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>
This commit is contained in:
Christoph Hellwig 2020-05-28 07:12:19 +02:00 committed by David S. Miller
parent db10538a4b
commit 12abc5ee78
16 changed files with 49 additions and 127 deletions

View File

@ -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;

View File

@ -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;
}

View File

@ -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;

View File

@ -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;

View File

@ -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

View File

@ -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);

View File

@ -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) {

View File

@ -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,

View File

@ -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);

View File

@ -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) {

View File

@ -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 */

View File

@ -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;

View File

@ -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:

View File

@ -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;

View File

@ -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,

View File

@ -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;