Otherwise we can execced the array bound of path->slots[].
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>

Before the reader/writer locks, btrfs_next_leaf needed to keep
the path blocking to avoid making lockdep upset.

Now that btrfs_next_leaf only takes read locks, this isn't required.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The btrfs metadata btree is the source of significant
lock contention, especially in the root node.   This
commit changes our locking to use a reader/writer
lock.

The lock is built on top of rw spinlocks, and it
extends the lock tracking to remember if we have a
read lock or a write lock when we go to blocking.  Atomics
count the number of blocking readers or writers at any
given time.

It removes all of the adaptive spinning from the old code
and uses only the spinning/blocking hints inside of btrfs
to decide when it should continue spinning.

In read heavy workloads this is dramatically faster.  In write
heavy workloads we're still faster because of less contention
on the root node lock.

We suffer slightly in dbench because we schedule more often
during write locks, but all other benchmarks so far are improved.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The extent_buffers have a very complex interface where
we use HIGHMEM for metadata and try to cache a kmap mapping
to access the memory.

The next commit adds reader/writer locks, and concurrent use
of this kmap cache would make it even more complex.

This commit drops the ability to use HIGHMEM with extent buffers,
and rips out all of the related code.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Arne's scrub stuff exposed a problem with mapping the extent buffer in
reada_for_search.  He searches the commit root with multiple threads and with
skip_locking set, so we can race and overwrite node->map_token since node isn't
locked.  So fix this so that we only map the extent buffer if we don't already
have a map_token and skip_locking isn't set.  Without this patch scrub would
panic almost immediately, with the patch it doesn't panic anymore.  Thanks,
Reported-by: NArne Jansen <sensille@gmx.net>
Signed-off-by: NJosef Bacik <josef@redhat.com>

Arne's scrub stuff exposed a problem with mapping the extent buffer in
reada_for_search.  He searches the commit root with multiple threads and with
skip_locking set, so we can race and overwrite node->map_token since node isn't
locked.  So fix this so that we only map the extent buffer if we don't already
have a map_token and skip_locking isn't set.  Without this patch scrub would
panic almost immediately, with the patch it doesn't panic anymore.  Thanks,
Reported-by: NArne Jansen <sensille@gmx.net>
Signed-off-by: NJosef Bacik <josef@redhat.com>

Currently, btrfs_truncate_item and btrfs_extend_item returns only 0.
So, the check by BUG_ON in the caller is unnecessary.
Signed-off-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Our readahead is sort of sloppy, and really isn't always needed.  For example if
ls is doing a stating ls (which is the default) it's going to stat in non-disk
order, so if say you have a directory with a stupid amount of files, readahead
is going to do nothing but waste time in the case of doing the stat.  Taking the
unconditional readahead out made my test go from 57 minutes to 36 minutes.  This
means that everywhere we do loop through the tree we want to make sure we do set
path->reada properly, so I went through and found all of the places where we
loop through the path and set reada to 1.  Thanks,
Signed-off-by: NJosef Bacik <josef@redhat.com>

We have a bit of debugging in btrfs_search_slot to make sure the level of the
cow block is the same as the original block we were cow'ing.  I don't think I've
ever seen this tripped, so kill it.  This saves us 2 kmap's per level in our
search.  Thanks,
Signed-off-by: NJosef Bacik <josef@redhat.com>

If we have particularly full nodes, we could call btrfs_node_blockptr up to 32
times, which is 32 pairs of kmap/kunmap, which _sucks_.  So go ahead and map the
extent buffer while we look for readahead targets.  Thanks,
Signed-off-by: NJosef Bacik <josef@redhat.com>

Changelog V5 -> V6:
- Fix oom when the memory load is high, by storing the delayed nodes into the
  root's radix tree, and letting btrfs inodes go.

Changelog V4 -> V5:
- Fix the race on adding the delayed node to the inode, which is spotted by
  Chris Mason.
- Merge Chris Mason's incremental patch into this patch.
- Fix deadlock between readdir() and memory fault, which is reported by
  Itaru Kitayama.

Changelog V3 -> V4:
- Fix nested lock, which is reported by Itaru Kitayama, by updating space cache
  inode in time.

Changelog V2 -> V3:
- Fix the race between the delayed worker and the task which does delayed items
  balance, which is reported by Tsutomu Itoh.
- Modify the patch address David Sterba's comment.
- Fix the bug of the cpu recursion spinlock, reported by Chris Mason

Changelog V1 -> V2:
- break up the global rb-tree, use a list to manage the delayed nodes,
  which is created for every directory and file, and used to manage the
  delayed directory name index items and the delayed inode item.
- introduce a worker to deal with the delayed nodes.

Compare with Ext3/4, the performance of file creation and deletion on btrfs
is very poor. the reason is that btrfs must do a lot of b+ tree insertions,
such as inode item, directory name item, directory name index and so on.

If we can do some delayed b+ tree insertion or deletion, we can improve the
performance, so we made this patch which implemented delayed directory name
index insertion/deletion and delayed inode update.

Implementation:
- introduce a delayed root object into the filesystem, that use two lists to
  manage the delayed nodes which are created for every file/directory.
  One is used to manage all the delayed nodes that have delayed items. And the
  other is used to manage the delayed nodes which is waiting to be dealt with
  by the work thread.
- Every delayed node has two rb-tree, one is used to manage the directory name
  index which is going to be inserted into b+ tree, and the other is used to
  manage the directory name index which is going to be deleted from b+ tree.
- introduce a worker to deal with the delayed operation. This worker is used
  to deal with the works of the delayed directory name index items insertion
  and deletion and the delayed inode update.
  When the delayed items is beyond the lower limit, we create works for some
  delayed nodes and insert them into the work queue of the worker, and then
  go back.
  When the delayed items is beyond the upper bound, we create works for all
  the delayed nodes that haven't been dealt with, and insert them into the work
  queue of the worker, and then wait for that the untreated items is below some
  threshold value.
- When we want to insert a directory name index into b+ tree, we just add the
  information into the delayed inserting rb-tree.
  And then we check the number of the delayed items and do delayed items
  balance. (The balance policy is above.)
- When we want to delete a directory name index from the b+ tree, we search it
  in the inserting rb-tree at first. If we look it up, just drop it. If not,
  add the key of it into the delayed deleting rb-tree.
  Similar to the delayed inserting rb-tree, we also check the number of the
  delayed items and do delayed items balance.
  (The same to inserting manipulation)
- When we want to update the metadata of some inode, we cached the data of the
  inode into the delayed node. the worker will flush it into the b+ tree after
  dealing with the delayed insertion and deletion.
- We will move the delayed node to the tail of the list after we access the
  delayed node, By this way, we can cache more delayed items and merge more
  inode updates.
- If we want to commit transaction, we will deal with all the delayed node.
- the delayed node will be freed when we free the btrfs inode.
- Before we log the inode items, we commit all the directory name index items
  and the delayed inode update.

I did a quick test by the benchmark tool[1] and found we can improve the
performance of file creation by ~15%, and file deletion by ~20%.

Before applying this patch:
Create files:
        Total files: 50000
        Total time: 1.096108
        Average time: 0.000022
Delete files:
        Total files: 50000
        Total time: 1.510403
        Average time: 0.000030

After applying this patch:
Create files:
        Total files: 50000
        Total time: 0.932899
        Average time: 0.000019
Delete files:
        Total files: 50000
        Total time: 1.215732
        Average time: 0.000024

[1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3

Many thanks for Kitayama-san's help!
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dave@jikos.cz>
Tested-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Tested-by: NItaru Kitayama <kitayama@cl.bb4u.ne.jp>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

parameter tree root it's not used since commit
5f39d397 ("Btrfs: Create extent_buffer
interface for large blocksizes")
Signed-off-by: NDavid Sterba <dsterba@suse.cz>

Signed-off-by: NDavid Sterba <dsterba@suse.cz>

Signed-off-by: NDavid Sterba <dsterba@suse.cz>

This patch is checking return value of read_tree_block(),
and if it is NULL, error processing.
Signed-off-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This patch changes some BUG_ON() to the error return.
(but, most callers still use BUG_ON())
Signed-off-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Tracepoints can provide insight into why btrfs hits bugs and be greatly
helpful for debugging, e.g
              dd-7822  [000]  2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0
              dd-7822  [000]  2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0
 btrfs-transacti-7804  [001]  2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0)
 btrfs-transacti-7804  [001]  2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0)
 btrfs-transacti-7804  [001]  2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8
   flush-btrfs-2-7821  [001]  2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA
   flush-btrfs-2-7821  [001]  2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0)
   flush-btrfs-2-7821  [001]  2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0)
   flush-btrfs-2-7821  [000]  2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0)
 btrfs-endio-wri-7800  [001]  2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0)
 btrfs-endio-wri-7800  [001]  2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0)

Here is what I have added:

1) ordere_extent:
        btrfs_ordered_extent_add
        btrfs_ordered_extent_remove
        btrfs_ordered_extent_start
        btrfs_ordered_extent_put

These provide critical information to understand how ordered_extents are
updated.

2) extent_map:
        btrfs_get_extent

extent_map is used in both read and write cases, and it is useful for tracking
how btrfs specific IO is running.

3) writepage:
        __extent_writepage
        btrfs_writepage_end_io_hook

Pages are cirtical resourses and produce a lot of corner cases during writeback,
so it is valuable to know how page is written to disk.

4) inode:
        btrfs_inode_new
        btrfs_inode_request
        btrfs_inode_evict

These can show where and when a inode is created, when a inode is evicted.

5) sync:
        btrfs_sync_file
        btrfs_sync_fs

These show sync arguments.

6) transaction:
        btrfs_transaction_commit

In transaction based filesystem, it will be useful to know the generation and
who does commit.

7) back reference and cow:
	btrfs_delayed_tree_ref
	btrfs_delayed_data_ref
	btrfs_delayed_ref_head
	btrfs_cow_block

Btrfs natively supports back references, these tracepoints are helpful on
understanding btrfs's COW mechanism.

8) chunk:
	btrfs_chunk_alloc
	btrfs_chunk_free

Chunk is a link between physical offset and logical offset, and stands for space
infomation in btrfs, and these are helpful on tracing space things.

9) reserved_extent:
	btrfs_reserved_extent_alloc
	btrfs_reserved_extent_free

These can show how btrfs uses its space.
Signed-off-by: NLiu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The pointer to the extent buffer for the root of each tree
is protected by a spinlock so that we can safely read the pointer
and take a reference on the extent buffer.

But now that the extent buffers are freed via RCU, we can safely
use rcu_read_lock instead.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Currently if we have corrupted items things will blow up in spectacular ways.
So as we read in blocks and they are leaves, check the entire leaf to make sure
all of the items are correct and point to valid parts in the leaf for the item
data the are responsible for.  If the item is corrupt we will kick back EIO and
not read any of the copies since they are likely to not be correct either.  This
will catch generic corruptions, it will be up to the individual callers of
btrfs_search_slot to make sure their items are right.  Thanks,
Signed-off-by: NJosef Bacik <josef@redhat.com>

Should check if functions returns NULL or not.
Signed-off-by: NTsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Hi,

In fs/btrfs/inode.c::fixup_tree_root_location() we have this code:

...
 		if (!path) {
 			err = -ENOMEM;
 			goto out;
 		}
...
 	out:
 		btrfs_free_path(path);
 		return err;

btrfs_free_path() passes its argument on to other functions and some of
them end up dereferencing the pointer.
In the code above that pointer is clearly NULL, so btrfs_free_path() will
eventually cause a NULL dereference.

There are many ways to cut this cake (fix the bug). The one I chose was to
make btrfs_free_path() deal gracefully with NULL pointers. If you
disagree, feel free to come up with an alternative patch.
Signed-off-by: NJesper Juhl <jj@chaosbits.net>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

These are all the cases where a variable is set, but not read which are
not bugs as far as I can see, but simply leftovers.

Still needs more review.

Found by gcc 4.6's new warnings
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Chris Mason <chris.mason@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

When btrfs discovers the generation number in a btree block is
incorrect, it can loop forever without forcing the RAID
code to try a valid mirror, and without returning EIO.

This changes things to properly kick out the EIO.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

split_leaf was not properly balancing leaves when it was forced to
split a leaf twice.  This commit adds an extra push left and right
before forcing the double split in hopes of getting the slot where
we want to insert at either the start or end of the leaf.

If the extra pushes do work, then we are able to avoid splitting twice
and we keep the tree properly balanced.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

After the path is released, the generation number got from block
pointer is no long valid. The race may cause disk corruption, because
verify_parent_transid() calls clear_extent_buffer_uptodate() when
generation numbers mismatch.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This patch adds metadata ENOSPC handling for the balance code.
It is consisted by following major changes:

1. Avoid COW tree leave in the phrase of merging tree.

2. Handle interaction with snapshot creation.

3. make the backref cache can live across transactions.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Introducing metadata reseravtion contexts has two major advantages.
First, it makes metadata reseravtion more traceable. Second, it can
reclaim freed space and re-add them to the itself after transaction
committed.

Besides add btrfs_block_rsv structure and related helper functions,
This patch contains following changes:

Move code that decides if freed tree block should be pinned into
btrfs_free_tree_block().

Make space accounting more accurate, mainly for handling read only
block groups.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

setup_leaf_for_split needs to drop the path and search again, and has
checks to see if the item we want to split changed size.  But, it misses
the case where the leaf changed and now has enough room for the item
we want to insert.

This adds an extra check to make sure the leaf really needs splitting
before we call btrfs_split_leaf(), which keeps us from trying to split
a leaf with a single item.

btrfs_split_leaf() will blindly split the single item leaf, leaving us
with one good leaf and one empty leaf and then a crash.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h

percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: NTejun Heo <tj@kernel.org>
Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

The bytes_used field in root item was originally planned to
trace the amount of used data and tree blocks. But it never
worked right since we can't trace freeing of data accurately.
This patch changes it to only trace the amount of tree blocks.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs_duplicate_item duplicates item with new key, guaranteeing
the source item and the new items are in the same tree leaf and
contiguous. It allows us to split file extent in place, without
using lock_extent to prevent bookend extent race.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

For every hardlink in btrfs, there is a corresponding inode back
reference. All inode back references for hardlinks in a given
directory are stored in single b-tree item. The size of b-tree item
is limited by the size of b-tree leaf, so we can only create limited
number of hardlinks to a given file in a directory.

The original code lacks of the check, it oops if the number of
hardlinks goes over the limit. This patch fixes the issue by adding
check to btrfs_link and btrfs_rename.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs_split_leaf and btrfs_del_items can end up in a loop
where one is constantly spliting a given leaf and the other
is constantly merging it back with the adjacent nodes.

There is a better fix for this, but in the interest of something
small, this patch just changes btrfs_del_items back to balancing less
often.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Check objectid of item before checking the item type, otherwise we may return
zero for a key that is actually too low.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

comp_keys is duplicating what is done in btrfs_comp_cpu_keys, so just
call it.
Signed-off-by: NDiego Calleja <diegocg@gmail.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

When walking up the tree, btrfs_find_next_key assumes the upper level tree
block is properly locked. This isn't always true even path->keep_locks is 1.
This is because btrfs_find_next_key may advance path->slots[] several times
instead of only once.

When 'path->slots[level] >= btrfs_header_nritems(path->nodes[level])' is found,
we can't guarantee the original value of 'path->slots[level]' is
'btrfs_header_nritems(path->nodes[level]) - 1'. If it's not, the tree block at
'level + 1' isn't locked.

This patch fixes the issue by explicitly checking the locking state,
re-searching the tree if it's not locked.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

if 1 is returned by btrfs_search_slot, the path already points to the
first item with 'key > searching key'. So increasing path->slots[0] by
one is superfluous in that case.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

With the new back reference code, the cost of a balance has gone down
in terms of the number of back reference updates done.  This commit
makes us more aggressively balance leaves and nodes as they become
less full.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

When the delayed reference code was added, some checks were added
to avoid extra balancing while the delayed references were being flushed.
This made for less efficient btrees, but it reduced the chances of
loops where no forward progress was made because the balances made
more delayed ref updates.

With the new dead root removal code and the mixed back references,
the extent allocation tree is no longer using precise back refs, and
the delayed reference updates don't carry the risk of looping forever
anymore.  So, the balance avoidance is no longer required.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.

When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one.  At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.

The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root.  This commit reduces the
transaction overhead by avoiding the need for dead root records.

When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.

This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.

We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.

This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.

This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.

This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.

The improved balancing code scales significantly better with a large
number of snapshots.

This is a very large commit and was written in a number of
pieces.  But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>