Expand the capacity of a keyring to be able to hold a lot more keys by using
the previously added associative array implementation.  Currently the maximum
capacity is:

	(PAGE_SIZE - sizeof(header)) / sizeof(struct key *)

which, on a 64-bit system, is a little more 500.  However, since this is being
used for the NFS uid mapper, we need more than that.  The new implementation
gives us effectively unlimited capacity.

With some alterations, the keyutils testsuite runs successfully to completion
after this patch is applied.  The alterations are because (a) keyrings that
are simply added to no longer appear ordered and (b) some of the errors have
changed a bit.
Signed-off-by: David Howells <dhowells@redhat.com>

Add a generic associative array implementation that can be used as the
container for keyrings, thereby massively increasing the capacity available
whilst also speeding up searching in keyrings that contain a lot of keys.

This may also be useful in FS-Cache for tracking cookies.

Documentation is added into Documentation/associative_array.txt

Some of the properties of the implementation are:

 (1) Objects are opaque pointers.  The implementation does not care where they
     point (if anywhere) or what they point to (if anything).

     [!] NOTE: Pointers to objects _must_ be zero in the two least significant
     	       bits.

 (2) Objects do not need to contain linkage blocks for use by the array.  This
     permits an object to be located in multiple arrays simultaneously.
     Rather, the array is made up of metadata blocks that point to objects.

 (3) Objects are labelled as being one of two types (the type is a bool value).
     This information is stored in the array, but has no consequence to the
     array itself or its algorithms.

 (4) Objects require index keys to locate them within the array.

 (5) Index keys must be unique.  Inserting an object with the same key as one
     already in the array will replace the old object.

 (6) Index keys can be of any length and can be of different lengths.

 (7) Index keys should encode the length early on, before any variation due to
     length is seen.

 (8) Index keys can include a hash to scatter objects throughout the array.

 (9) The array can iterated over.  The objects will not necessarily come out in
     key order.

(10) The array can be iterated whilst it is being modified, provided the RCU
     readlock is being held by the iterator.  Note, however, under these
     circumstances, some objects may be seen more than once.  If this is a
     problem, the iterator should lock against modification.  Objects will not
     be missed, however, unless deleted.

(11) Objects in the array can be looked up by means of their index key.

(12) Objects can be looked up whilst the array is being modified, provided the
     RCU readlock is being held by the thread doing the look up.

The implementation uses a tree of 16-pointer nodes internally that are indexed
on each level by nibbles from the index key.  To improve memory efficiency,
shortcuts can be emplaced to skip over what would otherwise be a series of
single-occupancy nodes.  Further, nodes pack leaf object pointers into spare
space in the node rather than making an extra branch until as such time an
object needs to be added to a full node.
Signed-off-by: David Howells <dhowells@redhat.com>

Drop the permissions argument from __keyring_search_one() as the only caller
passes 0 here - which causes all checks to be skipped.
Signed-off-by: David Howells <dhowells@redhat.com>

Define a __key_get() wrapper to use rather than atomic_inc() on the key usage
count as this makes it easier to hook in refcount error debugging.
Signed-off-by: David Howells <dhowells@redhat.com>

Search for auth-key by name rather than by target key ID as, in a future
patch, we'll by searching directly by index key in preference to iteration
over all keys.
Signed-off-by: David Howells <dhowells@redhat.com>

Search functions pass around a bunch of arguments, each of which gets copied
with each call.  Introduce a search context structure to hold these.

Whilst we're at it, create a search flag that indicates whether the search
should be directly to the description or whether it should iterate through all
keys looking for a non-description match.

This will be useful when keyrings use a generic data struct with generic
routines to manage their content as the search terms can just be passed
through to the iterator callback function.

Also, for future use, the data to be supplied to the match function is
separated from the description pointer in the search context.  This makes it
clear which is being supplied.
Signed-off-by: David Howells <dhowells@redhat.com>

Consolidate the concept of an 'index key' for accessing keys.  The index key
is the search term needed to find a key directly - basically the key type and
the key description.  We can add to that the description length.

This will be useful when turning a keyring into an associative array rather
than just a pointer block.
Signed-off-by: David Howells <dhowells@redhat.com>

key_is_dead() should take a const key pointer argument as it doesn't modify
what it points to.
Signed-off-by: David Howells <dhowells@redhat.com>

Make make_key_ref() take a bool possession parameter and make
is_key_possessed() return a bool.
Signed-off-by: David Howells <dhowells@redhat.com>

Skip key state checks (invalidation, revocation and expiration) when checking
for possession.  Without this, keys that have been marked invalid, revoked
keys and expired keys are not given a possession attribute - which means the
possessor is not granted any possession permits and cannot do anything with
them unless they also have one a user, group or other permit.

This causes failures in the keyutils test suite's revocation and expiration
tests now that commit 96b5c8fe reduced the
initial permissions granted to a key.

The failures are due to accesses to revoked and expired keys being given
EACCES instead of EKEYREVOKED or EKEYEXPIRED.
Signed-off-by: David Howells <dhowells@redhat.com>

Signed-off-by: Paul Moore <paul@paul-moore.com>
Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>

Back when we had half ass LSM stacking we had to link capabilities.o
after bigger LSMs so that on initialization the bigger LSM would
register first and the capabilities module would be the one stacked as
the 'seconday'.  Somewhere around 6f0f0fd4 (back in 2008) we
finally removed the last of the kinda module stacking code but this
comment in the makefile still lives today.
Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>

Pull staging fixes from Greg KH:
 "Here are a number of small staging tree and iio driver fixes.  Nothing
  major, just lots of little things"

* tag 'staging-3.12-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging: (34 commits)
  iio:buffer_cb: Add missing iio_buffer_init()
  iio: Prevent race between IIO chardev opening and IIO device free
  iio: fix: Keep a reference to the IIO device for open file descriptors
  iio: Stop sampling when the device is removed
  iio: Fix crash when scan_bytes is computed with active_scan_mask == NULL
  iio: Fix mcp4725 dev-to-indio_dev conversion in suspend/resume
  iio: Fix bma180 dev-to-indio_dev conversion in suspend/resume
  iio: Fix tmp006 dev-to-indio_dev conversion in suspend/resume
  iio: iio_device_add_event_sysfs() bugfix
  staging: iio: ade7854-spi: Fix return value
  staging:iio:hmc5843: Fix measurement conversion
  iio: isl29018: Fix uninitialized value
  staging:iio:dummy fix kfifo_buf kconfig dependency issue if kfifo modular and buffer enabled for built in dummy driver.
  iio: at91: fix adc_clk overflow
  staging: line6: add bounds check in snd_toneport_source_put()
  Staging: comedi: Fix dependencies for drivers misclassified as PCI
  staging: r8188eu: Adjust RX gain
  staging: r8188eu: Fix smatch warning in core/rtw_ieee80211.
  staging: r8188eu: Fix smatch error in core/rtw_mlme_ext.c
  staging: r8188eu: Fix Smatch off-by-one warning in hal/rtl8188e_hal_init.c
  ...

Pull USB fixes from Greg KH:
 "Here are a number of small USB fixes for 3.12-rc2.

  One is a revert of a EHCI change that isn't quite ready for 3.12.
  Others are minor things, gadget fixes, Kconfig fixes, and some quirks
  and documentation updates.

  All have been in linux-next for a bit"

* tag 'usb-3.12-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  USB: pl2303: distinguish between original and cloned HX chips
  USB: Faraday fotg210: fix email addresses
  USB: fix typo in usb serial simple driver Kconfig
  Revert "USB: EHCI: support running URB giveback in tasklet context"
  usb: s3c-hsotg: do not disconnect gadget when receiving ErlySusp intr
  usb: s3c-hsotg: fix unregistration function
  usb: gadget: f_mass_storage: reset endpoint driver data when disabled
  usb: host: fsl-mph-dr-of: Staticize local symbols
  usb: gadget: f_eem: Staticize eem_alloc
  usb: gadget: f_ecm: Staticize ecm_alloc
  usb: phy: omap-usb3: Fix return value
  usb: dwc3: gadget: avoid memory leak when failing to allocate all eps
  usb: dwc3: remove extcon dependency
  usb: gadget: add '__ref' for rndis_config_register() and cdc_config_register()
  usb: dwc3: pci: add support for BayTrail
  usb: gadget: cdc2: fix conversion to new interface of f_ecm
  usb: gadget: fix a bug and a WARN_ON in dummy-hcd
  usb: gadget: mv_u3d_core: fix violation of locking discipline in mv_u3d_ep_disable()

Pull drm fixes from Dave Airlie:
 - some small fixes for msm and exynos
 - a regression revert affecting nouveau users with old userspace
 - intel pageflip deadlock and gpu hang fixes, hsw modesetting hangs

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (22 commits)
  Revert "drm: mark context support as a legacy subsystem"
  drm/i915: Don't enable the cursor on a disable pipe
  drm/i915: do not update cursor in crtc mode set
  drm/exynos: fix return value check in lowlevel_buffer_allocate()
  drm/exynos: Fix address space warnings in exynos_drm_fbdev.c
  drm/exynos: Fix address space warning in exynos_drm_buf.c
  drm/exynos: Remove redundant OF dependency
  drm/msm: drop unnecessary set_need_resched()
  drm/i915: kill set_need_resched
  drm/msm: fix potential NULL pointer dereference
  drm/i915/dvo: set crtc timings again for panel fixed modes
  drm/i915/sdvo: Robustify the dtd<->drm_mode conversions
  drm/msm: workaround for missing irq
  drm/msm: return -EBUSY if bo still active
  drm/msm: fix return value check in ERR_PTR()
  drm/msm: fix cmdstream size check
  drm/msm: hangcheck harder
  drm/msm: handle read vs write fences
  drm/i915/sdvo: Fully translate sync flags in the dtd->mode conversion
  drm/i915: Use proper print format for debug prints
  ...

Pull block IO fixes from Jens Axboe:
 "After merge window, no new stuff this time only a collection of neatly
  confined and simple fixes"

* 'for-3.12/core' of git://git.kernel.dk/linux-block:
  cfq: explicitly use 64bit divide operation for 64bit arguments
  block: Add nr_bios to block_rq_remap tracepoint
  If the queue is dying then we only call the rq->end_io callout. This leaves bios setup on the request, because the caller assumes when the blk_execute_rq_nowait/blk_execute_rq call has completed that the rq->bios have been cleaned up.
  bio-integrity: Fix use of bs->bio_integrity_pool after free
  blkcg: relocate root_blkg setting and clearing
  block: Convert kmalloc_node(...GFP_ZERO...) to kzalloc_node(...)
  block: trace all devices plug operation

Pull btrfs fixes from Chris Mason:
 "These are mostly bug fixes and a two small performance fixes.  The
  most important of the bunch are Josef's fix for a snapshotting
  regression and Mark's update to fix compile problems on arm"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (25 commits)
  Btrfs: create the uuid tree on remount rw
  btrfs: change extent-same to copy entire argument struct
  Btrfs: dir_inode_operations should use btrfs_update_time also
  btrfs: Add btrfs: prefix to kernel log output
  btrfs: refuse to remount read-write after abort
  Btrfs: btrfs_ioctl_default_subvol: Revert back to toplevel subvolume when arg is 0
  Btrfs: don't leak transaction in btrfs_sync_file()
  Btrfs: add the missing mutex unlock in write_all_supers()
  Btrfs: iput inode on allocation failure
  Btrfs: remove space_info->reservation_progress
  Btrfs: kill delay_iput arg to the wait_ordered functions
  Btrfs: fix worst case calculator for space usage
  Revert "Btrfs: rework the overcommit logic to be based on the total size"
  Btrfs: improve replacing nocow extents
  Btrfs: drop dir i_size when adding new names on replay
  Btrfs: replay dir_index items before other items
  Btrfs: check roots last log commit when checking if an inode has been logged
  Btrfs: actually log directory we are fsync()'ing
  Btrfs: actually limit the size of delalloc range
  Btrfs: allocate the free space by the existed max extent size when ENOSPC
  ...

'samples' is 64bit operant, but do_div() second parameter is 32.
do_div silently truncates high 32 bits and calculated result
is invalid.

In case if low 32bit of 'samples' are zeros then do_div() produces
kernel crash.
Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Merge tag 'iio-fixes-for-3.12a' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio into staging-linus

Jonathan writes:

First round of IIO fixes for 3.12

A series of wrong 'struct dev' assumptions in suspend/resume callbacks
following on from this issue being identified in a new driver review.
One to watch out for in future.

A number of driver specific fixes
1) at91 - fix a overflow in clock rate computation
2) dummy - Kconfig dependency issue
3) isl29018 - uninitialized value
4) hmc5843 - measurement conversion bug introduced by recent cleanup.
5) ade7854-spi - wrong return value.

Some IIO core fixes
1) Wrong value picked up for event code creation for a modified channel
2) A null dereference on failure to initialize a buffer after no buffer has
   been in use, when using the available_scan_masks approach.
3) Sampling not stopped when a device is removed. Effects forced removal
   such as hot unplugging.
4) Prevent device going away if a chrdev is still open in userspace.
5) Prevent race on chardev opening and device being freed.
6) Add a missing iio_buffer_init in the call back buffer.

These last few are the first part of a set from Lars-Peter Clausen who
has been taking a closer look at our removal paths and buffer handling
than anyone has for quite some time.

Pull NFS client bugfix from Trond Myklebust:
 "Fix a regression due to incorrect sharing of gss auth caches"

* tag 'nfs-for-3.12-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  RPCSEC_GSS: fix crash on destroying gss auth

Adding the number of bios in a remapped request to 'block_rq_remap'
tracepoint.

Request remapper clones bios in a request to track the completion
status of each bio. So the number of bios can be useful information
for investigation.

Related discussions:
  http://www.redhat.com/archives/dm-devel/2013-August/msg00084.html
  http://www.redhat.com/archives/dm-devel/2013-September/msg00024.htmlSigned-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Users have been complaining of the uuid tree stuff warning that there is no uuid
root when trying to do snapshot operations.  This is because if you mount -o ro
we will not create the uuid tree.  But then if you mount -o rw,remount we will
still not create it and then any subsequent snapshot/subvol operations you try
to do will fail gloriously.  Fix this by creating the uuid_root on remount rw if
it was not already there.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

btrfs_ioctl_file_extent_same() uses __put_user_unaligned() to copy some data
back to it's argument struct. Unfortunately, not all architectures provide
__put_user_unaligned(), so compiles break on them if btrfs is selected.

Instead, just copy the whole struct in / out at the start and end of
operations, respectively.
Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

Commit 2bc55652 (Btrfs: don't update atime on
RO subvolumes) ensures that the access time of an inode is not updated when
the inode lives in a read-only subvolume.
However, if a directory on a read-only subvolume is accessed, the atime is
updated. This results in a write operation to a read-only subvolume. I
believe that access times should never be updated on read-only subvolumes.

To reproduce:

 # mkfs.btrfs -f /dev/dm-3
 (...)
 # mount /dev/dm-3 /mnt
 # btrfs subvol create /mnt/sub
 	Create subvolume '/mnt/sub'
 # mkdir /mnt/sub/dir
 # echo "abc" > /mnt/sub/dir/file
 # btrfs subvol snapshot -r /mnt/sub /mnt/rosnap
 	Create a readonly snapshot of '/mnt/sub' in '/mnt/rosnap'
 # stat /mnt/rosnap/dir
 	File: `/mnt/rosnap/dir'
 	Size: 8         Blocks: 0          IO Block: 4096   directory
 Device: 16h/22d    Inode: 257         Links: 1
 Access: (0755/drwxr-xr-x)  Uid: (    0/    root)   Gid: (    0/    root)
 	Access: 2013-09-11 07:21:49.389157126 -0400
 	Modify: 2013-09-11 07:22:02.330156079 -0400
 	Change: 2013-09-11 07:22:02.330156079 -0400
 # ls /mnt/rosnap/dir
 	file
 # stat /mnt/rosnap/dir
 	File: `/mnt/rosnap/dir'
 	Size: 8         Blocks: 0          IO Block: 4096   directory
 Device: 16h/22d    Inode: 257         Links: 1
 Access: (0755/drwxr-xr-x)  Uid: (    0/    root)   Gid: (    0/    root)
 	Access: 2013-09-11 07:22:56.797151670 -0400
 	Modify: 2013-09-11 07:22:02.330156079 -0400
 	Change: 2013-09-11 07:22:02.330156079 -0400
Reported-by: Koen De Wit <koen.de.wit@oracle.com>
Signed-off-by: Guangyu Sun <guangyu.sun@oracle.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

The kernel log entries for device label %s and device fsid %pU
are missing the btrfs: prefix. Add those here.
Signed-off-by: Frank Holton <fholton@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

It's still possible to flip the filesystem into RW mode after it's
remounted RO due to an abort. There are lots of places that check for
the superblock error bit and will not write data, but we should not let
the filesystem appear read-write.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

This patch makes it possible to set BTRFS_FS_TREE_OBJECTID as the default
subvolume by passing a subvolume id of 0.
Signed-off-by: chandan <chandan@linux.vnet.ibm.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

In btrfs_sync_file(), if the call to btrfs_log_dentry_safe() returns
a negative error (for e.g. -ENOMEM via btrfs_log_inode()), we would
return without ending/freeing the transaction.
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

The BUG() was replaced by btrfs_error() and return -EIO with the
patch "get rid of one BUG() in write_all_supers()", but the missing
mutex_unlock() was overlooked.

The 0-DAY kernel build service from Intel reported the missing
unlock which was found by the coccinelle tool:

    fs/btrfs/disk-io.c:3422:2-8: preceding lock on line 3374
Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

We don't do the iput when we fail to allocate our delayed delalloc work in
__start_delalloc_inodes, fix this.
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

This isn't used for anything anymore, just remove it.
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

This is a left over of how we used to wait for ordered extents, which was to
grab the inode and then run filemap flush on it.  However if we have an ordered
extent then we already are holding a ref on the inode, and we just use
btrfs_start_ordered_extent anyway, so there is no reason to have an extra ref on
the inode to start work on the ordered extent.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

Forever ago I made the worst case calculator say that we could potentially split
into 3 blocks for every level on the way down, which isn't right.  If we split
we're only going to get two new blocks, the one we originally cow'ed and the new
one we're going to split.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

This reverts commit 70afa399.  It is causing
performance issues and wasn't actually correct.  There were problems with the
way we flushed delalloc and that was the real cause of the early enospc.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

Various people have hit a deadlock when running btrfs/011.  This is because when
replacing nocow extents we will take the i_mutex to make sure nobody messes with
the file while we are replacing the extent.  The problem is we are already
holding a transaction open, which is a locking inversion, so instead we need to
save these inodes we find and then process them outside of the transaction.

Further we can't just lock the inode and assume we are good to go.  We need to
lock the extent range and then read back the extent cache for the inode to make
sure the extent really still points at the physical block we want.  If it
doesn't we don't have to copy it.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

So if we have dir_index items in the log that means we also have the inode item
as well, which means that the inode's i_size is correct.  However when we
process dir_index'es we call btrfs_add_link() which will increase the
directory's i_size for the new entry.  To fix this we need to just set the dir
items i_size to 0, and then as we find dir_index items we adjust the i_size.
btrfs_add_link() will do it for new entries, and if the entry already exists we
can just add the name_len to the i_size ourselves.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

A user reported a bug where his log would not replay because he was getting
-EEXIST back.  This was because he had a file moved into a directory that was
logged.  What happens is the file had a lower inode number, and so it is
processed first when replaying the log, and so we add the inode ref in for the
directory it was moved to.  But then we process the directories DIR_INDEX item
and try to add the inode ref for that inode and it fails because we already
added it when we replayed the inode.  To solve this problem we need to just
process any DIR_INDEX items we have in the log first so this all is taken care
of, and then we can replay the rest of the items.  With this patch my reproducer
can remount the file system properly instead of erroring out.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

Liu introduced a local copy of the last log commit for an inode to make sure we
actually log an inode even if a log commit has already taken place.  In order to
make sure we didn't relog the same inode multiple times he set this local copy
to the current trans when we log the inode, because usually we log the inode and
then sync the log.  The exception to this is during rename, we will relog an
inode if the name changed and it is already in the log.  The problem with this
is then we go to sync the inode, and our check to see if the inode has already
been logged is tripped and we don't sync the log.  To fix this we need to _also_
check against the roots last log commit, because it could be less than what is
in our local copy of the log commit.  This fixes a bug where we rename a file
into a directory and then fsync the directory and then on remount the directory
is no longer there.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

If you just create a directory and then fsync that directory and then pull the
power plug you will come back up and the directory will not be there.  That is
because we won't actually create directories if we've logged files inside of
them since they will be created on replay, but in this check we will set our
logged_trans of our current directory if it happens to be a directory, making us
think it doesn't need to be logged.  Fix the logic to only do this to parent
directories.  Thanks,
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>