Skip to contentSkip to conversation

perf metricgroup: Fix Default metric group lookup for non-Intel CPUs

PATCH In review Francesco Nigro 2 participants 2 messages Mar 22 perf events

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 perf metricgroup: Fix Default metric group lookup for non-Intel CPUs

metricgroup__has_metric_or_groups() only searches the CPU-specific metrics table returned by pmu_metrics_table__find(). The "Default" metric group (used by 'perf stat' when no events are specified) is defined in the common/arch-independent metrics table, not in CPU-specific tables.

For AMD CPUs (e.g. Zen4), the CPU-specific metrics table contains metrics for groups like PipelineL1, l2_cache, etc., but not "Default". This causes bare 'perf stat <command>' to fail with "No supported events found" because add_default_events() never adds any events.

Other code paths like metricgroup__for_each_metric() (used by 'perf list' and 'perf stat -M Default') correctly search both the CPU-specific table and the common/default table via pmu_metrics_table__default(), which is why 'perf stat -M Default' works while bare 'perf stat' does not.

Fix metricgroup__has_metric_or_groups() to also search the default metrics table as a fallback, consistent with metricgroup__for_each_metric().

Tested on AMD Ryzen 9 7950X (Zen4, family 25h) with kernel 6.18.13 and perf built from 6.19.8 source.

Before the fix:

  $ perf stat true
  Error: No supported events found.

After the fix:

  $ perf stat true
  Performance counter stats for 'true':
    0      context-switches        #  0.0 cs/sec
   55      page-faults             #  ...
    0.22 msec task-clock           #  0.0 CPUs utilized
Fixes b0a9e8f81fc4 ("perf stat,jevents: Introduce Default tags for the default mode")
---
 tools/perf/util/metricgroup.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
tools/perf/util/metricgroup.c +9 -3
index a21f2d4969c5..670b650f86fe 100644
@@ -1606,9 +1606,15 @@ bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_gr
 		.metric_or_groups = metric_or_groups,
 	};
 
-	return pmu_metrics_table__for_each_metric(table,
-						  metricgroup__has_metric_or_groups_callback,
-						  &data)
+	if (pmu_metrics_table__for_each_metric(table,
+					       metricgroup__has_metric_or_groups_callback,
+					       &data))
+		return true;
+
+	table = pmu_metrics_table__default();
+	return table && pmu_metrics_table__for_each_metric(table,
+							   metricgroup__has_metric_or_groups_callback,
+							   &data)
 		? true : false;
 }
 
Signature · 1 line
2.53.0
reviewer
#1 lore raw
Quoted 30 lines · Francesco Nigro

metricgroup__has_metric_or_groups() only searches the CPU-specific metrics table returned by pmu_metrics_table__find(). The "Default" metric group (used by 'perf stat' when no events are specified) is defined in the common/arch-independent metrics table, not in CPU-specific tables.

For AMD CPUs (e.g. Zen4), the CPU-specific metrics table contains metrics for groups like PipelineL1, l2_cache, etc., but not "Default". This causes bare 'perf stat <command>' to fail with "No supported events found" because add_default_events() never adds any events.

Other code paths like metricgroup__for_each_metric() (used by 'perf list' and 'perf stat -M Default') correctly search both the CPU-specific table and the common/default table via pmu_metrics_table__default(), which is why 'perf stat -M Default' works while bare 'perf stat' does not.

Fix metricgroup__has_metric_or_groups() to also search the default metrics table as a fallback, consistent with metricgroup__for_each_metric().

Tested on AMD Ryzen 9 7950X (Zen4, family 25h) with kernel 6.18.13 and perf built from 6.19.8 source.

Before the fix:

  $ perf stat true
  Error: No supported events found.

After the fix:

Quoted 8 lines
  $ perf stat true
  Performance counter stats for 'true':
    0      context-switches        #  0.0 cs/sec
   55      page-faults             #  ...
    0.22 msec task-clock           #  0.0 CPUs utilized
Fixes b0a9e8f81fc4 ("perf stat,jevents: Introduce Default tags for the default mode")

Sorry for the issue. I believe this is already fixed but there are issues getting it into Linus' tree:
https://lore.kernel.org/lkml/[email protected]/

Thanks,
Ian

Quoted 30 lines
---
 tools/perf/util/metricgroup.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
tools/perf/util/metricgroup.c +9 -4
index a21f2d4969c5..670b650f86fe 100644
@@ -1606,9 +1606,15 @@ bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_gr
                .metric_or_groups = metric_or_groups,
        };
 
-       return pmu_metrics_table__for_each_metric(table,
-                                                 metricgroup__has_metric_or_groups_callback,
-                                                 &data)
+       if (pmu_metrics_table__for_each_metric(table,
+                                              metricgroup__has_metric_or_groups_callback,
+                                              &data))
+               return true;
+
+       table = pmu_metrics_table__default();
+       return table && pmu_metrics_table__for_each_metric(table,
+                                                          metricgroup__has_metric_or_groups_callback,
+                                                          &data)
                ? true : false;
 }
 
--

2.53.0