lockdep report following warning in test:
[25176.843958] =================================
[25176.844519] [ INFO: inconsistent lock state ]
[25176.845047] 4.1.0-rc3 #22 Tainted: G W
[25176.845591] ---------------------------------
[25176.846153] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[25176.846713] fsstress/26661 [HC0[0]:SC1[1]:HE1:SE0] takes:
[25176.847246] (&wr_ctx->wr_lock){+.?...}, at: [<ffffffffa04cdc6d>] scrub_free_ctx+0x2d/0xf0 [btrfs]
[25176.847838] {SOFTIRQ-ON-W} state was registered at:
[25176.848396] [<ffffffff810bf460>] __lock_acquire+0x6a0/0xe10
[25176.848955] [<ffffffff810bfd1e>] lock_acquire+0xce/0x2c0
[25176.849491] [<ffffffff816489af>] mutex_lock_nested+0x7f/0x410
[25176.850029] [<ffffffffa04d04ff>] scrub_stripe+0x4df/0x1080 [btrfs]
[25176.850575] [<ffffffffa04d11b1>] scrub_chunk.isra.19+0x111/0x130 [btrfs]
[25176.851110] [<ffffffffa04d144c>] scrub_enumerate_chunks+0x27c/0x510 [btrfs]
[25176.851660] [<ffffffffa04d3b87>] btrfs_scrub_dev+0x1c7/0x6c0 [btrfs]
[25176.852189] [<ffffffffa04e918e>] btrfs_dev_replace_start+0x36e/0x450 [btrfs]
[25176.852771] [<ffffffffa04a98e0>] btrfs_ioctl+0x1e10/0x2d20 [btrfs]
[25176.853315] [<ffffffff8121c5b8>] do_vfs_ioctl+0x318/0x570
[25176.853868] [<ffffffff8121c851>] SyS_ioctl+0x41/0x80
[25176.854406] [<ffffffff8164da17>] system_call_fastpath+0x12/0x6f
[25176.854935] irq event stamp: 51506
[25176.855511] hardirqs last enabled at (51506): [<ffffffff810d4ce5>] vprintk_emit+0x225/0x5e0
[25176.856059] hardirqs last disabled at (51505): [<ffffffff810d4b77>] vprintk_emit+0xb7/0x5e0
[25176.856642] softirqs last enabled at (50886): [<ffffffff81067a23>] __do_softirq+0x363/0x640
[25176.857184] softirqs last disabled at (50949): [<ffffffff8106804d>] irq_exit+0x10d/0x120
[25176.857746]
other info that might help us debug this:
[25176.858845] Possible unsafe locking scenario:
[25176.859981] CPU0
[25176.860537] ----
[25176.861059] lock(&wr_ctx->wr_lock);
[25176.861705] <Interrupt>
[25176.862272] lock(&wr_ctx->wr_lock);
[25176.862881]
*** DEADLOCK ***
Reason:
Above warning is caused by:
Interrupt
-> bio_endio()
-> ...
-> scrub_put_ctx()
-> scrub_free_ctx() *1
-> ...
-> mutex_lock(&wr_ctx->wr_lock);
scrub_put_ctx() is allowed to be called in end_bio interrupt, but
in code design, it will never call scrub_free_ctx(sctx) in interrupe
context(above *1), because btrfs_scrub_dev() get one additional
reference of sctx->refs, which makes scrub_free_ctx() only called
withine btrfs_scrub_dev().
Now the code runs out of our wish, because free sequence in
scrub_pending_bio_dec() have a gap.
Current code:
-----------------------------------+-----------------------------------
scrub_pending_bio_dec() | btrfs_scrub_dev
-----------------------------------+-----------------------------------
atomic_dec(&sctx->bios_in_flight); |
wake_up(&sctx->list_wait); |
| scrub_put_ctx()
| -> atomic_dec_and_test(&sctx->refs)
scrub_put_ctx(sctx); |
-> atomic_dec_and_test(&sctx->refs)|
-> scrub_free_ctx() |
-----------------------------------+-----------------------------------
We expected:
-----------------------------------+-----------------------------------
scrub_pending_bio_dec() | btrfs_scrub_dev
-----------------------------------+-----------------------------------
atomic_dec(&sctx->bios_in_flight); |
wake_up(&sctx->list_wait); |
scrub_put_ctx(sctx); |
-> atomic_dec_and_test(&sctx->refs)|
| scrub_put_ctx()
| -> atomic_dec_and_test(&sctx->refs)
| -> scrub_free_ctx()
-----------------------------------+-----------------------------------
Fix:
Move scrub_pending_bio_dec() to a workqueue, to avoid this function run
in interrupt context.
Tested by check tracelog in debug.
Changelog v1->v2:
Use workqueue instead of adjust function call sequence in v1,
because v1 will introduce a bug pointed out by:
Filipe David Manana <fdmanana@gmail.com>
Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
When allocating a new chunk or removing one we need to update num_devs
device items and insert or remove a chunk item in the chunk tree, so
in the worst case the space needed in the chunk space_info is:
btrfs_calc_trunc_metadata_size(chunk_root, num_devs) +
btrfs_calc_trans_metadata_size(chunk_root, 1)
That is, in the worst case we need to cow num_devs paths and cow 1 other
path that can result in splitting every node and leaf, and each path
consisting of BTRFS_MAX_LEVEL - 1 nodes and 1 leaf. We were requiring
some additional chunk_root->nodesize * BTRFS_MAX_LEVEL * num_devs bytes,
which were unnecessary since updating the existing device items does
not result in splitting the nodes and leaf since after updating them
they remain with the same size.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Unlike when attempting to allocate a new block group, where we check
that we have enough space in the system space_info to update the device
items and insert a new chunk item in the chunk tree, we were not checking
if the system space_info had enough space for updating the device items
and deleting the chunk item in the chunk tree. This often lead to -ENOSPC
error when attempting to allocate blocks for the chunk tree (during btree
node/leaf COW operations) while updating the device items or deleting the
chunk item, which resulted in the current transaction being aborted and
turning the filesystem into read-only mode.
While running fstests generic/038, which stresses allocation of block
groups and removal of unused block groups, with a large scratch device
(750Gb) this happened often, despite more than enough unallocated space,
and resulted in the following trace:
[68663.586604] WARNING: CPU: 3 PID: 1521 at fs/btrfs/super.c:260 __btrfs_abort_transaction+0x52/0x114 [btrfs]()
[68663.600407] BTRFS: Transaction aborted (error -28)
(...)
[68663.730829] Call Trace:
[68663.732585] [<ffffffff8142fa46>] dump_stack+0x4f/0x7b
[68663.734334] [<ffffffff8108b6a2>] ? console_unlock+0x361/0x3ad
[68663.739980] [<ffffffff81045ea5>] warn_slowpath_common+0xa1/0xbb
[68663.757153] [<ffffffffa036ca6d>] ? __btrfs_abort_transaction+0x52/0x114 [btrfs]
[68663.760925] [<ffffffff81045f05>] warn_slowpath_fmt+0x46/0x48
[68663.762854] [<ffffffffa03b159d>] ? btrfs_update_device+0x15a/0x16c [btrfs]
[68663.764073] [<ffffffffa036ca6d>] __btrfs_abort_transaction+0x52/0x114 [btrfs]
[68663.765130] [<ffffffffa03b3638>] btrfs_remove_chunk+0x597/0x5ee [btrfs]
[68663.765998] [<ffffffffa0384663>] ? btrfs_delete_unused_bgs+0x245/0x296 [btrfs]
[68663.767068] [<ffffffffa0384676>] btrfs_delete_unused_bgs+0x258/0x296 [btrfs]
[68663.768227] [<ffffffff8143527f>] ? _raw_spin_unlock_irq+0x2d/0x4c
[68663.769081] [<ffffffffa038b109>] cleaner_kthread+0x13d/0x16c [btrfs]
[68663.799485] [<ffffffffa038afcc>] ? btrfs_alloc_root+0x28/0x28 [btrfs]
[68663.809208] [<ffffffff8105f367>] kthread+0xef/0xf7
[68663.828795] [<ffffffff810e603f>] ? time_hardirqs_on+0x15/0x28
[68663.844942] [<ffffffff8105f278>] ? __kthread_parkme+0xad/0xad
[68663.846486] [<ffffffff81435a88>] ret_from_fork+0x58/0x90
[68663.847760] [<ffffffff8105f278>] ? __kthread_parkme+0xad/0xad
[68663.849503] ---[ end trace 798477c6d6dbaad6 ]---
[68663.850525] BTRFS: error (device sdc) in btrfs_remove_chunk:2652: errno=-28 No space left
So fix this by verifying that enough space exists in system space_info,
and reserving the space in the chunk block reserve, before attempting to
delete the block group and allocate a new system chunk if we don't have
enough space to perform the necessary updates and delete in the chunk
tree. Like for the block group creation case, we don't error our if we
fail to allocate a new system chunk, since we might end up not needing
it (no node/leaf splits happen during the COW operations and/or we end
up not needing to COW any btree nodes or leafs because they were already
COWed in the current transaction and their writeback didn't start yet).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
While creating a block group, we often end up getting ENOSPC while updating
the chunk tree, which leads to a transaction abortion that produces a trace
like the following:
[30670.116368] WARNING: CPU: 4 PID: 20735 at fs/btrfs/super.c:260 __btrfs_abort_transaction+0x52/0x106 [btrfs]()
[30670.117777] BTRFS: Transaction aborted (error -28)
(...)
[30670.163567] Call Trace:
[30670.163906] [<ffffffff8142fa46>] dump_stack+0x4f/0x7b
[30670.164522] [<ffffffff8108b6a2>] ? console_unlock+0x361/0x3ad
[30670.165171] [<ffffffff81045ea5>] warn_slowpath_common+0xa1/0xbb
[30670.166323] [<ffffffffa035daa7>] ? __btrfs_abort_transaction+0x52/0x106 [btrfs]
[30670.167213] [<ffffffff81045f05>] warn_slowpath_fmt+0x46/0x48
[30670.167862] [<ffffffffa035daa7>] __btrfs_abort_transaction+0x52/0x106 [btrfs]
[30670.169116] [<ffffffffa03743d7>] btrfs_create_pending_block_groups+0x101/0x130 [btrfs]
[30670.170593] [<ffffffffa038426a>] __btrfs_end_transaction+0x84/0x366 [btrfs]
[30670.171960] [<ffffffffa038455c>] btrfs_end_transaction+0x10/0x12 [btrfs]
[30670.174649] [<ffffffffa036eb6b>] btrfs_check_data_free_space+0x11f/0x27c [btrfs]
[30670.176092] [<ffffffffa039450d>] btrfs_fallocate+0x7c8/0xb96 [btrfs]
[30670.177218] [<ffffffff812459f2>] ? __this_cpu_preempt_check+0x13/0x15
[30670.178622] [<ffffffff81152447>] vfs_fallocate+0x14c/0x1de
[30670.179642] [<ffffffff8116b915>] ? __fget_light+0x2d/0x4f
[30670.180692] [<ffffffff81152863>] SyS_fallocate+0x47/0x62
[30670.186737] [<ffffffff81435b32>] system_call_fastpath+0x12/0x17
[30670.187792] ---[ end trace 0373e6b491c4a8cc ]---
This is because we don't do proper space reservation for the chunk block
reserve when we have multiple tasks allocating chunks in parallel.
So block group creation has 2 phases, and the first phase essentially
checks if there is enough space in the system space_info, allocating a
new system chunk if there isn't, while the second phase updates the
device, extent and chunk trees. However, because the updates to the
chunk tree happen in the second phase, if we have N tasks, each with
its own transaction handle, allocating new chunks in parallel and if
there is only enough space in the system space_info to allocate M chunks,
where M < N, none of the tasks ends up allocating a new system chunk in
the first phase and N - M tasks will get -ENOSPC when attempting to
update the chunk tree in phase 2 if they need to COW any nodes/leafs
from the chunk tree.
Fix this by doing proper reservation in the chunk block reserve.
The issue could be reproduced by running fstests generic/038 in a loop,
which eventually triggered the problem.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Old csum type check is wrong and can't catch csum_type 1(not supported).
Fix it to avoid hostile 0 division.
Reported-by: Lukas Lueg <lukas.lueg@gmail.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
The annotated functios will be placed into .text.unlikely section. The
annotation also hints compiler to move the code out of the hot paths,
and may implicitly mark if-statement leading to that block as unlikely.
This is a heuristic, the impact on the generated code is not
significant.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
WARN is called from a single location and all bugreports say that's in
super.c __btrfs_abort_transaction. This is slightly confusing as we'd
rather want to know the exact callsite. Whereas this information is
printed in the syslog below the stacktrace, this requires further look
and we usually see only the headline from WARNING.
Moving the WARN into the macro has to inline some code and increases
code by a few kilobytes:
text data bss dec hex filename
835481 20305 14120 869906 d4612 btrfs.ko.before
842883 20305 14120 877308 d62fc btrfs.ko.after
The delta is +7k (130+ calls), measured on 3.19 x86_64, distro config.
The increase is not small and could lead to worse icache use. The code
is on error/exit paths that can be recognized by compiler as cold and
moved out of the way so the impact is speculated to be low, if
measurable at all.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
This patch will provide a framework and help to create attributes
from the structure btrfs_fs_devices which are available even before
fs_info is created. So by moving the parent kobject super_kobj from
fs_info to btrfs_fs_devices, it will help to create attributes
from the btrfs_fs_devices as well.
Patches on top of this patch now will be able to create the
sys/fs/btrfs/fsid kobject and attributes from btrfs_fs_devices
when devices are scanned and registered to the kernel.
Just to note, this does not change any of the existing btrfs sysfs
external kobject names and its attributes and not even the life
cycle of them. Changes are internal only. And to ensure the same,
this path has been tested with various device operations and,
checking and comparing the sysfs kobjects and attributes with
sysfs kobject and attributes with out this patch, and they remain
same.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.cz>
Btrfs will create qgroup on subvolume creation if quota is enabled, but
qgroup uses the high bits(currently 16 bits) as level, to build the
inheritance.
However it is fully possible a subvolume can be created with a
subvolumeid larger than 1 << BTRFS_QGROUP_LEVEL_SHIFT, so it will be
considered as level 1 and can't be assigned to other qgroup in level 1.
This patch will prevent such things so qgroup inheritance will not be
screwed up.
The downside is very clear, btrfs subvolume number limit will decrease
from (u64 max - 256(fisrt free objectid) - 256(last free objectid)) to
(u48 max -256(first free objectid)).
But we still have near u48(that's 15 digits in dec), so that should not
be a huge problem.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
Although we have qgroup level check in btrfs-progs, it's not enough
since other programe may still call ioctl directly not using
btrfs-progs. For example, systemd.
But it's btrfs-progs to be blame since we don't provide a
full-function(like subvolume create things) btrfs library with enough
check, and only rely on kernel ioctl.
So Add level checks in kernel too.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
There are two problems in qgroup:
a). The PAGE_CACHE is 4K, even when we are writing a data of 1K,
qgroup will reserve a 4K size. It will cause the last 3K in a qgroup
is not available to user.
b). When user is writing a inline data, qgroup will not reserve it,
it means this is a window we can exceed the limit of a qgroup.
The main idea of this patch is reserving the data size of write_bytes
rather than the reserve_bytes. It means qgroup will not care about
the data size btrfs will reserve for user, but only care about the
data size user is going to write. Then reserve it when user want to
write and release it in transaction committed.
In this way, qgroup can be released from the complex procedure in
btrfs and only do the reserve when user want to write and account
when the data is written in commit_transaction().
Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Steps to reproduce:
while true; do
dd if=/dev/zero of=/btrfs_dir/file count=[fs_size * 75%]
rm /btrfs_dir/file
sync
done
And we'll see dd failed because btrfs return NO_SPACE.
Reason:
Normally, btrfs_commit_transaction() call btrfs_run_delayed_iputs()
in end to free fs space for next write, but sometimes it hadn't
done work on time, because btrfs-cleaner thread get delayed-iputs
from list before, but do iput() after next write.
This is log:
[ 2569.050776] comm=btrfs-cleaner func=btrfs_evict_inode() begin
[ 2569.084280] comm=sync func=btrfs_commit_transaction() call btrfs_run_delayed_iputs()
[ 2569.085418] comm=sync func=btrfs_commit_transaction() done btrfs_run_delayed_iputs()
[ 2569.087554] comm=sync func=btrfs_commit_transaction() end
[ 2569.191081] comm=dd begin
[ 2569.790112] comm=dd func=__btrfs_buffered_write() ret=-28
[ 2569.847479] comm=btrfs-cleaner func=add_pinned_bytes() 0 + 32677888 = 32677888
[ 2569.849530] comm=btrfs-cleaner func=add_pinned_bytes() 32677888 + 23834624 = 56512512
...
[ 2569.903893] comm=btrfs-cleaner func=add_pinned_bytes() 943976448 + 21762048 = 965738496
[ 2569.908270] comm=btrfs-cleaner func=btrfs_evict_inode() end
Fix:
Make btrfs_commit_transaction() wait current running btrfs-cleaner's
delayed-iputs() done in end.
Test:
Use script similar to above(more complex),
before patch:
7 failed in 100 * 20 loop.
after patch:
0 failed in 100 * 20 loop.
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Near the end of close_ctree, we're calling btrfs_free_block_rsv
to free up the orphan rsv. The problem is this call updates the
space_info, which has already been freed.
This adds a new __ function that directly calls kfree instead of trying
to update the space infos.
Signed-off-by: Chris Mason <clm@fb.com>
We loop through all of the dirty block groups during commit and write
the free space cache. In order to make sure the cache is currect, we do
this while no other writers are allowed in the commit.
If a large number of block groups are dirty, this can introduce long
stalls during the final stages of the commit, which can block new procs
trying to change the filesystem.
This commit changes the block group cache writeout to take appropriate
locks and allow it to run earlier in the commit. We'll still have to
redo some of the block groups, but it means we can get most of the work
out of the way without blocking the entire FS.
Signed-off-by: Chris Mason <clm@fb.com>
Block group cache writeout is currently waiting on the pages for each
block group cache before moving on to writing the next one. This commit
switches things around to send down all the caches and then wait on them
in batches.
The end result is much faster, since we're keeping the disk pipeline
full.
Signed-off-by: Chris Mason <clm@fb.com>
We'll need to put the io_ctl into the block_group cache struct, so
name it struct btrfs_io_ctl and move it into ctree.h
Signed-off-by: Chris Mason <clm@fb.com>
When truncate starts, it allocates some space in the block reserves so
that we'll have enough to update metadata along the way.
For very large files, we can easily go through all of that space as we
loop through the extents. This changes truncate to refill the space
reservation as it progresses through the file.
Signed-off-by: Chris Mason <clm@fb.com>
Pull btrfs fixes from Chris Mason:
"Most of these are fixing extent reservation accounting, or corners
with tree writeback during commit.
Josef's set does add a test, which isn't strictly a fix, but it'll
keep us from making this same mistake again"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: fix outstanding_extents accounting in DIO
Btrfs: add sanity test for outstanding_extents accounting
Btrfs: just free dummy extent buffers
Btrfs: account merges/splits properly
Btrfs: prepare block group cache before writing
Btrfs: fix ASSERT(list_empty(&cur_trans->dirty_bgs_list)
Btrfs: account for the correct number of extents for delalloc reservations
Btrfs: fix merge delalloc logic
Btrfs: fix comp_oper to get right order
Btrfs: catch transaction abortion after waiting for it
btrfs: fix sizeof format specifier in btrfs_check_super_valid()
I introduced a regression wrt outstanding_extents accounting. These are tricky
areas that aren't easily covered by xfstests as we could change MAX_EXTENT_SIZE
at any time. So add sanity tests to cover the various conditions that are
tricky in order to make sure we don't introduce regressions in the future.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Writing the block group cache will modify the extent tree quite a bit because it
truncates the old space cache and pre-allocates new stuff. To try and cut down
on the churn lets do the setup dance first, then later on hopefully we can avoid
looping with newly dirtied roots. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Using {} as initializer for struct seq_elem does not properly initialize
the list_head member, but it currently works because it gets set through
btrfs_get_tree_mod_seq if 'seq' is 0.
Signed-off-by: David Sterba <dsterba@suse.cz>
Pull btrfs updates from Chris Mason:
"This pull is mostly cleanups and fixes:
- The raid5/6 cleanups from Zhao Lei fixup some long standing warts
in the code and add improvements on top of the scrubbing support
from 3.19.
- Josef has round one of our ENOSPC fixes coming from large btrfs
clusters here at FB.
- Dave Sterba continues a long series of cleanups (thanks Dave), and
Filipe continues hammering on corner cases in fsync and others
This all was held up a little trying to track down a use-after-free in
btrfs raid5/6. It's not clear yet if this is just made easier to
trigger with this pull or if its a new bug from the raid5/6 cleanups.
Dave Sterba is the only one to trigger it so far, but he has a
consistent way to reproduce, so we'll get it nailed shortly"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (68 commits)
Btrfs: don't remove extents and xattrs when logging new names
Btrfs: fix fsync data loss after adding hard link to inode
Btrfs: fix BUG_ON in btrfs_orphan_add() when delete unused block group
Btrfs: account for large extents with enospc
Btrfs: don't set and clear delalloc for O_DIRECT writes
Btrfs: only adjust outstanding_extents when we do a short write
btrfs: Fix out-of-space bug
Btrfs: scrub, fix sleep in atomic context
Btrfs: fix scheduler warning when syncing log
Btrfs: Remove unnecessary placeholder in btrfs_err_code
btrfs: cleanup init for list in free-space-cache
btrfs: delete chunk allocation attemp when setting block group ro
btrfs: clear bio reference after submit_one_bio()
Btrfs: fix scrub race leading to use-after-free
Btrfs: add missing cleanup on sysfs init failure
Btrfs: fix race between transaction commit and empty block group removal
btrfs: add more checks to btrfs_read_sys_array
btrfs: cleanup, rename a few variables in btrfs_read_sys_array
btrfs: add checks for sys_chunk_array sizes
btrfs: more superblock checks, lower bounds on devices and sectorsize/nodesize
...
This patch is part of a larger project to cleanup btrfs's internal usage
of struct btrfs_root. Many functions take btrfs_root only to grab a
pointer to fs_info.
This causes programmers to ponder which root can be passed. Since only
the fs_info is read affected functions can accept any root, except this
is only obvious upon inspection.
This patch reduces the specificty of such functions to accept the
fs_info directly.
This patch does not address the two functions in ctree.c (insert_ptr,
and split_item) which only use root for BUG_ONs in ctree.c
This patch affects the following functions:
1) fixup_low_keys
2) btrfs_set_item_key_safe
Signed-off-by: Daniel Dressler <danieru.dressler@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.cz>
On our gluster boxes we stream large tar balls of backups onto our fses. With
160gb of ram this means we get really large contiguous ranges of dirty data, but
the way our ENOSPC stuff works is that as long as it's contiguous we only hold
metadata reservation for one extent. The problem is we limit our extents to
128mb, so we'll end up with at least 800 extents so our enospc accounting is
quite a bit lower than what we need. To keep track of this make sure we
increase outstanding_extents for every multiple of the max extent size so we can
be sure to have enough reserved metadata space. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
There isn't any real use of following members of struct btrfs_root
so delete them.
struct kobject root_kobj;
struct completion kobj_unregister;
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
So we can check raid56 with:
(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
instead of long:
(map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Currently any time we try to update the block groups on disk we will walk _all_
block groups and check for the ->dirty flag to see if it is set. This function
can get called several times during a commit. So if you have several terabytes
of data you will be a very sad panda as we will loop through _all_ of the block
groups several times, which makes the commit take a while which slows down the
rest of the file system operations.
This patch introduces a dirty list for the block groups that we get added to
when we dirty the block group for the first time. Then we simply update any
block groups that have been dirtied since the last time we called
btrfs_write_dirty_block_groups. This allows us to clean up how we write the
free space cache out so it is much cleaner. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
I've been overloading root->dirty_list to keep track of dirty roots and which
roots need to have their commit roots switched at transaction commit time. This
could cause us to lose an update to the root which could corrupt the file
system. To fix this use a state bit to know if the root is dirty, and if it
isn't set we go ahead and move the root to the dirty list. This way if we
re-dirty the root after adding it to the switch_commit list we make sure to
update it. This also makes it so that the extent root is always the last root
on the dirty list to try and keep the amount of churn down at this point in the
commit. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
When removing a block group we were deleting it from its space_info's
ro_bgs list without the correct protection - the space info's spinlock.
Fix this by doing the list delete while holding the spinlock of the
corresponding space info, which is the correct lock for any operation
on that list.
This issue was introduced in the 3.19 kernel by the following change:
Btrfs: move read only block groups onto their own list V2
commit 633c0aad4c
I ran into a kernel crash while a task was running statfs, which iterates
the space_info->ro_bgs list while holding the space info's spinlock,
and another task was deleting it from the same list, without holding that
spinlock, as part of the block group remove operation (while running the
function btrfs_remove_block_group). This happened often when running the
stress test xfstests/generic/038 I recently made.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
It doesn't do anything special, it just calls btrfs_discard_extent(),
so just remove it.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Our fs trim operation, which is completely transactionless (doesn't start
or joins an existing transaction) consists of visiting all block groups
and then for each one to iterate its free space entries and perform a
discard operation against the space range represented by the free space
entries. However before performing a discard, the corresponding free space
entry is removed from the free space rbtree, and when the discard completes
it is added back to the free space rbtree.
If a block group remove operation happens while the discard is ongoing (or
before it starts and after a free space entry is hidden), we end up not
waiting for the discard to complete, remove the extent map that maps
logical address to physical addresses and the corresponding chunk metadata
from the the chunk and device trees. After that and before the discard
completes, the current running transaction can finish and a new one start,
allowing for new block groups that map to the same physical addresses to
be allocated and written to.
So fix this by keeping the extent map in memory until the discard completes
so that the same physical addresses aren't reused before it completes.
If the physical locations that are under a discard operation end up being
used for a new metadata block group for example, and dirty metadata extents
are written before the discard finishes (the VM might call writepages() of
our btree inode's i_mapping for example, or an fsync log commit happens) we
end up overwriting metadata with zeroes, which leads to errors from fsck
like the following:
checking extents
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
read block failed check_tree_block
owner ref check failed [833912832 16384]
Errors found in extent allocation tree or chunk allocation
checking free space cache
checking fs roots
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
Check tree block failed, want=833912832, have=0
read block failed check_tree_block
root 5 root dir 256 error
root 5 inode 260 errors 2001, no inode item, link count wrong
unresolved ref dir 256 index 0 namelen 8 name foobar_3 filetype 1 errors 6, no dir index, no inode ref
root 5 inode 262 errors 2001, no inode item, link count wrong
unresolved ref dir 256 index 0 namelen 8 name foobar_5 filetype 1 errors 6, no dir index, no inode ref
root 5 inode 263 errors 2001, no inode item, link count wrong
(...)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
The commit c404e0dc (Btrfs: fix use-after-free in the finishing
procedure of the device replace) fixed a use-after-free problem
which happened when removing the source device at the end of device
replace, but at that time, btrfs didn't support device replace
on raid56, so we didn't fix the problem on the raid56 profile.
Currently, we implemented device replace for raid56, so we need
kick that problem out before we enable that function for raid56.
The fix method is very simple, we just increase the bio per-cpu
counter before we submit a raid56 io, and decrease the counter
when the raid56 io ends.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
If right after starting the snapshot creation ioctl we perform a write against a
file followed by a truncate, with both operations increasing the file's size, we
can get a snapshot tree that reflects a state of the source subvolume's tree where
the file truncation happened but the write operation didn't. This leaves a gap
between 2 file extent items of the inode, which makes btrfs' fsck complain about it.
For example, if we perform the following file operations:
$ mkfs.btrfs -f /dev/vdd
$ mount /dev/vdd /mnt
$ xfs_io -f \
-c "pwrite -S 0xaa -b 32K 0 32K" \
-c "fsync" \
-c "pwrite -S 0xbb -b 32770 16K 32770" \
-c "truncate 90123" \
/mnt/foobar
and the snapshot creation ioctl was just called before the second write, we often
can get the following inode items in the snapshot's btree:
item 120 key (257 INODE_ITEM 0) itemoff 7987 itemsize 160
inode generation 146 transid 7 size 90123 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 flags 0x0
item 121 key (257 INODE_REF 256) itemoff 7967 itemsize 20
inode ref index 282 namelen 10 name: foobar
item 122 key (257 EXTENT_DATA 0) itemoff 7914 itemsize 53
extent data disk byte 1104855040 nr 32768
extent data offset 0 nr 32768 ram 32768
extent compression 0
item 123 key (257 EXTENT_DATA 53248) itemoff 7861 itemsize 53
extent data disk byte 0 nr 0
extent data offset 0 nr 40960 ram 40960
extent compression 0
There's a file range, corresponding to the interval [32K; ALIGN(16K + 32770, 4096)[
for which there's no file extent item covering it. This is because the file write
and file truncate operations happened both right after the snapshot creation ioctl
called btrfs_start_delalloc_inodes(), which means we didn't start and wait for the
ordered extent that matches the write and, in btrfs_setsize(), we were able to call
btrfs_cont_expand() before being able to commit the current transaction in the
snapshot creation ioctl. So this made it possibe to insert the hole file extent
item in the source subvolume (which represents the region added by the truncate)
right before the transaction commit from the snapshot creation ioctl.
Btrfs' fsck tool complains about such cases with a message like the following:
"root 331 inode 257 errors 100, file extent discount"
>From a user perspective, the expectation when a snapshot is created while those
file operations are being performed is that the snapshot will have a file that
either:
1) is empty
2) only the first write was captured
3) only the 2 writes were captured
4) both writes and the truncation were captured
But never capture a state where only the first write and the truncation were
captured (since the second write was performed before the truncation).
A test case for xfstests follows.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
When doing a fsync with a fast path we have a time window where we can miss
the fact that writeback of some file data failed, and therefore we endup
returning success (0) from fsync when we should return an error.
The steps that lead to this are the following:
1) We start all ordered extents by calling filemap_fdatawrite_range();
2) We do some other work like locking the inode's i_mutex, start a transaction,
start a log transaction, etc;
3) We enter btrfs_log_inode(), acquire the inode's log_mutex and collect all the
ordered extents from inode's ordered tree into a list;
4) But by the time we do ordered extent collection, some ordered extents we started
at step 1) might have already completed with an error, and therefore we didn't
found them in the ordered tree and had no idea they finished with an error. This
makes our fsync return success (0) to userspace, but has no bad effects on the log
like for example insertion of file extent items into the log that point to unwritten
extents, because the invalid extent maps were removed before the ordered extent
completed (in inode.c:btrfs_finish_ordered_io).
So after collecting the ordered extents just check if the inode's i_mapping has any
error flags set (AS_EIO or AS_ENOSPC) and leave with an error if it does. Whenever
writeback fails for a page of an ordered extent, we call mapping_set_error (done in
extent_io.c:end_extent_writepage, called by extent_io.c:end_bio_extent_writepage)
that sets one of those error flags in the inode's i_mapping flags.
This change also has the side effect of fixing the issue where for fast fsyncs we
never checked/cleared the error flags from the inode's i_mapping flags, which means
that a full fsync performed after a fast fsync could get such errors that belonged
to the fast fsync - because the full fsync calls btrfs_wait_ordered_range() which
calls filemap_fdatawait_range(), and the later checks for and clears those flags,
while for fast fsyncs we never call filemap_fdatawait_range() or anything else
that checks for and clears the error flags from the inode's i_mapping.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Replacing a xattr consists of doing a lookup for its existing value, delete
the current value from the respective leaf, release the search path and then
finally insert the new value. This leaves a time window where readers (getxattr,
listxattrs) won't see any value for the xattr. Xattrs are used to store ACLs,
so this has security implications.
This change also fixes 2 other existing issues which were:
*) Deleting the old xattr value without verifying first if the new xattr will
fit in the existing leaf item (in case multiple xattrs are packed in the
same item due to name hash collision);
*) Returning -EEXIST when the flag XATTR_CREATE is given and the xattr doesn't
exist but we have have an existing item that packs muliple xattrs with
the same name hash as the input xattr. In this case we should return ENOSPC.
A test case for xfstests follows soon.
Thanks to Alexandre Oliva for reporting the non-atomicity of the xattr replace
implementation.
Reported-by: Alexandre Oliva <oliva@gnu.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Our gluster boxes were spending lots of time in statfs because our fs'es are
huge. The problem is statfs loops through all of the block groups looking for
read only block groups, and when you have several terabytes worth of data that
ends up being a lot of block groups. Move the read only block groups onto a
read only list and only proces that list in
btrfs_account_ro_block_groups_free_space to reduce the amount of churn. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
To avoid duplicating this double filemap_fdatawrite_range() call for
inodes with async extents (compressed writes) so often.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
In some contexts, like in sysfs handlers, we don't want to trigger a
transaction commit. It's a heavy operation, we don't know what external
locks may be taken. Instead, make it possible to finish the operation
through sync syscall or SYNC_FS ioctl.
Signed-off-by: David Sterba <dsterba@suse.cz>
The pending mount option(s) now share namespace and bits with the normal
options, and the existing one for (inode_cache) is unset unconditionally
at each transaction commit.
Introduce a separate namespace for pending changes and enhance the
descriptions of the intended change to use separate bits for each
action.
Signed-off-by: David Sterba <dsterba@suse.cz>
There are some actions that modify global filesystem state but cannot be
performed at the time of request, but later at the transaction commit
time when the filesystem is in a known state.
For example enabling new incompat features on-the-fly or issuing
transaction commit from unsafe contexts (sysfs handlers).
Signed-off-by: David Sterba <dsterba@suse.cz>
If we couldn't find our extent item, we accessed the current slot
(path->slots[0]) to check if it corresponds to an equivalent skinny
metadata item. However this slot could be beyond our last item in the
leaf (i.e. path->slots[0] >= btrfs_header_nritems(leaf)), in which case
we shouldn't process it.
Since btrfs_lookup_extent() is only used to find extent items for data
extents, fix this by removing completely the logic that looks up for an
equivalent skinny metadata item, since it can not exist.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Chris Mason