mirror of
https://github.com/torvalds/linux.git
synced 2026-05-18 20:03:14 +02:00
5207c393d3
The caching mode for buffer objects with VRAM as a possible placement was forced to write-combined, regardless of placement. However, write-combined system memory is expensive to allocate and even though it is pooled, the pool is expensive to shrink, since it involves global CPU TLB flushes. Moreover write-combined system memory from TTM is only reliably available on x86 and DGFX doesn't have an x86 restriction. So regardless of the cpu caching mode selected for a bo, internally use write-back caching mode for system memory on DGFX. Coherency is maintained, but user-space clients may perceive a difference in cpu access speeds. v2: - Update RB- and Ack tags. - Rephrase wording in xe_drm.h (Matt Roper) v3: - Really rephrase wording. Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> Fixes: |
||
|---|---|---|
| .. | ||
| amdgpu_drm.h | ||
| armada_drm.h | ||
| drm_fourcc.h | ||
| drm_mode.h | ||
| drm_sarea.h | ||
| drm.h | ||
| etnaviv_drm.h | ||
| exynos_drm.h | ||
| habanalabs_accel.h | ||
| i915_drm.h | ||
| ivpu_accel.h | ||
| lima_drm.h | ||
| msm_drm.h | ||
| nouveau_drm.h | ||
| omap_drm.h | ||
| panfrost_drm.h | ||
| panthor_drm.h | ||
| pvr_drm.h | ||
| qaic_accel.h | ||
| qxl_drm.h | ||
| radeon_drm.h | ||
| tegra_drm.h | ||
| v3d_drm.h | ||
| vc4_drm.h | ||
| vgem_drm.h | ||
| virtgpu_drm.h | ||
| vmwgfx_drm.h | ||
| xe_drm.h | ||