tools/bpf: add a test for bpf_get_stack with raw tracepoint prog

The test attached a raw_tracepoint program to raw_syscalls/sys_enter.
It tested to get stack for user space, kernel space and user
space with build_id request. It also tested to get user
and kernel stack into the same buffer with back-to-back
bpf_get_stack helper calls.

If jit is not enabled, the user space application will check
to ensure that the kernel function for raw_tracepoint
___bpf_prog_run is part of the stack.

If jit is enabled, we did not have a reliable way to
verify the kernel stack, so just assume the kernel stack
is good when the kernel stack size is greater than 0.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/Makefile

@@ -32,7 +32,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.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
+	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
+	test_get_stack_rawtp.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -58,6 +59,7 @@ $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_progs: trace_helpers.c
 
 .PHONY: force
 

tools/testing/selftests/bpf/test_get_stack_rawtp.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* Permit pretty deep stack traces */
+#define MAX_STACK_RAWTP 100
+struct stack_trace_t {
+	int pid;
+	int kern_stack_size;
+	int user_stack_size;
+	int user_stack_buildid_size;
+	__u64 kern_stack[MAX_STACK_RAWTP];
+	__u64 user_stack[MAX_STACK_RAWTP];
+	struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+struct bpf_map_def SEC("maps") perfmap = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(__u32),
+	.max_entries = 2,
+};
+
+struct bpf_map_def SEC("maps") stackdata_map = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct stack_trace_t),
+	.max_entries = 1,
+};
+
+/* Allocate per-cpu space twice the needed. For the code below
+ *   usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+ *   if (usize < 0)
+ *     return 0;
+ *   ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+ *
+ * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64),
+ * verifier will complain that access "raw_data + usize"
+ * with size "max_len - usize" may be out of bound.
+ * The maximum "raw_data + usize" is "raw_data + max_len"
+ * and the maximum "max_len - usize" is "max_len", verifier
+ * concludes that the maximum buffer access range is
+ * "raw_data[0...max_len * 2 - 1]" and hence reject the program.
+ *
+ * Doubling the to-be-used max buffer size can fix this verifier
+ * issue and avoid complicated C programming massaging.
+ * This is an acceptable workaround since there is one entry here.
+ */
+struct bpf_map_def SEC("maps") rawdata_map = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2,
+	.max_entries = 1,
+};
+
+SEC("tracepoint/raw_syscalls/sys_enter")
+int bpf_prog1(void *ctx)
+{
+	int max_len, max_buildid_len, usize, ksize, total_size;
+	struct stack_trace_t *data;
+	void *raw_data;
+	__u32 key = 0;
+
+	data = bpf_map_lookup_elem(&stackdata_map, &key);
+	if (!data)
+		return 0;
+
+	max_len = MAX_STACK_RAWTP * sizeof(__u64);
+	max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id);
+	data->pid = bpf_get_current_pid_tgid();
+	data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack,
+					      max_len, 0);
+	data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len,
+					    BPF_F_USER_STACK);
+	data->user_stack_buildid_size = bpf_get_stack(
+		ctx, data->user_stack_buildid, max_buildid_len,
+		BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+	bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data));
+
+	/* write both kernel and user stacks to the same buffer */
+	raw_data = bpf_map_lookup_elem(&rawdata_map, &key);
+	if (!raw_data)
+		return 0;
+
+	usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+	if (usize < 0)
+		return 0;
+
+	ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+	if (ksize < 0)
+		return 0;
+
+	total_size = usize + ksize;
+	if (total_size > 0 && total_size <= max_len)
+		bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */

tools/testing/selftests/bpf/test_progs.c

@@ -38,8 +38,10 @@ typedef __u16 __sum16;
 #include "bpf_util.h"
 #include "bpf_endian.h"
 #include "bpf_rlimit.h"
+#include "trace_helpers.h"
 
 static int error_cnt, pass_cnt;
+static bool jit_enabled;
 
 #define MAGIC_BYTES 123
 
@@ -391,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
+static bool is_jit_enabled(void)
+{
+	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	bool enabled = false;
+	int sysctl_fd;
+
+	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
+	if (sysctl_fd != -1) {
+		char tmpc;
+
+		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+			enabled = (tmpc != '0');
+		close(sysctl_fd);
+	}
+
+	return enabled;
+}
+
 static void test_bpf_obj_id(void)
 {
 	const __u64 array_magic_value = 0xfaceb00c;
 	const __u32 array_key = 0;
 	const int nr_iters = 2;
 	const char *file = "./test_obj_id.o";
-	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
 	const char *expected_prog_name = "test_obj_id";
 	const char *expected_map_name = "test_map_id";
 	const __u64 nsec_per_sec = 1000000000;
@@ -414,20 +433,11 @@ static void test_bpf_obj_id(void)
 	char jited_insns[128], xlated_insns[128], zeros[128];
 	__u32 i, next_id, info_len, nr_id_found, duration = 0;
 	struct timespec real_time_ts, boot_time_ts;
-	int sysctl_fd, jit_enabled = 0, err = 0;
+	int err = 0;
 	__u64 array_value;
 	uid_t my_uid = getuid();
 	time_t now, load_time;
 
-	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
-	if (sysctl_fd != -1) {
-		char tmpc;
-
-		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
-			jit_enabled = (tmpc != '0');
-		close(sysctl_fd);
-	}
-
 	err = bpf_prog_get_fd_by_id(0);
 	CHECK(err >= 0 || errno != ENOENT,
 	      "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
@@ -1204,8 +1214,147 @@ out:
 	return;
 }
 
+#define MAX_CNT_RAWTP	10ull
+#define MAX_STACK_RAWTP	100
+struct get_stack_trace_t {
+	int pid;
+	int kern_stack_size;
+	int user_stack_size;
+	int user_stack_buildid_size;
+	__u64 kern_stack[MAX_STACK_RAWTP];
+	__u64 user_stack[MAX_STACK_RAWTP];
+	struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+static int get_stack_print_output(void *data, int size)
+{
+	bool good_kern_stack = false, good_user_stack = false;
+	const char *nonjit_func = "___bpf_prog_run";
+	struct get_stack_trace_t *e = data;
+	int i, num_stack;
+	static __u64 cnt;
+	struct ksym *ks;
+
+	cnt++;
+
+	if (size < sizeof(struct get_stack_trace_t)) {
+		__u64 *raw_data = data;
+		bool found = false;
+
+		num_stack = size / sizeof(__u64);
+		/* If jit is enabled, we do not have a good way to
+		 * verify the sanity of the kernel stack. So we
+		 * just assume it is good if the stack is not empty.
+		 * This could be improved in the future.
+		 */
+		if (jit_enabled) {
+			found = num_stack > 0;
+		} else {
+			for (i = 0; i < num_stack; i++) {
+				ks = ksym_search(raw_data[i]);
+				if (strcmp(ks->name, nonjit_func) == 0) {
+					found = true;
+					break;
+				}
+			}
+		}
+		if (found) {
+			good_kern_stack = true;
+			good_user_stack = true;
+		}
+	} else {
+		num_stack = e->kern_stack_size / sizeof(__u64);
+		if (jit_enabled) {
+			good_kern_stack = num_stack > 0;
+		} else {
+			for (i = 0; i < num_stack; i++) {
+				ks = ksym_search(e->kern_stack[i]);
+				if (strcmp(ks->name, nonjit_func) == 0) {
+					good_kern_stack = true;
+					break;
+				}
+			}
+		}
+		if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
+			good_user_stack = true;
+	}
+	if (!good_kern_stack || !good_user_stack)
+		return PERF_EVENT_ERROR;
+
+	if (cnt == MAX_CNT_RAWTP)
+		return PERF_EVENT_DONE;
+
+	return PERF_EVENT_CONT;
+}
+
+static void test_get_stack_raw_tp(void)
+{
+	const char *file = "./test_get_stack_rawtp.o";
+	int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
+	struct perf_event_attr attr = {};
+	struct timespec tv = {0, 10};
+	__u32 key = 0, duration = 0;
+	struct bpf_object *obj;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+		return;
+
+	efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+	if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+		goto close_prog;
+
+	perfmap_fd = bpf_find_map(__func__, obj, "perfmap");
+	if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+		  perfmap_fd, errno))
+		goto close_prog;
+
+	err = load_kallsyms();
+	if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	attr.sample_type = PERF_SAMPLE_RAW;
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
+	pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/,
+			 -1/*group_fd*/, 0);
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
+		  errno))
+		goto close_prog;
+
+	err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY);
+	if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err,
+		  errno))
+		goto close_prog;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n",
+		  err, errno))
+		goto close_prog;
+
+	err = perf_event_mmap(pmu_fd);
+	if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	/* trigger some syscall action */
+	for (i = 0; i < MAX_CNT_RAWTP; i++)
+		nanosleep(&tv, NULL);
+
+	err = perf_event_poller(pmu_fd, get_stack_print_output);
+	if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno))
+		goto close_prog;
+
+	goto close_prog_noerr;
+close_prog:
+	error_cnt++;
+close_prog_noerr:
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
+	jit_enabled = is_jit_enabled();
+
 	test_pkt_access();
 	test_xdp();
 	test_xdp_adjust_tail();
@@ -1219,6 +1368,7 @@ int main(void)
 	test_stacktrace_map();
 	test_stacktrace_build_id();
 	test_stacktrace_map_raw_tp();
+	test_get_stack_raw_tp();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;