Re: [PATCH] x86: put trigger in to detect mismatched apic versions.

[Mike Travis <travis@sgi.com>]

Jack Steiner wrote:
> On Sun, Jan 18, 2009 at 08:08:49PM +0100, Ingo Molnar wrote:
>> * Jack Steiner <steiner@sgi.com> wrote:
>>
>>>> Btw, I checked with our UV architect and the problem is that we need a 
>>>> 16 bit apic id which is what caused the MAX_APICS to be bumped to 32k. 
>>>> The lower 8 bits are the normal apic id, and the upper bit relate to 
>>>> the node.  This means cpu 0 on node 0 has the same apic id as cpu 0 on 
>>>> node 1, etc.  I also asked about whether we could rely on always 
>>>> having
>>> Not strictly true. The apicids in the ACPI tables are always globally 
>>> unique across the entire system. Because of the size of UV systems, UV 
>>> needs 16 bit apicids. This fits in the ACPI apicid id/eid fields.

Ahh, I did mean to say this applied to the lower 8 bits only.
>>>
>>> The actual processor apicid register is unfortunately only 11 bits and 
>>> there are some restrictions on the actual values loaded into the apicid 
>>> register.

This is for x2apics only, yes?

>>>
>>> If we can put unique ids into the apicid register, we do. If we can't, 
>>> the function that reads the apicid will automatically supply the rest of 
>>> the bits.  Most of the kernel is unaware that the processor apicid 
>>> register may have only a subset of the bits that are in the ACPI tables.

>> apicid remapping is something we need/want, so we cannot remove that 
>> array. But it would be nice to offload such properties to the percpu area 
>> instead - is there any reason why that is hard? The local apic is attached 
>> to a CPU in any case. Is there some early init reason that complicates 
>> this?
> 
> I can't think of any reason why it could not be moved into
> the percpu data area. Mike???

WHich array?  There are two now, the x86_cpu_to_apicid and x86_bios_cpu_apicid
that are in the percpu area?  (Maybe it's time to find out why there are two. ;-)

Thanks,
Mike