* [PATCH v3 nf-next 01/12] netfilter: add and use nf_ct_netns_get/put
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 02/12] netfilter: conntrack: register hooks in netns when needed by ruleset Florian Westphal
` (11 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
currently aliased to try_module_get/_put.
Will be changed in next patch when we add functions to make use of ->net
argument to store usercount per l3proto tracker.
This is needed to avoid registering the conntrack hooks in all netns and
later only enable connection tracking in those that need conntrack.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
No changes since v2.
Changes since v1 were:
- prefer par->family over hardcoded NFPROTO_FOO (Jan Engelhardt)
include/net/netfilter/nf_conntrack.h | 4 ++++
net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 ++--
net/ipv4/netfilter/ipt_SYNPROXY.c | 4 ++--
net/ipv6/netfilter/ip6t_SYNPROXY.c | 4 ++--
net/netfilter/nf_conntrack_proto.c | 12 ++++++++++++
net/netfilter/nft_ct.c | 24 ++++++++++++------------
net/netfilter/xt_CONNSECMARK.c | 4 ++--
net/netfilter/xt_CT.c | 6 +++---
net/netfilter/xt_connbytes.c | 4 ++--
net/netfilter/xt_connlabel.c | 6 +++---
net/netfilter/xt_connlimit.c | 6 +++---
net/netfilter/xt_connmark.c | 8 ++++----
net/netfilter/xt_conntrack.c | 4 ++--
net/netfilter/xt_helper.c | 4 ++--
net/netfilter/xt_state.c | 4 ++--
15 files changed, 57 insertions(+), 41 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index fde4068..9dd4a6b 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -175,6 +175,10 @@ static inline void nf_ct_put(struct nf_conn *ct)
int nf_ct_l3proto_try_module_get(unsigned short l3proto);
void nf_ct_l3proto_module_put(unsigned short l3proto);
+/* load module; enable/disable conntrack in this namespace */
+int nf_ct_netns_get(struct net *net, u8 nfproto);
+void nf_ct_netns_put(struct net *net, u8 nfproto);
+
/*
* Allocate a hashtable of hlist_head (if nulls == 0),
* or hlist_nulls_head (if nulls == 1)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 4a9e6db..2c3fe06 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -419,7 +419,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
}
cipinfo->config = config;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -444,7 +444,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par)
clusterip_config_put(cipinfo->config);
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_get(par->net, par->family);
}
#ifdef CONFIG_COMPAT
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 5fdc556..c2cc22e 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -415,12 +415,12 @@ static int synproxy_tg4_check(const struct xt_tgchk_param *par)
e->ip.invflags & XT_INV_PROTO)
return -EINVAL;
- return nf_ct_l3proto_try_module_get(par->family);
+ return nf_ct_netns_get(par->net, par->family);
}
static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_target synproxy_tg4_reg __read_mostly = {
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 3deed58..484f4b6 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -436,12 +436,12 @@ static int synproxy_tg6_check(const struct xt_tgchk_param *par)
e->ipv6.invflags & XT_INV_PROTO)
return -EINVAL;
- return nf_ct_l3proto_try_module_get(par->family);
+ return nf_ct_netns_get(par->net, par->family);
}
static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_target synproxy_tg6_reg __read_mostly = {
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index b65d586..609c789 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -125,6 +125,18 @@ void nf_ct_l3proto_module_put(unsigned short l3proto)
}
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);
+}
+EXPORT_SYMBOL_GPL(nf_ct_netns_get);
+
+void nf_ct_netns_put(struct net *net, u8 nfproto)
+{
+ nf_ct_l3proto_module_put(nfproto);
+}
+EXPORT_SYMBOL_GPL(nf_ct_netns_put);
+
struct nf_conntrack_l4proto *
nf_ct_l4proto_find_get(u_int16_t l3num, u_int8_t l4num)
{
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 8cbca34..8c775b1 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -186,37 +186,37 @@ static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
[NFTA_CT_SREG] = { .type = NLA_U32 },
};
-static int nft_ct_l3proto_try_module_get(uint8_t family)
+static int nft_ct_netns_get(struct net *net, uint8_t family)
{
int err;
if (family == NFPROTO_INET) {
- err = nf_ct_l3proto_try_module_get(NFPROTO_IPV4);
+ err = nf_ct_netns_get(net, NFPROTO_IPV4);
if (err < 0)
goto err1;
- err = nf_ct_l3proto_try_module_get(NFPROTO_IPV6);
+ err = nf_ct_netns_get(net, NFPROTO_IPV6);
if (err < 0)
goto err2;
} else {
- err = nf_ct_l3proto_try_module_get(family);
+ err = nf_ct_netns_get(net, family);
if (err < 0)
goto err1;
}
return 0;
err2:
- nf_ct_l3proto_module_put(NFPROTO_IPV4);
+ nf_ct_netns_put(net, NFPROTO_IPV4);
err1:
return err;
}
-static void nft_ct_l3proto_module_put(uint8_t family)
+static void nft_ct_netns_put(struct net *net, uint8_t family)
{
if (family == NFPROTO_INET) {
- nf_ct_l3proto_module_put(NFPROTO_IPV4);
- nf_ct_l3proto_module_put(NFPROTO_IPV6);
+ nf_ct_netns_put(net, NFPROTO_IPV4);
+ nf_ct_netns_put(net, NFPROTO_IPV6);
} else
- nf_ct_l3proto_module_put(family);
+ nf_ct_netns_put(net, family);
}
static int nft_ct_get_init(const struct nft_ctx *ctx,
@@ -312,7 +312,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
if (err < 0)
return err;
- err = nft_ct_l3proto_try_module_get(ctx->afi->family);
+ err = nft_ct_netns_get(ctx->net, ctx->afi->family);
if (err < 0)
return err;
@@ -343,7 +343,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
if (err < 0)
return err;
- err = nft_ct_l3proto_try_module_get(ctx->afi->family);
+ err = nft_ct_netns_get(ctx->net, ctx->afi->family);
if (err < 0)
return err;
@@ -353,7 +353,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
static void nft_ct_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
- nft_ct_l3proto_module_put(ctx->afi->family);
+ nft_ct_netns_put(ctx->net, ctx->afi->family);
}
static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/netfilter/xt_CONNSECMARK.c b/net/netfilter/xt_CONNSECMARK.c
index e04dc28..da56c06 100644
--- a/net/netfilter/xt_CONNSECMARK.c
+++ b/net/netfilter/xt_CONNSECMARK.c
@@ -106,7 +106,7 @@ static int connsecmark_tg_check(const struct xt_tgchk_param *par)
return -EINVAL;
}
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -115,7 +115,7 @@ static int connsecmark_tg_check(const struct xt_tgchk_param *par)
static void connsecmark_tg_destroy(const struct xt_tgdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_target connsecmark_tg_reg __read_mostly = {
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index e7ac07e..48f1ddb 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -216,7 +216,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
goto err1;
#endif
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
goto err1;
@@ -260,7 +260,7 @@ out:
err3:
nf_ct_tmpl_free(ct);
err2:
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
err1:
return ret;
}
@@ -341,7 +341,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
if (help)
module_put(help->helper->me);
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
xt_ct_destroy_timeout(ct);
nf_ct_put(info->ct);
diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c
index d4bec26..cad0b7b 100644
--- a/net/netfilter/xt_connbytes.c
+++ b/net/netfilter/xt_connbytes.c
@@ -110,7 +110,7 @@ static int connbytes_mt_check(const struct xt_mtchk_param *par)
sinfo->direction != XT_CONNBYTES_DIR_BOTH)
return -EINVAL;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -129,7 +129,7 @@ static int connbytes_mt_check(const struct xt_mtchk_param *par)
static void connbytes_mt_destroy(const struct xt_mtdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_match connbytes_mt_reg __read_mostly = {
diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c
index bb9cbeb..b7e57f2 100644
--- a/net/netfilter/xt_connlabel.c
+++ b/net/netfilter/xt_connlabel.c
@@ -48,7 +48,7 @@ static int connlabel_mt_check(const struct xt_mtchk_param *par)
return -EINVAL;
}
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0) {
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -57,14 +57,14 @@ static int connlabel_mt_check(const struct xt_mtchk_param *par)
ret = nf_connlabels_get(par->net, info->bit + 1);
if (ret < 0)
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
return ret;
}
static void connlabel_mt_destroy(const struct xt_mtdtor_param *par)
{
nf_connlabels_put(par->net);
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_match connlabels_mt_reg __read_mostly = {
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 99bbc82..66f5480 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -374,7 +374,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
} while (!rand);
cmpxchg(&connlimit_rnd, 0, rand);
}
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0) {
pr_info("cannot load conntrack support for "
"address family %u\n", par->family);
@@ -384,7 +384,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
/* init private data */
info->data = kmalloc(sizeof(struct xt_connlimit_data), GFP_KERNEL);
if (info->data == NULL) {
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
return -ENOMEM;
}
@@ -420,7 +420,7 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
const struct xt_connlimit_info *info = par->matchinfo;
unsigned int i;
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i)
destroy_tree(&info->data->climit_root4[i]);
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 69f78e9..ec377cc 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -77,7 +77,7 @@ static int connmark_tg_check(const struct xt_tgchk_param *par)
{
int ret;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -86,7 +86,7 @@ static int connmark_tg_check(const struct xt_tgchk_param *par)
static void connmark_tg_destroy(const struct xt_tgdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static bool
@@ -107,7 +107,7 @@ static int connmark_mt_check(const struct xt_mtchk_param *par)
{
int ret;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -116,7 +116,7 @@ static int connmark_mt_check(const struct xt_mtchk_param *par)
static void connmark_mt_destroy(const struct xt_mtdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_target connmark_tg_reg __read_mostly = {
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 188404b9..9480b52 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -273,7 +273,7 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par)
{
int ret;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -282,7 +282,7 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par)
static void conntrack_mt_destroy(const struct xt_mtdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_match conntrack_mt_reg[] __read_mostly = {
diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c
index 9f4ab00..8e451ec 100644
--- a/net/netfilter/xt_helper.c
+++ b/net/netfilter/xt_helper.c
@@ -59,7 +59,7 @@ static int helper_mt_check(const struct xt_mtchk_param *par)
struct xt_helper_info *info = par->matchinfo;
int ret;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0) {
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -71,7 +71,7 @@ static int helper_mt_check(const struct xt_mtchk_param *par)
static void helper_mt_destroy(const struct xt_mtdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_match helper_mt_reg __read_mostly = {
diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c
index a507922..5746a33 100644
--- a/net/netfilter/xt_state.c
+++ b/net/netfilter/xt_state.c
@@ -43,7 +43,7 @@ static int state_mt_check(const struct xt_mtchk_param *par)
{
int ret;
- ret = nf_ct_l3proto_try_module_get(par->family);
+ ret = nf_ct_netns_get(par->net, par->family);
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
@@ -52,7 +52,7 @@ static int state_mt_check(const struct xt_mtchk_param *par)
static void state_mt_destroy(const struct xt_mtdtor_param *par)
{
- nf_ct_l3proto_module_put(par->family);
+ nf_ct_netns_put(par->net, par->family);
}
static struct xt_match state_mt_reg __read_mostly = {
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 02/12] netfilter: conntrack: register hooks in netns when needed by ruleset
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 01/12] netfilter: add and use nf_ct_netns_get/put Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 03/12] netfilter: xtables: don't register table hooks in namespace at init time Florian Westphal
` (10 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
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@strlen.de>
---
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
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 03/12] netfilter: xtables: don't register table hooks in namespace at init time
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 01/12] netfilter: add and use nf_ct_netns_get/put Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 02/12] netfilter: conntrack: register hooks in netns when needed by ruleset Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 04/12] netfilter: defrag: only register defrag functionality if needed Florian Westphal
` (9 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
delay hook registration until the table is being requested inside a
namespace.
Historically, a particular table (iptables mangle, ip6tables filter, etc)
was registered on module load.
When netns support was added to iptables only the ip/ip6tables ruleset was
made namespace aware, not the actual hook points.
This means f.e. that when ipt_filter table/module is loaded on a system,
then each namespace on that system has an (empty) iptables filter ruleset.
In other words, if a namespace sends a packet, such skb is 'caught' by
netfilter machinery and fed to hooking points for that table (i.e. INPUT,
FORWARD, etc).
Thanks to Eric Biederman, hooks are no longer global, but per namespace.
This means that we can avoid allocation of empty ruleset in a namespace and
defer hook registration until we need the functionality.
We register a tables hook entry points ONLY in the initial namespace.
When an iptables get/setockopt is issued inside a given namespace, we check
if the table is found in the per-namespace list.
If not, we attempt to find it in the initial namespace, and, if found,
create an empty default table in the requesting namespace and register the
needed hooks.
Hook points are destroyed only once namespace is deleted, there is no
'usage count' (it makes no sense since there is no 'remove table' operation
in xtables api).
Signed-off-by: Florian Westphal <fw@strlen.de>
---
No changes since v2.
Changes since v1:
- perform netns hook registration from xx_register_table() (Pablo Neira)
- don't make nat table register conntrack hooks (causes hard to resolve
link order problems w. conntrack initcalls -- followup patch adds expicit
conntrack-enable calls to MASQUERADE, REDIRECT, etc)
include/linux/netfilter/x_tables.h | 6 ++-
include/linux/netfilter_arp/arp_tables.h | 9 +++--
include/linux/netfilter_ipv4/ip_tables.h | 9 +++--
include/linux/netfilter_ipv6/ip6_tables.h | 9 +++--
net/ipv4/netfilter/arp_tables.c | 66 +++++++++++++++++++------------
net/ipv4/netfilter/arptable_filter.c | 40 +++++++++++--------
net/ipv4/netfilter/ip_tables.c | 63 +++++++++++++++++------------
net/ipv4/netfilter/iptable_filter.c | 55 ++++++++++++++++----------
net/ipv4/netfilter/iptable_mangle.c | 41 +++++++++++++------
net/ipv4/netfilter/iptable_nat.c | 41 ++++++++++---------
net/ipv4/netfilter/iptable_raw.c | 42 +++++++++++++-------
net/ipv4/netfilter/iptable_security.c | 44 +++++++++++++--------
net/ipv6/netfilter/ip6_tables.c | 65 ++++++++++++++++++------------
net/ipv6/netfilter/ip6table_filter.c | 47 +++++++++++++---------
net/ipv6/netfilter/ip6table_mangle.c | 45 ++++++++++++---------
net/ipv6/netfilter/ip6table_nat.c | 41 ++++++++++---------
net/ipv6/netfilter/ip6table_raw.c | 46 ++++++++++++---------
net/ipv6/netfilter/ip6table_security.c | 44 +++++++++++++--------
net/netfilter/x_tables.c | 65 ++++++++++++++++++------------
19 files changed, 475 insertions(+), 303 deletions(-)
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index c557741..80a305b 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -200,6 +200,9 @@ struct xt_table {
u_int8_t af; /* address/protocol family */
int priority; /* hook order */
+ /* called when table is needed in the given netns */
+ int (*table_init)(struct net *net);
+
/* A unique name... */
const char name[XT_TABLE_MAXNAMELEN];
};
@@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
return cnt;
}
-struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
-void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
+struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
#ifdef CONFIG_COMPAT
#include <net/compat.h>
diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h
index 6f074db..029b95e 100644
--- a/include/linux/netfilter_arp/arp_tables.h
+++ b/include/linux/netfilter_arp/arp_tables.h
@@ -48,10 +48,11 @@ struct arpt_error {
}
extern void *arpt_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *arpt_register_table(struct net *net,
- const struct xt_table *table,
- const struct arpt_replace *repl);
-extern void arpt_unregister_table(struct xt_table *table);
+int arpt_register_table(struct net *net, const struct xt_table *table,
+ const struct arpt_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
extern unsigned int arpt_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct xt_table *table);
diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h
index aa598f9..7bfc589 100644
--- a/include/linux/netfilter_ipv4/ip_tables.h
+++ b/include/linux/netfilter_ipv4/ip_tables.h
@@ -24,10 +24,11 @@
extern void ipt_init(void) __init;
-extern struct xt_table *ipt_register_table(struct net *net,
- const struct xt_table *table,
- const struct ipt_replace *repl);
-extern void ipt_unregister_table(struct net *net, struct xt_table *table);
+int ipt_register_table(struct net *net, const struct xt_table *table,
+ const struct ipt_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
/* Standard entry. */
struct ipt_standard {
diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index 0f76e5c..b21c392 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -25,10 +25,11 @@
extern void ip6t_init(void) __init;
extern void *ip6t_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *ip6t_register_table(struct net *net,
- const struct xt_table *table,
- const struct ip6t_replace *repl);
-extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
+int ip6t_register_table(struct net *net, const struct xt_table *table,
+ const struct ip6t_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
extern unsigned int ip6t_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct xt_table *table);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b488cac..bf08192 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1780,9 +1780,29 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
return ret;
}
-struct xt_table *arpt_register_table(struct net *net,
- const struct xt_table *table,
- const struct arpt_replace *repl)
+static void __arpt_unregister_table(struct xt_table *table)
+{
+ struct xt_table_info *private;
+ void *loc_cpu_entry;
+ struct module *table_owner = table->me;
+ struct arpt_entry *iter;
+
+ private = xt_unregister_table(table);
+
+ /* Decrease module usage counts and free resources */
+ loc_cpu_entry = private->entries;
+ xt_entry_foreach(iter, loc_cpu_entry, private->size)
+ cleanup_entry(iter);
+ if (private->number > private->initial_entries)
+ module_put(table_owner);
+ xt_free_table_info(private);
+}
+
+int arpt_register_table(struct net *net,
+ const struct xt_table *table,
+ const struct arpt_replace *repl,
+ const struct nf_hook_ops *ops,
+ struct xt_table **res)
{
int ret;
struct xt_table_info *newinfo;
@@ -1791,10 +1811,8 @@ struct xt_table *arpt_register_table(struct net *net,
struct xt_table *new_table;
newinfo = xt_alloc_table_info(repl->size);
- if (!newinfo) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!newinfo)
+ return -ENOMEM;
loc_cpu_entry = newinfo->entries;
memcpy(loc_cpu_entry, repl->entries, repl->size);
@@ -1809,30 +1827,28 @@ struct xt_table *arpt_register_table(struct net *net,
ret = PTR_ERR(new_table);
goto out_free;
}
- return new_table;
+
+ /* set res now, will see skbs right after nf_register_net_hooks */
+ WRITE_ONCE(*res, new_table);
+
+ ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+ if (ret != 0) {
+ __arpt_unregister_table(new_table);
+ *res = NULL;
+ }
+
+ return ret;
out_free:
xt_free_table_info(newinfo);
-out:
- return ERR_PTR(ret);
+ return ret;
}
-void arpt_unregister_table(struct xt_table *table)
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
- struct module *table_owner = table->me;
- struct arpt_entry *iter;
-
- private = xt_unregister_table(table);
-
- /* Decrease module usage counts and free resources */
- loc_cpu_entry = private->entries;
- xt_entry_foreach(iter, loc_cpu_entry, private->size)
- cleanup_entry(iter);
- if (private->number > private->initial_entries)
- module_put(table_owner);
- xt_free_table_info(private);
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ __arpt_unregister_table(table);
}
/* The built-in targets: standard (NULL) and error. */
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 1897ee1..aa0ad5a 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -17,12 +17,15 @@ MODULE_DESCRIPTION("arptables filter table");
#define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \
(1 << NF_ARP_FORWARD))
+static int __net_init arptable_filter_table_init(struct net *net);
+
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_ARP,
.priority = NF_IP_PRI_FILTER,
+ .table_init = arptable_filter_table_init,
};
/* The work comes in here from netfilter.c */
@@ -35,26 +38,32 @@ arptable_filter_hook(void *priv, struct sk_buff *skb,
static struct nf_hook_ops *arpfilter_ops __read_mostly;
-static int __net_init arptable_filter_net_init(struct net *net)
+static int __net_init arptable_filter_table_init(struct net *net)
{
struct arpt_replace *repl;
-
+ int err = 0;
+
+ if (net->ipv4.arptable_filter)
+ return 0;
+
repl = arpt_alloc_initial_table(&packet_filter);
if (repl == NULL)
return -ENOMEM;
- net->ipv4.arptable_filter =
- arpt_register_table(net, &packet_filter, repl);
+ err = arpt_register_table(net, &packet_filter, repl, arpfilter_ops,
+ &net->ipv4.arptable_filter);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.arptable_filter);
+ return err;
}
static void __net_exit arptable_filter_net_exit(struct net *net)
{
- arpt_unregister_table(net->ipv4.arptable_filter);
+ if (net->ipv4.arptable_filter)
+ arpt_unregister_table(net, net->ipv4.arptable_filter,
+ arpfilter_ops);
+ net->ipv4.arptable_filter = NULL;
}
static struct pernet_operations arptable_filter_net_ops = {
- .init = arptable_filter_net_init,
.exit = arptable_filter_net_exit,
};
@@ -62,26 +71,23 @@ static int __init arptable_filter_init(void)
{
int ret;
+ arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook);
+ if (IS_ERR(arpfilter_ops))
+ return PTR_ERR(arpfilter_ops);
+
ret = register_pernet_subsys(&arptable_filter_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(arpfilter_ops);
return ret;
-
- arpfilter_ops = xt_hook_link(&packet_filter, arptable_filter_hook);
- if (IS_ERR(arpfilter_ops)) {
- ret = PTR_ERR(arpfilter_ops);
- goto cleanup_table;
}
- return ret;
-cleanup_table:
- unregister_pernet_subsys(&arptable_filter_net_ops);
return ret;
}
static void __exit arptable_filter_fini(void)
{
- xt_hook_unlink(&packet_filter, arpfilter_ops);
unregister_pernet_subsys(&arptable_filter_net_ops);
+ kfree(arpfilter_ops);
}
module_init(arptable_filter_init);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b99affa..e53f8d6 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -2062,9 +2062,27 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
return ret;
}
-struct xt_table *ipt_register_table(struct net *net,
- const struct xt_table *table,
- const struct ipt_replace *repl)
+static void __ipt_unregister_table(struct net *net, struct xt_table *table)
+{
+ struct xt_table_info *private;
+ void *loc_cpu_entry;
+ struct module *table_owner = table->me;
+ struct ipt_entry *iter;
+
+ private = xt_unregister_table(table);
+
+ /* Decrease module usage counts and free resources */
+ loc_cpu_entry = private->entries;
+ xt_entry_foreach(iter, loc_cpu_entry, private->size)
+ cleanup_entry(iter, net);
+ if (private->number > private->initial_entries)
+ module_put(table_owner);
+ xt_free_table_info(private);
+}
+
+int ipt_register_table(struct net *net, const struct xt_table *table,
+ const struct ipt_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res)
{
int ret;
struct xt_table_info *newinfo;
@@ -2073,10 +2091,8 @@ struct xt_table *ipt_register_table(struct net *net,
struct xt_table *new_table;
newinfo = xt_alloc_table_info(repl->size);
- if (!newinfo) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!newinfo)
+ return -ENOMEM;
loc_cpu_entry = newinfo->entries;
memcpy(loc_cpu_entry, repl->entries, repl->size);
@@ -2091,30 +2107,27 @@ struct xt_table *ipt_register_table(struct net *net,
goto out_free;
}
- return new_table;
+ /* set res now, will see skbs right after nf_register_net_hooks */
+ WRITE_ONCE(*res, new_table);
+
+ ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+ if (ret != 0) {
+ __ipt_unregister_table(net, new_table);
+ *res = NULL;
+ }
+
+ return ret;
out_free:
xt_free_table_info(newinfo);
-out:
- return ERR_PTR(ret);
+ return ret;
}
-void ipt_unregister_table(struct net *net, struct xt_table *table)
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
- struct module *table_owner = table->me;
- struct ipt_entry *iter;
-
- private = xt_unregister_table(table);
-
- /* Decrease module usage counts and free resources */
- loc_cpu_entry = private->entries;
- xt_entry_foreach(iter, loc_cpu_entry, private->size)
- cleanup_entry(iter, net);
- if (private->number > private->initial_entries)
- module_put(table_owner);
- xt_free_table_info(private);
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ __ipt_unregister_table(net, table);
}
/* Returns 1 if the type and code is matched by the range, 0 otherwise */
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 397ef2d..49e8d35 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -24,12 +24,21 @@ MODULE_DESCRIPTION("iptables filter table");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT))
+static struct nf_hook_ops *filter_ops __read_mostly;
+
+/* Default to forward because I got too much mail already. */
+static bool forward __read_mostly = true;
+module_param(forward, bool, 0000);
+
+static int __net_init iptable_filter_table_init(struct net *net);
+
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_FILTER,
+ .table_init = iptable_filter_table_init,
};
static unsigned int
@@ -45,15 +54,13 @@ iptable_filter_hook(void *priv, struct sk_buff *skb,
return ipt_do_table(skb, state, state->net->ipv4.iptable_filter);
}
-static struct nf_hook_ops *filter_ops __read_mostly;
-
-/* Default to forward because I got too much mail already. */
-static bool forward = true;
-module_param(forward, bool, 0000);
-
-static int __net_init iptable_filter_net_init(struct net *net)
+static int __net_init iptable_filter_table_init(struct net *net)
{
struct ipt_replace *repl;
+ int err;
+
+ if (net->ipv4.iptable_filter)
+ return 0;
repl = ipt_alloc_initial_table(&packet_filter);
if (repl == NULL)
@@ -62,15 +69,26 @@ static int __net_init iptable_filter_net_init(struct net *net)
((struct ipt_standard *)repl->entries)[1].target.verdict =
forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
- net->ipv4.iptable_filter =
- ipt_register_table(net, &packet_filter, repl);
+ err = ipt_register_table(net, &packet_filter, repl, filter_ops,
+ &net->ipv4.iptable_filter);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.iptable_filter);
+ return err;
+}
+
+static int __net_init iptable_filter_net_init(struct net *net)
+{
+ if (net == &init_net || !forward)
+ return iptable_filter_table_init(net);
+
+ return 0;
}
static void __net_exit iptable_filter_net_exit(struct net *net)
{
- ipt_unregister_table(net, net->ipv4.iptable_filter);
+ if (!net->ipv4.iptable_filter)
+ return;
+ ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops);
+ net->ipv4.iptable_filter = NULL;
}
static struct pernet_operations iptable_filter_net_ops = {
@@ -82,24 +100,21 @@ static int __init iptable_filter_init(void)
{
int ret;
+ filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook);
+ if (IS_ERR(filter_ops))
+ return PTR_ERR(filter_ops);
+
ret = register_pernet_subsys(&iptable_filter_net_ops);
if (ret < 0)
- return ret;
-
- /* Register hooks */
- filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook);
- if (IS_ERR(filter_ops)) {
- ret = PTR_ERR(filter_ops);
- unregister_pernet_subsys(&iptable_filter_net_ops);
- }
+ kfree(filter_ops);
return ret;
}
static void __exit iptable_filter_fini(void)
{
- xt_hook_unlink(&packet_filter, filter_ops);
unregister_pernet_subsys(&iptable_filter_net_ops);
+ kfree(filter_ops);
}
module_init(iptable_filter_init);
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index ba5d392..57fc97c 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables mangle table");
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
+static int __net_init iptable_mangle_table_init(struct net *net);
+
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_MANGLE,
+ .table_init = iptable_mangle_table_init,
};
static unsigned int
@@ -92,27 +95,32 @@ iptable_mangle_hook(void *priv,
}
static struct nf_hook_ops *mangle_ops __read_mostly;
-
-static int __net_init iptable_mangle_net_init(struct net *net)
+static int __net_init iptable_mangle_table_init(struct net *net)
{
struct ipt_replace *repl;
+ int ret;
+
+ if (net->ipv4.iptable_mangle)
+ return 0;
repl = ipt_alloc_initial_table(&packet_mangler);
if (repl == NULL)
return -ENOMEM;
- net->ipv4.iptable_mangle =
- ipt_register_table(net, &packet_mangler, repl);
+ ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops,
+ &net->ipv4.iptable_mangle);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.iptable_mangle);
+ return ret;
}
static void __net_exit iptable_mangle_net_exit(struct net *net)
{
- ipt_unregister_table(net, net->ipv4.iptable_mangle);
+ if (!net->ipv4.iptable_mangle)
+ return;
+ ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops);
+ net->ipv4.iptable_mangle = NULL;
}
static struct pernet_operations iptable_mangle_net_ops = {
- .init = iptable_mangle_net_init,
.exit = iptable_mangle_net_exit,
};
@@ -120,15 +128,22 @@ static int __init iptable_mangle_init(void)
{
int ret;
+ mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
+ if (IS_ERR(mangle_ops)) {
+ ret = PTR_ERR(mangle_ops);
+ return ret;
+ }
+
ret = register_pernet_subsys(&iptable_mangle_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(mangle_ops);
return ret;
+ }
- /* Register hooks */
- mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook);
- if (IS_ERR(mangle_ops)) {
- ret = PTR_ERR(mangle_ops);
+ ret = iptable_mangle_table_init(&init_net);
+ if (ret) {
unregister_pernet_subsys(&iptable_mangle_net_ops);
+ kfree(mangle_ops);
}
return ret;
@@ -136,8 +151,8 @@ static int __init iptable_mangle_init(void)
static void __exit iptable_mangle_fini(void)
{
- xt_hook_unlink(&packet_mangler, mangle_ops);
unregister_pernet_subsys(&iptable_mangle_net_ops);
+ kfree(mangle_ops);
}
module_init(iptable_mangle_init);
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index ae2cd27..138a24b 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -18,6 +18,8 @@
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
+static int __net_init iptable_nat_table_init(struct net *net);
+
static const struct xt_table nf_nat_ipv4_table = {
.name = "nat",
.valid_hooks = (1 << NF_INET_PRE_ROUTING) |
@@ -26,6 +28,7 @@ static const struct xt_table nf_nat_ipv4_table = {
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
+ .table_init = iptable_nat_table_init,
};
static unsigned int iptable_nat_do_chain(void *priv,
@@ -95,50 +98,50 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
},
};
-static int __net_init iptable_nat_net_init(struct net *net)
+static int __net_init iptable_nat_table_init(struct net *net)
{
struct ipt_replace *repl;
+ int ret;
+
+ if (net->ipv4.nat_table)
+ return 0;
repl = ipt_alloc_initial_table(&nf_nat_ipv4_table);
if (repl == NULL)
return -ENOMEM;
- net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl);
+ ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
+ nf_nat_ipv4_ops, &net->ipv4.nat_table);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.nat_table);
+ return ret;
}
static void __net_exit iptable_nat_net_exit(struct net *net)
{
- ipt_unregister_table(net, net->ipv4.nat_table);
+ if (!net->ipv4.nat_table)
+ return;
+ ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops);
+ net->ipv4.nat_table = NULL;
}
static struct pernet_operations iptable_nat_net_ops = {
- .init = iptable_nat_net_init,
.exit = iptable_nat_net_exit,
};
static int __init iptable_nat_init(void)
{
- int err;
+ int ret = register_pernet_subsys(&iptable_nat_net_ops);
- err = register_pernet_subsys(&iptable_nat_net_ops);
- if (err < 0)
- goto err1;
+ if (ret)
+ return ret;
- err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
- if (err < 0)
- goto err2;
- return 0;
-
-err2:
- unregister_pernet_subsys(&iptable_nat_net_ops);
-err1:
- return err;
+ ret = iptable_nat_table_init(&init_net);
+ if (ret)
+ unregister_pernet_subsys(&iptable_nat_net_ops);
+ return ret;
}
static void __exit iptable_nat_exit(void)
{
- nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
unregister_pernet_subsys(&iptable_nat_net_ops);
}
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 1ba0281..ca83ed8 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -10,12 +10,17 @@
#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
+static struct nf_hook_ops *rawtable_ops __read_mostly;
+
+static int __net_init iptable_raw_table_init(struct net *net);
+
static const struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_RAW,
+ .table_init = iptable_raw_table_init,
};
/* The work comes in here from netfilter.c. */
@@ -32,28 +37,32 @@ iptable_raw_hook(void *priv, struct sk_buff *skb,
return ipt_do_table(skb, state, state->net->ipv4.iptable_raw);
}
-static struct nf_hook_ops *rawtable_ops __read_mostly;
-
-static int __net_init iptable_raw_net_init(struct net *net)
+static int __net_init iptable_raw_table_init(struct net *net)
{
struct ipt_replace *repl;
+ int ret;
+
+ if (net->ipv4.iptable_raw)
+ return 0;
repl = ipt_alloc_initial_table(&packet_raw);
if (repl == NULL)
return -ENOMEM;
- net->ipv4.iptable_raw =
- ipt_register_table(net, &packet_raw, repl);
+ ret = ipt_register_table(net, &packet_raw, repl, rawtable_ops,
+ &net->ipv4.iptable_raw);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.iptable_raw);
+ return ret;
}
static void __net_exit iptable_raw_net_exit(struct net *net)
{
- ipt_unregister_table(net, net->ipv4.iptable_raw);
+ if (!net->ipv4.iptable_raw)
+ return;
+ ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops);
+ net->ipv4.iptable_raw = NULL;
}
static struct pernet_operations iptable_raw_net_ops = {
- .init = iptable_raw_net_init,
.exit = iptable_raw_net_exit,
};
@@ -61,15 +70,20 @@ static int __init iptable_raw_init(void)
{
int ret;
+ rawtable_ops = xt_hook_ops_alloc(&packet_raw, iptable_raw_hook);
+ if (IS_ERR(rawtable_ops))
+ return PTR_ERR(rawtable_ops);
+
ret = register_pernet_subsys(&iptable_raw_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(rawtable_ops);
return ret;
+ }
- /* Register hooks */
- rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook);
- if (IS_ERR(rawtable_ops)) {
- ret = PTR_ERR(rawtable_ops);
+ ret = iptable_raw_table_init(&init_net);
+ if (ret) {
unregister_pernet_subsys(&iptable_raw_net_ops);
+ kfree(rawtable_ops);
}
return ret;
@@ -77,8 +91,8 @@ static int __init iptable_raw_init(void)
static void __exit iptable_raw_fini(void)
{
- xt_hook_unlink(&packet_raw, rawtable_ops);
unregister_pernet_subsys(&iptable_raw_net_ops);
+ kfree(rawtable_ops);
}
module_init(iptable_raw_init);
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index c2e23d5..ff22659 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT)
+static int __net_init iptable_security_table_init(struct net *net);
+
static const struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV4,
.priority = NF_IP_PRI_SECURITY,
+ .table_init = iptable_security_table_init,
};
static unsigned int
@@ -51,26 +54,33 @@ iptable_security_hook(void *priv, struct sk_buff *skb,
static struct nf_hook_ops *sectbl_ops __read_mostly;
-static int __net_init iptable_security_net_init(struct net *net)
+static int __net_init iptable_security_table_init(struct net *net)
{
struct ipt_replace *repl;
+ int ret;
+
+ if (net->ipv4.iptable_security)
+ return 0;
repl = ipt_alloc_initial_table(&security_table);
if (repl == NULL)
return -ENOMEM;
- net->ipv4.iptable_security =
- ipt_register_table(net, &security_table, repl);
+ ret = ipt_register_table(net, &security_table, repl, sectbl_ops,
+ &net->ipv4.iptable_security);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv4.iptable_security);
+ return ret;
}
static void __net_exit iptable_security_net_exit(struct net *net)
{
- ipt_unregister_table(net, net->ipv4.iptable_security);
+ if (!net->ipv4.iptable_security)
+ return;
+
+ ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops);
+ net->ipv4.iptable_security = NULL;
}
static struct pernet_operations iptable_security_net_ops = {
- .init = iptable_security_net_init,
.exit = iptable_security_net_exit,
};
@@ -78,27 +88,29 @@ static int __init iptable_security_init(void)
{
int ret;
+ sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook);
+ if (IS_ERR(sectbl_ops))
+ return PTR_ERR(sectbl_ops);
+
ret = register_pernet_subsys(&iptable_security_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(sectbl_ops);
return ret;
-
- sectbl_ops = xt_hook_link(&security_table, iptable_security_hook);
- if (IS_ERR(sectbl_ops)) {
- ret = PTR_ERR(sectbl_ops);
- goto cleanup_table;
}
- return ret;
+ ret = iptable_security_table_init(&init_net);
+ if (ret) {
+ unregister_pernet_subsys(&iptable_security_net_ops);
+ kfree(sectbl_ops);
+ }
-cleanup_table:
- unregister_pernet_subsys(&iptable_security_net_ops);
return ret;
}
static void __exit iptable_security_fini(void)
{
- xt_hook_unlink(&security_table, sectbl_ops);
unregister_pernet_subsys(&iptable_security_net_ops);
+ kfree(sectbl_ops);
}
module_init(iptable_security_init);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 99425cf..84f9baf 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -2071,9 +2071,28 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
return ret;
}
-struct xt_table *ip6t_register_table(struct net *net,
- const struct xt_table *table,
- const struct ip6t_replace *repl)
+static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
+{
+ struct xt_table_info *private;
+ void *loc_cpu_entry;
+ struct module *table_owner = table->me;
+ struct ip6t_entry *iter;
+
+ private = xt_unregister_table(table);
+
+ /* Decrease module usage counts and free resources */
+ loc_cpu_entry = private->entries;
+ xt_entry_foreach(iter, loc_cpu_entry, private->size)
+ cleanup_entry(iter, net);
+ if (private->number > private->initial_entries)
+ module_put(table_owner);
+ xt_free_table_info(private);
+}
+
+int ip6t_register_table(struct net *net, const struct xt_table *table,
+ const struct ip6t_replace *repl,
+ const struct nf_hook_ops *ops,
+ struct xt_table **res)
{
int ret;
struct xt_table_info *newinfo;
@@ -2082,10 +2101,8 @@ struct xt_table *ip6t_register_table(struct net *net,
struct xt_table *new_table;
newinfo = xt_alloc_table_info(repl->size);
- if (!newinfo) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!newinfo)
+ return -ENOMEM;
loc_cpu_entry = newinfo->entries;
memcpy(loc_cpu_entry, repl->entries, repl->size);
@@ -2099,30 +2116,28 @@ struct xt_table *ip6t_register_table(struct net *net,
ret = PTR_ERR(new_table);
goto out_free;
}
- return new_table;
+
+ /* set res now, will see skbs right after nf_register_net_hooks */
+ WRITE_ONCE(*res, new_table);
+
+ ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+ if (ret != 0) {
+ __ip6t_unregister_table(net, new_table);
+ *res = NULL;
+ }
+
+ return ret;
out_free:
xt_free_table_info(newinfo);
-out:
- return ERR_PTR(ret);
+ return ret;
}
-void ip6t_unregister_table(struct net *net, struct xt_table *table)
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops)
{
- struct xt_table_info *private;
- void *loc_cpu_entry;
- struct module *table_owner = table->me;
- struct ip6t_entry *iter;
-
- private = xt_unregister_table(table);
-
- /* Decrease module usage counts and free resources */
- loc_cpu_entry = private->entries;
- xt_entry_foreach(iter, loc_cpu_entry, private->size)
- cleanup_entry(iter, net);
- if (private->number > private->initial_entries)
- module_put(table_owner);
- xt_free_table_info(private);
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ __ip6t_unregister_table(net, table);
}
/* Returns 1 if the type and code is matched by the range, 0 otherwise */
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 8b277b9..1343077 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -22,12 +22,15 @@ MODULE_DESCRIPTION("ip6tables filter table");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT))
+static int __net_init ip6table_filter_table_init(struct net *net);
+
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
.priority = NF_IP6_PRI_FILTER,
+ .table_init = ip6table_filter_table_init,
};
/* The work comes in here from netfilter.c. */
@@ -44,9 +47,13 @@ static struct nf_hook_ops *filter_ops __read_mostly;
static bool forward = true;
module_param(forward, bool, 0000);
-static int __net_init ip6table_filter_net_init(struct net *net)
+static int __net_init ip6table_filter_table_init(struct net *net)
{
struct ip6t_replace *repl;
+ int err;
+
+ if (net->ipv6.ip6table_filter)
+ return 0;
repl = ip6t_alloc_initial_table(&packet_filter);
if (repl == NULL)
@@ -55,15 +62,26 @@ static int __net_init ip6table_filter_net_init(struct net *net)
((struct ip6t_standard *)repl->entries)[1].target.verdict =
forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
- net->ipv6.ip6table_filter =
- ip6t_register_table(net, &packet_filter, repl);
+ err = ip6t_register_table(net, &packet_filter, repl, filter_ops,
+ &net->ipv6.ip6table_filter);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter);
+ return err;
+}
+
+static int __net_init ip6table_filter_net_init(struct net *net)
+{
+ if (net == &init_net || !forward)
+ return ip6table_filter_table_init(net);
+
+ return 0;
}
static void __net_exit ip6table_filter_net_exit(struct net *net)
{
- ip6t_unregister_table(net, net->ipv6.ip6table_filter);
+ if (!net->ipv6.ip6table_filter)
+ return;
+ ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops);
+ net->ipv6.ip6table_filter = NULL;
}
static struct pernet_operations ip6table_filter_net_ops = {
@@ -75,28 +93,21 @@ static int __init ip6table_filter_init(void)
{
int ret;
+ filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook);
+ if (IS_ERR(filter_ops))
+ return PTR_ERR(filter_ops);
+
ret = register_pernet_subsys(&ip6table_filter_net_ops);
if (ret < 0)
- return ret;
-
- /* Register hooks */
- filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook);
- if (IS_ERR(filter_ops)) {
- ret = PTR_ERR(filter_ops);
- goto cleanup_table;
- }
+ kfree(filter_ops);
return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&ip6table_filter_net_ops);
- return ret;
}
static void __exit ip6table_filter_fini(void)
{
- xt_hook_unlink(&packet_filter, filter_ops);
unregister_pernet_subsys(&ip6table_filter_net_ops);
+ kfree(filter_ops);
}
module_init(ip6table_filter_init);
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index abe278b..bc09dc8 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -23,12 +23,14 @@ MODULE_DESCRIPTION("ip6tables mangle table");
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
+static int __net_init ip6table_mangle_table_init(struct net *net);
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
.priority = NF_IP6_PRI_MANGLE,
+ .table_init = ip6table_mangle_table_init,
};
static unsigned int
@@ -88,26 +90,33 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb,
}
static struct nf_hook_ops *mangle_ops __read_mostly;
-static int __net_init ip6table_mangle_net_init(struct net *net)
+static int __net_init ip6table_mangle_table_init(struct net *net)
{
struct ip6t_replace *repl;
+ int ret;
+
+ if (net->ipv6.ip6table_mangle)
+ return 0;
repl = ip6t_alloc_initial_table(&packet_mangler);
if (repl == NULL)
return -ENOMEM;
- net->ipv6.ip6table_mangle =
- ip6t_register_table(net, &packet_mangler, repl);
+ ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops,
+ &net->ipv6.ip6table_mangle);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle);
+ return ret;
}
static void __net_exit ip6table_mangle_net_exit(struct net *net)
{
- ip6t_unregister_table(net, net->ipv6.ip6table_mangle);
+ if (!net->ipv6.ip6table_mangle)
+ return;
+
+ ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops);
+ net->ipv6.ip6table_mangle = NULL;
}
static struct pernet_operations ip6table_mangle_net_ops = {
- .init = ip6table_mangle_net_init,
.exit = ip6table_mangle_net_exit,
};
@@ -115,28 +124,28 @@ static int __init ip6table_mangle_init(void)
{
int ret;
+ mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
+ if (IS_ERR(mangle_ops))
+ return PTR_ERR(mangle_ops);
+
ret = register_pernet_subsys(&ip6table_mangle_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(mangle_ops);
return ret;
-
- /* Register hooks */
- mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook);
- if (IS_ERR(mangle_ops)) {
- ret = PTR_ERR(mangle_ops);
- goto cleanup_table;
}
- return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&ip6table_mangle_net_ops);
+ ret = ip6table_mangle_table_init(&init_net);
+ if (ret) {
+ unregister_pernet_subsys(&ip6table_mangle_net_ops);
+ kfree(mangle_ops);
+ }
return ret;
}
static void __exit ip6table_mangle_fini(void)
{
- xt_hook_unlink(&packet_mangler, mangle_ops);
unregister_pernet_subsys(&ip6table_mangle_net_ops);
+ kfree(mangle_ops);
}
module_init(ip6table_mangle_init);
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index de2a10a..7d2bd94 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -20,6 +20,8 @@
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
+static int __net_init ip6table_nat_table_init(struct net *net);
+
static const struct xt_table nf_nat_ipv6_table = {
.name = "nat",
.valid_hooks = (1 << NF_INET_PRE_ROUTING) |
@@ -28,6 +30,7 @@ static const struct xt_table nf_nat_ipv6_table = {
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
+ .table_init = ip6table_nat_table_init,
};
static unsigned int ip6table_nat_do_chain(void *priv,
@@ -97,50 +100,50 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
},
};
-static int __net_init ip6table_nat_net_init(struct net *net)
+static int __net_init ip6table_nat_table_init(struct net *net)
{
struct ip6t_replace *repl;
+ int ret;
+
+ if (net->ipv6.ip6table_nat)
+ return 0;
repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table);
if (repl == NULL)
return -ENOMEM;
- net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl);
+ ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl,
+ nf_nat_ipv6_ops, &net->ipv6.ip6table_nat);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat);
+ return ret;
}
static void __net_exit ip6table_nat_net_exit(struct net *net)
{
- ip6t_unregister_table(net, net->ipv6.ip6table_nat);
+ if (!net->ipv6.ip6table_nat)
+ return;
+ ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops);
+ net->ipv6.ip6table_nat = NULL;
}
static struct pernet_operations ip6table_nat_net_ops = {
- .init = ip6table_nat_net_init,
.exit = ip6table_nat_net_exit,
};
static int __init ip6table_nat_init(void)
{
- int err;
+ int ret = register_pernet_subsys(&ip6table_nat_net_ops);
- err = register_pernet_subsys(&ip6table_nat_net_ops);
- if (err < 0)
- goto err1;
+ if (ret)
+ return ret;
- err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
- if (err < 0)
- goto err2;
- return 0;
-
-err2:
- unregister_pernet_subsys(&ip6table_nat_net_ops);
-err1:
- return err;
+ ret = ip6table_nat_table_init(&init_net);
+ if (ret)
+ unregister_pernet_subsys(&ip6table_nat_net_ops);
+ return ret;
}
static void __exit ip6table_nat_exit(void)
{
- nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
unregister_pernet_subsys(&ip6table_nat_net_ops);
}
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 9021963..d4bc564 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -9,12 +9,15 @@
#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
+static int __net_init ip6table_raw_table_init(struct net *net);
+
static const struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
.priority = NF_IP6_PRI_RAW,
+ .table_init = ip6table_raw_table_init,
};
/* The work comes in here from netfilter.c. */
@@ -27,26 +30,32 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb,
static struct nf_hook_ops *rawtable_ops __read_mostly;
-static int __net_init ip6table_raw_net_init(struct net *net)
+static int __net_init ip6table_raw_table_init(struct net *net)
{
struct ip6t_replace *repl;
+ int ret;
+
+ if (net->ipv6.ip6table_raw)
+ return 0;
repl = ip6t_alloc_initial_table(&packet_raw);
if (repl == NULL)
return -ENOMEM;
- net->ipv6.ip6table_raw =
- ip6t_register_table(net, &packet_raw, repl);
+ ret = ip6t_register_table(net, &packet_raw, repl, rawtable_ops,
+ &net->ipv6.ip6table_raw);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw);
+ return ret;
}
static void __net_exit ip6table_raw_net_exit(struct net *net)
{
- ip6t_unregister_table(net, net->ipv6.ip6table_raw);
+ if (!net->ipv6.ip6table_raw)
+ return;
+ ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops);
+ net->ipv6.ip6table_raw = NULL;
}
static struct pernet_operations ip6table_raw_net_ops = {
- .init = ip6table_raw_net_init,
.exit = ip6table_raw_net_exit,
};
@@ -54,28 +63,29 @@ static int __init ip6table_raw_init(void)
{
int ret;
+ /* Register hooks */
+ rawtable_ops = xt_hook_ops_alloc(&packet_raw, ip6table_raw_hook);
+ if (IS_ERR(rawtable_ops))
+ return PTR_ERR(rawtable_ops);
+
ret = register_pernet_subsys(&ip6table_raw_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(rawtable_ops);
return ret;
-
- /* Register hooks */
- rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook);
- if (IS_ERR(rawtable_ops)) {
- ret = PTR_ERR(rawtable_ops);
- goto cleanup_table;
}
- return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&ip6table_raw_net_ops);
+ ret = ip6table_raw_table_init(&init_net);
+ if (ret) {
+ unregister_pernet_subsys(&ip6table_raw_net_ops);
+ kfree(rawtable_ops);
+ }
return ret;
}
static void __exit ip6table_raw_fini(void)
{
- xt_hook_unlink(&packet_raw, rawtable_ops);
unregister_pernet_subsys(&ip6table_raw_net_ops);
+ kfree(rawtable_ops);
}
module_init(ip6table_raw_init);
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 0d856fe..cf26ccb 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -27,12 +27,15 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT)
+static int __net_init ip6table_security_table_init(struct net *net);
+
static const struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
.priority = NF_IP6_PRI_SECURITY,
+ .table_init = ip6table_security_table_init,
};
static unsigned int
@@ -44,26 +47,32 @@ ip6table_security_hook(void *priv, struct sk_buff *skb,
static struct nf_hook_ops *sectbl_ops __read_mostly;
-static int __net_init ip6table_security_net_init(struct net *net)
+static int __net_init ip6table_security_table_init(struct net *net)
{
struct ip6t_replace *repl;
+ int ret;
+
+ if (net->ipv6.ip6table_security)
+ return 0;
repl = ip6t_alloc_initial_table(&security_table);
if (repl == NULL)
return -ENOMEM;
- net->ipv6.ip6table_security =
- ip6t_register_table(net, &security_table, repl);
+ ret = ip6t_register_table(net, &security_table, repl, sectbl_ops,
+ &net->ipv6.ip6table_security);
kfree(repl);
- return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security);
+ return ret;
}
static void __net_exit ip6table_security_net_exit(struct net *net)
{
- ip6t_unregister_table(net, net->ipv6.ip6table_security);
+ if (!net->ipv6.ip6table_security)
+ return;
+ ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops);
+ net->ipv6.ip6table_security = NULL;
}
static struct pernet_operations ip6table_security_net_ops = {
- .init = ip6table_security_net_init,
.exit = ip6table_security_net_exit,
};
@@ -71,27 +80,28 @@ static int __init ip6table_security_init(void)
{
int ret;
+ sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook);
+ if (IS_ERR(sectbl_ops))
+ return PTR_ERR(sectbl_ops);
+
ret = register_pernet_subsys(&ip6table_security_net_ops);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(sectbl_ops);
return ret;
-
- sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook);
- if (IS_ERR(sectbl_ops)) {
- ret = PTR_ERR(sectbl_ops);
- goto cleanup_table;
}
- return ret;
-
-cleanup_table:
- unregister_pernet_subsys(&ip6table_security_net_ops);
+ ret = ip6table_security_table_init(&init_net);
+ if (ret) {
+ unregister_pernet_subsys(&ip6table_security_net_ops);
+ kfree(sectbl_ops);
+ }
return ret;
}
static void __exit ip6table_security_fini(void)
{
- xt_hook_unlink(&security_table, sectbl_ops);
unregister_pernet_subsys(&ip6table_security_net_ops);
+ kfree(sectbl_ops);
}
module_init(ip6table_security_init);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index c8a0b7d..d0cd2b9 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -694,12 +694,45 @@ EXPORT_SYMBOL(xt_free_table_info);
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
const char *name)
{
- struct xt_table *t;
+ struct xt_table *t, *found = NULL;
mutex_lock(&xt[af].mutex);
list_for_each_entry(t, &net->xt.tables[af], list)
if (strcmp(t->name, name) == 0 && try_module_get(t->me))
return t;
+
+ if (net == &init_net)
+ goto out;
+
+ /* Table doesn't exist in this netns, re-try init */
+ list_for_each_entry(t, &init_net.xt.tables[af], list) {
+ if (strcmp(t->name, name))
+ continue;
+ if (!try_module_get(t->me))
+ return NULL;
+
+ mutex_unlock(&xt[af].mutex);
+ if (t->table_init(net) != 0) {
+ module_put(t->me);
+ return NULL;
+ }
+
+ found = t;
+
+ mutex_lock(&xt[af].mutex);
+ break;
+ }
+
+ if (!found)
+ goto out;
+
+ /* and once again: */
+ list_for_each_entry(t, &net->xt.tables[af], list)
+ if (strcmp(t->name, name) == 0)
+ return t;
+
+ module_put(found->me);
+ out:
mutex_unlock(&xt[af].mutex);
return NULL;
}
@@ -1170,20 +1203,20 @@ static const struct file_operations xt_target_ops = {
#endif /* CONFIG_PROC_FS */
/**
- * xt_hook_link - set up hooks for a new table
+ * xt_hook_ops_alloc - set up hooks for a new table
* @table: table with metadata needed to set up hooks
* @fn: Hook function
*
- * This function will take care of creating and registering the necessary
- * Netfilter hooks for XT tables.
+ * This function will create the nf_hook_ops that the x_table needs
+ * to hand to xt_hook_link_net().
*/
-struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn)
+struct nf_hook_ops *
+xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
{
unsigned int hook_mask = table->valid_hooks;
uint8_t i, num_hooks = hweight32(hook_mask);
uint8_t hooknum;
struct nf_hook_ops *ops;
- int ret;
ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL);
if (ops == NULL)
@@ -1200,27 +1233,9 @@ struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn)
++i;
}
- ret = nf_register_hooks(ops, num_hooks);
- if (ret < 0) {
- kfree(ops);
- return ERR_PTR(ret);
- }
-
return ops;
}
-EXPORT_SYMBOL_GPL(xt_hook_link);
-
-/**
- * xt_hook_unlink - remove hooks for a table
- * @ops: nf_hook_ops array as returned by nf_hook_link
- * @hook_mask: the very same mask that was passed to nf_hook_link
- */
-void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops)
-{
- nf_unregister_hooks(ops, hweight32(table->valid_hooks));
- kfree(ops);
-}
-EXPORT_SYMBOL_GPL(xt_hook_unlink);
+EXPORT_SYMBOL_GPL(xt_hook_ops_alloc);
int xt_proto_init(struct net *net, u_int8_t af)
{
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 04/12] netfilter: defrag: only register defrag functionality if needed
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (2 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 03/12] netfilter: xtables: don't register table hooks in namespace at init time Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 05/12] netfilter: nat: add dependencies on conntrack module Florian Westphal
` (8 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
nf_defrag modules for ipv4 and ipv6 export an empty stub function.
Any module that needs the defragmentation hooks registered simply 'calls'
this empty function to create a 'phony' module dependency -- modprobe magic
will make sure the appropriate defrag module is loaded.
This extends defragmentation to delay the defragmentation hook registration
until the functionality is requested within a network namespace instead of
module load time for all namespaces.
Hooks are only un-registered on module unload or when a namespace that used
such defrag functionality exits.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
no changes since v2
include/net/netfilter/ipv4/nf_defrag_ipv4.h | 3 +-
include/net/netfilter/ipv6/nf_defrag_ipv6.h | 3 +-
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 7 +++-
net/ipv4/netfilter/nf_defrag_ipv4.c | 49 +++++++++++++++++++++++--
net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 7 +++-
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 50 +++++++++++++++++++++++---
net/netfilter/xt_TPROXY.c | 15 +++++---
net/netfilter/xt_socket.c | 33 ++++++++++++++---
8 files changed, 146 insertions(+), 21 deletions(-)
diff --git a/include/net/netfilter/ipv4/nf_defrag_ipv4.h b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
index f01ef20..db405f7 100644
--- a/include/net/netfilter/ipv4/nf_defrag_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
@@ -1,6 +1,7 @@
#ifndef _NF_DEFRAG_IPV4_H
#define _NF_DEFRAG_IPV4_H
-void nf_defrag_ipv4_enable(void);
+struct net;
+int nf_defrag_ipv4_enable(struct net *);
#endif /* _NF_DEFRAG_IPV4_H */
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index ddf162f..7664efe 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -1,7 +1,8 @@
#ifndef _NF_DEFRAG_IPV6_H
#define _NF_DEFRAG_IPV6_H
-void nf_defrag_ipv6_enable(void);
+struct net;
+int nf_defrag_ipv6_enable(struct net *);
int nf_ct_frag6_init(void);
void nf_ct_frag6_cleanup(void);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 8ed9777..909681e 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -385,6 +385,12 @@ static int ipv4_hooks_register(struct net *net)
if (cnet->users > 1)
goto out_unlock;
+ err = nf_defrag_ipv4_enable(net);
+ if (err) {
+ cnet->users = 0;
+ goto out_unlock;
+ }
+
err = nf_register_net_hooks(net, ipv4_conntrack_ops,
ARRAY_SIZE(ipv4_conntrack_ops));
@@ -490,7 +496,6 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
int ret = 0;
need_conntrack();
- nf_defrag_ipv4_enable();
ret = nf_register_sockopt(&so_getorigdst);
if (ret < 0) {
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f6..c812bf5 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -11,6 +11,7 @@
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/skbuff.h>
+#include <net/netns/generic.h>
#include <net/route.h>
#include <net/ip.h>
@@ -22,6 +23,13 @@
#endif
#include <net/netfilter/nf_conntrack_zones.h>
+static int defrag4_net_id __read_mostly;
+static DEFINE_MUTEX(defrag4_mutex);
+
+struct defrag4_net {
+ bool enabled;
+};
+
static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
u_int32_t user)
{
@@ -106,18 +114,53 @@ static struct nf_hook_ops ipv4_defrag_ops[] = {
},
};
+static void __net_exit defrag4_net_exit(struct net *net)
+{
+ struct defrag4_net *n = net_generic(net, defrag4_net_id);
+
+ if (n->enabled)
+ nf_unregister_net_hooks(net, ipv4_defrag_ops,
+ ARRAY_SIZE(ipv4_defrag_ops));
+}
+
+static struct pernet_operations defrag4_net_ops = {
+ .exit = defrag4_net_exit,
+ .id = &defrag4_net_id,
+ .size = sizeof(struct defrag4_net),
+};
+
static int __init nf_defrag_init(void)
{
- return nf_register_hooks(ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops));
+ return register_pernet_subsys(&defrag4_net_ops);
}
static void __exit nf_defrag_fini(void)
{
- nf_unregister_hooks(ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops));
+ unregister_pernet_subsys(&defrag4_net_ops);
}
-void nf_defrag_ipv4_enable(void)
+int nf_defrag_ipv4_enable(struct net *net)
{
+ struct defrag4_net *n = net_generic(net, defrag4_net_id);
+ int err = 0;
+
+ might_sleep();
+
+ if (n->enabled)
+ return 0;
+
+ mutex_lock(&defrag4_mutex);
+ if (n->enabled)
+ goto out_unlock;
+
+ err = nf_register_net_hooks(net, ipv4_defrag_ops,
+ ARRAY_SIZE(ipv4_defrag_ops));
+ if (err == 0)
+ n->enabled = true;
+
+ out_unlock:
+ mutex_unlock(&defrag4_mutex);
+ return err;
}
EXPORT_SYMBOL_GPL(nf_defrag_ipv4_enable);
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 92a090f..1e6a5f4 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -325,6 +325,12 @@ static int ipv6_hooks_register(struct net *net)
if (cnet->users > 1)
goto out_unlock;
+ err = nf_defrag_ipv6_enable(net);
+ if (err < 0) {
+ cnet->users = 0;
+ goto out_unlock;
+ }
+
err = nf_register_net_hooks(net, ipv6_conntrack_ops,
ARRAY_SIZE(ipv6_conntrack_ops));
if (err)
@@ -430,7 +436,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
int ret = 0;
need_conntrack();
- nf_defrag_ipv6_enable();
ret = nf_register_sockopt(&so_getorigdst6);
if (ret < 0) {
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index f7aab5a..b3c10f4 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -30,6 +30,13 @@
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+static int defrag6_net_id __read_mostly;
+static DEFINE_MUTEX(defrag6_mutex);
+
+struct defrag6_net {
+ bool enabled;
+};
+
static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
@@ -87,6 +94,21 @@ static struct nf_hook_ops ipv6_defrag_ops[] = {
},
};
+static void __net_exit defrag6_net_exit(struct net *net)
+{
+ struct defrag6_net *n = net_generic(net, defrag6_net_id);
+
+ if (n->enabled)
+ nf_unregister_net_hooks(net, ipv6_defrag_ops,
+ ARRAY_SIZE(ipv6_defrag_ops));
+}
+
+static struct pernet_operations defrag6_net_ops = {
+ .exit = defrag6_net_exit,
+ .id = &defrag6_net_id,
+ .size = sizeof(struct defrag6_net),
+};
+
static int __init nf_defrag_init(void)
{
int ret = 0;
@@ -96,9 +118,9 @@ static int __init nf_defrag_init(void)
pr_err("nf_defrag_ipv6: can't initialize frag6.\n");
return ret;
}
- ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+ ret = register_pernet_subsys(&defrag6_net_ops);
if (ret < 0) {
- pr_err("nf_defrag_ipv6: can't register hooks\n");
+ pr_err("nf_defrag_ipv6: can't register pernet ops\n");
goto cleanup_frag6;
}
return ret;
@@ -111,12 +133,32 @@ cleanup_frag6:
static void __exit nf_defrag_fini(void)
{
- nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+ unregister_pernet_subsys(&defrag6_net_ops);
nf_ct_frag6_cleanup();
}
-void nf_defrag_ipv6_enable(void)
+int nf_defrag_ipv6_enable(struct net *net)
{
+ struct defrag6_net *n = net_generic(net, defrag6_net_id);
+ int err = 0;
+
+ might_sleep();
+
+ if (n->enabled)
+ return 0;
+
+ mutex_lock(&defrag6_mutex);
+ if (n->enabled)
+ goto out_unlock;
+
+ err = nf_register_net_hooks(net, ipv6_defrag_ops,
+ ARRAY_SIZE(ipv6_defrag_ops));
+ if (err == 0)
+ n->enabled = true;
+
+ out_unlock:
+ mutex_unlock(&defrag6_mutex);
+ return err;
}
EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable);
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 3ab591e..f091244 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -516,6 +516,11 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
static int tproxy_tg6_check(const struct xt_tgchk_param *par)
{
const struct ip6t_ip6 *i = par->entryinfo;
+ int err;
+
+ err = nf_defrag_ipv6_enable(par->net);
+ if (err)
+ return err;
if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) &&
!(i->invflags & IP6T_INV_PROTO))
@@ -530,6 +535,11 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par)
static int tproxy_tg4_check(const struct xt_tgchk_param *par)
{
const struct ipt_ip *i = par->entryinfo;
+ int err;
+
+ err = nf_defrag_ipv4_enable(par->net);
+ if (err)
+ return err;
if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
&& !(i->invflags & IPT_INV_PROTO))
@@ -581,11 +591,6 @@ static struct xt_target tproxy_tg_reg[] __read_mostly = {
static int __init tproxy_tg_init(void)
{
- nf_defrag_ipv4_enable();
-#ifdef XT_TPROXY_HAVE_IPV6
- nf_defrag_ipv6_enable();
-#endif
-
return xt_register_targets(tproxy_tg_reg, ARRAY_SIZE(tproxy_tg_reg));
}
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 2ec08f0..d0f0064 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -418,9 +418,28 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
}
#endif
+static int socket_mt_enable_defrag(struct net *net, int family)
+{
+ switch (family) {
+ case NFPROTO_IPV4:
+ return nf_defrag_ipv4_enable(net);
+#ifdef XT_SOCKET_HAVE_IPV6
+ case NFPROTO_IPV6:
+ return nf_defrag_ipv6_enable(net);
+#endif
+ }
+ WARN_ONCE(1, "Unknown family %d\n", family);
+ return 0;
+}
+
static int socket_mt_v1_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
+ int err;
+
+ err = socket_mt_enable_defrag(par->net, par->family);
+ if (err)
+ return err;
if (info->flags & ~XT_SOCKET_FLAGS_V1) {
pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1);
@@ -432,6 +451,11 @@ static int socket_mt_v1_check(const struct xt_mtchk_param *par)
static int socket_mt_v2_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo;
+ int err;
+
+ err = socket_mt_enable_defrag(par->net, par->family);
+ if (err)
+ return err;
if (info->flags & ~XT_SOCKET_FLAGS_V2) {
pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2);
@@ -444,7 +468,11 @@ static int socket_mt_v3_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo3 *info =
(struct xt_socket_mtinfo3 *)par->matchinfo;
+ int err;
+ err = socket_mt_enable_defrag(par->net, par->family);
+ if (err)
+ return err;
if (info->flags & ~XT_SOCKET_FLAGS_V3) {
pr_info("unknown flags 0x%x\n",
info->flags & ~XT_SOCKET_FLAGS_V3);
@@ -539,11 +567,6 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
static int __init socket_mt_init(void)
{
- nf_defrag_ipv4_enable();
-#ifdef XT_SOCKET_HAVE_IPV6
- nf_defrag_ipv6_enable();
-#endif
-
return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg));
}
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 05/12] netfilter: nat: add dependencies on conntrack module
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (3 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 04/12] netfilter: defrag: only register defrag functionality if needed Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 06/12] netfilter: bridge: register hooks only when bridge interface is added Florian Westphal
` (7 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
MASQUERADE, S/DNAT and REDIRECT already call functions that depend on the
conntrack module.
However, since the conntrack hooks are now registered in a lazy fashion
(i.e., only when needed) a symbol reference is not enough.
Thus, when something is added to a nat table, make sure that it will see
packets by calling nf_ct_netns_get() which will register the conntrack
hooks in the current netns.
An alternative would be to add these dependencies to the NAT table.
However, that has problems when using non-modular builds -- we might
register e.g. ipv6 conntrack before its initcall has run, leading to NULL
deref crashes since its per-netns storage has not yet been allocated.
Adding the dependency in the modules instead has the advantage that nat
table also does not register its hooks until rules are added.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
no changes since v2.
net/ipv4/netfilter/ipt_MASQUERADE.c | 8 +++++++-
net/netfilter/xt_NETMAP.c | 11 +++++++++--
net/netfilter/xt_REDIRECT.c | 12 ++++++++++--
net/netfilter/xt_nat.c | 18 +++++++++++++++++-
4 files changed, 43 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index da7f02a..e758e53 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -41,7 +41,7 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par)
pr_debug("bad rangesize %u\n", mr->rangesize);
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(par->net, par->family);
}
static unsigned int
@@ -58,6 +58,11 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
return nf_nat_masquerade_ipv4(skb, par->hooknum, &range, par->out);
}
+static void masquerade_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_ct_netns_put(par->net, par->family);
+}
+
static struct xt_target masquerade_tg_reg __read_mostly = {
.name = "MASQUERADE",
.family = NFPROTO_IPV4,
@@ -66,6 +71,7 @@ static struct xt_target masquerade_tg_reg __read_mostly = {
.table = "nat",
.hooks = 1 << NF_INET_POST_ROUTING,
.checkentry = masquerade_tg_check,
+ .destroy = masquerade_tg_destroy,
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c
index b253e07..222458c 100644
--- a/net/netfilter/xt_NETMAP.c
+++ b/net/netfilter/xt_NETMAP.c
@@ -60,7 +60,12 @@ static int netmap_tg6_checkentry(const struct xt_tgchk_param *par)
if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
return -EINVAL;
- return 0;
+ return nf_ct_netns_get(par->net, par->family);
+}
+
+static void netmap_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_ct_netns_put(par->net, par->family);
}
static unsigned int
@@ -111,7 +116,7 @@ static int netmap_tg4_check(const struct xt_tgchk_param *par)
pr_debug("bad rangesize %u.\n", mr->rangesize);
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(par->net, par->family);
}
static struct xt_target netmap_tg_reg[] __read_mostly = {
@@ -127,6 +132,7 @@ static struct xt_target netmap_tg_reg[] __read_mostly = {
(1 << NF_INET_LOCAL_OUT) |
(1 << NF_INET_LOCAL_IN),
.checkentry = netmap_tg6_checkentry,
+ .destroy = netmap_tg_destroy,
.me = THIS_MODULE,
},
{
@@ -141,6 +147,7 @@ static struct xt_target netmap_tg_reg[] __read_mostly = {
(1 << NF_INET_LOCAL_OUT) |
(1 << NF_INET_LOCAL_IN),
.checkentry = netmap_tg4_check,
+ .destroy = netmap_tg_destroy,
.me = THIS_MODULE,
},
};
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index 03f0b37..1406516 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -40,7 +40,13 @@ static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
if (range->flags & NF_NAT_RANGE_MAP_IPS)
return -EINVAL;
- return 0;
+
+ return nf_ct_netns_get(par->net, par->family);
+}
+
+static void redirect_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_ct_netns_put(par->net, par->family);
}
/* FIXME: Take multiple ranges --RR */
@@ -56,7 +62,7 @@ static int redirect_tg4_check(const struct xt_tgchk_param *par)
pr_debug("bad rangesize %u.\n", mr->rangesize);
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(par->net, par->family);
}
static unsigned int
@@ -72,6 +78,7 @@ static struct xt_target redirect_tg_reg[] __read_mostly = {
.revision = 0,
.table = "nat",
.checkentry = redirect_tg6_checkentry,
+ .destroy = redirect_tg_destroy,
.target = redirect_tg6,
.targetsize = sizeof(struct nf_nat_range),
.hooks = (1 << NF_INET_PRE_ROUTING) |
@@ -85,6 +92,7 @@ static struct xt_target redirect_tg_reg[] __read_mostly = {
.table = "nat",
.target = redirect_tg4,
.checkentry = redirect_tg4_check,
+ .destroy = redirect_tg_destroy,
.targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_LOCAL_OUT),
diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c
index bea7464..8107b3e 100644
--- a/net/netfilter/xt_nat.c
+++ b/net/netfilter/xt_nat.c
@@ -23,7 +23,17 @@ static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par)
par->target->name);
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(par->net, par->family);
+}
+
+static int xt_nat_checkentry(const struct xt_tgchk_param *par)
+{
+ return nf_ct_netns_get(par->net, par->family);
+}
+
+static void xt_nat_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_ct_netns_put(par->net, par->family);
}
static void xt_nat_convert_range(struct nf_nat_range *dst,
@@ -106,6 +116,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = {
.name = "SNAT",
.revision = 0,
.checkentry = xt_nat_checkentry_v0,
+ .destroy = xt_nat_destroy,
.target = xt_snat_target_v0,
.targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.family = NFPROTO_IPV4,
@@ -118,6 +129,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = {
.name = "DNAT",
.revision = 0,
.checkentry = xt_nat_checkentry_v0,
+ .destroy = xt_nat_destroy,
.target = xt_dnat_target_v0,
.targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
.family = NFPROTO_IPV4,
@@ -129,6 +141,8 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = {
{
.name = "SNAT",
.revision = 1,
+ .checkentry = xt_nat_checkentry,
+ .destroy = xt_nat_destroy,
.target = xt_snat_target_v1,
.targetsize = sizeof(struct nf_nat_range),
.table = "nat",
@@ -139,6 +153,8 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = {
{
.name = "DNAT",
.revision = 1,
+ .checkentry = xt_nat_checkentry,
+ .destroy = xt_nat_destroy,
.target = xt_dnat_target_v1,
.targetsize = sizeof(struct nf_nat_range),
.table = "nat",
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 06/12] netfilter: bridge: register hooks only when bridge interface is added
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (4 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 05/12] netfilter: nat: add dependencies on conntrack module Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 07/12] netfilter: don't call nf_hook_state_init/_hook_slow unless needed Florian Westphal
` (6 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
This moves the last 'common' hooks to a 'register only when needed' scheme.
We use a device notifier to register the 'call-iptables' netfilter hooks
only once a bridge gets added.
This means that if the initial namespace uses a bridge, newly created
network namespaces no longer 'inherit' the PRE_ROUTING ipt_sabotage hook,
instead it will only be registered in that network namespace if a bridge
is added within that namespace.
After this patch, only a few modules still use global hooks:
- bridge PF_BRIDGE hooks
- ipvs
- CLUSTER match (deprecated)
- SYNPROXY
As long as these modules are not loaded/used, a new network namespace has
empty hook list and NF_HOOK() will boil down to single list_empty test even
if initial namespace does packet filtering, conntrack, etc.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
no changes since v2
net/bridge/br_netfilter_hooks.c | 68 +++++++++++++++++++++++++++++++++++++++--
1 file changed, 65 insertions(+), 3 deletions(-)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 7ddbe7e..44114a9 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -37,6 +37,7 @@
#include <net/addrconf.h>
#include <net/route.h>
#include <net/netfilter/br_netfilter.h>
+#include <net/netns/generic.h>
#include <asm/uaccess.h>
#include "br_private.h"
@@ -44,6 +45,12 @@
#include <linux/sysctl.h>
#endif
+static int brnf_net_id __read_mostly;
+
+struct brnf_net {
+ bool enabled;
+};
+
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *brnf_sysctl_header;
static int brnf_call_iptables __read_mostly = 1;
@@ -938,6 +945,53 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
},
};
+static int brnf_device_event(struct notifier_block *unused, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct brnf_net *brnet;
+ struct net *net;
+ int ret;
+
+ if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE))
+ return NOTIFY_DONE;
+
+ ASSERT_RTNL();
+
+ net = dev_net(dev);
+ brnet = net_generic(net, brnf_net_id);
+ if (brnet->enabled)
+ return NOTIFY_OK;
+
+ ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ if (ret)
+ return NOTIFY_BAD;
+
+ brnet->enabled = true;
+ return NOTIFY_OK;
+}
+
+static void __net_exit brnf_exit_net(struct net *net)
+{
+ struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+ if (!brnet->enabled)
+ return;
+
+ nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ brnet->enabled = false;
+}
+
+static struct pernet_operations brnf_net_ops __read_mostly = {
+ .exit = brnf_exit_net,
+ .id = &brnf_net_id,
+ .size = sizeof(struct brnf_net),
+};
+
+static struct notifier_block brnf_notifier __read_mostly = {
+ .notifier_call = brnf_device_event,
+};
+
#ifdef CONFIG_SYSCTL
static
int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
@@ -1003,16 +1057,23 @@ static int __init br_netfilter_init(void)
{
int ret;
- ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ ret = register_pernet_subsys(&brnf_net_ops);
if (ret < 0)
return ret;
+ ret = register_netdevice_notifier(&brnf_notifier);
+ if (ret < 0) {
+ unregister_pernet_subsys(&brnf_net_ops);
+ return ret;
+ }
+
#ifdef CONFIG_SYSCTL
brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table);
if (brnf_sysctl_header == NULL) {
printk(KERN_WARNING
"br_netfilter: can't register to sysctl.\n");
- nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ unregister_netdevice_notifier(&brnf_notifier);
+ unregister_pernet_subsys(&brnf_net_ops);
return -ENOMEM;
}
#endif
@@ -1024,7 +1085,8 @@ static int __init br_netfilter_init(void)
static void __exit br_netfilter_fini(void)
{
RCU_INIT_POINTER(nf_br_ops, NULL);
- nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+ unregister_netdevice_notifier(&brnf_notifier);
+ unregister_pernet_subsys(&brnf_net_ops);
#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(brnf_sysctl_header);
#endif
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 07/12] netfilter: don't call nf_hook_state_init/_hook_slow unless needed
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (5 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 06/12] netfilter: bridge: register hooks only when bridge interface is added Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 08/12] nftables: add conntrack dependencies for nat/masq/redir expressions Florian Westphal
` (5 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
With the previous patches in place, a netns nf_hook_list might be empty,
even if e.g. init_net performs filtering/conntrack.
Thus, change nf_hook_thresh to check the hook_list as well before
initializing hook_state and calling nf_hook_slow().
We still make use of static keys, if no netfilter hooks are loaded we can
elide further testing since list is guaranteed to be empty.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
no changes since v2
include/linux/netfilter.h | 29 +++++++++++------------------
1 file changed, 11 insertions(+), 18 deletions(-)
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 0ad5567..9230f9a 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
#ifdef HAVE_JUMP_LABEL
extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
-static inline bool nf_hook_list_active(struct list_head *hook_list,
- u_int8_t pf, unsigned int hook)
-{
- if (__builtin_constant_p(pf) &&
- __builtin_constant_p(hook))
- return static_key_false(&nf_hooks_needed[pf][hook]);
-
- return !list_empty(hook_list);
-}
-#else
-static inline bool nf_hook_list_active(struct list_head *hook_list,
- u_int8_t pf, unsigned int hook)
-{
- return !list_empty(hook_list);
-}
#endif
int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
@@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
int (*okfn)(struct net *, struct sock *, struct sk_buff *),
int thresh)
{
- struct list_head *hook_list = &net->nf.hooks[pf][hook];
+ struct list_head *hook_list;
+
+#ifdef HAVE_JUMP_LABEL
+ if (__builtin_constant_p(pf) &&
+ __builtin_constant_p(hook) &&
+ !static_key_false(&nf_hooks_needed[pf][hook]))
+ return 1;
+#endif
+
+ hook_list = &net->nf.hooks[pf][hook];
- if (nf_hook_list_active(hook_list, pf, hook)) {
+ if (!list_empty(hook_list)) {
struct nf_hook_state state;
nf_hook_state_init(&state, hook_list, hook, thresh,
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 08/12] nftables: add conntrack dependencies for nat/masq/redir expressions
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (6 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 07/12] netfilter: don't call nf_hook_state_init/_hook_slow unless needed Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 09/12] nfnetlink: add nfnl_dereference_protected helper Florian Westphal
` (4 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
so that conntrack core will add the needed hooks in this namespace.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
no changes since v2.
net/ipv4/netfilter/nft_masq_ipv4.c | 7 +++++++
net/ipv4/netfilter/nft_redir_ipv4.c | 7 +++++++
net/ipv6/netfilter/nft_masq_ipv6.c | 7 +++++++
net/ipv6/netfilter/nft_redir_ipv6.c | 7 +++++++
net/netfilter/nft_masq.c | 5 +++--
net/netfilter/nft_nat.c | 11 ++++++++++-
net/netfilter/nft_redir.c | 2 +-
7 files changed, 42 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index b72ffc5..ee5bb98 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -30,12 +30,19 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
&range, pkt->out);
}
+static void
+nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
+}
+
static struct nft_expr_type nft_masq_ipv4_type;
static const struct nft_expr_ops nft_masq_ipv4_ops = {
.type = &nft_masq_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
.eval = nft_masq_ipv4_eval,
.init = nft_masq_init,
+ .destroy = nft_masq_ipv4_destroy,
.dump = nft_masq_dump,
.validate = nft_masq_validate,
};
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index c09d438..862eb5a 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -39,12 +39,19 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
pkt->hook);
}
+static void
+nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
+}
+
static struct nft_expr_type nft_redir_ipv4_type;
static const struct nft_expr_ops nft_redir_ipv4_ops = {
.type = &nft_redir_ipv4_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
.eval = nft_redir_ipv4_eval,
.init = nft_redir_init,
+ .destroy = nft_redir_ipv4_destroy,
.dump = nft_redir_dump,
.validate = nft_redir_validate,
};
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index cd1ac16..a8b3626 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -30,12 +30,19 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
}
+static void
+nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
+}
+
static struct nft_expr_type nft_masq_ipv6_type;
static const struct nft_expr_ops nft_masq_ipv6_ops = {
.type = &nft_masq_ipv6_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
.eval = nft_masq_ipv6_eval,
.init = nft_masq_init,
+ .destroy = nft_masq_ipv6_destroy,
.dump = nft_masq_dump,
.validate = nft_masq_validate,
};
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index aca44e8..ef673cd 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -38,12 +38,19 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->hook);
}
+static void
+nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
+}
+
static struct nft_expr_type nft_redir_ipv6_type;
static const struct nft_expr_ops nft_redir_ipv6_ops = {
.type = &nft_redir_ipv6_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
.eval = nft_redir_ipv6_eval,
.init = nft_redir_init,
+ .destroy = nft_redir_ipv6_destroy,
.dump = nft_redir_dump,
.validate = nft_redir_validate,
};
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 9aea747..c7269c3 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -48,13 +48,14 @@ int nft_masq_init(const struct nft_ctx *ctx,
return err;
if (tb[NFTA_MASQ_FLAGS] == NULL)
- return 0;
+ goto out;
priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
if (priv->flags & ~NF_NAT_RANGE_MASK)
return -EINVAL;
+ out:
+ return nf_ct_netns_get(ctx->net, ctx->afi->family);
- return 0;
}
EXPORT_SYMBOL_GPL(nft_masq_init);
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index ee2d717..19a7bf3 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -209,7 +209,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(ctx->net, family);
}
static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -257,12 +257,21 @@ nla_put_failure:
return -1;
}
+static void
+nft_nat_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ const struct nft_nat *priv = nft_expr_priv(expr);
+
+ nf_ct_netns_put(ctx->net, priv->family);
+}
+
static struct nft_expr_type nft_nat_type;
static const struct nft_expr_ops nft_nat_ops = {
.type = &nft_nat_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
.eval = nft_nat_eval,
.init = nft_nat_init,
+ .destroy = nft_nat_destroy,
.dump = nft_nat_dump,
.validate = nft_nat_validate,
};
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 03f7bf4..f8227ec 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -79,7 +79,7 @@ int nft_redir_init(const struct nft_ctx *ctx,
return -EINVAL;
}
- return 0;
+ return nf_ct_netns_get(ctx->net, ctx->afi->family);
}
EXPORT_SYMBOL_GPL(nft_redir_init);
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 09/12] nfnetlink: add nfnl_dereference_protected helper
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (7 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 08/12] nftables: add conntrack dependencies for nat/masq/redir expressions Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-18 10:39 ` Pablo Neira Ayuso
2015-12-03 9:49 ` [PATCH v3 nf-next 10/12] netfilter: ctnetlink: make ctnetlink bind register conntrack hooks Florian Westphal
` (3 subsequent siblings)
12 siblings, 1 reply; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
to avoid overly long line in followup patch.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
not part of v2 series.
net/netfilter/nfnetlink.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 46453ab..197b2c6 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -33,6 +33,10 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER);
+#define nfnl_dereference_protected(id) \
+ rcu_dereference_protected(table[(id)].subsys, \
+ lockdep_nfnl_is_held((id)))
+
static char __initdata nfversion[] = "0.30";
static struct {
@@ -207,8 +211,7 @@ replay:
} else {
rcu_read_unlock();
nfnl_lock(subsys_id);
- if (rcu_dereference_protected(table[subsys_id].subsys,
- lockdep_is_held(&table[subsys_id].mutex)) != ss ||
+ if (nfnl_dereference_protected(subsys_id) != ss ||
nfnetlink_find_client(type, ss) != nc)
err = -EAGAIN;
else if (nc->call)
@@ -298,15 +301,13 @@ replay:
skb->sk = oskb->sk;
nfnl_lock(subsys_id);
- ss = rcu_dereference_protected(table[subsys_id].subsys,
- lockdep_is_held(&table[subsys_id].mutex));
+ ss = nfnl_dereference_protected(subsys_id);
if (!ss) {
#ifdef CONFIG_MODULES
nfnl_unlock(subsys_id);
request_module("nfnetlink-subsys-%d", subsys_id);
nfnl_lock(subsys_id);
- ss = rcu_dereference_protected(table[subsys_id].subsys,
- lockdep_is_held(&table[subsys_id].mutex));
+ ss = nfnl_dereference_protected(subsys_id);
if (!ss)
#endif
{
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 10/12] netfilter: ctnetlink: make ctnetlink bind register conntrack hooks
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (8 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 09/12] nfnetlink: add nfnl_dereference_protected helper Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 11/12] netfilter: hook up nfnetlink log/queue to " Florian Westphal
` (2 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
several problems remain even after this patch:
1. conntrack -E followed by a 'modprobe nf_conntrack_ipv4' will
*not* register ipv4 conntrack hooks (i.e., there will be no output) anymore.
2. since ctnetlink has no dependencies on nf_conntrack_xxx its possible
to rmmod nf_conntrack_xxx while event listener is running which means the
tracker has to remove hooks on netns destruction.
Both issues are addressed in followup patches.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
not part of v2 series.
This is a separate patch to ease review.
include/linux/netfilter/nfnetlink.h | 1 +
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 17 ++++-
net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 17 ++++-
net/netfilter/nf_conntrack_netlink.c | 86 ++++++++++++++++++++++++++
net/netfilter/nfnetlink.c | 35 ++++++++---
5 files changed, 146 insertions(+), 10 deletions(-)
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 249d1bb..9049c6a 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -28,6 +28,7 @@ struct nfnetlink_subsystem {
const struct nfnl_callback *cb; /* callback for individual types */
int (*commit)(struct sk_buff *skb);
int (*abort)(struct sk_buff *skb);
+ int (*bind)(struct net *net);
};
int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 909681e..7fcccf3 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -401,12 +401,25 @@ static int ipv4_hooks_register(struct net *net)
return err;
}
+static void ipv4_hooks_unregister_force(struct net *net)
+{
+ struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
+
+ mutex_lock(®ister_ipv4_hooks);
+ if (cnet->users) {
+ cnet->users = 0;
+ nf_unregister_net_hooks(net, ipv4_conntrack_ops,
+ ARRAY_SIZE(ipv4_conntrack_ops));
+ }
+ mutex_unlock(®ister_ipv4_hooks);
+}
+
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)
+ if (cnet->users > 0 && --cnet->users == 0)
nf_unregister_net_hooks(net, ipv4_conntrack_ops,
ARRAY_SIZE(ipv4_conntrack_ops));
mutex_unlock(®ister_ipv4_hooks);
@@ -478,6 +491,8 @@ out_tcp:
static void ipv4_net_exit(struct net *net)
{
+ ipv4_hooks_unregister_force(net);
+
nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp);
nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4);
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 1e6a5f4..f3b422b 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -340,12 +340,25 @@ static int ipv6_hooks_register(struct net *net)
return err;
}
+static void ipv6_hooks_unregister_force(struct net *net)
+{
+ struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
+
+ mutex_lock(®ister_ipv6_hooks);
+ if (cnet->users) {
+ cnet->users = 0;
+ nf_unregister_net_hooks(net, ipv6_conntrack_ops,
+ ARRAY_SIZE(ipv6_conntrack_ops));
+ }
+ mutex_unlock(®ister_ipv6_hooks);
+}
+
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)
+ if (cnet->users > 0 && --cnet->users == 0)
nf_unregister_net_hooks(net, ipv6_conntrack_ops,
ARRAY_SIZE(ipv6_conntrack_ops));
mutex_unlock(®ister_ipv6_hooks);
@@ -418,6 +431,8 @@ static int ipv6_net_init(struct net *net)
static void ipv6_net_exit(struct net *net)
{
+ ipv6_hooks_unregister_force(net);
+
nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6);
nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9f52729..b8a4067 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -57,6 +57,11 @@
MODULE_LICENSE("GPL");
static char __initdata version[] = "0.93";
+static int ctnetlink_net_id __read_mostly;
+
+struct ctnl_net {
+ DECLARE_BITMAP(enabled, NFPROTO_NUMPROTO);
+};
static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb,
@@ -2133,6 +2138,50 @@ ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *mask);
+static int ctnl_bind(struct net *net)
+{
+ struct ctnl_net *ctnet = net_generic(net, ctnetlink_net_id);
+ int i;
+
+ might_sleep();
+
+ rcu_read_lock();
+
+ for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+ struct nf_conntrack_l3proto *l3proto;
+ int ret;
+
+ /* don't autoload modules; only ensure those present have
+ * their hooks registered.
+ */
+ l3proto = __nf_ct_l3proto_find(i);
+ if (!l3proto || !l3proto->net_ns_get)
+ continue;
+
+ if (test_and_set_bit(i, ctnet->enabled))
+ continue;
+
+ if (!try_module_get(l3proto->me))
+ continue;
+
+ rcu_read_unlock();
+
+ /* might sleep, l3proto can't go away, module ref held */
+ ret = l3proto->net_ns_get(net);
+
+ module_put(l3proto->me);
+
+ if (ret < 0)
+ clear_bit(i, ctnet->enabled);
+
+ rcu_read_lock();
+ }
+
+ rcu_read_unlock();
+
+ return 0;
+}
+
#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
static size_t
ctnetlink_glue_build_size(const struct nf_conn *ct)
@@ -3304,6 +3353,7 @@ static const struct nfnetlink_subsystem ctnl_subsys = {
.subsys_id = NFNL_SUBSYS_CTNETLINK,
.cb_count = IPCTNL_MSG_MAX,
.cb = ctnl_cb,
+ .bind = ctnl_bind,
};
static const struct nfnetlink_subsystem ctnl_exp_subsys = {
@@ -3311,6 +3361,7 @@ static const struct nfnetlink_subsystem ctnl_exp_subsys = {
.subsys_id = NFNL_SUBSYS_CTNETLINK_EXP,
.cb_count = IPCTNL_MSG_EXP_MAX,
.cb = ctnl_exp_cb,
+ .bind = ctnl_bind,
};
MODULE_ALIAS("ip_conntrack_netlink");
@@ -3346,10 +3397,43 @@ err_out:
static void ctnetlink_net_exit(struct net *net)
{
+ struct ctnl_net *ctnet = net_generic(net, ctnetlink_net_id);
+ int i;
+
#ifdef CONFIG_NF_CONNTRACK_EVENTS
nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp);
nf_conntrack_unregister_notifier(net, &ctnl_notifier);
#endif
+
+ might_sleep();
+
+ rcu_read_lock();
+
+ for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+ struct nf_conntrack_l3proto *l3proto;
+
+ if (!test_bit(i, ctnet->enabled))
+ continue;
+
+ l3proto = __nf_ct_l3proto_find(i);
+ /* module might have been unloaded, l3proto->net_ns_put
+ * must have been called by that modules' netns exit handler.
+ */
+ if (!l3proto)
+ continue;
+
+ if (!try_module_get(l3proto->me))
+ continue;
+
+ rcu_read_unlock();
+
+ l3proto->net_ns_put(net);
+ module_put(l3proto->me);
+
+ rcu_read_lock();
+ }
+
+ rcu_read_unlock();
}
static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
@@ -3363,6 +3447,8 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
static struct pernet_operations ctnetlink_net_ops = {
.init = ctnetlink_net_init,
.exit_batch = ctnetlink_net_exit_batch,
+ .id = &ctnetlink_net_id,
+ .size = sizeof(struct ctnl_net),
};
static int __init ctnetlink_init(void)
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 197b2c6..63a16e6 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -481,11 +481,11 @@ static void nfnetlink_rcv(struct sk_buff *skb)
}
}
-#ifdef CONFIG_MODULES
static int nfnetlink_bind(struct net *net, int group)
{
const struct nfnetlink_subsystem *ss;
- int type;
+ int type, ret;
+ u8 subsys_id;
if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
return 0;
@@ -494,12 +494,33 @@ static int nfnetlink_bind(struct net *net, int group)
rcu_read_lock();
ss = nfnetlink_get_subsys(type << 8);
- rcu_read_unlock();
- if (!ss)
+ ret = -EINVAL;
+#ifdef CONFIG_MODULES
+ if (!ss) {
+ rcu_read_unlock();
request_module("nfnetlink-subsys-%d", type);
- return 0;
-}
+ rcu_read_lock();
+ ss = nfnetlink_get_subsys(type << 8);
+ }
#endif
+ if (!ss) {
+ rcu_read_unlock();
+ return ret;
+ }
+
+ subsys_id = ss->subsys_id;
+ rcu_read_unlock();
+
+ if (!ss->bind)
+ return 0;
+
+ nfnl_lock(subsys_id);
+ if (nfnl_dereference_protected(subsys_id) == ss)
+ ret = ss->bind(net);
+ nfnl_unlock(subsys_id);
+
+ return ret;
+}
static int __net_init nfnetlink_net_init(struct net *net)
{
@@ -507,9 +528,7 @@ static int __net_init nfnetlink_net_init(struct net *net)
struct netlink_kernel_cfg cfg = {
.groups = NFNLGRP_MAX,
.input = nfnetlink_rcv,
-#ifdef CONFIG_MODULES
.bind = nfnetlink_bind,
-#endif
};
nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg);
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 11/12] netfilter: hook up nfnetlink log/queue to register conntrack hooks
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (9 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 10/12] netfilter: ctnetlink: make ctnetlink bind register conntrack hooks Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-03 9:49 ` [PATCH v3 nf-next 12/12] netfilter: inform ctnetlink about new l3 protocol trackers Florian Westphal
2015-12-18 11:42 ` [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Pablo Neira Ayuso
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
If userspace using nfqueue or nflog requests conntrack info, make sure
that we register the conntrack netfilter hooks in the affected netns.
This is a one-shot scheme: There is no unregister equivalent (except when backend
conntrack l3proto module is unloaded or the network namespace is removed).
Once nflog/nfqueue wants conntrack, the hooks are activated without being
able to unregister the hooks again.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
not part of v2 series.
This is a seperate patch to ease review.
include/linux/netfilter.h | 1 +
net/netfilter/nf_conntrack_netlink.c | 1 +
net/netfilter/nfnetlink_log.c | 28 ++++++++++++++++++----------
net/netfilter/nfnetlink_queue.c | 8 ++++++++
4 files changed, 28 insertions(+), 10 deletions(-)
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 9230f9a..c3cf796 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -396,6 +396,7 @@ struct nfnl_ct_hook {
u32 portid, u32 report);
void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo, s32 off);
+ int (*register_hooks)(struct net *);
};
extern struct nfnl_ct_hook __rcu *nfnl_ct_hook;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index b8a4067..0a9b1e9 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2451,6 +2451,7 @@ static struct nfnl_ct_hook ctnetlink_glue_hook = {
.parse = ctnetlink_glue_parse,
.attach_expect = ctnetlink_glue_attach_expect,
.seq_adjust = ctnetlink_glue_seqadj,
+ .register_hooks = ctnl_bind,
};
#endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index dea4676..229685d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -853,19 +853,27 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
if (nfula[NFULA_CFG_FLAGS]) {
flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS]));
- if ((flags & NFULNL_CFG_F_CONNTRACK) &&
- !rcu_access_pointer(nfnl_ct_hook)) {
+ if (flags & NFULNL_CFG_F_CONNTRACK) {
+ struct nfnl_ct_hook *nfnl_ct;
+
+ nfnl_ct = rcu_dereference(nfnl_ct_hook);
+ if (!nfnl_ct) {
#ifdef CONFIG_MODULES
- nfnl_unlock(NFNL_SUBSYS_ULOG);
- request_module("ip_conntrack_netlink");
- nfnl_lock(NFNL_SUBSYS_ULOG);
- if (rcu_access_pointer(nfnl_ct_hook)) {
- ret = -EAGAIN;
+ nfnl_unlock(NFNL_SUBSYS_ULOG);
+ request_module("ip_conntrack_netlink");
+ nfnl_lock(NFNL_SUBSYS_ULOG);
+
+ if (rcu_access_pointer(nfnl_ct_hook)) {
+ ret = -EAGAIN;
+ goto out_put;
+ }
+#endif
+ ret = -EOPNOTSUPP;
goto out_put;
+
}
-#endif
- ret = -EOPNOTSUPP;
- goto out_put;
+
+ nfnl_ct->register_hooks(net);
}
}
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 7d81d28..235f4c1 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1222,6 +1222,14 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
goto err_out_unlock;
}
#endif
+ if (flags & mask & NFQA_CFG_F_CONNTRACK) {
+ struct nfnl_ct_hook *nfnl_ct;
+
+ nfnl_ct = rcu_dereference(nfnl_ct_hook);
+ if (nfnl_ct)
+ nfnl_ct->register_hooks(net);
+ }
+
spin_lock_bh(&queue->lock);
queue->flags &= ~mask;
queue->flags |= flags & mask;
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 nf-next 12/12] netfilter: inform ctnetlink about new l3 protocol trackers
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (10 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 11/12] netfilter: hook up nfnetlink log/queue to " Florian Westphal
@ 2015-12-03 9:49 ` Florian Westphal
2015-12-18 11:42 ` [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Pablo Neira Ayuso
12 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-03 9:49 UTC (permalink / raw)
To: netfilter-devel; +Cc: Florian Westphal
Previous patch made 'conntrack -E' (or other ctnetlink event tools)
register netfilter hooks of already-loaded conntrack l3 protocols, but this
fails when a new l3 protocol is loaded at a later point in time.
This informs ctnetlink about new module and also registers their hooks
if needed.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
not part of v2.
This is a seperate patch to ease review.
include/linux/netfilter.h | 1 +
net/netfilter/nf_conntrack_netlink.c | 37 +++++++++++++++++++++++++++++++++++-
net/netfilter/nf_conntrack_proto.c | 6 ++++++
3 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index c3cf796..663832d 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -397,6 +397,7 @@ struct nfnl_ct_hook {
void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo, s32 off);
int (*register_hooks)(struct net *);
+ void (*newproto)(void);
};
extern struct nfnl_ct_hook __rcu *nfnl_ct_hook;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0a9b1e9..1350a28 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -61,6 +61,7 @@ static int ctnetlink_net_id __read_mostly;
struct ctnl_net {
DECLARE_BITMAP(enabled, NFPROTO_NUMPROTO);
+ bool active;
};
static inline int
@@ -2138,7 +2139,7 @@ ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *mask);
-static int ctnl_bind(struct net *net)
+static void __ctnl_bind(struct net *net)
{
struct ctnl_net *ctnet = net_generic(net, ctnetlink_net_id);
int i;
@@ -2178,11 +2179,43 @@ static int ctnl_bind(struct net *net)
}
rcu_read_unlock();
+}
+
+static int ctnl_bind(struct net *net)
+{
+ struct ctnl_net *ctnet = net_generic(net, ctnetlink_net_id);
+
+ __ctnl_bind(net);
+
+ if (!ctnet->active)
+ ctnet->active = true;
return 0;
}
#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
+/* called with RCU read lock held */
+static void ctnl_newproto(void)
+{
+ struct ctnl_net *ctnet;
+ struct net *net;
+
+ if (!try_module_get(THIS_MODULE))
+ return;
+
+ rcu_read_unlock();
+ rtnl_lock();
+ for_each_net(net) {
+ ctnet = net_generic(net, ctnetlink_net_id);
+ if (ctnet->active)
+ __ctnl_bind(net);
+ }
+ rtnl_unlock();
+ rcu_read_lock();
+
+ module_put(THIS_MODULE);
+}
+
static size_t
ctnetlink_glue_build_size(const struct nf_conn *ct)
{
@@ -2452,6 +2485,7 @@ static struct nfnl_ct_hook ctnetlink_glue_hook = {
.attach_expect = ctnetlink_glue_attach_expect,
.seq_adjust = ctnetlink_glue_seqadj,
.register_hooks = ctnl_bind,
+ .newproto = ctnl_newproto,
};
#endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */
@@ -3434,6 +3468,7 @@ static void ctnetlink_net_exit(struct net *net)
rcu_read_lock();
}
+ ctnet->active = false;
rcu_read_unlock();
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 1fb11b6..20d51e4 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -259,6 +259,7 @@ int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto)
{
int ret = 0;
struct nf_conntrack_l3proto *old;
+ struct nfnl_ct_hook *nfnl_ct;
if (proto->l3proto >= AF_MAX)
return -EBUSY;
@@ -279,6 +280,11 @@ int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto)
rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto);
+ rcu_read_lock();
+ nfnl_ct = rcu_dereference(nfnl_ct_hook);
+ if (nfnl_ct)
+ nfnl_ct->newproto();
+ rcu_read_unlock();
out_unlock:
mutex_unlock(&nf_ct_proto_mutex);
return ret;
--
2.4.10
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces
2015-12-03 9:49 [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Florian Westphal
` (11 preceding siblings ...)
2015-12-03 9:49 ` [PATCH v3 nf-next 12/12] netfilter: inform ctnetlink about new l3 protocol trackers Florian Westphal
@ 2015-12-18 11:42 ` Pablo Neira Ayuso
2015-12-20 21:01 ` Florian Westphal
12 siblings, 1 reply; 16+ messages in thread
From: Pablo Neira Ayuso @ 2015-12-18 11:42 UTC (permalink / raw)
To: Florian Westphal; +Cc: netfilter-devel
Hi Florian,
On Thu, Dec 03, 2015 at 10:49:33AM +0100, Florian Westphal wrote:
> My problem with this patch set is the ridiculous amount of code that needs
> to be added to cover all the 'register the hooks for conntrack' cases.
I spent some time spinning on this, and to be honest I couldn't come
up with any better solution following this automatic hook registration
by infering from the dependencies.
Still my concerns also go in the direction of breaking corner cases,
for example, people polling (no event subscription) from ctnetlink to
retrieve statistics (then send them to some centralized collector)
assuming no rules at all.
> IOW, it might be a much better idea to respin this patch series so
> that it does NOT contain any of the conntrack changes (only 'don't register
> xtables hooks + don't register bridge hooks), and then add
> net.netfilter.nf_conntrack_disable (or whatever), plus -j CT --track.
It would be good to agree on some design for this. Patrick also have
concerns on loose conntrack enabling. That we can probably resolve
through explicit configuration, something like:
-j CT --track --protocols sctp,tcp,udp --unsupported generic
so we explicitly indicate what protocol trackers are on and indicate
that otherwise to use the generic tracker.
> That would also solve this issue, albeit not by default and it leaves
> the question of how we should deal with defragmentation
> (-s 10.2.3.0/24 -p tcp --dport 80 would not work reliably).
IIRC in iptables, we drop this via hotdrop, but in nftables this is an
open issue, a user with no defrag should drop fragments in first place
in his ruleset.
In iptables, we can still register the defragmentation hooks as soon
as we need conntrack, socket or tproxy.
> Perhaps we could attempt to propogate a *conntrack rule active* bit into
> the xtables core and call defrag from there. Another, simpler alternative
> would be to stick an unconditional 'defrag' call into the raw table.
I couldn't come up so far with any scenario that would break with
unconditional defragmentation. But unconditional stuff makes me feel a
bit nervous as there is usually someone following up with rare
situation that forces us to disable it.
Let me know, thanks Florian.
^ permalink raw reply [flat|nested] 16+ messages in thread* Re: [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces
2015-12-18 11:42 ` [PATCH v3 nf-next 0/12] netfilter: don't copy init ns hooks to new namespaces Pablo Neira Ayuso
@ 2015-12-20 21:01 ` Florian Westphal
0 siblings, 0 replies; 16+ messages in thread
From: Florian Westphal @ 2015-12-20 21:01 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: Florian Westphal, netfilter-devel
Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> On Thu, Dec 03, 2015 at 10:49:33AM +0100, Florian Westphal wrote:
> > My problem with this patch set is the ridiculous amount of code that needs
> > to be added to cover all the 'register the hooks for conntrack' cases.
[..]
> > IOW, it might be a much better idea to respin this patch series so
> > that it does NOT contain any of the conntrack changes (only 'don't register
> > xtables hooks + don't register bridge hooks), and then add
> > net.netfilter.nf_conntrack_disable (or whatever), plus -j CT --track.
>
> It would be good to agree on some design for this. Patrick also have
> concerns on loose conntrack enabling. That we can probably resolve
> through explicit configuration, something like:
[..]
> > That would also solve this issue, albeit not by default and it leaves
> > the question of how we should deal with defragmentation
> > (-s 10.2.3.0/24 -p tcp --dport 80 would not work reliably).
>
> IIRC in iptables, we drop this via hotdrop, but in nftables this is an
> open issue, a user with no defrag should drop fragments in first place
> in his ruleset.
To clarify, what I meant was user doing this:
-s 10.0.0.8/24 -p tcp --dport 80 -j CT --track
Which will only do the expected thing -- feed all http traffic to
conntrack_in -- for non-fragmented packets.
So if we'd follow this route, i.e. conditional tracking via ruleset,
we'd need to figure out how to...
1. make sure fragments don't bypass such rules
2. deal with reply direction (we'd probably need some 'passive'
input hook that doesn't create new connections and only checks for
reply direction)
3. how to handle expecations, helpers, etc
Simplest and most backwards-compat solution for #1 would be to
register the defrag hooks once such a rule is inserted, which IMO
is the preferable solution, especially because it won't cause backwards
compat issues.
For #2, I don't have a good solution yet, alternative would be
to also force adding rule in reply dir, but I hate it since we don't
require it for NAT either.
Haven't thought about #3 yet.
> In iptables, we can still register the defragmentation hooks as soon
> as we need conntrack, socket or tproxy.
Yes, we'd need some of the patches from this set to avoid registering in
all net namespaces, but, I agree -- inferring if defrag is needed seems
to be easy and correct path forward.
> > Perhaps we could attempt to propogate a *conntrack rule active* bit into
> > the xtables core and call defrag from there. Another, simpler alternative
> > would be to stick an unconditional 'defrag' call into the raw table.
>
> I couldn't come up so far with any scenario that would break with
> unconditional defragmentation. But unconditional stuff makes me feel a
> bit nervous as there is usually someone following up with rare
> situation that forces us to disable it.
Lets forget about unconditional defrag in raw table, it was a ba idea.
> Let me know, thanks Florian.
I'd propose to respin this patch series with all the conntrack parts removed.
I think the conntrack parts are too fragile for now, lets discuss
conditional-conntrack-via-ruleset during netdev1.1.
We've mentioned 'inverted NOTRACK' so often by now that it would be a
desaster if we close that door forever by applying a half-baked
'auto-inferring "solution"' now.
If you'd prefer to toss entire patch set and discuss the entire
'netns hooking' mess at netdev1.1 -- no problem, just let me know.
Thanks!
^ permalink raw reply [flat|nested] 16+ messages in thread