Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel side changes:

   - A couple of x86/cpu cleanups and changes were grandfathered in due
     to patch dependencies. These clean up the set of CPU model/family
     matching macros with a consistent namespace and C99 initializer
     style.

   - A bunch of updates to various low level PMU drivers:
       * AMD Family 19h L3 uncore PMU
       * Intel Tiger Lake uncore support
       * misc fixes to LBR TOS sampling

   - optprobe fixes

   - perf/cgroup: optimize cgroup event sched-in processing

   - misc cleanups and fixes

  Tooling side changes are to:

   - perf {annotate,expr,record,report,stat,test}

   - perl scripting

   - libapi, libperf and libtraceevent

   - vendor events on Intel and S390, ARM cs-etm

   - Intel PT updates

   - Documentation changes and updates to core facilities

   - misc cleanups, fixes and other enhancements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (89 commits)
  cpufreq/intel_pstate: Fix wrong macro conversion
  x86/cpu: Cleanup the now unused CPU match macros
  hwrng: via_rng: Convert to new X86 CPU match macros
  crypto: Convert to new CPU match macros
  ASoC: Intel: Convert to new X86 CPU match macros
  powercap/intel_rapl: Convert to new X86 CPU match macros
  PCI: intel-mid: Convert to new X86 CPU match macros
  mmc: sdhci-acpi: Convert to new X86 CPU match macros
  intel_idle: Convert to new X86 CPU match macros
  extcon: axp288: Convert to new X86 CPU match macros
  thermal: Convert to new X86 CPU match macros
  hwmon: Convert to new X86 CPU match macros
  platform/x86: Convert to new CPU match macros
  EDAC: Convert to new X86 CPU match macros
  cpufreq: Convert to new X86 CPU match macros
  ACPI: Convert to new X86 CPU match macros
  x86/platform: Convert to new CPU match macros
  x86/kernel: Convert to new CPU match macros
  x86/kvm: Convert to new CPU match macros
  x86/perf/events: Convert to new CPU match macros
  ...

1 files changed, 30 insertions, 9 deletions

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bc31fccc0057..76c6052b12e2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include "cgroup.h"
 #include <api/fs/fs.h>
+#include "util.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -110,7 +111,7 @@ static void aggr_printout(struct perf_stat_config *config,
 			config->csv_sep);
 			break;
 	case AGGR_NONE:
-		if (evsel->percore) {
+		if (evsel->percore && !config->percore_show_thread) {
 			fprintf(config->output, "S%d-D%d-C%*d%s",
 				cpu_map__id_to_socket(id),
 				cpu_map__id_to_die(id),
@@ -628,7 +629,7 @@ static void aggr_cb(struct perf_stat_config *config,
 static void print_counter_aggrdata(struct perf_stat_config *config,
 				   struct evsel *counter, int s,
 				   char *prefix, bool metric_only,
-				   bool *first)
+				   bool *first, int cpu)
 {
 	struct aggr_data ad;
 	FILE *output = config->output;
@@ -654,7 +655,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = val * counter->scale;
-	printout(config, id, nr, counter, uval, prefix,
+	printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
 		 run, ena, 1.0, &rt_stat);
 	if (!metric_only)
 		fputc('\n', output);
@@ -687,7 +688,7 @@ static void print_aggr(struct perf_stat_config *config,
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, s,
 					       prefix, metric_only,
-					       &first);
+					       &first, -1);
 		}
 		if (metric_only)
 			fputc('\n', output);
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
-	int n;
 
 	if (!config->null_run)
 		fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
+	if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
@@ -1146,6 +1144,26 @@ static void print_footer(struct perf_stat_config *config)
 			"the same PMU. Try reorganizing the group.\n");
 }
 
+static void print_percore_thread(struct perf_stat_config *config,
+				 struct evsel *counter, char *prefix)
+{
+	int s, s2, id;
+	bool first = true;
+
+	for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+		for (s = 0; s < config->aggr_map->nr; s++) {
+			id = config->aggr_map->map[s];
+			if (s2 == id)
+				break;
+		}
+
+		print_counter_aggrdata(config, counter, s,
+				       prefix, false,
+				       &first, i);
+	}
+}
+
 static void print_percore(struct perf_stat_config *config,
 			  struct evsel *counter, char *prefix)
 {
@@ -1157,13 +1175,16 @@ static void print_percore(struct perf_stat_config *config,
 	if (!(config->aggr_map || config->aggr_get_id))
 		return;
 
+	if (config->percore_show_thread)
+		return print_percore_thread(config, counter, prefix);
+
 	for (s = 0; s < config->aggr_map->nr; s++) {
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
 		print_counter_aggrdata(config, counter, s,
 				       prefix, metric_only,
-				       &first);
+				       &first, -1);
 	}
 
 	if (metric_only)