[PATCH] drm/amdgpu: Fix page table setup on Arcturus

[Felix Kuehling]

Am 2022-08-22 um 11:52 schrieb Mukul Joshi:
> When translate_further is enabled, page table depth needs to
> be updated. This was missing on Arcturus MMHUB init. This was
> causing address translations to fail for SDMA user-mode queues.
>
> Fixes: 2abf2573b1c69 ("drm/amdgpu: Enable translate_further to extend UTCL2 reach"
> Signed-off-by: Mukul Joshi <mukul.joshi at amd.com>

Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>


> ---
>   drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 12 ++++++++++--
>   1 file changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> index 6e0145b2b408..445cb06b9d26 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> @@ -295,9 +295,17 @@ static void mmhub_v9_4_disable_identity_aperture(struct amdgpu_device *adev,
>   static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
>   {
>   	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
> +	unsigned int num_level, block_size;
>   	uint32_t tmp;
>   	int i;
>   
> +	num_level = adev->vm_manager.num_level;
> +	block_size = adev->vm_manager.block_size;
> +	if (adev->gmc.translate_further)
> +		num_level -= 1;
> +	else
> +		block_size -= 9;
> +
>   	for (i = 0; i <= 14; i++) {
>   		tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
>   				hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i);
> @@ -305,7 +313,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
>   				    ENABLE_CONTEXT, 1);
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
>   				    PAGE_TABLE_DEPTH,
> -				    adev->vm_manager.num_level);
> +				    num_level);
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
>   				    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
> @@ -323,7 +331,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
>   				    EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
>   				    PAGE_TABLE_BLOCK_SIZE,
> -				    adev->vm_manager.block_size - 9);
> +				    block_size);
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,