From: Chia-Yu Chang <[email protected]>

When AccECN is not successfully negociated for a TCP flow, it defaults
fallback to classic ECN (RFC3168). However, L4S service will fallback
to non-ECN.

This patch enables congestion control module to control whether it
should not fallback to classic ECN after unsuccessful AccECN negotiation.
A new CA module flag (TCP_CONG_NO_FALLBACK_RFC3168) identifies this
behavior expected by the CA.

Signed-off-by: Chia-Yu Chang <[email protected]>

---
v3:
- Add empty line between variable declarations and code.
---
 include/net/tcp.h        | 12 +++++++++++-
 include/net/tcp_ecn.h    | 11 ++++++++---
 net/ipv4/tcp_input.c     |  2 +-
 net/ipv4/tcp_minisocks.c |  7 ++++---
 4 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8467c83e4aee..08ac4433535f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1195,8 +1195,11 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CONG_NEEDS_ACCECN          BIT(2)
 /* Use ECT(1) instead of ECT(0) while the CA is uninitialized */
 #define TCP_CONG_WANTS_ECT_1           BIT(3)
+/* Cannot fallback to RFC3168 during AccECN negotiation */
+#define TCP_CONG_NO_FALLBACK_RFC3168   BIT(4)
 #define TCP_CONG_MASK  (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
-                       TCP_CONG_NEEDS_ACCECN | TCP_CONG_WANTS_ECT_1)
+                       TCP_CONG_NEEDS_ACCECN | TCP_CONG_WANTS_ECT_1 | \
+                       TCP_CONG_NO_FALLBACK_RFC3168)
 
 union tcp_cc_info;
 
@@ -1335,6 +1338,13 @@ static inline bool tcp_ca_needs_accecn(const struct sock 
*sk)
        return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN;
 }
 
+static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk)
+{
+       const struct inet_connection_sock *icsk = inet_csk(sk);
+
+       return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168;
+}
+
 static inline bool tcp_ca_wants_ect_1(const struct sock *sk)
 {
        const struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index 0cc698a8438c..a7ba21d298ff 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -507,7 +507,9 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, 
const struct sk_buff *skb
                 * | ECN    | AccECN | 0   0   1  | Classic ECN |
                 * +========+========+============+=============+
                 */
-               if (tcp_ecn_mode_pending(tp))
+               if (tcp_ca_no_fallback_rfc3168(sk))
+                       tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
+               else if (tcp_ecn_mode_pending(tp))
                        /* Downgrade from AccECN, or requested initially */
                        tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
                break;
@@ -531,9 +533,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, 
const struct sk_buff *skb
        }
 }
 
-static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr 
*th,
+static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th,
                                   const struct sk_buff *skb)
 {
+       struct tcp_sock *tp = tcp_sk(sk);
+
        if (tcp_ecn_mode_pending(tp)) {
                if (!tcp_accecn_syn_requested(th)) {
                        /* Downgrade to classic ECN feedback */
@@ -545,7 +549,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, 
const struct tcphdr *th,
                        tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
                }
        }
-       if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr))
+       if (tcp_ecn_mode_rfc3168(tp) &&
+           (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk)))
                tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 27fba14bb3b2..4a6abf536dbe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6828,7 +6828,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, 
struct sk_buff *skb,
                tp->snd_wl1    = TCP_SKB_CB(skb)->seq;
                tp->max_window = tp->snd_wnd;
 
-               tcp_ecn_rcv_syn(tp, th, skb);
+               tcp_ecn_rcv_syn(sk, th, skb);
 
                tcp_mtup_init(sk);
                tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2ec8c6f1cdcc..1fade94813c6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -488,9 +488,10 @@ static void tcp_ecn_openreq_child(struct sock *sk,
                tp->accecn_opt_demand = 1;
                tcp_ecn_received_counters_payload(sk, skb);
        } else {
-               tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
-                                    TCP_ECN_MODE_RFC3168 :
-                                    TCP_ECN_DISABLED);
+               if (inet_rsk(req)->ecn_ok && !tcp_ca_no_fallback_rfc3168(sk))
+                       tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+               else
+                       tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
        }
 }
 
-- 
2.34.1


Reply via email to