/*
 * Detect Hung Task
 *
 * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state
 *
 */

#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/lockdep.h>
#include <linux/export.h>
#include <linux/sysctl.h>
#include <linux/utsname.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>

#include <trace/events/sched.h>

/*
 * The number of tasks checked:
 */
int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;

/*
 * Limit number of tasks checked in a batch.
 *
 * This value controls the preemptibility of khungtaskd since preemption
 * is disabled during the critical section. It also controls the size of
 * the RCU grace period. So it needs to be upper-bound.
 */
#define HUNG_TASK_BATCHING 1024

/*
 * Zero means infinite timeout - no checking done:
 */
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;

int __read_mostly sysctl_hung_task_warnings = 10;

static int __read_mostly did_panic;
static bool hung_task_show_lock;

static struct task_struct *watchdog_task;

/*
 * Should we panic (and reboot, if panic_timeout= is set) when a
 * hung task is detected:
 */
unsigned int __read_mostly sysctl_hung_task_panic =
                                CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;

static int __init hung_task_panic_setup(char *str)
{
        int rc = kstrtouint(str, 0, &sysctl_hung_task_panic);

        if (rc)
                return rc;
        return 1;
}
__setup("hung_task_panic=", hung_task_panic_setup);

static int
hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
{
        did_panic = 1;

        return NOTIFY_DONE;
}

static struct notifier_block panic_block = {
        .notifier_call = hung_task_panic,
};

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;

        if (switch_count != t->last_switch_count) {
                t->last_switch_count = switch_count;
                return;
        }

        trace_sched_process_hang(t);

        if (!sysctl_hung_task_warnings && !sysctl_hung_task_panic)
                return;

        /*
         * Ok, the task did not get scheduled for more than 2 minutes,
         * complain:
         */
        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();

        if (sysctl_hung_task_panic) {
                if (hung_task_show_lock)
                        debug_show_all_locks();
                trigger_all_cpu_backtrace();
                panic("hung_task: blocked tasks");
        }
}

/*
 * To avoid extending the RCU grace period for an unbounded amount of time,
 * periodically exit the critical section and enter a new one.
 *
 * For preemptible RCU it is sufficient to call rcu_read_unlock in order
 * to exit the grace period. For classic RCU, a reschedule is required.
 */
static bool rcu_lock_break(struct task_struct *g, struct task_struct *t)
{
        bool can_cont;

        get_task_struct(g);
        get_task_struct(t);
        rcu_read_unlock();
        cond_resched();
        rcu_read_lock();
        can_cont = pid_alive(g) && pid_alive(t);
        put_task_struct(t);
        put_task_struct(g);

        return can_cont;
}

/*
 * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
 * a really long time (120 seconds). If that happens, print out
 * a warning.
 */
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();
        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;
                }
                /* 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();
}

static long hung_timeout_jiffies(unsigned long last_checked,
                                 unsigned long timeout)
{
        /* timeout of 0 will disable the watchdog */
        return timeout ? last_checked - jiffies + timeout * HZ :
                MAX_SCHEDULE_TIMEOUT;
}

/*
 * Process updating of timeout sysctl
 */
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
                                  void __user *buffer,
                                  size_t *lenp, loff_t *ppos)
{
        int ret;

        ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);

        if (ret || !write)
                goto out;

        wake_up_process(watchdog_task);

 out:
        return ret;
}

static atomic_t reset_hung_task = ATOMIC_INIT(0);

void reset_hung_task_detector(void)
{
        atomic_set(&reset_hung_task, 1);
}
EXPORT_SYMBOL_GPL(reset_hung_task_detector);

/*
 * 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 ( ; ; ) {
                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))
                                check_hung_uninterruptible_tasks(timeout);
                        hung_last_checked = jiffies;
                        continue;
                }
                schedule_timeout_interruptible(t);
        }

        return 0;
}

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);