diff mbox series

[v4,net-next,15/15] tcp: try to avoid safer when ACKs are thinned

Message ID 20250417230029.21905-16-chia-yu.chang@nokia-bell-labs.com (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series AccECN protocol patch series | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 20 this patch: 20
netdev/build_tools success Errors and warnings before: 26 (+2) this patch: 26 (+2)
netdev/cc_maintainers success CCed 9 of 9 maintainers
netdev/build_clang success Errors and warnings before: 33 this patch: 33
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 2055 this patch: 2055
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns WARNING: line length of 93 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 4 this patch: 4
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-04-18--09-00 (tests: 916)

Commit Message

Chia-Yu Chang (Nokia) April 17, 2025, 11 p.m. UTC 
From: Ilpo Järvinen <ij@kernel.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.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
 include/linux/tcp.h  |  1 +
 net/ipv4/tcp.c       |  4 +++-
 net/ipv4/tcp_input.c | 20 +++++++++++++++++++-
 3 files changed, 23 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 782e4dd58bf7..230f55b22a51 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -313,6 +313,7 @@  struct tcp_sock {
 		prev_ecnfield:2,/* ECN bits from the previous segment */
 		accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */
 		est_ecnfield:2;/* ECN field for AccECN delivered estimates */
+	u16	pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */
 	u64	accecn_opt_tstamp;	/* Last AccECN option sent timestamp */
 	u32	app_limited;	/* limited until "delivered" reaches this val */
 	u32	rcv_wnd;	/* Current receiver window		*/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8e3582c1b5bb..56b6467df18b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3371,6 +3371,7 @@  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));
@@ -5109,6 +5110,7 @@  static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ecn_bytes);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ce);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ecn_bytes);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pkts_acked_ewma);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, accecn_opt_tstamp);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
@@ -5117,7 +5119,7 @@  static void __init tcp_struct_check(void)
 	/* 32bit arches with 8byte alignment on u64 fields might need padding
 	 * before tcp_clock_cache.
 	 */
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 130 + 6);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 132 + 8);
 
 	/* RX read-write hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c6dac3c2d47a..5bdd82d3c201 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -689,6 +689,10 @@  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,
@@ -708,6 +712,19 @@  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)
@@ -756,7 +773,8 @@  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;
 }