linux-kernel - Re: [PATCH v4 2/5] KVM: x86: Add IBPB support

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <bf5054c0-b586-757b-0b0f-4c09ee51e99b@redhat.com>
Date:   Wed, 31 Jan 2018 13:53:48 -0500
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Jim Mattson <jmattson@...gle.com>
Cc:     KarimAllah Ahmed <karahmed@...zon.de>,
        the arch/x86 maintainers <x86@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        kvm list <kvm@...r.kernel.org>,
        Ashok Raj <ashok.raj@...el.com>,
        Asit Mallick <asit.k.mallick@...el.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Arjan Van De Ven <arjan.van.de.ven@...el.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Dan Williams <dan.j.williams@...el.com>,
        Jun Nakajima <jun.nakajima@...el.com>,
        Andy Lutomirski <luto@...nel.org>,
        Greg KH <gregkh@...uxfoundation.org>,
        Peter Zijlstra <peterz@...radead.org>,
        David Woodhouse <dwmw@...zon.co.uk>
Subject: Re: [PATCH v4 2/5] KVM: x86: Add IBPB support

On 31/01/2018 12:39, Jim Mattson wrote:
> On Wed, Jan 31, 2018 at 8:55 AM, Paolo Bonzini <pbonzini@...hat.com> wrote:
> 
>> In fact this MSR can even be passed down unconditionally, since it needs
>> no save/restore and has no ill performance effect on the sibling
>> hyperthread.
> 
> I'm a bit surprised to hear that IBPB has no ill performance impact on
> the sibling hyperthread. On current CPUs, this has to flush the BTB,
> doesn't it? And since the BTB is shared between hyperthreads, doesn't
> the sibling lose all of its branch predictions?

Yeah, I knew about that, but I hadn't heard yet that it also blocks the
hyperthread while you do the write.  It makes sense in retrospect.

In any case, there's no difference (unlike IBRS) in the vmexit cost if
the MSR is passed through.

Paolo