From: "Michael S. Tsirkin" <mst@redhat.com>
To: Srivatsa Vaddagiri <quic_svaddagi@quicinc.com>
Cc: Jason Wang <jasowang@redhat.com>,
xieyongji@bytedance.com, stefanha@redhat.com,
virtio-dev@lists.linux.dev, virtualization@lists.linux.dev,
quic_mnalajal@quicinc.com, quic_eberman@quicinc.com,
quic_pheragu@quicinc.com, quic_pderrin@quicinc.com,
quic_cvanscha@quicinc.com, quic_pkondeti@quicinc.com,
quic_tsoni@quicinc.com, eperezma <eperezma@redhat.com>,
Stefano Garzarella <sgarzare@redhat.com>,
Cindy Lu <lulu@redhat.com>
Subject: Re: [RFC] vduse config write support
Date: Fri, 26 Jul 2024 03:29:39 -0400 [thread overview]
Message-ID: <20240726032801-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <20240726070324.GA723942@quicinc.com>
On Fri, Jul 26, 2024 at 12:33:24PM +0530, Srivatsa Vaddagiri wrote:
> > Maybe you can give an example for this? We cache the configuration
> > space to a faster access to that.
>
> Yes for the same reason of faster access, we wish to have config information
> cached in hypervisor. In case of VDUSE,
>
> Guest read -> (VM exit) -> VHOST_VDPA_GET_CONFIG -> vduse_vdpa_get_config
>
> Basically a guest read terminates in host kernel, before resuming.
>
> In our case,
>
> Guest read - (VM exit) - Hyp emulates read - (VM resume)
>
> So a guest read would terminate in hypervisor itself, before it is resumed.
>
> Without this optimization, guest VCPU would have stalled until VMM in host can
> emulate it, which can be long, especially a concern when the read is issued in
> hot path (interrupt handler, w/o MSI_X).
Instead of optimizing INT#x (which is futile, it's a shared interrupt
and will trigger a ton of exits anyway), just enable MSI-X.
next prev parent reply other threads:[~2024-07-26 7:29 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-24 3:38 [RFC] vduse config write support Srivatsa Vaddagiri
2024-07-26 2:37 ` Yongji Xie
2024-07-26 7:06 ` Srivatsa Vaddagiri
2024-07-26 2:47 ` Jason Wang
2024-07-26 5:15 ` Michael S. Tsirkin
2024-07-29 2:06 ` Jason Wang
2024-07-26 7:03 ` Srivatsa Vaddagiri
2024-07-26 7:29 ` Michael S. Tsirkin [this message]
2024-07-29 2:16 ` Jason Wang
2024-07-29 6:02 ` Srivatsa Vaddagiri
2024-07-30 3:06 ` Jason Wang
2024-07-30 3:10 ` Jason Wang
2024-07-26 12:42 ` Srivatsa Vaddagiri
2024-07-30 2:53 ` Jason Wang
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=20240726032801-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=eperezma@redhat.com \
--cc=jasowang@redhat.com \
--cc=lulu@redhat.com \
--cc=quic_cvanscha@quicinc.com \
--cc=quic_eberman@quicinc.com \
--cc=quic_mnalajal@quicinc.com \
--cc=quic_pderrin@quicinc.com \
--cc=quic_pheragu@quicinc.com \
--cc=quic_pkondeti@quicinc.com \
--cc=quic_svaddagi@quicinc.com \
--cc=quic_tsoni@quicinc.com \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.com \
--cc=virtio-dev@lists.linux.dev \
--cc=virtualization@lists.linux.dev \
--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).