tcp: refactor DCTCP ECN ACK handling

DCTCP has two parts - a new ECN signalling mechanism and the response
function to it. The first part can be used by other congestion
control for DCTCP-ECN deployed networks. This patch moves that part
into a separate tcp_dctcp.h to be used by other congestion control
module (like how Yeah uses Vegas algorithmas). For example, BBR is
experimenting such ECN signal currently
https://tinyurl.com/ietf-102-iccrg-bbr2

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index ca61e2a..cd4814f 100644 (file)
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -44,6 +44,7 @@
 #include <linux/mm.h>
 #include <net/tcp.h>
 #include <linux/inet_diag.h>
+#include "tcp_dctcp.h"
 
 #define DCTCP_MAX_ALPHA        1024U
 
@@ -118,54 +119,6 @@ static u32 dctcp_ssthresh(struct sock *sk)
        return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
-/* Minimal DCTP CE state machine:
- *
- * S:  0 <- last pkt was non-CE
- *     1 <- last pkt was CE
- */
-
-static void dctcp_ce_state_0_to_1(struct sock *sk)
-{
-       struct dctcp *ca = inet_csk_ca(sk);
-       struct tcp_sock *tp = tcp_sk(sk);
-
-       if (!ca->ce_state) {
-               /* State has changed from CE=0 to CE=1, force an immediate
-                * ACK to reflect the new CE state. If an ACK was delayed,
-                * send that first to reflect the prior CE state.
-                */
-               if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-                       __tcp_send_ack(sk, ca->prior_rcv_nxt);
-               inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
-       }
-
-       ca->prior_rcv_nxt = tp->rcv_nxt;
-       ca->ce_state = 1;
-
-       tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-}
-
-static void dctcp_ce_state_1_to_0(struct sock *sk)
-{
-       struct dctcp *ca = inet_csk_ca(sk);
-       struct tcp_sock *tp = tcp_sk(sk);
-
-       if (ca->ce_state) {
-               /* State has changed from CE=1 to CE=0, force an immediate
-                * ACK to reflect the new CE state. If an ACK was delayed,
-                * send that first to reflect the prior CE state.
-                */
-               if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-                       __tcp_send_ack(sk, ca->prior_rcv_nxt);
-               inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
-       }
-
-       ca->prior_rcv_nxt = tp->rcv_nxt;
-       ca->ce_state = 0;
-
-       tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-}
-
 static void dctcp_update_alpha(struct sock *sk, u32 flags)
 {
        const struct tcp_sock *tp = tcp_sk(sk);
@@ -230,12 +183,12 @@ static void dctcp_state(struct sock *sk, u8 new_state)
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 {
+       struct dctcp *ca = inet_csk_ca(sk);
+
        switch (ev) {
        case CA_EVENT_ECN_IS_CE:
-               dctcp_ce_state_0_to_1(sk);
-               break;
        case CA_EVENT_ECN_NO_CE:
-               dctcp_ce_state_1_to_0(sk);
+               dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
                break;
        default:
                /* Don't care for the rest. */

diff --git a/net/ipv4/tcp_dctcp.h b/net/ipv4/tcp_dctcp.h
new file mode 100644 (file)
index 0000000..d69a77c
--- /dev/null
+++ b/net/ipv4/tcp_dctcp.h
@@ -0,0 +1,40 @@
+#ifndef _TCP_DCTCP_H
+#define _TCP_DCTCP_H
+
+static inline void dctcp_ece_ack_cwr(struct sock *sk, u32 ce_state)
+{
+       struct tcp_sock *tp = tcp_sk(sk);
+
+       if (ce_state == 1)
+               tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+       else
+               tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S:  0 <- last pkt was non-CE
+ *     1 <- last pkt was CE
+ */
+static inline void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+                                       u32 *prior_rcv_nxt, u32 *ce_state)
+{
+       u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
+
+       if (*ce_state != new_ce_state) {
+               /* CE state has changed, force an immediate ACK to
+                * reflect the new CE state. If an ACK was delayed,
+                * send that first to reflect the prior CE state.
+                */
+               if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+                       dctcp_ece_ack_cwr(sk, *ce_state);
+                       __tcp_send_ack(sk, *prior_rcv_nxt);
+               }
+               inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+       }
+       *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt;
+       *ce_state = new_ce_state;
+       dctcp_ece_ack_cwr(sk, new_ce_state);
+}
+
+#endif