1 files changed, 144 insertions, 30 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5fa3d3540c93..167074283ea9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx,
 				  const struct nft_set_iter *iter,
 				  struct nft_elem_priv *elem_priv)
 {
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
+	nft_set_elem_change_active(ctx->net, set, ext);
 	nft_setelem_data_deactivate(ctx->net, set, elem_priv);
 
 	return 0;
@@ -617,6 +623,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 		if (!nft_set_elem_active(ext, genmask))
 			continue;
 
+		nft_set_elem_change_active(ctx->net, set, ext);
 		nft_setelem_data_deactivate(ctx->net, set, catchall->elem);
 		break;
 	}
@@ -626,6 +633,7 @@ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	struct nft_set_iter iter = {
 		.genmask	= nft_genmask_next(ctx->net),
+		.type		= NFT_ITER_UPDATE,
 		.fn		= nft_mapelem_deactivate,
 	};
 
@@ -1200,6 +1208,26 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table)
 					 __NFT_TABLE_F_WAS_AWAKEN | \
 					 __NFT_TABLE_F_WAS_ORPHAN)
 
+static bool nft_table_pending_update(const struct nft_ctx *ctx)
+{
+	struct nftables_pernet *nft_net = nft_pernet(ctx->net);
+	struct nft_trans *trans;
+
+	if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+		return true;
+
+	list_for_each_entry(trans, &nft_net->commit_list, list) {
+		if (trans->ctx.table == ctx->table &&
+		    ((trans->msg_type == NFT_MSG_NEWCHAIN &&
+		      nft_trans_chain_update(trans)) ||
+		     (trans->msg_type == NFT_MSG_DELCHAIN &&
+		      nft_is_base_chain(trans->ctx.chain))))
+			return true;
+	}
+
+	return false;
+}
+
 static int nf_tables_updtable(struct nft_ctx *ctx)
 {
 	struct nft_trans *trans;
@@ -1226,7 +1254,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 		return -EOPNOTSUPP;
 
 	/* No dormant off/on/off/on games in single transaction */
-	if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+	if (nft_table_pending_update(ctx))
 		return -EINVAL;
 
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
@@ -2430,6 +2458,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		struct nft_stats __percpu *stats = NULL;
 		struct nft_chain_hook hook = {};
 
+		if (table->flags & __NFT_TABLE_F_UPDATE)
+			return -EINVAL;
+
 		if (flags & NFT_CHAIN_BINDING)
 			return -EOPNOTSUPP;
 
@@ -2631,6 +2662,13 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 		}
 	}
 
+	if (table->flags & __NFT_TABLE_F_UPDATE &&
+	    !list_empty(&hook.list)) {
+		NL_SET_BAD_ATTR(extack, attr);
+		err = -EOPNOTSUPP;
+		goto err_hooks;
+	}
+
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
 	    nft_is_base_chain(chain) &&
 	    !list_empty(&hook.list)) {
@@ -2860,6 +2898,9 @@ static int nft_delchain_hook(struct nft_ctx *ctx,
 	struct nft_trans *trans;
 	int err;
 
+	if (ctx->table->flags & __NFT_TABLE_F_UPDATE)
+		return -EOPNOTSUPP;
+
 	err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook,
 				   ctx->family, chain->flags, extack);
 	if (err < 0)
@@ -2944,7 +2985,8 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
 
 	if (nla[NFTA_CHAIN_HOOK]) {
-		if (chain->flags & NFT_CHAIN_HW_OFFLOAD)
+		if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN ||
+		    chain->flags & NFT_CHAIN_HW_OFFLOAD)
 			return -EOPNOTSUPP;
 
 		if (nft_is_base_chain(chain)) {
@@ -3026,7 +3068,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
 {
 	const struct nft_expr_type *type, *candidate = NULL;
 
-	list_for_each_entry(type, &nf_tables_expressions, list) {
+	list_for_each_entry_rcu(type, &nf_tables_expressions, list) {
 		if (!nla_strcmp(nla, type->name)) {
 			if (!type->family && !candidate)
 				candidate = type;
@@ -3058,9 +3100,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
+	rcu_read_lock();
 	type = __nft_expr_type_get(family, nla);
-	if (type != NULL && try_module_get(type->owner))
+	if (type != NULL && try_module_get(type->owner)) {
+		rcu_read_unlock();
 		return type;
+	}
+	rcu_read_unlock();
 
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
@@ -3841,6 +3887,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 	const struct nft_data *data;
 	int err;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
 	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
 		return 0;
@@ -3864,17 +3913,20 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 
 int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set)
 {
-	u8 genmask = nft_genmask_next(ctx->net);
+	struct nft_set_iter dummy_iter = {
+		.genmask	= nft_genmask_next(ctx->net),
+	};
 	struct nft_set_elem_catchall *catchall;
+
 	struct nft_set_ext *ext;
 	int ret = 0;
 
 	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_set_elem_active(ext, genmask))
+		if (!nft_set_elem_active(ext, dummy_iter.genmask))
 			continue;
 
-		ret = nft_setelem_validate(ctx, set, NULL, catchall->elem);
+		ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem);
 		if (ret < 0)
 			return ret;
 	}
@@ -5363,6 +5415,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					struct nft_elem_priv *elem_priv)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	return nft_setelem_data_validate(ctx, set, elem_priv);
 }
 
@@ -5407,6 +5464,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		}
 
 		iter.genmask	= nft_genmask_next(ctx->net);
+		iter.type	= NFT_ITER_UPDATE;
 		iter.skip 	= 0;
 		iter.count	= 0;
 		iter.err	= 0;
@@ -5454,6 +5512,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx,
 				const struct nft_set_iter *iter,
 				struct nft_elem_priv *elem_priv)
 {
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+	/* called from abort path, reverse check to undo changes. */
+	if (nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
+	nft_clear(ctx->net, ext);
 	nft_setelem_data_activate(ctx->net, set, elem_priv);
 
 	return 0;
@@ -5471,6 +5536,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx,
 		if (!nft_set_elem_active(ext, genmask))
 			continue;
 
+		nft_clear(ctx->net, ext);
 		nft_setelem_data_activate(ctx->net, set, catchall->elem);
 		break;
 	}
@@ -5480,6 +5546,7 @@ static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	struct nft_set_iter iter = {
 		.genmask	= nft_genmask_next(ctx->net),
+		.type		= NFT_ITER_UPDATE,
 		.fn		= nft_mapelem_activate,
 	};
 
@@ -5744,6 +5811,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 	struct nft_set_dump_args *args;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
@@ -5854,6 +5924,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	args.skb		= skb;
 	args.reset		= dump_ctx->reset;
 	args.iter.genmask	= nft_genmask_cur(net);
+	args.iter.type		= NFT_ITER_READ;
 	args.iter.skip		= cb->args[0];
 	args.iter.count		= 0;
 	args.iter.err		= 0;
@@ -6593,7 +6664,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set,
 	struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 
 	if (nft_setelem_is_catchall(set, elem_priv)) {
-		nft_set_elem_change_active(net, set, ext);
+		nft_clear(net, ext);
 	} else {
 		set->ops->activate(net, set, elem_priv);
 	}
@@ -7152,6 +7223,16 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
 	}
 }
 
+static int nft_setelem_active_next(const struct net *net,
+				   const struct nft_set *set,
+				   struct nft_elem_priv *elem_priv)
+{
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+	u8 genmask = nft_genmask_next(net);
+
+	return nft_set_elem_active(ext, genmask);
+}
+
 static void nft_setelem_data_activate(const struct net *net,
 				      const struct nft_set *set,
 				      struct nft_elem_priv *elem_priv)
@@ -7275,8 +7356,12 @@ static int nft_setelem_flush(const struct nft_ctx *ctx,
 			     const struct nft_set_iter *iter,
 			     struct nft_elem_priv *elem_priv)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 	struct nft_trans *trans;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM,
 				    sizeof(struct nft_trans_elem), GFP_ATOMIC);
 	if (!trans)
@@ -7338,6 +7423,7 @@ static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask)
 {
 	struct nft_set_iter iter = {
 		.genmask	= genmask,
+		.type		= NFT_ITER_UPDATE,
 		.fn		= nft_setelem_flush,
 	};
 
@@ -7573,7 +7659,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
-	list_for_each_entry(type, &nf_tables_objects, list) {
+	list_for_each_entry_rcu(type, &nf_tables_objects, list) {
 		if (type->family != NFPROTO_UNSPEC &&
 		    type->family != family)
 			continue;
@@ -7589,9 +7675,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
+	rcu_read_lock();
 	type = __nft_obj_type_get(objtype, family);
-	if (type != NULL && try_module_get(type->owner))
+	if (type != NULL && try_module_get(type->owner)) {
+		rcu_read_unlock();
 		return type;
+	}
+	rcu_read_unlock();
 
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
@@ -8263,11 +8353,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx,
 	return err;
 }
 
+/* call under rcu_read_lock */
 static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family)
 {
 	const struct nf_flowtable_type *type;
 
-	list_for_each_entry(type, &nf_tables_flowtables, list) {
+	list_for_each_entry_rcu(type, &nf_tables_flowtables, list) {
 		if (family == type->family)
 			return type;
 	}
@@ -8279,9 +8370,13 @@ nft_flowtable_type_get(struct net *net, u8 family)
 {
 	const struct nf_flowtable_type *type;
 
+	rcu_read_lock();
 	type = __nft_flowtable_type_get(family);
-	if (type != NULL && try_module_get(type->owner))
+	if (type != NULL && try_module_get(type->owner)) {
+		rcu_read_unlock();
 		return type;
+	}
+	rcu_read_unlock();
 
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
@@ -10182,9 +10277,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			if (nft_trans_chain_update(trans)) {
 				nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN,
 						       &nft_trans_chain_hooks(trans));
-				nft_netdev_unregister_hooks(net,
-							    &nft_trans_chain_hooks(trans),
-							    true);
+				if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) {
+					nft_netdev_unregister_hooks(net,
+								    &nft_trans_chain_hooks(trans),
+								    true);
+				}
 			} else {
 				nft_chain_del(trans->ctx.chain);
 				nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN,
@@ -10423,10 +10520,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 	struct nft_trans *trans, *next;
 	LIST_HEAD(set_update_list);
 	struct nft_trans_elem *te;
+	int err = 0;
 
 	if (action == NFNL_ABORT_VALIDATE &&
 	    nf_tables_validate(net) < 0)
-		return -EAGAIN;
+		err = -EAGAIN;
 
 	list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list,
 					 list) {
@@ -10460,9 +10558,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			break;
 		case NFT_MSG_NEWCHAIN:
 			if (nft_trans_chain_update(trans)) {
-				nft_netdev_unregister_hooks(net,
-							    &nft_trans_chain_hooks(trans),
-							    true);
+				if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) {
+					nft_netdev_unregister_hooks(net,
+								    &nft_trans_chain_hooks(trans),
+								    true);
+				}
 				free_percpu(nft_trans_chain_stats(trans));
 				kfree(nft_trans_chain_name(trans));
 				nft_trans_destroy(trans);
@@ -10554,8 +10654,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		case NFT_MSG_DESTROYSETELEM:
 			te = (struct nft_trans_elem *)trans->data;
 
-			nft_setelem_data_activate(net, te->set, te->elem_priv);
-			nft_setelem_activate(net, te->set, te->elem_priv);
+			if (!nft_setelem_active_next(net, te->set, te->elem_priv)) {
+				nft_setelem_data_activate(net, te->set, te->elem_priv);
+				nft_setelem_activate(net, te->set, te->elem_priv);
+			}
 			if (!nft_setelem_is_catchall(te->set, te->elem_priv))
 				te->set->ndeact--;
 
@@ -10616,12 +10718,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		nf_tables_abort_release(trans);
 	}
 
-	if (action == NFNL_ABORT_AUTOLOAD)
-		nf_tables_module_autoload(net);
-	else
-		nf_tables_module_autoload_cleanup(net);
-
-	return 0;
+	return err;
 }
 
 static int nf_tables_abort(struct net *net, struct sk_buff *skb,
@@ -10634,6 +10731,17 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb,
 	gc_seq = nft_gc_seq_begin(nft_net);
 	ret = __nf_tables_abort(net, action);
 	nft_gc_seq_end(nft_net, gc_seq);
+
+	WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+	/* module autoload needs to happen after GC sequence update because it
+	 * temporarily releases and grabs mutex again.
+	 */
+	if (action == NFNL_ABORT_AUTOLOAD)
+		nf_tables_module_autoload(net);
+	else
+		nf_tables_module_autoload_cleanup(net);
+
 	mutex_unlock(&nft_net->commit_mutex);
 
 	return ret;
@@ -10737,6 +10845,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
 	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
 		return 0;
@@ -10821,6 +10932,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 				continue;
 
 			iter.genmask	= nft_genmask_next(ctx->net);
+			iter.type	= NFT_ITER_UPDATE;
 			iter.skip 	= 0;
 			iter.count	= 0;
 			iter.err	= 0;
@@ -11439,9 +11551,10 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
-	if (!list_empty(&nft_net->commit_list) ||
-	    !list_empty(&nft_net->module_list))
-		__nf_tables_abort(net, NFNL_ABORT_NONE);
+	WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+
+	if (!list_empty(&nft_net->module_list))
+		nf_tables_module_autoload_cleanup(net);
 
 	__nft_release_tables(net);
 
@@ -11533,6 +11646,7 @@ static void __exit nf_tables_module_exit(void)
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 	nft_chain_filter_fini();
 	nft_chain_route_fini();
+	nf_tables_trans_destroy_flush_work();
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_gc_work);
 	cancel_work_sync(&trans_destroy_work);