It is possible to reduce the size of GFS2 inodes by taking the i_alloc
structure out of the gfs2_inode. This patch allocates the i_alloc
structure whenever its needed, and frees it afterward. This decreases
the amount of low memory we use at the expense of requiring a memory
allocation for each page or partial page that we write. A quick test
with postmark shows that the overhead is not measurable and I also note
that OCFS2 use the same approach.

In the future I'd like to solve the problem by shrinking down the size
of the members of the i_alloc structure, but for now, this reduces the
immediate problem of using too much low-memory on x86 and doesn't add
too much overhead.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch fixes a couple of problems which affected the execution of files
on GFS2. The first is that there was a corner case where inodes were not
always uptodate at the point at which permissions checks were being carried
out, this was resulting in refusal of execute permission, but only on the
first lookup, subsequent requests worked correctly. The second was a problem
relating to incorrect updating of file sizes which was introduced with the
write_begin/end code for GFS2 a little while back.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Abhijith Das <adas@redhat.com>

To improve performance on NUMA, we use the VM's standard page
migration for writeback and ordered pages. Probably we could
also do the same for journaled data, but that would need a
careful audit of the code, so will be the subject of a later
patch.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch is just a cleanup.  Function gfs2_get_block() just calls
function gfs2_block_map reversing the last two parameters.  By
reversing the parameters, gfs2_block_map() may be called directly
and function gfs2_get_block may be eliminated altogether.
Since this function is done for every block operation,
this streamlines the code and makes it a little bit more efficient.
Signed-off-by: NBob Peterson <rpeterso@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

Something changed in the upstream kernel, and it needs this
one-liner to allow ops_address.c to build.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This is an addendum to the new AOPs work which moves the point
at which we take the page lock so that we don't get it until
the last possible moment. This resolves a conflict between
starting transactions and the page lock.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch resolves a lock ordering issue where we had been getting
a transaction lock in the wrong order with respect to the page lock.
By using writepages rather than just writepage, it is then possible
to start a transaction before locking the page, and thus matching the
locking order elsewhere in the code.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch splits gfs2_writepage into separate functions for each of
the three cases: writeback, ordered and journalled. As a result
it becomes a lot easier to see what each one is doing. The common
code is moved into gfs2_writepage_common.

This fixes a performance bug where we were doing more work than
strictly required in the ordered write case.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

Just like ext3 we now have three sets of address space operations
to cover the cases of writeback, ordered and journalled data
writes. This means that the individual operations can now become
less complicated as we are able to remove some of the tests for
file data mode from the code.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This adds a function "gfs2_is_writeback()" along the lines of the
existing "gfs2_is_jdata()" in order to clean up the code and make
the various tests for the inode mode more obvious. It also fixes
the PageChecked() logic where we were resetting the flag too early
in the case of an error path.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

The i_cache was designed to keep references to the indirect blocks
used during block mapping so that they didn't have to be looked
up continually. The idea failed because there are too many places
where the i_cache needs to be freed, and this has in the past been
the cause of many bugs.

In addition there was no performance benefit being gained since the
disk blocks in question were cached anyway. So this patch removes
it in order to simplify the code to prepare for other changes which
would otherwise have had to add further support for this feature.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This cleans up the mmap() code path for GFS2 by implementing the
page_mkwrite function for GFS2. We are thus able to use the
generic filemap_fault function for our ->fault() implementation.

This now means that shared writable mappings will be much more
efficiently shared across the cluster if there is a reasonable
proportion of read activity (the greater proportion, the better).

As a side effect, it also reduces the size of the code, removes
special cases from readpage and readpages, and makes the code
path easier to follow.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

As requested by Christoph, this patch cleans up GFS2's internal
read function so that it no longer uses the do_generic_mapping_read
function. This function is obsolete and GFS2 is the last user of it.

As a side effect the internal read code gets smaller and easier
to read and gfs2_readpage is split into two. One function has the locking
and the other function has the rest of the logic.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

* GFS2 has been using i_cache array to store its indirect meta blocks.
Its flush routine doesn't correctly clean up all the entries. The
problem would show while multiple nodes do simultaneous writes to the
same file. Upon glock exclusive lock transfer, if the file is a sparse
file with large file size where the indirect meta blocks span multiple
array entries with "zero" entries in between. The flush routine
prematurely stops the flushing that leaves old (stale) entries around.
This leads to several nasty issues, including data corruption.
* Fix gfs2_get_block_noalloc checking to correctly return EIO upon
unmapped buffer.
Signed-off-by: NWendy Cheng <wcheng@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch cleans up the code for writing journaled data into the log.
It also removes the need to allocate a small "tag" structure for each
block written into the log. Instead we just keep count of the outstanding
I/O so that we can be sure that its all been written at the correct time.
Another result of this patch is that a number of ll_rw_block() calls
have become submit_bh() calls, closing some races at the same time.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

The following patch removes the ordered write processing from
databuf_lo_before_commit() and moves it to log.c. This has the effect of
greatly simplyfying databuf_lo_before_commit() and well as potentially
making the ordered write code more efficient.

As a side effect of this, its now possible to remove ordered buffers
from the ordered buffer list at any time, so we now make use of this in
invalidatepage and releasepage to ensure timely release of these
buffers.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch fixes some bugs relating to journaled data files by cleaning
up the gfs2_invalidatepage() and gfs2_releasepage() functions. We now
never block during gfs2_releasepage(), instead we always either release
or refuse to release depending on the status of the buffers.

This fixes Red Hat bugzillas #248969 and #252392.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Bob Peterson <rpeterso@redhat.com>

The error path in prepare_write() was incorrect in the (very rare) event
that the transaction fails to start. The following prevents a NULL
pointer dereference,
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes
the virtual address -> file offset differently from linear mappings.

->populate is a layering violation because the filesystem/pagecache code
should need to know anything about the virtual memory mapping.  The hitch here
is that the ->nopage handler didn't pass down enough information (ie.  pgoff).
 But it is more logical to pass pgoff rather than have the ->nopage function
calculate it itself anyway (because that's a similar layering violation).

Having the populate handler install the pte itself is likewise a nasty thing
to be doing.

This patch introduces a new fault handler that replaces ->nopage and
->populate and (later) ->nopfn.  Most of the old mechanism is still in place
so there is a lot of duplication and nice cleanups that can be removed if
everyone switches over.

The rationale for doing this in the first place is that nonlinear mappings are
subject to the pagefault vs invalidate/truncate race too, and it seemed stupid
to duplicate the synchronisation logic rather than just consolidate the two.

After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in
pagecache.  Seems like a fringe functionality anyway.

NOPAGE_REFAULT is removed.  This should be implemented with ->fault, and no
users have hit mainline yet.

[akpm@linux-foundation.org: cleanup]
[randy.dunlap@oracle.com: doc. fixes for readahead]
[akpm@linux-foundation.org: build fix]
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Cc: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

As suggested by Robert P. J. Day <rpjday@mindspring.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Robert P. J. Day <rpjday@mindspring.com>

This patch is for bugzilla bug 283162, which uncovered a number of
bugs pertaining to writing to files that have the journaled bit on.
These bugs happen most often when writing to the meta_fs because
the files are always journaled.  So operations like gfs2_grow were
particularly vulnerable, although many of the problems could be
recreated with normal files after setting the journaled bit on.
The problems fixed are:

-GFS2 wasn't ever writing unstuffed journaled data blocks to their
 in-place location on disk. Now it does.

-If you unmounted too quickly after doing IO to a journaled file,
 GFS2 was crashing because you would discard a buffer whose bufdata
 was still on the active items list.  GFS2 now deals with this
 gracefully.

-GFS2 was losing track of the bufdata for journaled data blocks,
 and it wasn't getting freed, causing an error when you tried to
 unmount the module.  GFS2 now frees all the bufdata structures.

-There was a memory corruption occurring because GFS2 wrote
 twice as many log entries for journaled buffers.

-It was occasionally trying to write journal headers in buffers
 that weren't currently mapped.
Signed-off-by: NBob Peterson <rpeterso@redhat.com>
Signed-off-by: NBenjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This is a patch for the first three issues of RHBZ #238162

The first issue is that when you allocate a new page for a file, it will not
start off uptodate. This makes sense, since you haven't written anything to that
part of the file yet.  Unfortunately, gfs2_pin() checks to make sure that the
buffers are uptodate.  The solution to this is to mark the buffers uptodate in
gfs2_commit_write(), after they have been zeroed out and have the data written
into them.  I'm pretty confident with this fix, although it's not completely
obvious that there is no problem with marking the buffers uptodate here.

The second issue is simply that you can try to pin a data buffer that is already
on the incore log, and thus, already pinned. This patch checks to see if this
buffer is already on the log, and exits databuf_lo_add() if it is, just like
buf_lo_add() does.

The third issue is that gfs2_log_flush() doesn't do it's block accounting
correctly.  Both metadata and journaled data are logged, but gfs2_log_flush()
only compares the number of metadata blocks with the number of blocks to commit
to the ondisk journal.  This patch also counts the journaled data blocks.
Signed-off-by: NBenjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This patch cleans up the inode number handling code. The main difference
is that instead of looking up the inodes using a struct gfs2_inum_host
we now use just the no_addr member of this structure. The tests relating
to no_formal_ino can then be done by the calling code. This has
advantages in that we want to do different things in different code
paths if the no_formal_ino doesn't match. In the NFS patch we want to
return -ESTALE, but in the ->lookup() path, its a bug in the fs if the
no_formal_ino doesn't match and thus we can withdraw in this case.

In order to later fix bz #201012, we need to be able to look up an inode
without knowing no_formal_ino, as the only information that is known to
us is the on-disk location of the inode in question.

This patch will also help us to fix bz #236099 at a later date by
cleaning up a lot of the code in that area.

There are no user visible changes as a result of this patch and there
are no changes to the on-disk format either.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This addendum patch 2 corrects three things:

1. It fixes a stupid mistake in the previous addendum that broke gfs2.
   Ref: https://www.redhat.com/archives/cluster-devel/2007-May/msg00162.html
2. It fixes a problem that Dave Teigland pointed out regarding the
   external declarations in ops_address.h being in the wrong place.
3. It recasts a couple more %llu printks to (unsigned long long)
   as requested by Steve Whitehouse.

I would have loved to put this all in one revised patch, but there was
a rush to get some patches for RHEL5.	Therefore, the previous patches
were applied to the git tree "as is" and therefore, I'm posting another
addendum.  Sorry.
Signed-off-by: NBob Peterson <rpeterso@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

To avoid code redundancy, I separated out the operational "guts" into
a new function called read_rindex_entry.  Then I made two functions:
the closer-to-original gfs2_ri_update (without the special condition
checks) and gfs2_ri_update_special that's designed with that condition
in mind.  (I don't like the name, but if you have a suggestion, I'm
all ears).

Oh, and there's an added benefit:  we don't need all the ugly gotos
anymore.  ;)

This patch has been tested with gfs2_fsck_hellfire (which runs for
three and a half hours, btw).
Signed-off-By: NBob Peterson <rpeterso@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This is another revision of my gfs2 kernel patch that allows
gfs2_grow to function properly.

Steve Whitehouse expressed some concerns about the previous
patch and I restructured it based on his comments.
The previous patch was doing the statfs_change at file close time,
under its own transaction.  The current patch does the statfs_change
inside the gfs2_commit_write function, which keeps it under the
umbrella of the inode transaction.

I can't call ri_update to re-read the rindex file during the
transaction because the transaction may have outstanding unwritten
buffers attached to the rgrps that would be otherwise blown away.
So instead, I created a new function, gfs2_ri_total, that will
re-read the rindex file just to total the file system space
for the sake of the statfs_change.  The ri_update will happen
later, when gfs2 realizes the version number has changed, as it
happened before my patch.

Since the statfs_change is happening at write_commit time and there
may be multiple writes to the rindex file for one grow operation.
So one consequence of this restructuring is that instead of getting
one kernel message to indicate the change, you may see several.
For example, before when you did a gfs2_grow, you'd get a single
message like:

GFS2: File system extended by 247876 blocks (968MB)

Now you get something like:

GFS2: File system extended by 207896 blocks (812MB)
GFS2: File system extended by 39980 blocks (156MB)

This version has also been successfully run against the hours-long
"gfs2_fsck_hellfire" test that does several gfs2_grow and gfs2_fsck
while interjecting file system damage.  It does this repeatedly
under a variety Resource Group conditions.
Signed-off-By: NBob Peterson <rpeterso@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

If a stuffed file is mmaped and a page fault is generated at some offset
above the initial page, we need to create a zero page to hang the buffer
heads off before we can unstuff the file. This is a fix for bz #236087
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

If we are writing a file, and in the middle of writing the file
another node attempts to get a shared lock on that file (by doing a du for
example) the process doing the writing will hang waiting on lock_page.  The
reason for this is because when we have waiters on a exclusive glock, we will go
through and flush out all dirty pages associated with that inode and release the
lock.  The problem is that when we flush the dirty pages, we could hit a page
that we have locked durring the generic_file_buffered_write part of this
operation.  This patch unlocks the page before we go to dequeue the lock and
locks it immediatly afterwards, since generic_file_buffered_write needs the page
locked when the commit_write is completed.  This patch resolves the problem,
however if somebody sees a better way to do this please don't hesistate to yell.
Signed-off-by: NJosef Whiter <jwhiter@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This fixes a problem I encountered while running bonnie++.  When you have one
thread that opens a file and starts to write to it, and then another thread that
tries to open and write to the same file, the second thread will loop forever
trying to grab the inode lock for that inode.  Basically we come in through
generic_buffered_file_write, which calls gfs2_prepare_write, which then attempts
to grab the glock.  Because we don't own the lock, gfs2_prepare_write gets
GLR_TRYFAILED, which returns AOP_TRUNCATED_PAGE to generic_buffered_file_write.
At this point generic_buffered_file_write loops around again and immediately
retries the prepare_write.  This means that the second process never gets off of
the processor in order to allow the process that holds the lock to finish its
work and let go of the lock.  This patch makes gfs2_glock_nq schedule() if it
gets back a GLR_TRYFAILED, which resolves this problem.
Signed-off-by: NJosef Whiter <jwhiter@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

On Mon, Jan 29, 2007 at 08:45:28PM -0800, Andrew Morton wrote:
>...
> Changes since 2.6.20-rc6-mm2:
>...
>  git-gfs2-nmw.patch
>...
>  git trees
>...

This patch makes the needlessly global gfs2_writepages() static.
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

When the try lock of the glock failed in prepare_write we were
incorrectly exiting this function with the page still locked.
This was resulting in further I/O to this page hanging.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

It occurred to me that although a gfs2 specific writepages for ordered
writes and journaled data would be tricky, by hooking writepages only
for "data=writeback" mounts we could take advantage of not needing
buffer heads (we don't use them on the read side, nor have we for some
time) and create much larger I/Os for the block layer.

Using blktrace both before and after, its possible to see that for large
I/Os, most of the requests generated through writepages are now 1024
sectors after this patch is applied as opposed to 8 sectors before.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This is partially derrived from a patch written by Russell Cattelan.
It fixes a bug where there is a race between readpages and truncate
by ignoring readpages for stuffed files. This is ok because a stuffed
file will never be more than one block (minus sizeof(struct gfs2_dinode))
in size and block size is always less than page size, so we do not lose
anything efficiency-wise by not doing readahead for stuffed files. They
will have already been "read ahead" by the action of reading the inode
in, in the first place.

This is the remaining part of the fix for Red Hat bugzilla #218966
which had not yet made it upstream.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Russell Cattelan <cattelan@redhat.com>

This patch fixes Red Hat bugzilla #212627 in which a deadlock occurs
due to trying to take the i_mutex while holding a glock. The correct
locking order is defined as i_mutex -> glock in all cases.

I've left dealing with allocating writes. I know that we need to do
that, but for now this should do the trick. We don't need to take the
i_mutex on write, because the VFS has already taken it for us. On read
we don't need it since the glock is enough protection. The reason that
I've made some of the checks into a separate function is that we'll need
to do the checks again in the allocating write case eventually, so this
is partly in preparation for this. Likewise the return value test of !=
1 might look a bit odd and thats because we'll need a third return value
in case of requiring an allocation.

I've made the change to deferred mode on the glock to ensure flushing
read caches on other nodes. I notice that (using blktrace to look at
whats going on) we appear to do a better job of large I/Os than ext3
after this patch (in terms of not splitting up the I/Os).
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>
Cc: Wendy Cheng <wcheng@redhat.com>

Writes to stuffed files were not being marked dirty correctly.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

The gfs2_glock_nq_m_atime function is unused in so far as its only
ever called with num_gh = 1, and this falls through to the
gfs2_glock_nq_atime function, so we might as well call that directly.
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

Stuffed files only consist of a maximum of
(gfs2 block size - sizeof(struct gfs2_dinode)) bytes. Since the
gfs2 block size is always less than page size, we will never see
a call to stuffed_readpage for anything other than the first page
in the file.
Signed-off-by: NRussell Cattelan <cattelan@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>

This fixes a race between the glock and the page lock encountered
during truncate in gfs2_readpage and gfs2_prepare_write. The gfs2_readpages
function doesn't need the same fix since it only uses a try lock anyway, so
it will fail back to gfs2_readpage in the case of a potential deadlock.

This bug was spotted by Russell Cattelan.

Cc: Russell Cattelan <cattelan@redhat.com>
Signed-off-by: NSteven Whitehouse <swhiteho@redhat.com>