File

net.server_epoll: Call :shutdown() on TLS sockets when supported Comment from Matthew: This fixes a potential issue where the Prosody process gets blocked on sockets waiting for them to close. Unlike non-TLS sockets, closing a TLS socket sends layer 7 data, and this can cause problems for sockets which are in the process of being cleaned up. This depends on LuaSec changes which are not yet upstream. From Martijn's original email: So first my analysis of luasec. in ssl.c the socket is put into blocking mode right before calling SSL_shutdown() inside meth_destroy(). My best guess to why this is is because meth_destroy is linked to the __close and __gc methods, which can't exactly be called multiple times and luasec does want to make sure that a tls session is shutdown as clean as possible. I can't say I disagree with this reasoning and don't want to change this behaviour. My solution to this without changing the current behaviour is to introduce a shutdown() method. I am aware that this overlaps in a conflicting way with tcp's shutdown method, but it stays close to the OpenSSL name. This method calls SSL_shutdown() in the current (non)blocking mode of the underlying socket and returns a boolean whether or not the shutdown is completed (matching SSL_shutdown()'s 0 or 1 return values), and returns the familiar ssl_ioerror() strings on error with a false for completion. This error can then be used to determine if we have wantread/wantwrite to finalize things. Once meth_shutdown() has been called once a shutdown flag will be set, which indicates to meth_destroy() that the SSL_shutdown() has been handled by the application and it shouldn't be needed to set the socket to blocking mode. I've left the SSL_shutdown() call in the LSEC_STATE_CONNECTED to prevent TOCTOU if the application reaches a timeout for the shutdown code, which might allow SSL_shutdown() to clean up anyway at the last possible moment. Another thing I've changed to luasec is the call to socket_setblocking() right before calling close(2) in socket_destroy() in usocket.c. According to the latest POSIX[0]: Note that the requirement for close() on a socket to block for up to the current linger interval is not conditional on the O_NONBLOCK setting. Which I read to mean that removing O_NONBLOCK on the socket before close doesn't impact the behaviour and only causes noise in system call tracers. I didn't touch the windows bits of this, since I don't do windows. For the prosody side of things I've made the TLS shutdown bits resemble interface:onwritable(), and put it under a combined guard of self._tls and self.conn.shutdown. The self._tls bit is there to prevent getting stuck on this condition, and self.conn.shutdown is there to prevent the code being called by instances where the patched luasec isn't deployed. The destroy() method can be called from various places and is read by me as the "we give up" error path. To accommodate for these unexpected entrypoints I've added a single call to self.conn:shutdown() to prevent the socket being put into blocking mode. I have no expectations that there is any other use here. Same as previous, the self.conn.shutdown check is there to make sure it's not called on unpatched luasec deployments and self._tls is there to make sure we don't call shutdown() on tcp sockets. I wouldn't recommend logging of the conn:shutdown() error inside close(), since a lot of clients simply close the connection before SSL_shutdown() is done.

module:set_global();

local dns = require "prosody.net.adns";
local async = require "prosody.util.async";
local encodings = require "prosody.util.encodings";
local hashes = require "prosody.util.hashes";
local promise = require "prosody.util.promise";
local x509 = require "prosody.util.x509";

local idna_to_ascii = encodings.idna.to_ascii;
local sha256 = hashes.sha256;
local sha512 = hashes.sha512;

local use_dane = module:get_option_boolean("use_dane", nil);
if use_dane == nil then
	module:log("warn", "DANE support incomplete, add use_dane = true in the global section to support outgoing s2s connections");
elseif use_dane == false then
	module:log("debug", "DANE support disabled with use_dane = false, disabling.")
	return
end

local function ensure_secure(r)
	assert(r.secure, "insecure");
	return r;
end

local function ensure_nonempty(r)
	assert(r[1], "empty");
	return r;
end

local function flatten(a)
	local seen = {};
	local ret = {};
	for _, rrset in ipairs(a) do
		for _, rr in ipairs(rrset) do
			if not seen[tostring(rr)] then
				table.insert(ret, rr);
				seen[tostring(rr)] = true;
			end
		end
	end
	return ret;
end

local lazy_tlsa_mt = {
	__index = function(t, i)
		if i == 1 then
			local h = sha256(t[0]);
			t[1] = h;
			return h;
		elseif i == 2 then
			local h = sha512(t[0]);
			t[1] = h;
			return h;
		end
	end;
}
local function lazy_hash(t)
	return setmetatable(t, lazy_tlsa_mt);
end

module:hook("s2s-check-certificate", function(event)
	local session, host, cert = event.session, event.host, event.cert;
	local log = session.log or module._log;

	if not host or not cert or session.direction ~= "incoming" then
		return
	end

	local by_select_match = {
		[0] = lazy_hash {
			-- cert
			[0] = x509.pem2der(cert:pem());

		};
	}
	if cert.pubkey then
		by_select_match[1] = lazy_hash {
			-- spki
			[0] = x509.pem2der(cert:pubkey());
		};
	end

	local resolver = dns.resolver();

	local dns_domain = idna_to_ascii(host);

	local function fetch_tlsa(res)
		local tlsas = {};
		for _, rr in ipairs(res) do
			if rr.srv.target == "." then return {}; end
			table.insert(tlsas, resolver:lookup_promise(("_%d._tcp.%s"):format(rr.srv.port, rr.srv.target), "TLSA"):next(ensure_secure));
		end
		return promise.all(tlsas):next(flatten);
	end

	local ret = async.wait_for(resolver:lookup_promise("_xmpp-server." .. dns_domain, "TLSA"):next(ensure_secure):next(ensure_nonempty):catch(function()
		return promise.all({
			resolver:lookup_promise("_xmpps-server._tcp." .. dns_domain, "SRV"):next(ensure_secure):next(fetch_tlsa);
			resolver:lookup_promise("_xmpp-server._tcp." .. dns_domain, "SRV"):next(ensure_secure):next(fetch_tlsa);
		}):next(flatten);
	end));

	if not ret then
		return
	end

	local found_supported = false;
	for _, rr in ipairs(ret) do
		if rr.tlsa.use == 3 and by_select_match[rr.tlsa.select] and rr.tlsa.match <= 2 then
			found_supported = true;
			if rr.tlsa.data == by_select_match[rr.tlsa.select][rr.tlsa.match] then
				module:log("debug", "%s matches", rr)
				session.cert_chain_status = "valid";
				session.cert_identity_status = "valid";
				return true;
			end
		else
			log("debug", "Unsupported DANE TLSA record: %s", rr);
		end
	end

	if found_supported then
		session.cert_chain_status = "invalid";
		session.cert_identity_status = nil;
		return true;
	end

end, 800);