[PATCH v6] perf stat: Include PMU name and split uncore events per PMU in metric-only JSON output

[Chun-Tse Shao <ctshao@google.com>]

When running `perf stat` with `-A` (--no-aggr) and `--metric-only` in
JSON output mode (`-j`), `perf stat` evaluates metric expressions
across all matching PMUs (including uncore PMUs like `uncore_iio_0`,
`uncore_iio_1`, etc.).

However, `perf stat` previously formatted JSON output by printing only
"cpu" : "<id>" and grouping all metric values on a single line per CPU
without identifying which PMU instance evaluated each metric. As a
result, when an uncore event spans multiple PMU boxes, `perf stat`
printed repeated, ambiguous metric keys without PMU names.

Fix this by:
1. Including "pmu" : "<pmu_name>" in print_aggr_id_json when evsel->pmu
   is a non-core or hybrid PMU in AGGR_NONE mode (-A). Tool events are
   not labeled as they don't belong to a hardware PMU instance.
2. Starting a new JSON metric line in AGGR_NONE mode (-A) whenever the
   PMU name changes, so that a line only has metrics from the PMU it is
   labeled with.
3. Opening a metric line only for events that have a metric, as other
   events print nothing in metric-only mode. This avoids spurious lines
   like {"cpu" : "0", "pmu" : "tool"} for events like user_time, while
   metrics on tool events, like tma_info_system_time (duration_time),
   are still printed with the line prefix.
4. Updating perf_json_output_lint.py to recognize the new "pmu" key in
   the JSON test suite.

Before the fix:
  $ perf stat -M iio_bandwidth_read -a -A --metric-only -j -I 1000
  {"interval" : 1.001017947, "cpu" : "0", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "22.5", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.2", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.0", "MB/s  iio_bandwidth_read" : "0.0"}

There is no way to determine which uncore device generated the metrics.

After:
  $ perf stat -M iio_bandwidth_read -a -A --metric-only -j -I 1000
  {"interval" : 1.000314908, "cpu" : "0", "pmu" : "uncore_iio_0", "MB/s  iio_bandwidth_read" : "0.0"}
  {"interval" : 1.000314908, "cpu" : "0", "pmu" : "uncore_iio_1", "MB/s  iio_bandwidth_read" : "0.1"}
  {"interval" : 1.000314908, "cpu" : "0", "pmu" : "uncore_iio_11", "MB/s  iio_bandwidth_read" : "0.0"}
  ...
  {"interval" : 1.000314908, "cpu" : "56", "pmu" : "uncore_iio_0", "MB/s  iio_bandwidth_read" : "0.0"}
  {"interval" : 1.000314908, "cpu" : "56", "pmu" : "uncore_iio_1", "MB/s  iio_bandwidth_read" : "0.0"}
  {"interval" : 1.000314908, "cpu" : "56", "pmu" : "uncore_iio_11", "MB/s  iio_bandwidth_read" : "0.0"}

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
v6:
  - Open metric lines for events that have a metric instead of skipping
    tool events, so metrics on tool events (e.g. tma_info_system_time)
    keep the line prefix and are terminated properly. (Sashiko)
  - Split JSON lines only when the shown PMU name changes. Tool event
    metrics are no longer mislabeled with an uncore PMU name, and the
    STD and CSV output are no longer split.
  - Rebase onto the latest perf-tools-next.
v5: lore.kernel.org/20260811230518.3360-2-ctshao@google.com
  - Fix perf test "perf stat JSON output linter" failure.
v4: lore.kernel.org/20260804210659.112192-1-ctshao@google.com
  - Fix the line splitting issue, causing spurious empty {"pmu": "tool"}
    objects and order-dependent PMU mislabeling.
v3: lore.kernel.org/20260729170416.41904-1-ctshao@google.com
  - Add before the fix output.
v2: lore.kernel.org/20260715203055.2981363-1-ctshao@google.com
  - Fix print_metric_begin() initialization in print_no_aggr_metric()
    to ensure tool events always open lines cleanly.

 .../tests/shell/lib/perf_json_output_lint.py  |  5 +-
 tools/perf/util/stat-display.c                | 74 ++++++++++++++++---
 2 files changed, 66 insertions(+), 13 deletions(-)

diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
index 8cde22ac9d97..982be893bd69 100644
--- a/tools/perf/tests/shell/lib/perf_json_output_lint.py
+++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py
@@ -65,6 +65,7 @@ def check_json_output(expected_count):
       'metricgroup': lambda x: True,
       'node': lambda x: True,
       'pcnt-running': isfloat,
+      'pmu': lambda x: True,
       'socket': lambda x: True,
       'thread': lambda x: True,
       'unit': lambda x: True,
@@ -99,8 +100,10 @@ def check_json_output(expected_count):
 try:
   if args.no_args or args.system_wide or args.event:
     expected_items = [5, 7]
-  elif args.interval or args.per_thread or args.system_wide_no_aggr:
+  elif args.interval or args.per_thread:
     expected_items = [6, 8]
+  elif args.system_wide_no_aggr:
+    expected_items = [6, 7, 8, 9]
   elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cluster or args.per_cache:
     expected_items = [7, 9]
   elif args.metric_only:
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index b337cc23f413..9f1d74019d1e 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -1,6 +1,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <inttypes.h>
+#include <string.h>
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <math.h>
@@ -23,6 +24,7 @@
 #include "pmu.h"
 #include "pmus.h"
 #include "tool_pmu.h"
+#include "metricgroup.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -361,9 +363,33 @@ static void print_aggr_id_csv(struct perf_stat_config *config,
 	}
 }
 
+/*
+ * In no-aggregation mode, JSON output includes the PMU name of non-core and
+ * hybrid events so that events and metrics from different PMU instances, like
+ * uncore_iio_0 and uncore_iio_1, can be told apart. Tool events don't belong
+ * to a hardware PMU instance and so are not labeled.
+ */
+static const char *json_pmu_name(const struct evsel *evsel)
+{
+	if (!evsel || !evsel->pmu || evsel__is_tool(evsel))
+		return NULL;
+	if (evsel->pmu->is_core && !evsel__is_hybrid(evsel))
+		return NULL;
+	return evsel->pmu->name;
+}
+
+static bool json_pmu_name_changed(const char *name, const char *prev)
+{
+	if (!name || !prev)
+		return name != prev;
+	return strcmp(name, prev) != 0;
+}
+
 static void print_aggr_id_json(struct perf_stat_config *config, struct outstate *os,
 			       struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
 {
+	const char *pmu_name;
+
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
 		json_out(os, "\"core\" : \"S%d-D%d-C%d\", \"counters\" : %d",
@@ -397,6 +423,9 @@ static void print_aggr_id_json(struct perf_stat_config *config, struct outstate
 			json_out(os, "\"cpu\" : \"%d\"",
 				id.cpu.cpu);
 		}
+		pmu_name = json_pmu_name(evsel);
+		if (pmu_name)
+			json_out(os, "\"pmu\" : \"%s\"", pmu_name);
 		break;
 	case AGGR_THREAD:
 		json_out(os, "\"thread\" : \"%s-%d\"",
@@ -1012,11 +1041,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 
 static void print_metric_begin(struct perf_stat_config *config,
 			       struct evlist *evlist,
-			       struct outstate *os, int aggr_idx)
+			       struct outstate *os, int aggr_idx,
+			       struct evsel *counter)
 {
 	struct perf_stat_aggr *aggr;
 	struct aggr_cpu_id id;
-	struct evsel *evsel;
+	struct evsel *evsel = counter ?: evlist__first(evlist);
 
 	os->first = true;
 	if (!config->metric_only)
@@ -1031,7 +1061,6 @@ static void print_metric_begin(struct perf_stat_config *config,
 		else
 			fprintf(config->output, "%s", os->timestamp);
 	}
-	evsel = evlist__first(evlist);
 	id = config->aggr_map->map[aggr_idx];
 	aggr = &evsel->stats->aggr[aggr_idx];
 	aggr_printout(config, os, evsel, id, aggr->nr);
@@ -1069,7 +1098,7 @@ static void print_aggr(struct perf_stat_config *config,
 	 * Without each counter has its own line.
 	 */
 	cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
-		print_metric_begin(config, evlist, os, aggr_idx);
+		print_metric_begin(config, evlist, os, aggr_idx, NULL);
 
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, aggr_idx, os);
@@ -1095,7 +1124,7 @@ static void print_aggr_cgroup(struct perf_stat_config *config,
 		os->cgrp = evsel->cgrp;
 
 		cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
-			print_metric_begin(config, evlist, os, aggr_idx);
+			print_metric_begin(config, evlist, os, aggr_idx, NULL);
 
 			evlist__for_each_entry(evlist, counter) {
 				if (counter->cgrp != os->cgrp)
@@ -1131,7 +1160,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 
 	perf_cpu_map__for_each_cpu(cpu, all_idx, evlist__core(evlist)->user_requested_cpus) {
 		struct evsel *counter;
-		bool first = true;
+		const char *line_pmu = NULL;
+		bool line_open = false;
 
 		evlist__for_each_entry(evlist, counter) {
 			u64 ena, run, val;
@@ -1146,12 +1176,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 				if (config->aggr_map->map[aggr_idx].cpu.cpu == cpu.cpu)
 					break;
 			}
+			if (aggr_idx >= config->aggr_map->nr)
+				continue;
 
 			os->evsel = counter;
 			os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
-			if (first) {
-				print_metric_begin(config, evlist, os, aggr_idx);
-				first = false;
+
+			/*
+			 * Only events with a metric print something in metric-only
+			 * mode, so let them open the line. For JSON, start a new
+			 * line when the PMU name changes so that a line only has
+			 * metrics from the PMU it is labeled with.
+			 */
+			if (config->iostat_run ||
+			    metricgroup__lookup(evlist__metric_events(evlist), counter, false)) {
+				const char *pmu_name = json_pmu_name(counter);
+
+				if (line_open && config->json_output &&
+				    json_pmu_name_changed(pmu_name, line_pmu)) {
+					print_metric_end(config, os);
+					line_open = false;
+				}
+				if (!line_open) {
+					print_metric_begin(config, evlist, os, aggr_idx, counter);
+					line_pmu = pmu_name;
+					line_open = true;
+				}
 			}
 			val = ps->aggr[aggr_idx].counts.val;
 			ena = ps->aggr[aggr_idx].counts.ena;
@@ -1160,7 +1210,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 			uval = val * counter->scale;
 			printout(config, os, uval, run, ena, 1.0, aggr_idx);
 		}
-		if (!first)
+		if (line_open)
 			print_metric_end(config, os);
 	}
 }
@@ -1523,7 +1573,7 @@ static void print_cgroup_counter(struct perf_stat_config *config, struct evlist
 				print_metric_end(config, os);
 
 			os->cgrp = counter->cgrp;
-			print_metric_begin(config, evlist, os, /*aggr_idx=*/0);
+			print_metric_begin(config, evlist, os, /*aggr_idx=*/0, NULL);
 		}
 
 		print_counter(config, counter, os);
@@ -1573,7 +1623,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 		} else if (config->cgroup_list) {
 			print_cgroup_counter(config, evlist, &os);
 		} else {
-			print_metric_begin(config, evlist, &os, /*aggr_idx=*/0);
+			print_metric_begin(config, evlist, &os, /*aggr_idx=*/0, NULL);
 			evlist__for_each_entry(evlist, counter) {
 				print_counter(config, counter, &os);
 			}
-- 
2.56.0.317.g454f8302e1-goog