Revision 7b70e9efb18c2cc3f219af399bd384c5801ba1d7 authored by Jeff King on 16 April 2024, 08:35:33 UTC, committed by Johannes Schindelin on 17 April 2024, 20:29:56 UTC
The upload-pack command tries to avoid trusting the repository in which
it's run (e.g., by not running any hooks and not using any config that
contains arbitrary commands). But if the server side of a fetch or a
clone is a partial clone, then either upload-pack or its child
pack-objects may run a lazy "git fetch" under the hood. And it is very
easy to convince fetch to run arbitrary commands.

The "server" side can be a local repository owned by someone else, who
would be able to configure commands that are run during a clone with the
current user's permissions. This issue has been designated
CVE-2024-32004.

The fix in this commit's parent helps in this scenario, as well as in
related scenarios using SSH to clone, where the untrusted .git directory
is owned by a different user id. But if you received one as a zip file,
on a USB stick, etc, it may be owned by your user but still untrusted.

This has been designated CVE-2024-32465.

To mitigate the issue more completely, let's disable lazy fetching
entirely during `upload-pack`. While fetching from a partial repository
should be relatively rare, it is certainly not an unreasonable workflow.
And thus we need to provide an escape hatch.

This commit works by respecting a GIT_NO_LAZY_FETCH environment variable
(to skip the lazy-fetch), and setting it in upload-pack, but only when
the user has not already done so (which gives us the escape hatch).

The name of the variable is specifically chosen to match what has
already been added in 'master' via e6d5479e7a (git: extend
--no-lazy-fetch to work across subprocesses, 2024-02-27). Since we're
building this fix as a backport for older versions, we could cherry-pick
that patch and its earlier steps. However, we don't really need the
niceties (like a "--no-lazy-fetch" option) that it offers. By using the
same name, everything should just work when the two are eventually
merged, but here are a few notes:

  - the blocking of the fetch in e6d5479e7a is incomplete! It sets
    fetch_if_missing to 0 when we setup the repository variable, but
    that isn't enough. pack-objects in particular will call
    prefetch_to_pack() even if that variable is 0. This patch by
    contrast checks the environment variable at the lowest level before
    we call the lazy fetch, where we can be sure to catch all code
    paths.

    Possibly the setting of fetch_if_missing from e6d5479e7a can be
    reverted, but it may be useful to have. For example, some code may
    want to use that flag to change behavior before it gets to the point
    of trying to start the fetch. At any rate, that's all outside the
    scope of this patch.

  - there's documentation for GIT_NO_LAZY_FETCH in e6d5479e7a. We can
    live without that here, because for the most part the user shouldn't
    need to set it themselves. The exception is if they do want to
    override upload-pack's default, and that requires a separate
    documentation section (which is added here)

  - it would be nice to use the NO_LAZY_FETCH_ENVIRONMENT macro added by
    e6d5479e7a, but those definitions have moved from cache.h to
    environment.h between 2.39.3 and master. I just used the raw string
    literals, and we can replace them with the macro once this topic is
    merged to master.

At least with respect to CVE-2024-32004, this does render this commit's
parent commit somewhat redundant. However, it is worth retaining that
commit as defense in depth, and because it may help other issues (e.g.,
symlink/hardlink TOCTOU races, where zip files are not really an
interesting attack vector).

The tests in t0411 still pass, but now we have _two_ mechanisms ensuring
that the evil command is not run. Let's beef up the existing ones to
check that they failed for the expected reason, that we refused to run
upload-pack at all with an alternate user id. And add two new ones for
the same-user case that both the restriction and its escape hatch.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
1 parent f4aa8c8
Raw File
hex.c
#include "cache.h"

const signed char hexval_table[256] = {
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 00-07 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 08-0f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 10-17 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 18-1f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 20-27 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 28-2f */
	  0,  1,  2,  3,  4,  5,  6,  7,		/* 30-37 */
	  8,  9, -1, -1, -1, -1, -1, -1,		/* 38-3f */
	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 40-47 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 48-4f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 50-57 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 58-5f */
	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 60-67 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 68-67 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 70-77 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 78-7f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 80-87 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 88-8f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 90-97 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 98-9f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a0-a7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a8-af */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b0-b7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b8-bf */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c0-c7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c8-cf */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d0-d7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d8-df */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e0-e7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e8-ef */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f0-f7 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f8-ff */
};

int hex_to_bytes(unsigned char *binary, const char *hex, size_t len)
{
	for (; len; len--, hex += 2) {
		unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]);

		if (val & ~0xff)
			return -1;
		*binary++ = val;
	}
	return 0;
}

static int get_hash_hex_algop(const char *hex, unsigned char *hash,
			      const struct git_hash_algo *algop)
{
	int i;
	for (i = 0; i < algop->rawsz; i++) {
		int val = hex2chr(hex);
		if (val < 0)
			return -1;
		*hash++ = val;
		hex += 2;
	}
	return 0;
}

int get_sha1_hex(const char *hex, unsigned char *sha1)
{
	return get_hash_hex_algop(hex, sha1, the_hash_algo);
}

int get_oid_hex_algop(const char *hex, struct object_id *oid,
		      const struct git_hash_algo *algop)
{
	int ret = get_hash_hex_algop(hex, oid->hash, algop);
	if (!ret)
		oid_set_algo(oid, algop);
	return ret;
}

/*
 * NOTE: This function relies on hash algorithms being in order from shortest
 * length to longest length.
 */
int get_oid_hex_any(const char *hex, struct object_id *oid)
{
	int i;
	for (i = GIT_HASH_NALGOS - 1; i > 0; i--) {
		if (!get_oid_hex_algop(hex, oid, &hash_algos[i]))
			return i;
	}
	return GIT_HASH_UNKNOWN;
}

int get_oid_hex(const char *hex, struct object_id *oid)
{
	return get_oid_hex_algop(hex, oid, the_hash_algo);
}

int parse_oid_hex_algop(const char *hex, struct object_id *oid,
			const char **end,
			const struct git_hash_algo *algop)
{
	int ret = get_oid_hex_algop(hex, oid, algop);
	if (!ret)
		*end = hex + algop->hexsz;
	return ret;
}

int parse_oid_hex_any(const char *hex, struct object_id *oid, const char **end)
{
	int ret = get_oid_hex_any(hex, oid);
	if (ret)
		*end = hex + hash_algos[ret].hexsz;
	return ret;
}

int parse_oid_hex(const char *hex, struct object_id *oid, const char **end)
{
	return parse_oid_hex_algop(hex, oid, end, the_hash_algo);
}

char *hash_to_hex_algop_r(char *buffer, const unsigned char *hash,
			  const struct git_hash_algo *algop)
{
	static const char hex[] = "0123456789abcdef";
	char *buf = buffer;
	int i;

	/*
	 * Our struct object_id has been memset to 0, so default to printing
	 * using the default hash.
	 */
	if (algop == &hash_algos[0])
		algop = the_hash_algo;

	for (i = 0; i < algop->rawsz; i++) {
		unsigned int val = *hash++;
		*buf++ = hex[val >> 4];
		*buf++ = hex[val & 0xf];
	}
	*buf = '\0';

	return buffer;
}

char *oid_to_hex_r(char *buffer, const struct object_id *oid)
{
	return hash_to_hex_algop_r(buffer, oid->hash, &hash_algos[oid->algo]);
}

char *hash_to_hex_algop(const unsigned char *hash, const struct git_hash_algo *algop)
{
	static int bufno;
	static char hexbuffer[4][GIT_MAX_HEXSZ + 1];
	bufno = (bufno + 1) % ARRAY_SIZE(hexbuffer);
	return hash_to_hex_algop_r(hexbuffer[bufno], hash, algop);
}

char *hash_to_hex(const unsigned char *hash)
{
	return hash_to_hex_algop(hash, the_hash_algo);
}

char *oid_to_hex(const struct object_id *oid)
{
	return hash_to_hex_algop(oid->hash, &hash_algos[oid->algo]);
}
back to top