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 <alice@isovalent.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260205133925.526371-3-alice.kernel@fastmail.im
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 57ab6c97ee7eba3e2b21b04cf6aa9ff9b13f56eb..bdbd63f9a85e9fd03c4a6da1b967834c8437bad0 100644 (file)
--- 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 e622a9e086cc0a3bc775fc87a379115bcf438e77..769c39fed1f38dd507d907a43ca21a2023245999 100644 (file)
--- 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);