前言
根据上一节linux电源管理-概述可知，linux电源管理存在的几种方式，如何查看这几种方式，以及最后的如何睡眠唤醒等。
通过echo mem > /sys/power/state就可以达到睡眠，所以可以根据此节点的sys代码分析suspend的流程。
suspend代码分析
在手机端执行如下命令:
echo mem > /sys/power/state
state_store函数分析
static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
suspend_state_t state;
int error;
error = pm_autosleep_lock();
if (error)
return error;
if (pm_autosleep_state() > PM_SUSPEND_ON) {
error = -EBUSY;
goto out;
}
state = decode_state(buf, n);
if (state < PM_SUSPEND_MAX)
error = pm_suspend(state);
else if (state == PM_SUSPEND_MAX)
error = hibernate();
else
error = -EINVAL;
out:
pm_autosleep_unlock();
return error ? error : n;
}
int pm_autosleep_lock(void)
{
return mutex_lock_interruptible(&autosleep_lock);
}
2. 判断当前autosleep的状态，如果当前状态大于PM_SUSPEND_ON则，返回退出。关于suspend的状态如下：
#define PM_SUSPEND_ON ((__force suspend_state_t) 0)
#define PM_SUSPEND_FREEZE ((__force suspend_state_t) 1)
#define PM_SUSPEND_STANDBY ((__force suspend_state_t) 2)
#define PM_SUSPEND_MEM ((__force suspend_state_t) 3)
#define PM_SUSPEND_MIN PM_SUSPEND_FREEZE
#define PM_SUSPEND_MAX ((__force suspend_state_t) 4)pm_suspend函数分析
int pm_suspend(suspend_state_t state)
{
int error;
if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
return -EINVAL;
pm_suspend_marker("entry");
error = enter_state(state);
if (error) {
suspend_stats.fail++;
dpm_save_failed_errno(error);
} else {
suspend_stats.success++;
}
pm_suspend_marker("exit");
return error;
}
2. pm_suspend_marker("entry")
static void pm_suspend_marker(char *annotation)
{
struct timespec ts;
struct rtc_time tm;
getnstimeofday(&ts);
rtc_time_to_tm(ts.tv_sec, &tm);
pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n",
annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
}
3. 调用enter_state进入suspend的下一步，如果执行suspend成功，增加suspend.success的引用计数，否则增加suspend.fail的引用计数。
enter_state函数分析
static int enter_state(suspend_state_t state)
{
int error;
trace_suspend_resume(TPS("suspend_enter"), state, true);
if (state == PM_SUSPEND_FREEZE) {
#ifdef CONFIG_PM_DEBUG
if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
pr_warning("PM: Unsupported test mode for freeze state,"
"please choose none/freezer/devices/platform.\n");
return -EAGAIN;
}
#endif
} else if (!valid_state(state)) {
return -EINVAL;
}
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
if (state == PM_SUSPEND_FREEZE)
freeze_begin();
trace_suspend_resume(TPS("sync_filesystems"), 0, true);
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
printk("done.\n");
trace_suspend_resume(TPS("sync_filesystems"), 0, false);
pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
error = suspend_prepare(state);
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
trace_suspend_resume(TPS("suspend_enter"), state, false);
pr_debug("PM: Entering %s sleep\n", pm_states[state]);
pm_restrict_gfp_mask();
error = suspend_devices_and_enter(state);
pm_restore_gfp_mask();
Finish:
pr_debug("PM: Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}static bool valid_state(suspend_state_t state)
{
/*
* PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
* support and need to be valid to the low level
* implementation, no valid callback implies that none are valid.
*/
return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
}
内核也提供了只支持mem睡眠的函数
int suspend_valid_only_mem(suspend_state_t state)
{
return state == PM_SUSPEND_MEM;
}
2. 调用mutex_trylock获得一个mutex锁，防止在suspend的时候再次suspend。
3. 如果当前state是PM_SUSPEND_FREEZE，则调用freeze_begin做开始准备工作。
4. 同步文件系统。
5. 调用suspend_prepare做进一步suspend前期准备工作，准备控制台，冻结内核线程等。
6. 调用suspend_devices_and_enter做设备以及系统相关的susupend操作。
7. 调用suspend_finish做最后的恢复工作。
suspend_prepare函数分析
/**
* suspend_prepare - Prepare for entering system sleep state.
*
* Common code run for every system sleep state that can be entered (except for
* hibernation). Run suspend notifiers, allocate the "suspend" console and
* freeze processes.
*/
static int suspend_prepare(suspend_state_t state)
{
int error;
if (!sleep_state_supported(state))
return -EPERM;
pm_prepare_console();
error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
if (error)
goto Finish;
trace_suspend_resume(TPS("freeze_processes"), 0, true);
error = suspend_freeze_processes();
trace_suspend_resume(TPS("freeze_processes"), 0, false);
if (!error)
return 0;
suspend_stats.failed_freeze++;
dpm_save_failed_step(SUSPEND_FREEZE);
Finish:
pm_notifier_call_chain(PM_POST_SUSPEND);
pm_restore_console();
return error;
}static bool sleep_state_supported(suspend_state_t state)
{
return state == PM_SUSPEND_FREEZE || (suspend_ops && suspend_ops->enter);
}
3. 通过调用pm通知链，发送PM_SUSPEND_PREPARE消息。
int pm_notifier_call_chain(unsigned long val)
{
int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL);
return notifier_to_errno(ret);
}int register_pm_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&pm_chain_head, nb);
}
5. 接着会通过通知链恢复suspend，已经恢复控制台。
suspend_devices_and_enter函数分析
/**
* suspend_devices_and_enter - Suspend devices and enter system sleep state.
* @state: System sleep state to enter.
*/
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
bool wakeup = false;
if (!sleep_state_supported(state))
return -ENOSYS;
error = platform_suspend_begin(state);
if (error)
goto Close;
suspend_console();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
pr_err("PM: Some devices failed to suspend, or early wake event detected\n");
log_suspend_abort_reason("Some devices failed to suspend, or early wake event detected");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
if (suspend_test(TEST_DEVICES))
goto Recover_platform;
do {
error = suspend_enter(state, &wakeup);
} while (!error && !wakeup && platform_suspend_again(state));
Resume_devices:
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
trace_suspend_resume(TPS("resume_console"), state, true);
resume_console();
trace_suspend_resume(TPS("resume_console"), state, false);
Close:
platform_resume_end(state);
return error;
Recover_platform:
platform_recover(state);
goto Resume_devices;
}
2. 如果当前状态是freeze，就调用freeze_ops的begin函数。否则就调用平台相关的begin函数。这里的begin主要是各个平台pm的一些设置，每个平台的操作都不一样，这里不详细说明。
static int platform_suspend_begin(suspend_state_t state)
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin)
return freeze_ops->begin();
else if (suspend_ops->begin)
return suspend_ops->begin(state);
else
return 0;
}
3. 调用suspend_console挂起控制台，防止其它代码访问该控制台。
4. 调用suspend_test_start记录当前suspend刚开始的时候的时间，使用jiffies表示。
void suspend_test_start(void)
{
/* FIXME Use better timebase than "jiffies", ideally a clocksource.
* What we want is a hardware counter that will work correctly even
* during the irqs-are-off stages of the suspend/resume cycle...
*/
suspend_test_start_time = jiffies;
}static void platform_recover(suspend_state_t state)
{
if (state != PM_SUSPEND_FREEZE && suspend_ops->recover)
suspend_ops->recover();
}
6. 调用suspend_enter使整个系统进入suspend状态。
dpm_suspend_start函数分析
int dpm_suspend_start(pm_message_t state)
{
int error;
error = dpm_prepare(state);
if (error) {
suspend_stats.failed_prepare++;
dpm_save_failed_step(SUSPEND_PREPARE);
} else
error = dpm_suspend(state);
return error;
}
2. 调用dpm_suspend函数，执行所有设备的suspend回调函数。
dpm_prepare函数分析
/**
* dpm_prepare - Prepare all non-sysdev devices for a system PM transition.
* @state: PM transition of the system being carried out.
*
* Execute the ->prepare() callback(s) for all devices.
*/
int dpm_prepare(pm_message_t state)
{
int error = 0;
trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
might_sleep();
mutex_lock(&dpm_list_mtx);
while (!list_empty(&dpm_list)) {
struct device *dev = to_device(dpm_list.next);
get_device(dev);
mutex_unlock(&dpm_list_mtx);
error = device_prepare(dev, state);
mutex_lock(&dpm_list_mtx);
if (error) {
if (error == -EAGAIN) {
put_device(dev);
error = 0;
continue;
}
printk(KERN_INFO "PM: Device %s not prepared "
"for power transition: code %d\n",
dev_name(dev), error);
put_device(dev);
break;
}
dev->power.is_prepared = true;
if (!list_empty(&dev->power.entry))
list_move_tail(&dev->power.entry, &dpm_prepared_list);
put_device(dev);
}
mutex_unlock(&dpm_list_mtx);
trace_suspend_resume(TPS("dpm_prepare"), state.event, false);
return error;
}
void device_pm_add(struct device *dev)
{
pr_debug("PM: Adding info for %s:%s\n",
dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
mutex_lock(&dpm_list_mtx);
if (dev->parent && dev->parent->power.is_prepared)
dev_warn(dev, "parent %s should not be sleeping\n",
dev_name(dev->parent));
list_add_tail(&dev->power.entry, &dpm_list);
mutex_unlock(&dpm_list_mtx);
}
3. 设置该设备的is_prepared标志位，然后将该设备添加到dom_prepared_list链表中。
device_prepare函数分析
static int device_prepare(struct device *dev, pm_message_t state)
{
int (*callback)(struct device *) = NULL;
char *info = NULL;
int ret = 0;
if (dev->power.syscore)
return 0;
/*
* If a device's parent goes into runtime suspend at the wrong time,
* it won't be possible to resume the device. To prevent this we
* block runtime suspend here, during the prepare phase, and allow
* it again during the complete phase.
*/
pm_runtime_get_noresume(dev);
device_lock(dev);
dev->power.wakeup_path = device_may_wakeup(dev);
if (dev->pm_domain) {
info = "preparing power domain ";
callback = dev->pm_domain->ops.prepare;
} else if (dev->type && dev->type->pm) {
info = "preparing type ";
callback = dev->type->pm->prepare;
} else if (dev->class && dev->class->pm) {
info = "preparing class ";
callback = dev->class->pm->prepare;
} else if (dev->bus && dev->bus->pm) {
info = "preparing bus ";
callback = dev->bus->pm->prepare;
}
if (!callback && dev->driver && dev->driver->pm) {
info = "preparing driver ";
callback = dev->driver->pm->prepare;
}
if (callback) {
trace_device_pm_callback_start(dev, info, state.event);
ret = callback(dev);
trace_device_pm_callback_end(dev, ret);
}
device_unlock(dev);
if (ret < 0) {
suspend_report_result(callback, ret);
pm_runtime_put(dev);
return ret;
}
/*
* A positive return value from ->prepare() means "this device appears
* to be runtime-suspended and its state is fine, so if it really is
* runtime-suspended, you can leave it in that state provided that you
* will do the same thing with all of its descendants". This only
* applies to suspend transitions, however.
*/
spin_lock_irq(&dev->power.lock);
dev->power.direct_complete = ret > 0 && state.event == PM_EVENT_SUSPEND;
spin_unlock_irq(&dev->power.lock);
return 0;
}
dpm_suspend函数分析
当对系统中的所有设备调用prepare回调函数之后，就会调用所有设备的suspend回调函数。
int dpm_suspend(pm_message_t state)
{
ktime_t starttime = ktime_get();
int error = 0;
trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
might_sleep();
cpufreq_suspend();
mutex_lock(&dpm_list_mtx);
pm_transition = state;
async_error = 0;
while (!list_empty(&dpm_prepared_list)) {
struct device *dev = to_device(dpm_prepared_list.prev);
get_device(dev);
mutex_unlock(&dpm_list_mtx);
error = device_suspend(dev);
mutex_lock(&dpm_list_mtx);
if (error) {
pm_dev_err(dev, state, "", error);
dpm_save_failed_dev(dev_name(dev));
put_device(dev);
break;
}
if (!list_empty(&dev->power.entry))
list_move(&dev->power.entry, &dpm_suspended_list);
put_device(dev);
if (async_error)
break;
}
mutex_unlock(&dpm_list_mtx);
async_synchronize_full();
if (!error)
error = async_error;
if (error) {
suspend_stats.failed_suspend++;
dpm_save_failed_step(SUSPEND_SUSPEND);
} else
dpm_show_time(starttime, state, NULL);
trace_suspend_resume(TPS("dpm_suspend"), state.event, false);
return error;
}
__device_suspend函数分析
static int __device_suspend(struct device *dev, pm_message_t state, bool async)
{
pm_callback_t callback = NULL;
char *info = NULL;
int error = 0;
struct timer_list timer;
struct dpm_drv_wd_data data;
char suspend_abort[MAX_SUSPEND_ABORT_LEN];
DECLARE_DPM_WATCHDOG_ON_STACK(wd);
dpm_wait_for_children(dev, async);
if (async_error)
goto Complete;
/*
* If a device configured to wake up the system from sleep states
* has been suspended at run time and there's a resume request pending
* for it, this is equivalent to the device signaling wakeup, so the
* system suspend operation should be aborted.
*/
if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
pm_wakeup_event(dev, 0);
if (pm_wakeup_pending()) {
pm_get_active_wakeup_sources(suspend_abort,
MAX_SUSPEND_ABORT_LEN);
log_suspend_abort_reason(suspend_abort);
async_error = -EBUSY;
goto Complete;
}
if (dev->power.syscore)
goto Complete;
data.dev = dev;
data.tsk = get_current();
init_timer_on_stack(&timer);
timer.expires = jiffies + HZ * 12;
timer.function = dpm_drv_timeout;
timer.data = (unsigned long)&data;
add_timer(&timer);
if (dev->power.direct_complete) {
if (pm_runtime_status_suspended(dev)) {
pm_runtime_disable(dev);
if (pm_runtime_suspended_if_enabled(dev))
goto Complete;
pm_runtime_enable(dev);
}
dev->power.direct_complete = false;
}
dpm_watchdog_set(&wd, dev);
device_lock(dev);
if (dev->pm_domain) {
info = "power domain ";
callback = pm_op(&dev->pm_domain->ops, state);
goto Run;
}
if (dev->type && dev->type->pm) {
info = "type ";
callback = pm_op(dev->type->pm, state);
goto Run;
}
if (dev->class) {
if (dev->class->pm) {
info = "class ";
callback = pm_op(dev->class->pm, state);
goto Run;
} else if (dev->class->suspend) {
pm_dev_dbg(dev, state, "legacy class ");
error = legacy_suspend(dev, state, dev->class->suspend,
"legacy class ");
goto End;
}
}
if (dev->bus) {
if (dev->bus->pm) {
info = "bus ";
callback = pm_op(dev->bus->pm, state);
} else if (dev->bus->suspend) {
pm_dev_dbg(dev, state, "legacy bus ");
error = legacy_suspend(dev, state, dev->bus->suspend,
"legacy bus ");
goto End;
}
}
Run:
if (!callback && dev->driver && dev->driver->pm) {
info = "driver ";
callback = pm_op(dev->driver->pm, state);
}
error = dpm_run_callback(callback, dev, state, info);
End:
if (!error) {
struct device *parent = dev->parent;
dev->power.is_suspended = true;
if (parent) {
spin_lock_irq(&parent->power.lock);
dev->parent->power.direct_complete = false;
if (dev->power.wakeup_path
&& !dev->parent->power.ignore_children)
dev->parent->power.wakeup_path = true;
spin_unlock_irq(&parent->power.lock);
}
}
device_unlock(dev);
dpm_watchdog_clear(&wd);
del_timer_sync(&timer);
destroy_timer_on_stack(&timer);
Complete:
complete_all(&dev->power.completion);
if (error)
async_error = error;
return error;
}
2. 如果此时有wakup事件发生，应该停止系统suspend。
3. 如果没有wakup事件发生，创建一个12s的定时器，然后启动定时器。如果在12s之内suspend没有处理完成，就打印call stack，导致系统panic。
static void dpm_drv_timeout(unsigned long data)
{
struct dpm_drv_wd_data *wd_data = (void *)data;
struct device *dev = wd_data->dev;
struct task_struct *tsk = wd_data->tsk;
printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev),
(dev->driver ? dev->driver->name : "no driver"));
printk(KERN_EMERG "dpm suspend stack:\n");
show_stack(tsk, NULL);
BUG();
}
5. 依次调用subsystem-level(pm_domain, type, class, bus)级别的suspend回调函数，如果subsystem-level级别的suspend回调函数都没有实现，则调用driver的suspend回调。
6. 销毁之前创建的定时器。
suspend_enter函数分析
suspend_enter函数分析
在之前对dpm_suspend_start函数进行了分析，该函数中主要是调用所有设备的prepare和suspend回调函数。而在suspend_enter主要是使系统进入到suspend中。
static int suspend_enter(suspend_state_t state, bool *wakeup)
{
char suspend_abort[MAX_SUSPEND_ABORT_LEN];
int error, last_dev;
error = platform_suspend_prepare(state);
if (error)
goto Platform_finish;
error = dpm_suspend_late(PMSG_SUSPEND);
if (error) {
last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
last_dev %= REC_FAILED_NUM;
printk(KERN_ERR "PM: late suspend of devices failed\n");
log_suspend_abort_reason("%s device failed to power down",
suspend_stats.failed_devs[last_dev]);
goto Platform_finish;
}
error = platform_suspend_prepare_late(state);
if (error)
goto Devices_early_resume;
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
last_dev %= REC_FAILED_NUM;
printk(KERN_ERR "PM: noirq suspend of devices failed\n");
log_suspend_abort_reason("noirq suspend of %s device failed",
suspend_stats.failed_devs[last_dev]);
goto Platform_early_resume;
}
error = platform_suspend_prepare_noirq(state);
if (error)
goto Platform_wake;
if (suspend_test(TEST_PLATFORM))
goto Platform_wake;
/*
* PM_SUSPEND_FREEZE equals
* frozen processes + suspended devices + idle processors.
* Thus we should invoke freeze_enter() soon after
* all the devices are suspended.
*/
if (state == PM_SUSPEND_FREEZE) {
trace_suspend_resume(TPS("machine_suspend"), state, true);
freeze_enter();
trace_suspend_resume(TPS("machine_suspend"), state, false);
goto Platform_wake;
}
error = disable_nonboot_cpus();
if (error || suspend_test(TEST_CPUS)) {
log_suspend_abort_reason("Disabling non-boot cpus failed");
goto Enable_cpus;
}
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
error = syscore_suspend();
if (!error) {
*wakeup = pm_wakeup_pending();
if (!(suspend_test(TEST_CORE) || *wakeup)) {
trace_suspend_resume(TPS("machine_suspend"),
state, true);
error = suspend_ops->enter(state);
trace_suspend_resume(TPS("machine_suspend"),
state, false);
events_check_enabled = false;
} else if (*wakeup) {
pm_get_active_wakeup_sources(suspend_abort,
MAX_SUSPEND_ABORT_LEN);
log_suspend_abort_reason(suspend_abort);
error = -EBUSY;
}
syscore_resume();
}
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
Enable_cpus:
enable_nonboot_cpus();
Platform_wake:
platform_resume_noirq(state);
dpm_resume_noirq(PMSG_RESUME);
Platform_early_resume:
platform_resume_early(state);
Devices_early_resume:
dpm_resume_early(PMSG_RESUME);
Platform_finish:
platform_resume_finish(state);
return error;
}
2. 调用dpm_suspend_late函数。此函数主要调用dpm_suspend_list中的设备的suspend_late回调函数，然后又将这些设备加入到dpm_late_early_list链表中。如果出现失败，则跳到platform_finish做恢复工作。
3. 如果当前休眠状态是PM_SUSPEND_FREEZE的话，调用freeze_ops中的prepare回调。
4. 调用dpm_suspend_noirq函数，此函数主要是从dpm_late_early_list链表中取一个设备，然后调用该设备的suspend_noirq回调，同时将该设备加入到dpm_noirq_list链表中。
5. 回调平台相关的preplate_late函数，做suspend最后关头的事情。
6. 如果休眠状态是PM_SUSPEND_FREEZE，则frozen processes + suspended devices + idle processors
7. disable所有非nonboot的CPU，失败之后启动CPU。
8. 关掉全局cpu中断，如果关掉中断，则报BUG
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
10. 如果执行成功的话，这时候系统还会调用pm_wakeup_pending检查下，是否有唤醒事件发生，如果发生停止suspend，恢复系统。
11. 这时候系统已经睡眠，如果这时候有唤醒事件发生，比如按下手机的power按键，系统又会接着suspend的地方，再次往下执行。也就是suspend的一些列反操作。
suspend/resume过程总结
如下是suspend/resume过程的简图
以上就是整个系统的suspend/resume执行过程，但是对于一般的驱动开发工程师来说主要关心的是Device Suspend和Device Resume过程。
suspend: prepare->suspend->suspend_late->suspend_noirq
resume： resume_noirq->resume_early->resume->complete
扫一扫
422
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
