nagai/kernel
3
0
Fork 0
forked from mirrors/linux
Code Pull requests Activity
kernel/include/linux/nmi.h
Paul E. McKenney 344da544f1 x86/nmi: Print reasons why backtrace NMIs are ignored 
Instrument nmi_trigger_cpumask_backtrace() to dump out diagnostics based
on evidence accumulated by exc_nmi().  These diagnostics are dumped for
CPUs that ignored an NMI backtrace request for more than 10 seconds.

[ paulmck: Apply Ingo Molnar feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
2023-01-19 15:55:12 -08:00

225 lines
7.1 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* linux/include/linux/nmi.h
*/
#ifndef LINUX_NMI_H
#define LINUX_NMI_H
#include <linux/sched.h>
#include <asm/irq.h>
#if defined(CONFIG_HAVE_NMI_WATCHDOG)
#include <asm/nmi.h>
#endif
#ifdef CONFIG_LOCKUP_DETECTOR
void lockup_detector_init(void);
void lockup_detector_soft_poweroff(void);
void lockup_detector_cleanup(void);
bool is_hardlockup(void);
extern int watchdog_user_enabled;
extern int nmi_watchdog_user_enabled;
extern int soft_watchdog_user_enabled;
extern int watchdog_thresh;
extern unsigned long watchdog_enabled;
extern struct cpumask watchdog_cpumask;
extern unsigned long *watchdog_cpumask_bits;
#ifdef CONFIG_SMP
extern int sysctl_softlockup_all_cpu_backtrace;
extern int sysctl_hardlockup_all_cpu_backtrace;
#else
#define sysctl_softlockup_all_cpu_backtrace 0
#define sysctl_hardlockup_all_cpu_backtrace 0
#endif /* !CONFIG_SMP */
#else /* CONFIG_LOCKUP_DETECTOR */
static inline void lockup_detector_init(void) { }
static inline void lockup_detector_soft_poweroff(void) { }
static inline void lockup_detector_cleanup(void) { }
#endif /* !CONFIG_LOCKUP_DETECTOR */
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
extern void touch_softlockup_watchdog_sched(void);
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern unsigned int softlockup_panic;
extern int lockup_detector_online_cpu(unsigned int cpu);
extern int lockup_detector_offline_cpu(unsigned int cpu);
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
static inline void touch_softlockup_watchdog_sched(void) { }
static inline void touch_softlockup_watchdog(void) { }
static inline void touch_softlockup_watchdog_sync(void) { }
static inline void touch_all_softlockup_watchdogs(void) { }
#define lockup_detector_online_cpu NULL
#define lockup_detector_offline_cpu NULL
#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
#ifdef CONFIG_DETECT_HUNG_TASK
void reset_hung_task_detector(void);
#else
static inline void reset_hung_task_detector(void) { }
#endif
/*
* The run state of the lockup detectors is controlled by the content of the
* 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
* bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
*
* 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and
* 'soft_watchdog_user_enabled' are variables that are only used as an
* 'interface' between the parameters in /proc/sys/kernel and the internal
* state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is
* handled differently because its value is not boolean, and the lockup
* detectors are 'suspended' while 'watchdog_thresh' is equal zero.
*/
#define NMI_WATCHDOG_ENABLED_BIT 0
#define SOFT_WATCHDOG_ENABLED_BIT 1
#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
#if defined(CONFIG_HARDLOCKUP_DETECTOR)
extern void hardlockup_detector_disable(void);
extern unsigned int hardlockup_panic;
#else
static inline void hardlockup_detector_disable(void) {}
#endif
#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
# define NMI_WATCHDOG_SYSCTL_PERM 0644
#else
# define NMI_WATCHDOG_SYSCTL_PERM 0444
#endif
#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
extern void arch_touch_nmi_watchdog(void);
extern void hardlockup_detector_perf_stop(void);
extern void hardlockup_detector_perf_restart(void);
extern void hardlockup_detector_perf_disable(void);
extern void hardlockup_detector_perf_enable(void);
extern void hardlockup_detector_perf_cleanup(void);
extern int hardlockup_detector_perf_init(void);
#else
static inline void hardlockup_detector_perf_stop(void) { }
static inline void hardlockup_detector_perf_restart(void) { }
static inline void hardlockup_detector_perf_disable(void) { }
static inline void hardlockup_detector_perf_enable(void) { }
static inline void hardlockup_detector_perf_cleanup(void) { }
# if !defined(CONFIG_HAVE_NMI_WATCHDOG)
static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
static inline void arch_touch_nmi_watchdog(void) {}
# else
static inline int hardlockup_detector_perf_init(void) { return 0; }
# endif
#endif
void watchdog_nmi_stop(void);
void watchdog_nmi_start(void);
int watchdog_nmi_probe(void);
int watchdog_nmi_enable(unsigned int cpu);
void watchdog_nmi_disable(unsigned int cpu);
void lockup_detector_reconfigure(void);
/**
* touch_nmi_watchdog - restart NMI watchdog timeout.
*
* If the architecture supports the NMI watchdog, touch_nmi_watchdog()
* may be used to reset the timeout - for code which intentionally
* disables interrupts for a long time. This call is stateless.
*/
static inline void touch_nmi_watchdog(void)
{
arch_touch_nmi_watchdog();
touch_softlockup_watchdog();
}
/*
* Create trigger_all_cpu_backtrace() out of the arch-provided
* base function. Return whether such support was available,
* to allow calling code to fall back to some other mechanism:
*/
#ifdef arch_trigger_cpumask_backtrace
static inline bool trigger_all_cpu_backtrace(void)
{
arch_trigger_cpumask_backtrace(cpu_online_mask, false);
return true;
}
static inline bool trigger_allbutself_cpu_backtrace(void)
{
arch_trigger_cpumask_backtrace(cpu_online_mask, true);
return true;
}
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
arch_trigger_cpumask_backtrace(mask, false);
return true;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
arch_trigger_cpumask_backtrace(cpumask_of(cpu), false);
return true;
}
/* generic implementation */
void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self,
void (*raise)(cpumask_t *mask));
bool nmi_cpu_backtrace(struct pt_regs *regs);
#else
static inline bool trigger_all_cpu_backtrace(void)
{
return false;
}
static inline bool trigger_allbutself_cpu_backtrace(void)
{
return false;
}
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
return false;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
return false;
}
#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh);
#endif
#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
defined(CONFIG_HARDLOCKUP_DETECTOR)
void watchdog_update_hrtimer_threshold(u64 period);
#else
static inline void watchdog_update_hrtimer_threshold(u64 period) { }
#endif
struct ctl_table;
int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *);
int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *);
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
#include <asm/nmi.h>
#endif
#ifdef CONFIG_NMI_CHECK_CPU
void nmi_backtrace_stall_snap(const struct cpumask *btp);
void nmi_backtrace_stall_check(const struct cpumask *btp);
#else
static inline void nmi_backtrace_stall_snap(const struct cpumask *btp) {}
static inline void nmi_backtrace_stall_check(const struct cpumask *btp) {}
#endif
#endif
View git blame Copy permalink