netfilter: nf_tables: honor NLM_F_EXCL flag in set element insertion

If the NLM_F_EXCL flag is set, then new elements that clash with an
existing one return EEXIST. In case you try to add an element whose
data area differs from what we have, then this returns EBUSY. If no
flag is specified at all, then this returns success to userspace.

This patch also update the set insert operation so we can fetch the
existing element that clashes with the one you want to add, we need
this to make sure the element data doesn't differ.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/netfilter/nf_tables.h

@@ -251,7 +251,8 @@ struct nft_set_ops {
 
 	int				(*insert)(const struct net *net,
 						  const struct nft_set *set,
-						  const struct nft_set_elem *elem);
+						  const struct nft_set_elem *elem,
+						  struct nft_set_ext **ext);
 	void				(*activate)(const struct net *net,
 						    const struct nft_set *set,
 						    const struct nft_set_elem *elem);

net/netfilter/nf_tables_api.c

@@ -3483,12 +3483,12 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
 }
 
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
-			    const struct nlattr *attr)
+			    const struct nlattr *attr, u32 nlmsg_flags)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_data_desc d1, d2;
 	struct nft_set_ext_tmpl tmpl;
-	struct nft_set_ext *ext;
+	struct nft_set_ext *ext, *ext2;
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
 	struct nft_userdata *udata;
@@ -3615,9 +3615,19 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err4;
 
 	ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
-	err = set->ops->insert(ctx->net, set, &elem);
-	if (err < 0)
+	err = set->ops->insert(ctx->net, set, &elem, &ext2);
+	if (err) {
+		if (err == -EEXIST) {
+			if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
+			    nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
+			    memcmp(nft_set_ext_data(ext),
+				   nft_set_ext_data(ext2), set->dlen) != 0)
+				err = -EBUSY;
+			else if (!(nlmsg_flags & NLM_F_EXCL))
+				err = 0;
+		}
 		goto err5;
+	}
 
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
@@ -3673,7 +3683,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
 		    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
 			return -ENFILE;
 
-		err = nft_add_set_elem(&ctx, set, attr);
+		err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags);
 		if (err < 0) {
 			atomic_dec(&set->nelems);
 			break;

net/netfilter/nft_set_hash.c

@@ -126,7 +126,8 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key,
 }
 
 static int nft_hash_insert(const struct net *net, const struct nft_set *set,
-			   const struct nft_set_elem *elem)
+			   const struct nft_set_elem *elem,
+			   struct nft_set_ext **ext)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_elem *he = elem->priv;
@@ -135,9 +136,17 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set,
 		.set	 = set,
 		.key	 = elem->key.val.data,
 	};
-
-	return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
-					    nft_hash_params);
+	struct nft_hash_elem *prev;
+
+	prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
+					       nft_hash_params);
+	if (IS_ERR(prev))
+		return PTR_ERR(prev);
+	if (prev) {
+		*ext = &prev->ext;
+		return -EEXIST;
+	}
+	return 0;
 }
 
 static void nft_hash_activate(const struct net *net, const struct nft_set *set,

net/netfilter/nft_set_rbtree.c

@@ -94,7 +94,8 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 }
 
 static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
-			       struct nft_rbtree_elem *new)
+			       struct nft_rbtree_elem *new,
+			       struct nft_set_ext **ext)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_next(net);
@@ -122,8 +123,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 				else if (!nft_rbtree_interval_end(rbe) &&
 					 nft_rbtree_interval_end(new))
 					p = &parent->rb_right;
-				else
+				else {
+					*ext = &rbe->ext;
 					return -EEXIST;
+				}
 			}
 		}
 	}
@@ -133,13 +136,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 }
 
 static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
-			     const struct nft_set_elem *elem)
+			     const struct nft_set_elem *elem,
+			     struct nft_set_ext **ext)
 {
 	struct nft_rbtree_elem *rbe = elem->priv;
 	int err;
 
 	spin_lock_bh(&nft_rbtree_lock);
-	err = __nft_rbtree_insert(net, set, rbe);
+	err = __nft_rbtree_insert(net, set, rbe, ext);
 	spin_unlock_bh(&nft_rbtree_lock);
 
 	return err;