summaryrefslogtreecommitdiff
path: root/net/tipc/socket.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/tipc/socket.c')
-rw-r--r--net/tipc/socket.c127
1 files changed, 96 insertions, 31 deletions
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 87466607097f..a94f38333698 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -48,6 +48,8 @@
#include "group.h"
#include "trace.h"
+#define NAGLE_START_INIT 4
+#define NAGLE_START_MAX 1024
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
@@ -119,7 +121,10 @@ struct tipc_sock {
struct rcu_head rcu;
struct tipc_group *group;
u32 oneway;
+ u32 nagle_start;
u16 snd_backlog;
+ u16 msg_acc;
+ u16 pkt_cnt;
bool expect_ack;
bool nodelay;
bool group_is_open;
@@ -143,7 +148,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
-static void tipc_sk_push_backlog(struct tipc_sock *tsk);
+static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -191,17 +196,17 @@ static int tsk_importance(struct tipc_sock *tsk)
return msg_importance(&tsk->phdr);
}
-static int tsk_set_importance(struct tipc_sock *tsk, int imp)
+static struct tipc_sock *tipc_sk(const struct sock *sk)
{
- if (imp > TIPC_CRITICAL_IMPORTANCE)
- return -EINVAL;
- msg_set_importance(&tsk->phdr, (u32)imp);
- return 0;
+ return container_of(sk, struct tipc_sock, sk);
}
-static struct tipc_sock *tipc_sk(const struct sock *sk)
+int tsk_set_importance(struct sock *sk, int imp)
{
- return container_of(sk, struct tipc_sock, sk);
+ if (imp > TIPC_CRITICAL_IMPORTANCE)
+ return -EINVAL;
+ msg_set_importance(&tipc_sk(sk)->phdr, (u32)imp);
+ return 0;
}
static bool tsk_conn_cong(struct tipc_sock *tsk)
@@ -474,6 +479,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
tsk = tipc_sk(sk);
tsk->max_pkt = MAX_PKT_DEFAULT;
tsk->maxnagle = 0;
+ tsk->nagle_start = NAGLE_START_INIT;
INIT_LIST_HEAD(&tsk->publications);
INIT_LIST_HEAD(&tsk->cong_links);
msg = &tsk->phdr;
@@ -541,7 +547,7 @@ static void __tipc_shutdown(struct socket *sock, int error)
!tsk_conn_cong(tsk)));
/* Push out delayed messages if in Nagle mode */
- tipc_sk_push_backlog(tsk);
+ tipc_sk_push_backlog(tsk, false);
/* Remove pending SYN */
__skb_queue_purge(&sk->sk_write_queue);
@@ -1252,14 +1258,37 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
/* tipc_sk_push_backlog(): send accumulated buffers in socket write queue
* when socket is in Nagle mode
*/
-static void tipc_sk_push_backlog(struct tipc_sock *tsk)
+static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack)
{
struct sk_buff_head *txq = &tsk->sk.sk_write_queue;
+ struct sk_buff *skb = skb_peek_tail(txq);
struct net *net = sock_net(&tsk->sk);
u32 dnode = tsk_peer_node(tsk);
- struct sk_buff *skb = skb_peek(txq);
int rc;
+ if (nagle_ack) {
+ tsk->pkt_cnt += skb_queue_len(txq);
+ if (!tsk->pkt_cnt || tsk->msg_acc / tsk->pkt_cnt < 2) {
+ tsk->oneway = 0;
+ if (tsk->nagle_start < NAGLE_START_MAX)
+ tsk->nagle_start *= 2;
+ tsk->expect_ack = false;
+ pr_debug("tsk %10u: bad nagle %u -> %u, next start %u!\n",
+ tsk->portid, tsk->msg_acc, tsk->pkt_cnt,
+ tsk->nagle_start);
+ } else {
+ tsk->nagle_start = NAGLE_START_INIT;
+ if (skb) {
+ msg_set_ack_required(buf_msg(skb));
+ tsk->expect_ack = true;
+ } else {
+ tsk->expect_ack = false;
+ }
+ }
+ tsk->msg_acc = 0;
+ tsk->pkt_cnt = 0;
+ }
+
if (!skb || tsk->cong_link_cnt)
return;
@@ -1267,9 +1296,10 @@ static void tipc_sk_push_backlog(struct tipc_sock *tsk)
if (msg_is_syn(buf_msg(skb)))
return;
+ if (tsk->msg_acc)
+ tsk->pkt_cnt += skb_queue_len(txq);
tsk->snt_unacked += tsk->snd_backlog;
tsk->snd_backlog = 0;
- tsk->expect_ack = true;
rc = tipc_node_xmit(net, txq, dnode, tsk->portid);
if (rc == -ELINKCONG)
tsk->cong_link_cnt = 1;
@@ -1322,8 +1352,7 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
return;
} else if (mtyp == CONN_ACK) {
was_cong = tsk_conn_cong(tsk);
- tsk->expect_ack = false;
- tipc_sk_push_backlog(tsk);
+ tipc_sk_push_backlog(tsk, msg_nagle_ack(hdr));
tsk->snt_unacked -= msg_conn_ack(hdr);
if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
tsk->snd_win = msg_adv_win(hdr);
@@ -1516,6 +1545,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = &tsk->phdr;
struct net *net = sock_net(sk);
+ struct sk_buff *skb;
u32 dnode = tsk_peer_node(tsk);
int maxnagle = tsk->maxnagle;
int maxpkt = tsk->max_pkt;
@@ -1544,17 +1574,30 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
break;
send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE);
blocks = tsk->snd_backlog;
- if (tsk->oneway++ >= 4 && send <= maxnagle) {
+ if (tsk->oneway++ >= tsk->nagle_start && maxnagle &&
+ send <= maxnagle) {
rc = tipc_msg_append(hdr, m, send, maxnagle, txq);
if (unlikely(rc < 0))
break;
blocks += rc;
+ tsk->msg_acc++;
if (blocks <= 64 && tsk->expect_ack) {
tsk->snd_backlog = blocks;
sent += send;
break;
+ } else if (blocks > 64) {
+ tsk->pkt_cnt += skb_queue_len(txq);
+ } else {
+ skb = skb_peek_tail(txq);
+ if (skb) {
+ msg_set_ack_required(buf_msg(skb));
+ tsk->expect_ack = true;
+ } else {
+ tsk->expect_ack = false;
+ }
+ tsk->msg_acc = 0;
+ tsk->pkt_cnt = 0;
}
- tsk->expect_ack = true;
} else {
rc = tipc_msg_build(hdr, m, sent, send, maxpkt, txq);
if (unlikely(rc != send))
@@ -1739,22 +1782,21 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
return 0;
}
-static void tipc_sk_send_ack(struct tipc_sock *tsk)
+static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk)
{
struct sock *sk = &tsk->sk;
- struct net *net = sock_net(sk);
struct sk_buff *skb = NULL;
struct tipc_msg *msg;
u32 peer_port = tsk_peer_port(tsk);
u32 dnode = tsk_peer_node(tsk);
if (!tipc_sk_connected(sk))
- return;
+ return NULL;
skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
dnode, tsk_own_node(tsk), peer_port,
tsk->portid, TIPC_OK);
if (!skb)
- return;
+ return NULL;
msg = buf_msg(skb);
msg_set_conn_ack(msg, tsk->rcv_unacked);
tsk->rcv_unacked = 0;
@@ -1764,7 +1806,19 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk)
tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf);
msg_set_adv_win(msg, tsk->rcv_win);
}
- tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg));
+ return skb;
+}
+
+static void tipc_sk_send_ack(struct tipc_sock *tsk)
+{
+ struct sk_buff *skb;
+
+ skb = tipc_sk_build_ack(tsk);
+ if (!skb)
+ return;
+
+ tipc_node_xmit_skb(sock_net(&tsk->sk), skb, tsk_peer_node(tsk),
+ msg_link_selector(buf_msg(skb)));
}
static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
@@ -1938,7 +1992,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
bool peek = flags & MSG_PEEK;
int offset, required, copy, copied = 0;
int hlen, dlen, err, rc;
- bool ack = false;
long timeout;
/* Catch invalid receive attempts */
@@ -1983,7 +2036,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
/* Copy data if msg ok, otherwise return error/partial data */
if (likely(!err)) {
- ack = msg_ack_required(hdr);
offset = skb_cb->bytes_read;
copy = min_t(int, dlen - offset, buflen - copied);
rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
@@ -2011,7 +2063,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
/* Send connection flow control advertisement when applicable */
tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
- if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
+ if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
tipc_sk_send_ack(tsk);
/* Exit if all requested data or FIN/error received */
@@ -2082,7 +2134,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
smp_wmb();
tsk->cong_link_cnt--;
wakeup = true;
- tipc_sk_push_backlog(tsk);
+ tipc_sk_push_backlog(tsk, false);
break;
case GROUP_PROTOCOL:
tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq);
@@ -2105,9 +2157,11 @@ static void tipc_sk_proto_rcv(struct sock *sk,
* tipc_sk_filter_connect - check incoming message for a connection-based socket
* @tsk: TIPC socket
* @skb: pointer to message buffer.
+ * @xmitq: for Nagle ACK if any
* Returns true if message should be added to receive queue, false otherwise
*/
-static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
+static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
@@ -2169,10 +2223,21 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
return false;
case TIPC_ESTABLISHED:
if (!skb_queue_empty(&sk->sk_write_queue))
- tipc_sk_push_backlog(tsk);
+ tipc_sk_push_backlog(tsk, false);
/* Accept only connection-based messages sent by peer */
- if (likely(con_msg && !err && pport == oport && pnode == onode))
+ if (likely(con_msg && !err && pport == oport &&
+ pnode == onode)) {
+ if (msg_ack_required(hdr)) {
+ struct sk_buff *skb;
+
+ skb = tipc_sk_build_ack(tsk);
+ if (skb) {
+ msg_set_nagle_ack(buf_msg(skb));
+ __skb_queue_tail(xmitq, skb);
+ }
+ }
return true;
+ }
if (!tsk_peer_msg(tsk, hdr))
return false;
if (!err)
@@ -2267,7 +2332,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
while ((skb = __skb_dequeue(&inputq))) {
hdr = buf_msg(skb);
limit = rcvbuf_limit(sk, skb);
- if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
+ if ((sk_conn && !tipc_sk_filter_connect(tsk, skb, xmitq)) ||
(!sk_conn && msg_connected(hdr)) ||
(!grp && msg_in_group(hdr)))
err = TIPC_ERR_NO_PORT;
@@ -2661,7 +2726,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
/* Connect new socket to it's peer */
tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
- tsk_set_importance(new_tsock, msg_importance(msg));
+ tsk_set_importance(new_sk, msg_importance(msg));
if (msg_named(msg)) {
new_tsock->conn_type = msg_nametype(msg);
new_tsock->conn_instance = msg_nameinst(msg);
@@ -3079,7 +3144,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
switch (opt) {
case TIPC_IMPORTANCE:
- res = tsk_set_importance(tsk, value);
+ res = tsk_set_importance(sk, value);
break;
case TIPC_SRC_DROPPABLE:
if (sock->type != SOCK_STREAM)
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-05-22 10:28:03 +0000