Re: [PATCH] drm/amdkfd: fix ttm size refactor fallout

[Felix Kuehling <felix.kuehling@amd.com>]

Am 2020-12-14 um 3:27 p.m. schrieb Christian König:
> Am 14.12.20 um 20:17 schrieb Daniel Vetter:
>> I guess Christian didn't compile test amdkfd.
>
> Scratching my head what has happened here. When I tested everything
> was at least building fine.

Looks like you were missing CONFIG_HSA_AMD in your .config for some reason.

Regards,
  Felix


>
>>
>> Fixes: e11bfb99d6ec ("drm/ttm: cleanup BO size handling v3")
>> Cc: Christian König <christian.koenig@amd.com>
>> Cc: Huang Rui <ray.huang@amd.com> (v1)
>> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
>> Cc: Felix Kuehling <Felix.Kuehling@amd.com>
>> Cc: amd-gfx@lists.freedesktop.org
>> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
>
> Reviewed-by: Christian König <christian.koenig@amd.com>
>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 8 ++++----
>>   1 file changed, 4 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
>> index 7791d074bd32..a9647e7f98a8 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
>> @@ -453,7 +453,7 @@ static int add_bo_to_vm(struct amdgpu_device
>> *adev, struct kgd_mem *mem,
>>       struct amdgpu_bo *bo = mem->bo;
>>       uint64_t va = mem->va;
>>       struct list_head *list_bo_va = &mem->bo_va_list;
>> -    unsigned long bo_size = bo->tbo.mem.size;
>> +    unsigned long bo_size = bo->tbo.base.size;
>>         if (!va) {
>>           pr_err("Invalid VA when adding BO to VM\n");
>> @@ -1281,7 +1281,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
>>           struct kgd_dev *kgd, struct kgd_mem *mem, uint64_t *size)
>>   {
>>       struct amdkfd_process_info *process_info = mem->process_info;
>> -    unsigned long bo_size = mem->bo->tbo.mem.size;
>> +    unsigned long bo_size = mem->bo->tbo.base.size;
>>       struct kfd_bo_va_list *entry, *tmp;
>>       struct bo_vm_reservation_context ctx;
>>       struct ttm_validate_buffer *bo_list_entry;
>> @@ -1402,7 +1402,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
>>       mutex_lock(&mem->lock);
>>         domain = mem->domain;
>> -    bo_size = bo->tbo.mem.size;
>> +    bo_size = bo->tbo.base.size;
>>         pr_debug("Map VA 0x%llx - 0x%llx to vm %p domain %s\n",
>>               mem->va,
>> @@ -1506,7 +1506,7 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
>>       struct amdgpu_device *adev = get_amdgpu_device(kgd);
>>       struct amdkfd_process_info *process_info =
>>           ((struct amdgpu_vm *)vm)->process_info;
>> -    unsigned long bo_size = mem->bo->tbo.mem.size;
>> +    unsigned long bo_size = mem->bo->tbo.base.size;
>>       struct kfd_bo_va_list *entry;
>>       struct bo_vm_reservation_context ctx;
>>       int ret;
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel