In testing SMT disable, we have been regularly seeing the following message:
Querying DEAD? cpu %i (%i) shows %i
This indicates the current delay in pseries_cpu_die where we wait
for the specified CPU to die, is insufficient. Usually, this does
not cause a problem, but we've seen this result in BUG_ON's going
off in the timer code when we try to migrate the timers off the
dead cpu while a timer is still running. Increasing this delay,
as is done in this patch, seems to resolve this issue.
Signed-off-by: Brian King <brk...@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/hotplug-cpu.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff -puN arch/powerpc/platforms/pseries/hotplug-cpu.c~powerpc_cpu_die_delay
arch/powerpc/platforms/pseries/hotplug-cpu.c
---
linux-2.6/arch/powerpc/platforms/pseries/hotplug-cpu.c~powerpc_cpu_die_delay
2010-07-20 09:24:01.000000000 -0500
+++ linux-2.6-bjking1/arch/powerpc/platforms/pseries/hotplug-cpu.c
2010-07-20 09:24:20.000000000 -0500
@@ -193,12 +193,12 @@ static void pseries_cpu_die(unsigned int
if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
cpu_status = 1;
- for (tries = 0; tries < 1000; tries++) {
+ for (tries = 0; tries < 5000; tries++) {
if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) {
cpu_status = 0;
break;
}
- cpu_relax();
+ msleep(1);
}
} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
_
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
