include/download.mk: generate reproducable SCM tarballs

Apply a number of changes to the tarball generation in order to produce
identical files on different systems:

1) Use an explicit `gzip -cn` to avoid storing file mtime in the gzip header
2) Instruct `tar` to unconditionally use uid and gid 0 for archive members
3) Instruct `tar` to sort archive members by file name
4) For SCMs that do not preserve file modification times like Git or Mercurial,
   use the date of the last commit to the repository and pass it as `--mtime`
   value to `tar`

After these changes, locally produced tarballs generated from SCM checkouts
should be identical on any system, simplifying the mirroring of cache archives.

Signed-off-by: Jo-Philipp Wich <jo@mein.io>

diff --git a/include/download.mk b/include/download.mk
index 74e2c317d6ce3f2369dc2a0d3f7b4e94270366e1..227612d9b844abbae0e60d6740bde663cab2c944 100644 (file)
--- a/include/download.mk
+++ b/include/download.mk
@@ -33,9 +33,9 @@ $(strip \
 endef
 
 # code for creating tarballs from cvs/svn/git/bzr/hg/darcs checkouts - useful for mirror support
-dl_pack/bz2=$(TAR) cjf $(1) $(2)
-dl_pack/gz=$(TAR) czf $(1) $(2)
-dl_pack/xz=$(TAR) c $(2) | xz -zc > $(1)
+dl_pack/bz2=$(TAR) --owner=0 --group=0 --sort=name $$$${TAR_TIMESTAMP:+--mtime="$$$$TAR_TIMESTAMP"} -cjf $(1) $(2)
+dl_pack/gz=$(TAR) --owner=0 --group=0 --sort=name $$$${TAR_TIMESTAMP:+--mtime="$$$$TAR_TIMESTAMP"} -c $(2) | gzip -nc > $(1)
+dl_pack/xz=$(TAR) --owner=0 --group=0 --sort=name $$$${TAR_TIMESTAMP:+--mtime="$$$$TAR_TIMESTAMP"} -c $(2) | xz -zc > $(1)
 dl_pack/unknown=echo "ERROR: Unknown pack format for file $(1)"; false
 define dl_pack
        $(if $(dl_pack/$(call ext,$(1))),$(dl_pack/$(call ext,$(1))),$(dl_pack/unknown))
@@ -79,6 +79,7 @@ define DownloadMethod/svn
                svn export --non-interactive --trust-server-cert -r$(VERSION) $(URL) $(SUBDIR) || \
                svn export --non-interactive -r$(VERSION) $(URL) $(SUBDIR) ) && \
                echo "Packing checkout..." && \
+               export TAR_TIMESTAMP="" && \
                $(call dl_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
                mv $(TMP_DIR)/dl/$(FILE) $(DL_DIR)/ && \
                rm -rf $(SUBDIR); \
@@ -96,6 +97,7 @@ define DownloadMethod/git
                (cd $(SUBDIR) && git checkout $(VERSION) && \
                git submodule update --init --recursive) && \
                echo "Packing checkout..." && \
+               export TAR_TIMESTAMP=`cd $(SUBDIR) && git log -1 --format='@%ct'` && \
                rm -rf $(SUBDIR)/.git && \
                $(call dl_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
                mv $(TMP_DIR)/dl/$(FILE) $(DL_DIR)/ && \
@@ -110,8 +112,9 @@ define DownloadMethod/bzr
                cd $(TMP_DIR)/dl && \
                rm -rf $(SUBDIR) && \
                [ \! -d $(SUBDIR) ] && \
-               bzr export -r$(VERSION) $(SUBDIR) $(URL) && \
+               bzr export --per-file-timestamps -r$(VERSION) $(SUBDIR) $(URL) && \
                echo "Packing checkout..." && \
+               export TAR_TIMESTAMP="" && \
                $(call dl_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
                mv $(TMP_DIR)/dl/$(FILE) $(DL_DIR)/ && \
                rm -rf $(SUBDIR); \
@@ -126,6 +129,7 @@ define DownloadMethod/hg
                rm -rf $(SUBDIR) && \
                [ \! -d $(SUBDIR) ] && \
                hg clone -r $(VERSION) $(URL) $(SUBDIR) && \
+               export TAR_TIMESTAMP=`cd $(SUBDIR) && hg log --template '@{date}' -l 1` && \
                find $(SUBDIR) -name .hg | xargs rm -rf && \
                echo "Packing checkout..." && \
                $(call dl_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
@@ -142,6 +146,7 @@ define DownloadMethod/darcs
                rm -rf $(SUBDIR) && \
                [ \! -d $(SUBDIR) ] && \
                darcs get -t $(VERSION) $(URL) $(SUBDIR) && \
+               export TAR_TIMESTAMP=`cd $(SUBDIR) && LC_ALL=C darcs log --last 1 | sed -ne 's!^Date: \+!!p'` && \
                find $(SUBDIR) -name _darcs | xargs rm -rf && \
                echo "Packing checkout..." && \
                $(call dl_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \