diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 59afc9a10b4f..13bbac50dc8b 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -451,6 +451,7 @@ tcp_recovery - INTEGER RACK: 0x1 enables the RACK loss detection for fast detection of lost retransmissions and tail drops. RACK: 0x2 makes RACK's reordering window static (min_rtt/4). + RACK: 0x4 disables RACK's DUPACK threshold heuristic Default: 0x1 diff --git a/include/net/tcp.h b/include/net/tcp.h index a08eab58ef70..994f869d793c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -245,6 +245,7 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ +#define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 3a81720ac0c4..1c1bdf12a96f 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -21,6 +21,32 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } +u32 tcp_rack_reo_wnd(const struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->rack.reord) { + /* If reordering has not been observed, be aggressive during + * the recovery or starting the recovery by DUPACK threshold. + */ + if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery) + return 0; + + if (tp->sacked_out >= tp->reordering && + !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + return 0; + } + + /* To be more reordering resilient, allow min_rtt/4 settling delay. + * Use min_rtt instead of the smoothed RTT because reordering is + * often a path property and less related to queuing or delayed ACKs. + * Upon receiving DSACKs, linearly increase the window up to the + * smoothed RTT. + */ + return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps, + tp->srtt_us >> 3); +} + /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): * * Marks a packet lost, if some packet sent later has been (s)acked. @@ -44,23 +70,11 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); - u32 min_rtt = tcp_min_rtt(tp); struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; - /* To be more reordering resilient, allow min_rtt/4 settling delay - * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed - * RTT because reordering is often a path property and less related - * to queuing or delayed ACKs. - */ - reo_wnd = 1000; - if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) && - min_rtt != ~0U) { - reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd); - reo_wnd = min(reo_wnd, tp->srtt_us >> 3); - } - + reo_wnd = tcp_rack_reo_wnd(sk); list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb);