Messages in this thread | | | From | TAKADA Yoshihito <> | Subject | Re: [PATCH 1/1] i386: Geode's TSC is not neccessary to mark tu unstable | Date | Mon, 16 Jul 2007 08:59:00 +0900 |
| |
Hi. Thanks. you are right. TSC is still unstable.
On Sun, 15 Jul 2007 21:06:27 +0200 Juergen Beisert <juergen127@kreuzholzen.de> wrote:
> 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
-- TAKADA <takada@mbf.nifty.com>
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |