iproute2: add support for tcp_metrics

ip tcp_metrics/tcpmetrics

	We support get/del for single entry and dump for
show/flush.

v3:
 - fix rtt/rttvar shifts as suggested by Eric Dumazet
 - show rtt/rttvar usecs as suggested by David Laight
Signed-off-by: Julian Anastasov <ja@ssi.bg>

include/linux/tcp_metrics.h

+/* tcp_metrics.h - TCP Metrics Interface */
+
+#ifndef _LINUX_TCP_METRICS_H
+#define _LINUX_TCP_METRICS_H
+
+#include <linux/types.h>
+
+/* NETLINK_GENERIC related info
+ */
+#define TCP_METRICS_GENL_NAME		"tcp_metrics"
+#define TCP_METRICS_GENL_VERSION	0x1
+
+enum tcp_metric_index {
+	TCP_METRIC_RTT,
+	TCP_METRIC_RTTVAR,
+	TCP_METRIC_SSTHRESH,
+	TCP_METRIC_CWND,
+	TCP_METRIC_REORDERING,
+
+	/* Always last.  */
+	__TCP_METRIC_MAX,
+};
+
+#define TCP_METRIC_MAX	(__TCP_METRIC_MAX - 1)
+
+enum {
+	TCP_METRICS_ATTR_UNSPEC,
+	TCP_METRICS_ATTR_ADDR_IPV4,		/* u32 */
+	TCP_METRICS_ATTR_ADDR_IPV6,		/* binary */
+	TCP_METRICS_ATTR_AGE,			/* msecs */
+	TCP_METRICS_ATTR_TW_TSVAL,		/* u32, raw, rcv tsval */
+	TCP_METRICS_ATTR_TW_TS_STAMP,		/* s32, sec age */
+	TCP_METRICS_ATTR_VALS,			/* nested +1, u32 */
+	TCP_METRICS_ATTR_FOPEN_MSS,		/* u16 */
+	TCP_METRICS_ATTR_FOPEN_SYN_DROPS,	/* u16, count of drops */
+	TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS,	/* msecs age */
+	TCP_METRICS_ATTR_FOPEN_COOKIE,		/* binary */
+
+	__TCP_METRICS_ATTR_MAX,
+};
+
+#define TCP_METRICS_ATTR_MAX	(__TCP_METRICS_ATTR_MAX - 1)
+
+enum {
+	TCP_METRICS_CMD_UNSPEC,
+	TCP_METRICS_CMD_GET,
+	TCP_METRICS_CMD_DEL,
+
+	__TCP_METRICS_CMD_MAX,
+};
+
+#define TCP_METRICS_CMD_MAX	(__TCP_METRICS_CMD_MAX - 1)
+
+#endif /* _LINUX_TCP_METRICS_H */

ip/Makefile

@@ -4,7 +4,7 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
     ipxfrm.o xfrm_state.o xfrm_policy.o xfrm_monitor.o \
     iplink_vlan.o link_veth.o link_gre.o iplink_can.o \
     iplink_macvlan.o iplink_macvtap.o ipl2tp.o link_vti.o \
-    iplink_vxlan.o
+    iplink_vxlan.o tcp_metrics.o
 
 RTMONOBJ=rtmon.o
 

ip/ip.c

@@ -45,7 +45,7 @@ static void usage(void)
 "       ip [ -force ] -batch filename\n"
 "where  OBJECT := { link | addr | addrlabel | route | rule | neigh | ntable |\n"
 "                   tunnel | tuntap | maddr | mroute | mrule | monitor | xfrm |\n"
-"                   netns | l2tp }\n"
+"                   netns | l2tp | tcp_metrics }\n"
 "       OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] | -r[esolve] |\n"
 "                    -f[amily] { inet | inet6 | ipx | dnet | bridge | link } |\n"
 "                    -l[oops] { maximum-addr-flush-attempts } |\n"
@@ -78,6 +78,8 @@ static const struct cmd {
 	{ "tunl",	do_iptunnel },
 	{ "tuntap",	do_iptuntap },
 	{ "tap",	do_iptuntap },
+	{ "tcpmetrics",	do_tcp_metrics },
+	{ "tcp_metrics",do_tcp_metrics },
 	{ "monitor",	do_ipmonitor },
 	{ "xfrm",	do_xfrm },
 	{ "mroute",	do_multiroute },

ip/ip_common.h

@@ -42,6 +42,7 @@ extern int do_multirule(int argc, char **argv);
 extern int do_netns(int argc, char **argv);
 extern int do_xfrm(int argc, char **argv);
 extern int do_ipl2tp(int argc, char **argv);
+extern int do_tcp_metrics(int argc, char **argv);
 
 static inline int rtm_get_table(struct rtmsg *r, struct rtattr **tb)
 {

man/man8/Makefile

@@ -8,7 +8,8 @@ MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnstat.8 routel.8 rtacct.8 rtmon.8 ss.8 \
 	bridge.8 rtstat.8 ctstat.8 nstat.8 routef.8 \
 	ip-address.8 ip-addrlabel.8 ip-l2tp.8 ip-link.8 \
 	ip-maddress.8 ip-monitor.8 ip-mroute.8 ip-neighbour.8 \
-	ip-netns.8 ip-ntable.8 ip-route.8 ip-rule.8 ip-tunnel.8 ip-xfrm.8
+	ip-netns.8 ip-ntable.8 ip-route.8 ip-rule.8 ip-tunnel.8 ip-xfrm.8 \
+	ip-tcp_metrics.8
 
 all: $(TARGETS)
 

man/man8/ip-tcp_metrics.8

+.TH "IP\-TCP_METRICS" 8 "23 Aug 2012" "iproute2" "Linux"
+.SH "NAME"
+ip-tcp_metrics \- management for TCP Metrics
+.SH "SYNOPSIS"
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.RI "[ " OPTIONS " ]"
+.B tcp_metrics
+.RI "{ " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip tcp_metrics" " { " show " | " flush " }
+.IR SELECTOR
+
+.ti -8
+.BR "ip tcp_metrics delete " [ " address " ]
+.IR ADDRESS
+
+.ti -8
+.IR SELECTOR " := "
+.RB "[ [ " address " ] "
+.IR PREFIX " ]"
+
+.SH "DESCRIPTION"
+.B ip tcp_metrics
+is used to manipulate entries in the kernel that keep TCP information
+for IPv4 and IPv6 destinations. The entries are created when
+TCP sockets want to share information for destinations and are
+stored in a cache keyed by the destination address. The saved
+information may include values for metrics (initially obtained from
+routes), recent TSVAL for TIME-WAIT recycling purposes, state for the
+Fast Open feature, etc.
+For performance reasons the cache can not grow above configured limit
+and the older entries are replaced with fresh information, sometimes
+reclaimed and used for new destinations. The kernel never removes
+entries, they can be flushed only with this tool.
+
+.SS ip tcp_metrics show - show cached entries
+
+.TP
+.BI address " PREFIX " (default)
+IPv4/IPv6 prefix or address. If no prefix is provided all entries are shown.
+
+.LP
+The output may contain the following information:
+
+.BI age " <S.MMM>" sec
+- time after the entry was created, reset or updated with metrics
+from sockets. The entry is reset and refreshed on use with metrics from
+route if the metrics are not updated in last hour. Not all cached values
+reset the age on update.
+
+.BI cwnd " <N>"
+- CWND metric value
+
+.BI fo_cookie " <HEX-STRING>"
+- Cookie value received in SYN-ACK to be used by Fast Open for next SYNs
+
+.BI fo_mss " <N>"
+- MSS value received in SYN-ACK to be used by Fast Open for next SYNs
+
+.BI fo_syn_drops " <N>/<S.MMM>" "sec ago"
+- Number of drops of initial outgoing Fast Open SYNs with data
+detected by monitoring the received SYN-ACK after SYN retransmission.
+The seconds show the time after last SYN drop and together with
+the drop count can be used to disable Fast Open for some time.
+
+.BI reordering " <N>"
+- Reordering metric value
+
+.BI rtt " <N>" us
+- RTT metric value
+
+.BI rttvar " <N>" us
+- RTTVAR metric value
+
+.BI ssthresh " <SSTHRESH>"
+- SSTHRESH metric value
+
+.BI tw_ts " <TSVAL>/<SEC>" "sec ago"
+- recent TSVAL and the seconds after saving it into TIME-WAIT socket
+
+.SS ip tcp_metrics delete - delete single entry
+
+.TP
+.BI address " ADDRESS " (default)
+IPv4/IPv6 address. The address is a required argument.
+
+.SS ip tcp_metrics flush - flush entries
+This command flushes the entries selected by some criteria.
+
+.PP
+This command has the same arguments as
+.B show.
+
+.SH "EXAMPLES"
+.PP
+ip tcp_metrics show address 192.168.0.0/24
+.RS 4
+Shows the entries for destinations from subnet
+.RE
+.PP
+ip tcp_metrics show 192.168.0.0/24
+.RS 4
+The same but address keyword is optional
+.RE
+.PP
+ip tcp_metrics
+.RS 4
+Show all is the default action
+.RE
+.PP
+ip tcp_metrics delete 192.168.0.1
+.RS 4
+Removes the entry for 192.168.0.1 from cache.
+.RE
+.PP
+ip tcp_metrics flush 192.168.0.0/24
+.RS 4
+Removes entries for destinations from subnet
+.RE
+.PP
+ip tcp_metrics flush all
+.RS 4
+Removes all entries from cache
+.RE
+.PP
+ip -6 tcp_metrics flush all
+.RS 4
+Removes all IPv6 entries from cache keeping the IPv4 entries.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8)
+
+.SH AUTHOR
+Original Manpage by Julian Anastasov <ja@ssi.bg>

man/man8/ip.8

@@ -15,7 +15,7 @@ ip \- show / manipulate routing, devices, policy routing and tunnels
 .IR OBJECT " := { "
 .BR link " | " addr " | " addrlabel " | " route " | " rule " | " neigh " | "\
  ntable " | " tunnel " | " tuntap " | " maddr " | "  mroute " | " mrule " | "\
- monitor " | " xfrm " | " netns " | "  l2tp " }"
+ monitor " | " xfrm " | " netns " | "  l2tp " | "  tcp_metrics " }"
 .sp
 
 .ti -8
@@ -160,6 +160,10 @@ host addresses.
 .B rule
 - rule in routing policy database.
 
+.TP
+.B tcp_metrics/tcpmetrics
+- manage TCP Metrics
+
 .TP
 .B tunnel
 - tunnel over IP.
@@ -220,6 +224,7 @@ was written by Alexey N. Kuznetsov and added in Linux 2.2.
 .BR ip-ntable (8),
 .BR ip-route (8),
 .BR ip-rule (8),
+.BR ip-tcp_metrics (8),
 .BR ip-tunnel (8),
 .BR ip-xfrm (8)
 .br