Merge pull request #28 from L4STeam/AccECN-2023

Acc ecn 2023

.github/workflows/kernel.yml

@@ -63,7 +63,7 @@ jobs:
     runs-on: ubuntu-20.04
     needs: build
     permissions: write-all
-    if: ${{ github.ref == 'refs/heads/testing' || github.ref == 'refs/heads/ratebase'}}
+    if: ${{ github.ref == 'refs/heads/testing' || github.ref == 'refs/heads/ratebase' || github.ref == 'refs/heads/AccECN-2023'}}
     steps:
     - name: Get artifact
       uses: actions/download-artifact@v3

Documentation/networking/ip-sysctl.rst

@@ -431,6 +431,12 @@ tcp_ecn_option - INTEGER
 
 	Default: 2
 
+tcp_ecn_option_beacon - INTEGER
+        Control Accurate ECN (AccECN) option sending frequency per RTT and it 
+        takes effect only when tcp_ecn_option is set to 2.
+
+        Default: 1 (AccECN will be send at least 1 time per RTT)
+
 tcp_ecn_fallback - BOOLEAN
 	If the kernel detects that ECN connection misbehaves, enable fall
 	back to non-ECN. Currently, this knob implements the fallback

include/linux/tcp.h

@@ -234,6 +234,9 @@ struct tcp_sock {
 		syn_ect_snt:2,	/* AccECN ECT memory, only */
 		syn_ect_rcv:2,	/* ... needed durign 3WHS + first seqno */
 		ecn_fail:1;	/* ECN reflector detected path mangling */
+	u8	accecn_no_respond:1, /* AccECN no response on feedback */
+		accecn_no_options:1, /* AccECN no options send out */
+		first_data_ack:1;    /* Check for first data ack */
 	u8	saw_accecn_opt:2,    /* An AccECN option was seen */
 		fast_ack_mode:2, /* which fast ack mode ? */
 		unused:4;

include/net/request_sock.h

@@ -62,7 +62,8 @@ struct request_sock {
 	u16				mss;
 	u8				num_retrans; /* number of retransmits */
 	u8				syncookie:1; /* syncookie: encode tcpopts in timestamp */
-	u8				num_timeout:7; /* number of timeouts */
+	u8				num_timeout:7,
+					is_rtx:1; /* number of timeouts */
 	u32				ts_recent;
 	struct timer_list		rsk_timer;
 	const struct request_sock_ops	*rsk_ops;
@@ -105,6 +106,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
 	sk_tx_queue_clear(req_to_sk(req));
 	req->saved_syn = NULL;
 	req->num_timeout = 0;
+	req->is_rtx = 0;
 	req->num_retrans = 0;
 	req->sk = NULL;
 	refcount_set(&req->rsk_refcnt, 0);

include/net/tcp.h

@@ -228,7 +228,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCP_ACCECN_MAXSIZE		(TCPOLEN_ACCECN_BASE + \
 					 TCPOLEN_ACCECN_PERFIELD * \
 					 TCP_ACCECN_NUMFIELDS)
-#define TCP_ACCECN_BEACON_FREQ_SHIFT	2 /* Send option at least 2^2 times per RTT */
 #define TCP_ACCECN_SAFETY_SHIFT	1	/* SAFETY_FACTOR in accecn draft */
 
 /* tp->saw_accecn_opt states */

net/ipv4/inet_connection_sock.c

@@ -688,6 +688,7 @@ static void syn_ack_recalc(struct request_sock *req,
 
 int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 {
+	req->is_rtx = 1;
 	int err = req->rsk_ops->rtx_syn_ack(parent, req);
 
 	if (!err)

net/ipv4/tcp.c

@@ -3034,6 +3034,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->delivered_ce = 0;
 	tp->saw_accecn_opt = 0;
 	tp->ecn_fail = 0;
+	tp->accecn_no_respond = 0;
+	tp->accecn_no_options = 0;
+	tp->first_data_ack = 0;
 	tcp_accecn_init_counters(tp);
 	tp->prev_ecnfield = 0;
 	tp->accecn_opt_tstamp = 0;

net/ipv4/tcp_input.c

@@ -444,11 +444,31 @@ static void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb,
 		tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 		break;
 	case 0x1:
-	case 0x5:
 		if (tcp_ca_no_fallback_rfc3168(sk))
-			tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
-		else if (tcp_ecn_mode_pending(tp))
-			tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+		    tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
+		else
+		    tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+		break;
+	/* [CY] 3.1.2. Backward Compatibility - If a TCP Client has sent a SYN requesting AccECN feedback with (AE,CWR,ECE) =
+	 * (1,1,1) then receives a SYN/ACK with the currently reserved combination (AE,CWR,ECE) = (1,0,1) but it does not
+	 * have logic specific to such a combination, the Client MUST enable AccECN mode as if the SYN/ACK confirmed that the
+	 * Server supported AccECN and as if it fed back that the IP-ECN field on the SYN had arrived unchanged.
+	 */
+	case 0x5:
+		if (tcp_ecn_mode_pending(tp)) {
+		    tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
+		    tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK;
+		    if (tp->rx_opt.accecn &&
+			tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
+			    tp->saw_accecn_opt = tcp_accecn_option_init(skb,
+									tp->rx_opt.accecn);
+				tp->accecn_opt_demand = 2;
+		    }
+		    if (INET_ECN_is_ce(ip_dsfield)) {
+			    tp->received_ce++;
+			    tp->received_ce_pending++;
+		    }
+		}
 		break;
 	default:
 		tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
@@ -575,7 +595,7 @@ static bool tcp_accecn_process_option(struct tcp_sock *tp,
 	bool order1, res;
 	unsigned int i;
 
-	if (tp->saw_accecn_opt == TCP_ACCECN_OPT_FAIL)
+	if (tp->saw_accecn_opt == TCP_ACCECN_OPT_FAIL || tp->accecn_no_respond)
 		return false;
 
 	if (!(flag & FLAG_SLOWPATH) || !tp->rx_opt.accecn) {
@@ -683,6 +703,22 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
 	if (flag & FLAG_SYN_ACKED)
 		return 0;
 
+	/* [CY] 3.2.2.4. Testing for Zeroing of the ACE Field - If AccECN has been successfully negotiated, the Data Sender
+	 * MAY check the value of the ACE counter in the first feedback packet (with or without data) that arrives after the
+	 * 3-way handshake.  If the value of this ACE field is found to be zero (0b000), for the remainder of the half-
+	 * connection the Data Sender ought to send non-ECN-capable packets and it is advised not to respond to any feedback
+	 * of CE markings.
+	 */
+	if (!tp->first_data_ack) {
+		tp->first_data_ack = 1;
+		if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) {
+			tp->ecn_fail = 1;
+			INET_ECN_dontxmit(sk);
+			tp->accecn_no_respond = 1;
+			return 0;
+		}
+	}
+
 	if (tp->received_ce_pending >= TCP_ACCECN_ACE_MAX_DELTA)
 		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 
@@ -4873,8 +4909,18 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
 	 * DSACK state and change the txhash to re-route speculatively.
 	 */
 	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
-	    sk_rethink_txhash(sk))
+	    sk_rethink_txhash(sk)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
+		/* [CY] 3.2.3.2.2. Testing for Loss of Packets Carrying the AccECN Option - If a middlebox is dropping
+		 * packets with options it does not recognize, a host that is sending little or no data but mostly pure
+		 * ACKs will not inherently detect such losses. Such a host MAY detect loss of ACKs carrying the AccECN
+		 * Option by detecting whether the acknowledged data always reappears as a retransmission. In such cases,
+		 * the host SHOULD disable the sending of the AccECN Option for this half-connection.
+		 */
+			if (tcp_ecn_mode_accecn(tcp_sk(sk)))
+				tcp_sk(sk)->accecn_no_options = 1;
+
+	}
 }
 
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
@@ -6215,6 +6261,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	if (th->syn) {
 		if (tcp_ecn_mode_accecn(tp)) {
 			send_accecn_reflector = true;
+			/* [CY] 3.1.5. Implications of AccECN Mode - A host in AccECN mode that is feeding back the IP-ECN
+			 * field on a SYN or SYN/ACK: MUST feed back the IP-ECN field on the latest valid SYN or acceptable
+			 * SYN/ACK to arrive.”
+			 */
+			tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK;
 			if (tp->rx_opt.accecn &&
 			    tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
 				tp->saw_accecn_opt = tcp_accecn_option_init(skb,

net/ipv4/tcp_ipv4.c

@@ -3142,7 +3142,7 @@ static int __net_init tcp_sk_init(struct net *net)
 
 	net->ipv4.sysctl_tcp_ecn = 2;
 	net->ipv4.sysctl_tcp_ecn_option = 2;
-	net->ipv4.sysctl_tcp_ecn_option_beacon = 1;
+	net->ipv4.sysctl_tcp_ecn_option_beacon = 3;
 	net->ipv4.sysctl_tcp_ecn_fallback = 1;
 	net->ipv4.sysctl_tcp_ecn_unsafe_cep = 0;
 

net/ipv4/tcp_minisocks.c

@@ -405,7 +405,13 @@ void tcp_accecn_third_ack(struct sock *sk, const struct sk_buff *skb,
 
 	switch (ace) {
 	case 0x0:
+		/* [CY] 3.2.2.1. ACE Field on the ACK of the SYN/ACK - If the Server is in AccECN mode and in SYN-RCVD
+		 * state, and if it receives a value of zero on a pure ACK with SYN=0 and no SACK blocks, for the rest
+		 * of the connection the Server MUST NOT set ECT on outgoing packets and MUST NOT respond to AccECN
+		 * feedback. Nonetheless, as a Data Receiver it MUST NOT disable AccECN feedback.
+		 */
 		tp->ecn_fail = 1;
+		tp->accecn_no_respond = 1;
 		break;
 	case 0x7:
 	case 0x5:
@@ -432,6 +438,10 @@ static void tcp_ecn_openreq_child(struct sock *sk,
 	const struct tcp_request_sock *treq = tcp_rsk(req);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	/* [CY] 3.1.5. Implications of AccECN Mode - A TCP Server in AccECN mode: MUST NOT set ECT on
+	 * any packet for the rest of the connection, if it has received or sent at least one valid
+	 * SYN or Acceptable SYN/ACK with (AE,CWR,ECE) = (0,0,0) during the handshake.
+	 */
 	if (treq->accecn_ok) {
 		const struct tcphdr *th = (const struct tcphdr *)skb->data;
 		tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
@@ -694,9 +704,24 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 */
 		if (!tcp_oow_rate_limited(sock_net(sk), skb,
 					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
-					  &tcp_rsk(req)->last_oow_ack_time) &&
+					  &tcp_rsk(req)->last_oow_ack_time)) {
+
+		    if (tcp_rsk(req)->accecn_ok) {
+			/* [CY] 3.1.5 Implications of AccECN Mode - A host in AccECN mode that is feeding back the IP-ECN
+			 * field on a SYN or SYN/ACK: MUST feed back the IP-ECN field on the latest valid SYN or acceptable
+			 * SYN/ACK to arrive.
+			 */ 
+			tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK;
+			if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) {
+			/* [CY] 3.1.5. Implications of AccECN Mode - A TCP Server in AccECN mode: MUST NOT set ECT on
+			 * any packet for the rest of the connection, if it has received or sent at least one valid
+			 * SYN or Acceptable SYN/ACK with (AE,CWR,ECE) = (0,0,0) during the handshake
+			 */
+			    tcp_sk(sk)->ecn_fail = 1;
+			}
+		    }
 
-		    !inet_rtx_syn_ack(sk, req)) {
+		    if (!inet_rtx_syn_ack(sk, req)) {
 			unsigned long expires = jiffies;
 
 			expires += min(TCP_TIMEOUT_INIT << req->num_timeout,
@@ -705,6 +730,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 				mod_timer_pending(&req->rsk_timer, expires);
 			else
 				req->rsk_timer.expires = expires;
+		    }
 		}
 		return NULL;
 	}

net/ipv4/tcp_output.c

@@ -378,12 +378,27 @@ static void tcp_accecn_echo_syn_ect(struct tcphdr *th, u8 ect)
 }
 
 static void
-tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
+tcp_ecn_make_synack(struct sock *sk, const struct request_sock *req, struct tcphdr *th)
 {
-	if (tcp_rsk(req)->accecn_ok)
-		tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv);
-	else if (inet_rsk(req)->ecn_ok)
-		th->ece = 1;
+	if (!req->is_rtx || req->num_timeout < 1) {
+		if (tcp_rsk(req)->accecn_ok)
+		    tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv);
+		else if (inet_rsk(req)->ecn_ok)
+		    th->ece = 1;
+	} else if (tcp_rsk(req)->accecn_ok) {
+	/* [CY] 3.2.3.2.2. Testing for Loss of Packets Carrying the AccECN Option - If this retransmission times out,
+	 * to expedite connection setup, the TCP Server SHOULD retransmit the SYN/ACK with (AE,CWR,ECE) = (0,0,0) and
+	 * no AccECN Option, but it remains in AccECN feedback mode
+	 */
+		th->ae  = 0;
+		th->cwr = 0;
+		th->ece = 0;
+	/* [CY] 3.1.5. Implications of AccECN Mode - A TCP Server in AccECN mode: MUST NOT set ECT on any packet for
+	 * the rest of the connection, if it has received or sent at least one valid SYN or Acceptable SYN/ACK with
+	 * (AE,CWR,ECE) = (0,0,0) during the handshake.
+	 */
+		tcp_sk(sk)->ecn_fail = 1;
+	}
 }
 
 static void tcp_accecn_set_ace(struct tcp_sock *tp, struct sk_buff *skb,
@@ -922,8 +937,12 @@ static bool tcp_accecn_option_beacon_check(const struct sock *sk)
 	if (!sock_net(sk)->ipv4.sysctl_tcp_ecn_option_beacon)
 		return false;
 
-	return tcp_stamp_us_delta(tp->tcp_mstamp, tp->accecn_opt_tstamp) >=
-	       (tp->srtt_us >> (3 + TCP_ACCECN_BEACON_FREQ_SHIFT));
+	/* [CY] AccECN period shall be larger than srtt[us]/TCP_ECN_OPTION_BEACON
+	 * Following texts are removed in AccECN “6.  Summary: Protocol Properties - However, it has to send a full-sized
+	 *  AccECN Option at least three times per RTT, which the Data Sender can rely on as a regular beacon or checkpoint.”
+	 */
+	return tcp_stamp_us_delta(tp->tcp_mstamp, tp->accecn_opt_tstamp) * sock_net(sk)->ipv4.sysctl_tcp_ecn_option_beacon >=
+	       (tp->srtt_us >> 3);
 }
 
 /* Compute TCP options for SYN packets. This is not the final
@@ -1086,8 +1105,11 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
+	/* [CY] 3.2.3.2.2. Testing for Loss of Packets Carrying the AccECN Option - TCP Server SHOULD retransmit the
+	 * SYN/ACK, but with no AccECN Option
+	 */
 	if (treq->accecn_ok && sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
-	    req->num_timeout < 1 && (remaining >= TCPOLEN_ACCECN_BASE)) {
+	    !req->is_rtx && (remaining >= TCPOLEN_ACCECN_BASE)) {
 		opts->ecn_bytes = synack_ecn_bytes;
 		remaining -= tcp_options_fit_accecn(opts, 0, remaining,
 						    tcp_synack_options_combine_saving(opts));
@@ -1167,7 +1189,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	if (tcp_ecn_mode_accecn(tp) &&
 	    sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
-	    (tp->saw_accecn_opt && tp->saw_accecn_opt != TCP_ACCECN_OPT_FAIL)) {
+	    (tp->saw_accecn_opt && tp->saw_accecn_opt != TCP_ACCECN_OPT_FAIL && !tp->accecn_no_options)) {
 		if (sock_net(sk)->ipv4.sysctl_tcp_ecn_option >= 2 ||
 		    tp->accecn_opt_demand ||
 		    tcp_accecn_option_beacon_check(sk)) {
@@ -3431,12 +3453,20 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 			tcp_retrans_try_collapse(sk, skb, avail_wnd);
 	}
 
-	/* RFC3168, section 6.1.1.1. ECN fallback
-	 * As AccECN uses the same SYN flags (+ AE), this check covers both
-	 * cases.
+	/* [CY] 3.1.4.1. Retransmitted SYNs - If the sender of an AccECN SYN (the TCP Client) times out before receiving the SYN/ACK,
+	 * it SHOULD attempt to negotiate the use of AccECN at least one more time by continuing to set all three TCP ECN flags
+	 * (AE,CWR,ECE) = (1,1,1) on the first retransmitted SYN (using the usual retransmission time-outs). If this first
+	 * retransmission also fails to be acknowledged, in deployment scenarios where AccECN path traversal might be problematic, the
+	 * TCP Client SHOULD send subsequent retransmissions of the SYN with the three TCP-ECN flags cleared (AE,CWR,ECE) = (0,0,0).
 	 */
-	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
-		tcp_ecn_clear_syn(sk, skb);
+	if (!tcp_ecn_mode_pending(tp) || icsk->icsk_retransmits > 1) {
+		/* 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);
+	}
 
 	/* Update global and local TCP statistics. */
 	segs = tcp_skb_pcount(skb);
@@ -3822,7 +3852,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
-	tcp_ecn_make_synack(req, th);
+	tcp_ecn_make_synack((struct sock *)sk, req, th);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	skb->mark = ireq->ir_mark;