: Netfilter update

new file mode 100644
index 0000000..2db5432
@@ -0,0 +1,13 @@
+#ifndef _XT_TCPOPTSTRIP_H
+#define _XT_TCPOPTSTRIP_H
+
+#define tcpoptstrip_set_bit(bmap, idx) \
+	(bmap[(idx) >> 5] |= 1U << (idx & 31))
+#define tcpoptstrip_test_bit(bmap, idx) \
+	(((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0)
+
+struct xt_tcpoptstrip_target_info {
+	u_int32_t strip_bmap[8];
+};
+
+#endif /* _XT_TCPOPTSTRIP_H */

147 lines not on this page · raw message

index 2f544da..311361e 100644
@@ -109,11 +109,9 @@ clusterip_config_entry_put(struct clusterip_config *c)
 static struct clusterip_config *
 __clusterip_config_find(__be32 clusterip)
 {
-	struct list_head *pos;
+	struct clusterip_config *c;
 
-	list_for_each(pos, &clusterip_configs) {
-		struct clusterip_config *c = list_entry(pos,
-					struct clusterip_config, list);
+	list_for_each_entry(c, &clusterip_configs, list) {
 		if (c->clusterip == clusterip)
 			return c;
 	}

index 631d269..e6d3a69 100644
@@ -62,17 +62,17 @@ static DEFINE_MUTEX(nf_hook_mutex);
 
 int nf_register_hook(struct nf_hook_ops *reg)
 {
-	struct list_head *i;
+	struct nf_hook_ops *elem;
 	int err;
 
 	err = mutex_lock_interruptible(&nf_hook_mutex);
 	if (err < 0)
 		return err;
-	list_for_each(i, &nf_hooks[reg->pf][reg->hooknum]) {
-		if (reg->priority < ((struct nf_hook_ops *)i)->priority)
+	list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) {
+		if (reg->priority < elem->priority)
 			break;
 	}
-	list_add_rcu(&reg->list, i->prev);
+	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
 	return 0;
 }

index 9657c4e..e305f2d 100644
@@ -269,9 +269,12 @@ struct xt_table_info
 	unsigned int underflow[NF_INET_NUMHOOKS];
 
 	/* ipt_entry tables: one per CPU */
-	char *entries[NR_CPUS];
+	/* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */
+	char *entries[1];
 };
 
+#define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \
+			  + nr_cpu_ids * sizeof(char *))
 extern int xt_register_target(struct xt_target *target);
 extern void xt_unregister_target(struct xt_target *target);
 extern int xt_register_targets(struct xt_target *target, unsigned int n);

index 2909c92..a21722d 100644
@@ -811,8 +811,7 @@ static int do_replace(void __user *user, unsigned int len)
 		return -ENOPROTOOPT;
 
 	/* overflow check */
-	if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS -
-			SMP_CACHE_BYTES)
+	if (tmp.size >= INT_MAX / num_possible_cpus())
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;

@@ -1090,7 +1089,7 @@ int arpt_register_table(struct arpt_table *table,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	static struct xt_table_info bootstrap
+	struct xt_table_info bootstrap
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 	void *loc_cpu_entry;
 

index a99fe89..4200fde 100644
@@ -1090,7 +1090,8 @@ compat_calc_match(struct ipt_entry_match *m, int * size)
 	return 0;
 }
 
-static int compat_calc_entry(struct ipt_entry *e, struct xt_table_info *info,
+static int compat_calc_entry(struct ipt_entry *e,
+		const struct xt_table_info *info,
 		void *base, struct xt_table_info *newinfo)
 {
 	struct ipt_entry_target *t;

@@ -1118,22 +1119,17 @@ static int compat_calc_entry(struct ipt_entry *e, struct xt_table_info *info,
 	return 0;
 }
 
-static int compat_table_info(struct xt_table_info *info,
+static int compat_table_info(const struct xt_table_info *info,
 		struct xt_table_info *newinfo)
 {
 	void *loc_cpu_entry;
-	int i;
 
 	if (!newinfo || !info)
 		return -EINVAL;
 
-	memset(newinfo, 0, sizeof(struct xt_table_info));
-	newinfo->size = info->size;
-	newinfo->number = info->number;
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
-	}
+	/* we dont care about newinfo->entries[] */
+	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
+	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
 	return IPT_ENTRY_ITERATE(loc_cpu_entry, info->size,
 			compat_calc_entry, info, loc_cpu_entry, newinfo);

@@ -1327,8 +1323,7 @@ do_replace(void __user *user, unsigned int len)
 		return -ENOPROTOOPT;
 
 	/* overflow check */
-	if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS -
-			SMP_CACHE_BYTES)
+	if (tmp.size >= INT_MAX / num_possible_cpus())
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;

@@ -1861,8 +1856,7 @@ compat_do_replace(void __user *user, unsigned int len)
 		return -ENOPROTOOPT;
 
 	/* overflow check */
-	if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS -
-			SMP_CACHE_BYTES)
+	if (tmp.size >= INT_MAX / num_possible_cpus())
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;

@@ -2159,7 +2153,7 @@ int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl)
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	static struct xt_table_info bootstrap
+	struct xt_table_info bootstrap
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 	void *loc_cpu_entry;
 

index e1e87ef..e60c1b4 100644
@@ -1042,8 +1042,7 @@ do_replace(void __user *user, unsigned int len)
 		return -EFAULT;
 
 	/* overflow check */
-	if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS -
-			SMP_CACHE_BYTES)
+	if (tmp.size >= INT_MAX / num_possible_cpus())
 		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;

@@ -1339,7 +1338,7 @@ int ip6t_register_table(struct xt_table *table,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	static struct xt_table_info bootstrap
+	struct xt_table_info bootstrap
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 	void *loc_cpu_entry;
 

index d9a3bde..862b27d 100644
@@ -495,7 +495,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > num_physpages)
 		return NULL;
 
-	newinfo = kzalloc(sizeof(struct xt_table_info), GFP_KERNEL);
+	newinfo = kzalloc(XT_TABLE_INFO_SZ, GFP_KERNEL);
 	if (!newinfo)
 		return NULL;
 

index a21722d..d5cae7e 100644
@@ -811,8 +811,6 @@ static int do_replace(void __user *user, unsigned int len)
 		return -ENOPROTOOPT;
 
 	/* overflow check */
-	if (tmp.size >= INT_MAX / num_possible_cpus())
-		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
 

index 4200fde..0f2614e 100644
@@ -1323,8 +1323,6 @@ do_replace(void __user *user, unsigned int len)
 		return -ENOPROTOOPT;
 
 	/* overflow check */
-	if (tmp.size >= INT_MAX / num_possible_cpus())
-		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
 

index e60c1b4..d3e884a 100644
@@ -1042,8 +1042,6 @@ do_replace(void __user *user, unsigned int len)
 		return -EFAULT;
 
 	/* overflow check */
-	if (tmp.size >= INT_MAX / num_possible_cpus())
-		return -ENOMEM;
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
 

new file mode 100644
index 0000000..eacd34e
@@ -0,0 +1,16 @@
+#ifndef _XT_OWNER_MATCH_H
+#define _XT_OWNER_MATCH_H
+
+enum {
+	XT_OWNER_UID    = 1 << 0,
+	XT_OWNER_GID    = 1 << 1,
+	XT_OWNER_SOCKET = 1 << 2,
+};
+
+struct xt_owner_match_info {
+	u_int32_t uid;
+	u_int32_t gid;
+	u_int8_t match, invert;
+};
+
+#endif /* _XT_OWNER_MATCH_H */

87 lines not on this page · raw message

87 lines not on this page · raw message

211 lines not on this page · raw message

index f7ce625..723b519 100644
@@ -119,6 +119,7 @@ extern unsigned short	ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mt
 extern void		ip_rt_send_redirect(struct sk_buff *skb);
 
 extern unsigned		inet_addr_type(__be32 addr);
+extern unsigned		inet_dev_addr_type(const struct net_device *dev, __be32 addr);
 extern void		ip_rt_multicast_event(struct in_device *);
 extern int		ip_rt_ioctl(unsigned int cmd, void __user *arg);
 extern void		ip_rt_get_source(u8 *src, struct rtable *rt);

index c211887..7962830 100644
@@ -155,7 +155,12 @@ out:
 	return dev;
 }
 
-unsigned inet_addr_type(__be32 addr)
+/*
+ * Find address type as if only "dev" was present in the system. If
+ * on_dev is NULL then all interfaces are taken into consideration.
+ */
+static inline unsigned __inet_dev_addr_type(const struct net_device *dev,
+					    __be32 addr)
 {
 	struct flowi		fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
 	struct fib_result	res;

@@ -175,13 +180,24 @@ unsigned inet_addr_type(__be32 addr)
 	if (local_table) {
 		ret = RTN_UNICAST;
 		if (!local_table->tb_lookup(local_table, &fl, &res)) {
-			ret = res.type;
+			if (!dev || dev == res.fi->fib_dev)
+				ret = res.type;
 			fib_res_put(&res);
 		}
 	}
 	return ret;
 }
 
+unsigned int inet_addr_type(__be32 addr)
+{
+	return __inet_dev_addr_type(NULL, addr);
+}
+
+unsigned int inet_dev_addr_type(const struct net_device *dev, __be32 addr)
+{
+       return __inet_dev_addr_type(dev, addr);
+}
+
 /* Given (packet source, input interface) and optional (dst, oif, tos):
    - (main) check, that source is valid i.e. not broadcast or our local
      address.

@@ -937,4 +953,5 @@ void __init ip_fib_init(void)
 }
 
 EXPORT_SYMBOL(inet_addr_type);
+EXPORT_SYMBOL(inet_dev_addr_type);
 EXPORT_SYMBOL(ip_dev_find);

index 166ed01..446de6a 100644
@@ -1,6 +1,20 @@
 #ifndef _IPT_ADDRTYPE_H
 #define _IPT_ADDRTYPE_H
 
+enum {
+	IPT_ADDRTYPE_INVERT_SOURCE	= 0x0001,
+	IPT_ADDRTYPE_INVERT_DEST	= 0x0002,
+	IPT_ADDRTYPE_LIMIT_IFACE_IN	= 0x0004,
+	IPT_ADDRTYPE_LIMIT_IFACE_OUT	= 0x0008,
+};
+
+struct ipt_addrtype_info_v1 {
+	u_int16_t	source;		/* source-type mask */
+	u_int16_t	dest;		/* dest-type mask */
+	u_int32_t	flags;
+};
+
+/* revision 0 */
 struct ipt_addrtype_info {
 	u_int16_t	source;		/* source-type mask */
 	u_int16_t	dest;		/* dest-type mask */

139 lines not on this page · raw message

index eb65bf2..8a8d4e0 100644
@@ -12,15 +12,15 @@
 #include <asm/byteorder.h>
 
 
-static inline __u8 ipv4_get_dsfield(struct iphdr *iph)
+static inline __u8 ipv4_get_dsfield(const struct iphdr *iph)
 {
 	return iph->tos;
 }
 
 
-static inline __u8 ipv6_get_dsfield(struct ipv6hdr *ipv6h)
+static inline __u8 ipv6_get_dsfield(const struct ipv6hdr *ipv6h)
 {
-	return ntohs(*(__be16 *) ipv6h) >> 4;
+	return ntohs(*(const __be16 *)ipv6h) >> 4;
 }
 
 

50 lines not on this page · raw message

index 63f7354..75b0df9 100644
@@ -13,14 +13,16 @@
 #include <linux/ipv6.h>
 #include <net/dsfield.h>
 
-#include <linux/netfilter/xt_dscp.h>
 #include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_dscp.h>
+#include <linux/netfilter_ipv4/ipt_tos.h>
 
 MODULE_AUTHOR("Harald Welte <[email protected]>");
-MODULE_DESCRIPTION("x_tables DSCP matching module");
+MODULE_DESCRIPTION("x_tables DSCP/tos matching module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("ipt_dscp");
 MODULE_ALIAS("ip6t_dscp");
+MODULE_ALIAS("ipt_tos");
 
 static bool
 dscp_mt(const struct sk_buff *skb, const struct net_device *in,

@@ -60,6 +62,16 @@ dscp_mt_check(const char *tablename, const void *info,
 	return true;
 }
 
+static bool tos_mt_v0(const struct sk_buff *skb, const struct net_device *in,
+                      const struct net_device *out,
+                      const struct xt_match *match, const void *matchinfo,
+                      int offset, unsigned int protoff, bool *hotdrop)
+{
+	const struct ipt_tos_info *info = matchinfo;
+
+	return (ip_hdr(skb)->tos == info->tos) ^ info->invert;
+}
+
 static struct xt_match dscp_mt_reg[] __read_mostly = {
 	{
 		.name		= "dscp",

@@ -77,6 +89,14 @@ static struct xt_match dscp_mt_reg[] __read_mostly = {
 		.matchsize	= sizeof(struct xt_dscp_info),
 		.me		= THIS_MODULE,
 	},
+	{
+		.name		= "tos",
+		.revision	= 0,
+		.family		= AF_INET,
+		.match		= tos_mt_v0,
+		.matchsize	= sizeof(struct ipt_tos_info),
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init dscp_mt_init(void)

75 lines not on this page · raw message

index 1da61e6..f49bc1a 100644
@@ -20,4 +20,10 @@ struct xt_dscp_info {
 	u_int8_t invert;
 };
 
+struct xt_tos_match_info {
+	u_int8_t tos_mask;
+	u_int8_t tos_value;
+	u_int8_t invert;
+};
+
 #endif /* _XT_DSCP_H */

index 75b0df9..834e437 100644
@@ -23,6 +23,7 @@ MODULE_LICENSE("GPL");
 MODULE_ALIAS("ipt_dscp");
 MODULE_ALIAS("ip6t_dscp");
 MODULE_ALIAS("ipt_tos");
+MODULE_ALIAS("ip6t_tos");
 
 static bool
 dscp_mt(const struct sk_buff *skb, const struct net_device *in,

@@ -72,6 +73,21 @@ static bool tos_mt_v0(const struct sk_buff *skb, const struct net_device *in,
 	return (ip_hdr(skb)->tos == info->tos) ^ info->invert;
 }
 
+static bool tos_mt(const struct sk_buff *skb, const struct net_device *in,
+                   const struct net_device *out, const struct xt_match *match,
+                   const void *matchinfo, int offset, unsigned int protoff,
+                   bool *hotdrop)
+{
+	const struct xt_tos_match_info *info = matchinfo;
+
+	if (match->family == AF_INET)
+		return ((ip_hdr(skb)->tos & info->tos_mask) ==
+		       info->tos_value) ^ !!info->invert;
+	else
+		return ((ipv6_get_dsfield(ipv6_hdr(skb)) & info->tos_mask) ==
+		       info->tos_value) ^ !!info->invert;
+}
+
 static struct xt_match dscp_mt_reg[] __read_mostly = {
 	{
 		.name		= "dscp",

@@ -97,6 +113,22 @@ static struct xt_match dscp_mt_reg[] __read_mostly = {
 		.matchsize	= sizeof(struct ipt_tos_info),
 		.me		= THIS_MODULE,
 	},
+	{
+		.name		= "tos",
+		.revision	= 1,
+		.family		= AF_INET,
+		.match		= tos_mt,
+		.matchsize	= sizeof(struct xt_tos_match_info),
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "tos",
+		.revision	= 1,
+		.family		= AF_INET6,
+		.match		= tos_mt,
+		.matchsize	= sizeof(struct xt_tos_match_info),
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init dscp_mt_init(void)

index 3c7c963..14da196 100644
@@ -17,4 +17,9 @@ struct xt_DSCP_info {
 	u_int8_t dscp;
 };
 
+struct xt_tos_target_info {
+	u_int8_t tos_value;
+	u_int8_t tos_mask;
+};
+
 #endif /* _XT_DSCP_TARGET_H */

81 lines not on this page · raw message

174 lines not on this page · raw message

new file mode 100644
index 0000000..670f2e4
@@ -0,0 +1,11 @@
+#ifndef _XT_RATEEST_TARGET_H
+#define _XT_RATEEST_TARGET_H
+
+struct xt_rateest_target_info {
+	char			name[IFNAMSIZ];
+	int8_t			interval;
+	u_int8_t		ewma_log;
+	struct xt_rateest	*est __attribute__((aligned(8)));
+};
+
+#endif /* _XT_RATEEST_TARGET_H */

new file mode 100644
index 0000000..65d594d
@@ -0,0 +1,17 @@
+#ifndef _XT_RATEEST_H
+#define _XT_RATEEST_H
+
+struct xt_rateest {
+	struct hlist_node		list;
+	char				name[IFNAMSIZ];
+	unsigned int			refcnt;
+	spinlock_t			lock;
+	struct gnet_estimator		params;
+	struct gnet_stats_rate_est	rstats;
+	struct gnet_stats_basic		bstats;
+};
+
+extern struct xt_rateest *xt_rateest_lookup(const char *name);
+extern void xt_rateest_put(struct xt_rateest *est);
+
+#endif /* _XT_RATEEST_H */

204 lines not on this page · raw message

new file mode 100644
index 0000000..51948e1
@@ -0,0 +1,33 @@
+#ifndef _XT_RATEEST_MATCH_H
+#define _XT_RATEEST_MATCH_H
+
+enum xt_rateest_match_flags {
+	XT_RATEEST_MATCH_INVERT	= 1<<0,
+	XT_RATEEST_MATCH_ABS	= 1<<1,
+	XT_RATEEST_MATCH_REL	= 1<<2,
+	XT_RATEEST_MATCH_DELTA	= 1<<3,
+	XT_RATEEST_MATCH_BPS	= 1<<4,
+	XT_RATEEST_MATCH_PPS	= 1<<5,
+};
+
+enum xt_rateest_match_mode {
+	XT_RATEEST_MATCH_NONE,
+	XT_RATEEST_MATCH_EQ,
+	XT_RATEEST_MATCH_LT,
+	XT_RATEEST_MATCH_GT,
+};
+
+struct xt_rateest_match_info {
+	char			name1[IFNAMSIZ];
+	char			name2[IFNAMSIZ];
+	u_int16_t		flags;
+	u_int16_t		mode;
+	u_int32_t		bps1;
+	u_int32_t		pps1;
+	u_int32_t		bps2;
+	u_int32_t		pps2;
+	struct xt_rateest	*est1 __attribute__((aligned(8)));
+	struct xt_rateest	*est2 __attribute__((aligned(8)));
+};
+
+#endif /* _XT_RATEEST_MATCH_H */

178 lines not on this page · raw message

index fba2155..f8c613a 100644
@@ -337,7 +337,9 @@ static void dump_packet(const struct nf_loginfo *info,
 	if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) {
 		read_lock_bh(&skb->sk->sk_callback_lock);
 		if (skb->sk->sk_socket && skb->sk->sk_socket->file)
-			printk("UID=%u ", skb->sk->sk_socket->file->f_uid);
+			printk("UID=%u GID=%u",
+				skb->sk->sk_socket->file->f_uid,
+				skb->sk->sk_socket->file->f_gid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 	}
 

index cd51c42..1952324 100644
@@ -362,7 +362,9 @@ static void dump_packet(const struct nf_loginfo *info,
 	if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) {
 		read_lock_bh(&skb->sk->sk_callback_lock);
 		if (skb->sk->sk_socket && skb->sk->sk_socket->file)
-			printk("UID=%u ", skb->sk->sk_socket->file->f_uid);
+			printk("UID=%u GID=%u",
+				skb->sk->sk_socket->file->f_uid,
+				skb->sk->sk_socket->file->f_gid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 	}
 }

index 8a8b267..033d448 100644
@@ -21,6 +21,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 
 #include <linux/netfilter/x_tables.h>

@@ -379,7 +380,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 		   const struct sk_buff *skb, unsigned int protoff)
 {
 	__be16 _ports[2], *ports;
-	int nexthdr;
+	u8 nexthdr;
 
 	memset(dst, 0, sizeof(*dst));
 

@@ -407,8 +408,9 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 		if (!(hinfo->cfg.mode &
 		      (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT)))
 			return 0;
-		nexthdr = ipv6_find_hdr(skb, &protoff, -1, NULL);
-		if (nexthdr < 0)
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+		if ((int)protoff < 0)
 			return -1;
 		break;
 #endif

index f42e436..9bfc7d4 100644
@@ -298,10 +298,12 @@ extern void nf_invalidate_cache(int pf);
    Returns true or false. */
 extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
 
+struct flowi;
 struct nf_afinfo {
 	unsigned short	family;
 	__sum16		(*checksum)(struct sk_buff *skb, unsigned int hook,
 				    unsigned int dataoff, u_int8_t protocol);
+	int		(*route)(struct dst_entry **dst, struct flowi *fl);
 	void		(*saveroute)(const struct sk_buff *skb,
 				     struct nf_info *info);
 	int		(*reroute)(struct sk_buff *skb,

index d902246..599d448 100644
@@ -182,9 +182,15 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 
 EXPORT_SYMBOL(nf_ip_checksum);
 
+static int nf_ip_route(struct dst_entry **dst, struct flowi *fl)
+{
+	return ip_route_output_key((struct rtable **)dst, fl);
+}
+
 static struct nf_afinfo nf_ip_afinfo = {
 	.family		= AF_INET,
 	.checksum	= nf_ip_checksum,
+	.route		= nf_ip_route,
 	.saveroute	= nf_ip_saveroute,
 	.reroute	= nf_ip_reroute,
 	.route_key_size	= sizeof(struct ip_rt_info),

index 175e19f..281f732 100644
@@ -81,6 +81,12 @@ static int nf_ip6_reroute(struct sk_buff *skb, const struct nf_info *info)
 	return 0;
 }
 
+static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
+{
+	*dst = ip6_route_output(NULL, fl);
+	return (*dst)->error;
+}
+
 __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
 			     unsigned int dataoff, u_int8_t protocol)
 {

@@ -118,6 +124,7 @@ EXPORT_SYMBOL(nf_ip6_checksum);
 static struct nf_afinfo nf_ip6_afinfo = {
 	.family		= AF_INET6,
 	.checksum	= nf_ip6_checksum,
+	.route		= nf_ip6_route,
 	.saveroute	= nf_ip6_saveroute,
 	.reroute	= nf_ip6_reroute,
 	.route_key_size	= sizeof(struct ip6_rt_info),

index f23fd95..c550257 100644
@@ -708,9 +708,15 @@ static int callforward_do_filter(union nf_conntrack_address *src,
 				 union nf_conntrack_address *dst,
 				 int family)
 {
+	struct nf_afinfo *afinfo;
 	struct flowi fl1, fl2;
 	int ret = 0;
 
+	/* rcu_read_lock()ed by nf_hook_slow() */
+	afinfo = nf_get_afinfo(family);
+	if (!afinfo)
+		return 0;
+
 	memset(&fl1, 0, sizeof(fl1));
 	memset(&fl2, 0, sizeof(fl2));
 

@@ -720,8 +726,8 @@ static int callforward_do_filter(union nf_conntrack_address *src,
 
 		fl1.fl4_dst = src->ip;
 		fl2.fl4_dst = dst->ip;
-		if (ip_route_output_key(&rt1, &fl1) == 0) {
-			if (ip_route_output_key(&rt2, &fl2) == 0) {
+		if (!afinfo->route((struct dst_entry **)&rt1, &fl1)) {
+			if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) {
 				if (rt1->rt_gateway == rt2->rt_gateway &&
 				    rt1->u.dst.dev  == rt2->u.dst.dev)
 					ret = 1;

@@ -731,16 +737,15 @@ static int callforward_do_filter(union nf_conntrack_address *src,
 		}
 		break;
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if defined(CONFIG_NF_CONNTRACK_IPV6) || \
+    defined(CONFIG_NF_CONNTRACK_IPV6_MODULE)
 	case AF_INET6: {
 		struct rt6_info *rt1, *rt2;
 
 		memcpy(&fl1.fl6_dst, src, sizeof(fl1.fl6_dst));
 		memcpy(&fl2.fl6_dst, dst, sizeof(fl2.fl6_dst));
-		rt1 = (struct rt6_info *)ip6_route_output(NULL, &fl1);
-		if (rt1) {
-			rt2 = (struct rt6_info *)ip6_route_output(NULL, &fl2);
-			if (rt2) {
+		if (!afinfo->route((struct dst_entry **)&rt1, &fl1)) {
+			if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) {
 				if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
 					    sizeof(rt1->rt6i_gateway)) &&
 				    rt1->u.dst.dev == rt2->u.dst.dev)

index 0e2c448..4153e04 100644
@@ -128,7 +128,6 @@ static int icmp_new(struct nf_conn *conntrack,
 	return 1;
 }
 
-extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
 /* Returns conntrack if it dealt with ICMP, and filled in skb fields */
 static int
 icmp_error_message(struct sk_buff *skb,

index 30e8f75..f5ba606 100644
@@ -1025,43 +1025,42 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
 }
 
 
-/* After packet filtering, forward packet through VS/DR, VS/TUN,
-   or VS/NAT(change destination), so that filtering rules can be
-   applied to IPVS. */
-static struct nf_hook_ops ip_vs_in_ops = {
-	.hook		= ip_vs_in,
-	.owner		= THIS_MODULE,
-	.pf		= PF_INET,
-	.hooknum        = NF_INET_LOCAL_IN,
-	.priority       = 100,
-};
-
-/* After packet filtering, change source only for VS/NAT */
-static struct nf_hook_ops ip_vs_out_ops = {
-	.hook		= ip_vs_out,
-	.owner		= THIS_MODULE,
-	.pf		= PF_INET,
-	.hooknum        = NF_INET_FORWARD,
-	.priority       = 100,
-};
-
-/* After packet filtering (but before ip_vs_out_icmp), catch icmp
-   destined for 0.0.0.0/0, which is for incoming IPVS connections */
-static struct nf_hook_ops ip_vs_forward_icmp_ops = {
-	.hook		= ip_vs_forward_icmp,
-	.owner		= THIS_MODULE,
-	.pf		= PF_INET,
-	.hooknum        = NF_INET_FORWARD,
-	.priority       = 99,
-};
-
-/* Before the netfilter connection tracking, exit from POST_ROUTING */
-static struct nf_hook_ops ip_vs_post_routing_ops = {
-	.hook		= ip_vs_post_routing,
-	.owner		= THIS_MODULE,
-	.pf		= PF_INET,
-	.hooknum        = NF_INET_POST_ROUTING,
-	.priority       = NF_IP_PRI_NAT_SRC-1,
+static struct nf_hook_ops ip_vs_ops[]  = {
+	/* After packet filtering, forward packet through VS/DR, VS/TUN,
+	 * or VS/NAT(change destination), so that filtering rules can be
+	 * applied to IPVS. */
+	{
+		.hook		= ip_vs_in,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET,
+		.hooknum        = NF_INET_LOCAL_IN,
+		.priority       = 100,
+	},
+	/* After packet filtering, change source only for VS/NAT */
+	{
+		.hook		= ip_vs_out,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET,
+		.hooknum        = NF_INET_FORWARD,
+		.priority       = 100,
+	},
+	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
+	 * destined for 0.0.0.0/0, which is for incoming IPVS connections */
+	{
+		.hook		= ip_vs_forward_icmp,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET,
+		.hooknum        = NF_INET_FORWARD,
+		.priority       = 99,
+	},
+	/* Before the netfilter connection tracking, exit from POST_ROUTING */
+	{
+		.hook		= ip_vs_post_routing,
+		.owner		= THIS_MODULE,
+		.pf		= PF_INET,
+		.hooknum        = NF_INET_POST_ROUTING,
+		.priority       = NF_IP_PRI_NAT_SRC-1,
+	},
 };
 
 

@@ -1092,37 +1091,15 @@ static int __init ip_vs_init(void)
 		goto cleanup_app;
 	}
 
-	ret = nf_register_hook(&ip_vs_in_ops);
+	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	if (ret < 0) {
-		IP_VS_ERR("can't register in hook.\n");
+		IP_VS_ERR("can't register hooks.\n");
 		goto cleanup_conn;
 	}
 
-	ret = nf_register_hook(&ip_vs_out_ops);
-	if (ret < 0) {
-		IP_VS_ERR("can't register out hook.\n");
-		goto cleanup_inops;
-	}
-	ret = nf_register_hook(&ip_vs_post_routing_ops);
-	if (ret < 0) {
-		IP_VS_ERR("can't register post_routing hook.\n");
-		goto cleanup_outops;
-	}
-	ret = nf_register_hook(&ip_vs_forward_icmp_ops);
-	if (ret < 0) {
-		IP_VS_ERR("can't register forward_icmp hook.\n");
-		goto cleanup_postroutingops;
-	}
-
 	IP_VS_INFO("ipvs loaded.\n");
 	return ret;
 
-  cleanup_postroutingops:
-	nf_unregister_hook(&ip_vs_post_routing_ops);
-  cleanup_outops:
-	nf_unregister_hook(&ip_vs_out_ops);
-  cleanup_inops:
-	nf_unregister_hook(&ip_vs_in_ops);
   cleanup_conn:
 	ip_vs_conn_cleanup();
   cleanup_app:

@@ -1136,10 +1113,7 @@ static int __init ip_vs_init(void)
 
 static void __exit ip_vs_cleanup(void)
 {
-	nf_unregister_hook(&ip_vs_forward_icmp_ops);
-	nf_unregister_hook(&ip_vs_post_routing_ops);
-	nf_unregister_hook(&ip_vs_out_ops);
-	nf_unregister_hook(&ip_vs_in_ops);
+	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ip_vs_conn_cleanup();
 	ip_vs_app_cleanup();
 	ip_vs_protocol_cleanup();

66 lines not on this page · raw message

index 5f5b98a..32ac035 100644
@@ -838,7 +838,7 @@ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb,
  * PF_BRIDGE/NF_BR_LOCAL_OUT functions don't get bridged traffic as input.
  * For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
  * ip_refrag() can return NF_STOLEN. */
-static struct nf_hook_ops br_nf_ops[] = {
+static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 	{ .hook = br_nf_pre_routing,
 	  .owner = THIS_MODULE,
 	  .pf = PF_BRIDGE,

index 210493f..fb81090 100644
@@ -67,7 +67,7 @@ ebt_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
 	return ebt_do_table(hook, skb, in, out, &frame_filter);
 }
 
-static struct nf_hook_ops ebt_ops_filter[] = {
+static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
 	{
 		.hook		= ebt_hook,
 		.owner		= THIS_MODULE,

index 3e58c2e..bc71273 100644
@@ -74,7 +74,7 @@ ebt_nat_src(unsigned int hook, struct sk_buff *skb, const struct net_device *in
 	return ebt_do_table(hook, skb, in, out, &frame_nat);
 }
 
-static struct nf_hook_ops ebt_ops_nat[] = {
+static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
 	{
 		.hook		= ebt_nat_dst,
 		.owner		= THIS_MODULE,

index 43fcd29..96375f2 100644
@@ -115,7 +115,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 	RCV_SKB_FAIL(-EINVAL);
 }
 
-static struct nf_hook_ops dnrmg_ops = {
+static struct nf_hook_ops dnrmg_ops __read_mostly = {
 	.hook		= dnrmg_hook,
 	.pf		= PF_DECnet,
 	.hooknum	= NF_DN_ROUTE,

index f5ba606..041f512 100644
@@ -1025,7 +1025,7 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
 }
 
 
-static struct nf_hook_ops ip_vs_ops[]  = {
+static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	/* After packet filtering, forward packet through VS/DR, VS/TUN,
 	 * or VS/NAT(change destination), so that filtering rules can be
 	 * applied to IPVS. */

index 302d3da..7201511 100644
@@ -64,7 +64,7 @@ static unsigned int arpt_hook(unsigned int hook,
 	return arpt_do_table(skb, hook, in, out, &packet_filter);
 }
 
-static struct nf_hook_ops arpt_ops[] = {
+static struct nf_hook_ops arpt_ops[] __read_mostly = {
 	{
 		.hook		= arpt_hook,
 		.owner		= THIS_MODULE,

index b5de6bd..dc1e7b4 100644
@@ -551,7 +551,7 @@ arp_mangle(unsigned int hook,
 	return NF_ACCEPT;
 }
 
-static struct nf_hook_ops cip_arp_ops = {
+static struct nf_hook_ops cip_arp_ops __read_mostly = {
 	.hook = arp_mangle,
 	.pf = NF_ARP,
 	.hooknum = NF_ARP_OUT,

index 06ab64e..29bb4f9 100644
@@ -91,7 +91,7 @@ ipt_local_out_hook(unsigned int hook,
 	return ipt_do_table(skb, hook, in, out, &packet_filter);
 }
 
-static struct nf_hook_ops ipt_ops[] = {
+static struct nf_hook_ops ipt_ops[] __read_mostly = {
 	{
 		.hook		= ipt_hook,
 		.owner		= THIS_MODULE,

index 0335827..5c4be20 100644
@@ -128,7 +128,7 @@ ipt_local_hook(unsigned int hook,
 	return ret;
 }
 
-static struct nf_hook_ops ipt_ops[] = {
+static struct nf_hook_ops ipt_ops[] __read_mostly = {
 	{
 		.hook		= ipt_route_hook,
 		.owner		= THIS_MODULE,

index 66be232..dc34aa2 100644
@@ -74,7 +74,7 @@ ipt_local_hook(unsigned int hook,
 }
 
 /* 'raw' is the very first table. */
-static struct nf_hook_ops ipt_ops[] = {
+static struct nf_hook_ops ipt_ops[] __read_mostly = {
 	{
 		.hook = ipt_hook,
 		.pf = PF_INET,

index 9ac3020..e0e09f5 100644
@@ -185,7 +185,7 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum,
 
 /* Connection tracking may drop packets, but never alters them, so
    make it the first hook. */
-static struct nf_hook_ops ipv4_conntrack_ops[] = {
+static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = {
 	{
 		.hook		= ipv4_conntrack_defrag,
 		.owner		= THIS_MODULE,

index 84172e9..a2b02f0 100644
@@ -273,7 +273,7 @@ nf_nat_adjust(unsigned int hooknum,
 
 /* We must be after connection tracking and before packet filtering. */
 
-static struct nf_hook_ops nf_nat_ops[] = {
+static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
 		.hook		= nf_nat_in,

index 0ae072d..87d38d0 100644
@@ -90,7 +90,7 @@ ip6t_local_out_hook(unsigned int hook,
 	return ip6t_do_table(skb, hook, in, out, &packet_filter);
 }
 
-static struct nf_hook_ops ip6t_ops[] = {
+static struct nf_hook_ops ip6t_ops[] __read_mostly = {
 	{
 		.hook		= ip6t_hook,
 		.owner		= THIS_MODULE,

index 8e62b23..d608260 100644
@@ -120,7 +120,7 @@ ip6t_local_hook(unsigned int hook,
 	return ret;
 }
 
-static struct nf_hook_ops ip6t_ops[] = {
+static struct nf_hook_ops ip6t_ops[] __read_mostly = {
 	{
 		.hook		= ip6t_route_hook,
 		.owner		= THIS_MODULE,

index 4fecd8d..eccbaaa 100644
@@ -54,7 +54,7 @@ ip6t_hook(unsigned int hook,
 	return ip6t_do_table(skb, hook, in, out, &packet_raw);
 }
 
-static struct nf_hook_ops ip6t_ops[] = {
+static struct nf_hook_ops ip6t_ops[] __read_mostly = {
 	{
 	  .hook = ip6t_hook,
 	  .pf = PF_INET6,

index 50f4678..97a5530 100644
@@ -258,7 +258,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 	return ipv6_conntrack_in(hooknum, skb, in, out, okfn);
 }
 
-static struct nf_hook_ops ipv6_conntrack_ops[] = {
+static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
 	{
 		.hook		= ipv6_defrag,
 		.owner		= THIS_MODULE,

index f4af9b6..89c32a9 100644
@@ -231,7 +231,7 @@ ing_hook(unsigned int hook, struct sk_buff *skb,
 }
 
 /* after ipt_filter */
-static struct nf_hook_ops ing_ops[] = {
+static struct nf_hook_ops ing_ops[] __read_mostly = {
 	{
 		.hook           = ing_hook,
 		.owner		= THIS_MODULE,

index 0cef143..81d010a 100644
@@ -138,15 +138,18 @@ static int __nf_queue(struct sk_buff *skb,
 	}
 
 	/* Bump dev refs so they don't vanish while packet is out */
-	if (indev) dev_hold(indev);
-	if (outdev) dev_hold(outdev);
-
+	if (indev)
+		dev_hold(indev);
+	if (outdev)
+		dev_hold(outdev);
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge) {
 		physindev = skb->nf_bridge->physindev;
-		if (physindev) dev_hold(physindev);
+		if (physindev)
+			dev_hold(physindev);
 		physoutdev = skb->nf_bridge->physoutdev;
-		if (physoutdev) dev_hold(physoutdev);
+		if (physoutdev)
+			dev_hold(physoutdev);
 	}
 #endif
 	afinfo->saveroute(skb, info);

@@ -156,11 +159,15 @@ static int __nf_queue(struct sk_buff *skb,
 
 	if (status < 0) {
 		/* James M doesn't say fuck enough. */
-		if (indev) dev_put(indev);
-		if (outdev) dev_put(outdev);
+		if (indev)
+			dev_put(indev);
+		if (outdev)
+			dev_put(outdev);
 #ifdef CONFIG_BRIDGE_NETFILTER
-		if (physindev) dev_put(physindev);
-		if (physoutdev) dev_put(physoutdev);
+		if (physindev)
+			dev_put(physindev);
+		if (physoutdev)
+			dev_put(physoutdev);
 #endif
 		module_put(info->elem->owner);
 		kfree(info);

@@ -222,8 +229,10 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
 	rcu_read_lock();
 
 	/* Release those devices we held, or Alexey will kill me. */
-	if (info->indev) dev_put(info->indev);
-	if (info->outdev) dev_put(info->outdev);
+	if (info->indev)
+		dev_put(info->indev);
+	if (info->outdev)
+		dev_put(info->outdev);
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge) {
 		if (skb->nf_bridge->physindev)

index e6d3a69..6819a41 100644
@@ -51,11 +51,6 @@ void nf_unregister_afinfo(struct nf_afinfo *afinfo)
 }
 EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
 
-/* In this code, we can be waiting indefinitely for userspace to
- * service a packet if a hook returns NF_QUEUE.  We could keep a count
- * of skbuffs queued for userspace, and not deregister a hook unless
- * this is zero, but that sucks.  Now, we simply check when the
- * packets come back: if the hook is gone, the packet is discarded. */
 struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS] __read_mostly;
 EXPORT_SYMBOL(nf_hooks);
 static DEFINE_MUTEX(nf_hook_mutex);

index 81d010a..0bea88c 100644
@@ -223,7 +223,6 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
 		 unsigned int verdict)
 {
 	struct list_head *elem = &info->elem->list;
-	struct list_head *i;
 	struct nf_afinfo *afinfo;
 
 	rcu_read_lock();

@@ -245,18 +244,6 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
 	/* Drop reference to owner of hook which queued us. */
 	module_put(info->elem->owner);
 
-	list_for_each_rcu(i, &nf_hooks[info->pf][info->hook]) {
-		if (i == elem)
-			break;
-	}
-
-	if (i == &nf_hooks[info->pf][info->hook]) {
-		/* The module which sent it to userspace is gone. */
-		NFDEBUG("%s: module disappeared, dropping packet.\n",
-			__FUNCTION__);
-		verdict = NF_DROP;
-	}
-
 	/* Continue traversal iff userspace said ok... */
 	if (verdict == NF_REPEAT) {
 		elem = elem->prev;

index 9bfc7d4..c2c3faf 100644
@@ -281,11 +281,11 @@ struct nf_queue_handler {
 	void *data;
 	char *name;
 };
-extern int nf_register_queue_handler(int pf, 
-                                     struct nf_queue_handler *qh);
+extern int nf_register_queue_handler(int pf,
+				     const struct nf_queue_handler *qh);
 extern int nf_unregister_queue_handler(int pf,
-				       struct nf_queue_handler *qh);
-extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh);
+				       const struct nf_queue_handler *qh);
+extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh);
 extern void nf_reinject(struct sk_buff *skb,
 			struct nf_info *info,
 			unsigned int verdict);

index 14d64a3..062ff19 100644
@@ -645,7 +645,7 @@ static const struct file_operations ip_queue_proc_fops = {
 	.owner		= THIS_MODULE,
 };
 
-static struct nf_queue_handler nfqh = {
+static const struct nf_queue_handler nfqh = {
 	.name	= "ip_queue",
 	.outfn	= &ipq_enqueue_packet,
 };

index e273605..d6e971b 100644
@@ -634,7 +634,7 @@ static const struct file_operations ip6_queue_proc_fops = {
 	.owner		= THIS_MODULE,
 };
 
-static struct nf_queue_handler nfqh = {
+static const struct nf_queue_handler nfqh = {
 	.name	= "ip6_queue",
 	.outfn	= &ipq_enqueue_packet,
 };

index 0bea88c..dd18126 100644
@@ -15,13 +15,13 @@
  * long term mutex.  The handler must provide an an outfn() to accept packets
  * for queueing and must reinject all packets it receives, no matter what.
  */
-static struct nf_queue_handler *queue_handler[NPROTO];
+static const struct nf_queue_handler *queue_handler[NPROTO];
 
 static DEFINE_MUTEX(queue_handler_mutex);
 
 /* return EBUSY when somebody else is registered, return EEXIST if the
  * same handler is registered, return 0 in case of success. */
-int nf_register_queue_handler(int pf, struct nf_queue_handler *qh)
+int nf_register_queue_handler(int pf, const struct nf_queue_handler *qh)
 {
 	int ret;
 

@@ -44,7 +44,7 @@ int nf_register_queue_handler(int pf, struct nf_queue_handler *qh)
 EXPORT_SYMBOL(nf_register_queue_handler);
 
 /* The caller must flush their queue before this */
-int nf_unregister_queue_handler(int pf, struct nf_queue_handler *qh)
+int nf_unregister_queue_handler(int pf, const struct nf_queue_handler *qh)
 {
 	if (pf >= NPROTO)
 		return -EINVAL;

@@ -64,7 +64,7 @@ int nf_unregister_queue_handler(int pf, struct nf_queue_handler *qh)
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
-void nf_unregister_queue_handlers(struct nf_queue_handler *qh)
+void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
 {
 	int pf;
 

@@ -98,7 +98,7 @@ static int __nf_queue(struct sk_buff *skb,
 	struct net_device *physoutdev = NULL;
 #endif
 	struct nf_afinfo *afinfo;
-	struct nf_queue_handler *qh;
+	const struct nf_queue_handler *qh;
 
 	/* QUEUE == DROP if noone is waiting, to be safe. */
 	rcu_read_lock();

@@ -313,7 +313,7 @@ static int seq_show(struct seq_file *s, void *v)
 {
 	int ret;
 	loff_t *pos = v;
-	struct nf_queue_handler *qh;
+	const struct nf_queue_handler *qh;
 
 	rcu_read_lock();
 	qh = rcu_dereference(queue_handler[*pos]);

index 3ceeffc..b75091c 100644
@@ -849,7 +849,7 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 	[NFQA_CFG_PARAMS]	= { .len = sizeof(struct nfqnl_msg_config_params) },
 };
 
-static struct nf_queue_handler nfqh = {
+static const struct nf_queue_handler nfqh = {
 	.name 	= "nf_queue",
 	.outfn	= &nfqnl_enqueue_packet,
 };

index c2c3faf..1ba6011 100644
@@ -277,8 +277,7 @@ int compat_nf_getsockopt(struct sock *sk, int pf, int optval,
 /* Packet queuing */
 struct nf_queue_handler {
 	int (*outfn)(struct sk_buff *skb, struct nf_info *info,
-		     unsigned int queuenum, void *data);
-	void *data;
+		     unsigned int queuenum);
 	char *name;
 };
 extern int nf_register_queue_handler(int pf,

index 062ff19..08e7f8b 100644
@@ -272,7 +272,7 @@ nlmsg_failure:
 
 static int
 ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info,
-		   unsigned int queuenum, void *data)
+		   unsigned int queuenum)
 {
 	int status = -EINVAL;
 	struct sk_buff *nskb;

index d6e971b..5a9ca0d 100644
@@ -269,7 +269,7 @@ nlmsg_failure:
 
 static int
 ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info,
-		   unsigned int queuenum, void *data)
+		   unsigned int queuenum)
 {
 	int status = -EINVAL;
 	struct sk_buff *nskb;

index dd18126..c098ccb 100644
@@ -153,7 +153,7 @@ static int __nf_queue(struct sk_buff *skb,
 	}
 #endif
 	afinfo->saveroute(skb, info);
-	status = qh->outfn(skb, info, queuenum, qh->data);
+	status = qh->outfn(skb, info, queuenum);
 
 	rcu_read_unlock();
 

index b75091c..94ec1c2 100644
@@ -534,7 +534,7 @@ nla_put_failure:
 
 static int
 nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info,
-		     unsigned int queuenum, void *data)
+		     unsigned int queuenum)
 {
 	int status = -EINVAL;
 	struct sk_buff *nskb;

index 1ba6011..5fe4ef4 100644
@@ -101,19 +101,6 @@ struct nf_sockopt_ops
 	struct module *owner;
 };
 
-/* Each queued (to userspace) skbuff has one of these. */
-struct nf_info
-{
-	/* The ops struct which sent us to userspace. */
-	struct nf_hook_ops *elem;
-	
-	/* If we're sent to userspace, this keeps housekeeping info */
-	int pf;
-	unsigned int hook;
-	struct net_device *indev, *outdev;
-	int (*okfn)(struct sk_buff *);
-};
-                                                                                
 /* Function to register/unregister hook points. */
 int nf_register_hook(struct nf_hook_ops *reg);
 void nf_unregister_hook(struct nf_hook_ops *reg);

@@ -274,21 +261,6 @@ int compat_nf_setsockopt(struct sock *sk, int pf, int optval,
 int compat_nf_getsockopt(struct sock *sk, int pf, int optval,
 		char __user *opt, int *len);
 
-/* Packet queuing */
-struct nf_queue_handler {
-	int (*outfn)(struct sk_buff *skb, struct nf_info *info,
-		     unsigned int queuenum);
-	char *name;
-};
-extern int nf_register_queue_handler(int pf,
-				     const struct nf_queue_handler *qh);
-extern int nf_unregister_queue_handler(int pf,
-				       const struct nf_queue_handler *qh);
-extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh);
-extern void nf_reinject(struct sk_buff *skb,
-			struct nf_info *info,
-			unsigned int verdict);
-
 /* FIXME: Before cache is ever used, this must be implemented for real. */
 extern void nf_invalidate_cache(int pf);
 

@@ -298,6 +270,8 @@ extern void nf_invalidate_cache(int pf);
 extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
 
 struct flowi;
+struct nf_info;
+
 struct nf_afinfo {
 	unsigned short	family;
 	__sum16		(*checksum)(struct sk_buff *skb, unsigned int hook,

@@ -334,8 +308,6 @@ nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff,
 extern int nf_register_afinfo(struct nf_afinfo *afinfo);
 extern void nf_unregister_afinfo(struct nf_afinfo *afinfo);
 
-#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info))
-
 #include <net/flow.h>
 extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
 

new file mode 100644
index 0000000..8c6b382
@@ -0,0 +1,32 @@
+#ifndef _NF_QUEUE_H
+#define _NF_QUEUE_H
+
+/* Each queued (to userspace) skbuff has one of these. */
+struct nf_info {
+	struct nf_hook_ops	*elem;
+	int			pf;
+	unsigned int		hook;
+	struct net_device	*indev;
+	struct net_device	*outdev;
+	int			(*okfn)(struct sk_buff *);
+};
+
+#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info))
+
+/* Packet queuing */
+struct nf_queue_handler {
+	int			(*outfn)(struct sk_buff *skb,
+					 struct nf_info *info,
+					 unsigned int queuenum);
+	char			*name;
+};
+
+extern int nf_register_queue_handler(int pf,
+				     const struct nf_queue_handler *qh);
+extern int nf_unregister_queue_handler(int pf,
+				       const struct nf_queue_handler *qh);
+extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh);
+extern void nf_reinject(struct sk_buff *skb, struct nf_info *info,
+			unsigned int verdict);
+
+#endif /* _NF_QUEUE_H */

index 599d448..f716608 100644
@@ -7,6 +7,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
 int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)

index 08e7f8b..2966fbd 100644
@@ -28,6 +28,7 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/route.h>
+#include <net/netfilter/nf_queue.h>
 
 #define IPQ_QMAX_DEFAULT 1024
 #define IPQ_PROC_FS_NAME "ip_queue"

index 281f732..55ea9c6 100644
@@ -8,6 +8,7 @@
 #include <net/ip6_route.h>
 #include <net/xfrm.h>
 #include <net/ip6_checksum.h>
+#include <net/netfilter/nf_queue.h>
 
 int ip6_route_me_harder(struct sk_buff *skb)
 {

index 5a9ca0d..7ff9915 100644
@@ -29,6 +29,7 @@
 #include <net/sock.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
+#include <net/netfilter/nf_queue.h>
 #include <linux/netfilter_ipv4/ip_queue.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>

index c098ccb..bd71f43 100644
@@ -7,6 +7,7 @@
 #include <linux/seq_file.h>
 #include <linux/rcupdate.h>
 #include <net/protocol.h>
+#include <net/netfilter/nf_queue.h>
 
 #include "nf_internals.h"
 

index 94ec1c2..3a09f02 100644
@@ -27,6 +27,7 @@
 #include <linux/netfilter/nfnetlink_queue.h>
 #include <linux/list.h>
 #include <net/sock.h>
+#include <net/netfilter/nf_queue.h>
 
 #include <asm/atomic.h>
 

index 2966fbd..9e72246 100644
@@ -73,7 +73,7 @@ ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
 static inline void
 __ipq_enqueue_entry(struct ipq_queue_entry *entry)
 {
-       list_add(&entry->list, &queue_list);
+       list_add_tail(&entry->list, &queue_list);
        queue_total++;
 }
 

@@ -84,11 +84,9 @@ __ipq_enqueue_entry(struct ipq_queue_entry *entry)
 static inline struct ipq_queue_entry *
 __ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
 {
-	struct list_head *p;
-
-	list_for_each_prev(p, &queue_list) {
-		struct ipq_queue_entry *entry = (struct ipq_queue_entry *)p;
+	struct ipq_queue_entry *entry;
 
+	list_for_each_entry(entry, &queue_list, list) {
 		if (!cmpfn || cmpfn(entry, data))
 			return entry;
 	}

index 7ff9915..243a00b 100644
@@ -71,7 +71,7 @@ ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
 static inline void
 __ipq_enqueue_entry(struct ipq_queue_entry *entry)
 {
-       list_add(&entry->list, &queue_list);
+       list_add_tail(&entry->list, &queue_list);
        queue_total++;
 }
 

@@ -82,11 +82,9 @@ __ipq_enqueue_entry(struct ipq_queue_entry *entry)
 static inline struct ipq_queue_entry *
 __ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
 {
-	struct list_head *p;
-
-	list_for_each_prev(p, &queue_list) {
-		struct ipq_queue_entry *entry = (struct ipq_queue_entry *)p;
+	struct ipq_queue_entry *entry;
 
+	list_for_each_entry(entry, &queue_list, list) {
 		if (!cmpfn || cmpfn(entry, data))
 			return entry;
 	}

index 3a09f02..74d5ed9 100644
@@ -231,7 +231,7 @@ static inline void
 __enqueue_entry(struct nfqnl_instance *queue,
 		      struct nfqnl_queue_entry *entry)
 {
-       list_add(&entry->list, &queue->queue_list);
+       list_add_tail(&entry->list, &queue->queue_list);
        queue->queue_total++;
 }
 

@@ -243,11 +243,9 @@ static inline struct nfqnl_queue_entry *
 __find_entry(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
 		   unsigned long data)
 {
-	struct list_head *p;
-
-	list_for_each_prev(p, &queue->queue_list) {
-		struct nfqnl_queue_entry *entry = (struct nfqnl_queue_entry *)p;
+	struct nfqnl_queue_entry *entry;
 
+	list_for_each_entry(entry, &queue->queue_list, list) {
 		if (!cmpfn || cmpfn(entry, data))
 			return entry;
 	}

index 74d5ed9..cb901cf 100644
@@ -171,7 +171,8 @@ out_unlock:
 	return NULL;
 }
 
-static void nfqnl_flush(struct nfqnl_instance *queue, int verdict);
+static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
+			unsigned long data);
 
 static void
 _instance_destroy2(struct nfqnl_instance *inst, int lock)

@@ -188,7 +189,7 @@ _instance_destroy2(struct nfqnl_instance *inst, int lock)
 		write_unlock_bh(&instances_lock);
 
 	/* then flush all pending skbs from the queue */
-	nfqnl_flush(inst, NF_DROP);
+	nfqnl_flush(inst, NULL, 0);
 
 	/* and finally put the refcount */
 	instance_put(inst);

@@ -235,54 +236,6 @@ __enqueue_entry(struct nfqnl_instance *queue,
        queue->queue_total++;
 }
 
-/*
- * Find and return a queued entry matched by cmpfn, or return the last
- * entry if cmpfn is NULL.
- */
-static inline struct nfqnl_queue_entry *
-__find_entry(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
-		   unsigned long data)
-{
-	struct nfqnl_queue_entry *entry;
-
-	list_for_each_entry(entry, &queue->queue_list, list) {
-		if (!cmpfn || cmpfn(entry, data))
-			return entry;
-	}
-	return NULL;
-}
-
-static inline void
-__dequeue_entry(struct nfqnl_instance *q, struct nfqnl_queue_entry *entry)
-{
-	list_del(&entry->list);
-	q->queue_total--;
-}
-
-static inline struct nfqnl_queue_entry *
-__find_dequeue_entry(struct nfqnl_instance *queue,
-		     nfqnl_cmpfn cmpfn, unsigned long data)
-{
-	struct nfqnl_queue_entry *entry;
-
-	entry = __find_entry(queue, cmpfn, data);
-	if (entry == NULL)
-		return NULL;
-
-	__dequeue_entry(queue, entry);
-	return entry;
-}
-
-
-static inline void
-__nfqnl_flush(struct nfqnl_instance *queue, int verdict)
-{
-	struct nfqnl_queue_entry *entry;
-
-	while ((entry = __find_dequeue_entry(queue, NULL, 0)))
-		issue_verdict(entry, verdict);
-}
-
 static inline int
 __nfqnl_set_mode(struct nfqnl_instance *queue,
 		 unsigned char mode, unsigned int range)

@@ -313,23 +266,42 @@ __nfqnl_set_mode(struct nfqnl_instance *queue,
 }
 
 static struct nfqnl_queue_entry *
-find_dequeue_entry(struct nfqnl_instance *queue,
-			 nfqnl_cmpfn cmpfn, unsigned long data)
+find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id)
 {
-	struct nfqnl_queue_entry *entry;
+	struct nfqnl_queue_entry *entry = NULL, *i;
 
 	spin_lock_bh(&queue->lock);
-	entry = __find_dequeue_entry(queue, cmpfn, data);
+
+	list_for_each_entry(i, &queue->queue_list, list) {
+		if (i->id == id) {
+			entry = i;
+			break;
+		}
+	}
+
+	if (entry) {
+		list_del(&entry->list);
+		queue->queue_total--;
+	}
+
 	spin_unlock_bh(&queue->lock);
 
 	return entry;
 }
 
 static void
-nfqnl_flush(struct nfqnl_instance *queue, int verdict)
+nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
 {
+	struct nfqnl_queue_entry *entry, *next;
+
 	spin_lock_bh(&queue->lock);
-	__nfqnl_flush(queue, verdict);
+	list_for_each_entry_safe(entry, next, &queue->queue_list, list) {
+		if (!cmpfn || cmpfn(entry, data)) {
+			list_del(&entry->list);
+			queue->queue_total--;
+			issue_verdict(entry, NF_DROP);
+		}
+	}
 	spin_unlock_bh(&queue->lock);
 }
 

@@ -644,12 +616,6 @@ nfqnl_mangle(void *data, int data_len, struct nfqnl_queue_entry *e)
 	return 0;
 }
 
-static inline int
-id_cmp(struct nfqnl_queue_entry *e, unsigned long id)
-{
-	return (id == e->id);
-}
-
 static int
 nfqnl_set_mode(struct nfqnl_instance *queue,
 	       unsigned char mode, unsigned int range)

@@ -706,12 +672,8 @@ nfqnl_dev_drop(int ifindex)
 		struct nfqnl_instance *inst;
 		struct hlist_head *head = &instance_table[i];
 
-		hlist_for_each_entry(inst, tmp, head, hlist) {
-			struct nfqnl_queue_entry *entry;
-			while ((entry = find_dequeue_entry(inst, dev_cmp,
-							   ifindex)) != NULL)
-				issue_verdict(entry, NF_DROP);
-		}
+		hlist_for_each_entry(inst, tmp, head, hlist)
+			nfqnl_flush(inst, dev_cmp, ifindex);
 	}
 
 	read_unlock_bh(&instances_lock);

@@ -811,7 +773,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
 		goto err_out_put;
 	}
 
-	entry = find_dequeue_entry(queue, id_cmp, ntohl(vhdr->id));
+	entry = find_dequeue_entry(queue, ntohl(vhdr->id));
 	if (entry == NULL) {
 		err = -ENOENT;
 		goto err_out_put;

index 9e72246..df2957c 100644
@@ -77,52 +77,6 @@ __ipq_enqueue_entry(struct ipq_queue_entry *entry)
        queue_total++;
 }
 
-/*
- * Find and return a queued entry matched by cmpfn, or return the last
- * entry if cmpfn is NULL.
- */
-static inline struct ipq_queue_entry *
-__ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
-{
-	struct ipq_queue_entry *entry;
-
-	list_for_each_entry(entry, &queue_list, list) {
-		if (!cmpfn || cmpfn(entry, data))
-			return entry;
-	}
-	return NULL;
-}
-
-static inline void
-__ipq_dequeue_entry(struct ipq_queue_entry *entry)
-{
-	list_del(&entry->list);
-	queue_total--;
-}
-
-static inline struct ipq_queue_entry *
-__ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
-{
-	struct ipq_queue_entry *entry;
-
-	entry = __ipq_find_entry(cmpfn, data);
-	if (entry == NULL)
-		return NULL;
-
-	__ipq_dequeue_entry(entry);
-	return entry;
-}
-
-
-static inline void
-__ipq_flush(int verdict)
-{
-	struct ipq_queue_entry *entry;
-
-	while ((entry = __ipq_find_dequeue_entry(NULL, 0)))
-		ipq_issue_verdict(entry, verdict);
-}
-
 static inline int
 __ipq_set_mode(unsigned char mode, unsigned int range)
 {

@@ -149,31 +103,59 @@ __ipq_set_mode(unsigned char mode, unsigned int range)
 	return status;
 }
 
+static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data);
+
 static inline void
 __ipq_reset(void)
 {
 	peer_pid = 0;
 	net_disable_timestamp();
 	__ipq_set_mode(IPQ_COPY_NONE, 0);
-	__ipq_flush(NF_DROP);
+	__ipq_flush(NULL, 0);
 }
 
 static struct ipq_queue_entry *
-ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
+ipq_find_dequeue_entry(unsigned long id)
 {
-	struct ipq_queue_entry *entry;
+	struct ipq_queue_entry *entry = NULL, *i;
 
 	write_lock_bh(&queue_lock);
-	entry = __ipq_find_dequeue_entry(cmpfn, data);
+
+	list_for_each_entry(i, &queue_list, list) {
+		if ((unsigned long)i == id) {
+			entry = i;
+			break;
+		}
+	}
+
+	if (entry) {
+		list_del(&entry->list);
+		queue_total--;
+	}
+
 	write_unlock_bh(&queue_lock);
 	return entry;
 }
 
 static void
-ipq_flush(int verdict)
+__ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
+{
+	struct ipq_queue_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &queue_list, list) {
+		if (!cmpfn || cmpfn(entry, data)) {
+			list_del(&entry->list);
+			queue_total--;
+			ipq_issue_verdict(entry, NF_DROP);
+		}
+	}
+}
+
+static void
+ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 {
 	write_lock_bh(&queue_lock);
-	__ipq_flush(verdict);
+	__ipq_flush(cmpfn, data);
 	write_unlock_bh(&queue_lock);
 }
 

@@ -367,12 +349,6 @@ ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
 	return 0;
 }
 
-static inline int
-id_cmp(struct ipq_queue_entry *e, unsigned long id)
-{
-	return (id == (unsigned long )e);
-}
-
 static int
 ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 {

@@ -381,7 +357,7 @@ ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 	if (vmsg->value > NF_MAX_VERDICT)
 		return -EINVAL;
 
-	entry = ipq_find_dequeue_entry(id_cmp, vmsg->id);
+	entry = ipq_find_dequeue_entry(vmsg->id);
 	if (entry == NULL)
 		return -ENOENT;
 	else {

@@ -460,10 +436,7 @@ dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
 static void
 ipq_dev_drop(int ifindex)
 {
-	struct ipq_queue_entry *entry;
-
-	while ((entry = ipq_find_dequeue_entry(dev_cmp, ifindex)) != NULL)
-		ipq_issue_verdict(entry, NF_DROP);
+	ipq_flush(dev_cmp, ifindex);
 }
 
 #define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)

@@ -699,7 +672,7 @@ static void __exit ip_queue_fini(void)
 {
 	nf_unregister_queue_handlers(&nfqh);
 	synchronize_net();
-	ipq_flush(NF_DROP);
+	ipq_flush(NULL, 0);
 
 	unregister_sysctl_table(ipq_sysctl_header);
 	unregister_netdevice_notifier(&ipq_dev_notifier);

index 243a00b..7d0780d 100644
@@ -75,52 +75,6 @@ __ipq_enqueue_entry(struct ipq_queue_entry *entry)
        queue_total++;
 }
 
-/*
- * Find and return a queued entry matched by cmpfn, or return the last
- * entry if cmpfn is NULL.
- */
-static inline struct ipq_queue_entry *
-__ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
-{
-	struct ipq_queue_entry *entry;
-
-	list_for_each_entry(entry, &queue_list, list) {
-		if (!cmpfn || cmpfn(entry, data))
-			return entry;
-	}
-	return NULL;
-}
-
-static inline void
-__ipq_dequeue_entry(struct ipq_queue_entry *entry)
-{
-	list_del(&entry->list);
-	queue_total--;
-}
-
-static inline struct ipq_queue_entry *
-__ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
-{
-	struct ipq_queue_entry *entry;
-
-	entry = __ipq_find_entry(cmpfn, data);
-	if (entry == NULL)
-		return NULL;
-
-	__ipq_dequeue_entry(entry);
-	return entry;
-}
-
-
-static inline void
-__ipq_flush(int verdict)
-{
-	struct ipq_queue_entry *entry;
-
-	while ((entry = __ipq_find_dequeue_entry(NULL, 0)))
-		ipq_issue_verdict(entry, verdict);
-}
-
 static inline int
 __ipq_set_mode(unsigned char mode, unsigned int range)
 {

@@ -147,31 +101,59 @@ __ipq_set_mode(unsigned char mode, unsigned int range)
 	return status;
 }
 
+static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data);
+
 static inline void
 __ipq_reset(void)
 {
 	peer_pid = 0;
 	net_disable_timestamp();
 	__ipq_set_mode(IPQ_COPY_NONE, 0);
-	__ipq_flush(NF_DROP);
+	__ipq_flush(NULL, 0);
 }
 
 static struct ipq_queue_entry *
-ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
+ipq_find_dequeue_entry(unsigned long id)
 {
-	struct ipq_queue_entry *entry;
+	struct ipq_queue_entry *entry = NULL, *i;
 
 	write_lock_bh(&queue_lock);
-	entry = __ipq_find_dequeue_entry(cmpfn, data);
+
+	list_for_each_entry(i, &queue_list, list) {
+		if ((unsigned long)i == id) {
+			entry = i;
+			break;
+		}
+	}
+
+	if (entry) {
+		list_del(&entry->list);
+		queue_total--;
+	}
+
 	write_unlock_bh(&queue_lock);
 	return entry;
 }
 
 static void
-ipq_flush(int verdict)
+__ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
+{
+	struct ipq_queue_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &queue_list, list) {
+		if (!cmpfn || cmpfn(entry, data)) {
+			list_del(&entry->list);
+			queue_total--;
+			ipq_issue_verdict(entry, NF_DROP);
+		}
+	}
+}
+
+static void
+ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 {
 	write_lock_bh(&queue_lock);
-	__ipq_flush(verdict);
+	__ipq_flush(cmpfn, data);
 	write_unlock_bh(&queue_lock);
 }
 

@@ -364,12 +346,6 @@ ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
 	return 0;
 }
 
-static inline int
-id_cmp(struct ipq_queue_entry *e, unsigned long id)
-{
-	return (id == (unsigned long )e);
-}
-
 static int
 ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 {

@@ -378,7 +354,7 @@ ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 	if (vmsg->value > NF_MAX_VERDICT)
 		return -EINVAL;
 
-	entry = ipq_find_dequeue_entry(id_cmp, vmsg->id);
+	entry = ipq_find_dequeue_entry(vmsg->id);
 	if (entry == NULL)
 		return -ENOENT;
 	else {

@@ -449,10 +425,7 @@ dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
 static void
 ipq_dev_drop(int ifindex)
 {
-	struct ipq_queue_entry *entry;
-
-	while ((entry = ipq_find_dequeue_entry(dev_cmp, ifindex)) != NULL)
-		ipq_issue_verdict(entry, NF_DROP);
+	ipq_flush(dev_cmp, ifindex);
 }
 
 #define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)

@@ -689,7 +662,7 @@ static void __exit ip6_queue_fini(void)
 {
 	nf_unregister_queue_handlers(&nfqh);
 	synchronize_net();
-	ipq_flush(NF_DROP);
+	ipq_flush(NULL, 0);
 
 	unregister_sysctl_table(ipq_sysctl_header);
 	unregister_netdevice_notifier(&ipq_dev_notifier);

index 7d0780d..9c50cb1 100644
@@ -418,7 +418,16 @@ dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
 	if (entry->info->outdev)
 		if (entry->info->outdev->ifindex == ifindex)
 			return 1;
-
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (entry->skb->nf_bridge) {
+		if (entry->skb->nf_bridge->physindev &&
+		    entry->skb->nf_bridge->physindev->ifindex == ifindex)
+			return 1;
+		if (entry->skb->nf_bridge->physoutdev &&
+		    entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
+			return 1;
+	}
+#endif
 	return 0;
 }
 

index 5fe4ef4..f25eec5 100644
@@ -270,7 +270,7 @@ extern void nf_invalidate_cache(int pf);
 extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
 
 struct flowi;
-struct nf_info;
+struct nf_queue_entry;
 
 struct nf_afinfo {
 	unsigned short	family;

@@ -278,9 +278,9 @@ struct nf_afinfo {
 				    unsigned int dataoff, u_int8_t protocol);
 	int		(*route)(struct dst_entry **dst, struct flowi *fl);
 	void		(*saveroute)(const struct sk_buff *skb,
-				     struct nf_info *info);
+				     struct nf_queue_entry *entry);
 	int		(*reroute)(struct sk_buff *skb,
-				   const struct nf_info *info);
+				   const struct nf_queue_entry *entry);
 	int		route_key_size;
 };
 

index 8c6b382..d030044 100644
@@ -2,7 +2,11 @@
 #define _NF_QUEUE_H
 
 /* Each queued (to userspace) skbuff has one of these. */
-struct nf_info {
+struct nf_queue_entry {
+	struct list_head	list;
+	struct sk_buff		*skb;
+	unsigned int		id;
+
 	struct nf_hook_ops	*elem;
 	int			pf;
 	unsigned int		hook;

@@ -11,12 +15,11 @@ struct nf_info {
 	int			(*okfn)(struct sk_buff *);
 };
 
-#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info))
+#define nf_queue_entry_reroute(x) ((void *)x + sizeof(struct nf_queue_entry))
 
 /* Packet queuing */
 struct nf_queue_handler {
-	int			(*outfn)(struct sk_buff *skb,
-					 struct nf_info *info,
+	int			(*outfn)(struct nf_queue_entry *entry,
 					 unsigned int queuenum);
 	char			*name;
 };

@@ -26,7 +29,6 @@ extern int nf_register_queue_handler(int pf,
 extern int nf_unregister_queue_handler(int pf,
 				       const struct nf_queue_handler *qh);
 extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh);
-extern void nf_reinject(struct sk_buff *skb, struct nf_info *info,
-			unsigned int verdict);
+extern void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
 
 #endif /* _NF_QUEUE_H */

index f716608..7bf5e4a 100644
@@ -123,11 +123,12 @@ struct ip_rt_info {
 	u_int8_t tos;
 };
 
-static void nf_ip_saveroute(const struct sk_buff *skb, struct nf_info *info)
+static void nf_ip_saveroute(const struct sk_buff *skb,
+			    struct nf_queue_entry *entry)
 {
-	struct ip_rt_info *rt_info = nf_info_reroute(info);
+	struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_INET_LOCAL_OUT) {
+	if (entry->hook == NF_INET_LOCAL_OUT) {
 		const struct iphdr *iph = ip_hdr(skb);
 
 		rt_info->tos = iph->tos;

@@ -136,11 +137,12 @@ static void nf_ip_saveroute(const struct sk_buff *skb, struct nf_info *info)
 	}
 }
 
-static int nf_ip_reroute(struct sk_buff *skb, const struct nf_info *info)
+static int nf_ip_reroute(struct sk_buff *skb,
+			 const struct nf_queue_entry *entry)
 {
-	const struct ip_rt_info *rt_info = nf_info_reroute(info);
+	const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_INET_LOCAL_OUT) {
+	if (entry->hook == NF_INET_LOCAL_OUT) {
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (!(iph->tos == rt_info->tos

163 lines not on this page · raw message

index 55ea9c6..945e6ae 100644
@@ -57,11 +57,12 @@ struct ip6_rt_info {
 	struct in6_addr saddr;
 };
 
-static void nf_ip6_saveroute(const struct sk_buff *skb, struct nf_info *info)
+static void nf_ip6_saveroute(const struct sk_buff *skb,
+			     struct nf_queue_entry *entry)
 {
-	struct ip6_rt_info *rt_info = nf_info_reroute(info);
+	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_INET_LOCAL_OUT) {
+	if (entry->hook == NF_INET_LOCAL_OUT) {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		rt_info->daddr = iph->daddr;

@@ -69,11 +70,12 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, struct nf_info *info)
 	}
 }
 
-static int nf_ip6_reroute(struct sk_buff *skb, const struct nf_info *info)
+static int nf_ip6_reroute(struct sk_buff *skb,
+			  const struct nf_queue_entry *entry)
 {
-	struct ip6_rt_info *rt_info = nf_info_reroute(info);
+	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
-	if (info->hook == NF_INET_LOCAL_OUT) {
+	if (entry->hook == NF_INET_LOCAL_OUT) {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr))

159 lines not on this page · raw message

141 lines not on this page · raw message

205 lines not on this page · raw message

index f1affd2..68b12ce 100644
@@ -49,19 +49,6 @@ static struct sock *ipqnl __read_mostly;
 static LIST_HEAD(queue_list);
 static DEFINE_MUTEX(ipqnl_mutex);
 
-static void
-ipq_issue_verdict(struct nf_queue_entry *entry, int verdict)
-{
-	/* TCP input path (and probably other bits) assume to be called
-	 * from softirq context, not from syscall, like ipq_issue_verdict is
-	 * called.  TCP input path deadlocks with locks taken from timer
-	 * softirq, e.g.  We therefore emulate this by local_bh_disable() */
-
-	local_bh_disable();
-	nf_reinject(entry, verdict);
-	local_bh_enable();
-}
-
 static inline void
 __ipq_enqueue_entry(struct nf_queue_entry *entry)
 {

@@ -138,7 +125,7 @@ __ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 		if (!cmpfn || cmpfn(entry, data)) {
 			list_del(&entry->list);
 			queue_total--;
-			ipq_issue_verdict(entry, NF_DROP);
+			nf_reinject(entry, NF_DROP);
 		}
 	}
 }

@@ -345,7 +332,7 @@ ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 			if (ipq_mangle_ipv4(vmsg, entry) < 0)
 				verdict = NF_DROP;
 
-		ipq_issue_verdict(entry, verdict);
+		nf_reinject(entry, verdict);
 		return 0;
 	}
 }

index 9014ada..e5b0059 100644
@@ -53,14 +53,6 @@ static struct sock *ipqnl __read_mostly;
 static LIST_HEAD(queue_list);
 static DEFINE_MUTEX(ipqnl_mutex);
 
-static void
-ipq_issue_verdict(struct nf_queue_entry *entry, int verdict)
-{
-	local_bh_disable();
-	nf_reinject(entry, verdict);
-	local_bh_enable();
-}
-
 static inline void
 __ipq_enqueue_entry(struct nf_queue_entry *entry)
 {

@@ -137,7 +129,7 @@ __ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 		if (!cmpfn || cmpfn(entry, data)) {
 			list_del(&entry->list);
 			queue_total--;
-			ipq_issue_verdict(entry, NF_DROP);
+			nf_reinject(entry, NF_DROP);
 		}
 	}
 }

@@ -343,7 +335,7 @@ ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
 			if (ipq_mangle_ipv6(vmsg, entry) < 0)
 				verdict = NF_DROP;
 
-		ipq_issue_verdict(entry, verdict);
+		nf_reinject(entry, verdict);
 		return 0;
 	}
 }

index d9d3dc4..f0dc727 100644
@@ -275,7 +275,9 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	switch (verdict & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_STOP:
+		local_bh_disable();
 		entry->okfn(skb);
+		local_bh_enable();
 	case NF_STOLEN:
 		break;
 	case NF_QUEUE:

index a493764..d9ce394 100644
@@ -202,23 +202,6 @@ instance_destroy(struct nfqnl_instance *inst)
 	_instance_destroy2(inst, 1);
 }
 
-
-
-static void
-issue_verdict(struct nf_queue_entry *entry, int verdict)
-{
-	QDEBUG("entering for entry %p, verdict %u\n", entry, verdict);
-
-	/* TCP input path (and probably other bits) assume to be called
-	 * from softirq context, not from syscall, like issue_verdict is
-	 * called.  TCP input path deadlocks with locks taken from timer
-	 * softirq, e.g.  We therefore emulate this by local_bh_disable() */
-
-	local_bh_disable();
-	nf_reinject(entry, verdict);
-	local_bh_enable();
-}
-
 static inline void
 __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
 {

@@ -289,7 +272,7 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
 		if (!cmpfn || cmpfn(entry, data)) {
 			list_del(&entry->list);
 			queue->queue_total--;
-			issue_verdict(entry, NF_DROP);
+			nf_reinject(entry, NF_DROP);
 		}
 	}
 	spin_unlock_bh(&queue->lock);

@@ -761,7 +744,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
 		entry->skb->mark = ntohl(*(__be32 *)
 					 nla_data(nfqa[NFQA_MARK]));
 
-	issue_verdict(entry, verdict);
+	nf_reinject(entry, verdict);
 	instance_put(queue);
 	return 0;
 

index f0dc727..7796511 100644
@@ -80,6 +80,27 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
 }
 EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers);
 
+static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
+{
+	/* Release those devices we held, or Alexey will kill me. */
+	if (entry->indev)
+		dev_put(entry->indev);
+	if (entry->outdev)
+		dev_put(entry->outdev);
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (entry->skb->nf_bridge) {
+		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
+
+		if (nf_bridge->physindev)
+			dev_put(nf_bridge->physindev);
+		if (nf_bridge->physoutdev)
+			dev_put(nf_bridge->physoutdev);
+	}
+#endif
+	/* Drop reference to owner of hook which queued us. */
+	module_put(entry->elem->owner);
+}
+
 /*
  * Any packet that leaves via this function must come back
  * through nf_reinject().