x86: C1E late detection fix. Really switch off lapic timer
Doh, I completely missed that devices marked DUMMY are not running
the set_mode function. So we force broadcasting, but we keep the
local APIC timer running.
Let the clock event layer mark the device _after_ switching it off.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index fab9dd8..8cfb8b2 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -222,20 +222,8 @@
if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
goto out;
- /*
- * Defect device ?
- */
- if (!tick_device_is_functional(dev)) {
- /*
- * AMD C1E wreckage fixup:
- *
- * Device was registered functional in the first
- * place. Now the secondary CPU detected the C1E
- * misfeature and notifies us to fix it up
- */
- if (*reason != CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
- goto out;
- }
+ if (!tick_device_is_functional(dev))
+ goto out;
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
@@ -246,6 +234,8 @@
clockevents_set_mode(dev,
CLOCK_EVT_MODE_SHUTDOWN);
}
+ if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
+ dev->features |= CLOCK_EVT_FEAT_DUMMY;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
if (cpu_isset(cpu, tick_broadcast_mask)) {