summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_dctcp.h
diff options
context:
space:
mode:
authorYuchung Cheng <ycheng@google.com>2018-10-09 01:32:20 +0300
committerDavid S. Miller <davem@davemloft.net>2018-10-11 08:26:00 +0300
commitffd177dea5c1ee5b717961d041df0778d58f50c0 (patch)
treebe10e3a3a741632cf00de77b29ae51c4f1787aea /net/ipv4/tcp_dctcp.h
parented792e28c4bd09e9a319d2ad914aa62982cb4c4a (diff)
downloadlinux-ffd177dea5c1ee5b717961d041df0778d58f50c0.tar.xz
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>
Diffstat (limited to 'net/ipv4/tcp_dctcp.h')
-rw-r--r--net/ipv4/tcp_dctcp.h40
1 files changed, 40 insertions, 0 deletions
diff --git a/net/ipv4/tcp_dctcp.h b/net/ipv4/tcp_dctcp.h
new file mode 100644
index 000000000000..d69a77cbd0c7
--- /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