1 files changed, 115 insertions, 145 deletions

diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b29c66df8d1f..63958f3394a5 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -39,24 +39,19 @@ MODULE_DESCRIPTION("IPv4 packet filter");
 /*#define DEBUG_IP_FIREWALL_USER*/
 
 #ifdef DEBUG_IP_FIREWALL
-#define dprintf(format, args...)  printk(format , ## args)
+#define dprintf(format, args...) pr_info(format , ## args)
 #else
 #define dprintf(format, args...)
 #endif
 
 #ifdef DEBUG_IP_FIREWALL_USER
-#define duprintf(format, args...) printk(format , ## args)
+#define duprintf(format, args...) pr_info(format , ## args)
 #else
 #define duprintf(format, args...)
 #endif
 
 #ifdef CONFIG_NETFILTER_DEBUG
-#define IP_NF_ASSERT(x)						\
-do {								\
-	if (!(x))						\
-		printk("IP_NF_ASSERT: %s:%s:%u\n",		\
-		       __func__, __FILE__, __LINE__);	\
-} while(0)
+#define IP_NF_ASSERT(x)		WARN_ON(!(x))
 #else
 #define IP_NF_ASSERT(x)
 #endif
@@ -165,30 +160,14 @@ ip_checkentry(const struct ipt_ip *ip)
 }
 
 static unsigned int
-ipt_error(struct sk_buff *skb, const struct xt_target_param *par)
+ipt_error(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	if (net_ratelimit())
-		printk("ip_tables: error: `%s'\n",
-		       (const char *)par->targinfo);
+		pr_info("error: `%s'\n", (const char *)par->targinfo);
 
 	return NF_DROP;
 }
 
-/* Performance critical - called for every packet */
-static inline bool
-do_match(const struct ipt_entry_match *m, const struct sk_buff *skb,
-	 struct xt_match_param *par)
-{
-	par->match     = m->u.kernel.match;
-	par->matchinfo = m->data;
-
-	/* Stop iteration if it doesn't match */
-	if (!m->u.kernel.match->match(skb, par))
-		return true;
-	else
-		return false;
-}
-
 /* Performance critical */
 static inline struct ipt_entry *
 get_entry(const void *base, unsigned int offset)
@@ -322,19 +301,16 @@ ipt_do_table(struct sk_buff *skb,
 	     const struct net_device *out,
 	     struct xt_table *table)
 {
-#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom
-
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	const struct iphdr *ip;
-	bool hotdrop = false;
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
 	const void *table_base;
-	struct ipt_entry *e, *back;
+	struct ipt_entry *e, **jumpstack;
+	unsigned int *stackptr, origptr, cpu;
 	const struct xt_table_info *private;
-	struct xt_match_param mtpar;
-	struct xt_target_param tgpar;
+	struct xt_action_param acpar;
 
 	/* Initialization */
 	ip = ip_hdr(skb);
@@ -346,40 +322,47 @@ ipt_do_table(struct sk_buff *skb,
 	 * things we don't know, ie. tcp syn flag or ports).  If the
 	 * rule is also a fragment-specific rule, non-fragments won't
 	 * match it. */
-	mtpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
-	mtpar.thoff   = ip_hdrlen(skb);
-	mtpar.hotdrop = &hotdrop;
-	mtpar.in      = tgpar.in  = in;
-	mtpar.out     = tgpar.out = out;
-	mtpar.family  = tgpar.family = NFPROTO_IPV4;
-	mtpar.hooknum = tgpar.hooknum = hook;
+	acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
+	acpar.thoff   = ip_hdrlen(skb);
+	acpar.hotdrop = false;
+	acpar.in      = in;
+	acpar.out     = out;
+	acpar.family  = NFPROTO_IPV4;
+	acpar.hooknum = hook;
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 	xt_info_rdlock_bh();
 	private = table->private;
-	table_base = private->entries[smp_processor_id()];
+	cpu        = smp_processor_id();
+	table_base = private->entries[cpu];
+	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
+	stackptr   = &private->stackptr[cpu];
+	origptr    = *stackptr;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
-	/* For return from builtin chain */
-	back = get_entry(table_base, private->underflow[hook]);
+	pr_debug("Entering %s(hook %u); sp at %u (UF %p)\n",
+		 table->name, hook, origptr,
+		 get_entry(table_base, private->underflow[hook]));
 
 	do {
 		const struct ipt_entry_target *t;
 		const struct xt_entry_match *ematch;
 
 		IP_NF_ASSERT(e);
-		IP_NF_ASSERT(back);
 		if (!ip_packet_match(ip, indev, outdev,
-		    &e->ip, mtpar.fragoff)) {
+		    &e->ip, acpar.fragoff)) {
  no_match:
 			e = ipt_next_entry(e);
 			continue;
 		}
 
-		xt_ematch_foreach(ematch, e)
-			if (do_match(ematch, skb, &mtpar) != 0)
+		xt_ematch_foreach(ematch, e) {
+			acpar.match     = ematch->u.kernel.match;
+			acpar.matchinfo = ematch->data;
+			if (!acpar.match->match(skb, &acpar))
 				goto no_match;
+		}
 
 		ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
 
@@ -404,41 +387,38 @@ ipt_do_table(struct sk_buff *skb,
 					verdict = (unsigned)(-v) - 1;
 					break;
 				}
-				e = back;
-				back = get_entry(table_base, back->comefrom);
+				if (*stackptr == 0) {
+					e = get_entry(table_base,
+					    private->underflow[hook]);
+					pr_debug("Underflow (this is normal) "
+						 "to %p\n", e);
+				} else {
+					e = jumpstack[--*stackptr];
+					pr_debug("Pulled %p out from pos %u\n",
+						 e, *stackptr);
+					e = ipt_next_entry(e);
+				}
 				continue;
 			}
 			if (table_base + v != ipt_next_entry(e) &&
 			    !(e->ip.flags & IPT_F_GOTO)) {
-				/* Save old back ptr in next entry */
-				struct ipt_entry *next = ipt_next_entry(e);
-				next->comefrom = (void *)back - table_base;
-				/* set back pointer to next entry */
-				back = next;
+				if (*stackptr >= private->stacksize) {
+					verdict = NF_DROP;
+					break;
+				}
+				jumpstack[(*stackptr)++] = e;
+				pr_debug("Pushed %p into pos %u\n",
+					 e, *stackptr - 1);
 			}
 
 			e = get_entry(table_base, v);
 			continue;
 		}
 
-		/* Targets which reenter must return
-		   abs. verdicts */
-		tgpar.target   = t->u.kernel.target;
-		tgpar.targinfo = t->data;
-
+		acpar.target   = t->u.kernel.target;
+		acpar.targinfo = t->data;
 
-#ifdef CONFIG_NETFILTER_DEBUG
-		tb_comefrom = 0xeeeeeeec;
-#endif
-		verdict = t->u.kernel.target->target(skb, &tgpar);
-#ifdef CONFIG_NETFILTER_DEBUG
-		if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) {
-			printk("Target %s reentered!\n",
-			       t->u.kernel.target->name);
-			verdict = NF_DROP;
-		}
-		tb_comefrom = 0x57acc001;
-#endif
+		verdict = t->u.kernel.target->target(skb, &acpar);
 		/* Target might have changed stuff. */
 		ip = ip_hdr(skb);
 		if (verdict == IPT_CONTINUE)
@@ -446,18 +426,18 @@ ipt_do_table(struct sk_buff *skb,
 		else
 			/* Verdict */
 			break;
-	} while (!hotdrop);
+	} while (!acpar.hotdrop);
 	xt_info_rdunlock_bh();
-
+	pr_debug("Exiting %s; resetting sp from %u to %u\n",
+		 __func__, *stackptr, origptr);
+	*stackptr = origptr;
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
 #else
-	if (hotdrop)
+	if (acpar.hotdrop)
 		return NF_DROP;
 	else return verdict;
 #endif
-
-#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -486,7 +466,7 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			int visited = e->comefrom & (1 << hook);
 
 			if (e->comefrom & (1 << NF_INET_NUMHOOKS)) {
-				printk("iptables: loop hook %u pos %u %08X.\n",
+				pr_err("iptables: loop hook %u pos %u %08X.\n",
 				       hook, pos, e->comefrom);
 				return 0;
 			}
@@ -591,7 +571,7 @@ check_entry(const struct ipt_entry *e, const char *name)
 	const struct ipt_entry_target *t;
 
 	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
+		duprintf("ip check failed %p %s.\n", e, par->match->name);
 		return -EINVAL;
 	}
 
@@ -618,8 +598,7 @@ check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par)
 	ret = xt_check_match(par, m->u.match_size - sizeof(*m),
 	      ip->proto, ip->invflags & IPT_INV_PROTO);
 	if (ret < 0) {
-		duprintf("ip_tables: check failed for `%s'.\n",
-			 par.match->name);
+		duprintf("check failed for `%s'.\n", par->match->name);
 		return ret;
 	}
 	return 0;
@@ -631,12 +610,11 @@ find_check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par)
 	struct xt_match *match;
 	int ret;
 
-	match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name,
-						      m->u.user.revision),
-					"ipt_%s", m->u.user.name);
-	if (IS_ERR(match) || !match) {
+	match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name,
+				      m->u.user.revision);
+	if (IS_ERR(match)) {
 		duprintf("find_check_match: `%s' not found\n", m->u.user.name);
-		return match ? PTR_ERR(match) : -ENOENT;
+		return PTR_ERR(match);
 	}
 	m->u.kernel.match = match;
 
@@ -667,7 +645,7 @@ static int check_target(struct ipt_entry *e, struct net *net, const char *name)
 	ret = xt_check_target(&par, t->u.target_size - sizeof(*t),
 	      e->ip.proto, e->ip.invflags & IPT_INV_PROTO);
 	if (ret < 0) {
-		duprintf("ip_tables: check failed for `%s'.\n",
+		duprintf("check failed for `%s'.\n",
 			 t->u.kernel.target->name);
 		return ret;
 	}
@@ -703,13 +681,11 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 	}
 
 	t = ipt_get_target(e);
-	target = try_then_request_module(xt_find_target(AF_INET,
-							t->u.user.name,
-							t->u.user.revision),
-					 "ipt_%s", t->u.user.name);
-	if (IS_ERR(target) || !target) {
+	target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name,
+					t->u.user.revision);
+	if (IS_ERR(target)) {
 		duprintf("find_check_entry: `%s' not found\n", t->u.user.name);
-		ret = target ? PTR_ERR(target) : -ENOENT;
+		ret = PTR_ERR(target);
 		goto cleanup_matches;
 	}
 	t->u.kernel.target = target;
@@ -843,6 +819,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			return ret;
 		++i;
+		if (strcmp(ipt_get_target(iter)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 
 	if (i != repl->num_entries) {
@@ -1311,7 +1290,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
 	if (ret != 0)
 		goto free_newinfo;
 
-	duprintf("ip_tables: Translated table\n");
+	duprintf("Translated table\n");
 
 	ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo,
 			   tmp.num_counters, tmp.counters);
@@ -1476,13 +1455,12 @@ compat_find_calc_match(struct ipt_entry_match *m,
 {
 	struct xt_match *match;
 
-	match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name,
-						      m->u.user.revision),
-					"ipt_%s", m->u.user.name);
-	if (IS_ERR(match) || !match) {
+	match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name,
+				      m->u.user.revision);
+	if (IS_ERR(match)) {
 		duprintf("compat_check_calc_match: `%s' not found\n",
 			 m->u.user.name);
-		return match ? PTR_ERR(match) : -ENOENT;
+		return PTR_ERR(match);
 	}
 	m->u.kernel.match = match;
 	*size += xt_compat_match_offset(match);
@@ -1549,14 +1527,12 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	}
 
 	t = compat_ipt_get_target(e);
-	target = try_then_request_module(xt_find_target(AF_INET,
-							t->u.user.name,
-							t->u.user.revision),
-					 "ipt_%s", t->u.user.name);
-	if (IS_ERR(target) || !target) {
+	target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name,
+					t->u.user.revision);
+	if (IS_ERR(target)) {
 		duprintf("check_compat_entry_size_and_hooks: `%s' not found\n",
 			 t->u.user.name);
-		ret = target ? PTR_ERR(target) : -ENOENT;
+		ret = PTR_ERR(target);
 		goto release_matches;
 	}
 	t->u.kernel.target = target;
@@ -2094,8 +2070,7 @@ struct xt_table *ipt_register_table(struct net *net,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap
-		= { 0, 0, 0, { 0 }, { 0 }, { } };
+	struct xt_table_info bootstrap = {0};
 	void *loc_cpu_entry;
 	struct xt_table *new_table;
 
@@ -2157,7 +2132,7 @@ icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,
 }
 
 static bool
-icmp_match(const struct sk_buff *skb, const struct xt_match_param *par)
+icmp_match(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct icmphdr *ic;
 	struct icmphdr _icmph;
@@ -2173,7 +2148,7 @@ icmp_match(const struct sk_buff *skb, const struct xt_match_param *par)
 		 * can't.  Hence, no choice but to drop.
 		 */
 		duprintf("Dropping evil ICMP tinygram.\n");
-		*par->hotdrop = true;
+		par->hotdrop = true;
 		return false;
 	}
 
@@ -2184,31 +2159,31 @@ icmp_match(const struct sk_buff *skb, const struct xt_match_param *par)
 				    !!(icmpinfo->invflags&IPT_ICMP_INV));
 }
 
-static bool icmp_checkentry(const struct xt_mtchk_param *par)
+static int icmp_checkentry(const struct xt_mtchk_param *par)
 {
 	const struct ipt_icmp *icmpinfo = par->matchinfo;
 
 	/* Must specify no unknown invflags */
-	return !(icmpinfo->invflags & ~IPT_ICMP_INV);
+	return (icmpinfo->invflags & ~IPT_ICMP_INV) ? -EINVAL : 0;
 }
 
-/* The built-in targets: standard (NULL) and error. */
-static struct xt_target ipt_standard_target __read_mostly = {
-	.name		= IPT_STANDARD_TARGET,
-	.targetsize	= sizeof(int),
-	.family		= NFPROTO_IPV4,
+static struct xt_target ipt_builtin_tg[] __read_mostly = {
+	{
+		.name             = IPT_STANDARD_TARGET,
+		.targetsize       = sizeof(int),
+		.family           = NFPROTO_IPV4,
 #ifdef CONFIG_COMPAT
-	.compatsize	= sizeof(compat_int_t),
-	.compat_from_user = compat_standard_from_user,
-	.compat_to_user	= compat_standard_to_user,
+		.compatsize       = sizeof(compat_int_t),
+		.compat_from_user = compat_standard_from_user,
+		.compat_to_user   = compat_standard_to_user,
 #endif
-};
-
-static struct xt_target ipt_error_target __read_mostly = {
-	.name		= IPT_ERROR_TARGET,
-	.target		= ipt_error,
-	.targetsize	= IPT_FUNCTION_MAXNAMELEN,
-	.family		= NFPROTO_IPV4,
+	},
+	{
+		.name             = IPT_ERROR_TARGET,
+		.target           = ipt_error,
+		.targetsize       = IPT_FUNCTION_MAXNAMELEN,
+		.family           = NFPROTO_IPV4,
+	},
 };
 
 static struct nf_sockopt_ops ipt_sockopts = {
@@ -2228,13 +2203,15 @@ static struct nf_sockopt_ops ipt_sockopts = {
 	.owner		= THIS_MODULE,
 };
 
-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		= NFPROTO_IPV4,
+static struct xt_match ipt_builtin_mt[] __read_mostly = {
+	{
+		.name       = "icmp",
+		.match      = icmp_match,
+		.matchsize  = sizeof(struct ipt_icmp),
+		.checkentry = icmp_checkentry,
+		.proto      = IPPROTO_ICMP,
+		.family     = NFPROTO_IPV4,
+	},
 };
 
 static int __net_init ip_tables_net_init(struct net *net)
@@ -2261,13 +2238,10 @@ static int __init ip_tables_init(void)
 		goto err1;
 
 	/* Noone else will be downing sem now, so we won't sleep */
-	ret = xt_register_target(&ipt_standard_target);
+	ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 	if (ret < 0)
 		goto err2;
-	ret = xt_register_target(&ipt_error_target);
-	if (ret < 0)
-		goto err3;
-	ret = xt_register_match(&icmp_matchstruct);
+	ret = xt_register_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
 	if (ret < 0)
 		goto err4;
 
@@ -2276,15 +2250,13 @@ static int __init ip_tables_init(void)
 	if (ret < 0)
 		goto err5;
 
-	printk(KERN_INFO "ip_tables: (C) 2000-2006 Netfilter Core Team\n");
+	pr_info("(C) 2000-2006 Netfilter Core Team\n");
 	return 0;
 
 err5:
-	xt_unregister_match(&icmp_matchstruct);
+	xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
 err4:
-	xt_unregister_target(&ipt_error_target);
-err3:
-	xt_unregister_target(&ipt_standard_target);
+	xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 err2:
 	unregister_pernet_subsys(&ip_tables_net_ops);
 err1:
@@ -2295,10 +2267,8 @@ static void __exit ip_tables_fini(void)
 {
 	nf_unregister_sockopt(&ipt_sockopts);
 
-	xt_unregister_match(&icmp_matchstruct);
-	xt_unregister_target(&ipt_error_target);
-	xt_unregister_target(&ipt_standard_target);
-
+	xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt));
+	xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg));
 	unregister_pernet_subsys(&ip_tables_net_ops);
 }