From: Pengcheng Yang <yangpc@xxxxxxxxxx>
[ Upstream commit b253a0680ceadc5d7b4acca7aa2d870326cad8ad ]
If an ACK (s)acks multiple skbs, we favor the information
from the most recently sent skb by choosing the skb with
the highest prior_delivered count. But in the interval
between receiving ACKs, we send multiple skbs with the same
prior_delivered, because the tp->delivered only changes
when we receive an ACK.
We used RACK's solution, copying tcp_rack_sent_after() as
tcp_skb_sent_after() helper to determine "which packet was
sent last?". Later, we will use tcp_skb_sent_after() instead
in RACK.
Fixes: b9f64820fb22 ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: Pengcheng Yang <yangpc@xxxxxxxxxx>
Cc: Paolo Abeni <pabeni@xxxxxxxxxx>
Acked-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Tested-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Link: https://lore.kernel.org/r/1650422081-22153-1-git-send-email-yangpc@xxxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
include/net/tcp.h | 6 ++++++
net/ipv4/tcp_rate.c | 11 ++++++++---
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b9fc978fb2ca..9f459e8f1689 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1042,6 +1042,7 @@ struct rate_sample {
int losses; /* number of packets marked lost upon ACK */
u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
u32 prior_in_flight; /* in flight before this ACK */
+ u32 last_end_seq; /* end_seq of most recently ACKed packet */
bool is_app_limited; /* is sample from packet with bubble in pipe? */
bool is_retrans; /* is sample from retransmission? */
bool is_ack_delayed; /* is this (likely) a delayed ACK? */
@@ -1164,6 +1165,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
bool is_sack_reneg, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);
+static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
+{
+ return t1 > t2 || (t1 == t2 && after(seq1, seq2));
+}
+
/* These functions determine how the current flow behaves in respect of SACK
* handling. SACK is negotiated with the peer, and therefore it can vary
* between different flows.
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index fbab921670cc..9a8e014d9b5b 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb)
*
* If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is
* called multiple times. We favor the information from the most recently
- * sent skb, i.e., the skb with the highest prior_delivered count.
+ * sent skb, i.e., the skb with the most recently sent time and the highest
+ * sequence.
*/
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ u64 tx_tstamp;
if (!scb->tx.delivered_mstamp)
return;
+ tx_tstamp = tcp_skb_timestamp_us(skb);
if (!rs->prior_delivered ||
- after(scb->tx.delivered, rs->prior_delivered)) {
+ tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp,
+ scb->end_seq, rs->last_end_seq)) {
rs->prior_delivered_ce = scb->tx.delivered_ce;
rs->prior_delivered = scb->tx.delivered;
rs->prior_mstamp = scb->tx.delivered_mstamp;
rs->is_app_limited = scb->tx.is_app_limited;
rs->is_retrans = scb->sacked & TCPCB_RETRANS;
+ rs->last_end_seq = scb->end_seq;
/* Record send time of most recently ACKed packet: */
- tp->first_tx_mstamp = tcp_skb_timestamp_us(skb);
+ tp->first_tx_mstamp = tx_tstamp;
/* Find the duration of the "send phase" of this window: */
rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,
scb->tx.first_tx_mstamp);
--
2.35.1
