Merge branch 'mptcp-add_addr-enhancements'

Mat Martineau says:

====================
mptcp: ADD_ADDR enhancements

This patch series from the MPTCP tree contains enhancements and
associated tests for the ADD_ADDR ("add address") MPTCP option. This
option allows already-connected MPTCP peers to share additional IP
addresses with each other, which can then be used to create additional
subflows within those MPTCP connections.

Patches 1 & 2 remove duplicated data in the per-connection path manager
structure.

Patches 3-6 initiate additional subflows when an address is added using
the netlink path manager interface and improve ADD_ADDR signaling
reliability, subject to configured limits. Self tests are also updated.

Patches 7-15 add new support for optional port numbers in ADD_ADDR. This
includes creating an additional in-kernel TCP listening socket for the
requested port number, validating the port number when processing
incoming subflow connections, including the port number in netlink
interfaces, and adding some new MIBs. New self test cases are added for
subflows connecting with alternate port numbers.
====================

Link: https://lore.kernel.org/r/20210201230920.66027-1-mathew.j.martineau@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 65 insertions, 14 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 586156281e5a..280da418d60b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -64,11 +64,23 @@ static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk)
 }
 
 /* validate received token and create truncated hmac and nonce for SYN-ACK */
-static struct mptcp_sock *subflow_token_join_request(struct request_sock *req,
-						     const struct sk_buff *skb)
+static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req)
 {
-	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+	struct mptcp_sock *msk = subflow_req->msk;
 	u8 hmac[SHA256_DIGEST_SIZE];
+
+	get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
+
+	subflow_generate_hmac(msk->local_key, msk->remote_key,
+			      subflow_req->local_nonce,
+			      subflow_req->remote_nonce, hmac);
+
+	subflow_req->thmac = get_unaligned_be64(hmac);
+}
+
+static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
+{
+	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct mptcp_sock *msk;
 	int local_id;
 
@@ -85,13 +97,6 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req,
 	}
 	subflow_req->local_id = local_id;
 
-	get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
-
-	subflow_generate_hmac(msk->local_key, msk->remote_key,
-			      subflow_req->local_nonce,
-			      subflow_req->remote_nonce, hmac);
-
-	subflow_req->thmac = get_unaligned_be64(hmac);
 	return msk;
 }
 
@@ -115,6 +120,11 @@ static int __subflow_init_req(struct request_sock *req, const struct sock *sk_li
 	return 0;
 }
 
+static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk)
+{
+	return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport;
+}
+
 /* Init mptcp request socket.
  *
  * Returns an error code if a JOIN has failed and a TCP reset
@@ -181,12 +191,30 @@ again:
 		subflow_req->remote_id = mp_opt.join_id;
 		subflow_req->token = mp_opt.token;
 		subflow_req->remote_nonce = mp_opt.nonce;
-		subflow_req->msk = subflow_token_join_request(req, skb);
+		subflow_req->msk = subflow_token_join_request(req);
 
 		/* Can't fall back to TCP in this case. */
 		if (!subflow_req->msk)
 			return -EPERM;
 
+		if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
+			pr_debug("syn inet_sport=%d %d",
+				 ntohs(inet_sk(sk_listener)->inet_sport),
+				 ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
+			if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
+				sock_put((struct sock *)subflow_req->msk);
+				mptcp_token_destroy_request(req);
+				tcp_request_sock_ops.destructor(req);
+				subflow_req->msk = NULL;
+				subflow_req->mp_join = 0;
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
+				return -EPERM;
+			}
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
+		}
+
+		subflow_req_create_thmac(subflow_req);
+
 		if (unlikely(req->syncookie)) {
 			if (mptcp_can_accept_new_subflow(subflow_req->msk))
 				subflow_init_req_cookie_join_save(subflow_req, skb);
@@ -329,6 +357,11 @@ void mptcp_subflow_reset(struct sock *ssk)
 	sock_put(sk);
 }
 
+static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk)
+{
+	return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -395,6 +428,13 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 		subflow->mp_join = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+
+		if (subflow_use_different_dport(mptcp_sk(parent), sk)) {
+			pr_debug("synack inet_dport=%d %d",
+				 ntohs(inet_sk(sk)->inet_dport),
+				 ntohs(inet_sk(parent)->inet_dport));
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
+		}
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
 		mptcp_rcv_space_init(mptcp_sk(parent), sk);
@@ -660,6 +700,17 @@ create_child:
 
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
 			tcp_rsk(req)->drop_req = true;
+
+			if (subflow_use_different_sport(owner, sk)) {
+				pr_debug("ack inet_sport=%d %d",
+					 ntohs(inet_sk(sk)->inet_sport),
+					 ntohs(inet_sk((struct sock *)owner)->inet_sport));
+				if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
+					SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
+					goto out;
+				}
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
+			}
 		}
 	}
 
@@ -1084,9 +1135,9 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
 }
 #endif
 
-static void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
-				struct sockaddr_storage *addr,
-				unsigned short family)
+void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
+			 struct sockaddr_storage *addr,
+			 unsigned short family)
 {
 	memset(addr, 0, sizeof(*addr));
 	addr->ss_family = family;