[PATCH v2 0/2] Interface for TCP Metrics

[PATCH v2 0/2] Interface for TCP Metrics

[Julian Anastasov]

	This patchset contains 2 patches, one for kernel
and one for iproute2. We add DUMP/GET/DEL support for
genl "tcp_metrics" and minimal support for filtering
by address prefix and family in user space.

	I tested show/del/flush, filtering by family, IPv4 prefix,
output for metrics such as rtt, rttvar, cwnd, ssthresh (after
modifying route). I didn't tested output for fast open.

	May be some corrections in output can be desired.

	The kernel patch has some parts to check:

- in tcp_metrics_nl_cmd_del I'm trying to flush all addresses
with single request, eg. when no family, address or other
selectors are provided. I use some arbitrary counter sync_count
to force memory to be freed in parts by using synchronize_rcu,
note that we are under genl_mutex, so may be this is bad idea
to delay other genl users? My idea was to avoid many commands
on "flush all", may be we should trigger flush by using some
other mechanism that is pernet? And I don't know how to test
it properly without large cache.

- I enabled lockdep in config and don't see any warnings.
make C=2 net/ipv4/tcp_metrics.o is silent too.

v2:
- patch 1: remove rcu_assign_pointer, add tcp_metrics_flush_all
- patch 2: properly flush by specifying address, improve man page

[PATCH v2 1/2] tcp: add generic netlink support for tcp_metrics

[Julian Anastasov]

	Add support for genl "tcp_metrics". No locking
is changed, only that now we can unlink and delete
entries after grace period. We implement get/del for
single entry and dump to support show/flush filtering
in user space. Del without address attribute causes
flush for all addresses, sadly under genl_mutex.

v2:
- remove rcu_assign_pointer as suggested by Eric Dumazet,
it is not needed because there are no other writes under lock
- move the flushing code in tcp_metrics_flush_all

Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
 include/linux/Kbuild        |    1 +
 include/linux/tcp_metrics.h |   54 +++++++
 net/ipv4/tcp_metrics.c      |  357 +++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 399 insertions(+), 13 deletions(-)
 create mode 100644 include/linux/tcp_metrics.h

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 1f2c1c7..90da0af 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -363,6 +363,7 @@ header-y += sysctl.h
 header-y += sysinfo.h
 header-y += taskstats.h
 header-y += tcp.h
+header-y += tcp_metrics.h
 header-y += telephony.h
 header-y += termios.h
 header-y += time.h
diff --git a/include/linux/tcp_metrics.h b/include/linux/tcp_metrics.h
new file mode 100644
index 0000000..cb5157b
--- /dev/null
+++ b/include/linux/tcp_metrics.h
@@ -0,0 +1,54 @@
+/* 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 */
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0abe67b..b020135 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/tcp.h>
 #include <linux/hash.h>
+#include <linux/tcp_metrics.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/net_namespace.h>
@@ -17,20 +18,10 @@
 #include <net/ipv6.h>
 #include <net/dst.h>
 #include <net/tcp.h>
+#include <net/genetlink.h>
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
-enum tcp_metric_index {
-	TCP_METRIC_RTT,
-	TCP_METRIC_RTTVAR,
-	TCP_METRIC_SSTHRESH,
-	TCP_METRIC_CWND,
-	TCP_METRIC_REORDERING,
-
-	/* Always last.  */
-	TCP_METRIC_MAX,
-};
-
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -45,8 +36,10 @@ struct tcp_metrics_block {
 	u32				tcpm_ts;
 	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
-	u32				tcpm_vals[TCP_METRIC_MAX];
+	u32				tcpm_vals[TCP_METRIC_MAX + 1];
 	struct tcp_fastopen_metrics	tcpm_fastopen;
+
+	struct rcu_head			rcu_head;
 };
 
 static bool tcp_metric_locked(struct tcp_metrics_block *tm,
@@ -690,6 +683,328 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 	rcu_read_unlock();
 }
 
+static struct genl_family tcp_metrics_nl_family = {
+	.id		= GENL_ID_GENERATE,
+	.hdrsize	= 0,
+	.name		= TCP_METRICS_GENL_NAME,
+	.version	= TCP_METRICS_GENL_VERSION,
+	.maxattr	= TCP_METRICS_ATTR_MAX,
+	.netnsok	= true,
+};
+
+static struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = {
+	[TCP_METRICS_ATTR_ADDR_IPV4]	= { .type = NLA_U32, },
+	[TCP_METRICS_ATTR_ADDR_IPV6]	= { .type = NLA_BINARY,
+					    .len = sizeof(struct in6_addr), },
+	/* Following attributes are not received for GET/DEL,
+	 * we keep them for reference
+	 */
+#if 0
+	[TCP_METRICS_ATTR_AGE]		= { .type = NLA_MSECS, },
+	[TCP_METRICS_ATTR_TW_TSVAL]	= { .type = NLA_U32, },
+	[TCP_METRICS_ATTR_TW_TS_STAMP]	= { .type = NLA_S32, },
+	[TCP_METRICS_ATTR_VALS]		= { .type = NLA_NESTED, },
+	[TCP_METRICS_ATTR_FOPEN_MSS]	= { .type = NLA_U16, },
+	[TCP_METRICS_ATTR_FOPEN_SYN_DROPS]	= { .type = NLA_U16, },
+	[TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS]	= { .type = NLA_MSECS, },
+	[TCP_METRICS_ATTR_FOPEN_COOKIE]	= { .type = NLA_BINARY,
+					    .len = TCP_FASTOPEN_COOKIE_MAX, },
+#endif
+};
+
+/* Add attributes, caller cancels its header on failure */
+static int tcp_metrics_fill_info(struct sk_buff *msg,
+				 struct tcp_metrics_block *tm)
+{
+	struct nlattr *nest;
+	int i;
+
+	switch (tm->tcpm_addr.family) {
+	case AF_INET:
+		if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4,
+				tm->tcpm_addr.addr.a4) < 0)
+			goto nla_put_failure;
+		break;
+	case AF_INET6:
+		if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16,
+			    tm->tcpm_addr.addr.a6) < 0)
+			goto nla_put_failure;
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE,
+			  jiffies - tm->tcpm_stamp) < 0)
+		goto nla_put_failure;
+	if (tm->tcpm_ts_stamp) {
+		if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,
+				(s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)
+			goto nla_put_failure;
+		if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,
+				tm->tcpm_ts) < 0)
+			goto nla_put_failure;
+	}
+
+	{
+		int n = 0;
+
+		nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
+		if (!nest)
+			goto nla_put_failure;
+		for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
+			if (!tm->tcpm_vals[i])
+				continue;
+			if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0)
+				goto nla_put_failure;
+			n++;
+		}
+		if (n)
+			nla_nest_end(msg, nest);
+		else
+			nla_nest_cancel(msg, nest);
+	}
+
+	{
+		struct tcp_fastopen_metrics tfom_copy[1], *tfom;
+		unsigned int seq;
+
+		do {
+			seq = read_seqbegin(&fastopen_seqlock);
+			tfom_copy[0] = tm->tcpm_fastopen;
+		} while (read_seqretry(&fastopen_seqlock, seq));
+
+		tfom = tfom_copy;
+		if (tfom->mss &&
+		    nla_put_u16(msg, TCP_METRICS_ATTR_FOPEN_MSS,
+				tfom->mss) < 0)
+			goto nla_put_failure;
+		if (tfom->syn_loss &&
+		    (nla_put_u16(msg, TCP_METRICS_ATTR_FOPEN_SYN_DROPS,
+				tfom->syn_loss) < 0 ||
+		     nla_put_msecs(msg, TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS,
+				jiffies - tfom->last_syn_loss) < 0))
+			goto nla_put_failure;
+		if (tfom->cookie.len > 0 &&
+		    nla_put(msg, TCP_METRICS_ATTR_FOPEN_COOKIE,
+			    tfom->cookie.len, tfom->cookie.val) < 0)
+			goto nla_put_failure;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int tcp_metrics_dump_info(struct sk_buff *skb,
+				 struct netlink_callback *cb,
+				 struct tcp_metrics_block *tm)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq,
+			  &tcp_metrics_nl_family, NLM_F_MULTI,
+			  TCP_METRICS_CMD_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (tcp_metrics_fill_info(skb, tm) < 0)
+		goto nla_put_failure;
+
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int tcp_metrics_nl_dump(struct sk_buff *skb,
+			       struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
+	unsigned int row, s_row = cb->args[0];
+	int s_col = cb->args[1], col = s_col;
+
+	for (row = s_row; row < max_rows; row++, s_col = 0) {
+		struct tcp_metrics_block *tm;
+		struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash + row;
+
+		rcu_read_lock();
+		for (col = 0, tm = rcu_dereference(hb->chain); tm;
+		     tm = rcu_dereference(tm->tcpm_next), col++) {
+			if (col < s_col)
+				continue;
+			if (tcp_metrics_dump_info(skb, cb, tm) < 0) {
+				rcu_read_unlock();
+				goto done;
+			}
+		}
+		rcu_read_unlock();
+	}
+
+done:
+	cb->args[0] = row;
+	cb->args[1] = col;
+	return skb->len;
+}
+
+static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
+			 unsigned int *hash, int optional)
+{
+	struct nlattr *a;
+
+	a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV4];
+	if (a) {
+		addr->family = AF_INET;
+		addr->addr.a4 = nla_get_be32(a);
+		*hash = (__force unsigned int) addr->addr.a4;
+		return 0;
+	}
+	a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6];
+	if (a) {
+		if (nla_len(a) != sizeof(sizeof(struct in6_addr)))
+			return -EINVAL;
+		addr->family = AF_INET6;
+		memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6));
+		*hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6);
+		return 0;
+	}
+	return optional ? 1 : -EAFNOSUPPORT;
+}
+
+static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct tcp_metrics_block *tm;
+	struct inetpeer_addr addr;
+	unsigned int hash;
+	struct sk_buff *msg;
+	struct net *net = genl_info_net(info);
+	void *reply;
+	int ret;
+
+	ret = parse_nl_addr(info, &addr, &hash, 0);
+	if (ret < 0)
+		return ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	reply = genlmsg_put_reply(msg, info, &tcp_metrics_nl_family, 0,
+				  info->genlhdr->cmd);
+	if (!reply)
+		goto nla_put_failure;
+
+	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	ret = -ESRCH;
+	rcu_read_lock();
+	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
+	     tm = rcu_dereference(tm->tcpm_next)) {
+		if (addr_same(&tm->tcpm_addr, &addr)) {
+			ret = tcp_metrics_fill_info(msg, tm);
+			break;
+		}
+	}
+	rcu_read_unlock();
+	if (ret < 0)
+		goto out_free;
+
+	genlmsg_end(msg, reply);
+	return genlmsg_reply(msg, info);
+
+nla_put_failure:
+	ret = -EMSGSIZE;
+
+out_free:
+	nlmsg_free(msg);
+	return ret;
+}
+
+#define deref_locked_genl(p)	\
+	rcu_dereference_protected(p, lockdep_genl_is_held() && \
+				     lockdep_is_held(&tcp_metrics_lock))
+
+#define deref_genl(p)	rcu_dereference_protected(p, lockdep_genl_is_held())
+
+static int tcp_metrics_flush_all(struct net *net)
+{
+	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
+	struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash;
+	struct tcp_metrics_block *tm;
+	unsigned int sync_count = 0;
+	unsigned int row;
+
+	for (row = 0; row < max_rows; row++, hb++) {
+		spin_lock_bh(&tcp_metrics_lock);
+		tm = deref_locked_genl(hb->chain);
+		if (tm)
+			hb->chain = NULL;
+		spin_unlock_bh(&tcp_metrics_lock);
+		while (tm) {
+			struct tcp_metrics_block *next;
+
+			next = deref_genl(tm->tcpm_next);
+			kfree_rcu(tm, rcu_head);
+			if (!((++sync_count) & 2047))
+				synchronize_rcu();
+			tm = next;
+		}
+	}
+	return 0;
+}
+
+static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct tcpm_hash_bucket *hb;
+	struct tcp_metrics_block *tm;
+	struct tcp_metrics_block __rcu **pp;
+	struct inetpeer_addr addr;
+	unsigned int hash;
+	struct net *net = genl_info_net(info);
+	int ret;
+
+	ret = parse_nl_addr(info, &addr, &hash, 1);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return tcp_metrics_flush_all(net);
+
+	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
+	hb = net->ipv4.tcp_metrics_hash + hash;
+	pp = &hb->chain;
+	spin_lock_bh(&tcp_metrics_lock);
+	for (tm = deref_locked_genl(*pp); tm;
+	     pp = &tm->tcpm_next, tm = deref_locked_genl(*pp)) {
+		if (addr_same(&tm->tcpm_addr, &addr)) {
+			*pp = tm->tcpm_next;
+			break;
+		}
+	}
+	spin_unlock_bh(&tcp_metrics_lock);
+	if (!tm)
+		return -ESRCH;
+	kfree_rcu(tm, rcu_head);
+	return 0;
+}
+
+static struct genl_ops tcp_metrics_nl_ops[] = {
+	{
+		.cmd = TCP_METRICS_CMD_GET,
+		.doit = tcp_metrics_nl_cmd_get,
+		.dumpit = tcp_metrics_nl_dump,
+		.policy = tcp_metrics_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = TCP_METRICS_CMD_DEL,
+		.doit = tcp_metrics_nl_cmd_del,
+		.policy = tcp_metrics_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+};
+
 static unsigned int tcpmhash_entries;
 static int __init set_tcpmhash_entries(char *str)
 {
@@ -753,5 +1068,21 @@ static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
 
 void __init tcp_metrics_init(void)
 {
-	register_pernet_subsys(&tcp_net_metrics_ops);
+	int ret;
+
+	ret = register_pernet_subsys(&tcp_net_metrics_ops);
+	if (ret < 0)
+		goto cleanup;
+	ret = genl_register_family_with_ops(&tcp_metrics_nl_family,
+					    tcp_metrics_nl_ops,
+					    ARRAY_SIZE(tcp_metrics_nl_ops));
+	if (ret < 0)
+		goto cleanup_subsys;
+	return;
+
+cleanup_subsys:
+	unregister_pernet_subsys(&tcp_net_metrics_ops);
+
+cleanup:
+	return;
 }
-- 
1.7.3.4

[PATCH v2 2/2] iproute2: add support for tcp_metrics

[Julian Anastasov]

	ip tcp_metrics/tcpmetrics

v2:
- On flush we should provide the address in req2
- "flush all" should use single del, just like when "all" is not provided
- Explain printed information in man page

Signed-off-by: Julian Anastasov <ja@ssi.bg>
---

diff -urpN iproute2-3.5.1/include/linux/tcp_metrics.h iproute2-3.5.1-tcp_metrics/include/linux/tcp_metrics.h
--- iproute2-3.5.1/include/linux/tcp_metrics.h	1970-01-01 02:00:00.000000000 +0200
+++ iproute2-3.5.1-tcp_metrics/include/linux/tcp_metrics.h	2012-08-23 09:50:54.385569009 +0300
@@ -0,0 +1,54 @@
+/* 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 */
diff -urpN iproute2-3.5.1/ip/Makefile iproute2-3.5.1-tcp_metrics/ip/Makefile
--- iproute2-3.5.1/ip/Makefile	2012-08-13 18:13:58.000000000 +0300
+++ iproute2-3.5.1-tcp_metrics/ip/Makefile	2012-08-23 10:24:01.561660891 +0300
@@ -3,7 +3,7 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o ipr
     ipmaddr.o ipmonitor.o ipmroute.o ipprefix.o iptuntap.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
+    iplink_macvlan.o iplink_macvtap.o ipl2tp.o tcp_metrics.o
 
 RTMONOBJ=rtmon.o
 
diff -urpN iproute2-3.5.1/ip/ip.c iproute2-3.5.1-tcp_metrics/ip/ip.c
--- iproute2-3.5.1/ip/ip.c	2012-08-13 18:13:58.000000000 +0300
+++ iproute2-3.5.1-tcp_metrics/ip/ip.c	2012-08-23 10:21:20.917653464 +0300
@@ -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 | 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 },
diff -urpN iproute2-3.5.1/ip/ip_common.h iproute2-3.5.1-tcp_metrics/ip/ip_common.h
--- iproute2-3.5.1/ip/ip_common.h	2012-08-13 18:13:58.000000000 +0300
+++ iproute2-3.5.1-tcp_metrics/ip/ip_common.h	2012-08-23 10:19:11.005647457 +0300
@@ -42,6 +42,7 @@ extern int do_multirule(int argc, char *
 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)
 {
diff -urpN iproute2-3.5.1/ip/tcp_metrics.c iproute2-3.5.1-tcp_metrics/ip/tcp_metrics.c
--- iproute2-3.5.1/ip/tcp_metrics.c	1970-01-01 02:00:00.000000000 +0200
+++ iproute2-3.5.1-tcp_metrics/ip/tcp_metrics.c	2012-08-25 15:18:31.695944914 +0300
@@ -0,0 +1,504 @@
+/*
+ * tcp_metrics.c	"ip tcp_metrics/tcpmetrics"
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		version 2 as published by the Free Software Foundation;
+ *
+ * Authors:	Julian Anastasov <ja@ssi.bg>, August 2012
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <sys/ioctl.h>
+#include <linux/if.h>
+
+#include <linux/genetlink.h>
+#include <linux/tcp_metrics.h>
+
+#include "utils.h"
+#include "ip_common.h"
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: ip tcp_metrics/tcpmetrics { COMMAND | help }\n");
+	fprintf(stderr, "       ip tcp_metrics { show | flush } SELECTOR\n");
+	fprintf(stderr, "       ip tcp_metrics delete [ address ] ADDRESS\n");
+	fprintf(stderr, "SELECTOR := [ [ address ] PREFIX ]\n");
+	exit(-1);
+}
+
+/* netlink socket */
+static struct rtnl_handle grth = { .fd = -1 };
+static int genl_family = -1;
+
+
+#define GENL_DEFINE_REQUEST(req, hdrsize, bufsiz)			\
+struct {								\
+	struct nlmsghdr		n;					\
+	struct genlmsghdr	g;					\
+	char			buf[NLMSG_ALIGN(hdrsize) + bufsiz];	\
+} req
+
+#define GENL_INIT_REQUEST(req, family, hdrsize, ver, cmd_, flags)	\
+	do {								\
+		memset(&req, 0, sizeof(req));				\
+		req.n.nlmsg_type = family;				\
+		req.n.nlmsg_flags = flags;				\
+		req.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN + hdrsize);	\
+		req.g.cmd = cmd_;					\
+		req.g.version = ver;					\
+	} while (0)
+
+#define INIT_GENL_ACTION(req, cmd, ack)					\
+	GENL_INIT_REQUEST(req, genl_family, 0,				\
+			  TCP_METRICS_GENL_VERSION, cmd,		\
+			  NLM_F_REQUEST | ((ack) ? NLM_F_ACK : 0))
+
+#define INIT_GENL_DUMP(req)						\
+	GENL_INIT_REQUEST(req, genl_family, 0,				\
+			  TCP_METRICS_GENL_VERSION,			\
+			  TCP_METRICS_CMD_GET,				\
+			  NLM_F_DUMP | NLM_F_REQUEST)
+
+#define CMD_LIST	0x0001	/* list, lst, show		*/
+#define CMD_DEL		0x0002	/* delete, remove		*/
+#define CMD_FLUSH	0x0004	/* flush			*/
+
+static struct {
+	char	*name;
+	int	code;
+} cmds[] = {
+	{	"list",		CMD_LIST	},
+	{	"lst",		CMD_LIST	},
+	{	"show",		CMD_LIST	},
+	{	"delete",	CMD_DEL		},
+	{	"remove",	CMD_DEL		},
+	{	"flush",	CMD_FLUSH	},
+};
+
+static char *metric_name[TCP_METRIC_MAX + 1] = {
+	[TCP_METRIC_RTT]		= "rtt",
+	[TCP_METRIC_RTTVAR]		= "rttvar",
+	[TCP_METRIC_SSTHRESH]		= "ssthresh",
+	[TCP_METRIC_CWND]		= "cwnd",
+	[TCP_METRIC_REORDERING]		= "reordering",
+};
+
+static struct
+{
+	int flushed;
+	char *flushb;
+	int flushp;
+	int flushe;
+	int cmd;
+	inet_prefix addr;
+} f;
+
+static int flush_update(void)
+{
+	if (rtnl_send_check(&grth, f.flushb, f.flushp) < 0) {
+		perror("Failed to send flush request\n");
+		return -1;
+	}
+	f.flushp = 0;
+	return 0;
+}
+
+static int process_msg(const struct sockaddr_nl *who, struct nlmsghdr *n,
+		       void *arg)
+{
+	FILE *fp = (FILE *) arg;
+	struct genlmsghdr *ghdr;
+	struct rtattr *attrs[TCP_METRICS_ATTR_MAX + 1], *a;
+	int len = n->nlmsg_len;
+	char abuf[256];
+	inet_prefix addr;
+	int family, i, atype;
+
+	if (n->nlmsg_type != genl_family)
+		return -1;
+
+	len -= NLMSG_LENGTH(GENL_HDRLEN);
+	if (len < 0)
+		return -1;
+
+	ghdr = NLMSG_DATA(n);
+	if (ghdr->cmd != TCP_METRICS_CMD_GET)
+		return 0;
+
+	parse_rtattr(attrs, TCP_METRICS_ATTR_MAX, (void *) ghdr + GENL_HDRLEN,
+		     len);
+
+	a = attrs[TCP_METRICS_ATTR_ADDR_IPV4];
+	if (a) {
+		if (f.addr.family && f.addr.family != AF_INET)
+			return 0;
+		memcpy(&addr.data, RTA_DATA(a), 4);
+		addr.bytelen = 4;
+		family = AF_INET;
+		atype = TCP_METRICS_ATTR_ADDR_IPV4;
+	} else {
+		a = attrs[TCP_METRICS_ATTR_ADDR_IPV6];
+		if (a) {
+			if (f.addr.family && f.addr.family != AF_INET6)
+				return 0;
+			memcpy(&addr.data, RTA_DATA(a), 16);
+			addr.bytelen = 16;
+			family = AF_INET6;
+			atype = TCP_METRICS_ATTR_ADDR_IPV6;
+		} else
+			return 0;
+	}
+
+	if (f.addr.family && f.addr.bitlen >= 0 &&
+	    inet_addr_match(&addr, &f.addr, f.addr.bitlen))
+		return 0;
+
+	if (f.flushb) {
+		struct nlmsghdr *fn;
+		GENL_DEFINE_REQUEST(req2, 0, 128);
+
+		INIT_GENL_ACTION(req2, TCP_METRICS_CMD_DEL, 0);
+		addattr_l(&req2.n, sizeof(req2), atype, &addr.data,
+			  addr.bytelen);
+
+		if (NLMSG_ALIGN(f.flushp) + req2.n.nlmsg_len > f.flushe) {
+			if (flush_update())
+				return -1;
+		}
+		fn = (struct nlmsghdr *) (f.flushb + NLMSG_ALIGN(f.flushp));
+		memcpy(fn, &req2.n, req2.n.nlmsg_len);
+		fn->nlmsg_seq = ++grth.seq;
+		f.flushp = (((char *) fn) + req2.n.nlmsg_len) - f.flushb;
+		f.flushed++;
+		if (show_stats < 2)
+			return 0;
+	}
+
+	if (f.cmd & (CMD_DEL | CMD_FLUSH))
+		fprintf(fp, "Deleted ");
+
+	fprintf(fp, "%s",
+		format_host(family, RTA_PAYLOAD(a), &addr.data,
+			    abuf, sizeof(abuf)));
+
+	a = attrs[TCP_METRICS_ATTR_AGE];
+	if (a) {
+		__u64 val = rta_getattr_u64(a);
+
+		fprintf(fp, " age %llu.%03llusec",
+			val / 1000, val % 1000);
+	}
+
+	a = attrs[TCP_METRICS_ATTR_TW_TS_STAMP];
+	if (a) {
+		__s32 val = (__s32) rta_getattr_u32(a);
+		__u32 tsval;
+
+		a = attrs[TCP_METRICS_ATTR_TW_TSVAL];
+		tsval = a ? rta_getattr_u32(a) : 0;
+		fprintf(fp, " tw_ts %u/%dsec ago", tsval, val);
+	}
+
+	a = attrs[TCP_METRICS_ATTR_VALS];
+	if (a) {
+		struct rtattr *m[TCP_METRIC_MAX + 1 + 1];
+
+		parse_rtattr_nested(m, TCP_METRIC_MAX + 1, a);
+
+		for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
+			__u32 val;
+
+			a = m[i + 1];
+			if (!a)
+				continue;
+			if (metric_name[i])
+				fprintf(fp, " %s ", metric_name[i]);
+			else
+				fprintf(fp, " metric_%d ", i);
+			val = rta_getattr_u32(a);
+			switch (i) {
+			case TCP_METRIC_RTT:
+			case TCP_METRIC_RTTVAR:
+				fprintf(fp, "%ums", val);
+				break;
+			case TCP_METRIC_SSTHRESH:
+			case TCP_METRIC_CWND:
+			case TCP_METRIC_REORDERING:
+			default:
+				fprintf(fp, "%u", val);
+				break;
+			}
+		}
+	}
+
+	a = attrs[TCP_METRICS_ATTR_FOPEN_MSS];
+	if (a)
+		fprintf(fp, " fo_mss %u", rta_getattr_u16(a));
+
+	a = attrs[TCP_METRICS_ATTR_FOPEN_SYN_DROPS];
+	if (a) {
+		__u16 syn_loss = rta_getattr_u16(a);
+		__u64 ts;
+
+		a = attrs[TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS];
+		ts = a ? rta_getattr_u64(a) : 0;
+
+		fprintf(fp, " fo_syn_drops %u/%llu.%03llusec ago",
+			syn_loss, ts / 1000, ts % 1000);
+	}
+
+	a = attrs[TCP_METRICS_ATTR_FOPEN_COOKIE];
+	if (a) {
+		char cookie[32 + 1];
+		unsigned char *ptr = RTA_DATA(a);
+		int i, max = RTA_PAYLOAD(a);
+
+		if (max > 16)
+			max = 16;
+		cookie[0] = 0;
+		for (i = 0; i < max; i++)
+			sprintf(cookie + i + i, "%02x", ptr[i]);
+		fprintf(fp, " fo_cookie %s", cookie);
+	}
+
+	fprintf(fp, "\n");
+
+	fflush(fp);
+	return 0;
+}
+
+static int genl_parse_getfamily(struct nlmsghdr *nlh)
+{
+	struct rtattr *tb[CTRL_ATTR_MAX + 1];
+	struct genlmsghdr *ghdr = NLMSG_DATA(nlh);
+	int len = nlh->nlmsg_len;
+	struct rtattr *attrs;
+
+	if (nlh->nlmsg_type != GENL_ID_CTRL) {
+		fprintf(stderr, "Not a controller message, nlmsg_len=%d "
+			"nlmsg_type=0x%x\n", nlh->nlmsg_len, nlh->nlmsg_type);
+		return -1;
+	}
+
+	if (ghdr->cmd != CTRL_CMD_NEWFAMILY) {
+		fprintf(stderr, "Unknown controller command %d\n", ghdr->cmd);
+		return -1;
+	}
+
+	len -= NLMSG_LENGTH(GENL_HDRLEN);
+
+	if (len < 0) {
+		fprintf(stderr, "wrong controller message len %d\n", len);
+		return -1;
+	}
+
+	attrs = (struct rtattr *) ((char *) ghdr + GENL_HDRLEN);
+	parse_rtattr(tb, CTRL_ATTR_MAX, attrs, len);
+
+	if (tb[CTRL_ATTR_FAMILY_ID] == NULL) {
+		fprintf(stderr, "Missing family id TLV\n");
+		return -1;
+	}
+
+	return rta_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+}
+
+static int genl_ctrl_resolve_family(const char *family)
+{
+	GENL_DEFINE_REQUEST(req, 0, 1024);
+
+	GENL_INIT_REQUEST(req, GENL_ID_CTRL, 0, 0, CTRL_CMD_GETFAMILY,
+			  NLM_F_REQUEST);
+
+	addattr_l(&req.n, 1024, CTRL_ATTR_FAMILY_NAME,
+		  family, strlen(family) + 1);
+
+	if (rtnl_talk(&grth, &req.n, 0, 0, &req.n) < 0) {
+		fprintf(stderr, "Error talking to the kernel\n");
+		return -2;
+	}
+
+	return genl_parse_getfamily(&req.n);
+}
+
+static int tcpm_do_cmd(int cmd, int argc, char **argv)
+{
+	GENL_DEFINE_REQUEST(req, 0, 1024);
+	int atype = -1;
+	int code, ack;
+
+	memset(&f, 0, sizeof(f));
+	f.addr.bitlen = -1;
+	f.addr.family = preferred_family;
+
+	switch (preferred_family) {
+	case AF_UNSPEC:
+	case AF_INET:
+	case AF_INET6:
+		break;
+	default:
+		fprintf(stderr, "Unsupported family:%d\n", preferred_family);
+		return -1;
+	}
+
+	for (; argc > 0; argc--, argv++) {
+		char *who = "address";
+
+		if (strcmp(*argv, "addr") == 0 ||
+		    strcmp(*argv, "address") == 0) {
+			who = *argv;
+			NEXT_ARG();
+		}
+		if (matches(*argv, "help") == 0)
+			usage();
+		if (f.addr.bitlen >= 0)
+			duparg2(who, *argv);
+
+		get_prefix(&f.addr, *argv, preferred_family);
+		if (f.addr.bytelen && f.addr.bytelen * 8 == f.addr.bitlen) {
+			if (f.addr.family == AF_INET)
+				atype = TCP_METRICS_ATTR_ADDR_IPV4;
+			else if (f.addr.family == AF_INET6)
+				atype = TCP_METRICS_ATTR_ADDR_IPV6;
+		}
+		if ((CMD_DEL & cmd) && atype < 0) {
+			fprintf(stderr, "Error: a specific IP address is expected rather than \"%s\"\n",
+				*argv);
+			return -1;
+		}
+
+		argc--; argv++;
+	}
+
+	if (cmd == CMD_DEL && atype < 0)
+		missarg("address");
+
+	/* flush for exact address ? Single del */
+	if (cmd == CMD_FLUSH && atype >= 0)
+		cmd = CMD_DEL;
+	/* flush for all addresses ? Single del without address */
+	if (cmd == CMD_FLUSH && f.addr.bitlen <= 0 &&
+	    preferred_family == AF_UNSPEC) {
+		cmd = CMD_DEL;
+		code = TCP_METRICS_CMD_DEL;
+		ack = 1;
+	} else if (cmd == CMD_DEL) {
+		code = TCP_METRICS_CMD_DEL;
+		ack = 1;
+	} else {	/* CMD_FLUSH, CMD_LIST */
+		code = TCP_METRICS_CMD_GET;
+		ack = 0;
+	}
+
+	if (genl_family < 0) {
+		if (rtnl_open_byproto(&grth, 0, NETLINK_GENERIC) < 0) {
+			fprintf(stderr, "Cannot open generic netlink socket\n");
+			exit(1);
+		}
+		genl_family = genl_ctrl_resolve_family(TCP_METRICS_GENL_NAME);
+		if (genl_family < 0)
+			exit(1);
+	}
+
+	if (!(cmd & CMD_FLUSH) && (atype >= 0 || (cmd & CMD_DEL))) {
+		INIT_GENL_ACTION(req, code, ack);
+		if (atype >= 0)
+			addattr_l(&req.n, sizeof(req), atype, &f.addr.data,
+				  f.addr.bytelen);
+	} else {
+		INIT_GENL_DUMP(req);
+	}
+
+	f.cmd = cmd;
+	if (cmd & CMD_FLUSH) {
+		int round = 0;
+		char flushb[4096-512];
+
+		f.flushb = flushb;
+		f.flushp = 0;
+		f.flushe = sizeof(flushb);
+
+		for (;;) {
+			req.n.nlmsg_seq = grth.dump = ++grth.seq;
+			if (rtnl_send(&grth, &req, req.n.nlmsg_len) < 0) {
+				perror("Failed to send flush request");
+				exit(1);
+			}
+			f.flushed = 0;
+			if (rtnl_dump_filter(&grth, process_msg, stdout) < 0) {
+				fprintf(stderr, "Flush terminated\n");
+				exit(1);
+			}
+			if (f.flushed == 0) {
+				if (round == 0) {
+					fprintf(stderr, "Nothing to flush.\n");
+				} else if (show_stats)
+					printf("*** Flush is complete after %d round%s ***\n",
+					       round, round > 1 ? "s" : "");
+				fflush(stdout);
+				return 0;
+			}
+			round++;
+			if (flush_update() < 0)
+				exit(1);
+			if (show_stats) {
+				printf("\n*** Round %d, deleting %d entries ***\n",
+				       round, f.flushed);
+				fflush(stdout);
+			}
+		}
+		return 0;
+	}
+
+	req.n.nlmsg_seq = ++grth.seq;
+	if (ack) {
+		if (rtnl_talk(&grth, &req.n, 0, 0, NULL) < 0)
+			return -2;
+	} else if (atype >= 0) {
+		if (rtnl_talk(&grth, &req.n, 0, 0, &req.n) < 0)
+			return -2;
+		if (process_msg(NULL, &req.n, stdout) < 0) {
+			fprintf(stderr, "Dump terminated\n");
+			exit(1);
+		}
+	} else {
+		grth.dump = grth.seq;
+		if (rtnl_send(&grth, &req, req.n.nlmsg_len) < 0) {
+			perror("Failed to send dump request");
+			exit(1);
+		}
+
+		if (rtnl_dump_filter(&grth, process_msg, stdout) < 0) {
+			fprintf(stderr, "Dump terminated\n");
+			exit(1);
+		}
+	}
+	return 0;
+}
+
+int do_tcp_metrics(int argc, char **argv)
+{
+	int i;
+
+	if (argc < 1)
+		return tcpm_do_cmd(CMD_LIST, 0, NULL);
+	for (i = 0; i < ARRAY_SIZE(cmds); i++) {
+		if (matches(argv[0], cmds[i].name) == 0)
+			return tcpm_do_cmd(cmds[i].code, argc-1, argv+1);
+	}
+	if (matches(argv[0], "help") == 0)
+		usage();
+
+	fprintf(stderr, "Command \"%s\" is unknown, "
+			"try \"ip tcp_metrics help\".\n", *argv);
+	exit(-1);
+}
+
diff -urpN iproute2-3.5.1/man/man8/Makefile iproute2-3.5.1-tcp_metrics/man/man8/Makefile
--- iproute2-3.5.1/man/man8/Makefile	2012-08-13 18:13:58.000000000 +0300
+++ iproute2-3.5.1-tcp_metrics/man/man8/Makefile	2012-08-23 14:45:12.506385476 +0300
@@ -7,7 +7,8 @@ MAN8PAGES = $(TARGETS) ip.8 arpd.8 lnsta
 	bridge.8 rtstat.8 ctstat.8 nstat.8 routef.8 \
 	ip-tunnel.8 ip-rule.8 ip-ntable.8 \
 	ip-monitor.8 tc-stab.8 tc-hfsc.8 ip-xfrm.8 ip-netns.8 \
-	ip-neighbour.8 ip-mroute.8 ip-maddress.8 ip-addrlabel.8 
+	ip-neighbour.8 ip-mroute.8 ip-maddress.8 ip-addrlabel.8 \
+	ip-tcp_metrics.8
 
 
 all: $(TARGETS)
diff -urpN iproute2-3.5.1/man/man8/ip-tcp_metrics.8 iproute2-3.5.1-tcp_metrics/man/man8/ip-tcp_metrics.8
--- iproute2-3.5.1/man/man8/ip-tcp_metrics.8	1970-01-01 02:00:00.000000000 +0200
+++ iproute2-3.5.1-tcp_metrics/man/man8/ip-tcp_metrics.8	2012-08-25 17:37:30.868321617 +0300
@@ -0,0 +1,143 @@
+.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>" ms
+- RTT metric value
+
+.BI rttvar " <N>" ms
+- 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>
diff -urpN iproute2-3.5.1/man/man8/ip.8 iproute2-3.5.1-tcp_metrics/man/man8/ip.8
--- iproute2-3.5.1/man/man8/ip.8	2012-08-13 18:13:58.000000000 +0300
+++ iproute2-3.5.1-tcp_metrics/man/man8/ip.8	2012-08-23 10:28:12.541672495 +0300
@@ -15,7 +15,7 @@ ip \- show / manipulate routing, devices
 .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
@@ -156,6 +156,10 @@ host addresses.
 - rule in routing policy database.
 
 .TP
+.B tcp_metrics/tcpmetrics
+- manage TCP Metrics
+
+.TP
 .B tunnel
 - tunnel over IP.
 
@@ -215,6 +219,7 @@ was written by Alexey N. Kuznetsov and a
 .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

Re: [PATCH v2 1/2] tcp: add generic netlink support for tcp_metrics

[Eric Dumazet]

On Sun, 2012-09-02 at 08:36 +0300, Julian Anastasov wrote:
> +
> +static int tcp_metrics_flush_all(struct net *net)
> +{
> +	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
> +	struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash;
> +	struct tcp_metrics_block *tm;
> +	unsigned int sync_count = 0;
> +	unsigned int row;
> +
> +	for (row = 0; row < max_rows; row++, hb++) {
> +		spin_lock_bh(&tcp_metrics_lock);
> +		tm = deref_locked_genl(hb->chain);
> +		if (tm)
> +			hb->chain = NULL;
> +		spin_unlock_bh(&tcp_metrics_lock);
> +		while (tm) {
> +			struct tcp_metrics_block *next;
> +
> +			next = deref_genl(tm->tcpm_next);
> +			kfree_rcu(tm, rcu_head);
> +			if (!((++sync_count) & 2047))
> +				synchronize_rcu();
> +			tm = next;
> +		}
> +	}
> +	return 0;
> +}

It looks like the synchronize_rcu() call is not exactly what you wanted,
but then net/ipv4/fib_trie.c has the same mistake.

What we want here is to force pending call_rcu() calls to complete, so
that we dont consume too much memory. So it would probably better to
call rcu_barrier() instead.

If other cpus are idle or outside of rcu read lock sections,
synchronize_rcu() should basically do nothing at all.

But I am not sure its worth the trouble ?

Commit c3059477fce2d956a0bb3e04357324780c5d8eeb (ipv4: Use
synchronize_rcu() during trie_rebalance()) was needed because FIB TRIE
can really use huge amounts of memory, thats hardly the case with
tcp_metrics.

Re: [PATCH v2 1/2] tcp: add generic netlink support for tcp_metrics

[Julian Anastasov]

	Hello,

On Mon, 3 Sep 2012, Eric Dumazet wrote:

> On Sun, 2012-09-02 at 08:36 +0300, Julian Anastasov wrote:
> > +
> > +static int tcp_metrics_flush_all(struct net *net)
> > +{
> > +	unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log;
> > +	struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash;
> > +	struct tcp_metrics_block *tm;
> > +	unsigned int sync_count = 0;
> > +	unsigned int row;
> > +
> > +	for (row = 0; row < max_rows; row++, hb++) {
> > +		spin_lock_bh(&tcp_metrics_lock);
> > +		tm = deref_locked_genl(hb->chain);
> > +		if (tm)
> > +			hb->chain = NULL;
> > +		spin_unlock_bh(&tcp_metrics_lock);
> > +		while (tm) {
> > +			struct tcp_metrics_block *next;
> > +
> > +			next = deref_genl(tm->tcpm_next);
> > +			kfree_rcu(tm, rcu_head);
> > +			if (!((++sync_count) & 2047))
> > +				synchronize_rcu();
> > +			tm = next;
> > +		}
> > +	}
> > +	return 0;
> > +}
> 
> It looks like the synchronize_rcu() call is not exactly what you wanted,
> but then net/ipv4/fib_trie.c has the same mistake.

	I used fib_trie as reference...

> What we want here is to force pending call_rcu() calls to complete, so
> that we dont consume too much memory. So it would probably better to
> call rcu_barrier() instead.

	I see

> If other cpus are idle or outside of rcu read lock sections,
> synchronize_rcu() should basically do nothing at all.
> 
> But I am not sure its worth the trouble ?
> 
> Commit c3059477fce2d956a0bb3e04357324780c5d8eeb (ipv4: Use
> synchronize_rcu() during trie_rebalance()) was needed because FIB TRIE
> can really use huge amounts of memory, thats hardly the case with
> tcp_metrics.

	I was worrying for the case
(TCP_METRICS_RECLAIM_DEPTH + 1) * tcpmhash_entries to be
large, eg. if some non-default value is configured. May be the
chance table to be filled immediately is small. I'll remove it.

	BTW, is it appropriate to use kmem_cache for
metrics and as result call_rcu for freeing?

Regards

--
Julian Anastasov <ja@ssi.bg>

Re: [PATCH v2 1/2] tcp: add generic netlink support for tcp_metrics

[David Miller]

From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 3 Sep 2012 11:22:15 +0300 (EEST)

> 	BTW, is it appropriate to use kmem_cache for
> metrics and as result call_rcu for freeing?

I think it would work as things are implemented currently in
slab/slub/slob, however I would not rely upon it.

If you do move to a SLAB cache for the tcp metrics objects,
you might consider SLAB_DESTROY_BY_RCU.  It's a very delicate
facility (read the huge comment in linux/slab.h) but I think
it provides the semantics we need for TCP metrics blobs.

Looking forward to v3 :-)

Re: [PATCH v2 1/2] tcp: add generic netlink support for tcp_metrics

[Julian Anastasov]

	Hello,

On Tue, 4 Sep 2012, David Miller wrote:

> From: Julian Anastasov <ja@ssi.bg>
> Date: Mon, 3 Sep 2012 11:22:15 +0300 (EEST)
> 
> > 	BTW, is it appropriate to use kmem_cache for
> > metrics and as result call_rcu for freeing?
> 
> I think it would work as things are implemented currently in
> slab/slub/slob, however I would not rely upon it.
> 
> If you do move to a SLAB cache for the tcp metrics objects,
> you might consider SLAB_DESTROY_BY_RCU.  It's a very delicate
> facility (read the huge comment in linux/slab.h) but I think
> it provides the semantics we need for TCP metrics blobs.

	ok, I'll not mix it with the genl support
because I'm not prepared to do it soon...

> Looking forward to v3 :-)

	Sending...

Regards

--
Julian Anastasov <ja@ssi.bg>