* netfilter 02/03: nf_conntrack: add support for "conntrack zones"
2010-02-08 17:39 netfilter 00/03: conntrack zones Patrick McHardy
2010-02-08 17:39 ` netfilter 01/03: nf_conntrack: pass template to l4proto ->error handler Patrick McHardy
@ 2010-02-08 17:39 ` Patrick McHardy
2010-02-08 17:39 ` netfilter 03/03: ctnetlink: add zone support Patrick McHardy
2 siblings, 0 replies; 4+ messages in thread
From: Patrick McHardy @ 2010-02-08 17:39 UTC (permalink / raw)
To: netfilter-devel; +Cc: Patrick McHardy
commit 6ccba6c701bc1f6673881dc90cc8655d2570dc2d
Author: Patrick McHardy <kaber@trash.net>
Date: Mon Feb 8 18:16:07 2010 +0100
netfilter: nf_conntrack: add support for "conntrack zones"
Normally, each connection needs a unique identity. Conntrack zones allow
to specify a numerical zone using the CT target, connections in different
zones can use the same identity.
Example:
# assign connections between veth0 and veth1 to conntrack zone 1:
iptables -t raw -I PREROUTING -i veth0 -j CT --zone 1
iptables -t raw -I PREROUTING -i veth1 -j CT --zone 1
Signed-off-by: Patrick McHardy <kaber@trash.net>
diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index 7fd0eff..1b56410 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -5,7 +5,7 @@
struct xt_ct_target_info {
u_int16_t flags;
- u_int16_t __unused;
+ u_int16_t zone;
u_int32_t ct_events;
u_int32_t exp_events;
char helper[16];
diff --git a/include/net/ip.h b/include/net/ip.h
index 85108cf..426c415 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -336,8 +336,11 @@ enum ip_defrag_users {
IP_DEFRAG_LOCAL_DELIVER,
IP_DEFRAG_CALL_RA_CHAIN,
IP_DEFRAG_CONNTRACK_IN,
+ __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHORT_MAX,
IP_DEFRAG_CONNTRACK_OUT,
+ __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHORT_MAX,
IP_DEFRAG_CONNTRACK_BRIDGE_IN,
+ __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX,
IP_DEFRAG_VS_IN,
IP_DEFRAG_VS_OUT,
IP_DEFRAG_VS_FWD
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 299bbf5..639ec53 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -355,8 +355,11 @@ struct inet_frag_queue;
enum ip6_defrag_users {
IP6_DEFRAG_LOCAL_DELIVER,
IP6_DEFRAG_CONNTRACK_IN,
+ __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHORT_MAX,
IP6_DEFRAG_CONNTRACK_OUT,
+ __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHORT_MAX,
IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
+ __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX,
};
struct ip6_create_arg {
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 5043d61..b38bc6a 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -198,7 +198,8 @@ extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int null
extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
extern struct nf_conntrack_tuple_hash *
-__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple);
+__nf_conntrack_find(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple);
extern void nf_conntrack_hash_insert(struct nf_conn *ct);
extern void nf_ct_delete_from_lists(struct nf_conn *ct);
@@ -267,7 +268,7 @@ extern void
nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data);
extern void nf_conntrack_free(struct nf_conn *ct);
extern struct nf_conn *
-nf_conntrack_alloc(struct net *net,
+nf_conntrack_alloc(struct net *net, u16 zone,
const struct nf_conntrack_tuple *orig,
const struct nf_conntrack_tuple *repl,
gfp_t gfp);
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 5a449b4..dffde8e 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -49,7 +49,8 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
/* Find a connection corresponding to a tuple. */
extern struct nf_conntrack_tuple_hash *
-nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple);
+nf_conntrack_find_get(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple);
extern int __nf_conntrack_confirm(struct sk_buff *skb);
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 9a2b9cb..83c49f3 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -77,13 +77,16 @@ int nf_conntrack_expect_init(struct net *net);
void nf_conntrack_expect_fini(struct net *net);
struct nf_conntrack_expect *
-__nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple);
+__nf_ct_expect_find(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
-nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_tuple *tuple);
+nf_ct_expect_find_get(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
-nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple);
+nf_ct_find_expectation(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple);
void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
void nf_ct_remove_expectations(struct nf_conn *ct);
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index e192dc1..2d2a1f9 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -8,6 +8,7 @@ enum nf_ct_ext_id {
NF_CT_EXT_NAT,
NF_CT_EXT_ACCT,
NF_CT_EXT_ECACHE,
+ NF_CT_EXT_ZONE,
NF_CT_EXT_NUM,
};
@@ -15,6 +16,7 @@ enum nf_ct_ext_id {
#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
#define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
+#define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {
diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h
new file mode 100644
index 0000000..0bbb2bd
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_zones.h
@@ -0,0 +1,23 @@
+#ifndef _NF_CONNTRACK_ZONES_H
+#define _NF_CONNTRACK_ZONES_H
+
+#include <net/netfilter/nf_conntrack_extend.h>
+
+#define NF_CT_DEFAULT_ZONE 0
+
+struct nf_conntrack_zone {
+ u16 id;
+};
+
+static inline u16 nf_ct_zone(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ struct nf_conntrack_zone *nf_ct_zone;
+ nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE);
+ if (nf_ct_zone)
+ return nf_ct_zone->id;
+#endif
+ return NF_CT_DEFAULT_ZONE;
+}
+
+#endif /* _NF_CONNTRACK_ZONES_H */
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index d171b12..2ce81ee 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -22,6 +22,7 @@
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
#include <net/netfilter/nf_nat_helper.h>
@@ -266,7 +267,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
return -EINVAL;
}
- h = nf_conntrack_find_get(sock_net(sk), &tuple);
+ h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
if (h) {
struct sockaddr_in sin;
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 327826a..7404bde 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -18,6 +18,7 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_log.h>
static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ;
@@ -114,13 +115,14 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
static int
-icmp_error_message(struct net *net, struct sk_buff *skb,
+icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
enum ip_conntrack_info *ctinfo,
unsigned int hooknum)
{
struct nf_conntrack_tuple innertuple, origtuple;
const struct nf_conntrack_l4proto *innerproto;
const struct nf_conntrack_tuple_hash *h;
+ u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
NF_CT_ASSERT(skb->nfct == NULL);
@@ -146,7 +148,7 @@ icmp_error_message(struct net *net, struct sk_buff *skb,
*ctinfo = IP_CT_RELATED;
- h = nf_conntrack_find_get(net, &innertuple);
+ h = nf_conntrack_find_get(net, zone, &innertuple);
if (!h) {
pr_debug("icmp_error_message: no match\n");
return -NF_ACCEPT;
@@ -209,7 +211,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl,
icmph->type != ICMP_REDIRECT)
return NF_ACCEPT;
- return icmp_error_message(net, skb, ctinfo, hooknum);
+ return icmp_error_message(net, tmpl, skb, ctinfo, hooknum);
}
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index f6f4668..d498a70 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -16,6 +16,7 @@
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#include <net/netfilter/nf_conntrack.h>
@@ -39,15 +40,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
+ u16 zone = NF_CT_DEFAULT_ZONE;
+
+ if (skb->nfct)
+ zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge &&
skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
- return IP_DEFRAG_CONNTRACK_BRIDGE_IN;
+ return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
#endif
if (hooknum == NF_INET_PRE_ROUTING)
- return IP_DEFRAG_CONNTRACK_IN;
+ return IP_DEFRAG_CONNTRACK_IN + zone;
else
- return IP_DEFRAG_CONNTRACK_OUT;
+ return IP_DEFRAG_CONNTRACK_OUT + zone;
}
static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index fe1a644..64b9979 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -30,6 +30,7 @@
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_zones.h>
static DEFINE_SPINLOCK(nf_nat_lock);
@@ -72,13 +73,13 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put);
/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
-hash_by_src(const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct nf_conntrack_tuple *tuple, u16 zone)
{
unsigned int hash;
/* Original src, to ensure we map it consistently if poss. */
hash = jhash_3words((__force u32)tuple->src.u3.ip,
- (__force u32)tuple->src.u.all,
+ (__force u32)tuple->src.u.all ^ zone,
tuple->dst.protonum, 0);
return ((u64)hash * nf_nat_htable_size) >> 32;
}
@@ -142,12 +143,12 @@ same_src(const struct nf_conn *ct,
/* Only called for SRC manip */
static int
-find_appropriate_src(struct net *net,
+find_appropriate_src(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
- unsigned int h = hash_by_src(tuple);
+ unsigned int h = hash_by_src(tuple, zone);
const struct nf_conn_nat *nat;
const struct nf_conn *ct;
const struct hlist_node *n;
@@ -155,7 +156,7 @@ find_appropriate_src(struct net *net,
rcu_read_lock();
hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) {
ct = nat->ct;
- if (same_src(ct, tuple)) {
+ if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
/* Copy source part from reply tuple. */
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@@ -178,7 +179,7 @@ find_appropriate_src(struct net *net,
the ip with the lowest src-ip/dst-ip/proto usage.
*/
static void
-find_best_ips_proto(struct nf_conntrack_tuple *tuple,
+find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
@@ -212,7 +213,7 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple,
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
range->flags & IP_NAT_RANGE_PERSISTENT ?
- 0 : (__force u32)tuple->dst.u3.ip, 0);
+ 0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
j = ((u64)j * (maxip - minip + 1)) >> 32;
*var_ipp = htonl(minip + j);
}
@@ -232,6 +233,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
{
struct net *net = nf_ct_net(ct);
const struct nf_nat_protocol *proto;
+ u16 zone = nf_ct_zone(ct);
/* 1) If this srcip/proto/src-proto-part is currently mapped,
and that same mapping gives a unique tuple within the given
@@ -242,7 +244,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
manips not an issue. */
if (maniptype == IP_NAT_MANIP_SRC &&
!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
- if (find_appropriate_src(net, orig_tuple, tuple, range)) {
+ if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) {
pr_debug("get_unique_tuple: Found current src map\n");
if (!nf_nat_used_tuple(tuple, ct))
return;
@@ -252,7 +254,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
/* 2) Select the least-used IP/proto combination in the given
range. */
*tuple = *orig_tuple;
- find_best_ips_proto(tuple, range, ct, maniptype);
+ find_best_ips_proto(zone, tuple, range, ct, maniptype);
/* 3) The per-protocol part of the manip is made to map into
the range to make a unique tuple. */
@@ -330,7 +332,8 @@ nf_nat_setup_info(struct nf_conn *ct,
if (have_to_hash) {
unsigned int srchash;
- srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ nf_ct_zone(ct));
spin_lock_bh(&nf_nat_lock);
/* nf_conntrack_alter_reply might re-allocate exntension aera */
nat = nfct_nat(ct);
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 9eb1710..4c06003 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -25,6 +25,7 @@
#include <net/netfilter/nf_nat_rule.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_proto_gre.h>
#include <linux/netfilter/nf_conntrack_pptp.h>
@@ -74,7 +75,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple_ip(&t);
- other_exp = nf_ct_expect_find_get(net, &t);
+ other_exp = nf_ct_expect_find_get(net, nf_ct_zone(ct), &t);
if (other_exp) {
nf_ct_unexpect_related(other_exp);
nf_ct_expect_put(other_exp);
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 55ce22e..996c3f4 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -27,6 +27,7 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
#include <net/netfilter/nf_log.h>
@@ -191,15 +192,20 @@ out:
static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
+ u16 zone = NF_CT_DEFAULT_ZONE;
+
+ if (skb->nfct)
+ zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge &&
skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
- return IP6_DEFRAG_CONNTRACK_BRIDGE_IN;
+ return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
#endif
if (hooknum == NF_INET_PRE_ROUTING)
- return IP6_DEFRAG_CONNTRACK_IN;
+ return IP6_DEFRAG_CONNTRACK_IN + zone;
else
- return IP6_DEFRAG_CONNTRACK_OUT;
+ return IP6_DEFRAG_CONNTRACK_OUT + zone;
}
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index d772dc2..9be8177 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -23,6 +23,7 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
#include <net/netfilter/nf_log.h>
@@ -128,7 +129,7 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
}
static int
-icmpv6_error_message(struct net *net,
+icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int icmp6off,
enum ip_conntrack_info *ctinfo,
@@ -137,6 +138,7 @@ icmpv6_error_message(struct net *net,
struct nf_conntrack_tuple intuple, origtuple;
const struct nf_conntrack_tuple_hash *h;
const struct nf_conntrack_l4proto *inproto;
+ u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
NF_CT_ASSERT(skb->nfct == NULL);
@@ -163,7 +165,7 @@ icmpv6_error_message(struct net *net,
*ctinfo = IP_CT_RELATED;
- h = nf_conntrack_find_get(net, &intuple);
+ h = nf_conntrack_find_get(net, zone, &intuple);
if (!h) {
pr_debug("icmpv6_error: no match\n");
return -NF_ACCEPT;
@@ -216,7 +218,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl,
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
- return icmpv6_error_message(net, skb, dataoff, ctinfo, hooknum);
+ return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
}
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 4469d45..ffe4796 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -83,6 +83,15 @@ config NF_CONNTRACK_SECMARK
If unsure, say 'N'.
+config NF_CONNTRACK_ZONES
+ bool 'Connection tracking zones'
+ help
+ This option enables support for connection tracking zones.
+ Normally, each connection needs to have a unique identity.
+ Connection tracking zones allow to have multiple connections
+ using the same identity, as long as they are contained in
+ different zones.
+
config NF_CONNTRACK_EVENTS
bool "Connection tracking events"
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9ae41cf..b7227d9 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -41,6 +41,7 @@
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
@@ -69,7 +70,7 @@ static int nf_conntrack_hash_rnd_initted;
static unsigned int nf_conntrack_hash_rnd;
static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
- unsigned int size, unsigned int rnd)
+ u16 zone, unsigned int size, unsigned int rnd)
{
unsigned int n;
u_int32_t h;
@@ -80,15 +81,16 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple,
*/
n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
h = jhash2((u32 *)tuple, n,
- rnd ^ (((__force __u16)tuple->dst.u.all << 16) |
- tuple->dst.protonum));
+ zone ^ rnd ^ (((__force __u16)tuple->dst.u.all << 16) |
+ tuple->dst.protonum));
return ((u64)h * size) >> 32;
}
-static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
+static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple,
+ u16 zone)
{
- return __hash_conntrack(tuple, nf_conntrack_htable_size,
+ return __hash_conntrack(tuple, zone, nf_conntrack_htable_size,
nf_conntrack_hash_rnd);
}
@@ -292,11 +294,12 @@ static void death_by_timeout(unsigned long ul_conntrack)
* - Caller must lock nf_conntrack_lock before calling this function
*/
struct nf_conntrack_tuple_hash *
-__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
+__nf_conntrack_find(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
- unsigned int hash = hash_conntrack(tuple);
+ unsigned int hash = hash_conntrack(tuple, zone);
/* Disable BHs the entire time since we normally need to disable them
* at least once for the stats anyway.
@@ -304,7 +307,8 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
local_bh_disable();
begin:
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
- if (nf_ct_tuple_equal(tuple, &h->tuple)) {
+ if (nf_ct_tuple_equal(tuple, &h->tuple) &&
+ nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
return h;
@@ -326,21 +330,23 @@ EXPORT_SYMBOL_GPL(__nf_conntrack_find);
/* Find a connection corresponding to a tuple. */
struct nf_conntrack_tuple_hash *
-nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple)
+nf_conntrack_find_get(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
rcu_read_lock();
begin:
- h = __nf_conntrack_find(net, tuple);
+ h = __nf_conntrack_find(net, zone, tuple);
if (h) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (unlikely(nf_ct_is_dying(ct) ||
!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
- if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
+ if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
+ nf_ct_zone(ct) != zone)) {
nf_ct_put(ct);
goto begin;
}
@@ -367,9 +373,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
void nf_conntrack_hash_insert(struct nf_conn *ct)
{
unsigned int hash, repl_hash;
+ u16 zone;
- hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ zone = nf_ct_zone(ct);
+ hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone);
+ repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone);
__nf_conntrack_hash_insert(ct, hash, repl_hash);
}
@@ -386,6 +394,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
struct hlist_nulls_node *n;
enum ip_conntrack_info ctinfo;
struct net *net;
+ u16 zone;
ct = nf_ct_get(skb, &ctinfo);
net = nf_ct_net(ct);
@@ -397,8 +406,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
return NF_ACCEPT;
- hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ zone = nf_ct_zone(ct);
+ hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone);
+ repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone);
/* We're not in hash table, and we refuse to set up related
connections for unconfirmed conns. But packet copies and
@@ -417,11 +427,13 @@ __nf_conntrack_confirm(struct sk_buff *skb)
not in the hash. If there is, we lost race. */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- &h->tuple))
+ &h->tuple) &&
+ zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- &h->tuple))
+ &h->tuple) &&
+ zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
/* Remove from unconfirmed list */
@@ -468,15 +480,19 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
struct net *net = nf_ct_net(ignored_conntrack);
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
- unsigned int hash = hash_conntrack(tuple);
+ struct nf_conn *ct;
+ u16 zone = nf_ct_zone(ignored_conntrack);
+ unsigned int hash = hash_conntrack(tuple, zone);
/* Disable BHs the entire time since we need to disable them at
* least once for the stats anyway.
*/
rcu_read_lock_bh();
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
- if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack &&
- nf_ct_tuple_equal(tuple, &h->tuple)) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (ct != ignored_conntrack &&
+ nf_ct_tuple_equal(tuple, &h->tuple) &&
+ nf_ct_zone(ct) == zone) {
NF_CT_STAT_INC(net, found);
rcu_read_unlock_bh();
return 1;
@@ -539,7 +555,7 @@ static noinline int early_drop(struct net *net, unsigned int hash)
return dropped;
}
-struct nf_conn *nf_conntrack_alloc(struct net *net,
+struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
const struct nf_conntrack_tuple *orig,
const struct nf_conntrack_tuple *repl,
gfp_t gfp)
@@ -557,7 +573,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
if (nf_conntrack_max &&
unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
- unsigned int hash = hash_conntrack(orig);
+ unsigned int hash = hash_conntrack(orig, zone);
if (!early_drop(net, hash)) {
atomic_dec(&net->ct.count);
if (net_ratelimit())
@@ -594,13 +610,28 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
#ifdef CONFIG_NET_NS
ct->ct_net = net;
#endif
-
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ if (zone) {
+ struct nf_conntrack_zone *nf_ct_zone;
+
+ nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC);
+ if (!nf_ct_zone)
+ goto out_free;
+ nf_ct_zone->id = zone;
+ }
+#endif
/*
* changes to lookup keys must be done before setting refcnt to 1
*/
smp_wmb();
atomic_set(&ct->ct_general.use, 1);
return ct;
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+out_free:
+ kmem_cache_free(nf_conntrack_cachep, ct);
+ return ERR_PTR(-ENOMEM);
+#endif
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
@@ -630,13 +661,14 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
struct nf_conntrack_tuple repl_tuple;
struct nf_conntrack_ecache *ecache;
struct nf_conntrack_expect *exp;
+ u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
pr_debug("Can't invert tuple.\n");
return NULL;
}
- ct = nf_conntrack_alloc(net, tuple, &repl_tuple, GFP_ATOMIC);
+ ct = nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC);
if (IS_ERR(ct)) {
pr_debug("Can't allocate conntrack.\n");
return (struct nf_conntrack_tuple_hash *)ct;
@@ -656,7 +688,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
GFP_ATOMIC);
spin_lock_bh(&nf_conntrack_lock);
- exp = nf_ct_find_expectation(net, tuple);
+ exp = nf_ct_find_expectation(net, zone, tuple);
if (exp) {
pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
ct, exp);
@@ -712,6 +744,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
struct nf_conntrack_tuple tuple;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
+ u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
dataoff, l3num, protonum, &tuple, l3proto,
@@ -721,7 +754,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
}
/* look for tuple match */
- h = nf_conntrack_find_get(net, &tuple);
+ h = nf_conntrack_find_get(net, zone, &tuple);
if (!h) {
h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
skb, dataoff);
@@ -957,6 +990,14 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
}
EXPORT_SYMBOL_GPL(__nf_ct_kill_acct);
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = {
+ .len = sizeof(struct nf_conntrack_zone),
+ .align = __alignof__(struct nf_conntrack_zone),
+ .id = NF_CT_EXT_ZONE,
+};
+#endif
+
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
#include <linux/netfilter/nfnetlink.h>
@@ -1134,6 +1175,9 @@ static void nf_conntrack_cleanup_init_net(void)
{
nf_conntrack_helper_fini();
nf_conntrack_proto_fini();
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ nf_ct_extend_unregister(&nf_ct_zone_extend);
+#endif
kmem_cache_destroy(nf_conntrack_cachep);
}
@@ -1212,6 +1256,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
int rnd;
struct hlist_nulls_head *hash, *old_hash;
struct nf_conntrack_tuple_hash *h;
+ struct nf_conn *ct;
/* On boot, we can set this without any fancy locking. */
if (!nf_conntrack_htable_size)
@@ -1239,8 +1284,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
h = hlist_nulls_entry(init_net.ct.hash[i].first,
struct nf_conntrack_tuple_hash, hnnode);
+ ct = nf_ct_tuplehash_to_ctrack(h);
hlist_nulls_del_rcu(&h->hnnode);
- bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
+ bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct),
+ hashsize, rnd);
hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
@@ -1307,8 +1354,17 @@ static int nf_conntrack_init_init_net(void)
if (ret < 0)
goto err_helper;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ ret = nf_ct_extend_register(&nf_ct_zone_extend);
+ if (ret < 0)
+ goto err_extend;
+#endif
return 0;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+err_extend:
+ nf_conntrack_helper_fini();
+#endif
err_helper:
nf_conntrack_proto_fini();
err_proto:
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index fdf5d2a..b3052cb 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -27,6 +27,7 @@
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_zones.h>
unsigned int nf_ct_expect_hsize __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);
@@ -84,7 +85,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
}
struct nf_conntrack_expect *
-__nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple)
+__nf_ct_expect_find(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i;
struct hlist_node *n;
@@ -95,7 +97,8 @@ __nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple)
h = nf_ct_expect_dst_hash(tuple);
hlist_for_each_entry_rcu(i, n, &net->ct.expect_hash[h], hnode) {
- if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask))
+ if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
+ nf_ct_zone(i->master) == zone)
return i;
}
return NULL;
@@ -104,12 +107,13 @@ EXPORT_SYMBOL_GPL(__nf_ct_expect_find);
/* Just find a expectation corresponding to a tuple. */
struct nf_conntrack_expect *
-nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_tuple *tuple)
+nf_ct_expect_find_get(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i;
rcu_read_lock();
- i = __nf_ct_expect_find(net, tuple);
+ i = __nf_ct_expect_find(net, zone, tuple);
if (i && !atomic_inc_not_zero(&i->use))
i = NULL;
rcu_read_unlock();
@@ -121,7 +125,8 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get);
/* If an expectation for this connection is found, it gets delete from
* global list then returned. */
struct nf_conntrack_expect *
-nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple)
+nf_ct_find_expectation(struct net *net, u16 zone,
+ const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i, *exp = NULL;
struct hlist_node *n;
@@ -133,7 +138,8 @@ nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple)
h = nf_ct_expect_dst_hash(tuple);
hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
- nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) {
+ nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
+ nf_ct_zone(i->master) == zone) {
exp = i;
break;
}
@@ -204,7 +210,8 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
{
return a->master == b->master && a->class == b->class &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
- nf_ct_tuple_mask_equal(&a->mask, &b->mask);
+ nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
+ nf_ct_zone(a->master) == nf_ct_zone(b->master);
}
/* Generally a bad idea to call this: could have matched already. */
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 6636949..a1c8dd9 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -29,6 +29,7 @@
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_h323.h>
/* Parameters */
@@ -1216,7 +1217,7 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct,
tuple.dst.u.tcp.port = port;
tuple.dst.protonum = IPPROTO_TCP;
- exp = __nf_ct_expect_find(net, &tuple);
+ exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple);
if (exp && exp->master == ct)
return exp;
return NULL;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 09044f9..1dcd7a0 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -796,7 +796,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- h = nf_conntrack_find_get(net, &tuple);
+ h = nf_conntrack_find_get(net, 0, &tuple);
if (!h)
return -ENOENT;
@@ -857,7 +857,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- h = nf_conntrack_find_get(net, &tuple);
+ h = nf_conntrack_find_get(net, 0, &tuple);
if (!h)
return -ENOENT;
@@ -1194,7 +1194,7 @@ ctnetlink_create_conntrack(struct net *net,
int err = -EINVAL;
struct nf_conntrack_helper *helper;
- ct = nf_conntrack_alloc(net, otuple, rtuple, GFP_ATOMIC);
+ ct = nf_conntrack_alloc(net, 0, otuple, rtuple, GFP_ATOMIC);
if (IS_ERR(ct))
return ERR_PTR(-ENOMEM);
@@ -1298,7 +1298,7 @@ ctnetlink_create_conntrack(struct net *net,
if (err < 0)
goto err2;
- master_h = nf_conntrack_find_get(net, &master);
+ master_h = nf_conntrack_find_get(net, 0, &master);
if (master_h == NULL) {
err = -ENOENT;
goto err2;
@@ -1347,9 +1347,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
spin_lock_bh(&nf_conntrack_lock);
if (cda[CTA_TUPLE_ORIG])
- h = __nf_conntrack_find(net, &otuple);
+ h = __nf_conntrack_find(net, 0, &otuple);
else if (cda[CTA_TUPLE_REPLY])
- h = __nf_conntrack_find(net, &rtuple);
+ h = __nf_conntrack_find(net, 0, &rtuple);
if (h == NULL) {
err = -ENOENT;
@@ -1678,7 +1678,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- exp = nf_ct_expect_find_get(net, &tuple);
+ exp = nf_ct_expect_find_get(net, 0, &tuple);
if (!exp)
return -ENOENT;
@@ -1734,7 +1734,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
return err;
/* bump usage count to 2 */
- exp = nf_ct_expect_find_get(net, &tuple);
+ exp = nf_ct_expect_find_get(net, 0, &tuple);
if (!exp)
return -ENOENT;
@@ -1819,7 +1819,7 @@ ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[],
return err;
/* Look for master conntrack of this expectation */
- h = nf_conntrack_find_get(net, &master_tuple);
+ h = nf_conntrack_find_get(net, 0, &master_tuple);
if (!h)
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
@@ -1876,7 +1876,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
return err;
spin_lock_bh(&nf_conntrack_lock);
- exp = __nf_ct_expect_find(net, &tuple);
+ exp = __nf_ct_expect_find(net, 0, &tuple);
if (!exp) {
spin_unlock_bh(&nf_conntrack_lock);
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 3807ac7..0889448 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -28,6 +28,7 @@
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_proto_gre.h>
#include <linux/netfilter/nf_conntrack_pptp.h>
@@ -123,7 +124,7 @@ static void pptp_expectfn(struct nf_conn *ct,
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple(&inv_t);
- exp_other = nf_ct_expect_find_get(net, &inv_t);
+ exp_other = nf_ct_expect_find_get(net, nf_ct_zone(ct), &inv_t);
if (exp_other) {
/* delete other expectation. */
pr_debug("found\n");
@@ -136,17 +137,18 @@ static void pptp_expectfn(struct nf_conn *ct,
rcu_read_unlock();
}
-static int destroy_sibling_or_exp(struct net *net,
+static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct,
const struct nf_conntrack_tuple *t)
{
const struct nf_conntrack_tuple_hash *h;
struct nf_conntrack_expect *exp;
struct nf_conn *sibling;
+ u16 zone = nf_ct_zone(ct);
pr_debug("trying to timeout ct or exp for tuple ");
nf_ct_dump_tuple(t);
- h = nf_conntrack_find_get(net, t);
+ h = nf_conntrack_find_get(net, zone, t);
if (h) {
sibling = nf_ct_tuplehash_to_ctrack(h);
pr_debug("setting timeout of conntrack %p to 0\n", sibling);
@@ -157,7 +159,7 @@ static int destroy_sibling_or_exp(struct net *net,
nf_ct_put(sibling);
return 1;
} else {
- exp = nf_ct_expect_find_get(net, t);
+ exp = nf_ct_expect_find_get(net, zone, t);
if (exp) {
pr_debug("unexpect_related of expect %p\n", exp);
nf_ct_unexpect_related(exp);
@@ -182,7 +184,7 @@ static void pptp_destroy_siblings(struct nf_conn *ct)
t.dst.protonum = IPPROTO_GRE;
t.src.u.gre.key = help->help.ct_pptp_info.pns_call_id;
t.dst.u.gre.key = help->help.ct_pptp_info.pac_call_id;
- if (!destroy_sibling_or_exp(net, &t))
+ if (!destroy_sibling_or_exp(net, ct, &t))
pr_debug("failed to timeout original pns->pac ct/exp\n");
/* try reply (pac->pns) tuple */
@@ -190,7 +192,7 @@ static void pptp_destroy_siblings(struct nf_conn *ct)
t.dst.protonum = IPPROTO_GRE;
t.src.u.gre.key = help->help.ct_pptp_info.pac_call_id;
t.dst.u.gre.key = help->help.ct_pptp_info.pns_call_id;
- if (!destroy_sibling_or_exp(net, &t))
+ if (!destroy_sibling_or_exp(net, ct, &t))
pr_debug("failed to timeout reply pac->pns ct/exp\n");
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4b57216..3b5efc9 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -22,6 +22,7 @@
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_sip.h>
MODULE_LICENSE("GPL");
@@ -777,7 +778,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb,
rcu_read_lock();
do {
- exp = __nf_ct_expect_find(net, &tuple);
+ exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple);
if (!exp || exp->master == ct ||
nfct_help(exp->master)->helper != nfct_help(ct)->helper ||
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 028aba6..4e7dd4f 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -26,6 +26,7 @@
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_zones.h>
MODULE_LICENSE("GPL");
@@ -171,6 +172,11 @@ static int ct_seq_show(struct seq_file *s, void *v)
goto release;
#endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ if (seq_printf(s, "zone=%u ", nf_ct_zone(ct)))
+ goto release;
+#endif
+
if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
goto release;
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 8183a05..61c50fa 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -16,6 +16,7 @@
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_zones.h>
static unsigned int xt_ct_target(struct sk_buff *skb,
const struct xt_target_param *par)
@@ -69,11 +70,16 @@ static bool xt_ct_tg_check(const struct xt_tgchk_param *par)
goto out;
}
+#ifndef CONFIG_NF_CONNTRACK_ZONES
+ if (info->zone)
+ goto err1;
+#endif
+
if (nf_ct_l3proto_try_module_get(par->family) < 0)
goto err1;
memset(&t, 0, sizeof(t));
- ct = nf_conntrack_alloc(par->net, &t, &t, GFP_KERNEL);
+ ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
if (IS_ERR(ct))
goto err2;
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 0d9d18e..26997ce 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -28,6 +28,7 @@
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_zones.h>
/* we will save the tuples of all connections we care about */
struct xt_connlimit_conn {
@@ -114,7 +115,8 @@ static int count_them(struct net *net,
/* check the saved connections */
list_for_each_entry_safe(conn, tmp, hash, list) {
- found = nf_conntrack_find_get(net, &conn->tuple);
+ found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
+ &conn->tuple);
found_ct = NULL;
if (found != NULL)
^ permalink raw reply related [flat|nested] 4+ messages in thread* netfilter 03/03: ctnetlink: add zone support
2010-02-08 17:39 netfilter 00/03: conntrack zones Patrick McHardy
2010-02-08 17:39 ` netfilter 01/03: nf_conntrack: pass template to l4proto ->error handler Patrick McHardy
2010-02-08 17:39 ` netfilter 02/03: nf_conntrack: add support for "conntrack zones" Patrick McHardy
@ 2010-02-08 17:39 ` Patrick McHardy
2 siblings, 0 replies; 4+ messages in thread
From: Patrick McHardy @ 2010-02-08 17:39 UTC (permalink / raw)
To: netfilter-devel; +Cc: Patrick McHardy
commit 30f087ba2567a392f47cfdfc31e315cf88c74c97
Author: Patrick McHardy <kaber@trash.net>
Date: Mon Feb 8 18:16:08 2010 +0100
netfilter: ctnetlink: add zone support
Parse and dump the conntrack zone in ctnetlink.
Signed-off-by: Patrick McHardy <kaber@trash.net>
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index ed4ef8d..9ed534c 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -40,6 +40,7 @@ enum ctattr_type {
CTA_NAT_SEQ_ADJ_ORIG,
CTA_NAT_SEQ_ADJ_REPLY,
CTA_SECMARK,
+ CTA_ZONE,
__CTA_MAX
};
#define CTA_MAX (__CTA_MAX - 1)
@@ -159,6 +160,7 @@ enum ctattr_expect {
CTA_EXPECT_TIMEOUT,
CTA_EXPECT_ID,
CTA_EXPECT_HELP_NAME,
+ CTA_EXPECT_ZONE,
__CTA_EXPECT_MAX
};
#define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1dcd7a0..af71f74 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -39,6 +39,7 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_zones.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_protocol.h>
@@ -379,6 +380,9 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
+ if (nf_ct_zone(ct))
+ NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct)));
+
if (ctnetlink_dump_status(skb, ct) < 0 ||
ctnetlink_dump_timeout(skb, ct) < 0 ||
ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
@@ -517,6 +521,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
goto nla_put_failure;
nla_nest_end(skb, nest_parms);
+ if (nf_ct_zone(ct))
+ NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct)));
+
if (ctnetlink_dump_id(skb, ct) < 0)
goto nla_put_failure;
@@ -745,6 +752,21 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
return 0;
}
+static int
+ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone)
+{
+ if (attr)
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ *zone = ntohs(nla_get_be16(attr));
+#else
+ return -EOPNOTSUPP;
+#endif
+ else
+ *zone = 0;
+
+ return 0;
+}
+
static inline int
ctnetlink_parse_help(const struct nlattr *attr, char **helper_name)
{
@@ -766,6 +788,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
[CTA_MARK] = { .type = NLA_U32 },
[CTA_USE] = { .type = NLA_U32 },
[CTA_ID] = { .type = NLA_U32 },
+ [CTA_ZONE] = { .type = NLA_U16 },
};
static int
@@ -779,7 +802,12 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct nf_conn *ct;
struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
+
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
if (cda[CTA_TUPLE_ORIG])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
@@ -796,7 +824,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- h = nf_conntrack_find_get(net, 0, &tuple);
+ h = nf_conntrack_find_get(net, zone, &tuple);
if (!h)
return -ENOENT;
@@ -841,12 +869,17 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct sk_buff *skb2 = NULL;
struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (nlh->nlmsg_flags & NLM_F_DUMP)
return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table,
ctnetlink_done);
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
+
if (cda[CTA_TUPLE_ORIG])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3);
else if (cda[CTA_TUPLE_REPLY])
@@ -857,7 +890,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- h = nf_conntrack_find_get(net, 0, &tuple);
+ h = nf_conntrack_find_get(net, zone, &tuple);
if (!h)
return -ENOENT;
@@ -1184,7 +1217,7 @@ ctnetlink_change_conntrack(struct nf_conn *ct,
}
static struct nf_conn *
-ctnetlink_create_conntrack(struct net *net,
+ctnetlink_create_conntrack(struct net *net, u16 zone,
const struct nlattr * const cda[],
struct nf_conntrack_tuple *otuple,
struct nf_conntrack_tuple *rtuple,
@@ -1194,7 +1227,7 @@ ctnetlink_create_conntrack(struct net *net,
int err = -EINVAL;
struct nf_conntrack_helper *helper;
- ct = nf_conntrack_alloc(net, 0, otuple, rtuple, GFP_ATOMIC);
+ ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC);
if (IS_ERR(ct))
return ERR_PTR(-ENOMEM);
@@ -1298,7 +1331,7 @@ ctnetlink_create_conntrack(struct net *net,
if (err < 0)
goto err2;
- master_h = nf_conntrack_find_get(net, 0, &master);
+ master_h = nf_conntrack_find_get(net, zone, &master);
if (master_h == NULL) {
err = -ENOENT;
goto err2;
@@ -1331,7 +1364,12 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct nf_conntrack_tuple_hash *h = NULL;
struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
+
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone);
+ if (err < 0)
+ return err;
if (cda[CTA_TUPLE_ORIG]) {
err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3);
@@ -1347,9 +1385,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
spin_lock_bh(&nf_conntrack_lock);
if (cda[CTA_TUPLE_ORIG])
- h = __nf_conntrack_find(net, 0, &otuple);
+ h = __nf_conntrack_find(net, zone, &otuple);
else if (cda[CTA_TUPLE_REPLY])
- h = __nf_conntrack_find(net, 0, &rtuple);
+ h = __nf_conntrack_find(net, zone, &rtuple);
if (h == NULL) {
err = -ENOENT;
@@ -1357,7 +1395,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct nf_conn *ct;
enum ip_conntrack_events events;
- ct = ctnetlink_create_conntrack(net, cda, &otuple,
+ ct = ctnetlink_create_conntrack(net, zone, cda, &otuple,
&rtuple, u3);
if (IS_ERR(ct)) {
err = PTR_ERR(ct);
@@ -1662,7 +1700,8 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
struct sk_buff *skb2;
struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
return netlink_dump_start(ctnl, skb, nlh,
@@ -1670,6 +1709,10 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
ctnetlink_exp_done);
}
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
if (cda[CTA_EXPECT_MASTER])
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3);
else
@@ -1678,7 +1721,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
return err;
- exp = nf_ct_expect_find_get(net, 0, &tuple);
+ exp = nf_ct_expect_find_get(net, zone, &tuple);
if (!exp)
return -ENOENT;
@@ -1725,16 +1768,21 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
struct hlist_node *n, *next;
u_int8_t u3 = nfmsg->nfgen_family;
unsigned int i;
+ u16 zone;
int err;
if (cda[CTA_EXPECT_TUPLE]) {
/* delete a single expect by tuple */
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
if (err < 0)
return err;
/* bump usage count to 2 */
- exp = nf_ct_expect_find_get(net, 0, &tuple);
+ exp = nf_ct_expect_find_get(net, zone, &tuple);
if (!exp)
return -ENOENT;
@@ -1796,7 +1844,8 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x,
}
static int
-ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[],
+ctnetlink_create_expect(struct net *net, u16 zone,
+ const struct nlattr * const cda[],
u_int8_t u3,
u32 pid, int report)
{
@@ -1819,7 +1868,7 @@ ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[],
return err;
/* Look for master conntrack of this expectation */
- h = nf_conntrack_find_get(net, 0, &master_tuple);
+ h = nf_conntrack_find_get(net, zone, &master_tuple);
if (!h)
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
@@ -1864,25 +1913,30 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
struct nf_conntrack_expect *exp;
struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u_int8_t u3 = nfmsg->nfgen_family;
- int err = 0;
+ u16 zone;
+ int err;
if (!cda[CTA_EXPECT_TUPLE]
|| !cda[CTA_EXPECT_MASK]
|| !cda[CTA_EXPECT_MASTER])
return -EINVAL;
+ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone);
+ if (err < 0)
+ return err;
+
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
if (err < 0)
return err;
spin_lock_bh(&nf_conntrack_lock);
- exp = __nf_ct_expect_find(net, 0, &tuple);
+ exp = __nf_ct_expect_find(net, zone, &tuple);
if (!exp) {
spin_unlock_bh(&nf_conntrack_lock);
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE) {
- err = ctnetlink_create_expect(net, cda,
+ err = ctnetlink_create_expect(net, zone, cda,
u3,
NETLINK_CB(skb).pid,
nlmsg_report(nlh));
^ permalink raw reply related [flat|nested] 4+ messages in thread