Since check_eofblocks_fl() only uses the m_lblk portion of the map
structure, we may as well pass that directly, rather than passing the
entire map, which IMHO obfuscates what parameters check_eofblocks_fl()
cares about. Not a big deal, but seems tidier and less confusing, to
me.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Commit 40389687 moved a call to ext4_forget() out of
ext4_free_branches and let ext4_free_blocks() handle calling
bforget(). But that change unfortunately did not replace the call to
ext4_forget() with brelse(), which was needed to drop the in-use count
of the indirect block's buffer head, which lead to a memory leak when
deleting files that used indirect blocks. Fix this.
Thanks to Hugh Dickins for pointing this out.
Cc: stable@kernel.org
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
This function was never implemented, except for a BUG_ON which was
tripping when ext4 is run without a journal. The problem is that
although the comment asserts that "truncate (which is the only way to
free block) discards all preallocations", ext4_free_blocks() is also
called in various error recovery paths when blocks have been
allocated, but for various reasons, we were not able to use those data
blocks (for example, because we ran out of memory while trying to
manipulate the extent tree, or some other similar situation).
In addition to the fact that this function isn't implemented except
for the incorrect BUG_ON, the single caller of this function,
ext4_free_blocks(), doesn't use it all if the journal is enabled.
So remove the (stub) function entirely for now. If we decide it's
better to add it back, it's only going to be useful with a relatively
large number of code changes anyway.
Google-Bug-Id: 3236408
Cc: Jiaying Zhang <jiayingz@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Ted first found the bug when running 2.6.36 kernel with dioread_nolock
mount option that xfstests #13 complained about wrong file size during fsck.
However, the bug exists in the older kernels as well although it is
somehow harder to trigger.
The problem is that ext4_end_io_work() can happen after we have truncated an
inode to a smaller size. Then when ext4_end_io_work() calls
ext4_convert_unwritten_extents(), we may reallocate some blocks that have
been truncated, so the inode size becomes inconsistent with the allocated
blocks.
The following patch flushes the i_completed_io_list during truncate to reduce
the risk that some pending end_io requests are executed later and convert
already truncated blocks to initialized.
Note that although the fix helps reduce the problem a lot there may still
be a race window between vmtruncate() and ext4_end_io_work(). The fundamental
problem is that if vmtruncate() is called without either i_mutex or i_alloc_sem
held, it can race with an ongoing write request so that the io_end request is
processed later when the corresponding blocks have been truncated.
Ted and I have discussed the problem offline and we saw a few ways to fix
the race completely:
a) We guarantee that i_mutex lock and i_alloc_sem write lock are both hold
whenever vmtruncate() is called. The i_mutex lock prevents any new write
requests from entering writeback and the i_alloc_sem prevents the race
from ext4_page_mkwrite(). Currently we hold both locks if vmtruncate()
is called from do_truncate(), which is probably the most common case.
However, there are places where we may call vmtruncate() without holding
either i_mutex or i_alloc_sem. I would like to ask for other people's
opinions on what locks are expected to be held before calling vmtruncate().
There seems a disagreement among the callers of that function.
b) We change the ext4 write path so that we change the extent tree to contain
the newly allocated blocks and update i_size both at the same time --- when
the write of the data blocks is completed.
c) We add some additional locking to synchronize vmtruncate() and
ext4_end_io_work(). This approach may have performance implications so we
need to be careful.
All of the above proposals may require more substantial changes, so
we may consider to take the following patch as a bandaid.
Signed-off-by: Jiaying Zhang <jiayingz@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Call ext4_std_error() in various places when we can't bail out
cleanly, so the file system can be marked as in error.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
When ext4_trim_fs() is called to trim a part of a single group, the
logic will wrongly set last block of the interval to 'len' instead
of 'first_block + len'. Thus a shorter interval is possibly trimmed.
Fix it.
CC: Lukas Czerner <lczerner@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
fs/ext4/super.c: In function 'ext4_register_li_request':
fs/ext4/super.c:2936: warning: 'ret' may be used uninitialized in this function
It looks buggy to me, too.
Cc: Lukas Czerner <lczerner@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Replace the jbd2_inode structure (which is 48 bytes) with a pointer
and only allocate the jbd2_inode when it is needed --- that is, when
the file system has a journal present and the inode has been opened
for writing. This allows us to further slim down the ext4_inode_info
structure.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
We can store the dynamic inode state flags in the high bits of
EXT4_I(inode)->i_flags, and eliminate i_state_flags. This saves 8
bytes from the size of ext4_inode_info structure, which when
multiplied by the number of the number of in the inode cache, can save
a lot of memory.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
By reordering the elements in the ext4_inode_info structure, we can
reduce the padding needed on an x86_64 system by 16 bytes.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
We can encode the ec_type information by using ee_len == 0 to denote
EXT4_EXT_CACHE_NO, ee_start == 0 to denote EXT4_EXT_CACHE_GAP, and if
neither is true, then the cache type must be EXT4_EXT_CACHE_EXTENT.
This allows us to reduce the size of ext4_ext_inode by another 8
bytes. (ec_type is 4 bytes, plus another 4 bytes of padding)
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
This fixes a number of places where we used sector_t instead of
ext4_lblk_t for logical blocks, which for ext4 are still 32-bit data
types. No point wasting space in the ext4_inode_info structure, and
requiring 64-bit arithmetic on 32-bit systems, when it isn't
necessary.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Remove the short element i_delalloc_reserved_flag from the
ext4_inode_info structure and replace it a new bit in i_state_flags.
Since we have an ext4_inode_info for every ext4 inode cached in the
inode cache, any savings we can produce here is a very good thing from
a memory utilization perspective.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
ext4_ext_find_goal() returns an ideal physical block number that the block
allocator tries to allocate first. However, if a required file offset is
smaller than the existing extent's one, ext4_ext_find_goal() returns
a wrong block number because it may overflow at
"block - le32_to_cpu(ex->ee_block)". This patch fixes the problem.
ext4_ext_find_goal() will also return a wrong block number in case
a file offset of the existing extent is too big. In this case,
the ideal physical block number is fixed in ext4_mb_initialize_context(),
so it's no problem.
reproduce:
# dd if=/dev/zero of=/mnt/mp1/tmp bs=127M count=1 oflag=sync
# dd if=/dev/zero of=/mnt/mp1/file bs=512K count=1 seek=1 oflag=sync
# filefrag -v /mnt/mp1/file
Filesystem type is: ef53
File size of /mnt/mp1/file is 1048576 (256 blocks, blocksize 4096)
ext logical physical expected length flags
0 128 67456 128 eof
/mnt/mp1/file: 2 extents found
# rm -rf /mnt/mp1/tmp
# echo $((512*4096)) > /sys/fs/ext4/loop0/mb_stream_req
# dd if=/dev/zero of=/mnt/mp1/file bs=512K count=1 oflag=sync conv=notrunc
result (linux-2.6.37-rc2 + ext4 patch queue):
# filefrag -v /mnt/mp1/file
Filesystem type is: ef53
File size of /mnt/mp1/file is 1048576 (256 blocks, blocksize 4096)
ext logical physical expected length flags
0 0 33280 128
1 128 67456 33407 128 eof
/mnt/mp1/file: 2 extents found
result(apply this patch):
# filefrag -v /mnt/mp1/file
Filesystem type is: ef53
File size of /mnt/mp1/file is 1048576 (256 blocks, blocksize 4096)
ext logical physical expected length flags
0 0 66560 128
1 128 67456 66687 128 eof
/mnt/mp1/file: 2 extents found
Signed-off-by: Kazuya Mio <k-mio@sx.jp.nec.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Check return value of ext4_journal_get_write_access,
ext4_journal_dirty_metadata and ext4_mark_inode_dirty. Move brelse()
under 'out_stop' to release bh properly in case of journal error.
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
ext4_ext_migrate() calls ext4_new_inode() and passes 0 instead of a pointer
to a struct qstr. This patch uses NULL, to make it obvious to the caller
that this was a pointer.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
d_path() returns an ERR_PTR and it doesn't return NULL. This is in
ext4_error_file() and no one actually calls ext4_error_file().
Signed-off-by: Dan Carpenter <error27@gmail.com>
This is a copy and paste error. The intent was to check
"io_page_cachep". We tested "io_page_cachep" earlier.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
ext4_issue_discard is supposed to be helper for calling discard, however
in case that underlying device does not support discard it prints out
the warning message and clears the DISCARD t_mount_opt flag. Since it
can be (and is) used by others, it should not do anything and let the
caller to handle the error case.
This commit removes warning message and flag setting from
ext4_issue_discard and use it just in place where it is really needed
(release_blocks_on_commit). FITRIM ioctl should not set any flags nor it
should print out warning messages, so get rid of the warning as well.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
When determining last group through ext4_get_group_no_and_offset() the
result may be wrong in cases when range->start and range-len are too
big, because it may overflow when summing up those two numbers.
Fix that by checking range->len and limit its value to
ext4_blocks_count(). This commit was tested by myself with expected
result.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Remove kobject.h from files which don't need it, notably,
sched.h and fs.h.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ryusuke/nilfs2:
nilfs2: unfold nilfs_dat_inode function
nilfs2: do not pass sbi to functions which can get it from inode
nilfs2: get rid of nilfs_mount_options structure
nilfs2: simplify nilfs_mdt_freeze_buffer
nilfs2: get rid of loaded flag from nilfs object
nilfs2: fix a checkpatch error in page.c
nilfs2: fiemap support
nilfs2: mark buffer heads as delayed until the data is written to disk
nilfs2: call nilfs_error inside bmap routines
fs/nilfs2/super.c: Use printf extension %pV
MAINTAINERS: add nilfs2 git tree entry
* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6:
cifs: use CreationTime like an i_generation field
cifs: switch cifs_open and cifs_create to use CIFSSMBUnixSetFileInfo
cifs: show "acl" in DebugData Features when it's compiled in
cifs: move "ntlmssp" and "local_leases" options out of experimental code
cifs: replace some hardcoded values with preprocessor constants
cifs: remove unnecessary locking around sequence_number
[CIFS] Fix minor merge conflict in fs/cifs/dir.c
CIFS: Simplify cifs_open code
CIFS: Simplify non-posix open stuff (try #2)
CIFS: Add match_port check during looking for an existing connection (try #4)
CIFS: Simplify ipv*_connect functions into one (try #4)
cifs: Support NTLM2 session security during NTLMSSP authentication [try #5]
cifs: don't overwrite dentry name in d_revalidate
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/dlm:
dlm: sanitize work_start() in lowcomms.c
dlm: reduce cond_resched during send
dlm: use TCP_NODELAY
dlm: Use cmwq for send and receive workqueues
dlm: Handle application limited situations properly.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
fuse: fix ioctl ABI
fuse: allow batching of FORGET requests
fuse: separate queue for FORGET requests
fuse: ioctl cleanup
Fix up trivial conflict in fs/fuse/inode.c due to RCU lookup having done
the RCU-freeing of the inode in fuse_destroy_inode().
Fix new kernel-doc notation warnings in fs/namei.c and spell
ECHILD correctly.
Warning(fs/namei.c:218): No description found for parameter 'flags'
Warning(fs/namei.c:425): Excess function parameter 'Returns' description in 'nameidata_drop_rcu'
Warning(fs/namei.c:478): Excess function parameter 'Returns' description in 'nameidata_dentry_drop_rcu'
Warning(fs/namei.c:540): Excess function parameter 'Returns' description in 'nameidata_drop_rcu_last'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
nilfs_dat_inode function was a wrapper to switch between normal dat
inode and gcdat, a clone of the dat inode for garbage collection.
This function got obsolete when the gcdat inode was removed, and now
we can access the dat inode directly from a nilfs object. So, we will
unfold the wrapper and remove it.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This removes argument for passing nilfs_sb_info structure from
nilfs_set_file_dirty and nilfs_load_inode_block functions. We can get
a pointer to the structure from inodes.
[Stephen Rothwell <sfr@canb.auug.org.au>: fix conflict with commit
b74c79e993]
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Only mount_opt member is used in the nilfs_mount_options structure,
and we can simplify it.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
nilfs_page_get_nth_block() function used in nilfs_mdt_freeze_buffer()
always returns a valid buffer head, so its validity check can be
removed.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
This adds fiemap to nilfs. Two new functions, nilfs_fiemap and
nilfs_find_uncommitted_extent are added.
nilfs_fiemap() implements the fiemap inode operation, and
nilfs_find_uncommitted_extent() helps to get a range of data blocks
whose physical location has not been determined.
nilfs_fiemap() collects extent information by looping through
nilfs_bmap_lookup_contig and nilfs_find_uncommitted_extent routines.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Nilfs does not allocate new blocks on disk until they are actually
written to. To implement fiemap, we need to deal with such blocks.
To allow successive fiemap patch to distinguish mapped but unallocated
regions, this marks buffer heads of those new blocks as delayed and
clears the flag after the blocks are written to disk.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Some functions using nilfs bmap routines can wrongly return invalid
argument error (i.e. -EINVAL) that bmap returns as an internal code
for btree corruption.
This fixes the issue by catching and converting the internal EINVAL to
EIO and calling nilfs_error function inside bmap routines.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Using %pV reduces the number of printk calls and
eliminates any possible message interleaving from
other printk calls.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Reduce false inode collisions by using the CreationTime like an
i_generation field. This way, even if the server ends up reusing
a uniqueid after a delete/create cycle, we can avoid matching
the inode incorrectly.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
We call CIFSSMBUnixSetPathInfo in these functions, but we have a
filehandle since an open was just done. Switch these functions to
use CIFSSMBUnixSetFileInfo instead.
In practice, these codepaths are only used if posix opens are broken.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
...and while we're at it, reduce the number of calls into the seq_*
functions by prepending spaces to strings.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
I see no real need to leave these sorts of options under an
EXPERIMENTAL ifdef. Since you need a mount option to turn this code
on, that only blows out the testing matrix.
local_leases has been under the EXPERIMENTAL tag for some time, but
it's only the mount option that's under this label. Move it out
from under this tag.
The NTLMSSP code is also under EXPERIMENTAL, but it needs a mount
option to turn it on, and in the future any distro will reasonably
want this enabled. Go ahead and move it out from under the
EXPERIMENTAL tag.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Acked-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Steve French <sfrench@us.ibm.com>
A number of places that deal with RFC1001/1002 negotiations have bare
"15" or "16" values. Replace them with RFC_1001_NAME_LEN and
RFC_1001_NAME_LEN_WITH_NULL.
The patch also cleans up some checkpatch warnings for code surrounding
the changes. This should apply cleanly on top of the patch to remove
Local_System_Name.
Reported-and-Reviwed-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
The server->sequence_number is already protected by the srv_mutex. The
GlobalMid_lock is unneeded here.
Reviewed-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Tristan Ye has done some refactoring against our truncate
process, so some functions like ocfs2_prepare_truncate and
ocfs2_free_truncate_context are no use and we'd better
remove them.
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
In the original code, we dereferenced "nst" before checking that it was
non-NULL. I moved the check forward and pulled the code in an indent
level.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
When CONFIG_OCFS2_FS_STATS is not enabled:
fs/ocfs2/cluster/tcp.c:1254: error: implicit declaration of function 'o2net_update_recv_stats'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <joel.becker@oracle.com>
Cc: ocfs2-devel@oss.oracle.com
Signed-off-by: Joel Becker <joel.becker@oracle.com>
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/hch/hfsplus:
hfsplus: %L-to-%ll, macro correction, and remove unneeded braces
hfsplus: spaces/indentation clean-up
hfsplus: C99 comments clean-up
hfsplus: over 80 character lines clean-up
hfsplus: fix an artifact in ioctl flag checking
hfsplus: flush disk caches in sync and fsync
hfsplus: optimize fsync
hfsplus: split up inode flags
hfsplus: write up fsync for directories
hfsplus: simplify fsync
hfsplus: avoid useless work in hfsplus_sync_fs
hfsplus: make sure sync writes out all metadata
hfsplus: use raw bio access for partition tables
hfsplus: use raw bio access for the volume headers
hfsplus: always use hfsplus_sync_fs to write the volume header
hfsplus: silence a few debug printks
hfsplus: fix option parsing during remount
Fix up conflicts due to VFS changes in fs/hfsplus/{hfsplus_fs.h,unicode.c}
* 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (30 commits)
gameport: use this_cpu_read instead of lookup
x86: udelay: Use this_cpu_read to avoid address calculation
x86: Use this_cpu_inc_return for nmi counter
x86: Replace uses of current_cpu_data with this_cpu ops
x86: Use this_cpu_ops to optimize code
vmstat: User per cpu atomics to avoid interrupt disable / enable
irq_work: Use per cpu atomics instead of regular atomics
cpuops: Use cmpxchg for xchg to avoid lock semantics
x86: this_cpu_cmpxchg and this_cpu_xchg operations
percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support
percpu,x86: relocate this_cpu_add_return() and friends
connector: Use this_cpu operations
xen: Use this_cpu_inc_return
taskstats: Use this_cpu_ops
random: Use this_cpu_inc_return
fs: Use this_cpu_inc_return in buffer.c
highmem: Use this_cpu_xx_return() operations
vmstat: Use this_cpu_inc_return for vm statistics
x86: Support for this_cpu_add, sub, dec, inc_return
percpu: Generic support for this_cpu_add, sub, dec, inc_return
...
Fixed up conflicts: in arch/x86/kernel/{apic/nmi.c, apic/x2apic_uv_x.c, process.c}
as per Tejun.
* 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (33 commits)
usb: don't use flush_scheduled_work()
speedtch: don't abuse struct delayed_work
media/video: don't use flush_scheduled_work()
media/video: explicitly flush request_module work
ioc4: use static work_struct for ioc4_load_modules()
init: don't call flush_scheduled_work() from do_initcalls()
s390: don't use flush_scheduled_work()
rtc: don't use flush_scheduled_work()
mmc: update workqueue usages
mfd: update workqueue usages
dvb: don't use flush_scheduled_work()
leds-wm8350: don't use flush_scheduled_work()
mISDN: don't use flush_scheduled_work()
macintosh/ams: don't use flush_scheduled_work()
vmwgfx: don't use flush_scheduled_work()
tpm: don't use flush_scheduled_work()
sonypi: don't use flush_scheduled_work()
hvsi: don't use flush_scheduled_work()
xen: don't use flush_scheduled_work()
gdrom: don't use flush_scheduled_work()
...
Fixed up trivial conflict in drivers/media/video/bt8xx/bttv-input.c
as per Tejun.
* 'tty-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty-2.6: (36 commits)
serial: apbuart: Fixup apbuart_console_init()
TTY: Add tty ioctl to figure device node of the system console.
tty: add 'active' sysfs attribute to tty0 and console device
drivers: serial: apbuart: Handle OF failures gracefully
Serial: Avoid unbalanced IRQ wake disable during resume
tty: fix typos/errors in tty_driver.h comments
pch_uart : fix warnings for 64bit compile
8250: fix uninitialized FIFOs
ip2: fix compiler warning on ip2main_pci_tbl
specialix: fix compiler warning on specialix_pci_tbl
rocket: fix compiler warning on rocket_pci_ids
8250: add a UPIO_DWAPB32 for 32 bit accesses
8250: use container_of() instead of casting
serial: omap-serial: Add support for kernel debugger
serial: fix pch_uart kconfig & build
drivers: char: hvc: add arm JTAG DCC console support
RS485 documentation: add 16C950 UART description
serial: ifx6x60: fix memory leak
serial: ifx6x60: free IRQ on error
Serial: EG20T: add PCH_UART driver
...
Fixed up conflicts in drivers/serial/apbuart.c with evil merge that
makes the code look fairly sane (unlike either side).
The problem that this patch aims to fix is vfsmount refcounting scalability.
We need to take a reference on the vfsmount for every successful path lookup,
which often go to the same mount point.
The fundamental difficulty is that a "simple" reference count can never be made
scalable, because any time a reference is dropped, we must check whether that
was the last reference. To do that requires communication with all other CPUs
that may have taken a reference count.
We can make refcounts more scalable in a couple of ways, involving keeping
distributed counters, and checking for the global-zero condition less
frequently.
- check the global sum once every interval (this will delay zero detection
for some interval, so it's probably a showstopper for vfsmounts).
- keep a local count and only taking the global sum when local reaches 0 (this
is difficult for vfsmounts, because we can't hold preempt off for the life of
a reference, so a counter would need to be per-thread or tied strongly to a
particular CPU which requires more locking).
- keep a local difference of increments and decrements, which allows us to sum
the total difference and hence find the refcount when summing all CPUs. Then,
keep a single integer "long" refcount for slow and long lasting references,
and only take the global sum of local counters when the long refcount is 0.
This last scheme is what I implemented here. Attached mounts and process root
and working directory references are "long" references, and everything else is
a short reference.
This allows scalable vfsmount references during path walking over mounted
subtrees and unattached (lazy umounted) mounts with processes still running
in them.
This results in one fewer atomic op in the fastpath: mntget is now just a
per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock
and non-atomic decrement in the common case. However code is otherwise bigger
and heavier, so single threaded performance is basically a wash.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Suggested by Andreas, mnt_ prefix is clearer namespace, follows kernel
conventions better, and is easier for tab complete. I introduced these
names so I'll admit they were not good choices.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
The standard memcmp function on a Westmere system shows up hot in
profiles in the `git diff` workload (both parallel and single threaded),
and it is likely due to the costs associated with trapping into
microcode, and little opportunity to improve memory access (dentry
name is not likely to take up more than a cacheline).
So replace it with an open-coded byte comparison. This increases code
size by 8 bytes in the critical __d_lookup_rcu function, but the
speedup is huge, averaging 10 runs of each:
git diff st user sys elapsed CPU
before 1.15 2.57 3.82 97.1
after 1.14 2.35 3.61 96.8
git diff mt user sys elapsed CPU
before 1.27 3.85 1.46 349
after 1.26 3.54 1.43 333
Elapsed time for single threaded git diff at 95.0% confidence:
-0.21 +/- 0.01
-5.45% +/- 0.24%
It's -0.66% +/- 0.06% elapsed time on my Opteron, so rep cmp costs on the
fam10h seem to be relatively smaller, but there is still a win.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This makes single threaded git diff -1.25% +/- 0.05% elapsed time on my
2s12c24t Westmere system, and -0.86% +/- 0.05% on my 2s8c Barcelona, by
prefetching the important first cacheline of the inode in while we do the
actual name compare and other operations on the dentry.
There was no measurable slowdown in the single file stat case, or the creat
case (where negative dentries would be common).
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Regardless of how much we possibly try to scale dcache, there is likely
always going to be some fundamental contention when adding or removing children
under the same parent. Pseudo filesystems do not seem need to have connected
dentries because by definition they are disconnected.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
dcache_inode_lock can be replaced with per-inode locking. Use existing
inode->i_lock for this. This is slightly non-trivial because we sometimes
need to find the inode from the dentry, which requires d_inode to be
stabilised (either with refcount or d_lock).
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This simple implementation just checks for no ACLs on the inode, and
if so, then the rcu-walk may proceed, otherwise fail it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This simple implementation just checks for no ACLs on the inode, and
if so, then the rcu-walk may proceed, otherwise fail it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This simple implementation just checks for no ACLs on the inode, and
if so, then the rcu-walk may proceed, otherwise fail it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
This simple implementation just checks for no ACLs on the inode, and
if so, then the rcu-walk may proceed, otherwise fail it.
This could easily be extended to put acls under RCU and check them
under seqlock, if need be. But this implementation is enough to show
the rcu-walk aware permissions code for path lookups is working, and
will handle cases where there are no ACLs or ACLs in just the final
element.
This patch implicity converts tmpfs to rcu-aware permission check.
Subsequent patches onvert ext*, xfs, and, btrfs. Each of these uses
acl/permission code in a different way, so convert them all to provide
templates and proof of concept.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Require filesystems be aware of .d_revalidate being called in rcu-walk
mode (nd->flags & LOOKUP_RCU). For now do a simple push down, returning
-ECHILD from all implementations.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Put dentry and inode fields into top of data structure. This allows RCU path
traversal to perform an RCU dentry lookup in a path walk by touching only the
first 56 bytes of the dentry.
We also fit in 8 bytes of inline name in the first 64 bytes, so for short
names, only 64 bytes needs to be touched to perform the lookup. We should
get rid of the hash->prev pointer from the first 64 bytes, and fit 16 bytes
of name in there, which will take care of 81% rather than 32% of the kernel
tree.
inode is also rearranged so that RCU lookup will only touch a single cacheline
in the inode, plus one in the i_ops structure.
This is important for directory component lookups in RCU path walking. In the
kernel source, directory names average is around 6 chars, so this works.
When we reach the last element of the lookup, we need to lock it and take its
refcount which requires another cacheline access.
Align dentry and inode operations structs, so members will be at predictable
offsets and we can group common operations into head of structure.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Reduce some branches and memory accesses in dcache lookup by adding dentry
flags to indicate common d_ops are set, rather than having to check them.
This saves a pointer memory access (dentry->d_op) in common path lookup
situations, and saves another pointer load and branch in cases where we
have d_op but not the particular operation.
Patched with:
git grep -E '[.>]([[:space:]])*d_op([[:space:]])*=' | xargs sed -e 's/\([^\t ]*\)->d_op = \(.*\);/d_set_d_op(\1, \2);/' -e 's/\([^\t ]*\)\.d_op = \(.*\);/d_set_d_op(\&\1, \2);/' -i
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Rather than keep a d_mounted count in the dentry, set a dentry flag instead.
The flag can be cleared by checking the hash table to see if there are any
mounts left, which is not time critical because it is performed at detach time.
The mounted state of a dentry is only used to speculatively take a look in the
mount hash table if it is set -- before following the mount, vfsmount lock is
taken and mount re-checked without races.
This saves 4 bytes on 32-bit, nothing on 64-bit but it does provide a hole I
might use later (and some configs have larger than 32-bit spinlocks which might
make use of the hole).
Autofs4 conversion and changelog by Ian Kent <raven@themaw.net>:
In autofs4, when expring direct (or offset) mounts we need to ensure that we
block user path walks into the autofs mount, which is covered by another mount.
To do this we clear the mounted status so that follows stop before walking into
the mount and are essentially blocked until the expire is completed. The
automount daemon still finds the correct dentry for the umount due to the
follow mount logic in fs/autofs4/root.c:autofs4_follow_link(), which is set as
an inode operation for direct and offset mounts only and is called following
the lookup that stopped at the covered mount.
At the end of the expire the covering mount probably has gone away so the
mounted status need not be restored. But we need to check this and only restore
the mounted status if the expire failed.
XXX: autofs may not work right if we have other mounts go over the top of it?
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Use a seqlock in the fs_struct to enable us to take an atomic copy of the
complete cwd and root paths. Use this in the RCU lookup path to avoid a
thread-shared spinlock in RCU lookup operations.
Multi-threaded apps may now perform path lookups with scalability matching
multi-process apps. Operations such as stat(2) become very scalable for
multi-threaded workload.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Perform common cases of path lookups without any stores or locking in the
ancestor dentry elements. This is called rcu-walk, as opposed to the current
algorithm which is a refcount based walk, or ref-walk.
This results in far fewer atomic operations on every path element,
significantly improving path lookup performance. It also avoids cacheline
bouncing on common dentries, significantly improving scalability.
The overall design is like this:
* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk.
* Take the RCU lock for the entire path walk, starting with the acquiring
of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are
not required for dentry persistence.
* synchronize_rcu is called when unregistering a filesystem, so we can
access d_ops and i_ops during rcu-walk.
* Similarly take the vfsmount lock for the entire path walk. So now mnt
refcounts are not required for persistence. Also we are free to perform mount
lookups, and to assume dentry mount points and mount roots are stable up and
down the path.
* Have a per-dentry seqlock to protect the dentry name, parent, and inode,
so we can load this tuple atomically, and also check whether any of its
members have changed.
* Dentry lookups (based on parent, candidate string tuple) recheck the parent
sequence after the child is found in case anything changed in the parent
during the path walk.
* inode is also RCU protected so we can load d_inode and use the inode for
limited things.
* i_mode, i_uid, i_gid can be tested for exec permissions during path walk.
* i_op can be loaded.
When we reach the destination dentry, we lock it, recheck lookup sequence,
and increment its refcount and mountpoint refcount. RCU and vfsmount locks
are dropped. This is termed "dropping rcu-walk". If the dentry refcount does
not match, we can not drop rcu-walk gracefully at the current point in the
lokup, so instead return -ECHILD (for want of a better errno). This signals the
path walking code to re-do the entire lookup with a ref-walk.
Aside from the final dentry, there are other situations that may be encounted
where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take
a reference on the last good dentry) and continue with a ref-walk. Again, if
we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup
using ref-walk. But it is very important that we can continue with ref-walk
for most cases, particularly to avoid the overhead of double lookups, and to
gain the scalability advantages on common path elements (like cwd and root).
The cases where rcu-walk cannot continue are:
* NULL dentry (ie. any uncached path element)
* parent with d_inode->i_op->permission or ACLs
* dentries with d_revalidate
* Following links
In future patches, permission checks and d_revalidate become rcu-walk aware. It
may be possible eventually to make following links rcu-walk aware.
Uncached path elements will always require dropping to ref-walk mode, at the
very least because i_mutex needs to be grabbed, and objects allocated.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Pseudo filesystems that don't put inode on RCU list or reachable by
rcu-walk dentries do not need to RCU free their inodes.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
RCU free the struct inode. This will allow:
- Subsequent store-free path walking patch. The inode must be consulted for
permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
to take i_lock no longer need to take sb_inode_list_lock to walk the list in
the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
page lock to follow page->mapping.
The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.
In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.
The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
The tricky locking for disposing of a dentry is duplicated 3 times in the
dcache (dput, pruning a dentry from the LRU, and pruning its ancestors).
Consolidate them all into a single function dentry_kill.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
prune_one_dentry can avoid quite a bit of locking in the common case where
ancestors have an elevated refcount. Alternatively, we could have gone the
other way and made fewer trylocks in the case where d_count goes to zero, but
is probably less common.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
dget_locked was a shortcut to avoid the lazy lru manipulation when we already
held dcache_lock (lru manipulation was relatively cheap at that point).
However, how that the lru lock is an innermost one, we never hold it at any
caller, so the lock cost can now be avoided. We already have well working lazy
dcache LRU, so it should be fine to defer LRU manipulations to scan time.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
dcache_inode_lock can be avoided in d_delete() and d_materialise_unique()
in cases where it is not required.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
It is possible to run dput without taking data structure locks up-front. In
many cases where we don't kill the dentry anyway, these locks are not required.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Long lived dcache "multi-step" operations which retry on rename seq can
be starved with a lot of rename activity. If they fail after the 1st pass,
take the rename_lock for writing to avoid further starvation.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
The remaining usages for dcache_lock is to allow atomic, multi-step read-side
operations over the directory tree by excluding modifications to the tree.
Also, to walk in the leaf->root direction in the tree where we don't have
a natural d_lock ordering.
This could be accomplished by taking every d_lock, but this would mean a
huge number of locks and actually gets very tricky.
Solve this instead by using the rename seqlock for multi-step read-side
operations, retry in case of a rename so we don't walk up the wrong parent.
Concurrent dentry insertions are not serialised against. Concurrent deletes
are tricky when walking up the directory: our parent might have been deleted
when dropping locks so also need to check and retry for that.
We can also use the rename lock in cases where livelock is a worry (and it
is introduced in subsequent patch).
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Add a new lock, dcache_inode_lock, to protect the inode's i_dentry list
from concurrent modification. d_alias is also protected by d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Protect d_subdirs and d_child with d_lock, except in filesystems that aren't
using dcache_lock for these anyway (eg. using i_mutex).
Note: if we change the locking rule in future so that ->d_child protection is
provided only with ->d_parent->d_lock, it may allow us to reduce some locking.
But it would be an exception to an otherwise regular locking scheme, so we'd
have to see some good results. Probably not worthwhile.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Protect d_unhashed(dentry) condition with d_lock. This means keeping
DCACHE_UNHASHED bit in synch with hash manipulations.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Make d_count non-atomic and protect it with d_lock. This allows us to ensure a
0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when
we start protecting many other dentry members with d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Add a new lock, dcache_lru_lock, to protect the dcache LRU list from concurrent
modification. d_lru is also protected by d_lock, which allows LRU lists to be
accessed without the lru lock, using RCU in future patches.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Add a new lock, dcache_hash_lock, to protect the dcache hash table from
concurrent modification. d_hash is also protected by d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Remove dcache_lock locking from hostfs filesystem, and move it into dcache
helpers. All that is required is a coherent path name. Protection from
concurrent modification of the namespace after path name generation is not
provided in current code, because dcache_lock is dropped before the path is
used.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Change d_hash so it may be called from lock-free RCU lookups. See similar
patch for d_compare for details.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Change d_compare so it may be called from lock-free RCU lookups. This
does put significant restrictions on what may be done from the callback,
however there don't seem to have been any problems with in-tree fses.
If some strange use case pops up that _really_ cannot cope with the
rcu-walk rules, we can just add new rcu-unaware callbacks, which would
cause name lookup to drop out of rcu-walk mode.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
smpfs and ncpfs want to update a live dentry name in-place. Rather than
have them open code the locking, provide a documented dcache API.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Use vfat's method for dealing with negative dentries to preserve case,
rather than overwrite dentry name in d_revalidate, which is a bit ugly
and also gets in the way of doing lock-free path walking.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
