Commit e09b457b (block: simplify holder symlink handling) incorrectly
assumed that there is only one link at maximum.  dm may use multiple
links and expects block layer to track reference count for each link,
which is different from and unrelated to the exclusive device holder
identified by @holder when the device is opened.

Remove the single holder assumption and automatic removal of the link
and revive the per-link reference count tracking.  The code
essentially behaves the same as before commit e09b457b sans the
unnecessary kobject reference count dancing.

While at it, note that this facility should not be used by anyone else
than the current ones.  Sysfs symlinks shouldn't be abused like this
and the whole thing doesn't belong in the block layer at all.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NMilan Broz <mbroz@redhat.com>
Cc: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: Neil Brown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

RCU free the struct inode. This will allow:

- Subsequent store-free path walking patch. The inode must be consulted for
  permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
  to take i_lock no longer need to take sb_inode_list_lock to walk the list in
  the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
  page lock to follow page->mapping.

The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.

In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.

The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Currently, media presence polling for removeable block devices is done
from userland.  There are several issues with this.

* Polling is done by periodically opening the device.  For SCSI
  devices, the command sequence generated by such action involves a
  few different commands including TEST_UNIT_READY.  This behavior,
  while perfectly legal, is different from Windows which only issues
  single command, GET_EVENT_STATUS_NOTIFICATION.  Unfortunately, some
  ATAPI devices lock up after being periodically queried such command
  sequences.

* There is no reliable and unintrusive way for a userland program to
  tell whether the target device is safe for media presence polling.
  For example, polling for media presence during an on-going burning
  session can make it fail.  The polling program can avoid this by
  opening the device with O_EXCL but then it risks making a valid
  exclusive user of the device fail w/ -EBUSY.

* Userland polling is unnecessarily heavy and in-kernel implementation
  is lighter and better coordinated (workqueue, timer slack).

This patch implements framework for in-kernel disk event handling,
which includes media presence polling.

* bdops->check_events() is added, which supercedes ->media_changed().
  It should check whether there's any pending event and return if so.
  Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and
  DISK_EVENT_EJECT_REQUEST.  ->check_events() is guaranteed not to be
  called parallelly.

* gendisk->events and ->async_events are added.  These should be
  initialized by block driver before passing the device to add_disk().
  The former contains the mask of all supported events and the latter
  the mask of all events which the device can report without polling.
  /sys/block/*/events[_async] export these to userland.

* Kernel parameter block.events_dfl_poll_msecs controls the system
  polling interval (default is 0 which means disable) and
  /sys/block/*/events_poll_msecs control polling intervals for
  individual devices (default is -1 meaning use system setting).  Note
  that if a device can report all supported events asynchronously and
  its polling interval isn't explicitly set, the device won't be
  polled regardless of the system polling interval.

* If a device is opened exclusively with write access, event checking
  is automatically disabled until all write exclusive accesses are
  released.

* There are event 'clearing' events.  For example, both of currently
  defined events are cleared after the device has been successfully
  opened.  This information is passed to ->check_events() callback
  using @clearing argument as a hint.

* Event checking is always performed from system_nrt_wq and timer
  slack is set to 25% for polling.

* Nothing changes for drivers which implement ->media_changed() but
  not ->check_events().  Going forward, all drivers will be converted
  to ->check_events() and ->media_change() will be dropped.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

The big kernel lock has been removed from all these files at some point,
leaving only the #include.

Remove this too as a cleanup.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

After recent blkdev_get() modifications, open_by_devnum() and
open_bdev_exclusive() are simple wrappers around blkdev_get().
Replace them with blkdev_get_by_dev() and blkdev_get_by_path().

blkdev_get_by_dev() is identical to open_by_devnum().
blkdev_get_by_path() is slightly different in that it doesn't
automatically add %FMODE_EXCL to @mode.

All users are converted.  Most conversions are mechanical and don't
introduce any behavior difference.  There are several exceptions.

* btrfs now sets FMODE_EXCL in btrfs_device->mode, so there's no
  reason to OR it explicitly on blkdev_put().

* gfs2, nilfs2 and the generic mount_bdev() now set FMODE_EXCL in
  sb->s_mode.

* With the above changes, sb->s_mode now always should contain
  FMODE_EXCL.  WARN_ON_ONCE() added to kill_block_super() to detect
  errors.

The new blkdev_get_*() functions are with proper docbook comments.
While at it, add function description to blkdev_get() too.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Joern Engel <joern@lazybastard.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jan Kara <jack@suse.cz>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
Cc: reiserfs-devel@vger.kernel.org
Cc: xfs-masters@oss.sgi.com
Cc: Alexander Viro <viro@zeniv.linux.org.uk>

bdev read-only status can be queried using bdev_read_only() and may
change while the device is being opened.  Enforce it by checking it
from blkdev_get() after open succeeds.

This makes bdev_read_only() check in open_bdev_exclusive() and
fsg_lun_open() unnecessary.  Drop them.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: David Brownell <dbrownell@users.sourceforge.net>
Cc: linux-usb@vger.kernel.org

With claim/release rolled into blkdev_get/put(), there's no reason to
keep bd_abort/finish_claim(), __bd_claim() and bd_release() as
separate functions.  It only makes the code difficult to follow.
Collapse them into blkdev_get/put().  This will ease future changes
around claim/release.
Signed-off-by: NTejun Heo <tj@kernel.org>

Over time, block layer has accumulated a set of APIs dealing with bdev
open, close, claim and release.

* blkdev_get/put() are the primary open and close functions.

* bd_claim/release() deal with exclusive open.

* open/close_bdev_exclusive() are combination of open and claim and
  the other way around, respectively.

* bd_link/unlink_disk_holder() to create and remove holder/slave
  symlinks.

* open_by_devnum() wraps bdget() + blkdev_get().

The interface is a bit confusing and the decoupling of open and claim
makes it impossible to properly guarantee exclusive access as
in-kernel open + claim sequence can disturb the existing exclusive
open even before the block layer knows the current open if for another
exclusive access.  Reorganize the interface such that,

* blkdev_get() is extended to include exclusive access management.
  @holder argument is added and, if is @FMODE_EXCL specified, it will
  gain exclusive access atomically w.r.t. other exclusive accesses.

* blkdev_put() is similarly extended.  It now takes @mode argument and
  if @FMODE_EXCL is set, it releases an exclusive access.  Also, when
  the last exclusive claim is released, the holder/slave symlinks are
  removed automatically.

* bd_claim/release() and close_bdev_exclusive() are no longer
  necessary and either made static or removed.

* bd_link_disk_holder() remains the same but bd_unlink_disk_holder()
  is no longer necessary and removed.

* open_bdev_exclusive() becomes a simple wrapper around lookup_bdev()
  and blkdev_get().  It also has an unexpected extra bdev_read_only()
  test which probably should be moved into blkdev_get().

* open_by_devnum() is modified to take @holder argument and pass it to
  blkdev_get().

Most of bdev open/close operations are unified into blkdev_get/put()
and most exclusive accesses are tested atomically at the open time (as
it should).  This cleans up code and removes some, both valid and
invalid, but unnecessary all the same, corner cases.

open_bdev_exclusive() and open_by_devnum() can use further cleanup -
rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop
special features.  Well, let's leave them for another day.

Most conversions are straight-forward.  drbd conversion is a bit more
involved as there was some reordering, but the logic should stay the
same.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NNeil Brown <neilb@suse.de>
Acked-by: NRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Acked-by: NPhilipp Reisner <philipp.reisner@linbit.com>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <joel.becker@oracle.com>
Cc: Alex Elder <aelder@sgi.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: dm-devel@redhat.com
Cc: drbd-dev@lists.linbit.com
Cc: Leo Chen <leochen@broadcom.com>
Cc: Scott Branden <sbranden@broadcom.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Joern Engel <joern@logfs.org>
Cc: reiserfs-devel@vger.kernel.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>

Code to manage symlinks in /sys/block/*/{holders|slaves} are overly
complex with multiple holder considerations, redundant extra
references to all involved kobjects, unused generic kobject holder
support and unnecessary mixup with bd_claim/release functionalities.

Strip it down to what's necessary (single gendisk holder) and make it
use a separate interface.  This is a step for cleaning up
bd_claim/release.  This patch makes dm-table slightly more complex but
it will be simplified again with further changes.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NNeil Brown <neilb@suse.de>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The use of the same inode list structure (inode->i_list) for two
different list constructs with different lifecycles and purposes
makes it impossible to separate the locking of the different
operations. Therefore, to enable the separation of the locking of
the writeback and reclaim lists, split the inode->i_list into two
separate lists dedicated to their specific tracking functions.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

bdev inodes can remain dirty even after their last close. Hence the
BDI associated with the bdev->inode gets modified duringthe last
close to point to the default BDI. However, the bdev inode still
needs to be moved to the dirty lists of the new BDI, otherwise it
will corrupt the writeback list is was left on.

Add a new function bdev_inode_switch_bdi() to move all the bdi state
from the old bdi to the new one safely. This is only a temporary
measure until the bdev inode<->bdi lifecycle problems are sorted
out.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Clones an existing reference to inode; caller must already hold one.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

All the blkdev_issue_* helpers can only sanely be used for synchronous
caller.  To issue cache flushes or barriers asynchronously the caller needs
to set up a bio by itself with a completion callback to move the asynchronous
state machine ahead.  So drop the BLKDEV_IFL_WAIT flag that is always
specified when calling blkdev_issue_* and also remove the now unused flags
argument to blkdev_issue_flush and blkdev_issue_zeroout.  For
blkdev_issue_discard we need to keep it for the secure discard flag, which
gains a more descriptive name and loses the bitops vs flag confusion.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

The cgroup device whitelist code gets confused when trying to grant
permission to a disk partition that is not currently open.  Part of
blkdev_open() includes __blkdev_get() on the whole disk.

Basically, the only ways to reliably allow a cgroup access to a partition
on a block device when using the whitelist are to 1) also give it access
to the whole block device or 2) make sure the partition is already open in
a different context.

The patch avoids the cgroup check for the whole disk case when opening a
partition.

Addresses https://bugzilla.redhat.com/show_bug.cgi?id=589662Signed-off-by: NChris Wright <chrisw@sous-sol.org>
Acked-by: NSerge E. Hallyn <serue@us.ibm.com>
Tested-by: NSerge E. Hallyn <serue@us.ibm.com>
Reported-by: NVivek Goyal <vgoyal@redhat.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Daniel P. Berrange" <berrange@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Move the call to vmtruncate to get rid of accessive blocks to the callers
in preparation of the new truncate sequence and rename the non-truncating
version to block_write_begin.

While we're at it also remove several unused arguments to block_write_begin.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Move the call to vmtruncate to get rid of accessive blocks to the callers
in prepearation of the new truncate calling sequence.  This was only done
for DIO_LOCKING filesystems, so the __blockdev_direct_IO_newtrunc variant
was not needed anyway.  Get rid of blockdev_direct_IO_no_locking and
its _newtrunc variant while at it as just opencoding the two additional
paramters is shorted than the name suffix.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The open and release block_device_operations are currently
called with the BKL held. In order to change that, we must
first make sure that all drivers that currently rely
on this have no regressions.

This blindly pushes the BKL into all .open and .release
operations for all block drivers to prepare for the
next step. The drivers can subsequently replace the BKL
with their own locks or remove it completely when it can
be shown that it is not needed.

The functions blkdev_get and blkdev_put are the only
remaining users of the big kernel lock in the block
layer, besides a few uses in the ioctl code, none
of which need to serialize with blkdev_{get,put}.

Most of these two functions is also under the protection
of bdev->bd_mutex, including the actual calls to
->open and ->release, and the common code does not
access any global data structures that need the BKL.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NChristoph Hellwig <hch@infradead.org>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

bd_prepare_to_claim() incorrectly allowed multiple attempts for
exclusive open to progress in parallel if the attempting holders are
identical.  This triggered BUG_ON() as reported in the following bug.

  https://bugzilla.kernel.org/show_bug.cgi?id=16393

__bd_abort_claiming() is used to finish claiming blocks and doesn't
work if multiple openers are inside a claiming block.  Allowing
multiple parallel open attempts to continue doesn't gain anything as
those are serialized down in the call chain anyway.  Fix it by always
allowing only single open attempt in a claiming block.

This problem can easily be reproduced by adding a delay after
bd_prepare_to_claim() and attempting to mount two partitions of a
disk.

stable: only applicable to v2.6.35
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NMarkus Trippelsdorf <markus@trippelsdorf.de>
Cc: stable@kernel.org
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We do the same BUG_ON() just a line later when calling into
__bd_abort_claiming().
Reported-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

I don't like the subtle multi-context code in bd_claim (ie.  detects where it
has been called based on bd_claiming). It seems clearer to just require a new
function to finish a 2-part claim.

Also improve commentary in bd_start_claiming as to how it should
be used.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

bd_start_claiming has an unbalanced module_put introduced in 6b4517a7.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

Convert simple filesystems: ramfs, configfs, sysfs, block_dev to new truncate
sequence.

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Currently the way we do freezing is by passing sb>s_bdev to freeze_bdev and then
letting it do all the work.  But freezing is more of an fs thing, and doesn't
really have much to do with the bdev at all, all the work gets done with the
super.  In btrfs we do not populate s_bdev, since we can have multiple bdev's
for one fs and setting s_bdev makes removing devices from a pool kind of tricky.
This means that freezing a btrfs filesystem fails, which causes us to corrupt
with things like tux-on-ice which use the fsfreeze mechanism.  So instead of
populating sb->s_bdev with a random bdev in our pool, I've broken the actual fs
freezing stuff into freeze_super and thaw_super.  These just take the
super_block that we're freezing and does the appropriate work.  It's basically
just copy and pasted from freeze_bdev.  I've then converted freeze_bdev over to
use the new super helpers.  I've tested this with ext4 and btrfs and verified
everything continues to work the same as before.

The only new gotcha is multiple calls to the fsfreeze ioctl will return EBUSY if
the fs is already frozen.  I thought this was a better solution than adding a
freeze counter to the super_block, but if everybody hates this idea I'm open to
suggestions.  Thanks,
Signed-off-by: NJosef Bacik <josef@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The patch just convert all blkdev_issue_xxx function to common
set of flags. Wait/allocation semantics preserved.
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Currently, device claiming for exclusive open is done after low level
open - disk->fops->open() - has completed successfully.  This means
that exclusive open attempts while a device is already exclusively
open will fail only after disk->fops->open() is called.

cdrom driver issues commands during open() which means that O_EXCL
open attempt can unintentionally inject commands to in-progress
command stream for burning thus disturbing burning process.  In most
cases, this doesn't cause problems because the first command to be
issued is TUR which most devices can process in the middle of burning.
However, depending on how a device replies to TUR during burning,
cdrom driver may end up issuing further commands.

This can't be resolved trivially by moving bd_claim() before doing
actual open() because that means an open attempt which will end up
failing could interfere other legit O_EXCL open attempts.
ie. unconfirmed open attempts can fail others.

This patch resolves the problem by introducing claiming block which is
started by bd_start_claiming() and terminated either by bd_claim() or
bd_abort_claiming().  bd_claim() from inside a claiming block is
guaranteed to succeed and once a claiming block is started, other
bd_start_claiming() or bd_claim() attempts block till the current
claiming block is terminated.

bd_claim() can still be used standalone although now it always
synchronizes against claiming blocks, so the existing users will keep
working without any change.

blkdev_open() and open_bdev_exclusive() are converted to use claiming
blocks so that exclusive open attempts from these functions don't
interfere with the existing exclusive open.

This problem was discovered while investigating bko#15403.

  https://bugzilla.kernel.org/show_bug.cgi?id=15403

The burning problem itself can be resolved by updating userspace
probing tools to always open w/ O_EXCL.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NMatthias-Christian Ott <ott@mirix.org>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Factor out bd_may_claim() from bd_claim(), add comments and apply a
couple of cosmetic edits.  This is to prepare for further updates to
claim path.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

We are seeing a large regression in database performance on recent
kernels.  The database opens a block device with O_DIRECT|O_SYNC and a
number of threads write to different regions of the file at the same time.

A simple test case is below.  I haven't defined DEVICE since getting it
wrong will destroy your data :) On an 3 disk LVM with a 64k chunk size we
see about 17MB/sec and only a few threads in IO wait:

procs  -----io---- -system-- -----cpu------
 r  b     bi    bo   in   cs us sy id wa st
 0  3      0 16170  656 2259  0  0 86 14  0
 0  2      0 16704  695 2408  0  0 92  8  0
 0  2      0 17308  744 2653  0  0 86 14  0
 0  2      0 17933  759 2777  0  0 89 10  0

Most threads are blocking in vfs_fsync_range, which has:

        mutex_lock(&mapping->host->i_mutex);
        err = fop->fsync(file, dentry, datasync);
        if (!ret)
                ret = err;
        mutex_unlock(&mapping->host->i_mutex);

commit 148f948b (vfs: Introduce new
helpers for syncing after writing to O_SYNC file or IS_SYNC inode) offers
some explanation of what is going on:

    Use these new helpers for syncing from generic VFS functions. This makes
    O_SYNC writes to block devices acquire i_mutex for syncing. If we really
    care about this, we can make block_fsync() drop the i_mutex and reacquire
    it before it returns.

Thanks Jan for such a good commit message!  As well as dropping i_mutex,
Christoph suggests we should remove the call to sync_blockdev():

> sync_blockdev is an overcomplicated alias for filemap_write_and_wait on
> the block device inode, which is exactly what we did just before calling
> into ->fsync

The patch below incorporates both suggestions. With it the testcase improves
from 17MB/s to 68M/sec:

procs  -----io---- -system-- -----cpu------
 r  b     bi    bo   in   cs us sy id wa st
 0  7      0 65536 1000 3878  0  0 70 30  0
 0 34      0 69632 1016 3921  0  1 46 53  0
 0 57      0 69632 1000 3921  0  0 55 45  0
 0 53      0 69640  754 4111  0  0 81 19  0

Testcase:

#define _GNU_SOURCE
#include <stdio.h>
#include <pthread.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>

#define NR_THREADS 64
#define BUFSIZE (64 * 1024)

#define DEVICE "/dev/mapper/XXXXXX"

#define ALIGN(VAL, SIZE) (((VAL)+(SIZE)-1) & ~((SIZE)-1))

static int fd;

static void *doit(void *arg)
{
	unsigned long offset = (long)arg;
	char *b, *buf;

	b = malloc(BUFSIZE + 1024);
	buf = (char *)ALIGN((unsigned long)b, 1024);
	memset(buf, 0, BUFSIZE);

	while (1)
		pwrite(fd, buf, BUFSIZE, offset);
}

int main(int argc, char *argv[])
{
	int flags = O_RDWR|O_DIRECT;
	int i;
	unsigned long offset = 0;

	if (argc > 1 && !strcmp(argv[1], "O_SYNC"))
		flags |= O_SYNC;

	fd = open(DEVICE, flags);
	if (fd == -1) {
		perror("open");
		exit(1);
	}

	for (i = 0; i < NR_THREADS-1; i++) {
		pthread_t tid;
		pthread_create(&tid, NULL, doit, (void *)offset);
		offset += BUFSIZE;
	}
	doit((void *)offset);

	return 0;
}
Signed-off-by: NAnton Blanchard <anton@samba.org>
Acked-by: NJan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Requested by hch, for consistency now it is exported.

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Anton Blanchard <anton@samba.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit 148f948b (vfs: Introduce new
helpers for syncing after writing to O_SYNC file or IS_SYNC inode) broke
the raw driver.

We now call through generic_file_aio_write -> generic_write_sync ->
vfs_fsync_range.  vfs_fsync_range has:

        if (!fop || !fop->fsync) {
                ret = -EINVAL;
                goto out;
        }

But drivers/char/raw.c doesn't set an fsync method.

We have two options: fix it or remove the raw driver completely.  I'm
happy to do either, the fact this has been broken for so long suggests it
is rarely used.

The patch below adds an fsync method to the raw driver.  My knowledge of
the block layer is pretty sketchy so this could do with a once over.

If we instead decide to remove the raw driver, this patch might still be
useful as a backport to 2.6.33 and 2.6.32.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <jens.axboe@oracle.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Tested-by: NJeff Moyer <jmoyer@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Thanks Thomas and Christoph for testing and review.
I removed 'smp_wmb()' before up_write from the previous patch,
since up_write() should have necessary ordering constraints.
(I.e. the change of s_frozen is visible to others after up_write)
I'm quite sure the change is harmless but if you are uncomfortable
with Tested-by/Reviewed-by on the modified patch, please remove them.

If MS_RDONLY, freeze_bdev should just up_write(s_umount) instead of
deactivate_locked_super().
Also, keep sb->s_frozen consistent so that remount can check the frozen state.

Otherwise a crash reported here can happen:
http://lkml.org/lkml/2010/1/16/37
http://lkml.org/lkml/2010/1/28/53

This patch should be applied for 2.6.32 stable series, too.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NThomas Backlund <tmb@mandriva.org>
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: stable@kernel.org
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Currently there is no barrier support in the block device code.  That
means we cannot guarantee any sort of data integerity when using the
block device node with dis kwrite caches enabled.  Using the raw block
device node is a typical use case for virtualization (and I assume
databases, too).  This patch changes block_fsync to issue a cache flush
and thus make fsync on block device nodes actually useful.

Note that in mainline we would also need to add such code to the
->aio_write method for O_SYNC handling, but assuming that Jan's patch
series for the O_SYNC rewrite goes in it will also call into ->fsync
for 2.6.32.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

commit 0762b8bd
(from 14 months ago) introduced a use-after-free bug which has just
recently started manifesting in my md testing.
I tried git bisect to find out what caused the bug to start
manifesting, and it could have been the recent change to
blk_unregister_queue (48c0d4d4) but the results were inconclusive.

This patch certainly fixes my symptoms and looks correct as the two
calls are now in the same order as elsewhere in that function.
Signed-off-by: NNeilBrown <neilb@suse.de>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Currently we held s_umount while a filesystem is frozen, despite that we
might return to userspace and unlock it from a different process.  Instead
grab an active reference to keep the file system busy and add an explicit
check for frozen filesystems in remount and reject the remount instead
of blocking on s_umount.

Add a new get_active_super helper to super.c for use by freeze_bdev that
grabs an active reference to a superblock from a given block device.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Now that we have the freeze count there is not much reason for bd_mount_sem
anymore.  The actual freeze/thaw operations are serialized using the
bd_fsfreeze_mutex, and the only other place we take bd_mount_sem is
get_sb_bdev which tries to prevent mounting a filesystem while the block
device is frozen.  Instead of add a check for bd_fsfreeze_count and
return -EBUSY if a filesystem is frozen.  While that is a change in user
visible behaviour a failing mount is much better for this case rather
than having the mount process stuck uninterruptible for a long time.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>