OSDN Git Service

perf evsel: Fix ftrace:function event recording
authorJiri Olsa <jolsa@kernel.org>
Thu, 13 Nov 2014 17:21:03 +0000 (18:21 +0100)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Wed, 19 Nov 2014 15:33:48 +0000 (12:33 -0300)
Following patch fails (-EINVAL) ftrace:function with enabled user
space callchains:
  cfa77bc4af2c perf: Disallow user-space callchains for function trace events

We need to follow in perf tool itself and explicitly set the
perf_event_attr::exclude_callchain_user flag for ftrace:function
event.

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1415899263-24820-1-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/util/evsel.c

index 34344ff..f2dc91f 100644 (file)
@@ -658,6 +658,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                attr->mmap_data = track;
        }
 
+       /*
+        * We don't allow user space callchains for  function trace
+        * event, due to issues with page faults while tracing page
+        * fault handler and its overall trickiness nature.
+        */
+       if (perf_evsel__is_function_event(evsel))
+               evsel->attr.exclude_callchain_user = 1;
+
        if (callchain_param.enabled && !evsel->no_aux_samples)
                perf_evsel__config_callgraph(evsel);