diff options
-rw-r--r-- | Documentation/networking/dctcp.txt | 1 | ||||
-rw-r--r-- | Documentation/networking/ip-sysctl.txt | 9 | ||||
-rw-r--r-- | include/net/netns/ipv4.h | 2 | ||||
-rw-r--r-- | include/net/tcp.h | 2 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 5 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 13 |
7 files changed, 38 insertions, 1 deletions
diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt index 0d5dfbc..13a8577 100644 --- 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 5095c63..cb083e0 100644 --- 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 614a49b..6848b8b 100644 --- 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 0d85223..2bb2bad 100644 --- 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 c3852a7..841de32 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -821,6 +821,13 @@ static struct ctl_table ipv4_net_table[] = { .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), .data = &init_net.ipv4.ip_local_ports.range, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 91cb476..0cc4b5a 100644 --- 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 08c2cc4..e29d43b 100644 --- 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 |