net/ipv6: Introduce payload_len helpers

The next commits will transition away from using the hop-by-hop
extension header to encode packet length for BIG TCP. Add wrappers
around ip6->payload_len that return the actual value if it's non-zero,
and calculate it from skb->len if payload_len is set to zero (and a
symmetrical setter).

The new helpers are used wherever the surrounding code supports the
hop-by-hop jumbo header for BIG TCP IPv6, or the corresponding IPv4 code
uses skb_ip_totlen (e.g., in include/net/netfilter/nf_tables_ipv6.h).

No behavioral change in this commit.

Signed-off-by: Alice Mikityanska <alice@isovalent.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260205133925.526371-2-alice.kernel@fastmail.im
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: gentoo-root

include/linux/ipv6.h

@@ -126,6 +126,28 @@ static inline unsigned int ipv6_transport_len(const struct sk_buff *skb)
 	       skb_network_header_len(skb);
 }
 
+static inline unsigned int
+ipv6_payload_len(const struct sk_buff *skb, const struct ipv6hdr *ip6)
+{
+	u32 len = ntohs(ip6->payload_len);
+
+	return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ?
+		len :
+		skb->len - skb_network_offset(skb) - sizeof(struct ipv6hdr);
+}
+
+static inline unsigned int skb_ipv6_payload_len(const struct sk_buff *skb)
+{
+	return ipv6_payload_len(skb, ipv6_hdr(skb));
+}
+
+#define IPV6_MAXPLEN		65535
+
+static inline void ipv6_set_payload_len(struct ipv6hdr *ip6, unsigned int len)
+{
+	ip6->payload_len = len <= IPV6_MAXPLEN ? htons(len) : 0;
+}
+
 /* 
    This structure contains results of exthdrs parsing
    as offsets from skb->nh.

include/net/ipv6.h

@@ -25,8 +25,6 @@ struct ip_tunnel_info;
 
 #define SIN6_LEN_RFC2133	24
 
-#define IPV6_MAXPLEN		65535
-
 /*
  *	NextHeader field of IPv6 header
  */

include/net/netfilter/nf_tables_ipv6.h

@@ -42,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
 	if (ip6h->version != 6)
 		return -1;
 
-	pkt_len = ntohs(ip6h->payload_len);
+	pkt_len = ipv6_payload_len(pkt->skb, ip6h);
 	skb_len = pkt->skb->len - skb_network_offset(pkt->skb);
 	if (pkt_len + sizeof(*ip6h) > skb_len)
 		return -1;
@@ -86,7 +86,7 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt)
 	if (ip6h->version != 6)
 		goto inhdr_error;
 
-	pkt_len = ntohs(ip6h->payload_len);
+	pkt_len = ipv6_payload_len(pkt->skb, ip6h);
 	if (pkt_len + sizeof(*ip6h) > pkt->skb->len) {
 		idev = __in6_dev_get(nft_in(pkt));
 		__IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS);

net/bridge/br_netfilter_ipv6.c

@@ -58,7 +58,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb)
 	if (hdr->version != 6)
 		goto inhdr_error;
 
-	pkt_len = ntohs(hdr->payload_len);
+	pkt_len = ipv6_payload_len(skb, hdr);
 	if (hdr->nexthdr == NEXTHDR_HOP && nf_ip6_check_hbh_len(skb, &pkt_len))
 		goto drop;
 

net/bridge/netfilter/nf_conntrack_bridge.c

@@ -229,7 +229,7 @@ static int nf_ct_br_ipv6_check(const struct sk_buff *skb)
 	if (hdr->version != 6)
 		return -1;
 
-	len = ntohs(hdr->payload_len) + sizeof(struct ipv6hdr) + nhoff;
+	len = ipv6_payload_len(skb, hdr) + sizeof(struct ipv6hdr) + nhoff;
 	if (skb->len < len)
 		return -1;
 
@@ -269,7 +269,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
 		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 			return NF_ACCEPT;
 
-		len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+		len = sizeof(struct ipv6hdr) + skb_ipv6_payload_len(skb);
 		if (pskb_trim_rcsum(skb, len))
 			return NF_ACCEPT;
 

net/ipv6/ip6_input.c

@@ -262,7 +262,7 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
-	pkt_len = ntohs(hdr->payload_len);
+	pkt_len = ipv6_payload_len(skb, hdr);
 
 	/* pkt_len may be zero if Jumbo payload option is present */
 	if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {

net/ipv6/ip6_offload.c

@@ -366,12 +366,11 @@ INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 		hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen);
 
 		iph->nexthdr = NEXTHDR_HOP;
-		iph->payload_len = 0;
-	} else {
-		iph = (struct ipv6hdr *)(skb->data + nhoff);
-		iph->payload_len = htons(payload_len);
 	}
 
+	iph = (struct ipv6hdr *)(skb->data + nhoff);
+	ipv6_set_payload_len(iph, payload_len);
+
 	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
 
 	if (likely(ops == &net_hotdata.tcpv6_offload))

net/ipv6/output_core.c

@@ -125,12 +125,7 @@ EXPORT_SYMBOL(ip6_dst_hoplimit);
 
 int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	int len;
-
-	len = skb->len - sizeof(struct ipv6hdr);
-	if (len > IPV6_MAXPLEN)
-		len = 0;
-	ipv6_hdr(skb)->payload_len = htons(len);
+	ipv6_set_payload_len(ipv6_hdr(skb), skb->len - sizeof(struct ipv6hdr));
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
 	/* if egress device is enslaved to an L3 master device pass the

net/netfilter/ipvs/ip_vs_xmit.c

@@ -949,7 +949,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 		*next_protocol = IPPROTO_IPV6;
 		if (payload_len)
 			*payload_len =
-				ntohs(old_ipv6h->payload_len) +
+				ipv6_payload_len(skb, old_ipv6h) +
 				sizeof(*old_ipv6h);
 		old_dsfield = ipv6_get_dsfield(old_ipv6h);
 		*ttl = old_ipv6h->hop_limit;

net/netfilter/nf_conntrack_ovs.c

@@ -121,7 +121,7 @@ int nf_ct_skb_network_trim(struct sk_buff *skb, int family)
 		len = skb_ip_totlen(skb);
 		break;
 	case NFPROTO_IPV6:
-		len = ntohs(ipv6_hdr(skb)->payload_len);
+		len = skb_ipv6_payload_len(skb);
 		if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) {
 			int err = nf_ip6_check_hbh_len(skb, &len);