linux-kernel - Re: [PATCH 1/2] x86: Remove dynamic NOP selection

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: <20240121195649.7355e1d5@rorschach.local.home>
Date: Sun, 21 Jan 2024 19:56:49 -0500
From: Steven Rostedt <rostedt@...dmis.org>
To: "H. Peter Anvin" <hpa@...or.com>
Cc: Thorsten Glaser <tg@...ian.org>, Peter Zijlstra <peterz@...radead.org>,
 x86@...nel.org, torvalds@...uxfoundation.org, linux-kernel@...r.kernel.org,
 linux-toolchains@...r.kernel.org, jpoimboe@...hat.com,
 alexei.starovoitov@...il.com, mhiramat@...nel.org
Subject: Re: [PATCH 1/2] x86: Remove dynamic NOP selection

On Sun, 21 Jan 2024 16:15:57 -0800
"H. Peter Anvin" <hpa@...or.com> wrote:

> On January 21, 2024 3:58:11 PM PST, Thorsten Glaser <tg@...ian.org> wrote:
> >H. Peter Anvin dixit:
> >  
> >> But yes, with all even remotely recent CPUs all actually handling nopl
> >> properly, this isn't relevant anymore.  
> >
> >This was, incidentally, triggered by looking into a problem report that
> >something did *not* work on a Geode LX system.

What problem happened?

> >
> >People don’t just run Linux on “recent CPUs” (though I at least got me
> >an Atom and a Core2Duo for it and run BSD on my Pentium-M and VIA C7
> >systems).
> >
> >bye,
> >//mirabilos  
> 
> Yes, but it is a matter of where we optimize for performance as opposed to correctness.

There is no such thing as "optimize for correctness", it is either
correct or it is not. Correctness should always come before performance
(at least that is what Thomas has pounded into me ;-)

If a kernel use to work on a machine but a newer version no longer
works, I call that a regression.

-- Steve