netfilter: nf_tables: use timestamp to check for set element timeout

Add a timestamp field at the beginning of the transaction, store it
in the nftables per-netns area.

Update set backend .insert, .deactivate and sync gc path to use the
timestamp, this avoids that an element expires while control plane
transaction is still unfinished.

.lookup and .update, which are used from packet path, still use the
current time to check if the element has expired. And .get path and dump
also since this runs lockless under rcu read size lock. Then, there is
async gc which also needs to check the current time since it runs
asynchronously from a workqueue.

Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 7 insertions, 4 deletions

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65..5fd74f993988 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	/* Descend the tree to search for an existing element greater than the
@@ -360,7 +361,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		/* perform garbage collection to avoid bogus overlap reports
 		 * but skip new elements in this transaction.
 		 */
-		if (nft_set_elem_expired(&rbe->ext) &&
+		if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			const struct nft_rbtree_elem *removed_end;
 
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
-			} else if (nft_set_elem_expired(&rbe->ext)) {
+			} else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
 				break;
 			} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
-	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
 			rbe_end = rbe;
 			continue;
 		}
-		if (!nft_set_elem_expired(&rbe->ext))
+		if (!__nft_set_elem_expired(&rbe->ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);