bpf: add selftest for stackmap with build_id in NMI context

This new test captures stackmap with build_id with hardware event
PERF_COUNT_HW_CPU_CYCLES.

Because we only support one ips-to-build_id lookup per cpu in NMI
context, stack_amap will not be able to do the lookup in this test.
Therefore, we didn't do compare_stack_ips(), as it will alwasy fail.

urandom_read.c is extended to run configurable cycles so that it can be
caught by the perf event.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/testing/selftests/bpf/test_progs.c

@@ -1272,6 +1272,139 @@ out:
 	return;
 }
 
+static void test_stacktrace_build_id_nmi(void)
+{
+	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+	const char *file = "./test_stacktrace_build_id.o";
+	int err, pmu_fd, prog_fd;
+	struct perf_event_attr attr = {
+		.sample_freq = 5000,
+		.freq = 1,
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	__u32 key, previous_key, val, duration = 0;
+	struct bpf_object *obj;
+	char buf[256];
+	int i, j;
+	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
+	int build_id_matches = 0;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
+	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+		return;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+	if (CHECK(pmu_fd < 0, "perf_event_open",
+		  "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+		  pmu_fd, errno))
+		goto close_prog;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
+		  err, errno))
+		goto close_pmu;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
+		  err, errno))
+		goto disable_pmu;
+
+	/* find map fds */
+	control_map_fd = bpf_find_map(__func__, obj, "control_map");
+	if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+	if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+	if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
+		  err, errno))
+		goto disable_pmu;
+
+	stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+	if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
+	       == 0);
+	assert(system("taskset 0x1 ./urandom_read 100000") == 0);
+	/* disable stack trace collection */
+	key = 0;
+	val = 1;
+	bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+	/* for every element in stackid_hmap, we can find a corresponding one
+	 * in stackmap, and vise versa.
+	 */
+	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+	if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	err = extract_build_id(buf, 256);
+
+	if (CHECK(err, "get build_id with readelf",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	err = bpf_map_get_next_key(stackmap_fd, NULL, &key);
+	if (CHECK(err, "get_next_key from stackmap",
+		  "err %d, errno %d\n", err, errno))
+		goto disable_pmu;
+
+	do {
+		char build_id[64];
+
+		err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
+		if (CHECK(err, "lookup_elem from stackmap",
+			  "err %d, errno %d\n", err, errno))
+			goto disable_pmu;
+		for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
+			if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
+			    id_offs[i].offset != 0) {
+				for (j = 0; j < 20; ++j)
+					sprintf(build_id + 2 * j, "%02x",
+						id_offs[i].build_id[j] & 0xff);
+				if (strstr(buf, build_id) != NULL)
+					build_id_matches = 1;
+			}
+		previous_key = key;
+	} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
+
+	if (CHECK(build_id_matches < 1, "build id match",
+		  "Didn't find expected build ID from the map\n"))
+		goto disable_pmu;
+
+	/*
+	 * We intentionally skip compare_stack_ips(). This is because we
+	 * only support one in_nmi() ips-to-build_id translation per cpu
+	 * at any time, thus stack_amap here will always fallback to
+	 * BPF_STACK_BUILD_ID_IP;
+	 */
+
+disable_pmu:
+	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+
+close_pmu:
+	close(pmu_fd);
+
+close_prog:
+	bpf_object__close(obj);
+}
+
 #define MAX_CNT_RAWTP	10ull
 #define MAX_STACK_RAWTP	100
 struct get_stack_trace_t {
@@ -1425,6 +1558,7 @@ int main(void)
 	test_tp_attach_query();
 	test_stacktrace_map();
 	test_stacktrace_build_id();
+	test_stacktrace_build_id_nmi();
 	test_stacktrace_map_raw_tp();
 	test_get_stack_raw_tp();
 

tools/testing/selftests/bpf/urandom_read.c

@@ -6,15 +6,21 @@
 #include <stdlib.h>
 
 #define BUF_SIZE 256
-int main(void)
+
+int main(int argc, char *argv[])
 {
 	int fd = open("/dev/urandom", O_RDONLY);
 	int i;
 	char buf[BUF_SIZE];
+	int count = 4;
 
 	if (fd < 0)
 		return 1;
-	for (i = 0; i < 4; ++i)
+
+	if (argc == 2)
+		count = atoi(argv[1]);
+
+	for (i = 0; i < count; ++i)
 		read(fd, buf, BUF_SIZE);
 
 	close(fd);