summaryrefslogtreecommitdiffstats
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/Kconfig33
-rw-r--r--net/netfilter/Makefile9
-rw-r--r--net/netfilter/core.c263
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_gen.h10
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ip.c8
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ipmac.c8
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_port.c8
-rw-r--r--net/netfilter/ipset/ip_set_core.c36
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h38
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c21
-rw-r--r--net/netfilter/ipvs/ip_vs_app.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c4
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c12
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_tcp.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_udp.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c9
-rw-r--r--net/netfilter/nf_conncount.c373
-rw-r--r--net/netfilter/nf_conntrack_core.c28
-rw-r--r--net/netfilter/nf_conntrack_expect.c1
-rw-r--r--net/netfilter/nf_conntrack_h323_asn1.c40
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c77
-rw-r--r--net/netfilter/nf_conntrack_netlink.c22
-rw-r--r--net/netfilter/nf_conntrack_proto.c18
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c21
-rw-r--r--net/netfilter/nf_conntrack_proto_generic.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c21
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c25
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c10
-rw-r--r--net/netfilter/nf_conntrack_standalone.c14
-rw-r--r--net/netfilter/nf_flow_table.c429
-rw-r--r--net/netfilter/nf_flow_table_inet.c48
-rw-r--r--net/netfilter/nf_internals.h2
-rw-r--r--net/netfilter/nf_log.c1
-rw-r--r--net/netfilter/nf_queue.c96
-rw-r--r--net/netfilter/nf_synproxy_core.c1
-rw-r--r--net/netfilter/nf_tables_api.c1658
-rw-r--r--net/netfilter/nf_tables_inet.c88
-rw-r--r--net/netfilter/nf_tables_netdev.c87
-rw-r--r--net/netfilter/nfnetlink.c4
-rw-r--r--net/netfilter/nfnetlink_acct.c2
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c2
-rw-r--r--net/netfilter/nfnetlink_log.c1
-rw-r--r--net/netfilter/nfnetlink_queue.c10
-rw-r--r--net/netfilter/nft_cmp.c2
-rw-r--r--net/netfilter/nft_compat.c26
-rw-r--r--net/netfilter/nft_ct.c16
-rw-r--r--net/netfilter/nft_dynset.c4
-rw-r--r--net/netfilter/nft_flow_offload.c264
-rw-r--r--net/netfilter/nft_log.c4
-rw-r--r--net/netfilter/nft_masq.c2
-rw-r--r--net/netfilter/nft_meta.c45
-rw-r--r--net/netfilter/nft_nat.c2
-rw-r--r--net/netfilter/nft_redir.c2
-rw-r--r--net/netfilter/nft_rt.c15
-rw-r--r--net/netfilter/nft_set_hash.c10
-rw-r--r--net/netfilter/utils.c90
-rw-r--r--net/netfilter/x_tables.c41
-rw-r--r--net/netfilter/xt_TCPMSS.c5
-rw-r--r--net/netfilter/xt_addrtype.c15
-rw-r--r--net/netfilter/xt_bpf.c14
-rw-r--r--net/netfilter/xt_connlimit.c369
-rw-r--r--net/netfilter/xt_hashlimit.c5
-rw-r--r--net/netfilter/xt_ipcomp.c2
-rw-r--r--net/netfilter/xt_policy.c3
-rw-r--r--net/netfilter/xt_set.c119
67 files changed, 3065 insertions, 1542 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e4a13cc8a2e7..9019fa98003d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -12,6 +12,12 @@ config NETFILTER_INGRESS
config NETFILTER_NETLINK
tristate
+config NETFILTER_FAMILY_BRIDGE
+ bool
+
+config NETFILTER_FAMILY_ARP
+ bool
+
config NETFILTER_NETLINK_ACCT
tristate "Netfilter NFACCT over NFNETLINK interface"
depends on NETFILTER_ADVANCED
@@ -62,6 +68,8 @@ config NF_LOG_NETDEV
select NF_LOG_COMMON
if NF_CONNTRACK
+config NETFILTER_CONNCOUNT
+ tristate
config NF_CONNTRACK_MARK
bool 'Connection mark tracking support'
@@ -497,6 +505,13 @@ config NFT_CT
This option adds the "ct" expression that you can use to match
connection tracking information such as the flow state.
+config NFT_FLOW_OFFLOAD
+ depends on NF_CONNTRACK && NF_FLOW_TABLE
+ tristate "Netfilter nf_tables hardware flow offload module"
+ help
+ This option adds the "flow_offload" expression that you can use to
+ choose what flows are placed into the hardware.
+
config NFT_SET_RBTREE
tristate "Netfilter nf_tables rbtree set module"
help
@@ -649,6 +664,23 @@ endif # NF_TABLES_NETDEV
endif # NF_TABLES
+config NF_FLOW_TABLE_INET
+ tristate "Netfilter flow table mixed IPv4/IPv6 module"
+ depends on NF_FLOW_TABLE_IPV4 && NF_FLOW_TABLE_IPV6
+ select NF_FLOW_TABLE
+ help
+ This option adds the flow table mixed IPv4/IPv6 support.
+
+ To compile it as a module, choose M here.
+
+config NF_FLOW_TABLE
+ tristate "Netfilter flow table module"
+ depends on NF_CONNTRACK && NF_TABLES
+ help
+ This option adds the flow table core infrastructure.
+
+ To compile it as a module, choose M here.
+
config NETFILTER_XTABLES
tristate "Netfilter Xtables support (required for ip_tables)"
default m if NETFILTER_ADVANCED=n
@@ -1120,6 +1152,7 @@ config NETFILTER_XT_MATCH_CONNLIMIT
tristate '"connlimit" match support'
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
+ select NETFILTER_CONNCOUNT
---help---
This match allows you to match against the number of parallel
connections to a server per client IP address (or address block).
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index f78ed2470831..5d9b8b959e58 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
+netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o
nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
@@ -67,6 +67,8 @@ obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
# SYNPROXY
obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
+obj-$(CONFIG_NETFILTER_CONNCOUNT) += nf_conncount.o
+
# generic packet duplication from netdev family
obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o
@@ -84,6 +86,7 @@ obj-$(CONFIG_NFT_META) += nft_meta.o
obj-$(CONFIG_NFT_RT) += nft_rt.o
obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o
obj-$(CONFIG_NFT_CT) += nft_ct.o
+obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o
obj-$(CONFIG_NFT_LIMIT) += nft_limit.o
obj-$(CONFIG_NFT_NAT) += nft_nat.o
obj-$(CONFIG_NFT_OBJREF) += nft_objref.o
@@ -107,6 +110,10 @@ obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o
obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o
obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o
+# flow table infrastructure
+obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
+obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
+
# generic X tables
obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 52cd2901a097..0f6b8172fb9a 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -4,8 +4,7 @@
* Thanks to Rob `CmdrTaco' Malda for not influencing this code in any
* way.
*
- * Rusty Russell (C)2000 -- This code is GPL.
- * Patrick McHardy (c) 2006-2012
+ * This code is GPL.
*/
#include <linux/kernel.h>
#include <linux/netfilter.h>
@@ -28,34 +27,12 @@
#include "nf_internals.h"
-static DEFINE_MUTEX(afinfo_mutex);
-
-const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
-EXPORT_SYMBOL(nf_afinfo);
const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
EXPORT_SYMBOL_GPL(nf_ipv6_ops);
DEFINE_PER_CPU(bool, nf_skb_duplicated);
EXPORT_SYMBOL_GPL(nf_skb_duplicated);
-int nf_register_afinfo(const struct nf_afinfo *afinfo)
-{
- mutex_lock(&afinfo_mutex);
- RCU_INIT_POINTER(nf_afinfo[afinfo->family], afinfo);
- mutex_unlock(&afinfo_mutex);
- return 0;
-}
-EXPORT_SYMBOL_GPL(nf_register_afinfo);
-
-void nf_unregister_afinfo(const struct nf_afinfo *afinfo)
-{
- mutex_lock(&afinfo_mutex);
- RCU_INIT_POINTER(nf_afinfo[afinfo->family], NULL);
- mutex_unlock(&afinfo_mutex);
- synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
-
#ifdef HAVE_JUMP_LABEL
struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
EXPORT_SYMBOL(nf_hooks_needed);
@@ -74,7 +51,8 @@ static struct nf_hook_entries *allocate_hook_entries_size(u16 num)
struct nf_hook_entries *e;
size_t alloc = sizeof(*e) +
sizeof(struct nf_hook_entry) * num +
- sizeof(struct nf_hook_ops *) * num;
+ sizeof(struct nf_hook_ops *) * num +
+ sizeof(struct nf_hook_entries_rcu_head);
if (num == 0)
return NULL;
@@ -85,6 +63,30 @@ static struct nf_hook_entries *allocate_hook_entries_size(u16 num)
return e;
}
+static void __nf_hook_entries_free(struct rcu_head *h)
+{
+ struct nf_hook_entries_rcu_head *head;
+
+ head = container_of(h, struct nf_hook_entries_rcu_head, head);
+ kvfree(head->allocation);
+}
+
+static void nf_hook_entries_free(struct nf_hook_entries *e)
+{
+ struct nf_hook_entries_rcu_head *head;
+ struct nf_hook_ops **ops;
+ unsigned int num;
+
+ if (!e)
+ return;
+
+ num = e->num_hook_entries;
+ ops = nf_hook_entries_get_hook_ops(e);
+ head = (void *)&ops[num];
+ head->allocation = e;
+ call_rcu(&head->head, __nf_hook_entries_free);
+}
+
static unsigned int accept_all(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -135,6 +137,12 @@ nf_hook_entries_grow(const struct nf_hook_entries *old,
++i;
continue;
}
+
+ if (reg->nat_hook && orig_ops[i]->nat_hook) {
+ kvfree(new);
+ return ERR_PTR(-EBUSY);
+ }
+
if (inserted || reg->priority > orig_ops[i]->priority) {
new_ops[nhooks] = (void *)orig_ops[i];
new->hooks[nhooks] = old->hooks[i];
@@ -237,27 +245,61 @@ out_assign:
return old;
}
-static struct nf_hook_entries __rcu **nf_hook_entry_head(struct net *net, const struct nf_hook_ops *reg)
+static struct nf_hook_entries __rcu **
+nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
+ struct net_device *dev)
{
- if (reg->pf != NFPROTO_NETDEV)
- return net->nf.hooks[reg->pf]+reg->hooknum;
+ switch (pf) {
+ case NFPROTO_NETDEV:
+ break;
+#ifdef CONFIG_NETFILTER_FAMILY_ARP
+ case NFPROTO_ARP:
+ if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum))
+ return NULL;
+ return net->nf.hooks_arp + hooknum;
+#endif
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ case NFPROTO_BRIDGE:
+ if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum))
+ return NULL;
+ return net->nf.hooks_bridge + hooknum;
+#endif
+ case NFPROTO_IPV4:
+ if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum))
+ return NULL;
+ return net->nf.hooks_ipv4 + hooknum;
+ case NFPROTO_IPV6:
+ if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum))
+ return NULL;
+ return net->nf.hooks_ipv6 + hooknum;
+#if IS_ENABLED(CONFIG_DECNET)
+ case NFPROTO_DECNET:
+ if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_decnet) <= hooknum))
+ return NULL;
+ return net->nf.hooks_decnet + hooknum;
+#endif
+ default:
+ WARN_ON_ONCE(1);
+ return NULL;
+ }
#ifdef CONFIG_NETFILTER_INGRESS
- if (reg->hooknum == NF_NETDEV_INGRESS) {
- if (reg->dev && dev_net(reg->dev) == net)
- return &reg->dev->nf_hooks_ingress;
+ if (hooknum == NF_NETDEV_INGRESS) {
+ if (dev && dev_net(dev) == net)
+ return &dev->nf_hooks_ingress;
}
#endif
WARN_ON_ONCE(1);
return NULL;
}
-int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
+static int __nf_register_net_hook(struct net *net, int pf,
+ const struct nf_hook_ops *reg)
{
struct nf_hook_entries *p, *new_hooks;
struct nf_hook_entries __rcu **pp;
- if (reg->pf == NFPROTO_NETDEV) {
+ if (pf == NFPROTO_NETDEV) {
#ifndef CONFIG_NETFILTER_INGRESS
if (reg->hooknum == NF_NETDEV_INGRESS)
return -EOPNOTSUPP;
@@ -267,7 +309,7 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
return -EINVAL;
}
- pp = nf_hook_entry_head(net, reg);
+ pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev);
if (!pp)
return -EINVAL;
@@ -285,21 +327,19 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
hooks_validate(new_hooks);
#ifdef CONFIG_NETFILTER_INGRESS
- if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
+ if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
net_inc_ingress_queue();
#endif
#ifdef HAVE_JUMP_LABEL
- static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
+ static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]);
#endif
- synchronize_net();
BUG_ON(p == new_hooks);
- kvfree(p);
+ nf_hook_entries_free(p);
return 0;
}
-EXPORT_SYMBOL(nf_register_net_hook);
/*
- * __nf_unregister_net_hook - remove a hook from blob
+ * nf_remove_net_hook - remove a hook from blob
*
* @oldp: current address of hook blob
* @unreg: hook to unregister
@@ -307,8 +347,8 @@ EXPORT_SYMBOL(nf_register_net_hook);
* This cannot fail, hook unregistration must always succeed.
* Therefore replace the to-be-removed hook with a dummy hook.
*/
-static void __nf_unregister_net_hook(struct nf_hook_entries *old,
- const struct nf_hook_ops *unreg)
+static void nf_remove_net_hook(struct nf_hook_entries *old,
+ const struct nf_hook_ops *unreg, int pf)
{
struct nf_hook_ops **orig_ops;
bool found = false;
@@ -326,24 +366,24 @@ static void __nf_unregister_net_hook(struct nf_hook_entries *old,
if (found) {
#ifdef CONFIG_NETFILTER_INGRESS
- if (unreg->pf == NFPROTO_NETDEV && unreg->hooknum == NF_NETDEV_INGRESS)
+ if (pf == NFPROTO_NETDEV && unreg->hooknum == NF_NETDEV_INGRESS)
net_dec_ingress_queue();
#endif
#ifdef HAVE_JUMP_LABEL
- static_key_slow_dec(&nf_hooks_needed[unreg->pf][unreg->hooknum]);
+ static_key_slow_dec(&nf_hooks_needed[pf][unreg->hooknum]);
#endif
} else {
- WARN_ONCE(1, "hook not found, pf %d num %d", unreg->pf, unreg->hooknum);
+ WARN_ONCE(1, "hook not found, pf %d num %d", pf, unreg->hooknum);
}
}
-void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
+static void __nf_unregister_net_hook(struct net *net, int pf,
+ const struct nf_hook_ops *reg)
{
struct nf_hook_entries __rcu **pp;
struct nf_hook_entries *p;
- unsigned int nfq;
- pp = nf_hook_entry_head(net, reg);
+ pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev);
if (!pp)
return;
@@ -355,23 +395,52 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
return;
}
- __nf_unregister_net_hook(p, reg);
+ nf_remove_net_hook(p, reg, pf);
p = __nf_hook_entries_try_shrink(pp);
mutex_unlock(&nf_hook_mutex);
if (!p)
return;
- synchronize_net();
+ nf_queue_nf_hook_drop(net);
+ nf_hook_entries_free(p);
+}
- /* other cpu might still process nfqueue verdict that used reg */
- nfq = nf_queue_nf_hook_drop(net);
- if (nfq)
- synchronize_net();
- kvfree(p);
+void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
+{
+ if (reg->pf == NFPROTO_INET) {
+ __nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+ __nf_unregister_net_hook(net, NFPROTO_IPV6, reg);
+ } else {
+ __nf_unregister_net_hook(net, reg->pf, reg);
+ }
}
EXPORT_SYMBOL(nf_unregister_net_hook);
+int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
+{
+ int err;
+
+ if (reg->pf == NFPROTO_INET) {
+ err = __nf_register_net_hook(net, NFPROTO_IPV4, reg);
+ if (err < 0)
+ return err;
+
+ err = __nf_register_net_hook(net, NFPROTO_IPV6, reg);
+ if (err < 0) {
+ __nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+ return err;
+ }
+ } else {
+ err = __nf_register_net_hook(net, reg->pf, reg);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(nf_register_net_hook);
+
int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg,
unsigned int n)
{
@@ -395,63 +464,10 @@ EXPORT_SYMBOL(nf_register_net_hooks);
void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg,
unsigned int hookcount)
{
- struct nf_hook_entries *to_free[16], *p;
- struct nf_hook_entries __rcu **pp;
- unsigned int i, j, n;
-
- mutex_lock(&nf_hook_mutex);
- for (i = 0; i < hookcount; i++) {
- pp = nf_hook_entry_head(net, &reg[i]);
- if (!pp)
- continue;
-
- p = nf_entry_dereference(*pp);
- if (WARN_ON_ONCE(!p))
- continue;
- __nf_unregister_net_hook(p, &reg[i]);
- }
- mutex_unlock(&nf_hook_mutex);
-
- do {
- n = min_t(unsigned int, hookcount, ARRAY_SIZE(to_free));
-
- mutex_lock(&nf_hook_mutex);
-
- for (i = 0, j = 0; i < hookcount && j < n; i++) {
- pp = nf_hook_entry_head(net, &reg[i]);
- if (!pp)
- continue;
-
- p = nf_entry_dereference(*pp);
- if (!p)
- continue;
-
- to_free[j] = __nf_hook_entries_try_shrink(pp);
- if (to_free[j])
- ++j;
- }
-
- mutex_unlock(&nf_hook_mutex);
-
- if (j) {
- unsigned int nfq;
-
- synchronize_net();
-
- /* need 2nd synchronize_net() if nfqueue is used, skb
- * can get reinjected right before nf_queue_hook_drop()
- */
- nfq = nf_queue_nf_hook_drop(net);
- if (nfq)
- synchronize_net();
-
- for (i = 0; i < j; i++)
- kvfree(to_free[i]);
- }
+ unsigned int i;
- reg += n;
- hookcount -= n;
- } while (hookcount > 0);
+ for (i = 0; i < hookcount; i++)
+ nf_unregister_net_hook(net, &reg[i]);
}
EXPORT_SYMBOL(nf_unregister_net_hooks);
@@ -569,14 +585,27 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
EXPORT_SYMBOL(nf_nat_decode_session_hook);
#endif
-static int __net_init netfilter_net_init(struct net *net)
+static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
{
- int i, h;
+ int h;
- for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) {
- for (h = 0; h < NF_MAX_HOOKS; h++)
- RCU_INIT_POINTER(net->nf.hooks[i][h], NULL);
- }
+ for (h = 0; h < max; h++)
+ RCU_INIT_POINTER(e[h], NULL);
+}
+
+static int __net_init netfilter_net_init(struct net *net)
+{
+ __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4));
+ __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6));
+#ifdef CONFIG_NETFILTER_FAMILY_ARP
+ __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp));
+#endif
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge));
+#endif
+#if IS_ENABLED(CONFIG_DECNET)
+ __netfilter_net_init(net->nf.hooks_decnet, ARRAY_SIZE(net->nf.hooks_decnet));
+#endif
#ifdef CONFIG_PROC_FS
net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter",
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 5ca18f07683b..257ca393e6f2 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -127,14 +127,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (ret <= 0)
return ret;
- if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(x, set)))
- return 0;
- if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(x, set), ext, mext, flags);
- if (SET_WITH_SKBINFO(set))
- ip_set_get_skbinfo(ext_skbinfo(x, set), ext, mext, flags);
- return 1;
+ return ip_set_match_extensions(set, ext, mext, flags, x);
}
static int
@@ -227,6 +220,7 @@ mtype_list(const struct ip_set *set,
rcu_read_lock();
for (; cb->args[IPSET_CB_ARG0] < map->elements;
cb->args[IPSET_CB_ARG0]++) {
+ cond_resched_rcu();
id = cb->args[IPSET_CB_ARG0];
x = get_ext(set, map, id);
if (!test_bit(id, map->members) ||
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index d8975a0b4282..488d6d05c65c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -263,12 +263,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip);
if (ret)
return ret;
- if (first_ip > last_ip) {
- u32 tmp = first_ip;
-
- first_ip = last_ip;
- last_ip = tmp;
- }
+ if (first_ip > last_ip)
+ swap(first_ip, last_ip);
} else if (tb[IPSET_ATTR_CIDR]) {
u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 4c279fbd2d5d..c00b6a2e8e3c 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -337,12 +337,8 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip);
if (ret)
return ret;
- if (first_ip > last_ip) {
- u32 tmp = first_ip;
-
- first_ip = last_ip;
- last_ip = tmp;
- }
+ if (first_ip > last_ip)
+ swap(first_ip, last_ip);
} else if (tb[IPSET_ATTR_CIDR]) {
u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 7f9bbd7c98b5..b561ca8b3659 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -238,12 +238,8 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
first_port = ip_set_get_h16(tb[IPSET_ATTR_PORT]);
last_port = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
- if (first_port > last_port) {
- u16 tmp = first_port;
-
- first_port = last_port;
- last_port = tmp;
- }
+ if (first_port > last_port)
+ swap(first_port, last_port);
elements = last_port - first_port + 1;
set->dsize = ip_set_elem_len(set, tb, 0, 0);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index cf84f7b37cd9..975a85a48d39 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -57,7 +57,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
/* When the nfnl mutex is held: */
#define ip_set_dereference(p) \
- rcu_dereference_protected(p, 1)
+ rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
#define ip_set(inst, id) \
ip_set_dereference((inst)->ip_set_list)[id]
@@ -472,6 +472,31 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
}
EXPORT_SYMBOL_GPL(ip_set_put_extensions);
+bool
+ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags, void *data)
+{
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(data, set)))
+ return false;
+ if (SET_WITH_COUNTER(set)) {
+ struct ip_set_counter *counter = ext_counter(data, set);
+
+ if (flags & IPSET_FLAG_MATCH_COUNTERS &&
+ !(ip_set_match_counter(ip_set_get_packets(counter),
+ mext->packets, mext->packets_op) &&
+ ip_set_match_counter(ip_set_get_bytes(counter),
+ mext->bytes, mext->bytes_op)))
+ return false;
+ ip_set_update_counter(counter, ext, flags);
+ }
+ if (SET_WITH_SKBINFO(set))
+ ip_set_get_skbinfo(ext_skbinfo(data, set),
+ ext, mext, flags);
+ return true;
+}
+EXPORT_SYMBOL_GPL(ip_set_match_extensions);
+
/* Creating/destroying/renaming/swapping affect the existence and
* the properties of a set. All of these can be executed from userspace
* only and serialized by the nfnl mutex indirectly from nfnetlink.
@@ -1386,11 +1411,9 @@ dump_last:
goto next_set;
if (set->variant->uref)
set->variant->uref(set, cb, true);
- /* Fall through and add elements */
+ /* fall through */
default:
- rcu_read_lock_bh();
ret = set->variant->list(set, skb, cb);
- rcu_read_unlock_bh();
if (!cb->args[IPSET_CB_ARG0])
/* Set is done, proceed with next one */
goto next_set;
@@ -2055,6 +2078,7 @@ ip_set_net_exit(struct net *net)
inst->is_deleted = true; /* flag for ip_set_nfnl_put */
+ nfnl_lock(NFNL_SUBSYS_IPSET);
for (i = 0; i < inst->ip_set_max; i++) {
set = ip_set(inst, i);
if (set) {
@@ -2062,6 +2086,7 @@ ip_set_net_exit(struct net *net)
ip_set_destroy_set(set);
}
}
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
kfree(rcu_dereference_protected(inst->ip_set_list, 1));
}
@@ -2097,7 +2122,6 @@ ip_set_init(void)
return ret;
}
- pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
return 0;
}
@@ -2113,3 +2137,5 @@ ip_set_fini(void)
module_init(ip_set_init);
module_exit(ip_set_fini);
+
+MODULE_DESCRIPTION("ip_set: protocol " __stringify(IPSET_PROTOCOL));
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index efffc8eabafe..bbad940c0137 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -917,12 +917,9 @@ static inline int
mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
struct ip_set_ext *mext, struct ip_set *set, u32 flags)
{
- if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(data, set),
- ext, mext, flags);
- if (SET_WITH_SKBINFO(set))
- ip_set_get_skbinfo(ext_skbinfo(data, set),
- ext, mext, flags);
+ if (!ip_set_match_extensions(set, ext, mext, flags, data))
+ return 0;
+ /* nomatch entries return -ENOTEMPTY */
return mtype_do_data_match(data);
}
@@ -941,9 +938,9 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
struct mtype_elem *data;
#if IPSET_NET_COUNT == 2
struct mtype_elem orig = *d;
- int i, j = 0, k;
+ int ret, i, j = 0, k;
#else
- int i, j = 0;
+ int ret, i, j = 0;
#endif
u32 key, multi = 0;
@@ -969,18 +966,13 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
data = ahash_data(n, i, set->dsize);
if (!mtype_data_equal(data, d, &multi))
continue;
- if (SET_WITH_TIMEOUT(set)) {
- if (!ip_set_timeout_expired(
- ext_timeout(data, set)))
- return mtype_data_match(data, ext,
- mext, set,
- flags);
+ ret = mtype_data_match(data, ext, mext, set, flags);
+ if (ret != 0)
+ return ret;
#ifdef IP_SET_HASH_WITH_MULTI
- multi = 0;
+ /* No match, reset multiple match flag */
+ multi = 0;
#endif
- } else
- return mtype_data_match(data, ext,
- mext, set, flags);
}
#if IPSET_NET_COUNT == 2
}
@@ -1027,12 +1019,11 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (!test_bit(i, n->used))
continue;
data = ahash_data(n, i, set->dsize);
- if (mtype_data_equal(data, d, &multi) &&
- !(SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, set)))) {
- ret = mtype_data_match(data, ext, mext, set, flags);
+ if (!mtype_data_equal(data, d, &multi))
+ continue;
+ ret = mtype_data_match(data, ext, mext, set, flags);
+ if (ret != 0)
goto out;
- }
}
out:
return ret;
@@ -1143,6 +1134,7 @@ mtype_list(const struct ip_set *set,
rcu_read_lock();
for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits);
cb->args[IPSET_CB_ARG0]++) {
+ cond_resched_rcu();
incomplete = skb_tail_pointer(skb);
n = rcu_dereference(hbucket(t, cb->args[IPSET_CB_ARG0]));
pr_debug("cb->arg bucket: %lu, t %p n %p\n",
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e864681b8dc5..072a658fde04 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -55,8 +55,9 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
struct ip_set_adt_opt *opt, const struct ip_set_ext *ext)
{
struct list_set *map = set->data;
+ struct ip_set_ext *mext = &opt->ext;
struct set_elem *e;
- u32 cmdflags = opt->cmdflags;
+ u32 flags = opt->cmdflags;
int ret;
/* Don't lookup sub-counters at all */
@@ -64,21 +65,11 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
list_for_each_entry_rcu(e, &map->members, list) {
- if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, set)))
- continue;
ret = ip_set_test(e->id, skb, par, opt);
- if (ret > 0) {
- if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(e, set),
- ext, &opt->ext,
- cmdflags);
- if (SET_WITH_SKBINFO(set))
- ip_set_get_skbinfo(ext_skbinfo(e, set),
- ext, &opt->ext,
- cmdflags);
- return ret;
- }
+ if (ret <= 0)
+ continue;
+ if (ip_set_match_extensions(set, ext, mext, flags, e))
+ return 1;
}
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 299edc6add5a..1c98c907bc63 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -595,7 +595,6 @@ static int ip_vs_app_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_app_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_app_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 3e053cb30070..370abbf6f421 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -322,7 +322,7 @@ ip_vs_conn_fill_param_proto(struct netns_ipvs *ipvs,
{
__be16 _ports[2], *pptr;
- pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
+ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports);
if (pptr == NULL)
return 1;
@@ -1143,7 +1143,6 @@ static int ip_vs_conn_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_conn_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_conn_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -1221,7 +1220,6 @@ static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_conn_sync_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_conn_sync_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5cb7cac9177d..5f6f73cf2174 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -433,7 +433,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
/*
* IPv6 frags, only the first hit here.
*/
- pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
+ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports);
if (pptr == NULL)
return NULL;
@@ -566,7 +566,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct netns_ipvs *ipvs = svc->ipvs;
struct net *net = ipvs->net;
- pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
+ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports);
if (!pptr)
return NF_DROP;
dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0];
@@ -982,7 +982,7 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
unsigned int offset;
*related = 1;
- ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
+ ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph);
if (ic == NULL)
return NF_DROP;
@@ -1214,7 +1214,7 @@ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum,
return NULL;
pptr = frag_safe_skb_hp(skb, iph->len,
- sizeof(_ports), _ports, iph);
+ sizeof(_ports), _ports);
if (!pptr)
return NULL;
@@ -1407,7 +1407,7 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
__be16 _ports[2], *pptr;
pptr = frag_safe_skb_hp(skb, iph.len,
- sizeof(_ports), _ports, &iph);
+ sizeof(_ports), _ports);
if (pptr == NULL)
return NF_ACCEPT; /* Not for me */
if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr,
@@ -1741,7 +1741,7 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb,
*related = 1;
- ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
+ ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph);
if (ic == NULL)
return NF_DROP;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index fff213eacf2a..5ebde4b15810 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2116,7 +2116,6 @@ static int ip_vs_info_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_info_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_info_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -2161,7 +2160,6 @@ static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_stats_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_stats_seq_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -2230,7 +2228,6 @@ static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
}
static const struct file_operations ip_vs_stats_percpu_fops = {
- .owner = THIS_MODULE,
.open = ip_vs_stats_percpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 121a321b91be..bcd9b7bde4ee 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -315,6 +315,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
switch (skb->ip_summed) {
case CHECKSUM_NONE:
skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0);
+ /* fall through */
case CHECKSUM_COMPLETE:
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 30e11cd6aa8a..c15ef7c2a1fa 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -319,6 +319,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
case CHECKSUM_NONE:
skb->csum = skb_checksum(skb, udphoff,
skb->len - udphoff, 0);
+ /* fall through */
case CHECKSUM_COMPLETE:
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 9ee71cb276d7..fbaf3bd05b2e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1636,17 +1636,14 @@ static int
ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
{
struct msghdr msg = {NULL,};
- struct kvec iov;
+ struct kvec iov = {buffer, buflen};
int len;
EnterFunction(7);
/* Receive a packet */
- iov.iov_base = buffer;
- iov.iov_len = (size_t)buflen;
-
- len = kernel_recvmsg(sock, &msg, &iov, 1, buflen, MSG_DONTWAIT);
-
+ iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen);
+ len = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
if (len < 0)
return len;
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
new file mode 100644
index 000000000000..6d65389e308f
--- /dev/null
+++ b/net/netfilter/nf_conncount.c
@@ -0,0 +1,373 @@
+/*
+ * count the number of connections matching an arbitrary key.
+ *
+ * (C) 2017 Red Hat GmbH
+ * Author: Florian Westphal <fw@strlen.de>
+ *
+ * split from xt_connlimit.c:
+ * (c) 2000 Gerd Knorr <kraxel@bytesex.org>
+ * Nov 2002: Martin Bene <martin.bene@icomedias.com>:
+ * only ignore TIME_WAIT or gone connections
+ * (C) CC Computer Consultants GmbH, 2007
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/netfilter/nf_conntrack_tcp.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_count.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+
+#define CONNCOUNT_SLOTS 256U
+
+#ifdef CONFIG_LOCKDEP
+#define CONNCOUNT_LOCK_SLOTS 8U
+#else
+#define CONNCOUNT_LOCK_SLOTS 256U
+#endif
+
+#define CONNCOUNT_GC_MAX_NODES 8
+#define MAX_KEYLEN 5
+
+/* we will save the tuples of all connections we care about */
+struct nf_conncount_tuple {
+ struct hlist_node node;
+ struct nf_conntrack_tuple tuple;
+};
+
+struct nf_conncount_rb {
+ struct rb_node node;
+ struct hlist_head hhead; /* connections/hosts in same subnet */
+ u32 key[MAX_KEYLEN];
+};
+
+static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp;
+
+struct nf_conncount_data {
+ unsigned int keylen;
+ struct rb_root root[CONNCOUNT_SLOTS];
+};
+
+static u_int32_t conncount_rnd __read_mostly;
+static struct kmem_cache *conncount_rb_cachep __read_mostly;
+static struct kmem_cache *conncount_conn_cachep __read_mostly;
+
+static inline bool already_closed(const struct nf_conn *conn)
+{
+ if (nf_ct_protonum(conn) == IPPROTO_TCP)
+ return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT ||
+ conn->proto.tcp.state == TCP_CONNTRACK_CLOSE;
+ else
+ return false;
+}
+
+static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
+{
+ return memcmp(a, b, klen * sizeof(u32));
+}
+
+static bool add_hlist(struct hlist_head *head,
+ const struct nf_conntrack_tuple *tuple)
+{
+ struct nf_conncount_tuple *conn;
+
+ conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+ if (conn == NULL)
+ return false;
+ conn->tuple = *tuple;
+ hlist_add_head(&conn->node, head);
+ return true;
+}
+
+static unsigned int check_hlist(struct net *net,
+ struct hlist_head *head,
+ const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_zone *zone,
+ bool *addit)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ struct nf_conncount_tuple *conn;
+ struct hlist_node *n;
+ struct nf_conn *found_ct;
+ unsigned int length = 0;
+
+ *addit = true;
+
+ /* check the saved connections */
+ hlist_for_each_entry_safe(conn, n, head, node) {
+ found = nf_conntrack_find_get(net, zone, &conn->tuple);
+ if (found == NULL) {
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ continue;
+ }
+
+ found_ct = nf_ct_tuplehash_to_ctrack(found);
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple)) {
+ /*
+ * Just to be sure we have it only once in the list.
+ * We should not see tuples twice unless someone hooks
+ * this into a table without "-p tcp --syn".
+ */
+ *addit = false;
+ } else if (already_closed(found_ct)) {
+ /*
+ * we do not care about connections which are
+ * closed already -> ditch it
+ */
+ nf_ct_put(found_ct);
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ continue;
+ }
+
+ nf_ct_put(found_ct);
+ length++;
+ }
+
+ return length;
+}
+
+static void tree_nodes_free(struct rb_root *root,
+ struct nf_conncount_rb *gc_nodes[],
+ unsigned int gc_count)
+{
+ struct nf_conncount_rb *rbconn;
+
+ while (gc_count) {
+ rbconn = gc_nodes[--gc_count];
+ rb_erase(&rbconn->node, root);
+ kmem_cache_free(conncount_rb_cachep, rbconn);
+ }
+}
+
+static unsigned int
+count_tree(struct net *net, struct rb_root *root,
+ const u32 *key, u8 keylen,
+ u8 family,
+ const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_zone *zone)
+{
+ struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
+ struct rb_node **rbnode, *parent;
+ struct nf_conncount_rb *rbconn;
+ struct nf_conncount_tuple *conn;
+ unsigned int gc_count;
+ bool no_gc = false;
+
+ restart:
+ gc_count = 0;
+ parent = NULL;
+ rbnode = &(root->rb_node);
+ while (*rbnode) {
+ int diff;
+ bool addit;
+
+ rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node);
+
+ parent = *rbnode;
+ diff = key_diff(key, rbconn->key, keylen);
+ if (diff < 0) {
+ rbnode = &((*rbnode)->rb_left);
+ } else if (diff > 0) {
+ rbnode = &((*rbnode)->rb_right);
+ } else {
+ /* same source network -> be counted! */
+ unsigned int count;
+ count = check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
+
+ tree_nodes_free(root, gc_nodes, gc_count);
+ if (!addit)
+ return count;
+
+ if (!add_hlist(&rbconn->hhead, tuple))
+ return 0; /* hotdrop */
+
+ return count + 1;
+ }
+
+ if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
+ continue;
+
+ /* only used for GC on hhead, retval and 'addit' ignored */
+ check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
+ if (hlist_empty(&rbconn->hhead))
+ gc_nodes[gc_count++] = rbconn;
+ }
+
+ if (gc_count) {
+ no_gc = true;
+ tree_nodes_free(root, gc_nodes, gc_count);
+ /* tree_node_free before new allocation permits
+ * allocator to re-use newly free'd object.
+ *
+ * This is a rare event; in most cases we will find
+ * existing node to re-use. (or gc_count is 0).
+ */
+ goto restart;
+ }
+
+ /* no match, need to insert new node */
+ rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
+ if (rbconn == NULL)
+ return 0;
+
+ conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+ if (conn == NULL) {
+ kmem_cache_free(conncount_rb_cachep, rbconn);
+ return 0;
+ }
+
+ conn->tuple = *tuple;
+ memcpy(rbconn->key, key, sizeof(u32) * keylen);
+
+ INIT_HLIST_HEAD(&rbconn->hhead);
+ hlist_add_head(&conn->node, &rbconn->hhead);
+
+ rb_link_node(&rbconn->node, parent, rbnode);
+ rb_insert_color(&rbconn->node, root);
+ return 1;
+}
+
+unsigned int nf_conncount_count(struct net *net,
+ struct nf_conncount_data *data,
+ const u32 *key,
+ unsigned int family,
+ const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_zone *zone)
+{
+ struct rb_root *root;
+ int count;
+ u32 hash;
+
+ hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
+ root = &data->root[hash];
+
+ spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+
+ count = count_tree(net, root, key, data->keylen, family, tuple, zone);
+
+ spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+
+ return count;
+}
+EXPORT_SYMBOL_GPL(nf_conncount_count);
+
+struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
+ unsigned int keylen)
+{
+ struct nf_conncount_data *data;
+ int ret, i;
+
+ if (keylen % sizeof(u32) ||
+ keylen / sizeof(u32) > MAX_KEYLEN ||
+ keylen == 0)
+ return ERR_PTR(-EINVAL);
+
+ net_get_random_once(&conncount_rnd, sizeof(conncount_rnd));
+
+ data = kmalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ ret = nf_ct_netns_get(net, family);
+ if (ret < 0) {
+ kfree(data);
+ return ERR_PTR(ret);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(data->root); ++i)
+ data->root[i] = RB_ROOT;
+
+ data->keylen = keylen / sizeof(u32);
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(nf_conncount_init);
+
+static void destroy_tree(struct rb_root *r)
+{
+ struct nf_conncount_tuple *conn;
+ struct nf_conncount_rb *rbconn;
+ struct hlist_node *n;
+ struct rb_node *node;
+
+ while ((node = rb_first(r)) != NULL) {
+ rbconn = rb_entry(node, struct nf_conncount_rb, node);
+
+ rb_erase(node, r);
+
+ hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node)
+ kmem_cache_free(conncount_conn_cachep, conn);
+
+ kmem_cache_free(conncount_rb_cachep, rbconn);
+ }
+}
+
+void nf_conncount_destroy(struct net *net, unsigned int family,
+ struct nf_conncount_data *data)
+{
+ unsigned int i;
+
+ nf_ct_netns_put(net, family);
+
+ for (i = 0; i < ARRAY_SIZE(data->root); ++i)
+ destroy_tree(&data->root[i]);
+
+ kfree(data);
+}
+EXPORT_SYMBOL_GPL(nf_conncount_destroy);
+
+static int __init nf_conncount_modinit(void)
+{
+ int i;
+
+ BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS);
+ BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0);
+
+ for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i)
+ spin_lock_init(&nf_conncount_locks[i]);
+
+ conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple",
+ sizeof(struct nf_conncount_tuple),
+ 0, 0, NULL);
+ if (!conncount_conn_cachep)
+ return -ENOMEM;
+
+ conncount_rb_cachep = kmem_cache_create("nf_conncount_rb",
+ sizeof(struct nf_conncount_rb),
+ 0, 0, NULL);
+ if (!conncount_rb_cachep) {
+ kmem_cache_destroy(conncount_conn_cachep);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void __exit nf_conncount_modexit(void)
+{
+ kmem_cache_destroy(conncount_conn_cachep);
+ kmem_cache_destroy(conncount_rb_cachep);
+}
+
+module_init(nf_conncount_modinit);
+module_exit(nf_conncount_modexit);
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("netfilter: count number of connections matching a key");
+MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 85f643c1e227..705198de671d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -58,8 +58,6 @@
#include "nf_internals.h"
-#define NF_CONNTRACK_VERSION "0.5.0"
-
int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
enum nf_nat_manip_type manip,
const struct nlattr *attr) __read_mostly;
@@ -901,6 +899,9 @@ static unsigned int early_drop_list(struct net *net,
hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
+ if (test_bit(IPS_OFFLOAD_BIT, &tmp->status))
+ continue;
+
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
continue;
@@ -975,6 +976,18 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
return false;
}
+#define DAY (86400 * HZ)
+
+/* Set an arbitrary timeout large enough not to ever expire, this save
+ * us a check for the IPS_OFFLOAD_BIT from the packet path via
+ * nf_ct_is_expired().
+ */
+static void nf_ct_offload_timeout(struct nf_conn *ct)
+{
+ if (nf_ct_expires(ct) < DAY / 2)
+ ct->timeout = nfct_time_stamp + DAY;
+}
+
static void gc_worker(struct work_struct *work)
{
unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
@@ -1011,6 +1024,11 @@ static void gc_worker(struct work_struct *work)
tmp = nf_ct_tuplehash_to_ctrack(h);
scanned++;
+ if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
+ nf_ct_offload_timeout(tmp);
+ continue;
+ }
+
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
expired_count++;
@@ -1044,7 +1062,7 @@ static void gc_worker(struct work_struct *work)
* we will just continue with next hash slot.
*/
rcu_read_unlock();
- cond_resched_rcu_qs();
+ cond_resched();
} while (++buckets < goal);
if (gc_work->exiting)
@@ -2048,10 +2066,6 @@ int nf_conntrack_init_start(void)
if (!nf_conntrack_cachep)
goto err_cachep;
- printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
- NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
- nf_conntrack_max);
-
ret = nf_conntrack_expect_init();
if (ret < 0)
goto err_expect;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index d6748a8a79c5..8ef21d9f9a00 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -649,7 +649,6 @@ static int exp_open(struct inode *inode, struct file *file)
}
static const struct file_operations exp_file_ops = {
- .owner = THIS_MODULE,
.open = exp_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index dc6347342e34..1601275efe2d 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -1,4 +1,4 @@
-/****************************************************************************
+/*
* ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323
* conntrack/NAT module.
*
@@ -8,7 +8,7 @@
*
* See ip_conntrack_helper_h323_asn1.h for details.
*
- ****************************************************************************/
+ */
#ifdef __KERNEL__
#include <linux/kernel.h>
@@ -140,14 +140,15 @@ static const decoder_t Decoders[] = {
decode_choice,
};
-/****************************************************************************
+/*
* H.323 Types
- ****************************************************************************/
+ */
#include "nf_conntrack_h323_types.c"
-/****************************************************************************
+/*
* Functions
- ****************************************************************************/
+ */
+
/* Assume bs is aligned && v < 16384 */
static unsigned int get_len(struct bitstr *bs)
{
@@ -177,7 +178,6 @@ static int nf_h323_error_boundary(struct bitstr *bs, size_t bytes, size_t bits)
return 0;
}
-/****************************************************************************/
static unsigned int get_bit(struct bitstr *bs)
{
unsigned int b = (*bs->cur) & (0x80 >> bs->bit);
@@ -187,7 +187,6 @@ static unsigned int get_bit(struct bitstr *bs)
return b;
}
-/****************************************************************************/
/* Assume b <= 8 */
static unsigned int get_bits(struct bitstr *bs, unsigned int b)
{
@@ -213,7 +212,6 @@ static unsigned int get_bits(struct bitstr *bs, unsigned int b)
return v;
}
-/****************************************************************************/
/* Assume b <= 32 */
static unsigned int get_bitmap(struct bitstr *bs, unsigned int b)
{
@@ -251,9 +249,9 @@ static unsigned int get_bitmap(struct bitstr *bs, unsigned int b)
return v;
}
-/****************************************************************************
+/*
* Assume bs is aligned and sizeof(unsigned int) == 4
- ****************************************************************************/
+ */
static unsigned int get_uint(struct bitstr *bs, int b)
{
unsigned int v = 0;
@@ -262,12 +260,15 @@ static unsigned int get_uint(struct bitstr *bs, int b)
case 4:
v |= *bs->cur++;
v <<= 8;
+ /* fall through */
case 3:
v |= *bs->cur++;
v <<= 8;
+ /* fall through */
case 2:
v |= *bs->cur++;
v <<= 8;
+ /* fall through */
case 1:
v |= *bs->cur++;
break;
@@ -275,7 +276,6 @@ static unsigned int get_uint(struct bitstr *bs, int b)
return v;
}
-/****************************************************************************/
static int decode_nul(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -284,7 +284,6 @@ static int decode_nul(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_bool(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -296,7 +295,6 @@ static int decode_bool(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_oid(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -316,7 +314,6 @@ static int decode_oid(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_int(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -364,7 +361,6 @@ static int decode_int(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_enum(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -381,7 +377,6 @@ static int decode_enum(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_bitstr(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -418,7 +413,6 @@ static int decode_bitstr(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_numstr(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -439,7 +433,6 @@ static int decode_numstr(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_octstr(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -493,7 +486,6 @@ static int decode_octstr(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_bmpstr(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -523,7 +515,6 @@ static int decode_bmpstr(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_seq(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -653,7 +644,6 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
static int decode_seqof(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -750,8 +740,6 @@ static int decode_seqof(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-
-/****************************************************************************/
static int decode_choice(struct bitstr *bs, const struct field_t *f,
char *base, int level)
{
@@ -833,7 +821,6 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f,
return H323_ERROR_NONE;
}
-/****************************************************************************/
int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage *ras)
{
static const struct field_t ras_message = {
@@ -849,7 +836,6 @@ int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage *ras)
return decode_choice(&bs, &ras_message, (char *) ras, 0);
}
-/****************************************************************************/
static int DecodeH323_UserInformation(unsigned char *buf, unsigned char *beg,
size_t sz, H323_UserInformation *uuie)
{
@@ -867,7 +853,6 @@ static int DecodeH323_UserInformation(unsigned char *buf, unsigned char *beg,
return decode_seq(&bs, &h323_userinformation, (char *) uuie, 0);
}
-/****************************************************************************/
int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz,
MultimediaSystemControlMessage *
mscm)
@@ -886,7 +871,6 @@ int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz,
(char *) mscm, 0);
}
-/****************************************************************************/
int DecodeQ931(unsigned char *buf, size_t sz, Q931 *q931)
{
unsigned char *p = buf;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index f71f0d2558fd..005589c6d0f6 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -24,6 +24,7 @@
#include <linux/skbuff.h>
#include <net/route.h>
#include <net/ip6_route.h>
+#include <linux/netfilter_ipv6.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
@@ -115,7 +116,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_h245;
static struct nf_conntrack_helper nf_conntrack_helper_q931[];
static struct nf_conntrack_helper nf_conntrack_helper_ras[];
-/****************************************************************************/
static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo,
unsigned char **data, int *datalen, int *dataoff)
@@ -219,7 +219,6 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
return 0;
}
-/****************************************************************************/
static int get_h245_addr(struct nf_conn *ct, const unsigned char *data,
H245_TransportAddress *taddr,
union nf_inet_addr *addr, __be16 *port)
@@ -254,7 +253,6 @@ static int get_h245_addr(struct nf_conn *ct, const unsigned char *data,
return 1;
}
-/****************************************************************************/
static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -328,7 +326,6 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
return ret;
}
-/****************************************************************************/
static int expect_t120(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -380,7 +377,6 @@ static int expect_t120(struct sk_buff *skb,
return ret;
}
-/****************************************************************************/
static int process_h245_channel(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -410,7 +406,6 @@ static int process_h245_channel(struct sk_buff *skb,
return 0;
}
-/****************************************************************************/
static int process_olc(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -472,7 +467,6 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_olca(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
@@ -542,7 +536,6 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_h245(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
@@ -578,7 +571,6 @@ static int process_h245(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int h245_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
@@ -628,7 +620,6 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff,
return NF_DROP;
}
-/****************************************************************************/
static const struct nf_conntrack_expect_policy h245_exp_policy = {
.max_expected = H323_RTP_CHANNEL_MAX * 4 + 2 /* T.120 */,
.timeout = 240,
@@ -643,7 +634,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
.expect_policy = &h245_exp_policy,
};
-/****************************************************************************/
int get_h225_addr(struct nf_conn *ct, unsigned char *data,
TransportAddress *taddr,
union nf_inet_addr *addr, __be16 *port)
@@ -675,7 +665,6 @@ int get_h225_addr(struct nf_conn *ct, unsigned char *data,
return 1;
}
-/****************************************************************************/
static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
@@ -726,20 +715,15 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
}
/* If the calling party is on the same side of the forward-to party,
- * we don't need to track the second call */
+ * we don't need to track the second call
+ */
static int callforward_do_filter(struct net *net,
const union nf_inet_addr *src,
const union nf_inet_addr *dst,
u_int8_t family)
{
- const struct nf_afinfo *afinfo;
int ret = 0;
- /* rcu_read_lock()ed by nf_hook_thresh */
- afinfo = nf_get_afinfo(family);
- if (!afinfo)
- return 0;
-
switch (family) {
case AF_INET: {
struct flowi4 fl1, fl2;
@@ -750,10 +734,10 @@ static int callforward_do_filter(struct net *net,
memset(&fl2, 0, sizeof(fl2));
fl2.daddr = dst->ip;
- if (!afinfo->route(net, (struct dst_entry **)&rt1,
- flowi4_to_flowi(&fl1), false)) {
- if (!afinfo->route(net, (struct dst_entry **)&rt2,
- flowi4_to_flowi(&fl2), false)) {
+ if (!nf_ip_route(net, (struct dst_entry **)&rt1,
+ flowi4_to_flowi(&fl1), false)) {
+ if (!nf_ip_route(net, (struct dst_entry **)&rt2,
+ flowi4_to_flowi(&fl2), false)) {
if (rt_nexthop(rt1, fl1.daddr) ==
rt_nexthop(rt2, fl2.daddr) &&
rt1->dst.dev == rt2->dst.dev)
@@ -766,18 +750,23 @@ static int callforward_do_filter(struct net *net,
}
#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
case AF_INET6: {
- struct flowi6 fl1, fl2;
+ const struct nf_ipv6_ops *v6ops;
struct rt6_info *rt1, *rt2;
+ struct flowi6 fl1, fl2;
+
+ v6ops = nf_get_ipv6_ops();
+ if (!v6ops)
+ return 0;
memset(&fl1, 0, sizeof(fl1));
fl1.daddr = src->in6;
memset(&fl2, 0, sizeof(fl2));
fl2.daddr = dst->in6;
- if (!afinfo->route(net, (struct dst_entry **)&rt1,
- flowi6_to_flowi(&fl1), false)) {
- if (!afinfo->route(net, (struct dst_entry **)&rt2,
- flowi6_to_flowi(&fl2), false)) {
+ if (!v6ops->route(net, (struct dst_entry **)&rt1,
+ flowi6_to_flowi(&fl1), false)) {
+ if (!v6ops->route(net, (struct dst_entry **)&rt2,
+ flowi6_to_flowi(&fl2), false)) {
if (ipv6_addr_equal(rt6_nexthop(rt1, &fl1.daddr),
rt6_nexthop(rt2, &fl2.daddr)) &&
rt1->dst.dev == rt2->dst.dev)
@@ -794,7 +783,6 @@ static int callforward_do_filter(struct net *net,
}
-/****************************************************************************/
static int expect_callforwarding(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -815,7 +803,8 @@ static int expect_callforwarding(struct sk_buff *skb,
return 0;
/* If the calling party is on the same side of the forward-to party,
- * we don't need to track the second call */
+ * we don't need to track the second call
+ */
if (callforward_filter &&
callforward_do_filter(net, &addr, &ct->tuplehash[!dir].tuple.src.u3,
nf_ct_l3num(ct))) {
@@ -854,7 +843,6 @@ static int expect_callforwarding(struct sk_buff *skb,
return ret;
}
-/****************************************************************************/
static int process_setup(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -925,7 +913,6 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_callproceeding(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
@@ -958,7 +945,6 @@ static int process_callproceeding(struct sk_buff *skb,
return 0;
}
-/****************************************************************************/
static int process_connect(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -990,7 +976,6 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_alerting(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1022,7 +1007,6 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_facility(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1063,7 +1047,6 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_progress(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1095,7 +1078,6 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_q931(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data, int dataoff,
@@ -1154,7 +1136,6 @@ static int process_q931(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int q931_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
@@ -1203,7 +1184,6 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff,
return NF_DROP;
}
-/****************************************************************************/
static const struct nf_conntrack_expect_policy q931_exp_policy = {
/* T.120 and H.245 */
.max_expected = H323_RTP_CHANNEL_MAX * 4 + 4,
@@ -1231,7 +1211,6 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = {
},
};
-/****************************************************************************/
static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff,
int *datalen)
{
@@ -1249,7 +1228,6 @@ static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff,
return skb_header_pointer(skb, dataoff, *datalen, h323_buffer);
}
-/****************************************************************************/
static struct nf_conntrack_expect *find_expect(struct nf_conn *ct,
union nf_inet_addr *addr,
__be16 port)
@@ -1270,7 +1248,6 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct,
return NULL;
}
-/****************************************************************************/
static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff, unsigned char **data,
@@ -1328,7 +1305,6 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
return ret;
}
-/****************************************************************************/
static int process_grq(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1346,7 +1322,6 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1391,7 +1366,6 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
return ret;
}
-/****************************************************************************/
static int process_rrq(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1428,7 +1402,6 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1480,7 +1453,6 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_urq(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1514,7 +1486,6 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_arq(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1559,7 +1530,6 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1608,7 +1578,6 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
return ret;
}
-/****************************************************************************/
static int process_lrq(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1626,7 +1595,6 @@ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1666,7 +1634,6 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
return ret;
}
-/****************************************************************************/
static int process_irr(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1700,7 +1667,6 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int process_ras(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int protoff,
@@ -1745,7 +1711,6 @@ static int process_ras(struct sk_buff *skb, struct nf_conn *ct,
return 0;
}
-/****************************************************************************/
static int ras_help(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
@@ -1788,7 +1753,6 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff,
return NF_DROP;
}
-/****************************************************************************/
static const struct nf_conntrack_expect_policy ras_exp_policy = {
.max_expected = 32,
.timeout = 240,
@@ -1849,7 +1813,6 @@ static void __exit h323_helper_exit(void)
nf_conntrack_helper_unregister(&nf_conntrack_helper_h245);
}
-/****************************************************************************/
static void __exit nf_conntrack_h323_fini(void)
{
h323_helper_exit();
@@ -1857,7 +1820,6 @@ static void __exit nf_conntrack_h323_fini(void)
pr_debug("nf_ct_h323: fini\n");
}
-/****************************************************************************/
static int __init nf_conntrack_h323_init(void)
{
int ret;
@@ -1877,7 +1839,6 @@ err1:
return ret;
}
-/****************************************************************************/
module_init(nf_conntrack_h323_init);
module_exit(nf_conntrack_h323_fini);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 382d49792f42..dd177ebee9aa 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -57,8 +57,6 @@
MODULE_LICENSE("GPL");
-static char __initdata version[] = "0.93";
-
static int ctnetlink_dump_tuples_proto(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_l4proto *l4proto)
@@ -544,7 +542,7 @@ static size_t ctnetlink_proto_size(const struct nf_conn *ct)
len *= 3u; /* ORIG, REPLY, MASTER */
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
- len += l4proto->nla_size;
+ len += l4proto->nlattr_size;
if (l4proto->nlattr_tuple_size) {
len4 = l4proto->nlattr_tuple_size();
len4 *= 3u; /* ORIG, REPLY, MASTER */
@@ -1110,6 +1108,14 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
.len = NF_CT_LABELS_MAX_SIZE },
};
+static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data)
+{
+ if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
+ return 0;
+
+ return ctnetlink_filter_match(ct, data);
+}
+
static int ctnetlink_flush_conntrack(struct net *net,
const struct nlattr * const cda[],
u32 portid, int report)
@@ -1122,7 +1128,7 @@ static int ctnetlink_flush_conntrack(struct net *net,
return PTR_ERR(filter);
}
- nf_ct_iterate_cleanup_net(net, ctnetlink_filter_match, filter,
+ nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter,
portid, report);
kfree(filter);
@@ -1168,6 +1174,11 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
ct = nf_ct_tuplehash_to_ctrack(h);
+ if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) {
+ nf_ct_put(ct);
+ return -EBUSY;
+ }
+
if (cda[CTA_ID]) {
u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
if (id != (u32)(unsigned long)ct) {
@@ -3412,7 +3423,6 @@ static int __init ctnetlink_init(void)
{
int ret;
- pr_info("ctnetlink v%s: registering with nfnetlink.\n", version);
ret = nfnetlink_subsys_register(&ctnl_subsys);
if (ret < 0) {
pr_err("ctnetlink_init: cannot register with nfnetlink.\n");
@@ -3446,8 +3456,6 @@ err_out:
static void __exit ctnetlink_exit(void)
{
- pr_info("ctnetlink: unregistering from nfnetlink.\n");
-
unregister_pernet_subsys(&ctnetlink_net_ops);
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
nfnetlink_subsys_unregister(&ctnl_subsys);
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index c8e9c9503a08..afdeca53e88b 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -385,14 +385,14 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net,
/* FIXME: Allow NULL functions and sub in pointers to generic for
them. --RR */
-int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto)
+int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *l4proto)
{
int ret = 0;
if (l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos))
return -EBUSY;
- if ((l4proto->to_nlattr && !l4proto->nlattr_size) ||
+ if ((l4proto->to_nlattr && l4proto->nlattr_size == 0) ||
(l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size))
return -EINVAL;
@@ -428,10 +428,6 @@ int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto)
goto out_unlock;
}
- l4proto->nla_size = 0;
- if (l4proto->nlattr_size)
- l4proto->nla_size += l4proto->nlattr_size();
-
rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
l4proto);
out_unlock:
@@ -502,7 +498,7 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net,
}
EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one);
-int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto[],
+int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[],
unsigned int num_proto)
{
int ret = -EINVAL, ver;
@@ -524,7 +520,7 @@ int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto[],
EXPORT_SYMBOL_GPL(nf_ct_l4proto_register);
int nf_ct_l4proto_pernet_register(struct net *net,
- struct nf_conntrack_l4proto *const l4proto[],
+ const struct nf_conntrack_l4proto *const l4proto[],
unsigned int num_proto)
{
int ret = -EINVAL;
@@ -545,7 +541,7 @@ int nf_ct_l4proto_pernet_register(struct net *net,
}
EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register);
-void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto[],
+void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[],
unsigned int num_proto)
{
mutex_lock(&nf_ct_proto_mutex);
@@ -555,12 +551,12 @@ void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto[],
synchronize_net();
/* Remove all contrack entries for this protocol */
- nf_ct_iterate_destroy(kill_l4proto, l4proto);
+ nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto);
}
EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister);
void nf_ct_l4proto_pernet_unregister(struct net *net,
- struct nf_conntrack_l4proto *const l4proto[],
+ const struct nf_conntrack_l4proto *const l4proto[],
unsigned int num_proto)
{
while (num_proto-- != 0)
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 2a446f4a554c..abe647d5b8c6 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -654,6 +654,12 @@ static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = {
[CTA_PROTOINFO_DCCP_PAD] = { .type = NLA_UNSPEC },
};
+#define DCCP_NLATTR_SIZE ( \
+ NLA_ALIGN(NLA_HDRLEN + 1) + \
+ NLA_ALIGN(NLA_HDRLEN + 1) + \
+ NLA_ALIGN(NLA_HDRLEN + sizeof(u64)) + \
+ NLA_ALIGN(NLA_HDRLEN + 0))
+
static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
{
struct nlattr *attr = cda[CTA_PROTOINFO_DCCP];
@@ -691,13 +697,6 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
spin_unlock_bh(&ct->lock);
return 0;
}
-
-static int dccp_nlattr_size(void)
-{
- return nla_total_size(0) /* CTA_PROTOINFO_DCCP */
- + nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1);
-}
-
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
@@ -862,7 +861,7 @@ static struct nf_proto_net *dccp_get_net_proto(struct net *net)
return &net->ct.nf_ct_proto.dccp.pn;
}
-struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = {
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
.l3proto = AF_INET,
.l4proto = IPPROTO_DCCP,
.pkt_to_tuple = dccp_pkt_to_tuple,
@@ -876,8 +875,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = {
.print_conntrack = dccp_print_conntrack,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+ .nlattr_size = DCCP_NLATTR_SIZE,
.to_nlattr = dccp_to_nlattr,
- .nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
@@ -898,7 +897,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 __read_mostly = {
};
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_dccp4);
-struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 __read_mostly = {
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
.l3proto = AF_INET6,
.l4proto = IPPROTO_DCCP,
.pkt_to_tuple = dccp_pkt_to_tuple,
@@ -912,8 +911,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 __read_mostly = {
.print_conntrack = dccp_print_conntrack,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+ .nlattr_size = DCCP_NLATTR_SIZE,
.to_nlattr = dccp_to_nlattr,
- .nlattr_size = dccp_nlattr_size,
.from_nlattr = nlattr_to_dccp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 1f86ddf6649a..6c6896d21cd7 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -12,7 +12,7 @@
#include <linux/netfilter.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
-static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ;
+static const unsigned int nf_ct_generic_timeout = 600*HZ;
static bool nf_generic_should_process(u8 proto)
{
@@ -163,7 +163,7 @@ static struct nf_proto_net *generic_get_net_proto(struct net *net)
return &net->ct.nf_ct_proto.generic.pn;
}
-struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic =
{
.l3proto = PF_UNSPEC,
.l4proto = 255,
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index a2503005d80b..d049ea5a3770 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -48,7 +48,7 @@ enum grep_conntrack {
GRE_CT_MAX
};
-static unsigned int gre_timeouts[GRE_CT_MAX] = {
+static const unsigned int gre_timeouts[GRE_CT_MAX] = {
[GRE_CT_UNREPLIED] = 30*HZ,
[GRE_CT_REPLIED] = 180*HZ,
};
@@ -352,7 +352,7 @@ static int gre_init_net(struct net *net, u_int16_t proto)
}
/* protocol helper struct */
-static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = {
+static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
.l3proto = AF_INET,
.l4proto = IPPROTO_GRE,
.pkt_to_tuple = gre_pkt_to_tuple,
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 80faf04ddf15..fb9a35d16069 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -52,7 +52,7 @@ static const char *const sctp_conntrack_names[] = {
#define HOURS * 60 MINS
#define DAYS * 24 HOURS
-static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = {
+static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
[SCTP_CONNTRACK_CLOSED] = 10 SECS,
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
@@ -578,6 +578,11 @@ static const struct nla_policy sctp_nla_policy[CTA_PROTOINFO_SCTP_MAX+1] = {
[CTA_PROTOINFO_SCTP_VTAG_REPLY] = { .type = NLA_U32 },
};
+#define SCTP_NLATTR_SIZE ( \
+ NLA_ALIGN(NLA_HDRLEN + 1) + \
+ NLA_ALIGN(NLA_HDRLEN + 4) + \
+ NLA_ALIGN(NLA_HDRLEN + 4))
+
static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
{
struct nlattr *attr = cda[CTA_PROTOINFO_SCTP];
@@ -608,12 +613,6 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
return 0;
}
-
-static int sctp_nlattr_size(void)
-{
- return nla_total_size(0) /* CTA_PROTOINFO_SCTP */
- + nla_policy_len(sctp_nla_policy, CTA_PROTOINFO_SCTP_MAX + 1);
-}
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
@@ -778,7 +777,7 @@ static struct nf_proto_net *sctp_get_net_proto(struct net *net)
return &net->ct.nf_ct_proto.sctp.pn;
}
-struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
.l3proto = PF_INET,
.l4proto = IPPROTO_SCTP,
.pkt_to_tuple = sctp_pkt_to_tuple,
@@ -793,8 +792,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
.can_early_drop = sctp_can_early_drop,
.me = THIS_MODULE,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+ .nlattr_size = SCTP_NLATTR_SIZE,
.to_nlattr = sctp_to_nlattr,
- .nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
@@ -815,7 +814,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
};
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_sctp4);
-struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
.l3proto = PF_INET6,
.l4proto = IPPROTO_SCTP,
.pkt_to_tuple = sctp_pkt_to_tuple,
@@ -830,8 +829,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
.can_early_drop = sctp_can_early_drop,
.me = THIS_MODULE,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+ .nlattr_size = SCTP_NLATTR_SIZE,
.to_nlattr = sctp_to_nlattr,
- .nlattr_size = sctp_nlattr_size,
.from_nlattr = nlattr_to_sctp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 37ef35b861f2..e97cdc1cf98c 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -68,7 +68,7 @@ static const char *const tcp_conntrack_names[] = {
#define HOURS * 60 MINS
#define DAYS * 24 HOURS
-static unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] __read_mostly = {
+static const unsigned int tcp_timeouts[TCP_CONNTRACK_TIMEOUT_MAX] = {
[TCP_CONNTRACK_SYN_SENT] = 2 MINS,
[TCP_CONNTRACK_SYN_RECV] = 60 SECS,
[TCP_CONNTRACK_ESTABLISHED] = 5 DAYS,
@@ -305,6 +305,9 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
/* Print out the private part of the conntrack. */
static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
{
+ if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
+ return;
+
seq_printf(s, "%s ", tcp_conntrack_names[ct->proto.tcp.state]);
}
#endif
@@ -1222,6 +1225,12 @@ static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = {
[CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) },
};
+#define TCP_NLATTR_SIZE ( \
+ NLA_ALIGN(NLA_HDRLEN + 1) + \
+ NLA_ALIGN(NLA_HDRLEN + 1) + \
+ NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))) + \
+ NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))))
+
static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
{
struct nlattr *pattr = cda[CTA_PROTOINFO_TCP];
@@ -1274,12 +1283,6 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
return 0;
}
-static int tcp_nlattr_size(void)
-{
- return nla_total_size(0) /* CTA_PROTOINFO_TCP */
- + nla_policy_len(tcp_nla_policy, CTA_PROTOINFO_TCP_MAX + 1);
-}
-
static unsigned int tcp_nlattr_tuple_size(void)
{
static unsigned int size __read_mostly;
@@ -1541,7 +1544,7 @@ static struct nf_proto_net *tcp_get_net_proto(struct net *net)
return &net->ct.nf_ct_proto.tcp.pn;
}
-struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
{
.l3proto = PF_INET,
.l4proto = IPPROTO_TCP,
@@ -1557,11 +1560,11 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
.can_early_drop = tcp_can_early_drop,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.to_nlattr = tcp_to_nlattr,
- .nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
.nlattr_tuple_size = tcp_nlattr_tuple_size,
+ .nlattr_size = TCP_NLATTR_SIZE,
.nla_policy = nf_ct_port_nla_policy,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
@@ -1579,7 +1582,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
};
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp4);
-struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
{
.l3proto = PF_INET6,
.l4proto = IPPROTO_TCP,
@@ -1594,8 +1597,8 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
.error = tcp_error,
.can_early_drop = tcp_can_early_drop,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+ .nlattr_size = TCP_NLATTR_SIZE,
.to_nlattr = tcp_to_nlattr,
- .nlattr_size = tcp_nlattr_size,
.from_nlattr = nlattr_to_tcp,
.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 3a5f727103af..fe7243970aa4 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -26,7 +26,7 @@
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
-static unsigned int udp_timeouts[UDP_CT_MAX] = {
+static const unsigned int udp_timeouts[UDP_CT_MAX] = {
[UDP_CT_UNREPLIED] = 30*HZ,
[UDP_CT_REPLIED] = 180*HZ,
};
@@ -296,7 +296,7 @@ static struct nf_proto_net *udp_get_net_proto(struct net *net)
return &net->ct.nf_ct_proto.udp.pn;
}
-struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
{
.l3proto = PF_INET,
.l4proto = IPPROTO_UDP,
@@ -328,7 +328,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp4);
#ifdef CONFIG_NF_CT_PROTO_UDPLITE
-struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
{
.l3proto = PF_INET,
.l4proto = IPPROTO_UDPLITE,
@@ -360,7 +360,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly =
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite4);
#endif
-struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
{
.l3proto = PF_INET6,
.l4proto = IPPROTO_UDP,
@@ -392,7 +392,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly =
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp6);
#ifdef CONFIG_NF_CT_PROTO_UDPLITE
-struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly =
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
{
.l3proto = PF_INET6,
.l4proto = IPPROTO_UDPLITE,
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 5a101caa3e12..9123fdec5e14 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -309,10 +309,12 @@ static int ct_seq_show(struct seq_file *s, void *v)
WARN_ON(!l4proto);
ret = -ENOSPC;
- seq_printf(s, "%-8s %u %-8s %u %ld ",
+ seq_printf(s, "%-8s %u %-8s %u ",
l3proto_name(l3proto->l3proto), nf_ct_l3num(ct),
- l4proto_name(l4proto->l4proto), nf_ct_protonum(ct),
- nf_ct_expires(ct) / HZ);
+ l4proto_name(l4proto->l4proto), nf_ct_protonum(ct));
+
+ if (!test_bit(IPS_OFFLOAD_BIT, &ct->status))
+ seq_printf(s, "%ld ", nf_ct_expires(ct) / HZ);
if (l4proto->print_conntrack)
l4proto->print_conntrack(s, ct);
@@ -339,7 +341,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
goto release;
- if (test_bit(IPS_ASSURED_BIT, &ct->status))
+ if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
+ seq_puts(s, "[OFFLOAD] ");
+ else if (test_bit(IPS_ASSURED_BIT, &ct->status))
seq_puts(s, "[ASSURED] ");
if (seq_has_overflowed(s))
@@ -378,7 +382,6 @@ static int ct_open(struct inode *inode, struct file *file)
}
static const struct file_operations ct_file_ops = {
- .owner = THIS_MODULE,
.open = ct_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -471,7 +474,6 @@ static int ct_cpu_seq_open(struct inode *inode, struct file *file)
}
static const struct file_operations ct_cpu_seq_fops = {
- .owner = THIS_MODULE,
.open = ct_cpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table.c
new file mode 100644
index 000000000000..2f5099cb85b8
--- /dev/null
+++ b/net/netfilter/nf_flow_table.c
@@ -0,0 +1,429 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/netdevice.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+
+struct flow_offload_entry {
+ struct flow_offload flow;
+ struct nf_conn *ct;
+ struct rcu_head rcu_head;
+};
+
+struct flow_offload *
+flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
+{
+ struct flow_offload_entry *entry;
+ struct flow_offload *flow;
+
+ if (unlikely(nf_ct_is_dying(ct) ||
+ !atomic_inc_not_zero(&ct->ct_general.use)))
+ return NULL;
+
+ entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ goto err_ct_refcnt;
+
+ flow = &entry->flow;
+
+ if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst))
+ goto err_dst_cache_original;
+
+ if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst))
+ goto err_dst_cache_reply;
+
+ entry->ct = ct;
+
+ switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
+ case NFPROTO_IPV4:
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
+ break;
+ case NFPROTO_IPV6:
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
+ break;
+ }
+
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
+
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
+ route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
+ route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;
+
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
+ ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
+
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
+ FLOW_OFFLOAD_DIR_ORIGINAL;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
+ FLOW_OFFLOAD_DIR_REPLY;
+
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
+ route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
+ route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
+ route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
+ flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
+ route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
+
+ if (ct->status & IPS_SRC_NAT)
+ flow->flags |= FLOW_OFFLOAD_SNAT;
+ else if (ct->status & IPS_DST_NAT)
+ flow->flags |= FLOW_OFFLOAD_DNAT;
+
+ return flow;
+
+err_dst_cache_reply:
+ dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst);
+err_dst_cache_original:
+ kfree(entry);
+err_ct_refcnt:
+ nf_ct_put(ct);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(flow_offload_alloc);
+
+void flow_offload_free(struct flow_offload *flow)
+{
+ struct flow_offload_entry *e;
+
+ dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
+ dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
+ e = container_of(flow, struct flow_offload_entry, flow);
+ kfree(e);
+}
+EXPORT_SYMBOL_GPL(flow_offload_free);
+
+void flow_offload_dead(struct flow_offload *flow)
+{
+ flow->flags |= FLOW_OFFLOAD_DYING;
+}
+EXPORT_SYMBOL_GPL(flow_offload_dead);
+
+int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
+{
+ flow->timeout = (u32)jiffies;
+
+ rhashtable_insert_fast(&flow_table->rhashtable,
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
+ *flow_table->type->params);
+ rhashtable_insert_fast(&flow_table->rhashtable,
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
+ *flow_table->type->params);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(flow_offload_add);
+
+void flow_offload_del(struct nf_flowtable *flow_table,
+ struct flow_offload *flow)
+{
+ struct flow_offload_entry *e;
+
+ rhashtable_remove_fast(&flow_table->rhashtable,
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
+ *flow_table->type->params);
+ rhashtable_remove_fast(&flow_table->rhashtable,
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
+ *flow_table->type->params);
+
+ e = container_of(flow, struct flow_offload_entry, flow);
+ kfree_rcu(e, rcu_head);
+}
+EXPORT_SYMBOL_GPL(flow_offload_del);
+
+struct flow_offload_tuple_rhash *
+flow_offload_lookup(struct nf_flowtable *flow_table,
+ struct flow_offload_tuple *tuple)
+{
+ return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
+ *flow_table->type->params);
+}
+EXPORT_SYMBOL_GPL(flow_offload_lookup);
+
+static void nf_flow_release_ct(const struct flow_offload *flow)
+{
+ struct flow_offload_entry *e;
+
+ e = container_of(flow, struct flow_offload_entry, flow);
+ nf_ct_delete(e->ct, 0, 0);
+ nf_ct_put(e->ct);
+}
+
+int nf_flow_table_iterate(struct nf_flowtable *flow_table,
+ void (*iter)(struct flow_offload *flow, void *data),
+ void *data)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct rhashtable_iter hti;
+ struct flow_offload *flow;
+ int err;
+
+ err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
+ if (err)
+ return err;
+
+ rhashtable_walk_start(&hti);
+
+ while ((tuplehash = rhashtable_walk_next(&hti))) {
+ if (IS_ERR(tuplehash)) {
+ err = PTR_ERR(tuplehash);
+ if (err != -EAGAIN)
+ goto out;
+
+ continue;
+ }
+ if (tuplehash->tuple.dir)
+ continue;
+
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
+
+ iter(flow, data);
+ }
+out:
+ rhashtable_walk_stop(&hti);
+ rhashtable_walk_exit(&hti);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_iterate);
+
+static inline bool nf_flow_has_expired(const struct flow_offload *flow)
+{
+ return (__s32)(flow->timeout - (u32)jiffies) <= 0;
+}
+
+static inline bool nf_flow_is_dying(const struct flow_offload *flow)
+{
+ return flow->flags & FLOW_OFFLOAD_DYING;
+}
+
+void nf_flow_offload_work_gc(struct work_struct *work)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table;
+ struct rhashtable_iter hti;
+ struct flow_offload *flow;
+ int err;
+
+ flow_table = container_of(work, struct nf_flowtable, gc_work.work);
+
+ err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
+ if (err)
+ goto schedule;
+
+ rhashtable_walk_start(&hti);
+
+ while ((tuplehash = rhashtable_walk_next(&hti))) {
+ if (IS_ERR(tuplehash)) {
+ err = PTR_ERR(tuplehash);
+ if (err != -EAGAIN)
+ goto out;
+
+ continue;
+ }
+ if (tuplehash->tuple.dir)
+ continue;
+
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
+
+ if (nf_flow_has_expired(flow) ||
+ nf_flow_is_dying(flow)) {
+ flow_offload_del(flow_table, flow);
+ nf_flow_release_ct(flow);
+ }
+ }
+out:
+ rhashtable_walk_stop(&hti);
+ rhashtable_walk_exit(&hti);
+schedule:
+ queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
+
+static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple *tuple = data;
+
+ return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple_rhash *tuplehash = data;
+
+ return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct flow_offload_tuple *tuple = arg->key;
+ const struct flow_offload_tuple_rhash *x = ptr;
+
+ if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
+ return 1;
+
+ return 0;
+}
+
+const struct rhashtable_params nf_flow_offload_rhash_params = {
+ .head_offset = offsetof(struct flow_offload_tuple_rhash, node),
+ .hashfn = flow_offload_hash,
+ .obj_hashfn = flow_offload_hash_obj,
+ .obj_cmpfn = flow_offload_hash_cmp,
+ .automatic_shrinking = true,
+};
+EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params);
+
+static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
+ __be16 port, __be16 new_port)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ inet_proto_csum_replace2(&tcph->check, skb, port, new_port, true);
+
+ return 0;
+}
+
+static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
+ __be16 port, __be16 new_port)
+{
+ struct udphdr *udph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*udph)))
+ return -1;
+
+ udph = (void *)(skb_network_header(skb) + thoff);
+ if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace2(&udph->check, skb, port,
+ new_port, true);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff,
+ u8 protocol, __be16 port, __be16 new_port)
+{
+ switch (protocol) {
+ case IPPROTO_TCP:
+ if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0)
+ return NF_DROP;
+ break;
+ case IPPROTO_UDP:
+ if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0)
+ return NF_DROP;
+ break;
+ }
+
+ return 0;
+}
+
+int nf_flow_snat_port(const struct flow_offload *flow,
+ struct sk_buff *skb, unsigned int thoff,
+ u8 protocol, enum flow_offload_tuple_dir dir)
+{
+ struct flow_ports *hdr;
+ __be16 port, new_port;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*hdr)))
+ return -1;
+
+ hdr = (void *)(skb_network_header(skb) + thoff);
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ port = hdr->source;
+ new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port;
+ hdr->source = new_port;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ port = hdr->dest;
+ new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port;
+ hdr->dest = new_port;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
+}
+EXPORT_SYMBOL_GPL(nf_flow_snat_port);
+
+int nf_flow_dnat_port(const struct flow_offload *flow,
+ struct sk_buff *skb, unsigned int thoff,
+ u8 protocol, enum flow_offload_tuple_dir dir)
+{
+ struct flow_ports *hdr;
+ __be16 port, new_port;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*hdr)))
+ return -1;
+
+ hdr = (void *)(skb_network_header(skb) + thoff);
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ port = hdr->dest;
+ new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port;
+ hdr->dest = new_port;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ port = hdr->source;
+ new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port;
+ hdr->source = new_port;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
+}
+EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
new file mode 100644
index 000000000000..281209aeba8f
--- /dev/null
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -0,0 +1,48 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_tables.h>
+
+static unsigned int
+nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ return nf_flow_offload_ip_hook(priv, skb, state);
+ case htons(ETH_P_IPV6):
+ return nf_flow_offload_ipv6_hook(priv, skb, state);
+ }
+
+ return NF_ACCEPT;
+}
+
+static struct nf_flowtable_type flowtable_inet = {
+ .family = NFPROTO_INET,
+ .params = &nf_flow_offload_rhash_params,
+ .gc = nf_flow_offload_work_gc,
+ .hook = nf_flow_offload_inet_hook,
+ .owner = THIS_MODULE,
+};
+
+static int __init nf_flow_inet_module_init(void)
+{
+ nft_register_flowtable_type(&flowtable_inet);
+
+ return 0;
+}
+
+static void __exit nf_flow_inet_module_exit(void)
+{
+ nft_unregister_flowtable_type(&flowtable_inet);
+}
+
+module_init(nf_flow_inet_module_init);
+module_exit(nf_flow_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NF_FLOWTABLE(1); /* NFPROTO_INET */
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index 44284cd2528d..18f6d7ae995b 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -10,7 +10,7 @@
int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
const struct nf_hook_entries *entries, unsigned int index,
unsigned int verdict);
-unsigned int nf_queue_nf_hook_drop(struct net *net);
+void nf_queue_nf_hook_drop(struct net *net);
/* nf_log.c */
int __init netfilter_log_init(void);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8bb152a7cca4..c2c1b16b7538 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -402,7 +402,6 @@ static int nflog_open(struct inode *inode, struct file *file)
}
static const struct file_operations nflog_file_ops = {
- .owner = THIS_MODULE,
.open = nflog_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index f7e21953b1de..d67a96a25a68 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -10,6 +10,8 @@
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
#include <linux/seq_file.h>
#include <linux/rcupdate.h>
@@ -96,30 +98,56 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
}
EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
-unsigned int nf_queue_nf_hook_drop(struct net *net)
+void nf_queue_nf_hook_drop(struct net *net)
{
const struct nf_queue_handler *qh;
- unsigned int count = 0;
rcu_read_lock();
qh = rcu_dereference(net->nf.queue_handler);
if (qh)
- count = qh->nf_hook_drop(net);
+ qh->nf_hook_drop(net);
rcu_read_unlock();
-
- return count;
}
EXPORT_SYMBOL_GPL(nf_queue_nf_hook_drop);
+static void nf_ip_saveroute(const struct sk_buff *skb,
+ struct nf_queue_entry *entry)
+{
+ struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);
+
+ if (entry->state.hook == NF_INET_LOCAL_OUT) {
+ const struct iphdr *iph = ip_hdr(skb);
+
+ rt_info->tos = iph->tos;
+ rt_info->daddr = iph->daddr;
+ rt_info->saddr = iph->saddr;
+ rt_info->mark = skb->mark;
+ }
+}
+
+static void nf_ip6_saveroute(const struct sk_buff *skb,
+ struct nf_queue_entry *entry)
+{
+ struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
+
+ if (entry->state.hook == NF_INET_LOCAL_OUT) {
+ const struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ rt_info->daddr = iph->daddr;
+ rt_info->saddr = iph->saddr;
+ rt_info->mark = skb->mark;
+ }
+}
+
static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
const struct nf_hook_entries *entries,
unsigned int index, unsigned int queuenum)
{
int status = -ENOENT;
struct nf_queue_entry *entry = NULL;
- const struct nf_afinfo *afinfo;
const struct nf_queue_handler *qh;
struct net *net = state->net;
+ unsigned int route_key_size;
/* QUEUE == DROP if no one is waiting, to be safe. */
qh = rcu_dereference(net->nf.queue_handler);
@@ -128,11 +156,19 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
goto err;
}
- afinfo = nf_get_afinfo(state->pf);
- if (!afinfo)
- goto err;
+ switch (state->pf) {
+ case AF_INET:
+ route_key_size = sizeof(struct ip_rt_info);
+ break;
+ case AF_INET6:
+ route_key_size = sizeof(struct ip6_rt_info);
+ break;
+ default:
+ route_key_size = 0;
+ break;
+ }
- entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC);
+ entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC);
if (!entry) {
status = -ENOMEM;
goto err;
@@ -142,12 +178,21 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
.skb = skb,
.state = *state,
.hook_index = index,
- .size = sizeof(*entry) + afinfo->route_key_size,
+ .size = sizeof(*entry) + route_key_size,
};
nf_queue_entry_get_refs(entry);
skb_dst_force(skb);
- afinfo->saveroute(skb, entry);
+
+ switch (entry->state.pf) {
+ case AF_INET:
+ nf_ip_saveroute(skb, entry);
+ break;
+ case AF_INET6:
+ nf_ip6_saveroute(skb, entry);
+ break;
+ }
+
status = qh->outfn(entry, queuenum);
if (status < 0) {
@@ -204,13 +249,31 @@ repeat:
return NF_ACCEPT;
}
+static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum)
+{
+ switch (pf) {
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ case NFPROTO_BRIDGE:
+ return rcu_dereference(net->nf.hooks_bridge[hooknum]);
+#endif
+ case NFPROTO_IPV4:
+ return rcu_dereference(net->nf.hooks_ipv4[hooknum]);
+ case NFPROTO_IPV6:
+ return rcu_dereference(net->nf.hooks_ipv6[hooknum]);
+ default:
+ WARN_ON_ONCE(1);
+ return NULL;
+ }
+
+ return NULL;
+}
+
/* Caller must hold rcu read-side lock */
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
{
const struct nf_hook_entry *hook_entry;
const struct nf_hook_entries *hooks;
struct sk_buff *skb = entry->skb;
- const struct nf_afinfo *afinfo;
const struct net *net;
unsigned int i;
int err;
@@ -219,12 +282,12 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
net = entry->state.net;
pf = entry->state.pf;
- hooks = rcu_dereference(net->nf.hooks[pf][entry->state.hook]);
+ hooks = nf_hook_entries_head(net, pf, entry->state.hook);
nf_queue_entry_release_refs(entry);
i = entry->hook_index;
- if (WARN_ON_ONCE(i >= hooks->num_hook_entries)) {
+ if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) {
kfree_skb(skb);
kfree(entry);
return;
@@ -237,8 +300,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state);
if (verdict == NF_ACCEPT) {
- afinfo = nf_get_afinfo(entry->state.pf);
- if (!afinfo || afinfo->reroute(entry->state.net, skb, entry) < 0)
+ if (nf_reroute(skb, entry) < 0)
verdict = NF_DROP;
}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 49bd8bb16b18..92139a087260 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -317,7 +317,6 @@ static int synproxy_cpu_seq_open(struct inode *inode, struct file *file)
}
static const struct file_operations synproxy_cpu_seq_fops = {
- .owner = THIS_MODULE,
.open = synproxy_cpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 07bd4138c84e..0791813a1e7d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -17,6 +17,7 @@
#include <linux/netfilter.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/net_namespace.h>
@@ -24,86 +25,20 @@
static LIST_HEAD(nf_tables_expressions);
static LIST_HEAD(nf_tables_objects);
-
-/**
- * nft_register_afinfo - register nf_tables address family info
- *
- * @afi: address family info to register
- *
- * Register the address family for use with nf_tables. Returns zero on
- * success or a negative errno code otherwise.
- */
-int nft_register_afinfo(struct net *net, struct nft_af_info *afi)
-{
- INIT_LIST_HEAD(&afi->tables);
- nfnl_lock(NFNL_SUBSYS_NFTABLES);
- list_add_tail_rcu(&afi->list, &net->nft.af_info);
- nfnl_unlock(NFNL_SUBSYS_NFTABLES);
- return 0;
-}
-EXPORT_SYMBOL_GPL(nft_register_afinfo);
-
-static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi);
-
-/**
- * nft_unregister_afinfo - unregister nf_tables address family info
- *
- * @afi: address family info to unregister
- *
- * Unregister the address family for use with nf_tables.
- */
-void nft_unregister_afinfo(struct net *net, struct nft_af_info *afi)
-{
- nfnl_lock(NFNL_SUBSYS_NFTABLES);
- __nft_release_afinfo(net, afi);
- list_del_rcu(&afi->list);
- nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-}
-EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
-
-static struct nft_af_info *nft_afinfo_lookup(struct net *net, int family)
-{
- struct nft_af_info *afi;
-
- list_for_each_entry(afi, &net->nft.af_info, list) {
- if (afi->family == family)
- return afi;
- }
- return NULL;
-}
-
-static struct nft_af_info *
-nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
-{
- struct nft_af_info *afi;
-
- afi = nft_afinfo_lookup(net, family);
- if (afi != NULL)
- return afi;
-#ifdef CONFIG_MODULES
- if (autoload) {
- nfnl_unlock(NFNL_SUBSYS_NFTABLES);
- request_module("nft-afinfo-%u", family);
- nfnl_lock(NFNL_SUBSYS_NFTABLES);
- afi = nft_afinfo_lookup(net, family);
- if (afi != NULL)
- return ERR_PTR(-EAGAIN);
- }
-#endif
- return ERR_PTR(-EAFNOSUPPORT);
-}
+static LIST_HEAD(nf_tables_flowtables);
+static u64 table_handle;
static void nft_ctx_init(struct nft_ctx *ctx,
struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
- struct nft_af_info *afi,
+ u8 family,
struct nft_table *table,
struct nft_chain *chain,
const struct nlattr * const *nla)
{
ctx->net = net;
- ctx->afi = afi;
+ ctx->family = family;
ctx->table = table;
ctx->chain = chain;
ctx->nla = nla;
@@ -139,29 +74,26 @@ static void nft_trans_destroy(struct nft_trans *trans)
kfree(trans);
}
-static int nf_tables_register_hooks(struct net *net,
- const struct nft_table *table,
- struct nft_chain *chain,
- unsigned int hook_nops)
+static int nf_tables_register_hook(struct net *net,
+ const struct nft_table *table,
+ struct nft_chain *chain)
{
if (table->flags & NFT_TABLE_F_DORMANT ||
!nft_is_base_chain(chain))
return 0;
- return nf_register_net_hooks(net, nft_base_chain(chain)->ops,
- hook_nops);
+ return nf_register_net_hook(net, &nft_base_chain(chain)->ops);
}
-static void nf_tables_unregister_hooks(struct net *net,
- const struct nft_table *table,
- struct nft_chain *chain,
- unsigned int hook_nops)
+static void nf_tables_unregister_hook(struct net *net,
+ const struct nft_table *table,
+ struct nft_chain *chain)
{
if (table->flags & NFT_TABLE_F_DORMANT ||
!nft_is_base_chain(chain))
return;
- nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, hook_nops);
+ nf_unregister_net_hook(net, &nft_base_chain(chain)->ops);
}
static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
@@ -348,34 +280,99 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
return err;
}
+static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
+ struct nft_flowtable *flowtable)
+{
+ struct nft_trans *trans;
+
+ trans = nft_trans_alloc(ctx, msg_type,
+ sizeof(struct nft_trans_flowtable));
+ if (trans == NULL)
+ return -ENOMEM;
+
+ if (msg_type == NFT_MSG_NEWFLOWTABLE)
+ nft_activate_next(ctx->net, flowtable);
+
+ nft_trans_flowtable(trans) = flowtable;
+ list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+
+ return 0;
+}
+
+static int nft_delflowtable(struct nft_ctx *ctx,
+ struct nft_flowtable *flowtable)
+{
+ int err;
+
+ err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable);
+ if (err < 0)
+ return err;
+
+ nft_deactivate_next(ctx->net, flowtable);
+ ctx->table->use--;
+
+ return err;
+}
+
/*
* Tables
*/
-static struct nft_table *nft_table_lookup(const struct nft_af_info *afi,
+static struct nft_table *nft_table_lookup(const struct net *net,
const struct nlattr *nla,
- u8 genmask)
+ u8 family, u8 genmask)
{
struct nft_table *table;
- list_for_each_entry(table, &afi->tables, list) {
+ list_for_each_entry(table, &net->nft.tables, list) {
if (!nla_strcmp(nla, table->name) &&
+ table->family == family &&
nft_active_genmask(table, genmask))
return table;
}
return NULL;
}
-static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
+static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
+ const struct nlattr *nla,
+ u8 genmask)
+{
+ struct nft_table *table;
+
+ list_for_each_entry(table, &net->nft.tables, list) {
+ if (be64_to_cpu(nla_get_be64(nla)) == table->handle &&
+ nft_active_genmask(table, genmask))
+ return table;
+ }
+ return NULL;
+}
+
+static struct nft_table *nf_tables_table_lookup(const struct net *net,
const struct nlattr *nla,
- u8 genmask)
+ u8 family, u8 genmask)
+{
+ struct nft_table *table;
+
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ table = nft_table_lookup(net, nla, family, genmask);
+ if (table != NULL)
+ return table;
+
+ return ERR_PTR(-ENOENT);
+}
+
+static struct nft_table *nf_tables_table_lookup_byhandle(const struct net *net,
+ const struct nlattr *nla,
+ u8 genmask)
{
struct nft_table *table;
if (nla == NULL)
return ERR_PTR(-EINVAL);
- table = nft_table_lookup(afi, nla, genmask);
+ table = nft_table_lookup_byhandle(net, nla, genmask);
if (table != NULL)
return table;
@@ -390,7 +387,7 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
static const struct nf_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
static const struct nf_chain_type *
-__nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
+__nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
{
int i;
@@ -403,22 +400,20 @@ __nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
}
static const struct nf_chain_type *
-nf_tables_chain_type_lookup(const struct nft_af_info *afi,
- const struct nlattr *nla,
- bool autoload)
+nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family, bool autoload)
{
const struct nf_chain_type *type;
- type = __nf_tables_chain_type_lookup(afi->family, nla);
+ type = __nf_tables_chain_type_lookup(nla, family);
if (type != NULL)
return type;
#ifdef CONFIG_MODULES
if (autoload) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
- request_module("nft-chain-%u-%.*s", afi->family,
+ request_module("nft-chain-%u-%.*s", family,
nla_len(nla), (const char *)nla_data(nla));
nfnl_lock(NFNL_SUBSYS_NFTABLES);
- type = __nf_tables_chain_type_lookup(afi->family, nla);
+ type = __nf_tables_chain_type_lookup(nla, family);
if (type != NULL)
return ERR_PTR(-EAGAIN);
}
@@ -430,6 +425,7 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
[NFTA_TABLE_NAME] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_TABLE_FLAGS] = { .type = NLA_U32 },
+ [NFTA_TABLE_HANDLE] = { .type = NLA_U64 },
};
static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
@@ -451,7 +447,9 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
- nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
+ nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) ||
+ nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle),
+ NFTA_TABLE_PAD))
goto nla_put_failure;
nlmsg_end(skb, nlh);
@@ -476,7 +474,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
goto err;
err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq,
- event, 0, ctx->afi->family, ctx->table);
+ event, 0, ctx->family, ctx->table);
if (err < 0) {
kfree_skb(skb);
goto err;
@@ -493,7 +491,6 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
- const struct nft_af_info *afi;
const struct nft_table *table;
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
@@ -502,30 +499,27 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
rcu_read_lock();
cb->seq = net->nft.base_seq;
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (family != NFPROTO_UNSPEC && family != afi->family)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (family != NFPROTO_UNSPEC && family != table->family)
continue;
- list_for_each_entry_rcu(table, &afi->tables, list) {
- if (idx < s_idx)
- goto cont;
- if (idx > s_idx)
- memset(&cb->args[1], 0,
- sizeof(cb->args) - sizeof(cb->args[0]));
- if (!nft_is_active(net, table))
- continue;
- if (nf_tables_fill_table_info(skb, net,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWTABLE,
- NLM_F_MULTI,
- afi->family, table) < 0)
- goto done;
-
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (!nft_is_active(net, table))
+ continue;
+ if (nf_tables_fill_table_info(skb, net,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWTABLE, NLM_F_MULTI,
+ table->family, table) < 0)
+ goto done;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
- idx++;
- }
+ idx++;
}
done:
rcu_read_unlock();
@@ -540,7 +534,6 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
- const struct nft_af_info *afi;
const struct nft_table *table;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
@@ -553,11 +546,8 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk,
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -578,10 +568,7 @@ err:
return err;
}
-static void _nf_tables_table_disable(struct net *net,
- const struct nft_af_info *afi,
- struct nft_table *table,
- u32 cnt)
+static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt)
{
struct nft_chain *chain;
u32 i = 0;
@@ -595,14 +582,11 @@ static void _nf_tables_table_disable(struct net *net,
if (cnt && i++ == cnt)
break;
- nf_unregister_net_hooks(net, nft_base_chain(chain)->ops,
- afi->nops);
+ nf_unregister_net_hook(net, &nft_base_chain(chain)->ops);
}
}
-static int nf_tables_table_enable(struct net *net,
- const struct nft_af_info *afi,
- struct nft_table *table)
+static int nf_tables_table_enable(struct net *net, struct nft_table *table)
{
struct nft_chain *chain;
int err, i = 0;
@@ -613,8 +597,7 @@ static int nf_tables_table_enable(struct net *net,
if (!nft_is_base_chain(chain))
continue;
- err = nf_register_net_hooks(net, nft_base_chain(chain)->ops,
- afi->nops);
+ err = nf_register_net_hook(net, &nft_base_chain(chain)->ops);
if (err < 0)
goto err;
@@ -623,15 +606,13 @@ static int nf_tables_table_enable(struct net *net,
return 0;
err:
if (i)
- _nf_tables_table_disable(net, afi, table, i);
+ nft_table_disable(net, table, i);
return err;
}
-static void nf_tables_table_disable(struct net *net,
- const struct nft_af_info *afi,
- struct nft_table *table)
+static void nf_tables_table_disable(struct net *net, struct nft_table *table)
{
- _nf_tables_table_disable(net, afi, table, 0);
+ nft_table_disable(net, table, 0);
}
static int nf_tables_updtable(struct nft_ctx *ctx)
@@ -660,7 +641,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
nft_trans_table_enable(trans) = false;
} else if (!(flags & NFT_TABLE_F_DORMANT) &&
ctx->table->flags & NFT_TABLE_F_DORMANT) {
- ret = nf_tables_table_enable(ctx->net, ctx->afi, ctx->table);
+ ret = nf_tables_table_enable(ctx->net, ctx->table);
if (ret >= 0) {
ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
nft_trans_table_enable(trans) = true;
@@ -685,19 +666,14 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
const struct nlattr *name;
- struct nft_af_info *afi;
struct nft_table *table;
int family = nfmsg->nfgen_family;
u32 flags = 0;
struct nft_ctx ctx;
int err;
- afi = nf_tables_afinfo_lookup(net, family, true);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
name = nla[NFTA_TABLE_NAME];
- table = nf_tables_table_lookup(afi, name, genmask);
+ table = nf_tables_table_lookup(net, name, family, genmask);
if (IS_ERR(table)) {
if (PTR_ERR(table) != -ENOENT)
return PTR_ERR(table);
@@ -707,7 +683,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
return nf_tables_updtable(&ctx);
}
@@ -717,47 +693,45 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
return -EINVAL;
}
- err = -EAFNOSUPPORT;
- if (!try_module_get(afi->owner))
- goto err1;
-
err = -ENOMEM;
table = kzalloc(sizeof(*table), GFP_KERNEL);
if (table == NULL)
- goto err2;
+ goto err_kzalloc;
table->name = nla_strdup(name, GFP_KERNEL);
if (table->name == NULL)
- goto err3;
+ goto err_strdup;
INIT_LIST_HEAD(&table->chains);
INIT_LIST_HEAD(&table->sets);
INIT_LIST_HEAD(&table->objects);
+ INIT_LIST_HEAD(&table->flowtables);
+ table->family = family;
table->flags = flags;
+ table->handle = ++table_handle;
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
if (err < 0)
- goto err4;
+ goto err_trans;
- list_add_tail_rcu(&table->list, &afi->tables);
+ list_add_tail_rcu(&table->list, &net->nft.tables);
return 0;
-err4:
+err_trans:
kfree(table->name);
-err3:
+err_strdup:
kfree(table);
-err2:
- module_put(afi->owner);
-err1:
+err_kzalloc:
return err;
}
static int nft_flush_table(struct nft_ctx *ctx)
{
- int err;
+ struct nft_flowtable *flowtable, *nft;
struct nft_chain *chain, *nc;
struct nft_object *obj, *ne;
struct nft_set *set, *ns;
+ int err;
list_for_each_entry(chain, &ctx->table->chains, list) {
if (!nft_is_active_next(ctx->net, chain))
@@ -774,7 +748,7 @@ static int nft_flush_table(struct nft_ctx *ctx)
if (!nft_is_active_next(ctx->net, set))
continue;
- if (set->flags & NFT_SET_ANONYMOUS &&
+ if (nft_set_is_anonymous(set) &&
!list_empty(&set->bindings))
continue;
@@ -783,6 +757,12 @@ static int nft_flush_table(struct nft_ctx *ctx)
goto out;
}
+ list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) {
+ err = nft_delflowtable(ctx, flowtable);
+ if (err < 0)
+ goto out;
+ }
+
list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) {
err = nft_delobj(ctx, obj);
if (err < 0)
@@ -807,30 +787,28 @@ out:
static int nft_flush(struct nft_ctx *ctx, int family)
{
- struct nft_af_info *afi;
struct nft_table *table, *nt;
const struct nlattr * const *nla = ctx->nla;
int err = 0;
- list_for_each_entry(afi, &ctx->net->nft.af_info, list) {
- if (family != AF_UNSPEC && afi->family != family)
+ list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) {
+ if (family != AF_UNSPEC && table->family != family)
continue;
- ctx->afi = afi;
- list_for_each_entry_safe(table, nt, &afi->tables, list) {
- if (!nft_is_active_next(ctx->net, table))
- continue;
+ ctx->family = table->family;
- if (nla[NFTA_TABLE_NAME] &&
- nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0)
- continue;
+ if (!nft_is_active_next(ctx->net, table))
+ continue;
- ctx->table = table;
+ if (nla[NFTA_TABLE_NAME] &&
+ nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0)
+ continue;
- err = nft_flush_table(ctx);
- if (err < 0)
- goto out;
- }
+ ctx->table = table;
+
+ err = nft_flush_table(ctx);
+ if (err < 0)
+ goto out;
}
out:
return err;
@@ -843,20 +821,23 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- struct nft_af_info *afi;
struct nft_table *table;
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
- nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla);
- if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL)
+ nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla);
+ if (family == AF_UNSPEC ||
+ (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE]))
return nft_flush(&ctx, family);
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
+ if (nla[NFTA_TABLE_HANDLE])
+ table = nf_tables_table_lookup_byhandle(net,
+ nla[NFTA_TABLE_HANDLE],
+ genmask);
+ else
+ table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME],
+ family, genmask);
- table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -864,7 +845,7 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk,
table->use > 0)
return -EBUSY;
- ctx.afi = afi;
+ ctx.family = family;
ctx.table = table;
return nft_flush_table(&ctx);
@@ -876,7 +857,6 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
kfree(ctx->table->name);
kfree(ctx->table);
- module_put(ctx->afi->owner);
}
int nft_register_chain_type(const struct nf_chain_type *ctype)
@@ -1026,7 +1006,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
if (nft_is_base_chain(chain)) {
const struct nft_base_chain *basechain = nft_base_chain(chain);
- const struct nf_hook_ops *ops = &basechain->ops[0];
+ const struct nf_hook_ops *ops = &basechain->ops;
struct nlattr *nest;
nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
@@ -1077,7 +1057,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
goto err;
err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq,
- event, 0, ctx->afi->family, ctx->table,
+ event, 0, ctx->family, ctx->table,
ctx->chain);
if (err < 0) {
kfree_skb(skb);
@@ -1095,7 +1075,6 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
- const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
unsigned int idx = 0, s_idx = cb->args[0];
@@ -1105,31 +1084,30 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
rcu_read_lock();
cb->seq = net->nft.base_seq;
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (family != NFPROTO_UNSPEC && family != afi->family)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (family != NFPROTO_UNSPEC && family != table->family)
continue;
- list_for_each_entry_rcu(table, &afi->tables, list) {
- list_for_each_entry_rcu(chain, &table->chains, list) {
- if (idx < s_idx)
- goto cont;
- if (idx > s_idx)
- memset(&cb->args[1], 0,
- sizeof(cb->args) - sizeof(cb->args[0]));
- if (!nft_is_active(net, chain))
- continue;
- if (nf_tables_fill_chain_info(skb, net,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWCHAIN,
- NLM_F_MULTI,
- afi->family, table, chain) < 0)
- goto done;
+ list_for_each_entry_rcu(chain, &table->chains, list) {
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (!nft_is_active(net, chain))
+ continue;
+ if (nf_tables_fill_chain_info(skb, net,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWCHAIN,
+ NLM_F_MULTI,
+ table->family, table,
+ chain) < 0)
+ goto done;
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
- idx++;
- }
+ idx++;
}
}
done:
@@ -1145,7 +1123,6 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
- const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
struct sk_buff *skb2;
@@ -1159,11 +1136,8 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -1227,13 +1201,13 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
static void nft_chain_stats_replace(struct nft_base_chain *chain,
struct nft_stats __percpu *newstats)
{
+ struct nft_stats __percpu *oldstats;
+
if (newstats == NULL)
return;
if (chain->stats) {
- struct nft_stats __percpu *oldstats =
- nft_dereference(chain->stats);
-
+ oldstats = nfnl_dereference(chain->stats, NFNL_SUBSYS_NFTABLES);
rcu_assign_pointer(chain->stats, newstats);
synchronize_rcu();
free_percpu(oldstats);
@@ -1252,8 +1226,8 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
free_percpu(basechain->stats);
if (basechain->stats)
static_branch_dec(&nft_counters_enabled);
- if (basechain->ops[0].dev != NULL)
- dev_put(basechain->ops[0].dev);
+ if (basechain->ops.dev != NULL)
+ dev_put(basechain->ops.dev);
kfree(chain->name);
kfree(basechain);
} else {
@@ -1264,15 +1238,15 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
struct nft_chain_hook {
u32 num;
- u32 priority;
+ s32 priority;
const struct nf_chain_type *type;
struct net_device *dev;
};
static int nft_chain_parse_hook(struct net *net,
const struct nlattr * const nla[],
- struct nft_af_info *afi,
- struct nft_chain_hook *hook, bool create)
+ struct nft_chain_hook *hook, u8 family,
+ bool create)
{
struct nlattr *ha[NFTA_HOOK_MAX + 1];
const struct nf_chain_type *type;
@@ -1289,27 +1263,29 @@ static int nft_chain_parse_hook(struct net *net,
return -EINVAL;
hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
- if (hook->num >= afi->nhooks)
- return -EINVAL;
-
hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
- type = chain_type[afi->family][NFT_CHAIN_T_DEFAULT];
+ type = chain_type[family][NFT_CHAIN_T_DEFAULT];
if (nla[NFTA_CHAIN_TYPE]) {
- type = nf_tables_chain_type_lookup(afi, nla[NFTA_CHAIN_TYPE],
- create);
+ type = nf_tables_chain_type_lookup(nla[NFTA_CHAIN_TYPE],
+ family, create);
if (IS_ERR(type))
return PTR_ERR(type);
}
if (!(type->hook_mask & (1 << hook->num)))
return -EOPNOTSUPP;
+
+ if (type->type == NFT_CHAIN_T_NAT &&
+ hook->priority <= NF_IP_PRI_CONNTRACK)
+ return -EOPNOTSUPP;
+
if (!try_module_get(type->owner))
return -ENOENT;
hook->type = type;
hook->dev = NULL;
- if (afi->flags & NFT_AF_NEEDS_DEV) {
+ if (family == NFPROTO_NETDEV) {
char ifname[IFNAMSIZ];
if (!ha[NFTA_HOOK_DEV]) {
@@ -1344,12 +1320,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
{
const struct nlattr * const *nla = ctx->nla;
struct nft_table *table = ctx->table;
- struct nft_af_info *afi = ctx->afi;
struct nft_base_chain *basechain;
struct nft_stats __percpu *stats;
struct net *net = ctx->net;
struct nft_chain *chain;
- unsigned int i;
int err;
if (table->use == UINT_MAX)
@@ -1358,9 +1332,8 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (nla[NFTA_CHAIN_HOOK]) {
struct nft_chain_hook hook;
struct nf_hook_ops *ops;
- nf_hookfn *hookfn;
- err = nft_chain_parse_hook(net, nla, afi, &hook, create);
+ err = nft_chain_parse_hook(net, nla, &hook, family, create);
if (err < 0)
return err;
@@ -1384,23 +1357,19 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
static_branch_inc(&nft_counters_enabled);
}
- hookfn = hook.type->hooks[hook.num];
basechain->type = hook.type;
chain = &basechain->chain;
- for (i = 0; i < afi->nops; i++) {
- ops = &basechain->ops[i];
- ops->pf = family;
- ops->hooknum = hook.num;
- ops->priority = hook.priority;
- ops->priv = chain;
- ops->hook = afi->hooks[ops->hooknum];
- ops->dev = hook.dev;
- if (hookfn)
- ops->hook = hookfn;
- if (afi->hook_ops_init)
- afi->hook_ops_init(ops, i);
- }
+ ops = &basechain->ops;
+ ops->pf = family;
+ ops->hooknum = hook.num;
+ ops->priority = hook.priority;
+ ops->priv = chain;
+ ops->hook = hook.type->hooks[ops->hooknum];
+ ops->dev = hook.dev;
+
+ if (basechain->type->type == NFT_CHAIN_T_NAT)
+ ops->nat_hook = true;
chain->flags |= NFT_BASE_CHAIN;
basechain->policy = policy;
@@ -1418,7 +1387,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
goto err1;
}
- err = nf_tables_register_hooks(net, table, chain, afi->nops);
+ err = nf_tables_register_hook(net, table, chain);
if (err < 0)
goto err1;
@@ -1432,7 +1401,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
return 0;
err2:
- nf_tables_unregister_hooks(net, table, chain, afi->nops);
+ nf_tables_unregister_hook(net, table, chain);
err1:
nf_tables_chain_destroy(chain);
@@ -1445,20 +1414,19 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
const struct nlattr * const *nla = ctx->nla;
struct nft_table *table = ctx->table;
struct nft_chain *chain = ctx->chain;
- struct nft_af_info *afi = ctx->afi;
struct nft_base_chain *basechain;
struct nft_stats *stats = NULL;
struct nft_chain_hook hook;
const struct nlattr *name;
struct nf_hook_ops *ops;
struct nft_trans *trans;
- int err, i;
+ int err;
if (nla[NFTA_CHAIN_HOOK]) {
if (!nft_is_base_chain(chain))
return -EBUSY;
- err = nft_chain_parse_hook(ctx->net, nla, ctx->afi, &hook,
+ err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family,
create);
if (err < 0)
return err;
@@ -1469,14 +1437,12 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
return -EBUSY;
}
- for (i = 0; i < afi->nops; i++) {
- ops = &basechain->ops[i];
- if (ops->hooknum != hook.num ||
- ops->priority != hook.priority ||
- ops->dev != hook.dev) {
- nft_chain_release_hook(&hook);
- return -EBUSY;
- }
+ ops = &basechain->ops;
+ if (ops->hooknum != hook.num ||
+ ops->priority != hook.priority ||
+ ops->dev != hook.dev) {
+ nft_chain_release_hook(&hook);
+ return -EBUSY;
}
nft_chain_release_hook(&hook);
}
@@ -1539,7 +1505,6 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
const struct nlattr * uninitialized_var(name);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
u8 policy = NF_ACCEPT;
@@ -1549,11 +1514,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- afi = nf_tables_afinfo_lookup(net, family, true);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -1593,7 +1555,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
}
}
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
if (chain != NULL) {
if (nlh->nlmsg_flags & NLM_F_EXCL)
@@ -1614,24 +1576,26 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule;
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
+ u64 handle;
u32 use;
int err;
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
- chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+ if (nla[NFTA_CHAIN_HANDLE]) {
+ handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
+ chain = nf_tables_chain_lookup_byhandle(table, handle, genmask);
+ } else {
+ chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+ }
if (IS_ERR(chain))
return PTR_ERR(chain);
@@ -1639,7 +1603,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
chain->use > 0)
return -EBUSY;
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
use = chain->use;
list_for_each_entry(rule, &chain->rules, list) {
@@ -1804,7 +1768,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
if (err < 0)
return err;
- type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
+ type = nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]);
if (IS_ERR(type))
return PTR_ERR(type);
@@ -2027,7 +1991,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
goto err;
err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq,
- event, 0, ctx->afi->family, ctx->table,
+ event, 0, ctx->family, ctx->table,
ctx->chain, rule);
if (err < 0) {
kfree_skb(skb);
@@ -2051,7 +2015,6 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
const struct nft_rule_dump_ctx *ctx = cb->data;
- const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
const struct nft_rule *rule;
@@ -2062,39 +2025,37 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
rcu_read_lock();
cb->seq = net->nft.base_seq;
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (family != NFPROTO_UNSPEC && family != afi->family)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (family != NFPROTO_UNSPEC && family != table->family)
continue;
- list_for_each_entry_rcu(table, &afi->tables, list) {
- if (ctx && ctx->table &&
- strcmp(ctx->table, table->name) != 0)
+ if (ctx && ctx->table && strcmp(ctx->table, table->name) != 0)
+ continue;
+
+ list_for_each_entry_rcu(chain, &table->chains, list) {
+ if (ctx && ctx->chain &&
+ strcmp(ctx->chain, chain->name) != 0)
continue;
- list_for_each_entry_rcu(chain, &table->chains, list) {
- if (ctx && ctx->chain &&
- strcmp(ctx->chain, chain->name) != 0)
- continue;
-
- list_for_each_entry_rcu(rule, &chain->rules, list) {
- if (!nft_is_active(net, rule))
- goto cont;
- if (idx < s_idx)
- goto cont;
- if (idx > s_idx)
- memset(&cb->args[1], 0,
- sizeof(cb->args) - sizeof(cb->args[0]));
- if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWRULE,
- NLM_F_MULTI | NLM_F_APPEND,
- afi->family, table, chain, rule) < 0)
- goto done;
-
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ list_for_each_entry_rcu(rule, &chain->rules, list) {
+ if (!nft_is_active(net, rule))
+ goto cont;
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWRULE,
+ NLM_F_MULTI | NLM_F_APPEND,
+ table->family,
+ table, chain, rule) < 0)
+ goto done;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
- idx++;
- }
+ idx++;
}
}
}
@@ -2124,7 +2085,6 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
- const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
const struct nft_rule *rule;
@@ -2168,11 +2128,8 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -2229,7 +2186,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- struct nft_af_info *afi;
+ int family = nfmsg->nfgen_family;
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule, *old_rule = NULL;
@@ -2245,11 +2202,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -2288,7 +2242,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
return PTR_ERR(old_rule);
}
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
n = 0;
size = 0;
@@ -2412,18 +2366,14 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain = NULL;
struct nft_rule *rule;
int family = nfmsg->nfgen_family, err = 0;
struct nft_ctx ctx;
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -2434,7 +2384,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
return PTR_ERR(chain);
}
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
if (chain) {
if (nla[NFTA_RULE_HANDLE]) {
@@ -2601,6 +2551,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
[NFTA_SET_USERDATA] = { .type = NLA_BINARY,
.len = NFT_USERDATA_MAXLEN },
[NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 },
+ [NFTA_SET_HANDLE] = { .type = NLA_U64 },
};
static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
@@ -2614,26 +2565,17 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
u8 genmask)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
- struct nft_af_info *afi = NULL;
+ int family = nfmsg->nfgen_family;
struct nft_table *table = NULL;
- if (nfmsg->nfgen_family != NFPROTO_UNSPEC) {
- afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
- }
-
if (nla[NFTA_SET_TABLE] != NULL) {
- if (afi == NULL)
- return -EAFNOSUPPORT;
-
- table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE],
- genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE],
+ family, genmask);
if (IS_ERR(table))
return PTR_ERR(table);
}
- nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
return 0;
}
@@ -2653,6 +2595,22 @@ static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
return ERR_PTR(-ENOENT);
}
+static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
+{
+ struct nft_set *set;
+
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ list_for_each_entry(set, &table->sets, list) {
+ if (be64_to_cpu(nla_get_be64(nla)) == set->handle &&
+ nft_active_genmask(set, genmask))
+ return set;
+ }
+ return ERR_PTR(-ENOENT);
+}
+
static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
const struct nlattr *nla,
u8 genmask)
@@ -2760,7 +2718,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = ctx->afi->family;
+ nfmsg->nfgen_family = ctx->family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff);
@@ -2768,6 +2726,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_NAME, set->name))
goto nla_put_failure;
+ if (nla_put_be64(skb, NFTA_SET_HANDLE, cpu_to_be64(set->handle),
+ NFTA_SET_PAD))
+ goto nla_put_failure;
if (set->flags != 0)
if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags)))
goto nla_put_failure;
@@ -2852,10 +2813,8 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
{
const struct nft_set *set;
unsigned int idx, s_idx = cb->args[0];
- struct nft_af_info *afi;
struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
struct net *net = sock_net(skb->sk);
- int cur_family = cb->args[3];
struct nft_ctx *ctx = cb->data, ctx_set;
if (cb->args[1])
@@ -2864,51 +2823,44 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
cb->seq = net->nft.base_seq;
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (ctx->afi && ctx->afi != afi)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (ctx->family != NFPROTO_UNSPEC &&
+ ctx->family != table->family)
continue;
- if (cur_family) {
- if (afi->family != cur_family)
+ if (ctx->table && ctx->table != table)
+ continue;
+
+ if (cur_table) {
+ if (cur_table != table)
continue;
- cur_family = 0;
+ cur_table = NULL;
}
- list_for_each_entry_rcu(table, &afi->tables, list) {
- if (ctx->table && ctx->table != table)
- continue;
+ idx = 0;
+ list_for_each_entry_rcu(set, &table->sets, list) {
+ if (idx < s_idx)
+ goto cont;
+ if (!nft_is_active(net, set))
+ goto cont;
- if (cur_table) {
- if (cur_table != table)
- continue;
+ ctx_set = *ctx;
+ ctx_set.table = table;
+ ctx_set.family = table->family;
- cur_table = NULL;
+ if (nf_tables_fill_set(skb, &ctx_set, set,
+ NFT_MSG_NEWSET,
+ NLM_F_MULTI) < 0) {
+ cb->args[0] = idx;
+ cb->args[2] = (unsigned long) table;
+ goto done;
}
- idx = 0;
- list_for_each_entry_rcu(set, &table->sets, list) {
- if (idx < s_idx)
- goto cont;
- if (!nft_is_active(net, set))
- goto cont;
-
- ctx_set = *ctx;
- ctx_set.table = table;
- ctx_set.afi = afi;
- if (nf_tables_fill_set(skb, &ctx_set, set,
- NFT_MSG_NEWSET,
- NLM_F_MULTI) < 0) {
- cb->args[0] = idx;
- cb->args[2] = (unsigned long) table;
- cb->args[3] = afi->family;
- goto done;
- }
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
- idx++;
- }
- if (s_idx)
- s_idx = 0;
+ idx++;
}
+ if (s_idx)
+ s_idx = 0;
}
cb->args[1] = 1;
done:
@@ -3006,8 +2958,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
+ int family = nfmsg->nfgen_family;
const struct nft_set_ops *ops;
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
@@ -3114,15 +3066,12 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME], genmask);
if (IS_ERR(set)) {
@@ -3188,6 +3137,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
set->udata = udata;
set->timeout = timeout;
set->gc_int = gc_int;
+ set->handle = nf_tables_alloc_handle(table);
err = ops->init(set, &desc, nla);
if (err < 0)
@@ -3245,7 +3195,10 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
if (err < 0)
return err;
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
+ if (nla[NFTA_SET_HANDLE])
+ set = nf_tables_set_lookup_byhandle(ctx.table, nla[NFTA_SET_HANDLE], genmask);
+ else
+ set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
if (IS_ERR(set))
return PTR_ERR(set);
@@ -3277,7 +3230,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *i;
struct nft_set_iter iter;
- if (!list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
+ if (!list_empty(&set->bindings) && nft_set_is_anonymous(set))
return -EBUSY;
if (binding->flags & NFT_SET_MAP) {
@@ -3312,7 +3265,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
{
list_del_rcu(&binding->list);
- if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS &&
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
nft_is_active(ctx->net, set))
nf_tables_set_destroy(ctx, set);
}
@@ -3380,19 +3333,15 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
u8 genmask)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
- struct nft_af_info *afi;
+ int family = nfmsg->nfgen_family;
struct nft_table *table;
- afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE],
- genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE],
+ family, genmask);
if (IS_ERR(table))
return PTR_ERR(table);
- nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
return 0;
}
@@ -3497,7 +3446,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
{
struct nft_set_dump_ctx *dump_ctx = cb->data;
struct net *net = sock_net(skb->sk);
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_set *set;
struct nft_set_dump_args args;
@@ -3509,21 +3457,19 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
int event;
rcu_read_lock();
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (afi != dump_ctx->ctx.afi)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
+ dump_ctx->ctx.family != table->family)
continue;
- list_for_each_entry_rcu(table, &afi->tables, list) {
- if (table != dump_ctx->ctx.table)
- continue;
+ if (table != dump_ctx->ctx.table)
+ continue;
- list_for_each_entry_rcu(set, &table->sets, list) {
- if (set == dump_ctx->set) {
- set_found = true;
- break;
- }
+ list_for_each_entry_rcu(set, &table->sets, list) {
+ if (set == dump_ctx->set) {
+ set_found = true;
+ break;
}
- break;
}
break;
}
@@ -3543,7 +3489,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = afi->family;
+ nfmsg->nfgen_family = table->family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
@@ -3606,7 +3552,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = ctx->afi->family;
+ nfmsg->nfgen_family = ctx->family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff);
@@ -3963,7 +3909,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
list_for_each_entry(binding, &set->bindings, list) {
struct nft_ctx bind_ctx = {
.net = ctx->net,
- .afi = ctx->afi,
+ .family = ctx->family,
.table = ctx->table,
.chain = (struct nft_chain *)binding->chain,
};
@@ -4382,6 +4328,21 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
}
EXPORT_SYMBOL_GPL(nf_tables_obj_lookup);
+struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla,
+ u32 objtype, u8 genmask)
+{
+ struct nft_object *obj;
+
+ list_for_each_entry(obj, &table->objects, list) {
+ if (be64_to_cpu(nla_get_be64(nla)) == obj->handle &&
+ objtype == obj->ops->type->type &&
+ nft_active_genmask(obj, genmask))
+ return obj;
+ }
+ return ERR_PTR(-ENOENT);
+}
+
static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
[NFTA_OBJ_TABLE] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
@@ -4389,6 +4350,7 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
.len = NFT_OBJ_MAXNAMELEN - 1 },
[NFTA_OBJ_TYPE] = { .type = NLA_U32 },
[NFTA_OBJ_DATA] = { .type = NLA_NESTED },
+ [NFTA_OBJ_HANDLE] = { .type = NLA_U64},
};
static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
@@ -4494,7 +4456,6 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
const struct nft_object_type *type;
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_object *obj;
struct nft_ctx ctx;
@@ -4506,11 +4467,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
!nla[NFTA_OBJ_DATA])
return -EINVAL;
- afi = nf_tables_afinfo_lookup(net, family, true);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -4528,7 +4486,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
return 0;
}
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
type = nft_obj_type_get(objtype);
if (IS_ERR(type))
@@ -4540,6 +4498,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
goto err1;
}
obj->table = table;
+ obj->handle = nf_tables_alloc_handle(table);
+
obj->name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL);
if (!obj->name) {
err = -ENOMEM;
@@ -4586,7 +4546,9 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
nla_put_string(skb, NFTA_OBJ_NAME, obj->name) ||
nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) ||
nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) ||
- nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset))
+ nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset) ||
+ nla_put_be64(skb, NFTA_OBJ_HANDLE, cpu_to_be64(obj->handle),
+ NFTA_OBJ_PAD))
goto nla_put_failure;
nlmsg_end(skb, nlh);
@@ -4605,7 +4567,6 @@ struct nft_obj_filter {
static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
- const struct nft_af_info *afi;
const struct nft_table *table;
unsigned int idx = 0, s_idx = cb->args[0];
struct nft_obj_filter *filter = cb->data;
@@ -4620,38 +4581,37 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
cb->seq = net->nft.base_seq;
- list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
- if (family != NFPROTO_UNSPEC && family != afi->family)
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (family != NFPROTO_UNSPEC && family != table->family)
continue;
- list_for_each_entry_rcu(table, &afi->tables, list) {
- list_for_each_entry_rcu(obj, &table->objects, list) {
- if (!nft_is_active(net, obj))
- goto cont;
- if (idx < s_idx)
- goto cont;
- if (idx > s_idx)
- memset(&cb->args[1], 0,
- sizeof(cb->args) - sizeof(cb->args[0]));
- if (filter && filter->table[0] &&
- strcmp(filter->table, table->name))
- goto cont;
- if (filter &&
- filter->type != NFT_OBJECT_UNSPEC &&
- obj->ops->type->type != filter->type)
- goto cont;
+ list_for_each_entry_rcu(obj, &table->objects, list) {
+ if (!nft_is_active(net, obj))
+ goto cont;
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (filter && filter->table[0] &&
+ strcmp(filter->table, table->name))
+ goto cont;
+ if (filter &&
+ filter->type != NFT_OBJECT_UNSPEC &&
+ obj->ops->type->type != filter->type)
+ goto cont;
- if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWOBJ,
- NLM_F_MULTI | NLM_F_APPEND,
- afi->family, table, obj, reset) < 0)
- goto done;
+ if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWOBJ,
+ NLM_F_MULTI | NLM_F_APPEND,
+ table->family, table,
+ obj, reset) < 0)
+ goto done;
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
- idx++;
- }
+ idx++;
}
}
done:
@@ -4703,7 +4663,6 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
int family = nfmsg->nfgen_family;
- const struct nft_af_info *afi;
const struct nft_table *table;
struct nft_object *obj;
struct sk_buff *skb2;
@@ -4734,11 +4693,8 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
!nla[NFTA_OBJ_TYPE])
return -EINVAL;
- afi = nf_tables_afinfo_lookup(net, family, false);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -4784,32 +4740,33 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk,
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_object *obj;
struct nft_ctx ctx;
u32 objtype;
if (!nla[NFTA_OBJ_TYPE] ||
- !nla[NFTA_OBJ_NAME])
+ (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE]))
return -EINVAL;
- afi = nf_tables_afinfo_lookup(net, family, true);
- if (IS_ERR(afi))
- return PTR_ERR(afi);
-
- table = nf_tables_table_lookup(afi, nla[NFTA_OBJ_TABLE], genmask);
+ table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
+ if (nla[NFTA_OBJ_HANDLE])
+ obj = nf_tables_obj_lookup_byhandle(table, nla[NFTA_OBJ_HANDLE],
+ objtype, genmask);
+ else
+ obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME],
+ objtype, genmask);
if (IS_ERR(obj))
return PTR_ERR(obj);
if (obj->use > 0)
return -EBUSY;
- nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
return nft_delobj(&ctx, obj);
}
@@ -4847,7 +4804,613 @@ static void nf_tables_obj_notify(const struct nft_ctx *ctx,
struct nft_object *obj, int event)
{
nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event,
- ctx->afi->family, ctx->report, GFP_KERNEL);
+ ctx->family, ctx->report, GFP_KERNEL);
+}
+
+/*
+ * Flow tables
+ */
+void nft_register_flowtable_type(struct nf_flowtable_type *type)
+{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_add_tail_rcu(&type->list, &nf_tables_flowtables);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_register_flowtable_type);
+
+void nft_unregister_flowtable_type(struct nf_flowtable_type *type)
+{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_del_rcu(&type->list);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_flowtable_type);
+
+static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = {
+ [NFTA_FLOWTABLE_TABLE] = { .type = NLA_STRING,
+ .len = NFT_NAME_MAXLEN - 1 },
+ [NFTA_FLOWTABLE_NAME] = { .type = NLA_STRING,
+ .len = NFT_NAME_MAXLEN - 1 },
+ [NFTA_FLOWTABLE_HOOK] = { .type = NLA_NESTED },
+ [NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 },
+};
+
+struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
+ const struct nlattr *nla,
+ u8 genmask)
+{
+ struct nft_flowtable *flowtable;
+
+ list_for_each_entry(flowtable, &table->flowtables, list) {
+ if (!nla_strcmp(nla, flowtable->name) &&
+ nft_active_genmask(flowtable, genmask))
+ return flowtable;
+ }
+ return ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL_GPL(nf_tables_flowtable_lookup);
+
+struct nft_flowtable *
+nf_tables_flowtable_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
+{
+ struct nft_flowtable *flowtable;
+
+ list_for_each_entry(flowtable, &table->flowtables, list) {
+ if (be64_to_cpu(nla_get_be64(nla)) == flowtable->handle &&
+ nft_active_genmask(flowtable, genmask))
+ return flowtable;
+ }
+ return ERR_PTR(-ENOENT);
+}
+
+#define NFT_FLOWTABLE_DEVICE_MAX 8
+
+static int nf_tables_parse_devices(const struct nft_ctx *ctx,
+ const struct nlattr *attr,
+ struct net_device *dev_array[], int *len)
+{
+ const struct nlattr *tmp;
+ struct net_device *dev;
+ char ifname[IFNAMSIZ];
+ int rem, n = 0, err;
+
+ nla_for_each_nested(tmp, attr, rem) {
+ if (nla_type(tmp) != NFTA_DEVICE_NAME) {
+ err = -EINVAL;
+ goto err1;
+ }
+
+ nla_strlcpy(ifname, tmp, IFNAMSIZ);
+ dev = dev_get_by_name(ctx->net, ifname);
+ if (!dev) {
+ err = -ENOENT;
+ goto err1;
+ }
+
+ dev_array[n++] = dev;
+ if (n == NFT_FLOWTABLE_DEVICE_MAX) {
+ err = -EFBIG;
+ goto err1;
+ }
+ }
+ if (!len)
+ return -EINVAL;
+
+ err = 0;
+err1:
+ *len = n;
+ return err;
+}
+
+static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = {
+ [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 },
+ [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 },
+ [NFTA_FLOWTABLE_HOOK_DEVS] = { .type = NLA_NESTED },
+};
+
+static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
+ const struct nlattr *attr,
+ struct nft_flowtable *flowtable)
+{
+ struct net_device *dev_array[NFT_FLOWTABLE_DEVICE_MAX];
+ struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1];
+ struct nf_hook_ops *ops;
+ int hooknum, priority;
+ int err, n = 0, i;
+
+ err = nla_parse_nested(tb, NFTA_FLOWTABLE_HOOK_MAX, attr,
+ nft_flowtable_hook_policy, NULL);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFTA_FLOWTABLE_HOOK_NUM] ||
+ !tb[NFTA_FLOWTABLE_HOOK_PRIORITY] ||
+ !tb[NFTA_FLOWTABLE_HOOK_DEVS])
+ return -EINVAL;
+
+ hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM]));
+ if (hooknum != NF_NETDEV_INGRESS)
+ return -EINVAL;
+
+ priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));
+
+ err = nf_tables_parse_devices(ctx, tb[NFTA_FLOWTABLE_HOOK_DEVS],
+ dev_array, &n);
+ if (err < 0)
+ goto err1;
+
+ ops = kzalloc(sizeof(struct nf_hook_ops) * n, GFP_KERNEL);
+ if (!ops) {
+ err = -ENOMEM;
+ goto err1;
+ }
+
+ flowtable->hooknum = hooknum;
+ flowtable->priority = priority;
+ flowtable->ops = ops;
+ flowtable->ops_len = n;
+
+ for (i = 0; i < n; i++) {
+ flowtable->ops[i].pf = NFPROTO_NETDEV;
+ flowtable->ops[i].hooknum = hooknum;
+ flowtable->ops[i].priority = priority;
+ flowtable->ops[i].priv = &flowtable->data.rhashtable;
+ flowtable->ops[i].hook = flowtable->data.type->hook;
+ flowtable->ops[i].dev = dev_array[i];
+ }
+
+ err = 0;
+err1:
+ for (i = 0; i < n; i++)
+ dev_put(dev_array[i]);
+
+ return err;
+}
+
+static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family)
+{
+ const struct nf_flowtable_type *type;
+
+ list_for_each_entry(type, &nf_tables_flowtables, list) {
+ if (family == type->family)
+ return type;
+ }
+ return NULL;
+}
+
+static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family)
+{
+ const struct nf_flowtable_type *type;
+
+ type = __nft_flowtable_type_get(family);
+ if (type != NULL && try_module_get(type->owner))
+ return type;
+
+#ifdef CONFIG_MODULES
+ if (type == NULL) {
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ request_module("nf-flowtable-%u", family);
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ if (__nft_flowtable_type_get(family))
+ return ERR_PTR(-EAGAIN);
+ }
+#endif
+ return ERR_PTR(-ENOENT);
+}
+
+void nft_flow_table_iterate(struct net *net,
+ void (*iter)(struct nf_flowtable *flowtable, void *data),
+ void *data)
+{
+ struct nft_flowtable *flowtable;
+ const struct nft_table *table;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(flowtable, &table->flowtables, list) {
+ iter(&flowtable->data, data);
+ }
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
+
+static void nft_unregister_flowtable_net_hooks(struct net *net,
+ struct nft_flowtable *flowtable)
+{
+ int i;
+
+ for (i = 0; i < flowtable->ops_len; i++) {
+ if (!flowtable->ops[i].dev)
+ continue;
+
+ nf_unregister_net_hook(net, &flowtable->ops[i]);
+ }
+}
+
+static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[],
+ struct netlink_ext_ack *extack)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nf_flowtable_type *type;
+ u8 genmask = nft_genmask_next(net);
+ int family = nfmsg->nfgen_family;
+ struct nft_flowtable *flowtable;
+ struct nft_table *table;
+ struct nft_ctx ctx;
+ int err, i, k;
+
+ if (!nla[NFTA_FLOWTABLE_TABLE] ||
+ !nla[NFTA_FLOWTABLE_NAME] ||
+ !nla[NFTA_FLOWTABLE_HOOK])
+ return -EINVAL;
+
+ table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
+ family, genmask);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
+ genmask);
+ if (IS_ERR(flowtable)) {
+ err = PTR_ERR(flowtable);
+ if (err != -ENOENT)
+ return err;
+ } else {
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+
+ return 0;
+ }
+
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+
+ flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL);
+ if (!flowtable)
+ return -ENOMEM;
+
+ flowtable->table = table;
+ flowtable->handle = nf_tables_alloc_handle(table);
+
+ flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL);
+ if (!flowtable->name) {
+ err = -ENOMEM;
+ goto err1;
+ }
+
+ type = nft_flowtable_type_get(family);
+ if (IS_ERR(type)) {
+ err = PTR_ERR(type);
+ goto err2;
+ }
+
+ flowtable->data.type = type;
+ err = rhashtable_init(&flowtable->data.rhashtable, type->params);
+ if (err < 0)
+ goto err3;
+
+ err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
+ flowtable);
+ if (err < 0)
+ goto err3;
+
+ for (i = 0; i < flowtable->ops_len; i++) {
+ err = nf_register_net_hook(net, &flowtable->ops[i]);
+ if (err < 0)
+ goto err4;
+ }
+
+ err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
+ if (err < 0)
+ goto err5;
+
+ INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc);
+ queue_delayed_work(system_power_efficient_wq,
+ &flowtable->data.gc_work, HZ);
+
+ list_add_tail_rcu(&flowtable->list, &table->flowtables);
+ table->use++;
+
+ return 0;
+err5:
+ i = flowtable->ops_len;
+err4:
+ for (k = i - 1; k >= 0; k--)
+ nf_unregister_net_hook(net, &flowtable->ops[i]);
+
+ kfree(flowtable->ops);
+err3:
+ module_put(type->owner);
+err2:
+ kfree(flowtable->name);
+err1:
+ kfree(flowtable);
+ return err;
+}
+
+static int nf_tables_delflowtable(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[],
+ struct netlink_ext_ack *extack)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ u8 genmask = nft_genmask_next(net);
+ int family = nfmsg->nfgen_family;
+ struct nft_flowtable *flowtable;
+ struct nft_table *table;
+ struct nft_ctx ctx;
+
+ table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
+ family, genmask);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ if (nla[NFTA_FLOWTABLE_HANDLE])
+ flowtable = nf_tables_flowtable_lookup_byhandle(table,
+ nla[NFTA_FLOWTABLE_HANDLE],
+ genmask);
+ else
+ flowtable = nf_tables_flowtable_lookup(table,
+ nla[NFTA_FLOWTABLE_NAME],
+ genmask);
+ if (IS_ERR(flowtable))
+ return PTR_ERR(flowtable);
+ if (flowtable->use > 0)
+ return -EBUSY;
+
+ nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+
+ return nft_delflowtable(&ctx, flowtable);
+}
+
+static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
+ u32 portid, u32 seq, int event,
+ u32 flags, int family,
+ struct nft_flowtable *flowtable)
+{
+ struct nlattr *nest, *nest_devs;
+ struct nfgenmsg *nfmsg;
+ struct nlmsghdr *nlh;
+ int i;
+
+ event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
+ if (nlh == NULL)
+ goto nla_put_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = family;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
+
+ if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) ||
+ nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) ||
+ nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
+ nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle),
+ NFTA_FLOWTABLE_PAD))
+ goto nla_put_failure;
+
+ nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK);
+ if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) ||
+ nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority)))
+ goto nla_put_failure;
+
+ nest_devs = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK_DEVS);
+ if (!nest_devs)
+ goto nla_put_failure;
+
+ for (i = 0; i < flowtable->ops_len; i++) {
+ if (flowtable->ops[i].dev &&
+ nla_put_string(skb, NFTA_DEVICE_NAME,
+ flowtable->ops[i].dev->name))
+ goto nla_put_failure;
+ }
+ nla_nest_end(skb, nest_devs);
+ nla_nest_end(skb, nest);
+
+ nlmsg_end(skb, nlh);
+ return 0;
+
+nla_put_failure:
+ nlmsg_trim(skb, nlh);
+ return -1;
+}
+
+struct nft_flowtable_filter {
+ char *table;
+};
+
+static int nf_tables_dump_flowtable(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+ struct nft_flowtable_filter *filter = cb->data;
+ unsigned int idx = 0, s_idx = cb->args[0];
+ struct net *net = sock_net(skb->sk);
+ int family = nfmsg->nfgen_family;
+ struct nft_flowtable *flowtable;
+ const struct nft_table *table;
+
+ rcu_read_lock();
+ cb->seq = net->nft.base_seq;
+
+ list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ if (family != NFPROTO_UNSPEC && family != table->family)
+ continue;
+
+ list_for_each_entry_rcu(flowtable, &table->flowtables, list) {
+ if (!nft_is_active(net, flowtable))
+ goto cont;
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (filter && filter->table[0] &&
+ strcmp(filter->table, table->name))
+ goto cont;
+
+ if (nf_tables_fill_flowtable_info(skb, net, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWFLOWTABLE,
+ NLM_F_MULTI | NLM_F_APPEND,
+ table->family, flowtable) < 0)
+ goto done;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ }
+done:
+ rcu_read_unlock();
+
+ cb->args[0] = idx;
+ return skb->len;
+}
+
+static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
+{
+ struct nft_flowtable_filter *filter = cb->data;
+
+ if (!filter)
+ return 0;
+
+ kfree(filter->table);
+ kfree(filter);
+
+ return 0;
+}
+
+static struct nft_flowtable_filter *
+nft_flowtable_filter_alloc(const struct nlattr * const nla[])
+{
+ struct nft_flowtable_filter *filter;
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return ERR_PTR(-ENOMEM);
+
+ if (nla[NFTA_FLOWTABLE_TABLE]) {
+ filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
+ GFP_KERNEL);
+ if (!filter->table) {
+ kfree(filter);
+ return ERR_PTR(-ENOMEM);
+ }
+ }
+ return filter;
+}
+
+static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[],
+ struct netlink_ext_ack *extack)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ u8 genmask = nft_genmask_cur(net);
+ int family = nfmsg->nfgen_family;
+ struct nft_flowtable *flowtable;
+ const struct nft_table *table;
+ struct sk_buff *skb2;
+ int err;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = nf_tables_dump_flowtable,
+ .done = nf_tables_dump_flowtable_done,
+ };
+
+ if (nla[NFTA_FLOWTABLE_TABLE]) {
+ struct nft_flowtable_filter *filter;
+
+ filter = nft_flowtable_filter_alloc(nla);
+ if (IS_ERR(filter))
+ return -ENOMEM;
+
+ c.data = filter;
+ }
+ return netlink_dump_start(nlsk, skb, nlh, &c);
+ }
+
+ if (!nla[NFTA_FLOWTABLE_NAME])
+ return -EINVAL;
+
+ table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
+ family, genmask);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
+ genmask);
+ if (IS_ERR(flowtable))
+ return PTR_ERR(flowtable);
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb2)
+ return -ENOMEM;
+
+ err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq,
+ NFT_MSG_NEWFLOWTABLE, 0, family,
+ flowtable);
+ if (err < 0)
+ goto err;
+
+ return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+err:
+ kfree_skb(skb2);
+ return err;
+}
+
+static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
+ struct nft_flowtable *flowtable,
+ int event)
+{
+ struct sk_buff *skb;
+ int err;
+
+ if (ctx->report &&
+ !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
+ return;
+
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (skb == NULL)
+ goto err;
+
+ err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid,
+ ctx->seq, event, 0,
+ ctx->family, flowtable);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto err;
+ }
+
+ nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+ ctx->report, GFP_KERNEL);
+ return;
+err:
+ nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
+}
+
+static void nft_flowtable_destroy(void *ptr, void *arg)
+{
+ kfree(ptr);
+}
+
+static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
+{
+ cancel_delayed_work_sync(&flowtable->data.gc_work);
+ kfree(flowtable->name);
+ rhashtable_free_and_destroy(&flowtable->data.rhashtable,
+ nft_flowtable_destroy, NULL);
+ module_put(flowtable->data.type->owner);
}
static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
@@ -4880,6 +5443,46 @@ nla_put_failure:
return -EMSGSIZE;
}
+static void nft_flowtable_event(unsigned long event, struct net_device *dev,
+ struct nft_flowtable *flowtable)
+{
+ int i;
+
+ for (i = 0; i < flowtable->ops_len; i++) {
+ if (flowtable->ops[i].dev != dev)
+ continue;
+
+ nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
+ flowtable->ops[i].dev = NULL;
+ break;
+ }
+}
+
+static int nf_tables_flowtable_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct nft_flowtable *flowtable;
+ struct nft_table *table;
+
+ if (event != NETDEV_UNREGISTER)
+ return 0;
+
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_for_each_entry(table, &dev_net(dev)->nft.tables, list) {
+ list_for_each_entry(flowtable, &table->flowtables, list) {
+ nft_flowtable_event(event, dev, flowtable);
+ }
+ }
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block nf_tables_flowtable_notifier = {
+ .notifier_call = nf_tables_flowtable_event,
+};
+
static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
int event)
{
@@ -5032,6 +5635,21 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
.attr_count = NFTA_OBJ_MAX,
.policy = nft_obj_policy,
},
+ [NFT_MSG_NEWFLOWTABLE] = {
+ .call_batch = nf_tables_newflowtable,
+ .attr_count = NFTA_FLOWTABLE_MAX,
+ .policy = nft_flowtable_policy,
+ },
+ [NFT_MSG_GETFLOWTABLE] = {
+ .call = nf_tables_getflowtable,
+ .attr_count = NFTA_FLOWTABLE_MAX,
+ .policy = nft_flowtable_policy,
+ },
+ [NFT_MSG_DELFLOWTABLE] = {
+ .call_batch = nf_tables_delflowtable,
+ .attr_count = NFTA_FLOWTABLE_MAX,
+ .policy = nft_flowtable_policy,
+ },
};
static void nft_chain_commit_update(struct nft_trans *trans)
@@ -5077,6 +5695,9 @@ static void nf_tables_commit_release(struct nft_trans *trans)
case NFT_MSG_DELOBJ:
nft_obj_destroy(nft_trans_obj(trans));
break;
+ case NFT_MSG_DELFLOWTABLE:
+ nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
+ break;
}
kfree(trans);
}
@@ -5103,7 +5724,6 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
if (nft_trans_table_update(trans)) {
if (!nft_trans_table_enable(trans)) {
nf_tables_table_disable(net,
- trans->ctx.afi,
trans->ctx.table);
trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
}
@@ -5129,10 +5749,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
case NFT_MSG_DELCHAIN:
list_del_rcu(&trans->ctx.chain->list);
nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN);
- nf_tables_unregister_hooks(trans->ctx.net,
- trans->ctx.table,
- trans->ctx.chain,
- trans->ctx.afi->nops);
+ nf_tables_unregister_hook(trans->ctx.net,
+ trans->ctx.table,
+ trans->ctx.chain);
break;
case NFT_MSG_NEWRULE:
nft_clear(trans->ctx.net, nft_trans_rule(trans));
@@ -5152,7 +5771,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
/* This avoids hitting -EBUSY when deleting the table
* from the transaction.
*/
- if (nft_trans_set(trans)->flags & NFT_SET_ANONYMOUS &&
+ if (nft_set_is_anonymous(nft_trans_set(trans)) &&
!list_empty(&nft_trans_set(trans)->bindings))
trans->ctx.table->use--;
@@ -5195,6 +5814,21 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans),
NFT_MSG_DELOBJ);
break;
+ case NFT_MSG_NEWFLOWTABLE:
+ nft_clear(net, nft_trans_flowtable(trans));
+ nf_tables_flowtable_notify(&trans->ctx,
+ nft_trans_flowtable(trans),
+ NFT_MSG_NEWFLOWTABLE);
+ nft_trans_destroy(trans);
+ break;
+ case NFT_MSG_DELFLOWTABLE:
+ list_del_rcu(&nft_trans_flowtable(trans)->list);
+ nf_tables_flowtable_notify(&trans->ctx,
+ nft_trans_flowtable(trans),
+ NFT_MSG_DELFLOWTABLE);
+ nft_unregister_flowtable_net_hooks(net,
+ nft_trans_flowtable(trans));
+ break;
}
}
@@ -5232,6 +5866,9 @@ static void nf_tables_abort_release(struct nft_trans *trans)
case NFT_MSG_NEWOBJ:
nft_obj_destroy(nft_trans_obj(trans));
break;
+ case NFT_MSG_NEWFLOWTABLE:
+ nf_tables_flowtable_destroy(nft_trans_flowtable(trans));
+ break;
}
kfree(trans);
}
@@ -5248,7 +5885,6 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
if (nft_trans_table_update(trans)) {
if (nft_trans_table_enable(trans)) {
nf_tables_table_disable(net,
- trans->ctx.afi,
trans->ctx.table);
trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
}
@@ -5269,10 +5905,9 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
} else {
trans->ctx.table->use--;
list_del_rcu(&trans->ctx.chain->list);
- nf_tables_unregister_hooks(trans->ctx.net,
- trans->ctx.table,
- trans->ctx.chain,
- trans->ctx.afi->nops);
+ nf_tables_unregister_hook(trans->ctx.net,
+ trans->ctx.table,
+ trans->ctx.chain);
}
break;
case NFT_MSG_DELCHAIN:
@@ -5322,6 +5957,17 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
nft_clear(trans->ctx.net, nft_trans_obj(trans));
nft_trans_destroy(trans);
break;
+ case NFT_MSG_NEWFLOWTABLE:
+ trans->ctx.table->use--;
+ list_del_rcu(&nft_trans_flowtable(trans)->list);
+ nft_unregister_flowtable_net_hooks(net,
+ nft_trans_flowtable(trans));
+ break;
+ case NFT_MSG_DELFLOWTABLE:
+ trans->ctx.table->use++;
+ nft_clear(trans->ctx.net, nft_trans_flowtable(trans));
+ nft_trans_destroy(trans);
+ break;
}
}
@@ -5373,7 +6019,7 @@ int nft_chain_validate_hooks(const struct nft_chain *chain,
if (nft_is_base_chain(chain)) {
basechain = nft_base_chain(chain);
- if ((1 << basechain->ops[0].hooknum) & hook_flags)
+ if ((1 << basechain->ops.hooknum) & hook_flags)
return 0;
return -EOPNOTSUPP;
@@ -5841,28 +6487,13 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
}
EXPORT_SYMBOL_GPL(nft_data_dump);
-static int __net_init nf_tables_init_net(struct net *net)
-{
- INIT_LIST_HEAD(&net->nft.af_info);
- INIT_LIST_HEAD(&net->nft.commit_list);
- net->nft.base_seq = 1;
- return 0;
-}
-
-static void __net_exit nf_tables_exit_net(struct net *net)
-{
- WARN_ON_ONCE(!list_empty(&net->nft.af_info));
- WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
-}
-
int __nft_release_basechain(struct nft_ctx *ctx)
{
struct nft_rule *rule, *nr;
BUG_ON(!nft_is_base_chain(ctx->chain));
- nf_tables_unregister_hooks(ctx->net, ctx->chain->table, ctx->chain,
- ctx->afi->nops);
+ nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain);
list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
list_del(&rule->list);
ctx->chain->use--;
@@ -5876,9 +6507,9 @@ int __nft_release_basechain(struct nft_ctx *ctx)
}
EXPORT_SYMBOL_GPL(__nft_release_basechain);
-/* Called by nft_unregister_afinfo() from __net_exit path, nfnl_lock is held. */
-static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi)
+static void __nft_release_tables(struct net *net)
{
+ struct nft_flowtable *flowtable, *nf;
struct nft_table *table, *nt;
struct nft_chain *chain, *nc;
struct nft_object *obj, *ne;
@@ -5886,13 +6517,16 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi)
struct nft_set *set, *ns;
struct nft_ctx ctx = {
.net = net,
- .afi = afi,
};
- list_for_each_entry_safe(table, nt, &afi->tables, list) {
+ list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
+ ctx.family = table->family;
+
list_for_each_entry(chain, &table->chains, list)
- nf_tables_unregister_hooks(net, table, chain,
- afi->nops);
+ nf_tables_unregister_hook(net, table, chain);
+ list_for_each_entry(flowtable, &table->flowtables, list)
+ nf_unregister_net_hooks(net, flowtable->ops,
+ flowtable->ops_len);
/* No packets are walking on these chains anymore. */
ctx.table = table;
list_for_each_entry(chain, &table->chains, list) {
@@ -5903,6 +6537,11 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi)
nf_tables_rule_destroy(&ctx, rule);
}
}
+ list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
+ list_del(&flowtable->list);
+ table->use--;
+ nf_tables_flowtable_destroy(flowtable);
+ }
list_for_each_entry_safe(set, ns, &table->sets, list) {
list_del(&set->list);
table->use--;
@@ -5923,6 +6562,21 @@ static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi)
}
}
+static int __net_init nf_tables_init_net(struct net *net)
+{
+ INIT_LIST_HEAD(&net->nft.tables);
+ INIT_LIST_HEAD(&net->nft.commit_list);
+ net->nft.base_seq = 1;
+ return 0;
+}
+
+static void __net_exit nf_tables_exit_net(struct net *net)
+{
+ __nft_release_tables(net);
+ WARN_ON_ONCE(!list_empty(&net->nft.tables));
+ WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
+}
+
static struct pernet_operations nf_tables_net_ops = {
.init = nf_tables_init_net,
.exit = nf_tables_exit_net,
@@ -5947,7 +6601,8 @@ static int __init nf_tables_module_init(void)
if (err < 0)
goto err3;
- pr_info("nf_tables: (c) 2007-2009 Patrick McHardy <kaber@trash.net>\n");
+ register_netdevice_notifier(&nf_tables_flowtable_notifier);
+
return register_pernet_subsys(&nf_tables_net_ops);
err3:
nf_tables_core_module_exit();
@@ -5961,6 +6616,7 @@ static void __exit nf_tables_module_exit(void)
{
unregister_pernet_subsys(&nf_tables_net_ops);
nfnetlink_subsys_unregister(&nf_tables_subsys);
+ unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
rcu_barrier();
nf_tables_core_module_exit();
kfree(info);
diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c
index f713cc205669..e30c7da09d0d 100644
--- a/net/netfilter/nf_tables_inet.c
+++ b/net/netfilter/nf_tables_inet.c
@@ -9,6 +9,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <net/netfilter/nf_tables.h>
@@ -16,56 +17,27 @@
#include <net/netfilter/nf_tables_ipv6.h>
#include <net/ip.h>
-static void nft_inet_hook_ops_init(struct nf_hook_ops *ops, unsigned int n)
+static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
{
- struct nft_af_info *afi;
-
- if (n == 1)
- afi = &nft_af_ipv4;
- else
- afi = &nft_af_ipv6;
-
- ops->pf = afi->family;
- if (afi->hooks[ops->hooknum])
- ops->hook = afi->hooks[ops->hooknum];
-}
-
-static struct nft_af_info nft_af_inet __read_mostly = {
- .family = NFPROTO_INET,
- .nhooks = NF_INET_NUMHOOKS,
- .owner = THIS_MODULE,
- .nops = 2,
- .hook_ops_init = nft_inet_hook_ops_init,
-};
-
-static int __net_init nf_tables_inet_init_net(struct net *net)
-{
- net->nft.inet = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
- if (net->nft.inet == NULL)
- return -ENOMEM;
- memcpy(net->nft.inet, &nft_af_inet, sizeof(nft_af_inet));
-
- if (nft_register_afinfo(net, net->nft.inet) < 0)
- goto err;
-
- return 0;
-
-err:
- kfree(net->nft.inet);
- return -ENOMEM;
-}
-
-static void __net_exit nf_tables_inet_exit_net(struct net *net)
-{
- nft_unregister_afinfo(net, net->nft.inet);
- kfree(net->nft.inet);
+ struct nft_pktinfo pkt;
+
+ nft_set_pktinfo(&pkt, skb, state);
+
+ switch (state->pf) {
+ case NFPROTO_IPV4:
+ nft_set_pktinfo_ipv4(&pkt, skb);
+ break;
+ case NFPROTO_IPV6:
+ nft_set_pktinfo_ipv6(&pkt, skb);
+ break;
+ default:
+ break;
+ }
+
+ return nft_do_chain(&pkt, priv);
}
-static struct pernet_operations nf_tables_inet_net_ops = {
- .init = nf_tables_inet_init_net,
- .exit = nf_tables_inet_exit_net,
-};
-
static const struct nf_chain_type filter_inet = {
.name = "filter",
.type = NFT_CHAIN_T_DEFAULT,
@@ -76,26 +48,22 @@ static const struct nf_chain_type filter_inet = {
(1 << NF_INET_FORWARD) |
(1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING),
+ .hooks = {
+ [NF_INET_LOCAL_IN] = nft_do_chain_inet,
+ [NF_INET_LOCAL_OUT] = nft_do_chain_inet,
+ [NF_INET_FORWARD] = nft_do_chain_inet,
+ [NF_INET_PRE_ROUTING] = nft_do_chain_inet,
+ [NF_INET_POST_ROUTING] = nft_do_chain_inet,
+ },
};
static int __init nf_tables_inet_init(void)
{
- int ret;
-
- ret = nft_register_chain_type(&filter_inet);
- if (ret < 0)
- return ret;
-
- ret = register_pernet_subsys(&nf_tables_inet_net_ops);
- if (ret < 0)
- nft_unregister_chain_type(&filter_inet);
-
- return ret;
+ return nft_register_chain_type(&filter_inet);
}
static void __exit nf_tables_inet_exit(void)
{
- unregister_pernet_subsys(&nf_tables_inet_net_ops);
nft_unregister_chain_type(&filter_inet);
}
@@ -104,4 +72,4 @@ module_exit(nf_tables_inet_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_FAMILY(1);
+MODULE_ALIAS_NFT_CHAIN(1, "filter");
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 403432988313..4041fafca934 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -21,66 +21,32 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb,
{
struct nft_pktinfo pkt;
+ nft_set_pktinfo(&pkt, skb, state);
+
switch (skb->protocol) {
case htons(ETH_P_IP):
- nft_set_pktinfo_ipv4_validate(&pkt, skb, state);
+ nft_set_pktinfo_ipv4_validate(&pkt, skb);
break;
case htons(ETH_P_IPV6):
- nft_set_pktinfo_ipv6_validate(&pkt, skb, state);
+ nft_set_pktinfo_ipv6_validate(&pkt, skb);
break;
default:
- nft_set_pktinfo_unspec(&pkt, skb, state);
+ nft_set_pktinfo_unspec(&pkt, skb);
break;
}
return nft_do_chain(&pkt, priv);
}
-static struct nft_af_info nft_af_netdev __read_mostly = {
- .family = NFPROTO_NETDEV,
- .nhooks = NF_NETDEV_NUMHOOKS,
- .owner = THIS_MODULE,
- .flags = NFT_AF_NEEDS_DEV,
- .nops = 1,
- .hooks = {
- [NF_NETDEV_INGRESS] = nft_do_chain_netdev,
- },
-};
-
-static int nf_tables_netdev_init_net(struct net *net)
-{
- net->nft.netdev = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
- if (net->nft.netdev == NULL)
- return -ENOMEM;
-
- memcpy(net->nft.netdev, &nft_af_netdev, sizeof(nft_af_netdev));
-
- if (nft_register_afinfo(net, net->nft.netdev) < 0)
- goto err;
-
- return 0;
-err:
- kfree(net->nft.netdev);
- return -ENOMEM;
-}
-
-static void nf_tables_netdev_exit_net(struct net *net)
-{
- nft_unregister_afinfo(net, net->nft.netdev);
- kfree(net->nft.netdev);
-}
-
-static struct pernet_operations nf_tables_netdev_net_ops = {
- .init = nf_tables_netdev_init_net,
- .exit = nf_tables_netdev_exit_net,
-};
-
static const struct nf_chain_type nft_filter_chain_netdev = {
.name = "filter",
.type = NFT_CHAIN_T_DEFAULT,
.family = NFPROTO_NETDEV,
.owner = THIS_MODULE,
.hook_mask = (1 << NF_NETDEV_INGRESS),
+ .hooks = {
+ [NF_NETDEV_INGRESS] = nft_do_chain_netdev,
+ },
};
static void nft_netdev_event(unsigned long event, struct net_device *dev,
@@ -96,7 +62,7 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
__nft_release_basechain(ctx);
break;
case NETDEV_CHANGENAME:
- if (dev->ifindex != basechain->ops[0].dev->ifindex)
+ if (dev->ifindex != basechain->ops.dev->ifindex)
return;
strncpy(basechain->dev_name, dev->name, IFNAMSIZ);
@@ -108,7 +74,6 @@ static int nf_tables_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain, *nr;
struct nft_ctx ctx = {
@@ -120,20 +85,18 @@ static int nf_tables_netdev_event(struct notifier_block *this,
return NOTIFY_DONE;
nfnl_lock(NFNL_SUBSYS_NFTABLES);
- list_for_each_entry(afi, &dev_net(dev)->nft.af_info, list) {
- ctx.afi = afi;
- if (afi->family != NFPROTO_NETDEV)
+ list_for_each_entry(table, &ctx.net->nft.tables, list) {
+ if (table->family != NFPROTO_NETDEV)
continue;
- list_for_each_entry(table, &afi->tables, list) {
- ctx.table = table;
- list_for_each_entry_safe(chain, nr, &table->chains, list) {
- if (!nft_is_base_chain(chain))
- continue;
+ ctx.family = table->family;
+ ctx.table = table;
+ list_for_each_entry_safe(chain, nr, &table->chains, list) {
+ if (!nft_is_base_chain(chain))
+ continue;
- ctx.chain = chain;
- nft_netdev_event(event, dev, &ctx);
- }
+ ctx.chain = chain;
+ nft_netdev_event(event, dev, &ctx);
}
}
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
@@ -153,27 +116,21 @@ static int __init nf_tables_netdev_init(void)
if (ret)
return ret;
- ret = register_pernet_subsys(&nf_tables_netdev_net_ops);
- if (ret)
- goto err1;
-
ret = register_netdevice_notifier(&nf_tables_netdev_notifier);
if (ret)
- goto err2;
+ goto err_register_netdevice_notifier;
return 0;
-err2:
- unregister_pernet_subsys(&nf_tables_netdev_net_ops);
-err1:
+err_register_netdevice_notifier:
nft_unregister_chain_type(&nft_filter_chain_netdev);
+
return ret;
}
static void __exit nf_tables_netdev_exit(void)
{
unregister_netdevice_notifier(&nf_tables_netdev_notifier);
- unregister_pernet_subsys(&nf_tables_netdev_net_ops);
nft_unregister_chain_type(&nft_filter_chain_netdev);
}
@@ -182,4 +139,4 @@ module_exit(nf_tables_netdev_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
-MODULE_ALIAS_NFT_FAMILY(5); /* NFPROTO_NETDEV */
+MODULE_ALIAS_NFT_CHAIN(5, "filter"); /* NFPROTO_NETDEV */
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 733d3e4a30d8..03ead8a9e90c 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -37,8 +37,6 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER);
rcu_dereference_protected(table[(id)].subsys, \
lockdep_nfnl_is_held((id)))
-static char __initdata nfversion[] = "0.30";
-
static struct {
struct mutex mutex;
const struct nfnetlink_subsystem __rcu *subsys;
@@ -580,13 +578,11 @@ static int __init nfnetlink_init(void)
for (i=0; i<NFNL_SUBSYS_COUNT; i++)
mutex_init(&table[i].mutex);
- pr_info("Netfilter messages via NETLINK v%s.\n", nfversion);
return register_pernet_subsys(&nfnetlink_net_ops);
}
static void __exit nfnetlink_exit(void)
{
- pr_info("Removing netfilter NETLINK layer.\n");
unregister_pernet_subsys(&nfnetlink_net_ops);
}
module_init(nfnetlink_init);
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index c45e6d4358ab..88d427f9f9e6 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -527,7 +527,6 @@ static int __init nfnl_acct_init(void)
goto err_out;
}
- pr_info("nfnl_acct: registering with nfnetlink.\n");
ret = nfnetlink_subsys_register(&nfnl_acct_subsys);
if (ret < 0) {
pr_err("nfnl_acct_init: cannot register with nfnetlink.\n");
@@ -543,7 +542,6 @@ err_out:
static void __exit nfnl_acct_exit(void)
{
- pr_info("nfnl_acct: unregistering from nfnetlink.\n");
nfnetlink_subsys_unregister(&nfnl_acct_subsys);
unregister_pernet_subsys(&nfnl_acct_ops);
}
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 32b1c0b44e79..95b04702a655 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -615,8 +615,6 @@ err_out:
static void __exit cttimeout_exit(void)
{
- pr_info("cttimeout: unregistering from nfnetlink.\n");
-
nfnetlink_subsys_unregister(&cttimeout_subsys);
unregister_pernet_subsys(&cttimeout_ops);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index e955bec0acc6..7b46aa4c478d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1054,7 +1054,6 @@ static int nful_open(struct inode *inode, struct file *file)
}
static const struct file_operations nful_file_ops = {
- .owner = THIS_MODULE,
.open = nful_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index c09b36755ed7..8bba23160a68 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -941,23 +941,18 @@ static struct notifier_block nfqnl_dev_notifier = {
.notifier_call = nfqnl_rcv_dev_event,
};
-static unsigned int nfqnl_nf_hook_drop(struct net *net)
+static void nfqnl_nf_hook_drop(struct net *net)
{
struct nfnl_queue_net *q = nfnl_queue_pernet(net);
- unsigned int instances = 0;
int i;
for (i = 0; i < INSTANCE_BUCKETS; i++) {
struct nfqnl_instance *inst;
struct hlist_head *head = &q->instance_table[i];
- hlist_for_each_entry_rcu(inst, head, hlist) {
+ hlist_for_each_entry_rcu(inst, head, hlist)
nfqnl_flush(inst, NULL, 0);
- instances++;
- }
}
-
- return instances;
}
static int
@@ -1482,7 +1477,6 @@ static int nfqnl_open(struct inode *inode, struct file *file)
}
static const struct file_operations nfqnl_file_ops = {
- .owner = THIS_MODULE,
.open = nfqnl_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index c2945eb3397c..fa90a8402845 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -44,6 +44,7 @@ static void nft_cmp_eval(const struct nft_expr *expr,
case NFT_CMP_LT:
if (d == 0)
goto mismatch;
+ /* fall through */
case NFT_CMP_LTE:
if (d > 0)
goto mismatch;
@@ -51,6 +52,7 @@ static void nft_cmp_eval(const struct nft_expr *expr,
case NFT_CMP_GT:
if (d == 0)
goto mismatch;
+ /* fall through */
case NFT_CMP_GTE:
if (d < 0)
goto mismatch;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index b89f4f65b2a0..8e23726b9081 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -144,7 +144,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
{
par->net = ctx->net;
par->table = ctx->table->name;
- switch (ctx->afi->family) {
+ switch (ctx->family) {
case AF_INET:
entry->e4.ip.proto = proto;
entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
@@ -169,13 +169,13 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
if (nft_is_base_chain(ctx->chain)) {
const struct nft_base_chain *basechain =
nft_base_chain(ctx->chain);
- const struct nf_hook_ops *ops = &basechain->ops[0];
+ const struct nf_hook_ops *ops = &basechain->ops;
par->hook_mask = 1 << ops->hooknum;
} else {
par->hook_mask = 0;
}
- par->family = ctx->afi->family;
+ par->family = ctx->family;
par->nft_compat = true;
}
@@ -267,7 +267,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
par.net = ctx->net;
par.target = target;
par.targinfo = info;
- par.family = ctx->afi->family;
+ par.family = ctx->family;
if (par.target->destroy != NULL)
par.target->destroy(&par);
@@ -302,7 +302,7 @@ static int nft_target_validate(const struct nft_ctx *ctx,
if (nft_is_base_chain(ctx->chain)) {
const struct nft_base_chain *basechain =
nft_base_chain(ctx->chain);
- const struct nf_hook_ops *ops = &basechain->ops[0];
+ const struct nf_hook_ops *ops = &basechain->ops;
hook_mask = 1 << ops->hooknum;
if (target->hooks && !(hook_mask & target->hooks))
@@ -358,7 +358,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
{
par->net = ctx->net;
par->table = ctx->table->name;
- switch (ctx->afi->family) {
+ switch (ctx->family) {
case AF_INET:
entry->e4.ip.proto = proto;
entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
@@ -383,13 +383,13 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
if (nft_is_base_chain(ctx->chain)) {
const struct nft_base_chain *basechain =
nft_base_chain(ctx->chain);
- const struct nf_hook_ops *ops = &basechain->ops[0];
+ const struct nf_hook_ops *ops = &basechain->ops;
par->hook_mask = 1 << ops->hooknum;
} else {
par->hook_mask = 0;
}
- par->family = ctx->afi->family;
+ par->family = ctx->family;
par->nft_compat = true;
}
@@ -446,7 +446,7 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
par.net = ctx->net;
par.match = match;
par.matchinfo = info;
- par.family = ctx->afi->family;
+ par.family = ctx->family;
if (par.match->destroy != NULL)
par.match->destroy(&par);
@@ -481,7 +481,7 @@ static int nft_match_validate(const struct nft_ctx *ctx,
if (nft_is_base_chain(ctx->chain)) {
const struct nft_base_chain *basechain =
nft_base_chain(ctx->chain);
- const struct nf_hook_ops *ops = &basechain->ops[0];
+ const struct nf_hook_ops *ops = &basechain->ops;
hook_mask = 1 << ops->hooknum;
if (match->hooks && !(hook_mask & match->hooks))
@@ -648,7 +648,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
mt_name = nla_data(tb[NFTA_MATCH_NAME]);
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
- family = ctx->afi->family;
+ family = ctx->family;
/* Re-use the existing match if it's already loaded. */
list_for_each_entry(nft_match, &nft_match_list, head) {
@@ -733,7 +733,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
tg_name = nla_data(tb[NFTA_TARGET_NAME]);
rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV]));
- family = ctx->afi->family;
+ family = ctx->family;
/* Re-use the existing target if it's already loaded. */
list_for_each_entry(nft_target, &nft_target_list, head) {
@@ -812,8 +812,6 @@ static int __init nft_compat_module_init(void)
goto err_target;
}
- pr_info("nf_tables_compat: (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>\n");
-
return ret;
err_target:
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 2647b895f4b0..6ab274b14484 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -405,7 +405,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
if (tb[NFTA_CT_DIRECTION] == NULL)
return -EINVAL;
- switch (ctx->afi->family) {
+ switch (ctx->family) {
case NFPROTO_IPV4:
len = FIELD_SIZEOF(struct nf_conntrack_tuple,
src.u3.ip);
@@ -456,7 +456,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
if (err < 0)
return err;
- err = nf_ct_netns_get(ctx->net, ctx->afi->family);
+ err = nf_ct_netns_get(ctx->net, ctx->family);
if (err < 0)
return err;
@@ -550,7 +550,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
if (err < 0)
goto err1;
- err = nf_ct_netns_get(ctx->net, ctx->afi->family);
+ err = nf_ct_netns_get(ctx->net, ctx->family);
if (err < 0)
goto err1;
@@ -564,7 +564,7 @@ err1:
static void nft_ct_get_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr)
{
- nf_ct_netns_put(ctx->net, ctx->afi->family);
+ nf_ct_netns_put(ctx->net, ctx->family);
}
static void nft_ct_set_destroy(const struct nft_ctx *ctx,
@@ -573,7 +573,7 @@ static void nft_ct_set_destroy(const struct nft_ctx *ctx,
struct nft_ct *priv = nft_expr_priv(expr);
__nft_ct_set_destroy(ctx, priv);
- nf_ct_netns_put(ctx->net, ctx->afi->family);
+ nf_ct_netns_put(ctx->net, ctx->family);
}
static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -734,7 +734,7 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
struct nft_ct_helper_obj *priv = nft_obj_data(obj);
struct nf_conntrack_helper *help4, *help6;
char name[NF_CT_HELPER_NAME_LEN];
- int family = ctx->afi->family;
+ int family = ctx->family;
if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO])
return -EINVAL;
@@ -753,14 +753,14 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
switch (family) {
case NFPROTO_IPV4:
- if (ctx->afi->family == NFPROTO_IPV6)
+ if (ctx->family == NFPROTO_IPV6)
return -EINVAL;
help4 = nf_conntrack_helper_try_module_get(name, family,
priv->l4proto);
break;
case NFPROTO_IPV6:
- if (ctx->afi->family == NFPROTO_IPV4)
+ if (ctx->family == NFPROTO_IPV4)
return -EINVAL;
help6 = nf_conntrack_helper_try_module_get(name, family,
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 66221ad891a9..fc83e29d6634 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -164,7 +164,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
}
priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
- err = nft_validate_register_load(priv->sreg_key, set->klen);;
+ err = nft_validate_register_load(priv->sreg_key, set->klen);
if (err < 0)
return err;
@@ -184,7 +184,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
if (tb[NFTA_DYNSET_EXPR] != NULL) {
if (!(set->flags & NFT_SET_EVAL))
return -EINVAL;
- if (!(set->flags & NFT_SET_ANONYMOUS))
+ if (!nft_set_is_anonymous(set))
return -EOPNOTSUPP;
priv->expr = nft_expr_init(ctx, tb[NFTA_DYNSET_EXPR]);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
new file mode 100644
index 000000000000..4503b8dcf9c0
--- /dev/null
+++ b/net/netfilter/nft_flow_offload.c
@@ -0,0 +1,264 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/ip.h> /* for ipv4 options. */
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <linux/netfilter/nf_conntrack_common.h>
+#include <net/netfilter/nf_flow_table.h>
+
+struct nft_flow_offload {
+ struct nft_flowtable *flowtable;
+};
+
+static int nft_flow_route(const struct nft_pktinfo *pkt,
+ const struct nf_conn *ct,
+ struct nf_flow_route *route,
+ enum ip_conntrack_dir dir)
+{
+ struct dst_entry *this_dst = skb_dst(pkt->skb);
+ struct dst_entry *other_dst = NULL;
+ struct flowi fl;
+
+ memset(&fl, 0, sizeof(fl));
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.dst.u3.ip;
+ break;
+ case NFPROTO_IPV6:
+ fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.dst.u3.in6;
+ break;
+ }
+
+ nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
+ if (!other_dst)
+ return -ENOENT;
+
+ route->tuple[dir].dst = this_dst;
+ route->tuple[dir].ifindex = nft_in(pkt)->ifindex;
+ route->tuple[!dir].dst = other_dst;
+ route->tuple[!dir].ifindex = nft_out(pkt)->ifindex;
+
+ return 0;
+}
+
+static bool nft_flow_offload_skip(struct sk_buff *skb)
+{
+ struct ip_options *opt = &(IPCB(skb)->opt);
+
+ if (unlikely(opt->optlen))
+ return true;
+ if (skb_sec_path(skb))
+ return true;
+
+ return false;
+}
+
+static void nft_flow_offload_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_flow_offload *priv = nft_expr_priv(expr);
+ struct nf_flowtable *flowtable = &priv->flowtable->data;
+ enum ip_conntrack_info ctinfo;
+ struct nf_flow_route route;
+ struct flow_offload *flow;
+ enum ip_conntrack_dir dir;
+ struct nf_conn *ct;
+ int ret;
+
+ if (nft_flow_offload_skip(pkt->skb))
+ goto out;
+
+ ct = nf_ct_get(pkt->skb, &ctinfo);
+ if (!ct)
+ goto out;
+
+ switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ break;
+ default:
+ goto out;
+ }
+
+ if (test_bit(IPS_HELPER_BIT, &ct->status))
+ goto out;
+
+ if (ctinfo == IP_CT_NEW ||
+ ctinfo == IP_CT_RELATED)
+ goto out;
+
+ if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
+ goto out;
+
+ dir = CTINFO2DIR(ctinfo);
+ if (nft_flow_route(pkt, ct, &route, dir) < 0)
+ goto err_flow_route;
+
+ flow = flow_offload_alloc(ct, &route);
+ if (!flow)
+ goto err_flow_alloc;
+
+ ret = flow_offload_add(flowtable, flow);
+ if (ret < 0)
+ goto err_flow_add;
+
+ return;
+
+err_flow_add:
+ flow_offload_free(flow);
+err_flow_alloc:
+ dst_release(route.tuple[!dir].dst);
+err_flow_route:
+ clear_bit(IPS_OFFLOAD_BIT, &ct->status);
+out:
+ regs->verdict.code = NFT_BREAK;
+}
+
+static int nft_flow_offload_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ unsigned int hook_mask = (1 << NF_INET_FORWARD);
+
+ return nft_chain_validate_hooks(ctx->chain, hook_mask);
+}
+
+static int nft_flow_offload_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_flow_offload *priv = nft_expr_priv(expr);
+ u8 genmask = nft_genmask_next(ctx->net);
+ struct nft_flowtable *flowtable;
+
+ if (!tb[NFTA_FLOW_TABLE_NAME])
+ return -EINVAL;
+
+ flowtable = nf_tables_flowtable_lookup(ctx->table,
+ tb[NFTA_FLOW_TABLE_NAME],
+ genmask);
+ if (IS_ERR(flowtable))
+ return PTR_ERR(flowtable);
+
+ priv->flowtable = flowtable;
+ flowtable->use++;
+
+ return nf_ct_netns_get(ctx->net, ctx->family);
+}
+
+static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_flow_offload *priv = nft_expr_priv(expr);
+
+ priv->flowtable->use--;
+ nf_ct_netns_put(ctx->net, ctx->family);
+}
+
+static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ struct nft_flow_offload *priv = nft_expr_priv(expr);
+
+ if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_type nft_flow_offload_type;
+static const struct nft_expr_ops nft_flow_offload_ops = {
+ .type = &nft_flow_offload_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)),
+ .eval = nft_flow_offload_eval,
+ .init = nft_flow_offload_init,
+ .destroy = nft_flow_offload_destroy,
+ .validate = nft_flow_offload_validate,
+ .dump = nft_flow_offload_dump,
+};
+
+static struct nft_expr_type nft_flow_offload_type __read_mostly = {
+ .name = "flow_offload",
+ .ops = &nft_flow_offload_ops,
+ .maxattr = NFTA_FLOW_MAX,
+ .owner = THIS_MODULE,
+};
+
+static void flow_offload_iterate_cleanup(struct flow_offload *flow, void *data)
+{
+ struct net_device *dev = data;
+
+ if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+ return;
+
+ flow_offload_dead(flow);
+}
+
+static void nft_flow_offload_iterate_cleanup(struct nf_flowtable *flowtable,
+ void *data)
+{
+ nf_flow_table_iterate(flowtable, flow_offload_iterate_cleanup, data);
+}
+
+static int flow_offload_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (event != NETDEV_DOWN)
+ return NOTIFY_DONE;
+
+ nft_flow_table_iterate(dev_net(dev), nft_flow_offload_iterate_cleanup, dev);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block flow_offload_netdev_notifier = {
+ .notifier_call = flow_offload_netdev_event,
+};
+
+static int __init nft_flow_offload_module_init(void)
+{
+ int err;
+
+ register_netdevice_notifier(&flow_offload_netdev_notifier);
+
+ err = nft_register_expr(&nft_flow_offload_type);
+ if (err < 0)
+ goto register_expr;
+
+ return 0;
+
+register_expr:
+ unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+ return err;
+}
+
+static void __exit nft_flow_offload_module_exit(void)
+{
+ struct net *net;
+
+ nft_unregister_expr(&nft_flow_offload_type);
+ unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+ rtnl_lock();
+ for_each_net(net)
+ nft_flow_table_iterate(net, nft_flow_offload_iterate_cleanup, NULL);
+ rtnl_unlock();
+}
+
+module_init(nft_flow_offload_module_init);
+module_exit(nft_flow_offload_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_EXPR("flow_offload");
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 6f6e64423643..a27be36dc0af 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -112,7 +112,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
break;
}
- err = nf_logger_find_get(ctx->afi->family, li->type);
+ err = nf_logger_find_get(ctx->family, li->type);
if (err < 0)
goto err1;
@@ -133,7 +133,7 @@ static void nft_log_destroy(const struct nft_ctx *ctx,
if (priv->prefix != nft_log_null_prefix)
kfree(priv->prefix);
- nf_logger_put(ctx->afi->family, li->type);
+ nf_logger_put(ctx->family, li->type);
}
static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 6ac03d4266c9..9d8655bc1bea 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -73,7 +73,7 @@ int nft_masq_init(const struct nft_ctx *ctx,
}
}
- return nf_ct_netns_get(ctx->net, ctx->afi->family);
+ return nf_ct_netns_get(ctx->net, ctx->family);
}
EXPORT_SYMBOL_GPL(nft_masq_init);
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 5a60eb23a7ed..8fb91940e2e7 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -210,6 +210,11 @@ void nft_meta_get_eval(const struct nft_expr *expr,
*dest = prandom_u32_state(state);
break;
}
+#ifdef CONFIG_XFRM
+ case NFT_META_SECPATH:
+ nft_reg_store8(dest, !!skb->sp);
+ break;
+#endif
default:
WARN_ON(1);
goto err;
@@ -308,6 +313,11 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
prandom_init_once(&nft_prandom_state);
len = sizeof(u32);
break;
+#ifdef CONFIG_XFRM
+ case NFT_META_SECPATH:
+ len = sizeof(u8);
+ break;
+#endif
default:
return -EOPNOTSUPP;
}
@@ -318,6 +328,38 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
}
EXPORT_SYMBOL_GPL(nft_meta_get_init);
+static int nft_meta_get_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+#ifdef CONFIG_XFRM
+ const struct nft_meta *priv = nft_expr_priv(expr);
+ unsigned int hooks;
+
+ if (priv->key != NFT_META_SECPATH)
+ return 0;
+
+ switch (ctx->family) {
+ case NFPROTO_NETDEV:
+ hooks = 1 << NF_NETDEV_INGRESS;
+ break;
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ hooks = (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, hooks);
+#else
+ return 0;
+#endif
+}
+
int nft_meta_set_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
@@ -328,7 +370,7 @@ int nft_meta_set_validate(const struct nft_ctx *ctx,
if (priv->key != NFT_META_PKTTYPE)
return 0;
- switch (ctx->afi->family) {
+ switch (ctx->family) {
case NFPROTO_BRIDGE:
hooks = 1 << NF_BR_PRE_ROUTING;
break;
@@ -434,6 +476,7 @@ static const struct nft_expr_ops nft_meta_get_ops = {
.eval = nft_meta_get_eval,
.init = nft_meta_get_init,
.dump = nft_meta_get_dump,
+ .validate = nft_meta_get_validate,
};
static const struct nft_expr_ops nft_meta_set_ops = {
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index ed548d06b6dd..1f36954c2ba9 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -142,7 +142,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
- if (family != ctx->afi->family)
+ if (family != ctx->family)
return -EOPNOTSUPP;
switch (family) {
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 1e66538bf0ff..c64cbe78dee7 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -75,7 +75,7 @@ int nft_redir_init(const struct nft_ctx *ctx,
return -EINVAL;
}
- return nf_ct_netns_get(ctx->net, ctx->afi->family);
+ return nf_ct_netns_get(ctx->net, ctx->family);
}
EXPORT_SYMBOL_GPL(nft_redir_init);
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
index a6b7d05aeacf..11a2071b6dd4 100644
--- a/net/netfilter/nft_rt.c
+++ b/net/netfilter/nft_rt.c
@@ -27,7 +27,7 @@ static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skb
{
u32 minlen = sizeof(struct ipv6hdr), mtu = dst_mtu(skbdst);
const struct sk_buff *skb = pkt->skb;
- const struct nf_afinfo *ai;
+ struct dst_entry *dst = NULL;
struct flowi fl;
memset(&fl, 0, sizeof(fl));
@@ -43,15 +43,10 @@ static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skb
break;
}
- ai = nf_get_afinfo(nft_pf(pkt));
- if (ai) {
- struct dst_entry *dst = NULL;
-
- ai->route(nft_net(pkt), &dst, &fl, false);
- if (dst) {
- mtu = min(mtu, dst_mtu(dst));
- dst_release(dst);
- }
+ nf_route(nft_net(pkt), &dst, &fl, false, nft_pf(pkt));
+ if (dst) {
+ mtu = min(mtu, dst_mtu(dst));
+ dst_release(dst);
}
if (mtu <= minlen || mtu > 0xffff)
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index f8166c1d5430..3f1624ee056f 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -251,11 +251,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
if (err)
return;
- err = rhashtable_walk_start(&hti);
- if (err && err != -EAGAIN) {
- iter->err = err;
- goto out;
- }
+ rhashtable_walk_start(&hti);
while ((he = rhashtable_walk_next(&hti))) {
if (IS_ERR(he)) {
@@ -306,9 +302,7 @@ static void nft_rhash_gc(struct work_struct *work)
if (err)
goto schedule;
- err = rhashtable_walk_start(&hti);
- if (err && err != -EAGAIN)
- goto out;
+ rhashtable_walk_start(&hti);
while ((he = rhashtable_walk_next(&hti))) {
if (IS_ERR(he)) {
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
new file mode 100644
index 000000000000..0b660c568156
--- /dev/null
+++ b/net/netfilter/utils.c
@@ -0,0 +1,90 @@
+#include <linux/kernel.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_queue.h>
+
+__sum16 nf_checksum(struct sk_buff *skb, unsigned int hook,
+ unsigned int dataoff, u_int8_t protocol,
+ unsigned short family)
+{
+ const struct nf_ipv6_ops *v6ops;
+ __sum16 csum = 0;
+
+ switch (family) {
+ case AF_INET:
+ csum = nf_ip_checksum(skb, hook, dataoff, protocol);
+ break;
+ case AF_INET6:
+ v6ops = rcu_dereference(nf_ipv6_ops);
+ if (v6ops)
+ csum = v6ops->checksum(skb, hook, dataoff, protocol);
+ break;
+ }
+
+ return csum;
+}
+EXPORT_SYMBOL_GPL(nf_checksum);
+
+__sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
+ unsigned int dataoff, unsigned int len,
+ u_int8_t protocol, unsigned short family)
+{
+ const struct nf_ipv6_ops *v6ops;
+ __sum16 csum = 0;
+
+ switch (family) {
+ case AF_INET:
+ csum = nf_ip_checksum_partial(skb, hook, dataoff, len,
+ protocol);
+ break;
+ case AF_INET6:
+ v6ops = rcu_dereference(nf_ipv6_ops);
+ if (v6ops)
+ csum = v6ops->checksum_partial(skb, hook, dataoff, len,
+ protocol);
+ break;
+ }
+
+ return csum;
+}
+EXPORT_SYMBOL_GPL(nf_checksum_partial);
+
+int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
+ bool strict, unsigned short family)
+{
+ const struct nf_ipv6_ops *v6ops;
+ int ret = 0;
+
+ switch (family) {
+ case AF_INET:
+ ret = nf_ip_route(net, dst, fl, strict);
+ break;
+ case AF_INET6:
+ v6ops = rcu_dereference(nf_ipv6_ops);
+ if (v6ops)
+ ret = v6ops->route(net, dst, fl, strict);
+ break;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nf_route);
+
+int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry)
+{
+ const struct nf_ipv6_ops *v6ops;
+ int ret = 0;
+
+ switch (entry->state.pf) {
+ case AF_INET:
+ ret = nf_ip_reroute(skb, entry);
+ break;
+ case AF_INET6:
+ v6ops = rcu_dereference(nf_ipv6_ops);
+ if (v6ops)
+ ret = v6ops->reroute(skb, entry);
+ break;
+ }
+ return ret;
+}
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index d7070d18db20..8fa4d37141a7 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1032,7 +1032,7 @@ void xt_free_table_info(struct xt_table_info *info)
}
EXPORT_SYMBOL(xt_free_table_info);
-/* Find table by name, grabs mutex & ref. Returns NULL on error. */
+/* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
const char *name)
{
@@ -1048,17 +1048,17 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
/* Table doesn't exist in this netns, re-try init */
list_for_each_entry(t, &init_net.xt.tables[af], list) {
+ int err;
+
if (strcmp(t->name, name))
continue;
- if (!try_module_get(t->me)) {
- mutex_unlock(&xt[af].mutex);
- return NULL;
- }
-
+ if (!try_module_get(t->me))
+ goto out;
mutex_unlock(&xt[af].mutex);
- if (t->table_init(net) != 0) {
+ err = t->table_init(net);
+ if (err < 0) {
module_put(t->me);
- return NULL;
+ return ERR_PTR(err);
}
found = t;
@@ -1078,10 +1078,28 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
module_put(found->me);
out:
mutex_unlock(&xt[af].mutex);
- return NULL;
+ return ERR_PTR(-ENOENT);
}
EXPORT_SYMBOL_GPL(xt_find_table_lock);
+struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af,
+ const char *name)
+{
+ struct xt_table *t = xt_find_table_lock(net, af, name);
+
+#ifdef CONFIG_MODULES
+ if (IS_ERR(t)) {
+ int err = request_module("%stable_%s", xt_prefix[af], name);
+ if (err < 0)
+ return ERR_PTR(err);
+ t = xt_find_table_lock(net, af, name);
+ }
+#endif
+
+ return t;
+}
+EXPORT_SYMBOL_GPL(xt_request_find_table_lock);
+
void xt_table_unlock(struct xt_table *table)
{
mutex_unlock(&xt[table->af].mutex);
@@ -1349,7 +1367,6 @@ static int xt_table_open(struct inode *inode, struct file *file)
}
static const struct file_operations xt_table_ops = {
- .owner = THIS_MODULE,
.open = xt_table_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -1402,7 +1419,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
trav->curr = trav->curr->next;
if (trav->curr != trav->head)
break;
- /* fallthru, _stop will unlock */
+ /* fall through */
default:
return NULL;
}
@@ -1485,7 +1502,6 @@ static int xt_match_open(struct inode *inode, struct file *file)
}
static const struct file_operations xt_match_ops = {
- .owner = THIS_MODULE,
.open = xt_match_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -1538,7 +1554,6 @@ static int xt_target_open(struct inode *inode, struct file *file)
}
static const struct file_operations xt_target_ops = {
- .owner = THIS_MODULE,
.open = xt_target_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 9dae4d665965..99bb8e410f22 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -48,7 +48,6 @@ static u_int32_t tcpmss_reverse_mtu(struct net *net,
unsigned int family)
{
struct flowi fl;
- const struct nf_afinfo *ai;
struct rtable *rt = NULL;
u_int32_t mtu = ~0U;
@@ -62,10 +61,8 @@ static u_int32_t tcpmss_reverse_mtu(struct net *net,
memset(fl6, 0, sizeof(*fl6));
fl6->daddr = ipv6_hdr(skb)->saddr;
}
- ai = nf_get_afinfo(family);
- if (ai != NULL)
- ai->route(net, (struct dst_entry **)&rt, &fl, false);
+ nf_route(net, (struct dst_entry **)&rt, &fl, false, family);
if (rt != NULL) {
mtu = dst_mtu(&rt->dst);
dst_release(&rt->dst);
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index 3b2be2ae6987..911a7c0da504 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -36,7 +36,7 @@ MODULE_ALIAS("ip6t_addrtype");
static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
const struct in6_addr *addr, u16 mask)
{
- const struct nf_afinfo *afinfo;
+ const struct nf_ipv6_ops *v6ops;
struct flowi6 flow;
struct rt6_info *rt;
u32 ret = 0;
@@ -47,17 +47,14 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
if (dev)
flow.flowi6_oif = dev->ifindex;
- afinfo = nf_get_afinfo(NFPROTO_IPV6);
- if (afinfo != NULL) {
- const struct nf_ipv6_ops *v6ops;
-
+ v6ops = nf_get_ipv6_ops();
+ if (v6ops) {
if (dev && (mask & XT_ADDRTYPE_LOCAL)) {
- v6ops = nf_get_ipv6_ops();
- if (v6ops && v6ops->chk_addr(net, addr, dev, true))
+ if (v6ops->chk_addr(net, addr, dev, true))
ret = XT_ADDRTYPE_LOCAL;
}
- route_err = afinfo->route(net, (struct dst_entry **)&rt,
- flowi6_to_flowi(&flow), false);
+ route_err = v6ops->route(net, (struct dst_entry **)&rt,
+ flowi6_to_flowi(&flow), false);
} else {
route_err = 1;
}
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 1f7fbd3c7e5a..06b090d8e901 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -55,21 +55,11 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret)
static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
{
- mm_segment_t oldfs = get_fs();
- int retval, fd;
-
if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX)
return -EINVAL;
- set_fs(KERNEL_DS);
- fd = bpf_obj_get_user(path, 0);
- set_fs(oldfs);
- if (fd < 0)
- return fd;
-
- retval = __bpf_mt_check_fd(fd, ret);
- sys_close(fd);
- return retval;
+ *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER);
+ return PTR_ERR_OR_ZERO(*ret);
}
static int bpf_mt_check(const struct xt_mtchk_param *par)
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index a6214f235333..b1b17b9353e1 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -12,292 +12,30 @@
* GPL (C) 1999 Rusty Russell (rusty@rustcorp.com.au).
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/jhash.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
+
#include <linux/module.h>
-#include <linux/random.h>
#include <linux/skbuff.h>
-#include <linux/spinlock.h>
-#include <linux/netfilter/nf_conntrack_tcp.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_connlimit.h>
+
#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>
-
-#define CONNLIMIT_SLOTS 256U
-
-#ifdef CONFIG_LOCKDEP
-#define CONNLIMIT_LOCK_SLOTS 8U
-#else
-#define CONNLIMIT_LOCK_SLOTS 256U
-#endif
-
-#define CONNLIMIT_GC_MAX_NODES 8
-
-/* we will save the tuples of all connections we care about */
-struct xt_connlimit_conn {
- struct hlist_node node;
- struct nf_conntrack_tuple tuple;
-};
-
-struct xt_connlimit_rb {
- struct rb_node node;
- struct hlist_head hhead; /* connections/hosts in same subnet */
- union nf_inet_addr addr; /* search key */
-};
-
-static spinlock_t xt_connlimit_locks[CONNLIMIT_LOCK_SLOTS] __cacheline_aligned_in_smp;
-
-struct xt_connlimit_data {
- struct rb_root climit_root[CONNLIMIT_SLOTS];
-};
-
-static u_int32_t connlimit_rnd __read_mostly;
-static struct kmem_cache *connlimit_rb_cachep __read_mostly;
-static struct kmem_cache *connlimit_conn_cachep __read_mostly;
-
-static inline unsigned int connlimit_iphash(__be32 addr)
-{
- return jhash_1word((__force __u32)addr,
- connlimit_rnd) % CONNLIMIT_SLOTS;
-}
-
-static inline unsigned int
-connlimit_iphash6(const union nf_inet_addr *addr)
-{
- return jhash2((u32 *)addr->ip6, ARRAY_SIZE(addr->ip6),
- connlimit_rnd) % CONNLIMIT_SLOTS;
-}
-
-static inline bool already_closed(const struct nf_conn *conn)
-{
- if (nf_ct_protonum(conn) == IPPROTO_TCP)
- return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT ||
- conn->proto.tcp.state == TCP_CONNTRACK_CLOSE;
- else
- return 0;
-}
-
-static int
-same_source(const union nf_inet_addr *addr,
- const union nf_inet_addr *u3, u_int8_t family)
-{
- if (family == NFPROTO_IPV4)
- return ntohl(addr->ip) - ntohl(u3->ip);
-
- return memcmp(addr->ip6, u3->ip6, sizeof(addr->ip6));
-}
-
-static bool add_hlist(struct hlist_head *head,
- const struct nf_conntrack_tuple *tuple,
- const union nf_inet_addr *addr)
-{
- struct xt_connlimit_conn *conn;
-
- conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
- if (conn == NULL)
- return false;
- conn->tuple = *tuple;
- hlist_add_head(&conn->node, head);
- return true;
-}
-
-static unsigned int check_hlist(struct net *net,
- struct hlist_head *head,
- const struct nf_conntrack_tuple *tuple,
- const struct nf_conntrack_zone *zone,
- bool *addit)
-{
- const struct nf_conntrack_tuple_hash *found;
- struct xt_connlimit_conn *conn;
- struct hlist_node *n;
- struct nf_conn *found_ct;
- unsigned int length = 0;
-
- *addit = true;
-
- /* check the saved connections */
- hlist_for_each_entry_safe(conn, n, head, node) {
- found = nf_conntrack_find_get(net, zone, &conn->tuple);
- if (found == NULL) {
- hlist_del(&conn->node);
- kmem_cache_free(connlimit_conn_cachep, conn);
- continue;
- }
-
- found_ct = nf_ct_tuplehash_to_ctrack(found);
-
- if (nf_ct_tuple_equal(&conn->tuple, tuple)) {
- /*
- * Just to be sure we have it only once in the list.
- * We should not see tuples twice unless someone hooks
- * this into a table without "-p tcp --syn".
- */
- *addit = false;
- } else if (already_closed(found_ct)) {
- /*
- * we do not care about connections which are
- * closed already -> ditch it
- */
- nf_ct_put(found_ct);
- hlist_del(&conn->node);
- kmem_cache_free(connlimit_conn_cachep, conn);
- continue;
- }
-
- nf_ct_put(found_ct);
- length++;
- }
-
- return length;
-}
-
-static void tree_nodes_free(struct rb_root *root,
- struct xt_connlimit_rb *gc_nodes[],
- unsigned int gc_count)
-{
- struct xt_connlimit_rb *rbconn;
-
- while (gc_count) {
- rbconn = gc_nodes[--gc_count];
- rb_erase(&rbconn->node, root);
- kmem_cache_free(connlimit_rb_cachep, rbconn);
- }
-}
-
-static unsigned int
-count_tree(struct net *net, struct rb_root *root,
- const struct nf_conntrack_tuple *tuple,
- const union nf_inet_addr *addr,
- u8 family, const struct nf_conntrack_zone *zone)
-{
- struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
- struct rb_node **rbnode, *parent;
- struct xt_connlimit_rb *rbconn;
- struct xt_connlimit_conn *conn;
- unsigned int gc_count;
- bool no_gc = false;
-
- restart:
- gc_count = 0;
- parent = NULL;
- rbnode = &(root->rb_node);
- while (*rbnode) {
- int diff;
- bool addit;
-
- rbconn = rb_entry(*rbnode, struct xt_connlimit_rb, node);
-
- parent = *rbnode;
- diff = same_source(addr, &rbconn->addr, family);
- if (diff < 0) {
- rbnode = &((*rbnode)->rb_left);
- } else if (diff > 0) {
- rbnode = &((*rbnode)->rb_right);
- } else {
- /* same source network -> be counted! */
- unsigned int count;
- count = check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
-
- tree_nodes_free(root, gc_nodes, gc_count);
- if (!addit)
- return count;
-
- if (!add_hlist(&rbconn->hhead, tuple, addr))
- return 0; /* hotdrop */
-
- return count + 1;
- }
-
- if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
- continue;
-
- /* only used for GC on hhead, retval and 'addit' ignored */
- check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
- if (hlist_empty(&rbconn->hhead))
- gc_nodes[gc_count++] = rbconn;
- }
-
- if (gc_count) {
- no_gc = true;
- tree_nodes_free(root, gc_nodes, gc_count);
- /* tree_node_free before new allocation permits
- * allocator to re-use newly free'd object.
- *
- * This is a rare event; in most cases we will find
- * existing node to re-use. (or gc_count is 0).
- */
- goto restart;
- }
-
- /* no match, need to insert new node */
- rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC);
- if (rbconn == NULL)
- return 0;
-
- conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
- if (conn == NULL) {
- kmem_cache_free(connlimit_rb_cachep, rbconn);
- return 0;
- }
-
- conn->tuple = *tuple;
- rbconn->addr = *addr;
-
- INIT_HLIST_HEAD(&rbconn->hhead);
- hlist_add_head(&conn->node, &rbconn->hhead);
-
- rb_link_node(&rbconn->node, parent, rbnode);
- rb_insert_color(&rbconn->node, root);
- return 1;
-}
-
-static int count_them(struct net *net,
- struct xt_connlimit_data *data,
- const struct nf_conntrack_tuple *tuple,
- const union nf_inet_addr *addr,
- u_int8_t family,
- const struct nf_conntrack_zone *zone)
-{
- struct rb_root *root;
- int count;
- u32 hash;
-
- if (family == NFPROTO_IPV6)
- hash = connlimit_iphash6(addr);
- else
- hash = connlimit_iphash(addr->ip);
- root = &data->climit_root[hash];
-
- spin_lock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
-
- count = count_tree(net, root, tuple, addr, family, zone);
-
- spin_unlock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
-
- return count;
-}
+#include <net/netfilter/nf_conntrack_count.h>
static bool
connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
struct net *net = xt_net(par);
const struct xt_connlimit_info *info = par->matchinfo;
- union nf_inet_addr addr;
struct nf_conntrack_tuple tuple;
const struct nf_conntrack_tuple *tuple_ptr = &tuple;
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
enum ip_conntrack_info ctinfo;
const struct nf_conn *ct;
unsigned int connections;
+ u32 key[5];
ct = nf_ct_get(skb, &ctinfo);
if (ct != NULL) {
@@ -310,6 +48,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (xt_family(par) == NFPROTO_IPV6) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
+ union nf_inet_addr addr;
unsigned int i;
memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ?
@@ -317,22 +56,24 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
for (i = 0; i < ARRAY_SIZE(addr.ip6); ++i)
addr.ip6[i] &= info->mask.ip6[i];
+ memcpy(key, &addr, sizeof(addr.ip6));
+ key[4] = zone->id;
} else {
const struct iphdr *iph = ip_hdr(skb);
- addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ?
+ key[0] = (info->flags & XT_CONNLIMIT_DADDR) ?
iph->daddr : iph->saddr;
- addr.ip &= info->mask.ip;
+ key[0] &= info->mask.ip;
+ key[1] = zone->id;
}
- connections = count_them(net, info->data, tuple_ptr, &addr,
- xt_family(par), zone);
+ connections = nf_conncount_count(net, info->data, key,
+ xt_family(par), tuple_ptr, zone);
if (connections == 0)
/* kmalloc failed, drop it entirely */
goto hotdrop;
- return (connections > info->limit) ^
- !!(info->flags & XT_CONNLIMIT_INVERT);
+ return (connections > info->limit) ^ !!(info->flags & XT_CONNLIMIT_INVERT);
hotdrop:
par->hotdrop = true;
@@ -342,61 +83,27 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
static int connlimit_mt_check(const struct xt_mtchk_param *par)
{
struct xt_connlimit_info *info = par->matchinfo;
- unsigned int i;
- int ret;
+ unsigned int keylen;
- net_get_random_once(&connlimit_rnd, sizeof(connlimit_rnd));
-
- 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);
- return ret;
- }
+ keylen = sizeof(u32);
+ if (par->family == NFPROTO_IPV6)
+ keylen += sizeof(struct in6_addr);
+ else
+ keylen += sizeof(struct in_addr);
/* init private data */
- info->data = kmalloc(sizeof(struct xt_connlimit_data), GFP_KERNEL);
- if (info->data == NULL) {
- nf_ct_netns_put(par->net, par->family);
- return -ENOMEM;
- }
-
- for (i = 0; i < ARRAY_SIZE(info->data->climit_root); ++i)
- info->data->climit_root[i] = RB_ROOT;
+ info->data = nf_conncount_init(par->net, par->family, keylen);
+ if (IS_ERR(info->data))
+ return PTR_ERR(info->data);
return 0;
}
-static void destroy_tree(struct rb_root *r)
-{
- struct xt_connlimit_conn *conn;
- struct xt_connlimit_rb *rbconn;
- struct hlist_node *n;
- struct rb_node *node;
-
- while ((node = rb_first(r)) != NULL) {
- rbconn = rb_entry(node, struct xt_connlimit_rb, node);
-
- rb_erase(node, r);
-
- hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node)
- kmem_cache_free(connlimit_conn_cachep, conn);
-
- kmem_cache_free(connlimit_rb_cachep, rbconn);
- }
-}
-
static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
{
const struct xt_connlimit_info *info = par->matchinfo;
- unsigned int i;
-
- nf_ct_netns_put(par->net, par->family);
-
- for (i = 0; i < ARRAY_SIZE(info->data->climit_root); ++i)
- destroy_tree(&info->data->climit_root[i]);
- kfree(info->data);
+ nf_conncount_destroy(par->net, par->family, info->data);
}
static struct xt_match connlimit_mt_reg __read_mostly = {
@@ -413,40 +120,12 @@ static struct xt_match connlimit_mt_reg __read_mostly = {
static int __init connlimit_mt_init(void)
{
- int ret, i;
-
- BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS);
- BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0);
-
- for (i = 0; i < CONNLIMIT_LOCK_SLOTS; ++i)
- spin_lock_init(&xt_connlimit_locks[i]);
-
- connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn",
- sizeof(struct xt_connlimit_conn),
- 0, 0, NULL);
- if (!connlimit_conn_cachep)
- return -ENOMEM;
-
- connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb",
- sizeof(struct xt_connlimit_rb),
- 0, 0, NULL);
- if (!connlimit_rb_cachep) {
- kmem_cache_destroy(connlimit_conn_cachep);
- return -ENOMEM;
- }
- ret = xt_register_match(&connlimit_mt_reg);
- if (ret != 0) {
- kmem_cache_destroy(connlimit_conn_cachep);
- kmem_cache_destroy(connlimit_rb_cachep);
- }
- return ret;
+ return xt_register_match(&connlimit_mt_reg);
}
static void __exit connlimit_mt_exit(void)
{
xt_unregister_match(&connlimit_mt_reg);
- kmem_cache_destroy(connlimit_conn_cachep);
- kmem_cache_destroy(connlimit_rb_cachep);
}
module_init(connlimit_mt_init);
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 5da8746f7b88..ca6847403ca2 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -353,7 +353,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
static bool select_all(const struct xt_hashlimit_htable *ht,
const struct dsthash_ent *he)
{
- return 1;
+ return true;
}
static bool select_gc(const struct xt_hashlimit_htable *ht,
@@ -1266,7 +1266,6 @@ static int dl_proc_open(struct inode *inode, struct file *file)
}
static const struct file_operations dl_file_ops_v2 = {
- .owner = THIS_MODULE,
.open = dl_proc_open_v2,
.read = seq_read,
.llseek = seq_lseek,
@@ -1274,7 +1273,6 @@ static const struct file_operations dl_file_ops_v2 = {
};
static const struct file_operations dl_file_ops_v1 = {
- .owner = THIS_MODULE,
.open = dl_proc_open_v1,
.read = seq_read,
.llseek = seq_lseek,
@@ -1282,7 +1280,6 @@ static const struct file_operations dl_file_ops_v1 = {
};
static const struct file_operations dl_file_ops = {
- .owner = THIS_MODULE,
.open = dl_proc_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
index 000e70377f85..7ca64a50db04 100644
--- a/net/netfilter/xt_ipcomp.c
+++ b/net/netfilter/xt_ipcomp.c
@@ -58,7 +58,7 @@ static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par)
*/
pr_debug("Dropping evil IPComp tinygram.\n");
par->hotdrop = true;
- return 0;
+ return false;
}
return spi_match(compinfo->spis[0], compinfo->spis[1],
diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c
index 2b4ab189bba7..5639fb03bdd9 100644
--- a/net/netfilter/xt_policy.c
+++ b/net/netfilter/xt_policy.c
@@ -93,7 +93,8 @@ match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info,
if (dst->xfrm == NULL)
return -1;
- for (i = 0; dst && dst->xfrm; dst = dst->child, i++) {
+ for (i = 0; dst && dst->xfrm;
+ dst = ((struct xfrm_dst *)dst)->child, i++) {
pos = strict ? i : 0;
if (pos >= info->len)
return 0;
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 64285702afd5..16b6b11ee83f 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -39,13 +39,17 @@ match_set(ip_set_id_t index, const struct sk_buff *skb,
return inv;
}
-#define ADT_OPT(n, f, d, fs, cfs, t) \
-struct ip_set_adt_opt n = { \
- .family = f, \
- .dim = d, \
- .flags = fs, \
- .cmdflags = cfs, \
- .ext.timeout = t, \
+#define ADT_OPT(n, f, d, fs, cfs, t, p, b, po, bo) \
+struct ip_set_adt_opt n = { \
+ .family = f, \
+ .dim = d, \
+ .flags = fs, \
+ .cmdflags = cfs, \
+ .ext.timeout = t, \
+ .ext.packets = p, \
+ .ext.bytes = b, \
+ .ext.packets_op = po, \
+ .ext.bytes_op = bo, \
}
/* Revision 0 interface: backward compatible with netfilter/iptables */
@@ -56,7 +60,8 @@ set_match_v0(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_set_info_match_v0 *info = par->matchinfo;
ADT_OPT(opt, xt_family(par), info->match_set.u.compat.dim,
- info->match_set.u.compat.flags, 0, UINT_MAX);
+ info->match_set.u.compat.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
return match_set(info->match_set.index, skb, par, &opt,
info->match_set.u.compat.flags & IPSET_INV_MATCH);
@@ -119,7 +124,8 @@ set_match_v1(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_set_info_match_v1 *info = par->matchinfo;
ADT_OPT(opt, xt_family(par), info->match_set.dim,
- info->match_set.flags, 0, UINT_MAX);
+ info->match_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
if (opt.flags & IPSET_RETURN_NOMATCH)
opt.cmdflags |= IPSET_FLAG_RETURN_NOMATCH;
@@ -161,45 +167,21 @@ set_match_v1_destroy(const struct xt_mtdtor_param *par)
/* Revision 3 match */
static bool
-match_counter0(u64 counter, const struct ip_set_counter_match0 *info)
-{
- switch (info->op) {
- case IPSET_COUNTER_NONE:
- return true;
- case IPSET_COUNTER_EQ:
- return counter == info->value;
- case IPSET_COUNTER_NE:
- return counter != info->value;
- case IPSET_COUNTER_LT:
- return counter < info->value;
- case IPSET_COUNTER_GT:
- return counter > info->value;
- }
- return false;
-}
-
-static bool
set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_set_info_match_v3 *info = par->matchinfo;
- int ret;
ADT_OPT(opt, xt_family(par), info->match_set.dim,
- info->match_set.flags, info->flags, UINT_MAX);
+ info->match_set.flags, info->flags, UINT_MAX,
+ info->packets.value, info->bytes.value,
+ info->packets.op, info->bytes.op);
if (info->packets.op != IPSET_COUNTER_NONE ||
info->bytes.op != IPSET_COUNTER_NONE)
opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
- ret = match_set(info->match_set.index, skb, par, &opt,
- info->match_set.flags & IPSET_INV_MATCH);
-
- if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
- return ret;
-
- if (!match_counter0(opt.ext.packets, &info->packets))
- return false;
- return match_counter0(opt.ext.bytes, &info->bytes);
+ return match_set(info->match_set.index, skb, par, &opt,
+ info->match_set.flags & IPSET_INV_MATCH);
}
#define set_match_v3_checkentry set_match_v1_checkentry
@@ -208,45 +190,21 @@ set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
/* Revision 4 match */
static bool
-match_counter(u64 counter, const struct ip_set_counter_match *info)
-{
- switch (info->op) {
- case IPSET_COUNTER_NONE:
- return true;
- case IPSET_COUNTER_EQ:
- return counter == info->value;
- case IPSET_COUNTER_NE:
- return counter != info->value;
- case IPSET_COUNTER_LT:
- return counter < info->value;
- case IPSET_COUNTER_GT:
- return counter > info->value;
- }
- return false;
-}
-
-static bool
set_match_v4(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_set_info_match_v4 *info = par->matchinfo;
- int ret;
ADT_OPT(opt, xt_family(par), info->match_set.dim,
- info->match_set.flags, info->flags, UINT_MAX);
+ info->match_set.flags, info->flags, UINT_MAX,
+ info->packets.value, info->bytes.value,
+ info->packets.op, info->bytes.op);
if (info->packets.op != IPSET_COUNTER_NONE ||
info->bytes.op != IPSET_COUNTER_NONE)
opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
- ret = match_set(info->match_set.index, skb, par, &opt,
- info->match_set.flags & IPSET_INV_MATCH);
-
- if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
- return ret;
-
- if (!match_counter(opt.ext.packets, &info->packets))
- return false;
- return match_counter(opt.ext.bytes, &info->bytes);
+ return match_set(info->match_set.index, skb, par, &opt,
+ info->match_set.flags & IPSET_INV_MATCH);
}
#define set_match_v4_checkentry set_match_v1_checkentry
@@ -260,9 +218,11 @@ set_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_set_info_target_v0 *info = par->targinfo;
ADT_OPT(add_opt, xt_family(par), info->add_set.u.compat.dim,
- info->add_set.u.compat.flags, 0, UINT_MAX);
+ info->add_set.u.compat.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
ADT_OPT(del_opt, xt_family(par), info->del_set.u.compat.dim,
- info->del_set.u.compat.flags, 0, UINT_MAX);
+ info->del_set.u.compat.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
if (info->add_set.index != IPSET_INVALID_ID)
ip_set_add(info->add_set.index, skb, par, &add_opt);
@@ -333,9 +293,11 @@ set_target_v1(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_set_info_target_v1 *info = par->targinfo;
ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
- info->add_set.flags, 0, UINT_MAX);
+ info->add_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
- info->del_set.flags, 0, UINT_MAX);
+ info->del_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
if (info->add_set.index != IPSET_INVALID_ID)
ip_set_add(info->add_set.index, skb, par, &add_opt);
@@ -402,9 +364,11 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_set_info_target_v2 *info = par->targinfo;
ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
- info->add_set.flags, info->flags, info->timeout);
+ info->add_set.flags, info->flags, info->timeout,
+ 0, 0, 0, 0);
ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
- info->del_set.flags, 0, UINT_MAX);
+ info->del_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
/* Normalize to fit into jiffies */
if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
@@ -432,11 +396,14 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par)
int ret;
ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
- info->add_set.flags, info->flags, info->timeout);
+ info->add_set.flags, info->flags, info->timeout,
+ 0, 0, 0, 0);
ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
- info->del_set.flags, 0, UINT_MAX);
+ info->del_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
ADT_OPT(map_opt, xt_family(par), info->map_set.dim,
- info->map_set.flags, 0, UINT_MAX);
+ info->map_set.flags, 0, UINT_MAX,
+ 0, 0, 0, 0);
/* Normalize to fit into jiffies */
if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&