[PATCH net-next 4/4] tcp: add stat of data packet reordering events

[Wei Wang <weiwan@google.com>]

From: Wei Wang <weiwan@google.com>

Introduce a new TCP stats to record the number of reordering events seen
and expose it in both tcp_info (TCP_INFO) and opt_stats
(SOF_TIMESTAMPING_OPT_STATS).
Application can use this stats to track the frequency of the reordering
events in addition to the existing reordering stats which tracks the
magnitude of the latest reordering event.

Note: this new stats tracks reordering events triggered by ACKs, which
could often be fewer than the actual number of packets being delivered
out-of-order.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
---
 include/linux/tcp.h      | 4 ++--
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 5 ++++-
 net/ipv4/tcp_input.c     | 3 ++-
 net/ipv4/tcp_recovery.c  | 2 +-
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index da6281c549a5..263e37271afd 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -220,8 +220,7 @@ struct tcp_sock {
 #define TCP_RACK_RECOVERY_THRESH 16
 		u8 reo_wnd_persist:5, /* No. of recovery since last adj */
 		   dsack_seen:1, /* Whether DSACK seen after last adj */
-		   advanced:1,	 /* mstamp advanced since last lost marking */
-		   reord:1;	 /* reordering detected */
+		   advanced:1;	 /* mstamp advanced since last lost marking */
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
@@ -267,6 +266,7 @@ struct tcp_sock {
 	u8	ecn_flags;	/* ECN status bits.			*/
 	u8	keepalive_probes; /* num of allowed keep alive probes	*/
 	u32	reordering;	/* Packet reordering metric.		*/
+	u32	reord_seen;	/* number of data packet reordering events */
 	u32	snd_up;		/* Urgent pointer		*/
 
 /*
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 0e1c0aec0153..e02d31986ff9 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -239,6 +239,7 @@ struct tcp_info {
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
 	__u32	tcpi_dsack_dups;     /* RFC4898 tcpEStatsStackDSACKDups */
+	__u32	tcpi_reord_seen;     /* reordering events seen */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -264,6 +265,7 @@ enum {
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
 	TCP_NLA_DSACK_DUPS,	/* DSACK blocks received */
+	TCP_NLA_REORD_SEEN,	/* reordering events seen */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a8ec6564a7ec..250b73ccb644 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2597,6 +2597,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->bytes_sent = 0;
 	tp->bytes_retrans = 0;
 	tp->dsack_dups = 0;
+	tp->reord_seen = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3207,6 +3208,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_bytes_sent = tp->bytes_sent;
 	info->tcpi_bytes_retrans = tp->bytes_retrans;
 	info->tcpi_dsack_dups = tp->dsack_dups;
+	info->tcpi_reord_seen = tp->reord_seen;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3220,7 +3222,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	u32 rate;
 
 	stats = alloc_skb(9 * nla_total_size_64bit(sizeof(u64)) +
-			  8 * nla_total_size(sizeof(u32)) +
+			  9 * nla_total_size(sizeof(u32)) +
 			  3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
 	if (!stats)
 		return NULL;
@@ -3262,6 +3264,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
 			  TCP_NLA_PAD);
 	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
+	nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fbc85ff7d71d..3d6156f07a8d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -906,8 +906,8 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
 	}
 
-	tp->rack.reord = 1;
 	/* This exciting event is worth to be remembered. 8) */
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk),
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
@@ -1871,6 +1871,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 
 	tp->reordering = min_t(u32, tp->packets_out + addend,
 			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
 
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 71593e4400ab..c81aadff769b 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -25,7 +25,7 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tp->rack.reord) {
+	if (!tp->reord_seen) {
 		/* If reordering has not been observed, be aggressive during
 		 * the recovery or starting the recovery by DUPACK threshold.
 		 */
-- 
2.18.0.345.g5c9ce644c3-goog