Commit aa55a7dd authored Sep 16, 2025 by Chia-Yu Chang Committed by Paolo Abeni Sep 18, 2025

tcp: accecn: AccECN option send control



Instead of sending the option in every ACK, limit sending to
those ACKs where the option is necessary:
- Handshake
- "Change-triggered ACK" + the ACK following it. The
  2nd ACK is necessary to unambiguously indicate which
  of the ECN byte counters in increasing. The first
  ACK has two counters increasing due to the ecnfield
  edge.
- ACKs with CE to allow CEP delta validations to take
  advantage of the option.
- Force option to be sent every at least once per 2^22
  bytes. The check is done using the bit edges of the
  byte counters (avoids need for extra variables).
- AccECN option beacon to send a few times per RTT even if
  nothing in the ECN state requires that. The default is 3
  times per RTT, and its period can be set via
  sysctl_tcp_ecn_option_beacon.

Below are the pahole outcomes before and after this patch,
in which the group size of tcp_sock_write_tx is increased
from 89 to 97 due to the new u64 accecn_opt_tstamp member:

[BEFORE THIS PATCH]
struct tcp_sock {
    [...]
    u64                        tcp_wstamp_ns;        /*  2488     8 */
    struct list_head           tsorted_sent_queue;   /*  2496    16 */

    [...]
    __cacheline_group_end__tcp_sock_write_tx[0];     /*  2521     0 */
    __cacheline_group_begin__tcp_sock_write_txrx[0]; /*  2521     0 */
    u8                         nonagle:4;            /*  2521: 0  1 */
    u8                         rate_app_limited:1;   /*  2521: 4  1 */
    /* XXX 3 bits hole, try to pack */

    /* Force alignment to the next boundary: */
    u8                         :0;
    u8                         received_ce_pending:4;/*  2522: 0  1 */
    u8                         unused2:4;            /*  2522: 4  1 */
    u8                         accecn_minlen:2;      /*  2523: 0  1 */
    u8                         est_ecnfield:2;       /*  2523: 2  1 */
    u8                         unused3:4;            /*  2523: 4  1 */

    [...]
    __cacheline_group_end__tcp_sock_write_txrx[0];   /*  2628     0 */

    [...]
    /* size: 3200, cachelines: 50, members: 171 */
}

[AFTER THIS PATCH]
struct tcp_sock {
    [...]
    u64                        tcp_wstamp_ns;        /*  2488     8 */
    u64                        accecn_opt_tstamp;    /*  2596     8 */
    struct list_head           tsorted_sent_queue;   /*  2504    16 */

    [...]
    __cacheline_group_end__tcp_sock_write_tx[0];     /*  2529     0 */
    __cacheline_group_begin__tcp_sock_write_txrx[0]; /*  2529     0 */
    u8                         nonagle:4;            /*  2529: 0  1 */
    u8                         rate_app_limited:1;   /*  2529: 4  1 */
    /* XXX 3 bits hole, try to pack */

    /* Force alignment to the next boundary: */
    u8                         :0;
    u8                         received_ce_pending:4;/*  2530: 0  1 */
    u8                         unused2:4;            /*  2530: 4  1 */
    u8                         accecn_minlen:2;      /*  2531: 0  1 */
    u8                         est_ecnfield:2;       /*  2531: 2  1 */
    u8                         accecn_opt_demand:2;  /*  2531: 4  1 */
    u8                         prev_ecnfield:2;      /*  2531: 6  1 */

    [...]
    __cacheline_group_end__tcp_sock_write_txrx[0];   /*  2636     0 */

    [...]
    /* size: 3200, cachelines: 50, members: 173 */
}

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Co-developed-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-8-chia-yu.chang@nokia-bell-labs.com


Signed-off-by: Paolo Abeni <pabeni@redhat.com>

parent b5e74132

Documentation/networking/ip-sysctl.rst

+6 −0

Original line number	Diff line number	Diff line
		@@ -487,6 +487,12 @@ tcp_ecn_option - INTEGER

		Default: 2

		tcp_ecn_option_beacon - INTEGER
		Control Accurate ECN (AccECN) option sending frequency per RTT and it
		takes effect only when tcp_ecn_option is set to 2.

		Default: 3 (AccECN will be send at least 3 times per RTT)

		tcp_ecn_fallback - BOOLEAN
		If the kernel detects that ECN connection misbehaves, enable fall
		back to non-ECN. Currently, this knob implements the fallback

Documentation/networking/net_cachelines/tcp_sock.rst

+3 −0

Original line number	Diff line number	Diff line
		@@ -109,6 +109,9 @@ u8:2 syn_ect_snt write_mostly read_w
		u8:2 syn_ect_rcv read_mostly read_write
		u8:2 accecn_minlen write_mostly read_write
		u8:2 est_ecnfield read_write
		u8:2 accecn_opt_demand read_mostly read_write
		u8:2 prev_ecnfield read_write
		u64 accecn_opt_tstamp read_write
		u8:4 accecn_fail_mode
		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)

include/linux/tcp.h

+3 −1

Original line number	Diff line number	Diff line
		@@ -275,6 +275,7 @@ struct tcp_sock {
		u32 mdev_us; /* medium deviation */
		u32 rtt_seq; /* sequence number to update rttvar */
		u64 tcp_wstamp_ns; /* departure time for next sent data packet */
		u64 accecn_opt_tstamp; /* Last AccECN option sent timestamp */
		struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
		struct sk_buff highest_sack; / skb just after the highest
		* skb with SACKed bit set
		@@ -296,7 +297,8 @@ struct tcp_sock {
		unused2:4;
		u8 accecn_minlen:2,/* Minimum length of AccECN option sent */
		est_ecnfield:2,/* ECN field for AccECN delivered estimates */
		unused3:4;
		accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */
		prev_ecnfield:2; /* ECN bits from the previous segment */
		__be32 pred_flags;
		u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
		u64 tcp_mstamp; /* most recent packet received/sent */

include/net/netns/ipv4.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -149,6 +149,7 @@ struct netns_ipv4 {

		u8 sysctl_tcp_ecn;
		u8 sysctl_tcp_ecn_option;
		u8 sysctl_tcp_ecn_option_beacon;
		u8 sysctl_tcp_ecn_fallback;

		u8 sysctl_ip_default_ttl;

include/net/tcp.h

+3 −0

Original line number	Diff line number	Diff line
		@@ -100,6 +100,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
		/* Maximal number of window scale according to RFC1323 */
		#define TCP_MAX_WSCALE 14U

		/* Default sending frequency of accurate ECN option per RTT */
		#define TCP_ACCECN_OPTION_BEACON 3

		/* urg_data states */
		#define TCP_URG_VALID 0x0100
		#define TCP_URG_NOTYET 0x0200