kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: eperezma@redhat.com, kvm@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	lulu@redhat.com, eli@mellanox.com, lingshan.zhu@intel.com,
	rob.miller@broadcom.com, stefanha@redhat.com,
	sgarzare@redhat.com
Subject: Re: [PATCH 00/21] Control VQ support in vDPA
Date: Thu, 17 Dec 2020 11:30:18 +0800	[thread overview]
Message-ID: <aa061fcb-9395-3a1b-5d6e-76b5454dfb6c@redhat.com> (raw)
In-Reply-To: <20201216044051-mutt-send-email-mst@kernel.org>


On 2020/12/16 下午5:47, Michael S. Tsirkin wrote:
> On Wed, Dec 16, 2020 at 02:47:57PM +0800, Jason Wang wrote:
>> Hi All:
>>
>> This series tries to add the support for control virtqueue in vDPA.
>>
>> Control virtqueue is used by networking device for accepting various
>> commands from the driver. It's a must to support multiqueue and other
>> configurations.
>>
>> When used by vhost-vDPA bus driver for VM, the control virtqueue
>> should be shadowed via userspace VMM (Qemu) instead of being assigned
>> directly to Guest. This is because Qemu needs to know the device state
>> in order to start and stop device correctly (e.g for Live Migration).
>>
>> This requies to isolate the memory mapping for control virtqueue
>> presented by vhost-vDPA to prevent guest from accesing it directly.
>> To achieve this, vDPA introduce two new abstractions:
>>
>> - address space: identified through address space id (ASID) and a set
>>                   of memory mapping in maintained
>> - virtqueue group: the minimal set of virtqueues that must share an
>>                   address space
> How will this support the pretty common case where control vq
> is programmed by the kernel through the PF, and others by the VFs?


In this case, the VF parent need to provide a software control vq and 
decode the command then send them to VF.


>
>
> I actually thought the way to support it is by exposing
> something like an "inject buffers" API which sends data to a given VQ.
> Maybe an ioctl, and maybe down the road uio ring can support batching
> these ....


So the virtuqueue allows the request to be processed asynchronously (e.g 
driver may choose to use interrupt for control vq). This means we need 
to support that in uAPI level. And if we manage to do that, it's just 
another type of virtqueue.

For virtio-vDPA, this also means the extensions for queue processing 
which is a functional duplication. Using what proposed in this series, 
we don't need any changes for kernel virtio drivers.

What's more important, this series could be used for future features 
that requires DMA isolation between virtqueues:

- report dirty pages via virtqueue
- sub function level device slicing

...

Thanks


>
>
>> Device needs to advertise the following attributes to vDPA:
>>
>> - the number of address spaces supported in the device
>> - the number of virtqueue groups supported in the device
>> - the mappings from a specific virtqueue to its virtqueue groups
>>
>> The mappings from virtqueue to virtqueue groups is fixed and defined
>> by vDPA device driver. E.g:
>>
>> - For the device that has hardware ASID support, it can simply
>>    advertise a per virtqueue virtqueue group.
>> - For the device that does not have hardware ASID support, it can
>>    simply advertise a single virtqueue group that contains all
>>    virtqueues. Or if it wants a software emulated control virtqueue, it
>>    can advertise two virtqueue groups, one is for cvq, another is for
>>    the rest virtqueues.
>>
>> vDPA also allow to change the association between virtqueue group and
>> address space. So in the case of control virtqueue, userspace
>> VMM(Qemu) may use a dedicated address space for the control virtqueue
>> group to isolate the memory mapping.
>>
>> The vhost/vhost-vDPA is also extend for the userspace to:
>>
>> - query the number of virtqueue groups and address spaces supported by
>>    the device
>> - query the virtqueue group for a specific virtqueue
>> - assocaite a virtqueue group with an address space
>> - send ASID based IOTLB commands
>>
>> This will help userspace VMM(Qemu) to detect whether the control vq
>> could be supported and isolate memory mappings of control virtqueue
>> from the others.
>>
>> To demonstrate the usage, vDPA simulator is extended to support
>> setting MAC address via a emulated control virtqueue.
>>
>> Please review.
>>
>> Changes since RFC:
>>
>> - tweak vhost uAPI documentation
>> - switch to use device specific IOTLB really in patch 4
>> - tweak the commit log
>> - fix that ASID in vhost is claimed to be 32 actually but 16bit
>>    actually
>> - fix use after free when using ASID with IOTLB batching requests
>> - switch to use Stefano's patch for having separated iov
>> - remove unused "used_as" variable
>> - fix the iotlb/asid checking in vhost_vdpa_unmap()
>>
>> Thanks
>>
>> Jason Wang (20):
>>    vhost: move the backend feature bits to vhost_types.h
>>    virtio-vdpa: don't set callback if virtio doesn't need it
>>    vhost-vdpa: passing iotlb to IOMMU mapping helpers
>>    vhost-vdpa: switch to use vhost-vdpa specific IOTLB
>>    vdpa: add the missing comment for nvqs in struct vdpa_device
>>    vdpa: introduce virtqueue groups
>>    vdpa: multiple address spaces support
>>    vdpa: introduce config operations for associating ASID to a virtqueue
>>      group
>>    vhost_iotlb: split out IOTLB initialization
>>    vhost: support ASID in IOTLB API
>>    vhost-vdpa: introduce asid based IOTLB
>>    vhost-vdpa: introduce uAPI to get the number of virtqueue groups
>>    vhost-vdpa: introduce uAPI to get the number of address spaces
>>    vhost-vdpa: uAPI to get virtqueue group id
>>    vhost-vdpa: introduce uAPI to set group ASID
>>    vhost-vdpa: support ASID based IOTLB API
>>    vdpa_sim: advertise VIRTIO_NET_F_MTU
>>    vdpa_sim: factor out buffer completion logic
>>    vdpa_sim: filter destination mac address
>>    vdpasim: control virtqueue support
>>
>> Stefano Garzarella (1):
>>    vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
>>
>>   drivers/vdpa/ifcvf/ifcvf_main.c   |   9 +-
>>   drivers/vdpa/mlx5/net/mlx5_vnet.c |  11 +-
>>   drivers/vdpa/vdpa.c               |   8 +-
>>   drivers/vdpa/vdpa_sim/vdpa_sim.c  | 292 ++++++++++++++++++++++++------
>>   drivers/vhost/iotlb.c             |  23 ++-
>>   drivers/vhost/vdpa.c              | 246 ++++++++++++++++++++-----
>>   drivers/vhost/vhost.c             |  23 ++-
>>   drivers/vhost/vhost.h             |   4 +-
>>   drivers/virtio/virtio_vdpa.c      |   2 +-
>>   include/linux/vdpa.h              |  42 ++++-
>>   include/linux/vhost_iotlb.h       |   2 +
>>   include/uapi/linux/vhost.h        |  25 ++-
>>   include/uapi/linux/vhost_types.h  |  10 +-
>>   13 files changed, 561 insertions(+), 136 deletions(-)
>>
>> -- 
>> 2.25.1


  reply	other threads:[~2020-12-17  3:32 UTC|newest]

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-16  6:47 [PATCH 00/21] Control VQ support in vDPA Jason Wang
2020-12-16  6:47 ` [PATCH 01/21] vhost: move the backend feature bits to vhost_types.h Jason Wang
2020-12-16  6:47 ` [PATCH 02/21] virtio-vdpa: don't set callback if virtio doesn't need it Jason Wang
2020-12-16  6:48 ` [PATCH 03/21] vhost-vdpa: passing iotlb to IOMMU mapping helpers Jason Wang
2020-12-16  6:48 ` [PATCH 04/21] vhost-vdpa: switch to use vhost-vdpa specific IOTLB Jason Wang
2020-12-16  6:48 ` [PATCH 05/21] vdpa: add the missing comment for nvqs in struct vdpa_device Jason Wang
2020-12-16  6:48 ` [PATCH 06/21] vdpa: introduce virtqueue groups Jason Wang
2021-01-04 10:04   ` Stefan Hajnoczi
2021-01-05  4:13     ` Jason Wang
2020-12-16  6:48 ` [PATCH 07/21] vdpa: multiple address spaces support Jason Wang
2020-12-29  7:28   ` Eli Cohen
2020-12-30  4:00     ` Jason Wang
2020-12-30  4:04     ` Jason Wang
2020-12-30  9:44       ` Eli Cohen
2020-12-16  6:48 ` [PATCH 08/21] vdpa: introduce config operations for associating ASID to a virtqueue group Jason Wang
2020-12-16  6:48 ` [PATCH 09/21] vhost_iotlb: split out IOTLB initialization Jason Wang
2020-12-16  6:48 ` [PATCH 10/21] vhost: support ASID in IOTLB API Jason Wang
2020-12-29 10:20   ` Eli Cohen
2020-12-30  4:27     ` Jason Wang
2020-12-16  6:48 ` [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB Jason Wang
2020-12-29 11:41   ` Eli Cohen
2020-12-30  6:23     ` Jason Wang
2020-12-29 11:53   ` Eli Cohen
2020-12-30  6:34     ` Jason Wang
2020-12-29 12:05   ` Eli Cohen
2020-12-30  6:33     ` Jason Wang
2020-12-16  6:48 ` [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups Jason Wang
2020-12-29 12:24   ` Eli Cohen
2020-12-30  6:49     ` Jason Wang
2020-12-30 10:05   ` Eli Cohen
2020-12-31  2:36     ` Jason Wang
2020-12-16  6:48 ` [PATCH 13/21] vhost-vdpa: introduce uAPI to get the number of address spaces Jason Wang
2020-12-16  6:48 ` [PATCH 14/21] vhost-vdpa: uAPI to get virtqueue group id Jason Wang
2020-12-16  6:48 ` [PATCH 15/21] vhost-vdpa: introduce uAPI to set group ASID Jason Wang
2020-12-16  6:48 ` [PATCH 16/21] vhost-vdpa: support ASID based IOTLB API Jason Wang
2020-12-16  6:48 ` [PATCH 17/21] vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov Jason Wang
2020-12-16  6:48 ` [PATCH 18/21] vdpa_sim: advertise VIRTIO_NET_F_MTU Jason Wang
2020-12-16  6:48 ` [PATCH 19/21] vdpa_sim: factor out buffer completion logic Jason Wang
2020-12-16  6:48 ` [PATCH 20/21] vdpa_sim: filter destination mac address Jason Wang
2020-12-16  6:48 ` [PATCH 21/21] vdpasim: control virtqueue support Jason Wang
2020-12-17 20:19   ` kernel test robot
2021-01-11 12:26   ` Eli Cohen
2021-01-12  3:11     ` Jason Wang
2021-01-22 19:43       ` Eugenio Perez Martin
2021-01-25  3:16         ` Jason Wang
2020-12-16  9:47 ` [PATCH 00/21] Control VQ support in vDPA Michael S. Tsirkin
2020-12-17  3:30   ` Jason Wang [this message]
2020-12-17  7:58     ` Michael S. Tsirkin
2020-12-17  9:02       ` Jason Wang
2020-12-17 22:28         ` Michael S. Tsirkin
2020-12-18  2:56           ` Jason Wang
2020-12-17  7:26 ` Eli Cohen
2022-02-24 21:22 ` [RFC PATCH v2 00/19] " Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 01/19] vhost: move the backend feature bits to vhost_types.h Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 02/19] virtio-vdpa: don't set callback if virtio doesn't need it Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 03/19] vhost-vdpa: passing iotlb to IOMMU mapping helpers Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 04/19] vhost-vdpa: switch to use vhost-vdpa specific IOTLB Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 05/19] vdpa: introduce virtqueue groups Gautam Dawar
2022-02-28  8:07     ` Jason Wang
2022-02-28 10:57       ` Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 06/19] vdpa: multiple address spaces support Gautam Dawar
2022-03-03 19:39     ` Eugenio Perez Martin
2022-03-04  6:30       ` Gautam Dawar
2022-03-04 17:45         ` Eugenio Perez Martin
2022-02-24 21:22   ` [RFC PATCH v2 07/19] vdpa: introduce config operations for associating ASID to a virtqueue group Gautam Dawar
2022-03-04  9:54     ` Eugenio Perez Martin
2022-03-04 17:48       ` Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 08/19] vhost_iotlb: split out IOTLB initialization Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 09/19] vhost: support ASID in IOTLB API Gautam Dawar
2022-03-04 10:25     ` Eugenio Perez Martin
2022-03-04 17:52       ` Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 10/19] vhost-vdpa: introduce asid based IOTLB Gautam Dawar
2022-03-04 17:56     ` Eugenio Perez Martin
2022-03-07 10:07       ` Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 11/19] vhost-vdpa: introduce uAPI to get the number of virtqueue groups Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 12/19] vhost-vdpa: introduce uAPI to get the number of address spaces Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 13/19] vhost-vdpa: uAPI to get virtqueue group id Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 14/19] vhost-vdpa: introduce uAPI to set group ASID Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 15/19] vhost-vdpa: support ASID based IOTLB API Gautam Dawar
2022-03-04 18:04     ` Eugenio Perez Martin
2022-03-07 10:23       ` Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 16/19] vdpa_sim: advertise VIRTIO_NET_F_MTU Gautam Dawar
2022-03-10 17:55     ` Eugenio Perez Martin
2022-02-24 21:22   ` [RFC PATCH v2 17/19] vdpa_sim: factor out buffer completion logic Gautam Dawar
2022-02-24 21:22   ` [RFC PATCH v2 18/19] vdpa_sim: filter destination mac address Gautam Dawar
2022-03-10 18:22     ` Eugenio Perez Martin
2022-02-24 21:22   ` [RFC PATCH v2 19/19] vdpasim: control virtqueue support Gautam Dawar
2022-03-10 18:20     ` Eugenio Perez Martin
2022-03-18  7:35     ` Eugenio Perez Martin
2022-03-22  8:46       ` Gautam Dawar
2022-02-28  8:17   ` [RFC PATCH v2 00/19] Control VQ support in vDPA Jason Wang
2022-02-28 10:56     ` Gautam Dawar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aa061fcb-9395-3a1b-5d6e-76b5454dfb6c@redhat.com \
    --to=jasowang@redhat.com \
    --cc=eli@mellanox.com \
    --cc=eperezma@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=lingshan.zhu@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lulu@redhat.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=rob.miller@broadcom.com \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).