X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=net%2Fipv4%2Fnetfilter%2Fip_tables.c;h=4e7c719445c264c9f55dc00fa1c6ce3d4fc36671;hb=9a5467fd600669cda488771dac3e951034fe2b08;hp=07be12cc3fe35179a709506f700bb979347ca0a1;hpb=b386d9f5960a9afce7f077edf2095fccfbb1a8e6;p=linux-2.6

diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 07be12cc3f..4e7c719445 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -26,6 +26,7 @@
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
+#include <net/netfilter/nf_log.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -52,7 +53,7 @@ MODULE_DESCRIPTION("IPv4 packet filter");
 do {								\
 	if (!(x))						\
 		printk("IP_NF_ASSERT: %s:%s:%u\n",		\
-		       __FUNCTION__, __FILE__, __LINE__);	\
+		       __func__, __FILE__, __LINE__);	\
 } while(0)
 #else
 #define IP_NF_ASSERT(x)
@@ -74,7 +75,8 @@ do {								\
    Hence the start of any table is given by get_table() below.  */
 
 /* Returns whether matches rule or not. */
-static inline int
+/* Performance critical - called for every packet */
+static inline bool
 ip_packet_match(const struct iphdr *ip,
 		const char *indev,
 		const char *outdev,
@@ -84,7 +86,7 @@ ip_packet_match(const struct iphdr *ip,
 	size_t i;
 	unsigned long ret;
 
-#define FWINV(bool,invflg) ((bool) ^ !!(ipinfo->invflags & invflg))
+#define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg)))
 
 	if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr,
 		  IPT_INV_SRCIP)
@@ -102,7 +104,7 @@ ip_packet_match(const struct iphdr *ip,
 			NIPQUAD(ipinfo->dmsk.s_addr),
 			NIPQUAD(ipinfo->dst.s_addr),
 			ipinfo->invflags & IPT_INV_DSTIP ? " (INV)" : "");
-		return 0;
+		return false;
 	}
 
 	/* Look for ifname matches; this should unroll nicely. */
@@ -116,7 +118,7 @@ ip_packet_match(const struct iphdr *ip,
 		dprintf("VIA in mismatch (%s vs %s).%s\n",
 			indev, ipinfo->iniface,
 			ipinfo->invflags&IPT_INV_VIA_IN ?" (INV)":"");
-		return 0;
+		return false;
 	}
 
 	for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
@@ -129,7 +131,7 @@ ip_packet_match(const struct iphdr *ip,
 		dprintf("VIA out mismatch (%s vs %s).%s\n",
 			outdev, ipinfo->outiface,
 			ipinfo->invflags&IPT_INV_VIA_OUT ?" (INV)":"");
-		return 0;
+		return false;
 	}
 
 	/* Check specific protocol */
@@ -138,7 +140,7 @@ ip_packet_match(const struct iphdr *ip,
 		dprintf("Packet protocol %hi does not match %hi.%s\n",
 			ip->protocol, ipinfo->proto,
 			ipinfo->invflags&IPT_INV_PROTO ? " (INV)":"");
-		return 0;
+		return false;
 	}
 
 	/* If we have a fragment rule but the packet is not a fragment
@@ -146,13 +148,13 @@ ip_packet_match(const struct iphdr *ip,
 	if (FWINV((ipinfo->flags&IPT_F_FRAG) && !isfrag, IPT_INV_FRAG)) {
 		dprintf("Fragment rule but not fragment.%s\n",
 			ipinfo->invflags & IPT_INV_FRAG ? " (INV)" : "");
-		return 0;
+		return false;
 	}
 
-	return 1;
+	return true;
 }
 
-static inline bool
+static bool
 ip_checkentry(const struct ipt_ip *ip)
 {
 	if (ip->flags & ~IPT_F_MASK) {
@@ -182,8 +184,9 @@ ipt_error(struct sk_buff *skb,
 	return NF_DROP;
 }
 
-static inline
-bool do_match(struct ipt_entry_match *m,
+/* Performance critical - called for every packet */
+static inline bool
+do_match(struct ipt_entry_match *m,
 	      const struct sk_buff *skb,
 	      const struct net_device *in,
 	      const struct net_device *out,
@@ -198,6 +201,7 @@ bool do_match(struct ipt_entry_match *m,
 		return false;
 }
 
+/* Performance critical */
 static inline struct ipt_entry *
 get_entry(void *base, unsigned int offset)
 {
@@ -205,6 +209,7 @@ get_entry(void *base, unsigned int offset)
 }
 
 /* All zeroes == unconditional rule. */
+/* Mildly perf critical (only if packet tracing is on) */
 static inline int
 unconditional(const struct ipt_ip *ip)
 {
@@ -215,14 +220,15 @@ unconditional(const struct ipt_ip *ip)
 			return 0;
 
 	return 1;
+#undef FWINV
 }
 
 #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
     defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-static const char *hooknames[] = {
+static const char *const hooknames[] = {
 	[NF_INET_PRE_ROUTING]		= "PREROUTING",
 	[NF_INET_LOCAL_IN]		= "INPUT",
-	[NF_INET_FORWARD]			= "FORWARD",
+	[NF_INET_FORWARD]		= "FORWARD",
 	[NF_INET_LOCAL_OUT]		= "OUTPUT",
 	[NF_INET_POST_ROUTING]		= "POSTROUTING",
 };
@@ -233,7 +239,7 @@ enum nf_ip_trace_comments {
 	NF_IP_TRACE_COMMENT_POLICY,
 };
 
-static const char *comments[] = {
+static const char *const comments[] = {
 	[NF_IP_TRACE_COMMENT_RULE]	= "rule",
 	[NF_IP_TRACE_COMMENT_RETURN]	= "return",
 	[NF_IP_TRACE_COMMENT_POLICY]	= "policy",
@@ -249,6 +255,7 @@ static struct nf_loginfo trace_loginfo = {
 	},
 };
 
+/* Mildly perf critical (only if packet tracing is on) */
 static inline int
 get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
 		      char *hookname, char **chainname,
@@ -284,12 +291,12 @@ static void trace_packet(struct sk_buff *skb,
 			 unsigned int hook,
 			 const struct net_device *in,
 			 const struct net_device *out,
-			 char *tablename,
+			 const char *tablename,
 			 struct xt_table_info *private,
 			 struct ipt_entry *e)
 {
 	void *table_base;
-	struct ipt_entry *root;
+	const struct ipt_entry *root;
 	char *hookname, *chainname, *comment;
 	unsigned int rulenum = 0;
 
@@ -320,7 +327,7 @@ ipt_do_table(struct sk_buff *skb,
 {
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	u_int16_t offset;
-	struct iphdr *ip;
+	const struct iphdr *ip;
 	u_int16_t datalen;
 	bool hotdrop = false;
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
@@ -467,8 +474,7 @@ mark_source_chains(struct xt_table_info *newinfo,
 	   to 0 as we leave), and comefrom to save source hook bitmask */
 	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
-		struct ipt_entry *e
-			= (struct ipt_entry *)(entry0 + pos);
+		struct ipt_entry *e = (struct ipt_entry *)(entry0 + pos);
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
@@ -486,8 +492,7 @@ mark_source_chains(struct xt_table_info *newinfo,
 				       hook, pos, e->comefrom);
 				return 0;
 			}
-			e->comefrom
-				|= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
+			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
 			if ((e->target_offset == sizeof(struct ipt_entry)
@@ -567,7 +572,7 @@ mark_source_chains(struct xt_table_info *newinfo,
 	return 1;
 }
 
-static inline int
+static int
 cleanup_match(struct ipt_entry_match *m, unsigned int *i)
 {
 	if (i && (*i)-- == 0)
@@ -579,7 +584,7 @@ cleanup_match(struct ipt_entry_match *m, unsigned int *i)
 	return 0;
 }
 
-static inline int
+static int
 check_entry(struct ipt_entry *e, const char *name)
 {
 	struct ipt_entry_target *t;
@@ -589,7 +594,8 @@ check_entry(struct ipt_entry *e, const char *name)
 		return -EINVAL;
 	}
 
-	if (e->target_offset + sizeof(struct ipt_entry_target) > e->next_offset)
+	if (e->target_offset + sizeof(struct ipt_entry_target) >
+	    e->next_offset)
 		return -EINVAL;
 
 	t = ipt_get_target(e);
@@ -599,7 +605,8 @@ check_entry(struct ipt_entry *e, const char *name)
 	return 0;
 }
 
-static inline int check_match(struct ipt_entry_match *m, const char *name,
+static int
+check_match(struct ipt_entry_match *m, const char *name,
 			      const struct ipt_ip *ip,
 			      unsigned int hookmask, unsigned int *i)
 {
@@ -622,7 +629,7 @@ static inline int check_match(struct ipt_entry_match *m, const char *name,
 	return ret;
 }
 
-static inline int
+static int
 find_check_match(struct ipt_entry_match *m,
 		 const char *name,
 		 const struct ipt_ip *ip,
@@ -633,7 +640,7 @@ find_check_match(struct ipt_entry_match *m,
 	int ret;
 
 	match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name,
-						   m->u.user.revision),
+						      m->u.user.revision),
 					"ipt_%s", m->u.user.name);
 	if (IS_ERR(match) || !match) {
 		duprintf("find_check_match: `%s' not found\n", m->u.user.name);
@@ -651,7 +658,7 @@ err:
 	return ret;
 }
 
-static inline int check_target(struct ipt_entry *e, const char *name)
+static int check_target(struct ipt_entry *e, const char *name)
 {
 	struct ipt_entry_target *t;
 	struct xt_target *target;
@@ -672,7 +679,7 @@ static inline int check_target(struct ipt_entry *e, const char *name)
 	return ret;
 }
 
-static inline int
+static int
 find_check_entry(struct ipt_entry *e, const char *name, unsigned int size,
 		 unsigned int *i)
 {
@@ -716,7 +723,7 @@ find_check_entry(struct ipt_entry *e, const char *name, unsigned int size,
 	return ret;
 }
 
-static inline int
+static int
 check_entry_size_and_hooks(struct ipt_entry *e,
 			   struct xt_table_info *newinfo,
 			   unsigned char *base,
@@ -759,7 +766,7 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 	return 0;
 }
 
-static inline int
+static int
 cleanup_entry(struct ipt_entry *e, unsigned int *i)
 {
 	struct ipt_entry_target *t;
@@ -915,11 +922,11 @@ get_counters(const struct xt_table_info *t,
 	}
 }
 
-static inline struct xt_counters * alloc_counters(struct xt_table *table)
+static struct xt_counters * alloc_counters(struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = table->private;
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -946,9 +953,9 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	struct ipt_entry *e;
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = table->private;
 	int ret = 0;
-	void *loc_cpu_entry;
+	const void *loc_cpu_entry;
 
 	counters = alloc_counters(table);
 	if (IS_ERR(counters))
@@ -959,7 +966,6 @@ copy_entries_to_user(unsigned int total_size,
 	 * allowed to migrate to another cpu)
 	 */
 	loc_cpu_entry = private->entries[raw_smp_processor_id()];
-	/* ... then copy entire thing ... */
 	if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
 		ret = -EFAULT;
 		goto free_counters;
@@ -969,8 +975,8 @@ copy_entries_to_user(unsigned int total_size,
 	/* ... then go back and fix counters and names */
 	for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){
 		unsigned int i;
-		struct ipt_entry_match *m;
-		struct ipt_entry_target *t;
+		const struct ipt_entry_match *m;
+		const struct ipt_entry_target *t;
 
 		e = (struct ipt_entry *)(loc_cpu_entry + off);
 		if (copy_to_user(userptr + off
@@ -1086,15 +1092,15 @@ static int compat_table_info(const struct xt_table_info *info,
 }
 #endif
 
-static int get_info(void __user *user, int *len, int compat)
+static int get_info(struct net *net, void __user *user, int *len, int compat)
 {
 	char name[IPT_TABLE_MAXNAMELEN];
 	struct xt_table *t;
 	int ret;
 
 	if (*len != sizeof(struct ipt_getinfo)) {
-		duprintf("length %u != %u\n", *len,
-			(unsigned int)sizeof(struct ipt_getinfo));
+		duprintf("length %u != %zu\n", *len,
+			 sizeof(struct ipt_getinfo));
 		return -EINVAL;
 	}
 
@@ -1106,11 +1112,11 @@ static int get_info(void __user *user, int *len, int compat)
 	if (compat)
 		xt_compat_lock(AF_INET);
 #endif
-	t = try_then_request_module(xt_find_table_lock(AF_INET, name),
+	t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
 				    "iptable_%s", name);
 	if (t && !IS_ERR(t)) {
 		struct ipt_getinfo info;
-		struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = t->private;
 
 #ifdef CONFIG_COMPAT
 		if (compat) {
@@ -1146,39 +1152,35 @@ static int get_info(void __user *user, int *len, int compat)
 }
 
 static int
-get_entries(struct ipt_get_entries __user *uptr, int *len)
+get_entries(struct net *net, struct ipt_get_entries __user *uptr, int *len)
 {
 	int ret;
 	struct ipt_get_entries get;
 	struct xt_table *t;
 
 	if (*len < sizeof(get)) {
-		duprintf("get_entries: %u < %d\n", *len,
-				(unsigned int)sizeof(get));
+		duprintf("get_entries: %u < %zu\n", *len, sizeof(get));
 		return -EINVAL;
 	}
 	if (copy_from_user(&get, uptr, sizeof(get)) != 0)
 		return -EFAULT;
 	if (*len != sizeof(struct ipt_get_entries) + get.size) {
-		duprintf("get_entries: %u != %u\n", *len,
-				(unsigned int)(sizeof(struct ipt_get_entries) +
-				get.size));
+		duprintf("get_entries: %u != %zu\n",
+			 *len, sizeof(get) + get.size);
 		return -EINVAL;
 	}
 
-	t = xt_find_table_lock(AF_INET, get.name);
+	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (t && !IS_ERR(t)) {
-		struct xt_table_info *private = t->private;
-		duprintf("t->private->number = %u\n",
-			 private->number);
+		const struct xt_table_info *private = t->private;
+		duprintf("t->private->number = %u\n", private->number);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
 		else {
 			duprintf("get_entries: I've got %u not %u!\n",
-				 private->size,
-				 get.size);
-			ret = -EINVAL;
+				 private->size, get.size);
+			ret = -EAGAIN;
 		}
 		module_put(t->me);
 		xt_table_unlock(t);
@@ -1189,7 +1191,7 @@ get_entries(struct ipt_get_entries __user *uptr, int *len)
 }
 
 static int
-__do_replace(const char *name, unsigned int valid_hooks,
+__do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 	     struct xt_table_info *newinfo, unsigned int num_counters,
 	     void __user *counters_ptr)
 {
@@ -1206,7 +1208,7 @@ __do_replace(const char *name, unsigned int valid_hooks,
 		goto out;
 	}
 
-	t = try_then_request_module(xt_find_table_lock(AF_INET, name),
+	t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
 				    "iptable_%s", name);
 	if (!t || IS_ERR(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
@@ -1259,7 +1261,7 @@ __do_replace(const char *name, unsigned int valid_hooks,
 }
 
 static int
-do_replace(void __user *user, unsigned int len)
+do_replace(struct net *net, void __user *user, unsigned int len)
 {
 	int ret;
 	struct ipt_replace tmp;
@@ -1269,10 +1271,6 @@ do_replace(void __user *user, unsigned int len)
 	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
 		return -EFAULT;
 
-	/* Hack: Causes ipchains to give correct error msg --RR */
-	if (len != sizeof(tmp) + tmp.size)
-		return -ENOPROTOOPT;
-
 	/* overflow check */
 	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
 		return -ENOMEM;
@@ -1281,7 +1279,7 @@ do_replace(void __user *user, unsigned int len)
 	if (!newinfo)
 		return -ENOMEM;
 
-	/* choose the copy that is our node/cpu */
+	/* choose the copy that is on our node/cpu */
 	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
 	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
 			   tmp.size) != 0) {
@@ -1297,14 +1295,14 @@ do_replace(void __user *user, unsigned int len)
 
 	duprintf("ip_tables: Translated table\n");
 
-	ret = __do_replace(tmp.name, tmp.valid_hooks, newinfo,
+	ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo,
 			   tmp.num_counters, tmp.counters);
 	if (ret)
 		goto free_newinfo_untrans;
 	return 0;
 
  free_newinfo_untrans:
-	IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL);
+	IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
  free_newinfo:
 	xt_free_table_info(newinfo);
 	return ret;
@@ -1312,7 +1310,7 @@ do_replace(void __user *user, unsigned int len)
 
 /* We're lazy, and add to the first CPU; overflow works its fey magic
  * and everything is OK. */
-static inline int
+static int
 add_counter_to_entry(struct ipt_entry *e,
 		     const struct xt_counters addme[],
 		     unsigned int *i)
@@ -1333,17 +1331,17 @@ add_counter_to_entry(struct ipt_entry *e,
 }
 
 static int
-do_add_counters(void __user *user, unsigned int len, int compat)
+do_add_counters(struct net *net, void __user *user, unsigned int len, int compat)
 {
 	unsigned int i;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
 	unsigned int num_counters;
-	char *name;
+	const char *name;
 	int size;
 	void *ptmp;
 	struct xt_table *t;
-	struct xt_table_info *private;
+	const struct xt_table_info *private;
 	int ret = 0;
 	void *loc_cpu_entry;
 #ifdef CONFIG_COMPAT
@@ -1385,7 +1383,7 @@ do_add_counters(void __user *user, unsigned int len, int compat)
 		goto free;
 	}
 
-	t = xt_find_table_lock(AF_INET, name);
+	t = xt_find_table_lock(net, AF_INET, name);
 	if (!t || IS_ERR(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1431,7 +1429,7 @@ struct compat_ipt_replace {
 
 static int
 compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
-			  compat_uint_t *size, struct xt_counters *counters,
+			  unsigned int *size, struct xt_counters *counters,
 			  unsigned int *i)
 {
 	struct ipt_entry_target *t;
@@ -1473,12 +1471,12 @@ out:
 	return ret;
 }
 
-static inline int
+static int
 compat_find_calc_match(struct ipt_entry_match *m,
 		       const char *name,
 		       const struct ipt_ip *ip,
 		       unsigned int hookmask,
-		       int *size, int *i)
+		       int *size, unsigned int *i)
 {
 	struct xt_match *match;
 
@@ -1497,7 +1495,7 @@ compat_find_calc_match(struct ipt_entry_match *m,
 	return 0;
 }
 
-static inline int
+static int
 compat_release_match(struct ipt_entry_match *m, unsigned int *i)
 {
 	if (i && (*i)-- == 0)
@@ -1507,7 +1505,7 @@ compat_release_match(struct ipt_entry_match *m, unsigned int *i)
 	return 0;
 }
 
-static inline int
+static int
 compat_release_entry(struct compat_ipt_entry *e, unsigned int *i)
 {
 	struct ipt_entry_target *t;
@@ -1522,7 +1520,7 @@ compat_release_entry(struct compat_ipt_entry *e, unsigned int *i)
 	return 0;
 }
 
-static inline int
+static int
 check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
@@ -1536,7 +1534,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	struct ipt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
-	int ret, off, h, j;
+	unsigned int j;
+	int ret, off, h;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0
@@ -1645,13 +1644,16 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	return ret;
 }
 
-static inline int compat_check_entry(struct ipt_entry *e, const char *name,
+static int
+compat_check_entry(struct ipt_entry *e, const char *name,
 				     unsigned int *i)
 {
-	int j, ret;
+	unsigned int j;
+	int ret;
 
 	j = 0;
-	ret = IPT_MATCH_ITERATE(e, check_match, name, &e->ip, e->comefrom, &j);
+	ret = IPT_MATCH_ITERATE(e, check_match, name, &e->ip,
+				e->comefrom, &j);
 	if (ret)
 		goto cleanup_matches;
 
@@ -1744,8 +1746,8 @@ translate_compat_table(const char *name,
 	pos = entry1;
 	size = total_size;
 	ret = COMPAT_IPT_ENTRY_ITERATE(entry0, total_size,
-				       compat_copy_entry_from_user, &pos, &size,
-				       name, newinfo, entry1);
+				       compat_copy_entry_from_user,
+				       &pos, &size, name, newinfo, entry1);
 	xt_compat_flush_offsets(AF_INET);
 	xt_compat_unlock(AF_INET);
 	if (ret)
@@ -1789,7 +1791,7 @@ out_unlock:
 }
 
 static int
-compat_do_replace(void __user *user, unsigned int len)
+compat_do_replace(struct net *net, void __user *user, unsigned int len)
 {
 	int ret;
 	struct compat_ipt_replace tmp;
@@ -1799,10 +1801,6 @@ compat_do_replace(void __user *user, unsigned int len)
 	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
 		return -EFAULT;
 
-	/* Hack: Causes ipchains to give correct error msg --RR */
-	if (len != sizeof(tmp) + tmp.size)
-		return -ENOPROTOOPT;
-
 	/* overflow check */
 	if (tmp.size >= INT_MAX / num_possible_cpus())
 		return -ENOMEM;
@@ -1813,7 +1811,7 @@ compat_do_replace(void __user *user, unsigned int len)
 	if (!newinfo)
 		return -ENOMEM;
 
-	/* choose the copy that is our node/cpu */
+	/* choose the copy that is on our node/cpu */
 	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
 	if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
 			   tmp.size) != 0) {
@@ -1830,7 +1828,7 @@ compat_do_replace(void __user *user, unsigned int len)
 
 	duprintf("compat_do_replace: Translated table\n");
 
-	ret = __do_replace(tmp.name, tmp.valid_hooks, newinfo,
+	ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo,
 			   tmp.num_counters, compat_ptr(tmp.counters));
 	if (ret)
 		goto free_newinfo_untrans;
@@ -1854,11 +1852,11 @@ compat_do_ipt_set_ctl(struct sock *sk,	int cmd, void __user *user,
 
 	switch (cmd) {
 	case IPT_SO_SET_REPLACE:
-		ret = compat_do_replace(user, len);
+		ret = compat_do_replace(sock_net(sk), user, len);
 		break;
 
 	case IPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(user, len, 1);
+		ret = do_add_counters(sock_net(sk), user, len, 1);
 		break;
 
 	default:
@@ -1880,11 +1878,11 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = table->private;
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
-	void *loc_cpu_entry;
+	const void *loc_cpu_entry;
 	unsigned int i = 0;
 
 	counters = alloc_counters(table);
@@ -1907,15 +1905,15 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 }
 
 static int
-compat_get_entries(struct compat_ipt_get_entries __user *uptr, int *len)
+compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
+		   int *len)
 {
 	int ret;
 	struct compat_ipt_get_entries get;
 	struct xt_table *t;
 
 	if (*len < sizeof(get)) {
-		duprintf("compat_get_entries: %u < %u\n",
-			 *len, (unsigned int)sizeof(get));
+		duprintf("compat_get_entries: %u < %zu\n", *len, sizeof(get));
 		return -EINVAL;
 	}
 
@@ -1923,28 +1921,25 @@ compat_get_entries(struct compat_ipt_get_entries __user *uptr, int *len)
 		return -EFAULT;
 
 	if (*len != sizeof(struct compat_ipt_get_entries) + get.size) {
-		duprintf("compat_get_entries: %u != %u\n", *len,
-			 (unsigned int)(sizeof(struct compat_ipt_get_entries) +
-			 get.size));
+		duprintf("compat_get_entries: %u != %zu\n",
+			 *len, sizeof(get) + get.size);
 		return -EINVAL;
 	}
 
 	xt_compat_lock(AF_INET);
-	t = xt_find_table_lock(AF_INET, get.name);
+	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (t && !IS_ERR(t)) {
-		struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = t->private;
 		struct xt_table_info info;
-		duprintf("t->private->number = %u\n",
-			 private->number);
+		duprintf("t->private->number = %u\n", private->number);
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size) {
 			ret = compat_copy_entries_to_user(private->size,
 							  t, uptr->entrytable);
 		} else if (!ret) {
 			duprintf("compat_get_entries: I've got %u not %u!\n",
-				 private->size,
-				 get.size);
-			ret = -EINVAL;
+				 private->size, get.size);
+			ret = -EAGAIN;
 		}
 		xt_compat_flush_offsets(AF_INET);
 		module_put(t->me);
@@ -1968,10 +1963,10 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 
 	switch (cmd) {
 	case IPT_SO_GET_INFO:
-		ret = get_info(user, len, 1);
+		ret = get_info(sock_net(sk), user, len, 1);
 		break;
 	case IPT_SO_GET_ENTRIES:
-		ret = compat_get_entries(user, len);
+		ret = compat_get_entries(sock_net(sk), user, len);
 		break;
 	default:
 		ret = do_ipt_get_ctl(sk, cmd, user, len);
@@ -1981,7 +1976,7 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 #endif
 
 static int
-do_ipt_set_ctl(struct sock *sk,	int cmd, void __user *user, unsigned int len)
+do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 {
 	int ret;
 
@@ -1990,11 +1985,11 @@ do_ipt_set_ctl(struct sock *sk,	int cmd, void __user *user, unsigned int len)
 
 	switch (cmd) {
 	case IPT_SO_SET_REPLACE:
-		ret = do_replace(user, len);
+		ret = do_replace(sock_net(sk), user, len);
 		break;
 
 	case IPT_SO_SET_ADD_COUNTERS:
-		ret = do_add_counters(user, len, 0);
+		ret = do_add_counters(sock_net(sk), user, len, 0);
 		break;
 
 	default:
@@ -2015,11 +2010,11 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 
 	switch (cmd) {
 	case IPT_SO_GET_INFO:
-		ret = get_info(user, len, 0);
+		ret = get_info(sock_net(sk), user, len, 0);
 		break;
 
 	case IPT_SO_GET_ENTRIES:
-		ret = get_entries(user, len);
+		ret = get_entries(sock_net(sk), user, len);
 		break;
 
 	case IPT_SO_GET_REVISION_MATCH:
@@ -2056,21 +2051,23 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
-int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl)
+struct xt_table *ipt_register_table(struct net *net, struct xt_table *table,
+				    const struct ipt_replace *repl)
 {
 	int ret;
 	struct xt_table_info *newinfo;
 	struct xt_table_info bootstrap
 		= { 0, 0, 0, { 0 }, { 0 }, { } };
 	void *loc_cpu_entry;
+	struct xt_table *new_table;
 
 	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo)
-		return -ENOMEM;
+	if (!newinfo) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
-	/* choose the copy on our node/cpu
-	 * but dont care of preemption
-	 */
+	/* choose the copy on our node/cpu, but dont care about preemption */
 	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
 	memcpy(loc_cpu_entry, repl->entries, repl->size);
 
@@ -2079,30 +2076,36 @@ int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl)
 			      repl->num_entries,
 			      repl->hook_entry,
 			      repl->underflow);
-	if (ret != 0) {
-		xt_free_table_info(newinfo);
-		return ret;
-	}
+	if (ret != 0)
+		goto out_free;
 
-	ret = xt_register_table(table, &bootstrap, newinfo);
-	if (ret != 0) {
-		xt_free_table_info(newinfo);
-		return ret;
+	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	if (IS_ERR(new_table)) {
+		ret = PTR_ERR(new_table);
+		goto out_free;
 	}
 
-	return 0;
+	return new_table;
+
+out_free:
+	xt_free_table_info(newinfo);
+out:
+	return ERR_PTR(ret);
 }
 
 void ipt_unregister_table(struct xt_table *table)
 {
 	struct xt_table_info *private;
 	void *loc_cpu_entry;
+	struct module *table_owner = table->me;
 
 	private = xt_unregister_table(table);
 
 	/* Decrease module usage counts and free resources */
 	loc_cpu_entry = private->entries[raw_smp_processor_id()];
 	IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL);
+	if (private->number > private->initial_entries)
+		module_put(table_owner);
 	xt_free_table_info(private);
 }
 
@@ -2112,7 +2115,8 @@ icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,
 		     u_int8_t type, u_int8_t code,
 		     bool invert)
 {
-	return ((test_type == 0xFF) || (type == test_type && code >= min_code && code <= max_code))
+	return ((test_type == 0xFF) ||
+		(type == test_type && code >= min_code && code <= max_code))
 		^ invert;
 }
 
@@ -2126,7 +2130,8 @@ icmp_match(const struct sk_buff *skb,
 	   unsigned int protoff,
 	   bool *hotdrop)
 {
-	struct icmphdr _icmph, *ic;
+	const struct icmphdr *ic;
+	struct icmphdr _icmph;
 	const struct ipt_icmp *icmpinfo = matchinfo;
 
 	/* Must not be a fragment. */
@@ -2153,7 +2158,7 @@ icmp_match(const struct sk_buff *skb,
 /* Called when user tries to insert an entry of this type. */
 static bool
 icmp_checkentry(const char *tablename,
-	   const void *info,
+	   const void *entry,
 	   const struct xt_match *match,
 	   void *matchinfo,
 	   unsigned int hook_mask)
@@ -2204,16 +2209,31 @@ static struct xt_match icmp_matchstruct __read_mostly = {
 	.name		= "icmp",
 	.match		= icmp_match,
 	.matchsize	= sizeof(struct ipt_icmp),
+	.checkentry	= icmp_checkentry,
 	.proto		= IPPROTO_ICMP,
 	.family		= AF_INET,
-	.checkentry	= icmp_checkentry,
+};
+
+static int __net_init ip_tables_net_init(struct net *net)
+{
+	return xt_proto_init(net, AF_INET);
+}
+
+static void __net_exit ip_tables_net_exit(struct net *net)
+{
+	xt_proto_fini(net, AF_INET);
+}
+
+static struct pernet_operations ip_tables_net_ops = {
+	.init = ip_tables_net_init,
+	.exit = ip_tables_net_exit,
 };
 
 static int __init ip_tables_init(void)
 {
 	int ret;
 
-	ret = xt_proto_init(AF_INET);
+	ret = register_pernet_subsys(&ip_tables_net_ops);
 	if (ret < 0)
 		goto err1;
 
@@ -2243,7 +2263,7 @@ err4:
 err3:
 	xt_unregister_target(&ipt_standard_target);
 err2:
-	xt_proto_fini(AF_INET);
+	unregister_pernet_subsys(&ip_tables_net_ops);
 err1:
 	return ret;
 }
@@ -2256,7 +2276,7 @@ static void __exit ip_tables_fini(void)
 	xt_unregister_target(&ipt_error_target);
 	xt_unregister_target(&ipt_standard_target);
 
-	xt_proto_fini(AF_INET);
+	unregister_pernet_subsys(&ip_tables_net_ops);
 }
 
 EXPORT_SYMBOL(ipt_register_table);