Dear Alex,


On 03/05/19 20:07, Alex Deucher wrote:
> On Tue, Mar 5, 2019 at 1:16 PM Paul Menzel wrote:

>> Using the MST display Dell UP3214Q (two panels) with an AMD system,
>> the virtual monitor object is not created. GDM and Xfce consider both
>> panels as separate screens (`xrandr --listmonitors`).
>>
>> [    0.000000] Linux version 4.20.13.mx64.248 (root@holidayincambodia.molgen.mpg.de) (gcc version 7.3.0 (GCC)) #1 SMP Wed Feb 27 14:10:55 CET 2019
>>
>> [   79.494297] [drm] DM_MST: stopping TM on aconnector: 00000000a8109331 [id: 56]
>> [   79.494362] [drm] DM_MST: Disabling connector: 00000000776ea22b [id: 63] [master: 00000000a8109331]
>> [   79.494406] [drm] DM_MST: Disabling connector: 00000000057ebdbb [id: 67] [master: 00000000a8109331]
>> [   79.781882] snd_hda_intel 0000:00:1f.3: spurious response 0x0:0x2, last cmd=0x201f0500
>> [   86.028806] [drm] DM_MST: starting TM on aconnector: 00000000a8109331 [id: 56]
>> [   86.053072] [drm] DM_MST: added connector: 000000001c9b49ed [id: 71] [master: 00000000a8109331]
>> [   86.108540] [drm] SADs count is: -2, don't need to read it
>> [   86.386661] [drm:create_stream_for_sink [amdgpu]] *ERROR* Failed to create stream for sink!
>> [   87.237878] [drm] DM_MST: added connector: 00000000c3ffcbbb [id: 80] [master: 00000000a8109331]
>> [   87.293028] [drm] SADs count is: -2, don't need to read it
>> [  206.993344] [drm] DM_MST: stopping TM on aconnector: 00000000a8109331 [id: 56]
>> [  206.993423] [drm] DM_MST: Disabling connector: 000000001c9b49ed [id: 71] [master: 00000000a8109331]
>> [  206.993456] [drm] DM_MST: Disabling connector: 00000000c3ffcbbb [id: 80] [master: 00000000a8109331]
>> [  207.548051] [drm:create_stream_for_sink [amdgpu]] *ERROR* Failed to create stream for sink!
>> [  207.603193] [drm:create_stream_for_sink [amdgpu]] *ERROR* Failed to create stream for sink!
>> [  207.762388] traps: xfdesktop[2225] general protection fault ip:7f588981226c sp:7ffee65af370 error:0 in libgobject-2.0.so.0.5800.1[7f58897da000+56000]
>> [  210.320612] [drm] DM_MST: starting TM on aconnector: 00000000b456cd59 [id: 62]
>> [  210.343497] [drm] DM_MST: added connector: 00000000735839d5 [id: 73] [master: 00000000b456cd59]
>> [  210.399168] [drm] SADs count is: -2, don't need to read it
>> [  210.404454] [drm] DM_MST: added connector: 00000000cccb0c2d [id: 88] [master: 00000000b456cd59]
>> [  210.675589] [drm] SADs count is: -2, don't need to read it

I didn’t provide the output of xrandr in my previous message.

    $ xrandr --listmonitors
     Monitors: 2
     0: +DisplayPort-9 1920/698x2160/392+0+0  DisplayPort-9
     1: +DisplayPort-10 1920/698x2160/392+1920+0  DisplayPort-10

Please find the X.Org X Server log attached.

>> With an Intel system, the monitor object is shown.

To clarify, the modesetting driver is used with the Intel hardware.

>>     $ xrandr --listmonitors
>>     Monitors: 1
>>      0: +Auto-Monitor-1 3840/698x2160/392+0+0  DP-1-9 DP-1-8
>>
>> Do you have an idea, what the AMD drivers does differently, and how
>> to fix this?
> 
> + dri-devel
> 
> My understanding is that this is handled at the Desktop level rather
> than the driver.  X exposes the tile info via randr 1.5 and the
> desktop environment should handle it as a single monitor.  Mutter
> handles this in GNOME for example.
> 
> https://cgit.freedesktop.org/xorg/xserver/commit/?id=7e1f86d42b54fb7f6492875e47a718eaeca3069b
> https://lists.x.org/archives/xorg-announce/2015-May/002605.html
> https://mail.gnome.org/archives/desktop-devel-list/2015-November/msg00018.html

As it works with the modesetting driver, it looks to me like Xfce
supports it, and it’s a driver issue. The Linux error messages
also do not look promising. Any idea, if they are related?
Lastly, shouldn’t at least the output of `xrandr` be correct, if
everything is set up correctly?


Kind regards,

Paul