[PATCH 00/15] Netfilter updates for net-next

[PATCH 00/15] Netfilter updates for net-next

[Pablo Neira Ayuso]

Hi David,

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.

You can pull these changes from:

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

Thanks!

----------------------------------------------------------------

The following changes since commit 0144a81cccf7532bead90f0542f517bd028d3b3c:

  tcp: fix ipv4 mapped request socks (2015-03-25 00:57:48 -0400)

are available in the git repository at:

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

for you to fetch changes up to cc02e457bb86f7b6ffee3651bab22d104b60effb:

  netfilter: nf_tables: implement set transaction support (2015-03-26 11:09:35 +0100)

----------------------------------------------------------------
Joe Perches (1):
      netfilter: Use LOGLEVEL_<FOO> defines

Pablo Neira Ayuso (1):
      netfilter: nf_tables: restore nf_log_trace() in nf_tables_core.c

Patrick McHardy (13):
      netfilter: nf_tables: move struct net pointer to base chain
      netfilter: nf_tables: nft_queue does not depend on x_tables
      netfilter: nft_meta: use raw_smp_processor_id()
      rhashtable: provide len to obj_hashfn
      netfilter: nft_hash: restore struct nft_hash
      netfilter: nft_hash: indent rhashtable parameters
      netfilter: nft_hash: convert to use rhashtable callbacks
      netfilter: nf_tables: add set extensions
      netfilter: nf_tables: convert hash and rbtree to set extensions
      netfilter: nf_tables: consolide set element destruction
      netfilter: nf_tables: return set extensions from ->lookup()
      netfilter: nf_tables: add transaction helper functions
      netfilter: nf_tables: implement set transaction support

 include/linux/rhashtable.h        |    6 +-
 include/net/netfilter/nf_tables.h |  190 ++++++++++++++++++++++++++++++++---
 lib/rhashtable.c                  |    2 +-
 net/ipv4/netfilter/nf_log_arp.c   |    4 +-
 net/ipv4/netfilter/nf_log_ipv4.c  |    4 +-
 net/ipv6/netfilter/ip6_tables.c   |    5 +-
 net/ipv6/netfilter/nf_log_ipv6.c  |    4 +-
 net/netfilter/Kconfig             |    1 -
 net/netfilter/nf_tables_api.c     |  199 ++++++++++++++++++++++++++-----------
 net/netfilter/nf_tables_core.c    |   18 ++--
 net/netfilter/nft_hash.c          |  183 +++++++++++++++++++---------------
 net/netfilter/nft_log.c           |    2 +-
 net/netfilter/nft_lookup.c        |    6 +-
 net/netfilter/nft_meta.c          |    2 +-
 net/netfilter/nft_rbtree.c        |  123 +++++++++++------------
 net/netlink/af_netlink.c          |    2 +-
 16 files changed, 513 insertions(+), 238 deletions(-)

[PATCH 01/15] netfilter: nf_tables: move struct net pointer to base chain

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

The network namespace is only needed for base chains to get at the
gencursor. Also convert to possible_net_t.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |    4 ++--
 net/netfilter/nf_tables_api.c     |    2 +-
 net/netfilter/nf_tables_core.c    |    3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index d756af5..ace67a5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -449,7 +449,6 @@ 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 +459,6 @@ 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 +510,7 @@ 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 +518,7 @@ 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;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 363a39a..0b969b6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1354,6 +1354,7 @@ 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 +1382,6 @@ 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);
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 77165bf..4c921a3 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -112,6 +112,7 @@ 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];
@@ -123,7 +124,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	 * 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);
+	unsigned int gencursor = ACCESS_ONCE(net->nft.gencursor);
 
 do_chain:
 	rulenum = 0;
-- 
1.7.10.4

[PATCH 02/15] netfilter: Use LOGLEVEL_<FOO> defines

[Pablo Neira Ayuso]

From: Joe Perches <joe@perches.com>

Use the #defines where appropriate.

Miscellanea:

Add explicit #include <linux/kernel.h> where it was not
previously used so that these #defines are a bit more
explicitly defined instead of indirectly included via:
	module.h->moduleparam.h->kernel.h

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/nf_log_arp.c  |    4 +++-
 net/ipv4/netfilter/nf_log_ipv4.c |    4 +++-
 net/ipv6/netfilter/ip6_tables.c  |    5 ++++-
 net/ipv6/netfilter/nf_log_ipv6.c |    4 +++-
 net/netfilter/nf_tables_core.c   |    3 ++-
 net/netfilter/nft_log.c          |    2 +-
 6 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index d059182..e7ad950 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/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,
 		},
 	},
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 7510198..076aadd 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/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,
 		},
 	},
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index bb00c6f..83f59dc 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/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,
 		},
 	},
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index ddf07e6..8dd8696 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/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,
 		},
 	},
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 4c921a3..763a9d8 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/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,
 	        },
 	},
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index bde05f28..e18af9db 100644
--- a/net/netfilter/nft_log.c
+++ b/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 =
-- 
1.7.10.4

[PATCH 03/15] netfilter: nf_tables: restore nf_log_trace() in nf_tables_core.c

[Pablo Neira Ayuso]

As described by 4017a7e ("netfilter: restore rule tracing via
nfnetlink_log"), this accidentally slipped through during conflict
resolution in d5c1d8c.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_core.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 763a9d8..4429008 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -50,10 +50,10 @@ 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,
-		      pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
-		      chain->table->name, chain->name, comments[type],
-		      rulenum);
+	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);
 }
 
 static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
-- 
1.7.10.4

[PATCH 04/15] netfilter: nf_tables: nft_queue does not depend on x_tables

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig |    1 -
 1 file changed, 1 deletion(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 971cd75..f70e34a 100644
--- a/net/netfilter/Kconfig
+++ b/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
-- 
1.7.10.4

[PATCH 05/15] netfilter: nft_meta: use raw_smp_processor_id()

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Using smp_processor_id() triggers warnings with PREEMPT_RCU. There is no
point in disabling preemption since we only collect the numeric value,
so use raw_smp_processor_id() instead.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_meta.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index abe6811..5197874 100644
--- a/net/netfilter/nft_meta.c
+++ b/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)
-- 
1.7.10.4

[PATCH 06/15] rhashtable: provide len to obj_hashfn

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

nftables sets will be converted to use so called setextensions, moving
the key to a non-fixed position. To hash it, the obj_hashfn must be used,
however it so far doesn't receive the length parameter.

Pass the key length to obj_hashfn() and convert existing users.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/rhashtable.h |    6 ++++--
 lib/rhashtable.c           |    2 +-
 net/netlink/af_netlink.c   |    2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 99f2e49..e23d242 100644
--- a/include/linux/rhashtable.h
+++ b/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);
 }
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 4b7b7e6..4898442 100644
--- a/lib/rhashtable.c
+++ b/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;
  *
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4caa809..19909d0 100644
--- a/net/netlink/af_netlink.c
+++ b/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;
-- 
1.7.10.4

[PATCH 07/15] netfilter: nft_hash: restore struct nft_hash

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Following patches will add new private members, restore struct nft_hash
as preparation.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_hash.c |   37 +++++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index f9ce219..a517f84 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -23,6 +23,10 @@
 /* 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;
@@ -35,10 +39,10 @@ static bool nft_hash_lookup(const struct nft_set *set,
 			    const struct nft_data *key,
 			    struct nft_data *data)
 {
-	struct rhashtable *priv = nft_set_priv(set);
+	struct nft_hash *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
 
-	he = rhashtable_lookup_fast(priv, key, nft_hash_params);
+	he = rhashtable_lookup_fast(&priv->ht, key, nft_hash_params);
 	if (he && set->flags & NFT_SET_MAP)
 		nft_data_copy(data, he->data);
 
@@ -48,7 +52,7 @@ 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;
 	unsigned int size;
 	int err;
@@ -68,7 +72,7 @@ static int nft_hash_insert(const struct nft_set *set,
 	if (set->flags & NFT_SET_MAP)
 		nft_data_copy(he->data, &elem->data);
 
-	err = rhashtable_insert_fast(priv, &he->node, nft_hash_params);
+	err = rhashtable_insert_fast(&priv->ht, &he->node, nft_hash_params);
 	if (err)
 		kfree(he);
 
@@ -87,19 +91,19 @@ static void nft_hash_elem_destroy(const struct nft_set *set,
 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);
 
-	rhashtable_remove_fast(priv, elem->cookie, nft_hash_params);
+	rhashtable_remove_fast(&priv->ht, elem->cookie, 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 *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
 
-	he = rhashtable_lookup_fast(priv, &elem->key, nft_hash_params);
+	he = rhashtable_lookup_fast(&priv->ht, &elem->key, nft_hash_params);
 	if (!he)
 		return -ENOENT;
 
@@ -114,13 +118,13 @@ static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 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 rhashtable_iter hti;
 	struct nft_set_elem elem;
 	int err;
 
-	err = rhashtable_walk_init(priv, &hti);
+	err = rhashtable_walk_init(&priv->ht, &hti);
 	iter->err = err;
 	if (err)
 		return;
@@ -165,7 +169,7 @@ 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 = {
@@ -179,13 +183,13 @@ 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)
@@ -195,8 +199,9 @@ static void nft_free_element(void *ptr, void *arg)
 
 static void nft_hash_destroy(const struct nft_set *set)
 {
-	rhashtable_free_and_destroy(nft_set_priv(set), nft_free_element,
-				    (void *)set);
+	struct nft_hash *priv = nft_set_priv(set);
+
+	rhashtable_free_and_destroy(&priv->ht, nft_free_element, (void *)set);
 }
 
 static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
@@ -209,7 +214,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 		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;
-- 
1.7.10.4

[PATCH 08/15] netfilter: nft_hash: indent rhashtable parameters

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Improve readability by indenting the parameter initialization.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_hash.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index a517f84..e35f0b2 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -173,10 +173,10 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 }
 
 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 = jhash,
-	.automatic_shrinking = true,
+	.head_offset		= offsetof(struct nft_hash_elem, node),
+	.key_offset		= offsetof(struct nft_hash_elem, key),
+	.hashfn			= jhash,
+	.automatic_shrinking	= true,
 };
 
 static int nft_hash_init(const struct nft_set *set,
@@ -187,7 +187,7 @@ static int nft_hash_init(const struct nft_set *set,
 	struct rhashtable_params params = nft_hash_params;
 
 	params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT;
-	params.key_len = set->klen;
+	params.key_len	  = set->klen;
 
 	return rhashtable_init(&priv->ht, &params);
 }
-- 
1.7.10.4

[PATCH 09/15] netfilter: nft_hash: convert to use rhashtable callbacks

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

A following patch will convert sets to use so called set extensions,
where the key is not located in a fixed position anymore. This will
require rhashtable hashing and comparison callbacks to be used.

As preparation, convert nft_hash to use these callbacks without any
functional changes.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_hash.c |   54 +++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 49 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index e35f0b2..dc96a7e 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -33,16 +33,50 @@ struct nft_hash_elem {
 	struct nft_data			data[];
 };
 
+struct nft_hash_cmp_arg {
+	const struct nft_set		*set;
+	const struct nft_data		*key;
+};
+
 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(&he->key, 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(&he->key, x->key, x->set->klen))
+		return 1;
+	return 0;
+}
+
 static bool nft_hash_lookup(const struct nft_set *set,
 			    const struct nft_data *key,
 			    struct nft_data *data)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.set	 = set,
+		.key	 = key,
+	};
 
-	he = rhashtable_lookup_fast(&priv->ht, key, nft_hash_params);
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
 	if (he && set->flags & NFT_SET_MAP)
 		nft_data_copy(data, he->data);
 
@@ -54,6 +88,10 @@ static int nft_hash_insert(const struct nft_set *set,
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.set	 = set,
+		.key	 = &elem->key,
+	};
 	unsigned int size;
 	int err;
 
@@ -72,7 +110,8 @@ static int nft_hash_insert(const struct nft_set *set,
 	if (set->flags & NFT_SET_MAP)
 		nft_data_copy(he->data, &elem->data);
 
-	err = rhashtable_insert_fast(&priv->ht, &he->node, nft_hash_params);
+	err = rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
+					   nft_hash_params);
 	if (err)
 		kfree(he);
 
@@ -102,8 +141,12 @@ static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
+	struct nft_hash_cmp_arg arg = {
+		.set	 = set,
+		.key	 = &elem->key,
+	};
 
-	he = rhashtable_lookup_fast(&priv->ht, &elem->key, nft_hash_params);
+	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
 	if (!he)
 		return -ENOENT;
 
@@ -174,8 +217,9 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 
 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			= jhash,
+	.hashfn			= nft_hash_key,
+	.obj_hashfn		= nft_hash_obj,
+	.obj_cmpfn		= nft_hash_cmp,
 	.automatic_shrinking	= true,
 };
 
-- 
1.7.10.4

[PATCH 10/15] netfilter: nf_tables: add set extensions

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Add simple set extension infrastructure for maintaining variable sized
and optional per element data.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  105 +++++++++++++++++++++++++++++++++++++
 net/netfilter/nf_tables_api.c     |   16 ++++++
 2 files changed, 121 insertions(+)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ace67a5..038f8a6 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -311,6 +311,111 @@ 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
+ *
+ *	@offset: offsets of individual extension types
+ *	@data: beginning of extension data
+ */
+struct nft_set_ext {
+	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);
+}
 
 /**
  *	struct nft_expr_type - nf_tables expression type
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0b969b6..972c47f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2827,6 +2827,22 @@ 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
  */
-- 
1.7.10.4

[PATCH 11/15] netfilter: nf_tables: convert hash and rbtree to set extensions

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

The set implementations' private struct will only contain the elements
needed to maintain the search structure, all other elements are moved
to the set extensions.

Element allocation and initialization is performed centrally by
nf_tables_api instead of by the different set implementations'
->insert() functions. A new "elemsize" member in the set ops specifies
the amount of memory to reserve for internal usage. Destruction
will also be moved out of the set implementations by a following patch.

Except for element allocation, the patch is a simple conversion to
using data from the extension area.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |   14 +++--
 net/netfilter/nf_tables_api.c     |  119 +++++++++++++++++++++++++++----------
 net/netfilter/nft_hash.c          |   56 ++++-------------
 net/netfilter/nft_rbtree.c        |   64 +++++++-------------
 4 files changed, 132 insertions(+), 121 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 038f8a6..ef3457c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -140,8 +140,7 @@ struct nft_userdata {
  *
  *	@cookie: implementation specific element cookie
  *	@key: element key
- *	@data: element data (maps only)
- *	@flags: element flags (end of interval)
+ *	@priv: element private data and extensions
  *
  *	The cookie can be used to store a handle to the element for subsequent
  *	removal.
@@ -149,8 +148,7 @@ struct nft_userdata {
 struct nft_set_elem {
 	void			*cookie;
 	struct nft_data		key;
-	struct nft_data		data;
-	u32			flags;
+	void			*priv;
 };
 
 struct nft_set;
@@ -214,6 +212,7 @@ 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 {
@@ -241,6 +240,7 @@ struct nft_set_ops {
 
 	struct list_head		list;
 	struct module			*owner;
+	unsigned int			elemsize;
 	u32				features;
 };
 
@@ -417,6 +417,12 @@ 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;
+}
+
 /**
  *	struct nft_expr_type - nf_tables expression type
  *
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 972c47f..99cb884 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2771,10 +2771,11 @@ 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);
 }
@@ -2889,6 +2890,7 @@ 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;
 
@@ -2896,20 +2898,20 @@ 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,
-			  set->klen) < 0)
+	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext),
+			  NFT_DATA_VALUE, set->klen) < 0)
 		goto nla_put_failure;
 
-	if (set->flags & NFT_SET_MAP &&
-	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END) &&
-	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data,
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
+	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
 			  set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
 			  set->dlen) < 0)
 		goto nla_put_failure;
 
-	if (elem->flags != 0)
-		if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags)))
-			goto nla_put_failure;
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
+	    nla_put_be32(skb, NFTA_SET_ELEM_FLAGS,
+		         htonl(*nft_set_ext_flags(ext))))
+		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 	return 0;
@@ -3130,15 +3132,42 @@ 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;
+}
+
 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)
@@ -3152,22 +3181,26 @@ 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]));
-		if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END)
+		flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
+		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)
@@ -3185,8 +3218,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (set->ops->get(set, &elem) == 0)
 		goto err2;
 
+	nft_set_ext_add(&tmpl, NFT_SET_EXT_KEY);
+
 	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;
 
@@ -3203,29 +3238,42 @@ 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;
 
 	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:
@@ -3557,6 +3605,7 @@ static int nf_tables_commit(struct sk_buff *skb)
 	struct net *net = sock_net(skb->sk);
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
+	struct nft_set_ext *ext;
 
 	/* Bump generation counter, invalidate any dump in progress */
 	while (++net->nft.base_seq == 0);
@@ -3641,14 +3690,16 @@ static int nf_tables_commit(struct sk_buff *skb)
 			break;
 		case NFT_MSG_DELSETELEM:
 			te = (struct nft_trans_elem *)trans->data;
+			ext = nft_set_elem_ext(te->set, te->elem.priv);
+
 			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);
+			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+				nft_data_uninit(nft_set_ext_data(ext),
+						te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
 			nft_trans_destroy(trans);
 			break;
@@ -3691,6 +3742,7 @@ static int nf_tables_abort(struct sk_buff *skb)
 	struct net *net = sock_net(skb->sk);
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
+	struct nft_set_ext *ext;
 
 	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
 		switch (trans->msg_type) {
@@ -3752,11 +3804,13 @@ 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;
+			ext = nft_set_elem_ext(te->set, te->elem.priv);
+
 			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);
+			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
+				nft_data_uninit(nft_set_ext_data(ext),
+						te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
 			nft_trans_destroy(trans);
 			break;
@@ -3836,13 +3890,18 @@ 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;
 	}
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index dc96a7e..15951a8 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -29,8 +29,7 @@ struct nft_hash {
 
 struct nft_hash_elem {
 	struct rhash_head		node;
-	struct nft_data			key;
-	struct nft_data			data[];
+	struct nft_set_ext		ext;
 };
 
 struct nft_hash_cmp_arg {
@@ -51,7 +50,7 @@ static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct nft_hash_elem *he = data;
 
-	return jhash(&he->key, len, seed);
+	return jhash(nft_set_ext_key(&he->ext), len, seed);
 }
 
 static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -60,7 +59,7 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
 	const struct nft_hash_cmp_arg *x = arg->key;
 	const struct nft_hash_elem *he = ptr;
 
-	if (nft_data_cmp(&he->key, x->key, x->set->klen))
+	if (nft_data_cmp(nft_set_ext_key(&he->ext), x->key, x->set->klen))
 		return 1;
 	return 0;
 }
@@ -78,7 +77,7 @@ static bool nft_hash_lookup(const struct nft_set *set,
 
 	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
 	if (he && set->flags & NFT_SET_MAP)
-		nft_data_copy(data, he->data);
+		nft_data_copy(data, nft_set_ext_data(&he->ext));
 
 	return !!he;
 }
@@ -87,43 +86,22 @@ static int nft_hash_insert(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_elem *he = elem->priv;
 	struct nft_hash_cmp_arg arg = {
 		.set	 = set,
 		.key	 = &elem->key,
 	};
-	unsigned int size;
-	int err;
-
-	if (elem->flags != 0)
-		return -EINVAL;
-
-	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_lookup_insert_key(&priv->ht, &arg, &he->node,
-					   nft_hash_params);
-	if (err)
-		kfree(he);
 
-	return err;
+	return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
+					    nft_hash_params);
 }
 
 static void nft_hash_elem_destroy(const struct nft_set *set,
 				  struct nft_hash_elem *he)
 {
-	nft_data_uninit(&he->key, NFT_DATA_VALUE);
+	nft_data_uninit(nft_set_ext_key(&he->ext), NFT_DATA_VALUE);
 	if (set->flags & NFT_SET_MAP)
-		nft_data_uninit(he->data, set->dtype);
+		nft_data_uninit(nft_set_ext_data(&he->ext), set->dtype);
 	kfree(he);
 }
 
@@ -150,10 +128,7 @@ static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 	if (!he)
 		return -ENOENT;
 
-	elem->cookie = he;
-	elem->flags = 0;
-	if (set->flags & NFT_SET_MAP)
-		nft_data_copy(&elem->data, he->data);
+	elem->priv = he;
 
 	return 0;
 }
@@ -162,7 +137,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
 	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;
 	int err;
@@ -192,10 +167,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 		if (iter->count < iter->skip)
 			goto cont;
 
-		memcpy(&elem.key, &he->key, sizeof(elem.key));
-		if (set->flags & NFT_SET_MAP)
-			memcpy(&elem.data, he->data, sizeof(elem.data));
-		elem.flags = 0;
+		elem.priv = he;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0)
@@ -254,9 +226,6 @@ 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 nft_hash) +
 			    roundup_pow_of_two(desc->size * 4 / 3) *
@@ -278,6 +247,7 @@ 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,
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 2c75361..ebf6e60 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -26,9 +26,7 @@ struct nft_rbtree {
 
 struct nft_rbtree_elem {
 	struct rb_node		node;
-	u16			flags;
-	struct nft_data		key;
-	struct nft_data		data[];
+	struct nft_set_ext	ext;
 };
 
 static bool nft_rbtree_lookup(const struct nft_set *set,
@@ -45,7 +43,7 @@ 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;
@@ -53,10 +51,12 @@ 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_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);
+				nft_data_copy(data, nft_set_ext_data(&rbe->ext));
 
 			spin_unlock_bh(&nft_rbtree_lock);
 			return true;
@@ -75,10 +75,10 @@ out:
 static void nft_rbtree_elem_destroy(const struct nft_set *set,
 				    struct nft_rbtree_elem *rbe)
 {
-	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
+	nft_data_uninit(nft_set_ext_key(&rbe->ext), NFT_DATA_VALUE);
 	if (set->flags & NFT_SET_MAP &&
-	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-		nft_data_uninit(rbe->data, set->dtype);
+	    nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_DATA))
+		nft_data_uninit(nft_set_ext_data(&rbe->ext), set->dtype);
 
 	kfree(rbe);
 }
@@ -96,7 +96,9 @@ 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)
@@ -112,31 +114,13 @@ 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;
-	unsigned int size;
+	struct nft_rbtree_elem *rbe = elem->priv;
 	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;
 }
 
@@ -162,17 +146,15 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 	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 (set->flags & NFT_SET_MAP &&
-			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
-				nft_data_copy(&elem->data, rbe->data);
-			elem->flags = rbe->flags;
+			elem->priv   = rbe;
 			return 0;
 		}
 	}
@@ -184,7 +166,7 @@ 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;
 
@@ -194,11 +176,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 			goto cont;
 
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
-		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;
+		elem.priv = rbe;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0) {
@@ -245,9 +223,6 @@ 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
@@ -260,6 +235,7 @@ 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,
-- 
1.7.10.4

[PATCH 12/15] netfilter: nf_tables: consolide set element destruction

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

With the conversion to set extensions, it is now possible to consolidate
the different set element destruction functions.

The set implementations' ->remove() functions are changed to only take
the element out of their internal data structures. Elements will be freed
in a batched fashion after the global transaction's completion RCU grace
period.

This reduces the amount of grace periods required for nft_hash from N
to zero additional ones, additionally this guarantees that the set
elements' extensions of all implementations can be used under RCU
protection.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |    2 ++
 net/netfilter/nf_tables_api.c     |   34 ++++++++++++++++++++--------------
 net/netfilter/nft_hash.c          |   18 ++++--------------
 net/netfilter/nft_rbtree.c        |   14 +-------------
 4 files changed, 27 insertions(+), 41 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ef3457c..6ac6332 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -423,6 +423,8 @@ static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
 	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
  *
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 99cb884..b35512f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3155,6 +3155,18 @@ static void *nft_set_elem_init(const struct nft_set *set,
 	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)
 {
@@ -3596,6 +3608,10 @@ 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);
 }
@@ -3605,7 +3621,6 @@ static int nf_tables_commit(struct sk_buff *skb)
 	struct net *net = sock_net(skb->sk);
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
-	struct nft_set_ext *ext;
 
 	/* Bump generation counter, invalidate any dump in progress */
 	while (++net->nft.base_seq == 0);
@@ -3690,18 +3705,12 @@ static int nf_tables_commit(struct sk_buff *skb)
 			break;
 		case NFT_MSG_DELSETELEM:
 			te = (struct nft_trans_elem *)trans->data;
-			ext = nft_set_elem_ext(te->set, te->elem.priv);
 
 			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 (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
-				nft_data_uninit(nft_set_ext_data(ext),
-						te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
-			nft_trans_destroy(trans);
 			break;
 		}
 	}
@@ -3733,6 +3742,10 @@ 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);
 }
@@ -3742,7 +3755,6 @@ static int nf_tables_abort(struct sk_buff *skb)
 	struct net *net = sock_net(skb->sk);
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
-	struct nft_set_ext *ext;
 
 	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
 		switch (trans->msg_type) {
@@ -3804,15 +3816,9 @@ 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;
-			ext = nft_set_elem_ext(te->set, te->elem.priv);
 
 			te->set->ops->get(te->set, &te->elem);
-			nft_data_uninit(&te->elem.key, NFT_DATA_VALUE);
-			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
-				nft_data_uninit(nft_set_ext_data(ext),
-						te->set->dtype);
 			te->set->ops->remove(te->set, &te->elem);
-			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELSETELEM:
 			nft_trans_elem_set(trans)->nelems++;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 15951a8..94bf25d 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -96,23 +96,12 @@ static int nft_hash_insert(const struct nft_set *set,
 					    nft_hash_params);
 }
 
-static void nft_hash_elem_destroy(const struct nft_set *set,
-				  struct nft_hash_elem *he)
-{
-	nft_data_uninit(nft_set_ext_key(&he->ext), NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
-		nft_data_uninit(nft_set_ext_data(&he->ext), set->dtype);
-	kfree(he);
-}
-
 static void nft_hash_remove(const struct nft_set *set,
 			    const struct nft_set_elem *elem)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 
 	rhashtable_remove_fast(&priv->ht, elem->cookie, nft_hash_params);
-	synchronize_rcu();
-	kfree(elem->cookie);
 }
 
 static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
@@ -208,16 +197,17 @@ static int nft_hash_init(const struct nft_set *set,
 	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)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 
-	rhashtable_free_and_destroy(&priv->ht, nft_free_element, (void *)set);
+	rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy,
+				    (void *)set);
 }
 
 static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index ebf6e60..332c6af 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -72,17 +72,6 @@ out:
 	return false;
 }
 
-static void nft_rbtree_elem_destroy(const struct nft_set *set,
-				    struct nft_rbtree_elem *rbe)
-{
-	nft_data_uninit(nft_set_ext_key(&rbe->ext), NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP &&
-	    nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_DATA))
-		nft_data_uninit(nft_set_ext_data(&rbe->ext), set->dtype);
-
-	kfree(rbe);
-}
-
 static int __nft_rbtree_insert(const struct nft_set *set,
 			       struct nft_rbtree_elem *new)
 {
@@ -133,7 +122,6 @@ static void nft_rbtree_remove(const struct nft_set *set,
 	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)
@@ -213,7 +201,7 @@ 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);
 	}
 }
 
-- 
1.7.10.4

[PATCH 13/15] netfilter: nf_tables: return set extensions from ->lookup()

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Return the extension area from the ->lookup() function to allow to
consolidate common actions.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |    4 +++-
 net/netfilter/nft_hash.c          |    6 +++---
 net/netfilter/nft_lookup.c        |    6 +++++-
 net/netfilter/nft_rbtree.c        |    7 +++----
 4 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 6ac6332..f190d26 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -200,6 +200,8 @@ struct nft_set_estimate {
 	enum nft_set_class	class;
 };
 
+struct nft_set_ext;
+
 /**
  *	struct nft_set_ops - nf_tables set operations
  *
@@ -218,7 +220,7 @@ struct nft_set_estimate {
 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,
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 94bf25d..5bee821 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -66,7 +66,7 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
 
 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 nft_hash *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
@@ -76,8 +76,8 @@ static bool nft_hash_lookup(const struct nft_set *set,
 	};
 
 	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
-	if (he && set->flags & NFT_SET_MAP)
-		nft_data_copy(data, nft_set_ext_data(&he->ext));
+	if (he != NULL)
+		*ext = &he->ext;
 
 	return !!he;
 }
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 9615b8b..a5f30b8 100644
--- a/net/netfilter/nft_lookup.c
+++ b/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;
 }
 
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 332c6af..cbba755 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -31,7 +31,7 @@ struct nft_rbtree_elem {
 
 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;
@@ -55,10 +55,9 @@ found:
 			    *nft_set_ext_flags(&rbe->ext) &
 			    NFT_SET_ELEM_INTERVAL_END)
 				goto out;
-			if (set->flags & NFT_SET_MAP)
-				nft_data_copy(data, nft_set_ext_data(&rbe->ext));
-
 			spin_unlock_bh(&nft_rbtree_lock);
+
+			*ext = &rbe->ext;
 			return true;
 		}
 	}
-- 
1.7.10.4

[PATCH 14/15] netfilter: nf_tables: add transaction helper functions

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Add some helper functions for building the genmask as preparation for
set transactions.

Also add a little documentation how this stuff actually works.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |   28 ++++++++++++++++++++++++++++
 net/netfilter/nf_tables_api.c     |   17 ++++++-----------
 net/netfilter/nf_tables_core.c    |    6 +-----
 3 files changed, 35 insertions(+), 16 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index f190d26..4c46a32 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -720,6 +720,34 @@ 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);
+}
+
 /**
  *	struct nft_trans - nf_tables object update in transaction
  *
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b35512f..66fa5e9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/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;
-}
-
-static inline int gencursor_next(struct net *net)
-{
-	return net->nft.gencursor+1 == 1 ? 1 : 0;
+	return (rule->genmask & nft_genmask_cur(net)) == 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
@@ -3626,7 +3621,7 @@ 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.
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 4429008..ef4dfcb 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -121,11 +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;
-	/*
-	 * Cache cursor to avoid problems in case that the cursor is updated
-	 * while traversing the ruleset.
-	 */
-	unsigned int gencursor = ACCESS_ONCE(net->nft.gencursor);
+	unsigned int gencursor = nft_genmask_cur(net);
 
 do_chain:
 	rulenum = 0;
-- 
1.7.10.4

[PATCH 15/15] netfilter: nf_tables: implement set transaction support

[Pablo Neira Ayuso]

From: Patrick McHardy <kaber@trash.net>

Set elements are the last object type not supporting transaction support.
Implement similar to the existing rule transactions:

The global transaction counter keeps track of two generations, current
and next. Each element contains a bitmask specifying in which generations
it is inactive.

New elements start out as inactive in the current generation and active
in the next. On commit, the previous next generation becomes the current
generation and the element becomes active. The bitmask is then cleared
to indicate that the element is active in all future generations. If the
transaction is aborted, the element is removed from the set before it
becomes active.

When removing an element, it gets marked as inactive in the next generation.
On commit the next generation becomes active and the therefor the element
inactive. It is then taken out of then set and released. On abort, the
element is marked as active for the next generation again.

Lookups ignore elements not active in the current generation.

The current set types (hash/rbtree) both use a field in the extension area
to store the generation mask. This (currently) does not require any
additional memory since we have some free space in there.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |   33 +++++++++++++++++++------
 net/netfilter/nf_tables_api.c     |   33 +++++++++++++++----------
 net/netfilter/nft_hash.c          |   38 +++++++++++++++++++++--------
 net/netfilter/nft_rbtree.c        |   48 +++++++++++++++++++++++++++++--------
 4 files changed, 112 insertions(+), 40 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4c46a32..b8cd60d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -138,15 +138,10 @@ struct nft_userdata {
 /**
  *	struct nft_set_elem - generic representation of set elements
  *
- *	@cookie: implementation specific element cookie
  *	@key: element key
  *	@priv: element private data and extensions
- *
- *	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;
 	void			*priv;
 };
@@ -207,6 +202,8 @@ struct nft_set_ext;
  *
  *	@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
@@ -221,10 +218,12 @@ struct nft_set_ops {
 	bool				(*lookup)(const struct nft_set *set,
 						  const struct nft_data *key,
 						  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,
@@ -261,6 +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
@@ -277,6 +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;
@@ -355,10 +356,12 @@ struct nft_set_ext_tmpl {
 /**
  *	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];
 };
@@ -748,6 +751,22 @@ static inline u8 nft_genmask_cur(const struct net *net)
 	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
  *
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 66fa5e9..5604c2d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2690,6 +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;
@@ -3221,10 +3222,6 @@ 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;
-	if (set->ops->get(set, &elem) == 0)
-		goto err2;
-
 	nft_set_ext_add(&tmpl, NFT_SET_EXT_KEY);
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
@@ -3266,6 +3263,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (trans == NULL)
 		goto err4;
 
+	ext->genmask = nft_genmask_cur(ctx->net);
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
 		goto err5;
@@ -3353,19 +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:
@@ -3692,9 +3695,11 @@ 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,
-						 nft_trans_elem_set(trans),
-						 &nft_trans_elem(trans),
+			te = (struct nft_trans_elem *)trans->data;
+
+			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;
@@ -3704,7 +3709,6 @@ static int nf_tables_commit(struct sk_buff *skb)
 			nf_tables_setelem_notify(&trans->ctx, te->set,
 						 &te->elem,
 						 NFT_MSG_DELSETELEM, 0);
-			te->set->ops->get(te->set, &te->elem);
 			te->set->ops->remove(te->set, &te->elem);
 			break;
 		}
@@ -3812,11 +3816,14 @@ static int nf_tables_abort(struct sk_buff *skb)
 			nft_trans_elem_set(trans)->nelems--;
 			te = (struct nft_trans_elem *)trans->data;
 
-			te->set->ops->get(te->set, &te->elem);
 			te->set->ops->remove(te->set, &te->elem);
 			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;
 		}
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 5bee821..c7e1a9d 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -35,6 +35,7 @@ struct nft_hash_elem {
 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;
@@ -61,6 +62,8 @@ static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg,
 
 	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;
 }
 
@@ -71,6 +74,7 @@ static bool nft_hash_lookup(const struct nft_set *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,
 	};
@@ -88,6 +92,7 @@ static int nft_hash_insert(const struct nft_set *set,
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he = elem->priv;
 	struct nft_hash_cmp_arg arg = {
+		.genmask = nft_genmask_next(read_pnet(&set->pnet)),
 		.set	 = set,
 		.key	 = &elem->key,
 	};
@@ -96,30 +101,39 @@ static int nft_hash_insert(const struct nft_set *set,
 					    nft_hash_params);
 }
 
-static void nft_hash_remove(const struct nft_set *set,
-			    const struct nft_set_elem *elem)
+static void nft_hash_activate(const struct nft_set *set,
+			      const struct nft_set_elem *elem)
 {
-	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he = elem->priv;
 
-	rhashtable_remove_fast(&priv->ht, elem->cookie, nft_hash_params);
+	nft_set_elem_change_active(set, &he->ext);
 }
 
-static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
+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)
-		return -ENOENT;
+	if (he != NULL)
+		nft_set_elem_change_active(set, &he->ext);
 
-	elem->priv = he;
+	return he;
+}
 
-	return 0;
+static void nft_hash_remove(const struct nft_set *set,
+			    const struct nft_set_elem *elem)
+{
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he = elem->priv;
+
+	rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
 }
 
 static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
@@ -129,6 +143,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 	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->ht, &hti);
@@ -155,6 +170,8 @@ 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;
 
 		elem.priv = he;
 
@@ -241,8 +258,9 @@ static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.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,
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index cbba755..42d0ca4 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -29,6 +29,7 @@ struct nft_rbtree_elem {
 	struct nft_set_ext	ext;
 };
 
+
 static bool nft_rbtree_lookup(const struct nft_set *set,
 			      const struct nft_data *key,
 			      const struct nft_set_ext **ext)
@@ -36,6 +37,7 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 	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);
@@ -51,6 +53,10 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 			parent = parent->rb_right;
 		else {
 found:
+			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)
@@ -77,6 +83,7 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 	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;
@@ -91,8 +98,11 @@ static int __nft_rbtree_insert(const struct nft_set *set,
 			p = &parent->rb_left;
 		else if (d > 0)
 			p = &parent->rb_right;
-		else
-			return -EEXIST;
+		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);
@@ -116,18 +126,28 @@ 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);
 }
 
-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) {
@@ -140,12 +160,15 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 		else if (d > 0)
 			parent = parent->rb_right;
 		else {
-			elem->cookie = rbe;
-			elem->priv   = rbe;
-			return 0;
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
+				parent = parent->rb_left;
+				continue;
+			}
+			nft_set_elem_change_active(set, &rbe->ext);
+			return rbe;
 		}
 	}
-	return -ENOENT;
+	return NULL;
 }
 
 static void nft_rbtree_walk(const struct nft_ctx *ctx,
@@ -156,13 +179,17 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	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;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
@@ -228,7 +255,8 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.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,
-- 
1.7.10.4

Re: [PATCH 00/15] Netfilter updates for net-next

[David Miller]

From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 26 Mar 2015 13:06:47 +0100

> 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:
 ...
> You can pull these changes from:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git

Pulled, thanks Pablo.