ip_tables.c

linux2.6.16版本

		return -ENOMEM;

	newinfo = xt_alloc_table_info(tmp.size);
	if (!newinfo)
		return -ENOMEM;

	/* choose the copy that is 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) {
		ret = -EFAULT;
		goto free_newinfo;
	}

	counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters));
	if (!counters) {
		ret = -ENOMEM;
		goto free_newinfo;
	}

	ret = translate_table(tmp.name, tmp.valid_hooks,
			      newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
			      tmp.hook_entry, tmp.underflow);
	if (ret != 0)
		goto free_newinfo_counters;

	duprintf("ip_tables: Translated table\n");

	t = try_then_request_module(xt_find_table_lock(AF_INET, tmp.name),
				    "iptable_%s", tmp.name);
	if (!t || IS_ERR(t)) {
		ret = t ? PTR_ERR(t) : -ENOENT;
		goto free_newinfo_counters_untrans;
	}

	/* You lied! */
	if (tmp.valid_hooks != t->valid_hooks) {
		duprintf("Valid hook crap: %08X vs %08X\n",
			 tmp.valid_hooks, t->valid_hooks);
		ret = -EINVAL;
		goto put_module;
	}

	oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret);
	if (!oldinfo)
		goto put_module;

	/* Update module usage count based on number of rules */
	duprintf("do_replace: oldnum=%u, initnum=%u, newnum=%u\n",
		oldinfo->number, oldinfo->initial_entries, newinfo->number);
	if ((oldinfo->number > oldinfo->initial_entries) || 
	    (newinfo->number <= oldinfo->initial_entries)) 
		module_put(t->me);
	if ((oldinfo->number > oldinfo->initial_entries) &&
	    (newinfo->number <= oldinfo->initial_entries))
		module_put(t->me);

	/* Get the old counters. */
	get_counters(oldinfo, counters);
	/* Decrease module usage counts and free resource */
	loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
	IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL);
	xt_free_table_info(oldinfo);
	if (copy_to_user(tmp.counters, counters,
			 sizeof(struct xt_counters) * tmp.num_counters) != 0)
		ret = -EFAULT;
	vfree(counters);
	xt_table_unlock(t);
	return ret;

 put_module:
	module_put(t->me);
	xt_table_unlock(t);
 free_newinfo_counters_untrans:
	IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL);
 free_newinfo_counters:
	vfree(counters);
 free_newinfo:
	xt_free_table_info(newinfo);
	return ret;
}

/* We're lazy, and add to the first CPU; overflow works its fey magic
 * and everything is OK. */
static inline int
add_counter_to_entry(struct ipt_entry *e,
		     const struct xt_counters addme[],
		     unsigned int *i)
{
#if 0
	duprintf("add_counter: Entry %u %lu/%lu + %lu/%lu\n",
		 *i,
		 (long unsigned int)e->counters.pcnt,
		 (long unsigned int)e->counters.bcnt,
		 (long unsigned int)addme[*i].pcnt,
		 (long unsigned int)addme[*i].bcnt);
#endif

	ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);

	(*i)++;
	return 0;
}

static int
do_add_counters(void __user *user, unsigned int len)
{
	unsigned int i;
	struct xt_counters_info tmp, *paddc;
	struct ipt_table *t;
	struct xt_table_info *private;
	int ret = 0;
	void *loc_cpu_entry;

	if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
		return -EFAULT;

	if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters))
		return -EINVAL;

	paddc = vmalloc_node(len, numa_node_id());
	if (!paddc)
		return -ENOMEM;

	if (copy_from_user(paddc, user, len) != 0) {
		ret = -EFAULT;
		goto free;
	}

	t = xt_find_table_lock(AF_INET, tmp.name);
	if (!t || IS_ERR(t)) {
		ret = t ? PTR_ERR(t) : -ENOENT;
		goto free;
	}

	write_lock_bh(&t->lock);
	private = t->private;
	if (private->number != paddc->num_counters) {
		ret = -EINVAL;
		goto unlock_up_free;
	}

	i = 0;
	/* Choose the copy that is on our node */
	loc_cpu_entry = private->entries[raw_smp_processor_id()];
	IPT_ENTRY_ITERATE(loc_cpu_entry,
			  private->size,
			  add_counter_to_entry,
			  paddc->counters,
			  &i);
 unlock_up_free:
	write_unlock_bh(&t->lock);
	xt_table_unlock(t);
	module_put(t->me);
 free:
	vfree(paddc);

	return ret;
}

static int
do_ipt_set_ctl(struct sock *sk,	int cmd, void __user *user, unsigned int len)
{
	int ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	switch (cmd) {
	case IPT_SO_SET_REPLACE:
		ret = do_replace(user, len);
		break;

	case IPT_SO_SET_ADD_COUNTERS:
		ret = do_add_counters(user, len);
		break;

	default:
		duprintf("do_ipt_set_ctl:  unknown request %i\n", cmd);
		ret = -EINVAL;
	}

	return ret;
}

static int
do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
	int ret;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	switch (cmd) {
	case IPT_SO_GET_INFO: {
		char name[IPT_TABLE_MAXNAMELEN];
		struct ipt_table *t;

		if (*len != sizeof(struct ipt_getinfo)) {
			duprintf("length %u != %u\n", *len,
				 sizeof(struct ipt_getinfo));
			ret = -EINVAL;
			break;
		}

		if (copy_from_user(name, user, sizeof(name)) != 0) {
			ret = -EFAULT;
			break;
		}
		name[IPT_TABLE_MAXNAMELEN-1] = '\0';

		t = try_then_request_module(xt_find_table_lock(AF_INET, name),
					    "iptable_%s", name);
		if (t && !IS_ERR(t)) {
			struct ipt_getinfo info;
			struct xt_table_info *private = t->private;

			info.valid_hooks = t->valid_hooks;
			memcpy(info.hook_entry, private->hook_entry,
			       sizeof(info.hook_entry));
			memcpy(info.underflow, private->underflow,
			       sizeof(info.underflow));
			info.num_entries = private->number;
			info.size = private->size;
			memcpy(info.name, name, sizeof(info.name));

			if (copy_to_user(user, &info, *len) != 0)
				ret = -EFAULT;
			else
				ret = 0;
			xt_table_unlock(t);
			module_put(t->me);
		} else
			ret = t ? PTR_ERR(t) : -ENOENT;
	}
	break;

	case IPT_SO_GET_ENTRIES: {
		struct ipt_get_entries get;

		if (*len < sizeof(get)) {
			duprintf("get_entries: %u < %u\n", *len, sizeof(get));
			ret = -EINVAL;
		} else if (copy_from_user(&get, user, sizeof(get)) != 0) {
			ret = -EFAULT;
		} else if (*len != sizeof(struct ipt_get_entries) + get.size) {
			duprintf("get_entries: %u != %u\n", *len,
				 sizeof(struct ipt_get_entries) + get.size);
			ret = -EINVAL;
		} else
			ret = get_entries(&get, user);
		break;
	}

	case IPT_SO_GET_REVISION_MATCH:
	case IPT_SO_GET_REVISION_TARGET: {
		struct ipt_get_revision rev;
		int target;

		if (*len != sizeof(rev)) {
			ret = -EINVAL;
			break;
		}
		if (copy_from_user(&rev, user, sizeof(rev)) != 0) {
			ret = -EFAULT;
			break;
		}

		if (cmd == IPT_SO_GET_REVISION_TARGET)
			target = 1;
		else
			target = 0;

		try_then_request_module(xt_find_revision(AF_INET, rev.name,
							 rev.revision,
							 target, &ret),
					"ipt_%s", rev.name);
		break;
	}

	default:
		duprintf("do_ipt_get_ctl: unknown request %i\n", cmd);
		ret = -EINVAL;
	}

	return ret;
}

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
		= { 0, 0, 0, { 0 }, { 0 }, { } };
	void *loc_cpu_entry;

	newinfo = xt_alloc_table_info(repl->size);
	if (!newinfo)
		return -ENOMEM;

	/* choose the copy on our node/cpu
	 * but dont care of preemption
	 */
	loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
	memcpy(loc_cpu_entry, repl->entries, repl->size);

	ret = translate_table(table->name, table->valid_hooks,
			      newinfo, loc_cpu_entry, repl->size,
			      repl->num_entries,
			      repl->hook_entry,
			      repl->underflow);
	if (ret != 0) {
		xt_free_table_info(newinfo);
		return ret;
	}

	if (xt_register_table(table, &bootstrap, newinfo) != 0) {
		xt_free_table_info(newinfo);
		return ret;
	}

	return 0;
}

void ipt_unregister_table(struct ipt_table *table)
{
	struct xt_table_info *private;
	void *loc_cpu_entry;

 	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);
	xt_free_table_info(private);
}

/* Returns 1 if the type and code is matched by the range, 0 otherwise */
static inline int
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,
		     int invert)
{
	return ((test_type == 0xFF) || (type == test_type && code >= min_code && code <= max_code))
		^ invert;
}

static int
icmp_match(const struct sk_buff *skb,
	   const struct net_device *in,
	   const struct net_device *out,
	   const void *matchinfo,
	   int offset,
	   unsigned int protoff,
	   int *hotdrop)
{
	struct icmphdr _icmph, *ic;
	const struct ipt_icmp *icmpinfo = matchinfo;

	/* Must not be a fragment. */
	if (offset)
		return 0;

	ic = skb_header_pointer(skb, protoff, sizeof(_icmph), &_icmph);
	if (ic == NULL) {
		/* We've been asked to examine this packet, and we
		 * can't.  Hence, no choice but to drop.
		 */
		duprintf("Dropping evil ICMP tinygram.\n");
		*hotdrop = 1;
		return 0;
	}

	return icmp_type_code_match(icmpinfo->type,
				    icmpinfo->code[0],
				    icmpinfo->code[1],
				    ic->type, ic->code,
				    !!(icmpinfo->invflags&IPT_ICMP_INV));
}

/* Called when user tries to insert an entry of this type. */
static int
icmp_checkentry(const char *tablename,
	   const void *info,
	   void *matchinfo,
	   unsigned int matchsize,
	   unsigned int hook_mask)
{
	const struct ipt_ip *ip = info;
	const struct ipt_icmp *icmpinfo = matchinfo;

	/* Must specify proto == ICMP, and no unknown invflags */
	return ip->proto == IPPROTO_ICMP
		&& !(ip->invflags & IPT_INV_PROTO)
		&& matchsize == IPT_ALIGN(sizeof(struct ipt_icmp))
		&& !(icmpinfo->invflags & ~IPT_ICMP_INV);
}

/* The built-in targets: standard (NULL) and error. */
static struct ipt_target ipt_standard_target = {
	.name		= IPT_STANDARD_TARGET,
};

static struct ipt_target ipt_error_target = {
	.name		= IPT_ERROR_TARGET,
	.target		= ipt_error,
};

static struct nf_sockopt_ops ipt_sockopts = {
	.pf		= PF_INET,
	.set_optmin	= IPT_BASE_CTL,
	.set_optmax	= IPT_SO_SET_MAX+1,
	.set		= do_ipt_set_ctl,
	.get_optmin	= IPT_BASE_CTL,
	.get_optmax	= IPT_SO_GET_MAX+1,
	.get		= do_ipt_get_ctl,
};

static struct ipt_match icmp_matchstruct = {
	.name		= "icmp",
	.match		= &icmp_match,
	.checkentry	= &icmp_checkentry,
};

static int __init init(void)
{
	int ret;

	xt_proto_init(AF_INET);

	/* Noone else will be downing sem now, so we won't sleep */
	xt_register_target(AF_INET, &ipt_standard_target);
	xt_register_target(AF_INET, &ipt_error_target);
	xt_register_match(AF_INET, &icmp_matchstruct);

	/* Register setsockopt */
	ret = nf_register_sockopt(&ipt_sockopts);
	if (ret < 0) {
		duprintf("Unable to register sockopts.\n");
		return ret;
	}

	printk("ip_tables: (C) 2000-2006 Netfilter Core Team\n");
	return 0;
}

static void __exit fini(void)
{
	nf_unregister_sockopt(&ipt_sockopts);

	xt_unregister_match(AF_INET, &icmp_matchstruct);
	xt_unregister_target(AF_INET, &ipt_error_target);
	xt_unregister_target(AF_INET, &ipt_standard_target);

	xt_proto_fini(AF_INET);
}

EXPORT_SYMBOL(ipt_register_table);
EXPORT_SYMBOL(ipt_unregister_table);
EXPORT_SYMBOL(ipt_do_table);
module_init(init);
module_exit(fini);