Merge branch 'mptcp-more-miscellaneous-mptcp-fixes'

Mat Martineau says:

====================
mptcp: More miscellaneous MPTCP fixes

Here's another batch of fixup and enhancement patches that we have
collected in the MPTCP tree.

Patch 1 removes an unnecessary flag and related code.

Patch 2 fixes a bug encountered when closing fallback sockets.

Patches 3 and 4 choose a better transmit subflow, with a self test.

Patch 5 adjusts tracking of unaccepted subflows

Patches 6-8 improve handling of long ADD_ADDR options, with a test.

Patch 9 more reliably tracks the MPTCP-level window shared with peers.

Patch 10 sends MPTCP-level acknowledgements more aggressively, so the
peer can send more data without extra delay.
====================

Link: https://lore.kernel.org/r/20201119194603.103158-1-mathew.j.martineau@linux.intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/mptcp.h

@@ -88,7 +88,8 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       struct mptcp_out_options *opts);
 void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+			 struct mptcp_out_options *opts);
 
 /* move the skb extension owership, with the assumption that 'to' is
  * newly allocated

net/ipv4/tcp_output.c

@@ -445,11 +445,12 @@ struct tcp_out_options {
 	struct mptcp_out_options mptcp;
 };
 
-static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp,
+				struct tcp_out_options *opts)
 {
 #if IS_ENABLED(CONFIG_MPTCP)
 	if (unlikely(OPTION_MPTCP & opts->options))
-		mptcp_write_options(ptr, &opts->mptcp);
+		mptcp_write_options(ptr, tp, &opts->mptcp);
 #endif
 }
 
@@ -701,7 +702,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 	smc_options_write(ptr, &options);
 
-	mptcp_options_write(ptr, opts);
+	mptcp_options_write(ptr, tp, opts);
 }
 
 static void smc_set_option(const struct tcp_sock *tp,
@@ -1346,7 +1347,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
-	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	skb_shinfo(skb)->gso_type = sk->sk_gso_type;
 	if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) {
 		th->window      = htons(tcp_select_window(sk));
@@ -1357,6 +1357,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		 */
 		th->window	= htons(min(tp->rcv_wnd, 65535U));
 	}
+
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+
 #ifdef CONFIG_TCP_MD5SIG
 	/* Calculate the MD5 hash, as we have all we need now */
 	if (md5) {

net/mptcp/options.c

@@ -242,7 +242,9 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 		mp_opt->add_addr = 1;
 		mp_opt->addr_id = *ptr++;
-		pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
+		pr_debug("ADD_ADDR%s: id=%d, echo=%d",
+			 (mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
+			 mp_opt->addr_id, mp_opt->echo);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
 			memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
 			ptr += 4;
@@ -528,6 +530,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		opts->ext_copy.ack64 = 0;
 	}
 	opts->ext_copy.use_ack = 1;
+	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -573,17 +576,27 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 }
 #endif
 
-static bool mptcp_established_options_add_addr(struct sock *sk,
+static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
 					       unsigned int *size,
 					       unsigned int remaining,
 					       struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	bool drop_other_suboptions = false;
+	unsigned int opt_size = *size;
 	struct mptcp_addr_info saddr;
 	bool echo;
 	int len;
 
+	if (mptcp_pm_should_add_signal_ipv6(msk) &&
+	    skb && skb_is_tcp_pure_ack(skb)) {
+		pr_debug("drop other suboptions");
+		opts->suboptions = 0;
+		remaining += opt_size;
+		drop_other_suboptions = true;
+	}
+
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo)))
 		return false;
@@ -593,6 +606,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk,
 		return false;
 
 	*size = len;
+	if (drop_other_suboptions)
+		*size -= opt_size;
 	opts->addr_id = saddr.id;
 	if (saddr.family == AF_INET) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
@@ -678,7 +693,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	*size += opt_size;
 	remaining -= opt_size;
-	if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) {
+	if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
 		*size += opt_size;
 		remaining -= opt_size;
 		ret = true;
@@ -759,6 +774,11 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		goto fully_established;
 	}
 
+	if (mp_opt->add_addr) {
+		WRITE_ONCE(msk->fully_established, true);
+		return true;
+	}
+
 	/* If the first established packet does not contain MP_CAPABLE + data
 	 * then fallback to TCP. Fallback scenarios requires a reset for
 	 * MP_JOIN subflows.
@@ -991,7 +1011,24 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+static void mptcp_set_rwin(const struct tcp_sock *tp)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	const struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk;
+	u64 ack_seq;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	msk = mptcp_sk(subflow->conn);
+
+	ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+
+	if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+}
+
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+			 struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
 	     OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
@@ -1148,4 +1185,7 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 		}
 	}
+
+	if (tp)
+		mptcp_set_rwin(tp);
 }

net/mptcp/pm.c

@@ -16,11 +16,17 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo)
 {
+	u8 add_addr = READ_ONCE(msk->pm.add_addr_signal);
+
 	pr_debug("msk=%p, local_id=%d", msk, addr->id);
 
 	msk->pm.local = *addr;
-	WRITE_ONCE(msk->pm.add_addr_echo, echo);
-	WRITE_ONCE(msk->pm.add_addr_signal, true);
+	add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL);
+	if (echo)
+		add_addr |= BIT(MPTCP_ADD_ADDR_ECHO);
+	if (addr->family == AF_INET6)
+		add_addr |= BIT(MPTCP_ADD_ADDR_IPV6);
+	WRITE_ONCE(msk->pm.add_addr_signal, add_addr);
 	return 0;
 }
 
@@ -149,14 +155,24 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 
 	spin_lock_bh(&pm->lock);
 
-	if (!READ_ONCE(pm->accept_addr))
+	if (!READ_ONCE(pm->accept_addr)) {
 		mptcp_pm_announce_addr(msk, addr, true);
-	else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
+		mptcp_pm_add_addr_send_ack(msk);
+	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->remote = *addr;
+	}
 
 	spin_unlock_bh(&pm->lock);
 }
 
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	if (!mptcp_pm_should_add_signal_ipv6(msk))
+		return;
+
+	mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK);
+}
+
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
@@ -182,13 +198,13 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 	if (!mptcp_pm_should_add_signal(msk))
 		goto out_unlock;
 
-	*echo = READ_ONCE(msk->pm.add_addr_echo);
+	*echo = mptcp_pm_should_add_signal_echo(msk);
 
 	if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo))
 		goto out_unlock;
 
 	*saddr = msk->pm.local;
-	WRITE_ONCE(msk->pm.add_addr_signal, false);
+	WRITE_ONCE(msk->pm.add_addr_signal, 0);
 	ret = true;
 
 out_unlock:
@@ -232,11 +248,10 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 	msk->pm.subflows = 0;
 	msk->pm.rm_id = 0;
 	WRITE_ONCE(msk->pm.work_pending, false);
-	WRITE_ONCE(msk->pm.add_addr_signal, false);
+	WRITE_ONCE(msk->pm.add_addr_signal, 0);
 	WRITE_ONCE(msk->pm.rm_addr_signal, false);
 	WRITE_ONCE(msk->pm.accept_addr, false);
 	WRITE_ONCE(msk->pm.accept_subflow, false);
-	WRITE_ONCE(msk->pm.add_addr_echo, false);
 	msk->pm.status = 0;
 
 	spin_lock_init(&msk->pm.lock);

net/mptcp/pm_netlink.c

@@ -228,6 +228,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 	if (!mptcp_pm_should_add_signal(msk)) {
 		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
 		mptcp_pm_announce_addr(msk, &entry->addr, false);
+		mptcp_pm_add_addr_send_ack(msk);
 		entry->retrans_times++;
 	}
 
@@ -328,6 +329,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 			if (mptcp_pm_alloc_anno_list(msk, local)) {
 				msk->pm.add_addr_signaled++;
 				mptcp_pm_announce_addr(msk, &local->addr, false);
+				mptcp_pm_nl_add_addr_send_ack(msk);
 			}
 		} else {
 			/* pick failed, avoid fourther attempts later */
@@ -398,6 +400,33 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	spin_lock_bh(&msk->pm.lock);
 
 	mptcp_pm_announce_addr(msk, &remote, true);
+	mptcp_pm_nl_add_addr_send_ack(msk);
+}
+
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	if (!mptcp_pm_should_add_signal_ipv6(msk))
+		return;
+
+	__mptcp_flush_join_list(msk);
+	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
+	if (subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u8 add_addr;
+
+		spin_unlock_bh(&msk->pm.lock);
+		pr_debug("send ack for add_addr6");
+		lock_sock(ssk);
+		tcp_send_ack(ssk);
+		release_sock(ssk);
+		spin_lock_bh(&msk->pm.lock);
+
+		add_addr = READ_ONCE(msk->pm.add_addr_signal);
+		add_addr &= ~BIT(MPTCP_ADD_ADDR_IPV6);
+		WRITE_ONCE(msk->pm.add_addr_signal, add_addr);
+	}
 }
 
 void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)

net/mptcp/protocol.c

@@ -168,19 +168,19 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	struct rb_node **p, *parent;
 	u64 seq, end_seq, max_seq;
 	struct sk_buff *skb1;
-	int space;
 
 	seq = MPTCP_SKB_CB(skb)->map_seq;
 	end_seq = MPTCP_SKB_CB(skb)->end_seq;
-	space = tcp_space(sk);
-	max_seq = space > 0 ? space + msk->ack_seq : msk->ack_seq;
+	max_seq = READ_ONCE(msk->rcv_wnd_sent);
 
 	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
 		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
-	if (after64(seq, max_seq)) {
+	if (after64(end_seq, max_seq)) {
 		/* out of window */
 		mptcp_drop(sk, skb);
-		pr_debug("oow by %ld", (unsigned long)seq - (unsigned long)max_seq);
+		pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
+			 (unsigned long long)end_seq - (unsigned long)max_seq,
+			 (unsigned long long)msk->rcv_wnd_sent);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
 		return;
 	}
@@ -407,16 +407,42 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
 	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
 }
 
-static void mptcp_send_ack(struct mptcp_sock *msk)
+static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+	if (subflow->request_join && !subflow->fully_established)
+		return false;
+
+	/* only send if our side has not closed yet */
+	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
+static void mptcp_send_ack(struct mptcp_sock *msk, bool force)
 {
 	struct mptcp_subflow_context *subflow;
+	struct sock *pick = NULL;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
-		lock_sock(ssk);
-		tcp_send_ack(ssk);
-		release_sock(ssk);
+		if (force) {
+			lock_sock(ssk);
+			tcp_send_ack(ssk);
+			release_sock(ssk);
+			continue;
+		}
+
+		/* if the hintes ssk is still active, use it */
+		pick = ssk;
+		if (ssk == msk->ack_hint)
+			break;
+	}
+	if (!force && pick) {
+		lock_sock(pick);
+		tcp_cleanup_rbuf(pick, 1);
+		release_sock(pick);
 	}
 }
 
@@ -468,7 +494,7 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 		ret = true;
 		mptcp_set_timeout(sk, NULL);
-		mptcp_send_ack(msk);
+		mptcp_send_ack(msk, true);
 		mptcp_close_wake_up(sk);
 	}
 	return ret;
@@ -483,7 +509,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	unsigned int moved = 0;
 	bool more_data_avail;
 	struct tcp_sock *tp;
-	u32 old_copied_seq;
 	bool done = false;
 	int sk_rbuf;
 
@@ -500,7 +525,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 
 	pr_debug("msk=%p ssk=%p", msk, ssk);
 	tp = tcp_sk(ssk);
-	old_copied_seq = tp->copied_seq;
 	do {
 		u32 map_remaining, offset;
 		u32 seq = tp->copied_seq;
@@ -564,11 +588,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 			break;
 		}
 	} while (more_data_avail);
+	msk->ack_hint = ssk;
 
 	*bytes += moved;
-	if (tp->copied_seq != old_copied_seq)
-		tcp_cleanup_rbuf(ssk, 1);
-
 	return done;
 }
 
@@ -672,25 +694,14 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
 		goto wake;
 
-	if (move_skbs_to_msk(msk, ssk))
-		goto wake;
-
-	/* mptcp socket is owned, release_cb should retry */
-	if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
-			      &sk->sk_tsq_flags)) {
-		sock_hold(sk);
+	move_skbs_to_msk(msk, ssk);
 
-		/* need to try again, its possible release_cb() has already
-		 * been called after the test_and_set_bit() above.
-		 */
-		move_skbs_to_msk(msk, ssk);
-	}
 wake:
 	if (wake)
 		sk->sk_data_ready(sk);
 }
 
-static void __mptcp_flush_join_list(struct mptcp_sock *msk)
+void __mptcp_flush_join_list(struct mptcp_sock *msk)
 {
 	if (likely(list_empty(&msk->join_list)))
 		return;
@@ -777,7 +788,9 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		inet_sk_state_store(sk, TCP_CLOSE_WAIT);
 		break;
 	case TCP_FIN_WAIT1:
-		/* fallback sockets skip TCP_CLOSING - TCP will take care */
+		inet_sk_state_store(sk, TCP_CLOSING);
+		break;
+	case TCP_FIN_WAIT2:
 		inet_sk_state_store(sk, TCP_CLOSE);
 		break;
 	default:
@@ -1093,18 +1106,6 @@ static void mptcp_nospace(struct mptcp_sock *msk)
 	mptcp_clean_una((struct sock *)msk);
 }
 
-static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
-{
-	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
-	if (subflow->request_join && !subflow->fully_established)
-		return false;
-
-	/* only send if our side has not closed yet */
-	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
-}
-
 #define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
 					 sizeof(struct tcphdr) - \
 					 MAX_TCP_OPTION_SPACE - \
@@ -1532,7 +1533,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	msk->rcvq_space.time = mstamp;
 }
 
-static bool __mptcp_move_skbs(struct mptcp_sock *msk)
+static bool __mptcp_move_skbs(struct mptcp_sock *msk, unsigned int rcv)
 {
 	unsigned int moved = 0;
 	bool done;
@@ -1551,12 +1552,16 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
 
 		slowpath = lock_sock_fast(ssk);
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+		if (moved && rcv) {
+			WRITE_ONCE(msk->rmem_pending, min(rcv, moved));
+			tcp_cleanup_rbuf(ssk, 1);
+			WRITE_ONCE(msk->rmem_pending, 0);
+		}
 		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
 	if (mptcp_ofo_queue(msk) || moved > 0) {
-		if (!mptcp_check_data_fin((struct sock *)msk))
-			mptcp_send_ack(msk);
+		mptcp_check_data_fin((struct sock *)msk);
 		return true;
 	}
 	return false;
@@ -1580,8 +1585,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 	__mptcp_flush_join_list(msk);
 
-	while (len > (size_t)copied) {
-		int bytes_read;
+	for (;;) {
+		int bytes_read, old_space;
 
 		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied);
 		if (unlikely(bytes_read < 0)) {
@@ -1593,9 +1598,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		copied += bytes_read;
 
 		if (skb_queue_empty(&sk->sk_receive_queue) &&
-		    __mptcp_move_skbs(msk))
+		    __mptcp_move_skbs(msk, len - copied))
 			continue;
 
+		/* be sure to advertise window change */
+		old_space = READ_ONCE(msk->old_wspace);
+		if ((tcp_space(sk) - old_space) >= old_space)
+			mptcp_send_ack(msk, false);
+
 		/* only the master socket status is relevant here. The exit
 		 * conditions mirror closely tcp_recvmsg()
 		 */
@@ -1648,7 +1658,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		/* .. race-breaker: ssk might have gotten new data
 		 * after last __mptcp_move_skbs() returned false.
 		 */
-		if (unlikely(__mptcp_move_skbs(msk)))
+		if (unlikely(__mptcp_move_skbs(msk, 0)))
 			set_bit(MPTCP_DATA_READY, &msk->flags);
 	} else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) {
 		/* data to read but mptcp_wait_data() cleared DATA_READY */
@@ -1724,8 +1734,11 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 			continue;
 
 		/* still data outstanding at TCP level?  Don't retransmit. */
-		if (!tcp_write_queue_empty(ssk))
+		if (!tcp_write_queue_empty(ssk)) {
+			if (inet_csk(ssk)->icsk_ca_state >= TCP_CA_Loss)
+				continue;
 			return NULL;
+		}
 
 		if (subflow->backup) {
 			if (!backup)
@@ -1803,6 +1816,10 @@ static void pm_work(struct mptcp_sock *msk)
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
 		mptcp_pm_nl_add_addr_received(msk);
 	}
+	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
+		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
+		mptcp_pm_nl_add_addr_send_ack(msk);
+	}
 	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
 		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
 		mptcp_pm_nl_rm_addr_received(msk);
@@ -1862,7 +1879,6 @@ static void mptcp_worker(struct work_struct *work)
 	int state, ret;
 
 	lock_sock(sk);
-	set_bit(MPTCP_WORKER_RUNNING, &msk->flags);
 	state = sk->sk_state;
 	if (unlikely(state == TCP_CLOSE))
 		goto unlock;
@@ -1873,7 +1889,6 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
 		__mptcp_close_subflow(msk);
 
-	__mptcp_move_skbs(msk);
 	if (mptcp_send_head(sk))
 		mptcp_push_pending(sk, 0);
 
@@ -1940,7 +1955,6 @@ static void mptcp_worker(struct work_struct *work)
 		mptcp_reset_timer(sk);
 
 unlock:
-	clear_bit(MPTCP_WORKER_RUNNING, &msk->flags);
 	release_sock(sk);
 	sock_put(sk);
 }
@@ -1958,6 +1972,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->out_of_order_queue = RB_ROOT;
 	msk->first_pending = NULL;
 
+	msk->ack_hint = NULL;
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 
@@ -2011,11 +2026,7 @@ static void mptcp_cancel_work(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	/* if called by the work itself, do not try to cancel the work, or
-	 * we will hang.
-	 */
-	if (!test_bit(MPTCP_WORKER_RUNNING, &msk->flags) &&
-	    cancel_work_sync(&msk->work))
+	if (cancel_work_sync(&msk->work))
 		__sock_put(sk);
 }
 
@@ -2092,10 +2103,16 @@ static void __mptcp_check_send_data_fin(struct sock *sk)
 
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 
-	/* fallback socket will not get data_fin/ack, can move to close now */
-	if (__mptcp_check_fallback(msk) && sk->sk_state == TCP_LAST_ACK) {
-		inet_sk_state_store(sk, TCP_CLOSE);
-		mptcp_close_wake_up(sk);
+	/* fallback socket will not get data_fin/ack, can move to the next
+	 * state now
+	 */
+	if (__mptcp_check_fallback(msk)) {
+		if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
+			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_close_wake_up(sk);
+		} else if (sk->sk_state == TCP_FIN_WAIT1) {
+			inet_sk_state_store(sk, TCP_FIN_WAIT2);
+		}
 	}
 
 	__mptcp_flush_join_list(msk);
@@ -2286,6 +2303,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		WRITE_ONCE(msk->ack_seq, ack_seq);
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	}
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
@@ -2338,7 +2356,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *new_mptcp_sock;
-		struct sock *ssk = newsk;
 
 		subflow = mptcp_subflow_ctx(newsk);
 		new_mptcp_sock = subflow->conn;
@@ -2353,22 +2370,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 
 		/* acquire the 2nd reference for the owning socket */
 		sock_hold(new_mptcp_sock);
-
-		local_bh_disable();
-		bh_lock_sock(new_mptcp_sock);
-		msk = mptcp_sk(new_mptcp_sock);
-		msk->first = newsk;
-
 		newsk = new_mptcp_sock;
-		mptcp_copy_inaddrs(newsk, ssk);
-		list_add(&subflow->node, &msk->conn_list);
-		sock_hold(ssk);
-
-		mptcp_rcv_space_init(msk, ssk);
-		bh_unlock_sock(new_mptcp_sock);
-
-		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-		local_bh_enable();
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
 		MPTCP_INC_STATS(sock_net(sk),
 				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
@@ -2505,8 +2508,7 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	return -EOPNOTSUPP;
 }
 
-#define MPTCP_DEFERRED_ALL (TCPF_DELACK_TIMER_DEFERRED | \
-			    TCPF_WRITE_TIMER_DEFERRED)
+#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)
 
 /* this is very alike tcp_release_cb() but we must handle differently a
  * different set of events
@@ -2524,16 +2526,6 @@ static void mptcp_release_cb(struct sock *sk)
 
 	sock_release_ownership(sk);
 
-	if (flags & TCPF_DELACK_TIMER_DEFERRED) {
-		struct mptcp_sock *msk = mptcp_sk(sk);
-		struct sock *ssk;
-
-		ssk = mptcp_subflow_recv_lookup(msk);
-		if (!ssk || sk->sk_state == TCP_CLOSE ||
-		    !schedule_work(&msk->work))
-			__sock_put(sk);
-	}
-
 	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
 		mptcp_retransmit_handler(sk);
 		__sock_put(sk);
@@ -2593,6 +2585,7 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->ack_seq, ack_seq);
+	WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	WRITE_ONCE(msk->can_ack, 1);
 	atomic64_set(&msk->snd_una, msk->write_seq);
 
@@ -2819,6 +2812,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
 		struct mptcp_sock *msk = mptcp_sk(newsock->sk);
 		struct mptcp_subflow_context *subflow;
+		struct sock *newsk = newsock->sk;
+		bool slowpath;
+
+		slowpath = lock_sock_fast(newsk);
+		mptcp_copy_inaddrs(newsk, msk->first);
+		mptcp_rcv_space_init(msk, msk->first);
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
@@ -2830,6 +2829,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+		unlock_sock_fast(newsk, slowpath);
 	}
 
 	if (inet_csk_listen_poll(ssock->sk))

net/mptcp/protocol.h

@@ -91,7 +91,6 @@
 #define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
 #define MPTCP_WORK_CLOSE_SUBFLOW 5
-#define MPTCP_WORKER_RUNNING	6
 
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
@@ -161,11 +160,18 @@ struct mptcp_addr_info {
 
 enum mptcp_pm_status {
 	MPTCP_PM_ADD_ADDR_RECEIVED,
+	MPTCP_PM_ADD_ADDR_SEND_ACK,
 	MPTCP_PM_RM_ADDR_RECEIVED,
 	MPTCP_PM_ESTABLISHED,
 	MPTCP_PM_SUBFLOW_ESTABLISHED,
 };
 
+enum mptcp_add_addr_status {
+	MPTCP_ADD_ADDR_SIGNAL,
+	MPTCP_ADD_ADDR_ECHO,
+	MPTCP_ADD_ADDR_IPV6,
+};
+
 struct mptcp_pm_data {
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
@@ -173,13 +179,12 @@ struct mptcp_pm_data {
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
-	bool		add_addr_signal;
+	u8		add_addr_signal;
 	bool		rm_addr_signal;
 	bool		server_side;
 	bool		work_pending;
 	bool		accept_addr;
 	bool		accept_subflow;
-	bool		add_addr_echo;
 	u8		add_addr_signaled;
 	u8		add_addr_accepted;
 	u8		local_addr_used;
@@ -211,13 +216,16 @@ struct mptcp_sock {
 	u64		write_seq;
 	u64		snd_nxt;
 	u64		ack_seq;
+	u64		rcv_wnd_sent;
 	u64		rcv_data_fin_seq;
 	struct sock	*last_snd;
 	int		snd_burst;
+	int		old_wspace;
 	atomic64_t	snd_una;
 	atomic64_t	wnd_end;
 	unsigned long	timer_ival;
 	u32		token;
+	int		rmem_pending;
 	unsigned long	flags;
 	bool		can_ack;
 	bool		fully_established;
@@ -225,6 +233,7 @@ struct mptcp_sock {
 	bool		snd_data_fin_enable;
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	spinlock_t	join_list_lock;
+	struct sock	*ack_hint;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -252,6 +261,11 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
 	return (struct mptcp_sock *)sk;
 }
 
+static inline int __mptcp_space(const struct sock *sk)
+{
+	return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
+}
+
 static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
 {
 	const struct mptcp_sock *msk = mptcp_sk(sk);
@@ -404,6 +418,15 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
 	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
 }
 
+static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
+					     struct mptcp_subflow_context *subflow)
+{
+	sock_hold(mptcp_subflow_tcp_sock(subflow));
+	spin_lock_bh(&msk->join_list_lock);
+	list_add_tail(&subflow->node, &msk->join_list);
+	spin_unlock_bh(&msk->join_list_lock);
+}
+
 int mptcp_is_enabled(struct net *net);
 unsigned int mptcp_get_add_addr_timeout(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
@@ -454,6 +477,7 @@ bool mptcp_schedule_work(struct sock *sk);
 void mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
+void __mptcp_flush_join_list(struct mptcp_sock *msk);
 static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->snd_data_fin_enable) &&
@@ -494,6 +518,7 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk,
 void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 struct mptcp_pm_add_entry *
@@ -508,7 +533,17 @@ int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.add_addr_signal);
+	return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
+}
+
+static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
+}
+
+static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.add_addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
 }
 
 static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
@@ -535,6 +570,7 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
 void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);

net/mptcp/subflow.c

@@ -578,6 +578,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			 */
 			inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED);
 
+			/* link the newly created socket to the msk */
+			mptcp_add_pending_subflow(mptcp_sk(new_msk), ctx);
+			WRITE_ONCE(mptcp_sk(new_msk)->first, child);
+
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
@@ -846,8 +850,6 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
 		subflow->map_valid = 0;
-	if (incr)
-		tcp_cleanup_rbuf(ssk, incr);
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -969,7 +971,7 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
 	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	const struct sock *sk = subflow->conn;
 
-	*space = tcp_space(sk);
+	*space = __mptcp_space(sk);
 	*full_space = tcp_full_space(sk);
 }
 
@@ -1124,11 +1126,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	if (err && err != -EINPROGRESS)
 		goto failed;
 
-	sock_hold(ssk);
-	spin_lock_bh(&msk->join_list_lock);
-	list_add_tail(&subflow->node, &msk->join_list);
-	spin_unlock_bh(&msk->join_list_lock);
-
+	mptcp_add_pending_subflow(msk, subflow);
 	return err;
 
 failed:

tools/testing/selftests/net/mptcp/mptcp_join.sh

@@ -5,6 +5,7 @@ ret=0
 sin=""
 sout=""
 cin=""
+cinsent=""
 cout=""
 ksft_skip=4
 timeout=30
@@ -81,7 +82,7 @@ cleanup_partial()
 cleanup()
 {
 	rm -f "$cin" "$cout"
-	rm -f "$sin" "$sout"
+	rm -f "$sin" "$sout" "$cinsent"
 	cleanup_partial
 }
 
@@ -144,6 +145,13 @@ if [ $? -ne 0 ];then
 	exit $ksft_skip
 fi
 
+print_file_err()
+{
+	ls -l "$1" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "$1"
+}
+
 check_transfer()
 {
 	in=$1
@@ -155,6 +163,7 @@ check_transfer()
 		echo "[ FAIL ] $what does not match (in, out):"
 		print_file_err "$in"
 		print_file_err "$out"
+		ret=1
 
 		return 1
 	fi
@@ -175,6 +184,23 @@ do_ping()
 	fi
 }
 
+link_failure()
+{
+	ns="$1"
+
+	l=$((RANDOM%4))
+	l=$((l+1))
+
+	veth="ns1eth$l"
+	ip -net "$ns" link set "$veth" down
+}
+
+# $1: IP address
+is_v6()
+{
+	[ -z "${1##*:*}" ]
+}
+
 do_transfer()
 {
 	listener_ns="$1"
@@ -182,9 +208,10 @@ do_transfer()
 	cl_proto="$3"
 	srv_proto="$4"
 	connect_addr="$5"
-	rm_nr_ns1="$6"
-	rm_nr_ns2="$7"
-	speed="$8"
+	test_link_fail="$6"
+	rm_nr_ns1="$7"
+	rm_nr_ns2="$8"
+	speed="$9"
 
 	port=$((10000+$TEST_COUNT))
 	TEST_COUNT=$((TEST_COUNT+1))
@@ -215,12 +242,25 @@ do_transfer()
 		mptcp_connect="./mptcp_connect -r"
 	fi
 
-	ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port \
+		-s ${srv_proto} ${local_addr} < "$sin" > "$sout" &
 	spid=$!
 
 	sleep 1
 
-	ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+	if [ "$test_link_fail" -eq 0 ];then
+		ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+	else
+		( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | tee "$cinsent" | \
+		ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr > "$cout" &
+	fi
 	cpid=$!
 
 	if [ $rm_nr_ns1 -gt 0 ]; then
@@ -265,12 +305,17 @@ do_transfer()
 		ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
 
 		cat "$capout"
+		ret=1
 		return 1
 	fi
 
 	check_transfer $sin $cout "file received by client"
 	retc=$?
-	check_transfer $cin $sout "file received by server"
+	if [ "$test_link_fail" -eq 0 ];then
+		check_transfer $cin $sout "file received by server"
+	else
+		check_transfer $cinsent $sout "file received by server"
+	fi
 	rets=$?
 
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
@@ -286,13 +331,12 @@ make_file()
 {
 	name=$1
 	who=$2
+	size=$3
 
-	SIZE=1
-
-	dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
 	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
 
-	echo "Created $name (size $SIZE KB) containing data sent by $who"
+	echo "Created $name (size $size KB) containing data sent by $who"
 }
 
 run_tests()
@@ -300,14 +344,32 @@ run_tests()
 	listener_ns="$1"
 	connector_ns="$2"
 	connect_addr="$3"
-	rm_nr_ns1="${4:-0}"
-	rm_nr_ns2="${5:-0}"
-	speed="${6:-fast}"
+	test_linkfail="${4:-0}"
+	rm_nr_ns1="${5:-0}"
+	rm_nr_ns2="${6:-0}"
+	speed="${7:-fast}"
 	lret=0
+	oldin=""
+
+	if [ "$test_linkfail" -eq 1 ];then
+		size=$((RANDOM%1024))
+		size=$((size+1))
+		size=$((size*128))
+
+		oldin=$(mktemp)
+		cp "$cin" "$oldin"
+		make_file "$cin" "client" $size
+	fi
 
 	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \
-		${rm_nr_ns1} ${rm_nr_ns2} ${speed}
+		${test_linkfail} ${rm_nr_ns1} ${rm_nr_ns2} ${speed}
 	lret=$?
+
+	if [ "$test_linkfail" -eq 1 ];then
+		cp "$oldin" "$cin"
+		rm -f "$oldin"
+	fi
+
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		return
@@ -440,10 +502,11 @@ chk_rm_nr()
 sin=$(mktemp)
 sout=$(mktemp)
 cin=$(mktemp)
+cinsent=$(mktemp)
 cout=$(mktemp)
 init
-make_file "$cin" "client"
-make_file "$sin" "server"
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
 trap cleanup EXIT
 
 run_tests $ns1 $ns2 10.0.1.1
@@ -528,12 +591,23 @@ run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "multiple subflows and signal" 3 3 3
 chk_add_nr 1 1
 
+# accept and use add_addr with additional subflows and link loss
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1 1
+chk_join_nr "multiple flows, signal, link failure" 3 3 3
+chk_add_nr 1 1
+
 # add_addr timeout
 reset_with_add_addr_timeout
 ip netns exec $ns1 ./pm_nl_ctl limits 0 1
 ip netns exec $ns2 ./pm_nl_ctl limits 1 1
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
-run_tests $ns1 $ns2 10.0.1.1 0 0 slow
+run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
 chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1
 chk_add_nr 4 0
 
@@ -542,7 +616,7 @@ reset
 ip netns exec $ns1 ./pm_nl_ctl limits 0 1
 ip netns exec $ns2 ./pm_nl_ctl limits 0 1
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_tests $ns1 $ns2 10.0.1.1 0 1 slow
+run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow
 chk_join_nr "remove single subflow" 1 1 1
 chk_rm_nr 1 1
 
@@ -552,7 +626,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
 ip netns exec $ns2 ./pm_nl_ctl limits 0 2
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_tests $ns1 $ns2 10.0.1.1 0 2 slow
+run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow
 chk_join_nr "remove multiple subflows" 2 2 2
 chk_rm_nr 2 2
 
@@ -561,7 +635,7 @@ reset
 ip netns exec $ns1 ./pm_nl_ctl limits 0 1
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 ip netns exec $ns2 ./pm_nl_ctl limits 1 1
-run_tests $ns1 $ns2 10.0.1.1 1 0 slow
+run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow
 chk_join_nr "remove single address" 1 1 1
 chk_add_nr 1 1
 chk_rm_nr 0 0
@@ -572,7 +646,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 ip netns exec $ns2 ./pm_nl_ctl limits 1 2
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_tests $ns1 $ns2 10.0.1.1 1 1 slow
+run_tests $ns1 $ns2 10.0.1.1 0 1 1 slow
 chk_join_nr "remove subflow and signal" 2 2 2
 chk_add_nr 1 1
 chk_rm_nr 1 1
@@ -584,11 +658,65 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 ip netns exec $ns2 ./pm_nl_ctl limits 1 3
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
-run_tests $ns1 $ns2 10.0.1.1 1 2 slow
+run_tests $ns1 $ns2 10.0.1.1 0 1 2 slow
 chk_join_nr "remove subflows and signal" 3 3 3
 chk_add_nr 1 1
 chk_rm_nr 2 2
 
+# subflow IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single subflow IPv6" 1 1 1
+
+# add_address, unused IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "unused signal address IPv6" 0 0 0
+chk_add_nr 1 1
+
+# signal address IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single address IPv6" 1 1 1
+chk_add_nr 1 1
+
+# add_addr timeout IPv6
+reset_with_add_addr_timeout 6
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1
+chk_add_nr 4 0
+
+# single address IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 0 slow
+chk_join_nr "remove single address IPv6" 1 1 1
+chk_add_nr 1 1
+chk_rm_nr 0 0
+
+# subflow and signal IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 1 slow
+chk_join_nr "remove subflow and signal IPv6" 2 2 2
+chk_add_nr 1 1
+chk_rm_nr 1 1
+
 # single subflow, syncookies
 reset_with_cookies
 ip netns exec $ns1 ./pm_nl_ctl limits 0 1