From 5cb82a38c6b5152b1deaba0c1596ce63222a4710 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Jan 2017 18:30:07 +0100
Subject: netfilter: nf_tables: pass netns to set->ops->remove()

This new parameter is required by the new bitmap set type that comes in a
follow up patch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 7dfdb517f0be..a721bcb1210c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -298,7 +298,8 @@ struct nft_set_ops {
 	bool				(*deactivate_one)(const struct net *net,
 							  const struct nft_set *set,
 							  void *priv);
-	void				(*remove)(const struct nft_set *set,
+	void				(*remove)(const struct net *net,
+						  const struct nft_set *set,
 						  const struct nft_set_elem *elem);
 	void				(*walk)(const struct nft_ctx *ctx,
 						struct nft_set *set,
-- 
cgit v1.2.3-70-g09d2


From 1ba1c41408df8a9d2f8b9b67e4c9e6f59b29d8ee Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Jan 2017 18:30:09 +0100
Subject: netfilter: nf_tables: rename deactivate_one() to flush()

Although semantics are similar to deactivate() with no implicit element
lookup, this is only called from the set flush path, so better rename
this to flush().

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 8 ++++----
 net/netfilter/nf_tables_api.c     | 2 +-
 net/netfilter/nft_set_hash.c      | 8 ++++----
 net/netfilter/nft_set_rbtree.c    | 8 ++++----
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index a721bcb1210c..ab155644d489 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -260,7 +260,7 @@ struct nft_expr;
  *	@insert: insert new element into set
  *	@activate: activate new element in the next generation
  *	@deactivate: lookup for element and deactivate it in the next generation
- *	@deactivate_one: deactivate element in the next generation
+ *	@flush: 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
@@ -295,9 +295,9 @@ struct nft_set_ops {
 	void *				(*deactivate)(const struct net *net,
 						      const struct nft_set *set,
 						      const struct nft_set_elem *elem);
-	bool				(*deactivate_one)(const struct net *net,
-							  const struct nft_set *set,
-							  void *priv);
+	bool				(*flush)(const struct net *net,
+						 const struct nft_set *set,
+						 void *priv);
 	void				(*remove)(const struct net *net,
 						  const struct nft_set *set,
 						  const struct nft_set_elem *elem);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 790ffed82930..c09b11eb36fc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3898,7 +3898,7 @@ static int nft_flush_set(const struct nft_ctx *ctx,
 	if (!trans)
 		return -ENOMEM;
 
-	if (!set->ops->deactivate_one(ctx->net, set, elem->priv)) {
+	if (!set->ops->flush(ctx->net, set, elem->priv)) {
 		err = -ENOENT;
 		goto err1;
 	}
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index bb157bd47fe8..2f10ac3b1b10 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -167,8 +167,8 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set,
 	nft_set_elem_clear_busy(&he->ext);
 }
 
-static bool nft_hash_deactivate_one(const struct net *net,
-				    const struct nft_set *set, void *priv)
+static bool nft_hash_flush(const struct net *net,
+			   const struct nft_set *set, void *priv)
 {
 	struct nft_hash_elem *he = priv;
 
@@ -195,7 +195,7 @@ static void *nft_hash_deactivate(const struct net *net,
 	rcu_read_lock();
 	he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params);
 	if (he != NULL &&
-	    !nft_hash_deactivate_one(net, set, he))
+	    !nft_hash_flush(net, set, he))
 		he = NULL;
 
 	rcu_read_unlock();
@@ -398,7 +398,7 @@ static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.insert		= nft_hash_insert,
 	.activate	= nft_hash_activate,
 	.deactivate	= nft_hash_deactivate,
-	.deactivate_one	= nft_hash_deactivate_one,
+	.flush		= nft_hash_flush,
 	.remove		= nft_hash_remove,
 	.lookup		= nft_hash_lookup,
 	.update		= nft_hash_update,
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 9fbd70da1633..81b8a4c2c061 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -172,8 +172,8 @@ static void nft_rbtree_activate(const struct net *net,
 	nft_set_elem_change_active(net, set, &rbe->ext);
 }
 
-static bool nft_rbtree_deactivate_one(const struct net *net,
-				      const struct nft_set *set, void *priv)
+static bool nft_rbtree_flush(const struct net *net,
+			     const struct nft_set *set, void *priv)
 {
 	struct nft_rbtree_elem *rbe = priv;
 
@@ -214,7 +214,7 @@ static void *nft_rbtree_deactivate(const struct net *net,
 				parent = parent->rb_right;
 				continue;
 			}
-			nft_rbtree_deactivate_one(net, set, rbe);
+			nft_rbtree_flush(net, set, rbe);
 			return rbe;
 		}
 	}
@@ -305,7 +305,7 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.insert		= nft_rbtree_insert,
 	.remove		= nft_rbtree_remove,
 	.deactivate	= nft_rbtree_deactivate,
-	.deactivate_one	= nft_rbtree_deactivate_one,
+	.flush		= nft_rbtree_flush,
 	.activate	= nft_rbtree_activate,
 	.lookup		= nft_rbtree_lookup,
 	.walk		= nft_rbtree_walk,
-- 
cgit v1.2.3-70-g09d2


From 1f48ff6c5393aa7fe290faf5d633164f105b0aa7 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Jan 2017 18:30:10 +0100
Subject: netfilter: nf_tables: add flush field to struct nft_set_iter

This provides context to walk callback iterator, thus, we know if the
walk happens from the set flush path. This is required by the new bitmap
set type coming in a follow up patch which has no real struct
nft_set_ext, so it has to allocate it based on the two bit compact
element representation.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 1 +
 net/netfilter/nf_tables_api.c     | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ab155644d489..5830f594842e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -203,6 +203,7 @@ struct nft_set_elem {
 struct nft_set;
 struct nft_set_iter {
 	u8		genmask;
+	bool		flush;
 	unsigned int	count;
 	unsigned int	skip;
 	int		err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c09b11eb36fc..7ae810b03462 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3121,6 +3121,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		iter.count	= 0;
 		iter.err	= 0;
 		iter.fn		= nf_tables_bind_check_setelem;
+		iter.flush	= false;
 
 		set->ops->walk(ctx, set, &iter);
 		if (iter.err < 0)
@@ -3374,6 +3375,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	args.iter.count		= 0;
 	args.iter.err		= 0;
 	args.iter.fn		= nf_tables_dump_setelem;
+	args.iter.flush		= false;
 	set->ops->walk(&ctx, set, &args.iter);
 
 	nla_nest_end(skb, nest);
@@ -3939,6 +3941,7 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
 		struct nft_set_iter iter = {
 			.genmask	= genmask,
 			.fn		= nft_flush_set,
+			.flush		= true,
 		};
 		set->ops->walk(&ctx, set, &iter);
 
@@ -5089,6 +5092,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 			iter.count	= 0;
 			iter.err	= 0;
 			iter.fn		= nf_tables_loop_check_setelem;
+			iter.flush	= false;
 
 			set->ops->walk(ctx, set, &iter);
 			if (iter.err < 0)
-- 
cgit v1.2.3-70-g09d2


From 55af753cd9fda9c5300f5318253b08bd15fb412e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Jan 2017 18:30:11 +0100
Subject: netfilter: nf_tables: rename struct nft_set_estimate class field

Use lookup as field name instead, to prepare the introduction of the
memory class in a follow up patch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  4 ++--
 net/netfilter/nf_tables_api.c     | 12 ++++++------
 net/netfilter/nft_set_hash.c      |  2 +-
 net/netfilter/nft_set_rbtree.c    |  2 +-
 4 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 5830f594842e..d76ac2f80a40 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -244,11 +244,11 @@ enum nft_set_class {
  *				  characteristics
  *
  *	@size: required memory
- *	@class: lookup performance class
+ *	@lookup: lookup performance class
  */
 struct nft_set_estimate {
 	unsigned int		size;
-	enum nft_set_class	class;
+	enum nft_set_class	lookup;
 };
 
 struct nft_set_ext;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 7ae810b03462..fa7cd1679079 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2401,9 +2401,9 @@ nft_select_set_ops(const struct nlattr * const nla[],
 		features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT;
 	}
 
-	bops	   = NULL;
-	best.size  = ~0;
-	best.class = ~0;
+	bops	    = NULL;
+	best.size   = ~0;
+	best.lookup = ~0;
 
 	list_for_each_entry(ops, &nf_tables_set_ops, list) {
 		if ((ops->features & features) != features)
@@ -2413,15 +2413,15 @@ nft_select_set_ops(const struct nlattr * const nla[],
 
 		switch (policy) {
 		case NFT_SET_POL_PERFORMANCE:
-			if (est.class < best.class)
+			if (est.lookup < best.lookup)
 				break;
-			if (est.class == best.class && est.size < best.size)
+			if (est.lookup == best.lookup && est.size < best.size)
 				break;
 			continue;
 		case NFT_SET_POL_MEMORY:
 			if (est.size < best.size)
 				break;
-			if (est.size == best.size && est.class < best.class)
+			if (est.size == best.size && est.lookup < best.lookup)
 				break;
 			continue;
 		default:
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 2f10ac3b1b10..e58e7f02138b 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -384,7 +384,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 		est->size = esize + 2 * sizeof(struct nft_hash_elem *);
 	}
 
-	est->class = NFT_SET_CLASS_O_1;
+	est->lookup = NFT_SET_CLASS_O_1;
 
 	return true;
 }
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 81b8a4c2c061..2b6ea10c4bbd 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -291,7 +291,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 	else
 		est->size = nsize;
 
-	est->class = NFT_SET_CLASS_O_LOG_N;
+	est->lookup = NFT_SET_CLASS_O_LOG_N;
 
 	return true;
 }
-- 
cgit v1.2.3-70-g09d2


From 0b5a78749260560f41e3b7c1f60f2c7dd9aff4f0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 18 Jan 2017 18:30:12 +0100
Subject: netfilter: nf_tables: add space notation to sets

The space notation allows us to classify the set backend implementation
based on the amount of required memory. This provides an order of the
set representation scalability in terms of memory. The size field is
still left in place so use this if the userspace provides no explicit
number of elements, so we cannot calculate the real memory that this set
needs. This also helps us break ties in the set backend selection
routine, eg. two backend implementations provide the same performance.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 22 +++++++++++++++++-----
 net/netfilter/nft_set_hash.c      |  1 +
 net/netfilter/nft_set_rbtree.c    |  1 +
 4 files changed, 21 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index d76ac2f80a40..21ce50e6d0c5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -245,10 +245,12 @@ enum nft_set_class {
  *
  *	@size: required memory
  *	@lookup: lookup performance class
+ *	@space: memory class
  */
 struct nft_set_estimate {
 	unsigned int		size;
 	enum nft_set_class	lookup;
+	enum nft_set_class	space;
 };
 
 struct nft_set_ext;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fa7cd1679079..cb6ae46f6c48 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2404,6 +2404,7 @@ nft_select_set_ops(const struct nlattr * const nla[],
 	bops	    = NULL;
 	best.size   = ~0;
 	best.lookup = ~0;
+	best.space  = ~0;
 
 	list_for_each_entry(ops, &nf_tables_set_ops, list) {
 		if ((ops->features & features) != features)
@@ -2415,14 +2416,25 @@ nft_select_set_ops(const struct nlattr * const nla[],
 		case NFT_SET_POL_PERFORMANCE:
 			if (est.lookup < best.lookup)
 				break;
-			if (est.lookup == best.lookup && est.size < best.size)
-				break;
+			if (est.lookup == best.lookup) {
+				if (!desc->size) {
+					if (est.space < best.space)
+						break;
+				} else if (est.size < best.size) {
+					break;
+				}
+			}
 			continue;
 		case NFT_SET_POL_MEMORY:
-			if (est.size < best.size)
-				break;
-			if (est.size == best.size && est.lookup < best.lookup)
+			if (!desc->size) {
+				if (est.space < best.space)
+					break;
+				if (est.space == best.space &&
+				    est.lookup < best.lookup)
+					break;
+			} else if (est.size < best.size) {
 				break;
+			}
 			continue;
 		default:
 			break;
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index e58e7f02138b..6938bc890f31 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -385,6 +385,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
 	}
 
 	est->lookup = NFT_SET_CLASS_O_1;
+	est->space  = NFT_SET_CLASS_O_N;
 
 	return true;
 }
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2b6ea10c4bbd..3387ed7dd231 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -292,6 +292,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 		est->size = nsize;
 
 	est->lookup = NFT_SET_CLASS_O_LOG_N;
+	est->space  = NFT_SET_CLASS_O_N;
 
 	return true;
 }
-- 
cgit v1.2.3-70-g09d2


From 1a94e38d254b3622d5d53f74b3b716b0fcab0ba8 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 10 Feb 2017 12:08:23 +0100
Subject: netfilter: nf_tables: add NFTA_RULE_ID attribute

This new attribute allows us to uniquely identify a rule in transaction.
Robots may trigger an insertion followed by deletion in a batch, in that
scenario we still don't have a public rule handle that we can use to
delete the rule. This is similar to the NFTA_SET_ID attribute that
allows us to refer to an anonymous set from a batch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  3 +++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 26 ++++++++++++++++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 21ce50e6d0c5..ac84686aaafb 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1202,10 +1202,13 @@ struct nft_trans {
 
 struct nft_trans_rule {
 	struct nft_rule			*rule;
+	u32				rule_id;
 };
 
 #define nft_trans_rule(trans)	\
 	(((struct nft_trans_rule *)trans->data)->rule)
+#define nft_trans_rule_id(trans)	\
+	(((struct nft_trans_rule *)trans->data)->rule_id)
 
 struct nft_trans_set {
 	struct nft_set			*set;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 207951516ede..05215d30fe5c 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -207,6 +207,7 @@ enum nft_chain_attributes {
  * @NFTA_RULE_COMPAT: compatibility specifications of the rule (NLA_NESTED: nft_rule_compat_attributes)
  * @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64)
  * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN)
+ * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32)
  */
 enum nft_rule_attributes {
 	NFTA_RULE_UNSPEC,
@@ -218,6 +219,7 @@ enum nft_rule_attributes {
 	NFTA_RULE_POSITION,
 	NFTA_RULE_USERDATA,
 	NFTA_RULE_PAD,
+	NFTA_RULE_ID,
 	__NFTA_RULE_MAX
 };
 #define NFTA_RULE_MAX		(__NFTA_RULE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 71c60a04b66b..6c782532615f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -240,6 +240,10 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type,
 	if (trans == NULL)
 		return NULL;
 
+	if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) {
+		nft_trans_rule_id(trans) =
+			ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID]));
+	}
 	nft_trans_rule(trans) = rule;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
@@ -2293,6 +2297,22 @@ err1:
 	return err;
 }
 
+static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
+					     const struct nlattr *nla)
+{
+	u32 id = ntohl(nla_get_be32(nla));
+	struct nft_trans *trans;
+
+	list_for_each_entry(trans, &net->nft.commit_list, list) {
+		struct nft_rule *rule = nft_trans_rule(trans);
+
+		if (trans->msg_type == NFT_MSG_NEWRULE &&
+		    id == nft_trans_rule_id(trans))
+			return rule;
+	}
+	return ERR_PTR(-ENOENT);
+}
+
 static int nf_tables_delrule(struct net *net, struct sock *nlsk,
 			     struct sk_buff *skb, const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
@@ -2330,6 +2350,12 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
 			if (IS_ERR(rule))
 				return PTR_ERR(rule);
 
+			err = nft_delrule(&ctx, rule);
+		} else if (nla[NFTA_RULE_ID]) {
+			rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
+			if (IS_ERR(rule))
+				return PTR_ERR(rule);
+
 			err = nft_delrule(&ctx, rule);
 		} else {
 			err = nft_delrule_by_chain(&ctx);
-- 
cgit v1.2.3-70-g09d2