perf record: Allocate area for sample_id_hdr in a synthesized comm event
authorNamhyung Kim <namhyung@kernel.org>
Wed, 30 Sep 2015 01:45:24 +0000 (10:45 +0900)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Thu, 1 Oct 2015 12:54:33 +0000 (09:54 -0300)
A previous patch added a synthesized comm event for forked child process
but it missed that the event should contain area for sample_id_hdr at
the end.  It worked by accident since the perf_event union contains
bigger event structs like mmap_events.

This patch fixes it by dynamically allocating event struct including
those area like in perf_event__synthesize_thread_map().

Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1443577526-3240-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/builtin-record.c

index a01c8ae1ee074437484f1d19b3e77507d217324c..5e01c070dbf2592236ed8e3b4b3a22336d31e47a 100644 (file)
@@ -637,17 +637,25 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         * Let the child rip
         */
        if (forks) {
-               union perf_event event;
+               union perf_event *event;
+
+               event = malloc(sizeof(event->comm) + machine->id_hdr_size);
+               if (event == NULL) {
+                       err = -ENOMEM;
+                       goto out_child;
+               }
+
                /*
                 * Some H/W events are generated before COMM event
                 * which is emitted during exec(), so perf script
                 * cannot see a correct process name for those events.
                 * Synthesize COMM event to prevent it.
                 */
-               perf_event__synthesize_comm(tool, &event,
+               perf_event__synthesize_comm(tool, event,
                                            rec->evlist->workload.pid,
                                            process_synthesized_event,
                                            machine);
+               free(event);
 
                perf_evlist__start_workload(rec->evlist);
        }