drm/xe: Use BO's GT to determine dma_offset when programming PTEs

Rather than using the passed in GT, use the BO's GT determine dma_offset
when programming PTEs as these two GT's could differ (i.e. mapping a BO
from a remote GT). The BO's GT is correct GT to use as this where BO
resides, while the passed in GT is where the mapping is created.

v2:
  (Thomas)      - Kernel doc, extra new line
  (CI)          - Rebase to tip
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_bo.c

@@ -79,6 +79,19 @@ mem_type_to_gt(struct xe_device *xe, u32 mem_type)
 	return xe_device_get_gt(xe, mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0));
 }
 
+/**
+ * xe_bo_to_gt() - Get a GT from a BO's memory location
+ * @bo: The buffer object
+ *
+ * Get a GT from a BO's memory location, should be called on BOs in VRAM only.
+ *
+ * Return: xe_gt object which is closest to the BO
+ */
+struct xe_gt *xe_bo_to_gt(struct xe_bo *bo)
+{
+	return mem_type_to_gt(xe_bo_device(bo), bo->ttm.resource->mem_type);
+}
+
 static void try_add_system(struct xe_bo *bo, struct ttm_place *places,
 			   u32 bo_flags, u32 *c)
 {

drivers/gpu/drm/xe/xe_bo.h

@@ -105,6 +105,8 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_gt *gt,
 int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
 			      u32 bo_flags);
 
+struct xe_gt *xe_bo_to_gt(struct xe_bo *bo);
+
 static inline struct xe_bo *ttm_to_xe_bo(const struct ttm_buffer_object *bo)
 {
 	return container_of(bo, struct xe_bo, ttm);

drivers/gpu/drm/xe/xe_pt.c

@@ -758,10 +758,12 @@ xe_pt_stage_bind(struct xe_gt *gt, struct xe_vma *vma,
 	int ret;
 
 	if (is_vram) {
+		struct xe_gt *bo_gt = xe_bo_to_gt(bo);
+
 		xe_walk.default_pte = GEN12_PPGTT_PTE_LM;
 		if (vma && vma->use_atomic_access_pte_bit)
 			xe_walk.default_pte |= GEN12_USM_PPGTT_PTE_AE;
-		xe_walk.dma_offset = gt->mem.vram.io_start -
+		xe_walk.dma_offset = bo_gt->mem.vram.io_start -
 			gt_to_xe(gt)->mem.vram.io_start;
 		xe_walk.cache = XE_CACHE_WB;
 	} else {