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 07:53:38 +1100 [thread overview] Message-ID: <20190116205338.GQ4205@dastard> (raw) In-Reply-To: <20190116175003.17880-13-axboe@kernel.dk> On Wed, Jan 16, 2019 at 10:50:00AM -0700, Jens Axboe wrote: > If we have fixed user buffers, we can map them into the kernel when we > setup the io_context. That avoids the need to do get_user_pages() for > each and every IO. ..... > + return -ENOMEM; > + } while (atomic_long_cmpxchg(&ctx->user->locked_vm, cur_pages, > + new_pages) != cur_pages); > + > + return 0; > +} > + > +static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) > +{ > + int i, j; > + > + if (!ctx->user_bufs) > + return -EINVAL; > + > + for (i = 0; i < ctx->sq_entries; i++) { > + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; > + > + for (j = 0; j < imu->nr_bvecs; j++) { > + set_page_dirty_lock(imu->bvec[j].bv_page); > + put_page(imu->bvec[j].bv_page); > + } Hmmm, so we call set_page_dirty() when the gup reference is dropped... ..... > +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, > + unsigned nr_args) > +{ ..... > + down_write(¤t->mm->mmap_sem); > + pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE, > + pages, NULL); > + up_write(¤t->mm->mmap_sem); Thought so. This has the same problem as RDMA w.r.t. using file-backed mappings for the user buffer. It is not synchronised against truncate, hole punches, async page writeback cleaning the page, etc, and so can lead to data corruption and/or kernel panics. It also can't be used with DAX because the above problems are actually a user-after-free of storage space, not just a dangling page reference that can be cleaned up after the gup pin is dropped. Perhaps, at least until we solve the GUP problems w.r.t. file backed pages and/or add and require file layout leases for these reference, we should error out if the user buffer pages are file-backed mappings? Cheers, Dave. -- Dave Chinner david@fromorbit.com
next prev parent reply other threads:[~2019-01-16 20:53 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 [this message] 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 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=20190116205338.GQ4205@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 \ --subject='Re: [PATCH 12/15] io_uring: add support for pre-mapped user IO buffers' \ /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
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).