lkml.org 
[lkml]   [2018]   [Jan]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH v6 11/10] x86/retpoline: Avoid return buffer underflows on context switch II
Date
From
On Mon, 2018-01-08 at 17:21 -0800, Andi Kleen wrote:
> On Mon, Jan 08, 2018 at 05:16:02PM -0800, Andi Kleen wrote:
> > > If we clear the registers, what the hell are you going to put in the
> > > RSB that helps you?
> > 
> > RSB allows you to control chains of gadgets.
>
> I admit the gadget thing is a bit obscure.
>
> There's another case we were actually more worried about: 
>
> On Skylake and Broadwell when the RSB underflows it will fall back to the 
> indirect branch predictor, which can be poisoned and we try to avoid
> using with retpoline. So we try to avoid underflows, and this filling
> helps us with that.

That's no longer true for Broadwell with the latest microcode, right?

And is why we *were* talking about using retpoline only for pre-
Skylake, and using IBRS on Skylake onwards (where IBRS isn't quite so
horribly slow anyway).
[unhandled content-type:application/x-pkcs7-signature]
\
 
 \ /
  Last update: 2018-01-14 23:18    [W:0.071 / U:0.452 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site