tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In

Per RFC4898, they count segments sent/received
containing a positive length data segment (that includes
retransmission segments carrying data).  Unlike
tcpi_segs_out/in, tcpi_data_segs_out/in excludes segments
carrying no data (e.g. pure ack).

The patch also updates the segs_in in tcp_fastopen_add_skb()
so that segs_in >= data_segs_in property is kept.

Together with retransmission data, tcpi_data_segs_out
gives a better signal on the rxmit rate.

v6: Rebase on the latest net-next

v5: Eric pointed out that checking skb->len is still needed in
tcp_fastopen_add_skb() because skb can carry a FIN without data.
Hence, instead of open coding segs_in and data_segs_in, tcp_segs_in()
helper is used.  Comment is added to the fastopen case to explain why
segs_in has to be reset and tcp_segs_in() has to be called before
__skb_pull().

v4: Add comment to the changes in tcp_fastopen_add_skb()
and also add remark on this case in the commit message.

v3: Add const modifier to the skb parameter in tcp_segs_in()

v2: Rework based on recent fix by Eric:
commit a9d99ce28e ("tcp: fix tcpi_segs_in after connection establishment")

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Chris Rapier <rapier@psc.edu>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <mleitner@redhat.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -158,6 +158,9 @@ struct tcp_sock {
 	u32	segs_in;	/* RFC4898 tcpEStatsPerfSegsIn
 				 * total number of segments in.
 				 */
+	u32	data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
+				 * total number of data segments in.
+				 */
  	u32	rcv_nxt;	/* What we want to receive next 	*/
 	u32	copied_seq;	/* Head of yet unread data		*/
 	u32	rcv_wup;	/* rcv_nxt on last window update sent	*/
@@ -165,6 +168,9 @@ struct tcp_sock {
 	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
 				 * The total number of segments sent.
 				 */
+	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.

include/net/tcp.h

@@ -1840,4 +1840,14 @@ static inline int tcp_inq(struct sock *sk)
 	return answ;
 }
 
+static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
+{
+	u16 segs_in;
+
+	segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+	tp->segs_in += segs_in;
+	if (skb->len > tcp_hdrlen(skb))
+		tp->data_segs_in += segs_in;
+}
+
 #endif	/* _TCP_H */

include/uapi/linux/tcp.h

@@ -199,6 +199,8 @@ struct tcp_info {
 
 	__u32	tcpi_notsent_bytes;
 	__u32	tcpi_min_rtt;
+	__u32	tcpi_data_segs_in;	/* RFC4898 tcpEStatsDataSegsIn */
+	__u32	tcpi_data_segs_out;	/* RFC4898 tcpEStatsDataSegsOut */
 };
 
 /* for TCP_MD5SIG socket option */

net/ipv4/tcp.c

@@ -2715,6 +2715,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_notsent_bytes = max(0, notsent_bytes);
 
 	info->tcpi_min_rtt = tcp_min_rtt(tp);
+	info->tcpi_data_segs_in = tp->data_segs_in;
+	info->tcpi_data_segs_out = tp->data_segs_out;
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 

net/ipv4/tcp_fastopen.c

@@ -140,6 +140,14 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
 		return;
 
 	skb_dst_drop(skb);
+	/* segs_in has been initialized to 1 in tcp_create_openreq_child().
+	 * Hence, reset segs_in to 0 before calling tcp_segs_in()
+	 * to avoid double counting.  Also, tcp_segs_in() expects
+	 * skb->len to include the tcp_hdrlen.  Hence, it should
+	 * be called before __skb_pull().
+	 */
+	tp->segs_in = 0;
+	tcp_segs_in(tp, skb);
 	__skb_pull(skb, tcp_hdrlen(skb));
 	skb_set_owner_r(skb, sk);
 

net/ipv4/tcp_ipv4.c

@@ -1650,7 +1650,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	sk_incoming_cpu_update(sk);
 
 	bh_lock_sock_nested(sk);
-	tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))

net/ipv4/tcp_minisocks.c

@@ -812,7 +812,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
-	tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+	tcp_segs_in(tcp_sk(child), skb);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */

net/ipv4/tcp_output.c

@@ -1003,8 +1003,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
 		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
 
-	if (skb->len != tcp_header_size)
+	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
+		tp->data_segs_out += tcp_skb_pcount(skb);
+	}
 
 	if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,

net/ipv6/tcp_ipv6.c

@@ -1443,7 +1443,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	sk_incoming_cpu_update(sk);
 
 	bh_lock_sock_nested(sk);
-	tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))