From: John Hubbard <jhubbard@nvidia.com>
To: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>,
Dan Williams <dan.j.williams@intel.com>,
Christoph Hellwig <hch@lst.de>, Jason Gunthorpe <jgg@ziepe.ca>,
John Hubbard <john.hubbard@gmail.com>,
Michal Hocko <mhocko@kernel.org>,
Christopher Lameter <cl@linux.com>, Linux MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-rdma <linux-rdma@vger.kernel.org>
Subject: Re: [PATCH 2/2] mm: set PG_dma_pinned on get_user_pages*()
Date: Wed, 20 Jun 2018 15:55:41 -0700 [thread overview]
Message-ID: <151edbf3-66ff-df0c-c1cc-5998de50111e@nvidia.com> (raw)
In-Reply-To: <20180620120824.bghoklv7qu2z5wgy@quack2.suse.cz>
On 06/20/2018 05:08 AM, Jan Kara wrote:
> On Tue 19-06-18 11:11:48, John Hubbard wrote:
>> On 06/19/2018 03:41 AM, Jan Kara wrote:
>>> On Tue 19-06-18 02:02:55, Matthew Wilcox wrote:
>>>> On Tue, Jun 19, 2018 at 10:29:49AM +0200, Jan Kara wrote:
[...]
>>> I'm also still pondering the idea of inserting a "virtual" VMA into vma
>>> interval tree in the inode - as the GUP references are IMHO closest to an
>>> mlocked mapping - and that would achieve all the functionality we need as
>>> well. I just didn't have time to experiment with it.
>>
>> How would this work? Would it have the same virtual address range? And how
>> does it avoid the problems we've been discussing? Sorry to be a bit slow
>> here. :)
>
> The range covered by the virtual mapping would be the one sent to
> get_user_pages() to get page references. And then we would need to teach
> page_mkclean() to check for these virtual VMAs and block / skip / report
> (different situations would need different behavior) such page. But this
> second part is the same regardless how we identify a page that is pinned by
> get_user_pages().
OK. That neatly avoids the need a new page flag, I think. But of course it is
somewhat more extensive to implement. Sounds like something to keep in mind,
in case it has better tradeoffs than the direction I'm heading so far.
>>> And then there's the aspect that both these approaches are a bit too
>>> heavyweight for some get_user_pages_fast() users (e.g. direct IO) - Al Viro
>>> had an idea to use page lock for that path but e.g. fs/direct-io.c would have
>>> problems due to lock ordering constraints (filesystem ->get_block would
>>> suddently get called with the page lock held). But we can probably leave
>>> performance optimizations for phase two.
>>
>>
>> So I assume that phase one would be to apply this approach only to
>> get_user_pages_longterm. (Please let me know if that's wrong.)
>
> No, I meant phase 1 would be to apply this to all get_user_pages() flavors.
> Then phase 2 is to try to find a way to make get_user_pages_fast() fast
> again. And then in parallel to that, we also need to find a way for
> get_user_pages_longterm() to signal to the user pinned pages must be
> released soon. Because after phase 1 pinned pages will block page
> writeback and such system won't oops but will become unusable
> sooner rather than later. And again this problem needs to be solved
> regardless of a mechanism of identifying pinned pages.
>
OK, thanks, that does help. I had the priorities of these get_user_pages*()
changes all scrambled, but between your and Dan's explanation, I finally
understand the preferred ordering of this work.
next prev parent reply other threads:[~2018-06-20 22:55 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-17 1:25 [PATCH 0/2] mm: gup: don't unmap or drop filesystem buffers john.hubbard
2018-06-17 1:25 ` [PATCH 1/2] consolidate get_user_pages error handling john.hubbard
2018-06-17 1:25 ` [PATCH 2/2] mm: set PG_dma_pinned on get_user_pages*() john.hubbard
2018-06-17 19:53 ` Dan Williams
2018-06-17 20:04 ` Jason Gunthorpe
2018-06-17 20:10 ` Dan Williams
2018-06-17 20:28 ` John Hubbard
2018-06-18 8:12 ` Christoph Hellwig
2018-06-18 17:50 ` John Hubbard
2018-06-18 17:56 ` Dan Williams
2018-06-18 18:14 ` John Hubbard
2018-06-18 19:21 ` Dan Williams
2018-06-18 19:31 ` Jason Gunthorpe
2018-06-18 20:04 ` Dan Williams
2018-06-18 21:36 ` John Hubbard
2018-06-19 8:29 ` Jan Kara
2018-06-19 9:02 ` Matthew Wilcox
2018-06-19 10:41 ` Jan Kara
2018-06-19 18:11 ` John Hubbard
2018-06-20 1:24 ` Dan Williams
2018-06-20 1:34 ` John Hubbard
2018-06-20 1:57 ` Dan Williams
2018-06-20 2:03 ` John Hubbard
2018-06-20 12:08 ` Jan Kara
2018-06-20 22:55 ` John Hubbard [this message]
2018-06-21 16:30 ` Jan Kara
2018-06-25 15:21 ` Jan Kara
2018-06-25 19:03 ` John Hubbard
2018-06-26 7:52 ` Jan Kara
2018-06-26 6:31 ` John Hubbard
2018-06-26 11:48 ` Jan Kara
2018-06-26 13:47 ` Michal Hocko
2018-06-26 16:48 ` Jan Kara
2018-06-27 11:32 ` Michal Hocko
2018-06-27 11:53 ` Jan Kara
2018-06-27 11:59 ` Michal Hocko
2018-06-27 12:42 ` Jan Kara
2018-06-27 14:57 ` Jason Gunthorpe
2018-06-27 17:02 ` Jan Kara
2018-06-28 2:42 ` John Hubbard
2018-06-28 9:17 ` Jan Kara
2018-07-02 5:52 ` Leon Romanovsky
2018-07-02 6:10 ` John Hubbard
2018-07-02 6:34 ` Leon Romanovsky
2018-07-02 6:41 ` John Hubbard
2018-07-02 10:36 ` Michal Hocko
2018-07-02 7:02 ` Jan Kara
2018-07-02 14:48 ` Michal Hocko
2018-07-02 6:58 ` Jan Kara
2018-06-18 8:11 ` Christoph Hellwig
2018-06-19 6:15 ` Leon Romanovsky
2018-06-17 22:19 ` John Hubbard
2018-06-18 7:56 ` Christoph Hellwig
2018-06-18 17:44 ` John Hubbard
2018-06-17 21:54 ` [PATCH 0/2] mm: gup: don't unmap or drop filesystem buffers Christopher Lameter
2018-06-17 22:23 ` John Hubbard
2018-06-18 8:10 ` Christoph Hellwig
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=151edbf3-66ff-df0c-c1cc-5998de50111e@nvidia.com \
--to=jhubbard@nvidia.com \
--cc=cl@linux.com \
--cc=dan.j.williams@intel.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jgg@ziepe.ca \
--cc=john.hubbard@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mhocko@kernel.org \
--cc=willy@infradead.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).