linux-kernel - Re: [PATCH 1/1] i386: Geode's TSC is not neccessary to mark tu unstable

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]

Date:	Sun, 15 Jul 2007 21:06:27 +0200
From:	Juergen Beisert <juergen127@...uzholzen.de>
To:	TAKADA Yoshihito <takada@....nifty.com>
Cc:	linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/1] i386: Geode's TSC is not neccessary to mark tu unstable

Hi,

On Sunday 15 July 2007 14:00, TAKADA Yoshihito wrote:
> Hi. I reported to remove pit_latch_buggy(http://lkml.org/lkml/2007/2/10/8).
> In the report, I stated that TSC was unstable.
> When I installed 2.6.21, GeodeGX's TSC is stable.

GeodeGX1's TSC is stable until you activate halt/suspend feature. In 
arch/i386/kernel/cpu/cyrix.c:geode_configure() it will be activated by 
default. But due to a macro failure the line
  setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
does nothing.
Replace the setCx86/getCx86 macros by the attached patch, and the TSC will be 
unstable again!

So it makes sense to mark the TSC unstable if the halt/suspend feature is 
activated.

Juergen

View attachment "setup_correct_chipset_access_functions.patch" of type "text/x-diff" (3555 bytes)