diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index bc9a01606daf..28c7e4f5ecf9 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -482,7 +482,9 @@ tcp_ecn_option - INTEGER 1 Send AccECN option sparingly according to the minimum option rules outlined in draft-ietf-tcpm-accurate-ecn. 2 Send AccECN option on every packet whenever it fits into TCP - option space. + option space except when AccECN fallback is triggered. + 3 Send AccECN option on every packet whenever it fits into TCP + option space even when AccECN fallback is triggered. = ============================================================ Default: 2 diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index 26f32dbcf6ec..563daea10d6c 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -105,6 +105,7 @@ u32 received_ce read_mostly read_w u32[3] received_ecn_bytes read_mostly read_write u8:4 received_ce_pending read_mostly read_write u32[3] delivered_ecn_bytes read_write +u16 pkts_acked_ewma read_write u8:2 syn_ect_snt write_mostly read_write u8:2 syn_ect_rcv read_mostly read_write u8:2 accecn_minlen write_mostly read_write diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 367b491ddf97..f72eef31fa23 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -291,7 +291,8 @@ struct tcp_sock { u8 nonagle : 4,/* Disable Nagle algorithm? */ rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ u8 received_ce_pending:4, /* Not yet transmit cnt of received_ce */ - unused2:4; + accecn_opt_sent_w_dsack:1,/* Sent ACCECN opt in previous ACK w/ D-SACK */ + unused2:3; u8 accecn_minlen:2,/* Minimum length of AccECN option sent */ est_ecnfield:2,/* ECN field for AccECN delivered estimates */ accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */ @@ -342,6 +343,7 @@ struct tcp_sock { u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_rtt_last_tsecr; u32 delivered_ecn_bytes[3]; + u16 pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */ u64 first_tx_mstamp; /* start of window send phase */ u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ea32393464a2..827b87a95dab 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -51,11 +51,25 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; } +/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + static inline void INET_ECN_xmit(struct sock *sk) { - inet_sk(sk)->tos |= INET_ECN_ECT_0; - if (inet6_sk(sk) != NULL) - inet6_sk(sk)->tclass |= INET_ECN_ECT_0; + __INET_ECN_xmit(sk, false); } static inline void INET_ECN_dontxmit(struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index cecec1a92d5e..6c12be2cdd4d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -552,6 +552,7 @@ enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, + TCP_SYNACK_RETRANS, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, @@ -1215,7 +1216,15 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) -#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) +/* Require successfully negotiated AccECN capability */ +#define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ +#define TCP_CONG_ECT_1_NEGOTIATION BIT(3) +/* Cannot fallback to RFC3168 during AccECN negotiation */ +#define TCP_CONG_NO_FALLBACK_RFC3168 BIT(4) +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ + TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \ + TCP_CONG_NO_FALLBACK_RFC3168) union tcp_cc_info; @@ -1356,6 +1365,27 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } +static inline bool tcp_ca_needs_accecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; +} + +static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION; +} + +static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; +} + static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f13e5cd2b1ac..e9a933641636 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -29,8 +29,15 @@ enum tcp_accecn_option { TCP_ACCECN_OPTION_DISABLED = 0, TCP_ACCECN_OPTION_MINIMUM = 1, TCP_ACCECN_OPTION_FULL = 2, + TCP_ACCECN_OPTION_PERSIST = 3, }; +/* Apply either ECT(0) or ECT(1) based on TCP_CONG_ECT_1_NEGOTIATION flag */ +static inline void INET_ECN_xmit_ect_1_negotiation(struct sock *sk) +{ + __INET_ECN_xmit(sk, tcp_ca_ect_1_negotiation(sk)); +} + static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp) { /* Do not set CWR if in AccECN mode! */ @@ -60,12 +67,6 @@ static inline void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; } -/* tp->accecn_fail_mode */ -#define TCP_ACCECN_ACE_FAIL_SEND BIT(0) -#define TCP_ACCECN_ACE_FAIL_RECV BIT(1) -#define TCP_ACCECN_OPT_FAIL_SEND BIT(2) -#define TCP_ACCECN_OPT_FAIL_RECV BIT(3) - static inline bool tcp_accecn_ace_fail_send(const struct tcp_sock *tp) { return tp->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND; @@ -91,11 +92,6 @@ static inline void tcp_accecn_fail_mode_set(struct tcp_sock *tp, u8 mode) tp->accecn_fail_mode |= mode; } -#define TCP_ACCECN_OPT_NOT_SEEN 0x0 -#define TCP_ACCECN_OPT_EMPTY_SEEN 0x1 -#define TCP_ACCECN_OPT_COUNTER_SEEN 0x2 -#define TCP_ACCECN_OPT_FAIL_SEEN 0x3 - static inline u8 tcp_accecn_ace(const struct tcphdr *th) { return (th->ae << 2) | (th->cwr << 1) | th->ece; @@ -169,7 +165,9 @@ static inline void tcp_accecn_third_ack(struct sock *sk, switch (ace) { case 0x0: /* Invalid value */ - tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV); + if (!TCP_SKB_CB(skb)->sacked) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV | + TCP_ACCECN_OPT_FAIL_RECV); break; case 0x7: case 0x5: @@ -398,6 +396,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp) tp->received_ce_pending = 0; __tcp_accecn_init_bytes_counters(tp->received_ecn_bytes); __tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes); + tp->accecn_opt_sent_w_dsack = 0; tp->accecn_minlen = 0; tp->accecn_opt_demand = 0; tp->est_ecnfield = 0; @@ -467,6 +466,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb, return TCP_ACCECN_OPT_COUNTER_SEEN; } +static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk, + const struct sk_buff *skb, u8 dsf) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_rcv = dsf & INET_ECN_MASK; + /* Demand Accurate ECN option in response to the SYN on the SYN/ACK + * and the TCP server will try to send one more packet with an AccECN + * Option at a later point during the connection. + */ + if (tp->rx_opt.accecn && + tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + tp->accecn_opt_demand = 2; + } +} + /* See Table 2 of the AccECN draft */ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th, u8 ip_dsfield) @@ -489,32 +508,32 @@ static inline 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: /* +========+========+============+=============+ * | A | B | SYN/ACK | Feedback | * | | | B->A | Mode of A | * | | | AE CWR ECE | | * +========+========+============+=============+ - * | AccECN | Nonce | 1 0 1 | (Reserved) | * | AccECN | ECN | 0 0 1 | Classic ECN | * | Nonce | AccECN | 0 0 1 | Classic ECN | * | ECN | AccECN | 0 0 1 | Classic ECN | * +========+========+============+=============+ */ - if (tcp_ecn_mode_pending(tp)) - /* Downgrade from AccECN, or requested initially */ + if (tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); + else tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; - default: - 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) { - u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); - - tcp_accecn_saw_opt_fail_recv(tp, saw_opt); - tp->accecn_opt_demand = 2; + case 0x5: + if (tcp_ecn_mode_pending(tp)) { + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); + if (INET_ECN_is_ce(ip_dsfield)) { + tp->received_ce++; + tp->received_ce_pending++; + } } + break; + default: + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); if (INET_ECN_is_ce(ip_dsfield) && tcp_accecn_validate_syn_feedback(sk, ace, tp->syn_ect_snt)) { @@ -525,9 +544,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb } } -static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, +static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + if (tcp_ecn_mode_pending(tp)) { if (!tcp_accecn_syn_requested(th)) { /* Downgrade to classic ECN feedback */ @@ -539,7 +560,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); } } - if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr)) + if (tcp_ecn_mode_rfc3168(tp) && + (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk))) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } @@ -561,7 +583,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE; @@ -579,7 +601,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) bool use_ecn, use_accecn; u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); - use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN; + use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN || + tcp_ca_needs_accecn(sk); use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN || tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN || tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn; @@ -595,7 +618,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; if (use_accecn) { @@ -619,12 +642,22 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) } static inline void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) +tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th, + enum tcp_synack_type synack_type) { - 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; + /* Accurate ECN shall retransmit SYN/ACK with ACE=0 if the + * previously retransmitted SYN/ACK also times out. + */ + if (!req->num_timeout || synack_type != TCP_SYNACK_RETRANS) { + 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) { + th->ae = 0; + th->cwr = 0; + th->ece = 0; + } } static inline bool tcp_accecn_option_beacon_check(const struct sock *sk) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index dce3113787a7..03772dd4d399 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -226,6 +226,24 @@ enum tcp_ca_state { #define TCPF_CA_Loss (1< #include #include +#include #include #include @@ -1103,6 +1104,8 @@ static void reqsk_timer_handler(struct timer_list *t) (!resend || !tcp_rtx_synack(sk_listener, req) || inet_rsk(req)->acked)) { + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; if (req->num_timeout++ == 0) atomic_dec(&queue->young); mod_timer(&req->rsk_timer, jiffies + tcp_reqsk_timeout(req)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a1a50a5c80dc..643763bc2142 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -47,7 +47,7 @@ static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; -static int tcp_ecn_mode_max = 2; +static int tcp_ecn_mode_max = 5; static u32 icmp_errors_extension_mask_all = GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0); @@ -749,7 +749,7 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, + .extra2 = SYSCTL_THREE, }, { .procname = "tcp_ecn_option_beacon", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6e94c5859f4b..6ce03a9adb4a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3470,6 +3470,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_accecn_init_counters(tp); tp->prev_ecnfield = 0; tp->accecn_opt_tstamp = 0; + tp->pkts_acked_ewma = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -4372,6 +4373,14 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; + if (tcp_ecn_disabled(tp)) + info->tcpi_ecn_mode = TCPI_ECN_MODE_DISABLED; + else if (tcp_ecn_mode_rfc3168(tp)) + info->tcpi_ecn_mode = TCPI_ECN_MODE_RFC3168; + else if (tcp_ecn_mode_accecn(tp)) + info->tcpi_ecn_mode = TCPI_ECN_MODE_ACCECN; + else if (tcp_ecn_mode_pending(tp)) + info->tcpi_ecn_mode = TCPI_ECN_MODE_PENDING; info->tcpi_accecn_fail_mode = tp->accecn_fail_mode; info->tcpi_accecn_opt_seen = tp->saw_accecn_opt; info->tcpi_received_ce = tp->received_ce; @@ -5243,6 +5252,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, pkts_acked_ewma); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index df758adbb445..e9f6c77e0631 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -16,6 +16,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(tcp_cong_list_lock); @@ -227,7 +228,7 @@ void tcp_assign_congestion_control(struct sock *sk) memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); } @@ -257,7 +258,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a2a872382fc0..89526f0f2301 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -488,6 +488,10 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, tcp_count_delivered_ce(tp, delivered); } +#define PKTS_ACKED_WEIGHT 6 +#define PKTS_ACKED_PREC 6 +#define ACK_COMP_THRESH 4 + /* Returns the ECN CE delta */ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delivered_pkts, u32 delivered_bytes, @@ -499,6 +503,7 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delta, safe_delta, d_ceb; bool opt_deltas_valid; u32 corrected_ace; + u32 ewma; /* Reordered ACK or uncertain due to lack of data to send and ts */ if (!(flag & (FLAG_FORWARD_PROGRESS | FLAG_TS_PROGRESS))) @@ -507,6 +512,18 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, opt_deltas_valid = tcp_accecn_process_option(tp, skb, delivered_bytes, flag); + if (delivered_pkts) { + if (!tp->pkts_acked_ewma) { + ewma = delivered_pkts << PKTS_ACKED_PREC; + } else { + ewma = tp->pkts_acked_ewma; + ewma = (((ewma << PKTS_ACKED_WEIGHT) - ewma) + + (delivered_pkts << PKTS_ACKED_PREC)) >> + PKTS_ACKED_WEIGHT; + } + tp->pkts_acked_ewma = min_t(u32, ewma, 0xFFFFU); + } + if (!(flag & FLAG_SLOWPATH)) { /* AccECN counter might overflow on large ACKs */ if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK) @@ -555,7 +572,8 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, if (d_ceb < safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT) return delta; - } + } else if (tp->pkts_acked_ewma > (ACK_COMP_THRESH << PKTS_ACKED_PREC)) + return delta; return safe_delta; } @@ -5028,8 +5046,11 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) tcp_sack_extend(tp->duplicate_sack, seq, end_seq); } -static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) +static void tcp_rcv_spurious_retrans(struct sock *sk, + const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + /* When the ACK path fails or drops most ACKs, the sender would * timeout and spuriously retransmit the same segment repeatedly. * If it seems our ACKs are not reaching the other side, @@ -5049,6 +5070,14 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) /* Save last flowlabel after a spurious retrans. */ tcp_save_lrcv_flowlabel(sk, skb); #endif + /* Check DSACK info to detect that the previous ACK carrying the + * AccECN option was lost after the second retransmision, and then + * stop sending AccECN option in all subsequent ACKs. + */ + if (tcp_ecn_mode_accecn(tp) && + tp->accecn_opt_sent_w_dsack && + TCP_SKB_CB(skb)->seq == tp->duplicate_sack[0].start_seq) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_OPT_FAIL_SEND); } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) @@ -6451,6 +6480,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (th->syn) { if (tcp_ecn_mode_accecn(tp)) { accecn_reflector = true; + 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) { u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); @@ -7072,7 +7103,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd; - tcp_ecn_rcv_syn(tp, th, skb); + tcp_ecn_rcv_syn(sk, th, skb); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -7477,7 +7508,8 @@ static void tcp_ecn_create_request(struct request_sock *req, u32 ecn_ok_dst; if (tcp_accecn_syn_requested(th) && - READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3) { + (READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3 || + tcp_ca_needs_accecn(listen_sk))) { inet_rsk(req)->ecn_ok = 1; tcp_rsk(req)->accecn_ok = 1; tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bd5462154f97..ec128865f5c0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -481,13 +481,18 @@ static void tcp_ecn_openreq_child(struct sock *sk, tp->syn_ect_snt = treq->syn_ect_snt; tcp_accecn_third_ack(sk, skb, treq->syn_ect_snt); tp->saw_accecn_opt = treq->saw_accecn_opt; + if (treq->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_SEND); + if (treq->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_RECV) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV); tp->prev_ecnfield = treq->syn_ect_rcv; tp->accecn_opt_demand = 1; tcp_ecn_received_counters_payload(sk, skb); } else { - tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ? - TCP_ECN_MODE_RFC3168 : - TCP_ECN_DISABLED); + if (inet_rsk(req)->ecn_ok && !tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); + else + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } } @@ -748,16 +753,28 @@ 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) { + u8 ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; - !tcp_rtx_synack(sk, req)) { - unsigned long expires = jiffies; + tcp_rsk(req)->syn_ect_rcv = ect_rcv; + if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) + tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_RECV; + } + if (!tcp_rtx_synack(sk, req)) { + unsigned long expires = jiffies; - expires += tcp_reqsk_timeout(req); - if (!fastopen) - mod_timer_pending(&req->rsk_timer, expires); - else - req->rsk_timer.expires = expires; + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; + + expires += tcp_reqsk_timeout(req); + if (!fastopen) + mod_timer_pending(&req->rsk_timer, + expires); + else + req->rsk_timer.expires = expires; + } } return NULL; } diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 942a948f1a31..3b1fdcd3cb29 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -304,8 +304,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, goto out_check_final; th2 = tcp_hdr(p); - flush = (__force int)(flags & TCP_FLAG_CWR); - flush |= (__force int)((flags ^ tcp_flag_word(th2)) & + flush = (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 597e888af36d..f44d60d13b9f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -334,8 +334,11 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, return; if (tcp_ecn_mode_accecn(tp)) { - if (!tcp_accecn_ace_fail_recv(tp)) + if (!tcp_accecn_ace_fail_recv(tp) && + !tcp_accecn_ace_fail_send(tp)) INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); tcp_accecn_set_ace(tp, skb, th); skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; } else { @@ -712,9 +715,12 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, if (tp) { tp->accecn_minlen = 0; tp->accecn_opt_tstamp = tp->tcp_mstamp; + tp->accecn_opt_sent_w_dsack = tp->rx_opt.dsack; if (tp->accecn_opt_demand) tp->accecn_opt_demand--; } + } else if (tp) { + tp->accecn_opt_sent_w_dsack = 0; } if (unlikely(OPTION_SACK_ADVERTISE & options)) { @@ -1106,7 +1112,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (treq->accecn_ok && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && - req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) { + synack_type != TCP_SYNACK_RETRANS && remaining >= TCPOLEN_ACCECN_BASE) { opts->use_synack_ecn_bytes = 1; remaining -= tcp_options_fit_accecn(opts, 0, remaining); } @@ -1186,7 +1192,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (tcp_ecn_mode_accecn(tp)) { int ecn_opt = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option); - if (ecn_opt && tp->saw_accecn_opt && !tcp_accecn_opt_fail_send(tp) && + if (ecn_opt && tp->saw_accecn_opt && + (ecn_opt >= TCP_ACCECN_OPTION_PERSIST || + !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; @@ -3606,12 +3614,15 @@ 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. - */ - 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); @@ -3926,6 +3937,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, switch (synack_type) { case TCP_SYNACK_NORMAL: + case TCP_SYNACK_RETRANS: skb_set_owner_edemux(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: @@ -4008,7 +4020,7 @@ 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(req, th, synack_type); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; @@ -4611,7 +4623,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); - res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_RETRANS, NULL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 160080c9021d..5a14a53a3c9e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,6 +22,7 @@ #include #include #include +#include #include static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) @@ -479,6 +480,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * it's not good to give up too easily. */ tcp_rtx_synack(sk, req); + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) diff --git a/tools/testing/selftests/drivers/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index e76c618704cf..3c0745b68bfa 100644 --- a/tools/testing/selftests/drivers/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -17,8 +17,8 @@ * Pure ACK does not coalesce. * * flags_*: - * No packets with PSH, SYN, URG, RST set will be coalesced. - * - flags_psh, flags_syn, flags_rst, flags_urg + * No packets with PSH, SYN, URG, RST, CWR set will be coalesced. + * - flags_psh, flags_syn, flags_rst, flags_urg, flags_cwr * * tcp_*: * Packets with incorrect checksum, non-consecutive seqno and @@ -360,32 +360,58 @@ static void create_packet(void *buf, int seq_offset, int ack_offset, fill_datalinklayer(buf); } -/* send one extra flag, not first and not last pkt */ -static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, - int rst, int urg) +#ifndef TH_CWR +#define TH_CWR 0x80 +#endif +static void set_flags(struct tcphdr *tcph, int payload_len, int psh, int syn, + int rst, int urg, int cwr) { - static char flag_buf[MAX_HDR_LEN + PAYLOAD_LEN]; - static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; - int payload_len, pkt_size, flag, i; - struct tcphdr *tcph; - - payload_len = PAYLOAD_LEN * psh; - pkt_size = total_hdr_len + payload_len; - flag = NUM_PACKETS / 2; - - create_packet(flag_buf, flag * payload_len, 0, payload_len, 0); - - tcph = (struct tcphdr *)(flag_buf + tcp_offset); tcph->psh = psh; tcph->syn = syn; tcph->rst = rst; tcph->urg = urg; + if (cwr) + tcph->th_flags |= TH_CWR; + else + tcph->th_flags &= ~TH_CWR; tcph->check = 0; tcph->check = tcp_checksum(tcph, payload_len); +} + +/* send extra flags of the (NUM_PACKETS / 2) and (NUM_PACKETS / 2 - 1) + * pkts, not first and not last pkt + */ +static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, + int rst, int urg, int cwr) +{ + static char flag_buf[2][MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + int payload_len, pkt_size, i; + struct tcphdr *tcph; + int flag[2]; + + payload_len = PAYLOAD_LEN * (psh || cwr); + pkt_size = total_hdr_len + payload_len; + flag[0] = NUM_PACKETS / 2; + flag[1] = NUM_PACKETS / 2 - 1; + + /* Create and configure packets with flags + */ + for (i = 0; i < 2; i++) { + if (flag[i] > 0) { + create_packet(flag_buf[i], flag[i] * payload_len, 0, + payload_len, 0); + tcph = (struct tcphdr *)(flag_buf[i] + tcp_offset); + set_flags(tcph, payload_len, psh, syn, rst, urg, cwr); + } + } for (i = 0; i < NUM_PACKETS + 1; i++) { - if (i == flag) { - write_packet(fd, flag_buf, pkt_size, daddr); + if (i == flag[0]) { + write_packet(fd, flag_buf[0], pkt_size, daddr); + continue; + } else if (i == flag[1] && cwr) { + write_packet(fd, flag_buf[1], pkt_size, daddr); continue; } create_packet(buf, i * PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); @@ -1068,16 +1094,19 @@ static void gro_sender(void) /* flags sub-tests */ } else if (strcmp(testname, "flags_psh") == 0) { - send_flags(txfd, &daddr, 1, 0, 0, 0); + send_flags(txfd, &daddr, 1, 0, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "flags_syn") == 0) { - send_flags(txfd, &daddr, 0, 1, 0, 0); + send_flags(txfd, &daddr, 0, 1, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "flags_rst") == 0) { - send_flags(txfd, &daddr, 0, 0, 1, 0); + send_flags(txfd, &daddr, 0, 0, 1, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "flags_urg") == 0) { - send_flags(txfd, &daddr, 0, 0, 0, 1); + send_flags(txfd, &daddr, 0, 0, 0, 1, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + } else if (strcmp(testname, "flags_cwr") == 0) { + send_flags(txfd, &daddr, 0, 0, 0, 0, 1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); /* tcp sub-tests */ @@ -1239,6 +1268,12 @@ static void gro_receiver(void) correct_payload[2] = PAYLOAD_LEN * 2; printf("urg flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 3); + } else if (strcmp(testname, "flags_cwr") == 0) { + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN * 2; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("cwr flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); /* tcp sub-tests */ } else if (strcmp(testname, "tcp_csum") == 0) { diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py index 1bb8af571456..cbc1b19dbc91 100755 --- a/tools/testing/selftests/drivers/net/gro.py +++ b/tools/testing/selftests/drivers/net/gro.py @@ -17,6 +17,7 @@ Test cases: - flags_syn: Packets with SYN flag don't coalesce - flags_rst: Packets with RST flag don't coalesce - flags_urg: Packets with URG flag don't coalesce + - flags_cwr: Packets with CWR flag don't coalesce - tcp_csum: Packets with incorrect checksum don't coalesce - tcp_seq: Packets with non-consecutive seqno don't coalesce - tcp_ts: Packets with different timestamp options don't coalesce @@ -191,7 +192,7 @@ def _gro_variants(): common_tests = [ "data_same", "data_lrg_sml", "data_sml_lrg", "ack", - "flags_psh", "flags_syn", "flags_rst", "flags_urg", + "flags_psh", "flags_syn", "flags_rst", "flags_urg", "flags_cwr", "tcp_csum", "tcp_seq", "tcp_ts", "tcp_opt", "ip_ecn", "ip_tos", "large_max", "large_rem", diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first.pkt new file mode 100644 index 000000000000..07e9936e70e6 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first.pkt @@ -0,0 +1,24 @@ +// 3rd ACK + 1st data segment lost, data segments with ce + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + ++0.05 < SEWA 0:0(0) win 32767 ++.002 > SW. 0:0(0) ack 1 +// 3rd ACK lost +// 1st data segment lost ++0.05 < [ce] EAP. 1001:2001(1000) ack 1 win 264 ++.002 > [ect0] WA. 1:1(0) ack 1 ++.002 accept(3, ..., ...) = 4 + ++0.2 < [ce] EAP. 1:1001(1000) ack 1 win 264 ++.001 > [ect0] EWA. 1:1(0) ack 2001 + ++0.05 < [ce] EAP. 2001:3001(1000) ack 1 win 264 ++.001 > [ect0] . 1:1(0) ack 3001 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first_connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first_connect.pkt new file mode 100644 index 000000000000..76b8422b34dc --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_2nd_data_as_first_connect.pkt @@ -0,0 +1,30 @@ +// 3rd ACK + 1st data segment lost, 2nd data segments with ce + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] SW. 0:0(0) ack 1 win 32767 +// 3rd ACK lost ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.01 write(4, ..., 2000) = 2000 +// 1st data segment lost + 2nd gets CE ++.002 > [ect0] .5 1:1005(1004) ack 1 ++.000 > [ect0] P.5 1005:2001(996) ack 1 ++0.05 < [ect0] .6 1:1(0) ack 1 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 1, tcpi_delivered_ce }% + ++0.002~+0.1 > [ect0] .5 1:1005(1004) ack 1 ++.05 < [ect0] .6 1:1(0) ack 2001 win 264 + ++0.01 write(4, ..., 1000) = 1000 ++0~+0.002 > [ect0] P.5 2001:3001(1000) ack 1 + ++0.1 < [ect0] .5 1:1001(1000) ack 3001 win 264 ++0~+0.01 > [ect0] .5 3001:3001(0) ack 1001 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_after_synack_rxmt.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_after_synack_rxmt.pkt new file mode 100644 index 000000000000..84060e490589 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_after_synack_rxmt.pkt @@ -0,0 +1,19 @@ +// Test 3rd ACK flags when SYN-ACK is rexmitted + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.1 < [ect0] S. 0:0(0) ack 1 win 32767 + +// Our code currently sends a challenge ACK +// when it receives a SYN in ESTABLISHED state +// based on the latest SYN ++.002 > [ect0] A. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_ce_updates_received_ce.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_ce_updates_received_ce.pkt new file mode 100644 index 000000000000..d3fe09d0606f --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_ce_updates_received_ce.pkt @@ -0,0 +1,18 @@ +// Third ACK CE increases r.cep + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + ++0.05 < SEWA 0:0(0) win 32767 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ce] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] WAP. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_lost_data_ce.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_lost_data_ce.pkt new file mode 100644 index 000000000000..d28722db42b1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_ack_lost_data_ce.pkt @@ -0,0 +1,22 @@ +// 3rd ACK lost, CE for the first data segment + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + ++0.05 < SEWA 0:0(0) win 32767 ++.002 > SW. 0:0(0) ack 1 +// 3rd ACK lost ++0.05 < [ce] EAP. 1:1001(1000) ack 1 win 264 ++.002 > [ect0] WA. 1:1(0) ack 1001 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.05 < [ce] EAP. 1001:2001(1000) ack 1 win 264 ++.001 > [ect0] EWA. 1:1(0) ack 2001 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_dups.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_dups.pkt new file mode 100644 index 000000000000..a4d808116e34 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_3rd_dups.pkt @@ -0,0 +1,26 @@ +// Test SYN/ACK rexmit triggered 3rd ACK duplicate + CE on first data seg + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 + +// SYN/ACK rexmitted => two 3rd ACKs in-flight ++1.0~+1.1 > SW. 0:0(0) ack 1 +// Delivered 1st 3rd ACK ++0.05 < [ect0] W. 1:1(0) ack 1 win 257 ++.002 accept(3, ..., ...) = 4 + +// Duplicate 3rd ACK delivered ++1.05 < [ect0] W. 1:1(0) ack 1 win 257 + ++0.05 < [ce] EAP. 1:1001(1000) ack 1 win 257 ++.002 > [ect0] WA. 1:1(0) ack 1001 + +0 read(4, ..., 1000) = 1000 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_acc_ecn_disabled.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_acc_ecn_disabled.pkt new file mode 100644 index 000000000000..410a303c6d49 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_acc_ecn_disabled.pkt @@ -0,0 +1,13 @@ +// Test that when accurate ECN is disabled, +// client uses RFC3168 ECN for SYN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=1 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEW 0:0(0) ++0.05 < [noecn] S. 0:0(0) ack 1 win 32767 ++.002 > [noecn] . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_then_notecn_syn.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_then_notecn_syn.pkt new file mode 100644 index 000000000000..10728114b11b --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_then_notecn_syn.pkt @@ -0,0 +1,28 @@ +// Test that SYN-ACK with ACE flags and without +// ACE flags got dropped. Although we disable ECN, +// we shouldn't consider this as blackholed as +// these are dropped due to congestion + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [ect0] SEWA 0:0(0) win 32792 ++.002 > [noecn] SA. 0:0(0) ack 1 + +// Retransmit SYN ++0.1 < [noecn] S 0:0(0) win 32792 ++.002 > [noecn] SW. 0:0(0) ack 1 + ++0.1 < [noecn] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + +// Write with AccECN option but with ip-noecn since we received one SYN with ACE=0 ++0.01 write(4, ..., 100) = 100 ++.002 > [noecn] P5. 1:101(100) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_to_rfc3168.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_to_rfc3168.pkt new file mode 100644 index 000000000000..04d928f0d44d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_accecn_to_rfc3168.pkt @@ -0,0 +1,18 @@ +// Test AccECN -> RFC3168 fallback when sysctl asks for RFC3168 ECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=1 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SE. 0:0(0) ack 1 ++0.05 < . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] P. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_drop.pkt new file mode 100644 index 000000000000..788af6bea69c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_drop.pkt @@ -0,0 +1,34 @@ +// Client negotiates AccECN and starts sending +// AccECN option in last ACK and data segments +// Middlebox drops AccECN option and client +// reverts to ACE flags only + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +sysctl -q net.ipv4.tcp_ecn_option_beacon=1 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 257 ++.002 accept(3, ..., ...) = 4 + ++0.05 < [ect0] EAP. 1:1001(1000) ack 1 win 257 ++.002 > [ect0] EA. 1:1(0) ack 1001 + +0 read(4, ..., 1000) = 1000 + ++0.05 < [ect0] EAP. 1:1001(1000) ack 1 win 257 ++.002 > [ect0] EA. 1:1(0) ack 1001 + ++0.05 < [ect0] EAP. 1:1001(1000) ack 1 win 257 ++.002 > [ect0] EA. 1:1(0) ack 1001 + ++0.05 < [ect0] EAP. 1001:2001(1000) ack 1 win 257 ++.002 > [ect0] EA. 1:1(0) ack 2001 + +0 read(4, ..., 1000) = 1000 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_lost.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_lost.pkt new file mode 100644 index 000000000000..f5839c2e682d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_client_accecn_options_lost.pkt @@ -0,0 +1,38 @@ +// Client negotiates AccECN and starts sending +// AccECN option in last ACK and data segments +// Middlebox accepts AccECN option but some packets +// are lost due to congestion. Client should +// continue to send AccECN option + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.102 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.1 < [ect0] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] A. 1:1(0) ack 1 + +// Send ++0.01 write(4, ..., 3000) = 3000 ++.002 > [ect0] .5 1:1013(1012) ack 1 ++.002 > [ect0] P.5 1013:2025(1012) ack 1 ++.002 > [ect0] P.5 2025:3001(976) ack 1 + +// First two segments were lost due to congestion as SACK was +// received acknowledging 3rd segment ++0.1 < [ect0] .5 1:1(0) ack 1 win 264 + +// Since data with option was SACKed, we can +// continue to use AccECN option for the rest of +// the connection. This one is a rexmt ++.02~+0.5 > [ect0] .5 1:1013(1012) ack 1 ++0.1 < [ect0] .5 1:1(0) ack 3001 win 264 + +// Send new data, it should contain AccECN option ++0.01 write(4, ..., 2000) = 2000 ++.002 > [ect0] .5 3001:4013(1012) ack 1 ++.002 > [ect0] P.5 4013:5001(988) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_clientside_disabled.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_clientside_disabled.pkt new file mode 100644 index 000000000000..c00b36d6a833 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_clientside_disabled.pkt @@ -0,0 +1,12 @@ +// AccECN sysctl server-side only, no ECN/AccECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=5 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > S 0:0(0) ++0.05 < S. 0:0(0) ack 1 win 32767 ++.002 > . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_close_local_close_then_remote_fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_close_local_close_then_remote_fin.pkt new file mode 100644 index 000000000000..f9c27f39f354 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_close_local_close_then_remote_fin.pkt @@ -0,0 +1,25 @@ +// Test basic connection teardown where local process closes first: +// the local process calls close() first, so we send a FIN, and receive an ACK. +// Then we receive a FIN and ACK it. + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +.01...0.011 connect(3, ..., ...) = 0 + +0 > [noecn] SEWA 0:0(0) <...> + +0 < [ect1] SW. 0:0(0) ack 1 win 32768 + +0 > [ect0] EW. 1:1(0) ack 1 + + +0 write(3, ..., 1000) = 1000 + +0 > [ect0] P5. 1:1001(1000) ack 1 + +0 < [ect0] .5 1:1(0) ack 1001 win 257 + + +0 close(3) = 0 + +0 > [ect0] F5. 1001:1001(0) ack 1 + +0 < [ect0] .5 1:1(0) ack 1002 win 257 + + +0 < [ect0] F5. 1:1(0) ack 1002 win 257 + +0 > [ect0] . 1002:1002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_2ndlargeack.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_2ndlargeack.pkt new file mode 100644 index 000000000000..6d771234124a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_2ndlargeack.pkt @@ -0,0 +1,25 @@ +// Test a large ACK (> ACE field max) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 14600) = 14600 ++.002 > [ect0] P.5 1:14601(14600) ack 1 ++0.05 < [ect0] .5 1:1(0) ack 1461 win 264 ++0.05 < [ect0] .5 1:1(0) ack 14601 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 8, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_falseoverflow_detect.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_falseoverflow_detect.pkt new file mode 100644 index 000000000000..76384f52b021 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_falseoverflow_detect.pkt @@ -0,0 +1,31 @@ +// Test false overflow detection with option used to rule out overflow + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + +// Stop sending option to allow easier testing ++0 `sysctl -q net.ipv4.tcp_ecn_option=0` + ++0.002 write(4, ..., 14600) = 14600 ++.002 > [ect0] P.5 1:14601(14600) ack 1 + ++0.05 < [ect0] .5 1:1(0) ack 1460 win 264 ++0.05 < [ect0] .5 1:1(0) ack 14601 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 0, tcpi_delivered_ce +assert tcpi_delivered_e0_bytes == 14600, tcpi_delivered_e0_bytes +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack.pkt new file mode 100644 index 000000000000..8bce5dce35a2 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack.pkt @@ -0,0 +1,24 @@ +// Test a large ACK (> ACE field max) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 14600) = 14600 ++.002 > [ect0] P.5 1:14601(14600) ack 1 ++0.05 < [ect0] .5 1:1(0) ack 14601 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack2.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack2.pkt new file mode 100644 index 000000000000..5f2b147214f4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_largeack2.pkt @@ -0,0 +1,25 @@ +// Test a large ACK (> ACE field max) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 14600) = 14600 ++.002 > [ect0] P.5 1:14601(14600) ack 1 + // Fake CE ++0.05 < [ect0] .6 1:1(0) ack 14601 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 1, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_maxack.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_maxack.pkt new file mode 100644 index 000000000000..fd07bdc14f37 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_maxack.pkt @@ -0,0 +1,25 @@ +// Test a large ACK (at ACE field max delta) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 14600) = 14600 ++.002 > [ect0] P.5 1:14601(14600) ack 1 + // Fake CE ++0.05 < [ect0] .4 1:1(0) ack 14601 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 7, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_updates.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_updates.pkt new file mode 100644 index 000000000000..cb1e70ff2d26 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_delivered_updates.pkt @@ -0,0 +1,70 @@ +// Test basic AccECN CEP/CEB/E0B/E1B functionality & CEP wrapping + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ +assert tcpi_delivered_ce == 0, tcpi_delivered_ce +assert tcpi_delivered_ce_bytes == 0, tcpi_delivered_ce_bytes +}% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 + // Fake CE ++0.05 < [ect0] WA. 1:1(0) ack 1001 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 1, tcpi_delivered_ce +assert tcpi_delivered_ce_bytes == 1000, tcpi_delivered_ce_bytes +}% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 + // Fake ect0 ++0.05 < [ect0] WA. 1:1(0) ack 2001 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 1, tcpi_delivered_ce +assert tcpi_delivered_e0_bytes == 1000, tcpi_delivered_e0_bytes +}% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 2001:3001(1000) ack 1 + // Fake ce ++0.05 < [ect0] EWA. 1:1(0) ack 3001 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 2, tcpi_delivered_ce +assert tcpi_delivered_ce_bytes == 2000, tcpi_delivered_ce_bytes +}% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 3001:4001(1000) ack 1 + // Fake ect1 ++0.05 < [ect0] EWA. 1:1(0) ack 4001 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 2, tcpi_delivered_ce +assert tcpi_delivered_e1_bytes == 1000, tcpi_delivered_e1_bytes +}% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 4001:5001(1000) ack 1 + // Fake ce ++0.05 < [ect0] . 1:1(0) ack 5001 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 3, tcpi_delivered_ce +assert tcpi_delivered_ce_bytes == 3000, tcpi_delivered_ce_bytes +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn3.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn3.pkt new file mode 100644 index 000000000000..6627c7bb2d26 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn3.pkt @@ -0,0 +1,12 @@ +// Test that tcp_ecn=4 uses RFC3168 ECN for SYN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=4 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.05 connect(4, ..., ...) = 0 + ++.002 > SEW 0:0(0) ++0.05 < S. 0:0(0) ack 1 win 32767 ++.002 > . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn_field_updates_opt.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn_field_updates_opt.pkt new file mode 100644 index 000000000000..51879477bb50 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_ecn_field_updates_opt.pkt @@ -0,0 +1,35 @@ +// Test basic AccECN CEP/CEB/E0B/E1B functionality & CEP wrapping + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 257 ++.002 accept(3, ..., ...) = 4 + ++0.05 < [ce] EAP. 1:1001(1000) ack 1 win 257 ++.002 > [ect0] WA. 1:1(0) ack 1001 + +0 read(4, ..., 1000) = 1000 + ++0.05 < [ect0] EAP. 1001:2001(1000) ack 1 win 257 ++.002 > [ect0] WA. 1:1(0) ack 2001 + +0 read(4, ..., 1000) = 1000 + ++0.05 < [ce] EAP. 2001:3001(1000) ack 1 win 257 ++.002 > [ect0] EWA. 1:1(0) ack 3001 + +0 read(4, ..., 1000) = 1000 + ++0.05 < [ect1] EAP. 3001:4001(1000) ack 1 win 257 ++.002 > [ect0] EWA. 1:1(0) ack 4001 + +0 read(4, ..., 1000) = 1000 + ++0.05 < [ce] EAP. 4001:5001(1000) ack 1 win 257 ++.002 > [ect0] . 1:1(0) ack 5001 + +0 read(4, ..., 1000) = 1000 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_ipflags_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_ipflags_drop.pkt new file mode 100644 index 000000000000..0c72fa4a1251 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_ipflags_drop.pkt @@ -0,0 +1,14 @@ +// Test IP flags drop +--tolerance_usecs=50000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 1.1 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++.02 ~ +1.1 > SEWA 0:0(0) ++0.05 < S. 0:0(0) ack 1 win 32767 ++.002 > [noecn] . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_listen_opt_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_listen_opt_drop.pkt new file mode 100644 index 000000000000..171f9433e55f --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_listen_opt_drop.pkt @@ -0,0 +1,16 @@ +// SYN/ACK option drop test + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++.02 ~+2 > SW. 0:0(0) ack 1 ++.02 ~+5 > S. 0:0(0) ack 1 ++.02 ~+8 > S. 0:0(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_ack_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_ack_drop.pkt new file mode 100644 index 000000000000..0f65cf56cd2b --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_ack_drop.pkt @@ -0,0 +1,28 @@ +// Test that SYN-ACK with ACE flags and without +// ACE flags got dropped. Although we disable ECN, +// we shouldn't consider this as blackholed as +// these are dropped due to congestion + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [noecn] SEWA 0:0(0) win 32792 ++.002 > [noecn] SW. 0:0(0) ack 1 + +// Retransmit SYN-ACK without option ++1~+1.1 > [noecn] SW. 0:0(0) ack 1 + +// SYN-ACK maybe getting blackholed, disable ECN ++2~+2.2 > [noecn] S. 0:0(0) ack 1 ++4~+4.4 > [noecn] S. 0:0(0) ack 1 + +// Received an ACK after sending 3rd retransmission, not a blackhole ++0.1 < [noecn] . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_drop.pkt new file mode 100644 index 000000000000..343181633980 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_multiple_syn_drop.pkt @@ -0,0 +1,18 @@ +// Test that SYN with ACE flags and without +// ACE flags got dropped. Although we disable +// ECN, we shouldn't consider this as blackholed +// as these are dropped due to congestion + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 3.1 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++.02~+1.1 > [noecn] SEWA 0:0(0) ++.02~+1.1 > [noecn] S 0:0(0) ++.02~+1.1 > [noecn] S 0:0(0) ++0.1 < [noecn] S. 0:0(0) ack 1 win 32767 ++0~+0.01 > [noecn] . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_bleach.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_bleach.pkt new file mode 100644 index 000000000000..37dabc4603c8 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_bleach.pkt @@ -0,0 +1,23 @@ +// Test AccECN flags bleach + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [noecn] EAP. 1:1001(1000) ack 1 ++0.05 < [ect0] EAP. 1:1(0) ack 1001 win 320 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_connect.pkt new file mode 100644 index 000000000000..5b14892fda51 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_connect.pkt @@ -0,0 +1,23 @@ +// Test basic AccECN negotiation + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 ++.05 < [ect0] EAP. 1:1(0) ack 1001 win 256 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_listen.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_listen.pkt new file mode 100644 index 000000000000..25f7cb2feb25 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_listen.pkt @@ -0,0 +1,26 @@ +// Test basic AccECN negotiation + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 ++0.05 < [ect0] EAP. 1:1(0) ack 1001 win 320 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_noopt_connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_noopt_connect.pkt new file mode 100644 index 000000000000..50e08c492a69 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_noopt_connect.pkt @@ -0,0 +1,23 @@ +// Test basic AccECN negotiation without option + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 ++.05 < [ect0] EAP. 1:1(0) ack 1001 win 256 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_optenable.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_optenable.pkt new file mode 100644 index 000000000000..2904f1ba9975 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_negotiation_optenable.pkt @@ -0,0 +1,23 @@ +// Test basic AccECN negotiation, late option enable + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 ++.05 < [ect0] EAP. 1:1(0) ack 1001 win 256 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_no_ecn_after_accecn.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_no_ecn_after_accecn.pkt new file mode 100644 index 000000000000..64e0fc1c1f14 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_no_ecn_after_accecn.pkt @@ -0,0 +1,20 @@ +// Test client behavior on receiving a non ECN SYN-ACK +// after receiving an AccECN SYN-ACK and moving to +// ESTABLISHED state + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) +// Receive an AccECN SYN-ACK and move to ESTABLISHED ++0.05 < [noecn] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + +// Receive a non ECN SYN-ACK and send a challenge ACK with ACE feedback ++0.1 < [noecn] S. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_noopt.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_noopt.pkt new file mode 100644 index 000000000000..f407c629a3f7 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_noopt.pkt @@ -0,0 +1,27 @@ +// Test basic AccECN negotiation with option off using sysctl + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 ++0.05 < [ect0] EAP. 1:1(0) ack 1001 win 320 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1001:2001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_noprogress.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_noprogress.pkt new file mode 100644 index 000000000000..32454e7187f9 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_noprogress.pkt @@ -0,0 +1,27 @@ +// Test no progress filtering + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 + // Fake CE and claim no progress ++0.05 < [ect0] WA. 1:1(0) ack 1 win 264 + ++0.01 %{ +assert tcpi_delivered_ce == 0, tcpi_delivered_ce +assert tcpi_delivered_ce_bytes == 0, tcpi_delivered_ce_bytes +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_notecn_then_accecn_syn.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_notecn_then_accecn_syn.pkt new file mode 100644 index 000000000000..6597d5f2d778 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_notecn_then_accecn_syn.pkt @@ -0,0 +1,28 @@ +// Test that SYN-ACK with ACE flags and without +// ACE flags got dropped. Although we disable ECN, +// we shouldn't consider this as blackholed as +// these are dropped due to congestion + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [noecn] S 0:0(0) win 32792 ++.002 > [noecn] S. 0:0(0) ack 1 + +// Retransmit SYN ++0.1 < [ect0] SEWA 0:0(0) win 32792 ++.002 > [noecn] S. 0:0(0) ack 1 + ++0.1 < [noecn] . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + +// Write with AccECN option but with ip-noecn since we received one SYN with ACE=0 ++0.01 write(4, ..., 100) = 100 ++.002 > [noecn] P. 1:101(100) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_fallback.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_fallback.pkt new file mode 100644 index 000000000000..0f97dfcfa82d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_fallback.pkt @@ -0,0 +1,18 @@ +// Test RFC3168 fallback when sysctl asks for AccECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEW 0:0(0) win 32792 ++.002 > SE. 0:0(0) ack 1 ++0.05 < . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] P. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_rfc3168.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_rfc3168.pkt new file mode 100644 index 000000000000..9baffdd66fe5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_rfc3168_to_rfc3168.pkt @@ -0,0 +1,18 @@ +// Test RFC3168 ECN when sysctl asks for RFC3168 ECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=1 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEW 0:0(0) win 32792 ++.002 > SE. 0:0(0) ack 1 ++0.05 < . 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] P. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab.pkt new file mode 100644 index 000000000000..3fc56f9c6a6f --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab.pkt @@ -0,0 +1,28 @@ +// Test SACK space grab to fit AccECN option +--tcp_ts_tick_usecs=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++.01 < [ect1] EAP. 1001:2001(1000) ack 1 win 264 ++0.002 > [ect0] EA. 1:1(0) ack 1 ++.01 < [ect0] EAP. 3001:4001(1000) ack 1 win 264 ++0.002 > [ect0] EA. 1:1(0) ack 1 ++.01 < [ce] EAP. 5001:6001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 +// DSACK works? ++.01 < [ect0] EAP. 5001:6001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 ++.01 < [ect1] EAP. 6001:7001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab_with_ts.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab_with_ts.pkt new file mode 100644 index 000000000000..1c075b5d81ae --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_sack_space_grab_with_ts.pkt @@ -0,0 +1,39 @@ +// Test SACK space grab to fit AccECN option +--tcp_ts_tick_usecs=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + +// One SACK block should allow all 3 AccECN fields: ++.01 < [ect1] EAP. 1001:2001(1000) ack 1 win 264 ++0.002 > [ect0] EA. 1:1(0) ack 1 + +// Two SACK blocks should fit w/ AccECN if we only need to use 2 AccECN fields: check ect1 arriving. ++.01 < [ect1] EAP. 3001:4001(1000) ack 1 win 264 ++0.002 > [ect0] EA. 1:1(0) ack 1 + +// Two SACK blocks should fit w/ AccECN if we only need to use 2 AccECN fields: check CE arriving. ++.01 < [ce] EAP. 5001:6001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 + +// Check that DSACK works, using 2 SACK blocks in total, if we only need to use 2 AccECN fields: check ect1 arriving. ++.01 < [ect1] EAP. 5001:6001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 + +// Check the case where the AccECN option doesn't fit, because sending ect0 +// with order 1 would rquire 3 AccECN fields, +// and TS (12 bytes) + 2 SACK blocks (20 bytes) + 3 AccECN fields (2 + 3*3 bytes) > 40 bytes. +// That's OK; Linux TCP AccECN is optimized for the ECT1 case, not ECT0. ++.01 < [ect0] EAP. 6001:7001(1000) ack 1 win 264 ++0.002 > [ect0] WA. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled1.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled1.pkt new file mode 100644 index 000000000000..6b88ab78bfce --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled1.pkt @@ -0,0 +1,20 @@ +// Test against classic ECN server +// Not-ECT on SYN and server sets 1|0|1 (AE is unused for classic ECN) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] SEA. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0 write(4, ..., 100) = 100 ++.002 > [ect0] P.5 1:101(100) ack 1 ++0 close(4) = 0 + ++.002 > [ect0] F.5 101:101(0) ack 1 ++0.1 < [noecn] R. 1:1(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled2.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled2.pkt new file mode 100644 index 000000000000..d24ada008ece --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_accecn_disabled2.pkt @@ -0,0 +1,20 @@ +// Test against classic ECN server +// Not-ECT on SYN and server sets 0|0|1 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] SE. 0:0(0) ack 1 win 32767 ++.002 > [noecn] . 1:1(0) ack 1 + ++0 write(4, ..., 100) = 100 ++.002 > [ect0] P. 1:101(100) ack 1 ++0 close(4) = 0 + ++0 > [noecn] F. 101:101(0) ack 1 <...> ++0.1 < R. 1:1(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_broken.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_broken.pkt new file mode 100644 index 000000000000..a20d7e890ee1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_broken.pkt @@ -0,0 +1,19 @@ +// Test against broken server (1|1|1) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] SEWA. 0:0(0) ack 1 win 32767 ++.002 > [noecn] . 1:1(0) ack 1 + ++0 write(4, ..., 100) = 100 ++.002 > [noecn] P. 1:101(100) ack 1 ++0 close(4) = 0 + ++.002 > [noecn] F. 101:101(0) ack 1 <...> ++0.1 < [noecn] R. 1:1(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_ecn_disabled.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_ecn_disabled.pkt new file mode 100644 index 000000000000..428255bedab7 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_ecn_disabled.pkt @@ -0,0 +1,19 @@ +// Test against Non ECN server (0|0|0) + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [noecn] S. 0:0(0) ack 1 win 32767 ++.002 > [noecn] . 1:1(0) ack 1 + ++0 write(4, ..., 100) = 100 ++.002 > [noecn] P. 1:101(100) ack 1 ++0 close(4) = 0 + ++.002 > [noecn] F. 101:101(0) ack 1 ++0.1 < [noecn] R. 1:1(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_only.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_only.pkt new file mode 100644 index 000000000000..e9a5a0d3677c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_serverside_only.pkt @@ -0,0 +1,18 @@ +// Test AccECN with sysctl set to server-side only + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=5 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_acked_after_retransmit.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_acked_after_retransmit.pkt new file mode 100644 index 000000000000..412fa903105c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_acked_after_retransmit.pkt @@ -0,0 +1,18 @@ +// Test that SYN with ACE flags was Acked +// after 2nd retransmission. In this case, +// since we got SYN-ACK that supports Accurate +// ECN, we consider this as successful negotiation + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 2.1 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++1~+1.1 > [noecn] SEWA 0:0(0) ++1~+1.1 > [noecn] S 0:0(0) + ++0.1 < [noecn] SW. 0:0(0) ack 1 win 32767 ++0~+0.01 > [ect0] W. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_drop.pkt new file mode 100644 index 000000000000..4622754a2270 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ace_flags_drop.pkt @@ -0,0 +1,16 @@ +// Test that SYN with ACE flags got dropped +// We retry one more time with ACE and then +// fallback to disabled ECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 2.1 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++1~+1.1 > [noecn] SEWA 0:0(0) ++1~+1.1 > [noecn] S 0:0(0) ++0.1 < [noecn] S. 0:0(0) ack 1 win 32767 ++0~+0.01 > [noecn] . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_acked_after_retransmit.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_acked_after_retransmit.pkt new file mode 100644 index 000000000000..ee15f108cafe --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_acked_after_retransmit.pkt @@ -0,0 +1,27 @@ +// Test that SYN-ACK with ACE flags was Acked +// after 2nd retransmission. In this case, +// since we got the last ACK that supports Accurate +// ECN, we consider this as successful negotiation + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [noecn] SEWA 0:0(0) win 32792 ++.002 > [noecn] SW. 0:0(0) ack 1 + +// Retransmit SYN-ACK without option ++1~+1.1 > [noecn] SW. 0:0(0) ack 1 + +// SYN-ACK maybe getting blackholed, disable ECN ++2~+2.2 > [noecn] S. 0:0(0) ack 1 + +// Received an ACK with ACE flags, state should be set to negotiation succeeded ++0.1 < [noecn] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_drop.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_drop.pkt new file mode 100644 index 000000000000..ccfe353a8ee4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ack_ace_flags_drop.pkt @@ -0,0 +1,26 @@ +// Test that SYN-ACK with ACE flags got dropped +// We retry one more time with ACE and then +// fallback to disabled ECN + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [noecn] SEWA 0:0(0) win 32792 ++.002 > [noecn] SW. 0:0(0) ack 1 + +// Retransmit SYN-ACK without option ++1~+1.1 > [noecn] SW. 0:0(0) ack 1 + +// SYN-ACK maybe getting blackholed, disable ECN ++2~+2.2 > [noecn] S. 0:0(0) ack 1 + +// Received an ACK with no ACE flags, state should be set to blackholed ++0.1 < [noecn] . 1:1(0) ack 1 win 320 ++0 accept(3, ..., ...) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ce.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ce.pkt new file mode 100644 index 000000000000..dc83f7a18180 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ce.pkt @@ -0,0 +1,13 @@ +// Test AccECN ECN field reflector in SYNACK + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < [ce] SEWA 0:0(0) win 32792 ++.002 > SWA. 0:0(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect0.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect0.pkt new file mode 100644 index 000000000000..e63a8d018c37 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect0.pkt @@ -0,0 +1,13 @@ +// Test AccECN ECN field reflector in SYNACK + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < [ect0] SEWA 0:0(0) win 32792 ++.002 > SA. 0:0(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect1.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect1.pkt new file mode 100644 index 000000000000..23c0e43b3dbe --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_syn_ect1.pkt @@ -0,0 +1,13 @@ +// Test AccECN ECN field reflector in SYNACK + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < [ect1] SEWA 0:0(0) win 32792 ++.002 > SEW. 0:0(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce.pkt new file mode 100644 index 000000000000..c3497738f680 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce.pkt @@ -0,0 +1,27 @@ +// Test SYNACK CE & received_ce update + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > [noecn] SEWA 0:0(0) ++0.05 < [ce] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] WA. 1:1(0) ack 1 + ++0.01 write(4, ..., 100) = 100 ++.002 > [ect0] P.6 1:101(100) ack 1 ++0.05 < [ect0] P.5 1:101(100) ack 101 win 256 ++.002 > [ect0] .6 101:101(0) ack 101 + ++0.01 write(4, ..., 100) = 100 ++.002 > [ect0] P.6 101:201(100) ack 101 + ++0.1 < [ect1] P.5 201:301(100) ack 201 win 256 ++.002 > [ect0] .6 201:201(0) ack 101 + ++0.01 < [ce] .6 401:501(100) ack 201 win 256 ++.002 > [ect0] .7 201:201(0) ack 101 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce_updates_delivered_ce.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce_updates_delivered_ce.pkt new file mode 100644 index 000000000000..5fd77f466572 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ce_updates_delivered_ce.pkt @@ -0,0 +1,22 @@ +// Reflected SYNACK CE mark increases delivered_ce + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_fallback=0 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + ++0.05 < SEWA 0:0(0) win 32767 ++.002 > SW. 0:0(0) ack 1 +// Fake ce for prev, ECT validator must be disabled for this to work ++0.05 < [ect0] WA. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 1, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect0.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect0.pkt new file mode 100644 index 000000000000..f6ad1ea5c0c4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect0.pkt @@ -0,0 +1,24 @@ +// Test SYN=0 reflector + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < [ect0] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] A. 1:1(0) ack 1 + ++0.01 write(4, ..., 100) = 100 ++.002 > [ect0] P.5 1:101(100) ack 1 ++0.05 < [ect0] P.5 1:1(0) ack 101 win 256 + ++0.01 < [ect0] P.5 1:101(100) ack 101 win 256 ++.002 > [ect0] .5 101:101(0) ack 101 ++0 read(4, ..., 100) = 100 + ++0 close(4) = 0 ++0 > F.5 101:101(0) ack 101 <...> ++0.1 < R. 101:101(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect1.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect1.pkt new file mode 100644 index 000000000000..7ecfc5fb9dbb --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_ect1.pkt @@ -0,0 +1,24 @@ +// Test SYN=0 reflector + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < [ect1] SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] EW. 1:1(0) ack 1 + ++0.01 write(4, ..., 100) = 100 ++.002 > [ect0] P.5 1:101(100) ack 1 ++0.05 < [ect1] P.5 1:1(0) ack 101 win 256 + ++0.01 < [ect1] P.5 1:101(100) ack 101 win 256 ++.002 > [ect0] .5 101:101(0) ack 101 ++0 read(4, ..., 100) = 100 + ++0 close(4) = 0 ++0 > F5. 101:101(0) ack 101 <...> ++0.1 < R. 101:101(0) ack 102 win 4242 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rexmit.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rexmit.pkt new file mode 100644 index 000000000000..9e0959782ef5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rexmit.pkt @@ -0,0 +1,15 @@ +// Test 3rd ACK flags when SYN-ACK is rexmitted + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++.002 ... 0.052 connect(4, ..., ...) = 0 + ++.002 > SEWA 0:0(0) ++0.05 < SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 + ++0.05 < SW. 0:0(0) ack 1 win 32767 ++.002 > [ect0] W. 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rxmt.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rxmt.pkt new file mode 100644 index 000000000000..a5a41633af07 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_synack_rxmt.pkt @@ -0,0 +1,25 @@ +// Test that we retransmit SYN-ACK with ACE and without +// AccECN options after +// SYN-ACK was lost and TCP moved to TCPS_SYN_RECEIVED + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +sysctl -q net.ipv4.tcp_ecn_option=2 +` + ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 ++0 bind(3, ..., ...) = 0 ++0 listen(3, 1) = 0 + ++0 < [noecn] SEWA 0:0(0) win 32792 ++.002 > [noecn] SW. 0:0(0) ack 1 + +// Retransmit SYN-ACK without option ++1~+1.1 > [noecn] SW. 0:0(0) ack 1 ++0.1 < [noecn] W. 1:1(0) ack 1 win 320 ++.002 accept(3, ..., ...) = 4 + +// We try to write with AccECN option ++0.01 write(4, ..., 100) = 100 ++.002 > [ect0] P5. 1:101(100) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_tsnoprogress.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_tsnoprogress.pkt new file mode 100644 index 000000000000..f3fe2f098966 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_tsnoprogress.pkt @@ -0,0 +1,26 @@ +// Test TS progress filtering +--tcp_ts_tick_usecs=1000 +--tolerance_usecs=7000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 + // Fake CE and claim no progress ++0.05 < [ect0] WA. 1:1(0) ack 1 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_accecn_tsprogress.pkt b/tools/testing/selftests/net/packetdrill/tcp_accecn_tsprogress.pkt new file mode 100644 index 000000000000..1446799d2481 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_accecn_tsprogress.pkt @@ -0,0 +1,25 @@ +// Test TS progress filtering +--tcp_ts_tick_usecs=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=3 +` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < SEWA 0:0(0) win 32792 ++.002 > SW. 0:0(0) ack 1 ++0.05 < [ect0] W. 1:1(0) ack 1 win 264 ++.002 accept(3, ..., ...) = 4 + ++0.01 %{ assert tcpi_delivered_ce == 0, tcpi_delivered_ce }% + ++0.01 write(4, ..., 1000) = 1000 ++.002 > [ect0] EAP. 1:1001(1000) ack 1 + // Fake CE and claim no progress ++0.05 < [ect0] WA. 1:1(0) ack 1 win 264 + ++0.01 %{ assert tcpi_delivered_ce == 1, tcpi_delivered_ce }%