are we sure it isn't the icache that's the problem?
the icache isn't coherent with stores from the CPU, and I can't think of
anything in the NFS i/o path that would do any icache flushing.
is there some mechanism for handling this, or is it just missing?

-Chuck


On Sat, Nov 23, 2002 at 01:54:07PM -0800, Jason R Thorpe wrote:
> Folks...
> 
> On my CP1500 (diskless, with only 64M of RAM), the follow patch
> is required in order for my system to make it through a GCC 3.3
> "make bootstrap".
> 
> I know that, in theory, a dcache flush shouldn't be necessary in
> pmap_clear_modify(), since the UltraSPARC cache is write-though.
> 
> However, emperically, it's necessary.  Anyone have any bright
> ideas? :-)
> 
> -- 
>         -- Jason R. Thorpe <thorpej@wasabisystems.com>