Interlace modes with r600 KMS

Interlace modes with r600 KMS

[Marius Gröger]

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?

Thanks
Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/7 Marius Gröger <marius.groeger@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

Alex

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 07.09.2010 16:52, wrote Alex Deucher:
> 2010/9/7 Marius Gröger<marius.groeger@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)?

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?

Regards
Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/7 Marius Gröger <marius.groeger@googlemail.com>:
> Am 07.09.2010 16:52, wrote Alex Deucher:
>>
>> 2010/9/7 Marius Gröger<marius.groeger@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

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 07.09.2010 17:53, wrote Alex Deucher:
> 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?

I'll try, thanks.

Marius

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 07.09.2010 17:53, schrieb Alex Deucher:
> 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?

No change, at all, unfortunately. The interlace modes, while listed in 
Xorg.conf, are not visible in xrandr. Manually adding an interlaced mode 
with xrandr results in a broken screen display.

Any other thoughts?

Regards
Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/7 Marius Gröger <marius.groeger@googlemail.com>:
> Am 07.09.2010 17:53, schrieb Alex Deucher:
>>
>> 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?
>
> No change, at all, unfortunately. The interlace modes, while listed in
> Xorg.conf, are not visible in xrandr. Manually adding an interlaced mode
> with xrandr results in a broken screen display.
>
> Any other thoughts?
>

Does this patch help?

diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c
b/drivers/gpu/drm/radeon/radeon_encoders.c
index 2c293e8..f821247 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -288,8 +288,8 @@ static bool radeon_atom_mode_fixup(struct
drm_encoder *encoder,
        drm_mode_set_crtcinfo(adjusted_mode, 0);

        /* hw bug */
-       if ((mode->flags & DRM_MODE_FLAG_INTERLACE)
-           && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2)))
+       if ((adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
+           && (adjusted_mode->crtc_vsync_start <
(adjusted_mode->crtc_vdisplay + 2)))
                adjusted_mode->crtc_vsync_start =
adjusted_mode->crtc_vdisplay + 2;

        /* get the native mode for LVDS */


If not, does it work ok with ums (boot with radeon.modeset=0)?  If so,
we'll need to compare the modesetting paths between ums and kms and
see what got broken with kms.

Alex

> Regards
> Marius
>
>

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 07.09.2010 21:00, schrieb Alex Deucher:
> Does this patch help?

No change...

> If not, does it work ok with ums (boot with radeon.modeset=0)?  If so,
> we'll need to compare the modesetting paths between ums and kms and
> see what got broken with kms.

Without KMS the interlaced modes are listed in xrandr right away, and 
they are working!

Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/7 Marius Gröger <marius.groeger@googlemail.com>:
> Am 07.09.2010 21:00, schrieb Alex Deucher:
>>
>> Does this patch help?
>
> No change...
>
>> If not, does it work ok with ums (boot with radeon.modeset=0)?  If so,
>> we'll need to compare the modesetting paths between ums and kms and
>> see what got broken with kms.
>
> Without KMS the interlaced modes are listed in xrandr right away, and they
> are working!
>

What card do you have?  Can you dump the registers with both kms and
ums with an interlaced mode set and send them to me?  Use avivotool
(as root) available here:
http://cgit.freedesktop.org/~airlied/radeontool/

with interlaced mode set in kms:
./avivotool regs all > broken.dump
with interlaced mode set in ums:
./avivotool regs all > working.dump

Thanks,

Alex

> Marius
>

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 08.09.2010 00:00, wrote Alex Deucher:
> What card do you have?  Can you dump the registers with both kms and
> ums with an interlaced mode set and send them to me?  Use avivotool

I have a GA-MA78GM-UD2H mainboard with an onboard RS780 chipset.

I sent the requested dumps in a PM.

While typing this I realize that I don't use a pristine d-r-t. I did 
fiddle with the HDMI underscan settings a bit to make my 1280x720p mode 
fit better. That fiddling went so far that I broke the original ratio a 
little bit. Just to let you know.

Thanks
Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/8 Marius Gröger <marius.groeger@googlemail.com>:
> Am 08.09.2010 00:00, wrote Alex Deucher:
>>
>> What card do you have?  Can you dump the registers with both kms and
>> ums with an interlaced mode set and send them to me?  Use avivotool
>
> I have a GA-MA78GM-UD2H mainboard with an onboard RS780 chipset.
>
> I sent the requested dumps in a PM.
>
> While typing this I realize that I don't use a pristine d-r-t. I did fiddle
> with the HDMI underscan settings a bit to make my 1280x720p mode fit better.
> That fiddling went so far that I broke the original ratio a little bit. Just
> to let you know.

Does disabling underscan fix interlaced?

Alex

>
> Thanks
> Marius
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel
>

Re: Interlace modes with r600 KMS

[Marius Gröger]

Am 09.09.2010 17:03, schrieb Alex Deucher:
> Does disabling underscan fix interlaced?

I just pulled the latest d-r-t and at least I can confirm that the 
problem is present without any of my tinkerings :-) I still need to 
check with underscan disabled. There is no cmdline option for this yet, 
is there? What's the quickest way to disable underscan, replace 
UNDERSCAN_AUTO with UNDERSCAN_OFF?

Regards
Marius

Re: Interlace modes with r600 KMS

[Alex Deucher]

2010/9/9 Marius Gröger <marius.groeger@googlemail.com>:
> Am 09.09.2010 17:03, schrieb Alex Deucher:
>>
>> Does disabling underscan fix interlaced?
>
> I just pulled the latest d-r-t and at least I can confirm that the problem
> is present without any of my tinkerings :-) I still need to check with
> underscan disabled. There is no cmdline option for this yet, is there?
> What's the quickest way to disable underscan, replace UNDERSCAN_AUTO with
> UNDERSCAN_OFF?

ether change the default like that or just use xrandr:

xrandr --output <output> --set underscan off

Alex

>
> Regards
> Marius
>
>

Re: Interlace modes with r600 KMS

[Marius Gröger]

On Thu, 9 Sep 2010 11:03:54 -0400
wrote Alex Deucher <alexdeucher@gmail.com>:

> Does disabling underscan fix interlaced?

Yes, without underscan I can switch to my manually defined interlace
mode and it looks ok.

However, the EDID reported interlace modes are still pruned by the
Xserver, so there still seems to be a subtle difference between KMS and
UMS.

Thanks
Marius