[PATCH] perf cs-etm: Delay decode of non-timeless data until cs_etm__flush_events()

[Mathieu Poirier]

On Thu, 1 Jul 2021 at 11:15, Arnaldo Carvalho de Melo <acme at kernel.org> wrote:
>
> Em Mon, Jun 14, 2021 at 09:54:42AM -0600, Mathieu Poirier escreveu:
> > On Wed, Jun 09, 2021 at 04:04:20PM +0300, James Clark wrote:
> > > Currently, timeless mode starts the decode on PERF_RECORD_EXIT, and
> > > non-timeless mode starts decoding on the fist PERF_RECORD_AUX record.
> > >
> > > This can cause the "data has no samples!" error if the first
> > > PERF_RECORD_AUX record comes before the first (or any relevant)
> > > PERF_RECORD_MMAP2 record because the mmaps are required by the decoder
> > > to access the binary data.
> > >
> > > This change pushes the start of non-timeless decoding to the very end of
> > > parsing the file. The PERF_RECORD_EXIT event can't be used because it
> > > might not exist in system-wide or snapshot modes.
>
> <SNIP>
>
> > This looks good to me but I'd like to have other people testing it.
>
> So Leo reviewed and tested this, I'm taking your "looks good to me" as
> an Acked-by, as per Documentation/process/submitting-patches.rst.
>

Yes, please.  My goal here was to wait for other people to test this
code, which Leo did.

> - Arnaldo
>
> > Thanks,
> > Mathieu