tcp: add rfc3168, section 6.1.1.1. fallback

This work as a follow-up of commit f7b3bec6f516 ("net: allow setting ecn
via routing table") and adds RFC3168 section 6.1.1.1. fallback for outgoing
ECN connections. In other words, this work adds a retry with a non-ECN
setup SYN packet, as suggested from the RFC on the first timeout:

  [...] A host that receives no reply to an ECN-setup SYN within the
  normal SYN retransmission timeout interval MAY resend the SYN and
  any subsequent SYN retransmissions with CWR and ECE cleared. [...]

Schematic client-side view when assuming the server is in tcp_ecn=2 mode,
that is, Linux default since 2009 via commit 255cac91c3c9 ("tcp: extend
ECN sysctl to allow server-side only ECN"):

 1) Normal ECN-capable path:

    SYN ECE CWR ----->
                <----- SYN ACK ECE
            ACK ----->

 2) Path with broken middlebox, when client has fallback:

    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
            SYN ----->
                <----- SYN ACK
            ACK ----->

In case we would not have the fallback implemented, the middlebox drop
point would basically end up as:

    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)
    SYN ECE CWR ----X crappy middlebox drops packet
                      (timeout, rtx)

In any case, it's rather a smaller percentage of sites where there would
occur such additional setup latency: it was found in end of 2014 that ~56%
of IPv4 and 65% of IPv6 servers of Alexa 1 million list would negotiate
ECN (aka tcp_ecn=2 default), 0.42% of these webservers will fail to connect
when trying to negotiate with ECN (tcp_ecn=1) due to timeouts, which the
fallback would mitigate with a slight latency trade-off. Recent related
paper on this topic:

  Brian Trammell, Mirja Kühlewind, Damiano Boppart, Iain Learmonth,
  Gorry Fairhurst, and Richard Scheffenegger:
    "Enabling Internet-Wide Deployment of Explicit Congestion Notification."
    Proc. PAM 2015, New York.
  http://ecn.ethz.ch/ecn-pam15.pdf

Thus, when net.ipv4.tcp_ecn=1 is being set, the patch will perform RFC3168,
section 6.1.1.1. fallback on timeout. For users explicitly not wanting this
which can be in DC use case, we add a net.ipv4.tcp_ecn_fallback knob that
allows for disabling the fallback.

tp->ecn_flags are not being cleared in tcp_ecn_clear_syn() on output, but
rather we let tcp_ecn_rcv_synack() take that over on input path in case a
SYN ACK ECE was delayed. Thus a spurious SYN retransmission will not prevent
ECN being negotiated eventually in that case.

Reference: https://www.ietf.org/proceedings/92/slides/slides-92-iccrg-1.pdf
Reference: https://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdf
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mirja Kühlewind <mirja.kuehlewind@tik.ee.ethz.ch>
Signed-off-by: Brian Trammell <trammell@tik.ee.ethz.ch>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Dave That <dave.taht@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt
index 0d5dfbc89ec9e37e27b53a610594dd112d3c6e37..13a85775320875a886442375fcfc027628613f2b 100644 (file)
--- a/Documentation/networking/dctcp.txt
+++ b/Documentation/networking/dctcp.txt
@@ -8,6 +8,7 @@ the data center network to provide multi-bit feedback to the end hosts.
 To enable it on end hosts:
 
   sysctl -w net.ipv4.tcp_congestion_control=dctcp
+  sysctl -w net.ipv4.tcp_ecn_fallback=0 (optional)
 
 All switches in the data center network running DCTCP must support ECN
 marking and be configured for marking when reaching defined switch buffer

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 5095c63e50eda6783f847ddf36f2a47cd8d2cdd2..cb083e0d682c6faae13aea21aa1a88868a39c632 100644 (file)
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -267,6 +267,15 @@ tcp_ecn - INTEGER
                  but do not request ECN on outgoing connections.
        Default: 2
 
+tcp_ecn_fallback - BOOLEAN
+       If the kernel detects that ECN connection misbehaves, enable fall
+       back to non-ECN. Currently, this knob implements the fallback
+       from RFC3168, section 6.1.1.1., but we reserve that in future,
+       additional detection mechanisms could be implemented under this
+       knob. The value is not used, if tcp_ecn or per route (or congestion
+       control) ECN settings are disabled.
+       Default: 1 (fallback enabled)
+
 tcp_fack - BOOLEAN
        Enable FACK congestion avoidance and fast retransmission.
        The value is not used, if tcp_sack is not enabled.

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 614a49be68a92897525ce9a1b5a7afd458faf126..6848b8bb2e6319ac9ddd90dd45b39eb01c6c9ff8 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -77,6 +77,8 @@ struct netns_ipv4 {
        struct local_ports ip_local_ports;
 
        int sysctl_tcp_ecn;
+       int sysctl_tcp_ecn_fallback;
+
        int sysctl_ip_no_pmtu_disc;
        int sysctl_ip_fwd_use_pmtu;
        int sysctl_ip_nonlocal_bind;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d85223efa4c747917d72dfb7c18279ae7a21984..2bb2bad21d5c2e0d1b079e7bcf19e192bc126637 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -712,6 +712,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
 #define TCPHDR_ECE 0x40
 #define TCPHDR_CWR 0x80
 
+#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
+
 /* This is what the send packet queuing engine uses to pass
  * TCP per-packet control information to the transmission code.
  * We also store the host-order sequence numbers in here too.

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c3852a7ff3c7630f4114cbc33a51a35fa3645e8c..841de32f1fee4e6faa55ebf855df7168ee996fc3 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -820,6 +820,13 @@ static struct ctl_table ipv4_net_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec
        },
+       {
+               .procname       = "tcp_ecn_fallback",
+               .data           = &init_net.ipv4.sysctl_tcp_ecn_fallback,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec
+       },
        {
                .procname       = "ip_local_port_range",
                .maxlen         = sizeof(init_net.ipv4.ip_local_ports.range),

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 91cb4768a860345d3ec40c716ec2a10a813e9969..0cc4b5a630cd49c60ea0767debf4ee171f41ad3e 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2411,12 +2411,15 @@ static int __net_init tcp_sk_init(struct net *net)
                        goto fail;
                *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
        }
+
        net->ipv4.sysctl_tcp_ecn = 2;
+       net->ipv4.sysctl_tcp_ecn_fallback = 1;
+
        net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
        net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
        net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
-       return 0;
 
+       return 0;
 fail:
        tcp_sk_exit(net);
 

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 08c2cc40b26d65227eccaf3b5a068c16cef62fa1..e29d43b5a0bb46305b0ab4af29bd05a61abd522d 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -350,6 +350,15 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
        }
 }
 
+static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
+{
+       if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+               /* tp->ecn_flags are cleared at a later point in time when
+                * SYN ACK is ultimatively being received.
+                */
+               TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
+}
+
 static void
 tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
                    struct sock *sk)
@@ -2615,6 +2624,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                }
        }
 
+       /* RFC3168, section 6.1.1.1. ECN fallback */
+       if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
+               tcp_ecn_clear_syn(sk, skb);
+
        tcp_retrans_try_collapse(sk, skb, cur_mss);
 
        /* Make a copy, if the first transmission SKB clone we made