[PATCH 2/2] drm/amdgpu: add full TMZ support into amdgpu_ttm_map_buffer v2

[Huang Rui]

On Sun, Mar 22, 2020 at 04:48:35PM +0100, Christian König wrote:
> This should allow us to also support VRAM->GTT moves.
> 
> v2: fix missing vram_base_adjustment
> 
> Signed-off-by: Christian König <christian.koenig at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 38 ++++++++++++++++++++++++++-------
>  1 file changed, 30 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 53de99dbaead..e15a343a944b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -309,21 +309,21 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>  				 unsigned window, struct amdgpu_ring *ring,
>  				 bool tmz, uint64_t *addr)
>  {
> -	struct ttm_dma_tt *dma = container_of(bo->ttm, struct ttm_dma_tt, ttm);
>  	struct amdgpu_device *adev = ring->adev;
>  	struct amdgpu_job *job;
>  	unsigned num_dw, num_bytes;
> -	dma_addr_t *dma_address;
>  	struct dma_fence *fence;
>  	uint64_t src_addr, dst_addr;
> +	void *cpu_addr;
>  	uint64_t flags;
> +	unsigned int i;
>  	int r;
>  
>  	BUG_ON(adev->mman.buffer_funcs->copy_max_bytes <
>  	       AMDGPU_GTT_MAX_TRANSFER_SIZE * 8);
>  
>  	/* Map only what can't be accessed directly */
> -	if (mem->start != AMDGPU_BO_INVALID_OFFSET) {
> +	if (!tmz && mem->start != AMDGPU_BO_INVALID_OFFSET) {
>  		*addr = amdgpu_mm_node_addr(bo, mm_node, mem) + offset;
>  		return 0;
>  	}
> @@ -351,15 +351,37 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
>  	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>  	WARN_ON(job->ibs[0].length_dw > num_dw);
>  
> -	dma_address = &dma->dma_address[offset >> PAGE_SHIFT];
>  	flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, mem);
>  	if (tmz)
>  		flags |= AMDGPU_PTE_TMZ;
>  
> -	r = amdgpu_gart_map(adev, 0, num_pages, dma_address, flags,
> -			    &job->ibs[0].ptr[num_dw]);
> -	if (r)
> -		goto error_free;
> +	cpu_addr = &job->ibs[0].ptr[num_dw];
> +
> +	if (mem->mem_type == TTM_PL_TT) {
> +		struct ttm_dma_tt *dma;
> +		dma_addr_t *dma_address;
> +
> +		dma = container_of(bo->ttm, struct ttm_dma_tt, ttm);
> +		dma_address = &dma->dma_address[offset >> PAGE_SHIFT];
> +		r = amdgpu_gart_map(adev, 0, num_pages, dma_address, flags,
> +				    cpu_addr);
> +		if (r)
> +			goto error_free;
> +	} else {
> +		dma_addr_t dma_address;
> +
> +		dma_address = (mm_node->start << PAGE_SHIFT) + offset;
> +		dma_address += adev->vm_manager.vram_base_offset;
> +
> +		for (i = 0; i < num_pages; ++i) {
> +			r = amdgpu_gart_map(adev, i << PAGE_SHIFT, 1,
> +					    &dma_address, flags, cpu_addr);

May I know why do we need map the page one by one here? Is it because if
not PL_TT, the buffer might not be continuous?

Thanks,
Ray

> +			if (r)
> +				goto error_free;
> +
> +			dma_address += PAGE_SIZE;
> +		}
> +	}
>  
>  	r = amdgpu_job_submit(job, &adev->mman.entity,
>  			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
> -- 
> 2.14.1
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cray.huang%40amd.com%7C456a9e561ae44b6bb94508d7ce787f99%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637204889263466725&sdata=zoVAOn4UX4Y3voMhyI4OwEKte7TgzGLC5ZmAj9TkW%2FU%3D&reserved=0