softlockup: fix NMI hangs due to lock race - 2.6.26-rc regression
The touch_nmi_watchdog() routine on x86 ultimately calls touch_softlockup_watchdog(). The problem is that to touch the softlockup watchdog, the cpu_clock code has to be called which could involve multiple cpu locks and can lead to a hard hang if one of the locks is held by a processor that is not going to return anytime soon (such as could be the case with kgdb or perhaps even with some other kind of exception). This patch causes the public version of the touch_softlockup_watchdog() to defer the cpu clock access to a later point. The test case for this problem is to use the following kernel config options: CONFIG_KGDB_TESTS=y CONFIG_KGDB_TESTS_ON_BOOT=y CONFIG_KGDB_TESTS_BOOT_STRING="V1F100I100000" It should be noted that kgdb test suite and these options were not available until 2.6.26-rc2, so it was necessary to patch the kgdb test suite during the bisection. I would consider this patch a regression fix because the problem first appeared in commit27ec440779
when some logic was added to try to periodically sync the clocks. It was possible to work around this particular problem by simply not performing the sync anytime the system was in a critical context. This was ok until commit3e51f33fcc
, which added config option CONFIG_HAVE_UNSTABLE_SCHED_CLOCK and some multi-cpu locks to sync the clocks. It became clear that accessing this code from an nmi was the source of the lockups. Avoiding the access to the low level clock code from an code inside the NMI processing also fixed the problem with the 27ec44... commit. Signed-off-by: Jason Wessel <jason.wessel@windriver.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
02ff375590
commit
8c2238eaaf
|
@ -64,12 +64,17 @@ static unsigned long get_timestamp(int this_cpu)
|
|||
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
|
||||
}
|
||||
|
||||
void touch_softlockup_watchdog(void)
|
||||
static void __touch_softlockup_watchdog(void)
|
||||
{
|
||||
int this_cpu = raw_smp_processor_id();
|
||||
|
||||
__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
|
||||
}
|
||||
|
||||
void touch_softlockup_watchdog(void)
|
||||
{
|
||||
__raw_get_cpu_var(touch_timestamp) = 0;
|
||||
}
|
||||
EXPORT_SYMBOL(touch_softlockup_watchdog);
|
||||
|
||||
void touch_all_softlockup_watchdogs(void)
|
||||
|
@ -103,7 +108,7 @@ void softlockup_tick(void)
|
|||
}
|
||||
|
||||
if (touch_timestamp == 0) {
|
||||
touch_softlockup_watchdog();
|
||||
__touch_softlockup_watchdog();
|
||||
return;
|
||||
}
|
||||
|
||||
|
@ -118,7 +123,7 @@ void softlockup_tick(void)
|
|||
|
||||
/* do not print during early bootup: */
|
||||
if (unlikely(system_state != SYSTEM_RUNNING)) {
|
||||
touch_softlockup_watchdog();
|
||||
__touch_softlockup_watchdog();
|
||||
return;
|
||||
}
|
||||
|
||||
|
@ -243,7 +248,7 @@ static int watchdog(void *__bind_cpu)
|
|||
sched_setscheduler(current, SCHED_FIFO, ¶m);
|
||||
|
||||
/* initialize timestamp */
|
||||
touch_softlockup_watchdog();
|
||||
__touch_softlockup_watchdog();
|
||||
|
||||
set_current_state(TASK_INTERRUPTIBLE);
|
||||
/*
|
||||
|
@ -252,7 +257,7 @@ static int watchdog(void *__bind_cpu)
|
|||
* debug-printout triggers in softlockup_tick().
|
||||
*/
|
||||
while (!kthread_should_stop()) {
|
||||
touch_softlockup_watchdog();
|
||||
__touch_softlockup_watchdog();
|
||||
schedule();
|
||||
|
||||
if (kthread_should_stop())
|
||||
|
|
Loading…
Reference in New Issue