net: add sock_no_linger

Add a helper to directly set the SO_LINGER sockopt from kernel space
with onoff set to true and a linger time of 0 without going through a
fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 16 insertions, 37 deletions

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index c15a92163c1f..e72d87482eb7 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1313,7 +1313,6 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
-	struct linger sol = { .l_onoff = 1, .l_linger = 0 };
 	int ret, opt, rcv_pdu_size;
 
 	queue->ctrl = ctrl;
@@ -1361,13 +1360,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	 * close. This is done to prevent stale data from being sent should
 	 * the network connection be restored before TCP times out.
 	 */
-	ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_LINGER,
-			(char *)&sol, sizeof(sol));
-	if (ret) {
-		dev_err(nctrl->device,
-			"failed to set SO_LINGER sock opt %d\n", ret);
-		goto err_sock;
-	}
+	sock_no_linger(queue->sock->sk);
 
 	if (so_priority > 0) {
 		ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_PRIORITY,
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 40757a63f455..e0801494b097 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1429,7 +1429,6 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 {
 	struct socket *sock = queue->sock;
 	struct inet_sock *inet = inet_sk(sock->sk);
-	struct linger sol = { .l_onoff = 1, .l_linger = 0 };
 	int ret;
 
 	ret = kernel_getsockname(sock,
@@ -1447,10 +1446,7 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
 	 * close. This is done to prevent stale data from being sent should
 	 * the network connection be restored before TCP times out.
 	 */
-	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
-			(char *)&sol, sizeof(sol));
-	if (ret)
-		return ret;
+	sock_no_linger(sock->sk);
 
 	if (so_priority > 0) {
 		ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
diff --git a/include/net/sock.h b/include/net/sock.h
index 2ec085044790..6ed00bf009bb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2688,6 +2688,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
 
 void sock_def_readable(struct sock *sk);
 
+void sock_no_linger(struct sock *sk);
 void sock_set_reuseaddr(struct sock *sk);
 
 #endif	/* _SOCK_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 18eb84fdf5fb..f0f09524911c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -720,6 +720,15 @@ void sock_set_reuseaddr(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_set_reuseaddr);
 
+void sock_no_linger(struct sock *sk)
+{
+	lock_sock(sk);
+	sk->sk_lingertime = 0;
+	sock_set_flag(sk, SOCK_LINGER);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_no_linger);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 3c69361d21c7..d640e210b97b 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -73,7 +73,6 @@ void rds_tcp_listen_data_ready(struct sock *sk);
 int rds_tcp_accept_one(struct socket *sock);
 int rds_tcp_keepalive(struct socket *sock);
 void *rds_tcp_listen_sock_def_readable(struct net *net);
-void rds_tcp_set_linger(struct socket *sock);
 
 /* tcp_recv.c */
 int rds_tcp_recv_init(void);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 008f50fb25dd..4e64598176b0 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -207,7 +207,7 @@ void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp)
 
 	if (sock) {
 		if (rds_destroy_pending(cp->cp_conn))
-			rds_tcp_set_linger(sock);
+			sock_no_linger(sock->sk);
 		sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN);
 		lock_sock(sock->sk);
 		rds_tcp_restore_callbacks(sock, tc); /* tc->tc_sock = NULL */
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 810a3a49e947..bbb31b9c0b39 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -111,17 +111,6 @@ struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
 	return NULL;
 }
 
-void rds_tcp_set_linger(struct socket *sock)
-{
-	struct linger no_linger = {
-		.l_onoff = 1,
-		.l_linger = 0,
-	};
-
-	kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
-			  (char *)&no_linger, sizeof(no_linger));
-}
-
 int rds_tcp_accept_one(struct socket *sock)
 {
 	struct socket *new_sock = NULL;
@@ -241,7 +230,7 @@ rst_nsk:
 	 * be pending on it. By setting linger, we achieve the side-effect
 	 * of avoiding TIME_WAIT state on new_sock.
 	 */
-	rds_tcp_set_linger(new_sock);
+	sock_no_linger(new_sock->sk);
 	kernel_sock_shutdown(new_sock, SHUT_RDWR);
 	ret = 0;
 out:
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 023514e392b3..6773dacc64d8 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -323,17 +323,9 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 
 static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
 {
-	struct svc_sock *svsk;
-	struct socket *sock;
-	struct linger no_linger = {
-		.l_onoff = 1,
-		.l_linger = 0,
-	};
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 
-	svsk = container_of(xprt, struct svc_sock, sk_xprt);
-	sock = svsk->sk_sock;
-	kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
-			  (char *)&no_linger, sizeof(no_linger));
+	sock_no_linger(svsk->sk_sock->sk);
 }
 
 /*