From efe4208f47f907b86f528788da711e8ab9dea44d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Oct 2013 15:42:29 -0700 Subject: ipv6: make lookups simpler and faster TCP listener refactoring, part 4 : To speed up inet lookups, we moved IPv4 addresses from inet to struct sock_common Now is time to do the same for IPv6, because it permits us to have fast lookups for all kind of sockets, including upcoming SYN_RECV. Getting IPv6 addresses in TCP lookups currently requires two extra cache lines, plus a dereference (and memory stall). inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6 This patch is way bigger than its IPv4 counter part, because for IPv4, we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6, it's not doable easily. inet6_sk(sk)->daddr becomes sk->sk_v6_daddr inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr at the same offset. We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic macro. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4b85e6f636c9..af07b5b23ebf 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -374,9 +374,8 @@ void tcp_retransmit_timer(struct sock *sk) } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &np->daddr, + &sk->sk_v6_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } -- cgit v1.2.3 From c968601d174739cb1e7100c95e0eb3d2f7e91bc9 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 29 Oct 2013 10:09:05 -0700 Subject: tcp: temporarily disable Fast Open on SYN timeout Fast Open currently has a fall back feature to address SYN-data being dropped but it requires the middle-box to pass on regular SYN retry after SYN-data. This is implemented in commit aab487435 ("net-tcp: Fast Open client - detecting SYN-data drops") However some NAT boxes will drop all subsequent packets after first SYN-data and blackholes the entire connections. An example is in commit 356d7d8 "netfilter: nf_conntrack: fix tcp_in_window for Fast Open". The sender should note such incidents and fall back to use the regular TCP handshake on subsequent attempts temporarily as well: after the second SYN timeouts the original Fast Open SYN is most likely lost. When such an event recurs Fast Open is disabled based on the number of recurrences exponentially. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index af07b5b23ebf..64f0354c84c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -156,12 +156,16 @@ static bool retransmits_timed_out(struct sock *sk, static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); int retry_until; bool do_reset, syn_set = false; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { - if (icsk->icsk_retransmits) + if (icsk->icsk_retransmits) { dst_negative_advice(sk); + if (tp->syn_fastopen || tp->syn_data) + tcp_fastopen_cache_set(sk, 0, NULL, true); + } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; } else { -- cgit v1.2.3