[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACGkMEuFTRBYU+z3ZSWzMMv2650PQ=kduGxcGXaf0T5222Bh4g@mail.gmail.com>
Date: Thu, 11 Jan 2024 10:55:23 +0800
From: Jason Wang <jasowang@...hat.com>
To: Steve Sistare <steven.sistare@...cle.com>
Cc: virtualization@...ts.linux-foundation.org, linux-kernel@...r.kernel.org,
"Michael S. Tsirkin" <mst@...hat.com>, Si-Wei Liu <si-wei.liu@...cle.com>,
Eugenio Perez Martin <eperezma@...hat.com>, Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
Dragos Tatulea <dtatulea@...dia.com>, Eli Cohen <elic@...dia.com>,
Xie Yongji <xieyongji@...edance.com>
Subject: Re: [RFC V1 00/13] vdpa live update
On Thu, Jan 11, 2024 at 4:40 AM Steve Sistare <steven.sistare@...cle.com> wrote:
>
> Live update is a technique wherein an application saves its state, exec's
> to an updated version of itself, and restores its state. Clients of the
> application experience a brief suspension of service, on the order of
> 100's of milliseconds, but are otherwise unaffected.
>
> Define and implement interfaces that allow vdpa devices to be preserved
> across fork or exec, to support live update for applications such as qemu.
> The device must be suspended during the update, but its dma mappings are
> preserved, so the suspension is brief.
>
> The VHOST_NEW_OWNER ioctl transfers device ownership and pinned memory
> accounting from one process to another.
>
> The VHOST_BACKEND_F_NEW_OWNER backend capability indicates that
> VHOST_NEW_OWNER is supported.
>
> The VHOST_IOTLB_REMAP message type updates a dma mapping with its userland
> address in the new process.
>
> The VHOST_BACKEND_F_IOTLB_REMAP backend capability indicates that
> VHOST_IOTLB_REMAP is supported and required. Some devices do not
> require it, because the userland address of each dma mapping is discarded
> after being translated to a physical address.
>
> Here is a pseudo-code sequence for performing live update, based on
> suspend + reset because resume is not yet available. The vdpa device
> descriptor, fd, remains open across the exec.
>
> ioctl(fd, VHOST_VDPA_SUSPEND)
> ioctl(fd, VHOST_VDPA_SET_STATUS, 0)
> exec
Is there a userspace implementation as a reference?
>
> ioctl(fd, VHOST_NEW_OWNER)
>
> issue ioctls to re-create vrings
>
> if VHOST_BACKEND_F_IOTLB_REMAP
> foreach dma mapping
> write(fd, {VHOST_IOTLB_REMAP, new_addr})
I think I need to understand the advantages of this approach. For
example, why it is better than
ioctl(VHOST_RESET_OWNER)
exec
ioctl(VHOST_SET_OWNER)
for each dma mapping
ioctl(VHOST_IOTLB_UPDATE)
Thanks
>
> ioctl(fd, VHOST_VDPA_SET_STATUS,
> ACKNOWLEDGE | DRIVER | FEATURES_OK | DRIVER_OK)
>
>
> Steve Sistare (13):
> vhost-vdpa: count pinned memory
> vhost-vdpa: pass mm to bind
> vhost-vdpa: VHOST_NEW_OWNER
> vhost-vdpa: VHOST_BACKEND_F_NEW_OWNER
> vhost-vdpa: VHOST_IOTLB_REMAP
> vhost-vdpa: VHOST_BACKEND_F_IOTLB_REMAP
> vhost-vdpa: flush workers on suspend
> vduse: flush workers on suspend
> vdpa_sim: reset must not run
> vdpa_sim: flush workers on suspend
> vdpa/mlx5: new owner capability
> vdpa_sim: new owner capability
> vduse: new owner capability
>
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +-
> drivers/vdpa/vdpa_sim/vdpa_sim.c | 24 ++++++-
> drivers/vdpa/vdpa_user/vduse_dev.c | 32 +++++++++
> drivers/vhost/vdpa.c | 101 +++++++++++++++++++++++++++--
> drivers/vhost/vhost.c | 15 +++++
> drivers/vhost/vhost.h | 1 +
> include/uapi/linux/vhost.h | 10 +++
> include/uapi/linux/vhost_types.h | 15 ++++-
> 8 files changed, 191 insertions(+), 10 deletions(-)
>
> --
> 2.39.3
>
Powered by blists - more mailing lists