[PATCH 02/11] nvmet-tcp: implement accept mptcp proto

[Geliang Tang]

From: Geliang Tang <tanggeliang at kylinos.cn>

An MPTCP-specific version of struct nvmet_tcp_proto is implemented for
accept sockets. It is assigned to queue->proto when the accepted socket
protocol is IPPROTO_MPTCP.

Dedicated MPTCP helpers are introduced for setting accept socket options.
These helpers (no_linger, set_priority, set_tos) set the values on all
existing subflows using mptcp_for_each_subflow(). The values are then
synchronized to other newly created subflows in sync_socket_options().

Cc: Hannes Reinecke <hare at suse.de>
Cc: John Meneghini <jmeneghi at redhat.com>
Cc: Randy Jennings <randyj at purestorage.com>
Cc: Nilay Shroff <nilay at linux.ibm.com>
Co-developed-by: zhenwei pi <zhenwei.pi at linux.dev>
Signed-off-by: zhenwei pi <zhenwei.pi at linux.dev>
Co-developed-by: Hui Zhu <zhuhui at kylinos.cn>
Signed-off-by: Hui Zhu <zhuhui at kylinos.cn>
Co-developed-by: Gang Yan <yangang at kylinos.cn>
Signed-off-by: Gang Yan <yangang at kylinos.cn>
Signed-off-by: Geliang Tang <tanggeliang at kylinos.cn>
---
 drivers/nvme/target/tcp.c | 16 ++++++++
 include/net/mptcp.h       | 12 ++++++
 net/mptcp/sockopt.c       | 79 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 107 insertions(+)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 01c23fb15b79..16f153a9772b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -220,6 +220,9 @@ static DEFINE_MUTEX(nvmet_tcp_queue_mutex);
 
 static struct workqueue_struct *nvmet_tcp_wq;
 static const struct nvmet_fabrics_ops nvmet_tcp_ops;
+#ifdef CONFIG_MPTCP
+static const struct nvmet_fabrics_ops nvmet_mptcp_ops;
+#endif
 static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c);
 static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd);
 
@@ -1928,6 +1931,15 @@ static const struct nvmet_tcp_proto nvmet_tcp_proto = {
 	.ops		= &nvmet_tcp_ops,
 };
 
+#ifdef CONFIG_MPTCP
+static const struct nvmet_tcp_proto nvmet_mptcp_proto = {
+	.no_linger	= mptcp_sock_no_linger,
+	.set_priority	= mptcp_sock_set_priority,
+	.set_tos	= mptcp_sock_set_tos,
+	.ops		= &nvmet_mptcp_ops,
+};
+#endif
+
 static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 		struct socket *newsock)
 {
@@ -1947,6 +1959,10 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	queue->sock = newsock;
 	if (newsock->sk->sk_protocol == IPPROTO_TCP) {
 		queue->proto = &nvmet_tcp_proto;
+#ifdef CONFIG_MPTCP
+	} else if (newsock->sk->sk_protocol == IPPROTO_MPTCP) {
+		queue->proto = &nvmet_mptcp_proto;
+#endif
 	} else {
 		ret = -EINVAL;
 		goto out_free_queue;
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index aef2dbeb847b..bf74dedc578d 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -233,6 +233,12 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
 }
 
 void mptcp_active_detect_blackhole(struct sock *sk, bool expired);
+
+void mptcp_sock_no_linger(struct sock *sk);
+
+void mptcp_sock_set_priority(struct sock *sk, u32 priority);
+
+void mptcp_sock_set_tos(struct sock *sk);
 #else
 
 static inline void mptcp_init(void)
@@ -319,6 +325,12 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct reques
 static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
 
 static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { }
+
+static inline void mptcp_sock_no_linger(struct sock *sk) { }
+
+static inline void mptcp_sock_set_priority(struct sock *sk, u32 priority) { }
+
+static inline void mptcp_sock_set_tos(struct sock *sk) { }
 #endif /* CONFIG_MPTCP */
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 87b5796d0135..359b1eb2d0a9 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1662,3 +1662,82 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 	}
 	return 0;
 }
+
+void mptcp_sock_no_linger(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct sock *ssk;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	WRITE_ONCE(sk->sk_lingertime, 0);
+	sock_set_flag(sk, SOCK_LINGER);
+	mptcp_for_each_subflow(msk, subflow) {
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		if (ssk) {
+			lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+			WRITE_ONCE(ssk->sk_lingertime, 0);
+			sock_set_flag(ssk, SOCK_LINGER);
+			release_sock(ssk);
+		}
+	}
+	release_sock(sk);
+}
+EXPORT_SYMBOL(mptcp_sock_no_linger);
+
+void mptcp_sock_set_priority(struct sock *sk, u32 priority)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct sock *ssk;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	sock_set_priority(sk, priority);
+	mptcp_for_each_subflow(msk, subflow) {
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		if (ssk) {
+			lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+			sock_set_priority(ssk, priority);
+			release_sock(ssk);
+		}
+	}
+	release_sock(sk);
+}
+EXPORT_SYMBOL(mptcp_sock_set_priority);
+
+static void __mptcp_sock_set_tos(struct sock *sk, int val)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_subflow_context *subflow;
+	struct sock *ssk;
+
+	lock_sock(sk);
+	sockopt_seq_inc(msk);
+	__ip_sock_set_tos(sk, val);
+	mptcp_for_each_subflow(msk, subflow) {
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		if (ssk) {
+			lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+			__ip_sock_set_tos(ssk, val);
+			release_sock(ssk);
+		}
+	}
+	release_sock(sk);
+}
+
+void mptcp_sock_set_tos(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	int val = 0;
+
+	lock_sock(sk);
+	if (msk->first)
+		val = inet_sk(msk->first)->rcv_tos;
+	release_sock(sk);
+
+	if (val > 0)
+		__mptcp_sock_set_tos(sk, val);
+}
+EXPORT_SYMBOL(mptcp_sock_set_tos);
-- 
2.53.0