/* 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;
}
static int
ipmi_nmi(unsigned int val, struct pt_regs *regs)
{
/*
* If we get here, it's an NMI that's not a memory or I/O
* error. We can't truly tell if it's from IPMI or not
* without sending a message, and sending a message is almost
* impossible because of locking.
*/
if (testing_nmi) {
testing_nmi = 2;
return NMI_HANDLED;
}
/* If we are not expecting a timeout, ignore it. */
if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
return NMI_DONE;
if (preaction_val != WDOG_PRETIMEOUT_NMI)
return NMI_DONE;
/*
* If no one else handled the NMI, we assume it was the IPMI
* watchdog.
*/
if (preop_val == WDOG_PREOP_PANIC) {
/* On some machines, the heartbeat will give
an error and not work unless we re-enable
the timer. So do so. */
pretimeout_since_last_heartbeat = 1;
if (atomic_inc_and_test(&preop_panic_excl))
nmi_panic(regs, PFX "pre-timeout");
}
return NMI_HANDLED;
}
/*
* NMI Handler
*/
static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs)
{
unsigned int mynmi = hpwdt_my_nmi();
static char panic_msg[] =
"00: An NMI occurred. Depending on your system the reason "
"for the NMI is logged in any one of the following resources:\n"
"1. Integrated Management Log (IML)\n"
"2. OA Syslog\n"
"3. OA Forward Progress Log\n"
"4. iLO Event Log";
if (ilo5 && ulReason == NMI_UNKNOWN && !mynmi)
return NMI_DONE;
if (ilo5 && !pretimeout && !mynmi)
return NMI_DONE;
hpwdt_stop();
hex_byte_pack(panic_msg, mynmi);
nmi_panic(regs, panic_msg);
return NMI_HANDLED;
}
