Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - support "prefer busy polling" NAPI operation mode, where we defer
     softirq for some time expecting applications to periodically busy
     poll

   - AF_XDP: improve efficiency by more batching and hindering the
     adjacency cache prefetcher

   - af_packet: make packet_fanout.arr size configurable up to 64K

   - tcp: optimize TCP zero copy receive in presence of partial or
     unaligned reads making zero copy a performance win for much smaller
     messages

   - XDP: add bulk APIs for returning / freeing frames

   - sched: support fragmenting IP packets as they come out of conntrack

   - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs

  BPF:

   - BPF switch from crude rlimit-based to memcg-based memory accounting

   - BPF type format information for kernel modules and related tracing
     enhancements

   - BPF implement task local storage for BPF LSM

   - allow the FENTRY/FEXIT/RAW_TP tracing programs to use
     bpf_sk_storage

  Protocols:

   - mptcp: improve multiple xmit streams support, memory accounting and
     many smaller improvements

   - TLS: support CHACHA20-POLY1305 cipher

   - seg6: add support for SRv6 End.DT4/DT6 behavior

   - sctp: Implement RFC 6951: UDP Encapsulation of SCTP

   - ppp_generic: add ability to bridge channels directly

   - bridge: Connectivity Fault Management (CFM) support as is defined
     in IEEE 802.1Q section 12.14.

  Drivers:

   - mlx5: make use of the new auxiliary bus to organize the driver
     internals

   - mlx5: more accurate port TX timestamping support

   - mlxsw:
      - improve the efficiency of offloaded next hop updates by using
        the new nexthop object API
      - support blackhole nexthops
      - support IEEE 802.1ad (Q-in-Q) bridging

   - rtw88: major bluetooth co-existance improvements

   - iwlwifi: support new 6 GHz frequency band

   - ath11k: Fast Initial Link Setup (FILS)

   - mt7915: dual band concurrent (DBDC) support

   - net: ipa: add basic support for IPA v4.5

  Refactor:

   - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
     Siewior

   - phy: add support for shared interrupts; get rid of multiple driver
     APIs and have the drivers write a full IRQ handler, slight growth
     of driver code should be compensated by the simpler API which also
     allows shared IRQs

   - add common code for handling netdev per-cpu counters

   - move TX packet re-allocation from Ethernet switch tag drivers to a
     central place

   - improve efficiency and rename nla_strlcpy

   - number of W=1 warning cleanups as we now catch those in a patchwork
     build bot

  Old code removal:

   - wan: delete the DLCI / SDLA drivers

   - wimax: move to staging

   - wifi: remove old WDS wifi bridging support"

* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
  net: hns3: fix expression that is currently always true
  net: fix proc_fs init handling in af_packet and tls
  nfc: pn533: convert comma to semicolon
  af_vsock: Assign the vsock transport considering the vsock address flags
  af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
  vsock_addr: Check for supported flag values
  vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
  vm_sockets: Add flags field in the vsock address data structure
  net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
  tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
  net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
  nfc: s3fwrn5: Release the nfc firmware
  net: vxget: clean up sparse warnings
  mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
  mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
  mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
  mlxsw: reg: Add Router LPM Cache Enable Register
  mlxsw: reg: Add Router LPM Cache ML Delete Register
  mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
  mlxsw: reg: Add XM Router M Table Register
  ...

8 files changed, 1803 insertions, 757 deletions

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 54b888f94009..96ba616f59bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -18,6 +18,7 @@ struct mptcp_pernet {
 	struct ctl_table_header *ctl_table_hdr;
 
 	int mptcp_enabled;
+	unsigned int add_addr_timeout;
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net)
 	return mptcp_get_pernet(net)->mptcp_enabled;
 }
 
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+	return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		 */
 		.proc_handler = proc_dointvec,
 	},
+	{
+		.procname = "add_addr_timeout",
+		.maxlen = sizeof(unsigned int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_jiffies,
+	},
 	{}
 };
 
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
+	pernet->add_addr_timeout = TCP_RTO_MAX;
 }
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	}
 
 	table[0].data = &pernet->mptcp_enabled;
+	table[1].data = &pernet->add_addr_timeout;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 5f390a97f556..b70ae4ba3000 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -140,7 +140,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	info->mptcpi_flags = flags;
 	info->mptcpi_token = READ_ONCE(msk->token);
 	info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
-	info->mptcpi_snd_una = atomic64_read(&msk->snd_una);
+	info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
 	info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
 	unlock_sock_fast(sk, slow);
 }
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 90cd52df99a6..c5328f407aab 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -242,7 +242,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 		mp_opt->add_addr = 1;
 		mp_opt->addr_id = *ptr++;
-		pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
 			memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
 			ptr += 4;
@@ -267,6 +266,9 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->ahmac = get_unaligned_be64(ptr);
 			ptr += 8;
 		}
+		pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
+			 (mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
+			 mp_opt->addr_id, mp_opt->ahmac, mp_opt->echo, mp_opt->port);
 		break;
 
 	case MPTCPOPT_RM_ADDR:
@@ -280,6 +282,16 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
 		break;
 
+	case MPTCPOPT_MP_FASTCLOSE:
+		if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
+			break;
+
+		ptr += 2;
+		mp_opt->rcvr_key = get_unaligned_be64(ptr);
+		ptr += 8;
+		mp_opt->fastclose = 1;
+		break;
+
 	default:
 		break;
 	}
@@ -297,6 +309,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->mp_join = 0;
 	mp_opt->add_addr = 0;
 	mp_opt->ahmac = 0;
+	mp_opt->fastclose = 0;
 	mp_opt->port = 0;
 	mp_opt->rm_addr = 0;
 	mp_opt->dss = 0;
@@ -492,7 +505,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	bool ret = false;
 
 	mpext = skb ? mptcp_get_ext(skb) : NULL;
-	snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable);
+	snd_data_fin_enable = mptcp_data_fin_enabled(msk);
 
 	if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
 		unsigned int map_size;
@@ -528,6 +541,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		opts->ext_copy.ack64 = 0;
 	}
 	opts->ext_copy.use_ack = 1;
+	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -573,27 +587,43 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 }
 #endif
 
-static bool mptcp_established_options_add_addr(struct sock *sk,
+static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
 					       unsigned int *size,
 					       unsigned int remaining,
 					       struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	bool drop_other_suboptions = false;
+	unsigned int opt_size = *size;
 	struct mptcp_addr_info saddr;
 	bool echo;
+	bool port;
 	int len;
 
+	if ((mptcp_pm_should_add_signal_ipv6(msk) ||
+	     mptcp_pm_should_add_signal_port(msk)) &&
+	    skb && skb_is_tcp_pure_ack(skb)) {
+		pr_debug("drop other suboptions");
+		opts->suboptions = 0;
+		remaining += opt_size;
+		drop_other_suboptions = true;
+	}
+
 	if (!mptcp_pm_should_add_signal(msk) ||
-	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo)))
+	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo, &port)))
 		return false;
 
-	len = mptcp_add_addr_len(saddr.family, echo);
+	len = mptcp_add_addr_len(saddr.family, echo, port);
 	if (remaining < len)
 		return false;
 
 	*size = len;
+	if (drop_other_suboptions)
+		*size -= opt_size;
 	opts->addr_id = saddr.id;
+	if (port)
+		opts->port = ntohs(saddr.port);
 	if (saddr.family == AF_INET) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 		opts->addr = saddr.addr;
@@ -616,7 +646,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk,
 		}
 	}
 #endif
-	pr_debug("addr_id=%d, ahmac=%llu, echo=%d", opts->addr_id, opts->ahmac, echo);
+	pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
+		 opts->addr_id, opts->ahmac, echo, opts->port);
 
 	return true;
 }
@@ -678,7 +709,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	*size += opt_size;
 	remaining -= opt_size;
-	if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) {
+	if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
 		*size += opt_size;
 		remaining -= opt_size;
 		ret = true;
@@ -759,6 +790,11 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		goto fully_established;
 	}
 
+	if (mp_opt->add_addr) {
+		WRITE_ONCE(msk->fully_established, true);
+		return true;
+	}
+
 	/* If the first established packet does not contain MP_CAPABLE + data
 	 * then fallback to TCP. Fallback scenarios requires a reset for
 	 * MP_JOIN subflows.
@@ -777,7 +813,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	mptcp_subflow_fully_established(subflow, mp_opt);
 
 fully_established:
-	if (likely(subflow->pm_notified))
+	/* if the subflow is not already linked into the conn_list, we can't
+	 * notify the PM: this subflow is still on the listener queue
+	 * and the PM possibly acquiring the subflow lock could race with
+	 * the listener close
+	 */
+	if (likely(subflow->pm_notified) || list_empty(&subflow->node))
 		return true;
 
 	subflow->pm_notified = 1;
@@ -809,31 +850,39 @@ static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
 	return cur_ack;
 }
 
-static void update_una(struct mptcp_sock *msk,
-		       struct mptcp_options_received *mp_opt)
+static void ack_update_msk(struct mptcp_sock *msk,
+			   struct sock *ssk,
+			   struct mptcp_options_received *mp_opt)
 {
-	u64 new_snd_una, snd_una, old_snd_una = atomic64_read(&msk->snd_una);
-	u64 write_seq = READ_ONCE(msk->write_seq);
+	u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
+	struct sock *sk = (struct sock *)msk;
+	u64 old_snd_una;
+
+	mptcp_data_lock(sk);
 
 	/* avoid ack expansion on update conflict, to reduce the risk of
 	 * wrongly expanding to a future ack sequence number, which is way
 	 * more dangerous than missing an ack
 	 */
+	old_snd_una = msk->snd_una;
 	new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
 
 	/* ACK for data not even sent yet? Ignore. */
-	if (after64(new_snd_una, write_seq))
+	if (after64(new_snd_una, snd_nxt))
 		new_snd_una = old_snd_una;
 
-	while (after64(new_snd_una, old_snd_una)) {
-		snd_una = old_snd_una;
-		old_snd_una = atomic64_cmpxchg(&msk->snd_una, snd_una,
-					       new_snd_una);
-		if (old_snd_una == snd_una) {
-			mptcp_data_acked((struct sock *)msk);
-			break;
-		}
+	new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
+
+	if (after64(new_wnd_end, msk->wnd_end)) {
+		msk->wnd_end = new_wnd_end;
+		__mptcp_wnd_updated(sk, ssk);
+	}
+
+	if (after64(new_snd_una, old_snd_una)) {
+		msk->snd_una = new_snd_una;
+		__mptcp_data_acked(sk);
 	}
+	mptcp_data_unlock(sk);
 }
 
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
@@ -886,13 +935,30 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	if (__mptcp_check_fallback(msk))
+	if (__mptcp_check_fallback(msk)) {
+		/* Keep it simple and unconditionally trigger send data cleanup and
+		 * pending queue spooling. We will need to acquire the data lock
+		 * for more accurate checks, and once the lock is acquired, such
+		 * helpers are cheap.
+		 */
+		mptcp_data_lock(subflow->conn);
+		if (mptcp_send_head(subflow->conn))
+			__mptcp_wnd_updated(subflow->conn, sk);
+		__mptcp_data_acked(subflow->conn);
+		mptcp_data_unlock(subflow->conn);
 		return;
+	}
 
 	mptcp_get_options(skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
+	if (mp_opt.fastclose &&
+	    msk->local_key == mp_opt.rcvr_key) {
+		WRITE_ONCE(msk->rcv_fastclose, true);
+		mptcp_schedule_work((struct sock *)msk);
+	}
+
 	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
@@ -930,7 +996,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	 * monodirectional flows will stuck
 	 */
 	if (mp_opt.use_ack)
-		update_una(msk, &mp_opt);
+		ack_update_msk(msk, sk, &mp_opt);
 
 	/* Zero-data-length packets are dropped by the caller and not
 	 * propagated to the MPTCP layer, so the skb extension does not
@@ -975,7 +1041,24 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+static void mptcp_set_rwin(const struct tcp_sock *tp)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	const struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk;
+	u64 ack_seq;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	msk = mptcp_sk(subflow->conn);
+
+	ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+
+	if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+}
+
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+			 struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
 	     OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
@@ -1014,44 +1097,66 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 	}
 
 mp_capable_done:
-	if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
-		ptr += 1;
+	if ((OPTION_MPTCP_ADD_ADDR
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	     | OPTION_MPTCP_ADD_ADDR6
+#endif
+	    ) & opts->suboptions) {
+		u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+		u8 echo = MPTCP_ADDR_ECHO;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions)
+			len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+#endif
+
+		if (opts->port)
+			len += TCPOLEN_MPTCP_PORT_LEN;
+
 		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+			len += sizeof(opts->ahmac);
+			echo = 0;
 		}
-	}
 
+		*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
+				      len, echo, opts->addr_id);
+		if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
+			memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
+			ptr += 1;
+		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
-		ptr += 4;
-		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+		else if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
+			memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
+			ptr += 4;
 		}
-	}
 #endif
 
+		if (!opts->port) {
+			if (opts->ahmac) {
+				put_unaligned_be64(opts->ahmac, ptr);
+				ptr += 2;
+			}
+		} else {
+			if (opts->ahmac) {
+				u8 *bptr = (u8 *)ptr;
+
+				put_unaligned_be16(opts->port, bptr);
+				bptr += 2;
+				put_unaligned_be64(opts->ahmac, bptr);
+				bptr += 8;
+				put_unaligned_be16(TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, bptr);
+
+				ptr += 3;
+			} else {
+				put_unaligned_be32(opts->port << 16 |
+						   TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, ptr);
+				ptr += 1;
+			}
+		}
+	}
+
 	if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
 		*ptr++ = mptcp_option(MPTCPOPT_RM_ADDR,
 				      TCPOLEN_MPTCP_RM_ADDR_BASE,
@@ -1132,4 +1237,7 @@ mp_capable_done:
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 		}
 	}
+
+	if (tp)
+		mptcp_set_rwin(tp);
 }
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index e19e1525ecbb..da2ed576f289 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -14,22 +14,43 @@
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
-			   bool echo)
+			   bool echo, bool port)
 {
+	u8 add_addr = READ_ONCE(msk->pm.addr_signal);
+
 	pr_debug("msk=%p, local_id=%d", msk, addr->id);
 
+	if (add_addr) {
+		pr_warn("addr_signal error, add_addr=%d", add_addr);
+		return -EINVAL;
+	}
+
 	msk->pm.local = *addr;
-	WRITE_ONCE(msk->pm.add_addr_echo, echo);
-	WRITE_ONCE(msk->pm.add_addr_signal, true);
+	add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL);
+	if (echo)
+		add_addr |= BIT(MPTCP_ADD_ADDR_ECHO);
+	if (addr->family == AF_INET6)
+		add_addr |= BIT(MPTCP_ADD_ADDR_IPV6);
+	if (port)
+		add_addr |= BIT(MPTCP_ADD_ADDR_PORT);
+	WRITE_ONCE(msk->pm.addr_signal, add_addr);
 	return 0;
 }
 
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id)
 {
+	u8 rm_addr = READ_ONCE(msk->pm.addr_signal);
+
 	pr_debug("msk=%p, local_id=%d", msk, local_id);
 
+	if (rm_addr) {
+		pr_warn("addr_signal error, rm_addr=%d", rm_addr);
+		return -EINVAL;
+	}
+
 	msk->pm.rm_id = local_id;
-	WRITE_ONCE(msk->pm.rm_addr_signal, true);
+	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
+	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
 	return 0;
 }
 
@@ -89,8 +110,7 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
 		return false;
 
 	msk->pm.status |= BIT(new_status);
-	if (schedule_work(&msk->work))
-		sock_hold((struct sock *)msk);
+	mptcp_schedule_work((struct sock *)msk);
 	return true;
 }
 
@@ -106,8 +126,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk)
 
 	spin_lock_bh(&pm->lock);
 
-	if (READ_ONCE(pm->work_pending))
+	/* mptcp_pm_fully_established() can be invoked by multiple
+	 * racing paths - accept() and check_fully_established()
+	 * be sure to serve this event only once.
+	 */
+	if (READ_ONCE(pm->work_pending) &&
+	    !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
 		mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED);
+	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 
 	spin_unlock_bh(&pm->lock);
 }
@@ -150,14 +176,25 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 
 	spin_lock_bh(&pm->lock);
 
-	if (!READ_ONCE(pm->accept_addr))
-		mptcp_pm_announce_addr(msk, addr, true);
-	else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
+	if (!READ_ONCE(pm->accept_addr)) {
+		mptcp_pm_announce_addr(msk, addr, true, addr->port);
+		mptcp_pm_add_addr_send_ack(msk);
+	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->remote = *addr;
+	}
 
 	spin_unlock_bh(&pm->lock);
 }
 
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	if (!mptcp_pm_should_add_signal_ipv6(msk) &&
+	    !mptcp_pm_should_add_signal_port(msk))
+		return;
+
+	mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK);
+}
+
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
@@ -173,7 +210,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
 /* path manager helpers */
 
 bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			      struct mptcp_addr_info *saddr, bool *echo)
+			      struct mptcp_addr_info *saddr, bool *echo, bool *port)
 {
 	int ret = false;
 
@@ -183,13 +220,14 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 	if (!mptcp_pm_should_add_signal(msk))
 		goto out_unlock;
 
-	*echo = READ_ONCE(msk->pm.add_addr_echo);
+	*echo = mptcp_pm_should_add_signal_echo(msk);
+	*port = mptcp_pm_should_add_signal_port(msk);
 
-	if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo))
+	if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo, *port))
 		goto out_unlock;
 
 	*saddr = msk->pm.local;
-	WRITE_ONCE(msk->pm.add_addr_signal, false);
+	WRITE_ONCE(msk->pm.addr_signal, 0);
 	ret = true;
 
 out_unlock:
@@ -212,7 +250,7 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 		goto out_unlock;
 
 	*rm_id = msk->pm.rm_id;
-	WRITE_ONCE(msk->pm.rm_addr_signal, false);
+	WRITE_ONCE(msk->pm.addr_signal, 0);
 	ret = true;
 
 out_unlock:
@@ -233,11 +271,9 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 	msk->pm.subflows = 0;
 	msk->pm.rm_id = 0;
 	WRITE_ONCE(msk->pm.work_pending, false);
-	WRITE_ONCE(msk->pm.add_addr_signal, false);
-	WRITE_ONCE(msk->pm.rm_addr_signal, false);
+	WRITE_ONCE(msk->pm.addr_signal, 0);
 	WRITE_ONCE(msk->pm.accept_addr, false);
 	WRITE_ONCE(msk->pm.accept_subflow, false);
-	WRITE_ONCE(msk->pm.add_addr_echo, false);
 	msk->pm.status = 0;
 
 	spin_lock_init(&msk->pm.lock);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 0d6f3d912891..a6d983d80576 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -135,7 +135,7 @@ select_local_address(const struct pm_nl_pernet *pernet,
 	struct mptcp_pm_addr_entry *entry, *ret = NULL;
 
 	rcu_read_lock();
-	spin_lock_bh(&msk->join_list_lock);
+	__mptcp_flush_join_list(msk);
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
 		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
 			continue;
@@ -144,13 +144,11 @@ select_local_address(const struct pm_nl_pernet *pernet,
 		 * pending join
 		 */
 		if (entry->addr.family == ((struct sock *)msk)->sk_family &&
-		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
-		    !lookup_subflow_by_saddr(&msk->join_list, &entry->addr)) {
+		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) {
 			ret = entry;
 			break;
 		}
 	}
-	spin_unlock_bh(&msk->join_list_lock);
 	rcu_read_unlock();
 	return ret;
 }
@@ -227,12 +225,14 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 
 	if (!mptcp_pm_should_add_signal(msk)) {
 		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
-		mptcp_pm_announce_addr(msk, &entry->addr, false);
+		mptcp_pm_announce_addr(msk, &entry->addr, false, entry->addr.port);
+		mptcp_pm_add_addr_send_ack(msk);
 		entry->retrans_times++;
 	}
 
 	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
-		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+		sk_reset_timer(sk, timer,
+			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
 
 	spin_unlock_bh(&msk->pm.lock);
 
@@ -264,6 +264,7 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *add_entry = NULL;
 	struct sock *sk = (struct sock *)msk;
+	struct net *net = sock_net(sk);
 
 	if (lookup_anno_list_by_saddr(msk, &entry->addr))
 		return false;
@@ -279,7 +280,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 	add_entry->retrans_times = 0;
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
-	sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+	sk_reset_timer(sk, &add_entry->add_timer,
+		       jiffies + mptcp_get_add_addr_timeout(net));
 
 	return true;
 }
@@ -309,7 +311,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	struct mptcp_pm_addr_entry *local;
 	struct pm_nl_pernet *pernet;
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
+	pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
 
 	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
 		 msk->pm.local_addr_used, msk->pm.local_addr_max,
@@ -324,7 +326,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (local) {
 			if (mptcp_pm_alloc_anno_list(msk, local)) {
 				msk->pm.add_addr_signaled++;
-				mptcp_pm_announce_addr(msk, &local->addr, false);
+				mptcp_pm_announce_addr(msk, &local->addr, false, local->addr.port);
+				mptcp_pm_nl_add_addr_send_ack(msk);
 			}
 		} else {
 			/* pick failed, avoid fourther attempts later */
@@ -371,6 +374,7 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_addr_info remote;
 	struct mptcp_addr_info local;
+	bool use_port = false;
 
 	pr_debug("accepted %d:%d remote family %d",
 		 msk->pm.add_addr_accepted, msk->pm.add_addr_accept_max,
@@ -387,14 +391,51 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	remote = msk->pm.remote;
 	if (!remote.port)
 		remote.port = sk->sk_dport;
+	else
+		use_port = true;
 	memset(&local, 0, sizeof(local));
 	local.family = remote.family;
 
 	spin_unlock_bh(&msk->pm.lock);
-	__mptcp_subflow_connect((struct sock *)msk, &local, &remote);
+	__mptcp_subflow_connect(sk, &local, &remote);
 	spin_lock_bh(&msk->pm.lock);
 
-	mptcp_pm_announce_addr(msk, &remote, true);
+	mptcp_pm_announce_addr(msk, &remote, true, use_port);
+	mptcp_pm_nl_add_addr_send_ack(msk);
+}
+
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	if (!mptcp_pm_should_add_signal_ipv6(msk) &&
+	    !mptcp_pm_should_add_signal_port(msk))
+		return;
+
+	__mptcp_flush_join_list(msk);
+	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
+	if (subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u8 add_addr;
+
+		spin_unlock_bh(&msk->pm.lock);
+		if (mptcp_pm_should_add_signal_ipv6(msk))
+			pr_debug("send ack for add_addr6");
+		if (mptcp_pm_should_add_signal_port(msk))
+			pr_debug("send ack for add_addr_port");
+
+		lock_sock(ssk);
+		tcp_send_ack(ssk);
+		release_sock(ssk);
+		spin_lock_bh(&msk->pm.lock);
+
+		add_addr = READ_ONCE(msk->pm.addr_signal);
+		if (mptcp_pm_should_add_signal_ipv6(msk))
+			add_addr &= ~BIT(MPTCP_ADD_ADDR_IPV6);
+		if (mptcp_pm_should_add_signal_port(msk))
+			add_addr &= ~BIT(MPTCP_ADD_ADDR_PORT);
+		WRITE_ONCE(msk->pm.addr_signal, add_addr);
+	}
 }
 
 void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
@@ -413,14 +454,13 @@ void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
 	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-		long timeout = 0;
 
 		if (msk->pm.rm_id != subflow->remote_id)
 			continue;
 
 		spin_unlock_bh(&msk->pm.lock);
 		mptcp_subflow_shutdown(sk, ssk, how);
-		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		__mptcp_close_ssk(sk, ssk, subflow);
 		spin_lock_bh(&msk->pm.lock);
 
 		msk->pm.add_addr_accepted--;
@@ -449,14 +489,13 @@ void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id)
 	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-		long timeout = 0;
 
 		if (rm_id != subflow->local_id)
 			continue;
 
 		spin_unlock_bh(&msk->pm.lock);
 		mptcp_subflow_shutdown(sk, ssk, how);
-		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		__mptcp_close_ssk(sk, ssk, subflow);
 		spin_lock_bh(&msk->pm.lock);
 
 		msk->pm.local_addr_used--;
@@ -826,13 +865,14 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
-static void __flush_addrs(struct pm_nl_pernet *pernet)
+static void __flush_addrs(struct net *net, struct list_head *list)
 {
-	while (!list_empty(&pernet->local_addr_list)) {
+	while (!list_empty(list)) {
 		struct mptcp_pm_addr_entry *cur;
 
-		cur = list_entry(pernet->local_addr_list.next,
+		cur = list_entry(list->next,
 				 struct mptcp_pm_addr_entry, list);
+		mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr);
 		list_del_rcu(&cur->list);
 		kfree_rcu(cur, rcu);
 	}
@@ -849,11 +889,13 @@ static void __reset_counters(struct pm_nl_pernet *pernet)
 static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)
 {
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	LIST_HEAD(free_list);
 
 	spin_lock_bh(&pernet->lock);
-	__flush_addrs(pernet);
+	list_splice_init(&pernet->local_addr_list, &free_list);
 	__reset_counters(pernet);
 	spin_unlock_bh(&pernet->lock);
+	__flush_addrs(sock_net(skb->sk), &free_list);
 	return 0;
 }
 
@@ -1115,10 +1157,12 @@ 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);
+
 		/* net is removed from namespace list, can't race with
 		 * other modifiers
 		 */
-		__flush_addrs(net_generic(net, pm_nl_pernet_id));
+		__flush_addrs(net, &pernet->local_addr_list);
 	}
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 88f2a7a0ccb8..b812aaae8044 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -21,6 +21,7 @@
 #include <net/transp_v6.h>
 #endif
 #include <net/mptcp.h>
+#include <net/xfrm.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -41,6 +42,9 @@ struct mptcp_skb_cb {
 
 static struct percpu_counter mptcp_sockets_allocated;
 
+static void __mptcp_destroy_sock(struct sock *sk);
+static void __mptcp_check_send_data_fin(struct sock *sk);
+
 /* 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.
@@ -53,6 +57,12 @@ static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
 	return msk->subflow;
 }
 
+/* Returns end sequence number of the receiver's advertised window */
+static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->wnd_end);
+}
+
 static bool mptcp_is_tcpsk(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
@@ -102,6 +112,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	msk->subflow = ssock;
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
+	sock_hold(ssock->sk);
 	subflow->request_mptcp = 1;
 
 	/* accept() will wait on first subflow sk_wq, and we always wakes up
@@ -157,18 +168,19 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	struct rb_node **p, *parent;
 	u64 seq, end_seq, max_seq;
 	struct sk_buff *skb1;
-	int space;
 
 	seq = MPTCP_SKB_CB(skb)->map_seq;
 	end_seq = MPTCP_SKB_CB(skb)->end_seq;
-	space = tcp_space(sk);
-	max_seq = space > 0 ? space + msk->ack_seq : msk->ack_seq;
+	max_seq = READ_ONCE(msk->rcv_wnd_sent);
 
 	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
 		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
-	if (after64(seq, max_seq)) {
+	if (after64(end_seq, max_seq)) {
 		/* out of window */
 		mptcp_drop(sk, skb);
+		pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
+			 (unsigned long long)end_seq - (unsigned long)max_seq,
+			 (unsigned long long)msk->rcv_wnd_sent);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
 		return;
 	}
@@ -323,17 +335,35 @@ static void mptcp_stop_timer(struct sock *sk)
 	mptcp_sk(sk)->timer_ival = 0;
 }
 
-static void mptcp_check_data_fin_ack(struct sock *sk)
+static void mptcp_close_wake_up(struct sock *sk)
+{
+	if (sock_flag(sk, SOCK_DEAD))
+		return;
+
+	sk->sk_state_change(sk);
+	if (sk->sk_shutdown == SHUTDOWN_MASK ||
+	    sk->sk_state == TCP_CLOSE)
+		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+	else
+		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+}
+
+static bool mptcp_pending_data_fin_ack(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (__mptcp_check_fallback(msk))
-		return;
+	return !__mptcp_check_fallback(msk) &&
+	       ((1 << sk->sk_state) &
+		(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
+	       msk->write_seq == READ_ONCE(msk->snd_una);
+}
+
+static void mptcp_check_data_fin_ack(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	/* Look for an acknowledged DATA_FIN */
-	if (((1 << sk->sk_state) &
-	     (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
-	    msk->write_seq == atomic64_read(&msk->snd_una)) {
+	if (mptcp_pending_data_fin_ack(sk)) {
 		mptcp_stop_timer(sk);
 
 		WRITE_ONCE(msk->snd_data_fin_enable, 0);
@@ -341,20 +371,14 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
 		switch (sk->sk_state) {
 		case TCP_FIN_WAIT1:
 			inet_sk_state_store(sk, TCP_FIN_WAIT2);
-			sk->sk_state_change(sk);
 			break;
 		case TCP_CLOSING:
 		case TCP_LAST_ACK:
 			inet_sk_state_store(sk, TCP_CLOSE);
-			sk->sk_state_change(sk);
 			break;
 		}
 
-		if (sk->sk_shutdown == SHUTDOWN_MASK ||
-		    sk->sk_state == TCP_CLOSE)
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-		else
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+		mptcp_close_wake_up(sk);
 	}
 }
 
@@ -388,13 +412,79 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
 	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
 }
 
-static void mptcp_check_data_fin(struct sock *sk)
+static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+	if (subflow->request_join && !subflow->fully_established)
+		return false;
+
+	/* only send if our side has not closed yet */
+	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
+static bool tcp_can_send_ack(const struct sock *ssk)
+{
+	return !((1 << inet_sk_state_load(ssk)) &
+	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE));
+}
+
+static void mptcp_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		if (tcp_can_send_ack(ssk))
+			tcp_send_ack(ssk);
+		release_sock(ssk);
+	}
+}
+
+static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk)
+{
+	int ret;
+
+	lock_sock(ssk);
+	ret = tcp_can_send_ack(ssk);
+	if (ret)
+		tcp_cleanup_rbuf(ssk, 1);
+	release_sock(ssk);
+	return ret;
+}
+
+static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
+{
+	struct sock *ack_hint = READ_ONCE(msk->ack_hint);
+	struct mptcp_subflow_context *subflow;
+
+	/* if the hinted ssk is still active, try to use it */
+	if (likely(ack_hint)) {
+		mptcp_for_each_subflow(msk, subflow) {
+			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+			if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk))
+				return;
+		}
+	}
+
+	/* otherwise pick the first active subflow */
+	mptcp_for_each_subflow(msk, subflow)
+		if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow)))
+			return;
+}
+
+static bool mptcp_check_data_fin(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	u64 rcv_data_fin_seq;
+	bool ret = false;
 
 	if (__mptcp_check_fallback(msk) || !msk->first)
-		return;
+		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.
@@ -410,8 +500,6 @@ static void mptcp_check_data_fin(struct sock *sk)
 	 */
 
 	if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
-		struct mptcp_subflow_context *subflow;
-
 		WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
 		WRITE_ONCE(msk->rcv_data_fin, 0);
 
@@ -428,7 +516,6 @@ static void mptcp_check_data_fin(struct sock *sk)
 			break;
 		case TCP_FIN_WAIT2:
 			inet_sk_state_store(sk, TCP_CLOSE);
-			// @@ Close subflows now?
 			break;
 		default:
 			/* Other states not expected */
@@ -436,23 +523,12 @@ static void mptcp_check_data_fin(struct sock *sk)
 			break;
 		}
 
+		ret = true;
 		mptcp_set_timeout(sk, NULL);
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-			lock_sock(ssk);
-			tcp_send_ack(ssk);
-			release_sock(ssk);
-		}
-
-		sk->sk_state_change(sk);
-
-		if (sk->sk_shutdown == SHUTDOWN_MASK ||
-		    sk->sk_state == TCP_CLOSE)
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-		else
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+		mptcp_send_ack(msk);
+		mptcp_close_wake_up(sk);
 	}
+	return ret;
 }
 
 static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
@@ -464,12 +540,22 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	unsigned int moved = 0;
 	bool more_data_avail;
 	struct tcp_sock *tp;
-	u32 old_copied_seq;
 	bool done = false;
+	int sk_rbuf;
+
+	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+		int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+		if (unlikely(ssk_rbuf > sk_rbuf)) {
+			WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+			sk_rbuf = ssk_rbuf;
+		}
+	}
 
 	pr_debug("msk=%p ssk=%p", msk, ssk);
 	tp = tcp_sk(ssk);
-	old_copied_seq = tp->copied_seq;
 	do {
 		u32 map_remaining, offset;
 		u32 seq = tp->copied_seq;
@@ -528,20 +614,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		WRITE_ONCE(tp->copied_seq, seq);
 		more_data_avail = mptcp_subflow_data_available(ssk);
 
-		if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+		if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
 			done = true;
 			break;
 		}
 	} while (more_data_avail);
+	WRITE_ONCE(msk->ack_hint, ssk);
 
 	*bytes += moved;
-	if (tp->copied_seq != old_copied_seq)
-		tcp_cleanup_rbuf(ssk, 1);
-
 	return done;
 }
 
-static bool mptcp_ofo_queue(struct mptcp_sock *msk)
+static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *skb, *tail;
@@ -587,43 +671,43 @@ static bool mptcp_ofo_queue(struct mptcp_sock *msk)
 /* In most cases we will be able to lock the mptcp socket.  If its already
  * owned, we need to defer to the work queue to avoid ABBA deadlock.
  */
-static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
 	unsigned int moved = 0;
 
-	if (READ_ONCE(sk->sk_lock.owned))
-		return false;
-
-	if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock)))
-		return false;
-
-	/* must re-check after taking the lock */
-	if (!READ_ONCE(sk->sk_lock.owned)) {
-		__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
-		mptcp_ofo_queue(msk);
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return;
 
-		/* If the moves have caught up with the DATA_FIN sequence number
-		 * it's time to ack the DATA_FIN and change socket state, but
-		 * this is not a good place to change state. Let the workqueue
-		 * do it.
-		 */
-		if (mptcp_pending_data_fin(sk, NULL) &&
-		    schedule_work(&msk->work))
-			sock_hold(sk);
-	}
+	mptcp_data_lock(sk);
 
-	spin_unlock_bh(&sk->sk_lock.slock);
+	__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+	__mptcp_ofo_queue(msk);
 
-	return moved > 0;
+	/* If the moves have caught up with the DATA_FIN sequence number
+	 * it's time to ack the DATA_FIN and change socket state, but
+	 * this is not a good place to change state. Let the workqueue
+	 * do it.
+	 */
+	if (mptcp_pending_data_fin(sk, NULL))
+		mptcp_schedule_work(sk);
+	mptcp_data_unlock(sk);
 }
 
 void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	int sk_rbuf, ssk_rbuf;
 	bool wake;
 
+	/* The peer can send data while we are shutting down this
+	 * subflow at msk destruction time, but we must avoid enqueuing
+	 * more data to the msk receive queue
+	 */
+	if (unlikely(subflow->disposable))
+		return;
+
 	/* move_skbs_to_msk below can legitly clear the data_avail flag,
 	 * but we will need later to properly woke the reader, cache its
 	 * value
@@ -632,30 +716,23 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	if (wake)
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 
-	if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
-	    move_skbs_to_msk(msk, ssk))
-		goto wake;
+	ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+	if (unlikely(ssk_rbuf > sk_rbuf))
+		sk_rbuf = ssk_rbuf;
 
-	/* don't schedule if mptcp sk is (still) over limit */
-	if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+	/* over limit? can't append more skbs to msk */
+	if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
 		goto wake;
 
-	/* mptcp socket is owned, release_cb should retry */
-	if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
-			      &sk->sk_tsq_flags)) {
-		sock_hold(sk);
+	move_skbs_to_msk(msk, ssk);
 
-		/* need to try again, its possible release_cb() has already
-		 * been called after the test_and_set_bit() above.
-		 */
-		move_skbs_to_msk(msk, ssk);
-	}
 wake:
 	if (wake)
 		sk->sk_data_ready(sk);
 }
 
-static void __mptcp_flush_join_list(struct mptcp_sock *msk)
+void __mptcp_flush_join_list(struct mptcp_sock *msk)
 {
 	if (likely(list_empty(&msk->join_list)))
 		return;
@@ -675,6 +752,10 @@ static void mptcp_reset_timer(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned long tout;
 
+	/* prevent rescheduling on close */
+	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+		return;
+
 	/* should never be called with mptcp level timer cleared */
 	tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
 	if (WARN_ON_ONCE(!tout))
@@ -682,23 +763,23 @@ static void mptcp_reset_timer(struct sock *sk)
 	sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
 }
 
-void mptcp_data_acked(struct sock *sk)
+bool mptcp_schedule_work(struct sock *sk)
 {
-	mptcp_reset_timer(sk);
-
-	if ((!test_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags) ||
-	     (inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
-	    schedule_work(&mptcp_sk(sk)->work))
+	if (inet_sk_state_load(sk) != TCP_CLOSE &&
+	    schedule_work(&mptcp_sk(sk)->work)) {
+		/* each subflow already holds a reference to the sk, and the
+		 * workqueue is invoked by a subflow, so sk can't go away here.
+		 */
 		sock_hold(sk);
+		return true;
+	}
+	return false;
 }
 
 void mptcp_subflow_eof(struct sock *sk)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	if (!test_and_set_bit(MPTCP_WORK_EOF, &msk->flags) &&
-	    schedule_work(&msk->work))
-		sock_hold(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)
@@ -709,8 +790,10 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 
 	mptcp_for_each_subflow(msk, subflow)
 		receivers += !subflow->rx_eof;
+	if (receivers)
+		return;
 
-	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+	if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
 		/* hopefully temporary hack: propagate shutdown status
 		 * to msk, when all subflows agree on it
 		 */
@@ -720,16 +803,21 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 		sk->sk_data_ready(sk);
 	}
-}
-
-static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
-{
-	const struct sock *sk = (const struct sock *)msk;
 
-	if (!msk->cached_ext)
-		msk->cached_ext = __skb_ext_alloc(sk->sk_allocation);
-
-	return !!msk->cached_ext;
+	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)
@@ -754,8 +842,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
 	if (!tcp_skb_can_collapse_to(skb))
 		return false;
 
-	/* can collapse only if MPTCP level sequence is in order */
-	return mpext && mpext->data_seq + mpext->data_len == write_seq;
+	/* can collapse only if MPTCP level sequence is in order and this
+	 * mapping has not been xmitted yet
+	 */
+	return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+	       !mpext->frozen;
 }
 
 static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
@@ -763,9 +854,125 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
 				       const struct mptcp_data_frag *df)
 {
 	return df && pfrag->page == df->page &&
+		pfrag->size - pfrag->offset > 0 &&
 		df->data_seq + df->data_len == msk->write_seq;
 }
 
+static int mptcp_wmem_with_overhead(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	int ret, skbs;
+
+	ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
+	skbs = (msk->tx_pending_data + size) / msk->size_goal_cache;
+	if (skbs < msk->skb_tx_cache.qlen)
+		return ret;
+
+	return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER);
+}
+
+static void __mptcp_wmem_reserve(struct sock *sk, int size)
+{
+	int amount = mptcp_wmem_with_overhead(sk, size);
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	WARN_ON_ONCE(msk->wmem_reserved);
+	if (amount <= sk->sk_forward_alloc)
+		goto reserve;
+
+	/* under memory pressure try to reserve at most a single page
+	 * otherwise try to reserve the full estimate and fallback
+	 * to a single page before entering the error path
+	 */
+	if ((tcp_under_memory_pressure(sk) && amount > PAGE_SIZE) ||
+	    !sk_wmem_schedule(sk, amount)) {
+		if (amount <= PAGE_SIZE)
+			goto nomem;
+
+		amount = PAGE_SIZE;
+		if (!sk_wmem_schedule(sk, amount))
+			goto nomem;
+	}
+
+reserve:
+	msk->wmem_reserved = amount;
+	sk->sk_forward_alloc -= amount;
+	return;
+
+nomem:
+	/* we will wait for memory on next allocation */
+	msk->wmem_reserved = -1;
+}
+
+static void __mptcp_update_wmem(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (!msk->wmem_reserved)
+		return;
+
+	if (msk->wmem_reserved < 0)
+		msk->wmem_reserved = 0;
+	if (msk->wmem_reserved > 0) {
+		sk->sk_forward_alloc += msk->wmem_reserved;
+		msk->wmem_reserved = 0;
+	}
+}
+
+static bool mptcp_wmem_alloc(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	/* check for pre-existing error condition */
+	if (msk->wmem_reserved < 0)
+		return false;
+
+	if (msk->wmem_reserved >= size)
+		goto account;
+
+	mptcp_data_lock(sk);
+	if (!sk_wmem_schedule(sk, size)) {
+		mptcp_data_unlock(sk);
+		return false;
+	}
+
+	sk->sk_forward_alloc -= size;
+	msk->wmem_reserved += size;
+	mptcp_data_unlock(sk);
+
+account:
+	msk->wmem_reserved -= size;
+	return true;
+}
+
+static void mptcp_wmem_uncharge(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (msk->wmem_reserved < 0)
+		msk->wmem_reserved = 0;
+	msk->wmem_reserved += size;
+}
+
+static void mptcp_mem_reclaim_partial(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	/* if we are experiencing a transint allocation error,
+	 * the forward allocation memory has been already
+	 * released
+	 */
+	if (msk->wmem_reserved < 0)
+		return;
+
+	mptcp_data_lock(sk);
+	sk->sk_forward_alloc += msk->wmem_reserved;
+	sk_mem_reclaim_partial(sk);
+	msk->wmem_reserved = sk->sk_forward_alloc;
+	sk->sk_forward_alloc = 0;
+	mptcp_data_unlock(sk);
+}
+
 static void dfrag_uncharge(struct sock *sk, int len)
 {
 	sk_mem_uncharge(sk, len);
@@ -781,21 +988,7 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
 	put_page(dfrag->page);
 }
 
-static bool mptcp_is_writeable(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-
-	if (!sk_stream_is_writeable((struct sock *)msk))
-		return false;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (sk_stream_is_writeable(subflow->tcp_sock))
-			return true;
-	}
-	return false;
-}
-
-static void mptcp_clean_una(struct sock *sk)
+static void __mptcp_clean_una(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
@@ -806,13 +999,15 @@ static void mptcp_clean_una(struct sock *sk)
 	 * plain TCP
 	 */
 	if (__mptcp_check_fallback(msk))
-		atomic64_set(&msk->snd_una, msk->write_seq);
-	snd_una = atomic64_read(&msk->snd_una);
+		msk->snd_una = READ_ONCE(msk->snd_nxt);
 
+	snd_una = msk->snd_una;
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
 		if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
 			break;
 
+		if (WARN_ON_ONCE(dfrag == msk->first_pending))
+			break;
 		dfrag_clear(sk, dfrag);
 		cleaned = true;
 	}
@@ -821,12 +1016,13 @@ static void mptcp_clean_una(struct sock *sk)
 	if (dfrag && after64(snd_una, dfrag->data_seq)) {
 		u64 delta = snd_una - dfrag->data_seq;
 
-		if (WARN_ON_ONCE(delta > dfrag->data_len))
+		if (WARN_ON_ONCE(delta > dfrag->already_sent))
 			goto out;
 
 		dfrag->data_seq += delta;
 		dfrag->offset += delta;
 		dfrag->data_len -= delta;
+		dfrag->already_sent -= delta;
 
 		dfrag_uncharge(sk, delta);
 		cleaned = true;
@@ -834,19 +1030,42 @@ static void mptcp_clean_una(struct sock *sk)
 
 out:
 	if (cleaned) {
-		sk_mem_reclaim_partial(sk);
-
-		/* Only wake up writers if a subflow is ready */
-		if (mptcp_is_writeable(msk)) {
-			set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
-			smp_mb__after_atomic();
+		if (tcp_under_memory_pressure(sk)) {
+			__mptcp_update_wmem(sk);
+			sk_mem_reclaim_partial(sk);
+		}
 
-			/* set SEND_SPACE before sk_stream_write_space clears
-			 * NOSPACE
-			 */
-			sk_stream_write_space(sk);
+		if (sk_stream_is_writeable(sk)) {
+			/* pairs with memory barrier in mptcp_poll */
+			smp_mb();
+			if (test_and_clear_bit(MPTCP_NOSPACE, &msk->flags))
+				sk_stream_write_space(sk);
 		}
 	}
+
+	if (snd_una == READ_ONCE(msk->snd_nxt)) {
+		if (msk->timer_ival)
+			mptcp_stop_timer(sk);
+	} else {
+		mptcp_reset_timer(sk);
+	}
+}
+
+static void mptcp_enter_memory_pressure(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	bool first = true;
+
+	sk_stream_moderate_sndbuf(sk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		if (first)
+			tcp_enter_memory_pressure(ssk);
+		sk_stream_moderate_sndbuf(ssk);
+		first = false;
+	}
 }
 
 /* ensure we get enough memory for the frag hdr, beyond some minimal amount of
@@ -858,8 +1077,7 @@ static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 					pfrag, sk->sk_allocation)))
 		return true;
 
-	sk->sk_prot->enter_memory_pressure(sk);
-	sk_stream_moderate_sndbuf(sk);
+	mptcp_enter_memory_pressure(sk);
 	return false;
 }
 
@@ -875,149 +1093,241 @@ mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
 	dfrag->data_seq = msk->write_seq;
 	dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
 	dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+	dfrag->already_sent = 0;
 	dfrag->page = pfrag->page;
 
 	return dfrag;
 }
 
-static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
-			      struct msghdr *msg, struct mptcp_data_frag *dfrag,
-			      long *timeo, int *pmss_now,
-			      int *ps_goal)
+struct mptcp_sendmsg_info {
+	int mss_now;
+	int size_goal;
+	u16 limit;
+	u16 sent;
+	unsigned int flags;
+};
+
+static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
+				    int avail_size)
+{
+	u64 window_end = mptcp_wnd_end(msk);
+
+	if (__mptcp_check_fallback(msk))
+		return avail_size;
+
+	if (!before64(data_seq + avail_size, window_end)) {
+		u64 allowed_size = window_end - data_seq;
+
+		return min_t(unsigned int, allowed_size, avail_size);
+	}
+
+	return avail_size;
+}
+
+static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp)
+{
+	struct skb_ext *mpext = __skb_ext_alloc(gfp);
+
+	if (!mpext)
+		return false;
+	__skb_ext_set(skb, SKB_EXT_MPTCP, mpext);
+	return true;
+}
+
+static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
+	if (likely(skb)) {
+		if (likely(__mptcp_add_ext(skb, gfp))) {
+			skb_reserve(skb, MAX_TCP_HEADER);
+			skb->reserved_tailroom = skb->end - skb->tail;
+			return skb;
+		}
+		__kfree_skb(skb);
+	} else {
+		mptcp_enter_memory_pressure(sk);
+	}
+	return NULL;
+}
+
+static bool mptcp_tx_cache_refill(struct sock *sk, int size,
+				  struct sk_buff_head *skbs, int *total_ts)
 {
-	int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
-	bool dfrag_collapsed, can_collapse = false;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct mptcp_ext *mpext = NULL;
-	bool retransmission = !!dfrag;
-	struct sk_buff *skb, *tail;
-	struct page_frag *pfrag;
-	struct page *page;
-	u64 *write_seq;
-	size_t psize;
-
-	/* use the mptcp page cache so that we can easily move the data
-	 * from one substream to another, but do per subflow memory accounting
-	 * Note: pfrag is used only !retransmission, but the compiler if
-	 * fooled into a warning if we don't init here
-	 */
-	pfrag = sk_page_frag(sk);
-	if (!retransmission) {
-		write_seq = &msk->write_seq;
-		page = pfrag->page;
+	struct sk_buff *skb;
+	int space_needed;
+
+	if (unlikely(tcp_under_memory_pressure(sk))) {
+		mptcp_mem_reclaim_partial(sk);
+
+		/* under pressure pre-allocate at most a single skb */
+		if (msk->skb_tx_cache.qlen)
+			return true;
+		space_needed = msk->size_goal_cache;
 	} else {
-		write_seq = &dfrag->data_seq;
-		page = dfrag->page;
+		space_needed = msk->tx_pending_data + size -
+			       msk->skb_tx_cache.qlen * msk->size_goal_cache;
 	}
 
-	/* compute copy limit */
-	mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
-	*pmss_now = mss_now;
-	*ps_goal = size_goal;
-	avail_size = size_goal;
-	skb = tcp_write_queue_tail(ssk);
+	while (space_needed > 0) {
+		skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			/* under memory pressure, try to pass the caller a
+			 * single skb to allow forward progress
+			 */
+			while (skbs->qlen > 1) {
+				skb = __skb_dequeue_tail(skbs);
+				__kfree_skb(skb);
+			}
+			return skbs->qlen > 0;
+		}
+
+		*total_ts += skb->truesize;
+		__skb_queue_tail(skbs, skb);
+		space_needed -= msk->size_goal_cache;
+	}
+	return true;
+}
+
+static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sk_buff *skb;
+
+	if (ssk->sk_tx_skb_cache) {
+		skb = ssk->sk_tx_skb_cache;
+		if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) &&
+			     !__mptcp_add_ext(skb, gfp)))
+			return false;
+		return true;
+	}
+
+	skb = skb_peek(&msk->skb_tx_cache);
 	if (skb) {
-		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+		if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+			skb = __skb_dequeue(&msk->skb_tx_cache);
+			if (WARN_ON_ONCE(!skb))
+				return false;
+
+			mptcp_wmem_uncharge(sk, skb->truesize);
+			ssk->sk_tx_skb_cache = skb;
+			return true;
+		}
+
+		/* over memory limit, no point to try to allocate a new skb */
+		return false;
+	}
+
+	skb = __mptcp_do_alloc_tx_skb(sk, gfp);
+	if (!skb)
+		return false;
+
+	if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+		ssk->sk_tx_skb_cache = skb;
+		return true;
+	}
+	kfree_skb(skb);
+	return false;
+}
+
+static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk)
+{
+	return !ssk->sk_tx_skb_cache &&
+	       !skb_peek(&mptcp_sk(sk)->skb_tx_cache) &&
+	       tcp_under_memory_pressure(sk);
+}
+
+static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
+{
+	if (unlikely(mptcp_must_reclaim_memory(sk, ssk)))
+		mptcp_mem_reclaim_partial(sk);
+	return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
+}
 
+static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+			      struct mptcp_data_frag *dfrag,
+			      struct mptcp_sendmsg_info *info)
+{
+	u64 data_seq = dfrag->data_seq + info->sent;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	bool zero_window_probe = false;
+	struct mptcp_ext *mpext = NULL;
+	struct sk_buff *skb, *tail;
+	bool can_collapse = false;
+	int size_bias = 0;
+	int avail_size;
+	size_t ret = 0;
+
+	pr_debug("msk=%p ssk=%p sending dfrag at seq=%lld len=%d already sent=%d",
+		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
+
+	/* compute send limit */
+	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
+	avail_size = info->size_goal;
+	msk->size_goal_cache = info->size_goal;
+	skb = tcp_write_queue_tail(ssk);
+	if (skb) {
 		/* Limit the write to the size available in the
 		 * current skb, if any, so that we create at most a new skb.
 		 * Explicitly tells TCP internals to avoid collapsing on later
 		 * queue management operation, to avoid breaking the ext <->
 		 * SSN association set here
 		 */
-		can_collapse = (size_goal - skb->len > 0) &&
-			      mptcp_skb_can_collapse_to(*write_seq, skb, mpext);
-		if (!can_collapse)
+		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+		can_collapse = (info->size_goal - skb->len > 0) &&
+			 mptcp_skb_can_collapse_to(data_seq, skb, mpext);
+		if (!can_collapse) {
 			TCP_SKB_CB(skb)->eor = 1;
-		else
-			avail_size = size_goal - skb->len;
-	}
-
-	if (!retransmission) {
-		/* reuse tail pfrag, if possible, or carve a new one from the
-		 * page allocator
-		 */
-		dfrag = mptcp_rtx_tail(sk);
-		offset = pfrag->offset;
-		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
-		if (!dfrag_collapsed) {
-			dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
-			offset = dfrag->offset;
-			frag_truesize = dfrag->overhead;
-		}
-		psize = min_t(size_t, pfrag->size - offset, avail_size);
-
-		/* Copy to page */
-		pr_debug("left=%zu", msg_data_left(msg));
-		psize = copy_page_from_iter(pfrag->page, offset,
-					    min_t(size_t, msg_data_left(msg),
-						  psize),
-					    &msg->msg_iter);
-		pr_debug("left=%zu", msg_data_left(msg));
-		if (!psize)
-			return -EINVAL;
-
-		if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
-			iov_iter_revert(&msg->msg_iter, psize);
-			return -ENOMEM;
+		} else {
+			size_bias = skb->len;
+			avail_size = info->size_goal - skb->len;
 		}
-	} else {
-		offset = dfrag->offset;
-		psize = min_t(size_t, dfrag->data_len, avail_size);
 	}
 
-	/* tell the TCP stack to delay the push so that we can safely
-	 * access the skb after the sendpages call
-	 */
-	ret = do_tcp_sendpages(ssk, page, offset, psize,
-			       msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
-	if (ret <= 0) {
-		if (!retransmission)
-			iov_iter_revert(&msg->msg_iter, psize);
-		return ret;
-	}
+	/* Zero window and all data acked? Probe. */
+	avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
+	if (avail_size == 0) {
+		u64 snd_una = READ_ONCE(msk->snd_una);
 
-	frag_truesize += ret;
-	if (!retransmission) {
-		if (unlikely(ret < psize))
-			iov_iter_revert(&msg->msg_iter, psize - ret);
+		if (skb || snd_una != msk->snd_nxt)
+			return 0;
+		zero_window_probe = true;
+		data_seq = snd_una - 1;
+		avail_size = 1;
+	}
 
-		/* send successful, keep track of sent data for mptcp-level
-		 * retransmission
-		 */
-		dfrag->data_len += ret;
-		if (!dfrag_collapsed) {
-			get_page(dfrag->page);
-			list_add_tail(&dfrag->list, &msk->rtx_queue);
-			sk_wmem_queued_add(sk, frag_truesize);
-		} else {
-			sk_wmem_queued_add(sk, ret);
-		}
+	if (WARN_ON_ONCE(info->sent > info->limit ||
+			 info->limit > dfrag->data_len))
+		return 0;
 
-		/* charge data on mptcp rtx queue to the master socket
-		 * Note: we charge such data both to sk and ssk
-		 */
-		sk->sk_forward_alloc -= frag_truesize;
+	ret = info->limit - info->sent;
+	tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags,
+			      dfrag->page, dfrag->offset + info->sent, &ret);
+	if (!tail) {
+		tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+		return -ENOMEM;
 	}
 
-	/* if the tail skb extension is still the cached one, collapsing
-	 * really happened. Note: we can't check for 'same skb' as the sk_buff
-	 * hdr on tail can be transmitted, freed and re-allocated by the
-	 * do_tcp_sendpages() call
+	/* if the tail skb is still the cached one, collapsing really happened.
 	 */
-	tail = tcp_write_queue_tail(ssk);
-	if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
-		WARN_ON_ONCE(!can_collapse);
+	if (skb == tail) {
+		TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
 		mpext->data_len += ret;
+		WARN_ON_ONCE(!can_collapse);
+		WARN_ON_ONCE(zero_window_probe);
 		goto out;
 	}
 
-	skb = tcp_write_queue_tail(ssk);
-	mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
-	msk->cached_ext = NULL;
+	mpext = skb_ext_find(tail, SKB_EXT_MPTCP);
+	if (WARN_ON_ONCE(!mpext)) {
+		/* should never reach here, stream corrupted */
+		return -EINVAL;
+	}
 
 	memset(mpext, 0, sizeof(*mpext));
-	mpext->data_seq = *write_seq;
+	mpext->data_seq = data_seq;
 	mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
 	mpext->data_len = ret;
 	mpext->use_map = 1;
@@ -1027,44 +1337,17 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		 mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 		 mpext->dsn64);
 
+	if (zero_window_probe) {
+		mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+		mpext->frozen = 1;
+		ret = 0;
+		tcp_push_pending_frames(ssk);
+	}
 out:
-	if (!retransmission)
-		pfrag->offset += frag_truesize;
-	WRITE_ONCE(*write_seq, *write_seq + ret);
 	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-
 	return ret;
 }
 
-static void mptcp_nospace(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-
-	clear_bit(MPTCP_SEND_SPACE, &msk->flags);
-	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		struct socket *sock = READ_ONCE(ssk->sk_socket);
-
-		/* enables ssk->write_space() callbacks */
-		if (sock)
-			set_bit(SOCK_NOSPACE, &sock->flags);
-	}
-}
-
-static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
-{
-	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
-	if (subflow->request_join && !subflow->fully_established)
-		return false;
-
-	/* only send if our side has not closed yet */
-	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
-}
-
 #define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
 					 sizeof(struct tcphdr) - \
 					 MAX_TCP_OPTION_SPACE - \
@@ -1089,9 +1372,6 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
 	sock_owned_by_me((struct sock *)msk);
 
 	*sndbuf = 0;
-	if (!mptcp_ext_cache_refill(msk))
-		return NULL;
-
 	if (__mptcp_check_fallback(msk)) {
 		if (!msk->first)
 			return NULL;
@@ -1154,27 +1434,160 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
 	return NULL;
 }
 
-static void ssk_check_wmem(struct mptcp_sock *msk)
+static void mptcp_push_release(struct sock *sk, struct sock *ssk,
+			       struct mptcp_sendmsg_info *info)
+{
+	mptcp_set_timeout(sk, ssk);
+	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+	release_sock(ssk);
+}
+
+static void mptcp_push_pending(struct sock *sk, unsigned int flags)
+{
+	struct sock *prev_ssk = NULL, *ssk = NULL;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_sendmsg_info info = {
+				.flags = flags,
+	};
+	struct mptcp_data_frag *dfrag;
+	int len, copied = 0;
+	u32 sndbuf;
+
+	while ((dfrag = mptcp_send_head(sk))) {
+		info.sent = dfrag->already_sent;
+		info.limit = dfrag->data_len;
+		len = dfrag->data_len - dfrag->already_sent;
+		while (len > 0) {
+			int ret = 0;
+
+			prev_ssk = ssk;
+			__mptcp_flush_join_list(msk);
+			ssk = mptcp_subflow_get_send(msk, &sndbuf);
+
+			/* do auto tuning */
+			if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+			    sndbuf > READ_ONCE(sk->sk_sndbuf))
+				WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
+			/* try to keep the subflow socket lock across
+			 * consecutive xmit on the same socket
+			 */
+			if (ssk != prev_ssk && prev_ssk)
+				mptcp_push_release(sk, prev_ssk, &info);
+			if (!ssk)
+				goto out;
+
+			if (ssk != prev_ssk || !prev_ssk)
+				lock_sock(ssk);
+
+			/* keep it simple and always provide a new skb for the
+			 * subflow, even if we will not use it when collapsing
+			 * on the pending one
+			 */
+			if (!mptcp_alloc_tx_skb(sk, ssk)) {
+				mptcp_push_release(sk, ssk, &info);
+				goto out;
+			}
+
+			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+			if (ret <= 0) {
+				mptcp_push_release(sk, ssk, &info);
+				goto out;
+			}
+
+			info.sent += ret;
+			dfrag->already_sent += ret;
+			msk->snd_nxt += ret;
+			msk->snd_burst -= ret;
+			msk->tx_pending_data -= ret;
+			copied += ret;
+			len -= ret;
+		}
+		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+	}
+
+	/* at this point we held the socket lock for the last subflow we used */
+	if (ssk)
+		mptcp_push_release(sk, ssk, &info);
+
+out:
+	if (copied) {
+		/* start the timer, if it's not pending */
+		if (!mptcp_timer_pending(sk))
+			mptcp_reset_timer(sk);
+		__mptcp_check_send_data_fin(sk);
+	}
+}
+
+static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 {
-	if (unlikely(!mptcp_is_writeable(msk)))
-		mptcp_nospace(msk);
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_sendmsg_info info;
+	struct mptcp_data_frag *dfrag;
+	int len, copied = 0;
+
+	info.flags = 0;
+	while ((dfrag = mptcp_send_head(sk))) {
+		info.sent = dfrag->already_sent;
+		info.limit = dfrag->data_len;
+		len = dfrag->data_len - dfrag->already_sent;
+		while (len > 0) {
+			int ret = 0;
+
+			/* do auto tuning */
+			if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+			    ssk->sk_sndbuf > READ_ONCE(sk->sk_sndbuf))
+				WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf);
+
+			if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) {
+				__mptcp_update_wmem(sk);
+				sk_mem_reclaim_partial(sk);
+			}
+			if (!__mptcp_alloc_tx_skb(sk, ssk, GFP_ATOMIC))
+				goto out;
+
+			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+			if (ret <= 0)
+				goto out;
+
+			info.sent += ret;
+			dfrag->already_sent += ret;
+			msk->snd_nxt += ret;
+			msk->snd_burst -= ret;
+			msk->tx_pending_data -= ret;
+			copied += ret;
+			len -= ret;
+		}
+		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+	}
+
+out:
+	/* __mptcp_alloc_tx_skb could have released some wmem and we are
+	 * not going to flush it via release_sock()
+	 */
+	__mptcp_update_wmem(sk);
+	if (copied) {
+		mptcp_set_timeout(sk, ssk);
+		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+			 info.size_goal);
+		if (msk->snd_data_fin_enable &&
+		    msk->snd_nxt + 1 == msk->write_seq)
+			mptcp_schedule_work(sk);
+	}
 }
 
 static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
-	int mss_now = 0, size_goal = 0, ret = 0;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct page_frag *pfrag;
 	size_t copied = 0;
-	struct sock *ssk;
-	u32 sndbuf;
-	bool tx_ok;
+	int ret = 0;
 	long timeo;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
 
-	lock_sock(sk);
+	mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, len));
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -1185,130 +1598,97 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	pfrag = sk_page_frag(sk);
-restart:
-	mptcp_clean_una(sk);
-
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
-		ret = -EPIPE;
-		goto out;
-	}
 
-	__mptcp_flush_join_list(msk);
-	ssk = mptcp_subflow_get_send(msk, &sndbuf);
-	while (!sk_stream_memory_free(sk) ||
-	       !ssk ||
-	       !mptcp_page_frag_refill(ssk, pfrag)) {
-		if (ssk) {
-			/* make sure retransmit timer is
-			 * running before we wait for memory.
-			 *
-			 * The retransmit timer might be needed
-			 * to make the peer send an up-to-date
-			 * MPTCP Ack.
-			 */
-			mptcp_set_timeout(sk, ssk);
-			if (!mptcp_timer_pending(sk))
-				mptcp_reset_timer(sk);
-		}
+	while (msg_data_left(msg)) {
+		int total_ts, frag_truesize = 0;
+		struct mptcp_data_frag *dfrag;
+		struct sk_buff_head skbs;
+		bool dfrag_collapsed;
+		size_t psize, offset;
 
-		mptcp_nospace(msk);
-		ret = sk_stream_wait_memory(sk, &timeo);
-		if (ret)
-			goto out;
-
-		mptcp_clean_una(sk);
-
-		ssk = mptcp_subflow_get_send(msk, &sndbuf);
-		if (list_empty(&msk->conn_list)) {
-			ret = -ENOTCONN;
+		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
+			ret = -EPIPE;
 			goto out;
 		}
-	}
 
-	/* do auto tuning */
-	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
-	    sndbuf > READ_ONCE(sk->sk_sndbuf))
-		WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+		/* reuse tail pfrag, if possible, or carve a new one from the
+		 * page allocator
+		 */
+		dfrag = mptcp_pending_tail(sk);
+		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+		if (!dfrag_collapsed) {
+			if (!sk_stream_memory_free(sk))
+				goto wait_for_memory;
 
-	pr_debug("conn_list->subflow=%p", ssk);
+			if (!mptcp_page_frag_refill(sk, pfrag))
+				goto wait_for_memory;
 
-	lock_sock(ssk);
-	tx_ok = msg_data_left(msg);
-	while (tx_ok) {
-		ret = mptcp_sendmsg_frag(sk, ssk, msg, NULL, &timeo, &mss_now,
-					 &size_goal);
-		if (ret < 0) {
-			if (ret == -EAGAIN && timeo > 0) {
-				mptcp_set_timeout(sk, ssk);
-				release_sock(ssk);
-				goto restart;
-			}
-			break;
+			dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
+			frag_truesize = dfrag->overhead;
 		}
 
-		/* burst can be negative, we will try move to the next subflow
-		 * at selection time, if possible.
+		/* we do not bound vs wspace, to allow a single packet.
+		 * memory accounting will prevent execessive memory usage
+		 * anyway
 		 */
-		msk->snd_burst -= ret;
-		copied += ret;
-
-		tx_ok = msg_data_left(msg);
-		if (!tx_ok)
-			break;
+		offset = dfrag->offset + dfrag->data_len;
+		psize = pfrag->size - offset;
+		psize = min_t(size_t, psize, msg_data_left(msg));
+		total_ts = psize + frag_truesize;
+		__skb_queue_head_init(&skbs);
+		if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts))
+			goto wait_for_memory;
+
+		if (!mptcp_wmem_alloc(sk, total_ts)) {
+			__skb_queue_purge(&skbs);
+			goto wait_for_memory;
+		}
 
-		if (!sk_stream_memory_free(ssk) ||
-		    !mptcp_page_frag_refill(ssk, pfrag) ||
-		    !mptcp_ext_cache_refill(msk)) {
-			tcp_push(ssk, msg->msg_flags, mss_now,
-				 tcp_sk(ssk)->nonagle, size_goal);
-			mptcp_set_timeout(sk, ssk);
-			release_sock(ssk);
-			goto restart;
+		skb_queue_splice_tail(&skbs, &msk->skb_tx_cache);
+		if (copy_page_from_iter(dfrag->page, offset, psize,
+					&msg->msg_iter) != psize) {
+			mptcp_wmem_uncharge(sk, psize + frag_truesize);
+			ret = -EFAULT;
+			goto out;
 		}
 
-		/* memory is charged to mptcp level socket as well, i.e.
-		 * if msg is very large, mptcp socket may run out of buffer
-		 * space.  mptcp_clean_una() will release data that has
-		 * been acked at mptcp level in the mean time, so there is
-		 * a good chance we can continue sending data right away.
-		 *
-		 * Normally, when the tcp subflow can accept more data, then
-		 * so can the MPTCP socket.  However, we need to cope with
-		 * peers that might lag behind in their MPTCP-level
-		 * acknowledgements, i.e.  data might have been acked at
-		 * tcp level only.  So, we must also check the MPTCP socket
-		 * limits before we send more data.
+		/* data successfully copied into the write queue */
+		copied += psize;
+		dfrag->data_len += psize;
+		frag_truesize += psize;
+		pfrag->offset += frag_truesize;
+		WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
+
+		/* charge data on mptcp pending queue to the msk socket
+		 * Note: we charge such data both to sk and ssk
 		 */
-		if (unlikely(!sk_stream_memory_free(sk))) {
-			tcp_push(ssk, msg->msg_flags, mss_now,
-				 tcp_sk(ssk)->nonagle, size_goal);
-			mptcp_clean_una(sk);
-			if (!sk_stream_memory_free(sk)) {
-				/* can't send more for now, need to wait for
-				 * MPTCP-level ACKs from peer.
-				 *
-				 * Wakeup will happen via mptcp_clean_una().
-				 */
-				mptcp_set_timeout(sk, ssk);
-				release_sock(ssk);
-				goto restart;
-			}
+		sk_wmem_queued_add(sk, frag_truesize);
+		if (!dfrag_collapsed) {
+			get_page(dfrag->page);
+			list_add_tail(&dfrag->list, &msk->rtx_queue);
+			if (!msk->first_pending)
+				WRITE_ONCE(msk->first_pending, dfrag);
 		}
+		pr_debug("msk=%p dfrag at seq=%lld len=%d sent=%d new=%d", msk,
+			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
+			 !dfrag_collapsed);
+
+		continue;
+
+wait_for_memory:
+		set_bit(MPTCP_NOSPACE, &msk->flags);
+		mptcp_push_pending(sk, msg->msg_flags);
+		ret = sk_stream_wait_memory(sk, &timeo);
+		if (ret)
+			goto out;
 	}
 
-	mptcp_set_timeout(sk, ssk);
 	if (copied) {
-		tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
-			 size_goal);
-
-		/* start the timer, if it's not pending */
-		if (!mptcp_timer_pending(sk))
-			mptcp_reset_timer(sk);
+		msk->tx_pending_data += copied;
+		mptcp_push_pending(sk, msg->msg_flags);
 	}
 
-	release_sock(ssk);
 out:
-	ssk_check_wmem(msk);
 	release_sock(sk);
 	return copied ? : ret;
 }
@@ -1332,11 +1712,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len)
 {
-	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *skb;
 	int copied = 0;
 
-	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
+	while ((skb = skb_peek(&msk->receive_queue)) != NULL) {
 		u32 offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
 		u32 count = min_t(size_t, len - copied, data_len);
@@ -1356,7 +1735,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 			break;
 		}
 
-		__skb_unlink(skb, &sk->sk_receive_queue);
+		/* we will bulk release the skb memory later */
+		skb->destructor = NULL;
+		msk->rmem_released += skb->truesize;
+		__skb_unlink(skb, &msk->receive_queue);
 		__kfree_skb(skb);
 
 		if (copied >= len)
@@ -1464,32 +1846,68 @@ new_measure:
 	msk->rcvq_space.time = mstamp;
 }
 
-static bool __mptcp_move_skbs(struct mptcp_sock *msk)
+static void __mptcp_update_rmem(struct sock *sk)
 {
-	unsigned int moved = 0;
-	bool done;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	/* avoid looping forever below on racing close */
-	if (((struct sock *)msk)->sk_state == TCP_CLOSE)
-		return false;
+	if (!msk->rmem_released)
+		return;
+
+	atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
+	sk_mem_uncharge(sk, msk->rmem_released);
+	msk->rmem_released = 0;
+}
+
+static void __mptcp_splice_receive_queue(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue);
+}
+
+static bool __mptcp_move_skbs(struct mptcp_sock *msk, unsigned int rcv)
+{
+	struct sock *sk = (struct sock *)msk;
+	unsigned int moved = 0;
+	bool ret, done;
 
 	__mptcp_flush_join_list(msk);
 	do {
 		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+		bool slowpath;
 
-		if (!ssk)
+		/* we can have data pending in the subflows only if the msk
+		 * receive buffer was full at subflow_data_ready() time,
+		 * that is an unlikely slow path.
+		 */
+		if (likely(!ssk))
 			break;
 
-		lock_sock(ssk);
+		slowpath = lock_sock_fast(ssk);
+		mptcp_data_lock(sk);
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
-		release_sock(ssk);
+		mptcp_data_unlock(sk);
+		if (moved && rcv) {
+			WRITE_ONCE(msk->rmem_pending, min(rcv, moved));
+			tcp_cleanup_rbuf(ssk, 1);
+			WRITE_ONCE(msk->rmem_pending, 0);
+		}
+		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
-	if (mptcp_ofo_queue(msk) || moved > 0) {
-		mptcp_check_data_fin((struct sock *)msk);
-		return true;
+	/* acquire the data lock only if some input data is pending */
+	ret = moved > 0;
+	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
+	    !skb_queue_empty_lockless(&sk->sk_receive_queue)) {
+		mptcp_data_lock(sk);
+		__mptcp_update_rmem(sk);
+		ret |= __mptcp_ofo_queue(msk);
+		__mptcp_splice_receive_queue(sk);
+		mptcp_data_unlock(sk);
 	}
-	return false;
+	if (ret)
+		mptcp_check_data_fin((struct sock *)msk);
+	return !skb_queue_empty(&msk->receive_queue);
 }
 
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
@@ -1503,15 +1921,19 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
 		return -EOPNOTSUPP;
 
-	lock_sock(sk);
+	mptcp_lock_sock(sk, __mptcp_splice_receive_queue(sk));
+	if (unlikely(sk->sk_state == TCP_LISTEN)) {
+		copied = -ENOTCONN;
+		goto out_err;
+	}
+
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	len = min_t(size_t, len, INT_MAX);
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-	__mptcp_flush_join_list(msk);
 
-	while (len > (size_t)copied) {
-		int bytes_read;
+	while (copied < len) {
+		int bytes_read, old_space;
 
 		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied);
 		if (unlikely(bytes_read < 0)) {
@@ -1522,10 +1944,15 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 		copied += bytes_read;
 
-		if (skb_queue_empty(&sk->sk_receive_queue) &&
-		    __mptcp_move_skbs(msk))
+		if (skb_queue_empty(&msk->receive_queue) &&
+		    __mptcp_move_skbs(msk, len - copied))
 			continue;
 
+		/* be sure to advertise window change */
+		old_space = READ_ONCE(msk->old_wspace);
+		if ((tcp_space(sk) - old_space) >= old_space)
+			mptcp_cleanup_rbuf(msk);
+
 		/* only the master socket status is relevant here. The exit
 		 * conditions mirror closely tcp_recvmsg()
 		 */
@@ -1548,8 +1975,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
 				mptcp_check_for_eof(msk);
 
-			if (sk->sk_shutdown & RCV_SHUTDOWN)
+			if (sk->sk_shutdown & RCV_SHUTDOWN) {
+				/* race breaker: the shutdown could be after the
+				 * previous receive queue check
+				 */
+				if (__mptcp_move_skbs(msk, len - copied))
+					continue;
 				break;
+			}
 
 			if (sk->sk_state == TCP_CLOSE) {
 				copied = -ENOTCONN;
@@ -1571,14 +2004,15 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		mptcp_wait_data(sk, &timeo);
 	}
 
-	if (skb_queue_empty(&sk->sk_receive_queue)) {
+	if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
+	    skb_queue_empty(&msk->receive_queue)) {
 		/* entire backlog drained, clear DATA_READY. */
 		clear_bit(MPTCP_DATA_READY, &msk->flags);
 
 		/* .. race-breaker: ssk might have gotten new data
 		 * after last __mptcp_move_skbs() returned false.
 		 */
-		if (unlikely(__mptcp_move_skbs(msk)))
+		if (unlikely(__mptcp_move_skbs(msk, 0)))
 			set_bit(MPTCP_DATA_READY, &msk->flags);
 	} else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) {
 		/* data to read but mptcp_wait_data() cleared DATA_READY */
@@ -1587,7 +2021,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 out_err:
 	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
 		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
-		 skb_queue_empty(&sk->sk_receive_queue), copied);
+		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
 	mptcp_rcv_space_adjust(msk, copied);
 
 	release_sock(sk);
@@ -1598,13 +2032,8 @@ static void mptcp_retransmit_handler(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) {
-		mptcp_stop_timer(sk);
-	} else {
-		set_bit(MPTCP_WORK_RTX, &msk->flags);
-		if (schedule_work(&msk->work))
-			sock_hold(sk);
-	}
+	set_bit(MPTCP_WORK_RTX, &msk->flags);
+	mptcp_schedule_work(sk);
 }
 
 static void mptcp_retransmit_timer(struct timer_list *t)
@@ -1626,6 +2055,14 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 	sock_put(sk);
 }
 
+static void mptcp_timeout_timer(struct timer_list *t)
+{
+	struct sock *sk = from_timer(sk, t, sk_timer);
+
+	mptcp_schedule_work(sk);
+	sock_put(sk);
+}
+
 /* Find an idle subflow.  Return NULL if there is unacked data at tcp
  * level.
  *
@@ -1639,7 +2076,7 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 	sock_owned_by_me((const struct sock *)msk);
 
 	if (__mptcp_check_fallback(msk))
-		return msk->first;
+		return NULL;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -1648,8 +2085,11 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 			continue;
 
 		/* still data outstanding at TCP level?  Don't retransmit. */
-		if (!tcp_write_queue_empty(ssk))
+		if (!tcp_write_queue_empty(ssk)) {
+			if (inet_csk(ssk)->icsk_ca_state >= TCP_CA_Loss)
+				continue;
 			return NULL;
+		}
 
 		if (subflow->backup) {
 			if (!backup)
@@ -1672,20 +2112,44 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
  * parent socket.
  */
 void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
-		       struct mptcp_subflow_context *subflow,
-		       long timeout)
+		       struct mptcp_subflow_context *subflow)
 {
-	struct socket *sock = READ_ONCE(ssk->sk_socket);
+	bool dispose_socket = false;
+	struct socket *sock;
 
 	list_del(&subflow->node);
 
-	if (sock && sock != sk->sk_socket) {
-		/* outgoing subflow */
-		sock_release(sock);
+	lock_sock(ssk);
+
+	/* if we are invoked by the msk cleanup code, the subflow is
+	 * already orphaned
+	 */
+	sock = ssk->sk_socket;
+	if (sock) {
+		dispose_socket = sock != sk->sk_socket;
+		sock_orphan(ssk);
+	}
+
+	subflow->disposable = 1;
+
+	/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
+	 * the ssk has been already destroyed, we just need to release the
+	 * reference owned by msk;
+	 */
+	if (!inet_csk(ssk)->icsk_ulp_ops) {
+		kfree_rcu(subflow, rcu);
 	} else {
-		/* incoming subflow */
-		tcp_close(ssk, timeout);
+		/* otherwise tcp will dispose of the ssk and subflow ctx */
+		__tcp_close(ssk, 0);
+
+		/* close acquired an extra ref */
+		__sock_put(ssk);
 	}
+	release_sock(ssk);
+	if (dispose_socket)
+		iput(SOCK_INODE(sock));
+
+	sock_put(ssk);
 }
 
 static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
@@ -1704,6 +2168,10 @@ static void pm_work(struct mptcp_sock *msk)
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
 		mptcp_pm_nl_add_addr_received(msk);
 	}
+	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
+		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
+		mptcp_pm_nl_add_addr_send_ack(msk);
+	}
 	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
 		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
 		mptcp_pm_nl_rm_addr_received(msk);
@@ -1730,40 +2198,102 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
 		if (inet_sk_state_load(ssk) != TCP_CLOSE)
 			continue;
 
-		__mptcp_close_ssk((struct sock *)msk, ssk, subflow, 0);
+		__mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+	}
+}
+
+static bool mptcp_check_close_timeout(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)
+		return true;
+
+	/* if all subflows are in closed status don't bother with additional
+	 * timeout
+	 */
+	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+		if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
+		    TCP_CLOSE)
+			return false;
+	}
+	return true;
+}
+
+static void mptcp_check_fastclose(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+
+	if (likely(!READ_ONCE(msk->rcv_fastclose)))
+		return;
+
+	mptcp_token_destroy(msk);
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(tcp_sk);
+		if (tcp_sk->sk_state != TCP_CLOSE) {
+			tcp_send_active_reset(tcp_sk, GFP_ATOMIC);
+			tcp_set_state(tcp_sk, TCP_CLOSE);
+		}
+		release_sock(tcp_sk);
 	}
+
+	inet_sk_state_store(sk, TCP_CLOSE);
+	sk->sk_shutdown = SHUTDOWN_MASK;
+	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
+	set_bit(MPTCP_DATA_READY, &msk->flags);
+	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
+
+	mptcp_close_wake_up(sk);
 }
 
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
 	struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
-	int orig_len, orig_offset, mss_now = 0, size_goal = 0;
+	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
-	u64 orig_write_seq;
 	size_t copied = 0;
-	struct msghdr msg = {
-		.msg_flags = MSG_DONTWAIT,
-	};
-	long timeo = 0;
+	int state, ret;
 
 	lock_sock(sk);
-	mptcp_clean_una(sk);
+	state = sk->sk_state;
+	if (unlikely(state == TCP_CLOSE))
+		goto unlock;
+
 	mptcp_check_data_fin_ack(sk);
 	__mptcp_flush_join_list(msk);
+
+	mptcp_check_fastclose(msk);
+
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
 		__mptcp_close_subflow(msk);
 
-	__mptcp_move_skbs(msk);
-
 	if (msk->pm.status)
 		pm_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_data_fin(sk);
 
+	/* if the msk data is completely acked, or the socket timedout,
+	 * there is no point in keeping around an orphaned sk
+	 */
+	if (sock_flag(sk, SOCK_DEAD) &&
+	    (mptcp_check_close_timeout(sk) ||
+	    (state != sk->sk_state &&
+	    ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+		inet_sk_state_store(sk, TCP_CLOSE);
+		__mptcp_destroy_sock(sk);
+		goto unlock;
+	}
+
 	if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		goto unlock;
 
@@ -1771,39 +2301,30 @@ static void mptcp_worker(struct work_struct *work)
 	if (!dfrag)
 		goto unlock;
 
-	if (!mptcp_ext_cache_refill(msk))
-		goto reset_unlock;
-
 	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		goto reset_unlock;
 
 	lock_sock(ssk);
 
-	orig_len = dfrag->data_len;
-	orig_offset = dfrag->offset;
-	orig_write_seq = dfrag->data_seq;
-	while (dfrag->data_len > 0) {
-		int ret = mptcp_sendmsg_frag(sk, ssk, &msg, dfrag, &timeo,
-					     &mss_now, &size_goal);
-		if (ret < 0)
+	/* limit retransmission to the bytes already sent on some subflows */
+	info.sent = 0;
+	info.limit = dfrag->already_sent;
+	while (info.sent < dfrag->already_sent) {
+		if (!mptcp_alloc_tx_skb(sk, ssk))
+			break;
+
+		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+		if (ret <= 0)
 			break;
 
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
 		copied += ret;
-		dfrag->data_len -= ret;
-		dfrag->offset += ret;
-
-		if (!mptcp_ext_cache_refill(msk))
-			break;
+		info.sent += ret;
 	}
 	if (copied)
-		tcp_push(ssk, msg.msg_flags, mss_now, tcp_sk(ssk)->nonagle,
-			 size_goal);
-
-	dfrag->data_seq = orig_write_seq;
-	dfrag->offset = orig_offset;
-	dfrag->data_len = orig_len;
+		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+			 info.size_goal);
 
 	mptcp_set_timeout(sk, ssk);
 	release_sock(ssk);
@@ -1826,10 +2347,17 @@ static int __mptcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&msk->conn_list);
 	INIT_LIST_HEAD(&msk->join_list);
 	INIT_LIST_HEAD(&msk->rtx_queue);
-	__set_bit(MPTCP_SEND_SPACE, &msk->flags);
 	INIT_WORK(&msk->work, mptcp_worker);
+	__skb_queue_head_init(&msk->receive_queue);
+	__skb_queue_head_init(&msk->skb_tx_cache);
 	msk->out_of_order_queue = RB_ROOT;
+	msk->first_pending = NULL;
+	msk->wmem_reserved = 0;
+	msk->rmem_released = 0;
+	msk->tx_pending_data = 0;
+	msk->size_goal_cache = TCP_BASE_MSS;
 
+	msk->ack_hint = NULL;
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 
@@ -1837,7 +2365,7 @@ static int __mptcp_init_sock(struct sock *sk)
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-
+	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
 	return 0;
 }
 
@@ -1871,11 +2399,15 @@ static void __mptcp_clear_xmit(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
+	struct sk_buff *skb;
 
-	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
-
+	WRITE_ONCE(msk->first_pending, NULL);
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
 		dfrag_clear(sk, dfrag);
+	while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) {
+		sk->sk_forward_alloc += skb->truesize;
+		kfree_skb(skb);
+	}
 }
 
 static void mptcp_cancel_work(struct sock *sk)
@@ -1883,7 +2415,7 @@ static void mptcp_cancel_work(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	if (cancel_work_sync(&msk->work))
-		sock_put(sk);
+		__sock_put(sk);
 }
 
 void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
@@ -1941,42 +2473,67 @@ static int mptcp_close_state(struct sock *sk)
 	return next & TCP_ACTION_FIN;
 }
 
-static void mptcp_close(struct sock *sk, long timeout)
+static void __mptcp_check_send_data_fin(struct sock *sk)
 {
-	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	LIST_HEAD(conn_list);
 
-	lock_sock(sk);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+		 msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+		 msk->snd_nxt, msk->write_seq);
 
-	if (sk->sk_state == TCP_LISTEN) {
-		inet_sk_state_store(sk, TCP_CLOSE);
-		goto cleanup;
-	} else if (sk->sk_state == TCP_CLOSE) {
-		goto cleanup;
-	}
+	/* we still need to enqueue subflows or not really shutting down,
+	 * skip this
+	 */
+	if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
+	    mptcp_send_head(sk))
+		return;
+
+	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)) {
-		goto update_state;
-	} else if (mptcp_close_state(sk)) {
-		pr_debug("Sending DATA_FIN sk=%p", sk);
-		WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
-		WRITE_ONCE(msk->snd_data_fin_enable, 1);
+		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);
+	__mptcp_flush_join_list(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
-			mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK);
-		}
+		mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
 	}
+}
 
-	sk_stream_wait_close(sk, timeout);
+static void __mptcp_wr_shutdown(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
-update_state:
-	inet_sk_state_store(sk, TCP_CLOSE);
+	pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+		 msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+		 !!mptcp_send_head(sk));
+
+	/* will be ignored by fallback sockets */
+	WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
+	WRITE_ONCE(msk->snd_data_fin_enable, 1);
+
+	__mptcp_check_send_data_fin(sk);
+}
+
+static void __mptcp_destroy_sock(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	LIST_HEAD(conn_list);
+
+	pr_debug("msk=%p", msk);
 
-cleanup:
 	/* be sure to always acquire the join list lock, to sync vs
 	 * mptcp_finish_join().
 	 */
@@ -1985,20 +2542,77 @@ cleanup:
 	spin_unlock_bh(&msk->join_list_lock);
 	list_splice_init(&msk->conn_list, &conn_list);
 
-	__mptcp_clear_xmit(sk);
-
-	release_sock(sk);
+	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
+	msk->pm.status = 0;
 
 	list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		__mptcp_close_ssk(sk, ssk, subflow);
 	}
 
-	mptcp_cancel_work(sk);
+	sk->sk_prot->destroy(sk);
+
+	WARN_ON_ONCE(msk->wmem_reserved);
+	WARN_ON_ONCE(msk->rmem_released);
+	sk_stream_kill_queues(sk);
+	xfrm_sk_free_policy(sk);
+	sk_refcnt_debug_release(sk);
+	sock_put(sk);
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+	struct mptcp_subflow_context *subflow;
+	bool do_cancel_work = false;
 
-	__skb_queue_purge(&sk->sk_receive_queue);
+	lock_sock(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
-	sk_common_release(sk);
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
+		inet_sk_state_store(sk, TCP_CLOSE);
+		goto cleanup;
+	}
+
+	if (mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
+
+	sk_stream_wait_close(sk, timeout);
+
+cleanup:
+	/* orphan all the subflows */
+	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
+	list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow, dispose_socket;
+		struct socket *sock;
+
+		slow = lock_sock_fast(ssk);
+		sock = ssk->sk_socket;
+		dispose_socket = sock && sock != sk->sk_socket;
+		sock_orphan(ssk);
+		unlock_sock_fast(ssk, slow);
+
+		/* for the outgoing subflows we additionally need to free
+		 * the associated socket
+		 */
+		if (dispose_socket)
+			iput(SOCK_INODE(sock));
+	}
+	sock_orphan(sk);
+
+	sock_hold(sk);
+	pr_debug("msk=%p state=%d", sk, sk->sk_state);
+	if (sk->sk_state == TCP_CLOSE) {
+		__mptcp_destroy_sock(sk);
+		do_cancel_work = true;
+	} else {
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+	}
+	release_sock(sk);
+	if (do_cancel_work)
+		mptcp_cancel_work(sk);
+	sock_put(sk);
 }
 
 static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
@@ -2069,13 +2683,17 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	WRITE_ONCE(msk->fully_established, false);
 
 	msk->write_seq = subflow_req->idsn + 1;
-	atomic64_set(&msk->snd_una, msk->write_seq);
+	msk->snd_nxt = msk->write_seq;
+	msk->snd_una = msk->write_seq;
+	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+
 	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
 		msk->remote_key = mp_opt->sndr_key;
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		WRITE_ONCE(msk->ack_seq, ack_seq);
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	}
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
@@ -2102,6 +2720,8 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
+
+	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
 static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
@@ -2126,7 +2746,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *new_mptcp_sock;
-		struct sock *ssk = newsk;
 
 		subflow = mptcp_subflow_ctx(newsk);
 		new_mptcp_sock = subflow->conn;
@@ -2141,21 +2760,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 
 		/* acquire the 2nd reference for the owning socket */
 		sock_hold(new_mptcp_sock);
-
-		local_bh_disable();
-		bh_lock_sock(new_mptcp_sock);
-		msk = mptcp_sk(new_mptcp_sock);
-		msk->first = newsk;
-
 		newsk = new_mptcp_sock;
-		mptcp_copy_inaddrs(newsk, ssk);
-		list_add(&subflow->node, &msk->conn_list);
-
-		mptcp_rcv_space_init(msk, ssk);
-		bh_unlock_sock(new_mptcp_sock);
-
-		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-		local_bh_enable();
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
 		MPTCP_INC_STATS(sock_net(sk),
 				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
@@ -2166,6 +2772,13 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 
 void mptcp_destroy_common(struct mptcp_sock *msk)
 {
+	struct sock *sk = (struct sock *)msk;
+
+	__mptcp_clear_xmit(sk);
+
+	/* move to sk_receive_queue, sk_stream_kill_queues will purge it */
+	skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
+
 	skb_rbtree_purge(&msk->out_of_order_queue);
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
@@ -2175,9 +2788,6 @@ static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (msk->cached_ext)
-		__skb_ext_put(msk->cached_ext);
-
 	mptcp_destroy_common(msk);
 	sk_sockets_allocated_dec(sk);
 }
@@ -2292,16 +2902,58 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	return -EOPNOTSUPP;
 }
 
-#define MPTCP_DEFERRED_ALL (TCPF_DELACK_TIMER_DEFERRED | \
-			    TCPF_WRITE_TIMER_DEFERRED)
+void __mptcp_data_acked(struct sock *sk)
+{
+	if (!sock_owned_by_user(sk))
+		__mptcp_clean_una(sk);
+	else
+		set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags);
 
-/* this is very alike tcp_release_cb() but we must handle differently a
- * different set of events
- */
+	if (mptcp_pending_data_fin_ack(sk))
+		mptcp_schedule_work(sk);
+}
+
+void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk)
+{
+	if (!mptcp_send_head(sk))
+		return;
+
+	if (!sock_owned_by_user(sk))
+		__mptcp_subflow_push_pending(sk, ssk);
+	else
+		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+}
+
+#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)
+
+/* processes deferred events and flush wmem */
 static void mptcp_release_cb(struct sock *sk)
 {
 	unsigned long flags, nflags;
 
+	/* push_pending may touch wmem_reserved, do it before the later
+	 * cleanup
+	 */
+	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
+		__mptcp_clean_una(sk);
+	if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) {
+		/* mptcp_push_pending() acquires the subflow socket lock
+		 *
+		 * 1) can't be invoked in atomic scope
+		 * 2) must avoid ABBA deadlock with msk socket spinlock: the RX
+		 *    datapath acquires the msk socket spinlock while helding
+		 *    the subflow socket lock
+		 */
+
+		spin_unlock_bh(&sk->sk_lock.slock);
+		mptcp_push_pending(sk, 0);
+		spin_lock_bh(&sk->sk_lock.slock);
+	}
+
+	/* clear any wmem reservation and errors */
+	__mptcp_update_wmem(sk);
+	__mptcp_update_rmem(sk);
+
 	do {
 		flags = sk->sk_tsq_flags;
 		if (!(flags & MPTCP_DEFERRED_ALL))
@@ -2311,15 +2963,6 @@ static void mptcp_release_cb(struct sock *sk)
 
 	sock_release_ownership(sk);
 
-	if (flags & TCPF_DELACK_TIMER_DEFERRED) {
-		struct mptcp_sock *msk = mptcp_sk(sk);
-		struct sock *ssk;
-
-		ssk = mptcp_subflow_recv_lookup(msk);
-		if (!ssk || !schedule_work(&msk->work))
-			__sock_put(sk);
-	}
-
 	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
 		mptcp_retransmit_handler(sk);
 		__sock_put(sk);
@@ -2377,9 +3020,11 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->remote_key, subflow->remote_key);
 	WRITE_ONCE(msk->local_key, subflow->local_key);
 	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->ack_seq, ack_seq);
+	WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	WRITE_ONCE(msk->can_ack, 1);
-	atomic64_set(&msk->snd_una, msk->write_seq);
+	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
 	mptcp_pm_new_connection(msk, 0);
 
@@ -2395,9 +3040,9 @@ static void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
-bool mptcp_finish_join(struct sock *sk)
+bool mptcp_finish_join(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct sock *parent = (void *)msk;
 	struct socket *parent_sock;
@@ -2418,12 +3063,14 @@ bool mptcp_finish_join(struct sock *sk)
 	/* active connections are already on conn_list, and we can't acquire
 	 * msk lock here.
 	 * use the join list lock as synchronization point and double-check
-	 * msk status to avoid racing with mptcp_close()
+	 * msk status to avoid racing with __mptcp_destroy_sock()
 	 */
 	spin_lock_bh(&msk->join_list_lock);
 	ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
-	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) {
 		list_add_tail(&subflow->node, &msk->join_list);
+		sock_hold(ssk);
+	}
 	spin_unlock_bh(&msk->join_list_lock);
 	if (!ret)
 		return false;
@@ -2432,19 +3079,12 @@ bool mptcp_finish_join(struct sock *sk)
 	 * at close time
 	 */
 	parent_sock = READ_ONCE(parent->sk_socket);
-	if (parent_sock && !sk->sk_socket)
-		mptcp_sock_graft(sk, parent_sock);
+	if (parent_sock && !ssk->sk_socket)
+		mptcp_sock_graft(ssk, parent_sock);
 	subflow->map_seq = READ_ONCE(msk->ack_seq);
 	return true;
 }
 
-static bool mptcp_memory_free(const struct sock *sk, int wake)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
-}
-
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -2465,7 +3105,6 @@ static struct proto mptcp_prot = {
 	.sockets_allocated	= &mptcp_sockets_allocated,
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
-	.stream_memory_free	= mptcp_memory_free,
 	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
 	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
 	.sysctl_mem	= sysctl_tcp_mem,
@@ -2610,6 +3249,23 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
 		struct mptcp_sock *msk = mptcp_sk(newsock->sk);
 		struct mptcp_subflow_context *subflow;
+		struct sock *newsk = newsock->sk;
+		bool slowpath;
+
+		slowpath = lock_sock_fast(newsk);
+
+		/* PM/worker can now acquire the first subflow socket
+		 * lock without racing with listener queue cleanup,
+		 * we can notify it, if needed.
+		 */
+		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);
+
+		mptcp_copy_inaddrs(newsk, msk->first);
+		mptcp_rcv_space_init(msk, msk->first);
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
@@ -2621,6 +3277,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+		unlock_sock_fast(newsk, slowpath);
 	}
 
 	if (inet_csk_listen_poll(ssock->sk))
@@ -2639,6 +3296,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 	       0;
 }
 
+static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+
+	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
+		return 0;
+
+	if (sk_stream_is_writeable(sk))
+		return EPOLLOUT | EPOLLWRNORM;
+
+	set_bit(MPTCP_NOSPACE, &msk->flags);
+	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
+	if (sk_stream_is_writeable(sk))
+		return EPOLLOUT | EPOLLWRNORM;
+
+	return 0;
+}
+
 static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait)
 {
@@ -2657,8 +3332,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
-		if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
-			mask |= EPOLLOUT | EPOLLWRNORM;
+		mask |= mptcp_check_writeable(msk);
 	}
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
@@ -2669,12 +3343,12 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 static int mptcp_shutdown(struct socket *sock, int how)
 {
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
-	struct mptcp_subflow_context *subflow;
+	struct sock *sk = sock->sk;
 	int ret = 0;
 
 	pr_debug("sk=%p, how=%d", msk, how);
 
-	lock_sock(sock->sk);
+	lock_sock(sk);
 
 	how++;
 	if ((how & ~SHUTDOWN_MASK) || !how) {
@@ -2683,45 +3357,22 @@ static int mptcp_shutdown(struct socket *sock, int how)
 	}
 
 	if (sock->state == SS_CONNECTING) {
-		if ((1 << sock->sk->sk_state) &
+		if ((1 << sk->sk_state) &
 		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
 			sock->state = SS_DISCONNECTING;
 		else
 			sock->state = SS_CONNECTED;
 	}
 
-	/* If we've already sent a FIN, or it's a closed state, skip this. */
-	if (__mptcp_check_fallback(msk)) {
-		if (how == SHUT_WR || how == SHUT_RDWR)
-			inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
-
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
-			mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
-		}
-	} else if ((how & SEND_SHUTDOWN) &&
-		   ((1 << sock->sk->sk_state) &
-		    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
-		     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) &&
-		   mptcp_close_state(sock->sk)) {
-		__mptcp_flush_join_list(msk);
-
-		WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
-		WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
-			mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
-		}
-	}
+	sk->sk_shutdown |= how;
+	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
 
 	/* Wake up anyone sleeping in poll. */
-	sock->sk->sk_state_change(sock->sk);
+	sk->sk_state_change(sk);
 
 out_unlock:
-	release_sock(sock->sk);
+	release_sock(sk);
 
 	return ret;
 }
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 13ab89dc1914..7cf9d110b85f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -23,6 +23,7 @@
 #define OPTION_MPTCP_ADD_ADDR	BIT(6)
 #define OPTION_MPTCP_ADD_ADDR6	BIT(7)
 #define OPTION_MPTCP_RM_ADDR	BIT(8)
+#define OPTION_MPTCP_FASTCLOSE	BIT(9)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0
@@ -49,15 +50,16 @@
 #define TCPOLEN_MPTCP_DSS_MAP64		14
 #define TCPOLEN_MPTCP_DSS_CHECKSUM	2
 #define TCPOLEN_MPTCP_ADD_ADDR		16
-#define TCPOLEN_MPTCP_ADD_ADDR_PORT	18
+#define TCPOLEN_MPTCP_ADD_ADDR_PORT	20
 #define TCPOLEN_MPTCP_ADD_ADDR_BASE	8
-#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	10
+#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	12
 #define TCPOLEN_MPTCP_ADD_ADDR6		28
-#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	30
+#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	32
 #define TCPOLEN_MPTCP_ADD_ADDR6_BASE	20
-#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	22
-#define TCPOLEN_MPTCP_PORT_LEN		2
+#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	24
+#define TCPOLEN_MPTCP_PORT_LEN		4
 #define TCPOLEN_MPTCP_RM_ADDR_BASE	4
+#define TCPOLEN_MPTCP_FASTCLOSE		12
 
 /* MPTCP MP_JOIN flags */
 #define MPTCPOPT_BACKUP		BIT(0)
@@ -86,11 +88,20 @@
 
 /* MPTCP socket flags */
 #define MPTCP_DATA_READY	0
-#define MPTCP_SEND_SPACE	1
+#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
+#define MPTCP_PUSH_PENDING	6
+#define MPTCP_CLEAN_UNA		7
+
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+	return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1)	before64(seq1, seq2)
 
 struct mptcp_options_received {
 	u64	sndr_key;
@@ -101,6 +112,7 @@ struct mptcp_options_received {
 	u16	data_len;
 	u16	mp_capable : 1,
 		mp_join : 1,
+		fastclose : 1,
 		dss : 1,
 		add_addr : 1,
 		rm_addr : 1,
@@ -110,7 +122,7 @@ struct mptcp_options_received {
 	u32	token;
 	u32	nonce;
 	u64	thmac;
-	u8	hmac[20];
+	u8	hmac[MPTCPOPT_HMAC_LEN];
 	u8	join_id;
 	u8	use_map:1,
 		dsn64:1,
@@ -153,11 +165,21 @@ struct mptcp_addr_info {
 
 enum mptcp_pm_status {
 	MPTCP_PM_ADD_ADDR_RECEIVED,
+	MPTCP_PM_ADD_ADDR_SEND_ACK,
 	MPTCP_PM_RM_ADDR_RECEIVED,
 	MPTCP_PM_ESTABLISHED,
+	MPTCP_PM_ALREADY_ESTABLISHED,	/* persistent status, set after ESTABLISHED event */
 	MPTCP_PM_SUBFLOW_ESTABLISHED,
 };
 
+enum mptcp_addr_signal_status {
+	MPTCP_ADD_ADDR_SIGNAL,
+	MPTCP_ADD_ADDR_ECHO,
+	MPTCP_ADD_ADDR_IPV6,
+	MPTCP_ADD_ADDR_PORT,
+	MPTCP_RM_ADDR_SIGNAL,
+};
+
 struct mptcp_pm_data {
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
@@ -165,13 +187,11 @@ struct mptcp_pm_data {
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
-	bool		add_addr_signal;
-	bool		rm_addr_signal;
+	u8		addr_signal;
 	bool		server_side;
 	bool		work_pending;
 	bool		accept_addr;
 	bool		accept_subflow;
-	bool		add_addr_echo;
 	u8		add_addr_signaled;
 	u8		add_addr_accepted;
 	u8		local_addr_used;
@@ -187,9 +207,10 @@ struct mptcp_pm_data {
 struct mptcp_data_frag {
 	struct list_head list;
 	u64 data_seq;
-	int data_len;
-	int offset;
-	int overhead;
+	u16 data_len;
+	u16 offset;
+	u16 overhead;
+	u16 already_sent;
 	struct page *page;
 };
 
@@ -200,27 +221,40 @@ struct mptcp_sock {
 	u64		local_key;
 	u64		remote_key;
 	u64		write_seq;
+	u64		snd_nxt;
 	u64		ack_seq;
+	u64		rcv_wnd_sent;
 	u64		rcv_data_fin_seq;
+	int		wmem_reserved;
 	struct sock	*last_snd;
 	int		snd_burst;
-	atomic64_t	snd_una;
+	int		old_wspace;
+	u64		snd_una;
+	u64		wnd_end;
 	unsigned long	timer_ival;
 	u32		token;
+	int		rmem_pending;
+	int		rmem_released;
 	unsigned long	flags;
 	bool		can_ack;
 	bool		fully_established;
 	bool		rcv_data_fin;
 	bool		snd_data_fin_enable;
+	bool		rcv_fastclose;
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	spinlock_t	join_list_lock;
+	struct sock	*ack_hint;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
+	struct sk_buff_head receive_queue;
+	struct sk_buff_head skb_tx_cache;	/* this is wmem accounted */
+	int		tx_pending_data;
+	int		size_goal_cache;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
+	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct skb_ext	*cached_ext;	/* for the next sendmsg */
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
@@ -232,6 +266,22 @@ struct mptcp_sock {
 	} rcvq_space;
 };
 
+#define mptcp_lock_sock(___sk, cb) do {					\
+	struct sock *__sk = (___sk); /* silence macro reuse warning */	\
+	might_sleep();							\
+	spin_lock_bh(&__sk->sk_lock.slock);				\
+	if (__sk->sk_lock.owned)					\
+		__lock_sock(__sk);					\
+	cb;								\
+	__sk->sk_lock.owned = 1;					\
+	spin_unlock(&__sk->sk_lock.slock);				\
+	mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_);		\
+	local_bh_enable();						\
+} while (0)
+
+#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
+#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)
+
 #define mptcp_for_each_subflow(__msk, __subflow)			\
 	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
 
@@ -240,11 +290,46 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
 	return (struct mptcp_sock *)sk;
 }
 
+static inline int __mptcp_space(const struct sock *sk)
+{
+	return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
+{
+	const struct mptcp_sock *msk = mptcp_sk(sk);
+
+	return READ_ONCE(msk->first_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_data_frag *cur;
+
+	cur = msk->first_pending;
+	return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
+						     list_next_entry(cur, list);
+}
+
+static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (!msk->first_pending)
+		return NULL;
+
+	if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
+		return NULL;
+
+	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+}
+
 static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (list_empty(&msk->rtx_queue))
+	if (!before64(msk->snd_nxt, READ_ONCE(msk->snd_una)))
 		return NULL;
 
 	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
@@ -312,7 +397,8 @@ struct mptcp_subflow_context {
 		mpc_map : 1,
 		backup : 1,
 		rx_eof : 1,
-		can_ack : 1;	    /* only after processing the remote a key */
+		can_ack : 1,        /* only after processing the remote a key */
+		disposable : 1;	    /* ctx can be free at ulp release time */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -361,15 +447,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
 	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
 }
 
+static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
+					     struct mptcp_subflow_context *subflow)
+{
+	sock_hold(mptcp_subflow_tcp_sock(subflow));
+	spin_lock_bh(&msk->join_list_lock);
+	list_add_tail(&subflow->node, &msk->join_list);
+	spin_unlock_bh(&msk->join_list_lock);
+}
+
 int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
 void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
 void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
-		       struct mptcp_subflow_context *subflow,
-		       long timeout);
+		       struct mptcp_subflow_context *subflow);
 void mptcp_subflow_reset(struct sock *ssk);
 
 /* called with sk socket lock held */
@@ -407,9 +502,18 @@ static inline bool mptcp_is_fully_established(struct sock *sk)
 void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
-void mptcp_data_acked(struct sock *sk);
+bool mptcp_schedule_work(struct sock *sk);
+void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk);
+void __mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
+void __mptcp_flush_join_list(struct mptcp_sock *msk);
+static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->snd_data_fin_enable) &&
+	       READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
+}
+
 void mptcp_destroy_common(struct mptcp_sock *msk);
 
 void __init mptcp_token_init(void);
@@ -444,6 +548,7 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk,
 void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 struct mptcp_pm_add_entry *
@@ -452,30 +557,51 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
-			   bool echo);
+			   bool echo, bool port);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
 int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.add_addr_signal);
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
+}
+
+static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
+}
+
+static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
+}
+
+static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT);
 }
 
 static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.rm_addr_signal);
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_RM_ADDR_SIGNAL);
 }
 
-static inline unsigned int mptcp_add_addr_len(int family, bool echo)
+static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
 {
-	if (family == AF_INET)
-		return echo ? TCPOLEN_MPTCP_ADD_ADDR_BASE
-			    : TCPOLEN_MPTCP_ADD_ADDR;
-	return echo ? TCPOLEN_MPTCP_ADD_ADDR6_BASE : TCPOLEN_MPTCP_ADD_ADDR6;
+	u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+
+	if (family == AF_INET6)
+		len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+	if (!echo)
+		len += MPTCPOPT_THMAC_LEN;
+	if (port)
+		len += TCPOLEN_MPTCP_PORT_LEN;
+
+	return len;
 }
 
 bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			      struct mptcp_addr_info *saddr, bool *echo);
+			      struct mptcp_addr_info *saddr, bool *echo, bool *port);
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     u8 *rm_id);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
@@ -485,6 +611,7 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
 void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
@@ -494,13 +621,6 @@ static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
 	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
 }
 
-static inline bool before64(__u64 seq1, __u64 seq2)
-{
-	return (__s64)(seq1 - seq2) < 0;
-}
-
-#define after64(seq2, seq1)	before64(seq1, seq2)
-
 void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
 
 static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c21a852a6ffa..278cbe3e539e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -112,9 +112,14 @@ static int __subflow_init_req(struct request_sock *req, const struct sock *sk_li
 	return 0;
 }
 
-static void subflow_init_req(struct request_sock *req,
-			     const struct sock *sk_listener,
-			     struct sk_buff *skb)
+/* Init mptcp request socket.
+ *
+ * Returns an error code if a JOIN has failed and a TCP reset
+ * should be sent.
+ */
+static int subflow_init_req(struct request_sock *req,
+			    const struct sock *sk_listener,
+			    struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
@@ -125,7 +130,7 @@ static void subflow_init_req(struct request_sock *req,
 
 	ret = __subflow_init_req(req, sk_listener);
 	if (ret)
-		return;
+		return 0;
 
 	mptcp_get_options(skb, &mp_opt);
 
@@ -133,7 +138,7 @@ static void subflow_init_req(struct request_sock *req,
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
 		if (mp_opt.mp_join)
-			return;
+			return 0;
 	} else if (mp_opt.mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
 	}
@@ -157,7 +162,7 @@ again:
 			} else {
 				subflow_req->mp_capable = 1;
 			}
-			return;
+			return 0;
 		}
 
 		err = mptcp_token_new_request(req);
@@ -175,7 +180,11 @@ again:
 		subflow_req->remote_nonce = mp_opt.nonce;
 		subflow_req->msk = subflow_token_join_request(req, skb);
 
-		if (unlikely(req->syncookie) && subflow_req->msk) {
+		/* Can't fall back to TCP in this case. */
+		if (!subflow_req->msk)
+			return -EPERM;
+
+		if (unlikely(req->syncookie)) {
 			if (mptcp_can_accept_new_subflow(subflow_req->msk))
 				subflow_init_req_cookie_join_save(subflow_req, skb);
 		}
@@ -183,6 +192,8 @@ again:
 		pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
 			 subflow_req->remote_nonce, subflow_req->msk);
 	}
+
+	return 0;
 }
 
 int mptcp_subflow_init_cookie_req(struct request_sock *req,
@@ -228,27 +239,53 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 }
 EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
 
-static void subflow_v4_init_req(struct request_sock *req,
-				const struct sock *sk_listener,
-				struct sk_buff *skb)
+static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
+					      struct sk_buff *skb,
+					      struct flowi *fl,
+					      struct request_sock *req)
 {
+	struct dst_entry *dst;
+	int err;
+
 	tcp_rsk(req)->is_mptcp = 1;
 
-	tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb);
+	dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
+	if (!dst)
+		return NULL;
+
+	err = subflow_init_req(req, sk, skb);
+	if (err == 0)
+		return dst;
 
-	subflow_init_req(req, sk_listener, skb);
+	dst_release(dst);
+	if (!req->syncookie)
+		tcp_request_sock_ops.send_reset(sk, skb);
+	return NULL;
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static void subflow_v6_init_req(struct request_sock *req,
-				const struct sock *sk_listener,
-				struct sk_buff *skb)
+static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
+					      struct sk_buff *skb,
+					      struct flowi *fl,
+					      struct request_sock *req)
 {
+	struct dst_entry *dst;
+	int err;
+
 	tcp_rsk(req)->is_mptcp = 1;
 
-	tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb);
+	dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
+	if (!dst)
+		return NULL;
 
-	subflow_init_req(req, sk_listener, skb);
+	err = subflow_init_req(req, sk, skb);
+	if (err == 0)
+		return dst;
+
+	dst_release(dst);
+	if (!req->syncookie)
+		tcp6_request_sock_ops.send_reset(sk, skb);
+	return NULL;
 }
 #endif
 
@@ -276,12 +313,17 @@ void mptcp_subflow_reset(struct sock *ssk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
+	/* 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))
-		sock_hold(sk);
+		return; /* worker will put sk for us */
+
+	sock_put(sk);
 }
 
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
@@ -577,6 +619,11 @@ create_child:
 			 */
 			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);
+
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
@@ -845,8 +892,6 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
 		subflow->map_valid = 0;
-	if (incr)
-		tcp_cleanup_rbuf(ssk, incr);
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -968,7 +1013,7 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
 	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	const struct sock *sk = subflow->conn;
 
-	*space = tcp_space(sk);
+	*space = __mptcp_space(sk);
 	*full_space = tcp_full_space(sk);
 }
 
@@ -993,20 +1038,9 @@ static void subflow_data_ready(struct sock *sk)
 		mptcp_data_ready(parent, sk);
 }
 
-static void subflow_write_space(struct sock *sk)
+static void subflow_write_space(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sock *parent = subflow->conn;
-
-	if (!sk_stream_is_writeable(sk))
-		return;
-
-	if (sk_stream_is_writeable(parent)) {
-		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
-		smp_mb__after_atomic();
-		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
-		sk_stream_write_space(parent);
-	}
+	/* we take action in __mptcp_clean_una() */
 }
 
 static struct inet_connection_sock_af_ops *
@@ -1120,21 +1154,48 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr);
 
+	mptcp_add_pending_subflow(msk, subflow);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
 	if (err && err != -EINPROGRESS)
-		goto failed;
+		goto failed_unlink;
 
+	return err;
+
+failed_unlink:
 	spin_lock_bh(&msk->join_list_lock);
-	list_add_tail(&subflow->node, &msk->join_list);
+	list_del(&subflow->node);
 	spin_unlock_bh(&msk->join_list_lock);
 
-	return err;
-
 failed:
+	subflow->disposable = 1;
 	sock_release(sf);
 	return err;
 }
 
+static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
+{
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data,
+				*child_skcd = &child->sk_cgrp_data;
+
+	/* only the additional subflows created by kworkers have to be modified */
+	if (cgroup_id(sock_cgroup_ptr(parent_skcd)) !=
+	    cgroup_id(sock_cgroup_ptr(child_skcd))) {
+#ifdef CONFIG_MEMCG
+		struct mem_cgroup *memcg = parent->sk_memcg;
+
+		mem_cgroup_sk_free(child);
+		if (memcg && css_tryget(&memcg->css))
+			child->sk_memcg = memcg;
+#endif /* CONFIG_MEMCG */
+
+		cgroup_sk_free(child_skcd);
+		*child_skcd = *parent_skcd;
+		cgroup_sk_clone(child_skcd);
+	}
+#endif /* CONFIG_SOCK_CGROUP_DATA */
+}
+
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1155,6 +1216,9 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 
 	lock_sock(sf->sk);
 
+	/* the newly created socket has to be in the same cgroup as its parent */
+	mptcp_attach_cgroup(sk, sf->sk);
+
 	/* kernel sockets do not by default acquire net ref, but TCP timer
 	 * needs it.
 	 */
@@ -1253,7 +1317,6 @@ static void subflow_state_change(struct sock *sk)
 		mptcp_data_ready(parent, sk);
 
 	if (__mptcp_check_fallback(mptcp_sk(parent)) &&
-	    !(parent->sk_shutdown & RCV_SHUTDOWN) &&
 	    !subflow->rx_eof && subflow_is_done(sk)) {
 		subflow->rx_eof = 1;
 		mptcp_subflow_eof(parent);
@@ -1296,17 +1359,27 @@ out:
 	return err;
 }
 
-static void subflow_ulp_release(struct sock *sk)
+static void subflow_ulp_release(struct sock *ssk)
 {
-	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
+	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
+	bool release = true;
+	struct sock *sk;
 
 	if (!ctx)
 		return;
 
-	if (ctx->conn)
-		sock_put(ctx->conn);
+	sk = ctx->conn;
+	if (sk) {
+		/* if the msk has been orphaned, keep the ctx
+		 * alive, will be freed by __mptcp_close_ssk(),
+		 * when the subflow is still unaccepted
+		 */
+		release = ctx->disposable || list_empty(&ctx->node);
+		sock_put(sk);
+	}
 
-	kfree_rcu(ctx, rcu);
+	if (release)
+		kfree_rcu(ctx, rcu);
 }
 
 static void subflow_ulp_clone(const struct request_sock *req,
@@ -1391,7 +1464,7 @@ void __init mptcp_subflow_init(void)
 		panic("MPTCP: failed to init subflow request sock ops\n");
 
 	subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
-	subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req;
+	subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req;
 
 	subflow_specific = ipv4_specific;
 	subflow_specific.conn_request = subflow_v4_conn_request;
@@ -1400,7 +1473,7 @@ void __init mptcp_subflow_init(void)
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
-	subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req;
+	subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
 
 	subflow_v6_specific = ipv6_specific;
 	subflow_v6_specific.conn_request = subflow_v6_conn_request;