aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c30
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c155
-rw-r--r--net/netfilter/nf_conntrack_core.c39
-rw-r--r--net/netfilter/nf_conntrack_helper.c26
-rw-r--r--net/netfilter/nf_conntrack_netlink.c14
-rw-r--r--net/netfilter/nf_nat_proto_common.c7
-rw-r--r--net/netfilter/nft_dynset.c5
-rw-r--r--net/netfilter/x_tables.c89
-rw-r--r--net/netfilter/xt_CT.c11
-rw-r--r--net/netfilter/xt_IDLETIMER.c9
-rw-r--r--net/netfilter/xt_LED.c12
-rw-r--r--net/netfilter/xt_hashlimit.c11
-rw-r--r--net/netfilter/xt_recent.c6
13 files changed, 282 insertions, 132 deletions
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 2155c2498aed..c5f2350a2b50 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2393,11 +2393,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn));
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
@@ -3092,6 +3088,17 @@ nla_put_failure:
return skb->len;
}
+static bool ip_vs_is_af_valid(int af)
+{
+ if (af == AF_INET)
+ return true;
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6 && ipv6_mod_enabled())
+ return true;
+#endif
+ return false;
+}
+
static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
struct ip_vs_service_user_kern *usvc,
struct nlattr *nla, int full_entry,
@@ -3118,11 +3125,7 @@ static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
memset(usvc, 0, sizeof(*usvc));
usvc->af = nla_get_u16(nla_af);
-#ifdef CONFIG_IP_VS_IPV6
- if (usvc->af != AF_INET && usvc->af != AF_INET6)
-#else
- if (usvc->af != AF_INET)
-#endif
+ if (!ip_vs_is_af_valid(usvc->af))
return -EAFNOSUPPORT;
if (nla_fwmark) {
@@ -3488,12 +3491,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
@@ -3624,6 +3623,11 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
if (udest.af == 0)
udest.af = svc->af;
+ if (!ip_vs_is_af_valid(udest.af)) {
+ ret = -EAFNOSUPPORT;
+ goto out;
+ }
+
if (udest.af != svc->af && cmd != IPVS_CMD_DEL_DEST) {
/* The synchronization protocol is incompatible
* with mixed family services
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 9350530c16c1..5fbf4b232592 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -48,6 +48,7 @@
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
@@ -1359,15 +1360,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1395,19 +1390,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1422,15 +1412,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1442,24 +1427,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
@@ -1492,7 +1471,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1504,9 +1484,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
@@ -1521,7 +1502,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
@@ -1537,19 +1518,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1561,8 +1541,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
@@ -1570,7 +1551,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
@@ -1581,21 +1562,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
@@ -1780,13 +1760,12 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
@@ -1794,6 +1773,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
@@ -1812,7 +1803,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1829,26 +1821,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
@@ -1864,39 +1860,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
} else {
array = kzalloc(count * sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
@@ -1913,20 +1908,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
@@ -1934,13 +1929,23 @@ outtinfo:
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 750b8bf13e60..2039fd7daf4e 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1542,7 +1542,6 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct hlist_nulls_node *n;
- int cpu;
spinlock_t *lockp;
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
@@ -1564,24 +1563,40 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
cond_resched();
}
+ return NULL;
+found:
+ atomic_inc(&ct->ct_general.use);
+ spin_unlock(lockp);
+ local_bh_enable();
+ return ct;
+}
+
+static void
+__nf_ct_unconfirmed_destroy(struct net *net)
+{
+ int cpu;
+
for_each_possible_cpu(cpu) {
- struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+ struct nf_conntrack_tuple_hash *h;
+ struct hlist_nulls_node *n;
+ struct ct_pcpu *pcpu;
+
+ pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
spin_lock_bh(&pcpu->lock);
hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
+ struct nf_conn *ct;
+
ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- set_bit(IPS_DYING_BIT, &ct->status);
+
+ /* we cannot call iter() on unconfirmed list, the
+ * owning cpu can reallocate ct->ext at any time.
+ */
+ set_bit(IPS_DYING_BIT, &ct->status);
}
spin_unlock_bh(&pcpu->lock);
cond_resched();
}
- return NULL;
-found:
- atomic_inc(&ct->ct_general.use);
- spin_unlock(lockp);
- local_bh_enable();
- return ct;
}
void nf_ct_iterate_cleanup(struct net *net,
@@ -1596,6 +1611,10 @@ void nf_ct_iterate_cleanup(struct net *net,
if (atomic_read(&net->ct.count) == 0)
return;
+ __nf_ct_unconfirmed_destroy(net);
+
+ synchronize_net();
+
while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
/* Time to push up daises... */
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 6dc44d9b4190..92e69af41656 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -379,17 +379,33 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
unsigned int h = helper_hash(&me->tuple);
struct nf_conntrack_helper *cur;
- int ret = 0;
+ int ret = 0, i;
BUG_ON(me->expect_policy == NULL);
BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
mutex_lock(&nf_ct_helper_mutex);
- hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
- if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
- ret = -EEXIST;
- goto out;
+ for (i = 0; i < nf_ct_helper_hsize; i++) {
+ hlist_for_each_entry(cur, &nf_ct_helper_hash[i], hnode) {
+ if (!strcmp(cur->name, me->name) &&
+ (cur->tuple.src.l3num == NFPROTO_UNSPEC ||
+ cur->tuple.src.l3num == me->tuple.src.l3num) &&
+ cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+ }
+
+ /* avoid unpredictable behaviour for auto_assign_helper */
+ if (!(me->flags & NF_CT_HELPER_F_USERSPACE)) {
+ hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
+ if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple,
+ &mask)) {
+ ret = -EEXIST;
+ goto out;
+ }
}
}
hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d5caed5bcfb1..9e30fd0ab227 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -890,8 +890,13 @@ restart:
}
out:
local_bh_enable();
- if (last)
+ if (last) {
+ /* nf ct hash resize happened, now clear the leftover. */
+ if ((struct nf_conn *)cb->args[1] == last)
+ cb->args[1] = 0;
+
nf_ct_put(last);
+ }
while (i) {
i--;
@@ -1008,9 +1013,8 @@ static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = {
static int
ctnetlink_parse_tuple(const struct nlattr * const cda[],
- struct nf_conntrack_tuple *tuple,
- enum ctattr_type type, u_int8_t l3num,
- struct nf_conntrack_zone *zone)
+ struct nf_conntrack_tuple *tuple, u32 type,
+ u_int8_t l3num, struct nf_conntrack_zone *zone)
{
struct nlattr *tb[CTA_TUPLE_MAX+1];
int err;
@@ -2409,7 +2413,7 @@ static struct nfnl_ct_hook ctnetlink_glue_hook = {
static int ctnetlink_exp_dump_tuple(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple,
- enum ctattr_expect type)
+ u32 type)
{
struct nlattr *nest_parms;
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index fbce552a796e..7d7466dbf663 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -41,7 +41,7 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
const struct nf_conn *ct,
u16 *rover)
{
- unsigned int range_size, min, i;
+ unsigned int range_size, min, max, i;
__be16 *portptr;
u_int16_t off;
@@ -71,7 +71,10 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
}
} else {
min = ntohs(range->min_proto.all);
- range_size = ntohs(range->max_proto.all) - min + 1;
+ max = ntohs(range->max_proto.all);
+ if (unlikely(max < min))
+ swap(max, min);
+ range_size = max - min + 1;
}
if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 31ca94793aa9..b9dd4e960426 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -82,8 +82,7 @@ static void nft_dynset_eval(const struct nft_expr *expr,
nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
timeout = priv->timeout ? : set->timeout;
*nft_set_ext_expiration(ext) = jiffies + timeout;
- } else if (sexpr == NULL)
- goto out;
+ }
if (sexpr != NULL)
sexpr->ops->eval(sexpr, regs, pkt);
@@ -92,7 +91,7 @@ static void nft_dynset_eval(const struct nft_expr *expr,
regs->verdict.code = NFT_BREAK;
return;
}
-out:
+
if (!priv->invert)
regs->verdict.code = NFT_BREAK;
}
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e47ade305a46..59be89813a29 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -39,6 +39,8 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
+#define XT_PCPU_BLOCK_SIZE 4096
+
struct compat_delta {
unsigned int offset; /* offset in kernel */
int delta; /* delta in 32bit user land */
@@ -365,6 +367,36 @@ textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto)
return buf;
}
+/**
+ * xt_check_proc_name - check that name is suitable for /proc file creation
+ *
+ * @name: file name candidate
+ * @size: length of buffer
+ *
+ * some x_tables modules wish to create a file in /proc.
+ * This function makes sure that the name is suitable for this
+ * purpose, it checks that name is NUL terminated and isn't a 'special'
+ * name, like "..".
+ *
+ * returns negative number on error or 0 if name is useable.
+ */
+int xt_check_proc_name(const char *name, unsigned int size)
+{
+ if (name[0] == '\0')
+ return -EINVAL;
+
+ if (strnlen(name, size) == size)
+ return -ENAMETOOLONG;
+
+ if (strcmp(name, ".") == 0 ||
+ strcmp(name, "..") == 0 ||
+ strchr(name, '/'))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL(xt_check_proc_name);
+
int xt_check_match(struct xt_mtchk_param *par,
unsigned int size, u_int8_t proto, bool inv_proto)
{
@@ -1004,8 +1036,10 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
list_for_each_entry(t, &init_net.xt.tables[af], list) {
if (strcmp(t->name, name))
continue;
- if (!try_module_get(t->me))
+ if (!try_module_get(t->me)) {
+ mutex_unlock(&xt[af].mutex);
return NULL;
+ }
mutex_unlock(&xt[af].mutex);
if (t->table_init(net) != 0) {
@@ -1619,6 +1653,59 @@ void xt_proto_fini(struct net *net, u_int8_t af)
}
EXPORT_SYMBOL_GPL(xt_proto_fini);
+/**
+ * xt_percpu_counter_alloc - allocate x_tables rule counter
+ *
+ * @state: pointer to xt_percpu allocation state
+ * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct
+ *
+ * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then
+ * contain the address of the real (percpu) counter.
+ *
+ * Rule evaluation needs to use xt_get_this_cpu_counter() helper
+ * to fetch the real percpu counter.
+ *
+ * To speed up allocation and improve data locality, a 4kb block is
+ * allocated.
+ *
+ * xt_percpu_counter_alloc_state contains the base address of the
+ * allocated page and the current sub-offset.
+ *
+ * returns false on error.
+ */
+bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state,
+ struct xt_counters *counter)
+{
+ BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2));
+
+ if (nr_cpu_ids <= 1)
+ return true;
+
+ if (!state->mem) {
+ state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE,
+ XT_PCPU_BLOCK_SIZE);
+ if (!state->mem)
+ return false;
+ }
+ counter->pcnt = (__force unsigned long)(state->mem + state->off);
+ state->off += sizeof(*counter);
+ if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) {
+ state->mem = NULL;
+ state->off = 0;
+ }
+ return true;
+}
+EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc);
+
+void xt_percpu_counter_free(struct xt_counters *counters)
+{
+ unsigned long pcnt = counters->pcnt;
+
+ if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0)
+ free_percpu((void __percpu *)pcnt);
+}
+EXPORT_SYMBOL_GPL(xt_percpu_counter_free);
+
static int __net_init xt_net_init(struct net *net)
{
int i;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 6669e68d589e..00ef8243d48d 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -168,8 +168,10 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par,
goto err_put_timeout;
}
timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC);
- if (timeout_ext == NULL)
+ if (!timeout_ext) {
ret = -ENOMEM;
+ goto err_put_timeout;
+ }
rcu_read_unlock();
return ret;
@@ -201,6 +203,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
struct xt_ct_target_info_v1 *info)
{
struct nf_conntrack_zone zone;
+ struct nf_conn_help *help;
struct nf_conn *ct;
int ret = -EOPNOTSUPP;
@@ -249,7 +252,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
if (info->timeout[0]) {
ret = xt_ct_set_timeout(ct, par, info->timeout);
if (ret < 0)
- goto err3;
+ goto err4;
}
__set_bit(IPS_CONFIRMED_BIT, &ct->status);
nf_conntrack_get(&ct->ct_general);
@@ -257,6 +260,10 @@ out:
info->ct = ct;
return 0;
+err4:
+ help = nfct_help(ct);
+ if (help)
+ module_put(help->helper->me);
err3:
nf_ct_tmpl_free(ct);
err2:
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index daf45da448fa..bb5d6a058fb7 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -147,11 +147,11 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
(unsigned long) info->timer);
info->timer->refcnt = 1;
+ INIT_WORK(&info->timer->work, idletimer_tg_work);
+
mod_timer(&info->timer->timer,
msecs_to_jiffies(info->timeout * 1000) + jiffies);
- INIT_WORK(&info->timer->work, idletimer_tg_work);
-
return 0;
out_free_attr:
@@ -192,7 +192,10 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
pr_debug("timeout value is zero\n");
return -EINVAL;
}
-
+ if (info->timeout >= INT_MAX / 1000) {
+ pr_debug("timeout value is too big\n");
+ return -EINVAL;
+ }
if (info->label[0] == '\0' ||
strnlen(info->label,
MAX_IDLETIMER_LABEL_SIZE) == MAX_IDLETIMER_LABEL_SIZE) {
diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c
index 3ba31c194cce..0858fe17e14a 100644
--- a/net/netfilter/xt_LED.c
+++ b/net/netfilter/xt_LED.c
@@ -141,10 +141,11 @@ static int led_tg_check(const struct xt_tgchk_param *par)
goto exit_alloc;
}
- /* See if we need to set up a timer */
- if (ledinfo->delay > 0)
- setup_timer(&ledinternal->timer, led_timeout_callback,
- (unsigned long)ledinternal);
+ /* Since the letinternal timer can be shared between multiple targets,
+ * always set it up, even if the current target does not need it
+ */
+ setup_timer(&ledinternal->timer, led_timeout_callback,
+ (unsigned long)ledinternal);
list_add_tail(&ledinternal->list, &xt_led_triggers);
@@ -181,8 +182,7 @@ static void led_tg_destroy(const struct xt_tgdtor_param *par)
list_del(&ledinternal->list);
- if (ledinfo->delay > 0)
- del_timer_sync(&ledinternal->timer);
+ del_timer_sync(&ledinternal->timer);
led_trigger_unregister(&ledinternal->netfilter_led_trigger);
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index b89b688e9d01..a1a29cdc58fc 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -794,8 +794,9 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par)
struct hashlimit_cfg2 cfg = {};
int ret;
- if (info->name[sizeof(info->name) - 1] != '\0')
- return -EINVAL;
+ ret = xt_check_proc_name(info->name, sizeof(info->name));
+ if (ret)
+ return ret;
ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
@@ -809,9 +810,11 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par)
static int hashlimit_mt_check(const struct xt_mtchk_param *par)
{
struct xt_hashlimit_mtinfo2 *info = par->matchinfo;
+ int ret;
- if (info->name[sizeof(info->name) - 1] != '\0')
- return -EINVAL;
+ ret = xt_check_proc_name(info->name, sizeof(info->name));
+ if (ret)
+ return ret;
return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg,
info->name, 2);
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index e3b7a09b103e..79d7ad621a80 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -361,9 +361,9 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
info->hit_count, XT_RECENT_MAX_NSTAMPS - 1);
return -EINVAL;
}
- if (info->name[0] == '\0' ||
- strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN)
- return -EINVAL;
+ ret = xt_check_proc_name(info->name, sizeof(info->name));
+ if (ret)
+ return ret;
if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot)
nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1;
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-30 15:37:41 +0000