Skip to main content

Browse the archive

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 
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 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
csum-file.h 
#ifndef CSUM_FILE_H
#define CSUM_FILE_H

#include "cache.h"
#include "hash.h"

struct progress;

/* A SHA1-protected file */
struct hashfile {
	int fd;
	int check_fd;
	unsigned int offset;
	git_hash_ctx ctx;
	off_t total;
	struct progress *tp;
	const char *name;
	int do_crc;
	uint32_t crc32;
	size_t buffer_len;
	unsigned char *buffer;
	unsigned char *check_buffer;
};

/* Checkpoint */
struct hashfile_checkpoint {
	off_t offset;
	git_hash_ctx ctx;
};

void hashfile_checkpoint(struct hashfile *, struct hashfile_checkpoint *);
int hashfile_truncate(struct hashfile *, struct hashfile_checkpoint *);

/* finalize_hashfile flags */
#define CSUM_CLOSE		1
#define CSUM_FSYNC		2
#define CSUM_HASH_IN_STREAM	4

struct hashfile *hashfd(int fd, const char *name);
struct hashfile *hashfd_check(const char *name);
struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp);
int finalize_hashfile(struct hashfile *, unsigned char *, enum fsync_component, unsigned int);
void hashwrite(struct hashfile *, const void *, unsigned int);
void hashflush(struct hashfile *f);
void crc32_begin(struct hashfile *);
uint32_t crc32_end(struct hashfile *);

/* Verify checksum validity while reading. Returns non-zero on success. */
int hashfile_checksum_valid(const unsigned char *data, size_t len);

/*
 * Returns the total number of bytes fed to the hashfile so far (including ones
 * that have not been written out to the descriptor yet).
 */
static inline off_t hashfile_total(struct hashfile *f)
{
	return f->total + f->offset;
}

static inline void hashwrite_u8(struct hashfile *f, uint8_t data)
{
	hashwrite(f, &data, sizeof(data));
}

static inline void hashwrite_be32(struct hashfile *f, uint32_t data)
{
	data = htonl(data);
	hashwrite(f, &data, sizeof(data));
}

static inline size_t hashwrite_be64(struct hashfile *f, uint64_t data)
{
	data = htonll(data);
	hashwrite(f, &data, sizeof(data));
	return sizeof(data);
}

#endif
back to top