diff mbox series

[v5,net-next,05/15] tcp: accecn: add AccECN rx byte counters

Message ID 20250422153602.54787-6-chia-yu.chang@nokia-bell-labs.com
State New
Headers show
Series AccECN protocol patch series | expand

Commit Message

Chia-Yu Chang (Nokia) April 22, 2025, 3:35 p.m. UTC 
From: Ilpo Järvinen <ij@kernel.org>

These counters track IP ECN field payload byte sums for all
arriving (acceptable) packets. The AccECN option (added by
a later patch in the series) echoes these counters back to
sender side.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
 include/linux/tcp.h      |  1 +
 include/net/tcp.h        | 18 +++++++++++++++++-
 net/ipv4/tcp.c           |  3 ++-
 net/ipv4/tcp_input.c     | 13 +++++++++----
 net/ipv4/tcp_minisocks.c |  3 ++-
 5 files changed, 31 insertions(+), 7 deletions(-)

Comments

Paolo Abeni April 29, 2025, 10:45 a.m. UTC | #1 
On 4/22/25 5:35 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index af38fff24aa4..9cbfefd693e3 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -303,6 +303,7 @@ struct tcp_sock {
>  	u32	delivered;	/* Total data packets delivered incl. rexmits */
>  	u32	delivered_ce;	/* Like the above but only ECE marked packets */
>  	u32	received_ce;	/* Like the above but for rcvd CE marked pkts */
> +	u32	received_ecn_bytes[3];

I'm unsure if this should belong to the fast-path area. In any case
AFAICS this is the wrong location, as the fields are only written and
only in the rx path, while the above chunk belongs to the
tcp_sock_write_txrx group.

/P
diff mbox series

Patch

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index af38fff24aa4..9cbfefd693e3 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -303,6 +303,7 @@  struct tcp_sock {
 	u32	delivered;	/* Total data packets delivered incl. rexmits */
 	u32	delivered_ce;	/* Like the above but only ECE marked packets */
 	u32	received_ce;	/* Like the above but for rcvd CE marked pkts */
+	u32	received_ecn_bytes[3];
 	u8	received_ce_pending:4, /* Not yet transmit cnt of received_ce */
 		unused2:4;
 	u32	app_limited;	/* limited until "delivered" reaches this val */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f36a1a3d538f..6ffa4ae085db 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -467,7 +467,8 @@  static inline int tcp_accecn_extract_syn_ect(u8 ace)
 bool tcp_accecn_validate_syn_feedback(struct sock *sk, u8 ace, u8 sent_ect);
 void tcp_accecn_third_ack(struct sock *sk, const struct sk_buff *skb,
 			  u8 syn_ect_snt);
-void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb);
+void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
+			       u32 payload_len);
 
 enum tcp_tw_status {
 	TCP_TW_SUCCESS = 0,
@@ -1035,11 +1036,26 @@  static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
  * See draft-ietf-tcpm-accurate-ecn for the latest values.
  */
 #define TCP_ACCECN_CEP_INIT_OFFSET 5
+#define TCP_ACCECN_E1B_INIT_OFFSET 1
+#define TCP_ACCECN_E0B_INIT_OFFSET 1
+#define TCP_ACCECN_CEB_INIT_OFFSET 0
+
+static inline void __tcp_accecn_init_bytes_counters(int *counter_array)
+{
+	BUILD_BUG_ON(INET_ECN_ECT_1 != 0x1);
+	BUILD_BUG_ON(INET_ECN_ECT_0 != 0x2);
+	BUILD_BUG_ON(INET_ECN_CE != 0x3);
+
+	counter_array[INET_ECN_ECT_1 - 1] = 0;
+	counter_array[INET_ECN_ECT_0 - 1] = 0;
+	counter_array[INET_ECN_CE - 1] = 0;
+}
 
 static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
 {
 	tp->received_ce = 0;
 	tp->received_ce_pending = 0;
+	__tcp_accecn_init_bytes_counters(tp->received_ecn_bytes);
 }
 
 /* State flags for sacked in struct tcp_skb_cb */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 73f8cc715bff..1e21bdf43f23 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5092,6 +5092,7 @@  static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce);
 	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, app_limited);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
@@ -5099,7 +5100,7 @@  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, 97 + 7);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 109 + 7);
 
 	/* 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 cc34664805f8..c017e342f092 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6106,7 +6106,8 @@  static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 }
 
 /* Updates Accurate ECN received counters from the received IP ECN field */
-void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb)
+void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
+			       u32 payload_len)
 {
 	u8 ecnfield = TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK;
 	u8 is_ce = INET_ECN_is_ce(ecnfield);
@@ -6121,6 +6122,9 @@  void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb)
 		tp->received_ce += pcount;
 		tp->received_ce_pending = min(tp->received_ce_pending + pcount,
 					      0xfU);
+
+		if (payload_len > 0)
+			tp->received_ecn_bytes[ecnfield - 1] += payload_len;
 	}
 }
 
@@ -6398,7 +6402,7 @@  void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 					flag |= __tcp_replace_ts_recent(tp,
 									delta);
 
-				tcp_ecn_received_counters(sk, skb);
+				tcp_ecn_received_counters(sk, skb, 0);
 
 				/* We know that such packets are checksummed
 				 * on entry.
@@ -6444,7 +6448,8 @@  void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			/* Bulk data transfer: receiver */
 			tcp_cleanup_skb(skb);
 			__skb_pull(skb, tcp_header_len);
-			tcp_ecn_received_counters(sk, skb);
+			tcp_ecn_received_counters(sk, skb,
+						  len - tcp_header_len);
 			eaten = tcp_queue_rcv(sk, skb, &fragstolen);
 
 			tcp_event_data_recv(sk, skb);
@@ -6491,7 +6496,7 @@  void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			tcp_accecn_third_ack(sk, skb, tp->syn_ect_snt);
 		tcp_fast_path_on(tp);
 	}
-	tcp_ecn_received_counters(sk, skb);
+	tcp_ecn_received_counters(sk, skb, len - th->doff * 4);
 
 	reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT);
 	if ((int)reason < 0) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 779a206a5ca6..3f8225bae49f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -497,10 +497,11 @@  static void tcp_ecn_openreq_child(struct sock *sk,
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (treq->accecn_ok) {
+		const struct tcphdr *th = (const struct tcphdr *)skb->data;
 		tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
 		tp->syn_ect_snt = treq->syn_ect_snt;
 		tcp_accecn_third_ack(sk, skb, treq->syn_ect_snt);
-		tcp_ecn_received_counters(sk, skb);
+		tcp_ecn_received_counters(sk, skb, skb->len - th->doff * 4);
 	} else {
 		tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
 				     TCP_ECN_MODE_RFC3168 :