[PATCH v4 bpf-next 3/3] selftests/bpf: add test for bpf_get_branch_snapshot

[Song Liu <songliubraving@fb.com>]

This test uses bpf_get_branch_snapshot from a fexit program. The test uses
a target function (bpf_testmod_loop_test) and compares the record against
kallsyms. If there isn't enough record matching kallsyms, the test fails.

Signed-off-by: Song Liu <songliubraving@fb.com>
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c   |  14 ++-
 .../bpf/prog_tests/get_branch_snapshot.c      | 101 ++++++++++++++++++
 .../selftests/bpf/progs/get_branch_snapshot.c |  44 ++++++++
 tools/testing/selftests/bpf/trace_helpers.c   |  37 +++++++
 tools/testing/selftests/bpf/trace_helpers.h   |   5 +
 5 files changed, 200 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
 create mode 100644 tools/testing/selftests/bpf/progs/get_branch_snapshot.c

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 141d8da687d21..19635e57ff21a 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -13,6 +13,18 @@
 
 DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
 
+noinline int bpf_testmod_loop_test(int n)
+{
+	int i, sum = 0;
+
+	/* the primary goal of this test is to test LBR. Create a lot of
+	 * branches in the function, so we can catch it easily.
+	 */
+	for (i = 0; i < n; i++)
+		sum += i;
+	return sum;
+}
+
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		      struct bin_attribute *bin_attr,
@@ -24,6 +36,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		.len = len,
 	};
 
+	bpf_testmod_loop_test(101);
 	trace_bpf_testmod_test_read(current, &ctx);
 
 	return -EIO; /* always fail */
@@ -71,4 +84,3 @@ module_exit(bpf_testmod_exit);
 MODULE_AUTHOR("Andrii Nakryiko");
 MODULE_DESCRIPTION("BPF selftests module");
 MODULE_LICENSE("Dual BSD/GPL");
-
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
new file mode 100644
index 0000000000000..03ffa5cdf9b09
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "get_branch_snapshot.skel.h"
+
+static int *pfd_array;
+static int cpu_cnt;
+
+static int create_perf_events(void)
+{
+	struct perf_event_attr attr = {0};
+	int cpu;
+
+	/* create perf event */
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_RAW;
+	attr.config = 0x1b00;
+	attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL |
+		PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY;
+
+	cpu_cnt = libbpf_num_possible_cpus();
+	pfd_array = malloc(sizeof(int) * cpu_cnt);
+	if (!pfd_array) {
+		cpu_cnt = 0;
+		return 1;
+	}
+
+	for (cpu = 0; cpu < cpu_cnt; cpu++) {
+		pfd_array[cpu] = syscall(__NR_perf_event_open, &attr,
+					 -1, cpu, -1, PERF_FLAG_FD_CLOEXEC);
+		if (pfd_array[cpu] < 0)
+			break;
+	}
+
+	return cpu == 0;
+}
+
+static void close_perf_events(void)
+{
+	int cpu = 0;
+	int fd;
+
+	while (cpu++ < cpu_cnt) {
+		fd = pfd_array[cpu];
+		if (fd < 0)
+			break;
+		close(fd);
+	}
+	free(pfd_array);
+}
+
+void test_get_branch_snapshot(void)
+{
+	struct get_branch_snapshot *skel = NULL;
+	int err;
+
+	if (create_perf_events()) {
+		test__skip();  /* system doesn't support LBR */
+		goto cleanup;
+	}
+
+	skel = get_branch_snapshot__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_branch_snapshot__open_and_load"))
+		goto cleanup;
+
+	err = kallsyms_find("bpf_testmod_loop_test", &skel->bss->address_low);
+	if (!ASSERT_OK(err, "kallsyms_find"))
+		goto cleanup;
+
+	err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high);
+	if (!ASSERT_OK(err, "kallsyms_find_next"))
+		goto cleanup;
+
+	err = get_branch_snapshot__attach(skel);
+	if (!ASSERT_OK(err, "get_branch_snapshot__attach"))
+		goto cleanup;
+
+	/* trigger the program */
+	system("cat /sys/kernel/bpf_testmod > /dev/null 2>& 1");
+
+	if (skel->bss->total_entries < 16) {
+		/* too few entries for the hit/waste test */
+		test__skip();
+		goto cleanup;
+	}
+
+	ASSERT_GT(skel->bss->test1_hits, 1, "find_looptest_in_lbr");
+
+	/* Given we stop LBR in software, we will waste a few entries.
+	 * But we should try to waste as few as possible entries. We are at
+	 * about 11 on x86_64 systems.
+	 * Add a check for < 15 so that we get heads-up when something
+	 * changes and wastes too many entries.
+	 */
+	ASSERT_LT(skel->bss->wasted_entries, 15, "check_wasted_entries");
+
+cleanup:
+	get_branch_snapshot__destroy(skel);
+	close_perf_events();
+}
diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
new file mode 100644
index 0000000000000..24a6e7a9c08ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_hits = 0;
+__u64 address_low = 0;
+__u64 address_high = 0;
+int wasted_entries = 0;
+long total_entries = 0;
+
+struct perf_branch_entry entries[PERF_MAX_BRANCH_SNAPSHOT] = {};
+
+
+static inline bool in_range(__u64 val)
+{
+	return (val >= address_low) && (val < address_high);
+}
+
+SEC("fexit/bpf_testmod_loop_test")
+int BPF_PROG(test1, int n, int ret)
+{
+	long i;
+
+	total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0);
+	total_entries /= sizeof(struct perf_branch_entry);
+
+	bpf_printk("total_entries %lu\n", total_entries);
+
+	for (i = 0; i < PERF_MAX_BRANCH_SNAPSHOT; i++) {
+		if (i >= total_entries)
+			break;
+		if (in_range(entries[i].from) && in_range(entries[i].to))
+			test1_hits++;
+		else if (!test1_hits)
+			wasted_entries++;
+		bpf_printk("i %d from %llx to %llx", i, entries[i].from,
+			   entries[i].to);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index e7a19b04d4eaf..5100a169b72b1 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <ctype.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -117,6 +118,42 @@ int kallsyms_find(const char *sym, unsigned long long *addr)
 	return err;
 }
 
+/* find the address of the next symbol of the same type, this can be used
+ * to determine the end of a function.
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr)
+{
+	char type, found_type, name[500];
+	unsigned long long value;
+	bool found = false;
+	int err = 0;
+	FILE *f;
+
+	f = fopen("/proc/kallsyms", "r");
+	if (!f)
+		return -EINVAL;
+
+	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
+		/* Different types of symbols in kernel modules are mixed
+		 * in /proc/kallsyms. Only return the next matching type.
+		 * Use tolower() for type so that 'T' matches 't'.
+		 */
+		if (found && found_type == tolower(type)) {
+			*addr = value;
+			goto out;
+		}
+		if (strcmp(name, sym) == 0) {
+			found = true;
+			found_type = tolower(type);
+		}
+	}
+	err = -ENOENT;
+
+out:
+	fclose(f);
+	return err;
+}
+
 void read_trace_pipe(void)
 {
 	int trace_fd;
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index d907b445524d5..bc8ed86105d94 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -16,6 +16,11 @@ long ksym_get_addr(const char *name);
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
+/* find the address of the next symbol, this can be used to determine the
+ * end of a function
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr);
+
 void read_trace_pipe(void);
 
 ssize_t get_uprobe_offset(const void *addr, ssize_t base);
-- 
2.30.2