From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795114009; b=tG06ZFMMehG//IgRz8dHxSUjUdG2f7+nZBROoqkkJOL+bx7GGDVFh7ClU9S+Zp1nQkYo 0JfKcn46arf9RAZcD94bwHkERSrR3bTr93e4806dw3jnY7k0IUsNWv4fbouiZmhMVkxhj /OYXxwn37L5Az23qznqBb0NwG4335UexIpkbKSuPWUWvni3hDXEpYf46wUbJRddXU2Jef bZ3q7OXleUEU6VxR3HrZ4S+AT0mA2B4IokeK4vFNP7C4uvMJBWmg/m0c4s/tqhsi6+7fb Bpf4yQw20l3t8PEgHj+L6ACQ7M6VS8OtPmlZT5YvsJCrvV1u55eGWZnYmG4B0YMyYew== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795114009; h=Received:DKIM-Signature:Received:X-Gm-Message-State:X-Received: MIME-Version:References:In-Reply-To:From:Date: X-Gmail-Original-Message-ID:X-Gm-Features:Message-ID:Subject:To:Cc: Content-Type:Content-Transfer-Encoding; bh=tpiPU8++XfQSCP9ULe9LXdelFvKTKcALUKX3kHYjn+4=; b=i2gZ1TERFWr1tiOSq1d2K1//XAY9qnbPZBBc3zD6R/pMtlvf/dUCuH4TZU22+Db0Iq93 5T0eQNeQTKyh0U6h10dkOO3WLX87VbjFtyBY2I6ldygakHyNdwNlrPQxWtltyxsS3lzpb yjl9mcYKKJdi4eZySm/X/AgryxSfAMZ8Gd3ZSsfJ0f03tUdoZCnTPnMJ6RIszAUhRY11c pLUfCw06KNfmqzNn7oRy6jfUvIflUD/tUFxZUEaUZGe6rp+Hd8T6RlwDI45mF2jmj52Ve nEaf85yezdxMZ8C0SiBCzUv386O9Rj4Ezc8xgkInLWopm3g6Axgt4bGYwd8uqIeGMGQ== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=fUNG9Hmm; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 4F7A1606A326 for ; Thu, 19 Nov 2026 18:46:49 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=fUNG9Hmm Received: by smtp.kernel.org (Postfix) with ESMTPSA id 1200E1F000D0 for ; Thu, 19 Nov 2026 18:46:49 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1795114009; bh=tpiPU8++XfQSCP9ULe9LXdelFvKTKcALUKX3kHYjn+4=; h=References:In-Reply-To:From:Date:Subject:To:Cc; b=fUNG9Hmmpnw906AVNfBTDC24dtOuJFtFSrE4knpssFOSWboTWgU/TUr/Fzor9QkD5 Z1wC8SKht2FYjEBPA2qVVbDmz61NVZrfbJyHVTloXjzmVbsgycNAUugiLyzT0gz53u afA9XGO7x/cjK8lYSUlAqH4E8JshyiZeklTcrQw8uVnxN2zq4WX+Wwvm5bhJe4k93D 3lhw/vnDiYT9uJZBUrR+saoY3Qr1RwzooKtI9/H8Vl8d5tCdbR1MNhcj9VS4NRz7Bm +d9GUoxbMuBhqZTrCS0QQa77gmAPWaIHzxOzFBmaBOyWZG74QNOq7GApeAoJhITJrR CFcG04gVC5LOA== Received: by mail-oa1-f44.google.com with SMTP id 586e51a60fabf-4911df1e196so89036fac.1 for ; Thu, 19 Nov 2026 10:46:49 -0800 (PST) X-Gm-Message-State: APuU4Z+wkK2Y4+xmgJohzspXHUanBziT2ypewlC9a2m91XscdLRRzktC iuQHkv9Zm2AzayKMLkKYdjLfg8BEFsToZ/uq9gTKU2Qa2qw/BkjsOGE+ODwFXfbJgI2PHq37Bxt ltQdxFjVA6w42fCAz9kuT2/ialm9ay3A= X-Received: by 2002:a05:6870:9d98:b0:442:175:cea7 with SMTP id 586e51a60fabf-4bc7beb0334mr556077fac.1.1795114008363; Thu, 19 Nov 2026 10:46:48 -0800 (PST) X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 References: <20261119180143.2912138-1-chia-yu.chang@nokia-bell-labs.com> <20261119180143.2912138-2-chia-yu.chang@nokia-bell-labs.com> In-Reply-To: <20261119180143.2912138-2-chia-yu.chang@nokia-bell-labs.com> From: Eric Dumazet Date: Thu, 19 Nov 2026 19:46:37 +0100 X-Gmail-Original-Message-ID: X-Gm-Features: AclHuK-tsqmjCJGsuoHtwqpC8EpbRAKIkGBsk_sdnPDFvh8WOjjREis7vqFOKyo Message-ID: Subject: Re: [PATCH net-next v4 1/4] tcp: export CE count in rate_sample To: chia-yu.chang@nokia-bell-labs.com Cc: linux-kernel@vger.kernel.org, kuba@kernel.org, netdev@vger.kernel.org, pabeni@redhat.com, davem@davemloft.net, kuniyu@google.com, ij@kernel.org, ncardwell@google.com, koen0607@gmail.com, g.white@cablelabs.com, ingemar.s.johansson@ericsson.com, mirja.kuehlewind@ericsson.com, cheshire@apple.com, rs.ietf@gmx.at, Jason_Livingood@comcast.com, vidhi_goel@apple.com, Mike_Rudolph@comcast.com, Jeff_Howe@comcast.com, srichard@netapp.com, Olivier Tilmans Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Le jeu. 19 nov. 2026 =C3=A0 19:01, a = =C3=A9crit : > > From: Ilpo J=C3=A4rvinen > > Store the number of newly ACKed/SACKed CE-marked packets in rate_sample. > This will be used by upcoming congestion control algorithms, e.g., > TCP Prague, that need access to AccECN-derived congestion info. > > For RFC3168 ECN mode, acked_sacked_ce equals delivered when FLAG_ECE > is present. For AccECN mode, it carries the derived CE-marked packets > from AccECN options or ACE field based on RFC9768. > > Signed-off-by: Ilpo J=C3=A4rvinen > Co-developed-by: Olivier Tilmans > Signed-off-by: Olivier Tilmans > Co-developed-by: Chia-Yu Chang > Signed-off-by: Chia-Yu Chang > > -- > v3: > - Improve commit message > - Rename ece_delta to acked_sacked_ce > - Remove redundant rate_sample initializer > --- > include/net/tcp.h | 1 + > net/ipv4/tcp_input.c | 40 +++++++++++++++++++--------------------- > 2 files changed, 20 insertions(+), 21 deletions(-) > > diff --git a/include/net/tcp.h b/include/net/tcp.h > index 25d11fab1b03..4b1159e6c125 100644 > --- a/include/net/tcp.h > +++ b/include/net/tcp.h > @@ -1353,6 +1353,7 @@ struct rate_sample { > long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ > int losses; /* number of packets marked lost upon ACK= */ > u32 acked_sacked; /* number of packets newly (S)ACKed upon = ACK */ > + u32 acked_sacked_ce; /* number of packets ECE-marked upon ACK = */ I presume you meant "CE-marked" instead of "ECE-marked" > u32 prior_in_flight; /* in flight before this ACK */ > u32 last_end_seq; /* end_seq of most recently ACKed packet = */ > bool is_app_limited; /* is sample from packet with bubble in p= ipe? */ > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c > index 67e4aa73bd6a..72826cafa246 100644 > --- a/net/ipv4/tcp_input.c > +++ b/net/ipv4/tcp_input.c > @@ -616,9 +616,10 @@ static u32 __tcp_accecn_process(struct sock *sk, con= st struct sk_buff *skb, > return safe_delta; > } > > -static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb= , > - u32 delivered_pkts, u32 delivered_bytes, > - u64 prior_bytes_acked, int *flag) > +static void tcp_accecn_process(struct sock *sk, struct rate_sample *rs, > + const struct sk_buff *skb, u32 delivered_p= kts, > + u32 delivered_bytes, u64 prior_bytes_acked= , > + int *flag) > { > struct tcp_sock *tp =3D tcp_sk(sk); > u32 delta; > @@ -628,11 +629,11 @@ static u32 tcp_accecn_process(struct sock *sk, cons= t struct sk_buff *skb, > if (delta > 0) { > tcp_count_delivered_ce(tp, delta); > *flag |=3D FLAG_ECE; > + rs->acked_sacked_ce =3D delta; > /* Recalculate header predictor */ > if (tp->pred_flags) > tcp_fast_path_on(tp); > } > - return delta; > } > > /* Buffer size and advertised window tuning. > @@ -4248,8 +4249,8 @@ static void tcp_xmit_recovery(struct sock *sk, int = rexmit) > } > > /* Returns the number of packets newly acked or sacked by the current AC= K */ > -static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, > - u32 ecn_count, int flag) > +static u32 tcp_newly_delivered(struct sock *sk, struct rate_sample *rs, > + u32 prior_delivered, int flag) > { > const struct net *net =3D sock_net(sk); > struct tcp_sock *tp =3D tcp_sk(sk); > @@ -4260,8 +4261,9 @@ static u32 tcp_newly_delivered(struct sock *sk, u32= prior_delivered, > > if (flag & FLAG_ECE) { > if (tcp_ecn_mode_rfc3168(tp)) > - ecn_count =3D delivered; > - NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, ecn_count); > + rs->acked_sacked_ce =3D delivered; > + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, > + rs->acked_sacked_ce); In RFC 3168 mode this is every packet delivered by an ACK carrying ECE, not the number of CE-marked packets. This was fine for a MIB counter, but once exposed to congestion control modules it should be documented in the field comment, especially since rate_sample already has delivered_ce with a different meaning. > } > > return delivered; > @@ -4327,7 +4329,6 @@ static int tcp_ack(struct sock *sk, const struct sk= _buff *skb, int flag) > u32 delivered =3D tp->delivered; > u32 lost =3D tp->lost; > int rexmit =3D REXMIT_NONE; /* Flag to (re)transmit to recover lo= sses */ > - u32 ecn_count =3D 0; /* Did we receive ECE/an AccECN ACE u= pdate? */ > u32 prior_fack; > > sack_state.first_sackt =3D 0; > @@ -4441,10 +4442,9 @@ static int tcp_ack(struct sock *sk, const struct s= k_buff *skb, int flag) > tcp_rack_update_reo_wnd(sk, &rs); > > if (tcp_ecn_mode_accecn(tp)) > - ecn_count =3D tcp_accecn_process(sk, skb, > - tp->delivered - delivered, > - sack_state.delivered_bytes= , > - prior_bytes_acked, &flag); > + tcp_accecn_process(sk, &rs, skb, tp->delivered - delivere= d, > + sack_state.delivered_bytes, > + prior_bytes_acked, &flag); > > tcp_in_ack_event(sk, flag); > > @@ -4470,7 +4470,7 @@ static int tcp_ack(struct sock *sk, const struct sk= _buff *skb, int flag) > if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) > sk_dst_confirm(sk); > > - delivered =3D tcp_newly_delivered(sk, delivered, ecn_count, flag)= ; > + delivered =3D tcp_newly_delivered(sk, &rs, delivered, flag); > > lost =3D tp->lost - lost; /* freshly marked lost = */ > rs.is_ack_delayed =3D !!(flag & FLAG_ACK_MAYBE_DELAYED); > @@ -4481,17 +4481,15 @@ static int tcp_ack(struct sock *sk, const struct = sk_buff *skb, int flag) > > no_queue: > if (tcp_ecn_mode_accecn(tp)) > - ecn_count =3D tcp_accecn_process(sk, skb, > - tp->delivered - delivered, > - sack_state.delivered_bytes= , > - prior_bytes_acked, &flag); > - > + tcp_accecn_process(sk, &rs, skb, tp->delivered - delivere= d, > + sack_state.delivered_bytes, > + prior_bytes_acked, &flag); > tcp_in_ack_event(sk, flag); > /* If data was DSACKed, see if we can undo a cwnd reduction. */ > if (flag & FLAG_DSACKING_ACK) { > tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &fla= g, > &rexmit); > - tcp_newly_delivered(sk, delivered, ecn_count, flag); > + tcp_newly_delivered(sk, &rs, delivered, flag); > } > /* If this ack opens up a zero window, clear backoff. It was > * being used to time the probes, and is probably far higher than > @@ -4518,7 +4516,7 @@ static int tcp_ack(struct sock *sk, const struct sk= _buff *skb, int flag) > &sack_state); > tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &fla= g, > &rexmit); > - tcp_newly_delivered(sk, delivered, ecn_count, flag); > + tcp_newly_delivered(sk, &rs, delivered, flag); > tcp_xmit_recovery(sk, rexmit); > } > > -- > 2.34.1 >