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
|
/*
* HW NMI watchdog support
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
* Arch specific calls to support NMI watchdog
*
* Bits copied from original nmi.c file
*
*/
#include <asm/apic.h>
#include <linux/smp.h>
#include <linux/cpumask.h>
#include <linux/sched.h>
#include <linux/percpu.h>
#include <linux/cpumask.h>
#include <linux/kernel_stat.h>
#include <asm/mce.h>
#include <linux/kdebug.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/module.h>
/* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
static DEFINE_PER_CPU(unsigned, last_irq_sum);
/*
* Take the local apic timer and PIT/HPET into account. We don't
* know which one is active, when we have highres/dyntick on
*/
static inline unsigned int get_timer_irqs(int cpu)
{
unsigned int irqs = per_cpu(irq_stat, cpu).irq0_irqs;
#if defined(CONFIG_X86_LOCAL_APIC)
irqs += per_cpu(irq_stat, cpu).apic_timer_irqs;
#endif
return irqs;
}
static inline int mce_in_progress(void)
{
#if defined(CONFIG_X86_MCE)
return atomic_read(&mce_entry) > 0;
#endif
return 0;
}
int hw_nmi_is_cpu_stuck(struct pt_regs *regs)
{
unsigned int sum;
int cpu = smp_processor_id();
/* if we are doing an mce, just assume the cpu is not stuck */
/* Could check oops_in_progress here too, but it's safer not to */
if (mce_in_progress())
return 0;
/* We determine if the cpu is stuck by checking whether any
* interrupts have happened since we last checked. Of course
* an nmi storm could create false positives, but the higher
* level logic should account for that
*/
sum = get_timer_irqs(cpu);
if (__get_cpu_var(last_irq_sum) == sum) {
return 1;
} else {
__get_cpu_var(last_irq_sum) = sum;
return 0;
}
}
u64 hw_nmi_get_sample_period(void)
{
return (u64)(cpu_khz) * 1000 * 60;
}
#ifdef ARCH_HAS_NMI_WATCHDOG
void arch_trigger_all_cpu_backtrace(void)
{
int i;
cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
printk(KERN_INFO "sending NMI to all CPUs:\n");
apic->send_IPI_all(NMI_VECTOR);
/* Wait for up to 10 seconds for all CPUs to do the backtrace */
for (i = 0; i < 10 * 1000; i++) {
if (cpumask_empty(to_cpumask(backtrace_mask)))
break;
mdelay(1);
}
}
static int __kprobes
arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
unsigned long cmd, void *__args)
{
struct die_args *args = __args;
struct pt_regs *regs;
int cpu = smp_processor_id();
switch (cmd) {
case DIE_NMI:
case DIE_NMI_IPI:
break;
default:
return NOTIFY_DONE;
}
regs = args->regs;
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
arch_spin_lock(&lock);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
dump_stack();
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NOTIFY_STOP;
}
return NOTIFY_DONE;
}
static __read_mostly struct notifier_block backtrace_notifier = {
.notifier_call = arch_trigger_all_cpu_backtrace_handler,
.next = NULL,
.priority = 1
};
static int __init register_trigger_all_cpu_backtrace(void)
{
register_die_notifier(&backtrace_notifier);
return 0;
}
early_initcall(register_trigger_all_cpu_backtrace);
#endif
/* STUB calls to mimic old nmi_watchdog behaviour */
#if defined(CONFIG_X86_LOCAL_APIC)
unsigned int nmi_watchdog = NMI_NONE;
EXPORT_SYMBOL(nmi_watchdog);
void acpi_nmi_enable(void) { return; }
void acpi_nmi_disable(void) { return; }
#endif
atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
EXPORT_SYMBOL(nmi_active);
int unknown_nmi_panic;
void cpu_nmi_set_wd_enabled(void) { return; }
void stop_apic_nmi_watchdog(void *unused) { return; }
void setup_apic_nmi_watchdog(void *unused) { return; }
int __init check_nmi_watchdog(void) { return 0; }
|
