[PATCH] drm/amdgpu: OR init_pte_flags into invalid leaf PTE updates

[PATCH] drm/amdgpu: OR init_pte_flags into invalid leaf PTE updates

[Siwei He]

Invalid leaf clears that only set AMDGPU_PTE_EXECUTABLE match the old
GMC9 fault-priority workaround but omit adev->gmc.init_pte_flags.
On GFX12 that includes AMDGPU_PTE_IS_PTE; without it, some cleared
PTEs can fault as no-retry and bypass the SVM/XNACK handler when a
VA is reused after a BO unmap.

Apply init_pte_flags in amdgpu_vm_pte_update_flags() alongside
EXECUTABLE so range-driven clears (e.g. amdgpu_vm_clear_freed) match
amdgpu_vm_pt_clear() for leaf templates.

Signed-off-by: Siwei He <siwei.he@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 31a437ce9570..a930f1522f96 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -693,8 +693,11 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params,
 		   !(flags & AMDGPU_PTE_VALID) &&
 		   !(flags & AMDGPU_PTE_PRT_FLAG(params->adev))) {
 
-		/* Workaround for fault priority problem on GMC9 */
-		flags |= AMDGPU_PTE_EXECUTABLE;
+		/* Workaround for fault priority problem on GMC9 and GFX12,
+		 * EXECUTABLE for GMC9 fault priority and init_pte_flags
+		 * (e.g. AMDGPU_PTE_IS_PTE on GFX12)
+		 */
+		flags |= AMDGPU_PTE_EXECUTABLE | adev->gmc.init_pte_flags;
 	}
 
 	/*
-- 
2.43.0

Re: [PATCH] drm/amdgpu: OR init_pte_flags into invalid leaf PTE updates

[Philip Yang]

[-- Attachment #1: Type: text/plain, Size: 1663 bytes --]



On 2026-04-14 14:48, Siwei He wrote:
> Invalid leaf clears that only set AMDGPU_PTE_EXECUTABLE match the old
> GMC9 fault-priority workaround but omit adev->gmc.init_pte_flags.
> On GFX12 that includes AMDGPU_PTE_IS_PTE; without it, some cleared
> PTEs can fault as no-retry and bypass the SVM/XNACK handler when a
> VA is reused after a BO unmap.
>
> Apply init_pte_flags in amdgpu_vm_pte_update_flags() alongside
> EXECUTABLE so range-driven clears (e.g. amdgpu_vm_clear_freed) match
> amdgpu_vm_pt_clear() for leaf templates.
>
> Signed-off-by: Siwei He<siwei.he@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 7 +++++--
>   1 file changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> index 31a437ce9570..a930f1522f96 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> @@ -693,8 +693,11 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params,
>   		   !(flags & AMDGPU_PTE_VALID) &&
>   		   !(flags & AMDGPU_PTE_PRT_FLAG(params->adev))) {
>   
> -		/* Workaround for fault priority problem on GMC9 */
> -		flags |= AMDGPU_PTE_EXECUTABLE;
> +		/* Workaround for fault priority problem on GMC9 and GFX12,
> +		 * EXECUTABLE for GMC9 fault priority and init_pte_flags
> +		 * (e.g. AMDGPU_PTE_IS_PTE on GFX12)
> +		 */
> +		flags |= AMDGPU_PTE_EXECUTABLE | adev->gmc.init_pte_flags;

Looks good to me, !(flags & AMDGPU_PTE_PRT_FLAG(params->adev) handles the NPA mapping update case correctly too.

Reviewed-by: Philip Yang<philip.yang@amd.com>
  

>   	}
>   
>   	/*

[-- Attachment #2: Type: text/html, Size: 2352 bytes --]