Re: [PATCH V18 05/14] drm/xe: Guard teardown paths against purged BOs

["Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>]

On 26-08-2026 19:21, Tejas Upadhyay wrote:
> VRAM page offlining can purge BOs that are still referenced by page
> tables, exec queues, and DMA-buf exports. Add xe_bo_is_purged()
> guards in the teardown paths to prevent unpinning or mapping an
> already-purged BO:
> 
> - xe_bo_unpin_map_no_vm(): skip unpin if purged
> - xe_dma_buf_map(): return -ENOENT early if purged
> - xe_exec_queue_update_run_ticks(): skip LRC timestamp read if purged
> - xe_pt_destroy(): skip unpin if purged
> 
> v3(Sashiko):
> - Remove dma_resv is already held
> v2(Himal):
> - take dma_resv lock before calling xe_bo_is_purged()
> 
> Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_bo.h         | 3 ++-
>   drivers/gpu/drm/xe/xe_dma_buf.c    | 3 +++
>   drivers/gpu/drm/xe/xe_exec_queue.c | 8 ++++++--
>   drivers/gpu/drm/xe/xe_pt.c         | 3 ++-
>   4 files changed, 13 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
> index eede678ad303..dfcd0e57073b 100644
> --- a/drivers/gpu/drm/xe/xe_bo.h
> +++ b/drivers/gpu/drm/xe/xe_bo.h
> @@ -364,7 +364,8 @@ static inline void xe_bo_unpin_map_no_vm(struct xe_bo *bo)
>   {
>   	if (likely(bo)) {
>   		xe_bo_lock(bo, false);
> -		xe_bo_unpin(bo);
> +		if (!xe_bo_is_purged(bo))
> +			xe_bo_unpin(bo);
>   		xe_bo_unlock(bo);
>   
>   		xe_bo_put(bo);
> diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
> index bf0728838ead..5d9f1cd24b7f 100644
> --- a/drivers/gpu/drm/xe/xe_dma_buf.c
> +++ b/drivers/gpu/drm/xe/xe_dma_buf.c
> @@ -104,6 +104,9 @@ static struct sg_table *xe_dma_buf_map(struct dma_buf_attachment *attach,
>   	struct sg_table *sgt;
>   	int r = 0;
>   
> +	if (xe_bo_is_purged(bo))
> +		return ERR_PTR(-ENOENT);
> +
>   	if (!attach->peer2peer && !xe_bo_can_migrate(bo, XE_PL_TT))
>   		return ERR_PTR(-EOPNOTSUPP);
>   
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index 91ed6c0fac84..91e4f3cb5617 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -1572,8 +1572,12 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
>   	 * errors.
>   	 */
>   	lrc = q->lrc[0];
> -	new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
> -	q->xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
> +	xe_bo_lock(lrc->bo, false);
> +	if (!xe_bo_is_purged(lrc->bo)) {
> +		new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
> +		q->xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
> +	}
> +	xe_bo_unlock(lrc->bo);
>   
>   	drm_dev_exit(idx);
>   }
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index 5d990c1c3740..dbf1aa26a21b 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -212,7 +212,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
>   		return;
>   
>   	XE_WARN_ON(!list_empty(&pt->bo->ttm.base.gpuva.list));
> -	xe_bo_unpin(pt->bo);
> +	if (!xe_bo_is_purged(pt->bo))
> +		xe_bo_unpin(pt->bo);

IMO, moving purge check within xe_bo_unpin seems better, with comment 
what might cause purge.

>   	xe_bo_put_deferred(pt->bo, deferred);
>   
>   	if (pt->level > 0 && pt->num_live) {