linux-kernel - RE: [PATCH 2/2] x86/speculation: Support "Enhanced IBRS" on future CPUs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 20 Feb 2018 01:08:32 +0000
From:   "Van De Ven, Arjan" <arjan.van.de.ven@...el.com>
To:     Alan Cox <gnomes@...rguk.ukuu.org.uk>,
        Linus Torvalds <torvalds@...ux-foundation.org>
CC:     "valdis.kletnieks@...edu" <valdis.kletnieks@...edu>,
        Jon Masters <jcm@...masters.org>,
        David Woodhouse <dwmw2@...radead.org>,
        Paolo Bonzini <pbonzini@...hat.com>,
        "tglx@...utronix.de" <tglx@...utronix.de>,
        "x86@...nel.org" <x86@...nel.org>,
        "kvm@...r.kernel.org" <kvm@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "Hansen, Dave" <dave.hansen@...el.com>,
        Ingo Molnar <mingo@...nel.org>
Subject: RE: [PATCH 2/2] x86/speculation: Support "Enhanced IBRS" on future
 CPUs

> > On Mon, Feb 19, 2018 at 4:13 PM, Alan Cox <gnomes@...rguk.ukuu.org.uk>
> wrote:
> > >
> > > In theory there's nothing stopping a guest getting a 'you are about to
> > > gain/lose IBRS' message or having a new 'CPU' hotplugged and the old one
> > > removed.
> >
> > I'm not convinced we handle the case of hotplug CPU's with different
> > CPU models correctly.
> 
> We don't. And even if we did the user space doesn't. It would be a
> painful task to resolve.


in a cloud world it ends up being the launch/restart of the VM in reality.
Just the JIT caches all over in userspace make this case not pretty.

And we as kernel don't even really do mixed cpus without hotplug afaict
(other than maybe taking lowest subset, while the case here would be the opposite direction)