tcp: add tcp_sock_set_keepcnt

Add a helper to directly set the TCP_KEEPCNT sockopt from kernel space
without going through a fake uaccess.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 		  int shiftlen);
 
 void tcp_sock_set_cork(struct sock *sk, bool on);
+int tcp_sock_set_keepcnt(struct sock *sk, int val);
 int tcp_sock_set_keepidle(struct sock *sk, int val);
 int tcp_sock_set_keepintvl(struct sock *sk, int val);
 void tcp_sock_set_nodelay(struct sock *sk);

net/ipv4/tcp.c

@@ -2946,6 +2946,18 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_keepintvl);
 
+int tcp_sock_set_keepcnt(struct sock *sk, int val)
+{
+	if (val < 1 || val > MAX_TCP_KEEPCNT)
+		return -EINVAL;
+
+	lock_sock(sk);
+	tcp_sk(sk)->keepalive_probes = val;
+	release_sock(sk);
+	return 0;
+}
+EXPORT_SYMBOL(tcp_sock_set_keepcnt);
+
 /*
  *	Socket option code for TCP.
  */

net/rds/tcp.h

@@ -70,7 +70,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6);
 void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
 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_keepalive(struct socket *sock);
 void *rds_tcp_listen_sock_def_readable(struct net *net);
 
 /* tcp_recv.c */

net/rds/tcp_listen.c

@@ -38,27 +38,19 @@
 #include "rds.h"
 #include "tcp.h"
 
-int rds_tcp_keepalive(struct socket *sock)
+void rds_tcp_keepalive(struct socket *sock)
 {
 	/* values below based on xs_udp_default_timeout */
 	int keepidle = 5; /* send a probe 'keepidle' secs after last data */
 	int keepcnt = 5; /* number of unack'ed probes before declaring dead */
-	int ret = 0;
 
 	sock_set_keepalive(sock->sk);
-
+	tcp_sock_set_keepcnt(sock->sk, keepcnt);
-	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT,
-				(char *)&keepcnt, sizeof(keepcnt));
-	if (ret < 0)
-		goto bail;
-
 	tcp_sock_set_keepidle(sock->sk, keepidle);
 	/* KEEPINTVL is the interval between successive probes. We follow
 	 * the model in xs_tcp_finish_connecting() and re-use keepidle.
 	 */
 	tcp_sock_set_keepintvl(sock->sk, keepidle);
-bail:
-	return ret;
 }
 
 /* rds_tcp_accept_one_path(): if accepting on cp_index > 0, make sure the
@@ -140,10 +132,7 @@ int rds_tcp_accept_one(struct socket *sock)
 	new_sock->ops = sock->ops;
 	__module_get(new_sock->ops->owner);
 
-	ret = rds_tcp_keepalive(new_sock);
+	rds_tcp_keepalive(new_sock);
-	if (ret < 0)
-		goto out;
-
 	rds_tcp_tune(new_sock);
 
 	inet = inet_sk(new_sock->sk);

net/sunrpc/xprtsock.c

@@ -2109,8 +2109,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 	sock_set_keepalive(sock->sk);
 	tcp_sock_set_keepidle(sock->sk, keepidle);
 	tcp_sock_set_keepintvl(sock->sk, keepidle);
-	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
+	tcp_sock_set_keepcnt(sock->sk, keepcnt);
-			(char *)&keepcnt, sizeof(keepcnt));
 
 	/* TCP user timeout (see RFC5482) */
 	tcp_sock_set_user_timeout(sock->sk, timeo);