5 files changed, 187 insertions, 168 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c254accb14de..cd15ec73073e 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1269,12 +1269,13 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
 
 			if (rcv_wnd == rcv_wnd_old)
 				break;
-			if (before64(rcv_wnd_new, rcv_wnd)) {
+
+			rcv_wnd_old = rcv_wnd;
+			if (before64(rcv_wnd_new, rcv_wnd_old)) {
 				MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE);
 				goto raise_win;
 			}
 			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT);
-			rcv_wnd_old = rcv_wnd;
 		}
 		return;
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b5a8aa4c1ebd..d042d32beb4d 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -307,12 +307,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
 		goto create_err;
 	}
 
-	if (addr_l.id == 0) {
-		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local addr id");
-		err = -EINVAL;
-		goto create_err;
-	}
-
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a7fc16f5175d..886ab689a8ae 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -405,7 +405,7 @@ drop:
 	return false;
 }
 
-static void mptcp_stop_timer(struct sock *sk)
+static void mptcp_stop_rtx_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -770,6 +770,46 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 	return moved;
 }
 
+static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
+{
+	int err = sock_error(ssk);
+	int ssk_state;
+
+	if (!err)
+		return false;
+
+	/* only propagate errors on fallen-back sockets or
+	 * on MPC connect
+	 */
+	if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk)))
+		return false;
+
+	/* We need to propagate only transition to CLOSE state.
+	 * Orphaned socket will see such state change via
+	 * subflow_sched_work_if_closed() and that path will properly
+	 * destroy the msk as needed.
+	 */
+	ssk_state = inet_sk_state_load(ssk);
+	if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
+		inet_sk_state_store(sk, ssk_state);
+	WRITE_ONCE(sk->sk_err, -err);
+
+	/* This barrier is coupled with smp_rmb() in mptcp_poll() */
+	smp_wmb();
+	sk_error_report(sk);
+	return true;
+}
+
+void __mptcp_error_report(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	mptcp_for_each_subflow(msk, subflow)
+		if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow)))
+			break;
+}
+
 /* In most cases we will be able to lock the mptcp socket.  If its already
  * owned, we need to defer to the work queue to avoid ABBA deadlock.
  */
@@ -852,6 +892,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
 	mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++;
 	mptcp_sockopt_sync_locked(msk, ssk);
 	mptcp_subflow_joined(msk, ssk);
+	mptcp_stop_tout_timer(sk);
 	return true;
 }
 
@@ -871,12 +912,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list
 	}
 }
 
-static bool mptcp_timer_pending(struct sock *sk)
+static bool mptcp_rtx_timer_pending(struct sock *sk)
 {
 	return timer_pending(&inet_csk(sk)->icsk_retransmit_timer);
 }
 
-static void mptcp_reset_timer(struct sock *sk)
+static void mptcp_reset_rtx_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned long tout;
@@ -1010,10 +1051,10 @@ static void __mptcp_clean_una(struct sock *sk)
 out:
 	if (snd_una == READ_ONCE(msk->snd_nxt) &&
 	    snd_una == READ_ONCE(msk->write_seq)) {
-		if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
-			mptcp_stop_timer(sk);
+		if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk))
+			mptcp_stop_rtx_timer(sk);
 	} else {
-		mptcp_reset_timer(sk);
+		mptcp_reset_rtx_timer(sk);
 	}
 }
 
@@ -1257,7 +1298,7 @@ alloc_skb:
 	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
-		if (snd_una != msk->snd_nxt) {
+		if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) {
 			tcp_remove_empty_skb(ssk);
 			return 0;
 		}
@@ -1265,11 +1306,6 @@ alloc_skb:
 		zero_window_probe = true;
 		data_seq = snd_una - 1;
 		copy = 1;
-
-		/* all mptcp-level data is acked, no skbs should be present into the
-		 * ssk write queue
-		 */
-		WARN_ON_ONCE(reuse_skb);
 	}
 
 	copy = min_t(size_t, copy, info->limit - info->sent);
@@ -1298,7 +1334,6 @@ alloc_skb:
 	if (reuse_skb) {
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 		mpext->data_len += copy;
-		WARN_ON_ONCE(zero_window_probe);
 		goto out;
 	}
 
@@ -1586,8 +1621,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 		mptcp_push_release(ssk, &info);
 
 	/* ensure the rtx timer is running */
-	if (!mptcp_timer_pending(sk))
-		mptcp_reset_timer(sk);
+	if (!mptcp_rtx_timer_pending(sk))
+		mptcp_reset_rtx_timer(sk);
 	if (do_check_data_fin)
 		mptcp_check_send_data_fin(sk);
 }
@@ -1650,8 +1685,8 @@ out:
 	if (copied) {
 		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
 			 info.size_goal);
-		if (!mptcp_timer_pending(sk))
-			mptcp_reset_timer(sk);
+		if (!mptcp_rtx_timer_pending(sk))
+			mptcp_reset_rtx_timer(sk);
 
 		if (msk->snd_data_fin_enable &&
 		    msk->snd_nxt + 1 == msk->write_seq)
@@ -2220,7 +2255,7 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 	sock_put(sk);
 }
 
-static void mptcp_timeout_timer(struct timer_list *t)
+static void mptcp_tout_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
 
@@ -2313,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 #define MPTCP_CF_PUSH		BIT(1)
 #define MPTCP_CF_FASTCLOSE	BIT(2)
 
+/* be sure to send a reset only if the caller asked for it, also
+ * clean completely the subflow status when the subflow reaches
+ * TCP_CLOSE state
+ */
+static void __mptcp_subflow_disconnect(struct sock *ssk,
+				       struct mptcp_subflow_context *subflow,
+				       unsigned int flags)
+{
+	if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    (flags & MPTCP_CF_FASTCLOSE)) {
+		/* The MPTCP code never wait on the subflow sockets, TCP-level
+		 * disconnect should never fail
+		 */
+		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+		mptcp_subflow_ctx_reset(subflow);
+	} else {
+		tcp_shutdown(ssk, SEND_SHUTDOWN);
+	}
+}
+
 /* subflow sockets can be either outgoing (connect) or incoming
  * (accept).
  *
@@ -2329,18 +2384,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	bool dispose_it, need_push = false;
 
 	/* If the first subflow moved to a close state before accept, e.g. due
-	 * to an incoming reset, mptcp either:
-	 * - if either the subflow or the msk are dead, destroy the context
-	 *   (the subflow socket is deleted by inet_child_forget) and the msk
-	 * - otherwise do nothing at the moment and take action at accept and/or
-	 *   listener shutdown - user-space must be able to accept() the closed
-	 *   socket.
+	 * to an incoming reset or listener shutdown, the subflow socket is
+	 * already deleted by inet_child_forget() and the mptcp socket can't
+	 * survive too.
 	 */
-	if (msk->in_accept_queue && msk->first == ssk) {
-		if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD))
-			return;
-
+	if (msk->in_accept_queue && msk->first == ssk &&
+	    (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) {
 		/* ensure later check in mptcp_worker() will dispose the msk */
+		mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1));
 		sock_set_flag(sk, SOCK_DEAD);
 		lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 		mptcp_subflow_drop_ctx(ssk);
@@ -2354,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 
 	if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
-		/* be sure to force the tcp_disconnect() path,
+		/* be sure to force the tcp_close path
 		 * to generate the egress reset
 		 */
 		ssk->sk_lingertime = 0;
@@ -2364,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
-		/* The MPTCP code never wait on the subflow sockets, TCP-level
-		 * disconnect should never fail
-		 */
-		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
-		mptcp_subflow_ctx_reset(subflow);
+		__mptcp_subflow_disconnect(ssk, subflow, flags);
 		release_sock(ssk);
 
 		goto out;
@@ -2392,6 +2439,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 	}
 
 out_release:
+	__mptcp_subflow_error_report(sk, ssk);
 	release_sock(ssk);
 
 	sock_put(ssk);
@@ -2402,6 +2450,22 @@ out_release:
 out:
 	if (need_push)
 		__mptcp_push_pending(sk, 0);
+
+	/* Catch every 'all subflows closed' scenario, including peers silently
+	 * closing them, e.g. due to timeout.
+	 * For established sockets, allow an additional timeout before closing,
+	 * as the protocol can still create more subflows.
+	 */
+	if (list_is_singular(&msk->conn_list) && msk->first &&
+	    inet_sk_state_load(msk->first) == TCP_CLOSE) {
+		if (sk->sk_state != TCP_ESTABLISHED ||
+		    msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) {
+			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_close_wake_up(sk);
+		} else {
+			mptcp_start_tout_timer(sk);
+		}
+	}
 }
 
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
@@ -2445,23 +2509,14 @@ static void __mptcp_close_subflow(struct sock *sk)
 
 }
 
-static bool mptcp_should_close(const struct sock *sk)
+static bool mptcp_close_tout_expired(const struct sock *sk)
 {
-	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
-	struct mptcp_subflow_context *subflow;
-
-	if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue)
-		return true;
+	if (!inet_csk(sk)->icsk_mtup.probe_timestamp ||
+	    sk->sk_state == TCP_CLOSE)
+		return false;
 
-	/* if all subflows are in closed status don't bother with additional
-	 * timeout
-	 */
-	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
-		if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
-		    TCP_CLOSE)
-			return false;
-	}
-	return true;
+	return time_after32(tcp_jiffies32,
+		  inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN);
 }
 
 static void mptcp_check_fastclose(struct mptcp_sock *msk)
@@ -2588,27 +2643,28 @@ static void __mptcp_retrans(struct sock *sk)
 reset_timer:
 	mptcp_check_and_set_pending(sk);
 
-	if (!mptcp_timer_pending(sk))
-		mptcp_reset_timer(sk);
+	if (!mptcp_rtx_timer_pending(sk))
+		mptcp_reset_rtx_timer(sk);
 }
 
 /* schedule the timeout timer for the relevant event: either close timeout
  * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
  */
-void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
+void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout)
 {
 	struct sock *sk = (struct sock *)msk;
 	unsigned long timeout, close_timeout;
 
-	if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
+	if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp)
 		return;
 
-	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;
+	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies +
+			TCP_TIMEWAIT_LEN;
 
 	/* the close timeout takes precedence on the fail one, and here at least one of
 	 * them is active
 	 */
-	timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;
+	timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout;
 
 	sk_reset_timer(sk, &sk->sk_timer, timeout);
 }
@@ -2627,8 +2683,6 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
 	mptcp_subflow_reset(ssk);
 	WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
 	unlock_sock_fast(ssk, slow);
-
-	mptcp_reset_timeout(msk, 0);
 }
 
 static void mptcp_do_fastclose(struct sock *sk)
@@ -2665,18 +2719,14 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
 		__mptcp_close_subflow(sk);
 
-	/* There is no point in keeping around an orphaned sk timedout or
-	 * closed, but we need the msk around to reply to incoming DATA_FIN,
-	 * even if it is orphaned and in FIN_WAIT2 state
-	 */
-	if (sock_flag(sk, SOCK_DEAD)) {
-		if (mptcp_should_close(sk))
-			mptcp_do_fastclose(sk);
+	if (mptcp_close_tout_expired(sk)) {
+		mptcp_do_fastclose(sk);
+		mptcp_close_wake_up(sk);
+	}
 
-		if (sk->sk_state == TCP_CLOSE) {
-			__mptcp_destroy_sock(sk);
-			goto unlock;
-		}
+	if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) {
+		__mptcp_destroy_sock(sk);
+		goto unlock;
 	}
 
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
@@ -2717,7 +2767,7 @@ static void __mptcp_init_sock(struct sock *sk)
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
+	timer_setup(&sk->sk_timer, mptcp_tout_timer, 0);
 }
 
 static void mptcp_ca_reset(struct sock *sk)
@@ -2808,8 +2858,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 		} else {
 			pr_debug("Sending DATA_FIN on subflow %p", ssk);
 			tcp_send_ack(ssk);
-			if (!mptcp_timer_pending(sk))
-				mptcp_reset_timer(sk);
+			if (!mptcp_rtx_timer_pending(sk))
+				mptcp_reset_rtx_timer(sk);
 		}
 		break;
 	}
@@ -2892,7 +2942,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 
 	might_sleep();
 
-	mptcp_stop_timer(sk);
+	mptcp_stop_rtx_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
 	mptcp_release_sched(msk);
@@ -2975,7 +3025,6 @@ bool __mptcp_close(struct sock *sk, long timeout)
 
 cleanup:
 	/* orphan all the subflows */
-	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast_nested(ssk);
@@ -3012,7 +3061,7 @@ cleanup:
 		__mptcp_destroy_sock(sk);
 		do_cancel_work = true;
 	} else {
-		mptcp_reset_timeout(msk, 0);
+		mptcp_start_tout_timer(sk);
 	}
 
 	return do_cancel_work;
@@ -3059,12 +3108,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	/* Deny disconnect if other threads are blocked in sk_wait_event()
-	 * or inet_wait_for_connect().
-	 */
-	if (sk->sk_wait_pending)
-		return -EBUSY;
-
 	/* We are on the fastopen error path. We can't call straight into the
 	 * subflows cleanup code due to lock nesting (we are already under
 	 * msk->firstsocket lock).
@@ -3075,8 +3118,8 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_check_listen_stop(sk);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
-	mptcp_stop_timer(sk);
-	sk_stop_timer(sk, &sk->sk_timer);
+	mptcp_stop_rtx_timer(sk);
+	mptcp_stop_tout_timer(sk);
 
 	if (msk->token)
 		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
@@ -3134,7 +3177,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 		inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
 #endif
 
-	nsk->sk_wait_pending = 0;
 	__mptcp_init_sock(nsk);
 
 	msk = mptcp_sk(nsk);
@@ -3386,24 +3428,21 @@ static void schedule_3rdack_retransmission(struct sock *ssk)
 	sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
 }
 
-void mptcp_subflow_process_delegated(struct sock *ssk)
+void mptcp_subflow_process_delegated(struct sock *ssk, long status)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
-	if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+	if (status & BIT(MPTCP_DELEGATE_SEND)) {
 		mptcp_data_lock(sk);
 		if (!sock_owned_by_user(sk))
 			__mptcp_subflow_push_pending(sk, ssk, true);
 		else
 			__set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags);
 		mptcp_data_unlock(sk);
-		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND);
 	}
-	if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) {
+	if (status & BIT(MPTCP_DELEGATE_ACK))
 		schedule_3rdack_retransmission(ssk);
-		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK);
-	}
 }
 
 static int mptcp_hash(struct sock *sk)
@@ -3929,14 +3968,17 @@ static int mptcp_napi_poll(struct napi_struct *napi, int budget)
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
 		bh_lock_sock_nested(ssk);
-		if (!sock_owned_by_user(ssk) &&
-		    mptcp_subflow_has_delegated_action(subflow))
-			mptcp_subflow_process_delegated(ssk);
-		/* ... elsewhere tcp_release_cb_override already processed
-		 * the action or will do at next release_sock().
-		 * In both case must dequeue the subflow here - on the same
-		 * CPU that scheduled it.
-		 */
+		if (!sock_owned_by_user(ssk)) {
+			mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0));
+		} else {
+			/* tcp_release_cb_override already processed
+			 * the action or will do at next release_sock().
+			 * In both case must dequeue the subflow here - on the same
+			 * CPU that scheduled it.
+			 */
+			smp_wmb();
+			clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status);
+		}
 		bh_unlock_sock(ssk);
 		sock_put(ssk);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7254b3562575..3612545fa62e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -444,9 +444,11 @@ struct mptcp_delegated_action {
 
 DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 
-#define MPTCP_DELEGATE_SEND		0
-#define MPTCP_DELEGATE_ACK		1
+#define MPTCP_DELEGATE_SCHEDULED	0
+#define MPTCP_DELEGATE_SEND		1
+#define MPTCP_DELEGATE_ACK		2
 
+#define MPTCP_DELEGATE_ACTIONS_MASK	(~BIT(MPTCP_DELEGATE_SCHEDULED))
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
 	struct	list_head node;/* conn_list of subflows */
@@ -564,23 +566,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
 	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
 }
 
-void mptcp_subflow_process_delegated(struct sock *ssk);
+void mptcp_subflow_process_delegated(struct sock *ssk, long actions);
 
 static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action)
 {
+	long old, set_bits = BIT(MPTCP_DELEGATE_SCHEDULED) | BIT(action);
 	struct mptcp_delegated_action *delegated;
 	bool schedule;
 
 	/* the caller held the subflow bh socket lock */
 	lockdep_assert_in_softirq();
 
-	/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
-	 * ensures the below list check sees list updates done prior to status
-	 * bit changes
+	/* The implied barrier pairs with tcp_release_cb_override()
+	 * mptcp_napi_poll(), and ensures the below list check sees list
+	 * updates done prior to delegated status bits changes
 	 */
-	if (!test_and_set_bit(action, &subflow->delegated_status)) {
-		/* still on delegated list from previous scheduling */
-		if (!list_empty(&subflow->delegated_node))
+	old = set_mask_bits(&subflow->delegated_status, 0, set_bits);
+	if (!(old & BIT(MPTCP_DELEGATE_SCHEDULED))) {
+		if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node)))
 			return;
 
 		delegated = this_cpu_ptr(&mptcp_delegated_actions);
@@ -605,20 +608,6 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
 	return ret;
 }
 
-static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
-{
-	return !!READ_ONCE(subflow->delegated_status);
-}
-
-static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action)
-{
-	/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
-	 * touching the status bit
-	 */
-	smp_wmb();
-	clear_bit(action, &subflow->delegated_status);
-}
-
 int mptcp_is_enabled(const struct net *net);
 unsigned int mptcp_get_add_addr_timeout(const struct net *net);
 int mptcp_is_checksum_enabled(const struct net *net);
@@ -718,7 +707,29 @@ void mptcp_get_options(const struct sk_buff *skb,
 
 void mptcp_finish_connect(struct sock *sk);
 void __mptcp_set_connected(struct sock *sk);
-void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout);
+void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout);
+
+static inline void mptcp_stop_tout_timer(struct sock *sk)
+{
+	if (!inet_csk(sk)->icsk_mtup.probe_timestamp)
+		return;
+
+	sk_stop_timer(sk, &sk->sk_timer);
+	inet_csk(sk)->icsk_mtup.probe_timestamp = 0;
+}
+
+static inline void mptcp_set_close_tout(struct sock *sk, unsigned long tout)
+{
+	/* avoid 0 timestamp, as that means no close timeout */
+	inet_csk(sk)->icsk_mtup.probe_timestamp = tout ? : 1;
+}
+
+static inline void mptcp_start_tout_timer(struct sock *sk)
+{
+	mptcp_set_close_tout(sk, tcp_jiffies32);
+	mptcp_reset_tout_timer(mptcp_sk(sk), 0);
+}
+
 static inline bool mptcp_is_fully_established(struct sock *sk)
 {
 	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 9bf3c7bc1762..9c1f8d1d63d2 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1226,7 +1226,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 	WRITE_ONCE(subflow->fail_tout, fail_tout);
 	tcp_send_ack(ssk);
 
-	mptcp_reset_timeout(msk, subflow->fail_tout);
+	mptcp_reset_tout_timer(msk, subflow->fail_tout);
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -1362,42 +1362,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
 	*full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
-void __mptcp_error_report(struct sock *sk)
-{
-	struct mptcp_subflow_context *subflow;
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		int err = sock_error(ssk);
-		int ssk_state;
-
-		if (!err)
-			continue;
-
-		/* only propagate errors on fallen-back sockets or
-		 * on MPC connect
-		 */
-		if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk))
-			continue;
-
-		/* We need to propagate only transition to CLOSE state.
-		 * Orphaned socket will see such state change via
-		 * subflow_sched_work_if_closed() and that path will properly
-		 * destroy the msk as needed.
-		 */
-		ssk_state = inet_sk_state_load(ssk);
-		if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
-			inet_sk_state_store(sk, ssk_state);
-		WRITE_ONCE(sk->sk_err, -err);
-
-		/* This barrier is coupled with smp_rmb() in mptcp_poll() */
-		smp_wmb();
-		sk_error_report(sk);
-		break;
-	}
-}
-
 static void subflow_error_report(struct sock *ssk)
 {
 	struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
@@ -1588,6 +1552,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	mptcp_sock_graft(ssk, sk->sk_socket);
 	iput(SOCK_INODE(sf));
 	WRITE_ONCE(msk->allow_infinite_fallback, false);
+	mptcp_stop_tout_timer(sk);
 	return 0;
 
 failed_unlink:
@@ -1991,9 +1956,15 @@ 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);
 }