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/IPVS updates for net-next,
more specifically:

* Updates for ipset:

1) Coding style fix for ipset comment extension, from Jeremy Sowden.

2) De-inline many functions in ipset, from Jeremy Sowden.

3) Move ipset function definition from header to source file.

4) Move ip_set_put_flags() to source, export it as a symbol, remove
   inline.

5) Move range_to_mask() to the source file where this is used.

6) Move ip_set_get_ip_port() to the source file where this is used.

* IPVS selftests and netns improvements:

7) Two patches to speedup ipvs netns dismantle, from Haishuang Yan.

8) Three patches to add selftest script for ipvs, also from
   Haishuang Yan.

* Conntrack updates and new nf_hook_slow_list() function:

9) Document ct ecache extension, from Florian Westphal.

10) Skip ct extensions from ctnetlink dump, from Florian.

11) Free ct extension immediately, from Florian.

12) Skip access to ecache extension from nf_ct_deliver_cached_events()
    this is not correct as reported by Syzbot.

13) Add and use nf_hook_slow_list(), from Florian.

* Flowtable infrastructure updates:

14) Move priority to nf_flowtable definition.

15) Dynamic allocation of per-device hooks in flowtables.

16) Allow to include netdevice only once in flowtable definitions.

17) Rise maximum number of devices per flowtable.

* Netfilter hardware offload infrastructure updates:

18) Add nft_flow_block_chain() helper function.

19) Pass callback list to nft_setup_cb_call().

20) Add nft_flow_cls_offload_setup() helper function.

21) Remove rules for the unregistered device via netdevice event.

22) Support for multiple devices in a basechain definition at the
    ingress hook.

22) Add nft_chain_offload_cmd() helper function.

23) Add nft_flow_block_offload_init() helper function.

24) Rewind in case of failing to bind multiple devices to hook.

25) Typo in IPv6 tproxy module description, from Norman Rasmussen.
====================

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

9 files changed, 53 insertions, 232 deletions

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 77ebb61faf48..eb312e7ca36e 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -199,6 +199,8 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
 		 const struct nf_hook_entries *e, unsigned int i);
 
+void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state,
+		       const struct nf_hook_entries *e);
 /**
  *	nf_hook - call a netfilter hook
  *
@@ -311,17 +313,36 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
 	     struct list_head *head, struct net_device *in, struct net_device *out,
 	     int (*okfn)(struct net *, struct sock *, struct sk_buff *))
 {
-	struct sk_buff *skb, *next;
-	struct list_head sublist;
-
-	INIT_LIST_HEAD(&sublist);
-	list_for_each_entry_safe(skb, next, head, list) {
-		list_del(&skb->list);
-		if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1)
-			list_add_tail(&skb->list, &sublist);
+	struct nf_hook_entries *hook_head = NULL;
+
+#ifdef CONFIG_JUMP_LABEL
+	if (__builtin_constant_p(pf) &&
+	    __builtin_constant_p(hook) &&
+	    !static_key_false(&nf_hooks_needed[pf][hook]))
+		return;
+#endif
+
+	rcu_read_lock();
+	switch (pf) {
+	case NFPROTO_IPV4:
+		hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]);
+		break;
+	case NFPROTO_IPV6:
+		hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
-	/* Put passed packets back on main list */
-	list_splice(&sublist, head);
+
+	if (hook_head) {
+		struct nf_hook_state state;
+
+		nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn);
+
+		nf_hook_slow_list(head, &state, hook_head);
+	}
+	rcu_read_unlock();
 }
 
 /* Call setsockopt() */
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 9bc255a8461b..4d8b1eaf7708 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -269,34 +269,15 @@ ip_set_ext_destroy(struct ip_set *set, void *data)
 	/* Check that the extension is enabled for the set and
 	 * call it's destroy function for its extension part in data.
 	 */
-	if (SET_WITH_COMMENT(set))
-		ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(
-			set, ext_comment(data, set));
-}
+	if (SET_WITH_COMMENT(set)) {
+		struct ip_set_comment *c = ext_comment(data, set);
 
-static inline int
-ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
-{
-	u32 cadt_flags = 0;
-
-	if (SET_WITH_TIMEOUT(set))
-		if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
-					   htonl(set->timeout))))
-			return -EMSGSIZE;
-	if (SET_WITH_COUNTER(set))
-		cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
-	if (SET_WITH_COMMENT(set))
-		cadt_flags |= IPSET_FLAG_WITH_COMMENT;
-	if (SET_WITH_SKBINFO(set))
-		cadt_flags |= IPSET_FLAG_WITH_SKBINFO;
-	if (SET_WITH_FORCEADD(set))
-		cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
-
-	if (!cadt_flags)
-		return 0;
-	return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags));
+		ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(set, c);
+	}
 }
 
+int ip_set_put_flags(struct sk_buff *skb, struct ip_set *set);
+
 /* Netlink CB args */
 enum {
 	IPSET_CB_NET = 0,	/* net namespace */
@@ -506,144 +487,8 @@ ip_set_timeout_set(unsigned long *timeout, u32 value)
 	*timeout = t;
 }
 
-static inline u32
-ip_set_timeout_get(const unsigned long *timeout)
-{
-	u32 t;
-
-	if (*timeout == IPSET_ELEM_PERMANENT)
-		return 0;
-
-	t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
-	/* Zero value in userspace means no timeout */
-	return t == 0 ? 1 : t;
-}
-
-static inline char*
-ip_set_comment_uget(struct nlattr *tb)
-{
-	return nla_data(tb);
-}
-
-/* Called from uadd only, protected by the set spinlock.
- * The kadt functions don't use the comment extensions in any way.
- */
-static inline void
-ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
-		    const struct ip_set_ext *ext)
-{
-	struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1);
-	size_t len = ext->comment ? strlen(ext->comment) : 0;
-
-	if (unlikely(c)) {
-		set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
-		kfree_rcu(c, rcu);
-		rcu_assign_pointer(comment->c, NULL);
-	}
-	if (!len)
-		return;
-	if (unlikely(len > IPSET_MAX_COMMENT_SIZE))
-		len = IPSET_MAX_COMMENT_SIZE;
-	c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC);
-	if (unlikely(!c))
-		return;
-	strlcpy(c->str, ext->comment, len + 1);
-	set->ext_size += sizeof(*c) + strlen(c->str) + 1;
-	rcu_assign_pointer(comment->c, c);
-}
-
-/* Used only when dumping a set, protected by rcu_read_lock() */
-static inline int
-ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment)
-{
-	struct ip_set_comment_rcu *c = rcu_dereference(comment->c);
-
-	if (!c)
-		return 0;
-	return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str);
-}
-
-/* Called from uadd/udel, flush or the garbage collectors protected
- * by the set spinlock.
- * Called when the set is destroyed and when there can't be any user
- * of the set data anymore.
- */
-static inline void
-ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment)
-{
-	struct ip_set_comment_rcu *c;
-
-	c = rcu_dereference_protected(comment->c, 1);
-	if (unlikely(!c))
-		return;
-	set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
-	kfree_rcu(c, rcu);
-	rcu_assign_pointer(comment->c, NULL);
-}
-
-static inline void
-ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
-{
-	atomic64_add((long long)bytes, &(counter)->bytes);
-}
-
-static inline void
-ip_set_add_packets(u64 packets, struct ip_set_counter *counter)
-{
-	atomic64_add((long long)packets, &(counter)->packets);
-}
-
-static inline u64
-ip_set_get_bytes(const struct ip_set_counter *counter)
-{
-	return (u64)atomic64_read(&(counter)->bytes);
-}
-
-static inline u64
-ip_set_get_packets(const struct ip_set_counter *counter)
-{
-	return (u64)atomic64_read(&(counter)->packets);
-}
-
-static inline bool
-ip_set_match_counter(u64 counter, u64 match, u8 op)
-{
-	switch (op) {
-	case IPSET_COUNTER_NONE:
-		return true;
-	case IPSET_COUNTER_EQ:
-		return counter == match;
-	case IPSET_COUNTER_NE:
-		return counter != match;
-	case IPSET_COUNTER_LT:
-		return counter < match;
-	case IPSET_COUNTER_GT:
-		return counter > match;
-	}
-	return false;
-}
-
-static inline void
-ip_set_update_counter(struct ip_set_counter *counter,
-		      const struct ip_set_ext *ext, u32 flags)
-{
-	if (ext->packets != ULLONG_MAX &&
-	    !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
-		ip_set_add_bytes(ext->bytes, counter);
-		ip_set_add_packets(ext->packets, counter);
-	}
-}
-
-static inline bool
-ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter)
-{
-	return nla_put_net64(skb, IPSET_ATTR_BYTES,
-			     cpu_to_be64(ip_set_get_bytes(counter)),
-			     IPSET_ATTR_PAD) ||
-	       nla_put_net64(skb, IPSET_ATTR_PACKETS,
-			     cpu_to_be64(ip_set_get_packets(counter)),
-			     IPSET_ATTR_PAD);
-}
+void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
+			 const struct ip_set_ext *ext);
 
 static inline void
 ip_set_init_counter(struct ip_set_counter *counter,
@@ -656,31 +501,6 @@ ip_set_init_counter(struct ip_set_counter *counter,
 }
 
 static inline void
-ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
-		   const struct ip_set_ext *ext,
-		   struct ip_set_ext *mext, u32 flags)
-{
-	mext->skbinfo = *skbinfo;
-}
-
-static inline bool
-ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo)
-{
-	/* Send nonzero parameters only */
-	return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
-		nla_put_net64(skb, IPSET_ATTR_SKBMARK,
-			      cpu_to_be64((u64)skbinfo->skbmark << 32 |
-					  skbinfo->skbmarkmask),
-			      IPSET_ATTR_PAD)) ||
-	       (skbinfo->skbprio &&
-		nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
-			      cpu_to_be32(skbinfo->skbprio))) ||
-	       (skbinfo->skbqueue &&
-		nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
-			      cpu_to_be16(skbinfo->skbqueue)));
-}
-
-static inline void
 ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo,
 		    const struct ip_set_ext *ext)
 {
diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h
index 2dddbc6dcac7..fcc4d214a788 100644
--- a/include/linux/netfilter/ipset/ip_set_bitmap.h
+++ b/include/linux/netfilter/ipset/ip_set_bitmap.h
@@ -12,18 +12,4 @@ enum {
 	IPSET_ADD_START_STORED_TIMEOUT,
 };
 
-/* Common functions */
-
-static inline u32
-range_to_mask(u32 from, u32 to, u8 *bits)
-{
-	u32 mask = 0xFFFFFFFE;
-
-	*bits = 32;
-	while (--(*bits) > 0 && mask && (to & mask) != from)
-		mask <<= 1;
-
-	return mask;
-}
-
 #endif /* __IP_SET_BITMAP_H */
diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h
index d74cd112b88a..1ecaabd9a048 100644
--- a/include/linux/netfilter/ipset/ip_set_getport.h
+++ b/include/linux/netfilter/ipset/ip_set_getport.h
@@ -20,9 +20,6 @@ static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 }
 #endif
 
-extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src,
-				__be16 *port);
-
 static inline bool ip_set_proto_with_ports(u8 proto)
 {
 	switch (proto) {
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 3759167f91f5..93e7a252993d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1324,7 +1324,7 @@ void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs);
 void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs);
 void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs);
 void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs);
-void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs);
+void ip_vs_service_nets_cleanup(struct list_head *net_list);
 
 /* IPVS application functions
  * (from ip_vs_app.c)
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 112a6f40dfaf..5ae5295aa46d 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -43,7 +43,6 @@ enum nf_ct_ext_id {
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
-	struct rcu_head rcu;
 	u8 offset[NF_CT_EXT_NUM];
 	u8 len;
 	char data[0];
@@ -72,15 +71,6 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
 /* Destroy all relationships */
 void nf_ct_ext_destroy(struct nf_conn *ct);
 
-/* Free operation. If you want to free a object referred from private area,
- * please implement __nf_ct_ext_free() and call it.
- */
-static inline void nf_ct_ext_free(struct nf_conn *ct)
-{
-	if (ct->ext)
-		kfree_rcu(ct->ext, rcu);
-}
-
 /* Add this type, returns pointer to data or NULL. */
 void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
 
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index b37a7d608134..158514281a75 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -24,6 +24,7 @@ struct nf_flowtable_type {
 struct nf_flowtable {
 	struct list_head		list;
 	struct rhashtable		rhashtable;
+	int				priority;
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;
 };
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 001d294edf57..5bf569e1173b 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -963,25 +963,31 @@ struct nft_stats {
 	struct u64_stats_sync	syncp;
 };
 
+struct nft_hook {
+	struct list_head	list;
+	struct nf_hook_ops	ops;
+	struct rcu_head		rcu;
+};
+
 /**
  *	struct nft_base_chain - nf_tables base chain
  *
  *	@ops: netfilter hook ops
+ *	@hook_list: list of netfilter hooks (for NFPROTO_NETDEV family)
  *	@type: chain type
  *	@policy: default policy
  *	@stats: per-cpu chain stats
  *	@chain: the chain
- *	@dev_name: device name that this base chain is attached to (if any)
  *	@flow_block: flow block (for hardware offload)
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
+	struct list_head		hook_list;
 	const struct nft_chain_type	*type;
 	u8				policy;
 	u8				flags;
 	struct nft_stats __percpu	*stats;
 	struct nft_chain		chain;
-	char 				dev_name[IFNAMSIZ];
 	struct flow_block		flow_block;
 };
 
@@ -1146,7 +1152,7 @@ struct nft_object_ops {
 int nft_register_obj(struct nft_object_type *obj_type);
 void nft_unregister_obj(struct nft_object_type *obj_type);
 
-#define NFT_FLOWTABLE_DEVICE_MAX	8
+#define NFT_NETDEVICE_MAX	256
 
 /**
  *	struct nft_flowtable - nf_tables flow table
@@ -1155,7 +1161,6 @@ void nft_unregister_obj(struct nft_object_type *obj_type);
  * 	@table: the table the flow table is contained in
  *	@name: name of this flow table
  *	@hooknum: hook number
- *	@priority: hook priority
  *	@ops_len: number of hooks in array
  *	@genmask: generation mask
  *	@use: number of references to this flow table
@@ -1169,13 +1174,12 @@ struct nft_flowtable {
 	struct nft_table		*table;
 	char				*name;
 	int				hooknum;
-	int				priority;
 	int				ops_len;
 	u32				genmask:2,
 					use:30;
 	u64				handle;
 	/* runtime data below here */
-	struct nf_hook_ops		*ops ____cacheline_aligned;
+	struct list_head		hook_list ____cacheline_aligned;
 	struct nf_flowtable		data;
 };
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ed8881ad18ed..81fed16fe2b2 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -144,12 +144,14 @@ enum nft_list_attributes {
  * @NFTA_HOOK_HOOKNUM: netfilter hook number (NLA_U32)
  * @NFTA_HOOK_PRIORITY: netfilter hook priority (NLA_U32)
  * @NFTA_HOOK_DEV: netdevice name (NLA_STRING)
+ * @NFTA_HOOK_DEVS: list of netdevices (NLA_NESTED)
  */
 enum nft_hook_attributes {
 	NFTA_HOOK_UNSPEC,
 	NFTA_HOOK_HOOKNUM,
 	NFTA_HOOK_PRIORITY,
 	NFTA_HOOK_DEV,
+	NFTA_HOOK_DEVS,
 	__NFTA_HOOK_MAX
 };
 #define NFTA_HOOK_MAX		(__NFTA_HOOK_MAX - 1)