This gets rid of pdflush for bdi writeout and kupdated style cleaning.
pdflush writeout suffers from lack of locality and also requires more
threads to handle the same workload, since it has to work in a
non-blocking fashion against each queue. This also introduces lumpy
behaviour and potential request starvation, since pdflush can be starved
for queue access if others are accessing it. A sample ffsb workload that
does random writes to files is about 8% faster here on a simple SATA drive
during the benchmark phase. File layout also seems a LOT more smooth in
vmstat:

 r  b   swpd   free   buff  cache   si   so    bi    bo   in    cs us sy id wa
 0  1      0 608848   2652 375372    0    0     0 71024  604    24  1 10 48 42
 0  1      0 549644   2712 433736    0    0     0 60692  505    27  1  8 48 44
 1  0      0 476928   2784 505192    0    0     4 29540  553    24  0  9 53 37
 0  1      0 457972   2808 524008    0    0     0 54876  331    16  0  4 38 58
 0  1      0 366128   2928 614284    0    0     4 92168  710    58  0 13 53 34
 0  1      0 295092   3000 684140    0    0     0 62924  572    23  0  9 53 37
 0  1      0 236592   3064 741704    0    0     4 58256  523    17  0  8 48 44
 0  1      0 165608   3132 811464    0    0     0 57460  560    21  0  8 54 38
 0  1      0 102952   3200 873164    0    0     4 74748  540    29  1 10 48 41
 0  1      0  48604   3252 926472    0    0     0 53248  469    29  0  7 47 45

where vanilla tends to fluctuate a lot in the creation phase:

 r  b   swpd   free   buff  cache   si   so    bi    bo   in    cs us sy id wa
 1  1      0 678716   5792 303380    0    0     0 74064  565    50  1 11 52 36
 1  0      0 662488   5864 319396    0    0     4   352  302   329  0  2 47 51
 0  1      0 599312   5924 381468    0    0     0 78164  516    55  0  9 51 40
 0  1      0 519952   6008 459516    0    0     4 78156  622    56  1 11 52 37
 1  1      0 436640   6092 541632    0    0     0 82244  622    54  0 11 48 41
 0  1      0 436640   6092 541660    0    0     0     8  152    39  0  0 51 49
 0  1      0 332224   6200 644252    0    0     4 102800  728    46  1 13 49 36
 1  0      0 274492   6260 701056    0    0     4 12328  459    49  0  7 50 43
 0  1      0 211220   6324 763356    0    0     0 106940  515    37  1 10 51 39
 1  0      0 160412   6376 813468    0    0     0  8224  415    43  0  6 49 45
 1  1      0  85980   6452 886556    0    0     4 113516  575    39  1 11 54 34
 0  2      0  85968   6452 886620    0    0     0  1640  158   211  0  0 46 54

A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A
SSD based writeback test on XFS performs over 20% better as well, with
the throughput being very stable around 1GB/sec, where pdflush only
manages 750MB/sec and fluctuates wildly while doing so. Random buffered
writes to many files behave a lot better as well, as does random mmap'ed
writes.

A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This adds two new exported functions:

- writeback_inodes_sb(), which only attempts to writeback dirty inodes on
  this super_block, for WB_SYNC_NONE writeout.
- sync_inodes_sb(), which writes out all dirty inodes on this super_block
  and also waits for the IO to complete.
Acked-by: NJan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

I run many ffsb test cases on JBODs (typically 13/12 disks).  Comparing
with kernel 2.6.30, 2.6.31-rc1 has about 16% regression with
ffsb_create_4k.  The sub test case creates files continuously for 10
minitues and every file is 1MB.

Bisect located below patch.

5cee5815 is first bad commit
commit 5cee5815
Author: Jan Kara <jack@suse.cz>
Date:   Mon Apr 27 16:43:51 2009 +0200

    vfs: Make sys_sync() use fsync_super() (version 4)

    It is unnecessarily fragile to have two places (fsync_super() and do_sync())
    doing data integrity sync of the filesystem. Alter __fsync_super() to
    accommodate needs of both callers and use it. So after this patch
    __fsync_super() is the only place where we gather all the calls needed to
    properly send all data on a filesystem to disk.

As a matter of fact, ffsb calls sys_sync in the end to make sure all data
is flushed to disks and the flushing is counted into the result.  vmstat
shows ffsb is blocked when syncing for a long time.  With 2.6.30, ffsb is
blocked for a short time.

I checked the patch and did experiments to recover the original methods.
Eventually, the root cause is the patch deletes the calling to
wakeup_pdflush when syncing, so only ffsb is blocked on disk I/O.
wakeup_pdflush could ask pdflush to write back pages with ffsb at the
same time.

[akpm@linux-foundation.org: restore comment too]
Signed-off-by: NZhang Yanmin <yanmin_zhang@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: NJens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Now that all filesystems provide ->sync_fs methods we can change
__sync_filesystem to only call ->sync_fs.

This gives us a clear separation between periodic writeouts which
are driven by ->write_super and data integrity syncs that go
through ->sync_fs. (modulo file_fsync which is also going away)
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Push down lock_super into ->write_super instances and remove it from the
caller.

Following filesystem don't need ->s_lock in ->write_super and are skipped:

 * bfs, nilfs2 - no other uses of s_lock and have internal locks in
	->write_super
 * ext2 - uses BKL in ext2_write_super and has internal calls without s_lock
 * reiserfs - no other uses of s_lock as has reiserfs_write_lock (BKL) in
 	->write_super
 * xfs - no other uses of s_lock and uses internal lock (buffer lock on
	superblock buffer) to serialize ->write_super.  Also xfs_fs_write_super
	is superflous and will go away in the next merge window
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Make sure a superblock really is writeable by checking MS_RDONLY
under s_umount.  sync_filesystems needed some re-arragement for
that, but all but one sync_filesystem caller had the correct locking
already so that we could add that check there.  cachefiles grew
s_umount locking.

I've also added a WARN_ON to sync_filesystem to assert this for
future callers.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Introduce this function which just writes all the quota structures but
avoids all the syncing and cache pruning work to expose quota structures
to userspace. Use this function from __sync_filesystem when wait == 0.
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Currently the VFS calls vfs_dq_sync to sync out disk quotas for a given
superblock.  This is a small wrapper around sync_dquots which for the
case of a non-NULL superblock is a small wrapper around quota_sync_sb.

Just make quota_sync_sb global (rename it to sync_quota_sb) and call it
directly.  Also call it directly for those cases in quota.c that have a
superblock and leave sync_dquots purely an iterator over sync_quota_sb and
remove it's superblock argument.

To make this nicer move the check for the lack of a quota_sync method
from the callers into sync_quota_sb.

[folded build fix from Alexander Beregalov <a.beregalov@gmail.com>]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Rename the function so that it better describe what it really does. Also
remove the unnecessary include of buffer_head.h.
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Move sync_filesystems(), __fsync_super(), fsync_super() from
super.c to sync.c where it fits better.

[build fixes folded]
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

It is unnecessarily fragile to have two places (fsync_super() and do_sync())
doing data integrity sync of the filesystem. Alter __fsync_super() to
accommodate needs of both callers and use it. So after this patch
__fsync_super() is the only place where we gather all the calls needed to
properly send all data on a filesystem to disk.

Nice bonus is that we get a complete livelock avoidance and write_supers()
is now only used for periodic writeback of superblocks.

sync_blockdevs() introduced a couple of patches ago is gone now.

[build fixes folded]
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

So far, do_sync() called:
  sync_inodes(0);
  sync_supers();
  sync_filesystems(0);
  sync_filesystems(1);
  sync_inodes(1);

This ordering makes it kind of hard for filesystems as sync_inodes(0) need not
submit all the IO (for example it skips inodes with I_SYNC set) so e.g. forcing
transaction to disk in ->sync_fs() is not really enough. Therefore sys_sync has
not been completely reliable on some filesystems (ext3, ext4, reiserfs, ocfs2
and others are hit by this) when racing e.g. with background writeback. A
similar problem hits also other filesystems (e.g. ext2) because of
write_supers() being called before the sync_inodes(1).

Change the ordering of calls in do_sync() - this requires a new function
sync_blockdevs() to preserve the property that block devices are always synced
after write_super() / sync_fs() call.

The same issue is fixed in __fsync_super() function used on umount /
remount read-only.

[AV: build fixes]
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Opencode a cheasy approach with kevent. The idea here is that we'll
add some generic delayed work infrastructure, which probably wont be
based on pdflush (or maybe it will, in which case we can just add it
back).

This is in preparation for getting rid of pdflush completely.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Use lowercase names of quota functions instead of old uppercase ones.
Signed-off-by: NJan Kara <jack@suse.cz>
CC: Alexander Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>

System calls with an unsigned long long argument can't be converted with
the standard wrappers since that would include a cast to long, which in
turn means that we would lose the upper 32 bit on 32 bit architectures.
Also semctl can't use the standard wrapper since it has a 'union'
parameter.

So we handle them as special case and add some extra wrappers instead.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>

Chris Mason notices do_sync_mapping_range didn't actually ask for data
integrity writeout.  Unfortunately, it is advertised as being usable for
data integrity operations.

This is a data integrity bug.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fsync currently has a fdatawrite/fdatawait pair around the method call,
and a mutex_lock/unlock of the inode mutex.  All callers of fsync have
to duplicate this, but we have a few and most of them don't quite get
it right.  This patch adds a new vfs_fsync that takes care of this.
It's a little more complicated as usual as ->fsync might get a NULL file
pointer and just a dentry from nfsd, but otherwise gets afile and we
want to take the mapping and file operations from it when it is there.

Notes on the fsync callers:

 - ecryptfs wasn't calling filemap_fdatawrite / filemap_fdatawait on the
   	lower file
 - coda wasn't calling filemap_fdatawrite / filemap_fdatawait on the host
	file, and returning 0 when ->fsync was missing
 - shm wasn't calling either filemap_fdatawrite / filemap_fdatawait nor
   taking i_mutex.  Now given that shared memory doesn't have disk
   backing not doing anything in fsync seems fine and I left it out of
   the vfs_fsync conversion for now, but in that case we might just
   not pass it through to the lower file at all but just call the no-op
   simple_sync_file directly.

[and now actually export vfs_fsync]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

[akpm@linux-foundation.org: fix comment text]
Signed-off-by: NPavel Machek <pavel@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We need to check ->s_dirt before calling write_super().  It became the cause
of an unneeded write.

This bug was noticed by Sudhanshu Saxena.
Signed-off-by: NOGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Not all the world is an i386.  Many architectures need 64-bit arguments to be
aligned in suitable pairs of registers, and the original
sys_sync_file_range(int, loff_t, loff_t, int) was therefore wasting an
argument register for padding after the first integer.  Since we don't
normally have more than 6 arguments for system calls, that left no room for
the final argument on some architectures.

Fix this by introducing sys_sync_file_range2(int, int, loff_t, loff_t) which
all fits nicely.  In fact, ARM already had that, but called it
sys_arm_sync_file_range.  Move it to fs/sync.c and rename it, then implement
the needed compatibility routine.  And stop the missing syscall check from
bitching about the absence of sys_sync_file_range() if we've implemented
sys_sync_file_range2() instead.

Tested on PPC32 and with 32-bit and 64-bit userspace on PPC64.
Signed-off-by: NDavid Woodhouse <dwmw2@infradead.org>
Acked-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Remove do_sync_file_range() and convert callers to just use
do_sync_mapping_range().
Signed-off-by: NMark Fasheh <mark.fasheh@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

do_sync_file_range() accepts a file * from which it takes an address_space to
sync.  Abstract out the bulk of the function into do_sync_mapping_range()
which takes the address_space directly.  This way callers who want to sync an
address_space directly can take advantage of the functionality provided.

do_sync_file_range() is preserved as a small wrapper around
do_sync_mapping_range().

Ocfs2 in particular would like to use this to initiate a sync of a specific
inode range during truncate, where a file * may not be available.
Signed-off-by: NMark Fasheh <mark.fasheh@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

This patch changes struct file to use struct path instead of having
independent pointers to struct dentry and struct vfsmount, and converts all
users of f_{dentry,vfsmnt} in fs/ to use f_path.{dentry,mnt}.

Additionally, it adds two #define's to make the transition easier for users of
the f_dentry and f_vfsmnt.
Signed-off-by: NJosef "Jeff" Sipek <jsipek@cs.sunysb.edu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

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

Move some functions out of the buffering code that aren't strictly buffering
specific.  This is a precursor to being able to disable the block layer.

 (*) Moved some stuff out of fs/buffer.c:

     (*) The file sync and general sync stuff moved to fs/sync.c.

     (*) The superblock sync stuff moved to fs/super.c.

     (*) do_invalidatepage() moved to mm/truncate.c.

     (*) try_to_release_page() moved to mm/filemap.c.

 (*) Moved some related declarations between header files:

     (*) declarations for do_invalidatepage() and try_to_release_page() moved
     	 to linux/mm.h.

     (*) __set_page_dirty_buffers() moved to linux/buffer_head.h.
Signed-Off-By: NDavid Howells <dhowells@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When a writeback_control's `start' and `end' fields are used to
indicate a one-byte-range starting at file offset zero, the required
values of .start=0,.end=0 mean that the ->writepages() implementation
has no way of telling that it is being asked to perform a range
request.  Because we're currently overloading (start == 0 && end == 0)
to mean "this is not a write-a-range request".

To make all this sane, the patch changes range of writeback_control.

So caller does: If it is calling ->writepages() to write pages, it
sets range (range_start/end or range_cyclic) always.

And if range_cyclic is true, ->writepages() thinks the range is
cyclic, otherwise it just uses range_start and range_end.

This patch does,

    - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h
      -1 is usually ok for range_end (type is long long). But, if someone did,

		range_end += val;		range_end is "val - 1"
		u64val = range_end >> bits;	u64val is "~(0ULL)"

      or something, they are wrong. So, this adds LLONG_MAX to avoid nasty
      things, and uses LLONG_MAX for range_end.

    - All callers of ->writepages() sets range_start/end or range_cyclic.

    - Fix updates of ->writeback_index. It seems already bit strange.
      If it starts at 0 and ended by check of nr_to_write, this last
      index may reduce chance to scan end of file.  So, this updates
      ->writeback_index only if range_cyclic is true or whole-file is
      scanned.
Signed-off-by: NOGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Anton Altaparmakov <aia21@cantab.net>
Cc: Steven French <sfrench@us.ibm.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Ulrich suggested that the `flags' arg to sync_file_range() become unsigned.

Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Remove the recently-added LINUX_FADV_ASYNC_WRITE and LINUX_FADV_WRITE_WAIT
fadvise() additions, do it in a new sys_sync_file_range() syscall instead.
Reasons:

- It's more flexible.  Things which would require two or three syscalls with
  fadvise() can be done in a single syscall.

- Using fadvise() in this manner is something not covered by POSIX.

The patch wires up the syscall for x86.

The sycall is implemented in the new fs/sync.c.  The intention is that we can
move sys_fsync(), sys_fdatasync() and perhaps sys_sync() into there later.

Documentation for the syscall is in fs/sync.c.

A test app (sync_file_range.c) is in
http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz.

The available-to-GPL-modules do_sync_file_range() is for knfsd: "A COMMIT can
say NFS_DATA_SYNC or NFS_FILE_SYNC.  I can skip the ->fsync call for
NFS_DATA_SYNC which is hopefully the more common."

Note: the `async' writeout mode SYNC_FILE_RANGE_WRITE will turn synchronous if
the queue is congested.  This is trivial to fix: add a new flag bit, set
wbc->nonblocking.  But I'm not sure that we want to expose implementation
details down to that level.

Note: it's notable that we can sync an fd which wasn't opened for writing.
Same with fsync() and fdatasync()).

Note: the code takes some care to handle attempts to sync file contents
outside the 16TB offset on 32-bit machines.  It makes such attempts appear to
succeed, for best 32-bit/64-bit compatibility.  Perhaps it should make such
requests fail...

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>