Merge branch 'accecn-protocol-patch-series'

Chia-Yu Chang says:

====================
AccECN protocol patch series

Please find the v19 AccECN protocol patch series, which covers the core
functionality of Accurate ECN, AccECN negotiation, AccECN TCP options,
and AccECN failure handling. The Accurate ECN draft can be found in
https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28, and it
will be RFC9768.

This patch series is part of the full AccECN patch series, which is available at
https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/
---
Chia-Yu Chang (3):
  tcp: accecn: AccECN option send control
  tcp: accecn: AccECN option failure handling
  tcp: accecn: try to fit AccECN option with SACK

Ilpo Järvinen (7):
  tcp: AccECN core
  tcp: accecn: AccECN negotiation
  tcp: accecn: add AccECN rx byte counters
  tcp: accecn: AccECN needs to know delivered bytes
  tcp: sack option handling improvements
  tcp: accecn: AccECN option
  tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics

 Documentation/networking/ip-sysctl.rst        |  55 +-
 .../networking/net_cachelines/tcp_sock.rst    |  12 +
 include/linux/tcp.h                           |  28 +-
 include/net/netns/ipv4.h                      |   2 +
 include/net/tcp.h                             |  33 ++
 include/net/tcp_ecn.h                         | 554 +++++++++++++++++-
 include/uapi/linux/tcp.h                      |   9 +
 net/ipv4/syncookies.c                         |   4 +
 net/ipv4/sysctl_net_ipv4.c                    |  19 +
 net/ipv4/tcp.c                                |  30 +-
 net/ipv4/tcp_input.c                          | 318 +++++++++-
 net/ipv4/tcp_ipv4.c                           |   8 +-
 net/ipv4/tcp_minisocks.c                      |  40 +-
 net/ipv4/tcp_output.c                         | 239 +++++++-
 net/ipv6/syncookies.c                         |   2 +
 net/ipv6/tcp_ipv6.c                           |   1 +
 16 files changed, 1278 insertions(+), 76 deletions(-)
====================

Link: https://patch.msgid.link/20250916082434.100722-1-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 223 insertions, 16 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index be8ceefa5332..388c45859469 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -328,7 +328,15 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_ecn_mode_rfc3168(tp)) {
+	if (!tcp_ecn_mode_any(tp))
+		return;
+
+	if (tcp_ecn_mode_accecn(tp)) {
+		if (!tcp_accecn_ace_fail_recv(tp))
+			INET_ECN_xmit(sk);
+		tcp_accecn_set_ace(tp, skb, th);
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN;
+	} else {
 		/* Not-retransmitted data segment: set ECT and inject CWR. */
 		if (skb->len != tcp_header_len &&
 		    !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {
@@ -377,6 +385,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_SMC		BIT(9)
 #define OPTION_MPTCP		BIT(10)
 #define OPTION_AO		BIT(11)
+#define OPTION_ACCECN		BIT(12)
 
 static void smc_options_write(__be32 *ptr, u16 *options)
 {
@@ -398,6 +407,8 @@ struct tcp_out_options {
 	u16 mss;		/* 0 to disable */
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
+	u8 num_accecn_fields:7,	/* number of AccECN fields needed */
+	   use_synack_ecn_bytes:1; /* Use synack_ecn_bytes or not */
 	u8 hash_size;		/* bytes in hash_location */
 	u8 bpf_opt_len;		/* length of BPF hdr option */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
@@ -595,6 +606,11 @@ static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
 	return ptr;
 }
 
+/* Initial values for AccECN option, ordered is based on ECN field bits
+ * similar to received_ecn_bytes. Used for SYN/ACK AccECN option.
+ */
+static const u32 synack_ecn_bytes[3] = { 0, 0, 0 };
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -613,6 +629,8 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 			      struct tcp_out_options *opts,
 			      struct tcp_key *key)
 {
+	u8 leftover_highbyte = TCPOPT_NOP; /* replace 1st NOP if avail */
+	u8 leftover_lowbyte = TCPOPT_NOP;  /* replace 2nd NOP in succession */
 	__be32 *ptr = (__be32 *)(th + 1);
 	u16 options = opts->options;	/* mungable copy */
 
@@ -648,15 +666,75 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 		*ptr++ = htonl(opts->tsecr);
 	}
 
+	if (OPTION_ACCECN & options) {
+		const u32 *ecn_bytes = opts->use_synack_ecn_bytes ?
+				       synack_ecn_bytes :
+				       tp->received_ecn_bytes;
+		const u8 ect0_idx = INET_ECN_ECT_0 - 1;
+		const u8 ect1_idx = INET_ECN_ECT_1 - 1;
+		const u8 ce_idx = INET_ECN_CE - 1;
+		u32 e0b;
+		u32 e1b;
+		u32 ceb;
+		u8 len;
+
+		e0b = ecn_bytes[ect0_idx] + TCP_ACCECN_E0B_INIT_OFFSET;
+		e1b = ecn_bytes[ect1_idx] + TCP_ACCECN_E1B_INIT_OFFSET;
+		ceb = ecn_bytes[ce_idx] + TCP_ACCECN_CEB_INIT_OFFSET;
+		len = TCPOLEN_ACCECN_BASE +
+		      opts->num_accecn_fields * TCPOLEN_ACCECN_PERFIELD;
+
+		if (opts->num_accecn_fields == 2) {
+			*ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+				       ((e1b >> 8) & 0xffff));
+			*ptr++ = htonl(((e1b & 0xff) << 24) |
+				       (ceb & 0xffffff));
+		} else if (opts->num_accecn_fields == 1) {
+			*ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+				       ((e1b >> 8) & 0xffff));
+			leftover_highbyte = e1b & 0xff;
+			leftover_lowbyte = TCPOPT_NOP;
+		} else if (opts->num_accecn_fields == 0) {
+			leftover_highbyte = TCPOPT_ACCECN1;
+			leftover_lowbyte = len;
+		} else if (opts->num_accecn_fields == 3) {
+			*ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+				       ((e1b >> 8) & 0xffff));
+			*ptr++ = htonl(((e1b & 0xff) << 24) |
+				       (ceb & 0xffffff));
+			*ptr++ = htonl(((e0b & 0xffffff) << 8) |
+				       TCPOPT_NOP);
+		}
+		if (tp) {
+			tp->accecn_minlen = 0;
+			tp->accecn_opt_tstamp = tp->tcp_mstamp;
+			if (tp->accecn_opt_demand)
+				tp->accecn_opt_demand--;
+		}
+	}
+
 	if (unlikely(OPTION_SACK_ADVERTISE & options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
-			       (TCPOPT_NOP << 16) |
+		*ptr++ = htonl((leftover_highbyte << 24) |
+			       (leftover_lowbyte << 16) |
 			       (TCPOPT_SACK_PERM << 8) |
 			       TCPOLEN_SACK_PERM);
+		leftover_highbyte = TCPOPT_NOP;
+		leftover_lowbyte = TCPOPT_NOP;
 	}
 
 	if (unlikely(OPTION_WSCALE & options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
+		u8 highbyte = TCPOPT_NOP;
+
+		/* Do not split the leftover 2-byte to fit into a single
+		 * NOP, i.e., replace this NOP only when 1 byte is leftover
+		 * within leftover_highbyte.
+		 */
+		if (unlikely(leftover_highbyte != TCPOPT_NOP &&
+			     leftover_lowbyte == TCPOPT_NOP)) {
+			highbyte = leftover_highbyte;
+			leftover_highbyte = TCPOPT_NOP;
+		}
+		*ptr++ = htonl((highbyte << 24) |
 			       (TCPOPT_WINDOW << 16) |
 			       (TCPOLEN_WINDOW << 8) |
 			       opts->ws);
@@ -667,11 +745,13 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 			tp->duplicate_sack : tp->selective_acks;
 		int this_sack;
 
-		*ptr++ = htonl((TCPOPT_NOP  << 24) |
-			       (TCPOPT_NOP  << 16) |
+		*ptr++ = htonl((leftover_highbyte << 24) |
+			       (leftover_lowbyte << 16) |
 			       (TCPOPT_SACK <<  8) |
 			       (TCPOLEN_SACK_BASE + (opts->num_sack_blocks *
 						     TCPOLEN_SACK_PERBLOCK)));
+		leftover_highbyte = TCPOPT_NOP;
+		leftover_lowbyte = TCPOPT_NOP;
 
 		for (this_sack = 0; this_sack < opts->num_sack_blocks;
 		     ++this_sack) {
@@ -680,6 +760,14 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 		}
 
 		tp->rx_opt.dsack = 0;
+	} else if (unlikely(leftover_highbyte != TCPOPT_NOP ||
+			    leftover_lowbyte != TCPOPT_NOP)) {
+		*ptr++ = htonl((leftover_highbyte << 24) |
+			       (leftover_lowbyte << 16) |
+			       (TCPOPT_NOP << 8) |
+			       TCPOPT_NOP);
+		leftover_highbyte = TCPOPT_NOP;
+		leftover_lowbyte = TCPOPT_NOP;
 	}
 
 	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
@@ -760,6 +848,80 @@ static void mptcp_set_option_cond(const struct request_sock *req,
 	}
 }
 
+static u32 tcp_synack_options_combine_saving(struct tcp_out_options *opts)
+{
+	/* How much there's room for combining with the alignment padding? */
+	if ((opts->options & (OPTION_SACK_ADVERTISE | OPTION_TS)) ==
+	    OPTION_SACK_ADVERTISE)
+		return 2;
+	else if (opts->options & OPTION_WSCALE)
+		return 1;
+	return 0;
+}
+
+/* Calculates how long AccECN option will fit to @remaining option space.
+ *
+ * AccECN option can sometimes replace NOPs used for alignment of other
+ * TCP options (up to @max_combine_saving available).
+ *
+ * Only solutions with at least @required AccECN fields are accepted.
+ *
+ * Returns: The size of the AccECN option excluding space repurposed from
+ * the alignment of the other options.
+ */
+static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
+				  int remaining)
+{
+	int size = TCP_ACCECN_MAXSIZE;
+	int sack_blocks_reduce = 0;
+	int max_combine_saving;
+	int rem = remaining;
+	int align_size;
+
+	if (opts->use_synack_ecn_bytes)
+		max_combine_saving = tcp_synack_options_combine_saving(opts);
+	else
+		max_combine_saving = opts->num_sack_blocks > 0 ? 2 : 0;
+	opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS;
+	while (opts->num_accecn_fields >= required) {
+		/* Pad to dword if cannot combine */
+		if ((size & 0x3) > max_combine_saving)
+			align_size = ALIGN(size, 4);
+		else
+			align_size = ALIGN_DOWN(size, 4);
+
+		if (rem >= align_size) {
+			size = align_size;
+			break;
+		} else if (opts->num_accecn_fields == required &&
+			   opts->num_sack_blocks > 2 &&
+			   required > 0) {
+			/* Try to fit the option by removing one SACK block */
+			opts->num_sack_blocks--;
+			sack_blocks_reduce++;
+			rem = rem + TCPOLEN_SACK_PERBLOCK;
+
+			opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS;
+			size = TCP_ACCECN_MAXSIZE;
+			continue;
+		}
+
+		opts->num_accecn_fields--;
+		size -= TCPOLEN_ACCECN_PERFIELD;
+	}
+	if (sack_blocks_reduce > 0) {
+		if (opts->num_accecn_fields >= required)
+			size -= sack_blocks_reduce * TCPOLEN_SACK_PERBLOCK;
+		else
+			opts->num_sack_blocks += sack_blocks_reduce;
+	}
+	if (opts->num_accecn_fields < required)
+		return 0;
+
+	opts->options |= OPTION_ACCECN;
+	return size;
+}
+
 /* Compute TCP options for SYN packets. This is not the final
  * network wire format yet.
  */
@@ -842,6 +1004,20 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	/* Simultaneous open SYN/ACK needs AccECN option but not SYN.
+	 * It is attempted to negotiate the use of AccECN also on the first
+	 * retransmitted SYN, as mentioned in "3.1.4.1. Retransmitted SYNs"
+	 * of AccECN draft.
+	 */
+	if (unlikely((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) &&
+		     tcp_ecn_mode_accecn(tp) &&
+		     inet_csk(sk)->icsk_retransmits < 2 &&
+		     READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) &&
+		     remaining >= TCPOLEN_ACCECN_BASE)) {
+		opts->use_synack_ecn_bytes = 1;
+		remaining -= tcp_options_fit_accecn(opts, 0, remaining);
+	}
+
 	bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
 
 	return MAX_TCP_OPTION_SPACE - remaining;
@@ -859,6 +1035,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
+	struct tcp_request_sock *treq = tcp_rsk(req);
 
 	if (tcp_key_is_md5(key)) {
 		opts->options |= OPTION_MD5;
@@ -921,6 +1098,13 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
+	if (treq->accecn_ok &&
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) &&
+	    req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) {
+		opts->use_synack_ecn_bytes = 1;
+		remaining -= tcp_options_fit_accecn(opts, 0, remaining);
+	}
+
 	bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
 			      synack_type, opts, &remaining);
 
@@ -977,17 +1161,32 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
 	if (unlikely(eff_sacks)) {
 		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
-		if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
-					 TCPOLEN_SACK_PERBLOCK))
-			return size;
+		if (likely(remaining >= TCPOLEN_SACK_BASE_ALIGNED +
+					TCPOLEN_SACK_PERBLOCK)) {
+			opts->num_sack_blocks =
+				min_t(unsigned int, eff_sacks,
+				      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
+				      TCPOLEN_SACK_PERBLOCK);
+
+			size += TCPOLEN_SACK_BASE_ALIGNED +
+				opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+		} else {
+			opts->num_sack_blocks = 0;
+		}
+	} else {
+		opts->num_sack_blocks = 0;
+	}
 
-		opts->num_sack_blocks =
-			min_t(unsigned int, eff_sacks,
-			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
-			      TCPOLEN_SACK_PERBLOCK);
+	if (tcp_ecn_mode_accecn(tp)) {
+		int ecn_opt = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option);
 
-		size += TCPOLEN_SACK_BASE_ALIGNED +
-			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+		if (ecn_opt && tp->saw_accecn_opt && !tcp_accecn_opt_fail_send(tp) &&
+		    (ecn_opt >= TCP_ACCECN_OPTION_FULL || tp->accecn_opt_demand ||
+		     tcp_accecn_option_beacon_check(sk))) {
+			opts->use_synack_ecn_bytes = 0;
+			size += tcp_options_fit_accecn(opts, tp->accecn_minlen,
+						       MAX_TCP_OPTION_SPACE - size);
+		}
 	}
 
 	if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
@@ -2697,6 +2896,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	sent_pkts = 0;
 
 	tcp_mstamp_refresh(tp);
+
+	/* AccECN option beacon depends on mstamp, it may change mss */
+	if (tcp_ecn_mode_accecn(tp) && tcp_accecn_option_beacon_check(sk))
+		mss_now = tcp_current_mss(sk);
+
 	if (!push_one) {
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
@@ -3349,7 +3553,10 @@ start:
 			tcp_retrans_try_collapse(sk, skb, avail_wnd);
 	}
 
-	/* RFC3168, section 6.1.1.1. ECN fallback */
+	/* RFC3168, section 6.1.1.1. ECN fallback
+	 * As AccECN uses the same SYN flags (+ AE), this check covers both
+	 * cases.
+	 */
 	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
 		tcp_ecn_clear_syn(sk, skb);