Messages in this thread | | | Date | Wed, 14 Aug 2013 09:58:07 -0700 | From | "H. Peter Anvin" <> | Subject | Re: [RFC][PATCH 0/5] preempt_count rework |
| |
On 08/14/2013 09:52 AM, Peter Zijlstra wrote: > > Oh curses, this is because lea can't do segment offsets? So there's no > sane way to get addresses of per-cpu variables. > > Because ideally we'd have something like: > > lea %gs:__percpu_runqueues,%rax > > So in this case it makes sense to also store the actual pointer; how > unfortunate. >
Correct; the segment offset is not part of the effective address, even in 64-bit mode.
-hpa
| |