linux/kernel/hung_task.c
Tetsuo Handa 401c636a0e kernel/hung_task.c: show all hung tasks before panic
When we get a hung task it can often be valuable to see _all_ the hung
tasks on the system before calling panic().

Quoting from https://syzkaller.appspot.com/text?tag=CrashReport&id=5316056503549952
----------------------------------------
INFO: task syz-executor0:6540 blocked for more than 120 seconds.
      Not tainted 4.16.0+ #13
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
syz-executor0   D23560  6540   4521 0x80000004
Call Trace:
 context_switch kernel/sched/core.c:2848 [inline]
 __schedule+0x8fb/0x1ef0 kernel/sched/core.c:3490
 schedule+0xf5/0x430 kernel/sched/core.c:3549
 schedule_preempt_disabled+0x10/0x20 kernel/sched/core.c:3607
 __mutex_lock_common kernel/locking/mutex.c:833 [inline]
 __mutex_lock+0xb7f/0x1810 kernel/locking/mutex.c:893
 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908
 lo_ioctl+0x8b/0x1b70 drivers/block/loop.c:1355
 __blkdev_driver_ioctl block/ioctl.c:303 [inline]
 blkdev_ioctl+0x1759/0x1e00 block/ioctl.c:601
 ioctl_by_bdev+0xa5/0x110 fs/block_dev.c:2060
 isofs_get_last_session fs/isofs/inode.c:567 [inline]
 isofs_fill_super+0x2ba9/0x3bc0 fs/isofs/inode.c:660
 mount_bdev+0x2b7/0x370 fs/super.c:1119
 isofs_mount+0x34/0x40 fs/isofs/inode.c:1560
 mount_fs+0x66/0x2d0 fs/super.c:1222
 vfs_kern_mount.part.26+0xc6/0x4a0 fs/namespace.c:1037
 vfs_kern_mount fs/namespace.c:2514 [inline]
 do_new_mount fs/namespace.c:2517 [inline]
 do_mount+0xea4/0x2b90 fs/namespace.c:2847
 ksys_mount+0xab/0x120 fs/namespace.c:3063
 SYSC_mount fs/namespace.c:3077 [inline]
 SyS_mount+0x39/0x50 fs/namespace.c:3074
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
(...snipped...)
Showing all locks held in the system:
(...snipped...)
2 locks held by syz-executor0/6540:
 #0: 00000000566d4c39 (&type->s_umount_key#49/1){+.+.}, at: alloc_super fs/super.c:211 [inline]
 #0: 00000000566d4c39 (&type->s_umount_key#49/1){+.+.}, at: sget_userns+0x3b2/0xe60 fs/super.c:502 /* down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); */
 #1: 0000000043ca8836 (&lo->lo_ctl_mutex/1){+.+.}, at: lo_ioctl+0x8b/0x1b70 drivers/block/loop.c:1355 /* mutex_lock_nested(&lo->lo_ctl_mutex, 1); */
(...snipped...)
3 locks held by syz-executor7/6541:
 #0: 0000000043ca8836 (&lo->lo_ctl_mutex/1){+.+.}, at: lo_ioctl+0x8b/0x1b70 drivers/block/loop.c:1355 /* mutex_lock_nested(&lo->lo_ctl_mutex, 1); */
 #1: 000000007bf3d3f9 (&bdev->bd_mutex){+.+.}, at: blkdev_reread_part+0x1e/0x40 block/ioctl.c:192
 #2: 00000000566d4c39 (&type->s_umount_key#50){.+.+}, at: __get_super.part.10+0x1d3/0x280 fs/super.c:663 /* down_read(&sb->s_umount); */
----------------------------------------

When reporting an AB-BA deadlock like shown above, it would be nice if
trace of PID=6541 is printed as well as trace of PID=6540 before calling
panic().

Showing hung tasks up to /proc/sys/kernel/hung_task_warnings could delay
calling panic() but normally there should not be so many hung tasks.

Link: http://lkml.kernel.org/r/201804050705.BHE57833.HVFOFtSOMQJFOL@I-love.SAKURA.ne.jp
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Mandeep Singh Baines <msb@chromium.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-07 17:34:39 -07:00

270 lines
6.2 KiB
C

/*
* 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 bool hung_task_call_panic;
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) {
hung_task_show_lock = true;
hung_task_call_panic = true;
}
}
/*
* 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();
if (hung_task_call_panic) {
trigger_all_cpu_backtrace();
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 __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);