netfilter: nf_tables: drop map element references from preparation phase

commit 628bd3e49cba1c066228e23d71a852c23e26da73 upstream.

set .destroy callback releases the references to other objects in maps.
This is very late and it results in spurious EBUSY errors. Drop refcount
from the preparation phase instead, update set backend not to drop
reference counter from set .destroy path.

Exceptions: NFT_TRANS_PREPARE_ERROR does not require to drop the
reference counter because the transaction abort path releases the map
references for each element since the set is unbound. The abort path
also deals with releasing reference counter for new elements added to
unbound sets.

Fixes: 591054469b3e ("netfilter: nf_tables: revisit chain/object refcounting from elements")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 104 insertions, 18 deletions

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2bd522abb334..6e1fa13d37c0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -403,6 +403,31 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
 	return 0;
 }
 
+static void nft_setelem_data_deactivate(const struct net *net,
+					const struct nft_set *set,
+					struct nft_set_elem *elem);
+
+static int nft_mapelem_deactivate(const struct nft_ctx *ctx,
+				  struct nft_set *set,
+				  const struct nft_set_iter *iter,
+				  struct nft_set_elem *elem)
+{
+	nft_setelem_data_deactivate(ctx->net, set, elem);
+
+	return 0;
+}
+
+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),
+		.fn		= nft_mapelem_deactivate,
+	};
+
+	set->ops->walk(ctx, set, &iter);
+	WARN_ON_ONCE(iter.err);
+}
+
 static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	int err;
@@ -411,6 +436,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
 	if (err < 0)
 		return err;
 
+	if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+		nft_map_deactivate(ctx, set);
+
 	nft_deactivate_next(ctx->net, set);
 	nft_use_dec(&ctx->table->use);
 
@@ -3840,7 +3868,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	return 0;
 
 err4:
-	ops->destroy(set);
+	ops->destroy(&ctx, set);
 err3:
 	kfree(set->name);
 err2:
@@ -3857,7 +3885,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 	if (WARN_ON(set->use > 0))
 		return;
 
-	set->ops->destroy(set);
+	set->ops->destroy(ctx, set);
 	module_put(to_set_type(set->ops)->owner);
 	kfree(set->name);
 	kvfree(set);
@@ -3981,10 +4009,39 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	}
 }
 
+static void nft_setelem_data_activate(const struct net *net,
+				      const struct nft_set *set,
+				      struct nft_set_elem *elem);
+
+static int nft_mapelem_activate(const struct nft_ctx *ctx,
+				struct nft_set *set,
+				const struct nft_set_iter *iter,
+				struct nft_set_elem *elem)
+{
+	nft_setelem_data_activate(ctx->net, set, elem);
+
+	return 0;
+}
+
+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),
+		.fn		= nft_mapelem_activate,
+	};
+
+	set->ops->walk(ctx, set, &iter);
+	WARN_ON_ONCE(iter.err);
+}
+
 void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set)
 {
-	if (nft_set_is_anonymous(set))
+	if (nft_set_is_anonymous(set)) {
+		if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_activate(ctx, set);
+
 		nft_clear(ctx->net, set);
+	}
 
 	nft_use_inc_restore(&set->use);
 }
@@ -4005,13 +4062,20 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 		nft_use_dec(&set->use);
 		break;
 	case NFT_TRANS_PREPARE:
-		if (nft_set_is_anonymous(set))
-			nft_deactivate_next(ctx->net, set);
+		if (nft_set_is_anonymous(set)) {
+			if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+				nft_map_deactivate(ctx, set);
 
+			nft_deactivate_next(ctx->net, set);
+		}
 		nft_use_dec(&set->use);
 		return;
 	case NFT_TRANS_ABORT:
 	case NFT_TRANS_RELEASE:
+		if (nft_set_is_anonymous(set) &&
+		    set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_deactivate(ctx, set);
+
 		nft_use_dec(&set->use);
 		/* fall through */
 	default:
@@ -4574,6 +4638,7 @@ void *nft_set_elem_init(const struct nft_set *set,
 	return elem;
 }
 
+/* Drop references and destroy. Called from gc, dynset and abort path. */
 void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 			  bool destroy_expr)
 {
@@ -4602,11 +4667,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 }
 EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
 
-/* Only called from commit path, nft_setelem_data_deactivate() already deals
- * with the refcounting from the preparation phase.
+/* Destroy element. References have been already dropped in the preparation
+ * path via nft_setelem_data_deactivate().
  */
-static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
-				       const struct nft_set *set, void *elem)
+void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
+				const struct nft_set *set, void *elem)
 {
 	struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
 
@@ -4614,6 +4679,7 @@ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
 		nf_tables_expr_destroy(ctx, nft_set_ext_expr(ext));
 	kfree(elem);
 }
+EXPORT_SYMBOL_GPL(nf_tables_set_elem_destroy);
 
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr, u32 nlmsg_flags)
@@ -7263,6 +7329,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		case NFT_MSG_DELSET:
 			nft_use_inc_restore(&trans->ctx.table->use);
 			nft_clear(trans->ctx.net, nft_trans_set(trans));
+			if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+				nft_map_activate(&trans->ctx, nft_trans_set(trans));
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
@@ -7951,6 +8019,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 	list_for_each_entry_safe(set, ns, &table->sets, list) {
 		list_del(&set->list);
 		nft_use_dec(&table->use);
+		if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
+			nft_map_deactivate(&ctx, set);
+
 		nft_set_destroy(&ctx, set);
 	}
 	list_for_each_entry_safe(obj, ne, &table->objects, list) {
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 087a056e34d1..b0f6b1490e1a 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -270,13 +270,14 @@ static int nft_bitmap_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_bitmap_destroy(const struct nft_set *set)
+static void nft_bitmap_destroy(const struct nft_ctx *ctx,
+			       const struct nft_set *set)
 {
 	struct nft_bitmap *priv = nft_set_priv(set);
 	struct nft_bitmap_elem *be, *n;
 
 	list_for_each_entry_safe(be, n, &priv->list, head)
-		nft_set_elem_destroy(set, be, true);
+		nf_tables_set_elem_destroy(ctx, set, be);
 }
 
 static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index e7eb56b4b89e..7f66eeb97947 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -380,19 +380,31 @@ static int nft_rhash_init(const struct nft_set *set,
 	return 0;
 }
 
+struct nft_rhash_ctx {
+	const struct nft_ctx	ctx;
+	const struct nft_set	*set;
+};
+
 static void nft_rhash_elem_destroy(void *ptr, void *arg)
 {
-	nft_set_elem_destroy(arg, ptr, true);
+	struct nft_rhash_ctx *rhash_ctx = arg;
+
+	nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr);
 }
 
-static void nft_rhash_destroy(const struct nft_set *set)
+static void nft_rhash_destroy(const struct nft_ctx *ctx,
+			      const struct nft_set *set)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
+	struct nft_rhash_ctx rhash_ctx = {
+		.ctx	= *ctx,
+		.set	= set,
+	};
 
 	cancel_delayed_work_sync(&priv->gc_work);
 	rcu_barrier();
 	rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
-				    (void *)set);
+				    (void *)&rhash_ctx);
 }
 
 /* Number of buckets is stored in u32, so cap our result to 1U<<31 */
@@ -621,7 +633,8 @@ static int nft_hash_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_hash_destroy(const struct nft_set *set)
+static void nft_hash_destroy(const struct nft_ctx *ctx,
+			     const struct nft_set *set)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he;
@@ -631,7 +644,7 @@ static void nft_hash_destroy(const struct nft_set *set)
 	for (i = 0; i < priv->buckets; i++) {
 		hlist_for_each_entry_safe(he, next, &priv->table[i], node) {
 			hlist_del_rcu(&he->node);
-			nft_set_elem_destroy(set, he, true);
+			nf_tables_set_elem_destroy(ctx, set, he);
 		}
 	}
 }
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2c58e9ae0b0e..12ab7a5de785 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -480,7 +480,8 @@ static int nft_rbtree_init(const struct nft_set *set,
 	return 0;
 }
 
-static void nft_rbtree_destroy(const struct nft_set *set)
+static void nft_rbtree_destroy(const struct nft_ctx *ctx,
+			       const struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
@@ -491,7 +492,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
-		nft_set_elem_destroy(set, rbe, true);
+		nf_tables_set_elem_destroy(ctx, set, rbe);
 	}
 }