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

3 files changed, 38 insertions, 9 deletions

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 94624733af7e..8271ab764eb5 100644
--- a/tools/perf/util/bpf-event.c
+++ b/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,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f9a320694b85..a7f93f5a1ac8 100644
--- a/tools/perf/util/session.c
+++ b/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);
+			}
 		}
 	}
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 817a2de264b4..c1af37e11f98 100644
--- a/tools/perf/util/stat.c
+++ b/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;
 }