kernel-ark/include/asm-x86/nmi.h
Aristeu Rozanski b3e15bdef6 x86, NMI watchdog: setup before enabling NMI watchdog
There's a small window when NMI watchdog is being set up that if any NMIs
are triggered, the NMI code will make make use of not initalized wd_ops
elements:
	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:
			/* enable it before to avoid race with handler */
-->			__get_cpu_var(wd_enabled) = 1;
-->			if (lapic_watchdog_init(nmi_hz) < 0) {
(...)
	asmlinkage notrace __kprobes void default_do_nmi(struct pt_regs *regs)
	{
	(...)
			if (nmi_watchdog_tick(regs, reason))
				return;
(...)
	notrace __kprobes int
	nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
	{
	(...)
		if (!__get_cpu_var(wd_enabled))
			return rc;
		switch (nmi_watchdog) {
		case NMI_LOCAL_APIC:
			rc |= lapic_wd_event(nmi_hz);
(...)
int lapic_wd_event(unsigned nmi_hz)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
	u64 ctr;

-->	rdmsrl(wd->perfctr_msr, ctr);

and wd->*_msr will be initialized on each processor type specific setup, after
enabling NMIs for PMIs. Since the counter was just set, the chances of an
performance counter generated NMI is minimal, but any other unknown NMI would
trigger the problem. This patch fixes the problem by setting everything up
before enabling performance counter generated NMIs and will set wd_enabled
using a callback function.

Signed-off-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-22 19:48:19 +02:00

86 lines
2.3 KiB
C

#ifndef _ASM_X86_NMI_H_
#define _ASM_X86_NMI_H_
#include <linux/pm.h>
#include <asm/irq.h>
#include <asm/io.h>
#ifdef ARCH_HAS_NMI_WATCHDOG
/**
* do_nmi_callback
*
* Check to see if a callback exists and execute it. Return 1
* if the handler exists and was handled successfully.
*/
int do_nmi_callback(struct pt_regs *regs, int cpu);
#ifdef CONFIG_X86_64
extern void default_do_nmi(struct pt_regs *);
#endif
extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
extern int check_nmi_watchdog(void);
extern int nmi_watchdog_enabled;
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
extern int avail_to_resrv_perfctr_nmi(unsigned int);
extern int reserve_perfctr_nmi(unsigned int);
extern void release_perfctr_nmi(unsigned int);
extern int reserve_evntsel_nmi(unsigned int);
extern void release_evntsel_nmi(unsigned int);
extern void setup_apic_nmi_watchdog(void *);
extern void stop_apic_nmi_watchdog(void *);
extern void disable_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 atomic_t nmi_active;
extern unsigned int nmi_watchdog;
#define NMI_NONE 0
#define NMI_IO_APIC 1
#define NMI_LOCAL_APIC 2
#define NMI_INVALID 3
struct ctl_table;
struct file;
extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
void __user *, size_t *, loff_t *);
extern int unknown_nmi_panic;
void __trigger_all_cpu_backtrace(void);
#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
static inline void localise_nmi_watchdog(void)
{
if (nmi_watchdog == NMI_IO_APIC)
nmi_watchdog = NMI_LOCAL_APIC;
}
/* check if nmi_watchdog is active (ie was specified at boot) */
static inline int nmi_watchdog_active(void)
{
/*
* actually it should be:
* return (nmi_watchdog == NMI_LOCAL_APIC ||
* nmi_watchdog == NMI_IO_APIC)
* but since they are power of two we could use a
* cheaper way --cvg
*/
return nmi_watchdog & 0x3;
}
#endif
void lapic_watchdog_stop(void);
int lapic_watchdog_init(unsigned nmi_hz);
int lapic_wd_event(unsigned nmi_hz);
unsigned lapic_adjust_nmi_hz(unsigned hz);
int lapic_watchdog_ok(void);
void disable_lapic_nmi_watchdog(void);
void enable_lapic_nmi_watchdog(void);
void stop_nmi(void);
void restart_nmi(void);
#endif