[PATCH v5 0/4] virgl: fence fd support

[PATCH v5 0/4] virgl: fence fd support

[Robert Foss]

This series implements fence support for drm/virtio and
has been tested using qemu, kmscube and the below branches.

Rob Herring solved a reference counting issue and
suggested a context check for the execbuf ioctl, his
changes have been included in the below commits to
keep the tree working at all commits.


The linux series can be found here:
https://gitlab.collabora.com/robertfoss/linux/commits/virtio_fences_v5

As for mesa, the branch can be found here:
https://gitlab.collabora.com/robertfoss/mesa/commits/virtio_fences_v3


Changes since v4:
 - drm/virtio: add uapi for in and out explicit fences
   - Emil/Gerd: Improved commit message and fence_fd comment

Changes since v3:
 - Rebased on drm-misc-next
 - drm/virtio: add virtio_gpu_alloc_fence()
   - Gerd: Clarified and extended commit message
   - Emil: Fixed whitespace issue
   - Emil: Changed label name from fail_fence to fail_backoff
   - Emil: Remove special case for !fence->drv in virtio_gpu_fence_cleanup()
 - drm/virtio: add uapi for in and out explicit fences
   - Emil: Added r-b
   - Emil: Move fence_fd assignment to after sanity checks
 - drm/virtio: add in-fences support for explicit synchronization
   - Move all in_fence handling to the same VIRTGPU_EXECBUF_FENCE_FD_IN block
   - Emil: Make sure to always call dma_fence_put()
   - Emil: Added r-b
 - drm/virtio: add out-fences support for explicit synchronization
   - Emil: Combine with in-fences patch
 -  drm/virtio: bump driver version after explicit synchronization addition
   - Emil: Added r-b

Changes since v2:
 - drm/virtio: add virtio_gpu_alloc_fence()
   - Forward port and fix compilation issues
 - drm/virtio: add uapi for in and out explicit fences
   - Check exbuf->flags for unsupported flags
 - drm/virtio: add in-fences support for explicit synchronization


Gustavo Padovan (1):
  drm/virtio: bump driver version after explicit synchronization
    addition

Robert Foss (3):
  drm/virtio: add virtio_gpu_alloc_fence()
  drm/virtio: add uapi for in and out explicit fences
  drm/virtio: add in/out fence support for explicit synchronization

 drivers/gpu/drm/virtio/virtgpu_drv.h   |   8 +-
 drivers/gpu/drm/virtio/virtgpu_fence.c |  29 +++++--
 drivers/gpu/drm/virtio/virtgpu_ioctl.c | 108 +++++++++++++++++++++----
 drivers/gpu/drm/virtio/virtgpu_plane.c |  46 +++++++++--
 drivers/gpu/drm/virtio/virtgpu_vq.c    |   2 +-
 include/uapi/drm/virtgpu_drm.h         |  13 ++-
 6 files changed, 173 insertions(+), 33 deletions(-)

-- 
2.17.1

[PATCH v5 1/4] drm/virtio: add virtio_gpu_alloc_fence()

[Robert Foss]

Refactor fence creation, add fences to relevant GPU
operations and add cursor helper functions.

This removes the potential for allocation failures from the
cmd_submit and atomic_commit paths.
Now a fence will be allocated first and only after that
will we proceed with the rest of the execution.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Signed-off-by: Robert Foss <robert.foss@collabora.com>
Suggested-by: Rob Herring <robh@kernel.org>
---

Changes since v3:
 - Gerd: Clarified and extended commit message
 - Emil: Fixed whitespace issue
 - Emil: Changed label name from fail_fence to fail_backoff
 - Emil: Remove special case for !fence->drv in virtio_gpu_fence_cleanup()

 drivers/gpu/drm/virtio/virtgpu_drv.h   |  4 +++
 drivers/gpu/drm/virtio/virtgpu_fence.c | 29 ++++++++++++----
 drivers/gpu/drm/virtio/virtgpu_ioctl.c | 30 +++++++++++++++--
 drivers/gpu/drm/virtio/virtgpu_plane.c | 46 +++++++++++++++++++++++---
 drivers/gpu/drm/virtio/virtgpu_vq.c    |  2 +-
 5 files changed, 96 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 6474e83cbf3d..acd130c58e33 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -131,6 +131,7 @@ struct virtio_gpu_framebuffer {
 	int x1, y1, x2, y2; /* dirty rect */
 	spinlock_t dirty_lock;
 	uint32_t hw_res_handle;
+	struct virtio_gpu_fence *fence;
 };
 #define to_virtio_gpu_framebuffer(x) \
 	container_of(x, struct virtio_gpu_framebuffer, base)
@@ -349,6 +350,9 @@ void virtio_gpu_ttm_fini(struct virtio_gpu_device *vgdev);
 int virtio_gpu_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /* virtio_gpu_fence.c */
+struct virtio_gpu_fence *virtio_gpu_fence_alloc(
+	struct virtio_gpu_device *vgdev);
+void virtio_gpu_fence_cleanup(struct virtio_gpu_fence *fence);
 int virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev,
 			  struct virtio_gpu_ctrl_hdr *cmd_hdr,
 			  struct virtio_gpu_fence **fence);
diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c
index 00c742a441bf..6b5d92215cfb 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fence.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fence.c
@@ -67,6 +67,28 @@ static const struct dma_fence_ops virtio_fence_ops = {
 	.timeline_value_str  = virtio_timeline_value_str,
 };
 
+struct virtio_gpu_fence *virtio_gpu_fence_alloc(struct virtio_gpu_device *vgdev)
+{
+	struct virtio_gpu_fence_driver *drv = &vgdev->fence_drv;
+	struct virtio_gpu_fence *fence = kzalloc(sizeof(struct virtio_gpu_fence),
+							GFP_ATOMIC);
+	if (!fence)
+		return fence;
+
+	fence->drv = drv;
+	dma_fence_init(&fence->f, &virtio_fence_ops, &drv->lock, drv->context, 0);
+
+	return fence;
+}
+
+void virtio_gpu_fence_cleanup(struct virtio_gpu_fence *fence)
+{
+	if (!fence)
+		return;
+
+	dma_fence_put(&fence->f);
+}
+
 int virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev,
 			  struct virtio_gpu_ctrl_hdr *cmd_hdr,
 			  struct virtio_gpu_fence **fence)
@@ -74,15 +96,8 @@ int virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_fence_driver *drv = &vgdev->fence_drv;
 	unsigned long irq_flags;
 
-	*fence = kmalloc(sizeof(struct virtio_gpu_fence), GFP_ATOMIC);
-	if ((*fence) == NULL)
-		return -ENOMEM;
-
 	spin_lock_irqsave(&drv->lock, irq_flags);
-	(*fence)->drv = drv;
 	(*fence)->seq = ++drv->sync_seq;
-	dma_fence_init(&(*fence)->f, &virtio_fence_ops, &drv->lock,
-		       drv->context, (*fence)->seq);
 	dma_fence_get(&(*fence)->f);
 	list_add_tail(&(*fence)->node, &drv->fences);
 	spin_unlock_irqrestore(&drv->lock, irq_flags);
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index bc5afa4f906e..d69fc356df0a 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -168,6 +168,13 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 		ret = PTR_ERR(buf);
 		goto out_unresv;
 	}
+
+	fence = virtio_gpu_fence_alloc(vgdev);
+	if (!fence) {
+		kfree(buf);
+		ret = -ENOMEM;
+		goto out_unresv;
+	}
 	virtio_gpu_cmd_submit(vgdev, buf, exbuf->size,
 			      vfpriv->ctx_id, &fence);
 
@@ -283,11 +290,17 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data,
 		rc_3d.nr_samples = cpu_to_le32(rc->nr_samples);
 		rc_3d.flags = cpu_to_le32(rc->flags);
 
+		fence = virtio_gpu_fence_alloc(vgdev);
+		if (!fence) {
+			ret = -ENOMEM;
+			goto fail_backoff;
+		}
+
 		virtio_gpu_cmd_resource_create_3d(vgdev, qobj, &rc_3d, NULL);
 		ret = virtio_gpu_object_attach(vgdev, qobj, &fence);
 		if (ret) {
-			ttm_eu_backoff_reservation(&ticket, &validate_list);
-			goto fail_unref;
+			virtio_gpu_fence_cleanup(fence);
+			goto fail_backoff;
 		}
 		ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f);
 	}
@@ -312,6 +325,8 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data,
 		dma_fence_put(&fence->f);
 	}
 	return 0;
+fail_backoff:
+	ttm_eu_backoff_reservation(&ticket, &validate_list);
 fail_unref:
 	if (vgdev->has_virgl_3d) {
 		virtio_gpu_unref_list(&validate_list);
@@ -374,6 +389,12 @@ static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev,
 		goto out_unres;
 
 	convert_to_hw_box(&box, &args->box);
+
+	fence = virtio_gpu_fence_alloc(vgdev);
+	if (!fence) {
+		ret = -ENOMEM;
+		goto out_unres;
+	}
 	virtio_gpu_cmd_transfer_from_host_3d
 		(vgdev, qobj->hw_res_handle,
 		 vfpriv->ctx_id, offset, args->level,
@@ -423,6 +444,11 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
 			(vgdev, qobj, offset,
 			 box.w, box.h, box.x, box.y, NULL);
 	} else {
+		fence = virtio_gpu_fence_alloc(vgdev);
+		if (!fence) {
+			ret = -ENOMEM;
+			goto out_unres;
+		}
 		virtio_gpu_cmd_transfer_to_host_3d
 			(vgdev, qobj,
 			 vfpriv ? vfpriv->ctx_id : 0, offset,
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index a9f4ae7d4483..b84ac8c25856 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -137,6 +137,41 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 				      plane->state->src_h >> 16);
 }
 
+static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane,
+					struct drm_plane_state *new_state)
+{
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_object *bo;
+
+	if (!new_state->fb)
+		return 0;
+
+	vgfb = to_virtio_gpu_framebuffer(new_state->fb);
+	bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
+	if (bo && bo->dumb && (plane->state->fb != new_state->fb)) {
+		vgfb->fence = virtio_gpu_fence_alloc(vgdev);
+		if (!vgfb->fence)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void virtio_gpu_cursor_cleanup_fb(struct drm_plane *plane,
+					 struct drm_plane_state *old_state)
+{
+	struct virtio_gpu_framebuffer *vgfb;
+
+	if (!plane->state->fb)
+		return;
+
+	vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+	if (vgfb->fence)
+		virtio_gpu_fence_cleanup(vgfb->fence);
+}
+
 static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 					   struct drm_plane_state *old_state)
 {
@@ -144,7 +179,6 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_output *output = NULL;
 	struct virtio_gpu_framebuffer *vgfb;
-	struct virtio_gpu_fence *fence = NULL;
 	struct virtio_gpu_object *bo = NULL;
 	uint32_t handle;
 	int ret = 0;
@@ -170,13 +204,13 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 			(vgdev, bo, 0,
 			 cpu_to_le32(plane->state->crtc_w),
 			 cpu_to_le32(plane->state->crtc_h),
-			 0, 0, &fence);
+			 0, 0, &vgfb->fence);
 		ret = virtio_gpu_object_reserve(bo, false);
 		if (!ret) {
 			reservation_object_add_excl_fence(bo->tbo.resv,
-							  &fence->f);
-			dma_fence_put(&fence->f);
-			fence = NULL;
+							  &vgfb->fence->f);
+			dma_fence_put(&vgfb->fence->f);
+			vgfb->fence = NULL;
 			virtio_gpu_object_unreserve(bo);
 			virtio_gpu_object_wait(bo, false);
 		}
@@ -218,6 +252,8 @@ static const struct drm_plane_helper_funcs virtio_gpu_primary_helper_funcs = {
 };
 
 static const struct drm_plane_helper_funcs virtio_gpu_cursor_helper_funcs = {
+	.prepare_fb		= virtio_gpu_cursor_prepare_fb,
+	.cleanup_fb		= virtio_gpu_cursor_cleanup_fb,
 	.atomic_check		= virtio_gpu_plane_atomic_check,
 	.atomic_update		= virtio_gpu_cursor_plane_update,
 };
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 51bef1775e47..93f2c3a51ee8 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -896,9 +896,9 @@ void virtio_gpu_object_detach(struct virtio_gpu_device *vgdev,
 			      struct virtio_gpu_object *obj)
 {
 	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
-	struct virtio_gpu_fence *fence;
 
 	if (use_dma_api && obj->mapped) {
+		struct virtio_gpu_fence *fence = virtio_gpu_fence_alloc(vgdev);
 		/* detach backing and wait for the host process it ... */
 		virtio_gpu_cmd_resource_inval_backing(vgdev, obj->hw_res_handle, &fence);
 		dma_fence_wait(&fence->f, true);
-- 
2.17.1

[PATCH v5 2/4] drm/virtio: add uapi for in and out explicit fences

[Robert Foss]

Add a new field called fence_fd that will be used by userspace to send
in-fences to the kernel and receive out-fences created by the kernel.

This uapi enables virtio to take advantage of explicit synchronization of
dma-bufs.

There are two new flags:

* VIRTGPU_EXECBUF_FENCE_FD_IN to be used when passing an in-fence fd.
* VIRTGPU_EXECBUF_FENCE_FD_OUT to be used when requesting an out-fence fd

The execbuffer IOCTL is now read-write to allow the userspace to read the
out-fence.

On error -1 should be returned in the fence_fd field.

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>
---

Changes since v4:
 - Emil/Gerd: Improved commit message and fence_fd comment

Changes since v3:
 - Emil: Move fence_fd assignment to after sanity checks
 - Emil: Added r-b


 drivers/gpu/drm/virtio/virtgpu_ioctl.c |  5 +++++
 include/uapi/drm/virtgpu_drm.h         | 13 ++++++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index d69fc356df0a..3d497835b0f5 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -119,6 +119,11 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 	if (vgdev->has_virgl_3d == false)
 		return -ENOSYS;
 
+	if ((exbuf->flags & ~VIRTGPU_EXECBUF_FLAGS))
+		return -EINVAL;
+
+	exbuf->fence_fd = -1;
+
 	INIT_LIST_HEAD(&validate_list);
 	if (exbuf->num_bo_handles) {
 
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index 9a781f0611df..91062f4ac7c5 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -47,6 +47,13 @@ extern "C" {
 #define DRM_VIRTGPU_WAIT     0x08
 #define DRM_VIRTGPU_GET_CAPS  0x09
 
+#define VIRTGPU_EXECBUF_FENCE_FD_IN	0x01
+#define VIRTGPU_EXECBUF_FENCE_FD_OUT	0x02
+#define VIRTGPU_EXECBUF_FLAGS  (\
+		VIRTGPU_EXECBUF_FENCE_FD_IN |\
+		VIRTGPU_EXECBUF_FENCE_FD_OUT |\
+		0)
+
 struct drm_virtgpu_map {
 	__u64 offset; /* use for mmap system call */
 	__u32 handle;
@@ -54,12 +61,12 @@ struct drm_virtgpu_map {
 };
 
 struct drm_virtgpu_execbuffer {
-	__u32		flags;		/* for future use */
+	__u32 flags;
 	__u32 size;
 	__u64 command; /* void* */
 	__u64 bo_handles;
 	__u32 num_bo_handles;
-	__u32 pad;
+	__s32 fence_fd;
 };
 
 #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */
@@ -137,7 +144,7 @@ struct drm_virtgpu_get_caps {
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map)
 
 #define DRM_IOCTL_VIRTGPU_EXECBUFFER \
-	DRM_IOW(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\
 		struct drm_virtgpu_execbuffer)
 
 #define DRM_IOCTL_VIRTGPU_GETPARAM \
-- 
2.17.1

[PATCH v5 3/4] drm/virtio: add in/out fence support for explicit synchronization

[Robert Foss]

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>
Suggested-by: Rob Herring <robh@kernel.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
---

Changes since v3:
 - Move all in_fence handling to the same VIRTGPU_EXECBUF_FENCE_FD_IN block
 - Emil: Make sure to always call dma_fence_put()
 - Emil: Added r-b


 drivers/gpu/drm/virtio/virtgpu_ioctl.c | 81 ++++++++++++++++++++------
 include/uapi/drm/virtgpu_drm.h         |  2 +-
 2 files changed, 65 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 3d497835b0f5..340f2513d829 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/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);
-			kvfree(buflist);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto out_unused_fd;
 		}
 
 		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);
-			kvfree(buflist);
-			return ret;
+			goto out_unused_fd;
 		}
 
 		for (i = 0; i < exbuf->num_bo_handles; i++) {
 			gobj = drm_gem_object_lookup(drm_file, bo_handles[i]);
 			if (!gobj) {
-				kvfree(bo_handles);
-				kvfree(buflist);
-				return -ENOENT;
+				ret = -ENOENT;
+				goto out_unused_fd;
 			}
 
 			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);
-	if (!fence) {
-		kfree(buf);
+	out_fence = virtio_gpu_fence_alloc(vgdev);
+	if(!out_fence) {
 		ret = -ENOMEM;
-		goto out_unresv;
+		goto out_memdup;
+	}
+
+	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, &fence);
+			      vfpriv->ctx_id, &out_fence);
 
-	ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f);
+	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;
 }
 
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index 91062f4ac7c5..f06a789f34cd 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/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 */
-- 
2.17.1

[PATCH v5 4/4] drm/virtio: bump driver version after explicit synchronization addition

[Robert Foss]

From: Gustavo Padovan <gustavo.padovan@collabora.com>

To reflect the (backward compatible) changes in the uabi we are bumping
the driver's version.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co>
Signed-off-by: Robert Foss <robert.foss@collabora.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
---

Changes since v3:
 - Emil: Added r-b

 drivers/gpu/drm/virtio/virtgpu_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index acd130c58e33..4632bd7e1972 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -47,8 +47,8 @@
 #define DRIVER_DATE "0"
 
 #define DRIVER_MAJOR 0
-#define DRIVER_MINOR 0
-#define DRIVER_PATCHLEVEL 1
+#define DRIVER_MINOR 1
+#define DRIVER_PATCHLEVEL 0
 
 /* virtgpu_drm_bus.c */
 int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev);
-- 
2.17.1

Re: [PATCH v5 0/4] virgl: fence fd support

[Gerd Hoffmann]

On Mon, Nov 12, 2018 at 05:51:53PM +0100, Robert Foss wrote:
> 
> This series implements fence support for drm/virtio and
> has been tested using qemu, kmscube and the below branches.
> 
> Rob Herring solved a reference counting issue and
> suggested a context check for the execbuf ioctl, his
> changes have been included in the below commits to
> keep the tree working at all commits.

Patches added to qemu queue, should land in drm-misc-next soon.

thanks,
  Gerd