diff options
Diffstat (limited to 'kernel/watchdog.c')
| -rw-r--r-- | kernel/watchdog.c | 1557 |
1 files changed, 989 insertions, 568 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 06d3389bca0d..0685e3a8aa0a 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * @@ -11,43 +12,89 @@ #define pr_fmt(fmt) "watchdog: " fmt -#include <linux/mm.h> #include <linux/cpu.h> -#include <linux/nmi.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/smpboot.h> -#include <linux/sched/rt.h> -#include <uapi/linux/sched/types.h> #include <linux/tick.h> -#include <linux/workqueue.h> +#include <linux/sys_info.h> + #include <linux/sched/clock.h> #include <linux/sched/debug.h> +#include <linux/sched/isolation.h> #include <asm/irq_regs.h> -#include <linux/kvm_para.h> -#include <linux/kthread.h> - -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); -#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64) +# define WATCHDOG_HARDLOCKUP_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif +#define NUM_SAMPLE_PERIODS 5 + +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; +static int __read_mostly watchdog_softlockup_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +static int __read_mostly watchdog_thresh_next; +static int __read_mostly watchdog_hardlockup_available; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ + +# 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 = - CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; + IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC); + +/* + * bitmasks to control what kinds of system info to be printed when + * hard lockup is detected, it could be task, memory, lock etc. + * Refer include/linux/sys_info.h for detailed bit definition. + */ +static unsigned long hardlockup_si_mask; + +#ifdef CONFIG_SYSFS + +static unsigned int hardlockup_count; + +static ssize_t hardlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%u\n", hardlockup_count); +} + +static struct kobj_attribute hardlockup_count_attr = __ATTR_RO(hardlockup_count); + +static __init int kernel_hardlockup_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &hardlockup_count_attr.attr, NULL); + return 0; +} + +late_initcall(kernel_hardlockup_sysfs_init); + +#endif // CONFIG_SYSFS + /* * 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 @@ -56,156 +103,521 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + watchdog_hardlockup_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) { +next: if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + watchdog_hardlockup_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + watchdog_hardlockup_user_enabled = 1; + else if (!strncmp(str, "r", 1)) + hardlockup_config_perf_event(str + 1); + while (*(str++)) { + if (*str == ',') { + str++; + goto next; + } + } return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif +#if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER) -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; +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; -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; -int __read_mostly sysctl_hardlockup_all_cpu_backtrace; +notrace void arch_touch_nmi_watchdog(void) +{ + /* + * Using __raw here because some code paths have + * preemption enabled. If preemption is enabled + * then interrupts should be enabled too, in which + * case we shouldn't have to worry about the watchdog + * going off. + */ + raw_cpu_write(watchdog_hardlockup_touched, true); +} +EXPORT_SYMBOL(arch_touch_nmi_watchdog); + +void watchdog_hardlockup_touch_cpu(unsigned int cpu) +{ + per_cpu(watchdog_hardlockup_touched, cpu) = true; +} + +static bool is_hardlockup(unsigned int cpu) +{ + int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu)); + + if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint) + return true; + + /* + * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE + * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is + * written/read by a single CPU. + */ + per_cpu(hrtimer_interrupts_saved, cpu) = hrint; + + return false; +} + +static void watchdog_hardlockup_kick(void) +{ + int new_interrupts; + + new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts)); + watchdog_buddy_check_hardlockup(new_interrupts); +} + +void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) +{ + int hardlockup_all_cpu_backtrace; + + if (per_cpu(watchdog_hardlockup_touched, cpu)) { + per_cpu(watchdog_hardlockup_touched, cpu) = false; + return; + } + + hardlockup_all_cpu_backtrace = (hardlockup_si_mask & SYS_INFO_ALL_BT) ? + 1 : sysctl_hardlockup_all_cpu_backtrace; + /* + * Check for a hardlockup by making sure the CPU's timer + * interrupt is incrementing. The timer interrupt should have + * fired multiple times before we overflow'd. If it hasn't + * then this is a good indication the cpu is stuck + */ + if (is_hardlockup(cpu)) { + unsigned int this_cpu = smp_processor_id(); + unsigned long flags; + +#ifdef CONFIG_SYSFS + ++hardlockup_count; #endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + /* + * A poorly behaving BPF scheduler can trigger hard lockup by + * e.g. putting numerous affinitized tasks in a single queue and + * directing all CPUs at it. The following call can return true + * only once when sched_ext is enabled and will immediately + * abort the BPF scheduler and print out a warning message. + */ + if (scx_hardlockup(cpu)) + return; + + /* Only print hardlockups once. */ + if (per_cpu(watchdog_hardlockup_warned, cpu)) + return; + + /* + * Prevent multiple hard-lockup reports if one cpu is already + * engaged in dumping all cpu back traces. + */ + if (hardlockup_all_cpu_backtrace) { + if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn)) + return; + } + + /* + * NOTE: we call printk_cpu_sync_get_irqsave() after printing + * the lockup message. While it would be nice to serialize + * that printout, we really want to make sure that if some + * other CPU somehow locked up while holding the lock associated + * with printk_cpu_sync_get_irqsave() that we can still at least + * get the message about the lockup out. + */ + pr_emerg("CPU%u: Watchdog detected hard LOCKUP on cpu %u\n", this_cpu, cpu); + printk_cpu_sync_get_irqsave(flags); + + print_modules(); + print_irqtrace_events(current); + if (cpu == this_cpu) { + if (regs) + show_regs(regs); + else + dump_stack(); + printk_cpu_sync_put_irqrestore(flags); + } else { + printk_cpu_sync_put_irqrestore(flags); + trigger_single_cpu_backtrace(cpu); + } + + if (hardlockup_all_cpu_backtrace) { + trigger_allbutcpu_cpu_backtrace(cpu); + if (!hardlockup_panic) + clear_bit_unlock(0, &hard_lockup_nmi_warn); + } + + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + + per_cpu(watchdog_hardlockup_warned, cpu) = true; + } else { + per_cpu(watchdog_hardlockup_warned, cpu) = false; + } +} + +#else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ + +static inline void watchdog_hardlockup_kick(void) { } + +#endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ /* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). + * These functions can be overridden based on the configured hardlockdup detector. * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). + * 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. */ -int __read_mostly watchdog_suspended; +void __weak watchdog_hardlockup_enable(unsigned int cpu) { } + +void __weak watchdog_hardlockup_disable(unsigned int cpu) { } /* - * These functions can be overridden if an architecture implements its - * own hardlockup detector. + * Watchdog-detector specific API. * - * watchdog_nmi_enable/disable can be implemented to start and stop when - * softlockup watchdog threads start and stop. The arch must select the - * SOFTLOCKUP_DETECTOR Kconfig. + * 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 watchdog_nmi_enable(unsigned int cpu) -{ - return 0; -} -void __weak watchdog_nmi_disable(unsigned int cpu) +int __weak __init watchdog_hardlockup_probe(void) { + return -ENODEV; } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/** + * 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 - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +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) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (watchdog_hardlockup_available && watchdog_hardlockup_user_enabled) + watchdog_enabled |= WATCHDOG_HARDLOCKUP_ENABLED; + if (watchdog_softlockup_user_enabled) + watchdog_enabled |= WATCHDOG_SOFTOCKUP_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) +/* + * 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 ULONG_MAX -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +#ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; +#endif + +/* + * bitmasks to control what kinds of system info to be printed when + * soft lockup is detected, it could be task, memory, lock etc. + * Refer include/linux/sys_info.h for detailed bit definition. + */ +static unsigned long softlockup_si_mask; +static struct cpumask watchdog_allowed_mask __read_mostly; + +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + IS_ENABLED(CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC); + +static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; +#ifdef CONFIG_SYSFS + +static unsigned int softlockup_count; + +static ssize_t softlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%u\n", softlockup_count); +} + +static struct kobj_attribute softlockup_count_attr = __ATTR_RO(softlockup_count); + +static __init int kernel_softlockup_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &softlockup_count_attr.attr, NULL); + return 0; +} + +late_initcall(kernel_softlockup_sysfs_init); + +#endif // CONFIG_SYSFS + +/* Timestamp taken after the last successful reschedule. */ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +/* 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 DEFINE_PER_CPU(bool, soft_watchdog_warn); -static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); -static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); -static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); -static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + watchdog_softlockup_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); -#ifdef CONFIG_SMP -static int __init softlockup_all_cpu_backtrace_setup(char *str) +static int __init watchdog_thresh_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + get_option(&str, &watchdog_thresh); return 1; } -__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) +__setup("watchdog_thresh=", watchdog_thresh_setup); + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM +enum stats_per_group { + STATS_SYSTEM, + STATS_SOFTIRQ, + STATS_HARDIRQ, + STATS_IDLE, + NUM_STATS_PER_GROUP, +}; + +static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { + CPUTIME_SYSTEM, + CPUTIME_SOFTIRQ, + CPUTIME_IRQ, + CPUTIME_IDLE, +}; + +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) { - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; + /* + * 2^24ns ~= 16.8ms + * Round to the nearest multiple of 16.8 milliseconds. + */ + return (data_ns + (1 << 23)) >> 24LL; } -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif + +static void update_cpustat(void) +{ + int i; + u8 util; + u16 old_stat, new_stat; + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u8 tail = __this_cpu_read(cpustat_tail); + u16 sample_period_16 = get_16bit_precision(sample_period); + + kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); + + for (i = 0; i < NUM_STATS_PER_GROUP; i++) { + old_stat = __this_cpu_read(cpustat_old[i]); + new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); + util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); + /* + * Since we use 16-bit precision, the raw data will undergo + * integer division, which may sometimes result in data loss, + * and then result might exceed 100%. To avoid confusion, + * we enforce a 100% display cap when calculations exceed this threshold. + */ + if (util > 100) + util = 100; + __this_cpu_write(cpustat_util[tail][i], util); + __this_cpu_write(cpustat_old[i], new_stat); + } + + __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); +} + +static void print_cpustat(void) +{ + int i, group; + u8 tail = __this_cpu_read(cpustat_tail); + u64 sample_period_msecond = sample_period; + + do_div(sample_period_msecond, NSEC_PER_MSEC); + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Utilization every %llums during lockup:\n", + smp_processor_id(), sample_period_msecond); + + for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { + group = (tail + i) % NUM_SAMPLE_PERIODS; + printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" + "%3u%% hardirq,\t%3u%% idle\n", i + 1, + __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), + __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), + __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), + __this_cpu_read(cpustat_util[group][STATS_IDLE])); + } +} + +#define HARDIRQ_PERCENT_THRESH 50 +#define NUM_HARDIRQ_REPORT 5 +struct irq_counts { + int irq; + u32 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) +{ + int i; + struct irq_counts new_count = {irq, counts}; + + for (i = 0; i < rank; i++) { + if (counts > irq_counts[i].counts) + swap(new_count, irq_counts[i]); + } +} + +/* + * 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) +{ + u8 util; + int tail = __this_cpu_read(cpustat_tail); + + tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT; + util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]); + return util > HARDIRQ_PERCENT_THRESH; +} + +static void start_counting_irqs(void) +{ + if (!__this_cpu_read(snapshot_taken)) { + kstat_snapshot_irqs(); + __this_cpu_write(snapshot_taken, true); + } +} + +static void stop_counting_irqs(void) +{ + __this_cpu_write(snapshot_taken, false); +} + +static void print_irq_counts(void) +{ + unsigned int i, count; + struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = { + {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0} + }; + + if (__this_cpu_read(snapshot_taken)) { + for_each_active_irq(i) { + count = kstat_get_irq_since_snapshot(i); + tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT); + } + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n", + smp_processor_id(), HARDIRQ_PERCENT_THRESH); + + for (i = 0; i < NUM_HARDIRQ_REPORT; i++) { + if (irq_counts_sorted[i].irq == -1) + break; + + printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n", + i + 1, irq_counts_sorted[i].counts, + irq_counts_sorted[i].irq); + } + + /* + * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last + * sample_period, then we suspect the interrupt storm might be subsiding. + */ + if (!need_counting_irqs()) + stop_counting_irqs(); + } +} + +static void report_cpu_status(void) +{ + print_cpustat(); + print_irq_counts(); +} +#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 /* @@ -239,13 +651,20 @@ static void set_sample_period(void) * and hard thresholds) to increment before the * hardlockup detector generates a warning */ - sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); + watchdog_update_hrtimer_threshold(sample_period); +} + +static void update_report_ts(void) +{ + __this_cpu_write(watchdog_report_ts, get_timestamp()); } /* Commands for resetting the watchdog */ -static void __touch_watchdog(void) +static void update_touch_ts(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); + update_report_ts(); } /** @@ -256,16 +675,16 @@ static void __touch_watchdog(void) * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ -void touch_softlockup_watchdog_sched(void) +notrace void touch_softlockup_watchdog_sched(void) { /* - * Preemption can be enabled. It doesn't matter which CPU's timestamp - * gets zeroed here, so use the raw_ operation. + * Preemption can be enabled. It doesn't matter which CPU's watchdog + * report period gets restarted here, so use the raw_ operation. */ - raw_cpu_write(watchdog_touch_ts, 0); + raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } -void touch_softlockup_watchdog(void) +notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); @@ -277,74 +696,135 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) - per_cpu(watchdog_touch_ts, cpu) = 0; - wq_watchdog_touch(-1); + for_each_cpu(cpu, &watchdog_allowed_mask) { + per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT; + wq_watchdog_touch(cpu); + } } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); - __this_cpu_write(watchdog_touch_ts, 0); + __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } -static int is_softlockup(unsigned long touch_ts) +static int is_softlockup(unsigned long touch_ts, + unsigned long period_ts, + unsigned long now) { - unsigned long now = get_timestamp(); + if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) { + /* + * If period_ts has not been updated during a sample_period, then + * in the subsequent few sample_periods, period_ts might also not + * be updated, which could indicate a potential softlockup. In + * this case, if we suspect the cause of the potential softlockup + * might be interrupt storm, then we need to count the interrupts + * to find which interrupt is storming. + */ + if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) && + need_counting_irqs()) + start_counting_irqs(); + + /* + * A poorly behaving BPF scheduler can live-lock the system into + * soft lockups. Tell sched_ext to try ejecting the BPF + * scheduler when close to a soft lockup. + */ + if (time_after_eq(now, period_ts + get_softlockup_thresh() * 3 / 4)) + scx_softlockup(now - touch_ts); - if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ - if (time_after(now, touch_ts + get_softlockup_thresh())) + if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; } /* watchdog detector functions */ -bool is_hardlockup(void) -{ - unsigned long hrint = __this_cpu_read(hrtimer_interrupts); +static DEFINE_PER_CPU(struct completion, softlockup_completion); +static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); - if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) - return true; - - __this_cpu_write(hrtimer_interrupts_saved, hrint); - return false; -} - -static void watchdog_interrupt_count(void) +/* + * 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) { - __this_cpu_inc(hrtimer_interrupts); -} + update_touch_ts(); + stop_counting_irqs(); + complete(this_cpu_ptr(&softlockup_completion)); -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); + return 0; +} /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { - unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); + unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int duration; - int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + int softlockup_all_cpu_backtrace; + unsigned long flags; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; - /* kick the hardlockup detector */ - watchdog_interrupt_count(); + /* + * pass the buddy check if a panic is in process + */ + if (panic_in_progress()) + return HRTIMER_NORESTART; + + softlockup_all_cpu_backtrace = (softlockup_si_mask & SYS_INFO_ALL_BT) ? + 1 : sysctl_softlockup_all_cpu_backtrace; + + watchdog_hardlockup_kick(); /* kick the softlockup detector */ - wake_up_process(__this_cpu_read(softlockup_watchdog)); + if (completion_done(this_cpu_ptr(&softlockup_completion))) { + reinit_completion(this_cpu_ptr(&softlockup_completion)); + stop_one_cpu_nowait(smp_processor_id(), + softlockup_fn, NULL, + this_cpu_ptr(&softlockup_stop_work)); + } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); - if (touch_ts == 0) { + /* + * Read the current timestamp first. It might become invalid anytime + * when a virtual machine is stopped by the host or when the watchog + * is touched from NMI. + */ + now = get_timestamp(); + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a soft lockup. This function touches the watchdog. + */ + kvm_check_and_clear_guest_paused(); + /* + * The stored timestamp is comparable with @now only when not touched. + * It might get touched anytime from NMI. Make sure that is_softlockup() + * uses the same (valid) value. + */ + period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); + + update_cpustat(); + + /* Reset the interval when touched by known problematic code. */ + if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically @@ -354,539 +834,331 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) sched_clock_tick(); } - /* Clear the guest paused flag on watchdog reset */ - kvm_check_and_clear_guest_paused(); - __touch_watchdog(); + update_report_ts(); return HRTIMER_RESTART; } - /* check for a softlockup - * This is done by making sure a high priority task is - * being scheduled. The task touches the watchdog to - * indicate it is getting cpu time. If it hasn't then - * this is a good indication some task is hogging the cpu - */ - duration = is_softlockup(touch_ts); + /* Check for a softlockup. */ + touch_ts = __this_cpu_read(watchdog_touch_ts); + duration = is_softlockup(touch_ts, period_ts, now); if (unlikely(duration)) { +#ifdef CONFIG_SYSFS + ++softlockup_count; +#endif + /* - * If a virtual machine is stopped by the host it can look to - * the watchdog like a soft lockup, check to see if the host - * stopped the vm before we issue the warning + * Prevent multiple soft-lockup reports if one cpu is already + * engaged in dumping all cpu back traces. */ - if (kvm_check_and_clear_guest_paused()) - return HRTIMER_RESTART; - - /* only warn once */ - if (__this_cpu_read(soft_watchdog_warn) == true) { - /* - * When multiple processes are causing softlockups the - * softlockup detector only warns on the first one - * because the code relies on a full quiet cycle to - * re-arm. The second process prevents the quiet cycle - * and never gets reported. Use task pointers to detect - * this. - */ - if (__this_cpu_read(softlockup_task_ptr_saved) != - current) { - __this_cpu_write(soft_watchdog_warn, false); - __touch_watchdog(); - } - return HRTIMER_RESTART; - } - if (softlockup_all_cpu_backtrace) { - /* Prevent multiple soft-lockup reports if one cpu is already - * engaged in dumping cpu back traces - */ - if (test_and_set_bit(0, &soft_lockup_nmi_warn)) { - /* Someone else will report us. Let's give up */ - __this_cpu_write(soft_watchdog_warn, true); + if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn)) return HRTIMER_RESTART; - } } + /* Start period for the next softlockup warning. */ + update_report_ts(); + + printk_cpu_sync_get_irqsave(flags); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); - __this_cpu_write(softlockup_task_ptr_saved, current); + report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); + printk_cpu_sync_put_irqrestore(flags); if (softlockup_all_cpu_backtrace) { - /* Avoid generating two back traces for current - * given that one is already made above - */ - trigger_allbutself_cpu_backtrace(); - - clear_bit(0, &soft_lockup_nmi_warn); - /* Barrier to sync with other cpus */ - smp_mb__after_atomic(); + trigger_allbutcpu_cpu_backtrace(smp_processor_id()); + if (!softlockup_panic) + clear_bit_unlock(0, &soft_lockup_nmi_warn); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + sys_info(softlockup_si_mask & ~SYS_INFO_ALL_BT); if (softlockup_panic) panic("softlockup: hung tasks"); - __this_cpu_write(soft_watchdog_warn, true); - } else - __this_cpu_write(soft_watchdog_warn, false); + } return HRTIMER_RESTART; } -static void watchdog_set_prio(unsigned int policy, unsigned int prio) -{ - struct sched_param param = { .sched_priority = prio }; - - sched_setscheduler(current, policy, ¶m); -} - static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); + struct completion *done = this_cpu_ptr(&softlockup_completion); - /* kick off the timer for the hardlockup detector */ - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; + WARN_ON_ONCE(cpu != smp_processor_id()); - /* Enable the perf event */ - watchdog_nmi_enable(cpu); + init_completion(done); + complete(done); - /* done here because hrtimer_start can only pin to smp_processor_id() */ + /* + * Start the timer first to prevent the hardlockup watchdog triggering + * before the timer has a chance to fire. + */ + hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer_start(hrtimer, ns_to_ktime(sample_period), - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_HARD); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); - __touch_watchdog(); + /* Initialize timestamp */ + update_touch_ts(); + /* Enable the hardlockup detector */ + if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED) + watchdog_hardlockup_enable(cpu); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); - - watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ - watchdog_nmi_disable(cpu); -} - -static void watchdog_cleanup(unsigned int cpu, bool online) -{ - watchdog_disable(cpu); -} + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); -static int watchdog_should_run(unsigned int cpu) -{ - return __this_cpu_read(hrtimer_interrupts) != - __this_cpu_read(soft_lockup_hrtimer_cnt); -} - -/* - * The watchdog thread 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 void watchdog(unsigned int cpu) -{ - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); - __touch_watchdog(); + WARN_ON_ONCE(cpu != smp_processor_id()); /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. + * Disable the hardlockup detector first. That prevents that a large + * delay between disabling the timer and disabling the hardlockup + * detector causes a false positive. */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); -} - -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .cleanup = watchdog_cleanup, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) -{ - int cpu, ret = 0; - - atomic_set(&watchdog_park_in_progress, 1); - - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; -} - -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) -{ - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + watchdog_hardlockup_disable(cpu); + hrtimer_cancel(hrtimer); + wait_for_completion(this_cpu_ptr(&softlockup_completion)); } -static int update_watchdog_all_cpus(void) +static int softlockup_stop_fn(void *data) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - + watchdog_disable(smp_processor_id()); return 0; } -static int watchdog_enable_all_cpus(void) +static void softlockup_stop_all(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); + int cpu; - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } + if (!softlockup_initialized) + return; - if (err) - watchdog_enabled = 0; + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); - return err; + cpumask_clear(&watchdog_allowed_mask); } -static void watchdog_disable_all_cpus(void) +static int softlockup_start_fn(void *data) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } + watchdog_enable(smp_processor_id()); + return 0; } -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static void softlockup_start_all(void) { - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + int cpu; -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } -static void watchdog_unpark_threads(void) +int lockup_detector_online_cpu(unsigned int cpu) { + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_enable(cpu); + return 0; } -static int watchdog_enable_all_cpus(void) +int lockup_detector_offline_cpu(unsigned int cpu) { + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_disable(cpu); return 0; } -static void watchdog_disable_all_cpus(void) +static void __lockup_detector_reconfigure(bool thresh_changed) { -} + cpus_read_lock(); + watchdog_hardlockup_stop(); -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return 0; + softlockup_stop_all(); + /* + * To prevent watchdog_timer_fn from using the old interval and + * the new watchdog_thresh at the same time, which could lead to + * false softlockup reports, it is necessary to update the + * watchdog_thresh after the softlockup is completed. + */ + if (thresh_changed) + watchdog_thresh = READ_ONCE(watchdog_thresh_next); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_start_all(); + + watchdog_hardlockup_start(); + cpus_read_unlock(); } -#endif -static void set_sample_period(void) +void lockup_detector_reconfigure(void) { + mutex_lock(&watchdog_mutex); + __lockup_detector_reconfigure(false); + mutex_unlock(&watchdog_mutex); } -#endif /* SOFTLOCKUP */ /* - * Suspend the hard and soft lockup detector by parking the watchdog threads. + * Create the watchdog infrastructure and configure the detector(s). */ -int lockup_detector_suspend(void) +static __init void lockup_detector_setup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } + lockup_detector_update_enable(); - watchdog_nmi_reconfigure(); + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; - mutex_unlock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); + __lockup_detector_reconfigure(false); + softlockup_initialized = true; + mutex_unlock(&watchdog_mutex); +} - return ret; +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static void __lockup_detector_reconfigure(bool thresh_changed) +{ + cpus_read_lock(); + watchdog_hardlockup_stop(); + if (thresh_changed) + watchdog_thresh = READ_ONCE(watchdog_thresh_next); + lockup_detector_update_enable(); + watchdog_hardlockup_start(); + cpus_read_unlock(); +} +void lockup_detector_reconfigure(void) +{ + __lockup_detector_reconfigure(false); +} +static inline void lockup_detector_setup(void) +{ + __lockup_detector_reconfigure(false); } +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * 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_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog infrastructure */ +static void proc_watchdog_update(bool thresh_changed) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + __lockup_detector_reconfigure(thresh_changed); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * 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, struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog_common(int which, const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old, *param = table->data; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ + old = *param; if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + *param = old; } else { err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(false); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } /* * /proc/sys/kernel/watchdog */ -int proc_watchdog(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, + return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED | + WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/nmi_watchdog */ -int proc_nmi_watchdog(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_nmi_watchdog(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - return proc_watchdog_common(NMI_WATCHDOG_ENABLED, + if (!watchdog_hardlockup_available && write) + return -ENOTSUPP; + return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED, table, write, buffer, lenp, ppos); } +#ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * /proc/sys/kernel/soft_watchdog */ -int proc_soft_watchdog(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_soft_watchdog(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, + return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } +#endif /* * /proc/sys/kernel/watchdog_thresh */ -int proc_watchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog_thresh(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; + int err, old; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + watchdog_thresh_next = READ_ONCE(watchdog_thresh); - old = ACCESS_ONCE(watchdog_thresh); + old = watchdog_thresh_next; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh_next)) + proc_watchdog_update(true); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -896,60 +1168,209 @@ out: * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ -int proc_watchdog_cpumask(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog_cpumask(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(false); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } +static const int sixty = 60; + +static const struct ctl_table watchdog_sysctls[] = { + { + .procname = "watchdog", + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "watchdog_thresh", + .data = &watchdog_thresh_next, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog_thresh, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&sixty, + }, + { + .procname = "watchdog_cpumask", + .data = &watchdog_cpumask_bits, + .maxlen = NR_CPUS, + .mode = 0644, + .proc_handler = proc_watchdog_cpumask, + }, +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + { + .procname = "soft_watchdog", + .data = &watchdog_softlockup_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "softlockup_sys_info", + .data = &softlockup_si_mask, + .maxlen = sizeof(softlockup_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR + { + .procname = "hardlockup_panic", + .data = &hardlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "hardlockup_sys_info", + .data = &hardlockup_si_mask, + .maxlen = sizeof(hardlockup_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, +#ifdef CONFIG_SMP + { + .procname = "hardlockup_all_cpu_backtrace", + .data = &sysctl_hardlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif + { + .procname = "nmi_watchdog", + .data = &watchdog_hardlockup_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_nmi_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +}; + +static void __init watchdog_sysctl_init(void) +{ + register_sysctl_init("kernel", watchdog_sysctls); +} + +#else +#define watchdog_sysctl_init() do { } while (0) #endif /* CONFIG_SYSCTL */ -void __init lockup_detector_init(void) +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 = + __WORK_INITIALIZER(detector_work, lockup_detector_delay_init); + +static void __init lockup_detector_delay_init(struct work_struct *work) { - set_sample_period(); + int ret; + + ret = watchdog_hardlockup_probe(); + if (ret) { + if (ret == -ENODEV) + pr_info("NMI not fully supported\n"); + else + pr_info("Delayed init of the lockup detector failed: %d\n", ret); + pr_info("Hard watchdog permanently disabled\n"); + return; + } + + allow_lockup_detector_init_retry = false; + + watchdog_hardlockup_available = true; + lockup_detector_setup(); +} + +/* + * 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) +{ + /* Must be called before late init calls */ + if (!allow_lockup_detector_init_retry) + return; + + schedule_work(&detector_work); +} + +/* + * Ensure that optional delayed hardlockup init is proceed before + * the init code and memory is freed. + */ +static int __init lockup_detector_check(void) +{ + /* Prevent any later retry. */ + allow_lockup_detector_init_retry = false; + + /* Make sure no work is pending. */ + flush_work(&detector_work); + + watchdog_sysctl_init(); + + return 0; + +} +late_initcall_sync(lockup_detector_check); -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) { +void __init lockup_detector_init(void) +{ + if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); - cpumask_copy(&watchdog_cpumask, housekeeping_mask); - } else - cpumask_copy(&watchdog_cpumask, cpu_possible_mask); -#else - cpumask_copy(&watchdog_cpumask, cpu_possible_mask); -#endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + cpumask_copy(&watchdog_cpumask, + housekeeping_cpumask(HK_TYPE_TIMER)); + + if (!watchdog_hardlockup_probe()) + watchdog_hardlockup_available = true; + else + allow_lockup_detector_init_retry = true; + + lockup_detector_setup(); } |