Messages in this thread | | | Date | Thu, 12 Mar 2009 14:38:46 +0100 | From | Martin Wilck <> | Subject | Re: [PATCH] x86 (64): make calibrate_APIC_clock() SMI-safe (take 3) |
| |
Hi Jean,
same answer as on Bugzilla...
> Sorry for replying to such an old thread, but did this patch go > anywhere? I can't seem to find it in git. Was it somehow obsoleted > by a different fix for the same issue (SMI flood during APIC > calibration)? Or is the upstream kernel still affected?
We were asked for a solution for all affected architectures (in particular, also i386) which was more than we were able to do at the time, given that the pressure had been reduced by finding a BIOS fix for the particular situation on system in question.
The APIC clock calibration code on i386 is more complex than x86_64, we saw no way to provide a high-quality, regression-safe, tested patch for that to upstream with a reasonable amount of effort.
That aside, I still think the x86_64 patch is fine and won't cause regressions. It just doesn't help on 32bit systems.
Martin
-- Martin Wilck PRIMERGY System Software Engineer FSC IP ESP DEV 6
Fujitsu Siemens Computers GmbH Heinz-Nixdorf-Ring 1 33106 Paderborn Germany
Tel: ++49 5251 525 2796 Fax: ++49 5251 525 2820 Email: mailto:martin.wilck@fujitsu-siemens.com Internet: http://www.fujitsu-siemens.com Company Details: http://www.fujitsu-siemens.com/imprint.html
| |