diff options
Diffstat (limited to 'net/ipv4/tcp_output.c')
| -rw-r--r-- | net/ipv4/tcp_output.c | 52 |
1 files changed, 40 insertions, 12 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a4d214c7b506..6818042cd8a9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1730,7 +1730,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, */ segs = max_t(u32, bytes / mss_now, min_tso_segs); - return min_t(u32, segs, sk->sk_gso_max_segs); + return segs; } EXPORT_SYMBOL(tcp_tso_autosize); @@ -1742,9 +1742,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; - return tso_segs ? : - tcp_tso_autosize(sk, mss_now, - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + if (!tso_segs) + tso_segs = tcp_tso_autosize(sk, mss_now, + sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ @@ -1944,7 +1945,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, in_flight = tcp_packets_in_flight(tp); - BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight)); + BUG_ON(tcp_skb_pcount(skb) <= 1); + BUG_ON(tp->snd_cwnd <= in_flight); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; @@ -2026,6 +2028,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) } } +static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) +{ + struct sk_buff *skb, *next; + + skb = tcp_send_head(sk); + tcp_for_write_queue_from_safe(skb, next, sk) { + if (len <= skb->len) + break; + + if (unlikely(TCP_SKB_CB(skb)->eor)) + return false; + + len -= skb->len; + } + + return true; +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2098,6 +2118,9 @@ static int tcp_mtu_probe(struct sock *sk) return 0; } + if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) + return -1; + /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) @@ -2133,6 +2156,10 @@ static int tcp_mtu_probe(struct sock *sk) /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + /* If this is the last SKB we copy and eor is set + * we need to propagate it to the new skb. + */ + TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { @@ -2414,15 +2441,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; /* Schedule a loss probe in 2*RTT for SACK capable connections - * in Open state, that are either limited by cwnd or application. + * not in loss recovery, that are either limited by cwnd or application. */ if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || - icsk->icsk_ca_state != TCP_CA_Open) - return false; - - if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - !tcp_write_queue_empty(sk)) + (icsk->icsk_ca_state != TCP_CA_Open && + icsk->icsk_ca_state != TCP_CA_CWR)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account @@ -2907,6 +2931,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) + tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, + TCP_SKB_CB(skb)->seq, segs, err); + if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; trace_tcp_retransmit_skb(sk, skb); @@ -3471,7 +3499,7 @@ int tcp_connect(struct sock *sk) struct sk_buff *buff; int err; - tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ |