Steps to Reproduce: Open sketchfab.com, while loading chromium shows something, but then everything gets black. It is happening on 18.50-725072 amdgpu-pro drivers, while on 18.40-697810 chromium doesn't show blackscreen. I use Lubuntu 18.04. Some outputs (there is one comment after dmesg): $uname -a Linux user 4.15.0-46-generic #49-Ubuntu SMP Wed Feb 6 09:33:07 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux $ dmesg | grep amdgpu [ 6.246244] [drm] amdgpu kernel modesetting enabled. [ 6.246246] [drm] amdgpu version: 18.50.1.418 [ 6.257297] fb: switching to amdgpudrmfb from VESA VGA [ 6.257997] amdgpu 0000:01:00.0: Invalid PCI ROM header signature: expecting 0xaa55, got 0xffff [ 6.263289] amdgpu 0000:01:00.0: VRAM: 2048M 0x000000F400000000 - 0x000000F47FFFFFFF (2048M used) [ 6.263292] amdgpu 0000:01:00.0: GART: 256M 0x000000FF00000000 - 0x000000FF0FFFFFFF [ 6.267778] [drm] amdgpu: 2048M of VRAM memory ready [ 6.267780] [drm] amdgpu: 13014M of GTT memory ready. [ 6.633726] fbcon: amdgpudrmfb (fb0) is primary device [ 6.694025] amdgpu 0000:01:00.0: fb0: amdgpudrmfb frame buffer device [ 6.711472] [drm] Initialized amdgpu 3.27.0 20150101 for 0000:01:00.0 on minor 0 [ 203.253903] amdgpu 0000:01:00.0: GPU fault detected: 146 0x0378770c for process chromium-browse pid 2365 thread chromium-browse pid 2365 [ 203.253910] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0011306F [ 203.253912] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0807700C [ 203.253915] amdgpu 0000:01:00.0: VM fault (0x0c, vmid 4, pasid 32771) at page 1126511, read from 'SDM0' (0x53444d30) (119) [ 579.809297] amdgpu 0000:01:00.0: GPU fault detected: 146 0x0378770c for process chromium-browse pid 2365 thread chromium-browse pid 2365 [ 579.809305] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0011306F [ 579.809307] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x0E07700C [ 579.809310] amdgpu 0000:01:00.0: VM fault (0x0c, vmid 7, pasid 32771) at page 1126511, read from 'SDM0' (0x53444d30) (119) (The comment:) The error messages after point [ 203.253903] are typical for 18.40-697810 too, but chromium seems work not so bad. Render artifacts doesn't count. (End of comment) chrome://version tab: Chromium 72.0.3626.119 (Official Build) Built on Ubuntu , running on Ubuntu 18.04 (64-bit) Revision 9a65993e2cde1b5797ec98da4cd9abcea464cd7b-refs/branch-heads/3626@{#876} OS Linux JavaScript V8 7.2.502.26 Flash 32.0.0.142 /usr/lib/adobe-flashplugin/libpepflashplayer.so User Agent Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/72.0.3626.119 Chrome/72.0.3626.119 Safari/537.36 Command Line /usr/lib/chromium-browser/chromium-browser --ppapi-flash-path=/usr/lib/adobe-flashplugin/libpepflashplayer.so --ppapi-flash-version=32.0.0.142 --enable-pinch --enable-native-gpu-memory-buffers --enable-features=CheckerImaging --flag-switches-begin --autoplay-policy=no-user-gesture-required --enable-gpu-rasterization --enable-offline-auto-reload-visible-only --disable-offline-auto-reload --enable-tcp-fastopen --enable-zero-copy --ignore-gpu-blacklist --num-raster-threads=3 --enable-features=CheckerImaging,DrawOcclusion,ExpensiveBackgroundTimerThrottling,OptimizationHints,ParallelDownloading,UseSurfaceLayerForVideo --disable-features=AutofillExpandedPopupViews,MemoryCoordinator,WebPayments,fill-on-account-select --flag-switches-end Executable Path /usr/lib/chromium-browser/chromium-browser If it's not the right place for this bug please tell me where can I report it, if you know.
When the GPU rasterization option in Chromium is turned off the blackscreen doesn't appear.
Please attach the output of glxinfo each with 18.50-725072 and 18.40-697810.
Created attachment 143567 [details] glxinfo.18.50-725072
Created attachment 143568 [details] glxinfo-18.40-697810
Seems that "GPU fault detected: 146" is not so typical for 18.40-697810 as I thought. I still can't get that error messages on it. Seems it happen much rare than on 18.50-725072.
Created attachment 143570 [details] glxinfo-default-ubuntu-bionic Just made it before 18.40-697810 installation. (I uninstalled 18.50, rebooted with default Ubuntu drivers, made this glxinfo, installed 18.40).
Are you sure you want to use the amdgpu-pro OpenGL driver? At this point it's only intended for specialized use-cases such as Workstation applications, the Mesa radeonsi driver generally works better.
I need it for Blender Cycles OpenCL render.
(In reply to Dima from comment #8) > I need it for Blender Cycles OpenCL render. You can install only the amdgpu-pro OpenCL ICD, shouldn't need the OpenGL driver for that.
When I install OpenCL icd package with dependencies Blender doesn't recognize OpenCL. I've tried "./amdgpu-pro-install --opencl=legacy --headless" and Blender segfaults. If the Cycles GPU compute is enabled by default Blender doesn't even show its GUI. When I try to run Blender 2.8 with Eevee enabled by default it starts and works until I choose Cycles GPU render.
I've got the "--headless" installation working in Blender by installing of addition packages from amdgpu-pro 18.50 archive. The packages are libdrm-amdgpu-common, libdrm2-amdgpu, libdrm-amdgpu-amdgpu1. I used this tutorial to know what files are needed https://blog.cryptomilk.org/2018/03/02/using-amd-open-source-and-the-amdgpu-pro-opencl-driver-for-image-processing/. Now I have OpenCL in Blender and amdgpu open drivers working together. No any render artifacts and blackscreens. Thank you for the idea.
-- GitLab Migration Automatic Message -- This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity. You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/drm/amd/issues/21.
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.