Filesystems often to do compute intensive operation on some
metadata.  If this operation is repeated many times, it can be very
expensive.  It would be much nicer if the operation could be performed
once before a buffer goes to disk.

This adds triggers to jbd2 buffer heads.  Just before writing a metadata
buffer to the journal, jbd2 will optionally call a commit trigger associated
with the buffer.  If the journal is aborted, an abort trigger will be
called on any dirty buffers as they are dropped from pending
transactions.

ocfs2 will use this feature.

Initially I tried to come up with a more generic trigger that could be
used for non-buffer-related events like transaction completion.  It
doesn't tie nicely, because the information a buffer trigger needs
(specific to a journal_head) isn't the same as what a transaction
trigger needs (specific to a tranaction_t or perhaps journal_t).  So I
implemented a buffer set, with the understanding that
journal/transaction wide triggers should be implemented separately.

There is only one trigger set allowed per buffer.  I can't think of any
reason to attach more than one set.  Contrast this with a journal or
transaction in which multiple places may want to watch the entire
transaction separately.

The trigger sets are considered static allocation from the jbd2
perspective.  ocfs2 will just have one trigger set per block type,
setting the same set on every bh of the same type.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The multiblock allocator needs to be able to release blocks (and issue
a blkdev discard request) when the transaction which freed those
blocks is committed.  Previously this was done via a polling mechanism
when blocks are allocated or freed.  A much better way of doing things
is to create a jbd2 callback function and attaching the list of blocks
to be freed directly to the transaction structure.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

the names were too generic:

 drivers/uio/uio.c:87: error: expected identifier or '(' before 'do'
 drivers/uio/uio.c:87: error: expected identifier or '(' before 'while'
 drivers/uio/uio.c:113: error: 'map_release' undeclared here (not in a function)
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Most the free-standing lock_acquire() usages look remarkably similar, sweep
them into a new helper.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NJan Kara <jack@suse.cz>

This patch adds necessary framework into JBD2 to be able to track inodes
with each transaction and write-out their dirty data during transaction
commit time.

This new ordered mode brings all sorts of advantages such as possibility 
to get rid of journal heads and buffer heads for data buffers in ordered 
mode, better ordering of writes on transaction commit, simplification of
 some JBD code, no more anonymous pages when truncate of data being 
committed happens.  Also with this new ordered mode, delayed allocation 
on ordered mode is much simpler.
Signed-off-by: NJan Kara <jack@suse.cz>

journal_try_to_free_buffers() could race with jbd commit transaction
when the later is holding the buffer reference while waiting for the
data buffer to flush to disk. If the caller of
journal_try_to_free_buffers() request tries hard to release the buffers,
it will treat the failure as error and return back to the caller. We
have seen the directo IO failed due to this race.  Some of the caller of
releasepage() also expecting the buffer to be dropped when passed with
GFP_KERNEL mask to the releasepage()->journal_try_to_free_buffers().

With this patch, if the caller is passing the GFP_KERNEL to indicating
this call could wait, in case of try_to_free_buffers() failed, let's
waiting for journal_commit_transaction() to finish commit the current
committing transaction , then try to free those buffers again with
journal locked.
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Reviewed-by: Badari Pulavarty <pbadari@us.ibm.com> 
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

__FUNCTION__ is gcc-specific, use __func__
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Fix kernel-doc notation in jbd2.
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

There are several cases where the running transaction can get buffers
added to its BJ_Metadata list which it never dirtied, which makes its
t_nr_buffers counter end up larger than its t_outstanding_credits
counter.

This will cause issues when starting new transactions as while we are
logging buffers we decrement t_outstanding_buffers, so when
t_outstanding_buffers goes negative, we will report that we need less
space in the journal than we actually need, so transactions will be
started even though there may not be enough room for them.  In the worst
case scenario (which admittedly is almost impossible to reproduce) this
will result in the journal running out of space.

The fix is to only refile buffers from the committing transaction to the
running transactions BJ_Modified list when b_modified is set on that
journal, which is the only way to be sure if the running transaction has
modified that buffer.

This patch also fixes an accounting error in journal_forget, it is
possible that we can call journal_forget on a buffer without having
modified it, only gotten write access to it, so instead of freeing a
credit, we only do so if the buffer was modified.  The assert will help
catch if this problem occurs.  Without these two patches I could hit
this assert within minutes of running postmark, with them this issue no
longer arises.

Cc: <linux-ext4@vger.kernel.org>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: NJosef Bacik <jbacik@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Currently at the start of a journal commit we loop through all of the buffers
on the committing transaction and clear the b_modified flag (the flag that is
set when a transaction modifies the buffer) under the j_list_lock.

The problem is that everywhere else this flag is modified only under the jbd2
lock buffer flag, so it will race with a running transaction who could
potentially set it, and have it unset by the committing transaction.

This is also a big waste, you can have several thousands of buffers that you
are clearing the modified flag on when you may not need to.  This patch
removes this code and instead clears the b_modified flag upon entering
do_get_write_access/journal_get_create_access, so if that transaction does
indeed use the buffer then it will be accounted for properly, and if it does
not then we know we didn't use it.

That will be important for the next patch in this series.  Tested thoroughly
by myself using postmark/iozone/bonnie++.

Cc: <linux-ext4@vger.kernel.org>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: NJosef Bacik <jbacik@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Get rid of sparse related warnings from places that use integer as NULL
pointer.  (Ported from upstream ext3/jbd changes.)
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

While "every 5 seconds" doesn't sound as a problem, there can be many
of these (and these timers do add up over all the kernel).  The "5
second" wakeup isn't really timing sensitive; in addition even with
rounding it'll still happen every 5 seconds (with the exception of the
very first time, which is likely to be rounded up to somewhere closer
to 6 seconds)

(Ported from similar JBD patch made by Arjan van de Ven to
fs/jbd/transaction.c)

Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Ported from similar patch for the jbd layer.
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

The patch below updates the jbd stats patch to 2.6.20/jbd2.
The initial patch was posted by Alex Tomas in December 2005
(http://marc.info/?l=linux-ext4&m=113538565128617&w=2).
It provides statistics via procfs such as transaction lifetime and size.

Sometimes, investigating performance problems, i find useful to have
stats from jbd about transaction's lifetime, size, etc. here is a
patch for review and inclusion probably.

for example, stats after creation of 3M files in htree directory:

[root@bob ~]# cat /proc/fs/jbd/sda/history
R/C  tid   wait  run   lock  flush log   hndls  block inlog ctime write drop  close
R    261   8260  2720  0     0     750   9892   8170  8187
C    259                                                    750   0     4885  1
R    262   20    2200  10    0     770   9836   8170  8187
R    263   30    2200  10    0     3070  9812   8170  8187
R    264   0     5000  10    0     1340  0      0     0
C    261                                                    8240  3212  4957  0
R    265   8260  1470  0     0     4640  9854   8170  8187
R    266   0     5000  10    0     1460  0      0     0
C    262                                                    8210  2989  4868  0
R    267   8230  1490  10    0     4440  9875   8171  8188
R    268   0     5000  10    0     1260  0      0     0
C    263                                                    7710  2937  4908  0
R    269   7730  1470  10    0     3330  9841   8170  8187
R    270   0     5000  10    0     830   0      0     0
C    265                                                    8140  3234  4898  0
C    267                                                    720   0     4849  1
R    271   8630  2740  20    0     740   9819   8170  8187
C    269                                                    800   0     4214  1
R    272   40    2170  10    0     830   9716   8170  8187
R    273   40    2280  0     0     3530  9799   8170  8187
R    274   0     5000  10    0     990   0      0     0


where,

R     - line for transaction's life from T_RUNNING to T_FINISHED
C     - line for transaction's checkpointing
tid   - transaction's id
wait  - for how long we were waiting for new transaction to start
         (the longest period journal_start() took in this transaction)
run   - real transaction's lifetime (from T_RUNNING to T_LOCKED
lock  - how long we were waiting for all handles to close
         (time the transaction was in T_LOCKED)
flush - how long it took to flush all data (data=ordered)
log   - how long it took to write the transaction to the log
hndls - how many handles got to the transaction
block - how many blocks got to the transaction
inlog - how many blocks are written to the log (block + descriptors)
ctime - how long it took to checkpoint the transaction
write - how many blocks have been written during checkpointing
drop  - how many blocks have been dropped during checkpointing
close - how many running transactions have been closed to checkpoint this one

all times are in msec.


[root@bob ~]# cat /proc/fs/jbd/sda/info
280 transaction, each upto 8192 blocks
average:
  1633ms waiting for transaction
  3616ms running transaction
  5ms transaction was being locked
  1ms flushing data (in ordered mode)
  1799ms logging transaction
  11781 handles per transaction
  5629 blocks per transaction
  5641 logged blocks per transaction
Signed-off-by: NJohann Lombardi <johann.lombardi@bull.net>
Signed-off-by: NMariusz Kozlowski <m.kozlowski@tuxland.pl>
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: NEric Sandeen <sandeen@redhat.com>

Convert kmalloc to kzalloc() and get rid of the memset().
Signed-off-by: NMingming Cao <cmm@us.ibm.com>

This patch cleans up jbd_kmalloc and replace it with kmalloc directly
Signed-off-by: NMingming Cao <cmm@us.ibm.com>

JBD2: Replace slab allocations with page allocations

JBD2 allocate memory for committed_data and frozen_data from slab. However
JBD2 should not pass slab pages down to the block layer. Use page allocator
pages instead. This will also prepare JBD for the large blocksize patchset.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NMingming Cao <cmm@us.ibm.com>

Many files include the filename at the beginning, serveral used a wrong one.
Signed-off-by: NUwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>

Remove includes of <linux/smp_lock.h> where it is not used/needed.
Suggested by Al Viro.

Builds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc,
sparc64, and arm (all 59 defconfigs).
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

When running several fsx's and other filesystem stress tests, we found
cases where an unmapped buffer was still being sent to submit_bh by the
ext3 dirty data journaling code.

I saw this happen in two ways, both related to another thread doing a
truncate which would unmap the buffer in question.

Either we would get into journal_dirty_data with a bh which was already
unmapped (although journal_dirty_data_fn had checked for this earlier, the
state was not locked at that point), or it would get unmapped in the middle
of journal_dirty_data when we dropped locks to call sync_dirty_buffer.

By re-checking for mapped state after we've acquired the bh state lock, we
should avoid these races.  If we find a buffer which is no longer mapped,
we essentially ignore it, because journal_unmap_buffer has already decided
that this buffer can go away.

I've also added tracepoints in these two cases, and made a couple other
tracepoint changes that I found useful in debugging this.
Signed-off-by: NEric Sandeen <esandeen@redhat.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

A disk generated some I/O error, after it, I hitted
J_ASSERT(transaction->t_updates > 0) in journal_stop().

It seems to happened on ext3_truncate() path from stack trace. Then,
maybe the following case may trigger J_ASSERT(transaction->t_updates > 0).

ext3_truncate()
    -> ext3_free_branches()
        -> ext3_journal_test_restart()
	    -> ext3_journal_restart()
                -> journal_restart()
                transaction->t_updates--;
                /* another process aborted journal */
                    -> start_this_handle()
		    returns -EROFS without transaction->t_updates++;

    -> ext3_journal_stop()
        -> journal_stop()
	J_ASSERT(transaction->t_updates > 0)

If journal was aborted in middle of journal_restart(), ext3_truncate()
may trigger J_ASSERT().
Signed-off-by: NOGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Mingming Cao originally did this work, and Shaggy reproduced it using some
scripts from her.
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This is a simple copy of the files in fs/jbd to fs/jbd2 and
/usr/incude/linux/[ext4_]jbd.h to /usr/include/[ext4_]jbd2.h
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

More white space cleanups in preparation of cloning ext4 from ext3.
Removing spaces that precede a tab.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Remove whitespace from ext3 and jbd, before we clone ext4.

Signed-off-by: Mingming Cao<cmm@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Missed a place where I forgot to convert kfree() to kmem_cache_free() as
part of jbd-manage-its-own-slab changes.
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

JBD currently allocates commit and frozen buffers from slabs.  With
CONFIG_SLAB_DEBUG, its possible for an allocation to cross the page
boundary causing IO problems.

https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=200127

So, instead of allocating these from regular slabs - manage allocation from
its own slabs and disable slab debug for these slabs.

[akpm@osdl.org: cleanups]
Signed-off-by: NBadari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

There are a couple of places where JBD has to check to see whether an unneeded
memory allocation was performed.  Usually it _was_ needed, so we end up
calling kfree(NULL).  We can micro-optimise that by checking the pointer
before calling kfree().

Thanks to Steven Rostedt <rostedt@goodmis.org> for identifying this.
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix possible assertion failure in journal_commit_transaction() on
jh->b_next_transaction == NULL (when we are processing BJ_Forget list and
buffer is not jbddirty).

!jbddirty buffers can be placed on BJ_Forget list for example by
journal_forget() or by __dispose_buffer() - generally such buffer means
that it has been freed by this transaction.

Freed buffers should not be reallocated until the transaction has committed
(that's why we have the assertion there) but they *can* be reallocated when
the transaction has already been committed to disk and we are just
processing the BJ_Forget list (as soon as we remove b_committed_data from
the bitmap bh, ext3 will be able to reallocate buffers freed by the
committing transaction).  So we have to also count with the case that the
buffer has been reallocated and b_next_transaction has been already set.

And one more subtle point: it can happen that we manage to reallocate the
buffer and also mark it jbddirty.  Then we also add the freed buffer to the
checkpoint list of the committing trasaction.  But that should do no harm.

Non-jbddirty buffers should be filed to BJ_Reserved and not BJ_Metadata
list.  It can actually happen that we refile such buffers during the commit
phase when we reallocate in the running transaction blocks deleted in
committing transaction (and that can happen if the committing transaction
already wrote all the data and is just cleaning up BJ_Forget list).
Signed-off-by: NJan Kara <jack@suse.cz>
Acked-by: N"Stephen C. Tweedie" <sct@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The return value of this function is never used, so let's be honest and
declare it as void.

Some places where invalidatepage returned 0, I have inserted comments
suggesting a BUG_ON.

[akpm@osdl.org: JBD BUG fix]
[akpm@osdl.org: rework for git-nfs]
[akpm@osdl.org: don't go BUG in block_invalidate_page()]
Signed-off-by: NNeil Brown <neilb@suse.de>
Acked-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The kjournald timer is currently on the kernel thread's stack and the journal
structure points at it.  Save a pointer hop by moving the timer into the
journal structure.
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Semaphore to mutex conversion.

The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: NArjan van de Ven <arjan@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Ben points out that:

  When writing files out using O_SYNC, jbd's 1 jiffy delay results in a
  significant drop in throughput as the disk sits idle.  The patch below
  results in a 4-5x performance improvement (from 6.5MB/s to ~24-30MB/s on my
  IDE test box) when writing out files using O_SYNC.

So optimise the batching code by omitting it entirely if the process which is
doing a sync write is the same as the one which did the most recent sync
write.  If that's true, we're unlikely to get any other processes joining the
transaction.

(Has been in -mm for ages - it took me a long time to get on to performance
testing it)

Numbers, on write-cache-disabled IDE:

/usr/bin/time -p synctest -n 10 -uf -t 1 -p 1 dir-name

Unpatched:
	40 seconds
Patched:
	35 seconds
Batching disabled:
	35 seconds

This is the problematic single-process-doing-fsync case.  With multiple
fsyncing processes the numbers are AFACIT unaltered by the patch.

Aside: performance testing and instrumentation shows that the transaction
batching almost doesn't help (testing with synctest -n 1 -uf -t 100 -p 10
dir-name on non-writeback-caching IDE).  This is because by the time one
process is running a synchronous commit, a bunch of other processes already
have a transaction handle open, so they're all going to batch into the same
transaction anyway.

The batching seems to offer maybe 5-10% speedup with this workload, but I'm
pretty sure it was more important than that when it was first developed 4-odd
years ago...

Cc: "Stephen C. Tweedie" <sct@redhat.com>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This is the fs/ part of the big kfree cleanup patch.

Remove pointless checks for NULL prior to calling kfree() in fs/.
Signed-off-by: NJesper Juhl <jesper.juhl@gmail.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

 - ->releasepage() annotated (s/int/gfp_t), instances updated
 - missing gfp_t in fs/* added
 - fixed misannotation from the original sweep caught by bitwise checks:
   XFS used __nocast both for gfp_t and for flags used by XFS allocator.
   The latter left with unsigned int __nocast; we might want to add a
   different type for those but for now let's leave them alone.  That,
   BTW, is a case when __nocast use had been actively confusing - it had
   been used in the same code for two different and similar types, with
   no way to catch misuses.  Switch of gfp_t to bitwise had caught that
   immediately...

One tricky bit is left alone to be dealt with later - mapping->flags is
a mix of gfp_t and error indications.  Left alone for now.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Use schedule_timeout_{,un}interruptible() instead of
set_current_state()/schedule_timeout() to reduce kernel size.  Also use helper
functions to convert between human time units and jiffies rather than constant
HZ division to avoid rounding errors.
Signed-off-by: NNishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

  attached patch should fix the following race:
     Proc 1                               Proc 2

     __flush_batch()
       ll_rw_block()
                                        do_get_write_access()
					   lock_buffer
                                             jh is only waiting for checkpoint
					     -> b_transaction == NULL ->
					     do nothing
                                           unlock_buffer
    test_set_buffer_locked()
    test_clear_buffer_dirty()
                                           __journal_file_buffer()
                                        change the data
    submit_bh()

and we have sent wrong data to disk...  We now clean the dirty buffer flag
under buffer lock in all cases and hence we know that whenever a buffer is
starting to be journaled we either finish the pending write-out before
attaching a buffer to a transaction or we won't write the buffer until the
transaction is going to be committed.

The test in jbd_unexpected_dirty_buffer() is redundant - remove it.
Furthermore we have to clear the buffer dirty bit under the buffer lock to
prevent races with buffer write-out (and hence prevent returning a buffer with
IO happening).
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This fixes the lots-of-fsx-linux-instances-cause-a-slow-leak bug.

It's been there since 2.6.6, caused by:

ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.5/2.6.5-mm4/broken-out/jbd-move-locked-buffers.patch

That patch moves under-writeout ordered-data buffers onto a separate journal
list during commit.  It took out the old code which was based on a single
list.

The old code (necessarily) had logic which would restart I/O against buffers
which had been redirtied while they were on the committing transaction's
t_sync_datalist list.  The new code only writes buffers once, ignoring
redirtyings by a later transaction, which is good.

But over on the truncate side of things, in journal_unmap_buffer(), we're
treating buffers on the t_locked_list as inviolable things which belong to the
committing transaction, and we just leave them alone during concurrent
truncate-vs-commit.

The net effect is that when truncate tries to invalidate a page whose buffers
are on t_locked_list and have been redirtied, journal_unmap_buffer() just
leaves those buffers alone.  truncate will remove the page from its mapping
and we end up with an anonymous clean page with dirty buffers, which is an
illegal state for a page.  The JBD commit will not clean those buffers as they
are removed from t_locked_list.  The VM (try_to_free_buffers) cannot reclaim
these pages.

The patch teaches journal_unmap_buffer() about buffers which are on the
committing transaction's t_locked_list.  These buffers have been written and
I/O has completed.  We can take them off the transaction and undirty them
within the context of journal_invalidatepage()->journal_unmap_buffer().
Acked-by: N"Stephen C. Tweedie" <sct@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>