linux-kernel - Re: [PATCH 1/3] X86: Optimise fls(), ffs() and fls64()

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] [day] [month] [year] [list]

Message-ID: <20100415114146.GA10863@shareable.org>
Date:	Thu, 15 Apr 2010 12:41:47 +0100
From:	Jamie Lokier <jamie@...reable.org>
To:	Avi Kivity <avi@...hat.com>
Cc:	David Howells <dhowells@...hat.com>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Matthew Wilcox <matthew@....cx>,
	Ralf Baechle <ralf@...ux-mips.org>, mingo@...e.hu,
	tglx@...utronix.de, linux-arch@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/3] X86: Optimise fls(), ffs() and fls64()

Avi Kivity wrote:
> Likely.  But we haven't tested all current and future x86 clones, and 
> they may be based off the Intel documentation instead of the AMD 
> documentation.

I wonder about that too.  I got the impression Transmeta did lots of
testing real x86s in all sorts of corner cases, because the manuals
don't cover everything that the broad base of software depends on in
practice.  Clone makers have to do it to a much higher standard than
emulators because you can't generally release patches...

I think Via (including whatever the CPU line was formerly called)
have been bitten a few times by not quite matching software
expectations.

Even Intel was caught on x86_64 at the beginning by slight differences
when they cloned AMD's design :-)

-- Jamie
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/