drm/ttm: use per BO cleanup workers

Instead of a single worker going over the list of delete BOs in regular
intervals use a per BO worker which blocks for the resv object and
locking of the BO.

This not only simplifies the handling massively, but also results in
much better response time when cleaning up buffers.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221125102137.1801-3-christian.koenig@amd.com

1 files changed, 40 insertions, 72 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b77262a623e0..4749b65bedc4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -280,14 +280,13 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 		ret = 0;
 	}
 
-	if (ret || unlikely(list_empty(&bo->ddestroy))) {
+	if (ret) {
 		if (unlock_resv)
 			dma_resv_unlock(bo->base.resv);
 		spin_unlock(&bo->bdev->lru_lock);
 		return ret;
 	}
 
-	list_del_init(&bo->ddestroy);
 	spin_unlock(&bo->bdev->lru_lock);
 	ttm_bo_cleanup_memtype_use(bo);
 
@@ -300,47 +299,21 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 }
 
 /*
- * Traverse the delayed list, and call ttm_bo_cleanup_refs on all
- * encountered buffers.
+ * Block for the dma_resv object to become idle, lock the buffer and clean up
+ * the resource and tt object.
  */
-bool ttm_bo_delayed_delete(struct ttm_device *bdev, bool remove_all)
+static void ttm_bo_delayed_delete(struct work_struct *work)
 {
-	struct list_head removed;
-	bool empty;
-
-	INIT_LIST_HEAD(&removed);
-
-	spin_lock(&bdev->lru_lock);
-	while (!list_empty(&bdev->ddestroy)) {
-		struct ttm_buffer_object *bo;
-
-		bo = list_first_entry(&bdev->ddestroy, struct ttm_buffer_object,
-				      ddestroy);
-		list_move_tail(&bo->ddestroy, &removed);
-		if (!ttm_bo_get_unless_zero(bo))
-			continue;
-
-		if (remove_all || bo->base.resv != &bo->base._resv) {
-			spin_unlock(&bdev->lru_lock);
-			dma_resv_lock(bo->base.resv, NULL);
-
-			spin_lock(&bdev->lru_lock);
-			ttm_bo_cleanup_refs(bo, false, !remove_all, true);
-
-		} else if (dma_resv_trylock(bo->base.resv)) {
-			ttm_bo_cleanup_refs(bo, false, !remove_all, true);
-		} else {
-			spin_unlock(&bdev->lru_lock);
-		}
+	struct ttm_buffer_object *bo;
 
-		ttm_bo_put(bo);
-		spin_lock(&bdev->lru_lock);
-	}
-	list_splice_tail(&removed, &bdev->ddestroy);
-	empty = list_empty(&bdev->ddestroy);
-	spin_unlock(&bdev->lru_lock);
+	bo = container_of(work, typeof(*bo), delayed_delete);
 
-	return empty;
+	dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, false,
+			      MAX_SCHEDULE_TIMEOUT);
+	dma_resv_lock(bo->base.resv, NULL);
+	ttm_bo_cleanup_memtype_use(bo);
+	dma_resv_unlock(bo->base.resv);
+	ttm_bo_put(bo);
 }
 
 static void ttm_bo_release(struct kref *kref)
@@ -369,44 +342,40 @@ static void ttm_bo_release(struct kref *kref)
 
 		drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node);
 		ttm_mem_io_free(bdev, bo->resource);
-	}
-
-	if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP) ||
-	    !dma_resv_trylock(bo->base.resv)) {
-		/* The BO is not idle, resurrect it for delayed destroy */
-		ttm_bo_flush_all_fences(bo);
-		bo->deleted = true;
 
-		spin_lock(&bo->bdev->lru_lock);
+		if (!dma_resv_test_signaled(bo->base.resv,
+					    DMA_RESV_USAGE_BOOKKEEP) ||
+		    !dma_resv_trylock(bo->base.resv)) {
+			/* The BO is not idle, resurrect it for delayed destroy */
+			ttm_bo_flush_all_fences(bo);
+			bo->deleted = true;
 
-		/*
-		 * Make pinned bos immediately available to
-		 * shrinkers, now that they are queued for
-		 * destruction.
-		 *
-		 * FIXME: QXL is triggering this. Can be removed when the
-		 * driver is fixed.
-		 */
-		if (bo->pin_count) {
-			bo->pin_count = 0;
-			ttm_resource_move_to_lru_tail(bo->resource);
-		}
+			spin_lock(&bo->bdev->lru_lock);
 
-		kref_init(&bo->kref);
-		list_add_tail(&bo->ddestroy, &bdev->ddestroy);
-		spin_unlock(&bo->bdev->lru_lock);
+			/*
+			 * Make pinned bos immediately available to
+			 * shrinkers, now that they are queued for
+			 * destruction.
+			 *
+			 * FIXME: QXL is triggering this. Can be removed when the
+			 * driver is fixed.
+			 */
+			if (bo->pin_count) {
+				bo->pin_count = 0;
+				ttm_resource_move_to_lru_tail(bo->resource);
+			}
 
-		schedule_delayed_work(&bdev->wq,
-				      ((HZ / 100) < 1) ? 1 : HZ / 100);
-		return;
-	}
+			kref_init(&bo->kref);
+			spin_unlock(&bo->bdev->lru_lock);
 
-	spin_lock(&bo->bdev->lru_lock);
-	list_del(&bo->ddestroy);
-	spin_unlock(&bo->bdev->lru_lock);
+			INIT_WORK(&bo->delayed_delete, ttm_bo_delayed_delete);
+			queue_work(bdev->wq, &bo->delayed_delete);
+			return;
+		}
 
-	ttm_bo_cleanup_memtype_use(bo);
-	dma_resv_unlock(bo->base.resv);
+		ttm_bo_cleanup_memtype_use(bo);
+		dma_resv_unlock(bo->base.resv);
+	}
 
 	atomic_dec(&ttm_glob.bo_count);
 	bo->destroy(bo);
@@ -946,7 +915,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, struct ttm_buffer_object *bo,
 	int ret;
 
 	kref_init(&bo->kref);
-	INIT_LIST_HEAD(&bo->ddestroy);
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->page_alignment = alignment;