From: "Michael S. Tsirkin" <mst@redhat.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Ram Pai <linuxram@us.ibm.com>,
robh@kernel.org, pawel.moll@arm.com,
Tom Lendacky <thomas.lendacky@amd.com>,
aik@ozlabs.ru, jasowang@redhat.com, cohuck@redhat.com,
linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org, joe@perches.com,
"Rustad, Mark D" <mark.d.rustad@intel.com>,
david@gibson.dropbear.id.au, linuxppc-dev@lists.ozlabs.org,
elfring@users.sourceforge.net,
Anshuman Khandual <khandual@linux.vnet.ibm.com>
Subject: Re: [RFC V2] virtio: Add platform specific DMA API translation for virito devices
Date: Wed, 13 Jun 2018 16:59:41 +0300 [thread overview]
Message-ID: <20180613164500-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <20180613074141.GA12033@infradead.org>
On Wed, Jun 13, 2018 at 12:41:41AM -0700, Christoph Hellwig wrote:
> On Mon, Jun 11, 2018 at 01:29:18PM +1000, Benjamin Herrenschmidt wrote:
> > At the risk of repeating myself, let's just do the first pass which is
> > to switch virtio over to always using the DMA API in the actual data
> > flow code, with a hook at initialization time that replaces the DMA ops
> > with some home cooked "direct" ops in the case where the IOMMU flag
> > isn't set.
> >
> > This will be equivalent to what we have today but avoids having 2
> > separate code path all over the driver.
> >
> > Then a second stage, I think, is to replace this "hook" so that the
> > architecture gets a say in the matter.
>
> I don't think we can actually use dma_direct_ops. It still allows
> architectures to override parts of the dma setup, which virtio seems
> to blindly assume phys == dma and not cache flushing.
>
> I think the right way forward is to either add a new
> VIRTIO_F_IS_PCI_DEVICE (or redefine the existing iommu flag if deemed
> possible).
Given this is exactly what happens now, this seems possible, but maybe
we want a non-PCI specific name.
> And then make sure recent qemu always sets it.
I don't think that part is going to happen, sorry.
Hypervisors can set it when they *actually have* a real PCI device.
People emulate systems which have a bunch of overhead in the DMA API
which is required for real DMA. Your proposal would double that overhead
by first doing it in guest then re-doing it in host.
I don't think it's justified when 99% of the world doesn't need it.
--
MST
next prev parent reply other threads:[~2018-06-13 13:59 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-22 6:33 [RFC V2] virtio: Add platform specific DMA API translation for virito devices Anshuman Khandual
2018-05-23 18:50 ` Michael S. Tsirkin
2018-05-23 22:27 ` Benjamin Herrenschmidt
2018-05-24 7:17 ` Christoph Hellwig
2018-05-25 17:45 ` Michael S. Tsirkin
2018-05-28 23:48 ` Benjamin Herrenschmidt
2018-05-28 23:56 ` Benjamin Herrenschmidt
2018-05-29 14:03 ` Christoph Hellwig
2018-05-29 22:13 ` Benjamin Herrenschmidt
2018-06-04 8:57 ` David Gibson
2018-06-04 9:48 ` Benjamin Herrenschmidt
2018-06-04 12:50 ` Michael S. Tsirkin
2018-06-05 1:52 ` David Gibson
2018-06-04 12:43 ` Michael S. Tsirkin
2018-06-04 12:55 ` Christoph Hellwig
2018-06-04 13:14 ` Benjamin Herrenschmidt
2018-06-04 16:34 ` Michael S. Tsirkin
2018-06-04 13:11 ` Benjamin Herrenschmidt
2018-06-04 16:21 ` Michael S. Tsirkin
2018-06-04 23:26 ` Benjamin Herrenschmidt
2018-06-05 1:25 ` Michael S. Tsirkin
2018-06-05 4:52 ` Christoph Hellwig
2018-05-24 7:21 ` Ram Pai
2018-05-31 3:39 ` Anshuman Khandual
2018-05-31 17:43 ` Michael S. Tsirkin
2018-06-07 5:23 ` Christoph Hellwig
2018-06-07 16:28 ` Michael S. Tsirkin
2018-06-08 6:36 ` Christoph Hellwig
2018-06-13 13:49 ` Michael S. Tsirkin
2018-06-11 2:39 ` Ram Pai
2018-06-11 3:28 ` Michael S. Tsirkin
2018-06-11 3:34 ` Benjamin Herrenschmidt
2018-06-13 14:23 ` Michael S. Tsirkin
2018-06-11 3:29 ` Benjamin Herrenschmidt
2018-06-13 7:41 ` Christoph Hellwig
2018-06-13 12:25 ` Benjamin Herrenschmidt
2018-06-13 13:11 ` Benjamin Herrenschmidt
2018-06-15 9:16 ` Christoph Hellwig
2018-06-16 1:07 ` Benjamin Herrenschmidt
2018-06-13 13:59 ` Michael S. Tsirkin [this message]
2018-06-13 14:03 ` 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=20180613164500-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=aik@ozlabs.ru \
--cc=benh@kernel.crashing.org \
--cc=cohuck@redhat.com \
--cc=david@gibson.dropbear.id.au \
--cc=elfring@users.sourceforge.net \
--cc=hch@infradead.org \
--cc=jasowang@redhat.com \
--cc=joe@perches.com \
--cc=khandual@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=linuxram@us.ibm.com \
--cc=mark.d.rustad@intel.com \
--cc=pawel.moll@arm.com \
--cc=robh@kernel.org \
--cc=thomas.lendacky@amd.com \
--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 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).