From: Logan Gunthorpe <logang@deltatee.com>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Dan Williams <dan.j.williams@intel.com>,
Bjorn Helgaas <helgaas@kernel.org>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
Jens Axboe <axboe@kernel.dk>,
Steve Wise <swise@opengridcomputing.com>,
Stephen Bates <sbates@raithlin.com>,
Max Gurtovoy <maxg@mellanox.com>,
Keith Busch <keith.busch@intel.com>,
linux-pci@vger.kernel.org,
linux-scsi <linux-scsi@vger.kernel.org>,
linux-nvme@lists.infradead.org, linux-rdma@vger.kernel.org,
linux-nvdimm <linux-nvdimm@ml01.01.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Jerome Glisse <jglisse@redhat.com>
Subject: Re: [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory
Date: Wed, 19 Apr 2017 13:02:49 -0600 [thread overview]
Message-ID: <21e8099a-d19d-7df0-682d-627d8b81dfde@deltatee.com> (raw)
In-Reply-To: <20170419183247.GA13716@obsidianresearch.com>
On 19/04/17 12:32 PM, Jason Gunthorpe wrote:
> On Wed, Apr 19, 2017 at 12:01:39PM -0600, Logan Gunthorpe wrote:
> Not entirely, it would have to call through the whole process
> including the arch_p2p_cross_segment()..
Hmm, yes. Though it's still not clear what, if anything,
arch_p2p_cross_segment would be doing. In my experience, if you are
going between host bridges, the CPU address (or PCI address -- I'm not
sure which seeing they are the same on my system) would still work fine
-- it just _may_ be a bad idea because of performance.
Similarly if you are crossing via a QPI bus or similar, I'd expect the
CPU address to work fine. But here the performance is even less likely
to be any good.
> // Try the arch specific helper
> const struct dma_map_ops *comp_ops = get_dma_ops(completer);
> const struct dma_map_ops *init_ops = get_dma_ops(initiator);
So, in this case, what device does the completer point to? The PCI
device or a more specific GPU device? If it's the former, who's
responsible for setting the new dma_ops? Typically the dma_ops are arch
specific but now you'd be adding ones that are tied to hmm or the gpu.
>> I'm not sure I like the name pci_p2p_same_segment. It reads as though
>> it's only checking if the devices are not the same segment.
>
> Well, that is exactly what it is doing. If it succeeds then the caller
> knows the DMA will not flow outside the segment and no iommu setup/etc
> is required.
It appears to me like it's calculating the DMA address, and the check is
just a side requirement. It reads as though it's only doing the check.
Logan
next prev parent reply other threads:[~2017-04-19 19:02 UTC|newest]
Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-16 15:44 [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory Dan Williams
2017-04-16 16:47 ` Logan Gunthorpe
2017-04-16 22:32 ` Benjamin Herrenschmidt
2017-04-17 5:13 ` Logan Gunthorpe
2017-04-17 7:20 ` Benjamin Herrenschmidt
2017-04-17 16:52 ` Logan Gunthorpe
2017-04-17 17:04 ` Dan Williams
2017-04-18 5:22 ` Logan Gunthorpe
2017-04-17 18:04 ` Jerome Glisse
2017-04-18 6:14 ` Logan Gunthorpe
2017-04-17 21:11 ` Benjamin Herrenschmidt
2017-04-18 5:43 ` Logan Gunthorpe
2017-04-18 6:29 ` Benjamin Herrenschmidt
2017-04-16 22:23 ` Benjamin Herrenschmidt
2017-04-18 16:45 ` Jason Gunthorpe
2017-04-18 17:27 ` Dan Williams
2017-04-18 18:00 ` Jason Gunthorpe
2017-04-18 18:34 ` Dan Williams
2017-04-19 1:13 ` Benjamin Herrenschmidt
2017-04-18 22:46 ` Benjamin Herrenschmidt
2017-04-18 22:52 ` Dan Williams
2017-04-18 18:30 ` Logan Gunthorpe
2017-04-18 19:01 ` Jason Gunthorpe
2017-04-18 19:35 ` Logan Gunthorpe
2017-04-18 19:48 ` Dan Williams
2017-04-18 20:29 ` Jerome Glisse
2017-04-18 20:31 ` Dan Williams
2017-04-18 20:48 ` Logan Gunthorpe
2017-04-19 1:17 ` Benjamin Herrenschmidt
2017-04-18 21:03 ` Jason Gunthorpe
2017-04-18 21:11 ` Dan Williams
2017-04-18 21:22 ` Jason Gunthorpe
2017-04-18 21:36 ` Dan Williams
2017-04-18 22:15 ` Logan Gunthorpe
2017-04-18 22:28 ` Dan Williams
2017-04-18 22:42 ` Jason Gunthorpe
2017-04-18 22:51 ` Dan Williams
2017-04-18 23:21 ` Jason Gunthorpe
2017-04-19 1:25 ` Benjamin Herrenschmidt
2017-04-18 22:48 ` Logan Gunthorpe
2017-04-18 22:50 ` Dan Williams
2017-04-18 22:56 ` Logan Gunthorpe
2017-04-18 23:02 ` Dan Williams
2017-04-19 1:21 ` Benjamin Herrenschmidt
2017-04-18 21:31 ` Logan Gunthorpe
2017-04-18 22:24 ` Jason Gunthorpe
2017-04-18 23:03 ` Logan Gunthorpe
2017-04-19 1:23 ` Benjamin Herrenschmidt
2017-04-19 1:20 ` Benjamin Herrenschmidt
2017-04-19 15:55 ` Jason Gunthorpe
2017-04-19 16:48 ` Logan Gunthorpe
2017-04-19 17:01 ` Dan Williams
2017-04-19 17:32 ` Jerome Glisse
2017-04-19 17:41 ` Dan Williams
2017-04-19 18:11 ` Logan Gunthorpe
2017-04-19 18:19 ` Logan Gunthorpe
2017-04-19 18:30 ` Dan Williams
2017-04-19 18:41 ` Logan Gunthorpe
2017-04-19 18:44 ` Dan Williams
2017-04-20 20:43 ` Stephen Bates
2017-04-20 20:47 ` Dan Williams
2017-04-20 23:07 ` Stephen Bates
2017-04-21 4:59 ` Dan Williams
2017-04-19 17:14 ` Jason Gunthorpe
2017-04-19 18:01 ` Logan Gunthorpe
2017-04-19 18:32 ` Jason Gunthorpe
2017-04-19 19:02 ` Logan Gunthorpe [this message]
2017-04-19 19:31 ` Jason Gunthorpe
2017-04-19 19:41 ` Logan Gunthorpe
2017-04-19 20:48 ` Jason Gunthorpe
2017-04-19 22:55 ` Logan Gunthorpe
2017-04-20 0:07 ` Dan Williams
2017-04-18 19:48 ` Jason Gunthorpe
2017-04-18 20:06 ` Logan Gunthorpe
-- strict thread matches above, loose matches on Subject: below --
2017-03-30 22:12 Logan Gunthorpe
2017-04-12 5:22 ` Benjamin Herrenschmidt
2017-04-12 17:09 ` Logan Gunthorpe
2017-04-12 21:55 ` Benjamin Herrenschmidt
2017-04-13 21:22 ` Logan Gunthorpe
2017-04-13 22:37 ` Benjamin Herrenschmidt
2017-04-13 23:26 ` Bjorn Helgaas
2017-04-14 4:16 ` Jason Gunthorpe
2017-04-14 4:40 ` Logan Gunthorpe
2017-04-14 11:37 ` Benjamin Herrenschmidt
2017-04-14 11:39 ` Benjamin Herrenschmidt
2017-04-14 11:37 ` Benjamin Herrenschmidt
2017-04-14 17:30 ` Logan Gunthorpe
2017-04-14 19:04 ` Bjorn Helgaas
2017-04-14 22:07 ` Benjamin Herrenschmidt
2017-04-15 17:41 ` Logan Gunthorpe
2017-04-15 22:09 ` Dan Williams
2017-04-16 3:01 ` Benjamin Herrenschmidt
2017-04-16 4:46 ` Logan Gunthorpe
2017-04-16 15:53 ` Dan Williams
2017-04-16 16:34 ` Logan Gunthorpe
2017-04-16 22:31 ` Benjamin Herrenschmidt
2017-04-24 7:36 ` Knut Omang
2017-04-24 16:14 ` Logan Gunthorpe
2017-04-25 6:30 ` Knut Omang
2017-04-25 17:03 ` Logan Gunthorpe
2017-04-25 21:23 ` Stephen Bates
2017-04-25 21:23 ` Stephen Bates
2017-04-16 22:26 ` Benjamin Herrenschmidt
2017-04-15 22:17 ` Benjamin Herrenschmidt
2017-04-16 5:36 ` Logan Gunthorpe
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=21e8099a-d19d-7df0-682d-627d8b81dfde@deltatee.com \
--to=logang@deltatee.com \
--cc=axboe@kernel.dk \
--cc=benh@kernel.crashing.org \
--cc=dan.j.williams@intel.com \
--cc=hch@lst.de \
--cc=helgaas@kernel.org \
--cc=jejb@linux.vnet.ibm.com \
--cc=jglisse@redhat.com \
--cc=jgunthorpe@obsidianresearch.com \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@ml01.01.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=maxg@mellanox.com \
--cc=sagi@grimberg.me \
--cc=sbates@raithlin.com \
--cc=swise@opengridcomputing.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).