randr: Virtual monitor not present with MST display
Alex Deucher
alexdeucher at gmail.com
Tue Mar 5 19:07:42 UTC 2019
On Tue, Mar 5, 2019 at 1:16 PM Paul Menzel
<pmenzel+amd-gfx at molgen.mpg.de> wrote:
>
> Dear Linux folks,
>
>
> 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 at 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
>
> With an Intel system, the monitor object is shown.
>
> $ 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
Alex
More information about the amd-gfx
mailing list