1 files changed, 163 insertions, 23 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1ab349abe904..e108d90ae2ed 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 +44,8 @@
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
+#include "util/util.h"
+#include "util/pfm.h"
 #include "asm/bug.h"
 #include "perf.h"
 
@@ -50,9 +53,13 @@
 #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>
@@ -84,7 +91,10 @@ 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 +513,20 @@ 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 +542,9 @@ 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 +554,21 @@ 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)
@@ -805,19 +847,28 @@ 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 (opts->initial_delay || target__has_cpu(&opts->target)) {
 		if (perf_evlist__add_dummy(evlist))
 			return -ENOMEM;
 
+		/* Disable tracking of mmaps on lead event. */
 		pos = evlist__first(evlist);
 		pos->tracking = 0;
+		/* Set up dummy event. */
 		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->core.attr.enable_on_exec = 1;
+		else
+			pos->immediate = 1;
 	}
 
 	perf_evlist__config(evlist, opts, &callchain_param);
@@ -825,7 +876,7 @@ 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 +888,7 @@ 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 +909,7 @@ 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;
@@ -1288,6 +1338,7 @@ 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 +1453,67 @@ 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();
+	}
+
+	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;
+		}
+	}
+
+	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 __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -1420,7 +1525,6 @@ 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;
 
@@ -1465,6 +1569,20 @@ 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;
@@ -1546,21 +1664,17 @@ 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)
@@ -1827,11 +1941,15 @@ 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;
 }
 
@@ -2142,10 +2260,19 @@ 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 +2359,7 @@ static struct record record = {
 			.default_per_cpu = true,
 		},
 		.mmap_flush          = MMAP_FLUSH_DEFAULT,
+		.nr_threads_synthesize = 1,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -2374,8 +2502,9 @@ 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 +2531,9 @@ 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 +2553,14 @@ 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_END()
 };