linux-kernel - Re: [PATCH v4 0/2] fix MADV_COLLAPSE issue if THP settings are disabled

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: <3ec483b4-9f13-daa4-68ac-2af3eabe8583@google.com>
Date: Wed, 25 Jun 2025 14:51:52 -0700 (PDT)
From: Hugh Dickins <hughd@...gle.com>
To: David Hildenbrand <david@...hat.com>
cc: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>, 
    Hugh Dickins <hughd@...gle.com>, 
    Baolin Wang <baolin.wang@...ux.alibaba.com>, akpm@...ux-foundation.org, 
    ziy@...dia.com, Liam.Howlett@...cle.com, npache@...hat.com, 
    ryan.roberts@....com, dev.jain@....com, baohua@...nel.org, 
    zokeefe@...gle.com, shy828301@...il.com, usamaarif642@...il.com, 
    linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v4 0/2] fix MADV_COLLAPSE issue if THP settings are
 disabled

On Wed, 25 Jun 2025, David Hildenbrand wrote:
> 
> I know, See my other mail, the problem is rather if there is no somebody
> relying on never+MADV_COLLAPSE from doing the MADV_COLLAPSE-documented thing.
> 
> It's a mess.
> 
> (I have the suspicion that Hugh might know of such a user :) )

I've not yet read my way through this firestorm I've raised,
but on this point: no, I don't know of such a user.

You'll be suspecting that I know of some such use by Google: no, I haven't
even investigated to see if that's the case; I think not, I think we're
not neverers, but cannot check at the moment (and might have got in a 
muddle with the defrag options).

I never(!) bothered to investigate that, because if Google does rely on
this behaviour, it is very easy for Google to maintain its own variation
from whatever is decided here (though management won't like me saying so).

My concern is for everyone else who read the madvise MADV_COLLAPSE manpage.

Hugh