i965: Fix Haswell CS per-thread scratch space encoding.

i965: Fix Haswell CS per-thread scratch space encoding.

Most scratch stages use power of two sizes, in kilobytes, where
0 means 1kB.  But compute shaders on Haswell have a minimum of 2kB,
and use a representation where 0 = 2kB.

This meant that we were effectively telling the hardware to allocate
each thread twice as much space as we meant to, while simultaneously
not allocating that much space in the buffer, leading to overflows.

Note that the existing code is completely wrong for Ivybridge,
but that will take additional work to sort out, so I've left it
as is for now.  A subsequent commit will take care of that.

Together with the previous patches, this fixes rendering corruption
on Synmark's Gl43CSDof on Haswell.

Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>