aboutsummaryrefslogtreecommitdiffstats
path: root/include/net/tcp.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r--include/net/tcp.h26
1 files changed, 20 insertions, 6 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9a154fe06c60..49da4d4a3c3d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -128,6 +128,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
* to combine FIN-WAIT-2 timeout with
* TIME-WAIT timer.
*/
+#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */
#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
#if HZ >= 100
@@ -140,6 +141,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCP_RTO_MAX ((unsigned)(120*HZ))
#define TCP_RTO_MIN ((unsigned)(HZ/5))
#define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */
+
+#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */
+
#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now
* used as a fallback RTO for the
@@ -345,13 +349,14 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
-static inline void tcp_dec_quickack_mode(struct sock *sk,
- const unsigned int pkts)
+static inline void tcp_dec_quickack_mode(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ack.quick) {
+ /* How many ACKs S/ACKing new data have we sent? */
+ const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0;
+
if (pkts >= icsk->icsk_ack.quick) {
icsk->icsk_ack.quick = 0;
/* Leaving quickack mode we deflate ATO. */
@@ -389,6 +394,7 @@ void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
+void __tcp_close(struct sock *sk, long timeout);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op);
@@ -1881,15 +1887,23 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
- return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
+ u32 val;
+
+ val = READ_ONCE(tp->notsent_lowat);
+
+ return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
}
-static inline bool tcp_stream_memory_free(const struct sock *sk)
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
{
const struct tcp_sock *tp = tcp_sk(sk);
u32 notsent_bytes = READ_ONCE(tp->write_seq) - tp->snd_nxt;
- return notsent_bytes < tcp_notsent_lowat(tp);
+ return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
}
#ifdef CONFIG_PROC_FS