Merge tag 'nf-23-10-12' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Florian Westphal says:

====================
netfilter updates for net

Patch 1, from Pablo Neira Ayuso, fixes a performance regression
(since 6.4) when a large pending set update has to be canceled towards
the end of the transaction.

Patch 2 from myself, silences an incorrect compiler warning reported
with a few (older) compiler toolchains.

Patch 3, from Kees Cook, adds __counted_by annotation to
nft_pipapo set backend type.  I took this for net instead of -next
given infra is already in place and no actual code change is made.

Patch 4, from Pablo Neira Ayso, disables timeout resets on
stateful element reset.  The rest should only affect internal object
state, e.g. reset a quota or counter, but not affect a pending timeout.

Patches 5 and 6 fix NULL dereferences in 'inner header' match,
control plane doesn't test for netlink attribute presence before
accessing them. Broken since feature was added in 6.2, fixes from
Xingyuan Mo.

Last patch, from myself, fixes a bogus rule match when skb has
a 0-length mac header, in this case we'd fetch data from network
header instead of canceling rule evaluation.  This is a day 0 bug,
present since nftables was merged in 3.13.

* tag 'nf-23-10-12' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_payload: fix wrong mac header matching
  nf_tables: fix NULL pointer dereference in nft_expr_inner_parse()
  nf_tables: fix NULL pointer dereference in nft_inner_init()
  netfilter: nf_tables: do not refresh timeout when resetting element
  netfilter: nf_tables: Annotate struct nft_pipapo_match with __counted_by
  netfilter: nfnetlink_log: silence bogus compiler warning
  netfilter: nf_tables: do not remove elements if set backend implements .abort
====================

Link: https://lore.kernel.org/r/20231012085724.15155-1-fw@strlen.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/netfilter/nf_tables_api.c

@@ -3166,7 +3166,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla,
 	if (err < 0)
 		return err;
 
-	if (!tb[NFTA_EXPR_DATA])
+	if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME])
 		return -EINVAL;
 
 	type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]);
@@ -5556,7 +5556,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
-	u64 timeout = 0;
 
 	nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
 	if (nest == NULL)
@@ -5592,15 +5591,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 		         htonl(*nft_set_ext_flags(ext))))
 		goto nla_put_failure;
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
-		timeout = *nft_set_ext_timeout(ext);
-		if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
-				 nf_jiffies64_to_msecs(timeout),
-				 NFTA_SET_ELEM_PAD))
-			goto nla_put_failure;
-	} else if (set->flags & NFT_SET_TIMEOUT) {
-		timeout = READ_ONCE(set->timeout);
-	}
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+	    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+			 nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
+			 NFTA_SET_ELEM_PAD))
+		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
 		u64 expires, now = get_jiffies_64();
@@ -5615,9 +5610,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 				 nf_jiffies64_to_msecs(expires),
 				 NFTA_SET_ELEM_PAD))
 			goto nla_put_failure;
-
-		if (reset)
-			*nft_set_ext_expiration(ext) = now + timeout;
 	}
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -10347,7 +10339,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				break;
 			}
 			te = (struct nft_trans_elem *)trans->data;
-			nft_setelem_remove(net, te->set, &te->elem);
+			if (!te->set->ops->abort ||
+			    nft_setelem_is_catchall(te->set, &te->elem))
+				nft_setelem_remove(net, te->set, &te->elem);
+
 			if (!nft_setelem_is_catchall(te->set, &te->elem))
 				atomic_dec(&te->set->nelems);
 

net/netfilter/nfnetlink_log.c

@@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net,
 	unsigned int plen = 0;
 	struct nfnl_log_net *log = nfnl_log_pernet(net);
 	const struct nfnl_ct_hook *nfnl_ct = NULL;
+	enum ip_conntrack_info ctinfo = 0;
 	struct nf_conn *ct = NULL;
-	enum ip_conntrack_info ctinfo;
 
 	if (li_user && li_user->type == NF_LOG_TYPE_ULOG)
 		li = li_user;

net/netfilter/nft_inner.c

@@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx,
 	int err;
 
 	if (!tb[NFTA_INNER_FLAGS] ||
+	    !tb[NFTA_INNER_NUM] ||
 	    !tb[NFTA_INNER_HDRSIZE] ||
 	    !tb[NFTA_INNER_TYPE] ||
 	    !tb[NFTA_INNER_EXPR])

net/netfilter/nft_payload.c

@@ -179,7 +179,7 @@ void nft_payload_eval(const struct nft_expr *expr,
 
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
-		if (!skb_mac_header_was_set(skb))
+		if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0)
 			goto err;
 
 		if (skb_vlan_tag_present(skb) &&

net/netfilter/nft_set_pipapo.h

@@ -147,7 +147,7 @@ struct nft_pipapo_match {
 	unsigned long * __percpu *scratch;
 	size_t bsize_max;
 	struct rcu_head rcu;
-	struct nft_pipapo_field f[];
+	struct nft_pipapo_field f[] __counted_by(field_count);
 };
 
 /**