> actually, doesn't kernel bcopy() not work for overlapping
   > regions of memory, by design?  they are not exactly the same.
   
   Depends what you mean by 'not work'....

as in, by definition, the kernel bcopy(9) will do nothing special
to avoid not working for overlapping regions, unlike userland
bcopy(3).  ovbcopy(9) does the check like bcopy(3)...


as far as your strange screen memory issue, sounds like using the
cached/uncached addresses differently and using standard copying
routines is your real problem - not feeding it a "uniform" address
space...  of course, this has nothing really to do with the fact
that kernel & userland bcopy() have slightly different semantics. :-)


.mrg.