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

[Ville Syrjälä]

On Tue, Mar 05, 2019 at 02:21:04PM -0500, Alex Deucher wrote:
> On Tue, Mar 5, 2019 at 2:15 PM Ville Syrjälä
> <ville.syrjala at linux.intel.com> wrote:
> >
> > On Tue, Mar 05, 2019 at 05:24:13PM +0200, Ville Syrjälä wrote:
> > > On Tue, Mar 05, 2019 at 10:12:40AM +0100, Maxime Ripard wrote:
> > > > 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.
> > >
> > > We already provide the ELD to alsa. I'm pretty sure pulseaudio uses
> > > that stuff somehow to figure out whether to play audio over HDMI.
> > > But since I don't use pulseaudio myself I can't be 100% sure.
> > >
> > > Cc:ing Takashi/alsa folks for confirmation.
> >
> > I forgot that the .pin_eld_notify() stuff is i915 specific. But
> > I see some kind of hdmi_codec_ops thing used by some other drivers.
> > I guess that is supposed to achieve the same thing more or less?
> > I'm not immediately seeing any kind of drm->alsa notification
> > hook in there though.
> 
> On AMD hw, the GPU has backdoor access to some of the audio state, so
> when stuff happens on the GPU side, it's reflected on the audio side
> automatically.

Right. i915 has a similar thing (my theory is that it's basically
an industry wide hardware workaround for inflexible Windows driver
architecture). But that was problematic for some power management
related reasons (IIRC) so we added a software mechanism for it.
Though I believe we still write the ELD into the hardware buffer
as well.

-- 
Ville Syrjälä
Intel