From: Dave Chinner <david@fromorbit.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-fsdevel@vger.kernel.org, linux-aio@kvack.org,
linux-block@vger.kernel.org, linux-arch@vger.kernel.org,
hch@lst.de, jmoyer@redhat.com, avi@scylladb.com
Subject: Re: [PATCH 12/15] io_uring: add support for pre-mapped user IO buffers
Date: Thu, 17 Jan 2019 10:09:20 +1100 [thread overview]
Message-ID: <20190116230920.GT4205@dastard> (raw)
In-Reply-To: <7fd5cb40-2288-3c54-41d1-3163098b25ef@kernel.dk>
On Wed, Jan 16, 2019 at 03:21:21PM -0700, Jens Axboe wrote:
> On 1/16/19 3:09 PM, Dave Chinner wrote:
> > On Wed, Jan 16, 2019 at 02:20:53PM -0700, Jens Axboe wrote:
> >> On 1/16/19 1:53 PM, Dave Chinner wrote:
> >> I'd be fine with that restriction, especially since it can get relaxed
> >> down the line. Do we have an appropriate API for this? And why isn't
> >> get_user_pages_longterm() that exact API already?
> >
> > get_user_pages_longterm() is the right thing to use to ensure DAX
> > doesn't trip over this - it's effectively just get_user_pages()
> > with a "if (vma_is_fsdax(vma))" check in it to abort and return
> > -EOPNOTSUPP. IOWs, this is safe on DAX but it's not safe on anything
> > else. :/
> >
> > Unfortunately, disallowing userspace GUP pins on non-DAX file backed
> > pages will break existing "mostly just work" userspace apps all over
> > the place. And so right now there are discussions ongoing about how
> > to map gup references avoid the writeback races and be able to be
> > seen/tracked by other kernel infrastructure (see the long, long
> > thread "[PATCH 0/2] put_user_page*(): start converting the call
> > sites" on -fsdevel). Progress is slow, but I think we're starting to
> > close on a workable solution.
> >
> > FWIW, this doesn't solve the "long term user pin will block
> > filesystem operations until unpin" problem, that's what moving to
> > using revocable file layout leases is intended to solve. There have
> > been patches posted some time ago to add this user API for this, but
> > we've got to solve the other problems first....
> >
> >> Would seem that most
> >> (all?) callers of this API is currently broken then.
> >
> > Yup, there's a long, long history of machines using userspace RDMA
> > panicing because filesystems have detected or tripped over invalid
> > page cache state during writeback attempts. This is not a new
> > problem....
>
> Thanks for your detailed answer, Dave! I didn't see it before I sent
> out the previous email. FWIW, I've updated the patch:
>
> http://git.kernel.dk/cgit/linux-block/commit/?h=io_uring&id=0c8f2299f8069af6b2fa8f99a10d81646d1237a7
>
> Checks for file backed memory, fails the registration with EOPNOTSUPP
> if the check fails.
Doesn't it need to call put_pages() on all the pages picked up by
get_user_pages_longterm() when it returns -EOPNOTSUPP? They haven't
been mapped into the imu->bvec array yet, so AFAICT there's nothing
to release the page references on teardown here.
Also, not a vma expert here, but the vma array contents may only be
valid while the mmap_sem is held - I think vmas can come and go
after it has been dropped and so accessing vmas to check
vma->vm_file after the mmap_sem has been dropped may be open to
read-after-free races.
> That should handle the issue on the io_uring side at least, and it's a
> restriction that can always be relaxed/lifted, when appropriate solutions
> to file backed buffers exists.
Modulo the issue above, that works for me.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
next prev parent reply other threads:[~2019-01-16 23:09 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-16 17:49 [PATCHSET v5] io_uring IO interface Jens Axboe
2019-01-16 17:49 ` [PATCH 01/15] fs: add an iopoll method to struct file_operations Jens Axboe
2019-01-16 17:49 ` [PATCH 02/15] block: wire up block device iopoll method Jens Axboe
2019-01-16 17:49 ` [PATCH 03/15] block: add bio_set_polled() helper Jens Axboe
2019-01-16 17:49 ` [PATCH 04/15] iomap: wire up the iopoll method Jens Axboe
2019-01-16 17:49 ` [PATCH 05/15] Add io_uring IO interface Jens Axboe
2019-01-17 12:02 ` Roman Penyaev
2019-01-17 13:54 ` Jens Axboe
2019-01-17 14:34 ` Roman Penyaev
2019-01-17 14:54 ` Jens Axboe
2019-01-17 15:19 ` Roman Penyaev
2019-01-17 12:48 ` Roman Penyaev
2019-01-17 14:01 ` Jens Axboe
2019-01-17 20:03 ` Jeff Moyer
2019-01-17 20:09 ` Jens Axboe
2019-01-17 20:14 ` Jens Axboe
2019-01-17 20:50 ` Jeff Moyer
2019-01-17 20:53 ` Jens Axboe
2019-01-17 21:02 ` Jeff Moyer
2019-01-17 21:17 ` Jens Axboe
2019-01-17 21:21 ` Jeff Moyer
2019-01-17 21:27 ` Jens Axboe
2019-01-18 8:23 ` Roman Penyaev
2019-01-16 17:49 ` [PATCH 06/15] io_uring: add fsync support Jens Axboe
2019-01-16 17:49 ` [PATCH 07/15] io_uring: support for IO polling Jens Axboe
2019-01-16 17:49 ` [PATCH 08/15] fs: add fget_many() and fput_many() Jens Axboe
2019-01-16 17:49 ` [PATCH 09/15] io_uring: use fget/fput_many() for file references Jens Axboe
2019-01-16 17:49 ` [PATCH 10/15] io_uring: batch io_kiocb allocation Jens Axboe
2019-01-16 17:49 ` [PATCH 11/15] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-01-16 17:50 ` [PATCH 12/15] io_uring: add support for pre-mapped user IO buffers Jens Axboe
2019-01-16 20:53 ` Dave Chinner
2019-01-16 21:20 ` Jens Axboe
2019-01-16 22:09 ` Dave Chinner
2019-01-16 22:21 ` Jens Axboe
2019-01-16 23:09 ` Dave Chinner [this message]
2019-01-16 23:17 ` Jens Axboe
2019-01-16 22:13 ` Jens Axboe
2019-01-16 17:50 ` [PATCH 13/15] io_uring: add submission polling Jens Axboe
2019-01-16 17:50 ` [PATCH 14/15] io_uring: add file registration Jens Axboe
2019-01-16 17:50 ` [PATCH 15/15] io_uring: add io_uring_event cache hit information Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2019-01-10 2:43 [PATCHSET v2] io_uring IO interface Jens Axboe
2019-01-10 2:44 ` [PATCH 12/15] io_uring: add support for pre-mapped user IO buffers Jens Axboe
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=20190116230920.GT4205@dastard \
--to=david@fromorbit.com \
--cc=avi@scylladb.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=jmoyer@redhat.com \
--cc=linux-aio@kvack.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.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).