This reverts commit d4f032e36b as it
causes merge conflicts in 6.0-rc2.
If it is still needed in an Android kernel release, it can be added back
into a release-specific branch at a later point in time.
Bug: 184594949
Cc: Pavankumar Kondeti <quic_pkondeti@quicinc.com>
Cc: Shaleen Agrawal <shalagra@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I5d2ff43a1e4e14308c41cfd5d2d752836a134ae0
This `clang-analyzer` check flags the use of memset(), suggesting a more
secure version of the API, such as memset_s(), which does not exist in
the kernel:
warning: Call to function 'memset' is insecure as it does not provide
security checks introduced in the C11 standard. Replace with analogous
functions that support length arguments or provides boundary checks such
as 'memset_s' in case of C11
[clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling]
Signed-off-by: Guru Das Srinagesh <quic_gurus@quicinc.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
(cherry picked from commit 4be72c1b9f)
Change-Id: Idb6c210cb6566044948fe95222ded9aad854fcba
This config has been removed from upstream in commit f9987921cb
("lib/stackdepot: replace CONFIG_STACK_HASH_ORDER with automatic
sizing").
Fixes: f9987921cb ("lib/stackdepot: replace CONFIG_STACK_HASH_ORDER with automatic sizing")
Signed-off-by: Will McVicker <willmcvicker@google.com>
Change-Id: I06a194a234bd630d8ce28bf9e1b9346f08e3f32c
Upstream mandates registering shrinkers with a name now.
Fixes: e33c267ab7 ("mm: shrinkers: provide shrinkers with names")
Change-Id: I434150d024e976fc3facfc4b34a2199a9c2e5d08
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
Steps on the way to 6.0-rc1
Resolves merge conflicts with:
init/Kconfig
kernel/module/Kconfig
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I92b7f12c0ba853ee8bfc81d072fb6eced54dbfa9
Steps on the way to 6.0-rc1
Resolves merge conflicts with:
include/linux/sched.h
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I90c2473a63b1484f91ac5e64f524faa586d5ab93
* changes:
ANDROID: vendor_hooks: update android_vh_ufs_send_uic_command
Merge 29b1d469f3 ("Merge tag 'trace-rtla-v5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace") into android-mainline
Merge 746fc76b82 ("Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi") into android-mainline
Merge 328141e51e ("Merge tag 'mmc-v5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc") into android-mainline
ANDROID: fix up arm64 gki_defconfig for CONFIG_CLK_SUNXI
Merge 36001a2fa6 ("Merge tag 'clk-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux") into android-mainline
Merge 37644cac6e ("Merge tag 'gpio-updates-for-v6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux") into android-mainline
Pull cgroup fixes from Tejun Heo:
- The psi data structure was changed to be allocated dynamically but
it wasn't being cleared leading to it reporting garbage values and
triggering spurious oom kills.
- A deadlock involving cpuset and cpu hotplug.
- When a controller is moved across cgroup hierarchies,
css->rstat_css_node didn't get RCU drained properly from the previous
list.
* tag 'cgroup-for-6.0-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: Fix race condition at rebind_subsystems()
cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock
sched/psi: Remove redundant cgroup_psi() when !CONFIG_CGROUPS
sched/psi: Remove unused parameter nbytes of psi_trigger_create()
sched/psi: Zero the memory of struct psi_group
Pull audit fix from Paul Moore:
"A single fix for a potential double-free on a fsnotify error path"
* tag 'audit-pr-20220823' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit:
audit: fix potential double free on error path from fsnotify_add_inode_mark
Pull file_remove_privs() fix from Christian Brauner:
"As part of Stefan's and Jens' work to add async buffered write
support to xfs we refactored file_remove_privs() and added
__file_remove_privs() to avoid calling __remove_privs() when
IOCB_NOWAIT is passed.
While debugging a recent performance regression report I found that
during review we missed that commit faf99b5635 ("fs: add
__remove_file_privs() with flags parameter") accidently changed
behavior when dentry_needs_remove_privs() returns zero.
Before the commit it would still call inode_has_no_xattr() setting
the S_NOSEC bit and thereby avoiding even calling into
dentry_needs_remove_privs() the next time this function is called.
After that commit inode_has_no_xattr() would only be called if
__remove_privs() had to be called.
Restore the old behavior. This is likely the cause of the performance
regression"
* tag 'fs.fixes.v6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping:
fs: __file_remove_privs(): restore call to inode_has_no_xattr()
Revert submission 2188970-db845c_mixed_build
Reason for revert: It breaks android-mainline
Reverted Changes:
I6cfb1ef19:ANDROID: Convert db845c to a mixed build.
I6680cb8ef:kleaf: Convert db845c to a mixed build.
I6cfb1ef19:ANDROID: Convert db845c to a mixed build.
Signed-off-by: Ulises Mendez Martinez <umendez@google.com>
Change-Id: I337800cc4483877587f0a25d1fde2dadc444a81e
This updates the vendor hook `android_vh_ufs_send_uic_command` due to
the function parameter changes from the upstream commit 35d11ec239
("scsi: ufs: ufshcd: Constify pointed data").
Fixes: 35d11ec239 ("scsi: ufs: ufshcd: Constify pointed data")
Signed-off-by: Will McVicker <willmcvicker@google.com>
Change-Id: I6d1559bf74982cdf0a4ef4b28618265ba40dbab4
Pull parisc fixes from Helge Deller:
"Some interesting background to the current patchset:
It turned out that the fldw instruction (which loads a 32-bit word
from memory into one half of a FP register) failed on unaligned
addresses and even trashed some other random FP register instead. It's
a trivial one-liner fix in the exception handler but this failure
dates back to the very beginnings of the parisc-port. It's strange
that it was never noticed before.
Another patch fixes an annoyance noticed by Randy Dunlap. Running
"make ARCH=parisc64 randconfig" always returned a 32-bit config,
although one would expect a 64-bit config. Masahiro Yamada suggested
to mimik sparc Kconfig code, which fixed the issue nicely. This
allowed to drop some compiler build checks too.
Third, it's possible to build an optimized 32-bit kernel for PA8X00
(64-bit) CPUs, which then wouldn't start on 32-bit-only (PA1.x)
machines. I've added a bootup check which prevents that and which
prints a message to the console. This can be tested with qemu, which
currently only supports 32-bit emulation.
The other patches are usual clean-up stuff like added return value
checks and typo fixes in comments.
Summary:
- Fix emulation of fldw instruction on unaligned addresses
- Fix "make ARCH=parisc64 randconfig" to return a 64-bit config
- Prevent boot if trying to boot a 32-bit kernel compiled for PA8X00
CPUs on 32-bit only machines
- ccio-dma: Handle kmalloc failure in ccio_init_resources()"
* tag 'parisc-for-6.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Add runtime check to prevent PA2.0 kernels on PA1.x machines
parisc: ccio-dma: Handle kmalloc failure in ccio_init_resources()
parisc: led: Move from strlcpy with unused retval to strscpy
parisc: ccio-dma: Fix typo in comment
Revert "parisc: Show error if wrong 32/64-bit compiler is being used"
parisc: Make CONFIG_64BIT available for ARCH=parisc64 only
parisc: Fix exception handler for fldw and fstw instructions
Pull misc fixes from Andrew Morton:
"Thirteen fixes, almost all for MM.
Seven of these are cc:stable and the remainder fix up the changes
which went into this -rc cycle"
* tag 'mm-hotfixes-stable-2022-08-22' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
kprobes: don't call disarm_kprobe() for disabled kprobes
mm/shmem: shmem_replace_page() remember NR_SHMEM
mm/shmem: tmpfs fallocate use file_modified()
mm/shmem: fix chattr fsflags support in tmpfs
mm/hugetlb: support write-faults in shared mappings
mm/hugetlb: fix hugetlb not supporting softdirty tracking
mm/uffd: reset write protection when unregister with wp-mode
mm/smaps: don't access young/dirty bit if pte unpresent
mm: add DEVICE_ZONE to FOR_ALL_ZONES
kernel/sys_ni: add compat entry for fadvise64_64
mm/gup: fix FOLL_FORCE COW security issue and remove FOLL_COW
Revert "zram: remove double compression logic"
get_maintainer: add Alan to .get_maintainer.ignore
Pull KUnit fixes from Shuah Khan:
"Fix for a mmc test and to load .kunit_test_suites section when
CONFIG_KUNIT=m, and not just when KUnit is built-in"
* tag 'linux-kselftest-kunit-fixes-6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest:
module: kunit: Load .kunit_test_suites section when CONFIG_KUNIT=m
mmc: sdhci-of-aspeed: test: Fix dependencies when KUNIT=m
Pull Kselftest fixes from Shuah Khan:
"Fixes to vm and sgx test builds"
* tag 'linux-kselftest-fixes-6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest:
selftests/vm: fix inability to build any vm tests
selftests/sgx: Ignore OpenSSL 3.0 deprecated functions warning
Steps on the way to 6.0-rc1
Resolves merge conflicts with:
include/ufs/ufshcd.h
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ifb6b6d3fefbce01620b120ccefd51acf252d72d5
In commit 2b4c206963 ("clk: sunxi: Limit legacy clocks to 32-bit ARM")
the CLK_SUNXI config symbol had the dependency properly fixed up, so we
no longer need to specify that we have this disabled, it's the default
for now. So remove it from the gki_defconfig file to fix the build up.
Fixes: 2b4c206963 ("clk: sunxi: Limit legacy clocks to 32-bit ARM")
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ib0b1fe3a716b8efa592d18b217cffedb27f6137d
Steps on the way to 6.0-rc1
Resolves merge conflict with:
include/linux/clk-provider.h
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ifff54041c5978afe50c4ad777dec9dba3955eb62
In commit 3158e39aa5 ("phy: qcom-qmp: switch to new split QMP PHY
driver") the qcom-qmp driver got split up into smaller drivers, so
update the BUILD.bazel file so that the build can continue to work
properly.
Fixes: 3158e39aa5 ("phy: qcom-qmp: switch to new split QMP PHY driver")
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I23da8f220c78a497d2a7d2406cbcca36c4637b6f
Signed-off-by: Will McVicker <willmcvicker@google.com>
In commit 1045a06724 ("remove CONFIG_ANDROID"), CONFIG_ANDROID was
removed, yet the xfrm networking code was doing some functionally
different things if this option was, or was not, enabled. Restore the
functionality by having the xfrm code check CONFIG_GKI_HACKS_TO_FIX
instead.
Fixes: 1045a06724 ("remove CONFIG_ANDROID")
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ib153d5ef8a6935f56e634bcac5afef5070ec9f51
In commit 1045a06724 ("remove CONFIG_ANDROID"), CONFIG_ANDROID was
removed, so also remove it from the gki_defconfig files to fix up the
build.
Fixes: 1045a06724 ("remove CONFIG_ANDROID")
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: If773c7903325f5b0c56f0815465eeefc4a2cbcca
In commit 1045a06724 ("remove CONFIG_ANDROID"), CONFIG_ANDROID is
removed, so fix up the CONFIG_ASHMEM build option to not require it to
be selected and built properly.
Fixes: 1045a06724 ("remove CONFIG_ANDROID")
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: If9cdf1350949cf98444c20d778d1ca1228a6cd6d
Audit_alloc_mark() assign pathname to audit_mark->path, on error path
from fsnotify_add_inode_mark(), fsnotify_put_mark will free memory
of audit_mark->path, but the caller of audit_alloc_mark will free
the pathname again, so there will be double free problem.
Fix this by resetting audit_mark->path to NULL pointer on error path
from fsnotify_add_inode_mark().
Cc: stable@vger.kernel.org
Fixes: 7b12932340 ("fsnotify: Add group pointer in fsnotify_init_mark()")
Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Pull NFS client fixes from Trond Myklebust:
"Stable fixes:
- NFS: Fix another fsync() issue after a server reboot
Bugfixes:
- NFS: unlink/rmdir shouldn't call d_delete() twice on ENOENT
- NFS: Fix missing unlock in nfs_unlink()
- Add sanity checking of the file type used by __nfs42_ssc_open
- Fix a case where we're failing to set task->tk_rpc_status
Cleanups:
- Remove the NFS_CONTEXT_RESEND_WRITES flag that got obsoleted by the
fsync() fix"
* tag 'nfs-for-5.20-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
SUNRPC: RPC level errors should set task->tk_rpc_status
NFSv4.2 fix problems with __nfs42_ssc_open
NFS: unlink/rmdir shouldn't call d_delete() twice on ENOENT
NFS: Cleanup to remove unused flag NFS_CONTEXT_RESEND_WRITES
NFS: Remove a bogus flag setting in pnfs_write_done_resend_to_mds
NFS: Fix another fsync() issue after a server reboot
NFS: Fix missing unlock in nfs_unlink()
Pull idmapping fixes from Christian Brauner:
- Since Seth joined as co-maintainer for idmapped mounts we decided to
use a shared git tree. Konstantin suggested we use vfs/idmapping.git
on kernel.org under the vfs/ namespace. So this updates the tree in
the maintainers file.
- Ensure that POSIX ACLs checking, getting, and setting works correctly
for filesystems mountable with a filesystem idmapping that want to
support idmapped mounts.
Since no filesystems mountable with an fs_idmapping do yet support
idmapped mounts there is no problem. But this could change in the
future, so add a check to refuse to create idmapped mounts when the
mounter is not privileged over the mount's idmapping.
- Check that caller is privileged over the idmapping that will be
attached to a mount.
Currently no FS_USERNS_MOUNT filesystems support idmapped mounts,
thus this is not a problem as only CAP_SYS_ADMIN in init_user_ns is
allowed to set up idmapped mounts. But this could change in the
future, so add a check to refuse to create idmapped mounts when the
mounter is not privileged over the mount's idmapping.
- Fix POSIX ACLs for ntfs3. While looking at our current POSIX ACL
handling in the context of some overlayfs work I went through a range
of other filesystems checking how they handle them currently and
encountered a few bugs in ntfs3.
I've sent this some time ago and the fixes haven't been picked up
even though the pull request for other ntfs3 fixes got sent after.
This should really be fixed as right now POSIX ACLs are broken in
certain circumstances for ntfs3.
* tag 'fs.idmapped.fixes.v6.0-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping:
ntfs: fix acl handling
fs: require CAP_SYS_ADMIN in target namespace for idmapped mounts
MAINTAINERS: update idmapping tree
acl: handle idmapped mounts for idmapped filesystems
Pull file locking fix from Jeff Layton:
"Just a single patch for a bugfix in the flock() codepath, introduced
by a patch that went in recently"
* tag 'filelock-v6.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux:
locks: Fix dropped call to ->fl_release_private()
Commit a0a12c3ed0 ("asm goto: eradicate CC_HAS_ASM_GOTO") eradicates
CC_HAS_ASM_GOTO, and in the process also causes the perf tool on x86 to
use asm_volatile_goto when compiling __GEN_RMWcc.
However, asm_volatile_goto is not declared in the perf tool headers,
which causes a compilation error:
In file included from tools/arch/x86/include/asm/atomic.h:7,
from tools/include/asm/atomic.h:6,
from tools/include/linux/atomic.h:5,
from tools/include/linux/refcount.h:41,
from tools/lib/perf/include/internal/cpumap.h:5,
from tools/perf/util/cpumap.h:7,
from tools/perf/util/env.h:7,
from tools/perf/util/header.h:12,
from pmu-events/pmu-events.c:9:
tools/arch/x86/include/asm/atomic.h: In function ‘atomic_dec_and_test’:
tools/arch/x86/include/asm/rmwcc.h:7:2: error: implicit declaration of function ‘asm_volatile_goto’ [-Werror=implicit-function-declaration]
asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
^~~~~~~~~~~~~~~~~
Define asm_volatile_goto in compiler_types.h if not declared, like the
main kernel header files do.
Fixes: a0a12c3ed0 ("asm goto: eradicate CC_HAS_ASM_GOTO")
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While looking at our current POSIX ACL handling in the context of some
overlayfs work I went through a range of other filesystems checking how they
handle them currently and encountered ntfs3.
The posic_acl_{from,to}_xattr() helpers always need to operate on the
filesystem idmapping. Since ntfs3 can only be mounted in the initial user
namespace the relevant idmapping is init_user_ns.
The posix_acl_{from,to}_xattr() helpers are concerned with translating between
the kernel internal struct posix_acl{_entry} and the uapi struct
posix_acl_xattr_{header,entry} and the kernel internal data structure is cached
filesystem wide.
Additional idmappings such as the caller's idmapping or the mount's idmapping
are handled higher up in the VFS. Individual filesystems usually do not need to
concern themselves with these.
The posix_acl_valid() helper is concerned with checking whether the values in
the kernel internal struct posix_acl can be represented in the filesystem's
idmapping. IOW, if they can be written to disk. So this helper too needs to
take the filesystem's idmapping.
Fixes: be71b5cba2 ("fs/ntfs3: Add attrib operations")
Cc: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Cc: ntfs3@lists.linux.dev
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
If a 32-bit kernel was compiled for PA2.0 CPUs, it won't be able to run
on machines with PA1.x CPUs. Add a check and bail out early if a PA1.x
machine is detected.
Signed-off-by: Helge Deller <deller@gmx.de>
As the possible failure of the kmalloc(), it should be better
to fix this error path, check and return '-ENOMEM' error code.
Signed-off-by: Li Qiong <liqiong@nfschina.com>
Signed-off-by: Helge Deller <deller@gmx.de>
The double `was' is duplicated in the comment, remove one.
Signed-off-by: Jason Wang <wangborong@cdjrlc.com>
Signed-off-by: Helge Deller <deller@gmx.de>
This reverts commit b160628e9e.
There is no need any longer to have this sanity check, because the
previous commit ("parisc: Make CONFIG_64BIT available for ARCH=parisc64
only") prevents that CONFIG_64BIT is set if ARCH==parisc.
Signed-off-by: Helge Deller <deller@gmx.de>
With this patch the ARCH= parameter decides if the
CONFIG_64BIT option will be set or not. This means, the
ARCH= parameter will give:
ARCH=parisc -> 32-bit kernel
ARCH=parisc64 -> 64-bit kernel
This simplifies the usage of the other config options like
randconfig, allmodconfig and allyesconfig a lot and produces
the output which is expected for parisc64 (64-bit) vs. parisc (32-bit).
Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Helge Deller <deller@gmx.de>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Cc: <stable@vger.kernel.org> # 5.15+
