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>

1 files changed, 23 insertions, 22 deletions

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 08a76734ccd2..e3acc739bd00 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -113,6 +113,25 @@ arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts,
 	}
 }
 
+static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu)
+{
+	static __u64 sample_period;
+
+	if (sample_period)
+		return sample_period;
+
+	/*
+	 * If kernel driver doesn't advertise a minimum,
+	 * use max allowable by PMSIDR_EL1.INTERVAL
+	 */
+	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
+				&sample_period) != 1) {
+		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
+		sample_period = 4096;
+	}
+	return sample_period;
+}
+
 static int arm_spe_recording_options(struct auxtrace_record *itr,
 				     struct evlist *evlist,
 				     struct record_opts *opts)
@@ -136,7 +155,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 				return -EINVAL;
 			}
 			evsel->core.attr.freq = 0;
-			evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period;
+			evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
 			evsel->needs_auxtrace_mmap = true;
 			arm_spe_evsel = evsel;
 			opts->full_auxtrace = true;
@@ -495,26 +514,8 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	return &sper->itr;
 }
 
-struct perf_event_attr
-*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu)
+void
+arm_spe_pmu_default_config(const struct perf_pmu *arm_spe_pmu, struct perf_event_attr *attr)
 {
-	struct perf_event_attr *attr;
-
-	attr = zalloc(sizeof(struct perf_event_attr));
-	if (!attr) {
-		pr_err("arm_spe default config cannot allocate a perf_event_attr\n");
-		return NULL;
-	}
-
-	/*
-	 * If kernel driver doesn't advertise a minimum,
-	 * use max allowable by PMSIDR_EL1.INTERVAL
-	 */
-	if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
-				  &attr->sample_period) != 1) {
-		pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
-		attr->sample_period = 4096;
-	}
-
-	return attr;
+	attr->sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
 }