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

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains a large batch with Netfilter fixes for
your net tree, they are:

1) Two patches to solve conntrack garbage collector cpu hogging, one to
   remove GC_MAX_EVICTS and another to look at the ratio (scanned entries
   vs. evicted entries) to make a decision on whether to reduce or not
   the scanning interval. From Florian Westphal.

2) Two patches to fix incorrect set element counting if NLM_F_EXCL is
   is not set. Moreover, don't decrenent set->nelems from abort patch
   if -ENFILE which leaks a spare slot in the set. This includes a
   patch to deconstify the set walk callback to update set->ndeact.

3) Two fixes for the fwmark_reflect sysctl feature: Propagate mark to
   reply packets both from nf_reject and local stack, from Pau Espin Pedrol.

4) Fix incorrect handling of loopback traffic in rpfilter and nf_tables
   fib expression, from Liping Zhang.

5) Fix oops on stateful objects netlink dump, when no filter is specified.
   Also from Liping Zhang.

6) Fix a build error if proc is not available in ipt_CLUSTERIP, related
   to fix that was applied in the previous batch for net. From Arnd Bergmann.

7) Fix lack of string validation in table, chain, set and stateful
   object names in nf_tables, from Liping Zhang. Moreover, restrict
   maximum log prefix length to 127 bytes, otherwise explicitly bail
   out.

8) Two patches to fix spelling and typos in nf_tables uapi header file
   and Kconfig, patches from Alexander Alemayhu and William Breathitt Gray.
====================

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

10 files changed, 73 insertions, 60 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 63729b489c2c..bbc45f8a7b2d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -494,7 +494,7 @@ config NFT_CT
 	depends on NF_CONNTRACK
 	tristate "Netfilter nf_tables conntrack module"
 	help
-	  This option adds the "meta" expression that you can use to match
+	  This option adds the "ct" expression that you can use to match
 	  connection tracking information such as the flow state.
 
 config NFT_SET_RBTREE
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3a073cd9fcf4..4e8083c5e01d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -85,11 +85,11 @@ static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
 static __read_mostly bool nf_conntrack_locks_all;
 
 /* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
-#define GC_MAX_BUCKETS_DIV	64u
-/* upper bound of scan intervals */
-#define GC_INTERVAL_MAX		(2 * HZ)
-/* maximum conntracks to evict per gc run */
-#define GC_MAX_EVICTS		256u
+#define GC_MAX_BUCKETS_DIV	128u
+/* upper bound of full table scan */
+#define GC_MAX_SCAN_JIFFIES	(16u * HZ)
+/* desired ratio of entries found to be expired */
+#define GC_EVICT_RATIO	50u
 
 static struct conntrack_gc_work conntrack_gc_work;
 
@@ -938,6 +938,7 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 
 static void gc_worker(struct work_struct *work)
 {
+	unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
 	unsigned int i, goal, buckets = 0, expired_count = 0;
 	struct conntrack_gc_work *gc_work;
 	unsigned int ratio, scanned = 0;
@@ -979,8 +980,7 @@ static void gc_worker(struct work_struct *work)
 		 */
 		rcu_read_unlock();
 		cond_resched_rcu_qs();
-	} while (++buckets < goal &&
-		 expired_count < GC_MAX_EVICTS);
+	} while (++buckets < goal);
 
 	if (gc_work->exiting)
 		return;
@@ -997,27 +997,25 @@ static void gc_worker(struct work_struct *work)
 	 * 1. Minimize time until we notice a stale entry
 	 * 2. Maximize scan intervals to not waste cycles
 	 *
-	 * Normally, expired_count will be 0, this increases the next_run time
-	 * to priorize 2) above.
+	 * Normally, expire ratio will be close to 0.
 	 *
-	 * As soon as a timed-out entry is found, move towards 1) and increase
-	 * the scan frequency.
-	 * In case we have lots of evictions next scan is done immediately.
+	 * As soon as a sizeable fraction of the entries have expired
+	 * increase scan frequency.
 	 */
 	ratio = scanned ? expired_count * 100 / scanned : 0;
-	if (ratio >= 90 || expired_count == GC_MAX_EVICTS) {
-		gc_work->next_gc_run = 0;
-		next_run = 0;
-	} else if (expired_count) {
-		gc_work->next_gc_run /= 2U;
-		next_run = msecs_to_jiffies(1);
+	if (ratio > GC_EVICT_RATIO) {
+		gc_work->next_gc_run = min_interval;
 	} else {
-		if (gc_work->next_gc_run < GC_INTERVAL_MAX)
-			gc_work->next_gc_run += msecs_to_jiffies(1);
+		unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;
 
-		next_run = gc_work->next_gc_run;
+		BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
+
+		gc_work->next_gc_run += min_interval;
+		if (gc_work->next_gc_run > max)
+			gc_work->next_gc_run = max;
 	}
 
+	next_run = gc_work->next_gc_run;
 	gc_work->last_bucket = i;
 	queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
 }
@@ -1025,7 +1023,7 @@ static void gc_worker(struct work_struct *work)
 static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
 {
 	INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
-	gc_work->next_gc_run = GC_INTERVAL_MAX;
+	gc_work->next_gc_run = HZ;
 	gc_work->exiting = false;
 }
 
@@ -1917,7 +1915,7 @@ int nf_conntrack_init_start(void)
 	nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
 
 	conntrack_gc_work_init(&conntrack_gc_work);
-	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX);
+	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
 
 	return 0;
 
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 3dca90dc24ad..ffb9e8ada899 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -13,7 +13,6 @@
 /* Internal logging interface, which relies on the real
    LOG target modules */
 
-#define NF_LOG_PREFIXLEN		128
 #define NFLOGGER_NAME_LEN		64
 
 static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0db5f9782265..1b913760f205 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -928,7 +928,8 @@ static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
 }
 
 static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
-	[NFTA_CHAIN_TABLE]	= { .type = NLA_STRING },
+	[NFTA_CHAIN_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HANDLE]	= { .type = NLA_U64 },
 	[NFTA_CHAIN_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
@@ -1854,7 +1855,8 @@ static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
 }
 
 static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
-	[NFTA_RULE_TABLE]	= { .type = NLA_STRING },
+	[NFTA_RULE_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_RULE_CHAIN]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_RULE_HANDLE]	= { .type = NLA_U64 },
@@ -2443,7 +2445,8 @@ nft_select_set_ops(const struct nlattr * const nla[],
 }
 
 static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
-	[NFTA_SET_TABLE]		= { .type = NLA_STRING },
+	[NFTA_SET_TABLE]		= { .type = NLA_STRING,
+					    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_SET_NAME]			= { .type = NLA_STRING,
 					    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_SET_FLAGS]		= { .type = NLA_U32 },
@@ -3084,9 +3087,9 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
 }
 
 static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
-					const struct nft_set *set,
+					struct nft_set *set,
 					const struct nft_set_iter *iter,
-					const struct nft_set_elem *elem)
+					struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	enum nft_registers dreg;
@@ -3192,8 +3195,10 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
-	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING },
-	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING },
+	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING,
+					    .len = NFT_TABLE_MAXNAMELEN - 1 },
+	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING,
+					    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_SET_ELEM_LIST_ELEMENTS]	= { .type = NLA_NESTED },
 	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
@@ -3303,9 +3308,9 @@ struct nft_set_dump_args {
 };
 
 static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
-				  const struct nft_set *set,
+				  struct nft_set *set,
 				  const struct nft_set_iter *iter,
-				  const struct nft_set_elem *elem)
+				  struct nft_set_elem *elem)
 {
 	struct nft_set_dump_args *args;
 
@@ -3317,7 +3322,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
 	u8 genmask = nft_genmask_cur(net);
-	const struct nft_set *set;
+	struct nft_set *set;
 	struct nft_set_dump_args args;
 	struct nft_ctx ctx;
 	struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1];
@@ -3740,10 +3745,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err5;
 	}
 
+	if (set->size &&
+	    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
+		err = -ENFILE;
+		goto err6;
+	}
+
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
+err6:
+	set->ops->remove(set, &elem);
 err5:
 	kfree(trans);
 err4:
@@ -3790,15 +3803,9 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
 		return -EBUSY;
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		if (set->size &&
-		    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
-			return -ENFILE;
-
 		err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags);
-		if (err < 0) {
-			atomic_dec(&set->nelems);
+		if (err < 0)
 			break;
-		}
 	}
 	return err;
 }
@@ -3883,9 +3890,9 @@ err1:
 }
 
 static int nft_flush_set(const struct nft_ctx *ctx,
-			 const struct nft_set *set,
+			 struct nft_set *set,
 			 const struct nft_set_iter *iter,
-			 const struct nft_set_elem *elem)
+			 struct nft_set_elem *elem)
 {
 	struct nft_trans *trans;
 	int err;
@@ -3899,9 +3906,10 @@ static int nft_flush_set(const struct nft_ctx *ctx,
 		err = -ENOENT;
 		goto err1;
 	}
+	set->ndeact++;
 
-	nft_trans_elem_set(trans) = (struct nft_set *)set;
-	nft_trans_elem(trans) = *((struct nft_set_elem *)elem);
+	nft_trans_elem_set(trans) = set;
+	nft_trans_elem(trans) = *elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	return 0;
@@ -4032,8 +4040,10 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
 EXPORT_SYMBOL_GPL(nf_tables_obj_lookup);
 
 static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
-	[NFTA_OBJ_TABLE]	= { .type = NLA_STRING },
-	[NFTA_OBJ_NAME]		= { .type = NLA_STRING },
+	[NFTA_OBJ_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
+	[NFTA_OBJ_NAME]		= { .type = NLA_STRING,
+				    .len = NFT_OBJ_MAXNAMELEN - 1 },
 	[NFTA_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 };
@@ -4262,10 +4272,11 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 				if (idx > s_idx)
 					memset(&cb->args[1], 0,
 					       sizeof(cb->args) - sizeof(cb->args[0]));
-				if (filter->table[0] &&
+				if (filter && filter->table[0] &&
 				    strcmp(filter->table, table->name))
 					goto cont;
-				if (filter->type != NFT_OBJECT_UNSPEC &&
+				if (filter &&
+				    filter->type != NFT_OBJECT_UNSPEC &&
 				    obj->type->type != filter->type)
 					goto cont;
 
@@ -5009,9 +5020,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 				 const struct nft_chain *chain);
 
 static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
-					const struct nft_set *set,
+					struct nft_set *set,
 					const struct nft_set_iter *iter,
-					const struct nft_set_elem *elem)
+					struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	const struct nft_data *data;
@@ -5035,7 +5046,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 {
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
-	const struct nft_set *set;
+	struct nft_set *set;
 	struct nft_set_binding *binding;
 	struct nft_set_iter iter;
 
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 7de2f46734a4..049ad2d9ee66 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -98,7 +98,8 @@ out:
 }
 
 static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
-	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING },
+	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_DYNSET_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_DYNSET_OP]	= { .type = NLA_U32 },
 	[NFTA_DYNSET_SREG_KEY]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 6271e40a3dd6..6f6e64423643 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -39,7 +39,8 @@ static void nft_log_eval(const struct nft_expr *expr,
 
 static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
 	[NFTA_LOG_GROUP]	= { .type = NLA_U16 },
-	[NFTA_LOG_PREFIX]	= { .type = NLA_STRING },
+	[NFTA_LOG_PREFIX]	= { .type = NLA_STRING,
+				    .len = NF_LOG_PREFIXLEN - 1 },
 	[NFTA_LOG_SNAPLEN]	= { .type = NLA_U32 },
 	[NFTA_LOG_QTHRESHOLD]	= { .type = NLA_U16 },
 	[NFTA_LOG_LEVEL]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index d4f97fa7e21d..e21aea7e5ec8 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -49,7 +49,8 @@ static void nft_lookup_eval(const struct nft_expr *expr,
 }
 
 static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
-	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING },
+	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_LOOKUP_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_SREG]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_DREG]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 415a65ba2b85..1ae8c49ca4a1 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -193,10 +193,12 @@ nft_objref_select_ops(const struct nft_ctx *ctx,
 }
 
 static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = {
-	[NFTA_OBJREF_IMM_NAME]	= { .type = NLA_STRING },
+	[NFTA_OBJREF_IMM_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_OBJ_MAXNAMELEN - 1 },
 	[NFTA_OBJREF_IMM_TYPE]	= { .type = NLA_U32 },
 	[NFTA_OBJREF_SET_SREG]	= { .type = NLA_U32 },
-	[NFTA_OBJREF_SET_NAME]	= { .type = NLA_STRING },
+	[NFTA_OBJREF_SET_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_OBJREF_SET_ID]	= { .type = NLA_U32 },
 };
 
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 1e20e2bbb6d9..e36069fb76ae 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -212,7 +212,7 @@ static void nft_hash_remove(const struct nft_set *set,
 	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,
+static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
 	struct nft_hash *priv = nft_set_priv(set);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 08376e50f6cd..f06f55ee516d 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -221,7 +221,7 @@ static void *nft_rbtree_deactivate(const struct net *net,
 }
 
 static void nft_rbtree_walk(const struct nft_ctx *ctx,
-			    const struct nft_set *set,
+			    struct nft_set *set,
 			    struct nft_set_iter *iter)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);