Re: [PATCH 3.16 045/305] x86/speculation: Apply IBPB more strictly to avoid cross-process data leak

[Ben Hutchings]

On Sun, 2019-02-03 at 13:37 -0800, Andi Kleen wrote:
> On Sun, Feb 03, 2019 at 08:05:53PM +0100, Jiri Kosina wrote:
> > On Sun, 3 Feb 2019, Ben Hutchings wrote:
> > 
> > > 3.16.63-rc1 review patch.  If anyone has any objections, please let me know.
> > > 
> > > ------------------
> > > 
> > > From: Jiri Kosina <jkosina@xxxxxxx>
> > > 
> > > commit dbfe2953f63c640463c630746cd5d9de8b2f63ae upstream.
> > 
> > You really want the whole IBPB+STIBP revamp from upstream, otherwise 
> > you're going to get noticeable performance penalties on some workloads 
> > with some microcodes.
> 
> Yes, we would need the opt-in/opt-out support too.
> 
> Please don't merge it just as is.

Thanks, I've now dropped this.

Ben.

-- 
Ben Hutchings
It is impossible to make anything foolproof
because fools are so ingenious.

Attachment: signature.asc
Description: This is a digitally signed message part