Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter/IPVS updates for net-next,
most relevantly they are:

* cleanup to remove double semicolon from stephen hemminger.

* calm down sparse warning in xt_ipcomp, from Fan Du.

* nf_ct_labels support for nf_tables, from Florian Westphal.

* new macros to simplify rcu dereferences in the scope of nfnetlink
  and nf_tables, from Patrick McHardy.

* Accept queue and drop (including reason for drop) to verdict
  parsing in nf_tables, also from Patrick.

* Remove unused random seed initialization in nfnetlink_log, from
  Florian Westphal.

* Allow to attach user-specific information to nf_tables rules, useful
  to attach user comments to rule, from me.

* Return errors in ipset according to the manpage documentation, from
  Jozsef Kadlecsik.

* Fix coccinelle warnings related to incorrect bool type usage for ipset,
  from Fengguang Wu.

* Add hash:ip,mark set type to ipset, from Vytas Dauksa.

* Fix message for each spotted by ipset for each netns that is created,
  from Ilia Mirkin.

* Add forceadd option to ipset, which evicts a random entry from the set
  if it becomes full, from Josh Hunt.

* Minor IPVS cleanups and fixes from Andi Kleen and Tingwei Liu.

* Improve conntrack scalability by removing a central spinlock, original
  work from Eric Dumazet. Jesper Dangaard Brouer took them over to address
  remaining issues. Several patches to prepare this change come in first
  place.

* Rework nft_hash to resolve bugs (leaking chain, missing rcu synchronization
  on element removal, etc. from Patrick McHardy.

* Restore context in the rule deletion path, as we now release rule objects
  synchronously, from Patrick McHardy. This gets back event notification for
  anonymous sets.

* Fix NAT family validation in nft_nat, also from Patrick.

* Improve scalability of xt_connlimit by using an array of spinlocks and
  by introducing a rb-tree of hashtables for faster lookup of accounted
  objects per network. This patch was preceded by several patches and
  refactorizations to accomodate this change including the use of kmem_cache,
  from Florian Westphal.
====================

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

5 files changed, 47 insertions, 18 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index b2ac6246b7e..37252f71a38 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -73,10 +73,17 @@ struct nf_conn_help {
 
 struct nf_conn {
 	/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
-           plus 1 for any connection(s) we are `master' for */
+	 * plus 1 for any connection(s) we are `master' for
+	 *
+	 * Hint, SKB address this struct and refcnt via skb->nfct and
+	 * helpers nf_conntrack_get() and nf_conntrack_put().
+	 * Helper nf_ct_put() equals nf_conntrack_put() by dec refcnt,
+	 * beware nf_ct_get() is different and don't inc refcnt.
+	 */
 	struct nf_conntrack ct_general;
 
-	spinlock_t lock;
+	spinlock_t	lock;
+	u16		cpu;
 
 	/* XXX should I move this to the tail ? - Y.K */
 	/* These are my tuples; original and reply */
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 15308b8eb5b..cc0c1882760 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -77,6 +77,13 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *proto);
 
-extern spinlock_t nf_conntrack_lock ;
+#ifdef CONFIG_LOCKDEP
+# define CONNTRACK_LOCKS 8
+#else
+# define CONNTRACK_LOCKS 1024
+#endif
+extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+
+extern spinlock_t nf_conntrack_expect_lock;
 
 #endif /* _NF_CONNTRACK_CORE_H */
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index c985695283b..dec6336bf85 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -7,6 +7,8 @@
 
 #include <uapi/linux/netfilter/xt_connlabel.h>
 
+#define NF_CT_LABELS_MAX_SIZE ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE)
+
 struct nf_conn_labels {
 	u8 words;
 	unsigned long bits[];
@@ -29,7 +31,7 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct)
 	u8 words;
 
 	words = ACCESS_ONCE(net->ct.label_words);
-	if (words == 0 || WARN_ON_ONCE(words > 8))
+	if (words == 0)
 		return NULL;
 
 	cl_ext = nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e7e14ffe0f6..e6bc14d8fa9 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -3,6 +3,7 @@
 
 #include <linux/list.h>
 #include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netlink.h>
@@ -288,7 +289,8 @@ struct nft_expr_ops {
 	int				(*init)(const struct nft_ctx *ctx,
 						const struct nft_expr *expr,
 						const struct nlattr * const tb[]);
-	void				(*destroy)(const struct nft_expr *expr);
+	void				(*destroy)(const struct nft_ctx *ctx,
+						   const struct nft_expr *expr);
 	int				(*dump)(struct sk_buff *skb,
 						const struct nft_expr *expr);
 	int				(*validate)(const struct nft_ctx *ctx,
@@ -325,13 +327,15 @@ static inline void *nft_expr_priv(const struct nft_expr *expr)
  *	@handle: rule handle
  *	@genmask: generation mask
  *	@dlen: length of expression data
+ *	@ulen: length of user data (used for comments)
  *	@data: expression data
  */
 struct nft_rule {
 	struct list_head		list;
-	u64				handle:46,
+	u64				handle:42,
 					genmask:2,
-					dlen:16;
+					dlen:12,
+					ulen:8;
 	unsigned char			data[]
 		__attribute__((aligned(__alignof__(struct nft_expr))));
 };
@@ -340,19 +344,13 @@ struct nft_rule {
  *	struct nft_rule_trans - nf_tables rule update in transaction
  *
  *	@list: used internally
+ *	@ctx: rule context
  *	@rule: rule that needs to be updated
- *	@chain: chain that this rule belongs to
- *	@table: table for which this chain applies
- *	@nlh: netlink header of the message that contain this update
- *	@family: family expressesed as AF_*
  */
 struct nft_rule_trans {
 	struct list_head		list;
+	struct nft_ctx			ctx;
 	struct nft_rule			*rule;
-	const struct nft_chain		*chain;
-	const struct nft_table		*table;
-	const struct nlmsghdr		*nlh;
-	u8				family;
 };
 
 static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
@@ -370,6 +368,11 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule)
 	return (struct nft_expr *)&rule->data[rule->dlen];
 }
 
+static inline void *nft_userdata(const struct nft_rule *rule)
+{
+	return (void *)&rule->data[rule->dlen];
+}
+
 /*
  * The last pointer isn't really necessary, but the compiler isn't able to
  * determine that the result of nft_expr_last() is always the same since it
@@ -521,6 +524,9 @@ void nft_unregister_chain_type(const struct nf_chain_type *);
 int nft_register_expr(struct nft_expr_type *);
 void nft_unregister_expr(struct nft_expr_type *);
 
+#define nft_dereference(p)					\
+	nfnl_dereference(p, NFNL_SUBSYS_NFTABLES)
+
 #define MODULE_ALIAS_NFT_FAMILY(family)	\
 	MODULE_ALIAS("nft-afinfo-" __stringify(family))
 
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index fbcc7fa536d..773cce308bc 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -5,6 +5,7 @@
 #include <linux/list_nulls.h>
 #include <linux/atomic.h>
 #include <linux/netfilter/nf_conntrack_tcp.h>
+#include <linux/seqlock.h>
 
 struct ctl_table_header;
 struct nf_conntrack_ecache;
@@ -62,6 +63,13 @@ struct nf_ip_net {
 #endif
 };
 
+struct ct_pcpu {
+	spinlock_t		lock;
+	struct hlist_nulls_head unconfirmed;
+	struct hlist_nulls_head dying;
+	struct hlist_nulls_head tmpl;
+};
+
 struct netns_ct {
 	atomic_t		count;
 	unsigned int		expect_count;
@@ -83,12 +91,11 @@ struct netns_ct {
 	int			sysctl_checksum;
 
 	unsigned int		htable_size;
+	seqcount_t		generation;
 	struct kmem_cache	*nf_conntrack_cachep;
 	struct hlist_nulls_head	*hash;
 	struct hlist_head	*expect_hash;
-	struct hlist_nulls_head	unconfirmed;
-	struct hlist_nulls_head	dying;
-	struct hlist_nulls_head tmpl;
+	struct ct_pcpu __percpu *pcpu_lists;
 	struct ip_conntrack_stat __percpu *stat;
 	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
 	struct nf_exp_event_notifier __rcu *nf_expect_event_cb;