From: Stefano Garzarella <sgarzare@redhat.com>
To: virtualization@lists.linux-foundation.org
Cc: Stefano Garzarella <sgarzare@redhat.com>,
Xie Yongji <xieyongji@bytedance.com>,
kvm@vger.kernel.org, Laurent Vivier <lvivier@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
Max Gurtovoy <mgurtovoy@nvidia.com>,
linux-kernel@vger.kernel.org, Jason Wang <jasowang@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>
Subject: [PATCH v3 00/13] vdpa: add vdpa simulator for block device
Date: Thu, 4 Feb 2021 18:22:17 +0100 [thread overview]
Message-ID: <20210204172230.85853-1-sgarzare@redhat.com> (raw)
v3:
- added new patches
- 'vringh: explain more about cleaning riov and wiov'
- 'vdpa: add return value to get_config/set_config callbacks'
- 'vhost/vdpa: remove vhost_vdpa_config_validate()'
- split Xie's patch 'vhost/vdpa: Remove the restriction that only supports
virtio-net devices'
- updated Mellanox copyright to NVIDIA [Max]
- explained in the 'vdpa: add vdpa simulator for block device' commit
message that inputs are validated in subsequent patches [Stefan]
v2: https://lore.kernel.org/lkml/20210128144127.113245-1-sgarzare@redhat.com/
v1: https://lore.kernel.org/lkml/93f207c0-61e6-3696-f218-e7d7ea9a7c93@redhat.com/
This series is the second part of the v1 linked above. The first part with
refactoring of vdpa_sim has already been merged.
The patches are based on Max Gurtovoy's work and extend the block simulator to
have a ramdisk behaviour.
As mentioned in the v1 there was 2 issues and I fixed them in this series:
1. The identical mapping in the IOMMU used until now in vdpa_sim created issues
when mapping different virtual pages with the same physical address.
Fixed by patch "vdpa_sim: use iova module to allocate IOVA addresses"
2. There was a race accessing the IOMMU between the vdpasim_blk_work() and the
device driver that map/unmap DMA regions. Fixed by patch "vringh: add
'iotlb_lock' to synchronize iotlb accesses"
I used the Xie's patch coming from VDUSE series to allow vhost-vdpa to use
block devices. As Jason suggested I split it into two patches and I added
a return value to get_config()/set_config() callbacks.
The series also includes small fixes for vringh, vdpa, and vdpa_sim that I
discovered while implementing and testing the block simulator.
Thanks for your feedback,
Stefano
Max Gurtovoy (1):
vdpa: add vdpa simulator for block device
Stefano Garzarella (11):
vdpa_sim: use iova module to allocate IOVA addresses
vringh: add 'iotlb_lock' to synchronize iotlb accesses
vringh: reset kiov 'consumed' field in __vringh_iov()
vringh: explain more about cleaning riov and wiov
vringh: implement vringh_kiov_advance()
vringh: add vringh_kiov_length() helper
vdpa_sim: cleanup kiovs in vdpasim_free()
vdpa: add return value to get_config/set_config callbacks
vhost/vdpa: remove vhost_vdpa_config_validate()
vdpa_sim_blk: implement ramdisk behaviour
vdpa_sim_blk: handle VIRTIO_BLK_T_GET_ID
Xie Yongji (1):
vhost/vdpa: Remove the restriction that only supports virtio-net
devices
drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 +
include/linux/vdpa.h | 18 +-
include/linux/vringh.h | 19 +-
drivers/vdpa/ifcvf/ifcvf_main.c | 24 ++-
drivers/vdpa/mlx5/net/mlx5_vnet.c | 17 +-
drivers/vdpa/vdpa_sim/vdpa_sim.c | 134 ++++++++-----
drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 288 +++++++++++++++++++++++++++
drivers/vhost/vdpa.c | 47 ++---
drivers/vhost/vringh.c | 69 +++++--
drivers/vdpa/Kconfig | 8 +
drivers/vdpa/vdpa_sim/Makefile | 1 +
11 files changed, 504 insertions(+), 123 deletions(-)
create mode 100644 drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
--
2.29.2
next reply other threads:[~2021-02-04 17:24 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-04 17:22 Stefano Garzarella [this message]
2021-02-04 17:22 ` [PATCH v3 01/13] vdpa_sim: use iova module to allocate IOVA addresses Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 02/13] vringh: add 'iotlb_lock' to synchronize iotlb accesses Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 03/13] vringh: reset kiov 'consumed' field in __vringh_iov() Stefano Garzarella
2021-02-05 3:18 ` Jason Wang
2021-02-04 17:22 ` [PATCH v3 04/13] vringh: explain more about cleaning riov and wiov Stefano Garzarella
2021-02-05 3:18 ` Jason Wang
2021-02-04 17:22 ` [PATCH v3 05/13] vringh: implement vringh_kiov_advance() Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 06/13] vringh: add vringh_kiov_length() helper Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 07/13] vdpa_sim: cleanup kiovs in vdpasim_free() Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 08/13] vdpa: add return value to get_config/set_config callbacks Stefano Garzarella
2021-02-04 22:31 ` kernel test robot
2021-02-04 22:39 ` Stefano Garzarella
2021-02-05 3:20 ` Jason Wang
2021-02-05 8:48 ` Stefano Garzarella
2021-02-05 14:11 ` Michael S. Tsirkin
2021-02-05 14:17 ` Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 09/13] vhost/vdpa: remove vhost_vdpa_config_validate() Stefano Garzarella
2021-02-05 3:27 ` Jason Wang
2021-02-05 9:16 ` Stefano Garzarella
2021-02-05 13:32 ` Michael S. Tsirkin
2021-02-05 14:17 ` Stefano Garzarella
2021-02-08 4:13 ` Jason Wang
2021-02-04 17:22 ` [PATCH v3 10/13] vhost/vdpa: Remove the restriction that only supports virtio-net devices Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 11/13] vdpa: add vdpa simulator for block device Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 12/13] vdpa_sim_blk: implement ramdisk behaviour Stefano Garzarella
2021-02-04 17:22 ` [PATCH v3 13/13] vdpa_sim_blk: handle VIRTIO_BLK_T_GET_ID Stefano Garzarella
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=20210204172230.85853-1-sgarzare@redhat.com \
--to=sgarzare@redhat.com \
--cc=jasowang@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lvivier@redhat.com \
--cc=mgurtovoy@nvidia.com \
--cc=mst@redhat.com \
--cc=stefanha@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=xieyongji@bytedance.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 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).