On 31.10.2022 19:37, Andrew Cooper wrote: > On 31/10/2022 15:55, Jan Beulich wrote: >> Hello, >> >> quite likely this isn't new, but I've ended up noticing it only recently: >> On an oldish system where I hand a HVM guest an SR-IOV NIC (not sure yet >> whether that actually matters) all APs have that warning issued, with all >> reported values zero except for the very first IRR one - that's 00080000. >> Which is suspicious by itself, for naming vector 0x13, i.e. below 0x20 >> and hence within CPU exception range. > > To be clear, these are the VM's APs ?
Yes. I'm now also pretty sure this is a Linux side issue, as I've verified it to be new in 6.0. Debugging is complicated some by the host not being very reliable anymore - the SR-IOV card has been producing floods of corrected errors for a long time, but recently apparently uncorrected errors have been occurring every now and then, resulting in a host reset. But I'll keep trying to see if I can spot where this behavior is coming from. Jan
