hash: require hash algorithm in hasheq(), hashcmp() and hashclr()

Many of our hash functions have two variants, one receiving a `struct
git_hash_algo` and one that derives it via `the_repository`. Adapt all
of those functions to always require the hash algorithm as input and
drop the variants that do not accept one.

As those functions are now independent of `the_repository`, we can move
them from "hash.h" to "hash-ll.h".

Note that both in this and subsequent commits in this series we always
just pass `the_repository->hash_algo` as input even if it is obvious
that there is a repository in the context that we should be using the
hash from instead. This is done to be on the safe side and not introduce
any regressions. All callsites should eventually be amended to use a
repo passed via parameters, but this is outside the scope of this patch
series.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

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);
 	}

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++;

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);
 

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;
 		}

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);
 }

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);

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)

hash.h

@@ -6,24 +6,14 @@
 
 #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;
 	if (!oid1->algo)
 		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)
@@ -33,19 +23,14 @@ 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)
 {
 	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);

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)

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;