Re: interrupts on APs

[Manuel Bouyer <bouyer%antioche.eu.org@localhost>]

On Fri, Dec 09, 2011 at 11:34:00AM -0600, David Young wrote:
> > Tested on a Dell poweredge 2850 with 2 Xen 3,2Ghz (single-core, hyperthread)
> > with:
> > pchb0 at pci0 dev 0 function 0
> > pchb0: Intel E7525 Memory Controller Hub (rev. 0x09)
> > ppb0 at pci0 dev 2 function 0: Intel E7525 PCI Express Port A (rev. 0x09)
> > 
> > Boot fails with obvious interrupts issues (messages from ehci controller
> > which looks like timeouts; 'lost interrupts' from cmdide).
> > With plain GENERIC from HEAD, there's no such issues.
> 
> Well, *that's* disappointing! :-)
> 
> I don't have much idea how interrupts are routed.  Is it possible that
> NetBSD needs to write some registers on the CPU/chipset to enable
> interrupt machinery on the application processors because the BIOS
> neglected to do so?

I've no idea, but not that this is one of the chipset linux has
in its blacklist for this feature ...

-- 
Manuel Bouyer <bouyer%antioche.eu.org@localhost>
     NetBSD: 26 ans d'experience feront toujours la difference
--