1 files changed, 47 insertions, 36 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a26c2c840fd9..37ebcb7640eb 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -139,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	    !skb_try_coalesce(to, from, &fragstolen, &delta))
 		return false;
 
-	pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
+	pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n",
 		 MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
 		 to->len, MPTCP_SKB_CB(from)->end_seq);
 	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
@@ -217,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	end_seq = MPTCP_SKB_CB(skb)->end_seq;
 	max_seq = atomic64_read(&msk->rcv_wnd_sent);
 
-	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
+	pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq,
 		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
 	if (after64(end_seq, max_seq)) {
 		/* out of window */
@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	skb_orphan(skb);
 
 	/* try to fetch required memory from subflow */
-	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		goto drop;
+	}
 
 	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
 
@@ -641,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		}
 	}
 
-	pr_debug("msk=%p ssk=%p", msk, ssk);
+	pr_debug("msk=%p ssk=%p\n", msk, ssk);
 	tp = tcp_sk(ssk);
 	do {
 		u32 map_remaining, offset;
@@ -722,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 	u64 end_seq;
 
 	p = rb_first(&msk->out_of_order_queue);
-	pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
+	pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
 	while (p) {
 		skb = rb_to_skb(p);
 		if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
@@ -744,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 			int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
 
 			/* skip overlapping data, if any */
-			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
+			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n",
 				 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
 				 delta);
 			MPTCP_SKB_CB(skb)->offset += delta;
@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 		sk_rbuf = ssk_rbuf;
 
 	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (__mptcp_rmem(sk) > sk_rbuf) {
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+	if (__mptcp_rmem(sk) > sk_rbuf)
 		return;
-	}
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
@@ -1240,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	size_t copy;
 	int i;
 
-	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
+	pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n",
 		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
 
 	if (WARN_ON_ONCE(info->sent > info->limit ||
@@ -1341,7 +1341,7 @@ alloc_skb:
 	mpext->use_map = 1;
 	mpext->dsn64 = 1;
 
-	pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
+	pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n",
 		 mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 		 mpext->dsn64);
 
@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	}
 
 	mptcp_for_each_subflow(msk, subflow) {
+		bool backup = subflow->backup || subflow->request_bkup;
+
 		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
 		tout = max(tout, mptcp_timeout_from_subflow(subflow));
-		nr_active += !subflow->backup;
+		nr_active += !backup;
 		pace = subflow->avg_pacing_rate;
 		if (unlikely(!pace)) {
 			/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		}
 
 		linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
-		if (linger_time < send_info[subflow->backup].linger_time) {
-			send_info[subflow->backup].ssk = ssk;
-			send_info[subflow->backup].linger_time = linger_time;
+		if (linger_time < send_info[backup].linger_time) {
+			send_info[backup].ssk = ssk;
+			send_info[backup].linger_time = linger_time;
 		}
 	}
 	__mptcp_set_timeout(sk, tout);
@@ -1890,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			if (!msk->first_pending)
 				WRITE_ONCE(msk->first_pending, dfrag);
 		}
-		pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
+		pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
 			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
 			 !dfrag_collapsed);
 
@@ -2246,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			}
 		}
 
-		pr_debug("block timeout %ld", timeo);
+		pr_debug("block timeout %ld\n", timeo);
 		sk_wait_data(sk, &timeo, NULL);
 	}
 
@@ -2262,7 +2264,7 @@ out_err:
 		}
 	}
 
-	pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+	pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
 		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
 		 skb_queue_empty(&msk->receive_queue), copied);
 	if (!(flags & MSG_PEEK))
@@ -2324,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 			continue;
 		}
 
-		if (subflow->backup) {
+		if (subflow->backup || subflow->request_bkup) {
 			if (!backup)
 				backup = ssk;
 			continue;
@@ -2506,6 +2508,12 @@ out:
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		     struct mptcp_subflow_context *subflow)
 {
+	/* The first subflow can already be closed and still in the list */
+	if (subflow->close_event_done)
+		return;
+
+	subflow->close_event_done = true;
+
 	if (sk->sk_state == TCP_ESTABLISHED)
 		mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
 
@@ -2531,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk)
 
 	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int ssk_state = inet_sk_state_load(ssk);
 
-		if (inet_sk_state_load(ssk) != TCP_CLOSE)
+		if (ssk_state != TCP_CLOSE &&
+		    (ssk_state != TCP_CLOSE_WAIT ||
+		     inet_sk_state_load(sk) != TCP_ESTABLISHED))
 			continue;
 
 		/* 'subflow_data_ready' will re-sched once rx queue is empty */
@@ -2712,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
 	if (!ssk)
 		return;
 
-	pr_debug("MP_FAIL doesn't respond, reset the subflow");
+	pr_debug("MP_FAIL doesn't respond, reset the subflow\n");
 
 	slow = lock_sock_fast(ssk);
 	mptcp_subflow_reset(ssk);
@@ -2886,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 		break;
 	default:
 		if (__mptcp_check_fallback(mptcp_sk(sk))) {
-			pr_debug("Fallback");
+			pr_debug("Fallback\n");
 			ssk->sk_shutdown |= how;
 			tcp_shutdown(ssk, how);
 
@@ -2896,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 			WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
 			mptcp_schedule_work(sk);
 		} else {
-			pr_debug("Sending DATA_FIN on subflow %p", ssk);
+			pr_debug("Sending DATA_FIN on subflow %p\n", ssk);
 			tcp_send_ack(ssk);
 			if (!mptcp_rtx_timer_pending(sk))
 				mptcp_reset_rtx_timer(sk);
@@ -2962,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk)
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+	pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n",
 		 msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
 		 msk->snd_nxt, msk->write_seq);
 
@@ -2986,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+	pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n",
 		 msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
 		 !!mptcp_send_head(sk));
 
@@ -3001,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	pr_debug("msk=%p", msk);
+	pr_debug("msk=%p\n", msk);
 
 	might_sleep();
 
@@ -3109,7 +3120,7 @@ cleanup:
 		mptcp_set_state(sk, TCP_CLOSE);
 
 	sock_hold(sk);
-	pr_debug("msk=%p state=%d", sk, sk->sk_state);
+	pr_debug("msk=%p state=%d\n", sk, sk->sk_state);
 	if (msk->token)
 		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 
@@ -3541,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	pr_debug("msk=%p, ssk=%p", msk, msk->first);
+	pr_debug("msk=%p, ssk=%p\n", msk, msk->first);
 	if (WARN_ON_ONCE(!msk->first))
 		return -EINVAL;
 
@@ -3558,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk)
 	sk = subflow->conn;
 	msk = mptcp_sk(sk);
 
-	pr_debug("msk=%p, token=%u", sk, subflow->token);
+	pr_debug("msk=%p, token=%u\n", sk, subflow->token);
 
 	subflow->map_seq = subflow->iasn;
 	subflow->map_subflow_seq = 1;
@@ -3587,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk)
 	struct sock *parent = (void *)msk;
 	bool ret = true;
 
-	pr_debug("msk=%p, subflow=%p", msk, subflow);
+	pr_debug("msk=%p, subflow=%p\n", msk, subflow);
 
 	/* mptcp socket already closing? */
 	if (!mptcp_is_fully_established(parent)) {
@@ -3633,7 +3644,7 @@ err_prohibited:
 
 static void mptcp_shutdown(struct sock *sk, int how)
 {
-	pr_debug("sk=%p, how=%d", sk, how);
+	pr_debug("sk=%p, how=%d\n", sk, how);
 
 	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
 		__mptcp_wr_shutdown(sk);
@@ -3854,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
 	struct sock *ssk;
 	int err;
 
-	pr_debug("msk=%p", msk);
+	pr_debug("msk=%p\n", msk);
 
 	lock_sock(sk);
 
@@ -3893,7 +3904,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	struct mptcp_sock *msk = mptcp_sk(sock->sk);
 	struct sock *ssk, *newsk;
 
-	pr_debug("msk=%p", msk);
+	pr_debug("msk=%p\n", msk);
 
 	/* Buggy applications can call accept on socket states other then LISTEN
 	 * but no need to allocate the first subflow just to error out.
@@ -3902,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (!ssk)
 		return -EINVAL;
 
-	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+	pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk));
 	newsk = inet_csk_accept(ssk, arg);
 	if (!newsk)
 		return arg->err;
 
-	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+	pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk));
 	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *new_mptcp_sock;
@@ -4000,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	sock_poll_wait(file, sock, wait);
 
 	state = inet_sk_state_load(sk);
-	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
+	pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags);
 	if (state == TCP_LISTEN) {
 		struct sock *ssk = READ_ONCE(msk->first);