ip_tables.c

linux 内核源代码

	info->number = number;

	/* Init all hooks to impossible value. */
	for (i = 0; i < NF_IP_NUMHOOKS; i++) {
		info->hook_entry[i] = 0xFFFFFFFF;
		info->underflow[i] = 0xFFFFFFFF;
	}

	duprintf("translate_compat_table: size %u\n", info->size);
	j = 0;
	xt_compat_lock(AF_INET);
	/* Walk through entries, checking offsets. */
	ret = IPT_ENTRY_ITERATE(entry0, total_size,
				check_compat_entry_size_and_hooks,
				info, &size, entry0,
				entry0 + total_size,
				hook_entries, underflows, &j, name);
	if (ret != 0)
		goto out_unlock;

	ret = -EINVAL;
	if (j != number) {
		duprintf("translate_compat_table: %u not %u entries\n",
			 j, number);
		goto out_unlock;
	}

	/* Check hooks all assigned */
	for (i = 0; i < NF_IP_NUMHOOKS; i++) {
		/* Only hooks which are valid */
		if (!(valid_hooks & (1 << i)))
			continue;
		if (info->hook_entry[i] == 0xFFFFFFFF) {
			duprintf("Invalid hook entry %u %u\n",
				 i, hook_entries[i]);
			goto out_unlock;
		}
		if (info->underflow[i] == 0xFFFFFFFF) {
			duprintf("Invalid underflow %u %u\n",
				 i, underflows[i]);
			goto out_unlock;
		}
	}

	ret = -ENOMEM;
	newinfo = xt_alloc_table_info(size);
	if (!newinfo)
		goto out_unlock;

	newinfo->number = number;
	for (i = 0; i < NF_IP_NUMHOOKS; i++) {
		newinfo->hook_entry[i] = info->hook_entry[i];
		newinfo->underflow[i] = info->underflow[i];
	}
	entry1 = newinfo->entries[raw_smp_processor_id()];
	pos = entry1;
	size =  total_size;
	ret = IPT_ENTRY_ITERATE(entry0, total_size,
			compat_copy_entry_from_user, &pos, &size,
			name, newinfo, entry1);
	compat_flush_offsets();
	xt_compat_unlock(AF_INET);
	if (ret)
		goto free_newinfo;

	ret = -ELOOP;
	if (!mark_source_chains(newinfo, valid_hooks, entry1))
		goto free_newinfo;

	i = 0;
	ret = IPT_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry,
								name, &i);
	if (ret) {
		j -= i;
		IPT_ENTRY_ITERATE_CONTINUE(entry1, newinfo->size, i,
						compat_release_entry, &j);
		IPT_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i);
		xt_free_table_info(newinfo);
		return ret;
	}

	/* And one copy for every other CPU */
	for_each_possible_cpu(i)
		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
			memcpy(newinfo->entries[i], entry1, newinfo->size);

	*pinfo = newinfo;
	*pentry0 = entry1;
	xt_free_table_info(info);
	return 0;

free_newinfo:
	xt_free_table_info(newinfo);
out:
	IPT_ENTRY_ITERATE(entry0, total_size, compat_release_entry, &j);
	return ret;
out_unlock:
	compat_flush_offsets();
	xt_compat_unlock(AF_INET);
	goto out;
}

static int
compat_do_replace(void __user *user, unsigned int len)
{
	int ret;
	struct compat_ipt_replace tmp;
	struct xt_table_info *newinfo;
	void *loc_cpu_entry;

	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 - sizeof(struct xt_table_info)) / NR_CPUS -
			SMP_CACHE_BYTES)
		return -ENOMEM;
	if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
		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;
	}

	ret = translate_compat_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;

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

	ret = __do_replace(tmp.name, tmp.valid_hooks,
			      newinfo, tmp.num_counters,
			      compat_ptr(tmp.counters));
	if (ret)
		goto free_newinfo_untrans;
	return 0;

 free_newinfo_untrans:
	IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL);
 free_newinfo:
	xt_free_table_info(newinfo);
	return ret;
}

static int
compat_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 = compat_do_replace(user, len);
		break;

	case IPT_SO_SET_ADD_COUNTERS:
		ret = do_add_counters(user, len, 1);
		break;

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

	return ret;
}

struct compat_ipt_get_entries
{
	char name[IPT_TABLE_MAXNAMELEN];
	compat_uint_t size;
	struct compat_ipt_entry entrytable[0];
};

static int 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;
	void __user *pos;
	unsigned int size;
	int ret = 0;
	void *loc_cpu_entry;
	unsigned int i = 0;

	counters = alloc_counters(table);
	if (IS_ERR(counters))
		return PTR_ERR(counters);

	/* choose the copy that is on our node/cpu, ...
	 * This choice is lazy (because current thread is
	 * allowed to migrate to another cpu)
	 */
	loc_cpu_entry = private->entries[raw_smp_processor_id()];
	pos = userptr;
	size = total_size;
	ret = IPT_ENTRY_ITERATE(loc_cpu_entry, total_size,
				compat_copy_entry_to_user,
				&pos, &size, counters, &i);

	vfree(counters);
	return ret;
}

static int
compat_get_entries(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));
		return -EINVAL;
	}

	if (copy_from_user(&get, uptr, sizeof(get)) != 0)
		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));
		return -EINVAL;
	}

	xt_compat_lock(AF_INET);
	t = xt_find_table_lock(AF_INET, get.name);
	if (t && !IS_ERR(t)) {
		struct xt_table_info *private = t->private;
		struct xt_table_info info;
		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;
		}
		compat_flush_offsets();
		module_put(t->me);
		xt_table_unlock(t);
	} else
		ret = t ? PTR_ERR(t) : -ENOENT;

	xt_compat_unlock(AF_INET);
	return ret;
}

static int do_ipt_get_ctl(struct sock *, int, void __user *, int *);

static int
compat_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:
		ret = get_info(user, len, 1);
		break;
	case IPT_SO_GET_ENTRIES:
		ret = compat_get_entries(user, len);
		break;
	default:
		ret = do_ipt_get_ctl(sk, cmd, user, len);
	}
	return ret;
}
#endif

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, 0);
		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:
		ret = get_info(user, len, 0);
		break;

	case IPT_SO_GET_ENTRIES:
		ret = get_entries(user, len);
		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;
	}

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

	return 0;
}

void ipt_unregister_table(struct xt_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 bool
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))
		^ invert;
}

static bool
icmp_match(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)
{
	struct icmphdr _icmph, *ic;
	const struct ipt_icmp *icmpinfo = matchinfo;

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

	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 = true;
		return false;
	}

	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 bool
icmp_checkentry(const char *tablename,
	   const void *info,
	   const struct xt_match *match,
	   void *matchinfo,
	   unsigned int hook_mask)
{
	const struct ipt_icmp *icmpinfo = matchinfo;

	/* Must specify no unknown invflags */
	return !(icmpinfo->invflags & ~IPT_ICMP_INV);
}

/* 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		= AF_INET,
#ifdef CONFIG_COMPAT
	.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		= AF_INET,
};

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,
#ifdef CONFIG_COMPAT
	.compat_set	= compat_do_ipt_set_ctl,
#endif
	.get_optmin	= IPT_BASE_CTL,
	.get_optmax	= IPT_SO_GET_MAX+1,
	.get		= do_ipt_get_ctl,
#ifdef CONFIG_COMPAT
	.compat_get	= compat_do_ipt_get_ctl,
#endif
	.owner		= THIS_MODULE,
};

static struct xt_match icmp_matchstruct __read_mostly = {
	.name		= "icmp",
	.match		= icmp_match,
	.matchsize	= sizeof(struct ipt_icmp),
	.proto		= IPPROTO_ICMP,
	.family		= AF_INET,
	.checkentry	= icmp_checkentry,
};

static int __init ip_tables_init(void)
{
	int ret;

	ret = xt_proto_init(AF_INET);
	if (ret < 0)
		goto err1;

	/* Noone else will be downing sem now, so we won't sleep */
	ret = xt_register_target(&ipt_standard_target);
	if (ret < 0)
		goto err2;
	ret = xt_register_target(&ipt_error_target);
	if (ret < 0)
		goto err3;
	ret = xt_register_match(&icmp_matchstruct);
	if (ret < 0)
		goto err4;

	/* Register setsockopt */
	ret = nf_register_sockopt(&ipt_sockopts);
	if (ret < 0)
		goto err5;

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

err5:
	xt_unregister_match(&icmp_matchstruct);
err4:
	xt_unregister_target(&ipt_error_target);
err3:
	xt_unregister_target(&ipt_standard_target);
err2:
	xt_proto_fini(AF_INET);
err1:
	return ret;
}

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_proto_fini(AF_INET);
}

EXPORT_SYMBOL(ipt_register_table);
EXPORT_SYMBOL(ipt_unregister_table);
EXPORT_SYMBOL(ipt_do_table);
module_init(ip_tables_init);
module_exit(ip_tables_fini);