selftests/bpf: support BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG

bpf_flow.c: exit early unless BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG is
passed in flags. Also, set ip_proto earlier, this makes sure we have
correct value with fragmented packets.

Add selftest cases to test ipv4/ipv6 fragments and skip eth_get_headlen
tests that don't have BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG flag.

eth_get_headlen calls flow dissector with
BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG flag so we can't run tests that
have different set of input flags against it.

v2:
 * sefltests -> selftests (Willem de Bruijn)
 * Reword a comment about eth_get_headlen flags (Song Liu)

Acked-by: Petar Penkov <ppenkov@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Petar Penkov <ppenkov@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 132 insertions, 1 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index c938283ac232..8e8c18aced9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -5,6 +5,10 @@
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
+#ifndef IP_MF
+#define IP_MF 0x2000
+#endif
+
 #define CHECK_FLOW_KEYS(desc, got, expected)				\
 	CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0,		\
 	      desc,							\
@@ -49,6 +53,18 @@ struct ipv6_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipv6_frag_pkt {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct frag_hdr {
+		__u8 nexthdr;
+		__u8 reserved;
+		__be16 frag_off;
+		__be32 identification;
+	} ipf;
+	struct tcphdr tcp;
+} __packed;
+
 struct dvlan_ipv6_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -65,9 +81,11 @@ struct test {
 		struct ipv4_pkt ipv4;
 		struct svlan_ipv4_pkt svlan_ipv4;
 		struct ipv6_pkt ipv6;
+		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
 	} pkt;
 	struct bpf_flow_keys keys;
+	__u32 flags;
 };
 
 #define VLAN_HLEN	4
@@ -143,6 +161,102 @@ struct test tests[] = {
 			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 		},
 	},
+	{
+		.name = "ipv4-frag",
+		.pkt.ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv4-no-frag",
+		.pkt.ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
+	{
+		.name = "ipv6-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv6-no-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
 };
 
 static int create_tap(const char *ifname)
@@ -225,6 +339,13 @@ void test_flow_dissector(void)
 			.data_size_in = sizeof(tests[i].pkt),
 			.data_out = &flow_keys,
 		};
+		static struct bpf_flow_keys ctx = {};
+
+		if (tests[i].flags) {
+			tattr.ctx_in = &ctx;
+			tattr.ctx_size_in = sizeof(ctx);
+			ctx.flags = tests[i].flags;
+		}
 
 		err = bpf_prog_test_run_xattr(&tattr);
 		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
@@ -251,10 +372,20 @@ void test_flow_dissector(void)
 	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		struct bpf_flow_keys flow_keys = {};
+		/* Keep in sync with 'flags' from eth_get_headlen. */
+		__u32 eth_get_headlen_flags =
+			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
 		struct bpf_prog_test_run_attr tattr = {};
+		struct bpf_flow_keys flow_keys = {};
 		__u32 key = 0;
 
+		/* For skb-less case we can't pass input flags; run
+		 * only the tests that have a matching set of flags.
+		 */
+
+		if (tests[i].flags != eth_get_headlen_flags)
+			continue;
+
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
 		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);