0197da7aff
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>
43 lines
1 KiB
C
43 lines
1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <string.h>
|
|
#include <stdio.h>
|
|
#include <sys/types.h>
|
|
#include <dirent.h>
|
|
#include <fcntl.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/zalloc.h>
|
|
#include <api/fs/fs.h>
|
|
#include <errno.h>
|
|
|
|
#include "../../../util/intel-pt.h"
|
|
#include "../../../util/intel-bts.h"
|
|
#include "../../../util/pmu.h"
|
|
#include "../../../util/fncache.h"
|
|
#include "../../../util/pmus.h"
|
|
#include "env.h"
|
|
|
|
void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
|
|
{
|
|
#ifdef HAVE_AUXTRACE_SUPPORT
|
|
if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
|
|
pmu->auxtrace = true;
|
|
pmu->selectable = true;
|
|
pmu->perf_event_attr_init_default = intel_pt_pmu_default_config;
|
|
}
|
|
if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) {
|
|
pmu->auxtrace = true;
|
|
pmu->selectable = true;
|
|
}
|
|
#endif
|
|
}
|
|
|
|
int perf_pmus__num_mem_pmus(void)
|
|
{
|
|
/* AMD uses IBS OP pmu and not a core PMU for perf mem/c2c */
|
|
if (x86__is_amd_cpu())
|
|
return 1;
|
|
|
|
/* Intel uses core pmus for perf mem/c2c */
|
|
return perf_pmus__num_core_pmus();
|
|
}
|