Fix regression test parallel-make hazard.

Fix regression test parallel-make hazard.

Back-patch 9.4-era commit 384f933046dc9e9a2b416f5f7b3be30b93587c63 into
the previous branches.  Although that was only advertised as repairing a
problem with missed header-file dependencies, it turns out to also be
important for parallel make safety.  The previous coding allowed two
independent make jobs to get launched concurrently in contrib/spi.
Normally this would be OK, because they are building independent targets;
but if --enable-depend is in use, it's unsafe, because one make run might
try to read a .deps file that the other one is in process of rewriting.
This is evidently the cause of buildfarm member francolin's recent failure
in the 9.2 branch.  I believe this patch will result in only one subsidiary
make run, making it safe(r).

Report: http://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=francolin&dt=2016-08-12%2017%3A12%3A52