mptcp: get rid of msk->subflow

Such field is now unused just as a flag to control the first subflow
deletion at close() time. Introduce a new bit flag for that and finally
drop the mentioned field.

As an intended side effect, now the first subflow sock is not freed
before close() even for passive sockets. The msk has no open/active
subflows if the first one is closed and the subflow list is singular,
update accordingly the state check in mptcp_stream_accept().

Among other benefits, the subflow removal, reduces the amount of memory
used on the client side for each mptcp connection, allows passive sockets
to go through successful accept()/disconnect()/connect() and makes return
error code consistent for failing both passive and active sockets.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/290
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 12 insertions, 26 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index fafa83ee4a72..e715771ded7c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -92,7 +92,6 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 
 	msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio;
 	WRITE_ONCE(msk->first, ssock->sk);
-	WRITE_ONCE(msk->subflow, ssock);
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssock->sk);
@@ -102,6 +101,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	/* This is the first subflow, always with id 0 */
 	subflow->local_id_valid = 1;
 	mptcp_sock_graft(msk->first, sk->sk_socket);
+	iput(SOCK_INODE(ssock));
 
 	return 0;
 }
@@ -2238,14 +2238,6 @@ static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
 	return min_stale_count > 1 ? backup : NULL;
 }
 
-static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
-{
-	if (msk->subflow) {
-		iput(SOCK_INODE(msk->subflow));
-		WRITE_ONCE(msk->subflow, NULL);
-	}
-}
-
 bool __mptcp_retransmit_pending_data(struct sock *sk)
 {
 	struct mptcp_data_frag *cur, *rtx_head;
@@ -2324,7 +2316,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		goto out_release;
 	}
 
-	dispose_it = !msk->subflow || ssk != msk->subflow->sk;
+	dispose_it = msk->free_first || ssk != msk->first;
 	if (dispose_it)
 		list_del(&subflow->node);
 
@@ -2345,7 +2337,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		 * disconnect should never fail
 		 */
 		WARN_ON_ONCE(tcp_disconnect(ssk, 0));
-		msk->subflow->state = SS_UNCONNECTED;
 		mptcp_subflow_ctx_reset(subflow);
 		release_sock(ssk);
 
@@ -3106,7 +3097,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
-	WRITE_ONCE(msk->subflow, NULL);
 	msk->in_accept_queue = 1;
 	WRITE_ONCE(msk->fully_established, false);
 	if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
@@ -3240,10 +3230,8 @@ static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	/* clears msk->subflow, allowing the following to close
-	 * even the initial subflow
-	 */
-	mptcp_dispose_initial_subflow(msk);
+	/* allow the following to close even the initial subflow */
+	msk->free_first = 1;
 	mptcp_destroy_common(msk, 0);
 	sk_sockets_allocated_dec(sk);
 }
@@ -3782,11 +3770,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 		/* Do late cleanup for the first subflow as necessary. Also
 		 * deal with bad peers not doing a complete shutdown.
 		 */
-		if (msk->first &&
-		    unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
+		if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) {
 			__mptcp_close_ssk(newsk, msk->first,
 					  mptcp_subflow_ctx(msk->first), 0);
-			if (unlikely(list_empty(&msk->conn_list)))
+			if (unlikely(list_is_singular(&msk->conn_list)))
 				inet_sk_state_store(newsk, TCP_CLOSE);
 		}
 	}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index dccc96dc2d6b..38c7ea013361 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -299,7 +299,8 @@ struct mptcp_sock {
 			cork:1,
 			nodelay:1,
 			fastopening:1,
-			in_accept_queue:1;
+			in_accept_queue:1,
+			free_first:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -308,12 +309,10 @@ struct mptcp_sock {
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct socket	*subflow; /* outgoing connect/listener/!mp_capable
-				   * The mptcp ops can safely dereference, using suitable
-				   * ONCE annotation, the subflow outside the socket
-				   * lock as such sock is freed after close().
-				   */
-	struct sock	*first;
+	struct sock	*first; /* The mptcp ops can safely dereference, using suitable
+				 * ONCE annotation, the subflow outside the socket
+				 * lock as such sock is freed after close().
+				 */
 	struct mptcp_pm_data	pm;
 	struct {
 		u32	space;	/* bytes copied in last measurement window */