Web lists-archives.com

Re: “Meltdown” and “Spectre”: Every modern processor has unfixable security flaws




-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On Fri, Jan 05, 2018 at 10:33:45AM -0600, Nicholas Geovanis wrote:
> On Fri, Jan 5, 2018 at 6:55 AM,  <tomas@xxxxxxxxxx> wrote:
> > (mainframes of that time had at least VM, possibly
> > speculative prefetch).
> 
> Is it correct to call branch prediction the same as speculative execution?

I'm far from a processor expert myself but yes, that sounds plausible: the
memory unit is prefeching stuff on the speculation that the branch will
go one way, to keep the pipeline full. When things go the other way...

> If so, then "yes" they had it, but I don't honestly know if that's correct.
> Pipeline rewinding was necessary on prediction failure, etc, similarly.

... this happens.

I guess that this, in combination with a cache, could be enough for the
kind of timing attacks demonstrated by Spectre. But I'm speculating myself
here :)

Cheers
- -- tomás
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)

iEYEARECAAYFAlpPq9QACgkQBcgs9XrR2kZPhQCeNpZYsjInyrAh5HNPqTkJ6w33
s9gAn1th2QyrDsjqu/dOlZcOjRFTC3Mo
=dV+r
-----END PGP SIGNATURE-----