1 files changed, 16 insertions, 41 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index dbcebf56798f..d073b2111382 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -528,7 +528,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
 
 		sk->sk_shutdown |= RCV_SHUTDOWN;
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
 
 		switch (sk->sk_state) {
 		case TCP_ESTABLISHED:
@@ -742,10 +741,9 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
-	if (move_skbs_to_msk(msk, ssk)) {
-		set_bit(MPTCP_DATA_READY, &msk->flags);
+	if (move_skbs_to_msk(msk, ssk))
 		sk->sk_data_ready(sk);
-	}
+
 	mptcp_data_unlock(sk);
 }
 
@@ -847,7 +845,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		sk->sk_shutdown |= RCV_SHUTDOWN;
 
 		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
 		sk->sk_data_ready(sk);
 	}
 
@@ -1759,21 +1756,6 @@ out:
 	return copied ? : ret;
 }
 
-static void mptcp_wait_data(struct sock *sk, long *timeo)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	add_wait_queue(sk_sleep(sk), &wait);
-	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-
-	sk_wait_event(sk, timeo,
-		      test_bit(MPTCP_DATA_READY, &msk->flags), &wait);
-
-	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	remove_wait_queue(sk_sleep(sk), &wait);
-}
-
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len, int flags,
@@ -2077,19 +2059,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		pr_debug("block timeout %ld", timeo);
-		mptcp_wait_data(sk, &timeo);
-	}
-
-	if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
-	    skb_queue_empty(&msk->receive_queue)) {
-		/* entire backlog drained, clear DATA_READY. */
-		clear_bit(MPTCP_DATA_READY, &msk->flags);
-
-		/* .. race-breaker: ssk might have gotten new data
-		 * after last __mptcp_move_skbs() returned false.
-		 */
-		if (unlikely(__mptcp_move_skbs(msk)))
-			set_bit(MPTCP_DATA_READY, &msk->flags);
+		sk_wait_data(sk, &timeo, NULL);
 	}
 
 out_err:
@@ -2098,9 +2068,9 @@ out_err:
 			tcp_recv_timestamp(msg, sk, &tss);
 	}
 
-	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
-		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
-		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
+	pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
+		 skb_queue_empty(&msk->receive_queue), copied);
 	if (!(flags & MSG_PEEK))
 		mptcp_rcv_space_adjust(msk, copied);
 
@@ -2368,7 +2338,6 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 	inet_sk_state_store(sk, TCP_CLOSE);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-	set_bit(MPTCP_DATA_READY, &msk->flags);
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
 
 	mptcp_close_wake_up(sk);
@@ -2735,7 +2704,7 @@ cleanup:
 	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
 	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		bool slow = lock_sock_fast(ssk);
+		bool slow = lock_sock_fast_nested(ssk);
 
 		sock_orphan(ssk);
 		unlock_sock_fast(ssk, slow);
@@ -3385,8 +3354,14 @@ unlock_fail:
 
 static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 {
-	return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM :
-	       0;
+	/* Concurrent splices from sk_receive_queue into receive_queue will
+	 * always show at least one non-empty queue when checked in this order.
+	 */
+	if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) &&
+	    skb_queue_empty_lockless(&msk->receive_queue))
+		return 0;
+
+	return EPOLLIN | EPOLLRDNORM;
 }
 
 static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
@@ -3421,7 +3396,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	state = inet_sk_state_load(sk);
 	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN)
-		return mptcp_check_readable(msk);
+		return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : 0;
 
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);