mptcp: implement delayed seq generation for passive fastopen

With fastopen in place, the first subflow socket is created before the
MPC handshake completes, and we need to properly initialize the sequence
numbers at MPC ACK reception.

Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Dmytro Shytyi <dmytro@shytyi.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/mptcp/Makefile

@@ -2,7 +2,7 @@
 obj-$(CONFIG_MPTCP) += mptcp.o
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
-	   mib.o pm_netlink.o sockopt.o pm_userspace.o
+	   mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o

net/mptcp/fastopen.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* MPTCP Fast Open Mechanism
+ *
+ * Copyright (c) 2021-2022, Dmytro SHYTYI
+ */
+
+#include "protocol.h"
+
+void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				   const struct mptcp_options_received *mp_opt)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct sk_buff *skb;
+
+	mptcp_data_lock(sk);
+	skb = skb_peek_tail(&sk->sk_receive_queue);
+	if (skb) {
+		WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
+		pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk,
+			 MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
+			 MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
+		MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
+		MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
+	}
+
+	pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
+	mptcp_data_unlock(sk);
+}

net/mptcp/options.c

@@ -939,7 +939,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		    subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) &&
 		    !subflow->request_join)
 			tcp_send_ack(ssk);
-		goto fully_established;
+		goto check_notify;
 	}
 
 	/* we must process OoO packets before the first subflow is fully
@@ -950,6 +950,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) {
 		if (subflow->mp_join)
 			goto reset;
+		if (subflow->is_mptfo && mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+			goto set_fully_established;
 		return subflow->mp_capable;
 	}
 
@@ -961,7 +963,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		 */
 		subflow->fully_established = 1;
 		WRITE_ONCE(msk->fully_established, true);
-		goto fully_established;
+		goto check_notify;
 	}
 
 	/* If the first established packet does not contain MP_CAPABLE + data
@@ -980,11 +982,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	if (mp_opt->deny_join_id0)
 		WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 
+set_fully_established:
 	if (unlikely(!READ_ONCE(msk->pm.server_side)))
 		pr_warn_once("bogus mpc option on established client sk");
 	mptcp_subflow_fully_established(subflow, mp_opt);
 
-fully_established:
+check_notify:
 	/* 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

net/mptcp/protocol.c

@@ -36,15 +36,6 @@ struct mptcp6_sock {
 };
 #endif
 
-struct mptcp_skb_cb {
-	u64 map_seq;
-	u64 end_seq;
-	u32 offset;
-	u8  has_rxtstamp:1;
-};
-
-#define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))
-
 enum {
 	MPTCP_CMSG_TS = BIT(0),
 	MPTCP_CMSG_INQ = BIT(1),

net/mptcp/protocol.h

@@ -126,6 +126,15 @@
 #define MPTCP_CONNECTED		6
 #define MPTCP_RESET_SCHEDULER	7
 
+struct mptcp_skb_cb {
+	u64 map_seq;
+	u64 end_seq;
+	u32 offset;
+	u8  has_rxtstamp:1;
+};
+
+#define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))
+
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
 	return (__s64)(seq1 - seq2) < 0;
@@ -471,7 +480,9 @@ struct mptcp_subflow_context {
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
 		local_id_valid : 1, /* local_id is correctly initialized */
-		valid_csum_seen : 1;        /* at least one csum validated */
+		valid_csum_seen : 1,        /* at least one csum validated */
+		is_mptfo : 1,	    /* subflow is doing TFO */
+		__unused : 8;
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -829,6 +840,9 @@ void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_
 void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);
 bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
+void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				   const struct mptcp_options_received *mp_opt);
+
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
 	return READ_ONCE(msk->pm.addr_signal) &

net/mptcp/subflow.c

@@ -664,6 +664,9 @@ void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	subflow->fully_established = 1;
 	WRITE_ONCE(msk->fully_established, true);
+
+	if (subflow->is_mptfo)
+		mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -779,7 +782,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
 			 */
-			if (mp_opt.suboptions & OPTIONS_MPTCP_MPC)
+			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK)
 				mptcp_subflow_fully_established(ctx, &mp_opt);
 		} else if (ctx->mp_join) {
 			struct mptcp_sock *owner;