[PATCH net-next 4/4] tcp: export packets delivery info

[Yuchung Cheng <ycheng@google.com>]

Export data delivered and delivered with CE marks to
1) SNMP TCPDelivered and TCPDeliveredCE
2) getsockopt(TCP_INFO)
3) Timestamping API SOF_TIMESTAMPING_OPT_STATS

Note that for SCM_TSTAMP_ACK, the delivery info in
SOF_TIMESTAMPING_OPT_STATS is reported before the info
was fully updated on the ACK.

These stats help application monitor TCP delivery and ECN status
on per host, per connection, even per message level.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
---
 include/uapi/linux/snmp.h | 2 ++
 include/uapi/linux/tcp.h  | 5 +++++
 net/ipv4/proc.c           | 2 ++
 net/ipv4/tcp.c            | 7 ++++++-
 net/ipv4/tcp_input.c      | 6 +++++-
 5 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 33a70ece462f..d02e859301ff 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -276,6 +276,8 @@ enum
 	LINUX_MIB_TCPKEEPALIVE,			/* TCPKeepAlive */
 	LINUX_MIB_TCPMTUPFAIL,			/* TCPMTUPFail */
 	LINUX_MIB_TCPMTUPSUCCESS,		/* TCPMTUPSuccess */
+	LINUX_MIB_TCPDELIVERED,			/* TCPDelivered */
+	LINUX_MIB_TCPDELIVEREDCE,		/* TCPDeliveredCE */
 	__LINUX_MIB_MAX
 };
 
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 560374c978f9..379b08700a54 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -224,6 +224,9 @@ struct tcp_info {
 	__u64	tcpi_busy_time;      /* Time (usec) busy sending data */
 	__u64	tcpi_rwnd_limited;   /* Time (usec) limited by receive window */
 	__u64	tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */
+
+	__u32	tcpi_delivered;
+	__u32	tcpi_delivered_ce;
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -244,6 +247,8 @@ enum {
 	TCP_NLA_SNDQ_SIZE,	/* Data (bytes) pending in send queue */
 	TCP_NLA_CA_STATE,	/* ca_state of socket */
 	TCP_NLA_SND_SSTHRESH,	/* Slow start size threshold */
+	TCP_NLA_DELIVERED,	/* Data pkts delivered incl. out-of-order */
+	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
 
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a058de677e94..261b71d0ccc5 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -296,6 +296,8 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
 	SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL),
 	SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
+	SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
+	SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5a5ce6da4792..4022073b0aee 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3167,6 +3167,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	rate64 = tcp_compute_delivery_rate(tp);
 	if (rate64)
 		info->tcpi_delivery_rate = rate64;
+	info->tcpi_delivered = tp->delivered;
+	info->tcpi_delivered_ce = tp->delivered_ce;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3180,7 +3182,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	u32 rate;
 
 	stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
-			  5 * nla_total_size(sizeof(u32)) +
+			  7 * nla_total_size(sizeof(u32)) +
 			  3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
 	if (!stats)
 		return NULL;
@@ -3211,9 +3213,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits);
 	nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);
 	nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh);
+	nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered);
+	nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce);
 
 	nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
 	nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
+
 	return stats;
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b3bff9c20606..0396fb919b5d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3499,12 +3499,16 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
 /* Returns the number of packets newly acked or sacked by the current ACK */
 static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
 {
+	const struct net *net = sock_net(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 delivered;
 
 	delivered = tp->delivered - prior_delivered;
-	if (flag & FLAG_ECE)
+	NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
+	if (flag & FLAG_ECE) {
 		tp->delivered_ce += delivered;
+		NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
+	}
 	return delivered;
 }
 
-- 
2.17.0.484.g0c8726318c-goog