From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org,
pabeni@redhat.com, edumazet@kernel.org, horms@kernel.org,
fw@strlen.de, ja@ssi.bg
Subject: [PATCH net-next 15/15] netfilter: flowtable: unify tunnel push for IPv4 and IPv6
Date: Sun, 18 Oct 2026 02:56:38 +0200 [thread overview]
Message-ID: <20261018005638.1776148-16-pablo@netfilter.org> (raw)
In-Reply-To: <20261018005638.1776148-1-pablo@netfilter.org>
From: Lorenzo Bianconi <lorenzo.bianconi@oss.qualcomm.com>
Refactor nf_flow_tunnel_ipip_push() and nf_flow_tunnel_ip6ip6_push()
into nf_flow_tunnel_ip_push() and nf_flow_tunnel_ip6_push(), keying the
inner header handling off tuple->tun.inner_proto so both IP-in-IP and
IPv6-in-IPv6 inner protocols are supported regardless of the outer
address family. Replace nf_flow_tunnel_v4_push() and
nf_flow_tunnel_v6_push() with a single nf_flow_tunnel_push() that
dispatches on tuple->tun.encap_proto, and set skb->protocol explicitly
after pushing the outer header.
This is a preliminary patch to support IPv4 over IPv6 and SIT tunnel
flowtable offload.
Please note IPv4 over IPv6 and SIT tunnel flowtable offloading is not
enabled yet.
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@oss.qualcomm.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_ip.c | 143 +++++++++++++++++++------------
1 file changed, 87 insertions(+), 56 deletions(-)
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 29a769736dbf..e13f9397e8cb 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -587,23 +587,44 @@ static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id,
return 0;
}
-static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb,
- struct flow_offload_tuple *tuple,
- struct dst_entry *dst, __be32 *ip_daddr)
+static int nf_flow_tunnel_ip_push(struct net *net, struct sk_buff *skb,
+ struct flow_offload_tuple *tuple,
+ struct dst_entry *dst,
+ union nf_inet_addr **ip_addr)
{
- struct iphdr *iph = (struct iphdr *)skb_network_header(skb);
- struct rtable *rt = dst_rtable(dst);
- u8 tos = iph->tos, ttl = iph->ttl;
- __be16 frag_off = iph->frag_off;
- u32 headroom = sizeof(*iph);
+ __be16 frag_off = 0;
+ struct iphdr *iph;
+ u8 tos = 0, ttl;
+ u32 headroom;
int err;
+ switch (tuple->tun.inner_proto) {
+ case IPPROTO_IPV6: {
+ struct ipv6hdr *ip6h;
+
+ ip6h = (struct ipv6hdr *)skb_network_header(skb);
+ tos = ipv6_get_dsfield(ip6h);
+ ttl = ip6h->hop_limit;
+ frag_off = htons(IP_DF);
+ break;
+ }
+ case IPPROTO_IPIP:
+ iph = (struct iphdr *)skb_network_header(skb);
+ frag_off = iph->frag_off;
+ tos = iph->tos;
+ ttl = iph->ttl;
+ break;
+ default:
+ return 0;
+ }
+
err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4);
if (err)
return err;
- skb_set_inner_ipproto(skb, IPPROTO_IPIP);
- headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
+ skb_set_inner_ipproto(skb, tuple->tun.inner_proto);
+ headroom = sizeof(*iph) + LL_RESERVED_SPACE(dst->dev) +
+ dst->header_len;
err = skb_cow_head(skb, headroom);
if (err)
return err;
@@ -614,11 +635,12 @@ static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb,
/* Push down and install the IP header. */
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
+ skb->protocol = htons(ETH_P_IP);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(*iph) >> 2;
- iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : frag_off;
+ iph->frag_off = ip_mtu_locked(dst) ? 0 : frag_off;
iph->protocol = tuple->tun.inner_proto;
iph->tos = tos;
iph->daddr = tuple->tun.src_v4.s_addr;
@@ -628,81 +650,91 @@ static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb,
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
ip_send_check(iph);
- *ip_daddr = tuple->tun.src_v4.s_addr;
-
- return 0;
-}
-
-static int nf_flow_tunnel_v4_push(struct net *net, struct sk_buff *skb,
- struct flow_offload_tuple *tuple,
- struct dst_entry *dst, __be32 *ip_daddr)
-{
- if (tuple->tun_num)
- return nf_flow_tunnel_ipip_push(net, skb, tuple, dst, ip_daddr);
+ *ip_addr = (union nf_inet_addr *)&tuple->tun.src_v4;
return 0;
}
-static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
- struct flow_offload_tuple *tuple,
- struct dst_entry *dst,
- struct in6_addr **ip6_daddr)
+static int nf_flow_tunnel_ip6_push(struct net *net, struct sk_buff *skb,
+ struct flow_offload_tuple *tuple,
+ struct dst_entry *dst,
+ union nf_inet_addr **ip_addr)
{
- struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb);
- __u8 dsfield = ipv6_get_dsfield(ip6h);
- struct rtable *rt = dst_rtable(dst);
struct flowi6 fl6 = {
.daddr = tuple->tun.src_v6,
.saddr = tuple->tun.dst_v6,
- .flowi6_proto = IPPROTO_IPV6,
+ .flowi6_proto = tuple->tun.inner_proto,
};
- u8 hop_limit = ip6h->hop_limit;
+ u8 hop_limit, dsfield;
+ struct ipv6hdr *ip6h;
int err, mtu;
u32 headroom;
+ switch (tuple->tun.inner_proto) {
+ case IPPROTO_IPIP: {
+ struct iphdr *iph = (struct iphdr *)skb_network_header(skb);
+
+ dsfield = ipv4_get_dsfield(iph);
+ hop_limit = iph->ttl;
+ break;
+ }
+ case IPPROTO_IPV6:
+ ip6h = (struct ipv6hdr *)skb_network_header(skb);
+ dsfield = ipv6_get_dsfield(ip6h);
+ hop_limit = ip6h->hop_limit;
+ break;
+ default:
+ return 0;
+ }
+
err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
if (err)
return err;
- skb_set_inner_ipproto(skb, IPPROTO_IPV6);
- headroom = sizeof(*ip6h) + LL_RESERVED_SPACE(rt->dst.dev) +
- rt->dst.header_len;
+ skb_set_inner_ipproto(skb, tuple->tun.inner_proto);
+ headroom = sizeof(*ip6h) + LL_RESERVED_SPACE(dst->dev) +
+ dst->header_len;
err = skb_cow_head(skb, headroom);
if (err)
return err;
skb_scrub_packet(skb, true);
- mtu = dst_mtu(&rt->dst) - sizeof(*ip6h);
+ mtu = dst_mtu(dst) - sizeof(*ip6h);
mtu = max(mtu, IPV6_MIN_MTU);
skb_dst_update_pmtu_no_confirm(skb, mtu);
skb_push(skb, sizeof(*ip6h));
skb_reset_network_header(skb);
+ skb->protocol = htons(ETH_P_IPV6);
ip6h = ipv6_hdr(skb);
ip6_flow_hdr(ip6h, dsfield,
ip6_make_flowlabel(net, skb, fl6.flowlabel, true, &fl6));
ip6h->hop_limit = hop_limit;
- ip6h->nexthdr = IPPROTO_IPV6;
+ ip6h->nexthdr = tuple->tun.inner_proto;
ip6h->daddr = tuple->tun.src_v6;
ip6h->saddr = tuple->tun.dst_v6;
ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(*ip6h));
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
- *ip6_daddr = &tuple->tun.src_v6;
+ *ip_addr = (union nf_inet_addr *)&tuple->tun.src_v6;
return 0;
}
-static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb,
- struct flow_offload_tuple *tuple,
- struct dst_entry *dst,
- struct in6_addr **ip6_daddr)
+static int nf_flow_tunnel_push(struct net *net, struct sk_buff *skb,
+ struct flow_offload_tuple *tuple,
+ struct dst_entry *dst,
+ union nf_inet_addr **ip_addr)
{
- if (tuple->tun_num)
- return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, dst, ip6_daddr);
-
- return 0;
+ switch (tuple->tun.encap_proto) {
+ case AF_INET:
+ return nf_flow_tunnel_ip_push(net, skb, tuple, dst, ip_addr);
+ case AF_INET6:
+ return nf_flow_tunnel_ip6_push(net, skb, tuple, dst, ip_addr);
+ default:
+ return 0;
+ }
}
static int nf_flow_encap_push(struct sk_buff *skb,
@@ -809,10 +841,10 @@ static int nf_flow_queue_xmit4(struct sk_buff *skb,
struct flow_offload_tuple *other_tuple;
enum flow_offload_tuple_dir dir;
struct nf_flow_xmit xmit = {};
+ union nf_inet_addr *ip_addr;
struct flow_offload *flow;
struct neighbour *neigh;
struct rtable *rt;
- __be32 ip_daddr;
if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
rt = dst_rtable(tuplehash->tuple.dst_cache);
@@ -825,10 +857,10 @@ static int nf_flow_queue_xmit4(struct sk_buff *skb,
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
other_tuple = &flow->tuplehash[!dir].tuple;
- ip_daddr = other_tuple->src_v4.s_addr;
+ ip_addr = (union nf_inet_addr *)&other_tuple->src_v4;
- if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple,
- tuplehash->tuple.dst_cache, &ip_daddr) < 0)
+ if (nf_flow_tunnel_push(state->net, skb, other_tuple,
+ tuplehash->tuple.dst_cache, &ip_addr) < 0)
return NF_DROP;
switch (tuplehash->tuple.xmit_type) {
@@ -839,7 +871,7 @@ static int nf_flow_queue_xmit4(struct sk_buff *skb,
flow_offload_teardown(flow);
return NF_DROP;
}
- neigh = ip_neigh_gw4(rt->dst.dev, rt_nexthop(rt, ip_daddr));
+ neigh = ip_neigh_gw4(rt->dst.dev, rt_nexthop(rt, ip_addr->ip));
if (IS_ERR(neigh)) {
flow_offload_teardown(flow);
return NF_DROP;
@@ -1137,7 +1169,7 @@ static int nf_flow_queue_xmit6(struct sk_buff *skb,
struct flow_offload_tuple *other_tuple;
enum flow_offload_tuple_dir dir;
struct nf_flow_xmit xmit = {};
- struct in6_addr *ip6_daddr;
+ union nf_inet_addr *ip_addr;
struct flow_offload *flow;
struct neighbour *neigh;
struct rt6_info *rt;
@@ -1153,11 +1185,10 @@ static int nf_flow_queue_xmit6(struct sk_buff *skb,
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
other_tuple = &flow->tuplehash[!dir].tuple;
- ip6_daddr = &other_tuple->src_v6;
+ ip_addr = (union nf_inet_addr *)&other_tuple->src_v6;
- if (nf_flow_tunnel_v6_push(state->net, skb, other_tuple,
- tuplehash->tuple.dst_cache,
- &ip6_daddr) < 0)
+ if (nf_flow_tunnel_push(state->net, skb, other_tuple,
+ tuplehash->tuple.dst_cache, &ip_addr) < 0)
return NF_DROP;
switch (tuplehash->tuple.xmit_type) {
@@ -1168,7 +1199,7 @@ static int nf_flow_queue_xmit6(struct sk_buff *skb,
flow_offload_teardown(flow);
return NF_DROP;
}
- neigh = ip_neigh_gw6(rt->dst.dev, rt6_nexthop(rt, ip6_daddr));
+ neigh = ip_neigh_gw6(rt->dst.dev, rt6_nexthop(rt, &ip_addr->in6));
if (IS_ERR(neigh)) {
flow_offload_teardown(flow);
return NF_DROP;
--
2.47.3
prev parent reply other threads:[~2026-10-18 0:57 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-18 0:56 [PATCH net-next 00/15] Netfilter updates for net-next Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 01/15] netfilter: disable br_netfilter in user namespaces Pablo Neira Ayuso
2026-10-18 1:03 ` netdev-bot+sinfo
2026-10-18 1:20 ` Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 9:15 ` Pablo Neira Ayuso
2026-10-20 21:00 ` patchwork-bot+netdevbpf
2026-10-18 0:56 ` [PATCH net-next 02/15] selftests: netfilter: nft_queue.sh: only queue icmp echo request/reply Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 4:23 ` Florian Westphal
2026-10-19 9:12 ` Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 03/15] ipvs: fix buffer overflow when sending sync messages Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 04/15] netfilter: nf_queue: limit the hook drop flush to the unregistered hook point Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 4:49 ` Florian Westphal
2026-10-19 9:18 ` Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 05/15] selftests: netfilter: nft_queue: check the scope of the hook drop flush Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 4:54 ` Florian Westphal
2026-10-18 0:56 ` [PATCH net-next 06/15] netfilter: conntrack: fix unlikely UaF in gc worker Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 07/15] netfilter: nf_tables: switch chain_types array to rcu Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 5:00 ` Florian Westphal
2026-10-18 0:56 ` [PATCH net-next 08/15] netfilter: nft_exthdr: remove redundant op parsing in tcp_set_init Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 09/15] netfilter: nft_exthdr: avoid 60 bytes stack buffer in TCP option mangling Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 9:11 ` Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 10/15] selftests: netfilter: fix return value in zone subtest Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 11/15] netfilter: nft_compat: restrict raw table targets/matches Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 5:17 ` Florian Westphal
2026-10-18 0:56 ` [PATCH net-next 12/15] netfilter: flowtable: set inner protocol when popping tunnel header Pablo Neira Ayuso
2026-10-19 1:21 ` netdev-bot+sashiko
2026-10-19 9:11 ` Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 13/15] netfilter: flowtable: populate tunnel tuple regardless of inner protocol Pablo Neira Ayuso
2026-10-18 0:56 ` [PATCH net-next 14/15] netfilter: flowtable: add encap_proto to flow_offload_tunnel Pablo Neira Ayuso
2026-10-18 0:56 ` Pablo Neira Ayuso [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261018005638.1776148-16-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=edumazet@kernel.org \
--cc=fw@strlen.de \
--cc=horms@kernel.org \
--cc=ja@ssi.bg \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.