Interlace modes with r600 KMS

[Alex Deucher]

2010/9/7 Marius Gröger <marius.groeger at googlemail.com>:
> Am 07.09.2010 16:52, wrote Alex Deucher:
>>
>> 2010/9/7 Marius Gröger<marius.groeger at googlemail.com>:
>>>
>>> Hi All,
>>>
>>> I'm not able to use interlace modes (r600 KMS from d-r-t, HDMI output,
>>> Xorg
>>> stack on xorg-edgers, Ubuntu lucid). All interlace modes which are
>>> defined
>>> in EDID seem to be pruned and don't appear in xrandr. Manually adding a
>>> mode
>>> using xrandr does work, and the TV set detects the mode, but the image
>>> shows
>>> horizontal lines. No crash though.
>>>
>>> Interlace modes did use to work fine in the past, but I don't know when
>>> they
>>> ceased to function.
>>>
>>> What is the status of interlace modes on this kind of setup? What more
>>> tests
>>> or logs would be helpful to analyze the problem? What are other people's
>>> experiences with this?
>>
>> This isn't a driver bug as far as I can tell.  At some point the
>> Xserver started purging interlaced modes.  See this bug:
>> https://bugs.freedesktop.org/show_bug.cgi?id=29591
>
> Thanks for the pointer. I did look into the xserver sources a bit and while
> I'm far from understanding exactly what's going on, it seems like the server
> is relying on output->interlaceAllowed and output->doubleScanAllowed. Aren't
> these bools in the domain of the display driver (granted, this wouldn't be
> the radeon module but the xf86-video-ati driver)?
>

I guess so.  Interlace used to work without those parameters set; I
guess the xserver behavior changed in the meantime.  I've gone ahead
and set them in the driver.

> Also, as I wrote, the purging seems to be half-done, since I am able to
> manually add an interlaced mode. But since that mode doesn't work properly -
> does the radeon module support interlaced modes? Is there a non-X way to
> verify this?

It did in the past, however, at the moment, I don't have a interlaced
capable monitor to test.  Can you try again with xf86-video-ati from
git master?

Alex