Messages in this thread | | | Date | Wed, 20 Feb 2008 10:57:26 -0800 | From | Mike Travis <> | Subject | Re: [PATCH 1/2] x86_64: Fold pda into per cpu area v3 |
| |
Ingo Molnar wrote: > * Mike Travis <travis@sgi.com> wrote: > >> * Declare the pda as a per cpu variable. This will move the pda area >> to an address accessible by the x86_64 per cpu macros. >> Subtraction of __per_cpu_start will make the offset based from the >> beginning of the per cpu area. Since %gs is pointing to the pda, >> it will then also point to the per cpu variables and can be >> accessed thusly: >> >> %gs:[&per_cpu_xxxx - __per_cpu_start] > > randconfig QA on x86.git found a crash on x86.git#testing with > nmi_watchdog=2 (config attached) - and i bisected it down to this patch. > > config and crashlog attached. You can pick up x86.git#testing via: > > http://people.redhat.com/mingo/x86.git/README > > (since i had to hand-merge the patch when integrating it, i've attached > the merged version below.) > > Ingo >
I must need some different test machines as my AMD box does not fail with either yours or Thomas's configs, and the Intel box complains about the PCI-e e1000 driver and dies. I'll see about configuring a new box.
Did you try Eric's patch to see if that fixed the failure?
Thanks, Mike
| |