Merge branch 'mptcp-advertisement-reliability-improvement-and-misc-updates'

Mat Martineau says:

====================
mptcp: Advertisement reliability improvement and misc. updates

Patch 1 adds a helpful debug tracepoint for outgoing MPTCP packets.

Patch 2 is a small "magic number" refactor.

Patches 3 & 4 refactor parts of the mptcp_join.sh selftest. No change in
test coverage.

Patch 5 ensures only advertised address IDs are un-advertised.

Patches 6-8 improve handling of an edge case where endpoint IDs need to
be created on-the-fly when adding subflows. Includes selftest coverage.

Patch 9 adds validation of the fullmesh flag in a MPTCP netlink command,
which was overlooked when this flag was introduced for 5.18.
====================

Link: https://lore.kernel.org/r/20220307204439.65164-1-mathew.j.martineau@linux.intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/trace/events/mptcp.h

@@ -115,6 +115,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		  __entry->csum_reqd)
 );
 
+DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag,
+	TP_PROTO(struct mptcp_ext *mpext),
+	TP_ARGS(mpext));
+
 DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status,
 	TP_PROTO(struct mptcp_ext *mpext),
 	TP_ARGS(mpext));

include/uapi/linux/mptcp.h

@@ -81,6 +81,7 @@ enum {
 #define MPTCP_PM_ADDR_FLAG_SUBFLOW			(1 << 1)
 #define MPTCP_PM_ADDR_FLAG_BACKUP			(1 << 2)
 #define MPTCP_PM_ADDR_FLAG_FULLMESH			(1 << 3)
+#define MPTCP_PM_ADDR_FLAG_IMPLICIT			(1 << 4)
 
 enum {
 	MPTCP_PM_CMD_UNSPEC,

net/mptcp/pm_netlink.c

@@ -83,16 +83,6 @@ static bool addresses_equal(const struct mptcp_addr_info *a,
 	return a->port == b->port;
 }
 
-static bool address_zero(const struct mptcp_addr_info *addr)
-{
-	struct mptcp_addr_info zero;
-
-	memset(&zero, 0, sizeof(zero));
-	zero.family = addr->family;
-
-	return addresses_equal(addr, &zero, true);
-}
-
 static void local_address(const struct sock_common *skc,
 			  struct mptcp_addr_info *addr)
 {
@@ -877,10 +867,18 @@ static bool address_use_port(struct mptcp_pm_addr_entry *entry)
 		MPTCP_PM_ADDR_FLAG_SIGNAL;
 }
 
+/* caller must ensure the RCU grace period is already elapsed */
+static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
+{
+	if (entry->lsk)
+		sock_release(entry->lsk);
+	kfree(entry);
+}
+
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 					     struct mptcp_pm_addr_entry *entry)
 {
-	struct mptcp_pm_addr_entry *cur;
+	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
 	int ret = -EINVAL;
 
@@ -901,8 +899,22 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 	list_for_each_entry(cur, &pernet->local_addr_list, list) {
 		if (addresses_equal(&cur->addr, &entry->addr,
 				    address_use_port(entry) &&
-				    address_use_port(cur)))
-			goto out;
+				    address_use_port(cur))) {
+			/* allow replacing the exiting endpoint only if such
+			 * endpoint is an implicit one and the user-space
+			 * did not provide an endpoint id
+			 */
+			if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT))
+				goto out;
+			if (entry->addr.id)
+				goto out;
+
+			pernet->addrs--;
+			entry->addr.id = cur->addr.id;
+			list_del_rcu(&cur->list);
+			del_entry = cur;
+			break;
+		}
 	}
 
 	if (!entry->addr.id) {
@@ -938,6 +950,12 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 
 out:
 	spin_unlock_bh(&pernet->lock);
+
+	/* just replaced an existing entry, free it */
+	if (del_entry) {
+		synchronize_rcu();
+		__mptcp_pm_release_addr_entry(del_entry);
+	}
 	return ret;
 }
 
@@ -1011,9 +1029,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	if (addresses_equal(&msk_local, &skc_local, false))
 		return 0;
 
-	if (address_zero(&skc_local))
-		return 0;
-
 	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 
 	rcu_read_lock();
@@ -1036,7 +1051,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	entry->addr.id = 0;
 	entry->addr.port = 0;
 	entry->ifindex = 0;
-	entry->flags = 0;
+	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
 	if (ret < 0)
@@ -1249,6 +1264,17 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
+	if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
+	    addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
+		GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh");
+		return -EINVAL;
+	}
+
+	if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
+		GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint");
+		return -EINVAL;
+	}
+
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "can't allocate addr");
@@ -1333,11 +1359,12 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
 }
 
 static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
-						   struct mptcp_addr_info *addr)
+						   const struct mptcp_pm_addr_entry *entry)
 {
-	struct mptcp_sock *msk;
-	long s_slot = 0, s_num = 0;
+	const struct mptcp_addr_info *addr = &entry->addr;
 	struct mptcp_rm_list list = { .nr = 0 };
+	long s_slot = 0, s_num = 0;
+	struct mptcp_sock *msk;
 
 	pr_debug("remove_id=%d", addr->id);
 
@@ -1354,7 +1381,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 
 		lock_sock(sk);
 		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
-		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow);
+		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
 		if (remove_subflow)
 			mptcp_pm_remove_subflow(msk, &list);
 		release_sock(sk);
@@ -1367,14 +1395,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 	return 0;
 }
 
-/* caller must ensure the RCU grace period is already elapsed */
-static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
-{
-	if (entry->lsk)
-		sock_release(entry->lsk);
-	kfree(entry);
-}
-
 static int mptcp_nl_remove_id_zero_address(struct net *net,
 					   struct mptcp_addr_info *addr)
 {
@@ -1451,7 +1471,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	__clear_bit(entry->addr.id, pernet->id_bitmap);
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr);
+	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry);
 	synchronize_rcu();
 	__mptcp_pm_release_addr_entry(entry);
 
@@ -1466,14 +1486,12 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 
 	list_for_each_entry(entry, rm_list, list) {
 		if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
-		    alist.nr < MPTCP_RM_IDS_MAX &&
-		    slist.nr < MPTCP_RM_IDS_MAX) {
-			alist.ids[alist.nr++] = entry->addr.id;
+		    slist.nr < MPTCP_RM_IDS_MAX)
 			slist.ids[slist.nr++] = entry->addr.id;
-		} else if (remove_anno_list_by_saddr(msk, &entry->addr) &&
-			 alist.nr < MPTCP_RM_IDS_MAX) {
+
+		if (remove_anno_list_by_saddr(msk, &entry->addr) &&
+		    alist.nr < MPTCP_RM_IDS_MAX)
 			alist.ids[alist.nr++] = entry->addr.id;
-		}
 	}
 
 	if (alist.nr) {

net/mptcp/protocol.c

@@ -117,6 +117,9 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssock->sk);
 	subflow->request_mptcp = 1;
+
+	/* This is the first subflow, always with id 0 */
+	subflow->local_id_valid = 1;
 	mptcp_sock_graft(msk->first, sk->sk_socket);
 
 	return 0;
@@ -1356,6 +1359,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 out:
 	if (READ_ONCE(msk->csum_enabled))
 		mptcp_update_data_checksum(skb, copy);
+	trace_mptcp_sendmsg_frag(mpext);
 	mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
 	return copy;
 }

net/mptcp/protocol.h

@@ -442,7 +442,8 @@ struct mptcp_subflow_context {
 		rx_eof : 1,
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */
-		stale : 1;	    /* unable to snd/rcv data, do not use for xmit */
+		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
+		local_id_valid : 1; /* local_id is correctly initialized */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;

net/mptcp/subflow.c

@@ -481,6 +481,51 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	mptcp_subflow_reset(sk);
 }
 
+static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
+{
+	subflow->local_id = local_id;
+	subflow->local_id_valid = 1;
+}
+
+static int subflow_chk_local_id(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	int err;
+
+	if (likely(subflow->local_id_valid))
+		return 0;
+
+	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
+	if (err < 0)
+		return err;
+
+	subflow_set_local_id(subflow, err);
+	return 0;
+}
+
+static int subflow_rebuild_header(struct sock *sk)
+{
+	int err = subflow_chk_local_id(sk);
+
+	if (unlikely(err < 0))
+		return err;
+
+	return inet_sk_rebuild_header(sk);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int subflow_v6_rebuild_header(struct sock *sk)
+{
+	int err = subflow_chk_local_id(sk);
+
+	if (unlikely(err < 0))
+		return err;
+
+	return inet6_sk_rebuild_header(sk);
+}
+#endif
+
 struct request_sock_ops mptcp_subflow_request_sock_ops;
 static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;
 
@@ -1104,7 +1149,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	struct sk_buff *skb;
 
 	if (!skb_peek(&ssk->sk_receive_queue))
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 	if (subflow->data_avail)
 		return true;
 
@@ -1169,7 +1214,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		subflow->reset_transient = 0;
 		subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
 		tcp_send_active_reset(ssk, GFP_ATOMIC);
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 		return true;
 	}
 
@@ -1182,7 +1227,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		subflow->reset_transient = 0;
 		subflow->reset_reason = MPTCP_RST_EMPTCP;
 		tcp_send_active_reset(ssk, GFP_ATOMIC);
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 		return false;
 	}
 
@@ -1204,7 +1249,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
 	if (subflow->map_valid &&
 	    mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
 		subflow->map_valid = 0;
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 
 		pr_debug("Done with mapping: seq=%u data_len=%u",
 			 subflow->map_subflow_seq,
@@ -1398,13 +1443,8 @@ 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) {
-		err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk);
-		if (err < 0)
-			goto failed;
-
-		local_id = err;
-	}
+	if (local_id)
+		subflow_set_local_id(subflow, local_id);
 
 	mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id,
 					     &flags, &ifindex);
@@ -1429,7 +1469,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
-	subflow->local_id = local_id;
 	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
@@ -1728,15 +1767,22 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->token = subflow_req->token;
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->idsn = subflow_req->idsn;
+
+		/* this is the first subflow, id is always 0 */
+		new_ctx->local_id_valid = 1;
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
 		new_ctx->fully_established = 1;
 		new_ctx->backup = subflow_req->backup;
-		new_ctx->local_id = subflow_req->local_id;
 		new_ctx->remote_id = subflow_req->remote_id;
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
+
+		/* the subflow req id is valid, fetched via subflow_check_req()
+		 * and subflow_token_join_request()
+		 */
+		subflow_set_local_id(new_ctx, subflow_req->local_id);
 	}
 }
 
@@ -1789,6 +1835,7 @@ void __init mptcp_subflow_init(void)
 	subflow_specific.conn_request = subflow_v4_conn_request;
 	subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
 	subflow_specific.sk_rx_dst_set = subflow_finish_connect;
+	subflow_specific.rebuild_header = subflow_rebuild_header;
 
 	tcp_prot_override = tcp_prot;
 	tcp_prot_override.release_cb = tcp_release_cb_override;
@@ -1801,6 +1848,7 @@ void __init mptcp_subflow_init(void)
 	subflow_v6_specific.conn_request = subflow_v6_conn_request;
 	subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
 	subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
+	subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header;
 
 	subflow_v6m_specific = subflow_v6_specific;
 	subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
@@ -1808,6 +1856,7 @@ void __init mptcp_subflow_init(void)
 	subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
 	subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
 	subflow_v6m_specific.net_frag_header_len = 0;
+	subflow_v6m_specific.rebuild_header = subflow_rebuild_header;
 
 	tcpv6_prot_override = tcpv6_prot;
 	tcpv6_prot_override.release_cb = tcp_release_cb_override;

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

@@ -16,7 +16,6 @@ capture=0
 checksum=0
 ip_mptcp=0
 check_invert=0
-do_all_tests=1
 init=0
 
 TEST_COUNT=0
@@ -311,6 +310,21 @@ wait_rm_addr()
 	done
 }
 
+wait_mpj()
+{
+	local ns="${1}"
+	local cnt old_cnt
+
+	old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}')
+
+	local i
+	for i in $(seq 10); do
+		cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}')
+		[ "$cnt" = "${old_cnt}" ] || break
+		sleep 0.1
+	done
+}
+
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -411,6 +425,80 @@ pm_nl_change_endpoint()
 	fi
 }
 
+pm_nl_check_endpoint()
+{
+	local line expected_line
+	local title="$1"
+	local msg="$2"
+	local ns=$3
+	local addr=$4
+	local _flags=""
+	local flags
+	local _port
+	local port
+	local dev
+	local _id
+	local id
+
+	if [ -n "${title}" ]; then
+		printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "${msg}"
+	else
+		printf "%-${nr_blank}s %s" " " "${msg}"
+	fi
+
+	shift 4
+	while [ -n "$1" ]; do
+		if [ $1 = "flags" ]; then
+			_flags=$2
+			[ ! -z $_flags ]; flags="flags $_flags"
+			shift
+		elif [ $1 = "dev" ]; then
+			[ ! -z $2 ]; dev="dev $1"
+			shift
+		elif [ $1 = "id" ]; then
+			_id=$2
+			[ ! -z $_id ]; id="id $_id"
+			shift
+		elif [ $1 = "port" ]; then
+			_port=$2
+			[ ! -z $_port ]; port=" port $_port"
+			shift
+		fi
+
+		shift
+	done
+
+	if [ -z "$id" ]; then
+		echo "[skip] bad test - missing endpoint id"
+		return
+	fi
+
+	if [ $ip_mptcp -eq 1 ]; then
+		line=$(ip -n $ns mptcp endpoint show $id)
+		# the dump order is: address id flags port dev
+		expected_line="$addr"
+		[ -n "$addr" ] && expected_line="$expected_line $addr"
+		expected_line="$expected_line $id"
+		[ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}"
+		[ -n "$dev" ] && expected_line="$expected_line $dev"
+		[ -n "$port" ] && expected_line="$expected_line $port"
+	else
+		line=$(ip netns exec $ns ./pm_nl_ctl get $_id)
+		# the dump order is: id flags dev address port
+		expected_line="$id"
+		[ -n "$flags" ] && expected_line="$expected_line $flags"
+		[ -n "$dev" ] && expected_line="$expected_line $dev"
+		[ -n "$addr" ] && expected_line="$expected_line $addr"
+		[ -n "$_port" ] && expected_line="$expected_line $_port"
+	fi
+	if [ "$line" = "$expected_line" ]; then
+		echo "[ ok ]"
+	else
+		echo "[fail] expected '$expected_line' found '$line'"
+		ret=1
+	fi
+}
+
 do_transfer()
 {
 	listener_ns="$1"
@@ -1150,14 +1238,25 @@ chk_rm_nr()
 {
 	local rm_addr_nr=$1
 	local rm_subflow_nr=$2
-	local invert=${3:-""}
+	local invert
+	local simult
 	local count
 	local dump_stats
 	local addr_ns=$ns1
 	local subflow_ns=$ns2
 	local extra_msg=""
 
-	if [[ $invert = "invert" ]]; then
+	shift 2
+	while [ -n "$1" ]; do
+		[ "$1" = "invert" ] && invert=true
+		[ "$1" = "simult" ] && simult=true
+		shift
+	done
+
+	if [ -z $invert ]; then
+		addr_ns=$ns1
+		subflow_ns=$ns2
+	elif [ $invert = "true" ]; then
 		addr_ns=$ns2
 		subflow_ns=$ns1
 		extra_msg="   invert"
@@ -1177,6 +1276,25 @@ chk_rm_nr()
 	echo -n " - rmsf  "
 	count=`ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'`
 	[ -z "$count" ] && count=0
+	if [ -n "$simult" ]; then
+		local cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}')
+		local suffix
+
+		# in case of simult flush, the subflow removal count on each side is
+		# unreliable
+		[ -z "$cnt" ] && cnt=0
+		count=$((count + cnt))
+		[ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
+		if [ $count -ge "$rm_subflow_nr" ] && \
+		   [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then
+			echo "[ ok ] $suffix"
+		else
+			echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]"
+			ret=1
+			dump_stats=1
+		fi
+		return
+	fi
 	if [ "$count" != "$rm_subflow_nr" ]; then
 		echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
 		ret=1
@@ -1243,7 +1361,7 @@ chk_link_usage()
 	fi
 }
 
-wait_for_tw()
+wait_attempt_fail()
 {
 	local timeout_ms=$((timeout_poll * 1000))
 	local time=0
@@ -1362,7 +1480,7 @@ subflows_error_tests()
 	TEST_COUNT=$((TEST_COUNT+1))
 
 	# mpj subflow will be in TW after the reset
-	wait_for_tw $ns2
+	wait_attempt_fail $ns2
 	pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 	wait
 
@@ -1667,7 +1785,7 @@ remove_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow
 	chk_join_nr "flush subflows and signal" 3 3 3
 	chk_add_nr 1 1
-	chk_rm_nr 2 2
+	chk_rm_nr 1 3 invert simult
 
 	# subflows flush
 	reset
@@ -1678,7 +1796,7 @@ remove_tests()
 	pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow
 	run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow
 	chk_join_nr "flush subflows" 3 3 3
-	chk_rm_nr 3 3
+	chk_rm_nr 0 3 simult
 
 	# addresses flush
 	reset
@@ -1690,7 +1808,7 @@ remove_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow
 	chk_join_nr "flush addresses" 3 3 3
 	chk_add_nr 3 3
-	chk_rm_nr 3 3 invert
+	chk_rm_nr 3 3 invert simult
 
 	# invalid addresses flush
 	reset
@@ -1909,7 +2027,7 @@ backup_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup
 	chk_join_nr "single address, backup" 1 1 1
 	chk_add_nr 1 1
-	chk_prio_nr 1 0
+	chk_prio_nr 1 1
 
 	# single address with port, backup
 	reset
@@ -1919,7 +2037,7 @@ backup_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup
 	chk_join_nr "single address with port, backup" 1 1 1
 	chk_add_nr 1 1
-	chk_prio_nr 1 0
+	chk_prio_nr 1 1
 }
 
 add_addr_ports_tests()
@@ -1974,7 +2092,7 @@ add_addr_ports_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow
 	chk_join_nr "flush subflows and signal with port" 3 3 3
 	chk_add_nr 1 1
-	chk_rm_nr 2 2
+	chk_rm_nr 1 3 invert simult
 
 	# multiple addresses with port
 	reset
@@ -2240,6 +2358,30 @@ fastclose_tests()
 	chk_rst_nr 1 1 invert
 }
 
+implicit_tests()
+{
+	# userspace pm type prevents add_addr
+	reset
+	pm_nl_set_limits $ns1 2 2
+	pm_nl_set_limits $ns2 2 2
+	pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow &
+
+	wait_mpj $ns1
+	TEST_COUNT=$((TEST_COUNT + 1))
+	pm_nl_check_endpoint "implicit EP" "creation" \
+		$ns2 10.0.2.2 id 1 flags implicit
+
+	pm_nl_add_endpoint $ns2 10.0.2.2 id 33
+	pm_nl_check_endpoint "" "ID change is prevented" \
+		$ns2 10.0.2.2 id 1 flags implicit
+
+	pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
+	pm_nl_check_endpoint "" "modif is allowed" \
+		$ns2 10.0.2.2 id 1 flags signal
+	wait
+}
+
 all_tests()
 {
 	subflows_tests
@@ -2258,6 +2400,7 @@ all_tests()
 	deny_join_id0_tests
 	fullmesh_tests
 	fastclose_tests
+	implicit_tests
 }
 
 # [$1: error message]
@@ -2285,6 +2428,7 @@ usage()
 	echo "  -d deny_join_id0_tests"
 	echo "  -m fullmesh_tests"
 	echo "  -z fastclose_tests"
+	echo "  -I implicit_tests"
 	echo "  -c capture pcap files"
 	echo "  -C enable data checksum"
 	echo "  -i use ip mptcp"
@@ -2293,84 +2437,69 @@ usage()
 	exit ${ret}
 }
 
-for arg in "$@"; do
-	# check for "capture/checksum" args before launching tests
-	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
-		capture=1
-	fi
-	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then
-		checksum=1
-	fi
-	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"i"[0-9a-zA-Z]*$ ]]; then
-		ip_mptcp=1
-	fi
-
-	# exception for the capture/checksum/ip_mptcp options, the rest means: a part of the tests
-	if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ] && [ "${arg}" != "-i" ]; then
-		do_all_tests=0
-	fi
-done
-
-if [ $do_all_tests -eq 1 ]; then
-	all_tests
-	exit $ret
-fi
 
-while getopts 'fesltra64bpkdmchzCSi' opt; do
+tests=()
+while getopts 'fesltra64bpkdmchzICSi' opt; do
 	case $opt in
 		f)
-			subflows_tests
+			tests+=(subflows_tests)
 			;;
 		e)
-			subflows_error_tests
+			tests+=(subflows_error_tests)
 			;;
 		s)
-			signal_address_tests
+			tests+=(signal_address_tests)
 			;;
 		l)
-			link_failure_tests
+			tests+=(link_failure_tests)
 			;;
 		t)
-			add_addr_timeout_tests
+			tests+=(add_addr_timeout_tests)
 			;;
 		r)
-			remove_tests
+			tests+=(remove_tests)
 			;;
 		a)
-			add_tests
+			tests+=(add_tests)
 			;;
 		6)
-			ipv6_tests
+			tests+=(ipv6_tests)
 			;;
 		4)
-			v4mapped_tests
+			tests+=(v4mapped_tests)
 			;;
 		b)
-			backup_tests
+			tests+=(backup_tests)
 			;;
 		p)
-			add_addr_ports_tests
+			tests+=(add_addr_ports_tests)
 			;;
 		k)
-			syncookies_tests
+			tests+=(syncookies_tests)
 			;;
 		S)
-			checksum_tests
+			tests+=(checksum_tests)
 			;;
 		d)
-			deny_join_id0_tests
+			tests+=(deny_join_id0_tests)
 			;;
 		m)
-			fullmesh_tests
+			tests+=(fullmesh_tests)
 			;;
 		z)
-			fastclose_tests
+			tests+=(fastclose_tests)
+			;;
+		I)
+			tests+=(implicit_tests)
 			;;
 		c)
+			capture=1
 			;;
 		C)
+			checksum=1
 			;;
 		i)
+			ip_mptcp=1
 			;;
 		h)
 			usage
@@ -2381,4 +2510,12 @@ while getopts 'fesltra64bpkdmchzCSi' opt; do
 	esac
 done
 
+if [ ${#tests[@]} -eq 0 ]; then
+	all_tests
+else
+	for subtests in "${tests[@]}"; do
+		"${subtests}"
+	done
+fi
+
 exit $ret

tools/testing/selftests/net/mptcp/pm_nl_ctl.c

@@ -436,6 +436,13 @@ static void print_addr(struct rtattr *attrs, int len)
 					printf(",");
 			}
 
+			if (flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
+				printf("implicit");
+				flags &= ~MPTCP_PM_ADDR_FLAG_IMPLICIT;
+				if (flags)
+					printf(",");
+			}
+
 			/* bump unknown flags, if any */
 			if (flags)
 				printf("0x%x", flags);