tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info

This patch tracks the total number of inbound and outbound segments on a
TCP socket. One may use this number to have an idea on connection
quality when compared against the retransmissions.

RFC4898 named these : tcpEStatsPerfSegsIn and tcpEStatsPerfSegsOut

These are a 32bit field each and can be fetched both from TCP_INFO
getsockopt() if one has a handle on a TCP socket, or from inet_diag
netlink facility (iproute2/ss patch will follow)

Note that tp->segs_out was placed near tp->snd_nxt for good data
locality and minimal performance impact, while tp->segs_in was placed
near tp->bytes_received for the same reason.

Join work with Eric Dumazet.

Note that received SYN are accounted on the listener, but sent SYNACK
are not accounted.

Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -149,11 +149,16 @@ struct tcp_sock {
 				 * sum(delta(rcv_nxt)), or how many bytes
 				 * were acked.
 				 */
+	u32	segs_in;	/* RFC4898 tcpEStatsPerfSegsIn
+				 * total number of 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	*/
  	u32	snd_nxt;	/* Next sequence we send		*/
-
+	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.

include/uapi/linux/tcp.h

@@ -194,6 +194,8 @@ struct tcp_info {
 	__u64	tcpi_max_pacing_rate;
 	__u64	tcpi_bytes_acked;    /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
 	__u64	tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+	__u32	tcpi_segs_out;	     /* RFC4898 tcpEStatsPerfSegsOut */
+	__u32	tcpi_segs_in;	     /* RFC4898 tcpEStatsPerfSegsIn */
 };
 
 /* for TCP_MD5SIG socket option */

net/ipv4/tcp.c

@@ -2695,6 +2695,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	spin_lock_bh(&sk->sk_lock.slock);
 	info->tcpi_bytes_acked = tp->bytes_acked;
 	info->tcpi_bytes_received = tp->bytes_received;
+	info->tcpi_segs_out = tp->segs_out;
+	info->tcpi_segs_in = tp->segs_in;
 	spin_unlock_bh(&sk->sk_lock.slock);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);

net/ipv4/tcp_ipv4.c

@@ -1626,6 +1626,7 @@ process:
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
+	tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))

net/ipv4/tcp_minisocks.c

@@ -448,6 +448,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 
 		newtp->rcv_wup = newtp->copied_seq =
 		newtp->rcv_nxt = treq->rcv_isn + 1;
+		newtp->segs_in = 0;
 
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;

net/ipv4/tcp_output.c

@@ -1027,6 +1027,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
+	tp->segs_out += tcp_skb_pcount(skb);
 	/* OK, its time to fill skb_shinfo(skb)->gso_segs */
 	skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
 

net/ipv6/tcp_ipv6.c

@@ -1421,6 +1421,7 @@ process:
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
+	tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))