Implementation of RFC 4898 Extended TCP Statistics (Web10G)

index 67309ec..8758360 100644
@@ -126,6 +126,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 	return (struct tcp_request_sock *)req;
 }
 
+#ifdef CONFIG_TCP_ESTATS
+struct tcp_estats;
+#endif
+
 struct tcp_sock {
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;

@@ -309,6 +313,10 @@ struct tcp_sock {
 	struct tcp_md5sig_info	__rcu *md5sig_info;
 #endif
 
+#ifdef CONFIG_TCP_ESTATS
+	struct tcp_estats	*tcp_stats;
+#endif
+
 /* TCP fastopen related information */
 	struct tcp_fastopen_request *fastopen_req;
 	/* fastopen_rsk points to request_sock that resulted in this big

index f50f29faf..9f7e31e 100644
@@ -43,6 +43,7 @@
 #include <net/tcp_states.h>
 #include <net/inet_ecn.h>
 #include <net/dst.h>
+#include <net/tcp_estats.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>

376 lines not on this page · raw message

index 3b97183..5dae043 100644
@@ -186,9 +186,13 @@ struct tcp_info {
 	__u32	tcpi_rcv_space;
 
 	__u32	tcpi_total_retrans;
-
 	__u64	tcpi_pacing_rate;
 	__u64	tcpi_max_pacing_rate;
+
+#ifdef CONFIG_TCP_ESTATS
+	/* RFC 4898 extended stats Info */
+	__u32	tcpi_estats_cid;
+#endif
 };
 
 /* for TCP_MD5SIG socket option */

index e0ee384..edc5a66 100644
@@ -42,6 +42,11 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 
+/* Extended statistics (RFC4898). */
+#ifdef CONFIG_TCP_ESTATS
+int sysctl_tcp_estats __read_mostly;
+#endif  /* CONFIG_TCP_ESTATS */
+
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {

@@ -767,6 +772,15 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &one
 	},
+#ifdef CONFIG_TCP_ESTATS
+	{
+		.procname	= "tcp_estats",
+		.data		= &sysctl_tcp_estats,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif /* CONFIG TCP ESTATS */
 	{ }
 };
 

index 3075723..698dbb7 100644
@@ -418,6 +418,10 @@ void tcp_init_sock(struct sock *sk)
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
+#ifdef CONFIG_TCP_ESTATS
+	tp->tcp_stats = NULL;
+#endif
+
 	local_bh_disable();
 	sock_update_memcg(sk);
 	sk_sockets_allocated_inc(sk);

@@ -972,6 +976,9 @@ wait_for_memory:
 		tcp_push(sk, flags & ~MSG_MORE, mss_now,
 			 TCP_NAGLE_PUSH, size_goal);
 
+		if (copied)
+                        TCP_ESTATS_UPDATE(tp, tcp_estats_update_writeq(sk));
+
 		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 			goto do_error;
 

@@ -1264,9 +1271,11 @@ new_segment:
 wait_for_sndbuf:
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
+			if (copied) {
 				tcp_push(sk, flags & ~MSG_MORE, mss_now,
 					 TCP_NAGLE_PUSH, size_goal);
+				TCP_ESTATS_UPDATE(tp, tcp_estats_update_writeq(sk));
+			}
 
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 				goto do_error;

@@ -1658,6 +1667,8 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			     *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
 		}
 
+		TCP_ESTATS_UPDATE(tp, tcp_estats_update_recvq(sk));
+
 		/* Well, if we have backlog, try to process it now yet. */
 
 		if (copied >= target && !sk->sk_backlog.tail)

@@ -2684,6 +2695,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 					sk->sk_pacing_rate : ~0ULL;
 	info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
 					sk->sk_max_pacing_rate : ~0ULL;
+
+#ifdef CONFIG_TCP_ESTATS
+	info->tcpi_estats_cid = (tp->tcp_stats && tp->tcp_stats->tcpe_cid > 0)
+					? tp->tcp_stats->tcpe_cid : 0;
+#endif
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 

@@ -3101,6 +3117,9 @@ void __init tcp_init(void)
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
 	tcp_metrics_init();
+
 	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
+	tcp_estats_init();
+
 	tcp_tasklet_init();
 }

index 27ead0d..e93929d 100644
@@ -295,6 +295,8 @@ void tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
+	TCP_ESTATS_VAR_INC(tp, stack_table, SlowStart);
+
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);

@@ -304,6 +306,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start);
 /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
 {
+	TCP_ESTATS_VAR_INC(tp, stack_table, CongAvoid);
 	if (tp->snd_cwnd_cnt >= w) {
 		if (tp->snd_cwnd < tp->snd_cwnd_clamp)
 			tp->snd_cwnd++;

736 lines not on this page · raw message

index 58469ff..5facb4c 100644
@@ -251,6 +251,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 			tp->snd_cwnd_cnt += ca->pkts_acked;
 
 		ca->pkts_acked = 1;
+		TCP_ESTATS_VAR_INC(tp, stack_table, CongAvoid);
 	}
 }
 

366 lines not on this page · raw message

index a3f72d7..9c85a54 100644
@@ -1310,6 +1310,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	if (!newsk)
 		goto exit_nonewsk;
 
+	tcp_estats_create(newsk, TCP_ESTATS_ADDRTYPE_IPV4, TCP_ESTATS_INACTIVE);
+
 	newsk->sk_gso_type = SKB_GSO_TCPV4;
 	inet_sk_rx_dst_set(newsk, skb);
 

@@ -1670,6 +1672,8 @@ process:
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
+	TCP_ESTATS_UPDATE(
+		tcp_sk(sk), tcp_estats_update_segrecv(tcp_sk(sk), skb));
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))

@@ -1680,6 +1684,8 @@ process:
 		NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
 		goto discard_and_relse;
 	}
+	TCP_ESTATS_UPDATE(
+		tcp_sk(sk), tcp_estats_update_finish_segrecv(tcp_sk(sk)));
 	bh_unlock_sock(sk);
 
 	sock_put(sk);

@@ -1809,6 +1815,8 @@ static int tcp_v4_init_sock(struct sock *sk)
 	tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific;
 #endif
 
+	tcp_estats_create(sk, TCP_ESTATS_ADDRTYPE_IPV4, TCP_ESTATS_ACTIVE);
+
 	return 0;
 }
 

@@ -1842,6 +1850,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
+	tcp_estats_destroy(sk);
+
 	BUG_ON(tp->fastopen_rsk != NULL);
 
 	/* If socket is aborted during connect operation */

178 lines not on this page · raw message

index 1829c7f..0f6f1f4 100644
@@ -477,6 +477,9 @@ out_reset_timer:
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
+
+        TCP_ESTATS_UPDATE(tp, tcp_estats_update_timeout(sk));
+
 	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0))
 		__sk_dst_reset(sk);
 

index 5ff8780..db1f88f 100644
@@ -1131,6 +1131,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	if (newsk == NULL)
 		goto out_nonewsk;
 
+	tcp_estats_create(newsk, TCP_ESTATS_ADDRTYPE_IPV6, TCP_ESTATS_INACTIVE);
+
 	/*
 	 * No need to charge this sock to the relevant IPv6 refcnt debug socks
 	 * count here, tcp_create_openreq_child now does this for us, see the

@@ -1463,6 +1465,8 @@ process:
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
+	TCP_ESTATS_UPDATE(
+		tcp_sk(sk), tcp_estats_update_segrecv(tcp_sk(sk), skb));
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
 		if (!tcp_prequeue(sk, skb))

@@ -1473,6 +1477,8 @@ process:
 		NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
 		goto discard_and_relse;
 	}
+	TCP_ESTATS_UPDATE(
+		tcp_sk(sk), tcp_estats_update_finish_segrecv(tcp_sk(sk)));
 	bh_unlock_sock(sk);
 
 	sock_put(sk);

@@ -1661,6 +1667,7 @@ static int tcp_v6_init_sock(struct sock *sk)
 #ifdef CONFIG_TCP_MD5SIG
 	tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific;
 #endif
+	tcp_estats_create(sk, TCP_ESTATS_ADDRTYPE_IPV6, TCP_ESTATS_ACTIVE);
 
 	return 0;
 }