From: Colin Stagner Date: Wed, 18 Feb 2026 02:31:32 +0000 (-0600) Subject: contrib/subtree: process out-of-prefix subtrees X-Git-Tag: v2.54.0-rc0~133^2 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=1f70684b517f4fcfeb7b998b0b7f3146ee8a8c75;p=thirdparty%2Fgit.git contrib/subtree: process out-of-prefix subtrees `should_ignore_subtree_split_commit` detects subtrees which are outside of the current path --prefix and ignores them. This can speed up splits of repositories that have many subtrees. Since its inception [1], every iteration of this logic [2], [3] incorrectly excludes commits. This alters the split history. The split history and its commit hashes are API contract, so this is not permissible. While a commit from a different subtree may look like it doesn't contribute anything to a split, sometimes it does. Merge commits are a particular hot spot. For these, the pruning logic in `copy_or_skip` performs: 1. a check for "treesame" parents 2. two different common ancestry checks These checks operate on the **split history**, not the input history. The split history omits commits that do not affect the --prefix. This can significantly alter the ancestry of a merge. In order to determine if `copy_or_skip` will skip a merge, it is likely necessary to compute all the split history... which is what `should_ignore_subtree_split_commit` tries to avoid. To make this logic API-preserving, we could gate it behind a new CLI argument. The present implementation is actually a speed penalty in many cases, however, so this is not done here. Remove the `should_ignore_subtree_split_commit` logic. This fixes the regression reported in [4]. [1]: 98ba49ccc2 (subtree: fix split processing with multiple subtrees present, 2023-12-01) [2]: 83f9dad7d6 (contrib/subtree: fix split with squashed subtrees, 2025-09-09) [3]: 28a7e27cff (contrib/subtree: detect rewritten subtree commits, 2026-01-09) [4]: <20251230170719.845029-1-george@mail.dietrich.pub> Reported-by: George Reported-by: Christian Heusel Signed-off-by: Colin Stagner Signed-off-by: Junio C Hamano --- diff --git a/contrib/subtree/git-subtree.sh b/contrib/subtree/git-subtree.sh index 17106d1a72..ba9fb2ee5d 100755 --- a/contrib/subtree/git-subtree.sh +++ b/contrib/subtree/git-subtree.sh @@ -785,42 +785,6 @@ ensure_valid_ref_format () { die "fatal: '$1' does not look like a ref" } -# Usage: should_ignore_subtree_split_commit REV -# -# Check if REV is a commit from another subtree and should be -# ignored from processing for splits -should_ignore_subtree_split_commit () { - assert test $# = 1 - - git show \ - --no-patch \ - --no-show-signature \ - --format='%(trailers:key=git-subtree-dir,key=git-subtree-mainline)' \ - "$1" | - ( - have_mainline= - subtree_dir= - - while read -r trailer val - do - case "$trailer" in - git-subtree-dir:) - subtree_dir="${val%/}" ;; - git-subtree-mainline:) - have_mainline=y ;; - esac - done - - if test -n "${subtree_dir}" && - test -z "${have_mainline}" && - test "${subtree_dir}" != "$arg_prefix" - then - return 0 - fi - return 1 - ) -} - # Usage: process_split_commit REV PARENTS process_split_commit () { assert test $# = 2 @@ -1006,19 +970,7 @@ cmd_split () { eval "$grl" | while read rev parents do - if should_ignore_subtree_split_commit "$rev" - then - continue - fi - parsedparents='' - for parent in $parents - do - if ! should_ignore_subtree_split_commit "$parent" - then - parsedparents="$parsedparents$parent " - fi - done - process_split_commit "$rev" "$parsedparents" + process_split_commit "$rev" "$parents" done || exit $? latest_new=$(cache_get latest_new) || exit $? diff --git a/contrib/subtree/t/t7900-subtree.sh b/contrib/subtree/t/t7900-subtree.sh index dad8dea63a..05a774ad47 100755 --- a/contrib/subtree/t/t7900-subtree.sh +++ b/contrib/subtree/t/t7900-subtree.sh @@ -428,8 +428,7 @@ test_expect_success 'split sub dir/ with --rejoin' ' # - Perform 'split' on subtree B # - Create new commits with changes to subtree A and B # - Perform split on subtree A -# - Check that the commits in subtree B are not processed -# as part of the subtree A split +# - Check for expected history test_expect_success 'split with multiple subtrees' ' subtree_test_create_repo "$test_count" && subtree_test_create_repo "$test_count/subA" && @@ -458,8 +457,8 @@ test_expect_success 'split with multiple subtrees' ' --squash --rejoin -m "Sub A Split 2" -b a2 && test "$(git -C "$test_count" rev-list --count main..a2)" -eq 2 && test "$(git -C "$test_count" rev-list --count a1..a2)" -eq 1 && - test "$(git -C "$test_count" subtree split --prefix=subBDir \ - --squash --rejoin -d -m "Sub B Split 1" -b b2 2>&1 | grep -w "\[1\]")" = "" && + git -C "$test_count" subtree split --prefix=subBDir \ + --squash --rejoin -d -m "Sub B Split 1" -b b2 && test "$(git -C "$test_count" rev-list --count main..b2)" -eq 2 && test "$(git -C "$test_count" rev-list --count b1..b2)" -eq 1 ' @@ -507,6 +506,67 @@ do ' done +# Usually, +# +# git subtree merge -P subA --squash f00... +# +# makes two commits, in this order: +# +# 1. Squashed 'subA/' content from commit f00... +# 2. Merge commit (1) as 'subA' +# +# Commit 1 updates the subtree but does *not* rewrite paths. +# Commit 2 rewrites all trees to start with `subA/` +# +# Commit 1 either has no parents or depends only on other +# "Squashed 'subA/' content" commits. +# +# For merge without --squash, subtree produces just one commit: +# a merge commit with git-subtree trailers. +# +# In either case, if the user rebases these commits, they will +# still have the git-subtree-* trailers… but will NOT have +# the layout described above. +# +# Test that subsequent `git subtree split` are not confused by this. +test_expect_success 'split with rebased subtree commit' ' + subtree_test_create_repo "$test_count" && + ( + cd "$test_count" && + test_commit file0 && + test_create_subtree_add \ + . mksubtree subA file1 --squash && + test_path_is_file subA/file1.t && + mkdir subB && + test_commit subB/bfile && + git commit --amend -F - <<'EOF' && +Squashed '\''subB/'\'' content from commit '\''badf00da911bbe895347b4b236f5461d55dc9877'\'' + +Simulate a cherry-picked or rebased subtree commit. + +git-subtree-dir: subB +git-subtree-split: badf00da911bbe895347b4b236f5461d55dc9877 +EOF + test_commit subA/file2 && + test_commit subB/bfile2 && + git commit --amend -F - <<'EOF' && +Split '\''subB/'\'' into commit '\''badf00da911bbe895347b4b236f5461d55dc9877'\'' + +Simulate a cherry-picked or rebased subtree commit. + +git-subtree-dir: subB +git-subtree-mainline: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +git-subtree-split: badf00da911bbe895347b4b236f5461d55dc9877 +EOF + git subtree split --prefix=subA --branch=bsplit && + git checkout bsplit && + test_path_is_file file1.t && + test_path_is_file file2.t && + test "$(last_commit_subject)" = "subA/file2" && + test "$(git rev-list --count bsplit)" -eq 2 + ) +' + test_expect_success 'split sub dir/ with --rejoin from scratch' ' subtree_test_create_repo "$test_count" && test_create_commit "$test_count" main1 &&