netfilter: accounting rework: ct_extend + 64bit counters (v4)

Initially netfilter has had 64bit counters for conntrack-based accounting, but
it was changed in 2.6.14 to save memory. Unfortunately in-kernel 64bit counters are
still required, for example for "connbytes" extension. However, 64bit counters
waste a lot of memory and it was not possible to enable/disable it runtime.

This patch:
 - reimplements accounting with respect to the extension infrastructure,
 - makes one global version of seq_print_acct() instead of two seq_print_counters(),
 - makes it possible to enable it at boot time (for CONFIG_SYSCTL/CONFIG_SYSFS=n),
 - makes it possible to enable/disable it at runtime by sysctl or sysfs,
 - extends counters from 32bit to 64bit,
 - renames ip_conntrack_counter -> nf_conn_counter,
 - enables accounting code unconditionally (no longer depends on CONFIG_NF_CT_ACCT),
 - set initial accounting enable state based on CONFIG_NF_CT_ACCT
 - removes buggy IPCT_COUNTER_FILLING event handling.

If accounting is enabled newly created connections get additional acct extend.
Old connections are not changed as it is not possible to add a ct_extend area
to confirmed conntrack. Accounting is performed for all connections with
acct extend regardless of a current state of "net.netfilter.nf_conntrack_acct".

Signed-off-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 170 insertions, 54 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 316c7af..ee898e7 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -49,6 +49,15 @@ config NF_CT_ACCT
 	  Those counters can be used for flow-based accounting or the
 	  `connbytes' match.
 
+	  Please note that currently this option only sets a default state.
+	  You may change it at boot time with nf_conntrack.acct=0/1 kernel
+	  paramater or by loading the nf_conntrack module with acct=0/1.
+
+	  You may also disable/enable it on a running system with:
+	   sysctl net.netfilter.nf_conntrack_acct=0/1
+
+	  This option will be removed in 2.6.29.
+
 	  If unsure, say `N'.
 
 config NF_CONNTRACK_MARK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 5c4b183..3bd2cc5 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,6 +1,6 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
 
-nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o
+nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
new file mode 100644
index 0000000..59bd8b9
--- /dev/null
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -0,0 +1,104 @@
+/* Accouting handling for netfilter. */
+
+/*
+ * (C) 2008 Krzysztof Piotr Oledzki <ole@ans.pl>
+ *
+ * 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.
+ */
+
+#include <linux/netfilter.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_acct.h>
+
+#ifdef CONFIG_NF_CT_ACCT
+#define NF_CT_ACCT_DEFAULT 1
+#else
+#define NF_CT_ACCT_DEFAULT 0
+#endif
+
+int nf_ct_acct __read_mostly = NF_CT_ACCT_DEFAULT;
+EXPORT_SYMBOL_GPL(nf_ct_acct);
+
+module_param_named(acct, nf_ct_acct, bool, 0644);
+MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting.");
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_header *acct_sysctl_header;
+static struct ctl_table acct_sysctl_table[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "nf_conntrack_acct",
+		.data		= &nf_ct_acct,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{}
+};
+#endif /* CONFIG_SYSCTL */
+
+unsigned int
+seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
+{
+	struct nf_conn_counter *acct;
+
+	acct = nf_conn_acct_find(ct);
+	if (!acct)
+		return 0;
+
+	return seq_printf(s, "packets=%llu bytes=%llu ",
+			  (unsigned long long)acct[dir].packets,
+			  (unsigned long long)acct[dir].bytes);
+};
+EXPORT_SYMBOL_GPL(seq_print_acct);
+
+static struct nf_ct_ext_type acct_extend __read_mostly = {
+	.len	= sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]),
+	.align	= __alignof__(struct nf_conn_counter[IP_CT_DIR_MAX]),
+	.id	= NF_CT_EXT_ACCT,
+};
+
+int nf_conntrack_acct_init(void)
+{
+	int ret;
+
+#ifdef CONFIG_NF_CT_ACCT
+	printk(KERN_WARNING "CONFIG_NF_CT_ACCT is deprecated and will be removed soon. Plase use\n");
+	printk(KERN_WARNING "nf_conntrack.acct=1 kernel paramater, acct=1 nf_conntrack module option or\n");
+	printk(KERN_WARNING "sysctl net.netfilter.nf_conntrack_acct=1 to enable it.\n");
+#endif
+
+	ret = nf_ct_extend_register(&acct_extend);
+	if (ret < 0) {
+		printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n");
+		return ret;
+	}
+
+#ifdef CONFIG_SYSCTL
+	acct_sysctl_header = register_sysctl_paths(nf_net_netfilter_sysctl_path,
+				acct_sysctl_table);
+
+	if (!acct_sysctl_header) {
+		nf_ct_extend_unregister(&acct_extend);
+
+		printk(KERN_ERR "nf_conntrack_acct: can't register to sysctl.\n");
+		return -ENOMEM;
+	}
+#endif
+
+	return 0;
+}
+
+void nf_conntrack_acct_fini(void)
+{
+#ifdef CONFIG_SYSCTL
+	unregister_sysctl_table(acct_sysctl_header);
+#endif
+	nf_ct_extend_unregister(&acct_extend);
+}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 28d03e6..c519d09 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -37,6 +37,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 
 #define NF_CONNTRACK_VERSION	"0.5.0"
 
@@ -555,6 +556,8 @@ init_conntrack(const struct nf_conntrack_tuple *tuple,
 		return NULL;
 	}
 
+	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+
 	spin_lock_bh(&nf_conntrack_lock);
 	exp = nf_ct_find_expectation(tuple);
 	if (exp) {
@@ -828,17 +831,16 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 	}
 
 acct:
-#ifdef CONFIG_NF_CT_ACCT
 	if (do_acct) {
-		ct->counters[CTINFO2DIR(ctinfo)].packets++;
-		ct->counters[CTINFO2DIR(ctinfo)].bytes +=
-			skb->len - skb_network_offset(skb);
+		struct nf_conn_counter *acct;
 
-		if ((ct->counters[CTINFO2DIR(ctinfo)].packets & 0x80000000)
-		    || (ct->counters[CTINFO2DIR(ctinfo)].bytes & 0x80000000))
-			event |= IPCT_COUNTER_FILLING;
+		acct = nf_conn_acct_find(ct);
+		if (acct) {
+			acct[CTINFO2DIR(ctinfo)].packets++;
+			acct[CTINFO2DIR(ctinfo)].bytes +=
+				skb->len - skb_network_offset(skb);
+		}
 	}
-#endif
 
 	spin_unlock_bh(&nf_conntrack_lock);
 
@@ -853,15 +855,19 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       int do_acct)
 {
-#ifdef CONFIG_NF_CT_ACCT
 	if (do_acct) {
+		struct nf_conn_counter *acct;
+
 		spin_lock_bh(&nf_conntrack_lock);
-		ct->counters[CTINFO2DIR(ctinfo)].packets++;
-		ct->counters[CTINFO2DIR(ctinfo)].bytes +=
-			skb->len - skb_network_offset(skb);
+		acct = nf_conn_acct_find(ct);
+		if (acct) {
+			acct[CTINFO2DIR(ctinfo)].packets++;
+			acct[CTINFO2DIR(ctinfo)].bytes +=
+				skb->len - skb_network_offset(skb);
+		}
 		spin_unlock_bh(&nf_conntrack_lock);
 	}
-#endif
+
 	if (del_timer(&ct->timeout)) {
 		ct->timeout.function((unsigned long)ct);
 		return true;
@@ -1029,6 +1035,7 @@ void nf_conntrack_cleanup(void)
 	nf_conntrack_proto_fini();
 	nf_conntrack_helper_fini();
 	nf_conntrack_expect_fini();
+	nf_conntrack_acct_fini();
 }
 
 struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced)
@@ -1168,6 +1175,10 @@ int __init nf_conntrack_init(void)
 	if (ret < 0)
 		goto out_fini_expect;
 
+	ret = nf_conntrack_acct_init();
+	if (ret < 0)
+		goto out_fini_helper;
+
 	/* For use by REJECT target */
 	rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach);
 	rcu_assign_pointer(nf_ct_destroy, destroy_conntrack);
@@ -1180,6 +1191,8 @@ int __init nf_conntrack_init(void)
 
 	return ret;
 
+out_fini_helper:
+	nf_conntrack_helper_fini();
 out_fini_expect:
 	nf_conntrack_expect_fini();
 out_fini_proto:
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 95a7967..105a616 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -37,6 +37,7 @@
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_protocol.h>
@@ -206,22 +207,26 @@ nla_put_failure:
 	return -1;
 }
 
-#ifdef CONFIG_NF_CT_ACCT
 static int
 ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
 			enum ip_conntrack_dir dir)
 {
 	enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
 	struct nlattr *nest_count;
+	const struct nf_conn_counter *acct;
+
+	acct = nf_conn_acct_find(ct);
+	if (!acct)
+		return 0;
 
 	nest_count = nla_nest_start(skb, type | NLA_F_NESTED);
 	if (!nest_count)
 		goto nla_put_failure;
 
-	NLA_PUT_BE32(skb, CTA_COUNTERS32_PACKETS,
-		     htonl(ct->counters[dir].packets));
-	NLA_PUT_BE32(skb, CTA_COUNTERS32_BYTES,
-		     htonl(ct->counters[dir].bytes));
+	NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS,
+		     cpu_to_be64(acct[dir].packets));
+	NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES,
+		     cpu_to_be64(acct[dir].bytes));
 
 	nla_nest_end(skb, nest_count);
 
@@ -230,9 +235,6 @@ ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
 nla_put_failure:
 	return -1;
 }
-#else
-#define ctnetlink_dump_counters(a, b, c) (0)
-#endif
 
 #ifdef CONFIG_NF_CONNTRACK_MARK
 static inline int
@@ -501,11 +503,6 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
 			goto nla_put_failure;
 #endif
 
-		if (events & IPCT_COUNTER_FILLING &&
-		    (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
-		     ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0))
-			goto nla_put_failure;
-
 		if (events & IPCT_RELATED &&
 		    ctnetlink_dump_master(skb, ct) < 0)
 			goto nla_put_failure;
@@ -576,11 +573,15 @@ restart:
 				cb->args[1] = (unsigned long)ct;
 				goto out;
 			}
-#ifdef CONFIG_NF_CT_ACCT
+
 			if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) ==
-						IPCTNL_MSG_CT_GET_CTRZERO)
-				memset(&ct->counters, 0, sizeof(ct->counters));
-#endif
+						IPCTNL_MSG_CT_GET_CTRZERO) {
+				struct nf_conn_counter *acct;
+
+				acct = nf_conn_acct_find(ct);
+				if (acct)
+					memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]));
+			}
 		}
 		if (cb->args[1]) {
 			cb->args[1] = 0;
@@ -832,14 +833,9 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
-	if (nlh->nlmsg_flags & NLM_F_DUMP) {
-#ifndef CONFIG_NF_CT_ACCT
-		if (NFNL_MSG_TYPE(nlh->nlmsg_type) == IPCTNL_MSG_CT_GET_CTRZERO)
-			return -ENOTSUPP;
-#endif
+	if (nlh->nlmsg_flags & NLM_F_DUMP)
 		return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table,
 					  ctnetlink_done);
-	}
 
 	if (cda[CTA_TUPLE_ORIG])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
@@ -1152,6 +1148,8 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 			goto err;
 	}
 
+	nf_ct_acct_ext_add(ct, GFP_KERNEL);
+
 #if defined(CONFIG_NF_CONNTRACK_MARK)
 	if (cda[CTA_MARK])
 		ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 46ea542..869ef93 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -25,6 +25,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 
 MODULE_LICENSE("GPL");
 
@@ -38,19 +39,6 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
 }
 EXPORT_SYMBOL_GPL(print_tuple);
 
-#ifdef CONFIG_NF_CT_ACCT
-static unsigned int
-seq_print_counters(struct seq_file *s,
-		   const struct ip_conntrack_counter *counter)
-{
-	return seq_printf(s, "packets=%llu bytes=%llu ",
-			  (unsigned long long)counter->packets,
-			  (unsigned long long)counter->bytes);
-}
-#else
-#define seq_print_counters(x, y)	0
-#endif
-
 struct ct_iter_state {
 	unsigned int bucket;
 };
@@ -146,7 +134,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 			l3proto, l4proto))
 		return -ENOSPC;
 
-	if (seq_print_counters(s, &ct->counters[IP_CT_DIR_ORIGINAL]))
+	if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
 		return -ENOSPC;
 
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
@@ -157,7 +145,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 			l3proto, l4proto))
 		return -ENOSPC;
 
-	if (seq_print_counters(s, &ct->counters[IP_CT_DIR_REPLY]))
+	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		return -ENOSPC;
 
 	if (test_bit(IPS_ASSURED_BIT, &ct->status))
diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c
index d7e8983..3e39c4f 100644
--- a/net/netfilter/xt_connbytes.c
+++ b/net/netfilter/xt_connbytes.c
@@ -8,6 +8,7 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_connbytes.h>
 #include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_acct.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
@@ -27,12 +28,15 @@ connbytes_mt(const struct sk_buff *skb, const struct net_device *in,
 	u_int64_t what = 0;	/* initialize to make gcc happy */
 	u_int64_t bytes = 0;
 	u_int64_t pkts = 0;
-	const struct ip_conntrack_counter *counters;
+	const struct nf_conn_counter *counters;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (!ct)
 		return false;
-	counters = ct->counters;
+
+	counters = nf_conn_acct_find(ct);
+	if (!counters)
+		return false;
 
 	switch (sinfo->what) {
 	case XT_CONNBYTES_PKTS: