perf parse-events: Remove "not supported" hybrid cache events

By default, we create two hybrid cache events, one is for cpu_core, and
another is for cpu_atom. But Some hybrid hardware cache events are only
available on one CPU PMU. For example, the 'L1-dcache-load-misses' is only
available on cpu_core, while the 'L1-icache-loads' is only available on
cpu_atom. We need to remove "not supported" hybrid cache events. By
extending is_event_supported() to global API and using it to check if the
hybrid cache events are supported before being created, we can remove the
"not supported" hybrid cache events.

Before:

 # ./perf stat -e L1-dcache-load-misses,L1-icache-loads -a sleep 1

 Performance counter stats for 'system wide':

            52,570      cpu_core/L1-dcache-load-misses/
   <not supported>      cpu_atom/L1-dcache-load-misses/
   <not supported>      cpu_core/L1-icache-loads/
         1,471,817      cpu_atom/L1-icache-loads/

       1.004915229 seconds time elapsed

After:

 # ./perf stat -e L1-dcache-load-misses,L1-icache-loads -a sleep 1

 Performance counter stats for 'system wide':

            54,510      cpu_core/L1-dcache-load-misses/
         1,441,286      cpu_atom/L1-icache-loads/

       1.005114281 seconds time elapsed

Fixes: 30def61f64 ("perf parse-events: Create two hybrid cache events")
Reported-by: Yi Ammy <ammy.yi@intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220923030013.3726410-2-zhengjun.xing@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/parse-events-hybrid.c

@@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr,
 	 * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
 	 */
 	attr->type = type;
-	attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
+	attr->config = (attr->config & PERF_HW_EVENT_MASK) |
+			((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
 }
 
 static int create_event_hybrid(__u32 config_type, int *idx,
@@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx,
 	__u64 config = attr->config;
 
 	config_hybrid_attr(attr, config_type, pmu->type);
+
+	/*
+	 * Some hybrid hardware cache events are only available on one CPU
+	 * PMU. For example, the 'L1-dcache-load-misses' is only available
+	 * on cpu_core, while the 'L1-icache-loads' is only available on
+	 * cpu_atom. We need to remove "not supported" hybrid cache events.
+	 */
+	if (attr->type == PERF_TYPE_HW_CACHE
+	    && !is_event_supported(attr->type, attr->config))
+		return 0;
+
 	evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id,
 					       pmu, config_terms);
-	if (evsel)
+	if (evsel) {
 		evsel->pmu_name = strdup(pmu->name);
-	else
+		if (!evsel->pmu_name)
+			return -ENOMEM;
+	} else
 		return -ENOMEM;
-
 	attr->type = type;
 	attr->config = config;
 	return 0;

tools/perf/util/parse-events.c

@@ -28,6 +28,7 @@
 #include "util/parse-events-hybrid.h"
 #include "util/pmu-hybrid.h"
 #include "tracepoint.h"
+#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
+bool is_event_supported(u8 type, u64 config)
+{
+	bool ret = true;
+	int open_return;
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
+
+	evsel = evsel__new(&attr);
+	if (evsel) {
+		open_return = evsel__open(evsel, NULL, tmap);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+		evsel__delete(evsel);
+	}
+
+	perf_thread_map__put(tmap);
+	return ret;
+}
+
 const char *event_type(int type)
 {
 	switch (type) {

tools/perf/util/parse-events.h

@@ -19,6 +19,7 @@ struct option;
 struct perf_pmu;
 
 bool have_tracepoints(struct list_head *evlist);
+bool is_event_supported(u8 type, u64 config);
 
 const char *event_type(int type);
 

tools/perf/util/print-events.c

@@ -22,7 +22,6 @@
 #include "probe-file.h"
 #include "string2.h"
 #include "strlist.h"
-#include "thread_map.h"
 #include "tracepoint.h"
 #include "pfm.h"
 #include "pmu-hybrid.h"
@@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
 	strlist__delete(sdtlist);
 }
 
-static bool is_event_supported(u8 type, u64 config)
-{
-	bool ret = true;
-	int open_return;
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = type,
-		.config = config,
-		.disabled = 1,
-	};
-	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
-	if (tmap == NULL)
-		return false;
-
-	evsel = evsel__new(&attr);
-	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
-
-		if (open_return == -EACCES) {
-			/*
-			 * This happens if the paranoid value
-			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
-			 */
-			evsel->core.attr.exclude_kernel = 1;
-			ret = evsel__open(evsel, NULL, tmap) >= 0;
-		}
-		evsel__delete(evsel);
-	}
-
-	perf_thread_map__put(tmap);
-	return ret;
-}
-
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
 	unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;