Add hook in add_delayed_ref_head() to record quota-related extent record
into delayed_ref_root->dirty_extent_record rb-tree for later qgroup
accounting.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Add function qgroup_update_counters(), which will update related
qgroups' rfer/excl according to old/new_roots.
This is one of the two core functions for the new qgroup implement.
This is based on btrfs_adjust_coutners() but with clearer logic and
comment.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
This function is used to update refcnt for qgroups.
And is one of the two core functions used in the new qgroup implement.
This is based on the old update_old/new_refcnt, but provides a unified
logic and behavior.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
__btrfs_inc_extent_ref() and __btrfs_free_extent() have already had too
many parameters, but three of them can be extracted from
btrfs_delayed_ref_node struct.
So use btrfs_delayed_ref_node struct as a single parameter to replace
the bytenr/num_byte/no_quota parameters.
The real objective of this patch is to allow btrfs_qgroup_record_ref()
get the delayed_ref_node in incoming qgroup patches.
Other functions calling btrfs_qgroup_record_ref() are not affected since
the rest will only add/sub exclusive extents, where node is not used.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Use inline functions to do such things, to improve readability.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Acked-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Cleanup the rb_tree merge/insert/update functions, since now we use list
instead of rb_tree now.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
This patch replace the rbtree used in ref_head to list.
This has the following advantage:
1) Easier merge logic.
With the new list implement, we only need to care merging the tail
ref_node with the new ref_node.
And this can be done quite easy at insert time, no need to do a
indicated merge at run_delayed_refs().
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Old __merge_refs() in backref.c will even merge refs whose root_id are
different, which makes qgroup gives wrong result.
Fix it by checking ref_for_same_block() before any mode specific works.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
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>
The extent-same code rejects requests with an unaligned length. This
poses a problem when we want to dedupe the tail extent of files as we
skip cloning the portion between i_size and the extent boundary.
If we don't clone the entire extent, it won't be deleted. So the
combination of these behaviors winds up giving us worst-case dedupe on
many files.
We can fix this by allowing a length that extents to i_size and
internally aligining those to the end of the block. This is what
btrfs_ioctl_clone() so we can just copy that check over.
Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Signed-off-by: Chris Mason <clm@fb.com>
max_to_defrag represents the number of pages to defrag rather than the last
page of the file range to be defragged.
Consider a file having 10 4k blocks (i.e. blocks in the range [0 - 9]). If the
defrag ioctl was invoked for the block range [3 - 6], then max_to_defrag
should actually have the value 4. Instead in the current code we end up
setting it to 6.
Now, this does not (yet) cause an issue since the first part of the while loop
condition in btrfs_defrag_file() (i.e. "i <= last_index") causes the control
to flow out of the while loop before any buggy behavior is actually caused. So
the patch just makes sure that max_to_defrag ends up having the right value
rather than fixing a bug. I did run the xfstests suite to make sure that the
code does not regress.
Changelog: v1->v2:
Provide a much descriptive commit message.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Signed-off-by: Chris Mason <clm@fb.com>
Read-ahead is done for the pages in the range [ra_index, ra_index + cluster -
1]. So the next read-ahead should be starting from the page at index 'ra_index
+ cluster' (unless we deemed that the extent at 'ra_index + cluster' as
non-defraggable) rather than from the page at index 'ra_index +
max_cluster'. This patch fixes this. I did run the xfstests suite to make sure
that the code does not regress.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.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>
We don't need to attach ordered extents that have completed to the current
transaction. Doing so only makes us hold memory for longer than necessary
and delaying the iput of the inode until the transaction is committed (for
each created ordered extent we do an igrab and then schedule an asynchronous
iput when the ordered extent's reference count drops to 0), preventing the
inode from being evictable until the transaction commits.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Commit 3a8b36f378 ("Btrfs: fix data loss in the fast fsync path") added
a performance regression for that causes an unnecessary sync of the log
trees (fs/subvol and root log trees) when 2 consecutive fsyncs are done
against a file, without no writes or any metadata updates to the inode in
between them and if a transaction is committed before the second fsync is
called.
Huang Ying reported this to lkml (https://lkml.org/lkml/2015/3/18/99)
after a test sysbench test that measured a -62% decrease of file io
requests per second for that tests' workload.
The test is:
echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor
echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor
echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor
mkfs -t btrfs /dev/sda2
mount -t btrfs /dev/sda2 /fs/sda2
cd /fs/sda2
for ((i = 0; i < 1024; i++)); do fallocate -l 67108864 testfile.$i; done
sysbench --test=fileio --max-requests=0 --num-threads=4 --max-time=600 \
--file-test-mode=rndwr --file-total-size=68719476736 --file-io-mode=sync \
--file-num=1024 run
A test on kvm guest, running a debug kernel gave me the following results:
Without 3a8b36f378060d: 16.01 reqs/sec
With 3a8b36f378060d: 3.39 reqs/sec
With 3a8b36f378 and this patch: 16.04 reqs/sec
Reported-by: Huang Ying <ying.huang@intel.com>
Tested-by: Huang, Ying <ying.huang@intel.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Zygo Blaxell and other users have reported occasional hangs while an
inode is being evicted, leading to traces like the following:
[ 5281.972322] INFO: task rm:20488 blocked for more than 120 seconds.
[ 5281.973836] Not tainted 4.0.0-rc5-btrfs-next-9+ #2
[ 5281.974818] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 5281.976364] rm D ffff8800724cfc38 0 20488 7747 0x00000000
[ 5281.977506] ffff8800724cfc38 ffff8800724cfc38 ffff880065da5c50 0000000000000001
[ 5281.978461] ffff8800724cffd8 ffff8801540a5f50 0000000000000008 ffff8801540a5f78
[ 5281.979541] ffff8801540a5f50 ffff8800724cfc58 ffffffff8143107e 0000000000000123
[ 5281.981396] Call Trace:
[ 5281.982066] [<ffffffff8143107e>] schedule+0x74/0x83
[ 5281.983341] [<ffffffffa03b33cf>] wait_on_state+0xac/0xcd [btrfs]
[ 5281.985127] [<ffffffff81075cd6>] ? signal_pending_state+0x31/0x31
[ 5281.986715] [<ffffffffa03b4b71>] wait_extent_bit.constprop.32+0x7c/0xde [btrfs]
[ 5281.988680] [<ffffffffa03b540b>] lock_extent_bits+0x5d/0x88 [btrfs]
[ 5281.990200] [<ffffffffa03a621d>] btrfs_evict_inode+0x24e/0x5be [btrfs]
[ 5281.991781] [<ffffffff8116964d>] evict+0xa0/0x148
[ 5281.992735] [<ffffffff8116a43d>] iput+0x18f/0x1e5
[ 5281.993796] [<ffffffff81160d4a>] do_unlinkat+0x15b/0x1fa
[ 5281.994806] [<ffffffff81435b54>] ? ret_from_sys_call+0x1d/0x58
[ 5281.996120] [<ffffffff8107d314>] ? trace_hardirqs_on_caller+0x18f/0x1ab
[ 5281.997562] [<ffffffff8123960b>] ? trace_hardirqs_on_thunk+0x3a/0x3f
[ 5281.998815] [<ffffffff81161a16>] SyS_unlinkat+0x29/0x2b
[ 5281.999920] [<ffffffff81435b32>] system_call_fastpath+0x12/0x17
[ 5282.001299] 1 lock held by rm/20488:
[ 5282.002066] #0: (sb_writers#12){.+.+.+}, at: [<ffffffff8116dd81>] mnt_want_write+0x24/0x4b
This happens when we have readahead, which calls readpages(), happening
right before the inode eviction handler is invoked. So the reason is
essentially:
1) readpages() is called while a reference on the inode is held, so
eviction can not be triggered before readpages() returns. It also
locks one or more ranges in the inode's io_tree (which is done at
extent_io.c:__do_contiguous_readpages());
2) readpages() submits several read bios, all with an end io callback
that runs extent_io.c:end_bio_extent_readpage() and that is executed
by other task when a bio finishes, corresponding to a work queue
(fs_info->end_io_workers) worker kthread. This callback unlocks
the ranges in the inode's io_tree that were previously locked in
step 1;
3) readpages() returns, the reference on the inode is dropped;
4) One or more of the read bios previously submitted are still not
complete (their end io callback was not yet invoked or has not
yet finished execution);
5) Inode eviction is triggered (through an unlink call for example).
The inode reference count was not incremented before submitting
the read bios, therefore this is possible;
6) The eviction handler starts executing and enters the loop that
iterates over all extent states in the inode's io_tree;
7) The loop picks one extent state record and uses its ->start and
->end fields, after releasing the inode's io_tree spinlock, to
call lock_extent_bits() and clear_extent_bit(). The call to lock
the range [state->start, state->end] blocks because the whole
range or a part of it was locked by the previous call to
readpages() and the corresponding end io callback, which unlocks
the range was not yet executed;
8) The end io callback for the read bio is executed and unlocks the
range [state->start, state->end] (or a superset of that range).
And at clear_extent_bit() the extent_state record state is used
as a second argument to split_state(), which sets state->start to
a larger value;
9) The task executing the eviction handler is woken up by the task
executing the bio's end io callback (through clear_state_bit) and
the eviction handler locks the range
[old value for state->start, state->end]. Shortly after, when
calling clear_extent_bit(), it unlocks the range
[new value for state->start, state->end], so it ends up unlocking
only part of the range that it locked, leaving an extent state
record in the io_tree that represents the unlocked subrange;
10) The eviction handler loop, in its next iteration, gets the
extent_state record for the subrange that it did not unlock in the
previous step and then tries to lock it, resulting in an hang.
So fix this by not using the ->start and ->end fields of an existing
extent_state record. This is a simple solution, and an alternative
could be to bump the inode's reference count before submitting each
read bio and having it dropped in the bio's end io callback. But that
would be a more invasive/complex change and would not protect against
other possible places that are not holding a reference on the inode
as well. Something to consider in the future.
Many thanks to Zygo Blaxell for reporting, in the mailing list, the
issue, a set of scripts to trigger it and testing this fix.
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Tested-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
The return value of read_tree_block() can confuse callers as it always
returns NULL for either -ENOMEM or -EIO, so it's likely that callers
parse it to a wrong error, for instance, in btrfs_read_tree_root().
This fixes the above issue.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
read_tree_block may take a reference on the 'eb', a following
free_extent_buffer is necessary.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
After commit 8407f55326
("Btrfs: fix data corruption after fast fsync and writeback error"),
during wait_ordered_extents(), we wait for ordered extent setting
BTRFS_ORDERED_IO_DONE or BTRFS_ORDERED_IOERR, at which point we've
already got checksum information, so we don't need to check
(csum_bytes_left == 0) in the whole logging path.
Signed-off-by: Liu Bo <bo.li.liu@oracle.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>
Now that we're guaranteed to have a meaningful root dentry, we can just
export seq_dentry() and use it in btrfs_show_options(). The subvolume ID
is easy to get and can also be useful, so put that in there, too.
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
Currently, mounting a subvolume with subvolid= takes a different code
path than mounting with subvol=. This isn't really a big deal except for
the fact that mounts done with subvolid= or the default subvolume don't
have a dentry that's connected to the dentry tree like in the subvol=
case. To unify the code paths, when given subvolid= or using the default
subvolume ID, translate it into a subvolume name by walking
ROOT_BACKREFs in the root tree and INODE_REFs in the filesystem trees.
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
There's nothing to stop a user from passing both subvol= and subvolid=
to mount, but if they don't refer to the same subvolume, someone is
going to be surprised at some point. Error out on this case, but allow
users to pass in both if they do match (which they could, for example,
get out of /proc/mounts).
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
In preparation for new functionality in mount_subvol(), give it
ownership of subvol_name and tidy up the error paths.
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
Currently, setup_root_args() substitutes 's/subvol=[^,]*/subvolid=0/'.
But, this means that if the user passes both a subvol and subvolid for
some reason, we won't actually mount the top-level when we recursively
mount. For example, consider:
mkfs.btrfs -f /dev/sdb
mount /dev/sdb /mnt
btrfs subvol create /mnt/subvol1 # subvolid=257
btrfs subvol create /mnt/subvol2 # subvolid=258
umount /mnt
mount -osubvol=/subvol1,subvolid=258 /dev/sdb /mnt
In the final mount, subvol=/subvol1,subvolid=258 becomes
subvolid=0,subvolid=258, and the last option takes precedence, so we
mount subvol2 and try to look up subvol1 inside of it, which fails.
So, instead, do a thorough scan through the argument list and remove any
subvol= and subvolid= options, then append subvolid=0 to the end. This
implicitly makes subvol= take precedence over subvolid=, but we're about
to add a stricter check for that. This also makes setup_root_args() more
generic, which we'll need soon.
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
Since commit 0723a0473f ("btrfs: allow mounting btrfs subvolumes with
different ro/rw options"), when mounting a subvolume read/write when
another subvolume has previously been mounted read-only, we first do a
remount. However, this should be done with the superblock locked, as per
sync_filesystem():
/*
* We need to be protected against the filesystem going from
* r/o to r/w or vice versa.
*/
WARN_ON(!rwsem_is_locked(&sb->s_umount));
This WARN_ON can easily be hit with:
mkfs.btrfs -f /dev/vdb
mount /dev/vdb /mnt
btrfs subvol create /mnt/vol1
btrfs subvol create /mnt/vol2
umount /mnt
mount -oro,subvol=/vol1 /dev/vdb /mnt
mount -orw,subvol=/vol2 /dev/vdb /mnt2
Fixes: 0723a0473f ("btrfs: allow mounting btrfs subvolumes with different ro/rw options")
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
When we clear an extent state's EXTENT_LOCKED bit with clear_extent_bits()
through free_io_failure(), we weren't waking up any tasks waiting for the
extent's state EXTENT_LOCKED bit, leading to an hang.
So make sure clear_extent_bits() ends up waking up any waiters if the
bit EXTENT_LOCKED is supplied by its callers.
Zygo Blaxell was experiencing such hangs at inode eviction time after
file unlinks. Thanks to him for a set of scripts to reproduce the issue.
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
With commit 1b98450816 ("Btrfs: fix find_free_dev_extent() malfunction
in case device tree has hole") introduced in the kernel 4.1 merge window,
we end up using part of a device hole for which there are already pending
chunks or pinned chunks. Before that commit we didn't use the hole and
would just move on to the next hole in the device.
However when we adjust the start offset for the chunk allocation and we
have pinned chunks, we set it blindly to the end offset of the pinned
chunk we are currently processing, which is dangerous because we can
have a pending chunk that has a start offset that matches the end offset
of our pinned chunk - leading us to a case where we end up getting two
pending chunks that start at the same physical device offset, which makes
us later abort the current transaction with -EEXIST when finishing the
chunk allocation at btrfs_create_pending_block_groups():
[194737.659017] ------------[ cut here ]------------
[194737.660192] WARNING: CPU: 15 PID: 31111 at fs/btrfs/super.c:260 __btrfs_abort_transaction+0x52/0x106 [btrfs]()
[194737.662209] BTRFS: Transaction aborted (error -17)
[194737.663175] Modules linked in: btrfs dm_snapshot dm_bufio dm_flakey dm_mod crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse
[194737.674015] CPU: 15 PID: 31111 Comm: xfs_io Tainted: G W 4.0.0-rc5-btrfs-next-9+ #2
[194737.675986] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[194737.682999] 0000000000000009 ffff8800564c7a98 ffffffff8142fa46 ffffffff8108b6a2
[194737.684540] ffff8800564c7ae8 ffff8800564c7ad8 ffffffff81045ea5 ffff8800564c7b78
[194737.686017] ffffffffa0383aa7 00000000ffffffef ffff88000c7ba000 ffff8801a1f66f40
[194737.687509] Call Trace:
[194737.688068] [<ffffffff8142fa46>] dump_stack+0x4f/0x7b
[194737.689027] [<ffffffff8108b6a2>] ? console_unlock+0x361/0x3ad
[194737.690095] [<ffffffff81045ea5>] warn_slowpath_common+0xa1/0xbb
[194737.691198] [<ffffffffa0383aa7>] ? __btrfs_abort_transaction+0x52/0x106 [btrfs]
[194737.693789] [<ffffffff81045f05>] warn_slowpath_fmt+0x46/0x48
[194737.695065] [<ffffffffa0383aa7>] __btrfs_abort_transaction+0x52/0x106 [btrfs]
[194737.696806] [<ffffffffa039a3bd>] btrfs_create_pending_block_groups+0x101/0x130 [btrfs]
[194737.698683] [<ffffffffa03aa433>] __btrfs_end_transaction+0x84/0x366 [btrfs]
[194737.700329] [<ffffffffa03aa725>] btrfs_end_transaction+0x10/0x12 [btrfs]
[194737.701924] [<ffffffffa0394b51>] btrfs_check_data_free_space+0x11f/0x27c [btrfs]
[194737.703675] [<ffffffffa03b8ba4>] __btrfs_buffered_write+0x16a/0x4c8 [btrfs]
[194737.705417] [<ffffffffa03bb502>] ? btrfs_file_write_iter+0x19a/0x431 [btrfs]
[194737.707058] [<ffffffffa03bb511>] ? btrfs_file_write_iter+0x1a9/0x431 [btrfs]
[194737.708560] [<ffffffffa03bb68d>] btrfs_file_write_iter+0x325/0x431 [btrfs]
[194737.710673] [<ffffffff81067d85>] ? get_parent_ip+0xe/0x3e
[194737.712076] [<ffffffff811534c3>] new_sync_write+0x7c/0xa0
[194737.713293] [<ffffffff81153b58>] vfs_write+0xb2/0x117
[194737.714443] [<ffffffff81154424>] SyS_pwrite64+0x64/0x82
[194737.715646] [<ffffffff81435b32>] system_call_fastpath+0x12/0x17
[194737.717175] ---[ end trace f2d5dc04e56d7e48 ]---
[194737.718170] BTRFS: error (device sdc) in btrfs_create_pending_block_groups:9524: errno=-17 Object already exists
The -EEXIST failure comes from btrfs_finish_chunk_alloc(), called by
btrfs_create_pending_block_groups(), when it attempts to insert a
duplicated device extent item via btrfs_alloc_dev_extent().
This issue was reproducible with fstests generic/038 running in a loop for
several hours (it's very hard to hit) and using MOUNT_OPTIONS="-o discard".
Applying Jeff's recent patch titled "btrfs: add missing discards when
unpinning extents with -o discard" makes the issue much easier to reproduce
(usually within 4 to 5 hours), since it pins chunks for longer periods of
time when an unused block group is deleted by the cleaner kthread.
Fix this by making sure that we never adjust the start offset to a lower
value than it currently has.
Fixes: 1b98450816 ("Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole"
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
__btrfs_close_devices() would call_rcu to free the device, which is racy with
list_for_each_entry() accessing the memory to retrieve the next device on the
list.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
The INO_LOOKUP ioctl can lookup path for a given inode number and is
thus restricted. As a sideefect it can find the root id of the
containing subvolume and we're using this int the 'btrfs inspect rootid'
command.
The restriction is unnecessary in case we set the ioctl args
args::treeid = 0
args::objectid = 256 (BTRFS_FIRST_FREE_OBJECTID)
Then the path will be empty and the treeid is filled with the root id of
the inode on which the ioctl is called. This behaviour is unchanged,
after the root restriction is removed.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Report missing device when add is successful,
otherwise it would exit as ENOMEM. And add uuid
to the report.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
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>
Marc reported a problem where the receiving end of an incremental send
was performing clone operations that failed with -EINVAL. This happened
because, unlike for uncompressed extents, we were not checking if the
source clone offset and length, after summing the data offset, falls
within the source file's boundaries.
So make sure we do such checks when attempting to issue clone operations
for compressed extents.
Problem reproducible with the following steps:
$ mkfs.btrfs -f /dev/sdb
$ mount -o compress /dev/sdb /mnt
$ mkfs.btrfs -f /dev/sdc
$ mount -o compress /dev/sdc /mnt2
# Create the file with a single extent of 128K. This creates a metadata file
# extent item with a data start offset of 0 and a logical length of 128K.
$ xfs_io -f -c "pwrite -S 0xaa 64K 128K" -c "fsync" /mnt/foo
# Now rewrite the range 64K to 112K of our file. This will make the inode's
# metadata continue to point to the 128K extent we created before, but now
# with an extent item that points to the extent with a data start offset of
# 112K and a logical length of 16K.
# That metadata file extent item is associated with the logical file offset
# at 176K and covers the logical file range 176K to 192K.
$ xfs_io -c "pwrite -S 0xbb 64K 112K" -c "fsync" /mnt/foo
# Now rewrite the range 180K to 12K. This will make the inode's metadata
# continue to point the the 128K extent we created earlier, with a single
# extent item that points to it with a start offset of 112K and a logical
# length of 4K.
# That metadata file extent item is associated with the logical file offset
# at 176K and covers the logical file range 176K to 180K.
$ xfs_io -c "pwrite -S 0xcc 180K 12K" -c "fsync" /mnt/foo
$ btrfs subvolume snapshot -r /mnt /mnt/snap1
$ touch /mnt/bar
# Calls the btrfs clone ioctl.
$ ~/xfstests/src/cloner -s $((176 * 1024)) -d $((176 * 1024)) \
-l $((4 * 1024)) /mnt/foo /mnt/bar
$ btrfs subvolume snapshot -r /mnt /mnt/snap2
$ btrfs send /mnt/snap1 | btrfs receive /mnt2
At subvol /mnt/snap1
At subvol snap1
$ btrfs send -p /mnt/snap1 /mnt/snap2 | btrfs receive /mnt2
At subvol /mnt/snap2
At snapshot snap2
ERROR: failed to clone extents to bar
Invalid argument
A test case for fstests follows soon.
Reported-by: Marc MERLIN <marc@merlins.org>
Tested-by: Marc MERLIN <marc@merlins.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Tested-by: David Sterba <dsterba@suse.cz>
Tested-by: Jan Alexander Steffens (heftig) <jan.steffens@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
Commit 9c8b35b1ba ("btrfs: quota: Automatically update related qgroups or
mark INCONSISTENT flags when assigning/deleting a qgroup relations.")
introduced the allocation of a temporary ulist in function
btrfs_add_qgroup_relation() and added the corresponding cleanup to the out
path. However, the allocation was introduced before the src/dst level check
that directly returns. Fix the possible leakage of the ulist by moving the
allocation after the input validation. Detected by Coverity CID 1295988.
Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
If the call to btrfs_truncate_inode_items() failed and we don't have a block
group, we were unlocking the cache_write_mutex without having locked it (we
do it only if we have a block group).
Fixes: 1bbc621ef2 ("Btrfs: allow block group cache writeout
outside critical section in commit")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
fs/btrfs/volumes.c: In function ‘btrfs_create_uuid_tree’:
fs/btrfs/volumes.c:3909:3: warning: format ‘%d’ expects argument of type ‘int’, but argument 4 has type ‘long int’ [-Wformat=]
btrfs_abort_transaction(trans, tree_root,
^
CC [M] fs/btrfs/ioctl.o
fs/btrfs/ioctl.c: In function ‘create_subvol’:
fs/btrfs/ioctl.c:549:3: warning: format ‘%d’ expects argument of type ‘int’, but argument 4 has type ‘long int’ [-Wformat=]
btrfs_abort_transaction(trans, root, PTR_ERR(new_root));
PTR_ERR returns long, but we're really using 'int' for the error codes
everywhere so just set and use the local variable.
Signed-off-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>
Long time ago (2008) the defrag was automatic for new b-tree writes but
has been disabled after performance problems. There was a leftover in
tree-defrag.c that effectively stops any defragmentation on b-trees.
This is a bit unexpected and IMHO undesired. The SSD mode is an
optimization and defrag is supposed to work if the users asks for it.
Related commits:
6702ed490c
Btrfs: Add run time btree defrag, and an ioctl to force btree defrag
e18e4809b1
Btrfs: Add mount -o ssd, which includes optimizations for seek free
storage
b3236e68bf
Btrfs: Leave on the tree defragger in mount -o ssd, it still helps there
9afbb0b752
Btrfs: Disable tree defrag in SSD mode
The last three commits switch the defrag+ssd off/on/off and the last one
3f157a2fd2
Btrfs: Online btree defragmentation fixes
misses the bits from tree-defrag.c to revert to the behaviour introduced
in e18e4809b1.
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
When we shrink the usable size of a device (its total_bytes), we go over
all the device extent items in the device tree and attempt to relocate
the chunk of any device extent that goes beyond the new usable size for
the device. We do that after setting the new usable size (total_bytes) in
the device object, so that all new allocations (and reallocations) don't
use areas of the device that go beyond the new (shorter) size. However we
were not considering that before setting the new size in the device,
pending chunks might have been created that use device extents that go
beyond the new size, and those device extents are not yet in the device
tree after we search the device tree - they are still attached to the
list of new block group for some ongoing transaction handle, and they are
only added to the device tree when the transaction handle is ended (via
btrfs_create_pending_block_groups()).
So check for pending chunks with device extents that go beyond the new
size and if any exists, commit the current transaction and repeat the
search in the device tree.
Not doing this it would mean we would return success to user space while
still having extents that go beyond the new size, and later user space
could override those locations on the device while the fs still references
them, causing all sorts of corruption and unexpected events.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Since commit bafc9b754f ("vfs: More precise tests in d_invalidate"),
mounted subvolumes can be deleted because d_invalidate() won't fail.
However, we run into problems when we attempt to delete the default
subvolume while it is mounted as the root filesystem:
# btrfs subvol list /
ID 257 gen 306 top level 5 path rootvol
ID 267 gen 334 top level 5 path snap1
# btrfs subvol get-default /
ID 267 gen 334 top level 5 path snap1
# btrfs inspect-internal rootid /
267
# mount -o subvol=/ /dev/vda1 /mnt
# btrfs subvol del /mnt/snap1
Delete subvolume (no-commit): '/mnt/snap1'
ERROR: cannot delete '/mnt/snap1' - Operation not permitted
# findmnt /
findmnt: can't read /proc/mounts: No such file or directory
# ls /proc
#
Markus reported that this same scenario simply led to a kernel oops.
This happens because in btrfs_ioctl_snap_destroy(), we call
d_invalidate() before we check may_destroy_subvol(), which means that we
detach the submounts and drop the dentry before erroring out. Instead,
we should only invalidate the dentry once the deletion has succeeded.
Additionally, the shrink_dcache_sb() isn't necessary; d_invalidate()
will prune the dcache for the deleted subvolume.
Cc: <stable@vger.kernel.org>
Fixes: bafc9b754f ("vfs: More precise tests in d_invalidate")
Reported-by: Markus Schauler <mschauler@gmail.com>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
If a directory inode is orphanized, because some inode previously
processed has a new name that collides with the old name of the current
inode, we need to check if it needs its rename operation delayed too,
as its ancestor-descendent relationship with some other inode might
have been reversed between the parent and send snapshots and therefore
its rename operation needs to happen after that other inode is renamed.
For example, for the following reproducer where this is needed (provided
by Robbie Ko):
$ mkfs.btrfs -f /dev/sdb
$ mount /dev/sdb /mnt
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt2
$ mkdir -p /mnt/data/n1/n2
$ mkdir /mnt/data/n4
$ mkdir -p /mnt/data/t6/t7
$ mkdir /mnt/data/t5
$ mkdir /mnt/data/t7
$ mkdir /mnt/data/n4/t2
$ mkdir /mnt/data/t4
$ mkdir /mnt/data/t3
$ mv /mnt/data/t7 /mnt/data/n4/t2
$ mv /mnt/data/t4 /mnt/data/n4/t2/t7
$ mv /mnt/data/t5 /mnt/data/n4/t2/t7/t4
$ mv /mnt/data/t6 /mnt/data/n4/t2/t7/t4/t5
$ mv /mnt/data/n1/n2 /mnt/data/n4/t2/t7/t4/t5/t6
$ mv /mnt/data/n1 /mnt/data/n4/t2/t7/t4/t5/t6
$ mv /mnt/data/n4/t2/t7/t4/t5/t6/t7 /mnt/data/n4/t2/t7/t4/t5/t6/n2
$ mv /mnt/data/t3 /mnt/data/n4/t2/t7/t4/t5/t6/n2/t7
$ btrfs subvolume snapshot -r /mnt /mnt/snap1
$ mv /mnt/data/n4/t2/t7/t4/t5/t6/n1 /mnt/data/n4
$ mv /mnt/data/n4/t2 /mnt/data/n4/n1
$ mv /mnt/data/n4/n1/t2/t7/t4/t5/t6/n2 /mnt/data/n4/n1/t2
$ mv /mnt/data/n4/n1/t2/n2/t7/t3 /mnt/data/n4/n1/t2
$ mv /mnt/data/n4/n1/t2/t7/t4/t5/t6 /mnt/data/n4/n1/t2
$ mv /mnt/data/n4/n1/t2/t7/t4 /mnt/data/n4/n1/t2/t6
$ mv /mnt/data/n4/n1/t2/t7 /mnt/data/n4/n1/t2/t3
$ mv /mnt/data/n4/n1/t2/n2/t7 /mnt/data/n4/n1/t2
$ btrfs subvolume snapshot -r /mnt /mnt/snap2
$ btrfs send /mnt/snap1 | btrfs receive /mnt2
$ btrfs send -p /mnt/snap1 /mnt/snap2 | btrfs receive /mnt2
ERROR: send ioctl failed with -12: Cannot allocate memory
Where the parent snapshot directory hierarchy is the following:
. (ino 256)
|-- data/ (ino 257)
|-- n4/ (ino 260)
|-- t2/ (ino 265)
|-- t7/ (ino 264)
|-- t4/ (ino 266)
|-- t5/ (ino 263)
|-- t6/ (ino 261)
|-- n1/ (ino 258)
|-- n2/ (ino 259)
|-- t7/ (ino 262)
|-- t3/ (ino 267)
And the send snapshot's directory hierarchy is the following:
. (ino 256)
|-- data/ (ino 257)
|-- n4/ (ino 260)
|-- n1/ (ino 258)
|-- t2/ (ino 265)
|-- n2/ (ino 259)
|-- t3/ (ino 267)
| |-- t7 (ino 264)
|
|-- t6/ (ino 261)
| |-- t4/ (ino 266)
| |-- t5/ (ino 263)
|
|-- t7/ (ino 262)
While processing inode 262 we orphanize inode 264 and later attempt
to rename inode 264 to its new name/location, which resulted in building
an incorrect destination path string for the rename operation with the
value "data/n4/t2/t7/t4/t5/t6/n2/t7/t3/t7". This rename operation must
have been done only after inode 267 is processed and renamed, as the
ancestor-descendent relationship between inodes 264 and 267 was reversed
between both snapshots, because otherwise it results in an infinite loop
when building the path string for inode 264 when we are processing an
inode with a number larger than 264. That loop is the following:
start inode 264, send progress of 265 for example
parent of 264 -> 267
parent of 267 -> 262
parent of 262 -> 259
parent of 259 -> 261
parent of 261 -> 263
parent of 263 -> 266
parent of 266 -> 264
|--> back to first iteration while current path string length
is <= PATH_MAX, and fail with -ENOMEM otherwise
So fix this by making the check if we need to delay a directory rename
regardless of the current inode having been orphanized or not.
A test case for fstests follows soon.
Thanks to Robbie Ko for providing a reproducer for this problem.
Reported-by: Robbie Ko <robbieko@synology.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Even though we delay the rename of directories when they become
descendents of other directories that were also renamed in the send
root to prevent infinite path build loops, we were doing it in cases
where this was not needed and was actually harmful resulting in
infinite path build loops as we ended up with a circular dependency
of delayed directory renames.
Consider the following reproducer:
$ mkfs.btrfs -f /dev/sdb
$ mount /dev/sdb /mnt
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt2
$ mkdir /mnt/data
$ mkdir /mnt/data/n1
$ mkdir /mnt/data/n1/n2
$ mkdir /mnt/data/n4
$ mkdir /mnt/data/n1/n2/p1
$ mkdir /mnt/data/n1/n2/p1/p2
$ mkdir /mnt/data/t6
$ mkdir /mnt/data/t7
$ mkdir -p /mnt/data/t5/t7
$ mkdir /mnt/data/t2
$ mkdir /mnt/data/t4
$ mkdir -p /mnt/data/t1/t3
$ mkdir /mnt/data/p1
$ mv /mnt/data/t1 /mnt/data/p1
$ mkdir -p /mnt/data/p1/p2
$ mv /mnt/data/t4 /mnt/data/p1/p2/t1
$ mv /mnt/data/t5 /mnt/data/n4/t5
$ mv /mnt/data/n1/n2/p1/p2 /mnt/data/n4/t5/p2
$ mv /mnt/data/t7 /mnt/data/n4/t5/p2/t7
$ mv /mnt/data/t2 /mnt/data/n4/t1
$ mv /mnt/data/p1 /mnt/data/n4/t5/p2/p1
$ mv /mnt/data/n1/n2 /mnt/data/n4/t5/p2/p1/p2/n2
$ mv /mnt/data/n4/t5/p2/p1/p2/t1 /mnt/data/n4/t5/p2/p1/p2/n2/t1
$ mv /mnt/data/n4/t5/t7 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t7
$ mv /mnt/data/n4/t5/p2/p1/t1/t3 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t3
$ mv /mnt/data/n4/t5/p2/p1/p2/n2/p1 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t7/p1
$ mv /mnt/data/t6 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t3/t5
$ mv /mnt/data/n4/t5/p2/p1/t1 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t3/t1
$ mv /mnt/data/n1 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t7/p1/n1
$ btrfs subvolume snapshot -r /mnt /mnt/snap1
$ mv /mnt/data/n4/t1 /mnt/data/n4/t5/p2/p1/p2/n2/t1/t7/p1/t1
$ mv /mnt/data/n4/t5/p2/p1/p2/n2/t1 /mnt/data/n4/
$ mv /mnt/data/n4/t5/p2/p1/p2/n2 /mnt/data/n4/t1/n2
$ mv /mnt/data/n4/t1/t7/p1 /mnt/data/n4/t1/n2/p1
$ mv /mnt/data/n4/t1/t3/t1 /mnt/data/n4/t1/n2/t1
$ mv /mnt/data/n4/t1/t3 /mnt/data/n4/t1/n2/t1/t3
$ mv /mnt/data/n4/t5/p2/p1/p2 /mnt/data/n4/t1/n2/p1/p2
$ mv /mnt/data/n4/t1/t7 /mnt/data/n4/t1/n2/p1/t7
$ mv /mnt/data/n4/t5/p2/p1 /mnt/data/n4/t1/n2/p1/p2/p1
$ mv /mnt/data/n4/t1/n2/t1/t3/t5 /mnt/data/n4/t1/n2/p1/p2/t5
$ mv /mnt/data/n4/t5 /mnt/data/n4/t1/n2/p1/p2/p1/t5
$ mv /mnt/data/n4/t1/n2/p1/p2/p1/t5/p2 /mnt/data/n4/t1/n2/p1/p2/p1/p2
$ mv /mnt/data/n4/t1/n2/p1/p2/p1/p2/t7 /mnt/data/n4/t1/t7
$ btrfs subvolume snapshot -r /mnt /mnt/snap2
$ btrfs send /mnt/snap1 | btrfs receive /mnt2
$ btrfs send -p /mnt/snap1 /mnt/snap2 | btrfs receive -vv /mnt2
ERROR: send ioctl failed with -12: Cannot allocate memory
This reproducer resulted in an infinite path build loop when building the
path for inode 266 because the following circular dependency of delayed
directory renames was created:
ino 272 <- ino 261 <- ino 259 <- ino 268 <- ino 267 <- ino 261
Where the notation "X <- Y" means the rename of inode X is delayed by the
rename of inode Y (X will be renamed after Y is renamed). This resulted
in an infinite path build loop of inode 266 because that inode has inode
261 as an ancestor in the send root and inode 261 is in the circular
dependency of delayed renames listed above.
Fix this by not delaying the rename of a directory inode if an ancestor of
the inode in the send root, which has a delayed rename operation, is not
also a descendent of the inode in the parent root.
Thanks to Robbie Ko for sending the reproducer example.
A test case for xfstests follows soon.
Reported-by: Robbie Ko <robbieko@synology.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Pull vfs fix from Al Viro:
"Off-by-one in d_walk()/__dentry_kill() race fix.
It's very hard to hit; possible in the same conditions as the original
bug, except that you need the skipped branch to contain all the
remaining evictables, so that the d_walk()-calling loop in
d_invalidate() decides there's nothing more to do and doesn't go for
another pass - otherwise that next pass will sweep the sucker.
So it's not too urgent, but seeing that the fix is obvious and the
original commit has spread into all -stable branches..."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
d_walk() might skip too much
Qu Wenruo