net: tcp: more detailed ACK events and events for CE marked packets

DataCenter TCP (DCTCP) determines cwnd growth based on ECN information
and ACK properties, e.g. ACK that updates window is treated differently
than DUPACK.

Also DCTCP needs information whether ACK was delayed ACK. Furthermore,
DCTCP also implements a CE state machine that keeps track of CE markings
of incoming packets.

Therefore, extend the congestion control framework to provide these
event types, so that DCTCP can be properly implemented as a normal
congestion algorithm module outside of the core stack.

Joint work with Daniel Borkmann and Glenn Judd.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7ec6a28..1f57c53 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -763,10 +763,17 @@ enum tcp_ca_event {
        CA_EVENT_CWND_RESTART,  /* congestion window restart */
        CA_EVENT_COMPLETE_CWR,  /* end of congestion recovery */
        CA_EVENT_LOSS,          /* loss timeout */
+       CA_EVENT_ECN_NO_CE,     /* ECT set, but not CE marked */
+       CA_EVENT_ECN_IS_CE,     /* received CE marked IP packet */
+       CA_EVENT_DELAYED_ACK,   /* Delayed ack is sent */
+       CA_EVENT_NON_DELAYED_ACK,
 };
 
+/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
 enum tcp_ca_ack_event_flags {
-       CA_ACK_SLOWPATH = (1 << 0),
+       CA_ACK_SLOWPATH         = (1 << 0),     /* In slow path processing */
+       CA_ACK_WIN_UPDATE       = (1 << 1),     /* ACK updated window */
+       CA_ACK_ECE              = (1 << 2),     /* ECE bit is set on ack */
 };
 
 /*

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8a38774..fc13317 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -233,14 +233,21 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s
                        tcp_enter_quickack_mode((struct sock *)tp);
                break;
        case INET_ECN_CE:
+               if (tcp_ca_needs_ecn((struct sock *)tp))
+                       tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+
                if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
                        /* Better not delay acks, sender can have a very low cwnd */
                        tcp_enter_quickack_mode((struct sock *)tp);
                        tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
                }
-               /* fallinto */
+               tp->ecn_flags |= TCP_ECN_SEEN;
+               break;
        default:
+               if (tcp_ca_needs_ecn((struct sock *)tp))
+                       tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
                tp->ecn_flags |= TCP_ECN_SEEN;
+               break;
        }
 }
 
@@ -3429,10 +3436,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
                tp->snd_una = ack;
                flag |= FLAG_WIN_UPDATE;
 
-               tcp_in_ack_event(sk, 0);
+               tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
 
                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
        } else {
+               u32 ack_ev_flags = CA_ACK_SLOWPATH;
+
                if (ack_seq != TCP_SKB_CB(skb)->end_seq)
                        flag |= FLAG_DATA;
                else
@@ -3444,10 +3453,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
                        flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
                                                        &sack_rtt_us);
 
-               if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
+               if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) {
                        flag |= FLAG_ECE;
+                       ack_ev_flags |= CA_ACK_ECE;
+               }
+
+               if (flag & FLAG_WIN_UPDATE)
+                       ack_ev_flags |= CA_ACK_WIN_UPDATE;
 
-               tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
+               tcp_in_ack_event(sk, ack_ev_flags);
        }
 
        /* We passed data and got it acked, remove any soft error

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20e7327..124f9e4 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3130,6 +3130,8 @@ void tcp_send_delayed_ack(struct sock *sk)
        int ato = icsk->icsk_ack.ato;
        unsigned long timeout;
 
+       tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
+
        if (ato > TCP_DELACK_MIN) {
                const struct tcp_sock *tp = tcp_sk(sk);
                int max_ato = HZ / 2;
@@ -3186,6 +3188,8 @@ void tcp_send_ack(struct sock *sk)
        if (sk->sk_state == TCP_CLOSE)
                return;
 
+       tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
+
        /* We are not putting this on the write queue, so
         * tcp_transmit_skb() will set the ownership to this
         * sock.