From 23e89e8ee7be73e21200947885a6d3a109a2c58d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 10 Jul 2024 10:12:45 -0700 Subject: [PATCH 1/2] tcp: Don't drop SYN+ACK for simultaneous connect(). RFC 9293 states that in the case of simultaneous connect(), the connection gets established when SYN+ACK is received. [0] TCP Peer A TCP Peer B 1. CLOSED CLOSED 2. SYN-SENT --> ... 3. SYN-RECEIVED <-- <-- SYN-SENT 4. ... --> SYN-RECEIVED 5. SYN-RECEIVED --> ... 6. ESTABLISHED <-- <-- SYN-RECEIVED 7. ... --> ESTABLISHED However, since commit 0c24604b68fc ("tcp: implement RFC 5961 4.2"), such a SYN+ACK is dropped in tcp_validate_incoming() and responded with Challenge ACK. For example, the write() syscall in the following packetdrill script fails with -EAGAIN, and wrong SNMP stats get incremented. 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) +0 > S 0:0(0) +0 < S 0:0(0) win 1000 +0 > S. 0:0(0) ack 1 +0 < S. 0:0(0) ack 1 win 1000 +0 write(3, ..., 100) = 100 +0 > P. 1:101(100) ack 1 -- # packetdrill cross-synack.pkt cross-synack.pkt:13: runtime error in write call: Expected result 100 but got -1 with errno 11 (Resource temporarily unavailable) # nstat ... TcpExtTCPChallengeACK 1 0.0 TcpExtTCPSYNChallenge 1 0.0 The problem is that bpf_skops_established() is triggered by the Challenge ACK instead of SYN+ACK. This causes the bpf prog to miss the chance to check if the peer supports a TCP option that is expected to be exchanged in SYN and SYN+ACK. Let's accept a bare SYN+ACK for active-open TCP_SYN_RECV sockets to avoid such a situation. Note that tcp_ack_snd_check() in tcp_rcv_state_process() is skipped not to send an unnecessary ACK, but this could be a bit risky for net.git, so this targets for net-next. Link: https://www.rfc-editor.org/rfc/rfc9293.html#section-3.5-7 [0] Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240710171246.87533-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_input.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e0f54b9be850..ff9ab3d01ced 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5998,6 +5998,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, * RFC 5961 4.2 : Send a challenge ack */ if (th->syn) { + if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack && + TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq && + TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt && + TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt) + goto pass; syn_challenge: if (syn_inerr) TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); @@ -6007,6 +6012,7 @@ syn_challenge: goto discard; } +pass: bpf_skops_parse_hdr(sk, skb); return true; @@ -6813,6 +6819,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_fast_path_on(tp); if (sk->sk_shutdown & SEND_SHUTDOWN) tcp_shutdown(sk, SEND_SHUTDOWN); + + if (sk->sk_socket) + goto consume; break; case TCP_FIN_WAIT1: { From b3bb4d23a41b825c78ff4436c9dc8650b1ea5704 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 10 Jul 2024 10:12:46 -0700 Subject: [PATCH 2/2] selftests: tcp: Remove broken SNMP assumptions for TCP AO self-connect tests. tcp_ao/self-connect.c checked the following SNMP stats before/after connect() to confirm that the test exercises the simultaneous connect() path. * TCPChallengeACK * TCPSYNChallenge But the stats should not be counted for self-connect in the first place, and the assumption is no longer true. Let's remove the check. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Dmitry Safonov Link: https://patch.msgid.link/20240710171246.87533-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- .../selftests/net/tcp_ao/self-connect.c | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c index e154d9e198a9..a5698b0a3718 100644 --- a/tools/testing/selftests/net/tcp_ao/self-connect.c +++ b/tools/testing/selftests/net/tcp_ao/self-connect.c @@ -30,8 +30,6 @@ static void setup_lo_intf(const char *lo_intf) static void tcp_self_connect(const char *tst, unsigned int port, bool different_keyids, bool check_restore) { - uint64_t before_challenge_ack, after_challenge_ack; - uint64_t before_syn_challenge, after_syn_challenge; struct tcp_ao_counters before_ao, after_ao; uint64_t before_aogood, after_aogood; struct netstat *ns_before, *ns_after; @@ -62,8 +60,6 @@ static void tcp_self_connect(const char *tst, unsigned int port, ns_before = netstat_read(); before_aogood = netstat_get(ns_before, "TCPAOGood", NULL); - before_challenge_ack = netstat_get(ns_before, "TCPChallengeACK", NULL); - before_syn_challenge = netstat_get(ns_before, "TCPSYNChallenge", NULL); if (test_get_tcp_ao_counters(sk, &before_ao)) test_error("test_get_tcp_ao_counters()"); @@ -82,8 +78,6 @@ static void tcp_self_connect(const char *tst, unsigned int port, ns_after = netstat_read(); after_aogood = netstat_get(ns_after, "TCPAOGood", NULL); - after_challenge_ack = netstat_get(ns_after, "TCPChallengeACK", NULL); - after_syn_challenge = netstat_get(ns_after, "TCPSYNChallenge", NULL); if (test_get_tcp_ao_counters(sk, &after_ao)) test_error("test_get_tcp_ao_counters()"); if (!check_restore) { @@ -98,18 +92,6 @@ static void tcp_self_connect(const char *tst, unsigned int port, close(sk); return; } - if (after_challenge_ack <= before_challenge_ack || - after_syn_challenge <= before_syn_challenge) { - /* - * It's also meant to test simultaneous open, so check - * these counters as well. - */ - test_fail("%s: Didn't challenge SYN or ACK: %zu <= %zu OR %zu <= %zu", - tst, after_challenge_ack, before_challenge_ack, - after_syn_challenge, before_syn_challenge); - close(sk); - return; - } if (test_tcp_ao_counters_cmp(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) { close(sk);