From db10538a4b997a77a1fd561adaaa58afc7dcfa2f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:18 +0200
Subject: tcp: add tcp_sock_set_cork

Add a helper to directly set the TCP_CORK sockopt from kernel space
without going through a fake uaccess.  Cleanup the callers to avoid
pointless wrappers now that this is a simple function call.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index bf44e85d709d..889eeb2256c2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -497,4 +497,6 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
 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);
+
 #endif	/* _LINUX_TCP_H */
-- 
cgit v1.3-6-gb490


From 12abc5ee7873a085cc280240822b8ac53c86fecd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:19 +0200
Subject: tcp: add tcp_sock_set_nodelay

Add a helper to directly set the TCP_NODELAY sockopt from kernel space
without going through a fake uaccess.  Cleanup the callers to avoid
pointless wrappers now that this is a simple function call.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_int.h             |  7 ------
 drivers/block/drbd/drbd_main.c            |  2 +-
 drivers/block/drbd/drbd_receiver.c        |  4 ++--
 drivers/infiniband/sw/siw/siw_cm.c        | 24 ++++---------------
 drivers/nvme/host/tcp.c                   |  9 +------
 drivers/nvme/target/tcp.c                 | 12 ++--------
 drivers/target/iscsi/iscsi_target_login.c | 15 +++---------
 fs/cifs/connect.c                         | 10 ++------
 fs/dlm/lowcomms.c                         |  8 ++-----
 fs/ocfs2/cluster/tcp.c                    | 20 ++--------------
 include/linux/tcp.h                       |  1 +
 net/ceph/messenger.c                      | 11 ++-------
 net/ipv4/tcp.c                            | 39 ++++++++++++++++++++-----------
 net/rds/tcp.c                             | 11 +--------
 net/rds/tcp.h                             |  1 -
 net/rds/tcp_listen.c                      |  2 +-
 16 files changed, 49 insertions(+), 127 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 3550adc93c68..e24bba87c8e0 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1570,13 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-static inline void drbd_tcp_nodelay(struct socket *sock)
-{
-	int val = 1;
-	(void) kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-			(char*)&val, sizeof(val));
-}
-
 static inline void drbd_tcp_quickack(struct socket *sock)
 {
 	int val = 2;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index c094c3c2c5d4..45fbd526c453 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -660,7 +660,7 @@ static int __send_command(struct drbd_connection *connection, int vnr,
 	/* DRBD protocol "pings" are latency critical.
 	 * This is supposed to trigger tcp_push_pending_frames() */
 	if (!err && (cmd == P_PING || cmd == P_PING_ACK))
-		drbd_tcp_nodelay(sock->socket);
+		tcp_sock_set_nodelay(sock->socket->sk);
 
 	return err;
 }
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 55ea907ad33c..20a5e94494ac 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1051,8 +1051,8 @@ randomize:
 
 	/* we don't want delays.
 	 * we use TCP_CORK where appropriate, though */
-	drbd_tcp_nodelay(sock.socket);
-	drbd_tcp_nodelay(msock.socket);
+	tcp_sock_set_nodelay(sock.socket->sk);
+	tcp_sock_set_nodelay(msock.socket->sk);
 
 	connection->data.socket = sock.socket;
 	connection->meta.socket = msock.socket;
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index d1860f3e8740..1662216be66d 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -947,16 +947,8 @@ static void siw_accept_newconn(struct siw_cep *cep)
 	siw_cep_get(new_cep);
 	new_s->sk->sk_user_data = new_cep;
 
-	if (siw_tcp_nagle == false) {
-		int val = 1;
-
-		rv = kernel_setsockopt(new_s, SOL_TCP, TCP_NODELAY,
-				       (char *)&val, sizeof(val));
-		if (rv) {
-			siw_dbg_cep(cep, "setsockopt NODELAY error: %d\n", rv);
-			goto error;
-		}
-	}
+	if (siw_tcp_nagle == false)
+		tcp_sock_set_nodelay(new_s->sk);
 	new_cep->state = SIW_EPSTATE_AWAIT_MPAREQ;
 
 	rv = siw_cm_queue_work(new_cep, SIW_CM_WORK_MPATIMEOUT);
@@ -1386,16 +1378,8 @@ int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *params)
 		siw_dbg_qp(qp, "kernel_bindconnect: error %d\n", rv);
 		goto error;
 	}
-	if (siw_tcp_nagle == false) {
-		int val = 1;
-
-		rv = kernel_setsockopt(s, SOL_TCP, TCP_NODELAY, (char *)&val,
-				       sizeof(val));
-		if (rv) {
-			siw_dbg_qp(qp, "setsockopt NODELAY error: %d\n", rv);
-			goto error;
-		}
-	}
+	if (siw_tcp_nagle == false)
+		tcp_sock_set_nodelay(s->sk);
 	cep = siw_cep_alloc(sdev);
 	if (!cep) {
 		rv = -ENOMEM;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a307972d33a0..4e4a750ecdb9 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1346,14 +1346,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	}
 
 	/* Set TCP no delay */
-	opt = 1;
-	ret = kernel_setsockopt(queue->sock, IPPROTO_TCP,
-			TCP_NODELAY, (char *)&opt, sizeof(opt));
-	if (ret) {
-		dev_err(nctrl->device,
-			"failed to set TCP_NODELAY sock opt %d\n", ret);
-		goto err_sock;
-	}
+	tcp_sock_set_nodelay(queue->sock->sk);
 
 	/*
 	 * Cleanup whatever is sitting in the TCP transmit queue on socket
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f3088156d01d..55bc4c3c0a74 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1580,7 +1580,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 {
 	struct nvmet_tcp_port *port;
 	__kernel_sa_family_t af;
-	int opt, ret;
+	int ret;
 
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	if (!port)
@@ -1625,15 +1625,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	port->data_ready = port->sock->sk->sk_data_ready;
 	port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;
 	sock_set_reuseaddr(port->sock->sk);
-
-	opt = 1;
-	ret = kernel_setsockopt(port->sock, IPPROTO_TCP,
-			TCP_NODELAY, (char *)&opt, sizeof(opt));
-	if (ret) {
-		pr_err("failed to set TCP_NODELAY sock opt %d\n", ret);
-		goto err_sock;
-	}
-
+	tcp_sock_set_nodelay(port->sock->sk);
 	if (so_priority > 0)
 		sock_set_priority(port->sock->sk, so_priority);
 
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 91acb3f07b4c..b561b07a869a 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -897,20 +897,11 @@ int iscsit_setup_np(
 	/*
 	 * Set SO_REUSEADDR, and disable Nagel Algorithm with TCP_NODELAY.
 	 */
-	/* FIXME: Someone please explain why this is endian-safe */
-	opt = 1;
-	if (np->np_network_transport == ISCSI_TCP) {
-		ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_NODELAY,
-				(char *)&opt, sizeof(opt));
-		if (ret < 0) {
-			pr_err("kernel_setsockopt() for TCP_NODELAY"
-				" failed: %d\n", ret);
-			goto fail;
-		}
-	}
-
+	if (np->np_network_transport == ISCSI_TCP)
+		tcp_sock_set_nodelay(sock->sk);
 	sock_set_reuseaddr(sock->sk);
 
+	opt = 1;
 	ret = kernel_setsockopt(sock, IPPROTO_IP, IP_FREEBIND,
 			(char *)&opt, sizeof(opt));
 	if (ret < 0) {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 28268ed461b8..ad8fb53b3682 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3929,14 +3929,8 @@ generic_ip_connect(struct TCP_Server_Info *server)
 			socket->sk->sk_rcvbuf = 140 * 1024;
 	}
 
-	if (server->tcp_nodelay) {
-		int val = 1;
-		rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
-				(char *)&val, sizeof(val));
-		if (rc)
-			cifs_dbg(FYI, "set TCP_NODELAY socket option error %d\n",
-				 rc);
-	}
+	if (server->tcp_nodelay)
+		tcp_sock_set_nodelay(socket->sk);
 
 	cifs_dbg(FYI, "sndbuf %d rcvbuf %d rcvtimeo 0x%lx\n",
 		 socket->sk->sk_sndbuf,
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 2822a430a2b4..69333728d871 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1011,7 +1011,6 @@ static void tcp_connect_to_sock(struct connection *con)
 	struct sockaddr_storage saddr, src_addr;
 	int addr_len;
 	struct socket *sock = NULL;
-	int one = 1;
 	int result;
 
 	if (con->nodeid == 0) {
@@ -1060,8 +1059,7 @@ static void tcp_connect_to_sock(struct connection *con)
 	log_print("connecting to %d", con->nodeid);
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
-			  sizeof(one));
+	tcp_sock_set_nodelay(sock->sk);
 
 	result = sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
 				   O_NONBLOCK);
@@ -1103,7 +1101,6 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 {
 	struct socket *sock = NULL;
 	int result = 0;
-	int one = 1;
 	int addr_len;
 
 	if (dlm_local_addr[0]->ss_family == AF_INET)
@@ -1120,8 +1117,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	}
 
 	/* Turn off Nagle's algorithm */
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
-			  sizeof(one));
+	tcp_sock_set_nodelay(sock->sk);
 
 	sock_set_reuseaddr(sock->sk);
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2c512b40a940..4c70fe9d19ab 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static int o2net_set_nodelay(struct socket *sock)
-{
-	int val = 1;
-
-	return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-				    (void *)&val, sizeof(val));
-}
-
 static int o2net_set_usertimeout(struct socket *sock)
 {
 	int user_timeout = O2NET_TCP_USER_TIMEOUT;
@@ -1636,11 +1628,7 @@ static void o2net_start_connect(struct work_struct *work)
 		goto out;
 	}
 
-	ret = o2net_set_nodelay(sc->sc_sock);
-	if (ret) {
-		mlog(ML_ERROR, "setting TCP_NODELAY failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_nodelay(sc->sc_sock->sk);
 
 	ret = o2net_set_usertimeout(sock);
 	if (ret) {
@@ -1832,11 +1820,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	*more = 1;
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
-	ret = o2net_set_nodelay(new_sock);
-	if (ret) {
-		mlog(ML_ERROR, "setting TCP_NODELAY failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_nodelay(new_sock->sk);
 
 	ret = o2net_set_usertimeout(new_sock);
 	if (ret) {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 889eeb2256c2..9e42c7fe50a8 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -498,5 +498,6 @@ 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);
+void tcp_sock_set_nodelay(struct sock *sk);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index f8ca5edc5f2c..27d6ab11f9ee 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -490,15 +490,8 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 
-	if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY)) {
-		int optval = 1;
-
-		ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
-					(char *)&optval, sizeof(optval));
-		if (ret)
-			pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d",
-			       ret);
-	}
+	if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY))
+		tcp_sock_set_nodelay(sock->sk);
 
 	con->sock = sock;
 	return 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e6cf702e16d6..a65f293a19fa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2832,6 +2832,30 @@ void tcp_sock_set_cork(struct sock *sk, bool on)
 }
 EXPORT_SYMBOL(tcp_sock_set_cork);
 
+/* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is
+ * remembered, but it is not activated until cork is cleared.
+ *
+ * However, when TCP_NODELAY is set we make an explicit push, which overrides
+ * even TCP_CORK for currently queued segments.
+ */
+static void __tcp_sock_set_nodelay(struct sock *sk, bool on)
+{
+	if (on) {
+		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
+		tcp_push_pending_frames(sk);
+	} else {
+		tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF;
+	}
+}
+
+void tcp_sock_set_nodelay(struct sock *sk)
+{
+	lock_sock(sk);
+	__tcp_sock_set_nodelay(sk, true);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_nodelay);
+
 /*
  *	Socket option code for TCP.
  */
@@ -2929,20 +2953,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_NODELAY:
-		if (val) {
-			/* TCP_NODELAY is weaker than TCP_CORK, so that
-			 * this option on corked socket is remembered, but
-			 * it is not activated until cork is cleared.
-			 *
-			 * However, when TCP_NODELAY is set we make
-			 * an explicit push, which overrides even TCP_CORK
-			 * for currently queued segments.
-			 */
-			tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
-			tcp_push_pending_frames(sk);
-		} else {
-			tp->nonagle &= ~TCP_NAGLE_OFF;
-		}
+		__tcp_sock_set_nodelay(sk, val);
 		break;
 
 	case TCP_THIN_LINEAR_TIMEOUTS:
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 46782fac4c16..43db0eca911f 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -89,15 +89,6 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 	{ }
 };
 
-/* doing it this way avoids calling tcp_sk() */
-void rds_tcp_nonagle(struct socket *sock)
-{
-	int val = 1;
-
-	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val,
-			      sizeof(val));
-}
-
 u32 rds_tcp_write_seq(struct rds_tcp_connection *tc)
 {
 	/* seq# of the last byte of data in tcp send buffer */
@@ -502,7 +493,7 @@ void rds_tcp_tune(struct socket *sock)
 	struct net *net = sock_net(sk);
 	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
 
-	rds_tcp_nonagle(sock);
+	tcp_sock_set_nodelay(sock->sk);
 	lock_sock(sk);
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index d640e210b97b..f6d75d8cb167 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -50,7 +50,6 @@ struct rds_tcp_statistics {
 
 /* tcp.c */
 void rds_tcp_tune(struct socket *sock);
-void rds_tcp_nonagle(struct socket *sock);
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp);
 void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp);
 void rds_tcp_restore_callbacks(struct socket *sock,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index d8bd13276959..6f90ea077adc 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -288,7 +288,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6)
 	}
 
 	sock->sk->sk_reuse = SK_CAN_REUSE;
-	rds_tcp_nonagle(sock);
+	tcp_sock_set_nodelay(sock->sk);
 
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_user_data = sock->sk->sk_data_ready;
-- 
cgit v1.3-6-gb490


From ddd061b8daed3ce0c01109a69c9a2a9f9669f01a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:20 +0200
Subject: tcp: add tcp_sock_set_quickack

Add a helper to directly set the TCP_QUICKACK sockopt from kernel space
without going through a fake uaccess.  Cleanup the callers to avoid
pointless wrappers now that this is a simple function call.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_int.h      |  7 -------
 drivers/block/drbd/drbd_receiver.c |  5 ++---
 include/linux/tcp.h                |  1 +
 net/ipv4/tcp.c                     | 39 +++++++++++++++++++++++++-------------
 4 files changed, 29 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index e24bba87c8e0..14345a87c7cc 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1570,13 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-static inline void drbd_tcp_quickack(struct socket *sock)
-{
-	int val = 2;
-	(void) kernel_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
-			(char*)&val, sizeof(val));
-}
-
 /* sets the number of 512 byte sectors of our virtual device */
 void drbd_set_my_capacity(struct drbd_device *device, sector_t size);
 
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 20a5e94494ac..3a3f2b6a821f 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1223,7 +1223,7 @@ static int drbd_recv_header_maybe_unplug(struct drbd_connection *connection, str
 		 * quickly as possible, and let remote TCP know what we have
 		 * received so far. */
 		if (err == -EAGAIN) {
-			drbd_tcp_quickack(connection->data.socket);
+			tcp_sock_set_quickack(connection->data.socket->sk, 2);
 			drbd_unplug_all_devices(connection);
 		}
 		if (err > 0) {
@@ -4959,8 +4959,7 @@ static int receive_UnplugRemote(struct drbd_connection *connection, struct packe
 {
 	/* Make sure we've acked all the TCP data associated
 	 * with the data requests being unplugged */
-	drbd_tcp_quickack(connection->data.socket);
-
+	tcp_sock_set_quickack(connection->data.socket->sk, 2);
 	return 0;
 }
 
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 9e42c7fe50a8..2eaf8320b9db 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -499,5 +499,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 
 void tcp_sock_set_cork(struct sock *sk, bool on);
 void tcp_sock_set_nodelay(struct sock *sk);
+void tcp_sock_set_quickack(struct sock *sk, int val);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a65f293a19fa..27b5e7a4e2ef 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2856,6 +2856,31 @@ void tcp_sock_set_nodelay(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_sock_set_nodelay);
 
+static void __tcp_sock_set_quickack(struct sock *sk, int val)
+{
+	if (!val) {
+		inet_csk_enter_pingpong_mode(sk);
+		return;
+	}
+
+	inet_csk_exit_pingpong_mode(sk);
+	if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
+	    inet_csk_ack_scheduled(sk)) {
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED;
+		tcp_cleanup_rbuf(sk, 1);
+		if (!(val & 1))
+			inet_csk_enter_pingpong_mode(sk);
+	}
+}
+
+void tcp_sock_set_quickack(struct sock *sk, int val)
+{
+	lock_sock(sk);
+	__tcp_sock_set_quickack(sk, val);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_quickack);
+
 /*
  *	Socket option code for TCP.
  */
@@ -3096,19 +3121,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_QUICKACK:
-		if (!val) {
-			inet_csk_enter_pingpong_mode(sk);
-		} else {
-			inet_csk_exit_pingpong_mode(sk);
-			if ((1 << sk->sk_state) &
-			    (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
-			    inet_csk_ack_scheduled(sk)) {
-				icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
-				tcp_cleanup_rbuf(sk, 1);
-				if (!(val & 1))
-					inet_csk_enter_pingpong_mode(sk);
-			}
-		}
+		__tcp_sock_set_quickack(sk, val);
 		break;
 
 #ifdef CONFIG_TCP_MD5SIG
-- 
cgit v1.3-6-gb490


From 557eadfcc5ee8f8fa98a795e05ed21db58a65db5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:21 +0200
Subject: tcp: add tcp_sock_set_syncnt

Add a helper to directly set the TCP_SYNCNT sockopt from kernel space
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>
---
 drivers/nvme/host/tcp.c |  9 +--------
 include/linux/tcp.h     |  1 +
 net/ipv4/tcp.c          | 12 ++++++++++++
 3 files changed, 14 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4e4a750ecdb9..2872584f52f6 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1336,14 +1336,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	}
 
 	/* Single syn retry */
-	opt = 1;
-	ret = kernel_setsockopt(queue->sock, IPPROTO_TCP, TCP_SYNCNT,
-			(char *)&opt, sizeof(opt));
-	if (ret) {
-		dev_err(nctrl->device,
-			"failed to set TCP_SYNCNT sock opt %d\n", ret);
-		goto err_sock;
-	}
+	tcp_sock_set_syncnt(queue->sock->sk, 1);
 
 	/* Set TCP no delay */
 	tcp_sock_set_nodelay(queue->sock->sk);
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 2eaf8320b9db..6aa4ae5ebf3d 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -500,5 +500,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 void tcp_sock_set_cork(struct sock *sk, bool on);
 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);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27b5e7a4e2ef..d2c67ae1da07 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2881,6 +2881,18 @@ void tcp_sock_set_quickack(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_quickack);
 
+int tcp_sock_set_syncnt(struct sock *sk, int val)
+{
+	if (val < 1 || val > MAX_TCP_SYNCNT)
+		return -EINVAL;
+
+	lock_sock(sk);
+	inet_csk(sk)->icsk_syn_retries = val;
+	release_sock(sk);
+	return 0;
+}
+EXPORT_SYMBOL(tcp_sock_set_syncnt);
+
 /*
  *	Socket option code for TCP.
  */
-- 
cgit v1.3-6-gb490


From c488aeadcbd002a992593e6090d54e8ac27c4310 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:22 +0200
Subject: tcp: add tcp_sock_set_user_timeout

Add a helper to directly set the TCP_USER_TIMEOUT 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>
---
 fs/ocfs2/cluster/tcp.c | 22 ++--------------------
 include/linux/tcp.h    |  1 +
 net/ipv4/tcp.c         |  8 ++++++++
 net/sunrpc/xprtsock.c  |  3 +--
 4 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4c70fe9d19ab..79a231719460 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static int o2net_set_usertimeout(struct socket *sock)
-{
-	int user_timeout = O2NET_TCP_USER_TIMEOUT;
-
-	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-				(void *)&user_timeout, sizeof(user_timeout));
-}
-
 static void o2net_initialize_handshake(void)
 {
 	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
@@ -1629,12 +1621,7 @@ static void o2net_start_connect(struct work_struct *work)
 	}
 
 	tcp_sock_set_nodelay(sc->sc_sock->sk);
-
-	ret = o2net_set_usertimeout(sock);
-	if (ret) {
-		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_user_timeout(sock->sk, O2NET_TCP_USER_TIMEOUT);
 
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 
@@ -1821,12 +1808,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
 	tcp_sock_set_nodelay(new_sock->sk);
-
-	ret = o2net_set_usertimeout(new_sock);
-	if (ret) {
-		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
-		goto out;
-	}
+	tcp_sock_set_user_timeout(new_sock->sk, O2NET_TCP_USER_TIMEOUT);
 
 	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1);
 	if (ret < 0)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 6aa4ae5ebf3d..de682143efe4 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -501,5 +501,6 @@ void tcp_sock_set_cork(struct sock *sk, bool on);
 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);
+void tcp_sock_set_user_timeout(struct sock *sk, u32 val);
 
 #endif	/* _LINUX_TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d2c67ae1da07..0004bd9ae7b0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2893,6 +2893,14 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_syncnt);
 
+void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
+{
+	lock_sock(sk);
+	inet_csk(sk)->icsk_user_timeout = val;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(tcp_sock_set_user_timeout);
+
 /*
  *	Socket option code for TCP.
  */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 399848c2bcb2..231fd6162f68 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2115,8 +2115,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 			(char *)&keepcnt, sizeof(keepcnt));
 
 	/* TCP user timeout (see RFC5482) */
-	kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-			(char *)&timeo, sizeof(timeo));
+	tcp_sock_set_user_timeout(sock->sk, timeo);
 }
 
 static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
-- 
cgit v1.3-6-gb490


From 71c48eb81c9ecb6fed49dc33e7c9b621fdcb7bf8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:23 +0200
Subject: 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>
---
 include/linux/tcp.h   |  1 +
 net/ipv4/tcp.c        | 49 ++++++++++++++++++++++++++++++++++---------------
 net/rds/tcp_listen.c  |  5 +----
 net/sunrpc/xprtsock.c |  3 +--
 4 files changed, 37 insertions(+), 21 deletions(-)

(limited to 'include/linux')

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,
-- 
cgit v1.3-6-gb490


From d41ecaac903c9f4658a71d4e7a708673cfb5abba Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:24 +0200
Subject: tcp: add tcp_sock_set_keepintvl

Add a helper to directly set the TCP_KEEPINTVL 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   |  1 +
 net/ipv4/tcp.c        | 12 ++++++++++++
 net/rds/tcp_listen.c  |  4 +---
 net/sunrpc/xprtsock.c |  3 +--
 4 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 5724dd84a85e..1f9bada00faa 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
 
 void tcp_sock_set_cork(struct sock *sk, bool on);
 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);
 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 bdf0ff933351..7eb083e09786 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2934,6 +2934,18 @@ int tcp_sock_set_keepidle(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_keepidle);
 
+int tcp_sock_set_keepintvl(struct sock *sk, int val)
+{
+	if (val < 1 || val > MAX_TCP_KEEPINTVL)
+		return -EINVAL;
+
+	lock_sock(sk);
+	tcp_sk(sk)->keepalive_intvl = val * HZ;
+	release_sock(sk);
+	return 0;
+}
+EXPORT_SYMBOL(tcp_sock_set_keepintvl);
+
 /*
  *	Socket option code for TCP.
  */
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 79f9adc00811..9ad555c48d15 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -53,12 +53,10 @@ int rds_tcp_keepalive(struct socket *sock)
 		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.
 	 */
-	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPINTVL,
-				(char *)&keepidle, sizeof(keepidle));
+	tcp_sock_set_keepintvl(sock->sk, keepidle);
 bail:
 	return ret;
 }
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 473290f7c5c0..5ca64e12af0c 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2108,8 +2108,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 	/* TCP Keepalive options */
 	sock_set_keepalive(sock->sk);
 	tcp_sock_set_keepidle(sock->sk, keepidle);
-	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
-			(char *)&keepidle, sizeof(keepidle));
+	tcp_sock_set_keepintvl(sock->sk, keepidle);
 	kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
 			(char *)&keepcnt, sizeof(keepcnt));
 
-- 
cgit v1.3-6-gb490


From 480aeb9639d6a077c611b303a22f9b1e5937d081 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 May 2020 07:12:25 +0200
Subject: 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   |  1 +
 net/ipv4/tcp.c        | 12 ++++++++++++
 net/rds/tcp.h         |  2 +-
 net/rds/tcp_listen.c  | 17 +++--------------
 net/sunrpc/xprtsock.c |  3 +--
 5 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1f9bada00faa..9aac824c523c 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_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);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7eb083e09786..15d47d5e7951 100644
--- a/net/ipv4/tcp.c
+++ b/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.
  */
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index f6d75d8cb167..bad9cf49d565 100644
--- a/net/rds/tcp.h
+++ b/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 */
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 9ad555c48d15..101cf14215a0 100644
--- a/net/rds/tcp_listen.c
+++ b/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);
-
-	ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT,
-				(char *)&keepcnt, sizeof(keepcnt));
-	if (ret < 0)
-		goto bail;
-
+	tcp_sock_set_keepcnt(sock->sk, keepcnt);
 	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);
-	if (ret < 0)
-		goto out;
-
+	rds_tcp_keepalive(new_sock);
 	rds_tcp_tune(new_sock);
 
 	inet = inet_sk(new_sock->sk);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 5ca64e12af0c..0d3ec055bc12 100644
--- a/net/sunrpc/xprtsock.c
+++ b/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,
-			(char *)&keepcnt, sizeof(keepcnt));
+	tcp_sock_set_keepcnt(sock->sk, keepcnt);
 
 	/* TCP user timeout (see RFC5482) */
 	tcp_sock_set_user_timeout(sock->sk, timeo);
-- 
cgit v1.3-6-gb490