[PATCH], issue EOI to APIC prior to calling crash_kexec in die_nmi path

Neil Horman nhorman at redhat.com
Wed Feb 6 16:04:07 EST 2008

On Wed, Feb 06, 2008 at 12:21:30PM -0800, H. Peter Anvin wrote:
> Neil Horman wrote:
> >Can an APIC accept an NMI while already handling an NMI?  I didn't think 
> >they
> >would interrupt one another, but rather, pend until such time as the 
> >previous
> >NMI was cleared
> The CPU certainly won't (there is a hidden flag that's cleared on IRET 
> which disables NMI; it's possible to re-enable NMI by executing a dummy 
> IRET inside the NMI handler.)
> 	-hpa

So that would be another solution I would expect.  Would you rather I
investigate that, or is the proposed solution more reasonable?


 *Neil Horman
 *Software Engineer
 *Red Hat, Inc.
 *nhorman at redhat.com
 *gpg keyid: 1024D / 0x92A74FA1

More information about the kexec mailing list