drm/amdgpu: Set/clear CPU_ACCESS flag on page fault and move to VRAM

When a BO is moved to VRAM, clear AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED.
This allows it to potentially later move to invisible VRAM if the CPU
does not access it again.

Setting the CPU_ACCESS flag in amdgpu_bo_fault_reserve_notify() also means
that we can remove the loop to restrict lpfn to the end of visible VRAM,
because amdgpu_ttm_placement_init() will do it for us.

v3 [Michel Dänzer]
* Use AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED instead of a new flag
  (Christian König)
* Clear flag in amdgpu_bo_move instead of amdgpu_move_ram_vram
  (Christian)
* Explicitly mention amdgpu_bo_fault_reserve_notify in amdgpu_bo_move
* Also clear flag in amdgpu_bo_create_restricted

Suggested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: John Brooks <john@fastquake.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

@@ -432,6 +432,10 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 
 	trace_amdgpu_bo_create(bo);
 
+	/* Treat CPU_ACCESS_REQUIRED only as a hint if given by UMD */
+	if (type == ttm_bo_type_device)
+		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
 	return 0;
 
 fail_unreserve:
@@ -945,13 +949,17 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo;
-	unsigned long offset, size, lpfn;
-	int i, r;
+	unsigned long offset, size;
+	int r;
 
 	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
 		return 0;
 
 	abo = container_of(bo, struct amdgpu_bo, tbo);
+
+	/* Remember that this BO was accessed by the CPU */
+	abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
 	if (bo->mem.mem_type != TTM_PL_VRAM)
 		return 0;
 
@@ -967,14 +975,6 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	/* hurrah the memory is not visible ! */
 	atomic64_inc(&adev->num_vram_cpu_page_faults);
 	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM);
-	lpfn =	adev->mc.visible_vram_size >> PAGE_SHIFT;
-	for (i = 0; i < abo->placement.num_placement; i++) {
-		/* Force into visible VRAM */
-		if ((abo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
-		    (!abo->placements[i].lpfn ||
-		     abo->placements[i].lpfn > lpfn))
-			abo->placements[i].lpfn = lpfn;
-	}
 	r = ttm_bo_validate(bo, &abo->placement, false, false);
 	if (unlikely(r == -ENOMEM)) {
 		amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

@@ -499,6 +499,15 @@ memcpy:
 		}
 	}
 
+	if (bo->type == ttm_bo_type_device &&
+	    new_mem->mem_type == TTM_PL_VRAM &&
+	    old_mem->mem_type != TTM_PL_VRAM) {
+		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
+		 * accesses the BO after it's moved.
+		 */
+		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+	}
+
 	/* update statistics */
 	atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &adev->num_bytes_moved);
 	return 0;