perf: Introduce a new "round of buffers read" pseudo event

In order to provide a more rubust and deterministic reordering
algorithm, we need to know when we reach a point where we just
did a pass through over every counter buffers to read every thing
they had.

This patch introduces a new PERF_RECORD_FINISHED_ROUND pseudo event
that only consist in an event header and doesn't need to contain
anything.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>

1 files changed, 24 insertions, 10 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d3981ac50e1..6b77b285fe1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -494,6 +494,29 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
                        " relocation symbol.\n", machine->pid);
 }
 
+static struct perf_event_header finished_round_event = {
+        .size = sizeof(struct perf_event_header),
+        .type = PERF_RECORD_FINISHED_ROUND,
+};
+
+static void mmap_read_all(void)
+{
+        int i, counter, thread;
+
+        for (i = 0; i < nr_cpu; i++) {
+                for (counter = 0; counter < nr_counters; counter++) {
+                        for (thread = 0; thread < thread_num; thread++) {
+                                if (mmap_array[i][counter][thread].base)
+                                        mmap_read(&mmap_array[i][counter][thread]);
+                        }
+
+                }
+        }
+
+        if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
+                write_output(&finished_round_event, sizeof(finished_round_event));
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
         int i, counter;
@@ -726,16 +749,7 @@ static int __cmd_record(int argc, const char **argv)
                 int hits = samples;
                 int thread;
 
-                for (i = 0; i < nr_cpu; i++) {
-                        for (counter = 0; counter < nr_counters; counter++) {
-                                for (thread = 0;
-                                        thread < thread_num; thread++) {
-                                        if (mmap_array[i][counter][thread].base)
-                                                mmap_read(&mmap_array[i][counter][thread]);
-                                }
-
-                        }
-                }
+                mmap_read_all();
 
                 if (hits == samples) {
                         if (done)