linux-kernel - Re: LKMM: Making RMW barriers explicit

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: <Zk9waJNBwifS/Ops@andrea>
Date: Thu, 23 May 2024 18:35:52 +0200
From: Andrea Parri <parri.andrea@...il.com>
To: Jonas Oberhauser <jonas.oberhauser@...weicloud.com>
Cc: Alan Stern <stern@...land.harvard.edu>,
	Hernan Ponce de Leon <hernan.poncedeleon@...weicloud.com>,
	"Paul E. McKenney" <paulmck@...nel.org>,
	linux-kernel@...r.kernel.org, linux-arch@...r.kernel.org,
	kernel-team@...a.com, boqun.feng@...il.com, j.alglave@....ac.uk,
	luc.maranget@...ia.fr, Joel Fernandes <joel@...lfernandes.org>
Subject: Re: LKMM: Making RMW barriers explicit

> I would phrase it more extreme: I want to get rid of the unnecessary
> non-standard parts of the herd representation.

Please indulge the thought that what might appear to be "non-standard"
to one or one's community might appear differently to others.

Continuing with the example above, I'm pretty sure your "standard" and
simple idea of mb-reads and mb-writes, or even "unsuccessful" mb-reads
will turn up the nose of many kernel developers...  The current repre-
sentation for xchg() was described in the ASPLOS'18 work and it's been
used (& tested) upstream since the LKMM was first merged ~6 years ago.

But that's not the point, "standards" can change and certainly kernels
and tools do.  My remark was more to point out that you're not getting
rid of anything..., you're simply proposing a different representation
(asking kernel developers & maintainers to "deal with it"): here's why
I was and I am looking forward to something more than "because we can".

  Andrea