mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 12:45:16 +07:00
cfacbabd1d
Currently we can crash perf record when running in pipe mode, like: $ perf record ls | perf report # To display the perf.data header info, please use --header/--header-only options. # perf: Segmentation fault Error: The - file has no samples! The callstack of the crash is: 0x0000000000515242 in perf_event__synthesize_event_update_name 3513 ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]); (gdb) bt #0 0x0000000000515242 in perf_event__synthesize_event_update_name #1 0x00000000005158a4 in perf_event__synthesize_extra_attr #2 0x0000000000443347 in record__synthesize #3 0x00000000004438e3 in __cmd_record #4 0x000000000044514e in cmd_record #5 0x00000000004cbc95 in run_builtin #6 0x00000000004cbf02 in handle_internal_command #7 0x00000000004cc054 in run_argv #8 0x00000000004cc422 in main The reason of the crash is that the evsel does not have ids array allocated and the pipe's synthesize code tries to access it. We don't force evsel ids allocation when we have single event, because it's not needed. However we need it when we are in pipe mode even for single event as a key for evsel update event. Fixing this by forcing evsel ids allocation event for single event, when we are in pipe mode. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180302161354.30192-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
327 lines
7.1 KiB
C
327 lines
7.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include "evlist.h"
|
|
#include "evsel.h"
|
|
#include "cpumap.h"
|
|
#include "parse-events.h"
|
|
#include <errno.h>
|
|
#include <api/fs/fs.h>
|
|
#include <subcmd/parse-options.h>
|
|
#include "util.h"
|
|
#include "cloexec.h"
|
|
|
|
typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
|
|
|
|
static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
|
|
{
|
|
struct perf_evlist *evlist;
|
|
struct perf_evsel *evsel;
|
|
unsigned long flags = perf_event_open_cloexec_flag();
|
|
int err = -EAGAIN, fd;
|
|
static pid_t pid = -1;
|
|
|
|
evlist = perf_evlist__new();
|
|
if (!evlist)
|
|
return -ENOMEM;
|
|
|
|
if (parse_events(evlist, str, NULL))
|
|
goto out_delete;
|
|
|
|
evsel = perf_evlist__first(evlist);
|
|
|
|
while (1) {
|
|
fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
|
|
if (fd < 0) {
|
|
if (pid == -1 && errno == EACCES) {
|
|
pid = 0;
|
|
continue;
|
|
}
|
|
goto out_delete;
|
|
}
|
|
break;
|
|
}
|
|
close(fd);
|
|
|
|
fn(evsel);
|
|
|
|
fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
|
|
if (fd < 0) {
|
|
if (errno == EINVAL)
|
|
err = -EINVAL;
|
|
goto out_delete;
|
|
}
|
|
close(fd);
|
|
err = 0;
|
|
|
|
out_delete:
|
|
perf_evlist__delete(evlist);
|
|
return err;
|
|
}
|
|
|
|
static bool perf_probe_api(setup_probe_fn_t fn)
|
|
{
|
|
const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
|
|
struct cpu_map *cpus;
|
|
int cpu, ret, i = 0;
|
|
|
|
cpus = cpu_map__new(NULL);
|
|
if (!cpus)
|
|
return false;
|
|
cpu = cpus->map[0];
|
|
cpu_map__put(cpus);
|
|
|
|
do {
|
|
ret = perf_do_probe_api(fn, cpu, try[i++]);
|
|
if (!ret)
|
|
return true;
|
|
} while (ret == -EAGAIN && try[i]);
|
|
|
|
return false;
|
|
}
|
|
|
|
static void perf_probe_sample_identifier(struct perf_evsel *evsel)
|
|
{
|
|
evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
|
|
}
|
|
|
|
static void perf_probe_comm_exec(struct perf_evsel *evsel)
|
|
{
|
|
evsel->attr.comm_exec = 1;
|
|
}
|
|
|
|
static void perf_probe_context_switch(struct perf_evsel *evsel)
|
|
{
|
|
evsel->attr.context_switch = 1;
|
|
}
|
|
|
|
bool perf_can_sample_identifier(void)
|
|
{
|
|
return perf_probe_api(perf_probe_sample_identifier);
|
|
}
|
|
|
|
static bool perf_can_comm_exec(void)
|
|
{
|
|
return perf_probe_api(perf_probe_comm_exec);
|
|
}
|
|
|
|
bool perf_can_record_switch_events(void)
|
|
{
|
|
return perf_probe_api(perf_probe_context_switch);
|
|
}
|
|
|
|
bool perf_can_record_cpu_wide(void)
|
|
{
|
|
struct perf_event_attr attr = {
|
|
.type = PERF_TYPE_SOFTWARE,
|
|
.config = PERF_COUNT_SW_CPU_CLOCK,
|
|
.exclude_kernel = 1,
|
|
};
|
|
struct cpu_map *cpus;
|
|
int cpu, fd;
|
|
|
|
cpus = cpu_map__new(NULL);
|
|
if (!cpus)
|
|
return false;
|
|
cpu = cpus->map[0];
|
|
cpu_map__put(cpus);
|
|
|
|
fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
|
|
if (fd < 0)
|
|
return false;
|
|
close(fd);
|
|
|
|
return true;
|
|
}
|
|
|
|
void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
|
|
struct callchain_param *callchain)
|
|
{
|
|
struct perf_evsel *evsel;
|
|
bool use_sample_identifier = false;
|
|
bool use_comm_exec;
|
|
bool sample_id = opts->sample_id;
|
|
|
|
/*
|
|
* Set the evsel leader links before we configure attributes,
|
|
* since some might depend on this info.
|
|
*/
|
|
if (opts->group)
|
|
perf_evlist__set_leader(evlist);
|
|
|
|
if (evlist->cpus->map[0] < 0)
|
|
opts->no_inherit = true;
|
|
|
|
use_comm_exec = perf_can_comm_exec();
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
perf_evsel__config(evsel, opts, callchain);
|
|
if (evsel->tracking && use_comm_exec)
|
|
evsel->attr.comm_exec = 1;
|
|
}
|
|
|
|
if (opts->full_auxtrace) {
|
|
/*
|
|
* Need to be able to synthesize and parse selected events with
|
|
* arbitrary sample types, which requires always being able to
|
|
* match the id.
|
|
*/
|
|
use_sample_identifier = perf_can_sample_identifier();
|
|
sample_id = true;
|
|
} else if (evlist->nr_entries > 1) {
|
|
struct perf_evsel *first = perf_evlist__first(evlist);
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
if (evsel->attr.sample_type == first->attr.sample_type)
|
|
continue;
|
|
use_sample_identifier = perf_can_sample_identifier();
|
|
break;
|
|
}
|
|
sample_id = true;
|
|
}
|
|
|
|
if (sample_id) {
|
|
evlist__for_each_entry(evlist, evsel)
|
|
perf_evsel__set_sample_id(evsel, use_sample_identifier);
|
|
}
|
|
|
|
perf_evlist__set_id_pos(evlist);
|
|
}
|
|
|
|
static int get_max_rate(unsigned int *rate)
|
|
{
|
|
return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate);
|
|
}
|
|
|
|
static int record_opts__config_freq(struct record_opts *opts)
|
|
{
|
|
bool user_freq = opts->user_freq != UINT_MAX;
|
|
unsigned int max_rate;
|
|
|
|
if (opts->user_interval != ULLONG_MAX)
|
|
opts->default_interval = opts->user_interval;
|
|
if (user_freq)
|
|
opts->freq = opts->user_freq;
|
|
|
|
/*
|
|
* User specified count overrides default frequency.
|
|
*/
|
|
if (opts->default_interval)
|
|
opts->freq = 0;
|
|
else if (opts->freq) {
|
|
opts->default_interval = opts->freq;
|
|
} else {
|
|
pr_err("frequency and count are zero, aborting\n");
|
|
return -1;
|
|
}
|
|
|
|
if (get_max_rate(&max_rate))
|
|
return 0;
|
|
|
|
/*
|
|
* User specified frequency is over current maximum.
|
|
*/
|
|
if (user_freq && (max_rate < opts->freq)) {
|
|
if (opts->strict_freq) {
|
|
pr_err("error: Maximum frequency rate (%'u Hz) exceeded.\n"
|
|
" Please use -F freq option with a lower value or consider\n"
|
|
" tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
|
|
max_rate);
|
|
return -1;
|
|
} else {
|
|
pr_warning("warning: Maximum frequency rate (%'u Hz) exceeded, throttling from %'u Hz to %'u Hz.\n"
|
|
" The limit can be raised via /proc/sys/kernel/perf_event_max_sample_rate.\n"
|
|
" The kernel will lower it when perf's interrupts take too long.\n"
|
|
" Use --strict-freq to disable this throttling, refusing to record.\n",
|
|
max_rate, opts->freq, max_rate);
|
|
|
|
opts->freq = max_rate;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Default frequency is over current maximum.
|
|
*/
|
|
if (max_rate < opts->freq) {
|
|
pr_warning("Lowering default frequency rate to %u.\n"
|
|
"Please consider tweaking "
|
|
"/proc/sys/kernel/perf_event_max_sample_rate.\n",
|
|
max_rate);
|
|
opts->freq = max_rate;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int record_opts__config(struct record_opts *opts)
|
|
{
|
|
return record_opts__config_freq(opts);
|
|
}
|
|
|
|
bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
|
|
{
|
|
struct perf_evlist *temp_evlist;
|
|
struct perf_evsel *evsel;
|
|
int err, fd, cpu;
|
|
bool ret = false;
|
|
pid_t pid = -1;
|
|
|
|
temp_evlist = perf_evlist__new();
|
|
if (!temp_evlist)
|
|
return false;
|
|
|
|
err = parse_events(temp_evlist, str, NULL);
|
|
if (err)
|
|
goto out_delete;
|
|
|
|
evsel = perf_evlist__last(temp_evlist);
|
|
|
|
if (!evlist || cpu_map__empty(evlist->cpus)) {
|
|
struct cpu_map *cpus = cpu_map__new(NULL);
|
|
|
|
cpu = cpus ? cpus->map[0] : 0;
|
|
cpu_map__put(cpus);
|
|
} else {
|
|
cpu = evlist->cpus->map[0];
|
|
}
|
|
|
|
while (1) {
|
|
fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
|
|
perf_event_open_cloexec_flag());
|
|
if (fd < 0) {
|
|
if (pid == -1 && errno == EACCES) {
|
|
pid = 0;
|
|
continue;
|
|
}
|
|
goto out_delete;
|
|
}
|
|
break;
|
|
}
|
|
close(fd);
|
|
ret = true;
|
|
|
|
out_delete:
|
|
perf_evlist__delete(temp_evlist);
|
|
return ret;
|
|
}
|
|
|
|
int record__parse_freq(const struct option *opt, const char *str, int unset __maybe_unused)
|
|
{
|
|
unsigned int freq;
|
|
struct record_opts *opts = opt->value;
|
|
|
|
if (!str)
|
|
return -EINVAL;
|
|
|
|
if (strcasecmp(str, "max") == 0) {
|
|
if (get_max_rate(&freq)) {
|
|
pr_err("couldn't read /proc/sys/kernel/perf_event_max_sample_rate\n");
|
|
return -1;
|
|
}
|
|
pr_info("info: Using a maximum frequency rate of %'d Hz\n", freq);
|
|
} else {
|
|
freq = atoi(str);
|
|
}
|
|
|
|
opts->user_freq = freq;
|
|
return 0;
|
|
}
|