[PATCH 07/11] nvme-tcp: define host tcp_proto struct

[Geliang Tang]

From: Geliang Tang <tanggeliang at kylinos.cn>

To add MPTCP support in "NVMe over TCP", the host side needs to pass
IPPROTO_MPTCP to sock_create_kern() instead of IPPROTO_TCP to create an
MPTCP socket.

Similar to the target-side nvmet_tcp_proto, this patch defines the
host-side nvme_tcp_proto structure, which contains the protocol of the
socket and a set of function pointers for socket operations. The only
difference is that it defines .set_syncnt instead of .set_reuseaddr.

A TCP-specific version of this structure is defined, and a proto field is
added to nvme_tcp_ctrl. When the transport string is "tcp", it is assigned
to ctrl->proto.

All locations that previously called TCP setsockopt functions are updated
to call the corresponding function pointers in the nvme_tcp_proto
structure. The controller's proto pointer is set during initialization and
remains valid throughout the controller's lifetime.

v2:
 - use 'trtype' instead of '--mptcp' (Hannes)

v3:
 - check mptcp protocol from opts->transport instead of passing a
parameter (Hannes).

v4:
 - check CONFIG_MPTCP.

v5:
 - define nvme_tcp_proto struct.
 - add a pointer to this structure in nvme_tcp_ctrl.

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/host/tcp.c | 44 ++++++++++++++++++++++++++++++++++-------
 1 file changed, 37 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 15d36d6a728e..13a5240623ef 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -182,6 +182,16 @@ struct nvme_tcp_queue {
 	void (*write_space)(struct sock *);
 };
 
+struct nvme_tcp_proto {
+	int			protocol;
+	int (*set_syncnt)(struct sock *sk, int val);
+	void (*set_nodelay)(struct sock *sk);
+	void (*no_linger)(struct sock *sk);
+	void (*set_priority)(struct sock *sk, u32 priority);
+	void (*set_tos)(struct sock *sk, int val);
+	const struct nvme_ctrl_ops *ops;
+};
+
 struct nvme_tcp_ctrl {
 	/* read only in the hot path */
 	struct nvme_tcp_queue	*queues;
@@ -198,6 +208,8 @@ struct nvme_tcp_ctrl {
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
 	u32			io_queues[HCTX_MAX_TYPES];
+
+	const struct nvme_tcp_proto *proto;
 };
 
 static LIST_HEAD(nvme_tcp_ctrl_list);
@@ -1799,7 +1811,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 
 	ret = sock_create_kern(current->nsproxy->net_ns,
 			ctrl->addr.ss_family, SOCK_STREAM,
-			IPPROTO_TCP, &queue->sock);
+			ctrl->proto->protocol, &queue->sock);
 	if (ret) {
 		dev_err(nctrl->device,
 			"failed to create socket: %d\n", ret);
@@ -1816,24 +1828,24 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 	nvme_tcp_reclassify_socket(queue->sock);
 
 	/* Single syn retry */
-	tcp_sock_set_syncnt(queue->sock->sk, 1);
+	ctrl->proto->set_syncnt(queue->sock->sk, 1);
 
 	/* Set TCP no delay */
-	tcp_sock_set_nodelay(queue->sock->sk);
+	ctrl->proto->set_nodelay(queue->sock->sk);
 
 	/*
 	 * Cleanup whatever is sitting in the TCP transmit queue on socket
 	 * close. This is done to prevent stale data from being sent should
 	 * the network connection be restored before TCP times out.
 	 */
-	sock_no_linger(queue->sock->sk);
+	ctrl->proto->no_linger(queue->sock->sk);
 
 	if (so_priority > 0)
-		sock_set_priority(queue->sock->sk, so_priority);
+		ctrl->proto->set_priority(queue->sock->sk, so_priority);
 
 	/* Set socket type of service */
 	if (nctrl->opts->tos >= 0)
-		ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos);
+		ctrl->proto->set_tos(queue->sock->sk, nctrl->opts->tos);
 
 	/* Set 10 seconds timeout for icresp recvmsg */
 	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
@@ -2900,6 +2912,17 @@ nvme_tcp_existing_controller(struct nvmf_ctrl_options *opts)
 	return found;
 }
 
+static const struct nvme_tcp_proto nvme_tcp_proto = {
+	.protocol	= IPPROTO_TCP,
+	.set_syncnt	= tcp_sock_set_syncnt,
+	.set_nodelay	= tcp_sock_set_nodelay,
+	.no_linger	= sock_no_linger,
+	.set_priority	= sock_set_priority,
+	.set_tos	= ip_sock_set_tos,
+	.ops		= &nvme_tcp_ctrl_ops,
+
+};
+
 static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
@@ -2964,13 +2987,20 @@ static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
 		goto out_free_ctrl;
 	}
 
+	if (!strcmp(ctrl->ctrl.opts->transport, "tcp")) {
+		ctrl->proto = &nvme_tcp_proto;
+	} else {
+		ret = -EINVAL;
+		goto out_free_ctrl;
+	}
+
 	ctrl->queues = kzalloc_objs(*ctrl->queues, ctrl->ctrl.queue_count);
 	if (!ctrl->queues) {
 		ret = -ENOMEM;
 		goto out_free_ctrl;
 	}
 
-	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_tcp_ctrl_ops, 0);
+	ret = nvme_init_ctrl(&ctrl->ctrl, dev, ctrl->proto->ops, 0);
 	if (ret)
 		goto out_kfree_queues;
 
-- 
2.53.0