diff options
| author | Philip Yang <Philip.Yang@amd.com> | 2023-03-08 11:57:00 -0500 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-06-09 10:36:38 -0400 |
| commit | 3ebfd221c1a83e5f0edadb87d173d8fd93d1d125 (patch) | |
| tree | ac81bd8c25170d61d01a2627fe14f72ac38fda28 /drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | |
| parent | 6cfba94a77c5cbad2d7c106ac5f026b6a8b1efe6 (diff) | |
| download | linux-stable-3ebfd221c1a83e5f0edadb87d173d8fd93d1d125.tar.gz linux-stable-3ebfd221c1a83e5f0edadb87d173d8fd93d1d125.tar.bz2 linux-stable-3ebfd221c1a83e5f0edadb87d173d8fd93d1d125.zip | |
drm/amdkfd: Store xcp partition id to amdgpu bo
For memory accounting per compute partition and export drm amdgpu bo and
then import to KFD, we need the xcp id to account the memory usage or
find the KFD node of the original amdgpu bo to create the KFD bo on the
correct adev KFD node.
Set xcp_id_plus1 of amdgpu_bo_param to create bo and store xcp_id to
amddgpu bo. Add helper macro to get the mem_id from adev and xcp_id.
v2: squash in fix ("drm/amdgpu: Fix BO creation failure on GFX 9.4.3 dGPU")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 62fc7e8d326e..cc3b1b596e56 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -502,6 +502,7 @@ exit: int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int level, bool immediate, struct amdgpu_bo_vm **vmbo) { + struct amdgpu_fpriv *fpriv = container_of(vm, struct amdgpu_fpriv, vm); struct amdgpu_bo_param bp; struct amdgpu_bo *bo; struct dma_resv *resv; @@ -534,7 +535,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, bp.type = ttm_bo_type_kernel; bp.no_wait_gpu = immediate; - bp.mem_id_plus1 = vm->mem_id + 1; + bp.xcp_id_plus1 = fpriv->xcp_id == ~0 ? 0 : fpriv->xcp_id + 1; if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; @@ -560,7 +561,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, bp.type = ttm_bo_type_kernel; bp.resv = bo->tbo.base.resv; bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.mem_id_plus1 = vm->mem_id + 1; + bp.xcp_id_plus1 = fpriv->xcp_id == ~0 ? 0 : fpriv->xcp_id + 1; r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); |