netfilter: nf_tables: don't skip expired elements during walk

There is an asymmetry between commit/abort and preparation phase if the
following conditions are met:

1. set is a verdict map ("1.2.3.4 : jump foo")
2. timeouts are enabled

In this case, following sequence is problematic:

1. element E in set S refers to chain C
2. userspace requests removal of set S
3. kernel does a set walk to decrement chain->use count for all elements
   from preparation phase
4. kernel does another set walk to remove elements from the commit phase
   (or another walk to do a chain->use increment for all elements from
    abort phase)

If E has already expired in 1), it will be ignored during list walk, so its use count
won't have been changed.

Then, when set is culled, ->destroy callback will zap the element via
nf_tables_set_elem_destroy(), but this function is only safe for
elements that have been deactivated earlier from the preparation phase:
lack of earlier deactivate removes the element but leaks the chain use
count, which results in a WARN splat when the chain gets removed later,
plus a leak of the nft_chain structure.

Update pipapo_get() not to skip expired elements, otherwise flush
command reports bogus ENOENT errors.

Fixes: 3c4287f ("nf_tables: Add set type for arbitrary concatenation of ranges")
Fixes: 8d8540c ("netfilter: nft_set_rbtree: add timeout support")
Fixes: 9d09829 ("netfilter: nft_hash: add support for timeouts")
Signed-off-by: Florian Westphal <[email protected]>
Signed-off-by: Pablo Neira Ayuso <[email protected]>

Author: Florian Westphal

net/netfilter/nf_tables_api.c

@@ -5602,8 +5602,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 				  const struct nft_set_iter *iter,
 				  struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_set_dump_args *args;
 
+	if (nft_set_elem_expired(ext))
+		return 0;
+
 	args = container_of(iter, struct nft_set_dump_args, iter);
 	return nf_tables_fill_setelem(args->skb, set, elem, args->reset);
 }

net/netfilter/nft_set_hash.c

@@ -278,8 +278,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (nft_set_elem_expired(&he->ext))
-			goto cont;
 		if (!nft_set_elem_active(&he->ext, iter->genmask))
 			goto cont;
 

net/netfilter/nft_set_pipapo.c

@@ -566,8 +566,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 			goto out;
 
 		if (last) {
-			if (nft_set_elem_expired(&f->mt[b].e->ext) ||
-			    (genmask &&
+			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
 				goto next_match;
 
@@ -601,8 +600,17 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 static void *nft_pipapo_get(const struct net *net, const struct nft_set *set,
 			    const struct nft_set_elem *elem, unsigned int flags)
 {
-	return pipapo_get(net, set, (const u8 *)elem->key.val.data,
-			  nft_genmask_cur(net));
+	struct nft_pipapo_elem *ret;
+
+	ret = pipapo_get(net, set, (const u8 *)elem->key.val.data,
+			 nft_genmask_cur(net));
+	if (IS_ERR(ret))
+		return ret;
+
+	if (nft_set_elem_expired(&ret->ext))
+		return ERR_PTR(-ENOENT);
+
+	return ret;
 }
 
 /**
@@ -2005,8 +2013,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 			goto cont;
 
 		e = f->mt[r].e;
-		if (nft_set_elem_expired(&e->ext))
-			goto cont;
 
 		elem.priv = e;
 

net/netfilter/nft_set_rbtree.c

@@ -552,8 +552,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (nft_set_elem_expired(&rbe->ext))
-			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;