perf stat record: Synthesize stat record data

Synthesizing needed stat record data for report/script:
  - cpu/thread maps
  - stat config

Committer note:

New records generated on a perf.data file with this patch:

  $ perf report -D | grep PERF_RECORD_
  0x568 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 29097
  0x590 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
  0x5a2 [0x40]: PERF_RECORD_STAT_CONFIG
  $

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Kan Liang <kan.liang@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1446734469-11352-5-git-send-email-jolsa@kernel.org
[ Adjusted wrt kernel PERF_RECORD_MMAP added when introducing 'perf stat record' ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 43 insertions, 13 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c9c896a..45bf4d2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -217,26 +217,20 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 	return 0;
 }
 
-static int perf_stat__write(struct perf_stat *stat, void *bf, size_t size)
+static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
 {
-	if (perf_data_file__write(stat->session->file, bf, size) < 0) {
+	if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
 
-	stat->bytes_written += size;
+	perf_stat.bytes_written += event->header.size;
 	return 0;
 }
 
-static int process_synthesized_event(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_sample *sample __maybe_unused,
-				     struct machine *machine __maybe_unused)
-{
-	struct perf_stat *stat = (void *)tool;
-	return perf_stat__write(stat, event, event->header.size);
-}
-
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
@@ -323,6 +317,35 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
+static int perf_stat_synthesize_config(void)
+{
+	int err;
+
+	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
+						process_synthesized_event,
+						NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
+					     process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(NULL, &stat_config,
+						 process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
@@ -403,6 +426,10 @@ static int __run_perf_stat(int argc, const char **argv)
 						 fd, false);
 		if (err < 0)
 			return err;
+
+		err = perf_stat_synthesize_config();
+		if (err < 0)
+			return err;
 	}
 
 	/*
@@ -1560,7 +1587,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		 * a saner message about no samples being in the perf.data file.
 		 *
 		 * This also serves to suppress a warning about f_header.data.size == 0
-		 * in header.c.  -acme
+		 * in header.c at the moment 'perf stat record' gets introduced, which
+		 * is not really needed once we start adding the stat specific PERF_RECORD_
+		 * records, but the need to suppress the kptr_restrict messages in older
+		 * tools remain  -acme
 		 */
 		int fd = perf_data_file__fd(&perf_stat.file);
 		int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,