ip_conntrack_netlink.c

linux-2.6.15.6

/* Connection tracking via netlink socket. Allows for user space
 * protocol helpers and general trouble making from userspace.
 *
 * (C) 2001 by Jay Schulist <[e-mail]>
 * (C) 2002-2005 by Harald Welte <[e-mail]>
 * (C) 2003 by Patrick Mchardy <[e-mail]>
 * (C) 2005 by Pablo Neira Ayuso <[e-mail]>
 *
 * I've reworked this stuff to use attributes instead of conntrack 
 * structures. 5.44 am. I need more tea. --pablo 05/07/11.
 *
 * Initial connection tracking via netlink development funded and 
 * generally made possible by Network Robots, Inc. (www.networkrobots.com)
 *
 * Further development of this code funded by Astaro AG (http://www.astaro.com)
 *
 * This software may be used and distributed according to the terms
 * of the GNU General Public License, incorporated herein by reference.
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/netlink.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/notifier.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4/ip_conntrack.h>
#include <linux/netfilter_ipv4/ip_conntrack_core.h>
#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
#include <linux/netfilter_ipv4/ip_conntrack_protocol.h>
#include <linux/netfilter_ipv4/ip_nat_protocol.h>

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

MODULE_LICENSE("GPL");

static char __initdata version[] = "0.90";

#if 0
#define DEBUGP printk
#else
#define DEBUGP(format, args...)
#endif


static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb, 
			    const struct ip_conntrack_tuple *tuple)
{
	struct ip_conntrack_protocol *proto;
	int ret = 0;

	NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum);

	/* If no protocol helper is found, this function will return the
	 * generic protocol helper, so proto won't *ever* be NULL */
	proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
	if (likely(proto->tuple_to_nfattr))
		ret = proto->tuple_to_nfattr(skb, tuple);
	
	ip_conntrack_proto_put(proto);

	return ret;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_tuples(struct sk_buff *skb, 
		      const struct ip_conntrack_tuple *tuple)
{
	struct nfattr *nest_parms;
	
	nest_parms = NFA_NEST(skb, CTA_TUPLE_IP);
	NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t), &tuple->src.ip);
	NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t), &tuple->dst.ip);
	NFA_NEST_END(skb, nest_parms);

	nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO);
	ctnetlink_dump_tuples_proto(skb, tuple);
	NFA_NEST_END(skb, nest_parms);

	return 0;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_status(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	u_int32_t status = htonl((u_int32_t) ct->status);
	NFA_PUT(skb, CTA_STATUS, sizeof(status), &status);
	return 0;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_timeout(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	long timeout_l = ct->timeout.expires - jiffies;
	u_int32_t timeout;

	if (timeout_l < 0)
		timeout = 0;
	else
		timeout = htonl(timeout_l / HZ);
	
	NFA_PUT(skb, CTA_TIMEOUT, sizeof(timeout), &timeout);
	return 0;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	struct ip_conntrack_protocol *proto = ip_conntrack_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);

	struct nfattr *nest_proto;
	int ret;

	if (!proto->to_nfattr) {
		ip_conntrack_proto_put(proto);
		return 0;
	}
	
	nest_proto = NFA_NEST(skb, CTA_PROTOINFO);

	ret = proto->to_nfattr(skb, nest_proto, ct);

	ip_conntrack_proto_put(proto);

	NFA_NEST_END(skb, nest_proto);

	return ret;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	struct nfattr *nest_helper;

	if (!ct->helper)
		return 0;
		
	nest_helper = NFA_NEST(skb, CTA_HELP);
	NFA_PUT(skb, CTA_HELP_NAME, CTA_HELP_MAXNAMESIZE, &ct->helper->name);

	if (ct->helper->to_nfattr)
		ct->helper->to_nfattr(skb, ct);

	NFA_NEST_END(skb, nest_helper);

	return 0;

nfattr_failure:
	return -1;
}

#ifdef CONFIG_IP_NF_CT_ACCT
static inline int
ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *ct,
			enum ip_conntrack_dir dir)
{
	enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
	struct nfattr *nest_count = NFA_NEST(skb, type);
	u_int32_t tmp;

	tmp = htonl(ct->counters[dir].packets);
	NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp);

	tmp = htonl(ct->counters[dir].bytes);
	NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(u_int32_t), &tmp);

	NFA_NEST_END(skb, nest_count);

	return 0;

nfattr_failure:
	return -1;
}
#else
#define ctnetlink_dump_counters(a, b, c) (0)
#endif

#ifdef CONFIG_IP_NF_CONNTRACK_MARK
static inline int
ctnetlink_dump_mark(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	u_int32_t mark = htonl(ct->mark);

	NFA_PUT(skb, CTA_MARK, sizeof(u_int32_t), &mark);
	return 0;

nfattr_failure:
	return -1;
}
#else
#define ctnetlink_dump_mark(a, b) (0)
#endif

static inline int
ctnetlink_dump_id(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	u_int32_t id = htonl(ct->id);
	NFA_PUT(skb, CTA_ID, sizeof(u_int32_t), &id);
	return 0;

nfattr_failure:
	return -1;
}

static inline int
ctnetlink_dump_use(struct sk_buff *skb, const struct ip_conntrack *ct)
{
	unsigned int use = htonl(atomic_read(&ct->ct_general.use));
	
	NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use);
	return 0;

nfattr_failure:
	return -1;
}

#define tuple(ct, dir) (&(ct)->tuplehash[dir].tuple)

static int
ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
		    int event, int nowait, 
		    const struct ip_conntrack *ct)
{
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	struct nfattr *nest_parms;
	unsigned char *b;

	b = skb->tail;

	event |= NFNL_SUBSYS_CTNETLINK << 8;
	nlh    = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
	nfmsg  = NLMSG_DATA(nlh);

	nlh->nlmsg_flags    = (nowait && pid) ? NLM_F_MULTI : 0;
	nfmsg->nfgen_family = AF_INET;
	nfmsg->version      = NFNETLINK_V0;
	nfmsg->res_id	    = 0;

	nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG);
	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
		goto nfattr_failure;
	NFA_NEST_END(skb, nest_parms);
	
	nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY);
	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
		goto nfattr_failure;
	NFA_NEST_END(skb, nest_parms);

	if (ctnetlink_dump_status(skb, ct) < 0 ||
	    ctnetlink_dump_timeout(skb, ct) < 0 ||
	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
	    ctnetlink_dump_mark(skb, ct) < 0 ||
	    ctnetlink_dump_id(skb, ct) < 0 ||
	    ctnetlink_dump_use(skb, ct) < 0)
		goto nfattr_failure;

	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
nfattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
static int ctnetlink_conntrack_event(struct notifier_block *this,
                                     unsigned long events, void *ptr)
{
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	struct nfattr *nest_parms;
	struct ip_conntrack *ct = (struct ip_conntrack *)ptr;
	struct sk_buff *skb;
	unsigned int type;
	unsigned char *b;
	unsigned int flags = 0, group;

	/* ignore our fake conntrack entry */
	if (ct == &ip_conntrack_untracked)
		return NOTIFY_DONE;

	if (events & IPCT_DESTROY) {
		type = IPCTNL_MSG_CT_DELETE;
		group = NFNLGRP_CONNTRACK_DESTROY;
		goto alloc_skb;
	}
	if (events & (IPCT_NEW | IPCT_RELATED)) {
		type = IPCTNL_MSG_CT_NEW;
		flags = NLM_F_CREATE|NLM_F_EXCL;
		/* dump everything */
		events = ~0UL;
		group = NFNLGRP_CONNTRACK_NEW;
		goto alloc_skb;
	}
	if (events & (IPCT_STATUS |
		      IPCT_PROTOINFO |
		      IPCT_HELPER |
		      IPCT_HELPINFO |
		      IPCT_NATINFO)) {
		type = IPCTNL_MSG_CT_NEW;
		group = NFNLGRP_CONNTRACK_UPDATE;
		goto alloc_skb;
	} 
	
	return NOTIFY_DONE;

alloc_skb:
  /* FIXME: Check if there are any listeners before, don't hurt performance */
	
	skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
	if (!skb)
		return NOTIFY_DONE;

	b = skb->tail;

	type |= NFNL_SUBSYS_CTNETLINK << 8;
	nlh   = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg));
	nfmsg = NLMSG_DATA(nlh);

	nlh->nlmsg_flags    = flags;
	nfmsg->nfgen_family = AF_INET;
	nfmsg->version	= NFNETLINK_V0;
	nfmsg->res_id	= 0;

	nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG);
	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
		goto nfattr_failure;
	NFA_NEST_END(skb, nest_parms);
	
	nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY);
	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
		goto nfattr_failure;
	NFA_NEST_END(skb, nest_parms);
	
	/* NAT stuff is now a status flag */
	if ((events & IPCT_STATUS || events & IPCT_NATINFO)
	    && ctnetlink_dump_status(skb, ct) < 0)
		goto nfattr_failure;
	if (events & IPCT_REFRESH
	    && ctnetlink_dump_timeout(skb, ct) < 0)
		goto nfattr_failure;
	if (events & IPCT_PROTOINFO
	    && ctnetlink_dump_protoinfo(skb, ct) < 0)
		goto nfattr_failure;
	if (events & IPCT_HELPINFO
	    && ctnetlink_dump_helpinfo(skb, ct) < 0)
		goto nfattr_failure;

	if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
		goto nfattr_failure;

	nlh->nlmsg_len = skb->tail - b;
	nfnetlink_send(skb, 0, group, 0);
	return NOTIFY_DONE;

nlmsg_failure:
nfattr_failure:
	kfree_skb(skb);
	return NOTIFY_DONE;
}
#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */

static int ctnetlink_done(struct netlink_callback *cb)
{
	DEBUGP("entered %s\n", __FUNCTION__);
	return 0;
}

static int
ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct ip_conntrack *ct = NULL;
	struct ip_conntrack_tuple_hash *h;
	struct list_head *i;
	u_int32_t *id = (u_int32_t *) &cb->args[1];

	DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, 
			cb->args[0], *id);

	read_lock_bh(&ip_conntrack_lock);
	for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) {
		list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) {
			h = (struct ip_conntrack_tuple_hash *) i;
			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
				continue;
			ct = tuplehash_to_ctrack(h);
			if (ct->id <= *id)
				continue;
			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
		                        	cb->nlh->nlmsg_seq,
						IPCTNL_MSG_CT_NEW,
						1, ct) < 0)
				goto out;
			*id = ct->id;
		}
	}
out:	
	read_unlock_bh(&ip_conntrack_lock);

	DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);

	return skb->len;
}

#ifdef CONFIG_IP_NF_CT_ACCT
static int
ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct ip_conntrack *ct = NULL;
	struct ip_conntrack_tuple_hash *h;
	struct list_head *i;
	u_int32_t *id = (u_int32_t *) &cb->args[1];

	DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, 
			cb->args[0], *id);

	write_lock_bh(&ip_conntrack_lock);
	for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) {
		list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) {
			h = (struct ip_conntrack_tuple_hash *) i;
			if (DIRECTION(h) != IP_CT_DIR_ORIGINAL)
				continue;
			ct = tuplehash_to_ctrack(h);
			if (ct->id <= *id)
				continue;
			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
		                        	cb->nlh->nlmsg_seq,
						IPCTNL_MSG_CT_NEW,
						1, ct) < 0)
				goto out;
			*id = ct->id;

			memset(&ct->counters, 0, sizeof(ct->counters));
		}
	}
out:	
	write_unlock_bh(&ip_conntrack_lock);

	DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);

	return skb->len;
}
#endif

static const size_t cta_min_ip[CTA_IP_MAX] = {
	[CTA_IP_V4_SRC-1]	= sizeof(u_int32_t),
	[CTA_IP_V4_DST-1]	= sizeof(u_int32_t),
};

static inline int
ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple)
{
	struct nfattr *tb[CTA_IP_MAX];

	DEBUGP("entered %s\n", __FUNCTION__);

	nfattr_parse_nested(tb, CTA_IP_MAX, attr);

	if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip))
		return -EINVAL;

	if (!tb[CTA_IP_V4_SRC-1])
		return -EINVAL;
	tuple->src.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_SRC-1]);

	if (!tb[CTA_IP_V4_DST-1])
		return -EINVAL;
	tuple->dst.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_DST-1]);

	DEBUGP("leaving\n");

	return 0;
}

static const size_t cta_min_proto[CTA_PROTO_MAX] = {
	[CTA_PROTO_NUM-1]	= sizeof(u_int8_t),
	[CTA_PROTO_SRC_PORT-1]	= sizeof(u_int16_t),
	[CTA_PROTO_DST_PORT-1]	= sizeof(u_int16_t),
	[CTA_PROTO_ICMP_TYPE-1]	= sizeof(u_int8_t),
	[CTA_PROTO_ICMP_CODE-1]	= sizeof(u_int8_t),
	[CTA_PROTO_ICMP_ID-1]	= sizeof(u_int16_t),
};

static inline int
ctnetlink_parse_tuple_proto(struct nfattr *attr, 
			    struct ip_conntrack_tuple *tuple)
{
	struct nfattr *tb[CTA_PROTO_MAX];
	struct ip_conntrack_protocol *proto;
	int ret = 0;

	DEBUGP("entered %s\n", __FUNCTION__);

	nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);

	if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
		return -EINVAL;

	if (!tb[CTA_PROTO_NUM-1])
		return -EINVAL;
	tuple->dst.protonum = *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_NUM-1]);

	proto = ip_conntrack_proto_find_get(tuple->dst.protonum);

	if (likely(proto->nfattr_to_tuple))
		ret = proto->nfattr_to_tuple(tb, tuple);
	
	ip_conntrack_proto_put(proto);
	
	return ret;
}

static inline int
ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple,
		      enum ctattr_tuple type)
{
	struct nfattr *tb[CTA_TUPLE_MAX];