mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 09:28:24 +07:00
7edaeb6841
The hardlockup detector on x86 uses a performance counter based on unhalted
CPU cycles and a periodic hrtimer. The hrtimer period is about 2/5 of the
performance counter period, so the hrtimer should fire 2-3 times before the
performance counter NMI fires. The NMI code checks whether the hrtimer
fired since the last invocation. If not, it assumess a hard lockup.
The calculation of those periods is based on the nominal CPU
frequency. Turbo modes increase the CPU clock frequency and therefore
shorten the period of the perf/NMI watchdog. With extreme Turbo-modes (3x
nominal frequency) the perf/NMI period is shorter than the hrtimer period
which leads to false positives.
A simple fix would be to shorten the hrtimer period, but that comes with
the side effect of more frequent hrtimer and softlockup thread wakeups,
which is not desired.
Implement a low pass filter, which checks the perf/NMI period against
kernel time. If the perf/NMI fires before 4/5 of the watchdog period has
elapsed then the event is ignored and postponed to the next perf/NMI.
That solves the problem and avoids the overhead of shorter hrtimer periods
and more frequent softlockup thread wakeups.
Fixes: 58687acba5 ("lockup_detector: Combine nmi_watchdog and softlockup detector")
Reported-and-tested-by: Kan Liang <Kan.liang@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: dzickus@redhat.com
Cc: prarit@redhat.com
Cc: ak@linux.intel.com
Cc: babu.moger@oracle.com
Cc: peterz@infradead.org
Cc: eranian@google.com
Cc: acme@redhat.com
Cc: stable@vger.kernel.org
Cc: atomlin@redhat.com
Cc: akpm@linux-foundation.org
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1708150931310.1886@nanos
209 lines
5.5 KiB
C
209 lines
5.5 KiB
C
/*
|
|
* 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);
|
|
#else
|
|
static inline void lockup_detector_init(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#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 soft_watchdog_enabled;
|
|
extern atomic_t watchdog_park_in_progress;
|
|
#else
|
|
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)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#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_enabled' and 'soft_watchdog_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_HARDLOCKUP_DETECTOR_PERF)
|
|
extern void arch_touch_nmi_watchdog(void);
|
|
#else
|
|
#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
|
|
static inline void arch_touch_nmi_watchdog(void) {}
|
|
#endif
|
|
#endif
|
|
|
|
/**
|
|
* 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
|
|
|
|
#ifdef CONFIG_LOCKUP_DETECTOR
|
|
extern int nmi_watchdog_enabled;
|
|
extern int watchdog_user_enabled;
|
|
extern int watchdog_thresh;
|
|
extern unsigned long watchdog_enabled;
|
|
extern struct cpumask watchdog_cpumask;
|
|
extern unsigned long *watchdog_cpumask_bits;
|
|
extern int __read_mostly watchdog_suspended;
|
|
#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
|
|
|
|
#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
|
|
|
|
extern bool is_hardlockup(void);
|
|
struct ctl_table;
|
|
extern int proc_watchdog(struct ctl_table *, int ,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_nmi_watchdog(struct ctl_table *, int ,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_soft_watchdog(struct ctl_table *, int ,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_watchdog_thresh(struct ctl_table *, int ,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int proc_watchdog_cpumask(struct ctl_table *, int,
|
|
void __user *, size_t *, loff_t *);
|
|
extern int lockup_detector_suspend(void);
|
|
extern void lockup_detector_resume(void);
|
|
#else
|
|
static inline int lockup_detector_suspend(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void lockup_detector_resume(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
|
|
#include <asm/nmi.h>
|
|
#endif
|
|
|
|
#endif
|