linux-kernel - Re: [RFC 00/10] Process-local memory allocations for hiding KVM secrets

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]

Message-ID: <7b17ff38-b505-74c6-d773-8ab5e000be10@intel.com>
Date:   Thu, 13 Jun 2019 07:19:02 -0700
From:   Dave Hansen <dave.hansen@...el.com>
To:     Alexander Graf <graf@...zon.com>,
        Marius Hillenbrand <mhillenb@...zon.de>, kvm@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, kernel-hardening@...ts.openwall.com,
        linux-mm@...ck.org, Alexander Graf <graf@...zon.de>,
        David Woodhouse <dwmw@...zon.co.uk>,
        the arch/x86 maintainers <x86@...nel.org>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>
Subject: Re: [RFC 00/10] Process-local memory allocations for hiding KVM
 secrets

On 6/13/19 12:27 AM, Alexander Graf wrote:
>> Where's the context-switching code?  Did I just miss it?
> 
> I'm not sure I understand the question. With this mechanism, the global
> linear map pages are just not present anymore, so there is no context
> switching needed. For the process local memory, the page table is
> already mm local, so we don't need to do anything special during context
> switch, no?

Thanks for explaining, I was just confused.

Andy reminded me when comparing it to the LDT area: since this area is
per-mm/pgd and we context switch that *obviously* there's no extra work
to do at context switch time, as long as the area is marked non-Global.