If userspace never maps GEM object, then BO wastes hostmem space
because VirtIO-GPU driver maps VRAM BO at the BO's creating time.

Make mappings on-demand by adding new RESOURCE_CREATE_BLOB IOCTL/UAPI
hinting flag telling that host mapping should be deferred until first
mapping is made when the flag is set by userspace.

Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
---

Changelog:

v2: Rebased on recent kernel. Intel i915 native ctx landed to Mesa, lets to
    proceed with merging the mapping hint as a first user of the feature.

 drivers/gpu/drm/virtio/virtgpu_drv.h   |  2 ++
 drivers/gpu/drm/virtio/virtgpu_ioctl.c |  1 +
 drivers/gpu/drm/virtio/virtgpu_vram.c  | 30 +++++++++++++++++++++-----
 include/uapi/drm/virtgpu_drm.h         |  4 ++++
 4 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index f17660a71a3e..6f49213e23f8 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -84,6 +84,7 @@ struct virtio_gpu_object_params {
 	uint32_t blob_mem;
 	uint32_t blob_flags;
 	uint64_t blob_id;
+	uint32_t blob_hints;
 };
 
 struct virtio_gpu_object {
@@ -507,6 +508,7 @@ struct sg_table *virtio_gpu_vram_map_dma_buf(struct virtio_gpu_object *bo,
 void virtio_gpu_vram_unmap_dma_buf(struct device *dev,
 				   struct sg_table *sgt,
 				   enum dma_data_direction dir);
+void virtio_gpu_vram_map_deferred(struct virtio_gpu_object_vram *vram);
 
 /* virtgpu_submit.c */
 int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index c33c057365f8..01daa72b1310 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -489,6 +489,7 @@ static int verify_blob(struct virtio_gpu_device *vgdev,
 	params->size = rc_blob->size;
 	params->blob = true;
 	params->blob_flags = rc_blob->blob_flags;
+	params->blob_hints = rc_blob->blob_hints;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_vram.c b/drivers/gpu/drm/virtio/virtgpu_vram.c
index 084e80227433..4ae3cbc35dd3 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vram.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vram.c
@@ -3,6 +3,8 @@
 
 #include <linux/dma-mapping.h>
 
+static DEFINE_MUTEX(map_lock);
+
 static void virtio_gpu_vram_free(struct drm_gem_object *obj)
 {
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
@@ -42,6 +44,11 @@ static int virtio_gpu_vram_mmap(struct drm_gem_object *obj,
 	if (!(bo->blob_flags & VIRTGPU_BLOB_FLAG_USE_MAPPABLE))
 		return -EINVAL;
 
+	virtio_gpu_vram_map_deferred(vram);
+
+	if (vram->map_state == STATE_INITIALIZING)
+		virtio_gpu_notify(vgdev);
+
 	wait_event(vgdev->resp_wq, vram->map_state != STATE_INITIALIZING);
 	if (vram->map_state != STATE_OK)
 		return -EINVAL;
@@ -218,14 +225,27 @@ int virtio_gpu_vram_create(struct virtio_gpu_device *vgdev,
 
 	virtio_gpu_cmd_resource_create_blob(vgdev, &vram->base, params, NULL,
 					    0);
-	if (params->blob_flags & VIRTGPU_BLOB_FLAG_USE_MAPPABLE) {
-		ret = virtio_gpu_vram_map(&vram->base);
-		if (ret) {
-			virtio_gpu_vram_free(obj);
-			return ret;
+	if (!(params->blob_hints & DRM_VIRTGPU_BLOB_FLAG_HINT_DEFER_MAPPING)) {
+		if (params->blob_flags & VIRTGPU_BLOB_FLAG_USE_MAPPABLE) {
+			ret = virtio_gpu_vram_map(&vram->base);
+			if (ret) {
+				virtio_gpu_vram_free(obj);
+				return ret;
+			}
 		}
 	}
 
 	*bo_ptr = &vram->base;
 	return 0;
 }
+
+void virtio_gpu_vram_map_deferred(struct virtio_gpu_object_vram *vram)
+{
+	if (!(vram->base.blob_flags & VIRTGPU_BLOB_FLAG_USE_MAPPABLE))
+		return;
+
+	mutex_lock(&map_lock);
+	if (!drm_mm_node_allocated(&vram->vram_node))
+		virtio_gpu_vram_map(&vram->base);
+	mutex_unlock(&map_lock);
+}
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index 9debb320c34b..ba09a4ee3e77 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -200,6 +200,10 @@ struct drm_virtgpu_resource_create_blob {
 	__u32 cmd_size;
 	__u64 cmd;
 	__u64 blob_id;
+
+#define DRM_VIRTGPU_BLOB_FLAG_HINT_DEFER_MAPPING        0x0001
+	__u32 blob_hints;
+	__u32 pad2;
 };
 
 #define VIRTGPU_CONTEXT_PARAM_CAPSET_ID       0x0001
-- 
2.53.0