If we have accumulated a contiguous region of memory to be written
out, and the next page can added to this region, don't bother locking
(and then unlocking the page) before writing out the memory.  In the
unlikely event that the next page was being written back by some other
CPU, we can also skip waiting that page to finish writeback.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Because the ext4 page writeback codepath had been prematurely calling
clear_page_dirty_for_io(), if it turned out that a particular page
couldn't be written out during a particular pass of
write_cache_pages_da(), the page would have to get redirtied by
calling redirty_pages_for_writeback().  Not only was this wasted work,
but redirty_page_for_writeback() would increment wbc->pages_skipped to
signal to writeback_sb_inodes() that buffers were locked, and that it
should skip this inode until later.

Since this signal was incorrect in ext4's case --- which was caused by
ext4's historically incorrect use of write_cache_pages() ---
ext4_da_writepages() saved and restored wbc->skipped_pages to avoid
confusing writeback_sb_inodes().

Now that we've fixed ext4 to call clear_page_dirty_for_io() right
before initiating the page I/O, we can nuke the page_skipped
save/restore hackery, and breathe a sigh of relief.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Move when we call clear_page_dirty_for_io() to just before we actually
write the page.  This simplifies the code somewhat, and avoids marking
pages as clean and then needing to remark them as dirty later.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Eliminate duplicate code, unneeded variables, etc., to make it easier
to understand the code.  No behavioral changes were made in this patch.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Fold the __mpage_da_writepage() function into write_cache_pages_da().
This will give us opportunities to clean up and simplify the resulting
code.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Now that we've fixed the file corruption bug in commit d50bdd5a,
it's time to enable mblk_io_submit by default.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

If ext4_da_block_invalidatepages() is called because of a
failure from ext4_map_blocks() in mpage_da_map_and_submit(),
it's supposed to clean up -- including unlock -- all the
pages in the mpd structure.  But these values may not match
up, even on a system in which block size == page size:

   mpd->b_blocknr != mpd->first_page
   mpd->b_size != (mpd->next_page - mpd->first_page)

ext4_da_block_invalidatepages() has been using b_blocknr and
b_size; this patch changes it to use first_page and
next_page.

Tested:  I injected a small number (5%) of failures in
ext4_map_blocks() in the case that the flags contain
EXT4_GET_BLOCKS_DELALLOC_RESERVE, and ran fsstress on this
kernel.  Without this patch, I got hung tasks every time.
With this patch, I see no hangs in many runs of fsstress.
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

In mpage_da_map_and_submit(), if we have a delayed block
allocation failure from ext4_map_blocks(), we need to mark
the IO as complete, by setting

      mpd->io_done = 1;

Otherwise, we could end up submitting the pages in an outer
loop; since they are unlocked on mapping failure in
ext4_da_block_invalidatepages(), this will cause a bug check
in mpage_da_submit_io().

I tested this by injected failures into ext4_map_blocks().
Without this patch, a simple fsstress run will bug check;
with the patch, it works fine.
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

In ext4_mb_check_group_pa(), the current preallocation space is
replaced with a new preallocation space when the two have the same
distance from the goal block.

This doesn't actually gain us anything, so change things so that the
function only switches to the new preallocation group if its distance
from the goal block is strictly smaller than the current preallocaiton
group's distance from the goal block.
Signed-off-by: NColy Li <bosong.ly@taobao.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Signed-off-by: NColy Li <bosong.ly@taobao.com>
Cc: Alex Tomas <alex@clusterfs.com>
Cc: Theodore Tso <tytso@google.com>

This patch adds comments to ext4_mb_mark_free_simple to make it more
understandable.
Signed-off-by: NColy Li <bosong.ly@taobao.com>
Cc: Alex Tomas <alex@clusterfs.com>
Cc: Theodore Tso <tytso@google.com>

In __mb_check_buddy(), look at the code below:
  591         fstart = -1;
  592         buddy = mb_find_buddy(e4b, 0, &max);
  593         for (i = 0; i < max; i++) {
  594                 if (!mb_test_bit(i, buddy)) {
  595                         MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free);
  596                         if (fstart == -1) {
  597                                 fragments++;
  598                                 fstart = i;
  599                         }
  600                         continue;
  601                 }
  602                 fstart = -1;
  603                 /* check used bits only */
  604                 for (j = 0; j < e4b->bd_blkbits + 1; j++) {
  605                         buddy2 = mb_find_buddy(e4b, j, &max2);
  606                         k = i >> j;
  607                         MB_CHECK_ASSERT(k < max2);
  608                         MB_CHECK_ASSERT(mb_test_bit(k, buddy2));
  609                 }
  610         }
  611         MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info));
  612         MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments);
  613
  614         grp = ext4_get_group_info(sb, e4b->bd_group);
  615         buddy = mb_find_buddy(e4b, 0, &max);

On line 592, buddy is fetched by mb_find_buddy() with order 0, between
line 593 to line 615, buddy is not changed, therefore there is
no need to fetch buddy again from mb_find_buddy() with order 0 again.

We can safely remove the second mb_find_buddy() on line 615.
Signed-off-by: NColy Li <bosong.ly@taobao.com>
Cc: Alex Tomas <alex@clusterfs.com>
Cc: Theodore Tso <tytso@google.com>

Current code calculate max no matter whether order is zero, it's
unnecessary. This cleanup patch sets max to "1 << (e4b->bd_blkbits
+ 3)" only when order == 0.
Signed-off-by: NColy Li <bosong.ly@taobao.com>
Cc: Alex Tomas <alex@clusterfs.com>
Cc: Theodore Tso <tytso@google.com>

There's no good reason to require the extra step of providing
a mount option for acl or user_xattr once the feature is configured
on; no other filesystem that I know of requires this.

Userspace patches have set these options in default mount options,
and this patch makes them default in the kernel.  At some point
we can start to deprecate the options, perhaps.

For now I've removed default mount option checks in show_options()
to be explicit about what's set, since it's changing the default,
but I'm open to alternatives if desired.
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Discard granularity tells us the minimum size of extent that can be
discarded by the device.  If the user supplies a minimum extent that
should be discarded (range.minlen) which is smaller than the discard
granularity, increase minlen to the discard granularity, since there's
no point submitting trim requests that the device will reject anyway.
Signed-off-by: NLukas Czerner <lczerner@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

For a device that does not support discard, the FITRIM ioctl returns
-EOPNOTSUPP when blkdev_issue_discard() returns this error code, which
is how the user is informed that the device does not support discard.

If there are no suitable free extents to be trimmed, then FITRIM will
return success even though the device does not support discard, which
could confuse the user.  So check explicitly if the device supports
discard and return an error code at the beginning of the FITRIM ioctl
processing.
Signed-off-by: NLukas Czerner <lczerner@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Signed-off-by: NLukas Czerner <lczerner@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

I cannot disable inode-read-ahead feature of ext4 (on 2.6.37):

# echo 0 > /sys/fs/ext4/sda2/inode_readahead_blks 
bash: echo: write error: Invalid argument

On a server with lots of small files and random access this read-ahead makes
performance worse, and I'd like to disable it. I work around this problem
by using value of 1, but it still reads an extra block.

This patch fixes the problem by checking for zero explicitly.
Signed-off-by: NAlexander V. Lukyanov <lav@netis.ru>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This patch fixes the warning "Using plain integer as NULL pointer",
generated by sparse, by replacing the offending 0s with NULL.
Signed-off-by: NPeter Huewe <peterhuewe@gmx.de>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Compile 2.6.38-rc1 with turning EXT4FS_DEBUG on,
we get following compile warnings. This patch fixes them.

  CC      fs/ext4/hash.o
  CC      fs/ext4/resize.o
fs/ext4/resize.c: In function 'setup_new_group_blocks':
fs/ext4/resize.c:233:2: warning: format '%#04llx' expects type 'long long
unsigned int', but argument 3 has type 'long unsigned int'
fs/ext4/resize.c:251:2: warning: format '%#04llx' expects type 'long long
unsigned int', but argument 3 has type 'long unsigned int'
  CC      fs/ext4/extents.o
  CC      fs/ext4/ext4_jbd2.o
  CC      fs/ext4/migrate.o
Reported-by: NAkira Fujita <a-fujita@rs.jp.nec.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

ext4 has a data corruption case when doing non-block-aligned
asynchronous direct IO into a sparse file, as demonstrated
by xfstest 240.

The root cause is that while ext4 preallocates space in the
hole, mappings of that space still look "new" and 
dio_zero_block() will zero out the unwritten portions.  When
more than one AIO thread is going, they both find this "new"
block and race to zero out their portion; this is uncoordinated
and causes data corruption.

Dave Chinner fixed this for xfs by simply serializing all
unaligned asynchronous direct IO.  I've done the same here.
The difference is that we only wait on conversions, not all IO.
This is a very big hammer, and I'm not very pleased with
stuffing this into ext4_file_write().  But since ext4 is
DIO_LOCKING, we need to serialize it at this high level.

I tried to move this into ext4_ext_direct_IO, but by then
we have the i_mutex already, and we will wait on the
work queue to do conversions - which must also take the
i_mutex.  So that won't work.

This was originally exposed by qemu-kvm installing to
a raw disk image with a normal sector-63 alignment.  I've
tested a backport of this patch with qemu, and it does
avoid the corruption.  It is also quite a lot slower
(14 min for package installs, vs. 8 min for well-aligned)
but I'll take slow correctness over fast corruption any day.

Mingming suggested that we can track outstanding
conversions, and wait on those so that non-sparse
files won't be affected, and I've implemented that here;
unaligned AIO to nonsparse files won't take a perf hit.

[tytso@mit.edu: Keep the mutex as a hashed array instead
 of bloating the ext4 inode]

[tytso@mit.edu: Fix up namespace issues so that global
 variables are protected with an "ext4_" prefix.]
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

In 2.6.37 I was running into oopses with repeated module
loads & unloads.  I tracked this down to:

fb1813f4 ext4: use dedicated slab caches for group_info structures

(this was in addition to the features advert unload problem)

The kstrdup & subsequent kfree of the cache name was causing
a double free.  In slub, at least, if I read it right it allocates
& frees the name itself, slab seems to do something different...
so in slub I think we were leaking -our- cachep->name, and double
freeing the one allocated by slub.

After getting lost in slab/slub/slob a bit, I just looked at other
sized-caches that get allocated.  jbd2, biovec, sgpool all do it
more or less the way jbd2 does.  Below patch follows the jbd2
method of dynamically allocating a cache at mount time from
a list of static names.

(This might also possibly fix a race creating the caches with
parallel mounts running).

[Folded in a fix from Dan Carpenter which fixed an off-by-one error in
the original patch]

Cc: stable@kernel.org
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This fixes a corruption problem with the multi-block
writepages submittal change for ext4, from commit
bd2d0210 ("ext4: use bio
layer instead of buffer layer in mpage_da_submit_io").

(Note that this corruption is not present in 2.6.37 on
ext4, because the corruption was detected after the
feature was merged in 2.6.37-rc1, and so it was turned
off by adding a non-default mount option,
mblk_io_submit.  With this commit, which hopefully
fixes the last of the bugs with this feature, we'll be
able to turn on this performance feature by default in
2.6.38, and remove the mblk_io_submit option.)

The ext4 code path to bundle multiple pages for
writeback in ext4_bio_write_page() had a bug: we should
be clearing buffer head dirty flags *before* we submit
the bio, not in the completion routine.

The patch below was tested on 2.6.37 under KVM with the
postgresql script which was submitted by Jon Nelson as
documented in commit 1449032b.

Without the patch, I'd hit the corruption problem about
50-70% of the time.  With the patch, I executed the
script > 100 times with no corruption seen.

I also fixed a bug to make sure ext4_end_bio() doesn't
dereference the bio after the bio_put() call.
Reported-by: NJon Nelson <jnelson@jamponi.net>
Reported-by: NMatthias Bayer <jackdachef@gmail.com>
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>
Cc: stable@kernel.org

Make sure we the correct cleanup happens if we die while trying to
load the ext4 file system.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Ext4 features interface was not properly unregistered which led to
problems while unloading/reloading ext4 module. This commit fixes that by
adding proper kobject unregistration code into ext4_exit_fs() as well as
fail-path of ext4_init_fs()
Reported-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: NLukas Czerner <lczerner@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>
Cc: stable@kernel.org

https://bugzilla.kernel.org/show_bug.cgi?id=27652

If the lazyinit thread is running, the teardown function
ext4_destroy_lazyinit_thread() has problems:

        ext4_clear_request_list();
        while (ext4_li_info->li_task) {
                wake_up(&ext4_li_info->li_wait_daemon);
                wait_event(ext4_li_info->li_wait_task,
                           ext4_li_info->li_task == NULL);
        }

Clearing the request list will cause the thread to exit and free
ext4_li_info, so then we're waiting on something which is getting
freed.

Fix this up by making the thread respond to kthread_stop, and exit,
without the need to wait for that exit in some other homegrown way.

Cc: stable@kernel.org
Reported-and-Tested-by: NTao Ma <boyu.mt@taobao.com>
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Currently all filesystems except XFS implement fallocate asynchronously,
while XFS forced a commit.  Both of these are suboptimal - in case of O_SYNC
I/O we really want our allocation on disk, especially for the !KEEP_SIZE
case where we actually grow the file with user-visible zeroes.  On the
other hand always commiting the transaction is a bad idea for fast-path
uses of fallocate like for example in recent Samba versions.   Given
that block allocation is a data plane operation anyway change it from
an inode operation to a file operation so that we have the file structure
available that lets us check for O_SYNC.

This also includes moving the code around for a few of the filesystems,
and remove the already unnedded S_ISDIR checks given that we only wire
up fallocate for regular files.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Instead of various home grown checks that might need updates for new
flags just check for any bit outside the mask of the features supported
by the filesystem.  This makes the check future proof for any newly
added flag.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

pr_warning_ratelimited() doesn't exist.

Also include printk.h, which defines these things.

Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Ext4 doesn't have the ability to punch holes yet, so make sure we return
EOPNOTSUPP if we try to use hole punching through fallocate.  This support can
be added later.  Thanks,
Acked-by: NJan Kara <jack@suse.cz>
Signed-off-by: NJosef Bacik <josef@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

As Al Viro pointed out path resolution during Q_QUOTAON calls to quotactl
is prone to deadlocks. We hold s_umount semaphore for reading during the
path resolution and resolution itself may need to acquire the semaphore
for writing when e. g. autofs mountpoint is passed.

Solve the problem by performing the resolution before we get hold of the
superblock (and thus s_umount semaphore). The whole thing is complicated
by the fact that some filesystems (OCFS2) ignore the path argument. So to
distinguish between filesystem which want the path and which do not we
introduce new .quota_on_meta callback which does not get the path. OCFS2
then uses this callback instead of old .quota_on.

CC: Al Viro <viro@ZenIV.linux.org.uk>
CC: Christoph Hellwig <hch@lst.de>
CC: Ted Ts'o <tytso@mit.edu>
CC: Joel Becker <joel.becker@oracle.com>
Signed-off-by: NJan Kara <jack@suse.cz>

When s_first_data_block is not zero (which happens e.g. when block size is 1KB)
and trim ioctl is called to start trimming from block 0, the math in
ext4_get_group_no_and_offset() overflows. The overall result is that ioctl
returns EINVAL which is kind of unexpected and we probably don't want
userspace tools to bother with internal details of filesystem structure.
So just silently increase starting offset (and shorten length) when starting
block is below s_first_data_block.

CC: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This reverts commit 4f531501: ext4: fix possible overflow in
ext4_trim_fs()
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Since check_eofblocks_fl() only uses the m_lblk portion of the map
structure, we may as well pass that directly, rather than passing the
entire map, which IMHO obfuscates what parameters check_eofblocks_fl()
cares about.  Not a big deal, but seems tidier and less confusing, to
me.
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Commit 40389687 moved a call to ext4_forget() out of
ext4_free_branches and let ext4_free_blocks() handle calling
bforget().  But that change unfortunately did not replace the call to
ext4_forget() with brelse(), which was needed to drop the in-use count
of the indirect block's buffer head, which lead to a memory leak when
deleting files that used indirect blocks.  Fix this.

Thanks to Hugh Dickins for pointing this out.

Cc: stable@kernel.org
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This function was never implemented, except for a BUG_ON which was
tripping when ext4 is run without a journal.  The problem is that
although the comment asserts that "truncate (which is the only way to
free block) discards all preallocations", ext4_free_blocks() is also
called in various error recovery paths when blocks have been
allocated, but for various reasons, we were not able to use those data
blocks (for example, because we ran out of memory while trying to
manipulate the extent tree, or some other similar situation).

In addition to the fact that this function isn't implemented except
for the incorrect BUG_ON, the single caller of this function,
ext4_free_blocks(), doesn't use it all if the journal is enabled.

So remove the (stub) function entirely for now.  If we decide it's
better to add it back, it's only going to be useful with a relatively
large number of code changes anyway.

Google-Bug-Id: 3236408

Cc: Jiaying Zhang <jiayingz@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Ted first found the bug when running 2.6.36 kernel with dioread_nolock
mount option that xfstests #13 complained about wrong file size during fsck.
However, the bug exists in the older kernels as well although it is
somehow harder to trigger.

The problem is that ext4_end_io_work() can happen after we have truncated an
inode to a smaller size. Then when ext4_end_io_work() calls 
ext4_convert_unwritten_extents(), we may reallocate some blocks that have 
been truncated, so the inode size becomes inconsistent with the allocated
blocks. 

The following patch flushes the i_completed_io_list during truncate to reduce 
the risk that some pending end_io requests are executed later and convert 
already truncated blocks to initialized. 

Note that although the fix helps reduce the problem a lot there may still 
be a race window between vmtruncate() and ext4_end_io_work(). The fundamental
problem is that if vmtruncate() is called without either i_mutex or i_alloc_sem
held, it can race with an ongoing write request so that the io_end request is
processed later when the corresponding blocks have been truncated.

Ted and I have discussed the problem offline and we saw a few ways to fix
the race completely:

a) We guarantee that i_mutex lock and i_alloc_sem write lock are both hold 
whenever vmtruncate() is called. The i_mutex lock prevents any new write
requests from entering writeback and the i_alloc_sem prevents the race
from ext4_page_mkwrite(). Currently we hold both locks if vmtruncate()
is called from do_truncate(), which is probably the most common case.
However, there are places where we may call vmtruncate() without holding
either i_mutex or i_alloc_sem. I would like to ask for other people's
opinions on what locks are expected to be held before calling vmtruncate().
There seems a disagreement among the callers of that function.

b) We change the ext4 write path so that we change the extent tree to contain 
the newly allocated blocks and update i_size both at the same time --- when 
the write of the data blocks is completed.

c) We add some additional locking to synchronize vmtruncate() and 
ext4_end_io_work(). This approach may have performance implications so we
need to be careful.

All of the above proposals may require more substantial changes, so
we may consider to take the following patch as a bandaid.
Signed-off-by: NJiaying Zhang <jiayingz@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Call ext4_std_error() in various places when we can't bail out
cleanly, so the file system can be marked as in error.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

When ext4_trim_fs() is called to trim a part of a single group, the
logic will wrongly set last block of the interval to 'len' instead
of 'first_block + len'. Thus a shorter interval is possibly trimmed.
Fix it.

CC: Lukas Czerner <lczerner@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

fs/ext4/super.c: In function 'ext4_register_li_request':
fs/ext4/super.c:2936: warning: 'ret' may be used uninitialized in this function

It looks buggy to me, too.

Cc: Lukas Czerner <lczerner@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>