Re: [PATCH 5/6] x86, NMI: Allow NMI reason io port (0x61) to beprocessed on any CPU

From: huang ying
Date: Sat Feb 26 2011 - 06:19:27 EST


On Sat, Feb 26, 2011 at 4:02 PM, Cyrill Gorcunov <gorcunov@xxxxxxxxx> wrote:
> On 02/23/2011 05:39 AM, Maciej W. Rozycki wrote:
> ...
>> Â[Catching up with old e-mail...]
>> ÂIn line with the comment above that you're removing -- have you (or
>> anyone else) adjusted code elsewhere so that external NMIs are actually
>> delivered to processors other than the BSP? ÂI can't see such code in this
>> series nor an explanation as to why it wouldn't be needed.
>> ÂFor the record -- the piece of code above reflects our setup where the
>> LINT1 input is enabled and configured for the NMI delivery mode on the BSP
>> only and all the other processors have this line disabled in their local
>> APIC units. ÂIf system NMIs are to be handled after the removal of the
>> BSP, then another processor has to be selected and configured for NMI
>> reception. ÂAlternatively, all local units could have their LINT1 input
>> enabled and arbitrate handling, although it would be quite disruptive as
>> all the processors would take the interrupt if it happened. ÂOTOH it would
>> be more fault-tolerant in the case of a CPU failure. ÂOn a typical x86 box
>> the system NMI cannot be routed to an I/O APIC input.
>> Â Maciej
> ÂHi Maciej, good catch! The code doesn't reconfig LVT. As just Don pointed
> it might be Intel is working on something, dunno. Probably we better should
> drop this patch for now (at least until LVT reconfig would not be
> implemented).

Why? Without LVT reconfig, system with this patch can not work
properly? This is just one of the steps to make CPU 0 hot-removable.
We must enable CPU 0 hot-removing in one step?

Best Regards,
Huang Ying
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at