Provide read-and-reset objects- and blocks-released counters for cachefilesd
to use to work out whether there's anything new that can be culled.
One of the problems cachefilesd has is that if all the objects in the cache
are pinned by inodes lying dormant in the kernel inode cache, there isn't
anything for it to cull. In such a case, it just spins around walking the
filesystem tree and scanning for something to cull. This eats up a lot of
CPU time.
By telling cachefilesd if there have been any releases, the daemon can
sleep until there is the possibility of something to do.
cachefilesd finds this information by the following means:
(1) When the control fd is read, the kernel presents a list of values of
interest. "freleased=N" and "breleased=N" are added to this list to
indicate the number of files released and number of blocks released
since the last read call. At this point the counters are reset.
(2) POLLIN is signalled if the number of files released becomes greater
than 0.
Note that by 'released' it just means that the kernel has released its
interest in those files for the moment, not necessarily that the files
should be deleted from the cache.
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Steve Dickson <steved@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
parallel to mutex_{lock,unlock,trylock,is_locked,lock_nested},
inode_foo(inode) being mutex_foo(&inode->i_mutex).
Please, use those for access to ->i_mutex; over the coming cycle
->i_mutex will become rwsem, with ->lookup() done with it held
only shared.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
cachefiles requires that s_blocksize in the cache is not greater than
PAGE_SIZE, and performs the check every time a block is accessed.
Move the test to the place where the file is "opened", where other
file-validity tests are performed.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Cachefiles should perform fs modifications (eg. vfs_unlink()) on the top layer
only and should not attempt to alter the lower layer.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Count the number of objects that get culled by the cache backend and the
number of objects that the cache backend declines to instantiate due to lack
of space in the cache.
These numbers are made available through /proc/fs/fscache/stats
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Steve Dickson <steved@redhat.com>
Acked-by: Jeff Layton <jeff.layton@primarydata.com>
Fix up the following scripted S_ISDIR/S_ISREG/S_ISLNK conversions (or lack
thereof) in cachefiles:
(1) Cachefiles mostly wants to use d_can_lookup() rather than d_is_dir() as
it doesn't want to deal with automounts in its cache.
(2) Coccinelle didn't find S_IS* expressions in ASSERT() statements in
cachefiles.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Convert the following where appropriate:
(1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry).
(2) S_ISREG(dentry->d_inode) to d_is_reg(dentry).
(3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more
complicated than it appears as some calls should be converted to
d_can_lookup() instead. The difference is whether the directory in
question is a real dir with a ->lookup op or whether it's a fake dir with
a ->d_automount op.
In some circumstances, we can subsume checks for dentry->d_inode not being
NULL into this, provided we the code isn't in a filesystem that expects
d_inode to be NULL if the dirent really *is* negative (ie. if we're going to
use d_inode() rather than d_backing_inode() to get the inode pointer).
Note that the dentry type field may be set to something other than
DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS
manages the fall-through from a negative dentry to a lower layer. In such a
case, the dentry type of the negative union dentry is set to the same as the
type of the lower dentry.
However, if you know d_inode is not NULL at the call site, then you can use
the d_is_xxx() functions even in a filesystem.
There is one further complication: a 0,0 chardev dentry may be labelled
DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was
intended for special directory entry types that don't have attached inodes.
The following perl+coccinelle script was used:
use strict;
my @callers;
open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') ||
die "Can't grep for S_ISDIR and co. callers";
@callers = <$fd>;
close($fd);
unless (@callers) {
print "No matches\n";
exit(0);
}
my @cocci = (
'@@',
'expression E;',
'@@',
'',
'- S_ISLNK(E->d_inode->i_mode)',
'+ d_is_symlink(E)',
'',
'@@',
'expression E;',
'@@',
'',
'- S_ISDIR(E->d_inode->i_mode)',
'+ d_is_dir(E)',
'',
'@@',
'expression E;',
'@@',
'',
'- S_ISREG(E->d_inode->i_mode)',
'+ d_is_reg(E)' );
my $coccifile = "tmp.sp.cocci";
open($fd, ">$coccifile") || die $coccifile;
print($fd "$_\n") || die $coccifile foreach (@cocci);
close($fd);
foreach my $file (@callers) {
chomp $file;
print "Processing ", $file, "\n";
system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 ||
die "spatch failed";
}
[AV: overlayfs parts skipped]
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
When CacheFiles cache objects are in use, they have in-memory representations,
as defined by the cachefiles_object struct. These are kept in a tree rooted in
the cache and indexed by dentry pointer (since there's a unique mapping between
object index key and dentry).
Collisions can occur between a representation already in the tree and a new
representation being set up because it takes time to dispose of an old
representation - particularly if it must be unlinked or renamed.
When such a collision occurs, cachefiles_mark_object_active() is meant to check
to see if the old, already-present representation is in the process of being
discarded (ie. FSCACHE_OBJECT_IS_LIVE is not set on it) - and, if so, wait for
the representation to be removed (ie. CACHEFILES_OBJECT_ACTIVE is then
cleared).
However, the test for whether the old representation is still live is checking
the new object - which always will be live at this point. This leads to an
oops looking like:
CacheFiles: Error: Unexpected object collision
object: OBJ1b354
objstate=LOOK_UP_OBJECT fl=8 wbusy=2 ev=0[0]
ops=0 inp=0 exc=0
parent=ffff88053f5417c0
cookie=ffff880538f202a0 [pr=ffff8805381b7160 nd=ffff880509c6eb78 fl=27]
key=[8] '2490000000000000'
xobject: OBJ1a600
xobjstate=DROP_OBJECT fl=70 wbusy=2 ev=0[0]
xops=0 inp=0 exc=0
xparent=ffff88053f5417c0
xcookie=ffff88050f4cbf70 [pr=ffff8805381b7160 nd= (null) fl=12]
------------[ cut here ]------------
kernel BUG at fs/cachefiles/namei.c:200!
...
Workqueue: fscache_object fscache_object_work_func [fscache]
...
RIP: ... cachefiles_walk_to_object+0x7ea/0x860 [cachefiles]
...
Call Trace:
[<ffffffffa04dadd8>] ? cachefiles_lookup_object+0x58/0x100 [cachefiles]
[<ffffffffa01affe9>] ? fscache_look_up_object+0xb9/0x1d0 [fscache]
[<ffffffffa01afc4d>] ? fscache_parent_ready+0x2d/0x80 [fscache]
[<ffffffffa01b0672>] ? fscache_object_work_func+0x92/0x1f0 [fscache]
[<ffffffff8107e82b>] ? process_one_work+0x16b/0x400
[<ffffffff8107fc16>] ? worker_thread+0x116/0x380
[<ffffffff8107fb00>] ? manage_workers.isra.21+0x290/0x290
[<ffffffff81085edc>] ? kthread+0xbc/0xe0
[<ffffffff81085e20>] ? flush_kthread_worker+0x80/0x80
[<ffffffff81502d0c>] ? ret_from_fork+0x7c/0xb0
[<ffffffff81085e20>] ? flush_kthread_worker+0x80/0x80
Reported-by: Manuel Schölling <manuel.schoelling@gmx.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Steve Dickson <steved@redhat.com>
Commit 0227d6abb3 ("fs/cachefiles: replace kerror by pr_err") didn't
include newline featuring in original kerror definition
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Reported-by: David Howells <dhowells@redhat.com>
Acked-by: David Howells <dhowells@redhat.com>
Cc: <stable@vger.kernel.org> [3.16.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Not all filesystems now provide the rename i_op - ext4 for one - but rather
provide the rename2 i_op. CacheFiles checks that the filesystem has rename
and so will reject ext4 now with EPERM:
CacheFiles: Failed to register: -1
Fix this by checking for rename2 as an alternative. The call to vfs_rename()
actually handles selection of the appropriate function, so we needn't worry
about that.
Turning on debugging shows:
[cachef] ==> cachefiles_get_directory(,,cache)
[cachef] subdir -> ffff88000b22b778 positive
[cachef] <== cachefiles_get_directory() = -1 [check]
where -1 is EPERM.
Signed-off-by: David Howells <dhowells@redhat.com>
Also add pr_fmt in internal.h
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull vfs updates from Al Viro:
"The first vfs pile, with deep apologies for being very late in this
window.
Assorted cleanups and fixes, plus a large preparatory part of iov_iter
work. There's a lot more of that, but it'll probably go into the next
merge window - it *does* shape up nicely, removes a lot of
boilerplate, gets rid of locking inconsistencie between aio_write and
splice_write and I hope to get Kent's direct-io rewrite merged into
the same queue, but some of the stuff after this point is having
(mostly trivial) conflicts with the things already merged into
mainline and with some I want more testing.
This one passes LTP and xfstests without regressions, in addition to
usual beating. BTW, readahead02 in ltp syscalls testsuite has started
giving failures since "mm/readahead.c: fix readahead failure for
memoryless NUMA nodes and limit readahead pages" - might be a false
positive, might be a real regression..."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
missing bits of "splice: fix racy pipe->buffers uses"
cifs: fix the race in cifs_writev()
ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
kill generic_file_buffered_write()
ocfs2_file_aio_write(): switch to generic_perform_write()
ceph_aio_write(): switch to generic_perform_write()
xfs_file_buffered_aio_write(): switch to generic_perform_write()
export generic_perform_write(), start getting rid of generic_file_buffer_write()
generic_file_direct_write(): get rid of ppos argument
btrfs_file_aio_write(): get rid of ppos
kill the 5th argument of generic_file_buffered_write()
kill the 4th argument of __generic_file_aio_write()
lustre: don't open-code kernel_recvmsg()
ocfs2: don't open-code kernel_recvmsg()
drbd: don't open-code kernel_recvmsg()
constify blk_rq_map_user_iov() and friends
lustre: switch to kernel_sendmsg()
ocfs2: don't open-code kernel_sendmsg()
take iov_iter stuff to mm/iov_iter.c
process_vm_access: tidy up a bit
...
Add flags to security_path_rename() and security_inode_rename() hooks.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
Add new renameat2 syscall, which is the same as renameat with an added
flags argument.
Pass flags to vfs_rename() and to i_op->rename() as well.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
We need to break delegations on any operation that changes the set of
links pointing to an inode. Start with unlink.
Such operations also hold the i_mutex on a parent directory. Breaking a
delegation may require waiting for a timeout (by default 90 seconds) in
the case of a unresponsive NFS client. To avoid blocking all directory
operations, we therefore drop locks before waiting for the delegation.
The logic then looks like:
acquire locks
...
test for delegation; if found:
take reference on inode
release locks
wait for delegation break
drop reference on inode
retry
It is possible this could never terminate. (Even if we take precautions
to prevent another delegation being acquired on the same inode, we could
get a different inode on each retry.) But this seems very unlikely.
The initial test for a delegation happens after the lock on the target
inode is acquired, but the directory inode may have been acquired
further up the call stack. We therefore add a "struct inode **"
argument to any intervening functions, which we use to pass the inode
back up to the caller in the case it needs a delegation synchronously
broken.
Cc: David Howells <dhowells@redhat.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Dustin Kirkland <dustin.kirkland@gazzang.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Don't try to dump the index key that distinguishes an object if netfs
data in the cookie the object refers to has been cleared (ie. the
cookie has passed most of the way through
__fscache_relinquish_cookie()).
Since the netfs holds the index key, we can't get at it once the ->def
and ->netfs_data pointers have been cleared - and a NULL pointer
exception will ensue, usually just after a:
CacheFiles: Error: Unexpected object collision
error is reported.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix object state machine to have separate work and wait states as that makes
it easier to envision.
There are now three kinds of state:
(1) Work state. This is an execution state. No event processing is performed
by a work state. The function attached to a work state returns a pointer
indicating the next state to which the OSM should transition. Returning
NO_TRANSIT repeats the current state, but goes back to the scheduler
first.
(2) Wait state. This is an event processing state. No execution is
performed by a wait state. Wait states are just tables of "if event X
occurs, clear it and transition to state Y". The dispatcher returns to
the scheduler if none of the events in which the wait state has an
interest are currently pending.
(3) Out-of-band state. This is a special work state. Transitions to normal
states can be overridden when an unexpected event occurs (eg. I/O error).
Instead the dispatcher disables and clears the OOB event and transits to
the specified work state. This then acts as an ordinary work state,
though object->state points to the overridden destination. Returning
NO_TRANSIT resumes the overridden transition.
In addition, the states have names in their definitions, so there's no need for
tables of state names. Further, the EV_REQUEUE event is no longer necessary as
that is automatic for work states.
Since the states are now separate structs rather than values in an enum, it's
not possible to use comparisons other than (non-)equality between them, so use
some object->flags to indicate what phase an object is in.
The EV_RELEASE, EV_RETIRE and EV_WITHDRAW events have been squished into one
(EV_KILL). An object flag now carries the information about retirement.
Similarly, the RELEASING, RECYCLING and WITHDRAWING states have been merged
into an KILL_OBJECT state and additional states have been added for handling
waiting dependent objects (JUMPSTART_DEPS and KILL_DEPENDENTS).
A state has also been added for synchronising with parent object initialisation
(WAIT_FOR_PARENT) and another for initiating look up (PARENT_READY).
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-By: Milosz Tanski <milosz@adfin.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Wrap checks on object state (mostly outside of fs/fscache/object.c) with
inline functions so that the mechanism can be replaced.
Some of the state checks within object.c are left as-is as they will be
replaced.
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-By: Milosz Tanski <milosz@adfin.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Just some cleanup.
(And note the caller of this function may, for example, call vfs_unlink
on a child, so the "1" (I_MUTEX_PARENT) really was what was intended
here.)
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-By: Milosz Tanski <milosz@adfin.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Don't mask off the object event mask when printing it. That way it can be seen
if threre are bits set that shouldn't be.
Signed-off-by: David Howells <dhowells@redhat.com>
Add calls to path-based security hooks into CacheFiles as, unlike inode-based
security, these aren't implicit in the vfs_mkdir() and similar calls.
Reported-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
Make fscache object state transition callbacks use workqueue instead
of slow-work. New dedicated unbound CPU workqueue fscache_object_wq
is created. get/put callbacks are renamed and modified to take
@object and called directly from the enqueue wrapper and the work
function. While at it, make all open coded instances of get/put to
use fscache_get/put_object().
* Unbound workqueue is used.
* work_busy() output is printed instead of slow-work flags in object
debugging outputs. They mean basically the same thing bit-for-bit.
* sysctl fscache.object_max_active added to control concurrency. The
default value is nr_cpus clamped between 4 and
WQ_UNBOUND_MAX_ACTIVE.
* slow_work_sleep_till_thread_needed() is replaced with fscache
private implementation fscache_object_sleep_till_congested() which
waits on fscache_object_wq congestion.
* debugfs support is dropped for now. Tracing API based debug
facility is planned to be added.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David Howells <dhowells@redhat.com>
Fix an occasional EIO returned by a call to vfs_unlink():
[ 4868.465413] CacheFiles: I/O Error: Unlink failed
[ 4868.465444] FS-Cache: Cache cachefiles stopped due to I/O error
[ 4947.320011] CacheFiles: File cache on md3 unregistering
[ 4947.320041] FS-Cache: Withdrawing cache "mycache"
[ 5127.348683] FS-Cache: Cache "mycache" added (type cachefiles)
[ 5127.348716] CacheFiles: File cache on md3 registered
[ 7076.871081] CacheFiles: I/O Error: Unlink failed
[ 7076.871130] FS-Cache: Cache cachefiles stopped due to I/O error
[ 7116.780891] CacheFiles: File cache on md3 unregistering
[ 7116.780937] FS-Cache: Withdrawing cache "mycache"
[ 7296.813394] FS-Cache: Cache "mycache" added (type cachefiles)
[ 7296.813432] CacheFiles: File cache on md3 registered
What happens is this:
(1) A cached NFS file is seen to have become out of date, so NFS retires the
object and immediately acquires a new object with the same key.
(2) Retirement of the old object is done asynchronously - so the lookup/create
to generate the new object may be done first.
This can be a problem as the old object and the new object must exist at
the same point in the backing filesystem (i.e. they must have the same
pathname).
(3) The lookup for the new object sees that a backing file already exists,
checks to see whether it is valid and sees that it isn't. It then deletes
that file and creates a new one on disk.
(4) The retirement phase for the old file is then performed. It tries to
delete the dentry it has, but ext4_unlink() returns -EIO because the inode
attached to that dentry no longer matches the inode number associated with
the filename in the parent directory.
The trace below shows this quite well.
[md5sum] ==> __fscache_relinquish_cookie(ffff88002d12fb58{NFS.fh,ffff88002ce62100},1)
[md5sum] ==> __fscache_acquire_cookie({NFS.server},{NFS.fh},ffff88002ce62100)
NFS has retired the old cookie and asked for a new one.
[kslowd] ==> fscache_object_state_machine({OBJ52,OBJECT_ACTIVE,24})
[kslowd] <== fscache_object_state_machine() [->OBJECT_DYING]
[kslowd] ==> fscache_object_state_machine({OBJ53,OBJECT_INIT,0})
[kslowd] <== fscache_object_state_machine() [->OBJECT_LOOKING_UP]
[kslowd] ==> fscache_object_state_machine({OBJ52,OBJECT_DYING,24})
[kslowd] <== fscache_object_state_machine() [->OBJECT_RECYCLING]
The old object (OBJ52) is going through the terminal states to get rid of it,
whilst the new object - (OBJ53) - is coming into being.
[kslowd] ==> fscache_object_state_machine({OBJ53,OBJECT_LOOKING_UP,0})
[kslowd] ==> cachefiles_walk_to_object({ffff88003029d8b8},OBJ53,@68,)
[kslowd] lookup '@68'
[kslowd] next -> ffff88002ce41bd0 positive
[kslowd] advance
[kslowd] lookup 'Es0g00og0_Nd_XCYe3BOzvXrsBLMlN6aw16M1htaA'
[kslowd] next -> ffff8800369faac8 positive
The new object has looked up the subdir in which the file would be in (getting
dentry ffff88002ce41bd0) and then looked up the file itself (getting dentry
ffff8800369faac8).
[kslowd] validate 'Es0g00og0_Nd_XCYe3BOzvXrsBLMlN6aw16M1htaA'
[kslowd] ==> cachefiles_bury_object(,'@68','Es0g00og0_Nd_XCYe3BOzvXrsBLMlN6aw16M1htaA')
[kslowd] remove ffff8800369faac8 from ffff88002ce41bd0
[kslowd] unlink stale object
[kslowd] <== cachefiles_bury_object() = 0
It then checks the file's xattrs to see if it's valid. NFS says that the
auxiliary data indicate the file is out of date (obvious to us - that's why NFS
ditched the old version and got a new one). CacheFiles then deletes the old
file (dentry ffff8800369faac8).
[kslowd] redo lookup
[kslowd] lookup 'Es0g00og0_Nd_XCYe3BOzvXrsBLMlN6aw16M1htaA'
[kslowd] next -> ffff88002cd94288 negative
[kslowd] create -> ffff88002cd94288{ffff88002cdaf238{ino=148247}}
CacheFiles then redoes the lookup and gets a negative result in a new dentry
(ffff88002cd94288) which it then creates a file for.
[kslowd] ==> cachefiles_mark_object_active(,OBJ53)
[kslowd] <== cachefiles_mark_object_active() = 0
[kslowd] === OBTAINED_OBJECT ===
[kslowd] <== cachefiles_walk_to_object() = 0 [148247]
[kslowd] <== fscache_object_state_machine() [->OBJECT_AVAILABLE]
The new object is then marked active and the state machine moves to the
available state - at which point NFS can start filling the object.
[kslowd] ==> fscache_object_state_machine({OBJ52,OBJECT_RECYCLING,20})
[kslowd] ==> fscache_release_object()
[kslowd] ==> cachefiles_drop_object({OBJ52,2})
[kslowd] ==> cachefiles_delete_object(,OBJ52{ffff8800369faac8})
The old object, meanwhile, goes on with being retired. If allocation occurs
first, cachefiles_delete_object() has to wait for dir->d_inode->i_mutex to
become available before it can continue.
[kslowd] ==> cachefiles_bury_object(,'@68','Es0g00og0_Nd_XCYe3BOzvXrsBLMlN6aw16M1htaA')
[kslowd] remove ffff8800369faac8 from ffff88002ce41bd0
[kslowd] unlink stale object
EXT4-fs warning (device sda6): ext4_unlink: Inode number mismatch in unlink (148247!=148193)
CacheFiles: I/O Error: Unlink failed
FS-Cache: Cache cachefiles stopped due to I/O error
CacheFiles then tries to delete the file for the old object, but the dentry it
has (ffff8800369faac8) no longer points to a valid inode for that directory
entry, and so ext4_unlink() returns -EIO when de->inode does not match i_ino.
[kslowd] <== cachefiles_bury_object() = -5
[kslowd] <== cachefiles_delete_object() = -5
[kslowd] <== fscache_object_state_machine() [->OBJECT_DEAD]
[kslowd] ==> fscache_object_state_machine({OBJ53,OBJECT_AVAILABLE,0})
[kslowd] <== fscache_object_state_machine() [->OBJECT_ACTIVE]
(Note that the above trace includes extra information beyond that produced by
the upstream code).
The fix is to note when an object that is being retired has had its object
deleted preemptively by a replacement object that is being created, and to
skip the second removal attempt in such a case.
Reported-by: Greg M <gregm@servu.net.au>
Reported-by: Mark Moseley <moseleymark@gmail.com>
Reported-by: Romain DEGEZ <romain.degez@smartjog.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
cachefiles_delete_object() can race with rename. It gets the parent directory
of the object it's asked to delete, then locks it - but rename may have changed
the object's parent between the get and the completion of the lock.
However, if such a circumstance is detected, we abandon our attempt to delete
the object - since it's no longer in the index key path, it won't be seen
again by lookups of that key. The assumption is that cachefilesd may have
culled it by renaming it to the graveyard for later destruction.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Catch an overly long wait for an old, dying active object when we want to
replace it with a new one. The probability is that all the slow-work threads
are hogged, and the delete can't get a look in.
What we do instead is:
(1) if there's nothing in the slow work queue, we sleep until either the dying
object has finished dying or there is something in the slow work queue
behind which we can queue our object.
(2) if there is something in the slow work queue, we return ETIMEDOUT to
fscache_lookup_object(), which then puts us back on the slow work queue,
presumably behind the deletion that we're blocked by. We are then
deferred for a while until we work our way back through the queue -
without blocking a slow-work thread unnecessarily.
A backtrace similar to the following may appear in the log without this patch:
INFO: task kslowd004:5711 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kslowd004 D 0000000000000000 0 5711 2 0x00000080
ffff88000340bb80 0000000000000046 ffff88002550d000 0000000000000000
ffff88002550d000 0000000000000007 ffff88000340bfd8 ffff88002550d2a8
000000000000ddf0 00000000000118c0 00000000000118c0 ffff88002550d2a8
Call Trace:
[<ffffffff81058e21>] ? trace_hardirqs_on+0xd/0xf
[<ffffffffa011c4d8>] ? cachefiles_wait_bit+0x0/0xd [cachefiles]
[<ffffffffa011c4e1>] cachefiles_wait_bit+0x9/0xd [cachefiles]
[<ffffffff81353153>] __wait_on_bit+0x43/0x76
[<ffffffff8111ae39>] ? ext3_xattr_get+0x1ec/0x270
[<ffffffff813531ef>] out_of_line_wait_on_bit+0x69/0x74
[<ffffffffa011c4d8>] ? cachefiles_wait_bit+0x0/0xd [cachefiles]
[<ffffffff8104c125>] ? wake_bit_function+0x0/0x2e
[<ffffffffa011bc79>] cachefiles_mark_object_active+0x203/0x23b [cachefiles]
[<ffffffffa011c209>] cachefiles_walk_to_object+0x558/0x827 [cachefiles]
[<ffffffffa011a429>] cachefiles_lookup_object+0xac/0x12a [cachefiles]
[<ffffffffa00aa1e9>] fscache_lookup_object+0x1c7/0x214 [fscache]
[<ffffffffa00aafc5>] fscache_object_state_machine+0xa5/0x52d [fscache]
[<ffffffffa00ab4ac>] fscache_object_slow_work_execute+0x5f/0xa0 [fscache]
[<ffffffff81082093>] slow_work_execute+0x18f/0x2d1
[<ffffffff8108239a>] slow_work_thread+0x1c5/0x308
[<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
[<ffffffff810821d5>] ? slow_work_thread+0x0/0x308
[<ffffffff8104be91>] kthread+0x7a/0x82
[<ffffffff8100beda>] child_rip+0xa/0x20
[<ffffffff8100b87c>] ? restore_args+0x0/0x30
[<ffffffff8104be17>] ? kthread+0x0/0x82
[<ffffffff8100bed0>] ? child_rip+0x0/0x20
1 lock held by kslowd004/5711:
#0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [<ffffffffa011be64>] cachefiles_walk_to_object+0x1b3/0x827 [cachefiles]
Signed-off-by: David Howells <dhowells@redhat.com>
Show more debugging information if cachefiles_mark_object_active() is asked to
activate an active object.
This may happen, for instance, if the netfs tries to register an object with
the same key multiple times.
The code is changed to (a) get the appropriate object lock to protect the
cookie pointer whilst we dereference it, and (b) get and display the cookie key
if available.
Signed-off-by: David Howells <dhowells@redhat.com>
Add an FS-Cache cache-backend that permits a mounted filesystem to be used as a
backing store for the cache.
CacheFiles uses a userspace daemon to do some of the cache management - such as
reaping stale nodes and culling. This is called cachefilesd and lives in
/sbin. The source for the daemon can be downloaded from:
http://people.redhat.com/~dhowells/cachefs/cachefilesd.c
And an example configuration from:
http://people.redhat.com/~dhowells/cachefs/cachefilesd.conf
The filesystem and data integrity of the cache are only as good as those of the
filesystem providing the backing services. Note that CacheFiles does not
attempt to journal anything since the journalling interfaces of the various
filesystems are very specific in nature.
CacheFiles creates a misc character device - "/dev/cachefiles" - that is used
to communication with the daemon. Only one thing may have this open at once,
and whilst it is open, a cache is at least partially in existence. The daemon
opens this and sends commands down it to control the cache.
CacheFiles is currently limited to a single cache.
CacheFiles attempts to maintain at least a certain percentage of free space on
the filesystem, shrinking the cache by culling the objects it contains to make
space if necessary - see the "Cache Culling" section. This means it can be
placed on the same medium as a live set of data, and will expand to make use of
spare space and automatically contract when the set of data requires more
space.
============
REQUIREMENTS
============
The use of CacheFiles and its daemon requires the following features to be
available in the system and in the cache filesystem:
- dnotify.
- extended attributes (xattrs).
- openat() and friends.
- bmap() support on files in the filesystem (FIBMAP ioctl).
- The use of bmap() to detect a partial page at the end of the file.
It is strongly recommended that the "dir_index" option is enabled on Ext3
filesystems being used as a cache.
=============
CONFIGURATION
=============
The cache is configured by a script in /etc/cachefilesd.conf. These commands
set up cache ready for use. The following script commands are available:
(*) brun <N>%
(*) bcull <N>%
(*) bstop <N>%
(*) frun <N>%
(*) fcull <N>%
(*) fstop <N>%
Configure the culling limits. Optional. See the section on culling
The defaults are 7% (run), 5% (cull) and 1% (stop) respectively.
The commands beginning with a 'b' are file space (block) limits, those
beginning with an 'f' are file count limits.
(*) dir <path>
Specify the directory containing the root of the cache. Mandatory.
(*) tag <name>
Specify a tag to FS-Cache to use in distinguishing multiple caches.
Optional. The default is "CacheFiles".
(*) debug <mask>
Specify a numeric bitmask to control debugging in the kernel module.
Optional. The default is zero (all off). The following values can be
OR'd into the mask to collect various information:
1 Turn on trace of function entry (_enter() macros)
2 Turn on trace of function exit (_leave() macros)
4 Turn on trace of internal debug points (_debug())
This mask can also be set through sysfs, eg:
echo 5 >/sys/modules/cachefiles/parameters/debug
==================
STARTING THE CACHE
==================
The cache is started by running the daemon. The daemon opens the cache device,
configures the cache and tells it to begin caching. At that point the cache
binds to fscache and the cache becomes live.
The daemon is run as follows:
/sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>]
The flags are:
(*) -d
Increase the debugging level. This can be specified multiple times and
is cumulative with itself.
(*) -s
Send messages to stderr instead of syslog.
(*) -n
Don't daemonise and go into background.
(*) -f <configfile>
Use an alternative configuration file rather than the default one.
===============
THINGS TO AVOID
===============
Do not mount other things within the cache as this will cause problems. The
kernel module contains its own very cut-down path walking facility that ignores
mountpoints, but the daemon can't avoid them.
Do not create, rename or unlink files and directories in the cache whilst the
cache is active, as this may cause the state to become uncertain.
Renaming files in the cache might make objects appear to be other objects (the
filename is part of the lookup key).
Do not change or remove the extended attributes attached to cache files by the
cache as this will cause the cache state management to get confused.
Do not create files or directories in the cache, lest the cache get confused or
serve incorrect data.
Do not chmod files in the cache. The module creates things with minimal
permissions to prevent random users being able to access them directly.
=============
CACHE CULLING
=============
The cache may need culling occasionally to make space. This involves
discarding objects from the cache that have been used less recently than
anything else. Culling is based on the access time of data objects. Empty
directories are culled if not in use.
Cache culling is done on the basis of the percentage of blocks and the
percentage of files available in the underlying filesystem. There are six
"limits":
(*) brun
(*) frun
If the amount of free space and the number of available files in the cache
rises above both these limits, then culling is turned off.
(*) bcull
(*) fcull
If the amount of available space or the number of available files in the
cache falls below either of these limits, then culling is started.
(*) bstop
(*) fstop
If the amount of available space or the number of available files in the
cache falls below either of these limits, then no further allocation of
disk space or files is permitted until culling has raised things above
these limits again.
These must be configured thusly:
0 <= bstop < bcull < brun < 100
0 <= fstop < fcull < frun < 100
Note that these are percentages of available space and available files, and do
_not_ appear as 100 minus the percentage displayed by the "df" program.
The userspace daemon scans the cache to build up a table of cullable objects.
These are then culled in least recently used order. A new scan of the cache is
started as soon as space is made in the table. Objects will be skipped if
their atimes have changed or if the kernel module says it is still using them.
===============
CACHE STRUCTURE
===============
The CacheFiles module will create two directories in the directory it was
given:
(*) cache/
(*) graveyard/
The active cache objects all reside in the first directory. The CacheFiles
kernel module moves any retired or culled objects that it can't simply unlink
to the graveyard from which the daemon will actually delete them.
The daemon uses dnotify to monitor the graveyard directory, and will delete
anything that appears therein.
The module represents index objects as directories with the filename "I..." or
"J...". Note that the "cache/" directory is itself a special index.
Data objects are represented as files if they have no children, or directories
if they do. Their filenames all begin "D..." or "E...". If represented as a
directory, data objects will have a file in the directory called "data" that
actually holds the data.
Special objects are similar to data objects, except their filenames begin
"S..." or "T...".
If an object has children, then it will be represented as a directory.
Immediately in the representative directory are a collection of directories
named for hash values of the child object keys with an '@' prepended. Into
this directory, if possible, will be placed the representations of the child
objects:
INDEX INDEX INDEX DATA FILES
========= ========== ================================= ================
cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400
cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry
cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry
cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...FP1ry
If the key is so long that it exceeds NAME_MAX with the decorations added on to
it, then it will be cut into pieces, the first few of which will be used to
make a nest of directories, and the last one of which will be the objects
inside the last directory. The names of the intermediate directories will have
'+' prepended:
J1223/@23/+xy...z/+kl...m/Epqr
Note that keys are raw data, and not only may they exceed NAME_MAX in size,
they may also contain things like '/' and NUL characters, and so they may not
be suitable for turning directly into a filename.
To handle this, CacheFiles will use a suitably printable filename directly and
"base-64" encode ones that aren't directly suitable. The two versions of
object filenames indicate the encoding:
OBJECT TYPE PRINTABLE ENCODED
=============== =============== ===============
Index "I..." "J..."
Data "D..." "E..."
Special "S..." "T..."
Intermediate directories are always "@" or "+" as appropriate.
Each object in the cache has an extended attribute label that holds the object
type ID (required to distinguish special objects) and the auxiliary data from
the netfs. The latter is used to detect stale objects in the cache and update
or retire them.
Note that CacheFiles will erase from the cache any file it doesn't recognise or
any file of an incorrect type (such as a FIFO file or a device file).
==========================
SECURITY MODEL AND SELINUX
==========================
CacheFiles is implemented to deal properly with the LSM security features of
the Linux kernel and the SELinux facility.
One of the problems that CacheFiles faces is that it is generally acting on
behalf of a process, and running in that process's context, and that includes a
security context that is not appropriate for accessing the cache - either
because the files in the cache are inaccessible to that process, or because if
the process creates a file in the cache, that file may be inaccessible to other
processes.
The way CacheFiles works is to temporarily change the security context (fsuid,
fsgid and actor security label) that the process acts as - without changing the
security context of the process when it the target of an operation performed by
some other process (so signalling and suchlike still work correctly).
When the CacheFiles module is asked to bind to its cache, it:
(1) Finds the security label attached to the root cache directory and uses
that as the security label with which it will create files. By default,
this is:
cachefiles_var_t
(2) Finds the security label of the process which issued the bind request
(presumed to be the cachefilesd daemon), which by default will be:
cachefilesd_t
and asks LSM to supply a security ID as which it should act given the
daemon's label. By default, this will be:
cachefiles_kernel_t
SELinux transitions the daemon's security ID to the module's security ID
based on a rule of this form in the policy.
type_transition <daemon's-ID> kernel_t : process <module's-ID>;
For instance:
type_transition cachefilesd_t kernel_t : process cachefiles_kernel_t;
The module's security ID gives it permission to create, move and remove files
and directories in the cache, to find and access directories and files in the
cache, to set and access extended attributes on cache objects, and to read and
write files in the cache.
The daemon's security ID gives it only a very restricted set of permissions: it
may scan directories, stat files and erase files and directories. It may
not read or write files in the cache, and so it is precluded from accessing the
data cached therein; nor is it permitted to create new files in the cache.
There are policy source files available in:
http://people.redhat.com/~dhowells/fscache/cachefilesd-0.8.tar.bz2
and later versions. In that tarball, see the files:
cachefilesd.te
cachefilesd.fc
cachefilesd.if
They are built and installed directly by the RPM.
If a non-RPM based system is being used, then copy the above files to their own
directory and run:
make -f /usr/share/selinux/devel/Makefile
semodule -i cachefilesd.pp
You will need checkpolicy and selinux-policy-devel installed prior to the
build.
By default, the cache is located in /var/fscache, but if it is desirable that
it should be elsewhere, than either the above policy files must be altered, or
an auxiliary policy must be installed to label the alternate location of the
cache.
For instructions on how to add an auxiliary policy to enable the cache to be
located elsewhere when SELinux is in enforcing mode, please see:
/usr/share/doc/cachefilesd-*/move-cache.txt
When the cachefilesd rpm is installed; alternatively, the document can be found
in the sources.
==================
A NOTE ON SECURITY
==================
CacheFiles makes use of the split security in the task_struct. It allocates
its own task_security structure, and redirects current->act_as to point to it
when it acts on behalf of another process, in that process's context.
The reason it does this is that it calls vfs_mkdir() and suchlike rather than
bypassing security and calling inode ops directly. Therefore the VFS and LSM
may deny the CacheFiles access to the cache data because under some
circumstances the caching code is running in the security context of whatever
process issued the original syscall on the netfs.
Furthermore, should CacheFiles create a file or directory, the security
parameters with that object is created (UID, GID, security label) would be
derived from that process that issued the system call, thus potentially
preventing other processes from accessing the cache - including CacheFiles's
cache management daemon (cachefilesd).
What is required is to temporarily override the security of the process that
issued the system call. We can't, however, just do an in-place change of the
security data as that affects the process as an object, not just as a subject.
This means it may lose signals or ptrace events for example, and affects what
the process looks like in /proc.
So CacheFiles makes use of a logical split in the security between the
objective security (task->sec) and the subjective security (task->act_as). The
objective security holds the intrinsic security properties of a process and is
never overridden. This is what appears in /proc, and is what is used when a
process is the target of an operation by some other process (SIGKILL for
example).
The subjective security holds the active security properties of a process, and
may be overridden. This is not seen externally, and is used whan a process
acts upon another object, for example SIGKILLing another process or opening a
file.
LSM hooks exist that allow SELinux (or Smack or whatever) to reject a request
for CacheFiles to run in a context of a specific security label, or to create
files and directories with another security label.
This documentation is added by the patch to:
Documentation/filesystems/caching/cachefiles.txt
Signed-Off-By: David Howells <dhowells@redhat.com>
Acked-by: Steve Dickson <steved@redhat.com>
Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
David Howells