perf trace: Hide sys_exit messages about syscall id = -1

That was reproduced via ftrace as described in this cset comment log,
need to investigate further.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-n1i3m0vo6mgq3ddjj95sls2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 16 insertions, 1 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c907e7e41a74..c3caabbe18fa 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -298,7 +298,22 @@ static struct syscall *trace__syscall_info(struct trace *trace,
         int id = perf_evsel__intval(evsel, sample, "id");
 
         if (id < 0) {
-                fprintf(trace->output, "Invalid syscall %d id, skipping...\n", id);
+
+                /*
+                 * XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
+                 * before that, leaving at a higher verbosity level till that is
+                 * explained. Reproduced with plain ftrace with:
+                 *
+                 * echo 1 > /t/events/raw_syscalls/sys_exit/enable
+                 * grep "NR -1 " /t/trace_pipe
+                 *
+                 * After generating some load on the machine.
+                 */
+                if (verbose > 1) {
+                        static u64 n;
+                        fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
+                                id, perf_evsel__name(evsel), ++n);
+                }
                 return NULL;
         }