Files
linux_media/include/linux/nmi.h
Douglas Anderson 77c12fc959 watchdog/hardlockup: add a "cpu" param to watchdog_hardlockup_check()
In preparation for the buddy hardlockup detector where the CPU checking
for lockup might not be the currently running CPU, add a "cpu" parameter
to watchdog_hardlockup_check().

As part of this change, make hrtimer_interrupts an atomic_t since now the
CPU incrementing the value and the CPU reading the value might be
different.  Technially this could also be done with just READ_ONCE and
WRITE_ONCE, but atomic_t feels a little cleaner in this case.

While hrtimer_interrupts is made atomic_t, we change
hrtimer_interrupts_saved from "unsigned long" to "int".  The "int" is
needed to match the data type backing atomic_t for hrtimer_interrupts. 
Even if this changes us from 64-bits to 32-bits (which I don't think is
true for most compilers), it doesn't really matter.  All we ever do is
increment it every few seconds and compare it to an old value so 32-bits
is fine (even 16-bits would be).  The "signed" vs "unsigned" also doesn't
matter for simple equality comparisons.

hrtimer_interrupts_saved is _not_ switched to atomic_t nor even accessed
with READ_ONCE / WRITE_ONCE.  The hrtimer_interrupts_saved is always
consistently accessed with the same CPU.  NOTE: with the upcoming "buddy"
detector there is one special case.  When a CPU goes offline/online then
we can change which CPU is the one to consistently access a given instance
of hrtimer_interrupts_saved.  We still can't end up with a partially
updated hrtimer_interrupts_saved, however, because we end up petting all
affected CPUs to make sure the new and old CPU can't end up somehow
read/write hrtimer_interrupts_saved at the same time.

Link: https://lkml.kernel.org/r/20230519101840.v5.10.I3a7d4dd8c23ac30ee0b607d77feb6646b64825c0@changeid
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Colin Cross <ccross@android.com>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guenter Roeck <groeck@chromium.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Lecopzer Chen <lecopzer.chen@mediatek.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masayoshi Mizuma <msys.mizuma@gmail.com>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
Cc: Ricardo Neri <ricardo.neri@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Stephen Boyd <swboyd@chromium.org>
Cc: Sumit Garg <sumit.garg@linaro.org>
Cc: Tzung-Bi Shih <tzungbi@chromium.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 17:44:20 -07:00

244 lines
7.7 KiB
C

/* 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);
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_HARDLOCKUP_DETECTOR_PERF)
void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
#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);
void watchdog_nmi_enable(unsigned int cpu);
void watchdog_nmi_disable(unsigned int cpu);
void lockup_detector_reconfigure(void);
/**
* touch_nmi_watchdog - manually reset the hardlockup watchdog timeout.
*
* If we support detecting hardlockups, touch_nmi_watchdog() may be
* used to pet the watchdog (reset the timeout) - for code which
* intentionally disables interrupts for a long time. This call is stateless.
*
* Though this function has "nmi" in the name, the hardlockup watchdog might
* not be backed by NMIs. This function will likely be renamed to
* touch_hardlockup_watchdog() in the future.
*/
static inline void touch_nmi_watchdog(void)
{
/*
* Pass on to the hardlockup detector selected via CONFIG_. Note that
* the hardlockup detector may not be arch-specific nor using NMIs
* and the arch_touch_nmi_watchdog() function will likely be renamed
* in the future.
*/
arch_touch_nmi_watchdog();
/*
* Touching the hardlock detector implicitly resets the
* softlockup detector too
*/
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_PERF)
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