On Tue, Mar 05, 2019 at 01:47:38PM -0800, Eric Anholt wrote:
> Maxime Ripard <maxime.ripard@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@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.
> 
> Oh, right, the HDMI encoder passes the ELD to ALSA, and userspace gets
> to use that.  So, open source is already doing the right thing, and the
> problem was that the old driver talking to the firmware wouldn't, thus
> the need for a flag.

I started to look into this, and while on my laptop, the ELD seems to
be exposed as part of /proc/asound/card0/eld*, there's no such file on
the RPi with a 5.0 kernel (and an HDMI monitor with audio support,
obviously). Is it something that used to work at some point?

Maxime

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