Blame view
kernel/softlockup.c
3.48 KB
8446f1d39
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
/* * Detect Soft Lockups * * started by Ingo Molnar, (C) 2005, Red Hat * * this code detects soft lockups: incidents in where on a CPU * the kernel does not reschedule for 10 seconds or more. */ #include <linux/mm.h> #include <linux/cpu.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/notifier.h> #include <linux/module.h> static DEFINE_SPINLOCK(print_lock); static DEFINE_PER_CPU(unsigned long, timestamp) = 0; static DEFINE_PER_CPU(unsigned long, print_timestamp) = 0; static DEFINE_PER_CPU(struct task_struct *, watchdog_task); static int did_panic = 0; static int softlock_panic(struct notifier_block *this, unsigned long event, void *ptr) { did_panic = 1; return NOTIFY_DONE; } static struct notifier_block panic_block = { .notifier_call = softlock_panic, }; void touch_softlockup_watchdog(void) { per_cpu(timestamp, raw_smp_processor_id()) = jiffies; } EXPORT_SYMBOL(touch_softlockup_watchdog); /* * This callback runs from the timer interrupt, and checks * whether the watchdog thread has hung or not: */ void softlockup_tick(struct pt_regs *regs) { int this_cpu = smp_processor_id(); unsigned long timestamp = per_cpu(timestamp, this_cpu); if (per_cpu(print_timestamp, this_cpu) == timestamp) return; /* Do not cause a second panic when there already was one */ if (did_panic) return; if (time_after(jiffies, timestamp + 10*HZ)) { per_cpu(print_timestamp, this_cpu) = timestamp; spin_lock(&print_lock); printk(KERN_ERR "BUG: soft lockup detected on CPU#%d! ", this_cpu); show_regs(regs); spin_unlock(&print_lock); } } /* * The watchdog thread - runs every second and touches the timestamp. */ static int watchdog(void * __bind_cpu) { struct sched_param param = { .sched_priority = 99 }; |
8446f1d39
|
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
sched_setscheduler(current, SCHED_FIFO, ¶m); current->flags |= PF_NOFREEZE; set_current_state(TASK_INTERRUPTIBLE); /* * Run briefly once per second - if this gets delayed for * more than 10 seconds then the debug-printout triggers * in softlockup_tick(): */ while (!kthread_should_stop()) { msleep_interruptible(1000); touch_softlockup_watchdog(); } __set_current_state(TASK_RUNNING); return 0; } /* * Create/destroy watchdog threads as CPUs come and go: */ static int __devinit cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { int hotcpu = (unsigned long)hcpu; struct task_struct *p; switch (action) { case CPU_UP_PREPARE: BUG_ON(per_cpu(watchdog_task, hotcpu)); p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu); if (IS_ERR(p)) { printk("watchdog for %i failed ", hotcpu); return NOTIFY_BAD; } per_cpu(watchdog_task, hotcpu) = p; kthread_bind(p, hotcpu); break; case CPU_ONLINE: wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: /* Unbind so it can run. Fall thru. */ |
a4c4af7c8
|
125 126 |
kthread_bind(per_cpu(watchdog_task, hotcpu), any_online_cpu(cpu_online_map)); |
8446f1d39
|
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
case CPU_DEAD: p = per_cpu(watchdog_task, hotcpu); per_cpu(watchdog_task, hotcpu) = NULL; kthread_stop(p); break; #endif /* CONFIG_HOTPLUG_CPU */ } return NOTIFY_OK; } static struct notifier_block __devinitdata cpu_nfb = { .notifier_call = cpu_callback }; __init void spawn_softlockup_task(void) { void *cpu = (void *)(long)smp_processor_id(); cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); notifier_chain_register(&panic_notifier_list, &panic_block); } |