[PATCH 0/2] worktree repair: avoid breaking unrelated .git file and gitdir

[PATCH 0/2] worktree repair: avoid breaking unrelated .git file and gitdir

[Yoichi NAKAYAMA via GitGitGadget]

'git worktree repair' does not sufficiently validate the cross-references
between a linked working tree and its administrative data before repairing
them. This can cause the repair to modify the wrong .git file or gitdir in
certain situations.

This series first refactors the code to read the .git file once and extract
the worktree ID, then uses that information to validate the repair target
before modifying the cross-references.

 * [1/2] Refactor the code without changing functionality before making the
   fix
 * [2/2] Validate the worktree ID and inferred gitdir path before repairing

Yoichi NAKAYAMA (2):
  worktree repair: refactor and reduce .git file reads
  worktree repair: avoid breaking unrelated .git file and gitdir

 t/t2406-worktree-repair.sh |  33 +++++++++---
 worktree.c                 | 105 ++++++++++++++++++++-----------------
 2 files changed, 83 insertions(+), 55 deletions(-)


base-commit: 47ce80527c56f462cb97db4ca8125342204d3783
Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-2225%2Fyoichi%2Fworktree-repair-keep-unrelated-gitfile-v1
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-2225/yoichi/worktree-repair-keep-unrelated-gitfile-v1
Pull-Request: https://github.com/gitgitgadget/git/pull/2225
-- 
gitgitgadget

[PATCH 1/2] worktree repair: refactor and reduce .git file reads

[Yoichi NAKAYAMA via GitGitGadget]

From: Yoichi NAKAYAMA <yoichi.nakayama@gmail.com>

Remove the file reading and trimming logic from `infer_backlink()`,
and instead read the .git file once in its caller,
`repair_worktree_at_path()`, using `read_gitfile_raw()`. Since
`read_gitfile_gently()` is replaced with `read_gitfile_raw()`, restore
the logic for constructing the absolute path and replace the
READ_GITFILE_ERR_NOT_A_REPO handling with a check using
`is_git_directory()`. Simplify the logic for prioritizing
'inferred_backlink' over 'backlink'.

Extract `get_worktree_id()` to get the worktree ID from the contents
of the .git file. We are going to modify and use this function in
subsequent commits.

Signed-off-by: Yoichi NAKAYAMA <yoichi.nakayama@gmail.com>
---
 worktree.c | 89 ++++++++++++++++++++++++++----------------------------
 1 file changed, 43 insertions(+), 46 deletions(-)

diff --git a/worktree.c b/worktree.c
index 8cb8637b18..7af13898d0 100644
--- a/worktree.c
+++ b/worktree.c
@@ -637,6 +637,14 @@ int other_head_refs(struct repository *repo,
 	return ret;
 }
 
+static const char *get_worktree_id(const char *dotgit_contents)
+{
+	const char *slash = find_last_dir_sep(dotgit_contents);
+	if (!slash)
+		return "";
+	return slash + 1;
+}
+
 /*
  * Repair worktree's /path/to/worktree/.git file if missing, corrupt, or not
  * pointing at <repo>/worktrees/<id>.
@@ -798,30 +806,20 @@ static int is_main_worktree_path(struct repository *repo, const char *path)
  * Returns -1 on failure and strbuf.len on success.
  */
 static ssize_t infer_backlink(struct repository *repo,
-			      const char *gitfile,
+			      const char *dotgit_contents,
 			      struct strbuf *inferred)
 {
-	struct strbuf actual = STRBUF_INIT;
 	const char *id;
 
-	if (strbuf_read_file(&actual, gitfile, 0) < 0)
-		goto error;
-	if (!starts_with(actual.buf, "gitdir:"))
-		goto error;
-	if (!(id = find_last_dir_sep(actual.buf)))
-		goto error;
-	strbuf_trim(&actual);
-	id++; /* advance past '/' to point at <id> */
+	id = get_worktree_id(dotgit_contents);
 	if (!*id)
 		goto error;
 	repo_common_path_replace(repo, inferred, "worktrees/%s", id);
 	if (!is_directory(inferred->buf))
 		goto error;
 
-	strbuf_release(&actual);
 	return inferred->len;
 error:
-	strbuf_release(&actual);
 	strbuf_reset(inferred); /* clear invalid path */
 	return -1;
 }
@@ -840,7 +838,8 @@ void repair_worktree_at_path(struct repository *repo,
 	struct strbuf inferred_backlink = STRBUF_INIT;
 	struct strbuf gitdir = STRBUF_INIT;
 	struct strbuf olddotgit = STRBUF_INIT;
-	char *dotgit_contents = NULL;
+	struct strbuf contents = STRBUF_INIT;
+	const char *dotgit_contents = NULL;
 	const char *repair = NULL;
 	int err;
 
@@ -856,51 +855,49 @@ void repair_worktree_at_path(struct repository *repo,
 		goto done;
 	}
 
-	infer_backlink(repo, dotgit.buf, &inferred_backlink);
-	strbuf_realpath_forgiving(&inferred_backlink, inferred_backlink.buf, 0);
-	dotgit_contents = xstrdup_or_null(read_gitfile_gently(dotgit.buf, &err));
-	if (dotgit_contents) {
-		strbuf_addstr(&backlink, dotgit_contents);
-	} else if (err == READ_GITFILE_ERR_NOT_A_FILE ||
-			err == READ_GITFILE_ERR_IS_A_DIR) {
+	err = read_gitfile_raw(&contents, dotgit.buf);
+	if (err == READ_GITFILE_ERR_NOT_A_FILE ||
+	    err == READ_GITFILE_ERR_IS_A_DIR) {
 		fn(1, dotgit.buf, _("unable to locate repository; .git is not a file"), cb_data);
 		goto done;
-	} else if (err == READ_GITFILE_ERR_NOT_A_REPO) {
-		if (inferred_backlink.len) {
-			/*
-			 * Worktree's .git file does not point at a repository
-			 * but we found a .git/worktrees/<id> in this
-			 * repository with the same <id> as recorded in the
-			 * worktree's .git file so make the worktree point at
-			 * the discovered .git/worktrees/<id>.
-			 */
-			strbuf_swap(&backlink, &inferred_backlink);
-		} else {
-			fn(1, dotgit.buf, _("unable to locate repository; .git file does not reference a repository"), cb_data);
-			goto done;
-		}
-	} else {
+	} else if (err) {
 		fn(1, dotgit.buf, _("unable to locate repository; .git file broken"), cb_data);
 		goto done;
 	}
 
+	dotgit_contents = contents.buf;
+	infer_backlink(repo, dotgit_contents, &inferred_backlink);
+	strbuf_realpath_forgiving(&inferred_backlink, inferred_backlink.buf, 0);
+
+	if (is_absolute_path(dotgit_contents)) {
+		strbuf_addstr(&backlink, dotgit_contents);
+	} else {
+		strbuf_addbuf(&backlink, &dotgit);
+		strbuf_strip_suffix(&backlink, ".git");
+		strbuf_addstr(&backlink, dotgit_contents);
+		strbuf_realpath_forgiving(&backlink, backlink.buf, 0);
+	}
+
+	if (!is_git_directory(backlink.buf) && !inferred_backlink.len) {
+		fn(1, dotgit.buf, _("unable to locate repository; .git file does not reference a repository"), cb_data);
+		goto done;
+	}
+
 	/*
 	 * If we got this far, either the worktree's .git file pointed at a
-	 * valid repository (i.e. read_gitfile_gently() returned success) or
+	 * valid repository (i.e. is_git_directory() returned true) or
 	 * the .git file did not point at a repository but we were able to
 	 * infer a suitable new value for the .git file by locating a
 	 * .git/worktrees/<id> in *this* repository corresponding to the <id>
 	 * recorded in the worktree's .git file.
 	 *
-	 * However, if, at this point, inferred_backlink is non-NULL (i.e. we
-	 * found a suitable .git/worktrees/<id> in *this* repository) *and* the
-	 * worktree's .git file points at a valid repository *and* those two
-	 * paths differ, then that indicates that the user probably *copied*
-	 * the main and linked worktrees to a new location as a unit rather
-	 * than *moving* them. Thus, the copied worktree's .git file actually
-	 * points at the .git/worktrees/<id> in the *original* repository, not
-	 * in the "copy" repository. In this case, point the "copy" worktree's
-	 * .git file at the "copy" repository.
+	 * Even if the worktree's .git file pointed at a valid repository,
+	 * it doesn't always mean that the backlink is correct. For example,
+	 * the user might have *copied* the main and linked worktrees to a
+	 * new location as a unit rather than *moving* them (the copied
+	 * worktree's .git file actually points at the .git/worktrees/<id>
+	 * in the *original* repository, not in the "copy" repository).
+	 * Therefore, we prioritize inferred_backlink over backlink.
 	 */
 	if (inferred_backlink.len && fspathcmp(backlink.buf, inferred_backlink.buf))
 		strbuf_swap(&backlink, &inferred_backlink);
@@ -926,12 +923,12 @@ void repair_worktree_at_path(struct repository *repo,
 					     gitdir.buf, use_relative_paths);
 	}
 done:
-	free(dotgit_contents);
 	strbuf_release(&olddotgit);
 	strbuf_release(&backlink);
 	strbuf_release(&inferred_backlink);
 	strbuf_release(&gitdir);
 	strbuf_release(&dotgit);
+	strbuf_release(&contents);
 }
 
 int should_prune_worktree(struct repository *repo,
-- 
gitgitgadget

[PATCH 2/2] worktree repair: avoid breaking unrelated .git file and gitdir

[Yoichi NAKAYAMA via GitGitGadget]

From: Yoichi NAKAYAMA <yoichi.nakayama@gmail.com>

Currently, `repair_gitfile()` does not verify whether the worktree ID
recorded in the .git file matches the worktree being repaired, which
can result in an unrelated .git file being corrupted. For instance,
if two worktree directories are swapped without using 'git worktree
move', running 'git worktree repair' in the main worktree accidentally
swaps the links between their .git files and gitdirs.

`repair_worktree_at_path()` proceeds even if it fails to infer the
gitdir path. This can result in the corruption of an unrelated
gitdir. For instance, if we copied a linked worktree to a new location
X, running 'git worktree repair X' in a working tree which does not
belong to the original repository can accidentally overwrite the
gitdir in the original repository (the scope of impact should be
limited to the repository where the command was executed).

Resolve these issues by validating the worktree ID and stopping the
repair when the ID does not match or the gitdir path cannot be
inferred.

Signed-off-by: Yoichi NAKAYAMA <yoichi.nakayama@gmail.com>
---
 t/t2406-worktree-repair.sh | 33 +++++++++++++++++++++++++++------
 worktree.c                 | 18 ++++++++++++++----
 2 files changed, 41 insertions(+), 10 deletions(-)

diff --git a/t/t2406-worktree-repair.sh b/t/t2406-worktree-repair.sh
index d4e53d492b..2ffa123f42 100755
--- a/t/t2406-worktree-repair.sh
+++ b/t/t2406-worktree-repair.sh
@@ -56,15 +56,12 @@ test_expect_success 'repair missing .git file' '
 '
 
 test_expect_success 'repair bogus .git file' '
-	test_corrupt_gitfile "echo \"gitdir: /nowhere\" >corrupt/.git" \
+	test_corrupt_gitfile "echo \"contents not started with gitdir:\" >corrupt/.git" \
 		".git file broken"
 '
 
-test_expect_success 'repair incorrect .git file' '
-	test_when_finished "rm -rf other && git worktree prune" &&
-	test_create_repo other &&
-	other=$(git -C other rev-parse --absolute-git-dir) &&
-	test_corrupt_gitfile "echo \"gitdir: $other\" >corrupt/.git" \
+test_expect_success 'repair unlinked .git file' '
+	test_corrupt_gitfile "echo \"gitdir: /nowhere/worktrees/corrupt\" >corrupt/.git" \
 		".git file incorrect"
 '
 
@@ -89,6 +86,18 @@ test_expect_success 'repair .git file from bare.git' '
 	test_cmp expect actual
 '
 
+test_expect_success 'skip unrelated .git file' '
+	test_when_finished "rm -rf corrupt other && git worktree prune" &&
+	git worktree add --detach corrupt &&
+	rm -rf corrupt &&
+	git worktree add --detach other &&
+	mv other corrupt &&
+	cat corrupt/.git >expect &&
+	test_must_fail git worktree repair 2>err &&
+	test_cmp expect corrupt/.git &&
+	test_grep "unrelated .git file" err
+'
+
 test_expect_success 'invalid worktree path' '
 	test_must_fail git worktree repair /notvalid >out 2>err &&
 	test_must_be_empty out &&
@@ -113,6 +122,18 @@ test_expect_success 'repo not found; .git not referencing repo' '
 	test_grep ".git file does not reference a repository" err
 '
 
+test_expect_success 'repo not found; .git not for worktree' '
+	test_when_finished "rm -rf side other-repo && git worktree prune" &&
+	test_create_repo other-repo &&
+	git worktree add --detach side &&
+	cat .git/worktrees/side/gitdir >expect &&
+	cp -R side other-repo/side &&
+	test_must_fail git -C other-repo worktree repair side >out 2>err &&
+	test_cmp expect .git/worktrees/side/gitdir &&
+	test_must_be_empty out &&
+	test_grep ".git file is not for a linked worktree" err
+'
+
 test_expect_success 'repo not found; .git file broken' '
 	test_when_finished "rm -rf orig moved && git worktree prune" &&
 	git worktree add --detach orig &&
diff --git a/worktree.c b/worktree.c
index 7af13898d0..88da599ab6 100644
--- a/worktree.c
+++ b/worktree.c
@@ -640,7 +640,11 @@ int other_head_refs(struct repository *repo,
 static const char *get_worktree_id(const char *dotgit_contents)
 {
 	const char *slash = find_last_dir_sep(dotgit_contents);
-	if (!slash)
+	const char *prefix = "/worktrees";
+	int prefixlen = strlen(prefix);
+	if (!slash ||
+	    slash - dotgit_contents < prefixlen ||
+	    strncmp(slash - prefixlen, prefix, prefixlen))
 		return "";
 	return slash + 1;
 }
@@ -692,8 +696,10 @@ static void repair_gitfile(struct worktree *wt,
 	if (err == READ_GITFILE_ERR_NOT_A_FILE ||
 		err == READ_GITFILE_ERR_IS_A_DIR)
 		fn(1, wt->path, _(".git is not a file"), cb_data);
-	else if (err || !is_git_directory(backlink.buf))
+	else if (err)
 		repair = _(".git file broken");
+	else if (strcmp(get_worktree_id(dotgit_contents), wt->id))
+		fn(1, wt->path, _("unrelated .git file"), cb_data);
 	else if (fspathcmp(backlink.buf, repo.buf))
 		repair = _(".git file incorrect");
 	else if (use_relative_paths == is_absolute_path(dotgit_contents))
@@ -815,7 +821,7 @@ static ssize_t infer_backlink(struct repository *repo,
 	if (!*id)
 		goto error;
 	repo_common_path_replace(repo, inferred, "worktrees/%s", id);
-	if (!is_directory(inferred->buf))
+	if (!is_git_directory(inferred->buf))
 		goto error;
 
 	return inferred->len;
@@ -882,6 +888,10 @@ void repair_worktree_at_path(struct repository *repo,
 		fn(1, dotgit.buf, _("unable to locate repository; .git file does not reference a repository"), cb_data);
 		goto done;
 	}
+	if (!inferred_backlink.len) {
+		fn(1, dotgit.buf, _("unable to locate repository; .git file is not for a linked worktree"), cb_data);
+		goto done;
+	}
 
 	/*
 	 * If we got this far, either the worktree's .git file pointed at a
@@ -899,7 +909,7 @@ void repair_worktree_at_path(struct repository *repo,
 	 * in the *original* repository, not in the "copy" repository).
 	 * Therefore, we prioritize inferred_backlink over backlink.
 	 */
-	if (inferred_backlink.len && fspathcmp(backlink.buf, inferred_backlink.buf))
+	if (fspathcmp(backlink.buf, inferred_backlink.buf))
 		strbuf_swap(&backlink, &inferred_backlink);
 
 	strbuf_addf(&gitdir, "%s/gitdir", backlink.buf);
-- 
gitgitgadget