/* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; } /* check for a hardlockup * This is done by making sure our 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()) { int this_cpu = smp_processor_id(); /* only print hardlockups once */ if (__this_cpu_read(hard_watchdog_warn) == true) return; pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); /* * Perform all-CPU dump only once to avoid multiple hardlockups * generating interleaving traces */ if (sysctl_hardlockup_all_cpu_backtrace && !test_and_set_bit(0, &hardlockup_allcpu_dumped)) trigger_allbutself_cpu_backtrace(); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); __this_cpu_write(hard_watchdog_warn, true); return; } __this_cpu_write(hard_watchdog_warn, false); return; }
void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args) { disable_trace_on_warning(); if (args) pr_warn(CUT_HERE); if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, caller); else pr_warn("WARNING: CPU: %d PID: %d at %pS\n", raw_smp_processor_id(), current->pid, caller); if (args) vprintk(args->fmt, args->args); if (panic_on_warn) { /* * This thread may hit another WARN() in the panic path. * Resetting this prevents additional WARN() from panicking the * system on this thread. Other threads are blocked by the * panic_mutex in panic(). */ panic_on_warn = 0; panic("panic_on_warn set ...\n"); } print_modules(); if (regs) show_regs(regs); else dump_stack(); print_irqtrace_events(current); print_oops_end_marker(); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); }
/* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; /* kick the hardlockup detector */ watchdog_interrupt_count(); /* kick the softlockup detector */ wake_up_process(__this_cpu_read(softlockup_watchdog)); /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period())); if (touch_ts == 0) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } /* Clear the guest paused flag on watchdog reset */ kvm_check_and_clear_guest_paused(); __touch_watchdog(); 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); if (unlikely(duration)) { /* * 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 */ if (kvm_check_and_clear_guest_paused()) return HRTIMER_RESTART; /* only warn once */ if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); 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; }
/* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ watchdog_interrupt_count(); /* kick the softlockup detector */ wake_up_process(__this_cpu_read(softlockup_watchdog)); /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); if (touch_ts == 0) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } /* Clear the guest paused flag on watchdog reset */ kvm_check_and_clear_guest_paused(); __touch_watchdog(); 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); if (unlikely(duration)) { /* * 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 */ 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); return HRTIMER_RESTART; } } 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); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); 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(); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); 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; }