Skip to content

RFC mdev based hardware virtio offloading support

Jason Wang kvm lkml netdev virtualization 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 RFC Latest4 patches 24 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/4vringh: fix copy direction of vringh_iov_push_kern()drivers/vhost/vringh.c+7 -10 replies
2/4mdev: introduce helper to set per device dma opsdrivers/vfio/mdev/mdev_core.c include/linux/mdev.h+9 -00 replies
2/4mdev: introduce helper to set per device dma opsdrivers/vfio/mdev/mdev_core.c include/linux/mdev.h+9 -04 replies
3/4virtio: introudce a mdev based transportdrivers/vfio/mdev/Kconfig drivers/vfio/mdev/Makefile drivers/vfio/mdev/virtio_mdev.c +1 more+639 -016 replies
4/4docs: Sample driver to demonstrate how to implement virtio-mdev frameworksamples/Kconfig samples/vfio-mdev/Makefile samples/vfio-mdev/mvnet.c+774 -00 replies
4/4docs: Sample driver to demonstrate how to implement virtio-mdev frameworksamples/Kconfig samples/vfio-mdev/Makefile samples/vfio-mdev/mvnet.c+774 -04 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.

Read the v1 thread

Cover letter [RFC PATCH 0/4] mdev based hardware virtio offloading support

Hi all:

There are hardware that can do virtio datapath offloading while having its own control path. This path tries to implement a mdev based unified API to support using kernel virtio driver to drive those devices. This is done by introducing a new mdev transport for virtio (virtio_mdev) and register itself as a new kind of mdev driver. Then it provides a unified way for kernel virtio driver to talk with mdev device implementation.

Though the series only contain kernel driver support, the goal is to make the transport generic enough to support userspace drivers. This means vhost-mdev[1] could be built on top as well by resuing the transport.

A sample driver is also implemented which simulate a virito-net loopback ethernet device on top of vringh + workqueue. This could be used as a reference implementation for real hardware driver.

Notes:

- Some of the key transport command for vhost-mdev(userspace driver) is not introduced. This includes:
1) set/get virtqueue state (idx etc), this could be simply done by introducing new transport command
2) dirty pages tracking, could be simply done by introducing new transport command
3) set/get device internal state, this requires more thought, of course we can introduce device specific transport command, but it would be better to have a unified API
- Current mdev_parent_ops assumes all pointers are userspace pointer, this block the kernel driver, this series just abuse those as kernel pointer and this could be addressed by inventing new parent_ops.
- For quick POC, mdev transport was just derived from virtio-MMIO, I'm pretty sure it has lots of space to be optimized, please share your thought.

Please review.

[1] https://lkml.org/lkml/2019/8/28/35

Jason Wang (4):
vringh: fix copy direction of vringh_iov_push_kern()
mdev: introduce helper to set per device dma ops
virtio: introudce a mdev based transport
docs: Sample driver to demonstrate how to implement virtio-mdev
framework

 drivers/vfio/mdev/Kconfig        |   7 +
 drivers/vfio/mdev/Makefile       |   1 +
 drivers/vfio/mdev/mdev_core.c    |   7 +
 drivers/vfio/mdev/virtio_mdev.c  | 500 ++++++++++++++++++++
 drivers/vhost/vringh.c           |   8 +-
 include/linux/mdev.h             |   2 +
 include/uapi/linux/virtio_mdev.h | 131 ++++++
 samples/Kconfig                  |   7 +
 samples/vfio-mdev/Makefile       |   1 +
 samples/vfio-mdev/mvnet.c        | 766 +++++++++++++++++++++++++++++++
 10 files changed, 1429 insertions(+), 1 deletion(-)
 create mode 100644 drivers/vfio/mdev/virtio_mdev.c
 create mode 100644 include/uapi/linux/virtio_mdev.h
 create mode 100644 samples/vfio-mdev/mvnet.c
Signature · 1 line
2.19.1