suspend/resume流程
Linux的suspend机制是一种节能技术，用于将计算机的当前状态保存起来，然后进入休眠状态，以节省能源。在休眠状态下，计算机的硬件设备会停止工作，而保存的计算机状态被保存在内存或磁盘中。在用户空间向“/sys/power/state”文件分别写入“freeze”、“standby”和“mem”，即可触发它们。
例如：echo mem > /sys/power/state即可触发
流程图：
/sys/power/state节点在Main.c (kernel4.14\kernel\power)中实现，当向/sys/power/state节点中写入时即会调用如下函数state_store：
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) {
if (state == PM_SUSPEND_MEM)
state = mem_sleep_current;
error = pm_suspend(state);
} else if (state == PM_SUSPEND_MAX) {
error = hibernate();
} else {
error = -EINVAL;
}
out:
pm_autosleep_unlock();
return error ? error : n;
}
power_attr(state);从上面state_store函数分析，调用pm_suspend进入suspend
Suspend.c (kernel4.14\kernel\power)
int pm_suspend(suspend_state_t state)
{
int error;
if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
return -EINVAL;
pr_info("suspend entry (%s)\n", mem_sleep_labels[state]);
error = enter_state(state);
if (error) {
suspend_stats.fail++;
dpm_save_failed_errno(error);
} else {
suspend_stats.success++;
}
pr_info("suspend exit\n");
return error;
}pm_suspend主要调用enter_state函数
static int enter_state(suspend_state_t state)
{
int error;
trace_suspend_resume(TPS("suspend_enter"), state, true);
if (state == PM_SUSPEND_TO_IDLE) {
#ifdef CONFIG_PM_DEBUG
if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
pr_warn("Unsupported test mode for suspend to idle, 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_TO_IDLE)
s2idle_begin();
#ifndef CONFIG_SUSPEND_SKIP_SYNC
trace_suspend_resume(TPS("sync_filesystems"), 0, true);
pr_info("Syncing filesystems ... ");
sys_sync();
pr_cont("done.\n");
trace_suspend_resume(TPS("sync_filesystems"), 0, false);
#endif
pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
pm_suspend_clear_flags();
error = suspend_prepare(state);
if (error)
goto Unlock;
if (suspend_test(TEST_FREEZER))
goto Finish;
trace_suspend_resume(TPS("suspend_enter"), state, false);
pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
pm_restrict_gfp_mask();
error = suspend_devices_and_enter(state);
pm_restore_gfp_mask();
Finish:
events_check_enabled = false;
pm_pr_dbg("Finishing wakeup.\n");
suspend_finish();
Unlock:
mutex_unlock(&pm_mutex);
return error;
}
从上：
suspend_prepare主要做休眠前的准备工作
suspend_devices_and_enter设备进入休眠
suspend_prepare函数如下：
static int suspend_prepare(suspend_state_t state)
{
int error, nr_calls = 0;
if (!sleep_state_supported(state))
return -EPERM;
pm_prepare_console();
error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
if (error) {
nr_calls--;
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, nr_calls, NULL);
pm_restore_console();
return error;
}
pm_prepare_console函数的主要作用是在系统进入睡眠状态（suspend）之前，准备控制台以使其能够在唤醒时正常工作。
__pm_notifier_call_chain通知一些设备做睡眠前的准备工作
suspend_freeze_processes 函数来挂起所有用户空间进程和kernel线程。挂起进程的目的是确保在睡眠过程中，没有任何进程在访问或修改系统资源，从而避免数据不一致或冲突的情况发生。
suspend_devices_and_enter函数
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
bool wakeup = false;
if (!sleep_state_supported(state))
return -ENOSYS;
pm_suspend_target_state = state;
error = platform_suspend_begin(state);
if (error)
goto Close;
suspend_console();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
pr_err("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);
pm_suspend_target_state = PM_SUSPEND_ON;
return error;
Recover_platform:
platform_recover(state);
goto Resume_devices;
}platform_suspend_begin平台suspend 开始，一般是空
suspend_console暂停控制台子系统
suspend_test_start 是空
dpm_suspend_start 所有设备的pm suspend回调，如果某个外设的suspend回调失败，可以通过看出这个函数往下追踪log进行去定位
suspend_enter使系统进入给定的睡眠状态
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;
}dpm_prepare用于设备系统电源转换为prepare,该函数将从dpm_list中获取设备，然后通过device_prepare函数调用pm prepare回调，并帮prepare的设备放到dpm_prepared_list链表中
int dpm_prepare(pm_message_t state)
{
int error = 0;
trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
might_sleep();
/*
* Give a chance for the known devices to complete their probes, before
* disable probing of devices. This sync point is important at least
* at boot time + hibernation restore.
*/
wait_for_device_probe();
/*
* It is unsafe if probing of devices will happen during suspend or
* hibernation and system behavior will be unpredictable in this case.
* So, let's prohibit device's probing here and defer their probes
* instead. The normal behavior will be restored in dpm_complete().
*/
device_block_probing();
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);
trace_device_pm_callback_start(dev, "", state.event);
error = device_prepare(dev, state);
trace_device_pm_callback_end(dev, error);
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;
}
dpm_suspend用于设备系统电源转换为suspend，该函数将从dpm_prepared_list中获取设备，然后通过device_suspend函数调用pm suspend回调，并帮suspend的设备放到dpm_suspended_list链表中
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;
}
suspend_enter函数如下：
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;
pr_err("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;
if (state == PM_SUSPEND_TO_IDLE && pm_test_level != TEST_PLATFORM) {
s2idle_loop();
goto Platform_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;
pr_err("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;
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);
} 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;
}
下面对suspend_enter函数中各个函数进行简要分析：
platform_suspend_prepare函数如下：主要是当state状态不等于PM_SUSPEND_FREEZE 且看suspend_ops->prepare是否存在，若存在，则调用suspend_ops->prepare()，这个一般与平台有关，不同的平台此回调实现不一样。
static int platform_suspend_prepare(suspend_state_t state)
{
return state != PM_SUSPEND_FREEZE && suspend_ops->prepare ?
suspend_ops->prepare() : 0;
}
dpm_suspend_late 调用设备的ops->suspend_late回调 ，该函数将从dpm_suspended_list中获取设备，然后通过device_suspend_late函数调用pm ops->suspend_late回调，并帮late suspend的设备放到dpm_late_early_list链表中
int dpm_suspend_late(pm_message_t state)
{
ktime_t starttime = ktime_get();
int error = 0;
trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
mutex_lock(&dpm_list_mtx);
pm_transition = state;
async_error = 0;
while (!list_empty(&dpm_suspended_list)) {
struct device *dev = to_device(dpm_suspended_list.prev);
get_device(dev);
mutex_unlock(&dpm_list_mtx);
error = device_suspend_late(dev);
mutex_lock(&dpm_list_mtx);
if (!list_empty(&dev->power.entry))
list_move(&dev->power.entry, &dpm_late_early_list);
if (error) {
pm_dev_err(dev, state, " late", error);
dpm_save_failed_dev(dev_name(dev));
put_device(dev);
break;
}
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_late++;
dpm_save_failed_step(SUSPEND_SUSPEND_LATE);
dpm_resume_early(resume_event(state));
} else {
dpm_show_time(starttime, state, "late");
}
trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false);
return error;
}
platform_suspend_prepare_late函数如下：主要是当state状态等于PM_SUSPEND_FREEZE 且看freeze_ops->prepare是否存在，若存在，则调用freeze_ops->prepare，这个一般与平台有关，不同的平台此回调实现不一样。
static int platform_suspend_prepare_late(suspend_state_t state)
{
return state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->prepare ?
freeze_ops->prepare() : 0;
}
dpm_suspend_noirq调用设备的ops->suspend_noirq回调 ，该函数将从dpm_late_early_list中获取设备，然后通过device_suspend_noirq函数调用pm ops->suspend_noirq回调，并帮设备放到dpm_noirq_list链表中
int dpm_suspend_noirq(pm_message_t state)
{
ktime_t starttime = ktime_get();
int error = 0;
trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
cpuidle_pause();
device_wakeup_arm_wake_irqs();
suspend_device_irqs();
mutex_lock(&dpm_list_mtx);
pm_transition = state;
async_error = 0;
while (!list_empty(&dpm_late_early_list)) {
struct device *dev = to_device(dpm_late_early_list.prev);
get_device(dev);
mutex_unlock(&dpm_list_mtx);
error = device_suspend_noirq(dev);
mutex_lock(&dpm_list_mtx);
if (error) {
pm_dev_err(dev, state, " noirq", error);
dpm_save_failed_dev(dev_name(dev));
put_device(dev);
break;
}
if (!list_empty(&dev->power.entry))
list_move(&dev->power.entry, &dpm_noirq_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_noirq++;
dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
dpm_resume_noirq(resume_event(state));
} else {
dpm_show_time(starttime, state, "noirq");
}
trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false);
return error;
}
以上主要是休眠的过程，唤醒的过程主要是休眠的过程的相反动作，这里不做过多介绍了。
下面说一下休眠失败常遇到的情况
1、设备suspend失败
主要dpm_suspend_start返回失败，如下log可以找到对应的设备进行分析：
PM: Device a600000.ssusb failed to suspend: error -16
PM: Some devices failed to suspend, or early wake event detected
2、中断唤醒
可以通过如下函数打印log查看是哪个中断唤醒的
void pm_system_irq_wakeup(unsigned int irq_number)
{
struct irq_desc *desc;
const char *name = "null";
if (pm_wakeup_irq == 0) {
if (msm_show_resume_irq_mask) {
desc = irq_to_desc(irq_number);
if (desc == NULL)
name = "stray irq";
else if (desc->action && desc->action->name)
name = desc->action->name;
pr_warn("%s: %d triggered %s\n", __func__,
irq_number, name);
}
pm_wakeup_irq = irq_number;
pm_system_wakeup();
}
}
3、唤醒事件唤醒
可以通过如下函数打印log查看唤醒源，
bool pm_wakeup_pending(void)
{
unsigned long flags;
bool ret = false;
spin_lock_irqsave(&events_lock, flags);
if (events_check_enabled) {
unsigned int cnt, inpr;
split_counters(&cnt, &inpr);
ret = (cnt != saved_count || inpr > 0);
events_check_enabled = !ret;
}
spin_unlock_irqrestore(&events_lock, flags);
if (ret) {
pr_info("PM: Wakeup pending, aborting suspend\n");
pm_print_active_wakeup_sources();
}
return ret || pm_abort_suspend;
}