Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2cba6355 authored by Pengcheng Yang's avatar Pengcheng Yang Committed by Greg Kroah-Hartman
Browse files

tcp: ensure to use the most recently sent skb when filling the rate sample 



[ 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: b9f64820 ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: default avatarPengcheng Yang <yangpc@wangsu.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Tested-by: default avatarNeal Cardwell <ncardwell@google.com>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/1650422081-22153-1-git-send-email-yangpc@wangsu.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
Signed-off-by: default avatarSasha Levin <sashal@kernel.org>
parent 3ea6190b

include/net/tcp.h

+6 −0
Original line number Original line Diff line number Diff line
@@ -1030,6 +1030,7 @@ struct rate_sample { 
	int  losses;		/* number of packets marked lost upon ACK */

	int  losses;		/* number of packets marked lost upon ACK */

	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */

	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */

	u32  prior_in_flight;	/* in flight before this 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_app_limited;	/* is sample from packet with bubble in pipe? */

	bool is_retrans;	/* is sample from retransmission? */

	bool is_retrans;	/* is sample from retransmission? */

	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */

	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */
@@ -1139,6 +1140,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, 
		  bool is_sack_reneg, struct rate_sample *rs);

		  bool is_sack_reneg, struct rate_sample *rs);

void tcp_rate_check_app_limited(struct sock *sk);

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

/* These functions determine how the current flow behaves in respect of SACK

 * handling. SACK is negotiated with the peer, and therefore it can vary

 * handling. SACK is negotiated with the peer, and therefore it can vary

 * between different flows.

 * between different flows.

net/ipv4/tcp_rate.c

+8 −3
Original line number Original line Diff line number Diff line
@@ -73,26 +73,31 @@ 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

 * 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

 * 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,

void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,

			    struct rate_sample *rs)

			    struct rate_sample *rs)

{

{

	struct tcp_sock *tp = tcp_sk(sk);

	struct tcp_sock *tp = tcp_sk(sk);

	struct tcp_skb_cb *scb = TCP_SKB_CB(skb);

	struct tcp_skb_cb *scb = TCP_SKB_CB(skb);

	u64 tx_tstamp;





	if (!scb->tx.delivered_mstamp)

	if (!scb->tx.delivered_mstamp)

		return;

		return;





	tx_tstamp = tcp_skb_timestamp_us(skb);

	if (!rs->prior_delivered ||

	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  = scb->tx.delivered;

		rs->prior_delivered  = scb->tx.delivered;

		rs->prior_mstamp     = scb->tx.delivered_mstamp;

		rs->prior_mstamp     = scb->tx.delivered_mstamp;

		rs->is_app_limited   = scb->tx.is_app_limited;

		rs->is_app_limited   = scb->tx.is_app_limited;

		rs->is_retrans	     = scb->sacked & TCPCB_RETRANS;

		rs->is_retrans	     = scb->sacked & TCPCB_RETRANS;

		rs->last_end_seq     = scb->end_seq;





		/* Record send time of most recently ACKed packet: */

		/* 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: */

		/* Find the duration of the "send phase" of this window: */

		rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,

		rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,

						     scb->tx.first_tx_mstamp);

						     scb->tx.first_tx_mstamp);