mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-08 19:44:10 +08:00
0255571a16
Switch some raw accesses to the cpu map to using the library API. This can help with reference count checking. Some BPF cases switch from index to CPU for consistency, this shouldn't matter as the CPU map is full. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Link: http://lore.kernel.org/lkml/20220503041757.2365696-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
304 lines
7.0 KiB
C
304 lines
7.0 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
/* Copyright (c) 2021 Facebook */
|
|
/* Copyright (c) 2021 Google */
|
|
|
|
#include <assert.h>
|
|
#include <limits.h>
|
|
#include <unistd.h>
|
|
#include <sys/file.h>
|
|
#include <sys/time.h>
|
|
#include <sys/resource.h>
|
|
#include <linux/err.h>
|
|
#include <linux/zalloc.h>
|
|
#include <linux/perf_event.h>
|
|
#include <api/fs/fs.h>
|
|
#include <perf/bpf_perf.h>
|
|
|
|
#include "affinity.h"
|
|
#include "bpf_counter.h"
|
|
#include "cgroup.h"
|
|
#include "counts.h"
|
|
#include "debug.h"
|
|
#include "evsel.h"
|
|
#include "evlist.h"
|
|
#include "target.h"
|
|
#include "cpumap.h"
|
|
#include "thread_map.h"
|
|
|
|
#include "bpf_skel/bperf_cgroup.skel.h"
|
|
|
|
static struct perf_event_attr cgrp_switch_attr = {
|
|
.type = PERF_TYPE_SOFTWARE,
|
|
.config = PERF_COUNT_SW_CGROUP_SWITCHES,
|
|
.size = sizeof(cgrp_switch_attr),
|
|
.sample_period = 1,
|
|
.disabled = 1,
|
|
};
|
|
|
|
static struct evsel *cgrp_switch;
|
|
static struct bperf_cgroup_bpf *skel;
|
|
|
|
#define FD(evt, cpu) (*(int *)xyarray__entry(evt->core.fd, cpu, 0))
|
|
|
|
static int bperf_load_program(struct evlist *evlist)
|
|
{
|
|
struct bpf_link *link;
|
|
struct evsel *evsel;
|
|
struct cgroup *cgrp, *leader_cgrp;
|
|
int i, j;
|
|
struct perf_cpu cpu;
|
|
int total_cpus = cpu__max_cpu().cpu;
|
|
int map_size, map_fd;
|
|
int prog_fd, err;
|
|
|
|
skel = bperf_cgroup_bpf__open();
|
|
if (!skel) {
|
|
pr_err("Failed to open cgroup skeleton\n");
|
|
return -1;
|
|
}
|
|
|
|
skel->rodata->num_cpus = total_cpus;
|
|
skel->rodata->num_events = evlist->core.nr_entries / nr_cgroups;
|
|
|
|
BUG_ON(evlist->core.nr_entries % nr_cgroups != 0);
|
|
|
|
/* we need one copy of events per cpu for reading */
|
|
map_size = total_cpus * evlist->core.nr_entries / nr_cgroups;
|
|
bpf_map__set_max_entries(skel->maps.events, map_size);
|
|
bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups);
|
|
/* previous result is saved in a per-cpu array */
|
|
map_size = evlist->core.nr_entries / nr_cgroups;
|
|
bpf_map__set_max_entries(skel->maps.prev_readings, map_size);
|
|
/* cgroup result needs all events (per-cpu) */
|
|
map_size = evlist->core.nr_entries;
|
|
bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size);
|
|
|
|
set_max_rlimit();
|
|
|
|
err = bperf_cgroup_bpf__load(skel);
|
|
if (err) {
|
|
pr_err("Failed to load cgroup skeleton\n");
|
|
goto out;
|
|
}
|
|
|
|
if (cgroup_is_v2("perf_event") > 0)
|
|
skel->bss->use_cgroup_v2 = 1;
|
|
|
|
err = -1;
|
|
|
|
cgrp_switch = evsel__new(&cgrp_switch_attr);
|
|
if (evsel__open_per_cpu(cgrp_switch, evlist->core.all_cpus, -1) < 0) {
|
|
pr_err("Failed to open cgroup switches event\n");
|
|
goto out;
|
|
}
|
|
|
|
perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
|
|
link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch,
|
|
FD(cgrp_switch, cpu.cpu));
|
|
if (IS_ERR(link)) {
|
|
pr_err("Failed to attach cgroup program\n");
|
|
err = PTR_ERR(link);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Update cgrp_idx map from cgroup-id to event index.
|
|
*/
|
|
cgrp = NULL;
|
|
i = 0;
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
if (cgrp == NULL || evsel->cgrp == leader_cgrp) {
|
|
leader_cgrp = evsel->cgrp;
|
|
evsel->cgrp = NULL;
|
|
|
|
/* open single copy of the events w/o cgroup */
|
|
err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1);
|
|
if (err) {
|
|
pr_err("Failed to open first cgroup events\n");
|
|
goto out;
|
|
}
|
|
|
|
map_fd = bpf_map__fd(skel->maps.events);
|
|
perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) {
|
|
int fd = FD(evsel, cpu.cpu);
|
|
__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
|
|
|
|
err = bpf_map_update_elem(map_fd, &idx, &fd,
|
|
BPF_ANY);
|
|
if (err < 0) {
|
|
pr_err("Failed to update perf_event fd\n");
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
evsel->cgrp = leader_cgrp;
|
|
}
|
|
evsel->supported = true;
|
|
|
|
if (evsel->cgrp == cgrp)
|
|
continue;
|
|
|
|
cgrp = evsel->cgrp;
|
|
|
|
if (read_cgroup_id(cgrp) < 0) {
|
|
pr_err("Failed to get cgroup id\n");
|
|
err = -1;
|
|
goto out;
|
|
}
|
|
|
|
map_fd = bpf_map__fd(skel->maps.cgrp_idx);
|
|
err = bpf_map_update_elem(map_fd, &cgrp->id, &i, BPF_ANY);
|
|
if (err < 0) {
|
|
pr_err("Failed to update cgroup index map\n");
|
|
goto out;
|
|
}
|
|
|
|
i++;
|
|
}
|
|
|
|
/*
|
|
* bperf uses BPF_PROG_TEST_RUN to get accurate reading. Check
|
|
* whether the kernel support it
|
|
*/
|
|
prog_fd = bpf_program__fd(skel->progs.trigger_read);
|
|
err = bperf_trigger_reading(prog_fd, 0);
|
|
if (err) {
|
|
pr_warning("The kernel does not support test_run for raw_tp BPF programs.\n"
|
|
"Therefore, --for-each-cgroup might show inaccurate readings\n");
|
|
err = 0;
|
|
}
|
|
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static int bperf_cgrp__load(struct evsel *evsel,
|
|
struct target *target __maybe_unused)
|
|
{
|
|
static bool bperf_loaded = false;
|
|
|
|
evsel->bperf_leader_prog_fd = -1;
|
|
evsel->bperf_leader_link_fd = -1;
|
|
|
|
if (!bperf_loaded && bperf_load_program(evsel->evlist))
|
|
return -1;
|
|
|
|
bperf_loaded = true;
|
|
/* just to bypass bpf_counter_skip() */
|
|
evsel->follower_skel = (struct bperf_follower_bpf *)skel;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused,
|
|
int cpu __maybe_unused, int fd __maybe_unused)
|
|
{
|
|
/* nothing to do */
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* trigger the leader prog on each cpu, so the cgrp_reading map could get
|
|
* the latest results.
|
|
*/
|
|
static int bperf_cgrp__sync_counters(struct evlist *evlist)
|
|
{
|
|
struct perf_cpu cpu;
|
|
int idx;
|
|
int prog_fd = bpf_program__fd(skel->progs.trigger_read);
|
|
|
|
perf_cpu_map__for_each_cpu(cpu, idx, evlist->core.all_cpus)
|
|
bperf_trigger_reading(prog_fd, cpu.cpu);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int bperf_cgrp__enable(struct evsel *evsel)
|
|
{
|
|
if (evsel->core.idx)
|
|
return 0;
|
|
|
|
bperf_cgrp__sync_counters(evsel->evlist);
|
|
|
|
skel->bss->enabled = 1;
|
|
return 0;
|
|
}
|
|
|
|
static int bperf_cgrp__disable(struct evsel *evsel)
|
|
{
|
|
if (evsel->core.idx)
|
|
return 0;
|
|
|
|
bperf_cgrp__sync_counters(evsel->evlist);
|
|
|
|
skel->bss->enabled = 0;
|
|
return 0;
|
|
}
|
|
|
|
static int bperf_cgrp__read(struct evsel *evsel)
|
|
{
|
|
struct evlist *evlist = evsel->evlist;
|
|
int total_cpus = cpu__max_cpu().cpu;
|
|
struct perf_counts_values *counts;
|
|
struct bpf_perf_event_value *values;
|
|
int reading_map_fd, err = 0;
|
|
|
|
if (evsel->core.idx)
|
|
return 0;
|
|
|
|
bperf_cgrp__sync_counters(evsel->evlist);
|
|
|
|
values = calloc(total_cpus, sizeof(*values));
|
|
if (values == NULL)
|
|
return -ENOMEM;
|
|
|
|
reading_map_fd = bpf_map__fd(skel->maps.cgrp_readings);
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
__u32 idx = evsel->core.idx;
|
|
int i;
|
|
struct perf_cpu cpu;
|
|
|
|
err = bpf_map_lookup_elem(reading_map_fd, &idx, values);
|
|
if (err) {
|
|
pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n",
|
|
idx, evsel__name(evsel), evsel->cgrp->name);
|
|
goto out;
|
|
}
|
|
|
|
perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
|
|
counts = perf_counts(evsel->counts, i, 0);
|
|
counts->val = values[cpu.cpu].counter;
|
|
counts->ena = values[cpu.cpu].enabled;
|
|
counts->run = values[cpu.cpu].running;
|
|
}
|
|
}
|
|
|
|
out:
|
|
free(values);
|
|
return err;
|
|
}
|
|
|
|
static int bperf_cgrp__destroy(struct evsel *evsel)
|
|
{
|
|
if (evsel->core.idx)
|
|
return 0;
|
|
|
|
bperf_cgroup_bpf__destroy(skel);
|
|
evsel__delete(cgrp_switch); // it'll destroy on_switch progs too
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct bpf_counter_ops bperf_cgrp_ops = {
|
|
.load = bperf_cgrp__load,
|
|
.enable = bperf_cgrp__enable,
|
|
.disable = bperf_cgrp__disable,
|
|
.read = bperf_cgrp__read,
|
|
.install_pe = bperf_cgrp__install_pe,
|
|
.destroy = bperf_cgrp__destroy,
|
|
};
|