Pull xfs updates from Darrick Wong:
"Here are the XFS changes for 4.12. The big new feature for this
release is the new space mapping ioctl that we've been discussing
since LSF2016, but other than that most of the patches are larger bug
fixes, memory corruption prevention, and other cleanups.
Summary:
- various code cleanups
- introduce GETFSMAP ioctl
- various refactoring
- avoid dio reads past eof
- fix memory corruption and other errors with fragmented directory blocks
- fix accidental userspace memory corruptions
- publish fs uuid in superblock
- make fstrim terminatable
- fix race between quotaoff and in-core inode creation
- avoid use-after-free when finishing up w/ buffer heads
- reserve enough space to handle bmap tree resizing during cow remap"
* tag 'xfs-4.12-merge-7' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (53 commits)
xfs: fix use-after-free in xfs_finish_page_writeback
xfs: reserve enough blocks to handle btree splits when remapping
xfs: wait on new inodes during quotaoff dquot release
xfs: update ag iterator to support wait on new inodes
xfs: support ability to wait on new inodes
xfs: publish UUID in struct super_block
xfs: Allow user to kill fstrim process
xfs: better log intent item refcount checking
xfs: fix up quotacheck buffer list error handling
xfs: remove xfs_trans_ail_delete_bulk
xfs: don't use bool values in trace buffers
xfs: fix getfsmap userspace memory corruption while setting OF_LAST
xfs: fix __user annotations for xfs_ioc_getfsmap
xfs: corruption needs to respect endianess too!
xfs: use NULL instead of 0 to initialize a pointer in xfs_ioc_getfsmap
xfs: use NULL instead of 0 to initialize a pointer in xfs_getfsmap
xfs: simplify validation of the unwritten extent bit
xfs: remove unused values from xfs_exntst_t
xfs: remove the unused XFS_MAXLINK_1 define
xfs: more do_div cleanups
...
Pull block fixes and updates from Jens Axboe:
"Some fixes and followup features/changes that should go in, in this
merge window. This contains:
- Two fixes for lightnvm from Javier, fixing problems in the new code
merge previously in this merge window.
- A fix from Jan for the backing device changes, fixing an issue in
NFS that causes a failure to mount on certain setups.
- A change from Christoph, cleaning up the blk-mq init and exit
request paths.
- Remove elevator_change(), which is now unused. From Bart.
- A fix for queue operation invocation on a dead queue, from Bart.
- A series fixing up mtip32xx for blk-mq scheduling, removing a
bandaid we previously had in place for this. From me.
- A regression fix for this series, fixing a case where we wait on
workqueue flushing from an invalid (non-blocking) context. From me.
- A fix/optimization from Ming, ensuring that we don't both quiesce
and freeze a queue at the same time.
- A fix from Peter on lock ordering for CPU hotplug. Not a real
problem right now, but will be once the CPU hotplug rework goes in.
- A series from Omar, cleaning up out blk-mq debugfs support, and
adding support for exporting info from schedulers in debugfs as
well. This is really useful in debugging stalls or livelocks. From
Omar"
* 'for-linus' of git://git.kernel.dk/linux-block: (28 commits)
mq-deadline: add debugfs attributes
kyber: add debugfs attributes
blk-mq-debugfs: allow schedulers to register debugfs attributes
blk-mq: untangle debugfs and sysfs
blk-mq: move debugfs declarations to a separate header file
blk-mq: Do not invoke queue operations on a dead queue
blk-mq-debugfs: get rid of a bunch of boilerplate
blk-mq-debugfs: rename hw queue directories from <n> to hctx<n>
blk-mq-debugfs: don't open code strstrip()
blk-mq-debugfs: error on long write to queue "state" file
blk-mq-debugfs: clean up flag definitions
blk-mq-debugfs: separate flags with |
nfs: Fix bdi handling for cloned superblocks
block/mq: Cure cpu hotplug lock inversion
lightnvm: fix bad back free on error path
lightnvm: create cmd before allocating request
blk-mq: don't use sync workqueue flushing from drivers
mtip32xx: convert internal commands to regular block infrastructure
mtip32xx: cleanup internal tag assumptions
block: don't call blk_mq_quiesce_queue() after queue is frozen
...
Pull libnvdimm updates from Dan Williams:
"The bulk of this has been in multiple -next releases. There were a few
late breaking fixes and small features that got added in the last
couple days, but the whole set has received a build success
notification from the kbuild robot.
Change summary:
- Region media error reporting: A libnvdimm region device is the
parent to one or more namespaces. To date, media errors have been
reported via the "badblocks" attribute attached to pmem block
devices for namespaces in "raw" or "memory" mode. Given that
namespaces can be in "device-dax" or "btt-sector" mode this new
interface reports media errors generically, i.e. independent of
namespace modes or state.
This subsequently allows userspace tooling to craft "ACPI 6.1
Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
requests and submit them via the ioctl path for NVDIMM root bus
devices.
- Introduce 'struct dax_device' and 'struct dax_operations': Prompted
by a request from Linus and feedback from Christoph this allows for
dax capable drivers to publish their own custom dax operations.
This fixes the broken assumption that all dax operations are
related to a persistent memory device, and makes it easier for
other architectures and platforms to add customized persistent
memory support.
- 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
available for storage appliance applications to manually trigger
memory controllers to drain write-pending buffers that would
otherwise be flushed automatically by the platform ADR
(asynchronous-DRAM-refresh) mechanism at a power loss event.
Support for "locked" DIMMs is included to prevent namespaces from
surfacing when the namespace label data area is locked. Finally,
fixes for various reported deadlocks and crashes, also tagged for
-stable.
- ACPI / nfit driver updates: General updates of the nfit driver to
add DSM command overrides, ACPI 6.1 health state flags support, DSM
payload debug available by default, and various fixes.
Acknowledgements that came after the branch was pushed:
- commmit 565851c972 "device-dax: fix sysfs attribute deadlock":
Tested-by: Yi Zhang <yizhan@redhat.com>
- commit 23f4984483 "libnvdimm: rework region badblocks clearing"
Tested-by: Toshi Kani <toshi.kani@hpe.com>"
* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
libnvdimm, pfn: fix 'npfns' vs section alignment
libnvdimm: handle locked label storage areas
libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
brd: fix uninitialized use of brd->dax_dev
block, dax: use correct format string in bdev_dax_supported
device-dax: fix sysfs attribute deadlock
libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
libnvdimm: rework region badblocks clearing
acpi, nfit: kill ACPI_NFIT_DEBUG
libnvdimm: fix clear length of nvdimm_forget_poison()
libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
libnvdimm, region: sysfs trigger for nvdimm_flush()
libnvdimm: fix phys_addr for nvdimm_clear_poison
x86, dax, pmem: remove indirection around memcpy_from_pmem()
block: remove block_device_operations ->direct_access()
block, dax: convert bdev_dax_supported() to dax_direct_access()
filesystem-dax: convert to dax_direct_access()
Revert "block: use DAX for partition table reads"
ext2, ext4, xfs: retrieve dax_device for iomap operations
...
Pull GFS2 updates from Bob Peterson:
"We've got ten GFS2 patches for this merge window.
- Andreas Gruenbacher wrote a patch to replace the deprecated call to
rhashtable_walk_init with rhashtable_walk_enter.
- Andreas also wrote a patch to eliminate redundant code in two of
our debugfs sequence files.
- Andreas also cleaned up the rhashtable key ugliness Linus pointed
out during this cycle, following Linus's suggestions.
- Andreas also wrote a patch to take advantage of his new function
rhashtable_lookup_get_insert_fast. This makes glock lookup faster
and more bullet-proof.
- Andreas also wrote a patch to revert a patch in the evict path that
caused occasional deadlocks, and is no longer needed.
- Andrew Price wrote a patch to re-enable fallocate for the rindex
system file to enable gfs2_grow to grow properly on secondary file
system grow operations.
- I wrote a patch to initialize an inode number field to make certain
kernel trace points more understandable.
- I also wrote a patch that makes GFS2 file system "withdraw" work
more like it should by ignoring operations after a withdraw that
would formerly cause a BUG() and kernel panic.
- I also reworked the entire truncate/delete algorithm, scrapping the
old recursive algorithm in favor of a new non-recursive algorithm.
This was done for performance: This way, GFS2 no longer needs to
lock multiple resource groups while doing truncates and deletes of
files that cross multiple resource group boundaries, allowing for
better parallelism. It also solves a problem whereby deleting large
files would request a large chunk of kernel memory, which resulted
in a get_page_from_freelist warning.
- Due to a regression found during testing, I added a new patch to
correct 'GFS2: Prevent BUG from occurring when normal Withdraws
occur'."
* tag 'gfs2-4.12.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
GFS2: Allow glocks to be unlocked after withdraw
GFS2: Non-recursive delete
gfs2: Re-enable fallocate for the rindex
Revert "GFS2: Wait for iopen glock dequeues"
gfs2: Switch to rhashtable_lookup_get_insert_fast
GFS2: Temporarily zero i_no_addr when creating a dinode
gfs2: Don't pack struct lm_lockname
gfs2: Deduplicate gfs2_{glocks,glstats}_open
gfs2: Replace rhashtable_walk_init with rhashtable_walk_enter
GFS2: Prevent BUG from occurring when normal Withdraws occur
Pull orangefs updates from Mike Marshall:
"Orangefs cleanups, fixes and statx support.
Some cleanups:
- remove unused get_fsid_from_ino
- fix bounds check for listxattr
- clean up oversize xattr validation
- do not set getattr_time on orangefs_lookup
- return from orangefs_devreq_read quickly if possible
- do not wait for timeout if umounting
- handle zero size write in debugfs
Bug fixes:
- do not check possibly stale size on truncate
- ensure the userspace component is unmounted if mount fails
- total reimplementation of dir.c
New feature:
- implement statx
The new implementation of dir.c is kind of a big deal, all new code.
It has been posted to fs-devel during the previous rc period, we
didn't get much review or feedback from there, but it has been
reviewed very heavily here, so much so that we have two entire
versions of the reimplementation.
Not only does the new implementation fix some xfstests, but it passes
all the new tests we made here that involve seeking and rewinding and
giant directories and long file names. The new dir code has three
patches itself:
- skip forward to the next directory entry if seek is short
- invalidate stored directory on seek
- count directory pieces correctly"
* tag 'for-linus-4.12-ofs-1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux:
orangefs: count directory pieces correctly
orangefs: invalidate stored directory on seek
orangefs: skip forward to the next directory entry if seek is short
orangefs: handle zero size write in debugfs
orangefs: do not wait for timeout if umounting
orangefs: return from orangefs_devreq_read quickly if possible
orangefs: ensure the userspace component is unmounted if mount fails
orangefs: do not check possibly stale size on truncate
orangefs: implement statx
orangefs: remove ORANGEFS_READDIR macros
orangefs: support very large directories
orangefs: support llseek on directories
orangefs: rewrite readdir to fix several bugs
orangefs: do not set getattr_time on orangefs_lookup
orangefs: clean up oversize xattr validation
orangefs: fix bounds check for listxattr
orangefs: remove unused get_fsid_from_ino
Pull befs fix from Luis de Bethencourt:
"One fix from Fabian Frederick making the nfs client still work after a
cache drop"
* tag 'befs-v4.12-rc1' of git://github.com/luisbg/linux-befs:
befs: make export work with cold dcache
Process RENAME_EXCHANGE in affs_rename2() adding static
affs_xrename() based on affs_rename().
We remove headers from respective directories then
affect bh to other inode directory entries for swapping.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Currently AFFS only supports RENAME_NOREPLACE.
This patch isolates that method to a static function to
prepare RENAME_EXCHANGE addition.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This bug fixes a regression introduced by patch 0d1c7ae9d8.
The intent of the patch was to stop promoting glocks after a
file system is withdrawn due to a variety of errors, because doing
so results in a BUG(). (You should be able to unmount after a
withdraw rather than having the kernel panic.)
Unfortunately, it also stopped demotions, so glocks could not be
unlocked after withdraw, which means the unmount would hang.
This patch allows function do_xmote to demote locks to an
unlocked state after a withdraw, but not promote them.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Pull namespace updates from Eric Biederman:
"This is a set of small fixes that were mostly stumbled over during
more significant development. This proc fix and the fix to
posix-timers are the most significant of the lot.
There is a lot of good development going on but unfortunately it
didn't quite make the merge window"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
proc: Fix unbalanced hard link numbers
signal: Make kill_proc_info static
rlimit: Properly call security_task_setrlimit
signal: Remove unused definition of sig_user_definied
ia64: Remove unused IA64_TASK_SIGHAND_OFFSET and IA64_SIGHAND_SIGLOCK_OFFSET
ipc: Remove unused declaration of recompute_msgmni
posix-timers: Correct sanity check in posix_cpu_nsleep
sysctl: Remove dead register_sysctl_root
This patch removes useless nfs_readdir_get_array() and
nfs_readdir_release_array() as suggested by Trond Myklebust
nfs_readdir() calls nfs_revalidate_mapping() before
readdir_search_pagecache() , nfs_do_filldir(), uncached_readdir()
so mapping should be correct.
While kmap() can't fail, all subsequent error checks were removed
as well as unused labels.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
When using 'ls -l' to display a large directory, if noac option is used,
in function nfs_getattr() nfs_need_revalidate_inode() will always be true
for NFSv3 and the nfs_entry cache of the directory will be flushed. The
flush will lead to a fully reread of the directory entries from server.
To prevent the unnecessary RPCs, we need to check whether or not the
noac option is used, and always report the invocation of nfs_getattr()
as cache hit instead cache miss when it's on.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
If memory allocation fails for the callback data, we need to put the nfs_client
or we end up with an elevated refcount.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
If the server returns NFS4ERR_CONN_NOT_BOUND_TO_SESSION because we
are trunking, then RECLAIM_COMPLETE must handle that by calling
nfs4_schedule_session_recovery() and then retrying.
Reported-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Tested-by: Chuck Lever <chuck.lever@oracle.com>
SFM is mapping doublequote to 0xF020
Without this patch creating files with doublequote fails to Windows/Mac
Signed-off-by: Bjoern Jacke <bjacke@samba.org>
Signed-off-by: Steve French <smfrench@gmail.com>
CC: stable <stable@vger.kernel.org>
based on commit b3b42c0dea
("fs/affs: make export work with cold dcache")
This adds get_parent function so that nfs client can still work after
cache drop (Tested on NFS v4 with echo 3 > /proc/sys/vm/drop_caches)
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Luis de Bethencourt <luisbg@osg.samsung.com>
An upper type non directory dentry that is a copy up target
should have a reference to its lower copy up origin.
There are three ways for an upper type dentry to be instantiated:
1. A lower type dentry that is being copied up
2. An entry that is found in upper dir by ovl_lookup()
3. A negative dentry is hardlinked to an upper type dentry
In the first case, the lower reference is set before copy up.
In the second case, the lower reference is found by ovl_lookup().
In the last case of hardlinked upper dentry, it is not easy to
update the lower reference of the negative dentry. Instead,
drop the newly hardlinked negative dentry from dcache and let
the next access call ovl_lookup() to find its lower reference.
This makes sure that the inode number reported by stat(2) after
the hardlink is created is the same inode number that will be
reported by stat(2) after mount cycle, which is the inode number
of the lower copy up origin of the hardlink source.
NOTE that this does not fix breaking of lower hardlinks on copy
up, but only fixes the case of lower nlink == 1, whose upper copy
up inode is hardlinked in upper dir.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
When all layers are on the same underlying filesystem, let stat(2) return
st_dev/st_ino values of the copy up origin inode if it is known.
This results in constant st_ino/st_dev representation of files in an
overlay mount before and after copy up.
When the underlying filesystem support NFS exportfs, the result is also
persistent st_ino/st_dev representation before and after mount cycle.
Lower hardlinks are broken on copy up to different upper files, so we
cannot use the lower origin st_ino for those different files, even for the
same fs case.
When all overlay layers are on the same fs, use overlay st_dev for non-dirs
to get the correct result from du -x.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
stat(2) on overlay directories reports the overlay temp inode
number, which is constant across copy up, but is not persistent.
When all layers are on the same fs, report the copy up origin inode
number for directories.
This inode number is persistent, unique across the overlay mount and
constant across copy up.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
For directory entries, non zero oe->numlower implies OVL_TYPE_MERGE.
Define a new type flag OVL_TYPE_ORIGIN to indicate that an entry holds a
reference to its lower copy up origin.
For directory entries ORIGIN := MERGE && UPPER. For non-dir entries ORIGIN
means that a lower type dentry has been recently copied up or that we were
able to find the copy up origin from overlay.origin xattr.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
If overlay.origin xattr is found on a non-dir upper inode try to get lower
dentry by calling exportfs_decode_fh().
On failure to lookup by file handle to lower layer, do not lookup the copy
up origin by name, because the lower found by name could be another file in
case the upper file was renamed.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Sometimes it is interesting to know if an upper file is pure upper or a
copy up target, and if it is a copy up target, it may be interesting to
find the copy up origin.
This will be used to preserve lower inode numbers across copy up.
Store the lower inode file handle in upper inode extended attribute
overlay.origin on copy up to use it later for these cases. Store the lower
filesystem uuid along side the file handle, so we can validate that we are
looking for the origin file in the original fs.
If lower fs does not support NFS export ops store a zero sized xattr so we
can always use the overlay.origin xattr to distinguish between a copy up
and a pure upper inode.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Some features can only work when all layers are on the same fs. Test this
condition during mount time, so features can check them later.
Add helper ovl_same_sb() to return the common super block in case all
layers are on the same fs.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Pull char/misc driver updates from Greg KH:
"Here is the big set of new char/misc driver drivers and features for
4.12-rc1.
There's lots of new drivers added this time around, new firmware
drivers from Google, more auxdisplay drivers, extcon drivers, fpga
drivers, and a bunch of other driver updates. Nothing major, except if
you happen to have the hardware for these drivers, and then you will
be happy :)
All of these have been in linux-next for a while with no reported
issues"
* tag 'char-misc-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (136 commits)
firmware: google memconsole: Fix return value check in platform_memconsole_init()
firmware: Google VPD: Fix return value check in vpd_platform_init()
goldfish_pipe: fix build warning about using too much stack.
goldfish_pipe: An implementation of more parallel pipe
fpga fr br: update supported version numbers
fpga: region: release FPGA region reference in error path
fpga altera-hps2fpga: disable/unprepare clock on error in alt_fpga_bridge_probe()
mei: drop the TODO from samples
firmware: Google VPD sysfs driver
firmware: Google VPD: import lib_vpd source files
misc: lkdtm: Add volatile to intentional NULL pointer reference
eeprom: idt_89hpesx: Add OF device ID table
misc: ds1682: Add OF device ID table
misc: tsl2550: Add OF device ID table
w1: Remove unneeded use of assert() and remove w1_log.h
w1: Use kernel common min() implementation
uio_mf624: Align memory regions to page size and set correct offsets
uio_mf624: Refactor memory info initialization
uio: Allow handling of non page-aligned memory regions
hangcheck-timer: Fix typo in comment
...
Commits cc8385b59e and 7ef70b4d99 added preallocation for the
reada radix trees and also switched them over to GFP_KERNEL for the
default gfp mask.
Since we're doing radix tree insertions under spinlocks, we need
to make sure the mask doesn't allow sleeping. This fix keeps
the radix preallocation but switches back to the original gfp_mask.
Reported-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
A large directory full of differently sized file names triggered this.
Most directories, even very large directories with shorter names, would
be lucky enough to fit in one server response.
Signed-off-by: Martin Brandenburg <martin@omnibond.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
If an application seeks to a position before the point which has been
read, it must want updates which have been made to the directory. So
delete the copy stored in the kernel so it will be fetched again.
Signed-off-by: Martin Brandenburg <martin@omnibond.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
If userspace seeks to a position in the stream which is not correct, it
would have returned EIO because the data in the buffer at that offset
would be incorrect. This and the userspace daemon returning a corrupt
directory are indistinguishable.
Now if the data does not look right, skip forward to the next chunk and
try again. The motivation is that if the directory changes, an
application may seek to a position that was valid and no longer is valid.
It is not yet possible for a directory to change.
Signed-off-by: Martin Brandenburg <martin@omnibond.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
When ext4 encryption was originally merged, we were encrypting the
user-specified filename in ext4_match(), introducing a lot of additional
complexity into ext4_match() and its callers. This has since been
changed to encrypt the filename earlier, so we can remove the gunk
that's no longer needed. This more or less reverts ext4_search_dir()
and ext4_find_dest_de() to the way they were in the v4.0 kernel.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Switch f2fs directory searches to use the fscrypt_match_name() helper
function. There should be no functional change.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Switch ext4 directory searches to use the fscrypt_match_name() helper
function. There should be no functional change.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Introduce a helper function fscrypt_match_name() which tests whether a
fscrypt_name matches a directory entry. Also clean up the magic numbers
and document things properly.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
When accessing an encrypted directory without the key, userspace must
operate on filenames derived from the ciphertext names, which contain
arbitrary bytes. Since we must support filenames as long as NAME_MAX,
we can't always just base64-encode the ciphertext, since that may make
it too long. Currently, this is solved by presenting long names in an
abbreviated form containing any needed filesystem-specific hashes (e.g.
to identify a directory block), then the last 16 bytes of ciphertext.
This needs to be sufficient to identify the actual name on lookup.
However, there is a bug. It seems to have been assumed that due to the
use of a CBC (ciphertext block chaining)-based encryption mode, the last
16 bytes (i.e. the AES block size) of ciphertext would depend on the
full plaintext, preventing collisions. However, we actually use CBC
with ciphertext stealing (CTS), which handles the last two blocks
specially, causing them to appear "flipped". Thus, it's actually the
second-to-last block which depends on the full plaintext.
This caused long filenames that differ only near the end of their
plaintexts to, when observed without the key, point to the wrong inode
and be undeletable. For example, with ext4:
# echo pass | e4crypt add_key -p 16 edir/
# seq -f "edir/abcdefghijklmnopqrstuvwxyz012345%.0f" 100000 | xargs touch
# find edir/ -type f | xargs stat -c %i | sort | uniq | wc -l
100000
# sync
# echo 3 > /proc/sys/vm/drop_caches
# keyctl new_session
# find edir/ -type f | xargs stat -c %i | sort | uniq | wc -l
2004
# rm -rf edir/
rm: cannot remove 'edir/_A7nNFi3rhkEQlJ6P,hdzluhODKOeWx5V': Structure needs cleaning
...
To fix this, when presenting long encrypted filenames, encode the
second-to-last block of ciphertext rather than the last 16 bytes.
Although it would be nice to solve this without depending on a specific
encryption mode, that would mean doing a cryptographic hash like SHA-256
which would be much less efficient. This way is sufficient for now, and
it's still compatible with encryption modes like HEH which are strong
pseudorandom permutations. Also, changing the presented names is still
allowed at any time because they are only provided to allow applications
to do things like delete encrypted directories. They're not designed to
be used to persistently identify files --- which would be hard to do
anyway, given that they're encrypted after all.
For ease of backports, this patch only makes the minimal fix to both
ext4 and f2fs. It leaves ubifs as-is, since ubifs doesn't compare the
ciphertext block yet. Follow-on patches will clean things up properly
and make the filesystems use a shared helper function.
Fixes: 5de0b4d0cd ("ext4 crypto: simplify and speed up filename encryption")
Reported-by: Gwendal Grignou <gwendal@chromium.org>
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
If user has no key under an encrypted dir, fscrypt gives digested dentries.
Previously, when looking up a dentry, f2fs only checks its hash value with
first 4 bytes of the digested dentry, which didn't handle hash collisions fully.
This patch enhances to check entire dentry bytes likewise ext4.
Eric reported how to reproduce this issue by:
# seq -f "edir/abcdefghijklmnopqrstuvwxyz012345%.0f" 100000 | xargs touch
# find edir -type f | xargs stat -c %i | sort | uniq | wc -l
100000
# sync
# echo 3 > /proc/sys/vm/drop_caches
# keyctl new_session
# find edir -type f | xargs stat -c %i | sort | uniq | wc -l
99999
Cc: <stable@vger.kernel.org>
Reported-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
(fixed f2fs_dentry_hash() to work even when the hash is 0)
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
As ext4 and f2fs do, ubifs should check for consistent encryption
contexts during ->lookup() in an encrypted directory. This protects
certain users of filesystem encryption against certain types of offline
attacks.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
As for ext4, now that fscrypt_has_permitted_context() correctly handles
the case where we have the key for the parent directory but not the
child, f2fs_lookup() no longer has to work around it. Also add the same
warning message that ext4 uses.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Now that fscrypt_has_permitted_context() correctly handles the case
where we have the key for the parent directory but not the child, we
don't need to try to work around this in ext4_lookup().
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
To mitigate some types of offline attacks, filesystem encryption is
designed to enforce that all files in an encrypted directory tree use
the same encryption policy (i.e. the same encryption context excluding
the nonce). However, the fscrypt_has_permitted_context() function which
enforces this relies on comparing struct fscrypt_info's, which are only
available when we have the encryption keys. This can cause two
incorrect behaviors:
1. If we have the parent directory's key but not the child's key, or
vice versa, then fscrypt_has_permitted_context() returned false,
causing applications to see EPERM or ENOKEY. This is incorrect if
the encryption contexts are in fact consistent. Although we'd
normally have either both keys or neither key in that case since the
master_key_descriptors would be the same, this is not guaranteed
because keys can be added or removed from keyrings at any time.
2. If we have neither the parent's key nor the child's key, then
fscrypt_has_permitted_context() returned true, causing applications
to see no error (or else an error for some other reason). This is
incorrect if the encryption contexts are in fact inconsistent, since
in that case we should deny access.
To fix this, retrieve and compare the fscrypt_contexts if we are unable
to set up both fscrypt_infos.
While this slightly hurts performance when accessing an encrypted
directory tree without the key, this isn't a case we really need to be
optimizing for; access *with* the key is much more important.
Furthermore, the performance hit is barely noticeable given that we are
already retrieving the fscrypt_context and doing two keyring searches in
fscrypt_get_encryption_info(). If we ever actually wanted to optimize
this case we might start by caching the fscrypt_contexts.
Cc: stable@vger.kernel.org # 4.0+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Currently jbd2_write_superblock() silently adds REQ_SYNC to flags with
which journal superblock is written. Make this explicit by making flags
passed down to jbd2_write_superblock() contain REQ_SYNC.
CC: linux-ext4@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Commit b685d3d65a "block: treat REQ_FUA and REQ_PREFLUSH as
synchronous" removed REQ_SYNC flag from WRITE_FUA implementation.
generic_make_request_checks() however strips REQ_FUA flag from a bio
when the storage doesn't report volatile write cache and thus write
effectively becomes asynchronous which can lead to performance
regressions. This affects superblock writes for ext4. Fix the problem
by marking superblock writes always as synchronous.
Fixes: b685d3d65a
CC: linux-ext4@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
In commit 0d3b12584972 "nfs: Convert to separately allocated bdi" I have
wrongly cloned bdi reference in nfs_clone_super(). Further inspection
has shown that originally the code was actually allocating a new bdi (in
->clone_server callback) which was later registered in
nfs_fs_mount_common() and used for sb->s_bdi in nfs_initialise_sb().
This could later result in bdi for the original superblock not getting
unregistered when that superblock got shutdown (as the cloned sb still
held bdi reference) and later when a new superblock was created under
the same anonymous device number, a clash in sysfs has happened on bdi
registration:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 10284 at /linux-next/fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x74
sysfs: cannot create duplicate filename '/devices/virtual/bdi/0:32'
Modules linked in: axp20x_usb_power gpio_axp209 nvmem_sunxi_sid sun4i_dma sun4i_ss virt_dma
CPU: 1 PID: 10284 Comm: mount.nfs Not tainted 4.11.0-rc4+ #14
Hardware name: Allwinner sun7i (A20) Family
[<c010f19c>] (unwind_backtrace) from [<c010bc74>] (show_stack+0x10/0x14)
[<c010bc74>] (show_stack) from [<c03c6e24>] (dump_stack+0x78/0x8c)
[<c03c6e24>] (dump_stack) from [<c0122200>] (__warn+0xe8/0x100)
[<c0122200>] (__warn) from [<c0122250>] (warn_slowpath_fmt+0x38/0x48)
[<c0122250>] (warn_slowpath_fmt) from [<c02ac178>] (sysfs_warn_dup+0x64/0x74)
[<c02ac178>] (sysfs_warn_dup) from [<c02ac254>] (sysfs_create_dir_ns+0x84/0x94)
[<c02ac254>] (sysfs_create_dir_ns) from [<c03c8b8c>] (kobject_add_internal+0x9c/0x2ec)
[<c03c8b8c>] (kobject_add_internal) from [<c03c8e24>] (kobject_add+0x48/0x98)
[<c03c8e24>] (kobject_add) from [<c048d75c>] (device_add+0xe4/0x5a0)
[<c048d75c>] (device_add) from [<c048ddb4>] (device_create_groups_vargs+0xac/0xbc)
[<c048ddb4>] (device_create_groups_vargs) from [<c048dde4>] (device_create_vargs+0x20/0x28)
[<c048dde4>] (device_create_vargs) from [<c02075c8>] (bdi_register_va+0x44/0xfc)
[<c02075c8>] (bdi_register_va) from [<c023d378>] (super_setup_bdi_name+0x48/0xa4)
[<c023d378>] (super_setup_bdi_name) from [<c0312ef4>] (nfs_fill_super+0x1a4/0x204)
[<c0312ef4>] (nfs_fill_super) from [<c03133f0>] (nfs_fs_mount_common+0x140/0x1e8)
[<c03133f0>] (nfs_fs_mount_common) from [<c03335cc>] (nfs4_remote_mount+0x50/0x58)
[<c03335cc>] (nfs4_remote_mount) from [<c023ef98>] (mount_fs+0x14/0xa4)
[<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128)
[<c025cba0>] (vfs_kern_mount) from [<c033352c>] (nfs_do_root_mount+0x80/0xa0)
[<c033352c>] (nfs_do_root_mount) from [<c0333818>] (nfs4_try_mount+0x28/0x3c)
[<c0333818>] (nfs4_try_mount) from [<c0313874>] (nfs_fs_mount+0x2cc/0x8c4)
[<c0313874>] (nfs_fs_mount) from [<c023ef98>] (mount_fs+0x14/0xa4)
[<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128)
[<c025cba0>] (vfs_kern_mount) from [<c02600f0>] (do_mount+0x158/0xc7c)
[<c02600f0>] (do_mount) from [<c0260f98>] (SyS_mount+0x8c/0xb4)
[<c0260f98>] (SyS_mount) from [<c0107840>] (ret_fast_syscall+0x0/0x3c)
Fix the problem by always creating new bdi for a superblock as we used
to do.
Reported-and-tested-by: Corentin Labbe <clabbe.montjoie@gmail.com>
Fixes: 0d3b12584972ce5781179ad3f15cca3cdb5cae05
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
The file open flags (O_foo) are platform specific and should never go
out to an interface that is not local to the system.
Unfortunately these flags have leaked out onto the wire in the cephfs
implementation. That lead to bogus flags getting transmitted on ppc64.
This patch converts the kernel view of flags to the ceph view of file
open flags.
Fixes: 124e68e74 ("ceph: file operations")
Signed-off-by: Alexander Graf <agraf@suse.de>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
The dirfragtree is lazily updated, it's not always accurate. Infinite
loops happens in following circumstance.
- client send request to read frag A
- frag A has been fragmented into frag B and C. So mds fills the reply
with contents of frag B
- client wants to read next frag C. ceph_choose_frag(frag value of C)
return frag A.
The fix is using previous readdir reply to calculate next readdir frag
when possible.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Currently, we don't have a real feedback mechanism in place for when we
start seeing buffered writeback errors. If writeback is failing, there
is nothing that prevents an application from continuing to dirty pages
that aren't being cleaned.
In the event that we're seeing write errors of any sort occur on an
inode, have the callback set a flag to force further writes to be
synchronous. When the next write succeeds, clear the flag to allow
buffered writeback to continue.
Since this is just a hint to the write submission mechanism, we only
take the i_ceph_lock when a lockless check shows that the flag needs to
be changed.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: "Yan, Zheng” <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This reverts commit b109eec6f4.
If I'm filling up a filesystem with this sort of command:
$ dd if=/dev/urandom of=/mnt/cephfs/fillfile bs=2M oflag=sync
...then I'll eventually get back EIO on a write. Further calls
will give us ENOSPC.
I'm not sure what prompted this change, but I don't think it's what we
want to do. If writepages failed, we will have already set the mapping
error appropriately, and that's what gets reported by fsync() or
close().
__filemap_fdatawait_range however, does this:
wait_on_page_writeback(page);
if (TestClearPageError(page))
ret = -EIO;
...and that -EIO ends up trumping the mapping's error if one exists.
When writepages fails, we only want to set the error in the mapping,
and not flag the individual pages.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: "Yan, Zheng” <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Have the client store and update the osdc epoch_barrier when a cap
message comes in with one.
When sending cap messages, send the epoch barrier as well. This allows
clients to inform servers that their released caps may not be used until
a particular OSD map epoch.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: "Yan, Zheng” <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
