From: "Eugenio Pérez" <eperezma@redhat.com>
To: qemu-devel@nongnu.org
Cc: Parav Pandit <parav@mellanox.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Jason Wang <jasowang@redhat.com>,
Juan Quintela <quintela@redhat.com>,
Markus Armbruster <armbru@redhat.com>,
virtualization@lists.linux-foundation.org,
Harpreet Singh Anand <hanand@xilinx.com>,
Xiao W Wang <xiao.w.wang@intel.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
Eli Cohen <eli@mellanox.com>,
Stefano Garzarella <sgarzare@redhat.com>,
Michael Lilja <ml@napatech.com>,
Jim Harford <jim.harford@broadcom.com>,
Rob Miller <rob.miller@broadcom.com>
Subject: [RFC 00/10] vDPA shadow virtqueue - notifications forwarding
Date: Fri, 29 Jan 2021 21:54:05 +0100 [thread overview]
Message-ID: <20210129205415.876290-1-eperezma@redhat.com> (raw)
This series enable vhost (And vhost-vdpa) notifications forwarding for
software assisted live migration, implemented through a shadow
virtqueue.
Shadow virtqueue is a new method of tracking memory for migration:
Instead of relay on vDPA device's dirty logging capability, SW assisted
LM intercepts dataplane, forwarding the descriptors between VM and
device.
In this migration mode, qemu offers a new (shadow) vring to the device
to read and write into, and forwards descriptors between host vring
and qemu one. On used buffer relay, qemu will mark the dirty memory as
with plain virtio-net devices. This way, devices does not need to have
dirty page logging capability.
This RFC series just enables just the notifications forwarding part,
not buffer forwarding/tracking.
It is based on the ideas of DPDK SW assisted LM, in the series of
DPDK's https://patchwork.dpdk.org/cover/48370/ , but will use memory in
qemu Virtual Address Space for rings, instead of in guest's.
Main changes from previous RFC [1] are:
* Use QMP to enable. Can disable through QMP too.
* Do not use vhost_dev_{enable,disable}_notifiers, since they override
the VM ioeventfd set, and could cause race conditions. Do never modify
irqfd or ioeventfd used for the guest.
Comments are welcome.
Thanks!
[1] https://patchew.org/QEMU/20201120185105.279030-1-eperezma@redhat.com/
Eugenio Pérez (10):
virtio: Add virtqueue_set_handler
virtio: Add set_vq_handler
virtio: Add virtio_queue_get_idx
virtio: Add virtio_queue_host_notifier_status
vhost: Add vhost_dev_from_virtio
vhost: Save masked_notifier state
vhost: Add VhostShadowVirtqueue
vhost: Add x-vhost-enable-shadow-vq qmp
vhost: Route guest->host notification through shadow virtqueue
vhost: Route host->guest notification through shadow virtqueue
qapi/net.json | 23 +++
hw/virtio/vhost-shadow-virtqueue.h | 31 ++++
include/hw/virtio/vhost.h | 6 +
include/hw/virtio/virtio.h | 14 +-
hw/net/virtio-net.c | 26 ++++
hw/virtio/vhost-shadow-virtqueue.c | 234 +++++++++++++++++++++++++++++
hw/virtio/vhost.c | 161 ++++++++++++++++++++
hw/virtio/virtio.c | 24 +++
hw/virtio/meson.build | 2 +-
9 files changed, 517 insertions(+), 4 deletions(-)
create mode 100644 hw/virtio/vhost-shadow-virtqueue.h
create mode 100644 hw/virtio/vhost-shadow-virtqueue.c
--
2.27.0
next reply other threads:[~2021-01-29 20:56 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-29 20:54 Eugenio Pérez [this message]
2021-01-29 20:54 ` [RFC 01/10] virtio: Add virtqueue_set_handler Eugenio Pérez
2021-01-29 20:54 ` [RFC 02/10] virtio: Add set_vq_handler Eugenio Pérez
2021-01-29 20:54 ` [RFC 03/10] virtio: Add virtio_queue_get_idx Eugenio Pérez
2021-02-01 6:10 ` Jason Wang
2021-02-01 6:10 ` Jason Wang
2021-02-01 7:20 ` Eugenio Perez Martin
2021-01-29 20:54 ` [RFC 04/10] virtio: Add virtio_queue_host_notifier_status Eugenio Pérez
2021-01-29 20:54 ` [RFC 05/10] vhost: Add vhost_dev_from_virtio Eugenio Pérez
2021-02-01 6:12 ` Jason Wang
2021-02-01 6:12 ` Jason Wang
2021-02-01 8:28 ` Eugenio Perez Martin
2021-02-02 3:31 ` Jason Wang
2021-02-02 3:31 ` Jason Wang
2021-02-02 10:17 ` Eugenio Perez Martin
2021-02-04 3:14 ` Jason Wang
2021-02-04 3:14 ` Jason Wang
2021-02-04 9:25 ` Eugenio Perez Martin
2021-02-05 3:51 ` Jason Wang
2021-02-05 3:51 ` Jason Wang
2021-02-09 15:35 ` Eugenio Perez Martin
2021-02-10 5:54 ` Jason Wang
2021-02-10 5:54 ` Jason Wang
2021-01-29 20:54 ` [RFC 06/10] vhost: Save masked_notifier state Eugenio Pérez
2021-01-29 20:54 ` [RFC 07/10] vhost: Add VhostShadowVirtqueue Eugenio Pérez
2021-01-29 20:54 ` [RFC 08/10] vhost: Add x-vhost-enable-shadow-vq qmp Eugenio Pérez
2021-02-02 15:38 ` Eric Blake
2021-02-02 15:38 ` Eric Blake
2021-02-04 9:01 ` Eugenio Perez Martin
2021-02-04 12:16 ` Markus Armbruster
2021-02-04 12:16 ` Markus Armbruster
2021-02-04 14:03 ` Eugenio Perez Martin
2021-01-29 20:54 ` [RFC 09/10] vhost: Route guest->host notification through shadow virtqueue Eugenio Pérez
2021-02-01 6:29 ` Jason Wang
2021-02-01 6:29 ` Jason Wang
2021-02-02 10:08 ` Eugenio Perez Martin
2021-02-04 3:26 ` Jason Wang
2021-02-04 3:26 ` Jason Wang
2021-02-09 15:02 ` Eugenio Perez Martin
2021-02-10 5:57 ` Jason Wang
2021-02-10 5:57 ` Jason Wang
2021-01-29 20:54 ` [RFC 10/10] vhost: Route host->guest " Eugenio Pérez
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=20210129205415.876290-1-eperezma@redhat.com \
--to=eperezma@redhat.com \
--cc=armbru@redhat.com \
--cc=eli@mellanox.com \
--cc=hanand@xilinx.com \
--cc=jasowang@redhat.com \
--cc=jim.harford@broadcom.com \
--cc=ml@napatech.com \
--cc=mst@redhat.com \
--cc=parav@mellanox.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=rob.miller@broadcom.com \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=xiao.w.wang@intel.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.