This makes use of nf_ct_netns_get/put added in previous patch.
We add get/put functions to nf_conntrack_l3proto structure, ipv4 and ipv6
then implement use-count to track how many users (nft or xtables modules)
have a dependency on ipv4 and/or ipv6 connection tracking functionality.
When count reaches zero, the hooks are unregistered.
The main goal of this patch is to delay activation of connection tracking
inside a namespace until a point in time where such functionality is needed
(which might be "never").
This patch will break some use cases, notably setups that *only* use
ctnetlink (e.g. for flow accouting) without any '-m conntrack' packet
filter rules. The ctnetlink issue is addressed by a later patch in
this series.
Signed-off-by: Florian Westphal <fw@xxxxxxxxx>
---
no changes since v2.
include/net/netfilter/nf_conntrack_l3proto.h | 4 ++
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 55 ++++++++++++++++++++------
net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 54 +++++++++++++++++++------
net/netfilter/nf_conntrack_proto.c | 38 +++++++++++++++++-
4 files changed, 127 insertions(+), 24 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index cdc920b..e0238db 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -52,6 +52,10 @@ struct nf_conntrack_l3proto {
int (*tuple_to_nlattr)(struct sk_buff *skb,
const struct nf_conntrack_tuple *t);
+ /* Called when netns wants to use connection tracking */
+ int (*net_ns_get)(struct net *);
+ void (*net_ns_put)(struct net *);
+
/*
* Calculate size of tuple nlattr
*/
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index e3c46e8..8ed9777 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -31,6 +31,13 @@
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#include <net/netfilter/nf_log.h>
+static int conntrack4_net_id __read_mostly;
+static DEFINE_MUTEX(register_ipv4_hooks);
+
+struct conntrack4_net {
+ unsigned int users;
+};
+
static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
struct nf_conntrack_tuple *tuple)
{
@@ -367,6 +374,38 @@ static int ipv4_init_net(struct net *net)
return 0;
}
+static int ipv4_hooks_register(struct net *net)
+{
+ struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
+ int err = 0;
+
+ mutex_lock(®ister_ipv4_hooks);
+
+ cnet->users++;
+ if (cnet->users > 1)
+ goto out_unlock;
+
+ err = nf_register_net_hooks(net, ipv4_conntrack_ops,
+ ARRAY_SIZE(ipv4_conntrack_ops));
+
+ if (err)
+ cnet->users = 0;
+ out_unlock:
+ mutex_unlock(®ister_ipv4_hooks);
+ return err;
+}
+
+static void ipv4_hooks_unregister(struct net *net)
+{
+ struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
+
+ mutex_lock(®ister_ipv4_hooks);
+ if (--cnet->users == 0)
+ nf_unregister_net_hooks(net, ipv4_conntrack_ops,
+ ARRAY_SIZE(ipv4_conntrack_ops));
+ mutex_unlock(®ister_ipv4_hooks);
+}
+
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
.l3proto = PF_INET,
.name = "ipv4",
@@ -383,6 +422,8 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = {
#if defined(CONFIG_SYSCTL) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT)
.ctl_table_path = "net/ipv4/netfilter",
#endif
+ .net_ns_get = ipv4_hooks_register,
+ .net_ns_put = ipv4_hooks_unregister,
.init_net = ipv4_init_net,
.me = THIS_MODULE,
};
@@ -440,6 +481,8 @@ static void ipv4_net_exit(struct net *net)
static struct pernet_operations ipv4_net_ops = {
.init = ipv4_net_init,
.exit = ipv4_net_exit,
+ .id = &conntrack4_net_id,
+ .size = sizeof(struct conntrack4_net),
};
static int __init nf_conntrack_l3proto_ipv4_init(void)
@@ -461,17 +504,10 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
goto cleanup_sockopt;
}
- ret = nf_register_hooks(ipv4_conntrack_ops,
- ARRAY_SIZE(ipv4_conntrack_ops));
- if (ret < 0) {
- pr_err("nf_conntrack_ipv4: can't register hooks.\n");
- goto cleanup_pernet;
- }
-
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4);
if (ret < 0) {
pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n");
- goto cleanup_hooks;
+ goto cleanup_pernet;
}
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4);
@@ -508,8 +544,6 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
cleanup_tcp4:
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
- cleanup_hooks:
- nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
cleanup_pernet:
unregister_pernet_subsys(&ipv4_net_ops);
cleanup_sockopt:
@@ -527,7 +561,6 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp);
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
- nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
unregister_pernet_subsys(&ipv4_net_ops);
nf_unregister_sockopt(&so_getorigdst);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 1aa5848..92a090f 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -34,6 +34,13 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_log.h>
+static int conntrack6_net_id;
+static DEFINE_MUTEX(register_ipv6_hooks);
+
+struct conntrack6_net {
+ unsigned int users;
+};
+
static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
struct nf_conntrack_tuple *tuple)
{
@@ -308,6 +315,36 @@ static int ipv6_nlattr_tuple_size(void)
}
#endif
+static int ipv6_hooks_register(struct net *net)
+{
+ struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
+ int err = 0;
+
+ mutex_lock(®ister_ipv6_hooks);
+ cnet->users++;
+ if (cnet->users > 1)
+ goto out_unlock;
+
+ err = nf_register_net_hooks(net, ipv6_conntrack_ops,
+ ARRAY_SIZE(ipv6_conntrack_ops));
+ if (err)
+ cnet->users = 0;
+ out_unlock:
+ mutex_unlock(®ister_ipv6_hooks);
+ return err;
+}
+
+static void ipv6_hooks_unregister(struct net *net)
+{
+ struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
+
+ mutex_lock(®ister_ipv6_hooks);
+ if (--cnet->users == 0)
+ nf_unregister_net_hooks(net, ipv6_conntrack_ops,
+ ARRAY_SIZE(ipv6_conntrack_ops));
+ mutex_unlock(®ister_ipv6_hooks);
+}
+
struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.l3proto = PF_INET6,
.name = "ipv6",
@@ -321,6 +358,8 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.nlattr_to_tuple = ipv6_nlattr_to_tuple,
.nla_policy = ipv6_nla_policy,
#endif
+ .net_ns_get = ipv6_hooks_register,
+ .net_ns_put = ipv6_hooks_unregister,
.me = THIS_MODULE,
};
@@ -382,6 +421,8 @@ static void ipv6_net_exit(struct net *net)
static struct pernet_operations ipv6_net_ops = {
.init = ipv6_net_init,
.exit = ipv6_net_exit,
+ .id = &conntrack6_net_id,
+ .size = sizeof(struct conntrack6_net),
};
static int __init nf_conntrack_l3proto_ipv6_init(void)
@@ -401,18 +442,10 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
if (ret < 0)
goto cleanup_sockopt;
- ret = nf_register_hooks(ipv6_conntrack_ops,
- ARRAY_SIZE(ipv6_conntrack_ops));
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register pre-routing defrag "
- "hook.\n");
- goto cleanup_pernet;
- }
-
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6);
if (ret < 0) {
pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n");
- goto cleanup_hooks;
+ goto cleanup_pernet;
}
ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6);
@@ -440,8 +473,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
cleanup_tcp6:
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
- cleanup_hooks:
- nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
cleanup_pernet:
unregister_pernet_subsys(&ipv6_net_ops);
cleanup_sockopt:
@@ -456,7 +487,6 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void)
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
unregister_pernet_subsys(&ipv6_net_ops);
nf_unregister_sockopt(&so_getorigdst6);
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 609c789..1fb11b6 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -127,12 +127,48 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put);
int nf_ct_netns_get(struct net *net, u8 nfproto)
{
- return nf_ct_l3proto_try_module_get(nfproto);
+ const struct nf_conntrack_l3proto *l3proto;
+ int ret;
+
+ might_sleep();
+
+ ret = nf_ct_l3proto_try_module_get(nfproto);
+ if (ret < 0)
+ return ret;
+
+ /* we already have a reference, can't fail */
+ rcu_read_lock();
+ l3proto = __nf_ct_l3proto_find(nfproto);
+ rcu_read_unlock();
+
+ if (!l3proto->net_ns_get)
+ return 0;
+
+ ret = l3proto->net_ns_get(net);
+ if (ret < 0)
+ nf_ct_l3proto_module_put(nfproto);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_netns_get);
void nf_ct_netns_put(struct net *net, u8 nfproto)
{
+ const struct nf_conntrack_l3proto *l3proto;
+
+ might_sleep();
+
+ /* same as nf_conntrack_netns_get(), reference assumed */
+ rcu_read_lock();
+ l3proto = __nf_ct_l3proto_find(nfproto);
+ rcu_read_unlock();
+
+ if (WARN_ON(!l3proto))
+ return;
+
+ if (l3proto->net_ns_put)
+ l3proto->net_ns_put(net);
+
nf_ct_l3proto_module_put(nfproto);
}
EXPORT_SYMBOL_GPL(nf_ct_netns_put);
--
2.4.10
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
