Writeback caching currently allocates requests with the maximum number of
possible pages, while the actual number of pages per request depends on a
couple of factors that cannot be determined when the request is allocated
(whether page is already under writeback, whether page is contiguous with
previous pages already added to a request).
This patch allows such requests to start with no page allocation (all pages
inline) and grow the page array on demand.
If the max_pages tunable remains the default value, then this will mean
just one allocation that is the same size as before. If the tunable is
larger, then this adds at most 3 additional memory allocations (which is
generously compensated by the improved performance from the larger
request).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Replace FUSE_MAX_PAGES_PER_REQ with the configurable parameter max_pages to
improve performance.
Old RFC with detailed description of the problem and many fixes by Mitsuo
Hayasaka (mitsuo.hayasaka.hu@hitachi.com):
- https://lkml.org/lkml/2012/7/5/136
We've encountered performance degradation and fixed it on a big and complex
virtual environment.
Environment to reproduce degradation and improvement:
1. Add lag to user mode FUSE
Add nanosleep(&(struct timespec){ 0, 1000 }, NULL); to xmp_write_buf in
passthrough_fh.c
2. patch UM fuse with configurable max_pages parameter. The patch will be
provided latter.
3. run test script and perform test on tmpfs
fuse_test()
{
cd /tmp
mkdir -p fusemnt
passthrough_fh -o max_pages=$1 /tmp/fusemnt
grep fuse /proc/self/mounts
dd conv=fdatasync oflag=dsync if=/dev/zero of=fusemnt/tmp/tmp \
count=1K bs=1M 2>&1 | grep -v records
rm fusemnt/tmp/tmp
killall passthrough_fh
}
Test results:
passthrough_fh /tmp/fusemnt fuse.passthrough_fh \
rw,nosuid,nodev,relatime,user_id=0,group_id=0 0 0
1073741824 bytes (1.1 GB) copied, 1.73867 s, 618 MB/s
passthrough_fh /tmp/fusemnt fuse.passthrough_fh \
rw,nosuid,nodev,relatime,user_id=0,group_id=0,max_pages=256 0 0
1073741824 bytes (1.1 GB) copied, 1.15643 s, 928 MB/s
Obviously with bigger lag the difference between 'before' and 'after'
will be more significant.
Mitsuo Hayasaka, in 2012 (https://lkml.org/lkml/2012/7/5/136),
observed improvement from 400-550 to 520-740.
Signed-off-by: Constantine Shulyupin <const@MakeLinux.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Do this by grouping fields used for cached writes and putting them into a
union with fileds used for cached readdir (with obviously no overlap, since
we don't have hybrid objects).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Use the internal iversion counter to make sure modifications of the
directory through this filesystem are not missed by the mtime check (due to
mtime granularity).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Store the modification time of the directory in the cache, obtained before
starting to fill the cache.
When reading the cache, verify that the directory hasn't changed, by
checking if current modification time is the same as the one stored in the
cache.
This only needs to be done when the current file position is at the
beginning of the directory, as mandated by POSIX.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Allow the cache to be invalidated when page(s) have gone missing. In this
case increment the version of the cache and reset to an empty state.
Add a version number to the directory stream in struct fuse_file as well,
indicating the version of the cache it's supposed to be reading. If the
cache version doesn't match the stream's version, then reset the stream to
the beginning of the cache.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
The cache is only used if it's completed, not while it's still being
filled; this constraint could be lifted later, if it turns out to be
useful.
Introduce state in struct fuse_file that indicates the position within the
cache. After a seek, reset the position to the beginning of the cache and
search the cache for the current position. If the current position is not
found in the cache, then fall back to uncached readdir.
It can also happen that page(s) disappear from the cache, in which case we
must also fall back to uncached readdir.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
This patch just adds the cache filling functions, which are invoked if
FOPEN_CACHE_DIR flag is set in the OPENDIR reply.
Cache reading and cache invalidation are added by subsequent patches.
The directory cache uses the page cache. Directory entries are packed into
a page in the same format as in the READDIR reply. A page only contains
whole entries, the space at the end of the page is cleared. The page is
locked while being modified.
Multiple parallel readdirs on the same directory can fill the cache; the
only constraint is that continuity must be maintained (d_off of last entry
points to position of current entry).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
We noticed the performance bottleneck in FUSE running our Virtuozzo storage
over rdma. On some types of workload we observe 20% of times spent in
request_find() in profiler. This function is iterating over long requests
list, and it scales bad.
The patch introduces hash table to reduce the number of iterations, we do
in this function. Hash generating algorithm is taken from hash_add()
function, while 256 lines table is used to store pending requests. This
fixes problem and improves the performance.
Reported-by: Alexey Kuznetsov <kuznet@virtuozzo.com>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
This field is not needed after the previous patch, since we can easily
convert request ID to interrupt request ID and vice versa.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Currently, we take fc->lock there only to check for fc->connected.
But this flag is changed only on connection abort, which is very
rare operation.
So allow checking fc->connected under just fc->bg_lock and use this lock
(as well as fc->lock) when resetting fc->connected.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
To reduce contention of fc->lock, this patch introduces bg_lock for
protection of fields related to background queue. These are:
max_background, congestion_threshold, num_background, active_background,
bg_queue and blocked.
This allows next patch to make async reads not requiring fc->lock, so async
reads and writes will have better performance executed in parallel.
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
There are several FUSE filesystems that can implement server-side copy
or other efficient copy/duplication/clone methods. The copy_file_range()
syscall is the standard interface that users have access to while not
depending on external libraries that bypass FUSE.
Signed-off-by: Niels de Vos <ndevos@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
If parallel dirops are enabled in FUSE_INIT reply, then first operation may
leave fi->mutex held.
Reported-by: syzbot <syzbot+3f7b29af1baa9d0a55be@syzkaller.appspotmail.com>
Fixes: 5c672ab3f0 ("fuse: serialize dirops by default")
Cc: <stable@vger.kernel.org> # v4.7
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
fuse_abort_conn() does not guarantee that all async requests have actually
finished aborting (i.e. their ->end() function is called). This could
actually result in still used inodes after umount.
Add a helper to wait until all requests are fully done. This is done by
looking at the "num_waiting" counter. When this counter drops to zero, we
can be sure that no more requests are outstanding.
Fixes: 0d8e84b043 ("fuse: simplify request abort")
Cc: <stable@vger.kernel.org> # v4.2
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Ensure the translation happens by failing to read or write
posix acls when the filesystem has not indicated it supports
posix acls.
This ensures that modern cached posix acl support is available
and used when dealing with posix acls. This is important
because only that path has the code to convernt the uids and
gids in posix acls into the user namespace of a fuse filesystem.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
In order to support mounts from namespaces other than init_user_ns, fuse
must translate uids and gids to/from the userns of the process servicing
requests on /dev/fuse. This patch does that, with a couple of restrictions
on the namespace:
- The userns for the fuse connection is fixed to the namespace
from which /dev/fuse is opened.
- The namespace must be the same as s_user_ns.
These restrictions simplify the implementation by avoiding the need to pass
around userns references and by allowing fuse to rely on the checks in
setattr_prepare for ownership changes. Either restriction could be relaxed
in the future if needed.
For cuse the userns used is the opener of /dev/cuse. Semantically the cuse
support does not appear safe for unprivileged users. Practically the
permissions on /dev/cuse only make it accessible to the global root user.
If something slips through the cracks in a user namespace the only users
who will be able to use the cuse device are those users mapped into the
user namespace.
Translation in the posix acl is updated to use the uuser namespace of the
filesystem. Avoiding cases which might bypass this translation is handled
in a following change.
This change is stronlgy based on a similar change from Seth Forshee and
Dongsu Park.
Cc: Seth Forshee <seth.forshee@canonical.com>
Cc: Dongsu Park <dongsu@kinvolk.io>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Currently the userspace has no way of knowing whether the fuse
connection ended because of umount or abort via sysfs. It makes it hard
for filesystems to free the mountpoint after abort without worrying
about removing some new mount.
The patch fixes it by returning different errors when userspace reads
from /dev/fuse (-ENODEV for umount and -ECONNABORTED for abort).
Add a new capability flag FUSE_ABORT_ERROR. If set and the connection is
gone because of sysfs abort, reading from the device will return
-ECONNABORTED.
Signed-off-by: Szymon Lukasz <noh4hss@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
The refreshed argument isn't used by any caller, get rid of it.
Use a helper for just updating the inode (no need to fill in a kstat).
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
If the IOCB_DSYNC flag is set a sync is not being performed by
fuse_file_write_iter.
Honor IOCB_DSYNC/IOCB_SYNC by setting O_DYSNC/O_SYNC respectively in the
flags filed of the write request.
We don't need to sync data or metadata, since fuse_perform_write() does
write-through and the filesystem is responsible for updating file times.
Original patch by Vitaly Zolotusky.
Reported-by: Nate Clark <nate@neworld.us>
Cc: Vitaly Zolotusky <vitaly@unitc.com>.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Commit 8fba54aebb ("fuse: direct-io: don't dirty ITER_BVEC pages") fixes
the ITER_BVEC page deadlock for direct io in fuse by checking in
fuse_direct_io(), whether the page is a bvec page or not, before locking
it. However, this check is missed when the "async_dio" mount option is
enabled. In this case, set_page_dirty_lock() is called from the req->end
callback in request_end(), when the fuse thread is returning from userspace
to respond to the read request. This will cause the same deadlock because
the bvec condition is not checked in this path.
Here is the stack of the deadlocked thread, while returning from userspace:
[13706.656686] INFO: task glusterfs:3006 blocked for more than 120 seconds.
[13706.657808] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables
this message.
[13706.658788] glusterfs D ffffffff816c80f0 0 3006 1
0x00000080
[13706.658797] ffff8800d6713a58 0000000000000086 ffff8800d9ad7000
ffff8800d9ad5400
[13706.658799] ffff88011ffd5cc0 ffff8800d6710008 ffff88011fd176c0
7fffffffffffffff
[13706.658801] 0000000000000002 ffffffff816c80f0 ffff8800d6713a78
ffffffff816c790e
[13706.658803] Call Trace:
[13706.658809] [<ffffffff816c80f0>] ? bit_wait_io_timeout+0x80/0x80
[13706.658811] [<ffffffff816c790e>] schedule+0x3e/0x90
[13706.658813] [<ffffffff816ca7e5>] schedule_timeout+0x1b5/0x210
[13706.658816] [<ffffffff81073ffb>] ? gup_pud_range+0x1db/0x1f0
[13706.658817] [<ffffffff810668fe>] ? kvm_clock_read+0x1e/0x20
[13706.658819] [<ffffffff81066909>] ? kvm_clock_get_cycles+0x9/0x10
[13706.658822] [<ffffffff810f5792>] ? ktime_get+0x52/0xc0
[13706.658824] [<ffffffff816c6f04>] io_schedule_timeout+0xa4/0x110
[13706.658826] [<ffffffff816c8126>] bit_wait_io+0x36/0x50
[13706.658828] [<ffffffff816c7d06>] __wait_on_bit_lock+0x76/0xb0
[13706.658831] [<ffffffffa0545636>] ? lock_request+0x46/0x70 [fuse]
[13706.658834] [<ffffffff8118800a>] __lock_page+0xaa/0xb0
[13706.658836] [<ffffffff810c8500>] ? wake_atomic_t_function+0x40/0x40
[13706.658838] [<ffffffff81194d08>] set_page_dirty_lock+0x58/0x60
[13706.658841] [<ffffffffa054d968>] fuse_release_user_pages+0x58/0x70 [fuse]
[13706.658844] [<ffffffffa0551430>] ? fuse_aio_complete+0x190/0x190 [fuse]
[13706.658847] [<ffffffffa0551459>] fuse_aio_complete_req+0x29/0x90 [fuse]
[13706.658849] [<ffffffffa05471e9>] request_end+0xd9/0x190 [fuse]
[13706.658852] [<ffffffffa0549126>] fuse_dev_do_write+0x336/0x490 [fuse]
[13706.658854] [<ffffffffa054963e>] fuse_dev_write+0x6e/0xa0 [fuse]
[13706.658857] [<ffffffff812a9ef3>] ? security_file_permission+0x23/0x90
[13706.658859] [<ffffffff81205300>] do_iter_readv_writev+0x60/0x90
[13706.658862] [<ffffffffa05495d0>] ? fuse_dev_splice_write+0x350/0x350
[fuse]
[13706.658863] [<ffffffff812062a1>] do_readv_writev+0x171/0x1f0
[13706.658866] [<ffffffff810b3d00>] ? try_to_wake_up+0x210/0x210
[13706.658868] [<ffffffff81206361>] vfs_writev+0x41/0x50
[13706.658870] [<ffffffff81206496>] SyS_writev+0x56/0xf0
[13706.658872] [<ffffffff810257a1>] ? syscall_trace_leave+0xf1/0x160
[13706.658874] [<ffffffff816cbb2e>] system_call_fastpath+0x12/0x71
Fix this by making should_dirty a fuse_io_priv parameter that can be
checked in fuse_aio_complete_req().
Reported-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Ashish Samant <ashish.samant@oracle.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Pull fuse updates from Miklos Szeredi:
"Support for pid namespaces from Seth and refcount_t work from Elena"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
fuse: Add support for pid namespaces
fuse: convert fuse_conn.count from atomic_t to refcount_t
fuse: convert fuse_req.count from atomic_t to refcount_t
fuse: convert fuse_file.count from atomic_t to refcount_t
It is not needed anymore since bdi is initialized whenever superblock
exists.
CC: Miklos Szeredi <miklos@szeredi.hu>
CC: linux-fsdevel@vger.kernel.org
Suggested-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.
CC: Miklos Szeredi <miklos@szeredi.hu>
CC: linux-fsdevel@vger.kernel.org
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
When the userspace process servicing fuse requests is running in
a pid namespace then pids passed via the fuse fd are not being
translated into that process' namespace. Translation is necessary
for the pid to be useful to that process.
Since no use case currently exists for changing namespaces all
translations can be done relative to the pid namespace in use
when fuse_conn_init() is called. For fuse this translates to
mount time, and for cuse this is when /dev/cuse is opened. IO for
this connection from another namespace will return errors.
Requests from processes whose pid cannot be translated into the
target namespace will have a value of 0 for in.h.pid.
File locking changes based on previous work done by Eric
Biederman.
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
struct fuse_file is stored in file->private_data. Make this always be a
counting reference for consistency.
This also allows fuse_sync_release() to call fuse_file_put() instead of
partially duplicating its functionality.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Since we need to change the implementation, stop exposing internals.
Provide KREF_INIT() to allow static initialization of struct kref.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull misc vfs updates from Al Viro:
"Assorted misc bits and pieces.
There are several single-topic branches left after this (rename2
series from Miklos, current_time series from Deepa Dinamani, xattr
series from Andreas, uaccess stuff from from me) and I'd prefer to
send those separately"
* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (39 commits)
proc: switch auxv to use of __mem_open()
hpfs: support FIEMAP
cifs: get rid of unused arguments of CIFSSMBWrite()
posix_acl: uapi header split
posix_acl: xattr representation cleanups
fs/aio.c: eliminate redundant loads in put_aio_ring_file
fs/internal.h: add const to ns_dentry_operations declaration
compat: remove compat_printk()
fs/buffer.c: make __getblk_slow() static
proc: unsigned file descriptors
fs/file: more unsigned file descriptors
fs: compat: remove redundant check of nr_segs
cachefiles: Fix attempt to read i_blocks after deleting file [ver #2]
cifs: don't use memcpy() to copy struct iov_iter
get rid of separate multipage fault-in primitives
fs: Avoid premature clearing of capabilities
fs: Give dentry to inode_change_ok() instead of inode
fuse: Propagate dentry down to inode_change_ok()
ceph: Propagate dentry down to inode_change_ok()
xfs: Propagate dentry down to inode_change_ok()
...
Only two flags: "default_permissions" and "allow_other". All other flags
are handled via bitfields. So convert these two as well. They don't
change during the lifetime of the filesystem, so this is quite safe.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Add a new INIT flag, FUSE_POSIX_ACL, for negotiating ACL support with
userspace. When it is set in the INIT response, ACL support will be
enabled. ACL support also implies "default_permissions".
When ACL support is enabled, the kernel will cache and have responsibility
for enforcing ACLs. ACL xattrs will be passed to userspace, which is
responsible for updating the ACLs in the filesystem, keeping the file mode
in sync, and inheritance of default ACLs when new filesystem nodes are
created.
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Only userspace filesystem can do the killing of suid/sgid without races.
So introduce an INIT flag and negotiate support for this.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
In preparation for posix acl support, rework fuse to use xattr handlers and
the generic setxattr/getxattr/listxattr callbacks. Split the xattr code
out into it's own file, and promote symbols to module-global scope as
needed.
Functionally these changes have no impact, as fuse still uses a single
handler for all xattrs which uses the old callbacks.
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
To avoid clearing of capabilities or security related extended
attributes too early, inode_change_ok() will need to take dentry instead
of inode. Propagate it down to fuse_do_setattr().
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Pull qstr constification updates from Al Viro:
"Fairly self-contained bunch - surprising lot of places passes struct
qstr * as an argument when const struct qstr * would suffice; it
complicates analysis for no good reason.
I'd prefer to feed that separately from the assorted fixes (those are
in #for-linus and with somewhat trickier topology)"
* 'work.const-qstr' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
qstr: constify instances in adfs
qstr: constify instances in lustre
qstr: constify instances in f2fs
qstr: constify instances in ext2
qstr: constify instances in vfat
qstr: constify instances in procfs
qstr: constify instances in fuse
qstr constify instances in fs/dcache.c
qstr: constify instances in nfs
qstr: constify instances in ocfs2
qstr: constify instances in autofs4
qstr: constify instances in hfs
qstr: constify instances in hfsplus
qstr: constify instances in logfs
qstr: constify dentry_init_security
While sending the blocking directIO in fuse, the write request is broken
into sub-requests, each of default size 128k and all the requests are sent
in non-blocking background mode if async_dio mode is supported by libfuse.
The process which issue the write wait for the completion of all the
sub-requests. Sending multiple requests parallely gives a chance to perform
parallel writes in the user space fuse implementation if it is
multi-threaded and hence improves the performance.
When there is a size extending aio dio write, we switch to blocking mode so
that we can properly update the size of the file after completion of the
writes. However, in this situation all the sub-requests are sent in
serialized manner where the next request is sent only after receiving the
reply of the current request. Hence the multi-threaded user space
implementation is not utilized properly.
This patch changes the size extending aio dio behavior to exactly follow
blocking dio. For multi threaded fuse implementation having 10 threads and
using buffer size of 64MB to perform async directIO, we are getting double
the speed.
Signed-off-by: Ashish Sangwan <ashishsangwan2@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Negotiate with userspace filesystems whether they support parallel readdir
and lookup. Disable parallelism by default for fear of breaking fuse
filesystems.
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 9902af79c0 ("parallel lookups: actual switch to rwsem")
Fixes: d9b3dbdcfd ("fuse: switch to ->iterate_shared()")
The 'reqs' member of fuse_io_priv serves two purposes. First is to track
the number of oustanding async requests to the server and to signal that
the io request is completed. The second is to be a reference count on the
structure to know when it can be freed.
For sync io requests these purposes can be at odds. fuse_direct_IO() wants
to block until the request is done, and since the signal is sent when
'reqs' reaches 0 it cannot keep a reference to the object. Yet it needs to
use the object after the userspace server has completed processing
requests. This leads to some handshaking and special casing that it
needlessly complicated and responsible for at least one race condition.
It's much cleaner and safer to maintain a separate reference count for the
object lifecycle and to let 'reqs' just be a count of outstanding requests
to the userspace server. Then we can know for sure when it is safe to free
the object without any handshaking or special cases.
The catch here is that most of the time these objects are stack allocated
and should not be freed. Initializing these objects with a single reference
that is never released prevents accidental attempts to free the objects.
Fixes: 9d5722b777 ("fuse: handle synchronous iocbs internally")
Cc: stable@vger.kernel.org # v4.1+
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
A useful performance improvement for accessing virtual machine images
via FUSE mount.
See https://bugzilla.redhat.com/show_bug.cgi?id=1220173 for a use-case
for glusterFS.
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Make each fuse device clone refer to a separate processing queue. The only
constraint on userspace code is that the request answer must be written to
the same device clone as it was read off.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Allow fuse device clones to refer to be distinguished. This patch just
adds the infrastructure by associating a separate "struct fuse_dev" with
each clone.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
When an unlocked request is aborted, it is moved from fpq->io to a private
list. Then, after unlocking fpq->lock, the private list is processed and
the requests are finished off.
To protect the private list, we need to mark the request with a flag, so if
in the meantime the request is unlocked the list is not corrupted.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
Add a fpq->lock for protecting members of struct fuse_pqueue and FR_LOCKED
request flag.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
This will allow checking ->connected just with the processing queue lock.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
This is just two fields: fc->io and fc->processing.
This patch just rearranges the fields, no functional change.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
This will allow checking ->connected just with the input queue lock.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
The input queue contains normal requests (fc->pending), forgets
(fc->forget_*) and interrupts (fc->interrupts). There's also fc->waitq and
fc->fasync for waking up the readers of the fuse device when a request is
available.
The fc->reqctr is also moved to the input queue (assigned to the request
when the request is added to the input queue.
This patch just rearranges the fields, no functional change.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
Use flags for representing the state in fuse_req. This is needed since
req->list will be protected by different locks in different states, hence
we'll want the state itself to be split into distinct bits, each protected
with the relevant lock in that state.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
FUSE_REQ_INIT is actually the same state as FUSE_REQ_PENDING and
FUSE_REQ_READING and FUSE_REQ_WRITING can be merged into a common
FUSE_REQ_IO state.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
Finer grained locking will mean there's no single lock to protect
modification of bitfileds in fuse_req.
So move to using bitops. Can use the non-atomic variants for those which
happen while the request definitely has only one reference.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Ashish Samant <ashish.samant@oracle.com>
Based on a patch from Maxim Patlasov <MPatlasov@parallels.com>.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Theoretically we need to order setting of various fields in fc with
fc->initialized.
No known bug reports related to this yet.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The following pattern is repeated many times:
req = fuse_get_req_nopages(fc);
/* Initialize req->(in|out).args */
fuse_request_send(fc, req);
err = req->out.h.error;
fuse_put_request(req);
Create a new replacement helper:
/* Initialize args */
err = fuse_simple_request(fc, &args);
In addition to reducing the code size, this will ease moving from the
complex arg-based to a simpler page-based I/O on the fuse device.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
path_put() in release could trigger a DESTROY request in fuseblk. The
possible deadlock was worked around by doing the path_put() with
schedule_work().
This complexity isn't needed if we just hold the inode instead of the path.
Since we now flush all requests before destroying the super block we can be
sure that all held inodes will be dropped.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Use fuse_abort_conn() instead of fuse_conn_kill() in fuse_put_super().
This flushes and aborts requests still on any queues. But since we've
already reset fc->connected, those requests would not be useful anyway and
would be flushed when the fuse device is closed.
Next patches will rely on requests being flushed before the superblock is
destroyed.
Use fuse_abort_conn() in cuse_process_init_reply() too, since it makes no
difference there, and we can get rid of fuse_conn_kill().
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch extends fuse_setattr_in, and extends the flush procedure
(fuse_flush_times()) called on ->write_inode() to send the ctime as well as
mtime.
Signed-off-by: Maxim Patlasov <MPatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
...and flush mtime from this. This allows us to use the kernel
infrastructure for writing out dirty metadata (mtime at this point, but
ctime in the next patches and also maybe atime).
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The problem is:
1. write cached data to a file
2. read directly from the same file (via another fd)
The 2nd operation may read stale data, i.e. the one that was in a file
before the 1st op. Problem is in how fuse manages writeback.
When direct op occurs the core kernel code calls filemap_write_and_wait
to flush all the cached ops in flight. But fuse acks the writeback right
after the ->writepages callback exits w/o waiting for the real write to
happen. Thus the subsequent direct op proceeds while the real writeback
is still in flight. This is a problem for backends that reorder operation.
Fix this by making the fuse direct IO callback explicitly wait on the
in-flight writeback to finish.
Signed-off-by: Maxim Patlasov <MPatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Let the kernel maintain i_mtime locally:
- clear S_NOCMTIME
- implement i_op->update_time()
- flush mtime on fsync and last close
- update i_mtime explicitly on truncate and fallocate
Fuse inode flag FUSE_I_MTIME_DIRTY serves as indication that local i_mtime
should be flushed to the server eventually.
Signed-off-by: Maxim Patlasov <MPatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Off (0) by default. Will be used in the next patches and will be turned
on at the very end.
Signed-off-by: Maxim Patlasov <MPatlasov@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
open/release operations require userspace transitions to keep track
of the open count and to perform any FS-specific setup. However,
for some purely read-only FSs which don't need to perform any setup
at open/release time, we can avoid the performance overhead of
calling into userspace for open/release calls.
This patch adds the necessary support to the fuse kernel modules to prevent
open/release operations from hitting in userspace. When the client returns
ENOSYS, we avoid sending the subsequent release to userspace, and also
remember this so that future opens also don't trigger a userspace
operation.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Various read operations (e.g. readlink, readdir) invalidate the cached
attrs for atime changes. This patch adds a new function
'fuse_invalidate_atime', which checks for a read-only super block and
avoids the attr invalidation in that case.
Signed-off-by: Andrew Gallagher <andrewjcg@fb.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Pull vfs updates from Al Viro:
"All kinds of stuff this time around; some more notable parts:
- RCU'd vfsmounts handling
- new primitives for coredump handling
- files_lock is gone
- Bruce's delegations handling series
- exportfs fixes
plus misc stuff all over the place"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (101 commits)
ecryptfs: ->f_op is never NULL
locks: break delegations on any attribute modification
locks: break delegations on link
locks: break delegations on rename
locks: helper functions for delegation breaking
locks: break delegations on unlink
namei: minor vfs_unlink cleanup
locks: implement delegations
locks: introduce new FL_DELEG lock flag
vfs: take i_mutex on renamed file
vfs: rename I_MUTEX_QUOTA now that it's not used for quotas
vfs: don't use PARENT/CHILD lock classes for non-directories
vfs: pull ext4's double-i_mutex-locking into common code
exportfs: fix quadratic behavior in filehandle lookup
exportfs: better variable name
exportfs: move most of reconnect_path to helper function
exportfs: eliminate unused "noprogress" counter
exportfs: stop retrying once we race with rename/remove
exportfs: clear DISCONNECTED on all parents sooner
exportfs: more detailed comment for path_reconnect
...
...which just returns -EBUSY if a directory alias would be created.
This is to be used by fuse mkdir to make sure that a buggy or malicious
userspace filesystem doesn't do anything nasty. Previously fuse used a
private mutex for this purpose, which can now go away.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
As Maxim Patlasov pointed out, it's possible to get a dirty page while it's
copy is still under writeback, despite fuse_page_mkwrite() doing its thing
(direct IO).
This could result in two concurrent write request for the same offset, with
data corruption if they get mixed up.
To prevent this, fuse needs to check and delay such writes. This
implementation does this by:
1. check if page is still under writeout, if so create a new, single page
secondary request for it
2. chain this secondary request onto the in-flight request
2/a. if a seconday request for the same offset was already chained to the
in-flight request, then just copy the contents of the page and discard
the new secondary request. This makes sure that for each page will
have at most two requests associated with it
3. when the in-flight request finished, send off all secondary requests
chained onto it
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Doing dput(parent) is not valid in RCU walk mode. In RCU mode it would
probably be okay to update the parent flags, but it's actually not
necessary most of the time...
So only set the FUSE_I_ADVISE_RDPLUS flag on the parent when the entry was
recently initialized by READDIRPLUS.
This is achieved by setting FUSE_I_INIT_RDPLUS on entries added by
READDIRPLUS and only dropping out of RCU mode if this flag is set.
FUSE_I_INIT_RDPLUS is cleared once the FUSE_I_ADVISE_RDPLUS flag is set in
the parent.
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Cc: stable@vger.kernel.org
The way how fuse calls truncate_pagecache() from fuse_change_attributes()
is completely wrong. Because, w/o i_mutex held, we never sure whether
'oldsize' and 'attr->size' are valid by the time of execution of
truncate_pagecache(inode, oldsize, attr->size). In fact, as soon as we
released fc->lock in the middle of fuse_change_attributes(), we completely
loose control of actions which may happen with given inode until we reach
truncate_pagecache. The list of potentially dangerous actions includes
mmap-ed reads and writes, ftruncate(2) and write(2) extending file size.
The typical outcome of doing truncate_pagecache() with outdated arguments
is data corruption from user point of view. This is (in some sense)
acceptable in cases when the issue is triggered by a change of the file on
the server (i.e. externally wrt fuse operation), but it is absolutely
intolerable in scenarios when a single fuse client modifies a file without
any external intervention. A real life case I discovered by fsx-linux
looked like this:
1. Shrinking ftruncate(2) comes to fuse_do_setattr(). The latter sends
FUSE_SETATTR to the server synchronously, but before getting fc->lock ...
2. fuse_dentry_revalidate() is asynchronously called. It sends FUSE_LOOKUP
to the server synchronously, then calls fuse_change_attributes(). The
latter updates i_size, releases fc->lock, but before comparing oldsize vs
attr->size..
3. fuse_do_setattr() from the first step proceeds by acquiring fc->lock and
updating attributes and i_size, but now oldsize is equal to
outarg.attr.size because i_size has just been updated (step 2). Hence,
fuse_do_setattr() returns w/o calling truncate_pagecache().
4. As soon as ftruncate(2) completes, the user extends file size by
write(2) making a hole in the middle of file, then reads data from the hole
either by read(2) or mmap-ed read. The user expects to get zero data from
the hole, but gets stale data because truncate_pagecache() is not executed
yet.
The scenario above illustrates one side of the problem: not truncating the
page cache even though we should. Another side corresponds to truncating
page cache too late, when the state of inode changed significantly.
Theoretically, the following is possible:
1. As in the previous scenario fuse_dentry_revalidate() discovered that
i_size changed (due to our own fuse_do_setattr()) and is going to call
truncate_pagecache() for some 'new_size' it believes valid right now. But
by the time that particular truncate_pagecache() is called ...
2. fuse_do_setattr() returns (either having called truncate_pagecache() or
not -- it doesn't matter).
3. The file is extended either by write(2) or ftruncate(2) or fallocate(2).
4. mmap-ed write makes a page in the extended region dirty.
The result will be the lost of data user wrote on the fourth step.
The patch is a hotfix resolving the issue in a simplistic way: let's skip
dangerous i_size update and truncate_pagecache if an operation changing
file size is in progress. This simplistic approach looks correct for the
cases w/o external changes. And to handle them properly, more sophisticated
and intrusive techniques (e.g. NFS-like one) would be required. I'd like to
postpone it until the issue is well discussed on the mailing list(s).
Changed in v2:
- improved patch description to cover both sides of the issue.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Cc: stable@vger.kernel.org
Without async DIO write requests to a single file were always serialized.
With async DIO that's no longer the case.
So don't turn on async DIO by default for fear of breaking backward
compatibility.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch improves error handling in fuse_direct_IO(): if we successfully
submitted several fuse requests on behalf of synchronous direct write
extending file and some of them failed, let's try to do our best to clean-up.
Changed in v2: reuse fuse_do_setattr(). Thanks to Brian for suggestion.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch implements passing "struct fuse_io_priv *io" down the stack up to
fuse_send_read/write where it is used to submit request asynchronously.
io->async==0 designates synchronous processing.
Non-trivial part of the patch is changes in fuse_direct_io(): resources
like fuse requests and user pages cannot be released immediately in async
case.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch implements a framework to process an IO request asynchronously. The
idea is to associate several fuse requests with a single kiocb by means of
fuse_io_priv structure. The structure plays the same role for FUSE as 'struct
dio' for direct-io.c.
The framework is supposed to be used like this:
- someone (who wants to process an IO asynchronously) allocates fuse_io_priv
and initializes it setting 'async' field to non-zero value.
- as soon as fuse request is filled, it can be submitted (in non-blocking way)
by fuse_async_req_send()
- when all submitted requests are ACKed by userspace, io->reqs drops to zero
triggering aio_complete()
In case of IO initiated by libaio, aio_complete() will finish processing the
same way as in case of dio_complete() calling aio_complete(). But the
framework may be also used for internal FUSE use when initial IO request
was synchronous (from user perspective), but it's beneficial to process it
asynchronously. Then the caller should wait on kiocb explicitly and
aio_complete() will wake the caller up.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Existing flag fc->blocked is used to suspend request allocation both in case
of many background request submitted and period of time before init_reply
arrives from userspace. Next patch will skip blocking allocations of
synchronous request (disregarding fc->blocked). This is mostly OK, but
we still need to suspend allocations if init_reply is not arrived yet. The
patch introduces flag fc->initialized which will serve this purpose.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
There are two types of processing requests in FUSE: synchronous (via
fuse_request_send()) and asynchronous (via adding to fc->bg_queue).
Fortunately, the type of processing is always known in advance, at the time
of request allocation. This preparatory patch utilizes this fact making
fuse_get_req() aware about the type. Next patches will use it.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
For some filesystems (e.g. GlusterFS), the cost of performing a
normal readdir and readdirplus are identical. Since adaptively
using readdirplus has no benefit for those systems, give
users/filesystems the option to control adaptive readdirplus use.
v2 of this patch incorporates Miklos's suggestion to simplify the code,
as well as improving consistency of macro names and documentation.
Signed-off-by: Eric Wong <normalperson@yhbt.net>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Use the same adaptive readdirplus mechanism as NFS:
http://permalink.gmane.org/gmane.linux.nfs/49299
If the user space implementation wants to disable readdirplus
temporarily, it could just return ENOTSUPP. Then kernel will
recall it with readdir.
Signed-off-by: Feng Shuo <steve.shuo.feng@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Commit c69e8d9c0 added rcu lock to fuse/dir.c It was assuming
that 'task' is some other process but in fact this parameter always
equals to 'current'. Inline this parameter to make it more readable
and remove RCU lock as it is not needed when access current process
credentials.
Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The ability to save page pointers along with lengths and offsets in fuse_req
will be useful to cover several iovec-s with a single fuse_req.
Per-request page_offset is removed because anybody who need it can use
req->page_descs[0].offset instead.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch categorizes all fuse_get_req() invocations into two categories:
- fuse_get_req_nopages(fc) - when caller doesn't care about req->pages
- fuse_get_req(fc, n) - when caller need n page pointers (n > 0)
Adding fuse_get_req_nopages() helps to avoid numerous fuse_get_req(fc, 0)
scattered over code. Now it's clear from the first glance when a caller need
fuse_req with page pointers.
The patch doesn't make any logic changes. In multi-page case, it silly
allocates array of FUSE_MAX_PAGES_PER_REQ page pointers. This will be amended
by future patches.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
The patch removes inline array of FUSE_MAX_PAGES_PER_REQ page pointers from
fuse_req. Instead of that, req->pages may now point either to small inline
array or to an array allocated dynamically.
This essentially means that all callers of fuse_request_alloc[_nofs] should
pass the number of pages needed explicitly.
The patch doesn't make any logic changes.
Signed-off-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
This patch implements readdirplus support in FUSE, similar to NFS.
The payload returned in the readdirplus call contains
'fuse_entry_out' structure thereby providing all the necessary inputs
for 'faking' a lookup() operation on the spot.
If the dentry and inode already existed (for e.g. in a re-run of ls -l)
then just the inode attributes timeout and dentry timeout are refreshed.
With a simple client->network->server implementation of a FUSE based
filesystem, the following performance observations were made:
Test: Performing a filesystem crawl over 20,000 files with
sh# time ls -lR /mnt
Without readdirplus:
Run 1: 18.1s
Run 2: 16.0s
Run 3: 16.2s
With readdirplus:
Run 1: 4.1s
Run 2: 3.8s
Run 3: 3.8s
The performance improvement is significant as it avoided 20,000 upcalls
calls (lookup). Cache consistency is no worse than what already is.
Signed-off-by: Anand V. Avati <avati@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Use kuid_t and kgid_t in struct fuse_conn and struct fuse_mount_data.
The connection between between a fuse filesystem and a fuse daemon is
established when a fuse filesystem is mounted and provided with a file
descriptor the fuse daemon created by opening /dev/fuse.
For now restrict the communication of uids and gids between the fuse
filesystem and the fuse daemon to the initial user namespace. Enforce
this by verifying the file descriptor passed to the mount of fuse was
opened in the initial user namespace. Ensuring the mount happens in
the initial user namespace is not necessary as mounts from non-initial
user namespaces are not yet allowed.
In fuse_req_init_context convert the currrent fsuid and fsgid into the
initial user namespace for the request that will be sent to the fuse
daemon.
In fuse_fill_attr convert the uid and gid passed from the fuse daemon
from the initial user namespace into kuids and kgids.
In iattr_to_fattr called from fuse_setattr convert kuids and kgids
into the uids and gids in the initial user namespace before passing
them to the fuse filesystem.
In fuse_change_attributes_common called from fuse_dentry_revalidate,
fuse_permission, fuse_geattr, and fuse_setattr, and fuse_iget convert
the uid and gid from the fuse daemon into a kuid and a kgid to store
on the fuse inode.
By default fuse mounts are restricted to task whose uid, suid, and
euid matches the fuse user_id and whose gid, sgid, and egid matches
the fuse group id. Convert the user_id and group_id mount options
into kuids and kgids at mount time, and use uid_eq and gid_eq to
compare the in fuse_allow_task.
Cc: Miklos Szeredi <miklos@szeredi.hu>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Now we store attr->ino at inode->i_ino, return attr->ino at the
first time and then return inode->i_ino if the attribute timeout
isn't expired. That's wrong on 32 bit platforms because attr->ino
is 64 bit and inode->i_ino is 32 bit in this case.
Fix this by saving 64 bit ino in fuse_inode structure and returning
it every time we call getattr. Also squash attr->ino into inode->i_ino
explicitly.
Signed-off-by: Pavel Shilovsky <piastry@etersoft.ru>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
FUSE: Notifying the kernel of deletion.
fuse: support ioctl on directories
fuse: Use kcalloc instead of kzalloc to allocate array
fuse: llseek optimize SEEK_CUR and SEEK_SET
Miklos Szeredi