There are a few d_obtain_alias callers that are using it to get the
root of a filesystem which may already have an alias somewhere else.
This is not the same as the filehandle-lookup case, and none of them
actually need DCACHE_DISCONNECTED set.
It isn't really a serious problem, but it would really be clearer if we
reserved DCACHE_DISCONNECTED for those cases where it's actually needed.
In the btrfs case this was causing a spurious printk from
nfsd/nfsfh.c:fh_verify when it found an unexpected DCACHE_DISCONNECTED
dentry. Josef worked around this by unsetting DCACHE_DISCONNECTED
manually in 3a0dfa6a12 "Btrfs: unset DCACHE_DISCONNECTED when mounting
default subvol", and this replaces that workaround.
Cc: Josef Bacik <jbacik@fb.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
RENAME_NOREPLACE is trivial to implement for most filesystems: switch over
to ->rename2() and check for the supported flags. The rest is done by the
VFS.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Cc: Chris Mason <clm@fb.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull btrfs fixes from Chris Mason:
"We have two more fixes in my for-linus branch.
I was hoping to also include a fix for a btrfs deadlock with
compression enabled, but we're still nailing that one down"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
btrfs: test for valid bdev before kobj removal in btrfs_rm_device
Btrfs: fix abnormal long waiting in fsync
commit 99994cd btrfs: dev delete should remove sysfs entry
added a btrfs_kobj_rm_device, which dereferences device->bdev...
right after we check whether device->bdev might be NULL.
I don't honestly know if it's possible to have a NULL device->bdev
here, but assuming that it is (given the test), we need to move
the kobject removal to be under that test.
(Coverity spotted this)
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Chris Mason <clm@fb.com>
xfstests generic/127 detected this problem.
With commit 7fc34a62ca, now fsync will only flush
data within the passed range. This is the cause of the above problem,
-- btrfs's fsync has a stage called 'sync log' which will wait for all the
ordered extents it've recorded to finish.
In xfstests/generic/127, with mixed operations such as truncate, fallocate,
punch hole, and mapwrite, we get some pre-allocated extents, and mapwrite will
mmap, and then msync. And I find that msync will wait for quite a long time
(about 20s in my case), thanks to ftrace, it turns out that the previous
fallocate calls 'btrfs_wait_ordered_range()' to flush dirty pages, but as the
range of dirty pages may be larger than 'btrfs_wait_ordered_range()' wants,
there can be some ordered extents created but not getting corresponding pages
flushed, then they're left in memory until we fsync which runs into the
stage 'sync log', and fsync will just wait for the system writeback thread
to flush those pages and get ordered extents finished, so the latency is
inevitable.
This adds a flush similar to btrfs_start_ordered_extent() in
btrfs_wait_logged_extents() to fix that.
Reviewed-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
Pull btrfs fixes from Chris Mason:
"We've queued up a few fixes in my for-linus branch"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: fix crash when starting transaction
Btrfs: fix btrfs_print_leaf for skinny metadata
Btrfs: fix race of using total_bytes_pinned
btrfs: use E2BIG instead of EIO if compression does not help
btrfs: remove stale comment from btrfs_flush_all_pending_stuffs
Btrfs: fix use-after-free when cloning a trailing file hole
btrfs: fix null pointer dereference in btrfs_show_devname when name is null
btrfs: fix null pointer dereference in clone_fs_devices when name is null
btrfs: fix nossd and ssd_spread mount option regression
Btrfs: fix race between balance recovery and root deletion
Btrfs: atomically set inode->i_flags in btrfs_update_iflags
btrfs: only unlock block in verify_parent_transid if we locked it
Btrfs: assert send doesn't attempt to start transactions
btrfs compression: reuse recently used workspace
Btrfs: fix crash when mounting raid5 btrfs with missing disks
btrfs: create sprout should rename fsid on the sysfs as well
btrfs: dev replace should replace the sysfs entry
btrfs: dev add should add its sysfs entry
btrfs: dev delete should remove sysfs entry
btrfs: rename add_device_membership to btrfs_kobj_add_device
We wouldn't actuall print the extent information if we had a skinny metadata
item, this fixes that. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
This percpu counter @total_bytes_pinned is introduced to skip unnecessary
operations of 'commit transaction', it accounts for those space we may free
but are stuck in delayed refs.
And we zero out @space_info->total_bytes_pinned every transaction period so
we have a better idea of how much space we'll actually free up by committing
this transaction. However, we do the 'zero out' part a little earlier, before
we actually unpin space, so we end up returning ENOSPC when we actually have
free space that's just unpinned from committing transaction.
xfstests/generic/074 complained then.
This fixes it by actually accounting the percpu pinned number when 'unpin',
and since it's protected by space_info->lock, the race is gone now.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
Return codes got updated in 60e1975acb
(btrfs: return errno instead of -1 from compression)
lzo wrapper returns E2BIG in this case, do the same for zlib.
Signed-off-by: David Sterba <dsterba@suse.cz>
The transaction handle was being used after being freed.
Cc: Chris Mason <clm@fb.com>
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
dev->name is null but missing flag is not set.
Strictly speaking the missing flag should have been set, but there
are more places where code just checks if name is null. For now this
patch does the same.
stack:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000064
IP: [<ffffffffa0228908>] btrfs_show_devname+0x58/0xf0 [btrfs]
[<ffffffff81198879>] show_vfsmnt+0x39/0x130
[<ffffffff81178056>] m_show+0x16/0x20
[<ffffffff8117d706>] seq_read+0x296/0x390
[<ffffffff8115aa7d>] vfs_read+0x9d/0x160
[<ffffffff8115b549>] SyS_read+0x49/0x90
[<ffffffff817abe52>] system_call_fastpath+0x16/0x1b
reproducer:
mkfs.btrfs -draid1 -mraid1 /dev/sdg1 /dev/sdg2
btrfstune -S 1 /dev/sdg1
modprobe -r btrfs && modprobe btrfs
mount -o degraded /dev/sdg1 /btrfs
btrfs dev add /dev/sdg3 /btrfs
Signed-off-by: Anand Jain <Anand.Jain@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
The commit
0780253 btrfs: Cleanup the btrfs_parse_options for remount.
broke ssd options quite badly; it stopped making ssd_spread
imply ssd, and it made "nossd" unsettable.
Put things back at least as well as they were before
(though ssd mount option handling is still pretty odd:
# mount -o "nossd,ssd_spread" works?)
Reported-by: Roman Mamedov <rm@romanrm.net>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Chris Mason <clm@fb.com>
Balance recovery is called when RW mounting or remounting from
RO to RW, it is called to finish roots merging.
When doing balance recovery, relocation root's corresponding
fs root(whose root refs is 0) might be destroyed by cleaner
thread, this will make btrfs fail to mount.
Fix this problem by holding @cleaner_mutex when doing balance
recovery.
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
This change is based on the corresponding recent change for ext4:
ext4: atomically set inode->i_flags in ext4_set_inode_flags()
That has the following commit message that applies to btrfs as well:
"Use cmpxchg() to atomically set i_flags instead of clearing out the
S_IMMUTABLE, S_APPEND, etc. flags and then setting them from the
EXT4_IMMUTABLE_FL, EXT4_APPEND_FL flags, since this opens up a race
where an immutable file has the immutable flag cleared for a brief
window of time."
Replacing EXT4_IMMUTABLE_FL and EXT4_APPEND_FL with BTRFS_INODE_IMMUTABLE
and BTRFS_INODE_APPEND, respectively.
Reviewed-by: David Sterba <dsterba@suse.cz>
Reviewed-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
This is a regression from my patch a26e8c9f75, we
need to only unlock the block if we were the one who locked it. Otherwise this
will trip BUG_ON()'s in locking.c Thanks,
cc: stable@vger.kernel.org
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
When starting a transaction just assert that current->journal_info
doesn't contain a send transaction stub, since send isn't supposed
to start transactions and when it finishes (either successfully or
not) it's supposed to set current->journal_info to NULL.
This is motivated by the change titled:
Btrfs: fix crash when starting transaction
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
Add compression `workspace' in free_workspace() to
`idle_workspace' list head, instead of tail. So we have
better chances to reuse most recently used `workspace'.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Creating sprout will change the fsid of the mounted root.
do the same on the sysfs as well.
reproducer:
mount /dev/sdb /btrfs (seed disk)
btrfs dev add /dev/sdc /btrfs
mount -o rw,remount /btrfs
btrfs dev del /dev/sdb /btrfs
mount /dev/sdb /btrfs
Error:
kobject_add_internal failed for fe350492-dc28-4051-a601-e017b17e6145 with -EEXIST, don't try to register things with the same name in the same directory.
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
when we replace the device its corresponding sysfs
entry has to be replaced as well
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
we would need the device links to be created,
when device is added.
Signed-off-by: Anand Jain <Anand.Jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
when we delete the device from the mounted btrfs,
we would need its corresponding sysfs enty to
be removed as well.
Signed-off-by: Anand Jain <Anand.Jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
Pull btrfs fixes from Chris Mason:
"This fixes some lockups in btrfs reported with rc1. It probably has
some performance impact because it is backing off our spinning locks
more often and switching to a blocking lock. I'll be able to nail
that down next week, but for now I want to get the lockups taken care
of.
Otherwise some more stack reduction and assorted fixes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
Btrfs: fix wrong error handle when the device is missing or is not writeable
Btrfs: fix deadlock when mounting a degraded fs
Btrfs: use bio_endio_nodec instead of open code
Btrfs: fix NULL pointer crash when running balance and scrub concurrently
btrfs: Skip scrubbing removed chunks to avoid -ENOENT.
Btrfs: fix broken free space cache after the system crashed
Btrfs: make free space cache write out functions more readable
Btrfs: remove unused wait queue in struct extent_buffer
Btrfs: fix deadlocks with trylock on tree nodes
The original bio might be submitted, so we shoud increase bi_remaining to
account for it when we deal with the error that the device is missing or
is not writeable, or we would skip the endio handle.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
The deadlock happened when we mount degraded filesystem, the reproduced
steps are following:
# mkfs.btrfs -f -m raid1 -d raid1 <dev0> <dev1>
# echo 1 > /sys/block/`basename <dev0>`/device/delete
# mount -o degraded <dev1> <mnt>
The reason was that the counter -- bi_remaining was wrong. If the missing
or unwriteable device was the last device in the mapping array, we would
not submit the original bio, so we shouldn't increase bi_remaining of it
in btrfs_end_bio(), or we would skip the final endio handle.
Fix this problem by adding a flag into btrfs bio structure. If we submit
the original bio, we will set the flag, and we increase bi_remaining counter,
or we don't.
Though there is another way to fix it -- decrease bi_remaining counter of the
original bio when we make sure the original bio is not submitted, this method
need add more check and is easy to make mistake.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
While running balance, scrub, fsstress concurrently we hit the
following kernel crash:
[56561.448845] BTRFS info (device sde): relocating block group 11005853696 flags 132
[56561.524077] BUG: unable to handle kernel NULL pointer dereference at 0000000000000078
[56561.524237] IP: [<ffffffffa038956d>] scrub_chunk.isra.12+0xdd/0x130 [btrfs]
[56561.524297] PGD 9be28067 PUD 7f3dd067 PMD 0
[56561.524325] Oops: 0000 [#1] SMP
[....]
[56561.527237] Call Trace:
[56561.527309] [<ffffffffa038980e>] scrub_enumerate_chunks+0x24e/0x490 [btrfs]
[56561.527392] [<ffffffff810abe00>] ? abort_exclusive_wait+0x50/0xb0
[56561.527476] [<ffffffffa038add4>] btrfs_scrub_dev+0x1a4/0x530 [btrfs]
[56561.527561] [<ffffffffa0368107>] btrfs_ioctl+0x13f7/0x2a90 [btrfs]
[56561.527639] [<ffffffff811c82f0>] do_vfs_ioctl+0x2e0/0x4c0
[56561.527712] [<ffffffff8109c384>] ? vtime_account_user+0x54/0x60
[56561.527788] [<ffffffff810f768c>] ? __audit_syscall_entry+0x9c/0xf0
[56561.527870] [<ffffffff811c8551>] SyS_ioctl+0x81/0xa0
[56561.527941] [<ffffffff815707f7>] tracesys+0xdd/0xe2
[...]
[56561.528304] RIP [<ffffffffa038956d>] scrub_chunk.isra.12+0xdd/0x130 [btrfs]
[56561.528395] RSP <ffff88004c0f5be8>
[56561.528454] CR2: 0000000000000078
This is because in btrfs_relocate_chunk(), we will free @bdev directly while
scrub may still hold extent mapping, and may access freed memory.
Fix this problem by wrapping freeing @bdev work into free_extent_map() which
is based on reference count.
Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
When run scrub with balance, sometimes -ENOENT will be returned, since
in scrub_enumerate_chunks() will search dev_extent in *COMMIT_ROOT*, but
btrfs_lookup_block_group() will search block group in *MEMORY*, so if a
chunk is removed but not committed, -ENOENT will be returned.
However, there is no need to stop scrubbing since other chunks may be
scrubbed without problem.
So this patch changes the behavior to skip removed chunks and continue
to scrub the rest.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
When we mounted the filesystem after the crash, we got the following
message:
BTRFS error (device xxx): block group xxxx has wrong amount of free space
BTRFS error (device xxx): failed to load free space cache for block group xxx
It is because we didn't update the metadata of the allocated space (in extent
tree) until the file data was written into the disk. During this time, there was
no information about the allocated spaces in either the extent tree nor the
free space cache. when we wrote out the free space cache at this time (commit
transaction), those spaces were lost. In fact, only the free space that is
used to store the file data had this problem, the others didn't because
the metadata of them is updated in the same transaction context.
There are many methods which can fix the above problem
- track the allocated space, and write it out when we write out the free
space cache
- account the size of the allocated space that is used to store the file
data, if the size is not zero, don't write out the free space cache.
The first one is complex and may make the performance drop down.
This patch chose the second method, we use a per-block-group variant to
account the size of that allocated space. Besides that, we also introduce
a per-block-group read-write semaphore to avoid the race between
the allocation and the free space cache write out.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
This patch makes the free space cache write out functions more readable,
and beisdes that, it also reduces the stack space that the function --
__btrfs_write_out_cache uses from 194bytes to 144bytes.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
The lock_wq wait queue is not used anywhere, therefore just remove it.
On a x86_64 system, this reduced sizeof(struct extent_buffer) from 320
bytes down to 296 bytes, which means a 4Kb page can now be used for
13 extent buffers instead of 12.
Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
The Btrfs tree trylock function is poorly named. It always takes
the spinlock and backs off if the blocking lock is held. This
can lead to surprising lockups because people expect it to really be a
trylock.
This commit makes it a pure trylock, both for the spinlock and the
blocking lock. It also reworks the nested lock handling slightly to
avoid taking the read lock while a spinning write lock might be held.
Signed-off-by: Chris Mason <clm@fb.com>
Pull more btrfs updates from Chris Mason:
"This has a few fixes since our last pull and a new ioctl for doing
btree searches from userland. It's very similar to the existing
ioctl, but lets us return larger items back down to the app"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
btrfs: fix error handling in create_pending_snapshot
btrfs: fix use of uninit "ret" in end_extent_writepage()
btrfs: free ulist in qgroup_shared_accounting() error path
Btrfs: fix qgroups sanity test crash or hang
btrfs: prevent RCU warning when dereferencing radix tree slot
Btrfs: fix unfinished readahead thread for raid5/6 degraded mounting
btrfs: new ioctl TREE_SEARCH_V2
btrfs: tree_search, search_ioctl: direct copy to userspace
btrfs: new function read_extent_buffer_to_user
btrfs: tree_search, copy_to_sk: return needed size on EOVERFLOW
btrfs: tree_search, copy_to_sk: return EOVERFLOW for too small buffer
btrfs: tree_search, search_ioctl: accept varying buffer
btrfs: tree_search: eliminate redundant nr_items check
fcebe456 cut and pasted some code to a later point
in create_pending_snapshot(), but didn't switch
to the appropriate error handling for this stage
of the function.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Chris Mason <clm@fb.com>
If this condition in end_extent_writepage() is false:
if (tree->ops && tree->ops->writepage_end_io_hook)
we will then test an uninitialized "ret" at:
ret = ret < 0 ? ret : -EIO;
The test for ret is for the case where ->writepage_end_io_hook
failed, and we'd choose that ret as the error; but if
there is no ->writepage_end_io_hook, nothing sets ret.
Initializing ret to 0 should be sufficient; if
writepage_end_io_hook wasn't set, (!uptodate) means
non-zero err was passed in, so we choose -EIO in that case.
Signed-of-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Chris Mason <clm@fb.com>
If tmp = ulist_alloc(GFP_NOFS) fails, we return without
freeing the previously allocated qgroups = ulist_alloc(GFP_NOFS)
and cause a memory leak.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Chris Mason <clm@fb.com>
Mark the dereference as protected by lock. Not doing so triggers
an RCU warning since the radix tree assumed that RCU is in use.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
Steps to reproduce:
# mkfs.btrfs -f /dev/sd[b-f] -m raid5 -d raid5
# mkfs.ext4 /dev/sdc --->corrupt one of btrfs device
# mount /dev/sdb /mnt -o degraded
# btrfs scrub start -BRd /mnt
This is because readahead would skip missing device, this is not true
for RAID5/6, because REQ_GET_READ_MIRRORS return 1 for RAID5/6 block
mapping. If expected data locates in missing device, readahead thread
would not call __readahead_hook() which makes event @rc->elems=0
wait forever.
Fix this problem by checking return value of btrfs_map_block(),we
can only skip missing device safely if there are several mirrors.
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
This new ioctl call allows the user to supply a buffer of varying size in which
a tree search can store its results. This is much more flexible if you want to
receive items which are larger than the current fixed buffer of 3992 bytes or
if you want to fetch more items at once. Items larger than this buffer are for
example some of the type EXTENT_CSUM.
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
By copying each found item seperatly to userspace, we do not need extra
buffer in the kernel.
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
This new function reads the content of an extent directly to user memory.
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
If an item in tree_search is too large to be stored in the given buffer, return
the needed size (including the header).
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
In copy_to_sk, if an item is too large for the given buffer, it now returns
-EOVERFLOW instead of copying a search_header with len = 0. For backward
compatibility for the first item it still copies such a header to the buffer,
but not any other following items, which could have fitted.
tree_search changes -EOVERFLOW back to 0 to behave similiar to the way it
behaved before this patch.
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
rewrite search_ioctl to accept a buffer with varying size
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
If the amount of items reached the given limit of nr_items, we can leave
copy_to_sk without updating the key. Also by returning 1 we leave the loop in
search_ioctl without rechecking if we reached the given limit.
Signed-off-by: Gerhard Heift <Gerhard@Heift.Name>
Signed-off-by: Chris Mason <clm@fb.com>
Acked-by: David Sterba <dsterba@suse.cz>
J. Bruce Fields