Messages in this thread | | | From | Gene Heskett <> | Subject | Re: Linux* Processor Microcode Data File | Date | Fri, 13 Mar 2009 10:55:44 -0400 |
| |
On Friday 13 March 2009, Dragoslav Zaric wrote: >--------------------------------------------- >I found this on web site http://kerneltrap.org > >Tigran Aivazian, author of the IA32 microcode driver and Microcode >Update Utility for Linux explained: > >"The answer to your question is that some Intel CPUs (just like any >other hardware or software) contain bugs >and, fortunately, their architecture is flexible enough to provide a >way to fix those bugs by means of loading the >microcode update on the fly, i.e. while the OS is running with no need >to reboot (in fact, rebooting or otherwise >resetting the CPU causes the update to be lost and requires to run the >update again)."
And what runs this update? I saw it apply once in the dmesg output, about 3 full powerdown reboots ago, never since, and the code is still there in /lib/firmware
AMD quad core 9550 here, stepping 03.
Thanks. >--------------------------------------------- > >So when you reboot system, you reset CPU to original state, and after >that you must apply microcode, and this >is what is actually doing right now, you put microcode in folder >/etc/firmware and after boot microcode is loaded. > >So I think for CPU hotplug it is also natural that microcode is loaded >after plugging, because you can not use >microcode from boot process. Maybe kernel should have database of >tested microcodes, so when you plug CPU >appropriate microcode is loaded.
-- Cheers, Gene "There are four boxes to be used in defense of liberty: soap, ballot, jury, and ammo. Please use in that order." -Ed Howdershelt (Author) The only thing that experience teaches us is that experience teaches us nothing. -- Andre Maurois (Emile Herzog)
| |