selftests/bpf: add a test case for sock_ops perf-event notification

This patch provides a tcp_bpf based eBPF sample. The test

- ncat(1) as the TCP client program to connect() to a port
  with the intention of triggerring SYN retransmissions: we
  first install an iptables DROP rule to make sure ncat SYNs are
  resent (instead of aborting instantly after a TCP RST)

- has a bpf kernel module that sends a perf-event notification for
  each TCP retransmit, and also tracks the number of such notifications
  sent in the global_map

The test passes when the number of event notifications intercepted
in user-space matches the value in the global_map.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/testing/selftests/bpf/Makefile

@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
 	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
-	test_netcnt
+	test_netcnt test_tcpnotify_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
 	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+	test_tcpnotify_kern.o \
 	sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
 	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
@@ -74,6 +75,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c

tools/testing/selftests/bpf/test_tcpnotify.h

@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+	__u32 total_retrans;
+	__u32 ncalls;
+};
+
+struct tcp_notifier {
+	__u8    type;
+	__u8    subtype;
+	__u8    source;
+	__u8    hash;
+};
+
+#define	TESTPORT	12877
+#endif

tools/testing/selftests/bpf/test_tcpnotify_kern.c

@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpnotify.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct tcpnotify_globals),
+	.max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") perf_event_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(__u32),
+	.max_entries = 2,
+};
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	op = (int) skops->op;
+
+	if (bpf_ntohl(skops->remote_port) != TESTPORT) {
+		skops->reply = -1;
+		return 0;
+	}
+
+	switch (op) {
+	case BPF_SOCK_OPS_TIMEOUT_INIT:
+	case BPF_SOCK_OPS_RWND_INIT:
+	case BPF_SOCK_OPS_NEEDS_ECN:
+	case BPF_SOCK_OPS_BASE_RTT:
+	case BPF_SOCK_OPS_RTO_CB:
+		rv = 1;
+		break;
+
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
+					  BPF_SOCK_OPS_RTO_CB_FLAG));
+		rv = 1;
+		break;
+	case BPF_SOCK_OPS_RETRANS_CB: {
+			__u32 key = 0;
+			struct tcpnotify_globals g, *gp;
+			struct tcp_notifier msg = {
+				.type = 0xde,
+				.subtype = 0xad,
+				.source = 0xbe,
+				.hash = 0xef,
+			};
+
+			rv = 1;
+
+			/* Update results */
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.total_retrans = skops->total_retrans;
+			g.ncalls++;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+			bpf_perf_event_output(skops, &perf_event_map,
+					      BPF_F_CURRENT_CPU,
+					      &msg, sizeof(msg));
+		}
+		break;
+	default:
+		rv = -1;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcpnotify_user.c

@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <sys/syscall.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <sys/ioctl.h>
+#include <linux/rtnetlink.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#include "test_tcpnotify.h"
+#include "trace_helpers.h"
+
+#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
+
+pthread_t tid;
+int rx_callbacks;
+
+static int dummyfn(void *data, int size)
+{
+	struct tcp_notifier *t = data;
+
+	if (t->type != 0xde || t->subtype != 0xad ||
+	    t->source != 0xbe || t->hash != 0xef)
+		return 1;
+	rx_callbacks++;
+	return 0;
+}
+
+void tcp_notifier_poller(int fd)
+{
+	while (1)
+		perf_event_poller(fd, dummyfn);
+}
+
+static void *poller_thread(void *arg)
+{
+	int fd = *(int *)arg;
+
+	tcp_notifier_poller(fd);
+	return arg;
+}
+
+int verify_result(const struct tcpnotify_globals *result)
+{
+	return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1);
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+static int setup_bpf_perf_event(int mapfd)
+{
+	struct perf_event_attr attr = {
+		.sample_type = PERF_SAMPLE_RAW,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_BPF_OUTPUT,
+	};
+	int key = 0;
+	int pmu_fd;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0);
+	if (pmu_fd < 0)
+		return pmu_fd;
+	bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
+
+	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	return pmu_fd;
+}
+
+int main(int argc, char **argv)
+{
+	const char *file = "test_tcpnotify_kern.o";
+	int prog_fd, map_fd, perf_event_fd;
+	struct tcpnotify_globals g = {0};
+	const char *cg_path = "/foo";
+	int error = EXIT_FAILURE;
+	struct bpf_object *obj;
+	int cg_fd = -1;
+	__u32 key = 0;
+	int rv;
+	char test_script[80];
+	int pmu_fd;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg_fd = create_and_get_cgroup(cg_path);
+	if (!cg_fd)
+		goto err;
+
+	if (join_cgroup(cg_path))
+		goto err;
+
+	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+		goto err;
+	}
+
+	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (rv) {
+		printf("FAILED: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		goto err;
+	}
+
+	perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map");
+	if (perf_event_fd < 0)
+		goto err;
+
+	map_fd = bpf_find_map(__func__, obj, "global_map");
+	if (map_fd < 0)
+		goto err;
+
+	pmu_fd = setup_bpf_perf_event(perf_event_fd);
+	if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0)
+		goto err;
+
+	pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	rv = bpf_map_lookup_elem(map_fd, &key, &g);
+	if (rv != 0) {
+		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+		goto err;
+	}
+
+	sleep(10);
+
+	if (verify_result(&g)) {
+		printf("FAILED: Wrong stats Expected %d calls, got %d\n",
+			g.ncalls, rx_callbacks);
+		goto err;
+	}
+
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	close(cg_fd);
+	cleanup_cgroup_environment();
+	return error;
+}