1 files changed, 79 insertions, 33 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bea47a1180dc..aba260f547da 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -153,7 +153,7 @@ static int subflow_check_req(struct request_sock *req,
 		return -EINVAL;
 #endif
 
-	mptcp_get_options(sk_listener, skb, &mp_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
 	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
@@ -250,7 +250,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	int err;
 
 	subflow_init_req(req, sk_listener);
-	mptcp_get_options(sk_listener, skb, &mp_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
 	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
@@ -344,9 +344,7 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 
 	thmac = get_unaligned_be64(hmac);
 	pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n",
-		 subflow, subflow->token,
-		 (unsigned long long)thmac,
-		 (unsigned long long)subflow->thmac);
+		 subflow, subflow->token, thmac, subflow->thmac);
 
 	return thmac == subflow->thmac;
 }
@@ -410,7 +408,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
 	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
 
-	mptcp_get_options(sk, skb, &mp_opt);
+	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
 		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
 			MPTCP_INC_STATS(sock_net(sk),
@@ -483,9 +481,53 @@ do_reset:
 	mptcp_subflow_reset(sk);
 }
 
+static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
+{
+	subflow->local_id = local_id;
+	subflow->local_id_valid = 1;
+}
+
+static int subflow_chk_local_id(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	int err;
+
+	if (likely(subflow->local_id_valid))
+		return 0;
+
+	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
+	if (err < 0)
+		return err;
+
+	subflow_set_local_id(subflow, err);
+	return 0;
+}
+
+static int subflow_rebuild_header(struct sock *sk)
+{
+	int err = subflow_chk_local_id(sk);
+
+	if (unlikely(err < 0))
+		return err;
+
+	return inet_sk_rebuild_header(sk);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int subflow_v6_rebuild_header(struct sock *sk)
+{
+	int err = subflow_chk_local_id(sk);
+
+	if (unlikely(err < 0))
+		return err;
+
+	return inet6_sk_rebuild_header(sk);
+}
+#endif
+
 struct request_sock_ops mptcp_subflow_request_sock_ops;
-EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops);
-static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops;
+static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;
 
 static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
@@ -506,9 +548,9 @@ drop:
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
-static struct inet_connection_sock_af_ops subflow_v6_specific;
-static struct inet_connection_sock_af_ops subflow_v6m_specific;
+static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init;
+static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init;
+static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init;
 static struct proto tcpv6_prot_override;
 
 static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
@@ -663,7 +705,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * reordered MPC will cause fallback, but we don't have other
 		 * options.
 		 */
-		mptcp_get_options(sk, skb, &mp_opt);
+		mptcp_get_options(skb, &mp_opt);
 		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
 			fallback = true;
 			goto create_child;
@@ -673,7 +715,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		if (!new_msk)
 			fallback = true;
 	} else if (subflow_req->mp_join) {
-		mptcp_get_options(sk, skb, &mp_opt);
+		mptcp_get_options(skb, &mp_opt);
 		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
 		    !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
@@ -790,7 +832,7 @@ dispose_child:
 	return child;
 }
 
-static struct inet_connection_sock_af_ops subflow_specific;
+static struct inet_connection_sock_af_ops subflow_specific __ro_after_init;
 static struct proto tcp_prot_override;
 
 enum mapping_status {
@@ -1107,7 +1149,7 @@ 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, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 	if (subflow->data_avail)
 		return true;
 
@@ -1172,7 +1214,7 @@ fallback:
 		subflow->reset_transient = 0;
 		subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
 		tcp_send_active_reset(ssk, GFP_ATOMIC);
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 		return true;
 	}
 
@@ -1185,7 +1227,7 @@ fallback:
 		subflow->reset_transient = 0;
 		subflow->reset_reason = MPTCP_RST_EMPTCP;
 		tcp_send_active_reset(ssk, GFP_ATOMIC);
-		WRITE_ONCE(subflow->data_avail, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 		return false;
 	}
 
@@ -1207,7 +1249,7 @@ 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, 0);
+		WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
 
 		pr_debug("Done with mapping: seq=%u data_len=%u",
 			 subflow->map_subflow_seq,
@@ -1311,7 +1353,7 @@ static void subflow_write_space(struct sock *ssk)
 	mptcp_write_space(sk);
 }
 
-static struct inet_connection_sock_af_ops *
+static const struct inet_connection_sock_af_ops *
 subflow_default_af_ops(struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -1326,7 +1368,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct inet_connection_sock_af_ops *target;
+	const struct inet_connection_sock_af_ops *target;
 
 	target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
 
@@ -1401,13 +1443,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 		get_random_bytes(&subflow->local_nonce, sizeof(u32));
 	} while (!subflow->local_nonce);
 
-	if (!local_id) {
-		err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk);
-		if (err < 0)
-			goto failed;
-
-		local_id = err;
-	}
+	if (local_id)
+		subflow_set_local_id(subflow, local_id);
 
 	mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id,
 					     &flags, &ifindex);
@@ -1432,7 +1469,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
-	subflow->local_id = local_id;
 	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
@@ -1657,10 +1693,12 @@ static int subflow_ulp_init(struct sock *sk)
 	tp->is_mptcp = 1;
 	ctx->icsk_af_ops = icsk->icsk_af_ops;
 	icsk->icsk_af_ops = subflow_default_af_ops(sk);
-	ctx->tcp_data_ready = sk->sk_data_ready;
 	ctx->tcp_state_change = sk->sk_state_change;
-	ctx->tcp_write_space = sk->sk_write_space;
 	ctx->tcp_error_report = sk->sk_error_report;
+
+	WARN_ON_ONCE(sk->sk_data_ready != sock_def_readable);
+	WARN_ON_ONCE(sk->sk_write_space != sk_stream_write_space);
+
 	sk->sk_data_ready = subflow_data_ready;
 	sk->sk_write_space = subflow_write_space;
 	sk->sk_state_change = subflow_state_change;
@@ -1715,9 +1753,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
 
 	new_ctx->conn_finished = 1;
 	new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
-	new_ctx->tcp_data_ready = old_ctx->tcp_data_ready;
 	new_ctx->tcp_state_change = old_ctx->tcp_state_change;
-	new_ctx->tcp_write_space = old_ctx->tcp_write_space;
 	new_ctx->tcp_error_report = old_ctx->tcp_error_report;
 	new_ctx->rel_write_seq = 1;
 	new_ctx->tcp_sock = newsk;
@@ -1731,15 +1767,22 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->token = subflow_req->token;
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->idsn = subflow_req->idsn;
+
+		/* this is the first subflow, id is always 0 */
+		new_ctx->local_id_valid = 1;
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
 		new_ctx->fully_established = 1;
 		new_ctx->backup = subflow_req->backup;
-		new_ctx->local_id = subflow_req->local_id;
 		new_ctx->remote_id = subflow_req->remote_id;
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
+
+		/* the subflow req id is valid, fetched via subflow_check_req()
+		 * and subflow_token_join_request()
+		 */
+		subflow_set_local_id(new_ctx, subflow_req->local_id);
 	}
 }
 
@@ -1792,6 +1835,7 @@ void __init mptcp_subflow_init(void)
 	subflow_specific.conn_request = subflow_v4_conn_request;
 	subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
 	subflow_specific.sk_rx_dst_set = subflow_finish_connect;
+	subflow_specific.rebuild_header = subflow_rebuild_header;
 
 	tcp_prot_override = tcp_prot;
 	tcp_prot_override.release_cb = tcp_release_cb_override;
@@ -1804,6 +1848,7 @@ void __init mptcp_subflow_init(void)
 	subflow_v6_specific.conn_request = subflow_v6_conn_request;
 	subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
 	subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
+	subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header;
 
 	subflow_v6m_specific = subflow_v6_specific;
 	subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
@@ -1811,6 +1856,7 @@ void __init mptcp_subflow_init(void)
 	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;
 	tcpv6_prot_override.release_cb = tcp_release_cb_override;