On 4/7/26 12:09, Christian König wrote:
>
>
> On 4/3/26 10:35, Pierre-Eric Pelloux-Prayer wrote:
>> It's doing the same thing as amdgpu_fill_buffer(src_data=0), so drop it.
>>
>> The only caveat is that amdgpu_res_cleared() return value is only valid
>> right after allocation.
>>
>> ---
>> v2: introduce new "bool consider_clear_status" arg
>> ---
>>
>> Signed-off-by: Pierre-Eric Pelloux-Prayer
>> <[email protected]>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 16 ++--
>> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 88 +++++-----------------
>> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 6 +-
>> 3 files changed, 32 insertions(+), 78 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
>> index 66c20dd46d12..d0884bbffa75 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
>> @@ -717,13 +717,17 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
>> bo->tbo.resource->mem_type == TTM_PL_VRAM) {
>> struct dma_fence *fence;
>>
>> - r = amdgpu_ttm_clear_buffer(bo, bo->tbo.base.resv, &fence);
>> + r = amdgpu_fill_buffer(amdgpu_ttm_next_clear_entity(adev),
>> + bo, 0, NULL, &fence,
>> + true,
>> AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>> if (unlikely(r))
>> goto fail_unreserve;
>>
>> - dma_resv_add_fence(bo->tbo.base.resv, fence,
>> - DMA_RESV_USAGE_KERNEL);
>> - dma_fence_put(fence);
>> + if (fence) {
>> + dma_resv_add_fence(bo->tbo.base.resv, fence,
>> + DMA_RESV_USAGE_KERNEL);
>> + dma_fence_put(fence);
>> + }
>> }
>> if (!bp->resv)
>> amdgpu_bo_unreserve(bo);
>> @@ -1326,8 +1330,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object
>> *bo)
>> goto out;
>>
>> r = amdgpu_fill_buffer(amdgpu_ttm_next_clear_entity(adev),
>> - abo, 0, &bo->base._resv,
>> - &fence, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
>> + abo, 0, &bo->base._resv, &fence,
>> + false, AMDGPU_KERNEL_JOB_ID_CLEAR_ON_RELEASE);
>> if (WARN_ON(r))
>> goto out;
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>> index 648ad344e89c..a3d0998b8cec 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>> @@ -418,7 +418,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
>> (abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
>> struct dma_fence *wipe_fence = NULL;
>> r = amdgpu_fill_buffer(entity, abo, 0, NULL, &wipe_fence,
>> - AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
>> + false, AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
>> if (r) {
>> goto error;
>> } else if (wipe_fence) {
>> @@ -2572,76 +2572,25 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_device
>> *adev,
>> }
>>
>> /**
>> - * amdgpu_ttm_clear_buffer - clear memory buffers
>> - * @bo: amdgpu buffer object
>> - * @resv: reservation object
>> - * @fence: dma_fence associated with the operation
>> + * amdgpu_fill_buffer - fill a buffer with a given value
>> + * @entity: entity to use
>> + * @bo: the bo to fill
>> + * @src_data: the value to set
>> + * @resv: fences contained in this reservation will be used as dependencies.
>> + * @out_fence: the fence from the last clear will be stored here. It might
>> be
>> + * NULL if no job was run.
>> + * @dependency: optional input dependency fence.
>> + * @consider_clear_status: true if region reported as cleared by
>> amdgpu_res_cleared()
>> + * are skipped.
>> + * @k_job_id: trace id
>> *
>> - * Clear the memory buffer resource.
>> - *
>> - * Returns:
>> - * 0 for success or a negative error code on failure.
>> */
>> -int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>> - struct dma_resv *resv,
>> - struct dma_fence **fence)
>> -{
>> - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
>> - struct amdgpu_ttm_buffer_entity *entity;
>> - struct amdgpu_res_cursor cursor;
>> - u64 addr;
>> - int r = 0;
>> -
>> - if (!adev->mman.buffer_funcs_enabled)
>> - return -EINVAL;
>> -
>> - if (!fence)
>> - return -EINVAL;
>> - entity = &adev->mman.clear_entities[0];
>> - *fence = dma_fence_get_stub();
>> -
>> - amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
>> -
>> - mutex_lock(&entity->lock);
>> - while (cursor.remaining) {
>> - struct dma_fence *next = NULL;
>> - u64 size;
>> -
>> - if (amdgpu_res_cleared(&cursor)) {
>> - amdgpu_res_next(&cursor, cursor.size);
>> - continue;
>> - }
>> -
>> - /* Never clear more than 256MiB at once to avoid timeouts */
>> - size = min(cursor.size, 256ULL << 20);
>> -
>> - r = amdgpu_ttm_map_buffer(entity, &bo->tbo, bo->tbo.resource,
>> &cursor,
>> - 0, false, &size, &addr);
>> - if (r)
>> - goto err;
>> -
>> - r = amdgpu_ttm_fill_mem(adev, entity, 0, addr, size, resv,
>> - &next, true,
>> - AMDGPU_KERNEL_JOB_ID_TTM_CLEAR_BUFFER);
>> - if (r)
>> - goto err;
>> -
>> - dma_fence_put(*fence);
>> - *fence = next;
>> -
>> - amdgpu_res_next(&cursor, size);
>> - }
>> -err:
>> - mutex_unlock(&entity->lock);
>> -
>> - return r;
>> -}
>> -
>> int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
>
> We should probably rename the function to amdgpu_ttm_clear_buffer() while
> doing this.
Forget that, I've just seen that patch #6 does exactly that.
Feel free to add Reviewed-by: Christian König <[email protected]>.
Regards,
Christian.
>
> Apart from that looks good to me.
>
> Regards,
> Christian.
>
>> struct amdgpu_bo *bo,
>> uint32_t src_data,
>> struct dma_resv *resv,
>> - struct dma_fence **f,
>> + struct dma_fence **out_fence,
>> + bool consider_clear_status,
>> u64 k_job_id)
>> {
>> struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
>> @@ -2659,6 +2608,11 @@ int amdgpu_fill_buffer(struct
>> amdgpu_ttm_buffer_entity *entity,
>> struct dma_fence *next;
>> uint64_t cur_size, to;
>>
>> + if (consider_clear_status && amdgpu_res_cleared(&dst)) {
>> + amdgpu_res_next(&dst, dst.size);
>> + continue;
>> + }
>> +
>> /* Never fill more than 256MiB at once to avoid timeouts */
>> cur_size = min(dst.size, 256ULL << 20);
>>
>> @@ -2680,9 +2634,7 @@ int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity
>> *entity,
>> }
>> error:
>> mutex_unlock(&entity->lock);
>> - if (f)
>> - *f = dma_fence_get(fence);
>> - dma_fence_put(fence);
>> + *out_fence = fence;
>> return r;
>> }
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
>> index a6249252948b..436a3e09a178 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
>> @@ -187,14 +187,12 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev,
>> struct dma_resv *resv,
>> struct dma_fence **fence,
>> bool vm_needs_flush, uint32_t copy_flags);
>> -int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
>> - struct dma_resv *resv,
>> - struct dma_fence **fence);
>> int amdgpu_fill_buffer(struct amdgpu_ttm_buffer_entity *entity,
>> struct amdgpu_bo *bo,
>> uint32_t src_data,
>> struct dma_resv *resv,
>> - struct dma_fence **f,
>> + struct dma_fence **out_fence,
>> + bool consider_clear_status,
>> u64 k_job_id);
>> struct amdgpu_ttm_buffer_entity *amdgpu_ttm_next_clear_entity(struct
>> amdgpu_device *adev);
>>
>
