEND, /* Prevent suspend */
WAKE_LOCK_IDLE, /* Prevent low power idle */
WAKE_LOCK_TYPE_COUNT
};
Wakelock有加锁和解锁2种操作,加锁有2种方式,第一种是永久加锁(wake_lock),这种锁必须手动的解锁;另一种是超时锁(wake_lock_timeout),这种锁在过去指定时间后,会自动解锁。
void wake_lock(struct wake_lock *lock)
{
wake_lock_internal(lock, 0, 0);
}
void wake_lock_timeout(struct wake_lock *lock, long timeout)
{
wake_lock_internal(lock, timeout, 1);
}
对于wakelock,timeout = has_timeout = 0;直接加锁后,然后退出;
static void wake_lock_internal(
struct wake_lock *lock, long timeout, int has_timeout)
{
int type;
unsigned long irqflags;
long expire_in;
spin_lock_irqsave(&list_lock, irqflags);
type = lock->flags & WAKE_LOCK_TYPE_MASK;
BUG_ON(type >= WAKE_LOCK_TYPE_COUNT);
BUG_ON(!(lock->flags & WAKE_LOCK_INITIALIZED));
#ifdef CONFIG_WAKELOCK_STAT
if (type == WAKE_LOCK_SUSPEND && wait_for_wakeup) {
if (debug_mask & DEBUG_WAKEUP)
pr_info("wakeup wake lock: %s\n", lock->name);
wait_for_wakeup = 0;
lock->stat.wakeup_count++;
}
if ((lock->flags & WAKE_LOCK_AUTO_EXPIRE) &&
(long)(lock->expires - jiffies) <= 0) {
wake_unlock_stat_locked(lock, 0);
lock->stat.last_time = ktime_get();
}
#endif
if (!(lock->flags & WAKE_LOCK_ACTIVE)) {
lock->flags |= WAKE_LOCK_ACTIVE;
#ifdef CONFIG_WAKELOCK_STAT
lock->stat.last_time = ktime_get();
#endif
}
list_del(&lock->link);
if (has_timeout) {
if (debug_mask & DEBUG_WAKE_LOCK)
pr_info("wake_lock: %s, type %d, timeout %ld.%03lu\n",
lock->name, type, timeout / HZ,
(timeout % HZ) * MSEC_PER_SEC / HZ);
lock->expires = jiffies + timeout;
lock->flags |= WAKE_LOCK_AUTO_EXPIRE;
list_add_tail(&lock->link, &active_wake_locks[type]);
} else {
if (debug_mask & DEBUG_WAKE_LOCK)
pr_info("wake_lock: %s, type %d\n", lock->name, type);
lock->expires = LONG_MAX;
lock->flags &= ~WAKE_LOCK_AUTO_EXPIRE;
list_add(&lock->link, &active_wake_locks[type]);
}
if (type == WAKE_LOCK_SUSPEND) {
current_event_num++;
#ifdef CONFIG_WAKELOCK_STAT
if (lock == &main_wake_lock)
update_sleep_wait_stats_locked(1);
else if (!wake_lock_active(&main_wake_lock))
update_sleep_wait_stats_locked(0);
#endif
if (has_timeout)
expire_in = has_wake_lock_locked(type);
else
expire_in = -1;
if (expire_in > 0) {
if (debug_mask & DEBUG_EXPIRE)
pr_info("wake_lock: %s, start expire timer, "
"%ld\n", lock->name, expire_in);
mod_timer(&expire_timer, jiffies + expire_in);
} else {
if (del_timer(&expire_timer))
if (debug_mask & DEBUG_EXPIRE)
pr_info("wake_lock: %s, stop expire timer\n",
lock->name);
if (expire_in == 0)
queue_work(suspend_work_queue, &suspend_work);
}
}
spin_unlock_irqrestore(&list_lock, irqflags);
}
而对于wake_lock_timeout,在经过timeout时间后,才加锁。再判断当前持有wakelock时,启动另一个定时器,在expire_timer的回调函数中再次判断是否持有wakelock。
static void expire_wake_locks(unsigned long data)
{
long has_lock;
unsigned long irqflags;
if (debug_mask & DEBUG_EXPIRE)
pr_info("expire_wake_locks: start\n");
spin_lock_irqsave(&list_lock, irqflags);
if (debug_mask & DEBUG_SUSPEND)
print_active_locks(WAKE_LOCK_SUSPEND);
has_lock = has_wake_lock_locked(WAKE_LOCK_SUSPEND);
if (debug_mask & DEBUG_EXPIRE)
pr_info("expire_wake_locks: done, has_lock %ld\n", has_lock);
if (has_lock == 0)
queue_work(suspend_work_queue, &suspend_work);
spin_unlock_irqrestore(&list_lock, irqflags);
}
static DEFINE_TIMER(expire_timer, expire_wake_locks, 0, 0);
在wakelock中,有2个地方可以让系统从early_suspend进入suspend状态。分别是:
l在wake_unlock中,解锁之后,若没有其他的wakelock,则进入suspend。
l在超时锁的定时器超时后,定时器的回调函数,会判断有没有其他的wakelock,若没有,则进入suspend。