Re: [RFC PATCH 10/10] x86/fpu: defer FPU state load until return to userspace

From: Andy Lutomirski
Date: Wed Sep 26 2018 - 12:24:43 EST

> On Sep 26, 2018, at 8:32 AM, Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx> wrote:
> On 2018-09-26 07:34:09 [-0700], Andy Lutomirski wrote:
>>> So I *think* nobody relies on FPU-emulation anymore. I would suggest to
>>> get this patch set into shape and then getting rid of
> Bryan, Denys, does anyone of you rely on CONFIG_MATH_EMULATION?
> The manual for Quark claims that the CPU has no FPU and yet the current
> kernel (or the yocto v3.14) does not select this option.
> Denys added support for some opcodes in 2015 but I didn't figure out
> *why* or which CPU in particular requires this.

Certainly the early Quark CPUs were, um, crappy. They had so many terrifying errata that Iâm surprised anyone is willing to use them.

I would *hope* that all supported Quark CPUs support FPU instructions even if theyâre microcoded and run extremely slowly.