tcp: be less liberal in TSEcr received while in SYN_RECV state

Yong-Hao Zou mentioned that linux was not strict as other OS in 3WHS,
for flows using TCP TS option (RFC 7323)

As hinted by an old comment in tcp_check_req(),
we can check the TSEcr value in the incoming packet corresponds
to one of the SYNACK TSval values we have sent.

In this patch, I record the oldest and most recent values
that SYNACK packets have used.

Send a challenge ACK if we receive a TSEcr outside
of this range, and increase a new SNMP counter.

nstat -az | grep TSEcrRejected
TcpExtTSEcrRejected            0                  0.0

Due to TCP fastopen implementation, do not apply yet these checks
for fastopen flows.

v2: No longer use req->num_timeout, but treq->snt_tsval_first
    to detect when first SYNACK is prepared. This means
    we make sure to not send an initial zero TSval.
    Make sure MPTCP and TCP selftests are passing.
    Change MIB name to TcpExtTSEcrRejected

v1: https://lore.kernel.org/netdev/CADVnQykD8i4ArpSZaPKaoNxLJ2if2ts9m4As+=Jvdkrgx1qMHw@mail.gmail.com/T/

Reported-by: Yong-Hao Zou <yonghaoz1994@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250225171048.3105061-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 15 insertions, 11 deletions

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1eccc518b957..4f87406ddbcd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -663,6 +663,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct sock *child;
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
+	bool tsecr_reject = false;
 	bool paws_reject = false;
 	bool own_req;
 
@@ -672,8 +673,13 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
-			if (tmp_opt.rcv_tsecr)
+			if (tmp_opt.rcv_tsecr) {
+				if (inet_rsk(req)->tstamp_ok && !fastopen)
+					tsecr_reject = !between(tmp_opt.rcv_tsecr,
+							tcp_rsk(req)->snt_tsval_first,
+							READ_ONCE(tcp_rsk(req)->snt_tsval_last));
 				tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off;
+			}
 			/* We do not store true stamp, but it is not required,
 			 * it can be estimated (approximately)
 			 * from another data.
@@ -788,18 +794,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	     tcp_rsk(req)->snt_isn + 1))
 		return sk;
 
-	/* Also, it would be not so bad idea to check rcv_tsecr, which
-	 * is essentially ACK extension and too early or too late values
-	 * should cause reset in unsynchronized states.
-	 */
-
 	/* RFC793: "first check sequence number". */
 
-	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq,
-					  TCP_SKB_CB(skb)->end_seq,
-					  tcp_rsk(req)->rcv_nxt,
-					  tcp_rsk(req)->rcv_nxt +
-					  tcp_synack_window(req))) {
+	if (paws_reject || tsecr_reject ||
+	    !tcp_in_window(TCP_SKB_CB(skb)->seq,
+			   TCP_SKB_CB(skb)->end_seq,
+			   tcp_rsk(req)->rcv_nxt,
+			   tcp_rsk(req)->rcv_nxt +
+			   tcp_synack_window(req))) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST) &&
 		    !tcp_oow_rate_limited(sock_net(sk), skb,
@@ -808,6 +810,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+		else if (tsecr_reject)
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TSECRREJECTED);
 		return NULL;
 	}