tcp: Add TCP_INFO counter for packets received out-of-order

For receive-heavy cases on the server-side, we want to track the
connection quality for individual client IPs. This counter, similar to
the existing system-wide TCPOFOQueue counter in /proc/net/netstat,
tracks out-of-order packet reception. By providing this counter in
TCP_INFO, it will allow understanding to what degree receive-heavy
sockets are experiencing out-of-order delivery and packet drops
indicating congestion.

Please note that this is similar to the counter in NetBSD TCP_INFO, and
has the same name.

Also note that we avoid increasing the size of the tcp_sock struct by
taking advantage of a hole.

Signed-off-by: Thomas Higdon <tph@fb.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 7 insertions, 0 deletions

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index f3a85a7fb4b1..99617e528ea2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -354,6 +354,8 @@ struct tcp_sock {
 #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
 #endif
 
+	u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
+
 /* Receiver side RTT estimation */
 	u32 rcv_rtt_last_tsecr;
 	struct {
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index b3564f85a762..20237987ccc8 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -270,6 +270,8 @@ struct tcp_info {
 	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
 	__u32	tcpi_dsack_dups;     /* RFC4898 tcpEStatsStackDSACKDups */
 	__u32	tcpi_reord_seen;     /* reordering events seen */
+
+	__u32	tcpi_rcv_ooopack;    /* Out-of-order packets received */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 94df48bcecc2..4cf58208270e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2653,6 +2653,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->rx_opt.saw_tstamp = 0;
 	tp->rx_opt.dsack = 0;
 	tp->rx_opt.num_sacks = 0;
+	tp->rcv_ooopack = 0;
 
 
 	/* Clean up fastopen related fields */
@@ -3295,6 +3296,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_bytes_retrans = tp->bytes_retrans;
 	info->tcpi_dsack_dups = tp->dsack_dups;
 	info->tcpi_reord_seen = tp->reord_seen;
+	info->tcpi_rcv_ooopack = tp->rcv_ooopack;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7e94223fdb2b..3578357abe30 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4555,6 +4555,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
 
+	tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE);
 	seq = TCP_SKB_CB(skb)->seq;
 	end_seq = TCP_SKB_CB(skb)->end_seq;