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
strmap.h
#ifndef STRMAP_H
#define STRMAP_H

#include "hashmap.h"

struct mem_pool;
struct strmap {
	struct hashmap map;
	struct mem_pool *pool;
	unsigned int strdup_strings:1;
};

struct strmap_entry {
	struct hashmap_entry ent;
	const char *key;
	void *value;
	/* strmap_entry may be allocated extra space to store the key at end */
};

int cmp_strmap_entry(const void *hashmap_cmp_fn_data,
		     const struct hashmap_entry *entry1,
		     const struct hashmap_entry *entry2,
		     const void *keydata);

#define STRMAP_INIT { \
			.map = HASHMAP_INIT(cmp_strmap_entry, NULL),  \
			.strdup_strings = 1,                          \
		    }
#define STRINTMAP_INIT { \
			.map = STRMAP_INIT,   \
			.default_value = 0,   \
		       }
#define STRSET_INIT { .map = STRMAP_INIT }

/*
 * Initialize the members of the strmap.  Any keys added to the strmap will
 * be strdup'ed with their memory managed by the strmap.
 */
void strmap_init(struct strmap *map);

/*
 * Same as strmap_init, but for those who want to control the memory management
 * carefully instead of using the default of strdup_strings=1 and pool=NULL.
 */
void strmap_init_with_options(struct strmap *map,
			      struct mem_pool *pool,
			      int strdup_strings);

/*
 * Remove all entries from the map, releasing any allocated resources.
 */
void strmap_clear(struct strmap *map, int free_values);

/*
 * Similar to strmap_clear() but leaves map->map->table allocated and
 * pre-sized so that subsequent uses won't need as many rehashings.
 */
void strmap_partial_clear(struct strmap *map, int free_values);

/*
 * Insert "str" into the map, pointing to "data".
 *
 * If an entry for "str" already exists, its data pointer is overwritten, and
 * the original data pointer returned. Otherwise, returns NULL.
 */
void *strmap_put(struct strmap *map, const char *str, void *data);

/*
 * Return the strmap_entry mapped by "str", or NULL if there is not such
 * an item in map.
 */
struct strmap_entry *strmap_get_entry(struct strmap *map, const char *str);

/*
 * Return the data pointer mapped by "str", or NULL if the entry does not
 * exist.
 */
void *strmap_get(struct strmap *map, const char *str);

/*
 * Return non-zero iff "str" is present in the map. This differs from
 * strmap_get() in that it can distinguish entries with a NULL data pointer.
 */
int strmap_contains(struct strmap *map, const char *str);

/*
 * Remove the given entry from the strmap.  If the string isn't in the
 * strmap, the map is not altered.
 */
void strmap_remove(struct strmap *map, const char *str, int free_value);

/*
 * Return how many entries the strmap has.
 */
static inline unsigned int strmap_get_size(struct strmap *map)
{
	return hashmap_get_size(&map->map);
}

/*
 * Return whether the strmap is empty.
 */
static inline int strmap_empty(struct strmap *map)
{
	return strmap_get_size(map) == 0;
}

/*
 * iterate through @map using @iter, @var is a pointer to a type strmap_entry
 */
#define strmap_for_each_entry(mystrmap, iter, var)	\
	hashmap_for_each_entry(&(mystrmap)->map, iter, var, ent)


/*
 * strintmap:
 *    A map of string -> int, typecasting the void* of strmap to an int.
 *
 * Primary differences:
 *    1) Since the void* value is just an int in disguise, there is no value
 *       to free.  (Thus one fewer argument to strintmap_clear)
 *    2) strintmap_get() returns an int, or returns the default_value if the
 *       key is not found in the strintmap.
 *    3) No strmap_put() equivalent; strintmap_set() and strintmap_incr()
 *       instead.
 */

struct strintmap {
	struct strmap map;
	int default_value;
};

#define strintmap_for_each_entry(mystrmap, iter, var)	\
	strmap_for_each_entry(&(mystrmap)->map, iter, var)

static inline void strintmap_init(struct strintmap *map, int default_value)
{
	strmap_init(&map->map);
	map->default_value = default_value;
}

static inline void strintmap_init_with_options(struct strintmap *map,
					       int default_value,
					       struct mem_pool *pool,
					       int strdup_strings)
{
	strmap_init_with_options(&map->map, pool, strdup_strings);
	map->default_value = default_value;
}

static inline void strintmap_clear(struct strintmap *map)
{
	strmap_clear(&map->map, 0);
}

static inline void strintmap_partial_clear(struct strintmap *map)
{
	strmap_partial_clear(&map->map, 0);
}

static inline int strintmap_contains(struct strintmap *map, const char *str)
{
	return strmap_contains(&map->map, str);
}

static inline void strintmap_remove(struct strintmap *map, const char *str)
{
	strmap_remove(&map->map, str, 0);
}

static inline int strintmap_empty(struct strintmap *map)
{
	return strmap_empty(&map->map);
}

static inline unsigned int strintmap_get_size(struct strintmap *map)
{
	return strmap_get_size(&map->map);
}

/*
 * Returns the value for str in the map.  If str isn't found in the map,
 * the map's default_value is returned.
 */
static inline int strintmap_get(struct strintmap *map, const char *str)
{
	struct strmap_entry *result = strmap_get_entry(&map->map, str);
	if (!result)
		return map->default_value;
	return (intptr_t)result->value;
}

static inline void strintmap_set(struct strintmap *map, const char *str,
				 intptr_t v)
{
	strmap_put(&map->map, str, (void *)v);
}

/*
 * Increment the value for str by amt.  If str isn't in the map, add it and
 * set its value to default_value + amt.
 */
void strintmap_incr(struct strintmap *map, const char *str, intptr_t amt);

/*
 * strset:
 *    A set of strings.
 *
 * Primary differences with strmap:
 *    1) The value is always NULL, and ignored.  As there is no value to free,
 *       there is one fewer argument to strset_clear
 *    2) No strset_get() because there is no value.
 *    3) No strset_put(); use strset_add() instead.
 */

struct strset {
	struct strmap map;
};

#define strset_for_each_entry(mystrset, iter, var)	\
	strmap_for_each_entry(&(mystrset)->map, iter, var)

static inline void strset_init(struct strset *set)
{
	strmap_init(&set->map);
}

static inline void strset_init_with_options(struct strset *set,
					    struct mem_pool *pool,
					    int strdup_strings)
{
	strmap_init_with_options(&set->map, pool, strdup_strings);
}

static inline void strset_clear(struct strset *set)
{
	strmap_clear(&set->map, 0);
}

static inline void strset_partial_clear(struct strset *set)
{
	strmap_partial_clear(&set->map, 0);
}

static inline int strset_contains(struct strset *set, const char *str)
{
	return strmap_contains(&set->map, str);
}

static inline void strset_remove(struct strset *set, const char *str)
{
	strmap_remove(&set->map, str, 0);
}

static inline int strset_empty(struct strset *set)
{
	return strmap_empty(&set->map);
}

static inline unsigned int strset_get_size(struct strset *set)
{
	return strmap_get_size(&set->map);
}

/* Returns 1 if str is added to the set; returns 0 if str was already in set */
int strset_add(struct strset *set, const char *str);

#endif /* STRMAP_H */
back to top