[PATCH 2/2] drm/amdgpu: fix scatter-gather mapping with user pages

[Alex Deucher]

On Mon, Mar 23, 2020 at 4:52 PM Shane Francis <bigbeeshane at gmail.com> wrote:
>
> Calls to dma_map_sg may return segments / entries than requested
> if they fall on page bounderies. The old implementation did not
> support this use case.
>
> Signed-off-by: Shane Francis <bigbeeshane at gmail.com>

Fixes: be62dbf554c5 ("iommu/amd: Convert AMD iommu driver to the dma-iommu api")

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index dee446278417..d07f143b50c3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -974,12 +974,13 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
>         /* Map SG to device */
>         r = -ENOMEM;
>         nents = dma_map_sg(adev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
> -       if (nents != ttm->sg->nents)
> +       if (nents == 0)
>                 goto release_sg;
>
>         /* convert SG to linear array of pages and dma addresses */
> -       drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
> -                                        gtt->ttm.dma_address, ttm->num_pages);
> +       drm_prime_dma_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
> +                                       gtt->ttm.dma_address, ttm->num_pages,
> +                                       nents);
>

I think the other call to drm_prime_sg_to_page_addr_arrays in amdgpu
needs a similar fix.

Alex

>         return 0;
>
> --
> 2.26.0
>