[coreboot] locking...

[Carl-Daniel Hailfinger]

On 20.06.2009 00:02, Myles Watson wrote:
>>> Field Descriptions
>>> Scratch Data (Data)-Bits 31-0.
>>>
>>> So you get one per socket, first one at PCI_DEV(0,0x18,2) 0x9C
>>>
>>>       
>> AFAICS this is not MMIO, so it's unusable for locking.
>>     
>
> ?  I thought you were looking for config space.  Why does it need to be
> MMIO?
>   

I'm unaware of any method to perform atomic value swaps or atomic
increments in config space. Unless I'm mistaken, such atomic operations
are required for locking.


>> I did look at the
>> Family 0Fh BKDG. Should I have looked elsewhere?
>>     
>
> I'm not an expert.  I'd just seen this scratch register recently.
>   

Thanks for digging it up. It seems that some CPU revisions change the
definition to be partially a scratch register.

Regards,
Carl-Daniel

-- 
http://www.hailfinger.org/