linux-kernel - Re: [PATCH v3 10/10] x86-64: Add CONFIG_UNSAFE

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: <13093.1306952865@turing-police.cc.vt.edu>
Date:	Wed, 01 Jun 2011 14:27:45 -0400
From:	Valdis.Kletnieks@...edu
To:	Andrew Lutomirski <luto@....edu>
Cc:	Ingo Molnar <mingo@...e.hu>, x86@...nel.org,
	Thomas Gleixner <tglx@...utronix.de>,
	linux-kernel@...r.kernel.org, Jesper Juhl <jj@...osbits.net>,
	Borislav Petkov <bp@...en8.de>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Arjan van de Ven <arjan@...radead.org>,
	Jan Beulich <JBeulich@...ell.com>,
	richard -rw- weinberger <richard.weinberger@...il.com>,
	Mikael Pettersson <mikpe@...uu.se>,
	Andi Kleen <andi@...stfloor.org>
Subject: Re: [PATCH v3 10/10] x86-64: Add CONFIG_UNSAFE_VSYSCALLS to feature-removal-schedule

On Wed, 01 Jun 2011 13:41:56 EDT, Andrew Lutomirski said:

>> +         On a system with recent enough glibc (probably 2.14 or
>>  +         newer) and no static binaries, you can say N without a
>>  +         performance penalty to improve security
>>
>> So I checked my laptop (Fedora 16 Rawhide), and found a bunch of static binaries. The ones
>> that look like people may care:

> The binaries will still work -- they'll just take a small performance
> hit (~220ns on Sandy Bridge) every time they call time().

Ah. I misparsed the Kconfig help - I read it as "If you have no static binaries,
setting this to N doesn't introduce a performance hit" (with an implied "if you
have static binaries, this will hose you").  Adding "Static binaries will continue
to work at a very small performance penalty" would probably help.

Content of type "application/pgp-signature" skipped