Thanks for following up on that. I'd use a more generic name, maybe AMDGPU_GEM_CREATE_NO_FALLBACK. And I think you should exclude this flag in amdgpu_gem_create_ioctl so that allocations through the GEM API can't use this option.
Regards, Felix On 2018-04-02 03:00 AM, Chunming Zhou wrote: > KFD wraps amdgpu_bo_create, they have no fallback case which is different > with amdgpu_gem_object_create. > since upstream branch has no amdgpu_amdkfd_gpuvm.c, which need KFD > guys add this flag to __alloc_memory_of_gpu: > + flags |= AMDGPU_GEM_CREATE_KFD; > > Change-Id: Id3ac1a0bdd48633328d0b22c4c057fab4e94d0b3 > Signed-off-by: Chunming Zhou <[email protected]> > Cc: [email protected] > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 3 ++- > include/uapi/drm/amdgpu_drm.h | 2 ++ > 2 files changed, 4 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c > index f04bfab1eebd..72dabb9886be 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c > @@ -420,7 +420,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device > *adev, unsigned long size, > r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, type, > &bo->placement, page_align, &ctx, acc_size, > NULL, resv, &amdgpu_ttm_bo_destroy); > - if (unlikely(r && r != -ERESTARTSYS) && type == ttm_bo_type_device) { > + if (unlikely(r && r != -ERESTARTSYS) && type == ttm_bo_type_device && > + !(flags & AMDGPU_GEM_CREATE_KFD)) { > if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { > flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; > goto retry; > diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h > index 0087799962cf..0be994be269f 100644 > --- a/include/uapi/drm/amdgpu_drm.h > +++ b/include/uapi/drm/amdgpu_drm.h > @@ -98,6 +98,8 @@ extern "C" { > #define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID (1 << 6) > /* Flag that BO sharing will be explicitly synchronized */ > #define AMDGPU_GEM_CREATE_EXPLICIT_SYNC (1 << 7) > +/* Flag that BO is created from KFD side */ > +#define AMDGPU_GEM_CREATE_KFD (1 << 8) > > struct drm_amdgpu_gem_create_in { > /** the requested memory size */ _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
