A set of watchdog/softlockup related improvements:

- Enforce that the watchdog timestamp is always valid on boot. The
    original implementation caused a watchdog disabled gap of one second in
    the boot process due to truncation of the underlying sched clock. The
    sched clock is divided by 1e9 to convert nanoseconds to seconds. So for
    the first second of the boot process the result is 0 which is at the
    same time the indicator to disable the watchdog. The trivial fix is to
    change the disabled indicator to ULONG_MAX.
 
  - Two cleanup patches removing unused and redundant code which got
    forgotten to be cleaned up in previous changes.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAl4vbrQTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoTQHD/9ONyg9VQLjk6aH94H1Sjik/K7zvxoC
 aMGY2onZ6PddVrcTgJoMmWteQlQ2YScCSVnfVedmxTRU8laEHU/LQnMntTAbuHWj
 VUkK8X/AI5l+VY6p0Sr1iCyxcFezoC2VMqOKntuQl3080mK7R7/fQ+ZVmimiPihr
 46qMikIfBN7w2od7Ger3dZRttbnRj5YsmLBenX/HtBY/HPdhoDx6lfW/5AbAgUH5
 qnAmM0yPZ/VUSfo45z+exESUezxByIkGsrROBtPSRwql3Oqbyrza2UC48dRjsuIQ
 vO0coorlhqJGF72WW45DiLvg4Hew/vVyzcYrIiOSQPZpeTtPzL23zk/cqcqpKy6N
 pCuiSgimzbPgzqTHs6WQR/D0Dn76rruUqXqteuD5zirC9Kjf2TWeIMPTgPfy8irt
 2RwT1+5Ao/SNkdm/Pxk0S/+Y99uRJSqeNTV3lroYGC7IFMAnG4P0S9uyFJ6ZFIMz
 nOvEOhUlFXWw/w7WPZv+ytx40sRkqFVIePSRtzq+cjlDEYCgLhuveE2A4/6IGPMP
 Ej6vsGh3lMyHieRhmymESG8uLU2P/L7hhPexUPJJu4QSxKbKQNfWx+0z7bm86Ic7
 0uDSNZZl7UDYq6tioS1DBTq9ybly9vn1WDe5tHMJDllPe9TIEnqynvVLIg6MMGdm
 GjbTNysDPx85yw==
 =WMiM
 -----END PGP SIGNATURE-----

Merge tag 'core-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull watchdog updates from Thomas Gleixner:
 "A set of watchdog/softlockup related improvements:

   - Enforce that the watchdog timestamp is always valid on boot. The
     original implementation caused a watchdog disabled gap of one
     second in the boot process due to truncation of the underlying
     sched clock.

     The sched clock is divided by 1e9 to convert nanoseconds to
     seconds. So for the first second of the boot process the result is
     0 which is at the same time the indicator to disable the watchdog.

     The trivial fix is to change the disabled indicator to ULONG_MAX.

   - Two cleanup patches removing unused and redundant code which got
     forgotten to be cleaned up in previous changes"

* tag 'core-core-2020-01-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  watchdog/softlockup: Enforce that timestamp is valid on boot
  watchdog/softlockup: Remove obsolete check of last reported task
  watchdog: Remove soft_lockup_hrtimer_cnt and related code
This commit is contained in:
Linus Torvalds 2020-01-27 16:42:11 -08:00
commit b11c89a158
1 changed files with 7 additions and 24 deletions

View File

@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void)
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
#define SOFTLOCKUP_RESET ULONG_MAX
/* Global variables, exported for sysctl */
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@ -173,8 +175,6 @@ 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;
@ -274,7 +274,7 @@ 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.
*/
raw_cpu_write(watchdog_touch_ts, 0);
raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
}
notrace void touch_softlockup_watchdog(void)
@ -298,14 +298,14 @@ void touch_all_softlockup_watchdogs(void)
* the softlockup check.
*/
for_each_cpu(cpu, &watchdog_allowed_mask)
per_cpu(watchdog_touch_ts, cpu) = 0;
per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
wq_watchdog_touch(-1);
}
void touch_softlockup_watchdog_sync(void)
{
__this_cpu_write(softlockup_touch_sync, true);
__this_cpu_write(watchdog_touch_ts, 0);
__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
}
static int is_softlockup(unsigned long touch_ts)
@ -350,8 +350,6 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
*/
static int softlockup_fn(void *data)
{
__this_cpu_write(soft_lockup_hrtimer_cnt,
__this_cpu_read(hrtimer_interrupts));
__touch_watchdog();
complete(this_cpu_ptr(&softlockup_completion));
@ -383,7 +381,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
/* .. and repeat */
hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
if (touch_ts == 0) {
if (touch_ts == SOFTLOCKUP_RESET) {
if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
/*
* If the time stamp was touched atomically
@ -416,22 +414,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
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();
}
if (__this_cpu_read(soft_watchdog_warn) == true)
return HRTIMER_RESTART;
}
if (softlockup_all_cpu_backtrace) {
/* Prevent multiple soft-lockup reports if one cpu is already
@ -447,7 +431,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
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)