* (C) 2001 by Jay Schulist <jschlst@samba.org>
* (C) 2002-2006 by Harald Welte <laforge@gnumonks.org>
* (C) 2003 by Patrick Mchardy <kaber@trash.net>
- * (C) 2005-2007 by Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org>
*
* Initial connection tracking via netlink development funded and
* generally made possible by Network Robots, Inc. (www.networkrobots.com)
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/rculist.h>
+#include <linux/rculist_nulls.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_acct.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_protocol.h>
return -1;
}
-static inline int
+static int
ctnetlink_dump_tuples(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_l3proto *l3proto;
struct nf_conntrack_l4proto *l4proto;
- l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+ l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
ret = ctnetlink_dump_tuples_ip(skb, tuple, l3proto);
- nf_ct_l3proto_put(l3proto);
if (unlikely(ret < 0))
return ret;
- l4proto = nf_ct_l4proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+ l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto);
- nf_ct_l4proto_put(l4proto);
return ret;
}
static inline int
ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct)
{
- struct nf_conntrack_l4proto *l4proto = nf_ct_l4proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
+ struct nf_conntrack_l4proto *l4proto;
struct nlattr *nest_proto;
int ret;
- if (!l4proto->to_nlattr) {
- nf_ct_l4proto_put(l4proto);
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
+ if (!l4proto->to_nlattr)
return 0;
- }
nest_proto = nla_nest_start(skb, CTA_PROTOINFO | NLA_F_NESTED);
if (!nest_proto)
ret = l4proto->to_nlattr(skb, nest_proto, ct);
- nf_ct_l4proto_put(l4proto);
-
nla_nest_end(skb, nest_proto);
return ret;
nla_put_failure:
- nf_ct_l4proto_put(l4proto);
return -1;
}
if (!help)
return 0;
- rcu_read_lock();
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
nla_nest_end(skb, nest_helper);
out:
- rcu_read_unlock();
return 0;
nla_put_failure:
- rcu_read_unlock();
return -1;
}
-#ifdef CONFIG_NF_CT_ACCT
-static inline int
+static int
ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
enum ip_conntrack_dir dir)
{
enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG;
struct nlattr *nest_count;
+ const struct nf_conn_counter *acct;
+
+ acct = nf_conn_acct_find(ct);
+ if (!acct)
+ return 0;
nest_count = nla_nest_start(skb, type | NLA_F_NESTED);
if (!nest_count)
goto nla_put_failure;
- NLA_PUT_BE32(skb, CTA_COUNTERS32_PACKETS,
- htonl(ct->counters[dir].packets));
- NLA_PUT_BE32(skb, CTA_COUNTERS32_BYTES,
- htonl(ct->counters[dir].bytes));
+ NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS,
+ cpu_to_be64(acct[dir].packets));
+ NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES,
+ cpu_to_be64(acct[dir].bytes));
nla_nest_end(skb, nest_count);
nla_put_failure:
return -1;
}
-#else
-#define ctnetlink_dump_counters(a, b, c) (0)
-#endif
#ifdef CONFIG_NF_CONNTRACK_MARK
static inline int
}
#ifdef CONFIG_NF_NAT_NEEDED
-static inline int
+static int
dump_nat_seq_adj(struct sk_buff *skb, const struct nf_nat_seq *natseq, int type)
{
struct nlattr *nest_parms;
nfmsg = NLMSG_DATA(nlh);
nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
- nfmsg->nfgen_family =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+ nfmsg->nfgen_family = nf_ct_l3num(ct);
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
+/*
+ * The general structure of a ctnetlink event is
+ *
+ * CTA_TUPLE_ORIG
+ * <l3/l4-proto-attributes>
+ * CTA_TUPLE_REPLY
+ * <l3/l4-proto-attributes>
+ * CTA_ID
+ * ...
+ * CTA_PROTOINFO
+ * <l4-proto-attributes>
+ * CTA_TUPLE_MASTER
+ * <l3/l4-proto-attributes>
+ *
+ * Therefore the formular is
+ *
+ * size = sizeof(headers) + sizeof(generic_nlas) + 3 * sizeof(tuple_nlas)
+ * + sizeof(protoinfo_nlas)
+ */
+static struct sk_buff *
+ctnetlink_alloc_skb(const struct nf_conntrack_tuple *tuple, gfp_t gfp)
+{
+ struct nf_conntrack_l3proto *l3proto;
+ struct nf_conntrack_l4proto *l4proto;
+ int len;
+
+#define NLA_TYPE_SIZE(type) nla_total_size(sizeof(type))
+
+ /* proto independant part */
+ len = NLMSG_SPACE(sizeof(struct nfgenmsg))
+ + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */
+ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */
+ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */
+ + 3 * NLA_TYPE_SIZE(u_int8_t) /* CTA_PROTO_NUM */
+ + NLA_TYPE_SIZE(u_int32_t) /* CTA_ID */
+ + NLA_TYPE_SIZE(u_int32_t) /* CTA_STATUS */
+#ifdef CONFIG_NF_CT_ACCT
+ + 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */
+ + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_PACKETS */
+ + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_BYTES */
+#endif
+ + NLA_TYPE_SIZE(u_int32_t) /* CTA_TIMEOUT */
+ + nla_total_size(0) /* CTA_PROTOINFO */
+ + nla_total_size(0) /* CTA_HELP */
+ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+ + NLA_TYPE_SIZE(u_int32_t) /* CTA_SECMARK */
+#endif
+#ifdef CONFIG_NF_NAT_NEEDED
+ + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_POS */
+ + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_BEFORE */
+ + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_AFTER */
+#endif
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ + NLA_TYPE_SIZE(u_int32_t) /* CTA_MARK */
+#endif
+ ;
+
+#undef NLA_TYPE_SIZE
+
+ rcu_read_lock();
+ l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
+ len += l3proto->nla_size;
+
+ l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
+ len += l4proto->nla_size;
+ rcu_read_unlock();
+
+ return alloc_skb(len, gfp);
+}
+
static int ctnetlink_conntrack_event(struct notifier_block *this,
unsigned long events, void *ptr)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
- struct nf_conn *ct = (struct nf_conn *)ptr;
+ struct nf_ct_event *item = (struct nf_ct_event *)ptr;
+ struct nf_conn *ct = item->ct;
struct sk_buff *skb;
unsigned int type;
sk_buff_data_t b;
} else
return NOTIFY_DONE;
- if (!nfnetlink_has_listeners(group))
+ if (!item->report && !nfnetlink_has_listeners(group))
return NOTIFY_DONE;
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+ skb = ctnetlink_alloc_skb(tuple(ct, IP_CT_DIR_ORIGINAL), GFP_ATOMIC);
if (!skb)
- return NOTIFY_DONE;
+ goto errout;
b = skb->tail;
type |= NFNL_SUBSYS_CTNETLINK << 8;
- nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg));
+ nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
nfmsg = NLMSG_DATA(nlh);
nlh->nlmsg_flags = flags;
- nfmsg->nfgen_family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+ nfmsg->nfgen_family = nf_ct_l3num(ct);
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
+ rcu_read_lock();
nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
if (!nest_parms)
goto nla_put_failure;
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
+ if (ctnetlink_dump_id(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if (ctnetlink_dump_status(skb, ct) < 0)
+ goto nla_put_failure;
+
if (events & IPCT_DESTROY) {
if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
goto nla_put_failure;
} else {
- if (ctnetlink_dump_status(skb, ct) < 0)
- goto nla_put_failure;
-
if (ctnetlink_dump_timeout(skb, ct) < 0)
goto nla_put_failure;
&& ctnetlink_dump_helpinfo(skb, ct) < 0)
goto nla_put_failure;
-#ifdef CONFIG_NF_CONNTRACK_MARK
- if ((events & IPCT_MARK || ct->mark)
- && ctnetlink_dump_mark(skb, ct) < 0)
- goto nla_put_failure;
-#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
if ((events & IPCT_SECMARK || ct->secmark)
&& ctnetlink_dump_secmark(skb, ct) < 0)
goto nla_put_failure;
#endif
- if (events & IPCT_COUNTER_FILLING &&
- (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
- ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0))
- goto nla_put_failure;
-
if (events & IPCT_RELATED &&
ctnetlink_dump_master(skb, ct) < 0)
goto nla_put_failure;
goto nla_put_failure;
}
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ if ((events & IPCT_MARK || ct->mark)
+ && ctnetlink_dump_mark(skb, ct) < 0)
+ goto nla_put_failure;
+#endif
+ rcu_read_unlock();
+
nlh->nlmsg_len = skb->tail - b;
- nfnetlink_send(skb, 0, group, 0);
+ nfnetlink_send(skb, item->pid, group, item->report);
return NOTIFY_DONE;
-nlmsg_failure:
nla_put_failure:
+ rcu_read_unlock();
+nlmsg_failure:
kfree_skb(skb);
+errout:
+ nfnetlink_set_err(0, group, -ENOBUFS);
return NOTIFY_DONE;
}
#endif /* CONFIG_NF_CONNTRACK_EVENTS */
return 0;
}
-#define L3PROTO(ct) ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num
-
static int
ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
struct nf_conn *ct, *last;
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
- read_lock_bh(&nf_conntrack_lock);
+ rcu_read_lock();
last = (struct nf_conn *)cb->args[1];
for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
restart:
- hlist_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]],
- hnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]],
+ hnnode) {
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
continue;
ct = nf_ct_tuplehash_to_ctrack(h);
+ if (!atomic_inc_not_zero(&ct->ct_general.use))
+ continue;
/* Dump entries of a given L3 protocol number.
* If it is not specified, ie. l3proto == 0,
* then dump everything. */
- if (l3proto && L3PROTO(ct) != l3proto)
- continue;
+ if (l3proto && nf_ct_l3num(ct) != l3proto)
+ goto releasect;
if (cb->args[1]) {
if (ct != last)
- continue;
+ goto releasect;
cb->args[1] = 0;
}
if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
IPCTNL_MSG_CT_NEW,
1, ct) < 0) {
- nf_conntrack_get(&ct->ct_general);
cb->args[1] = (unsigned long)ct;
goto out;
}
-#ifdef CONFIG_NF_CT_ACCT
+
if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) ==
- IPCTNL_MSG_CT_GET_CTRZERO)
- memset(&ct->counters, 0, sizeof(ct->counters));
-#endif
+ IPCTNL_MSG_CT_GET_CTRZERO) {
+ struct nf_conn_counter *acct;
+
+ acct = nf_conn_acct_find(ct);
+ if (acct)
+ memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]));
+ }
+releasect:
+ nf_ct_put(ct);
}
if (cb->args[1]) {
cb->args[1] = 0;
}
}
out:
- read_unlock_bh(&nf_conntrack_lock);
+ rcu_read_unlock();
if (last)
nf_ct_put(last);
nla_parse_nested(tb, CTA_IP_MAX, attr, NULL);
- l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+ rcu_read_lock();
+ l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
if (likely(l3proto->nlattr_to_tuple)) {
ret = nla_validate_nested(attr, CTA_IP_MAX,
ret = l3proto->nlattr_to_tuple(tb, tuple);
}
- nf_ct_l3proto_put(l3proto);
+ rcu_read_unlock();
return ret;
}
return -EINVAL;
tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]);
- l4proto = nf_ct_l4proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+ rcu_read_lock();
+ l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
if (likely(l4proto->nlattr_to_tuple)) {
ret = nla_validate_nested(attr, CTA_PROTO_MAX,
ret = l4proto->nlattr_to_tuple(tb, tuple);
}
- nf_ct_l4proto_put(l4proto);
+ rcu_read_unlock();
return ret;
}
-static inline int
+static int
ctnetlink_parse_tuple(struct nlattr *cda[], struct nf_conntrack_tuple *tuple,
enum ctattr_tuple type, u_int8_t l3num)
{
return 0;
}
-#ifdef CONFIG_NF_NAT_NEEDED
-static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = {
- [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 },
- [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 },
-};
-
-static int nfnetlink_parse_nat_proto(struct nlattr *attr,
- const struct nf_conn *ct,
- struct nf_nat_range *range)
-{
- struct nlattr *tb[CTA_PROTONAT_MAX+1];
- const struct nf_nat_protocol *npt;
- int err;
-
- err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy);
- if (err < 0)
- return err;
-
- npt = nf_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum);
-
- if (!npt->nlattr_to_range) {
- nf_nat_proto_put(npt);
- return 0;
- }
-
- /* nlattr_to_range returns 1 if it parsed, 0 if not, neg. on error */
- if (npt->nlattr_to_range(tb, range) > 0)
- range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED;
-
- nf_nat_proto_put(npt);
-
- return 0;
-}
-
-static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
- [CTA_NAT_MINIP] = { .type = NLA_U32 },
- [CTA_NAT_MAXIP] = { .type = NLA_U32 },
-};
-
-static inline int
-nfnetlink_parse_nat(struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range)
-{
- struct nlattr *tb[CTA_NAT_MAX+1];
- int err;
-
- memset(range, 0, sizeof(*range));
-
- err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy);
- if (err < 0)
- return err;
-
- if (tb[CTA_NAT_MINIP])
- range->min_ip = nla_get_be32(tb[CTA_NAT_MINIP]);
-
- if (!tb[CTA_NAT_MAXIP])
- range->max_ip = range->min_ip;
- else
- range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]);
-
- if (range->min_ip)
- range->flags |= IP_NAT_RANGE_MAP_IPS;
-
- if (!tb[CTA_NAT_PROTO])
- return 0;
-
- err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
- if (err < 0)
- return err;
-
- return 0;
-}
-#endif
-
static inline int
ctnetlink_parse_help(struct nlattr *attr, char **helper_name)
{
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3);
else {
/* Flush the whole table */
- nf_conntrack_flush();
+ nf_conntrack_flush(&init_net,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
return 0;
}
if (err < 0)
return err;
- h = nf_conntrack_find_get(&tuple);
+ h = nf_conntrack_find_get(&init_net, &tuple);
if (!h)
return -ENOENT;
return -ENOENT;
}
}
- if (del_timer(&ct->timeout))
- ct->timeout.function((unsigned long)ct);
+ nf_conntrack_event_report(IPCT_DESTROY,
+ ct,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+
+ /* death_by_timeout would report the event again */
+ set_bit(IPS_DYING_BIT, &ct->status);
+
+ nf_ct_kill(ct);
nf_ct_put(ct);
return 0;
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- if (nlh->nlmsg_flags & NLM_F_DUMP) {
-#ifndef CONFIG_NF_CT_ACCT
- if (NFNL_MSG_TYPE(nlh->nlmsg_type) == IPCTNL_MSG_CT_GET_CTRZERO)
- return -ENOTSUPP;
-#endif
+ if (nlh->nlmsg_flags & NLM_F_DUMP)
return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table,
ctnetlink_done);
- }
if (cda[CTA_TUPLE_ORIG])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
if (err < 0)
return err;
- h = nf_conntrack_find_get(&tuple);
+ h = nf_conntrack_find_get(&init_net, &tuple);
if (!h)
return -ENOENT;
return -ENOMEM;
}
+ rcu_read_lock();
err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq,
IPCTNL_MSG_CT_NEW, 1, ct);
+ rcu_read_unlock();
nf_ct_put(ct);
if (err <= 0)
goto free;
return err;
}
-static inline int
+#ifdef CONFIG_NF_NAT_NEEDED
+static int
+ctnetlink_parse_nat_setup(struct nf_conn *ct,
+ enum nf_nat_manip_type manip,
+ struct nlattr *attr)
+{
+ typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup;
+
+ parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook);
+ if (!parse_nat_setup) {
+#ifdef CONFIG_MODULES
+ rcu_read_unlock();
+ spin_unlock_bh(&nf_conntrack_lock);
+ nfnl_unlock();
+ if (request_module("nf-nat-ipv4") < 0) {
+ nfnl_lock();
+ spin_lock_bh(&nf_conntrack_lock);
+ rcu_read_lock();
+ return -EOPNOTSUPP;
+ }
+ nfnl_lock();
+ spin_lock_bh(&nf_conntrack_lock);
+ rcu_read_lock();
+ if (nfnetlink_parse_nat_setup_hook)
+ return -EAGAIN;
+#endif
+ return -EOPNOTSUPP;
+ }
+
+ return parse_nat_setup(ct, manip, attr);
+}
+#endif
+
+static int
ctnetlink_change_status(struct nf_conn *ct, struct nlattr *cda[])
{
unsigned long d;
if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING))
/* unchangeable */
- return -EINVAL;
+ return -EBUSY;
if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY))
/* SEEN_REPLY bit can only be set */
- return -EINVAL;
-
+ return -EBUSY;
if (d & IPS_ASSURED && !(status & IPS_ASSURED))
/* ASSURED bit can only be set */
- return -EINVAL;
-
- if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
-#ifndef CONFIG_NF_NAT_NEEDED
- return -EINVAL;
-#else
- struct nf_nat_range range;
-
- if (cda[CTA_NAT_DST]) {
- if (nfnetlink_parse_nat(cda[CTA_NAT_DST], ct,
- &range) < 0)
- return -EINVAL;
- if (nf_nat_initialized(ct, IP_NAT_MANIP_DST))
- return -EEXIST;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST);
- }
- if (cda[CTA_NAT_SRC]) {
- if (nfnetlink_parse_nat(cda[CTA_NAT_SRC], ct,
- &range) < 0)
- return -EINVAL;
- if (nf_nat_initialized(ct, IP_NAT_MANIP_SRC))
- return -EEXIST;
- nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC);
- }
-#endif
- }
+ return -EBUSY;
/* Be careful here, modifying NAT bits can screw up things,
* so don't let users modify them directly if they don't pass
return 0;
}
+static int
+ctnetlink_change_nat(struct nf_conn *ct, struct nlattr *cda[])
+{
+#ifdef CONFIG_NF_NAT_NEEDED
+ int ret;
+
+ if (cda[CTA_NAT_DST]) {
+ ret = ctnetlink_parse_nat_setup(ct,
+ IP_NAT_MANIP_DST,
+ cda[CTA_NAT_DST]);
+ if (ret < 0)
+ return ret;
+ }
+ if (cda[CTA_NAT_SRC]) {
+ ret = ctnetlink_parse_nat_setup(ct,
+ IP_NAT_MANIP_SRC,
+ cda[CTA_NAT_SRC]);
+ if (ret < 0)
+ return ret;
+ }
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
static inline int
ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[])
{
struct nf_conntrack_helper *helper;
struct nf_conn_help *help = nfct_help(ct);
- char *helpname;
+ char *helpname = NULL;
int err;
/* don't change helper of sibling connections */
if (ct->master)
- return -EINVAL;
+ return -EBUSY;
err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
if (err < 0)
}
helper = __nf_conntrack_helper_find_byname(helpname);
- if (helper == NULL)
- return -EINVAL;
+ if (helper == NULL) {
+#ifdef CONFIG_MODULES
+ spin_unlock_bh(&nf_conntrack_lock);
+
+ if (request_module("nfct-helper-%s", helpname) < 0) {
+ spin_lock_bh(&nf_conntrack_lock);
+ return -EOPNOTSUPP;
+ }
+
+ spin_lock_bh(&nf_conntrack_lock);
+ helper = __nf_conntrack_helper_find_byname(helpname);
+ if (helper)
+ return -EAGAIN;
+#endif
+ return -EOPNOTSUPP;
+ }
if (help) {
if (help->helper == helper)
/* need to zero data of old helper */
memset(&help->help, 0, sizeof(help->help));
} else {
- help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
+ help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
if (help == NULL)
return -ENOMEM;
}
{
struct nlattr *tb[CTA_PROTOINFO_MAX+1], *attr = cda[CTA_PROTOINFO];
struct nf_conntrack_l4proto *l4proto;
- u_int16_t npt = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
- u_int16_t l3num = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
int err = 0;
nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, NULL);
- l4proto = nf_ct_l4proto_find_get(l3num, npt);
-
+ rcu_read_lock();
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
if (l4proto->from_nlattr)
err = l4proto->from_nlattr(tb, ct);
- nf_ct_l4proto_put(l4proto);
+ rcu_read_unlock();
return err;
}
{
int err;
+ /* only allow NAT changes and master assignation for new conntracks */
+ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER])
+ return -EOPNOTSUPP;
+
if (cda[CTA_HELP]) {
err = ctnetlink_change_helper(ct, cda);
if (err < 0)
return 0;
}
-static int
+static struct nf_conn *
ctnetlink_create_conntrack(struct nlattr *cda[],
struct nf_conntrack_tuple *otuple,
struct nf_conntrack_tuple *rtuple,
- struct nf_conn *master_ct)
+ u8 u3)
{
struct nf_conn *ct;
int err = -EINVAL;
- struct nf_conn_help *help;
struct nf_conntrack_helper *helper;
- ct = nf_conntrack_alloc(otuple, rtuple);
- if (ct == NULL || IS_ERR(ct))
- return -ENOMEM;
+ ct = nf_conntrack_alloc(&init_net, otuple, rtuple, GFP_ATOMIC);
+ if (IS_ERR(ct))
+ return ERR_PTR(-ENOMEM);
if (!cda[CTA_TIMEOUT])
- goto err;
+ goto err1;
ct->timeout.expires = ntohl(nla_get_be32(cda[CTA_TIMEOUT]));
ct->timeout.expires = jiffies + ct->timeout.expires * HZ;
ct->status |= IPS_CONFIRMED;
+ rcu_read_lock();
+ if (cda[CTA_HELP]) {
+ char *helpname = NULL;
+
+ err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
+ if (err < 0)
+ goto err2;
+
+ helper = __nf_conntrack_helper_find_byname(helpname);
+ if (helper == NULL) {
+ rcu_read_unlock();
+#ifdef CONFIG_MODULES
+ if (request_module("nfct-helper-%s", helpname) < 0) {
+ err = -EOPNOTSUPP;
+ goto err1;
+ }
+
+ rcu_read_lock();
+ helper = __nf_conntrack_helper_find_byname(helpname);
+ if (helper) {
+ err = -EAGAIN;
+ goto err2;
+ }
+ rcu_read_unlock();
+#endif
+ err = -EOPNOTSUPP;
+ goto err1;
+ } else {
+ struct nf_conn_help *help;
+
+ help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+ if (help == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ /* not in hash table yet so not strictly necessary */
+ rcu_assign_pointer(help->helper, helper);
+ }
+ } else {
+ /* try an implicit helper assignation */
+ err = __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
+ if (err < 0)
+ goto err2;
+ }
+
if (cda[CTA_STATUS]) {
err = ctnetlink_change_status(ct, cda);
if (err < 0)
- goto err;
+ goto err2;
+ }
+
+ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
+ err = ctnetlink_change_nat(ct, cda);
+ if (err < 0)
+ goto err2;
}
+#ifdef CONFIG_NF_NAT_NEEDED
+ if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) {
+ err = ctnetlink_change_nat_seq_adj(ct, cda);
+ if (err < 0)
+ goto err2;
+ }
+#endif
+
if (cda[CTA_PROTOINFO]) {
err = ctnetlink_change_protoinfo(ct, cda);
if (err < 0)
- goto err;
+ goto err2;
}
+ nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+
#if defined(CONFIG_NF_CONNTRACK_MARK)
if (cda[CTA_MARK])
ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
#endif
- helper = nf_ct_helper_find_get(rtuple);
- if (helper) {
- help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
- if (help == NULL) {
- nf_ct_helper_put(helper);
- err = -ENOMEM;
- goto err;
- }
- /* not in hash table yet so not strictly necessary */
- rcu_assign_pointer(help->helper, helper);
- }
-
/* setup master conntrack: this is a confirmed expectation */
- if (master_ct) {
+ if (cda[CTA_TUPLE_MASTER]) {
+ struct nf_conntrack_tuple master;
+ struct nf_conntrack_tuple_hash *master_h;
+ struct nf_conn *master_ct;
+
+ err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3);
+ if (err < 0)
+ goto err2;
+
+ master_h = nf_conntrack_find_get(&init_net, &master);
+ if (master_h == NULL) {
+ err = -ENOENT;
+ goto err2;
+ }
+ master_ct = nf_ct_tuplehash_to_ctrack(master_h);
__set_bit(IPS_EXPECTED_BIT, &ct->status);
ct->master = master_ct;
}
add_timer(&ct->timeout);
nf_conntrack_hash_insert(ct);
+ rcu_read_unlock();
- if (helper)
- nf_ct_helper_put(helper);
-
- return 0;
+ return ct;
-err:
+err2:
+ rcu_read_unlock();
+err1:
nf_conntrack_free(ct);
- return err;
+ return ERR_PTR(err);
}
static int
return err;
}
- write_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_lock);
if (cda[CTA_TUPLE_ORIG])
- h = __nf_conntrack_find(&otuple, NULL);
+ h = __nf_conntrack_find(&init_net, &otuple);
else if (cda[CTA_TUPLE_REPLY])
- h = __nf_conntrack_find(&rtuple, NULL);
+ h = __nf_conntrack_find(&init_net, &rtuple);
if (h == NULL) {
- struct nf_conntrack_tuple master;
- struct nf_conntrack_tuple_hash *master_h = NULL;
- struct nf_conn *master_ct = NULL;
-
- if (cda[CTA_TUPLE_MASTER]) {
- err = ctnetlink_parse_tuple(cda,
- &master,
- CTA_TUPLE_MASTER,
- u3);
- if (err < 0)
- return err;
-
- master_h = __nf_conntrack_find(&master, NULL);
- if (master_h == NULL) {
- err = -ENOENT;
+ err = -ENOENT;
+ if (nlh->nlmsg_flags & NLM_F_CREATE) {
+ struct nf_conn *ct;
+ enum ip_conntrack_events events;
+
+ ct = ctnetlink_create_conntrack(cda, &otuple,
+ &rtuple, u3);
+ if (IS_ERR(ct)) {
+ err = PTR_ERR(ct);
goto out_unlock;
}
- master_ct = nf_ct_tuplehash_to_ctrack(master_h);
- atomic_inc(&master_ct->ct_general.use);
- }
-
- write_unlock_bh(&nf_conntrack_lock);
- err = -ENOENT;
- if (nlh->nlmsg_flags & NLM_F_CREATE)
- err = ctnetlink_create_conntrack(cda,
- &otuple,
- &rtuple,
- master_ct);
- if (err < 0 && master_ct)
- nf_ct_put(master_ct);
+ err = 0;
+ nf_conntrack_get(&ct->ct_general);
+ spin_unlock_bh(&nf_conntrack_lock);
+ if (test_bit(IPS_EXPECTED_BIT, &ct->status))
+ events = IPCT_RELATED;
+ else
+ events = IPCT_NEW;
+
+ nf_conntrack_event_report(IPCT_STATUS |
+ IPCT_HELPER |
+ IPCT_PROTOINFO |
+ IPCT_NATSEQADJ |
+ IPCT_MARK | events,
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+ nf_ct_put(ct);
+ } else
+ spin_unlock_bh(&nf_conntrack_lock);
return err;
}
* so there's no need to increase the refcount */
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
- /* we only allow nat config for new conntracks */
- if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
- err = -EINVAL;
- goto out_unlock;
- }
- /* can't link an existing conntrack to a master */
- if (cda[CTA_TUPLE_MASTER]) {
- err = -EINVAL;
- goto out_unlock;
- }
- err = ctnetlink_change_conntrack(nf_ct_tuplehash_to_ctrack(h),
- cda);
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+ err = ctnetlink_change_conntrack(ct, cda);
+ if (err == 0) {
+ nf_conntrack_get(&ct->ct_general);
+ spin_unlock_bh(&nf_conntrack_lock);
+ nf_conntrack_event_report(IPCT_STATUS |
+ IPCT_HELPER |
+ IPCT_PROTOINFO |
+ IPCT_NATSEQADJ |
+ IPCT_MARK,
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+ nf_ct_put(ct);
+ } else
+ spin_unlock_bh(&nf_conntrack_lock);
+
+ return err;
}
out_unlock:
- write_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_lock);
return err;
}
if (!nest_parms)
goto nla_put_failure;
- l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+ l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
ret = ctnetlink_dump_tuples_ip(skb, &m, l3proto);
- nf_ct_l3proto_put(l3proto);
if (unlikely(ret < 0))
goto nla_put_failure;
- l4proto = nf_ct_l4proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+ l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto);
- nf_ct_l4proto_put(l4proto);
if (unlikely(ret < 0))
goto nla_put_failure;
return -1;
}
-static inline int
+static int
ctnetlink_exp_dump_expect(struct sk_buff *skb,
const struct nf_conntrack_expect *exp)
{
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
- struct nf_conntrack_expect *exp = (struct nf_conntrack_expect *)ptr;
+ struct nf_exp_event *item = (struct nf_exp_event *)ptr;
+ struct nf_conntrack_expect *exp = item->exp;
struct sk_buff *skb;
unsigned int type;
sk_buff_data_t b;
} else
return NOTIFY_DONE;
- if (!nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW))
+ if (!item->report &&
+ !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW))
return NOTIFY_DONE;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
if (!skb)
- return NOTIFY_DONE;
+ goto errout;
b = skb->tail;
type |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
- nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg));
+ nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
nfmsg = NLMSG_DATA(nlh);
nlh->nlmsg_flags = flags;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
+ rcu_read_lock();
if (ctnetlink_exp_dump_expect(skb, exp) < 0)
goto nla_put_failure;
+ rcu_read_unlock();
nlh->nlmsg_len = skb->tail - b;
- nfnetlink_send(skb, 0, NFNLGRP_CONNTRACK_EXP_NEW, 0);
+ nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report);
return NOTIFY_DONE;
-nlmsg_failure:
nla_put_failure:
+ rcu_read_unlock();
+nlmsg_failure:
kfree_skb(skb);
+errout:
+ nfnetlink_set_err(0, 0, -ENOBUFS);
return NOTIFY_DONE;
}
#endif
static int
ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct net *net = &init_net;
struct nf_conntrack_expect *exp, *last;
struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
struct hlist_node *n;
u_int8_t l3proto = nfmsg->nfgen_family;
- read_lock_bh(&nf_conntrack_lock);
+ rcu_read_lock();
last = (struct nf_conntrack_expect *)cb->args[1];
for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
restart:
- hlist_for_each_entry(exp, n, &nf_ct_expect_hash[cb->args[0]],
+ hlist_for_each_entry(exp, n, &net->ct.expect_hash[cb->args[0]],
hnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
cb->nlh->nlmsg_seq,
IPCTNL_MSG_EXP_NEW,
1, exp) < 0) {
- atomic_inc(&exp->use);
+ if (!atomic_inc_not_zero(&exp->use))
+ continue;
cb->args[1] = (unsigned long)exp;
goto out;
}
}
}
out:
- read_unlock_bh(&nf_conntrack_lock);
+ rcu_read_unlock();
if (last)
nf_ct_expect_put(last);
if (err < 0)
return err;
- exp = nf_ct_expect_find_get(&tuple);
+ exp = nf_ct_expect_find_get(&init_net, &tuple);
if (!exp)
return -ENOENT;
if (!skb2)
goto out;
+ rcu_read_lock();
err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid,
nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW,
1, exp);
+ rcu_read_unlock();
if (err <= 0)
goto free;
return err;
/* bump usage count to 2 */
- exp = nf_ct_expect_find_get(&tuple);
+ exp = nf_ct_expect_find_get(&init_net, &tuple);
if (!exp)
return -ENOENT;
struct nf_conn_help *m_help;
/* delete all expectations for this helper */
- write_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_lock);
h = __nf_conntrack_helper_find_byname(name);
if (!h) {
- write_unlock_bh(&nf_conntrack_lock);
- return -EINVAL;
+ spin_unlock_bh(&nf_conntrack_lock);
+ return -EOPNOTSUPP;
}
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, n, next,
- &nf_ct_expect_hash[i],
+ &init_net.ct.expect_hash[i],
hnode) {
m_help = nfct_help(exp->master);
if (m_help->helper == h
}
}
}
- write_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_lock);
} else {
/* This basically means we have to flush everything*/
- write_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, n, next,
- &nf_ct_expect_hash[i],
+ &init_net.ct.expect_hash[i],
hnode) {
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
}
}
}
- write_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_lock);
}
return 0;
}
static int
-ctnetlink_create_expect(struct nlattr *cda[], u_int8_t u3)
+ctnetlink_create_expect(struct nlattr *cda[], u_int8_t u3, u32 pid, int report)
{
struct nf_conntrack_tuple tuple, mask, master_tuple;
struct nf_conntrack_tuple_hash *h = NULL;
return err;
/* Look for master conntrack of this expectation */
- h = nf_conntrack_find_get(&master_tuple);
+ h = nf_conntrack_find_get(&init_net, &master_tuple);
if (!h)
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
if (!help || !help->helper) {
/* such conntrack hasn't got any helper, abort */
- err = -EINVAL;
+ err = -EOPNOTSUPP;
goto out;
}
goto out;
}
+ exp->class = 0;
exp->expectfn = NULL;
exp->flags = 0;
exp->master = ct;
memcpy(&exp->mask.src.u3, &mask.src.u3, sizeof(exp->mask.src.u3));
exp->mask.src.u.all = mask.src.u.all;
- err = nf_ct_expect_related(exp);
+ err = nf_ct_expect_related_report(exp, pid, report);
nf_ct_expect_put(exp);
out:
if (err < 0)
return err;
- write_lock_bh(&nf_conntrack_lock);
- exp = __nf_ct_expect_find(&tuple);
+ spin_lock_bh(&nf_conntrack_lock);
+ exp = __nf_ct_expect_find(&init_net, &tuple);
if (!exp) {
- write_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_lock);
err = -ENOENT;
- if (nlh->nlmsg_flags & NLM_F_CREATE)
- err = ctnetlink_create_expect(cda, u3);
+ if (nlh->nlmsg_flags & NLM_F_CREATE) {
+ err = ctnetlink_create_expect(cda,
+ u3,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+ }
return err;
}
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL))
err = ctnetlink_change_expect(exp, cda);
- write_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_lock);
return err;
}