Merge branch 'bw/protocol-v2' into jt/partial-clone-proto-v2

The beginning of the next-gen transfer protocol.

* bw/protocol-v2: (35 commits)
  remote-curl: don't request v2 when pushing
  remote-curl: implement stateless-connect command
  http: eliminate "# service" line when using protocol v2
  http: don't always add Git-Protocol header
  http: allow providing extra headers for http requests
  remote-curl: store the protocol version the server responded with
  remote-curl: create copy of the service name
  pkt-line: add packet_buf_write_len function
  transport-helper: introduce stateless-connect
  transport-helper: refactor process_connect_service
  transport-helper: remove name parameter
  connect: don't request v2 when pushing
  connect: refactor git_connect to only get the protocol version once
  fetch-pack: support shallow requests
  fetch-pack: perform a fetch using v2
  upload-pack: introduce fetch server command
  push: pass ref prefixes when pushing
  fetch: pass ref prefixes when fetching
  ls-remote: pass ref prefixes when requesting a remote's refs
  transport: convert transport_get_remote_refs to take a list of ref prefixes
  ...

1 files changed, 333 insertions, 6 deletions

diff --git a/fetch-pack.c b/fetch-pack.c
index 4a8bad8487..f93723fec4 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -305,9 +305,9 @@ static void insert_one_alternate_object(struct object *obj)
 #define PIPESAFE_FLUSH 32
 #define LARGE_FLUSH 16384
 
-static int next_flush(struct fetch_pack_args *args, int count)
+static int next_flush(int stateless_rpc, int count)
 {
-	if (args->stateless_rpc) {
+	if (stateless_rpc) {
 		if (count < LARGE_FLUSH)
 			count <<= 1;
 		else
@@ -470,7 +470,7 @@ static int find_common(struct fetch_pack_args *args,
 			send_request(args, fd[1], &req_buf);
 			strbuf_setlen(&req_buf, state_len);
 			flushes++;
-			flush_at = next_flush(args, count);
+			flush_at = next_flush(args->stateless_rpc, count);
 
 			/*
 			 * We keep one window "ahead" of the other side, and
@@ -1080,6 +1080,328 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 	return ref;
 }
 
+static void add_shallow_requests(struct strbuf *req_buf,
+				 const struct fetch_pack_args *args)
+{
+	if (is_repository_shallow())
+		write_shallow_commits(req_buf, 1, NULL);
+	if (args->depth > 0)
+		packet_buf_write(req_buf, "deepen %d", args->depth);
+	if (args->deepen_since) {
+		timestamp_t max_age = approxidate(args->deepen_since);
+		packet_buf_write(req_buf, "deepen-since %"PRItime, max_age);
+	}
+	if (args->deepen_not) {
+		int i;
+		for (i = 0; i < args->deepen_not->nr; i++) {
+			struct string_list_item *s = args->deepen_not->items + i;
+			packet_buf_write(req_buf, "deepen-not %s", s->string);
+		}
+	}
+}
+
+static void add_wants(const struct ref *wants, struct strbuf *req_buf)
+{
+	for ( ; wants ; wants = wants->next) {
+		const struct object_id *remote = &wants->old_oid;
+		const char *remote_hex;
+		struct object *o;
+
+		/*
+		 * If that object is complete (i.e. it is an ancestor of a
+		 * local ref), we tell them we have it but do not have to
+		 * tell them about its ancestors, which they already know
+		 * about.
+		 *
+		 * We use lookup_object here because we are only
+		 * interested in the case we *know* the object is
+		 * reachable and we have already scanned it.
+		 */
+		if (((o = lookup_object(remote->hash)) != NULL) &&
+		    (o->flags & COMPLETE)) {
+			continue;
+		}
+
+		remote_hex = oid_to_hex(remote);
+		packet_buf_write(req_buf, "want %s\n", remote_hex);
+	}
+}
+
+static void add_common(struct strbuf *req_buf, struct oidset *common)
+{
+	struct oidset_iter iter;
+	const struct object_id *oid;
+	oidset_iter_init(common, &iter);
+
+	while ((oid = oidset_iter_next(&iter))) {
+		packet_buf_write(req_buf, "have %s\n", oid_to_hex(oid));
+	}
+}
+
+static int add_haves(struct strbuf *req_buf, int *haves_to_send, int *in_vain)
+{
+	int ret = 0;
+	int haves_added = 0;
+	const struct object_id *oid;
+
+	while ((oid = get_rev())) {
+		packet_buf_write(req_buf, "have %s\n", oid_to_hex(oid));
+		if (++haves_added >= *haves_to_send)
+			break;
+	}
+
+	*in_vain += haves_added;
+	if (!haves_added || *in_vain >= MAX_IN_VAIN) {
+		/* Send Done */
+		packet_buf_write(req_buf, "done\n");
+		ret = 1;
+	}
+
+	/* Increase haves to send on next round */
+	*haves_to_send = next_flush(1, *haves_to_send);
+
+	return ret;
+}
+
+static int send_fetch_request(int fd_out, const struct fetch_pack_args *args,
+			      const struct ref *wants, struct oidset *common,
+			      int *haves_to_send, int *in_vain)
+{
+	int ret = 0;
+	struct strbuf req_buf = STRBUF_INIT;
+
+	if (server_supports_v2("fetch", 1))
+		packet_buf_write(&req_buf, "command=fetch");
+	if (server_supports_v2("agent", 0))
+		packet_buf_write(&req_buf, "agent=%s", git_user_agent_sanitized());
+
+	packet_buf_delim(&req_buf);
+	if (args->use_thin_pack)
+		packet_buf_write(&req_buf, "thin-pack");
+	if (args->no_progress)
+		packet_buf_write(&req_buf, "no-progress");
+	if (args->include_tag)
+		packet_buf_write(&req_buf, "include-tag");
+	if (prefer_ofs_delta)
+		packet_buf_write(&req_buf, "ofs-delta");
+
+	/* Add shallow-info and deepen request */
+	if (server_supports_feature("fetch", "shallow", 0))
+		add_shallow_requests(&req_buf, args);
+	else if (is_repository_shallow() || args->deepen)
+		die(_("Server does not support shallow requests"));
+
+	/* add wants */
+	add_wants(wants, &req_buf);
+
+	/* Add all of the common commits we've found in previous rounds */
+	add_common(&req_buf, common);
+
+	/* Add initial haves */
+	ret = add_haves(&req_buf, haves_to_send, in_vain);
+
+	/* Send request */
+	packet_buf_flush(&req_buf);
+	write_or_die(fd_out, req_buf.buf, req_buf.len);
+
+	strbuf_release(&req_buf);
+	return ret;
+}
+
+/*
+ * Processes a section header in a server's response and checks if it matches
+ * `section`.  If the value of `peek` is 1, the header line will be peeked (and
+ * not consumed); if 0, the line will be consumed and the function will die if
+ * the section header doesn't match what was expected.
+ */
+static int process_section_header(struct packet_reader *reader,
+				  const char *section, int peek)
+{
+	int ret;
+
+	if (packet_reader_peek(reader) != PACKET_READ_NORMAL)
+		die("error reading section header '%s'", section);
+
+	ret = !strcmp(reader->line, section);
+
+	if (!peek) {
+		if (!ret)
+			die("expected '%s', received '%s'",
+			    section, reader->line);
+		packet_reader_read(reader);
+	}
+
+	return ret;
+}
+
+static int process_acks(struct packet_reader *reader, struct oidset *common)
+{
+	/* received */
+	int received_ready = 0;
+	int received_ack = 0;
+
+	process_section_header(reader, "acknowledgments", 0);
+	while (packet_reader_read(reader) == PACKET_READ_NORMAL) {
+		const char *arg;
+
+		if (!strcmp(reader->line, "NAK"))
+			continue;
+
+		if (skip_prefix(reader->line, "ACK ", &arg)) {
+			struct object_id oid;
+			if (!get_oid_hex(arg, &oid)) {
+				struct commit *commit;
+				oidset_insert(common, &oid);
+				commit = lookup_commit(&oid);
+				mark_common(commit, 0, 1);
+			}
+			continue;
+		}
+
+		if (!strcmp(reader->line, "ready")) {
+			clear_prio_queue(&rev_list);
+			received_ready = 1;
+			continue;
+		}
+
+		die("unexpected acknowledgment line: '%s'", reader->line);
+	}
+
+	if (reader->status != PACKET_READ_FLUSH &&
+	    reader->status != PACKET_READ_DELIM)
+		die("error processing acks: %d", reader->status);
+
+	/* return 0 if no common, 1 if there are common, or 2 if ready */
+	return received_ready ? 2 : (received_ack ? 1 : 0);
+}
+
+static void receive_shallow_info(struct fetch_pack_args *args,
+				 struct packet_reader *reader)
+{
+	process_section_header(reader, "shallow-info", 0);
+	while (packet_reader_read(reader) == PACKET_READ_NORMAL) {
+		const char *arg;
+		struct object_id oid;
+
+		if (skip_prefix(reader->line, "shallow ", &arg)) {
+			if (get_oid_hex(arg, &oid))
+				die(_("invalid shallow line: %s"), reader->line);
+			register_shallow(&oid);
+			continue;
+		}
+		if (skip_prefix(reader->line, "unshallow ", &arg)) {
+			if (get_oid_hex(arg, &oid))
+				die(_("invalid unshallow line: %s"), reader->line);
+			if (!lookup_object(oid.hash))
+				die(_("object not found: %s"), reader->line);
+			/* make sure that it is parsed as shallow */
+			if (!parse_object(&oid))
+				die(_("error in object: %s"), reader->line);
+			if (unregister_shallow(&oid))
+				die(_("no shallow found: %s"), reader->line);
+			continue;
+		}
+		die(_("expected shallow/unshallow, got %s"), reader->line);
+	}
+
+	if (reader->status != PACKET_READ_FLUSH &&
+	    reader->status != PACKET_READ_DELIM)
+		die("error processing shallow info: %d", reader->status);
+
+	setup_alternate_shallow(&shallow_lock, &alternate_shallow_file, NULL);
+	args->deepen = 1;
+}
+
+enum fetch_state {
+	FETCH_CHECK_LOCAL = 0,
+	FETCH_SEND_REQUEST,
+	FETCH_PROCESS_ACKS,
+	FETCH_GET_PACK,
+	FETCH_DONE,
+};
+
+static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
+				    int fd[2],
+				    const struct ref *orig_ref,
+				    struct ref **sought, int nr_sought,
+				    char **pack_lockfile)
+{
+	struct ref *ref = copy_ref_list(orig_ref);
+	enum fetch_state state = FETCH_CHECK_LOCAL;
+	struct oidset common = OIDSET_INIT;
+	struct packet_reader reader;
+	int in_vain = 0;
+	int haves_to_send = INITIAL_FLUSH;
+	packet_reader_init(&reader, fd[0], NULL, 0,
+			   PACKET_READ_CHOMP_NEWLINE);
+
+	while (state != FETCH_DONE) {
+		switch (state) {
+		case FETCH_CHECK_LOCAL:
+			sort_ref_list(&ref, ref_compare_name);
+			QSORT(sought, nr_sought, cmp_ref_by_name);
+
+			/* v2 supports these by default */
+			allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1;
+			use_sideband = 2;
+			if (args->depth > 0 || args->deepen_since || args->deepen_not)
+				args->deepen = 1;
+
+			if (marked)
+				for_each_ref(clear_marks, NULL);
+			marked = 1;
+
+			for_each_ref(rev_list_insert_ref_oid, NULL);
+			for_each_cached_alternate(insert_one_alternate_object);
+
+			/* Filter 'ref' by 'sought' and those that aren't local */
+			if (everything_local(args, &ref, sought, nr_sought))
+				state = FETCH_DONE;
+			else
+				state = FETCH_SEND_REQUEST;
+			break;
+		case FETCH_SEND_REQUEST:
+			if (send_fetch_request(fd[1], args, ref, &common,
+					       &haves_to_send, &in_vain))
+				state = FETCH_GET_PACK;
+			else
+				state = FETCH_PROCESS_ACKS;
+			break;
+		case FETCH_PROCESS_ACKS:
+			/* Process ACKs/NAKs */
+			switch (process_acks(&reader, &common)) {
+			case 2:
+				state = FETCH_GET_PACK;
+				break;
+			case 1:
+				in_vain = 0;
+				/* fallthrough */
+			default:
+				state = FETCH_SEND_REQUEST;
+				break;
+			}
+			break;
+		case FETCH_GET_PACK:
+			/* Check for shallow-info section */
+			if (process_section_header(&reader, "shallow-info", 1))
+				receive_shallow_info(args, &reader);
+
+			/* get the pack */
+			process_section_header(&reader, "packfile", 0);
+			if (get_pack(args, fd, pack_lockfile))
+				die(_("git fetch-pack: fetch failed."));
+
+			state = FETCH_DONE;
+			break;
+		case FETCH_DONE:
+			continue;
+		}
+	}
+
+	oidset_clear(&common);
+	return ref;
+}
+
 static void fetch_pack_config(void)
 {
 	git_config_get_int("fetch.unpacklimit", &fetch_unpack_limit);
@@ -1225,7 +1547,8 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       const char *dest,
 		       struct ref **sought, int nr_sought,
 		       struct oid_array *shallow,
-		       char **pack_lockfile)
+		       char **pack_lockfile,
+		       enum protocol_version version)
 {
 	struct ref *ref_cpy;
 	struct shallow_info si;
@@ -1239,8 +1562,12 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		die(_("no matching remote head"));
 	}
 	prepare_shallow_info(&si, shallow);
-	ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought,
-				&si, pack_lockfile);
+	if (version == protocol_v2)
+		ref_cpy = do_fetch_pack_v2(args, fd, ref, sought, nr_sought,
+					   pack_lockfile);
+	else
+		ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought,
+					&si, pack_lockfile);
 	reprepare_packed_git(the_repository);
 	update_shallow(args, sought, nr_sought, &si);
 	clear_shallow_info(&si);