i965: Fix scratch overallocation if the original slot size was already a power of...

i965: Fix scratch overallocation if the original slot size was already a power of two.

The bitwise arithmetic trick used in brw_get_scratch_size() to clamp
the scratch allocation to 1KB has the unintended side effect that it
will cause us to allocate 2x the required amount of scratch space if
the original per-thread scratch size happened to be already a power of
two.  Instead use the obvious MAX2 idiom to clamp the scratch
allocation to the expected range.

Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>