1 files changed, 211 insertions, 129 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1626dd20c68f..15613d691bfe 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -20,6 +20,7 @@
 #include <net/transp_v6.h>
 #endif
 #include <net/mptcp.h>
+
 #include "protocol.h"
 #include "mib.h"
 
@@ -38,7 +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);
@@ -99,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
 		return NULL;
 	}
 	subflow_req->local_id = local_id;
+	subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
 
 	return msk;
 }
@@ -130,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
 	}
 }
 
+static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb)
+{
+	SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT);
+	subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+	return -EPERM;
+}
+
 /* Init mptcp request socket.
  *
  * Returns an error code if a JOIN has failed and a TCP reset
@@ -144,14 +153,16 @@ 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
 	 * TCP option space.
 	 */
-	if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
+	if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) {
+		subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
 		return -EINVAL;
+	}
 #endif
 
 	mptcp_get_options(skb, &mp_opt);
@@ -161,10 +172,17 @@ static int subflow_check_req(struct request_sock *req,
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
+		if (unlikely(listener->pm_listener))
+			return subflow_reset_req_endp(req, skb);
 		if (opt_mp_join)
 			return 0;
 	} else if (opt_mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+		if (mp_opt.backup)
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
+	} else if (unlikely(listener->pm_listener)) {
+		return subflow_reset_req_endp(req, skb);
 	}
 
 	if (opt_mp_capable && listener->request_mptcp) {
@@ -214,11 +232,12 @@ 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)) {
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				return -EPERM;
 			}
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
@@ -227,13 +246,16 @@ again:
 		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);
-			else
+			if (!mptcp_can_accept_new_subflow(subflow_req->msk)) {
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINREJECTED);
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				return -EPERM;
+			}
+
+			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);
 	}
 
@@ -281,10 +303,21 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 }
 EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
 
+static enum sk_rst_reason mptcp_get_rst_reason(const struct sk_buff *skb)
+{
+	const struct mptcp_ext *mpext = mptcp_get_ext(skb);
+
+	if (!mpext)
+		return SK_RST_REASON_NOT_SPECIFIED;
+
+	return sk_rst_convert_mptcp_reason(mpext->reset_reason);
+}
+
 static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
 					      struct sk_buff *skb,
 					      struct flowi *fl,
-					      struct request_sock *req)
+					      struct request_sock *req,
+					      u32 tw_isn)
 {
 	struct dst_entry *dst;
 	int err;
@@ -292,7 +325,7 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
 	tcp_rsk(req)->is_mptcp = 1;
 	subflow_init_req(req, sk);
 
-	dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
+	dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req, tw_isn);
 	if (!dst)
 		return NULL;
 
@@ -302,7 +335,8 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
 
 	dst_release(dst);
 	if (!req->syncookie)
-		tcp_request_sock_ops.send_reset(sk, skb);
+		tcp_request_sock_ops.send_reset(sk, skb,
+						mptcp_get_rst_reason(skb));
 	return NULL;
 }
 
@@ -351,7 +385,8 @@ static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
 					      struct sk_buff *skb,
 					      struct flowi *fl,
-					      struct request_sock *req)
+					      struct request_sock *req,
+					      u32 tw_isn)
 {
 	struct dst_entry *dst;
 	int err;
@@ -359,7 +394,7 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
 	tcp_rsk(req)->is_mptcp = 1;
 	subflow_init_req(req, sk);
 
-	dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
+	dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req, tw_isn);
 	if (!dst)
 		return NULL;
 
@@ -369,7 +404,8 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
 
 	dst_release(dst);
 	if (!req->syncookie)
-		tcp6_request_sock_ops.send_reset(sk, skb);
+		tcp6_request_sock_ops.send_reset(sk, skb,
+						 mptcp_get_rst_reason(skb));
 	return NULL;
 }
 #endif
@@ -405,7 +441,7 @@ void mptcp_subflow_reset(struct sock *ssk)
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
-	tcp_send_active_reset(ssk, GFP_ATOMIC);
+	mptcp_send_active_reset_reason(ssk);
 	tcp_done(ssk);
 	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
 		mptcp_schedule_work(sk);
@@ -503,7 +539,7 @@ 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) {
@@ -522,6 +558,7 @@ 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];
@@ -535,7 +572,7 @@ 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);
 
@@ -557,13 +594,19 @@ 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->backup)
+			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);
 	}
@@ -594,6 +637,8 @@ static int subflow_chk_local_id(struct sock *sk)
 		return err;
 
 	subflow_set_local_id(subflow, err);
+	subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
 	return 0;
 }
 
@@ -626,7 +671,7 @@ 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))
@@ -657,7 +702,7 @@ 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);
@@ -701,17 +746,11 @@ struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *op
 EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc);
 
 /* validate hmac received in third ACK */
-static bool subflow_hmac_valid(const struct request_sock *req,
+static bool subflow_hmac_valid(const struct mptcp_subflow_request_sock *subflow_req,
 			       const struct mptcp_options_received *mp_opt)
 {
-	const struct mptcp_subflow_request_sock *subflow_req;
+	struct mptcp_sock *msk = subflow_req->msk;
 	u8 hmac[SHA256_DIGEST_SIZE];
-	struct mptcp_sock *msk;
-
-	subflow_req = mptcp_subflow_rsk(req);
-	msk = subflow_req->msk;
-	if (!msk)
-		return false;
 
 	subflow_generate_hmac(READ_ONCE(msk->remote_key),
 			      READ_ONCE(msk->local_key),
@@ -756,11 +795,8 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 				       const struct mptcp_options_received *mp_opt)
 {
 	subflow_set_remote_key(msk, subflow, mp_opt);
-	subflow->fully_established = 1;
+	WRITE_ONCE(subflow->fully_established, true);
 	WRITE_ONCE(msk->fully_established, true);
-
-	if (subflow->is_mptfo)
-		__mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -774,10 +810,11 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_subflow_request_sock *subflow_req;
 	struct mptcp_options_received mp_opt;
 	bool fallback, fallback_is_fatal;
+	enum sk_rst_reason reason;
 	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
@@ -808,12 +845,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) ||
-		    !subflow_hmac_valid(req, &mp_opt) ||
-		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
-			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK))
 			fallback = true;
-		}
 	}
 
 create_child:
@@ -863,23 +896,40 @@ create_child:
 				goto dispose_child;
 			}
 
+			if (!subflow_hmac_valid(subflow_req, &mp_opt)) {
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+				goto dispose_child;
+			}
+
+			if (!mptcp_can_accept_new_subflow(owner)) {
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINREJECTED);
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+				goto dispose_child;
+			}
+
 			/* move the msk reference ownership to the subflow */
 			subflow_req->msk = NULL;
 			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)) {
 					SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
+					subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 					goto dispose_child;
 				}
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
 			}
 
-			if (!mptcp_finish_join(child))
+			if (!mptcp_finish_join(child)) {
+				struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(child);
+
+				subflow_add_reset_reason(skb, subflow->reset_reason);
 				goto dispose_child;
+			}
 
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
 			tcp_rsk(req)->drop_req = true;
@@ -887,7 +937,7 @@ create_child:
 	}
 
 	/* check for expected invariant - should never trigger, just help
-	 * catching eariler subtle bugs
+	 * catching earlier subtle bugs
 	 */
 	WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
 		     (!mptcp_subflow_ctx(child) ||
@@ -899,12 +949,15 @@ dispose_child:
 	tcp_rsk(req)->drop_req = true;
 	inet_csk_prepare_for_destroy_sock(child);
 	tcp_done(child);
-	req->rsk_ops->send_reset(sk, skb);
+	reason = mptcp_get_rst_reason(skb);
+	req->rsk_ops->send_reset(sk, skb, reason);
 
 	/* The last child reference will be released by the caller */
 	return child;
 
 fallback:
+	if (fallback)
+		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
 	mptcp_subflow_drop_ctx(child);
 	return child;
 }
@@ -918,12 +971,13 @@ enum mapping_status {
 	MAPPING_EMPTY,
 	MAPPING_DATA_FIN,
 	MAPPING_DUMMY,
-	MAPPING_BAD_CSUM
+	MAPPING_BAD_CSUM,
+	MAPPING_NODSS
 };
 
 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);
 }
 
@@ -933,8 +987,10 @@ static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
 	unsigned int skb_consumed;
 
 	skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq;
-	if (WARN_ON_ONCE(skb_consumed >= skb->len))
+	if (unlikely(skb_consumed >= skb->len)) {
+		DEBUG_NET_WARN_ON_ONCE(1);
 		return true;
+	}
 
 	return skb->len - skb_consumed <= subflow->map_data_len -
 					  mptcp_subflow_get_map_offset(subflow);
@@ -1073,8 +1129,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 			return MAPPING_EMPTY;
 		}
 
+		/* If the required DSS has likely been dropped by a middlebox */
 		if (!subflow->map_valid)
-			return MAPPING_INVALID;
+			return MAPPING_NODSS;
 
 		goto validate_seq;
 	}
@@ -1083,17 +1140,18 @@ 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;
 	}
 
 	if (mpext->data_fin == 1) {
+		u64 data_fin_seq;
+
 		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
@@ -1102,26 +1160,26 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 				 */
 				skb_ext_del(skb, SKB_EXT_MPTCP);
 				return MAPPING_OK;
-			} else {
-				if (updated)
-					mptcp_schedule_work((struct sock *)msk);
-
-				return MAPPING_DATA_FIN;
 			}
-		} else {
-			u64 data_fin_seq = mpext->data_seq + data_len - 1;
 
-			/* If mpext->data_seq is a 32-bit value, data_fin_seq
-			 * must also be limited to 32 bits.
-			 */
-			if (!mpext->dsn64)
-				data_fin_seq &= GENMASK_ULL(31, 0);
+			if (updated)
+				mptcp_schedule_work((struct sock *)msk);
 
-			mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
-			pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
-				 data_fin_seq, mpext->dsn64);
+			return MAPPING_DATA_FIN;
 		}
 
+		data_fin_seq = mpext->data_seq + data_len - 1;
+
+		/* If mpext->data_seq is a 32-bit value, data_fin_seq must also
+		 * be limited to 32 bits.
+		 */
+		if (!mpext->dsn64)
+			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\n",
+			 data_fin_seq, mpext->dsn64);
+
 		/* Adjust for DATA_FIN using 1 byte of sequence space */
 		data_len--;
 	}
@@ -1165,7 +1223,7 @@ 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);
@@ -1190,41 +1248,56 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
-	u32 incr;
+	struct tcp_sock *tp = tcp_sk(ssk);
+	u32 offset, incr, avail_len;
+
+	offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+	if (WARN_ON_ONCE(offset > skb->len))
+		goto out;
 
-	incr = limit >= skb->len ? skb->len + fin : limit;
+	avail_len = skb->len - offset;
+	incr = limit >= avail_len ? avail_len + fin : limit;
 
-	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
-		 subflow->map_subflow_seq);
+	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;
+
+out:
 	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
 		subflow->map_valid = 0;
 }
 
-/* sched mptcp worker to remove the subflow if no more data is pending */
+static bool subflow_is_done(const struct sock *sk)
+{
+	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
+}
+
+/* sched mptcp worker for subflow cleanup 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);
-}
+	if (!skb_queue_empty(&ssk->sk_receive_queue))
+		return;
 
-static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
-{
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		mptcp_schedule_work(sk);
 
-	if (subflow->mp_join)
-		return false;
-	else if (READ_ONCE(msk->csum_enabled))
-		return !subflow->valid_csum_seen;
-	else
-		return !subflow->fully_established;
+	/* when the fallback subflow closes the rx side, trigger a 'dummy'
+	 * ingress data fin, so that the msk state will follow along
+	 */
+	if (__mptcp_check_fallback(msk) && subflow_is_done(ssk) &&
+	    msk->first == ssk &&
+	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
+		mptcp_schedule_work(sk);
 }
 
 static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
@@ -1232,7 +1305,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	unsigned long fail_tout;
 
-	/* greceful failure can happen only on the MPC subflow */
+	/* graceful failure can happen only on the MPC subflow */
 	if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
 		return;
 
@@ -1274,7 +1347,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		status = get_mapping_status(ssk, msk);
 		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
 		if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY ||
-			     status == MAPPING_BAD_CSUM))
+			     status == MAPPING_BAD_CSUM || status == MAPPING_NODSS))
 			goto fallback;
 
 		if (status != MAPPING_OK)
@@ -1289,7 +1362,7 @@ 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);
@@ -1322,19 +1395,21 @@ fallback:
 			return true;
 		}
 
-		if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
+		if (!READ_ONCE(msk->allow_infinite_fallback)) {
 			/* fatal protocol error, close the socket.
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */
 			subflow->reset_transient = 0;
-			subflow->reset_reason = MPTCP_RST_EMPTCP;
+			subflow->reset_reason = status == MAPPING_NODSS ?
+						MPTCP_RST_EMIDDLEBOX :
+						MPTCP_RST_EMPTCP;
 
 reset:
 			WRITE_ONCE(ssk->sk_err, EBADMSG);
 			tcp_set_state(ssk, TCP_CLOSE);
 			while ((skb = skb_peek(&ssk->sk_receive_queue)))
 				sk_eat_skb(ssk, skb);
-			tcp_send_active_reset(ssk, GFP_ATOMIC);
+			mptcp_send_active_reset_reason(ssk);
 			WRITE_ONCE(subflow->data_avail, false);
 			return false;
 		}
@@ -1361,7 +1436,7 @@ 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);
 	}
@@ -1471,7 +1546,7 @@ 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))
@@ -1513,28 +1588,31 @@ 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);
@@ -1542,42 +1620,61 @@ 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);
@@ -1677,10 +1774,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	 * needs it.
 	 * Update ns_tracker to current stack trace and refcounted tracker.
 	 */
-	__netns_tracker_free(net, &sf->sk->ns_tracker, false);
-	sf->sk->sk_net_refcnt = 1;
-	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
-	sock_inuse_add(net, 1);
+	sk_net_refcnt_upgrade(sf->sk);
 	err = tcp_set_ulp(sf->sk, "mptcp");
 	if (err)
 		goto err_free;
@@ -1688,7 +1782,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk);
 	release_sock(sf->sk);
 
-	/* the newly created socket really belongs to the owning MPTCP master
+	/* the newly created socket really belongs to the owning MPTCP
 	 * socket, even if for additional subflows the allocation is performed
 	 * by a kernel workqueue. Adjust inode references, so that the
 	 * procfs/diag interfaces really show this one belonging to the correct
@@ -1699,7 +1793,7 @@ 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);
@@ -1728,7 +1822,7 @@ 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);
@@ -1747,11 +1841,6 @@ static void __subflow_state_change(struct sock *sk)
 	rcu_read_unlock();
 }
 
-static bool subflow_is_done(const struct sock *sk)
-{
-	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
-}
-
 static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -1778,13 +1867,6 @@ static void subflow_state_change(struct sock *sk)
 		subflow_error_report(sk);
 
 	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
-
-	/* when the fallback subflow closes the rx side, trigger a 'dummy'
-	 * ingress data fin, so that the msk state will follow along
-	 */
-	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
-	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
-		mptcp_schedule_work(parent);
 }
 
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
@@ -1879,7 +1961,7 @@ 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;
@@ -1954,7 +2036,6 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	new_ctx->tcp_state_change = old_ctx->tcp_state_change;
 	new_ctx->tcp_error_report = old_ctx->tcp_error_report;
 	new_ctx->rel_write_seq = 1;
-	new_ctx->tcp_sock = newsk;
 
 	if (subflow_req->mp_capable) {
 		/* see comments in subflow_syn_recv_sock(), MPTCP connection
@@ -1971,9 +2052,10 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
-		new_ctx->fully_established = 1;
+		WRITE_ONCE(new_ctx->fully_established, true);
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
+		new_ctx->request_bkup = subflow_req->request_bkup;
 		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;