perf record: Add finished init event

In preparation for recording sideband events in a virtual machine guest so
that they can be injected into a host perf.data file.

This is needed to enable injecting events after the initial synthesized
user events (that have an all zero id sample) but before regular events.

Committer notes:

Add entry about PERF_RECORD_FINISHED_INIT to
tools/perf/Documentation/perf.data-file-format.txt.

Committer testing:

Before:

  # perf report -D | grep FINISHED
  0 0x5910 [0x8]: PERF_RECORD_FINISHED_ROUND
    FINISHED_ROUND events:          1  ( 0.5%)
  #

After:

  # perf record -- sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.020 MB perf.data (7 samples) ]
  # perf report -D | grep FINISHED
  0 0x5068 [0x8]: PERF_RECORD_FINISHED_INIT: unhandled!
  0 0x5390 [0x8]: PERF_RECORD_FINISHED_ROUND
    FINISHED_ROUND events:          1  ( 0.5%)
     FINISHED_INIT events:          1  ( 0.5%)
  #
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20220610113316.6682-5-adrian.hunter@intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/lib/perf/include/perf/event.h

@@ -389,6 +389,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_TIME_CONV			= 79,
 	PERF_RECORD_HEADER_FEATURE		= 80,
 	PERF_RECORD_COMPRESSED			= 81,
+	PERF_RECORD_FINISHED_INIT		= 82,
 	PERF_RECORD_HEADER_MAX
 };
 

tools/perf/Documentation/perf.data-file-format.txt

@@ -607,6 +607,16 @@ struct compressed_event {
 	char				data[];
 };
 
+	PERF_RECORD_FINISHED_INIT			= 82,
+
+Marks the end of records for the system, pre-existing threads in system wide
+sessions, etc. Those are the ones prefixed PERF_RECORD_USER_*.
+
+This is used, for instance, to 'perf inject' events after init and before
+regular events, those emitted by the kernel, to support combining guest and
+host records.
+
+
 The header is followed by compressed data frame that can be decompressed
 into array of perf trace records. The size of the entire compressed event
 record including the header is limited by the max value of header.size.

tools/perf/builtin-inject.c

@@ -1059,6 +1059,7 @@ int cmd_inject(int argc, const char **argv)
 			.stat		= perf_event__repipe_op2_synth,
 			.stat_round	= perf_event__repipe_op2_synth,
 			.feature	= perf_event__repipe_op2_synth,
+			.finished_init	= perf_event__repipe_op2_synth,
 			.compressed	= perf_event__repipe_op4_synth,
 			.auxtrace	= perf_event__repipe_auxtrace,
 		},

tools/perf/builtin-record.c

@@ -1388,6 +1388,11 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
+static struct perf_event_header finished_init_event = {
+	.size = sizeof(struct perf_event_header),
+	.type = PERF_RECORD_FINISHED_INIT,
+};
+
 static void record__adjust_affinity(struct record *rec, struct mmap *map)
 {
 	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
@@ -1696,6 +1701,14 @@ static int record__synthesize_workload(struct record *rec, bool tail)
 	return err;
 }
 
+static int write_finished_init(struct record *rec, bool tail)
+{
+	if (rec->opts.tail_synthesize != tail)
+		return 0;
+
+	return record__write(rec, NULL, &finished_init_event, sizeof(finished_init_event));
+}
+
 static int record__synthesize(struct record *rec, bool tail);
 
 static int
@@ -1710,6 +1723,8 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	record__aio_mmap_read_sync(rec);
 
+	write_finished_init(rec, true);
+
 	record__synthesize(rec, true);
 	if (target__none(&rec->opts.target))
 		record__synthesize_workload(rec, true);
@@ -1764,6 +1779,7 @@ record__switch_output(struct record *rec, bool at_exit)
 		 */
 		if (target__none(&rec->opts.target))
 			record__synthesize_workload(rec, false);
+		write_finished_init(rec, false);
 	}
 	return fd;
 }
@@ -2419,6 +2435,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	trigger_ready(&auxtrace_snapshot_trigger);
 	trigger_ready(&switch_output_trigger);
 	perf_hooks__invoke_record_start();
+
+	/*
+	 * Must write FINISHED_INIT so it will be seen after all other
+	 * synthesized user events, but before any regular events.
+	 */
+	err = write_finished_init(rec, false);
+	if (err < 0)
+		goto out_child;
+
 	for (;;) {
 		unsigned long long hits = thread->samples;
 
@@ -2563,6 +2588,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n",
 			record__waking(rec));
 
+	write_finished_init(rec, true);
+
 	if (target__none(&rec->opts.target))
 		record__synthesize_workload(rec, true);
 

tools/perf/util/event.c

@@ -76,6 +76,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
 	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
+	[PERF_RECORD_FINISHED_INIT]		= "FINISHED_INIT",
 };
 
 const char *perf_event__name(unsigned int id)

tools/perf/util/session.c

@@ -562,6 +562,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->feature = process_event_op2_stub;
 	if (tool->compressed == NULL)
 		tool->compressed = perf_session__process_compressed_event;
+	if (tool->finished_init == NULL)
+		tool->finished_init = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -1706,6 +1708,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		if (err)
 			dump_event(session->evlist, event, file_offset, &sample, file_path);
 		return err;
+	case PERF_RECORD_FINISHED_INIT:
+		return tool->finished_init(session, event);
 	default:
 		return -EINVAL;
 	}

tools/perf/util/tool.h

@@ -76,7 +76,8 @@ struct perf_tool {
 			stat_config,
 			stat,
 			stat_round,
-			feature;
+			feature,
+			finished_init;
 	event_op4	compressed;
 	event_op3	auxtrace;
 	bool		ordered_events;