Merge branch 'mptcp-various-small-improvements'

Matthieu Baerts says:

====================
mptcp: various small improvements

The following patches are not related to each other.

- Patch 1: Avoid sending advertisements on stale subflows, reducing
  risks on loosing them.

- Patch 2: Annotate data-races around subflow->fully_established, using
  READ/WRITE_ONCE().

- Patch 3: A small clean-up on the PM side, avoiding a bit of duplicated
  code.

- Patch 4: Use "Middlebox interference" MP_TCPRST code in reaction to a
  packet received without MPTCP options in the middle of a connection.
====================

Link: https://patch.msgid.link/20241021-net-next-mptcp-misc-6-13-v1-0-1ef02746504a@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/mptcp/diag.c

@@ -47,7 +47,7 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 		flags |= MPTCP_SUBFLOW_FLAG_BKUP_REM;
 	if (sf->request_bkup)
 		flags |= MPTCP_SUBFLOW_FLAG_BKUP_LOC;
-	if (sf->fully_established)
+	if (READ_ONCE(sf->fully_established))
 		flags |= MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED;
 	if (sf->conn_finished)
 		flags |= MPTCP_SUBFLOW_FLAG_CONNECTED;

net/mptcp/options.c

@@ -461,7 +461,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 		return false;
 
 	/* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */
-	if (subflow->fully_established || snd_data_fin_enable ||
+	if (READ_ONCE(subflow->fully_established) || snd_data_fin_enable ||
 	    subflow->snd_isn != TCP_SKB_CB(skb)->seq ||
 	    sk->sk_state != TCP_ESTABLISHED)
 		return false;
@@ -930,7 +930,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	/* here we can process OoO, in-window pkts, only in-sequence 4th ack
 	 * will make the subflow fully established
 	 */
-	if (likely(subflow->fully_established)) {
+	if (likely(READ_ONCE(subflow->fully_established))) {
 		/* on passive sockets, check for 3rd ack retransmission
 		 * note that msk is always set by subflow_syn_recv_sock()
 		 * for mp_join subflows

net/mptcp/pm.c

@@ -154,6 +154,9 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
 void mptcp_pm_connection_closed(struct mptcp_sock *msk)
 {
 	pr_debug("msk=%p\n", msk);
+
+	if (msk->token)
+		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 }
 
 void mptcp_pm_subflow_established(struct mptcp_sock *msk)

net/mptcp/pm_netlink.c

@@ -781,7 +781,7 @@ bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
 
 void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 {
-	struct mptcp_subflow_context *subflow;
+	struct mptcp_subflow_context *subflow, *alt = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -792,10 +792,18 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 
 	mptcp_for_each_subflow(msk, subflow) {
 		if (__mptcp_subflow_active(subflow)) {
-			mptcp_pm_send_ack(msk, subflow, false, false);
-			break;
+			if (!subflow->stale) {
+				mptcp_pm_send_ack(msk, subflow, false, false);
+				return;
+			}
+
+			if (!alt)
+				alt = subflow;
 		}
 	}
+
+	if (alt)
+		mptcp_pm_send_ack(msk, alt, false, false);
 }
 
 int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,

net/mptcp/protocol.c

@@ -3139,8 +3139,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
 
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d\n", sk, sk->sk_state);
-	if (msk->token)
-		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
+	mptcp_pm_connection_closed(msk);
 
 	if (sk->sk_state == TCP_CLOSE) {
 		__mptcp_destroy_sock(sk);
@@ -3206,8 +3205,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_stop_rtx_timer(sk);
 	mptcp_stop_tout_timer(sk);
 
-	if (msk->token)
-		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
+	mptcp_pm_connection_closed(msk);
 
 	/* msk->subflow is still intact, the following will not free the first
 	 * subflow
@@ -3511,7 +3509,7 @@ static void schedule_3rdack_retransmission(struct sock *ssk)
 	struct tcp_sock *tp = tcp_sk(ssk);
 	unsigned long timeout;
 
-	if (mptcp_subflow_ctx(ssk)->fully_established)
+	if (READ_ONCE(mptcp_subflow_ctx(ssk)->fully_established))
 		return;
 
 	/* reschedule with a timeout above RTT, as we must look only for drop */

net/mptcp/protocol.h

@@ -513,7 +513,6 @@ struct mptcp_subflow_context {
 		request_bkup : 1,
 		mp_capable : 1,	    /* remote is MPTCP capable */
 		mp_join : 1,	    /* remote is JOINing */
-		fully_established : 1,	    /* path validated */
 		pm_notified : 1,    /* PM hook called for established status */
 		conn_finished : 1,
 		map_valid : 1,
@@ -532,10 +531,11 @@ struct mptcp_subflow_context {
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
 		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
-		__unused : 8;
+		__unused : 9;
 	bool	data_avail;
 	bool	scheduled;
 	bool	pm_listener;	    /* a listener managed by the kernel PM? */
+	bool	fully_established;  /* path validated */
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
@@ -780,7 +780,7 @@ static inline bool __tcp_can_send(const struct sock *ssk)
 static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 {
 	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
-	if (subflow->request_join && !subflow->fully_established)
+	if (subflow->request_join && !READ_ONCE(subflow->fully_established))
 		return false;
 
 	return __tcp_can_send(mptcp_subflow_tcp_sock(subflow));

net/mptcp/subflow.c

@@ -800,7 +800,7 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 				       const struct mptcp_options_received *mp_opt)
 {
 	subflow_set_remote_key(msk, subflow, mp_opt);
-	subflow->fully_established = 1;
+	WRITE_ONCE(subflow->fully_established, true);
 	WRITE_ONCE(msk->fully_established, true);
 
 	if (subflow->is_mptfo)
@@ -971,7 +971,8 @@ enum mapping_status {
 	MAPPING_EMPTY,
 	MAPPING_DATA_FIN,
 	MAPPING_DUMMY,
-	MAPPING_BAD_CSUM
+	MAPPING_BAD_CSUM,
+	MAPPING_NODSS
 };
 
 static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
@@ -1128,8 +1129,9 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 			return MAPPING_EMPTY;
 		}
 
+		/* If the required DSS has likely been dropped by a middlebox */
 		if (!subflow->map_valid)
-			return MAPPING_INVALID;
+			return MAPPING_NODSS;
 
 		goto validate_seq;
 	}
@@ -1343,7 +1345,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		status = get_mapping_status(ssk, msk);
 		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
 		if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY ||
-			     status == MAPPING_BAD_CSUM))
+			     status == MAPPING_BAD_CSUM || status == MAPPING_NODSS))
 			goto fallback;
 
 		if (status != MAPPING_OK)
@@ -1396,7 +1398,9 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */
 			subflow->reset_transient = 0;
-			subflow->reset_reason = MPTCP_RST_EMPTCP;
+			subflow->reset_reason = status == MAPPING_NODSS ?
+						MPTCP_RST_EMIDDLEBOX :
+						MPTCP_RST_EMPTCP;
 
 reset:
 			WRITE_ONCE(ssk->sk_err, EBADMSG);
@@ -2062,7 +2066,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
-		new_ctx->fully_established = 1;
+		WRITE_ONCE(new_ctx->fully_established, true);
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
 		new_ctx->request_bkup = subflow_req->request_bkup;