From f1c722295e029eace7960fc687efd5afd67dc555 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Wed, 15 Dec 2010 22:58:53 +0100
Subject: netfilter: xtables: use guarded types

We are supposed to use the kernel's own types in userspace exports.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_CT.h          | 10 +++++-----
 include/linux/netfilter/xt_TCPOPTSTRIP.h |  2 +-
 include/linux/netfilter/xt_TPROXY.h      |  8 ++++----
 include/linux/netfilter/xt_cluster.h     |  8 ++++----
 include/linux/netfilter/xt_quota.h       |  6 +++---
 include/linux/netfilter/xt_time.h        | 14 +++++++-------
 include/linux/netfilter/xt_u32.h         | 16 ++++++++--------
 7 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index 1b564106891d..fbf4c5658554 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -4,11 +4,11 @@
 #define XT_CT_NOTRACK	0x1
 
 struct xt_ct_target_info {
-	u_int16_t	flags;
-	u_int16_t	zone;
-	u_int32_t	ct_events;
-	u_int32_t	exp_events;
-	char		helper[16];
+	__u16 flags;
+	__u16 zone;
+	__u32 ct_events;
+	__u32 exp_events;
+	char helper[16];
 
 	/* Used internally by the kernel */
 	struct nf_conn	*ct __attribute__((aligned(8)));
diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h
index 2db543214ff5..342ef14b1761 100644
--- a/include/linux/netfilter/xt_TCPOPTSTRIP.h
+++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h
@@ -7,7 +7,7 @@
 	(((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0)
 
 struct xt_tcpoptstrip_target_info {
-	u_int32_t strip_bmap[8];
+	__u32 strip_bmap[8];
 };
 
 #endif /* _XT_TCPOPTSTRIP_H */
diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h
index 3f3d69361289..8097e0b4c15e 100644
--- a/include/linux/netfilter/xt_TPROXY.h
+++ b/include/linux/netfilter/xt_TPROXY.h
@@ -5,15 +5,15 @@
  * redirection. We can get rid of that whenever we get support for
  * mutliple targets in the same rule. */
 struct xt_tproxy_target_info {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	__be32 laddr;
 	__be16 lport;
 };
 
 struct xt_tproxy_target_info_v1 {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	union nf_inet_addr laddr;
 	__be16 lport;
 };
diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h
index 886682656f09..66cfa3c782ac 100644
--- a/include/linux/netfilter/xt_cluster.h
+++ b/include/linux/netfilter/xt_cluster.h
@@ -6,10 +6,10 @@ enum xt_cluster_flags {
 };
 
 struct xt_cluster_match_info {
-	u_int32_t		total_nodes;
-	u_int32_t		node_mask;
-	u_int32_t		hash_seed;
-	u_int32_t		flags;
+	__u32 total_nodes;
+	__u32 node_mask;
+	__u32 hash_seed;
+	__u32 flags;
 };
 
 #define XT_CLUSTER_NODES_MAX	32
diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h
index b0d28c659ab7..8bda65f0bc92 100644
--- a/include/linux/netfilter/xt_quota.h
+++ b/include/linux/netfilter/xt_quota.h
@@ -9,9 +9,9 @@ enum xt_quota_flags {
 struct xt_quota_priv;
 
 struct xt_quota_info {
-	u_int32_t		flags;
-	u_int32_t		pad;
-	aligned_u64		quota;
+	__u32 flags;
+	__u32 pad;
+	aligned_u64 quota;
 
 	/* Used internally by the kernel */
 	struct xt_quota_priv	*master;
diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h
index 14b6df412c9f..b8bd4568efdb 100644
--- a/include/linux/netfilter/xt_time.h
+++ b/include/linux/netfilter/xt_time.h
@@ -2,13 +2,13 @@
 #define _XT_TIME_H 1
 
 struct xt_time_info {
-	u_int32_t date_start;
-	u_int32_t date_stop;
-	u_int32_t daytime_start;
-	u_int32_t daytime_stop;
-	u_int32_t monthdays_match;
-	u_int8_t weekdays_match;
-	u_int8_t flags;
+	__u32 date_start;
+	__u32 date_stop;
+	__u32 daytime_start;
+	__u32 daytime_stop;
+	__u32 monthdays_match;
+	__u8 weekdays_match;
+	__u8 flags;
 };
 
 enum {
diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h
index 9947f56cdbdd..e8c3d8722bae 100644
--- a/include/linux/netfilter/xt_u32.h
+++ b/include/linux/netfilter/xt_u32.h
@@ -9,13 +9,13 @@ enum xt_u32_ops {
 };
 
 struct xt_u32_location_element {
-	u_int32_t number;
-	u_int8_t nextop;
+	__u32 number;
+	__u8 nextop;
 };
 
 struct xt_u32_value_element {
-	u_int32_t min;
-	u_int32_t max;
+	__u32 min;
+	__u32 max;
 };
 
 /*
@@ -27,14 +27,14 @@ struct xt_u32_value_element {
 struct xt_u32_test {
 	struct xt_u32_location_element location[XT_U32_MAXSIZE+1];
 	struct xt_u32_value_element value[XT_U32_MAXSIZE+1];
-	u_int8_t nnums;
-	u_int8_t nvalues;
+	__u8 nnums;
+	__u8 nvalues;
 };
 
 struct xt_u32 {
 	struct xt_u32_test tests[XT_U32_MAXSIZE+1];
-	u_int8_t ntests;
-	u_int8_t invert;
+	__u8 ntests;
+	__u8 invert;
 };
 
 #endif /* _XT_U32_H */
-- 
cgit v1.2.3-71-gd317


From 5df15196a2bbf16ca4c6a797ec00ff36d0d5c179 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Sun, 26 Dec 2010 10:22:22 +0100
Subject: netfilter: xt_comment: drop unneeded unsigned qualifier

Since a string is stored, and not something like a MAC address that
would rely on (un)signedness, drop the qualifier.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_comment.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h
index eacfedc6b5d0..0ea5e79f5bd7 100644
--- a/include/linux/netfilter/xt_comment.h
+++ b/include/linux/netfilter/xt_comment.h
@@ -4,7 +4,7 @@
 #define XT_MAX_COMMENT_LEN 256
 
 struct xt_comment_info {
-	unsigned char comment[XT_MAX_COMMENT_LEN];
+	char comment[XT_MAX_COMMENT_LEN];
 };
 
 #endif /* XT_COMMENT_H */
-- 
cgit v1.2.3-71-gd317


From b017900aac4a158b9bf7ffdcb8a369a91115b3e4 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Wed, 15 Dec 2010 09:46:26 +0100
Subject: netfilter: xt_conntrack: support matching on port ranges

Add a new revision 3 that contains port ranges for all of origsrc,
origdst, replsrc and repldst. The high ports are appended to the
original v2 data structure to allow sharing most of the code with
v1 and v2. Use of the revision specific port matching function is
made dependant on par->match->revision.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_conntrack.h | 15 +++++++
 net/netfilter/xt_conntrack.c           | 75 +++++++++++++++++++++++++++++++++-
 2 files changed, 88 insertions(+), 2 deletions(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h
index 54f47a2f6152..74b904d8f99c 100644
--- a/include/linux/netfilter/xt_conntrack.h
+++ b/include/linux/netfilter/xt_conntrack.h
@@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 {
 	__u16 state_mask, status_mask;
 };
 
+struct xt_conntrack_mtinfo3 {
+	union nf_inet_addr origsrc_addr, origsrc_mask;
+	union nf_inet_addr origdst_addr, origdst_mask;
+	union nf_inet_addr replsrc_addr, replsrc_mask;
+	union nf_inet_addr repldst_addr, repldst_mask;
+	__u32 expires_min, expires_max;
+	__u16 l4proto;
+	__u16 origsrc_port, origdst_port;
+	__u16 replsrc_port, repldst_port;
+	__u16 match_flags, invert_flags;
+	__u16 state_mask, status_mask;
+	__u16 origsrc_port_high, origdst_port_high;
+	__u16 replsrc_port_high, repldst_port_high;
+};
+
 #endif /*_XT_CONNTRACK_H*/
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index e536710ad916..4ef1b63ad73f 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -112,6 +112,54 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
 	return true;
 }
 
+static inline bool
+port_match(u16 min, u16 max, u16 port, bool invert)
+{
+	return (port >= min && port <= max) ^ invert;
+}
+
+static inline bool
+ct_proto_port_check_v3(const struct xt_conntrack_mtinfo3 *info,
+		       const struct nf_conn *ct)
+{
+	const struct nf_conntrack_tuple *tuple;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+	if ((info->match_flags & XT_CONNTRACK_PROTO) &&
+	    (nf_ct_protonum(ct) == info->l4proto) ^
+	    !(info->invert_flags & XT_CONNTRACK_PROTO))
+		return false;
+
+	/* Shortcut to match all recognized protocols by using ->src.all. */
+	if ((info->match_flags & XT_CONNTRACK_ORIGSRC_PORT) &&
+	    !port_match(info->origsrc_port, info->origsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_ORIGDST_PORT) &&
+	    !port_match(info->origdst_port, info->origdst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGDST_PORT))
+		return false;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLSRC_PORT) &&
+	    !port_match(info->replsrc_port, info->replsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLDST_PORT) &&
+	    !port_match(info->repldst_port, info->repldst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLDST_PORT))
+		return false;
+
+	return true;
+}
+
 static bool
 conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
              u16 state_mask, u16 status_mask)
@@ -170,8 +218,13 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 		    !(info->invert_flags & XT_CONNTRACK_REPLDST))
 			return false;
 
-	if (!ct_proto_port_check(info, ct))
-		return false;
+	if (par->match->revision != 3) {
+		if (!ct_proto_port_check(info, ct))
+			return false;
+	} else {
+		if (!ct_proto_port_check_v3(par->matchinfo, ct))
+			return false;
+	}
 
 	if ((info->match_flags & XT_CONNTRACK_STATUS) &&
 	    (!!(status_mask & ct->status) ^
@@ -207,6 +260,14 @@ conntrack_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
 }
 
+static bool
+conntrack_mt_v3(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_conntrack_mtinfo3 *info = par->matchinfo;
+
+	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
+}
+
 static int conntrack_mt_check(const struct xt_mtchk_param *par)
 {
 	int ret;
@@ -244,6 +305,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.destroy    = conntrack_mt_destroy,
 		.me         = THIS_MODULE,
 	},
+	{
+		.name       = "conntrack",
+		.revision   = 3,
+		.family     = NFPROTO_UNSPEC,
+		.matchsize  = sizeof(struct xt_conntrack_mtinfo3),
+		.match      = conntrack_mt_v3,
+		.checkentry = conntrack_mt_check,
+		.destroy    = conntrack_mt_destroy,
+		.me         = THIS_MODULE,
+	},
 };
 
 static int __init conntrack_mt_init(void)
-- 
cgit v1.2.3-71-gd317


From 255d0dc34068a976550ce555e153c0bfcfec7cc6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 18 Dec 2010 18:35:15 +0100
Subject: netfilter: x_table: speedup compat operations

One iptables invocation with 135000 rules takes 35 seconds of cpu time
on a recent server, using a 32bit distro and a 64bit kernel.

We eventually trigger NMI/RCU watchdog.

INFO: rcu_sched_state detected stall on CPU 3 (t=6000 jiffies)

COMPAT mode has quadratic behavior and consume 16 bytes of memory per
rule.

Switch the xt_compat algos to use an array instead of list, and use a
binary search to locate an offset in the sorted array.

This halves memory need (8 bytes per rule), and removes quadratic
behavior [ O(N*N) -> O(N*log2(N)) ]

Time of iptables goes from 35 s to 150 ms.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h |  3 +-
 net/bridge/netfilter/ebtables.c    |  1 +
 net/ipv4/netfilter/arp_tables.c    |  2 +
 net/ipv4/netfilter/ip_tables.c     |  2 +
 net/ipv6/netfilter/ip6_tables.c    |  2 +
 net/netfilter/x_tables.c           | 82 ++++++++++++++++++++++----------------
 6 files changed, 57 insertions(+), 35 deletions(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 742bec051440..0f04d985b41c 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -611,8 +611,9 @@ struct _compat_xt_align {
 extern void xt_compat_lock(u_int8_t af);
 extern void xt_compat_unlock(u_int8_t af);
 
-extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta);
+extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
 extern void xt_compat_flush_offsets(u_int8_t af);
+extern void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 extern int xt_compat_match_offset(const struct xt_match *match);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 16df0532d4b9..5f1825df9dca 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info,
 
 	newinfo->entries_size = size;
 
+	xt_compat_init_offsets(AF_INET, info->nentries);
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
 }
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3fac340a28d5..47e5178b998b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -883,6 +883,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(NFPROTO_ARP, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1350,6 +1351,7 @@ static int translate_compat_table(const char *name,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
+	xt_compat_init_offsets(NFPROTO_ARP, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a846d633b3b6..c5a75d70970f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1080,6 +1080,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1681,6 +1682,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
+	xt_compat_init_offsets(AF_INET, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 455582384ece..0c9973a657fb 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1093,6 +1093,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET6, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1696,6 +1697,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
+	xt_compat_init_offsets(AF_INET6, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 80463507420e..ee5de3af510a 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -38,9 +38,8 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
 #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
 
 struct compat_delta {
-	struct compat_delta *next;
-	unsigned int offset;
-	int delta;
+	unsigned int offset; /* offset in kernel */
+	int delta; /* delta in 32bit user land */
 };
 
 struct xt_af {
@@ -49,7 +48,9 @@ struct xt_af {
 	struct list_head target;
 #ifdef CONFIG_COMPAT
 	struct mutex compat_mutex;
-	struct compat_delta *compat_offsets;
+	struct compat_delta *compat_tab;
+	unsigned int number; /* number of slots in compat_tab[] */
+	unsigned int cur; /* number of used slots in compat_tab[] */
 #endif
 };
 
@@ -414,54 +415,67 @@ int xt_check_match(struct xt_mtchk_param *par,
 EXPORT_SYMBOL_GPL(xt_check_match);
 
 #ifdef CONFIG_COMPAT
-int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta)
+int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
-	struct compat_delta *tmp;
+	struct xt_af *xp = &xt[af];
 
-	tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
+	if (!xp->compat_tab) {
+		if (!xp->number)
+			return -EINVAL;
+		xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number);
+		if (!xp->compat_tab)
+			return -ENOMEM;
+		xp->cur = 0;
+	}
 
-	tmp->offset = offset;
-	tmp->delta = delta;
+	if (xp->cur >= xp->number)
+		return -EINVAL;
 
-	if (xt[af].compat_offsets) {
-		tmp->next = xt[af].compat_offsets->next;
-		xt[af].compat_offsets->next = tmp;
-	} else {
-		xt[af].compat_offsets = tmp;
-		tmp->next = NULL;
-	}
+	if (xp->cur)
+		delta += xp->compat_tab[xp->cur - 1].delta;
+	xp->compat_tab[xp->cur].offset = offset;
+	xp->compat_tab[xp->cur].delta = delta;
+	xp->cur++;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_add_offset);
 
 void xt_compat_flush_offsets(u_int8_t af)
 {
-	struct compat_delta *tmp, *next;
-
-	if (xt[af].compat_offsets) {
-		for (tmp = xt[af].compat_offsets; tmp; tmp = next) {
-			next = tmp->next;
-			kfree(tmp);
-		}
-		xt[af].compat_offsets = NULL;
+	if (xt[af].compat_tab) {
+		vfree(xt[af].compat_tab);
+		xt[af].compat_tab = NULL;
+		xt[af].number = 0;
 	}
 }
 EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);
 
 int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
 {
-	struct compat_delta *tmp;
-	int delta;
-
-	for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next)
-		if (tmp->offset < offset)
-			delta += tmp->delta;
-	return delta;
+	struct compat_delta *tmp = xt[af].compat_tab;
+	int mid, left = 0, right = xt[af].cur - 1;
+
+	while (left <= right) {
+		mid = (left + right) >> 1;
+		if (offset > tmp[mid].offset)
+			left = mid + 1;
+		else if (offset < tmp[mid].offset)
+			right = mid - 1;
+		else
+			return mid ? tmp[mid - 1].delta : 0;
+	}
+	WARN_ON_ONCE(1);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
 
+void xt_compat_init_offsets(u_int8_t af, unsigned int number)
+{
+	xt[af].number = number;
+	xt[af].cur = 0;
+}
+EXPORT_SYMBOL(xt_compat_init_offsets);
+
 int xt_compat_match_offset(const struct xt_match *match)
 {
 	u_int16_t csize = match->compatsize ? : match->matchsize;
@@ -1337,7 +1351,7 @@ static int __init xt_init(void)
 		mutex_init(&xt[i].mutex);
 #ifdef CONFIG_COMPAT
 		mutex_init(&xt[i].compat_mutex);
-		xt[i].compat_offsets = NULL;
+		xt[i].compat_tab = NULL;
 #endif
 		INIT_LIST_HEAD(&xt[i].target);
 		INIT_LIST_HEAD(&xt[i].match);
-- 
cgit v1.2.3-71-gd317


From 43f393caec0362abe03c72799d3f342af3973070 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@infradead.org>
Date: Sun, 16 Jan 2011 18:10:28 +0100
Subject: netfilter: audit target to record accepted/dropped packets

This patch adds a new netfilter target which creates audit records
for packets traversing a certain chain.

It can be used to record packets which are rejected administraively
as follows:

  -N AUDIT_DROP
  -A AUDIT_DROP -j AUDIT --type DROP
  -A AUDIT_DROP -j DROP

a rule which would typically drop or reject a packet would then
invoke the new chain to record packets before dropping them.

  -j AUDIT_DROP

The module is protocol independant and works for iptables, ip6tables
and ebtables.

The following information is logged:
 - netfilter hook
 - packet length
 - incomming/outgoing interface
 - MAC src/dst/proto for ethernet packets
 - src/dst/protocol address for IPv4/IPv6
 - src/dst port for TCP/UDP/UDPLITE
 - icmp type/code

Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/audit.h              |   1 +
 include/linux/netfilter/Kbuild     |   1 +
 include/linux/netfilter/xt_AUDIT.h |  30 ++++++
 net/netfilter/Kconfig              |  10 ++
 net/netfilter/Makefile             |   1 +
 net/netfilter/xt_AUDIT.c           | 204 +++++++++++++++++++++++++++++++++++++
 6 files changed, 247 insertions(+)
 create mode 100644 include/linux/netfilter/xt_AUDIT.h
 create mode 100644 net/netfilter/xt_AUDIT.c

(limited to 'include/linux/netfilter')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 8b5c0620abf9..ae227dfcf9c6 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -103,6 +103,7 @@
 #define AUDIT_BPRM_FCAPS	1321	/* Information about fcaps increasing perms */
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
+#define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9d40effe7ca7..9f11fbc377e2 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -9,6 +9,7 @@ header-y += nfnetlink_conntrack.h
 header-y += nfnetlink_log.h
 header-y += nfnetlink_queue.h
 header-y += x_tables.h
+header-y += xt_AUDIT.h
 header-y += xt_CHECKSUM.h
 header-y += xt_CLASSIFY.h
 header-y += xt_CONNMARK.h
diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h
new file mode 100644
index 000000000000..38751d2ea52b
--- /dev/null
+++ b/include/linux/netfilter/xt_AUDIT.h
@@ -0,0 +1,30 @@
+/*
+ * Header file for iptables xt_AUDIT target
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * 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.
+ */
+
+#ifndef _XT_AUDIT_TARGET_H
+#define _XT_AUDIT_TARGET_H
+
+#include <linux/types.h>
+
+enum {
+	XT_AUDIT_TYPE_ACCEPT = 0,
+	XT_AUDIT_TYPE_DROP,
+	XT_AUDIT_TYPE_REJECT,
+	__XT_AUDIT_TYPE_MAX,
+};
+
+#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1)
+
+struct xt_audit_info {
+	__u8 type; /* XT_AUDIT_TYPE_* */
+};
+
+#endif /* _XT_AUDIT_TARGET_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1b79353a5d29..93918f022555 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -326,6 +326,16 @@ config NETFILTER_XT_CONNMARK
 
 comment "Xtables targets"
 
+config NETFILTER_XT_TARGET_AUDIT
+	tristate "AUDIT target support"
+	depends on AUDIT
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option adds a 'AUDIT' target, which can be used to create
+	  audit records for packets dropped/accepted.
+
+	  To compileit as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_TARGET_CHECKSUM
 	tristate "CHECKSUM target support"
 	depends on IP_NF_MANGLE || IP6_NF_MANGLE
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 441050f31111..401d574bdfd2 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
 
 # targets
+obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
new file mode 100644
index 000000000000..81802d27346e
--- /dev/null
+++ b/net/netfilter/xt_AUDIT.c
@@ -0,0 +1,204 @@
+/*
+ * Creates audit record for dropped/accepted packets
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * 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.
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/audit.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_AUDIT.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>");
+MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets");
+MODULE_ALIAS("ipt_AUDIT");
+MODULE_ALIAS("ip6t_AUDIT");
+MODULE_ALIAS("ebt_AUDIT");
+MODULE_ALIAS("arpt_AUDIT");
+
+static void audit_proto(struct audit_buffer *ab, struct sk_buff *skb,
+			unsigned int proto, unsigned int offset)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE: {
+		const __be16 *pptr;
+		__be16 _ports[2];
+
+		pptr = skb_header_pointer(skb, offset, sizeof(_ports), _ports);
+		if (pptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " sport=%hu dport=%hu",
+				 ntohs(pptr[0]), ntohs(pptr[1]));
+		}
+		break;
+
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6: {
+		const u8 *iptr;
+		u8 _ih[2];
+
+		iptr = skb_header_pointer(skb, offset, sizeof(_ih), &_ih);
+		if (iptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " icmptype=%hhu icmpcode=%hhu",
+				 iptr[0], iptr[1]);
+
+		}
+		break;
+	}
+}
+
+static void audit_ip4(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct iphdr _iph;
+	const struct iphdr *ih;
+
+	ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	audit_log_format(ab, " saddr=%pI4 daddr=%pI4 ipid=%hu proto=%hhu",
+		&ih->saddr, &ih->daddr, ntohs(ih->id), ih->protocol);
+
+	if (ntohs(ih->frag_off) & IP_OFFSET) {
+		audit_log_format(ab, " frag=1");
+		return;
+	}
+
+	audit_proto(ab, skb, ih->protocol, ih->ihl * 4);
+}
+
+static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct ipv6hdr _ip6h;
+	const struct ipv6hdr *ih;
+	u8 nexthdr;
+	int offset;
+
+	ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	nexthdr = ih->nexthdr;
+	offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
+				  &nexthdr);
+
+	audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
+			 &ih->saddr, &ih->daddr, nexthdr);
+
+	if (offset)
+		audit_proto(ab, skb, nexthdr, offset);
+}
+
+static unsigned int
+audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
+	if (ab == NULL)
+		goto errout;
+
+	audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s",
+			 info->type, par->hooknum, skb->len,
+			 par->in ? par->in->name : "?",
+			 par->out ? par->out->name : "?");
+
+	if (skb->mark)
+		audit_log_format(ab, " mark=%#x", skb->mark);
+
+	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+		audit_log_format(ab, " smac=%pM dmac=%pM macproto=0x%04x",
+				 eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+				 ntohs(eth_hdr(skb)->h_proto));
+
+		if (par->family == NFPROTO_BRIDGE) {
+			switch (eth_hdr(skb)->h_proto) {
+			case __constant_htons(ETH_P_IP):
+				audit_ip4(ab, skb);
+				break;
+
+			case __constant_htons(ETH_P_IPV6):
+				audit_ip6(ab, skb);
+				break;
+			}
+		}
+	}
+
+	switch (par->family) {
+	case NFPROTO_IPV4:
+		audit_ip4(ab, skb);
+		break;
+
+	case NFPROTO_IPV6:
+		audit_ip6(ab, skb);
+		break;
+	}
+
+	audit_log_end(ab);
+
+errout:
+	return XT_CONTINUE;
+}
+
+static int audit_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+
+	if (info->type > XT_AUDIT_TYPE_MAX) {
+		pr_info("Audit type out of range (valid range: 0..%hhu)\n",
+			XT_AUDIT_TYPE_MAX);
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static struct xt_target audit_tg_reg __read_mostly = {
+	.name		= "AUDIT",
+	.family		= NFPROTO_UNSPEC,
+	.target		= audit_tg,
+	.targetsize	= sizeof(struct xt_audit_info),
+	.checkentry	= audit_tg_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init audit_tg_init(void)
+{
+	return xt_register_target(&audit_tg_reg);
+}
+
+static void __exit audit_tg_exit(void)
+{
+	xt_unregister_target(&audit_tg_reg);
+}
+
+module_init(audit_tg_init);
+module_exit(audit_tg_exit);
-- 
cgit v1.2.3-71-gd317


From 0b8ad876275c74e4bfb6ec3150793f3c0ecfcee2 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Tue, 18 Jan 2011 11:23:06 +0100
Subject: netfilter: xtables: add missing header files to export list

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/Kbuild | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9f11fbc377e2..fc4e0aa805a2 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,6 +56,8 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
+header-y += xt_secmark.h
+header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
 header-y += xt_string.h
-- 
cgit v1.2.3-71-gd317


From 94b27cc36123069966616670c3653cd6873babe9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Jan 2011 16:08:30 +0100
Subject: netfilter: allow NFQUEUE bypass if no listener is available

If an skb is to be NF_QUEUE'd, but no program has opened the queue, the
packet is dropped.

This adds a v2 target revision of xt_NFQUEUE that allows packets to
continue through the ruleset instead.

Because the actual queueing happens outside of the target context, the
'bypass' flag has to be communicated back to the netfilter core.

Unfortunately the only choice to do this without adding a new function
argument is to use the target function return value (i.e. the verdict).

In the NF_QUEUE case, the upper 16bit already contain the queue number
to use.  The previous patch reduced NF_VERDICT_MASK to 0xff, i.e.
we now have extra room for a new flag.

If a hook issued a NF_QUEUE verdict, then the netfilter core will
continue packet processing if the queueing hook
returns -ESRCH (== "this queue does not exist") and the new
NF_VERDICT_FLAG_QUEUE_BYPASS flag is set in the verdict value.

Note: If the queue exists, but userspace does not consume packets fast
enough, the skb will still be dropped.

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h            |  1 +
 include/linux/netfilter/xt_NFQUEUE.h |  6 ++++++
 net/netfilter/core.c                 |  3 +++
 net/netfilter/nf_queue.c             |  7 ++++++-
 net/netfilter/xt_NFQUEUE.c           | 28 +++++++++++++++++++++++++---
 5 files changed, 41 insertions(+), 4 deletions(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 78b73cc10216..eeec00abb664 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -29,6 +29,7 @@
 #define NF_VERDICT_MASK 0x000000ff
 
 /* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS	0x00008000
 
 /* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h
index 2584f4a777de..9eafdbbb401c 100644
--- a/include/linux/netfilter/xt_NFQUEUE.h
+++ b/include/linux/netfilter/xt_NFQUEUE.h
@@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 {
 	__u16 queues_total;
 };
 
+struct xt_NFQ_info_v2 {
+	__u16 queuenum;
+	__u16 queues_total;
+	__u16 bypass;
+};
+
 #endif /* _XT_NFQ_TARGET_H */
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 4d88e45b978e..1e00bf7d27c5 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -184,6 +184,9 @@ next_hook:
 		if (ret < 0) {
 			if (ret == -ECANCELED)
 				goto next_hook;
+			if (ret == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		ret = 0;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index ce1150d4a3f2..5ab22e2bbd7d 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -138,8 +138,10 @@ static int __nf_queue(struct sk_buff *skb,
 	rcu_read_lock();
 
 	qh = rcu_dereference(queue_handler[pf]);
-	if (!qh)
+	if (!qh) {
+		status = -ESRCH;
 		goto err_unlock;
+	}
 
 	afinfo = nf_get_afinfo(pf);
 	if (!afinfo)
@@ -303,6 +305,9 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
+			if (err == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		break;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 39627706aac6..d4f4b5d66b20 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -83,9 +83,20 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	return NF_QUEUE_NR(queue);
 }
 
-static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
+static unsigned int
+nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
+	unsigned int ret = nfqueue_tg_v1(skb, par);
+
+	if (info->bypass)
+		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
+	return ret;
+}
+
+static int nfqueue_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
 	u32 maxid;
 
 	if (unlikely(!rnd_inited)) {
@@ -102,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
 		       info->queues_total, maxid);
 		return -ERANGE;
 	}
+	if (par->target->revision == 2 && info->bypass > 1)
+		return -EINVAL;
 	return 0;
 }
 
@@ -117,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = {
 		.name		= "NFQUEUE",
 		.revision	= 1,
 		.family		= NFPROTO_UNSPEC,
-		.checkentry	= nfqueue_tg_v1_check,
+		.checkentry	= nfqueue_tg_check,
 		.target		= nfqueue_tg_v1,
 		.targetsize	= sizeof(struct xt_NFQ_info_v1),
 		.me		= THIS_MODULE,
 	},
+	{
+		.name		= "NFQUEUE",
+		.revision	= 2,
+		.family		= NFPROTO_UNSPEC,
+		.checkentry	= nfqueue_tg_check,
+		.target		= nfqueue_tg_v2,
+		.targetsize	= sizeof(struct xt_NFQ_info_v2),
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init nfqueue_tg_init(void)
-- 
cgit v1.2.3-71-gd317


From 93557f53e1fbd9e2b6574ab0a9b5852628fde9e3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 18 Jan 2011 18:12:24 +0100
Subject: netfilter: nf_conntrack: nf_conntrack snmp helper

Adding support for SNMP broadcast connection tracking. The SNMP
broadcast requests are now paired with the SNMP responses.
Thus allowing using SNMP broadcasts with firewall enabled.

Please refer to the following conversation:
http://marc.info/?l=netfilter-devel&m=125992205006600&w=2

Patrick McHardy wrote:
> > The best solution would be to add generic broadcast tracking, the
> > use of expectations for this is a bit of abuse.
> > The second best choice I guess would be to move the help() function
> > to a shared module and generalize it so it can be used for both.
This patch implements the "second best choice".

Since the netbios-ns conntrack module uses the same helper
functionality as the snmp, only one helper function is added
for both snmp and netbios-ns modules into the new object -
nf_conntrack_broadcast.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nf_conntrack_snmp.h |  9 ++++
 include/net/netfilter/nf_conntrack_helper.h |  6 +++
 net/ipv4/netfilter/Kconfig                  |  3 +-
 net/ipv4/netfilter/nf_nat_snmp_basic.c      |  9 ++--
 net/netfilter/Kconfig                       | 19 +++++++
 net/netfilter/Makefile                      |  2 +
 net/netfilter/nf_conntrack_broadcast.c      | 82 +++++++++++++++++++++++++++++
 net/netfilter/nf_conntrack_netbios_ns.c     | 74 ++++----------------------
 net/netfilter/nf_conntrack_snmp.c           | 77 +++++++++++++++++++++++++++
 9 files changed, 211 insertions(+), 70 deletions(-)
 create mode 100644 include/linux/netfilter/nf_conntrack_snmp.h
 create mode 100644 net/netfilter/nf_conntrack_broadcast.c
 create mode 100644 net/netfilter/nf_conntrack_snmp.c

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h
new file mode 100644
index 000000000000..064bc63a5346
--- /dev/null
+++ b/include/linux/netfilter/nf_conntrack_snmp.h
@@ -0,0 +1,9 @@
+#ifndef _NF_CONNTRACK_SNMP_H
+#define _NF_CONNTRACK_SNMP_H
+
+extern int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo);
+
+#endif /* _NF_CONNTRACK_SNMP_H */
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 32c305dbdab6..f1c1311adc2c 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 extern int nf_conntrack_helper_init(void);
 extern void nf_conntrack_helper_fini(void);
 
+extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				       unsigned int protoff,
+				       struct nf_conn *ct,
+				       enum ip_conntrack_info ctinfo,
+				       unsigned int timeout);
+
 #endif /*_NF_CONNTRACK_HELPER_H*/
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index babd1a2bae5f..f926a310075d 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT
 
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT
 	depends on NETFILTER_ADVANCED
+	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
 
 	  This module implements an Application Layer Gateway (ALG) for
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index ee5f419d0a56..8812a02078ab 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -54,6 +54,7 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <linux/netfilter/nf_conntrack_snmp.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
@@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void)
 {
 	int ret = 0;
 
-	ret = nf_conntrack_helper_register(&snmp_helper);
-	if (ret < 0)
-		return ret;
+	BUG_ON(nf_nat_snmp_hook != NULL);
+	rcu_assign_pointer(nf_nat_snmp_hook, help);
+
 	ret = nf_conntrack_helper_register(&snmp_trap_helper);
 	if (ret < 0) {
 		nf_conntrack_helper_unregister(&snmp_helper);
@@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void)
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
-	nf_conntrack_helper_unregister(&snmp_helper);
+	rcu_assign_pointer(nf_nat_snmp_hook, NULL);
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e2480bddbfd5..939b504604c2 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -185,9 +185,13 @@ config NF_CONNTRACK_IRC
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_BROADCAST
+	tristate
+
 config NF_CONNTRACK_NETBIOS_NS
 	tristate "NetBIOS name service protocol support"
 	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
 	help
 	  NetBIOS name service requests are sent as broadcast messages from an
 	  unprivileged port and responded to with unicast messages to the
@@ -204,6 +208,21 @@ config NF_CONNTRACK_NETBIOS_NS
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_SNMP
+	tristate "SNMP service protocol support"
+	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
+	help
+	  SNMP service requests are sent as broadcast messages from an
+	  unprivileged port and responded to with unicast messages to the
+	  same port. This make them hard to firewall properly because connection
+	  tracking doesn't deal with broadcasts. This helper tracks locally
+	  originating SNMP service requests and the corresponding
+	  responses. It relies on correct IP address configuration, specifically
+	  netmask and broadcast address.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NF_CONNTRACK_PPTP
 	tristate "PPtP protocol support"
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 401d574bdfd2..2c2628de9d3f 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -28,7 +28,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o
 obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
 obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o
 obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o
+obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o
 obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o
+obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o
 obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o
 obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
new file mode 100644
index 000000000000..4e99cca61612
--- /dev/null
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -0,0 +1,82 @@
+/*
+ *      broadcast connection tracking helper
+ *
+ *      (c) 2005 Patrick McHardy <kaber@trash.net>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <net/route.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int timeout)
+{
+	struct nf_conntrack_expect *exp;
+	struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt = skb_rtable(skb);
+	struct in_device *in_dev;
+	struct nf_conn_help *help = nfct_help(ct);
+	__be32 mask = 0;
+
+	/* we're only interested in locally generated packets */
+	if (skb->sk == NULL)
+		goto out;
+	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
+		goto out;
+	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
+		goto out;
+
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(rt->dst.dev);
+	if (in_dev != NULL) {
+		for_primary_ifa(in_dev) {
+			if (ifa->ifa_broadcast == iph->daddr) {
+				mask = ifa->ifa_mask;
+				break;
+			}
+		} endfor_ifa(in_dev);
+	}
+	rcu_read_unlock();
+
+	if (mask == 0)
+		goto out;
+
+	exp = nf_ct_expect_alloc(ct);
+	if (exp == NULL)
+		goto out;
+
+	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+	exp->tuple.src.u.udp.port = help->helper->tuple.src.u.udp.port;
+
+	exp->mask.src.u3.ip       = mask;
+	exp->mask.src.u.udp.port  = htons(0xFFFF);
+
+	exp->expectfn             = NULL;
+	exp->flags                = NF_CT_EXPECT_PERMANENT;
+	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
+	exp->helper               = NULL;
+
+	nf_ct_expect_related(exp);
+	nf_ct_expect_put(exp);
+
+	nf_ct_refresh(ct, skb, timeout * HZ);
+out:
+	return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help);
+
+MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index aadde018a072..4c8f30a3d6d2 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -18,14 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/if_addr.h>
 #include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <net/route.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -40,75 +33,26 @@ MODULE_ALIAS("ip_conntrack_netbios_ns");
 MODULE_ALIAS_NFCT_HELPER("netbios_ns");
 
 static unsigned int timeout __read_mostly = 3;
-module_param(timeout, uint, 0400);
+module_param(timeout, uint, S_IRUSR);
 MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
 
-static int help(struct sk_buff *skb, unsigned int protoff,
-		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
-{
-	struct nf_conntrack_expect *exp;
-	struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt = skb_rtable(skb);
-	struct in_device *in_dev;
-	__be32 mask = 0;
-
-	/* we're only interested in locally generated packets */
-	if (skb->sk == NULL)
-		goto out;
-	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
-		goto out;
-	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
-		goto out;
-
-	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(rt->dst.dev);
-	if (in_dev != NULL) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_broadcast == iph->daddr) {
-				mask = ifa->ifa_mask;
-				break;
-			}
-		} endfor_ifa(in_dev);
-	}
-	rcu_read_unlock();
-
-	if (mask == 0)
-		goto out;
-
-	exp = nf_ct_expect_alloc(ct);
-	if (exp == NULL)
-		goto out;
-
-	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-	exp->tuple.src.u.udp.port = htons(NMBD_PORT);
-
-	exp->mask.src.u3.ip       = mask;
-	exp->mask.src.u.udp.port  = htons(0xFFFF);
-
-	exp->expectfn             = NULL;
-	exp->flags                = NF_CT_EXPECT_PERMANENT;
-	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
-	exp->helper               = NULL;
-
-	nf_ct_expect_related(exp);
-	nf_ct_expect_put(exp);
-
-	nf_ct_refresh(ct, skb, timeout * HZ);
-out:
-	return NF_ACCEPT;
-}
-
 static struct nf_conntrack_expect_policy exp_policy = {
 	.max_expected	= 1,
 };
 
+static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
+		   struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+}
+
 static struct nf_conntrack_helper helper __read_mostly = {
 	.name			= "netbios-ns",
-	.tuple.src.l3num	= AF_INET,
+	.tuple.src.l3num	= NFPROTO_IPV4,
 	.tuple.src.u.udp.port	= cpu_to_be16(NMBD_PORT),
 	.tuple.dst.protonum	= IPPROTO_UDP,
 	.me			= THIS_MODULE,
-	.help			= help,
+	.help			= netbios_ns_help,
 	.expect_policy		= &exp_policy,
 };
 
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
new file mode 100644
index 000000000000..6e545e26289e
--- /dev/null
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -0,0 +1,77 @@
+/*
+ *      SNMP service broadcast connection tracking helper
+ *
+ *      (c) 2011 Jiri Olsa <jolsa@redhat.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/in.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+#define SNMP_PORT	161
+
+MODULE_AUTHOR("Jiri Olsa <jolsa@redhat.com>");
+MODULE_DESCRIPTION("SNMP service broadcast connection tracking helper");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFCT_HELPER("snmp");
+
+static unsigned int timeout __read_mostly = 30;
+module_param(timeout, uint, S_IRUSR);
+MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
+
+int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+			unsigned int protoff,
+			struct nf_conn *ct,
+			enum ip_conntrack_info ctinfo);
+EXPORT_SYMBOL_GPL(nf_nat_snmp_hook);
+
+static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff,
+		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	typeof(nf_nat_snmp_hook) nf_nat_snmp;
+
+	nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+
+	nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook);
+	if (nf_nat_snmp && ct->status & IPS_NAT_MASK)
+		return nf_nat_snmp(skb, protoff, ct, ctinfo);
+
+	return NF_ACCEPT;
+}
+
+static struct nf_conntrack_expect_policy exp_policy = {
+	.max_expected	= 1,
+};
+
+static struct nf_conntrack_helper helper __read_mostly = {
+	.name			= "snmp",
+	.tuple.src.l3num	= NFPROTO_IPV4,
+	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
+	.tuple.dst.protonum	= IPPROTO_UDP,
+	.me			= THIS_MODULE,
+	.help			= snmp_conntrack_help,
+	.expect_policy		= &exp_policy,
+};
+
+static int __init nf_conntrack_snmp_init(void)
+{
+	exp_policy.timeout = timeout;
+	return nf_conntrack_helper_register(&helper);
+}
+
+static void __exit nf_conntrack_snmp_fini(void)
+{
+	nf_conntrack_helper_unregister(&helper);
+}
+
+module_init(nf_conntrack_snmp_init);
+module_exit(nf_conntrack_snmp_fini);
-- 
cgit v1.2.3-71-gd317


From a992ca2a0498edd22a88ac8c41570f536de29c9e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 19 Jan 2011 16:00:07 +0100
Subject: netfilter: nf_conntrack_tstamp: add flow-based timestamp extension

This patch adds flow-based timestamping for conntracks. This
conntrack extension is disabled by default. Basically, we use
two 64-bits variables to store the creation timestamp once the
conntrack has been confirmed and the other to store the deletion
time. This extension is disabled by default, to enable it, you
have to:

echo 1 > /proc/sys/net/netfilter/nf_conntrack_timestamp

This patch allows to save memory for user-space flow-based
loogers such as ulogd2. In short, ulogd2 does not need to
keep a hashtable with the conntrack in user-space to know
when they were created and destroyed, instead we use the
kernel timestamp. If we want to have a sane IPFIX implementation
in user-space, this nanosecs resolution timestamps are also
useful. Other custom user-space applications can benefit from
this via libnetfilter_conntrack.

This patch modifies the /proc output to display the delta time
in seconds since the flow start. You can also obtain the
flow-start date by means of the conntrack-tools.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nfnetlink_conntrack.h  |   9 ++
 include/net/netfilter/nf_conntrack_extend.h    |   4 +
 include/net/netfilter/nf_conntrack_timestamp.h |  53 +++++++++++
 include/net/netns/conntrack.h                  |   2 +
 net/netfilter/Kconfig                          |  11 +++
 net/netfilter/Makefile                         |   1 +
 net/netfilter/nf_conntrack_core.c              |  26 ++++++
 net/netfilter/nf_conntrack_netlink.c           |  46 +++++++++-
 net/netfilter/nf_conntrack_standalone.c        |  41 +++++++++
 net/netfilter/nf_conntrack_timestamp.c         | 120 +++++++++++++++++++++++++
 10 files changed, 312 insertions(+), 1 deletion(-)
 create mode 100644 include/net/netfilter/nf_conntrack_timestamp.h
 create mode 100644 net/netfilter/nf_conntrack_timestamp.c

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 19711e3ffd42..debf1aefd753 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -42,6 +42,7 @@ enum ctattr_type {
 	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
 	CTA_SECCTX,
+	CTA_TIMESTAMP,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -127,6 +128,14 @@ enum ctattr_counters {
 };
 #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
 
+enum ctattr_tstamp {
+	CTA_TIMESTAMP_UNSPEC,
+	CTA_TIMESTAMP_START,
+	CTA_TIMESTAMP_STOP,
+	__CTA_TIMESTAMP_MAX
+};
+#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1)
+
 enum ctattr_nat {
 	CTA_NAT_UNSPEC,
 	CTA_NAT_MINIP,
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 1a9f96db3798..2dcf31703acb 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -16,6 +16,9 @@ enum nf_ct_ext_id {
 #endif
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	NF_CT_EXT_TSTAMP,
 #endif
 	NF_CT_EXT_NUM,
 };
@@ -25,6 +28,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
+#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
new file mode 100644
index 000000000000..f17dcb664e29
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -0,0 +1,53 @@
+#ifndef _NF_CONNTRACK_TSTAMP_H
+#define _NF_CONNTRACK_TSTAMP_H
+
+#include <net/net_namespace.h>
+#include <linux/netfilter/nf_conntrack_common.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+
+struct nf_conn_tstamp {
+	u_int64_t start;
+	u_int64_t stop;
+};
+
+static inline
+struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP);
+#else
+	return NULL;
+#endif
+}
+
+static inline
+struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	struct net *net = nf_ct_net(ct);
+
+	if (!net->ct.sysctl_tstamp)
+		return NULL;
+
+	return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp);
+#else
+	return NULL;
+#endif
+};
+
+static inline bool nf_ct_tstamp_enabled(struct net *net)
+{
+	return net->ct.sysctl_tstamp != 0;
+}
+
+static inline void nf_ct_set_tstamp(struct net *net, bool enable)
+{
+	net->ct.sysctl_tstamp = enable;
+}
+
+extern int nf_conntrack_tstamp_init(struct net *net);
+extern void nf_conntrack_tstamp_fini(struct net *net);
+
+#endif /* _NF_CONNTRACK_TSTAMP_H */
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 5cf8a8c141aa..341eb089349e 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -21,11 +21,13 @@ struct netns_ct {
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;
+	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;
+	struct ctl_table_header	*tstamp_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
 #endif
 	char			*slabname;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 939b504604c2..faf7412ea453 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS
 
 	  If unsure, say `N'.
 
+config NF_CONNTRACK_TIMESTAMP
+	bool  'Connection tracking timestamping'
+	depends on NETFILTER_ADVANCED
+	help
+	  This option enables support for connection tracking timestamping.
+	  This allows you to store the flow start-time and to obtain
+	  the flow-stop time (once it has been destroyed) via Connection
+	  tracking events.
+
+	  If unsure, say `N'.
+
 config NF_CT_PROTO_DCCP
 	tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)'
 	depends on EXPERIMENTAL
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 2c2628de9d3f..9ae6878a85b1 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,6 +1,7 @@
 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_acct.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f47ac67e1bfe..1909311c392a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -43,6 +43,7 @@
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
 
@@ -282,6 +283,11 @@ EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
 static void death_by_timeout(unsigned long ul_conntrack)
 {
 	struct nf_conn *ct = (void *)ul_conntrack;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	if (!test_bit(IPS_DYING_BIT, &ct->status) &&
 	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
@@ -419,6 +425,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
+	struct nf_conn_tstamp *tstamp;
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
@@ -488,6 +495,14 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	atomic_inc(&ct->ct_general.use);
 	ct->status |= IPS_CONFIRMED;
 
+	/* set conntrack timestamp, if enabled. */
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		if (skb->tstamp.tv64 == 0)
+			__net_timestamp((struct sk_buff *)skb);
+
+		tstamp->start = ktime_to_ns(skb->tstamp);
+	}
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
 	 * guarantee that no other CPU can find the conntrack before the above
@@ -746,6 +761,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 
 	ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
 	nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
@@ -1186,6 +1202,11 @@ struct __nf_ct_flush_report {
 static int kill_report(struct nf_conn *i, void *data)
 {
 	struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(i);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	/* If we fail to deliver the event, death_by_timeout() will retry */
 	if (nf_conntrack_event_report(IPCT_DESTROY, i,
@@ -1497,6 +1518,9 @@ static int nf_conntrack_init_net(struct net *net)
 	ret = nf_conntrack_acct_init(net);
 	if (ret < 0)
 		goto err_acct;
+	ret = nf_conntrack_tstamp_init(net);
+	if (ret < 0)
+		goto err_tstamp;
 	ret = nf_conntrack_ecache_init(net);
 	if (ret < 0)
 		goto err_ecache;
@@ -1504,6 +1528,8 @@ static int nf_conntrack_init_net(struct net *net)
 	return 0;
 
 err_ecache:
+	nf_conntrack_tstamp_fini(net);
+err_tstamp:
 	nf_conntrack_acct_fini(net);
 err_acct:
 	nf_conntrack_expect_fini(net);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9eabaa6f28a8..715d56c85475 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -42,6 +42,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_protocol.h>
@@ -230,6 +231,33 @@ nla_put_failure:
 	return -1;
 }
 
+static int
+ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct)
+{
+	struct nlattr *nest_count;
+	const struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (!tstamp)
+		return 0;
+
+	nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED);
+	if (!nest_count)
+		goto nla_put_failure;
+
+	NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start));
+	if (tstamp->stop != 0) {
+		NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP,
+			     cpu_to_be64(tstamp->stop));
+	}
+	nla_nest_end(skb, nest_count);
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 #ifdef CONFIG_NF_CONNTRACK_MARK
 static inline int
 ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct)
@@ -404,6 +432,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	    ctnetlink_dump_timeout(skb, ct) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+	    ctnetlink_dump_timestamp(skb, ct) < 0 ||
 	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_mark(skb, ct) < 0 ||
@@ -470,6 +499,18 @@ ctnetlink_secctx_size(const struct nf_conn *ct)
 #endif
 }
 
+static inline size_t
+ctnetlink_timestamp_size(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP))
+		return 0;
+	return nla_total_size(0) + 2 * nla_total_size(sizeof(uint64_t));
+#else
+	return 0;
+#endif
+}
+
 static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
 {
@@ -481,6 +522,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
 	       + ctnetlink_counters_size(ct)
+	       + ctnetlink_timestamp_size(ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
 	       + nla_total_size(0) /* CTA_PROTOINFO */
 	       + nla_total_size(0) /* CTA_HELP */
@@ -571,7 +613,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 	if (events & (1 << IPCT_DESTROY)) {
 		if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
-		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
+		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+		    ctnetlink_dump_timestamp(skb, ct) < 0)
 			goto nla_put_failure;
 	} else {
 		if (ctnetlink_dump_timeout(skb, ct) < 0)
@@ -1360,6 +1403,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 8257bf643593..69107fd78d3e 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <linux/rculist_nulls.h>
 
 MODULE_LICENSE("GPL");
@@ -46,6 +47,7 @@ EXPORT_SYMBOL_GPL(print_tuple);
 struct ct_iter_state {
 	struct seq_net_private p;
 	unsigned int bucket;
+	u_int64_t time_now;
 };
 
 static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
@@ -96,6 +98,9 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
+	struct ct_iter_state *st = seq->private;
+
+	st->time_now = ktime_to_ns(ktime_get_real());
 	rcu_read_lock();
 	return ct_get_idx(seq, *pos);
 }
@@ -135,6 +140,39 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 }
 #endif
 
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+static u_int64_t ct_delta_time(u_int64_t time_now, const struct nf_conn *ct)
+{
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		u_int64_t delta_time = time_now - tstamp->start;
+		return delta_time > 0 ? div_s64(delta_time, NSEC_PER_SEC) : 0;
+	}
+	return -1;
+}
+
+static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	struct ct_iter_state *st = s->private;
+	u_int64_t delta_time;
+
+	delta_time = ct_delta_time(st->time_now, ct);
+	if (delta_time < 0)
+		return 0;
+
+	return seq_printf(s, "delta-time=%llu ",
+			  (unsigned long long)delta_time);
+}
+#else
+static inline int
+ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	return 0;
+}
+#endif
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
@@ -203,6 +241,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		goto release;
 #endif
 
+	if (ct_show_delta_time(s, ct))
+		goto release;
+
 	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
 		goto release;
 
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
new file mode 100644
index 000000000000..af7dd31af0a1
--- /dev/null
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -0,0 +1,120 @@
+/*
+ * (C) 2010 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * 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 (or any later at your option).
+ */
+
+#include <linux/netfilter.h>
+#include <linux/slab.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_timestamp.h>
+
+static int nf_ct_tstamp __read_mostly;
+
+module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
+MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table tstamp_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_timestamp",
+		.data		= &init_net.ct.sysctl_tstamp,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{}
+};
+#endif /* CONFIG_SYSCTL */
+
+static struct nf_ct_ext_type tstamp_extend __read_mostly = {
+	.len	= sizeof(struct nf_conn_tstamp),
+	.align	= __alignof__(struct nf_conn_tstamp),
+	.id	= NF_CT_EXT_TSTAMP,
+};
+
+#ifdef CONFIG_SYSCTL
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table),
+			GFP_KERNEL);
+	if (!table)
+		goto out;
+
+	table[0].data = &net->ct.sysctl_tstamp;
+
+	net->ct.tstamp_sysctl_header = register_net_sysctl_table(net,
+			nf_net_netfilter_sysctl_path, table);
+	if (!net->ct.tstamp_sysctl_header) {
+		printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n");
+		goto out_register;
+	}
+	return 0;
+
+out_register:
+	kfree(table);
+out:
+	return -ENOMEM;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->ct.tstamp_sysctl_header->ctl_table_arg;
+	unregister_net_sysctl_table(net->ct.tstamp_sysctl_header);
+	kfree(table);
+}
+#else
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	return 0;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+}
+#endif
+
+int nf_conntrack_tstamp_init(struct net *net)
+{
+	int ret;
+
+	net->ct.sysctl_tstamp = nf_ct_tstamp;
+
+	if (net_eq(net, &init_net)) {
+		ret = nf_ct_extend_register(&tstamp_extend);
+		if (ret < 0) {
+			printk(KERN_ERR "nf_ct_tstamp: Unable to register "
+					"extension\n");
+			goto out_extend_register;
+		}
+	}
+
+	ret = nf_conntrack_tstamp_init_sysctl(net);
+	if (ret < 0)
+		goto out_sysctl;
+
+	return 0;
+
+out_sysctl:
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+out_extend_register:
+	return ret;
+}
+
+void nf_conntrack_tstamp_fini(struct net *net)
+{
+	nf_conntrack_tstamp_fini_sysctl(net);
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+}
-- 
cgit v1.2.3-71-gd317


From 5d8449286456659cdd0998e62d80df2d9e77e9e3 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Thu, 20 Jan 2011 08:48:15 +0100
Subject: netfilter: xtables: remove extraneous header that slipped in

Commit 0b8ad87 (netfilter: xtables: add missing header files to export
list) erroneously added this.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/Kbuild | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux/netfilter')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index fc4e0aa805a2..89c0d1e20d72 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,7 +56,6 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
-header-y += xt_secmark.h
 header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
-- 
cgit v1.2.3-71-gd317