mptcp: add subflow write space signalling and mptcp_poll

Add new SEND_SPACE flag to indicate that a subflow has enough space to
accept more data for transmission.

It gets cleared at the end of mptcp_sendmsg() in case ssk has run
below the free watermark.

It is (re-set) from the wspace callback.

This allows us to use msk->flags to determine the poll mask.

Co-developed-by: Peter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: Peter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/mptcp/protocol.c

@@ -176,6 +176,23 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	return ret;
 }
 
+static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk)
+{
+	struct socket *sock;
+
+	if (likely(sk_stream_is_writeable(ssk)))
+		return;
+
+	sock = READ_ONCE(ssk->sk_socket);
+
+	if (sock) {
+		clear_bit(MPTCP_SEND_SPACE, &msk->flags);
+		smp_mb__after_atomic();
+		/* set NOSPACE only after clearing SEND_SPACE flag */
+		set_bit(SOCK_NOSPACE, &sock->flags);
+	}
+}
+
 static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -219,6 +236,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (copied > 0)
 		ret = copied;
 
+	ssk_check_wmem(msk, ssk);
 	release_sock(ssk);
 	release_sock(sk);
 	return ret;
@@ -315,6 +333,7 @@ static int mptcp_init_sock(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	INIT_LIST_HEAD(&msk->conn_list);
+	__set_bit(MPTCP_SEND_SPACE, &msk->flags);
 
 	return 0;
 }
@@ -576,6 +595,13 @@ static void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
+static bool mptcp_memory_free(const struct sock *sk, int wake)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
+}
+
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -591,6 +617,7 @@ static struct proto mptcp_prot = {
 	.hash		= inet_hash,
 	.unhash		= inet_unhash,
 	.get_port	= mptcp_get_port,
+	.stream_memory_free	= mptcp_memory_free,
 	.obj_size	= sizeof(struct mptcp_sock),
 	.no_autobind	= true,
 };
@@ -767,8 +794,34 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait)
 {
+	const struct mptcp_sock *msk;
+	struct sock *sk = sock->sk;
+	struct socket *ssock;
 	__poll_t mask = 0;
 
+	msk = mptcp_sk(sk);
+	lock_sock(sk);
+	ssock = __mptcp_nmpc_socket(msk);
+	if (ssock) {
+		mask = ssock->ops->poll(file, ssock, wait);
+		release_sock(sk);
+		return mask;
+	}
+
+	release_sock(sk);
+	sock_poll_wait(file, sock, wait);
+	lock_sock(sk);
+
+	if (test_bit(MPTCP_DATA_READY, &msk->flags))
+		mask = EPOLLIN | EPOLLRDNORM;
+	if (sk_stream_is_writeable(sk) &&
+	    test_bit(MPTCP_SEND_SPACE, &msk->flags))
+		mask |= EPOLLOUT | EPOLLWRNORM;
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+
+	release_sock(sk);
+
 	return mask;
 }
 

net/mptcp/protocol.h

@@ -56,6 +56,7 @@
 
 /* MPTCP socket flags */
 #define MPTCP_DATA_READY	BIT(0)
+#define MPTCP_SEND_SPACE	BIT(1)
 
 /* MPTCP connection sock */
 struct mptcp_sock {

net/mptcp/subflow.c

@@ -529,6 +529,9 @@ static void subflow_write_space(struct sock *sk)
 
 	sk_stream_write_space(sk);
 	if (parent && sk_stream_is_writeable(sk)) {
+		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
+		smp_mb__after_atomic();
+		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
 		sk_stream_write_space(parent);
 	}
 }