From: Jan Kiszka <jan.kiszka@siemens.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtio-dev@lists.oasis-open.org, Claudio.Fontana@huawei.com,
qemu-devel@nongnu.org, virtualization@lists.linux-foundation.org,
Varun Sethi <Varun.Sethi@freescale.com>,
opnfv-tech-discuss@lists.opnfv.org
Subject: Re: rfc: vhost user enhancements for vm2vm communication
Date: Thu, 3 Sep 2015 12:25:27 +0200 [thread overview]
Message-ID: <55E82017.3090708@siemens.com> (raw)
In-Reply-To: <20150903112343-mutt-send-email-mst@redhat.com>
On 2015-09-03 10:37, Michael S. Tsirkin wrote:
> On Thu, Sep 03, 2015 at 10:21:28AM +0200, Jan Kiszka wrote:
>> On 2015-09-03 10:08, Michael S. Tsirkin wrote:
>>>
>>> IOW if you wish, you actually can create a shared memory device,
>>> make it accessible to the IOMMU and place some or all
>>> data there.
>>>
>>
>> Actually, that could also be something more sophisticated, including
>> virtio-net, IF that device will be able to express its DMA window
>> restrictions (a bit like 32-bit PCI devices being restricted to <4G
>> addresses or ISA devices <1M).
>>
>> Jan
>
> Actually, it's the bus restriction, not the device restriction.
>
> So if you want to use bounce buffers in the name of security or
> real-time requirements, you should be able to do this if virtio uses the
> DMA API.
Bounce buffer will only be the simplest option (though fine for low-rate
traffic that we also have in mind, like virtual consoles). Given
properly-sized regions, even if fixed, and the right communication
stacks, you can directly allocate application buffers in those regions
and avoid most to all copying.
In any case, if we manage to address this variation along with your
proposal, that would help tremendously.
Jan
--
Siemens AG, Corporate Technology, CT RTC ITP SES-DE
Corporate Competence Center Embedded Linux
WARNING: multiple messages have this Message-ID (diff)
From: Jan Kiszka <jan.kiszka@siemens.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtio-dev@lists.oasis-open.org, Claudio.Fontana@huawei.com,
qemu-devel@nongnu.org, virtualization@lists.linux-foundation.org,
"Nakajima, Jun" <jun.nakajima@intel.com>,
Varun Sethi <Varun.Sethi@freescale.com>,
opnfv-tech-discuss@lists.opnfv.org
Subject: Re: [Qemu-devel] rfc: vhost user enhancements for vm2vm communication
Date: Thu, 3 Sep 2015 12:25:27 +0200 [thread overview]
Message-ID: <55E82017.3090708@siemens.com> (raw)
In-Reply-To: <20150903112343-mutt-send-email-mst@redhat.com>
On 2015-09-03 10:37, Michael S. Tsirkin wrote:
> On Thu, Sep 03, 2015 at 10:21:28AM +0200, Jan Kiszka wrote:
>> On 2015-09-03 10:08, Michael S. Tsirkin wrote:
>>>
>>> IOW if you wish, you actually can create a shared memory device,
>>> make it accessible to the IOMMU and place some or all
>>> data there.
>>>
>>
>> Actually, that could also be something more sophisticated, including
>> virtio-net, IF that device will be able to express its DMA window
>> restrictions (a bit like 32-bit PCI devices being restricted to <4G
>> addresses or ISA devices <1M).
>>
>> Jan
>
> Actually, it's the bus restriction, not the device restriction.
>
> So if you want to use bounce buffers in the name of security or
> real-time requirements, you should be able to do this if virtio uses the
> DMA API.
Bounce buffer will only be the simplest option (though fine for low-rate
traffic that we also have in mind, like virtual consoles). Given
properly-sized regions, even if fixed, and the right communication
stacks, you can directly allocate application buffers in those regions
and avoid most to all copying.
In any case, if we manage to address this variation along with your
proposal, that would help tremendously.
Jan
--
Siemens AG, Corporate Technology, CT RTC ITP SES-DE
Corporate Competence Center Embedded Linux
next prev parent reply other threads:[~2015-09-03 10:25 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-31 14:11 [Qemu-devel] rfc: vhost user enhancements for vm2vm communication Michael S. Tsirkin
2015-08-31 18:35 ` Nakajima, Jun
2015-08-31 18:35 ` [Qemu-devel] " Nakajima, Jun
2015-09-01 3:03 ` Varun Sethi
2015-09-01 3:03 ` Varun Sethi
2015-09-01 8:30 ` Michael S. Tsirkin
2015-09-01 8:30 ` Michael S. Tsirkin
2015-09-01 8:17 ` Michael S. Tsirkin
2015-09-01 22:56 ` Nakajima, Jun
2015-09-01 22:56 ` [Qemu-devel] " Nakajima, Jun
2015-09-01 8:17 ` Michael S. Tsirkin
2015-10-06 21:42 ` [Qemu-devel] " Nakajima, Jun
2015-10-07 5:39 ` Michael S. Tsirkin
2015-10-07 5:39 ` Michael S. Tsirkin
2015-10-06 21:42 ` Nakajima, Jun
2015-09-01 7:35 ` Jan Kiszka
2015-09-01 7:35 ` [Qemu-devel] " Jan Kiszka
2015-09-01 8:01 ` Michael S. Tsirkin
2015-09-01 9:11 ` Jan Kiszka
2015-09-01 9:11 ` [Qemu-devel] " Jan Kiszka
2015-09-01 9:24 ` Michael S. Tsirkin
2015-09-01 9:24 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-01 14:09 ` Jan Kiszka
2015-09-01 14:09 ` [Qemu-devel] " Jan Kiszka
2015-09-01 14:34 ` Michael S. Tsirkin
2015-09-01 14:34 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-01 15:34 ` Jan Kiszka
2015-09-01 15:34 ` [Qemu-devel] " Jan Kiszka
2015-09-01 16:02 ` Michael S. Tsirkin
2015-09-01 16:02 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-01 16:28 ` Jan Kiszka
2015-09-01 16:28 ` [Qemu-devel] " Jan Kiszka
2015-09-02 0:01 ` Nakajima, Jun
2015-09-02 0:01 ` [Qemu-devel] " Nakajima, Jun
2015-09-02 12:15 ` Michael S. Tsirkin
2015-09-02 12:15 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-03 4:45 ` Nakajima, Jun
2015-09-03 8:09 ` Michael S. Tsirkin
2015-09-03 8:09 ` Michael S. Tsirkin
2015-09-03 4:45 ` Nakajima, Jun
2015-09-03 8:08 ` Michael S. Tsirkin
2015-09-03 8:08 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-03 8:21 ` Jan Kiszka
2015-09-03 8:21 ` [Qemu-devel] " Jan Kiszka
2015-09-03 8:37 ` Michael S. Tsirkin
2015-09-03 8:37 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-03 10:25 ` Jan Kiszka [this message]
2015-09-03 10:25 ` Jan Kiszka
2015-09-01 8:01 ` Michael S. Tsirkin
2015-09-07 12:38 ` Claudio Fontana
2015-09-07 12:38 ` [Qemu-devel] " Claudio Fontana
2015-09-09 6:40 ` [Qemu-devel] [opnfv-tech-discuss] " Zhang, Yang Z
2015-09-09 8:39 ` Claudio Fontana
2015-09-09 8:39 ` [Qemu-devel] " Claudio Fontana
2015-09-18 16:29 ` RFC: virtio-peer shared memory based peer communication device Claudio Fontana
2015-09-18 16:29 ` [Qemu-devel] " Claudio Fontana
2015-09-18 21:11 ` Paolo Bonzini
2015-09-18 21:11 ` [Qemu-devel] " Paolo Bonzini
2015-09-21 10:47 ` Jan Kiszka
2015-09-21 10:47 ` [Qemu-devel] " Jan Kiszka
2015-09-21 12:15 ` Paolo Bonzini
2015-09-21 12:15 ` [Qemu-devel] " Paolo Bonzini
2015-09-21 12:13 ` Michael S. Tsirkin
2015-09-21 12:13 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-21 12:32 ` Jan Kiszka
2015-09-21 12:32 ` [Qemu-devel] " Jan Kiszka
2015-09-24 10:04 ` Michael S. Tsirkin
2015-09-24 10:04 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-09 6:40 ` [opnfv-tech-discuss] rfc: vhost user enhancements for vm2vm communication Zhang, Yang Z
2015-09-09 7:06 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-11 15:39 ` Claudio Fontana
2015-09-11 15:39 ` [Qemu-devel] " Claudio Fontana
2015-09-13 9:12 ` Michael S. Tsirkin
2015-09-13 9:12 ` [Qemu-devel] " Michael S. Tsirkin
2015-09-14 0:43 ` [opnfv-tech-discuss] " Zhang, Yang Z
2015-09-14 0:43 ` [Qemu-devel] " Zhang, Yang Z
2015-09-09 7:06 ` Michael S. Tsirkin
2015-09-14 16:00 ` [virtio-dev] " Stefan Hajnoczi
2015-09-14 16:00 ` [Qemu-devel] " Stefan Hajnoczi
-- strict thread matches above, loose matches on Subject: below --
2015-08-31 14:11 Michael S. Tsirkin
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=55E82017.3090708@siemens.com \
--to=jan.kiszka@siemens.com \
--cc=Claudio.Fontana@huawei.com \
--cc=Varun.Sethi@freescale.com \
--cc=mst@redhat.com \
--cc=opnfv-tech-discuss@lists.opnfv.org \
--cc=qemu-devel@nongnu.org \
--cc=virtio-dev@lists.oasis-open.org \
--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 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.