[PATCH 2/7] drm/edid: Allow to ignore the audio EDID data

[Daniel Vetter]

On Tue, Mar 05, 2019 at 10:11:51AM -0800, Eric Anholt wrote:
> Maxime Ripard <maxime.ripard at bootlin.com> writes:
> 
> > [ Unknown signature status ]
> > On Mon, Mar 04, 2019 at 03:05:31PM -0500, Alex Deucher wrote:
> >> On Mon, Mar 4, 2019 at 2:53 PM Eric Anholt <eric at anholt.net> wrote:
> >> >
> >> > Maxime Ripard <maxime.ripard at bootlin.com> writes:
> >> >
> >> > > In some cases, in order to accomodate with displays with poor EDIDs, we
> >> > > need to ignore that the monitor alledgedly supports audio output and
> >> > > disable the audio output.
> >> > >
> >> > > Signed-off-by: Maxime Ripard <maxime.ripard at bootlin.com>
> >> > > ---
> >> > >  drivers/gpu/drm/drm_edid.c | 8 ++++++++
> >> > >  1 file changed, 8 insertions(+)
> >> > >
> >> > > diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
> >> > > index 990b1909f9d7..c0258b011bb2 100644
> >> > > --- a/drivers/gpu/drm/drm_edid.c
> >> > > +++ b/drivers/gpu/drm/drm_edid.c
> >> > > @@ -4190,6 +4190,11 @@ bool drm_detect_hdmi_monitor(struct edid *edid)
> >> > >  }
> >> > >  EXPORT_SYMBOL(drm_detect_hdmi_monitor);
> >> > >
> >> > > +static bool ignore_edid_audio = false;
> >> > > +module_param(ignore_edid_audio, bool, 0644);
> >> > > +MODULE_PARM_DESC(ignore_edid_audio,
> >> > > +              "Ignore the EDID and always consider that a monitor doesn't have audio capabilities");
> >> > > +
> >> > >  /**
> >> > >   * drm_detect_monitor_audio - check monitor audio capability
> >> > >   * @edid: EDID block to scan
> >> > > @@ -4209,6 +4214,9 @@ bool drm_detect_monitor_audio(struct edid *edid)
> >> > >       bool has_audio = false;
> >> > >       int start_offset, end_offset;
> >> > >
> >> > > +     if (ignore_edid_audio)
> >> > > +             goto end;
> >> > > +
> >> > >       edid_ext = drm_find_cea_extension(edid);
> >> > >       if (!edid_ext)
> >> > >               goto end;
> >> >
> >> > It looks like the motivation for the original flag on Raspberry Pi was
> >> > "I've got a non-audio monitor, but the system comes up trying to play
> >> > audio to HDMI instead of the analog jack".  Do we have some way for DRM
> >> > to communicate to ALSA that this is not the right place to try to play
> >> > audio by default?
> >> 
> >> Apparently not.  We have users using debug knobs in our drivers to
> >> disable display audio because ALSA defaults to that rather than other
> >> audio.
> >
> > I guess one way to do this would be to register the card only when an
> > audio-capable monitor is connected instead of doing this at probe
> > time. I'm not sure how convenient it is for userspace though.
> 
> Yeah, I have no idea how this is supposed to work, but pulseaudio keeps
> doing reasonable things on my intel desktop so I'm wondering if we're
> just missing some bit of the HDMI driver communicating to ALSA about the
> state of the audio sink.

We transport (either through the i915/snd-hda component or hw backdoors)
both the "can this sink do audio" and the current eld describing the sinks
audio capability to the alsa side. Afaiui the "can this sink do audio"
even reflects whether the crtc is running or not (so the audio doesn't
disappear into silence if you've dpms off'ed the screen). I think it's
reflected into some alsa output sense/hotplug flag, that pulseaudio should
take into account by default.
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch