On Thu, Jun 8, 2017 at 4:54 AM, Jiri Olsa <jo...@redhat.com> wrote:
> On Tue, Jun 06, 2017 at 12:07:22AM -0700, David Carrillo-Cisneros wrote:
>
> SNIP
>
>> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
>> index 6c1963e5bf10..c91acd5b0838 100644
>> --- a/tools/perf/util/header.c
>> +++ b/tools/perf/util/header.c
>> @@ -66,6 +66,7 @@ struct feat_fd {
>> void *buf; /* Either buf != NULL or fd >= 0 */
>> ssize_t offset;
>> size_t size;
>> + struct perf_evsel *events;
>> };
>>
>> void perf_header__set_feat(struct perf_header *header, int feat)
>> @@ -1353,10 +1354,15 @@ static int __desc_attr__fprintf(FILE *fp, const char
>> *name, const char *val,
>>
>> static void print_event_desc(struct feat_fd *ff, FILE *fp)
>> {
>> - struct perf_evsel *evsel, *events = read_event_desc(ff);
>> + struct perf_evsel *evsel, *events;
>> u32 j;
>> u64 *id;
>>
>> + if (ff->events)
>> + events = ff->events;
>> + else
>> + events = read_event_desc(ff);
>
> can you read from ff at this point in print callback?
Yes, ->print it's always called after ->process in
perf_event__synthesize_features. So process_event_desc (that in
pipe-mode sets ff->events) is called before this print_event_desc.
>
> jirka
