perf pmu: Lazily compute default config

The default config is computed during creation of the PMU and may do
things like scanning sysfs, when the PMU may just be used as part of
scanning. Change default_config to perf_event_attr_init_default, a
callback that is used when a default config needs initializing. This
avoids holding onto the memory for a perf_event_attr and copying.

On a tigerlake laptop running the pmu-scan benchmark:

Before:
Running 'internals/pmu-scan' benchmark:
Computing performance of sysfs PMU event scan for 100 times
  Average core PMU scanning took: 28.780 usec (+- 0.503 usec)
  Average PMU scanning took: 283.480 usec (+- 18.471 usec)
Number of openat syscalls: 30,227

After:
Running 'internals/pmu-scan' benchmark:
Computing performance of sysfs PMU event scan for 100 times
  Average core PMU scanning took: 27.880 usec (+- 0.169 usec)
  Average PMU scanning took: 245.260 usec (+- 15.758 usec)
Number of openat syscalls: 28,914

Over 3 runs it is a nearly 12% reduction in execution time and a 4.3%
of openat calls.

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: James Clark <james.clark@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: John Garry <john.g.garry@oracle.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: coresight@lists.linaro.org
Link: https://lore.kernel.org/r/20231012175645.1849503-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

2 files changed, 13 insertions, 14 deletions

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 6d6cd8f9133c..fa0c718b9e72 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -60,7 +60,7 @@ struct intel_pt_recording {
 	size_t				priv_size;
 };
 
-static int intel_pt_parse_terms_with_default(struct perf_pmu *pmu,
+static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu,
 					     const char *str,
 					     u64 *config)
 {
@@ -84,7 +84,7 @@ out_free:
 	return err;
 }
 
-static int intel_pt_parse_terms(struct perf_pmu *pmu, const char *str, u64 *config)
+static int intel_pt_parse_terms(const struct perf_pmu *pmu, const char *str, u64 *config)
 {
 	*config = 0;
 	return intel_pt_parse_terms_with_default(pmu, str, config);
@@ -177,7 +177,7 @@ static int intel_pt_pick_bit(int bits, int target)
 	return pick;
 }
 
-static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
+static u64 intel_pt_default_config(const struct perf_pmu *intel_pt_pmu)
 {
 	char buf[256];
 	int mtc, mtc_periods = 0, mtc_period;
@@ -256,18 +256,17 @@ static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr,
 	return 0;
 }
 
-struct perf_event_attr *
-intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
+void intel_pt_pmu_default_config(const struct perf_pmu *intel_pt_pmu,
+				 struct perf_event_attr *attr)
 {
-	struct perf_event_attr *attr;
+	static u64 config;
+	static bool initialized;
 
-	attr = zalloc(sizeof(struct perf_event_attr));
-	if (!attr)
-		return NULL;
-
-	attr->config = intel_pt_default_config(intel_pt_pmu);
-
-	return attr;
+	if (!initialized) {
+		config = intel_pt_default_config(intel_pt_pmu);
+		initialized = true;
+	}
+	attr->config = config;
 }
 
 static const char *intel_pt_find_filter(struct evlist *evlist,
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 949b3e2c67bd..469555ae9b3c 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -23,7 +23,7 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
 		pmu->auxtrace = true;
 		pmu->selectable = true;
-		pmu->default_config = intel_pt_pmu_default_config(pmu);
+		pmu->perf_event_attr_init_default = intel_pt_pmu_default_config;
 	}
 	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) {
 		pmu->auxtrace = true;