summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-record.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/builtin-record.c')
-rw-r--r--tools/perf/builtin-record.c481
1 files changed, 334 insertions, 147 deletions
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1ab349abe904..adf311d15d3d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -34,6 +34,7 @@
#include "util/tsc.h"
#include "util/parse-branch-options.h"
#include "util/parse-regs-options.h"
+#include "util/perf_api_probe.h"
#include "util/llvm-utils.h"
#include "util/bpf-loader.h"
#include "util/trigger.h"
@@ -43,6 +44,9 @@
#include "util/time-utils.h"
#include "util/units.h"
#include "util/bpf-event.h"
+#include "util/util.h"
+#include "util/pfm.h"
+#include "util/clockid.h"
#include "asm/bug.h"
#include "perf.h"
@@ -50,9 +54,13 @@
#include <inttypes.h>
#include <locale.h>
#include <poll.h>
+#include <pthread.h>
#include <unistd.h>
#include <sched.h>
#include <signal.h>
+#ifdef HAVE_EVENTFD_SUPPORT
+#include <sys/eventfd.h>
+#endif
#include <sys/mman.h>
#include <sys/wait.h>
#include <sys/types.h>
@@ -63,6 +71,7 @@
#include <linux/time64.h>
#include <linux/zalloc.h>
#include <linux/bitmap.h>
+#include <sys/time.h>
struct switch_output {
bool enabled;
@@ -84,7 +93,10 @@ struct record {
struct auxtrace_record *itr;
struct evlist *evlist;
struct perf_session *session;
+ struct evlist *sb_evlist;
+ pthread_t thread_id;
int realtime_prio;
+ bool switch_output_event_set;
bool no_buildid;
bool no_buildid_set;
bool no_buildid_cache;
@@ -503,6 +515,20 @@ static int process_synthesized_event(struct perf_tool *tool,
return record__write(rec, NULL, event, event->header.size);
}
+static int process_locked_synthesized_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+ static pthread_mutex_t synth_lock = PTHREAD_MUTEX_INITIALIZER;
+ int ret;
+
+ pthread_mutex_lock(&synth_lock);
+ ret = process_synthesized_event(tool, event, sample, machine);
+ pthread_mutex_unlock(&synth_lock);
+ return ret;
+}
+
static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
{
struct record *rec = to;
@@ -518,6 +544,9 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
static volatile int signr = -1;
static volatile int child_finished;
+#ifdef HAVE_EVENTFD_SUPPORT
+static int done_fd = -1;
+#endif
static void sig_handler(int sig)
{
@@ -527,6 +556,21 @@ static void sig_handler(int sig)
signr = sig;
done = 1;
+#ifdef HAVE_EVENTFD_SUPPORT
+{
+ u64 tmp = 1;
+ /*
+ * It is possible for this signal handler to run after done is checked
+ * in the main loop, but before the perf counter fds are polled. If this
+ * happens, the poll() will continue to wait even though done is set,
+ * and will only break out if either another signal is received, or the
+ * counters are ready for read. To ensure the poll() doesn't sleep when
+ * done is set, use an eventfd (done_fd) to wake up the poll().
+ */
+ if (write(done_fd, &tmp, sizeof(tmp)) < 0)
+ pr_err("failed to signal wakeup fd, error: %m\n");
+}
+#endif // HAVE_EVENTFD_SUPPORT
}
static void sigsegv_handler(int sig)
@@ -723,6 +767,43 @@ static int record__auxtrace_init(struct record *rec __maybe_unused)
#endif
+static int record__config_text_poke(struct evlist *evlist)
+{
+ struct evsel *evsel;
+ int err;
+
+ /* Nothing to do if text poke is already configured */
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.text_poke)
+ return 0;
+ }
+
+ err = parse_events(evlist, "dummy:u", NULL);
+ if (err)
+ return err;
+
+ evsel = evlist__last(evlist);
+
+ evsel->core.attr.freq = 0;
+ evsel->core.attr.sample_period = 1;
+ evsel->core.attr.text_poke = 1;
+ evsel->core.attr.ksymbol = 1;
+
+ evsel->core.system_wide = true;
+ evsel->no_aux_samples = true;
+ evsel->immediate = true;
+
+ /* Text poke must be collected on all CPUs */
+ perf_cpu_map__put(evsel->core.own_cpus);
+ evsel->core.own_cpus = perf_cpu_map__new(NULL);
+ perf_cpu_map__put(evsel->core.cpus);
+ evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
+
+ evsel__set_sample_bit(evsel, TIME);
+
+ return 0;
+}
+
static bool record__kcore_readable(struct machine *machine)
{
char kcore[PATH_MAX];
@@ -805,19 +886,28 @@ static int record__open(struct record *rec)
int rc = 0;
/*
- * For initial_delay we need to add a dummy event so that we can track
- * PERF_RECORD_MMAP while we wait for the initial delay to enable the
- * real events, the ones asked by the user.
+ * For initial_delay or system wide, we need to add a dummy event so
+ * that we can track PERF_RECORD_MMAP to cover the delay of waiting or
+ * event synthesis.
*/
- if (opts->initial_delay) {
- if (perf_evlist__add_dummy(evlist))
- return -ENOMEM;
+ if (opts->initial_delay || target__has_cpu(&opts->target)) {
+ pos = perf_evlist__get_tracking_event(evlist);
+ if (!evsel__is_dummy_event(pos)) {
+ /* Set up dummy event. */
+ if (evlist__add_dummy(evlist))
+ return -ENOMEM;
+ pos = evlist__last(evlist);
+ perf_evlist__set_tracking_event(evlist, pos);
+ }
- pos = evlist__first(evlist);
- pos->tracking = 0;
- pos = evlist__last(evlist);
- pos->tracking = 1;
- pos->core.attr.enable_on_exec = 1;
+ /*
+ * Enable the dummy event when the process is forked for
+ * initial_delay, immediately for system wide.
+ */
+ if (opts->initial_delay && !pos->immediate)
+ pos->core.attr.enable_on_exec = 1;
+ else
+ pos->immediate = 1;
}
perf_evlist__config(evlist, opts, &callchain_param);
@@ -825,7 +915,7 @@ static int record__open(struct record *rec)
evlist__for_each_entry(evlist, pos) {
try_again:
if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
- if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
+ if (evsel__fallback(pos, errno, msg, sizeof(msg))) {
if (verbose > 0)
ui__warning("%s\n", msg);
goto try_again;
@@ -837,8 +927,7 @@ try_again:
goto try_again;
}
rc = -errno;
- perf_evsel__open_strerror(pos, &opts->target,
- errno, msg, sizeof(msg));
+ evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg));
ui__error("%s\n", msg);
goto out;
}
@@ -859,7 +948,7 @@ try_again:
if (perf_evlist__apply_filters(evlist, &pos)) {
pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
- pos->filter, perf_evsel__name(pos), errno,
+ pos->filter, evsel__name(pos), errno,
str_error_r(errno, msg, sizeof(msg)));
rc = -1;
goto out;
@@ -1116,6 +1205,9 @@ static void record__init_features(struct record *rec)
if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+ if (!rec->opts.use_clockid)
+ perf_header__clear_feat(&session->header, HEADER_CLOCK_DATA);
+
perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
if (!record__comp_enabled(rec))
perf_header__clear_feat(&session->header, HEADER_COMPRESSED);
@@ -1288,6 +1380,7 @@ static int record__synthesize(struct record *rec, bool tail)
struct perf_tool *tool = &rec->tool;
int fd = perf_data__fd(data);
int err = 0;
+ event_op f = process_synthesized_event;
if (rec->opts.tail_synthesize != tail)
return 0;
@@ -1402,13 +1495,114 @@ static int record__synthesize(struct record *rec, bool tail)
if (err < 0)
pr_warning("Couldn't synthesize cgroup events.\n");
+ if (rec->opts.nr_threads_synthesize > 1) {
+ perf_set_multithreaded();
+ f = process_locked_synthesized_event;
+ }
+
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
- process_synthesized_event, opts->sample_address,
- 1);
+ f, opts->sample_address,
+ rec->opts.nr_threads_synthesize);
+
+ if (rec->opts.nr_threads_synthesize > 1)
+ perf_set_singlethreaded();
+
out:
return err;
}
+static int record__process_signal_event(union perf_event *event __maybe_unused, void *data)
+{
+ struct record *rec = data;
+ pthread_kill(rec->thread_id, SIGUSR2);
+ return 0;
+}
+
+static int record__setup_sb_evlist(struct record *rec)
+{
+ struct record_opts *opts = &rec->opts;
+
+ if (rec->sb_evlist != NULL) {
+ /*
+ * We get here if --switch-output-event populated the
+ * sb_evlist, so associate a callback that will send a SIGUSR2
+ * to the main thread.
+ */
+ evlist__set_cb(rec->sb_evlist, record__process_signal_event, rec);
+ rec->thread_id = pthread_self();
+ }
+#ifdef HAVE_LIBBPF_SUPPORT
+ if (!opts->no_bpf_event) {
+ if (rec->sb_evlist == NULL) {
+ rec->sb_evlist = evlist__new();
+
+ if (rec->sb_evlist == NULL) {
+ pr_err("Couldn't create side band evlist.\n.");
+ return -1;
+ }
+ }
+
+ if (evlist__add_bpf_sb_event(rec->sb_evlist, &rec->session->header.env)) {
+ pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
+ return -1;
+ }
+ }
+#endif
+ if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) {
+ pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+ opts->no_bpf_event = true;
+ }
+
+ return 0;
+}
+
+static int record__init_clock(struct record *rec)
+{
+ struct perf_session *session = rec->session;
+ struct timespec ref_clockid;
+ struct timeval ref_tod;
+ u64 ref;
+
+ if (!rec->opts.use_clockid)
+ return 0;
+
+ if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+ session->header.env.clock.clockid_res_ns = rec->opts.clockid_res_ns;
+
+ session->header.env.clock.clockid = rec->opts.clockid;
+
+ if (gettimeofday(&ref_tod, NULL) != 0) {
+ pr_err("gettimeofday failed, cannot set reference time.\n");
+ return -1;
+ }
+
+ if (clock_gettime(rec->opts.clockid, &ref_clockid)) {
+ pr_err("clock_gettime failed, cannot set reference time.\n");
+ return -1;
+ }
+
+ ref = (u64) ref_tod.tv_sec * NSEC_PER_SEC +
+ (u64) ref_tod.tv_usec * NSEC_PER_USEC;
+
+ session->header.env.clock.tod_ns = ref;
+
+ ref = (u64) ref_clockid.tv_sec * NSEC_PER_SEC +
+ (u64) ref_clockid.tv_nsec;
+
+ session->header.env.clock.clockid_ns = ref;
+ return 0;
+}
+
+static void hit_auxtrace_snapshot_trigger(struct record *rec)
+{
+ if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
+ trigger_hit(&auxtrace_snapshot_trigger);
+ auxtrace_record__snapshot_started = 1;
+ if (auxtrace_record__snapshot_start(rec->itr))
+ trigger_error(&auxtrace_snapshot_trigger);
+ }
+}
+
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
@@ -1420,9 +1614,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
struct perf_data *data = &rec->data;
struct perf_session *session;
bool disabled = false, draining = false;
- struct evlist *sb_evlist = NULL;
int fd;
float ratio = 0;
+ enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
atexit(record__sig_exit);
signal(SIGCHLD, sig_handler);
@@ -1465,6 +1659,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
pr_err("Compression initialization failed.\n");
return -1;
}
+#ifdef HAVE_EVENTFD_SUPPORT
+ done_fd = eventfd(0, EFD_NONBLOCK);
+ if (done_fd < 0) {
+ pr_err("Failed to create wakeup eventfd, error: %m\n");
+ status = -1;
+ goto out_delete_session;
+ }
+ err = evlist__add_pollfd(rec->evlist, done_fd);
+ if (err < 0) {
+ pr_err("Failed to add wakeup eventfd to poll list\n");
+ status = err;
+ goto out_delete_session;
+ }
+#endif // HAVE_EVENTFD_SUPPORT
session->header.env.comp_type = PERF_COMP_ZSTD;
session->header.env.comp_level = rec->opts.comp_level;
@@ -1475,10 +1683,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
return -1;
}
- record__init_features(rec);
+ if (record__init_clock(rec))
+ return -1;
- if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
- session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+ record__init_features(rec);
if (forks) {
err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
@@ -1528,7 +1736,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
* Normally perf_session__new would do this, but it doesn't have the
* evlist.
*/
- if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
+ if (rec->tool.ordered_events && !evlist__sample_id_all(rec->evlist)) {
pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
rec->tool.ordered_events = false;
}
@@ -1546,21 +1754,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
goto out_child;
}
+ err = -1;
if (!rec->no_buildid
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
pr_err("Couldn't generate buildids. "
"Use --no-buildid to profile anyway.\n");
- err = -1;
goto out_child;
}
- if (!opts->no_bpf_event)
- bpf_event__add_sb_event(&sb_evlist, &session->header.env);
-
- if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) {
- pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
- opts->no_bpf_event = true;
- }
+ err = record__setup_sb_evlist(rec);
+ if (err)
+ goto out_child;
err = record__synthesize(rec, false);
if (err < 0)
@@ -1634,9 +1838,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
perf_evlist__start_workload(rec->evlist);
}
+ if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack))
+ goto out_child;
+
if (opts->initial_delay) {
- usleep(opts->initial_delay * USEC_PER_MSEC);
- evlist__enable(rec->evlist);
+ pr_info(EVLIST_DISABLED_MSG);
+ if (opts->initial_delay > 0) {
+ usleep(opts->initial_delay * USEC_PER_MSEC);
+ evlist__enable(rec->evlist);
+ pr_info(EVLIST_ENABLED_MSG);
+ }
}
trigger_ready(&auxtrace_snapshot_trigger);
@@ -1728,6 +1939,25 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
draining = true;
}
+ if (evlist__ctlfd_process(rec->evlist, &cmd) > 0) {
+ switch (cmd) {
+ case EVLIST_CTL_CMD_ENABLE:
+ pr_info(EVLIST_ENABLED_MSG);
+ break;
+ case EVLIST_CTL_CMD_DISABLE:
+ pr_info(EVLIST_DISABLED_MSG);
+ break;
+ case EVLIST_CTL_CMD_SNAPSHOT:
+ hit_auxtrace_snapshot_trigger(rec);
+ evlist__ctlfd_ack(rec->evlist);
+ break;
+ case EVLIST_CTL_CMD_ACK:
+ case EVLIST_CTL_CMD_UNSUPPORTED:
+ default:
+ break;
+ }
+ }
+
/*
* When perf is starting the traced process, at the end events
* die with the process and we wait for that. Thus no need to
@@ -1761,6 +1991,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
record__synthesize_workload(rec, true);
out_child:
+ evlist__finalize_ctlfd(rec->evlist);
record__mmap_read_all(rec, true);
record__aio_mmap_read_sync(rec);
@@ -1827,11 +2058,15 @@ out_child:
}
out_delete_session:
+#ifdef HAVE_EVENTFD_SUPPORT
+ if (done_fd >= 0)
+ close(done_fd);
+#endif
zstd_fini(&session->zstd_data);
perf_session__delete(session);
if (!opts->no_bpf_event)
- perf_evlist__stop_sb_thread(sb_evlist);
+ perf_evlist__stop_sb_thread(rec->sb_evlist);
return status;
}
@@ -1923,103 +2158,6 @@ static int perf_record_config(const char *var, const char *value, void *cb)
return 0;
}
-struct clockid_map {
- const char *name;
- int clockid;
-};
-
-#define CLOCKID_MAP(n, c) \
- { .name = n, .clockid = (c), }
-
-#define CLOCKID_END { .name = NULL, }
-
-
-/*
- * Add the missing ones, we need to build on many distros...
- */
-#ifndef CLOCK_MONOTONIC_RAW
-#define CLOCK_MONOTONIC_RAW 4
-#endif
-#ifndef CLOCK_BOOTTIME
-#define CLOCK_BOOTTIME 7
-#endif
-#ifndef CLOCK_TAI
-#define CLOCK_TAI 11
-#endif
-
-static const struct clockid_map clockids[] = {
- /* available for all events, NMI safe */
- CLOCKID_MAP("monotonic", CLOCK_MONOTONIC),
- CLOCKID_MAP("monotonic_raw", CLOCK_MONOTONIC_RAW),
-
- /* available for some events */
- CLOCKID_MAP("realtime", CLOCK_REALTIME),
- CLOCKID_MAP("boottime", CLOCK_BOOTTIME),
- CLOCKID_MAP("tai", CLOCK_TAI),
-
- /* available for the lazy */
- CLOCKID_MAP("mono", CLOCK_MONOTONIC),
- CLOCKID_MAP("raw", CLOCK_MONOTONIC_RAW),
- CLOCKID_MAP("real", CLOCK_REALTIME),
- CLOCKID_MAP("boot", CLOCK_BOOTTIME),
-
- CLOCKID_END,
-};
-
-static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
-{
- struct timespec res;
-
- *res_ns = 0;
- if (!clock_getres(clk_id, &res))
- *res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
- else
- pr_warning("WARNING: Failed to determine specified clock resolution.\n");
-
- return 0;
-}
-
-static int parse_clockid(const struct option *opt, const char *str, int unset)
-{
- struct record_opts *opts = (struct record_opts *)opt->value;
- const struct clockid_map *cm;
- const char *ostr = str;
-
- if (unset) {
- opts->use_clockid = 0;
- return 0;
- }
-
- /* no arg passed */
- if (!str)
- return 0;
-
- /* no setting it twice */
- if (opts->use_clockid)
- return -1;
-
- opts->use_clockid = true;
-
- /* if its a number, we're done */
- if (sscanf(str, "%d", &opts->clockid) == 1)
- return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
-
- /* allow a "CLOCK_" prefix to the name */
- if (!strncasecmp(str, "CLOCK_", 6))
- str += 6;
-
- for (cm = clockids; cm->name; cm++) {
- if (!strcasecmp(str, cm->name)) {
- opts->clockid = cm->clockid;
- return get_clockid_res(opts->clockid,
- &opts->clockid_res_ns);
- }
- }
-
- opts->use_clockid = false;
- ui__warning("unknown clockid %s, check man page\n", ostr);
- return -1;
-}
static int record__parse_affinity(const struct option *opt, const char *str, int unset)
{
@@ -2106,6 +2244,15 @@ out_free:
return ret;
}
+static int parse_control_option(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct record_opts *opts = opt->value;
+
+ return evlist__parse_control(str, &opts->ctl_fd, &opts->ctl_fd_ack, &opts->ctl_fd_close);
+}
+
static void switch_output_size_warn(struct record *rec)
{
u64 wakeup_size = evlist__mmap_size(rec->opts.mmap_pages);
@@ -2142,10 +2289,19 @@ static int switch_output_setup(struct record *rec)
};
unsigned long val;
+ /*
+ * If we're using --switch-output-events, then we imply its
+ * --switch-output=signal, as we'll send a SIGUSR2 from the side band
+ * thread to its parent.
+ */
+ if (rec->switch_output_event_set)
+ goto do_signal;
+
if (!s->set)
return 0;
if (!strcmp(s->str, "signal")) {
+do_signal:
s->signal = true;
pr_debug("switch-output with SIGUSR2 signal\n");
goto enabled;
@@ -2232,6 +2388,9 @@ static struct record record = {
.default_per_cpu = true,
},
.mmap_flush = MMAP_FLUSH_DEFAULT,
+ .nr_threads_synthesize = 1,
+ .ctl_fd = -1,
+ .ctl_fd_ack = -1,
},
.tool = {
.sample = process_sample_event,
@@ -2289,7 +2448,7 @@ static struct option __record_options[] = {
OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
"synthesize non-sample events at the end of output"),
OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
- OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
+ OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"),
OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
"Fail if the specified frequency can't be used"),
OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -2334,8 +2493,8 @@ static struct option __record_options[] = {
OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
"monitor event in cgroup name only",
parse_cgroups),
- OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
- "ms to wait before starting measurement after program start"),
+ OPT_INTEGER('D', "delay", &record.opts.initial_delay,
+ "ms to wait before starting measurement after program start (-1: start with events disabled)"),
OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"),
OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
"user to profile"),
@@ -2374,8 +2533,9 @@ static struct option __record_options[] = {
"Record namespaces events"),
OPT_BOOLEAN(0, "all-cgroups", &record.opts.record_cgroup,
"Record cgroup events"),
- OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
- "Record context switch events"),
+ OPT_BOOLEAN_SET(0, "switch-events", &record.opts.record_switch_events,
+ &record.opts.record_switch_events_set,
+ "Record context switch events"),
OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
"Configure all used events to run in kernel space.",
PARSE_OPT_EXCLUSIVE),
@@ -2402,6 +2562,9 @@ static struct option __record_options[] = {
&record.switch_output.set, "signal or size[BKMG] or time[smhd]",
"Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
"signal"),
+ OPT_CALLBACK_SET(0, "switch-output-event", &record.sb_evlist, &record.switch_output_event_set, "switch output event",
+ "switch output event selector. use 'perf list' to list available events",
+ parse_events_option_new_evlist),
OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
"Limit number of switch output generated files"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
@@ -2421,6 +2584,20 @@ static struct option __record_options[] = {
#endif
OPT_CALLBACK(0, "max-size", &record.output_max_size,
"size", "Limit the maximum size of the output file", parse_output_max_size),
+ OPT_UINTEGER(0, "num-thread-synthesize",
+ &record.opts.nr_threads_synthesize,
+ "number of threads to run for event synthesis"),
+#ifdef HAVE_LIBPFM
+ OPT_CALLBACK(0, "pfm-events", &record.evlist, "event",
+ "libpfm4 event selector. use 'perf list' to list available events",
+ parse_libpfm_events_option),
+#endif
+ OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]",
+ "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events,\n"
+ "\t\t\t 'snapshot': AUX area tracing snapshot).\n"
+ "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
+ "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
+ parse_control_option),
OPT_END()
};
@@ -2492,12 +2669,14 @@ int cmd_record(int argc, const char **argv)
!perf_can_record_switch_events()) {
ui__error("kernel does not support recording context switch events\n");
parse_options_usage(record_usage, record_options, "switch-events", 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto out_opts;
}
if (switch_output_setup(rec)) {
parse_options_usage(record_usage, record_options, "switch-output", 0);
- return -EINVAL;
+ err = -EINVAL;
+ goto out_opts;
}
if (rec->switch_output.time) {
@@ -2508,8 +2687,10 @@ int cmd_record(int argc, const char **argv)
if (rec->switch_output.num_files) {
rec->switch_output.filenames = calloc(sizeof(char *),
rec->switch_output.num_files);
- if (!rec->switch_output.filenames)
- return -EINVAL;
+ if (!rec->switch_output.filenames) {
+ err = -EINVAL;
+ goto out_opts;
+ }
}
/*
@@ -2525,7 +2706,8 @@ int cmd_record(int argc, const char **argv)
rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits);
if (!rec->affinity_mask.bits) {
pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out_opts;
}
pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits);
}
@@ -2582,7 +2764,7 @@ int cmd_record(int argc, const char **argv)
record.opts.tail_synthesize = true;
if (rec->evlist->core.nr_entries == 0 &&
- __perf_evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) {
+ __evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out;
}
@@ -2626,6 +2808,14 @@ int cmd_record(int argc, const char **argv)
if (rec->opts.full_auxtrace)
rec->buildid_all = true;
+ if (rec->opts.text_poke) {
+ err = record__config_text_poke(rec->evlist);
+ if (err) {
+ pr_err("record__config_text_poke failed, error %d\n", err);
+ goto out;
+ }
+ }
+
if (record_opts__config(&rec->opts)) {
err = -EINVAL;
goto out;
@@ -2648,6 +2838,8 @@ out:
evlist__delete(rec->evlist);
symbol__exit();
auxtrace_record__free(rec->itr);
+out_opts:
+ evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
return err;
}
@@ -2655,12 +2847,7 @@ static void snapshot_sig_handler(int sig __maybe_unused)
{
struct record *rec = &record;
- if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
- trigger_hit(&auxtrace_snapshot_trigger);
- auxtrace_record__snapshot_started = 1;
- if (auxtrace_record__snapshot_start(record.itr))
- trigger_error(&auxtrace_snapshot_trigger);
- }
+ hit_auxtrace_snapshot_trigger(rec);
if (switch_output_signal(rec))
trigger_hit(&switch_output_trigger);