UBIFS's recovery code strictly assumes that a deleted inode will never
come back, therefore it removes all data which belongs to that inode
as soon it faces an inode with link count 0 in the replay list.
Before O_TMPFILE this assumption was perfectly fine. With O_TMPFILE
it can lead to data loss upon a power-cut.
Consider a journal with entries like:
0: inode X (nlink = 0) /* O_TMPFILE was created */
1: data for inode X /* Someone writes to the temp file */
2: inode X (nlink = 0) /* inode was changed, xattr, chmod, … */
3: inode X (nlink = 1) /* inode was re-linked via linkat() */
Upon replay of entry #2 UBIFS will drop all data that belongs to inode X,
this will lead to an empty file after mounting.
As solution for this problem, scan the replay list for a re-link entry
before dropping data.
Fixes: 474b93704f ("ubifs: Implement O_TMPFILE")
Cc: stable@vger.kernel.org
Cc: Russell Senior <russell@personaltelco.net>
Cc: Rafał Miłecki <zajec5@gmail.com>
Reported-by: Russell Senior <russell@personaltelco.net>
Reported-by: Rafał Miłecki <zajec5@gmail.com>
Tested-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Richard Weinberger <richard@nod.at>
When ubifs is build without the LZO compressor and no compressor is
given the creation of the default file system will fail. before
selection the LZO compressor check if it is present and if not fall back
to the zlib or none.
Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
If the call to ubifs_read_nnode() fails in ubifs_lpt_calc_hash() an
error is returned without freeing the memory allocated to 'buf'.
Read and check the root node before allocating the buffer.
Detected by CoverityScan, CID 1441025 ("Resource leak")
Signed-off-by: Garry McNulty <garrmcnu@gmail.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
The new authentication support causes a build failure
when CONFIG_KEYS is disabled, so add a dependency.
fs/ubifs/auth.c: In function 'ubifs_init_authentication':
fs/ubifs/auth.c:249:16: error: implicit declaration of function 'request_key'; did you mean 'request_irq'? [-Werror=implicit-function-declaration]
keyring_key = request_key(&key_type_logon, c->auth_key_name, NULL);
Fixes: d8a22773a1 ("ubifs: Enable authentication support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
Instead of adding yet another dependency on UBIFS_FS, wrap the whole
block of ubifs config options in a single "if UBIFS_FS".
Fixes: d8a22773a1 ("ubifs: Enable authentication support")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
Having two shash descriptors on the stack cause a very significant kernel
stack usage that can cross the warning threshold:
fs/ubifs/replay.c: In function 'authenticate_sleb':
fs/ubifs/replay.c:633:1: error: the frame size of 1144 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
Normally, gcc optimizes the out, but with CONFIG_CC_OPTIMIZE_FOR_DEBUGGING,
it does not. Splitting the two stack allocations into separate functions
means that they will use the same memory again. In normal configurations
(optimizing for size or performance), those should get inlined and we get
the same behavior as before.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
Since mkfs always formats the filesystem with the realtime bitmap and
summary inodes immediately after the root directory, we should expect
that both of them are present and loadable, even if there isn't a
realtime volume attached. There's no reason to skip this if rbmino ==
NULLFSINO; in fact, this causes an immediate crash if the there /is/ a
realtime volume and someone writes to it.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Pull overlayfs fixes from Miklos Szeredi:
"Needed to revert a patch, because it possibly introduces a security
hole. Since the patch is basically a conceptual cleanup, not a bug
fix, it's safe to revert. I'm not giving up on this, and discussions
seemed to have reached an agreement over how to move forward, but that
can wait 'till the next release.
The other two patches are fixes for bugs introduced in recent
releases"
* tag 'ovl-fixes-4.20-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
Revert "ovl: relax permission checking on underlying layers"
ovl: fix decode of dir file handle with multi lower layers
ovl: fix missing override creds in link of a metacopy upper
Pull fuse fixes from Miklos Szeredi:
"There's one patch fixing a minor but long lived bug, the others are
fixing regressions introduced in this cycle"
* tag 'fuse-fixes-4.20-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
fuse: continue to send FUSE_RELEASEDIR when FUSE_OPEN returns ENOSYS
fuse: Fix memory leak in fuse_dev_free()
fuse: fix revalidation of attributes for permission check
fuse: fix fsync on directory
fuse: Add bad inode check in fuse_destroy_inode()
The realtime summary is a two-dimensional array on disk, effectively:
u32 rsum[log2(number of realtime extents) + 1][number of blocks in the bitmap]
rsum[log][bbno] is the number of extents of size 2**log which start in
bitmap block bbno.
xfs_rtallocate_extent_near() uses xfs_rtany_summary() to check whether
rsum[log][bbno] != 0 for any log level. However, the summary array is
stored in row-major order (i.e., like an array in C), so all of these
entries are not adjacent, but rather spread across the entire summary
file. In the worst case (a full bitmap block), xfs_rtany_summary() has
to check every level.
This means that on a moderately-used realtime device, an allocation will
waste a lot of time finding, reading, and releasing buffers for the
realtime summary. In particular, one of our storage services (which runs
on servers with 8 very slow CPUs and 15 8 TB XFS realtime filesystems)
spends almost 5% of its CPU cycles in xfs_rtbuf_get() and
xfs_trans_brelse() called from xfs_rtany_summary().
One solution would be to also store the summary with the dimensions
swapped. However, this would require a disk format change to a very old
component of XFS.
Instead, we can cache the minimum size which contains any extents. We do
so lazily; rather than guaranteeing that the cache contains the precise
minimum, it always contains a loose lower bound which we tighten when we
read or update a summary block. This only uses a few kilobytes of memory
and is already serialized via the realtime bitmap and summary inode
locks, so the cost is minimal. With this change, the same workload only
spends 0.2% of its CPU cycles in the realtime allocator.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
A big block filesystem might require more than one inobt record to cover
all the inodes in the block. In these cases it is not correct to round
the irec count up to the nearest block because this causes us to
overestimate the number of inode blocks we expect to find.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Store the inode cluster alignment information in units of inodes and
blocks in the mount data so that we don't have to keep recalculating
them.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Store the number of inodes and blocks per inode cluster in the mount
data so that we don't have to keep recalculating them.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Add new helpers to convert units of fs blocks into inodes, and AG blocks
into AG inodes, respectively. Convert all the open-coded conversions
and XFS_OFFBNO_TO_AGINO(, , 0) calls to use them, as appropriate. The
OFFBNO_TO_AGINO macro is retained for xfs_repair.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Owner information for static fs metadata can be defined readonly at
build time because it never changes across filesystems. This enables us
to reduce stack usage (particularly in scrub) because we can use the
statically defined oinfo structures.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Only certain functions actually change the contents of an
xfs_owner_info; the rest can accept a const struct pointer. This will
enable us to save stack space by hoisting static owner info types to
be const global variables.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
There's no need to bundle a pointer to the defer op type into the defer
op control structure. Instead, store the defer op type enum, which
enables us to shorten some of the lines.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Recently, we forgot to port a new defer op type to xfsprogs, which
caused us some userspace pain. Reorganize the way we make libxfs
clients supply defer op type information so that all type information
has to be provided at build time instead of risky runtime dynamic
configuration.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
A log recovery failure has been reproduced where a symlink inode has
a zero length in extent form. It was caused by a shutdown during a
combined fstress+fsmark workload.
The underlying problem is the issue in xfs_inactive_symlink(): the
inode is unlocked between the symlink inactivation/truncation and
the inode being freed. This opens a window for the inode to be
written to disk before it xfs_ifree() removes it from the unlinked
list, marks it free in the inobt and zeros the mode.
For shortform inodes, the fix is simple. xfs_ifree() clears the data
fork state, so there's no need to do it in xfs_inactive_symlink().
This means the shortform fork verifier will not see a zero length
data fork as it mirrors the inode size through to xfs_ifree()), and
hence if the inode gets written back and the fork verifiers are run
they will still see a fork that matches the on-disk inode size.
For extent form (remote) symlinks, it is a little more tricky. Here
we explicitly set the inode size to zero, so the above race can lead
to zero length symlinks on disk. Because the inode is unlinked at
this point (i.e. on the unlinked list) and unreferenced, it can
never be seen again by a user. Hence when we set the inode size to
zeor, also change the type to S_IFREG. xfs_ifree() expects S_IFREG
inodes to be of zero length, and so this avoids all the problems of
zero length symlinks ever hitting the disk. It also avoids the
problem of needing to handle zero length symlink inodes in log
recovery to replay the extent free intents and the remaining
deferops to free the extents the symlink used.
Also add a couple of asserts to warn us if zero length symlinks end
up in either the symlink create or inactivation paths.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
The function xfs_alloc_get_freelist calls xfs_perag_put to drop the
reference. However, pag->pagf_btreeblks is read and written after the
put operation. This patch moves the put operation later.
Signed-off-by: Pan Bian <bianpan2016@163.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
[darrick: minor changelog edits]
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
In xfs_reflink_end_cow, we allocate a single transaction for the entire
end_cow operation and then loop the CoW fork mappings to move them to
the data fork. This design fails on a heavily fragmented filesystem
where an inode's data fork has exactly one more extent than would fit in
an extents-format fork, because the unmap can collapse the data fork
into extents format (freeing the bmbt block) but the remap can expand
the data fork back into a (newly allocated) bmbt block. If the number
of extents we end up remapping is large, we can overflow the block
reservation because we reserved blocks assuming that we were adding
mappings into an already-cleared area of the data fork.
Let's say we have 8 extents in the data fork, 8 extents in the CoW fork,
and the data fork can hold at most 7 extents before needing to convert
to btree format; and that blocks A-P are discontiguous single-block
extents:
0......7
D: ABCDEFGH
C: IJKLMNOP
When a write to file blocks 0-7 completes, we must remap I-P into the
data fork. We start by removing H from the btree-format data fork. Now
we have 7 extents, so we convert the fork to extents format, freeing the
bmbt block. We then move P into the data fork and it now has 8 extents
again. We must convert the data fork back to btree format, requiring a
block allocation. If we repeat this sequence for blocks 6-5-4-3-2-1-0,
we'll need a total of 8 block allocations to remap all 8 blocks. We
reserved only enough blocks to handle one btree split (5 blocks on a 4k
block filesystem), which means we overflow the block reservation.
To fix this issue, create a separate helper function to remap a single
extent, and change _reflink_end_cow to call it in a tight loop over the
entire range we're completing. As a side effect this also removes the
size restrictions on how many extents we can end_cow at a time, though
nobody ever hit that. It is not reasonable to reserve N blocks to remap
N blocks.
Note that this can be reproduced after ~320 million fsx ops while
running generic/938 (long soak directio fsx exerciser):
XFS: Assertion failed: tp->t_blk_res >= tp->t_blk_res_used, file: fs/xfs/xfs_trans.c, line: 116
<machine registers snipped>
Call Trace:
xfs_trans_dup+0x211/0x250 [xfs]
xfs_trans_roll+0x6d/0x180 [xfs]
xfs_defer_trans_roll+0x10c/0x3b0 [xfs]
xfs_defer_finish_noroll+0xdf/0x740 [xfs]
xfs_defer_finish+0x13/0x70 [xfs]
xfs_reflink_end_cow+0x2c6/0x680 [xfs]
xfs_dio_write_end_io+0x115/0x220 [xfs]
iomap_dio_complete+0x3f/0x130
iomap_dio_rw+0x3c3/0x420
xfs_file_dio_aio_write+0x132/0x3c0 [xfs]
xfs_file_write_iter+0x8b/0xc0 [xfs]
__vfs_write+0x193/0x1f0
vfs_write+0xba/0x1c0
ksys_write+0x52/0xc0
do_syscall_64+0x50/0x160
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
When inode is corrupted so that extent type is invalid, some functions
(such as udf_truncate_extents()) will just BUG. Check that extent type
is valid when loading the inode to memory.
Reported-by: Anatoly Trosinenko <anatoly.trosinenko@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Make all the required change to start use the ib_device_ops structure.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch is based on an idea from Steve Whitehouse. The idea is
to dump the number of pages for inodes in the glock dumps.
The additional locking required me to drop const from quite a few
places.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Fix the resource group wrap-around logic in gfs2_rbm_find that commit
e579ed4f44 broke. The bug can lead to unnecessary repeated scanning of the
same bitmaps; there is a risk that future changes will turn this into an
endless loop.
Fixes: e579ed4f44 ("GFS2: Introduce rbm field bii")
Cc: stable@vger.kernel.org # v3.13+
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
When FUSE_OPEN returns ENOSYS, the no_open bit is set on the connection.
Because the FUSE_RELEASE and FUSE_RELEASEDIR paths share code, this
incorrectly caused the FUSE_RELEASEDIR request to be dropped and never sent
to userspace.
Pass an isdir bool to distinguish between FUSE_RELEASE and FUSE_RELEASEDIR
inside of fuse_file_put.
Fixes: 7678ac5061 ("fuse: support clients that don't implement 'open'")
Cc: <stable@vger.kernel.org> # v3.14
Signed-off-by: Chad Austin <chadaustin@fb.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
In gfs2_create_inode, after setting and releasing the acl / default_acl, the
acl / default_acl pointers are not set to NULL as they should be. In that
state, when the function reaches label fail_free_acls, gfs2_create_inode will
try to release the same acls again.
Fix that by setting the pointers to NULL after releasing the acls. Slightly
simplify the logic. Also, posix_acl_release checks for NULL already, so
there is no need to duplicate those checks here.
Fixes: e01580bf9e ("gfs2: use generic posix ACL infrastructure")
Reported-by: Pan Bian <bianpan2016@163.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org # v4.9+
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Field bd_ops was set but never used, so I removed it, and all
code supporting it.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Acked-by: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Matthew pointed out that the ioctx_table is susceptible to spectre v1,
because the index can be controlled by an attacker. The below patch
should mitigate the attack for all of the aio system calls.
Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Matthew pointed out that the ioctx_table is susceptible to spectre v1,
because the index can be controlled by an attacker. The below patch
should mitigate the attack for all of the aio system calls.
Cc: stable@vger.kernel.org
Reported-by: Matthew Wilcox <willy@infradead.org>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since we found a problem with the 'copy-from' operation after objects have
been truncated, offloading object copies to OSDs should be discouraged
until the issue is fixed.
Thus, this patch adds the 'nocopyfrom' mount option to the default mount
options which effectily means that remote copies won't be done in
copy_file_range unless they are explicitly enabled at mount time.
[ Adjust ceph_show_options() accordingly. ]
Link: https://tracker.ceph.com/issues/37378
Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Use bio(s) to read in the journal sequentially in large chunks and
locate the head of the journal.
This version addresses the issues Christoph pointed out w.r.t error handling
and using deprecated API.
Signed-off-by: Abhi Das <adas@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Move and re-order the error checks and hash/crc computations into another
function __get_log_header() so it can be used in scenarios where buffer_heads
are not being used for the log header.
Signed-off-by: Abhi Das <adas@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Change gfs2_log_XXX_bio family of functions so they can be used
with different bios, not just sdp->sd_log_bio.
This patch also contains some clean up suggested by Andreas.
Signed-off-by: Abhi Das <adas@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Tells you how many milliseconds map_journal_extents and find_jhead
take.
Signed-off-by: Abhi Das <adas@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
The gfs2_is_ordered and gfs2_is_writeback checks are weird in that they
implicitly check for !gfs2_is_jdata. This makes understanding how to
use those functions correctly a challenge. Clean this up by making
gfs2_is_ordered and gfs2_is_writeback take a super block instead of an
inode and by removing the implicit !gfs2_is_jdata checks. Update the
callers accordingly.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Use the aptly named function rather than opencoding i_writecount check.
No functional changes.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Jan Kara <jack@suse.cz>
prepare_bprm_creds is not used outside exec.c, so there's no reason for it
to have external linkage.
Signed-off-by: Chanho Min <chanho.min@lge.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
If new mode is the same as old mode we don't have to reset
inode mode in the rest of the code, so compare old and new
mode before setting update_mode flag.
Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Pull in v4.20-rc6 to resolve the conflict in NVMe, but also to get the
two corruption fixes. We're going to be overhauling the direct dispatch
path, and we need to do that on top of the changes we made for that
in mainline.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull cifs fixes from Steve French:
"Three small fixes: a fix for smb3 direct i/o, a fix for CIFS DFS for
stable and a minor cifs Kconfig fix"
* tag '4.20-rc5-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
CIFS: Avoid returning EBUSY to upper layer VFS
cifs: Fix separator when building path from dentry
cifs: In Kconfig CONFIG_CIFS_POSIX needs depends on legacy (insecure cifs)
Pull dax fixes from Dan Williams:
"The last of the known regression fixes and fallout from the Xarray
conversion of the filesystem-dax implementation.
On the path to debugging why the dax memory-failure injection test
started failing after the Xarray conversion a couple more fixes for
the dax_lock_mapping_entry(), now called dax_lock_page(), surfaced.
Those plus the bug that started the hunt are now addressed. These
patches have appeared in a -next release with no issues reported.
Note the touches to mm/memory-failure.c are just the conversion to the
new function signature for dax_lock_page().
Summary:
- Fix the Xarray conversion of fsdax to properly handle
dax_lock_mapping_entry() in the presense of pmd entries
- Fix inode destruction racing a new lock request"
* tag 'dax-fixes-4.20-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
dax: Fix unlock mismatch with updated API
dax: Don't access a freed inode
dax: Check page->mapping isn't NULL
Pull xfs fixes from Darrick Wong:
"Here are hopefully the last set of fixes for 4.20.
There's a fix for a longstanding statfs reporting problem with project
quotas, a correction for page cache invalidation behaviors when
fallocating near EOF, and a fix for a broken metadata verifier return
code.
Finally, the most important fix is to the pipe splicing code (aka the
generic copy_file_range fallback) to avoid pointless short directio
reads by only asking the filesystem for as much data as there are
available pages in the pipe buffer. Our previous fix (simulated short
directio reads because the number of pages didn't match the length of
the read requested) caused subtle problems on overlayfs, so that part
is reverted.
Anyhow, this series passes fstests -g all on xfs and overlay+xfs, and
has passed 17 billion fsx operations problem-free since I started
testing
Summary:
- Fix broken project quota inode counts
- Fix incorrect PAGE_MASK/PAGE_SIZE usage
- Fix incorrect return value in btree verifier
- Fix WARN_ON remap flags false positive
- Fix splice read overflows"
* tag 'xfs-4.20-fixes-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
iomap: partially revert 4721a60109 (simulated directio short read on EFAULT)
splice: don't read more than available pipe space
vfs: allow some remap flags to be passed to vfs_clone_file_range
xfs: fix inverted return from xfs_btree_sblock_verify_crc
xfs: fix PAGE_MASK usage in xfs_free_file_space
fs/xfs: fix f_ffree value for statfs when project quota is set
One of the goals of this series is to remove a separate reference to
the css of the bio. This can and should be accessed via bio_blkcg(). In
this patch, wbc_init_bio() now requires a bio to have a device
associated with it.
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
- spaces before tabs,
- spaces at the end of lines,
- multiple blank lines,
- blank lines before EXPORT_SYMBOL,
can all go.
Signed-off-by: NeilBrown <neilb@suse.com>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
posix_unblock_lock() is not specific to posix locks, and behaves
nearly identically to locks_delete_block() - the former returning a
status while the later doesn't.
So discard posix_unblock_lock() and use locks_delete_block() instead,
after giving that function an appropriate return value.
Signed-off-by: NeilBrown <neilb@suse.com>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
When we find an existing lock which conflicts with a request,
and the request wants to wait, we currently add the request
to a list. When the lock is removed, the whole list is woken.
This can cause the thundering-herd problem.
To reduce the problem, we make use of the (new) fact that
a pending request can itself have a list of blocked requests.
When we find a conflict, we look through the existing blocked requests.
If any one of them blocks the new request, the new request is attached
below that request, otherwise it is added to the list of blocked
requests, which are now known to be mutually non-conflicting.
This way, when the lock is released, only a set of non-conflicting
locks will be woken, the rest can stay asleep.
If the lock request cannot be granted and the request needs to be
requeued, all the other requests it blocks will then be woken
To make this more concrete:
If you have a many-core machine, and have many threads all wanting to
briefly lock a give file (udev is known to do this), you can get quite
poor performance.
When one thread releases a lock, it wakes up all other threads that
are waiting (classic thundering-herd) - one will get the lock and the
others go to sleep.
When you have few cores, this is not very noticeable: by the time the
4th or 5th thread gets enough CPU time to try to claim the lock, the
earlier threads have claimed it, done what was needed, and released.
So with few cores, many of the threads don't end up contending.
With 50+ cores, lost of threads can get the CPU at the same time,
and the contention can easily be measured.
This patchset creates a tree of pending lock requests in which siblings
don't conflict and each lock request does conflict with its parent.
When a lock is released, only requests which don't conflict with each
other a woken.
Testing shows that lock-acquisitions-per-second is now fairly stable
even as the number of contending process goes to 1000. Without this
patch, locks-per-second drops off steeply after a few 10s of
processes.
There is a small cost to this extra complexity.
At 20 processes running a particular test on 72 cores, the lock
acquisitions per second drops from 1.8 million to 1.4 million with
this patch. For 100 processes, this patch still provides 1.4 million
while without this patch there are about 700,000.
Reported-and-tested-by: Martin Wilck <mwilck@suse.de>
Signed-off-by: NeilBrown <neilb@suse.com>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
