linux-kernel - Re: [FYI PATCH 0/7] Mitigation for CVE-2018-12207

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

Message-ID: <6cb5e680-86f1-108d-92db-62e904dccb7c@redhat.com>
Date:   Wed, 13 Nov 2019 15:44:08 +0100
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Jinpu Wang <jinpuwang@...il.com>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        "KVM-ML (kvm@...r.kernel.org)" <kvm@...r.kernel.org>
Subject: Re: [FYI PATCH 0/7] Mitigation for CVE-2018-12207

On 13/11/19 14:00, Jinpu Wang wrote:
> Hi Paolo, hi list,
> 
> Thanks for info, do we need qemu patch for full mitigation?
> Debian mentioned:
> https://linuxsecurity.com/advisories/debian/debian-dsa-4566-1-qemu-security-update-17-10-10
> "
>     A qemu update adding support for the PSCHANGE_MC_NO feature, which
>     allows to disable iTLB Multihit mitigations in nested hypervisors
>     will be provided via DSA 4566-1.
> 
> "
> But It's not yet available  publicly.

I will send it today, but it's not needed for full mitigation.  It just
provides a knob to turn it on and off in nested hypervisors.

> About the performance hit, do you know any number? probably the answer
> is workload dependent.

We generally measured 0-4%.  There can be latency spikes for RT, which I
will send a patch for soon.

Paolo