1 files changed, 34 insertions, 22 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 918c1a235790..e120e9616454 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -421,6 +421,7 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 
 void __mptcp_set_connected(struct sock *sk)
 {
+	__mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
 		inet_sk_state_store(sk, TCP_ESTABLISHED);
 		sk->sk_state_change(sk);
@@ -472,7 +473,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		return;
 
 	msk = mptcp_sk(parent);
-	mptcp_propagate_sndbuf(parent, sk);
 	subflow->rel_write_seq = 1;
 	subflow->conn_finished = 1;
 	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
@@ -1237,7 +1237,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	struct sk_buff *skb;
 
 	if (!skb_peek(&ssk->sk_receive_queue))
-		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
+		WRITE_ONCE(subflow->data_avail, false);
 	if (subflow->data_avail)
 		return true;
 
@@ -1271,7 +1271,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			continue;
 		}
 
-		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
+		WRITE_ONCE(subflow->data_avail, true);
 		break;
 	}
 	return true;
@@ -1293,7 +1293,7 @@ fallback:
 				goto reset;
 			}
 			mptcp_subflow_fail(msk, ssk);
-			WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
+			WRITE_ONCE(subflow->data_avail, true);
 			return true;
 		}
 
@@ -1310,7 +1310,7 @@ reset:
 			while ((skb = skb_peek(&ssk->sk_receive_queue)))
 				sk_eat_skb(ssk, skb);
 			tcp_send_active_reset(ssk, GFP_ATOMIC);
-			WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
+			WRITE_ONCE(subflow->data_avail, false);
 			return false;
 		}
 
@@ -1322,7 +1322,7 @@ reset:
 	subflow->map_seq = READ_ONCE(msk->ack_seq);
 	subflow->map_data_len = skb->len;
 	subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
-	WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
+	WRITE_ONCE(subflow->data_avail, true);
 	return true;
 }
 
@@ -1334,7 +1334,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
 	if (subflow->map_valid &&
 	    mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
 		subflow->map_valid = 0;
-		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
+		WRITE_ONCE(subflow->data_avail, false);
 
 		pr_debug("Done with mapping: seq=%u data_len=%u",
 			 subflow->map_subflow_seq,
@@ -1405,10 +1405,18 @@ static void subflow_data_ready(struct sock *sk)
 	WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
 		     !subflow->mp_join && !(state & TCPF_CLOSE));
 
-	if (mptcp_subflow_data_available(sk))
+	if (mptcp_subflow_data_available(sk)) {
 		mptcp_data_ready(parent, sk);
-	else if (unlikely(sk->sk_err))
+
+		/* subflow-level lowat test are not relevant.
+		 * respect the msk-level threshold eventually mandating an immediate ack
+		 */
+		if (mptcp_data_avail(msk) < parent->sk_rcvlowat &&
+		    (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss)
+			inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+	} else if (unlikely(sk->sk_err)) {
 		subflow_error_report(sk);
+	}
 }
 
 static void subflow_write_space(struct sock *ssk)
@@ -1525,8 +1533,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	if (addr.ss_family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	mptcp_sockopt_sync(msk, ssk);
-
 	ssk->sk_bound_dev_if = ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
@@ -1637,7 +1643,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 
 	err = security_mptcp_add_subflow(sk, sf->sk);
 	if (err)
-		goto release_ssk;
+		goto err_free;
 
 	/* the newly created socket has to be in the same cgroup as its parent */
 	mptcp_attach_cgroup(sk, sf->sk);
@@ -1651,15 +1657,12 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
 	sock_inuse_add(net, 1);
 	err = tcp_set_ulp(sf->sk, "mptcp");
+	if (err)
+		goto err_free;
 
-release_ssk:
+	mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk);
 	release_sock(sf->sk);
 
-	if (err) {
-		sock_release(sf);
-		return err;
-	}
-
 	/* the newly created socket really belongs to the owning MPTCP master
 	 * socket, even if for additional subflows the allocation is performed
 	 * by a kernel workqueue. Adjust inode references, so that the
@@ -1679,6 +1682,11 @@ release_ssk:
 	mptcp_subflow_ops_override(sf->sk);
 
 	return 0;
+
+err_free:
+	release_sock(sf->sk);
+	sock_release(sf);
+	return err;
 }
 
 static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
@@ -1728,7 +1736,6 @@ static void subflow_state_change(struct sock *sk)
 
 	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
-		mptcp_propagate_sndbuf(parent, sk);
 		mptcp_do_fallback(sk);
 		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
@@ -1956,9 +1963,15 @@ static void subflow_ulp_clone(const struct request_sock *req,
 static void tcp_release_cb_override(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	long status;
 
-	if (mptcp_subflow_has_delegated_action(subflow))
-		mptcp_subflow_process_delegated(ssk);
+	/* process and clear all the pending actions, but leave the subflow into
+	 * the napi queue. To respect locking, only the same CPU that originated
+	 * the action can touch the list. mptcp_napi_poll will take care of it.
+	 */
+	status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0);
+	if (status)
+		mptcp_subflow_process_delegated(ssk, status);
 
 	tcp_release_cb(ssk);
 }
@@ -2038,7 +2051,6 @@ void __init mptcp_subflow_init(void)
 	subflow_v6m_specific.send_check = ipv4_specific.send_check;
 	subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
 	subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
-	subflow_v6m_specific.net_frag_header_len = 0;
 	subflow_v6m_specific.rebuild_header = subflow_rebuild_header;
 
 	tcpv6_prot_override = tcpv6_prot;