Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Matthieu Baerts <matthieu.baerts@tessares.net>
Date:   Fri, 11 Aug 2023 17:57:15 +0200
Subject: [PATCH net-next 02/14] mptcp: avoid additional
 __inet_stream_connect() call
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Message-Id: <20230811-upstream-net-next-20230811-mptcp-get-rid-of-msk-subflow-v1-2-36183269ade8@tessares.net>
References: <20230811-upstream-net-next-20230811-mptcp-get-rid-of-msk-subflow-v1-0-36183269ade8@tessares.net>
In-Reply-To: <20230811-upstream-net-next-20230811-mptcp-get-rid-of-msk-subflow-v1-0-36183269ade8@tessares.net>
To:     mptcp@lists.linux.dev, Mat Martineau <martineau@kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        David Ahern <dsahern@kernel.org>
Cc:     netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
        Matthieu Baerts <matthieu.baerts@tessares.net>
Precedence: bulk

From: Paolo Abeni <pabeni@redhat.com>

The mptcp protocol maintains an additional socket just to easily
invoke a few stream operations on the first subflow. One of them is
__inet_stream_connect().

We are going to remove the first subflow socket soon, so avoid
the additional indirection via at connect time, calling directly
into the sock-level connect() ops.

The sk-level connect never return -EINPROGRESS, cleanup the error
path accordingly. Additionally, the ssk status on error is always
TCP_CLOSE. Avoid unneeded access to the subflow sk state.

No functional change intended.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
---
 net/mptcp/protocol.c | 49 +++++++++++++++++++++++++++++++++----------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index abb310548c37..b888d6339c80 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3589,22 +3589,24 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct socket *ssock;
 	int err = -EINVAL;
+	struct sock *ssk;
 
 	ssock = __mptcp_nmpc_socket(msk);
 	if (IS_ERR(ssock))
 		return PTR_ERR(ssock);
 
 	inet_sk_state_store(sk, TCP_SYN_SENT);
-	subflow = mptcp_subflow_ctx(ssock->sk);
+	ssk = msk->first;
+	subflow = mptcp_subflow_ctx(ssk);
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
 	 * TCP option space.
 	 */
-	if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
+	if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info))
 		mptcp_subflow_early_fallback(msk, subflow);
 #endif
-	if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) {
-		MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT);
+	if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT);
 		mptcp_subflow_early_fallback(msk, subflow);
 	}
 	if (likely(!__mptcp_check_fallback(msk)))
@@ -3613,27 +3615,42 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	/* if reaching here via the fastopen/sendmsg path, the caller already
 	 * acquired the subflow socket lock, too.
 	 */
-	if (msk->fastopening)
-		err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1);
-	else
-		err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK);
-	inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
+	if (!msk->fastopening)
+		lock_sock(ssk);
+
+	/* the following mirrors closely a very small chunk of code from
+	 * __inet_stream_connect()
+	 */
+	if (ssk->sk_state != TCP_CLOSE)
+		goto out;
+
+	if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) {
+		err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len);
+		if (err)
+			goto out;
+	}
+
+	err = ssk->sk_prot->connect(ssk, uaddr, addr_len);
+	if (err < 0)
+		goto out;
+
+	inet_sk(sk)->defer_connect = inet_sk(ssk)->defer_connect;
+
+out:
+	if (!msk->fastopening)
+		release_sock(ssk);
 
 	/* on successful connect, the msk state will be moved to established by
 	 * subflow_finish_connect()
 	 */
-	if (unlikely(err && err != -EINPROGRESS)) {
+	if (unlikely(err)) {
 		/* avoid leaving a dangling token in an unconnected socket */
 		mptcp_token_destroy(msk);
-		inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
+		inet_sk_state_store(sk, TCP_CLOSE);
 		return err;
 	}
 
-	mptcp_copy_inaddrs(sk, ssock->sk);
-
-	/* silence EINPROGRESS and let the caller inet_stream_connect
-	 * handle the connection in progress
-	 */
+	mptcp_copy_inaddrs(sk, ssk);
 	return 0;
 }
 

-- 
2.40.1