I rushed merging this a bit too much, and Noralf pointed out that we're a lot better already and have made great progress. Let's try again. v2: Fix typo spotted by Eric Engestrom.
Unified · Split
| @@ -228,9 +228,11 @@ struct drm_gem_object_funcs · 227 unmodified lines | ||
| 228 | 228 | GEM objects can now have a function table instead of having the callbacks on the |
| 229 | 229 | DRM driver struct. This is now the preferred way and drivers can be moved over. |
| 230 | 230 | |
| 231 | −Unfortunately some of the recently added GEM helpers are going in the wrong | |
| 232 | −direction by adding OPS macros that use the old, deprecated hooks. See | |
| 233 | −DRM_GEM_CMA_VMAP_DRIVER_OPS, DRM_GEM_SHMEM_DRIVER_OPS, and DRM_GEM_VRAM_DRIVER_PRIME. | |
| 231 | +DRM_GEM_CMA_VMAP_DRIVER_OPS, DRM_GEM_SHMEM_DRIVER_OPS already support this, but | |
| 232 | +DRM_GEM_VRAM_DRIVER_PRIME does not yet and needs to be aligned with the previous | |
| 233 | +two. We also need a 2nd version of the CMA define that doesn't require the | |
| 234 | +vmapping to be present (different hook for prime importing). Plus this needs to | |
| 235 | +be rolled out to all drivers using their own implementations, too. | |
| 234 | 236 | |
| 235 | 237 | Use DRM_MODESET_LOCK_ALL_* helpers instead of boilerplate |
| 236 | 238 | --------------------------------------------------------- |