Add .../share/mk to the default system make path. This will fix the problem
with broken in-tree builds (which are used far more pervasively than I'd
known outside the tree). However, weird results may now happen if at any
point in the tree above you there happens to be a directory that has
subdirectory of share/mk, as unpredictable results will follow. This was
considered the lessor of the two evils, at least for now. In the future this
will be removed again when the underlying issues are resolved.
For MFCing, this is to ensure that when upgrading to head the share/mk
in-tree is always used. Otherwise several build features will not work.
This passes a build using head's bmake which has this as the default
already.
Relnotes: yes
r266074:
Move old fmake tests into bmake and hook them to the build.
This first step is mostly to prevent the code from rotting even further
and to ensure these do not get wiped when fmake's code is removed from
the tree.
These tests are currently being skipped because they detect the underlying
make is not fmake and thus disable themselves -- and the reason is that
some of the tests fail, possibly due to legitimate bugs. Enabling them to
run against bmake will come separately.
Lastly, it would be ideal if these tests were fed upstream but they are
not ready for that yet. In the interim, just put them under usr.bin/bmake/
while we sort things out. The existence of a different unit-tests directory
within here makes me feel less guilty about this.
Change confirmed working with a clean amd64 build.
r266104:
Undo changes to the generated Makefile. Move tests directory to proper
location, including updating the test to work in the more-fragile
fmake -> bmake bootstrap environment.
r266147:
Makefile.inc is also included by the tests subdirectory, which results
in SUBDIRS having tests added to it, which fails. Work around this by
checking to make sure tests exists before adding it to subdirs and
work to get the generated file fixed so we can rename Makefile.inc to
something else so it isn't automatically included by subdirs...
Discussed with: sjg
r255285:
If MAKE_JOB_ERROR_TOKEN is set to false, do not put an error token ("E")
into the job queue.
This avoids closing down an entire build on failure of one branch.
Probably has no use outside the context of universe/tinderbox.
Reviewed by: obrien
r255916:
Fix Fx syntax.
PR: 182269
Approved by: re@
r258113:
Avoid SEGV when passed NULL for list
r258114:
Don't SEGV when Hash_Table is uninitialized
r261212:
Merge bmake-20140101 from vendor
r266760:
Portmgr no longer need the UL hack.
Reviewed by: obrien
r268437:
Update to bmake-20140620
Main change is detection of malformed variable references.
Reviewed by: obrien
make) ended up being built with -DFORCE_MACHINE. This broke the lib32
built for amd64 & powerpc64.
This fix is comes with the next import of bmake, but is committed here
and now to minimize the exposure to the bug.
Submitted by: Simon Gerraty <sjg@juniper.net>
of FreeBSD's make by setting WITH_BMAKE. The WITH_BMAKE build makes it
easy for people to switch while working out the kinks -- think ports
tree here. The option will be removed in due time.
Submitted by: Simon Gerraty (sjg@juniper.net)
