drm/ttm: remove bo->moving

This is now handled by the DMA-buf framework in the dma_resv obj.

Also remove the workaround inside VMWGFX to update the moving fence.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-14-christian.koenig@amd.com

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

@@ -2447,6 +2447,8 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 		struct amdgpu_bo *bo = mem->bo;
 		uint32_t domain = mem->domain;
 		struct kfd_mem_attachment *attachment;
+		struct dma_resv_iter cursor;
+		struct dma_fence *fence;
 
 		total_size += amdgpu_bo_size(bo);
 
@@ -2461,11 +2463,14 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				goto validate_map_fail;
 			}
 		}
-		ret = amdgpu_sync_fence(&sync_obj, bo->tbo.moving);
+		dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
+					DMA_RESV_USAGE_KERNEL, fence) {
+			ret = amdgpu_sync_fence(&sync_obj, fence);
 			if (ret) {
 				pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
 				goto validate_map_fail;
 			}
+		}
 		list_for_each_entry(attachment, &mem->attachments, list) {
 			if (!attachment->is_mapped)
 				continue;

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

@@ -612,9 +612,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 		if (unlikely(r))
 			goto fail_unreserve;
 
-		amdgpu_bo_fence(bo, fence, false);
-		dma_fence_put(bo->tbo.moving);
-		bo->tbo.moving = dma_fence_get(fence);
+		dma_resv_add_fence(bo->tbo.base.resv, fence,
+				   DMA_RESV_USAGE_KERNEL);
 		dma_fence_put(fence);
 	}
 	if (!bp->resv)

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

@@ -74,13 +74,12 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p,
 {
 	unsigned int i;
 	uint64_t value;
-	int r;
+	long r;
 
-	if (vmbo->bo.tbo.moving) {
-		r = dma_fence_wait(vmbo->bo.tbo.moving, true);
-		if (r)
+	r = dma_resv_wait_timeout(vmbo->bo.tbo.base.resv, DMA_RESV_USAGE_KERNEL,
+				  true, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0)
 		return r;
-	}
 
 	pe += (unsigned long)amdgpu_bo_kptr(&vmbo->bo);
 

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

@@ -204,14 +204,19 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p,
 	struct amdgpu_bo *bo = &vmbo->bo;
 	enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE
 		: AMDGPU_IB_POOL_DELAYED;
+	struct dma_resv_iter cursor;
 	unsigned int i, ndw, nptes;
+	struct dma_fence *fence;
 	uint64_t *pte;
 	int r;
 
 	/* Wait for PD/PT moves to be completed */
-	r = amdgpu_sync_fence(&p->job->sync, bo->tbo.moving);
+	dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
+				DMA_RESV_USAGE_KERNEL, fence) {
+		r = amdgpu_sync_fence(&p->job->sync, fence);
 		if (r)
 			return r;
+	}
 
 	do {
 		ndw = p->num_dw_left;

drivers/gpu/drm/ttm/ttm_bo.c

@@ -418,7 +418,6 @@ static void ttm_bo_release(struct kref *kref)
 	dma_resv_unlock(bo->base.resv);
 
 	atomic_dec(&ttm_glob.bo_count);
-	dma_fence_put(bo->moving);
 	bo->destroy(bo);
 }
 
@@ -714,9 +713,8 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
 EXPORT_SYMBOL(ttm_bo_unpin);
 
 /*
- * Add the last move fence to the BO and reserve a new shared slot. We only use
- * a shared slot to avoid unecessary sync and rely on the subsequent bo move to
- * either stall or use an exclusive fence respectively set bo->moving.
+ * Add the last move fence to the BO as kernel dependency and reserve a new
+ * fence slot.
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 				 struct ttm_resource_manager *man,
@@ -746,9 +744,6 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 		dma_fence_put(fence);
 		return ret;
 	}
-
-	dma_fence_put(bo->moving);
-	bo->moving = fence;
 	return 0;
 }
 
@@ -951,7 +946,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev,
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->page_alignment = page_alignment;
-	bo->moving = NULL;
 	bo->pin_count = 0;
 	bo->sg = sg;
 	bo->bulk_move = NULL;

drivers/gpu/drm/ttm/ttm_bo_util.c

@@ -228,7 +228,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 
 	atomic_inc(&ttm_glob.bo_count);
 	INIT_LIST_HEAD(&fbo->base.ddestroy);
-	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 
 	kref_init(&fbo->base.kref);
@@ -500,9 +499,6 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	 * operation has completed.
 	 */
 
-	dma_fence_put(bo->moving);
-	bo->moving = dma_fence_get(fence);
-
 	ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 	if (ret)
 		return ret;
@@ -546,9 +542,6 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo,
 	spin_unlock(&from->move_lock);
 
 	ttm_resource_free(bo, &bo->resource);
-
-	dma_fence_put(bo->moving);
-	bo->moving = dma_fence_get(fence);
 }
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -46,17 +46,13 @@
 static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_fault *vmf)
 {
-	vm_fault_t ret = 0;
-	int err = 0;
-
-	if (likely(!bo->moving))
-		goto out_unlock;
+	long err = 0;
 
 	/*
 	 * Quick non-stalling check for idle.
 	 */
-	if (dma_fence_is_signaled(bo->moving))
-		goto out_clear;
+	if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_KERNEL))
+		return 0;
 
 	/*
 	 * If possible, avoid waiting for GPU with mmap_lock
@@ -64,34 +60,30 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 	 * is the first attempt.
 	 */
 	if (fault_flag_allow_retry_first(vmf->flags)) {
-		ret = VM_FAULT_RETRY;
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
-			goto out_unlock;
+			return VM_FAULT_RETRY;
 
 		ttm_bo_get(bo);
 		mmap_read_unlock(vmf->vma->vm_mm);
-		(void) dma_fence_wait(bo->moving, true);
+		(void)dma_resv_wait_timeout(bo->base.resv,
+					    DMA_RESV_USAGE_KERNEL, true,
+					    MAX_SCHEDULE_TIMEOUT);
 		dma_resv_unlock(bo->base.resv);
 		ttm_bo_put(bo);
-		goto out_unlock;
+		return VM_FAULT_RETRY;
 	}
 
 	/*
 	 * Ordinary wait.
 	 */
-	err = dma_fence_wait(bo->moving, true);
-	if (unlikely(err != 0)) {
-		ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
+	err = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_KERNEL, true,
+				    MAX_SCHEDULE_TIMEOUT);
+	if (unlikely(err < 0)) {
+		return (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
 			VM_FAULT_NOPAGE;
-		goto out_unlock;
 	}
 
-out_clear:
-	dma_fence_put(bo->moving);
-	bo->moving = NULL;
-
-out_unlock:
-	return ret;
+	return 0;
 }
 
 static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,

drivers/gpu/drm/vmwgfx/vmwgfx_resource.c

@@ -1161,12 +1161,6 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start,
 		*num_prefault = __KERNEL_DIV_ROUND_UP(last_cleaned - res_start,
 						      PAGE_SIZE);
 		vmw_bo_fence_single(bo, NULL);
-		if (bo->moving)
-			dma_fence_put(bo->moving);
-
-		return dma_resv_get_singleton(bo->base.resv,
-					      DMA_RESV_USAGE_WRITE,
-					      &bo->moving);
 	}
 
 	return 0;

include/drm/ttm/ttm_bo_api.h

@@ -94,7 +94,6 @@ struct ttm_tt;
  * @deleted: True if the object is only a zombie and already deleted.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
- * @moving: Fence set when BO is moving
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
  * @cur_placement: Hint of current placement.
@@ -147,7 +146,6 @@ struct ttm_buffer_object {
 	 * Members protected by a bo reservation.
 	 */
 
-	struct dma_fence *moving;
 	unsigned priority;
 	unsigned pin_count;