Merge branch 'MPTCP-improve-fallback-to-TCP'

Davide Caratti says:

====================
MPTCP: improve fallback to TCP

there are situations where MPTCP sockets should fall-back to regular TCP:
this series reworks the fallback code to pursue the following goals:

1) cleanup the non fallback code, removing most of 'if (<fallback>)' in
   the data path
2) improve performance for non-fallback sockets, avoiding locks in poll()

further work will also leverage on this changes to achieve:

a) more consistent behavior of gestockopt()/setsockopt() on passive sockets
   after fallback
b) support for "infinite maps" as per RFC8684, section 3.7

the series is made of the following items:

- patch 1 lets sendmsg() / recvmsg() / poll() use the main socket also
  after fallback
- patch 2 fixes 'simultaneous connect' scenario after fallback. The
  problem was present also before the rework, but the fix is much easier
  to implement after patch 1
- patch 3, 4, 5 are clean-ups for code that is no more needed after the
  fallback rework
- patch 6 fixes a race condition between close() and poll(). The problem
  was theoretically present before the rework, but it became almost
  systematic after patch 1
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mptcp/options.c

@@ -624,6 +624,9 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	opts->suboptions = 0;
 
+	if (unlikely(mptcp_check_fallback(sk)))
+		return false;
+
 	if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts))
 		ret = true;
 	else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
@@ -714,7 +717,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 	 */
 	if (!mp_opt->mp_capable) {
 		subflow->mp_capable = 0;
-		tcp_sk(sk)->is_mptcp = 0;
+		pr_fallback(msk);
+		__mptcp_do_fallback(msk);
 		return false;
 	}
 
@@ -814,6 +818,9 @@ 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))
+		return;
+
 	mptcp_get_options(skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;

net/mptcp/protocol.h

@@ -89,6 +89,7 @@
 #define MPTCP_SEND_SPACE	1
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
+#define MPTCP_FALLBACK_DONE	4
 
 struct mptcp_options_received {
 	u64	sndr_key;
@@ -457,4 +458,46 @@ static inline bool before64(__u64 seq1, __u64 seq2)
 
 void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
 
+static inline bool __mptcp_check_fallback(struct mptcp_sock *msk)
+{
+	return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+}
+
+static inline bool mptcp_check_fallback(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	return __mptcp_check_fallback(msk);
+}
+
+static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
+{
+	if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) {
+		pr_debug("TCP fallback already done (msk=%p)", msk);
+		return;
+	}
+	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+}
+
+static inline void mptcp_do_fallback(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	__mptcp_do_fallback(msk);
+}
+
+#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
+
+static inline bool subflow_simultaneous_connect(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct sock *parent = subflow->conn;
+
+	return sk->sk_state == TCP_ESTABLISHED &&
+	       !mptcp_sk(parent)->pm.server_side &&
+	       !subflow->conn_finished;
+}
+
 #endif /* __MPTCP_PROTOCOL_H */

net/mptcp/subflow.c

@@ -216,7 +216,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_options_received mp_opt;
 	struct sock *parent = subflow->conn;
-	struct tcp_sock *tp = tcp_sk(sk);
 
 	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
 
@@ -230,6 +229,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		return;
 
 	subflow->conn_finished = 1;
+	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
+	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
 
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp && mp_opt.mp_capable) {
@@ -245,21 +246,20 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
 			 subflow->thmac, subflow->remote_nonce);
 	} else {
-		tp->is_mptcp = 0;
+		if (subflow->request_mptcp)
+			MPTCP_INC_STATS(sock_net(sk),
+					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
+		mptcp_do_fallback(sk);
+		pr_fallback(mptcp_sk(subflow->conn));
 	}
 
-	if (!tp->is_mptcp)
+	if (mptcp_check_fallback(sk))
 		return;
 
 	if (subflow->mp_capable) {
 		pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
 			 subflow->remote_key);
 		mptcp_finish_connect(sk);
-
-		if (skb) {
-			pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
-			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
-		}
 	} else if (subflow->mp_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
@@ -279,9 +279,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 		memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
 
-		if (skb)
-			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
-
 		if (!mptcp_finish_join(sk))
 			goto do_reset;
 
@@ -557,7 +554,8 @@ enum mapping_status {
 	MAPPING_OK,
 	MAPPING_INVALID,
 	MAPPING_EMPTY,
-	MAPPING_DATA_FIN
+	MAPPING_DATA_FIN,
+	MAPPING_DUMMY
 };
 
 static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq)
@@ -621,6 +619,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk)
 	if (!skb)
 		return MAPPING_EMPTY;
 
+	if (mptcp_check_fallback(ssk))
+		return MAPPING_DUMMY;
+
 	mpext = mptcp_get_ext(skb);
 	if (!mpext || !mpext->use_map) {
 		if (!subflow->map_valid && !skb->len) {
@@ -762,6 +763,16 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			ssk->sk_err = EBADMSG;
 			goto fatal;
 		}
+		if (status == MAPPING_DUMMY) {
+			__mptcp_do_fallback(msk);
+			skb = skb_peek(&ssk->sk_receive_queue);
+			subflow->map_valid = 1;
+			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;
+			return true;
+		}
 
 		if (status != MAPPING_OK)
 			return false;
@@ -885,14 +896,18 @@ static void subflow_data_ready(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
+	struct mptcp_sock *msk;
 
-	if (!subflow->mp_capable && !subflow->mp_join) {
-		subflow->tcp_data_ready(sk);
-
+	msk = mptcp_sk(parent);
+	if (inet_sk_state_load(sk) == TCP_LISTEN) {
+		set_bit(MPTCP_DATA_READY, &msk->flags);
 		parent->sk_data_ready(parent);
 		return;
 	}
 
+	WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
+		     !subflow->mp_join);
+
 	if (mptcp_subflow_data_available(sk))
 		mptcp_data_ready(parent, sk);
 }
@@ -1113,11 +1128,21 @@ static void subflow_state_change(struct sock *sk)
 
 	__subflow_state_change(sk);
 
+	if (subflow_simultaneous_connect(sk)) {
+		mptcp_do_fallback(sk);
+		pr_fallback(mptcp_sk(parent));
+		subflow->conn_finished = 1;
+		if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
+			inet_sk_state_store(parent, TCP_ESTABLISHED);
+			parent->sk_state_change(parent);
+		}
+	}
+
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
 	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
 	 * the data available machinery here.
 	 */
-	if (subflow->mp_capable && mptcp_subflow_data_available(sk))
+	if (mptcp_subflow_data_available(sk))
 		mptcp_data_ready(parent, sk);
 
 	if (!(parent->sk_shutdown & RCV_SHUTDOWN) &&