mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-06 02:24:14 +08:00
71bd934101
Merge more updates from Andrew Morton: "190 patches. Subsystems affected by this patch series: mm (hugetlb, userfaultfd, vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock, migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap, zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc, core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs, signals, exec, kcov, selftests, compress/decompress, and ipc" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits) ipc/util.c: use binary search for max_idx ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock ipc: use kmalloc for msg_queue and shmid_kernel ipc sem: use kvmalloc for sem_undo allocation lib/decompressors: remove set but not used variabled 'level' selftests/vm/pkeys: exercise x86 XSAVE init state selftests/vm/pkeys: refill shadow register after implicit kernel write selftests/vm/pkeys: handle negative sys_pkey_alloc() return code selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random kcov: add __no_sanitize_coverage to fix noinstr for all architectures exec: remove checks in __register_bimfmt() x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned hfsplus: report create_date to kstat.btime hfsplus: remove unnecessary oom message nilfs2: remove redundant continue statement in a while-loop kprobes: remove duplicated strong free_insn_page in x86 and s390 init: print out unknown kernel parameters checkpatch: do not complain about positive return values starting with EPOLL checkpatch: improve the indented label test checkpatch: scripts/spdxcheck.py now requires python3 ...
317 lines
7.5 KiB
C
317 lines
7.5 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* 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/panic_notifier.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/sched/debug.h>
|
|
#include <linux/sched/sysctl.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_LOCK_BREAK (HZ / 10)
|
|
|
|
/*
|
|
* Zero means infinite timeout - no checking done:
|
|
*/
|
|
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
|
|
|
|
/*
|
|
* Zero (default value) means use sysctl_hung_task_timeout_secs:
|
|
*/
|
|
unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
|
|
|
|
int __read_mostly sysctl_hung_task_warnings = 10;
|
|
|
|
static int __read_mostly did_panic;
|
|
static bool hung_task_show_lock;
|
|
static bool hung_task_call_panic;
|
|
static bool hung_task_show_all_bt;
|
|
|
|
static struct task_struct *watchdog_task;
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* Should we dump all CPUs backtraces in a hung task event?
|
|
* Defaults to 0, can be changed via sysctl.
|
|
*/
|
|
unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace;
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/*
|
|
* 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
|
|
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;
|
|
t->last_switch_time = jiffies;
|
|
return;
|
|
}
|
|
if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
|
|
return;
|
|
|
|
trace_sched_process_hang(t);
|
|
|
|
if (sysctl_hung_task_panic) {
|
|
console_verbose();
|
|
hung_task_show_lock = true;
|
|
hung_task_call_panic = true;
|
|
}
|
|
|
|
/*
|
|
* 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, (jiffies - t->last_switch_time) / HZ);
|
|
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;
|
|
|
|
if (sysctl_hung_task_all_cpu_backtrace)
|
|
hung_task_show_all_bt = true;
|
|
}
|
|
|
|
touch_nmi_watchdog();
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
unsigned long last_break = jiffies;
|
|
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 (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) {
|
|
if (!rcu_lock_break(g, t))
|
|
goto unlock;
|
|
last_break = jiffies;
|
|
}
|
|
/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
|
|
if (READ_ONCE(t->__state) == TASK_UNINTERRUPTIBLE)
|
|
check_hung_task(t, timeout);
|
|
}
|
|
unlock:
|
|
rcu_read_unlock();
|
|
if (hung_task_show_lock)
|
|
debug_show_all_locks();
|
|
|
|
if (hung_task_show_all_bt) {
|
|
hung_task_show_all_bt = false;
|
|
trigger_all_cpu_backtrace();
|
|
}
|
|
|
|
if (hung_task_call_panic)
|
|
panic("hung_task: blocked tasks");
|
|
}
|
|
|
|
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 *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);
|
|
|
|
static bool hung_detector_suspended;
|
|
|
|
static int hungtask_pm_notify(struct notifier_block *self,
|
|
unsigned long action, void *hcpu)
|
|
{
|
|
switch (action) {
|
|
case PM_SUSPEND_PREPARE:
|
|
case PM_HIBERNATION_PREPARE:
|
|
case PM_RESTORE_PREPARE:
|
|
hung_detector_suspended = true;
|
|
break;
|
|
case PM_POST_SUSPEND:
|
|
case PM_POST_HIBERNATION:
|
|
case PM_POST_RESTORE:
|
|
hung_detector_suspended = false;
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
unsigned long interval = sysctl_hung_task_check_interval_secs;
|
|
long t;
|
|
|
|
if (interval == 0)
|
|
interval = timeout;
|
|
interval = min_t(unsigned long, interval, timeout);
|
|
t = hung_timeout_jiffies(hung_last_checked, interval);
|
|
if (t <= 0) {
|
|
if (!atomic_xchg(&reset_hung_task, 0) &&
|
|
!hung_detector_suspended)
|
|
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);
|
|
|
|
/* Disable hung task detector on suspend */
|
|
pm_notifier(hungtask_pm_notify, 0);
|
|
|
|
watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");
|
|
|
|
return 0;
|
|
}
|
|
subsys_initcall(hung_task_init);
|