6.5-stable review patch. If anyone has any objections, please let me know. ------------------ From: Gurchetan Singh <gurchetansingh@xxxxxxxxxxxx> 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@xxxxxxxxxxxx> Reviewed-by: Dmitry Osipenko <dmitry.osipenko@xxxxxxxxxxxxx> Tested-by: Dmitry Osipenko <dmitry.osipenko@xxxxxxxxxxxxx> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@xxxxxxxxxxxxx> # edited coding style Link: https://patchwork.freedesktop.org/patch/msgid/20230707213124.494-1-gurchetansingh@xxxxxxxxxxxx Signed-off-by: Alyssa Ross <hi@xxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- 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;
