=?gb2312?b?tPC4tA==?=: coherent hypertransport enumeration on opteron

[Eric W. Biederman]

YhLu <YhLu at tyan.com> writes:

> Stefan,
> 
> I swap the 
> 
> 	PCI_ADDR(0, 0x18, 0, 0x6C), 0xffffff8c, 0x00000070, //1C
> 
> The 4th line. It can go through setup_coherent_ht_domain.
> 
> But seems then both CPU all works. Please refer the attached.

Congratulations.

I refuse to put any more hard codes in the tree at this point.  The code
should at least be trying to solve the problems generically.  But at least
someone has made this work.  So when failures happen there is
something to compare against.

Eric