From: Kit Chow <kchow@gigaio.com>
To: Logan Gunthorpe <logang@deltatee.com>,
Eric Pilmore <epilmore@gigaio.com>,
Bjorn Helgaas <helgaas@kernel.org>
Cc: linux-pci@vger.kernel.org, David Woodhouse <dwmw2@infradead.org>,
Alex Williamson <alex.williamson@redhat.com>,
iommu@lists.linux-foundation.org
Subject: Re: IOAT DMA w/IOMMU
Date: Thu, 9 Aug 2018 12:47:57 -0700 [thread overview]
Message-ID: <95e53520-b05f-4be4-e694-463d717453a8@gigaio.com> (raw)
In-Reply-To: <b54899a8-a144-e8e0-9880-1800c4657b95@deltatee.com>
On 08/09/2018 12:35 PM, Logan Gunthorpe wrote:
> Hey,
>
> On 09/08/18 12:51 PM, Eric Pilmore wrote:
>>>> Was wondering if anybody here has used IOAT DMA engines with an
>>>> IOMMU turned on (Xeon based system)? My specific question is really
>>>> whether it is possible to DMA (w/IOAT) to a PCI BAR address as the
>>>> destination without having to map that address to the IOVA space of
>>>> the DMA engine first (assuming the IOMMU is on)?
> I haven't tested this scenario but my guess would be that IOAT would
> indeed go through the IOMMU and the PCI BAR address would need to be
> properly mapped into the IOAT's IOVA. The fact that you see DMAR errors
> is probably a good indication that this is the case. I really don't know
> why you'd want to DMA something without mapping it.
I have experimented with changing ntb_async_tx_submit to dma_map the PCI
BAR
address. With this, I get a different DMAR error:
DMAR: [DMA Write] Request device [07:00.4] fault addr ffd00000
[fault reason 12] non-zero reserved fields in PTE
Kit
>>> So is this a peer-to-peer DMA scenario? You mention DMA, which would
>>> be a transaction initiated by a PCI device, to a PCI BAR address, so
>>> it doesn't sound like system memory is involved.
>> No, not peer-to-peer. This is from system memory (e.g. SKB buffer which
>> has had an IOMMU mapping created) to a PCI BAR address.
> It's definitely peer-to-peer in the case where you are using a DMA
> engine in the PCI tree. You have the DMA PCI device sending TLPs
> directly to the PCI BAR device. So, if everything is done right, the
> TLPs will avoid the root complex completely. (Though, ACS settings could
> also prevent this from working and you'd either get similar DMAR errors
> or they'd disappear into a black hole).
>
> When using the IOAT, it is part of the CPU so I wouldn't say it's really
> peer-to-peer. But an argument could be made that it is. Though, this is
> exactly what the existing ntb_transport is doing: DMAing from system
> memory to a PCI BAR and vice versa using IOAT.
>
> Logan
>
next prev parent reply other threads:[~2018-08-09 19:47 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-09 18:14 IOAT DMA w/IOMMU Eric Pilmore
2018-08-09 18:43 ` Bjorn Helgaas
2018-08-09 18:51 ` Eric Pilmore
2018-08-09 19:35 ` Logan Gunthorpe
2018-08-09 19:47 ` Kit Chow [this message]
2018-08-09 20:11 ` Logan Gunthorpe
2018-08-09 20:57 ` Kit Chow
2018-08-09 21:11 ` Logan Gunthorpe
2018-08-09 21:47 ` Kit Chow
2018-08-09 22:40 ` Jiang, Dave
2018-08-09 22:48 ` Kit Chow
2018-08-09 22:50 ` Logan Gunthorpe
2018-08-09 23:00 ` Kit Chow
2018-08-10 16:02 ` Kit Chow
2018-08-10 16:23 ` Kit Chow
2018-08-10 16:24 ` Logan Gunthorpe
2018-08-10 16:24 ` Logan Gunthorpe
2018-08-10 16:31 ` Dave Jiang
2018-08-10 16:33 ` Logan Gunthorpe
2018-08-10 17:01 ` Dave Jiang
2018-08-10 17:15 ` Logan Gunthorpe
2018-08-10 17:46 ` Dave Jiang
2018-08-11 0:53 ` Kit Chow
2018-08-11 2:10 ` Logan Gunthorpe
2018-08-13 14:23 ` Kit Chow
2018-08-13 14:59 ` Robin Murphy
2018-08-13 15:21 ` Kit Chow
2018-08-13 23:30 ` Kit Chow
2018-08-13 23:39 ` Logan Gunthorpe
2018-08-13 23:48 ` Kit Chow
2018-08-13 23:50 ` Logan Gunthorpe
2018-08-14 13:47 ` Kit Chow
2018-08-14 14:03 ` Robin Murphy
2018-08-13 23:36 ` Kit Chow
2018-08-09 21:31 ` Eric Pilmore
2018-08-09 21:36 ` Logan Gunthorpe
2018-08-16 17:16 ` Kit Chow
2018-08-16 17:21 ` Logan Gunthorpe
2018-08-16 18:53 ` Kit Chow
2018-08-16 18:56 ` Logan Gunthorpe
2018-08-21 23:18 ` Eric Pilmore
2018-08-21 23:20 ` Logan Gunthorpe
2018-08-21 23:28 ` Eric Pilmore
2018-08-21 23:35 ` Logan Gunthorpe
2018-08-21 23:45 ` Eric Pilmore
2018-08-21 23:53 ` Logan Gunthorpe
2018-08-21 23:59 ` Eric Pilmore
2018-08-21 23:30 ` Eric Pilmore
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=95e53520-b05f-4be4-e694-463d717453a8@gigaio.com \
--to=kchow@gigaio.com \
--cc=alex.williamson@redhat.com \
--cc=dwmw2@infradead.org \
--cc=epilmore@gigaio.com \
--cc=helgaas@kernel.org \
--cc=iommu@lists.linux-foundation.org \
--cc=linux-pci@vger.kernel.org \
--cc=logang@deltatee.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).