promisor-remote: check advertised name or URL

A previous commit introduced a "promisor.acceptFromServer" configuration
variable with only "None" or "All" as valid values.

Let's introduce "KnownName" and "KnownUrl" as valid values for this
configuration option to give more choice to a client about which
promisor remotes it might accept among those that the server advertised.

In case of "KnownName", the client will accept promisor remotes which
are already configured on the client and have the same name as those
advertised by the client. This could be useful in a corporate setup
where servers and clients are trusted to not switch names and URLs, but
where some kind of control is still useful.

In case of "KnownUrl", the client will accept promisor remotes which
have both the same name and the same URL configured on the client as the
name and URL advertised by the server. This is the most secure option,
so it should be used if possible.

Signed-off-by: Christian Couder <[email protected]>

Author: chriscool

Documentation/config/promisor.txt

@@ -12,9 +12,19 @@ promisor.advertise::
 promisor.acceptFromServer::
 	If set to "all", a client will accept all the promisor remotes
 	a server might advertise using the "promisor-remote"
-	capability. Default is "none", which means no promisor remote
-	advertised by a server will be accepted. By accepting a
-	promisor remote, the client agrees that the server might omit
-	objects that are lazily fetchable from this promisor remote
-	from its responses to "fetch" and "clone" requests from the
-	client. See linkgit:gitprotocol-v2[5].
+	capability. If set to "knownName" the client will accept
+	promisor remotes which are already configured on the client
+	and have the same name as those advertised by the client. This
+	is not very secure, but could be used in a corporate setup
+	where servers and clients are trusted to not switch name and
+	URLs. If set to "knownUrl", the client will accept promisor
+	remotes which have both the same name and the same URL
+	configured on the client as the name and URL advertised by the
+	server. This is more secure than "all" or "knownUrl", so it
+	should be used if possible instead of those options. Default
+	is "none", which means no promisor remote advertised by a
+	server will be accepted. By accepting a promisor remote, the
+	client agrees that the server might omit objects that are
+	lazily fetchable from this promisor remote from its responses
+	to "fetch" and "clone" requests from the client. See
+	linkgit:gitprotocol-v2[5].

promisor-remote.c

@@ -370,30 +370,73 @@ char *promisor_remote_info(struct repository *repo)
 	return strbuf_detach(&sb, NULL);
 }
 
+/*
+ * Find first index of 'vec' where there is 'val'. 'val' is compared
+ * case insensively to the strings in 'vec'. If not found 'vec->nr' is
+ * returned.
+ */
+static size_t strvec_find_index(struct strvec *vec, const char *val)
+{
+	for (size_t i = 0; i < vec->nr; i++)
+		if (!strcasecmp(vec->v[i], val))
+			return i;
+	return vec->nr;
+}
+
 enum accept_promisor {
 	ACCEPT_NONE = 0,
+	ACCEPT_KNOWN_URL,
+	ACCEPT_KNOWN_NAME,
 	ACCEPT_ALL
 };
 
 static int should_accept_remote(enum accept_promisor accept,
-				const char *remote_name UNUSED,
-				const char *remote_url UNUSED)
+				const char *remote_name, const char *remote_url,
+				struct strvec *names, struct strvec *urls)
 {
+	size_t i;
+
 	if (accept == ACCEPT_ALL)
 		return 1;
 
-	BUG("Unhandled 'enum accept_promisor' value '%d'", accept);
+	i = strvec_find_index(names, remote_name);
+
+	if (i >= names->nr)
+		/* We don't know about that remote */
+		return 0;
+
+	if (accept == ACCEPT_KNOWN_NAME)
+		return 1;
+
+	if (accept != ACCEPT_KNOWN_URL)
+		BUG("Unhandled 'enum accept_promisor' value '%d'", accept);
+
+	if (!strcasecmp(urls->v[i], remote_url))
+		return 1;
+
+	warning(_("known remote named '%s' but with url '%s' instead of '%s'"),
+		remote_name, urls->v[i], remote_url);
+
+	return 0;
 }
 
-static void filter_promisor_remote(struct strvec *accepted, const char *info)
+static void filter_promisor_remote(struct repository *repo,
+				   struct strvec *accepted,
+				   const char *info)
 {
 	struct strbuf **remotes;
 	const char *accept_str;
 	enum accept_promisor accept = ACCEPT_NONE;
+	struct strvec names = STRVEC_INIT;
+	struct strvec urls = STRVEC_INIT;
 
 	if (!git_config_get_string_tmp("promisor.acceptfromserver", &accept_str)) {
 		if (!accept_str || !*accept_str || !strcasecmp("None", accept_str))
 			accept = ACCEPT_NONE;
+		else if (!strcasecmp("KnownUrl", accept_str))
+			accept = ACCEPT_KNOWN_URL;
+		else if (!strcasecmp("KnownName", accept_str))
+			accept = ACCEPT_KNOWN_NAME;
 		else if (!strcasecmp("All", accept_str))
 			accept = ACCEPT_ALL;
 		else
@@ -404,6 +447,9 @@ static void filter_promisor_remote(struct strvec *accepted, const char *info)
 	if (accept == ACCEPT_NONE)
 		return;
 
+	if (accept != ACCEPT_ALL)
+		promisor_info_vecs(repo, &names, &urls);
+
 	/* Parse remote info received */
 
 	remotes = strbuf_split_str(info, ';', 0);
@@ -433,14 +479,16 @@ static void filter_promisor_remote(struct strvec *accepted, const char *info)
 		if (remote_url)
 			decoded_url = url_percent_decode(remote_url);
 
-		if (decoded_name && should_accept_remote(accept, decoded_name, decoded_url))
+		if (decoded_name && should_accept_remote(accept, decoded_name, decoded_url, &names, &urls))
 			strvec_push(accepted, decoded_name);
 
 		strbuf_list_free(elems);
 		free(decoded_name);
 		free(decoded_url);
 	}
 
+	strvec_clear(&names);
+	strvec_clear(&urls);
 	strbuf_list_free(remotes);
 }
 
@@ -449,7 +497,7 @@ char *promisor_remote_reply(const char *info)
 	struct strvec accepted = STRVEC_INIT;
 	struct strbuf reply = STRBUF_INIT;
 
-	filter_promisor_remote(&accepted, info);
+	filter_promisor_remote(the_repository, &accepted, info);
 
 	if (!accepted.nr)
 		return NULL;

t/t5710-promisor-remote-capability.sh

@@ -160,6 +160,74 @@ test_expect_success "init + fetch with promisor.advertise set to 'true'" '
 	check_missing_objects server 1 "$oid"
 '
 
+test_expect_success "clone with promisor.acceptfromserver set to 'KnownName'" '
+	git -C server config promisor.advertise true &&
+
+	# Clone from server to create a client
+	GIT_NO_LAZY_FETCH=0 git clone -c remote.server2.promisor=true \
+		-c remote.server2.fetch="+refs/heads/*:refs/remotes/server2/*" \
+		-c remote.server2.url="file://$(pwd)/server2" \
+		-c promisor.acceptfromserver=KnownName \
+		--no-local --filter="blob:limit=5k" server client &&
+	test_when_finished "rm -rf client" &&
+
+	# Check that the largest object is still missing on the server
+	check_missing_objects server 1 "$oid"
+'
+
+test_expect_success "clone with 'KnownName' and different remote names" '
+	git -C server config promisor.advertise true &&
+
+	# Clone from server to create a client
+	GIT_NO_LAZY_FETCH=0 git clone -c remote.serverTwo.promisor=true \
+		-c remote.serverTwo.fetch="+refs/heads/*:refs/remotes/server2/*" \
+		-c remote.serverTwo.url="file://$(pwd)/server2" \
+		-c promisor.acceptfromserver=KnownName \
+		--no-local --filter="blob:limit=5k" server client &&
+	test_when_finished "rm -rf client" &&
+
+	# Check that the largest object is not missing on the server
+	check_missing_objects server 0 "" &&
+
+	# Reinitialize server so that the largest object is missing again
+	initialize_server 1 "$oid"
+'
+
+test_expect_success "clone with promisor.acceptfromserver set to 'KnownUrl'" '
+	git -C server config promisor.advertise true &&
+
+	# Clone from server to create a client
+	GIT_NO_LAZY_FETCH=0 git clone -c remote.server2.promisor=true \
+		-c remote.server2.fetch="+refs/heads/*:refs/remotes/server2/*" \
+		-c remote.server2.url="file://$(pwd)/server2" \
+		-c promisor.acceptfromserver=KnownUrl \
+		--no-local --filter="blob:limit=5k" server client &&
+	test_when_finished "rm -rf client" &&
+
+	# Check that the largest object is still missing on the server
+	check_missing_objects server 1 "$oid"
+'
+
+test_expect_success "clone with 'KnownUrl' and different remote urls" '
+	ln -s server2 serverTwo &&
+
+	git -C server config promisor.advertise true &&
+
+	# Clone from server to create a client
+	GIT_NO_LAZY_FETCH=0 git clone -c remote.server2.promisor=true \
+		-c remote.server2.fetch="+refs/heads/*:refs/remotes/server2/*" \
+		-c remote.server2.url="file://$(pwd)/serverTwo" \
+		-c promisor.acceptfromserver=KnownUrl \
+		--no-local --filter="blob:limit=5k" server client &&
+	test_when_finished "rm -rf client" &&
+
+	# Check that the largest object is not missing on the server
+	check_missing_objects server 0 "" &&
+
+	# Reinitialize server so that the largest object is missing again
+	initialize_server 1 "$oid"
+'
+
 test_expect_success "clone with promisor.advertise set to 'true' but don't delete the client" '
 	git -C server config promisor.advertise true &&