diff mbox series

[net-next,20/44] tcp: accecn: AccECN needs to know delivered bytes

Message ID 20241015102940.26157-21-chia-yu.chang@nokia-bell-labs.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series DualPI2, Accurate ECN, TCP Prague patch series | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 5 this patch: 5
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers fail 4 maintainers not CCed: edumazet@google.com pabeni@redhat.com dsahern@kernel.org kuba@kernel.org
netdev/build_clang success Errors and warnings before: 3 this patch: 3
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 5 this patch: 5
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 62 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 1 this patch: 1
netdev/source_inline success Was 0 now: 0

Commit Message

Chia-Yu Chang (Nokia) Oct. 15, 2024, 10:29 a.m. UTC 
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 mbox series

Patch

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c6b1324caab4..f70b65034e45 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1159,6 +1159,7 @@  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;
@@ -1520,7 +1521,7 @@  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);
@@ -1580,6 +1581,7 @@  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 &&
@@ -1621,7 +1623,7 @@  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);
 
@@ -1913,6 +1915,7 @@  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)
@@ -3529,6 +3532,8 @@  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))
@@ -3632,6 +3637,10 @@  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))) {
@@ -4085,6 +4094,7 @@  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);