From b409a7f7176bb8fc0002b8592d14b11ebe481b1d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 30 Jan 2026 21:03:03 +0000 Subject: ipv6: colocate inet6_cork in inet_cork_full All inet6_cork users also use one inet_cork_full. Reduce number of parameters and increase data locality. This saves ~275 bytes of code on x86_64. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260130210303.3888261-9-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 7294e4e89b79..20aae8357dd1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -205,13 +205,6 @@ struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; -struct inet6_cork { - struct ipv6_txoptions *opt; - u8 hop_limit; - u8 tclass; - u8 dontfrag:1; -}; - /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ @@ -267,7 +260,6 @@ struct ipv6_pinfo { struct sk_buff *pktoptions; struct sk_buff *rxpmtu; - struct inet6_cork cork; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; -- cgit v1.2.3 From b2936b4fd56294e49d6c8e9152ea6c4982757c7d Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Thu, 5 Feb 2026 15:39:14 +0200 Subject: 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 Acked-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260205133925.526371-2-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 22 ++++++++++++++++++++++ include/net/ipv6.h | 2 -- include/net/netfilter/nf_tables_ipv6.h | 4 ++-- net/bridge/br_netfilter_ipv6.c | 2 +- net/bridge/netfilter/nf_conntrack_bridge.c | 4 ++-- net/ipv6/ip6_input.c | 2 +- net/ipv6/ip6_offload.c | 7 +++---- net/ipv6/output_core.c | 7 +------ net/netfilter/ipvs/ip_vs_xmit.c | 2 +- net/netfilter/nf_conntrack_ovs.c | 2 +- net/netfilter/nf_log_syslog.c | 2 +- net/sched/sch_cake.c | 2 +- 12 files changed, 36 insertions(+), 22 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 20aae8357dd1..57ab6c97ee7e 100644 --- a/include/linux/ipv6.h +++ b/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. diff --git a/include/net/ipv6.h b/include/net/ipv6.h index c27b9d7aeb7c..1c2d6095b050 100644 --- a/include/net/ipv6.h +++ b/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 */ diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index a0633eeaec97..c53ac00bb974 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/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); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index e0421eaa3abc..76ce70b4e7f3 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/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; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 3b28b84191be..58a33d0380b0 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/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; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 168ec07e31cc..2bcb981c91aa 100644 --- a/net/ipv6/ip6_input.c +++ b/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) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 32a104ead876..ceb4752a5358 100644 --- a/net/ipv6/ip6_offload.c +++ b/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)) diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 1c9b283a4132..cba1684a3f30 100644 --- a/net/ipv6/output_core.c +++ b/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 diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 64c697212578..f861d116cc33 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/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; diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c index 068e9489e1c2..a6988eeb1579 100644 --- a/net/netfilter/nf_conntrack_ovs.c +++ b/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); diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index 86d5fc5d28e3..41503847d9d7 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -561,7 +561,7 @@ dump_ipv6_packet(struct net *net, struct nf_log_buf *m, /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ nf_log_buf_add(m, "LEN=%zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", - ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + ipv6_payload_len(skb, ih) + sizeof(struct ipv6hdr), (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, ih->hop_limit, (ntohl(*(__be32 *)ih) & 0x000fffff)); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index fd56b7d88301..d2bbd5654d5b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1279,7 +1279,7 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr)) continue; - seglen = ntohs(ipv6h_check->payload_len); + seglen = ipv6_payload_len(skb, ipv6h_check); } else { WARN_ON(1); /* shouldn't happen */ continue; -- cgit v1.2.3 From 741d069aa488866ae8425f87ad270ed3815ccaac Mon Sep 17 00:00:00 2001 From: Alice Mikityanska Date: Thu, 5 Feb 2026 15:39:15 +0200 Subject: net/ipv6: Drop HBH for BIG TCP on TX side BIG TCP IPv6 inserts a hop-by-hop extension header to indicate the real IPv6 payload length when it doesn't fit into the 16-bit field in the IPv6 header itself. While it helps tools parse the packet, it also requires every driver that supports TSO and BIG TCP to remove this 8-byte extension header. It might not sound that bad until we try to apply it to tunneled traffic. Currently, the drivers don't attempt to strip HBH if skb->encapsulation = 1. Moreover, trying to do so would require dissecting different tunnel protocols and making corresponding adjustments on case-by-case basis, which would slow down the fastpath (potentially also requiring adjusting checksums in outer headers). At the same time, BIG TCP IPv4 doesn't insert any extra headers and just calculates the payload length from skb->len, significantly simplifying implementing BIG TCP for tunnels. Stop inserting HBH when building BIG TCP GSO SKBs. Signed-off-by: Alice Mikityanska Acked-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260205133925.526371-3-alice.kernel@fastmail.im Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 1 - net/ipv6/ip6_output.c | 20 +++----------------- 2 files changed, 3 insertions(+), 18 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 57ab6c97ee7e..bdbd63f9a85e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -177,7 +177,6 @@ struct inet6_skb_parm { #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 -#define IP6SKB_FAKEJUMBO 512 #define IP6SKB_MULTIPATH 1024 #define IP6SKB_MCROUTE 2048 }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e622a9e086cc..769c39fed1f3 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -179,8 +179,7 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, static int ip6_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { - if (unlikely(!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && - !skb_gso_validate_network_len(skb, mtu))) + if (unlikely(!skb_gso_validate_network_len(skb, mtu))) return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); return ip6_finish_output2(net, sk, skb); @@ -273,8 +272,6 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct inet6_dev *idev = ip6_dst_idev(dst); - struct hop_jumbo_hdr *hop_jumbo; - int hoplen = sizeof(*hop_jumbo); struct net *net = sock_net(sk); unsigned int head_room; struct net_device *dev; @@ -287,7 +284,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, rcu_read_lock(); dev = dst_dev_rcu(dst); - head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev); + head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; @@ -313,19 +310,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, &fl6->saddr); } - if (unlikely(seg_len > IPV6_MAXPLEN)) { - hop_jumbo = __skb_push(skb, hoplen); - - hop_jumbo->nexthdr = proto; - hop_jumbo->hdrlen = 0; - hop_jumbo->tlv_type = IPV6_TLV_JUMBO; - hop_jumbo->tlv_len = 4; - hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen); - - proto = IPPROTO_HOPOPTS; + if (unlikely(seg_len > IPV6_MAXPLEN)) seg_len = 0; - IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO; - } __skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); -- cgit v1.2.3 From 03ff0cb1a9269a12c648e69e8b6ae6c2a723977c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Feb 2026 17:34:20 +0000 Subject: ipv6: add daddr/final storage in struct ipv6_pinfo After commit b409a7f7176b ("ipv6: colocate inet6_cork in inet_cork_full") we have room in ipv6_pinfo to hold daddr/final in case they need to be populated in fl6_update_dst() calls. This will allow stack canary removal in IPv6 tx fast paths. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260206173426.1638518-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bdbd63f9a85e..443053a76dcf 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -230,6 +230,10 @@ struct ipv6_fl_socklist; struct ipv6_pinfo { /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ struct in6_addr saddr; + union { + struct in6_addr daddr; + struct in6_addr final; + }; __be32 flow_label; u32 dst_cookie; struct ipv6_txoptions __rcu *opt; -- cgit v1.2.3