Revision 9cf85473209ea8ae2b56c13145c4704d12ee1374 authored by Filip Hejsek on 28 January 2024, 04:09:17 UTC, committed by Johannes Schindelin on 17 April 2024, 20:30:01 UTC
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 a8dee3ca61 (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 <filip.hejsek@gmail.com>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
1 parent b20c10f
Raw File
tag.c
#include "cache.h"
#include "tag.h"
#include "object-store.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "alloc.h"
#include "gpg-interface.h"
#include "packfile.h"

const char *tag_type = "tag";

static int run_gpg_verify(const char *buf, unsigned long size, unsigned flags)
{
	struct signature_check sigc;
	struct strbuf payload = STRBUF_INIT;
	struct strbuf signature = STRBUF_INIT;
	int ret;

	memset(&sigc, 0, sizeof(sigc));

	if (!parse_signature(buf, size, &payload, &signature)) {
		if (flags & GPG_VERIFY_VERBOSE)
			write_in_full(1, buf, size);
		return error("no signature found");
	}

	sigc.payload_type = SIGNATURE_PAYLOAD_TAG;
	sigc.payload = strbuf_detach(&payload, &sigc.payload_len);
	ret = check_signature(&sigc, signature.buf, signature.len);

	if (!(flags & GPG_VERIFY_OMIT_STATUS))
		print_signature_buffer(&sigc, flags);

	signature_check_clear(&sigc);
	strbuf_release(&payload);
	strbuf_release(&signature);
	return ret;
}

int gpg_verify_tag(const struct object_id *oid, const char *name_to_report,
		unsigned flags)
{
	enum object_type type;
	char *buf;
	unsigned long size;
	int ret;

	type = oid_object_info(the_repository, oid, NULL);
	if (type != OBJ_TAG)
		return error("%s: cannot verify a non-tag object of type %s.",
				name_to_report ?
				name_to_report :
				find_unique_abbrev(oid, DEFAULT_ABBREV),
				type_name(type));

	buf = read_object_file(oid, &type, &size);
	if (!buf)
		return error("%s: unable to read file.",
				name_to_report ?
				name_to_report :
				find_unique_abbrev(oid, DEFAULT_ABBREV));

	ret = run_gpg_verify(buf, size, flags);

	free(buf);
	return ret;
}

struct object *deref_tag(struct repository *r, struct object *o, const char *warn, int warnlen)
{
	struct object_id *last_oid = NULL;
	while (o && o->type == OBJ_TAG)
		if (((struct tag *)o)->tagged) {
			last_oid = &((struct tag *)o)->tagged->oid;
			o = parse_object(r, last_oid);
		} else {
			last_oid = NULL;
			o = NULL;
		}
	if (!o && warn) {
		if (last_oid && is_promisor_object(last_oid))
			return NULL;
		if (!warnlen)
			warnlen = strlen(warn);
		error("missing object referenced by '%.*s'", warnlen, warn);
	}
	return o;
}

struct object *deref_tag_noverify(struct object *o)
{
	while (o && o->type == OBJ_TAG) {
		o = parse_object(the_repository, &o->oid);
		if (o && o->type == OBJ_TAG && ((struct tag *)o)->tagged)
			o = ((struct tag *)o)->tagged;
		else
			o = NULL;
	}
	return o;
}

struct tag *lookup_tag(struct repository *r, const struct object_id *oid)
{
	struct object *obj = lookup_object(r, oid);
	if (!obj)
		return create_object(r, oid, alloc_tag_node(r));
	return object_as_type(obj, OBJ_TAG, 0);
}

static timestamp_t parse_tag_date(const char *buf, const char *tail)
{
	const char *dateptr;

	while (buf < tail && *buf++ != '>')
		/* nada */;
	if (buf >= tail)
		return 0;
	dateptr = buf;
	while (buf < tail && *buf++ != '\n')
		/* nada */;
	if (buf >= tail)
		return 0;
	/* dateptr < buf && buf[-1] == '\n', so parsing will stop at buf-1 */
	return parse_timestamp(dateptr, NULL, 10);
}

void release_tag_memory(struct tag *t)
{
	free(t->tag);
	t->tagged = NULL;
	t->object.parsed = 0;
	t->date = 0;
}

int parse_tag_buffer(struct repository *r, struct tag *item, const void *data, unsigned long size)
{
	struct object_id oid;
	char type[20];
	const char *bufptr = data;
	const char *tail = bufptr + size;
	const char *nl;

	if (item->object.parsed)
		return 0;

	if (item->tag) {
		/*
		 * Presumably left over from a previous failed parse;
		 * clear it out in preparation for re-parsing (we'll probably
		 * hit the same error, which lets us tell our current caller
		 * about the problem).
		 */
		FREE_AND_NULL(item->tag);
	}

	if (size < the_hash_algo->hexsz + 24)
		return -1;
	if (memcmp("object ", bufptr, 7) || parse_oid_hex(bufptr + 7, &oid, &bufptr) || *bufptr++ != '\n')
		return -1;

	if (!starts_with(bufptr, "type "))
		return -1;
	bufptr += 5;
	nl = memchr(bufptr, '\n', tail - bufptr);
	if (!nl || sizeof(type) <= (nl - bufptr))
		return -1;
	memcpy(type, bufptr, nl - bufptr);
	type[nl - bufptr] = '\0';
	bufptr = nl + 1;

	if (!strcmp(type, blob_type)) {
		item->tagged = (struct object *)lookup_blob(r, &oid);
	} else if (!strcmp(type, tree_type)) {
		item->tagged = (struct object *)lookup_tree(r, &oid);
	} else if (!strcmp(type, commit_type)) {
		item->tagged = (struct object *)lookup_commit(r, &oid);
	} else if (!strcmp(type, tag_type)) {
		item->tagged = (struct object *)lookup_tag(r, &oid);
	} else {
		return error("unknown tag type '%s' in %s",
			     type, oid_to_hex(&item->object.oid));
	}

	if (!item->tagged)
		return error("bad tag pointer to %s in %s",
			     oid_to_hex(&oid),
			     oid_to_hex(&item->object.oid));

	if (bufptr + 4 < tail && starts_with(bufptr, "tag "))
		; 		/* good */
	else
		return -1;
	bufptr += 4;
	nl = memchr(bufptr, '\n', tail - bufptr);
	if (!nl)
		return -1;
	item->tag = xmemdupz(bufptr, nl - bufptr);
	bufptr = nl + 1;

	if (bufptr + 7 < tail && starts_with(bufptr, "tagger "))
		item->date = parse_tag_date(bufptr, tail);
	else
		item->date = 0;

	item->object.parsed = 1;
	return 0;
}

int parse_tag(struct tag *item)
{
	enum object_type type;
	void *data;
	unsigned long size;
	int ret;

	if (item->object.parsed)
		return 0;
	data = read_object_file(&item->object.oid, &type, &size);
	if (!data)
		return error("Could not read %s",
			     oid_to_hex(&item->object.oid));
	if (type != OBJ_TAG) {
		free(data);
		return error("Object %s not a tag",
			     oid_to_hex(&item->object.oid));
	}
	ret = parse_tag_buffer(the_repository, item, data, size);
	free(data);
	return ret;
}

struct object_id *get_tagged_oid(struct tag *tag)
{
	if (!tag->tagged)
		die("bad tag");
	return &tag->tagged->oid;
}
back to top