kernel对D状态（TASK_UNINTERRUPTIBLE）task在120s不被调度的检测

当打开CONFIG_DETECT_HUNG_TASK选项的时候，kernel会对处于D状态也就是TASK_UNINTERRUPTIBLE的task进行检测，如果在120s内都没有被调动就会处于D状态task的pid,ppid 和stack等信息。
其源码在kernel/hung_task.c 中
static int __init hung_task_init(void)
{
atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");

return 0;
}
subsys_initcall(hung_task_init);
直接调用kthread_run来运行watchdog 这个死循环，这个thread的name为khungtaskd
/*
* kthread which checks for tasks stuck in D state
*/
static int watchdog(void *dummy)
{
unsigned long hung_last_checked = jiffies;

set_user_nice(current, 0);

for ( ; ; ) {
//每次检测的周期可以通过sysctl_hung_task_timeout_secs来设置
unsigned long timeout = sysctl_hung_task_timeout_secs;
long t = hung_timeout_jiffies(hung_last_checked, timeout);

if (t <= 0) {
if (!atomic_xchg(&reset_hung_task, 0))
//调用check_hung_uninterruptible_tasks 来检测
check_hung_uninterruptible_tasks(timeout);
hung_last_checked = jiffies;
continue;
}
//如果能跑到这里说明没有检测到错误，睡眠sysctl_hung_task_timeout_secs 后来进行下一次检测
schedule_timeout_interruptible(t);
}

return 0;
}
继续看看check_hung_uninterruptible_tasks
static void check_hung_uninterruptible_tasks(unsigned long timeout)
{
int max_count = sysctl_hung_task_check_count;
int batch_count = HUNG_TASK_BATCHING;
struct task_struct *g, *t;

/*
* If the system crashed already then all bets are off,
* do not report extra hung tasks:
*/
if (test_taint(TAINT_DIE) || did_panic)
return;

hung_task_show_lock = false;
rcu_read_lock();
//遍历系统中所有的thread
for_each_process_thread(g, t) {
if (!max_count--)
goto unlock;
if (!--batch_count) {
batch_count = HUNG_TASK_BATCHING;
if (!rcu_lock_break(g, t))
goto unlock;
}
//只有对处于D状态也就是TASK_UNINTERRUPTIBLE的thread进行检测，最终调用check_hung_task来检测处于D状态的thread是否在规定的时间内没有被调度
/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
if (t->state == TASK_UNINTERRUPTIBLE)
check_hung_task(t, timeout);
}
unlock:
rcu_read_unlock();
if (hung_task_show_lock)
debug_show_all_locks();
}
继续看看check_hung_task
static void check_hung_task(struct task_struct *t, unsigned long timeout)
{
unsigned long switch_count = t->nvcsw + t->nivcsw;

/*
* Ensure the task is not frozen.
* Also, skip vfork and any other user process that freezer should skip.
*/
if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP)))
return;

/*
* When a freshly created task is scheduled once, changes its state to
* TASK_UNINTERRUPTIBLE without having ever been switched out once, it
* musn't be checked.
*/
if (unlikely(!switch_count))
return;
//这一句是核心，如果120s内被调度。则这个if条件成立，则在这里就返回了
if (switch_count != t->last_switch_count) {
t->last_switch_count = switch_count;
return;
}

trace_sched_process_hang(t);
//走到这里说明就不正常，但是如果没有定义sysctl_hung_task_warnings和sysctl_hung_task_panic的话，则不产生任何warning log
if (!sysctl_hung_task_warnings && !sysctl_hung_task_panic)
return;

/*
* Ok, the task did not get scheduled for more than 2 minutes,
* complain:
*/
//如果定义了sysctl_hung_task_warnings。则显示下面的log 显示警告，并调用sched_show_task显示当前task的pid,ppid,stack等信息
if (sysctl_hung_task_warnings) {
if (sysctl_hung_task_warnings > 0)
sysctl_hung_task_warnings--;
pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",
t->comm, t->pid, timeout);
pr_err("      %s %s %.*s\n",
print_tainted(), init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
" disables this message.\n");
sched_show_task(t);
hung_task_show_lock = true;
}

touch_nmi_watchdog();
//如果定义了sysctl_hung_task_panic，则通过trigger_all_cpu_backtrace触发让所有的cpu都挂掉
if (sysctl_hung_task_panic) {
//如果定义了hung_task_show_lock，则显示系统中所有被持有的锁
if (hung_task_show_lock)
debug_show_all_locks();
trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
}
}