On Fri, 2006-10-06 at 01:14 +0200, Andi Kleen wrote:

On Thursday 05 October 2006 22:51, Andi Kleen wrote:

quoted

quoted

hmm, rather than bugging you with patches now, I'll see what I can find 
with the x86_64 machines I have access to and see can I reproduce it.

I started the bisect, should finish soon.

It ended at 

diff-tree d5cdb67236dba94496de052c9f9f431e1fc658f4 (from 0dad3510ee82bcf8a380b81
a2184a664a911ef9c)
Author: Satoru Takeuchi [off-list ref]
Date:   Tue Sep 12 10:19:00 2006 -0700

    acpiphp: disable bridges
    
    Currently acpiphp calls pci_enable_device() against all
    hot-added bridges, but acpiphp does not call pci_disable_device()
    against them in hot-remove. So ioapic hot-remove would fail.
    This patch fixes this issue.

Not sure that is it really, it is possible i made a mistake during bisect
(the symptoms changed from bad page to just networking doesn't work
somewhere at 4cfee88ad30acc47f02b8b7ba3db8556262dce1e) 

I don't have time to rerun unfortunately
for some time. Anyone else looking would be useful.

As of yet I haven't been able to recreate the hang.  I am running
similar HW to Steve. 

Thanks,
  Keith