drm/xe: Bump prefetch BO LRU via GPUSVM devmem callback

Add xe_svm_devmem_lru_bump() and set it as drm_gpusvm_ctx.devmem_fn in
the prefetch worker so each backing BO is moved to the LRU tail during
get_pages.

v2:
- Guard xe_svm_devmem_lru_bump() against foreign device-memory
  allocations before casting to xe_bo: return early when
  devmem_allocation->ops != &dpagemap_devmem_ops. A shared
  device_private_page_owner can hand us another driver's allocation.
  (Matthew Brost / Sashiko AI review)
- Add stub for function (CI)

v3:
- Guard xe_svm_devmem_lru_bump() body with CONFIG_DRM_XE_PAGEMAP; it
  references dpagemap_devmem_ops and to_xe_bo(), which only exist when
  PAGEMAP is enabled. Fixes the build with GPUSVM=y, PAGEMAP=n.
  (Sashiko AI review)

v4:
- Fix xe_svm_devmem_lru_bump() kernel-doc to explain the locking (Matt)

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20261001033602.3166274-9-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_svm.c

@@ -9,6 +9,7 @@
 #include <drm/drm_managed.h>
 #include <drm/drm_pagemap.h>
 #include <drm/drm_pagemap_util.h>
+#include <drm/ttm/ttm_bo.h>
 
 #include "xe_bo.h"
 #include "xe_exec_queue_types.h"
@@ -1625,6 +1626,39 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
 	return err;
 }
 
+/**
+ * xe_svm_devmem_lru_bump() - Move a range's backing BO to the TTM LRU tail
+ * @devmem_allocation: The device-memory allocation backing the range's pages
+ *
+ * Intended as a &drm_gpusvm_ctx.devmem_fn, so drm_gpusvm_get_pages() calls it
+ * under the GPUSVM notifier lock. That lock sits in the reclaim path, so
+ * dma-resv cannot be acquired blocking beneath it; dma-resv is also the outer
+ * lock of the notifier when memory is allocated and migrated, so a blocking
+ * acquire here would invert that order. Hence the trylock. The BO is private
+ * (dedicated dma-resv), so the trylock succeeds unless the BO is being moved
+ * elsewhere (e.g. eviction); a contended BO is simply skipped.
+ *
+ * A shared device_private_page_owner can hand us allocations backed by a
+ * foreign driver; skip anything that is not an Xe BO before casting.
+ */
+void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation)
+{
+#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
+	struct xe_bo *bo;
+
+	if (devmem_allocation->ops != &dpagemap_devmem_ops)
+		return;
+
+	bo = to_xe_bo(devmem_allocation);
+
+	if (!dma_resv_trylock(bo->ttm.base.resv))
+		return;
+
+	ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);
+	dma_resv_unlock(bo->ttm.base.resv);
+#endif
+}
+
 /**
  * xe_svm_ranges_zap_ptes_in_range - clear ptes of svm ranges in input range
  * @vm: Pointer to the xe_vm structure

drivers/gpu/drm/xe/xe_svm.h

@@ -128,6 +128,8 @@ struct xe_svm_range *xe_svm_range_find_or_insert(struct xe_vm *vm, u64 addr,
 int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
 			   struct drm_gpusvm_ctx *ctx);
 
+void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation);
+
 bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vma *vma,
 					const struct drm_pagemap *dpagemap);
 
@@ -356,6 +358,11 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
 	return -EINVAL;
 }
 
+static inline
+void xe_svm_devmem_lru_bump(struct drm_pagemap_devmem *devmem_allocation)
+{
+}
+
 static inline struct xe_svm_range *to_xe_range(struct drm_gpusvm_range *r)
 {
 	return NULL;

drivers/gpu/drm/xe/xe_vm.c

@@ -3246,6 +3246,7 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_ops *vops,
 	ctx.devmem_possible = devmem_possible;
 	ctx.check_pages_threshold = devmem_possible ? SZ_64K : 0;
 	ctx.device_private_page_owner = xe_svm_private_page_owner(vm, !dpagemap);
+	ctx.devmem_fn = xe_svm_devmem_lru_bump;
 
 	skip_threads =  op->prefetch_range.ranges_count == 1 ||
 		(!dpagemap && !(vops->flags &