Re: [PATCH 4/5] x86/fpu: Speed up lazy FPU restores slightly
From: Borislav Petkov
Date: Sat Jan 23 2016 - 18:35:54 EST
On Sat, Jan 23, 2016 at 02:09:59PM -0800, Andy Lutomirski wrote:
> Maybe this will be just cpu_has some day if my theory about the new
> improved static_cpu_has being shorter than boot_cpu_has pans out :)
Yeah, I have the static_cpu_has() simplification patchset v2 ready, will
send out tomorrow.
And yeah, as a next step, we probably should think about hiding
boot_cpu_has() and using solely static_cpu_has() everywhere instead.
The cpu_has() thing takes struct cpuinfo_x86 * and I'll bet a bunch of
money that a lot of the callsites could do static_cpu_has(), i.e., look
at boot CPU bits instead. That's for later, though.
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.