netfilter: nft_set_rbtree: bogus lookup/get on consecutive elements i…

…n named sets

[ Upstream commit db3b665dd77b34e34df00e17d7b299c98fcfb2c5 ]

The existing rbtree implementation might store consecutive elements
where the closing element and the opening element might overlap, eg.

	[ a, a+1) [ a+1, a+2)

This patch removes the optimization for non-anonymous sets in the exact
matching case, where it is assumed to stop searching in case that the
closing element is found. Instead, invalidate candidate interval and
keep looking further in the tree.

The lookup/get operation might return false, while there is an element
in the rbtree. Moreover, the get operation returns true as if a+2 would
be in the tree. This happens with named sets after several set updates.

The existing lookup optimization (that only works for the anonymous
sets) might not reach the opening [ a+1,... element if the closing
...,a+1) is found in first place when walking over the rbtree. Hence,
walking the full tree in that case is needed.

This patch fixes the lookup and get operations.

Fixes: e701001 ("netfilter: nft_rbtree: allow adjacent intervals with dynamic updates")
Fixes: ba0e4d9 ("netfilter: nf_tables: get set elements via netlink")
Signed-off-by: Pablo Neira Ayuso <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>

net/netfilter/nft_set_rbtree.c

@@ -77,8 +77,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				parent = rcu_dereference_raw(parent->rb_left);
 				continue;
 			}
-			if (nft_rbtree_interval_end(rbe))
-				goto out;
+			if (nft_rbtree_interval_end(rbe)) {
+				if (nft_set_is_anonymous(set))
+					return false;
+				parent = rcu_dereference_raw(parent->rb_left);
+				interval = NULL;
+				continue;
+			}
 
 			*ext = &rbe->ext;
 			return true;
@@ -91,7 +96,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 		*ext = &interval->ext;
 		return true;
 	}
-out:
+
 	return false;
 }
 
@@ -139,16 +144,22 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 		} else if (d > 0) {
 			parent = rcu_dereference_raw(parent->rb_right);
 		} else {
-			if (!nft_set_elem_active(&rbe->ext, genmask))
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = rcu_dereference_raw(parent->rb_left);
+				continue;
+			}
 
 			if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) ||
 			    (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) ==
 			    (flags & NFT_SET_ELEM_INTERVAL_END)) {
 				*elem = rbe;
 				return true;
 			}
-			return false;
+
+			if (nft_rbtree_interval_end(rbe))
+				interval = NULL;
+
+			parent = rcu_dereference_raw(parent->rb_left);
 		}
 	}