drm/virtio: add in/out fence support for explicit synchronization

When the execbuf call receives an in-fence it will get the dma_fence
related to that fence fd and wait on it before submitting the draw call.

On the out-fence side we get fence returned by the submitted draw call
and attach it to a sync_file and send the sync_file fd to userspace. On
error -1 is returned to userspace.

VIRTGPU_EXECBUF_FENCE_FD_IN & VIRTGPU_EXECBUF_FENCE_FD_OUT
are supported at the simultaneously and can be flagged
for simultaneously.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Signed-off-by: Robert Foss <robert.foss@collabora.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20181112165157.32765-4-robert.foss@collabora.com
Suggested-by: Rob Herring <robh@kernel.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

drivers/gpu/drm/virtio/virtgpu_ioctl.c

@@ -28,6 +28,7 @@
 #include <drm/drmP.h>
 #include <drm/virtgpu_drm.h>
 #include <drm/ttm/ttm_execbuf_util.h>
+#include <linux/sync_file.h>
 
 #include "virtgpu_drv.h"
 
@@ -105,7 +106,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv;
 	struct drm_gem_object *gobj;
-	struct virtio_gpu_fence *fence;
+	struct virtio_gpu_fence *out_fence;
 	struct virtio_gpu_object *qobj;
 	int ret;
 	uint32_t *bo_handles = NULL;
@@ -114,6 +115,9 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	struct ttm_validate_buffer *buflist = NULL;
 	int i;
 	struct ww_acquire_ctx ticket;
+	struct sync_file *sync_file;
+	int in_fence_fd = exbuf->fence_fd;
+	int out_fence_fd = -1;
 	void *buf;
 
 	if (vgdev->has_virgl_3d == false)
@@ -124,6 +128,33 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 
 	exbuf->fence_fd = -1;
 
+	if (exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_IN) {
+		struct dma_fence *in_fence;
+
+		in_fence = sync_file_get_fence(in_fence_fd);
+
+		if (!in_fence)
+			return -EINVAL;
+
+		/*
+		 * Wait if the fence is from a foreign context, or if the fence
+		 * array contains any fence from a foreign context.
+		 */
+		ret = 0;
+		if (!dma_fence_match_context(in_fence, vgdev->fence_drv.context))
+			ret = dma_fence_wait(in_fence, true);
+
+		dma_fence_put(in_fence);
+		if (ret)
+			return ret;
+	}
+
+	if (exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) {
+		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
+		if (out_fence_fd < 0)
+			return out_fence_fd;
+	}
+
 	INIT_LIST_HEAD(&validate_list);
 	if (exbuf->num_bo_handles) {
 
@@ -133,26 +164,22 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 					   sizeof(struct ttm_validate_buffer),
 					   GFP_KERNEL | __GFP_ZERO);
 		if (!bo_handles || !buflist) {
-			kvfree(bo_handles);
+			ret = -ENOMEM;
-			kvfree(buflist);
+			goto out_unused_fd;
-			return -ENOMEM;
 		}
 
 		user_bo_handles = (void __user *)(uintptr_t)exbuf->bo_handles;
 		if (copy_from_user(bo_handles, user_bo_handles,
 				   exbuf->num_bo_handles * sizeof(uint32_t))) {
 			ret = -EFAULT;
-			kvfree(bo_handles);
+			goto out_unused_fd;
-			kvfree(buflist);
-			return ret;
 		}
 
 		for (i = 0; i < exbuf->num_bo_handles; i++) {
 			gobj = drm_gem_object_lookup(drm_file, bo_handles[i]);
 			if (!gobj) {
-				kvfree(bo_handles);
+				ret = -ENOENT;
-				kvfree(buflist);
+				goto out_unused_fd;
-				return -ENOENT;
 			}
 
 			qobj = gem_to_virtio_gpu_obj(gobj);
@@ -161,6 +188,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 			list_add(&buflist[i].head, &validate_list);
 		}
 		kvfree(bo_handles);
+		bo_handles = NULL;
 	}
 
 	ret = virtio_gpu_object_list_validate(&ticket, &validate_list);
@@ -174,28 +202,47 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 		goto out_unresv;
 	}
 
-	fence = virtio_gpu_fence_alloc(vgdev);
+	out_fence = virtio_gpu_fence_alloc(vgdev);
-	if (!fence) {
+	if(!out_fence) {
-		kfree(buf);
 		ret = -ENOMEM;
-		goto out_unresv;
+		goto out_memdup;
 	}
-	virtio_gpu_cmd_submit(vgdev, buf, exbuf->size,
-			      vfpriv->ctx_id, &fence);
 
-	ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f);
+	if (out_fence_fd >= 0) {
+		sync_file = sync_file_create(&out_fence->f);
+		if (!sync_file) {
+			dma_fence_put(&out_fence->f);
+			ret = -ENOMEM;
+			goto out_memdup;
+		}
+
+		exbuf->fence_fd = out_fence_fd;
+		fd_install(out_fence_fd, sync_file->file);
+	}
+
+	virtio_gpu_cmd_submit(vgdev, buf, exbuf->size,
+			      vfpriv->ctx_id, &out_fence);
+
+	ttm_eu_fence_buffer_objects(&ticket, &validate_list, &out_fence->f);
 
 	/* fence the command bo */
 	virtio_gpu_unref_list(&validate_list);
 	kvfree(buflist);
-	dma_fence_put(&fence->f);
 	return 0;
 
+out_memdup:
+	kfree(buf);
 out_unresv:
 	ttm_eu_backoff_reservation(&ticket, &validate_list);
 out_free:
 	virtio_gpu_unref_list(&validate_list);
+out_unused_fd:
+	kvfree(bo_handles);
 	kvfree(buflist);
+
+	if (out_fence_fd >= 0)
+		put_unused_fd(out_fence_fd);
+
 	return ret;
 }
 

include/uapi/drm/virtgpu_drm.h

@@ -66,7 +66,7 @@ struct drm_virtgpu_execbuffer {
 	__u64 command; /* void* */
 	__u64 bo_handles;
 	__u32 num_bo_handles;
-	__s32 fence_fd;
+	__s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */
 };
 
 #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */