[PATCH 07/15] drm/xe: Convert SVM validation for exhaustive eviction

[Matthew Brost]

On Wed, Aug 13, 2025 at 12:51:13PM +0200, Thomas Hellström wrote:
> Convert SVM validation to support exhaustive eviction,
> using xe_validation_guard().
> 

Do we not need to validation guard + xe_vm_set_validation_exec around
xe_vm_range_rebind, given that on first fault of range we can allocate
PTs?

Matt

> Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
>  drivers/gpu/drm/xe/xe_svm.c | 63 ++++++++++++++++++-------------------
>  1 file changed, 30 insertions(+), 33 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index 39e3aa6df25a..ba85665d85d4 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -699,51 +699,48 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
>  	struct xe_device *xe = vr->xe;
>  	struct device *dev = xe->drm.dev;
>  	struct drm_buddy_block *block;
> +	struct xe_validation_ctx vctx;
>  	struct list_head *blocks;
> -	struct drm_exec *exec;
> +	struct drm_exec exec;
>  	struct xe_bo *bo;
> -	ktime_t time_end = 0;
> -	int err, idx;
> +	int err = 0, idx;
>  
>  	if (!drm_dev_enter(&xe->drm, &idx))
>  		return -ENODEV;
>  
>  	xe_pm_runtime_get(xe);
> -	exec = XE_VALIDATION_UNIMPLEMENTED;
> -
> - retry:
> -	bo = xe_bo_create_locked(vr->xe, NULL, NULL, end - start,
> -				 ttm_bo_type_device,
> -				 (IS_DGFX(xe) ? XE_BO_FLAG_VRAM(vr) : XE_BO_FLAG_SYSTEM) |
> -				 XE_BO_FLAG_CPU_ADDR_MIRROR, exec);
> -	if (IS_ERR(bo)) {
> -		err = PTR_ERR(bo);
> -		if (xe_vm_validate_should_retry(NULL, err, &time_end))
> -			goto retry;
> -		goto out_pm_put;
> -	}
>  
> -	drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
> -				&dpagemap_devmem_ops, dpagemap, end - start);
> -
> -	blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;
> -	list_for_each_entry(block, blocks, link)
> -		block->private = vr;
> +	xe_validation_guard(&vctx, &xe->val, &exec, 0, err, false) {
> +		bo = xe_bo_create_locked(xe, NULL, NULL, end - start,
> +					 ttm_bo_type_device,
> +					 (IS_DGFX(xe) ? XE_BO_FLAG_VRAM(vr) : XE_BO_FLAG_SYSTEM) |
> +					 XE_BO_FLAG_CPU_ADDR_MIRROR, &exec);
> +		drm_exec_retry_on_contention(&exec);
> +		if (IS_ERR(bo)) {
> +			err = PTR_ERR(bo);
> +			xe_validation_retry_on_oom(&vctx, &err);
> +			break;
> +		}
>  
> -	xe_bo_get(bo);
> +		drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
> +					&dpagemap_devmem_ops, dpagemap, end - start);
>  
> -	/* Ensure the device has a pm ref while there are device pages active. */
> -	xe_pm_runtime_get_noresume(xe);
> -	err = drm_pagemap_migrate_to_devmem(&bo->devmem_allocation, mm,
> -					    start, end, timeslice_ms,
> -					    xe_svm_devm_owner(xe));
> -	if (err)
> -		xe_svm_devmem_release(&bo->devmem_allocation);
> +		blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;
> +		list_for_each_entry(block, blocks, link)
> +			block->private = vr;
>  
> -	xe_bo_unlock(bo);
> -	xe_bo_put(bo);
> +		xe_bo_get(bo);
>  
> -out_pm_put:
> +		/* Ensure the device has a pm ref while there are device pages active. */
> +		xe_pm_runtime_get_noresume(xe);
> +		err = drm_pagemap_migrate_to_devmem(&bo->devmem_allocation, mm,
> +						    start, end, timeslice_ms,
> +						    xe_svm_devm_owner(xe));
> +		if (err)
> +			xe_svm_devmem_release(&bo->devmem_allocation);
> +		xe_bo_unlock(bo);
> +		xe_bo_put(bo);
> +	}
>  	xe_pm_runtime_put(xe);
>  	drm_dev_exit(idx);
>  
> -- 
> 2.50.1
>