linux/kernel/time
Thomas Gleixner cdc6f27d9e clockevents: fix reprogramming decision in oneshot broadcast
Resolve the following regression of a choppy, almost unusable laptop:

 http://lkml.org/lkml/2007/12/7/299
 http://bugzilla.kernel.org/show_bug.cgi?id=9525

A previous version of the code did the reprogramming of the broadcast
device in the return from idle code. This was removed, but the logic in
tick_handle_oneshot_broadcast() was kept the same.

When a broadcast interrupt happens we signal the expiry to all CPUs
which have an expired event. If none of the CPUs has an expired event,
which can happen in dyntick mode, then we reprogram the broadcast
device. We do not reprogram otherwise, but this is only correct if all
CPUs, which are in the idle broadcast state have been woken up.

The code ignores, that there might be pending not yet expired events on
other CPUs, which are in the idle broadcast state. So the delivery of
those events can be delayed for quite a time.

Change the tick_handle_oneshot_broadcast() function to check for CPUs,
which are in broadcast state and are not woken up by the current event,
and enforce the rearming of the broadcast device for those CPUs.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-18 18:05:58 +01:00
..
clockevents.c clockevents: warn once when program_event() is called with negative expiry 2007-12-07 19:16:17 +01:00
clocksource.c kernel/time/clocksource.c: Use list_for_each_entry instead of list_for_each 2007-10-19 11:53:38 -07:00
jiffies.c [PATCH] fix jiffies clocksource inittime 2007-04-04 21:12:47 -07:00
Kconfig clockevents: Allow build w/o run-tine usage for migration purposes 2007-10-12 23:04:05 +02:00
Makefile clockevents: Allow build w/o run-tine usage for migration purposes 2007-10-12 23:04:05 +02:00
ntp.c time: add ADJ_OFFSET_SS_READ 2007-11-26 20:42:19 +01:00
tick-broadcast.c clockevents: fix reprogramming decision in oneshot broadcast 2007-12-18 18:05:58 +01:00
tick-common.c clockevents: introduce force broadcast notifier 2007-10-14 22:57:45 +02:00
tick-internal.h highres/dyntick: prevent xtime lock contention 2007-05-08 11:15:10 -07:00
tick-oneshot.c highres: improve debug output 2007-07-21 17:49:15 -07:00
tick-sched.c softlockup: fix false positives on CONFIG_NOHZ 2007-11-28 15:52:56 +01:00
timekeeping.c kernel/time/timekeeping.c: cleanups 2007-10-17 08:42:53 -07:00
timer_list.c timer_list: Fix printk format strings 2007-10-29 09:39:38 +01:00
timer_stats.c Fix timer_stats printout of events/sec 2007-10-07 16:28:43 -07:00