Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter updates for your net-next tree,
they are:

1) Remove useless debug message when deleting IPVS service, from
   Yannick Brosseau.

2) Get rid of compilation warning when CONFIG_PROC_FS is unset in
   several spots of the IPVS code, from Arnd Bergmann.

3) Add prandom_u32 support to nft_meta, from Florian Westphal.

4) Remove unused variable in xt_osf, from Sudip Mukherjee.

5) Don't calculate IP checksum twice from netfilter ipv4 defrag hook
   since fixing af_packet defragmentation issues, from Joe Stringer.

6) On-demand hook registration for iptables from netns. Instead of
   registering the hooks for every available netns whenever we need
   one of the support tables, we register this on the specific netns
   that needs it, patchset from Florian Westphal.

7) Add missing port range selection to nf_tables masquerading support.

BTW, just for the record, there is a typo in the description of
5f6c253 ("netfilter: bridge: register hooks only when bridge
interface is added") that refers to the cluster match as deprecated, but
it is actually the CLUSTERIP target (which registers hooks
inconditionally) the one that is scheduled for removal.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter.h

@@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
 
 #ifdef HAVE_JUMP_LABEL
 extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
-static inline bool nf_hook_list_active(struct list_head *hook_list,
-				       u_int8_t pf, unsigned int hook)
-{
-	if (__builtin_constant_p(pf) &&
-	    __builtin_constant_p(hook))
-		return static_key_false(&nf_hooks_needed[pf][hook]);
-
-	return !list_empty(hook_list);
-}
-#else
-static inline bool nf_hook_list_active(struct list_head *hook_list,
-				       u_int8_t pf, unsigned int hook)
-{
-	return !list_empty(hook_list);
-}
 #endif
 
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
@@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
 				 int (*okfn)(struct net *, struct sock *, struct sk_buff *),
 				 int thresh)
 {
-	struct list_head *hook_list = &net->nf.hooks[pf][hook];
+	struct list_head *hook_list;
+
+#ifdef HAVE_JUMP_LABEL
+	if (__builtin_constant_p(pf) &&
+	    __builtin_constant_p(hook) &&
+	    !static_key_false(&nf_hooks_needed[pf][hook]))
+		return 1;
+#endif
+
+	hook_list = &net->nf.hooks[pf][hook];
 
-	if (nf_hook_list_active(hook_list, pf, hook)) {
+	if (!list_empty(hook_list)) {
 		struct nf_hook_state state;
 
 		nf_hook_state_init(&state, hook_list, hook, thresh,

include/linux/netfilter/x_tables.h

@@ -200,6 +200,9 @@ struct xt_table {
 	u_int8_t af;		/* address/protocol family */
 	int priority;		/* hook order */
 
+	/* called when table is needed in the given netns */
+	int (*table_init)(struct net *net);
+
 	/* A unique name... */
 	const char name[XT_TABLE_MAXNAMELEN];
 };
@@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 	return cnt;
 }
 
-struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
-void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
+struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>

include/linux/netfilter_arp/arp_tables.h

@@ -48,10 +48,11 @@ struct arpt_error {
 }
 
 extern void *arpt_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *arpt_register_table(struct net *net,
-					    const struct xt_table *table,
-					    const struct arpt_replace *repl);
-extern void arpt_unregister_table(struct xt_table *table);
+int arpt_register_table(struct net *net, const struct xt_table *table,
+			const struct arpt_replace *repl,
+			const struct nf_hook_ops *ops, struct xt_table **res);
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops);
 extern unsigned int arpt_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);

include/linux/netfilter_ipv4/ip_tables.h

@@ -24,10 +24,11 @@
 
 extern void ipt_init(void) __init;
 
-extern struct xt_table *ipt_register_table(struct net *net,
-					   const struct xt_table *table,
-					   const struct ipt_replace *repl);
-extern void ipt_unregister_table(struct net *net, struct xt_table *table);
+int ipt_register_table(struct net *net, const struct xt_table *table,
+		       const struct ipt_replace *repl,
+		       const struct nf_hook_ops *ops, struct xt_table **res);
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+			  const struct nf_hook_ops *ops);
 
 /* Standard entry. */
 struct ipt_standard {

include/linux/netfilter_ipv6/ip6_tables.h

@@ -25,10 +25,11 @@
 extern void ip6t_init(void) __init;
 
 extern void *ip6t_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *ip6t_register_table(struct net *net,
-					    const struct xt_table *table,
-					    const struct ip6t_replace *repl);
-extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
+int ip6t_register_table(struct net *net, const struct xt_table *table,
+			const struct ip6t_replace *repl,
+			const struct nf_hook_ops *ops, struct xt_table **res);
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops);
 extern unsigned int ip6t_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);

include/net/netfilter/nft_masq.h

@@ -2,7 +2,9 @@
 #define _NFT_MASQ_H_
 
 struct nft_masq {
-	u32	flags;
+	u32			flags;
+	enum nft_registers      sreg_proto_min:8;
+	enum nft_registers      sreg_proto_max:8;
 };
 
 extern const struct nla_policy nft_masq_policy[];

include/uapi/linux/netfilter/nf_tables.h

@@ -681,6 +681,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_IIFGROUP: packet input interface group
  * @NFT_META_OIFGROUP: packet output interface group
  * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid)
+ * @NFT_META_PRANDOM: a 32bit pseudo-random number
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -707,6 +708,7 @@ enum nft_meta_keys {
 	NFT_META_IIFGROUP,
 	NFT_META_OIFGROUP,
 	NFT_META_CGROUP,
+	NFT_META_PRANDOM,
 };
 
 /**
@@ -949,10 +951,14 @@ enum nft_nat_attributes {
  * enum nft_masq_attributes - nf_tables masquerade expression attributes
  *
  * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ * @NFTA_MASQ_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_MASQ_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
  */
 enum nft_masq_attributes {
 	NFTA_MASQ_UNSPEC,
 	NFTA_MASQ_FLAGS,
+	NFTA_MASQ_REG_PROTO_MIN,
+	NFTA_MASQ_REG_PROTO_MAX,
 	__NFTA_MASQ_MAX
 };
 #define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)

lib/random32.c

@@ -255,6 +255,7 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 		prandom_warmup(state);
 	}
 }
+EXPORT_SYMBOL(prandom_seed_full_state);
 
 /*
  *	Generate better values after random number generator

net/bridge/br_netfilter_hooks.c

@@ -37,13 +37,20 @@
 #include <net/addrconf.h>
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
+#include <net/netns/generic.h>
 
 #include <asm/uaccess.h>
 #include "br_private.h"
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 #endif
 
+static int brnf_net_id __read_mostly;
+
+struct brnf_net {
+	bool enabled;
+};
+
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
@@ -938,6 +945,53 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 	},
 };
 
+static int brnf_device_event(struct notifier_block *unused, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct brnf_net *brnet;
+	struct net *net;
+	int ret;
+
+	if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE))
+		return NOTIFY_DONE;
+
+	ASSERT_RTNL();
+
+	net = dev_net(dev);
+	brnet = net_generic(net, brnf_net_id);
+	if (brnet->enabled)
+		return NOTIFY_OK;
+
+	ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	if (ret)
+		return NOTIFY_BAD;
+
+	brnet->enabled = true;
+	return NOTIFY_OK;
+}
+
+static void __net_exit brnf_exit_net(struct net *net)
+{
+	struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+	if (!brnet->enabled)
+		return;
+
+	nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	brnet->enabled = false;
+}
+
+static struct pernet_operations brnf_net_ops __read_mostly = {
+	.exit = brnf_exit_net,
+	.id   = &brnf_net_id,
+	.size = sizeof(struct brnf_net),
+};
+
+static struct notifier_block brnf_notifier __read_mostly = {
+	.notifier_call = brnf_device_event,
+};
+
 #ifdef CONFIG_SYSCTL
 static
 int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
@@ -1003,16 +1057,23 @@ static int __init br_netfilter_init(void)
 {
 	int ret;
 
-	ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	ret = register_pernet_subsys(&brnf_net_ops);
 	if (ret < 0)
 		return ret;
 
+	ret = register_netdevice_notifier(&brnf_notifier);
+	if (ret < 0) {
+		unregister_pernet_subsys(&brnf_net_ops);
+		return ret;
+	}
+
 #ifdef CONFIG_SYSCTL
 	brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table);
 	if (brnf_sysctl_header == NULL) {
 		printk(KERN_WARNING
 		       "br_netfilter: can't register to sysctl.\n");
-		nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+		unregister_netdevice_notifier(&brnf_notifier);
+		unregister_pernet_subsys(&brnf_net_ops);
 		return -ENOMEM;
 	}
 #endif
@@ -1024,7 +1085,8 @@ static int __init br_netfilter_init(void)
 static void __exit br_netfilter_fini(void)
 {
 	RCU_INIT_POINTER(nf_br_ops, NULL);
-	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	unregister_netdevice_notifier(&brnf_notifier);
+	unregister_pernet_subsys(&brnf_net_ops);
 #ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(brnf_sysctl_header);
 #endif

net/ipv4/netfilter/arp_tables.c

@@ -1780,9 +1780,29 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 	return ret;
 }
 
-struct xt_table *arpt_register_table(struct net *net,
-				     const struct xt_table *table,
-				     const struct arpt_replace *repl)
+static void __arpt_unregister_table(struct xt_table *table)
+{
+	struct xt_table_info *private;
+	void *loc_cpu_entry;
+	struct module *table_owner = table->me;
+	struct arpt_entry *iter;
+
+	private = xt_unregister_table(table);
+
+	/* Decrease module usage counts and free resources */
+	loc_cpu_entry = private->entries;
+	xt_entry_foreach(iter, loc_cpu_entry, private->size)
+		cleanup_entry(iter);
+	if (private->number > private->initial_entries)
+		module_put(table_owner);
+	xt_free_table_info(private);
+}
+
+int arpt_register_table(struct net *net,
+			const struct xt_table *table,
+			const struct arpt_replace *repl,
+			const struct nf_hook_ops *ops,
+			struct xt_table **res)
 {
 	int ret;
 	struct xt_table_info *newinfo;
@@ -1791,10 +1811,8 @@ struct xt_table *arpt_register_table(struct net *net,
 	struct xt_table *new_table;
 
 	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!newinfo)
+		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
 	memcpy(loc_cpu_entry, repl->entries, repl->size);
@@ -1809,30 +1827,28 @@ struct xt_table *arpt_register_table(struct net *net,
 		ret = PTR_ERR(new_table);
 		goto out_free;
 	}
-	return new_table;
+
+	/* set res now, will see skbs right after nf_register_net_hooks */
+	WRITE_ONCE(*res, new_table);
+
+	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+	if (ret != 0) {
+		__arpt_unregister_table(new_table);
+		*res = NULL;
+	}
+
+	return ret;
 
 out_free:
 	xt_free_table_info(newinfo);
-out:
-	return ERR_PTR(ret);
+	return ret;
 }
 
-void arpt_unregister_table(struct xt_table *table)
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops)
 {
-	struct xt_table_info *private;
-	void *loc_cpu_entry;
-	struct module *table_owner = table->me;
-	struct arpt_entry *iter;
-
-	private = xt_unregister_table(table);
-
-	/* Decrease module usage counts and free resources */
-	loc_cpu_entry = private->entries;
-	xt_entry_foreach(iter, loc_cpu_entry, private->size)
-		cleanup_entry(iter);
-	if (private->number > private->initial_entries)
-		module_put(table_owner);
-	xt_free_table_info(private);
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	__arpt_unregister_table(table);
 }
 
 /* The built-in targets: standard (NULL) and error. */