From: chai wen <chaiw.f...@cn.fujitsu.com>
For now, soft lockup detector warns once for each case of process softlockup.
But the thread 'watchdog/n' may not always get the cpu at the time slot between
the task switch of two processes hogging that cpu to reset soft_watchdog_warn.
An example would be two processes hogging the cpu. Process A causes the
softlockup warning and is killed manually by a user. Process B immediately
becomes the new process hogging the cpu preventing the softlockup code from
resetting the soft_watchdog_warn variable.
This case is a false negative of "warn only once for a process", as there may
be a different process that is going to hog the cpu. Resolve this by
saving/checking the pid of the hogging process and use that to reset
soft_watchdog_warn too.
Signed-off-by: chai wen <chaiw.f...@cn.fujitsu.com>
[modified the comment and changelog to be more specific]
Signed-off-by: Don Zickus <dzic...@redhat.com>
---
kernel/watchdog.c | 20 ++++++++++++++++++--
1 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4c2e11c..6d0a891 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -42,6 +42,7 @@ 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(pid_t, softlockup_warn_pid_saved);
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -317,6 +318,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct
hrtimer *hrtimer)
*/
duration = is_softlockup(touch_ts);
if (unlikely(duration)) {
+ pid_t pid = task_pid_nr(current);
+
/*
* 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
@@ -326,8 +329,20 @@ static enum hrtimer_restart watchdog_timer_fn(struct
hrtimer *hrtimer)
return HRTIMER_RESTART;
/* only warn once */
- if (__this_cpu_read(soft_watchdog_warn) == true)
+ if (__this_cpu_read(soft_watchdog_warn) == true) {
+
+ /*
+ * Handle the case where multiple processes are
+ * causing softlockups but the duration is small
+ * enough, the softlockup detector can not reset
+ * itself in time. Use pids to detect this.
+ */
+ if (__this_cpu_read(softlockup_warn_pid_saved) != pid) {
+ __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
@@ -342,7 +357,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct
hrtimer *hrtimer)
printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us!
[%s:%d]\n",
smp_processor_id(), duration,
- current->comm, task_pid_nr(current));
+ current->comm, pid);
+ __this_cpu_write(softlockup_warn_pid_saved, pid);
print_modules();
print_irqtrace_events(current);
if (regs)
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
