receive-pack: convert receive hooks to hook API

This converts the last remaining hooks to the new hook API, for
the same benefits as the previous conversions (no need to toggle
signals, manage custom struct child_process, call find_hook(),
prepares for specifyinig hooks via configs, etc.).

I noticed a performance degradation when processing large amounts
of hook input with just 1 line per callback, due to run-command's
poll loop, therefore I batched 500 lines per callback, to ensure
similar pipe throughput as before and to avoid hook child waiting
on stdin.

Signed-off-by: Emily Shaffer <emilyshaffer@google.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Adrian Ratiu <adrian.ratiu@collabora.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: nasamuffin

builtin/receive-pack.c

@@ -749,7 +749,7 @@ static int check_cert_push_options(const struct string_list *push_options)
 	return retval;
 }
 
-static void prepare_push_cert_sha1(struct child_process *proc)
+static void prepare_push_cert_sha1(struct run_hooks_opt *opt)
 {
 	static int already_done;
 
@@ -775,23 +775,23 @@ static void prepare_push_cert_sha1(struct child_process *proc)
 		nonce_status = check_nonce(sigcheck.payload);
 	}
 	if (!is_null_oid(&push_cert_oid)) {
-		strvec_pushf(&proc->env, "GIT_PUSH_CERT=%s",
+		strvec_pushf(&opt->env, "GIT_PUSH_CERT=%s",
 			     oid_to_hex(&push_cert_oid));
-		strvec_pushf(&proc->env, "GIT_PUSH_CERT_SIGNER=%s",
+		strvec_pushf(&opt->env, "GIT_PUSH_CERT_SIGNER=%s",
 			     sigcheck.signer ? sigcheck.signer : "");
-		strvec_pushf(&proc->env, "GIT_PUSH_CERT_KEY=%s",
+		strvec_pushf(&opt->env, "GIT_PUSH_CERT_KEY=%s",
 			     sigcheck.key ? sigcheck.key : "");
-		strvec_pushf(&proc->env, "GIT_PUSH_CERT_STATUS=%c",
+		strvec_pushf(&opt->env, "GIT_PUSH_CERT_STATUS=%c",
 			     sigcheck.result);
 		if (push_cert_nonce) {
-			strvec_pushf(&proc->env,
+			strvec_pushf(&opt->env,
 				     "GIT_PUSH_CERT_NONCE=%s",
 				     push_cert_nonce);
-			strvec_pushf(&proc->env,
+			strvec_pushf(&opt->env,
 				     "GIT_PUSH_CERT_NONCE_STATUS=%s",
 				     nonce_status);
 			if (nonce_status == NONCE_SLOP)
-				strvec_pushf(&proc->env,
+				strvec_pushf(&opt->env,
 					     "GIT_PUSH_CERT_NONCE_SLOP=%ld",
 					     nonce_stamp_slop);
 		}
@@ -803,119 +803,64 @@ struct receive_hook_feed_state {
 	struct ref_push_report *report;
 	int skip_broken;
 	struct strbuf buf;
-	const struct string_list *push_options;
 };
 
-typedef int (*feed_fn)(void *, const char **, size_t *);
-static int run_and_feed_hook(const char *hook_name, feed_fn feed,
-			     struct receive_hook_feed_state *feed_state)
+static int feed_receive_hook_cb(int hook_stdin_fd, void *pp_cb UNUSED, void *pp_task_cb)
 {
-	struct child_process proc = CHILD_PROCESS_INIT;
-	struct async muxer;
-	int code;
-	const char *hook_path = find_hook(the_repository, hook_name);
+	struct receive_hook_feed_state *state = pp_task_cb;
+	struct command *cmd = state->cmd;
+	unsigned int lines_batch_size = 500;
 
-	if (!hook_path)
-		return 0;
+	strbuf_reset(&state->buf);
 
-	strvec_push(&proc.args, hook_path);
-	proc.in = -1;
-	proc.stdout_to_stderr = 1;
-	proc.trace2_hook_name = hook_name;
-
-	if (feed_state->push_options) {
-		size_t i;
-		for (i = 0; i < feed_state->push_options->nr; i++)
-			strvec_pushf(&proc.env,
-				     "GIT_PUSH_OPTION_%"PRIuMAX"=%s",
-				     (uintmax_t)i,
-				     feed_state->push_options->items[i].string);
-		strvec_pushf(&proc.env, "GIT_PUSH_OPTION_COUNT=%"PRIuMAX"",
-			     (uintmax_t)feed_state->push_options->nr);
-	} else
-		strvec_pushf(&proc.env, "GIT_PUSH_OPTION_COUNT");
+	/* batch lines to avoid going through run-command's poll loop for each line */
+	for (unsigned int i = 0; i < lines_batch_size; i++) {
+		while (cmd &&
+		       state->skip_broken && (cmd->error_string || cmd->did_not_exist))
+			cmd = cmd->next;
 
-	if (tmp_objdir)
-		strvec_pushv(&proc.env, tmp_objdir_env(tmp_objdir));
+		if (!cmd)
+			break;  /* no more commands left */
 
-	if (use_sideband) {
-		memset(&muxer, 0, sizeof(muxer));
-		muxer.proc = copy_to_sideband;
-		muxer.in = -1;
-		code = start_async(&muxer);
-		if (code)
-			return code;
-		proc.err = muxer.in;
-	}
+		if (!state->report)
+			state->report = cmd->report;
 
-	prepare_push_cert_sha1(&proc);
+		if (state->report) {
+			struct object_id *old_oid;
+			struct object_id *new_oid;
+			const char *ref_name;
 
-	code = start_command(&proc);
-	if (code) {
-		if (use_sideband)
-			finish_async(&muxer);
-		return code;
-	}
+			old_oid = state->report->old_oid ? state->report->old_oid : &cmd->old_oid;
+			new_oid = state->report->new_oid ? state->report->new_oid : &cmd->new_oid;
+			ref_name = state->report->ref_name ? state->report->ref_name : cmd->ref_name;
 
-	sigchain_push(SIGPIPE, SIG_IGN);
+			strbuf_addf(&state->buf, "%s %s %s\n",
+				    oid_to_hex(old_oid), oid_to_hex(new_oid),
+				    ref_name);
 
-	while (1) {
-		const char *buf;
-		size_t n;
-		if (feed(feed_state, &buf, &n))
-			break;
-		if (write_in_full(proc.in, buf, n) < 0)
-			break;
+			state->report = state->report->next;
+			if (!state->report)
+				cmd = cmd->next;
+		} else {
+			strbuf_addf(&state->buf, "%s %s %s\n",
+				    oid_to_hex(&cmd->old_oid), oid_to_hex(&cmd->new_oid),
+				    cmd->ref_name);
+			cmd = cmd->next;
+		}
 	}
-	close(proc.in);
-	if (use_sideband)
-		finish_async(&muxer);
 
-	sigchain_pop(SIGPIPE);
+	state->cmd = cmd;
 
-	return finish_command(&proc);
-}
-
-static int feed_receive_hook(void *state_, const char **bufp, size_t *sizep)
-{
-	struct receive_hook_feed_state *state = state_;
-	struct command *cmd = state->cmd;
-
-	while (cmd &&
-	       state->skip_broken && (cmd->error_string || cmd->did_not_exist))
-		cmd = cmd->next;
-	if (!cmd)
-		return -1; /* EOF */
-	if (!bufp)
-		return 0; /* OK, can feed something. */
-	strbuf_reset(&state->buf);
-	if (!state->report)
-		state->report = cmd->report;
-	if (state->report) {
-		struct object_id *old_oid;
-		struct object_id *new_oid;
-		const char *ref_name;
-
-		old_oid = state->report->old_oid ? state->report->old_oid : &cmd->old_oid;
-		new_oid = state->report->new_oid ? state->report->new_oid : &cmd->new_oid;
-		ref_name = state->report->ref_name ? state->report->ref_name : cmd->ref_name;
-		strbuf_addf(&state->buf, "%s %s %s\n",
-			    oid_to_hex(old_oid), oid_to_hex(new_oid),
-			    ref_name);
-		state->report = state->report->next;
-		if (!state->report)
-			state->cmd = cmd->next;
-	} else {
-		strbuf_addf(&state->buf, "%s %s %s\n",
-			    oid_to_hex(&cmd->old_oid), oid_to_hex(&cmd->new_oid),
-			    cmd->ref_name);
-		state->cmd = cmd->next;
-	}
-	if (bufp) {
-		*bufp = state->buf.buf;
-		*sizep = state->buf.len;
+	if (state->buf.len > 0) {
+		int ret = write_in_full(hook_stdin_fd, state->buf.buf, state->buf.len);
+		if (ret < 0) {
+			if (errno == EPIPE)
+				return 1; /* child closed pipe */
+			return ret;
+		}
 	}
-	return 0;
+
+	return state->cmd ? 0 : 1;  /* 0 = more to come, 1 = EOF */
 }
 
 static void hook_output_to_sideband(struct strbuf *output, void *cb_data UNUSED)
@@ -933,20 +878,49 @@ static int run_receive_hook(struct command *commands,
 			    int skip_broken,
 			    const struct string_list *push_options)
 {
-	struct receive_hook_feed_state state;
-	int status;
-
-	strbuf_init(&state.buf, 0);
-	state.cmd = commands;
-	state.skip_broken = skip_broken;
-	state.report = NULL;
-	if (feed_receive_hook(&state, NULL, NULL))
+	struct run_hooks_opt opt = RUN_HOOKS_OPT_INIT;
+	struct command *iter = commands;
+	struct receive_hook_feed_state feed_state;
+	int ret;
+
+	/* if there are no valid commands, don't invoke the hook at all. */
+	while (iter && skip_broken && (iter->error_string || iter->did_not_exist))
+		iter = iter->next;
+	if (!iter)
 		return 0;
-	state.cmd = commands;
-	state.push_options = push_options;
-	status = run_and_feed_hook(hook_name, feed_receive_hook, &state);
-	strbuf_release(&state.buf);
-	return status;
+
+	if (push_options) {
+		for (int i = 0; i < push_options->nr; i++)
+			strvec_pushf(&opt.env, "GIT_PUSH_OPTION_%d=%s", i,
+				     push_options->items[i].string);
+		strvec_pushf(&opt.env, "GIT_PUSH_OPTION_COUNT=%"PRIuMAX"",
+					     (uintmax_t)push_options->nr);
+	} else {
+		strvec_push(&opt.env, "GIT_PUSH_OPTION_COUNT");
+	}
+
+	if (tmp_objdir)
+		strvec_pushv(&opt.env, tmp_objdir_env(tmp_objdir));
+
+	prepare_push_cert_sha1(&opt);
+
+	/* set up sideband printer */
+	if (use_sideband)
+		opt.consume_output = hook_output_to_sideband;
+
+	/* set up stdin callback */
+	feed_state.cmd = commands;
+	feed_state.skip_broken = skip_broken;
+	feed_state.report = NULL;
+	strbuf_init(&feed_state.buf, 0);
+	opt.feed_pipe_cb_data = &feed_state;
+	opt.feed_pipe = feed_receive_hook_cb;
+
+	ret = run_hooks_opt(the_repository, hook_name, &opt);
+
+	strbuf_release(&feed_state.buf);
+
+	return ret;
 }
 
 static int run_update_hook(struct command *cmd)