On 11/13/26 15:57, Zhigang Luo wrote:
> PDB0 block size 12 covers one 8GB entry. A GART start aligned only to
> 4GB can land in the middle of that entry. Align the sysvm GART start
> to 8GB, and use SZ_4G and SZ_8G in place of the local size constants.
> 
> Signed-off-by: Zhigang Luo <[email protected]>

Reviewed-by: Christian König <[email protected]>
CC: [email protected]

Please take a look at the gitlog and add a Fixes tag when the VRAM PDE 
workaround was added.

Regards,
Christian.

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 13 ++++++-------
>  1 file changed, 6 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 04cf02dd22ac..8a62f4f3aace 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -25,6 +25,7 @@
>   */
>  
>  #include <linux/io-64-nonatomic-lo-hi.h>
> +#include <linux/sizes.h>
>  #ifdef CONFIG_X86
>  #include <asm/hypervisor.h>
>  #endif
> @@ -41,8 +42,6 @@
>  #include <drm/drm_drv.h>
>  #include <drm/ttm/ttm_tt.h>
>  
> -static const u64 four_gb = 0x100000000ULL;
> -
>  bool amdgpu_gmc_is_pdb0_enabled(struct amdgpu_device *adev)
>  {
>       return adev->gmc.xgmi.connected_to_cpu || 
> amdgpu_virt_xgmi_migrate_enabled(adev);
> @@ -261,8 +260,8 @@ void amdgpu_gmc_sysvm_location(struct amdgpu_device 
> *adev, struct amdgpu_gmc *mc
>       u64 hive_vram_end = mc->xgmi.node_segment_size * 
> mc->xgmi.num_physical_nodes - 1;
>       mc->vram_start = mc->xgmi.node_segment_size * mc->xgmi.physical_node_id;
>       mc->vram_end = mc->vram_start + mc->xgmi.node_segment_size - 1;
> -     /* node_segment_size may not 4GB aligned on SRIOV, align up is needed. 
> */
> -     mc->gart_start = ALIGN(hive_vram_end + 1, four_gb);
> +     /* Round up to a PDB0 entry so GART starts on the page-table PDE. */
> +     mc->gart_start = ALIGN(hive_vram_end + 1, SZ_8G);
>       mc->gart_end = mc->gart_start + mc->gart_size - 1;
>       if (amdgpu_virt_xgmi_migrate_enabled(adev)) {
>               /* set mc->vram_start to 0 to switch the returned GPU address of
> @@ -313,7 +312,7 @@ 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 = max_mc_address + 1 - ALIGN(mc->fb_end + 1, four_gb);
> +     size_af = max_mc_address + 1 - ALIGN(mc->fb_end + 1, SZ_4G);
>  
>       if (mc->gart_size > max(size_bf, size_af)) {
>               dev_warn(adev->dev, "limiting GART\n");
> @@ -328,7 +327,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, 
> struct amdgpu_gmc *mc,
>               if (size_bf >= mc->gart_size)
>                       mc->gart_start = 0;
>               else
> -                     mc->gart_start = ALIGN(mc->fb_end, four_gb);
> +                     mc->gart_start = ALIGN(mc->fb_end, SZ_4G);
>               break;
>       case AMDGPU_GART_PLACEMENT_BEST_FIT:
>       default:
> @@ -340,7 +339,7 @@ void amdgpu_gmc_gart_location(struct amdgpu_device *adev, 
> struct amdgpu_gmc *mc,
>               break;
>       }
>  
> -     mc->gart_start &= ~(four_gb - 1);
> +     mc->gart_start &= ~(SZ_4G - 1);
>       mc->gart_end = mc->gart_start + mc->gart_size - 1;
>       dev_info(adev->dev, "GART: %lluM 0x%016llX - 0x%016llX\n",
>                       mc->gart_size >> 20, mc->gart_start, mc->gart_end);

Reply via email to