| Age | Commit message (Collapse) | Author |
|---|
|
commit 153c35b6cccc0c72de9fae06c8e2c8b2c47d79d4 upstream.
Commit 2f0810880f082fa8ba66ab2c33b02e4ff9770a5e changed
btrfs_set_block_group_ro to avoid trying to allocate new chunks with the
new raid profile during conversion. This fixed failures when there was
no space on the drive to allocate a new chunk, but the metadata
reserves were sufficient to continue the conversion.
But this ended up causing a regression when the drive had plenty of
space to allocate new chunks, mostly because reduce_alloc_profile isn't
using the new raid profile.
Fixing btrfs_reduce_alloc_profile is a bigger patch. For now, do a
partial revert of 2f0810880, and don't error out if we hit ENOSPC.
Signed-off-by: Chris Mason <clm@fb.com>
Tested-by: Dave Sterba <dsterba@suse.cz>
Reported-by: Holger Hoffstaette <holger.hoffstaette@googlemail.com>
[adapted for stable kernel branch, v4.0.5]
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit de249e66a73d696666281cd812087979c6fae552 upstream.
Commit 0d97a64e0 creates a new variable but doesn't always set it up.
This puts it back to the original method (key.offset + 1) for the cases
not covered by Filipe's new logic.
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit df858e76723ace61342b118aa4302bd09de4e386 upstream.
While searching for extents to clone we might find one where we only use
a part of it coming from its tail. If our destination inode is the same
the source inode, we end up removing the tail part of the extent item and
insert after a new one that point to the same extent with an adjusted
key file offset and data offset. After this we search for the next extent
item in the fs/subvol tree with a key that has an offset incremented by
one. But this second search leaves us at the new extent item we inserted
previously, and since that extent item has a non-zero data offset, it
it can make us call btrfs_drop_extents with an empty range (start == end)
which causes the following warning:
[23978.537119] WARNING: CPU: 6 PID: 16251 at fs/btrfs/file.c:550 btrfs_drop_extent_cache+0x43/0x385 [btrfs]()
(...)
[23978.557266] Call Trace:
[23978.557978] [<ffffffff81425fd9>] dump_stack+0x4c/0x65
[23978.559191] [<ffffffff81045390>] warn_slowpath_common+0xa1/0xbb
[23978.560699] [<ffffffffa047f0ea>] ? btrfs_drop_extent_cache+0x43/0x385 [btrfs]
[23978.562389] [<ffffffff8104544d>] warn_slowpath_null+0x1a/0x1c
[23978.563613] [<ffffffffa047f0ea>] btrfs_drop_extent_cache+0x43/0x385 [btrfs]
[23978.565103] [<ffffffff810e3a18>] ? time_hardirqs_off+0x15/0x28
[23978.566294] [<ffffffff81079ff8>] ? trace_hardirqs_off+0xd/0xf
[23978.567438] [<ffffffffa047f73d>] __btrfs_drop_extents+0x6b/0x9e1 [btrfs]
[23978.568702] [<ffffffff8107c03f>] ? trace_hardirqs_on+0xd/0xf
[23978.569763] [<ffffffff811441c0>] ? ____cache_alloc+0x69/0x2eb
[23978.570817] [<ffffffff81142269>] ? virt_to_head_page+0x9/0x36
[23978.571872] [<ffffffff81143c15>] ? cache_alloc_debugcheck_after.isra.42+0x16c/0x1cb
[23978.573466] [<ffffffff811420d5>] ? kmemleak_alloc_recursive.constprop.52+0x16/0x18
[23978.574962] [<ffffffffa0480d07>] btrfs_drop_extents+0x66/0x7f [btrfs]
[23978.576179] [<ffffffffa049aa35>] btrfs_clone+0x516/0xaf5 [btrfs]
[23978.577311] [<ffffffffa04983dc>] ? lock_extent_range+0x7b/0xcd [btrfs]
[23978.578520] [<ffffffffa049b2a2>] btrfs_ioctl_clone+0x28e/0x39f [btrfs]
[23978.580282] [<ffffffffa049d9ae>] btrfs_ioctl+0xb51/0x219a [btrfs]
(...)
[23978.591887] ---[ end trace 988ec2a653d03ed3 ]---
Then we attempt to insert a new extent item with a key that already
exists, which makes btrfs_insert_empty_item return -EEXIST resulting in
abortion of the current transaction:
[23978.594355] WARNING: CPU: 6 PID: 16251 at fs/btrfs/super.c:260 __btrfs_abort_transaction+0x52/0x114 [btrfs]()
(...)
[23978.622589] Call Trace:
[23978.623181] [<ffffffff81425fd9>] dump_stack+0x4c/0x65
[23978.624359] [<ffffffff81045390>] warn_slowpath_common+0xa1/0xbb
[23978.625573] [<ffffffffa044ab6c>] ? __btrfs_abort_transaction+0x52/0x114 [btrfs]
[23978.626971] [<ffffffff810453f0>] warn_slowpath_fmt+0x46/0x48
[23978.628003] [<ffffffff8108a6c8>] ? vprintk_default+0x1d/0x1f
[23978.629138] [<ffffffffa044ab6c>] __btrfs_abort_transaction+0x52/0x114 [btrfs]
[23978.630528] [<ffffffffa049ad1b>] btrfs_clone+0x7fc/0xaf5 [btrfs]
[23978.631635] [<ffffffffa04983dc>] ? lock_extent_range+0x7b/0xcd [btrfs]
[23978.632886] [<ffffffffa049b2a2>] btrfs_ioctl_clone+0x28e/0x39f [btrfs]
[23978.634119] [<ffffffffa049d9ae>] btrfs_ioctl+0xb51/0x219a [btrfs]
(...)
[23978.647714] ---[ end trace 988ec2a653d03ed4 ]---
This is wrong because we should not process the extent item that we just
inserted previously, and instead process the extent item that follows it
in the tree
For example for the test case I wrote for fstests:
bs=$((64 * 1024))
mkfs.btrfs -f -l $bs -O ^no-holes /dev/sdc
mount /dev/sdc /mnt
xfs_io -f -c "pwrite -S 0xaa $(($bs * 2)) $(($bs * 2))" /mnt/foo
$CLONER_PROG -s $((3 * $bs)) -d $((267 * $bs)) -l 0 /mnt/foo /mnt/foo
$CLONER_PROG -s $((217 * $bs)) -d $((95 * $bs)) -l 0 /mnt/foo /mnt/foo
The second clone call fails with -EEXIST, because when we process the
first extent item (offset 262144), we drop part of it (counting from the
end) and then insert a new extent item with a key greater then the key we
found. The next time we search the tree we search for a key with offset
262144 + 1, which leaves us at the new extent item we have just inserted
but we think it refers to an extent that we need to clone.
Fix this by ensuring the next search key uses an offset corresponding to
the offset of the key we found previously plus the data length of the
corresponding extent item. This ensures we skip new extent items that we
inserted and works for the case of implicit holes too (NO_HOLES feature).
A test case for fstests follows soon.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 727b9784b6085c99c2f836bf4fcc2848dc9cf904 upstream.
Orphans in the fs tree are cleaned up via open_ctree and subvolume
orphans are cleaned via btrfs_lookup_dentry -- except when a default
subvolume is in use. The name for the default subvolume uses a manual
lookup that doesn't trigger orphan cleanup and needs to trigger it
manually as well. This doesn't apply to the remount case since the
subvolumes are cleaned up by walking the root radix tree.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 26e726afe01c1c82072cf23a5ed89ce25f39d9f2 upstream.
fiemap_fill_next_extent returns 0 on success, -errno on error, 1 if this was
the last extent that will fit in user array. If 1 is returned, the return
value may eventually returned to user space, which should not happen, according
to manpage of ioctl.
Signed-off-by: Chengyu Song <csong84@gatech.edu>
Reviewed-by: David Sterba <dsterba@suse.cz>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 2f1f465ae6da244099af55c066e5355abd8ff620 upstream.
If the clone root was not readonly or the dead flag was set on it, we were
leaving without decrementing the root's send_progress counter (and before
we just incremented it). If a concurrent snapshot deletion was in progress
and ended up being aborted, it would be impossible to later attempt to
delete again the snapshot, since the root's send_in_progress counter could
never go back to 0.
We were also setting clone_sources_to_rollback to i + 1 too early - if we
bailed out because the clone root we got is not readonly or flagged as dead
we ended up later derreferencing a null pointer because we didn't assign
the clone root to sctx->clone_roots[i].root:
for (i = 0; sctx && i < clone_sources_to_rollback; i++)
btrfs_root_dec_send_in_progress(
sctx->clone_roots[i].root);
So just don't increment the send_in_progress counter if the root is readonly
or flagged as dead.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 5cc2b17e80cf5770f2e585c2d90fd8af1b901258 upstream.
After we locked the root's root item, a concurrent snapshot deletion
call might have set the dead flag on it. So check if the dead flag
is set and abort if it is, just like we do for the parent root.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit dc48e56d761610da4ea1088d1bea0a030b8e3e43 upstream.
exit_aio() currently serializes killing io contexts. Each context
killing ends up having to do percpu_ref_kill(), which in turns has
to wait for an RCU grace period. This can take a long time, depending
on the number of contexts. And there's no point in doing them serially,
when we could be waiting for all of them in one fell swoop.
This patches makes my fio thread offload test case exit 0.2s instead
of almost 6s.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 2b1d3ae940acd11be44c6eced5873d47c2e00ffa upstream.
load_elf_binary() returns `retval', not `error'.
Fixes: a87938b2e246b81b4fb ("fs/binfmt_elf.c: fix bug in loading of PIE binaries")
Reported-by: James Hogan <james.hogan@imgtec.com>
Cc: Michael Davidson <md@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 161f873b89136eb1e69477c847d5a5033239d9ba upstream.
We used to read file_handle twice. Once to get the amount of extra
bytes, and once to fetch the entire structure.
This may be problematic since we do size verifications only after the
first read, so if the number of extra bytes changes in userspace between
the first and second calls, we'll have an incoherent view of
file_handle.
Instead, read the constant size once, and copy that over to the final
structure without having to re-read it again.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit ebe9cb3bb13e7b9b281969cd279ce70834f7500f upstream.
If we find a non-confirmed openowner we jump to exit the function, but do
not set an error value. Fix this by factoring out a helper to do the
check and properly set the error from nfsd4_validate_stateid.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 40cdc7a530c7a075557651a071354bb42b99df08 upstream.
Commit df52699e4fcef ("NFSv4.1: Don't cache deviceids that have no
notifications") causes the Linux NFS client to stop caching deviceid's
unless a server pretends to support deviceid notifications. While this
behavior is stupid and the language around this area in rfc5661 is a
mess carified by an errata that I submittted, Trond insists on this
behavior. Not caching deviceids degrades block layout performance
massively as a GETDEVICEINFO is fairly expensive.
So add this hack to make the Linux client happy again.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 499611ed451508a42d1d7d1faff10177827755d5 upstream.
root->ino_ida is used for kernfs inode number allocations. Since IDA has
a layered structure, different IDs can reside on the same layer, which
is currently accounted to some memory cgroup. The problem is that each
kmem cache of a memory cgroup has its own directory on sysfs (under
/sys/fs/kernel/<cache-name>/cgroup). If the inode number of such a
directory or any file in it gets allocated from a layer accounted to the
cgroup which the cache is created for, the cgroup will get pinned for
good, because one has to free all kmem allocations accounted to a cgroup
in order to release it and destroy all its kmem caches. That said we
must not account layers of ino_ida to any memory cgroup.
Since per net init operations may create new sysfs entries directly
(e.g. lo device) or indirectly (nf_conntrack creates a new kmem cache
per each namespace, which, in turn, creates new sysfs entries), an easy
way to reproduce this issue is by creating network namespace(s) from
inside a kmem-active memory cgroup.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
architectures
commit d045c77c1a69703143a36169c224429c48b9eecd upstream.
On architectures where the stack grows upwards (CONFIG_STACK_GROWSUP=y,
currently parisc and metag only) stack randomization sometimes leads to crashes
when the stack ulimit is set to lower values than STACK_RND_MASK (which is 8 MB
by default if not defined in arch-specific headers).
The problem is, that when the stack vm_area_struct is set up in fs/exec.c, the
additional space needed for the stack randomization (as defined by the value of
STACK_RND_MASK) was not taken into account yet and as such, when the stack
randomization code added a random offset to the stack start, the stack
effectively got smaller than what the user defined via rlimit_max(RLIMIT_STACK)
which then sometimes leads to out-of-stack situations and crashes.
This patch fixes it by adding the maximum possible amount of memory (based on
STACK_RND_MASK) which theoretically could be added by the stack randomization
code to the initial stack size. That way, the user-defined stack size is always
guaranteed to be at minimum what is defined via rlimit_max(RLIMIT_STACK).
This bug is currently not visible on the metag architecture, because on metag
STACK_RND_MASK is defined to 0 which effectively disables stack randomization.
The changes to fs/exec.c are inside an "#ifdef CONFIG_STACK_GROWSUP"
section, so it does not affect other platformws beside those where the
stack grows upwards (parisc and metag).
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: linux-parisc@vger.kernel.org
Cc: James Hogan <james.hogan@imgtec.com>
Cc: linux-metag@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit e531d0bceb402e643a4499de40dd3fa39d8d2e43 upstream.
The journal revoke block recovery code does not check r_count for
sanity, which means that an evil value of r_count could result in
the kernel reading off the end of the revoke table and into whatever
garbage lies beyond. This could crash the kernel, so fix that.
However, in testing this fix, I discovered that the code to write
out the revoke tables also was not correctly checking to see if the
block was full -- the current offset check is fine so long as the
revoke table space size is a multiple of the record size, but this
is not true when either journal_csum_v[23] are set.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 2f974865ffdfe7b9f46a9940836c8b167342563d upstream.
The following commit introduced a bug when checking for zero length extent
5946d08 ext4: check for overlapping extents in ext4_valid_extent_entries()
Zero length extent could pass the check if lblock is zero.
Adding the explicit check for zero length back.
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 9d506594069355d1fb2de3f9104667312ff08ed3 upstream.
Currently when journal restart fails, we'll have the h_transaction of
the handle set to NULL to indicate that the handle has been effectively
aborted. We handle this situation quietly in the jbd2_journal_stop() and just
free the handle and exit because everything else has been done before we
attempted (and failed) to restart the journal.
Unfortunately there are a number of problems with that approach
introduced with commit
41a5b913197c "jbd2: invalidate handle if jbd2_journal_restart()
fails"
First of all in ext4 jbd2_journal_stop() will be called through
__ext4_journal_stop() where we would try to get a hold of the superblock
by dereferencing h_transaction which in this case would lead to NULL
pointer dereference and crash.
In addition we're going to free the handle regardless of the refcount
which is bad as well, because others up the call chain will still
reference the handle so we might potentially reference already freed
memory.
Moreover it's expected that we'll get aborted handle as well as detached
handle in some of the journalling function as the error propagates up
the stack, so it's unnecessary to call WARN_ON every time we get
detached handle.
And finally we might leak some memory by forgetting to free reserved
handle in jbd2_journal_stop() in the case where handle was detached from
the transaction (h_transaction is NULL).
Fix the NULL pointer dereference in __ext4_journal_stop() by just
calling jbd2_journal_stop() quietly as suggested by Jan Kara. Also fix
the potential memory leak in jbd2_journal_stop() and use proper
handle refcounting before we attempt to free it to avoid use-after-free
issues.
And finally remove all WARN_ON(!transaction) from the code so that we do
not get random traces when something goes wrong because when journal
restart fails we will get to some of those functions.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 8f4d855839179f410fa910a26eb81d646d628f26 upstream.
We had a fencepost error in the lazytime optimization which means that
timestamp would get written to the wrong inode.
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 2159184ea01e4ae7d15f2017e296d4bc82d5aeb0 upstream.
when we find that a child has died while we'd been trying to ascend,
we should go into the first live sibling itself, rather than its sibling.
Off-by-one in question had been introduced in "deal with deadlock in
d_walk()" and the fix needs to be backported to all branches this one
has been backported to.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit a96295965b600f2dc6ad661c4803c86e87db3d7b upstream.
If while setting a block group read-only we end up allocating a system
chunk, through check_system_chunk(), we were not doing it while holding
the chunk mutex which is a problem if a concurrent chunk allocation is
happening, through do_chunk_alloc(), as it means both block groups can
end up using the same logical addresses and physical regions in the
device(s). So make sure we hold the chunk mutex.
Fixes: 2f0810880f08 ("btrfs: delete chunk allocation attemp when
setting block group ro")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit cc6f67bcafcb6bbbb2d1be1603dcd95125a52800 upstream.
OpenWRT folks reported that overlayfs fails to mount if upper fs is full,
because workdir can't be created. Wordir creation can fail for various
other reasons too.
There's no reason that the mount itself should fail, overlayfs can work
fine without a workdir, as long as the overlay isn't modified.
So mount it read-only and don't allow remounting read-write.
Add a couple of WARN_ON()s for the impossible case of workdir being used
despite being read-only.
Reported-by: Bastian Bittorf <bittorf@bluebottle.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit d377c5eb54dd05aeb3094b7740252d19ba7791f7 upstream.
When removing an opaque directory we can't just call rmdir() to check for
emptiness, because the directory will need to be replaced with a whiteout.
The replacement is done with RENAME_EXCHANGE, which doesn't check
emptiness.
Solution is just to check emptiness by reading the directory. In the
future we could add a new rename flag to check for emptiness even for
RENAME_EXCHANGE to optimize this case.
Reported-by: Vincent Batts <vbatts@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Tested-by: Jordi Pujol Palomer <jordipujolp@gmail.com>
Fixes: 263b4a0fee43 ("ovl: dont replace opaque dir")
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit cddc116228cb9d51d3224d23ba3e61fbbc3ec3d2 upstream.
It was missed when we converted everything in XFs to use negative error
numbers, so fix it now. Bug introduced in 3.17 by commit 2451337 ("xfs: global
error sign conversion"), and should go back to stable kernels.
Thanks to Brian Foster for noticing it.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 6dfe5a049f2d48582050339d2a6b6fda36dfd14c upstream.
xfs_attr_inactive() is supposed to clean up the attribute fork when
the inode is being freed. While it removes attribute fork extents,
it completely ignores attributes in local format, which means that
there can still be active attributes on the inode after
xfs_attr_inactive() has run.
This leads to problems with concurrent inode writeback - the in-core
inode attribute fork is removed without locking on the assumption
that nothing will be attempting to access the attribute fork after a
call to xfs_attr_inactive() because it isn't supposed to exist on
disk any more.
To fix this, make xfs_attr_inactive() completely remove all traces
of the attribute fork from the inode, regardless of it's state.
Further, also remove the in-core attribute fork structure safely so
that there is nothing further that needs to be done by callers to
clean up the attribute fork. This means we can remove the in-core
and on-disk attribute forks atomically.
Also, on error simply remove the in-memory attribute fork. There's
nothing that can be done with it once we have failed to remove the
on-disk attribute fork, so we may as well just blow it away here
anyway.
Reported-by: Waiman Long <waiman.long@hp.com>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit c0345ee57d461343586b5e1e2f9c3c3766d07fe6 upstream.
The count variable is used to iterate down to (below) zero from the size
of the bitmap and handle the one-filling the remainder of the last
partial bitmap block. The loop conditional expects count to be signed
in order to detect when the final block is processed, after which count
goes negative.
Unfortunately, a recent change made this unsigned along with some other
related fields. The result of is this is that during mount,
omfs_get_imap will overrun the bitmap array and corrupt memory unless
number of blocks happens to be a multiple of 8 * blocksize.
Fix by changing count back to signed: it is guaranteed to fit in an s32
without overflow due to an enforced limit on the number of blocks in the
filesystem.
Signed-off-by: Bob Copeland <me@bobcopeland.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit dcbff39da3d815f08750552fdd04f96b51751129 upstream.
match_token() expects a NULL terminator at the end of the token list so
that it would know where to stop. Not having one causes it to overrun
to invalid memory.
In practice, passing a mount option that omfs didn't recognize would
sometimes panic the system.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Bob Copeland <me@bobcopeland.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 820f9f147dcce2602eefd9b575bbbd9ea14f0953 upstream.
This is needed to support lazily umounting locked mounts. Because the
entire unmounted subtree needs to stay together until there are no
users with references to any part of the subtree.
To support this guarantee that the fs_pin m_list and s_list nodes
are initialized by initializing them in init_fs_pin allowing
for the possibility that pin_insert_group does not touch them.
Further use hlist_del_init in pin_remove so that there is
a hlist_unhashed test before the list we attempt to update
the previous list item.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit cd4a40174b71acd021877341684d8bb1dc8ea4ae upstream.
The only users of collect_mounts are in audit_tree.c
In audit_trim_trees and audit_add_tree_rule the path passed into
collect_mounts is generated from kern_path passed an audit_tree
pathname which is guaranteed to be an absolute path. In those cases
collect_mounts is obviously intended to work on mounted paths and
if a race results in paths that are unmounted when collect_mounts
it is reasonable to fail early.
The paths passed into audit_tag_tree don't have the absolute path
check. But are used to play with fsnotify and otherwise interact with
the audit_trees, so again operating only on mounted paths appears
reasonable.
Avoid having to worry about what happens when we try and audit
unmounted filesystems by restricting collect_mounts to mounts
that appear in the mount tree.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 86cc05840a0da1afcb6b8151b53f3b606457c91b upstream.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit f15133df088ecadd141ea1907f2c96df67c729f0 upstream.
path_openat() jumps to the wrong place after do_tmpfile() - it has
already done path_cleanup() (as part of path_lookupat() called by
do_tmpfile()), so doing that again can lead to double fput().
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 7e96c1b0e0f495c5a7450dc4aa7c9a24ba4305bd upstream.
This fixes a dumb bug in fs_fully_visible that allows proc or sys to
be mounted if there is a bind mount of part of /proc/ or /sys/ visible.
Reported-by: Eric Windisch <ewindisch@docker.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit d8fd150fe3935e1692bf57c66691e17409ebb9c1 upstream.
The range check for b-tree level parameter in nilfs_btree_root_broken()
is wrong; it accepts the case of "level == NILFS_BTREE_LEVEL_MAX" even
though the level is limited to values in the range of 0 to
(NILFS_BTREE_LEVEL_MAX - 1).
Since the level parameter is read from storage device and used to index
nilfs_btree_path array whose element count is NILFS_BTREE_LEVEL_MAX, it
can cause memory overrun during btree operations if the boundary value
is set to the level parameter on device.
This fixes the broken sanity check and adds a comment to clarify that
the upper bound NILFS_BTREE_LEVEL_MAX is exclusive.
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit b1432a2a35565f538586774a03bf277c27fc267d upstream.
There is a race window in dlm_get_lock_resource(), which may return a
lock resource which has been purged. This will cause the process to
hang forever in dlmlock() as the ast msg can't be handled due to its
lock resource not existing.
dlm_get_lock_resource {
...
spin_lock(&dlm->spinlock);
tmpres = __dlm_lookup_lockres_full(dlm, lockid, namelen, hash);
if (tmpres) {
spin_unlock(&dlm->spinlock);
>>>>>>>> race window, dlm_run_purge_list() may run and purge
the lock resource
spin_lock(&tmpres->spinlock);
...
spin_unlock(&tmpres->spinlock);
}
}
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit db579e76f06e78de011b2cb7e028740a82f5558c upstream.
On Mac OS X, HFS+ extended attributes are not namespaced. Since we want
to be compatible with OS X filesystems and yet still support the Linux
namespacing system, the hfsplus driver implements a special "osx"
namespace that is reported for any attribute that is not namespaced
on-disk. However, the current code for getting and setting these
unprefixed attributes is broken.
hfsplus_osx_setattr() and hfsplus_osx_getattr() are passed names that have
already had their "osx." prefixes stripped by the generic functions. The
functions first, quite correctly, check those names to make sure that they
aren't prefixed with a known namespace, which would allow namespace access
restrictions to be bypassed. However, the functions then prepend "osx."
to the name they're given before passing it on to hfsplus_getattr() and
hfsplus_setattr(). Not only does this cause the "osx." prefix to be
stored on-disk, defeating its purpose, it also breaks the check for the
special "com.apple.FinderInfo" attribute, which is reported for all files,
and as a consequence makes some userspace applications (e.g. GNU patch)
fail even when extended attributes are not otherwise in use.
There are five commits which have touched this particular code:
127e5f5ae51e ("hfsplus: rework functionality of getting, setting and deleting of extended attributes")
b168fff72109 ("hfsplus: use xattr handlers for removexattr")
bf29e886b242 ("hfsplus: correct usage of HFSPLUS_ATTR_MAX_STRLEN for non-English attributes")
fcacbd95e121 ("fs/hfsplus: move xattr_name allocation in hfsplus_getxattr()")
ec1bbd346f18 ("fs/hfsplus: move xattr_name allocation in hfsplus_setxattr()")
The first commit creates the functions to begin with. The namespace is
prepended by the original code, which I believe was correct at the time,
since hfsplus_?etattr() stripped the prefix if found. The second commit
removes this behavior from hfsplus_?etattr() and appears to have been
intended to also remove the prefixing from hfsplus_osx_?etattr().
However, what it actually does is remove a necessary strncpy() call
completely, breaking the osx namespace entirely. The third commit re-adds
the strncpy() call as it was originally, but doesn't mention it in its
commit message. The final two commits refactor the code and don't affect
its functionality.
This commit does what b168fff attempted to do (prevent the prefix from
being added), but does it properly, instead of passing in an empty buffer
(which is what b168fff actually did).
Fixes: b168fff72109 ("hfsplus: use xattr handlers for removexattr")
Signed-off-by: Thomas Hebb <tommyhebb@gmail.com>
Cc: Hin-Tak Leung <htl10@users.sourceforge.net>
Cc: Sergei Antonov <saproj@gmail.com>
Cc: Anton Altaparmakov <anton@tuxera.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Christian Kujau <lists@nerdbynature.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Viacheslav Dubeyko <slava@dubeyko.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Hebb <tommyhebb@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 280227a75b56ab5d35854f3a77ef74a7ad56a203 upstream.
fallocate() checks that the file is extent-based and returns
EOPNOTSUPP in case is not. Other tasks can convert from and to
indirect and extent so it's safe to check only after grabbing
the inode mutex.
Signed-off-by: Davide Italiano <dccitaliano@gmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit d2dc317d564a46dfc683978a2e5a4f91434e9711 upstream.
Currently it is possible to lose whole file system block worth of data
when we hit the specific interaction with unwritten and delayed extents
in status extent tree.
The problem is that when we insert delayed extent into extent status
tree the only way to get rid of it is when we write out delayed buffer.
However there is a limitation in the extent status tree implementation
so that when inserting unwritten extent should there be even a single
delayed block the whole unwritten extent would be marked as delayed.
At this point, there is no way to get rid of the delayed extents,
because there are no delayed buffers to write out. So when a we write
into said unwritten extent we will convert it to written, but it still
remains delayed.
When we try to write into that block later ext4_da_map_blocks() will set
the buffer new and delayed and map it to invalid block which causes
the rest of the block to be zeroed loosing already written data.
For now we can fix this by simply not allowing to set delayed status on
written extent in the extent status tree. Also add WARN_ON() to make
sure that we notice if this happens in the future.
This problem can be easily reproduced by running the following xfs_io.
xfs_io -f -c "pwrite -S 0xaa 4096 2048" \
-c "falloc 0 131072" \
-c "pwrite -S 0xbb 65536 2048" \
-c "fsync" /mnt/test/fff
echo 3 > /proc/sys/vm/drop_caches
xfs_io -c "pwrite -S 0xdd 67584 2048" /mnt/test/fff
This can be theoretically also reproduced by at random by running fsx,
but it's not very reliable, though on machines with bigger page size
(like ppc) this can be seen more often (especially xfstest generic/127)
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 909e26dce3f7600f5e293ac0522c28790a0c8c9c upstream.
Whenever the check for a send in progress introduced in commit
521e0546c970 (btrfs: protect snapshots from deleting during send) is
hit, we return without unlocking inode->i_mutex. This is easy to see
with lockdep enabled:
[ +0.000059] ================================================
[ +0.000028] [ BUG: lock held when returning to user space! ]
[ +0.000029] 4.0.0-rc5-00096-g3c435c1 #93 Not tainted
[ +0.000026] ------------------------------------------------
[ +0.000029] btrfs/211 is leaving the kernel with locks still held!
[ +0.000029] 1 lock held by btrfs/211:
[ +0.000023] #0: (&type->i_mutex_dir_key){+.+.+.}, at: [<ffffffff8135b8df>] btrfs_ioctl_snap_destroy+0x2df/0x7a0
Make sure we unlock it in the error path.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 7c61f0d3897eeeff6f3294adb9f910ddefa8035a upstream.
d4b18c3e (pnfs: remove GETDEVICELIST implementation) removed the
GETDEVICELIST operation from the NFS client, but left a "hole" in the
nfs4_procedures array. This caused /proc/self/mountstats to report an
operation named "51" where GETDEVICELIST used to be. This patch adds a
stub to fix mountstats.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Fixes: d4b18c3e (pnfs: remove GETDEVICELIST implementation)
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 05f54903d9d370a4cd302a85681304d3ec59e5c1 upstream.
For flexfiles driver, we might choose to read from mirror index other
than 0 while mirror_count is always 1 for read.
Reported-by: Jean Spector <jean@primarydata.com>
Cc: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 1ccbad9f9f9bd36db26a10f0b17fbaf12b3ae93a upstream.
For direct read that has IO size larger than rsize, we'll split
it into several READ requests and nfs_direct_good_bytes() would
count completed bytes incorrectly by eating last zero count reply.
Fix it by handling mirror and non-mirror cases differently such that
we only count mirrored writes differently.
This fixes 5fadeb47("nfs: count DIO good bytes correctly with mirroring").
Reported-by: Jean Spector <jean@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 5d05e54af3cdbb13cf19c557ff2184781b91a22c upstream.
Chuck pointed out a problem that crept in with commit 6ffa30d3f734 (nfs:
don't call blocking operations while !TASK_RUNNING). Linux counts tasks
in uninterruptible sleep against the load average, so this caused the
system's load average to be pinned at at least 1 when there was a
NFSv4.1+ mount active.
Not a huge problem, but it's probably worth fixing before we get too
many complaints about it. This patch converts the code back to use
TASK_INTERRUPTIBLE sleep, simply has it flush any signals on each loop
iteration. In practice no one should really be signalling this thread at
all, so I think this is reasonably safe.
With this change, there's also no need to game the hung task watchdog so
we can also convert the schedule_timeout call back to a normal schedule.
Reported-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Tested-by: Chuck Lever <chuck.lever@oracle.com>
Fixes: commit 6ffa30d3f734 (“nfs: don't call blocking . . .”)
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit bb7ffbf29e76b89a86ca4c3ee0d4690641f2f772 upstream.
nfsd triggered a BUG_ON in net_generic(...) when rpc_pipefs_event(...)
in fs/nfsd/nfs4recover.c was called before assigning ntfsd_net_id.
The following was observed on a MIPS 32-core processor:
kernel: Call Trace:
kernel: [<ffffffffc00bc5e4>] rpc_pipefs_event+0x7c/0x158 [nfsd]
kernel: [<ffffffff8017a2a0>] notifier_call_chain+0x70/0xb8
kernel: [<ffffffff8017a4e4>] __blocking_notifier_call_chain+0x4c/0x70
kernel: [<ffffffff8053aff8>] rpc_fill_super+0xf8/0x1a0
kernel: [<ffffffff8022204c>] mount_ns+0xb4/0xf0
kernel: [<ffffffff80222b48>] mount_fs+0x50/0x1f8
kernel: [<ffffffff8023dc00>] vfs_kern_mount+0x58/0xf0
kernel: [<ffffffff802404ac>] do_mount+0x27c/0xa28
kernel: [<ffffffff80240cf0>] SyS_mount+0x98/0xe8
kernel: [<ffffffff80135d24>] handle_sys64+0x44/0x68
kernel:
kernel:
Code: 0040f809 00000000 2e020001 <00020336> 3c12c00d
3c02801a de100000 6442eb98 0040f809
kernel: ---[ end trace 7471374335809536 ]---
Fixed this behaviour by calling register_pernet_subsys(&nfsd_net_ops) before
registering rpc_pipefs_event(...) with the notifier chain.
Signed-off-by: Giuseppe Cantavenera <giuseppe.cantavenera.ext@nokia.com>
Signed-off-by: Lorenzo Restelli <lorenzo.restelli.ext@nokia.com>
Reviewed-by: Kinlong Mee <kinglongmee@gmail.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 135dd002c23054aaa056ea3162c1e0356905c195 upstream.
Commit f895b252d4edf ("sunrpc: eliminate RPC_DEBUG") introduced
use of IS_ENABLED() in a uapi header which leads to a build
failure for userspace apps trying to use <linux/nfsd/debug.h>:
linux/nfsd/debug.h:18:15: error: missing binary operator before token "("
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
^
Since this was only used to define NFSD_DEBUG if CONFIG_SUNRPC_DEBUG
is enabled, replace instances of NFSD_DEBUG with CONFIG_SUNRPC_DEBUG.
Fixes: f895b252d4edf "sunrpc: eliminate RPC_DEBUG"
Signed-off-by: Mark Salter <msalter@redhat.com>
Reviewed-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 980608fb50aea34993ba956b71cd4602aa42b14b upstream.
If the client uses a special stateid then we'll pass a NULL file to
vfs_llseek.
Fixes: 24bab491220f " NFSD: Implement SEEK"
Cc: Anna Schumaker <Anna.Schumaker@Netapp.com>
Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 6e4891dc289cd191d46ab7ba1dcb29646644f9ca upstream.
In the case we already have a struct file (derived from a stateid), we
still need to do permission-checking; otherwise an unauthorized user
could gain access to a file by sniffing or guessing somebody else's
stateid.
Fixes: dc97618ddda9 "nfsd4: separate splice and readv cases"
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 5ba4a25ab7b13be528b23f85182f4d09cf7f71ad upstream.
vfs_fallocate will hit a NULL dereference if the client tries an
ALLOCATE or DEALLOCATE with a special stateid. Fix that. (We also
depend on the open to have broken any conflicting leases or delegations
for us.)
(If it turns out we need to allow special stateid's then we could do a
temporary open here in the special-stateid case, as we do for read and
write. For now I'm assuming it's not necessary.)
Fixes: 95d871f03cae "nfsd: Add ALLOCATE support"
Cc: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 3708f842e107b9b79d54a75d152e666b693649e8 upstream.
This reverts commit 5a254d08b086d80cbead2ebcee6d2a4b3a15587a.
Since commit 5a254d08b086 ("nfs: replace nfs_add_stats with
nfs_inc_stats when add one"), nfs_readpage and nfs_do_writepage use
nfs_inc_stats to increment NFSIOS_READPAGES and NFSIOS_WRITEPAGES
instead of nfs_add_stats.
However nfs_inc_stats does not do the same thing as nfs_add_stats with
value 1 because these functions work on distinct stats:
nfs_inc_stats increments stats from "enum nfs_stat_eventcounters" (in
server->io_stats->events) and nfs_add_stats those from "enum
nfs_stat_bytecounters" (in server->io_stats->bytes).
Signed-off-by: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Fixes: 5a254d08b086 ("nfs: replace nfs_add_stats with nfs_inc_stats...")
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 3cab989afd8d8d1bc3d99fef0e7ed87c31e7b647 upstream.
Calling unlazy_walk() in walk_component() and do_last() when we find
a symlink that needs to be followed doesn't acquire a reference to vfsmount.
That's fine when the symlink is on the same vfsmount as the parent directory
(which is almost always the case), but it's not always true - one _can_
manage to bind a symlink on top of something. And in such cases we end up
with excessive mntput().
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit e0c9c0afd2fc958ffa34b697972721d81df8a56f upstream.
Now that it is possible to lazily unmount an entire mount tree and
leave the individual mounts connected to each other add a new flag
UMOUNT_CONNECTED to umount_tree to force this behavior and use
this flag in detach_mounts.
This closes a bug where the deletion of a file or directory could
trigger an unmount and reveal data under a mount point.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit f53e57975151f54ad8caa1b0ac8a78091cd5700a upstream.
lookup_mountpoint can return either NULL or an error value.
Update the test in __detach_mounts to test for an error value
to avoid pathological cases causing a NULL pointer dereferences.
The callers of __detach_mounts should prevent it from ever being
called on an unlinked dentry but don't take any chances.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
