RE: [PATCH] x86/hpet: Read HPET directly if panic in progress

From: Luck, Tony
Date: Wed Jun 05 2024 - 11:51:21 EST


> > Which types exactly do you mean when you're looking at the severities[]
> > array in severity.c?
> >
> > And what scenario are you talking about?
> >
> > To get an #MC exception and detect only UCNA/SRAO errors? Can that even
> > happen on any hardware?
> >
>
> Yes, I mean an #MC exception happened and detect only like SRAO errors
> like below:
>
> MCESEV(
> AO, "Action optional: memory scrubbing error",
> SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK,
> MCI_STATUS_UC|MCACOD_SCRUB)
> ),
> MCESEV(
> AO, "Action optional: last level cache writeback error",
> SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
> ),
>
> I think these errors are actually encountered on some platforms that
> support these type of errors report to the #MC.

Intel servers from Nehalem through Cascade Lake reported memory controller
patrol scrub uncorrected error with #MC and SRAO signature.

Icelake and newer use CMCI with a UCNA signature.

-Tony