diff options
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r-- | include/net/tcp.h | 46 |
1 files changed, 34 insertions, 12 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 65be8bd1f0f4..164ba7b77bd9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -125,6 +125,7 @@ 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 @@ -137,6 +138,9 @@ 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 @@ -342,13 +346,14 @@ 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. */ @@ -386,6 +391,7 @@ 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); @@ -548,7 +554,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); -u64 cookie_init_timestamp(struct request_sock *req); +u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, @@ -770,10 +776,16 @@ static inline u32 tcp_time_stamp(const struct tcp_sock *tp) return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); } +/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ +static inline u64 tcp_ns_to_ts(u64 ns) +{ + return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); +} + /* Could use tcp_clock_us() / 1000, but this version uses a single divide */ static inline u32 tcp_time_stamp_raw(void) { - return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); + return tcp_ns_to_ts(tcp_clock_ns()); } void tcp_mstamp_refresh(struct tcp_sock *tp); @@ -785,7 +797,7 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); + return tcp_ns_to_ts(skb->skb_mstamp_ns); } /* provide the departure time in us unit */ @@ -922,6 +934,8 @@ static inline int tcp_v6_sdif(const struct sk_buff *skb) #endif return 0; } + +void tcp_v6_early_demux(struct sk_buff *skb); #endif static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) @@ -1258,11 +1272,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + if (tp->is_cwnd_limited) + return true; + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tp->snd_cwnd < 2 * tp->max_packets_out; - return tp->is_cwnd_limited; + return false; } /* BBR congestion control needs pacing. @@ -1373,8 +1390,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); s32 delta; - if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out || - ca_ops->cong_control) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || + tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) @@ -1389,7 +1406,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, static inline int tcp_win_from_space(const struct sock *sk, int space) { - int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale; + int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale); return tcp_adv_win_scale <= 0 ? (space>>(-tcp_adv_win_scale)) : @@ -1465,7 +1482,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) @@ -1946,7 +1964,11 @@ 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 ?: net->ipv4.sysctl_tcp_notsent_lowat; + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } /* @wake is one when sk_stream_write_space() calls us. |