Merge tag 'perf-tools-fixes-for-v5.18-2022-05-21' of...

Merge tag 'perf-tools-fixes-for-v5.18-2022-05-21' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix and validate CPU map inputs in synthetic PERF_RECORD_STAT events
   in 'perf stat'.

 - Fix x86's arch__intr_reg_mask() for the hybrid platform.

 - Address 'perf bench numa' compiler error on s390.

 - Fix check for btf__load_from_kernel_by_id() in libbpf.

 - Fix "all PMU test" 'perf test' to skip hv_24x7/hv_gpci tests on
   powerpc.

 - Fix session topology test to skip the test in guest environment.

 - Skip BPF 'perf test' if clang is not present.

 - Avoid shell test description infinite loop in 'perf test'.

 - Fix Intel LBR callstack entries and nr print message.

* tag 'perf-tools-fixes-for-v5.18-2022-05-21' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf session: Fix Intel LBR callstack entries and nr print message
  perf test bpf: Skip test if clang is not present
  perf test session topology: Fix test to skip the test in guest environment
  perf bench numa: Address compiler error on s390
  perf test: Avoid shell test description infinite loop
  perf regs x86: Fix arch__intr_reg_mask() for the hybrid platform
  perf test: Fix "all PMU test" to skip hv_24x7/hv_gpci tests on powerpc
  perf stat: Fix and validate CPU map inputs in synthetic PERF_RECORD_STAT events
  perf build: Fix check for btf__load_from_kernel_by_id() in libbpf

tools/build/Makefile.feature

@@ -98,6 +98,7 @@ FEATURE_TESTS_EXTRA :=                  \
          llvm-version                   \
          clang                          \
          libbpf                         \
+         libbpf-btf__load_from_kernel_by_id \
          libpfm4                        \
          libdebuginfod			\
          clang-bpf-co-re

tools/build/feature/Makefile

@@ -57,6 +57,7 @@ FILES=                                          \
          test-lzma.bin                          \
          test-bpf.bin                           \
          test-libbpf.bin                        \
+         test-libbpf-btf__load_from_kernel_by_id.bin	\
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
@@ -287,6 +288,9 @@ $(OUTPUT)test-bpf.bin:
 $(OUTPUT)test-libbpf.bin:
 	$(BUILD) -lbpf
 
+$(OUTPUT)test-libbpf-btf__load_from_kernel_by_id.bin:
+	$(BUILD) -lbpf
+
 $(OUTPUT)test-sdt.bin:
 	$(BUILD)
 

tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c

+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/libbpf.h>
+
+int main(void)
+{
+	return btf__load_from_kernel_by_id(20151128, NULL);
+}

tools/perf/Makefile.config

@@ -553,9 +553,16 @@ ifndef NO_LIBELF
         ifeq ($(feature-libbpf), 1)
           EXTLIBS += -lbpf
           $(call detected,CONFIG_LIBBPF_DYNAMIC)
+
+          $(call feature_check,libbpf-btf__load_from_kernel_by_id)
+          ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1)
+            CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+          endif
         else
           dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
         endif
+      else
+	CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
       endif
     endif
 

tools/perf/arch/x86/util/perf_regs.c

@@ -9,6 +9,8 @@
 #include "../../../util/perf_regs.h"
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmu-hybrid.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
@@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void)
 		.disabled 		= 1,
 		.exclude_kernel		= 1,
 	};
+	struct perf_pmu *pmu;
 	int fd;
 	/*
 	 * In an unnamed union, init it here to build on older gcc versions
 	 */
 	attr.sample_period = 1;
 
+	if (perf_pmu__has_hybrid()) {
+		/*
+		 * The same register set is supported among different hybrid PMUs.
+		 * Only check the first available one.
+		 */
+		pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list);
+		attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+	}
+
 	event_attr_init(&attr);
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);

tools/perf/bench/numa.c

@@ -1740,7 +1740,7 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[14 + 2 * 10 + 1];
+		char tname[14 + 2 * 11 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {

tools/perf/tests/bpf.c

@@ -222,11 +222,11 @@ static int __test__bpf(int idx)
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
 				       bpf_testcase_table[idx].prog_id,
-				       true, NULL);
+				       false, NULL);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
 			 bpf_testcase_table[idx].msg_compile_fail);
-		if (idx == 0)
+		if ((idx == 0) || (ret == TEST_SKIP))
 			return TEST_SKIP;
 		else
 			return TEST_FAIL;
@@ -364,9 +364,11 @@ static int test__bpf_prologue_test(struct test_suite *test __maybe_unused,
 static struct test_case bpf_tests[] = {
 #ifdef HAVE_LIBBPF_SUPPORT
 	TEST_CASE("Basic BPF filtering", basic_bpf_test),
-	TEST_CASE("BPF pinning", bpf_pinning),
+	TEST_CASE_REASON("BPF pinning", bpf_pinning,
+			"clang isn't installed or environment missing BPF support"),
 #ifdef HAVE_BPF_PROLOGUE
-	TEST_CASE("BPF prologue generation", bpf_prologue_test),
+	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test,
+			"clang isn't installed or environment missing BPF support"),
 #else
 	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
 #endif

tools/perf/tests/builtin-test.c

@@ -279,6 +279,7 @@ static const char *shell_test__description(char *description, size_t size,
 {
 	FILE *fp;
 	char filename[PATH_MAX];
+	int ch;
 
 	path__join(filename, sizeof(filename), path, name);
 	fp = fopen(filename, "r");
@@ -286,7 +287,9 @@ static const char *shell_test__description(char *description, size_t size,
 		return NULL;
 
 	/* Skip shebang */
-	while (fgetc(fp) != '\n');
+	do {
+		ch = fgetc(fp);
+	} while (ch != EOF && ch != '\n');
 
 	description = fgets(description, size, fp);
 	fclose(fp);
@@ -417,7 +420,8 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
 			.priv = &st,
 		};
 
-		if (!perf_test__matches(test_suite.desc, curr, argc, argv))
+		if (test_suite.desc == NULL ||
+		    !perf_test__matches(test_suite.desc, curr, argc, argv))
 			continue;
 
 		st.file = ent->d_name;

tools/perf/tests/shell/stat_all_pmu.sh

@@ -5,6 +5,16 @@
 set -e
 
 for p in $(perf list --raw-dump pmu); do
+  # In powerpc, skip the events for hv_24x7 and hv_gpci.
+  # These events needs input values to be filled in for
+  # core, chip, partition id based on system.
+  # Example: hv_24x7/CPM_ADJUNCT_INST,domain=?,core=?/
+  # hv_gpci/event,partition_id=?/
+  # Hence skip these events for ppc.
+  if echo "$p" |grep -Eq 'hv_24x7|hv_gpci' ; then
+    echo "Skipping: Event '$p' in powerpc"
+    continue
+  fi
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
   if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then

tools/perf/tests/topology.c

@@ -109,6 +109,17 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 			&& strncmp(session->header.env.arch, "aarch64", 7))
 		return TEST_SKIP;
 
+	/*
+	 * In powerpc pSeries platform, not all the topology information
+	 * are exposed via sysfs. Due to restriction, detail like
+	 * physical_package_id will be set to -1. Hence skip this
+	 * test if physical_package_id returns -1 for cpu from perf_cpu_map.
+	 */
+	if (strncmp(session->header.env.arch, "powerpc", 7)) {
+		if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
+			return TEST_SKIP;
+	}
+
 	TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
 
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {

tools/perf/util/bpf-event.c

@@ -22,7 +22,8 @@
 #include "record.h"
 #include "util/synthetic-events.h"
 
-struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
+#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+struct btf *btf__load_from_kernel_by_id(__u32 id)
 {
        struct btf *btf;
 #pragma GCC diagnostic push
@@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
 
        return err ? ERR_PTR(err) : btf;
 }
+#endif
 
 int __weak bpf_prog_load(enum bpf_prog_type prog_type,
 			 const char *prog_name __maybe_unused,

tools/perf/util/session.c

@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
-	printf("%s: nr:%" PRIu64 "\n",
-		!callstack ? "... branch stack" : "... branch callstack",
-		sample->branch_stack->nr);
+	if (!callstack) {
+		printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+	} else {
+		/* the reason of adding 1 to nr is because after expanding
+		 * branch stack it generates nr + 1 callstack records. e.g.,
+		 *         B()->C()
+		 *         A()->B()
+		 * the final callstack should be:
+		 *         C()
+		 *         B()
+		 *         A()
+		 */
+		printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+	}
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 				(unsigned)e->flags.reserved,
 				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
-			printf("..... %2"PRIu64": %016" PRIx64 "\n",
-				i, i > 0 ? e->from : e->to);
+			if (i == 0) {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n"
+				       "..... %2"PRIu64": %016" PRIx64 "\n",
+						i, e->to, i+1, e->from);
+			} else {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+			}
 		}
 	}
 }

tools/perf/util/stat.c

@@ -472,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 int perf_event__process_stat_event(struct perf_session *session,
 				   union perf_event *event)
 {
-	struct perf_counts_values count;
+	struct perf_counts_values count, *ptr;
 	struct perf_record_stat *st = &event->stat;
 	struct evsel *counter;
+	int cpu_map_idx;
 
 	count.val = st->val;
 	count.ena = st->ena;
@@ -485,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session,
 		pr_err("Failed to resolve counter for stat event.\n");
 		return -EINVAL;
 	}
-
-	*perf_counts(counter->counts, st->cpu, st->thread) = count;
+	cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu});
+	if (cpu_map_idx == -1) {
+		pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter));
+		return -EINVAL;
+	}
+	ptr = perf_counts(counter->counts, cpu_map_idx, st->thread);
+	if (ptr == NULL) {
+		pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n",
+			st->cpu, st->thread, evsel__name(counter));
+		return -EINVAL;
+	}
+	*ptr = count;
 	counter->supported = true;
 	return 0;
 }