| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20250927084803.17784-5-chia-yu.chang@nokia-bell-labs.com>
Date: Sat, 27 Sep 2025 10:47:55 +0200
From: chia-yu.chang@...ia-bell-labs.com
To: pabeni@...hat.com,
edumazet@...gle.com,
linux-doc@...r.kernel.org,
corbet@....net,
horms@...nel.org,
dsahern@...nel.org,
kuniyu@...zon.com,
bpf@...r.kernel.org,
netdev@...r.kernel.org,
dave.taht@...il.com,
jhs@...atatu.com,
kuba@...nel.org,
stephen@...workplumber.org,
xiyou.wangcong@...il.com,
jiri@...nulli.us,
davem@...emloft.net,
andrew+netdev@...n.ch,
donald.hunter@...il.com,
ast@...erby.net,
liuhangbin@...il.com,
shuah@...nel.org,
linux-kselftest@...r.kernel.org,
ij@...nel.org,
ncardwell@...gle.com,
koen.de_schepper@...ia-bell-labs.com,
g.white@...lelabs.com,
ingemar.s.johansson@...csson.com,
mirja.kuehlewind@...csson.com,
cheshire@...le.com,
rs.ietf@....at,
Jason_Livingood@...cast.com,
vidhi_goel@...le.com
Cc: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
Subject: [PATCH v3 net-next 04/12] tcp: disable RFC3168 fallback identifier for CC modules
From: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
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 <chia-yu.chang@...ia-bell-labs.com>
---
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 cb8901e02ccc..b7f52175e367 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1194,8 +1194,11 @@ 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;
@@ -1334,6 +1337,13 @@ 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 2d58fc96677b..5317d471a6fb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6817,7 +6817,7 @@ 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
Powered by blists - more mailing lists