clone: prevent clashing git dirs when cloning submodule in parallel

While it is expected to have several git dirs within the `.git/modules/`
tree, it is important that they do not interfere with each other. For
example, if one submodule was called "captain" and another submodule
"captain/hooks", their respective git dirs would clash, as they would be
located in `.git/modules/captain/` and `.git/modules/captain/hooks/`,
respectively, i.e. the latter's files could clash with the actual Git
hooks of the former.

To prevent these clashes, and in particular to prevent hooks from being
written and then executed as part of a recursive clone, we introduced
checks as part of the fix for CVE-2019-1387 in a8dee3c (Disallow
dubiously-nested submodule git directories, 2019-10-01).

It is currently possible to bypass the check for clashing submodule
git dirs in two ways:

1. parallel cloning
2. checkout --recurse-submodules

Let's check not only before, but also after parallel cloning (and before
checking out the submodule), that the git dir is not clashing with
another one, otherwise fail. This addresses the parallel cloning issue.

As to the parallel checkout issue: It requires quite a few manual steps
to create clashing git dirs because Git itself would refuse to
initialize the inner one, as demonstrated by the test case.

Nevertheless, let's teach the recursive checkout (namely, the
`submodule_move_head()` function that is used by the recursive checkout)
to be careful to verify that it does not use a clashing git dir, and if
it does, disable it (by deleting the `HEAD` file so that subsequent Git
calls won't recognize it as a git dir anymore).

Note: The parallel cloning test case contains a `cat err` that proved to
be highly useful when analyzing the racy nature of the operation (the
operation can fail with three different error messages, depending on
timing), and was left on purpose to ease future debugging should the
need arise.

Signed-off-by: Filip Hejsek <[email protected]>
Signed-off-by: Johannes Schindelin <[email protected]>

Author: filip-hejsek

builtin/submodule--helper.c

@@ -1717,6 +1717,23 @@ static int clone_submodule(const struct module_clone_data *clone_data,
 		free(path);
 	}
 
+	/*
+	 * We already performed this check at the beginning of this function,
+	 * before cloning the objects. This tries to detect racy behavior e.g.
+	 * in parallel clones, where another process could easily have made the
+	 * gitdir nested _after_ it was created.
+	 *
+	 * To prevent further harm coming from this unintentionally-nested
+	 * gitdir, let's disable it by deleting the `HEAD` file.
+	 */
+	if (validate_submodule_git_dir(sm_gitdir, clone_data->name) < 0) {
+		char *head = xstrfmt("%s/HEAD", sm_gitdir);
+		unlink(head);
+		free(head);
+		die(_("refusing to create/use '%s' in another submodule's "
+		      "git dir"), sm_gitdir);
+	}
+
 	connect_work_tree_and_git_dir(clone_data_path, sm_gitdir, 0);
 
 	p = git_pathdup_submodule(clone_data_path, "config");

submodule.c

@@ -2146,10 +2146,27 @@ int submodule_move_head(const char *path,
 		if (old_head) {
 			if (!submodule_uses_gitfile(path))
 				absorb_git_dir_into_superproject(path);
+			else {
+				char *dotgit = xstrfmt("%s/.git", path);
+				char *git_dir = xstrdup(read_gitfile(dotgit));
+
+				free(dotgit);
+				if (validate_submodule_git_dir(git_dir,
+							       sub->name) < 0)
+					die(_("refusing to create/use '%s' in "
+					      "another submodule's git dir"),
+					    git_dir);
+				free(git_dir);
+			}
 		} else {
 			struct strbuf gitdir = STRBUF_INIT;
 			submodule_name_to_gitdir(&gitdir, the_repository,
 						 sub->name);
+			if (validate_submodule_git_dir(gitdir.buf,
+						       sub->name) < 0)
+				die(_("refusing to create/use '%s' in another "
+				      "submodule's git dir"),
+				    gitdir.buf);
 			connect_work_tree_and_git_dir(path, gitdir.buf, 0);
 			strbuf_release(&gitdir);
 

t/t7450-bad-git-dotfiles.sh

@@ -292,7 +292,7 @@ test_expect_success WINDOWS 'prevent git~1 squatting on Windows' '
 	fi
 '
 
-test_expect_success 'git dirs of sibling submodules must not be nested' '
+test_expect_success 'setup submodules with nested git dirs' '
 	git init nested &&
 	test_commit -C nested nested &&
 	(
@@ -310,9 +310,39 @@ test_expect_success 'git dirs of sibling submodules must not be nested' '
 		git add .gitmodules thing1 thing2 &&
 		test_tick &&
 		git commit -m nested
-	) &&
+	)
+'
+
+test_expect_success 'git dirs of sibling submodules must not be nested' '
 	test_must_fail git clone --recurse-submodules nested clone 2>err &&
 	test_i18ngrep "is inside git dir" err
 '
 
+test_expect_success 'submodule git dir nesting detection must work with parallel cloning' '
+	test_must_fail git clone --recurse-submodules --jobs=2 nested clone_parallel 2>err &&
+	cat err &&
+	grep -E "(already exists|is inside git dir|not a git repository)" err &&
+	{
+		test_path_is_missing .git/modules/hippo/HEAD ||
+		test_path_is_missing .git/modules/hippo/hooks/HEAD
+	}
+'
+
+test_expect_success 'checkout -f --recurse-submodules must not use a nested gitdir' '
+	git clone nested nested_checkout &&
+	(
+		cd nested_checkout &&
+		git submodule init &&
+		git submodule update thing1 &&
+		mkdir -p .git/modules/hippo/hooks/refs &&
+		mkdir -p .git/modules/hippo/hooks/objects/info &&
+		echo "../../../../objects" >.git/modules/hippo/hooks/objects/info/alternates &&
+		echo "ref: refs/heads/master" >.git/modules/hippo/hooks/HEAD
+	) &&
+	test_must_fail git -C nested_checkout checkout -f --recurse-submodules HEAD 2>err &&
+	cat err &&
+	grep "is inside git dir" err &&
+	test_path_is_missing nested_checkout/thing2/.git
+'
+
 test_done