summaryrefslogtreecommitdiffstats
path: root/kernel/softlockup.c
blob: 65839c54abf52a1a6c971dcae19b42cfd4b31f03 (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
/*
 * Detect Soft Lockups
 *
 * started by Ingo Molnar, Copyright (C) 2005, 2006 Red Hat, Inc.
 *
 * this code detects soft lockups: incidents in where on a CPU
 * the kernel does not reschedule for 10 seconds or more.
 */
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/notifier.h>
#include <linux/module.h>

#include <asm/irq_regs.h>

static DEFINE_SPINLOCK(print_lock);

static DEFINE_PER_CPU(unsigned long, touch_timestamp);
static DEFINE_PER_CPU(unsigned long, print_timestamp);
static DEFINE_PER_CPU(struct task_struct *, watchdog_task);

static int did_panic = 0;

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

	return NOTIFY_DONE;
}

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

/*
 * Returns seconds, approximately.  We don't need nanosecond
 * resolution, and we don't need to waste time with a big divide when
 * 2^30ns == 1.074s.
 */
static unsigned long get_timestamp(int this_cpu)
{
	return cpu_clock(this_cpu) >> 30;  /* 2^30 ~= 10^9 */
}

void touch_softlockup_watchdog(void)
{
	int this_cpu = raw_smp_processor_id();

	__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
}
EXPORT_SYMBOL(touch_softlockup_watchdog);

void touch_all_softlockup_watchdogs(void)
{
	int cpu;

	/* Cause each CPU to re-update its timestamp rather than complain */
	for_each_online_cpu(cpu)
		per_cpu(touch_timestamp, cpu) = 0;
}
EXPORT_SYMBOL(touch_all_softlockup_watchdogs);

/*
 * This callback runs from the timer interrupt, and checks
 * whether the watchdog thread has hung or not:
 */
void softlockup_tick(void)
{
	int this_cpu = smp_processor_id();
	unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
	unsigned long print_timestamp;
	struct pt_regs *regs = get_irq_regs();
	unsigned long now;

	if (touch_timestamp == 0) {
		touch_softlockup_watchdog();
		return;
	}

	print_timestamp = per_cpu(print_timestamp, this_cpu);

	/* report at most once a second */
	if ((print_timestamp >= touch_timestamp &&
			print_timestamp < (touch_timestamp + 1)) ||
			did_panic || !per_cpu(watchdog_task, this_cpu)) {
		return;
	}

	/* do not print during early bootup: */
	if (unlikely(system_state != SYSTEM_RUNNING)) {
		touch_softlockup_watchdog();
		return;
	}

	now = get_timestamp(this_cpu);

	/* Wake up the high-prio watchdog task every second: */
	if (now > (touch_timestamp + 1))
		wake_up_process(per_cpu(watchdog_task, this_cpu));

	/* Warn about unreasonable 10+ seconds delays: */
	if (now <= (touch_timestamp + 10))
		return;

	per_cpu(print_timestamp, this_cpu) = touch_timestamp;

	spin_lock(&print_lock);
	printk(KERN_ERR "BUG: soft lockup detected on CPU#%d!\n", this_cpu);
	if (regs)
		show_regs(regs);
	else
		dump_stack();
	spin_unlock(&print_lock);
}

/*
 * The watchdog thread - runs every second and touches the timestamp.
 */
static int watchdog(void * __bind_cpu)
{
	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };

	sched_setscheduler(current, SCHED_FIFO, &param);

	/* initialize timestamp */
	touch_softlockup_watchdog();

	/*
	 * Run briefly once per second to reset the softlockup timestamp.
	 * If this gets delayed for more than 10 seconds then the
	 * debug-printout triggers in softlockup_tick().
	 */
	while (!kthread_should_stop()) {
		set_current_state(TASK_INTERRUPTIBLE);
		touch_softlockup_watchdog();
		schedule();
	}

	return 0;
}

/*
 * Create/destroy watchdog threads as CPUs come and go:
 */
static int __cpuinit
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	int hotcpu = (unsigned long)hcpu;
	struct task_struct *p;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		BUG_ON(per_cpu(watchdog_task, hotcpu));
		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
		if (IS_ERR(p)) {
			printk("watchdog for %i failed\n", hotcpu);
			return NOTIFY_BAD;
		}
  		per_cpu(touch_timestamp, hotcpu) = 0;
  		per_cpu(watchdog_task, hotcpu) = p;
		kthread_bind(p, hotcpu);
 		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		wake_up_process(per_cpu(watchdog_task, hotcpu));
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		if (!per_cpu(watchdog_task, hotcpu))
			break;
		/* Unbind so it can run.  Fall thru. */
		kthread_bind(per_cpu(watchdog_task, hotcpu),
			     any_online_cpu(cpu_online_map));
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		p = per_cpu(watchdog_task, hotcpu);
		per_cpu(watchdog_task, hotcpu) = NULL;
		kthread_stop(p);
		break;
#endif /* CONFIG_HOTPLUG_CPU */
 	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata cpu_nfb = {
	.notifier_call = cpu_callback
};

__init void spawn_softlockup_task(void)
{
	void *cpu = (void *)(long)smp_processor_id();
	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);

	BUG_ON(err == NOTIFY_BAD);
	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
	register_cpu_notifier(&cpu_nfb);

	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
}