Merge branch 'mptcp-fastclose'

Mat Martineau says:

====================
mptcp: Fastclose edge cases and error handling

MPTCP has existing code to use the MP_FASTCLOSE option header, which
works like a RST for the MPTCP-level connection (regular RSTs only
affect specific subflows in MPTCP). This series has some improvements
for fastclose.

Patch 1 aligns fastclose socket error handling with TCP RST behavior on
TCP sockets.

Patch 2 adds use of MP_FASTCLOSE in some more edge cases, like file
descriptor close, FIN_WAIT timeout, and when the socket has unread data.

Patch 3 updates the fastclose self tests.

Patch 4 does not change any code, just fixes some outdated comments.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

net/mptcp/protocol.c

@@ -662,19 +662,19 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 
 		skb = skb_peek(&ssk->sk_receive_queue);
 		if (!skb) {
-			/* if no data is found, a racing workqueue/recvmsg
-			 * already processed the new data, stop here or we
-			 * can enter an infinite loop
+			/* With racing move_skbs_to_msk() and __mptcp_move_skbs(),
+			 * a different CPU can have already processed the pending
+			 * data, stop here or we can enter an infinite loop
 			 */
 			if (!moved)
 				done = true;
 			break;
 		}
 
 		if (__mptcp_check_fallback(msk)) {
-			/* if we are running under the workqueue, TCP could have
-			 * collapsed skbs between dummy map creation and now
-			 * be sure to adjust the size
+			/* Under fallback skbs have no MPTCP extension and TCP could
+			 * collapse them between the dummy map creation and the
+			 * current dequeue. Be sure to adjust the map size.
 			 */
 			map_remaining = skb->len;
 			subflow->map_data_len = skb->len;
@@ -1707,7 +1707,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			goto out;
 		} else if (ret) {
 			release_sock(ssk);
-			goto out;
+			goto do_error;
 		}
 		release_sock(ssk);
 	}
@@ -1717,9 +1717,13 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
 		ret = sk_stream_wait_connect(sk, &timeo);
 		if (ret)
-			goto out;
+			goto do_error;
 	}
 
+	ret = -EPIPE;
+	if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)))
+		goto do_error;
+
 	pfrag = sk_page_frag(sk);
 
 	while (msg_data_left(msg)) {
@@ -1728,11 +1732,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		bool dfrag_collapsed;
 		size_t psize, offset;
 
-		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
-			ret = -EPIPE;
-			goto out;
-		}
-
 		/* reuse tail pfrag, if possible, or carve a new one from the
 		 * page allocator
 		 */
@@ -1764,7 +1763,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (copy_page_from_iter(dfrag->page, offset, psize,
 					&msg->msg_iter) != psize) {
 			ret = -EFAULT;
-			goto out;
+			goto do_error;
 		}
 
 		/* data successfully copied into the write queue */
@@ -1796,15 +1795,22 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		__mptcp_push_pending(sk, msg->msg_flags);
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret)
-			goto out;
+			goto do_error;
 	}
 
 	if (copied)
 		__mptcp_push_pending(sk, msg->msg_flags);
 
 out:
 	release_sock(sk);
-	return copied ? : ret;
+	return copied;
+
+do_error:
+	if (copied)
+		goto out;
+
+	copied = sk_stream_error(sk, msg->msg_flags, ret);
+	goto out;
 }
 
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
@@ -2307,8 +2313,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 
 	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
 
-	if (flags & MPTCP_CF_FASTCLOSE)
+	if (flags & MPTCP_CF_FASTCLOSE) {
+		/* be sure to force the tcp_disconnect() path,
+		 * to generate the egress reset
+		 */
+		ssk->sk_lingertime = 0;
+		sock_set_flag(ssk, SOCK_LINGER);
 		subflow->send_fastclose = 1;
+	}
 
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
@@ -2441,12 +2453,31 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 		unlock_sock_fast(tcp_sk, slow);
 	}
 
+	/* Mirror the tcp_reset() error propagation */
+	switch (sk->sk_state) {
+	case TCP_SYN_SENT:
+		sk->sk_err = ECONNREFUSED;
+		break;
+	case TCP_CLOSE_WAIT:
+		sk->sk_err = EPIPE;
+		break;
+	case TCP_CLOSE:
+		return;
+	default:
+		sk->sk_err = ECONNRESET;
+	}
+
 	inet_sk_state_store(sk, TCP_CLOSE);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
 	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
 
-	mptcp_close_wake_up(sk);
+	/* the calling mptcp_worker will properly destroy the socket */
+	if (sock_flag(sk, SOCK_DEAD))
+		return;
+
+	sk->sk_state_change(sk);
+	sk_error_report(sk);
 }
 
 static void __mptcp_retrans(struct sock *sk)
@@ -2552,6 +2583,16 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
 	mptcp_reset_timeout(msk, 0);
 }
 
+static void mptcp_do_fastclose(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	mptcp_for_each_subflow_safe(msk, subflow, tmp)
+		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
+				  subflow, MPTCP_CF_FASTCLOSE);
+}
+
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
@@ -2580,11 +2621,15 @@ static void mptcp_worker(struct work_struct *work)
 	 * 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) &&
-	    (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) {
-		inet_sk_state_store(sk, TCP_CLOSE);
-		__mptcp_destroy_sock(sk);
-		goto unlock;
+	if (sock_flag(sk, SOCK_DEAD)) {
+		if (mptcp_check_close_timeout(sk)) {
+			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_do_fastclose(sk);
+		}
+		if (sk->sk_state == TCP_CLOSE) {
+			__mptcp_destroy_sock(sk);
+			goto unlock;
+		}
 	}
 
 	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
@@ -2825,6 +2870,18 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
+static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
+{
+	/* 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;
+}
+
 bool __mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow;
@@ -2838,8 +2895,13 @@ bool __mptcp_close(struct sock *sk, long timeout)
 		goto cleanup;
 	}
 
-	if (mptcp_close_state(sk))
+	if (mptcp_check_readable(msk)) {
+		/* the msk has read data, do the MPTCP equivalent of TCP reset */
+		inet_sk_state_store(sk, TCP_CLOSE);
+		mptcp_do_fastclose(sk);
+	} else if (mptcp_close_state(sk)) {
 		__mptcp_wr_shutdown(sk);
+	}
 
 	sk_stream_wait_close(sk, timeout);
 
@@ -3656,18 +3718,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	return err;
 }
 
-static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
-{
-	/* 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)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -3718,7 +3768,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
 
-	/* This barrier is coupled with smp_wmb() in tcp_reset() */
+	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
 	smp_rmb();
 	if (sk->sk_err)
 		mask |= EPOLLERR;