From: Dan Williams <dan.j.williams@intel.com>
To: Jerome Glisse <jglisse@redhat.com>
Cc: Logan Gunthorpe <logang@deltatee.com>,
Jason Gunthorpe <jgunthorpe@obsidianresearch.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
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>
Subject: Re: [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory
Date: Wed, 19 Apr 2017 10:41:42 -0700 [thread overview]
Message-ID: <CAPcyv4gxBgVsbSez7_dZYkZojUWU0X0txs7FxiJ+Z3xsMt6TqQ@mail.gmail.com> (raw)
In-Reply-To: <20170419173225.GA11255@redhat.com>
On Wed, Apr 19, 2017 at 10:32 AM, Jerome Glisse <jglisse@redhat.com> wrote:
> On Wed, Apr 19, 2017 at 10:01:23AM -0700, Dan Williams wrote:
>> On Wed, Apr 19, 2017 at 9:48 AM, Logan Gunthorpe <logang@deltatee.com> wrote:
>> >
>> >
>> > On 19/04/17 09:55 AM, Jason Gunthorpe wrote:
>> >> I was thinking only this one would be supported with a core code
>> >> helper..
>> >
>> > Pivoting slightly: I was looking at how HMM uses ZONE_DEVICE. They add a
>> > type flag to the dev_pagemap structure which would be very useful to us.
>> > We could add another MEMORY_DEVICE_P2P type to distinguish p2p pages.
>> > Then, potentially, we could add a dma_map callback to the structure
>> > (possibly unioned with an hmm field). The dev_ops providers would then
>> > just need to do something like this (enclosed in a helper):
>> >
>> > if (is_zone_device_page(page)) {
>> > pgmap = get_dev_pagemap(page_to_pfn(page));
>> > if (!pgmap || pgmap->type != MEMORY_DEVICE_P2P ||
>> > !pgmap->dma_map)
>> > return 0;
>> >
>> > dma_addr = pgmap->dma_map(dev, pgmap->dev, page);
>> > put_dev_pagemap(pgmap);
>> > if (!dma_addr)
>> > return 0;
>> > ...
>> > }
>> >
>> > The pci_enable_p2p_bar function would then just need to call
>> > devm_memremap_pages with the dma_map callback set to a function that
>> > does the segment check and the offset calculation.
>> >
>> > Thoughts?
>> >
>> > @Jerome: my feedback to you would be that your patch assumes all users
>> > of devm_memremap_pages are MEMORY_DEVICE_PERSISTENT. It would be more
>> > useful if it was generic. My suggestion would be to have the caller
>> > allocate the dev_pagemap structure, populate it and pass it into
>> > devm_memremap_pages. Given that pretty much everything in that structure
>> > are already arguments to that function, I feel like this makes sense.
>> > This should also help to unify hmm_devmem_pages_create and
>> > devm_memremap_pages which look very similar to each other.
>>
>> I like that change. Also the types should describe the memory relative
>> to its relationship to struct page, not whether it is persistent or
>> not. I would consider volatile and persistent memory that is attached
>> to the cpu memory controller and i/o coherent as the same type of
>> memory. DMA incoherent ranges like P2P and HMM should get their own
>> types.
>
> Dan you asked me to not use devm_memremap_pages() because you didn't
> want to have HMM memory in the pgmap_radix, did you change opinion
> on that ? :)
No, not quite ;-). I still don't think we should require the non-HMM
to pass NULL for all the HMM arguments. What I like about Logan's
proposal is to have a separate create and register steps dev_pagemap.
That way call paths that don't care about HMM specifics can just turn
around and register the vanilla dev_pagemap.
> Note i won't make any change now on that front but if it make sense
> i am happy to do it as separate patchset on top of HMM.
>
> Also i don't want p2pmem to be an exclusive or with HMM, we will want
> GPU to do peer to peer DMA and thus HMM ZONE_DEVICE pages to support
> this too.
Yes, this makes sense I think we really just want to distinguish host
memory or not in terms of the dev_pagemap type.
next prev parent reply other threads:[~2017-04-19 17:41 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 [this message]
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
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=CAPcyv4gxBgVsbSez7_dZYkZojUWU0X0txs7FxiJ+Z3xsMt6TqQ@mail.gmail.com \
--to=dan.j.williams@intel.com \
--cc=axboe@kernel.dk \
--cc=benh@kernel.crashing.org \
--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=logang@deltatee.com \
--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).