Merge tag 'perf-core-for-mingo-4.16-20171227' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Allow system wide 'perf stat --per-thread', sorting the result (Jin Yao)

  E.g.:

  [root@jouet ~]# perf stat --per-thread --metrics IPC
  ^C
   Performance counter stats for 'system wide':

              make-22229  23,012,094,032  inst_retired.any   #  0.8 IPC
               cc1-22419     692,027,497  inst_retired.any   #  0.8 IPC
               gcc-22418     328,231,855  inst_retired.any   #  0.9 IPC
               cc1-22509     220,853,647  inst_retired.any   #  0.8 IPC
               gcc-22486     199,874,810  inst_retired.any   #  1.0 IPC
                as-22466     177,896,365  inst_retired.any   #  0.9 IPC
               cc1-22465     150,732,374  inst_retired.any   #  0.8 IPC
               gcc-22508     112,555,593  inst_retired.any   #  0.9 IPC
               cc1-22487     108,964,079  inst_retired.any   #  0.7 IPC
   qemu-system-x86-2697       21,330,550  inst_retired.any   #  0.3 IPC
   systemd-journal-551        20,642,951  inst_retired.any   #  0.4 IPC
   docker-containe-17651       9,552,892  inst_retired.any   #  0.5 IPC
   dockerd-current-9809        7,528,586  inst_retired.any   #  0.5 IPC
              make-22153  12,504,194,380  inst_retired.any   #  0.8 IPC
           python2-22429  12,081,290,954  inst_retired.any   #  0.8 IPC
  <SNIP>
           python2-22429  15,026,328,103  cpu_clk_unhalted.thread
               cc1-22419     826,660,193  cpu_clk_unhalted.thread
               gcc-22418     365,321,295  cpu_clk_unhalted.thread
               cc1-22509     279,169,362  cpu_clk_unhalted.thread
               gcc-22486     210,156,950  cpu_clk_unhalted.thread
  <SNIP>

       5.638075538 seconds time elapsed

  [root@jouet ~]#

- Improve shell auto-completion of perf events (Jin Yao)

-  Fix symbol fixup issues in arm64 due to ELF type (Kim Phillips)

- Ignore threads when they vanish after procfs based enumeration and
  before we try to use them with sys_perf_event_open(), i.e. just remove
  them from the thread_map and continue with the rest. This makes, among
  other cases, the previous new feature (perf stat --per-thread for system
  wide, albeit that not seeming to be the motivation for this patch) more
  robust. (Mengting Zhang)

- Generate s390 syscall table from asm/unistd.h, doing like x86,
  removing the dependency on audit-libs to do this id->string translation,
  speeding up the support for newly introducted syscalls (Hendrik Brueckner)

- Fix 'perf test' on filesystems where readdir() returns d_type == DT_UNKNOWN,
  such as XFS (Jiri Olsa)

- Fix PERF_SAMPLE_RAW_DATA endianity handling for cross-arch tracepoint
  processing (Jiri Olsa)

- Add __return suffix for return events in 'perf probe', streamlining
  entry/exit tracing (Masami Hiramatsu)

- Improve support for versioned symbols in 'perf probe" (Masami Hiramatsu)

- Clarify error message about invalid 'perf probe' event names (Masami Hiramatsu)

- Fix check open filename arg using 'perf trace' in a 'perf test' entry for
  systems using glibc >= 2.26, such as some ARM and s390 distros (Michael Petlan)

- Make method for obtaining the (normalized) architecture id for a
  perf.data file or for the running system used by the annotation routines
  generally available, next user will be for generating per arch errno
  string tables to allow for pretty printing errno codes recorded in a
  perf.data file in architecture A to be properly decoded on hardware
  archictecture B.  (Arnaldo Carvalho de Melo)

- Remove duplicate includes, found using scripts/checkincludes.pl (Pravin Shedge)

- s390 needs -fPIC, enable it, also revert a patch that supposedly did
  that but instead enabled -fPIC for x86 (Hendrik Brueckner, Arnaldo Carvalho de Melo)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 143 insertions, 25 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a027b4712e48..98bf9d32f222 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -63,7 +63,6 @@
 #include "util/group.h"
 #include "util/session.h"
 #include "util/tool.h"
-#include "util/group.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
 #include "asm/bug.h"
@@ -214,8 +213,13 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 
 static void perf_stat__reset_stats(void)
 {
+	int i;
+
 	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
+
+	for (i = 0; i < stat_config.stats_num; i++)
+		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -272,7 +276,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 			attr->enable_on_exec = 1;
 	}
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
@@ -335,7 +339,7 @@ static int read_counter(struct perf_evsel *counter)
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;
 
-	if (target__has_cpu(&target))
+	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		ncpus = perf_evsel__nr_cpus(counter);
 	else
 		ncpus = 1;
@@ -1097,7 +1101,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 }
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-		     char *prefix, u64 run, u64 ena, double noise)
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
 {
 	struct perf_stat_output_ctx out;
 	struct outstate os = {
@@ -1190,7 +1195,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
-				&out, &metric_events);
+				&out, &metric_events, st);
 	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
@@ -1214,7 +1219,8 @@ static void aggr_update_shadow(void)
 				val += perf_counts(counter->counts, cpu, 0)->val;
 			}
 			perf_stat__update_shadow_stats(counter, val,
-						       first_shadow_cpu(counter, id));
+					first_shadow_cpu(counter, id),
+					&rt_stat);
 		}
 	}
 }
@@ -1334,7 +1340,8 @@ static void print_aggr(char *prefix)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
 			if (!metric_only)
 				fputc('\n', output);
 		}
@@ -1343,13 +1350,24 @@ static void print_aggr(char *prefix)
 	}
 }
 
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+static int cmp_val(const void *a, const void *b)
 {
-	FILE *output = stat_config.output;
-	int nthreads = thread_map__nr(counter->threads);
-	int ncpus = cpu_map__nr(counter->cpus);
-	int cpu, thread;
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret)
+{
+	int cpu, thread, i = 0;
 	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
 
 	for (thread = 0; thread < nthreads; thread++) {
 		u64 ena = 0, run = 0, val = 0;
@@ -1360,13 +1378,63 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			run += perf_counts(counter->counts, cpu, thread)->run;
 		}
 
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(&target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = stat_config.output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		uval = val * counter->scale;
-		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
+		id = buf[thread].id;
+		if (stat_config.stats)
+			printout(id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &stat_config.stats[id]);
+		else
+			printout(id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
 		fputc('\n', output);
 	}
+
+	free(buf);
 }
 
 struct caggr_data {
@@ -1401,7 +1469,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		fprintf(output, "%s", prefix);
 
 	uval = cd.avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
+	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
 	if (!metric_only)
 		fprintf(output, "\n");
 }
@@ -1440,7 +1509,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
 
 		fputc('\n', output);
 	}
@@ -1472,7 +1542,8 @@ static void print_no_aggr_metric(char *prefix)
 			run = perf_counts(counter->counts, cpu, 0)->run;
 
 			uval = val * counter->scale;
-			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
 		}
 		fputc('\n', stat_config.output);
 	}
@@ -1528,7 +1599,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
 					      &out,
-					      &metric_events);
+					      &metric_events,
+					      &rt_stat);
 	}
 	fputc('\n', stat_config.output);
 }
@@ -2487,6 +2559,35 @@ int process_cpu_map_event(struct perf_tool *tool,
 	return set_maps(st);
 }
 
+static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
+{
+	int i;
+
+	config->stats = calloc(nthreads, sizeof(struct runtime_stat));
+	if (!config->stats)
+		return -1;
+
+	config->stats_num = nthreads;
+
+	for (i = 0; i < nthreads; i++)
+		runtime_stat__init(&config->stats[i]);
+
+	return 0;
+}
+
+static void runtime_stat_delete(struct perf_stat_config *config)
+{
+	int i;
+
+	if (!config->stats)
+		return;
+
+	for (i = 0; i < config->stats_num; i++)
+		runtime_stat__exit(&config->stats[i]);
+
+	free(config->stats);
+}
+
 static const char * const stat_report_usage[] = {
 	"perf stat report [<options>]",
 	NULL,
@@ -2696,12 +2797,16 @@ int cmd_stat(int argc, const char **argv)
 		run_count = 1;
 	}
 
-	if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
-		fprintf(stderr, "The --per-thread option is only available "
-			"when monitoring via -p -t options.\n");
-		parse_options_usage(NULL, stat_options, "p", 1);
-		parse_options_usage(NULL, stat_options, "t", 1);
-		goto out;
+	if ((stat_config.aggr_mode == AGGR_THREAD) &&
+		!target__has_task(&target)) {
+		if (!target.system_wide || target.cpu_list) {
+			fprintf(stderr, "The --per-thread option is only "
+				"available when monitoring via -p -t -a "
+				"options or only --per-thread.\n");
+			parse_options_usage(NULL, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
+			goto out;
+		}
 	}
 
 	/*
@@ -2725,6 +2830,9 @@ int cmd_stat(int argc, const char **argv)
 
 	target__validate(&target);
 
+	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+		target.per_thread = true;
+
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
@@ -2742,8 +2850,15 @@ int cmd_stat(int argc, const char **argv)
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.
 	 */
-	if (stat_config.aggr_mode == AGGR_THREAD)
+	if (stat_config.aggr_mode == AGGR_THREAD) {
 		thread_map__read_comms(evsel_list->threads);
+		if (target.system_wide) {
+			if (runtime_stat_new(&stat_config,
+				thread_map__nr(evsel_list->threads))) {
+				goto out;
+			}
+		}
+	}
 
 	if (interval && interval < 100) {
 		if (interval < 10) {
@@ -2833,5 +2948,8 @@ out:
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
 
 	perf_evlist__delete(evsel_list);
+
+	runtime_stat_delete(&stat_config);
+
 	return status;
 }