summaryrefslogtreecommitdiffstats
path: root/kernel/hung_task.c
blob: 0c642d51aac2d8ab82c782a786eb13b90c0985c1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
/*
 * 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/module.h>
#include <linux/sysctl.h>

/*
 * The number of tasks checked:
 */
unsigned long __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 = 120;

unsigned long __read_mostly sysctl_hung_task_warnings = 10;

static int __read_mostly did_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)
{
	sysctl_hung_task_panic = simple_strtoul(str, NULL, 0);

	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, 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(t->flags & PF_FROZEN || !switch_count))
		return;

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

	/*
	 * Ok, the task did not get scheduled for more than 2 minutes,
	 * complain:
	 */
	printk(KERN_ERR "INFO: task %s:%d blocked for more than "
			"%ld seconds.\n", t->comm, t->pid, timeout);
	printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
			" disables this message.\n");
	sched_show_task(t);
	__debug_show_held_locks(t);

	touch_nmi_watchdog();

	if (sysctl_hung_task_panic)
		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
 * exit the grace period. For classic RCU, a reschedule is required.
 */
static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
{
	get_task_struct(g);
	get_task_struct(t);
	rcu_read_unlock();
	cond_resched();
	rcu_read_lock();
	put_task_struct(t);
	put_task_struct(g);
}

/*
 * 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;

	rcu_read_lock();
	do_each_thread(g, t) {
		if (!max_count--)
			goto unlock;
		if (!--batch_count) {
			batch_count = HUNG_TASK_BATCHING;
			rcu_lock_break(g, t);
			/* Exit if t or g was unhashed during refresh. */
			if (t->state == TASK_DEAD || g->state == TASK_DEAD)
				goto unlock;
		}
		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
		if (t->state == TASK_UNINTERRUPTIBLE)
			check_hung_task(t, timeout);
	} while_each_thread(g, t);
 unlock:
	rcu_read_unlock();
}

static unsigned long timeout_jiffies(unsigned long timeout)
{
	/* timeout of 0 will disable the watchdog */
	return timeout ? 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;
}

/*
 * kthread which checks for tasks stuck in D state
 */
static int watchdog(void *dummy)
{
	set_user_nice(current, 0);

	for ( ; ; ) {
		unsigned long timeout = sysctl_hung_task_timeout_secs;

		while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
			timeout = sysctl_hung_task_timeout_secs;

		check_hung_uninterruptible_tasks(timeout);
	}

	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;
}

module_init(hung_task_init);
OpenPOWER on IntegriCloud