drm/virtio: Conditionally allocate virtio_gpu_fence

commit 70d1ace56db6c79d39dbe9c0d5244452b67e2fde upstream.

We don't want to create a fence for every command submission.  It's
only necessary when userspace provides a waitable token for submission.
This could be:

1) bo_handles, to be used with VIRTGPU_WAIT
2) out_fence_fd, to be used with dma_fence apis
3) a ring_idx provided with VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK
   + DRM event API
4) syncobjs in the future

The use case for just submitting a command to the host, and expecting
no response.  For example, gfxstream has GFXSTREAM_CONTEXT_PING that
just wakes up the host side worker threads.  There's also
CROSS_DOMAIN_CMD_SEND which just sends data to the Wayland server.

This prevents the need to signal the automatically created
virtio_gpu_fence.

In addition, VIRTGPU_EXECBUF_RING_IDX is checked when creating a
DRM event object.  VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is
already defined in terms of per-context rings.  It was theoretically
possible to create a DRM event on the global timeline (ring_idx == 0),
if the context enabled DRM event polling.  However, that wouldn't
work and userspace (Sommelier).  Explicitly disallow it for
clarity.

Signed-off-by: Gurchetan Singh <gurchetansingh@chromium.org>
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com> # edited coding style
Link: https://patchwork.freedesktop.org/patch/msgid/20230707213124.494-1-gurchetansingh@chromium.org
Signed-off-by: Alyssa Ross <hi@alyssa.is>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index da45215..bc8c1e9 100644 (file)
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -43,13 +43,9 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev,
                                         struct virtio_gpu_fence *fence,
                                         uint32_t ring_idx)
 {
-       struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
        struct virtio_gpu_fence_event *e = NULL;
        int ret;
 
-       if (!(vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
-               return 0;
-
        e = kzalloc(sizeof(*e), GFP_KERNEL);
        if (!e)
                return -ENOMEM;
@@ -121,6 +117,7 @@ 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 = file->driver_priv;
        struct virtio_gpu_fence *out_fence;
+       bool drm_fence_event;
        int ret;
        uint32_t *bo_handles = NULL;
        void __user *user_bo_handles = NULL;
@@ -216,15 +213,24 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
                        goto out_memdup;
        }
 
-       out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
-       if(!out_fence) {
-               ret = -ENOMEM;
-               goto out_unresv;
-       }
+       if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX) &&
+           (vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
+               drm_fence_event = true;
+       else
+               drm_fence_event = false;
 
-       ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
-       if (ret)
-               goto out_unresv;
+       if ((exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) ||
+           exbuf->num_bo_handles ||
+           drm_fence_event)
+               out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
+       else
+               out_fence = NULL;
+
+       if (drm_fence_event) {
+               ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
+               if (ret)
+                       goto out_unresv;
+       }
 
        if (out_fence_fd >= 0) {
                sync_file = sync_file_create(&out_fence->f);