btrfs-transacion:5657
[stack snip]
btrfs_bio_map()
    btrfs_bio_counter_inc_blocked()
        percpu_counter_inc(&fs_info->bio_counter)  ###bio_counter > 0(A)
        __btrfs_bio_map()
            btrfs_dev_replace_lock()
                mutex_lock(dev_replace->lock)	   ###wait mutex(B)

btrfs:32612
[stack snip]
btrfs_dev_replace_start()
    btrfs_dev_replace_lock()
	mutex_lock(dev_replace->lock)		   ###hold mutex(B)
    btrfs_dev_replace_finishing()
        btrfs_rm_dev_replace_blocked()
            wait until percpu_counter_sum == 0	   ###wait on bio_counter(A)

This bug can be triggered quite easily by the following test script:
http://pastebin.com/MQmb37Cy

This patch will fix the ABBA problem by calling
btrfs_dev_replace_unlock() before btrfs_rm_dev_replace_blocked().

The consistency of btrfs devices list and their superblocks is protected
by device_list_mutex, not btrfs_dev_replace_lock/unlock().
So it is safe the move btrfs_dev_replace_unlock() before
btrfs_rm_dev_replace_blocked().
Reported-by: NZhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: NQu Wenruo <quwenruo@cn.fujitsu.com>
Cc: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: NChris Mason <clm@fb.com>

We've defined a 'offset' out of bio_for_each_segment_all.

This is just a clean rename, no function changes.
Signed-off-by: NLiu Bo <bo.li.liu@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

btrfs_drop_snapshot() leaves subvolume qgroup items on disk after
completion. This can cause problems with snapshot creation. If a new
snapshot tries to claim the deleted subvolumes id, btrfs will get -EEXIST
from add_qgroup_item() and go read-only. The following commands will
reproduce this problem (assume btrfs is on /dev/sda and is mounted at
/btrfs)

mkfs.btrfs -f /dev/sda
mount -t btrfs /dev/sda /btrfs/
btrfs quota enable /btrfs/
btrfs su sna /btrfs/ /btrfs/snap
btrfs su de /btrfs/snap
sleep 45
umount /btrfs/
mount -t btrfs /dev/sda /btrfs/

We can fix this by catching -EEXIST in add_qgroup_item() and
initializing the existing items. We have the problem of orphaned
relation items being on disk from an old snapshot but that is outside
the scope of this patch.
Signed-off-by: NMark Fasheh <mfasheh@suse.de>
Signed-off-by: NChris Mason <clm@fb.com>

Use %pf instead of %p, just same as kernel workqueue tracepoints.
Signed-off-by: NLiu Bo <bo.li.liu@oracle.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

The map_start and map_len fields aren't used anywhere, so just remove
them. On a x86_64 system, this reduced sizeof(struct extent_buffer)
from 296 bytes to 280 bytes, and therefore 14 extent_buffer structs can
now fit into a page instead of 13.
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

Maximum xattr size can be up to nearly the leaf size. For an fs with a
leaf size larger than the page size, using kmalloc requires allocating
multiple pages that are contiguous, which might not be possible if
there's heavy memory fragmentation. Therefore fallback to vmalloc if
we fail to allocate with kmalloc. Also start with a smaller buffer size,
since xattr values typically are smaller than a page.
Reported-by: NChris Murphy <lists@colorremedies.com>
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NChris Mason <clm@fb.com>

Last user removed in commit "btrfs: disable strict file flushes for
renames and truncates" (8d875f95).
Signed-off-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

While under random IO, a block group's free space cache eventually reaches
a state where it has a mix of extent entries and bitmap entries representing
free space regions.

As later free space regions are returned to the cache, some of them are merged
with existing extent entries if they are contiguous with them. But others are
not merged, because despite the existence of adjacent free space regions in
the cache, the merging doesn't happen because the existing free space regions
are represented in bitmap extents. Even when new free space regions are merged
with existing extent entries (enlarging the free space range they represent),
we create chances of having after an enlarged region that is contiguous with
some other region represented in a bitmap entry.

Both clustered and non-clustered space allocation work by iterating over our
extent and bitmap entries and skipping any that represents a region smaller
then the allocation request (and giving preference to extent entries before
bitmap entries). By having a contiguous free space region that is represented
by 2 (or more) entries (mix of extent and bitmap entries), we end up not
satisfying an allocation request with a size larger than the size of any of
the entries but no larger than the sum of their sizes. Making the caller assume
we're under a ENOSPC condition or force it to allocate multiple smaller space
regions (as we do for file data writes), which adds extra overhead and more
chances of causing fragmentation due to the smaller regions being all spread
apart from each other (more likely when under concurrency).

For example, if we have the following in the cache:

* extent entry representing free space range: [128Mb - 256Kb, 128Mb[

* bitmap entry covering the range [128Mb, 256Mb[, but only with the bits
  representing the range [128Mb, 128Mb + 768Kb[ set - that is, only that
  space in this 128Mb area is marked as free

An allocation request for 1Mb, starting at offset not greater than 128Mb - 256Kb,
would fail before, despite the existence of such contiguous free space area in the
cache. The caller could only allocate up to 768Kb of space at once and later another
256Kb (or vice-versa). In between each smaller allocation request, another task
working on a different file/inode might come in and take that space, preventing the
former task of getting a contiguous 1Mb region of free space.

Therefore this change implements the ability to move free space from bitmap
entries into existing and new free space regions represented with extent
entries. This is done when a space region is added to the cache.

A test was added to the sanity tests that explains in detail the issue too.

Some performance test results with compilebench on a 4 cores machine, with
32Gb of ram and using an HDD follow.

Test: compilebench -D /mnt -i 30 -r 1000 --makej

Before this change:

   intial create total runs 30 avg 69.02 MB/s (user 0.28s sys 0.57s)
   compile total runs 30 avg 314.96 MB/s (user 0.12s sys 0.25s)
   read compiled tree total runs 3 avg 27.14 MB/s (user 1.52s sys 0.90s)
   delete compiled tree total runs 30 avg 3.14 seconds (user 0.15s sys 0.66s)

After this change:

   intial create total runs 30 avg 68.37 MB/s (user 0.29s sys 0.55s)
   compile total runs 30 avg 382.83 MB/s (user 0.12s sys 0.24s)
   read compiled tree total runs 3 avg 27.82 MB/s (user 1.45s sys 0.97s)
   delete compiled tree total runs 30 avg 3.18 seconds (user 0.17s sys 0.65s)
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NChris Mason <clm@fb.com>

we are assigning number_devices to the total_bytes,
that's very confusing for a moment
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

there is no matching open parenthesis for the closing parenthesis
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

seed fs devices don't participate as rw_device, so don't increment
rw_devices when the device being handled belongs to a seed fs.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

When we replace all the seed device in the system there is
no point in just keeping the btrfs_fs_devices with out
any device
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

We are not updating sprout fs seed pointer when all seed device
is replaced. This patch will check if all seed device has been
replaced and then update the sprout pointer accordingly.

Same reproducer as in the previous patch would apply here.
And notice that btrfs_close_device will check if seed fs is
present and spits out the error with out this patch.

int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
::
                seed_devices = fs_devices->seed;
::
        while (seed_devices) {
                fs_devices = seed_devices;
                seed_devices = fs_devices->seed;
                __btrfs_close_devices(fs_devices);
                free_fs_devices(fs_devices);
        }
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

reproducer:
    reproducer:
    mount /dev/sdb /btrfs
    btrfs dev add /dev/sdc /btrfs
    btrfs rep start -B /dev/sdb /dev/sdd /btrfs
    umount /btrfs

WARNING: CPU: 0 PID: 3882 at fs/btrfs/volumes.c:892 __btrfs_close_devices+0x1c8/0x200 [btrfs]()

which is

        WARN_ON(fs_devices->rw_devices);

   The problem here is that we did not add one to the rw_devices when
   we replace the seed device with a writable device.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

reproducer:
mount /dev/sdb /btrfs
btrfs dev add /dev/sdc /btrfs
btrfs rep start -B /dev/sdb /dev/sdd /btrfs
umount /btrfs

WARNING: CPU: 0 PID: 12661 at fs/btrfs/volumes.c:891 __btrfs_close_devices+0x1b0/0x200 [btrfs]()
::

__btrfs_close_devices()
::
        WARN_ON(fs_devices->open_devices);

After the seed device has been replaced the new target device
is no more a seed device. So we need to update the device
numbers in the fs_devices as pointed by the fs_info.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Reviewed-by: NMiao Xie <miaox@cn.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

There is no logical change in this patch, just a preparatory patch,
so that changes can be easily reasoned.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

The issue was introduced in a79b7d4b,
adding allocation of extent_workers, so this stray check is surely not
meant to be a check of something else.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=82021Reported-by: NMaks Naumov <maksqwe1@ukr.net>
Signed-off-by: NAndrey Utkin <andrey.krieger.utkin@gmail.com>
Reviewed-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: NChris Mason <clm@fb.com>

None of the uses of btrfs_search_forward() need to have the path
nodes (level >= 1) read locked, only the leaf needs to be locked
while the caller processes it. Therefore make it return a path
with all nodes unlocked, except for the leaf.

This change is motivated by the observation that during a file
fsync we repeatdly call btrfs_search_forward() and process the
returned leaf while upper nodes of the returned path (level >= 1)
are read locked, which unnecessarily blocks other tasks that want
to write to the same fs/subvol btree.
Therefore instead of modifying the fsync code to unlock all nodes
with level >= 1 immediately after calling btrfs_search_forward(),
change btrfs_search_forward() to do it, so that it benefits all
callers.
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NChris Mason <clm@fb.com>

Not sure how this escaped many eyes so far
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

BTRFS_ATTR_RW could set the mode and be inline with BTRFS_ATTR
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

All that uses BTRFS_ATTR want mode to be set at 0444 so just do
it at the define.  And few spacing alignments.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

we have BTRFS_ATTR define to create sysfs RO file, use that.
Signed-off-by: NAnand Jain <anand.jain@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

If we need to cow a node, increase the write lock level and retry the
tree search, there's no point of changing the node locks in our path
to blocking mode, as we only waste time and unnecessarily wake up other
tasks waiting on the spinning locks (just to block them again shortly
after) because we release our path before repeating the tree search.
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NChris Mason <clm@fb.com>

In ctree.c:setup_items_for_insert(), we can unlock all nodes in our
path before we process the leaf (shift items and data, adjust data
offsets, etc). This allows for better btree concurrency, as we're
often holding a write lock on at least the node at level 1.
Signed-off-by: NFilipe Manana <fdmanana@suse.com>
Signed-off-by: NChris Mason <clm@fb.com>

btrfs_lookup_csums_range() uses ALIGN() to check if "start"
and "end + 1" are aligned to "root->sectorsize". It's better to
replace these with IS_ALIGNED() for simplicity.
Signed-off-by: NSatoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

Tracepoint trace_btrfs_normal_work_done never has an user, just cleanup it.
Signed-off-by: NLiu Bo <bo.li.liu@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

Kernel workqueue's tracepoints print the address of work_struct, while btrfs
workqueue's tracepoints print the address of btrfs_work.

We need a connection between this two, for example when debuging, we usually
grep an address in the trace output.  So it'd be better to also print
work_struct in btrfs workqueue's tracepoint.

Please note that we can only add this into those tracepoints whose work is still
available in memory because we need to reference the work.
Signed-off-by: NLiu Bo <bo.li.liu@oracle.com>
Signed-off-by: NChris Mason <clm@fb.com>

We want this to debug qgroup changes on live systems.
Signed-off-by: NMark Fasheh <mfasheh@suse.de>
Reviewed-by: NJosef Bacik <jbacik@fb.com>
Signed-off-by: NChris Mason <clm@fb.com>

The member variants - latest_devid and latest_trans - of fs_devices structure
are set, but no one use them to do anything. so remove them.
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

The io error might happen during writing out the device stats, and the
device stats information and dirty flag would be update at that time,
but the current code didn't consider this case, just clear the dirty
flag, it would cause that we forgot to write out the new device stats
information. Fix it.
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

The lock in btrfs_device structure was far away from its protected data, it would
make CPU load the cache line twice when we accessed them, move them together.
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Signed-off-by: NChris Mason <clm@fb.com>

The super block generation of the seed devices is not the same as the
filesystem which sprouted from them because we don't update the super
block on the seed devices when we change that new filesystem. So we
should not use the generation of that new filesystem to check the super
block generation on the seed devices, Fix it.
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

All the metadata in the seed devices has the same fsid as the fsid
of the seed filesystem which is on the seed device, so we should check
them by the current filesystem. Fix it.
Signed-off-by: NMiao Xie <miaox@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

The transaction thread may want to do more work, namely it pokes the
cleaner ktread that will start processing uncleaned subvols.

This can be triggered by user via the 'btrfs fi sync' command, otherwise
there was a delay up to 30 seconds before the cleaner started to clean
old snapshots.
Signed-off-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

inline data is stored from offset of @disk_bytenr in
struct btrfs_file_extent_item. So substracting total
size of struct btrfs_file_extent_item is wrong, fix it.
Signed-off-by: NWang Shilong <wangsl.fnst@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

Btrfs could still inline file data if its size is same as
page size, so don't skip max value here.
Signed-off-by: NWang Shilong <wangsl.fnst@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

If flag NOCOMPRESS is set which means bad compression ratio,
we could avoid call cow_file_range_async() for this case earlier.
Signed-off-by: NWang Shilong <wangsl.fnst@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

If a file's compression ratios is bad, we will set NOCOMPRESS
flag for it, and it will skip compression for that inode next time.

However, if we remount fs to COMPRESS_FORCE, it still should try
if we could compress pages for that inode, this patch fix wrong
check for this problem.
Signed-off-by: NWang Shilong <wangsl.fnst@cn.fujitsu.com>
Reviewed-by: NDavid Sterba <dsterba@suse.cz>
Signed-off-by: NChris Mason <clm@fb.com>

Fix the following sparse warning:
fs/btrfs/send.c:518:51: warning: incorrect type in argument 2 (different address spaces)
fs/btrfs/send.c:518:51:    expected char const [noderef] <asn:1>*<noident>
fs/btrfs/send.c:518:51:    got char *

We can safely use (const char __user *) with set_fs(KERNEL_DS)

__force added to avoid sparse-all warning:
fs/btrfs/send.c:518:40: warning: cast adds address space to expression (<asn:1>)
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Reviewed-by: NZach Brown <zab@zabbo.net>
Signed-off-by: NChris Mason <clm@fb.com>