tcp: add tcp_sock_set_keepidle

Add a helper to directly set the TCP_KEEP_IDLE 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>

4 files changed, 37 insertions, 21 deletions

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index de682143efe4..5724dd84a85e 100644
--- a/include/linux/tcp.h
+++ b/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_keepidle(struct sock *sk, int val);
 void tcp_sock_set_nodelay(struct sock *sk);
 void tcp_sock_set_quickack(struct sock *sk, int val);
 int tcp_sock_set_syncnt(struct sock *sk, int val);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0004bd9ae7b0..bdf0ff933351 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2901,6 +2901,39 @@ void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
 }
 EXPORT_SYMBOL(tcp_sock_set_user_timeout);
 
+static int __tcp_sock_set_keepidle(struct sock *sk, int val)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (val < 1 || val > MAX_TCP_KEEPIDLE)
+		return -EINVAL;
+
+	tp->keepalive_time = val * HZ;
+	if (sock_flag(sk, SOCK_KEEPOPEN) &&
+	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
+		u32 elapsed = keepalive_time_elapsed(tp);
+
+		if (tp->keepalive_time > elapsed)
+			elapsed = tp->keepalive_time - elapsed;
+		else
+			elapsed = 0;
+		inet_csk_reset_keepalive_timer(sk, elapsed);
+	}
+
+	return 0;
+}
+
+int tcp_sock_set_keepidle(struct sock *sk, int val)
+{
+	int err;
+
+	lock_sock(sk);
+	err = __tcp_sock_set_keepidle(sk, val);
+	release_sock(sk);
+	return err;
+}
+EXPORT_SYMBOL(tcp_sock_set_keepidle);
+
 /*
  *	Socket option code for TCP.
  */
@@ -3070,21 +3103,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_KEEPIDLE:
-		if (val < 1 || val > MAX_TCP_KEEPIDLE)
-			err = -EINVAL;
-		else {
-			tp->keepalive_time = val * HZ;
-			if (sock_flag(sk, SOCK_KEEPOPEN) &&
-			    !((1 << sk->sk_state) &
-			      (TCPF_CLOSE | TCPF_LISTEN))) {
-				u32 elapsed = keepalive_time_elapsed(tp);
-				if (tp->keepalive_time > elapsed)
-					elapsed = tp->keepalive_time - elapsed;
-				else
-					elapsed = 0;
-				inet_csk_reset_keepalive_timer(sk, elapsed);
-			}
-		}
+		err = __tcp_sock_set_keepidle(sk, val);
 		break;
 	case TCP_KEEPINTVL:
 		if (val < 1 || val > MAX_TCP_KEEPINTVL)
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 6f90ea077adc..79f9adc00811 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -52,10 +52,7 @@ int rds_tcp_keepalive(struct socket *sock)
 	if (ret < 0)
 		goto bail;
 
-	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPIDLE,
-				(char *)&keepidle, sizeof(keepidle));
-	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.
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 231fd6162f68..473290f7c5c0 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2107,8 +2107,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 
 	/* TCP Keepalive options */
 	sock_set_keepalive(sock->sk);
-	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
-			(char *)&keepidle, sizeof(keepidle));
+	tcp_sock_set_keepidle(sock->sk, keepidle);
 	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
 			(char *)&keepidle, sizeof(keepidle));
 	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,