--- /dev/null
+From 70d1ace56db6c79d39dbe9c0d5244452b67e2fde Mon Sep 17 00:00:00 2001
+From: Gurchetan Singh <gurchetansingh@chromium.org>
+Date: Fri, 7 Jul 2023 14:31:24 -0700
+Subject: drm/virtio: Conditionally allocate virtio_gpu_fence
+
+From: Gurchetan Singh <gurchetansingh@chromium.org>
+
+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>
+---
+ drivers/gpu/drm/virtio/virtgpu_submit.c | 32 ++++++++++++++++++++------------
+ 1 file changed, 20 insertions(+), 12 deletions(-)
+
+--- a/drivers/gpu/drm/virtio/virtgpu_submit.c
++++ b/drivers/gpu/drm/virtio/virtgpu_submit.c
+@@ -64,13 +64,9 @@ static int virtio_gpu_fence_event_create
+ struct virtio_gpu_fence *fence,
+ u32 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;
+@@ -164,18 +160,30 @@ static int virtio_gpu_init_submit(struct
+ struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
+ struct virtio_gpu_device *vgdev = dev->dev_private;
+ struct virtio_gpu_fence *out_fence;
++ bool drm_fence_event;
+ int err;
+
+ memset(submit, 0, sizeof(*submit));
+
+- out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
+- if (!out_fence)
+- return -ENOMEM;
+-
+- err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
+- if (err) {
+- dma_fence_put(&out_fence->f);
+- return err;
++ if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX) &&
++ (vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
++ drm_fence_event = true;
++ else
++ drm_fence_event = false;
++
++ 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) {
++ err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
++ if (err) {
++ dma_fence_put(&out_fence->f);
++ return err;
++ }
+ }
+
+ submit->out_fence = out_fence;