Re: [PATCH] drm/xe: Skip clearing purged page-table BOs

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

On Fri, Sep 04, 2026 at 05:51:22PM +0530, Tejas Upadhyay wrote:
> VRAM page offlining can clear a page-table BO's vmap before VM teardown
> calls xe_pt_clear(). Check for a purged BO under its dma-resv lock before
> writing to the mapping.
> 
> Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_pt.c | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index 5d990c1c3740..23bc74ba02cb 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -236,9 +236,12 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
>   */
>  void xe_pt_clear(struct xe_device *xe, struct xe_pt *pt)
>  {
> -	struct iosys_map *map = &pt->bo->vmap;
> +	struct xe_bo *bo = pt->bo;
>  
> -	xe_map_memset(xe, map, 0, 0, SZ_4K);
> +	xe_bo_lock(bo, false);
> +	if (!xe_bo_is_purged(bo))
> +		xe_map_memset(xe, &bo->vmap, 0, 0, SZ_4K);
> +	xe_bo_unlock(bo);

You have inverted the notifier lock and dma-resv [1].

The PT's dma-resv is the VM's dma-resv, so in xe_vm_close take this
before the notifier lock and drop the lock here.

For full clarity - assert dma-resv is held here via xe_bo_assert_held.

Matt

[1] https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-173375v1/bat-nvls-1/igt@xe_compute@compute-square.html

>  }
>  
>  /**
> -- 
> 2.52.0
>