selftests/bpf: support BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP

Exit as soon as we found that packet is encapped when
BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP is passed.
Add appropriate selftest cases.

v2:
* Subtract sizeof(struct iphdr) from .iph_inner.tot_len (Willem de Bruijn)

Acked-by: Petar Penkov <[email protected]>
Acked-by: Willem de Bruijn <[email protected]>
Acked-by: Song Liu <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Willem de Bruijn <[email protected]>
Cc: Petar Penkov <[email protected]>
Signed-off-by: Stanislav Fomichev <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: fomichev

tools/testing/selftests/bpf/prog_tests/flow_dissector.c

@@ -41,6 +41,13 @@ struct ipv4_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipip_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct iphdr iph_inner;
+	struct tcphdr tcp;
+} __packed;
+
 struct svlan_ipv4_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -82,6 +89,7 @@ struct test {
 	union {
 		struct ipv4_pkt ipv4;
 		struct svlan_ipv4_pkt svlan_ipv4;
+		struct ipip_pkt ipip;
 		struct ipv6_pkt ipv6;
 		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
@@ -303,6 +311,62 @@ struct test tests[] = {
 		},
 		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
 	},
+	{
+		.name = "ipip-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = 0,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr) +
+				sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+	},
+	{
+		.name = "ipip-no-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_IPIP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+	},
 };
 
 static int create_tap(const char *ifname)

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

@@ -167,9 +167,15 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
 		return export_flow_keys(keys, BPF_OK);
 	case IPPROTO_IPIP:
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
+
 		return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
 	case IPPROTO_IPV6:
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
+
 		return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
 	case IPPROTO_GRE:
 		gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
@@ -189,6 +195,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
 			keys->thoff += 4; /* Step over sequence number */
 
 		keys->is_encap = true;
+		if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+			return export_flow_keys(keys, BPF_OK);
 
 		if (gre->proto == bpf_htons(ETH_P_TEB)) {
 			eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),