netdev - [PATCH net-next 39/44] tcp: accecn: verify ACE counter in 1st ACK after AccECN negotiation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20241015102940.26157-40-chia-yu.chang@nokia-bell-labs.com>
Date: Tue, 15 Oct 2024 12:29:35 +0200
From: chia-yu.chang@...ia-bell-labs.com
To: netdev@...r.kernel.org, ij@...nel.org, ncardwell@...gle.com,
        koen.de_schepper@...ia-bell-labs.com, g.white@...leLabs.com,
        ingemar.s.johansson@...csson.com, mirja.kuehlewind@...csson.com,
        cheshire@...le.com, rs.ietf@....at, Jason_Livingood@...cast.com,
        vidhi_goel@...le.com
Cc: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
Subject: [PATCH net-next 39/44] tcp: accecn: verify ACE counter in 1st ACK after AccECN negotiation

From: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>

After successfully negotiating AccECN mode in the handshake, check
the ACE field of the first dta ACK. If zero, non-ECT packets are
sent and any response to CE marking feedback is disabled.

Based on specification:
  https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt

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.

Signed-off-by: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
---
 net/ipv4/tcp_input.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e88f449e89e1..0786e7127064 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -687,7 +687,8 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
 
 /* Returns the ECN CE delta */
 static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
-				u32 delivered_pkts, u32 delivered_bytes, int flag)
+				u32 delivered_pkts, u32 delivered_bytes,
+				u64 prior_bytes_acked, int flag)
 {
 	u32 old_ceb = tcp_sk(sk)->delivered_ecn_bytes[INET_ECN_CE - 1];
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -724,6 +725,16 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
 	if (flag & FLAG_SYN_ACKED)
 		return 0;
 
+	/* Verify ACE!=0 in the 1st data ACK after AccECN negotiation */
+	if ((flag & FLAG_DATA_ACKED) && prior_bytes_acked <= tp->mss_cache) {
+		if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) {
+			INET_ECN_dontxmit(sk);
+			tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV |
+						     TCP_ACCECN_OPT_FAIL_RECV);
+			return 0;
+		}
+	}
+
 	if (tp->received_ce_pending >= TCP_ACCECN_ACE_MAX_DELTA)
 		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 
@@ -763,13 +774,14 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
 
 static void tcp_accecn_process(struct sock *sk, struct rate_sample *rs,
 			       const struct sk_buff *skb,
-			       u32 delivered_pkts, u32 delivered_bytes, int *flag)
+			       u32 delivered_pkts, u32 delivered_bytes,
+			       u64 prior_bytes_acked, int *flag)
 {
 	u32 delta;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	delta = __tcp_accecn_process(sk, skb, delivered_pkts,
-				     delivered_bytes, *flag);
+				     delivered_bytes, prior_bytes_acked, *flag);
 	if (delta > 0) {
 		tcp_count_delivered_ce(tp, delta);
 		*flag |= FLAG_ECE;
@@ -4303,6 +4315,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_sacktag_state sack_state;
 	struct rate_sample rs = { .prior_delivered = 0, .ece_delta = 0 };
+	u64 prior_bytes_acked = tp->bytes_acked;
 	u32 prior_snd_una = tp->snd_una;
 	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
@@ -4422,7 +4435,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (tcp_ecn_mode_accecn(tp))
 		tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered,
-				   sack_state.delivered_bytes, &flag);
+				   sack_state.delivered_bytes,
+				   prior_bytes_acked, &flag);
 
 	tcp_in_ack_event(sk, flag);
 
@@ -4460,7 +4474,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 no_queue:
 	if (tcp_ecn_mode_accecn(tp))
 		tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered,
-				   sack_state.delivered_bytes, &flag);
+				   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) {
-- 
2.34.1