Re: [PATCH v7 3/3] drm/xe: Allow scratch page under fault mode for certain platform

[Matthew Brost <matthew.brost@intel.com>]

On Fri, Feb 28, 2025 at 10:30:58AM -0500, Oak Zeng wrote:
> Normally scratch page is not allowed when a vm is operate under page
> fault mode, i.e., in the existing codes, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE
> and DRM_XE_VM_CREATE_FLAG_FAULT_MODE are mutual exclusive. The reason
> is fault mode relies on recoverable page to work, while scratch page
> can mute recoverable page fault.
> 
> On xe2 and xe3, out of bound prefetch can cause page fault and further
> system hang because xekmd can't resolve such page fault. SYCL and OCL
> language runtime requires out of bound prefetch to be silently dropped
> without causing any functional problem, thus the existing behavior
> doesn't meet language runtime requirement.
> 
> At the same time, HW prefetching can cause page fault interrupt. Due to
> page fault interrupt overhead (i.e., need Guc and KMD involved to fix
> the page fault), HW prefetching can be slowed by many orders of magnitude.
> 
> Fix those problems by allowing scratch page under fault mode for xe2 and
> xe3. With scratch page in place, HW prefetching could always hit scratch
> page instead of causing interrupt.
> 
> A side effect is, scratch page could hide application program error.
> Application out of bound accesses are hided by scratch page mapping,
> instead of get reported to user.
> 
> v2: Refine commit message (Thomas)
> 
> v3: Move the scratch page flag check to after scratch page wa (Thomas)
> 
> v4: drop NEEDS_SCRATCH macro (matt)
>     Add a comment to DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE
> 
> Signed-off-by: Oak Zeng <oak.zeng@intel.com>

Reviewed-by: Matthew Brost <matthew.brost@intel.com>

> ---
>  drivers/gpu/drm/xe/xe_vm.c | 3 ++-
>  include/uapi/drm/xe_drm.h  | 6 +++++-
>  2 files changed, 7 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index 47051735f0e1..2356f12392a2 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -1791,7 +1791,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
>  		return -EINVAL;
>  
>  	if (XE_IOCTL_DBG(xe, args->flags & DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE &&
> -			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
> +			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE &&
> +			 !xe->info.needs_scratch))
>  		return -EINVAL;
>  
>  	if (XE_IOCTL_DBG(xe, !(args->flags & DRM_XE_VM_CREATE_FLAG_LR_MODE) &&
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 76a462fae05f..7471eaa669bc 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -911,7 +911,11 @@ struct drm_xe_gem_mmap_offset {
>   * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE
>   *
>   * The @flags can be:
> - *  - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE
> + *  - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE - Map the whole virtual address
> + *    space of the VM to scratch page. A vm_bind would overwrite the scratch
> + *    page mapping. This flag is mutually exclusive with the
> + *    %DRM_XE_VM_CREATE_FLAG_FAULT_MODE flag, with an exception of on x2 and
> + *    xe3 platform.
>   *  - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts
>   *    exec submissions to its exec_queues that don't have an upper time
>   *    limit on the job execution time. But exec submissions to these
> -- 
> 2.26.3
>