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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next tree.
Basically, nf_tables updates to add the set extension infrastructure and finish
the transaction for sets from Patrick McHardy. More specifically, they are:

1) Move netns to basechain and use recently added possible_net_t, from
   Patrick McHardy.

2) Use LOGLEVEL_<FOO> from nf_log infrastructure, from Joe Perches.

3) Restore nf_log_trace that was accidentally removed during conflict
   resolution.

4) nft_queue does not depend on NETFILTER_XTABLES, starting from here
   all patches from Patrick McHardy.

5) Use raw_smp_processor_id() in nft_meta.

Then, several patches to prepare ground for the new set extension
infrastructure:

6) Pass object length to the hash callback in rhashtable as needed by
   the new set extension infrastructure.

7) Cleanup patch to restore struct nft_hash as wrapper for struct
   rhashtable

8) Another small source code readability cleanup for nft_hash.

9) Convert nft_hash to rhashtable callbacks.

And finally...

10) Add the new set extension infrastructure.

11) Convert the nft_hash and nft_rbtree sets to use it.

12) Batch set element release to avoid several RCU grace period in a row
    and add new function nft_set_elem_destroy() to consolidate set element
    release.

13) Return the set extension data area from nft_lookup.

14) Refactor existing transaction code to add some helper functions
    and document it.

15) Complete the set transaction support, using similar approach to what we
    already use, to activate/deactivate elements in an atomic fashion.
====================

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

include/linux/rhashtable.h

@@ -88,7 +88,7 @@ struct rhashtable_compare_arg {
 };
 
 typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
-typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 seed);
+typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
 typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
 			       const void *obj);
 
@@ -242,7 +242,9 @@ static inline unsigned int rht_head_hashfn(
 	const char *ptr = rht_obj(ht, he);
 
 	return likely(params.obj_hashfn) ?
-	       rht_bucket_index(tbl, params.obj_hashfn(ptr, tbl->hash_rnd)) :
+	       rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?:
+							    ht->p.key_len,
+						       tbl->hash_rnd)) :
 	       rht_key_hashfn(ht, tbl, ptr + params.key_offset, params);
 }
 

include/net/netfilter/nf_tables.h

@@ -138,19 +138,12 @@ struct nft_userdata {
 /**
  *	struct nft_set_elem - generic representation of set elements
  *
- *	@cookie: implementation specific element cookie
  *	@key: element key
- *	@data: element data (maps only)
+ *	@priv: element private data and extensions
- *	@flags: element flags (end of interval)
- *
- *	The cookie can be used to store a handle to the element for subsequent
- *	removal.
  */
 struct nft_set_elem {
-	void			*cookie;
 	struct nft_data		key;
-	struct nft_data		data;
+	void			*priv;
-	u32			flags;
 };
 
 struct nft_set;
@@ -202,11 +195,15 @@ struct nft_set_estimate {
 	enum nft_set_class	class;
 };
 
+struct nft_set_ext;
+
 /**
  *	struct nft_set_ops - nf_tables set operations
  *
  *	@lookup: look up an element within the set
  *	@insert: insert new element into set
+ *	@activate: activate new element in the next generation
+ *	@deactivate: deactivate element in the next generation
  *	@remove: remove element from set
  *	@walk: iterate over all set elemeennts
  *	@privsize: function to return size of set private data
@@ -214,16 +211,19 @@ struct nft_set_estimate {
  *	@destroy: destroy private data of set instance
  *	@list: nf_tables_set_ops list node
  *	@owner: module reference
+ *	@elemsize: element private size
  *	@features: features supported by the implementation
  */
 struct nft_set_ops {
 	bool				(*lookup)(const struct nft_set *set,
 						  const struct nft_data *key,
-						  struct nft_data *data);
+						  const struct nft_set_ext **ext);
-	int				(*get)(const struct nft_set *set,
-					       struct nft_set_elem *elem);
 	int				(*insert)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
+	void				(*activate)(const struct nft_set *set,
+						    const struct nft_set_elem *elem);
+	void *				(*deactivate)(const struct nft_set *set,
+						      const struct nft_set_elem *elem);
 	void				(*remove)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
 	void				(*walk)(const struct nft_ctx *ctx,
@@ -241,6 +241,7 @@ struct nft_set_ops {
 
 	struct list_head		list;
 	struct module			*owner;
+	unsigned int			elemsize;
 	u32				features;
 };
 
@@ -259,6 +260,7 @@ void nft_unregister_set(struct nft_set_ops *ops);
  * 	@nelems: number of elements
  *	@policy: set parameterization (see enum nft_set_policies)
  * 	@ops: set ops
+ * 	@pnet: network namespace
  * 	@flags: set flags
  * 	@klen: key length
  * 	@dlen: data length
@@ -275,6 +277,7 @@ struct nft_set {
 	u16				policy;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
+	possible_net_t			pnet;
 	u16				flags;
 	u8				klen;
 	u8				dlen;
@@ -311,6 +314,121 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_binding *binding);
 
+/**
+ *	enum nft_set_extensions - set extension type IDs
+ *
+ *	@NFT_SET_EXT_KEY: element key
+ *	@NFT_SET_EXT_DATA: mapping data
+ *	@NFT_SET_EXT_FLAGS: element flags
+ *	@NFT_SET_EXT_NUM: number of extension types
+ */
+enum nft_set_extensions {
+	NFT_SET_EXT_KEY,
+	NFT_SET_EXT_DATA,
+	NFT_SET_EXT_FLAGS,
+	NFT_SET_EXT_NUM
+};
+
+/**
+ *	struct nft_set_ext_type - set extension type
+ *
+ * 	@len: fixed part length of the extension
+ * 	@align: alignment requirements of the extension
+ */
+struct nft_set_ext_type {
+	u8	len;
+	u8	align;
+};
+
+extern const struct nft_set_ext_type nft_set_ext_types[];
+
+/**
+ *	struct nft_set_ext_tmpl - set extension template
+ *
+ *	@len: length of extension area
+ *	@offset: offsets of individual extension types
+ */
+struct nft_set_ext_tmpl {
+	u16	len;
+	u8	offset[NFT_SET_EXT_NUM];
+};
+
+/**
+ *	struct nft_set_ext - set extensions
+ *
+ *	@genmask: generation mask
+ *	@offset: offsets of individual extension types
+ *	@data: beginning of extension data
+ */
+struct nft_set_ext {
+	u8	genmask;
+	u8	offset[NFT_SET_EXT_NUM];
+	char	data[0];
+};
+
+static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
+{
+	memset(tmpl, 0, sizeof(*tmpl));
+	tmpl->len = sizeof(struct nft_set_ext);
+}
+
+static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id,
+					  unsigned int len)
+{
+	tmpl->len	 = ALIGN(tmpl->len, nft_set_ext_types[id].align);
+	BUG_ON(tmpl->len > U8_MAX);
+	tmpl->offset[id] = tmpl->len;
+	tmpl->len	+= nft_set_ext_types[id].len + len;
+}
+
+static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id)
+{
+	nft_set_ext_add_length(tmpl, id, 0);
+}
+
+static inline void nft_set_ext_init(struct nft_set_ext *ext,
+				    const struct nft_set_ext_tmpl *tmpl)
+{
+	memcpy(ext->offset, tmpl->offset, sizeof(ext->offset));
+}
+
+static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
+{
+	return !!ext->offset[id];
+}
+
+static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
+{
+	return ext && __nft_set_ext_exists(ext, id);
+}
+
+static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id)
+{
+	return (void *)ext + ext->offset[id];
+}
+
+static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_KEY);
+}
+
+static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_DATA);
+}
+
+static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
+}
+
+static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
+						   void *elem)
+{
+	return elem + set->ops->elemsize;
+}
+
+void nft_set_elem_destroy(const struct nft_set *set, void *elem);
 
 /**
  *	struct nft_expr_type - nf_tables expression type
@@ -449,7 +567,6 @@ enum nft_chain_flags {
  *
  *	@rules: list of rules in the chain
  *	@list: used internally
- *	@net: net namespace that this chain belongs to
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
@@ -460,7 +577,6 @@ enum nft_chain_flags {
 struct nft_chain {
 	struct list_head		rules;
 	struct list_head		list;
-	struct net			*net;
 	struct nft_table		*table;
 	u64				handle;
 	u32				use;
@@ -512,6 +628,7 @@ struct nft_stats {
  *	struct nft_base_chain - nf_tables base chain
  *
  *	@ops: netfilter hook ops
+ *	@pnet: net namespace that this chain belongs to
  *	@type: chain type
  *	@policy: default policy
  *	@stats: per-cpu chain stats
@@ -519,6 +636,7 @@ struct nft_stats {
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops[NFT_HOOK_OPS_MAX];
+	possible_net_t			pnet;
 	const struct nf_chain_type	*type;
 	u8				policy;
 	struct nft_stats __percpu	*stats;
@@ -605,6 +723,50 @@ void nft_unregister_expr(struct nft_expr_type *);
 #define MODULE_ALIAS_NFT_SET() \
 	MODULE_ALIAS("nft-set")
 
+/*
+ * The gencursor defines two generations, the currently active and the
+ * next one. Objects contain a bitmask of 2 bits specifying the generations
+ * they're active in. A set bit means they're inactive in the generation
+ * represented by that bit.
+ *
+ * New objects start out as inactive in the current and active in the
+ * next generation. When committing the ruleset the bitmask is cleared,
+ * meaning they're active in all generations. When removing an object,
+ * it is set inactive in the next generation. After committing the ruleset,
+ * the objects are removed.
+ */
+static inline unsigned int nft_gencursor_next(const struct net *net)
+{
+	return net->nft.gencursor + 1 == 1 ? 1 : 0;
+}
+
+static inline u8 nft_genmask_next(const struct net *net)
+{
+	return 1 << nft_gencursor_next(net);
+}
+
+static inline u8 nft_genmask_cur(const struct net *net)
+{
+	/* Use ACCESS_ONCE() to prevent refetching the value for atomicity */
+	return 1 << ACCESS_ONCE(net->nft.gencursor);
+}
+
+/*
+ * Set element transaction helpers
+ */
+
+static inline bool nft_set_elem_active(const struct nft_set_ext *ext,
+				       u8 genmask)
+{
+	return !(ext->genmask & genmask);
+}
+
+static inline void nft_set_elem_change_active(const struct nft_set *set,
+					      struct nft_set_ext *ext)
+{
+	ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet));
+}
+
 /**
  *	struct nft_trans - nf_tables object update in transaction
  *

lib/rhashtable.c

@@ -691,7 +691,7 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
  *	struct rhash_head	node;
  * };
  *
- * u32 my_hash_fn(const void *data, u32 seed)
+ * u32 my_hash_fn(const void *data, u32 len, u32 seed)
  * {
  *	struct test_obj *obj = data;
  *

net/ipv4/netfilter/nf_log_arp.c

@@ -10,8 +10,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},

net/ipv4/netfilter/nf_log_ipv4.c

@@ -5,8 +5,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -26,7 +28,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},

net/ipv6/netfilter/ip6_tables.c

@@ -9,7 +9,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
 #include <linux/capability.h>
 #include <linux/in.h>
 #include <linux/skbuff.h>
@@ -234,7 +237,7 @@ static struct nf_loginfo trace_loginfo = {
 	.type = NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level = 4,
+			.level = LOGLEVEL_WARNING,
 			.logflags = NF_LOG_MASK,
 		},
 	},

net/ipv6/netfilter/nf_log_ipv6.c

@@ -5,8 +5,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
@@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = {
 	.type	= NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level	  = 5,
+			.level	  = LOGLEVEL_NOTICE,
 			.logflags = NF_LOG_MASK,
 		},
 	},

net/netfilter/Kconfig

@@ -522,7 +522,6 @@ config NFT_NAT
 	  typical Network Address Translation (NAT) packet transformations.
 
 config NFT_QUEUE
-	depends on NETFILTER_XTABLES
 	depends on NETFILTER_NETLINK_QUEUE
 	tristate "Netfilter nf_tables queue module"
 	help

net/netfilter/nf_tables_api.c

@@ -198,36 +198,31 @@ static int nft_delchain(struct nft_ctx *ctx)
 static inline bool
 nft_rule_is_active(struct net *net, const struct nft_rule *rule)
 {
-	return (rule->genmask & (1 << net->nft.gencursor)) == 0;
+	return (rule->genmask & nft_genmask_cur(net)) == 0;
-}
-
-static inline int gencursor_next(struct net *net)
-{
-	return net->nft.gencursor+1 == 1 ? 1 : 0;
 }
 
 static inline int
 nft_rule_is_active_next(struct net *net, const struct nft_rule *rule)
 {
-	return (rule->genmask & (1 << gencursor_next(net))) == 0;
+	return (rule->genmask & nft_genmask_next(net)) == 0;
 }
 
 static inline void
 nft_rule_activate_next(struct net *net, struct nft_rule *rule)
 {
 	/* Now inactive, will be active in the future */
-	rule->genmask = (1 << net->nft.gencursor);
+	rule->genmask = nft_genmask_cur(net);
 }
 
 static inline void
 nft_rule_deactivate_next(struct net *net, struct nft_rule *rule)
 {
-	rule->genmask = (1 << gencursor_next(net));
+	rule->genmask = nft_genmask_next(net);
 }
 
 static inline void nft_rule_clear(struct net *net, struct nft_rule *rule)
 {
-	rule->genmask &= ~(1 << gencursor_next(net));
+	rule->genmask &= ~nft_genmask_next(net);
 }
 
 static int
@@ -1354,6 +1349,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			rcu_assign_pointer(basechain->stats, stats);
 		}
 
+		write_pnet(&basechain->pnet, net);
 		basechain->type = type;
 		chain = &basechain->chain;
 
@@ -1381,7 +1377,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
-	chain->net = net;
 	chain->table = table;
 	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
@@ -2695,6 +2690,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 		goto err2;
 
 	INIT_LIST_HEAD(&set->bindings);
+	write_pnet(&set->pnet, net);
 	set->ops   = ops;
 	set->ktype = ktype;
 	set->klen  = desc.klen;
@@ -2771,10 +2767,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	enum nft_registers dreg;
 
 	dreg = nft_type_to_reg(set->dtype);
-	return nft_validate_data_load(ctx, dreg, &elem->data,
+	return nft_validate_data_load(ctx, dreg, nft_set_ext_data(ext),
 				      set->dtype == NFT_DATA_VERDICT ?
 				      NFT_DATA_VERDICT : NFT_DATA_VALUE);
 }
@@ -2827,6 +2824,22 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		nf_tables_set_destroy(ctx, set);
 }
 
+const struct nft_set_ext_type nft_set_ext_types[] = {
+	[NFT_SET_EXT_KEY]		= {
+		.len	= sizeof(struct nft_data),
+		.align	= __alignof__(struct nft_data),
+	},
+	[NFT_SET_EXT_DATA]		= {
+		.len	= sizeof(struct nft_data),
+		.align	= __alignof__(struct nft_data),
+	},
+	[NFT_SET_EXT_FLAGS]		= {
+		.len	= sizeof(u8),
+		.align	= __alignof__(u8),
+	},
+};
+EXPORT_SYMBOL_GPL(nft_set_ext_types);
+
 /*
  * Set elements
  */
@@ -2873,6 +2886,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 				  const struct nft_set *set,
 				  const struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
@@ -2880,19 +2894,19 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, &elem->key, NFT_DATA_VALUE,
+	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext),
-			  set->klen) < 0)
+			  NFT_DATA_VALUE, set->klen) < 0)
 		goto nla_put_failure;
 
-	if (set->flags & NFT_SET_MAP &&
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
-	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END) &&
+	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
-	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data,
 			  set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
 			  set->dlen) < 0)
 		goto nla_put_failure;
 
-	if (elem->flags != 0)
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
-		if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags)))
+	    nla_put_be32(skb, NFTA_SET_ELEM_FLAGS,
+		         htonl(*nft_set_ext_flags(ext))))
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
@@ -3114,15 +3128,54 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
 	return trans;
 }
 
+static void *nft_set_elem_init(const struct nft_set *set,
+			       const struct nft_set_ext_tmpl *tmpl,
+			       const struct nft_data *key,
+			       const struct nft_data *data,
+			       gfp_t gfp)
+{
+	struct nft_set_ext *ext;
+	void *elem;
+
+	elem = kzalloc(set->ops->elemsize + tmpl->len, gfp);
+	if (elem == NULL)
+		return NULL;
+
+	ext = nft_set_elem_ext(set, elem);
+	nft_set_ext_init(ext, tmpl);
+
+	memcpy(nft_set_ext_key(ext), key, set->klen);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+		memcpy(nft_set_ext_data(ext), data, set->dlen);
+
+	return elem;
+}
+
+void nft_set_elem_destroy(const struct nft_set *set, void *elem)
+{
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
+
+	nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE);
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+		nft_data_uninit(nft_set_ext_data(ext), set->dtype);
+
+	kfree(elem);
+}
+EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
+
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_data_desc d1, d2;
+	struct nft_set_ext_tmpl tmpl;
+	struct nft_set_ext *ext;
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
+	struct nft_data data;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
+	u32 flags;
 	int err;
 
 	if (set->size && set->nelems == set->size)
@@ -3136,22 +3189,26 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (nla[NFTA_SET_ELEM_KEY] == NULL)
 		return -EINVAL;
 
-	elem.flags = 0;
+	nft_set_ext_prepare(&tmpl);
+
+	flags = 0;
 	if (nla[NFTA_SET_ELEM_FLAGS] != NULL) {
-		elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
+		flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
-		if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END)
+		if (flags & ~NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
 		if (!(set->flags & NFT_SET_INTERVAL) &&
-		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+		    flags & NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
+		if (flags != 0)
+			nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
 	}
 
 	if (set->flags & NFT_SET_MAP) {
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
-		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
+		    !(flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
 		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
-		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+		    flags & NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
@@ -3165,12 +3222,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (d1.type != NFT_DATA_VALUE || d1.len != set->klen)
 		goto err2;
 
-	err = -EEXIST;
+	nft_set_ext_add(&tmpl, NFT_SET_EXT_KEY);
-	if (set->ops->get(set, &elem) == 0)
-		goto err2;
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
-		err = nft_data_init(ctx, &elem.data, &d2, nla[NFTA_SET_ELEM_DATA]);
+		err = nft_data_init(ctx, &data, &d2, nla[NFTA_SET_ELEM_DATA]);
 		if (err < 0)
 			goto err2;
 
@@ -3187,29 +3242,43 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			};
 
 			err = nft_validate_data_load(&bind_ctx, dreg,
-						     &elem.data, d2.type);
+						     &data, d2.type);
 			if (err < 0)
 				goto err3;
 		}
+
+		nft_set_ext_add(&tmpl, NFT_SET_EXT_DATA);
 	}
 
+	err = -ENOMEM;
+	elem.priv = nft_set_elem_init(set, &tmpl, &elem.key, &data, GFP_KERNEL);
+	if (elem.priv == NULL)
+		goto err3;
+
+	ext = nft_set_elem_ext(set, elem.priv);
+	if (flags)
+		*nft_set_ext_flags(ext) = flags;
+
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
 	if (trans == NULL)
-		goto err3;
+		goto err4;
 
+	ext->genmask = nft_genmask_cur(ctx->net);
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
-		goto err4;
+		goto err5;
 
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
-err4:
+err5:
 	kfree(trans);
+err4:
+	kfree(elem.priv);
 err3:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
-		nft_data_uninit(&elem.data, d2.type);
+		nft_data_uninit(&data, d2.type);
 err2:
 	nft_data_uninit(&elem.key, d1.type);
 err1:
@@ -3282,19 +3351,24 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
 		goto err2;
 
-	err = set->ops->get(set, &elem);
-	if (err < 0)
-		goto err2;
-
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
 	if (trans == NULL) {
 		err = -ENOMEM;
 		goto err2;
 	}
 
+	elem.priv = set->ops->deactivate(set, &elem);
+	if (elem.priv == NULL) {
+		err = -ENOENT;
+		goto err3;
+	}
+
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
+
+err3:
+	kfree(trans);
 err2:
 	nft_data_uninit(&elem.key, desc.type);
 err1:
@@ -3532,6 +3606,10 @@ static void nf_tables_commit_release(struct nft_trans *trans)
 	case NFT_MSG_DELSET:
 		nft_set_destroy(nft_trans_set(trans));
 		break;
+	case NFT_MSG_DELSETELEM:
+		nft_set_elem_destroy(nft_trans_elem_set(trans),
+				     nft_trans_elem(trans).priv);
+		break;
 	}
 	kfree(trans);
 }
@@ -3546,7 +3624,7 @@ static int nf_tables_commit(struct sk_buff *skb)
 	while (++net->nft.base_seq == 0);
 
 	/* A new generation has just started */
-	net->nft.gencursor = gencursor_next(net);
+	net->nft.gencursor = nft_gencursor_next(net);
 
 	/* Make sure all packets have left the previous generation before
 	 * purging old rules.
@@ -3617,24 +3695,21 @@ static int nf_tables_commit(struct sk_buff *skb)
 					     NFT_MSG_DELSET, GFP_KERNEL);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			nf_tables_setelem_notify(&trans->ctx,
+			te = (struct nft_trans_elem *)trans->data;
-						 nft_trans_elem_set(trans),
+
-						 &nft_trans_elem(trans),
+			te->set->ops->activate(te->set, &te->elem);
+			nf_tables_setelem_notify(&trans->ctx, te->set,
+						 &te->elem,
 						 NFT_MSG_NEWSETELEM, 0);
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELSETELEM:
 			te = (struct nft_trans_elem *)trans->data;
+
 			nf_tables_setelem_notify(&trans->ctx, te->set,
 						 &te->elem,
 						 NFT_MSG_DELSETELEM, 0);
-			te->set->ops->get(te->set, &te->elem);
-			nft_data_uninit(&te->elem.key, NFT_DATA_VALUE);
-			if (te->set->flags & NFT_SET_MAP &&
-			    !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END))
-				nft_data_uninit(&te->elem.data, te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
-			nft_trans_destroy(trans);
 			break;
 		}
 	}
@@ -3666,6 +3741,10 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	case NFT_MSG_NEWSET:
 		nft_set_destroy(nft_trans_set(trans));
 		break;
+	case NFT_MSG_NEWSETELEM:
+		nft_set_elem_destroy(nft_trans_elem_set(trans),
+				     nft_trans_elem(trans).priv);
+		break;
 	}
 	kfree(trans);
 }
@@ -3736,16 +3815,15 @@ static int nf_tables_abort(struct sk_buff *skb)
 		case NFT_MSG_NEWSETELEM:
 			nft_trans_elem_set(trans)->nelems--;
 			te = (struct nft_trans_elem *)trans->data;
-			te->set->ops->get(te->set, &te->elem);
+
-			nft_data_uninit(&te->elem.key, NFT_DATA_VALUE);
-			if (te->set->flags & NFT_SET_MAP &&
-			    !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END))
-				nft_data_uninit(&te->elem.data, te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
-			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELSETELEM:
+			te = (struct nft_trans_elem *)trans->data;
+
 			nft_trans_elem_set(trans)->nelems++;
+			te->set->ops->activate(te->set, &te->elem);
+
 			nft_trans_destroy(trans);
 			break;
 		}
@@ -3820,13 +3898,18 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
-	if (elem->flags & NFT_SET_ELEM_INTERVAL_END)
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+	const struct nft_data *data;
+
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
+	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
 		return 0;
 
-	switch (elem->data.verdict) {
+	data = nft_set_ext_data(ext);
+	switch (data->verdict) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		return nf_tables_check_loops(ctx, elem->data.chain);
+		return nf_tables_check_loops(ctx, data->chain);
 	default:
 		return 0;
 	}

net/netfilter/nf_tables_core.c

@@ -8,6 +8,7 @@
  * Development of this code funded by Astaro AG (http://www.astaro.com/)
  */
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/list.h>
@@ -37,7 +38,7 @@ static struct nf_loginfo trace_loginfo = {
 	.type = NF_LOG_TYPE_LOG,
 	.u = {
 		.log = {
-			.level = 4,
+			.level = LOGLEVEL_WARNING,
 			.logflags = NF_LOG_MASK,
 	        },
 	},
@@ -49,7 +50,7 @@ static void __nft_trace_packet(const struct nft_pktinfo *pkt,
 {
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
+	nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
 		     pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
 		     chain->table->name, chain->name, comments[type],
 		     rulenum);
@@ -112,6 +113,7 @@ unsigned int
 nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
 	const struct nft_chain *chain = ops->priv, *basechain = chain;
+	const struct net *net = read_pnet(&nft_base_chain(basechain)->pnet);
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
 	struct nft_data data[NFT_REG_MAX + 1];
@@ -119,11 +121,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 	struct nft_stats *stats;
 	int rulenum;
-	/*
+	unsigned int gencursor = nft_genmask_cur(net);
-	 * Cache cursor to avoid problems in case that the cursor is updated
-	 * while traversing the ruleset.
-	 */
-	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
 
 do_chain:
 	rulenum = 0;

net/netfilter/nft_hash.c

@@ -23,24 +23,65 @@
 /* We target a hash table size of 4, element hint is 75% of final size */
 #define NFT_HASH_ELEMENT_HINT 3
 
+struct nft_hash {
+	struct rhashtable		ht;
+};
+
 struct nft_hash_elem {
 	struct rhash_head		node;
-	struct nft_data			key;
+	struct nft_set_ext		ext;
-	struct nft_data			data[];
+};
+
+struct nft_hash_cmp_arg {
+	const struct nft_set		*set;
+	const struct nft_data		*key;
+	u8				genmask;
 };
 
 static const struct rhashtable_params nft_hash_params;
 
+static inline u32 nft_hash_key(const void *data, u32 len, u32 seed)
+{
+	const struct nft_hash_cmp_arg *arg = data;
+
+	return jhash(arg->key, len, seed);
+}
+
+static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed)
+{
+	const struct nft_hash_elem *he = data;
+
+	return jhash(nft_set_ext_key(&he->ext), len, seed);
+}
+
+static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
+			       const void *ptr)
+{
+	const struct nft_hash_cmp_arg *x = arg->key;
+	const struct nft_hash_elem *he = ptr;
+
+	if (nft_data_cmp(nft_set_ext_key(&he->ext), x->key, x->set->klen))
+		return 1;
+	if (!nft_set_elem_active(&he->ext, x->genmask))
+		return 1;
+	return 0;
+}
+
 static bool nft_hash_lookup(const struct nft_set *set,
 			    const struct nft_data *key,
-			    struct nft_data *data)
+			    const struct nft_set_ext **ext)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_cur(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = key,
+	};
 
-	he = rhashtable_lookup_fast(priv, key, nft_hash_params);
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
-	if (he && set->flags & NFT_SET_MAP)
+	if (he != NULL)
-		nft_data_copy(data, he->data);
+		*ext = &he->ext;
 
 	return !!he;
 }
@@ -48,79 +89,64 @@ static bool nft_hash_lookup(const struct nft_set *set,
 static int nft_hash_insert(const struct nft_set *set,
 			   const struct nft_set_elem *elem)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
-	struct nft_hash_elem *he;
+	struct nft_hash_elem *he = elem->priv;
-	unsigned int size;
+	struct nft_hash_cmp_arg arg = {
-	int err;
+		.genmask = nft_genmask_next(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = &elem->key,
+	};
 
-	if (elem->flags != 0)
+	return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
-		return -EINVAL;
+					    nft_hash_params);
-
-	size = sizeof(*he);
-	if (set->flags & NFT_SET_MAP)
-		size += sizeof(he->data[0]);
-
-	he = kzalloc(size, GFP_KERNEL);
-	if (he == NULL)
-		return -ENOMEM;
-
-	nft_data_copy(&he->key, &elem->key);
-	if (set->flags & NFT_SET_MAP)
-		nft_data_copy(he->data, &elem->data);
-
-	err = rhashtable_insert_fast(priv, &he->node, nft_hash_params);
-	if (err)
-		kfree(he);
-
-	return err;
 }
 
-static void nft_hash_elem_destroy(const struct nft_set *set,
+static void nft_hash_activate(const struct nft_set *set,
-				  struct nft_hash_elem *he)
+			      const struct nft_set_elem *elem)
 {
-	nft_data_uninit(&he->key, NFT_DATA_VALUE);
+	struct nft_hash_elem *he = elem->priv;
-	if (set->flags & NFT_SET_MAP)
+
-		nft_data_uninit(he->data, set->dtype);
+	nft_set_elem_change_active(set, &he->ext);
-	kfree(he);
+}
+
+static void *nft_hash_deactivate(const struct nft_set *set,
+				 const struct nft_set_elem *elem)
+{
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_next(read_pnet(&set->pnet)),
+		.set	 = set,
+		.key	 = &elem->key,
+	};
+
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
+	if (he != NULL)
+		nft_set_elem_change_active(set, &he->ext);
+
+	return he;
 }
 
 static void nft_hash_remove(const struct nft_set *set,
 			    const struct nft_set_elem *elem)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he = elem->priv;
 
-	rhashtable_remove_fast(priv, elem->cookie, nft_hash_params);
+	rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
-	synchronize_rcu();
-	kfree(elem->cookie);
-}
-
-static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
-{
-	struct rhashtable *priv = nft_set_priv(set);
-	struct nft_hash_elem *he;
-
-	he = rhashtable_lookup_fast(priv, &elem->key, nft_hash_params);
-	if (!he)
-		return -ENOENT;
-
-	elem->cookie = he;
-	elem->flags = 0;
-	if (set->flags & NFT_SET_MAP)
-		nft_data_copy(&elem->data, he->data);
-
-	return 0;
 }
 
 static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
-	const struct nft_hash_elem *he;
+	struct nft_hash_elem *he;
 	struct rhashtable_iter hti;
 	struct nft_set_elem elem;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int err;
 
-	err = rhashtable_walk_init(priv, &hti);
+	err = rhashtable_walk_init(&priv->ht, &hti);
 	iter->err = err;
 	if (err)
 		return;
@@ -144,11 +170,10 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 
 		if (iter->count < iter->skip)
 			goto cont;
+		if (!nft_set_elem_active(&he->ext, genmask))
+			goto cont;
 
-		memcpy(&elem.key, &he->key, sizeof(elem.key));
+		elem.priv = he;
-		if (set->flags & NFT_SET_MAP)
-			memcpy(&elem.data, he->data, sizeof(elem.data));
-		elem.flags = 0;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0)
@@ -165,13 +190,14 @@ out:
 
 static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 {
-	return sizeof(struct rhashtable);
+	return sizeof(struct nft_hash);
 }
 
 static const struct rhashtable_params nft_hash_params = {
 	.head_offset		= offsetof(struct nft_hash_elem, node),
-	.key_offset = offsetof(struct nft_hash_elem, key),
+	.hashfn			= nft_hash_key,
-	.hashfn = jhash,
+	.obj_hashfn		= nft_hash_obj,
+	.obj_cmpfn		= nft_hash_cmp,
 	.automatic_shrinking	= true,
 };
 
@@ -179,23 +205,25 @@ static int nft_hash_init(const struct nft_set *set,
 			 const struct nft_set_desc *desc,
 			 const struct nlattr * const tb[])
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
 	struct rhashtable_params params = nft_hash_params;
 
 	params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT;
 	params.key_len	  = set->klen;
 
-	return rhashtable_init(priv, &params);
+	return rhashtable_init(&priv->ht, &params);
 }
 
-static void nft_free_element(void *ptr, void *arg)
+static void nft_hash_elem_destroy(void *ptr, void *arg)
 {
-	nft_hash_elem_destroy((const struct nft_set *)arg, ptr);
+	nft_set_elem_destroy((const struct nft_set *)arg, ptr);
 }
 
 static void nft_hash_destroy(const struct nft_set *set)
 {
-	rhashtable_free_and_destroy(nft_set_priv(set), nft_free_element,
+	struct nft_hash *priv = nft_set_priv(set);
+
+	rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy,
 				    (void *)set);
 }
 
@@ -205,11 +233,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 	unsigned int esize;
 
 	esize = sizeof(struct nft_hash_elem);
-	if (features & NFT_SET_MAP)
-		esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]);
-
 	if (desc->size) {
-		est->size = sizeof(struct rhashtable) +
+		est->size = sizeof(struct nft_hash) +
 			    roundup_pow_of_two(desc->size * 4 / 3) *
 			    sizeof(struct nft_hash_elem *) +
 			    desc->size * esize;
@@ -229,11 +254,13 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 
 static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.privsize       = nft_hash_privsize,
+	.elemsize	= offsetof(struct nft_hash_elem, ext),
 	.estimate	= nft_hash_estimate,
 	.init		= nft_hash_init,
 	.destroy	= nft_hash_destroy,
-	.get		= nft_hash_get,
 	.insert		= nft_hash_insert,
+	.activate	= nft_hash_activate,
+	.deactivate	= nft_hash_deactivate,
 	.remove		= nft_hash_remove,
 	.lookup		= nft_hash_lookup,
 	.walk		= nft_hash_walk,

net/netfilter/nft_log.c

@@ -78,7 +78,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 			li->u.log.level =
 				ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL]));
 		} else {
-			li->u.log.level = 4;
+			li->u.log.level = LOGLEVEL_WARNING;
 		}
 		if (tb[NFTA_LOG_FLAGS] != NULL) {
 			li->u.log.logflags =

net/netfilter/nft_lookup.c

@@ -31,9 +31,13 @@ static void nft_lookup_eval(const struct nft_expr *expr,
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
+	const struct nft_set_ext *ext;
 
-	if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg]))
+	if (set->ops->lookup(set, &data[priv->sreg], &ext)) {
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(&data[priv->dreg], nft_set_ext_data(ext));
 		return;
+	}
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
 

net/netfilter/nft_meta.c

@@ -153,7 +153,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		}
 		break;
 	case NFT_META_CPU:
-		dest->data[0] = smp_processor_id();
+		dest->data[0] = raw_smp_processor_id();
 		break;
 	case NFT_META_IIFGROUP:
 		if (in == NULL)

net/netfilter/nft_rbtree.c

@@ -26,18 +26,18 @@ struct nft_rbtree {
 
 struct nft_rbtree_elem {
 	struct rb_node		node;
-	u16			flags;
+	struct nft_set_ext	ext;
-	struct nft_data		key;
-	struct nft_data		data[];
 };
 
+
 static bool nft_rbtree_lookup(const struct nft_set *set,
 			      const struct nft_data *key,
-			      struct nft_data *data)
+			      const struct nft_set_ext **ext)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
 	const struct rb_node *parent;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int d;
 
 	spin_lock_bh(&nft_rbtree_lock);
@@ -45,7 +45,7 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
-		d = nft_data_cmp(&rbe->key, key, set->klen);
+		d = nft_data_cmp(nft_set_ext_key(&rbe->ext), key, set->klen);
 		if (d < 0) {
 			parent = parent->rb_left;
 			interval = rbe;
@@ -53,12 +53,17 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 			parent = parent->rb_right;
 		else {
 found:
-			if (rbe->flags & NFT_SET_ELEM_INTERVAL_END)
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
+				parent = parent->rb_left;
+				continue;
+			}
+			if (nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
+			    *nft_set_ext_flags(&rbe->ext) &
+			    NFT_SET_ELEM_INTERVAL_END)
 				goto out;
-			if (set->flags & NFT_SET_MAP)
-				nft_data_copy(data, rbe->data);
-
 			spin_unlock_bh(&nft_rbtree_lock);
+
+			*ext = &rbe->ext;
 			return true;
 		}
 	}
@@ -72,23 +77,13 @@ out:
 	return false;
 }
 
-static void nft_rbtree_elem_destroy(const struct nft_set *set,
-				    struct nft_rbtree_elem *rbe)
-{
-	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP &&
-	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-		nft_data_uninit(rbe->data, set->dtype);
-
-	kfree(rbe);
-}
-
 static int __nft_rbtree_insert(const struct nft_set *set,
 			       struct nft_rbtree_elem *new)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *parent, **p;
+	u8 genmask = nft_genmask_next(read_pnet(&set->pnet));
 	int d;
 
 	parent = NULL;
@@ -96,13 +91,18 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 	while (*p != NULL) {
 		parent = *p;
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
-		d = nft_data_cmp(&rbe->key, &new->key, set->klen);
+		d = nft_data_cmp(nft_set_ext_key(&rbe->ext),
+				 nft_set_ext_key(&new->ext),
+				 set->klen);
 		if (d < 0)
 			p = &parent->rb_left;
 		else if (d > 0)
 			p = &parent->rb_right;
-		else
+		else {
+			if (nft_set_elem_active(&rbe->ext, genmask))
 				return -EEXIST;
+			p = &parent->rb_left;
+		}
 	}
 	rb_link_node(&new->node, parent, p);
 	rb_insert_color(&new->node, &priv->root);
@@ -112,31 +112,13 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 static int nft_rbtree_insert(const struct nft_set *set,
 			     const struct nft_set_elem *elem)
 {
-	struct nft_rbtree_elem *rbe;
+	struct nft_rbtree_elem *rbe = elem->priv;
-	unsigned int size;
 	int err;
 
-	size = sizeof(*rbe);
-	if (set->flags & NFT_SET_MAP &&
-	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
-		size += sizeof(rbe->data[0]);
-
-	rbe = kzalloc(size, GFP_KERNEL);
-	if (rbe == NULL)
-		return -ENOMEM;
-
-	rbe->flags = elem->flags;
-	nft_data_copy(&rbe->key, &elem->key);
-	if (set->flags & NFT_SET_MAP &&
-	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-		nft_data_copy(rbe->data, &elem->data);
-
 	spin_lock_bh(&nft_rbtree_lock);
 	err = __nft_rbtree_insert(set, rbe);
-	if (err < 0)
-		kfree(rbe);
-
 	spin_unlock_bh(&nft_rbtree_lock);
+
 	return err;
 }
 
@@ -144,39 +126,49 @@ static void nft_rbtree_remove(const struct nft_set *set,
 			      const struct nft_set_elem *elem)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
-	struct nft_rbtree_elem *rbe = elem->cookie;
+	struct nft_rbtree_elem *rbe = elem->priv;
 
 	spin_lock_bh(&nft_rbtree_lock);
 	rb_erase(&rbe->node, &priv->root);
 	spin_unlock_bh(&nft_rbtree_lock);
-	kfree(rbe);
 }
 
-static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
+static void nft_rbtree_activate(const struct nft_set *set,
+				const struct nft_set_elem *elem)
+{
+	struct nft_rbtree_elem *rbe = elem->priv;
+
+	nft_set_elem_change_active(set, &rbe->ext);
+}
+
+static void *nft_rbtree_deactivate(const struct nft_set *set,
+				   const struct nft_set_elem *elem)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	struct nft_rbtree_elem *rbe;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 	int d;
 
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
-		d = nft_data_cmp(&rbe->key, &elem->key, set->klen);
+		d = nft_data_cmp(nft_set_ext_key(&rbe->ext), &elem->key,
+				 set->klen);
 		if (d < 0)
 			parent = parent->rb_left;
 		else if (d > 0)
 			parent = parent->rb_right;
 		else {
-			elem->cookie = rbe;
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
-			if (set->flags & NFT_SET_MAP &&
+				parent = parent->rb_left;
-			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
+				continue;
-				nft_data_copy(&elem->data, rbe->data);
+			}
-			elem->flags = rbe->flags;
+			nft_set_elem_change_active(set, &rbe->ext);
-			return 0;
+			return rbe;
 		}
 	}
-	return -ENOENT;
+	return NULL;
 }
 
 static void nft_rbtree_walk(const struct nft_ctx *ctx,
@@ -184,21 +176,21 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 			    struct nft_set_iter *iter)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
-	const struct nft_rbtree_elem *rbe;
+	struct nft_rbtree_elem *rbe;
 	struct nft_set_elem elem;
 	struct rb_node *node;
+	u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
 
 	spin_lock_bh(&nft_rbtree_lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
+		rbe = rb_entry(node, struct nft_rbtree_elem, node);
+
 		if (iter->count < iter->skip)
 			goto cont;
+		if (!nft_set_elem_active(&rbe->ext, genmask))
+			goto cont;
 
-		rbe = rb_entry(node, struct nft_rbtree_elem, node);
+		elem.priv = rbe;
-		nft_data_copy(&elem.key, &rbe->key);
-		if (set->flags & NFT_SET_MAP &&
-		    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-			nft_data_copy(&elem.data, rbe->data);
-		elem.flags = rbe->flags;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0) {
@@ -235,7 +227,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
-		nft_rbtree_elem_destroy(set, rbe);
+		nft_set_elem_destroy(set, rbe);
 	}
 }
 
@@ -245,9 +237,6 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 	unsigned int nsize;
 
 	nsize = sizeof(struct nft_rbtree_elem);
-	if (features & NFT_SET_MAP)
-		nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]);
-
 	if (desc->size)
 		est->size = sizeof(struct nft_rbtree) + desc->size * nsize;
 	else
@@ -260,12 +249,14 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 
 static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.privsize	= nft_rbtree_privsize,
+	.elemsize	= offsetof(struct nft_rbtree_elem, ext),
 	.estimate	= nft_rbtree_estimate,
 	.init		= nft_rbtree_init,
 	.destroy	= nft_rbtree_destroy,
 	.insert		= nft_rbtree_insert,
 	.remove		= nft_rbtree_remove,
-	.get		= nft_rbtree_get,
+	.deactivate	= nft_rbtree_deactivate,
+	.activate	= nft_rbtree_activate,
 	.lookup		= nft_rbtree_lookup,
 	.walk		= nft_rbtree_walk,
 	.features	= NFT_SET_INTERVAL | NFT_SET_MAP,

net/netlink/af_netlink.c

@@ -3127,7 +3127,7 @@ static struct pernet_operations __net_initdata netlink_net_ops = {
 	.exit = netlink_net_exit,
 };
 
-static inline u32 netlink_hash(const void *data, u32 seed)
+static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
 {
 	const struct netlink_sock *nlk = data;
 	struct netlink_compare_arg arg;