1 files changed, 527 insertions, 289 deletions

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 7b96be1e9f14..9813ed0fde9b 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -22,14 +22,6 @@ static struct genl_family mptcp_genl_family;
 
 static int pm_nl_pernet_id;
 
-struct mptcp_pm_addr_entry {
-	struct list_head	list;
-	struct mptcp_addr_info	addr;
-	u8			flags;
-	int			ifindex;
-	struct socket		*lsk;
-};
-
 struct mptcp_pm_add_entry {
 	struct list_head	list;
 	struct mptcp_addr_info	addr;
@@ -38,9 +30,6 @@ struct mptcp_pm_add_entry {
 	u8			retrans_times;
 };
 
-#define MAX_ADDR_ID		255
-#define BITMAP_SZ DIV_ROUND_UP(MAX_ADDR_ID + 1, BITS_PER_LONG)
-
 struct pm_nl_pernet {
 	/* protects pernet updates */
 	spinlock_t		lock;
@@ -52,14 +41,25 @@ struct pm_nl_pernet {
 	unsigned int		local_addr_max;
 	unsigned int		subflows_max;
 	unsigned int		next_id;
-	unsigned long		id_bitmap[BITMAP_SZ];
+	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 };
 
 #define MPTCP_PM_ADDR_MAX	8
 #define ADD_ADDR_RETRANS_MAX	3
 
-static bool addresses_equal(const struct mptcp_addr_info *a,
-			    struct mptcp_addr_info *b, bool use_port)
+static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
+{
+	return net_generic(net, pm_nl_pernet_id);
+}
+
+static struct pm_nl_pernet *
+pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
+{
+	return pm_nl_get_pernet(sock_net((struct sock *)msk));
+}
+
+bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
+			   const struct mptcp_addr_info *b, bool use_port)
 {
 	bool addr_equals = false;
 
@@ -86,16 +86,6 @@ 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)
 {
@@ -123,7 +113,7 @@ static void remote_address(const struct sock_common *skc,
 }
 
 static bool lookup_subflow_by_saddr(const struct list_head *list,
-				    struct mptcp_addr_info *saddr)
+				    const struct mptcp_addr_info *saddr)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_addr_info cur;
@@ -133,7 +123,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list,
 		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
 
 		local_address(skc, &cur);
-		if (addresses_equal(&cur, saddr, saddr->port))
+		if (mptcp_addresses_equal(&cur, saddr, saddr->port))
 			return true;
 	}
 
@@ -141,7 +131,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list,
 }
 
 static bool lookup_subflow_by_daddr(const struct list_head *list,
-				    struct mptcp_addr_info *daddr)
+				    const struct mptcp_addr_info *daddr)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_addr_info cur;
@@ -151,7 +141,7 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
 
 		remote_address(skc, &cur);
-		if (addresses_equal(&cur, daddr, daddr->port))
+		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
 			return true;
 	}
 
@@ -160,19 +150,21 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 
 static struct mptcp_pm_addr_entry *
 select_local_address(const struct pm_nl_pernet *pernet,
-		     struct mptcp_sock *msk)
+		     const struct mptcp_sock *msk)
 {
+	const struct sock *sk = (const struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry, *ret = NULL;
-	struct sock *sk = (struct sock *)msk;
 
 	msk_owned_by_me(msk);
 
 	rcu_read_lock();
-	__mptcp_flush_join_list(msk);
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
 			continue;
 
+		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+			continue;
+
 		if (entry->addr.family != sk->sk_family) {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 			if ((entry->addr.family == AF_INET &&
@@ -183,23 +175,17 @@ select_local_address(const struct pm_nl_pernet *pernet,
 				continue;
 		}
 
-		/* avoid any address already in use by subflows and
-		 * pending join
-		 */
-		if (!lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) {
-			ret = entry;
-			break;
-		}
+		ret = entry;
+		break;
 	}
 	rcu_read_unlock();
 	return ret;
 }
 
 static struct mptcp_pm_addr_entry *
-select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
 {
 	struct mptcp_pm_addr_entry *entry, *ret = NULL;
-	int i = 0;
 
 	rcu_read_lock();
 	/* do not keep any additional per socket state, just signal
@@ -208,71 +194,74 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)
 	 * can lead to additional addresses not being announced.
 	 */
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+			continue;
+
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
-		if (i++ == pos) {
-			ret = entry;
-			break;
-		}
+
+		ret = entry;
+		break;
 	}
 	rcu_read_unlock();
 	return ret;
 }
 
-unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk)
+unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
 {
-	struct pm_nl_pernet *pernet;
+	const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 	return READ_ONCE(pernet->add_addr_signal_max);
 }
 EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);
 
-unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk)
+unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk)
 {
-	struct pm_nl_pernet *pernet;
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 	return READ_ONCE(pernet->add_addr_accept_max);
 }
 EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);
 
-unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk)
+unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk)
 {
-	struct pm_nl_pernet *pernet;
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 	return READ_ONCE(pernet->subflows_max);
 }
 EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);
 
-unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk)
+unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk)
 {
-	struct pm_nl_pernet *pernet;
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 	return READ_ONCE(pernet->local_addr_max);
 }
 EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);
 
-static void check_work_pending(struct mptcp_sock *msk)
+bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
 {
-	if (msk->pm.add_addr_signaled == mptcp_pm_get_add_addr_signal_max(msk) &&
-	    (msk->pm.local_addr_used == mptcp_pm_get_local_addr_max(msk) ||
-	     msk->pm.subflows == mptcp_pm_get_subflows_max(msk)))
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) ||
+	    (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap,
+			       MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) {
 		WRITE_ONCE(msk->pm.work_pending, false);
+		return false;
+	}
+	return true;
 }
 
 struct mptcp_pm_add_entry *
-mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
-				struct mptcp_addr_info *addr)
+mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
+				const struct mptcp_addr_info *addr)
 {
 	struct mptcp_pm_add_entry *entry;
 
 	lockdep_assert_held(&msk->pm.lock);
 
 	list_for_each_entry(entry, &msk->pm.anno_list, list) {
-		if (addresses_equal(&entry->addr, addr, true))
+		if (mptcp_addresses_equal(&entry->addr, addr, true))
 			return entry;
 	}
 
@@ -289,7 +278,7 @@ bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
 
 	spin_lock_bh(&msk->pm.lock);
 	list_for_each_entry(entry, &msk->pm.anno_list, list) {
-		if (addresses_equal(&entry->addr, &saddr, true)) {
+		if (mptcp_addresses_equal(&entry->addr, &saddr, true)) {
 			ret = true;
 			goto out;
 		}
@@ -346,7 +335,7 @@ out:
 
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       struct mptcp_addr_info *addr, bool check_id)
+		       const struct mptcp_addr_info *addr, bool check_id)
 {
 	struct mptcp_pm_add_entry *entry;
 	struct sock *sk = (struct sock *)msk;
@@ -363,8 +352,8 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 	return entry;
 }
 
-static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
-				     struct mptcp_pm_addr_entry *entry)
+bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+			      const struct mptcp_pm_addr_entry *entry)
 {
 	struct mptcp_pm_add_entry *add_entry = NULL;
 	struct sock *sk = (struct sock *)msk;
@@ -372,8 +361,16 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	lockdep_assert_held(&msk->pm.lock);
 
-	if (mptcp_lookup_anno_list_by_saddr(msk, &entry->addr))
-		return false;
+	add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr);
+
+	if (add_entry) {
+		if (mptcp_pm_is_kernel(msk))
+			return false;
+
+		sk_reset_timer(sk, &add_entry->add_timer,
+			       jiffies + mptcp_get_add_addr_timeout(net));
+		return true;
+	}
 
 	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
 	if (!add_entry)
@@ -410,13 +407,13 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	}
 }
 
-static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr,
-				  struct mptcp_addr_info *addr)
+static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
+				  const struct mptcp_addr_info *addr)
 {
 	int i;
 
 	for (i = 0; i < nr; i++) {
-		if (addresses_equal(&addrs[i], addr, addr->port))
+		if (addrs[i].id == addr->id)
 			return true;
 	}
 
@@ -429,6 +426,7 @@ static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr
 static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
 					      struct mptcp_addr_info *addrs)
 {
+	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
 	struct sock *sk = (struct sock *)msk, *ssk;
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_addr_info remote = { 0 };
@@ -436,22 +434,29 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 	int i = 0;
 
 	subflows_max = mptcp_pm_get_subflows_max(msk);
+	remote_address((struct sock_common *)sk, &remote);
 
 	/* Non-fullmesh endpoint, fill in the single entry
 	 * corresponding to the primary MPC subflow remote address
 	 */
 	if (!fullmesh) {
-		remote_address((struct sock_common *)sk, &remote);
+		if (deny_id0)
+			return 0;
+
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
-			remote_address((struct sock_common *)ssk, &remote);
-			if (!lookup_address_in_vec(addrs, i, &remote) &&
+			remote_address((struct sock_common *)ssk, &addrs[i]);
+			addrs[i].id = subflow->remote_id;
+			if (deny_id0 && !addrs[i].id)
+				continue;
+
+			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
 			    msk->pm.subflows < subflows_max) {
 				msk->pm.subflows++;
-				addrs[i++] = remote;
+				i++;
 			}
 		}
 	}
@@ -459,6 +464,64 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm
 	return i;
 }
 
+static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				bool prio, bool backup)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+	bool slow;
+
+	pr_debug("send ack for %s",
+		 prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
+
+	slow = lock_sock_fast(ssk);
+	if (prio) {
+		if (subflow->backup != backup)
+			msk->last_snd = NULL;
+
+		subflow->send_mp_prio = 1;
+		subflow->backup = backup;
+		subflow->request_bkup = backup;
+	}
+
+	__mptcp_subflow_send_ack(ssk);
+	unlock_sock_fast(ssk, slow);
+}
+
+static void mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+			      bool prio, bool backup)
+{
+	spin_unlock_bh(&msk->pm.lock);
+	__mptcp_pm_send_ack(msk, subflow, prio, backup);
+	spin_lock_bh(&msk->pm.lock);
+}
+
+static struct mptcp_pm_addr_entry *
+__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
+{
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry(entry, &pernet->local_addr_list, list) {
+		if (entry->addr.id == id)
+			return entry;
+	}
+	return NULL;
+}
+
+static struct mptcp_pm_addr_entry *
+__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info,
+	      bool lookup_by_id)
+{
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry(entry, &pernet->local_addr_list, list) {
+		if ((!lookup_by_id &&
+		     mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) ||
+		    (lookup_by_id && entry->addr.id == info->id))
+			return entry;
+	}
+	return NULL;
+}
+
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -468,12 +531,35 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
 
-	pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
+	pernet = pm_nl_get_pernet(sock_net(sk));
 
 	add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
 	local_addr_max = mptcp_pm_get_local_addr_max(msk);
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
+	/* do lazy endpoint usage accounting for the MPC subflows */
+	if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
+		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
+		struct mptcp_pm_addr_entry *entry;
+		struct mptcp_addr_info mpc_addr;
+		bool backup = false;
+
+		local_address((struct sock_common *)msk->first, &mpc_addr);
+		rcu_read_lock();
+		entry = __lookup_addr(pernet, &mpc_addr, false);
+		if (entry) {
+			__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
+			msk->mpc_endpoint_id = entry->addr.id;
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+		}
+		rcu_read_unlock();
+
+		if (backup)
+			mptcp_pm_send_ack(msk, subflow, true, backup);
+
+		msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
+	}
+
 	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
 		 msk->pm.local_addr_used, local_addr_max,
 		 msk->pm.add_addr_signaled, add_addr_signal_max,
@@ -481,47 +567,51 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 
 	/* check first for announce */
 	if (msk->pm.add_addr_signaled < add_addr_signal_max) {
-		local = select_signal_address(pernet,
-					      msk->pm.add_addr_signaled);
+		local = select_signal_address(pernet, msk);
+
+		/* due to racing events on both ends we can reach here while
+		 * previous add address is still running: if we invoke now
+		 * mptcp_pm_announce_addr(), that will fail and the
+		 * corresponding id will be marked as used.
+		 * Instead let the PM machinery reschedule us when the
+		 * current address announce will be completed.
+		 */
+		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
+			return;
 
 		if (local) {
 			if (mptcp_pm_alloc_anno_list(msk, local)) {
+				__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
 				msk->pm.add_addr_signaled++;
 				mptcp_pm_announce_addr(msk, &local->addr, false);
 				mptcp_pm_nl_addr_send_ack(msk);
 			}
-		} else {
-			/* pick failed, avoid fourther attempts later */
-			msk->pm.local_addr_used = add_addr_signal_max;
 		}
-
-		check_work_pending(msk);
 	}
 
 	/* check if should create a new subflow */
-	if (msk->pm.local_addr_used < local_addr_max &&
-	    msk->pm.subflows < subflows_max &&
-	    !READ_ONCE(msk->pm.remote_deny_join_id0)) {
+	while (msk->pm.local_addr_used < local_addr_max &&
+	       msk->pm.subflows < subflows_max) {
+		struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
+		bool fullmesh;
+		int i, nr;
+
 		local = select_local_address(pernet, msk);
-		if (local) {
-			bool fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
-			struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
-			int i, nr;
+		if (!local)
+			break;
 
-			msk->pm.local_addr_used++;
-			check_work_pending(msk);
-			nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
-			spin_unlock_bh(&msk->pm.lock);
-			for (i = 0; i < nr; i++)
-				__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
-			spin_lock_bh(&msk->pm.lock);
-			return;
-		}
+		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
-		/* lookup failed, avoid fourther attempts later */
-		msk->pm.local_addr_used = local_addr_max;
-		check_work_pending(msk);
+		msk->pm.local_addr_used++;
+		nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
+		if (nr)
+			__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		spin_unlock_bh(&msk->pm.lock);
+		for (i = 0; i < nr; i++)
+			__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+		spin_lock_bh(&msk->pm.lock);
 	}
+	mptcp_pm_nl_check_work_pending(msk);
 }
 
 static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk)
@@ -547,11 +637,10 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 	unsigned int subflows_max;
 	int i = 0;
 
-	pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
+	pernet = pm_nl_get_pernet_from_msk(msk);
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
 	rcu_read_lock();
-	__mptcp_flush_join_list(msk);
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
 			continue;
@@ -603,15 +692,20 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 		 msk->pm.add_addr_accepted, add_addr_accept_max,
 		 msk->pm.remote.family);
 
-	if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote))
-		goto add_addr_echo;
+	remote = msk->pm.remote;
+	mptcp_pm_announce_addr(msk, &remote, true);
+	mptcp_pm_nl_addr_send_ack(msk);
+
+	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
+		return;
+
+	/* pick id 0 port, if none is provided the remote address */
+	if (!remote.port)
+		remote.port = sk->sk_dport;
 
 	/* connect to the specified remote address, using whatever
 	 * local address the routing configuration will pick.
 	 */
-	remote = msk->pm.remote;
-	if (!remote.port)
-		remote.port = sk->sk_dport;
 	nr = fill_local_addresses_vec(msk, addrs);
 
 	msk->pm.add_addr_accepted++;
@@ -623,10 +717,6 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	for (i = 0; i < nr; i++)
 		__mptcp_subflow_connect(sk, &addrs[i], &remote);
 	spin_lock_bh(&msk->pm.lock);
-
-add_addr_echo:
-	mptcp_pm_announce_addr(msk, &msk->pm.remote, true);
-	mptcp_pm_nl_addr_send_ack(msk);
 }
 
 void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
@@ -640,23 +730,15 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 	    !mptcp_pm_should_rm_signal(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);
-
-		spin_unlock_bh(&msk->pm.lock);
-		pr_debug("send ack for %s",
-			 mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr");
-
-		mptcp_subflow_send_ack(ssk);
-		spin_lock_bh(&msk->pm.lock);
-	}
+	if (subflow)
+		mptcp_pm_send_ack(msk, subflow, false, false);
 }
 
-static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-					struct mptcp_addr_info *addr,
-					u8 bkup)
+int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+				 struct mptcp_addr_info *addr,
+				 struct mptcp_addr_info *rem,
+				 u8 bkup)
 {
 	struct mptcp_subflow_context *subflow;
 
@@ -664,29 +746,30 @@ static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		struct sock *sk = (struct sock *)msk;
-		struct mptcp_addr_info local;
+		struct mptcp_addr_info local, remote;
 
 		local_address((struct sock_common *)ssk, &local);
-		if (!addresses_equal(&local, addr, addr->port))
+		if (!mptcp_addresses_equal(&local, addr, addr->port))
 			continue;
 
-		subflow->backup = bkup;
-		subflow->send_mp_prio = 1;
-		subflow->request_bkup = bkup;
-		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX);
-
-		spin_unlock_bh(&msk->pm.lock);
-		pr_debug("send ack for mp_prio");
-		mptcp_subflow_send_ack(ssk);
-		spin_lock_bh(&msk->pm.lock);
+		if (rem && rem->family != AF_UNSPEC) {
+			remote_address((struct sock_common *)ssk, &remote);
+			if (!mptcp_addresses_equal(&remote, rem, rem->port))
+				continue;
+		}
 
+		__mptcp_pm_send_ack(msk, subflow, true, bkup);
 		return 0;
 	}
 
 	return -EINVAL;
 }
 
+static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
+{
+	return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
+}
+
 static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 					   const struct mptcp_rm_list *rm_list,
 					   enum linux_mptcp_mib_field rm_type)
@@ -700,6 +783,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 
 	msk_owned_by_me(msk);
 
+	if (sk->sk_state == TCP_LISTEN)
+		return;
+
 	if (!rm_list->nr)
 		return;
 
@@ -707,34 +793,47 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		return;
 
 	for (i = 0; i < rm_list->nr; i++) {
-		list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		u8 rm_id = rm_list->ids[i];
+		bool removed = false;
+
+		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
 			u8 id = subflow->local_id;
 
-			if (rm_type == MPTCP_MIB_RMADDR)
-				id = subflow->remote_id;
-
-			if (rm_list->ids[i] != id)
+			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+				continue;
+			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
-			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u",
+			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_list->ids[i], subflow->local_id, subflow->remote_id);
+				 i, rm_id, subflow->local_id, subflow->remote_id,
+				 msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
+
+			/* the following takes care of updating the subflows counter */
 			mptcp_close_ssk(sk, ssk, subflow);
 			spin_lock_bh(&msk->pm.lock);
 
-			if (rm_type == MPTCP_MIB_RMADDR) {
-				msk->pm.add_addr_accepted--;
-				WRITE_ONCE(msk->pm.accept_addr, true);
-			} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
-				msk->pm.local_addr_used--;
-			}
-			msk->pm.subflows--;
+			removed = true;
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
+		if (rm_type == MPTCP_MIB_RMSUBFLOW)
+			__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
+		if (!removed)
+			continue;
+
+		if (!mptcp_pm_is_kernel(msk))
+			continue;
+
+		if (rm_type == MPTCP_MIB_RMADDR) {
+			msk->pm.add_addr_accepted--;
+			WRITE_ONCE(msk->pm.accept_addr, true);
+		} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
+			msk->pm.local_addr_used--;
+		}
 	}
 }
 
@@ -755,6 +854,9 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk)
 
 	msk_owned_by_me(msk);
 
+	if (!(pm->status & MPTCP_PM_WORK_MASK))
+		return;
+
 	spin_lock_bh(&msk->pm.lock);
 
 	pr_debug("msk=%p status=%x", msk, pm->status);
@@ -789,10 +891,18 @@ 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;
 
@@ -800,7 +910,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 	/* to keep the code simple, don't do IDR-like allocation for address ID,
 	 * just bail when we exceed limits
 	 */
-	if (pernet->next_id == MAX_ADDR_ID)
+	if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
 		pernet->next_id = 1;
 	if (pernet->addrs >= MPTCP_PM_ADDR_MAX)
 		goto out;
@@ -810,26 +920,40 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 	/* do not insert duplicate address, differentiate on port only
 	 * singled addresses
 	 */
+	if (!address_use_port(entry))
+		entry->addr.port = 0;
 	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;
+		if (mptcp_addresses_equal(&cur->addr, &entry->addr,
+					  cur->addr.port || entry->addr.port)) {
+			/* 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) {
 find_next:
 		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
-						    MAX_ADDR_ID + 1,
+						    MPTCP_PM_MAX_ADDR_ID + 1,
 						    pernet->next_id);
-		if ((!entry->addr.id || entry->addr.id > MAX_ADDR_ID) &&
-		    pernet->next_id != 1) {
+		if (!entry->addr.id && pernet->next_id != 1) {
 			pernet->next_id = 1;
 			goto find_next;
 		}
 	}
 
-	if (!entry->addr.id || entry->addr.id > MAX_ADDR_ID)
+	if (!entry->addr.id)
 		goto out;
 
 	__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -846,17 +970,27 @@ find_next:
 	}
 
 	pernet->addrs++;
-	list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+	if (!entry->addr.port)
+		list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+	else
+		list_add_rcu(&entry->list, &pernet->local_addr_list);
 	ret = entry->addr.id;
 
 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;
 }
 
 static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 					    struct mptcp_pm_addr_entry *entry)
 {
+	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
 	struct mptcp_sock *msk;
 	struct socket *ssock;
@@ -881,8 +1015,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	}
 
 	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
-	err = kernel_bind(ssock, (struct sockaddr *)&addr,
-			  sizeof(struct sockaddr_in));
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (entry->addr.family == AF_INET6)
+		addrlen = sizeof(struct sockaddr_in6);
+#endif
+	err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen);
 	if (err) {
 		pr_warn("kernel_bind error, err=%d", err);
 		goto out;
@@ -917,17 +1054,17 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	 */
 	local_address((struct sock_common *)msk, &msk_local);
 	local_address((struct sock_common *)skc, &skc_local);
-	if (addresses_equal(&msk_local, &skc_local, false))
+	if (mptcp_addresses_equal(&msk_local, &skc_local, false))
 		return 0;
 
-	if (address_zero(&skc_local))
-		return 0;
+	if (mptcp_pm_is_userspace(msk))
+		return mptcp_userspace_pm_get_local_id(msk, &skc_local);
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
+	pernet = pm_nl_get_pernet_from_msk(msk);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
+		if (mptcp_addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
 			ret = entry->addr.id;
 			break;
 		}
@@ -945,7 +1082,7 @@ 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)
@@ -954,18 +1091,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	return ret;
 }
 
-void mptcp_pm_nl_data_init(struct mptcp_sock *msk)
-{
-	struct mptcp_pm_data *pm = &msk->pm;
-	bool subflows;
-
-	subflows = !!mptcp_pm_get_subflows_max(msk);
-	WRITE_ONCE(pm->work_pending, (!!mptcp_pm_get_local_addr_max(msk) && subflows) ||
-		   !!mptcp_pm_get_add_addr_signal_max(msk));
-	WRITE_ONCE(pm->accept_addr, !!mptcp_pm_get_add_addr_accept_max(msk) && subflows);
-	WRITE_ONCE(pm->accept_subflow, subflows);
-}
-
 #define MPTCP_PM_CMD_GRP_OFFSET       0
 #define MPTCP_PM_EV_GRP_OFFSET        1
 
@@ -993,6 +1118,10 @@ static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = {
 					NLA_POLICY_NESTED(mptcp_pm_addr_policy),
 	[MPTCP_PM_ATTR_RCV_ADD_ADDRS]	= { .type	= NLA_U32,	},
 	[MPTCP_PM_ATTR_SUBFLOWS]	= { .type	= NLA_U32,	},
+	[MPTCP_PM_ATTR_TOKEN]		= { .type	= NLA_U32,	},
+	[MPTCP_PM_ATTR_LOC_ID]		= { .type	= NLA_U8,	},
+	[MPTCP_PM_ATTR_ADDR_REMOTE]	=
+					NLA_POLICY_NESTED(mptcp_pm_addr_policy),
 };
 
 void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
@@ -1022,7 +1151,7 @@ void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ss
 			}
 			unlock_sock_fast(ssk, slow);
 
-			/* always try to push the pending data regarless of re-injections:
+			/* always try to push the pending data regardless of re-injections:
 			 * we can possibly use backup subflows now, and subflow selection
 			 * is cheap under the msk socket lock
 			 */
@@ -1041,11 +1170,12 @@ static int mptcp_pm_family_to_addr(int family)
 	return MPTCP_PM_ADDR_ATTR_ADDR4;
 }
 
-static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
-			       bool require_family,
-			       struct mptcp_pm_addr_entry *entry)
+static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[],
+				       const struct nlattr *attr,
+				       struct genl_info *info,
+				       struct mptcp_addr_info *addr,
+				       bool require_family)
 {
-	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
 	int err, addr_addr;
 
 	if (!attr) {
@@ -1059,27 +1189,29 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
 	if (err)
 		return err;
 
-	memset(entry, 0, sizeof(*entry));
+	if (tb[MPTCP_PM_ADDR_ATTR_ID])
+		addr->id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]);
+
 	if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) {
 		if (!require_family)
-			goto skip_family;
+			return err;
 
 		NL_SET_ERR_MSG_ATTR(info->extack, attr,
 				    "missing family");
 		return -EINVAL;
 	}
 
-	entry->addr.family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]);
-	if (entry->addr.family != AF_INET
+	addr->family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]);
+	if (addr->family != AF_INET
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	    && entry->addr.family != AF_INET6
+	    && addr->family != AF_INET6
 #endif
 	    ) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr,
 				    "unknown address family");
 		return -EINVAL;
 	}
-	addr_addr = mptcp_pm_family_to_addr(entry->addr.family);
+	addr_addr = mptcp_pm_family_to_addr(addr->family);
 	if (!tb[addr_addr]) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr,
 				    "missing address data");
@@ -1087,40 +1219,59 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
 	}
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (entry->addr.family == AF_INET6)
-		entry->addr.addr6 = nla_get_in6_addr(tb[addr_addr]);
+	if (addr->family == AF_INET6)
+		addr->addr6 = nla_get_in6_addr(tb[addr_addr]);
 	else
 #endif
-		entry->addr.addr.s_addr = nla_get_in_addr(tb[addr_addr]);
+		addr->addr.s_addr = nla_get_in_addr(tb[addr_addr]);
+
+	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
+		addr->port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));
+
+	return err;
+}
+
+int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
+			struct mptcp_addr_info *addr)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+	memset(addr, 0, sizeof(*addr));
+
+	return mptcp_pm_parse_pm_addr_attr(tb, attr, info, addr, true);
+}
+
+int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
+			 bool require_family,
+			 struct mptcp_pm_addr_entry *entry)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+	int err;
+
+	memset(entry, 0, sizeof(*entry));
+
+	err = mptcp_pm_parse_pm_addr_attr(tb, attr, info, &entry->addr, require_family);
+	if (err)
+		return err;
 
-skip_family:
 	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) {
 		u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
 
 		entry->ifindex = val;
 	}
 
-	if (tb[MPTCP_PM_ADDR_ATTR_ID])
-		entry->addr.id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]);
-
 	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
 		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
 
-	if (tb[MPTCP_PM_ADDR_ATTR_PORT]) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
-			NL_SET_ERR_MSG_ATTR(info->extack, attr,
-					    "flags must have signal when using port");
-			return -EINVAL;
-		}
+	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
 		entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));
-	}
 
 	return 0;
 }
 
 static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
 {
-	return net_generic(genl_info_net(info), pm_nl_pernet_id);
+	return pm_nl_get_pernet(genl_info_net(info));
 }
 
 static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
@@ -1131,7 +1282,8 @@ static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
 
-		if (!READ_ONCE(msk->fully_established))
+		if (!READ_ONCE(msk->fully_established) ||
+		    mptcp_pm_is_userspace(msk))
 			goto next;
 
 		lock_sock(sk);
@@ -1155,11 +1307,27 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
 	struct mptcp_pm_addr_entry addr, *entry;
 	int ret;
 
-	ret = mptcp_pm_parse_addr(attr, info, true, &addr);
+	ret = mptcp_pm_parse_entry(attr, info, true, &addr);
 	if (ret < 0)
 		return ret;
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+		GENL_SET_ERR_MSG(info, "flags must have signal when using port");
+		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_ACCOUNT);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "can't allocate addr");
 		return -ENOMEM;
@@ -1188,29 +1356,25 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static struct mptcp_pm_addr_entry *
-__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
-{
-	struct mptcp_pm_addr_entry *entry;
-
-	list_for_each_entry(entry, &pernet->local_addr_list, list) {
-		if (entry->addr.id == id)
-			return entry;
-	}
-	return NULL;
-}
-
-int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id,
+int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
 					 u8 *flags, int *ifindex)
 {
 	struct mptcp_pm_addr_entry *entry;
+	struct sock *sk = (struct sock *)msk;
+	struct net *net = sock_net(sk);
 
 	*flags = 0;
 	*ifindex = 0;
 
 	if (id) {
+		if (mptcp_pm_is_userspace(msk))
+			return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk,
+									      id,
+									      flags,
+									      ifindex);
+
 		rcu_read_lock();
-		entry = __lookup_addr_by_id(net_generic(net, pm_nl_pernet_id), id);
+		entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
 		if (entry) {
 			*flags = entry->flags;
 			*ifindex = entry->ifindex;
@@ -1222,7 +1386,7 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id,
 }
 
 static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
-				      struct mptcp_addr_info *addr)
+				      const struct mptcp_addr_info *addr)
 {
 	struct mptcp_pm_add_entry *entry;
 
@@ -1237,7 +1401,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 }
 
 static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
-				      struct mptcp_addr_info *addr,
+				      const struct mptcp_addr_info *addr,
 				      bool force)
 {
 	struct mptcp_rm_list list = { .nr = 0 };
@@ -1255,11 +1419,12 @@ 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);
 
@@ -1269,6 +1434,9 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		struct sock *sk = (struct sock *)msk;
 		bool remove_subflow;
 
+		if (mptcp_pm_is_userspace(msk))
+			goto next;
+
 		if (list_empty(&msk->conn_list)) {
 			mptcp_pm_remove_anno_addr(msk, addr, false);
 			goto next;
@@ -1276,7 +1444,8 @@ 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);
@@ -1289,14 +1458,6 @@ next:
 	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)
 {
@@ -1310,11 +1471,11 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
 		struct sock *sk = (struct sock *)msk;
 		struct mptcp_addr_info msk_local;
 
-		if (list_empty(&msk->conn_list))
+		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
 			goto next;
 
 		local_address((struct sock_common *)msk, &msk_local);
-		if (!addresses_equal(&msk_local, addr, addr->port))
+		if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
 			goto next;
 
 		lock_sock(sk);
@@ -1340,7 +1501,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	unsigned int addr_max;
 	int ret;
 
-	ret = mptcp_pm_parse_addr(attr, info, false, &addr);
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
 
@@ -1373,29 +1534,27 @@ 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);
 
 	return ret;
 }
 
-static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
-					       struct list_head *rm_list)
+void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+					struct list_head *rm_list)
 {
 	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
 	struct mptcp_pm_addr_entry *entry;
 
 	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) {
@@ -1419,9 +1578,11 @@ static void mptcp_nl_remove_addrs_list(struct net *net,
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
 
-		lock_sock(sk);
-		mptcp_pm_remove_addrs_and_subflows(msk, rm_list);
-		release_sock(sk);
+		if (!mptcp_pm_is_userspace(msk)) {
+			lock_sock(sk);
+			mptcp_pm_remove_addrs_and_subflows(msk, rm_list);
+			release_sock(sk);
+		}
 
 		sock_put(sk);
 		cond_resched();
@@ -1458,7 +1619,7 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)
 	list_splice_init(&pernet->local_addr_list, &free_list);
 	__reset_counters(pernet);
 	pernet->next_id = 1;
-	bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1);
+	bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	spin_unlock_bh(&pernet->lock);
 	mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list);
 	synchronize_rcu();
@@ -1514,7 +1675,7 @@ static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info)
 	void *reply;
 	int ret;
 
-	ret = mptcp_pm_parse_addr(attr, info, false, &addr);
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
 
@@ -1565,10 +1726,10 @@ static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg,
 	void *hdr;
 	int i;
 
-	pernet = net_generic(net, pm_nl_pernet_id);
+	pernet = pm_nl_get_pernet(net);
 
 	spin_lock_bh(&pernet->lock);
-	for (i = id; i < MAX_ADDR_ID + 1; i++) {
+	for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) {
 		if (test_bit(i, pernet->id_bitmap)) {
 			entry = __lookup_addr_by_id(pernet, i);
 			if (!entry)
@@ -1672,9 +1833,22 @@ fail:
 	return -EMSGSIZE;
 }
 
-static int mptcp_nl_addr_backup(struct net *net,
-				struct mptcp_addr_info *addr,
-				u8 bkup)
+static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
+				 struct mptcp_addr_info *addr)
+{
+	struct mptcp_rm_list list = { .nr = 0 };
+
+	list.ids[list.nr++] = addr->id;
+
+	spin_lock_bh(&msk->pm.lock);
+	mptcp_pm_nl_rm_subflow_received(msk, &list);
+	mptcp_pm_create_subflow_or_signal_addr(msk);
+	spin_unlock_bh(&msk->pm.lock);
+}
+
+static int mptcp_nl_set_flags(struct net *net,
+			      struct mptcp_addr_info *addr,
+			      u8 bkup, u8 changed)
 {
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
@@ -1683,13 +1857,14 @@ static int mptcp_nl_addr_backup(struct net *net,
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
 
-		if (list_empty(&msk->conn_list))
+		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
 			goto next;
 
 		lock_sock(sk);
-		spin_lock_bh(&msk->pm.lock);
-		ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup);
-		spin_unlock_bh(&msk->pm.lock);
+		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
+			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
+		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
+			mptcp_pm_nl_fullmesh(msk, addr);
 		release_sock(sk);
 
 next:
@@ -1702,31 +1877,58 @@ next:
 
 static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
 {
+	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
+	struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
+	struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
+	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct mptcp_pm_addr_entry addr, *entry;
+	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
+			   MPTCP_PM_ADDR_FLAG_FULLMESH;
 	struct net *net = sock_net(skb->sk);
-	u8 bkup = 0;
+	u8 bkup = 0, lookup_by_id = 0;
 	int ret;
 
-	ret = mptcp_pm_parse_addr(attr, info, true, &addr);
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
 
+	if (attr_rem) {
+		ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
 		bkup = 1;
+	if (addr.addr.family == AF_UNSPEC) {
+		lookup_by_id = 1;
+		if (!addr.addr.id)
+			return -EOPNOTSUPP;
+	}
 
-	list_for_each_entry(entry, &pernet->local_addr_list, list) {
-		if (addresses_equal(&entry->addr, &addr.addr, true)) {
-			mptcp_nl_addr_backup(net, &entry->addr, bkup);
+	if (token)
+		return mptcp_userspace_pm_set_flags(sock_net(skb->sk),
+						    token, &addr, &remote, bkup);
 
-			if (bkup)
-				entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
-			else
-				entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
-		}
+	spin_lock_bh(&pernet->lock);
+	entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
+	if (!entry) {
+		spin_unlock_bh(&pernet->lock);
+		return -EINVAL;
+	}
+	if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+	    (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+		spin_unlock_bh(&pernet->lock);
+		return -EINVAL;
 	}
 
+	changed = (addr.flags ^ entry->flags) & mask;
+	entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
+	addr = *entry;
+	spin_unlock_bh(&pernet->lock);
+
+	mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
 	return 0;
 }
 
@@ -1736,6 +1938,13 @@ static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gf
 				nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp);
 }
 
+bool mptcp_userspace_pm_active(const struct mptcp_sock *msk)
+{
+	return genl_has_listeners(&mptcp_genl_family,
+				  sock_net((const struct sock *)msk),
+				  MPTCP_PM_EV_GRP_OFFSET);
+}
+
 static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 {
 	const struct inet_sock *issk = inet_sk(ssk);
@@ -1856,6 +2065,9 @@ static int mptcp_event_created(struct sk_buff *skb,
 	if (err)
 		return err;
 
+	if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side)))
+		return -EMSGSIZE;
+
 	return mptcp_event_add_subflow(skb, ssk);
 }
 
@@ -1890,10 +2102,12 @@ nla_put_failure:
 	kfree_skb(skb);
 }
 
-void mptcp_event_addr_announced(const struct mptcp_sock *msk,
+void mptcp_event_addr_announced(const struct sock *ssk,
 				const struct mptcp_addr_info *info)
 {
-	struct net *net = sock_net((const struct sock *)msk);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	struct net *net = sock_net(ssk);
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
 
@@ -1915,7 +2129,10 @@ void mptcp_event_addr_announced(const struct mptcp_sock *msk,
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id))
 		goto nla_put_failure;
 
-	if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port))
+	if (nla_put_be16(skb, MPTCP_ATTR_DPORT,
+			 info->port == 0 ?
+			 inet_sk(ssk)->inet_dport :
+			 info->port))
 		goto nla_put_failure;
 
 	switch (info->family) {
@@ -2001,17 +2218,17 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_ADD_ADDR,
 		.doit   = mptcp_nl_cmd_add_addr,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_DEL_ADDR,
 		.doit   = mptcp_nl_cmd_del_addr,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_FLUSH_ADDRS,
 		.doit   = mptcp_nl_cmd_flush_addrs,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_GET_ADDR,
@@ -2021,7 +2238,7 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_SET_LIMITS,
 		.doit   = mptcp_nl_cmd_set_limits,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_GET_LIMITS,
@@ -2030,7 +2247,27 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_SET_FLAGS,
 		.doit   = mptcp_nl_cmd_set_flags,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd    = MPTCP_PM_CMD_ANNOUNCE,
+		.doit   = mptcp_nl_cmd_announce,
+		.flags  = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd    = MPTCP_PM_CMD_REMOVE,
+		.doit   = mptcp_nl_cmd_remove,
+		.flags  = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd    = MPTCP_PM_CMD_SUBFLOW_CREATE,
+		.doit   = mptcp_nl_cmd_sf_create,
+		.flags  = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd    = MPTCP_PM_CMD_SUBFLOW_DESTROY,
+		.doit   = mptcp_nl_cmd_sf_destroy,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 };
 
@@ -2043,13 +2280,14 @@ static struct genl_family mptcp_genl_family __ro_after_init = {
 	.module		= THIS_MODULE,
 	.small_ops	= mptcp_pm_ops,
 	.n_small_ops	= ARRAY_SIZE(mptcp_pm_ops),
+	.resv_start_op	= MPTCP_PM_CMD_SUBFLOW_DESTROY + 1,
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
 
 static int __net_init pm_nl_init_net(struct net *net)
 {
-	struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
 
 	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
 
@@ -2071,7 +2309,7 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list)
 	struct net *net;
 
 	list_for_each_entry(net, net_list, exit_list) {
-		struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
+		struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
 
 		/* net is removed from namespace list, can't race with
 		 * other modifiers, also netns core already waited for a