[PATCH v2 net-next 0/5] tcp: add 4 new stats

[PATCH v2 net-next 0/5] tcp: add 4 new stats

[Wei Wang]

From: Wei Wang <weiwan@google.com>

This patch series adds 3 RFC4898 stats:
1. tcpEStatsPerfHCDataOctetsOut
2. tcpEStatsPerfOctetsRetrans
3. tcpEStatsStackDSACKDups
and an addtional stat to record the number of data packet reordering
events seen:
4. tcp_reord_seen

Together with the existing stats, application can use them to measure
the retransmission rate in bytes, exclude spurious retransmissions
reflected by DSACK, and keep track of the reordering events on live
connections.
In particular the networks with different MTUs make bytes-based loss stats
more useful. Google servers have been using these stats for many years to
instrument transport and network performance.

Note: The first patch is a refactor to add a helper to calculate
opt_stats size in order to make later changes cleaner.

Wei Wang (5):
  tcp: add a helper to calculate size of opt_stats
  tcp: add data bytes sent stats
  tcp: add data bytes retransmitted stats
  tcp: add dsack blocks received stats
  tcp: add stat of data packet reordering events

 include/linux/tcp.h      | 13 ++++++++++--
 include/uapi/linux/tcp.h | 10 ++++++++-
 net/ipv4/tcp.c           | 46 +++++++++++++++++++++++++++++++++++++---
 net/ipv4/tcp_input.c     |  4 +++-
 net/ipv4/tcp_output.c    |  2 ++
 net/ipv4/tcp_recovery.c  |  2 +-
 6 files changed, 69 insertions(+), 8 deletions(-)

-- 
2.18.0.345.g5c9ce644c3-goog

[PATCH v2 net-next 1/5] tcp: add a helper to calculate size of opt_stats

[Wei Wang]

From: Wei Wang <weiwan@google.com>

This is to refactor the calculation of the size of opt_stats to a helper
function to make the code cleaner and easier for later changes.

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
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>
---
 net/ipv4/tcp.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f3bfb9f29520..27bbe6a792b7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3205,6 +3205,29 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
+static size_t tcp_opt_stats_get_size(void)
+{
+	return
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
+		0;
+}
+
 struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -3213,9 +3236,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	u64 rate64;
 	u32 rate;
 
-	stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
-			  7 * nla_total_size(sizeof(u32)) +
-			  3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
+	stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC);
 	if (!stats)
 		return NULL;
 
-- 
2.18.0.345.g5c9ce644c3-goog

[PATCH v2 net-next 2/5] tcp: add data bytes sent stats

[Wei Wang]

From: Wei Wang <weiwan@google.com>

Introduce a new TCP stat to record the number of bytes sent
(RFC4898 tcpEStatsPerfHCDataOctetsOut) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

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      | 3 +++
 include/uapi/linux/tcp.h | 4 +++-
 net/ipv4/tcp.c           | 6 ++++++
 net/ipv4/tcp_output.c    | 1 +
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 58a8d7d71354..d0798dcd2cab 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -181,6 +181,9 @@ struct tcp_sock {
 	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
 				 * total number of data segments sent.
 				 */
+	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
+				 * total number of data bytes sent.
+				 */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index e3f6ed8a7064..1c70ed287c3b 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -235,6 +235,8 @@ struct tcp_info {
 
 	__u32	tcpi_delivered;
 	__u32	tcpi_delivered_ce;
+
+	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -257,7 +259,7 @@ enum {
 	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 */
-
+	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27bbe6a792b7..873cb9968ff5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2594,6 +2594,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->bytes_sent = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3201,6 +3202,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_delivery_rate = rate64;
 	info->tcpi_delivered = tp->delivered;
 	info->tcpi_delivered_ce = tp->delivered_ce;
+	info->tcpi_bytes_sent = tp->bytes_sent;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3225,6 +3227,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		0;
 }
 
@@ -3272,6 +3275,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	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);
 
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
+			  TCP_NLA_PAD);
+
 	return stats;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 490df62f26d4..861531fe0e97 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1136,6 +1136,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
 		tp->data_segs_out += tcp_skb_pcount(skb);
+		tp->bytes_sent += skb->len - tcp_header_size;
 		tcp_internal_pacing(sk, skb);
 	}
 
-- 
2.18.0.345.g5c9ce644c3-goog

[PATCH v2 net-next 3/5] tcp: add data bytes retransmitted stats

[Wei Wang]

From: Wei Wang <weiwan@google.com>

Introduce a new TCP stat to record the number of bytes retransmitted
(RFC4898 tcpEStatsPerfOctetsRetrans) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

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      | 3 +++
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 5 +++++
 net/ipv4/tcp_output.c    | 1 +
 4 files changed, 11 insertions(+)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d0798dcd2cab..fb67f9a51b95 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -333,6 +333,9 @@ struct tcp_sock {
 				 * the first SYN. */
 	u32	undo_marker;	/* snd_una upon a new recovery episode. */
 	int	undo_retrans;	/* number of undoable retransmissions. */
+	u64	bytes_retrans;	/* RFC4898 tcpEStatsPerfOctetsRetrans
+				 * Total data bytes retransmitted
+				 */
 	u32	total_retrans;	/* Total retransmits for entire connection */
 
 	u32	urg_seq;	/* Seq of received urgent pointer */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 1c70ed287c3b..c31f5100b744 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -237,6 +237,7 @@ struct tcp_info {
 	__u32	tcpi_delivered_ce;
 
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
+	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -260,6 +261,7 @@ enum {
 	TCP_NLA_DELIVERED,	/* Data pkts delivered incl. out-of-order */
 	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
+	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 873cb9968ff5..5ed1be88e922 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2595,6 +2595,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
+	tp->bytes_retrans = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3203,6 +3204,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_delivered = tp->delivered;
 	info->tcpi_delivered_ce = tp->delivered_ce;
 	info->tcpi_bytes_sent = tp->bytes_sent;
+	info->tcpi_bytes_retrans = tp->bytes_retrans;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3228,6 +3230,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
 		0;
 }
 
@@ -3277,6 +3280,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 
 	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
 			  TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
+			  TCP_NLA_PAD);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 861531fe0e97..50cabf7656f3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2871,6 +2871,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
 	tp->total_retrans += segs;
+	tp->bytes_retrans += skb->len;
 
 	/* make sure skb->data is aligned on arches that require it
 	 * and check if ack-trimming & collapsing extended the headroom
-- 
2.18.0.345.g5c9ce644c3-goog

[PATCH v2 net-next 4/5] tcp: add dsack blocks received stats

[Wei Wang]

From: Wei Wang <weiwan@google.com>

Introduce a new TCP stat to record the number of DSACK blocks received
(RFC4989 tcpEStatsStackDSACKDups) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

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      | 3 +++
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 4 ++++
 net/ipv4/tcp_input.c     | 1 +
 4 files changed, 10 insertions(+)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index fb67f9a51b95..da6281c549a5 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -188,6 +188,9 @@ struct tcp_sock {
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	u32	dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
+				 * total number of DSACK blocks received
+				 */
  	u32	snd_una;	/* First byte we want an ack for	*/
  	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
 	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index c31f5100b744..0e1c0aec0153 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -238,6 +238,7 @@ struct tcp_info {
 
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
+	__u32	tcpi_dsack_dups;     /* RFC4898 tcpEStatsStackDSACKDups */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -262,6 +263,7 @@ enum {
 	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
+	TCP_NLA_DSACK_DUPS,	/* DSACK blocks received */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5ed1be88e922..d6232b598cae 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2596,6 +2596,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_retrans = 0;
+	tp->dsack_dups = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3205,6 +3206,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_delivered_ce = tp->delivered_ce;
 	info->tcpi_bytes_sent = tp->bytes_sent;
 	info->tcpi_bytes_retrans = tp->bytes_retrans;
+	info->tcpi_dsack_dups = tp->dsack_dups;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3231,6 +3233,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
 		0;
 }
 
@@ -3282,6 +3285,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 			  TCP_NLA_PAD);
 	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);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d51fa358b2b1..fbc85ff7d71d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -874,6 +874,7 @@ static void tcp_dsack_seen(struct tcp_sock *tp)
 {
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
 	tp->rack.dsack_seen = 1;
+	tp->dsack_dups++;
 }
 
 /* It's reordering when higher sequence was delivered (i.e. sacked) before
-- 
2.18.0.345.g5c9ce644c3-goog

[PATCH v2 net-next 5/5] tcp: add stat of data packet reordering events

[Wei Wang]

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           | 4 ++++
 net/ipv4/tcp_input.c     | 3 ++-
 net/ipv4/tcp_recovery.c  | 2 +-
 5 files changed, 11 insertions(+), 4 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 d6232b598cae..31fa1c080f28 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);
@@ -3234,6 +3236,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
 		0;
 }
 
@@ -3286,6 +3289,7 @@ 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

Re: [PATCH v2 net-next 0/5] tcp: add 4 new stats

[David Miller]

From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:19 -0700

> From: Wei Wang <weiwan@google.com>
> 
> This patch series adds 3 RFC4898 stats:
> 1. tcpEStatsPerfHCDataOctetsOut
> 2. tcpEStatsPerfOctetsRetrans
> 3. tcpEStatsStackDSACKDups
> and an addtional stat to record the number of data packet reordering
> events seen:
> 4. tcp_reord_seen
> 
> Together with the existing stats, application can use them to measure
> the retransmission rate in bytes, exclude spurious retransmissions
> reflected by DSACK, and keep track of the reordering events on live
> connections.
> In particular the networks with different MTUs make bytes-based loss stats
> more useful. Google servers have been using these stats for many years to
> instrument transport and network performance.
> 
> Note: The first patch is a refactor to add a helper to calculate
> opt_stats size in order to make later changes cleaner.

Series applied, thank you.