* [PATCH nf-next v5 1/2] net: netfilter: Add IPIP flowtable SW acceleration
2025-07-21 21:23 [PATCH nf-next v5 0/2] Add IPIP flowtable SW acceleratio Lorenzo Bianconi
@ 2025-07-21 21:23 ` Lorenzo Bianconi
2025-07-21 21:23 ` [PATCH nf-next v5 2/2] selftests: netfilter: nft_flowtable.sh: Add IPIP flowtable selftest Lorenzo Bianconi
2025-07-29 15:29 ` [PATCH nf-next v5 0/2] Add IPIP flowtable SW acceleratio Lorenzo Bianconi
2 siblings, 0 replies; 4+ messages in thread
From: Lorenzo Bianconi @ 2025-07-21 21:23 UTC (permalink / raw)
To: David S. Miller, David Ahern, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Jozsef Kadlecsik,
Shuah Khan, Andrew Lunn
Cc: Florian Westphal, netdev, netfilter-devel, coreteam,
linux-kselftest, Lorenzo Bianconi
Introduce SW acceleration for IPIP tunnels in the netfilter flowtable
infrastructure.
IPIP SW acceleration can be tested running the following scenario where
the traffic is forwarded between two NICs (eth0 and eth1) and an IPIP
tunnel is used to access a remote site (using eth1 as the underlay device):
ETH0 -- TUN0 <==> ETH1 -- [IP network] -- TUN1 (192.168.100.2)
$ip addr show
6: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
link/ether 00:00:22:33:11:55 brd ff:ff:ff:ff:ff:ff
inet 192.168.0.2/24 scope global eth0
valid_lft forever preferred_lft forever
7: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
link/ether 00:11:22:33:11:55 brd ff:ff:ff:ff:ff:ff
inet 192.168.1.1/24 scope global eth1
valid_lft forever preferred_lft forever
8: tun0@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1480 qdisc noqueue state UNKNOWN group default qlen 1000
link/ipip 192.168.1.1 peer 192.168.1.2
inet 192.168.100.1/24 scope global tun0
valid_lft forever preferred_lft forever
$ip route show
default via 192.168.100.2 dev tun0
192.168.0.0/24 dev eth0 proto kernel scope link src 192.168.0.2
192.168.1.0/24 dev eth1 proto kernel scope link src 192.168.1.1
192.168.100.0/24 dev tun0 proto kernel scope link src 192.168.100.1
$nft list ruleset
table inet filter {
flowtable ft {
hook ingress priority filter
devices = { eth0, eth1 }
}
chain forward {
type filter hook forward priority filter; policy accept;
meta l4proto { tcp, udp } flow add @ft
}
}
Reproducing the scenario described above using veths I got the following
results:
- TCP stream transmitted into the IPIP tunnel:
- net-next: ~41Gbps
- net-next + IPIP flowtbale support: ~40Gbps
- TCP stream received from the IPIP tunnel:
- net-next: ~35Gbps
- net-next + IPIP flowtbale support: ~49Gbps
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
include/linux/netdevice.h | 1 +
net/ipv4/ipip.c | 28 ++++++++++++++++++++
net/netfilter/nf_flow_table_ip.c | 56 ++++++++++++++++++++++++++++++++++++++--
net/netfilter/nft_flow_offload.c | 1 +
4 files changed, 84 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5aee8d3895f4c95adf1ab8a60d0564f17def2734..d6017da801c02c2887623b0288f48cc01c7dc358 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -873,6 +873,7 @@ enum net_device_path_type {
DEV_PATH_PPPOE,
DEV_PATH_DSA,
DEV_PATH_MTK_WDMA,
+ DEV_PATH_IPENCAP,
};
struct net_device_path {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 3e03af073a1ccc3d7597a998a515b6cfdded40b5..b7a3311bd061c341987380b5872caa8990d02e63 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -353,6 +353,33 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd)
return ip_tunnel_ctl(dev, p, cmd);
}
+static int ipip_fill_forward_path(struct net_device_path_ctx *ctx,
+ struct net_device_path *path)
+{
+ struct ip_tunnel *tunnel = netdev_priv(ctx->dev);
+ const struct iphdr *tiph = &tunnel->parms.iph;
+ struct rtable *rt;
+
+ rt = ip_route_output(dev_net(ctx->dev), tiph->daddr, 0, 0, 0,
+ RT_SCOPE_UNIVERSE);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+
+ path->type = DEV_PATH_IPENCAP;
+ path->dev = ctx->dev;
+ path->encap.proto = htons(ETH_P_IP);
+ /* Use the hash of outer header IP src and dst addresses as
+ * encapsulation ID. This must be kept in sync with
+ * nf_flow_tuple_encap().
+ */
+ path->encap.id = __ipv4_addr_hash(tiph->saddr, ntohl(tiph->daddr));
+
+ ctx->dev = rt->dst.dev;
+ ip_rt_put(rt);
+
+ return 0;
+}
+
static const struct net_device_ops ipip_netdev_ops = {
.ndo_init = ipip_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
@@ -362,6 +389,7 @@ static const struct net_device_ops ipip_netdev_ops = {
.ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip_tunnel_ctl,
+ .ndo_fill_forward_path = ipip_fill_forward_path,
};
#define IPIP_FEATURES (NETIF_F_SG | \
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 8cd4cf7ae21120f1057c4fce5aaca4e3152ae76d..454a2be3feafd181596374478a4ccd244f81d53b 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -147,6 +147,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
{
struct vlan_ethhdr *veth;
struct pppoe_hdr *phdr;
+ struct iphdr *iph;
int i = 0;
if (skb_vlan_tag_present(skb)) {
@@ -165,6 +166,19 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
tuple->encap[i].id = ntohs(phdr->sid);
tuple->encap[i].proto = skb->protocol;
break;
+ case htons(ETH_P_IP):
+ iph = (struct iphdr *)skb_network_header(skb);
+ if (iph->protocol != IPPROTO_IPIP)
+ break;
+
+ tuple->encap[i].proto = htons(ETH_P_IP);
+ /* For IP tunnels the hash of outer header IP src and dst
+ * addresses is used as encapsulation ID so it must be kept in
+ * sync with IP tunnel ndo_fill_forward_path callbacks.
+ */
+ tuple->encap[i].id = __ipv4_addr_hash(iph->daddr,
+ ntohl(iph->saddr));
+ break;
}
}
@@ -277,6 +291,40 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
return NF_STOLEN;
}
+static bool nf_flow_ip4_encap_proto(struct sk_buff *skb, u32 *psize)
+{
+ struct iphdr *iph;
+ u16 size;
+
+ if (!pskb_may_pull(skb, sizeof(*iph)))
+ return false;
+
+ iph = (struct iphdr *)skb_network_header(skb);
+ size = iph->ihl << 2;
+
+ if (ip_is_fragment(iph) || unlikely(ip_has_options(size)))
+ return false;
+
+ if (iph->ttl <= 1)
+ return false;
+
+ if (iph->protocol == IPPROTO_IPIP)
+ *psize += size;
+
+ return true;
+}
+
+static void nf_flow_ip4_ecanp_pop(struct sk_buff *skb)
+{
+ struct iphdr *iph = (struct iphdr *)skb_network_header(skb);
+
+ if (iph->protocol != IPPROTO_IPIP)
+ return;
+
+ skb_pull(skb, iph->ihl << 2);
+ skb_reset_network_header(skb);
+}
+
static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
u32 *offset)
{
@@ -284,6 +332,8 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
__be16 inner_proto;
switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ return nf_flow_ip4_encap_proto(skb, offset);
case htons(ETH_P_8021Q):
if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
return false;
@@ -331,6 +381,9 @@ static void nf_flow_encap_pop(struct sk_buff *skb,
break;
}
}
+
+ if (skb->protocol == htons(ETH_P_IP))
+ nf_flow_ip4_ecanp_pop(skb);
}
static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
@@ -357,8 +410,7 @@ nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx,
{
struct flow_offload_tuple tuple = {};
- if (skb->protocol != htons(ETH_P_IP) &&
- !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
+ if (!nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
return NULL;
if (nf_flow_tuple_ip(ctx, skb, &tuple) < 0)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 225ff293cd50081a30fc82feeed5bb054f6387f0..4fe9a5e5dab839b17fc2acea835b72efccf7e1d9 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -108,6 +108,7 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
case DEV_PATH_DSA:
case DEV_PATH_VLAN:
case DEV_PATH_PPPOE:
+ case DEV_PATH_IPENCAP:
info->indev = path->dev;
if (is_zero_ether_addr(info->h_source))
memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN);
--
2.50.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH nf-next v5 2/2] selftests: netfilter: nft_flowtable.sh: Add IPIP flowtable selftest
2025-07-21 21:23 [PATCH nf-next v5 0/2] Add IPIP flowtable SW acceleratio Lorenzo Bianconi
2025-07-21 21:23 ` [PATCH nf-next v5 1/2] net: netfilter: Add IPIP flowtable SW acceleration Lorenzo Bianconi
@ 2025-07-21 21:23 ` Lorenzo Bianconi
2025-07-29 15:29 ` [PATCH nf-next v5 0/2] Add IPIP flowtable SW acceleratio Lorenzo Bianconi
2 siblings, 0 replies; 4+ messages in thread
From: Lorenzo Bianconi @ 2025-07-21 21:23 UTC (permalink / raw)
To: David S. Miller, David Ahern, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Pablo Neira Ayuso, Jozsef Kadlecsik,
Shuah Khan, Andrew Lunn
Cc: Florian Westphal, netdev, netfilter-devel, coreteam,
linux-kselftest, Lorenzo Bianconi
Introduce specific selftest for IPIP flowtable SW acceleration in
nft_flowtable.sh
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
.../selftests/net/netfilter/nft_flowtable.sh | 40 ++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index a4ee5496f2a17cedf1ee71214397012c7906650f..d1c9d3eeda2c9874008f9d6de6cabaabea79b9fb 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -519,6 +519,44 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then
ip netns exec "$nsr1" nft list ruleset
fi
+# IPIP tunnel test:
+# Add IPIP tunnel interfaces and check flowtable acceleration.
+test_ipip() {
+if ! ip -net "$nsr1" link add name tun0 type ipip \
+ local 192.168.10.1 remote 192.168.10.2 >/dev/null;then
+ echo "SKIP: could not add ipip tunnel"
+ [ "$ret" -eq 0 ] && ret=$ksft_skip
+ return
+fi
+ip -net "$nsr1" link set tun0 up
+ip -net "$nsr1" addr add 192.168.100.1/24 dev tun0
+ip netns exec "$nsr1" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null
+
+ip -net "$nsr2" link add name tun0 type ipip local 192.168.10.2 remote 192.168.10.1
+ip -net "$nsr2" link set tun0 up
+ip -net "$nsr2" addr add 192.168.100.2/24 dev tun0
+ip netns exec "$nsr2" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null
+
+ip -net "$nsr1" route change default via 192.168.100.2
+ip -net "$nsr2" route change default via 192.168.100.1
+ip -net "$ns2" route add default via 10.0.2.1
+
+ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0 accept'
+ip netns exec "$nsr1" nft -a insert rule inet filter forward \
+ 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept'
+
+if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel"; then
+ echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel" 1>&2
+ ip netns exec "$nsr1" nft list ruleset
+ ret=1
+fi
+
+# Restore the previous configuration
+ip -net "$nsr1" route change default via 192.168.10.2
+ip -net "$nsr2" route change default via 192.168.10.1
+ip -net "$ns2" route del default via 10.0.2.1
+}
+
# Another test:
# Add bridge interface br0 to Router1, with NAT enabled.
test_bridge() {
@@ -604,6 +642,8 @@ ip -net "$nsr1" addr add dead:1::1/64 dev veth0 nodad
ip -net "$nsr1" link set up dev veth0
}
+test_ipip
+
test_bridge
KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1)
--
2.50.1
^ permalink raw reply related [flat|nested] 4+ messages in thread