UBUNTU: Ubuntu-4.15.0-96.97

[mirror_ubuntu-bionic-kernel.git] / net / ipv4 / tcp_dctcp.c

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e65739859d0d8d9717b3204482a43..f0de9fb92f0d31160487ea933505913df86ce4a9 100644 (file)
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
        u32 dctcp_alpha;
        u32 next_seq;
        u32 ce_state;
-       u32 delayed_ack_reserved;
        u32 loss_cwnd;
 };
 
@@ -67,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-                "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -96,7 +90,6 @@ static void dctcp_init(struct sock *sk)
 
                ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
-               ca->delayed_ack_reserved = 0;
                ca->loss_cwnd = 0;
                ca->ce_state = 0;
 
@@ -131,23 +124,14 @@ 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);
 
-       /* State has changed from CE=0 to CE=1 and delayed
-        * ACK has not sent yet.
-        */
-       if (!ca->ce_state && ca->delayed_ack_reserved) {
-               u32 tmp_rcv_nxt;
-
-               /* Save current rcv_nxt. */
-               tmp_rcv_nxt = tp->rcv_nxt;
-
-               /* Generate previous ack with CE=0. */
-               tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-               tp->rcv_nxt = ca->prior_rcv_nxt;
-
-               tcp_send_ack(sk);
-
-               /* Recover current rcv_nxt. */
-               tp->rcv_nxt = tmp_rcv_nxt;
+       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);
+               tcp_enter_quickack_mode(sk, 1);
        }
 
        ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -161,23 +145,14 @@ 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);
 
-       /* State has changed from CE=1 to CE=0 and delayed
-        * ACK has not sent yet.
-        */
-       if (ca->ce_state && ca->delayed_ack_reserved) {
-               u32 tmp_rcv_nxt;
-
-               /* Save current rcv_nxt. */
-               tmp_rcv_nxt = tp->rcv_nxt;
-
-               /* Generate previous ack with CE=1. */
-               tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-               tp->rcv_nxt = ca->prior_rcv_nxt;
-
-               tcp_send_ack(sk);
-
-               /* Recover current rcv_nxt. */
-               tp->rcv_nxt = tmp_rcv_nxt;
+       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);
+               tcp_enter_quickack_mode(sk, 1);
        }
 
        ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -231,40 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
        }
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-       if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-               struct dctcp *ca = inet_csk_ca(sk);
+       struct dctcp *ca = inet_csk_ca(sk);
+       struct tcp_sock *tp = tcp_sk(sk);
 
-               /* If this extension is enabled, we clamp dctcp_alpha to
-                * max on packet loss; the motivation is that dctcp_alpha
-                * is an indicator to the extend of congestion and packet
-                * loss is an indicator of extreme congestion; setting
-                * this in practice turned out to be beneficial, and
-                * effectively assumes total congestion which reduces the
-                * window by half.
-                */
-               ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-       }
+       ca->loss_cwnd = tp->snd_cwnd;
+       tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
 }
 
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
+static void dctcp_state(struct sock *sk, u8 new_state)
 {
-       struct dctcp *ca = inet_csk_ca(sk);
-
-       switch (ev) {
-       case CA_EVENT_DELAYED_ACK:
-               if (!ca->delayed_ack_reserved)
-                       ca->delayed_ack_reserved = 1;
-               break;
-       case CA_EVENT_NON_DELAYED_ACK:
-               if (ca->delayed_ack_reserved)
-                       ca->delayed_ack_reserved = 0;
-               break;
-       default:
-               /* Don't care for the rest. */
-               break;
-       }
+       if (new_state == TCP_CA_Recovery &&
+           new_state != inet_csk(sk)->icsk_ca_state)
+               dctcp_react_to_loss(sk);
+       /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+        * one loss-adjustment per RTT.
+        */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -276,9 +234,8 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
        case CA_EVENT_ECN_NO_CE:
                dctcp_ce_state_1_to_0(sk);
                break;
-       case CA_EVENT_DELAYED_ACK:
-       case CA_EVENT_NON_DELAYED_ACK:
-               dctcp_update_ack_reserved(sk, ev);
+       case CA_EVENT_LOSS:
+               dctcp_react_to_loss(sk);
                break;
        default:
                /* Don't care for the rest. */