[v2,02/20] hash: require hash algorithm in `hasheq()`, `hashcmp()` and `hashclr()`

Message ID	aa468c3d88eb673343b934d3c8e7fe991d15ba2f.1718259125.git.ps@pks.im (mailing list archive)
State	Superseded
Headers	show Received: from wfhigh8-smtp.messagingengine.com (wfhigh8-smtp.messagingengine.com [64.147.123.159]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 31E871369BE for <git@vger.kernel.org>; Thu, 13 Jun 2024 06:13:35 +0000 (UTC) Feedback-ID: i197146af:Fastmail Date: Thu, 13 Jun 2024 08:13:31 +0200 From: Patrick Steinhardt <ps@pks.im> To: git@vger.kernel.org Cc: Ghanshyam Thakkar <shyamthakkar001@gmail.com>, "brian m. carlson" <sandals@crustytoothpaste.net> Subject: [PATCH v2 02/20] hash: require hash algorithm in `hasheq()`, `hashcmp()` and `hashclr()` Message-ID: <aa468c3d88eb673343b934d3c8e7fe991d15ba2f.1718259125.git.ps@pks.im> References: <cover.1718106284.git.ps@pks.im> <cover.1718259125.git.ps@pks.im> Precedence: bulk MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="iC1ZFNsSGezsDCpH" Content-Disposition: inline In-Reply-To: <cover.1718259125.git.ps@pks.im>
Series	Introduce `USE_THE_REPOSITORY_VARIABLE` macro \| expand [v2,00/20] Introduce `USE_THE_REPOSITORY_VARIABLE` macro [v2,01/20] hash: drop (mostly) unused `is_empty_{blob,tree}_sha1()` functions [v2,02/20] hash: require hash algorithm in `hasheq()`, `hashcmp()` and `hashclr()` [v2,03/20] hash: require hash algorithm in `oidread()` and `oidclr()` [v2,04/20] global: ensure that object IDs are always padded [v2,05/20] hash: convert `oidcmp()` and `oideq()` to compare whole hash [v2,06/20] hash: make `is_null_oid()` independent of `the_repository` [v2,07/20] hash: require hash algorithm in `is_empty_{blob,tree}_oid()` [v2,08/20] hash: require hash algorithm in `empty_tree_oid_hex()` [v2,09/20] global: introduce `USE_THE_REPOSITORY_VARIABLE` macro [v2,10/20] refs: avoid include cycle with "repository.h" [v2,11/20] hash-ll: merge with "hash.h" [v2,12/20] http-fetch: don't crash when parsing packfile without a repo [v2,13/20] oidset: pass hash algorithm when parsing file [v2,14/20] protocol-caps: use hash algorithm from passed-in repository [v2,15/20] replace-object: use hash algorithm from passed-in repository [v2,16/20] compat/fsmonitor: fix socket path in networked SHA256 repos [v2,17/20] t/helper: use correct object hash in partial-clone helper [v2,18/20] t/helper: fix segfault in "oid-array" command without repository [v2,19/20] t/helper: remove dependency on `the_repository` in "proc-receive" [v2,20/20] hex: guard declarations with `USE_THE_REPOSITORY_VARIABLE`

diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 856428fef9..ea727fba16 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1204,7 +1204,7 @@ static void parse_pack_objects(unsigned char *hash) the_hash_algo->init_fn(&tmp_ctx); the_hash_algo->clone_fn(&tmp_ctx, &input_ctx); the_hash_algo->final_fn(hash, &tmp_ctx); - if (!hasheq(fill(the_hash_algo->rawsz), hash)) + if (!hasheq(fill(the_hash_algo->rawsz), hash, the_repository->hash_algo)) die(_("pack is corrupted (SHA1 mismatch)")); use(the_hash_algo->rawsz); @@ -1307,11 +1307,11 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha stop_progress_msg(&progress, msg.buf); strbuf_release(&msg); finalize_hashfile(f, tail_hash, FSYNC_COMPONENT_PACK, 0); - hashcpy(read_hash, pack_hash); + hashcpy(read_hash, pack_hash, the_repository->hash_algo); fixup_pack_header_footer(output_fd, pack_hash, curr_pack, nr_objects, read_hash, consumed_bytes-the_hash_algo->rawsz); - if (!hasheq(read_hash, tail_hash)) + if (!hasheq(read_hash, tail_hash, the_repository->hash_algo)) die(_("Unexpected tail checksum for %s " "(disk corruption?)"), curr_pack); } diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index 4c735ba069..103c11b9d3 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -155,7 +155,7 @@ static inline struct llist_item * llist_sorted_remove(struct llist *list, const l = (hint == NULL) ? list->front : hint; prev = NULL; while (l) { - const int cmp = hashcmp(l->oid.hash, oid); + const int cmp = hashcmp(l->oid.hash, oid, the_repository->hash_algo); if (cmp > 0) /* not in list, since sorted */ return prev; if (!cmp) { /* found */ @@ -258,7 +258,8 @@ static void cmp_two_packs(struct pack_list *p1, struct pack_list *p2) while (p1_off < p1->pack->num_objects * p1_step && p2_off < p2->pack->num_objects * p2_step) { - const int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off); + const int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off, + the_repository->hash_algo); /* cmp ~ p1 - p2 */ if (cmp == 0) { p1_hint = llist_sorted_remove(p1->unique_objects, @@ -296,7 +297,8 @@ static size_t sizeof_union(struct packed_git *p1, struct packed_git *p2) while (p1_off < p1->num_objects * p1_step && p2_off < p2->num_objects * p2_step) { - int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off); + int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off, + the_repository->hash_algo); /* cmp ~ p1 - p2 */ if (cmp == 0) { ret++; diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c index f1c85a00ae..0855572c27 100644 --- a/builtin/unpack-objects.c +++ b/builtin/unpack-objects.c @@ -674,7 +674,8 @@ int cmd_unpack_objects(int argc, const char **argv, const char *prefix UNUSED) if (fsck_finish(&fsck_options)) die(_("fsck error in pack objects")); } - if (!hasheq(fill(the_hash_algo->rawsz), oid.hash)) + if (!hasheq(fill(the_hash_algo->rawsz), oid.hash, + the_repository->hash_algo)) die("final sha1 did not match"); use(the_hash_algo->rawsz); diff --git a/commit-graph.c b/commit-graph.c index e5dd3553df..3429156b28 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -565,7 +565,8 @@ static int add_graph_to_chain(struct commit_graph *g, if (!cur_g || !oideq(&oids[n], &cur_g->oid) || - !hasheq(oids[n].hash, g->chunk_base_graphs + st_mult(g->hash_len, n))) { + !hasheq(oids[n].hash, g->chunk_base_graphs + st_mult(g->hash_len, n), + the_repository->hash_algo)) { warning(_("commit-graph chain does not match")); return 0; } diff --git a/csum-file.c b/csum-file.c index 870748e016..f4be0804b7 100644 --- a/csum-file.c +++ b/csum-file.c @@ -68,12 +68,12 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result, hashflush(f); if (f->skip_hash) - hashclr(f->buffer); + hashclr(f->buffer, the_repository->hash_algo); else the_hash_algo->final_fn(f->buffer, &f->ctx); if (result) - hashcpy(result, f->buffer); + hashcpy(result, f->buffer, the_repository->hash_algo); if (flags & CSUM_HASH_IN_STREAM) flush(f, f->buffer, the_hash_algo->rawsz); if (flags & CSUM_FSYNC) @@ -237,5 +237,5 @@ int hashfile_checksum_valid(const unsigned char *data, size_t total_len) the_hash_algo->update_fn(&ctx, data, data_len); the_hash_algo->final_fn(got, &ctx); - return hasheq(got, data + data_len); + return hasheq(got, data + data_len, the_repository->hash_algo); } diff --git a/hash-ll.h b/hash-ll.h index 2cfde63ae1..fabdd8ecc7 100644 --- a/hash-ll.h +++ b/hash-ll.h @@ -245,7 +245,7 @@ static inline int hash_algo_by_ptr(const struct git_hash_algo *p) const struct object_id *null_oid(void); -static inline int hashcmp_algop(const unsigned char *sha1, const unsigned char *sha2, const struct git_hash_algo *algop) +static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2, const struct git_hash_algo *algop) { /* * Teach the compiler that there are only two possibilities of hash size @@ -256,7 +256,7 @@ static inline int hashcmp_algop(const unsigned char *sha1, const unsigned char * return memcmp(sha1, sha2, GIT_SHA1_RAWSZ); } -static inline int hasheq_algop(const unsigned char *sha1, const unsigned char *sha2, const struct git_hash_algo *algop) +static inline int hasheq(const unsigned char *sha1, const unsigned char *sha2, const struct git_hash_algo *algop) { /* * We write this here instead of deferring to hashcmp so that the @@ -267,6 +267,17 @@ static inline int hasheq_algop(const unsigned char *sha1, const unsigned char *s return !memcmp(sha1, sha2, GIT_SHA1_RAWSZ); } +static inline void hashcpy(unsigned char *sha_dst, const unsigned char *sha_src, + const struct git_hash_algo *algop) +{ + memcpy(sha_dst, sha_src, algop->rawsz); +} + +static inline void hashclr(unsigned char *hash, const struct git_hash_algo *algop) +{ + memset(hash, 0, algop->rawsz); +} + static inline void oidcpy(struct object_id *dst, const struct object_id *src) { memcpy(dst->hash, src->hash, GIT_MAX_RAWSZ); diff --git a/hash-lookup.c b/hash-lookup.c index 9f0f95e2b9..9aa6b82eb7 100644 --- a/hash-lookup.c +++ b/hash-lookup.c @@ -112,7 +112,8 @@ int bsearch_hash(const unsigned char *hash, const uint32_t *fanout_nbo, while (lo < hi) { unsigned mi = lo + (hi - lo) / 2; - int cmp = hashcmp(table + mi * stride, hash); + int cmp = hashcmp(table + mi * stride, hash, + the_repository->hash_algo); if (!cmp) { if (result) diff --git a/hash.h b/hash.h index a1161e1b22..714938e2eb 100644 --- a/hash.h +++ b/hash.h @@ -6,11 +6,6 @@ #define the_hash_algo the_repository->hash_algo -static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2) -{ - return hashcmp_algop(sha1, sha2, the_hash_algo); -} - static inline int oidcmp(const struct object_id *oid1, const struct object_id *oid2) { const struct git_hash_algo *algop; @@ -18,12 +13,7 @@ static inline int oidcmp(const struct object_id *oid1, const struct object_id *o algop = the_hash_algo; else algop = &hash_algos[oid1->algo]; - return hashcmp_algop(oid1->hash, oid2->hash, algop); -} - -static inline int hasheq(const unsigned char *sha1, const unsigned char *sha2) -{ - return hasheq_algop(sha1, sha2, the_hash_algo); + return hashcmp(oid1->hash, oid2->hash, algop); } static inline int oideq(const struct object_id *oid1, const struct object_id *oid2) @@ -33,7 +23,7 @@ static inline int oideq(const struct object_id *oid1, const struct object_id *oi algop = the_hash_algo; else algop = &hash_algos[oid1->algo]; - return hasheq_algop(oid1->hash, oid2->hash, algop); + return hasheq(oid1->hash, oid2->hash, algop); } static inline int is_null_oid(const struct object_id *oid) @@ -41,11 +31,6 @@ static inline int is_null_oid(const struct object_id *oid) return oideq(oid, null_oid()); } -static inline void hashcpy(unsigned char *sha_dst, const unsigned char *sha_src) -{ - memcpy(sha_dst, sha_src, the_hash_algo->rawsz); -} - /* Like oidcpy() but zero-pads the unused bytes in dst's hash array. */ static inline void oidcpy_with_padding(struct object_id *dst, const struct object_id *src) @@ -62,11 +47,6 @@ static inline void oidcpy_with_padding(struct object_id *dst, dst->algo = src->algo; } -static inline void hashclr(unsigned char *hash) -{ - memset(hash, 0, the_hash_algo->rawsz); -} - static inline void oidclr(struct object_id *oid) { memset(oid->hash, 0, GIT_MAX_RAWSZ); diff --git a/http-walker.c b/http-walker.c index b395ef1327..cf7f8c82bc 100644 --- a/http-walker.c +++ b/http-walker.c @@ -485,7 +485,7 @@ static int fetch_object(struct walker *walker, unsigned char *hash) list_for_each(pos, head) { obj_req = list_entry(pos, struct object_request, node); - if (hasheq(obj_req->oid.hash, hash)) + if (hasheq(obj_req->oid.hash, hash, the_repository->hash_algo)) break; } if (!obj_req) diff --git a/match-trees.c b/match-trees.c index 3412b6a140..849b391d3d 100644 --- a/match-trees.c +++ b/match-trees.c @@ -237,7 +237,7 @@ static int splice_tree(const struct object_id *oid1, const char *prefix, } else { rewrite_with = oid2; } - hashcpy(rewrite_here, rewrite_with->hash); + hashcpy(rewrite_here, rewrite_with->hash, the_repository->hash_algo); status = write_object_file(buf, sz, OBJ_TREE, result); free(buf); return status; diff --git a/notes.c b/notes.c index 53ca25c814..5296fd863f 100644 --- a/notes.c +++ b/notes.c @@ -149,7 +149,7 @@ static struct leaf_node *note_tree_find(struct notes_tree *t, void **p = note_tree_search(t, &tree, &n, key_sha1); if (GET_PTR_TYPE(*p) == PTR_TYPE_NOTE) { struct leaf_node *l = (struct leaf_node *) CLR_PTR_TYPE(*p); - if (hasheq(key_sha1, l->key_oid.hash)) + if (hasheq(key_sha1, l->key_oid.hash, the_repository->hash_algo)) return l; } return NULL; diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 6cae670412..59d2e3a387 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -790,7 +790,7 @@ static void write_hash_cache(struct hashfile *f, void bitmap_writer_set_checksum(struct bitmap_writer *writer, const unsigned char *sha1) { - hashcpy(writer->pack_checksum, sha1); + hashcpy(writer->pack_checksum, sha1, the_repository->hash_algo); } void bitmap_writer_finish(struct bitmap_writer *writer, @@ -816,7 +816,7 @@ void bitmap_writer_finish(struct bitmap_writer *writer, header.version = htons(default_version); header.options = htons(flags | options); header.entry_count = htonl(writer->selected_nr); - hashcpy(header.checksum, writer->pack_checksum); + hashcpy(header.checksum, writer->pack_checksum, the_repository->hash_algo); hashwrite(f, &header, sizeof(header) - GIT_MAX_RAWSZ + the_hash_algo->rawsz); dump_bitmap(f, writer->commits); diff --git a/pack-bitmap.c b/pack-bitmap.c index fe8e8a51d3..184d28f05c 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -367,7 +367,8 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, if (load_bitmap_header(bitmap_git) < 0) goto cleanup; - if (!hasheq(get_midx_checksum(bitmap_git->midx), bitmap_git->checksum)) { + if (!hasheq(get_midx_checksum(bitmap_git->midx), bitmap_git->checksum, + the_repository->hash_algo)) { error(_("checksum doesn't match in MIDX and bitmap")); goto cleanup; } diff --git a/pack-check.c b/pack-check.c index 25104d5b14..288f5a3479 100644 --- a/pack-check.c +++ b/pack-check.c @@ -78,10 +78,11 @@ static int verify_packfile(struct repository *r, } while (offset < pack_sig_ofs); r->hash_algo->final_fn(hash, &ctx); pack_sig = use_pack(p, w_curs, pack_sig_ofs, NULL); - if (!hasheq(hash, pack_sig)) + if (!hasheq(hash, pack_sig, r->hash_algo)) err = error("%s pack checksum mismatch", p->pack_name); - if (!hasheq(index_base + index_size - r->hash_algo->hexsz, pack_sig)) + if (!hasheq(index_base + index_size - r->hash_algo->hexsz, pack_sig, + r->hash_algo)) err = error("%s pack checksum does not match its index", p->pack_name); unuse_pack(w_curs); diff --git a/pack-write.c b/pack-write.c index 80ecfa544c..eef625fa5b 100644 --- a/pack-write.c +++ b/pack-write.c @@ -428,7 +428,8 @@ void fixup_pack_header_footer(int pack_fd, if (partial_pack_offset == 0) { unsigned char hash[GIT_MAX_RAWSZ]; the_hash_algo->final_fn(hash, &old_hash_ctx); - if (!hasheq(hash, partial_pack_hash)) + if (!hasheq(hash, partial_pack_hash, + the_repository->hash_algo)) die("Unexpected checksum for %s " "(disk corruption?)", pack_name); /* diff --git a/packfile.c b/packfile.c index d4df7fdeea..9156e9122c 100644 --- a/packfile.c +++ b/packfile.c @@ -242,7 +242,7 @@ struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) struct packed_git *p = alloc_packed_git(alloc); memcpy(p->pack_name, path, alloc); /* includes NUL */ - hashcpy(p->hash, sha1); + hashcpy(p->hash, sha1, the_repository->hash_algo); if (check_packed_git_idx(idx_path, p)) { free(p); return NULL; @@ -596,7 +596,7 @@ static int open_packed_git_1(struct packed_git *p) if (read_result != hashsz) return error("packfile %s signature is unavailable", p->pack_name); idx_hash = ((unsigned char *)p->index_data) + p->index_size - hashsz * 2; - if (!hasheq(hash, idx_hash)) + if (!hasheq(hash, idx_hash, the_repository->hash_algo)) return error("packfile %s does not match index", p->pack_name); return 0; } @@ -751,7 +751,7 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local) p->mtime = st.st_mtime; if (path_len < the_hash_algo->hexsz || get_hash_hex(path + path_len - the_hash_algo->hexsz, p->hash)) - hashclr(p->hash); + hashclr(p->hash, the_repository->hash_algo); return p; } @@ -1971,7 +1971,7 @@ off_t find_pack_entry_one(const unsigned char *sha1, return 0; } - hashcpy(oid.hash, sha1); + hashcpy(oid.hash, sha1, the_repository->hash_algo); if (bsearch_pack(&oid, p, &result)) return nth_packed_object_offset(p, result); return 0; diff --git a/read-cache.c b/read-cache.c index 10e002ce6d..2642ac9558 100644 --- a/read-cache.c +++ b/read-cache.c @@ -1735,7 +1735,7 @@ static int verify_hdr(const struct cache_header *hdr, unsigned long size) the_hash_algo->init_fn(&c); the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz); the_hash_algo->final_fn(hash, &c); - if (!hasheq(hash, start)) + if (!hasheq(hash, start, the_repository->hash_algo)) return error(_("bad index file sha1 signature")); return 0; } @@ -2641,7 +2641,7 @@ static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, ondisk->uid = htonl(ce->ce_stat_data.sd_uid); ondisk->gid = htonl(ce->ce_stat_data.sd_gid); ondisk->size = htonl(ce->ce_stat_data.sd_size); - hashcpy(ondisk->data, ce->oid.hash); + hashcpy(ondisk->data, ce->oid.hash, the_repository->hash_algo); flags = ce->ce_flags & ~CE_NAMEMASK; flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce)); @@ -2730,7 +2730,7 @@ static int verify_index_from(const struct index_state *istate, const char *path) if (n != the_hash_algo->rawsz) goto out; - if (!hasheq(istate->oid.hash, hash)) + if (!hasheq(istate->oid.hash, hash, the_repository->hash_algo)) goto out; close(fd); @@ -3603,7 +3603,7 @@ static size_t read_eoie_extension(const char *mmap, size_t mmap_size) src_offset += extsize; } the_hash_algo->final_fn(hash, &c); - if (!hasheq(hash, (const unsigned char *)index)) + if (!hasheq(hash, (const unsigned char *)index, the_repository->hash_algo)) return 0; /* Validate that the extension offsets returned us back to the eoie extension. */

[v2,02/20] hash: require hash algorithm in `hasheq()`, `hashcmp()` and `hashclr()`

Commit Message

Patch