ip_tables.c

Linux Kernel 2.6.9 for OMAP1710

	return 1;
}

static inline int
check_match(struct ipt_entry_match *m,
	    const char *name,
	    const struct ipt_ip *ip,
	    unsigned int hookmask,
	    unsigned int *i)
{
	int ret;
	struct ipt_match *match;

	match = find_match_lock(m->u.user.name, &ret, &ipt_mutex);
	if (!match) {
		duprintf("check_match: `%s' not found\n", m->u.user.name);
		return ret;
	}
	if (!try_module_get(match->me)) {
		up(&ipt_mutex);
		return -ENOENT;
	}
	m->u.kernel.match = match;
	up(&ipt_mutex);

	if (m->u.kernel.match->checkentry
	    && !m->u.kernel.match->checkentry(name, ip, m->data,
					      m->u.match_size - sizeof(*m),
					      hookmask)) {
		module_put(m->u.kernel.match->me);
		duprintf("ip_tables: check failed for `%s'.\n",
			 m->u.kernel.match->name);
		return -EINVAL;
	}

	(*i)++;
	return 0;
}

static struct ipt_target ipt_standard_target;

static inline int
check_entry(struct ipt_entry *e, const char *name, unsigned int size,
	    unsigned int *i)
{
	struct ipt_entry_target *t;
	struct ipt_target *target;
	int ret;
	unsigned int j;

	if (!ip_checkentry(&e->ip)) {
		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
		return -EINVAL;
	}

	j = 0;
	ret = IPT_MATCH_ITERATE(e, check_match, name, &e->ip, e->comefrom, &j);
	if (ret != 0)
		goto cleanup_matches;

	t = ipt_get_target(e);
	target = ipt_find_target_lock(t->u.user.name, &ret, &ipt_mutex);
	if (!target) {
		duprintf("check_entry: `%s' not found\n", t->u.user.name);
		goto cleanup_matches;
	}
	if (!try_module_get(target->me)) {
		up(&ipt_mutex);
		ret = -ENOENT;
		goto cleanup_matches;
	}
	t->u.kernel.target = target;
	up(&ipt_mutex);

	if (t->u.kernel.target == &ipt_standard_target) {
		if (!standard_check(t, size)) {
			ret = -EINVAL;
			goto cleanup_matches;
		}
	} else if (t->u.kernel.target->checkentry
		   && !t->u.kernel.target->checkentry(name, e, t->data,
						      t->u.target_size
						      - sizeof(*t),
						      e->comefrom)) {
		module_put(t->u.kernel.target->me);
		duprintf("ip_tables: check failed for `%s'.\n",
			 t->u.kernel.target->name);
		ret = -EINVAL;
		goto cleanup_matches;
	}

	(*i)++;
	return 0;

 cleanup_matches:
	IPT_MATCH_ITERATE(e, cleanup_match, &j);
	return ret;
}

static inline int
check_entry_size_and_hooks(struct ipt_entry *e,
			   struct ipt_table_info *newinfo,
			   unsigned char *base,
			   unsigned char *limit,
			   const unsigned int *hook_entries,
			   const unsigned int *underflows,
			   unsigned int *i)
{
	unsigned int h;

	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0
	    || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
		duprintf("Bad offset %p\n", e);
		return -EINVAL;
	}

	if (e->next_offset
	    < sizeof(struct ipt_entry) + sizeof(struct ipt_entry_target)) {
		duprintf("checking: element %p size %u\n",
			 e, e->next_offset);
		return -EINVAL;
	}

	/* Check hooks & underflows */
	for (h = 0; h < NF_IP_NUMHOOKS; h++) {
		if ((unsigned char *)e - base == hook_entries[h])
			newinfo->hook_entry[h] = hook_entries[h];
		if ((unsigned char *)e - base == underflows[h])
			newinfo->underflow[h] = underflows[h];
	}

	/* FIXME: underflows must be unconditional, standard verdicts
           < 0 (not IPT_RETURN). --RR */

	/* Clear counters and comefrom */
	e->counters = ((struct ipt_counters) { 0, 0 });
	e->comefrom = 0;

	(*i)++;
	return 0;
}

static inline int
cleanup_entry(struct ipt_entry *e, unsigned int *i)
{
	struct ipt_entry_target *t;

	if (i && (*i)-- == 0)
		return 1;

	/* Cleanup all matches */
	IPT_MATCH_ITERATE(e, cleanup_match, NULL);
	t = ipt_get_target(e);
	if (t->u.kernel.target->destroy)
		t->u.kernel.target->destroy(t->data,
					    t->u.target_size - sizeof(*t));
	module_put(t->u.kernel.target->me);
	return 0;
}

/* Checks and translates the user-supplied table segment (held in
   newinfo) */
static int
translate_table(const char *name,
		unsigned int valid_hooks,
		struct ipt_table_info *newinfo,
		unsigned int size,
		unsigned int number,
		const unsigned int *hook_entries,
		const unsigned int *underflows)
{
	unsigned int i;
	int ret;

	newinfo->size = size;
	newinfo->number = number;

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

	duprintf("translate_table: size %u\n", newinfo->size);
	i = 0;
	/* Walk through entries, checking offsets. */
	ret = IPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
				check_entry_size_and_hooks,
				newinfo,
				newinfo->entries,
				newinfo->entries + size,
				hook_entries, underflows, &i);
	if (ret != 0)
		return ret;

	if (i != number) {
		duprintf("translate_table: %u not %u entries\n",
			 i, number);
		return -EINVAL;
	}

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

	if (!mark_source_chains(newinfo, valid_hooks))
		return -ELOOP;

	/* Finally, each sanity check must pass */
	i = 0;
	ret = IPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
				check_entry, name, size, &i);

	if (ret != 0) {
		IPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
				  cleanup_entry, &i);
		return ret;
	}

	/* And one copy for every other CPU */
	for (i = 1; i < NR_CPUS; i++) {
		memcpy(newinfo->entries + SMP_ALIGN(newinfo->size)*i,
		       newinfo->entries,
		       SMP_ALIGN(newinfo->size));
	}

	return ret;
}

static struct ipt_table_info *
replace_table(struct ipt_table *table,
	      unsigned int num_counters,
	      struct ipt_table_info *newinfo,
	      int *error)
{
	struct ipt_table_info *oldinfo;

#ifdef CONFIG_NETFILTER_DEBUG
	{
		struct ipt_entry *table_base;
		unsigned int i;

		for (i = 0; i < NR_CPUS; i++) {
			table_base =
				(void *)newinfo->entries
				+ TABLE_OFFSET(newinfo, i);

			table_base->comefrom = 0xdead57ac;
		}
	}
#endif

	/* Do the substitution. */
	write_lock_bh(&table->lock);
	/* Check inside lock: is the old number correct? */
	if (num_counters != table->private->number) {
		duprintf("num_counters != table->private->number (%u/%u)\n",
			 num_counters, table->private->number);
		write_unlock_bh(&table->lock);
		*error = -EAGAIN;
		return NULL;
	}
	oldinfo = table->private;
	table->private = newinfo;
	newinfo->initial_entries = oldinfo->initial_entries;
	write_unlock_bh(&table->lock);

	return oldinfo;
}

/* Gets counters. */
static inline int
add_entry_to_counter(const struct ipt_entry *e,
		     struct ipt_counters total[],
		     unsigned int *i)
{
	ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);

	(*i)++;
	return 0;
}

static void
get_counters(const struct ipt_table_info *t,
	     struct ipt_counters counters[])
{
	unsigned int cpu;
	unsigned int i;

	for (cpu = 0; cpu < NR_CPUS; cpu++) {
		i = 0;
		IPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
				  t->size,
				  add_entry_to_counter,
				  counters,
				  &i);
	}
}

static int
copy_entries_to_user(unsigned int total_size,
		     struct ipt_table *table,
		     void __user *userptr)
{
	unsigned int off, num, countersize;
	struct ipt_entry *e;
	struct ipt_counters *counters;
	int ret = 0;

	/* We need atomic snapshot of counters: rest doesn't change
	   (other than comefrom, which userspace doesn't care
	   about). */
	countersize = sizeof(struct ipt_counters) * table->private->number;
	counters = vmalloc(countersize);

	if (counters == NULL)
		return -ENOMEM;

	/* First, sum counters... */
	memset(counters, 0, countersize);
	write_lock_bh(&table->lock);
	get_counters(table->private, counters);
	write_unlock_bh(&table->lock);

	/* ... then copy entire thing from CPU 0... */
	if (copy_to_user(userptr, table->private->entries, total_size) != 0) {
		ret = -EFAULT;
		goto free_counters;
	}

	/* FIXME: use iterator macros --RR */
	/* ... 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;

		e = (struct ipt_entry *)(table->private->entries + off);
		if (copy_to_user(userptr + off
				 + offsetof(struct ipt_entry, counters),
				 &counters[num],
				 sizeof(counters[num])) != 0) {
			ret = -EFAULT;
			goto free_counters;
		}

		for (i = sizeof(struct ipt_entry);
		     i < e->target_offset;
		     i += m->u.match_size) {
			m = (void *)e + i;

			if (copy_to_user(userptr + off + i
					 + offsetof(struct ipt_entry_match,
						    u.user.name),
					 m->u.kernel.match->name,
					 strlen(m->u.kernel.match->name)+1)
			    != 0) {
				ret = -EFAULT;
				goto free_counters;
			}
		}

		t = ipt_get_target(e);
		if (copy_to_user(userptr + off + e->target_offset
				 + offsetof(struct ipt_entry_target,
					    u.user.name),
				 t->u.kernel.target->name,
				 strlen(t->u.kernel.target->name)+1) != 0) {
			ret = -EFAULT;
			goto free_counters;
		}
	}

 free_counters:
	vfree(counters);
	return ret;
}

static int
get_entries(const struct ipt_get_entries *entries,
	    struct ipt_get_entries __user *uptr)
{
	int ret;
	struct ipt_table *t;

	t = ipt_find_table_lock(entries->name, &ret, &ipt_mutex);
	if (t) {
		duprintf("t->private->number = %u\n",
			 t->private->number);
		if (entries->size == t->private->size)
			ret = copy_entries_to_user(t->private->size,
						   t, uptr->entrytable);
		else {
			duprintf("get_entries: I've got %u not %u!\n",
				 t->private->size,
				 entries->size);
			ret = -EINVAL;
		}
		up(&ipt_mutex);
	} else
		duprintf("get_entries: Can't find %s!\n",
			 entries->name);

	return ret;
}

static int
do_replace(void __user *user, unsigned int len)
{
	int ret;
	struct ipt_replace tmp;
	struct ipt_table *t;
	struct ipt_table_info *newinfo, *oldinfo;
	struct ipt_counters *counters;

	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;

	/* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */
	if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages)
		return -ENOMEM;

	newinfo = vmalloc(sizeof(struct ipt_table_info)
			  + SMP_ALIGN(tmp.size) * NR_CPUS);
	if (!newinfo)
		return -ENOMEM;

	if (copy_from_user(newinfo->entries, user + sizeof(tmp),
			   tmp.size) != 0) {
		ret = -EFAULT;
		goto free_newinfo;
	}

	counters = vmalloc(tmp.num_counters * sizeof(struct ipt_counters));
	if (!counters) {
		ret = -ENOMEM;
		goto free_newinfo;
	}
	memset(counters, 0, tmp.num_counters * sizeof(struct ipt_counters));

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

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

	t = ipt_find_table_lock(tmp.name, &ret, &ipt_mutex);
	if (!t)
		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 free_newinfo_counters_untrans_unlock;
	}

	/* Get a reference in advance, we're not allowed fail later */
	if (!try_module_get(t->me)) {
		ret = -EBUSY;
		goto free_newinfo_counters_untrans_unlock;
	}


	oldinfo = 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 */
	IPT_ENTRY_ITERATE(oldinfo->entries, oldinfo->size, cleanup_entry,NULL);
	vfree(oldinfo);
	/* Silent error: too late now. */
	copy_to_user(tmp.counters, counters,
		     sizeof(struct ipt_counters) * tmp.num_counters);
	vfree(counters);
	up(&ipt_mutex);
	return 0;

 put_module:
	module_put(t->me);
 free_newinfo_counters_untrans_unlock:
	up(&ipt_mutex);
 free_newinfo_counters_untrans:
	IPT_ENTRY_ITERATE(newinfo->entries, newinfo->size, cleanup_entry,NULL);
 free_newinfo_counters:
	vfree(counters);
 free_newinfo:
	vfree(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 ipt_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 ipt_counters_info tmp, *paddc;
	struct ipt_table *t;
	int ret;

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

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

	paddc = vmalloc(len);
	if (!paddc)
		return -ENOMEM;

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

	t = ipt_find_table_lock(tmp.name, &ret, &ipt_mutex);
	if (!t)
		goto free;

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

	i = 0;
	IPT_ENTRY_ITERATE(t->private->entries,
			  t->private->size,
			  add_counter_to_entry,
			  paddc->counters,
			  &i);
 unlock_up_free:
	write_unlock_bh(&t->lock);
	up(&ipt_mutex);
 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: {