Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Fix the iwlwifi regression, from Johannes Berg.

   2) Support BSS coloring and 802.11 encapsulation offloading in
      hardware, from John Crispin.

   3) Fix some potential Spectre issues in qtnfmac, from Sergey
      Matyukevich.

   4) Add TTL decrement action to openvswitch, from Matteo Croce.

   5) Allow paralleization through flow_action setup by not taking the
      RTNL mutex, from Vlad Buslov.

   6) A lot of zero-length array to flexible-array conversions, from
      Gustavo A. R. Silva.

   7) Align XDP statistics names across several drivers for consistency,
      from Lorenzo Bianconi.

   8) Add various pieces of infrastructure for offloading conntrack, and
      make use of it in mlx5 driver, from Paul Blakey.

   9) Allow using listening sockets in BPF sockmap, from Jakub Sitnicki.

  10) Lots of parallelization improvements during configuration changes
      in mlxsw driver, from Ido Schimmel.

  11) Add support to devlink for generic packet traps, which report
      packets dropped during ACL processing. And use them in mlxsw
      driver. From Jiri Pirko.

  12) Support bcmgenet on ACPI, from Jeremy Linton.

  13) Make BPF compatible with RT, from Thomas Gleixnet, Alexei
      Starovoitov, and your's truly.

  14) Support XDP meta-data in virtio_net, from Yuya Kusakabe.

  15) Fix sysfs permissions when network devices change namespaces, from
      Christian Brauner.

  16) Add a flags element to ethtool_ops so that drivers can more simply
      indicate which coalescing parameters they actually support, and
      therefore the generic layer can validate the user's ethtool
      request. Use this in all drivers, from Jakub Kicinski.

  17) Offload FIFO qdisc in mlxsw, from Petr Machata.

  18) Support UDP sockets in sockmap, from Lorenz Bauer.

  19) Fix stretch ACK bugs in several TCP congestion control modules,
      from Pengcheng Yang.

  20) Support virtual functiosn in octeontx2 driver, from Tomasz
      Duszynski.

  21) Add region operations for devlink and use it in ice driver to dump
      NVM contents, from Jacob Keller.

  22) Add support for hw offload of MACSEC, from Antoine Tenart.

  23) Add support for BPF programs that can be attached to LSM hooks,
      from KP Singh.

  24) Support for multiple paths, path managers, and counters in MPTCP.
      From Peter Krystad, Paolo Abeni, Florian Westphal, Davide Caratti,
      and others.

  25) More progress on adding the netlink interface to ethtool, from
      Michal Kubecek"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2121 commits)
  net: ipv6: rpl_iptunnel: Fix potential memory leak in rpl_do_srh_inline
  cxgb4/chcr: nic-tls stats in ethtool
  net: dsa: fix oops while probing Marvell DSA switches
  net/bpfilter: remove superfluous testing message
  net: macb: Fix handling of fixed-link node
  net: dsa: ksz: Select KSZ protocol tag
  netdevsim: dev: Fix memory leak in nsim_dev_take_snapshot_write
  net: stmmac: add EHL 2.5Gbps PCI info and PCI ID
  net: stmmac: add EHL PSE0 & PSE1 1Gbps PCI info and PCI ID
  net: stmmac: create dwmac-intel.c to contain all Intel platform
  net: dsa: bcm_sf2: Support specifying VLAN tag egress rule
  net: dsa: bcm_sf2: Add support for matching VLAN TCI
  net: dsa: bcm_sf2: Move writing of CFP_DATA(5) into slicing functions
  net: dsa: bcm_sf2: Check earlier for FLOW_EXT and FLOW_MAC_EXT
  net: dsa: bcm_sf2: Disable learning for ASP port
  net: dsa: b53: Deny enslaving port 7 for 7278 into a bridge
  net: dsa: b53: Prevent tagged VLAN on port 7 for 7278
  net: dsa: b53: Restore VLAN entries upon (re)configuration
  net: dsa: bcm_sf2: Fix overflow checks
  hv_netvsc: Remove unnecessary round_up for recv_completion_cnt
  ...

1 files changed, 357 insertions, 46 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 65122edf60aa..b5180c81588e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <crypto/algapi.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
@@ -19,17 +20,42 @@
 #endif
 #include <net/mptcp.h>
 #include "protocol.h"
+#include "mib.h"
+
+static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
+				  enum linux_mptcp_mib_field field)
+{
+	MPTCP_INC_STATS(sock_net(req_to_sk(req)), field);
+}
 
 static int subflow_rebuild_header(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	int err = 0;
+	int local_id, err = 0;
 
 	if (subflow->request_mptcp && !subflow->token) {
 		pr_debug("subflow=%p", sk);
 		err = mptcp_token_new_connect(sk);
+	} else if (subflow->request_join && !subflow->local_nonce) {
+		struct mptcp_sock *msk = (struct mptcp_sock *)subflow->conn;
+
+		pr_debug("subflow=%p", sk);
+
+		do {
+			get_random_bytes(&subflow->local_nonce, sizeof(u32));
+		} while (!subflow->local_nonce);
+
+		if (subflow->local_id)
+			goto out;
+
+		local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
+		if (local_id < 0)
+			return -EINVAL;
+
+		subflow->local_id = local_id;
 	}
 
+out:
 	if (err)
 		return err;
 
@@ -47,6 +73,51 @@ static void subflow_req_destructor(struct request_sock *req)
 	tcp_request_sock_ops.destructor(req);
 }
 
+static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
+				  void *hmac)
+{
+	u8 msg[8];
+
+	put_unaligned_be32(nonce1, &msg[0]);
+	put_unaligned_be32(nonce2, &msg[4]);
+
+	mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
+}
+
+/* validate received token and create truncated hmac and nonce for SYN-ACK */
+static bool subflow_token_join_request(struct request_sock *req,
+				       const struct sk_buff *skb)
+{
+	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+	u8 hmac[MPTCPOPT_HMAC_LEN];
+	struct mptcp_sock *msk;
+	int local_id;
+
+	msk = mptcp_token_get_sock(subflow_req->token);
+	if (!msk) {
+		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
+		return false;
+	}
+
+	local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req);
+	if (local_id < 0) {
+		sock_put((struct sock *)msk);
+		return false;
+	}
+	subflow_req->local_id = local_id;
+
+	get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
+
+	subflow_generate_hmac(msk->local_key, msk->remote_key,
+			      subflow_req->local_nonce,
+			      subflow_req->remote_nonce, hmac);
+
+	subflow_req->thmac = get_unaligned_be64(hmac);
+
+	sock_put((struct sock *)msk);
+	return true;
+}
+
 static void subflow_init_req(struct request_sock *req,
 			     const struct sock *sk_listener,
 			     struct sk_buff *skb)
@@ -61,6 +132,7 @@ static void subflow_init_req(struct request_sock *req,
 	mptcp_get_options(skb, &rx_opt);
 
 	subflow_req->mp_capable = 0;
+	subflow_req->mp_join = 0;
 	subflow_req->remote_key_valid = 0;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -71,6 +143,15 @@ static void subflow_init_req(struct request_sock *req,
 		return;
 #endif
 
+	if (rx_opt.mptcp.mp_capable) {
+		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
+
+		if (rx_opt.mptcp.mp_join)
+			return;
+	} else if (rx_opt.mptcp.mp_join) {
+		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+	}
+
 	if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
 		int err;
 
@@ -79,6 +160,19 @@ static void subflow_init_req(struct request_sock *req,
 			subflow_req->mp_capable = 1;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
+	} else if (rx_opt.mptcp.mp_join && listener->request_mptcp) {
+		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
+		subflow_req->mp_join = 1;
+		subflow_req->backup = rx_opt.mptcp.backup;
+		subflow_req->remote_id = rx_opt.mptcp.join_id;
+		subflow_req->token = rx_opt.mptcp.token;
+		subflow_req->remote_nonce = rx_opt.mptcp.nonce;
+		pr_debug("token=%u, remote_nonce=%u", subflow_req->token,
+			 subflow_req->remote_nonce);
+		if (!subflow_token_join_request(req, skb)) {
+			subflow_req->mp_join = 0;
+			// @@ need to trigger RST
+		}
 	}
 }
 
@@ -106,13 +200,41 @@ static void subflow_v6_init_req(struct request_sock *req,
 }
 #endif
 
+/* validate received truncated hmac and create hmac for third ACK */
+static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
+{
+	u8 hmac[MPTCPOPT_HMAC_LEN];
+	u64 thmac;
+
+	subflow_generate_hmac(subflow->remote_key, subflow->local_key,
+			      subflow->remote_nonce, subflow->local_nonce,
+			      hmac);
+
+	thmac = get_unaligned_be64(hmac);
+	pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n",
+		 subflow, subflow->token,
+		 (unsigned long long)thmac,
+		 (unsigned long long)subflow->thmac);
+
+	return thmac == subflow->thmac;
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct sock *parent = subflow->conn;
 
 	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
 
-	if (subflow->conn && !subflow->conn_finished) {
+	if (inet_sk_state_load(parent) != TCP_ESTABLISHED) {
+		inet_sk_state_store(parent, TCP_ESTABLISHED);
+		parent->sk_state_change(parent);
+	}
+
+	if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp)
+		return;
+
+	if (subflow->mp_capable) {
 		pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
 			 subflow->remote_key);
 		mptcp_finish_connect(sk);
@@ -122,6 +244,33 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
 			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
 		}
+	} else if (subflow->mp_join) {
+		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u",
+			 subflow, subflow->thmac,
+			 subflow->remote_nonce);
+		if (!subflow_thmac_valid(subflow)) {
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
+			subflow->mp_join = 0;
+			goto do_reset;
+		}
+
+		subflow_generate_hmac(subflow->local_key, subflow->remote_key,
+				      subflow->local_nonce,
+				      subflow->remote_nonce,
+				      subflow->hmac);
+
+		if (skb)
+			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
+
+		if (!mptcp_finish_join(sk))
+			goto do_reset;
+
+		subflow->conn_finished = 1;
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+	} else {
+do_reset:
+		tcp_send_active_reset(sk, GFP_ATOMIC);
+		tcp_done(sk);
 	}
 }
 
@@ -172,6 +321,32 @@ drop:
 }
 #endif
 
+/* validate hmac received in third ACK */
+static bool subflow_hmac_valid(const struct request_sock *req,
+			       const struct tcp_options_received *rx_opt)
+{
+	const struct mptcp_subflow_request_sock *subflow_req;
+	u8 hmac[MPTCPOPT_HMAC_LEN];
+	struct mptcp_sock *msk;
+	bool ret;
+
+	subflow_req = mptcp_subflow_rsk(req);
+	msk = mptcp_token_get_sock(subflow_req->token);
+	if (!msk)
+		return false;
+
+	subflow_generate_hmac(msk->remote_key, msk->local_key,
+			      subflow_req->remote_nonce,
+			      subflow_req->local_nonce, hmac);
+
+	ret = true;
+	if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac)))
+		ret = false;
+
+	sock_put((struct sock *)msk);
+	return ret;
+}
+
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 					  struct sk_buff *skb,
 					  struct request_sock *req,
@@ -182,6 +357,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
 	struct tcp_options_received opt_rx;
+	bool fallback_is_fatal = false;
+	struct sock *new_msk = NULL;
 	struct sock *child;
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
@@ -197,7 +374,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			 * out-of-order pkt, which will not carry the MP_CAPABLE
 			 * opt even on mptcp enabled paths
 			 */
-			goto create_child;
+			goto create_msk;
 		}
 
 		opt_rx.mptcp.mp_capable = 0;
@@ -207,6 +384,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			subflow_req->remote_key_valid = 1;
 		} else {
 			subflow_req->mp_capable = 0;
+			goto create_child;
+		}
+
+create_msk:
+		new_msk = mptcp_sk_clone(listener->conn, req);
+		if (!new_msk)
+			subflow_req->mp_capable = 0;
+	} else if (subflow_req->mp_join) {
+		fallback_is_fatal = true;
+		opt_rx.mptcp.mp_join = 0;
+		mptcp_get_options(skb, &opt_rx);
+		if (!opt_rx.mptcp.mp_join ||
+		    !subflow_hmac_valid(req, &opt_rx)) {
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
+			return NULL;
 		}
 	}
 
@@ -217,22 +409,45 @@ create_child:
 	if (child && *own_req) {
 		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
 
-		/* we have null ctx on TCP fallback, not fatal on MPC
-		 * handshake
+		/* we have null ctx on TCP fallback, which is fatal on
+		 * MPJ handshake
 		 */
-		if (!ctx)
-			return child;
+		if (!ctx) {
+			if (fallback_is_fatal)
+				goto close_child;
+			goto out;
+		}
 
 		if (ctx->mp_capable) {
-			if (mptcp_token_new_accept(ctx->token))
+			/* new mpc subflow takes ownership of the newly
+			 * created mptcp socket
+			 */
+			inet_sk_state_store(new_msk, TCP_ESTABLISHED);
+			mptcp_pm_new_connection(mptcp_sk(new_msk), 1);
+			ctx->conn = new_msk;
+			new_msk = NULL;
+		} else if (ctx->mp_join) {
+			struct mptcp_sock *owner;
+
+			owner = mptcp_token_get_sock(ctx->token);
+			if (!owner)
 				goto close_child;
+
+			ctx->conn = (struct sock *)owner;
+			if (!mptcp_finish_join(child))
+				goto close_child;
+
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
 		}
 	}
 
+out:
+	/* dispose of the left over mptcp master, if any */
+	if (unlikely(new_msk))
+		sock_put(new_msk);
 	return child;
 
 close_child:
-	pr_debug("closing child socket");
 	tcp_send_active_reset(child, GFP_ATOMIC);
 	inet_csk_prepare_forced_close(child);
 	tcp_done(child);
@@ -338,6 +553,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk)
 	data_len = mpext->data_len;
 	if (data_len == 0) {
 		pr_err("Infinite mapping not handled");
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
 		return MAPPING_INVALID;
 	}
 
@@ -381,8 +597,10 @@ static enum mapping_status get_mapping_status(struct sock *ssk)
 		/* If this skb data are fully covered by the current mapping,
 		 * the new map would need caching, which is not supported
 		 */
-		if (skb_is_fully_mapped(ssk, skb))
+		if (skb_is_fully_mapped(ssk, skb)) {
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSNOMATCH);
 			return MAPPING_INVALID;
+		}
 
 		/* will validate the next map after consuming the current one */
 		return MAPPING_OK;
@@ -408,6 +626,18 @@ validate_seq:
 	return MAPPING_OK;
 }
 
+static int subflow_read_actor(read_descriptor_t *desc,
+			      struct sk_buff *skb,
+			      unsigned int offset, size_t len)
+{
+	size_t copy_len = min(desc->count, len);
+
+	desc->count -= copy_len;
+
+	pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count);
+	return copy_len;
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -420,9 +650,6 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	if (subflow->data_avail)
 		return true;
 
-	if (!subflow->conn)
-		return false;
-
 	msk = mptcp_sk(subflow->conn);
 	for (;;) {
 		u32 map_remaining;
@@ -482,16 +709,12 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		pr_debug("discarding %zu bytes, current map len=%d", delta,
 			 map_remaining);
 		if (delta) {
-			struct mptcp_read_arg arg = {
-				.msg = NULL,
-			};
 			read_descriptor_t desc = {
 				.count = delta,
-				.arg.data = &arg,
 			};
 			int ret;
 
-			ret = tcp_read_sock(ssk, &desc, mptcp_read_actor);
+			ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
 			if (ret < 0) {
 				ssk->sk_err = -ret;
 				goto fatal;
@@ -546,19 +769,15 @@ static void subflow_data_ready(struct sock *sk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
 
-	if (!parent || !subflow->mp_capable) {
+	if (!subflow->mp_capable && !subflow->mp_join) {
 		subflow->tcp_data_ready(sk);
 
-		if (parent)
-			parent->sk_data_ready(parent);
+		parent->sk_data_ready(parent);
 		return;
 	}
 
-	if (mptcp_subflow_data_available(sk)) {
-		set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags);
-
-		parent->sk_data_ready(parent);
-	}
+	if (mptcp_subflow_data_available(sk))
+		mptcp_data_ready(parent, sk);
 }
 
 static void subflow_write_space(struct sock *sk)
@@ -567,7 +786,7 @@ static void subflow_write_space(struct sock *sk)
 	struct sock *parent = subflow->conn;
 
 	sk_stream_write_space(sk);
-	if (parent && sk_stream_is_writeable(sk)) {
+	if (sk_stream_is_writeable(sk)) {
 		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
 		smp_mb__after_atomic();
 		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
@@ -605,6 +824,85 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
 }
 #endif
 
+static void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
+				struct sockaddr_storage *addr)
+{
+	memset(addr, 0, sizeof(*addr));
+	addr->ss_family = info->family;
+	if (addr->ss_family == AF_INET) {
+		struct sockaddr_in *in_addr = (struct sockaddr_in *)addr;
+
+		in_addr->sin_addr = info->addr;
+		in_addr->sin_port = info->port;
+	}
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (addr->ss_family == AF_INET6) {
+		struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr;
+
+		in6_addr->sin6_addr = info->addr6;
+		in6_addr->sin6_port = info->port;
+	}
+#endif
+}
+
+int __mptcp_subflow_connect(struct sock *sk, int ifindex,
+			    const struct mptcp_addr_info *loc,
+			    const struct mptcp_addr_info *remote)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct sockaddr_storage addr;
+	struct socket *sf;
+	u32 remote_token;
+	int addrlen;
+	int err;
+
+	if (sk->sk_state != TCP_ESTABLISHED)
+		return -ENOTCONN;
+
+	err = mptcp_subflow_create_socket(sk, &sf);
+	if (err)
+		return err;
+
+	subflow = mptcp_subflow_ctx(sf->sk);
+	subflow->remote_key = msk->remote_key;
+	subflow->local_key = msk->local_key;
+	subflow->token = msk->token;
+	mptcp_info2sockaddr(loc, &addr);
+
+	addrlen = sizeof(struct sockaddr_in);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (loc->family == AF_INET6)
+		addrlen = sizeof(struct sockaddr_in6);
+#endif
+	sf->sk->sk_bound_dev_if = ifindex;
+	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
+	if (err)
+		goto failed;
+
+	mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
+	pr_debug("msk=%p remote_token=%u", msk, remote_token);
+	subflow->remote_token = remote_token;
+	subflow->local_id = loc->id;
+	subflow->request_join = 1;
+	subflow->request_bkup = 1;
+	mptcp_info2sockaddr(remote, &addr);
+
+	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
+	if (err && err != -EINPROGRESS)
+		goto failed;
+
+	spin_lock_bh(&msk->join_list_lock);
+	list_add_tail(&subflow->node, &msk->join_list);
+	spin_unlock_bh(&msk->join_list_lock);
+
+	return err;
+
+failed:
+	sock_release(sf);
+	return err;
+}
+
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 {
 	struct mptcp_subflow_context *subflow;
@@ -682,7 +980,7 @@ static bool subflow_is_done(const struct sock *sk)
 static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sock *parent = READ_ONCE(subflow->conn);
+	struct sock *parent = subflow->conn;
 
 	__subflow_state_change(sk);
 
@@ -690,13 +988,10 @@ static void subflow_state_change(struct sock *sk)
 	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
 	 * the data available machinery here.
 	 */
-	if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) {
-		set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags);
-
-		parent->sk_data_ready(parent);
-	}
+	if (subflow->mp_capable && mptcp_subflow_data_available(sk))
+		mptcp_data_ready(parent, sk);
 
-	if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) &&
+	if (!(parent->sk_shutdown & RCV_SHUTDOWN) &&
 	    !subflow->rx_eof && subflow_is_done(sk)) {
 		subflow->rx_eof = 1;
 		parent->sk_shutdown |= RCV_SHUTDOWN;
@@ -772,7 +1067,8 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk);
 	struct mptcp_subflow_context *new_ctx;
 
-	if (!tcp_rsk(req)->is_mptcp || !subflow_req->mp_capable) {
+	if (!tcp_rsk(req)->is_mptcp ||
+	    (!subflow_req->mp_capable && !subflow_req->mp_join)) {
 		subflow_ulp_fallback(newsk, old_ctx);
 		return;
 	}
@@ -783,22 +1079,35 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		return;
 	}
 
-	/* see comments in subflow_syn_recv_sock(), MPTCP connection is fully
-	 * established only after we receive the remote key
-	 */
 	new_ctx->conn_finished = 1;
 	new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
 	new_ctx->tcp_data_ready = old_ctx->tcp_data_ready;
 	new_ctx->tcp_state_change = old_ctx->tcp_state_change;
 	new_ctx->tcp_write_space = old_ctx->tcp_write_space;
-	new_ctx->mp_capable = 1;
-	new_ctx->fourth_ack = subflow_req->remote_key_valid;
-	new_ctx->can_ack = subflow_req->remote_key_valid;
-	new_ctx->remote_key = subflow_req->remote_key;
-	new_ctx->local_key = subflow_req->local_key;
-	new_ctx->token = subflow_req->token;
-	new_ctx->ssn_offset = subflow_req->ssn_offset;
-	new_ctx->idsn = subflow_req->idsn;
+	new_ctx->rel_write_seq = 1;
+	new_ctx->tcp_sock = newsk;
+
+	if (subflow_req->mp_capable) {
+		/* see comments in subflow_syn_recv_sock(), MPTCP connection
+		 * is fully established only after we receive the remote key
+		 */
+		new_ctx->mp_capable = 1;
+		new_ctx->fully_established = subflow_req->remote_key_valid;
+		new_ctx->can_ack = subflow_req->remote_key_valid;
+		new_ctx->remote_key = subflow_req->remote_key;
+		new_ctx->local_key = subflow_req->local_key;
+		new_ctx->token = subflow_req->token;
+		new_ctx->ssn_offset = subflow_req->ssn_offset;
+		new_ctx->idsn = subflow_req->idsn;
+	} else if (subflow_req->mp_join) {
+		new_ctx->ssn_offset = subflow_req->ssn_offset;
+		new_ctx->mp_join = 1;
+		new_ctx->fully_established = 1;
+		new_ctx->backup = subflow_req->backup;
+		new_ctx->local_id = subflow_req->local_id;
+		new_ctx->token = subflow_req->token;
+		new_ctx->thmac = subflow_req->thmac;
+	}
 }
 
 static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
@@ -860,6 +1169,8 @@ void mptcp_subflow_init(void)
 	subflow_v6m_specific.net_frag_header_len = 0;
 #endif
 
+	mptcp_diag_subflow_init(&subflow_ulp_ops);
+
 	if (tcp_register_ulp(&subflow_ulp_ops) != 0)
 		panic("MPTCP: failed to register subflows to ULP\n");
 }