When truncating cached inline_data, we don't need to allocate a new page
all the time. Instead, it must check its page cache only.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We don't need to make zeros beyond i_size, since we already wrote that through
NEW_ADDR case.
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Some applications may create multimeida file with temporary name like
'*.jpg.tmp' or '*.mp4.tmp', then rename to '*.jpg' or '*.mp4'.
Now, f2fs can only detect multimedia filename with specified format:
"filename + '.' + extension", so it will make f2fs missing to detect
multimedia file with special temporary name, result in failing to set
cold flag on file.
This patch enhances detection flow for enabling lookup extension in the
middle of temporary filename.
Reported-by: Xue Liu <liuxueliu.liu@huawei.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Add roll-forward recovery process for encrypted dentry, so the first fsync
issued to an encrypted file does not need writing checkpoint.
This improves the performance of the following test at thousands of small
files: open -> write -> fsync -> close
Signed-off-by: Shuoran Liu <liushuoran@huawei.com>
Acked-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: modify kernel message to show encrypted names]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch enhances the xattr consistency of dirs from suddern power-cuts.
Possible scenario would be:
1. dir->setxattr used by per-file encryption
2. file->setxattr goes into inline_xattr
3. file->fsync
In that case, we should do checkpoint for #1.
Otherwise we'd lose dir's key information for the file given #2.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Like most filesystems, f2fs will issue discard command synchronously, so
when user trigger fstrim through ioctl, multiple discard commands will be
issued serially with sync mode, which makes poor performance.
In this patch we try to support async discard, so that all discard
commands can be issued and be waited for endio in batch to improve
performance.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch sets encryption name flag in the add inline entry path
if filename is encrypted.
Signed-off-by: Shuoran Liu <liushuoran@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When decrypting dirents in ->readdir, fscrypt_fname_disk_to_usr won't
change content of original encrypted dirent, we don't need to allocate
additional buffer for storing mirror of it, so get rid of it.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When creating new inode, security_inode_init_security will be called for
initializing security info related to the inode, and filename is passed to
security module, it helps security module such as SElinux to know which
rule or label could be applied for the inode with specified name.
Previously, if new inode is created as an encrypted one, f2fs will transfer
encrypted filename to security module which may fail the check of security
policy belong to the inode. So in order to this issue, alter to transfer
original unencrypted filename instead.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In batch discard approach of fstrim will grab/release gc_mutex lock
repeatly, it makes contention of the lock becoming more intensive.
So after one batch discards were issued in checkpoint and the lock
was released, it's better to do schedule() to increase opportunity
of grabbing gc_mutex lock for other competitors.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Make inline_dentry as default mount option to improve space usage and
IO performance in scenario of numerous small directory.
It adds noinline_dentry mount option, instead.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In the following scenario,
1) we don't have the key and doing a lookup for encrypted file,
2) and the encrypted filename is big name
we should use fname->hash as name hash value instead of what is
calculated by fname->disk_name. Because in such case,
fname->disk_name is empty.
Signed-off-by: Shuoran Liu <liushuoran@huawei.com>
Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In write_begin(), we skip checking dnode block for preallocating block
when whole block needs to be updated since we preallocated its block in
f2fs_preallocate_blocks, for partial updated block, we will still try
to lock its node and do preallocation in write_begin(), so in
f2fs_preallocate_blocks we should not preallocate its block.
But previously, the calculation of preallocating block number is
incorrect, fix it.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: fix a bug]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Fixes the following sparse warning:
fs/f2fs/data.c:969:12: warning:
symbol 'f2fs_grab_bio' was not declared. Should it be static?
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
`flags' is used to save value from userspace, there is no need to
initialize it, and FS_FL_USER_VISIBLE is the mask for getflags.
Signed-off-by: Sheng Yong <shengyong1@huawei.com>
Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In available_free_memory, there are two same judgement conditions which
is used for checking NAT excess, remove one of them.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
During fstrim, if one of multiple write_checkpoint failed, break off and
return error number to caller.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If we preallocate blocks with f2fs_reserve_blocks in f2fs_map_blocks, we
should call f2fs_balance_fs for checking and reclaiming space, fix it.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When building each sit entry in cache, firstly, we will load it from
sit page, and then check all entries in sit journal, if there is one
updated entry in journal, cover cached entry with the journaled one.
Actually, most of check operation is unneeded since we only need
to update cached entries with journaled entries in batch, so
changing the flow as below for more efficient:
1. load all sit entries into cache from sit pages;
2. update sit entries with journal.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch changes to check valid block number of one GCed section
directly instead of checking the number in all segments of section
one by one in order to clean up codes of foreground GC.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We don't guarantee integrity of user data after checkpoint, since we only
guarantee meta data integrity for data consistency of filesystem.
Due to above reason, we only need to set fs as dirty when meta data is
updated, so that we can skip writing checkpoint in some case of non-meta
data is updated.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch enables to do fstrim without checkpoint, if there is no fs
change.
Signed-off-by: Yunlei He <heyunlei@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch add discard block count to sys entry of f2fs status
Signed-off-by: Yunlei He <heyunlei@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This includes a single bugfix for vhost-scsi.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJXvFsZAAoJECgfDbjSjVRpa0wIAJIiod8E6IShhSlMxF4cymyX
4XVIp/FDpaHE4jSVgWYX8uz4ZUC+49LHH9uM0bpH+EKxaatH+711krql+9cgxKaC
Jqq2kRlhfPxqcAadI4jKeeIFpk0WkBNkjyidZckpN/Ot4awAr0tjkJcK/mFGAN4p
j1ER8Y2AnAYaozly4Uz6FLgko8E0omRvdm9iY2TlV2WBUOy+UkIUPXsGGGsC1/Ws
2AjMQYrW9sfX0K9ZRu1h22PTq2jPN7901/HauKWCuqhlwjMGM4fP3DQNOdmnvOHV
moRRMMoxPwO9DNXnGep5agOknxijui8dWkxqjdeeIuagOPQE19bCRRalfEBWsr0=
=iYHw
-----END PGP SIGNATURE-----
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull vhost bugfix from Michael Tsirkin:
"This includes a single bugfix for vhost-scsi"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vhost/scsi: fix reuse of &vq->iov[out] in response
- avoid signed math problems on unexpected compilers
- avoid false positives at very end of kernel text range checks
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
Comment: Kees Cook <kees@outflux.net>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=5CiX
-----END PGP SIGNATURE-----
Merge tag 'usercopy-v4.8-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull hardened usercopy fixes from Kees Cook:
- avoid signed math problems on unexpected compilers
- avoid false positives at very end of kernel text range checks
* tag 'usercopy-v4.8-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
usercopy: fix overlap check for kernel text
usercopy: avoid potentially undefined behavior in pointer math
Pull crypto fixes from Herbert Xu:
"This fixes a number of memory corruption bugs in the newly added
sha256-mb/sha256-mb code"
* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
crypto: sha512-mb - fix ctx pointer
crypto: sha256-mb - fix ctx pointer and digest copy
The address of the iovec &vq->iov[out] is not guaranteed to contain the scsi
command's response iovec throughout the lifetime of the command. Rather, it
is more likely to contain an iovec from an immediately following command
after looping back around to vhost_get_vq_desc(). Pass along the iovec
entirely instead.
Fixes: 79c14141a4 ("vhost/scsi: Convert completion path to use copy_to_iter")
Cc: stable@vger.kernel.org
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
check_bogus_address() checked for pointer overflow using this expression,
where 'ptr' has type 'const void *':
ptr + n < ptr
Since pointer wraparound is undefined behavior, gcc at -O2 by default
treats it like the following, which would not behave as intended:
(long)n < 0
Fortunately, this doesn't currently happen for kernel code because kernel
code is compiled with -fno-strict-overflow. But the expression should be
fixed anyway to use well-defined integer arithmetic, since it could be
treated differently by different compilers in the future or could be
reported by tools checking for undefined behavior.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
- Support for Syscall ABI v4 with upstream gcc 6.x
- Lockdep fix (Daniel Mentz)
- gdb register clobber (Liav Rehana)
- Couple of missing exports for modules
- Other fixes here and there
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=1WGt
-----END PGP SIGNATURE-----
Merge tag 'arc-4.8-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc
Pull ARC fixes from Vineet Gupta:
- support for Syscall ABI v4 with upstream gcc 6.x
- lockdep fix (Daniel Mentz)
- gdb register clobber (Liav Rehana)
- couple of missing exports for modules
- other fixes here and there
* tag 'arc-4.8-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
ARC: export __udivdi3 for modules
ARC: mm: fix build breakage with STRICT_MM_TYPECHECKS
ARC: export kmap
ARC: Support syscall ABI v4
ARC: use correct offset in pt_regs for saving/restoring user mode r25
ARC: Elide redundant setup of DMA callbacks
ARC: Call trace_hardirqs_on() before enabling irqs
This fixes a Kconfig issue with UM: when I made GPIOLIB
available to all archs, that included UM, but the OF part
of GPIOLIB requires HAS_IOMEM, so we add HAS_IOMEM as a
dependency to OF_GPIO.
This in turn exposed the fact that a few GPIO drivers were
implicitly assuming OF_GPIO as their dependency but instead
depended on OF alone (the typical problem being a pointer
inside gpio_chip not existing unless OF_GPIO is selected)
and then UM would fail to compile with these drivers
instead. Then I lost patience and made any GPIO driver
depending on just OF depend on OF_GPIO instead, that is
certainly what they meant and the only thing that makes
sense anyway. GPIO with just OF but !OF_GPIO does not make
sense.
Also a fix for the max730x driver data pointer, and a minor
comment fix for the GPIO tools.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=isIb
-----END PGP SIGNATURE-----
Merge tag 'gpio-v4.8-2' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio
Pull GPIO fixes from Linus Walleij:
"Here are a few GPIO fixes for v4.8.
I was expecting some fallout from the new chardev rework but nothing
like that turned up att all. Instead a Kconfig confusion that I think
I have finally nailed, then some ordinary driver noise and trivia.
This fixes a Kconfig issue with UM: when I made GPIOLIB available to
all archs, that included UM, but the OF part of GPIOLIB requires
HAS_IOMEM, so we add HAS_IOMEM as a dependency to OF_GPIO.
This in turn exposed the fact that a few GPIO drivers were implicitly
assuming OF_GPIO as their dependency but instead depended on OF alone
(the typical problem being a pointer inside gpio_chip not existing
unless OF_GPIO is selected) and then UM would fail to compile with
these drivers instead. Then I lost patience and made any GPIO driver
depending on just OF depend on OF_GPIO instead, that is certainly what
they meant and the only thing that makes sense anyway. GPIO with just
OF but !OF_GPIO does not make sense.
Also a fix for the max730x driver data pointer, and a minor comment
fix for the GPIO tools"
* tag 'gpio-v4.8-2' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
gpio: make any OF dependent driver depend on OF_GPIO
gpio: Fix OF build problem on UM
gpio: max730x: set gpiochip data pointer before using it
tools/gpio: fix gpio-event-mon header comment
Pull two parisc fixes from Helge Deller:
"The first patch ensures that the high-res cr16 clocksource (which was
added in kernel 4.7) gets choosen as default clocksource for parisc.
The second patch moves the #define of EREFUSED down inside errno.h and
thus unbreaks building the gccgo compiler"
* 'parisc-4.8-2' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Fix order of EREFUSED define in errno.h
parisc: Fix automatic selection of cr16 clocksource
This is an entirely new driver instead of yet another set of patches
to sb_edac.c because:
1) Mapping from PCI devices to socket/memory controller is significantly
different. Skylake scatters devices on a socket across a number of
PCI buses.
2) There is an extra level of interleaving via the "mcroute" register
that would be a little messy to squeeze into the old driver.
3) Validation is getting too expensive. Changes to sb_edac need to
be checked against Sandy Bridge, Ivy Bridge, Haswell, Broadwell and
Knights Landing.
Acked-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When building gccgo in userspace, errno.h gets parsed and the go include file
sysinfo.go is generated.
Since EREFUSED is defined to the same value as ECONNREFUSED, and ECONNREFUSED
is defined later on in errno.h, this leads to go complaining that EREFUSED
isn't defined yet.
Fix this trivial problem by moving the define of EREFUSED down after
ECONNREFUSED in errno.h (and clean up the indenting while touching this line).
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org
Commit 54b6680090 (parisc: Add native high-resolution sched_clock()
implementation) added support to use the CPU-internal cr16 counters as reliable
clocksource with the help of HAVE_UNSTABLE_SCHED_CLOCK.
Sadly the commit missed to remove the hack which prevented cr16 to become the
default clocksource even on SMP systems.
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org # 4.7+
Some module using div_u64() was failing to link because the libgcc 64-bit
divide assist routine was not being exported for modules
Reported-by: avinashp@quantenna.com
Cc: stable@vger.kernel.org
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
The kernel test robot reported a usercopy failure in the new hardened
sanity checks, due to a page-crossing copy of the FPU state into the
task structure.
This happened because the kernel test robot was testing with SLOB, which
doesn't actually do the required book-keeping for slab allocations, and
as a result the hardening code didn't realize that the task struct
allocation was one single allocation - and the sanity checks fail.
Since SLOB doesn't even claim to support hardening (and you really
shouldn't use it), the straightforward solution is to just make the
usercopy hardening code depend on the allocator supporting it.
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
