Skip to content
This repository

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Fetching contributors…

Cannot retrieve contributors at this time

file 600 lines (499 sloc) 14.909 kb
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 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
/*
* 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) "NMI watchdog: " fmt

#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/lockdep.h>
#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/sysctl.h>

#include <asm/irq_regs.h>
#include <linux/perf_event.h>

int watchdog_enabled = 1;
int __read_mostly watchdog_thresh = 10;

static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif

/* boot commands */
/*
* Should we panic when a soft-lockup or hard-lockup occurs:
*/
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static int hardlockup_panic =
CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;

static int __init hardlockup_panic_setup(char *str)
{
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 = 0;
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
#endif

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;
return 1;
}
__setup("nowatchdog", nowatchdog_setup);

/* deprecated */
static int __init nosoftlockup_setup(char *str)
{
watchdog_enabled = 0;
return 1;
}
__setup("nosoftlockup", nosoftlockup_setup);
/* */

/*
* 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)
{
return watchdog_thresh * 2;
}

/*
* 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(int this_cpu)
{
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}

static unsigned long get_sample_period(void)
{
/*
* convert watchdog_thresh from seconds to ns
* the divide by 5 is to give hrtimer several chances (two
* or three with the current relation between the soft
* and hard thresholds) to increment before the
* hardlockup detector generates a warning
*/
return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
}

/* Commands for resetting the watchdog */
static void __touch_watchdog(void)
{
int this_cpu = smp_processor_id();

__this_cpu_write(watchdog_touch_ts, get_timestamp(this_cpu));
}

void touch_softlockup_watchdog(void)
{
__this_cpu_write(watchdog_touch_ts, 0);
}
EXPORT_SYMBOL(touch_softlockup_watchdog);

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
*/
for_each_online_cpu(cpu)
per_cpu(watchdog_touch_ts, cpu) = 0;
}

#ifdef CONFIG_HARDLOCKUP_DETECTOR
void touch_nmi_watchdog(void)
{
if (watchdog_enabled) {
unsigned cpu;

for_each_present_cpu(cpu) {
if (per_cpu(watchdog_nmi_touch, cpu) != true)
per_cpu(watchdog_nmi_touch, cpu) = true;
}
}
touch_softlockup_watchdog();
}
EXPORT_SYMBOL(touch_nmi_watchdog);

#endif

void touch_softlockup_watchdog_sync(void)
{
__raw_get_cpu_var(softlockup_touch_sync) = true;
__raw_get_cpu_var(watchdog_touch_ts) = 0;
}

#ifdef CONFIG_HARDLOCKUP_DETECTOR
/* watchdog detector functions */
static int is_hardlockup(void)
{
unsigned long hrint = __this_cpu_read(hrtimer_interrupts);

if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
return 1;

__this_cpu_write(hrtimer_interrupts_saved, hrint);
return 0;
}
#endif

static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp(smp_processor_id());

/* Warn about unreasonable delays: */
if (time_after(now, touch_ts + get_softlockup_thresh()))
return now - touch_ts;

return 0;
}

#ifdef CONFIG_HARDLOCKUP_DETECTOR

static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
.size = sizeof(struct perf_event_attr),
.pinned = 1,
.disabled = 1,
};

/* 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;

if (hardlockup_panic)
panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
else
WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);

__this_cpu_write(hard_watchdog_warn, true);
return;
}

__this_cpu_write(hard_watchdog_warn, false);
return;
}
static void watchdog_interrupt_count(void)
{
__this_cpu_inc(hrtimer_interrupts);
}
#else
static inline void watchdog_interrupt_count(void) { return; }
#endif /* CONFIG_HARDLOCKUP_DETECTOR */

/* 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();
}
__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)) {
/* 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;
}


/*
* The watchdog thread - touches the timestamp.
*/
static int watchdog(void *unused)
{
struct sched_param param = { .sched_priority = 0 };
struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);

/* initialize timestamp */
__touch_watchdog();

/* kick off the timer for the hardlockup detector */
/* done here because hrtimer_start can only pin to smp_processor_id() */
hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()),
HRTIMER_MODE_REL_PINNED);

set_current_state(TASK_INTERRUPTIBLE);
/*
* Run briefly (kicked by the hrtimer callback function) once every
* get_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().
*/
while (!kthread_should_stop()) {
__touch_watchdog();
schedule();

if (kthread_should_stop())
break;

set_current_state(TASK_INTERRUPTIBLE);
}
/*
* Drop the policy/priority elevation during thread exit to avoid a
* scheduling latency spike.
*/
__set_current_state(TASK_RUNNING);
sched_setscheduler(current, SCHED_NORMAL, &param);
return 0;
}


#ifdef CONFIG_HARDLOCKUP_DETECTOR
static int watchdog_nmi_enable(int cpu)
{
struct perf_event_attr *wd_attr;
struct perf_event *event = per_cpu(watchdog_ev, cpu);

/* is it already setup and enabled? */
if (event && event->state > PERF_EVENT_STATE_OFF)
goto out;

/* it is setup but not enabled */
if (event != NULL)
goto out_enable;

wd_attr = &wd_hw_attr;
wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);

/* Try to register using hardware perf events */
event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
if (!IS_ERR(event)) {
pr_info("enabled, takes one hw-pmu counter.\n");
goto out_save;
}


/* vary the KERN level based on the returned errno */
if (PTR_ERR(event) == -EOPNOTSUPP)
pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
else if (PTR_ERR(event) == -ENOENT)
pr_warning("disabled (cpu%i): hardware events not enabled\n",
cpu);
else
pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
cpu, PTR_ERR(event));
return PTR_ERR(event);

/* success path */
out_save:
per_cpu(watchdog_ev, cpu) = event;
out_enable:
perf_event_enable(per_cpu(watchdog_ev, cpu));
out:
return 0;
}

static void watchdog_nmi_disable(int cpu)
{
struct perf_event *event = per_cpu(watchdog_ev, cpu);

if (event) {
perf_event_disable(event);
per_cpu(watchdog_ev, cpu) = NULL;

/* should be in cleanup, but blocks oprofile */
perf_event_release_kernel(event);
}
return;
}
#else
static int watchdog_nmi_enable(int cpu) { return 0; }
static void watchdog_nmi_disable(int cpu) { return; }
#endif /* CONFIG_HARDLOCKUP_DETECTOR */

/* prepare/enable/disable routines */
static void watchdog_prepare_cpu(int cpu)
{
struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);

WARN_ON(per_cpu(softlockup_watchdog, cpu));
hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hrtimer->function = watchdog_timer_fn;
}

static int watchdog_enable(int cpu)
{
struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
int err = 0;

/* enable the perf event */
err = watchdog_nmi_enable(cpu);

/* Regardless of err above, fall through and start softlockup */

/* create the watchdog thread */
if (!p) {
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu);
if (IS_ERR(p)) {
pr_err("softlockup watchdog for %i failed\n", cpu);
if (!err) {
/* if hardlockup hasn't already set this */
err = PTR_ERR(p);
/* and disable the perf event */
watchdog_nmi_disable(cpu);
}
goto out;
}
sched_setscheduler(p, SCHED_FIFO, &param);
kthread_bind(p, cpu);
per_cpu(watchdog_touch_ts, cpu) = 0;
per_cpu(softlockup_watchdog, cpu) = p;
wake_up_process(p);
}

out:
return err;
}

static void watchdog_disable(int cpu)
{
struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);

/*
* cancel the timer first to stop incrementing the stats
* and waking up the kthread
*/
hrtimer_cancel(hrtimer);

/* disable the perf event */
watchdog_nmi_disable(cpu);

/* stop the watchdog thread */
if (p) {
per_cpu(softlockup_watchdog, cpu) = NULL;
kthread_stop(p);
}
}

/* sysctl functions */
#ifdef CONFIG_SYSCTL
static void watchdog_enable_all_cpus(void)
{
int cpu;

watchdog_enabled = 0;

for_each_online_cpu(cpu)
if (!watchdog_enable(cpu))
/* if any cpu succeeds, watchdog is considered
enabled for the system */
watchdog_enabled = 1;

if (!watchdog_enabled)
pr_err("failed to be enabled on some cpus\n");

}

static void watchdog_disable_all_cpus(void)
{
int cpu;

for_each_online_cpu(cpu)
watchdog_disable(cpu);

/* if all watchdogs are disabled, then they are disabled for the system */
watchdog_enabled = 0;
}


/*
* proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh
*/

int proc_dowatchdog(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret;

ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
goto out;

if (watchdog_enabled && watchdog_thresh)
watchdog_enable_all_cpus();
else
watchdog_disable_all_cpus();

out:
return ret;
}
#endif /* CONFIG_SYSCTL */


/*
* Create/destroy watchdog threads as CPUs come and go:
*/
static int __cpuinit
cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int hotcpu = (unsigned long)hcpu;

switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
watchdog_prepare_cpu(hotcpu);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
if (watchdog_enabled)
watchdog_enable(hotcpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
watchdog_disable(hotcpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
watchdog_disable(hotcpu);
break;
#endif /* CONFIG_HOTPLUG_CPU */
}

/*
* hardlockup and softlockup are not important enough
* to block cpu bring up. Just always succeed and
* rely on printk output to flag problems.
*/
return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};

void __init lockup_detector_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;

err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
WARN_ON(notifier_to_errno(err));

cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);

return;
}
Something went wrong with that request. Please try again.