X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=net%2Fipv4%2Ftcp_input.c;h=bc7f62e2792b4039e6b6f033696a0263f5cb1a8f;hb=e6e30add6bd8115af108de2a13ec82d997a55777;hp=8ac15a604e086b766552b3ff8a646ca3a8d44f08;hpb=bd1d23a81083f03ac63afbb7656b87eed04d8953;p=mirror_ubuntu-bionic-kernel.git diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8ac15a604e08..bc7f62e2792b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5,8 +5,6 @@ * * Implementation of the Transmission Control Protocol(TCP). * - * Version: $Id: tcp_input.c,v 1.243 2002/02/01 22:01:04 davem Exp $ - * * Authors: Ross Biro * Fred N. van Kempen, * Mark Evans, @@ -114,8 +112,6 @@ int sysctl_tcp_abc __read_mostly; #define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED) #define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED) -#define IsSackFrto() (sysctl_tcp_frto == 0x2) - #define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH) #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH)) @@ -1394,9 +1390,9 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, if (before(next_dup->start_seq, skip_to_seq)) { skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); - tcp_sacktag_walk(skb, sk, NULL, - next_dup->start_seq, next_dup->end_seq, - 1, fack_count, reord, flag); + skb = tcp_sacktag_walk(skb, sk, NULL, + next_dup->start_seq, next_dup->end_seq, + 1, fack_count, reord, flag); } return skb; @@ -1686,6 +1682,11 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp) tp->sacked_out = 0; } +static int tcp_is_sackfrto(const struct tcp_sock *tp) +{ + return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp); +} + /* F-RTO can only be used if TCP has never retransmitted anything other than * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here) */ @@ -1702,7 +1703,7 @@ int tcp_use_frto(struct sock *sk) if (icsk->icsk_mtup.probe_size) return 0; - if (IsSackFrto()) + if (tcp_is_sackfrto(tp)) return 1; /* Avoid expensive walking of rexmit queue if possible */ @@ -1792,7 +1793,7 @@ void tcp_enter_frto(struct sock *sk) /* Earlier loss recovery underway (see RFC4138; Appendix B). * The last condition is necessary at least in tp->frto_counter case. */ - if (IsSackFrto() && (tp->frto_counter || + if (tcp_is_sackfrto(tp) && (tp->frto_counter || ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) && after(tp->high_seq, tp->snd_una)) { tp->frto_highmark = tp->high_seq; @@ -1839,9 +1840,16 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; } - /* Don't lost mark skbs that were fwd transmitted after RTO */ - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) && - !after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) { + /* Marking forward transmissions that were made after RTO lost + * can cause unnecessary retransmissions in some scenarios, + * SACK blocks will mitigate that in some but not in all cases. + * We used to not mark them but it was causing break-ups with + * receivers that do only in-order receival. + * + * TODO: we could detect presence of such receiver and select + * different behavior per flow. + */ + if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); } @@ -1857,7 +1865,7 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) tp->reordering = min_t(unsigned int, tp->reordering, sysctl_tcp_reordering); tcp_set_ca_state(sk, TCP_CA_Loss); - tp->high_seq = tp->frto_highmark; + tp->high_seq = tp->snd_nxt; TCP_ECN_queue_cwr(tp); tcp_clear_retrans_hints_partial(tp); @@ -2473,28 +2481,34 @@ static inline void tcp_complete_cwr(struct sock *sk) tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } +static void tcp_try_keep_open(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int state = TCP_CA_Open; + + if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) + state = TCP_CA_Disorder; + + if (inet_csk(sk)->icsk_ca_state != state) { + tcp_set_ca_state(sk, state); + tp->high_seq = tp->snd_nxt; + } +} + static void tcp_try_to_open(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); tcp_verify_left_out(tp); - if (tp->retrans_out == 0) + if (!tp->frto_counter && tp->retrans_out == 0) tp->retrans_stamp = 0; if (flag & FLAG_ECE) tcp_enter_cwr(sk, 1); if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { - int state = TCP_CA_Open; - - if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) - state = TCP_CA_Disorder; - - if (inet_csk(sk)->icsk_ca_state != state) { - tcp_set_ca_state(sk, state); - tp->high_seq = tp->snd_nxt; - } + tcp_try_keep_open(sk); tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); @@ -3124,7 +3138,7 @@ static int tcp_process_frto(struct sock *sk, int flag) return 1; } - if (!IsSackFrto() || tcp_is_reno(tp)) { + if (!tcp_is_sackfrto(tp)) { /* RFC4138 shortcoming in step 2; should also have case c): * ACK isn't duplicate nor advances window, e.g., opposite dir * data, winupdate @@ -3300,8 +3314,11 @@ no_queue: return 1; old_ack: - if (TCP_SKB_CB(skb)->sacked) + if (TCP_SKB_CB(skb)->sacked) { tcp_sacktag_write_queue(sk, skb, prior_snd_una); + if (icsk->icsk_ca_state == TCP_CA_Open) + tcp_try_keep_open(sk); + } uninteresting_ack: SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -3431,6 +3448,43 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, return 1; } +#ifdef CONFIG_TCP_MD5SIG +/* + * Parse MD5 Signature option + */ +u8 *tcp_parse_md5sig_option(struct tcphdr *th) +{ + int length = (th->doff << 2) - sizeof (*th); + u8 *ptr = (u8*)(th + 1); + + /* If the TCP option is too short, we can short cut */ + if (length < TCPOLEN_MD5SIG) + return NULL; + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch(opcode) { + case TCPOPT_EOL: + return NULL; + case TCPOPT_NOP: + length--; + continue; + default: + opsize = *ptr++; + if (opsize < 2 || opsize > length) + return NULL; + if (opcode == TCPOPT_MD5SIG) + return ptr; + } + ptr += opsize - 2; + length -= opsize; + } + return NULL; +} +#endif + static inline void tcp_store_ts_recent(struct tcp_sock *tp) { tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; @@ -5448,6 +5502,9 @@ EXPORT_SYMBOL(sysctl_tcp_ecn); EXPORT_SYMBOL(sysctl_tcp_reordering); EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); EXPORT_SYMBOL(tcp_parse_options); +#ifdef CONFIG_TCP_MD5SIG +EXPORT_SYMBOL(tcp_parse_md5sig_option); +#endif EXPORT_SYMBOL(tcp_rcv_established); EXPORT_SYMBOL(tcp_rcv_state_process); EXPORT_SYMBOL(tcp_initialize_rcv_mss);