Maxime Ripard writes: > [ Unknown signature status ] > On Tue, Mar 05, 2019 at 01:47:38PM -0800, Eric Anholt wrote: >> Maxime Ripard 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 wrote: >> >> > >> >> > Maxime Ripard 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 >> >> > > --- >> >> > > 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? I don't know, personally. Sounds like it's worth investigating.