Merge branch 'next' into for-linus

Prepare input updates for 6.6 merge window.

9 files changed, 521 insertions, 387 deletions

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index d237d142171c..bceaab8dd8e4 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -9,11 +9,18 @@
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
 					      struct request_sock *req)
 {
-	struct sock *ssk = subflow->tcp_sock;
-	struct sock *sk = subflow->conn;
+	struct sock *sk, *ssk;
 	struct sk_buff *skb;
 	struct tcp_sock *tp;
 
+	/* on early fallback the subflow context is deleted by
+	 * subflow_syn_recv_sock()
+	 */
+	if (!subflow)
+		return;
+
+	ssk = subflow->tcp_sock;
+	sk = subflow->conn;
 	tp = tcp_sk(ssk);
 
 	subflow->is_mptfo = 1;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index b30cea2fbf3f..19a01b6566f1 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -442,7 +442,6 @@ static void clear_3rdack_retransmission(struct sock *sk)
 static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 					 bool snd_data_fin_enable,
 					 unsigned int *size,
-					 unsigned int remaining,
 					 struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -556,7 +555,6 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
 static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 					  bool snd_data_fin_enable,
 					  unsigned int *size,
-					  unsigned int remaining,
 					  struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -580,7 +578,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 			opts->ext_copy = *mpext;
 		}
 
-		remaining -= map_size;
 		dss_size = map_size;
 		if (skb && snd_data_fin_enable)
 			mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
@@ -851,9 +848,9 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 	}
 
 	snd_data_fin = mptcp_data_fin_enabled(msk);
-	if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
+	if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, opts))
 		ret = true;
-	else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) {
+	else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, opts)) {
 		unsigned int mp_fail_size;
 
 		ret = true;
@@ -1001,7 +998,7 @@ check_notify:
 		clear_3rdack_retransmission(ssk);
 		mptcp_pm_subflow_established(msk);
 	} else {
-		mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC);
+		mptcp_pm_fully_established(msk, ssk);
 	}
 	return true;
 
@@ -1192,9 +1189,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		if (mp_opt.data_fin && mp_opt.data_len == 1 &&
-		    mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) &&
-		    schedule_work(&msk->work))
-			sock_hold(subflow->conn);
+		    mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64))
+			mptcp_schedule_work((struct sock *)msk);
 
 		return true;
 	}
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 70f0ced3ca86..76612bca275a 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -87,8 +87,15 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 	unsigned int subflows_max;
 	int ret = 0;
 
-	if (mptcp_pm_is_userspace(msk))
-		return mptcp_userspace_pm_active(msk);
+	if (mptcp_pm_is_userspace(msk)) {
+		if (mptcp_userspace_pm_active(msk)) {
+			spin_lock_bh(&pm->lock);
+			pm->subflows++;
+			spin_unlock_bh(&pm->lock);
+			return true;
+		}
+		return false;
+	}
 
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
@@ -126,7 +133,7 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
 	return true;
 }
 
-void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp)
+void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
 	bool announce = false;
@@ -150,7 +157,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk,
 	spin_unlock_bh(&pm->lock);
 
 	if (announce)
-		mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, gfp);
+		mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, GFP_ATOMIC);
 }
 
 void mptcp_pm_connection_closed(struct mptcp_sock *msk)
@@ -181,8 +188,16 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 	struct mptcp_pm_data *pm = &msk->pm;
 	bool update_subflows;
 
-	update_subflows = (subflow->request_join || subflow->mp_join) &&
-			  mptcp_pm_is_kernel(msk);
+	update_subflows = subflow->request_join || subflow->mp_join;
+	if (mptcp_pm_is_userspace(msk)) {
+		if (update_subflows) {
+			spin_lock_bh(&pm->lock);
+			pm->subflows--;
+			spin_unlock_bh(&pm->lock);
+		}
+		return;
+	}
+
 	if (!READ_ONCE(pm->work_pending) && !update_subflows)
 		return;
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 56628b52d100..1224dfca5bf3 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -997,9 +997,13 @@ out:
 	return ret;
 }
 
+static struct lock_class_key mptcp_slock_keys[2];
+static struct lock_class_key mptcp_keys[2];
+
 static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 					    struct mptcp_pm_addr_entry *entry)
 {
+	bool is_ipv6 = sk->sk_family == AF_INET6;
 	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
 	struct socket *ssock;
@@ -1016,11 +1020,23 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (!newsk)
 		return -EINVAL;
 
+	/* The subflow socket lock is acquired in a nested to the msk one
+	 * in several places, even by the TCP stack, and this msk is a kernel
+	 * socket: lockdep complains. Instead of propagating the _nested
+	 * modifiers in several places, re-init the lock class for the msk
+	 * socket to an mptcp specific one.
+	 */
+	sock_lock_init_class_and_name(newsk,
+				      is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET",
+				      &mptcp_slock_keys[is_ipv6],
+				      is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET",
+				      &mptcp_keys[is_ipv6]);
+
 	lock_sock(newsk);
 	ssock = __mptcp_nmpc_socket(mptcp_sk(newsk));
 	release_sock(newsk);
-	if (!ssock)
-		return -EINVAL;
+	if (IS_ERR(ssock))
+		return PTR_ERR(ssock);
 
 	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -1031,6 +1047,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	if (err)
 		return err;
 
+	inet_sk_state_store(newsk, TCP_LISTEN);
 	err = kernel_listen(ssock, backlog);
 	if (err)
 		return err;
@@ -1542,6 +1559,24 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
+void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
+{
+	struct mptcp_rm_list alist = { .nr = 0 };
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry(entry, rm_list, list) {
+		remove_anno_list_by_saddr(msk, &entry->addr);
+		if (alist.nr < MPTCP_RM_IDS_MAX)
+			alist.ids[alist.nr++] = entry->addr.id;
+	}
+
+	if (alist.nr) {
+		spin_lock_bh(&msk->pm.lock);
+		mptcp_pm_remove_addr(msk, &alist);
+		spin_unlock_bh(&msk->pm.lock);
+	}
+}
+
 void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 					struct list_head *rm_list)
 {
@@ -2019,7 +2054,7 @@ static int mptcp_event_put_token_and_ssk(struct sk_buff *skb,
 	    nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if))
 		return -EMSGSIZE;
 
-	sk_err = ssk->sk_err;
+	sk_err = READ_ONCE(ssk->sk_err);
 	if (sk_err && sk->sk_state == TCP_ESTABLISHED &&
 	    nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err))
 		return -EMSGSIZE;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index a02d3cbf2a1b..b06aa58dfcf2 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -25,8 +25,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk)
 	}
 }
 
-int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
-					     struct mptcp_pm_addr_entry *entry)
+static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
+						    struct mptcp_pm_addr_entry *entry)
 {
 	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	struct mptcp_pm_addr_entry *match = NULL;
@@ -69,6 +69,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 							MPTCP_PM_MAX_ADDR_ID + 1,
 							1);
 		list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list);
+		msk->pm.local_addr_used++;
 		ret = e->addr.id;
 	} else if (match) {
 		ret = entry->addr.id;
@@ -79,6 +80,31 @@ append_err:
 	return ret;
 }
 
+/* If the subflow is closed from the other peer (not via a
+ * subflow destroy command then), we want to keep the entry
+ * not to assign the same ID to another address and to be
+ * able to send RM_ADDR after the removal of the subflow.
+ */
+static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk,
+						struct mptcp_pm_addr_entry *addr)
+{
+	struct mptcp_pm_addr_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) {
+			/* TODO: a refcount is needed because the entry can
+			 * be used multiple times (e.g. fullmesh mode).
+			 */
+			list_del_rcu(&entry->list);
+			kfree(entry);
+			msk->pm.local_addr_used--;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
 int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
 						   unsigned int id,
 						   u8 *flags, int *ifindex)
@@ -171,6 +197,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info)
 	spin_lock_bh(&msk->pm.lock);
 
 	if (mptcp_pm_alloc_anno_list(msk, &addr_val)) {
+		msk->pm.add_addr_signaled++;
 		mptcp_pm_announce_addr(msk, &addr_val.addr, false);
 		mptcp_pm_nl_addr_send_ack(msk);
 	}
@@ -232,7 +259,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info)
 
 	list_move(&match->list, &free_list);
 
-	mptcp_pm_remove_addrs_and_subflows(msk, &free_list);
+	mptcp_pm_remove_addrs(msk, &free_list);
 
 	release_sock((struct sock *)msk);
 
@@ -251,6 +278,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
+	struct mptcp_pm_addr_entry local = { 0 };
 	struct mptcp_addr_info addr_r;
 	struct mptcp_addr_info addr_l;
 	struct mptcp_sock *msk;
@@ -302,12 +330,26 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
 		goto create_err;
 	}
 
+	local.addr = addr_l;
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &local);
+	if (err < 0) {
+		GENL_SET_ERR_MSG(info, "did not match address and id");
+		goto create_err;
+	}
+
 	lock_sock(sk);
 
 	err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
 
 	release_sock(sk);
 
+	spin_lock_bh(&msk->pm.lock);
+	if (err)
+		mptcp_userspace_pm_delete_local_addr(msk, &local);
+	else
+		msk->pm.subflows++;
+	spin_unlock_bh(&msk->pm.lock);
+
  create_err:
 	sock_put((struct sock *)msk);
 	return err;
@@ -420,7 +462,11 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
 	ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r);
 	if (ssk) {
 		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+		struct mptcp_pm_addr_entry entry = { .addr = addr_l };
 
+		spin_lock_bh(&msk->pm.lock);
+		mptcp_userspace_pm_delete_local_addr(msk, &entry);
+		spin_unlock_bh(&msk->pm.lock);
 		mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN);
 		mptcp_close_ssk(sk, ssk, subflow);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ad9c46202fc..a6c7f2d24909 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -44,23 +44,11 @@ enum {
 static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;
 
 static void __mptcp_destroy_sock(struct sock *sk);
-static void __mptcp_check_send_data_fin(struct sock *sk);
+static void mptcp_check_send_data_fin(struct sock *sk);
 
 DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 static struct net_device mptcp_napi_dev;
 
-/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
- * completed yet or has failed, return the subflow socket.
- * Otherwise return NULL.
- */
-struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
-{
-	if (!msk->subflow || READ_ONCE(msk->can_ack))
-		return NULL;
-
-	return msk->subflow;
-}
-
 /* Returns end sequence number of the receiver's advertised window */
 static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 {
@@ -102,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	if (err)
 		return err;
 
-	msk->first = ssock->sk;
-	msk->subflow = ssock;
+	WRITE_ONCE(msk->first, ssock->sk);
+	WRITE_ONCE(msk->subflow, ssock);
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssock->sk);
@@ -116,6 +104,31 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
+/* If the MPC handshake is not started, returns the first subflow,
+ * eventually allocating it.
+ */
+struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+	int ret;
+
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+		return ERR_PTR(-EINVAL);
+
+	if (!msk->subflow) {
+		if (msk->first)
+			return ERR_PTR(-EINVAL);
+
+		ret = __mptcp_socket_create(msk);
+		if (ret)
+			return ERR_PTR(ret);
+
+		mptcp_sockopt_sync(msk, msk->first);
+	}
+
+	return msk->subflow;
+}
+
 static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -411,8 +424,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	return !__mptcp_check_fallback(msk) &&
-	       ((1 << sk->sk_state) &
+	return ((1 << sk->sk_state) &
 		(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
 	       msk->write_seq == READ_ONCE(msk->snd_una);
 }
@@ -459,7 +471,7 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
 	return false;
 }
 
-static void mptcp_set_datafin_timeout(const struct sock *sk)
+static void mptcp_set_datafin_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 retransmits;
@@ -570,9 +582,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
 	u64 rcv_data_fin_seq;
 	bool ret = false;
 
-	if (__mptcp_check_fallback(msk))
-		return ret;
-
 	/* Need to ack a DATA_FIN received from a peer while this side
 	 * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
 	 * msk->rcv_data_fin was set when parsing the incoming options
@@ -590,7 +599,7 @@ static bool mptcp_check_data_fin(struct sock *sk)
 		WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
 		WRITE_ONCE(msk->rcv_data_fin, 0);
 
-		sk->sk_shutdown |= RCV_SHUTDOWN;
+		WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 
 		switch (sk->sk_state) {
@@ -610,7 +619,8 @@ static bool mptcp_check_data_fin(struct sock *sk)
 		}
 
 		ret = true;
-		mptcp_send_ack(msk);
+		if (!__mptcp_check_fallback(msk))
+			mptcp_send_ack(msk);
 		mptcp_close_wake_up(sk);
 	}
 	return ret;
@@ -812,6 +822,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	mptcp_data_unlock(sk);
 }
 
+static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk)
+{
+	mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq);
+	WRITE_ONCE(msk->allow_infinite_fallback, false);
+	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
+}
+
 static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -825,17 +842,17 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 	if (sk->sk_socket && !ssk->sk_socket)
 		mptcp_sock_graft(ssk, sk->sk_socket);
 
-	mptcp_propagate_sndbuf((struct sock *)msk, ssk);
 	mptcp_sockopt_sync_locked(msk, ssk);
+	mptcp_subflow_joined(msk, ssk);
 	return true;
 }
 
-static void __mptcp_flush_join_list(struct sock *sk)
+static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list)
 {
 	struct mptcp_subflow_context *tmp, *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) {
+	list_for_each_entry_safe(subflow, tmp, join_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast(ssk);
 
@@ -877,49 +894,6 @@ bool mptcp_schedule_work(struct sock *sk)
 	return false;
 }
 
-void mptcp_subflow_eof(struct sock *sk)
-{
-	if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
-		mptcp_schedule_work(sk);
-}
-
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	int receivers = 0;
-
-	mptcp_for_each_subflow(msk, subflow)
-		receivers += !subflow->rx_eof;
-	if (receivers)
-		return;
-
-	if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
-		/* hopefully temporary hack: propagate shutdown status
-		 * to msk, when all subflows agree on it
-		 */
-		sk->sk_shutdown |= RCV_SHUTDOWN;
-
-		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		sk->sk_data_ready(sk);
-	}
-
-	switch (sk->sk_state) {
-	case TCP_ESTABLISHED:
-		inet_sk_state_store(sk, TCP_CLOSE_WAIT);
-		break;
-	case TCP_FIN_WAIT1:
-		inet_sk_state_store(sk, TCP_CLOSING);
-		break;
-	case TCP_FIN_WAIT2:
-		inet_sk_state_store(sk, TCP_CLOSE);
-		break;
-	default:
-		return;
-	}
-	mptcp_close_wake_up(sk);
-}
-
 static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1589,7 +1563,7 @@ out:
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
 	if (do_check_data_fin)
-		__mptcp_check_send_data_fin(sk);
+		mptcp_check_send_data_fin(sk);
 }
 
 static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
@@ -1663,16 +1637,33 @@ static void mptcp_set_nospace(struct sock *sk)
 
 static int mptcp_disconnect(struct sock *sk, int flags);
 
-static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
+static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				  size_t len, int *copied_syn)
 {
 	unsigned int saved_flags = msg->msg_flags;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct socket *ssock;
+	struct sock *ssk;
 	int ret;
 
+	/* on flags based fastopen the mptcp is supposed to create the
+	 * first subflow right now. Otherwise we are in the defer_connect
+	 * path, and the first subflow must be already present.
+	 * Since the defer_connect flag is cleared after the first succsful
+	 * fastopen attempt, no need to check for additional subflow status.
+	 */
+	if (msg->msg_flags & MSG_FASTOPEN) {
+		ssock = __mptcp_nmpc_socket(msk);
+		if (IS_ERR(ssock))
+			return PTR_ERR(ssock);
+	}
+	if (!msk->first)
+		return -EINVAL;
+
+	ssk = msk->first;
+
 	lock_sock(ssk);
 	msg->msg_flags |= MSG_DONTWAIT;
-	msk->connect_flags = O_NONBLOCK;
 	msk->fastopening = 1;
 	ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
 	msk->fastopening = 0;
@@ -1690,8 +1681,15 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
 		if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
 			*copied_syn = 0;
 	} else if (ret && ret != -EINPROGRESS) {
-		mptcp_disconnect(sk, 0);
+		/* The disconnect() op called by tcp_sendmsg_fastopen()/
+		 * __inet_stream_connect() can fail, due to looking check,
+		 * see mptcp_disconnect().
+		 * Attempt it again outside the problematic scope.
+		 */
+		if (!mptcp_disconnect(sk, 0))
+			sk->sk_socket->state = SS_UNCONNECTED;
 	}
+	inet_sk(sk)->defer_connect = 0;
 
 	return ret;
 }
@@ -1700,7 +1698,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct page_frag *pfrag;
-	struct socket *ssock;
 	size_t copied = 0;
 	int ret = 0;
 	long timeo;
@@ -1710,12 +1707,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	lock_sock(sk);
 
-	ssock = __mptcp_nmpc_socket(msk);
-	if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect ||
-			       msg->msg_flags & MSG_FASTOPEN))) {
+	if (unlikely(inet_sk(sk)->defer_connect || msg->msg_flags & MSG_FASTOPEN)) {
 		int copied_syn = 0;
 
-		ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
+		ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn);
 		copied += copied_syn;
 		if (ret == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -2123,9 +2118,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 				break;
 			}
 
-			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
-				mptcp_check_for_eof(msk);
-
 			if (sk->sk_shutdown & RCV_SHUTDOWN) {
 				/* race breaker: the shutdown could be after the
 				 * previous receive queue check
@@ -2255,7 +2247,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
 {
 	if (msk->subflow) {
 		iput(SOCK_INODE(msk->subflow));
-		msk->subflow = NULL;
+		WRITE_ONCE(msk->subflow, NULL);
 	}
 }
 
@@ -2316,7 +2308,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 			      unsigned int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	bool need_push, dispose_it;
+	bool dispose_it, need_push = false;
+
+	/* If the first subflow moved to a close state before accept, e.g. due
+	 * to an incoming reset, mptcp either:
+	 * - if either the subflow or the msk are dead, destroy the context
+	 *   (the subflow socket is deleted by inet_child_forget) and the msk
+	 * - otherwise do nothing at the moment and take action at accept and/or
+	 *   listener shutdown - user-space must be able to accept() the closed
+	 *   socket.
+	 */
+	if (msk->in_accept_queue && msk->first == ssk) {
+		if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD))
+			return;
+
+		/* ensure later check in mptcp_worker() will dispose the msk */
+		sock_set_flag(sk, SOCK_DEAD);
+		lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+		mptcp_subflow_drop_ctx(ssk);
+		goto out_release;
+	}
 
 	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
 	if (dispose_it)
@@ -2335,7 +2346,10 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
-		tcp_disconnect(ssk, 0);
+		/* The MPTCP code never wait on the subflow sockets, TCP-level
+		 * disconnect should never fail
+		 */
+		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
 		msk->subflow->state = SS_UNCONNECTED;
 		mptcp_subflow_ctx_reset(subflow);
 		release_sock(ssk);
@@ -2343,7 +2357,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		goto out;
 	}
 
-	sock_orphan(ssk);
 	subflow->disposable = 1;
 
 	/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
@@ -2351,26 +2364,23 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	 * reference owned by msk;
 	 */
 	if (!inet_csk(ssk)->icsk_ulp_ops) {
+		WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD));
 		kfree_rcu(subflow, rcu);
 	} else {
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
-		if (ssk->sk_state == TCP_LISTEN) {
-			tcp_set_state(ssk, TCP_CLOSE);
-			mptcp_subflow_queue_clean(sk, ssk);
-			inet_csk_listen_stop(ssk);
-			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
-		}
 		__tcp_close(ssk, 0);
 
 		/* close acquired an extra ref */
 		__sock_put(ssk);
 	}
+
+out_release:
 	release_sock(ssk);
 
 	sock_put(ssk);
 
 	if (ssk == msk->first)
-		msk->first = NULL;
+		WRITE_ONCE(msk->first, NULL);
 
 out:
 	if (ssk == msk->last_snd)
@@ -2399,9 +2409,10 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
 	return 0;
 }
 
-static void __mptcp_close_subflow(struct mptcp_sock *msk)
+static void __mptcp_close_subflow(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	might_sleep();
 
@@ -2415,16 +2426,17 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
 		if (!skb_queue_empty_lockless(&ssk->sk_receive_queue))
 			continue;
 
-		mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+		mptcp_close_ssk(sk, ssk, subflow);
 	}
+
 }
 
-static bool mptcp_check_close_timeout(const struct sock *sk)
+static bool mptcp_should_close(const struct sock *sk)
 {
 	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
 	struct mptcp_subflow_context *subflow;
 
-	if (delta >= TCP_TIMEWAIT_LEN)
+	if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue)
 		return true;
 
 	/* if all subflows are in closed status don't bother with additional
@@ -2463,19 +2475,19 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	/* Mirror the tcp_reset() error propagation */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
-		sk->sk_err = ECONNREFUSED;
+		WRITE_ONCE(sk->sk_err, ECONNREFUSED);
 		break;
 	case TCP_CLOSE_WAIT:
-		sk->sk_err = EPIPE;
+		WRITE_ONCE(sk->sk_err, EPIPE);
 		break;
 	case TCP_CLOSE:
 		return;
 	default:
-		sk->sk_err = ECONNRESET;
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	}
 
 	inet_sk_state_store(sk, TCP_CLOSE);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
 
@@ -2609,27 +2621,26 @@ static void mptcp_worker(struct work_struct *work)
 
 	lock_sock(sk);
 	state = sk->sk_state;
-	if (unlikely(state == TCP_CLOSE))
+	if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		goto unlock;
 
-	mptcp_check_data_fin_ack(sk);
-
 	mptcp_check_fastclose(msk);
 
 	mptcp_pm_nl_work(msk);
 
-	if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
-		mptcp_check_for_eof(msk);
-
-	__mptcp_check_send_data_fin(sk);
+	mptcp_check_send_data_fin(sk);
+	mptcp_check_data_fin_ack(sk);
 	mptcp_check_data_fin(sk);
 
+	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		__mptcp_close_subflow(sk);
+
 	/* There is no point in keeping around an orphaned sk timedout or
 	 * closed, but we need the msk around to reply to incoming DATA_FIN,
 	 * even if it is orphaned and in FIN_WAIT2 state
 	 */
 	if (sock_flag(sk, SOCK_DEAD)) {
-		if (mptcp_check_close_timeout(sk)) {
+		if (mptcp_should_close(sk)) {
 			inet_sk_state_store(sk, TCP_CLOSE);
 			mptcp_do_fastclose(sk);
 		}
@@ -2639,9 +2650,6 @@ static void mptcp_worker(struct work_struct *work)
 		}
 	}
 
-	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
-		__mptcp_close_subflow(msk);
-
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
@@ -2669,7 +2677,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	WRITE_ONCE(msk->rmem_released, 0);
 	msk->timer_ival = TCP_RTO_MIN;
 
-	msk->first = NULL;
+	WRITE_ONCE(msk->first, NULL);
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
 	WRITE_ONCE(msk->allow_infinite_fallback, true);
@@ -2711,10 +2719,6 @@ static int mptcp_init_sock(struct sock *sk)
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
-	ret = __mptcp_socket_create(mptcp_sk(sk));
-	if (ret)
-		return ret;
-
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 
 	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
@@ -2757,13 +2761,19 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 			break;
 		fallthrough;
 	case TCP_SYN_SENT:
-		tcp_disconnect(ssk, O_NONBLOCK);
+		WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK));
 		break;
 	default:
 		if (__mptcp_check_fallback(mptcp_sk(sk))) {
 			pr_debug("Fallback");
 			ssk->sk_shutdown |= how;
 			tcp_shutdown(ssk, how);
+
+			/* simulate the data_fin ack reception to let the state
+			 * machine move forward
+			 */
+			WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
+			mptcp_schedule_work(sk);
 		} else {
 			pr_debug("Sending DATA_FIN on subflow %p", ssk);
 			tcp_send_ack(ssk);
@@ -2803,7 +2813,7 @@ static int mptcp_close_state(struct sock *sk)
 	return next & TCP_ACTION_FIN;
 }
 
-static void __mptcp_check_send_data_fin(struct sock *sk)
+static void mptcp_check_send_data_fin(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -2821,19 +2831,6 @@ 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 the next
-	 * state now
-	 */
-	if (__mptcp_check_fallback(msk)) {
-		WRITE_ONCE(msk->snd_una, msk->write_seq);
-		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_for_each_subflow(msk, subflow) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
@@ -2853,7 +2850,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
 	WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
 	WRITE_ONCE(msk->snd_data_fin_enable, 1);
 
-	__mptcp_check_send_data_fin(sk);
+	mptcp_check_send_data_fin(sk);
 }
 
 static void __mptcp_destroy_sock(struct sock *sk)
@@ -2878,6 +2875,14 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
+void __mptcp_unaccepted_force_close(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_DEAD);
+	inet_sk_state_store(sk, TCP_CLOSE);
+	mptcp_do_fastclose(sk);
+	__mptcp_destroy_sock(sk);
+}
+
 static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 {
 	/* Concurrent splices from sk_receive_queue into receive_queue will
@@ -2890,10 +2895,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 	return EPOLLIN | EPOLLRDNORM;
 }
 
-static void mptcp_listen_inuse_dec(struct sock *sk)
+static void mptcp_check_listen_stop(struct sock *sk)
 {
-	if (inet_sk_state_load(sk) == TCP_LISTEN)
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	struct sock *ssk;
+
+	if (inet_sk_state_load(sk) != TCP_LISTEN)
+		return;
+
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+	ssk = mptcp_sk(sk)->first;
+	if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN))
+		return;
+
+	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+	mptcp_subflow_queue_clean(sk, ssk);
+	inet_csk_listen_stop(ssk);
+	mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
+	tcp_set_state(ssk, TCP_CLOSE);
+	release_sock(ssk);
 }
 
 bool __mptcp_close(struct sock *sk, long timeout)
@@ -2903,18 +2922,21 @@ bool __mptcp_close(struct sock *sk, long timeout)
 	bool do_cancel_work = false;
 	int subflows_alive = 0;
 
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
-		mptcp_listen_inuse_dec(sk);
+		mptcp_check_listen_stop(sk);
 		inet_sk_state_store(sk, TCP_CLOSE);
 		goto cleanup;
 	}
 
-	if (mptcp_check_readable(msk)) {
-		/* the msk has read data, do the MPTCP equivalent of TCP reset */
+	if (mptcp_check_readable(msk) || timeout < 0) {
+		/* If the msk has read data, or the caller explicitly ask it,
+		 * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
+		 */
 		inet_sk_state_store(sk, TCP_CLOSE);
 		mptcp_do_fastclose(sk);
+		timeout = 0;
 	} else if (mptcp_close_state(sk)) {
 		__mptcp_wr_shutdown(sk);
 	}
@@ -2980,7 +3002,7 @@ static void mptcp_close(struct sock *sk, long timeout)
 	sock_put(sk);
 }
 
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
+static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
@@ -3007,15 +3029,20 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	/* Deny disconnect if other threads are blocked in sk_wait_event()
+	 * or inet_wait_for_connect().
+	 */
+	if (sk->sk_wait_pending)
+		return -EBUSY;
+
 	/* We are on the fastopen error path. We can't call straight into the
 	 * subflows cleanup code due to lock nesting (we are already under
-	 * msk->firstsocket lock). Do nothing and leave the cleanup to the
-	 * caller.
+	 * msk->firstsocket lock).
 	 */
 	if (msk->fastopening)
-		return 0;
+		return -EBUSY;
 
-	mptcp_listen_inuse_dec(sk);
+	mptcp_check_listen_stop(sk);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
 	mptcp_stop_timer(sk);
@@ -3043,7 +3070,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_pm_data_reset(msk);
 	mptcp_ca_reset(sk);
 
-	sk->sk_shutdown = 0;
+	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
 	return 0;
 }
@@ -3057,9 +3084,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 }
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct mptcp_options_received *mp_opt,
-			    struct request_sock *req)
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+				 const struct mptcp_options_received *mp_opt,
+				 struct sock *ssk,
+				 struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
@@ -3073,12 +3101,14 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 		inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
 #endif
 
+	nsk->sk_wait_pending = 0;
 	__mptcp_init_sock(nsk);
 
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
-	msk->subflow = NULL;
+	WRITE_ONCE(msk->subflow, NULL);
+	msk->in_accept_queue = 1;
 	WRITE_ONCE(msk->fully_established, false);
 	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
 		WRITE_ONCE(msk->csum_enabled, true);
@@ -3090,14 +3120,33 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
-	/* will be fully established after successful MPC subflow creation */
-	inet_sk_state_store(nsk, TCP_SYN_RECV);
-
 	security_inet_csk_clone(nsk, req);
+
+	/* this can't race with mptcp_close(), as the msk is
+	 * not yet exposted to user-space
+	 */
+	inet_sk_state_store(nsk, TCP_ESTABLISHED);
+
+	/* The msk maintain a ref to each subflow in the connections list */
+	WRITE_ONCE(msk->first, ssk);
+	list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+	sock_hold(ssk);
+
+	/* new mpc subflow takes ownership of the newly
+	 * created mptcp socket
+	 */
+	mptcp_token_accept(subflow_req, msk);
+
+	/* set msk addresses early to ensure mptcp_pm_get_local_id()
+	 * uses the correct data
+	 */
+	mptcp_copy_inaddrs(nsk, ssk);
+	mptcp_propagate_sndbuf(nsk, ssk);
+
+	mptcp_rcv_space_init(msk, ssk);
 	bh_unlock_sock(nsk);
 
-	/* keep a single reference */
-	__sock_put(nsk);
+	/* note: the newly allocated socket refcount is 2 now */
 	return nsk;
 }
 
@@ -3126,7 +3175,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	struct socket *listener;
 	struct sock *newsk;
 
-	listener = __mptcp_nmpc_socket(msk);
+	listener = READ_ONCE(msk->subflow);
 	if (WARN_ON_ONCE(!listener)) {
 		*err = -EINVAL;
 		return NULL;
@@ -3153,8 +3202,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 			goto out;
 		}
 
-		/* acquire the 2nd reference for the owning socket */
-		sock_hold(new_mptcp_sock);
 		newsk = new_mptcp_sock;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
@@ -3242,9 +3289,14 @@ static void mptcp_release_cb(struct sock *sk)
 	for (;;) {
 		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
 				      msk->push_pending;
+		struct list_head join_list;
+
 		if (!flags)
 			break;
 
+		INIT_LIST_HEAD(&join_list);
+		list_splice_init(&msk->join_list, &join_list);
+
 		/* the following actions acquire the subflow socket lock
 		 *
 		 * 1) can't be invoked in atomic scope
@@ -3255,8 +3307,9 @@ static void mptcp_release_cb(struct sock *sk)
 		msk->push_pending = 0;
 		msk->cb_flags &= ~flags;
 		spin_unlock_bh(&sk->sk_lock.slock);
+
 		if (flags & BIT(MPTCP_FLUSH_JOIN_LIST))
-			__mptcp_flush_join_list(sk);
+			__mptcp_flush_join_list(sk, &join_list);
 		if (flags & BIT(MPTCP_PUSH_PENDING))
 			__mptcp_push_pending(sk, 0);
 		if (flags & BIT(MPTCP_RETRANSMIT))
@@ -3348,7 +3401,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct socket *ssock;
 
-	ssock = __mptcp_nmpc_socket(msk);
+	ssock = msk->subflow;
 	pr_debug("msk=%p, subflow=%p", msk, ssock);
 	if (WARN_ON_ONCE(!ssock))
 		return -EINVAL;
@@ -3408,14 +3461,16 @@ bool mptcp_finish_join(struct sock *ssk)
 		return false;
 	}
 
-	if (!list_empty(&subflow->node))
-		goto out;
+	/* active subflow, already present inside the conn_list */
+	if (!list_empty(&subflow->node)) {
+		mptcp_subflow_joined(msk, ssk);
+		return true;
+	}
 
 	if (!mptcp_pm_allow_new_subflow(msk))
 		goto err_prohibited;
 
-	/* active connections are already on conn_list.
-	 * If we can't acquire msk socket lock here, let the release callback
+	/* If we can't acquire msk socket lock here, let the release callback
 	 * handle it
 	 */
 	mptcp_data_lock(parent);
@@ -3438,11 +3493,6 @@ err_prohibited:
 		return false;
 	}
 
-	subflow->map_seq = READ_ONCE(msk->ack_seq);
-	WRITE_ONCE(msk->allow_infinite_fallback, false);
-
-out:
-	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
 	return true;
 }
 
@@ -3536,8 +3586,8 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int err = -EINVAL;
 
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock)
-		return -EINVAL;
+	if (IS_ERR(ssock))
+		return PTR_ERR(ssock);
 
 	mptcp_token_destroy(msk);
 	inet_sk_state_store(sk, TCP_SYN_SENT);
@@ -3560,9 +3610,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	 * acquired the subflow socket lock, too.
 	 */
 	if (msk->fastopening)
-		err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
+		err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1);
 	else
-		err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
+		err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK);
 	inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
 
 	/* on successful connect, the msk state will be moved to established by
@@ -3575,12 +3625,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	mptcp_copy_inaddrs(sk, ssock->sk);
 
-	/* unblocking connect, mptcp-level inet_stream_connect will error out
-	 * without changing the socket state, update it here.
+	/* silence EINPROGRESS and let the caller inet_stream_connect
+	 * handle the connection in progress
 	 */
-	if (err == -EINPROGRESS)
-		sk->sk_socket->state = ssock->state;
-	return err;
+	return 0;
 }
 
 static struct proto mptcp_prot = {
@@ -3625,8 +3673,8 @@ static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	lock_sock(sock->sk);
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock) {
-		err = -EINVAL;
+	if (IS_ERR(ssock)) {
+		err = PTR_ERR(ssock);
 		goto unlock;
 	}
 
@@ -3639,18 +3687,6 @@ unlock:
 	return err;
 }
 
-static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
-				int addr_len, int flags)
-{
-	int ret;
-
-	lock_sock(sock->sk);
-	mptcp_sk(sock->sk)->connect_flags = flags;
-	ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
-	release_sock(sock->sk);
-	return ret;
-}
-
 static int mptcp_listen(struct socket *sock, int backlog)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
@@ -3662,8 +3698,8 @@ static int mptcp_listen(struct socket *sock, int backlog)
 
 	lock_sock(sk);
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock) {
-		err = -EINVAL;
+	if (IS_ERR(ssock)) {
+		err = PTR_ERR(ssock);
 		goto unlock;
 	}
 
@@ -3694,7 +3730,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 
 	pr_debug("msk=%p", msk);
 
-	ssock = __mptcp_nmpc_socket(msk);
+	/* Buggy applications can call accept on socket states other then LISTEN
+	 * but no need to allocate the first subflow just to error out.
+	 */
+	ssock = READ_ONCE(msk->subflow);
 	if (!ssock)
 		return -EINVAL;
 
@@ -3705,25 +3744,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		struct sock *newsk = newsock->sk;
 
 		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+		msk->in_accept_queue = 0;
 
 		lock_sock(newsk);
 
-		/* PM/worker can now acquire the first subflow socket
-		 * lock without racing with listener queue cleanup,
-		 * we can notify it, if needed.
-		 *
-		 * Even if remote has reset the initial subflow by now
-		 * the refcnt is still at least one.
-		 */
-		subflow = mptcp_subflow_ctx(msk->first);
-		list_add(&subflow->node, &msk->conn_list);
-		sock_hold(msk->first);
-		if (mptcp_is_fully_established(newsk))
-			mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL);
-
-		mptcp_rcv_space_init(msk, msk->first);
-		mptcp_propagate_sndbuf(newsk, 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.
 		 */
@@ -3733,6 +3757,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+
+		/* Do late cleanup for the first subflow as necessary. Also
+		 * deal with bad peers not doing a complete shutdown.
+		 */
+		if (msk->first &&
+		    unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
+			__mptcp_close_ssk(newsk, msk->first,
+					  mptcp_subflow_ctx(msk->first), 0);
+			if (unlikely(list_empty(&msk->conn_list)))
+				inet_sk_state_store(newsk, TCP_CLOSE);
+		}
+
 		release_sock(newsk);
 	}
 
@@ -3743,9 +3779,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
 
-	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
-		return EPOLLOUT | EPOLLWRNORM;
-
 	if (sk_stream_is_writeable(sk))
 		return EPOLLOUT | EPOLLWRNORM;
 
@@ -3763,6 +3796,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct mptcp_sock *msk;
 	__poll_t mask = 0;
+	u8 shutdown;
 	int state;
 
 	msk = mptcp_sk(sk);
@@ -3771,27 +3805,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	state = inet_sk_state_load(sk);
 	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN) {
-		if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk))
+		struct socket *ssock = READ_ONCE(msk->subflow);
+
+		if (WARN_ON_ONCE(!ssock || !ssock->sk))
 			return 0;
 
-		return inet_csk_listen_poll(msk->subflow->sk);
+		return inet_csk_listen_poll(ssock->sk);
 	}
 
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+		mask |= EPOLLHUP;
+	if (shutdown & RCV_SHUTDOWN)
+		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
-		mask |= mptcp_check_writeable(msk);
+		if (shutdown & SEND_SHUTDOWN)
+			mask |= EPOLLOUT | EPOLLWRNORM;
+		else
+			mask |= mptcp_check_writeable(msk);
 	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
 		/* cf tcp_poll() note about TFO */
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
-	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
-		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
-		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
 	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
 	smp_rmb();
-	if (sk->sk_err)
+	if (READ_ONCE(sk->sk_err))
 		mask |= EPOLLERR;
 
 	return mask;
@@ -3802,7 +3843,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,
 	.bind		   = mptcp_bind,
-	.connect	   = mptcp_stream_connect,
+	.connect	   = inet_stream_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = mptcp_stream_accept,
 	.getname	   = inet_getname,
@@ -3897,7 +3938,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = mptcp_bind,
-	.connect	   = mptcp_stream_connect,
+	.connect	   = inet_stream_connect,
 	.socketpair	   = sock_no_socketpair,
 	.accept		   = mptcp_stream_accept,
 	.getname	   = inet6_getname,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 61fd8eabfca2..d3783a7056e1 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -113,7 +113,6 @@
 /* MPTCP socket atomic flags */
 #define MPTCP_NOSPACE		1
 #define MPTCP_WORK_RTX		2
-#define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
 #define MPTCP_WORK_CLOSE_SUBFLOW 5
 
@@ -295,8 +294,8 @@ struct mptcp_sock {
 	u8		recvmsg_inq:1,
 			cork:1,
 			nodelay:1,
-			fastopening:1;
-	int		connect_flags;
+			fastopening:1,
+			in_accept_queue:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -305,7 +304,11 @@ struct mptcp_sock {
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
+	struct socket	*subflow; /* outgoing connect/listener/!mp_capable
+				   * The mptcp ops can safely dereference, using suitable
+				   * ONCE annotation, the subflow outside the socket
+				   * lock as such sock is freed after close().
+				   */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
 	struct {
@@ -333,10 +336,7 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk)
 	sock_owned_by_me((const struct sock *)msk);
 }
 
-static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
-{
-	return (struct mptcp_sock *)sk;
-}
+#define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk)
 
 /* the msk socket don't use the backlog, also account for the bulk
  * free memory
@@ -370,7 +370,7 @@ static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
 
 static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
+	const struct mptcp_sock *msk = mptcp_sk(sk);
 
 	if (!msk->first_pending)
 		return NULL;
@@ -381,7 +381,7 @@ static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
 	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
 }
 
-static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk)
+static inline struct mptcp_data_frag *mptcp_rtx_head(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
@@ -475,14 +475,13 @@ struct mptcp_subflow_context {
 		send_mp_fail : 1,
 		send_fastclose : 1,
 		send_infinite_map : 1,
-		rx_eof : 1,
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
 		local_id_valid : 1, /* local_id is correctly initialized */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
-		__unused : 8;
+		__unused : 9;
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -615,7 +614,6 @@ int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 int mptcp_get_pm_type(const struct net *net);
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     const struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
@@ -630,9 +628,10 @@ void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
-struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
+struct socket *__mptcp_nmpc_socket(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
+void __mptcp_unaccepted_force_close(struct sock *sk);
 void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
@@ -666,6 +665,8 @@ void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow);
 
 bool mptcp_subflow_active(struct mptcp_subflow_context *subflow);
 
+void mptcp_subflow_drop_ctx(struct sock *ssk);
+
 static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 					      struct mptcp_subflow_context *ctx)
 {
@@ -682,9 +683,10 @@ void __init mptcp_proto_init(void);
 int __init mptcp_proto_v6_init(void);
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct mptcp_options_received *mp_opt,
-			    struct request_sock *req);
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+				 const struct mptcp_options_received *mp_opt,
+				 struct sock *ssk,
+				 struct request_sock *req);
 void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
@@ -716,7 +718,6 @@ static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
 void __mptcp_check_push(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void __mptcp_error_report(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);
 static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
 {
@@ -783,7 +784,7 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
-void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp);
+void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
 void mptcp_pm_connection_closed(struct mptcp_sock *msk);
 void mptcp_pm_subflow_established(struct mptcp_sock *msk);
@@ -828,11 +829,10 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   bool echo);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
 int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
+void mptcp_pm_remove_addrs(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);
 
-int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
-					     struct mptcp_pm_addr_entry *entry);
 void mptcp_free_local_addr_list(struct mptcp_sock *msk);
 int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info);
 int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 8a9656248b0f..d4258869ac48 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -301,9 +301,9 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 	case SO_BINDTOIFINDEX:
 		lock_sock(sk);
 		ssock = __mptcp_nmpc_socket(msk);
-		if (!ssock) {
+		if (IS_ERR(ssock)) {
 			release_sock(sk);
-			return -EINVAL;
+			return PTR_ERR(ssock);
 		}
 
 		ret = sock_setsockopt(ssock, SOL_SOCKET, optname, optval, optlen);
@@ -396,9 +396,9 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 	case IPV6_FREEBIND:
 		lock_sock(sk);
 		ssock = __mptcp_nmpc_socket(msk);
-		if (!ssock) {
+		if (IS_ERR(ssock)) {
 			release_sock(sk);
-			return -EINVAL;
+			return PTR_ERR(ssock);
 		}
 
 		ret = tcp_setsockopt(ssock->sk, SOL_IPV6, optname, optval, optlen);
@@ -693,9 +693,9 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 	lock_sock(sk);
 
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock) {
+	if (IS_ERR(ssock)) {
 		release_sock(sk);
-		return -EINVAL;
+		return PTR_ERR(ssock);
 	}
 
 	issk = inet_sk(ssock->sk);
@@ -762,13 +762,15 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 {
 	struct sock *sk = (struct sock *)msk;
 	struct socket *sock;
-	int ret = -EINVAL;
+	int ret;
 
 	/* Limit to first subflow, before the connection establishment */
 	lock_sock(sk);
 	sock = __mptcp_nmpc_socket(msk);
-	if (!sock)
+	if (IS_ERR(sock)) {
+		ret = PTR_ERR(sock);
 		goto unlock;
+	}
 
 	ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen);
 
@@ -861,7 +863,7 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 {
 	struct sock *sk = (struct sock *)msk;
 	struct socket *ssock;
-	int ret = -EINVAL;
+	int ret;
 	struct sock *ssk;
 
 	lock_sock(sk);
@@ -872,8 +874,10 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 	}
 
 	ssock = __mptcp_nmpc_socket(msk);
-	if (!ssock)
+	if (IS_ERR(ssock)) {
+		ret = PTR_ERR(ssock);
 		goto out;
+	}
 
 	ret = tcp_getsockopt(ssock->sk, level, optname, optval, optlen);
 
@@ -885,7 +889,6 @@ out:
 void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 {
 	u32 flags = 0;
-	u8 val;
 
 	memset(info, 0, sizeof(*info));
 
@@ -893,12 +896,19 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled);
 	info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
 	info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
-	info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk);
-	val = mptcp_pm_get_add_addr_signal_max(msk);
-	info->mptcpi_add_addr_signal_max = val;
-	val = mptcp_pm_get_add_addr_accept_max(msk);
-	info->mptcpi_add_addr_accepted_max = val;
-	info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk);
+
+	/* The following limits only make sense for the in-kernel PM */
+	if (mptcp_pm_is_kernel(msk)) {
+		info->mptcpi_subflows_max =
+			mptcp_pm_get_subflows_max(msk);
+		info->mptcpi_add_addr_signal_max =
+			mptcp_pm_get_add_addr_signal_max(msk);
+		info->mptcpi_add_addr_accepted_max =
+			mptcp_pm_get_add_addr_accept_max(msk);
+		info->mptcpi_local_addr_max =
+			mptcp_pm_get_local_addr_max(msk);
+	}
+
 	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags))
 		flags |= MPTCP_INFO_FLAG_FALLBACK;
 	if (READ_ONCE(msk->can_ack))
@@ -1046,7 +1056,7 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval,
 
 static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
 
 	memset(a, 0, sizeof(*a));
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 4ae1a7304cf0..d9c8b21c6076 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -397,15 +397,19 @@ void mptcp_subflow_reset(struct sock *ssk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
+	/* mptcp_mp_fail_no_response() can reach here on an already closed
+	 * socket
+	 */
+	if (ssk->sk_state == TCP_CLOSE)
+		return;
+
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
-	tcp_set_state(ssk, TCP_CLOSE);
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
 	tcp_done(ssk);
-	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) &&
-	    schedule_work(&mptcp_sk(sk)->work))
-		return; /* worker will put sk for us */
+	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
+		mptcp_schedule_work(sk);
 
 	sock_put(sk);
 }
@@ -622,7 +626,7 @@ static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init
 static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init;
 static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init;
 static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init;
-static struct proto tcpv6_prot_override;
+static struct proto tcpv6_prot_override __ro_after_init;
 
 static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
@@ -691,13 +695,6 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 	return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
 }
 
-static void mptcp_force_close(struct sock *sk)
-{
-	/* the msk is not yet exposed to user-space */
-	inet_sk_state_store(sk, TCP_CLOSE);
-	sk_common_release(sk);
-}
-
 static void subflow_ulp_fallback(struct sock *sk,
 				 struct mptcp_subflow_context *old_ctx)
 {
@@ -711,16 +708,19 @@ static void subflow_ulp_fallback(struct sock *sk,
 	mptcp_subflow_ops_undo_override(sk);
 }
 
-static void subflow_drop_ctx(struct sock *ssk)
+void mptcp_subflow_drop_ctx(struct sock *ssk)
 {
 	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
 
 	if (!ctx)
 		return;
 
-	subflow_ulp_fallback(ssk, ctx);
-	if (ctx->conn)
-		sock_put(ctx->conn);
+	list_del(&mptcp_subflow_ctx(ssk)->node);
+	if (inet_csk(ssk)->icsk_ulp_ops) {
+		subflow_ulp_fallback(ssk, ctx);
+		if (ctx->conn)
+			sock_put(ctx->conn);
+	}
 
 	kfree_rcu(ctx, rcu);
 }
@@ -749,7 +749,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_subflow_request_sock *subflow_req;
 	struct mptcp_options_received mp_opt;
 	bool fallback, fallback_is_fatal;
-	struct sock *new_msk = NULL;
+	struct mptcp_sock *owner;
 	struct sock *child;
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
@@ -777,14 +777,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
+		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC))
 			fallback = true;
-			goto create_child;
-		}
 
-		new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
-		if (!new_msk)
-			fallback = true;
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
 		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
@@ -813,49 +808,29 @@ create_child:
 				subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
 				goto dispose_child;
 			}
-
-			if (new_msk)
-				mptcp_copy_inaddrs(new_msk, child);
-			subflow_drop_ctx(child);
-			goto out;
+			goto fallback;
 		}
 
 		/* ssk inherits options of listener sk */
 		ctx->setsockopt_seq = listener->setsockopt_seq;
 
 		if (ctx->mp_capable) {
-			/* this can't race with mptcp_close(), as the msk is
-			 * not yet exposted to user-space
-			 */
-			inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED);
-
-			/* record the newly created socket as the first msk
-			 * subflow, but don't link it yet into conn_list
-			 */
-			WRITE_ONCE(mptcp_sk(new_msk)->first, child);
+			ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req);
+			if (!ctx->conn)
+				goto fallback;
 
-			/* new mpc subflow takes ownership of the newly
-			 * created mptcp socket
-			 */
-			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
-			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
-			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
-			ctx->conn = new_msk;
-			new_msk = NULL;
-
-			/* set msk addresses early to ensure mptcp_pm_get_local_id()
-			 * uses the correct data
-			 */
-			mptcp_copy_inaddrs(ctx->conn, child);
+			owner = mptcp_sk(ctx->conn);
+			mptcp_pm_new_connection(owner, child, 1);
 
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
 			 */
-			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK)
+			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
 				mptcp_subflow_fully_established(ctx, &mp_opt);
+				mptcp_pm_fully_established(owner, child);
+				ctx->pm_notified = 1;
+			}
 		} else if (ctx->mp_join) {
-			struct mptcp_sock *owner;
-
 			owner = subflow_req->msk;
 			if (!owner) {
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
@@ -885,11 +860,6 @@ create_child:
 		}
 	}
 
-out:
-	/* dispose of the left over mptcp master, if any */
-	if (unlikely(new_msk))
-		mptcp_force_close(new_msk);
-
 	/* check for expected invariant - should never trigger, just help
 	 * catching eariler subtle bugs
 	 */
@@ -899,7 +869,7 @@ out:
 	return child;
 
 dispose_child:
-	subflow_drop_ctx(child);
+	mptcp_subflow_drop_ctx(child);
 	tcp_rsk(req)->drop_req = true;
 	inet_csk_prepare_for_destroy_sock(child);
 	tcp_done(child);
@@ -907,10 +877,14 @@ dispose_child:
 
 	/* The last child reference will be released by the caller */
 	return child;
+
+fallback:
+	mptcp_subflow_drop_ctx(child);
+	return child;
 }
 
 static struct inet_connection_sock_af_ops subflow_specific __ro_after_init;
-static struct proto tcp_prot_override;
+static struct proto tcp_prot_override __ro_after_init;
 
 enum mapping_status {
 	MAPPING_OK,
@@ -1103,8 +1077,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 				skb_ext_del(skb, SKB_EXT_MPTCP);
 				return MAPPING_OK;
 			} else {
-				if (updated && schedule_work(&msk->work))
-					sock_hold((struct sock *)msk);
+				if (updated)
+					mptcp_schedule_work((struct sock *)msk);
 
 				return MAPPING_DATA_FIN;
 			}
@@ -1207,17 +1181,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 /* sched mptcp worker to remove the subflow if no more data is pending */
 static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
 {
-	struct sock *sk = (struct sock *)msk;
-
 	if (likely(ssk->sk_state != TCP_CLOSE))
 		return;
 
 	if (skb_queue_empty(&ssk->sk_receive_queue) &&
-	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) {
-		sock_hold(sk);
-		if (!schedule_work(&msk->work))
-			sock_put(sk);
-	}
+	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		mptcp_schedule_work((struct sock *)msk);
 }
 
 static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
@@ -1335,7 +1304,7 @@ fallback:
 			subflow->reset_reason = MPTCP_RST_EMPTCP;
 
 reset:
-			ssk->sk_err = EBADMSG;
+			WRITE_ONCE(ssk->sk_err, EBADMSG);
 			tcp_set_state(ssk, TCP_CLOSE);
 			while ((skb = skb_peek(&ssk->sk_receive_queue)))
 				sk_eat_skb(ssk, skb);
@@ -1419,7 +1388,7 @@ void __mptcp_error_report(struct sock *sk)
 		ssk_state = inet_sk_state_load(ssk);
 		if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
 			inet_sk_state_store(sk, ssk_state);
-		sk->sk_err = -err;
+		WRITE_ONCE(sk->sk_err, -err);
 
 		/* This barrier is coupled with smp_rmb() in mptcp_poll() */
 		smp_wmb();
@@ -1432,6 +1401,13 @@ static void subflow_error_report(struct sock *ssk)
 {
 	struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
 
+	/* bail early if this is a no-op, so that we avoid introducing a
+	 * problematic lockdep dependency between TCP accept queue lock
+	 * and msk socket spinlock
+	 */
+	if (!sk->sk_socket)
+		return;
+
 	mptcp_data_lock(sk);
 	if (!sock_owned_by_user(sk))
 		__mptcp_error_report(sk);
@@ -1773,14 +1749,16 @@ static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
+	struct mptcp_sock *msk;
 
 	__subflow_state_change(sk);
 
+	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
 		mptcp_propagate_sndbuf(parent, sk);
 		mptcp_do_fallback(sk);
-		mptcp_rcv_space_init(mptcp_sk(parent), sk);
-		pr_fallback(mptcp_sk(parent));
+		mptcp_rcv_space_init(msk, sk);
+		pr_fallback(msk);
 		subflow->conn_finished = 1;
 		mptcp_set_connected(parent);
 	}
@@ -1796,11 +1774,12 @@ static void subflow_state_change(struct sock *sk)
 
 	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
 
-	if (__mptcp_check_fallback(mptcp_sk(parent)) &&
-	    !subflow->rx_eof && subflow_is_done(sk)) {
-		subflow->rx_eof = 1;
-		mptcp_subflow_eof(parent);
-	}
+	/* when the fallback subflow closes the rx side, trigger a 'dummy'
+	 * ingress data fin, so that the msk state will follow along
+	 */
+	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
+	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
+		mptcp_schedule_work(parent);
 }
 
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
@@ -1808,13 +1787,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
 	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
 	struct mptcp_sock *msk, *next, *head = NULL;
 	struct request_sock *req;
+	struct sock *sk;
 
 	/* build a list of all unaccepted mptcp sockets */
 	spin_lock_bh(&queue->rskq_lock);
 	for (req = queue->rskq_accept_head; req; req = req->dl_next) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *ssk = req->sk;
-		struct mptcp_sock *msk;
 
 		if (!sk_is_mptcp(ssk))
 			continue;
@@ -1824,10 +1803,12 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
 			continue;
 
 		/* skip if already in list */
-		msk = mptcp_sk(subflow->conn);
+		sk = subflow->conn;
+		msk = mptcp_sk(sk);
 		if (msk->dl_next || msk == head)
 			continue;
 
+		sock_hold(sk);
 		msk->dl_next = head;
 		head = msk;
 	}
@@ -1841,34 +1822,30 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
 	release_sock(listener_ssk);
 
 	for (msk = head; msk; msk = next) {
-		struct sock *sk = (struct sock *)msk;
-		bool do_cancel_work;
+		sk = (struct sock *)msk;
 
-		sock_hold(sk);
 		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 		next = msk->dl_next;
-		msk->first = NULL;
 		msk->dl_next = NULL;
 
-		do_cancel_work = __mptcp_close(sk, 0);
+		__mptcp_unaccepted_force_close(sk);
 		release_sock(sk);
-		if (do_cancel_work) {
-			/* lockdep will report a false positive ABBA deadlock
-			 * between cancel_work_sync and the listener socket.
-			 * The involved locks belong to different sockets WRT
-			 * the existing AB chain.
-			 * Using a per socket key is problematic as key
-			 * deregistration requires process context and must be
-			 * performed at socket disposal time, in atomic
-			 * context.
-			 * Just tell lockdep to consider the listener socket
-			 * released here.
-			 */
-			mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
-			mptcp_cancel_work(sk);
-			mutex_acquire(&listener_sk->sk_lock.dep_map,
-				      SINGLE_DEPTH_NESTING, 0, _RET_IP_);
-		}
+
+		/* lockdep will report a false positive ABBA deadlock
+		 * between cancel_work_sync and the listener socket.
+		 * The involved locks belong to different sockets WRT
+		 * the existing AB chain.
+		 * Using a per socket key is problematic as key
+		 * deregistration requires process context and must be
+		 * performed at socket disposal time, in atomic
+		 * context.
+		 * Just tell lockdep to consider the listener socket
+		 * released here.
+		 */
+		mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
+		mptcp_cancel_work(sk);
+		mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+
 		sock_put(sk);
 	}
 
@@ -1932,6 +1909,13 @@ static void subflow_ulp_release(struct sock *ssk)
 		 * when the subflow is still unaccepted
 		 */
 		release = ctx->disposable || list_empty(&ctx->node);
+
+		/* inet_child_forget() does not call sk_state_change(),
+		 * explicitly trigger the socket close machinery
+		 */
+		if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW,
+						  &mptcp_sk(sk)->flags))
+			mptcp_schedule_work(sk);
 		sock_put(sk);
 	}