During the process of xatt insertion, we use binary search
to find the right place and "low" is set to it. But when
there is one xattr which has the same name hash as the inserted
one, low is the wrong value. So set it to the right position.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Patch adds check for [no]user_xattr in ocfs2_show_options() that completes
the list of all mount options.
Signed-off-by: NSunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

ocfs2 wants JBD2 for many reasons, not the least of which is that JBD is
limiting our maximum filesystem size.

It's a pretty trivial change.  Most functions are just renamed.  The
only functional change is moving to Jan's inode-based ordered data mode.
It's better, too.

Because JBD2 reads and writes JBD journals, this is compatible with any
existing filesystem.  It can even interact with JBD-based ocfs2 as long
as the journal is formated for JBD.

We provide a compatibility option so that paranoid people can still use
JBD for the time being.  This will go away shortly.

[ Moved call of ocfs2_begin_ordered_truncate() from ocfs2_delete_inode() to
  ocfs2_truncate_for_delete(). --Mark ]
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Now that ocfs2 limits inode numbers to 32bits, add a mount option to
disable the limit.  This parallels XFS.  64bit systems can handle the
larger inode numbers.

[ Added description of inode64 mount option in ocfs2.txt. --Mark ]
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

ocfs2 inode numbers are block numbers.  For any filesystem with less
than 2^32 blocks, this is not a problem.  However, when ocfs2 starts
using JDB2, it will be able to support filesystems with more than 2^32
blocks.  This would result in inode numbers higher than 2^32.

The problem is that stat(2) can't handle those numbers on 32bit
machines.  The simple solution is to have ocfs2 allocate all inodes
below that boundary.

The suballoc code is changed to honor an optional block limit.  Only the
inode suballocator sets that limit - all other allocations stay unlimited.

The biggest trick is to grow the inode suballocator beneath that limit.
There's no point in allocating block groups that are above the limit,
then rejecting their elements later on.  We want to prevent the inode
allocator from ever having block groups above the limit.  This involves
a little gyration with the local alloc code.  If the local alloc window
is above the limit, it signals the caller to try the global bitmap but
does not disable the local alloc file (which can be used for other
allocations).

[ Minor cleanup - removed an ML_NOTICE comment. --Mark ]
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

In ocfs2_xattr_free_block, we take a cluster lock on xb_alloc_inode while we
have a transaction open. This will deadlock the downconvert thread, so fix
it.

We can clean up how xattr blocks are removed while here - this patch also
moves the mechanism of releasing xattr block (including both value, xattr
tree and xattr block) into this function.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

In ocfs2_extend_trans, when we can't extend the current
transaction, it will commit current transaction and restart
a new one. So if the previous credits we have allocated aren't
used(the block isn't dirtied before our extend), we will not
have enough credits for any future operation(it will cause jbd
complain and bug out). So check this and re-extend it.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The original get/put_extent_tree() functions held a reference on
et_root_bh.  However, every single caller already has a safe reference,
making the get/put cycle irrelevant.

We change ocfs2_get_*_extent_tree() to ocfs2_init_*_extent_tree().  It
no longer gets a reference on et_root_bh.  ocfs2_put_extent_tree() is
removed.  Callers now have a simpler init+use pattern.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

struct ocfs2_extent_tree_operations provides methods for the different
on-disk btrees in ocfs2.  Describing what those methods do is probably a
good idea.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

We now have three different kinds of extent trees in ocfs2: inode data
(dinode), extended attributes (xattr_tree), and extended attribute
values (xattr_value).  There is a nice abstraction for them,
ocfs2_extent_tree, but it is hidden in alloc.c.  All the calling
functions have to pick amongst a varied API and pass in type bits and
often extraneous pointers.

A better way is to make ocfs2_extent_tree a first-class object.
Everyone converts their object to an ocfs2_extent_tree() via the
ocfs2_get_*_extent_tree() calls, then uses the ocfs2_extent_tree for all
tree calls to alloc.c.

This simplifies a lot of callers, making for readability.  It also
provides an easy way to add additional extent tree types, as they only
need to be defined in alloc.c with a ocfs2_get_<new>_extent_tree()
function.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

A couple places check an extent_tree for a valid inode.  We move that
out to add an eo_insert_check() operation.  It can be called from
ocfs2_insert_extent() and elsewhere.

We also have the wrapper calls ocfs2_et_insert_check() and
ocfs2_et_sanity_check() ignore NULL ops.  That way we don't have to
provide useless operations for xattr types.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

A caller knows what kind of extent tree they have.  There's no reason
they have to call ocfs2_get_extent_tree() with a NULL when they could
just as easily call a specific function to their type of extent tree.

Introduce ocfs2_dinode_get_extent_tree(),
ocfs2_xattr_tree_get_extent_tree(), and
ocfs2_xattr_value_get_extent_tree().  They only take the necessary
arguments, calling into the underlying __ocfs2_get_extent_tree() to do
the real work.

__ocfs2_get_extent_tree() is the old ocfs2_get_extent_tree(), but
without needing any switch-by-type logic.

ocfs2_get_extent_tree() is now a wrapper around the specific calls.  It
exists because a couple alloc.c functions can take et_type.  This will
go later.

Another benefit is that ocfs2_xattr_value_get_extent_tree() can take a
struct ocfs2_xattr_value_root* instead of void*.  This gives us
typechecking where we didn't have it before.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Provide an optional extent_tree_operation to specify the
max_leaf_clusters of an ocfs2_extent_tree.  If not provided, the value
is 0 (unlimited).
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

ocfs2_num_free_extents() re-implements the logic of
ocfs2_get_extent_tree().  Now that ocfs2_get_extent_tree() does not
allocate, let's use it in ocfs2_num_free_extents() to simplify the code.

The inode validation code in ocfs2_num_free_extents() is not needed.
All callers are passing in pre-validated inodes.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The root_el of an ocfs2_extent_tree needs to be calculated from
et->et_object.  Make it an operation on et->et_ops.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The 'private' pointer was a way to store off xattr values, which don't
live at a set place in the bh.  But the concept of "the object
containing the extent tree" is much more generic.  For an inode it's the
struct ocfs2_dinode, for an xattr value its the value.  Let's save off
the 'object' at all times.  If NULL is passed to
ocfs2_get_extent_tree(), 'object' is set to bh->b_data;
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Rather than allocating a struct ocfs2_extent_tree, just put it on the
stack.  Fill it with ocfs2_get_extent_tree() and drop it with
ocfs2_put_extent_tree().  Now the callers don't have to ENOMEM, yet
still safely ref the root_bh.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The members of the ocfs2_extent_tree structure gain a prefix of 'et_'.
All users are updated.
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The ocfs2_extent_tree_operations structure gains a field prefix on its
members.  The ->eo_sanity_check() operation gains a wrapper function for
completeness.  All of the extent tree operation wrappers gain a
consistent name (ocfs2_et_*()).
Signed-off-by: NJoel Becker <joel.becker@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

This patch fixes the following build warnings:

fs/ocfs2/xattr.c: In function 'ocfs2_half_xattr_bucket':
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 7 has type 'long int'
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 8 has type 'long int'
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 7 has type 'long int'
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 8 has type 'long int'
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 7 has type 'long int'
fs/ocfs2/xattr.c:3282: warning: format '%d' expects type 'int', but argument 8 has type 'long int'
fs/ocfs2/xattr.c: In function 'ocfs2_xattr_set_entry_in_bucket':
fs/ocfs2/xattr.c:4092: warning: format '%d' expects type 'int', but argument 6 has type 'size_t'
fs/ocfs2/xattr.c:4092: warning: format '%d' expects type 'int', but argument 6 has type 'size_t'
fs/ocfs2/xattr.c:4092: warning: format '%d' expects type 'int', but argument 6 has type 'size_t'
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

This patch adds the s_incompat flag for extended attribute support. This
helps us ensure that older versions of Ocfs2 or ocfs2-tools will not be able
to mount a volume with xattr support.
Signed-off-by: NTiger Yang <tiger.yang@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

In inode removal, we need to iterate all the buckets, remove any
externally-stored EA values and delete the xattr buckets.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Where the previous patches added the ability of list/get xattr in buckets
for ocfs2, this patch enables ocfs2 to store large numbers of EAs.

The original design doc is written by Mark Fasheh, and it can be found in
http://oss.oracle.com/osswiki/OCFS2/DesignDocs/IndexedEATrees. I only had to
make small modifications to it.

First, because the bucket size is 4K, a new field named xh_free_start is added
in ocfs2_xattr_header to indicate the next valid name/value offset in a bucket.
It is used when we store new EA name/value. With this field, we can find the
place more quickly and what's more, we don't need to sort the name/value every
time to let the last entry indicate the next unused space. This makes the
insert operation more efficient for blocksizes smaller than 4k.

Because of the new xh_free_start, another field named as xh_name_value_len is
also added in ocfs2_xattr_header. It records the total length of all the
name/values in the bucket. We need this so that we can check it and defragment
the bucket if there is not enough contiguous free space.

An xattr insertion looks like this:
1. xattr_index_block_find: find the right bucket by the name_hash, say bucketA.
2. check whether there is enough space in bucketA. If yes, insert it directly
   and modify xh_free_start and xh_name_value_len accordingly. If not, check
   xh_name_value_len to see whether we can store this by defragment the bucket.
   If yes, defragment it and go on insertion.
3. If defragement doesn't work, check whether there is new empty bucket in
   the clusters within this extent record. If yes, init the new bucket and move
   all the buckets after bucketA one by one to the next bucket. Move half of the
   entries in bucketA to the next bucket and go on insertion.
4. If there is no new bucket, grow the extent tree.

As for xattr deletion, we will delete an xattr bucket when all it's xattrs
are removed and move all the buckets after it to the previous one. When all
the xattr buckets in an extend record are freed, free this extend records
from ocfs2_xattr_tree.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

In xattr bucket, we want to limit the maximum size of a btree leaf,
otherwise we'll lose the benefits of hashing because we'll have to search
large leaves.

So add a new field in ocfs2_extent_tree which indicates the maximum leaf cluster
size we want so that we can prevent ocfs2_insert_extent() from merging the leaf
record even if it is contiguous with an adjacent record.

Other btree types are not affected by this change.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Add code to lookup a given extended attribute in the xattr btree. Lookup
follows this general scheme:

1. Use ocfs2_xattr_get_rec to find the xattr extent record

2. Find the xattr bucket within the extent which may contain this xattr

3. Iterate the bucket to find the xattr. In ocfs2_xattr_block_get(), we need
   to recalcuate the block offset and name offset for the right position of
   name/value.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Ocfs2 breaks up xattr index tree leaves into 4k regions, called buckets.
Attributes are stored within a given bucket, depending on hash value.

After a discussion with Mark, we decided that the per-bucket index
(xe_entry[]) would only exist in the 1st block of a bucket. Likewise,
name/value pairs will not straddle more than one block. This allows the
majority of operations to work directly on the buffer heads in a leaf block.

This patch adds code to iterate the buckets in an EA. A new abstration of
ocfs2_xattr_bucket is added. It records the bhs in this bucket and
ocfs2_xattr_header. This keeps the code neat, improving readibility.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

When necessary, an ocfs2_xattr_block will embed an ocfs2_extent_list to
store large numbers of EAs. This patch adds a new type in
ocfs2_extent_tree_type and adds the implementation so that we can re-use the
b-tree code to handle the storage of many EAs.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

This patch implements storing extended attributes both in inode or a single
external block. We only store EA's in-inode when blocksize > 512 or that
inode block has free space for it. When an EA's value is larger than 80
bytes, we will store the value via b-tree outside inode or block.
Signed-off-by: NTiger Yang <tiger.yang@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Add the structures and helper functions we want for handling inline extended
attributes. We also update the inline-data handlers so that they properly
function in the event that we have both inline data and inline attributes
sharing an inode block.
Signed-off-by: NTiger Yang <tiger.yang@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Add some thin wrappers around ocfs2_insert_extent() for each of the 3
different btree types, ocfs2_inode_insert_extent(),
ocfs2_xattr_value_insert_extent() and ocfs2_xattr_tree_insert_extent(). The
last is for the xattr index btree, which will be used in a followup patch.

All the old callers in file.c etc will call ocfs2_dinode_insert_extent(),
while the other two handle the xattr issue. And the init of extent tree are
handled by these functions.

When storing xattr value which is too large, we will allocate some clusters
for it and here ocfs2_extent_list and ocfs2_extent_rec will also be used. In
order to re-use the b-tree operation code, a new parameter named "private"
is added into ocfs2_extent_tree and it is used to indicate the root of
ocfs2_exent_list. The reason is that we can't deduce the root from the
buffer_head now. It may be in an inode, an ocfs2_xattr_block or even worse,
in any place in an ocfs2_xattr_bucket.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

The old uptodate only handles the issue of removing one buffer_head from
ocfs2 inode's buffer cache. With xattr clusters, we may need to remove
multiple buffer_head's at a time.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Ocfs2 uses a very flexible structure for storing extended attributes on
disk. Small amount of attributes are stored directly in the inode block - up
to 256 bytes worth. If that fills up, attributes are also stored in an
external block, linked to from the inode block. That block can in turn
expand to a btree, capable of storing large numbers of attributes.

Individual attribute values are stored inline if they're small enough
(currently about 80 bytes, this can be changed though), and otherwise are
expanded to a btree. The theoretical limit to the size of an individual
attribute is about the same as an inode, though the kernel's upper bound on
the size of an attributes data is far smaller.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Factor out the non-inode specifics of ocfs2_do_extend_allocation() into a more generic
function, ocfs2_do_cluster_allocation(). ocfs2_do_extend_allocation calls
ocfs2_do_cluster_allocation() now, but the latter can be used for other
btree types as well.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

In the old extent tree operation, we take the hypothesis that we
are using the ocfs2_extent_list in ocfs2_dinode as the tree root.
As xattr will also use ocfs2_extent_list to store large value
for a xattr entry, we refactor the tree operation so that xattr
can use it directly.

The refactoring includes 4 steps:
1. Abstract set/get of last_eb_blk and update_clusters since they may
   be stored in different location for dinode and xattr.
2. Add a new structure named ocfs2_extent_tree to indicate the
   extent tree the operation will work on.
3. Remove all the use of fe_bh and di, use root_bh and root_el in
   extent tree instead. So now all the fe_bh is replaced with
   et->root_bh, el with root_el accordingly.
4. Make ocfs2_lock_allocators generic. Now it is limited to be only used
   in file extend allocation. But the whole function is useful when we want
   to store large EAs.

Note: This patch doesn't touch ocfs2_commit_truncate() since it is not used
for anything other than truncate inode data btrees.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

ocfs2_extend_meta_needed(), ocfs2_calc_extend_credits() and
ocfs2_reserve_new_metadata() are all useful for extent tree operations. But
they are all limited to an inode btree because they use a struct
ocfs2_dinode parameter. Change their parameter to struct ocfs2_extent_list
(the part of an ocfs2_dinode they actually use) so that the xattr btree code
can use these functions.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

ocfs2_num_free_extents() is used to find the number of free extent records
in an inode btree. Hence, it takes an "ocfs2_dinode" parameter. We want to
use this for extended attribute trees in the future, so genericize the
interface the take a buffer head. A future patch will allow that buffer_head
to contain any structure rooting an ocfs2 btree.
Signed-off-by: NTao Ma <tao.ma@oracle.com>
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

A per-mount debugfs file, "local_alloc" is created which when read will
expose live state of the nodes local alloc file. Performance impact is
minimal, only a bit of memory overhead per mount point. Still, the code is
hidden behind CONFIG_OCFS2_FS_STATS. This feature will help us debug
local alloc performance problems on a live system.
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Ocfs2's local allocator disables itself for the duration of a mount point
when it has trouble allocating a large enough area from the primary bitmap.
That can cause performance problems, especially for disks which were only
temporarily full or fragmented. This patch allows for the allocator to
shrink it's window first, before being disabled. Later, it can also be
re-enabled so that any performance drop is minimized.

To do this, we allow the value of osb->local_alloc_bits to be shrunk when
needed. The default value is recorded in a mostly read-only variable so that
we can re-initialize when required.

Locking had to be updated so that we could protect changes to
local_alloc_bits. Mostly this involves protecting various local alloc values
with the osb spinlock. A new state is also added, OCFS2_LA_THROTTLED, which
is used when the local allocator is has shrunk, but is not disabled. If the
available space dips below 1 megabyte, the local alloc file is disabled. In
either case, local alloc is re-enabled 30 seconds after the event, or when
an appropriate amount of bits is seen in the primary bitmap.
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

Do this instead of tracking absolute local alloc size. This avoids
needless re-calculatiion of bits from bytes in localalloc.c. Additionally,
the value is now in a more natural unit for internal file system bitmap
work.
Signed-off-by: NMark Fasheh <mfasheh@suse.com>

This is actually pretty easy since fs/dlm already handles the bulk of the
work. The Ocfs2 userspace cluster stack module already uses fs/dlm as the
underlying lock manager, so I only had to add the right calls.

Cluster-aware POSIX locks ("plocks") can be turned off by the same means at
UNIX locks - mount with 'noflocks', or create a local-only Ocfs2 volume.
Internally, the file system uses two sets of file_operations, depending on
whether cluster aware plocks is required. This turns out to be easier than
implementing local-only versions of ->lock.
Signed-off-by: NMark Fasheh <mfasheh@suse.com>