linux-kernel - Re: [PATCH v21 1/4] mm: add VM_DROPPABLE for designating always lazily freeable mappings

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: <8bf64731-9e5c-4c8c-b46b-5b18ae3110a1@redhat.com>
Date: Mon, 8 Jul 2024 10:23:10 +0200
From: David Hildenbrand <david@...hat.com>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: "Jason A. Donenfeld" <Jason@...c4.com>, linux-kernel@...r.kernel.org,
 patches@...ts.linux.dev, tglx@...utronix.de, linux-crypto@...r.kernel.org,
 linux-api@...r.kernel.org, x86@...nel.org,
 Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
 Adhemerval Zanella Netto <adhemerval.zanella@...aro.org>,
 Carlos O'Donell <carlos@...hat.com>, Florian Weimer <fweimer@...hat.com>,
 Arnd Bergmann <arnd@...db.de>, Jann Horn <jannh@...gle.com>,
 Christian Brauner <brauner@...nel.org>,
 David Hildenbrand <dhildenb@...hat.com>, linux-mm@...ck.org
Subject: Re: [PATCH v21 1/4] mm: add VM_DROPPABLE for designating always
 lazily freeable mappings

> As a side note, I'll raise that I am not a particular fan of the
> "droppable" terminology, at least with the "read 0s" approach.
> 
>   From a user perspective, the memory might suddenly lose its state and
> read as 0s just like volatile memory when it loses power. "dropping
> pages" sounds more like an implementation detail.

Just to raise why I consider "dropping" an implementation detail: in 
combination with a previous idea I had of exposing "nonvolatile" memory 
to VMs, the following might be interesting:

A hypervisor could expose special "nonvolatile memory" as separate guest 
physical memory region to a VM.

We could use that special memory to back these MAP_XXX regions in our 
guest, in addition to trying to make use of them in the guest kernel, 
for example for something similar to cleancache.

Long story short: it's the hypervisor that could be effectively 
dropping/zeroing out that memory, not the guest VM. "NONVOLATILE" might 
be clearer than "DROPPABLE".

But again, naming is hard ... :)

-- 
Cheers,

David / dhildenb