mptcp: support TCP_CORK and TCP_NODELAY

First, add cork and nodelay fields to the mptcp_sock structure
so they can be used in sync_socket_options(), and fill them on setsockopt
while holding the msk socket lock.

Then, on setsockopt set proper tcp_sk(ssk)->nonagle values for subflows
by calling __tcp_sock_set_cork() or __tcp_sock_set_nodelay() on the ssk
while holding the ssk socket lock.

tcp_push_pending_frames() will be invoked on the ssk if a cork was cleared
or nodelay was set. Also set MPTCP_PUSH_PENDING bit by calling
mptcp_check_and_set_pending(). This will lead to __mptcp_push_pending()
being called inside mptcp_release_cb() with new tcp_sk(ssk)->nonagle.

Also add getsockopt support for TCP_CORK and TCP_NODELAY.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Maxim Galaganov <max@internet.ru>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 73 insertions, 1 deletions

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 147b22da41ca..e1469155fb15 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -249,7 +249,9 @@ struct mptcp_sock {
 	bool		rcv_fastclose;
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	bool		csum_enabled;
-	u8		recvmsg_inq:1;
+	u8		recvmsg_inq:1,
+			cork:1,
+			nodelay:1;
 	spinlock_t	join_list_lock;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 44e0a37c567c..3c3db22fd36a 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -616,6 +616,66 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	return ret;
 }
 
+static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval,
+					 unsigned int optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	int val;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
+		return -EFAULT;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	msk->cork = !!val;
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		__tcp_sock_set_cork(ssk, !!val);
+		release_sock(ssk);
+	}
+	if (!val)
+		mptcp_check_and_set_pending(sk);
+	release_sock(sk);
+
+	return 0;
+}
+
+static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval,
+					    unsigned int optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	int val;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
+		return -EFAULT;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	msk->nodelay = !!val;
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		__tcp_sock_set_nodelay(ssk, !!val);
+		release_sock(ssk);
+	}
+	if (val)
+		mptcp_check_and_set_pending(sk);
+	release_sock(sk);
+
+	return 0;
+}
+
 static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int optname,
 						   sockptr_t optval, unsigned int optlen)
 {
@@ -717,6 +777,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 		return -EOPNOTSUPP;
 	case TCP_CONGESTION:
 		return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
+	case TCP_CORK:
+		return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen);
+	case TCP_NODELAY:
+		return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen);
 	}
 
 	return -EOPNOTSUPP;
@@ -1087,6 +1151,10 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 						      optval, optlen);
 	case TCP_INQ:
 		return mptcp_put_int_option(msk, optval, optlen, msk->recvmsg_inq);
+	case TCP_CORK:
+		return mptcp_put_int_option(msk, optval, optlen, msk->cork);
+	case TCP_NODELAY:
+		return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
 	}
 	return -EOPNOTSUPP;
 }
@@ -1189,6 +1257,8 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 
 	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
 		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
+	__tcp_sock_set_cork(ssk, !!msk->cork);
+	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
 
 	inet_sk(ssk)->transparent = inet_sk(sk)->transparent;
 	inet_sk(ssk)->freebind = inet_sk(sk)->freebind;