1 files changed, 207 insertions, 110 deletions

diff --git a/object-file.c b/object-file.c
index c3d866a287..6c8e3b1660 100644
--- a/object-file.c
+++ b/object-file.c
@@ -165,54 +165,51 @@ static void git_hash_unknown_final_oid(struct object_id *oid, git_hash_ctx *ctx)
 	BUG("trying to finalize unknown hash");
 }
 
-
 const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = {
 	{
-		NULL,
-		0x00000000,
-		0,
-		0,
-		0,
-		git_hash_unknown_init,
-		git_hash_unknown_clone,
-		git_hash_unknown_update,
-		git_hash_unknown_final,
-		git_hash_unknown_final_oid,
-		NULL,
-		NULL,
-		NULL,
+		.name = NULL,
+		.format_id = 0x00000000,
+		.rawsz = 0,
+		.hexsz = 0,
+		.blksz = 0,
+		.init_fn = git_hash_unknown_init,
+		.clone_fn = git_hash_unknown_clone,
+		.update_fn = git_hash_unknown_update,
+		.final_fn = git_hash_unknown_final,
+		.final_oid_fn = git_hash_unknown_final_oid,
+		.empty_tree = NULL,
+		.empty_blob = NULL,
+		.null_oid = NULL,
 	},
 	{
-		"sha1",
-		/* "sha1", big-endian */
-		0x73686131,
-		GIT_SHA1_RAWSZ,
-		GIT_SHA1_HEXSZ,
-		GIT_SHA1_BLKSZ,
-		git_hash_sha1_init,
-		git_hash_sha1_clone,
-		git_hash_sha1_update,
-		git_hash_sha1_final,
-		git_hash_sha1_final_oid,
-		&empty_tree_oid,
-		&empty_blob_oid,
-		&null_oid_sha1,
+		.name = "sha1",
+		.format_id = GIT_SHA1_FORMAT_ID,
+		.rawsz = GIT_SHA1_RAWSZ,
+		.hexsz = GIT_SHA1_HEXSZ,
+		.blksz = GIT_SHA1_BLKSZ,
+		.init_fn = git_hash_sha1_init,
+		.clone_fn = git_hash_sha1_clone,
+		.update_fn = git_hash_sha1_update,
+		.final_fn = git_hash_sha1_final,
+		.final_oid_fn = git_hash_sha1_final_oid,
+		.empty_tree = &empty_tree_oid,
+		.empty_blob = &empty_blob_oid,
+		.null_oid = &null_oid_sha1,
 	},
 	{
-		"sha256",
-		/* "s256", big-endian */
-		0x73323536,
-		GIT_SHA256_RAWSZ,
-		GIT_SHA256_HEXSZ,
-		GIT_SHA256_BLKSZ,
-		git_hash_sha256_init,
-		git_hash_sha256_clone,
-		git_hash_sha256_update,
-		git_hash_sha256_final,
-		git_hash_sha256_final_oid,
-		&empty_tree_oid_sha256,
-		&empty_blob_oid_sha256,
-		&null_oid_sha256,
+		.name = "sha256",
+		.format_id = GIT_SHA256_FORMAT_ID,
+		.rawsz = GIT_SHA256_RAWSZ,
+		.hexsz = GIT_SHA256_HEXSZ,
+		.blksz = GIT_SHA256_BLKSZ,
+		.init_fn = git_hash_sha256_init,
+		.clone_fn = git_hash_sha256_clone,
+		.update_fn = git_hash_sha256_update,
+		.final_fn = git_hash_sha256_final,
+		.final_oid_fn = git_hash_sha256_final_oid,
+		.empty_tree = &empty_tree_oid_sha256,
+		.empty_blob = &empty_blob_oid_sha256,
+		.null_oid = &null_oid_sha256,
 	}
 };
 
@@ -277,10 +274,11 @@ static struct cached_object {
 static int cached_object_nr, cached_object_alloc;
 
 static struct cached_object empty_tree = {
-	{ EMPTY_TREE_SHA1_BIN_LITERAL },
-	OBJ_TREE,
-	"",
-	0
+	.oid = {
+		.hash = EMPTY_TREE_SHA1_BIN_LITERAL,
+	},
+	.type = OBJ_TREE,
+	.buf = "",
 };
 
 static struct cached_object *find_cached_object(const struct object_id *oid)
@@ -683,6 +681,49 @@ void add_to_alternates_memory(const char *reference)
 			     '\n', NULL, 0);
 }
 
+struct object_directory *set_temporary_primary_odb(const char *dir, int will_destroy)
+{
+	struct object_directory *new_odb;
+
+	/*
+	 * Make sure alternates are initialized, or else our entry may be
+	 * overwritten when they are.
+	 */
+	prepare_alt_odb(the_repository);
+
+	/*
+	 * Make a new primary odb and link the old primary ODB in as an
+	 * alternate
+	 */
+	new_odb = xcalloc(1, sizeof(*new_odb));
+	new_odb->path = xstrdup(dir);
+
+	/*
+	 * Disable ref updates while a temporary odb is active, since
+	 * the objects in the database may roll back.
+	 */
+	new_odb->disable_ref_updates = 1;
+	new_odb->will_destroy = will_destroy;
+	new_odb->next = the_repository->objects->odb;
+	the_repository->objects->odb = new_odb;
+	return new_odb->next;
+}
+
+void restore_primary_odb(struct object_directory *restore_odb, const char *old_path)
+{
+	struct object_directory *cur_odb = the_repository->objects->odb;
+
+	if (strcmp(old_path, cur_odb->path))
+		BUG("expected %s as primary object store; found %s",
+		    old_path, cur_odb->path);
+
+	if (cur_odb->next != restore_odb)
+		BUG("we expect the old primary object store to be the first alternate");
+
+	the_repository->objects->odb = restore_odb;
+	free_object_directory(cur_odb);
+}
+
 /*
  * Compute the exact path an alternate is at and returns it. In case of
  * error NULL is returned and the human readable error is added to `err`
@@ -797,7 +838,7 @@ static void fill_alternate_refs_command(struct child_process *cmd,
 		}
 	}
 
-	cmd->env = local_repo_env;
+	strvec_pushv(&cmd->env, (const char **)local_repo_env);
 	cmd->out = -1;
 }
 
@@ -956,7 +997,7 @@ int has_loose_object_nonlocal(const struct object_id *oid)
 	return check_and_freshen_nonlocal(oid, 0);
 }
 
-static int has_loose_object(const struct object_id *oid)
+int has_loose_object(const struct object_id *oid)
 {
 	return check_and_freshen(oid, 0);
 }
@@ -1009,35 +1050,50 @@ void *xmmap(void *start, size_t length,
 	return ret;
 }
 
-/*
- * With an in-core object data in "map", rehash it to make sure the
- * object name actually matches "oid" to detect object corruption.
- * With "map" == NULL, try reading the object named with "oid" using
- * the streaming interface and rehash it to do the same.
- */
+static int format_object_header_literally(char *str, size_t size,
+					  const char *type, size_t objsize)
+{
+	return xsnprintf(str, size, "%s %"PRIuMAX, type, (uintmax_t)objsize) + 1;
+}
+
+int format_object_header(char *str, size_t size, enum object_type type,
+			 size_t objsize)
+{
+	const char *name = type_name(type);
+
+	if (!name)
+		BUG("could not get a type name for 'enum object_type' value %d", type);
+
+	return format_object_header_literally(str, size, name, objsize);
+}
+
 int check_object_signature(struct repository *r, const struct object_id *oid,
-			   void *map, unsigned long size, const char *type,
-			   struct object_id *real_oidp)
+			   void *buf, unsigned long size,
+			   enum object_type type)
+{
+	struct object_id real_oid;
+
+	hash_object_file(r->hash_algo, buf, size, type, &real_oid);
+
+	return !oideq(oid, &real_oid) ? -1 : 0;
+}
+
+int stream_object_signature(struct repository *r, const struct object_id *oid)
 {
-	struct object_id tmp;
-	struct object_id *real_oid = real_oidp ? real_oidp : &tmp;
+	struct object_id real_oid;
+	unsigned long size;
 	enum object_type obj_type;
 	struct git_istream *st;
 	git_hash_ctx c;
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen;
 
-	if (map) {
-		hash_object_file(r->hash_algo, map, size, type, real_oid);
-		return !oideq(oid, real_oid) ? -1 : 0;
-	}
-
 	st = open_istream(r, oid, &obj_type, &size, NULL);
 	if (!st)
 		return -1;
 
 	/* Generate the header */
-	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX , type_name(obj_type), (uintmax_t)size) + 1;
+	hdrlen = format_object_header(hdr, sizeof(hdr), obj_type, size);
 
 	/* Sha1.. */
 	r->hash_algo->init_fn(&c);
@@ -1054,9 +1110,9 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
 			break;
 		r->hash_algo->update_fn(&c, buf, readlen);
 	}
-	r->hash_algo->final_oid_fn(real_oid, &c);
+	r->hash_algo->final_oid_fn(&real_oid, &c);
 	close_istream(st);
-	return !oideq(oid, real_oid) ? -1 : 0;
+	return !oideq(oid, &real_oid) ? -1 : 0;
 }
 
 int git_open_cloexec(const char *name, int flags)
@@ -1306,7 +1362,7 @@ static void *unpack_loose_rest(git_zstream *stream,
 int parse_loose_header(const char *hdr, struct object_info *oi)
 {
 	const char *type_buf = hdr;
-	unsigned long size;
+	size_t size;
 	int type, type_len = 0;
 
 	/*
@@ -1341,12 +1397,12 @@ int parse_loose_header(const char *hdr, struct object_info *oi)
 			if (c > 9)
 				break;
 			hdr++;
-			size = size * 10 + c;
+			size = st_add(st_mult(size, 10), c);
 		}
 	}
 
 	if (oi->sizep)
-		*oi->sizep = size;
+		*oi->sizep = cast_size_t_to_ulong(size);
 
 	/*
 	 * The length must be followed by a zero byte
@@ -1622,7 +1678,7 @@ int pretend_object_file(void *buf, unsigned long len, enum object_type type,
 {
 	struct cached_object *co;
 
-	hash_object_file(the_hash_algo, buf, len, type_name(type), oid);
+	hash_object_file(the_hash_algo, buf, len, type, oid);
 	if (has_object_file_with_flags(oid, OBJECT_INFO_QUICK | OBJECT_INFO_SKIP_FETCH_OBJECT) ||
 	    find_cached_object(oid))
 		return 0;
@@ -1672,7 +1728,7 @@ void *read_object_file_extended(struct repository *r,
 		die(_("loose object %s (stored in %s) is corrupt"),
 		    oid_to_hex(repl), path);
 
-	if ((p = has_packed_and_bad(r, repl)) != NULL)
+	if ((p = has_packed_and_bad(r, repl)))
 		die(_("packed object %s (stored in %s) is corrupt"),
 		    oid_to_hex(repl), p->pack_name);
 	obj_read_unlock();
@@ -1682,16 +1738,15 @@ void *read_object_file_extended(struct repository *r,
 
 void *read_object_with_reference(struct repository *r,
 				 const struct object_id *oid,
-				 const char *required_type_name,
+				 enum object_type required_type,
 				 unsigned long *size,
 				 struct object_id *actual_oid_return)
 {
-	enum object_type type, required_type;
+	enum object_type type;
 	void *buffer;
 	unsigned long isize;
 	struct object_id actual_oid;
 
-	required_type = type_from_string(required_type_name);
 	oidcpy(&actual_oid, oid);
 	while (1) {
 		int ref_length = -1;
@@ -1729,21 +1784,40 @@ void *read_object_with_reference(struct repository *r,
 	}
 }
 
+static void hash_object_body(const struct git_hash_algo *algo, git_hash_ctx *c,
+			     const void *buf, unsigned long len,
+			     struct object_id *oid,
+			     char *hdr, int *hdrlen)
+{
+	algo->init_fn(c);
+	algo->update_fn(c, hdr, *hdrlen);
+	algo->update_fn(c, buf, len);
+	algo->final_oid_fn(oid, c);
+}
+
 static void write_object_file_prepare(const struct git_hash_algo *algo,
 				      const void *buf, unsigned long len,
-				      const char *type, struct object_id *oid,
+				      enum object_type type, struct object_id *oid,
 				      char *hdr, int *hdrlen)
 {
 	git_hash_ctx c;
 
 	/* Generate the header */
-	*hdrlen = xsnprintf(hdr, *hdrlen, "%s %"PRIuMAX , type, (uintmax_t)len)+1;
+	*hdrlen = format_object_header(hdr, *hdrlen, type, len);
 
 	/* Sha1.. */
-	algo->init_fn(&c);
-	algo->update_fn(&c, hdr, *hdrlen);
-	algo->update_fn(&c, buf, len);
-	algo->final_oid_fn(oid, &c);
+	hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen);
+}
+
+static void write_object_file_prepare_literally(const struct git_hash_algo *algo,
+				      const void *buf, unsigned long len,
+				      const char *type, struct object_id *oid,
+				      char *hdr, int *hdrlen)
+{
+	git_hash_ctx c;
+
+	*hdrlen = format_object_header_literally(hdr, *hdrlen, type, len);
+	hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen);
 }
 
 /*
@@ -1796,21 +1870,38 @@ static int write_buffer(int fd, const void *buf, size_t len)
 	return 0;
 }
 
-int hash_object_file(const struct git_hash_algo *algo, const void *buf,
-		     unsigned long len, const char *type,
-		     struct object_id *oid)
+static void hash_object_file_literally(const struct git_hash_algo *algo,
+				       const void *buf, unsigned long len,
+				       const char *type, struct object_id *oid)
 {
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen = sizeof(hdr);
-	write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen);
-	return 0;
+
+	write_object_file_prepare_literally(algo, buf, len, type, oid, hdr, &hdrlen);
+}
+
+void hash_object_file(const struct git_hash_algo *algo, const void *buf,
+		      unsigned long len, enum object_type type,
+		      struct object_id *oid)
+{
+	hash_object_file_literally(algo, buf, len, type_name(type), oid);
 }
 
 /* Finalize a file on disk, and close it. */
-static void close_loose_object(int fd)
+static void close_loose_object(int fd, const char *filename)
 {
-	if (fsync_object_files)
-		fsync_or_die(fd, "loose object file");
+	if (the_repository->objects->odb->will_destroy)
+		goto out;
+
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		fsync_loose_object_bulk_checkin(fd, filename);
+	else if (fsync_object_files > 0)
+		fsync_or_die(fd, filename);
+	else
+		fsync_component_or_die(FSYNC_COMPONENT_LOOSE_OBJECT, fd,
+				       filename);
+
+out:
 	if (close(fd) != 0)
 		die_errno(_("error when closing loose object file"));
 }
@@ -1872,6 +1963,9 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 	static struct strbuf tmp_file = STRBUF_INIT;
 	static struct strbuf filename = STRBUF_INIT;
 
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		prepare_loose_object_bulk_checkin();
+
 	loose_object_path(the_repository, &filename, oid);
 
 	fd = create_tmpfile(&tmp_file, filename.buf);
@@ -1922,7 +2016,7 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 		die(_("confused by unstable object source data for %s"),
 		    oid_to_hex(oid));
 
-	close_loose_object(fd);
+	close_loose_object(fd, tmp_file.buf);
 
 	if (mtime) {
 		struct utimbuf utb;
@@ -1946,6 +2040,8 @@ static int freshen_packed_object(const struct object_id *oid)
 	struct pack_entry e;
 	if (!find_pack_entry(the_repository, oid, &e))
 		return 0;
+	if (e.p->is_cruft)
+		return 0;
 	if (e.p->freshened)
 		return 1;
 	if (!freshen_file(e.p->pack_name))
@@ -1955,7 +2051,7 @@ static int freshen_packed_object(const struct object_id *oid)
 }
 
 int write_object_file_flags(const void *buf, unsigned long len,
-			    const char *type, struct object_id *oid,
+			    enum object_type type, struct object_id *oid,
 			    unsigned flags)
 {
 	char hdr[MAX_HEADER_LEN];
@@ -1971,9 +2067,9 @@ int write_object_file_flags(const void *buf, unsigned long len,
 	return write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags);
 }
 
-int hash_object_file_literally(const void *buf, unsigned long len,
-			       const char *type, struct object_id *oid,
-			       unsigned flags)
+int write_object_file_literally(const void *buf, unsigned long len,
+				const char *type, struct object_id *oid,
+				unsigned flags)
 {
 	char *header;
 	int hdrlen, status = 0;
@@ -1981,8 +2077,8 @@ int hash_object_file_literally(const void *buf, unsigned long len,
 	/* type string, SP, %lu of the length plus NUL must fit this */
 	hdrlen = strlen(type) + MAX_HEADER_LEN;
 	header = xmalloc(hdrlen);
-	write_object_file_prepare(the_hash_algo, buf, len, type, oid, header,
-				  &hdrlen);
+	write_object_file_prepare_literally(the_hash_algo, buf, len, type,
+					    oid, header, &hdrlen);
 
 	if (!(flags & HASH_WRITE_OBJECT))
 		goto cleanup;
@@ -2009,7 +2105,7 @@ int force_object_loose(const struct object_id *oid, time_t mtime)
 	buf = read_object(the_repository, oid, &type, &len);
 	if (!buf)
 		return error(_("cannot read object for %s"), oid_to_hex(oid));
-	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX , type_name(type), (uintmax_t)len) + 1;
+	hdrlen = format_object_header(hdr, sizeof(hdr), type, len);
 	ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0);
 	free(buf);
 
@@ -2075,7 +2171,8 @@ static int index_mem(struct index_state *istate,
 		     enum object_type type,
 		     const char *path, unsigned flags)
 {
-	int ret, re_allocated = 0;
+	int ret = 0;
+	int re_allocated = 0;
 	int write_object = flags & HASH_WRITE_OBJECT;
 
 	if (!type)
@@ -2102,10 +2199,9 @@ static int index_mem(struct index_state *istate,
 	}
 
 	if (write_object)
-		ret = write_object_file(buf, size, type_name(type), oid);
+		ret = write_object_file(buf, size, type, oid);
 	else
-		ret = hash_object_file(the_hash_algo, buf, size,
-				       type_name(type), oid);
+		hash_object_file(the_hash_algo, buf, size, type, oid);
 	if (re_allocated)
 		free(buf);
 	return ret;
@@ -2117,7 +2213,7 @@ static int index_stream_convert_blob(struct index_state *istate,
 				     const char *path,
 				     unsigned flags)
 {
-	int ret;
+	int ret = 0;
 	const int write_object = flags & HASH_WRITE_OBJECT;
 	struct strbuf sbuf = STRBUF_INIT;
 
@@ -2128,11 +2224,11 @@ static int index_stream_convert_blob(struct index_state *istate,
 				 get_conv_flags(flags));
 
 	if (write_object)
-		ret = write_object_file(sbuf.buf, sbuf.len, type_name(OBJ_BLOB),
+		ret = write_object_file(sbuf.buf, sbuf.len, OBJ_BLOB,
 					oid);
 	else
-		ret = hash_object_file(the_hash_algo, sbuf.buf, sbuf.len,
-				       type_name(OBJ_BLOB), oid);
+		hash_object_file(the_hash_algo, sbuf.buf, sbuf.len, OBJ_BLOB,
+				 oid);
 	strbuf_release(&sbuf);
 	return ret;
 }
@@ -2251,8 +2347,8 @@ int index_path(struct index_state *istate, struct object_id *oid,
 			return error_errno("readlink(\"%s\")", path);
 		if (!(flags & HASH_WRITE_OBJECT))
 			hash_object_file(the_hash_algo, sb.buf, sb.len,
-					 blob_type, oid);
-		else if (write_object_file(sb.buf, sb.len, blob_type, oid))
+					 OBJ_BLOB, oid);
+		else if (write_object_file(sb.buf, sb.len, OBJ_BLOB, oid))
 			rc = error(_("%s: failed to insert into database"), path);
 		strbuf_release(&sb);
 		break;
@@ -2425,7 +2521,7 @@ struct oidtree *odb_loose_cache(struct object_directory *odb,
 	struct strbuf buf = STRBUF_INIT;
 	size_t word_bits = bitsizeof(odb->loose_objects_subdir_seen[0]);
 	size_t word_index = subdir_nr / word_bits;
-	size_t mask = 1u << (subdir_nr % word_bits);
+	size_t mask = (size_t)1u << (subdir_nr % word_bits);
 	uint32_t *bitmap;
 
 	if (subdir_nr < 0 ||
@@ -2535,7 +2631,7 @@ int read_loose_object(const char *path,
 	}
 
 	if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr),
-				NULL) < 0) {
+				NULL) != ULHR_OK) {
 		error(_("unable to unpack header of %s"), path);
 		goto out;
 	}
@@ -2556,9 +2652,10 @@ int read_loose_object(const char *path,
 			git_inflate_end(&stream);
 			goto out;
 		}
-		if (check_object_signature(the_repository, expected_oid,
+		hash_object_file_literally(the_repository->hash_algo,
 					   *contents, *size,
-					   oi->type_name->buf, real_oid))
+					   oi->type_name->buf, real_oid);
+		if (!oideq(expected_oid, real_oid))
 			goto out;
 	}