mirror of
https://github.com/torvalds/linux.git
synced 2024-11-27 22:51:35 +00:00
x86, nmi_watchdog: Remove the old nmi_watchdog
Now that we have a new nmi_watchdog that is more generic and sits on top of the perf subsystem, we really do not need the old nmi_watchdog any more. In addition, the old nmi_watchdog doesn't really work if you are using the default clocksource, hpet. The old nmi_watchdog code relied on local apic interrupts to determine if the cpu is still alive. With hpet as the clocksource, these interrupts don't increment any more and the old nmi_watchdog triggers false postives. This piece removes the old nmi_watchdog code and stubs out any variables and functions calls. The stubs are the same ones used by the new nmi_watchdog code, so it should be well tested. Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: fweisbec@gmail.com Cc: gorcunov@openvz.org LKML-Reference: <1289578944-28564-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Don Zickus
Ingo Molnar
parent
a89d4bd055
commit
5f2b0ba4d9
@ -17,9 +17,6 @@ int do_nmi_callback(struct pt_regs *regs, int cpu);
|
|||||||
|
|
||||||
extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
|
extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
|
||||||
extern int check_nmi_watchdog(void);
|
extern int check_nmi_watchdog(void);
|
||||||
#if !defined(CONFIG_LOCKUP_DETECTOR)
|
|
||||||
extern int nmi_watchdog_enabled;
|
|
||||||
#endif
|
|
||||||
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
|
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
|
||||||
extern int reserve_perfctr_nmi(unsigned int);
|
extern int reserve_perfctr_nmi(unsigned int);
|
||||||
extern void release_perfctr_nmi(unsigned int);
|
extern void release_perfctr_nmi(unsigned int);
|
||||||
@ -30,7 +27,6 @@ extern void setup_apic_nmi_watchdog(void *);
|
|||||||
extern void stop_apic_nmi_watchdog(void *);
|
extern void stop_apic_nmi_watchdog(void *);
|
||||||
extern void disable_timer_nmi_watchdog(void);
|
extern void disable_timer_nmi_watchdog(void);
|
||||||
extern void enable_timer_nmi_watchdog(void);
|
extern void enable_timer_nmi_watchdog(void);
|
||||||
extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
|
|
||||||
extern void cpu_nmi_set_wd_enabled(void);
|
extern void cpu_nmi_set_wd_enabled(void);
|
||||||
|
|
||||||
extern atomic_t nmi_active;
|
extern atomic_t nmi_active;
|
||||||
|
|||||||
@ -3,10 +3,7 @@
|
|||||||
#
|
#
|
||||||
|
|
||||||
obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o
|
obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o
|
||||||
ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
|
obj-y += hw_nmi.o
|
||||||
obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o
|
|
||||||
endif
|
|
||||||
obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o
|
|
||||||
|
|
||||||
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
|
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
|
||||||
obj-$(CONFIG_SMP) += ipi.o
|
obj-$(CONFIG_SMP) += ipi.o
|
||||||
|
|||||||
@ -20,12 +20,14 @@
|
|||||||
/* For reliability, we're prepared to waste bits here. */
|
/* For reliability, we're prepared to waste bits here. */
|
||||||
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
|
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
|
||||||
|
|
||||||
|
#ifdef CONFIG_HARDLOCKUP_DETECTOR
|
||||||
u64 hw_nmi_get_sample_period(void)
|
u64 hw_nmi_get_sample_period(void)
|
||||||
{
|
{
|
||||||
return (u64)(cpu_khz) * 1000 * 60;
|
return (u64)(cpu_khz) * 1000 * 60;
|
||||||
}
|
}
|
||||||
|
#endif
|
||||||
|
|
||||||
#ifdef ARCH_HAS_NMI_WATCHDOG
|
#ifdef arch_trigger_all_cpu_backtrace
|
||||||
void arch_trigger_all_cpu_backtrace(void)
|
void arch_trigger_all_cpu_backtrace(void)
|
||||||
{
|
{
|
||||||
int i;
|
int i;
|
||||||
@ -95,8 +97,6 @@ early_initcall(register_trigger_all_cpu_backtrace);
|
|||||||
#if defined(CONFIG_X86_LOCAL_APIC)
|
#if defined(CONFIG_X86_LOCAL_APIC)
|
||||||
unsigned int nmi_watchdog = NMI_NONE;
|
unsigned int nmi_watchdog = NMI_NONE;
|
||||||
EXPORT_SYMBOL(nmi_watchdog);
|
EXPORT_SYMBOL(nmi_watchdog);
|
||||||
void acpi_nmi_enable(void) { return; }
|
|
||||||
void acpi_nmi_disable(void) { return; }
|
|
||||||
#endif
|
#endif
|
||||||
atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
|
atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
|
||||||
EXPORT_SYMBOL(nmi_active);
|
EXPORT_SYMBOL(nmi_active);
|
||||||
|
|||||||
@ -1,567 +0,0 @@
|
|||||||
/*
|
|
||||||
* NMI watchdog support on APIC systems
|
|
||||||
*
|
|
||||||
* Started by Ingo Molnar <mingo@redhat.com>
|
|
||||||
*
|
|
||||||
* Fixes:
|
|
||||||
* Mikael Pettersson : AMD K7 support for local APIC NMI watchdog.
|
|
||||||
* Mikael Pettersson : Power Management for local APIC NMI watchdog.
|
|
||||||
* Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog.
|
|
||||||
* Pavel Machek and
|
|
||||||
* Mikael Pettersson : PM converted to driver model. Disable/enable API.
|
|
||||||
*/
|
|
||||||
|
|
||||||
#include <asm/apic.h>
|
|
||||||
|
|
||||||
#include <linux/nmi.h>
|
|
||||||
#include <linux/mm.h>
|
|
||||||
#include <linux/delay.h>
|
|
||||||
#include <linux/interrupt.h>
|
|
||||||
#include <linux/module.h>
|
|
||||||
#include <linux/slab.h>
|
|
||||||
#include <linux/sysdev.h>
|
|
||||||
#include <linux/sysctl.h>
|
|
||||||
#include <linux/percpu.h>
|
|
||||||
#include <linux/kprobes.h>
|
|
||||||
#include <linux/cpumask.h>
|
|
||||||
#include <linux/kernel_stat.h>
|
|
||||||
#include <linux/kdebug.h>
|
|
||||||
#include <linux/smp.h>
|
|
||||||
|
|
||||||
#include <asm/i8259.h>
|
|
||||||
#include <asm/io_apic.h>
|
|
||||||
#include <asm/proto.h>
|
|
||||||
#include <asm/timer.h>
|
|
||||||
|
|
||||||
#include <asm/mce.h>
|
|
||||||
|
|
||||||
#include <asm/mach_traps.h>
|
|
||||||
|
|
||||||
int unknown_nmi_panic;
|
|
||||||
int nmi_watchdog_enabled;
|
|
||||||
|
|
||||||
/* For reliability, we're prepared to waste bits here. */
|
|
||||||
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
|
|
||||||
|
|
||||||
/* nmi_active:
|
|
||||||
* >0: the lapic NMI watchdog is active, but can be disabled
|
|
||||||
* <0: the lapic NMI watchdog has not been set up, and cannot
|
|
||||||
* be enabled
|
|
||||||
* 0: the lapic NMI watchdog is disabled, but can be enabled
|
|
||||||
*/
|
|
||||||
atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
|
|
||||||
EXPORT_SYMBOL(nmi_active);
|
|
||||||
|
|
||||||
unsigned int nmi_watchdog = NMI_NONE;
|
|
||||||
EXPORT_SYMBOL(nmi_watchdog);
|
|
||||||
|
|
||||||
static int panic_on_timeout;
|
|
||||||
|
|
||||||
static unsigned int nmi_hz = HZ;
|
|
||||||
static DEFINE_PER_CPU(short, wd_enabled);
|
|
||||||
static int endflag __initdata;
|
|
||||||
|
|
||||||
static inline unsigned int get_nmi_count(int cpu)
|
|
||||||
{
|
|
||||||
return per_cpu(irq_stat, cpu).__nmi_count;
|
|
||||||
}
|
|
||||||
|
|
||||||
static inline int mce_in_progress(void)
|
|
||||||
{
|
|
||||||
#if defined(CONFIG_X86_MCE)
|
|
||||||
return atomic_read(&mce_entry) > 0;
|
|
||||||
#endif
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* 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)
|
|
||||||
{
|
|
||||||
return per_cpu(irq_stat, cpu).apic_timer_irqs +
|
|
||||||
per_cpu(irq_stat, cpu).irq0_irqs;
|
|
||||||
}
|
|
||||||
|
|
||||||
#ifdef CONFIG_SMP
|
|
||||||
/*
|
|
||||||
* The performance counters used by NMI_LOCAL_APIC don't trigger when
|
|
||||||
* the CPU is idle. To make sure the NMI watchdog really ticks on all
|
|
||||||
* CPUs during the test make them busy.
|
|
||||||
*/
|
|
||||||
static __init void nmi_cpu_busy(void *data)
|
|
||||||
{
|
|
||||||
local_irq_enable_in_hardirq();
|
|
||||||
/*
|
|
||||||
* Intentionally don't use cpu_relax here. This is
|
|
||||||
* to make sure that the performance counter really ticks,
|
|
||||||
* even if there is a simulator or similar that catches the
|
|
||||||
* pause instruction. On a real HT machine this is fine because
|
|
||||||
* all other CPUs are busy with "useless" delay loops and don't
|
|
||||||
* care if they get somewhat less cycles.
|
|
||||||
*/
|
|
||||||
while (endflag == 0)
|
|
||||||
mb();
|
|
||||||
}
|
|
||||||
#endif
|
|
||||||
|
|
||||||
static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
|
|
||||||
{
|
|
||||||
printk(KERN_CONT "\n");
|
|
||||||
|
|
||||||
printk(KERN_WARNING
|
|
||||||
"WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
|
|
||||||
cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
|
|
||||||
|
|
||||||
printk(KERN_WARNING
|
|
||||||
"Please report this to bugzilla.kernel.org,\n");
|
|
||||||
printk(KERN_WARNING
|
|
||||||
"and attach the output of the 'dmesg' command.\n");
|
|
||||||
|
|
||||||
per_cpu(wd_enabled, cpu) = 0;
|
|
||||||
atomic_dec(&nmi_active);
|
|
||||||
}
|
|
||||||
|
|
||||||
static void __acpi_nmi_disable(void *__unused)
|
|
||||||
{
|
|
||||||
apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
|
|
||||||
}
|
|
||||||
|
|
||||||
int __init check_nmi_watchdog(void)
|
|
||||||
{
|
|
||||||
unsigned int *prev_nmi_count;
|
|
||||||
int cpu;
|
|
||||||
|
|
||||||
if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
|
|
||||||
return 0;
|
|
||||||
|
|
||||||
prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
|
|
||||||
if (!prev_nmi_count)
|
|
||||||
goto error;
|
|
||||||
|
|
||||||
printk(KERN_INFO "Testing NMI watchdog ... ");
|
|
||||||
|
|
||||||
#ifdef CONFIG_SMP
|
|
||||||
if (nmi_watchdog == NMI_LOCAL_APIC)
|
|
||||||
smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
|
|
||||||
#endif
|
|
||||||
|
|
||||||
for_each_possible_cpu(cpu)
|
|
||||||
prev_nmi_count[cpu] = get_nmi_count(cpu);
|
|
||||||
local_irq_enable();
|
|
||||||
mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
|
|
||||||
|
|
||||||
for_each_online_cpu(cpu) {
|
|
||||||
if (!per_cpu(wd_enabled, cpu))
|
|
||||||
continue;
|
|
||||||
if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
|
|
||||||
report_broken_nmi(cpu, prev_nmi_count);
|
|
||||||
}
|
|
||||||
endflag = 1;
|
|
||||||
if (!atomic_read(&nmi_active)) {
|
|
||||||
kfree(prev_nmi_count);
|
|
||||||
atomic_set(&nmi_active, -1);
|
|
||||||
goto error;
|
|
||||||
}
|
|
||||||
printk("OK.\n");
|
|
||||||
|
|
||||||
/*
|
|
||||||
* now that we know it works we can reduce NMI frequency to
|
|
||||||
* something more reasonable; makes a difference in some configs
|
|
||||||
*/
|
|
||||||
if (nmi_watchdog == NMI_LOCAL_APIC)
|
|
||||||
nmi_hz = lapic_adjust_nmi_hz(1);
|
|
||||||
|
|
||||||
kfree(prev_nmi_count);
|
|
||||||
return 0;
|
|
||||||
error:
|
|
||||||
if (nmi_watchdog == NMI_IO_APIC) {
|
|
||||||
if (!timer_through_8259)
|
|
||||||
legacy_pic->mask(0);
|
|
||||||
on_each_cpu(__acpi_nmi_disable, NULL, 1);
|
|
||||||
}
|
|
||||||
|
|
||||||
#ifdef CONFIG_X86_32
|
|
||||||
timer_ack = 0;
|
|
||||||
#endif
|
|
||||||
return -1;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int __init setup_nmi_watchdog(char *str)
|
|
||||||
{
|
|
||||||
unsigned int nmi;
|
|
||||||
|
|
||||||
if (!strncmp(str, "panic", 5)) {
|
|
||||||
panic_on_timeout = 1;
|
|
||||||
str = strchr(str, ',');
|
|
||||||
if (!str)
|
|
||||||
return 1;
|
|
||||||
++str;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!strncmp(str, "lapic", 5))
|
|
||||||
nmi_watchdog = NMI_LOCAL_APIC;
|
|
||||||
else if (!strncmp(str, "ioapic", 6))
|
|
||||||
nmi_watchdog = NMI_IO_APIC;
|
|
||||||
else {
|
|
||||||
get_option(&str, &nmi);
|
|
||||||
if (nmi >= NMI_INVALID)
|
|
||||||
return 0;
|
|
||||||
nmi_watchdog = nmi;
|
|
||||||
}
|
|
||||||
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
__setup("nmi_watchdog=", setup_nmi_watchdog);
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Suspend/resume support
|
|
||||||
*/
|
|
||||||
#ifdef CONFIG_PM
|
|
||||||
|
|
||||||
static int nmi_pm_active; /* nmi_active before suspend */
|
|
||||||
|
|
||||||
static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
|
|
||||||
{
|
|
||||||
/* only CPU0 goes here, other CPUs should be offline */
|
|
||||||
nmi_pm_active = atomic_read(&nmi_active);
|
|
||||||
stop_apic_nmi_watchdog(NULL);
|
|
||||||
BUG_ON(atomic_read(&nmi_active) != 0);
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int lapic_nmi_resume(struct sys_device *dev)
|
|
||||||
{
|
|
||||||
/* only CPU0 goes here, other CPUs should be offline */
|
|
||||||
if (nmi_pm_active > 0) {
|
|
||||||
setup_apic_nmi_watchdog(NULL);
|
|
||||||
touch_nmi_watchdog();
|
|
||||||
}
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct sysdev_class nmi_sysclass = {
|
|
||||||
.name = "lapic_nmi",
|
|
||||||
.resume = lapic_nmi_resume,
|
|
||||||
.suspend = lapic_nmi_suspend,
|
|
||||||
};
|
|
||||||
|
|
||||||
static struct sys_device device_lapic_nmi = {
|
|
||||||
.id = 0,
|
|
||||||
.cls = &nmi_sysclass,
|
|
||||||
};
|
|
||||||
|
|
||||||
static int __init init_lapic_nmi_sysfs(void)
|
|
||||||
{
|
|
||||||
int error;
|
|
||||||
|
|
||||||
/*
|
|
||||||
* should really be a BUG_ON but b/c this is an
|
|
||||||
* init call, it just doesn't work. -dcz
|
|
||||||
*/
|
|
||||||
if (nmi_watchdog != NMI_LOCAL_APIC)
|
|
||||||
return 0;
|
|
||||||
|
|
||||||
if (atomic_read(&nmi_active) < 0)
|
|
||||||
return 0;
|
|
||||||
|
|
||||||
error = sysdev_class_register(&nmi_sysclass);
|
|
||||||
if (!error)
|
|
||||||
error = sysdev_register(&device_lapic_nmi);
|
|
||||||
return error;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* must come after the local APIC's device_initcall() */
|
|
||||||
late_initcall(init_lapic_nmi_sysfs);
|
|
||||||
|
|
||||||
#endif /* CONFIG_PM */
|
|
||||||
|
|
||||||
static void __acpi_nmi_enable(void *__unused)
|
|
||||||
{
|
|
||||||
apic_write(APIC_LVT0, APIC_DM_NMI);
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Enable timer based NMIs on all CPUs:
|
|
||||||
*/
|
|
||||||
void acpi_nmi_enable(void)
|
|
||||||
{
|
|
||||||
if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
|
|
||||||
on_each_cpu(__acpi_nmi_enable, NULL, 1);
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Disable timer based NMIs on all CPUs:
|
|
||||||
*/
|
|
||||||
void acpi_nmi_disable(void)
|
|
||||||
{
|
|
||||||
if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
|
|
||||||
on_each_cpu(__acpi_nmi_disable, NULL, 1);
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* This function is called as soon the LAPIC NMI watchdog driver has everything
|
|
||||||
* in place and it's ready to check if the NMIs belong to the NMI watchdog
|
|
||||||
*/
|
|
||||||
void cpu_nmi_set_wd_enabled(void)
|
|
||||||
{
|
|
||||||
__get_cpu_var(wd_enabled) = 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
void setup_apic_nmi_watchdog(void *unused)
|
|
||||||
{
|
|
||||||
if (__get_cpu_var(wd_enabled))
|
|
||||||
return;
|
|
||||||
|
|
||||||
/* cheap hack to support suspend/resume */
|
|
||||||
/* if cpu0 is not active neither should the other cpus */
|
|
||||||
if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
|
|
||||||
return;
|
|
||||||
|
|
||||||
switch (nmi_watchdog) {
|
|
||||||
case NMI_LOCAL_APIC:
|
|
||||||
if (lapic_watchdog_init(nmi_hz) < 0) {
|
|
||||||
__get_cpu_var(wd_enabled) = 0;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
/* FALL THROUGH */
|
|
||||||
case NMI_IO_APIC:
|
|
||||||
__get_cpu_var(wd_enabled) = 1;
|
|
||||||
atomic_inc(&nmi_active);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
void stop_apic_nmi_watchdog(void *unused)
|
|
||||||
{
|
|
||||||
/* only support LOCAL and IO APICs for now */
|
|
||||||
if (!nmi_watchdog_active())
|
|
||||||
return;
|
|
||||||
if (__get_cpu_var(wd_enabled) == 0)
|
|
||||||
return;
|
|
||||||
if (nmi_watchdog == NMI_LOCAL_APIC)
|
|
||||||
lapic_watchdog_stop();
|
|
||||||
else
|
|
||||||
__acpi_nmi_disable(NULL);
|
|
||||||
__get_cpu_var(wd_enabled) = 0;
|
|
||||||
atomic_dec(&nmi_active);
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* the best way to detect whether a CPU has a 'hard lockup' problem
|
|
||||||
* is to check it's local APIC timer IRQ counts. If they are not
|
|
||||||
* changing then that CPU has some problem.
|
|
||||||
*
|
|
||||||
* as these watchdog NMI IRQs are generated on every CPU, we only
|
|
||||||
* have to check the current processor.
|
|
||||||
*
|
|
||||||
* since NMIs don't listen to _any_ locks, we have to be extremely
|
|
||||||
* careful not to rely on unsafe variables. The printk might lock
|
|
||||||
* up though, so we have to break up any console locks first ...
|
|
||||||
* [when there will be more tty-related locks, break them up here too!]
|
|
||||||
*/
|
|
||||||
|
|
||||||
static DEFINE_PER_CPU(unsigned, last_irq_sum);
|
|
||||||
static DEFINE_PER_CPU(long, alert_counter);
|
|
||||||
static DEFINE_PER_CPU(int, nmi_touch);
|
|
||||||
|
|
||||||
void touch_nmi_watchdog(void)
|
|
||||||
{
|
|
||||||
if (nmi_watchdog_active()) {
|
|
||||||
unsigned cpu;
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Tell other CPUs to reset their alert counters. We cannot
|
|
||||||
* do it ourselves because the alert count increase is not
|
|
||||||
* atomic.
|
|
||||||
*/
|
|
||||||
for_each_present_cpu(cpu) {
|
|
||||||
if (per_cpu(nmi_touch, cpu) != 1)
|
|
||||||
per_cpu(nmi_touch, cpu) = 1;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Tickle the softlockup detector too:
|
|
||||||
*/
|
|
||||||
touch_softlockup_watchdog();
|
|
||||||
}
|
|
||||||
EXPORT_SYMBOL(touch_nmi_watchdog);
|
|
||||||
|
|
||||||
notrace __kprobes int
|
|
||||||
nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
|
|
||||||
{
|
|
||||||
/*
|
|
||||||
* Since current_thread_info()-> is always on the stack, and we
|
|
||||||
* always switch the stack NMI-atomically, it's safe to use
|
|
||||||
* smp_processor_id().
|
|
||||||
*/
|
|
||||||
unsigned int sum;
|
|
||||||
int touched = 0;
|
|
||||||
int cpu = smp_processor_id();
|
|
||||||
int rc = 0;
|
|
||||||
|
|
||||||
sum = get_timer_irqs(cpu);
|
|
||||||
|
|
||||||
if (__get_cpu_var(nmi_touch)) {
|
|
||||||
__get_cpu_var(nmi_touch) = 0;
|
|
||||||
touched = 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* We can be called before check_nmi_watchdog, hence NULL check. */
|
|
||||||
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
|
|
||||||
static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */
|
|
||||||
|
|
||||||
raw_spin_lock(&lock);
|
|
||||||
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
|
|
||||||
show_regs(regs);
|
|
||||||
dump_stack();
|
|
||||||
raw_spin_unlock(&lock);
|
|
||||||
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
|
|
||||||
|
|
||||||
rc = 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* Could check oops_in_progress here too, but it's safer not to */
|
|
||||||
if (mce_in_progress())
|
|
||||||
touched = 1;
|
|
||||||
|
|
||||||
/* if the none of the timers isn't firing, this cpu isn't doing much */
|
|
||||||
if (!touched && __get_cpu_var(last_irq_sum) == sum) {
|
|
||||||
/*
|
|
||||||
* Ayiee, looks like this CPU is stuck ...
|
|
||||||
* wait a few IRQs (5 seconds) before doing the oops ...
|
|
||||||
*/
|
|
||||||
__this_cpu_inc(alert_counter);
|
|
||||||
if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
|
|
||||||
/*
|
|
||||||
* die_nmi will return ONLY if NOTIFY_STOP happens..
|
|
||||||
*/
|
|
||||||
die_nmi("BUG: NMI Watchdog detected LOCKUP",
|
|
||||||
regs, panic_on_timeout);
|
|
||||||
} else {
|
|
||||||
__get_cpu_var(last_irq_sum) = sum;
|
|
||||||
__this_cpu_write(alert_counter, 0);
|
|
||||||
}
|
|
||||||
|
|
||||||
/* see if the nmi watchdog went off */
|
|
||||||
if (!__get_cpu_var(wd_enabled))
|
|
||||||
return rc;
|
|
||||||
switch (nmi_watchdog) {
|
|
||||||
case NMI_LOCAL_APIC:
|
|
||||||
rc |= lapic_wd_event(nmi_hz);
|
|
||||||
break;
|
|
||||||
case NMI_IO_APIC:
|
|
||||||
/*
|
|
||||||
* don't know how to accurately check for this.
|
|
||||||
* just assume it was a watchdog timer interrupt
|
|
||||||
* This matches the old behaviour.
|
|
||||||
*/
|
|
||||||
rc = 1;
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
return rc;
|
|
||||||
}
|
|
||||||
|
|
||||||
#ifdef CONFIG_SYSCTL
|
|
||||||
|
|
||||||
static void enable_ioapic_nmi_watchdog_single(void *unused)
|
|
||||||
{
|
|
||||||
__get_cpu_var(wd_enabled) = 1;
|
|
||||||
atomic_inc(&nmi_active);
|
|
||||||
__acpi_nmi_enable(NULL);
|
|
||||||
}
|
|
||||||
|
|
||||||
static void enable_ioapic_nmi_watchdog(void)
|
|
||||||
{
|
|
||||||
on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
|
|
||||||
touch_nmi_watchdog();
|
|
||||||
}
|
|
||||||
|
|
||||||
static void disable_ioapic_nmi_watchdog(void)
|
|
||||||
{
|
|
||||||
on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
|
|
||||||
}
|
|
||||||
|
|
||||||
static int __init setup_unknown_nmi_panic(char *str)
|
|
||||||
{
|
|
||||||
unknown_nmi_panic = 1;
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
|
|
||||||
|
|
||||||
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
|
|
||||||
{
|
|
||||||
unsigned char reason = get_nmi_reason();
|
|
||||||
char buf[64];
|
|
||||||
|
|
||||||
sprintf(buf, "NMI received for unknown reason %02x\n", reason);
|
|
||||||
die_nmi(buf, regs, 1); /* Always panic here */
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* proc handler for /proc/sys/kernel/nmi
|
|
||||||
*/
|
|
||||||
int proc_nmi_enabled(struct ctl_table *table, int write,
|
|
||||||
void __user *buffer, size_t *length, loff_t *ppos)
|
|
||||||
{
|
|
||||||
int old_state;
|
|
||||||
|
|
||||||
nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
|
|
||||||
old_state = nmi_watchdog_enabled;
|
|
||||||
proc_dointvec(table, write, buffer, length, ppos);
|
|
||||||
if (!!old_state == !!nmi_watchdog_enabled)
|
|
||||||
return 0;
|
|
||||||
|
|
||||||
if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
|
|
||||||
printk(KERN_WARNING
|
|
||||||
"NMI watchdog is permanently disabled\n");
|
|
||||||
return -EIO;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (nmi_watchdog == NMI_LOCAL_APIC) {
|
|
||||||
if (nmi_watchdog_enabled)
|
|
||||||
enable_lapic_nmi_watchdog();
|
|
||||||
else
|
|
||||||
disable_lapic_nmi_watchdog();
|
|
||||||
} else if (nmi_watchdog == NMI_IO_APIC) {
|
|
||||||
if (nmi_watchdog_enabled)
|
|
||||||
enable_ioapic_nmi_watchdog();
|
|
||||||
else
|
|
||||||
disable_ioapic_nmi_watchdog();
|
|
||||||
} else {
|
|
||||||
printk(KERN_WARNING
|
|
||||||
"NMI watchdog doesn't know what hardware to touch\n");
|
|
||||||
return -EIO;
|
|
||||||
}
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
#endif /* CONFIG_SYSCTL */
|
|
||||||
|
|
||||||
int do_nmi_callback(struct pt_regs *regs, int cpu)
|
|
||||||
{
|
|
||||||
#ifdef CONFIG_SYSCTL
|
|
||||||
if (unknown_nmi_panic)
|
|
||||||
return unknown_nmi_panic_callback(regs, cpu);
|
|
||||||
#endif
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
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);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
@ -398,15 +398,6 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
|
|||||||
== NOTIFY_STOP)
|
== NOTIFY_STOP)
|
||||||
return;
|
return;
|
||||||
|
|
||||||
#ifndef CONFIG_LOCKUP_DETECTOR
|
|
||||||
/*
|
|
||||||
* Ok, so this is none of the documented NMI sources,
|
|
||||||
* so it must be the NMI watchdog.
|
|
||||||
*/
|
|
||||||
if (nmi_watchdog_tick(regs, reason))
|
|
||||||
return;
|
|
||||||
if (!do_nmi_callback(regs, cpu))
|
|
||||||
#endif /* !CONFIG_LOCKUP_DETECTOR */
|
|
||||||
unknown_nmi_error(reason, regs);
|
unknown_nmi_error(reason, regs);
|
||||||
#else
|
#else
|
||||||
unknown_nmi_error(reason, regs);
|
unknown_nmi_error(reason, regs);
|
||||||
|
|||||||
@ -16,10 +16,7 @@
|
|||||||
*/
|
*/
|
||||||
#ifdef ARCH_HAS_NMI_WATCHDOG
|
#ifdef ARCH_HAS_NMI_WATCHDOG
|
||||||
#include <asm/nmi.h>
|
#include <asm/nmi.h>
|
||||||
extern void touch_nmi_watchdog(void);
|
#endif
|
||||||
extern void acpi_nmi_disable(void);
|
|
||||||
extern void acpi_nmi_enable(void);
|
|
||||||
#else
|
|
||||||
#ifndef CONFIG_HARDLOCKUP_DETECTOR
|
#ifndef CONFIG_HARDLOCKUP_DETECTOR
|
||||||
static inline void touch_nmi_watchdog(void)
|
static inline void touch_nmi_watchdog(void)
|
||||||
{
|
{
|
||||||
@ -30,7 +27,6 @@ extern void touch_nmi_watchdog(void);
|
|||||||
#endif
|
#endif
|
||||||
static inline void acpi_nmi_disable(void) { }
|
static inline void acpi_nmi_disable(void) { }
|
||||||
static inline void acpi_nmi_enable(void) { }
|
static inline void acpi_nmi_enable(void) { }
|
||||||
#endif
|
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Create trigger_all_cpu_backtrace() out of the arch-provided
|
* Create trigger_all_cpu_backtrace() out of the arch-provided
|
||||||
|
|||||||
@ -746,22 +746,6 @@ static struct ctl_table kern_table[] = {
|
|||||||
.extra2 = &one,
|
.extra2 = &one,
|
||||||
},
|
},
|
||||||
#endif
|
#endif
|
||||||
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
|
|
||||||
{
|
|
||||||
.procname = "unknown_nmi_panic",
|
|
||||||
.data = &unknown_nmi_panic,
|
|
||||||
.maxlen = sizeof (int),
|
|
||||||
.mode = 0644,
|
|
||||||
.proc_handler = proc_dointvec,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
.procname = "nmi_watchdog",
|
|
||||||
.data = &nmi_watchdog_enabled,
|
|
||||||
.maxlen = sizeof (int),
|
|
||||||
.mode = 0644,
|
|
||||||
.proc_handler = proc_nmi_enabled,
|
|
||||||
},
|
|
||||||
#endif
|
|
||||||
#if defined(CONFIG_X86)
|
#if defined(CONFIG_X86)
|
||||||
{
|
{
|
||||||
.procname = "panic_on_unrecovered_nmi",
|
.procname = "panic_on_unrecovered_nmi",
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user