summaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/Kconfig63
-rw-r--r--net/netfilter/Makefile4
-rw-r--r--net/netfilter/core.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c4
-rw-r--r--net/netfilter/nf_conntrack_amanda.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c139
-rw-r--r--net/netfilter/nf_conntrack_expect.c5
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c8
-rw-r--r--net/netfilter/nf_conntrack_helper.c8
-rw-r--r--net/netfilter/nf_conntrack_netbios_ns.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c251
-rw-r--r--net/netfilter/nf_conntrack_pptp.c4
-rw-r--r--net/netfilter/nf_conntrack_proto.c37
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c154
-rw-r--r--net/netfilter/nf_conntrack_proto_generic.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c1
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c10
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c20
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_udplite.c1
-rw-r--r--net/netfilter/nf_conntrack_standalone.c57
-rw-r--r--net/netfilter/nf_log.c201
-rw-r--r--net/netfilter/nf_tproxy_core.c1
-rw-r--r--net/netfilter/nfnetlink.c6
-rw-r--r--net/netfilter/nfnetlink_log.c18
-rw-r--r--net/netfilter/x_tables.c26
-rw-r--r--net/netfilter/xt_HL.c171
-rw-r--r--net/netfilter/xt_LED.c161
-rw-r--r--net/netfilter/xt_cluster.c164
-rw-r--r--net/netfilter/xt_connlimit.c6
-rw-r--r--net/netfilter/xt_hashlimit.c7
-rw-r--r--net/netfilter/xt_hl.c108
-rw-r--r--net/netfilter/xt_limit.c40
-rw-r--r--net/netfilter/xt_physdev.c20
-rw-r--r--net/netfilter/xt_quota.c31
-rw-r--r--net/netfilter/xt_statistic.c28
36 files changed, 1427 insertions, 341 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c2bac9c..2c967e4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -357,6 +357,45 @@ config NETFILTER_XT_TARGET_DSCP
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_TARGET_HL
+ tristate '"HL" hoplimit target support'
+ depends on IP_NF_MANGLE || IP6_NF_MANGLE
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option adds the "HL" (for IPv6) and "TTL" (for IPv4)
+ targets, which enable the user to change the
+ hoplimit/time-to-live value of the IP header.
+
+ While it is safe to decrement the hoplimit/TTL value, the
+ modules also allow to increment and set the hoplimit value of
+ the header to arbitrary values. This is EXTREMELY DANGEROUS
+ since you can easily create immortal packets that loop
+ forever on the network.
+
+config NETFILTER_XT_TARGET_LED
+ tristate '"LED" target support'
+ depends on LEDS_CLASS && LED_TRIGGERS
+ depends on NETFILTER_ADVANCED
+ help
+ This option adds a `LED' target, which allows you to blink LEDs in
+ response to particular packets passing through your machine.
+
+ This can be used to turn a spare LED into a network activity LED,
+ which only flashes in response to FTP transfers, for example. Or
+ you could have an LED which lights up for a minute or two every time
+ somebody connects to your machine via SSH.
+
+ You will need support for the "led" class to make this work.
+
+ To create an LED trigger for incoming SSH traffic:
+ iptables -A INPUT -p tcp --dport 22 -j LED --led-trigger-id ssh --led-delay 1000
+
+ Then attach the new trigger to an LED on your system:
+ echo netfilter-ssh > /sys/class/leds/<ledname>/trigger
+
+ For more information on the LEDs available on your system, see
+ Documentation/leds-class.txt
+
config NETFILTER_XT_TARGET_MARK
tristate '"MARK" target support'
default m if NETFILTER_ADVANCED=n
@@ -488,6 +527,22 @@ config NETFILTER_XT_TARGET_TCPOPTSTRIP
This option adds a "TCPOPTSTRIP" target, which allows you to strip
TCP options from TCP packets.
+config NETFILTER_XT_MATCH_CLUSTER
+ tristate '"cluster" match support'
+ depends on NF_CONNTRACK
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option allows you to build work-load-sharing clusters of
+ network servers/stateful firewalls without having a dedicated
+ load-balancing router/server/switch. Basically, this match returns
+ true when the packet must be handled by this cluster node. Thus,
+ all nodes see all packets and this match decides which node handles
+ what packets. The work-load sharing algorithm is based on source
+ address hashing.
+
+ If you say Y or M here, try `iptables -m cluster --help` for
+ more information.
+
config NETFILTER_XT_MATCH_COMMENT
tristate '"comment" match support'
depends on NETFILTER_ADVANCED
@@ -605,6 +660,14 @@ config NETFILTER_XT_MATCH_HELPER
To compile it as a module, choose M here. If unsure, say Y.
+config NETFILTER_XT_MATCH_HL
+ tristate '"hl" hoplimit/TTL match support'
+ depends on NETFILTER_ADVANCED
+ ---help---
+ HL matching allows you to match packets based on the hoplimit
+ in the IPv6 header, or the time-to-live field in the IPv4
+ header of the packet.
+
config NETFILTER_XT_MATCH_IPRANGE
tristate '"iprange" address range match support'
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index da3d909..6282060 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,8 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
obj-$(CONFIG_NETFILTER_XT_TARGET_MARK) += xt_MARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
@@ -57,6 +59,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP) += xt_TCPOPTSTRIP.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
# matches
+obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
@@ -67,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a90ac83..5bb3473 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -174,7 +174,6 @@ next_hook:
outdev, &elem, okfn, hook_thresh);
if (verdict == NF_ACCEPT || verdict == NF_STOP) {
ret = 1;
- goto unlock;
} else if (verdict == NF_DROP) {
kfree_skb(skb);
ret = -EPERM;
@@ -183,7 +182,6 @@ next_hook:
verdict >> NF_VERDICT_BITS))
goto next_hook;
}
-unlock:
rcu_read_unlock();
return ret;
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 6be5d4e..5c48378 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -149,8 +149,8 @@ static struct task_struct *sync_backup_thread;
/* multicast addr */
static struct sockaddr_in mcast_addr = {
.sin_family = AF_INET,
- .sin_port = __constant_htons(IP_VS_SYNC_PORT),
- .sin_addr.s_addr = __constant_htonl(IP_VS_SYNC_GROUP),
+ .sin_port = cpu_to_be16(IP_VS_SYNC_PORT),
+ .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP),
};
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index 4f8fcf4..07d9d88 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -177,7 +177,7 @@ static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
.me = THIS_MODULE,
.help = amanda_help,
.tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = __constant_htons(10080),
+ .tuple.src.u.udp.port = cpu_to_be16(10080),
.tuple.dst.protonum = IPPROTO_UDP,
.expect_policy = &amanda_exp_policy,
},
@@ -186,7 +186,7 @@ static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
.me = THIS_MODULE,
.help = amanda_help,
.tuple.src.l3num = AF_INET6,
- .tuple.src.u.udp.port = __constant_htons(10080),
+ .tuple.src.u.udp.port = cpu_to_be16(10080),
.tuple.dst.protonum = IPPROTO_UDP,
.expect_policy = &amanda_exp_policy,
},
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f4935e3..8020db6 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -29,6 +29,7 @@
#include <linux/netdevice.h>
#include <linux/socket.h>
#include <linux/mm.h>
+#include <linux/rculist_nulls.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
@@ -54,7 +55,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_lock);
unsigned int nf_conntrack_htable_size __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
-int nf_conntrack_max __read_mostly;
+unsigned int nf_conntrack_max __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_max);
struct nf_conn nf_conntrack_untracked __read_mostly;
@@ -163,8 +164,8 @@ static void
clean_from_lists(struct nf_conn *ct)
{
pr_debug("clean_from_lists(%p)\n", ct);
- hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
- hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);
/* Destroy all pending expectations */
nf_ct_remove_expectations(ct);
@@ -204,8 +205,8 @@ destroy_conntrack(struct nf_conntrack *nfct)
/* We overload first tuple to link into unconfirmed list. */
if (!nf_ct_is_confirmed(ct)) {
- BUG_ON(hlist_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode));
- hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+ BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
}
NF_CT_STAT_INC(net, delete);
@@ -242,18 +243,26 @@ static void death_by_timeout(unsigned long ul_conntrack)
nf_ct_put(ct);
}
+/*
+ * Warning :
+ * - Caller must take a reference on returned object
+ * and recheck nf_ct_tuple_equal(tuple, &h->tuple)
+ * OR
+ * - Caller must lock nf_conntrack_lock before calling this function
+ */
struct nf_conntrack_tuple_hash *
__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int hash = hash_conntrack(tuple);
/* Disable BHs the entire time since we normally need to disable them
* at least once for the stats anyway.
*/
local_bh_disable();
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+begin:
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
if (nf_ct_tuple_equal(tuple, &h->tuple)) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
@@ -261,6 +270,13 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
}
NF_CT_STAT_INC(net, searched);
}
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(n) != hash)
+ goto begin;
local_bh_enable();
return NULL;
@@ -275,11 +291,18 @@ nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple)
struct nf_conn *ct;
rcu_read_lock();
+begin:
h = __nf_conntrack_find(net, tuple);
if (h) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
+ else {
+ if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
+ nf_ct_put(ct);
+ goto begin;
+ }
+ }
}
rcu_read_unlock();
@@ -293,9 +316,9 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
{
struct net *net = nf_ct_net(ct);
- hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.hash[hash]);
- hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
&net->ct.hash[repl_hash]);
}
@@ -318,7 +341,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct nf_conn_help *help;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
enum ip_conntrack_info ctinfo;
struct net *net;
@@ -350,17 +373,17 @@ __nf_conntrack_confirm(struct sk_buff *skb)
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
- hlist_for_each_entry(h, n, &net->ct.hash[hash], hnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
&h->tuple))
goto out;
- hlist_for_each_entry(h, n, &net->ct.hash[repl_hash], hnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple))
goto out;
/* Remove from unconfirmed list */
- hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
__nf_conntrack_hash_insert(ct, hash, repl_hash);
/* Timer relative to confirmation time, not original
@@ -399,14 +422,14 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
{
struct net *net = nf_ct_net(ignored_conntrack);
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int hash = hash_conntrack(tuple);
/* Disable BHs the entire time since we need to disable them at
* least once for the stats anyway.
*/
rcu_read_lock_bh();
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack &&
nf_ct_tuple_equal(tuple, &h->tuple)) {
NF_CT_STAT_INC(net, found);
@@ -430,14 +453,14 @@ static noinline int early_drop(struct net *net, unsigned int hash)
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct = NULL, *tmp;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int i, cnt = 0;
int dropped = 0;
rcu_read_lock();
for (i = 0; i < nf_conntrack_htable_size; i++) {
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash],
- hnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
+ hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
ct = tmp;
@@ -472,7 +495,8 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
struct nf_conn *ct;
if (unlikely(!nf_conntrack_hash_rnd_initted)) {
- get_random_bytes(&nf_conntrack_hash_rnd, 4);
+ get_random_bytes(&nf_conntrack_hash_rnd,
+ sizeof(nf_conntrack_hash_rnd));
nf_conntrack_hash_rnd_initted = 1;
}
@@ -507,26 +531,19 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
#ifdef CONFIG_NET_NS
ct->ct_net = net;
#endif
- INIT_RCU_HEAD(&ct->rcu);
return ct;
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
-static void nf_conntrack_free_rcu(struct rcu_head *head)
+void nf_conntrack_free(struct nf_conn *ct)
{
- struct nf_conn *ct = container_of(head, struct nf_conn, rcu);
struct net *net = nf_ct_net(ct);
+ nf_ct_ext_destroy(ct);
+ atomic_dec(&net->ct.count);
nf_ct_ext_free(ct);
kmem_cache_free(nf_conntrack_cachep, ct);
- atomic_dec(&net->ct.count);
-}
-
-void nf_conntrack_free(struct nf_conn *ct)
-{
- nf_ct_ext_destroy(ct);
- call_rcu(&ct->rcu, nf_conntrack_free_rcu);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
@@ -592,7 +609,7 @@ init_conntrack(struct net *net,
}
/* Overload tuple linked list to put us in unconfirmed list. */
- hlist_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.unconfirmed);
spin_unlock_bh(&nf_conntrack_lock);
@@ -733,6 +750,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
NF_CT_STAT_INC_ATOMIC(net, invalid);
+ if (ret == -NF_DROP)
+ NF_CT_STAT_INC_ATOMIC(net, drop);
return -ret;
}
@@ -902,6 +921,12 @@ int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
return 0;
}
EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple);
+
+int nf_ct_port_nlattr_tuple_size(void)
+{
+ return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
+}
+EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
#endif
/* Used by ipt_REJECT and ip6t_REJECT. */
@@ -930,17 +955,17 @@ 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_node *n;
+ struct hlist_nulls_node *n;
spin_lock_bh(&nf_conntrack_lock);
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
- hlist_for_each_entry(h, n, &net->ct.hash[*bucket], hnode) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
goto found;
}
}
- hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
set_bit(IPS_DYING_BIT, &ct->status);
@@ -988,7 +1013,7 @@ static int kill_all(struct nf_conn *i, void *data)
return 1;
}
-void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, unsigned int size)
+void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
{
if (vmalloced)
vfree(hash);
@@ -1056,26 +1081,28 @@ void nf_conntrack_cleanup(struct net *net)
}
}
-struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced)
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls)
{
- struct hlist_head *hash;
- unsigned int size, i;
+ struct hlist_nulls_head *hash;
+ unsigned int nr_slots, i;
+ size_t sz;
*vmalloced = 0;
- size = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_head));
- hash = (void*)__get_free_pages(GFP_KERNEL|__GFP_NOWARN,
- get_order(sizeof(struct hlist_head)
- * size));
+ BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
+ nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
+ sz = nr_slots * sizeof(struct hlist_nulls_head);
+ hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
+ get_order(sz));
if (!hash) {
*vmalloced = 1;
printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
- hash = vmalloc(sizeof(struct hlist_head) * size);
+ hash = __vmalloc(sz, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
}
- if (hash)
- for (i = 0; i < size; i++)
- INIT_HLIST_HEAD(&hash[i]);
+ if (hash && nulls)
+ for (i = 0; i < nr_slots; i++)
+ INIT_HLIST_NULLS_HEAD(&hash[i], i);
return hash;
}
@@ -1086,7 +1113,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
int i, bucket, vmalloced, old_vmalloced;
unsigned int hashsize, old_size;
int rnd;
- struct hlist_head *hash, *old_hash;
+ struct hlist_nulls_head *hash, *old_hash;
struct nf_conntrack_tuple_hash *h;
/* On boot, we can set this without any fancy locking. */
@@ -1097,13 +1124,13 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
if (!hashsize)
return -EINVAL;
- hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced);
+ hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
if (!hash)
return -ENOMEM;
/* We have to rehahs for the new table anyway, so we also can
* use a newrandom seed */
- get_random_bytes(&rnd, 4);
+ get_random_bytes(&rnd, sizeof(rnd));
/* Lookups in the old hash might happen in parallel, which means we
* might get false negatives during connection lookup. New connections
@@ -1112,12 +1139,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
*/
spin_lock_bh(&nf_conntrack_lock);
for (i = 0; i < nf_conntrack_htable_size; i++) {
- while (!hlist_empty(&init_net.ct.hash[i])) {
- h = hlist_entry(init_net.ct.hash[i].first,
- struct nf_conntrack_tuple_hash, hnode);
- hlist_del_rcu(&h->hnode);
+ while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
+ h = hlist_nulls_entry(init_net.ct.hash[i].first,
+ struct nf_conntrack_tuple_hash, hnnode);
+ hlist_nulls_del_rcu(&h->hnnode);
bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
- hlist_add_head(&h->hnode, &hash[bucket]);
+ hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
old_size = nf_conntrack_htable_size;
@@ -1168,7 +1195,7 @@ static int nf_conntrack_init_init_net(void)
nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
sizeof(struct nf_conn),
- 0, 0, NULL);
+ 0, SLAB_DESTROY_BY_RCU, NULL);
if (!nf_conntrack_cachep) {
printk(KERN_ERR "Unable to create nf_conn slab cache\n");
ret = -ENOMEM;
@@ -1198,7 +1225,7 @@ static int nf_conntrack_init_net(struct net *net)
int ret;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_HEAD(&net->ct.unconfirmed);
+ INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0);
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
if (!net->ct.stat) {
ret = -ENOMEM;
@@ -1208,7 +1235,7 @@ static int nf_conntrack_init_net(struct net *net)
if (ret < 0)
goto err_ecache;
net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size,
- &net->ct.hash_vmalloc);
+ &net->ct.hash_vmalloc, 1);
if (!net->ct.hash) {
ret = -ENOMEM;
printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 3a8a34a..3940f99 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -72,7 +72,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
unsigned int hash;
if (unlikely(!nf_ct_expect_hash_rnd_initted)) {
- get_random_bytes(&nf_ct_expect_hash_rnd, 4);
+ get_random_bytes(&nf_ct_expect_hash_rnd,
+ sizeof(nf_ct_expect_hash_rnd));
nf_ct_expect_hash_rnd_initted = 1;
}
@@ -603,7 +604,7 @@ int nf_conntrack_expect_init(struct net *net)
net->ct.expect_count = 0;
net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize,
- &net->ct.expect_vmalloc);
+ &net->ct.expect_vmalloc, 0);
if (net->ct.expect_hash == NULL)
goto err1;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 687bd63..6636949 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -1167,7 +1167,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
.name = "Q.931",
.me = THIS_MODULE,
.tuple.src.l3num = AF_INET,
- .tuple.src.u.tcp.port = __constant_htons(Q931_PORT),
+ .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT),
.tuple.dst.protonum = IPPROTO_TCP,
.help = q931_help,
.expect_policy = &q931_exp_policy,
@@ -1176,7 +1176,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
.name = "Q.931",
.me = THIS_MODULE,
.tuple.src.l3num = AF_INET6,
- .tuple.src.u.tcp.port = __constant_htons(Q931_PORT),
+ .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT),
.tuple.dst.protonum = IPPROTO_TCP,
.help = q931_help,
.expect_policy = &q931_exp_policy,
@@ -1741,7 +1741,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
.name = "RAS",
.me = THIS_MODULE,
.tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = __constant_htons(RAS_PORT),
+ .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
.help = ras_help,
.expect_policy = &ras_exp_policy,
@@ -1750,7 +1750,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = {
.name = "RAS",
.me = THIS_MODULE,
.tuple.src.l3num = AF_INET6,
- .tuple.src.u.udp.port = __constant_htons(RAS_PORT),
+ .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
.help = ras_help,
.expect_policy = &ras_exp_policy,
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a51bdac..30b8e90 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -142,6 +142,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
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_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
@@ -158,6 +159,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_expect *exp;
const struct hlist_node *n, *next;
+ const struct hlist_nulls_node *nn;
unsigned int i;
/* Get rid of expectations */
@@ -174,10 +176,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
}
/* Get rid of expecteds, set helpers to NULL. */
- hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode)
+ hlist_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode)
unhelp(h, me);
for (i = 0; i < nf_conntrack_htable_size; i++) {
- hlist_for_each_entry(h, n, &net->ct.hash[i], hnode)
+ hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
unhelp(h, me);
}
}
@@ -217,7 +219,7 @@ int nf_conntrack_helper_init(void)
nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize,
- &nf_ct_helper_vmalloc);
+ &nf_ct_helper_vmalloc, 0);
if (!nf_ct_helper_hash)
return -ENOMEM;
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 5af4273..8a3875e 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -105,7 +105,7 @@ static struct nf_conntrack_expect_policy exp_policy = {
static struct nf_conntrack_helper helper __read_mostly = {
.name = "netbios-ns",
.tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = __constant_htons(NMBD_PORT),
+ .tuple.src.u.udp.port = cpu_to_be16(NMBD_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
.me = THIS_MODULE,
.help = help,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index ed6d873..c6439c7 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -19,6 +19,7 @@
#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>
@@ -404,6 +405,78 @@ nla_put_failure:
}
#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)
{
@@ -437,7 +510,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
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;
@@ -518,6 +591,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
nla_put_failure:
rcu_read_unlock();
nlmsg_failure:
+ nfnetlink_set_err(0, group, -ENOBUFS);
kfree_skb(skb);
return NOTIFY_DONE;
}
@@ -535,7 +609,7 @@ 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;
@@ -543,27 +617,27 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
last = (struct nf_conn *)cb->args[1];
for (; cb->args[0] < nf_conntrack_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_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 && nf_ct_l3num(ct) != l3proto)
- continue;
+ 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) {
- if (!atomic_inc_not_zero(&ct->ct_general.use))
- continue;
cb->args[1] = (unsigned long)ct;
goto out;
}
@@ -576,6 +650,8 @@ restart:
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;
@@ -599,7 +675,8 @@ ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple)
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,
@@ -608,7 +685,7 @@ ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple)
ret = l3proto->nlattr_to_tuple(tb, tuple);
}
- nf_ct_l3proto_put(l3proto);
+ rcu_read_unlock();
return ret;
}
@@ -633,7 +710,8 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr,
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,
@@ -642,7 +720,7 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr,
ret = l4proto->nlattr_to_tuple(tb, tuple);
}
- nf_ct_l4proto_put(l4proto);
+ rcu_read_unlock();
return ret;
}
@@ -989,10 +1067,11 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, struct nlattr *cda[])
nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, NULL);
- 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;
}
@@ -1062,6 +1141,10 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *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)
@@ -1124,13 +1207,11 @@ ctnetlink_event_report(struct nf_conn *ct, u32 pid, int report)
report);
}
-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,
- u32 pid,
- int report)
+ u8 u3)
{
struct nf_conn *ct;
int err = -EINVAL;
@@ -1138,10 +1219,10 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
ct = nf_conntrack_alloc(&init_net, 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;
@@ -1152,10 +1233,8 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
char *helpname;
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);
if (helper == NULL) {
@@ -1163,28 +1242,26 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
#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);
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 */
@@ -1193,44 +1270,34 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
} else {
/* try an implicit helper assignation */
err = __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ if (err < 0)
+ goto err2;
}
if (cda[CTA_STATUS]) {
err = ctnetlink_change_status(ct, cda);
- if (err < 0) {
- rcu_read_unlock();
- goto err;
- }
+ 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;
}
#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);
@@ -1241,23 +1308,36 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
#endif
/* 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;
}
- 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
@@ -1289,38 +1369,25 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
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)
- goto out_unlock;
+ err = -ENOENT;
+ if (nlh->nlmsg_flags & NLM_F_CREATE) {
+ struct nf_conn *ct;
- master_h = __nf_conntrack_find(&init_net, &master);
- if (master_h == NULL) {
- err = -ENOENT;
+ 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);
- nf_conntrack_get(&master_ct->ct_general);
- }
-
- err = -ENOENT;
- if (nlh->nlmsg_flags & NLM_F_CREATE)
- err = ctnetlink_create_conntrack(cda,
- &otuple,
- &rtuple,
- master_ct,
- NETLINK_CB(skb).pid,
- nlmsg_report(nlh));
- spin_unlock_bh(&nf_conntrack_lock);
- if (err < 0 && master_ct)
- nf_ct_put(master_ct);
+ 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_ct_put(ct);
+ } else
+ spin_unlock_bh(&nf_conntrack_lock);
return err;
}
@@ -1332,17 +1399,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
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);
@@ -1533,6 +1589,7 @@ static int ctnetlink_expect_event(struct notifier_block *this,
nla_put_failure:
rcu_read_unlock();
nlmsg_failure:
+ nfnetlink_set_err(0, 0, -ENOBUFS);
kfree_skb(skb);
return NOTIFY_DONE;
}
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 9e169ef..3807ac7 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -66,7 +66,7 @@ void
struct nf_conntrack_expect *exp) __read_mostly;
EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn);
-#if defined(DEBUG) || defined(CONFIG_DYNAMIC_PRINTK_DEBUG)
+#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
/* PptpControlMessageType names */
const char *const pptp_msg_name[] = {
"UNKNOWN_MESSAGE",
@@ -591,7 +591,7 @@ static struct nf_conntrack_helper pptp __read_mostly = {
.name = "pptp",
.me = THIS_MODULE,
.tuple.src.l3num = AF_INET,
- .tuple.src.u.tcp.port = __constant_htons(PPTP_CONTROL_PORT),
+ .tuple.src.u.tcp.port = cpu_to_be16(PPTP_CONTROL_PORT),
.tuple.dst.protonum = IPPROTO_TCP,
.help = conntrack_pptp_help,
.destroy = pptp_destroy_siblings,
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 592d733..1a4568b 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -74,27 +74,6 @@ EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find);
/* this is guaranteed to always return a valid protocol helper, since
* it falls back to generic_protocol */
-struct nf_conntrack_l4proto *
-nf_ct_l4proto_find_get(u_int16_t l3proto, u_int8_t l4proto)
-{
- struct nf_conntrack_l4proto *p;
-
- rcu_read_lock();
- p = __nf_ct_l4proto_find(l3proto, l4proto);
- if (!try_module_get(p->me))
- p = &nf_conntrack_l4proto_generic;
- rcu_read_unlock();
-
- return p;
-}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get);
-
-void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p)
-{
- module_put(p->me);
-}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_put);
-
struct nf_conntrack_l3proto *
nf_ct_l3proto_find_get(u_int16_t l3proto)
{
@@ -188,6 +167,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
if (proto->l3proto >= AF_MAX)
return -EBUSY;
+ if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size)
+ return -EINVAL;
+
mutex_lock(&nf_ct_proto_mutex);
if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) {
ret = -EBUSY;
@@ -198,6 +180,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
if (ret < 0)
goto out_unlock;
+ if (proto->nlattr_tuple_size)
+ proto->nla_size = 3 * proto->nlattr_tuple_size();
+
rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto);
out_unlock:
@@ -284,6 +269,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
if (l4proto->l3proto >= PF_MAX)
return -EBUSY;
+ if ((l4proto->to_nlattr && !l4proto->nlattr_size)
+ || (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size))
+ return -EINVAL;
+
mutex_lock(&nf_ct_proto_mutex);
if (!nf_ct_protos[l4proto->l3proto]) {
/* l3proto may be loaded latter. */
@@ -311,6 +300,12 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
if (ret < 0)
goto out_unlock;
+ l4proto->nla_size = 0;
+ if (l4proto->nlattr_size)
+ l4proto->nla_size += l4proto->nlattr_size();
+ if (l4proto->nlattr_tuple_size)
+ l4proto->nla_size += 3 * l4proto->nlattr_tuple_size();
+
rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
l4proto);
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 8fcf176..50dac8db 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -16,6 +16,9 @@
#include <linux/skbuff.h>
#include <linux/dccp.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
#include <linux/netfilter/nfnetlink_conntrack.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
@@ -23,8 +26,6 @@
static DEFINE_RWLOCK(dccp_lock);
-static int nf_ct_dccp_loose __read_mostly = 1;
-
/* Timeouts are based on values from RFC4340:
*
* - REQUEST:
@@ -72,16 +73,6 @@ static int nf_ct_dccp_loose __read_mostly = 1;
#define DCCP_MSL (2 * 60 * HZ)
-static unsigned int dccp_timeout[CT_DCCP_MAX + 1] __read_mostly = {
- [CT_DCCP_REQUEST] = 2 * DCCP_MSL,
- [CT_DCCP_RESPOND] = 4 * DCCP_MSL,
- [CT_DCCP_PARTOPEN] = 4 * DCCP_MSL,
- [CT_DCCP_OPEN] = 12 * 3600 * HZ,
- [CT_DCCP_CLOSEREQ] = 64 * HZ,
- [CT_DCCP_CLOSING] = 64 * HZ,
- [CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL,
-};
-
static const char * const dccp_state_names[] = {
[CT_DCCP_NONE] = "NONE",
[CT_DCCP_REQUEST] = "REQUEST",
@@ -393,6 +384,22 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
},
};
+/* this module per-net specifics */
+static int dccp_net_id;
+struct dccp_net {
+ int dccp_loose;
+ unsigned int dccp_timeout[CT_DCCP_MAX + 1];
+#ifdef CONFIG_SYSCTL
+ struct ctl_table_header *sysctl_header;
+ struct ctl_table *sysctl_table;
+#endif
+};
+
+static inline struct dccp_net *dccp_pernet(struct net *net)
+{
+ return net_generic(net, dccp_net_id);
+}
+
static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
struct nf_conntrack_tuple *tuple)
{
@@ -419,6 +426,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff)
{
struct net *net = nf_ct_net(ct);
+ struct dccp_net *dn;
struct dccp_hdr _dh, *dh;
const char *msg;
u_int8_t state;
@@ -429,7 +437,8 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
switch (state) {
default:
- if (nf_ct_dccp_loose == 0) {
+ dn = dccp_pernet(net);
+ if (dn->dccp_loose == 0) {
msg = "nf_ct_dccp: not picking up existing connection ";
goto out_invalid;
}
@@ -465,6 +474,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
u_int8_t pf, unsigned int hooknum)
{
struct net *net = nf_ct_net(ct);
+ struct dccp_net *dn;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct dccp_hdr _dh, *dh;
u_int8_t type, old_state, new_state;
@@ -542,7 +552,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
ct->proto.dccp.last_pkt = type;
ct->proto.dccp.state = new_state;
write_unlock_bh(&dccp_lock);
- nf_ct_refresh_acct(ct, ctinfo, skb, dccp_timeout[new_state]);
+
+ dn = dccp_pernet(net);
+ nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]);
return NF_ACCEPT;
}
@@ -657,16 +669,20 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
write_unlock_bh(&dccp_lock);
return 0;
}
+
+static int dccp_nlattr_size(void)
+{
+ return nla_total_size(0) /* CTA_PROTOINFO_DCCP */
+ + nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
-static unsigned int dccp_sysctl_table_users;
-static struct ctl_table_header *dccp_sysctl_header;
-static ctl_table dccp_sysctl_table[] = {
+/* template, data assigned later */
+static struct ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_request",
- .data = &dccp_timeout[CT_DCCP_REQUEST],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -674,7 +690,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_respond",
- .data = &dccp_timeout[CT_DCCP_RESPOND],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -682,7 +697,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_partopen",
- .data = &dccp_timeout[CT_DCCP_PARTOPEN],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -690,7 +704,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_open",
- .data = &dccp_timeout[CT_DCCP_OPEN],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -698,7 +711,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_closereq",
- .data = &dccp_timeout[CT_DCCP_CLOSEREQ],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -706,7 +718,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_closing",
- .data = &dccp_timeout[CT_DCCP_CLOSING],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -714,7 +725,6 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_timeout_timewait",
- .data = &dccp_timeout[CT_DCCP_TIMEWAIT],
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -722,8 +732,7 @@ static ctl_table dccp_sysctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "nf_conntrack_dccp_loose",
- .data = &nf_ct_dccp_loose,
- .maxlen = sizeof(nf_ct_dccp_loose),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
@@ -746,16 +755,13 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = {
.print_conntrack = dccp_print_conntrack,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = dccp_to_nlattr,
+ .nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
-#ifdef CONFIG_SYSCTL
- .ctl_table_users = &dccp_sysctl_table_users,
- .ctl_table_header = &dccp_sysctl_header,
- .ctl_table = dccp_sysctl_table,
-#endif
};
static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
@@ -773,37 +779,111 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
.to_nlattr = dccp_to_nlattr,
.from_nlattr = nlattr_to_dccp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
+};
+
+static __net_init int dccp_net_init(struct net *net)
+{
+ struct dccp_net *dn;
+ int err;
+
+ dn = kmalloc(sizeof(*dn), GFP_KERNEL);
+ if (!dn)
+ return -ENOMEM;
+
+ /* default values */
+ dn->dccp_loose = 1;
+ dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL;
+ dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL;
+ dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL;
+ dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ;
+ dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ;
+ dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ;
+ dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL;
+
+ err = net_assign_generic(net, dccp_net_id, dn);
+ if (err)
+ goto out;
+
+#ifdef CONFIG_SYSCTL
+ err = -ENOMEM;
+ dn->sysctl_table = kmemdup(dccp_sysctl_table,
+ sizeof(dccp_sysctl_table), GFP_KERNEL);
+ if (!dn->sysctl_table)
+ goto out;
+
+ dn->sysctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST];
+ dn->sysctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND];
+ dn->sysctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN];
+ dn->sysctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN];
+ dn->sysctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ];
+ dn->sysctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING];
+ dn->sysctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT];
+ dn->sysctl_table[7].data = &dn->dccp_loose;
+
+ dn->sysctl_header = register_net_sysctl_table(net,
+ nf_net_netfilter_sysctl_path, dn->sysctl_table);
+ if (!dn->sysctl_header) {
+ kfree(dn->sysctl_table);
+ goto out;
+ }
+#endif
+
+ return 0;
+
+out:
+ kfree(dn);
+ return err;
+}
+
+static __net_exit void dccp_net_exit(struct net *net)
+{
+ struct dccp_net *dn = dccp_pernet(net);
#ifdef CONFIG_SYSCTL
- .ctl_table_users = &dccp_sysctl_table_users,
- .ctl_table_header = &dccp_sysctl_header,
- .ctl_table = dccp_sysctl_table,
+ unregister_net_sysctl_table(dn->sysctl_header);
+ kfree(dn->sysctl_table);
#endif
+ kfree(dn);
+
+ net_assign_generic(net, dccp_net_id, NULL);
+}
+
+static struct pernet_operations dccp_net_ops = {
+ .init = dccp_net_init,
+ .exit = dccp_net_exit,
};
static int __init nf_conntrack_proto_dccp_init(void)
{
int err;
- err = nf_conntrack_l4proto_register(&dccp_proto4);
+ err = register_pernet_gen_subsys(&dccp_net_id, &dccp_net_ops);
if (err < 0)
goto err1;
- err = nf_conntrack_l4proto_register(&dccp_proto6);
+ err = nf_conntrack_l4proto_register(&dccp_proto4);
if (err < 0)
goto err2;
+
+ err = nf_conntrack_l4proto_register(&dccp_proto6);
+ if (err < 0)
+ goto err3;
return 0;
-err2:
+err3:
nf_conntrack_l4proto_unregister(&dccp_proto4);
+err2:
+ unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops);
err1:
return err;
}
static void __exit nf_conntrack_proto_dccp_fini(void)
{
+ unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops);
nf_conntrack_l4proto_unregister(&dccp_proto6);
nf_conntrack_l4proto_unregister(&dccp_proto4);
}
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 4be80d7..829374f 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -92,7 +92,7 @@ static struct ctl_table generic_compat_sysctl_table[] = {
struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly =
{
.l3proto = PF_UNSPEC,
- .l4proto = 0,
+ .l4proto = 255,
.name = "unknown",
.pkt_to_tuple = generic_pkt_to_tuple,
.invert_tuple = generic_invert_tuple,
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 1b279f9..117b801 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -293,6 +293,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = {
.me = THIS_MODULE,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 74e0379..101b4ad 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -537,6 +537,12 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
return 0;
}
+
+static int sctp_nlattr_size(void)
+{
+ return nla_total_size(0) /* CTA_PROTOINFO_SCTP */
+ + nla_policy_len(sctp_nla_policy, CTA_PROTOINFO_SCTP_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
@@ -668,8 +674,10 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
.me = THIS_MODULE,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = sctp_to_nlattr,
+ .nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
@@ -696,8 +704,10 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
.me = THIS_MODULE,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = sctp_to_nlattr,
+ .nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index f3fd154..b5ccf2b 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -15,6 +15,7 @@
#include <linux/skbuff.h>
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
+#include <asm/unaligned.h>
#include <net/tcp.h>
@@ -25,6 +26,8 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_log.h>
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
/* Protects ct->proto.tcp */
static DEFINE_RWLOCK(tcp_lock);
@@ -466,7 +469,7 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
for (i = 0;
i < (opsize - TCPOLEN_SACK_BASE);
i += TCPOLEN_SACK_PERBLOCK) {
- tmp = ntohl(*((__be32 *)(ptr+i)+1));
+ tmp = get_unaligned_be32((__be32 *)(ptr+i)+1);
if (after(tmp, *sack))
*sack = tmp;
@@ -1181,6 +1184,17 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
return 0;
}
+
+static int tcp_nlattr_size(void)
+{
+ return nla_total_size(0) /* CTA_PROTOINFO_TCP */
+ + nla_policy_len(tcp_nla_policy, CTA_PROTOINFO_TCP_MAX + 1);
+}
+
+static int tcp_nlattr_tuple_size(void)
+{
+ return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
+}
#endif
#ifdef CONFIG_SYSCTL
@@ -1396,9 +1410,11 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
.error = tcp_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = tcp_to_nlattr,
+ .nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = tcp_nlattr_tuple_size,
.nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
@@ -1426,9 +1442,11 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
.error = tcp_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.to_nlattr = tcp_to_nlattr,
+ .nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = tcp_nlattr_tuple_size,
.nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 2b8b1f5..70809d1 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -22,6 +22,8 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_log.h>
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
static unsigned int nf_ct_udp_timeout __read_mostly = 30*HZ;
static unsigned int nf_ct_udp_timeout_stream __read_mostly = 180*HZ;
@@ -193,6 +195,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
@@ -220,6 +223,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly =
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nla_policy = nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 4579d8d..4614696 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -180,6 +180,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly =
.error = udplite_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
+ .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nla_policy = nf_ct_port_nla_policy,
#endif
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 4da54b0..1935153 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -44,40 +44,42 @@ struct ct_iter_state {
unsigned int bucket;
};
-static struct hlist_node *ct_get_first(struct seq_file *seq)
+static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
{
struct net *net = seq_file_net(seq);
struct ct_iter_state *st = seq->private;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
for (st->bucket = 0;
st->bucket < nf_conntrack_htable_size;
st->bucket++) {
n = rcu_dereference(net->ct.hash[st->bucket].first);
- if (n)
+ if (!is_a_nulls(n))
return n;
}
return NULL;
}
-static struct hlist_node *ct_get_next(struct seq_file *seq,
- struct hlist_node *head)
+static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
+ struct hlist_nulls_node *head)
{
struct net *net = seq_file_net(seq);
struct ct_iter_state *st = seq->private;
head = rcu_dereference(head->next);
- while (head == NULL) {
- if (++st->bucket >= nf_conntrack_htable_size)
- return NULL;
+ while (is_a_nulls(head)) {
+ if (likely(get_nulls_value(head) == st->bucket)) {
+ if (++st->bucket >= nf_conntrack_htable_size)
+ return NULL;
+ }
head = rcu_dereference(net->ct.hash[st->bucket].first);
}
return head;
}
-static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos)
+static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
{
- struct hlist_node *head = ct_get_first(seq);
+ struct hlist_nulls_node *head = ct_get_first(seq);
if (head)
while (pos && (head = ct_get_next(seq, head)))
@@ -107,67 +109,74 @@ static void ct_seq_stop(struct seq_file *s, void *v)
/* return 0 on success, 1 in case of error */
static int ct_seq_show(struct seq_file *s, void *v)
{
- const struct nf_conntrack_tuple_hash *hash = v;
- const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
+ struct nf_conntrack_tuple_hash *hash = v;
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
const struct nf_conntrack_l3proto *l3proto;
const struct nf_conntrack_l4proto *l4proto;
+ int ret = 0;
NF_CT_ASSERT(ct);
+ if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ return 0;
/* we only want to print DIR_ORIGINAL */
if (NF_CT_DIRECTION(hash))
- return 0;
+ goto release;
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
NF_CT_ASSERT(l3proto);
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
NF_CT_ASSERT(l4proto);
+ ret = -ENOSPC;
if (seq_printf(s, "%-8s %u %-8s %u %ld ",
l3proto->name, nf_ct_l3num(ct),
l4proto->name, nf_ct_protonum(ct),
timer_pending(&ct->timeout)
? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
- return -ENOSPC;
+ goto release;
if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
- return -ENOSPC;
+ goto release;
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
l3proto, l4proto))
- return -ENOSPC;
+ goto release;
if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
- return -ENOSPC;
+ goto release;
if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
if (seq_printf(s, "[UNREPLIED] "))
- return -ENOSPC;
+ goto release;
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
l3proto, l4proto))
- return -ENOSPC;
+ goto release;
if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
- return -ENOSPC;
+ goto release;
if (test_bit(IPS_ASSURED_BIT, &ct->status))
if (seq_printf(s, "[ASSURED] "))
- return -ENOSPC;
+ goto release;
#if defined(CONFIG_NF_CONNTRACK_MARK)
if (seq_printf(s, "mark=%u ", ct->mark))
- return -ENOSPC;
+ goto release;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
if (seq_printf(s, "secmark=%u ", ct->secmark))
- return -ENOSPC;
+ goto release;
#endif
if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
- return -ENOSPC;
+ goto release;
+ ret = 0;
+release:
+ nf_ct_put(ct);
return 0;
}
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index fa8ae5d..8bb998f 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -14,58 +14,63 @@
LOG target modules */
#define NF_LOG_PREFIXLEN 128
+#define NFLOGGER_NAME_LEN 64
static const struct nf_logger *nf_loggers[NFPROTO_NUMPROTO] __read_mostly;
+static struct list_head nf_loggers_l[NFPROTO_NUMPROTO] __read_mostly;
static DEFINE_MUTEX(nf_log_mutex);
-/* return EBUSY if somebody else is registered, EEXIST if the same logger
- * is registred, 0 on success. */
-int nf_log_register(u_int8_t pf, const struct nf_logger *logger)
+static struct nf_logger *__find_logger(int pf, const char *str_logger)
{
- int ret;
+ struct nf_logger *t;
- if (pf >= ARRAY_SIZE(nf_loggers))
- return -EINVAL;
-
- /* Any setup of logging members must be done before
- * substituting pointer. */
- ret = mutex_lock_interruptible(&nf_log_mutex);
- if (ret < 0)
- return ret;
-
- if (!nf_loggers[pf])
- rcu_assign_pointer(nf_loggers[pf], logger);
- else if (nf_loggers[pf] == logger)
- ret = -EEXIST;
- else
- ret = -EBUSY;
+ list_for_each_entry(t, &nf_loggers_l[pf], list[pf]) {
+ if (!strnicmp(str_logger, t->name, strlen(t->name)))
+ return t;
+ }
- mutex_unlock(&nf_log_mutex);
- return ret;
+ return NULL;
}
-EXPORT_SYMBOL(nf_log_register);
-void nf_log_unregister_pf(u_int8_t pf)
+/* return EEXIST if the same logger is registred, 0 on success. */
+int nf_log_register(u_int8_t pf, struct nf_logger *logger)
{
+ const struct nf_logger *llog;
+
if (pf >= ARRAY_SIZE(nf_loggers))
- return;
+ return -EINVAL;
+
mutex_lock(&nf_log_mutex);
- rcu_assign_pointer(nf_loggers[pf], NULL);
+
+ if (pf == NFPROTO_UNSPEC) {
+ int i;
+ for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
+ list_add_tail(&(logger->list[i]), &(nf_loggers_l[i]));
+ } else {
+ /* register at end of list to honor first register win */
+ list_add_tail(&logger->list[pf], &nf_loggers_l[pf]);
+ llog = rcu_dereference(nf_loggers[pf]);
+ if (llog == NULL)
+ rcu_assign_pointer(nf_loggers[pf], logger);
+ }
+
mutex_unlock(&nf_log_mutex);
- /* Give time to concurrent readers. */
- synchronize_rcu();
+ return 0;
}
-EXPORT_SYMBOL(nf_log_unregister_pf);
+EXPORT_SYMBOL(nf_log_register);
-void nf_log_unregister(const struct nf_logger *logger)
+void nf_log_unregister(struct nf_logger *logger)
{
+ const struct nf_logger *c_logger;
int i;
mutex_lock(&nf_log_mutex);
for (i = 0; i < ARRAY_SIZE(nf_loggers); i++) {
- if (nf_loggers[i] == logger)
+ c_logger = rcu_dereference(nf_loggers[i]);
+ if (c_logger == logger)
rcu_assign_pointer(nf_loggers[i], NULL);
+ list_del(&logger->list[i]);
}
mutex_unlock(&nf_log_mutex);
@@ -73,6 +78,27 @@ void nf_log_unregister(const struct nf_logger *logger)
}
EXPORT_SYMBOL(nf_log_unregister);
+int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger)
+{
+ mutex_lock(&nf_log_mutex);
+ if (__find_logger(pf, logger->name) == NULL) {
+ mutex_unlock(&nf_log_mutex);
+ return -ENOENT;
+ }
+ rcu_assign_pointer(nf_loggers[pf], logger);
+ mutex_unlock(&nf_log_mutex);
+ return 0;
+}
+EXPORT_SYMBOL(nf_log_bind_pf);
+
+void nf_log_unbind_pf(u_int8_t pf)
+{
+ mutex_lock(&nf_log_mutex);
+ rcu_assign_pointer(nf_loggers[pf], NULL);
+ mutex_unlock(&nf_log_mutex);
+}
+EXPORT_SYMBOL(nf_log_unbind_pf);
+
void nf_log_packet(u_int8_t pf,
unsigned int hooknum,
const struct sk_buff *skb,
@@ -129,13 +155,37 @@ static int seq_show(struct seq_file *s, void *v)
{
loff_t *pos = v;
const struct nf_logger *logger;
+ struct nf_logger *t;
+ int ret;
logger = rcu_dereference(nf_loggers[*pos]);
if (!logger)
- return seq_printf(s, "%2lld NONE\n", *pos);
+ ret = seq_printf(s, "%2lld NONE (", *pos);
+ else
+ ret = seq_printf(s, "%2lld %s (", *pos, logger->name);
+
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&nf_log_mutex);
+ list_for_each_entry(t, &nf_loggers_l[*pos], list[*pos]) {
+ ret = seq_printf(s, "%s", t->name);
+ if (ret < 0) {
+ mutex_unlock(&nf_log_mutex);
+ return ret;
+ }
+ if (&t->list[*pos] != nf_loggers_l[*pos].prev) {
+ ret = seq_printf(s, ",");
+ if (ret < 0) {
+ mutex_unlock(&nf_log_mutex);
+ return ret;
+ }
+ }
+ }
+ mutex_unlock(&nf_log_mutex);
- return seq_printf(s, "%2lld %s\n", *pos, logger->name);
+ return seq_printf(s, ")\n");
}
static const struct seq_operations nflog_seq_ops = {
@@ -158,15 +208,102 @@ static const struct file_operations nflog_file_ops = {
.release = seq_release,
};
+
#endif /* PROC_FS */
+#ifdef CONFIG_SYSCTL
+struct ctl_path nf_log_sysctl_path[] = {
+ { .procname = "net", .ctl_name = CTL_NET, },
+ { .procname = "netfilter", .ctl_name = NET_NETFILTER, },
+ { .procname = "nf_log", .ctl_name = CTL_UNNUMBERED, },
+ { }
+};
+
+static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3];
+static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1];
+static struct ctl_table_header *nf_log_dir_header;
+
+static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ const struct nf_logger *logger;
+ int r = 0;
+ int tindex = (unsigned long)table->extra1;
+
+ if (write) {
+ if (!strcmp(buffer, "NONE")) {
+ nf_log_unbind_pf(tindex);
+ return 0;
+ }
+ mutex_lock(&nf_log_mutex);
+ logger = __find_logger(tindex, buffer);
+ if (logger == NULL) {
+ mutex_unlock(&nf_log_mutex);
+ return -ENOENT;
+ }
+ rcu_assign_pointer(nf_loggers[tindex], logger);
+ mutex_unlock(&nf_log_mutex);
+ } else {
+ rcu_read_lock();
+ logger = rcu_dereference(nf_loggers[tindex]);
+ if (!logger)
+ table->data = "NONE";
+ else
+ table->data = logger->name;
+ r = proc_dostring(table, write, filp, buffer, lenp, ppos);
+ rcu_read_unlock();
+ }
+
+ return r;
+}
+
+static __init int netfilter_log_sysctl_init(void)
+{
+ int i;
+
+ for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
+ snprintf(nf_log_sysctl_fnames[i-NFPROTO_UNSPEC], 3, "%d", i);
+ nf_log_sysctl_table[i].ctl_name = CTL_UNNUMBERED;
+ nf_log_sysctl_table[i].procname =
+ nf_log_sysctl_fnames[i-NFPROTO_UNSPEC];
+ nf_log_sysctl_table[i].data = NULL;
+ nf_log_sysctl_table[i].maxlen =
+ NFLOGGER_NAME_LEN * sizeof(char);
+ nf_log_sysctl_table[i].mode = 0644;
+ nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring;
+ nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i;
+ }
+
+ nf_log_dir_header = register_sysctl_paths(nf_log_sysctl_path,
+ nf_log_sysctl_table);
+ if (!nf_log_dir_header)
+ return -ENOMEM;
+
+ return 0;
+}
+#else
+static __init int netfilter_log_sysctl_init(void)
+{
+ return 0;
+}
+#endif /* CONFIG_SYSCTL */
int __init netfilter_log_init(void)
{
+ int i, r;
#ifdef CONFIG_PROC_FS
if (!proc_create("nf_log", S_IRUGO,
proc_net_netfilter, &nflog_file_ops))
return -1;
#endif
+
+ /* Errors will trigger panic, unroll on error is unnecessary. */
+ r = netfilter_log_sysctl_init();
+ if (r < 0)
+ return r;
+
+ for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
+ INIT_LIST_HEAD(&(nf_loggers_l[i]));
+
return 0;
}
diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index cdc97f3..5490fc3 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -71,6 +71,7 @@ int
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
{
if (inet_sk(sk)->transparent) {
+ skb_orphan(skb);
skb->sk = sk;
skb->destructor = nf_tproxy_destructor;
return 1;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 9c0ba17..2785d66 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -113,6 +113,12 @@ int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
}
EXPORT_SYMBOL_GPL(nfnetlink_send);
+void nfnetlink_set_err(u32 pid, u32 group, int error)
+{
+ netlink_set_err(nfnl, pid, group, error);
+}
+EXPORT_SYMBOL_GPL(nfnetlink_set_err);
+
int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags)
{
return netlink_unicast(nfnl, skb, pid, flags);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index c712e9f..fd326ac 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -693,7 +693,7 @@ nfulnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb,
return -ENOTSUPP;
}
-static const struct nf_logger nfulnl_logger = {
+static struct nf_logger nfulnl_logger __read_mostly = {
.name = "nfnetlink_log",
.logfn = &nfulnl_log_packet,
.me = THIS_MODULE,
@@ -725,9 +725,9 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
/* Commands without queue context */
switch (cmd->command) {
case NFULNL_CFG_CMD_PF_BIND:
- return nf_log_register(pf, &nfulnl_logger);
+ return nf_log_bind_pf(pf, &nfulnl_logger);
case NFULNL_CFG_CMD_PF_UNBIND:
- nf_log_unregister_pf(pf);
+ nf_log_unbind_pf(pf);
return 0;
}
}
@@ -952,17 +952,25 @@ static int __init nfnetlink_log_init(void)
goto cleanup_netlink_notifier;
}
+ status = nf_log_register(NFPROTO_UNSPEC, &nfulnl_logger);
+ if (status < 0) {
+ printk(KERN_ERR "log: failed to register logger\n");
+ goto cleanup_subsys;
+ }
+
#ifdef CONFIG_PROC_FS
if (!proc_create("nfnetlink_log", 0440,
proc_net_netfilter, &nful_file_ops))
- goto cleanup_subsys;
+ goto cleanup_logger;
#endif
return status;
#ifdef CONFIG_PROC_FS
+cleanup_logger:
+ nf_log_unregister(&nfulnl_logger);
+#endif
cleanup_subsys:
nfnetlink_subsys_unregister(&nfulnl_subsys);
-#endif
cleanup_netlink_notifier:
netlink_unregister_notifier(&nfulnl_rtnl_notifier);
return status;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 5baccfa..509a956 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -625,6 +625,20 @@ void xt_free_table_info(struct xt_table_info *info)
}
EXPORT_SYMBOL(xt_free_table_info);
+void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo,
+ struct xt_table_info *newinfo)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ void *p = oldinfo->entries[cpu];
+ rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]);
+ newinfo->entries[cpu] = p;
+ }
+
+}
+EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu);
+
/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
const char *name)
@@ -671,21 +685,22 @@ xt_replace_table(struct xt_table *table,
struct xt_table_info *oldinfo, *private;
/* Do the substitution. */
- write_lock_bh(&table->lock);
+ mutex_lock(&table->lock);
private = table->private;
/* Check inside lock: is the old number correct? */
if (num_counters != private->number) {
duprintf("num_counters != table->private->number (%u/%u)\n",
num_counters, private->number);
- write_unlock_bh(&table->lock);
+ mutex_unlock(&table->lock);
*error = -EAGAIN;
return NULL;
}
oldinfo = private;
- table->private = newinfo;
+ rcu_assign_pointer(table->private, newinfo);
newinfo->initial_entries = oldinfo->initial_entries;
- write_unlock_bh(&table->lock);
+ mutex_unlock(&table->lock);
+ synchronize_net();
return oldinfo;
}
EXPORT_SYMBOL_GPL(xt_replace_table);
@@ -719,7 +734,8 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table,
/* Simplifies replace_table code. */
table->private = bootstrap;
- rwlock_init(&table->lock);
+ mutex_init(&table->lock);
+
if (!xt_replace_table(table, 0, newinfo, &ret))
goto unlock;
diff --git a/net/netfilter/xt_HL.c b/net/netfilter/xt_HL.c
new file mode 100644
index 0000000..10e789e
--- /dev/null
+++ b/net/netfilter/xt_HL.c
@@ -0,0 +1,171 @@
+/*
+ * TTL modification target for IP tables
+ * (C) 2000,2005 by Harald Welte <laforge@netfilter.org>
+ *
+ * Hop Limit modification target for ip6tables
+ * Maciej Soltysiak <solt@dns.toxicfilms.tv>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/checksum.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv4/ipt_TTL.h>
+#include <linux/netfilter_ipv6/ip6t_HL.h>
+
+MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
+MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>");
+MODULE_DESCRIPTION("Xtables: Hoplimit/TTL Limit field modification target");
+MODULE_LICENSE("GPL");
+
+static unsigned int
+ttl_tg(struct sk_buff *skb, const struct xt_target_param *par)
+{
+ struct iphdr *iph;
+ const struct ipt_TTL_info *info = par->targinfo;
+ int new_ttl;
+
+ if (!skb_make_writable(skb, skb->len))
+ return NF_DROP;
+
+ iph = ip_hdr(skb);
+
+ switch (info->mode) {
+ case IPT_TTL_SET:
+ new_ttl = info->ttl;
+ break;
+ case IPT_TTL_INC:
+ new_ttl = iph->ttl + info->ttl;
+ if (new_ttl > 255)
+ new_ttl = 255;
+ break;
+ case IPT_TTL_DEC:
+ new_ttl = iph->ttl - info->ttl;
+ if (new_ttl < 0)
+ new_ttl = 0;
+ break;
+ default:
+ new_ttl = iph->ttl;
+ break;
+ }
+
+ if (new_ttl != iph->ttl) {
+ csum_replace2(&iph->check, htons(iph->ttl << 8),
+ htons(new_ttl << 8));
+ iph->ttl = new_ttl;
+ }
+
+ return XT_CONTINUE;
+}
+
+static unsigned int
+hl_tg6(struct sk_buff *skb, const struct xt_target_param *par)
+{
+ struct ipv6hdr *ip6h;
+ const struct ip6t_HL_info *info = par->targinfo;
+ int new_hl;
+
+ if (!skb_make_writable(skb, skb->len))
+ return NF_DROP;
+
+ ip6h = ipv6_hdr(skb);
+
+ switch (info->mode) {
+ case IP6T_HL_SET:
+ new_hl = info->hop_limit;
+ break;
+ case IP6T_HL_INC:
+ new_hl = ip6h->hop_limit + info->hop_limit;
+ if (new_hl > 255)
+ new_hl = 255;
+ break;
+ case IP6T_HL_DEC:
+ new_hl = ip6h->hop_limit - info->hop_limit;
+ if (new_hl < 0)
+ new_hl = 0;
+ break;
+ default:
+ new_hl = ip6h->hop_limit;
+ break;
+ }
+
+ ip6h->hop_limit = new_hl;
+
+ return XT_CONTINUE;
+}
+
+static bool ttl_tg_check(const struct xt_tgchk_param *par)
+{
+ const struct ipt_TTL_info *info = par->targinfo;
+
+ if (info->mode > IPT_TTL_MAXMODE) {
+ printk(KERN_WARNING "ipt_TTL: invalid or unknown Mode %u\n",
+ info->mode);
+ return false;
+ }
+ if (info->mode != IPT_TTL_SET && info->ttl == 0)
+ return false;
+ return true;
+}
+
+static bool hl_tg6_check(const struct xt_tgchk_param *par)
+{
+ const struct ip6t_HL_info *info = par->targinfo;
+
+ if (info->mode > IP6T_HL_MAXMODE) {
+ printk(KERN_WARNING "ip6t_HL: invalid or unknown Mode %u\n",
+ info->mode);
+ return false;
+ }
+ if (info->mode != IP6T_HL_SET && info->hop_limit == 0) {
+ printk(KERN_WARNING "ip6t_HL: increment/decrement doesn't "
+ "make sense with value 0\n");
+ return false;
+ }
+ return true;
+}
+
+static struct xt_target hl_tg_reg[] __read_mostly = {
+ {
+ .name = "TTL",
+ .revision = 0,
+ .family = NFPROTO_IPV4,
+ .target = ttl_tg,
+ .targetsize = sizeof(struct ipt_TTL_info),
+ .table = "mangle",
+ .checkentry = ttl_tg_check,
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "HL",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .target = hl_tg6,
+ .targetsize = sizeof(struct ip6t_HL_info),
+ .table = "mangle",
+ .checkentry = hl_tg6_check,
+ .me = THIS_MODULE,
+ },
+};
+
+static int __init hl_tg_init(void)
+{
+ return xt_register_targets(hl_tg_reg, ARRAY_SIZE(hl_tg_reg));
+}
+
+static void __exit hl_tg_exit(void)
+{
+ xt_unregister_targets(hl_tg_reg, ARRAY_SIZE(hl_tg_reg));
+}
+
+module_init(hl_tg_init);
+module_exit(hl_tg_exit);
+MODULE_ALIAS("ipt_TTL");
+MODULE_ALIAS("ip6t_HL");
diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c
new file mode 100644
index 0000000..8ff7843
--- /dev/null
+++ b/net/netfilter/xt_LED.c
@@ -0,0 +1,161 @@
+/*
+ * xt_LED.c - netfilter target to make LEDs blink upon packet matches
+ *
+ * Copyright (C) 2008 Adam Nielsen <a.nielsen@shikadi.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301 USA.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/leds.h>
+#include <linux/mutex.h>
+
+#include <linux/netfilter/xt_LED.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Adam Nielsen <a.nielsen@shikadi.net>");
+MODULE_DESCRIPTION("Xtables: trigger LED devices on packet match");
+
+/*
+ * This is declared in here (the kernel module) only, to avoid having these
+ * dependencies in userspace code. This is what xt_led_info.internal_data
+ * points to.
+ */
+struct xt_led_info_internal {
+ struct led_trigger netfilter_led_trigger;
+ struct timer_list timer;
+};
+
+static unsigned int
+led_tg(struct sk_buff *skb, const struct xt_target_param *par)
+{
+ const struct xt_led_info *ledinfo = par->targinfo;
+ struct xt_led_info_internal *ledinternal = ledinfo->internal_data;
+
+ /*
+ * If "always blink" is enabled, and there's still some time until the
+ * LED will switch off, briefly switch it off now.
+ */
+ if ((ledinfo->delay > 0) && ledinfo->always_blink &&
+ timer_pending(&ledinternal->timer))
+ led_trigger_event(&ledinternal->netfilter_led_trigger,LED_OFF);
+
+ led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL);
+
+ /* If there's a positive delay, start/update the timer */
+ if (ledinfo->delay > 0) {
+ mod_timer(&ledinternal->timer,
+ jiffies + msecs_to_jiffies(ledinfo->delay));
+
+ /* Otherwise if there was no delay given, blink as fast as possible */
+ } else if (ledinfo->delay == 0) {
+ led_trigger_event(&ledinternal->netfilter_led_trigger, LED_OFF);
+ }
+
+ /* else the delay is negative, which means switch on and stay on */
+
+ return XT_CONTINUE;
+}
+
+static void led_timeout_callback(unsigned long data)
+{
+ struct xt_led_info *ledinfo = (struct xt_led_info *)data;
+ struct xt_led_info_internal *ledinternal = ledinfo->internal_data;
+
+ led_trigger_event(&ledinternal->netfilter_led_trigger, LED_OFF);
+}
+
+static bool led_tg_check(const struct xt_tgchk_param *par)
+{
+ struct xt_led_info *ledinfo = par->targinfo;
+ struct xt_led_info_internal *ledinternal;
+ int err;
+
+ if (ledinfo->id[0] == '\0') {
+ printk(KERN_ERR KBUILD_MODNAME ": No 'id' parameter given.\n");
+ return false;
+ }
+
+ ledinternal = kzalloc(sizeof(struct xt_led_info_internal), GFP_KERNEL);
+ if (!ledinternal) {
+ printk(KERN_CRIT KBUILD_MODNAME ": out of memory\n");
+ return false;
+ }
+
+ ledinternal->netfilter_led_trigger.name = ledinfo->id;
+
+ err = led_trigger_register(&ledinternal->netfilter_led_trigger);
+ if (err) {
+ printk(KERN_CRIT KBUILD_MODNAME
+ ": led_trigger_register() failed\n");
+ if (err == -EEXIST)
+ printk(KERN_ERR KBUILD_MODNAME
+ ": Trigger name is already in use.\n");
+ 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)ledinfo);
+
+ ledinfo->internal_data = ledinternal;
+
+ return true;
+
+exit_alloc:
+ kfree(ledinternal);
+
+ return false;
+}
+
+static void led_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ const struct xt_led_info *ledinfo = par->targinfo;
+ struct xt_led_info_internal *ledinternal = ledinfo->internal_data;
+
+ if (ledinfo->delay > 0)
+ del_timer_sync(&ledinternal->timer);
+
+ led_trigger_unregister(&ledinternal->netfilter_led_trigger);
+ kfree(ledinternal);
+}
+
+static struct xt_target led_tg_reg __read_mostly = {
+ .name = "LED",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .target = led_tg,
+ .targetsize = XT_ALIGN(sizeof(struct xt_led_info)),
+ .checkentry = led_tg_check,
+ .destroy = led_tg_destroy,
+ .me = THIS_MODULE,
+};
+
+static int __init led_tg_init(void)
+{
+ return xt_register_target(&led_tg_reg);
+}
+
+static void __exit led_tg_exit(void)
+{
+ xt_unregister_target(&led_tg_reg);
+}
+
+module_init(led_tg_init);
+module_exit(led_tg_exit);
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
new file mode 100644
index 0000000..ad5bd89
--- /dev/null
+++ b/net/netfilter/xt_cluster.c
@@ -0,0 +1,164 @@
+/*
+ * (C) 2008-2009 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/jhash.h>
+#include <linux/ip.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <linux/netfilter/xt_cluster.h>
+
+static inline u_int32_t nf_ct_orig_ipv4_src(const struct nf_conn *ct)
+{
+ return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
+}
+
+static inline const void *nf_ct_orig_ipv6_src(const struct nf_conn *ct)
+{
+ return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6;
+}
+
+static inline u_int32_t
+xt_cluster_hash_ipv4(u_int32_t ip, const struct xt_cluster_match_info *info)
+{
+ return jhash_1word(ip, info->hash_seed);
+}
+
+static inline u_int32_t
+xt_cluster_hash_ipv6(const void *ip, const struct xt_cluster_match_info *info)
+{
+ return jhash2(ip, NF_CT_TUPLE_L3SIZE / sizeof(__u32), info->hash_seed);
+}
+
+static inline u_int32_t
+xt_cluster_hash(const struct nf_conn *ct,
+ const struct xt_cluster_match_info *info)
+{
+ u_int32_t hash = 0;
+
+ switch(nf_ct_l3num(ct)) {
+ case AF_INET:
+ hash = xt_cluster_hash_ipv4(nf_ct_orig_ipv4_src(ct), info);
+ break;
+ case AF_INET6:
+ hash = xt_cluster_hash_ipv6(nf_ct_orig_ipv6_src(ct), info);
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+ return (((u64)hash * info->total_nodes) >> 32);
+}
+
+static inline bool
+xt_cluster_is_multicast_addr(const struct sk_buff *skb, u_int8_t family)
+{
+ bool is_multicast = false;
+
+ switch(family) {
+ case NFPROTO_IPV4:
+ is_multicast = ipv4_is_multicast(ip_hdr(skb)->daddr);
+ break;
+ case NFPROTO_IPV6:
+ is_multicast = ipv6_addr_type(&ipv6_hdr(skb)->daddr) &
+ IPV6_ADDR_MULTICAST;
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+ return is_multicast;
+}
+
+static bool
+xt_cluster_mt(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+ struct sk_buff *pskb = (struct sk_buff *)skb;
+ const struct xt_cluster_match_info *info = par->matchinfo;
+ const struct nf_conn *ct;
+ enum ip_conntrack_info ctinfo;
+ unsigned long hash;
+
+ /* This match assumes that all nodes see the same packets. This can be
+ * achieved if the switch that connects the cluster nodes support some
+ * sort of 'port mirroring'. However, if your switch does not support
+ * this, your cluster nodes can reply ARP request using a multicast MAC
+ * address. Thus, your switch will flood the same packets to the
+ * cluster nodes with the same multicast MAC address. Using a multicast
+ * link address is a RFC 1812 (section 3.3.2) violation, but this works
+ * fine in practise.
+ *
+ * Unfortunately, if you use the multicast MAC address, the link layer
+ * sets skbuff's pkt_type to PACKET_MULTICAST, which is not accepted
+ * by TCP and others for packets coming to this node. For that reason,
+ * this match mangles skbuff's pkt_type if it detects a packet
+ * addressed to a unicast address but using PACKET_MULTICAST. Yes, I
+ * know, matches should not alter packets, but we are doing this here
+ * because we would need to add a PKTTYPE target for this sole purpose.
+ */
+ if (!xt_cluster_is_multicast_addr(skb, par->family) &&
+ skb->pkt_type == PACKET_MULTICAST) {
+ pskb->pkt_type = PACKET_HOST;
+ }
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct == NULL)
+ return false;
+
+ if (ct == &nf_conntrack_untracked)
+ return false;
+
+ if (ct->master)
+ hash = xt_cluster_hash(ct->master, info);
+ else
+ hash = xt_cluster_hash(ct, info);
+
+ return !!((1 << hash) & info->node_mask) ^
+ !!(info->flags & XT_CLUSTER_F_INV);
+}
+
+static bool xt_cluster_mt_checkentry(const struct xt_mtchk_param *par)
+{
+ struct xt_cluster_match_info *info = par->matchinfo;
+
+ if (info->node_mask >= (1 << info->total_nodes)) {
+ printk(KERN_ERR "xt_cluster: this node mask cannot be "
+ "higher than the total number of nodes\n");
+ return false;
+ }
+ return true;
+}
+
+static struct xt_match xt_cluster_match __read_mostly = {
+ .name = "cluster",
+ .family = NFPROTO_UNSPEC,
+ .match = xt_cluster_mt,
+ .checkentry = xt_cluster_mt_checkentry,
+ .matchsize = sizeof(struct xt_cluster_match_info),
+ .me = THIS_MODULE,
+};
+
+static int __init xt_cluster_mt_init(void)
+{
+ return xt_register_match(&xt_cluster_match);
+}
+
+static void __exit xt_cluster_mt_fini(void)
+{
+ xt_unregister_match(&xt_cluster_match);
+}
+
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: hash-based cluster match");
+MODULE_ALIAS("ipt_cluster");
+MODULE_ALIAS("ip6t_cluster");
+module_init(xt_cluster_mt_init);
+module_exit(xt_cluster_mt_fini);
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 7f404cc..6809809 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -108,7 +108,7 @@ static int count_them(struct xt_connlimit_data *data,
const struct nf_conntrack_tuple_hash *found;
struct xt_connlimit_conn *conn;
struct xt_connlimit_conn *tmp;
- const struct nf_conn *found_ct;
+ struct nf_conn *found_ct;
struct list_head *hash;
bool addit = true;
int matches = 0;
@@ -123,7 +123,7 @@ static int count_them(struct xt_connlimit_data *data,
/* check the saved connections */
list_for_each_entry_safe(conn, tmp, hash, list) {
- found = __nf_conntrack_find(&init_net, &conn->tuple);
+ found = nf_conntrack_find_get(&init_net, &conn->tuple);
found_ct = NULL;
if (found != NULL)
@@ -151,6 +151,7 @@ static int count_them(struct xt_connlimit_data *data,
* we do not care about connections which are
* closed already -> ditch it
*/
+ nf_ct_put(found_ct);
list_del(&conn->list);
kfree(conn);
continue;
@@ -160,6 +161,7 @@ static int count_them(struct xt_connlimit_data *data,
match->family))
/* same source network -> be counted! */
++matches;
+ nf_ct_put(found_ct);
}
rcu_read_unlock();
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index f97fded..a5b5369 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -149,7 +149,7 @@ dsthash_alloc_init(struct xt_hashlimit_htable *ht,
/* initialize hash with random val at the time we allocate
* the first hashtable entry */
if (!ht->rnd_initialized) {
- get_random_bytes(&ht->rnd, 4);
+ get_random_bytes(&ht->rnd, sizeof(ht->rnd));
ht->rnd_initialized = 1;
}
@@ -565,8 +565,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
static bool
hashlimit_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par)
{
- const struct xt_hashlimit_info *r =
- ((const struct xt_hashlimit_info *)par->matchinfo)->u.master;
+ const struct xt_hashlimit_info *r = par->matchinfo;
struct xt_hashlimit_htable *hinfo = r->hinfo;
unsigned long now = jiffies;
struct dsthash_ent *dh;
@@ -702,8 +701,6 @@ static bool hashlimit_mt_check_v0(const struct xt_mtchk_param *par)
}
mutex_unlock(&hlimit_mutex);
- /* Ugly hack: For SMP, we only want to use one set */
- r->u.master = r;
return true;
}
diff --git a/net/netfilter/xt_hl.c b/net/netfilter/xt_hl.c
new file mode 100644
index 0000000..7726154
--- /dev/null
+++ b/net/netfilter/xt_hl.c
@@ -0,0 +1,108 @@
+/*
+ * IP tables module for matching the value of the TTL
+ * (C) 2000,2001 by Harald Welte <laforge@netfilter.org>
+ *
+ * Hop Limit matching module
+ * (C) 2001-2002 Maciej Soltysiak <solt@dns.toxicfilms.tv>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv4/ipt_ttl.h>
+#include <linux/netfilter_ipv6/ip6t_hl.h>
+
+MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>");
+MODULE_DESCRIPTION("Xtables: Hoplimit/TTL field match");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_ttl");
+MODULE_ALIAS("ip6t_hl");
+
+static bool ttl_mt(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+ const struct ipt_ttl_info *info = par->matchinfo;
+ const u8 ttl = ip_hdr(skb)->ttl;
+
+ switch (info->mode) {
+ case IPT_TTL_EQ:
+ return ttl == info->ttl;
+ case IPT_TTL_NE:
+ return ttl != info->ttl;
+ case IPT_TTL_LT:
+ return ttl < info->ttl;
+ case IPT_TTL_GT:
+ return ttl > info->ttl;
+ default:
+ printk(KERN_WARNING "ipt_ttl: unknown mode %d\n",
+ info->mode);
+ return false;
+ }
+
+ return false;
+}
+
+static bool hl_mt6(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+ const struct ip6t_hl_info *info = par->matchinfo;
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+
+ switch (info->mode) {
+ case IP6T_HL_EQ:
+ return ip6h->hop_limit == info->hop_limit;
+ break;
+ case IP6T_HL_NE:
+ return ip6h->hop_limit != info->hop_limit;
+ break;
+ case IP6T_HL_LT:
+ return ip6h->hop_limit < info->hop_limit;
+ break;
+ case IP6T_HL_GT:
+ return ip6h->hop_limit > info->hop_limit;
+ break;
+ default:
+ printk(KERN_WARNING "ip6t_hl: unknown mode %d\n",
+ info->mode);
+ return false;
+ }
+
+ return false;
+}
+
+static struct xt_match hl_mt_reg[] __read_mostly = {
+ {
+ .name = "ttl",
+ .revision = 0,
+ .family = NFPROTO_IPV4,
+ .match = ttl_mt,
+ .matchsize = sizeof(struct ipt_ttl_info),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "hl",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .match = hl_mt6,
+ .matchsize = sizeof(struct ip6t_hl_info),
+ .me = THIS_MODULE,
+ },
+};
+
+static int __init hl_mt_init(void)
+{
+ return xt_register_matches(hl_mt_reg, ARRAY_SIZE(hl_mt_reg));
+}
+
+static void __exit hl_mt_exit(void)
+{
+ xt_unregister_matches(hl_mt_reg, ARRAY_SIZE(hl_mt_reg));
+}
+
+module_init(hl_mt_init);
+module_exit(hl_mt_exit);
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index c908d69..2e8089e 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -14,6 +14,11 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_limit.h>
+struct xt_limit_priv {
+ unsigned long prev;
+ uint32_t credit;
+};
+
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>");
MODULE_DESCRIPTION("Xtables: rate-limit match");
@@ -60,18 +65,18 @@ static DEFINE_SPINLOCK(limit_lock);
static bool
limit_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
- struct xt_rateinfo *r =
- ((const struct xt_rateinfo *)par->matchinfo)->master;
+ const struct xt_rateinfo *r = par->matchinfo;
+ struct xt_limit_priv *priv = r->master;
unsigned long now = jiffies;
spin_lock_bh(&limit_lock);
- r->credit += (now - xchg(&r->prev, now)) * CREDITS_PER_JIFFY;
- if (r->credit > r->credit_cap)
- r->credit = r->credit_cap;
+ priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
+ if (priv->credit > r->credit_cap)
+ priv->credit = r->credit_cap;
- if (r->credit >= r->cost) {
+ if (priv->credit >= r->cost) {
/* We're not limited. */
- r->credit -= r->cost;
+ priv->credit -= r->cost;
spin_unlock_bh(&limit_lock);
return true;
}
@@ -95,6 +100,7 @@ user2credits(u_int32_t user)
static bool limit_mt_check(const struct xt_mtchk_param *par)
{
struct xt_rateinfo *r = par->matchinfo;
+ struct xt_limit_priv *priv;
/* Check for overflow. */
if (r->burst == 0
@@ -104,19 +110,30 @@ static bool limit_mt_check(const struct xt_mtchk_param *par)
return false;
}
- /* For SMP, we only want to use one set of counters. */
- r->master = r;
+ priv = kmalloc(sizeof(*priv), GFP_KERNEL);
+ if (priv == NULL)
+ return -ENOMEM;
+
+ /* For SMP, we only want to use one set of state. */
+ r->master = priv;
if (r->cost == 0) {
/* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies *
128. */
- r->prev = jiffies;
- r->credit = user2credits(r->avg * r->burst); /* Credits full. */
+ priv->prev = jiffies;
+ priv->credit = user2credits(r->avg * r->burst); /* Credits full. */
r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */
r->cost = user2credits(r->avg);
}
return true;
}
+static void limit_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_rateinfo *info = par->matchinfo;
+
+ kfree(info->master);
+}
+
#ifdef CONFIG_COMPAT
struct compat_xt_rateinfo {
u_int32_t avg;
@@ -167,6 +184,7 @@ static struct xt_match limit_mt_reg __read_mostly = {
.family = NFPROTO_UNSPEC,
.match = limit_mt,
.checkentry = limit_mt_check,
+ .destroy = limit_mt_destroy,
.matchsize = sizeof(struct xt_rateinfo),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct compat_xt_rateinfo),
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index 1bcdfc1..8d28ca5 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -20,13 +20,13 @@ MODULE_DESCRIPTION("Xtables: Bridge physical device match");
MODULE_ALIAS("ipt_physdev");
MODULE_ALIAS("ip6t_physdev");
+
static bool
physdev_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
- int i;
- static const char nulldevname[IFNAMSIZ];
+ static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
const struct xt_physdev_info *info = par->matchinfo;
- bool ret;
+ unsigned long ret;
const char *indev, *outdev;
const struct nf_bridge_info *nf_bridge;
@@ -68,11 +68,7 @@ physdev_mt(const struct sk_buff *skb, const struct xt_match_param *par)
if (!(info->bitmask & XT_PHYSDEV_OP_IN))
goto match_outdev;
indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname;
- for (i = 0, ret = false; i < IFNAMSIZ/sizeof(unsigned int); i++) {
- ret |= (((const unsigned int *)indev)[i]
- ^ ((const unsigned int *)info->physindev)[i])
- & ((const unsigned int *)info->in_mask)[i];
- }
+ ret = ifname_compare_aligned(indev, info->physindev, info->in_mask);
if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN))
return false;
@@ -82,13 +78,9 @@ match_outdev:
return true;
outdev = nf_bridge->physoutdev ?
nf_bridge->physoutdev->name : nulldevname;
- for (i = 0, ret = false; i < IFNAMSIZ/sizeof(unsigned int); i++) {
- ret |= (((const unsigned int *)outdev)[i]
- ^ ((const unsigned int *)info->physoutdev)[i])
- & ((const unsigned int *)info->out_mask)[i];
- }
+ ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask);
- return ret ^ !(info->invert & XT_PHYSDEV_OP_OUT);
+ return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT));
}
static bool physdev_mt_check(const struct xt_mtchk_param *par)
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index c84fce5..01dd07b 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -9,6 +9,10 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_quota.h>
+struct xt_quota_priv {
+ uint64_t quota;
+};
+
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Sam Johnston <samj@samj.net>");
MODULE_DESCRIPTION("Xtables: countdown quota match");
@@ -20,18 +24,20 @@ static DEFINE_SPINLOCK(quota_lock);
static bool
quota_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
- struct xt_quota_info *q =
- ((const struct xt_quota_info *)par->matchinfo)->master;
+ struct xt_quota_info *q = (void *)par->matchinfo;
+ struct xt_quota_priv *priv = q->master;
bool ret = q->flags & XT_QUOTA_INVERT;
spin_lock_bh(&quota_lock);
- if (q->quota >= skb->len) {
- q->quota -= skb->len;
+ if (priv->quota >= skb->len) {
+ priv->quota -= skb->len;
ret = !ret;
} else {
/* we do not allow even small packets from now on */
- q->quota = 0;
+ priv->quota = 0;
}
+ /* Copy quota back to matchinfo so that iptables can display it */
+ q->quota = priv->quota;
spin_unlock_bh(&quota_lock);
return ret;
@@ -43,17 +49,28 @@ static bool quota_mt_check(const struct xt_mtchk_param *par)
if (q->flags & ~XT_QUOTA_MASK)
return false;
- /* For SMP, we only want to use one set of counters. */
- q->master = q;
+
+ q->master = kmalloc(sizeof(*q->master), GFP_KERNEL);
+ if (q->master == NULL)
+ return -ENOMEM;
+
return true;
}
+static void quota_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_quota_info *q = par->matchinfo;
+
+ kfree(q->master);
+}
+
static struct xt_match quota_mt_reg __read_mostly = {
.name = "quota",
.revision = 0,
.family = NFPROTO_UNSPEC,
.match = quota_mt,
.checkentry = quota_mt_check,
+ .destroy = quota_mt_destroy,
.matchsize = sizeof(struct xt_quota_info),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c
index 0d75141..d8c0f8f 100644
--- a/net/netfilter/xt_statistic.c
+++ b/net/netfilter/xt_statistic.c
@@ -16,6 +16,10 @@
#include <linux/netfilter/xt_statistic.h>
#include <linux/netfilter/x_tables.h>
+struct xt_statistic_priv {
+ uint32_t count;
+};
+
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("Xtables: statistics-based matching (\"Nth\", random)");
@@ -27,7 +31,7 @@ static DEFINE_SPINLOCK(nth_lock);
static bool
statistic_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
- struct xt_statistic_info *info = (void *)par->matchinfo;
+ const struct xt_statistic_info *info = par->matchinfo;
bool ret = info->flags & XT_STATISTIC_INVERT;
switch (info->mode) {
@@ -36,10 +40,9 @@ statistic_mt(const struct sk_buff *skb, const struct xt_match_param *par)
ret = !ret;
break;
case XT_STATISTIC_MODE_NTH:
- info = info->master;
spin_lock_bh(&nth_lock);
- if (info->u.nth.count++ == info->u.nth.every) {
- info->u.nth.count = 0;
+ if (info->master->count++ == info->u.nth.every) {
+ info->master->count = 0;
ret = !ret;
}
spin_unlock_bh(&nth_lock);
@@ -56,16 +59,31 @@ static bool statistic_mt_check(const struct xt_mtchk_param *par)
if (info->mode > XT_STATISTIC_MODE_MAX ||
info->flags & ~XT_STATISTIC_MASK)
return false;
- info->master = info;
+
+ info->master = kzalloc(sizeof(*info->master), GFP_KERNEL);
+ if (info->master == NULL) {
+ printk(KERN_ERR KBUILD_MODNAME ": Out of memory\n");
+ return false;
+ }
+ info->master->count = info->u.nth.count;
+
return true;
}
+static void statistic_mt_destroy(const struct xt_mtdtor_param *par)
+{
+ const struct xt_statistic_info *info = par->matchinfo;
+
+ kfree(info->master);
+}
+
static struct xt_match xt_statistic_mt_reg __read_mostly = {
.name = "statistic",
.revision = 0,
.family = NFPROTO_UNSPEC,
.match = statistic_mt,
.checkentry = statistic_mt_check,
+ .destroy = statistic_mt_destroy,
.matchsize = sizeof(struct xt_statistic_info),
.me = THIS_MODULE,
};