nvdimm.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Jan Kara <jack@suse.cz>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
	Jan Kara <jack@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Snitzer <snitzer@redhat.com>,
	Matthew Wilcox <mawilcox@microsoft.com>,
	linux-nvdimm <linux-nvdimm@lists.01.org>,
	Dave Chinner <david@fromorbit.com>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Christoph Hellwig <hch@lst.de>,
	linux-xfs <linux-xfs@vger.kernel.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Josh Triplett <josh.triplett@intel.com>,
	"Darrick J. Wong" <darrick.wong@oracle.com>
Subject: Re: [PATCH v8 15/18] mm, fs, dax: handle layout changes to pinned dax mappings
Date: Mon, 9 Apr 2018 18:39:10 +0200	[thread overview]
Message-ID: <20180409163910.2f6t734pwefylak3@quack2.suse.cz> (raw)
In-Reply-To: <20180408031113.GO3948@linux.vnet.ibm.com>

On Sat 07-04-18 20:11:13, Paul E. McKenney wrote:
> On Sat, Apr 07, 2018 at 12:38:24PM -0700, Dan Williams wrote:
> > [ adding Paul and Josh ]
> > 
> > On Wed, Apr 4, 2018 at 2:46 AM, Jan Kara <jack@suse.cz> wrote:
> > > On Fri 30-03-18 21:03:30, Dan Williams wrote:
> > >> Background:
> > >>
> > >> get_user_pages() in the filesystem pins file backed memory pages for
> > >> access by devices performing dma. However, it only pins the memory pages
> > >> not the page-to-file offset association. If a file is truncated the
> > >> pages are mapped out of the file and dma may continue indefinitely into
> > >> a page that is owned by a device driver. This breaks coherency of the
> > >> file vs dma, but the assumption is that if userspace wants the
> > >> file-space truncated it does not matter what data is inbound from the
> > >> device, it is not relevant anymore. The only expectation is that dma can
> > >> safely continue while the filesystem reallocates the block(s).
> > >>
> > >> Problem:
> > >>
> > >> This expectation that dma can safely continue while the filesystem
> > >> changes the block map is broken by dax. With dax the target dma page
> > >> *is* the filesystem block. The model of leaving the page pinned for dma,
> > >> but truncating the file block out of the file, means that the filesytem
> > >> is free to reallocate a block under active dma to another file and now
> > >> the expected data-incoherency situation has turned into active
> > >> data-corruption.
> > >>
> > >> Solution:
> > >>
> > >> Defer all filesystem operations (fallocate(), truncate()) on a dax mode
> > >> file while any page/block in the file is under active dma. This solution
> > >> assumes that dma is transient. Cases where dma operations are known to
> > >> not be transient, like RDMA, have been explicitly disabled via
> > >> commits like 5f1d43de5416 "IB/core: disable memory registration of
> > >> filesystem-dax vmas".
> > >>
> > >> The dax_layout_busy_page() routine is called by filesystems with a lock
> > >> held against mm faults (i_mmap_lock) to find pinned / busy dax pages.
> > >> The process of looking up a busy page invalidates all mappings
> > >> to trigger any subsequent get_user_pages() to block on i_mmap_lock.
> > >> The filesystem continues to call dax_layout_busy_page() until it finally
> > >> returns no more active pages. This approach assumes that the page
> > >> pinning is transient, if that assumption is violated the system would
> > >> have likely hung from the uncompleted I/O.
> > >>
> > >> Cc: Jan Kara <jack@suse.cz>
> > >> Cc: Jeff Moyer <jmoyer@redhat.com>
> > >> Cc: Dave Chinner <david@fromorbit.com>
> > >> Cc: Matthew Wilcox <mawilcox@microsoft.com>
> > >> Cc: Alexander Viro <viro@zeniv.linux.org.uk>
> > >> Cc: "Darrick J. Wong" <darrick.wong@oracle.com>
> > >> Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> > >> Cc: Dave Hansen <dave.hansen@linux.intel.com>
> > >> Cc: Andrew Morton <akpm@linux-foundation.org>
> > >> Reported-by: Christoph Hellwig <hch@lst.de>
> > >> Reviewed-by: Christoph Hellwig <hch@lst.de>
> > >> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> > >> ---
> > >>  drivers/dax/super.c |    2 +
> > >>  fs/dax.c            |   92 +++++++++++++++++++++++++++++++++++++++++++++++++++
> > >>  include/linux/dax.h |   25 ++++++++++++++
> > >>  mm/gup.c            |    5 +++
> > >>  4 files changed, 123 insertions(+), 1 deletion(-)
> > >
> > > ...
> > >
> > >> +/**
> > >> + * dax_layout_busy_page - find first pinned page in @mapping
> > >> + * @mapping: address space to scan for a page with ref count > 1
> > >> + *
> > >> + * DAX requires ZONE_DEVICE mapped pages. These pages are never
> > >> + * 'onlined' to the page allocator so they are considered idle when
> > >> + * page->count == 1. A filesystem uses this interface to determine if
> > >> + * any page in the mapping is busy, i.e. for DMA, or other
> > >> + * get_user_pages() usages.
> > >> + *
> > >> + * It is expected that the filesystem is holding locks to block the
> > >> + * establishment of new mappings in this address_space. I.e. it expects
> > >> + * to be able to run unmap_mapping_range() and subsequently not race
> > >> + * mapping_mapped() becoming true. It expects that get_user_pages() pte
> > >> + * walks are performed under rcu_read_lock().
> > >> + */
> > >> +struct page *dax_layout_busy_page(struct address_space *mapping)
> > >> +{
> > >> +     pgoff_t indices[PAGEVEC_SIZE];
> > >> +     struct page *page = NULL;
> > >> +     struct pagevec pvec;
> > >> +     pgoff_t index, end;
> > >> +     unsigned i;
> > >> +
> > >> +     /*
> > >> +      * In the 'limited' case get_user_pages() for dax is disabled.
> > >> +      */
> > >> +     if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
> > >> +             return NULL;
> > >> +
> > >> +     if (!dax_mapping(mapping) || !mapping_mapped(mapping))
> > >> +             return NULL;
> > >> +
> > >> +     pagevec_init(&pvec);
> > >> +     index = 0;
> > >> +     end = -1;
> > >> +     /*
> > >> +      * Flush dax_layout_lock() sections to ensure all possible page
> > >> +      * references have been taken, or otherwise arrange for faults
> > >> +      * to block on the filesystem lock that is taken for
> > >> +      * establishing new mappings.
> > >> +      */
> > >> +     unmap_mapping_range(mapping, 0, 0, 1);
> > >> +     synchronize_rcu();
> > >
> > > So I still don't like the use of RCU for this. It just seems as an abuse to
> > > use RCU like that. Furthermore it has a hefty latency cost for the truncate
> > > path. A trivial test to truncate 100 times the last page of a 16k file that
> > > is mmaped (only the first page):
> > >
> > > DAX+your patches        3.899s
> > > non-DAX                 0.015s
> > >
> > > So you can see synchronize_rcu() increased time to run truncate(2) more
> > > than 200 times (the process is indeed sitting in __wait_rcu_gp all the
> > > time). IMHO that's just too costly.
> > 
> > I wonder if this can be trivially solved by using srcu. I.e. we don't
> > need to wait for a global quiescent state, just a
> > get_user_pages_fast() quiescent state. ...or is that an abuse of the
> > srcu api?
> 
> From what I can see (not that I claim to understand DAX), SRCU
> is worth trying.  Another thing to try (as a test) is to replace the
> synchronize_rcu() above with synchronize_rcu_expedited(), which might
> get you an order of magnitude or thereabouts.

But having synchronize_rcu_expedited() easily triggerable by userspace
(potentially every 100 usec or even less) is not a great thing, right?
It would be hogging the system with IPIs...

								Honza
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  reply	other threads:[~2018-04-09 16:39 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-31  4:02 [PATCH v8 00/18] dax: fix dma vs truncate/hole-punch Dan Williams
2018-03-31  4:02 ` [PATCH v8 01/18] dax: store pfns in the radix Dan Williams
2018-03-31  4:02 ` [PATCH v8 02/18] fs, dax: prepare for dax-specific address_space_operations Dan Williams
2018-03-31  4:02 ` [PATCH v8 03/18] block, dax: remove dead code in blkdev_writepages() Dan Williams
2018-03-31  4:02 ` [PATCH v8 04/18] xfs, dax: introduce xfs_dax_aops Dan Williams
2018-03-31  4:02 ` [PATCH v8 05/18] ext4, dax: introduce ext4_dax_aops Dan Williams
2018-04-03 11:50   ` Jan Kara
2018-03-31  4:02 ` [PATCH v8 06/18] ext2, dax: introduce ext2_dax_aops Dan Williams
2018-04-03 11:51   ` Jan Kara
2018-03-31  4:02 ` [PATCH v8 07/18] fs, dax: use page->mapping to warn if truncate collides with a busy page Dan Williams
2018-03-31  4:02 ` [PATCH v8 08/18] dax: introduce CONFIG_DAX_DRIVER Dan Williams
2018-03-31  4:02 ` [PATCH v8 09/18] dax, dm: allow device-mapper to operate without dax support Dan Williams
2018-03-31  4:03 ` [PATCH v8 10/18] dax, dm: introduce ->fs_{claim, release}() dax_device infrastructure Dan Williams
2018-04-03 18:24   ` Dan Williams
2018-04-03 19:39     ` Mike Snitzer
2018-04-03 19:47       ` Dan Williams
2018-04-03 20:36         ` [PATCH v9] " Dan Williams
2018-04-03 21:13           ` Mike Snitzer
2018-03-31  4:03 ` [PATCH v8 11/18] mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks Dan Williams
2018-04-04 21:23   ` [v8, " Andrei Vagin
2018-04-04 21:27     ` Dan Williams
2018-04-04 21:35       ` Dan Williams
2018-04-04 23:19         ` Stephen Rothwell
2018-04-04 21:40     ` Andrei Vagin
2018-03-31  4:03 ` [PATCH v8 12/18] memremap: split devm_memremap_pages() and memremap() infrastructure Dan Williams
2018-03-31  4:03 ` [PATCH v8 13/18] mm, dev_pagemap: introduce CONFIG_DEV_PAGEMAP_OPS Dan Williams
2018-03-31  4:03 ` [PATCH v8 14/18] memremap: mark devm_memremap_pages() EXPORT_SYMBOL_GPL Dan Williams
2018-03-31  4:03 ` [PATCH v8 15/18] mm, fs, dax: handle layout changes to pinned dax mappings Dan Williams
2018-04-04  9:46   ` Jan Kara
2018-04-04 10:06     ` Jan Kara
2018-04-04 14:12     ` Dan Williams
2018-04-07 19:38     ` Dan Williams
2018-04-08  3:11       ` Paul E. McKenney
2018-04-09 16:39         ` Jan Kara [this message]
2018-04-09 18:14           ` Paul E. McKenney
2018-04-09 16:49       ` Jan Kara
2018-04-09 16:51         ` Dan Williams
2018-04-13 22:03           ` Dan Williams
2018-04-13 22:48             ` Paul E. McKenney
2018-04-19 10:44             ` Jan Kara
2018-04-20  3:00               ` Dan Williams
2018-03-31  4:03 ` [PATCH v8 16/18] xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL Dan Williams
2018-03-31  4:03 ` [PATCH v8 17/18] xfs: prepare xfs_break_layouts() for another layout type Dan Williams
2018-03-31  4:03 ` [PATCH v8 18/18] xfs, dax: introduce xfs_break_dax_layouts() Dan Williams
2018-04-04  9:55   ` Jan Kara

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=20180409163910.2f6t734pwefylak3@quack2.suse.cz \
    --to=jack@suse.cz \
    --cc=akpm@linux-foundation.org \
    --cc=darrick.wong@oracle.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --cc=josh.triplett@intel.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=mawilcox@microsoft.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=snitzer@redhat.com \
    --cc=viro@zeniv.linux.org.uk \
    /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).