Re: [PATCH -v3 5/6] x86, NMI, treat unknown NMI as hardware error

[Don Zickus <dzickus@redhat.com>]

On Mon, Oct 11, 2010 at 05:08:29PM -0400, Don Zickus wrote:
> On Sun, Oct 10, 2010 at 04:13:11PM +0200, Andi Kleen wrote:
> > > > These systems are identified via the presentation of APEI HEST or
> > > > some PCI ID of the host bridge. The PCI ID of host bridge instead of
> > > > DMI ID is used, so that the checking can be done based on the platform
> > > > type instead of motherboard. This should be simpler and sufficient.
> > > > 
> > > > The method to identify the platforms is designed by Andi Kleen.
> > > 
> > > Why not make the new flag also a boot option so you can force it on for
> > > platforms where we don't auto whitelist it.
> > 
> > You can already set it at run time using sysctl.
> > 
> > echo 1 > /proc/sys/kernel/panic_on_unrecovered_nmi
> > echo 1 > /proc/sys/kernel/panic_on_io_nmi
> 
> I get the impression Alan was talking about the option
> 
> unknown_nmi_as_hwerr
> 
> which isn't hooked into a sysctl but will cause machines to panic.

Gah.  disregard this, my brain is tired from a long day.

Cheers,
Don