Re: SSE related security hole

[Jan Hubicka]

> On Fri, Apr 19, 2002 at 02:00:31PM -0400, Doug Ledford wrote:
> > On Fri, Apr 19, 2002 at 04:06:17PM +0200, Andi Kleen wrote:
> > > "H. Peter Anvin" <[e-mail]> writes:
> > > > 
> > > > Perhaps the right thing to do is to have a description in data of the
> > > > desired initialization state and just F[NX]RSTOR it?
> > > 
> > > Sounds like the cleanest solution. The state could be saved at CPU bootup
> > > with just MXCSR initialized.
> > > 
> > > I'll implement that for x86-64.
> > 
> > Ummm...last I knew, fxrstor is *expensive*.  The fninit/xor regs setup is 
> > likely *very* much faster.  Someone should check this before we sacrifice 
> > 100 cycles needlessly or something.
> 
> most probably yes, fxrestor needs to read ram, pxor also takes some
> icache and bytecode ram but it sounds like it will be faster.
> 
> Maybe we could also interleave the pxor with the xorps, since they uses
> different parts of the cpu, Honza?

Yes, I guess that should help to at least some chips.
Definitly nothing to loose :)

Honza