On Wed, 29 Mar 2000, Toru Nishimura wrote:

> Isn't it ridiculous pmap_protect() does following, is it?
...
>                         MachTLBUpdate(sva | asid, entry);
>                 }
>         }
> 
> When pmap_protect() is called by uvmspace_fork1(), code above fills a
> bunch of entries into TLB which has only the capacity of 56, I think.

  The R4000 only has 48 total entries (although each entry is for two
pages), and only 40 entries available for random use.  [I think the
number of wired entries could be reduced, at least for the pmax.]

  Perhaps we need a different TLBUpdate that only updates current entries,
but does not enter new ones?

--
Michael L. Hitch			mhitch@montana.edu
Computer Consultant
Information Technology Center
Montana State University	Bozeman, MT	USA