* (C) 2001 by Jay Schulist <jschlst@samba.org>
* (C) 2002-2005 by Harald Welte <laforge@gnumonks.org>
* (C) 2003 by Patrick Mchardy <kaber@trash.net>
- * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net>
+ * (C) 2005-2006 by Pablo Neira Ayuso <pablo@eurodev.net>
*
* I've reworked this stuff to use attributes instead of conntrack
* structures. 5.44 am. I need more tea. --pablo 05/07/11.
#include <linux/errno.h>
#include <linux/netlink.h>
#include <linux/spinlock.h>
+#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/netfilter.h>
static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb,
- const struct ip_conntrack_tuple *tuple)
+ const struct ip_conntrack_tuple *tuple,
+ struct ip_conntrack_protocol *proto)
{
- struct ip_conntrack_protocol *proto;
int ret = 0;
+ struct nfattr *nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO);
NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum);
- proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
- if (likely(proto && proto->tuple_to_nfattr)) {
+ if (likely(proto->tuple_to_nfattr))
ret = proto->tuple_to_nfattr(skb, tuple);
- ip_conntrack_proto_put(proto);
- }
+
+ NFA_NEST_END(skb, nest_parms);
return ret;
}
static inline int
-ctnetlink_dump_tuples(struct sk_buff *skb,
- const struct ip_conntrack_tuple *tuple)
+ctnetlink_dump_tuples_ip(struct sk_buff *skb,
+ const struct ip_conntrack_tuple *tuple)
{
- struct nfattr *nest_parms;
+ struct nfattr *nest_parms = NFA_NEST(skb, CTA_TUPLE_IP);
- 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;
}
static inline int
+ctnetlink_dump_tuples(struct sk_buff *skb,
+ const struct ip_conntrack_tuple *tuple)
+{
+ int ret;
+ struct ip_conntrack_protocol *proto;
+
+ ret = ctnetlink_dump_tuples_ip(skb, tuple);
+ if (unlikely(ret < 0))
+ return ret;
+
+ proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
+ ret = ctnetlink_dump_tuples_proto(skb, tuple, proto);
+ ip_conntrack_proto_put(proto);
+
+ return ret;
+}
+
+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);
struct nfattr *nest_proto;
int ret;
-
- if (!proto || !proto->to_nfattr)
+
+ if (!proto->to_nfattr) {
+ ip_conntrack_proto_put(proto);
return 0;
+ }
nest_proto = NFA_NEST(skb, CTA_PROTOINFO);
return 0;
nest_helper = NFA_NEST(skb, CTA_HELP);
- NFA_PUT(skb, CTA_HELP_NAME, CTA_HELP_MAXNAMESIZE, &ct->helper->name);
+ NFA_PUT(skb, CTA_HELP_NAME, strlen(ct->helper->name), ct->helper->name);
if (ct->helper->to_nfattr)
ct->helper->to_nfattr(skb, ct);
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));
+ u_int32_t use = htonl(atomic_read(&ct->ct_general.use));
NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use);
return 0;
if (events & IPCT_DESTROY) {
type = IPCTNL_MSG_CT_DELETE;
group = NFNLGRP_CONNTRACK_DESTROY;
- goto alloc_skb;
- }
- if (events & (IPCT_NEW | IPCT_RELATED)) {
+ } else 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 |
+ } else 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;
+ } else
+ return NOTIFY_DONE;
+
+ if (!nfnetlink_has_listeners(group))
+ 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;
static int ctnetlink_done(struct netlink_callback *cb)
{
DEBUGP("entered %s\n", __FUNCTION__);
+ if (cb->args[1])
+ ip_conntrack_put((struct ip_conntrack *)cb->args[1]);
return 0;
}
static int
ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct ip_conntrack *ct = NULL;
+ struct ip_conntrack *ct, *last;
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) {
+ for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++) {
+restart:
+ last = (struct ip_conntrack *)cb->args[1];
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 (last != NULL) {
+ if (ct == last) {
+ ip_conntrack_put(last);
+ cb->args[1] = 0;
+ last = NULL;
+ } else
+ continue;
+ }
if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
IPCTNL_MSG_CT_NEW,
- 1, ct) < 0)
+ 1, ct) < 0) {
+ nf_conntrack_get(&ct->ct_general);
+ cb->args[1] = (unsigned long)ct;
goto out;
- *id = ct->id;
+ }
+ }
+ if (last != NULL) {
+ ip_conntrack_put(last);
+ cb->args[1] = 0;
+ goto restart;
}
}
-out:
+out:
read_unlock_bh(&ip_conntrack_lock);
DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
}
static const size_t cta_min_proto[CTA_PROTO_MAX] = {
- [CTA_PROTO_NUM-1] = sizeof(u_int16_t),
+ [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),
if (!tb[CTA_PROTO_NUM-1])
return -EINVAL;
- tuple->dst.protonum = *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_NUM-1]);
+ 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 && proto->nfattr_to_tuple)) {
+ if (likely(proto->nfattr_to_tuple))
ret = proto->nfattr_to_tuple(tb, tuple);
- ip_conntrack_proto_put(proto);
- }
+
+ ip_conntrack_proto_put(proto);
return ret;
}
return -EINVAL;
npt = ip_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
- if (!npt)
- return 0;
if (!npt->nfattr_to_range) {
ip_nat_proto_put(npt);
};
static inline int
-ctnetlink_parse_nat(struct nfattr *cda[],
+ctnetlink_parse_nat(struct nfattr *nat,
const struct ip_conntrack *ct, struct ip_nat_range *range)
{
struct nfattr *tb[CTA_NAT_MAX];
memset(range, 0, sizeof(*range));
- nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]);
+ nfattr_parse_nested(tb, CTA_NAT_MAX, nat);
if (nfattr_bad_size(tb, CTA_NAT_MAX, cta_min_nat))
return -EINVAL;
return -ENOENT;
}
}
- if (del_timer(&ct->timeout)) {
- ip_conntrack_put(ct);
+ if (del_timer(&ct->timeout))
ct->timeout.function((unsigned long)ct);
- return 0;
- }
+
ip_conntrack_put(ct);
DEBUGP("leaving\n");
/* ASSURED bit can only be set */
return -EINVAL;
- if (cda[CTA_NAT-1]) {
+ if (cda[CTA_NAT_SRC-1] || cda[CTA_NAT_DST-1]) {
#ifndef CONFIG_IP_NF_NAT_NEEDED
return -EINVAL;
#else
- unsigned int hooknum;
struct ip_nat_range range;
- if (ctnetlink_parse_nat(cda, ct, &range) < 0)
- return -EINVAL;
-
- DEBUGP("NAT: %u.%u.%u.%u-%u.%u.%u.%u:%u-%u\n",
- NIPQUAD(range.min_ip), NIPQUAD(range.max_ip),
- htons(range.min.all), htons(range.max.all));
-
- /* This is tricky but it works. ip_nat_setup_info needs the
- * hook number as parameter, so let's do the correct
- * conversion and run away */
- if (status & IPS_SRC_NAT_DONE)
- hooknum = NF_IP_POST_ROUTING; /* IP_NAT_MANIP_SRC */
- else if (status & IPS_DST_NAT_DONE)
- hooknum = NF_IP_PRE_ROUTING; /* IP_NAT_MANIP_DST */
- else
- return -EINVAL; /* Missing NAT flags */
-
- DEBUGP("NAT status: %lu\n",
- status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK));
-
- if (ip_nat_initialized(ct, hooknum))
- return -EEXIST;
- ip_nat_setup_info(ct, &range, hooknum);
-
- DEBUGP("NAT status after setup_info: %lu\n",
- ct->status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK));
+ if (cda[CTA_NAT_DST-1]) {
+ if (ctnetlink_parse_nat(cda[CTA_NAT_DST-1], ct,
+ &range) < 0)
+ return -EINVAL;
+ if (ip_nat_initialized(ct,
+ HOOK2MANIP(NF_IP_PRE_ROUTING)))
+ return -EEXIST;
+ ip_nat_setup_info(ct, &range, NF_IP_PRE_ROUTING);
+ }
+ if (cda[CTA_NAT_SRC-1]) {
+ if (ctnetlink_parse_nat(cda[CTA_NAT_SRC-1], ct,
+ &range) < 0)
+ return -EINVAL;
+ if (ip_nat_initialized(ct,
+ HOOK2MANIP(NF_IP_POST_ROUTING)))
+ return -EEXIST;
+ ip_nat_setup_info(ct, &range, NF_IP_POST_ROUTING);
+ }
#endif
}
nfattr_parse_nested(tb, CTA_PROTOINFO_MAX, attr);
proto = ip_conntrack_proto_find_get(npt);
- if (!proto)
- return -EINVAL;
if (proto->from_nfattr)
err = proto->from_nfattr(tb, ct);
return err;
}
+#if defined(CONFIG_IP_NF_CONNTRACK_MARK)
+ if (cda[CTA_MARK-1])
+ ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
+#endif
+
ct->helper = ip_conntrack_helper_find_get(rtuple);
add_timer(&ct->timeout);
if (ct->helper)
ip_conntrack_helper_put(ct->helper);
-#if defined(CONFIG_IP_NF_CONNTRACK_MARK)
- if (cda[CTA_MARK-1])
- ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
-#endif
-
DEBUGP("conntrack with id %u inserted\n", ct->id);
return 0;
/* implicit 'else' */
/* we only allow nat config for new conntracks */
- if (cda[CTA_NAT-1]) {
+ if (cda[CTA_NAT_SRC-1] || cda[CTA_NAT_DST-1]) {
err = -EINVAL;
goto out_unlock;
}
}
static inline int
+ctnetlink_exp_dump_mask(struct sk_buff *skb,
+ const struct ip_conntrack_tuple *tuple,
+ const struct ip_conntrack_tuple *mask)
+{
+ int ret;
+ struct ip_conntrack_protocol *proto;
+ struct nfattr *nest_parms = NFA_NEST(skb, CTA_EXPECT_MASK);
+
+ ret = ctnetlink_dump_tuples_ip(skb, mask);
+ if (unlikely(ret < 0))
+ goto nfattr_failure;
+
+ proto = ip_conntrack_proto_find_get(tuple->dst.protonum);
+ ret = ctnetlink_dump_tuples_proto(skb, mask, proto);
+ ip_conntrack_proto_put(proto);
+ if (unlikely(ret < 0))
+ goto nfattr_failure;
+
+ NFA_NEST_END(skb, nest_parms);
+
+ return 0;
+
+nfattr_failure:
+ return -1;
+}
+
+static inline int
ctnetlink_exp_dump_expect(struct sk_buff *skb,
const struct ip_conntrack_expect *exp)
{
if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0)
goto nfattr_failure;
- if (ctnetlink_exp_dump_tuple(skb, &exp->mask, CTA_EXPECT_MASK) < 0)
+ if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0)
goto nfattr_failure;
if (ctnetlink_exp_dump_tuple(skb,
&master->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
unsigned int type;
unsigned char *b;
int flags = 0;
- u16 proto;
if (events & IPEXP_NEW) {
type = IPCTNL_MSG_EXP_NEW;
b = skb->tail;
- type |= NFNL_SUBSYS_CTNETLINK << 8;
+ type |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg));
nfmsg = NLMSG_DATA(nlh);
goto nfattr_failure;
nlh->nlmsg_len = skb->tail - b;
- proto = exp->tuple.dst.protonum;
nfnetlink_send(skb, 0, NFNLGRP_CONNTRACK_EXP_NEW, 0);
return NOTIFY_DONE;
};
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK);
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP);
static int __init ctnetlink_init(void)
{
printk("ctnetlink: unregistering from nfnetlink.\n");
#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
- ip_conntrack_unregister_notifier(&ctnl_notifier_exp);
+ ip_conntrack_expect_unregister_notifier(&ctnl_notifier_exp);
ip_conntrack_unregister_notifier(&ctnl_notifier);
#endif