mirror of
https://github.com/torvalds/linux.git
synced 2024-12-14 15:13:52 +00:00
0df6ade711
evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps of all evsels. For non-task targets, cpus is set to be cpus requested from the command line, defaulting to all online cpus if no cpus are specified. For an uncore event, all_cpus may be just CPU 0 or every online CPU. This causes all_cpus to have fewer values than the cpus variable which is confusing given the 'all' in the name. To try to make the behavior clearer, rename cpus to user_requested_cpus and add comments on the two struct variables. Signed-off-by: Ian Rogers <irogers@google.com> 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: Namhyung Kim <namhyung@kernel.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> Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
155 lines
3.5 KiB
C
155 lines
3.5 KiB
C
#include <stdio.h>
|
|
#include <fcntl.h>
|
|
#include <stdint.h>
|
|
#include <stdlib.h>
|
|
|
|
#include <linux/err.h>
|
|
|
|
#include "util/ftrace.h"
|
|
#include "util/cpumap.h"
|
|
#include "util/thread_map.h"
|
|
#include "util/debug.h"
|
|
#include "util/evlist.h"
|
|
#include "util/bpf_counter.h"
|
|
|
|
#include "util/bpf_skel/func_latency.skel.h"
|
|
|
|
static struct func_latency_bpf *skel;
|
|
|
|
int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
|
|
{
|
|
int fd, err;
|
|
int i, ncpus = 1, ntasks = 1;
|
|
struct filter_entry *func;
|
|
|
|
if (!list_is_singular(&ftrace->filters)) {
|
|
pr_err("ERROR: %s target function(s).\n",
|
|
list_empty(&ftrace->filters) ? "No" : "Too many");
|
|
return -1;
|
|
}
|
|
|
|
func = list_first_entry(&ftrace->filters, struct filter_entry, list);
|
|
|
|
skel = func_latency_bpf__open();
|
|
if (!skel) {
|
|
pr_err("Failed to open func latency skeleton\n");
|
|
return -1;
|
|
}
|
|
|
|
/* don't need to set cpu filter for system-wide mode */
|
|
if (ftrace->target.cpu_list) {
|
|
ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus);
|
|
bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
|
|
}
|
|
|
|
if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
|
|
ntasks = perf_thread_map__nr(ftrace->evlist->core.threads);
|
|
bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
|
|
}
|
|
|
|
set_max_rlimit();
|
|
|
|
err = func_latency_bpf__load(skel);
|
|
if (err) {
|
|
pr_err("Failed to load func latency skeleton\n");
|
|
goto out;
|
|
}
|
|
|
|
if (ftrace->target.cpu_list) {
|
|
u32 cpu;
|
|
u8 val = 1;
|
|
|
|
skel->bss->has_cpu = 1;
|
|
fd = bpf_map__fd(skel->maps.cpu_filter);
|
|
|
|
for (i = 0; i < ncpus; i++) {
|
|
cpu = perf_cpu_map__cpu(ftrace->evlist->core.user_requested_cpus, i).cpu;
|
|
bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
|
|
}
|
|
}
|
|
|
|
if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
|
|
u32 pid;
|
|
u8 val = 1;
|
|
|
|
skel->bss->has_task = 1;
|
|
fd = bpf_map__fd(skel->maps.task_filter);
|
|
|
|
for (i = 0; i < ntasks; i++) {
|
|
pid = perf_thread_map__pid(ftrace->evlist->core.threads, i);
|
|
bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
|
|
}
|
|
}
|
|
|
|
skel->bss->use_nsec = ftrace->use_nsec;
|
|
|
|
skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin,
|
|
false, func->name);
|
|
if (IS_ERR(skel->links.func_begin)) {
|
|
pr_err("Failed to attach fentry program\n");
|
|
err = PTR_ERR(skel->links.func_begin);
|
|
goto out;
|
|
}
|
|
|
|
skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end,
|
|
true, func->name);
|
|
if (IS_ERR(skel->links.func_end)) {
|
|
pr_err("Failed to attach fexit program\n");
|
|
err = PTR_ERR(skel->links.func_end);
|
|
goto out;
|
|
}
|
|
|
|
/* XXX: we don't actually use this fd - just for poll() */
|
|
return open("/dev/null", O_RDONLY);
|
|
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
|
|
{
|
|
skel->bss->enabled = 1;
|
|
return 0;
|
|
}
|
|
|
|
int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
|
|
{
|
|
skel->bss->enabled = 0;
|
|
return 0;
|
|
}
|
|
|
|
int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
|
|
int buckets[])
|
|
{
|
|
int i, fd, err;
|
|
u32 idx;
|
|
u64 *hist;
|
|
int ncpus = cpu__max_cpu().cpu;
|
|
|
|
fd = bpf_map__fd(skel->maps.latency);
|
|
|
|
hist = calloc(ncpus, sizeof(*hist));
|
|
if (hist == NULL)
|
|
return -ENOMEM;
|
|
|
|
for (idx = 0; idx < NUM_BUCKET; idx++) {
|
|
err = bpf_map_lookup_elem(fd, &idx, hist);
|
|
if (err) {
|
|
buckets[idx] = 0;
|
|
continue;
|
|
}
|
|
|
|
for (i = 0; i < ncpus; i++)
|
|
buckets[idx] += hist[i];
|
|
}
|
|
|
|
free(hist);
|
|
return 0;
|
|
}
|
|
|
|
int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
|
|
{
|
|
func_latency_bpf__destroy(skel);
|
|
return 0;
|
|
}
|