// SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) … #include <linux/cpu.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/kvm_para.h> #include <linux/math64.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> #include <linux/stop_machine.h> #include <linux/sysctl.h> #include <linux/tick.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <asm/irq_regs.h> static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64) #define WATCHDOG_HARDLOCKUP_DEFAULT … #else #define WATCHDOG_HARDLOCKUP_DEFAULT … #endif #define NUM_SAMPLE_PERIODS … unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = …; static int __read_mostly watchdog_hardlockup_user_enabled = …; static int __read_mostly watchdog_softlockup_user_enabled = …; int __read_mostly watchdog_thresh = …; static int __read_mostly watchdog_hardlockup_available; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = …; #ifdef CONFIG_HARDLOCKUP_DETECTOR # ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; # endif /* CONFIG_SMP */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = … IS_ENABLED(…); /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these * cases this function can be called to disable hard lockup detection. This * function should only be executed once by the boot processor before the * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ void __init hardlockup_detector_disable(void) { … } static int __init hardlockup_panic_setup(char *str) { … } __setup(…); #endif /* CONFIG_HARDLOCKUP_DETECTOR */ #if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER) static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts); static DEFINE_PER_CPU(int, hrtimer_interrupts_saved); static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned); static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched); static unsigned long hard_lockup_nmi_warn; notrace void arch_touch_nmi_watchdog(void) { … } EXPORT_SYMBOL(…); void watchdog_hardlockup_touch_cpu(unsigned int cpu) { … } static bool is_hardlockup(unsigned int cpu) { … } static void watchdog_hardlockup_kick(void) { … } void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) { … } #else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ static inline void watchdog_hardlockup_kick(void) { } #endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ /* * These functions can be overridden based on the configured hardlockdup detector. * * watchdog_hardlockup_enable/disable can be implemented to start and stop when * softlockup watchdog start and stop. The detector must select the * SOFTLOCKUP_DETECTOR Kconfig. */ void __weak watchdog_hardlockup_enable(unsigned int cpu) { … } void __weak watchdog_hardlockup_disable(unsigned int cpu) { … } /* * Watchdog-detector specific API. * * Return 0 when hardlockup watchdog is available, negative value otherwise. * Note that the negative value means that a delayed probe might * succeed later. */ int __weak __init watchdog_hardlockup_probe(void) { … } /** * watchdog_hardlockup_stop - Stop the watchdog for reconfiguration * * The reconfiguration steps are: * watchdog_hardlockup_stop(); * update_variables(); * watchdog_hardlockup_start(); */ void __weak watchdog_hardlockup_stop(void) { … } /** * watchdog_hardlockup_start - Start the watchdog after reconfiguration * * Counterpart to watchdog_hardlockup_stop(). * * The following variables have been updated in update_variables() and * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask */ void __weak watchdog_hardlockup_start(void) { … } /** * lockup_detector_update_enable - Update the sysctl enable bit * * Caller needs to make sure that the hard watchdogs are off, so this * can't race with watchdog_hardlockup_disable(). */ static void lockup_detector_update_enable(void) { … } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * Delay the soflockup report when running a known slow code. * It does _not_ affect the timestamp of the last successdul reschedule. */ #define SOFTLOCKUP_DELAY_REPORT … #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = … IS_ENABLED(…); static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; /* Timestamp taken after the last successful reschedule. */ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); /* Timestamp of the last softlockup report. */ static DEFINE_PER_CPU(unsigned long, watchdog_report_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static unsigned long soft_lockup_nmi_warn; static int __init softlockup_panic_setup(char *str) { … } __setup(…); static int __init nowatchdog_setup(char *str) { … } __setup(…); static int __init nosoftlockup_setup(char *str) { … } __setup(…); static int __init watchdog_thresh_setup(char *str) { … } __setup(…); static void __lockup_detector_cleanup(void); #ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM enum stats_per_group { … }; static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = …; static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_tail); /* * We don't need nanosecond resolution. A granularity of 16ms is * sufficient for our precision, allowing us to use u16 to store * cpustats, which will roll over roughly every ~1000 seconds. * 2^24 ~= 16 * 10^6 */ static u16 get_16bit_precision(u64 data_ns) { … } static void update_cpustat(void) { … } static void print_cpustat(void) { … } #define HARDIRQ_PERCENT_THRESH … #define NUM_HARDIRQ_REPORT … struct irq_counts { … }; static DEFINE_PER_CPU(bool, snapshot_taken); /* Tabulate the most frequent interrupts. */ static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank) { … } /* * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period, * then the cause of softlockup might be interrupt storm. In this case, it * would be useful to start interrupt counting. */ static bool need_counting_irqs(void) { … } static void start_counting_irqs(void) { … } static void stop_counting_irqs(void) { … } static void print_irq_counts(void) { … } static void report_cpu_status(void) { … } #else static inline void update_cpustat(void) { } static inline void report_cpu_status(void) { } static inline bool need_counting_irqs(void) { return false; } static inline void start_counting_irqs(void) { } static inline void stop_counting_irqs(void) { } #endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally * want a higher threshold for soft lockups than for hard lockups. So we couple * the thresholds with a factor: we make the soft threshold twice the amount of * time the hard threshold is. */ static int get_softlockup_thresh(void) { … } /* * Returns seconds, approximately. We don't need nanosecond * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ static unsigned long get_timestamp(void) { … } static void set_sample_period(void) { … } static void update_report_ts(void) { … } /* Commands for resetting the watchdog */ static void update_touch_ts(void) { … } /** * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls * * Call when the scheduler may have stalled for legitimate reasons * preventing the watchdog task from executing - e.g. the scheduler * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ notrace void touch_softlockup_watchdog_sched(void) { … } notrace void touch_softlockup_watchdog(void) { … } EXPORT_SYMBOL(…); void touch_all_softlockup_watchdogs(void) { … } void touch_softlockup_watchdog_sync(void) { … } static int is_softlockup(unsigned long touch_ts, unsigned long period_ts, unsigned long now) { … } /* watchdog detector functions */ static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* * The watchdog feed function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). */ static int softlockup_fn(void *data) { … } /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { … } static void watchdog_enable(unsigned int cpu) { … } static void watchdog_disable(unsigned int cpu) { … } static int softlockup_stop_fn(void *data) { … } static void softlockup_stop_all(void) { … } static int softlockup_start_fn(void *data) { … } static void softlockup_start_all(void) { … } int lockup_detector_online_cpu(unsigned int cpu) { … } int lockup_detector_offline_cpu(unsigned int cpu) { … } static void __lockup_detector_reconfigure(void) { … } void lockup_detector_reconfigure(void) { … } /* * Create the watchdog infrastructure and configure the detector(s). */ static __init void lockup_detector_setup(void) { … } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_hardlockup_stop(); lockup_detector_update_enable(); watchdog_hardlockup_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { __lockup_detector_reconfigure(); } static inline void lockup_detector_setup(void) { __lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) { … } /** * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes * * Caller must not hold the cpu hotplug rwsem. */ void lockup_detector_cleanup(void) { … } /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * * Special interface for parisc. It prevents lockup detector warnings from * the default pm_poweroff() function which busy loops forever. */ void lockup_detector_soft_poweroff(void) { … } #ifdef CONFIG_SYSCTL /* Propagate any changes to the watchdog infrastructure */ static void proc_watchdog_update(void) { … } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * * caller | table->data points to | 'which' * -------------------|----------------------------------|------------------------------- * proc_watchdog | watchdog_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED | * | | WATCHDOG_SOFTOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_nmi_watchdog | watchdog_hardlockup_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED */ static int proc_watchdog_common(int which, const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } /* * /proc/sys/kernel/watchdog */ static int proc_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } /* * /proc/sys/kernel/nmi_watchdog */ static int proc_nmi_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * /proc/sys/kernel/soft_watchdog */ static int proc_soft_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } #endif /* * /proc/sys/kernel/watchdog_thresh */ static int proc_watchdog_thresh(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } static const int sixty = …; static struct ctl_table watchdog_sysctls[] = …; static struct ctl_table watchdog_hardlockup_sysctl[] = …; static void __init watchdog_sysctl_init(void) { … } #else #define watchdog_sysctl_init … #endif /* CONFIG_SYSCTL */ static void __init lockup_detector_delay_init(struct work_struct *work); static bool allow_lockup_detector_init_retry __initdata; static struct work_struct detector_work __initdata = …; static void __init lockup_detector_delay_init(struct work_struct *work) { … } /* * lockup_detector_retry_init - retry init lockup detector if possible. * * Retry hardlockup detector init. It is useful when it requires some * functionality that has to be initialized later on a particular * platform. */ void __init lockup_detector_retry_init(void) { … } /* * Ensure that optional delayed hardlockup init is proceed before * the init code and memory is freed. */ static int __init lockup_detector_check(void) { … } late_initcall_sync(lockup_detector_check); void __init lockup_detector_init(void) { … }
Codebase Browser
linux