[PATCH] drm/amdgpu: Limit the max mc address to hole start

[Christian König]

Am 10.10.2018 um 08:45 schrieb Emily Deng:
> Replace AMDGPU_VA_HOLE_START with AMDGPU_GMC_HOLE_START and add the comment.
>
> For the vram_start is 0 case, the gart range will be from 0x0000FFFF00000000
> to 0x0000FFFF1FFFFFFF, which will cause the engine hang.
>
> So to avoid the hole, limit the max mc address to AMDGPU_GMC_HOLE_START.
>
> Signed-off-by: Emily Deng <Emily.Deng at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 6 ++++--
>   1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 9a5b252..bb05d9b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -146,6 +146,8 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
>   {
>   	const uint64_t four_gb = 0x100000000ULL;
>   	u64 size_af, size_bf;
> +	/*To avoid the hole, limit the max mc address to AMDGPU_GMC_HOLE_START*/
> +	u64 max_mc_address = min(adev->gmc.mc_mask, AMDGPU_GMC_HOLE_START);

This needs to use "AMDGPU_GMC_HOLE_START - 1" because the mc_mask is the 
inclusive address space end.

Alternative you could do min(adev->gmc.mc_mask + 1, ....) and also 
remove the "+ 1" in the calculations below. That would probably be even 
cleaner.

With that fixed the patch is Reviewed-by: Christian König 
<christian.koenig at amd.com>.

Regards,
Christian.

>   
>   	mc->gart_size += adev->pm.smu_prv_buffer_size;
>   
> @@ -153,7 +155,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
>   	 * the GART base on a 4GB boundary as well.
>   	 */
>   	size_bf = mc->fb_start;
> -	size_af = adev->gmc.mc_mask + 1 - ALIGN(mc->fb_end + 1, four_gb);
> +	size_af = max_mc_address + 1 - ALIGN(mc->fb_end + 1, four_gb);
>   
>   	if (mc->gart_size > max(size_bf, size_af)) {
>   		dev_warn(adev->dev, "limiting GART\n");
> @@ -164,7 +166,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
>   	    (size_af < mc->gart_size))
>   		mc->gart_start = 0;
>   	else
> -		mc->gart_start = mc->mc_mask - mc->gart_size + 1;
> +		mc->gart_start = max_mc_address - mc->gart_size + 1;
>   
>   	mc->gart_start &= ~(four_gb - 1);
>   	mc->gart_end = mc->gart_start + mc->gart_size - 1;