selftests/bpf: Selftest for bpf_skb_ancestor_cgroup_id

Add selftests for bpf_skb_ancestor_cgroup_id helper.

test_skb_cgroup_id.sh prepares testing interface and adds tc qdisc and
filter for it using BPF object compiled from test_skb_cgroup_id_kern.c
program.

BPF program in test_skb_cgroup_id_kern.c gets ancestor cgroup id using
the new helper at different levels of cgroup hierarchy that skb belongs
to, including root level and non-existing level, and saves it to the map
where the key is the level of corresponding cgroup and the value is its
id.

To trigger BPF program, user space program test_skb_cgroup_id_user is
run. It adds itself into testing cgroup and sends UDP datagram to
link-local multicast address of testing interface. Then it reads cgroup
ids saved in kernel for different levels from the BPF map and compares
them with those in user space. They must be equal for every level of
ancestry.

Example of run:
  # ./test_skb_cgroup_id.sh
  Wait for testing link-local IP to become available ... OK
  Note: 8 bytes struct bpf_elf_map fixup performed due to size mismatch!
  [PASS]

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/testing/selftests/bpf/Makefile

@@ -34,7 +34,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
-	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o
+	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
+	test_skb_cgroup_id_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -45,10 +46,11 @@ TEST_PROGS := test_kmod.sh \
 	test_sock_addr.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
-	test_lirc_mode2.sh
+	test_lirc_mode2.sh \
+	test_skb_cgroup_id.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
 
 include ../lib.mk
 
@@ -59,6 +61,7 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
 $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c

tools/testing/selftests/bpf/test_skb_cgroup_id.sh

@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Facebook
+
+set -eu
+
+wait_for_ip()
+{
+	local _i
+	echo -n "Wait for testing link-local IP to become available "
+	for _i in $(seq ${MAX_PING_TRIES}); do
+		echo -n "."
+		if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+			echo " OK"
+			return
+		fi
+		sleep 1
+	done
+	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
+	exit 1
+}
+
+setup()
+{
+	# Create testing interfaces not to interfere with current environment.
+	ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
+	ip link set ${TEST_IF} up
+	ip link set ${TEST_IF_PEER} up
+
+	wait_for_ip
+
+	tc qdisc add dev ${TEST_IF} clsact
+	tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
+		sec ${BPF_PROG_SECTION} da
+
+	BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
+			awk '/ id / {sub(/.* id /, "", $0); print($1)}')
+}
+
+cleanup()
+{
+	ip link del ${TEST_IF} 2>/dev/null || :
+	ip link del ${TEST_IF_PEER} 2>/dev/null || :
+}
+
+main()
+{
+	trap cleanup EXIT 2 3 6 15
+	setup
+	${PROG} ${TEST_IF} ${BPF_PROG_ID}
+}
+
+DIR=$(dirname $0)
+TEST_IF="test_cgid_1"
+TEST_IF_PEER="test_cgid_2"
+MAX_PING_TRIES=5
+BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
+BPF_PROG_SECTION="cgroup_id_logger"
+BPF_PROG_ID=0
+PROG="${DIR}/test_skb_cgroup_id_user"
+
+main

tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c

@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+#include <string.h>
+
+#include "bpf_helpers.h"
+
+#define NUM_CGROUP_LEVELS	4
+
+struct bpf_map_def SEC("maps") cgroup_ids = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = NUM_CGROUP_LEVELS,
+};
+
+static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
+{
+	__u64 id;
+
+	/* [1] &level passed to external function that may change it, it's
+	 *     incompatible with loop unroll.
+	 */
+	id = bpf_skb_ancestor_cgroup_id(skb, level);
+	bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
+}
+
+SEC("cgroup_id_logger")
+int log_cgroup_id(struct __sk_buff *skb)
+{
+	/* Loop unroll can't be used here due to [1]. Unrolling manually.
+	 * Number of calls should be in sync with NUM_CGROUP_LEVELS.
+	 */
+	log_nth_level(skb, 0);
+	log_nth_level(skb, 1);
+	log_nth_level(skb, 2);
+	log_nth_level(skb, 3);
+
+	return TC_ACT_OK;
+}
+
+int _version SEC("version") = 1;
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_skb_cgroup_id_user.c

@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define CGROUP_PATH		"/skb_cgroup_test"
+#define NUM_CGROUP_LEVELS	4
+
+/* RFC 4291, Section 2.7.1 */
+#define LINKLOCAL_MULTICAST	"ff02::1"
+
+static int mk_dst_addr(const char *ip, const char *iface,
+		       struct sockaddr_in6 *dst)
+{
+	memset(dst, 0, sizeof(*dst));
+
+	dst->sin6_family = AF_INET6;
+	dst->sin6_port = htons(1025);
+
+	if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
+		log_err("Invalid IPv6: %s", ip);
+		return -1;
+	}
+
+	dst->sin6_scope_id = if_nametoindex(iface);
+	if (!dst->sin6_scope_id) {
+		log_err("Failed to get index of iface: %s", iface);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int send_packet(const char *iface)
+{
+	struct sockaddr_in6 dst;
+	char msg[] = "msg";
+	int err = 0;
+	int fd = -1;
+
+	if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
+		goto err;
+
+	fd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create UDP socket");
+		goto err;
+	}
+
+	if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
+		   sizeof(dst)) == -1) {
+		log_err("Failed to send datagram");
+		goto err;
+	}
+
+	goto out;
+err:
+	err = -1;
+out:
+	if (fd >= 0)
+		close(fd);
+	return err;
+}
+
+int get_map_fd_by_prog_id(int prog_id)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 map_ids[1];
+	int prog_fd = -1;
+	int map_fd = -1;
+
+	prog_fd = bpf_prog_get_fd_by_id(prog_id);
+	if (prog_fd < 0) {
+		log_err("Failed to get fd by prog id %d", prog_id);
+		goto err;
+	}
+
+	info.nr_map_ids = 1;
+	info.map_ids = (__u64) (unsigned long) map_ids;
+
+	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
+		log_err("Failed to get info by prog fd %d", prog_fd);
+		goto err;
+	}
+
+	if (!info.nr_map_ids) {
+		log_err("No maps found for prog fd %d", prog_fd);
+		goto err;
+	}
+
+	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
+	if (map_fd < 0)
+		log_err("Failed to get fd by map id %d", map_ids[0]);
+err:
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return map_fd;
+}
+
+int check_ancestor_cgroup_ids(int prog_id)
+{
+	__u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
+	__u32 level;
+	int err = 0;
+	int map_fd;
+
+	expected_ids[0] = 0x100000001;	/* root cgroup */
+	expected_ids[1] = get_cgroup_id("");
+	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
+	expected_ids[3] = 0; /* non-existent cgroup */
+
+	map_fd = get_map_fd_by_prog_id(prog_id);
+	if (map_fd < 0)
+		goto err;
+
+	for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
+		if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
+			log_err("Failed to lookup key %d", level);
+			goto err;
+		}
+		if (actual_ids[level] != expected_ids[level]) {
+			log_err("%llx (actual) != %llx (expected), level: %u\n",
+				actual_ids[level], expected_ids[level], level);
+			goto err;
+		}
+	}
+
+	goto out;
+err:
+	err = -1;
+out:
+	if (map_fd >= 0)
+		close(map_fd);
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	int cgfd = -1;
+	int err = 0;
+
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
+		exit(EXIT_FAILURE);
+	}
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cgfd = create_and_get_cgroup(CGROUP_PATH);
+	if (!cgfd)
+		goto err;
+
+	if (join_cgroup(CGROUP_PATH))
+		goto err;
+
+	if (send_packet(argv[1]))
+		goto err;
+
+	if (check_ancestor_cgroup_ids(atoi(argv[2])))
+		goto err;
+
+	goto out;
+err:
+	err = -1;
+out:
+	close(cgfd);
+	cleanup_cgroup_environment();
+	printf("[%s]\n", err ? "FAIL" : "PASS");
+	return err;
+}