1 files changed, 70 insertions, 40 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a21c712350c3..1040b3b9696b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -39,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 
-	pr_debug("subflow_req=%p", subflow_req);
+	pr_debug("subflow_req=%p\n", subflow_req);
 
 	if (subflow_req->msk)
 		sock_put((struct sock *)subflow_req->msk);
@@ -146,7 +146,7 @@ static int subflow_check_req(struct request_sock *req,
 	struct mptcp_options_received mp_opt;
 	bool opt_mp_capable, opt_mp_join;
 
-	pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
+	pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -221,7 +221,7 @@ again:
 		}
 
 		if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
-			pr_debug("syn inet_sport=%d %d",
+			pr_debug("syn inet_sport=%d %d\n",
 				 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)) {
@@ -243,7 +243,7 @@ again:
 			subflow_init_req_cookie_join_save(subflow_req, skb);
 		}
 
-		pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
+		pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token,
 			 subflow_req->remote_nonce, subflow_req->msk);
 	}
 
@@ -527,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	subflow->rel_write_seq = 1;
 	subflow->conn_finished = 1;
 	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
-	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
+	pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset);
 
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
@@ -546,6 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->mp_capable = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
+		mptcp_active_enable(parent);
 		mptcp_propagate_state(parent, sk, subflow, &mp_opt);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
@@ -559,7 +560,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
 		WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
-		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
+		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n",
 			 subflow, subflow->thmac, subflow->remote_nonce,
 			 subflow->backup);
 
@@ -585,12 +586,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
 
 		if (subflow_use_different_dport(msk, sk)) {
-			pr_debug("synack inet_dport=%d %d",
+			pr_debug("synack inet_dport=%d %d\n",
 				 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)) {
+		/* It looks like MPTCP is blocked, while TCP is not */
+		if (subflow->mpc_drop)
+			mptcp_active_disable(parent);
 fallback:
 		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
@@ -655,7 +659,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	pr_debug("subflow=%p", subflow);
+	pr_debug("subflow=%p\n", subflow);
 
 	/* Never answer to SYNs sent to broadcast or multicast */
 	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -686,7 +690,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	pr_debug("subflow=%p", subflow);
+	pr_debug("subflow=%p\n", subflow);
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return subflow_v4_conn_request(sk, skb);
@@ -807,7 +811,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_sock *owner;
 	struct sock *child;
 
-	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
+	pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn);
 
 	/* After child creation we must look for MPC even when options
 	 * are not parsed
@@ -898,7 +902,7 @@ create_child:
 			ctx->conn = (struct sock *)owner;
 
 			if (subflow_use_different_sport(owner, sk)) {
-				pr_debug("ack inet_sport=%d %d",
+				pr_debug("ack inet_sport=%d %d\n",
 					 ntohs(inet_sk(sk)->inet_sport),
 					 ntohs(inet_sk((struct sock *)owner)->inet_sport));
 				if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
@@ -961,7 +965,7 @@ enum mapping_status {
 
 static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
 {
-	pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+	pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n",
 		 ssn, subflow->map_subflow_seq, subflow->map_data_len);
 }
 
@@ -1121,7 +1125,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 
 	data_len = mpext->data_len;
 	if (data_len == 0) {
-		pr_debug("infinite mapping received");
+		pr_debug("infinite mapping received\n");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
 		subflow->map_data_len = 0;
 		return MAPPING_INVALID;
@@ -1133,7 +1137,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		if (data_len == 1) {
 			bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
 								 mpext->dsn64);
-			pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
+			pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq);
 			if (subflow->map_valid) {
 				/* A DATA_FIN might arrive in a DSS
 				 * option before the previous mapping
@@ -1159,7 +1163,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 			data_fin_seq &= GENMASK_ULL(31, 0);
 
 		mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
-		pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
+		pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n",
 			 data_fin_seq, mpext->dsn64);
 
 		/* Adjust for DATA_FIN using 1 byte of sequence space */
@@ -1205,7 +1209,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	if (unlikely(subflow->map_csum_reqd != csum_reqd))
 		return MAPPING_INVALID;
 
-	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
+	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
 		 subflow->map_seq, subflow->map_subflow_seq,
 		 subflow->map_data_len, subflow->map_csum_reqd,
 		 subflow->map_data_csum);
@@ -1240,7 +1244,7 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 	avail_len = skb->len - offset;
 	incr = limit >= avail_len ? avail_len + fin : limit;
 
-	pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+	pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len,
 		 offset, subflow->map_subflow_seq);
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
 	tcp_sk(ssk)->copied_seq += incr;
@@ -1255,12 +1259,16 @@ out:
 /* sched mptcp worker to remove the subflow if no more data is pending */
 static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
 {
-	if (likely(ssk->sk_state != TCP_CLOSE))
+	struct sock *sk = (struct sock *)msk;
+
+	if (likely(ssk->sk_state != TCP_CLOSE &&
+		   (ssk->sk_state != TCP_CLOSE_WAIT ||
+		    inet_sk_state_load(sk) != TCP_ESTABLISHED)))
 		return;
 
 	if (skb_queue_empty(&ssk->sk_receive_queue) &&
 	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
-		mptcp_schedule_work((struct sock *)msk);
+		mptcp_schedule_work(sk);
 }
 
 static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
@@ -1337,7 +1345,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
 		old_ack = READ_ONCE(msk->ack_seq);
 		ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
-		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
+		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack,
 			 ack_seq);
 		if (unlikely(before64(ack_seq, old_ack))) {
 			mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
@@ -1409,7 +1417,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
 		subflow->map_valid = 0;
 		WRITE_ONCE(subflow->data_avail, false);
 
-		pr_debug("Done with mapping: seq=%u data_len=%u",
+		pr_debug("Done with mapping: seq=%u data_len=%u\n",
 			 subflow->map_subflow_seq,
 			 subflow->map_data_len);
 	}
@@ -1519,7 +1527,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
 
 	target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
 
-	pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
+	pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n",
 		 subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
 
 	if (likely(icsk->icsk_af_ops == target))
@@ -1561,28 +1569,31 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 #endif
 }
 
-int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 			    const struct mptcp_addr_info *remote)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
+	int local_id = local->addr.id;
 	struct sockaddr_storage addr;
 	int remote_id = remote->id;
-	int local_id = loc->id;
 	int err = -ENOTCONN;
 	struct socket *sf;
 	struct sock *ssk;
 	u32 remote_token;
 	int addrlen;
-	int ifindex;
-	u8 flags;
 
+	/* The userspace PM sent the request too early? */
 	if (!mptcp_is_fully_established(sk))
 		goto err_out;
 
-	err = mptcp_subflow_create_socket(sk, loc->family, &sf);
-	if (err)
+	err = mptcp_subflow_create_socket(sk, local->addr.family, &sf);
+	if (err) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCREATSKERR);
+		pr_debug("msk=%p local=%d remote=%d create sock error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto err_out;
+	}
 
 	ssk = sf->sk;
 	subflow = mptcp_subflow_ctx(ssk);
@@ -1590,42 +1601,61 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 		get_random_bytes(&subflow->local_nonce, sizeof(u32));
 	} while (!subflow->local_nonce);
 
-	if (local_id)
+	/* if 'IPADDRANY', the ID will be set later, after the routing */
+	if (local->addr.family == AF_INET) {
+		if (!local->addr.addr.s_addr)
+			local_id = -1;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	} else if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_any(&local->addr.addr6))
+			local_id = -1;
+#endif
+	}
+
+	if (local_id >= 0)
 		subflow_set_local_id(subflow, local_id);
 
-	mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id,
-					     &flags, &ifindex);
 	subflow->remote_key_valid = 1;
 	subflow->remote_key = READ_ONCE(msk->remote_key);
 	subflow->local_key = READ_ONCE(msk->local_key);
 	subflow->token = msk->token;
-	mptcp_info2sockaddr(loc, &addr, ssk->sk_family);
+	mptcp_info2sockaddr(&local->addr, &addr, ssk->sk_family);
 
 	addrlen = sizeof(struct sockaddr_in);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	if (addr.ss_family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk->sk_bound_dev_if = ifindex;
+	ssk->sk_bound_dev_if = local->ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
-	if (err)
+	if (err) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXBINDERR);
+		pr_debug("msk=%p local=%d remote=%d bind error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto failed;
+	}
 
 	mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
-	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
+	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
 	WRITE_ONCE(subflow->remote_id, remote_id);
 	subflow->request_join = 1;
-	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	subflow->request_bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	subflow->subflow_id = msk->subflow_id++;
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
 
 	sock_hold(ssk);
 	list_add_tail(&subflow->node, &msk->conn_list);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
-	if (err && err != -EINPROGRESS)
+	if (err && err != -EINPROGRESS) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCONNECTERR);
+		pr_debug("msk=%p local=%d remote=%d connect error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto failed_unlink;
+	}
+
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTX);
 
 	/* discard the subflow socket */
 	mptcp_sock_graft(ssk, sk->sk_socket);
@@ -1747,7 +1777,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
 
 	subflow = mptcp_subflow_ctx(sf->sk);
-	pr_debug("subflow=%p", subflow);
+	pr_debug("subflow=%p\n", subflow);
 
 	*new_sock = sf;
 	sock_hold(sk);
@@ -1776,7 +1806,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
 	INIT_LIST_HEAD(&ctx->node);
 	INIT_LIST_HEAD(&ctx->delegated_node);
 
-	pr_debug("subflow=%p", ctx);
+	pr_debug("subflow=%p\n", ctx);
 
 	ctx->tcp_sock = sk;
 	WRITE_ONCE(ctx->local_id, -1);
@@ -1927,7 +1957,7 @@ static int subflow_ulp_init(struct sock *sk)
 		goto out;
 	}
 
-	pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
+	pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family);
 
 	tp->is_mptcp = 1;
 	ctx->icsk_af_ops = icsk->icsk_af_ops;