netfilter: nf_tables: handle nft_object lookups via rhltable

Instead of linear search, use rhlist interface to look up the objects.
This fixes rulesets with thousands of named objects (quota, counters and
the like).

We only use a single table for this and consider the address of the
table we're doing the lookup in as a part of the key.

This reduces restore time of a sample ruleset with ~20k named counters
from 37 seconds to 0.8 seconds.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 93 insertions, 13 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5e213941e85b..621ff834d3a4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -37,10 +37,16 @@ enum {
 	NFT_VALIDATE_DO,
 };
 
+static struct rhltable nft_objname_ht;
+
 static u32 nft_chain_hash(const void *data, u32 len, u32 seed);
 static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed);
 static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *);
 
+static u32 nft_objname_hash(const void *data, u32 len, u32 seed);
+static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed);
+static int nft_objname_hash_cmp(struct rhashtable_compare_arg *, const void *);
+
 static const struct rhashtable_params nft_chain_ht_params = {
 	.head_offset		= offsetof(struct nft_chain, rhlhead),
 	.key_offset		= offsetof(struct nft_chain, name),
@@ -51,6 +57,15 @@ static const struct rhashtable_params nft_chain_ht_params = {
 	.automatic_shrinking	= true,
 };
 
+static const struct rhashtable_params nft_objname_ht_params = {
+	.head_offset		= offsetof(struct nft_object, rhlhead),
+	.key_offset		= offsetof(struct nft_object, key),
+	.hashfn			= nft_objname_hash,
+	.obj_hashfn		= nft_objname_hash_obj,
+	.obj_cmpfn		= nft_objname_hash_cmp,
+	.automatic_shrinking	= true,
+};
+
 static void nft_validate_state_update(struct net *net, u8 new_validate_state)
 {
 	switch (net->nft.validate_state) {
@@ -814,6 +829,34 @@ static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg,
 	return strcmp(chain->name, name);
 }
 
+static u32 nft_objname_hash(const void *data, u32 len, u32 seed)
+{
+	const struct nft_object_hash_key *k = data;
+
+	seed ^= hash_ptr(k->table, 32);
+
+	return jhash(k->name, strlen(k->name), seed);
+}
+
+static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed)
+{
+	const struct nft_object *obj = data;
+
+	return nft_objname_hash(&obj->key, 0, seed);
+}
+
+static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg,
+				const void *ptr)
+{
+	const struct nft_object_hash_key *k = arg->key;
+	const struct nft_object *obj = ptr;
+
+	if (obj->key.table != k->table)
+		return -1;
+
+	return strcmp(obj->key.name, k->name);
+}
+
 static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 			      struct sk_buff *skb, const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[],
@@ -1070,7 +1113,7 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask)
 	return ERR_PTR(-ENOENT);
 }
 
-static bool lockdep_commit_lock_is_held(struct net *net)
+static bool lockdep_commit_lock_is_held(const struct net *net)
 {
 #ifdef CONFIG_PROVE_LOCKING
 	return lockdep_is_held(&net->nft.commit_mutex);
@@ -4386,7 +4429,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			err = -EINVAL;
 			goto err2;
 		}
-		obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF],
+		obj = nft_obj_lookup(ctx->net, ctx->table,
+				     nla[NFTA_SET_ELEM_OBJREF],
 				     set->objtype, genmask);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
@@ -4819,18 +4863,36 @@ void nft_unregister_obj(struct nft_object_type *obj_type)
 }
 EXPORT_SYMBOL_GPL(nft_unregister_obj);
 
-struct nft_object *nft_obj_lookup(const struct nft_table *table,
+struct nft_object *nft_obj_lookup(const struct net *net,
+				  const struct nft_table *table,
 				  const struct nlattr *nla, u32 objtype,
 				  u8 genmask)
 {
+	struct nft_object_hash_key k = { .table = table };
+	char search[NFT_OBJ_MAXNAMELEN];
+	struct rhlist_head *tmp, *list;
 	struct nft_object *obj;
 
-	list_for_each_entry_rcu(obj, &table->objects, list) {
-		if (!nla_strcmp(nla, obj->key.name) &&
-		    objtype == obj->ops->type->type &&
-		    nft_active_genmask(obj, genmask))
+	nla_strlcpy(search, nla, sizeof(search));
+	k.name = search;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() &&
+		     !lockdep_commit_lock_is_held(net));
+
+	rcu_read_lock();
+	list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params);
+	if (!list)
+		goto out;
+
+	rhl_for_each_entry_rcu(obj, tmp, list, rhlhead) {
+		if (objtype == obj->ops->type->type &&
+		    nft_active_genmask(obj, genmask)) {
+			rcu_read_unlock();
 			return obj;
+		}
 	}
+out:
+	rcu_read_unlock();
 	return ERR_PTR(-ENOENT);
 }
 EXPORT_SYMBOL_GPL(nft_obj_lookup);
@@ -4988,7 +5050,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
-	obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
+	obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		if (err != -ENOENT) {
@@ -5027,9 +5089,18 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	if (err < 0)
 		goto err3;
 
+	err = rhltable_insert(&nft_objname_ht, &obj->rhlhead,
+			      nft_objname_ht_params);
+	if (err < 0)
+		goto err4;
+
 	list_add_tail_rcu(&obj->list, &table->objects);
 	table->use++;
 	return 0;
+err4:
+	/* queued in transaction log */
+	INIT_LIST_HEAD(&obj->list);
+	return err;
 err3:
 	kfree(obj->key.name);
 err2:
@@ -5215,7 +5286,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
-	obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
+	obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
 	if (IS_ERR(obj)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
 		return PTR_ERR(obj);
@@ -5280,7 +5351,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk,
 		obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask);
 	} else {
 		attr = nla[NFTA_OBJ_NAME];
-		obj = nft_obj_lookup(table, attr, objtype, genmask);
+		obj = nft_obj_lookup(net, table, attr, objtype, genmask);
 	}
 
 	if (IS_ERR(obj)) {
@@ -6406,6 +6477,7 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain)
 
 static void nft_obj_del(struct nft_object *obj)
 {
+	rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params);
 	list_del_rcu(&obj->list);
 }
 
@@ -6721,7 +6793,7 @@ static int __nf_tables_abort(struct net *net)
 			break;
 		case NFT_MSG_NEWOBJ:
 			trans->ctx.table->use--;
-			list_del_rcu(&nft_trans_obj(trans)->list);
+			nft_obj_del(nft_trans_obj(trans));
 			break;
 		case NFT_MSG_DELOBJ:
 			trans->ctx.table->use++;
@@ -7397,12 +7469,18 @@ static int __init nf_tables_module_init(void)
 	if (err < 0)
 		goto err3;
 
+	err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params);
+	if (err < 0)
+		goto err4;
+
 	/* must be last */
 	err = nfnetlink_subsys_register(&nf_tables_subsys);
 	if (err < 0)
-		goto err4;
+		goto err5;
 
 	return err;
+err5:
+	rhltable_destroy(&nft_objname_ht);
 err4:
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 err3:
@@ -7422,6 +7500,7 @@ static void __exit nf_tables_module_exit(void)
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_destroy_work);
 	rcu_barrier();
+	rhltable_destroy(&nft_objname_ht);
 	nf_tables_core_module_exit();
 }
 
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 58eb75ad61bf..c1f2adf198a0 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -38,7 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 
 	objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE]));
-	obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype,
+	obj = nft_obj_lookup(ctx->net, ctx->table,
+			     tb[NFTA_OBJREF_IMM_NAME], objtype,
 			     genmask);
 	if (IS_ERR(obj))
 		return -ENOENT;