The first step of the rebalance process ensures there is 1MiB free on
each device. This number seems rather small. And in fact when talking to
the original authors their opinions were:
"man that's a little bonkers"
"i don't think we even need that code anymore"
"I think it was there to make sure we had room for the blank 1M at the
beginning. I bet it goes all the way back to v0"
"we just don't need any of that tho, i say we just delete it"
Clearly, this piece of code has lost its original intent throughout the
years. It doesn't really bring any real practical benefits to the
relocation process.
Additionally, this patch makes the balance process more lightweight by
removing a pair of shrink/grow operations which are rather expensive for
heavily populated filesystems. This is mainly due to shrink requiring
relocating block groups, involving heavy use of the btree.
The intermediate shrink/grow can fail and leave the filesystem in a
middle state that would need to be changed back by the user.
Suggested-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
If we create a snapshot of a snapshot currently being used by a send
operation, we can end up with send failing unexpectedly (returning
-ENOENT error to user space for example). The following diagram shows
how this happens.
CPU 1 CPU2 CPU3
btrfs_ioctl_send()
(...)
create_snapshot()
-> creates snapshot of a
root used by the send
task
btrfs_commit_transaction()
create_pending_snapshot()
__get_inode_info()
btrfs_search_slot()
btrfs_search_slot_get_root()
down_read commit_root_sem
get reference on eb of the
commit root
-> eb with bytenr == X
up_read commit_root_sem
btrfs_cow_block(root node)
btrfs_free_tree_block()
-> creates delayed ref to
free the extent
btrfs_run_delayed_refs()
-> runs the delayed ref,
adds extent to
fs_info->pinned_extents
btrfs_finish_extent_commit()
unpin_extent_range()
-> marks extent as free
in the free space cache
transaction commit finishes
btrfs_start_transaction()
(...)
btrfs_cow_block()
btrfs_alloc_tree_block()
btrfs_reserve_extent()
-> allocates extent at
bytenr == X
btrfs_init_new_buffer(bytenr X)
btrfs_find_create_tree_block()
alloc_extent_buffer(bytenr X)
find_extent_buffer(bytenr X)
-> returns existing eb,
which the send task got
(...)
-> modifies content of the
eb with bytenr == X
-> uses an eb that now
belongs to some other
tree and no more matches
the commit root of the
snapshot, resuts will be
unpredictable
The consequences of this race can be various, and can lead to searches in
the commit root performed by the send task failing unexpectedly (unable to
find inode items, returning -ENOENT to user space, for example) or not
failing because an inode item with the same number was added to the tree
that reused the metadata extent, in which case send can behave incorrectly
in the worst case or just fail later for some reason.
Fix this by performing a copy of the commit root's extent buffer when doing
a search in the context of a send operation.
CC: stable@vger.kernel.org # 4.4.x: 1fc28d8e2e9: Btrfs: move get root out of btrfs_search_slot to a helper
CC: stable@vger.kernel.org # 4.4.x: f9ddfd0592a: Btrfs: remove unused check of skip_locking
CC: stable@vger.kernel.org # 4.4.x
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When initializing the security xattrs, we are holding a transaction handle
therefore we need to use a GFP_NOFS context in order to avoid a deadlock
with reclaim in case it's triggered.
Fixes: 39a27ec100 ("btrfs: use GFP_KERNEL for xattr and acl allocations")
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With my delayed refs patches in place we started seeing a large amount
of aborts in __btrfs_free_extent:
BTRFS error (device sdb1): unable to find ref byte nr 91947008 parent 0 root 35964 owner 1 offset 0
Call Trace:
? btrfs_merge_delayed_refs+0xaf/0x340
__btrfs_run_delayed_refs+0x6ea/0xfc0
? btrfs_set_path_blocking+0x31/0x60
btrfs_run_delayed_refs+0xeb/0x180
btrfs_commit_transaction+0x179/0x7f0
? btrfs_check_space_for_delayed_refs+0x30/0x50
? should_end_transaction.isra.19+0xe/0x40
btrfs_drop_snapshot+0x41c/0x7c0
btrfs_clean_one_deleted_snapshot+0xb5/0xd0
cleaner_kthread+0xf6/0x120
kthread+0xf8/0x130
? btree_invalidatepage+0x90/0x90
? kthread_bind+0x10/0x10
ret_from_fork+0x35/0x40
This was because btrfs_drop_snapshot depends on the root not being
modified while it's dropping the snapshot. It will unlock the root node
(and really every node) as it walks down the tree, only to re-lock it
when it needs to do something. This is a problem because if we modify
the tree we could cow a block in our path, which frees our reference to
that block. Then once we get back to that shared block we'll free our
reference to it again, and get ENOENT when trying to lookup our extent
reference to that block in __btrfs_free_extent.
This is ultimately happening because we have delayed items left to be
processed for our deleted snapshot _after_ all of the inodes are closed
for the snapshot. We only run the delayed inode item if we're deleting
the inode, and even then we do not run the delayed insertions or delayed
removals. These can be run at any point after our final inode does its
last iput, which is what triggers the snapshot deletion. We can end up
with the snapshot deletion happening and then have the delayed items run
on that file system, resulting in the above problem.
This problem has existed forever, however my patches made it much easier
to hit as I wake up the cleaner much more often to deal with delayed
iputs, which made us more likely to start the snapshot dropping work
before the transaction commits, which is when the delayed items would
generally be run. Before, generally speaking, we would run the delayed
items, commit the transaction, and wakeup the cleaner thread to start
deleting snapshots, which means we were less likely to hit this problem.
You could still hit it if you had multiple snapshots to be deleted and
ended up with lots of delayed items, but it was definitely harder.
Fix for now by simply running all the delayed items before starting to
drop the snapshot. We could make this smarter in the future by making
the delayed items per-root, and then simply drop any delayed items for
roots that we are going to delete. But for now just a quick and easy
solution is the safest.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When debugging some weird extent reference bug I suspected that we were
changing a snapshot while we were deleting it, which could explain my
bug. This was indeed what was happening, and this patch helped me
verify my theory. It is never correct to modify the snapshot once it's
being deleted, so mark the root when we are deleting it and make sure we
complain about it when it happens.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
@blocksize variable in do_walk_down() is only used once, really no need
to declare it.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since scrub workers only do memory allocation with GFP_KERNEL when they
need to perform repair, we can move the recent setup of the nofs context
up to scrub_handle_errored_block() instead of setting it up down the call
chain at insert_full_stripe_lock() and scrub_add_page_to_wr_bio(),
removing some duplicate code and comment. So the only paths for which a
scrub worker can do memory allocations using GFP_KERNEL are the following:
scrub_bio_end_io_worker()
scrub_block_complete()
scrub_handle_errored_block()
lock_full_stripe()
insert_full_stripe_lock()
-> kmalloc with GFP_KERNEL
scrub_bio_end_io_worker()
scrub_block_complete()
scrub_handle_errored_block()
scrub_write_page_to_dev_replace()
scrub_add_page_to_wr_bio()
-> kzalloc with GFP_KERNEL
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The scrub context is allocated with GFP_KERNEL and called from
btrfs_scrub_dev under the fs_info::device_list_mutex. This is not safe
regarding reclaim that could try to flush filesystem data in order to
get the memory. And the device_list_mutex is held during superblock
commit, so this would cause a lockup.
Move the alocation and initialization before any changes that require
the mutex.
Signed-off-by: David Sterba <dsterba@suse.com>
We can pass fs_info directly as this is the only member of btrfs_device
that's bing used inside scrub_setup_ctx.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have a bunch of magic to make sure we're throttling delayed refs when
truncating a file. Now that we have a delayed refs rsv and a mechanism
for refilling that reserve simply use that instead of all of this magic.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Over the years we have built up a lot of infrastructure to keep delayed
refs in check, mostly by running them at btrfs_end_transaction() time.
We have a lot of different maths we do to figure out how much, if we
should do it inline or async, etc. This existed because we had no
feedback mechanism to force the flushing of delayed refs when they
became a problem. However with the enospc flushing infrastructure in
place for flushing delayed refs when they put too much pressure on the
enospc system we have this problem solved. Rip out all of this code as
it is no longer needed.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now with the delayed_refs_rsv we can now know exactly how much pending
delayed refs space we need. This means we can drastically simplify
btrfs_check_space_for_delayed_refs by simply checking how much space we
have reserved for the global rsv (which acts as a spill over buffer) and
the delayed refs rsv. If our total size is beyond that amount then we
know it's time to commit the transaction and stop any more delayed refs
from being generated.
With the introduction of dealyed_refs_rsv infrastructure, namely
btrfs_update_delayed_refs_rsv we now know exactly how much pending
delayed refs space is required.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
A nice thing we gain with the delayed refs rsv is the ability to flush
the delayed refs on demand to deal with enospc pressure. Add states to
flush delayed refs on demand, and this will allow us to remove a lot of
ad-hoc work around checking to see if we should commit the transaction
to run our delayed refs.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Any space used in the delayed_refs_rsv will be freed up by a transaction
commit, so instead of just counting the pinned space we also need to
account for any space in the delayed_refs_rsv when deciding if it will
make a different to commit the transaction to satisfy our space
reservation. If we have enough bytes to satisfy our reservation ticket
then we are good to go, otherwise subtract out what space we would gain
back by committing the transaction and compare that against the pinned
space to make our decision.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
We use this number to figure out how many delayed refs to run, but
__btrfs_run_delayed_refs really only checks every time we need a new
delayed ref head, so we always run at least one ref head completely no
matter what the number of items on it. Fix the accounting to only be
adjusted when we add/remove a ref head.
In addition to using this number to limit the number of delayed refs
run, a future patch is also going to use it to calculate the amount of
space required for delayed refs space reservation.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The cleanup_extent_op function actually would run the extent_op if it
needed running, which made the name sort of a misnomer. Change it to
run_and_cleanup_extent_op, and move the actual cleanup work to
cleanup_extent_op so it can be used by check_ref_cleanup() in order to
unify the extent op handling.
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We were missing some quota cleanups in check_ref_cleanup, so break the
ref head accounting cleanup into a helper and call that from both
check_ref_cleanup and cleanup_ref_head. This will hopefully ensure that
we don't screw up accounting in the future for other things that we add.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We do this dance in cleanup_ref_head and check_ref_cleanup, unify it
into a helper and cleanup the calling functions.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When using a 'var & (PAGE_SIZE - 1)' construct one is checking for a page
alignment and thus should use the PAGE_ALIGNED() macro instead of
open-coding it.
Convert all open-coded occurrences of PAGE_ALIGNED().
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Constructs like 'var & (PAGE_SIZE - 1)' or 'var & ~PAGE_MASK' can denote an
offset into a page.
So replace them by the offset_in_page() macro instead of open-coding it if
they're not used as an alignment check.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The dev-replace locking functions are now trivial wrappers around rw
semaphore that can be used directly everywhere. No functional change.
Signed-off-by: David Sterba <dsterba@suse.com>
After the rw semaphore has been added, the custom blocking using
::blocking_readers and ::read_lock_wq is redundant.
The blocking logic in __btrfs_map_block is replaced by extending the
time the semaphore is held, that has the same blocking effect on writes
as the previous custom scheme that waited until ::blocking_readers was
zero.
Signed-off-by: David Sterba <dsterba@suse.com>
This is the first part of removing the custom locking and waiting scheme
used for device replace. It was probably copied from extent buffer
locking, but there's nothing that would require more than is provided by
the common locking primitives.
The rw spinlock protects waiting tasks counter in case of incompatible
locks and the waitqueue. Same as rw semaphore.
This patch only switches the locking primitive, for better
bisectability. There should be no functional change other than the
overhead of the locking and potential sleeping instead of spinning when
the lock is contended.
Signed-off-by: David Sterba <dsterba@suse.com>
The device-replace read lock is going to use rw semaphore in followup
commits. The semaphore might sleep which is not possible in the radix
tree preload section. The lock nesting is now:
* device replace
* radix tree preload
* readahead spinlock
Signed-off-by: David Sterba <dsterba@suse.com>
Running btrfs/124 in a loop hung up on me sporadically with the
following call trace:
btrfs D 0 5760 5324 0x00000000
Call Trace:
? __schedule+0x243/0x800
schedule+0x33/0x90
btrfs_start_ordered_extent+0x10c/0x1b0 [btrfs]
? wait_woken+0xa0/0xa0
btrfs_wait_ordered_range+0xbb/0x100 [btrfs]
btrfs_relocate_block_group+0x1ff/0x230 [btrfs]
btrfs_relocate_chunk+0x49/0x100 [btrfs]
btrfs_balance+0xbeb/0x1740 [btrfs]
btrfs_ioctl_balance+0x2ee/0x380 [btrfs]
btrfs_ioctl+0x1691/0x3110 [btrfs]
? lockdep_hardirqs_on+0xed/0x180
? __handle_mm_fault+0x8e7/0xfb0
? _raw_spin_unlock+0x24/0x30
? __handle_mm_fault+0x8e7/0xfb0
? do_vfs_ioctl+0xa5/0x6e0
? btrfs_ioctl_get_supported_features+0x30/0x30 [btrfs]
do_vfs_ioctl+0xa5/0x6e0
? entry_SYSCALL_64_after_hwframe+0x3e/0xbe
ksys_ioctl+0x3a/0x70
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x60/0x1b0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
This happens because during page writeback it's valid for
writepage_delalloc to instantiate a delalloc range which doesn't belong
to the page currently being written back.
The reason this case is valid is due to find_lock_delalloc_range
returning any available range after the passed delalloc_start and
ignoring whether the page under writeback is within that range.
In turn ordered extents (OE) are always created for the returned range
from find_lock_delalloc_range. If, however, a failure occurs while OE
are being created then the clean up code in btrfs_cleanup_ordered_extents
will be called.
Unfortunately the code in btrfs_cleanup_ordered_extents doesn't consider
the case of such 'foreign' range being processed and instead it always
assumes that the range OE are created for belongs to the page. This
leads to the first page of such foregin range to not be cleaned up since
it's deliberately missed and skipped by the current cleaning up code.
Fix this by correctly checking whether the current page belongs to the
range being instantiated and if so adjsut the range parameters passed
for cleaning up. If it doesn't, then just clean the whole OE range
directly.
Fixes: 524272607e ("btrfs: Handle delalloc error correctly to avoid ordered extent hang")
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The @found is always false when it comes to the if branch. Besides, the
bool type is more suitable for @found. Change the return value of the
function and its caller to bool as well.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The test case btrfs/001 with inode_cache mount option will encounter the
following warning:
WARNING: CPU: 1 PID: 23700 at fs/btrfs/inode.c:956 cow_file_range.isra.19+0x32b/0x430 [btrfs]
CPU: 1 PID: 23700 Comm: btrfs Kdump: loaded Tainted: G W O 4.20.0-rc4-custom+ #30
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:cow_file_range.isra.19+0x32b/0x430 [btrfs]
Call Trace:
? free_extent_buffer+0x46/0x90 [btrfs]
run_delalloc_nocow+0x455/0x900 [btrfs]
btrfs_run_delalloc_range+0x1a7/0x360 [btrfs]
writepage_delalloc+0xf9/0x150 [btrfs]
__extent_writepage+0x125/0x3e0 [btrfs]
extent_write_cache_pages+0x1b6/0x3e0 [btrfs]
? __wake_up_common_lock+0x63/0xc0
extent_writepages+0x50/0x80 [btrfs]
do_writepages+0x41/0xd0
? __filemap_fdatawrite_range+0x9e/0xf0
__filemap_fdatawrite_range+0xbe/0xf0
btrfs_fdatawrite_range+0x1b/0x50 [btrfs]
__btrfs_write_out_cache+0x42c/0x480 [btrfs]
btrfs_write_out_ino_cache+0x84/0xd0 [btrfs]
btrfs_save_ino_cache+0x551/0x660 [btrfs]
commit_fs_roots+0xc5/0x190 [btrfs]
btrfs_commit_transaction+0x2bf/0x8d0 [btrfs]
btrfs_mksubvol+0x48d/0x4d0 [btrfs]
btrfs_ioctl_snap_create_transid+0x170/0x180 [btrfs]
btrfs_ioctl_snap_create_v2+0x124/0x180 [btrfs]
btrfs_ioctl+0x123f/0x3030 [btrfs]
The file extent generation of the free space inode is equal to the last
snapshot of the file root, so the inode will be passed to cow_file_rage.
But the inode was created and its extents were preallocated in
btrfs_save_ino_cache, there are no cow copies on disk.
The preallocated extent is not yet in the extent tree, and
btrfs_cross_ref_exist will ignore the -ENOENT returned by
check_committed_ref, so we can directly write the inode to the disk.
Fixes: 78d4295b1e ("btrfs: lift some btrfs_cross_ref_exist checks in nocow path")
CC: stable@vger.kernel.org # 4.18+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The log tree has a long standing problem that when a file is fsync'ed we
only check for new ancestors, created in the current transaction, by
following only the hard link for which the fsync was issued. We follow the
ancestors using the VFS' dget_parent() API. This means that if we create a
new link for a file in a directory that is new (or in an any other new
ancestor directory) and then fsync the file using an old hard link, we end
up not logging the new ancestor, and on log replay that new hard link and
ancestor do not exist. In some cases, involving renames, the file will not
exist at all.
Example:
mkfs.btrfs -f /dev/sdb
mount /dev/sdb /mnt
mkdir /mnt/A
touch /mnt/foo
ln /mnt/foo /mnt/A/bar
xfs_io -c fsync /mnt/foo
<power failure>
In this example after log replay only the hard link named 'foo' exists
and directory A does not exist, which is unexpected. In other major linux
filesystems, such as ext4, xfs and f2fs for example, both hard links exist
and so does directory A after mounting again the filesystem.
Checking if any new ancestors are new and need to be logged was added in
2009 by commit 12fcfd22fe ("Btrfs: tree logging unlink/rename fixes"),
however only for the ancestors of the hard link (dentry) for which the
fsync was issued, instead of checking for all ancestors for all of the
inode's hard links.
So fix this by tracking the id of the last transaction where a hard link
was created for an inode and then on fsync fallback to a full transaction
commit when an inode has more than one hard link and at least one new hard
link was created in the current transaction. This is the simplest solution
since this is not a common use case (adding frequently hard links for
which there's an ancestor created in the current transaction and then
fsync the file). In case it ever becomes a common use case, a solution
that consists of iterating the fs/subvol btree for each hard link and
check if any ancestor is new, could be implemented.
This solves many unexpected scenarios reported by Jayashree Mohan and
Vijay Chidambaram, and for which there is a new test case for fstests
under review.
Fixes: 12fcfd22fe ("Btrfs: tree logging unlink/rename fixes")
CC: stable@vger.kernel.org # 4.4+
Reported-by: Vijay Chidambaram <vvijay03@gmail.com>
Reported-by: Jayashree Mohan <jayashree2912@gmail.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The first auto-assigned value to enum is 0, we can use that and not
initialize all members where the auto-increment does the same. This is
used for values that are not part of on-disk format.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
ordered extent flags.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
extent map flags.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
extent buffer flags;
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
root tree flags.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
internal filesystem states.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
block reserve types.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
We can use simple enum for values that are not part of on-disk format:
global filesystem states.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
This function really checks whether adding more data to the bio will
straddle a stripe/chunk. So first let's give it a more appropraite name
- btrfs_bio_fits_in_stripe. Secondly, the offset parameter was never
used to just remove it. Thirdly, pages are submitted to either btree or
data inodes so it's guaranteed that tree->ops is set so replace the
check with an ASSERT. Finally, document the parameters of the function.
No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When it was introduced in commit f094ac32ab ("Btrfs: fix NULL pointer
after aborting a transaction"), it was not used.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
Document why map_private_extent_buffer() cannot return '1' (i.e. the map
spans two pages) for the csum_tree_block() case.
The current algorithm for detecting a page boundary crossing in
map_private_extent_buffer() will return a '1' *IFF* the extent buffer's
offset in the page + the offset passed in by csum_tree_block() and the
minimal length passed in by csum_tree_block() - 1 are bigger than
PAGE_SIZE.
We always pass BTRFS_CSUM_SIZE (32) as offset and a minimal length of 32
and the current extent buffer allocator always guarantees page aligned
extends, so the above condition can't be true.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
In map_private_extent_buffer() the 'offset' variable is initialized to a
page aligned version of the 'start' parameter.
But later on it is overwritten with either the offset from the extent
buffer's start or 0.
So get rid of the initial initialization.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
When a transaction commit starts, it attempts to pause scrub and it blocks
until the scrub is paused. So while the transaction is blocked waiting for
scrub to pause, we can not do memory allocation with GFP_KERNEL from scrub,
otherwise we risk getting into a deadlock with reclaim.
Checking for scrub pause requests is done early at the beginning of the
while loop of scrub_stripe() and later in the loop, scrub_extent() and
scrub_raid56_parity() are called, which in turn call scrub_pages() and
scrub_pages_for_parity() respectively. These last two functions do memory
allocations using GFP_KERNEL. Same problem could happen while scrubbing
the super blocks, since it calls scrub_pages().
We also can not have any of the worker tasks, created by the scrub task,
doing GFP_KERNEL allocations, because before pausing, the scrub task waits
for all the worker tasks to complete (also done at scrub_stripe()).
So make sure GFP_NOFS is used for the memory allocations because at any
time a scrub pause request can happen from another task that started to
commit a transaction.
Fixes: 58c4e17384 ("btrfs: scrub: use GFP_KERNEL on the submission path")
CC: stable@vger.kernel.org # 4.6+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For data inodes this hook does nothing but to return -EAGAIN which is
used to signal to the endio routines that this bio belongs to a data
inode. If this is the case the actual retrying is handled by
bio_readpage_error. Alternatively, if this bio belongs to the btree
inode then btree_io_failed_hook just does some cleanup and doesn't retry
anything.
This patch simplifies the code flow by eliminating
readpage_io_failed_hook and instead open-coding btree_io_failed_hook in
end_bio_extent_readpage. Also eliminate some needless checks since IO is
always performed on either data inode or btree inode, both of which are
guaranteed to have their extent_io_tree::ops set.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The btrfs_bio_end_io_t typedef was introduced with commit
a1d3c4786a ("btrfs: btrfs_multi_bio replaced with btrfs_bio")
but never used anywhere. This commit also introduced a forward declaration
of 'struct btrfs_bio' which is only needed for btrfs_bio_end_io_t.
Remove both as they're not needed anywhere.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
The end_io callback implemented as btrfs_io_bio_endio_readpage only
calls kfree. Also the callback is set only in case the csum buffer is
allocated and not pointing to the inline buffer. We can use that
information to drop the indirection and call a helper that will free the
csums only in the right case.
This shrinks struct btrfs_io_bio by 8 bytes.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
The io_bio tracks checksums and has an inline buffer or an allocated
one. And there's a third member that points to the right one, but we
don't need to use an extra pointer for that. Let btrfs_io_bio::csum
point to the right buffer and check that the inline buffer is not
accidentally freed.
This shrinks struct btrfs_io_bio by 8 bytes.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
The async_cow::root is used to propagate fs_info to async_cow_submit.
We can't use inode to reach it because it could become NULL after
write without compression in async_cow_start.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
There's one caller and its code is simple, we can open code it in
run_one_async_done. The errors are passed through bio.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
Print a kernel log message when the balance ends, either for cancel or
completed or if it is paused.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The information about balance arguments is important for system audit,
this patch prints the textual representation when balance starts or is
resumed.
Example command:
$ btrfs balance start -f -mprofiles=raid1,convert=single,soft -dlimit=10..20,usage=50 /btrfs
Example kernel log output:
BTRFS info (device sdb): balance: start -f -dusage=50,limit=10..20 -mconvert=single,soft,profiles=raid1 -sconvert=single,soft,profiles=raid1
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog, simplify code ]
Signed-off-by: David Sterba <dsterba@suse.com>
Factor out helper that describes block group flags from
describe_relocation. The result will not be longer than the given size.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add comments ]
Signed-off-by: David Sterba <dsterba@suse.com>
If the quota enable and snapshot creation ioctls are called concurrently
we can get into a deadlock where the task enabling quotas will deadlock
on the fs_info->qgroup_ioctl_lock mutex because it attempts to lock it
twice, or the task creating a snapshot tries to commit the transaction
while the task enabling quota waits for the former task to commit the
transaction while holding the mutex. The following time diagrams show how
both cases happen.
First scenario:
CPU 0 CPU 1
btrfs_ioctl()
btrfs_ioctl_quota_ctl()
btrfs_quota_enable()
mutex_lock(fs_info->qgroup_ioctl_lock)
btrfs_start_transaction()
btrfs_ioctl()
btrfs_ioctl_snap_create_v2
create_snapshot()
--> adds snapshot to the
list pending_snapshots
of the current
transaction
btrfs_commit_transaction()
create_pending_snapshots()
create_pending_snapshot()
qgroup_account_snapshot()
btrfs_qgroup_inherit()
mutex_lock(fs_info->qgroup_ioctl_lock)
--> deadlock, mutex already locked
by this task at
btrfs_quota_enable()
Second scenario:
CPU 0 CPU 1
btrfs_ioctl()
btrfs_ioctl_quota_ctl()
btrfs_quota_enable()
mutex_lock(fs_info->qgroup_ioctl_lock)
btrfs_start_transaction()
btrfs_ioctl()
btrfs_ioctl_snap_create_v2
create_snapshot()
--> adds snapshot to the
list pending_snapshots
of the current
transaction
btrfs_commit_transaction()
--> waits for task at
CPU 0 to release
its transaction
handle
btrfs_commit_transaction()
--> sees another task started
the transaction commit first
--> releases its transaction
handle
--> waits for the transaction
commit to be completed by
the task at CPU 1
create_pending_snapshot()
qgroup_account_snapshot()
btrfs_qgroup_inherit()
mutex_lock(fs_info->qgroup_ioctl_lock)
--> deadlock, task at CPU 0
has the mutex locked but
it is waiting for us to
finish the transaction
commit
So fix this by setting the quota enabled flag in fs_info after committing
the transaction at btrfs_quota_enable(). This ends up serializing quota
enable and snapshot creation as if the snapshot creation happened just
before the quota enable request. The quota rescan task, scheduled after
committing the transaction in btrfs_quote_enable(), will do the accounting.
Fixes: 6426c7ad69 ("btrfs: qgroup: Fix qgroup accounting when creating snapshot")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The available allocation bits members from struct btrfs_fs_info are
protected by a sequence lock, and when starting balance we access them
incorrectly in two different ways:
1) In the read sequence lock loop at btrfs_balance() we use the values we
read from fs_info->avail_*_alloc_bits and we can immediately do actions
that have side effects and can not be undone (printing a message and
jumping to a label). This is wrong because a retry might be needed, so
our actions must not have side effects and must be repeatable as long
as read_seqretry() returns a non-zero value. In other words, we were
essentially ignoring the sequence lock;
2) Right below the read sequence lock loop, we were reading the values
from avail_metadata_alloc_bits and avail_data_alloc_bits without any
protection from concurrent writers, that is, reading them outside of
the read sequence lock critical section.
So fix this by making sure we only read the available allocation bits
while in a read sequence lock critical section and that what we do in the
critical section is repeatable (has nothing that can not be undone) so
that any eventual retry that is needed is handled properly.
Fixes: de98ced9e7 ("Btrfs: use seqlock to protect fs_info->avail_{data, metadata, system}_alloc_bits")
Fixes: 1450612797 ("btrfs: fix a bogus warning when converting only data or metadata")
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We can have a lot freed extents during the life span of transaction, so
the red black tree that keeps track of the ranges of each freed extent
(fs_info->freed_extents[]) can get quite big. When finishing a
transaction commit we find each range, process it (discard the extents,
unpin them) and then remove it from the red black tree.
We can use an extent state record as a cache when searching for a range,
so that when we clean the range we can use the cached extent state we
passed to the search function instead of iterating the red black tree
again. Doing things as fast as possible when finishing a transaction (in
state TRANS_STATE_UNBLOCKED) is convenient as it reduces the time we
block another task that wants to commit the next transaction.
So change clear_extent_dirty() to allow an optional extent state record to
be passed as an argument, which will be passed down to __clear_extent_bit.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This patch lands the last case which needs to be handled by the fsid
change code. Namely, this is the case where a multidisk filesystem has
already undergone at least one successful fsid change i.e all disks
have the METADATA_UUID incompat bit and power failure occurs as another
fsid change is in progress. When such an event occurs, disks could be
split in 2 groups. One of the groups will have both METADATA_UUID and
CHANGING_FSID_V2 flags set coupled with old fsid/metadata_uuid pairs.
The other group of disks will have only METADATA_UUID bit set and their
fsid will be different than the one in disks in the first group. Here
we look at the following cases:
a) A disk from the first group is scanned first, so fs_devices is
created with stale fsid/metdata_uuid. Then when a disk from the
second group is scanned it needs to first check whether there exists
such an fs_devices that has fsid_change set to true (because it was
created with a disk having the CHANGING_FSID_V2 flag), the
metadata_uuid and fsid of the fs_devices will be different (since it was
created by a disk which already has had at least 1 successful fsid change)
and finally the metadata_uuid of the fs_devices will equal that of the
currently scanned disk (because metadata_uuid never really changes).
When the correct fs_devices is found the information from the scanned
disk will replace the current one in fs_devices since the scanned disk
will have higher generation number.
b) A disk from the second group is scanned so fs_devices is created
as usual with differing fsid/metdata_uid. Then when a disk from the
first group is scanned the code detects that it has both
CHANGING_FSID_V2 and METADATA_UUID flags set and will search for
fs_devices that has differing metadata_uuid/fsid and whose
metadata_uuid is the same as that of the scanned device.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit continues hardening the scanning code to handle cases where
power loss could have caused disks in a multi-disk filesystem to be
in inconsistent state. Namely handle the situation that can occur when
some of the disks in multi-disk fs have completed their fsid change i.e
they have METADATA_UUID incompat flag set, have cleared the
CHANGING_FSID_V2 flag and their fsid/metadata_uuid are different. At
the same time the other half of the disks will have their
fsid/metadata_uuid unchanged and will only have CHANGING_FSID_V2 flag.
This is handled by introducing code in the scan path which:
a) Handles the case when a device with CHANGING_FSID_V2 flag is
scanned and as a result btrfs_fs_devices is created with matching
fsid/metdata_uuid. Subsequently, when a device with completed fsid
change is scanned it will detect this via the new code in find_fsid
i.e that such an fs_devices exist that fsid_change flag is set to true,
it's metadata_uuid/fsid match and the metadata_uuid of the scanned
device matches that of the fs_devices. In this case, it's important to
note that the devices which has its fsid change completed will have a
higher generation number than the device with FSID_CHANGING_V2 flag
set, so its superblock block will be used during mount. To prevent an
assertion triggering because the sb used for mounting will have
differing fsid/metadata_uuid than the ones in the fs_devices struct
also add code in device_list_add which overwrites the values in
fs_devices.
b) Alternatively we can end up with a device that completed its
fsid change be scanned first which will create the respective
btrfs_fs_devices struct with differing fsid/metadata_uuid. In this
case when a device with FSID_CHANGING_V2 flag set is scanned it will
call the newly added find_fsid_inprogress function which will return
the correct fs_devices.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In order to gracefully handle split-brain scenario during fsid change
(which are very unlikely, yet possible), two more pieces of information
will be necessary:
1. The highest generation number among all devices registered to a
particular btrfs_fs_devices
2. A boolean flag whether a given btrfs_fs_devices was created by a
device which had the FSID_CHANGING_V2 flag set.
This is a preparatory patch and just introduces the variables as well
as code which sets them, their actual use is going to happen in a later
patch.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Even though fsid change without rewrite is a very quick operation it's
still possible to experience a split-brain scenario if power loss occurs
at the most inconvenient time. This patch handles the case where power
failure occurs while the first transaction (the one setting
CHANGING_FSID_V2) flag is being persisted on disk. This can cause the
btrfs_fs_devices of this filesystem to be created by a device which:
a) has the CHANGING_FSID_V2 flag set but its fsid value is intact
b) or a device which doesn't have CHANGING_FSID_V2 flag set and its
fsid value is intact
This situation is trivially handled by the current find_fsid code since
in both cases the devices are going to be treated like ordinary devices.
Since btrfs is always mounted using the superblock of the latest
device (the one with highest generation number), meaning it will have
the CHANGING_FSID_V2 flag set, ensure it's being cleared on mount. On
the first transaction commit following mount all disks will have it
cleared.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently btrfs_fs_info structure contains a copy of the
fsid/metadata_uuid fields. Same values are also contained in the
btrfs_fs_devices structure which fs_info has a reference to. Let's
reduce duplication by removing the fields from fs_info and always refer
to the ones in fs_devices. No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since the metadata_uuid is a new incompat feature it requires the
respective sysfs hooks. This patch adds the 'metdata_uuid' feature to
be shown if it supported by the kernel. Additionally it adds
/sys/fs/btrfs/UUID/metadata_uuid attribute which allows one to read
the current metadata_uuid.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This field is going to be used when the user wants to change the UUID
of the filesystem without having to rewrite all metadata blocks. This
field adds another level of indirection such that when the FSID is
changed what really happens is the current UUID (the one with which the
fs was created) is copied to the 'metadata_uuid' field in the superblock
as well as a new incompat flag is set METADATA_UUID. When the kernel
detects this flag is set it knows that the superblock in fact has 2
UUIDs:
1. Is the UUID which is user-visible, currently known as FSID.
2. Metadata UUID - this is the UUID which is stamped into all on-disk
datastructures belonging to this file system.
When the new incompat flag is present device scanning checks whether
both fsid/metadata_uuid of the scanned device match any of the
registered filesystems. When the flag is not set then both UUIDs are
equal and only the FSID is retained on disk, metadata_uuid is set only
in-memory during mount.
Additionally a new metadata_uuid field is also added to the fs_info
struct. It's initialised either with the FSID in case METADATA_UUID
incompat flag is not set or with the metdata_uuid of the superblock
otherwise.
This commit introduces the new fields as well as the new incompat flag
and switches all users of the fsid to the new logic.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ minor updates in comments ]
Signed-off-by: David Sterba <dsterba@suse.com>
Several functions in BTRFS are only used inside the source file they are
declared if CONFIG_BTRFS_FS_RUN_SANITY_TESTS is not defined. However if
CONFIG_BTRFS_FS_RUN_SANITY_TESTS is defined these functions are shared
with the unit tests code.
Before the introduction of the EXPORT_FOR_TESTS macro, these functions
could not be declared as static and the compiler had a harder task when
optimizing and inlining them.
As we have EXPORT_FOR_TESTS now, use it where appropriate to support the
compiler.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Depending on whether CONFIG_BTRFS_FS_RUN_SANITY_TESTS is set, some BTRFS
functions are either local to the file they are implemented in and thus
should be declared static or are called from within the test
implementation defined in a different file.
Introduce an EXPORT_FOR_TESTS macro which depending on
CONFIG_BTRFS_FS_RUN_SANITY_TESTS either adds the 'static' keyword to a
function or not.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
Up to commit 32955c5422 ("btrfs: switch to discard_new_inode()") the
drop_on_err variable in btrfs_mkdir() was used to check whether the
inode had to be dropped via iput().
After commit 32955c5422 ("btrfs: switch to discard_new_inode()")
discard_new_inode() is called when err is set and inode is non NULL.
Therefore drop_on_err is not used anymore and thus causes a warning when
building with -Wunused-but-set-variable.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: David Sterba <dsterba@suse.com>
lock_delalloc_pages should only return 2 values - 0 in case of success
and -EAGAIN if the range of pages to be locked should be shrunk due to
some of gone. Manual inspections confirms that this is indeed the case
since __process_pages_contig is where lock_delalloc_pages gets its
return value. The latter always returns 0 or -EAGAIN so the invariant
holds. No functional changes.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
All callers of this function pass BTRFS_MAX_EXTENT_SIZE (128M) so let's
reduce the argument count and make that a local variable. No functional
changes.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's unnecessary to check map->stripes[i].dev for NULL given its value
is already set and dereferenced above the the check. No functional
changes.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
As of now only user requested replace cancel can cancel the
replace-scrub so no need to log the error.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we successfully cancel the device replace, its scrub worker returns
-ECANCELED, which is then passed to btrfs_dev_replace_finishing.
It cleans up based on the returned status and propagates the same
-ECANCELED back the parent function. As of now only user can cancel the
replace-scrub, so its ok to silence the warning here.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We recast the replace return status
BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS to 0, to indicate no
error.
And since BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR should also return 0,
which is also declared as 0, so we just return. Instead add it to the if
statement so that there is enough clarity while reading the code.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When the replace state is in the suspended state, btrfs_scrub_cancel()
should fail with -ENOTCONN as there is no scrub running. As a safety
catch check if btrfs_scrub_cancel() returns -ENOTCONN and assert if it
doesn't.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The device-replace needs to check the result code of the scrub workers
in btrfs_dev_replace_cancel and distinguish if successful cancel
operation and when the there was no operation running.
If btrfs_scrub_cancel() fails, return
BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED so that user can try
to cancel the replace again.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
The device replace cancel thread can race with the replace start thread
and if fs_info::scrubs_running is not yet set, btrfs_scrub_cancel() will
fail to stop the scrub thread.
The scrub thread continues with the scrub for replace which then will
try to write to the target device and which is already freed by the
cancel thread.
scrub_setup_ctx() warns as tgtdev is NULL.
struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
{
...
if (is_dev_replace) {
WARN_ON(!fs_info->dev_replace.tgtdev); <===
sctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
sctx->wr_tgtdev = fs_info->dev_replace.tgtdev;
sctx->flush_all_writes = false;
}
[ 6724.497655] BTRFS info (device sdb): dev_replace from /dev/sdb (devid 1) to /dev/sdc started
[ 6753.945017] BTRFS info (device sdb): dev_replace from /dev/sdb (devid 1) to /dev/sdc canceled
[ 6852.426700] WARNING: CPU: 0 PID: 4494 at fs/btrfs/scrub.c:622 scrub_setup_ctx.isra.19+0x220/0x230 [btrfs]
...
[ 6852.428928] RIP: 0010:scrub_setup_ctx.isra.19+0x220/0x230 [btrfs]
...
[ 6852.432970] Call Trace:
[ 6852.433202] btrfs_scrub_dev+0x19b/0x5c0 [btrfs]
[ 6852.433471] btrfs_dev_replace_start+0x48c/0x6a0 [btrfs]
[ 6852.433800] btrfs_dev_replace_by_ioctl+0x3a/0x60 [btrfs]
[ 6852.434097] btrfs_ioctl+0x2476/0x2d20 [btrfs]
[ 6852.434365] ? do_sigaction+0x7d/0x1e0
[ 6852.434623] do_vfs_ioctl+0xa9/0x6c0
[ 6852.434865] ? syscall_trace_enter+0x1c8/0x310
[ 6852.435124] ? syscall_trace_enter+0x1c8/0x310
[ 6852.435387] ksys_ioctl+0x60/0x90
[ 6852.435663] __x64_sys_ioctl+0x16/0x20
[ 6852.435907] do_syscall_64+0x50/0x180
[ 6852.436150] entry_SYSCALL_64_after_hwframe+0x49/0xbe
Further, as the replace thread enters scrub_write_page_to_dev_replace()
without the target device it panics:
static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
struct scrub_page *spage)
{
...
bio_set_dev(bio, sbio->dev->bdev); <======
[ 6929.715145] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a0
..
[ 6929.717106] Workqueue: btrfs-scrub btrfs_scrub_helper [btrfs]
[ 6929.717420] RIP: 0010:scrub_write_page_to_dev_replace+0xb4/0x260
[btrfs]
..
[ 6929.721430] Call Trace:
[ 6929.721663] scrub_write_block_to_dev_replace+0x3f/0x60 [btrfs]
[ 6929.721975] scrub_bio_end_io_worker+0x1af/0x490 [btrfs]
[ 6929.722277] normal_work_helper+0xf0/0x4c0 [btrfs]
[ 6929.722552] process_one_work+0x1f4/0x520
[ 6929.722805] ? process_one_work+0x16e/0x520
[ 6929.723063] worker_thread+0x46/0x3d0
[ 6929.723313] kthread+0xf8/0x130
[ 6929.723544] ? process_one_work+0x520/0x520
[ 6929.723800] ? kthread_delayed_work_timer_fn+0x80/0x80
[ 6929.724081] ret_from_fork+0x3a/0x50
Fix this by letting the btrfs_dev_replace_finishing() to do the job of
cleaning after the cancel, including freeing of the target device.
btrfs_dev_replace_finishing() is called when btrfs_scub_dev() returns
along with the scrub return status.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In a secnario where balance and replace co-exists as below,
- start balance
- pause balance
- start replace
- reboot
and when system restarts, balance resumes first. Then the replace is
attempted to restart but will fail as the EXCL_OP lock is already held
by the balance. If so place the replace state back to
BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED state.
Fixes: 010a47bde9 ("btrfs: add proper safety check before resuming dev-replace")
CC: stable@vger.kernel.org # 4.18+
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At the time of forced unmount we place the running replace to
BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED state, so when the system comes
back and expect the target device is missing.
Then let the replace state continue to be in
BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED state instead of
BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED as there isn't any matching scrub
running as part of replace.
Fixes: e93c89c1aa ("Btrfs: add new sources for device replace code")
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There isn't any other consumer other than in its own file dev-replace.c.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It's not that impossible to imagine that a device OR a btrfs image is
copied just by using the dd or the cp command. Which in case both the
copies of the btrfs will have the same fsid. If on the system with
automount enabled, the copied FS gets scanned.
We have a known bug in btrfs, that we let the device path be changed
after the device has been mounted. So using this loop hole the new
copied device would appears as if its mounted immediately after it's
been copied.
For example:
Initially.. /dev/mmcblk0p4 is mounted as /
$ lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
mmcblk0 179:0 0 29.2G 0 disk
|-mmcblk0p4 179:4 0 4G 0 part /
|-mmcblk0p2 179:2 0 500M 0 part /boot
|-mmcblk0p3 179:3 0 256M 0 part [SWAP]
`-mmcblk0p1 179:1 0 256M 0 part /boot/efi
$ btrfs fi show
Label: none uuid: 07892354-ddaa-4443-90ea-f76a06accaba
Total devices 1 FS bytes used 1.40GiB
devid 1 size 4.00GiB used 3.00GiB path /dev/mmcblk0p4
Copy mmcblk0 to sda
$ dd if=/dev/mmcblk0 of=/dev/sda
And immediately after the copy completes the change in the device
superblock is notified which the automount scans using btrfs device scan
and the new device sda becomes the mounted root device.
$ lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
sda 8:0 1 14.9G 0 disk
|-sda4 8:4 1 4G 0 part /
|-sda2 8:2 1 500M 0 part
|-sda3 8:3 1 256M 0 part
`-sda1 8:1 1 256M 0 part
mmcblk0 179:0 0 29.2G 0 disk
|-mmcblk0p4 179:4 0 4G 0 part
|-mmcblk0p2 179:2 0 500M 0 part /boot
|-mmcblk0p3 179:3 0 256M 0 part [SWAP]
`-mmcblk0p1 179:1 0 256M 0 part /boot/efi
$ btrfs fi show /
Label: none uuid: 07892354-ddaa-4443-90ea-f76a06accaba
Total devices 1 FS bytes used 1.40GiB
devid 1 size 4.00GiB used 3.00GiB path /dev/sda4
The bug is quite nasty that you can't either unmount /dev/sda4 or
/dev/mmcblk0p4. And the problem does not get solved until you take sda
out of the system on to another system to change its fsid using the
'btrfstune -u' command.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of hardcoding exceptions for RAID5 and RAID6 in the code, use an
nparity field in raid_attr.
Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
RAID5 and RAID6 profile store one copy of the data, not 2 or 3. These
values are not yet used anywhere so there's no change.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Commit 92e222df7b "btrfs: alloc_chunk: fix DUP stripe size handling"
fixed calculating the stripe_size for a new DUP chunk.
However, the same calculation reappears a bit later, and that one was
not changed yet. The resulting bug that is exposed is that the newly
allocated device extents ('stripes') can have a few MiB overlap with the
next thing stored after them, which is another device extent or the end
of the disk.
The scenario in which this can happen is:
* The block device for the filesystem is less than 10GiB in size.
* The amount of contiguous free unallocated disk space chosen to use for
chunk allocation is 20% of the total device size, or a few MiB more or
less.
An example:
- The filesystem device is 7880MiB (max_chunk_size gets set to 788MiB)
- There's 1578MiB unallocated raw disk space left in one contiguous
piece.
In this case stripe_size is first calculated as 789MiB, (half of
1578MiB).
Since 789MiB (stripe_size * data_stripes) > 788MiB (max_chunk_size), we
enter the if block. Now stripe_size value is immediately overwritten
while calculating an adjusted value based on max_chunk_size, which ends
up as 788MiB.
Next, the value is rounded up to a 16MiB boundary, 800MiB, which is
actually more than the value we had before. However, the last comparison
fails to detect this, because it's comparing the value with the total
amount of free space, which is about twice the size of stripe_size.
In the example above, this means that the resulting raw disk space being
allocated is 1600MiB, while only a gap of 1578MiB has been found. The
second device extent object for this DUP chunk will overlap for 22MiB
with whatever comes next.
The underlying problem here is that the stripe_size is reused all the
time for different things. So, when entering the code in the if block,
stripe_size is immediately overwritten with something else. If later we
decide we want to have the previous value back, then the logic to
compute it was copy pasted in again.
With this change, the value in stripe_size is not unnecessarily
destroyed, so the duplicated calculation is not needed any more.
Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The variable num_bytes is really a way too generic name for a variable
in this function. There are a dozen other variables that hold a number
of bytes as value.
Give it a name that actually describes what it does, which is holding
the size of the chunk that we're allocating.
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The variable num_bytes is used to store the chunk length of the chunk
that we're allocating. Do not reuse it for something really different in
the same function.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Snapshot is expected to be fast. But if there are writers steadily
creating dirty pages in our subvolume, the snapshot may take a very long
time to complete. To fix the problem, we use tagged writepage for
snapshot flusher as we do in the generic write_cache_pages(), so we can
omit pages dirtied after the snapshot command.
This does not change the semantics regarding which data get to the
snapshot, if there are pages being dirtied during the snapshotting
operation. There's a sync called before snapshot is taken in old/new
case, any IO in flight just after that may be in the snapshot but this
depends on other system effects that might still sync the IO.
We do a simple snapshot speed test on a Intel D-1531 box:
fio --ioengine=libaio --iodepth=32 --bs=4k --rw=write --size=64G
--direct=0 --thread=1 --numjobs=1 --time_based --runtime=120
--filename=/mnt/sub/testfile --name=job1 --group_reporting & sleep 5;
time btrfs sub snap -r /mnt/sub /mnt/snap; killall fio
original: 1m58sec
patched: 6.54sec
This is the best case for this patch since for a sequential write case,
we omit nearly all pages dirtied after the snapshot command.
For a multi writers, random write test:
fio --ioengine=libaio --iodepth=32 --bs=4k --rw=randwrite --size=64G
--direct=0 --thread=1 --numjobs=4 --time_based --runtime=120
--filename=/mnt/sub/testfile --name=job1 --group_reporting & sleep 5;
time btrfs sub snap -r /mnt/sub /mnt/snap; killall fio
original: 15.83sec
patched: 10.35sec
The improvement is smaller compared to the sequential write case,
since we omit only half of the pages dirtied after snapshot command.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Ethan Lien <ethanlien@synology.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This parameter was never used, yet was part of the interface of the
function ever since its introduction as extent_io_ops::writepage_end_io_hook
in e6dcd2dc9c ("Btrfs: New data=ordered implementation"). Now that
NULL is passed everywhere as a value for this parameter let's remove it
for good. No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The only remaining use of the 'epd' argument in writepage_delalloc is
to reference the extent_io_tree which was set in extent_writepages. Since
it is guaranteed that page->mapping of any page passed to
writepage_delalloc (and __extent_writepage as the sole caller) to be
equal to that passed in extent_writepages we can directly get the
io_tree via the already passed inode (which is also taken from
page->mapping->host). No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If epd::extent_locked is set then writepage_delalloc terminates. Make
this a bit more apparent in the caller by simply bubbling the check up.
This enables to remove epd as an argument to writepage_delalloc in a
future patch. No functional change.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Before btrfs_map_bio submits all stripe bios it does a number of checks
to ensure the device for every stripe is present. However, it doesn't do
a DEV_STATE_MISSING check, instead this is relegated to the lower level
btrfs_schedule_bio (in the async submission case, sync submission
doesn't check DEV_STATE_MISSING at all). Additionally
btrfs_schedule_bios does the duplicate device->bdev check which has
already been performed in btrfs_map_bio.
This patch moves the DEV_STATE_MISSING check in btrfs_map_bio and
removes the duplicate device->bdev check. Doing so ensures that no bio
cloning/submission happens for both async/sync requests in the face of
missing device. This makes the async io submission path slightly shorter
in terms of instruction count. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
dev_replace::replace_state has been set to
BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED (0) in the same function,
So delete the line which sets replace_state = 0;
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The io_err field of struct btrfs_log_ctx is no longer used after the
recent simplification of the fast fsync path, where we now wait for
ordered extents to complete before logging the inode. We did this in
commit b5e6c3e170 ("btrfs: always wait on ordered extents at fsync
time") and commit a2120a473a ("btrfs: clean up the left over
logged_list usage") removed its last use.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We currently are in a loop finding each range (corresponding to a btree
node/leaf) in a log root's extent io tree and then clean it up. This is a
waste of time since we are traversing the extent io tree's rb_tree more
times then needed (one for a range lookup and another for cleaning it up)
without any good reason.
We free the log trees when we are in the critical section of a transaction
commit (the transaction state is set to TRANS_STATE_COMMIT_DOING), so it's
of great convenience to do everything as fast as possible in order to
reduce the time we block other tasks from starting a new transaction.
So fix this by traversing the extent io tree once and cleaning up all its
records in one go while traversing it.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The loop construct in free_extent_buffer was added in
242e18c7c1 ("Btrfs: reduce lock contention on extent buffer locks")
as means of reducing the times the eb lock is taken, the non-last ref
count is decremented and lock is released. As the special handling
of UNMAPPED extent buffers was removed now there is only one decrement
op which is happening for EXTENT_BUFFER_UNMAPPED case.
This commit modifies the loop condition so that in case of UNMAPPED
buffers the eb's lock is taken only if we are 100% sure the eb is going
to be freed by the current executor of the code. Additionally, remove
superfluous ref count ops in btrfs test.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that the whole of btrfs code has been audited for eb reference count
management it's time to remove the hunk in free_extent_buffer that
essentially considered the condition
"eb->ref == 2 && EXTENT_BUFFER_DUMMY"
to equal "eb->ref = 1". Also remove the last location
which takes an extra reference count in alloc_test_extent_buffer.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In qgroup_rescan_leaf a copy is made of the target leaf by calling
btrfs_clone_extent_buffer. The latter allocates a new buffer and
attaches a new set of pages and copies the content of the source buffer.
The new scratch buffer is only used to iterate it's items, it's not
published anywhere and cannot be accessed by a third party.
Hence, it's not necessary to perform any locking on it whatsoever.
Furthermore, remove the extra extent_buffer_get call since the new
buffer is always allocated with a reference count of 1 which is
sufficient here. No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When the 2 comparison trees roots are initialised they are private to
the function and already have reference counts of 1 each. There is no
need to further increment the reference count since the cloned buffers
are already accessed via struct btrfs_path. Eventually the 2 paths used
for comparison are going to be released, effectively disposing of the
cloned buffers.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When a rewound buffer is created it already has a ref count of 1 and the
dummy flag set. Then another ref is taken bumping the count to 2.
Finally when this buffer is released from btrfs_release_path the extra
reference is decremented by the special handling code in
free_extent_buffer.
However, this special code is in fact redundant sinca ref count of 1 is
still correct since the buffer is only accessed via btrfs_path struct.
This paves the way forward of removing the special handling in
free_extent_buffer.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
get_old_root used used only by btrfs_search_old_slot to initialise the
path structure. The old root is always a cloned buffer (either via alloc
dummy or via btrfs_clone_extent_buffer) and its reference count is 2: 1
from allocation, 1 from extent_buffer_get call in get_old_root.
This latter explicit ref count acquire operation is in fact unnecessary
since the semantic is such that the newly allocated buffer is handed
over to the btrfs_path for lifetime management. Considering this just
remove the extra extent_buffer_get in get_old_root.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In iterate_inode_exrefs the eb is cloned via btrfs_clone_extent_buffer
which creates a private extent buffer with the dummy flag set and ref
count of 1. Then this buffer is locked for reading and its ref count is
incremented by 1. Finally it's fed to the passed iterate_irefs_t
function. The actual iterate call back is inode_to_path (coming from
paths_from_inode) which feeds the eb to btrfs_ref_to_path. In this final
function the passed eb is only read by first assigning it to the local
eb variable. This variable is only modified in the case another eb was
referenced from the passed path that is eb != eb_in check triggers.
Considering this there is no point in locking the cloned eb in
iterate_inode_refs since it's never being modified and is not published
anywhere. Furthermore the cloned eb is completely fine having its ref
count be 1.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In iterate_inode_refs the eb is cloned via btrfs_clone_extent_buffer
which creates a private extent buffer with the dummy flag set and ref
count of 1. Then this buffer is locked for reading and its ref count is
incremented by 1. Finally it's fed to the passed iterate_irefs_t
function. The actual iterate call back is inode_to_path (coming from
paths_from_inode) which feeds the eb to btrfs_ref_to_path. In this final
function the passed eb is only read by first assigning it to the local
eb variable. This variable is only modified in the case another eb was
referenced from the passed path that is eb != eb_in check triggers.
Considering this there is no point in locking the cloned eb in
iterate_inode_refs since it's never being modified and is not published
anywhere. Furthermore the cloned eb is completely fine having its ref
count be 1.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In extent-io self test, we need 2 ordered extents at its maximum size to
do the test.
Instead of using the intermediate numbers, use BTRFS_MAX_EXTENT_SIZE for
@max_bytes, and twice @max_bytes for @total_dirty. This should explain
why we need all these magic numbers and prevent people to modify them by
accident.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Btrfs has not allowed swap files since commit 35054394c4 ("Btrfs: stop
providing a bmap operation to avoid swapfile corruptions"). However, now
that the proper restrictions are in place, Btrfs can support swap files
through the swap file a_ops, similar to iomap in commit 67482129cd
("iomap: add a swapfile activation function").
For Btrfs, activation needs to make sure that the file can be used as a
swap file, which currently means that it must be fully allocated as
NOCOW with no compression on one device. It must also do the proper
tracking so that ioctls will not interfere with the swap file.
Deactivation clears this tracking.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The Btrfs swap code is going to need it, so give it a btrfs_ prefix and
make it non-static.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
A later patch will implement swap file support for Btrfs, but before we
do that, we need to make sure that the various Btrfs ioctls cannot
change a swap file.
When a swap file is active, we must make sure that the extents of the
file are not moved and that they don't become shared. That means that
the following are not safe:
- chattr +c (enable compression)
- reflink
- dedupe
- snapshot
- defrag
Don't allow those to happen on an active swap file.
Additionally, balance, resize, device remove, and device replace are
also unsafe if they affect an active swapfile. Add a red-black tree of
block groups and devices which contain an active swapfile. Relocation
checks each block group against this tree and skips it or errors out for
balance or resize, respectively. Device remove and device replace check
the tree for the device they will operate on.
Note that we don't have to worry about chattr -C (disable nocow), which
we ignore for non-empty files, because an active swapfile must be
non-empty and can't be truncated. We also don't have to worry about
autodefrag because it's only done on COW files. Truncate and fallocate
are already taken care of by the generic code. Device add doesn't do
relocation so it's not an issue, either.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is the counterpart to merge_extent_hook, similarly, it's used only
for data/freespace inodes so let's remove it, rename it and call it
directly where necessary. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This callback is used only for data and free space inodes. Such inodes
are guaranteed to have their extent_io_tree::private_data set to the
inode struct. Exploit this fact to directly call the function. Also give
it a more descriptive name. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is the counterpart to ex-set_bit_hook (now btrfs_set_delalloc_extent),
similar to what was done before remove clear_bit_hook and rename the
function. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This callback is used to properly account delalloc extents for data
inodes (ordinary file inodes and freespace v1 inodes). Those can be
easily identified since they have their extent_io trees ->private_data
member point to the inode. Let's exploit this fact to remove the
needless indirection through extent_io_hooks and directly call the
function. Also give the function a name which reflects its purpose -
btrfs_set_delalloc_extent.
This patch also modified test_find_delalloc so that the extent_io_tree
used for testing doesn't have its ->private_data set which would have
caused a crash in btrfs_set_delalloc_extent due to the btrfs_inode->root
member not being initialised. The old version of the code also didn't
call set_bit_hook since the extent_io ops weren't set for the inode. No
functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This callback was only used in debug builds by btrfs_leak_debug_check.
A better approach is to move its implementation in
btrfs_leak_debug_check and ensure the latter is only executed for extent
tree which have ->private_data set i.e. relate to a data node and not
the btree one. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This callback is ony ever called for data page writeout so there is no
need to actually abstract it via extent_io_ops. Lets just export it,
remove the definition of the callback and call it directly in the
functions that invoke the callback. Also rename the function to
btrfs_writepage_endio_finish_ordered since what it really does is
account finished io in the ordered extent data structures. No
functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This hook is called only from __extent_writepage_io which is already
called only from the data page writeout path. So there is no need to
make an indirect call via extent_io_ops. This patch just removes the
callback definition, exports the callback function and calls it directly
at the only call site. Also give the function a more descriptive name.
No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This callback is called only from writepage_delalloc which in turn is
guaranteed to be called from the data page writeout path. In the end
there is no reason to have the call to this function to be indrected via
the extent_io_ops structure. This patch removes the callback definition,
exports the function and calls it directly. No functional changes.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ rename to btrfs_run_delalloc_range ]
Signed-off-by: David Sterba <dsterba@suse.com>
This will be used in future patches that remove the optional
extent_io_ops callbacks.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Add extra dev extent end check against device boundary.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Enhance btrfs_verify_dev_extents() to remember previous checked dev
extents, so it can verify no dev extents can overlap.
Analysis from Hans:
"Imagine allocating a DATA|DUP chunk.
In the chunk allocator, we first set...
max_stripe_size = SZ_1G;
max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE
... which is 10GiB.
Then...
/* we don't want a chunk larger than 10% of writeable space */
max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
max_chunk_size);
Imagine we only have one 7880MiB block device in this filesystem. Now
max_chunk_size is down to 788MiB.
The next step in the code is to search for max_stripe_size * dev_stripes
amount of free space on the device, which is in our example 1GiB * 2 =
2GiB. Imagine the device has exactly 1578MiB free in one contiguous
piece. This amount of bytes will be put in devices_info[ndevs - 1].max_avail
Next we recalculate the stripe_size (which is actually the device extent
length), based on the actual maximum amount of available raw disk space:
stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes);
stripe_size is now 789MiB
Next we do...
data_stripes = num_stripes / ncopies
...where data_stripes ends up as 1, because num_stripes is 2 (the amount
of device extents we're going to have), and DUP has ncopies 2.
Next there's a check...
if (stripe_size * data_stripes > max_chunk_size)
...which matches because 789MiB * 1 > 788MiB.
We go into the if code, and next is...
stripe_size = div_u64(max_chunk_size, data_stripes);
...which resets stripe_size to max_chunk_size: 788MiB
Next is a fun one...
/* bump the answer up to a 16MB boundary */
stripe_size = round_up(stripe_size, SZ_16M);
...which changes stripe_size from 788MiB to 800MiB.
We're not done changing stripe_size yet...
/* But don't go higher than the limits we found while searching
* for free extents
*/
stripe_size = min(devices_info[ndevs - 1].max_avail,
stripe_size);
This is bad. max_avail is twice the stripe_size (we need to fit 2 device
extents on the same device for DUP).
The result here is that 800MiB < 1578MiB, so it's unchanged. However,
the resulting DUP chunk will need 1600MiB disk space, which isn't there,
and the second dev_extent might extend into the next thing (next
dev_extent? end of device?) for 22MiB.
The last shown line of code relies on a situation where there's twice
the value of stripe_size present as value for the variable stripe_size
when it's DUP. This was actually the case before commit 92e222df7b
"btrfs: alloc_chunk: fix DUP stripe size handling", from which I quote:
"[...] in the meantime there's a check to see if the stripe_size does
not exceed max_chunk_size. Since during this check stripe_size is twice
the amount as intended, the check will reduce the stripe_size to
max_chunk_size if the actual correct to be used stripe_size is more than
half the amount of max_chunk_size."
In the previous version of the code, the 16MiB alignment (why is this
done, by the way?) would result in a 50% chance that it would actually
do an 8MiB alignment for the individual dev_extents, since it was
operating on double the size. Does this matter?
Does it matter that stripe_size can be set to anything which is not
16MiB aligned because of the amount of remaining available disk space
which is just taken?
What is the main purpose of this round_up?
The most straightforward thing to do seems something like...
stripe_size = min(
div_u64(devices_info[ndevs - 1].max_avail, dev_stripes),
stripe_size
)
..just putting half of the max_avail into stripe_size."
Link: https://lore.kernel.org/linux-btrfs/b3461a38-e5f8-f41d-c67c-2efac8129054@mendix.com/
Reported-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
[ add analysis from report ]
Signed-off-by: David Sterba <dsterba@suse.com>
We have a complex loop design for find_free_extent(), that has different
behavior for each loop, some even includes new chunk allocation.
Instead of putting such a long code into find_free_extent() and makes it
harder to read, just extract them into find_free_extent_update_loop().
With all the cleanups, the main find_free_extent() should be pretty
barebone:
find_free_extent()
|- Iterate through all block groups
| |- Get a valid block group
| |- Try to do clustered allocation in that block group
| |- Try to do unclustered allocation in that block group
| |- Check if the result is valid
| | |- If valid, then exit
| |- Jump to next block group
|
|- Push harder to find free extents
|- If not found, re-iterate all block groups
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
[ copy callchain from changelog to function comment ]
Signed-off-by: David Sterba <dsterba@suse.com>
This patch will extract unclsutered extent allocation code into
find_free_extent_unclustered().
And this helper function will use return value to indicate what to do
next.
This should make find_free_extent() a little easier to read.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
[Update merge conflict with fb5c39d7a8 ("btrfs: don't use ctl->free_space for max_extent_size")]
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have two main methods to find free extents inside a block group:
1) clustered allocation
2) unclustered allocation
This patch will extract the clustered allocation into
find_free_extent_clustered() to make it a little easier to read.
Instead of jumping between different labels in find_free_extent(), the
helper function will use return value to indicate different behavior.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of tons of different local variables in find_free_extent(),
extract them into find_free_extent_ctl structure, and add better
explanation for them.
Some modification may looks redundant, but will later greatly simplify
function parameter list during find_free_extent() refactor.
Also add two comments to co-operate with fb5c39d7a8 ("btrfs: don't use
ctl->free_space for max_extent_size"), to make ffe_ctl->max_extent_size
update more reader-friendly.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Introduce a new wrapper update_bytes_pinned to replace open coded
bytes_pinned modifiers. Now the underflows of space_info::bytes_pinned
get detected and reported.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Although we have space_info::bytes_may_use underflow detection in
btrfs_free_reserved_data_space_noquota(), we have more callers who are
subtracting number from space_info::bytes_may_use.
So instead of doing underflow detection for every caller, introduce a
new wrapper update_bytes_may_use() to replace open coded bytes_may_use
modifiers.
This also introduce a macro to declare more wrappers, but currently
space_info::bytes_may_use is the mostly interesting one.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Tracking pending ordered extents per transaction was introduced in commit
50d9aa99bd ("Btrfs: make sure logged extents complete in the current
transaction V3") and later updated in commit 161c3549b4 ("Btrfs: change
how we wait for pending ordered extents").
However now that on fsync we always wait for ordered extents to complete
before logging, done in commit 5636cf7d6d ("btrfs: remove the logged
extents infrastructure"), we no longer need the stuff to track for pending
ordered extents, which was not completely removed in the mentioned commit.
So remove the remaining of the pending ordered extents infrastructure.
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The logged_start and logged_end variables, at btrfs_log_changed_extents,
were added in commit 8c6c592831 ("btrfs: log csums for all modified
extents"). However since the recent simplification for fsync, which makes
us wait for all ordered extents to complete before logging extents, we
no longer need those variables. Commit a2120a473a ("btrfs: clean up the
left over logged_list usage") forgot to remove them.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=VW/F
-----END PGP SIGNATURE-----
Merge tag 'for-4.20-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fix from David Sterba:
"A patch in 4.19 introduced a sanity check that was too strict and a
filesystem cannot be mounted.
This happens for filesystems with more than 10 devices and has been
reported by a few users so we need the fix to propagate to stable"
* tag 'for-4.20-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: tree-checker: Don't check max block group size as current max chunk size limit is unreliable
[BUG]
A completely valid btrfs will refuse to mount, with error message like:
BTRFS critical (device sdb2): corrupt leaf: root=2 block=239681536 slot=172 \
bg_start=12018974720 bg_len=10888413184, invalid block group size, \
have 10888413184 expect (0, 10737418240]
This has been reported several times as the 4.19 kernel is now being
used. The filesystem refuses to mount, but is otherwise ok and booting
4.18 is a workaround.
Btrfs check returns no error, and all kernels used on this fs is later
than 2011, which should all have the 10G size limit commit.
[CAUSE]
For a 12 devices btrfs, we could allocate a chunk larger than 10G due to
stripe stripe bump up.
__btrfs_alloc_chunk()
|- max_stripe_size = 1G
|- max_chunk_size = 10G
|- data_stripe = 11
|- if (1G * 11 > 10G) {
stripe_size = 976128930;
stripe_size = round_up(976128930, SZ_16M) = 989855744
However the final stripe_size (989855744) * 11 = 10888413184, which is
still larger than 10G.
[FIX]
For the comprehensive check, we need to do the full check at chunk read
time, and rely on bg <-> chunk mapping to do the check.
We could just skip the length check for now.
Fixes: fce466eab7 ("btrfs: tree-checker: Verify block_group_item")
Cc: stable@vger.kernel.org # v4.19+
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=cCvI
-----END PGP SIGNATURE-----
Merge tag 'for-4.20-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Some of these bugs are being hit during testing so we'd like to get
them merged, otherwise there are usual stability fixes for stable
trees"
* tag 'for-4.20-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: relocation: set trans to be NULL after ending transaction
Btrfs: fix race between enabling quotas and subvolume creation
Btrfs: send, fix infinite loop due to directory rename dependencies
Btrfs: ensure path name is null terminated at btrfs_control_ioctl
Btrfs: fix rare chances for data loss when doing a fast fsync
btrfs: Always try all copies when reading extent buffers
The function relocate_block_group calls btrfs_end_transaction to release
trans when update_backref_cache returns 1, and then continues the loop
body. If btrfs_block_rsv_refill fails this time, it will jump out the
loop and the freed trans will be accessed. This may result in a
use-after-free bug. The patch assigns NULL to trans after trans is
released so that it will not be accessed.
Fixes: 0647bf564f ("Btrfs: improve forever loop when doing balance relocation")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Pan Bian <bianpan2016@163.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have a race between enabling quotas end subvolume creation that cause
subvolume creation to fail with -EINVAL, and the following diagram shows
how it happens:
CPU 0 CPU 1
btrfs_ioctl()
btrfs_ioctl_quota_ctl()
btrfs_quota_enable()
mutex_lock(fs_info->qgroup_ioctl_lock)
btrfs_ioctl()
create_subvol()
btrfs_qgroup_inherit()
-> save fs_info->quota_root
into quota_root
-> stores a NULL value
-> tries to lock the mutex
qgroup_ioctl_lock
-> blocks waiting for
the task at CPU0
-> sets BTRFS_FS_QUOTA_ENABLED in fs_info
-> sets quota_root in fs_info->quota_root
(non-NULL value)
mutex_unlock(fs_info->qgroup_ioctl_lock)
-> checks quota enabled
flag is set
-> returns -EINVAL because
fs_info->quota_root was
NULL before it acquired
the mutex
qgroup_ioctl_lock
-> ioctl returns -EINVAL
Returning -EINVAL to user space will be confusing if all the arguments
passed to the subvolume creation ioctl were valid.
Fix it by grabbing the value from fs_info->quota_root after acquiring
the mutex.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing an incremental send, due to the need of delaying directory move
(rename) operations we can end up in infinite loop at
apply_children_dir_moves().
An example scenario that triggers this problem is described below, where
directory names correspond to the numbers of their respective inodes.
Parent snapshot:
.
|--- 261/
|--- 271/
|--- 266/
|--- 259/
|--- 260/
| |--- 267
|
|--- 264/
| |--- 258/
| |--- 257/
|
|--- 265/
|--- 268/
|--- 269/
| |--- 262/
|
|--- 270/
|--- 272/
| |--- 263/
| |--- 275/
|
|--- 274/
|--- 273/
Send snapshot:
.
|-- 275/
|-- 274/
|-- 273/
|-- 262/
|-- 269/
|-- 258/
|-- 271/
|-- 268/
|-- 267/
|-- 270/
|-- 259/
| |-- 265/
|
|-- 272/
|-- 257/
|-- 260/
|-- 264/
|-- 263/
|-- 261/
|-- 266/
When processing inode 257 we delay its move (rename) operation because its
new parent in the send snapshot, inode 272, was not yet processed. Then
when processing inode 272, we delay the move operation for that inode
because inode 274 is its ancestor in the send snapshot. Finally we delay
the move operation for inode 274 when processing it because inode 275 is
its new parent in the send snapshot and was not yet moved.
When finishing processing inode 275, we start to do the move operations
that were previously delayed (at apply_children_dir_moves()), resulting in
the following iterations:
1) We issue the move operation for inode 274;
2) Because inode 262 depended on the move operation of inode 274 (it was
delayed because 274 is its ancestor in the send snapshot), we issue the
move operation for inode 262;
3) We issue the move operation for inode 272, because it was delayed by
inode 274 too (ancestor of 272 in the send snapshot);
4) We issue the move operation for inode 269 (it was delayed by 262);
5) We issue the move operation for inode 257 (it was delayed by 272);
6) We issue the move operation for inode 260 (it was delayed by 272);
7) We issue the move operation for inode 258 (it was delayed by 269);
8) We issue the move operation for inode 264 (it was delayed by 257);
9) We issue the move operation for inode 271 (it was delayed by 258);
10) We issue the move operation for inode 263 (it was delayed by 264);
11) We issue the move operation for inode 268 (it was delayed by 271);
12) We verify if we can issue the move operation for inode 270 (it was
delayed by 271). We detect a path loop in the current state, because
inode 267 needs to be moved first before we can issue the move
operation for inode 270. So we delay again the move operation for
inode 270, this time we will attempt to do it after inode 267 is
moved;
13) We issue the move operation for inode 261 (it was delayed by 263);
14) We verify if we can issue the move operation for inode 266 (it was
delayed by 263). We detect a path loop in the current state, because
inode 270 needs to be moved first before we can issue the move
operation for inode 266. So we delay again the move operation for
inode 266, this time we will attempt to do it after inode 270 is
moved (its move operation was delayed in step 12);
15) We issue the move operation for inode 267 (it was delayed by 268);
16) We verify if we can issue the move operation for inode 266 (it was
delayed by 270). We detect a path loop in the current state, because
inode 270 needs to be moved first before we can issue the move
operation for inode 266. So we delay again the move operation for
inode 266, this time we will attempt to do it after inode 270 is
moved (its move operation was delayed in step 12). So here we added
again the same delayed move operation that we added in step 14;
17) We attempt again to see if we can issue the move operation for inode
266, and as in step 16, we realize we can not due to a path loop in
the current state due to a dependency on inode 270. Again we delay
inode's 266 rename to happen after inode's 270 move operation, adding
the same dependency to the empty stack that we did in steps 14 and 16.
The next iteration will pick the same move dependency on the stack
(the only entry) and realize again there is still a path loop and then
again the same dependency to the stack, over and over, resulting in
an infinite loop.
So fix this by preventing adding the same move dependency entries to the
stack by removing each pending move record from the red black tree of
pending moves. This way the next call to get_pending_dir_moves() will
not return anything for the current parent inode.
A test case for fstests, with this reproducer, follows soon.
Signed-off-by: Robbie Ko <robbieko@synology.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
[Wrote changelog with example and more clear explanation]
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We were using the path name received from user space without checking that
it is null terminated. While btrfs-progs is well behaved and does proper
validation and null termination, someone could call the ioctl and pass
a non-null terminated patch, leading to buffer overrun problems in the
kernel. The ioctl is protected by CAP_SYS_ADMIN.
So just set the last byte of the path to a null character, similar to what
we do in other ioctls (add/remove/resize device, snapshot creation, etc).
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
After the simplification of the fast fsync patch done recently by commit
b5e6c3e170 ("btrfs: always wait on ordered extents at fsync time") and
commit e7175a6927 ("btrfs: remove the wait ordered logic in the
log_one_extent path"), we got a very short time window where we can get
extents logged without writeback completing first or extents logged
without logging the respective data checksums. Both issues can only happen
when doing a non-full (fast) fsync.
As soon as we enter btrfs_sync_file() we trigger writeback, then lock the
inode and then wait for the writeback to complete before starting to log
the inode. However before we acquire the inode's lock and after we started
writeback, it's possible that more writes happened and dirtied more pages.
If that happened and those pages get writeback triggered while we are
logging the inode (for example, the VM subsystem triggering it due to
memory pressure, or another concurrent fsync), we end up seeing the
respective extent maps in the inode's list of modified extents and will
log matching file extent items without waiting for the respective
ordered extents to complete, meaning that either of the following will
happen:
1) We log an extent after its writeback finishes but before its checksums
are added to the csum tree, leading to -EIO errors when attempting to
read the extent after a log replay.
2) We log an extent before its writeback finishes.
Therefore after the log replay we will have a file extent item pointing
to an unwritten extent (and without the respective data checksums as
well).
This could not happen before the fast fsync patch simplification, because
for any extent we found in the list of modified extents, we would wait for
its respective ordered extent to finish writeback or collect its checksums
for logging if it did not complete yet.
Fix this by triggering writeback again after acquiring the inode's lock
and before waiting for ordered extents to complete.
Fixes: e7175a6927 ("btrfs: remove the wait ordered logic in the log_one_extent path")
Fixes: b5e6c3e170 ("btrfs: always wait on ordered extents at fsync time")
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When a metadata read is served the endio routine btree_readpage_end_io_hook
is called which eventually runs the tree-checker. If tree-checker fails
to validate the read eb then it sets EXTENT_BUFFER_CORRUPT flag. This
leads to btree_read_extent_buffer_pages wrongly assuming that all
available copies of this extent buffer are wrong and failing prematurely.
Fix this modify btree_read_extent_buffer_pages to read all copies of
the data.
This failure was exhibitted in xfstests btrfs/124 which would
spuriously fail its balance operations. The reason was that when balance
was run following re-introduction of the missing raid1 disk
__btrfs_map_block would map the read request to stripe 0, which
corresponded to devid 2 (the disk which is being removed in the test):
item 2 key (FIRST_CHUNK_TREE CHUNK_ITEM 3553624064) itemoff 15975 itemsize 112
length 1073741824 owner 2 stripe_len 65536 type DATA|RAID1
io_align 65536 io_width 65536 sector_size 4096
num_stripes 2 sub_stripes 1
stripe 0 devid 2 offset 2156920832
dev_uuid 8466c350-ed0c-4c3b-b17d-6379b445d5c8
stripe 1 devid 1 offset 3553624064
dev_uuid 1265d8db-5596-477e-af03-df08eb38d2ca
This caused read requests for a checksum item that to be routed to the
stale disk which triggered the aforementioned logic involving
EXTENT_BUFFER_CORRUPT flag. This then triggered cascading failures of
the balance operation.
Fixes: a826d6dcb3 ("Btrfs: check items for correctness as we search")
CC: stable@vger.kernel.org # 4.4+
Suggested-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=K14u
-----END PGP SIGNATURE-----
Merge tag 'for-4.20-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Several fixes to recent release (4.19, fixes tagged for stable) and
other fixes"
* tag 'for-4.20-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
Btrfs: fix missing delayed iputs on unmount
Btrfs: fix data corruption due to cloning of eof block
Btrfs: fix infinite loop on inode eviction after deduplication of eof block
Btrfs: fix deadlock on tree root leaf when finding free extent
btrfs: avoid link error with CONFIG_NO_AUTO_INLINE
btrfs: tree-checker: Fix misleading group system information
Btrfs: fix missing data checksums after a ranged fsync (msync)
btrfs: fix pinned underflow after transaction aborted
Btrfs: fix cur_offset in the error case for nocow
There's a race between close_ctree() and cleaner_kthread().
close_ctree() sets btrfs_fs_closing(), and the cleaner stops when it
sees it set, but this is racy; the cleaner might have already checked
the bit and could be cleaning stuff. In particular, if it deletes unused
block groups, it will create delayed iputs for the free space cache
inodes. As of "btrfs: don't run delayed_iputs in commit", we're no
longer running delayed iputs after a commit. Therefore, if the cleaner
creates more delayed iputs after delayed iputs are run in
btrfs_commit_super(), we will leak inodes on unmount and get a busy
inode crash from the VFS.
Fix it by parking the cleaner before we actually close anything. Then,
any remaining delayed iputs will always be handled in
btrfs_commit_super(). This also ensures that the commit in close_ctree()
is really the last commit, so we can get rid of the commit in
cleaner_kthread().
The fstest/generic/475 followed by 476 can trigger a crash that
manifests as a slab corruption caused by accessing the freed kthread
structure by a wake up function. Sample trace:
[ 5657.077612] BUG: unable to handle kernel NULL pointer dereference at 00000000000000cc
[ 5657.079432] PGD 1c57a067 P4D 1c57a067 PUD da10067 PMD 0
[ 5657.080661] Oops: 0000 [#1] PREEMPT SMP
[ 5657.081592] CPU: 1 PID: 5157 Comm: fsstress Tainted: G W 4.19.0-rc8-default+ #323
[ 5657.083703] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014
[ 5657.086577] RIP: 0010:shrink_page_list+0x2f9/0xe90
[ 5657.091937] RSP: 0018:ffffb5c745c8f728 EFLAGS: 00010287
[ 5657.092953] RAX: 0000000000000074 RBX: ffffb5c745c8f830 RCX: 0000000000000000
[ 5657.094590] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff9a8747fdf3d0
[ 5657.095987] RBP: ffffb5c745c8f9e0 R08: 0000000000000000 R09: 0000000000000000
[ 5657.097159] R10: ffff9a8747fdf5e8 R11: 0000000000000000 R12: ffffb5c745c8f788
[ 5657.098513] R13: ffff9a877f6ff2c0 R14: ffff9a877f6ff2c8 R15: dead000000000200
[ 5657.099689] FS: 00007f948d853b80(0000) GS:ffff9a877d600000(0000) knlGS:0000000000000000
[ 5657.101032] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5657.101953] CR2: 00000000000000cc CR3: 00000000684bd000 CR4: 00000000000006e0
[ 5657.103159] Call Trace:
[ 5657.103776] shrink_inactive_list+0x194/0x410
[ 5657.104671] shrink_node_memcg.constprop.84+0x39a/0x6a0
[ 5657.105750] shrink_node+0x62/0x1c0
[ 5657.106529] try_to_free_pages+0x1a4/0x500
[ 5657.107408] __alloc_pages_slowpath+0x2c9/0xb20
[ 5657.108418] __alloc_pages_nodemask+0x268/0x2b0
[ 5657.109348] kmalloc_large_node+0x37/0x90
[ 5657.110205] __kmalloc_node+0x236/0x310
[ 5657.111014] kvmalloc_node+0x3e/0x70
Fixes: 30928e9baa ("btrfs: don't run delayed_iputs in commit")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add trace ]
Signed-off-by: David Sterba <dsterba@suse.com>
We currently allow cloning a range from a file which includes the last
block of the file even if the file's size is not aligned to the block
size. This is fine and useful when the destination file has the same size,
but when it does not and the range ends somewhere in the middle of the
destination file, it leads to corruption because the bytes between the EOF
and the end of the block have undefined data (when there is support for
discard/trimming they have a value of 0x00).
Example:
$ mkfs.btrfs -f /dev/sdb
$ mount /dev/sdb /mnt
$ export foo_size=$((256 * 1024 + 100))
$ xfs_io -f -c "pwrite -S 0x3c 0 $foo_size" /mnt/foo
$ xfs_io -f -c "pwrite -S 0xb5 0 1M" /mnt/bar
$ xfs_io -c "reflink /mnt/foo 0 512K $foo_size" /mnt/bar
$ od -A d -t x1 /mnt/bar
0000000 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5
*
0524288 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c
*
0786528 3c 3c 3c 3c 00 00 00 00 00 00 00 00 00 00 00 00
0786544 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
*
0790528 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5
*
1048576
The bytes in the range from 786532 (512Kb + 256Kb + 100 bytes) to 790527
(512Kb + 256Kb + 4Kb - 1) got corrupted, having now a value of 0x00 instead
of 0xb5.
This is similar to the problem we had for deduplication that got recently
fixed by commit de02b9f6bb ("Btrfs: fix data corruption when
deduplicating between different files").
Fix this by not allowing such operations to be performed and return the
errno -EINVAL to user space. This is what XFS is doing as well at the VFS
level. This change however now makes us return -EINVAL instead of
-EOPNOTSUPP for cases where the source range maps to an inline extent and
the destination range's end is smaller then the destination file's size,
since the detection of inline extents is done during the actual process of
dropping file extent items (at __btrfs_drop_extents()). Returning the
-EINVAL error is done early on and solely based on the input parameters
(offsets and length) and destination file's size. This makes us consistent
with XFS and anyone else supporting cloning since this case is now checked
at a higher level in the VFS and is where the -EINVAL will be returned
from starting with kernel 4.20 (the VFS changed was introduced in 4.20-rc1
by commit 07d19dc9fb ("vfs: avoid problematic remapping requests into
partial EOF block"). So this change is more geared towards stable kernels,
as it's unlikely the new VFS checks get removed intentionally.
A test case for fstests follows soon, as well as an update to filter
existing tests that expect -EOPNOTSUPP to accept -EINVAL as well.
CC: <stable@vger.kernel.org> # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we are writing out a free space cache, during the transaction commit
phase, we can end up in a deadlock which results in a stack trace like the
following:
schedule+0x28/0x80
btrfs_tree_read_lock+0x8e/0x120 [btrfs]
? finish_wait+0x80/0x80
btrfs_read_lock_root_node+0x2f/0x40 [btrfs]
btrfs_search_slot+0xf6/0x9f0 [btrfs]
? evict_refill_and_join+0xd0/0xd0 [btrfs]
? inode_insert5+0x119/0x190
btrfs_lookup_inode+0x3a/0xc0 [btrfs]
? kmem_cache_alloc+0x166/0x1d0
btrfs_iget+0x113/0x690 [btrfs]
__lookup_free_space_inode+0xd8/0x150 [btrfs]
lookup_free_space_inode+0x5b/0xb0 [btrfs]
load_free_space_cache+0x7c/0x170 [btrfs]
? cache_block_group+0x72/0x3b0 [btrfs]
cache_block_group+0x1b3/0x3b0 [btrfs]
? finish_wait+0x80/0x80
find_free_extent+0x799/0x1010 [btrfs]
btrfs_reserve_extent+0x9b/0x180 [btrfs]
btrfs_alloc_tree_block+0x1b3/0x4f0 [btrfs]
__btrfs_cow_block+0x11d/0x500 [btrfs]
btrfs_cow_block+0xdc/0x180 [btrfs]
btrfs_search_slot+0x3bd/0x9f0 [btrfs]
btrfs_lookup_inode+0x3a/0xc0 [btrfs]
? kmem_cache_alloc+0x166/0x1d0
btrfs_update_inode_item+0x46/0x100 [btrfs]
cache_save_setup+0xe4/0x3a0 [btrfs]
btrfs_start_dirty_block_groups+0x1be/0x480 [btrfs]
btrfs_commit_transaction+0xcb/0x8b0 [btrfs]
At cache_save_setup() we need to update the inode item of a block group's
cache which is located in the tree root (fs_info->tree_root), which means
that it may result in COWing a leaf from that tree. If that happens we
need to find a free metadata extent and while looking for one, if we find
a block group which was not cached yet we attempt to load its cache by
calling cache_block_group(). However this function will try to load the
inode of the free space cache, which requires finding the matching inode
item in the tree root - if that inode item is located in the same leaf as
the inode item of the space cache we are updating at cache_save_setup(),
we end up in a deadlock, since we try to obtain a read lock on the same
extent buffer that we previously write locked.
So fix this by using the tree root's commit root when searching for a
block group's free space cache inode item when we are attempting to load
a free space cache. This is safe since block groups once loaded stay in
memory forever, as well as their caches, so after they are first loaded
we will never need to read their inode items again. For new block groups,
once they are created they get their ->cached field set to
BTRFS_CACHE_FINISHED meaning we will not need to read their inode item.
Reported-by: Andrew Nelson <andrew.s.nelson@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CAPTELenq9x5KOWuQ+fa7h1r3nsJG8vyiTH8+ifjURc_duHh2Wg@mail.gmail.com/
Fixes: 9d66e233c7 ("Btrfs: load free space cache if it exists")
Tested-by: Andrew Nelson <andrew.s.nelson@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Note: this patch fixes a problem in a feature outside of btrfs ("kernel
hacking: add a config option to disable compiler auto-inlining") and is
applied ahead of time due to cross-subsystem dependencies.
On 32-bit ARM with gcc-8, I see a link error with the addition of the
CONFIG_NO_AUTO_INLINE option:
fs/btrfs/super.o: In function `btrfs_statfs':
super.c:(.text+0x67b8): undefined reference to `__aeabi_uldivmod'
super.c:(.text+0x67fc): undefined reference to `__aeabi_uldivmod'
super.c:(.text+0x6858): undefined reference to `__aeabi_uldivmod'
super.c:(.text+0x6920): undefined reference to `__aeabi_uldivmod'
super.c:(.text+0x693c): undefined reference to `__aeabi_uldivmod'
fs/btrfs/super.o:super.c:(.text+0x6958): more undefined references to `__aeabi_uldivmod' follow
So far this is the only file that shows the behavior, so I'd propose
to just work around it by marking the functions as 'static inline'
that normally get inlined here.
The reference to __aeabi_uldivmod comes from a div_u64() which has an
optimization for a constant division that uses a straight '/' operator
when the result should be known to the compiler. My interpretation is
that as we turn off inlining, gcc still expects the result to be constant
but fails to use that constant value.
Link: https://lkml.kernel.org/r/20181103153941.1881966-1-arnd@arndb.de
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
[ add the note ]
Signed-off-by: David Sterba <dsterba@suse.com>
block_group_err shows the group system as a decimal value with a '0x'
prefix, which is somewhat misleading.
Fix it to print hexadecimal, as was intended.
Fixes: fce466eab7 ("btrfs: tree-checker: Verify block_group_item")
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Recently we got a massive simplification for fsync, where for the fast
path we no longer log new extents while their respective ordered extents
are still running.
However that simplification introduced a subtle regression for the case
where we use a ranged fsync (msync). Consider the following example:
CPU 0 CPU 1
mmap write to range [2Mb, 4Mb[
mmap write to range [512Kb, 1Mb[
msync range [512K, 1Mb[
--> triggers fast fsync
(BTRFS_INODE_NEEDS_FULL_SYNC
not set)
--> creates extent map A for this
range and adds it to list of
modified extents
--> starts ordered extent A for
this range
--> waits for it to complete
writeback triggered for range
[2Mb, 4Mb[
--> create extent map B and
adds it to the list of
modified extents
--> creates ordered extent B
--> start looking for and logging
modified extents
--> logs extent maps A and B
--> finds checksums for extent A
in the csum tree, but not for
extent B
fsync (msync) finishes
--> ordered extent B
finishes and its
checksums are added
to the csum tree
<power cut>
After replaying the log, we have the extent covering the range [2Mb, 4Mb[
but do not have the data checksum items covering that file range.
This happens because at the very beginning of an fsync (btrfs_sync_file())
we start and wait for IO in the given range [512Kb, 1Mb[ and therefore
wait for any ordered extents in that range to complete before we start
logging the extents. However if right before we start logging the extent
in our range [512Kb, 1Mb[, writeback is started for any other dirty range,
such as the range [2Mb, 4Mb[ due to memory pressure or a concurrent fsync
or msync (btrfs_sync_file() starts writeback before acquiring the inode's
lock), an ordered extent is created for that other range and a new extent
map is created to represent that range and added to the inode's list of
modified extents.
That means that we will see that other extent in that list when collecting
extents for logging (done at btrfs_log_changed_extents()) and log the
extent before the respective ordered extent finishes - namely before the
checksum items are added to the checksums tree, which is where
log_extent_csums() looks for the checksums, therefore making us log an
extent without logging its checksums. Before that massive simplification
of fsync, this wasn't a problem because besides looking for checkums in
the checksums tree, we also looked for them in any ordered extent still
running.
The consequence of data checksums missing for a file range is that users
attempting to read the affected file range will get -EIO errors and dmesg
reports the following:
[10188.358136] BTRFS info (device sdc): no csum found for inode 297 start 57344
[10188.359278] BTRFS warning (device sdc): csum failed root 5 ino 297 off 57344 csum 0x98f94189 expected csum 0x00000000 mirror 1
So fix this by skipping extents outside of our logging range at
btrfs_log_changed_extents() and leaving them on the list of modified
extents so that any subsequent ranged fsync may collect them if needed.
Also, if we find a hole extent outside of the range still log it, just
to prevent having gaps between extent items after replaying the log,
otherwise fsck will complain when we are not using the NO_HOLES feature
(fstest btrfs/056 triggers such case).
Fixes: e7175a6927 ("btrfs: remove the wait ordered logic in the log_one_extent path")
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When the cow_file_range fails, the related resources are unlocked
according to the range [start..end), so the unlock cannot be repeated in
run_delalloc_nocow.
In some cases (e.g. cur_offset <= end && cow_start != -1), cur_offset is
not updated correctly, so move the cur_offset update before
cow_file_range.
kernel BUG at mm/page-writeback.c:2663!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 3 PID: 31525 Comm: kworker/u8:7 Tainted: P O
Hardware name: Realtek_RTD1296 (DT)
Workqueue: writeback wb_workfn (flush-btrfs-1)
task: ffffffc076db3380 ti: ffffffc02e9ac000 task.ti: ffffffc02e9ac000
PC is at clear_page_dirty_for_io+0x1bc/0x1e8
LR is at clear_page_dirty_for_io+0x14/0x1e8
pc : [<ffffffc00033c91c>] lr : [<ffffffc00033c774>] pstate: 40000145
sp : ffffffc02e9af4f0
Process kworker/u8:7 (pid: 31525, stack limit = 0xffffffc02e9ac020)
Call trace:
[<ffffffc00033c91c>] clear_page_dirty_for_io+0x1bc/0x1e8
[<ffffffbffc514674>] extent_clear_unlock_delalloc+0x1e4/0x210 [btrfs]
[<ffffffbffc4fb168>] run_delalloc_nocow+0x3b8/0x948 [btrfs]
[<ffffffbffc4fb948>] run_delalloc_range+0x250/0x3a8 [btrfs]
[<ffffffbffc514c0c>] writepage_delalloc.isra.21+0xbc/0x1d8 [btrfs]
[<ffffffbffc516048>] __extent_writepage+0xe8/0x248 [btrfs]
[<ffffffbffc51630c>] extent_write_cache_pages.isra.17+0x164/0x378 [btrfs]
[<ffffffbffc5185a8>] extent_writepages+0x48/0x68 [btrfs]
[<ffffffbffc4f5828>] btrfs_writepages+0x20/0x30 [btrfs]
[<ffffffc00033d758>] do_writepages+0x30/0x88
[<ffffffc0003ba0f4>] __writeback_single_inode+0x34/0x198
[<ffffffc0003ba6c4>] writeback_sb_inodes+0x184/0x3c0
[<ffffffc0003ba96c>] __writeback_inodes_wb+0x6c/0xc0
[<ffffffc0003bac20>] wb_writeback+0x1b8/0x1c0
[<ffffffc0003bb0f0>] wb_workfn+0x150/0x250
[<ffffffc0002b0014>] process_one_work+0x1dc/0x388
[<ffffffc0002b02f0>] worker_thread+0x130/0x500
[<ffffffc0002b6344>] kthread+0x10c/0x110
[<ffffffc000284590>] ret_from_fork+0x10/0x40
Code: d503201f a9025bb5 a90363b7 f90023b9 (d4210000)
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Robbie Ko <robbieko@synology.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Rework the vfs_clone_file_range and vfs_dedupe_file_range infrastructure to use
a common .remap_file_range method and supply generic bounds and sanity checking
functions that are shared with the data write path. The current VFS
infrastructure has problems with rlimit, LFS file sizes, file time stamps,
maximum filesystem file sizes, stripping setuid bits, etc and so they are
addressed in these commits.
We also introduce the ability for the ->remap_file_range methods to return short
clones so that clones for vfs_copy_file_range() don't get rejected if the entire
range can't be cloned. It also allows filesystems to sliently skip deduplication
of partial EOF blocks if they are not capable of doing so without requiring
errors to be thrown to userspace.
All existing filesystems are converted to user the new .remap_file_range method,
and both XFS and ocfs2 are modified to make use of the new generic checking
infrastructure.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=CE/A
-----END PGP SIGNATURE-----
Merge tag 'xfs-4.20-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull vfs dedup fixes from Dave Chinner:
"This reworks the vfs data cloning infrastructure.
We discovered many issues with these interfaces late in the 4.19 cycle
- the worst of them (data corruption, setuid stripping) were fixed for
XFS in 4.19-rc8, but a larger rework of the infrastructure fixing all
the problems was needed. That rework is the contents of this pull
request.
Rework the vfs_clone_file_range and vfs_dedupe_file_range
infrastructure to use a common .remap_file_range method and supply
generic bounds and sanity checking functions that are shared with the
data write path. The current VFS infrastructure has problems with
rlimit, LFS file sizes, file time stamps, maximum filesystem file
sizes, stripping setuid bits, etc and so they are addressed in these
commits.
We also introduce the ability for the ->remap_file_range methods to
return short clones so that clones for vfs_copy_file_range() don't get
rejected if the entire range can't be cloned. It also allows
filesystems to sliently skip deduplication of partial EOF blocks if
they are not capable of doing so without requiring errors to be thrown
to userspace.
Existing filesystems are converted to user the new remap_file_range
method, and both XFS and ocfs2 are modified to make use of the new
generic checking infrastructure"
* tag 'xfs-4.20-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (28 commits)
xfs: remove [cm]time update from reflink calls
xfs: remove xfs_reflink_remap_range
xfs: remove redundant remap partial EOF block checks
xfs: support returning partial reflink results
xfs: clean up xfs_reflink_remap_blocks call site
xfs: fix pagecache truncation prior to reflink
ocfs2: remove ocfs2_reflink_remap_range
ocfs2: support partial clone range and dedupe range
ocfs2: fix pagecache truncation prior to reflink
ocfs2: truncate page cache for clone destination file before remapping
vfs: clean up generic_remap_file_range_prep return value
vfs: hide file range comparison function
vfs: enable remap callers that can handle short operations
vfs: plumb remap flags through the vfs dedupe functions
vfs: plumb remap flags through the vfs clone functions
vfs: make remap_file_range functions take and return bytes completed
vfs: remap helper should update destination inode metadata
vfs: pass remap flags to generic_remap_checks
vfs: pass remap flags to generic_remap_file_range_prep
vfs: combine the clone and dedupe into a single remap_file_range
...
-----BEGIN PGP SIGNATURE-----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=CiDs
-----END PGP SIGNATURE-----
Merge tag 'for-4.20-part2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull more btrfs updates from David Sterba:
"This contains a few minor updates and fixes that were under testing or
arrived shortly after the merge window freeze, mostly stable material"
* tag 'for-4.20-part2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
Btrfs: fix use-after-free when dumping free space
Btrfs: fix use-after-free during inode eviction
btrfs: move the dio_sem higher up the callchain
btrfs: don't run delayed_iputs in commit
btrfs: fix insert_reserved error handling
btrfs: only free reserved extent if we didn't insert it
btrfs: don't use ctl->free_space for max_extent_size
btrfs: set max_extent_size properly
btrfs: reset max_extent_size properly
MAINTAINERS: update my email address for btrfs
btrfs: delayed-ref: extract find_first_ref_head from find_ref_head
Btrfs: fix deadlock when writing out free space caches
Btrfs: fix assertion on fsync of regular file when using no-holes feature
Btrfs: fix null pointer dereference on compressed write path error
Change the remap_file_range functions to take a number of bytes to
operate upon and return the number of bytes they operated on. This is a
requirement for allowing fs implementations to return short clone/dedupe
results to the user, which will enable us to obey resource limits in a
graceful manner.
A subsequent patch will enable copy_file_range to signal to the
->clone_file_range implementation that it can handle a short length,
which will be returned in the function's return value. For now the
short return is not implemented anywhere so the behavior won't change --
either copy_file_range manages to clone the entire range or it tries an
alternative.
Neither clone ioctl can take advantage of this, alas.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Combine the clone_file_range and dedupe_file_range operations into a
single remap_file_range file operation dispatch since they're
fundamentally the same operation. The differences between the two can
be made in the prep functions.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Pull XArray conversion from Matthew Wilcox:
"The XArray provides an improved interface to the radix tree data
structure, providing locking as part of the API, specifying GFP flags
at allocation time, eliminating preloading, less re-walking the tree,
more efficient iterations and not exposing RCU-protected pointers to
its users.
This patch set
1. Introduces the XArray implementation
2. Converts the pagecache to use it
3. Converts memremap to use it
The page cache is the most complex and important user of the radix
tree, so converting it was most important. Converting the memremap
code removes the only other user of the multiorder code, which allows
us to remove the radix tree code that supported it.
I have 40+ followup patches to convert many other users of the radix
tree over to the XArray, but I'd like to get this part in first. The
other conversions haven't been in linux-next and aren't suitable for
applying yet, but you can see them in the xarray-conv branch if you're
interested"
* 'xarray' of git://git.infradead.org/users/willy/linux-dax: (90 commits)
radix tree: Remove multiorder support
radix tree test: Convert multiorder tests to XArray
radix tree tests: Convert item_delete_rcu to XArray
radix tree tests: Convert item_kill_tree to XArray
radix tree tests: Move item_insert_order
radix tree test suite: Remove multiorder benchmarking
radix tree test suite: Remove __item_insert
memremap: Convert to XArray
xarray: Add range store functionality
xarray: Move multiorder_check to in-kernel tests
xarray: Move multiorder_shrink to kernel tests
xarray: Move multiorder account test in-kernel
radix tree test suite: Convert iteration test to XArray
radix tree test suite: Convert tag_tagged_items to XArray
radix tree: Remove radix_tree_clear_tags
radix tree: Remove radix_tree_maybe_preload_order
radix tree: Remove split/join code
radix tree: Remove radix_tree_update_node_t
page cache: Finish XArray conversion
dax: Convert page fault handlers to XArray
...
Pull more ->lookup() cleanups from Al Viro:
"Some ->lookup() instances are still overcomplicating the life
for themselves, open-coding the stuff that would be handled by
d_splice_alias() just fine.
Simplify a couple of such cases caught this cycle and document
d_splice_alias() intended use"
* 'work.lookup' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
Document d_splice_alias() calling conventions for ->lookup() users.
simplify btrfs_lookup()
clean erofs_lookup()
At inode.c:evict_inode_truncate_pages(), when we iterate over the
inode's extent states, we access an extent state record's "state" field
after we unlocked the inode's io tree lock. This can lead to a
use-after-free issue because after we unlock the io tree that extent
state record might have been freed due to being merged into another
adjacent extent state record (a previous inflight bio for a read
operation finished in the meanwhile which unlocked a range in the io
tree and cause a merge of extent state records, as explained in the
comment before the while loop added in commit 6ca0709756 ("Btrfs: fix
hang during inode eviction due to concurrent readahead")).
Fix this by keeping a copy of the extent state's flags in a local
variable and using it after unlocking the io tree.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201189
Fixes: b9d0b38928 ("btrfs: Add handler for invalidate page")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This could result in a really bad case where we do something like
evict
evict_refill_and_join
btrfs_commit_transaction
btrfs_run_delayed_iputs
evict
evict_refill_and_join
btrfs_commit_transaction
... forever
We have plenty of other places where we run delayed iputs that are much
safer, let those do the work.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We were not handling the reserved byte accounting properly for data
references. Metadata was fine, if it errored out the error paths would
free the bytes_reserved count and pin the extent, but it even missed one
of the error cases. So instead move this handling up into
run_one_delayed_ref so we are sure that both cases are properly cleaned
up in case of a transaction abort.
CC: stable@vger.kernel.org # 4.18+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When we insert the file extent once the ordered extent completes we free
the reserved extent reservation as it'll have been migrated to the
bytes_used counter. However if we error out after this step we'll still
clear the reserved extent reservation, resulting in a negative
accounting of the reserved bytes for the block group and space info.
Fix this by only doing the free if we didn't successfully insert a file
extent for this extent.
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
max_extent_size is supposed to be the largest contiguous range for the
space info, and ctl->free_space is the total free space in the block
group. We need to keep track of these separately and _only_ use the
max_free_space if we don't have a max_extent_size, as that means our
original request was too large to search any of the block groups for and
therefore wouldn't have a max_extent_size set.
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We can't use entry->bytes if our entry is a bitmap entry, we need to use
entry->max_extent_size in that case. Fix up all the logic to make this
consistent.
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we use up our block group before allocating a new one we'll easily
get a max_extent_size that's set really really low, which will result in
a lot of fragmentation. We need to make sure we're resetting the
max_extent_size when we add a new chunk or add new space.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The find_ref_head shouldn't return the first entry even if no exact match
is found. So move the hidden behavior to higher level.
Besides, remove the useless local variables in the btrfs_select_ref_head.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
[ reformat comment ]
Signed-off-by: David Sterba <dsterba@suse.com>
When writing out a block group free space cache we can end deadlocking
with ourselves on an extent buffer lock resulting in a warning like the
following:
[245043.379979] WARNING: CPU: 4 PID: 2608 at fs/btrfs/locking.c:251 btrfs_tree_lock+0x1be/0x1d0 [btrfs]
[245043.392792] CPU: 4 PID: 2608 Comm: btrfs-transacti Tainted: G
W I 4.16.8 #1
[245043.395489] RIP: 0010:btrfs_tree_lock+0x1be/0x1d0 [btrfs]
[245043.396791] RSP: 0018:ffffc9000424b840 EFLAGS: 00010246
[245043.398093] RAX: 0000000000000a30 RBX: ffff8807e20a3d20 RCX: 0000000000000001
[245043.399414] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff8807e20a3d20
[245043.400732] RBP: 0000000000000001 R08: ffff88041f39a700 R09: ffff880000000000
[245043.402021] R10: 0000000000000040 R11: ffff8807e20a3d20 R12: ffff8807cb220630
[245043.403296] R13: 0000000000000001 R14: ffff8807cb220628 R15: ffff88041fbdf000
[245043.404780] FS: 0000000000000000(0000) GS:ffff88082fc80000(0000) knlGS:0000000000000000
[245043.406050] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[245043.407321] CR2: 00007fffdbdb9f10 CR3: 0000000001c09005 CR4: 00000000000206e0
[245043.408670] Call Trace:
[245043.409977] btrfs_search_slot+0x761/0xa60 [btrfs]
[245043.411278] btrfs_insert_empty_items+0x62/0xb0 [btrfs]
[245043.412572] btrfs_insert_item+0x5b/0xc0 [btrfs]
[245043.413922] btrfs_create_pending_block_groups+0xfb/0x1e0 [btrfs]
[245043.415216] do_chunk_alloc+0x1e5/0x2a0 [btrfs]
[245043.416487] find_free_extent+0xcd0/0xf60 [btrfs]
[245043.417813] btrfs_reserve_extent+0x96/0x1e0 [btrfs]
[245043.419105] btrfs_alloc_tree_block+0xfb/0x4a0 [btrfs]
[245043.420378] __btrfs_cow_block+0x127/0x550 [btrfs]
[245043.421652] btrfs_cow_block+0xee/0x190 [btrfs]
[245043.422979] btrfs_search_slot+0x227/0xa60 [btrfs]
[245043.424279] ? btrfs_update_inode_item+0x59/0x100 [btrfs]
[245043.425538] ? iput+0x72/0x1e0
[245043.426798] write_one_cache_group.isra.49+0x20/0x90 [btrfs]
[245043.428131] btrfs_start_dirty_block_groups+0x102/0x420 [btrfs]
[245043.429419] btrfs_commit_transaction+0x11b/0x880 [btrfs]
[245043.430712] ? start_transaction+0x8e/0x410 [btrfs]
[245043.432006] transaction_kthread+0x184/0x1a0 [btrfs]
[245043.433341] kthread+0xf0/0x130
[245043.434628] ? btrfs_cleanup_transaction+0x4e0/0x4e0 [btrfs]
[245043.435928] ? kthread_create_worker_on_cpu+0x40/0x40
[245043.437236] ret_from_fork+0x1f/0x30
[245043.441054] ---[ end trace 15abaa2aaf36827f ]---
This is because at write_one_cache_group() when we are COWing a leaf from
the extent tree we end up allocating a new block group (chunk) and,
because we have hit a threshold on the number of bytes reserved for system
chunks, we attempt to finalize the creation of new block groups from the
current transaction, by calling btrfs_create_pending_block_groups().
However here we also need to modify the extent tree in order to insert
a block group item, and if the location for this new block group item
happens to be in the same leaf that we were COWing earlier, we deadlock
since btrfs_search_slot() tries to write lock the extent buffer that we
locked before at write_one_cache_group().
We have already hit similar cases in the past and commit d9a0540a79
("Btrfs: fix deadlock when finalizing block group creation") fixed some
of those cases by delaying the creation of pending block groups at the
known specific spots that could lead to a deadlock. This change reworks
that commit to be more generic so that we don't have to add similar logic
to every possible path that can lead to a deadlock. This is done by
making __btrfs_cow_block() disallowing the creation of new block groups
(setting the transaction's can_flush_pending_bgs to false) before it
attempts to allocate a new extent buffer for either the extent, chunk or
device trees, since those are the trees that pending block creation
modifies. Once the new extent buffer is allocated, it allows creation of
pending block groups to happen again.
This change depends on a recent patch from Josef which is not yet in
Linus' tree, named "btrfs: make sure we create all new block groups" in
order to avoid occasional warnings at btrfs_trans_release_chunk_metadata().
Fixes: d9a0540a79 ("Btrfs: fix deadlock when finalizing block group creation")
CC: stable@vger.kernel.org # 4.4+
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199753
Link: https://lore.kernel.org/linux-btrfs/CAJtFHUTHna09ST-_EEiyWmDH6gAqS6wa=zMNMBsifj8ABu99cw@mail.gmail.com/
Reported-by: E V <eliventer@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When using the NO_HOLES feature and logging a regular file, we were
expecting that if we find an inline extent, that either its size in RAM
(uncompressed and unenconded) matches the size of the file or if it does
not, that it matches the sector size and it represents compressed data.
This assertion does not cover a case where the length of the inline extent
is smaller than the sector size and also smaller the file's size, such
case is possible through fallocate. Example:
$ mkfs.btrfs -f -O no-holes /dev/sdb
$ mount /dev/sdb /mnt
$ xfs_io -f -c "pwrite -S 0xb60 0 21" /mnt/foobar
$ xfs_io -c "falloc 40 40" /mnt/foobar
$ xfs_io -c "fsync" /mnt/foobar
In the above example we trigger the assertion because the inline extent's
length is 21 bytes while the file size is 80 bytes. The fallocate() call
merely updated the file's size and did not touch the existing inline
extent, as expected.
So fix this by adjusting the assertion so that an inline extent length
smaller than the file size is valid if the file size is smaller than the
filesystem's sector size.
A test case for fstests follows soon.
Reported-by: Anatoly Trosinenko <anatoly.trosinenko@gmail.com>
Fixes: a89ca6f24f ("Btrfs: fix fsync after truncate when no_holes feature is enabled")
CC: stable@vger.kernel.org # 4.14+
Link: https://lore.kernel.org/linux-btrfs/CAE5jQCfRSBC7n4pUTFJcmHh109=gwyT9mFkCOL+NKfzswmR=_Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At inode.c:compress_file_range(), under the "free_pages_out" label, we can
end up dereferencing the "pages" pointer when it has a NULL value. This
case happens when "start" has a value of 0 and we fail to allocate memory
for the "pages" pointer. When that happens we jump to the "cont" label and
then enter the "if (start == 0)" branch where we immediately call the
cow_file_range_inline() function. If that function returns 0 (success
creating an inline extent) or an error (like -ENOMEM for example) we jump
to the "free_pages_out" label and then access "pages[i]" leading to a NULL
pointer dereference, since "nr_pages" has a value greater than zero at
that point.
Fix this by setting "nr_pages" to 0 when we fail to allocate memory for
the "pages" pointer.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201119
Fixes: 771ed689d2 ("Btrfs: Optimize compressed writeback and reads")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Using bool is more suitable than int here, and add the comment about the
return_bigger.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The avg_delayed_ref_runtime can be referenced from the transaction
handle.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
It can be referenced from the transaction handle.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since trans is only used for referring to delayed_refs, there is no need
to pass it instead of delayed_refs to btrfs_delayed_ref_lock().
No functional change.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since trans is only used for referring to delayed_refs, there is no need
to pass it instead of delayed_refs to btrfs_select_ref_head(). No
functional change.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There is no reason to put this check in (!qgroup)'s else branch because
if qgroup is null, it will goto out directly. So move it out to reduce
indentation level. No functional change.
Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Commit 581c176041 ("btrfs: Validate child tree block's level and first
key") has made tree block level check mandatory.
So if tree block level doesn't match, we won't get a valid extent
buffer. The extra WARN_ON() check can be removed completely.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
And add one line comment explaining what we're doing for each loop.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Some qgroup trace events like btrfs_qgroup_release_data() and
btrfs_qgroup_free_delayed_ref() can still be triggered even if qgroup is
not enabled.
This is caused by the lack of qgroup status check before calling some
qgroup functions. Thankfully the functions can handle quota disabled
case well and just do nothing for qgroup disabled case.
This patch will do earlier check before triggering related trace events.
And for enabled <-> disabled race case:
1) For enabled->disabled case
Disable will wipe out all qgroups data including reservation and
excl/rfer. Even if we leak some reservation or numbers, it will
still be cleared, so nothing will go wrong.
2) For disabled -> enabled case
Current btrfs_qgroup_release_data() will use extent_io tree to ensure
we won't underflow reservation. And for delayed_ref we use
head->qgroup_reserved to record the reserved space, so in that case
head->qgroup_reserved should be 0 and we won't underflow.
CC: stable@vger.kernel.org # 4.14+
Reported-by: Chris Murphy <lists@colorremedies.com>
Link: https://lore.kernel.org/linux-btrfs/CAJCQCtQau7DtuUUeycCkZ36qjbKuxNzsgqJ7+sJ6W0dK_NLE3w@mail.gmail.com/
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In a scenario like the following:
mkdir /mnt/A # inode 258
mkdir /mnt/B # inode 259
touch /mnt/B/bar # inode 260
sync
mv /mnt/B/bar /mnt/A/bar
mv -T /mnt/A /mnt/B
fsync /mnt/B/bar
<power fail>
After replaying the log we end up with file bar having 2 hard links, both
with the name 'bar' and one in the directory with inode number 258 and the
other in the directory with inode number 259. Also, we end up with the
directory inode 259 still existing and with the directory inode 258 still
named as 'A', instead of 'B'. In this scenario, file 'bar' should only
have one hard link, located at directory inode 258, the directory inode
259 should not exist anymore and the name for directory inode 258 should
be 'B'.
This incorrect behaviour happens because when attempting to log the old
parents of an inode, we skip any parents that no longer exist. Fix this
by forcing a full commit if an old parent no longer exists.
A test case for fstests follows soon.
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When replaying a log which contains a tmpfile (which necessarily has a
link count of 0) we end up calling inc_nlink(), at
fs/btrfs/tree-log.c:replay_one_buffer(), which produces a warning like
the following:
[195191.943673] WARNING: CPU: 0 PID: 6924 at fs/inode.c:342 inc_nlink+0x33/0x40
[195191.943723] CPU: 0 PID: 6924 Comm: mount Not tainted 4.19.0-rc6-btrfs-next-38 #1
[195191.943724] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014
[195191.943726] RIP: 0010:inc_nlink+0x33/0x40
[195191.943728] RSP: 0018:ffffb96e425e3870 EFLAGS: 00010246
[195191.943730] RAX: 0000000000000000 RBX: ffff8c0d1e6af4f0 RCX: 0000000000000006
[195191.943731] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8c0d1e6af4f0
[195191.943731] RBP: 0000000000000097 R08: 0000000000000001 R09: 0000000000000000
[195191.943732] R10: 0000000000000000 R11: 0000000000000000 R12: ffffb96e425e3a60
[195191.943733] R13: ffff8c0d10cff0c8 R14: ffff8c0d0d515348 R15: ffff8c0d78a1b3f8
[195191.943735] FS: 00007f570ee24480(0000) GS:ffff8c0dfb200000(0000) knlGS:0000000000000000
[195191.943736] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[195191.943737] CR2: 00005593286277c8 CR3: 00000000bb8f2006 CR4: 00000000003606f0
[195191.943739] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[195191.943740] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[195191.943741] Call Trace:
[195191.943778] replay_one_buffer+0x797/0x7d0 [btrfs]
[195191.943802] walk_up_log_tree+0x1c1/0x250 [btrfs]
[195191.943809] ? rcu_read_lock_sched_held+0x3f/0x70
[195191.943825] walk_log_tree+0xae/0x1d0 [btrfs]
[195191.943840] btrfs_recover_log_trees+0x1d7/0x4d0 [btrfs]
[195191.943856] ? replay_dir_deletes+0x280/0x280 [btrfs]
[195191.943870] open_ctree+0x1c3b/0x22a0 [btrfs]
[195191.943887] btrfs_mount_root+0x6b4/0x800 [btrfs]
[195191.943894] ? rcu_read_lock_sched_held+0x3f/0x70
[195191.943899] ? pcpu_alloc+0x55b/0x7c0
[195191.943906] ? mount_fs+0x3b/0x140
[195191.943908] mount_fs+0x3b/0x140
[195191.943912] ? __init_waitqueue_head+0x36/0x50
[195191.943916] vfs_kern_mount+0x62/0x160
[195191.943927] btrfs_mount+0x134/0x890 [btrfs]
[195191.943936] ? rcu_read_lock_sched_held+0x3f/0x70
[195191.943938] ? pcpu_alloc+0x55b/0x7c0
[195191.943943] ? mount_fs+0x3b/0x140
[195191.943952] ? btrfs_remount+0x570/0x570 [btrfs]
[195191.943954] mount_fs+0x3b/0x140
[195191.943956] ? __init_waitqueue_head+0x36/0x50
[195191.943960] vfs_kern_mount+0x62/0x160
[195191.943963] do_mount+0x1f9/0xd40
[195191.943967] ? memdup_user+0x4b/0x70
[195191.943971] ksys_mount+0x7e/0xd0
[195191.943974] __x64_sys_mount+0x21/0x30
[195191.943977] do_syscall_64+0x60/0x1b0
[195191.943980] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[195191.943983] RIP: 0033:0x7f570e4e524a
[195191.943986] RSP: 002b:00007ffd83589478 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5
[195191.943989] RAX: ffffffffffffffda RBX: 0000563f335b2060 RCX: 00007f570e4e524a
[195191.943990] RDX: 0000563f335b2240 RSI: 0000563f335b2280 RDI: 0000563f335b2260
[195191.943992] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000020
[195191.943993] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 0000563f335b2260
[195191.943994] R13: 0000563f335b2240 R14: 0000000000000000 R15: 00000000ffffffff
[195191.944002] irq event stamp: 8688
[195191.944010] hardirqs last enabled at (8687): [<ffffffff9cb004c3>] console_unlock+0x503/0x640
[195191.944012] hardirqs last disabled at (8688): [<ffffffff9ca037dd>] trace_hardirqs_off_thunk+0x1a/0x1c
[195191.944018] softirqs last enabled at (8638): [<ffffffff9cc0a5d1>] __set_page_dirty_nobuffers+0x101/0x150
[195191.944020] softirqs last disabled at (8634): [<ffffffff9cc26bbe>] wb_wakeup_delayed+0x2e/0x60
[195191.944022] ---[ end trace 5d6e873a9a0b811a ]---
This happens because the inode does not have the flag I_LINKABLE set,
which is a runtime only flag, not meant to be persisted, set when the
inode is created through open(2) if the flag O_EXCL is not passed to it.
Except for the warning, there are no other consequences (like corruptions
or metadata inconsistencies).
Since it's pointless to replay a tmpfile as it would be deleted in a
later phase of the log replay procedure (it has a link count of 0), fix
this by not logging tmpfiles and if a tmpfile is found in a log (created
by a kernel without this change), skip the replay of the inode.
A test case for fstests follows soon.
Fixes: 471d557afe ("Btrfs: fix loss of prealloc extents past i_size after fsync log replay")
CC: stable@vger.kernel.org # 4.18+
Reported-by: Martin Steigerwald <martin@lichtvoll.de>
Link: https://lore.kernel.org/linux-btrfs/3666619.NTnn27ZJZE@merkaba/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We don't need it, rsv->size is set once and never changes throughout
its lifetime, so just use that for the reserve size.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I ran into an issue where there was some reference being held on an
inode that I couldn't track. This assert wasn't triggered, but it at
least rules out we're doing something stupid.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Allocating new chunks modifies both the extent and chunk tree, which can
trigger new chunk allocations. So instead of doing list_for_each_safe,
just do while (!list_empty()) so we make sure we don't exit with other
pending bg's still on our list.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We need to clear the max_extent_size when we clear bits from a bitmap
since it could have been from the range that contains the
max_extent_size.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we're allocating a new space cache inode it's likely going to be
under a transaction handle, so we need to use memalloc_nofs_save() in
order to avoid deadlocks, and more importantly lockdep messages that
make xfstests fail.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We want to release the unused reservation we have since it refills the
delayed refs reserve, which will make everything go smoother when
running the delayed refs if we're short on our reservation.
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Btrfs's btree locking has two modes, spinning mode and blocking mode,
while searching btree, locking is always acquired in spinning mode and
then converted to blocking mode if necessary, and in some hot paths we may
switch the locking back to spinning mode by btrfs_clear_path_blocking().
When acquiring locks, both of reader and writer need to wait for blocking
readers and writers to complete before doing read_lock()/write_lock().
The problem is that btrfs_clear_path_blocking() needs to switch nodes
in the path to blocking mode at first (by btrfs_set_path_blocking) to
make lockdep happy before doing its actual clearing blocking job.
When switching to blocking mode from spinning mode, it consists of
step 1) bumping up blocking readers counter and
step 2) read_unlock()/write_unlock(),
this has caused serious ping-pong effect if there're a great amount of
concurrent readers/writers, as waiters will be woken up and go to
sleep immediately.
1) Killing this kind of ping-pong results in a big improvement in my 1600k
files creation script,
MNT=/mnt/btrfs
mkfs.btrfs -f /dev/sdf
mount /dev/def $MNT
time fsmark -D 10000 -S0 -n 100000 -s 0 -L 1 -l /tmp/fs_log.txt \
-d $MNT/0 -d $MNT/1 \
-d $MNT/2 -d $MNT/3 \
-d $MNT/4 -d $MNT/5 \
-d $MNT/6 -d $MNT/7 \
-d $MNT/8 -d $MNT/9 \
-d $MNT/10 -d $MNT/11 \
-d $MNT/12 -d $MNT/13 \
-d $MNT/14 -d $MNT/15
w/o patch:
real 2m27.307s
user 0m12.839s
sys 13m42.831s
w/ patch:
real 1m2.273s
user 0m15.802s
sys 8m16.495s
1.1) latency histogram from funclatency[1]
Overall with the patch, there're ~50% less write lock acquisition and
the 95% max latency that write lock takes also reduces to ~100ms from
>500ms.
--------------------------------------------
w/o patch:
--------------------------------------------
Function = btrfs_tree_lock
msecs : count distribution
0 -> 1 : 2385222 |****************************************|
2 -> 3 : 37147 | |
4 -> 7 : 20452 | |
8 -> 15 : 13131 | |
16 -> 31 : 3877 | |
32 -> 63 : 3900 | |
64 -> 127 : 2612 | |
128 -> 255 : 974 | |
256 -> 511 : 165 | |
512 -> 1023 : 13 | |
Function = btrfs_tree_read_lock
msecs : count distribution
0 -> 1 : 6743860 |****************************************|
2 -> 3 : 2146 | |
4 -> 7 : 190 | |
8 -> 15 : 38 | |
16 -> 31 : 4 | |
--------------------------------------------
w/ patch:
--------------------------------------------
Function = btrfs_tree_lock
msecs : count distribution
0 -> 1 : 1318454 |****************************************|
2 -> 3 : 6800 | |
4 -> 7 : 3664 | |
8 -> 15 : 2145 | |
16 -> 31 : 809 | |
32 -> 63 : 219 | |
64 -> 127 : 10 | |
Function = btrfs_tree_read_lock
msecs : count distribution
0 -> 1 : 6854317 |****************************************|
2 -> 3 : 2383 | |
4 -> 7 : 601 | |
8 -> 15 : 92 | |
2) dbench also proves the improvement,
dbench -t 120 -D /mnt/btrfs 16
w/o patch:
Throughput 158.363 MB/sec
w/ patch:
Throughput 449.52 MB/sec
3) xfstests didn't show any additional failures.
One thing to note is that callers may set path->leave_spinning to have
all nodes in the path stay in spinning mode, which means callers are
ready to not sleep before releasing the path, but it won't cause
problems if they don't want to sleep in blocking mode.
[1]: https://github.com/iovisor/bcc/blob/master/tools/funclatency.py
Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The value of blocking_readers is increased only when the lock is taken
for read, no way we can fail the condition with the write lock.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The replace_wait and bio_counter were mistakenly added to fs_info in
commit c404e0dc2c ("Btrfs: fix use-after-free in the finishing
procedure of the device replace"), but they logically belong to
fs_info::dev_replace. Besides, bio_counter is a very generic name and is
confusing in bare fs_info context.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The exit sequence in btrfs_dev_replace_start does not allow to simply
add a label to the right place so the error handling after starting
transaction failure jumps there. Currently there's a lock that pairs
with the unlock in the section, which is unnecessary and only raises
questions. Add a variable to track the locking status and avoid the
extra locking.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Too trivial, the purpose can be simply documented in a comment.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The wrapper is too trivial, open coding does not make it less readable.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's a single caller and the function name does not say it's actually
taking the lock, so open coding makes it more explicit.
For now, btrfs_dev_replace_read_lock is used instead of read_lock so
it's paired with the unlocking wrapper in the same block.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This member seems to be copied from the extent_buffer locking scheme and
is at least used to assert that the read lock/unlock is properly nested.
In some way. While the _inc/_dec are called inside the read lock
section, the asserts are both inside and outside, so the ordering is not
guaranteed and we can see read/inc/dec ordered in any way
(theoretically).
A missing call of btrfs_dev_replace_clear_lock_blocking could cause
unexpected read_locks count, so this at least looks like a valid
assertion, but this will become unnecessary with later updates.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Although we have tree level check at tree read runtime, it's completely
based on its parent level.
We still need to do accurate level check to avoid invalid tree blocks
sneak into kernel space.
The check itself is simple, for leaf its level should always be 0.
For nodes its level should be in range [1, BTRFS_MAX_LEVEL - 1].
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For qgroup_trace_extent_swap(), if we find one leaf that needs to be
traced, we will also iterate all file extents and trace them.
This is OK if we're relocating data block groups, but if we're
relocating metadata block groups, balance code itself has ensured that
both subtree of file tree and reloc tree contain the same contents.
That's to say, if we're relocating metadata block groups, all file
extents in reloc and file tree should match, thus no need to trace them.
This should reduce the total number of dirty extents processed in metadata
block group balance.
[[Benchmark]] (with all previous enhancement)
Hardware:
VM 4G vRAM, 8 vCPUs,
disk is using 'unsafe' cache mode,
backing device is SAMSUNG 850 evo SSD.
Host has 16G ram.
Mkfs parameter:
--nodesize 4K (To bump up tree size)
Initial subvolume contents:
4G data copied from /usr and /lib.
(With enough regular small files)
Snapshots:
16 snapshots of the original subvolume.
each snapshot has 3 random files modified.
balance parameter:
-m
So the content should be pretty similar to a real world root fs layout.
| v4.19-rc1 | w/ patchset | diff (*)
---------------------------------------------------------------
relocated extents | 22929 | 22851 | -0.3%
qgroup dirty extents | 227757 | 140886 | -38.1%
time (sys) | 65.253s | 37.464s | -42.6%
time (real) | 74.032s | 44.722s | -39.6%
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Reloc tree doesn't contribute to qgroup numbers, as we have accounted
them at balance time (see replace_path()).
Skipping the unneeded subtree tracing should reduce the overhead.
[[Benchmark]]
Hardware:
VM 4G vRAM, 8 vCPUs,
disk is using 'unsafe' cache mode,
backing device is SAMSUNG 850 evo SSD.
Host has 16G ram.
Mkfs parameter:
--nodesize 4K (To bump up tree size)
Initial subvolume contents:
4G data copied from /usr and /lib.
(With enough regular small files)
Snapshots:
16 snapshots of the original subvolume.
each snapshot has 3 random files modified.
balance parameter:
-m
So the content should be pretty similar to a real world root fs layout.
| v4.19-rc1 | w/ patchset | diff (*)
---------------------------------------------------------------
relocated extents | 22929 | 22900 | -0.1%
qgroup dirty extents | 227757 | 167139 | -26.6%
time (sys) | 65.253s | 50.123s | -23.2%
time (real) | 74.032s | 52.551s | -29.0%
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Before this patch, with quota enabled during balance, we need to mark
the whole subtree dirty for quota.
E.g.
OO = Old tree blocks (from file tree)
NN = New tree blocks (from reloc tree)
File tree (src) Reloc tree (dst)
OO (a) NN (a)
/ \ / \
(b) OO OO (c) (b) NN NN (c)
/ \ / \ / \ / \
OO OO OO OO (d) OO OO OO NN (d)
For old balance + quota case, quota will mark the whole src and dst tree
dirty, including all the 3 old tree blocks in reloc tree.
It's doable for small file tree or new tree blocks are all located at
lower level.
But for large file tree or new tree blocks are all located at higher
level, this will lead to mark the whole tree dirty, and be unbelievably
slow.
This patch will change how we handle such balance with quota enabled
case.
Now we will search from (b) and (c) for any new tree blocks whose
generation is equal to @last_snapshot, and only mark them dirty.
In above case, we only need to trace tree blocks NN(b), NN(c) and NN(d).
(NN(a) will be traced when COW happens for nodeptr modification). And
also for tree blocks OO(b), OO(c), OO(d). (OO(a) will be traced when COW
happens for nodeptr modification.)
For above case, we could skip 3 tree blocks, but for larger tree, we can
skip tons of unmodified tree blocks, and hugely speed up balance.
This patch will introduce a new function,
btrfs_qgroup_trace_subtree_swap(), which will do the following main
work:
1) Read out real root eb
And setup basic dst_path for later calls
2) Call qgroup_trace_new_subtree_blocks()
To trace all new tree blocks in reloc tree and their counter
parts in the file tree.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Introduce new function, qgroup_trace_new_subtree_blocks(), to iterate
all new tree blocks in a reloc tree.
So that qgroup could skip unrelated tree blocks during balance, which
should hugely speedup balance speed when quota is enabled.
The function qgroup_trace_new_subtree_blocks() itself only cares about
new tree blocks in reloc tree.
All its main works are:
1) Read out tree blocks according to parent pointers
2) Do recursive depth-first search
Will call the same function on all its children tree blocks, with
search level set to current level -1.
And will also skip all children whose generation is smaller than
@last_snapshot.
3) Call qgroup_trace_extent_swap() to trace tree blocks
So although we have parameter list related to source file tree, it's not
used at all, but only passed to qgroup_trace_extent_swap().
Thus despite the tree read code, the core should be pretty short and all
about recursive depth-first search.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Introduce a new function, qgroup_trace_extent_swap(), which will be used
later for balance qgroup speedup.
The basis idea of balance is swapping tree blocks between reloc tree and
the real file tree.
The swap will happen in highest tree block, but there may be a lot of
tree blocks involved.
For example:
OO = Old tree blocks
NN = New tree blocks allocated during balance
File tree (257) Reloc tree for 257
L2 OO NN
/ \ / \
L1 OO OO (a) OO NN (a)
/ \ / \ / \ / \
L0 OO OO OO OO OO OO NN NN
(b) (c) (b) (c)
When calling qgroup_trace_extent_swap(), we will pass:
@src_eb = OO(a)
@dst_path = [ nodes[1] = NN(a), nodes[0] = NN(c) ]
@dst_level = 0
@root_level = 1
In that case, qgroup_trace_extent_swap() will search from OO(a) to
reach OO(c), then mark both OO(c) and NN(c) as qgroup dirty.
The main work of qgroup_trace_extent_swap() can be split into 3 parts:
1) Tree search from @src_eb
It should acts as a simplified btrfs_search_slot().
The key for search can be extracted from @dst_path->nodes[dst_level]
(first key).
2) Mark the final tree blocks in @src_path and @dst_path qgroup dirty
NOTE: In above case, OO(a) and NN(a) won't be marked qgroup dirty.
They should be marked during preivous (@dst_level = 1) iteration.
3) Mark file extents in leaves dirty
We don't have good way to pick out new file extents only.
So we still follow the old method by scanning all file extents in
the leave.
This function can free us from keeping two pathes, thus later we only need
to care about how to iterate all new tree blocks in reloc tree.
Signed-off-by: Qu Wenruo <wqu@suse.com>
[ copy changelog to function comment ]
Signed-off-by: David Sterba <dsterba@suse.com>
Number of qgroup dirty extents is directly linked to the performance
overhead, so add a new trace event, trace_qgroup_num_dirty_extents(), to
record how many dirty extents is processed in
btrfs_qgroup_account_extents().
This will be pretty handy to analyze later balance performance
improvement.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
fs/btrfs/relocation.c:build_backref_tree() is some code from 2009 era,
although it works pretty fine, it's not that easy to understand.
Especially combined with the complex btrfs backref format.
This patch adds some basic comment for the backref build part of the
code, making it less hard to read, at least for backref searching part.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The only aops we define for symlinks are identical to the aops for
regular files. This has been the case since symlink support was added in
commit 2b8d99a723 ("Btrfs: symlinks and hard links"). As far as I can
tell, there wasn't a good reason to have separate aops then, and there
isn't now, so let's just do what most other filesystems do and reuse the
same structure.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During buffered writes, we follow this basic series of steps:
again:
lock all the pages
wait for writeback on all the pages
Take the extent range lock
wait for ordered extents on the whole range
clean all the pages
if (copy_from_user_in_atomic() hits a fault) {
drop our locks
goto again;
}
dirty all the pages
release all the locks
The extra waiting, cleaning and locking are there to make sure we don't
modify pages in flight to the drive, after they've been crc'd.
If some of the pages in the range were already dirty when the write
began, and we need to goto again, we create a window where a dirty page
has been cleaned and unlocked. It may be reclaimed before we're able to
lock it again, which means we'll read the old contents off the drive and
lose any modifications that had been pending writeback.
We don't actually need to clean the pages. All of the other locking in
place makes sure we don't start IO on the pages, so we can just leave
them dirty for the duration of the write.
Fixes: 73d59314e6 (the original btrfs merge)
CC: stable@vger.kernel.org # v4.4+
Signed-off-by: Chris Mason <clm@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The helper does the same math and we take care about the special case
when flags is 0 too.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Refactor the delayed refs loop by using the newly introduced
btrfs_run_delayed_refs_for_head function. This greatly simplifies
__btrfs_run_delayed_refs and makes it more obvious what is happening.
We now have 1 loop which iterates the existing delayed_heads and then
each selected ref head is processed by the new helper. All existing
semantics of the code are preserved so no functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This patch introduces a new helper encompassing the implicit inner loop
in __btrfs_run_delayed_refs which processes all the refs for a given
head. The code is mostly copy/paste, the only difference is that if we
detect a newer reference then -EAGAIN is returned so that callers can
react correctly.
Also, at the end of the loop the head is relocked and
btrfs_merge_delayed_refs is run again to retain the pre-refactoring
semantics.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is in preparation to refactor the giant loop in
__btrfs_run_delayed_refs. As a first step define a new function
which implements acquiring a reference to a btrfs_delayed_refs_head and
use it. No functional changes.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Nikolay Borisov