[PATCH 2/2] drm/radeon/kms: enable underscan option for digital connectors

Alex Deucher alexdeucher at gmail.com
Mon Aug 9 00:33:48 PDT 2010


2010/8/9 Marius Gröger <marius.groeger at googlemail.com>:
> Am 08.08.2010 20:09, wrote Alex Deucher:
>>
>> 2010/8/8 Marius Gröger<marius.groeger at googlemail.com>:
>>>
>>> Am 08.08.2010 18:22, wrote Alex Deucher:
>>>>>
>>>>> Also, I kind of was hoping that once I could use 1280x720 for both the
>>>>> console and the X screen, it would would allow me to switch between the
>>>>> two
>>>>> transparently. Instead, the TV takes notice of the switch and needs
>>>>> some
>>>>> extra syncing time. Is this expected behaviour?
>>>>
>>>> You mean switching underscan off and on or a VT switch?  The hw has to
>>>> reprogram the mode when it changes the underscan.  As for a VT switch,
>>>> it should just be changing the crtc base, but IIRC there was a bug
>>>> where X and the console used slightly different modes in some cases.
>>>
>>> VT switch. I use video=1280x720 at 50 on the command line and select the
>>> corresponding EDID resolution within X. Is this bug still pending or is
>>> my
>>> scenario supposed to work?
>>
>> You may be seeing this issue:
>> http://lists.x.org/archives/xorg-devel/2010-August/011743.html
>
> "In the absence of the user specifying an overriding monitor
> configuration, trust the KMS drivers to have correctly probed the output
> modes."
>
> Well, in my case I *am* specifying an overriding monitor configuration. Is
> there still a chance that video=1280x720 at 50 could be meaning s.th. different
> then the corresponding mode in X that I explicitly choose.

Can you verify that the console and X are using the same modeline?
The mode selected by video=1280x720 at 50 likely has different timing
than the timing used by the mode in X.  Is the VT switch smooth when
you don't specify the mode on the console or X (i.e., let the driver
decide on it's own)?

Alex


More information about the dri-devel mailing list