Merge tag 'nf-next-25-09-02' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Florian Westphal says:

====================
netfilter: updates for net-next

1) prefer vmalloc_array in ebtables, from Qianfeng Rong.

2) Use csum_replace4 instead of open-coding it, from Christophe Leroy.

3+4) Get rid of GFP_ATOMIC in transaction object allocations, those
cause silly failures with large sets under memory pressure, from
myself.

5) Remove test for AVX cpu feature in nftables pipapo set type,
testing for AVX2 feature is sufficient.

6) Unexport a few function in nf_reject infra: no external callers.

7) Extend payload offset to u16, this was restricted to values <=255
so far, from Fernando Fernandez Mancera.

* tag 'nf-next-25-09-02' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
netfilter: nft_payload: extend offset to 65535 bytes
netfilter: nf_reject: remove unneeded exports
netfilter: nft_set_pipapo: remove redundant test for avx feature bit
netfilter: nf_tables: all transaction allocations can now sleep
netfilter: nf_tables: allow iter callbacks to sleep
netfilter: nft_payload: Use csum_replace4() instead of opencoding
netfilter: ebtables: Use vmalloc_array() to improve code
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/net/netfilter/ipv4/nf_reject.h

···
 void nf_send_unreach(struct sk_buff *skb_in, int code, int hook);
 void nf_send_reset(struct net *net, struct sock *, struct sk_buff *oldskb,
 		   int hook);
-const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
-					     struct tcphdr *_oth, int hook);
-struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
-				  const struct sk_buff *oldskb,
-				  __u8 protocol, int ttl);
-void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
-			     const struct tcphdr *oth);
-
 struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
                                          struct sk_buff *oldskb,
                                          const struct net_device *dev,

include/net/netfilter/ipv6/nf_reject.h

···
 		      unsigned int hooknum);
 void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		    int hook);
-const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
-					      struct tcphdr *otcph,
-					      unsigned int *otcplen, int hook);
-struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb,
-				     const struct sk_buff *oldskb,
-				     __u8 protocol, int hoplimit);
-void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
-			      const struct sk_buff *oldskb,
-			      const struct tcphdr *oth, unsigned int otcplen);
-
 struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net,
 					   struct sk_buff *oldskb,
 					   const struct net_device *dev,

include/net/netfilter/nf_tables.h

···
  * 	@size: maximum set size
  *	@field_len: length of each field in concatenation, bytes
  *	@field_count: number of concatenated fields in element
+ *	@in_update_walk: true during ->walk() in transaction phase
  *	@use: number of rules references to this set
  * 	@nelems: number of elements
  * 	@ndeact: number of deactivated elements queued for removal
···
 	u32				size;
 	u8				field_len[NFT_REG32_COUNT];
 	u8				field_count;
+	bool				in_update_walk;
 	u32				use;
 	atomic_t			nelems;
 	u32				ndeact;

include/net/netfilter/nf_tables_core.h

···
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;
-	u8			offset;
+	u16			offset;
 	u8			len;
 	u8			dreg;
 };

net/bridge/netfilter/ebtables.c

···
 		 * if an error occurs
 		 */
 		newinfo->chainstack =
-			vmalloc(array_size(nr_cpu_ids,
-					   sizeof(*(newinfo->chainstack))));
+			vmalloc_array(nr_cpu_ids,
+				      sizeof(*(newinfo->chainstack)));
 		if (!newinfo->chainstack)
 			return -ENOMEM;
 		for_each_possible_cpu(i) {
···
 			}
 		}
 
-		cl_s = vmalloc(array_size(udc_cnt, sizeof(*cl_s)));
+		cl_s = vmalloc_array(udc_cnt, sizeof(*cl_s));
 		if (!cl_s)
 			return -ENOMEM;
 		i = 0; /* the i'th udc */
···
 	 * the check on the size is done later, when we have the lock
 	 */
 	if (repl->num_counters) {
-		unsigned long size = repl->num_counters * sizeof(*counterstmp);
-		counterstmp = vmalloc(size);
+		counterstmp = vmalloc_array(repl->num_counters,
+					    sizeof(*counterstmp));
 		if (!counterstmp)
 			return -ENOMEM;
 	}
···
 	if (num_counters == 0)
 		return -EINVAL;
 
-	tmp = vmalloc(array_size(num_counters, sizeof(*tmp)));
+	tmp = vmalloc_array(num_counters, sizeof(*tmp));
 	if (!tmp)
 		return -ENOMEM;
 
···
 	if (num_counters != nentries)
 		return -EINVAL;
 
-	counterstmp = vmalloc(array_size(nentries, sizeof(*counterstmp)));
+	counterstmp = vmalloc_array(nentries, sizeof(*counterstmp));
 	if (!counterstmp)
 		return -ENOMEM;
 

net/ipv4/netfilter/nf_reject_ipv4.c

···
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_bridge.h>
 
+static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
+					 const struct sk_buff *oldskb,
+					 __u8 protocol, int ttl);
+static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
+				    const struct tcphdr *oth);
+static const struct tcphdr *
+nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
+			struct tcphdr *_oth, int hook);
+
 static int nf_reject_iphdr_validate(struct sk_buff *skb)
 {
 	struct iphdr *iph;
···
 }
 EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach);
 
-const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
-					     struct tcphdr *_oth, int hook)
+static const struct tcphdr *
+nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
+			struct tcphdr *_oth, int hook)
 {
 	const struct tcphdr *oth;
 
···
 
 	return oth;
 }
-EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get);
 
-struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
-				  const struct sk_buff *oldskb,
-				  __u8 protocol, int ttl)
+static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb,
+					 const struct sk_buff *oldskb,
+					 __u8 protocol, int ttl)
 {
 	struct iphdr *niph, *oiph = ip_hdr(oldskb);
 
···
 
 	return niph;
 }
-EXPORT_SYMBOL_GPL(nf_reject_iphdr_put);
 
-void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
-			  const struct tcphdr *oth)
+static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb,
+				    const struct tcphdr *oth)
 {
 	struct iphdr *niph = ip_hdr(nskb);
 	struct tcphdr *tcph;
···
 	nskb->csum_start = (unsigned char *)tcph - nskb->head;
 	nskb->csum_offset = offsetof(struct tcphdr, check);
 }
-EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
 
 static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 {

net/ipv6/netfilter/nf_reject_ipv6.c

···
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_bridge.h>
 
+static struct ipv6hdr *
+nf_reject_ip6hdr_put(struct sk_buff *nskb,
+		     const struct sk_buff *oldskb,
+		     __u8 protocol, int hoplimit);
+static void
+nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
+			 const struct sk_buff *oldskb,
+			 const struct tcphdr *oth, unsigned int otcplen);
+static const struct tcphdr *
+nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
+			 struct tcphdr *otcph,
+			 unsigned int *otcplen, int hook);
+
 static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
···
 }
 EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach);
 
-const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
-					      struct tcphdr *otcph,
-					      unsigned int *otcplen, int hook)
+static const struct tcphdr *
+nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
+			 struct tcphdr *otcph,
+			 unsigned int *otcplen, int hook)
 {
 	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
 	u8 proto;
···
 
 	return otcph;
 }
-EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get);
 
-struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb,
-				     const struct sk_buff *oldskb,
-				     __u8 protocol, int hoplimit)
+static struct ipv6hdr *
+nf_reject_ip6hdr_put(struct sk_buff *nskb,
+		     const struct sk_buff *oldskb,
+		     __u8 protocol, int hoplimit)
 {
 	struct ipv6hdr *ip6h;
 	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
···
 
 	return ip6h;
 }
-EXPORT_SYMBOL_GPL(nf_reject_ip6hdr_put);
 
-void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
-			      const struct sk_buff *oldskb,
-			      const struct tcphdr *oth, unsigned int otcplen)
+static void
+nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
+			 const struct sk_buff *oldskb,
+			 const struct tcphdr *oth, unsigned int otcplen)
 {
 	struct tcphdr *tcph;
 
···
 				      csum_partial(tcph,
 						   sizeof(struct tcphdr), 0));
 }
-EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put);
 
 static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 {

net/netfilter/nf_tables_api.c

···
 	bitmap_zero(ctx->reg_inited, NFT_REG32_NUM);
 }
 
-static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
-					     int msg_type, u32 size, gfp_t gfp)
+static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx,
+					 int msg_type, u32 size)
 {
 	struct nft_trans *trans;
 
-	trans = kzalloc(size, gfp);
+	trans = kzalloc(size, GFP_KERNEL);
 	if (trans == NULL)
 		return NULL;
 
···
 	trans->report = ctx->report;
 
 	return trans;
-}
-
-static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx,
-					 int msg_type, u32 size)
-{
-	return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL);
 }
 
 static struct nft_trans_binding *nft_trans_get_binding(struct nft_trans *trans)
···
 
 static bool nft_trans_collapse_set_elem(struct nftables_pernet *nft_net,
 					struct nft_trans_elem *tail,
-					struct nft_trans_elem *trans,
-					gfp_t gfp)
+					struct nft_trans_elem *trans)
 {
 	unsigned int nelems, old_nelems = tail->nelems;
 	struct nft_trans_elem *new_trans;
···
 	/* krealloc might free tail which invalidates list pointers */
 	list_del_init(&tail->nft_trans.list);
 
-	new_trans = krealloc(tail, struct_size(tail, elems, nelems), gfp);
+	new_trans = krealloc(tail, struct_size(tail, elems, nelems),
+			     GFP_KERNEL);
 	if (!new_trans) {
-		list_add_tail(&tail->nft_trans.list, &nft_net->commit_list);
+		list_add_tail(&tail->nft_trans.list,
+			      &nft_net->commit_list);
 		return false;
 	}
 
···
 }
 
 static bool nft_trans_try_collapse(struct nftables_pernet *nft_net,
-				   struct nft_trans *trans, gfp_t gfp)
+				   struct nft_trans *trans)
 {
 	struct nft_trans *tail;
 
···
 	case NFT_MSG_DELSETELEM:
 		return nft_trans_collapse_set_elem(nft_net,
 						   nft_trans_container_elem(tail),
-						   nft_trans_container_elem(trans), gfp);
+						   nft_trans_container_elem(trans));
 	}
 
 	return false;
···
 	}
 }
 
-static void nft_trans_commit_list_add_elem(struct net *net, struct nft_trans *trans,
-					   gfp_t gfp)
+static void nft_trans_commit_list_add_elem(struct net *net, struct nft_trans *trans)
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 
 	WARN_ON_ONCE(trans->msg_type != NFT_MSG_NEWSETELEM &&
 		     trans->msg_type != NFT_MSG_DELSETELEM);
 
-	might_alloc(gfp);
-
-	if (nft_trans_try_collapse(nft_net, trans, gfp)) {
+	if (nft_trans_try_collapse(nft_net, trans)) {
 		kfree(trans);
 		return;
 	}
···
 						}
 
 						ue->priv = elem_priv;
-						nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL);
+						nft_trans_commit_list_add_elem(ctx->net, trans);
 						goto err_elem_free;
 					}
 				}
···
 	}
 
 	nft_trans_container_elem(trans)->elems[0].priv = elem.priv;
-	nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL);
+	nft_trans_commit_list_add_elem(ctx->net, trans);
 	return 0;
 
 err_set_full:
···
 	nft_setelem_data_deactivate(ctx->net, set, elem.priv);
 
 	nft_trans_container_elem(trans)->elems[0].priv = elem.priv;
-	nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL);
+	nft_trans_commit_list_add_elem(ctx->net, trans);
 	return 0;
 
 fail_ops:
···
 	if (!nft_set_elem_active(ext, iter->genmask))
 		return 0;
 
-	trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM,
-				    struct_size_t(struct nft_trans_elem, elems, 1),
-				    GFP_ATOMIC);
+	trans = nft_trans_alloc(ctx, NFT_MSG_DELSETELEM,
+				struct_size_t(struct nft_trans_elem, elems, 1));
 	if (!trans)
 		return -ENOMEM;
 
···
 	nft_trans_elem_set(trans) = set;
 	nft_trans_container_elem(trans)->nelems = 1;
 	nft_trans_container_elem(trans)->elems[0].priv = elem_priv;
-	nft_trans_commit_list_add_elem(ctx->net, trans, GFP_ATOMIC);
+	nft_trans_commit_list_add_elem(ctx->net, trans);
 
 	return 0;
 }
···
 
 	nft_setelem_data_deactivate(ctx->net, set, elem_priv);
 	nft_trans_container_elem(trans)->elems[0].priv = elem_priv;
-	nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL);
+	nft_trans_commit_list_add_elem(ctx->net, trans);
 
 	return 0;
 }

net/netfilter/nft_payload.c

···
 
 /* add vlan header into the user buffer for if tag was removed by offloads */
 static bool
-nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
+nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u16 offset, u8 len)
 {
 	int mac_off = skb_mac_header(skb) - skb->data;
 	u8 *vlanh, *dst_u8 = (u8 *) d;
···
 	[NFTA_PAYLOAD_SREG]		= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_DREG]		= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_BASE]		= { .type = NLA_U32 },
-	[NFTA_PAYLOAD_OFFSET]		= NLA_POLICY_MAX(NLA_BE32, 255),
+	[NFTA_PAYLOAD_OFFSET]		= { .type = NLA_BE32 },
 	[NFTA_PAYLOAD_LEN]		= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_PAYLOAD_CSUM_TYPE]	= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_CSUM_OFFSET]	= NLA_POLICY_MAX(NLA_BE32, 255),
···
 
 static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum)
 {
-	*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum));
+	csum_replace4(sum, (__force __be32)fsum, (__force __be32)tsum);
 	if (*sum == 0)
 		*sum = CSUM_MANGLED_0;
 }
···
 
 struct nft_payload_set {
 	enum nft_payload_bases	base:8;
-	u8			offset;
+	u16			offset;
 	u8			len;
 	u8			sreg;
 	u8			csum_type;
···
 };
 
 static bool
-nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len,
+nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u16 offset, u8 len,
 		     int *vlan_hlen)
 {
 	struct nft_payload_vlan_hdr *vlanh;
···
 				const struct nft_expr *expr,
 				const struct nlattr * const tb[])
 {
+	u32 csum_offset, offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
 	struct nft_payload_set *priv = nft_expr_priv(expr);
-	u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
 	int err;
 
 	priv->base        = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
-	priv->offset      = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len         = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U16_MAX, &offset);
+	if (err < 0)
+		return err;
+	priv->offset = offset;
 
 	if (tb[NFTA_PAYLOAD_CSUM_TYPE])
 		csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
···
 	if (tb[NFTA_PAYLOAD_DREG] == NULL)
 		return ERR_PTR(-EINVAL);
 
-	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U16_MAX, &offset);
 	if (err < 0)
 		return ERR_PTR(err);
 

net/netfilter/nft_set_hash.c

···
 struct nft_rhash_elem {
 	struct nft_elem_priv		priv;
 	struct rhash_head		node;
+	struct llist_node		walk_node;
 	u32				wq_gc_seq;
 	struct nft_set_ext		ext;
 };
···
 		goto err1;
 
 	he = nft_elem_priv_cast(elem_priv);
+	init_llist_node(&he->walk_node);
 	prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
 						nft_rhash_params);
 	if (IS_ERR(prev))
···
 	};
 	struct nft_rhash_elem *prev;
 
+	init_llist_node(&he->walk_node);
 	prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
 						nft_rhash_params);
 	if (IS_ERR(prev))
···
 	return true;
 }
 
-static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
-			   struct nft_set_iter *iter)
+static void nft_rhash_walk_ro(const struct nft_ctx *ctx, struct nft_set *set,
+			      struct nft_set_iter *iter)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
-	struct nft_rhash_elem *he;
 	struct rhashtable_iter hti;
+	struct nft_rhash_elem *he;
 
 	rhashtable_walk_enter(&priv->ht, &hti);
 	rhashtable_walk_start(&hti);
···
 	}
 	rhashtable_walk_stop(&hti);
 	rhashtable_walk_exit(&hti);
+}
+
+static void nft_rhash_walk_update(const struct nft_ctx *ctx,
+				  struct nft_set *set,
+				  struct nft_set_iter *iter)
+{
+	struct nft_rhash *priv = nft_set_priv(set);
+	struct nft_rhash_elem *he, *tmp;
+	struct llist_node *first_node;
+	struct rhashtable_iter hti;
+	LLIST_HEAD(walk_list);
+
+	lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
+
+	if (set->in_update_walk) {
+		/* This can happen with bogus rulesets during ruleset validation
+		 * when a verdict map causes a jump back to the same map.
+		 *
+		 * Without this extra check the walk_next loop below will see
+		 * elems on the callers walk_list and skip (not validate) them.
+		 */
+		iter->err = -EMLINK;
+		return;
+	}
+
+	/* walk happens under RCU.
+	 *
+	 * We create a snapshot list so ->iter callback can sleep.
+	 * commit_mutex is held, elements can ...
+	 * .. be added in parallel from dataplane (dynset)
+	 * .. be marked as dead in parallel from dataplane (dynset).
+	 * .. be queued for removal in parallel (gc timeout).
+	 * .. not be freed: transaction mutex is held.
+	 */
+	rhashtable_walk_enter(&priv->ht, &hti);
+	rhashtable_walk_start(&hti);
+
+	while ((he = rhashtable_walk_next(&hti))) {
+		if (IS_ERR(he)) {
+			if (PTR_ERR(he) != -EAGAIN) {
+				iter->err = PTR_ERR(he);
+				break;
+			}
+
+			continue;
+		}
+
+		/* rhashtable resized during walk, skip */
+		if (llist_on_list(&he->walk_node))
+			continue;
+
+		llist_add(&he->walk_node, &walk_list);
+	}
+	rhashtable_walk_stop(&hti);
+	rhashtable_walk_exit(&hti);
+
+	first_node = __llist_del_all(&walk_list);
+	set->in_update_walk = true;
+	llist_for_each_entry_safe(he, tmp, first_node, walk_node) {
+		if (iter->err == 0) {
+			iter->err = iter->fn(ctx, set, iter, &he->priv);
+			if (iter->err == 0)
+				iter->count++;
+		}
+
+		/* all entries must be cleared again, else next ->walk iteration
+		 * will skip entries.
+		 */
+		init_llist_node(&he->walk_node);
+	}
+	set->in_update_walk = false;
+}
+
+static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
+			   struct nft_set_iter *iter)
+{
+	switch (iter->type) {
+	case NFT_ITER_UPDATE:
+		/* only relevant for netlink dumps which use READ type */
+		WARN_ON_ONCE(iter->skip != 0);
+
+		nft_rhash_walk_update(ctx, set, iter);
+		break;
+	case NFT_ITER_READ:
+		nft_rhash_walk_ro(ctx, set, iter);
+		break;
+	default:
+		iter->err = -EINVAL;
+		WARN_ON_ONCE(1);
+		break;
+	}
 }
 
 static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set,

net/netfilter/nft_set_pipapo.c

···
 	local_bh_disable();
 
 #if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
-	if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX) &&
-	    irq_fpu_usable()) {
+	if (boot_cpu_has(X86_FEATURE_AVX2) && irq_fpu_usable()) {
 		e = pipapo_get_avx2(m, data, genmask, tstamp);
 		local_bh_enable();
 		return e;

net/netfilter/nft_set_pipapo_avx2.c

···
 	    desc->field_count < NFT_PIPAPO_MIN_FIELDS)
 		return false;
 
-	if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_AVX))
+	if (!boot_cpu_has(X86_FEATURE_AVX2))
 		return false;
 
 	est->size = pipapo_estimate_size(desc);

net/netfilter/nft_set_rbtree.c

···
 	return NULL;
 }
 
-static void nft_rbtree_walk(const struct nft_ctx *ctx,
-			    struct nft_set *set,
-			    struct nft_set_iter *iter)
+static void nft_rbtree_do_walk(const struct nft_ctx *ctx,
+			       struct nft_set *set,
+			       struct nft_set_iter *iter)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *node;
 
-	read_lock_bh(&priv->lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 
···
 			goto cont;
 
 		iter->err = iter->fn(ctx, set, iter, &rbe->priv);
-		if (iter->err < 0) {
-			read_unlock_bh(&priv->lock);
+		if (iter->err < 0)
 			return;
-		}
 cont:
 		iter->count++;
 	}
-	read_unlock_bh(&priv->lock);
+}
+
+static void nft_rbtree_walk(const struct nft_ctx *ctx,
+			    struct nft_set *set,
+			    struct nft_set_iter *iter)
+{
+	struct nft_rbtree *priv = nft_set_priv(set);
+
+	switch (iter->type) {
+	case NFT_ITER_UPDATE:
+		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
+		nft_rbtree_do_walk(ctx, set, iter);
+		break;
+	case NFT_ITER_READ:
+		read_lock_bh(&priv->lock);
+		nft_rbtree_do_walk(ctx, set, iter);
+		read_unlock_bh(&priv->lock);
+		break;
+	default:
+		iter->err = -EINVAL;
+		WARN_ON_ONCE(1);
+		break;
+	}
 }
 
 static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set,