summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/networking/net_cachelines/tcp_sock.rst2
-rw-r--r--include/linux/tcp.h3
-rw-r--r--include/net/tcp.h15
-rw-r--r--include/net/tcp_ecn.h53
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_input.c100
-rw-r--r--net/ipv4/tcp_output.c9
7 files changed, 175 insertions, 12 deletions
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 7bbda5944ee2..31313a9adccc 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -101,6 +101,8 @@ u32 prr_delivered
u32 prr_out read_mostly read_mostly tcp_rate_skb_sent,tcp_newly_delivered(tx);tcp_ack,tcp_rate_gen,tcp_clean_rtx_queue(rx)
u32 delivered read_mostly read_write tcp_rate_skb_sent, tcp_newly_delivered(tx);tcp_ack, tcp_rate_gen, tcp_clean_rtx_queue (rx)
u32 delivered_ce read_mostly read_write tcp_rate_skb_sent(tx);tcp_rate_gen(rx)
+u32 received_ce read_mostly read_write
+u8:4 received_ce_pending read_mostly read_write
u32 lost read_mostly tcp_ack
u32 app_limited read_write read_mostly tcp_rate_check_app_limited,tcp_rate_skb_sent(tx);tcp_rate_gen(rx)
u64 first_tx_mstamp read_write tcp_rate_skb_sent
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d103cc0e7a35..90cee6e53527 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -287,6 +287,8 @@ 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;
__be32 pred_flags;
u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
u64 tcp_mstamp; /* most recent packet received/sent */
@@ -299,6 +301,7 @@ struct tcp_sock {
u32 snd_up; /* Urgent pointer */
u32 delivered; /* Total data packets delivered incl. rexmits */
u32 delivered_ce; /* Like the above but only ECE marked packets */
+ u32 received_ce; /* Like the above but for rcvd CE marked pkts */
u32 app_limited; /* limited until "delivered" reaches this val */
u32 rcv_wnd; /* Current receiver window */
/*
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e25340459ce4..bc5159fe842e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -973,6 +973,14 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
+#define TCP_ACCECN_CEP_ACE_MASK 0x7
+#define TCP_ACCECN_ACE_MAX_DELTA 6
+
+/* To avoid/detect middlebox interference, not all counters start at 0.
+ * See draft-ietf-tcpm-accurate-ecn for the latest values.
+ */
+#define TCP_ACCECN_CEP_INIT_OFFSET 5
+
/* State flags for sacked in struct tcp_skb_cb */
enum tcp_skb_cb_sacked_flags {
TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */
@@ -1782,11 +1790,18 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
+ u32 ace;
+
/* mptcp hooks are only on the slow path */
if (sk_is_mptcp((struct sock *)tp))
return;
+ ace = tcp_ecn_mode_accecn(tp) ?
+ ((tp->delivered_ce + TCP_ACCECN_CEP_INIT_OFFSET) &
+ TCP_ACCECN_CEP_ACE_MASK) : 0;
+
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
+ (ace << 22) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
}
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index b3430557676b..b0ed89dbad41 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -12,6 +12,7 @@
static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp)
{
+ /* Do not set CWR if in AccECN mode! */
if (tcp_ecn_mode_rfc3168(tp))
tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
}
@@ -19,8 +20,10 @@ static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp)
static inline void tcp_ecn_accept_cwr(struct sock *sk,
const struct sk_buff *skb)
{
- if (tcp_hdr(skb)->cwr) {
- tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tcp_ecn_mode_rfc3168(tp) && tcp_hdr(skb)->cwr) {
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
/* If the sender is telling us it has entered CWR, then its
* cwnd may be very low (even just 1 packet), so we should ACK
@@ -36,6 +39,52 @@ static inline void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
}
+static inline u8 tcp_accecn_ace(const struct tcphdr *th)
+{
+ return (th->ae << 2) | (th->cwr << 1) | th->ece;
+}
+
+static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
+{
+ tp->received_ce = 0;
+ tp->received_ce_pending = 0;
+}
+
+/* Updates Accurate ECN received counters from the received IP ECN field */
+static inline void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb)
+{
+ u8 ecnfield = TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK;
+ u8 is_ce = INET_ECN_is_ce(ecnfield);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!INET_ECN_is_not_ect(ecnfield)) {
+ u32 pcount = is_ce * max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+
+ /* As for accurate ECN, the TCP_ECN_SEEN flag is set by
+ * tcp_ecn_received_counters() when the ECN codepoint of
+ * received TCP data or ACK contains ECT(0), ECT(1), or CE.
+ */
+ if (!tcp_ecn_mode_rfc3168(tp))
+ tp->ecn_flags |= TCP_ECN_SEEN;
+
+ /* ACE counter tracks *all* segments including pure ACKs */
+ tp->received_ce += pcount;
+ tp->received_ce_pending = min(tp->received_ce_pending + pcount,
+ 0xfU);
+ }
+}
+
+static inline void tcp_accecn_set_ace(struct tcphdr *th, struct tcp_sock *tp)
+{
+ u32 wire_ace;
+
+ wire_ace = tp->received_ce + TCP_ACCECN_CEP_INIT_OFFSET;
+ th->ece = !!(wire_ace & 0x1);
+ th->cwr = !!(wire_ace & 0x2);
+ th->ae = !!(wire_ace & 0x4);
+ tp->received_ce_pending = 0;
+}
+
static inline void tcp_ecn_rcv_synack(struct tcp_sock *tp,
const struct tcphdr *th)
{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1f643faa8b93..16456c10e5e8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -271,6 +271,7 @@
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
+#include <net/tcp_ecn.h>
#include <net/mptcp.h>
#include <net/proto_memory.h>
#include <net/xfrm.h>
@@ -3406,6 +3407,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
+ tcp_accecn_init_counters(tp);
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));
@@ -5138,6 +5140,7 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ce);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
@@ -5145,7 +5148,7 @@ static void __init tcp_struct_check(void)
/* 32bit arches with 8byte alignment on u64 fields might need padding
* before tcp_clock_cache.
*/
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 91 + 4);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 95 + 4);
/* RX read-write hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b2793e749cfd..98782134c2f4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -360,16 +360,25 @@ static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb)
if (tcp_ca_needs_ecn(sk))
tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
- if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
+ if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR) &&
+ tcp_ecn_mode_rfc3168(tp)) {
/* Better not delay acks, sender can have a very low cwnd */
tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
+ /* As for RFC3168 ECN, the TCP_ECN_SEEN flag is set by
+ * tcp_data_ecn_check() when the ECN codepoint of
+ * received TCP data contains ECT(0), ECT(1), or CE.
+ */
+ if (!tcp_ecn_mode_rfc3168(tp))
+ break;
tp->ecn_flags |= TCP_ECN_SEEN;
break;
default:
if (tcp_ca_needs_ecn(sk))
tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
+ if (!tcp_ecn_mode_rfc3168(tp))
+ break;
tp->ecn_flags |= TCP_ECN_SEEN;
break;
}
@@ -385,10 +394,64 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
bool ece_ack)
{
tp->delivered += delivered;
- if (ece_ack)
+ if (tcp_ecn_mode_rfc3168(tp) && ece_ack)
tcp_count_delivered_ce(tp, delivered);
}
+/* Returns the ECN CE delta */
+static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
+ u32 delivered_pkts, int flag)
+{
+ const struct tcphdr *th = tcp_hdr(skb);
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 delta, safe_delta;
+ u32 corrected_ace;
+
+ /* Reordered ACK or uncertain due to lack of data to send and ts */
+ if (!(flag & (FLAG_FORWARD_PROGRESS | FLAG_TS_PROGRESS)))
+ return 0;
+
+ if (!(flag & FLAG_SLOWPATH)) {
+ /* AccECN counter might overflow on large ACKs */
+ if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK)
+ return 0;
+ }
+
+ /* ACE field is not available during handshake */
+ if (flag & FLAG_SYN_ACKED)
+ return 0;
+
+ if (tp->received_ce_pending >= TCP_ACCECN_ACE_MAX_DELTA)
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+
+ corrected_ace = tcp_accecn_ace(th) - TCP_ACCECN_CEP_INIT_OFFSET;
+ delta = (corrected_ace - tp->delivered_ce) & TCP_ACCECN_CEP_ACE_MASK;
+ if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK)
+ return delta;
+
+ safe_delta = delivered_pkts -
+ ((delivered_pkts - delta) & TCP_ACCECN_CEP_ACE_MASK);
+
+ return safe_delta;
+}
+
+static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
+ u32 delivered_pkts, int *flag)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 delta;
+
+ delta = __tcp_accecn_process(sk, skb, delivered_pkts, *flag);
+ if (delta > 0) {
+ tcp_count_delivered_ce(tp, delta);
+ *flag |= FLAG_ECE;
+ /* Recalculate header predictor */
+ if (tp->pred_flags)
+ tcp_fast_path_on(tp);
+ }
+ return delta;
+}
+
/* Buffer size and advertised window tuning.
*
* 1. Tuning sk->sk_sndbuf, when connection enters established state.
@@ -3744,7 +3807,8 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
}
/* Returns the number of packets newly acked or sacked by the current ACK */
-static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
+static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered,
+ u32 ecn_count, int flag)
{
const struct net *net = sock_net(sk);
struct tcp_sock *tp = tcp_sk(sk);
@@ -3752,8 +3816,12 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
delivered = tp->delivered - prior_delivered;
NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
- if (flag & FLAG_ECE)
- NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
+
+ if (flag & FLAG_ECE) {
+ if (tcp_ecn_mode_rfc3168(tp))
+ ecn_count = delivered;
+ NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, ecn_count);
+ }
return delivered;
}
@@ -3774,6 +3842,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 delivered = tp->delivered;
u32 lost = tp->lost;
int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */
+ u32 ecn_count = 0; /* Did we receive ECE/an AccECN ACE update? */
u32 prior_fack;
sack_state.first_sackt = 0;
@@ -3881,6 +3950,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_rack_update_reo_wnd(sk, &rs);
+ if (tcp_ecn_mode_accecn(tp))
+ ecn_count = tcp_accecn_process(sk, skb,
+ tp->delivered - delivered,
+ &flag);
+
tcp_in_ack_event(sk, flag);
if (tp->tlp_high_seq)
@@ -3905,7 +3979,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
sk_dst_confirm(sk);
- delivered = tcp_newly_delivered(sk, delivered, flag);
+ delivered = tcp_newly_delivered(sk, delivered, ecn_count, flag);
+
lost = tp->lost - lost; /* freshly marked lost */
rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
@@ -3914,12 +3989,16 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
return 1;
no_queue:
+ if (tcp_ecn_mode_accecn(tp))
+ ecn_count = tcp_accecn_process(sk, skb,
+ tp->delivered - delivered,
+ &flag);
tcp_in_ack_event(sk, flag);
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK) {
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
- tcp_newly_delivered(sk, delivered, flag);
+ tcp_newly_delivered(sk, delivered, ecn_count, flag);
}
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
@@ -3940,7 +4019,7 @@ old_ack:
&sack_state);
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
&rexmit);
- tcp_newly_delivered(sk, delivered, flag);
+ tcp_newly_delivered(sk, delivered, ecn_count, flag);
tcp_xmit_recovery(sk, rexmit);
}
@@ -6071,6 +6150,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
flag |= __tcp_replace_ts_recent(tp,
delta);
+ tcp_ecn_received_counters(sk, skb);
+
/* We know that such packets are checksummed
* on entry.
*/
@@ -6119,6 +6200,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
/* Bulk data transfer: receiver */
tcp_cleanup_skb(skb);
__skb_pull(skb, tcp_header_len);
+ tcp_ecn_received_counters(sk, skb);
eaten = tcp_queue_rcv(sk, skb, &fragstolen);
tcp_event_data_recv(sk, skb);
@@ -6159,6 +6241,8 @@ validate:
return;
step5:
+ tcp_ecn_received_counters(sk, skb);
+
reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT);
if ((int)reason < 0) {
reason = -reason;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index be8ceefa5332..a3a6d3e91d84 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -328,7 +328,14 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_ecn_mode_rfc3168(tp)) {
+ if (!tcp_ecn_mode_any(tp))
+ return;
+
+ if (tcp_ecn_mode_accecn(tp)) {
+ INET_ECN_xmit(sk);
+ tcp_accecn_set_ace(th, tp);
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN;
+ } else {
/* Not-retransmitted data segment: set ECT and inject CWR. */
if (skb->len != tcp_header_len &&
!before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {
generated by cgit v1.2.3 (git 2.39.0) at 2026-04-23 22:25:07 +0300