12 Sep, 2017
1 commit
-
On a senario like writing out the first dirty page of the inode
as the inline data, we only cleared dirty flags of the pages, but
didn't clear the dirty tags of those pages in the radix tree.If we don't clear the dirty tags of the pages in the radix tree, the
inodes which contain the pages will be marked with I_DIRTY_PAGES again
and again, and writepages() for the inodes will be invoked in every
writeback period. As a result, nothing will be done in every
writepages() for the inodes and it will just consume CPU time
meaninglessly.Signed-off-by: Daeho Jeong
Reviewed-by: Chao Yu
Signed-off-by: Jaegeuk Kim
06 Sep, 2017
1 commit
-
This patch replaces (f2fs_encrypted_inode() && S_ISREG()) with
f2fs_encrypted_file(), which gives no functional change.Reviewed-by: Chao Yu
Signed-off-by: Jaegeuk Kim
10 Aug, 2017
1 commit
-
This patch enables inner app/fs io stats and introduces below virtual fs
nodes for exposing stats info:
/sys/fs/f2fs//iostat_enable
/proc/fs/f2fs//iostat_infoSigned-off-by: Chao Yu
[Jaegeuk Kim: fix wrong stat assignment]
Signed-off-by: Jaegeuk Kim
01 Aug, 2017
1 commit
-
This patch tries to make below macros calculating max inline size,
inline dentry field size considerring reserving size-changeable
space:
- MAX_INLINE_DATA
- NR_INLINE_DENTRY
- INLINE_DENTRY_BITMAP_SIZE
- INLINE_RESERVED_SIZEThen, when inline_{data,dentry} options is enabled, it allows us to
reserve inline space with different size flexibly for adding newly
introduced inode attribute.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
27 Jul, 2017
1 commit
-
Use f2fs_dentry_ptr structure to indicate inline dentry structure as
much as possible, so we can wrap inline dentry with size-fixed fields
to the one with size-changeable fields. With this change, we can
handle size-changeable inline dentry more easily.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
04 Jul, 2017
1 commit
-
It is better to use variable name "inline_dentry" instead of "dentry_blk"
when data type is "struct f2fs_inline_dentry". This patch has no functional
changes, just to make code more readable especially when call the function
make_dentry_ptr_inline() and f2fs_convert_inline_dir().Signed-off-by: Tiezhu Yang
Reviewed-by: Chao Yu
Signed-off-by: Jaegeuk Kim
09 May, 2017
1 commit
-
Pull f2fs updates from Jaegeuk Kim:
"In this round, we've focused on enhancing performance with regards to
block allocation, GC, and discard/in-place-update IO controls. There
are a bunch of clean-ups as well as minor bug fixes.Enhancements:
- disable heap-based allocation by default
- issue small-sized discard commands by default
- change the policy of data hotness for logging
- distinguish IOs in terms of size and wbc type
- start SSR earlier to avoid foreground GC
- enhance data structures managing discard commands
- enhance in-place update flow
- add some more fault injection routines
- secure one more xattr entryBug fixes:
- calculate victim cost for GC correctly
- remain correct victim segment number for GC
- race condition in nid allocator and initializer
- stale pointer produced by atomic_writes
- fix missing REQ_SYNC for flush commands
- handle missing errors in more corner cases"* tag 'for-f2fs-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (111 commits)
f2fs: fix a mount fail for wrong next_scan_nid
f2fs: enhance scalability of trace macro
f2fs: relocate inode_{,un}lock in F2FS_IOC_SETFLAGS
f2fs: Make flush bios explicitely sync
f2fs: show available_nids in f2fs/status
f2fs: flush dirty nats periodically
f2fs: introduce CP_TRIMMED_FLAG to avoid unneeded discard
f2fs: allow cpc->reason to indicate more than one reason
f2fs: release cp and dnode lock before IPU
f2fs: shrink size of struct discard_cmd
f2fs: don't hold cmd_lock during waiting discard command
f2fs: nullify fio->encrypted_page for each writes
f2fs: sanity check segment count
f2fs: introduce valid_ipu_blkaddr to clean up
f2fs: lookup extent cache first under IPU scenario
f2fs: reconstruct code to write a data page
f2fs: introduce __wait_discard_cmd
f2fs: introduce __issue_discard_cmd
f2fs: enable small discard by default
f2fs: delay awaking discard thread
...
04 May, 2017
1 commit
-
If user has no key under an encrypted dir, fscrypt gives digested dentries.
Previously, when looking up a dentry, f2fs only checks its hash value with
first 4 bytes of the digested dentry, which didn't handle hash collisions fully.
This patch enhances to check entire dentry bytes likewise ext4.Eric reported how to reproduce this issue by:
# seq -f "edir/abcdefghijklmnopqrstuvwxyz012345%.0f" 100000 | xargs touch
# find edir -type f | xargs stat -c %i | sort | uniq | wc -l
100000
# sync
# echo 3 > /proc/sys/vm/drop_caches
# keyctl new_session
# find edir -type f | xargs stat -c %i | sort | uniq | wc -l
99999Cc:
Reported-by: Eric Biggers
Signed-off-by: Jaegeuk Kim
(fixed f2fs_dentry_hash() to work even when the hash is 0)
Signed-off-by: Eric Biggers
Signed-off-by: Theodore Ts'o
06 Apr, 2017
2 commits
-
Since callers statically know which type to use, make_dentry_ptr()
can simply be splitted into two inline functions. This way, the code
has less inlined, fewer arguments, and no cast.Signed-off-by: Tomohiro Kusumi
Signed-off-by: Jaegeuk Kim -
It would better split small and large IOs separately in order to get more
consecutive big writes.The default threshold is set to 64KB, but configurable by sysfs/min_hot_blocks.
Signed-off-by: Jaegeuk Kim
22 Mar, 2017
2 commits
-
As discuss with Jaegeuk and Chao,
"Once checkpoint is done, f2fs doesn't need to update there-in filename at all."The disk-level filename is used only one case,
1. create a file A under a dir
2. sync A
3. godown
4. umount
5. mount (roll_forward)Only the rename/cross_rename changes the filename, if it happens,
a. between step 1 and 2, the sync A will caused checkpoint, so that,
the roll_forward at step 5 never happens.
b. after step 2, the roll_forward happens, file A will roll forward
to the result as after step 1.So that, any updating the disk filename is useless, just cleanup it.
Signed-off-by: Kinglong Mee
Reviewed-by: Chao Yu
Signed-off-by: Jaegeuk Kim -
Clear FI_DATA_EXIST flag atomically in truncate_inline_inode, and
the return value from truncate_inline_inode isn't used, remove it.Signed-off-by: Kinglong Mee
Signed-off-by: Jaegeuk Kim
15 Dec, 2016
1 commit
-
Pull f2fs updates from Jaegeuk Kim:
"This patch series contains several performance tuning patches
regarding to the IO submission flow, in addition to supporting new
features such as a ZBC-base drive and multiple devices.It also includes some major bug fixes such as:
- checkpoint version control
- fdatasync-related roll-forward recovery routine
- memory boundary or null-pointer access in corner cases
- missing error casesIt has various minor clean-up patches as well"
* tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (66 commits)
f2fs: fix a missing size change in f2fs_setattr
f2fs: fix to access nullified flush_cmd_control pointer
f2fs: free meta pages if sanity check for ckpt is failed
f2fs: detect wrong layout
f2fs: call sync_fs when f2fs is idle
Revert "f2fs: use percpu_counter for # of dirty pages in inode"
f2fs: return AOP_WRITEPAGE_ACTIVATE for writepage
f2fs: do not activate auto_recovery for fallocated i_size
f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
f2fs: fix 32-bit build
f2fs: set ->owner for debugfs status file's file_operations
f2fs: fix incorrect free inode count in ->statfs
f2fs: drop duplicate header timer.h
f2fs: fix wrong AUTO_RECOVER condition
f2fs: do not recover i_size if it's valid
f2fs: fix fdatasync
f2fs: fix to account total free nid correctly
f2fs: fix an infinite loop when flush nodes in cp
f2fs: don't wait writeback for datas during checkpoint
f2fs: fix wrong written_valid_blocks counting
...
24 Nov, 2016
4 commits
-
Report error of f2fs_fill_dentries to ->iterate_shared, otherwise when
error ocurrs, user may just list part of dirents in target directory
without any hints.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim -
This is to avoid no free segment bug during checkpoint caused by a number of
dirty inodes.The case was reported by Chao like this.
1. mount with lazytime option
2. fill 4k file until disk is full
3. sync filesystem
4. read all files in the image
5. umountIn this case, we actually don't need to flush dirty inode to inode page during
checkpoint.Reviewed-by: Chao Yu
Signed-off-by: Jaegeuk Kim -
f2fs contained a number of endianness conversion bugs.
Also, one function should have been 'static'.
Found with sparse by running 'make C=2 CF=-D__CHECK_ENDIAN__ fs/f2fs/'
Signed-off-by: Eric Biggers
Signed-off-by: Jaegeuk Kim -
If there is no dirty pages in inode, we should give a chance to detach
the inode from global dirty list, otherwise it needs to call another
unnecessary .writepages for detaching.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
01 Nov, 2016
1 commit
-
Remove the WRITE_* and READ_SYNC wrappers, and just use the flags
directly. Where applicable this also drops usage of the
bio_set_op_attrs wrapper.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
11 Oct, 2016
1 commit
-
Pull more vfs updates from Al Viro:
">rename2() work from Miklos + current_time() from Deepa"* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
fs: Replace current_fs_time() with current_time()
fs: Replace CURRENT_TIME_SEC with current_time() for inode timestamps
fs: Replace CURRENT_TIME with current_time() for inode timestamps
fs: proc: Delete inode time initializations in proc_alloc_inode()
vfs: Add current_time() api
vfs: add note about i_op->rename changes to porting
fs: rename "rename2" i_op to "rename"
vfs: remove unused i_op->rename
fs: make remaining filesystems use .rename2
libfs: support RENAME_NOREPLACE in simple_rename()
fs: support RENAME_NOREPLACE for local filesystems
ncpfs: fix unused variable warning
01 Oct, 2016
1 commit
-
Previously, we only support global fault injection configuration, so that
when we configure type/rate of fault injection through sysfs, mount
option, it will influence all f2fs partition which is being used.It is not make sence, since it will be not convenient if developer want
to test separated partitions with different fault injection rate/type
simultaneously, also it's not possible to enable fault injection in one
partition and disable fault injection in other one.>From now on, we move global configuration of fault injection in module
into per-superblock, hence injection testing can be more flexible.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
28 Sep, 2016
1 commit
-
CURRENT_TIME macro is not appropriate for filesystems as it
doesn't use the right granularity for filesystem timestamps.
Use current_time() instead.CURRENT_TIME is also not y2038 safe.
This is also in preparation for the patch that transitions
vfs timestamps to use 64 bit time and hence make them
y2038 safe. As part of the effort current_time() will be
extended to do range checks. Hence, it is necessary for all
file system timestamps to use current_time(). Also,
current_time() will be transitioned along with vfs to be
y2038 safe.Note that whenever a single call to current_time() is used
to change timestamps in different inodes, it is because they
share the same time granularity.Signed-off-by: Deepa Dinamani
Reviewed-by: Arnd Bergmann
Acked-by: Felipe Balbi
Acked-by: Steven Whitehouse
Acked-by: Ryusuke Konishi
Acked-by: David Sterba
Signed-off-by: Al Viro
08 Sep, 2016
3 commits
-
This fixes pointer panic when using inline_dentry, which was triggered when
backporting to 3.10.Signed-off-by: Jaegeuk Kim
-
This patch sets encryption name flag in the add inline entry path
if filename is encrypted.Signed-off-by: Shuoran Liu
Signed-off-by: Jaegeuk Kim -
When creating new inode, security_inode_init_security will be called for
initializing security info related to the inode, and filename is passed to
security module, it helps security module such as SElinux to know which
rule or label could be applied for the inode with specified name.Previously, if new inode is created as an encrypted one, f2fs will transfer
encrypted filename to security module which may fail the check of security
policy belong to the inode. So in order to this issue, alter to transfer
original unencrypted filename instead.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
28 Jul, 2016
1 commit
-
Pull f2fs updates from Jaegeuk Kim:
"The major change in this version is mitigating cpu overheads on write
paths by replacing redundant inode page updates with mark_inode_dirty
calls. And we tried to reduce lock contentions as well to improve
filesystem scalability. Other feature is setting F2FS automatically
when detecting host-managed SMR.Enhancements:
- ioctl to move a range of data between files
- inject orphan inode errors
- avoid flush commands congestion
- support lazytimeBug fixes:
- return proper results for some dentry operations
- fix deadlock in add_link failure
- disable extent_cache for fcollapse/finsert"* tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
f2fs: clean up coding style and redundancy
f2fs: get victim segment again after new cp
f2fs: handle error case with f2fs_bug_on
f2fs: avoid data race when deciding checkpoin in f2fs_sync_file
f2fs: support an ioctl to move a range of data blocks
f2fs: fix to report error number of f2fs_find_entry
f2fs: avoid memory allocation failure due to a long length
f2fs: reset default idle interval value
f2fs: use blk_plug in all the possible paths
f2fs: fix to avoid data update racing between GC and DIO
f2fs: add maximum prefree segments
f2fs: disable extent_cache for fcollapse/finsert inodes
f2fs: refactor __exchange_data_block for speed up
f2fs: fix ERR_PTR returned by bio
f2fs: avoid mark_inode_dirty
f2fs: move i_size_write in f2fs_write_end
f2fs: fix to avoid redundant discard during fstrim
f2fs: avoid mismatching block range for discard
f2fs: fix incorrect f_bfree calculation in ->statfs
f2fs: use percpu_rw_semaphore
...
09 Jul, 2016
2 commits
-
Let's check inode's dirtiness before calling mark_inode_dirty.
Signed-off-by: Jaegeuk Kim
-
SetPageUptodate() issues memory barrier, resulting in performance degrdation.
Let's avoid that.Signed-off-by: Jaegeuk Kim
16 Jun, 2016
1 commit
-
If dotdot directory is corrupted, its slot may be ocupied by another
file. In this case, dentry[1] is not the parent directory. Rename and
cross-rename will update the inode in dentry[1] incorrectly. This
patch finds dotdot dentry by name.Signed-off-by: Sheng Yong
[Jaegeuk Kim: remove wron bug_on]
Signed-off-by: Jaegeuk Kim
08 Jun, 2016
2 commits
-
Separate the op from the rq_flag_bits and have f2fs
set/get the bio using bio_set_op_attrs/bio_op.Signed-off-by: Mike Christie
Reviewed-by: Christoph Hellwig
Reviewed-by: Hannes Reinecke
Signed-off-by: Jens Axboe -
Remove deprecated paramter.
Signed-off-by: Jaegeuk Kim
03 Jun, 2016
5 commits
-
If we get ENOMEM or EIO in f2fs_find_entry, we should stop right away.
Otherwise, for example, we can get duplicate directory entry by ->chash and
->clevel.Signed-off-by: Jaegeuk Kim
-
This patch reduces to call them across the whole tree.
- sync_inode_page()
- update_inode_page()
- update_inode()
- f2fs_write_inode()Instead, checkpoint will flush all the dirty inode metadata before syncing
node pages.
Note that, this is doable, since we call mark_inode_dirty_sync() for all
inode's field change which needs to update on-disk inode as well.Signed-off-by: Jaegeuk Kim
-
This patch calls mark_inode_dirty_sync() for the following on-disk inode
changes.-> largest
-> ctime/mtime/atime
-> i_current_depth
-> i_xattr_nid
-> i_pino
-> i_advise
-> i_flags
-> i_modeSigned-off-by: Jaegeuk Kim
-
This patch introduces f2fs_i_size_write() to call mark_inode_dirty_sync() with
i_size_write().Signed-off-by: Jaegeuk Kim
-
This patch refactors to use inode pointer for set_inode_flag and
clear_inode_flag.Signed-off-by: Jaegeuk Kim
17 May, 2016
2 commits
-
Fix two bugs in error path of f2fs_move_rehashed_dirents:
- release dir's inode page if fail to call kmalloc
- recover i_current_depth if fail to convertingSigned-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim -
With below steps, we will see that dentry page becoming unaccessable later.
This is because we forget updating i_current_depth in inode during inline
dentry conversion, after that, once we failed at somewhere, it will leave
i_current_depth as 0 in non-inline directory. Then, during ->lookup, the
current_depth value makes all dentry pages in first level invisible. Fix
it.1) mount f2fs with inline_dentry option
2) mkdir dir
3) touch 180 files named [0-179] in dir
4) touch 180 in dir (fail after inline dir conversion)
5) ll dirls: cannot access /mnt/f2fs/dir/0: No such file or directory
ls: cannot access /mnt/f2fs/dir/1: No such file or directory
ls: cannot access /mnt/f2fs/dir/2: No such file or directory
ls: cannot access /mnt/f2fs/dir/3: No such file or directory
ls: cannot access /mnt/f2fs/dir/4: No such file or directorydrwxr-xr-x 2 root root 4096 may 13 21:47 ./
drwxr-xr-x 3 root root 4096 may 13 21:46 ../
-????????? ? ? ? ? ? 0
-????????? ? ? ? ? ? 1
-????????? ? ? ? ? ? 10
-????????? ? ? ? ? ? 100
-????????? ? ? ? ? ? 101
-????????? ? ? ? ? ? 102Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
08 May, 2016
2 commits
-
This patch converts grab_cache_page to f2fs_grab_cache_page.
Signed-off-by: Jaegeuk Kim
-
This patch adds f2fs_kmalloc.
Signed-off-by: Jaegeuk Kim
28 Apr, 2016
1 commit
-
The filename length in dirent of may become zero-sized after random junk
data injection, once encounter such dirent, find_target_dentry or
f2fs_add_inline_entries will run into an infinite loop. So let f2fs being
aware of that to avoid deadloop.Signed-off-by: Chao Yu
Signed-off-by: Jaegeuk Kim
