aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_input.c35
-rw-r--r--net/ipv4/tcp_minisocks.c14
-rw-r--r--net/ipv4/tcp_output.c11
4 files changed, 58 insertions, 5 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 090f9ac43d4c..5b5c655ded1d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3409,6 +3409,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->delivered = 0;
tp->delivered_ce = 0;
tp->accecn_fail_mode = 0;
+ tp->saw_accecn_opt = TCP_ACCECN_OPT_NOT_SEEN;
tcp_accecn_init_counters(tp);
tp->prev_ecnfield = 0;
tp->accecn_opt_tstamp = 0;
@@ -4287,6 +4288,8 @@ 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;
+ 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;
info->tcpi_delivered_e1_bytes = tp->delivered_ecn_bytes[ect1_idx];
info->tcpi_delivered_e0_bytes = tp->delivered_ecn_bytes[ect0_idx];
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 87154fd86167..5732f2d4329c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -398,7 +398,22 @@ static bool tcp_accecn_process_option(struct tcp_sock *tp,
unsigned int i;
u8 *ptr;
+ if (tcp_accecn_opt_fail_recv(tp))
+ return false;
+
if (!(flag & FLAG_SLOWPATH) || !tp->rx_opt.accecn) {
+ if (!tp->saw_accecn_opt) {
+ /* Too late to enable after this point due to
+ * potential counter wraps
+ */
+ if (tp->bytes_sent >= (1 << 23) - 1) {
+ u8 saw_opt = TCP_ACCECN_OPT_FAIL_SEEN;
+
+ tcp_accecn_saw_opt_fail_recv(tp, saw_opt);
+ }
+ return false;
+ }
+
if (estimate_ecnfield) {
u8 ecnfield = estimate_ecnfield - 1;
@@ -415,6 +430,13 @@ static bool tcp_accecn_process_option(struct tcp_sock *tp,
order1 = (ptr[0] == TCPOPT_ACCECN1);
ptr += 2;
+ if (tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
+ tp->saw_accecn_opt = tcp_accecn_option_init(skb,
+ tp->rx_opt.accecn);
+ if (tp->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN)
+ tcp_accecn_fail_mode_set(tp, TCP_ACCECN_OPT_FAIL_RECV);
+ }
+
res = !!estimate_ecnfield;
for (i = 0; i < 3; i++) {
u32 init_offset;
@@ -6123,7 +6145,13 @@ step1:
if (th->syn) {
if (tcp_ecn_mode_accecn(tp)) {
accecn_reflector = true;
- tcp_accecn_opt_demand_min(sk, 1);
+ 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);
+ tcp_accecn_opt_demand_min(sk, 1);
+ }
}
if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
@@ -6606,7 +6634,8 @@ consume:
*/
if (tcp_ecn_mode_any(tp))
- tcp_ecn_rcv_synack(sk, th, TCP_SKB_CB(skb)->ip_dsfield);
+ tcp_ecn_rcv_synack(sk, skb, th,
+ TCP_SKB_CB(skb)->ip_dsfield);
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
tcp_try_undo_spurious_syn(sk);
@@ -7177,6 +7206,8 @@ static void tcp_openreq_init(struct request_sock *req,
tcp_rsk(req)->snt_tsval_first = 0;
tcp_rsk(req)->last_oow_ack_time = 0;
tcp_rsk(req)->accecn_ok = 0;
+ tcp_rsk(req)->saw_accecn_opt = TCP_ACCECN_OPT_NOT_SEEN;
+ tcp_rsk(req)->accecn_fail_mode = 0;
tcp_rsk(req)->syn_ect_rcv = 0;
tcp_rsk(req)->syn_ect_snt = 0;
req->mss = rx_opt->mss_clamp;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 193343494558..327095ef95ef 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -463,6 +463,7 @@ static void tcp_ecn_openreq_child(struct sock *sk,
tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
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;
tp->prev_ecnfield = treq->syn_ect_rcv;
tp->accecn_opt_demand = 1;
tcp_ecn_received_counters_payload(sk, skb);
@@ -678,6 +679,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
bool own_req;
tmp_opt.saw_tstamp = 0;
+ tmp_opt.accecn = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);
@@ -855,6 +857,18 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!(flg & TCP_FLAG_ACK))
return NULL;
+ if (tcp_rsk(req)->accecn_ok && tmp_opt.accecn &&
+ tcp_rsk(req)->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
+ u8 saw_opt = tcp_accecn_option_init(skb, tmp_opt.accecn);
+
+ tcp_rsk(req)->saw_accecn_opt = saw_opt;
+ if (tcp_rsk(req)->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN) {
+ u8 fail_mode = TCP_ACCECN_OPT_FAIL_RECV;
+
+ tcp_rsk(req)->accecn_fail_mode |= fail_mode;
+ }
+ }
+
/* For Fast Open no more processing is needed (sk is the
* child socket).
*/
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f897c2594954..65b90f73daa0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -985,9 +985,14 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
}
}
- /* Simultaneous open SYN/ACK needs AccECN option but not SYN */
+ /* Simultaneous open SYN/ACK needs AccECN option but not SYN.
+ * It is attempted to negotiate the use of AccECN also on the first
+ * retransmitted SYN, as mentioned in "3.1.4.1. Retransmitted SYNs"
+ * of AccECN draft.
+ */
if (unlikely((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) &&
tcp_ecn_mode_accecn(tp) &&
+ inet_csk(sk)->icsk_retransmits < 2 &&
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) &&
remaining >= TCPOLEN_ACCECN_BASE)) {
opts->use_synack_ecn_bytes = 1;
@@ -1076,7 +1081,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
if (treq->accecn_ok &&
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) &&
- remaining >= TCPOLEN_ACCECN_BASE) {
+ req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) {
opts->use_synack_ecn_bytes = 1;
remaining -= tcp_options_fit_accecn(opts, 0, remaining);
}
@@ -1156,7 +1161,7 @@ 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 &&
+ if (ecn_opt && tp->saw_accecn_opt && !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;
generated by cgit v1.2.3 (git 2.39.1) at 2026-01-03 01:09:36 +0000