Re: [PATCH] x86: machine check exception handling

["Christoph Egger" <Christoph.Egger@AMD.COM>]

On Thursday 21 June 2007 16:59:47 Keir Fraser wrote:
> On 21/6/07 15:38, "Christoph Egger" <Christoph.Egger@amd.com> wrote:
> > That's not possible. The #MC handler and the polling handler (in
> > non-fatal.c) (are going to) do something completely different than any OS
> > will ever do. See the discussion with the subject "MCA/MCE concept" for
> > more information.
>
> Well, then I guess these files will change wholesale when this new MCE
> architecture is ready. That's fine.

That's right. (Except that I don't touch Intel code)

> > In opposition to the polling handler, #MC interruption is *very* bad.
> > A #MC always means, that an uncorrectable ECC error is detected
> > by the hw. First you have to figure out, who is impacted: Is it Xen, Dom0
> > or DomU?
> > In case of Xen and Dom0 you can only do something using hw correction
> > features or crash. In case of DomU, you can kill DomU in the worst case
> > and keep the rest running.
>
> If the error is such that it will impact correct execution of a Xen
> interrupt handler (which generally do very little indeed) then you are
> boned. Your #MC handler is unlikely to work properly either. Game over.
>
> And you already know my opinion of the new "MCA/MCE concept".

Yes, from the generic point of view, but not on the conceptual details
discussed there.


Christoph


-- 
AMD Saxony, Dresden, Germany
Operating System Research Center

Legal Information:
AMD Saxony Limited Liability Company & Co. KG
Sitz (Geschäftsanschrift):
   Wilschdorfer Landstr. 101, 01109 Dresden, Deutschland
Registergericht Dresden: HRA 4896
vertretungsberechtigter Komplementär:
   AMD Saxony LLC (Sitz Wilmington, Delaware, USA)
Geschäftsführer der AMD Saxony LLC:
   Dr. Hans-R. Deppe, Thomas McCoy