similar to: [PATCH] drm/virtio: fix command submission with objects but without fence.

On Wed, Sep 04, 2019 at 04:10:30PM -0700, Chia-I Wu wrote: > On Wed, Sep 4, 2019 at 12:48 AM Gerd Hoffmann <kraxel at redhat.com> wrote: > > > > Only call virtio_gpu_array_add_fence if we actually have a fence. > > > > Fixes: da758d51968a ("drm/virtio: rework virtio_gpu_execbuffer_ioctl fencing") > > Signed-off-by: Gerd Hoffmann <kraxel at

Rework fencing workflow, starting with virtio_gpu_execbuffer_ioctl. Stop using ttm helpers, use the virtio_gpu_array_* helpers (which work on the reservation objects directly) instead. New workflow: (1) All gem objects needed by a command are added to a virtio_gpu_object_array. (2) All reservation objects will be locked (virtio_gpu_array_lock_resv). (3) virtio_gpu_fence_emit() completes

Rework fencing workflow, starting with virtio_gpu_execbuffer_ioctl. Stop using ttm helpers, use the virtio_gpu_array_* helpers (which work on the reservation objects directly) instead. New workflow: (1) All gem objects needed by a command are added to a virtio_gpu_object_array. (2) All reservation objects will be locked (virtio_gpu_array_lock_resv). (3) virtio_gpu_fence_emit() completes

Hi, > > if (fence) > > virtio_gpu_fence_emit(vgdev, hdr, fence); > > + if (vbuf->objs) { > > + virtio_gpu_array_add_fence(vbuf->objs, &fence->f); > > + virtio_gpu_array_unlock_resv(vbuf->objs); > > + } > This is with the spinlock held. Maybe we should move the >

Hi, > > if (fence) > > virtio_gpu_fence_emit(vgdev, hdr, fence); > > + if (vbuf->objs) { > > + virtio_gpu_array_add_fence(vbuf->objs, &fence->f); > > + virtio_gpu_array_unlock_resv(vbuf->objs); > > + } > This is with the spinlock held. Maybe we should move the >

On Wed, Sep 4, 2019 at 12:48 AM Gerd Hoffmann <kraxel at redhat.com> wrote: > > Only call virtio_gpu_array_add_fence if we actually have a fence. > > Fixes: da758d51968a ("drm/virtio: rework virtio_gpu_execbuffer_ioctl fencing") > Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> > --- > drivers/gpu/drm/virtio/virtgpu_vq.c | 9 +++++---- > 1 file

Replace virtqueue_kick by virtqueue_kick_prepare, which requires serialization, and virtqueue_notify, which does not. Repurpose the return values to indicate whether the vq should be notified. This fixes a lock contention with qemu host. When the guest calls vibad rtqueue_notify, the qemu vcpu thread exits the guest and waits for the qemu iothread to perform the MMIO. If the qemu iothread is

Replace virtqueue_kick by virtqueue_kick_prepare, which requires serialization, and virtqueue_notify, which does not. Repurpose the return values to indicate whether the vq should be notified. This fixes a lock contention with qemu host. When the guest calls vibad rtqueue_notify, the qemu vcpu thread exits the guest and waits for the qemu iothread to perform the MMIO. If the qemu iothread is

Split virtio_gpu_deinit(), move the drm shutdown and release to virtio_gpu_release(). Drop vqs_ready variable, instead use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. v4: add changelog. v3: use drm_dev_*(). Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++-

Split virtio_gpu_deinit(), move the drm shutdown and release to virtio_gpu_release(). Drop vqs_ready variable, instead use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. v4: add changelog. v3: use drm_dev_*(). Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++-

On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann <kraxel at redhat.com> wrote: > > Rework fencing workflow, starting with virtio_gpu_execbuffer_ioctl. > Stop using ttm helpers, use the virtio_gpu_array_* helpers (which work > on the reservation objects directly) instead. > > New workflow: > > (1) All gem objects needed by a command are added to a >

Switch to the virtio_gpu_array_* helper workflow. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 2 +- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 43 ++++++++++++-------------- drivers/gpu/drm/virtio/virtgpu_vq.c | 5 ++- 3 files changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h

Switch to the virtio_gpu_array_* helper workflow. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 2 +- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 43 ++++++++++++-------------- drivers/gpu/drm/virtio/virtgpu_vq.c | 5 ++- 3 files changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h

Switch to the virtio_gpu_array_* helper workflow. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 35 +++++++++++--------------- drivers/gpu/drm/virtio/virtgpu_vq.c | 8 ++++-- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h

Switch to the virtio_gpu_array_* helper workflow. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 35 +++++++++++--------------- drivers/gpu/drm/virtio/virtgpu_vq.c | 8 ++++-- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h

Move virtio_gpu_notify() to higher-level functions for virtio_gpu_cmd_create_resource(), virtio_gpu_cmd_resource_create_3d() and virtio_gpu_cmd_resource_attach_backing(). virtio_gpu_object_create() will batch commands and notify only once when creating a resource. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_object.c | 1 +

Rework fencing workflow, starting with virtio_gpu_execbuffer_ioctl. Stop using ttm helpers, use the virtio_gpu_array_* helpers (which work on the reservation objects directly) instead. Also store the object array in struct virtio_gpu_vbuffer, so we explicitly keep a reference of all buffers used instead of depending on ttm_bo_put() checking whenever the object is actually idle before releasing

Add new virtio_gpu_cleanup_object() helper function for object cleanup. Wire up callback function for resource unref, do cleanup from callback when we know the host stopped using the resource. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_object.c | 19 ++++++++++----

Add new virtio_gpu_cleanup_object() helper function for object cleanup. Wire up callback function for resource unref, do cleanup from callback when we know the host stopped using the resource. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_object.c | 19 ++++++++++----

Some helper functions to manage an array of gem objects. v6: - add ticket to struct virtio_gpu_object_array. - add virtio_gpu_array_{lock,unlock}_resv helpers. - add virtio_gpu_array_add_fence helper. v5: some small optimizations (Chia-I Wu). v4: make them virtio-private instead of generic helpers. Signed-off-by: Gerd Hoffmann <kraxel at redhat.com> ---