* [PATCH v7 net-next 01/15] tcp: reorganize SYN ECN code
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 02/15] tcp: fast path functions later chia-yu.chang
` (13 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
Prepare for AccECN that needs to have access here on IP ECN
field value which is only available after INET_ECN_xmit().
No functional changes.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_output.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 13295a59d22e..9a1ab946ff62 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -350,10 +350,11 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
tp->ecn_flags = 0;
if (use_ecn) {
- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
- tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn)
INET_ECN_xmit(sk);
+
+ TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
+ tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
}
}
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 02/15] tcp: fast path functions later
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 01/15] tcp: reorganize SYN ECN code chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 03/15] tcp: reorganize tcp_sock_write_txrx group for variables later chia-yu.chang
` (12 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chai-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
The following patch will use tcp_ecn_mode_accecn(),
TCP_ACCECN_CEP_INIT_OFFSET, TCP_ACCECN_CEP_ACE_MASK in
__tcp_fast_path_on() to make new flag for AccECN.
No functional changes.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chai-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
include/net/tcp.h | 54 +++++++++++++++++++++++------------------------
1 file changed, 27 insertions(+), 27 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5078ad868fee..4dacd4a11669 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -812,33 +812,6 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
}
-static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
-{
- /* mptcp hooks are only on the slow path */
- if (sk_is_mptcp((struct sock *)tp))
- return;
-
- tp->pred_flags = htonl((tp->tcp_header_len << 26) |
- ntohl(TCP_FLAG_ACK) |
- snd_wnd);
-}
-
-static inline void tcp_fast_path_on(struct tcp_sock *tp)
-{
- __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
-}
-
-static inline void tcp_fast_path_check(struct sock *sk)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- if (RB_EMPTY_ROOT(&tp->out_of_order_queue) &&
- tp->rcv_wnd &&
- atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
- !tp->urg_data)
- tcp_fast_path_on(tp);
-}
-
u32 tcp_delack_max(const struct sock *sk);
/* Compute the actual rto_min value */
@@ -1798,6 +1771,33 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
return true;
}
+static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
+{
+ /* mptcp hooks are only on the slow path */
+ if (sk_is_mptcp((struct sock *)tp))
+ return;
+
+ tp->pred_flags = htonl((tp->tcp_header_len << 26) |
+ ntohl(TCP_FLAG_ACK) |
+ snd_wnd);
+}
+
+static inline void tcp_fast_path_on(struct tcp_sock *tp)
+{
+ __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
+}
+
+static inline void tcp_fast_path_check(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (RB_EMPTY_ROOT(&tp->out_of_order_queue) &&
+ tp->rcv_wnd &&
+ atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+ !tp->urg_data)
+ tcp_fast_path_on(tp);
+}
+
bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
int mib_idx, u32 *last_oow_ack_time);
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 03/15] tcp: reorganize tcp_sock_write_txrx group for variables later
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 01/15] tcp: reorganize SYN ECN code chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 02/15] tcp: fast path functions later chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 04/15] tcp: AccECN core chia-yu.chang
` (11 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Use the first 3-byte hole at the beginning of the tcp_sock_write_txrx
group for 'noneagle'/'rate_app_limited' to fill in the existing hole
in later patches. Therefore, the group size of tcp_sock_write_txrx is
reduced from 92 + 4 to 91 + 4. In addition, the group size of
tcp_sock_write_rx is changed to 96 to fit in the pahole outcome.
Below are the trimmed pahole outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2585 0 */
/* XXX 3 bytes hole, try to pack */
[...]
struct tcp_options_received rx_opt; /* 2652 24 */
u8 nonagle:4; /* 2676: 0 1 */
u8 rate_app_limited:1; /* 2676: 4 1 */
/* XXX 3 bits hole, try to pack */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2677 0 */
/* XXX 3 bytes hole, try to pack */
__cacheline_group_begin__tcp_sock_write_rx[0] __attribute__((__aligned__(8))); /* 2680 0 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2776 0 */
[...]
/* size: 3264, cachelines: 51, members: 163 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2585 0 */
u8 nonagle:4; /* 2585: 0 1 */
u8 rate_app_limited:1; /* 2585: 4 1 */
/* XXX 3 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
[...]
struct tcp_options_received rx_opt; /* 2652 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2676 0 */
/* XXX 4 bytes hole, try to pack */
__cacheline_group_begin__tcp_sock_write_rx[0] __attribute__((__aligned__(8))); /* 2680 0 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2776 0 */
[...]
/* size: 3264, cachelines: 51, members: 163 */
}
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
include/linux/tcp.h | 4 ++--
net/ipv4/tcp.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index a8af71623ba7..0c82a8c942dc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -286,6 +286,8 @@ struct tcp_sock {
* Header prediction flags
* 0x5?10 << 16 + snd_wnd in net byte order
*/
+ u8 nonagle : 4,/* Disable Nagle algorithm? */
+ rate_app_limited:1; /* rate_{delivered,interval_us} limited? */
__be32 pred_flags;
u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
u64 tcp_mstamp; /* most recent packet received/sent */
@@ -304,8 +306,6 @@ struct tcp_sock {
* Options received (usually on last packet, some only on SYN packets).
*/
struct tcp_options_received rx_opt;
- u8 nonagle : 4,/* Disable Nagle algorithm? */
- rate_app_limited:1; /* rate_{delivered,interval_us} limited? */
__cacheline_group_end(tcp_sock_write_txrx);
/* RX read-write hotpath cache lines */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0ae265d39184..bc9ab715fc2b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5130,7 +5130,7 @@ 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, 92 + 4);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 91 + 4);
/* RX read-write hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
@@ -5147,7 +5147,7 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 96);
}
void __init tcp_init(void)
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 04/15] tcp: AccECN core
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (2 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 03/15] tcp: reorganize tcp_sock_write_txrx group for variables later chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 05/15] tcp: accecn: AccECN negotiation chia-yu.chang
` (10 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Olivier Tilmans, Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
This change implements Accurate ECN without negotiation and
AccECN Option (that will be added by later changes). Based on
AccECN specifications:
https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
Accurate ECN allows feeding back the number of CE (congestion
experienced) marks accurately to the sender in contrast to
RFC3168 ECN that can only signal one marks-seen-yes/no per RTT.
Congestion control algorithms can take advantage of the accurate
ECN information to fine-tune their congestion response to avoid
drastic rate reduction when only mild congestion is encountered.
With Accurate ECN, tp->received_ce (r.cep in AccECN spec) keeps
track of how many segments have arrived with a CE mark. Accurate
ECN uses ACE field (ECE, CWR, AE) to communicate the value back
to the sender which updates tp->delivered_ce (s.cep) based on the
feedback. This signalling channel is lossy when ACE field overflow
occurs.
Conservative strategy is selected here to deal with the ACE
overflow, however, some strategies using the AccECN option later
in the overall patchset mitigate against false overflows detected.
The ACE field values on the wire are offset by
TCP_ACCECN_CEP_INIT_OFFSET. Delivered_ce/received_ce count the
real CE marks rather than forcing all downstream users to adapt
to the wire offset.
This patch uses the first 1-byte hole and the last 4-byte hole of
the tcp_sock_write_txrx for 'received_ce_pending' and 'received_ce'.
Also, the group size of tcp_sock_write_txrx is increased from
91 + 4 to 95 + 4 due to the new u32 received_ce member. Below are
the trimmed pahole outcomes before and after this patch.
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2585 0 */
u8 nonagle:4; /* 2585: 0 1 */
u8 rate_app_limited:1; /* 2585: 4 1 */
/* XXX 3 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
[...]
u32 delivered_ce; /* 2640 4 */
u32 app_limited; /* 2644 4 */
u32 rcv_wnd; /* 2648 4 */
struct tcp_options_received rx_opt; /* 2652 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2676 0 */
/* XXX 4 bytes hole, try to pack */
[...]
/* size: 3264, cachelines: 51, members: 163 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2585 0 */
u8 nonagle:4; /* 2585: 0 1 */
u8 rate_app_limited:1; /* 2585: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2586: 0 1 */
u8 unused2:4; /* 2586: 4 1 */
/* XXX 1 byte hole, try to pack */
[...]
u32 delivered_ce; /* 2640 4 */
u32 received_ce; /* 2644 4 */
u32 app_limited; /* 2648 4 */
u32 rcv_wnd; /* 2652 4 */
struct tcp_options_received rx_opt; /* 2656 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2680 0 */
[...]
/* size: 3264, cachelines: 51, 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>
---
.../networking/net_cachelines/tcp_sock.rst | 2 +
include/linux/tcp.h | 3 +
include/net/tcp.h | 26 ++++
net/ipv4/tcp.c | 4 +-
net/ipv4/tcp_input.c | 121 ++++++++++++++++--
net/ipv4/tcp_output.c | 20 ++-
6 files changed, 162 insertions(+), 14 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index bc9b2131bf7a..9bf507c349a0 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 0c82a8c942dc..e1884df45a27 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -288,6 +288,8 @@ 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 */
@@ -300,6 +302,7 @@ 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 4dacd4a11669..cc28255deef7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -415,6 +415,11 @@ static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode)
tp->ecn_flags |= mode;
}
+static inline u8 tcp_accecn_ace(const struct tcphdr *th)
+{
+ return (th->ae << 2) | (th->cwr << 1) | th->ece;
+}
+
enum tcp_tw_status {
TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1,
@@ -964,6 +969,20 @@ 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
+
+static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
+{
+ tp->received_ce = 0;
+ tp->received_ce_pending = 0;
+}
+
/* 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 */
@@ -1773,11 +1792,18 @@ 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/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bc9ab715fc2b..0c8a391d90fe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3396,6 +3396,7 @@ 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));
@@ -5123,6 +5124,7 @@ 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);
@@ -5130,7 +5132,7 @@ 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 a35018e2d0ba..8dbb625f5e8a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -341,14 +341,17 @@ static bool tcp_in_quickack_mode(struct sock *sk)
static 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;
}
static 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
@@ -384,17 +387,16 @@ 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;
}
- tp->ecn_flags |= TCP_ECN_SEEN;
break;
default:
if (tcp_ca_needs_ecn(sk))
tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
- tp->ecn_flags |= TCP_ECN_SEEN;
break;
}
}
@@ -428,10 +430,64 @@ 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.
@@ -3919,7 +3975,8 @@ 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);
@@ -3927,8 +3984,12 @@ 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;
}
@@ -3949,6 +4010,7 @@ 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;
@@ -4056,6 +4118,11 @@ 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)
@@ -4080,7 +4147,8 @@ 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);
@@ -4089,12 +4157,16 @@ 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
@@ -4115,7 +4187,7 @@ 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, flag);
+ tcp_newly_delivered(sk, delivered, ecn_count, flag);
tcp_xmit_recovery(sk, rexmit);
}
@@ -5952,6 +6024,26 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
}
}
+/* Updates Accurate ECN received counters from the received IP ECN field */
+static 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);
+
+ 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);
+ }
+}
+
/* Accept RST for rcv_nxt - 1 after a FIN.
* When tcp connections are abruptly terminated from Mac OSX (via ^C), a
* FIN is sent followed by a RST packet. The RST is sent with the same
@@ -6214,6 +6306,8 @@ 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.
*/
@@ -6258,6 +6352,7 @@ 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);
@@ -6298,6 +6393,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
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 9a1ab946ff62..63352372248b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -374,6 +374,17 @@ tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
th->ece = 1;
}
+static 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;
+}
+
/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
* be sent.
*/
@@ -382,7 +393,14 @@ 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)) {
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 05/15] tcp: accecn: AccECN negotiation
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (3 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 04/15] tcp: AccECN core chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 06/15] tcp: accecn: add AccECN rx byte counters chia-yu.chang
` (9 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Olivier Tilmans, Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
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; /* 2825: 0 1 */
u8 tlp_retrans:1; /* 2825: 2 1 */
u8 unused:5; /* 2825: 3 1 */
u8 thin_lto:1; /* 2826: 0 1 */
u8 fastopen_connect:1; /* 2826: 1 1 */
u8 fastopen_no_cookie:1; /* 2826: 2 1 */
u8 fastopen_client_fail:2; /* 2826: 3 1 */
u8 frto:1; /* 2826: 5 1 */
/* XXX 2 bits hole, try to pack */
[...]
u8 keepalive_probes; /* 2829 1 */
/* XXX 2 bytes hole, try to pack */
[...]
/* size: 3264, cachelines: 51, members: 166 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u8 dup_ack_counter:2; /* 2825: 0 1 */
u8 tlp_retrans:1; /* 2825: 2 1 */
u8 syn_ect_snt:2; /* 2825: 3 1 */
u8 syn_ect_rcv:2; /* 2825: 5 1 */
u8 wait_third_ack:1; /* 2825: 7 1 */
u8 thin_lto:1; /* 2826: 0 1 */
u8 fastopen_connect:1; /* 2826: 1 1 */
u8 fastopen_no_cookie:1; /* 2826: 2 1 */
u8 fastopen_client_fail:2; /* 2826: 3 1 */
u8 frto:1; /* 2826: 5 1 */
/* XXX 2 bits hole, try to pack */
[...]
u8 keepalive_probes; /* 2829 1 */
u8 accecn_fail_mode:4; /* 2830: 0 1 */
/* XXX 4 bits hole, try to pack */
/* XXX 1 byte hole, try to pack */
[...]
/* size: 3264, cachelines: 51, members: 169 */
}
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>
---
.../networking/net_cachelines/tcp_sock.rst | 4 +
include/linux/tcp.h | 9 +-
include/net/tcp.h | 93 ++++++++-
net/ipv4/syncookies.c | 3 +
net/ipv4/sysctl_net_ipv4.c | 3 +-
net/ipv4/tcp.c | 2 +
net/ipv4/tcp_input.c | 178 ++++++++++++++++--
net/ipv4/tcp_ipv4.c | 5 +-
net/ipv4/tcp_minisocks.c | 51 ++++-
net/ipv4/tcp_output.c | 78 ++++++--
net/ipv6/syncookies.c | 1 +
net/ipv6/tcp_ipv6.c | 1 +
12 files changed, 384 insertions(+), 44 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 9bf507c349a0..eef8700085de 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -103,6 +103,10 @@ 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
+u8:1 wait_third_ack 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
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index e1884df45a27..b0e6a11a3fa1 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -168,6 +168,10 @@ struct tcp_request_sock {
* after data-in-SYN.
*/
u8 syn_tos;
+ bool accecn_ok;
+ u8 syn_ect_snt: 2,
+ syn_ect_rcv: 2,
+ accecn_fail_mode:4;
#ifdef CONFIG_TCP_AO
u8 ao_keyid;
u8 ao_rcv_next;
@@ -376,7 +380,9 @@ struct tcp_sock {
u8 compressed_ack;
u8 dup_ack_counter:2,
tlp_retrans:1, /* TLP is a retransmission */
- unused:5;
+ syn_ect_snt:2, /* AccECN ECT memory, only */
+ syn_ect_rcv:2, /* ... needed durign 3WHS + first seqno */
+ wait_third_ack:1; /* Wait 3rd ACK in simultaneous open */
u8 thin_lto : 1,/* Use linear timeouts for thin streams */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
@@ -392,6 +398,7 @@ 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 */
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 cc28255deef7..5fce4b49e132 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -27,6 +27,7 @@
#include <linux/ktime.h>
#include <linux/indirect_call_wrapper.h>
#include <linux/bits.h>
+#include <linux/bitfield.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
@@ -234,6 +235,37 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
#define TCPOLEN_MSS_ALIGNED 4
#define TCPOLEN_EXP_SMC_BASE_ALIGNED 8
+/* tp->accecn_fail_mode */
+#define TCP_ACCECN_ACE_FAIL_SEND BIT(0)
+#define TCP_ACCECN_ACE_FAIL_RECV BIT(1)
+#define TCP_ACCECN_OPT_FAIL_SEND BIT(2)
+#define TCP_ACCECN_OPT_FAIL_RECV BIT(3)
+
+static inline bool tcp_accecn_ace_fail_send(const struct tcp_sock *tp)
+{
+ return tp->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND;
+}
+
+static inline bool tcp_accecn_ace_fail_recv(const struct tcp_sock *tp)
+{
+ return tp->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_RECV;
+}
+
+static inline bool tcp_accecn_opt_fail_send(const struct tcp_sock *tp)
+{
+ return tp->accecn_fail_mode & TCP_ACCECN_OPT_FAIL_SEND;
+}
+
+static inline bool tcp_accecn_opt_fail_recv(const struct tcp_sock *tp)
+{
+ return tp->accecn_fail_mode & TCP_ACCECN_OPT_FAIL_RECV;
+}
+
+static inline void tcp_accecn_fail_mode_set(struct tcp_sock *tp, u8 mode)
+{
+ tp->accecn_fail_mode |= mode;
+}
+
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
@@ -420,6 +452,23 @@ static inline u8 tcp_accecn_ace(const struct tcphdr *th)
return (th->ae << 2) | (th->cwr << 1) | th->ece;
}
+/* Infer the ECT value our SYN arrived with from the echoed ACE field */
+static inline int tcp_accecn_extract_syn_ect(u8 ace)
+{
+ if (ace & 0x1)
+ return INET_ECN_ECT_1;
+ if (!(ace & 0x2))
+ return INET_ECN_ECT_0;
+ if (ace & 0x4)
+ return INET_ECN_CE;
+ return INET_ECN_NOT_ECT;
+}
+
+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);
+void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb);
+
enum tcp_tw_status {
TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1,
@@ -657,6 +706,15 @@ static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *
dst_feature(dst, RTAX_FEATURE_ECN);
}
+/* AccECN specification, 5.1: [...] a server can determine that it
+ * negotiated AccECN as [...] if the ACK contains an ACE field with
+ * the value 0b010 to 0b111 (decimal 2 to 7).
+ */
+static inline bool cookie_accecn_ok(const struct tcphdr *th)
+{
+ return tcp_accecn_ace(th) > 0x1;
+}
+
#if IS_ENABLED(CONFIG_BPF)
static inline bool cookie_bpf_ok(struct sk_buff *skb)
{
@@ -968,6 +1026,7 @@ 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 TCPHDR_SYNACK_ACCECN (TCPHDR_SYN | TCPHDR_ACK | TCPHDR_CWR)
#define TCP_ACCECN_CEP_ACE_MASK 0x7
#define TCP_ACCECN_ACE_MAX_DELTA 6
@@ -977,6 +1036,19 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
*/
#define TCP_ACCECN_CEP_INIT_OFFSET 5
+/* The highest ECN variant (Accurate ECN, ECN, or no ECN) that is
+ * attemped to be negotiated and requested for incoming connection
+ * and outgoing connection, respectively.
+ */
+enum tcp_ecn_mode {
+ TCP_ECN_IN_NOECN_OUT_NOECN = 0,
+ TCP_ECN_IN_ECN_OUT_ECN = 1,
+ TCP_ECN_IN_ECN_OUT_NOECN = 2,
+ TCP_ECN_IN_ACCECN_OUT_ACCECN = 3,
+ TCP_ECN_IN_ACCECN_OUT_ECN = 4,
+ TCP_ECN_IN_ACCECN_OUT_NOECN = 5,
+};
+
static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
{
tp->received_ce = 0;
@@ -1051,6 +1123,15 @@ struct tcp_skb_cb {
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
+static inline u16 tcp_accecn_reflector_flags(u8 ect)
+{
+ u32 flags = ect + 2;
+
+ if (ect == 3)
+ flags++;
+ return FIELD_PREP(TCPHDR_ACE, flags);
+}
+
extern const struct inet_connection_sock_af_ops ipv4_specific;
#if IS_ENABLED(CONFIG_IPV6)
@@ -1173,7 +1254,10 @@ 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)
+#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \
+ TCP_CONG_NEEDS_ACCECN)
union tcp_cc_info;
@@ -1305,6 +1389,13 @@ 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 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/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 5459a78b9809..3a44eb9c1d1a 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -403,6 +403,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_request_sock *ireq;
struct net *net = sock_net(sk);
+ struct tcp_request_sock *treq;
struct request_sock *req;
struct sock *ret = sk;
struct flowi4 fl4;
@@ -428,6 +429,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
}
ireq = inet_rsk(req);
+ treq = tcp_rsk(req);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
@@ -482,6 +484,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
if (!req->syncookie)
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
+ treq->accecn_ok = ireq->ecn_ok && cookie_accecn_ok(th);
ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
/* ip_queue_xmit() depends on our flow being setup
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3a43010d726f..75ec1a599b52 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -47,6 +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 = 5;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -728,7 +729,7 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
.extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_TWO,
+ .extra2 = &tcp_ecn_mode_max,
},
{
.procname = "tcp_ecn_fallback",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0c8a391d90fe..29146bb3585a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3396,6 +3396,8 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
+ tp->wait_third_ack = 0;
+ tp->accecn_fail_mode = 0;
tcp_accecn_init_counters(tp);
if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release)
icsk->icsk_ca_ops->release(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8dbb625f5e8a..f0475f95e112 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -401,14 +401,114 @@ static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb)
}
}
-static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
+/* AccECN specificaiton, 3.1.2: If a TCP server that implements AccECN
+ * receives a SYN with the three TCP header flags (AE, CWR and ECE) set
+ * to any combination other than 000, 011 or 111, it MUST negotiate the
+ * use of AccECN as if they had been set to 111.
+ */
+static bool tcp_accecn_syn_requested(const struct tcphdr *th)
+{
+ u8 ace = tcp_accecn_ace(th);
+
+ return ace && ace != 0x3;
+}
+
+/* Check ECN field transition to detect invalid transitions */
+static bool tcp_ect_transition_valid(u8 snt, u8 rcv)
{
- if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || th->cwr))
+ if (rcv == snt)
+ return true;
+
+ /* Non-ECT altered to something or something became non-ECT */
+ if (snt == INET_ECN_NOT_ECT || rcv == INET_ECN_NOT_ECT)
+ return false;
+ /* CE -> ECT(0/1)? */
+ if (snt == INET_ECN_CE)
+ return false;
+ return true;
+}
+
+bool tcp_accecn_validate_syn_feedback(struct sock *sk, u8 ace, u8 sent_ect)
+{
+ u8 ect = tcp_accecn_extract_syn_ect(ace);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+ return true;
+
+ if (!tcp_ect_transition_valid(sent_ect, ect)) {
+ tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV);
+ return false;
+ }
+
+ return true;
+}
+
+/* See Table 2 of the AccECN draft */
+
+static void tcp_ecn_rcv_synack(struct sock *sk, const struct tcphdr *th,
+ u8 ip_dsfield)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u8 ace = tcp_accecn_ace(th);
+
+ switch (ace) {
+ case 0x0:
+ case 0x7:
+ /* +========+========+============+=============+
+ * | A | B | SYN/ACK | Feedback |
+ * | | | B->A | Mode of A |
+ * | | | AE CWR ECE | |
+ * +========+========+============+=============+
+ * | AccECN | No ECN | 0 0 0 | Not ECN |
+ * | AccECN | Broken | 1 1 1 | Not ECN |
+ * +--------+--------+------------+-------------+
+ */
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 |
+ * +--------+--------+------------+-------------+
+ */
+ if (tcp_ecn_mode_pending(tp))
+ /* Downgrade from AccECN, or requested initially */
+ 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 (INET_ECN_is_ce(ip_dsfield) &&
+ tcp_accecn_validate_syn_feedback(sk, ace,
+ tp->syn_ect_snt)) {
+ tp->received_ce++;
+ tp->received_ce_pending++;
+ }
+ break;
+ }
}
-static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th)
+static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th,
+ const struct sk_buff *skb)
{
+ if (tcp_ecn_mode_pending(tp)) {
+ if (!tcp_accecn_syn_requested(th)) {
+ /* Downgrade to classic ECN feedback */
+ tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+ } else {
+ tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield &
+ INET_ECN_MASK;
+ tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
+ }
+ }
if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr))
tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
}
@@ -3833,8 +3933,18 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
}
+static void tcp_send_ack_reflect_ect(struct sock *sk, bool accecn_reflector)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u16 flags = 0;
+
+ if (accecn_reflector)
+ flags = tcp_accecn_reflector_flags(tp->syn_ect_rcv);
+ __tcp_send_ack(sk, tp->rcv_nxt, flags);
+}
+
/* RFC 5961 7 [ACK Throttling] */
-static void tcp_send_challenge_ack(struct sock *sk)
+static void tcp_send_challenge_ack(struct sock *sk, bool accecn_reflector)
{
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
@@ -3864,7 +3974,7 @@ static void tcp_send_challenge_ack(struct sock *sk)
WRITE_ONCE(net->ipv4.tcp_challenge_count, count - 1);
send_ack:
NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
- tcp_send_ack(sk);
+ tcp_send_ack_reflect_ect(sk, accecn_reflector);
}
}
@@ -4031,7 +4141,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
if (before(ack, prior_snd_una - max_window)) {
if (!(flag & FLAG_NO_CHALLENGE_ACK))
- tcp_send_challenge_ack(sk);
+ tcp_send_challenge_ack(sk, false);
return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
}
goto old_ack;
@@ -6025,8 +6135,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
}
/* Updates Accurate ECN received counters from the received IP ECN field */
-static void tcp_ecn_received_counters(struct sock *sk,
- const struct sk_buff *skb)
+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);
@@ -6068,6 +6177,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, int syn_inerr)
{
struct tcp_sock *tp = tcp_sk(sk);
+ bool accecn_reflector = false;
SKB_DR(reason);
/* RFC1323: H1. Apply PAWS check first. */
@@ -6160,7 +6270,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
if (tp->syn_fastopen && !tp->data_segs_in &&
sk->sk_state == TCP_ESTABLISHED)
tcp_fastopen_active_disable(sk);
- tcp_send_challenge_ack(sk);
+ tcp_send_challenge_ack(sk, false);
SKB_DR_SET(reason, TCP_RESET);
goto discard;
}
@@ -6171,16 +6281,23 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
* RFC 5961 4.2 : Send a challenge ack
*/
if (th->syn) {
+ if (tcp_ecn_mode_accecn(tp))
+ accecn_reflector = true;
if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
- TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt)
+ TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt) {
+ if (!tcp_ecn_disabled(tp)) {
+ tp->wait_third_ack = true;
+ tcp_send_ack_reflect_ect(sk, accecn_reflector);
+ }
goto pass;
+ }
syn_challenge:
if (syn_inerr)
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
- tcp_send_challenge_ack(sk);
+ tcp_send_challenge_ack(sk, accecn_reflector);
SKB_DR_SET(reason, TCP_INVALID_SYN);
goto discard;
}
@@ -6393,6 +6510,12 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
return;
step5:
+ if (unlikely(tp->wait_third_ack)) {
+ tp->wait_third_ack = 0;
+ if (tcp_ecn_mode_accecn(tp))
+ tcp_accecn_third_ack(sk, skb, tp->syn_ect_snt);
+ tcp_fast_path_on(tp);
+ }
tcp_ecn_received_counters(sk, skb);
reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT);
@@ -6645,7 +6768,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* state to ESTABLISHED..."
*/
- tcp_ecn_rcv_synack(tp, th);
+ if (tcp_ecn_mode_any(tp))
+ tcp_ecn_rcv_synack(sk, th, TCP_SKB_CB(skb)->ip_dsfield);
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
tcp_try_undo_spurious_syn(sk);
@@ -6717,7 +6841,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
TCP_DELACK_MAX, false);
goto consume;
}
- tcp_send_ack(sk);
+ tcp_send_ack_reflect_ect(sk, tcp_ecn_mode_accecn(tp));
return -1;
}
@@ -6776,7 +6900,7 @@ 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);
+ tcp_ecn_rcv_syn(tp, th, skb);
tcp_mtup_init(sk);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
@@ -6958,7 +7082,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
}
/* accept old ack during closing */
if ((int)reason < 0) {
- tcp_send_challenge_ack(sk);
+ tcp_send_challenge_ack(sk, false);
reason = -reason;
goto discard;
}
@@ -7005,9 +7129,16 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tp->lsndtime = tcp_jiffies32;
tcp_initialize_rcv_mss(sk);
- tcp_fast_path_on(tp);
+ if (likely(!tp->wait_third_ack)) {
+ if (tcp_ecn_mode_accecn(tp))
+ tcp_accecn_third_ack(sk, skb, tp->syn_ect_snt);
+ tcp_fast_path_on(tp);
+ }
if (sk->sk_shutdown & SEND_SHUTDOWN)
tcp_shutdown(sk, SEND_SHUTDOWN);
+
+ if (sk->sk_socket && tp->wait_third_ack)
+ goto consume;
break;
case TCP_FIN_WAIT1: {
@@ -7177,6 +7308,15 @@ static void tcp_ecn_create_request(struct request_sock *req,
bool ect, ecn_ok;
u32 ecn_ok_dst;
+ if (tcp_accecn_syn_requested(th) &&
+ (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 &
+ INET_ECN_MASK;
+ return;
+ }
+
if (!th_ecn)
return;
@@ -7184,7 +7324,8 @@ static void tcp_ecn_create_request(struct request_sock *req,
ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst;
- if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
+ if (((!ect || th->res1 || th->ae) && ecn_ok) ||
+ tcp_ca_needs_ecn(listen_sk) ||
(ecn_ok_dst & DST_FEATURE_ECN_CA) ||
tcp_bpf_ca_needs_ecn((struct sock *)req))
inet_rsk(req)->ecn_ok = 1;
@@ -7202,6 +7343,9 @@ static void tcp_openreq_init(struct request_sock *req,
tcp_rsk(req)->snt_synack = 0;
tcp_rsk(req)->snt_tsval_first = 0;
tcp_rsk(req)->last_oow_ack_time = 0;
+ tcp_rsk(req)->accecn_ok = 0;
+ tcp_rsk(req)->syn_ect_rcv = 0;
+ tcp_rsk(req)->syn_ect_snt = 0;
req->mss = rx_opt->mss_clamp;
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
ireq->tstamp_ok = rx_opt->tstamp_ok;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d5b5c32115d2..5cec04ed6a8e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1189,7 +1189,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
enum tcp_synack_type synack_type,
struct sk_buff *syn_skb)
{
- const struct inet_request_sock *ireq = inet_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct flowi4 fl4;
int err = -1;
struct sk_buff *skb;
@@ -1202,6 +1202,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
+ tcp_rsk(req)->syn_ect_snt = inet_sk(sk)->tos & INET_ECN_MASK;
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
tos = READ_ONCE(inet_sk(sk)->tos);
@@ -3448,7 +3449,7 @@ static void __net_init tcp_set_hashinfo(struct net *net)
static int __net_init tcp_sk_init(struct net *net)
{
- net->ipv4.sysctl_tcp_ecn = 2;
+ net->ipv4.sysctl_tcp_ecn = TCP_ECN_IN_ECN_OUT_NOECN;
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 43d7852ce07e..779a206a5ca6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -461,12 +461,51 @@ void tcp_openreq_init_rwin(struct request_sock *req,
ireq->rcv_wscale = rcv_wscale;
}
-static void tcp_ecn_openreq_child(struct tcp_sock *tp,
- const struct request_sock *req)
+void tcp_accecn_third_ack(struct sock *sk, const struct sk_buff *skb,
+ u8 syn_ect_snt)
{
- tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
- TCP_ECN_MODE_RFC3168 :
- TCP_ECN_DISABLED);
+ u8 ace = tcp_accecn_ace(tcp_hdr(skb));
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ switch (ace) {
+ case 0x0:
+ tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV);
+ break;
+ case 0x7:
+ case 0x5:
+ case 0x1:
+ /* Unused but legal values */
+ break;
+ default:
+ /* Validation only applies to first non-data packet */
+ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
+ !TCP_SKB_CB(skb)->sacked &&
+ tcp_accecn_validate_syn_feedback(sk, ace, syn_ect_snt)) {
+ if ((tcp_accecn_extract_syn_ect(ace) == INET_ECN_CE) &&
+ !tp->delivered_ce)
+ tp->delivered_ce++;
+ }
+ break;
+ }
+}
+
+static void tcp_ecn_openreq_child(struct sock *sk,
+ const struct request_sock *req,
+ const struct sk_buff *skb)
+{
+ const struct tcp_request_sock *treq = tcp_rsk(req);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (treq->accecn_ok) {
+ 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);
+ tcp_ecn_received_counters(sk, skb);
+ } else {
+ tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
+ TCP_ECN_MODE_RFC3168 :
+ TCP_ECN_DISABLED);
+ }
}
void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
@@ -631,7 +670,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
newtp->rx_opt.mss_clamp = req->mss;
- tcp_ecn_openreq_child(newtp, req);
+ tcp_ecn_openreq_child(newsk, req, skb);
newtp->fastopen_req = NULL;
RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 63352372248b..d0f0fee8335e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -322,7 +322,7 @@ static u16 tcp_select_window(struct sock *sk)
/* Packet ECN state for a SYN-ACK */
static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
{
- const struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
if (tcp_ecn_disabled(tp))
@@ -330,6 +330,13 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
else if (tcp_ca_needs_ecn(sk) ||
tcp_bpf_ca_needs_ecn(sk))
INET_ECN_xmit(sk);
+
+ if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) {
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE;
+ TCP_SKB_CB(skb)->tcp_flags |=
+ tcp_accecn_reflector_flags(tp->syn_ect_rcv);
+ tp->syn_ect_snt = inet_sk(sk)->tos & INET_ECN_MASK;
+ }
}
/* Packet ECN state for a SYN. */
@@ -337,8 +344,20 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
- bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
- tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
+ bool use_ecn, use_accecn;
+ u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn);
+
+ /* ============== ==========================
+ * tcp_ecn values Outgoing connections
+ * ============== ==========================
+ * 0,2,5 Do not request ECN
+ * 1,4 Request ECN connection
+ * 3 Request AccECN connection
+ * ============== ==========================
+ */
+ use_accecn = tcp_ecn == 3 || tcp_ca_needs_accecn(sk);
+ use_ecn = tcp_ecn == 1 || tcp_ecn == 4 ||
+ tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn;
if (!use_ecn) {
const struct dst_entry *dst = __sk_dst_get(sk);
@@ -354,35 +373,58 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
INET_ECN_xmit(sk);
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
- tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+ if (use_accecn) {
+ TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_AE;
+ tcp_ecn_mode_set(tp, TCP_ECN_MODE_PENDING);
+ tp->syn_ect_snt = inet_sk(sk)->tos & INET_ECN_MASK;
+ } else {
+ tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
+ }
}
}
static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
{
- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) {
/* tp->ecn_flags are cleared at a later point in time when
* SYN ACK is ultimatively being received.
*/
- TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE;
+ }
+}
+
+static void tcp_accecn_echo_syn_ect(struct tcphdr *th, u8 ect)
+{
+ th->ae = !!(ect & INET_ECN_ECT_0);
+ th->cwr = ect != INET_ECN_ECT_0;
+ th->ece = ect == INET_ECN_ECT_1;
}
static void
tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
{
- if (inet_rsk(req)->ecn_ok)
+ 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;
}
-static void tcp_accecn_set_ace(struct tcphdr *th, struct tcp_sock *tp)
+static void tcp_accecn_set_ace(struct tcp_sock *tp, struct sk_buff *skb,
+ struct tcphdr *th)
{
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;
+ /* The final packet of the 3WHS or anything like it must reflect
+ * the SYN/ACK ECT instead of putting CEP into ACE field, such
+ * case show up in tcp_flags.
+ */
+ if (likely(!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_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;
+ }
}
/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
@@ -397,8 +439,9 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
return;
if (tcp_ecn_mode_accecn(tp)) {
- INET_ECN_xmit(sk);
- tcp_accecn_set_ace(th, tp);
+ if (!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;
} else {
/* Not-retransmitted data segment: set ECT and inject CWR. */
@@ -3415,7 +3458,10 @@ 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 */
+ /* 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);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 9d83eadd308b..50046460ee0b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -264,6 +264,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
if (!req->syncookie)
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok &= cookie_ecn_ok(net, dst);
+ tcp_rsk(req)->accecn_ok = ireq->ecn_ok && cookie_accecn_ok(th);
ret = tcp_get_cookie_sock(sk, skb, req, dst);
if (!ret) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e8e68a142649..eb7dc7fb08cc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -544,6 +544,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
+ tcp_rsk(req)->syn_ect_snt = np->tclass & INET_ECN_MASK;
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 06/15] tcp: accecn: add AccECN rx byte counters
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (4 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 05/15] tcp: accecn: AccECN negotiation chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 9:44 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 07/15] tcp: accecn: AccECN needs to know delivered bytes chia-yu.chang
` (8 subsequent siblings)
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
These three byte counters track IP ECN field payload byte sums for
all arriving (acceptable) packets for ECT0, ECT1, and CE. The
AccECN option (added by a later patch in the series) echoes these
counters back to sender side; therefore, it is placed within the
group of tcp_sock_write_txrx.
Below are the pahole outcomes before and after this patch, in which
the group size of tcp_sock_write_txrx is increased from 95 + 4 to
107 + 4 and an extra 4-byte hole is created but will be exploited
in later patches:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ce; /* 2640 4 */
u32 received_ce; /* 2644 4 */
u32 app_limited; /* 2648 4 */
u32 rcv_wnd; /* 2652 4 */
struct tcp_options_received rx_opt; /* 2656 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2680 0 */
[...]
/* size: 3264, cachelines: 51, members: 169 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u32 delivered_ce; /* 2640 4 */
u32 received_ce; /* 2644 4 */
u32 received_ecn_bytes[3];/* 2648 12 */
u32 app_limited; /* 2660 4 */
u32 rcv_wnd; /* 2664 4 */
struct tcp_options_received rx_opt; /* 2668 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2692 0 */
/* XXX 4 bytes hole, try to pack */
[...]
/* size: 3264, cachelines: 51, members: 170 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Neal Cardwell <ncardwell@google.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>
---
.../networking/net_cachelines/tcp_sock.rst | 1 +
include/linux/tcp.h | 4 ++++
include/net/tcp.h | 18 +++++++++++++++++-
net/ipv4/tcp.c | 3 ++-
net/ipv4/tcp_input.c | 13 +++++++++----
net/ipv4/tcp_minisocks.c | 3 ++-
6 files changed, 35 insertions(+), 7 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index eef8700085de..64306ae096cd 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -102,6 +102,7 @@ u32 prr_out read_mostly read_m
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
+u32[3] received_ecn_bytes 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
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b0e6a11a3fa1..427f2adab247 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -307,6 +307,10 @@ struct tcp_sock {
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 received_ecn_bytes[3]; /* received byte counters for three ECN
+ * types: INET_ECN_ECT_1, INET_ECN_ECT_0,
+ * and INET_ECN_CE
+ */
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 5fce4b49e132..101e07b8a089 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -467,7 +467,8 @@ 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);
-void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb);
+void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
+ u32 payload_len);
enum tcp_tw_status {
TCP_TW_SUCCESS = 0,
@@ -1035,6 +1036,20 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
* See draft-ietf-tcpm-accurate-ecn for the latest values.
*/
#define TCP_ACCECN_CEP_INIT_OFFSET 5
+#define TCP_ACCECN_E1B_INIT_OFFSET 1
+#define TCP_ACCECN_E0B_INIT_OFFSET 1
+#define TCP_ACCECN_CEB_INIT_OFFSET 0
+
+static inline void __tcp_accecn_init_bytes_counters(int *counter_array)
+{
+ BUILD_BUG_ON(INET_ECN_ECT_1 != 0x1);
+ BUILD_BUG_ON(INET_ECN_ECT_0 != 0x2);
+ BUILD_BUG_ON(INET_ECN_CE != 0x3);
+
+ counter_array[INET_ECN_ECT_1 - 1] = 0;
+ counter_array[INET_ECN_ECT_0 - 1] = 0;
+ counter_array[INET_ECN_CE - 1] = 0;
+}
/* The highest ECN variant (Accurate ECN, ECN, or no ECN) that is
* attemped to be negotiated and requested for incoming connection
@@ -1053,6 +1068,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
{
tp->received_ce = 0;
tp->received_ce_pending = 0;
+ __tcp_accecn_init_bytes_counters(tp->received_ecn_bytes);
}
/* State flags for sacked in struct tcp_skb_cb */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 29146bb3585a..af52ebfdd734 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5127,6 +5127,7 @@ static void __init tcp_struct_check(void)
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, received_ecn_bytes);
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);
@@ -5134,7 +5135,7 @@ 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, 95 + 4);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 107 + 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 f0475f95e112..76fda2a63add 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6135,7 +6135,8 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
}
/* Updates Accurate ECN received counters from the received IP ECN field */
-void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb)
+void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
+ u32 payload_len)
{
u8 ecnfield = TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK;
u8 is_ce = INET_ECN_is_ce(ecnfield);
@@ -6150,6 +6151,9 @@ void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb)
tp->received_ce += pcount;
tp->received_ce_pending = min(tp->received_ce_pending + pcount,
0xfU);
+
+ if (payload_len > 0)
+ tp->received_ecn_bytes[ecnfield - 1] += payload_len;
}
}
@@ -6423,7 +6427,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
flag |= __tcp_replace_ts_recent(tp,
delta);
- tcp_ecn_received_counters(sk, skb);
+ tcp_ecn_received_counters(sk, skb, 0);
/* We know that such packets are checksummed
* on entry.
@@ -6469,7 +6473,8 @@ 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);
+ tcp_ecn_received_counters(sk, skb,
+ len - tcp_header_len);
eaten = tcp_queue_rcv(sk, skb, &fragstolen);
tcp_event_data_recv(sk, skb);
@@ -6516,7 +6521,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
tcp_accecn_third_ack(sk, skb, tp->syn_ect_snt);
tcp_fast_path_on(tp);
}
- tcp_ecn_received_counters(sk, skb);
+ tcp_ecn_received_counters(sk, skb, len - th->doff * 4);
reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT);
if ((int)reason < 0) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 779a206a5ca6..3f8225bae49f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -497,10 +497,11 @@ static void tcp_ecn_openreq_child(struct sock *sk,
struct tcp_sock *tp = tcp_sk(sk);
if (treq->accecn_ok) {
+ const struct tcphdr *th = (const struct tcphdr *)skb->data;
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);
- tcp_ecn_received_counters(sk, skb);
+ tcp_ecn_received_counters(sk, skb, skb->len - th->doff * 4);
} else {
tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
TCP_ECN_MODE_RFC3168 :
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 06/15] tcp: accecn: add AccECN rx byte counters
2025-05-14 13:56 ` [PATCH v7 net-next 06/15] tcp: accecn: add AccECN rx byte counters chia-yu.chang
@ 2025-05-20 9:44 ` Paolo Abeni
0 siblings, 0 replies; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 9:44 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
> index 779a206a5ca6..3f8225bae49f 100644
> --- a/net/ipv4/tcp_minisocks.c
> +++ b/net/ipv4/tcp_minisocks.c
> @@ -497,10 +497,11 @@ static void tcp_ecn_openreq_child(struct sock *sk,
> struct tcp_sock *tp = tcp_sk(sk);
>
> if (treq->accecn_ok) {
> + const struct tcphdr *th = (const struct tcphdr *)skb->data;
Minor nit: please insert an empty line between the variable declaration
and the code.
> 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);
> - tcp_ecn_received_counters(sk, skb);
> + tcp_ecn_received_counters(sk, skb, skb->len - th->doff * 4);
There is an identic statement a few lines above, possibly worth an helper.
/P
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 07/15] tcp: accecn: AccECN needs to know delivered bytes
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (5 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 06/15] tcp: accecn: add AccECN rx byte counters chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 08/15] tcp: sack option handling improvements chia-yu.chang
` (7 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
AccECN byte counter estimation requires delivered bytes
which can be calculated while processing SACK blocks and
cumulative ACK. The delivered bytes will be used to estimate
the byte counters between AccECN option (on ACKs w/o the
option).
Non-SACK calculation is quite annoying, inaccurate, and
likely bogus.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
net/ipv4/tcp_input.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 76fda2a63add..e710ccf22dc8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1191,6 +1191,7 @@ struct tcp_sacktag_state {
u64 last_sackt;
u32 reord;
u32 sack_delivered;
+ u32 delivered_bytes;
int flag;
unsigned int mss_now;
struct rate_sample *rate;
@@ -1552,7 +1553,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
static u8 tcp_sacktag_one(struct sock *sk,
struct tcp_sacktag_state *state, u8 sacked,
u32 start_seq, u32 end_seq,
- int dup_sack, int pcount,
+ int dup_sack, int pcount, u32 plen,
u64 xmit_time)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1612,6 +1613,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
tp->sacked_out += pcount;
/* Out-of-order packets delivered */
state->sack_delivered += pcount;
+ state->delivered_bytes += plen;
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
if (tp->lost_skb_hint &&
@@ -1653,7 +1655,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
* tcp_highest_sack_seq() when skb is highest_sack.
*/
tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
- start_seq, end_seq, dup_sack, pcount,
+ start_seq, end_seq, dup_sack, pcount, skb->len,
tcp_skb_timestamp_us(skb));
tcp_rate_skb_delivered(sk, skb, state->rate);
@@ -1945,6 +1947,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
TCP_SKB_CB(skb)->end_seq,
dup_sack,
tcp_skb_pcount(skb),
+ skb->len,
tcp_skb_timestamp_us(skb));
tcp_rate_skb_delivered(sk, skb, state->rate);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
@@ -3561,6 +3564,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
if (sacked & TCPCB_SACKED_ACKED) {
tp->sacked_out -= acked_pcount;
+ /* snd_una delta covers these skbs */
+ sack->delivered_bytes -= skb->len;
} else if (tcp_is_sack(tp)) {
tcp_count_delivered(tp, acked_pcount, ece_ack);
if (!tcp_skb_spurious_retrans(tp, skb))
@@ -3664,6 +3669,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
delta = prior_sacked - tp->sacked_out;
tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
}
+
+ sack->delivered_bytes = (skb ?
+ TCP_SKB_CB(skb)->seq : tp->snd_una) -
+ prior_snd_una;
} else if (skb && rtt_update && sack_rtt_us >= 0 &&
sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
tcp_skb_timestamp_us(skb))) {
@@ -4126,6 +4135,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
sack_state.first_sackt = 0;
sack_state.rate = &rs;
sack_state.sack_delivered = 0;
+ sack_state.delivered_bytes = 0;
/* We very likely will need to access rtx queue. */
prefetch(sk->tcp_rtx_queue.rb_node);
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 08/15] tcp: sack option handling improvements
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (6 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 07/15] tcp: accecn: AccECN needs to know delivered bytes chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 9:34 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 09/15] tcp: accecn: AccECN option chia-yu.chang
` (6 subsequent siblings)
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
1) Don't early return when sack doesn't fit. AccECN code will be
placed after this fragment so no early returns please.
2) Make sure opts->num_sack_blocks is not left undefined. E.g.,
tcp_current_mss() does not memset its opts struct to zero.
AccECN code checks if SACK option is present and may even
alter it to make room for AccECN option when many SACK blocks
are present. Thus, num_sack_blocks needs to be always valid.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
net/ipv4/tcp_output.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d0f0fee8335e..d7fef3d2698b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1092,17 +1092,18 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
if (unlikely(eff_sacks)) {
const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
- if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
- TCPOLEN_SACK_PERBLOCK))
- return size;
-
- opts->num_sack_blocks =
- min_t(unsigned int, eff_sacks,
- (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
- TCPOLEN_SACK_PERBLOCK);
-
- size += TCPOLEN_SACK_BASE_ALIGNED +
- opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+ if (likely(remaining >= TCPOLEN_SACK_BASE_ALIGNED +
+ TCPOLEN_SACK_PERBLOCK)) {
+ opts->num_sack_blocks =
+ min_t(unsigned int, eff_sacks,
+ (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
+ TCPOLEN_SACK_PERBLOCK);
+
+ size += TCPOLEN_SACK_BASE_ALIGNED +
+ opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+ }
+ } else {
+ opts->num_sack_blocks = 0;
}
if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 08/15] tcp: sack option handling improvements
2025-05-14 13:56 ` [PATCH v7 net-next 08/15] tcp: sack option handling improvements chia-yu.chang
@ 2025-05-20 9:34 ` Paolo Abeni
0 siblings, 0 replies; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 9:34 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> From: Ilpo Järvinen <ij@kernel.org>
>
> 1) Don't early return when sack doesn't fit. AccECN code will be
> placed after this fragment so no early returns please.
>
> 2) Make sure opts->num_sack_blocks is not left undefined. E.g.,
> tcp_current_mss() does not memset its opts struct to zero.
> AccECN code checks if SACK option is present and may even
> alter it to make room for AccECN option when many SACK blocks
> are present. Thus, num_sack_blocks needs to be always valid.
>
> Signed-off-by: Ilpo Järvinen <ij@kernel.org>
> Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
> ---
> net/ipv4/tcp_output.c | 23 ++++++++++++-----------
> 1 file changed, 12 insertions(+), 11 deletions(-)
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index d0f0fee8335e..d7fef3d2698b 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -1092,17 +1092,18 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
> eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
> if (unlikely(eff_sacks)) {
> const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
> - if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
> - TCPOLEN_SACK_PERBLOCK))
> - return size;
> -
> - opts->num_sack_blocks =
> - min_t(unsigned int, eff_sacks,
> - (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
> - TCPOLEN_SACK_PERBLOCK);
> -
> - size += TCPOLEN_SACK_BASE_ALIGNED +
> - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
> + if (likely(remaining >= TCPOLEN_SACK_BASE_ALIGNED +
> + TCPOLEN_SACK_PERBLOCK)) {
> + opts->num_sack_blocks =
> + min_t(unsigned int, eff_sacks,
> + (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
> + TCPOLEN_SACK_PERBLOCK);
> +
> + size += TCPOLEN_SACK_BASE_ALIGNED +
> + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
> + }
> + } else {
> + opts->num_sack_blocks = 0;
> }
AFAICS here opts->num_sack_blocks is still uninitialized when:
eff_acks != 0 &&
remaining < (TCPOLEN_SACK_BASE_ALIGNED + TCPOLEN_SACK_PERBLOCK)
/P
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (7 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 08/15] tcp: sack option handling improvements chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 9:31 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 10/15] tcp: accecn: AccECN option send control chia-yu.chang
` (5 subsequent siblings)
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
The Accurate ECN allows echoing back the sum of bytes for
each IP ECN field value in the received packets using
AccECN option. This change implements AccECN option tx & rx
side processing without option send control related features
that are added by a later change.
Based on specification:
https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt
(Some features of the spec will be added in the later changes
rather than in this one).
A full-length AccECN option is always attempted but if it does
not fit, the minimum length is selected based on the counters
that have changed since the last update. The AccECN option
(with 24-bit fields) often ends in odd sizes so the option
write code tries to take advantage of some nop used to pad
the other TCP options.
The delivered_ecn_bytes pairs with received_ecn_bytes similar
to how delivered_ce pairs with received_ce. In contrast to
ACE field, however, the option is not always available to update
delivered_ecn_bytes. For ACK w/o AccECN option, the delivered
bytes calculated based on the cumulative ACK+SACK information
are assigned to one of the counters using an estimation
heuristic to select the most likely ECN byte counter. Any
estimation error is corrected when the next AccECN option
arrives. It may occur that the heuristic gets too confused
when there are enough different byte counter deltas between
ACKs with the AccECN option in which case the heuristic just
gives up on updating the counters for a while.
tcp_ecn_option sysctl can be used to select option sending
mode for AccECN: TCP_ECN_OPTION_DISABLED, TCP_ECN_OPTION_MINIMUM,
and TCP_ECN_OPTION_FULL.
This patch increases the size of tcp_info struct, as there is
no existing holes for new u32 variables. Below are the pahole
outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_info {
[...]
__u32 tcpi_total_rto_time; /* 244 4 */
/* size: 248, cachelines: 4, members: 61 */
}
[AFTER THIS PATCH]
struct tcp_info {
[...]
__u32 tcpi_total_rto_time; /* 244 4 */
__u32 tcpi_received_ce; /* 248 4 */
__u32 tcpi_delivered_e1_bytes; /* 252 4 */
__u32 tcpi_delivered_e0_bytes; /* 256 4 */
__u32 tcpi_delivered_ce_bytes; /* 260 4 */
__u32 tcpi_received_e1_bytes; /* 264 4 */
__u32 tcpi_received_e0_bytes; /* 268 4 */
__u32 tcpi_received_ce_bytes; /* 272 4 */
/* size: 280, cachelines: 5, members: 68 */
}
This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
group for new u8 members, but adds a 4-byte hole in tcp_sock_write_rx
group after the new u32 delivered_ecn_bytes[3] member. Therefore, the
group size of tcp_sock_write_rx is increased from 96 to 112. Below
are the pahole outcomes before and after this patch:
[BEFORE THIS PATCH]
struct tcp_sock {
[...]
u8 received_ce_pending:4; /* 2586: 0 1 */
u8 unused2:4; /* 2586: 4 1 */
/* XXX 1 byte hole, try to pack */
[...]
u32 rcv_rtt_last_tsecr; /* 2732 4 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2792 0 */
[...]
/* size: 3264, cachelines: 51, members: 170 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u8 received_ce_pending:4;/* 2586: 0 1 */
u8 unused2:4; /* 2586: 4 1 */
u8 accecn_minlen:2; /* 2587: 0 1 */
u8 est_ecnfield:2; /* 2587: 2 1 */
u8 unused3:4; /* 2587: 4 1 */
[...]
u32 rcv_rtt_last_tsecr; /* 2732 4 */
u32 delivered_ecn_bytes[3];/* 2736 12 */
/* XXX 4 bytes hole, try to pack */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2808 0 */
[...]
/* size: 3264, cachelines: 51, members: 174 */
}
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Neal Cardwell <ncardwell@google.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>
---
.../networking/net_cachelines/tcp_sock.rst | 3 +
include/linux/tcp.h | 9 +-
include/net/netns/ipv4.h | 1 +
include/net/tcp.h | 20 +++
include/uapi/linux/tcp.h | 7 +
net/ipv4/sysctl_net_ipv4.c | 9 +
net/ipv4/tcp.c | 15 +-
net/ipv4/tcp_input.c | 166 +++++++++++++++++-
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_output.c | 151 +++++++++++++++-
10 files changed, 369 insertions(+), 13 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 64306ae096cd..c74f939f32cc 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -104,9 +104,12 @@ u32 delivered_ce read_mostly read_w
u32 received_ce read_mostly read_write
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
u8:2 syn_ect_snt write_mostly read_write
u8:2 syn_ect_rcv read_mostly read_write
u8:1 wait_third_ack read_write
+u8:2 accecn_minlen write_mostly read_write
+u8:2 est_ecnfield 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)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 427f2adab247..afb1a5ac65bf 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -122,8 +122,9 @@ struct tcp_options_received {
smc_ok : 1, /* SMC seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
- u8 saw_unknown:1, /* Received unknown option */
- unused:7;
+ u8 accecn:6, /* AccECN index in header, 0=no options */
+ saw_unknown:1, /* Received unknown option */
+ unused:1;
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
@@ -294,6 +295,9 @@ struct tcp_sock {
rate_app_limited:1; /* rate_{delivered,interval_us} limited? */
u8 received_ce_pending:4, /* Not yet transmit cnt of received_ce */
unused2:4;
+ u8 accecn_minlen:2,/* Minimum length of AccECN option sent */
+ est_ecnfield:2,/* ECN field for AccECN delivered estimates */
+ unused3:4;
__be32 pred_flags;
u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
u64 tcp_mstamp; /* most recent packet received/sent */
@@ -338,6 +342,7 @@ struct tcp_sock {
u32 rate_delivered; /* saved rate sample: packets delivered */
u32 rate_interval_us; /* saved rate sample: time elapsed */
u32 rcv_rtt_last_tsecr;
+ u32 delivered_ecn_bytes[3];
u64 first_tx_mstamp; /* start of window send phase */
u64 delivered_mstamp; /* time we reached "delivered" */
u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 6373e3f17da8..4569a9ef4fb8 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -148,6 +148,7 @@ struct netns_ipv4 {
struct local_ports ip_local_ports;
u8 sysctl_tcp_ecn;
+ u8 sysctl_tcp_ecn_option;
u8 sysctl_tcp_ecn_fallback;
u8 sysctl_ip_default_ttl;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 101e07b8a089..50ad6e33d52d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -204,6 +204,8 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
#define TCPOPT_AO 29 /* Authentication Option (RFC5925) */
#define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */
#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */
+#define TCPOPT_ACCECN0 172 /* 0xAC: Accurate ECN Order 0 */
+#define TCPOPT_ACCECN1 174 /* 0xAE: Accurate ECN Order 1 */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
* experimental options. See draft-ietf-tcpm-experimental-options-00.txt
@@ -221,6 +223,7 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
#define TCPOLEN_FASTOPEN_BASE 2
+#define TCPOLEN_ACCECN_BASE 2
#define TCPOLEN_EXP_FASTOPEN_BASE 4
#define TCPOLEN_EXP_SMC_BASE 6
@@ -234,6 +237,13 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
#define TCPOLEN_MD5SIG_ALIGNED 20
#define TCPOLEN_MSS_ALIGNED 4
#define TCPOLEN_EXP_SMC_BASE_ALIGNED 8
+#define TCPOLEN_ACCECN_PERFIELD 3
+
+/* Maximum number of byte counters in AccECN option + size */
+#define TCP_ACCECN_NUMFIELDS 3
+#define TCP_ACCECN_MAXSIZE (TCPOLEN_ACCECN_BASE + \
+ TCPOLEN_ACCECN_PERFIELD * \
+ TCP_ACCECN_NUMFIELDS)
/* tp->accecn_fail_mode */
#define TCP_ACCECN_ACE_FAIL_SEND BIT(0)
@@ -1064,11 +1074,21 @@ enum tcp_ecn_mode {
TCP_ECN_IN_ACCECN_OUT_NOECN = 5,
};
+/* AccECN option sending when AccECN has been successfully negotiated */
+enum tcp_ecn_option {
+ TCP_ECN_OPTION_DISABLED = 0,
+ TCP_ECN_OPTION_MINIMUM = 1,
+ TCP_ECN_OPTION_FULL = 2,
+};
+
static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
{
tp->received_ce = 0;
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_minlen = 0;
+ tp->est_ecnfield = 0;
}
/* State flags for sacked in struct tcp_skb_cb */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index bdac8c42fa82..53e0e85b52be 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -316,6 +316,13 @@ struct tcp_info {
* in milliseconds, including any
* unfinished recovery.
*/
+ __u32 tcpi_received_ce; /* # of CE marks received */
+ __u32 tcpi_delivered_e1_bytes; /* Accurate ECN byte counters */
+ __u32 tcpi_delivered_e0_bytes;
+ __u32 tcpi_delivered_ce_bytes;
+ __u32 tcpi_received_e1_bytes;
+ __u32 tcpi_received_e0_bytes;
+ __u32 tcpi_received_ce_bytes;
};
/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 75ec1a599b52..1d7fd86ca7b9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -731,6 +731,15 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = &tcp_ecn_mode_max,
},
+ {
+ .procname = "tcp_ecn_option",
+ .data = &init_net.ipv4.sysctl_tcp_ecn_option,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
{
.procname = "tcp_ecn_fallback",
.data = &init_net.ipv4.sysctl_tcp_ecn_fallback,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index af52ebfdd734..a71260838ccf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -270,6 +270,7 @@
#include <net/icmp.h>
#include <net/inet_common.h>
+#include <net/inet_ecn.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include <net/proto_memory.h>
@@ -4142,6 +4143,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
const struct inet_connection_sock *icsk = inet_csk(sk);
+ const u8 ect1_idx = INET_ECN_ECT_1 - 1;
+ const u8 ect0_idx = INET_ECN_ECT_0 - 1;
+ const u8 ce_idx = INET_ECN_CE - 1;
unsigned long rate;
u32 now;
u64 rate64;
@@ -4268,6 +4272,14 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
if (tp->rto_stamp)
info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp;
+ info->tcpi_received_ce = tp->received_ce;
+ info->tcpi_delivered_e1_bytes = tp->delivered_ecn_bytes[ect1_idx];
+ info->tcpi_delivered_e0_bytes = tp->delivered_ecn_bytes[ect0_idx];
+ info->tcpi_delivered_ce_bytes = tp->delivered_ecn_bytes[ce_idx];
+ info->tcpi_received_e1_bytes = tp->received_ecn_bytes[ect1_idx];
+ info->tcpi_received_e0_bytes = tp->received_ecn_bytes[ect0_idx];
+ info->tcpi_received_ce_bytes = tp->received_ecn_bytes[ce_idx];
+
unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -5147,12 +5159,13 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered);
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, 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);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 96);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 112);
}
void __init tcp_init(void)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e710ccf22dc8..3de8cc56c5cd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -70,6 +70,7 @@
#include <linux/sysctl.h>
#include <linux/kernel.h>
#include <linux/prefetch.h>
+#include <linux/bitops.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/proto_memory.h>
@@ -520,6 +521,139 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
return false;
}
+/* Maps IP ECN field ECT/CE code point to AccECN option field number, given
+ * we are sending fields with Accurate ECN Order 1: ECT(1), CE, ECT(0).
+ */
+static u8 tcp_ecnfield_to_accecn_optfield(u8 ecnfield)
+{
+ switch (ecnfield & INET_ECN_MASK) {
+ case INET_ECN_NOT_ECT:
+ return 0; /* AccECN does not send counts of NOT_ECT */
+ case INET_ECN_ECT_1:
+ return 1;
+ case INET_ECN_CE:
+ return 2;
+ case INET_ECN_ECT_0:
+ return 3;
+ }
+ return 0;
+}
+
+/* Maps IP ECN field ECT/CE code point to AccECN option field value offset.
+ * Some fields do not start from zero, to detect zeroing by middleboxes.
+ */
+static u32 tcp_accecn_field_init_offset(u8 ecnfield)
+{
+ switch (ecnfield & INET_ECN_MASK) {
+ case INET_ECN_NOT_ECT:
+ return 0; /* AccECN does not send counts of NOT_ECT */
+ case INET_ECN_ECT_1:
+ return TCP_ACCECN_E1B_INIT_OFFSET;
+ case INET_ECN_CE:
+ return TCP_ACCECN_CEB_INIT_OFFSET;
+ case INET_ECN_ECT_0:
+ return TCP_ACCECN_E0B_INIT_OFFSET;
+ }
+ return 0;
+}
+
+/* Maps AccECN option field #nr to IP ECN field ECT/CE bits */
+static unsigned int tcp_accecn_optfield_to_ecnfield(unsigned int optfield,
+ bool order)
+{
+ u8 tmp;
+
+ optfield = order ? 2 - optfield : optfield;
+ tmp = optfield + 2;
+
+ return (tmp + (tmp >> 2)) & INET_ECN_MASK;
+}
+
+/* Handles AccECN option ECT and CE 24-bit byte counters update into
+ * the u32 value in tcp_sock. As we're processing TCP options, it is
+ * safe to access from - 1.
+ */
+static s32 tcp_update_ecn_bytes(u32 *cnt, const char *from, u32 init_offset)
+{
+ u32 truncated = (get_unaligned_be32(from - 1) - init_offset) &
+ 0xFFFFFFU;
+ u32 delta = (truncated - *cnt) & 0xFFFFFFU;
+
+ /* If delta has the highest bit set (24th bit) indicating
+ * negative, sign extend to correct an estimation using
+ * sign_extend32(delta, 24 - 1)
+ */
+ delta = sign_extend32(delta, 23);
+ *cnt += delta;
+ return (s32)delta;
+}
+
+/* Returns true if the byte counters can be used */
+static bool tcp_accecn_process_option(struct tcp_sock *tp,
+ const struct sk_buff *skb,
+ u32 delivered_bytes, int flag)
+{
+ u8 estimate_ecnfield = tp->est_ecnfield;
+ bool ambiguous_ecn_bytes_incr = false;
+ bool first_changed = false;
+ unsigned int optlen;
+ bool order1, res;
+ unsigned int i;
+ u8 *ptr;
+
+ if (!(flag & FLAG_SLOWPATH) || !tp->rx_opt.accecn) {
+ if (estimate_ecnfield) {
+ u8 ecnfield = estimate_ecnfield - 1;
+
+ tp->delivered_ecn_bytes[ecnfield] += delivered_bytes;
+ return true;
+ }
+ return false;
+ }
+
+ ptr = skb_transport_header(skb) + tp->rx_opt.accecn;
+ optlen = ptr[1] - 2;
+ WARN_ON_ONCE(ptr[0] != TCPOPT_ACCECN0 && ptr[0] != TCPOPT_ACCECN1);
+ order1 = (ptr[0] == TCPOPT_ACCECN1);
+ ptr += 2;
+
+ res = !!estimate_ecnfield;
+ for (i = 0; i < 3; i++) {
+ if (optlen < TCPOLEN_ACCECN_PERFIELD)
+ continue;
+
+ u32 init_offset;
+ u8 ecnfield;
+ s32 delta;
+ u32 *cnt;
+
+ ecnfield = tcp_accecn_optfield_to_ecnfield(i, order1);
+ init_offset = tcp_accecn_field_init_offset(ecnfield);
+ cnt = &tp->delivered_ecn_bytes[ecnfield - 1];
+ delta = tcp_update_ecn_bytes(cnt, ptr, init_offset);
+ if (delta && delta < 0) {
+ res = false;
+ ambiguous_ecn_bytes_incr = true;
+ }
+ if (delta && ecnfield != estimate_ecnfield) {
+ if (!first_changed) {
+ tp->est_ecnfield = ecnfield;
+ first_changed = true;
+ } else {
+ res = false;
+ ambiguous_ecn_bytes_incr = true;
+ }
+ }
+
+ optlen -= TCPOLEN_ACCECN_PERFIELD;
+ ptr += TCPOLEN_ACCECN_PERFIELD;
+ }
+ if (ambiguous_ecn_bytes_incr)
+ tp->est_ecnfield = 0;
+
+ return res;
+}
+
static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count)
{
tp->delivered_ce += ecn_count;
@@ -536,7 +670,8 @@ 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, int flag)
+ u32 delivered_pkts, u32 delivered_bytes,
+ int flag)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcp_sock *tp = tcp_sk(sk);
@@ -547,6 +682,8 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
if (!(flag & (FLAG_FORWARD_PROGRESS | FLAG_TS_PROGRESS)))
return 0;
+ tcp_accecn_process_option(tp, skb, delivered_bytes, flag);
+
if (!(flag & FLAG_SLOWPATH)) {
/* AccECN counter might overflow on large ACKs */
if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK)
@@ -572,12 +709,14 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
}
static u32 tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
- u32 delivered_pkts, int *flag)
+ u32 delivered_pkts, u32 delivered_bytes,
+ int *flag)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 delta;
- delta = __tcp_accecn_process(sk, skb, delivered_pkts, *flag);
+ delta = __tcp_accecn_process(sk, skb, delivered_pkts,
+ delivered_bytes, *flag);
if (delta > 0) {
tcp_count_delivered_ce(tp, delta);
*flag |= FLAG_ECE;
@@ -4241,6 +4380,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (tcp_ecn_mode_accecn(tp))
ecn_count = tcp_accecn_process(sk, skb,
tp->delivered - delivered,
+ sack_state.delivered_bytes,
&flag);
tcp_in_ack_event(sk, flag);
@@ -4280,6 +4420,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (tcp_ecn_mode_accecn(tp))
ecn_count = tcp_accecn_process(sk, 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. */
@@ -4407,6 +4548,7 @@ void tcp_parse_options(const struct net *net,
ptr = (const unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
+ opt_rx->accecn = 0;
opt_rx->saw_unknown = 0;
while (length > 0) {
@@ -4498,6 +4640,12 @@ void tcp_parse_options(const struct net *net,
ptr, th->syn, foc, false);
break;
+ case TCPOPT_ACCECN0:
+ case TCPOPT_ACCECN1:
+ /* Save offset of AccECN option in TCP header */
+ opt_rx->accecn = (ptr - 2) - (__u8 *)th;
+ break;
+
case TCPOPT_EXP:
/* Fast Open option shares code 254 using a
* 16 bits magic number.
@@ -4558,11 +4706,14 @@ static bool tcp_fast_parse_options(const struct net *net,
*/
if (th->doff == (sizeof(*th) / 4)) {
tp->rx_opt.saw_tstamp = 0;
+ tp->rx_opt.accecn = 0;
return false;
} else if (tp->rx_opt.tstamp_ok &&
th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) {
- if (tcp_parse_aligned_timestamp(tp, th))
+ if (tcp_parse_aligned_timestamp(tp, th)) {
+ tp->rx_opt.accecn = 0;
return true;
+ }
}
tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL);
@@ -6162,8 +6313,12 @@ void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
tp->received_ce_pending = min(tp->received_ce_pending + pcount,
0xfU);
- if (payload_len > 0)
+ if (payload_len > 0) {
+ u8 minlen = tcp_ecnfield_to_accecn_optfield(ecnfield);
tp->received_ecn_bytes[ecnfield - 1] += payload_len;
+ tp->accecn_minlen = max_t(u8, tp->accecn_minlen,
+ minlen);
+ }
}
}
@@ -6383,6 +6538,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
*/
tp->rx_opt.saw_tstamp = 0;
+ tp->rx_opt.accecn = 0;
/* pred_flags is 0xS?10 << 16 + snd_wnd
* if header_prediction is to be made
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5cec04ed6a8e..cc3049bb9d02 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3450,6 +3450,7 @@ static void __net_init tcp_set_hashinfo(struct net *net)
static int __net_init tcp_sk_init(struct net *net)
{
net->ipv4.sysctl_tcp_ecn = TCP_ECN_IN_ECN_OUT_NOECN;
+ net->ipv4.sysctl_tcp_ecn_option = TCP_ECN_OPTION_FULL;
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d7fef3d2698b..0a4d9791b4a2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -492,6 +492,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_SMC BIT(9)
#define OPTION_MPTCP BIT(10)
#define OPTION_AO BIT(11)
+#define OPTION_ACCECN BIT(12)
static void smc_options_write(__be32 *ptr, u16 *options)
{
@@ -513,12 +514,14 @@ struct tcp_out_options {
u16 mss; /* 0 to disable */
u8 ws; /* window scale, 0 to disable */
u8 num_sack_blocks; /* number of SACK blocks to include */
+ u8 num_accecn_fields; /* number of AccECN fields needed */
u8 hash_size; /* bytes in hash_location */
u8 bpf_opt_len; /* length of BPF hdr option */
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
struct mptcp_out_options mptcp;
+ u32 *ecn_bytes; /* AccECN ECT/CE byte counters */
};
static void mptcp_options_write(struct tcphdr *th, __be32 *ptr,
@@ -710,6 +713,8 @@ static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
return ptr;
}
+#define NOP_LEFTOVER ((TCPOPT_NOP << 8) | TCPOPT_NOP)
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -728,8 +733,10 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
struct tcp_out_options *opts,
struct tcp_key *key)
{
+ u16 leftover_bytes = NOP_LEFTOVER; /* replace next NOPs if avail */
__be32 *ptr = (__be32 *)(th + 1);
u16 options = opts->options; /* mungable copy */
+ int leftover_size = 2;
if (tcp_key_is_md5(key)) {
*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
@@ -763,18 +770,64 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
*ptr++ = htonl(opts->tsecr);
}
+ if (OPTION_ACCECN & options) {
+ const u8 ect0_idx = INET_ECN_ECT_0 - 1;
+ const u8 ect1_idx = INET_ECN_ECT_1 - 1;
+ const u8 ce_idx = INET_ECN_CE - 1;
+ u32 e0b;
+ u32 e1b;
+ u32 ceb;
+ u8 len;
+
+ e0b = opts->ecn_bytes[ect0_idx] + TCP_ACCECN_E0B_INIT_OFFSET;
+ e1b = opts->ecn_bytes[ect1_idx] + TCP_ACCECN_E1B_INIT_OFFSET;
+ ceb = opts->ecn_bytes[ce_idx] + TCP_ACCECN_CEB_INIT_OFFSET;
+ len = TCPOLEN_ACCECN_BASE +
+ opts->num_accecn_fields * TCPOLEN_ACCECN_PERFIELD;
+
+ if (opts->num_accecn_fields == 2) {
+ *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+ ((e1b >> 8) & 0xffff));
+ *ptr++ = htonl(((e1b & 0xff) << 24) |
+ (ceb & 0xffffff));
+ } else if (opts->num_accecn_fields == 1) {
+ *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+ ((e1b >> 8) & 0xffff));
+ leftover_bytes = ((e1b & 0xff) << 8) |
+ TCPOPT_NOP;
+ leftover_size = 1;
+ } else if (opts->num_accecn_fields == 0) {
+ leftover_bytes = (TCPOPT_ACCECN1 << 8) | len;
+ leftover_size = 2;
+ } else if (opts->num_accecn_fields == 3) {
+ *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
+ ((e1b >> 8) & 0xffff));
+ *ptr++ = htonl(((e1b & 0xff) << 24) |
+ (ceb & 0xffffff));
+ *ptr++ = htonl(((e0b & 0xffffff) << 8) |
+ TCPOPT_NOP);
+ }
+ if (tp)
+ tp->accecn_minlen = 0;
+ }
+
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
+ *ptr++ = htonl((leftover_bytes << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
+ leftover_bytes = NOP_LEFTOVER;
}
if (unlikely(OPTION_WSCALE & options)) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
+ u8 highbyte = TCPOPT_NOP;
+
+ if (unlikely(leftover_size == 1))
+ highbyte = leftover_bytes >> 8;
+ *ptr++ = htonl((highbyte << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
opts->ws);
+ leftover_bytes = NOP_LEFTOVER;
}
if (unlikely(opts->num_sack_blocks)) {
@@ -782,8 +835,7 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
tp->duplicate_sack : tp->selective_acks;
int this_sack;
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
+ *ptr++ = htonl((leftover_bytes << 16) |
(TCPOPT_SACK << 8) |
(TCPOLEN_SACK_BASE + (opts->num_sack_blocks *
TCPOLEN_SACK_PERBLOCK)));
@@ -795,6 +847,10 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
}
tp->rx_opt.dsack = 0;
+ } else if (unlikely(leftover_bytes != NOP_LEFTOVER)) {
+ *ptr++ = htonl((leftover_bytes << 16) |
+ (TCPOPT_NOP << 8) |
+ TCPOPT_NOP);
}
if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
@@ -875,6 +931,60 @@ static void mptcp_set_option_cond(const struct request_sock *req,
}
}
+/* Initial values for AccECN option, ordered is based on ECN field bits
+ * similar to received_ecn_bytes. Used for SYN/ACK AccECN option.
+ */
+static u32 synack_ecn_bytes[3] = { 0, 0, 0 };
+
+static u32 tcp_synack_options_combine_saving(struct tcp_out_options *opts)
+{
+ /* How much there's room for combining with the alignment padding? */
+ if ((opts->options & (OPTION_SACK_ADVERTISE | OPTION_TS)) ==
+ OPTION_SACK_ADVERTISE)
+ return 2;
+ else if (opts->options & OPTION_WSCALE)
+ return 1;
+ return 0;
+}
+
+/* Calculates how long AccECN option will fit to @remaining option space.
+ *
+ * AccECN option can sometimes replace NOPs used for alignment of other
+ * TCP options (up to @max_combine_saving available).
+ *
+ * Only solutions with at least @required AccECN fields are accepted.
+ *
+ * Returns: The size of the AccECN option excluding space repurposed from
+ * the alignment of the other options.
+ */
+static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
+ int remaining, int max_combine_saving)
+{
+ int size = TCP_ACCECN_MAXSIZE;
+
+ opts->num_accecn_fields = TCP_ACCECN_NUMFIELDS;
+
+ while (opts->num_accecn_fields >= required) {
+ int leftover_size = size & 0x3;
+ /* Pad to dword if cannot combine */
+ if (leftover_size > max_combine_saving)
+ leftover_size = -((4 - leftover_size) & 0x3);
+
+ if (remaining >= size - leftover_size) {
+ size -= leftover_size;
+ break;
+ }
+
+ opts->num_accecn_fields--;
+ size -= TCPOLEN_ACCECN_PERFIELD;
+ }
+ if (opts->num_accecn_fields < required)
+ return 0;
+
+ opts->options |= OPTION_ACCECN;
+ return size;
+}
+
/* Compute TCP options for SYN packets. This is not the final
* network wire format yet.
*/
@@ -957,6 +1067,17 @@ 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) &&
+ sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
+ remaining >= TCPOLEN_ACCECN_BASE)) {
+ u32 saving = tcp_synack_options_combine_saving(opts);
+
+ opts->ecn_bytes = synack_ecn_bytes;
+ remaining -= tcp_options_fit_accecn(opts, 0, remaining, saving);
+ }
+
bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
return MAX_TCP_OPTION_SPACE - remaining;
@@ -974,6 +1095,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
+ struct tcp_request_sock *treq = tcp_rsk(req);
if (tcp_key_is_md5(key)) {
opts->options |= OPTION_MD5;
@@ -1036,6 +1158,14 @@ 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) {
+ u32 saving = tcp_synack_options_combine_saving(opts);
+
+ opts->ecn_bytes = synack_ecn_bytes;
+ remaining -= tcp_options_fit_accecn(opts, 0, remaining, saving);
+ }
+
bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
synack_type, opts, &remaining);
@@ -1106,6 +1236,17 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
opts->num_sack_blocks = 0;
}
+ if (tcp_ecn_mode_accecn(tp) &&
+ sock_net(sk)->ipv4.sysctl_tcp_ecn_option) {
+ int saving = opts->num_sack_blocks > 0 ? 2 : 0;
+ int remaining = MAX_TCP_OPTION_SPACE - size;
+
+ opts->ecn_bytes = tp->received_ecn_bytes;
+ size += tcp_options_fit_accecn(opts, tp->accecn_minlen,
+ remaining,
+ saving);
+ }
+
if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
2025-05-14 13:56 ` [PATCH v7 net-next 09/15] tcp: accecn: AccECN option chia-yu.chang
@ 2025-05-20 9:31 ` Paolo Abeni
2025-05-20 10:32 ` Eric Dumazet
0 siblings, 1 reply; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 9:31 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
> group for new u8 members, but adds a 4-byte hole in tcp_sock_write_rx
> group after the new u32 delivered_ecn_bytes[3] member. Therefore, the
> group size of tcp_sock_write_rx is increased from 96 to 112.
Note that I'm still concerned by the relevant increase of the cacheline
groups size. My fear is that this change could defeat some/most of the
benefist from the cacheline reorg for all tcp users.
Some additional feedback from Eric and/or Neal more than welcome!
A possible alternative could be placing all the accounting fields
outside of all the fastpath cache groups, i.e. after
__cacheline_group_end(tcp_sock_write_rx)
> @@ -710,6 +713,8 @@ static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
> return ptr;
> }
>
> +#define NOP_LEFTOVER ((TCPOPT_NOP << 8) | TCPOPT_NOP)
> +
> /* Write previously computed TCP options to the packet.
> *
> * Beware: Something in the Internet is very sensitive to the ordering of
> @@ -728,8 +733,10 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
> struct tcp_out_options *opts,
> struct tcp_key *key)
> {
> + u16 leftover_bytes = NOP_LEFTOVER; /* replace next NOPs if avail */
> __be32 *ptr = (__be32 *)(th + 1);
> u16 options = opts->options; /* mungable copy */
> + int leftover_size = 2;
>
> if (tcp_key_is_md5(key)) {
> *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
> @@ -763,18 +770,64 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
> *ptr++ = htonl(opts->tsecr);
> }
>
> + if (OPTION_ACCECN & options) {
> + const u8 ect0_idx = INET_ECN_ECT_0 - 1;
> + const u8 ect1_idx = INET_ECN_ECT_1 - 1;
> + const u8 ce_idx = INET_ECN_CE - 1;
> + u32 e0b;
> + u32 e1b;
> + u32 ceb;
> + u8 len;
> +
> + e0b = opts->ecn_bytes[ect0_idx] + TCP_ACCECN_E0B_INIT_OFFSET;
> + e1b = opts->ecn_bytes[ect1_idx] + TCP_ACCECN_E1B_INIT_OFFSET;
> + ceb = opts->ecn_bytes[ce_idx] + TCP_ACCECN_CEB_INIT_OFFSET;
> + len = TCPOLEN_ACCECN_BASE +
> + opts->num_accecn_fields * TCPOLEN_ACCECN_PERFIELD;
> +
> + if (opts->num_accecn_fields == 2) {
> + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
> + ((e1b >> 8) & 0xffff));
> + *ptr++ = htonl(((e1b & 0xff) << 24) |
> + (ceb & 0xffffff));
> + } else if (opts->num_accecn_fields == 1) {
> + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
> + ((e1b >> 8) & 0xffff));
> + leftover_bytes = ((e1b & 0xff) << 8) |
> + TCPOPT_NOP;
> + leftover_size = 1;
> + } else if (opts->num_accecn_fields == 0) {
> + leftover_bytes = (TCPOPT_ACCECN1 << 8) | len;
> + leftover_size = 2;
> + } else if (opts->num_accecn_fields == 3) {
> + *ptr++ = htonl((TCPOPT_ACCECN1 << 24) | (len << 16) |
> + ((e1b >> 8) & 0xffff));
> + *ptr++ = htonl(((e1b & 0xff) << 24) |
> + (ceb & 0xffffff));
> + *ptr++ = htonl(((e0b & 0xffffff) << 8) |
> + TCPOPT_NOP);
> + }
> + if (tp)
> + tp->accecn_minlen = 0;
> + }
> +
> if (unlikely(OPTION_SACK_ADVERTISE & options)) {
> - *ptr++ = htonl((TCPOPT_NOP << 24) |
> - (TCPOPT_NOP << 16) |
> + *ptr++ = htonl((leftover_bytes << 16) |
> (TCPOPT_SACK_PERM << 8) |
> TCPOLEN_SACK_PERM);
> + leftover_bytes = NOP_LEFTOVER;
AFAICS here leftover_size could be == 1. why is not reset to 2?
More importantly this looks quite fragile and error prone. *Possibly*
have a tcp_accecn_write_option() helper that would rewrite the existing
option as needed could be simpler and less impacting for the existing code?
/P
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
2025-05-20 9:31 ` Paolo Abeni
@ 2025-05-20 10:32 ` Eric Dumazet
2025-05-20 13:37 ` Paolo Abeni
0 siblings, 1 reply; 26+ messages in thread
From: Eric Dumazet @ 2025-05-20 10:32 UTC (permalink / raw)
To: Paolo Abeni
Cc: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On Tue, May 20, 2025 at 2:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> > This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
> > group for new u8 members, but adds a 4-byte hole in tcp_sock_write_rx
> > group after the new u32 delivered_ecn_bytes[3] member. Therefore, the
> > group size of tcp_sock_write_rx is increased from 96 to 112.
>
> Note that I'm still concerned by the relevant increase of the cacheline
> groups size. My fear is that this change could defeat some/most of the
> benefist from the cacheline reorg for all tcp users.
>
> Some additional feedback from Eric and/or Neal more than welcome!
I have been trapped lately with production issues, sorry for the delay.
I am still working on an idpf bug, hopefully done today.
Then, I am OOO tomorrow, and can have a look at the whole series on Thursday.
Thanks.
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
2025-05-20 10:32 ` Eric Dumazet
@ 2025-05-20 13:37 ` Paolo Abeni
2025-05-28 7:26 ` Chia-Yu Chang (Nokia)
0 siblings, 1 reply; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 13:37 UTC (permalink / raw)
To: Eric Dumazet, chia-yu.chang
Cc: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
jhs, kuba, stephen, xiyou.wangcong, jiri, davem, andrew+netdev,
donald.hunter, ast, liuhangbin, shuah, linux-kselftest, ij,
ncardwell, koen.de_schepper, g.white, ingemar.s.johansson,
mirja.kuehlewind, cheshire, rs.ietf, Jason_Livingood, vidhi_goel
On 5/20/25 12:32 PM, Eric Dumazet wrote:
> On Tue, May 20, 2025 at 2:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
>>
>> On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
>>> This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
>>> group for new u8 members, but adds a 4-byte hole in tcp_sock_write_rx
>>> group after the new u32 delivered_ecn_bytes[3] member. Therefore, the
>>> group size of tcp_sock_write_rx is increased from 96 to 112.
>>
>> Note that I'm still concerned by the relevant increase of the cacheline
>> groups size. My fear is that this change could defeat some/most of the
>> benefist from the cacheline reorg for all tcp users.
>>
>> Some additional feedback from Eric and/or Neal more than welcome!
>
> I have been trapped lately with production issues, sorry for the delay.
>
> I am still working on an idpf bug, hopefully done today.
>
> Then, I am OOO tomorrow, and can have a look at the whole series on Thursday.
Thanks Eric!
@Chia-Yu: please consider the above timeline before posting a new
revision. i.e. it would be likely wise to wait for the additional review.
/P
^ permalink raw reply [flat|nested] 26+ messages in thread
* RE: [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
2025-05-20 13:37 ` Paolo Abeni
@ 2025-05-28 7:26 ` Chia-Yu Chang (Nokia)
0 siblings, 0 replies; 26+ messages in thread
From: Chia-Yu Chang (Nokia) @ 2025-05-28 7:26 UTC (permalink / raw)
To: Paolo Abeni, Eric Dumazet
Cc: linux-doc@vger.kernel.org, corbet@lwn.net, horms@kernel.org,
dsahern@kernel.org, kuniyu@amazon.com, bpf@vger.kernel.org,
netdev@vger.kernel.org, dave.taht@gmail.com, jhs@mojatatu.com,
kuba@kernel.org, stephen@networkplumber.org,
xiyou.wangcong@gmail.com, jiri@resnulli.us, davem@davemloft.net,
andrew+netdev@lunn.ch, donald.hunter@gmail.com, ast@fiberby.net,
liuhangbin@gmail.com, shuah@kernel.org,
linux-kselftest@vger.kernel.org, ij@kernel.org,
ncardwell@google.com, Koen De Schepper (Nokia), g.white,
ingemar.s.johansson@ericsson.com, mirja.kuehlewind@ericsson.com,
cheshire@apple.com, rs.ietf@gmx.at, Jason_Livingood@comcast.com,
vidhi_goel
> -----Original Message-----
> From: Paolo Abeni <pabeni@redhat.com>
> Sent: Tuesday, May 20, 2025 3:38 PM
> To: Eric Dumazet <edumazet@google.com>; Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com>
> Cc: linux-doc@vger.kernel.org; corbet@lwn.net; horms@kernel.org; dsahern@kernel.org; kuniyu@amazon.com; bpf@vger.kernel.org; netdev@vger.kernel.org; dave.taht@gmail.com; jhs@mojatatu.com; kuba@kernel.org; stephen@networkplumber.org; xiyou.wangcong@gmail.com; jiri@resnulli.us; davem@davemloft.net; andrew+netdev@lunn.ch; donald.hunter@gmail.com; ast@fiberby.net; liuhangbin@gmail.com; shuah@kernel.org; linux-kselftest@vger.kernel.org; ij@kernel.org; ncardwell@google.com; Koen De Schepper (Nokia) <koen.de_schepper@nokia-bell-labs.com>; g.white <g.white@cablelabs.com>; ingemar.s.johansson@ericsson.com; mirja.kuehlewind@ericsson.com; cheshire@apple.com; rs.ietf@gmx.at; Jason_Livingood@comcast.com; vidhi_goel <vidhi_goel@apple.com>
> Subject: Re: [PATCH v7 net-next 09/15] tcp: accecn: AccECN option
>
>
> CAUTION: This is an external email. Please be very careful when clicking links or opening attachments. See the URL nok.it/ext for additional information.
>
>
>
> On 5/20/25 12:32 PM, Eric Dumazet wrote:
> > On Tue, May 20, 2025 at 2:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
> >>
> >> On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> >>> This patch uses the existing 1-byte holes in the tcp_sock_write_txrx
> >>> group for new u8 members, but adds a 4-byte hole in
> >>> tcp_sock_write_rx group after the new u32 delivered_ecn_bytes[3]
> >>> member. Therefore, the group size of tcp_sock_write_rx is increased from 96 to 112.
> >>
> >> Note that I'm still concerned by the relevant increase of the
> >> cacheline groups size. My fear is that this change could defeat
> >> some/most of the benefist from the cacheline reorg for all tcp users.
> >>
> >> Some additional feedback from Eric and/or Neal more than welcome!
> >
> > I have been trapped lately with production issues, sorry for the delay.
> >
> > I am still working on an idpf bug, hopefully done today.
> >
> > Then, I am OOO tomorrow, and can have a look at the whole series on Thursday.
>
> Thanks Eric!
>
> @Chia-Yu: please consider the above timeline before posting a new revision. i.e. it would be likely wise to wait for the additional review.
>
> /P
Hi Eric and Paolo,
As you know that the merge window for v6.16 is begun and net-next is closed for new features till 9th of June.
May I ask did you manage yo review the patches we sent two weeks ago?
Thanks.
Best Regards,
Chia-Yu
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 10/15] tcp: accecn: AccECN option send control
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (8 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 09/15] tcp: accecn: AccECN option chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 9:49 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 11/15] tcp: accecn: AccECN option failure handling chia-yu.chang
` (4 subsequent siblings)
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
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; /* 2552 8 */
struct list_head tsorted_sent_queue; /* 2560 16 */
[...]
__cacheline_group_end__tcp_sock_write_tx[0]; /* 2585 0 */
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2585 0 */
u8 nonagle:4; /* 2585: 0 1 */
u8 rate_app_limited:1; /* 2585: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2586: 0 1 */
u8 unused2:4; /* 2586: 4 1 */
u8 accecn_minlen:2; /* 2587: 0 1 */
u8 est_ecnfield:2; /* 2587: 2 1 */
u8 unused3:4; /* 2587: 4 1 */
[...]
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2692 0 */
[...]
/* size: 3264, cachelines: 51, members: 174 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
u64 tcp_wstamp_ns; /* 2552 8 */
u64 accecn_opt_tstamp; /* 2560 8 */
struct list_head tsorted_sent_queue; /* 2568 16 */
[...]
__cacheline_group_end__tcp_sock_write_tx[0]; /* 2593 0 */
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2593 0 */
u8 nonagle:4; /* 2593: 0 1 */
u8 rate_app_limited:1; /* 2593: 4 1 */
/* XXX 3 bits hole, try to pack */
/* Force alignment to the next boundary: */
u8 :0;
u8 received_ce_pending:4;/* 2594: 0 1 */
u8 unused2:4; /* 2594: 4 1 */
u8 accecn_minlen:2; /* 2595: 0 1 */
u8 est_ecnfield:2; /* 2595: 2 1 */
u8 accecn_opt_demand:2; /* 2595: 4 1 */
u8 prev_ecnfield:2; /* 2595: 6 1 */
[...]
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2700 0 */
[...]
/* size: 3264, cachelines: 51, members: 176 */
}
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 | 3 ++
include/linux/tcp.h | 4 ++-
include/net/netns/ipv4.h | 1 +
include/net/tcp.h | 4 +++
net/ipv4/sysctl_net_ipv4.c | 9 +++++
net/ipv4/tcp.c | 5 ++-
net/ipv4/tcp_input.c | 36 ++++++++++++++++++-
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_minisocks.c | 2 ++
net/ipv4/tcp_output.c | 31 ++++++++++++++--
10 files changed, 90 insertions(+), 6 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index c74f939f32cc..af76d4f9b33a 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -110,6 +110,9 @@ u8:2 syn_ect_rcv read_mostly read_w
u8:1 wait_third_ack 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)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index afb1a5ac65bf..0740efaaef28 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -276,6 +276,7 @@ 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
@@ -297,7 +298,8 @@ 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 */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 4569a9ef4fb8..ff8b5b56ad00 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -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;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 50ad6e33d52d..3419618a7891 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -91,6 +91,9 @@ 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_ECN_OPTION_BEACON 3
+
/* urg_data states */
#define TCP_URG_VALID 0x0100
#define TCP_URG_NOTYET 0x0200
@@ -1088,6 +1091,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
__tcp_accecn_init_bytes_counters(tp->received_ecn_bytes);
__tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes);
tp->accecn_minlen = 0;
+ tp->accecn_opt_demand = 0;
tp->est_ecnfield = 0;
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1d7fd86ca7b9..169a393374b3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -740,6 +740,15 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
+ {
+ .procname = "tcp_ecn_option_beacon",
+ .data = &init_net.ipv4.sysctl_tcp_ecn_option_beacon,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_THREE,
+ },
{
.procname = "tcp_ecn_fallback",
.data = &init_net.ipv4.sysctl_tcp_ecn_fallback,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a71260838ccf..20a2e30e15f3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3400,6 +3400,8 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->wait_third_ack = 0;
tp->accecn_fail_mode = 0;
tcp_accecn_init_counters(tp);
+ tp->prev_ecnfield = 0;
+ tp->accecn_opt_tstamp = 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));
@@ -5119,11 +5121,12 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, accecn_opt_tstamp);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 97);
/* TXRX read-write hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3de8cc56c5cd..10c37a41b9a5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -487,6 +487,7 @@ 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 (INET_ECN_is_ce(ip_dsfield) &&
tcp_accecn_validate_syn_feedback(sk, ace,
tp->syn_ect_snt)) {
@@ -507,6 +508,7 @@ static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th,
} else {
tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield &
INET_ECN_MASK;
+ tp->prev_ecnfield = tp->syn_ect_rcv;
tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
}
}
@@ -6302,6 +6304,7 @@ 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);
+ bool ecn_edge;
if (!INET_ECN_is_not_ect(ecnfield)) {
u32 pcount = is_ce * max_t(u16, 1, skb_shinfo(skb)->gso_segs);
@@ -6315,9 +6318,36 @@ void tcp_ecn_received_counters(struct sock *sk, const struct sk_buff *skb,
if (payload_len > 0) {
u8 minlen = tcp_ecnfield_to_accecn_optfield(ecnfield);
+ u32 oldbytes = tp->received_ecn_bytes[ecnfield - 1];
+
tp->received_ecn_bytes[ecnfield - 1] += payload_len;
tp->accecn_minlen = max_t(u8, tp->accecn_minlen,
minlen);
+
+ /* Demand AccECN option at least every 2^22 bytes to
+ * avoid overflowing the ECN byte counters.
+ */
+ if ((tp->received_ecn_bytes[ecnfield - 1] ^ oldbytes) &
+ ~((1 << 22) - 1)) {
+ u8 opt_demand = max_t(u8, 1,
+ tp->accecn_opt_demand);
+
+ tp->accecn_opt_demand = opt_demand;
+ }
+ }
+ }
+
+ ecn_edge = tp->prev_ecnfield != ecnfield;
+ if (ecn_edge || is_ce) {
+ tp->prev_ecnfield = ecnfield;
+ /* Demand Accurate ECN change-triggered ACKs. Two ACK are
+ * demanded to indicate unambiguously the ecnfield value
+ * in the latter ACK.
+ */
+ if (tcp_ecn_mode_accecn(tp)) {
+ if (ecn_edge)
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+ tp->accecn_opt_demand = 2;
}
}
}
@@ -6450,8 +6480,12 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
* RFC 5961 4.2 : Send a challenge ack
*/
if (th->syn) {
- if (tcp_ecn_mode_accecn(tp))
+ 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 (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cc3049bb9d02..9e8eb0d639de 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3451,6 +3451,7 @@ static int __net_init tcp_sk_init(struct net *net)
{
net->ipv4.sysctl_tcp_ecn = TCP_ECN_IN_ECN_OUT_NOECN;
net->ipv4.sysctl_tcp_ecn_option = TCP_ECN_OPTION_FULL;
+ net->ipv4.sysctl_tcp_ecn_option_beacon = TCP_ECN_OPTION_BEACON;
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3f8225bae49f..e0f2bd2cee9e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -501,6 +501,8 @@ 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->prev_ecnfield = treq->syn_ect_rcv;
+ tp->accecn_opt_demand = 1;
tcp_ecn_received_counters(sk, skb, skb->len - th->doff * 4);
} else {
tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0a4d9791b4a2..ea37a30ff71c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -807,8 +807,12 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
*ptr++ = htonl(((e0b & 0xffffff) << 8) |
TCPOPT_NOP);
}
- if (tp)
+ if (tp) {
tp->accecn_minlen = 0;
+ tp->accecn_opt_tstamp = tp->tcp_mstamp;
+ if (tp->accecn_opt_demand)
+ tp->accecn_opt_demand--;
+ }
}
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
@@ -985,6 +989,18 @@ static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
return size;
}
+static bool tcp_accecn_option_beacon_check(const struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!sock_net(sk)->ipv4.sysctl_tcp_ecn_option_beacon)
+ return false;
+
+ return tcp_stamp_us_delta(tp->tcp_mstamp, tp->accecn_opt_tstamp) *
+ sock_net(sk)->ipv4.sysctl_tcp_ecn_option_beacon >=
+ (tp->srtt_us >> 3);
+}
+
/* Compute TCP options for SYN packets. This is not the final
* network wire format yet.
*/
@@ -1237,12 +1253,16 @@ 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) {
+ sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
+ (sock_net(sk)->ipv4.sysctl_tcp_ecn_option >= TCP_ECN_OPTION_FULL ||
+ tp->accecn_opt_demand ||
+ tcp_accecn_option_beacon_check(sk))) {
int saving = opts->num_sack_blocks > 0 ? 2 : 0;
int remaining = MAX_TCP_OPTION_SPACE - size;
opts->ecn_bytes = tp->received_ecn_bytes;
- size += tcp_options_fit_accecn(opts, tp->accecn_minlen,
+ size += tcp_options_fit_accecn(opts,
+ tp->accecn_minlen,
remaining,
saving);
}
@@ -2960,6 +2980,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
sent_pkts = 0;
tcp_mstamp_refresh(tp);
+
+ /* AccECN option beacon depends on mstamp, it may change mss */
+ if (tcp_ecn_mode_accecn(tp) && tcp_accecn_option_beacon_check(sk))
+ mss_now = tcp_current_mss(sk);
+
if (!push_one) {
/* Do MTU probing. */
result = tcp_mtu_probe(sk);
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 10/15] tcp: accecn: AccECN option send control
2025-05-14 13:56 ` [PATCH v7 net-next 10/15] tcp: accecn: AccECN option send control chia-yu.chang
@ 2025-05-20 9:49 ` Paolo Abeni
0 siblings, 0 replies; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 9:49 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> @@ -6450,8 +6480,12 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
> * RFC 5961 4.2 : Send a challenge ack
> */
> if (th->syn) {
> - if (tcp_ecn_mode_accecn(tp))
> + 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;
There is similar code to update accecn_opt_demand above, possibly worth
an helper.
> @@ -1237,12 +1253,16 @@ 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) {
> + sock_net(sk)->ipv4.sysctl_tcp_ecn_option &&
> + (sock_net(sk)->ipv4.sysctl_tcp_ecn_option >= TCP_ECN_OPTION_FULL ||
> + tp->accecn_opt_demand ||
> + tcp_accecn_option_beacon_check(sk))) {
> int saving = opts->num_sack_blocks > 0 ? 2 : 0;
> int remaining = MAX_TCP_OPTION_SPACE - size;
>
> opts->ecn_bytes = tp->received_ecn_bytes;
> - size += tcp_options_fit_accecn(opts, tp->accecn_minlen,
> + size += tcp_options_fit_accecn(opts,
> + tp->accecn_minlen,
> remaining,
> saving);
Please avoid unneeded white-space only changes.
/P
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 11/15] tcp: accecn: AccECN option failure handling
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (9 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 10/15] tcp: accecn: AccECN option send control chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 10:00 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 12/15] tcp: accecn: AccECN option ceb/cep heuristic chia-yu.chang
` (3 subsequent siblings)
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Chia-Yu Chang <chia-yu.chang@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 <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@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
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 11/15] tcp: accecn: AccECN option failure handling
2025-05-14 13:56 ` [PATCH v7 net-next 11/15] tcp: accecn: AccECN option failure handling chia-yu.chang
@ 2025-05-20 10:00 ` Paolo Abeni
0 siblings, 0 replies; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 10:00 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> @@ -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);
Similar code above, possibly an helper could be used.
> + }
> + 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;
> + }
> }
Too many indentation levels, please move into a separate helper
/P
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 12/15] tcp: accecn: AccECN option ceb/cep heuristic
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (10 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 11/15] tcp: accecn: AccECN option failure handling chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 13/15] tcp: accecn: AccECN ACE field multi-wrap heuristic chia-yu.chang
` (2 subsequent siblings)
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
The heuristic algorithm from draft-11 Appendix A.2.2 to
mitigate against false ACE field overflows.
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 | 18 ++++++++++++++++--
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5e4593e39de4..201326b10396 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -247,6 +247,7 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
#define TCP_ACCECN_MAXSIZE (TCPOLEN_ACCECN_BASE + \
TCPOLEN_ACCECN_PERFIELD * \
TCP_ACCECN_NUMFIELDS)
+#define TCP_ACCECN_SAFETY_SHIFT 1 /* SAFETY_FACTOR in accecn draft */
/* tp->accecn_fail_mode */
#define TCP_ACCECN_ACE_FAIL_SEND BIT(0)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c93e4bffb23e..f206c1a93a56 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -709,16 +709,19 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
u32 delivered_pkts, u32 delivered_bytes,
int flag)
{
+ u32 old_ceb = tcp_sk(sk)->delivered_ecn_bytes[INET_ECN_CE - 1];
const struct tcphdr *th = tcp_hdr(skb);
struct tcp_sock *tp = tcp_sk(sk);
- u32 delta, safe_delta;
+ u32 delta, safe_delta, d_ceb;
+ bool opt_deltas_valid;
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;
- tcp_accecn_process_option(tp, skb, delivered_bytes, flag);
+ opt_deltas_valid = tcp_accecn_process_option(tp, skb,
+ delivered_bytes, flag);
if (!(flag & FLAG_SLOWPATH)) {
/* AccECN counter might overflow on large ACKs */
@@ -741,6 +744,17 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
safe_delta = delivered_pkts -
((delivered_pkts - delta) & TCP_ACCECN_CEP_ACE_MASK);
+ if (opt_deltas_valid) {
+ d_ceb = tp->delivered_ecn_bytes[INET_ECN_CE - 1] - old_ceb;
+ if (!d_ceb)
+ return delta;
+ if (d_ceb > delta * tp->mss_cache)
+ return safe_delta;
+ if (d_ceb <
+ safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT)
+ return delta;
+ }
+
return safe_delta;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 13/15] tcp: accecn: AccECN ACE field multi-wrap heuristic
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (11 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 12/15] tcp: accecn: AccECN option ceb/cep heuristic chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK chia-yu.chang
2025-05-14 13:56 ` [PATCH v7 net-next 15/15] tcp: try to avoid safer when ACKs are thinned chia-yu.chang
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
Armed with ceb delta from option, delivered bytes, and
delivered packets it is possible to estimate how many times
ACE field wrapped.
This calculation is necessary only if more than one wrap
is possible. Without SACK, delivered bytes and packets are
not always trustworthy in which case TCP falls back to the
simpler no-or-all wraps ceb algorithm.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
net/ipv4/tcp_input.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f206c1a93a56..deced87f31f8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -748,6 +748,24 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb,
d_ceb = tp->delivered_ecn_bytes[INET_ECN_CE - 1] - old_ceb;
if (!d_ceb)
return delta;
+
+ if ((delivered_pkts >= (TCP_ACCECN_CEP_ACE_MASK + 1) * 2) &&
+ (tcp_is_sack(tp) ||
+ ((1 << inet_csk(sk)->icsk_ca_state) &
+ (TCPF_CA_Open | TCPF_CA_CWR)))) {
+ u32 est_d_cep;
+
+ if (delivered_bytes <= d_ceb)
+ return safe_delta;
+
+ est_d_cep = DIV_ROUND_UP_ULL((u64)d_ceb *
+ delivered_pkts,
+ delivered_bytes);
+ return min(safe_delta,
+ delta +
+ (est_d_cep & ~TCP_ACCECN_CEP_ACE_MASK));
+ }
+
if (d_ceb > delta * tp->mss_cache)
return safe_delta;
if (d_ceb <
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (12 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 13/15] tcp: accecn: AccECN ACE field multi-wrap heuristic chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
2025-05-20 10:03 ` Paolo Abeni
2025-05-14 13:56 ` [PATCH v7 net-next 15/15] tcp: try to avoid safer when ACKs are thinned chia-yu.chang
14 siblings, 1 reply; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
From: Ilpo Järvinen <ij@kernel.org>
As SACK blocks tend to eat all option space when there are
many holes, it is useful to compromise on sending many SACK
blocks in every ACK and try to fit AccECN option there
by reduction the number of SACK blocks. But never go below
two SACK blocks because of AccECN option.
As AccECN option is often not put to every ACK, the space
hijack is usually only temporary.
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
net/ipv4/tcp_output.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b630923c4cef..d9d3cc8dbb5b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -982,8 +982,21 @@ static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
opts->num_accecn_fields--;
size -= TCPOLEN_ACCECN_PERFIELD;
}
- if (opts->num_accecn_fields < required)
+ if (opts->num_accecn_fields < required) {
+ if (opts->num_sack_blocks > 2) {
+ /* Try to fit the option by removing one SACK block */
+ opts->num_sack_blocks--;
+ size = tcp_options_fit_accecn(opts, required,
+ remaining +
+ TCPOLEN_SACK_PERBLOCK,
+ max_combine_saving);
+ if (opts->options & OPTION_ACCECN)
+ return size - TCPOLEN_SACK_PERBLOCK;
+
+ opts->num_sack_blocks++;
+ }
return 0;
+ }
opts->options |= OPTION_ACCECN;
return size;
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK
2025-05-14 13:56 ` [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK chia-yu.chang
@ 2025-05-20 10:03 ` Paolo Abeni
2025-05-23 17:50 ` Chia-Yu Chang (Nokia)
0 siblings, 1 reply; 26+ messages in thread
From: Paolo Abeni @ 2025-05-20 10:03 UTC (permalink / raw)
To: chia-yu.chang, linux-doc, corbet, horms, dsahern, kuniyu, bpf,
netdev, dave.taht, jhs, kuba, stephen, xiyou.wangcong, jiri,
davem, edumazet, andrew+netdev, donald.hunter, ast, liuhangbin,
shuah, linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> From: Ilpo Järvinen <ij@kernel.org>
>
> As SACK blocks tend to eat all option space when there are
> many holes, it is useful to compromise on sending many SACK
> blocks in every ACK and try to fit AccECN option there
> by reduction the number of SACK blocks. But never go below
> two SACK blocks because of AccECN option.
>
> As AccECN option is often not put to every ACK, the space
> hijack is usually only temporary.
>
> Signed-off-by: Ilpo Järvinen <ij@kernel.org>
> Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
> ---
> net/ipv4/tcp_output.c | 15 ++++++++++++++-
> 1 file changed, 14 insertions(+), 1 deletion(-)
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index b630923c4cef..d9d3cc8dbb5b 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -982,8 +982,21 @@ static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
> opts->num_accecn_fields--;
> size -= TCPOLEN_ACCECN_PERFIELD;
> }
> - if (opts->num_accecn_fields < required)
> + if (opts->num_accecn_fields < required) {
> + if (opts->num_sack_blocks > 2) {
> + /* Try to fit the option by removing one SACK block */
> + opts->num_sack_blocks--;
> + size = tcp_options_fit_accecn(opts, required,
> + remaining +
> + TCPOLEN_SACK_PERBLOCK,
> + max_combine_saving);
How deep is the recursion level, worst case? In any case please try to
avoid recursion entirely. Possibly a 'goto' statement would help.
/P
^ permalink raw reply [flat|nested] 26+ messages in thread* RE: [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK
2025-05-20 10:03 ` Paolo Abeni
@ 2025-05-23 17:50 ` Chia-Yu Chang (Nokia)
0 siblings, 0 replies; 26+ messages in thread
From: Chia-Yu Chang (Nokia) @ 2025-05-23 17:50 UTC (permalink / raw)
To: Paolo Abeni, linux-doc@vger.kernel.org, corbet@lwn.net,
horms@kernel.org, dsahern@kernel.org, kuniyu@amazon.com,
bpf@vger.kernel.org, netdev@vger.kernel.org, dave.taht@gmail.com,
jhs@mojatatu.com, kuba@kernel.org, stephen@networkplumber.org,
xiyou.wangcong@gmail.com, jiri@resnulli.us, davem@davemloft.net,
edumazet@google.com, andrew+netdev@lunn.ch,
donald.hunter@gmail.com, ast@fiberby.net, liuhangbin@gmail.com,
shuah@kernel.org, linux-kselftest@vger.kernel.org, ij@kernel.org,
ncardwell@google.com, Koen De Schepper (Nokia), g.white,
ingemar.s.johansson@ericsson.com, mirja.kuehlewind@ericsson.com,
cheshire@apple.com, rs.ietf@gmx.at, Jason_Livingood@comcast.com,
vidhi_goel
-----Original Message-----
> From: Paolo Abeni <pabeni@redhat.com>
> Sent: Tuesday, May 20, 2025 12:04 PM
> To: Chia-Yu Chang (Nokia) <chia-yu.chang@nokia-bell-labs.com>; linux-doc@vger.kernel.org; corbet@lwn.net; horms@kernel.org; dsahern@kernel.org; kuniyu@amazon.com; bpf@vger.kernel.org; netdev@vger.kernel.org; dave.taht@gmail.com; jhs@mojatatu.com; kuba@kernel.org; stephen@networkplumber.org; xiyou.wangcong@gmail.com; jiri@resnulli.us; davem@davemloft.net; edumazet@google.com; andrew+netdev@lunn.ch; donald.hunter@gmail.com; ast@fiberby.net; liuhangbin@gmail.com; shuah@kernel.org; linux-kselftest@vger.kernel.org; ij@kernel.org; ncardwell@google.com; Koen De Schepper (Nokia) <koen.de_schepper@nokia-bell-labs.com>; g.white <g.white@cablelabs.com>; ingemar.s.johansson@ericsson.com; mirja.kuehlewind@ericsson.com; cheshire@apple.com; rs.ietf@gmx.at; Jason_Livingood@comcast.com; vidhi_goel <vidhi_goel@apple.com>
> Subject: Re: [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK
>
>
> CAUTION: This is an external email. Please be very careful when clicking links or opening attachments. See the URL nok.it/ext for additional information.
>
>
>
> On 5/14/25 3:56 PM, chia-yu.chang@nokia-bell-labs.com wrote:
> > From: Ilpo Järvinen <ij@kernel.org>
> >
> > As SACK blocks tend to eat all option space when there are many holes,
> > it is useful to compromise on sending many SACK blocks in every ACK
> > and try to fit AccECN option there by reduction the number of SACK
> > blocks. But never go below two SACK blocks because of AccECN option.
> >
> > As AccECN option is often not put to every ACK, the space hijack is
> > usually only temporary.
> >
> > Signed-off-by: Ilpo Järvinen <ij@kernel.org>
> > Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
> > ---
> > net/ipv4/tcp_output.c | 15 ++++++++++++++-
> > 1 file changed, 14 insertions(+), 1 deletion(-)
> >
> > diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index
> > b630923c4cef..d9d3cc8dbb5b 100644
> > --- a/net/ipv4/tcp_output.c
> > +++ b/net/ipv4/tcp_output.c
> > @@ -982,8 +982,21 @@ static int tcp_options_fit_accecn(struct tcp_out_options *opts, int required,
> > opts->num_accecn_fields--;
> > size -= TCPOLEN_ACCECN_PERFIELD;
> > }
> > - if (opts->num_accecn_fields < required)
> > + if (opts->num_accecn_fields < required) {
> > + if (opts->num_sack_blocks > 2) {
> > + /* Try to fit the option by removing one SACK block */
> > + opts->num_sack_blocks--;
> > + size = tcp_options_fit_accecn(opts, required,
> > + remaining +
> > + TCPOLEN_SACK_PERBLOCK,
> > +
> > + max_combine_saving);
>
> How deep is the recursion level, worst case? In any case please try to avoid recursion entirely. Possibly a 'goto' statement would help.
>
> /P
Hi Paolo,
Thanks for the feedback, in this case up to 2 extra levels will be needed.
And the recursion will be avoided in the next version.
BRs,
Chia-Yu
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 net-next 15/15] tcp: try to avoid safer when ACKs are thinned
2025-05-14 13:56 [PATCH v7 net-next 00/15] AccECN protocol patch series chia-yu.chang
` (13 preceding siblings ...)
2025-05-14 13:56 ` [PATCH v7 net-next 14/15] tcp: accecn: try to fit AccECN option with SACK chia-yu.chang
@ 2025-05-14 13:56 ` chia-yu.chang
14 siblings, 0 replies; 26+ messages in thread
From: chia-yu.chang @ 2025-05-14 13:56 UTC (permalink / raw)
To: linux-doc, corbet, horms, dsahern, kuniyu, bpf, netdev, dave.taht,
pabeni, jhs, kuba, stephen, xiyou.wangcong, jiri, davem, edumazet,
andrew+netdev, donald.hunter, ast, liuhangbin, shuah,
linux-kselftest, ij, ncardwell, koen.de_schepper, g.white,
ingemar.s.johansson, mirja.kuehlewind, cheshire, rs.ietf,
Jason_Livingood, vidhi_goel
Cc: Chia-Yu Chang
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 af76d4f9b33a..2e6ef8290aff 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
u8:1 wait_third_ack read_write
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b5066eef8782..b22914a4f3cb 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -346,6 +346,7 @@ 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 e68b9706eeff..b1ee5b6618f0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3403,6 +3403,7 @@ 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));
@@ -5164,6 +5165,7 @@ 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 deced87f31f8..7535de493d43 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -704,6 +704,10 @@ 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,
@@ -723,6 +727,19 @@ 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)
@@ -771,7 +788,8 @@ 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;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 26+ messages in thread