perf print-events: Print legacy cache events for each PMU

Mirroring parse_events_add_cache, list the legacy name alongside its
alias with the PMU. Remove the now unnecessary hybrid logic.

Note, the alias output removes the event type descriptor, so:
  L1-dcache-loads                                    [Hardware cache event]
becomes:
  L1-dcache-loads OR cpu/L1-dcache-loads/
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kang Minchul <tegongkang@gmail.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20230502223851.2234828-26-irogers@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/parse-events.c

@@ -414,7 +414,7 @@ static int config_attr(struct perf_event_attr *attr,
  *                                     contain hyphens and the longest name
  *                                     should always be selected.
  */
-static int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config)
+int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config)
 {
 	int len, cache_type = -1, cache_op = -1, cache_result = -1;
 	const char *name_end = &name[strlen(name) + 1];

tools/perf/util/parse-events.h

@@ -173,6 +173,7 @@ int parse_events_add_tool(struct parse_events_state *parse_state,
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_error *error,
 			   struct list_head *head_config);
+int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				u64 addr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,

tools/perf/util/print-events.c

@@ -230,56 +230,50 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state)
 
 int print_hwcache_events(const struct print_callbacks *print_cb, void *print_state)
 {
+	struct perf_pmu *pmu = NULL;
 	const char *event_type_descriptor = event_type_descriptors[PERF_TYPE_HW_CACHE];
 
-	for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
-		for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
-			/* skip invalid cache type */
-			if (!evsel__is_cache_op_valid(type, op))
-				continue;
-
-			for (int res = 0; res < PERF_COUNT_HW_CACHE_RESULT_MAX; res++) {
-				struct perf_pmu *pmu = NULL;
-				char name[64];
-
-				__evsel__hw_cache_type_op_res_name(type, op, res,
-								   name, sizeof(name));
-				if (!perf_pmu__has_hybrid()) {
-					if (is_event_supported(PERF_TYPE_HW_CACHE,
-								type | (op << 8) | (res << 16))) {
-						print_cb->print_event(print_state,
-								"cache",
-								/*pmu_name=*/NULL,
-								name,
-								/*event_alias=*/NULL,
-								/*scale_unit=*/NULL,
-								/*deprecated=*/false,
-								event_type_descriptor,
-								/*desc=*/NULL,
-								/*long_desc=*/NULL,
-								/*encoding_desc=*/NULL);
-					}
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		/*
+		 * Skip uncore PMUs for performance. PERF_TYPE_HW_CACHE type
+		 * attributes can accept software PMUs in the extended type, so
+		 * also skip.
+		 */
+		if (pmu->is_uncore || pmu->type == PERF_TYPE_SOFTWARE)
+			continue;
+
+		for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+			for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+				/* skip invalid cache type */
+				if (!evsel__is_cache_op_valid(type, op))
 					continue;
-				}
-				perf_pmu__for_each_hybrid_pmu(pmu) {
-					if (is_event_supported(PERF_TYPE_HW_CACHE,
-					    type | (op << 8) | (res << 16) |
-					    ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT))) {
-						char new_name[128];
-						snprintf(new_name, sizeof(new_name),
-							"%s/%s/", pmu->name, name);
-						print_cb->print_event(print_state,
-								"cache",
-								pmu->name,
-								name,
-								new_name,
-								/*scale_unit=*/NULL,
-								/*deprecated=*/false,
-								event_type_descriptor,
-								/*desc=*/NULL,
-								/*long_desc=*/NULL,
-								/*encoding_desc=*/NULL);
-					}
+
+				for (int res = 0; res < PERF_COUNT_HW_CACHE_RESULT_MAX; res++) {
+					char name[64];
+					char alias_name[128];
+					__u64 config;
+					int ret;
+
+					__evsel__hw_cache_type_op_res_name(type, op, res,
+									name, sizeof(name));
+
+					ret = parse_events__decode_legacy_cache(name, pmu->type,
+										&config);
+					if (ret || !is_event_supported(PERF_TYPE_HW_CACHE, config))
+						continue;
+					snprintf(alias_name, sizeof(alias_name), "%s/%s/",
+						 pmu->name, name);
+					print_cb->print_event(print_state,
+							"cache",
+							pmu->name,
+							name,
+							alias_name,
+							/*scale_unit=*/NULL,
+							/*deprecated=*/false,
+							event_type_descriptor,
+							/*desc=*/NULL,
+							/*long_desc=*/NULL,
+							/*encoding_desc=*/NULL);
 				}
 			}
 		}