From: Chia-Yu Chang <chia-yu.ch...@nokia-bell-labs.com>
AccECN option may fail in various way, handle these:
- Remove option from SYN/ACK rexmits to handle blackholes
- If no option arrives in SYN/ACK, assume Option is not usable
- If an option arrives later, re-enabled
- If option is zeroed, disable AccECN option processing
This patch use existing padding bits in tcp_request_sock and
holes in tcp_sock without increasing the size.
Signed-off-by: Ilpo Järvinen <i...@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.ch...@nokia-bell-labs.com>
---
include/linux/tcp.h | 4 ++-
include/net/tcp.h | 7 +++++
net/ipv4/tcp.c | 1 +
net/ipv4/tcp_input.c | 68 +++++++++++++++++++++++++++++++++++-----
net/ipv4/tcp_minisocks.c | 38 ++++++++++++++++++++++
net/ipv4/tcp_output.c | 5 ++-
6 files changed, 113 insertions(+), 10 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 0740efaaef28..b5066eef8782 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -173,6 +173,7 @@ struct tcp_request_sock {
u8 syn_ect_snt: 2,
syn_ect_rcv: 2,
accecn_fail_mode:4;
+ u8 saw_accecn_opt :2;
#ifdef CONFIG_TCP_AO
u8 ao_keyid;
u8 ao_rcv_next;
@@ -409,7 +410,8 @@ struct tcp_sock {
syn_fastopen_child:1; /* created TFO passive child socket */
u8 keepalive_probes; /* num of allowed keep alive probes */
- u8 accecn_fail_mode:4; /* AccECN failure handling */
+ u8 accecn_fail_mode:4, /* AccECN failure handling */
+ saw_accecn_opt:2; /* An AccECN option was seen */
u32 tcp_tx_delay; /* delay (in usec) added to TX packets */
/* RTT measurement */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3419618a7891..5e4593e39de4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -279,6 +279,12 @@ static inline void tcp_accecn_fail_mode_set(struct
tcp_sock *tp, u8 mode)
tp->accecn_fail_mode |= mode;
}
+/* tp->saw_accecn_opt states */
+#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
+
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
@@ -480,6 +486,7 @@ static inline int tcp_accecn_extract_syn_ect(u8 ace)
bool tcp_accecn_validate_syn_feedback(struct sock *sk, u8 ace, u8 sent_ect);
void tcp_accecn_third_ack(struct sock *sk, const struct sk_buff *skb,
u8 syn_ect_snt);
+u8 tcp_accecn_option_init(const struct sk_buff *skb, u8 opt_offset);
void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
u32 payload_len);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 20a2e30e15f3..e68b9706eeff 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3399,6 +3399,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->delivered_ce = 0;
tp->wait_third_ack = 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;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 10c37a41b9a5..c93e4bffb23e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -446,9 +446,8 @@ bool tcp_accecn_validate_syn_feedback(struct sock *sk, u8
ace, u8 sent_ect)
}
/* See Table 2 of the AccECN draft */
-
-static void tcp_ecn_rcv_synack(struct sock *sk, const struct tcphdr *th,
- u8 ip_dsfield)
+static void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb,
+ const struct tcphdr *th, u8 ip_dsfield)
{
struct tcp_sock *tp = tcp_sk(sk);
u8 ace = tcp_accecn_ace(th);
@@ -487,7 +486,19 @@ static void tcp_ecn_rcv_synack(struct sock *sk, const
struct tcphdr *th,
default:
tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK;
- tp->accecn_opt_demand = 2;
+ 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);
+
+ tp->saw_accecn_opt = saw_opt;
+ if (tp->saw_accecn_opt == TCP_ACCECN_OPT_FAIL_SEEN) {
+ u8 fail_mode = TCP_ACCECN_OPT_FAIL_RECV;
+
+ tcp_accecn_fail_mode_set(tp, fail_mode);
+ }
+ tp->accecn_opt_demand = 2;
+ }
if (INET_ECN_is_ce(ip_dsfield) &&
tcp_accecn_validate_syn_feedback(sk, ace,
tp->syn_ect_snt)) {
@@ -603,7 +614,23 @@ 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 fail_mode = TCP_ACCECN_OPT_FAIL_RECV;
+
+ tp->saw_accecn_opt = TCP_ACCECN_OPT_FAIL_SEEN;
+ tcp_accecn_fail_mode_set(tp, fail_mode);
+ }
+ return false;
+ }
+
if (estimate_ecnfield) {
u8 ecnfield = estimate_ecnfield - 1;
@@ -619,6 +646,13 @@ 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++) {
if (optlen < TCPOLEN_ACCECN_PERFIELD)
@@ -6481,10 +6515,25 @@ static bool tcp_validate_incoming(struct sock *sk,
struct sk_buff *skb,
*/
if (th->syn) {
if (tcp_ecn_mode_accecn(tp)) {
- u8 opt_demand = max_t(u8, 1, tp->accecn_opt_demand);
-
accecn_reflector = true;
- tp->accecn_opt_demand = opt_demand;
+ if (tp->rx_opt.accecn &&
+ tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
+ u8 offset = tp->rx_opt.accecn;
+ u8 opt_demand;
+ u8 saw_opt;
+
+ saw_opt = tcp_accecn_option_init(skb, offset);
+ tp->saw_accecn_opt = saw_opt;
+ if (tp->saw_accecn_opt ==
+ TCP_ACCECN_OPT_FAIL_SEEN) {
+ u8 fail_mode = TCP_ACCECN_OPT_FAIL_RECV;
+
+ tcp_accecn_fail_mode_set(tp, fail_mode);
+ }
+ opt_demand = max_t(u8, 1,
+ tp->accecn_opt_demand);
+ tp->accecn_opt_demand = opt_demand;
+ }
}
if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
@@ -6974,7 +7023,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk,
struct sk_buff *skb,
*/
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);
@@ -7549,6 +7599,8 @@ 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 e0f2bd2cee9e..87b03ee74676 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -501,6 +501,7 @@ 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(sk, skb, skb->len - th->doff * 4);
@@ -555,6 +556,30 @@ static void smc_check_reset_syn_req(const struct tcp_sock
*oldtp,
#endif
}
+u8 tcp_accecn_option_init(const struct sk_buff *skb, u8 opt_offset)
+{
+ u8 *ptr = skb_transport_header(skb) + opt_offset;
+ unsigned int optlen = ptr[1] - 2;
+
+ WARN_ON_ONCE(ptr[0] != TCPOPT_ACCECN0 && ptr[0] != TCPOPT_ACCECN1);
+ ptr += 2;
+
+ /* Detect option zeroing: an AccECN connection "MAY check that the
+ * initial value of the EE0B field or the EE1B field is non-zero"
+ */
+ if (optlen < TCPOLEN_ACCECN_PERFIELD)
+ return TCP_ACCECN_OPT_EMPTY_SEEN;
+ if (get_unaligned_be24(ptr) == 0)
+ return TCP_ACCECN_OPT_FAIL_SEEN;
+ if (optlen < TCPOLEN_ACCECN_PERFIELD * 3)
+ return TCP_ACCECN_OPT_COUNTER_SEEN;
+ ptr += TCPOLEN_ACCECN_PERFIELD * 2;
+ if (get_unaligned_be24(ptr) == 0)
+ return TCP_ACCECN_OPT_FAIL_SEEN;
+
+ return TCP_ACCECN_OPT_COUNTER_SEEN;
+}
+
/* This is not only more efficient than what we used to do, it eliminates
* a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
*
@@ -716,6 +741,7 @@ 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);
@@ -893,6 +919,18 @@ 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 ea37a30ff71c..b630923c4cef 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1086,6 +1086,7 @@ static unsigned int tcp_syn_options(struct sock *sk,
struct sk_buff *skb,
/* Simultaneous open SYN/ACK needs AccECN option but not SYN */
if (unlikely((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) &&
tcp_ecn_mode_accecn(tp) &&
+ inet_csk(sk)->icsk_retransmits < 2 &&
sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
remaining >= TCPOLEN_ACCECN_BASE)) {
u32 saving = tcp_synack_options_combine_saving(opts);
@@ -1175,7 +1176,7 @@ static unsigned int tcp_synack_options(const struct sock
*sk,
smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
if (treq->accecn_ok && sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
- remaining >= TCPOLEN_ACCECN_BASE) {
+ req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) {
u32 saving = tcp_synack_options_combine_saving(opts);
opts->ecn_bytes = synack_ecn_bytes;
@@ -1254,6 +1255,8 @@ static unsigned int tcp_established_options(struct sock
*sk, struct sk_buff *skb
if (tcp_ecn_mode_accecn(tp) &&
sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
+ tp->saw_accecn_opt &&
+ !tcp_accecn_opt_fail_send(tp) &&
(sock_net(sk)->ipv4.sysctl_tcp_ecn_option >= TCP_ECN_OPTION_FULL ||
tp->accecn_opt_demand ||
tcp_accecn_option_beacon_check(sk))) {
--
2.34.1
