From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Hello,
Plesae find the v2 AccECN case handling patch series, which covers several excpetional case handling of Accurate ECN spec (RFC9768), adds new identifiers to be used by CC modules, adds ecn_delta into rate_sample, and keeps the ACE counter for computation, etc.
This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/
Best regards, Chia-Yu
--- Chia-Yu Chang (11): tcp: L4S ECT(1) identifier and NEEDS_ACCECN for CC modules tcp: disable RFC3168 fallback identifier for CC modules tcp: accecn: handle unexpected AccECN negotiation feedback tcp: accecn: retransmit downgraded SYN in AccECN negotiation tcp: move increment of num_retrans tcp: accecn: retransmit SYN/ACK without AccECN option or non-AccECN SYN/ACK tcp: accecn: unset ECT if receive or send ACE=0 in AccECN negotiaion tcp: accecn: fallback outgoing half link to non-AccECN tcp: accecn: verify ACE counter in 1st ACK after AccECN negotiation tcp: accecn: stop sending AccECN opt when loss ACK w/ option tcp: accecn: enable AccECN
Ilpo Järvinen (3): tcp: try to avoid safer when ACKs are thinned gro: flushing when CWR is set negatively affects AccECN tcp: accecn: Add ece_delta to rate_sample
.../networking/net_cachelines/tcp_sock.rst | 1 + include/linux/tcp.h | 4 +- include/net/inet_ecn.h | 20 +++- include/net/tcp.h | 30 +++++- include/net/tcp_ecn.h | 85 ++++++++++++----- net/ipv4/sysctl_net_ipv4.c | 2 +- net/ipv4/tcp.c | 2 + net/ipv4/tcp_cong.c | 9 +- net/ipv4/tcp_input.c | 91 +++++++++++++------ net/ipv4/tcp_minisocks.c | 40 +++++--- net/ipv4/tcp_offload.c | 3 +- net/ipv4/tcp_output.c | 38 +++++--- 12 files changed, 239 insertions(+), 86 deletions(-)
From: Ilpo Järvinen ij@kernel.org
Add newly acked pkts EWMA. When ACK thinning occurs, select between safer and unsafe cep delta in AccECN processing based on it. If the packets ACKed per ACK tends to be large, don't conservatively assume ACE field overflow.
This patch uses the existing 2-byte holes in the rx group for new u16 variables withtout creating more holes. Below are the pahole outcomes before and after this patch:
[BEFORE THIS PATCH] struct tcp_sock { [...] u32 delivered_ecn_bytes[3]; /* 2744 12 */ /* XXX 4 bytes hole, try to pack */
[...] __cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...] /* size: 3264, cachelines: 51, members: 177 */ }
[AFTER THIS PATCH] struct tcp_sock { [...] u32 delivered_ecn_bytes[3]; /* 2744 12 */ u16 pkts_acked_ewma; /* 2756 2 */ /* XXX 2 bytes hole, try to pack */
[...] __cacheline_group_end__tcp_sock_write_rx[0]; /* 2816 0 */
[...] /* size: 3264, cachelines: 51, members: 178 */ }
Signed-off-by: Ilpo Järvinen ij@kernel.org 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 --- .../networking/net_cachelines/tcp_sock.rst | 1 + include/linux/tcp.h | 1 + net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_input.c | 20 ++++++++++++++++++- 4 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index d4dc01800945..6fef633ce6b2 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -105,6 +105,7 @@ u32 received_ce read_mostly read_w u32[3] received_ecn_bytes read_mostly read_write u8:4 received_ce_pending read_mostly read_write u32[3] delivered_ecn_bytes read_write +u16 pkts_acked_ewma read_write u8:2 syn_ect_snt write_mostly read_write u8:2 syn_ect_rcv read_mostly read_write u8:2 accecn_minlen write_mostly read_write diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3ca5ed02de6d..53a4a0da35cc 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -345,6 +345,7 @@ struct tcp_sock { u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_rtt_last_tsecr; u32 delivered_ecn_bytes[3]; + u16 pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */ u64 first_tx_mstamp; /* start of window send phase */ u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d6d0d970e014..92c91e35d1b5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3415,6 +3415,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_accecn_init_counters(tp); tp->prev_ecnfield = 0; tp->accecn_opt_tstamp = 0; + tp->pkts_acked_ewma = 0; 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)); @@ -5183,6 +5184,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, pkts_acked_ewma); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9fdc6ce25eb1..0b25bf03ae6a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -488,6 +488,10 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, tcp_count_delivered_ce(tp, delivered); }
+#define PKTS_ACKED_WEIGHT 6 +#define PKTS_ACKED_PREC 6 +#define ACK_COMP_THRESH 4 + /* Returns the ECN CE delta */ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delivered_pkts, u32 delivered_bytes, @@ -507,6 +511,19 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, opt_deltas_valid = tcp_accecn_process_option(tp, skb, delivered_bytes, flag);
+ if (delivered_pkts) { + if (!tp->pkts_acked_ewma) { + tp->pkts_acked_ewma = delivered_pkts << PKTS_ACKED_PREC; + } else { + u32 ewma = tp->pkts_acked_ewma; + + ewma = (((ewma << PKTS_ACKED_WEIGHT) - ewma) + + (delivered_pkts << PKTS_ACKED_PREC)) >> + PKTS_ACKED_WEIGHT; + tp->pkts_acked_ewma = min_t(u32, ewma, 0xFFFFU); + } + } + if (!(flag & FLAG_SLOWPATH)) { /* AccECN counter might overflow on large ACKs */ if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK) @@ -555,7 +572,8 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, if (d_ceb < safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT) return delta; - } + } else if (tp->pkts_acked_ewma > (ACK_COMP_THRESH << PKTS_ACKED_PREC)) + return delta;
return safe_delta; }
From: Ilpo Järvinen ij@kernel.org
As AccECN may keep CWR bit asserted due to different interpretation of the bit, flushing with GRO because of CWR may effectively disable GRO until AccECN counter field changes such that CWR-bit becomes 0.
There is no harm done from not immediately forwarding the CWR'ed segment with RFC3168 ECN.
Signed-off-by: Ilpo Järvinen ij@kernel.org Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- net/ipv4/tcp_offload.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index e6612bd84d09..533195e00e4b 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -330,8 +330,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, goto out_check_final;
th2 = tcp_hdr(p); - flush = (__force int)(flags & TCP_FLAG_CWR); - flush |= (__force int)((flags ^ tcp_flag_word(th2)) & + flush = (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4)
From: Ilpo Järvinen ij@kernel.org
Include echoed CE count into rate_sample. Replace local ecn_count variable with it.
Co-developed-by: Olivier Tilmans olivier.tilmans@nokia.com Signed-off-by: Olivier Tilmans olivier.tilmans@nokia.com Signed-off-by: Ilpo Järvinen ij@kernel.org Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 37 ++++++++++++++++--------------------- 2 files changed, 17 insertions(+), 21 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h index 7c51a0a5ace8..23f0355d1991 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1220,6 +1220,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 ece_delta; /* is this ACK echoing some received CE? */ u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0b25bf03ae6a..6f7c2f0fc0f6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -578,9 +578,9 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, return safe_delta; }
-static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, - u32 delivered_pkts, u32 delivered_bytes, - int *flag) +static void tcp_accecn_process(struct sock *sk, struct rate_sample *rs, + const struct sk_buff *skb, u32 delivered_pkts, + u32 delivered_bytes, int *flag) { struct tcp_sock *tp = tcp_sk(sk); u32 delta; @@ -590,11 +590,11 @@ static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, if (delta > 0) { tcp_count_delivered_ce(tp, delta); *flag |= FLAG_ECE; + rs->ece_delta = delta; /* Recalculate header predictor */ if (tp->pred_flags) tcp_fast_path_on(tp); } - return delta; }
/* Buffer size and advertised window tuning. @@ -3971,8 +3971,8 @@ 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, - u32 ecn_count, int flag) +static u32 tcp_newly_delivered(struct sock *sk, struct rate_sample *rs, + u32 prior_delivered, int flag) { const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3983,8 +3983,8 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered,
if (flag & FLAG_ECE) { if (tcp_ecn_mode_rfc3168(tp)) - ecn_count = delivered; - NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, ecn_count); + rs->ece_delta = delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, rs->ece_delta); }
return delivered; @@ -3996,7 +3996,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; - struct rate_sample rs = { .prior_delivered = 0 }; + struct rate_sample rs = { .prior_delivered = 0, .ece_delta = 0 }; u32 prior_snd_una = tp->snd_una; bool is_sack_reneg = tp->is_sack_reneg; u32 ack_seq = TCP_SKB_CB(skb)->seq; @@ -4006,7 +4006,6 @@ 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; @@ -4116,10 +4115,8 @@ 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, - sack_state.delivered_bytes, - &flag); + tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered, + sack_state.delivered_bytes, &flag);
tcp_in_ack_event(sk, flag);
@@ -4145,7 +4142,7 @@ 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, ecn_count, flag); + delivered = tcp_newly_delivered(sk, &rs, delivered, flag);
lost = tp->lost - lost; /* freshly marked lost */ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED); @@ -4156,16 +4153,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
no_queue: if (tcp_ecn_mode_accecn(tp)) - ecn_count = tcp_accecn_process(sk, skb, - tp->delivered - delivered, - sack_state.delivered_bytes, - &flag); + tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered, + sack_state.delivered_bytes, &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, ecn_count, flag); + tcp_newly_delivered(sk, &rs, delivered, 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 @@ -4186,7 +4181,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &sack_state); tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, &rexmit); - tcp_newly_delivered(sk, delivered, ecn_count, flag); + tcp_newly_delivered(sk, &rs, delivered, flag); tcp_xmit_recovery(sk, rexmit); }
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Two CA module flags are added in this patch. First, a new CA module flag (TCP_CONG_NEEDS_ACCECN) defines that the CA expects to negotiate AccECN functionality using the ECE, CWR and AE flags in the TCP header. The detailed AccECN negotiaotn during the 3WHS can be found in the AccECN spec: https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
Second, when ECN is negociated for a TCP flow, it defaults to use ECT(0) in the IP header. L4S service, however, needs to se ECT(1). This patch enables CA to control whether ECT(0) or ECT(1) should be used on a per-segment basis. A new flag (TCP_CONG_WANTS_ECT_1) defines the behavior expected by the CA when not-yet initialized for the connection. As such, it implicitely assumes that the CA also has the TCP_CONG_NEEDS_ECN set.
Co-developed-by: Olivier Tilmans olivier.tilmans@nokia.com Signed-off-by: Olivier Tilmans olivier.tilmans@nokia.com Signed-off-by: Ilpo Järvinen ij@kernel.org Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/inet_ecn.h | 20 +++++++++++++++++--- include/net/tcp.h | 20 +++++++++++++++++++- include/net/tcp_ecn.h | 7 ++++--- net/ipv4/tcp_cong.c | 9 ++++++--- net/ipv4/tcp_input.c | 3 ++- net/ipv4/tcp_output.c | 10 ++++++++-- 6 files changed, 56 insertions(+), 13 deletions(-)
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ea32393464a2..827b87a95dab 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -51,11 +51,25 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; }
+/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + static inline void INET_ECN_xmit(struct sock *sk) { - inet_sk(sk)->tos |= INET_ECN_ECT_0; - if (inet6_sk(sk) != NULL) - inet6_sk(sk)->tclass |= INET_ECN_ECT_0; + __INET_ECN_xmit(sk, false); }
static inline void INET_ECN_dontxmit(struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index 23f0355d1991..4b255b92cb42 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -402,6 +402,7 @@ static inline void tcp_dec_quickack_mode(struct sock *sk) #define TCP_ECN_DEMAND_CWR BIT(2) #define TCP_ECN_SEEN BIT(3) #define TCP_ECN_MODE_ACCECN BIT(4) +#define TCP_ECN_ECT_1 BIT(5)
#define TCP_ECN_DISABLED 0 #define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) @@ -1189,7 +1190,12 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) -#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) +/* Require successfully negotiated AccECN capability */ +#define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ +#define TCP_CONG_WANTS_ECT_1 (TCP_CONG_NEEDS_ECN | TCP_CONG_NEEDS_ACCECN) +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ + TCP_CONG_NEEDS_ACCECN)
union tcp_cc_info;
@@ -1322,6 +1328,18 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; }
+static inline bool tcp_ca_needs_accecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; +} + +static inline bool tcp_ca_wants_ect_1(const struct sock *sk) +{ + return inet_csk(sk)->icsk_ca_ops->flags & TCP_CONG_WANTS_ECT_1; +} + static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f13e5cd2b1ac..bde5835a30f0 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -561,7 +561,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + __INET_ECN_xmit(sk, tcp_ca_wants_ect_1(sk));
if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE; @@ -579,7 +579,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) bool use_ecn, use_accecn; u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn);
- use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN; + use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN || + tcp_ca_needs_accecn(sk); use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN || tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN || tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn; @@ -595,7 +596,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
if (use_ecn) { if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); + __INET_ECN_xmit(sk, tcp_ca_wants_ect_1(sk));
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; if (use_accecn) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index df758adbb445..f9efbcf1d856 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -227,7 +227,7 @@ void tcp_assign_congestion_control(struct sock *sk)
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + __INET_ECN_xmit(sk, tcp_ca_wants_ect_1(sk)); else INET_ECN_dontxmit(sk); } @@ -240,7 +240,10 @@ void tcp_init_congestion_control(struct sock *sk) if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + /* The CA is already initialized, expect it to set the + * appropriate flag to select ECT(1). + */ + __INET_ECN_xmit(sk, tcp_sk(sk)->ecn_flags & TCP_ECN_ECT_1); else INET_ECN_dontxmit(sk); icsk->icsk_ca_initialized = 1; @@ -257,7 +260,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + __INET_ECN_xmit(sk, tcp_ca_wants_ect_1(sk)); else INET_ECN_dontxmit(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6f7c2f0fc0f6..b0557f72f3be 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7216,7 +7216,8 @@ static void tcp_ecn_create_request(struct request_sock *req, u32 ecn_ok_dst;
if (tcp_accecn_syn_requested(th) && - READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3) { + (READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3 || + tcp_ca_needs_accecn(listen_sk))) { inet_rsk(req)->ecn_ok = 1; tcp_rsk(req)->accecn_ok = 1; tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 223d7feeb19d..18bbb30381f0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -328,12 +328,17 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { struct tcp_sock *tp = tcp_sk(sk); + bool ecn_ect_1;
if (!tcp_ecn_mode_any(tp)) return;
+ ecn_ect_1 = tp->ecn_flags & TCP_ECN_ECT_1; + if (ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp)) + __INET_ECN_xmit(sk, true); + if (tcp_ecn_mode_accecn(tp)) { - if (!tcp_accecn_ace_fail_recv(tp)) + if (!ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp)) INET_ECN_xmit(sk); tcp_accecn_set_ace(tp, skb, th); skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; @@ -341,7 +346,8 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { - INET_ECN_xmit(sk); + if (!ecn_ect_1) + INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; th->cwr = 1;
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
When AccECN is not successfully negociated for a TCP flow, it defaults fallback to classic ECN (RFC3168). However, L4S service will fallback to non-ECN.
This patch enables congestion control module to control whether it should not fallback to classic ECN after unsuccessful AccECN negotiation. A new CA module flag (TCP_CONG_NO_FALLBACK_RFC3168) identifies this behavior expected by the CA.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp.h | 11 ++++++++++- include/net/tcp_ecn.h | 10 +++++++--- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_minisocks.c | 7 ++++--- 4 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h index 4b255b92cb42..8458aa79f509 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1192,10 +1192,12 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NEEDS_ECN BIT(1) /* Require successfully negotiated AccECN capability */ #define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Cannot fallback to RFC3168 during AccECN negotiation */ +#define TCP_CONG_NO_FALLBACK_RFC3168 BIT(3) /* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ #define TCP_CONG_WANTS_ECT_1 (TCP_CONG_NEEDS_ECN | TCP_CONG_NEEDS_ACCECN) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ - TCP_CONG_NEEDS_ACCECN) + TCP_CONG_NEEDS_ACCECN | TCP_CONG_NO_FALLBACK_RFC3168)
union tcp_cc_info;
@@ -1335,6 +1337,13 @@ static inline bool tcp_ca_needs_accecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; }
+static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; +} + static inline bool tcp_ca_wants_ect_1(const struct sock *sk) { return inet_csk(sk)->icsk_ca_ops->flags & TCP_CONG_WANTS_ECT_1; diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index bde5835a30f0..fb4fcb641d24 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -501,7 +501,9 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb * | ECN | AccECN | 0 0 1 | Classic ECN | * +========+========+============+=============+ */ - if (tcp_ecn_mode_pending(tp)) + if (tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); + else if (tcp_ecn_mode_pending(tp)) /* Downgrade from AccECN, or requested initially */ tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; @@ -525,9 +527,10 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb } }
-static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, +static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); if (tcp_ecn_mode_pending(tp)) { if (!tcp_accecn_syn_requested(th)) { /* Downgrade to classic ECN feedback */ @@ -539,7 +542,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); } } - if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr)) + if (tcp_ecn_mode_rfc3168(tp) && + (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk))) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b0557f72f3be..beb23dd34c5a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6811,7 +6811,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd;
- tcp_ecn_rcv_syn(tp, th, skb); + tcp_ecn_rcv_syn(sk, th, skb);
tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 2ec8c6f1cdcc..1fade94813c6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -488,9 +488,10 @@ static void tcp_ecn_openreq_child(struct sock *sk, tp->accecn_opt_demand = 1; tcp_ecn_received_counters_payload(sk, skb); } else { - tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ? - TCP_ECN_MODE_RFC3168 : - TCP_ECN_DISABLED); + if (inet_rsk(req)->ecn_ok && !tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); + else + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } }
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
According to Section 3.1.2 of AccECN spec (RFC9768), if a TCP Client has sent a SYN requesting AccECN feedback with (AE,CWR,ECE) = (1,1,1) then receives a SYN/ACK with the currently reserved combination (AE,CWR,ECE) = (1,0,1) but it does not have logic specific to such a combination, the Client MUST enable AccECN mode as if the SYN/ACK confirmed that the Server supported AccECN and as if it fed back that the IP-ECN field on the SYN had arrived unchanged.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp_ecn.h | 44 ++++++++++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 13 deletions(-)
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index fb4fcb641d24..7ceb191893c6 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -467,6 +467,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb, return TCP_ACCECN_OPT_COUNTER_SEEN; }
+static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk, + const struct sk_buff *skb, u8 dsf) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_rcv = dsf & INET_ECN_MASK; + /* Demand Accurate ECN option in response to the SYN on the SYN/ACK + * and the TCP server will try to send one more packet with an AccECN + * Option at a later point during the connection. + */ + 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); + tp->accecn_opt_demand = 2; + } +} + /* See Table 2 of the AccECN draft */ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th, u8 ip_dsfield) @@ -489,13 +509,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); break; case 0x1: - case 0x5: /* +========+========+============+=============+ * | A | B | SYN/ACK | Feedback | * | | | B->A | Mode of A | * | | | AE CWR ECE | | * +========+========+============+=============+ - * | AccECN | Nonce | 1 0 1 | (Reserved) | * | AccECN | ECN | 0 0 1 | Classic ECN | * | Nonce | AccECN | 0 0 1 | Classic ECN | * | ECN | AccECN | 0 0 1 | Classic ECN | @@ -503,20 +521,20 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb */ if (tcp_ca_no_fallback_rfc3168(sk)) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); - else if (tcp_ecn_mode_pending(tp)) - /* Downgrade from AccECN, or requested initially */ + else tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; - default: - tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); - tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK; - 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); - tp->accecn_opt_demand = 2; + case 0x5: + if (tcp_ecn_mode_pending(tp)) { + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); + if (INET_ECN_is_ce(ip_dsfield)) { + tp->received_ce++; + tp->received_ce_pending++; + } } + break; + default: + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); if (INET_ECN_is_ce(ip_dsfield) && tcp_accecn_validate_syn_feedback(sk, ace, tp->syn_ect_snt)) {
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Based on AccECN spec (RFC9768), if the sender of an AccECN SYN (the TCP Client) times out before receiving the SYN/ACK, it SHOULD attempt to negotiate the use of AccECN at least one more time by continuing to set all three TCP ECN flags (AE,CWR,ECE) = (1,1,1) on the first retransmitted SYN (using the usual retransmission time-outs).
If this first retransmission also fails to be acknowledged, in deployment scenarios where AccECN path traversal might be problematic, the TCP Client SHOULD send subsequent retransmissions of the SYN with the three TCP-ECN flags cleared (AE,CWR,ECE) = (0,0,0).
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- net/ipv4/tcp_output.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 18bbb30381f0..1c372fe0e57f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3563,12 +3563,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tcp_retrans_try_collapse(sk, skb, avail_wnd); }
- /* RFC3168, section 6.1.1.1. ECN fallback - * As AccECN uses the same SYN flags (+ AE), this check covers both - * cases. - */ - if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) - tcp_ecn_clear_syn(sk, skb); + if (!tcp_ecn_mode_pending(tp) || icsk->icsk_retransmits > 1) { + /* RFC3168, section 6.1.1.1. ECN fallback + * As AccECN uses the same SYN flags (+ AE), this check + * covers both cases. + */ + if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == + TCPHDR_SYN_ECN) + tcp_ecn_clear_syn(sk, skb); + }
/* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb);
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Before this patch, num_retrans = 0 for the first SYN/ACK and the first retransmitted SYN/ACK; however, an upcoming change will need to differentiate between those two conditions. This patch moves the increment of num_tranns before rtx_syn_ack() so we can distinguish between these two cases when making SYN/ACK.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- net/ipv4/tcp_output.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c372fe0e57f..bf90c2b33af3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4593,6 +4593,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); + WRITE_ONCE(req->num_retrans, req->num_retrans + 1); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { @@ -4606,7 +4607,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) tcp_sk_rw(sk)->total_retrans++; } trace_tcp_retransmit_synack(sk, req); - WRITE_ONCE(req->num_retrans, req->num_retrans + 1); + } else { + WRITE_ONCE(req->num_retrans, req->num_retrans - 1); } return res; }
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
If the TCP Server has not received an ACK to acknowledge its SYN/ACK after the normal TCP timeout or it receives a second SYN with a request for AccECN support, then either the SYN/ACK might just have been lost, e.g. due to congestion, or a middlebox might be blocking AccECN Options. To expedite connection setup in deployment scenarios where AccECN path traversal might be problematic, the TCP Server SHOULD retransmit the SYN/ACK, but with no AccECN Option.
If this retransmission times out, to expedite connection setup, the TCP Server SHOULD retransmit the SYN/ACK with (AE,CWR,ECE) = (0,0,0) and no AccECN Option, but it remains in AccECN feedback mode.
This follows Section 3.2.3.2.2 of AccECN spec (RFC9768).
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp_ecn.h | 14 ++++++++++---- net/ipv4/tcp_output.c | 2 +- 2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index 7ceb191893c6..f01cac9d39c9 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -644,10 +644,16 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) static inline void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { - if (tcp_rsk(req)->accecn_ok) - tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); - else if (inet_rsk(req)->ecn_ok) - th->ece = 1; + if (req->num_retrans < 1 || req->num_timeout < 1) { + if (tcp_rsk(req)->accecn_ok) + tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); + else if (inet_rsk(req)->ecn_ok) + th->ece = 1; + } else if (tcp_rsk(req)->accecn_ok) { + th->ae = 0; + th->cwr = 0; + th->ece = 0; + } }
static inline bool tcp_accecn_option_beacon_check(const struct sock *sk) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bf90c2b33af3..d4aae5dc2201 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1109,7 +1109,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
if (treq->accecn_ok && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && - req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) { + req->num_retrans < 1 && remaining >= TCPOLEN_ACCECN_BASE) { opts->use_synack_ecn_bytes = 1; remaining -= tcp_options_fit_accecn(opts, 0, remaining); }
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Based on specification: https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
Based on Section 3.1.5 of AccECN spec (RFC9768), a TCP Server in AccECN mode MUST NOT set ECT on any packet for the rest of the connection, if it has received or sent at least one valid SYN or Acceptable SYN/ACK with (AE,CWR,ECE) = (0,0,0) during the handshake.
In addition, a host in AccECN mode that is feeding back the IP-ECN field on a SYN or SYN/ACK MUST feed back the IP-ECN field on the latest valid SYN or acceptable SYN/ACK to arrive.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp_ecn.h | 4 +++- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_minisocks.c | 33 +++++++++++++++++++++++---------- net/ipv4/tcp_output.c | 8 +++++--- 4 files changed, 33 insertions(+), 14 deletions(-)
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f01cac9d39c9..2256d2efa5ec 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -642,7 +642,8 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) }
static inline void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) +tcp_ecn_make_synack(struct sock *sk, const struct request_sock *req, + struct tcphdr *th) { if (req->num_retrans < 1 || req->num_timeout < 1) { if (tcp_rsk(req)->accecn_ok) @@ -653,6 +654,7 @@ tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) th->ae = 0; th->cwr = 0; th->ece = 0; + tcp_accecn_fail_mode_set(tcp_sk(sk), TCP_ACCECN_ACE_FAIL_SEND); } }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index beb23dd34c5a..752251268cbe 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6190,6 +6190,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (th->syn) { if (tcp_ecn_mode_accecn(tp)) { accecn_reflector = true; + tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; 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); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1fade94813c6..ecead2b771fd 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -751,16 +751,29 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, */ if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, - &tcp_rsk(req)->last_oow_ack_time) && - - !tcp_rtx_synack(sk, req)) { - unsigned long expires = jiffies; - - expires += reqsk_timeout(req, TCP_RTO_MAX); - if (!fastopen) - mod_timer_pending(&req->rsk_timer, expires); - else - req->rsk_timer.expires = expires; + &tcp_rsk(req)->last_oow_ack_time)) { + if (tcp_rsk(req)->accecn_ok) { + u8 ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; + + tcp_rsk(req)->syn_ect_rcv = ect_rcv; + if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) { + u8 fail_mode = TCP_ACCECN_ACE_FAIL_RECV; + + tcp_accecn_fail_mode_set(tcp_sk(sk), + fail_mode); + } + } + if (!tcp_rtx_synack(sk, req)) { + unsigned long expires = jiffies; + + expires += reqsk_timeout(req, TCP_RTO_MAX); + if (!fastopen) + mod_timer_pending(&req->rsk_timer, + expires); + else + req->rsk_timer.expires = expires; + } } return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d4aae5dc2201..df07b76ba84f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -334,11 +334,13 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, return;
ecn_ect_1 = tp->ecn_flags & TCP_ECN_ECT_1; - if (ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp)) + if (ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp) && + !tcp_accecn_ace_fail_send(tp)) __INET_ECN_xmit(sk, true);
if (tcp_ecn_mode_accecn(tp)) { - if (!ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp)) + if (!ecn_ect_1 && !tcp_accecn_ace_fail_recv(tp) && + !tcp_accecn_ace_fail_send(tp)) INET_ECN_xmit(sk); tcp_accecn_set_ace(tp, skb, th); skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; @@ -3990,7 +3992,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; - tcp_ecn_make_synack(req, th); + tcp_ecn_make_synack((struct sock *)sk, req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark;
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
According to Section 3.2.2.1 of AccECN spec (RFC9768), if the Server is in AccECN mode and in SYN-RCVD state, and if it receives a value of zero on a pure ACK with SYN=0 and no SACK blocks, for the rest of the connection the Server MUST NOT set ECT on outgoing packets and MUST NOT respond to AccECN feedback. Nonetheless, as a Data Receiver it MUST NOT disable AccECN feedback.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/net/tcp_ecn.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index 2256d2efa5ec..8317c3f279c9 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -169,7 +169,10 @@ static inline void tcp_accecn_third_ack(struct sock *sk, switch (ace) { case 0x0: /* Invalid value */ - tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV); + if (!TCP_SKB_CB(skb)->sacked) { + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV | + TCP_ACCECN_OPT_FAIL_RECV); + } break; case 0x7: case 0x5:
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
After successfully negotiating AccECN mode in the handshake, check the ACE field of the first data ACK. If zero (0b000), non-ECT packets are sent and any response to CE marking feedback is disabled. This follows Section 3.2.2.4 of AccECN spec (RFC9768).
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- net/ipv4/tcp_input.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 752251268cbe..f250b4912a0b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -495,7 +495,7 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, /* Returns the ECN CE delta */ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delivered_pkts, u32 delivered_bytes, - int flag) + u64 prior_bytes_acked, int flag) { u32 old_ceb = tcp_sk(sk)->delivered_ecn_bytes[INET_ECN_CE - 1]; const struct tcphdr *th = tcp_hdr(skb); @@ -534,6 +534,16 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, if (flag & FLAG_SYN_ACKED) return 0;
+ /* Verify ACE!=0 in the 1st data ACK after AccECN negotiation */ + if ((flag & FLAG_DATA_ACKED) && prior_bytes_acked <= tp->mss_cache) { + if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) { + INET_ECN_dontxmit(sk); + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV | + TCP_ACCECN_OPT_FAIL_RECV); + return 0; + } + } + if (tp->received_ce_pending >= TCP_ACCECN_ACE_MAX_DELTA) inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
@@ -580,13 +590,14 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
static void tcp_accecn_process(struct sock *sk, struct rate_sample *rs, const struct sk_buff *skb, u32 delivered_pkts, - u32 delivered_bytes, int *flag) + u32 delivered_bytes, u64 prior_bytes_acked, + int *flag) { struct tcp_sock *tp = tcp_sk(sk); u32 delta;
delta = __tcp_accecn_process(sk, skb, delivered_pkts, - delivered_bytes, *flag); + delivered_bytes, prior_bytes_acked, *flag); if (delta > 0) { tcp_count_delivered_ce(tp, delta); *flag |= FLAG_ECE; @@ -3997,6 +4008,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; struct rate_sample rs = { .prior_delivered = 0, .ece_delta = 0 }; + u64 prior_bytes_acked = tp->bytes_acked; u32 prior_snd_una = tp->snd_una; bool is_sack_reneg = tp->is_sack_reneg; u32 ack_seq = TCP_SKB_CB(skb)->seq; @@ -4116,7 +4128,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (tcp_ecn_mode_accecn(tp)) tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered, - sack_state.delivered_bytes, &flag); + sack_state.delivered_bytes, + prior_bytes_acked, &flag);
tcp_in_ack_event(sk, flag);
@@ -4154,7 +4167,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: if (tcp_ecn_mode_accecn(tp)) tcp_accecn_process(sk, &rs, skb, tp->delivered - delivered, - sack_state.delivered_bytes, &flag); + sack_state.delivered_bytes, + prior_bytes_acked, &flag); tcp_in_ack_event(sk, flag); /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) {
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Detect spurious retransmission of a previously sent ACK carrying the AccECN option after the second retransmission. Since this might be caused by the middlebox dropping ACK with options it does not recognize, disable the sending of the AccECN option in all subsequent ACKs. This patch follows Section 3.2.3.2.2 of AccECN spec (RFC9768).
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- include/linux/tcp.h | 3 ++- include/net/tcp_ecn.h | 1 + net/ipv4/tcp_input.c | 9 +++++++++ net/ipv4/tcp_output.c | 3 +++ 4 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 53a4a0da35cc..f3b72fb6fa76 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -295,7 +295,8 @@ 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; + accecn_opt_sent:1,/* Sent AccECN option in previous ACK */ + unused2:3; u8 accecn_minlen:2,/* Minimum length of AccECN option sent */ est_ecnfield:2,/* ECN field for AccECN delivered estimates */ accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */ diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index 8317c3f279c9..3eb450b4b648 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -401,6 +401,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp) tp->received_ce_pending = 0; __tcp_accecn_init_bytes_counters(tp->received_ecn_bytes); __tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes); + tp->accecn_opt_sent = 0; tp->accecn_minlen = 0; tp->accecn_opt_demand = 0; tp->est_ecnfield = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f250b4912a0b..6083260133e9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4804,6 +4804,7 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); /* When the ACK path fails or drops most ACKs, the sender would * timeout and spuriously retransmit the same segment repeatedly. * If it seems our ACKs are not reaching the other side, @@ -4823,6 +4824,14 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) /* Save last flowlabel after a spurious retrans. */ tcp_save_lrcv_flowlabel(sk, skb); #endif + /* Check DSACK info to detect that the previous ACK carrying the + * AccECN option was lost after the second retransmision, and then + * stop sending AccECN option in all subsequent ACKs. + */ + if (tcp_ecn_mode_accecn(tp) && + TCP_SKB_CB(skb)->seq == tp->duplicate_sack[0].start_seq && + tp->accecn_opt_sent) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_OPT_FAIL_SEND); }
static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index df07b76ba84f..a2f897b044b9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -719,9 +719,12 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, if (tp) { tp->accecn_minlen = 0; tp->accecn_opt_tstamp = tp->tcp_mstamp; + tp->accecn_opt_sent = 1; if (tp->accecn_opt_demand) tp->accecn_opt_demand--; } + } else if (tp) { + tp->accecn_opt_sent = 0; }
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
From: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com
Enable Accurate ECN negotiation and request for incoming and outgoing connection by setting sysctl_tcp_ecn:
+==============+===========================================+ | | Highest ECN variant (Accurate ECN, ECN, | | tcp_ecn | or no ECN) to be negotiated & requested | | +---------------------+---------------------+ | | Incoming connection | Outgoing connection | +==============+=====================+=====================+ | 0 | No ECN | No ECN | | 1 | ECN | ECN | | 2 | ECN | No ECN | +--------------+---------------------+---------------------+ | 3 | Accurate ECN | Accurate ECN | | 4 | Accurate ECN | ECN | | 5 | Accurate ECN | No ECN | +==============+=====================+=====================+
Refer Documentation/networking/ip-sysctl.rst for more details.
Signed-off-by: Chia-Yu Chang chia-yu.chang@nokia-bell-labs.com --- net/ipv4/sysctl_net_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 24dbc603cc44..169a393374b3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -47,7 +47,7 @@ static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; -static int tcp_ecn_mode_max = 2; +static int tcp_ecn_mode_max = 5;
/* obsolete */ static int sysctl_tcp_low_latency __read_mostly;
linux-kselftest-mirror@lists.linaro.org
-
chia-yu.chang＠nokia-bell-labs.com