#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/security.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/slab.h>
#include <linux/netfilter.h>
#include <net/netlink.h>
+#include <net/sock.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_protocol.h>
}
static inline int
-ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct)
+ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct)
{
struct nf_conntrack_l4proto *l4proto;
struct nlattr *nest_proto;
#ifdef CONFIG_NF_CONNTRACK_SECMARK
static inline int
-ctnetlink_dump_secmark(struct sk_buff *skb, const struct nf_conn *ct)
+ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
{
- NLA_PUT_BE32(skb, CTA_SECMARK, htonl(ct->secmark));
- return 0;
+ struct nlattr *nest_secctx;
+ int len, ret;
+ char *secctx;
+
+ ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+ if (ret)
+ return 0;
+ ret = -1;
+ nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED);
+ if (!nest_secctx)
+ goto nla_put_failure;
+
+ NLA_PUT_STRING(skb, CTA_SECCTX_NAME, secctx);
+ nla_nest_end(skb, nest_secctx);
+
+ ret = 0;
nla_put_failure:
- return -1;
+ security_release_secctx(secctx, len);
+ return ret;
}
#else
-#define ctnetlink_dump_secmark(a, b) (0)
+#define ctnetlink_dump_secctx(a, b) (0)
#endif
#define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
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 nf_conn *ct)
+ int event, struct nf_conn *ct)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
- unsigned char *b = skb_tail_pointer(skb);
+ unsigned int flags = pid ? NLM_F_MULTI : 0;
event |= NFNL_SUBSYS_CTNETLINK << 8;
- nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
- nfmsg = NLMSG_DATA(nlh);
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
- nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
+ nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = nf_ct_l3num(ct);
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
if (!nest_parms)
goto nla_put_failure;
- if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
if (!nest_parms)
goto nla_put_failure;
- if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
+ if (nf_ct_zone(ct))
+ NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct)));
+
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_protoinfo(skb, ct) < 0 ||
ctnetlink_dump_helpinfo(skb, ct) < 0 ||
ctnetlink_dump_mark(skb, ct) < 0 ||
- ctnetlink_dump_secmark(skb, ct) < 0 ||
+ ctnetlink_dump_secctx(skb, ct) < 0 ||
ctnetlink_dump_id(skb, ct) < 0 ||
ctnetlink_dump_use(skb, ct) < 0 ||
ctnetlink_dump_master(skb, ct) < 0 ||
ctnetlink_dump_nat_seq_adj(skb, ct) < 0)
goto nla_put_failure;
- nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+ nlmsg_end(skb, nlh);
return skb->len;
nlmsg_failure:
nla_put_failure:
- nlmsg_trim(skb, b);
+ nlmsg_cancel(skb, nlh);
return -1;
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
-static int ctnetlink_conntrack_event(struct notifier_block *this,
- unsigned long events, void *ptr)
+static inline size_t
+ctnetlink_proto_size(const struct nf_conn *ct)
+{
+ struct nf_conntrack_l3proto *l3proto;
+ struct nf_conntrack_l4proto *l4proto;
+ size_t len = 0;
+
+ rcu_read_lock();
+ l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
+ len += l3proto->nla_size;
+
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
+ len += l4proto->nla_size;
+ rcu_read_unlock();
+
+ return len;
+}
+
+static inline size_t
+ctnetlink_counters_size(const struct nf_conn *ct)
+{
+ if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT))
+ return 0;
+ return 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */
+ + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */
+ + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */
+ ;
+}
+
+static inline int
+ctnetlink_secctx_size(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+ int len, ret;
+
+ ret = security_secid_to_secctx(ct->secmark, NULL, &len);
+ if (ret)
+ return 0;
+
+ return nla_total_size(0) /* CTA_SECCTX */
+ + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */
+#else
+ return 0;
+#endif
+}
+
+static inline size_t
+ctnetlink_nlmsg_size(const struct nf_conn *ct)
{
+ return NLMSG_ALIGN(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_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
+ + ctnetlink_counters_size(ct)
+ + nla_total_size(sizeof(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 */
+ + ctnetlink_secctx_size(ct)
+#ifdef CONFIG_NF_NAT_NEEDED
+ + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
+#endif
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
+#endif
+ + ctnetlink_proto_size(ct)
+ ;
+}
+
+static int
+ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
+{
+ struct net *net;
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
- 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;
unsigned int flags = 0, group;
+ int err;
/* ignore our fake conntrack entry */
- if (ct == &nf_conntrack_untracked)
- return NOTIFY_DONE;
+ if (nf_ct_is_untracked(ct))
+ return 0;
- if (events & IPCT_DESTROY) {
+ if (events & (1 << IPCT_DESTROY)) {
type = IPCTNL_MSG_CT_DELETE;
group = NFNLGRP_CONNTRACK_DESTROY;
- } else if (events & (IPCT_NEW | IPCT_RELATED)) {
+ } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) {
type = IPCTNL_MSG_CT_NEW;
flags = NLM_F_CREATE|NLM_F_EXCL;
group = NFNLGRP_CONNTRACK_NEW;
- } else if (events & (IPCT_STATUS | IPCT_PROTOINFO)) {
+ } else if (events) {
type = IPCTNL_MSG_CT_NEW;
group = NFNLGRP_CONNTRACK_UPDATE;
} else
- return NOTIFY_DONE;
+ return 0;
- if (!item->report && !nfnetlink_has_listeners(group))
- return NOTIFY_DONE;
+ net = nf_ct_net(ct);
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
- if (!skb)
- return NOTIFY_DONE;
+ /* container deinit, netlink may have died before death_by_timeout */
+ if (!net->nfnl)
+ return 0;
- b = skb->tail;
+ if (!item->report && !nfnetlink_has_listeners(net, group))
+ return 0;
+
+ skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
type |= NFNL_SUBSYS_CTNETLINK << 8;
- nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
- nfmsg = NLMSG_DATA(nlh);
+ nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
- nlh->nlmsg_flags = flags;
+ nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = nf_ct_l3num(ct);
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
if (!nest_parms)
goto nla_put_failure;
- if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
if (!nest_parms)
goto nla_put_failure;
- if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
+ if (nf_ct_zone(ct))
+ NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct)));
+
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 (events & (1 << 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;
if (ctnetlink_dump_timeout(skb, ct) < 0)
goto nla_put_failure;
- if (events & IPCT_PROTOINFO
+ if (events & (1 << IPCT_PROTOINFO)
&& ctnetlink_dump_protoinfo(skb, ct) < 0)
goto nla_put_failure;
- if ((events & IPCT_HELPER || nfct_help(ct))
+ if ((events & (1 << IPCT_HELPER) || nfct_help(ct))
&& ctnetlink_dump_helpinfo(skb, ct) < 0)
goto nla_put_failure;
#ifdef CONFIG_NF_CONNTRACK_SECMARK
- if ((events & IPCT_SECMARK || ct->secmark)
- && ctnetlink_dump_secmark(skb, ct) < 0)
+ if ((events & (1 << IPCT_SECMARK) || ct->secmark)
+ && ctnetlink_dump_secctx(skb, ct) < 0)
goto nla_put_failure;
#endif
- if (events & IPCT_RELATED &&
+ if (events & (1 << IPCT_RELATED) &&
ctnetlink_dump_master(skb, ct) < 0)
goto nla_put_failure;
- if (events & IPCT_NATSEQADJ &&
+ if (events & (1 << IPCT_NATSEQADJ) &&
ctnetlink_dump_nat_seq_adj(skb, ct) < 0)
goto nla_put_failure;
}
#ifdef CONFIG_NF_CONNTRACK_MARK
- if ((events & IPCT_MARK || ct->mark)
+ if ((events & (1 << 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, item->pid, group, item->report);
- return NOTIFY_DONE;
+ nlmsg_end(skb, nlh);
+ err = nfnetlink_send(skb, net, item->pid, group, item->report,
+ GFP_ATOMIC);
+ if (err == -ENOBUFS || err == -EAGAIN)
+ return -ENOBUFS;
+
+ return 0;
nla_put_failure:
rcu_read_unlock();
+ nlmsg_cancel(skb, nlh);
nlmsg_failure:
kfree_skb(skb);
- return NOTIFY_DONE;
+errout:
+ if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0)
+ return -ENOBUFS;
+
+ return 0;
}
#endif /* CONFIG_NF_CONNTRACK_EVENTS */
static int
ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct net *net = sock_net(skb->sk);
struct nf_conn *ct, *last;
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
- struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
+ struct hlist_nulls_node *n;
+ struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
- rcu_read_lock();
+ spin_lock_bh(&nf_conntrack_lock);
last = (struct nf_conn *)cb->args[1];
- for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
+ for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
restart:
- hlist_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]],
- hnode) {
+ hlist_nulls_for_each_entry(h, n, &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 (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
- IPCTNL_MSG_CT_NEW,
- 1, ct) < 0) {
- if (!atomic_inc_not_zero(&ct->ct_general.use))
- continue;
+ IPCTNL_MSG_CT_NEW, ct) < 0) {
+ nf_conntrack_get(&ct->ct_general);
cb->args[1] = (unsigned long)ct;
goto out;
}
}
}
out:
- rcu_read_unlock();
+ spin_unlock_bh(&nf_conntrack_lock);
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 const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = {
+ [CTA_TUPLE_IP] = { .type = NLA_NESTED },
+ [CTA_TUPLE_PROTO] = { .type = NLA_NESTED },
+};
+
static int
-ctnetlink_parse_tuple(struct nlattr *cda[], struct nf_conntrack_tuple *tuple,
+ctnetlink_parse_tuple(const struct nlattr * const cda[],
+ struct nf_conntrack_tuple *tuple,
enum ctattr_tuple type, u_int8_t l3num)
{
struct nlattr *tb[CTA_TUPLE_MAX+1];
memset(tuple, 0, sizeof(*tuple));
- nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], NULL);
+ nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy);
if (!tb[CTA_TUPLE_IP])
return -EINVAL;
return 0;
}
+static int
+ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone)
+{
+ if (attr)
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ *zone = ntohs(nla_get_be16(attr));
+#else
+ return -EOPNOTSUPP;
+#endif
+ else
+ *zone = 0;
+
+ return 0;
+}
+
+static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = {
+ [CTA_HELP_NAME] = { .type = NLA_NUL_STRING },
+};
+
static inline int
-ctnetlink_parse_help(struct nlattr *attr, char **helper_name)
+ctnetlink_parse_help(const struct nlattr *attr, char **helper_name)
{
struct nlattr *tb[CTA_HELP_MAX+1];
- nla_parse_nested(tb, CTA_HELP_MAX, attr, NULL);
+ nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy);
if (!tb[CTA_HELP_NAME])
return -EINVAL;
}
static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
+ [CTA_TUPLE_ORIG] = { .type = NLA_NESTED },
+ [CTA_TUPLE_REPLY] = { .type = NLA_NESTED },
[CTA_STATUS] = { .type = NLA_U32 },
+ [CTA_PROTOINFO] = { .type = NLA_NESTED },
+ [CTA_HELP] = { .type = NLA_NESTED },
+ [CTA_NAT_SRC] = { .type = NLA_NESTED },
[CTA_TIMEOUT] = { .type = NLA_U32 },
[CTA_MARK] = { .type = NLA_U32 },
- [CTA_USE] = { .type = NLA_U32 },
[CTA_ID] = { .type = NLA_U32 },
+ [CTA_NAT_DST] = { .type = NLA_NESTED },
+ [CTA_TUPLE_MASTER] = { .type = NLA_NESTED },
+ [CTA_ZONE] = { .type = NLA_U16 },
};
static int
ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_tuple tuple;
struct nf_conn *ct;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
+
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
if (cda[CTA_TUPLE_ORIG])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3);
else {
/* Flush the whole table */
- nf_conntrack_flush(&init_net,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
+ nf_conntrack_flush_report(net,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
return 0;
}
if (err < 0)
return err;
- h = nf_conntrack_find_get(&init_net, &tuple);
+ h = nf_conntrack_find_get(net, zone, &tuple);
if (!h)
return -ENOENT;
}
}
- nf_conntrack_event_report(IPCT_DESTROY,
- ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
+ if (nf_conntrack_event_report(IPCT_DESTROY, ct,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh)) < 0) {
+ nf_ct_delete_from_lists(ct);
+ /* we failed to report the event, try later */
+ nf_ct_insert_dying_list(ct);
+ nf_ct_put(ct);
+ return 0;
+ }
/* death_by_timeout would report the event again */
set_bit(IPS_DYING_BIT, &ct->status);
static int
ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_tuple tuple;
struct nf_conn *ct;
struct sk_buff *skb2 = NULL;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (nlh->nlmsg_flags & NLM_F_DUMP)
return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table,
ctnetlink_done);
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
+
if (cda[CTA_TUPLE_ORIG])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
else if (cda[CTA_TUPLE_REPLY])
if (err < 0)
return err;
- h = nf_conntrack_find_get(&init_net, &tuple);
+ h = nf_conntrack_find_get(net, zone, &tuple);
if (!h)
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
err = -ENOMEM;
- skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (!skb2) {
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
nf_ct_put(ct);
return -ENOMEM;
}
rcu_read_lock();
err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq,
- IPCTNL_MSG_CT_NEW, 1, ct);
+ IPCTNL_MSG_CT_NEW, ct);
rcu_read_unlock();
nf_ct_put(ct);
if (err <= 0)
free:
kfree_skb(skb2);
out:
- return err;
+ /* this avoids a loop in nfnetlink. */
+ return err == -EAGAIN ? -ENOBUFS : err;
}
#ifdef CONFIG_NF_NAT_NEEDED
static int
ctnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
- struct nlattr *attr)
+ const struct nlattr *attr)
{
typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup;
#endif
static int
-ctnetlink_change_status(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
{
unsigned long d;
unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS]));
}
static int
-ctnetlink_change_nat(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
{
#ifdef CONFIG_NF_NAT_NEEDED
int ret;
}
static inline int
-ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const 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 */
return 0;
}
- helper = __nf_conntrack_helper_find_byname(helpname);
+ helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
+ nf_ct_protonum(ct));
if (helper == NULL) {
#ifdef CONFIG_MODULES
spin_unlock_bh(&nf_conntrack_lock);
}
spin_lock_bh(&nf_conntrack_lock);
- helper = __nf_conntrack_helper_find_byname(helpname);
+ helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
+ nf_ct_protonum(ct));
if (helper)
return -EAGAIN;
#endif
/* need to zero data of old helper */
memset(&help->help, 0, sizeof(help->help));
} else {
- help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
- if (help == NULL)
- return -ENOMEM;
+ /* we cannot set a helper for an existing conntrack */
+ return -EOPNOTSUPP;
}
rcu_assign_pointer(help->helper, helper);
}
static inline int
-ctnetlink_change_timeout(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[])
{
u_int32_t timeout = ntohl(nla_get_be32(cda[CTA_TIMEOUT]));
return 0;
}
+static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = {
+ [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED },
+ [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED },
+ [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED },
+};
+
static inline int
-ctnetlink_change_protoinfo(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[])
{
- struct nlattr *tb[CTA_PROTOINFO_MAX+1], *attr = cda[CTA_PROTOINFO];
+ const struct nlattr *attr = cda[CTA_PROTOINFO];
+ struct nlattr *tb[CTA_PROTOINFO_MAX+1];
struct nf_conntrack_l4proto *l4proto;
int err = 0;
- nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, NULL);
+ nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy);
- l4proto = nf_ct_l4proto_find_get(nf_ct_l3num(ct), nf_ct_protonum(ct));
+ 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;
}
#ifdef CONFIG_NF_NAT_NEEDED
+static const struct nla_policy nat_seq_policy[CTA_NAT_SEQ_MAX+1] = {
+ [CTA_NAT_SEQ_CORRECTION_POS] = { .type = NLA_U32 },
+ [CTA_NAT_SEQ_OFFSET_BEFORE] = { .type = NLA_U32 },
+ [CTA_NAT_SEQ_OFFSET_AFTER] = { .type = NLA_U32 },
+};
+
static inline int
-change_nat_seq_adj(struct nf_nat_seq *natseq, struct nlattr *attr)
+change_nat_seq_adj(struct nf_nat_seq *natseq, const struct nlattr * const attr)
{
struct nlattr *cda[CTA_NAT_SEQ_MAX+1];
- nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, NULL);
+ nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, nat_seq_policy);
if (!cda[CTA_NAT_SEQ_CORRECTION_POS])
return -EINVAL;
}
static int
-ctnetlink_change_nat_seq_adj(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_nat_seq_adj(struct nf_conn *ct,
+ const struct nlattr * const cda[])
{
int ret = 0;
struct nf_conn_nat *nat = nfct_nat(ct);
#endif
static int
-ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *cda[])
+ctnetlink_change_conntrack(struct nf_conn *ct,
+ const struct nlattr * const cda[])
{
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 inline void
-ctnetlink_event_report(struct nf_conn *ct, u32 pid, int report)
-{
- unsigned int events = 0;
-
- if (test_bit(IPS_EXPECTED_BIT, &ct->status))
- events |= IPCT_RELATED;
- else
- events |= IPCT_NEW;
-
- nf_conntrack_event_report(IPCT_STATUS |
- IPCT_HELPER |
- IPCT_REFRESH |
- IPCT_PROTOINFO |
- IPCT_NATSEQADJ |
- IPCT_MARK |
- events,
- ct,
- pid,
- report);
-}
-
-static int
-ctnetlink_create_conntrack(struct nlattr *cda[],
+static struct nf_conn *
+ctnetlink_create_conntrack(struct net *net, u16 zone,
+ const struct nlattr * const cda[],
struct nf_conntrack_tuple *otuple,
struct nf_conntrack_tuple *rtuple,
- u32 pid,
- int report,
u8 u3)
{
struct nf_conn *ct;
int err = -EINVAL;
struct nf_conntrack_helper *helper;
- ct = nf_conntrack_alloc(&init_net, otuple, rtuple, GFP_ATOMIC);
+ ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC);
if (IS_ERR(ct))
- return -ENOMEM;
+ 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;
+ char *helpname = NULL;
err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ if (err < 0)
+ goto err2;
- helper = __nf_conntrack_helper_find_byname(helpname);
+ helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
+ nf_ct_protonum(ct));
if (helper == NULL) {
rcu_read_unlock();
#ifdef CONFIG_MODULES
if (request_module("nfct-helper-%s", helpname) < 0) {
err = -EOPNOTSUPP;
- goto err;
+ goto err1;
}
rcu_read_lock();
- helper = __nf_conntrack_helper_find_byname(helpname);
+ helper = __nf_conntrack_helper_find(helpname,
+ nf_ct_l3num(ct),
+ nf_ct_protonum(ct));
if (helper) {
- rcu_read_unlock();
err = -EAGAIN;
- goto err;
+ goto err2;
}
rcu_read_unlock();
#endif
err = -EOPNOTSUPP;
- goto err;
+ goto err1;
} else {
struct nf_conn_help *help;
help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
if (help == NULL) {
- rcu_read_unlock();
err = -ENOMEM;
- goto err;
+ goto err2;
}
/* not in hash table yet so not strictly necessary */
}
} else {
/* try an implicit helper assignation */
- err = __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
- }
-
- if (cda[CTA_STATUS]) {
- err = ctnetlink_change_status(ct, cda);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
+ if (err < 0)
+ goto err2;
}
if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
err = ctnetlink_change_nat(ct, cda);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ if (err < 0)
+ goto err2;
+ }
+
+ nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+ nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
+ /* we must add conntrack extensions before confirmation. */
+ ct->status |= IPS_CONFIRMED;
+
+ if (cda[CTA_STATUS]) {
+ err = ctnetlink_change_status(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) {
- rcu_read_unlock();
- goto err;
- }
+ if (err < 0)
+ goto err2;
}
#endif
if (cda[CTA_PROTOINFO]) {
err = ctnetlink_change_protoinfo(ct, cda);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ if (err < 0)
+ 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]));
err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3);
if (err < 0)
- goto err;
+ goto err2;
- master_h = __nf_conntrack_find(&init_net, &master);
+ master_h = nf_conntrack_find_get(net, zone, &master);
if (master_h == NULL) {
err = -ENOENT;
- goto err;
+ goto err2;
}
master_ct = nf_ct_tuplehash_to_ctrack(master_h);
- nf_conntrack_get(&master_ct->ct_general);
__set_bit(IPS_EXPECTED_BIT, &ct->status);
ct->master = master_ct;
}
- nf_conntrack_get(&ct->ct_general);
add_timer(&ct->timeout);
nf_conntrack_hash_insert(ct);
rcu_read_unlock();
- ctnetlink_event_report(ct, pid, report);
- nf_ct_put(ct);
- return 0;
+ return ct;
-err:
+err2:
+ rcu_read_unlock();
+err1:
nf_conntrack_free(ct);
- return err;
+ return ERR_PTR(err);
}
static int
ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_tuple otuple, rtuple;
struct nf_conntrack_tuple_hash *h = NULL;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
+
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
if (cda[CTA_TUPLE_ORIG]) {
err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3);
spin_lock_bh(&nf_conntrack_lock);
if (cda[CTA_TUPLE_ORIG])
- h = __nf_conntrack_find(&init_net, &otuple);
+ h = __nf_conntrack_find(net, zone, &otuple);
else if (cda[CTA_TUPLE_REPLY])
- h = __nf_conntrack_find(&init_net, &rtuple);
+ h = __nf_conntrack_find(net, zone, &rtuple);
if (h == NULL) {
err = -ENOENT;
- if (nlh->nlmsg_flags & NLM_F_CREATE)
- err = ctnetlink_create_conntrack(cda,
- &otuple,
- &rtuple,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh),
- u3);
- spin_unlock_bh(&nf_conntrack_lock);
+ if (nlh->nlmsg_flags & NLM_F_CREATE) {
+ struct nf_conn *ct;
+ enum ip_conntrack_events events;
+
+ ct = ctnetlink_create_conntrack(net, zone, cda, &otuple,
+ &rtuple, u3);
+ if (IS_ERR(ct)) {
+ err = PTR_ERR(ct);
+ goto out_unlock;
+ }
+ 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_eventmask_report((1 << IPCT_REPLY) |
+ (1 << IPCT_ASSURED) |
+ (1 << IPCT_HELPER) |
+ (1 << IPCT_PROTOINFO) |
+ (1 << IPCT_NATSEQADJ) |
+ (1 << IPCT_MARK) | events,
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+ nf_ct_put(ct);
+ } else
+ spin_unlock_bh(&nf_conntrack_lock);
+
return err;
}
/* implicit 'else' */
if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
- /* we only allow nat config for new conntracks */
- if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
- /* can't link an existing conntrack to a master */
- if (cda[CTA_TUPLE_MASTER]) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
-
err = ctnetlink_change_conntrack(ct, cda);
if (err == 0) {
nf_conntrack_get(&ct->ct_general);
spin_unlock_bh(&nf_conntrack_lock);
- ctnetlink_event_report(ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
+ nf_conntrack_eventmask_report((1 << IPCT_REPLY) |
+ (1 << IPCT_ASSURED) |
+ (1 << IPCT_HELPER) |
+ (1 << IPCT_PROTOINFO) |
+ (1 << IPCT_NATSEQADJ) |
+ (1 << IPCT_MARK),
+ ct, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
nf_ct_put(ct);
} else
spin_unlock_bh(&nf_conntrack_lock);
struct nlattr *nest_parms;
memset(&m, 0xFF, sizeof(m));
- m.src.u.all = mask->src.u.all;
memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3));
+ m.src.u.all = mask->src.u.all;
+ m.dst.protonum = tuple->dst.protonum;
nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK | NLA_F_NESTED);
if (!nest_parms)
{
struct nf_conn *master = exp->master;
long timeout = (exp->timeout.expires - jiffies) / HZ;
+ struct nf_conn_help *help;
if (timeout < 0)
timeout = 0;
NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout));
NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp));
+ NLA_PUT_BE32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags));
+ help = nfct_help(master);
+ if (help) {
+ struct nf_conntrack_helper *helper;
+
+ helper = rcu_dereference(help->helper);
+ if (helper)
+ NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name);
+ }
return 0;
static int
ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
- int event,
- int nowait,
- const struct nf_conntrack_expect *exp)
+ int event, const struct nf_conntrack_expect *exp)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
- unsigned char *b = skb_tail_pointer(skb);
+ unsigned int flags = pid ? NLM_F_MULTI : 0;
event |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
- nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
- nfmsg = NLMSG_DATA(nlh);
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
- nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
+ nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = exp->tuple.src.l3num;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
if (ctnetlink_exp_dump_expect(skb, exp) < 0)
goto nla_put_failure;
- nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+ nlmsg_end(skb, nlh);
return skb->len;
nlmsg_failure:
nla_put_failure:
- nlmsg_trim(skb, b);
+ nlmsg_cancel(skb, nlh);
return -1;
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
-static int ctnetlink_expect_event(struct notifier_block *this,
- unsigned long events, void *ptr)
+static int
+ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
{
+ struct nf_conntrack_expect *exp = item->exp;
+ struct net *net = nf_ct_exp_net(exp);
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
- 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;
+ unsigned int type, group;
int flags = 0;
- if (events & IPEXP_NEW) {
+ if (events & (1 << IPEXP_DESTROY)) {
+ type = IPCTNL_MSG_EXP_DELETE;
+ group = NFNLGRP_CONNTRACK_EXP_DESTROY;
+ } else if (events & (1 << IPEXP_NEW)) {
type = IPCTNL_MSG_EXP_NEW;
flags = NLM_F_CREATE|NLM_F_EXCL;
+ group = NFNLGRP_CONNTRACK_EXP_NEW;
} else
- return NOTIFY_DONE;
-
- if (!item->report &&
- !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW))
- return NOTIFY_DONE;
+ return 0;
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
- if (!skb)
- return NOTIFY_DONE;
+ if (!item->report && !nfnetlink_has_listeners(net, group))
+ return 0;
- b = skb->tail;
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
type |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
- nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
- nfmsg = NLMSG_DATA(nlh);
+ nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
- nlh->nlmsg_flags = flags;
+ nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = exp->tuple.src.l3num;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
goto nla_put_failure;
rcu_read_unlock();
- nlh->nlmsg_len = skb->tail - b;
- nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report);
- return NOTIFY_DONE;
+ nlmsg_end(skb, nlh);
+ nfnetlink_send(skb, net, item->pid, group, item->report, GFP_ATOMIC);
+ return 0;
nla_put_failure:
rcu_read_unlock();
+ nlmsg_cancel(skb, nlh);
nlmsg_failure:
kfree_skb(skb);
- return NOTIFY_DONE;
+errout:
+ nfnetlink_set_err(net, 0, 0, -ENOBUFS);
+ return 0;
}
#endif
static int ctnetlink_exp_done(struct netlink_callback *cb)
static int
ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = &init_net;
+ struct net *net = sock_net(skb->sk);
struct nf_conntrack_expect *exp, *last;
- struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
struct hlist_node *n;
u_int8_t l3proto = nfmsg->nfgen_family;
continue;
cb->args[1] = 0;
}
- if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).pid,
+ if (ctnetlink_exp_fill_info(skb,
+ NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
IPCTNL_MSG_EXP_NEW,
- 1, exp) < 0) {
+ exp) < 0) {
if (!atomic_inc_not_zero(&exp->use))
continue;
cb->args[1] = (unsigned long)exp;
}
static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
+ [CTA_EXPECT_MASTER] = { .type = NLA_NESTED },
+ [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED },
+ [CTA_EXPECT_MASK] = { .type = NLA_NESTED },
[CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 },
[CTA_EXPECT_ID] = { .type = NLA_U32 },
+ [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING },
+ [CTA_EXPECT_ZONE] = { .type = NLA_U16 },
+ [CTA_EXPECT_FLAGS] = { .type = NLA_U32 },
};
static int
ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_tuple tuple;
struct nf_conntrack_expect *exp;
struct sk_buff *skb2;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
return netlink_dump_start(ctnl, skb, nlh,
ctnetlink_exp_done);
}
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
if (cda[CTA_EXPECT_MASTER])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3);
else
if (err < 0)
return err;
- exp = nf_ct_expect_find_get(&init_net, &tuple);
+ exp = nf_ct_expect_find_get(net, zone, &tuple);
if (!exp)
return -ENOENT;
}
err = -ENOMEM;
- skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (!skb2)
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL)
goto out;
rcu_read_lock();
err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid,
- nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW,
- 1, exp);
+ nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp);
rcu_read_unlock();
if (err <= 0)
goto free;
static int
ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple tuple;
- struct nf_conntrack_helper *h;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct hlist_node *n, *next;
u_int8_t u3 = nfmsg->nfgen_family;
unsigned int i;
+ u16 zone;
int err;
if (cda[CTA_EXPECT_TUPLE]) {
/* delete a single expect by tuple */
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
if (err < 0)
return err;
/* bump usage count to 2 */
- exp = nf_ct_expect_find_get(&init_net, &tuple);
+ exp = nf_ct_expect_find_get(net, zone, &tuple);
if (!exp)
return -ENOENT;
}
/* after list removal, usage count == 1 */
- nf_ct_unexpect_related(exp);
+ spin_lock_bh(&nf_conntrack_lock);
+ if (del_timer(&exp->timeout)) {
+ nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
+ nf_ct_expect_put(exp);
+ }
+ spin_unlock_bh(&nf_conntrack_lock);
/* have to put what we 'get' above.
* after this line usage count == 0 */
nf_ct_expect_put(exp);
/* delete all expectations for this helper */
spin_lock_bh(&nf_conntrack_lock);
- h = __nf_conntrack_helper_find_byname(name);
- if (!h) {
- 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,
- &init_net.ct.expect_hash[i],
+ &net->ct.expect_hash[i],
hnode) {
m_help = nfct_help(exp->master);
- if (m_help->helper == h
- && del_timer(&exp->timeout)) {
- nf_ct_unlink_expect(exp);
+ if (!strcmp(m_help->helper->name, name) &&
+ del_timer(&exp->timeout)) {
+ nf_ct_unlink_expect_report(exp,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
nf_ct_expect_put(exp);
}
}
spin_lock_bh(&nf_conntrack_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, n, next,
- &init_net.ct.expect_hash[i],
+ &net->ct.expect_hash[i],
hnode) {
if (del_timer(&exp->timeout)) {
- nf_ct_unlink_expect(exp);
+ nf_ct_unlink_expect_report(exp,
+ NETLINK_CB(skb).pid,
+ nlmsg_report(nlh));
nf_ct_expect_put(exp);
}
}
return 0;
}
static int
-ctnetlink_change_expect(struct nf_conntrack_expect *x, struct nlattr *cda[])
+ctnetlink_change_expect(struct nf_conntrack_expect *x,
+ const struct nlattr * const cda[])
{
return -EOPNOTSUPP;
}
static int
-ctnetlink_create_expect(struct nlattr *cda[], u_int8_t u3, u32 pid, int report)
+ctnetlink_create_expect(struct net *net, u16 zone,
+ const struct nlattr * const 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(&init_net, &master_tuple);
+ h = nf_conntrack_find_get(net, zone, &master_tuple);
if (!h)
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
- help = nfct_help(ct);
-
- if (!help || !help->helper) {
- /* such conntrack hasn't got any helper, abort */
- err = -EOPNOTSUPP;
- goto out;
- }
-
exp = nf_ct_expect_alloc(ct);
if (!exp) {
err = -ENOMEM;
goto out;
}
+ help = nfct_help(ct);
+ if (!help) {
+ if (!cda[CTA_EXPECT_TIMEOUT]) {
+ err = -EINVAL;
+ goto out;
+ }
+ exp->timeout.expires =
+ jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ;
+ exp->flags = NF_CT_EXPECT_USERSPACE;
+ if (cda[CTA_EXPECT_FLAGS]) {
+ exp->flags |=
+ ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS]));
+ }
+ } else {
+ if (cda[CTA_EXPECT_FLAGS]) {
+ exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS]));
+ exp->flags &= ~NF_CT_EXPECT_USERSPACE;
+ } else
+ exp->flags = 0;
+ }
+
+ exp->class = 0;
exp->expectfn = NULL;
- exp->flags = 0;
exp->master = ct;
exp->helper = NULL;
memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple));
static int
ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
- struct nlmsghdr *nlh, struct nlattr *cda[])
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
{
+ struct net *net = sock_net(ctnl);
struct nf_conntrack_tuple tuple;
struct nf_conntrack_expect *exp;
- struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+ struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (!cda[CTA_EXPECT_TUPLE]
|| !cda[CTA_EXPECT_MASK]
|| !cda[CTA_EXPECT_MASTER])
return -EINVAL;
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
if (err < 0)
return err;
spin_lock_bh(&nf_conntrack_lock);
- exp = __nf_ct_expect_find(&init_net, &tuple);
+ exp = __nf_ct_expect_find(net, zone, &tuple);
if (!exp) {
spin_unlock_bh(&nf_conntrack_lock);
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE) {
- err = ctnetlink_create_expect(cda,
+ err = ctnetlink_create_expect(net, zone, cda,
u3,
NETLINK_CB(skb).pid,
nlmsg_report(nlh));
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
-static struct notifier_block ctnl_notifier = {
- .notifier_call = ctnetlink_conntrack_event,
+static struct nf_ct_event_notifier ctnl_notifier = {
+ .fcn = ctnetlink_conntrack_event,
};
-static struct notifier_block ctnl_notifier_exp = {
- .notifier_call = ctnetlink_expect_event,
+static struct nf_exp_event_notifier ctnl_notifier_exp = {
+ .fcn = ctnetlink_expect_event,
};
#endif
{
int ret;
- printk("ctnetlink v%s: registering with nfnetlink.\n", version);
+ pr_info("ctnetlink v%s: registering with nfnetlink.\n", version);
ret = nfnetlink_subsys_register(&ctnl_subsys);
if (ret < 0) {
- printk("ctnetlink_init: cannot register with nfnetlink.\n");
+ pr_err("ctnetlink_init: cannot register with nfnetlink.\n");
goto err_out;
}
ret = nfnetlink_subsys_register(&ctnl_exp_subsys);
if (ret < 0) {
- printk("ctnetlink_init: cannot register exp with nfnetlink.\n");
+ pr_err("ctnetlink_init: cannot register exp with nfnetlink.\n");
goto err_unreg_subsys;
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
ret = nf_conntrack_register_notifier(&ctnl_notifier);
if (ret < 0) {
- printk("ctnetlink_init: cannot register notifier.\n");
+ pr_err("ctnetlink_init: cannot register notifier.\n");
goto err_unreg_exp_subsys;
}
ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp);
if (ret < 0) {
- printk("ctnetlink_init: cannot expect register notifier.\n");
+ pr_err("ctnetlink_init: cannot expect register notifier.\n");
goto err_unreg_notifier;
}
#endif
static void __exit ctnetlink_exit(void)
{
- printk("ctnetlink: unregistering from nfnetlink.\n");
+ pr_info("ctnetlink: unregistering from nfnetlink.\n");
+ nf_ct_remove_userspace_expectations();
#ifdef CONFIG_NF_CONNTRACK_EVENTS
nf_ct_expect_unregister_notifier(&ctnl_notifier_exp);
nf_conntrack_unregister_notifier(&ctnl_notifier);
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
nfnetlink_subsys_unregister(&ctnl_subsys);
- return;
}
module_init(ctnetlink_init);