| 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: <20250621193737.16593-16-chia-yu.chang@nokia-bell-labs.com>
Date: Sat, 21 Jun 2025 21:37:37 +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 v9 net-next 15/15] tcp: try to avoid safer when ACKs are thinned
From: Ilpo Järvinen <ij@...nel.org>
Add newly acked pkts EWMA. When ACK thinning occurs, select
between safer and unsafe cep delta in AccECN processing based
on it. If the packets ACKed per ACK tends to be large, don't
conservatively assume ACE field overflow.
This patch uses the existing 2-byte holes in the rx group for new
u16 variables withtout creating more holes. Below are the pahole
outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ecn_bytes[3]; /* 2744 12 */
/* XXX 4 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...]
/* size: 3264, cachelines: 51, members: 177 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ecn_bytes[3]; /* 2744 12 */
u16 pkts_acked_ewma; /* 2756 2 */
/* XXX 2 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...]
/* size: 3264, cachelines: 51, members: 178 */
}
Signed-off-by: Ilpo Järvinen <ij@...nel.org>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
---
.../networking/net_cachelines/tcp_sock.rst | 1 +
include/linux/tcp.h | 1 +
net/ipv4/tcp.c | 2 ++
net/ipv4/tcp_input.c | 20 ++++++++++++++++++-
4 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 88c668f9c68b..f431ff1eb932 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -105,6 +105,7 @@ u32 received_ce read_mostly read_w
u32[3] received_ecn_bytes read_mostly read_write
u8:4 received_ce_pending read_mostly read_write
u32[3] delivered_ecn_bytes read_write
+u16 pkts_acked_ewma read_write
u8:2 syn_ect_snt write_mostly read_write
u8:2 syn_ect_rcv read_mostly read_write
u8:1 wait_third_ack read_write
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 8609fb138108..c3b9ecc3f2e2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -345,6 +345,7 @@ struct tcp_sock {
u32 rate_interval_us; /* saved rate sample: time elapsed */
u32 rcv_rtt_last_tsecr;
u32 delivered_ecn_bytes[3];
+ u16 pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */
u64 first_tx_mstamp; /* start of window send phase */
u64 delivered_mstamp; /* time we reached "delivered" */
u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a9e30c72d71b..40fdfba1c04a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3399,6 +3399,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tcp_accecn_init_counters(tp);
tp->prev_ecnfield = 0;
tp->accecn_opt_tstamp = 0;
+ tp->pkts_acked_ewma = 0;
if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release)
icsk->icsk_ca_ops->release(sk);
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
@@ -5159,6 +5160,7 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, pkts_acked_ewma);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 97b5fe52d8fd..f15ebee4a641 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -714,6 +714,10 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
tcp_count_delivered_ce(tp, delivered);
}
+#define PKTS_ACKED_WEIGHT 6
+#define PKTS_ACKED_PREC 6
+#define ACK_COMP_THRESH 4
+
/* Returns the ECN CE delta */
static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
u32 delivered_pkts, u32 delivered_bytes,
@@ -733,6 +737,19 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
opt_deltas_valid = tcp_accecn_process_option(tp, skb,
delivered_bytes, flag);
+ if (delivered_pkts) {
+ if (!tp->pkts_acked_ewma) {
+ tp->pkts_acked_ewma = delivered_pkts << PKTS_ACKED_PREC;
+ } else {
+ u32 ewma = tp->pkts_acked_ewma;
+
+ ewma = (((ewma << PKTS_ACKED_WEIGHT) - ewma) +
+ (delivered_pkts << PKTS_ACKED_PREC)) >>
+ PKTS_ACKED_WEIGHT;
+ tp->pkts_acked_ewma = min_t(u32, ewma, 0xFFFFU);
+ }
+ }
+
if (!(flag & FLAG_SLOWPATH)) {
/* AccECN counter might overflow on large ACKs */
if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK)
@@ -781,7 +798,8 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
if (d_ceb <
safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT)
return delta;
- }
+ } else if (tp->pkts_acked_ewma > (ACK_COMP_THRESH << PKTS_ACKED_PREC))
+ return delta;
return safe_delta;
}
--
2.34.1
Powered by blists - more mailing lists