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

Pablo Neira Ayuso says:

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

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

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

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

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

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

5) Use raw_smp_processor_id() in nft_meta.

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

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

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

8) Another small source code readability cleanup for nft_hash.

9) Convert nft_hash to rhashtable callbacks.

And finally...

10) Add the new set extension infrastructure.

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

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

13) Return the set extension data area from nft_lookup.

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

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

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

include/linux/rhashtable.h

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

include/net/netfilter/nf_tables.h

@@ -138,19 +138,12 @@ struct nft_userdata {
 /**
  *	struct nft_set_elem - generic representation of set elements
  *
- *	@cookie: implementation specific element cookie
  *	@key: element key
- *	@data: element data (maps only)
- *	@flags: element flags (end of interval)
- *
- *	The cookie can be used to store a handle to the element for subsequent
- *	removal.
+ *	@priv: element private data and extensions
  */
 struct nft_set_elem {
-	void			*cookie;
 	struct nft_data		key;
-	struct nft_data		data;
-	u32			flags;
+	void			*priv;
 };
 
 struct nft_set;
@@ -202,28 +195,35 @@ struct nft_set_estimate {
 	enum nft_set_class	class;
 };
 
+struct nft_set_ext;
+
 /**
  *	struct nft_set_ops - nf_tables set operations
  *
  *	@lookup: look up an element within the set
  *	@insert: insert new element into set
+ *	@activate: activate new element in the next generation
+ *	@deactivate: deactivate element in the next generation
  *	@remove: remove element from set
  *	@walk: iterate over all set elemeennts
  *	@privsize: function to return size of set private data
  *	@init: initialize private data of new set instance
  *	@destroy: destroy private data of set instance
  *	@list: nf_tables_set_ops list node
  *	@owner: module reference
+ *	@elemsize: element private size
  *	@features: features supported by the implementation
  */
 struct nft_set_ops {
 	bool				(*lookup)(const struct nft_set *set,
 						  const struct nft_data *key,
-						  struct nft_data *data);
-	int				(*get)(const struct nft_set *set,
-					       struct nft_set_elem *elem);
+						  const struct nft_set_ext **ext);
 	int				(*insert)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
+	void				(*activate)(const struct nft_set *set,
+						    const struct nft_set_elem *elem);
+	void *				(*deactivate)(const struct nft_set *set,
+						      const struct nft_set_elem *elem);
 	void				(*remove)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
 	void				(*walk)(const struct nft_ctx *ctx,
@@ -241,6 +241,7 @@ struct nft_set_ops {
 
 	struct list_head		list;
 	struct module			*owner;
+	unsigned int			elemsize;
 	u32				features;
 };
 
@@ -259,6 +260,7 @@ void nft_unregister_set(struct nft_set_ops *ops);
  * 	@nelems: number of elements
  *	@policy: set parameterization (see enum nft_set_policies)
  * 	@ops: set ops
+ * 	@pnet: network namespace
  * 	@flags: set flags
  * 	@klen: key length
  * 	@dlen: data length
@@ -275,6 +277,7 @@ struct nft_set {
 	u16				policy;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
+	possible_net_t			pnet;
 	u16				flags;
 	u8				klen;
 	u8				dlen;
@@ -311,6 +314,121 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_binding *binding);
 
+/**
+ *	enum nft_set_extensions - set extension type IDs
+ *
+ *	@NFT_SET_EXT_KEY: element key
+ *	@NFT_SET_EXT_DATA: mapping data
+ *	@NFT_SET_EXT_FLAGS: element flags
+ *	@NFT_SET_EXT_NUM: number of extension types
+ */
+enum nft_set_extensions {
+	NFT_SET_EXT_KEY,
+	NFT_SET_EXT_DATA,
+	NFT_SET_EXT_FLAGS,
+	NFT_SET_EXT_NUM
+};
+
+/**
+ *	struct nft_set_ext_type - set extension type
+ *
+ * 	@len: fixed part length of the extension
+ * 	@align: alignment requirements of the extension
+ */
+struct nft_set_ext_type {
+	u8	len;
+	u8	align;
+};
+
+extern const struct nft_set_ext_type nft_set_ext_types[];
+
+/**
+ *	struct nft_set_ext_tmpl - set extension template
+ *
+ *	@len: length of extension area
+ *	@offset: offsets of individual extension types
+ */
+struct nft_set_ext_tmpl {
+	u16	len;
+	u8	offset[NFT_SET_EXT_NUM];
+};
+
+/**
+ *	struct nft_set_ext - set extensions
+ *
+ *	@genmask: generation mask
+ *	@offset: offsets of individual extension types
+ *	@data: beginning of extension data
+ */
+struct nft_set_ext {
+	u8	genmask;
+	u8	offset[NFT_SET_EXT_NUM];
+	char	data[0];
+};
+
+static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
+{
+	memset(tmpl, 0, sizeof(*tmpl));
+	tmpl->len = sizeof(struct nft_set_ext);
+}
+
+static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id,
+					  unsigned int len)
+{
+	tmpl->len	 = ALIGN(tmpl->len, nft_set_ext_types[id].align);
+	BUG_ON(tmpl->len > U8_MAX);
+	tmpl->offset[id] = tmpl->len;
+	tmpl->len	+= nft_set_ext_types[id].len + len;
+}
+
+static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id)
+{
+	nft_set_ext_add_length(tmpl, id, 0);
+}
+
+static inline void nft_set_ext_init(struct nft_set_ext *ext,
+				    const struct nft_set_ext_tmpl *tmpl)
+{
+	memcpy(ext->offset, tmpl->offset, sizeof(ext->offset));
+}
+
+static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
+{
+	return !!ext->offset[id];
+}
+
+static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
+{
+	return ext && __nft_set_ext_exists(ext, id);
+}
+
+static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id)
+{
+	return (void *)ext + ext->offset[id];
+}
+
+static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_KEY);
+}
+
+static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_DATA);
+}
+
+static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
+}
+
+static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
+						   void *elem)
+{
+	return elem + set->ops->elemsize;
+}
+
+void nft_set_elem_destroy(const struct nft_set *set, void *elem);
 
 /**
  *	struct nft_expr_type - nf_tables expression type
@@ -449,7 +567,6 @@ enum nft_chain_flags {
  *
  *	@rules: list of rules in the chain
  *	@list: used internally
- *	@net: net namespace that this chain belongs to
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
@@ -460,7 +577,6 @@ enum nft_chain_flags {
 struct nft_chain {
 	struct list_head		rules;
 	struct list_head		list;
-	struct net			*net;
 	struct nft_table		*table;
 	u64				handle;
 	u32				use;
@@ -512,13 +628,15 @@ 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
  *	@chain: the chain
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops[NFT_HOOK_OPS_MAX];
+	possible_net_t			pnet;
 	const struct nf_chain_type	*type;
 	u8				policy;
 	struct nft_stats __percpu	*stats;
@@ -605,6 +723,50 @@ void nft_unregister_expr(struct nft_expr_type *);
 #define MODULE_ALIAS_NFT_SET() \
 	MODULE_ALIAS("nft-set")
 
+/*
+ * The gencursor defines two generations, the currently active and the
+ * next one. Objects contain a bitmask of 2 bits specifying the generations
+ * they're active in. A set bit means they're inactive in the generation
+ * represented by that bit.
+ *
+ * New objects start out as inactive in the current and active in the
+ * next generation. When committing the ruleset the bitmask is cleared,
+ * meaning they're active in all generations. When removing an object,
+ * it is set inactive in the next generation. After committing the ruleset,
+ * the objects are removed.
+ */
+static inline unsigned int nft_gencursor_next(const struct net *net)
+{
+	return net->nft.gencursor + 1 == 1 ? 1 : 0;
+}
+
+static inline u8 nft_genmask_next(const struct net *net)
+{
+	return 1 << nft_gencursor_next(net);
+}
+
+static inline u8 nft_genmask_cur(const struct net *net)
+{
+	/* Use ACCESS_ONCE() to prevent refetching the value for atomicity */
+	return 1 << ACCESS_ONCE(net->nft.gencursor);
+}
+
+/*
+ * Set element transaction helpers
+ */
+
+static inline bool nft_set_elem_active(const struct nft_set_ext *ext,
+				       u8 genmask)
+{
+	return !(ext->genmask & genmask);
+}
+
+static inline void nft_set_elem_change_active(const struct nft_set *set,
+					      struct nft_set_ext *ext)
+{
+	ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet));
+}
+
 /**
  *	struct nft_trans - nf_tables object update in transaction
  *

lib/rhashtable.c

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

net/ipv4/netfilter/nf_log_arp.c

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

net/ipv4/netfilter/nf_log_ipv4.c

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

net/ipv6/netfilter/ip6_tables.c

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

net/ipv6/netfilter/nf_log_ipv6.c

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