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
bloom.h
#ifndef BLOOM_H
#define BLOOM_H
struct commit;
struct repository;
struct bloom_filter_settings {
/*
* The version of the hashing technique being used.
* We currently only support version = 1 which is
* the seeded murmur3 hashing technique implemented
* in bloom.c.
*/
uint32_t hash_version;
/*
* The number of times a path is hashed, i.e. the
* number of bit positions tht cumulatively
* determine whether a path is present in the
* Bloom filter.
*/
uint32_t num_hashes;
/*
* The minimum number of bits per entry in the Bloom
* filter. If the filter contains 'n' entries, then
* filter size is the minimum number of 8-bit words
* that contain n*b bits.
*/
uint32_t bits_per_entry;
/*
* The maximum number of changed paths per commit
* before declaring a Bloom filter to be too-large.
*
* Not written to the commit-graph file.
*/
uint32_t max_changed_paths;
};
#define DEFAULT_BLOOM_MAX_CHANGES 512
#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
#define BITS_PER_WORD 8
#define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
/*
* A bloom_filter struct represents a data segment to
* use when testing hash values. The 'len' member
* dictates how many entries are stored in
* 'data'.
*/
struct bloom_filter {
unsigned char *data;
size_t len;
};
/*
* A bloom_key represents the k hash values for a
* given string. These can be precomputed and
* stored in a bloom_key for re-use when testing
* against a bloom_filter. The number of hashes is
* given by the Bloom filter settings and is the same
* for all Bloom filters and keys interacting with
* the loaded version of the commit graph file and
* the Bloom data chunks.
*/
struct bloom_key {
uint32_t *hashes;
};
/*
* Calculate the murmur3 32-bit hash value for the given data
* using the given seed.
* Produces a uniformly distributed hash value.
* Not considered to be cryptographically secure.
* Implemented as described in https://en.wikipedia.org/wiki/MurmurHash#Algorithm
*/
uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len);
void fill_bloom_key(const char *data,
size_t len,
struct bloom_key *key,
const struct bloom_filter_settings *settings);
void clear_bloom_key(struct bloom_key *key);
void add_key_to_filter(const struct bloom_key *key,
struct bloom_filter *filter,
const struct bloom_filter_settings *settings);
void init_bloom_filters(void);
enum bloom_filter_computed {
BLOOM_NOT_COMPUTED = (1 << 0),
BLOOM_COMPUTED = (1 << 1),
BLOOM_TRUNC_LARGE = (1 << 2),
BLOOM_TRUNC_EMPTY = (1 << 3),
};
struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
struct commit *c,
int compute_if_not_present,
const struct bloom_filter_settings *settings,
enum bloom_filter_computed *computed);
#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
(r), (c), 0, NULL, NULL)
int bloom_filter_contains(const struct bloom_filter *filter,
const struct bloom_key *key,
const struct bloom_filter_settings *settings);
#endif
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...