wlroots
wlroots copied to clipboard
swaywm
Improve multi-GPU buffer sharing
On multi-GPU setups we render everything on one primary GPU and then we copy buffers around to display them on secondary GPUs. This is done by exporting a DMA-BUF on the primary GPU, importing it on the secondary GPU, and rendering it on the secondary GPU:
https://github.com/swaywm/wlroots/blob/11dc1f65d216acf31e81addb9817091e8d9ba9a6/backend/drm/renderer.c#L216
Instead we should use direct scan-out to skip rendering on the secondary GPU. This could be the groundwork for https://github.com/swaywm/wlroots/issues/1270.
wlroots has migrated to gitlab.freedesktop.org. This issue has been moved to:
https://gitlab.freedesktop.org/wlroots/wlroots/-/issues/1347
From issues we had with #1531 this doesn't seem possible on some drivers (radeon) because they can't scan-out from DMA-BUFs (which don't live in VRAM, but in system memory) directly. It would make more sense to copy the bo from system memory to VRAM, instead of using GL, but GBM doesn't have a way to copy buffers.
Weston has a bunch of checks to figure out if a buffer is suitable for scan-out.
Maybe we could try to scan-out and fallback to a copy if it doesn't work, too.
Use-cases:
- Display-only devices like DisplayLink don't have memory
- Nouveau doesn't support OpenGL for some NVIDIA hw (so falls back to llvmpipe)
We could try these strategies:
- Directly import and scan-out the DMA-BUF
- Import the buffer and perform a copy via OpenGL
- Do a manual copy via system memory
The copy could be improved with:
- Damage tracking support
- Detect whether the DRM device is render-capable, don't try to use OpenGL in this case (do a CPU copy instead)
