On 2024-03-26 11:52, Alex Deucher wrote:
This adds allocation latency, but aligns better with user
expectations. The latency should improve with the drm buddy
clearing patches that Arun has been working on.
If we submit this before the clear-page-tracking patches are in, this
will cause unacceptable performance regressions for ROCm applications.
Regards,
Felix
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 0ae9fd844623..f9a4ea082821 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1709,7 +1709,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
alloc_flags = 0;
} else {
- alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
+ alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE |
+ AMDGPU_GEM_CREATE_VRAM_CLEARED;
alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?
AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;
}
