tcp: accecn: AccECN negotiation

Accurate ECN negotiation parts based on the specification:
  https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt

Accurate ECN is negotiated using ECE, CWR and AE flags in the
TCP header. TCP falls back into using RFC3168 ECN if one of the
ends supports only RFC3168-style ECN.

The AccECN negotiation includes reflecting IP ECN field value
seen in SYN and SYNACK back using the same bits as negotiation
to allow responding to SYN CE marks and to detect ECN field
mangling. CE marks should not occur currently because SYN=1
segments are sent with Non-ECT in IP ECN field (but proposal
exists to remove this restriction).

Reflecting SYN IP ECN field in SYNACK is relatively simple.
Reflecting SYNACK IP ECN field in the final/third ACK of
the handshake is more challenging. Linux TCP code is not well
prepared for using the final/third ACK a signalling channel
which makes things somewhat complicated here.

tcp_ecn sysctl can be used to select the highest ECN variant
(Accurate ECN, ECN, No ECN) that is attemped to be negotiated and
requested for incoming connection and outgoing connection:
TCP_ECN_IN_NOECN_OUT_NOECN, TCP_ECN_IN_ECN_OUT_ECN,
TCP_ECN_IN_ECN_OUT_NOECN, TCP_ECN_IN_ACCECN_OUT_ACCECN,
TCP_ECN_IN_ACCECN_OUT_ECN, and TCP_ECN_IN_ACCECN_OUT_NOECN.

After this patch, the size of tcp_request_sock remains unchanged
and no new holes are added. Below are the pahole outcomes before
and after this patch:

[BEFORE THIS PATCH]
struct tcp_request_sock {
    [...]
    u32                        rcv_nxt;              /*   352     4 */
    u8                         syn_tos;              /*   356     1 */

    /* size: 360, cachelines: 6, members: 16 */
}

[AFTER THIS PATCH]
struct tcp_request_sock {
    [...]
    u32                        rcv_nxt;              /*   352     4 */
    u8                         syn_tos;              /*   356     1 */
    bool                       accecn_ok;            /*   357     1 */
    u8                         syn_ect_snt:2;        /*   358: 0  1 */
    u8                         syn_ect_rcv:2;        /*   358: 2  1 */
    u8                         accecn_fail_mode:4;   /*   358: 4  1 */

    /* size: 360, cachelines: 6, members: 20 */
}

After this patch, the size of tcp_sock remains unchanged and no new
holes are added. Also, 4 bits of the existing 2-byte hole are exploited.
Below are the pahole outcomes before and after this patch:

[BEFORE THIS PATCH]
struct tcp_sock {
    [...]
    u8                         dup_ack_counter:2;    /*  2761: 0  1 */
    u8                         tlp_retrans:1;        /*  2761: 2  1 */
    u8                         unused:5;             /*  2761: 3  1 */
    u8                         thin_lto:1;           /*  2762: 0  1 */
    u8                         fastopen_connect:1;   /*  2762: 1  1 */
    u8                         fastopen_no_cookie:1; /*  2762: 2  1 */
    u8                         fastopen_client_fail:2; /*  2762: 3  1 */
    u8                         frto:1;               /*  2762: 5  1 */
    /* XXX 2 bits hole, try to pack */

    [...]
    u8                         keepalive_probes;     /*  2765     1 */
    /* XXX 2 bytes hole, try to pack */

    [...]
    /* size: 3200, cachelines: 50, members: 164 */
}

[AFTER THIS PATCH]
struct tcp_sock {
    [...]
    u8                         dup_ack_counter:2;    /*  2761: 0  1 */
    u8                         tlp_retrans:1;        /*  2761: 2  1 */
    u8                         syn_ect_snt:2;        /*  2761: 3  1 */
    u8                         syn_ect_rcv:2;        /*  2761: 5  1 */
    u8                         thin_lto:1;           /*  2761: 7  1 */
    u8                         fastopen_connect:1;   /*  2762: 0  1 */
    u8                         fastopen_no_cookie:1; /*  2762: 1  1 */
    u8                         fastopen_client_fail:2; /*  2762: 2  1 */
    u8                         frto:1;               /*  2762: 4  1 */
    /* XXX 3 bits hole, try to pack */

    [...]
    u8                         keepalive_probes;     /*  2765     1 */
    u8                         accecn_fail_mode:4;   /*  2766: 0  1 */
    /* XXX 4 bits hole, try to pack */
    /* XXX 1 byte hole, try to pack */

    [...]
    /* size: 3200, cachelines: 50, members: 166 */
}

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Co-developed-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250916082434.100722-3-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

2 files changed, 25 insertions, 14 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 9f5891c9b07b..3d8eb54b84f9 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -443,20 +443,28 @@ tcp_early_retrans - INTEGER
 
 tcp_ecn - INTEGER
 	Control use of Explicit Congestion Notification (ECN) by TCP.
-	ECN is used only when both ends of the TCP connection indicate
-	support for it.  This feature is useful in avoiding losses due
-	to congestion by allowing supporting routers to signal
-	congestion before having to drop packets.
-
-	Possible values are:
-
-		=  =====================================================
-		0  Disable ECN.  Neither initiate nor accept ECN.
-		1  Enable ECN when requested by incoming connections and
-		   also request ECN on outgoing connection attempts.
-		2  Enable ECN when requested by incoming connections
-		   but do not request ECN on outgoing connections.
-		=  =====================================================
+	ECN is used only when both ends of the TCP connection indicate support
+	for it. This feature is useful in avoiding losses due to congestion by
+	allowing supporting routers to signal congestion before having to drop
+	packets. A host that supports ECN both sends ECN at the IP layer and
+	feeds back ECN at the TCP layer. The highest variant of ECN feedback
+	that both peers support is chosen by the ECN negotiation (Accurate ECN,
+	ECN, or no ECN).
+
+	The highest negotiated variant for incoming connection requests
+	and the highest variant requested by outgoing connection
+	attempts:
+
+	===== ==================== ====================
+	Value Incoming connections Outgoing connections
+	===== ==================== ====================
+	0     No ECN               No ECN
+	1     ECN                  ECN
+	2     ECN                  No ECN
+	3     AccECN               AccECN
+	4     AccECN               ECN
+	5     AccECN               No ECN
+	===== ==================== ====================
 
 	Default: 2
 
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 31313a9adccc..4f71ece7c655 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -103,6 +103,9 @@ u32                           delivered               read_mostly         read_w
 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
+u8:2                          syn_ect_snt             write_mostly        read_write
+u8:2                          syn_ect_rcv             read_mostly         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)
 u64                           first_tx_mstamp         read_write                              tcp_rate_skb_sent