selftests/bpf: add ipip6 and ip6ip decap to test_tc_tunnel

maillist inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I6EW1Q
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=7105f76fb56f5ed66a59bc048bc71e9f100e1d39

--------------------------------

Add ipip6 and ip6ip decap testcases. Verify that bpf_skb_adjust_room()
correctly decapsulate ipip6 and ip6ip tunnel packets.
Signed-off-by: NZiyang Xuan <william.xuanziyang@huawei.com>
Reviewed-by: NWillem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/dfd2d8cfdf9111bd129170d4345296f53bee6a67.1673574419.git.william.xuanziyang@huawei.comSigned-off-by: NMartin KaFai Lau <martin.lau@kernel.org>
Conflicts:
	tools/testing/selftests/bpf/progs/test_tc_tunnel.c
	tools/testing/selftests/bpf/test_tc_tunnel.sh
Signed-off-by: NZiyang Xuan <william.xuanziyang@huawei.com>

tools/testing/selftests/bpf/progs/test_tc_tunnel.c

@@ -28,6 +28,10 @@ static const int cfg_udp_src = 20000;
 #define	MPLS_OVER_UDP_PORT	6635
 #define	ETH_OVER_UDP_PORT	7777
 
+#ifndef NEXTHDR_DEST
+#define NEXTHDR_DEST	60
+#endif
+
 /* MPLS label 1000 with S bit (last label) set and ttl of 255. */
 static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
 						     MPLS_LS_S_MASK | 0xff);
@@ -309,6 +313,61 @@ 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, &eth, sizeof(eth)) < 0)
+		return TC_ACT_SHOT;
+	eth.h_proto = bpf_htons(ETH_P_IPV6);
+	if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
 SEC("encap_ipip_none")
 int __encap_ipip_none(struct __sk_buff *skb)
 {
@@ -390,6 +449,15 @@ 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)
 {
@@ -447,13 +515,33 @@ int __encap_ip6udp_eth(struct __sk_buff *skb)
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
 	char buf[sizeof(struct v6hdr)];
+	__u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+	struct ipv6_opt_hdr ip6_opt_hdr;
 	struct gre_hdr greh;
 	struct udphdr udph;
 	int olen = len;
 
 	switch (proto) {
 	case IPPROTO_IPIP:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+		break;
 	case IPPROTO_IPV6:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+		break;
+	case NEXTHDR_DEST:
+		if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr,
+				       sizeof(ip6_opt_hdr)) < 0)
+			return TC_ACT_OK;
+		switch (ip6_opt_hdr.nexthdr) {
+		case IPPROTO_IPIP:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+			break;
+		case IPPROTO_IPV6:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+			break;
+		default:
+			return TC_ACT_OK;
+		}
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
@@ -485,8 +573,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		return TC_ACT_OK;
 	}
 
-	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
-				BPF_F_ADJ_ROOM_FIXED_GSO))
+	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
 
 	return TC_ACT_OK;

tools/testing/selftests/bpf/test_tc_tunnel.sh

@@ -99,6 +99,9 @@ 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
 
@@ -214,6 +217,9 @@ if [[ "$tuntype" =~ "udp" ]]; then
 	targs="encap fou encap-sport auto encap-dport $dport"
 elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
 	ttype=$gretaptype
+elif [[ "$tuntype" == "ipip6" ]]; then
+	ttype="ip6tnl"
+	targs=""
 else
 	ttype=$tuntype
 	targs=""
@@ -223,6 +229,9 @@ 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}"
@@ -277,12 +286,6 @@ 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