submodules: submodule paths must not contain symlinks

When creating a submodule path, we must be careful not to follow
symbolic links. Otherwise we may follow a symbolic link pointing to
a gitdir (which are valid symbolic links!) e.g. while cloning.

On case-insensitive filesystems, however, we blindly replace a directory
that has been created as part of the `clone` operation with a symlink
when the path to the latter differs only in case from the former's path.

Let's simply avoid this situation by expecting not ever having to
overwrite any existing file/directory/symlink upon cloning. That way, we
won't even replace a directory that we just created.

This addresses CVE-2024-32002.

Reported-by: Filip Hejsek <filip.hejsek@gmail.com>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>

2 files changed, 83 insertions, 0 deletions

diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index b76e13ddce..4c1a7dbcda 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -1641,12 +1641,35 @@ static char *clone_submodule_sm_gitdir(const char *name)
 	return sm_gitdir;
 }
 
+static int dir_contains_only_dotgit(const char *path)
+{
+	DIR *dir = opendir(path);
+	struct dirent *e;
+	int ret = 1;
+
+	if (!dir)
+		return 0;
+
+	e = readdir_skip_dot_and_dotdot(dir);
+	if (!e)
+		ret = 0;
+	else if (strcmp(DEFAULT_GIT_DIR_ENVIRONMENT, e->d_name) ||
+		 (e = readdir_skip_dot_and_dotdot(dir))) {
+		error("unexpected item '%s' in '%s'", e->d_name, path);
+		ret = 0;
+	}
+
+	closedir(dir);
+	return ret;
+}
+
 static int clone_submodule(const struct module_clone_data *clone_data,
 			   struct string_list *reference)
 {
 	char *p;
 	char *sm_gitdir = clone_submodule_sm_gitdir(clone_data->name);
 	char *sm_alternate = NULL, *error_strategy = NULL;
+	struct stat st;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *clone_data_path = clone_data->path;
 	char *to_free = NULL;
@@ -1660,6 +1683,10 @@ static int clone_submodule(const struct module_clone_data *clone_data,
 		      "git dir"), sm_gitdir);
 
 	if (!file_exists(sm_gitdir)) {
+		if (clone_data->require_init && !stat(clone_data_path, &st) &&
+		    !is_empty_dir(clone_data_path))
+			die(_("directory not empty: '%s'"), clone_data_path);
+
 		if (safe_create_leading_directories_const(sm_gitdir) < 0)
 			die(_("could not create directory '%s'"), sm_gitdir);
 
@@ -1704,6 +1731,14 @@ static int clone_submodule(const struct module_clone_data *clone_data,
 		if(run_command(&cp))
 			die(_("clone of '%s' into submodule path '%s' failed"),
 			    clone_data->url, clone_data_path);
+
+		if (clone_data->require_init && !stat(clone_data_path, &st) &&
+		    !dir_contains_only_dotgit(clone_data_path)) {
+			char *dot_git = xstrfmt("%s/.git", clone_data_path);
+			unlink(dot_git);
+			free(dot_git);
+			die(_("directory not empty: '%s'"), clone_data_path);
+		}
 	} else {
 		char *path;
 
diff --git a/t/t7406-submodule-update.sh b/t/t7406-submodule-update.sh
index f094e3d7f3..63c24f7f7c 100755
--- a/t/t7406-submodule-update.sh
+++ b/t/t7406-submodule-update.sh
@@ -1179,4 +1179,52 @@ test_expect_success 'submodule update --recursive skip submodules with strategy=
 	test_cmp expect.err actual.err
 '
 
+test_expect_success CASE_INSENSITIVE_FS,SYMLINKS \
+	'submodule paths must not follow symlinks' '
+
+	# This is only needed because we want to run this in a self-contained
+	# test without having to spin up an HTTP server; However, it would not
+	# be needed in a real-world scenario where the submodule is simply
+	# hosted on a public site.
+	test_config_global protocol.file.allow always &&
+
+	# Make sure that Git tries to use symlinks on Windows
+	test_config_global core.symlinks true &&
+
+	tell_tale_path="$PWD/tell.tale" &&
+	git init hook &&
+	(
+		cd hook &&
+		mkdir -p y/hooks &&
+		write_script y/hooks/post-checkout <<-EOF &&
+		echo HOOK-RUN >&2
+		echo hook-run >"$tell_tale_path"
+		EOF
+		git add y/hooks/post-checkout &&
+		test_tick &&
+		git commit -m post-checkout
+	) &&
+
+	hook_repo_path="$(pwd)/hook" &&
+	git init captain &&
+	(
+		cd captain &&
+		git submodule add --name x/y "$hook_repo_path" A/modules/x &&
+		test_tick &&
+		git commit -m add-submodule &&
+
+		printf .git >dotgit.txt &&
+		git hash-object -w --stdin <dotgit.txt >dot-git.hash &&
+		printf "120000 %s 0\ta\n" "$(cat dot-git.hash)" >index.info &&
+		git update-index --index-info <index.info &&
+		test_tick &&
+		git commit -m add-symlink
+	) &&
+
+	test_path_is_missing "$tell_tale_path" &&
+	test_must_fail git clone --recursive captain hooked 2>err &&
+	grep "directory not empty" err &&
+	test_path_is_missing "$tell_tale_path"
+'
+
 test_done