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@anholt.net> wrote:
> >
> > Maxime Ripard <maxime.ripard@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@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.

Maxime

-- 
Maxime Ripard, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com