@@ -363,6 +363,61 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
return TC_ACT_OK;
}
+static int encap_ipv6_ipip6(struct __sk_buff *skb)
+{
+ struct iphdr iph_inner;
+ struct v6hdr h_outer;
+ struct tcphdr tcph;
+ struct ethhdr eth;
+ __u64 flags;
+ int olen;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+ sizeof(iph_inner)) < 0)
+ return TC_ACT_OK;
+
+ /* filter only packets we want */
+ if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2),
+ &tcph, sizeof(tcph)) < 0)
+ return TC_ACT_OK;
+
+ if (tcph.dest != __bpf_constant_htons(cfg_port))
+ return TC_ACT_OK;
+
+ olen = sizeof(h_outer.ip);
+
+ flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+ /* add room between mac and network header */
+ if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
+ return TC_ACT_SHOT;
+
+ /* prepare new outer network header */
+ memset(&h_outer.ip, 0, sizeof(h_outer.ip));
+ h_outer.ip.version = 6;
+ h_outer.ip.hop_limit = iph_inner.ttl;
+ h_outer.ip.saddr.s6_addr[1] = 0xfd;
+ h_outer.ip.saddr.s6_addr[15] = 1;
+ h_outer.ip.daddr.s6_addr[1] = 0xfd;
+ h_outer.ip.daddr.s6_addr[15] = 2;
+ h_outer.ip.payload_len = iph_inner.tot_len;
+ h_outer.ip.nexthdr = IPPROTO_IPIP;
+
+ /* store new outer network header */
+ if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
+ BPF_F_INVALIDATE_HASH) < 0)
+ return TC_ACT_SHOT;
+
+ /* update eth->h_proto */
+ if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0)
+ return TC_ACT_SHOT;
+ eth.h_proto = bpf_htons(ETH_P_IPV6);
+ if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0)
+ return TC_ACT_SHOT;
+
+ return TC_ACT_OK;
+}
+
static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
__u16 l2_proto)
{
@@ -461,6 +516,15 @@ int __encap_ip6tnl_none(struct __sk_buff *skb)
return TC_ACT_OK;
}
+SEC("encap_ipip6_none")
+int __encap_ipip6_none(struct __sk_buff *skb)
+{
+ if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+ return encap_ipv6_ipip6(skb);
+ else
+ return TC_ACT_OK;
+}
+
SEC("encap_ip6gre_none")
int __encap_ip6gre_none(struct __sk_buff *skb)
{
@@ -100,6 +100,9 @@ if [[ "$#" -eq "0" ]]; then
echo "ipip"
$0 ipv4 ipip none 100
+ echo "ipip6"
+ $0 ipv4 ipip6 none 100
+
echo "ip6ip6"
$0 ipv6 ip6tnl none 100
@@ -224,6 +227,9 @@ elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then
ttype="vxlan"
targs="id 1 dstport 8472 udp6zerocsumrx"
+elif [[ "$tuntype" == "ipip6" ]]; then
+ ttype="ip6tnl"
+ targs=""
else
ttype=$tuntype
targs=""
@@ -233,6 +239,9 @@ fi
if [[ "${tuntype}" == "sit" ]]; then
link_addr1="${ns1_v4}"
link_addr2="${ns2_v4}"
+elif [[ "${tuntype}" == "ipip6" ]]; then
+ link_addr1="${ns1_v6}"
+ link_addr2="${ns2_v6}"
else
link_addr1="${addr1}"
link_addr2="${addr2}"
@@ -287,12 +296,6 @@ else
server_listen
fi
-# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3.
-if [[ "${tuntype}" == "sit" ]]; then
- echo OK
- exit 0
-fi
-
# serverside, use BPF for decap
ip netns exec "${ns2}" ip link del dev testtun0
ip netns exec "${ns2}" tc qdisc add dev veth2 clsact
Add ipip6 and ip6ip decap testcases. Verify that bpf_skb_adjust_room() correctly decapsulate ipip6 and ip6ip tunnel packets. Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com> --- .../selftests/bpf/progs/test_tc_tunnel.c | 64 +++++++++++++++++++ tools/testing/selftests/bpf/test_tc_tunnel.sh | 15 +++-- 2 files changed, 73 insertions(+), 6 deletions(-)