Btrfs: fix wrong device bytes_used in the super block
device->bytes_used will be changed when allocating a new chunk, and
disk_total_size will be changed if resizing is successful.
Meanwhile, the on-disk super blocks of the previous transaction
might not be updated. Considering the consistency of the metadata
in the previous transaction, We should use the size in the previous
transaction to check if the super block is beyond the boundary
of the device.
Though it is not big problem because we don't use it now, but anyway
it is better that we make it be consistent with the common metadata,
maybe we will use it in the future.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Btrfs: fix wrong disk size when writing super blocks
total_size will be changed when resizing a device, and disk_total_size
will be changed if resizing is successful. Meanwhile, the on-disk super
blocks of the previous transaction might not be updated. Considering
the consistency of the metadata in the previous transaction, We should
use the size in the previous transaction to check if the super block is
beyond the boundary of the device. Fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Btrfs: fix unprotected assignment of the target device
We didn't protect the assignment of the target device, it might cause the
problem that the super block update was skipped because we might find wrong
size of the target device during the assignment. Fix it by moving the
assignment sentences into the initialization function of the target device.
And there is another merit that we can check if the target device is suitable
more early.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Mon, 8 Sep 2014 21:53:18 +0000 (22:53 +0100)]
Btrfs: fix directory recovery from fsync log
When replaying a directory from the fsync log, if a directory entry
exists both in the fs/subvol tree and in the log, the directory's inode
got its i_size updated incorrectly, accounting for the dentry's name
twice.
Liu Bo [Wed, 10 Sep 2014 04:58:50 +0000 (12:58 +0800)]
Btrfs: fix loop writing of async reclaim
One of my tests shows that when we really don't have space to reclaim via
flush_space and also run out of space, this async reclaim work loops on adding
itself into the workqueue and keeps writing something to disk according to
iostat's results, and these writes mainly comes from commit_transaction which
writes super_block. This's unacceptable as it can be bad to disks, especially
memeory storages.
This adds a check to avoid the above situation.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com> Signed-off-by: Chris Mason <clm@fb.com>
Josef Bacik [Wed, 10 Sep 2014 20:20:45 +0000 (16:20 -0400)]
Btrfs: make fiemap not blow when you have lots of snapshots
We have been iterating all references for each extent we have in a file when we
do fiemap to see if it is shared. This is fine when you have a few clones or a
few snapshots, but when you have 5k snapshots suddenly fiemap just sits there
and stares at you. So add btrfs_check_shared which will use the backref walking
code but will short circuit as soon as it finds a root or inode that doesn't
match the one we currently have. This makes fiemap on my testbox go from
looking at me blankly for a day to spitting out actual output in a reasonable
amount of time. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Thu, 11 Sep 2014 10:44:49 +0000 (11:44 +0100)]
Btrfs: add missing compression property remove in btrfs_ioctl_setflags
The behaviour of a 'chattr -c' consists of getting the current flags,
clearing the FS_COMPR_FL bit and then sending the result to the set
flags ioctl - this means the bit FS_NOCOMP_FL isn't set in the flags
passed to the ioctl. This results in the compression property not being
cleared from the inode - it was cleared only if the bit FS_NOCOMP_FL
was set in the received flags.
Reproducer:
$ mkfs.btrfs -f /dev/sdd
$ mount /dev/sdd /mnt && cd /mnt
$ mkdir a
$ chattr +c a
$ touch a/file
$ lsattr a/file
--------c------- a/file
$ chattr -c a
$ touch a/file2
$ lsattr a/file2
--------c------- a/file2
$ lsattr -d a
---------------- a
Reported-by: Andreas Schneider <asn@cryptomilk.org> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
btrfs:32612
[stack snip]
btrfs_dev_replace_start()
btrfs_dev_replace_lock()
mutex_lock(dev_replace->lock) ###hold mutex(B)
btrfs_dev_replace_finishing()
btrfs_rm_dev_replace_blocked()
wait until percpu_counter_sum == 0 ###wait on bio_counter(A)
This bug can be triggered quite easily by the following test script:
http://pastebin.com/MQmb37Cy
This patch will fix the ABBA problem by calling
btrfs_dev_replace_unlock() before btrfs_rm_dev_replace_blocked().
The consistency of btrfs devices list and their superblocks is protected
by device_list_mutex, not btrfs_dev_replace_lock/unlock().
So it is safe the move btrfs_dev_replace_unlock() before
btrfs_rm_dev_replace_blocked().
Reported-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com> Cc: Stefan Behrens <sbehrens@giantdisaster.de> Signed-off-by: Chris Mason <clm@fb.com>
Mark Fasheh [Mon, 18 Aug 2014 21:01:17 +0000 (14:01 -0700)]
btrfs: don't go readonly on existing qgroup items
btrfs_drop_snapshot() leaves subvolume qgroup items on disk after
completion. This can cause problems with snapshot creation. If a new
snapshot tries to claim the deleted subvolumes id, btrfs will get -EEXIST
from add_qgroup_item() and go read-only. The following commands will
reproduce this problem (assume btrfs is on /dev/sda and is mounted at
/btrfs)
mkfs.btrfs -f /dev/sda
mount -t btrfs /dev/sda /btrfs/
btrfs quota enable /btrfs/
btrfs su sna /btrfs/ /btrfs/snap
btrfs su de /btrfs/snap
sleep 45
umount /btrfs/
mount -t btrfs /dev/sda /btrfs/
We can fix this by catching -EEXIST in add_qgroup_item() and
initializing the existing items. We have the problem of orphaned
relation items being on disk from an old snapshot but that is outside
the scope of this patch.
Signed-off-by: Mark Fasheh <mfasheh@suse.de> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Thu, 14 Aug 2014 11:25:14 +0000 (12:25 +0100)]
Btrfs: shrink further sizeof(struct extent_buffer)
The map_start and map_len fields aren't used anywhere, so just remove
them. On a x86_64 system, this reduced sizeof(struct extent_buffer)
from 296 bytes to 280 bytes, and therefore 14 extent_buffer structs can
now fit into a page instead of 13.
Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Wed, 20 Aug 2014 09:45:45 +0000 (10:45 +0100)]
Btrfs: send, lower mem requirements for processing xattrs
Maximum xattr size can be up to nearly the leaf size. For an fs with a
leaf size larger than the page size, using kmalloc requires allocating
multiple pages that are contiguous, which might not be possible if
there's heavy memory fragmentation. Therefore fallback to vmalloc if
we fail to allocate with kmalloc. Also start with a smaller buffer size,
since xattr values typically are smaller than a page.
Reported-by: Chris Murphy <lists@colorremedies.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Fri, 29 Aug 2014 12:35:13 +0000 (13:35 +0100)]
Btrfs: improve free space cache management and space allocation
While under random IO, a block group's free space cache eventually reaches
a state where it has a mix of extent entries and bitmap entries representing
free space regions.
As later free space regions are returned to the cache, some of them are merged
with existing extent entries if they are contiguous with them. But others are
not merged, because despite the existence of adjacent free space regions in
the cache, the merging doesn't happen because the existing free space regions
are represented in bitmap extents. Even when new free space regions are merged
with existing extent entries (enlarging the free space range they represent),
we create chances of having after an enlarged region that is contiguous with
some other region represented in a bitmap entry.
Both clustered and non-clustered space allocation work by iterating over our
extent and bitmap entries and skipping any that represents a region smaller
then the allocation request (and giving preference to extent entries before
bitmap entries). By having a contiguous free space region that is represented
by 2 (or more) entries (mix of extent and bitmap entries), we end up not
satisfying an allocation request with a size larger than the size of any of
the entries but no larger than the sum of their sizes. Making the caller assume
we're under a ENOSPC condition or force it to allocate multiple smaller space
regions (as we do for file data writes), which adds extra overhead and more
chances of causing fragmentation due to the smaller regions being all spread
apart from each other (more likely when under concurrency).
For example, if we have the following in the cache:
* bitmap entry covering the range [128Mb, 256Mb[, but only with the bits
representing the range [128Mb, 128Mb + 768Kb[ set - that is, only that
space in this 128Mb area is marked as free
An allocation request for 1Mb, starting at offset not greater than 128Mb - 256Kb,
would fail before, despite the existence of such contiguous free space area in the
cache. The caller could only allocate up to 768Kb of space at once and later another
256Kb (or vice-versa). In between each smaller allocation request, another task
working on a different file/inode might come in and take that space, preventing the
former task of getting a contiguous 1Mb region of free space.
Therefore this change implements the ability to move free space from bitmap
entries into existing and new free space regions represented with extent
entries. This is done when a space region is added to the cache.
A test was added to the sanity tests that explains in detail the issue too.
Some performance test results with compilebench on a 4 cores machine, with
32Gb of ram and using an HDD follow.
Test: compilebench -D /mnt -i 30 -r 1000 --makej
Before this change:
intial create total runs 30 avg 69.02 MB/s (user 0.28s sys 0.57s)
compile total runs 30 avg 314.96 MB/s (user 0.12s sys 0.25s)
read compiled tree total runs 3 avg 27.14 MB/s (user 1.52s sys 0.90s)
delete compiled tree total runs 30 avg 3.14 seconds (user 0.15s sys 0.66s)
After this change:
intial create total runs 30 avg 68.37 MB/s (user 0.29s sys 0.55s)
compile total runs 30 avg 382.83 MB/s (user 0.12s sys 0.24s)
read compiled tree total runs 3 avg 27.82 MB/s (user 1.45s sys 0.97s)
delete compiled tree total runs 30 avg 3.18 seconds (user 0.17s sys 0.65s)
Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Anand Jain [Wed, 13 Aug 2014 06:24:22 +0000 (14:24 +0800)]
btrfs: update sprout seed pointer when seed fs is relinquished
We are not updating sprout fs seed pointer when all seed device
is replaced. This patch will check if all seed device has been
replaced and then update the sprout pointer accordingly.
Same reproducer as in the previous patch would apply here.
And notice that btrfs_close_device will check if seed fs is
present and spits out the error with out this patch.
After the seed device has been replaced the new target device
is no more a seed device. So we need to update the device
numbers in the fs_devices as pointed by the fs_info.
Andrey Utkin [Sat, 9 Aug 2014 11:51:15 +0000 (14:51 +0300)]
btrfs: Drop stray check of fixup_workers creation
The issue was introduced in a79b7d4b3e8118f265dcb4bdf9a572c392f02708,
adding allocation of extent_workers, so this stray check is surely not
meant to be a check of something else.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=82021 Reported-by: Maks Naumov <maksqwe1@ukr.net> Signed-off-by: Andrey Utkin <andrey.krieger.utkin@gmail.com> Reviewed-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Mon, 4 Aug 2014 18:37:21 +0000 (19:37 +0100)]
Btrfs: make btrfs_search_forward return with nodes unlocked
None of the uses of btrfs_search_forward() need to have the path
nodes (level >= 1) read locked, only the leaf needs to be locked
while the caller processes it. Therefore make it return a path
with all nodes unlocked, except for the leaf.
This change is motivated by the observation that during a file
fsync we repeatdly call btrfs_search_forward() and process the
returned leaf while upper nodes of the returned path (level >= 1)
are read locked, which unnecessarily blocks other tasks that want
to write to the same fs/subvol btree.
Therefore instead of modifying the fsync code to unlock all nodes
with level >= 1 immediately after calling btrfs_search_forward(),
change btrfs_search_forward() to do it, so that it benefits all
callers.
Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Mon, 28 Jul 2014 18:37:17 +0000 (19:37 +0100)]
Btrfs: avoid unnecessary switch of path locks to blocking mode
If we need to cow a node, increase the write lock level and retry the
tree search, there's no point of changing the node locks in our path
to blocking mode, as we only waste time and unnecessarily wake up other
tasks waiting on the spinning locks (just to block them again shortly
after) because we release our path before repeating the tree search.
Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Mon, 28 Jul 2014 18:34:35 +0000 (19:34 +0100)]
Btrfs: unlock nodes earlier when inserting items in a btree
In ctree.c:setup_items_for_insert(), we can unlock all nodes in our
path before we process the leaf (shift items and data, adjust data
offsets, etc). This allows for better btree concurrency, as we're
often holding a write lock on at least the node at level 1.
Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
btrfs: use IS_ALIGNED() for assertion in btrfs_lookup_csums_range() for simplicity
btrfs_lookup_csums_range() uses ALIGN() to check if "start"
and "end + 1" are aligned to "root->sectorsize". It's better to
replace these with IS_ALIGNED() for simplicity.
Signed-off-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Liu Bo [Tue, 12 Aug 2014 08:33:17 +0000 (16:33 +0800)]
Btrfs: add work_struct information for workqueue tracepoint
Kernel workqueue's tracepoints print the address of work_struct, while btrfs
workqueue's tracepoints print the address of btrfs_work.
We need a connection between this two, for example when debuging, we usually
grep an address in the trace output. So it'd be better to also print
work_struct in btrfs workqueue's tracepoint.
Please note that we can only add this into those tracepoints whose work is still
available in memory because we need to reference the work.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com> Signed-off-by: Chris Mason <clm@fb.com>
Btrfs: Fix the problem that the dirty flag of dev stats is cleared
The io error might happen during writing out the device stats, and the
device stats information and dirty flag would be update at that time,
but the current code didn't consider this case, just clear the dirty
flag, it would cause that we forgot to write out the new device stats
information. Fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Btrfs: make the device lock and its protected data in the same cacheline
The lock in btrfs_device structure was far away from its protected data, it would
make CPU load the cache line twice when we accessed them, move them together.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
Btrfs: fix wrong generation check of super block on a seed device
The super block generation of the seed devices is not the same as the
filesystem which sprouted from them because we don't update the super
block on the seed devices when we change that new filesystem. So we
should not use the generation of that new filesystem to check the super
block generation on the seed devices, Fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
All the metadata in the seed devices has the same fsid as the fsid
of the seed filesystem which is on the seed device, so we should check
them by the current filesystem. Fix it.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
David Sterba [Wed, 23 Jul 2014 12:39:35 +0000 (14:39 +0200)]
btrfs: wake up transaction thread from SYNC_FS ioctl
The transaction thread may want to do more work, namely it pokes the
cleaner ktread that will start processing uncleaned subvols.
This can be triggered by user via the 'btrfs fi sync' command, otherwise
there was a delay up to 30 seconds before the cleaner started to clean
old snapshots.
Signed-off-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
Wang Shilong [Thu, 17 Jul 2014 03:44:12 +0000 (11:44 +0800)]
Btrfs: fix wrong max inline data size limit
inline data is stored from offset of @disk_bytenr in
struct btrfs_file_extent_item. So substracting total
size of struct btrfs_file_extent_item is wrong, fix it.
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
Wang Shilong [Thu, 17 Jul 2014 03:44:09 +0000 (11:44 +0800)]
Btrfs: fix wrong skipping compression for an inode
If a file's compression ratios is bad, we will set NOCOMPRESS
flag for it, and it will skip compression for that inode next time.
However, if we remount fs to COMPRESS_FORCE, it still should try
if we could compress pages for that inode, this patch fix wrong
check for this problem.
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
btrfs compression: merge inflate and deflate z_streams
`struct workspace' used for zlib compression contains two zlib
z_stream-s: `def_strm' used in zlib_compress_pages(), and `inf_strm'
used in zlib_decompress/zlib_decompress_biovec(). None of these
functions use `inf_strm' and `def_strm' simultaniously, meaning that
for every compress/decompress operation we need only one z_stream
(out of two available).
`inf_strm' and `def_strm' are different in size of ->workspace. For
inflate stream we vmalloc() zlib_inflate_workspacesize() bytes, for
deflate stream - zlib_deflate_workspacesize() bytes. On my system zlib
returns the following workspace sizes, correspondingly: 42312 and 268104
(+ guard pages).
Keep only one `z_stream' in `struct workspace' and use it for both
compression and decompression. Hence, instead of vmalloc() of two
z_stream->worskpace-s, allocate only one of size:
max(zlib_deflate_workspacesize(), zlib_inflate_workspacesize())
Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Chris Mason <clm@fb.com>
Filipe Manana [Sun, 6 Jul 2014 19:09:59 +0000 (20:09 +0100)]
Btrfs: reduce size of struct extent_state
The tree field of struct extent_state was only used to figure out if
an extent state was connected to an inode's io tree or not. For this
we can just use the rb_node field itself.
On a x86_64 system with this change the sizeof(struct extent_state) is
reduced from 96 bytes down to 88 bytes, meaning that with a page size
of 4096 bytes we can now store 46 extent states per page instead of 42.
Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: linux-btrfs@vger.kernel.org Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Chris Mason <clm@fb.com>
Wang Shilong [Fri, 4 Jul 2014 09:59:06 +0000 (17:59 +0800)]
Btrfs: print btrfs specific info for some fatal error cases
Marc argued that if there are several btrfs filesystems mounted,
while users even don't know which filesystem hit the corrupted
errors something like generation verification failure.
Since @extent_buffer structure has a member @fs_info, let's output
btrfs device info.
Reported-by: Marc MERLIN <marc@merlins.org> Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
If we mounted a seed filesystem with degraded option, and then added a new
device into the seed filesystem, then we found adding device failed because
of the IO failure.
It is because the original didn't set the chunk on the seed device to be
read-only if the degraded flag was set. It was introduced by patch f48b90756,
which fixed the problem the raid1 filesystem became read-only after one device
of it was missing. But this fix method was not right, we should set the read-only
flag according to the number of the missing devices, not the degraded mount
option, if the number of the missing devices is less than the max error number
that the profile of the chunk tolerates, we don't set it to be read-only.
Cc: Josef Bacik <jbacik@fb.com> 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>
Wang Shilong [Thu, 3 Jul 2014 10:22:07 +0000 (18:22 +0800)]
Btrfs: make defragment work with nodatacow option
Btrfs defragment will utilize COW feature, which means this
did not work for nodatacow option, this problem was detected
by xfstests generic/018 with nodatacow mount option.
Fix this problem by forcing cow for a extent with state
@EXTETN_DEFRAG setting.
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>
mkfs.btrfs -f $TEST_DEV
UUID=$(btrfs fi show $TEST_DEV | head -1 | sed -e 's/.*uuid: \([-0-9a-z]*\)$/\1/')
mount $TEST_DEV $TEST_DIR
LABELFILE=/sys/fs/btrfs/$UUID/label
Anand Jain [Mon, 30 Jun 2014 16:58:56 +0000 (00:58 +0800)]
btrfs: device add must be sysloged
when we add a new disk to the mounted btrfs we don't record it
as of now, disk add is a critical change of btrfs configuration,
it must be recorded in the syslog to help offline investigations
of customer problems when reported.
Signed-off-by: Anand Jain <Anand.Jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
Wang Shilong [Mon, 30 Jun 2014 02:51:25 +0000 (10:51 +0800)]
Btrfs: clear compress-force when remounting with compress option
Steps to reproduce:
# mkfs.btrfs -f /dev/sdb
# mount /dev/sdb /mnt -o compress-force=lzo
# mount /dev/sdb /mnt -o remount,compress=zlib
# cat /proc/mounts
Remounting from compress-force to compress could not clear compress-force
option. The problem is there is no way for users to clear compress-force
option separately.
Fix this problem by clearing @FORCE_COMPRESS flag when remounting to
compress=xxx.
Suggested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com> Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> Reviewed-by: David Sterba <dsterba@suse.cz> Reviewed-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com> Tested-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
David Sterba [Wed, 4 Jun 2014 16:41:45 +0000 (18:41 +0200)]
btrfs: kill the key type accessor helpers
btrfs_set_key_type and btrfs_key_type are used inconsistently along with
open coded variants. Other members of btrfs_key are accessed directly
without any helpers anyway.
Signed-off-by: David Sterba <dsterba@suse.cz> Signed-off-by: Chris Mason <clm@fb.com>
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
"double iput() on failure exit in lustre, racy removal of spliced
dentries from ->s_anon in __d_materialise_dentry() plus a bunch of
assorted RCU pathwalk fixes"
The RCU pathwalk fixes end up fixing a couple of cases where we
incorrectly dropped out of RCU walking, due to incorrect initialization
and testing of the sequence locks in some corner cases. Since dropping
out of RCU walk mode forces the slow locked accesses, those corner cases
slowed down quite dramatically.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
be careful with nd->inode in path_init() and follow_dotdot_rcu()
don't bugger nd->seq on set_root_rcu() from follow_dotdot_rcu()
fix bogus read_seqretry() checks introduced in b37199e
move the call of __d_drop(anon) into __d_materialise_unique(dentry, anon)
[fix] lustre: d_make_root() does iput() on dentry allocation failure
vfs: avoid non-forwarding large load after small store in path lookup
The performance regression that Josef Bacik reported in the pathname
lookup (see commit 99d263d4c5b2 "vfs: fix bad hashing of dentries") made
me look at performance stability of the dcache code, just to verify that
the problem was actually fixed. That turned up a few other problems in
this area.
There are a few cases where we exit RCU lookup mode and go to the slow
serializing case when we shouldn't, Al has fixed those and they'll come
in with the next VFS pull.
But my performance verification also shows that link_path_walk() turns
out to have a very unfortunate 32-bit store of the length and hash of
the name we look up, followed by a 64-bit read of the combined hash_len
field. That screws up the processor store to load forwarding, causing
an unnecessary hickup in this critical routine.
It's caused by the ugly calling convention for the "hash_name()"
function, and easily fixed by just making hash_name() fill in the whole
'struct qstr' rather than passing it a pointer to just the hash value.
With that, the profile for this function looks much smoother.
Merge branch 'parisc-3.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux
Pull parisc updates from Helge Deller:
"The most important patch is a new Light Weigth Syscall (LWS) for 8,
16, 32 and 64 bit atomic CAS operations which is required in order to
be able to implement the atomic gcc builtins on our platform.
Other than that, we wire up the seccomp, getrandom and memfd_create
syscalls, fixes a minor off-by-one bug and a wrong printk string"
* 'parisc-3.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Implement new LWS CAS supporting 64 bit operations.
parisc: Wire up seccomp, getrandom and memfd_create syscalls
parisc: dino: fix %d confusingly prefixed with 0x in format string
parisc: sys_hpux: NUL terminator is one past the end
Al Viro [Sun, 14 Sep 2014 01:59:43 +0000 (21:59 -0400)]
be careful with nd->inode in path_init() and follow_dotdot_rcu()
in the former we simply check if dentry is still valid after picking
its ->d_inode; in the latter we fetch ->d_inode in the same places
where we fetch dentry and its ->d_seq, under the same checks.
Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Al Viro [Sun, 14 Sep 2014 01:55:46 +0000 (21:55 -0400)]
don't bugger nd->seq on set_root_rcu() from follow_dotdot_rcu()
return the value instead, and have path_init() do the assignment. Broken by
"vfs: Fix absolute RCU path walk failures due to uninitialized seq number",
which was Cc-stable with 2.6.38+ as destination. This one should go where
it went.
To avoid dummy value returned in case when root is already set (it would do
no harm, actually, since the only caller that doesn't ignore the return value
is guaranteed to have nd->root *not* set, but it's more obvious that way),
lift the check into callers. And do the same to set_root(), to keep them
in sync.
Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Merge tag 'ntb-3.17' of git://github.com/jonmason/ntb
Pull ntb driver bugfixes from Jon Mason:
"NTB driver fixes for queue spread and buffer alignment. Also, update
to MAINTAINERS to reflect new e-mail address"
* tag 'ntb-3.17' of git://github.com/jonmason/ntb:
ntb: Add alignment check to meet hardware requirement
MAINTAINERS: update NTB info
NTB: correct the spread of queues over mw's
Merge branch 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull ARM irq chip fixes from Thomas Gleixner:
"Another pile of ARM specific irq chip fixlets:
- off by one bugs in the crossbar driver
- missing annotations
- a bunch of "make it compile" updates
I pulled the lot today from Jason, but it has been in -next for at
least a week"
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip: gic-v3: Declare rdist as __percpu pointer to __iomem pointer
irqchip: gic: Make gic_default_routable_irq_domain_ops static
irqchip: exynos-combiner: Fix compilation error on ARM64
irqchip: crossbar: Off by one bugs in init
irqchip: gic-v3: Tag all low level accessors __maybe_unused
irqchip: gic-v3: Only define gic_peek_irq() when building SMP
Dave Jiang [Thu, 28 Aug 2014 20:53:02 +0000 (13:53 -0700)]
ntb: Add alignment check to meet hardware requirement
The NTB translate register must have the value to be BAR size aligned.
This alignment check make sure that the DMA memory allocated has the
proper alignment. Another requirement for NTB to function properly with
memory window BAR size greater or equal to 4M is to use the CMA feature
in 3.16 kernel with the appropriate CONFIG_CMA_ALIGNMENT and
CONFIG_CMA_SIZE_MBYTES set.
Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
Jon Mason [Thu, 19 Jun 2014 17:11:13 +0000 (10:11 -0700)]
NTB: correct the spread of queues over mw's
The detection of an uneven number of queues on the given memory windows
was not correct. The mw_num is zero based and the mod should be
division to spread them evenly over the mw's.
Merge branches 'locking-urgent-for-linus' and 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull futex and timer fixes from Thomas Gleixner:
"A oneliner bugfix for the jinxed futex code:
- Drop hash bucket lock in the error exit path. I really could slap
myself for intruducing that bug while fixing all the other horror
in that code three month ago ...
and the timer department is not too proud about the following fixes:
- Deal with a long standing rounding bug in the timeval to jiffies
conversion. It's a real issue and this fix fell through the cracks
for quite some time.
- Another round of alarmtimer fixes. Finally this code gets used
more widely and the subtle issues hidden for quite some time are
noticed and fixed. Nothing really exciting, just the itty bitty
details which bite the serious users here and there"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
futex: Unlock hb->lock in futex_wait_requeue_pi() error path
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
alarmtimer: Lock k_itimer during timer callback
alarmtimer: Do not signal SIGEV_NONE timers
alarmtimer: Return relative times in timer_gettime
jiffies: Fix timeval conversion to jiffies
Josef Bacik found a performance regression between 3.2 and 3.10 and
narrowed it down to commit bfcfaa77bdf0 ("vfs: use 'unsigned long'
accesses for dcache name comparison and hashing"). He reports:
On xfs on a fio card this goes at about 20k dir/sec with 3.2, and 12k
dir/sec with 3.10. This is because we spend waaaaay more time in
__d_lookup on 3.10 than in 3.2.
The new hashing function for strings is suboptimal for <
sizeof(unsigned long) string names (and hell even > sizeof(unsigned
long) string names that I've tested). I broke out the old hashing
function and the new one into a userspace helper to get real numbers
and this is what I'm getting:
Old hash table had 1000000 entries, 0 dupes, 0 max dupes
New hash table had 12628 entries, 987372 dupes, 900 max dupes
We had 11400 buckets with a p50 of 30 dupes, p90 of 240 dupes, p99 of 567 dupes for the new hash
My test does the hash, and then does the d_hash into a integer pointer
array the same size as the dentry hash table on my system, and then
just increments the value at the address we got to see how many
entries we overlap with.
As you can see the old hash function ended up with all 1 million
entries in their own bucket, whereas the new one they are only
distributed among ~12.5k buckets, which is why we're using so much
more CPU in __d_lookup".
The reason for this hash regression is two-fold:
- On 64-bit architectures the down-mixing of the original 64-bit
word-at-a-time hash into the final 32-bit hash value is very
simplistic and suboptimal, and just adds the two 32-bit parts
together.
In particular, because there is no bit shuffling and the mixing
boundary is also a byte boundary, similar character patterns in the
low and high word easily end up just canceling each other out.
- the old byte-at-a-time hash mixed each byte into the final hash as it
hashed the path component name, resulting in the low bits of the hash
generally being a good source of hash data. That is not true for the
word-at-a-time case, and the hash data is distributed among all the
bits.
The fix is the same in both cases: do a better job of mixing the bits up
and using as much of the hash data as possible. We already have the
"hash_32|64()" functions to do that.
Reported-by: Josef Bacik <jbacik@fb.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make hash_64() use a 64-bit multiply when appropriate
The hash_64() function historically does the multiply by the
GOLDEN_RATIO_PRIME_64 number with explicit shifts and adds, because
unlike the 32-bit case, gcc seems unable to turn the constant multiply
into the more appropriate shift and adds when required.
However, that means that we generate those shifts and adds even when the
architecture has a fast multiplier, and could just do it better in
hardware.
Use the now-cleaned-up CONFIG_ARCH_HAS_FAST_MULTIPLIER (together with
"is it a 64-bit architecture") to decide whether to use an integer
multiply or the explicit sequence of shift/add instructions.
Make ARCH_HAS_FAST_MULTIPLIER a real config variable
It used to be an ad-hoc hack defined by the x86 version of
<asm/bitops.h> that enabled a couple of library routines to know whether
an integer multiply is faster than repeated shifts and additions.
This just makes it use the real Kconfig system instead, and makes x86
(which was the only architecture that did this) select the option.
NOTE! Even for x86, this really is kind of wrong. If we cared, we would
probably not enable this for builds optimized for netburst (P4), where
shifts-and-adds are generally faster than multiplies. This patch does
*not* change that kind of logic, though, it is purely a syntactic change
with no code changes.
This was triggered by the fact that we have other places that really
want to know "do I want to expand multiples by constants by hand or
not", particularly the hash generation code.
Merge tag 'dm-3.17-fix2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fix from Mike Snitzer:
"Fix a race in the DM cache target that caused dirty blocks to be
marked as clean. This could cause no writeback to occur or spurious
dirty block counts"
* tag 'dm-3.17-fix2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm cache: fix race causing dirty blocks to be marked as clean
Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
"A small collection of fixes for the current rc series. This contains:
- Two small blk-mq patches from Rob Elliott, cleaning up error case
at init time.
- A fix from Ming Lei, fixing SG merging for blk-mq where
QUEUE_FLAG_SG_NO_MERGE is the default.
- A dev_t minor lifetime fix from Keith, fixing an issue where a
minor might be reused before all references to it were gone.
- Fix from Alan Stern where an unbalanced queue bypass caused SCSI
some headaches when it does a series of add/del on devices without
fully registrering the queue.
- A fix from me for improving the scaling of tag depth in blk-mq if
we are short on memory"
* 'for-linus' of git://git.kernel.dk/linux-block:
blk-mq: scale depth and rq map appropriate if low on memory
Block: fix unbalanced bypass-disable in blk_register_queue
block: Fix dev_t minor allocation lifetime
blk-mq: cleanup after blk_mq_init_rq_map failures
blk-mq: pass along blk_mq_alloc_tag_set return values
blk-merge: fix blk_recount_segments
Merge tag 'stable/for-linus-3.17-b-rc4-arm-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull Xen ARM bugfix from Stefano Stabellini:
"The patches fix the "xen_add_mach_to_phys_entry: cannot add" bug that
has been affecting xen on arm and arm64 guests since 3.16. They
require a few hypervisor side changes that just went in xen-unstable.
A couple of days ago David sent out a pull request with a few other
Xen fixes (it is already in master). Sorry we didn't synchronized
better among us"
* tag 'stable/for-linus-3.17-b-rc4-arm-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen/arm: remove mach_to_phys rbtree
xen/arm: reimplement xen_dma_unmap_page & friends
xen/arm: introduce XENFEAT_grant_map_identity
Richard Larocque [Wed, 10 Sep 2014 01:31:05 +0000 (18:31 -0700)]
alarmtimer: Lock k_itimer during timer callback
Locks the k_itimer's it_lock member when handling the alarm timer's
expiry callback.
The regular posix timers defined in posix-timers.c have this lock held
during timout processing because their callbacks are routed through
posix_timer_fn(). The alarm timers follow a different path, so they
ought to grab the lock somewhere else.
Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Sharvil Nanavati <sharvil@google.com> Signed-off-by: Richard Larocque <rlarocque@google.com> Signed-off-by: John Stultz <john.stultz@linaro.org>
Richard Larocque [Wed, 10 Sep 2014 01:31:04 +0000 (18:31 -0700)]
alarmtimer: Do not signal SIGEV_NONE timers
Avoids sending a signal to alarm timers created with sigev_notify set to
SIGEV_NONE by checking for that special case in the timeout callback.
The regular posix timers avoid sending signals to SIGEV_NONE timers by
not scheduling any callbacks for them in the first place. Although it
would be possible to do something similar for alarm timers, it's simpler
to handle this as a special case in the timeout.
Prior to this patch, the alarm timer would ignore the sigev_notify value
and try to deliver signals to the process anyway. Even worse, the
sanity check for the value of sigev_signo is skipped when SIGEV_NONE was
specified, so the signal number could be bogus. If sigev_signo was an
unitialized value (as it often would be if SIGEV_NONE is used), then
it's hard to predict which signal will be sent.
Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Sharvil Nanavati <sharvil@google.com> Signed-off-by: Richard Larocque <rlarocque@google.com> Signed-off-by: John Stultz <john.stultz@linaro.org>
Richard Larocque [Wed, 10 Sep 2014 01:31:03 +0000 (18:31 -0700)]
alarmtimer: Return relative times in timer_gettime
Returns the time remaining for an alarm timer, rather than the time at
which it is scheduled to expire. If the timer has already expired or it
is not currently scheduled, the it_value's members are set to zero.
This new behavior matches that of the other posix-timers and the POSIX
specifications.
This is a change in user-visible behavior, and may break existing
applications. Hopefully, few users rely on the old incorrect behavior.
Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Sharvil Nanavati <sharvil@google.com> Signed-off-by: Richard Larocque <rlarocque@google.com>
[jstultz: minor style tweak] Signed-off-by: John Stultz <john.stultz@linaro.org>
Andrew Hunter [Thu, 4 Sep 2014 21:17:16 +0000 (14:17 -0700)]
jiffies: Fix timeval conversion to jiffies
timeval_to_jiffies tried to round a timeval up to an integral number
of jiffies, but the logic for doing so was incorrect: intervals
corresponding to exactly N jiffies would become N+1. This manifested
itself particularly repeatedly stopping/starting an itimer:
would add a full tick to val, _even if it was exactly representable in
terms of jiffies_ (say, the result of a previous rounding.) Doing
this repeatedly would cause unbounded growth in val. So fix the math.
Here's what was wrong with the conversion: we essentially computed
(eliding seconds)
jiffies = usec * (NSEC_PER_USEC/TICK_NSEC)
by using scaling arithmetic, which took the best approximation of
NSEC_PER_USEC/TICK_NSEC with denominator of 2^USEC_JIFFIE_SC =
x/(2^USEC_JIFFIE_SC), and computed:
jiffies = (usec * x) >> USEC_JIFFIE_SC
and rounded this calculation up in the intermediate form (since we
can't necessarily exactly represent TICK_NSEC in usec.) But the
scaling arithmetic is a (very slight) *over*approximation of the true
value; that is, instead of dividing by (1 usec/ 1 jiffie), we
effectively divided by (1 usec/1 jiffie)-epsilon (rounding
down). This would normally be fine, but we want to round timeouts up,
and we did so by adding 2^USEC_JIFFIE_SC - 1 before the shift; this
would be fine if our division was exact, but dividing this by the
slightly smaller factor was equivalent to adding just _over_ 1 to the
final result (instead of just _under_ 1, as desired.)
In particular, with HZ=1000, we consistently computed that 10000 usec
was 11 jiffies; the same was true for any exact multiple of
TICK_NSEC.
We could possibly still round in the intermediate form, adding
something less than 2^USEC_JIFFIE_SC - 1, but easier still is to
convert usec->nsec, round in nanoseconds, and then convert using
time*spec*_to_jiffies. This adds one constant multiplication, and is
not observably slower in microbenchmarks on recent x86 hardware.
Tested: the following program:
int main() {
struct itimerval zero = {{0, 0}, {0, 0}};
/* Initially set to 10 ms. */
struct itimerval initial = zero;
initial.it_interval.tv_usec = 10000;
setitimer(ITIMER_PROF, &initial, NULL);
/* Save and restore several times. */
for (size_t i = 0; i < 10; ++i) {
struct itimerval prev;
setitimer(ITIMER_PROF, &zero, &prev);
/* on old kernels, this goes up by TICK_USEC every iteration */
printf("previous value: %ld %ld %ld %ld\n",
prev.it_interval.tv_sec, prev.it_interval.tv_usec,
prev.it_value.tv_sec, prev.it_value.tv_usec);
setitimer(ITIMER_PROF, &prev, NULL);
}
return 0;
}
Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Turner <pjt@google.com> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Reviewed-by: Paul Turner <pjt@google.com> Reported-by: Aaron Jacobs <jacobsa@google.com> Signed-off-by: Andrew Hunter <ahh@google.com>
[jstultz: Tweaked to apply to 3.17-rc] Signed-off-by: John Stultz <john.stultz@linaro.org>
Thomas Gleixner [Thu, 11 Sep 2014 21:44:35 +0000 (23:44 +0200)]
futex: Unlock hb->lock in futex_wait_requeue_pi() error path
futex_wait_requeue_pi() calls futex_wait_setup(). If
futex_wait_setup() succeeds it returns with hb->lock held and
preemption disabled. Now the sanity check after this does:
if (match_futex(&q.key, &key2)) {
ret = -EINVAL;
goto out_put_keys;
}
which releases the keys but does not release hb->lock.
So we happily return to user space with hb->lock held and therefor
preemption disabled.
Unlock hb->lock before taking the exit route.
Reported-by: Dave "Trinity" Jones <davej@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Darren Hart <dvhart@linux.intel.com> Reviewed-by: Davidlohr Bueso <dave@stgolabs.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1409112318500.4178@nanos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Merge tag 'char-misc-3.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char/misc driver fix from Greg KH:
"Here is one misc driver fix for 3.17-rc5. It resolves a kernel oops
that can happen in the lattice FPGA driver if the firmware isn't
present on the system.
It's been in the linux-next tree for a while now"
* tag 'char-misc-3.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
Lattice ECP3 FPGA: Check firmware pointer
Merge tag 'staging-3.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging
Pull staging driver fixes from Greg KH:
"Here are 3 tiny staging driver fixes for 3.17-rc5.
Two are fixes for the imx-drm driver, resolving issues that have been
reported. The other is a memory leak fix for the Android sync driver,
due to changes that went into 3.17-rc1.
All have been in linux-next for a while"
* tag 'staging-3.17-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
android: fix reference leak in sync_fence_create
imx-drm: imx-ldb: fix NULL pointer in imx_ldb_unbind()
imx-drm: ipuv3-plane: fix ipu_plane_dpms()
projects / linux-beck.git / log