selftests/bpf: test bpf flow dissection

Adds a test that sends different types of packets over multiple
tunnels and verifies that valid packets are dissected correctly.  To do
so, a tc-flower rule is added to drop packets on UDP src port 9, and
packets are sent from ports 8, 9, and 10. Only the packets on port 9
should be dropped. Because tc-flower relies on the flow dissector to
match flows, correct classification demonstrates correct dissection.

Also add support logic to load the BPF program and to inject the test
packets.
Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/.gitignore

@@ -23,3 +23,5 @@ test_skb_cgroup_id_user
 test_socket_cookie
 test_cgroup_storage
 test_select_reuseport
+test_flow_dissector
+flow_dissector_load

tools/testing/selftests/bpf/Makefile

@@ -47,10 +47,12 @@ TEST_PROGS := test_kmod.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
-	test_skb_cgroup_id.sh
+	test_skb_cgroup_id.sh \
+	test_flow_dissector.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
+	flow_dissector_load test_flow_dissector
 
 include ../lib.mk
 

tools/testing/selftests/bpf/config

@@ -18,3 +18,4 @@ CONFIG_CRYPTO_HMAC=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_VXLAN=y
 CONFIG_GENEVE=y
+CONFIG_NET_CLS_FLOWER=m

tools/testing/selftests/bpf/flow_dissector_load.c

+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <errno.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
+const char *cfg_map_name = "jmp_table";
+bool cfg_attach = true;
+char *cfg_section_name;
+char *cfg_path_name;
+
+static void load_and_attach_program(void)
+{
+	struct bpf_program *prog, *main_prog;
+	struct bpf_map *prog_array;
+	int i, fd, prog_fd, ret;
+	struct bpf_object *obj;
+	int prog_array_fd;
+
+	ret = bpf_prog_load(cfg_path_name, BPF_PROG_TYPE_FLOW_DISSECTOR, &obj,
+			    &prog_fd);
+	if (ret)
+		error(1, 0, "bpf_prog_load %s", cfg_path_name);
+
+	main_prog = bpf_object__find_program_by_title(obj, cfg_section_name);
+	if (!main_prog)
+		error(1, 0, "bpf_object__find_program_by_title %s",
+		      cfg_section_name);
+
+	prog_fd = bpf_program__fd(main_prog);
+	if (prog_fd < 0)
+		error(1, 0, "bpf_program__fd");
+
+	prog_array = bpf_object__find_map_by_name(obj, cfg_map_name);
+	if (!prog_array)
+		error(1, 0, "bpf_object__find_map_by_name %s", cfg_map_name);
+
+	prog_array_fd = bpf_map__fd(prog_array);
+	if (prog_array_fd < 0)
+		error(1, 0, "bpf_map__fd %s", cfg_map_name);
+
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		fd = bpf_program__fd(prog);
+		if (fd < 0)
+			error(1, 0, "bpf_program__fd");
+
+		if (fd != prog_fd) {
+			printf("%d: %s\n", i, bpf_program__title(prog, false));
+			bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
+			++i;
+		}
+	}
+
+	ret = bpf_prog_attach(prog_fd, 0 /* Ignore */, BPF_FLOW_DISSECTOR, 0);
+	if (ret)
+		error(1, 0, "bpf_prog_attach %s", cfg_path_name);
+
+	ret = bpf_object__pin(obj, cfg_pin_path);
+	if (ret)
+		error(1, 0, "bpf_object__pin %s", cfg_pin_path);
+
+}
+
+static void detach_program(void)
+{
+	char command[64];
+	int ret;
+
+	ret = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	if (ret)
+		error(1, 0, "bpf_prog_detach");
+
+	/* To unpin, it is necessary and sufficient to just remove this dir */
+	sprintf(command, "rm -r %s", cfg_pin_path);
+	ret = system(command);
+	if (ret)
+		error(1, errno, command);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	bool attach = false;
+	bool detach = false;
+	int c;
+
+	while ((c = getopt(argc, argv, "adp:s:")) != -1) {
+		switch (c) {
+		case 'a':
+			if (detach)
+				error(1, 0, "attach/detach are exclusive");
+			attach = true;
+			break;
+		case 'd':
+			if (attach)
+				error(1, 0, "attach/detach are exclusive");
+			detach = true;
+			break;
+		case 'p':
+			if (cfg_path_name)
+				error(1, 0, "only one prog name can be given");
+
+			cfg_path_name = optarg;
+			break;
+		case 's':
+			if (cfg_section_name)
+				error(1, 0, "only one section can be given");
+
+			cfg_section_name = optarg;
+			break;
+		}
+	}
+
+	if (detach)
+		cfg_attach = false;
+
+	if (cfg_attach && !cfg_path_name)
+		error(1, 0, "must provide a path to the BPF program");
+
+	if (cfg_attach && !cfg_section_name)
+		error(1, 0, "must provide a section name");
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	if (cfg_attach)
+		load_and_attach_program();
+	else
+		detach_program();
+	return 0;
+}

tools/testing/selftests/bpf/test_flow_dissector.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Load BPF flow dissector and verify it correctly dissects traffic
+export TESTNAME=test_flow_dissector
+unmount=0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
+# This test needs to be run in a network namespace with in_netns.sh. Check if
+# this is the case and run it with in_netns.sh if it is being run in the root
+# namespace.
+if [[ -z $(ip netns identify $$) ]]; then
+	../net/in_netns.sh "$0" "$@"
+	exit $?
+fi
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
+	if (( $? == 0 )); then
+		echo "selftests: $TESTNAME [PASS]";
+	else
+		echo "selftests: $TESTNAME [FAILED]";
+	fi
+
+	set +e
+
+	# Cleanup
+	tc filter del dev lo ingress pref 1337 2> /dev/null
+	tc qdisc del dev lo ingress 2> /dev/null
+	./flow_dissector_load -d 2> /dev/null
+	if [ $unmount -ne 0 ]; then
+		umount bpffs 2> /dev/null
+	fi
+}
+
+# Exit script immediately (well catched by trap handler) if any
+# program/thing exits with a non-zero status.
+set -e
+
+# (Use 'trap -l' to list meaning of numbers)
+trap exit_handler 0 2 3 6 9
+
+# Mount BPF file system
+if /bin/mount | grep /sys/fs/bpf > /dev/null; then
+	echo "bpffs already mounted"
+else
+	echo "bpffs not mounted. Mounting..."
+	unmount=1
+	/bin/mount bpffs /sys/fs/bpf -t bpf
+fi
+
+# Attach BPF program
+./flow_dissector_load -p bpf_flow.o -s dissect
+
+# Setup
+tc qdisc add dev lo ingress
+
+echo "Testing IPv4..."
+# Drops all IP/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 4 -f 8
+# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 4 -f 9 -F
+# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 4 -f 10
+
+echo "Testing IPIP..."
+# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+echo "Testing IPv4 + GRE..."
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+tc filter del dev lo ingress pref 1337
+
+echo "Testing IPv6..."
+# Drops all IPv6/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv6/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 6 -f 8
+# Send 10 IPv6/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 6 -f 9 -F
+# Send 10 IPv6/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 6 -f 10
+
+exit 0

tools/testing/selftests/bpf/with_addr.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# add private ipv4 and ipv6 addresses to loopback
+
+readonly V6_INNER='100::a/128'
+readonly V4_INNER='192.168.0.1/32'
+
+if getopts ":s" opt; then
+  readonly SIT_DEV_NAME='sixtofourtest0'
+  readonly V6_SIT='2::/64'
+  readonly V4_SIT='172.17.0.1/32'
+  shift
+fi
+
+fail() {
+  echo "error: $*" 1>&2
+  exit 1
+}
+
+setup() {
+  ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
+  ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
+
+  if [[ -n "${V6_SIT}" ]]; then
+    ip link add "${SIT_DEV_NAME}" type sit remote any local any \
+	    || fail 'failed to add sit'
+    ip link set dev "${SIT_DEV_NAME}" up \
+	    || fail 'failed to bring sit device up'
+    ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v6 SIT address'
+    ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v4 SIT address'
+  fi
+
+  sleep 2	# avoid race causing bind to fail
+}
+
+cleanup() {
+  if [[ -n "${V6_SIT}" ]]; then
+    ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
+    ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
+    ip link del "${SIT_DEV_NAME}"
+  fi
+
+  ip -4 addr del "${V4_INNER}" dev lo
+  ip -6 addr del "${V6_INNER}" dev lo
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"

tools/testing/selftests/bpf/with_tunnels.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# setup tunnels for flow dissection test
+
+readonly SUFFIX="test_$(mktemp -u XXXX)"
+CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
+
+setup() {
+  ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
+  ip link add "gre_${SUFFIX}" type gre ${CONFIG}
+  ip link add "sit_${SUFFIX}" type sit ${CONFIG}
+
+  echo "tunnels before test:"
+  ip tunnel show
+
+  ip link set "ipip_${SUFFIX}" up
+  ip link set "gre_${SUFFIX}" up
+  ip link set "sit_${SUFFIX}" up
+}
+
+
+cleanup() {
+  ip tunnel del "ipip_${SUFFIX}"
+  ip tunnel del "gre_${SUFFIX}"
+  ip tunnel del "sit_${SUFFIX}"
+
+  echo "tunnels after test:"
+  ip tunnel show
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"