linux-kernel - Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue

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: <20110726193336.GH32536@aftab>
Date:	Tue, 26 Jul 2011 21:33:36 +0200
From:	Borislav Petkov <bp@...64.org>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	Borislav Petkov <bp@...64.org>, Ray Lee <ray-lk@...rabbit.org>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	LKML <linux-kernel@...r.kernel.org>,
	"Przywara, Andre" <Andre.Przywara@....com>,
	"Pohlack, Martin" <Martin.Pohlack@....com>
Subject: Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue

On Tue, Jul 26, 2011 at 02:47:44PM -0400, Ingo Molnar wrote:
> So, unless i got the stats right, unmodified kernel has like a 75%
> mis-aligned rate, while with the simple fix this goes down to 30%?

Nah, I don't think this workaround has such an impact. Due
to the differing link order and the workaround tweaking
_only_ the start of the VA space of the process (see
http://marc.info/?l=linux-kernel&m=131163083618197), it actually doesn't
change a lot:

Total r-xp mappings: 902, aliasing: 282 (31.264%)

(I know, I know, those are different numbers but the percentage is in
the same ballpark).

> Have you run the numbers on the stock, unmodified kernel by any 
> chance, just to make sure the stats are ok?

attached.

-- 
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
GM: Alberto Bozzo
Reg: Dornach, Landkreis Muenchen
HRB Nr. 43632 WEEE Registernr: 129 19551

View attachment "unmodified-results.txt" of type "text/plain" (21279 bytes)