On Wednesday, March 02, 2011 8:07:59 am Mike Tancsa wrote: > On 3/2/2011 7:55 AM, John Baldwin wrote: > > > > Hmm, the interrupt pins on the each lapic look fine (they all either have a > > legal vector, are using NMI delivery, or are masked). > > > > All of the places that send IPIs have the interrupt vectors hard-coded as > > constant values in the code. > > > > Unfortunately there is no register that tells us which illegal vector was > > posted. > > > > Were you doing anything related to changing the state of device interrupts > > (cpuset -x, kldload, kldunload, etc.) when this happened? > > Hi, > No, nothing at all. I checked the logs again and nothing unusual > leading up to it, nor was anything recorded on the serial console other > than that error. Do you think its just a hardware issue?
No, was trying to think if there was a scenario where an I/O APIC pin or MSI message could specify an illegal vector. Can you reproduce this at all? -- John Baldwin _______________________________________________ [email protected] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[email protected]"
