tcp: invalidate rate samples during SACK reneging

Mark tcp_sock during a SACK reneging event and invalidate rate samples
while marked. Such rate samples may overestimate bw by including packets
that were SACKed before reneging.

< ack 6001 win 10000 sack 7001:38001
< ack 7001 win 0 sack 8001:38001 // Reneg detected
> seq 7001:8001 // RTO, SACK cleared.
< ack 38001 win 10000

In above example the rate sample taken after the last ack will count
7001-38001 as delivered while the actual delivery rate likely could
be much lower i.e. 7001-8001.

This patch adds a new field tcp_sock.sack_reneg and marks it when we
declare SACK reneging and entering TCP_CA_Loss, and unmarks it after
the last rate sample was taken before moving back to TCP_CA_Open. This
patch also invalidates rate samples taken while tcp_sock.is_sack_reneg
is set.

Fixes: b9f6482 ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: Yousuk Seung <[email protected]>
Signed-off-by: Neal Cardwell <[email protected]>
Signed-off-by: Yuchung Cheng <[email protected]>
Acked-by: Soheil Hassas Yeganeh <[email protected]>
Acked-by: Eric Dumazet <[email protected]>
Acked-by: Priyaranjan Jha <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

include/linux/tcp.h

@@ -224,7 +224,8 @@ struct tcp_sock {
 		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
 		fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
-		unused:3;
+		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
+		unused:2;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		unused1	    : 1,

include/net/tcp.h

@@ -1055,7 +1055,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
 void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 			    struct rate_sample *rs);
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct rate_sample *rs);
+		  bool is_sack_reneg, struct rate_sample *rs);
 void tcp_rate_check_app_limited(struct sock *sk);
 
 /* These functions determine how the current flow behaves in respect of SACK

net/ipv4/tcp.c

@@ -2412,6 +2412,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0

net/ipv4/tcp_input.c

@@ -1942,6 +1942,8 @@ void tcp_enter_loss(struct sock *sk)
 	if (is_reneg) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
 		tp->sacked_out = 0;
+		/* Mark SACK reneging until we recover from this loss event. */
+		tp->is_sack_reneg = 1;
 	}
 	tcp_clear_all_retrans_hints(tp);
 
@@ -2365,6 +2367,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 		return true;
 	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	return false;
 }
 
@@ -2398,8 +2401,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
-		if (frto_undo || tcp_is_sack(tp))
+		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
+			tp->is_sack_reneg = 0;
+		}
 		return true;
 	}
 	return false;
@@ -3496,6 +3501,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	struct tcp_sacktag_state sack_state;
 	struct rate_sample rs = { .prior_delivered = 0 };
 	u32 prior_snd_una = tp->snd_una;
+	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
@@ -3612,7 +3618,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
-	tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
 	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
 	tcp_xmit_recovery(sk, rexmit);
 	return 1;

net/ipv4/tcp_rate.c

@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 
 /* Update the connection delivery information and generate a rate sample. */
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct rate_sample *rs)
+		  bool is_sack_reneg, struct rate_sample *rs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 
 	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
 	rs->losses = lost;		/* freshly marked lost */
-	/* Return an invalid sample if no timing information is available. */
-	if (!rs->prior_mstamp) {
+	/* Return an invalid sample if no timing information is available or
+	 * in recovery from loss with SACK reneging. Rate samples taken during
+	 * a SACK reneging event may overestimate bw by including packets that
+	 * were SACKed before the reneg.
+	 */
+	if (!rs->prior_mstamp || is_sack_reneg) {
 		rs->delivered = -1;
 		rs->interval_us = -1;
 		return;