6d18804b96
A common problem is confusing CPU map indices with the CPU, by wrapping the CPU with a struct then this is avoided. This approach is similar to atomic_t. Committer notes: To make it build with BUILD_BPF_SKEL=1 these files needed the conversions to 'struct perf_cpu' usage: tools/perf/util/bpf_counter.c tools/perf/util/bpf_counter_cgroup.c tools/perf/util/bpf_ftrace.c Also perf_env__get_cpu() was removed back in "perf cpumap: Switch cpu_map__build_map to cpu function". Additionally these needed to be fixed for the ARM builds to complete: tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/pmu.c Suggested-by: John Garry <john.garry@huawei.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Vineet Singh <vineet.singh@intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220105061351.120843-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
74 lines
1.8 KiB
C
74 lines
1.8 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Manage affinity to optimize IPIs inside the kernel perf API. */
|
|
#define _GNU_SOURCE 1
|
|
#include <sched.h>
|
|
#include <stdlib.h>
|
|
#include <linux/bitmap.h>
|
|
#include <linux/zalloc.h>
|
|
#include "perf.h"
|
|
#include "cpumap.h"
|
|
#include "affinity.h"
|
|
|
|
static int get_cpu_set_size(void)
|
|
{
|
|
int sz = cpu__max_cpu().cpu + 8 - 1;
|
|
/*
|
|
* sched_getaffinity doesn't like masks smaller than the kernel.
|
|
* Hopefully that's big enough.
|
|
*/
|
|
if (sz < 4096)
|
|
sz = 4096;
|
|
return sz / 8;
|
|
}
|
|
|
|
int affinity__setup(struct affinity *a)
|
|
{
|
|
int cpu_set_size = get_cpu_set_size();
|
|
|
|
a->orig_cpus = bitmap_zalloc(cpu_set_size * 8);
|
|
if (!a->orig_cpus)
|
|
return -1;
|
|
sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
|
|
a->sched_cpus = bitmap_zalloc(cpu_set_size * 8);
|
|
if (!a->sched_cpus) {
|
|
zfree(&a->orig_cpus);
|
|
return -1;
|
|
}
|
|
bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size);
|
|
a->changed = false;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* perf_event_open does an IPI internally to the target CPU.
|
|
* It is more efficient to change perf's affinity to the target
|
|
* CPU and then set up all events on that CPU, so we amortize
|
|
* CPU communication.
|
|
*/
|
|
void affinity__set(struct affinity *a, int cpu)
|
|
{
|
|
int cpu_set_size = get_cpu_set_size();
|
|
|
|
if (cpu == -1)
|
|
return;
|
|
a->changed = true;
|
|
set_bit(cpu, a->sched_cpus);
|
|
/*
|
|
* We ignore errors because affinity is just an optimization.
|
|
* This could happen for example with isolated CPUs or cpusets.
|
|
* In this case the IPIs inside the kernel's perf API still work.
|
|
*/
|
|
sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus);
|
|
clear_bit(cpu, a->sched_cpus);
|
|
}
|
|
|
|
void affinity__cleanup(struct affinity *a)
|
|
{
|
|
int cpu_set_size = get_cpu_set_size();
|
|
|
|
if (a->changed)
|
|
sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
|
|
zfree(&a->sched_cpus);
|
|
zfree(&a->orig_cpus);
|
|
}
|