netfilter: add cttimeout infrastructure for fine timeout tuning

This patch adds the infrastructure to add fine timeout tuning
over nfnetlink. Now you can use the NFNL_SUBSYS_CTNETLINK_TIMEOUT
subsystem to create/delete/dump timeout objects that contain some
specific timeout policy for one flow.

The follow up patches will allow you attach timeout policy object
to conntrack via the CT target and the conntrack extension
infrastructure.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 127 insertions, 0 deletions

diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 8372bb43feb00..361eade62a09e 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1244,6 +1244,113 @@ static int tcp_nlattr_tuple_size(void)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_cttimeout.h>
+
+static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data)
+{
+	unsigned int *timeouts = data;
+	int i;
+
+	/* set default TCP timeouts. */
+	for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++)
+		timeouts[i] = tcp_timeouts[i];
+
+	if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) {
+		timeouts[TCP_CONNTRACK_SYN_SENT] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) {
+		timeouts[TCP_CONNTRACK_SYN_RECV] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_ESTABLISHED]) {
+		timeouts[TCP_CONNTRACK_ESTABLISHED] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_ESTABLISHED]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_FIN_WAIT]) {
+		timeouts[TCP_CONNTRACK_FIN_WAIT] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_FIN_WAIT]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]) {
+		timeouts[TCP_CONNTRACK_CLOSE_WAIT] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_LAST_ACK]) {
+		timeouts[TCP_CONNTRACK_LAST_ACK] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_LAST_ACK]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_TIME_WAIT]) {
+		timeouts[TCP_CONNTRACK_TIME_WAIT] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_TIME_WAIT]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_CLOSE]) {
+		timeouts[TCP_CONNTRACK_CLOSE] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_SYN_SENT2]) {
+		timeouts[TCP_CONNTRACK_SYN_SENT2] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT2]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_RETRANS]) {
+		timeouts[TCP_CONNTRACK_RETRANS] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_RETRANS]))*HZ;
+	}
+	if (tb[CTA_TIMEOUT_TCP_UNACK]) {
+		timeouts[TCP_CONNTRACK_UNACK] =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ;
+	}
+	return 0;
+}
+
+static int
+tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
+{
+	const unsigned int *timeouts = data;
+
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT,
+			htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_RECV,
+			htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_ESTABLISHED,
+			htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_FIN_WAIT,
+			htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT,
+			htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_LAST_ACK,
+			htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_TIME_WAIT,
+			htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE,
+			htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT2,
+			htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_RETRANS,
+			htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ));
+	NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_UNACK,
+			htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ));
+	return 0;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
+static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = {
+	[CTA_TIMEOUT_TCP_SYN_SENT]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_SYN_RECV]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_ESTABLISHED]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_FIN_WAIT]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_CLOSE_WAIT]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_LAST_ACK]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_TIME_WAIT]	= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_CLOSE]		= { .type = NLA_U32 },
+	[CTA_TIMEOUT_TCP_SYN_SENT2]	= { .type = NLA_U32 },
+};
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+
 #ifdef CONFIG_SYSCTL
 static unsigned int tcp_sysctl_table_users;
 static struct ctl_table_header *tcp_sysctl_header;
@@ -1462,6 +1569,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
 	.nlattr_tuple_size	= tcp_nlattr_tuple_size,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+	.ctnl_timeout		= {
+		.nlattr_to_obj	= tcp_timeout_nlattr_to_obj,
+		.obj_to_nlattr	= tcp_timeout_obj_to_nlattr,
+		.nlattr_max	= CTA_TIMEOUT_TCP_MAX,
+		.obj_size	= sizeof(unsigned int) *
+					TCP_CONNTRACK_TIMEOUT_MAX,
+		.nla_policy	= tcp_timeout_nla_policy,
+	},
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
 #ifdef CONFIG_SYSCTL
 	.ctl_table_users	= &tcp_sysctl_table_users,
 	.ctl_table_header	= &tcp_sysctl_header,
@@ -1495,6 +1612,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
 	.nlattr_tuple_size	= tcp_nlattr_tuple_size,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+	.ctnl_timeout		= {
+		.nlattr_to_obj	= tcp_timeout_nlattr_to_obj,
+		.obj_to_nlattr	= tcp_timeout_obj_to_nlattr,
+		.nlattr_max	= CTA_TIMEOUT_TCP_MAX,
+		.obj_size	= sizeof(unsigned int) *
+					TCP_CONNTRACK_TIMEOUT_MAX,
+		.nla_policy	= tcp_timeout_nla_policy,
+	},
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
 #ifdef CONFIG_SYSCTL
 	.ctl_table_users	= &tcp_sysctl_table_users,
 	.ctl_table_header	= &tcp_sysctl_header,