perf stat record: Write stat events on record

Writing stat events on 'perf stat record' at the time we read counter
values from kernel.

Committer note:

After the patch:

  $ perf stat record usleep 1

   Performance counter stats for 'usleep 1':

          0.598006      task-clock (msec)         #    0.484 CPUs utilized
                 1      context-switches          #    0.002 M/sec
                 0      cpu-migrations            #    0.000 K/sec
                52      page-faults               #    0.087 M/sec
           882,744      cycles                    #    1.476 GHz
           581,416      stalled-cycles-frontend   #   65.86% frontend cycles idle
   <not supported>      stalled-cycles-backend
           636,479      instructions              #    0.72  insns per cycle
                                                  #    0.91  stalled cycles per insn
           129,334      branches                  #  216.275 M/sec
             7,512      branch-misses             #    5.81% of all branches

       0.001235157 seconds time elapsed

  $ oldperf evlist
  task-clock
  context-switches
  cpu-migrations
  page-faults
  cycles
  stalled-cycles-frontend
  stalled-cycles-backend
  instructions
  branches
  branch-misses
  $ oldperf report --stdio
  Error:
  The perf.data file has no samples!
  # To display the perf.data header info, please use --header/--header-only options.
  #
  $ perf report -D | grep PERF_RECORD
  0x5b0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 5504
  0x5d8 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
  0x5ea [0x40]: PERF_RECORD_STAT_CONFIG
  0x62a [0x30]: PERF_RECORD_STAT
  0x65a [0x30]: PERF_RECORD_STAT
  0x68a [0x30]: PERF_RECORD_STAT
  0x6ba [0x30]: PERF_RECORD_STAT
  0x6ea [0x30]: PERF_RECORD_STAT
  0x71a [0x30]: PERF_RECORD_STAT
  0x74a [0x30]: PERF_RECORD_STAT
  0x77a [0x30]: PERF_RECORD_STAT
  0x7aa [0x30]: PERF_RECORD_STAT
  -1 -1 0x7da [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
  $

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
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/1446734469-11352-8-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -231,6 +231,18 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+static int
+perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
+			     struct perf_counts_values *count)
+{
+	struct perf_sample_id *sid = SID(counter, cpu, thread);
+
+	return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
+					   process_synthesized_event, NULL);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
@@ -254,6 +266,13 @@ static int read_counter(struct perf_evsel *counter)
 			count = perf_counts(counter->counts, cpu, thread);
 			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
+
+			if (STAT_RECORD) {
+				if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+					pr_err("failed to write stat event\n");
+					return -1;
+				}
+			}
 		}
 	}