* [PATCH] Timer interrupt cleanups [0/3]
@ 2003-01-06 2:32 Martin J. Bligh
2003-01-06 6:38 ` Martin J. Bligh
0 siblings, 1 reply; 2+ messages in thread
From: Martin J. Bligh @ 2003-01-06 2:32 UTC (permalink / raw)
To: Andrew Morton; +Cc: linux-kernel
Well, I tested these on the NUMA-Q and they seem to work.
Basically (as discussed previously) they rename the stuff off
the global timer to global_timer_* and the stuff off the
local timer to local_timer_*. Then I tried to clean up the
cross-calling ifdef madness. There are various corner cases,
so it's possible I screwed something up, but I think it's OK.
Original calling graph looked like this, I'll update this for
each patch to show what happens. Feel free to flame me, everyone.
--------------------
Assuming we're SMP with a local apic timer all firing away:
timer_interrupt
do_timer_interrupt
{ack the interrupt}
do_timer_interrupt_hook
do_timer
jiffies_64++;
update_times
{update CMOS clock} (In the interrupt still ??!!)
apic_timer_interrupt
smp_apic_timer_interrupt
{ack the interrupt}
smp_local_timer_interrupt
x86_do_profile
update_process_times
--------------------
On UP with local apic timer:
timer_interrupt
do_timer_interrupt
{ack the interrupt}
do_timer_interrupt_hook
do_timer
jiffies_64++;
update_process_times
update_times
{update CMOS clock} (In the interrupt still ??!!)
apic_timer_interrupt
smp_apic_timer_interrupt
{ack the interrupt}
smp_local_timer_interrupt
x86_do_profile
--------------------
On a UP 386 with stale crusty breadcrumbs, and no local timer:
timer_interrupt
do_timer_interrupt
{ack the interrupt}
do_timer_interrupt_hook
do_timer
jiffies_64++;
update_process_times
update_times
x86_do_profile()
{update CMOS clock} (In the interrupt still ??!!)
--------------------
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2003-01-06 6:29 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2003-01-06 2:32 [PATCH] Timer interrupt cleanups [0/3] Martin J. Bligh
2003-01-06 6:38 ` Martin J. Bligh
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox