Pull keys update from Jarkko Sakkinen:
"This contains only three fixes"
* tag 'keys-next-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd:
keys: Fix grammar and formatting in 'struct key_type' comments
keys: Replace deprecated strncpy in ecryptfs_fill_auth_tok
keys: Remove redundant less-than-zero checks
This patch adds a new ipe_bprm_creds_for_exec() hook that integrates
with the AT_EXECVE_CHECK mechanism. To enable script enforcement,
interpreters need to incorporate the AT_EXECVE_CHECK flag when
calling execveat() on script files before execution.
When a userspace interpreter calls execveat() with the AT_EXECVE_CHECK
flag, this hook triggers IPE policy evaluation on the script file. The
hook only triggers IPE when bprm->is_check is true, ensuring it's
being called from an AT_EXECVE_CHECK context. It then builds an
evaluation context for an IPE_OP_EXEC operation and invokes IPE policy.
The kernel returns the policy decision to the interpreter, which can
then decide whether to proceed with script execution.
This extends IPE enforcement to indirectly executed scripts, permitting
trusted scripts to execute while denying untrusted ones.
Signed-off-by: Yanzhu Huang <yanzhuhuang@linux.microsoft.com>
Signed-off-by: Fan Wu <wufan@kernel.org>
Looks like it got added by mistake, perhaps editor auto-completion
artifact. Drop it.
No functional changes.
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Fan Wu <wufan@kernel.org>
Pull directory locking updates from Christian Brauner:
"This contains the work to add centralized APIs for directory locking
operations.
This series is part of a larger effort to change directory operation
locking to allow multiple concurrent operations in a directory. The
ultimate goal is to lock the target dentry(s) rather than the whole
parent directory.
To help with changing the locking protocol, this series centralizes
locking and lookup in new helper functions. The helpers establish a
pattern where it is the dentry that is being locked and unlocked
(currently the lock is held on dentry->d_parent->d_inode, but that can
change in the future).
This also changes vfs_mkdir() to unlock the parent on failure, as well
as dput()ing the dentry. This allows end_creating() to only require
the target dentry (which may be IS_ERR() after vfs_mkdir()), not the
parent"
* tag 'vfs-6.19-rc1.directory.locking' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
nfsd: fix end_creating() conversion
VFS: introduce end_creating_keep()
VFS: change vfs_mkdir() to unlock on failure.
ecryptfs: use new start_creating/start_removing APIs
Add start_renaming_two_dentries()
VFS/ovl/smb: introduce start_renaming_dentry()
VFS/nfsd/ovl: introduce start_renaming() and end_renaming()
VFS: add start_creating_killable() and start_removing_killable()
VFS: introduce start_removing_dentry()
smb/server: use end_removing_noperm for for target of smb2_create_link()
VFS: introduce start_creating_noperm() and start_removing_noperm()
VFS/nfsd/cachefiles/ovl: introduce start_removing() and end_removing()
VFS/nfsd/cachefiles/ovl: add start_creating() and end_creating()
VFS: tidy up do_unlinkat()
VFS: introduce start_dirop() and end_dirop()
debugfs: rename end_creating() to debugfs_end_creating()
Pull cred guard updates from Christian Brauner:
"This contains substantial credential infrastructure improvements
adding guard-based credential management that simplifies code and
eliminates manual reference counting in many subsystems.
Features:
- Kernel Credential Guards
Add with_kernel_creds() and scoped_with_kernel_creds() guards that
allow using the kernel credentials without allocating and copying
them. This was requested by Linus after seeing repeated
prepare_kernel_creds() calls that duplicate the kernel credentials
only to drop them again later.
The new guards completely avoid the allocation and never expose the
temporary variable to hold the kernel credentials anywhere in
callers.
- Generic Credential Guards
Add scoped_with_creds() guards for the common override_creds() and
revert_creds() pattern. This builds on earlier work that made
override_creds()/revert_creds() completely reference count free.
- Prepare Credential Guards
Add prepare credential guards for the more complex pattern of
preparing a new set of credentials and overriding the current
credentials with them:
- prepare_creds()
- modify new creds
- override_creds()
- revert_creds()
- put_cred()
Cleanups:
- Make init_cred static since it should not be directly accessed
- Add kernel_cred() helper to properly access the kernel credentials
- Fix scoped_class() macro that was introduced two cycles ago
- coredump: split out do_coredump() from vfs_coredump() for cleaner
credential handling
- coredump: move revert_cred() before coredump_cleanup()
- coredump: mark struct mm_struct as const
- coredump: pass struct linux_binfmt as const
- sev-dev: use guard for path"
* tag 'kernel-6.19-rc1.cred' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (36 commits)
trace: use override credential guard
trace: use prepare credential guard
coredump: use override credential guard
coredump: use prepare credential guard
coredump: split out do_coredump() from vfs_coredump()
coredump: mark struct mm_struct as const
coredump: pass struct linux_binfmt as const
coredump: move revert_cred() before coredump_cleanup()
sev-dev: use override credential guards
sev-dev: use prepare credential guard
sev-dev: use guard for path
cred: add prepare credential guard
net/dns_resolver: use credential guards in dns_query()
cgroup: use credential guards in cgroup_attach_permissions()
act: use credential guards in acct_write_process()
smb: use credential guards in cifs_get_spnego_key()
nfs: use credential guards in nfs_idmap_get_key()
nfs: use credential guards in nfs_local_call_write()
nfs: use credential guards in nfs_local_call_read()
erofs: use credential guards
...
Pull vfs inode updates from Christian Brauner:
"Features:
- Hide inode->i_state behind accessors. Open-coded accesses prevent
asserting they are done correctly. One obvious aspect is locking,
but significantly more can be checked. For example it can be
detected when the code is clearing flags which are already missing,
or is setting flags when it is illegal (e.g., I_FREEING when
->i_count > 0)
- Provide accessors for ->i_state, converts all filesystems using
coccinelle and manual conversions (btrfs, ceph, smb, f2fs, gfs2,
overlayfs, nilfs2, xfs), and makes plain ->i_state access fail to
compile
- Rework I_NEW handling to operate without fences, simplifying the
code after the accessor infrastructure is in place
Cleanups:
- Move wait_on_inode() from writeback.h to fs.h
- Spell out fenced ->i_state accesses with explicit smp_wmb/smp_rmb
for clarity
- Cosmetic fixes to LRU handling
- Push list presence check into inode_io_list_del()
- Touch up predicts in __d_lookup_rcu()
- ocfs2: retire ocfs2_drop_inode() and I_WILL_FREE usage
- Assert on ->i_count in iput_final()
- Assert ->i_lock held in __iget()
Fixes:
- Add missing fences to I_NEW handling"
* tag 'vfs-6.19-rc1.inode' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (22 commits)
dcache: touch up predicts in __d_lookup_rcu()
fs: push list presence check into inode_io_list_del()
fs: cosmetic fixes to lru handling
fs: rework I_NEW handling to operate without fences
fs: make plain ->i_state access fail to compile
xfs: use the new ->i_state accessors
nilfs2: use the new ->i_state accessors
overlayfs: use the new ->i_state accessors
gfs2: use the new ->i_state accessors
f2fs: use the new ->i_state accessors
smb: use the new ->i_state accessors
ceph: use the new ->i_state accessors
btrfs: use the new ->i_state accessors
Manual conversion to use ->i_state accessors of all places not covered by coccinelle
Coccinelle-based conversion to use ->i_state accessors
fs: provide accessors for ->i_state
fs: spell out fenced ->i_state accesses with explicit smp_wmb/smp_rmb
fs: move wait_on_inode() from writeback.h to fs.h
fs: add missing fences to I_NEW handling
ocfs2: retire ocfs2_drop_inode() and I_WILL_FREE usage
...
'tpm2_load_cmd' allocates a tempoary blob indirectly via 'tpm2_key_decode'
but it is not freed in the failure paths. Address this by wrapping the blob
into with a cleanup helper.
Cc: stable@vger.kernel.org # v5.13+
Fixes: f221974525 ("security: keys: trusted: use ASN.1 TPM2 key format for the blobs")
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
'trusted_tpm2' duplicates 'tpm2_hash_map' originally part of the TPN
driver, which is suboptimal.
Implement and export `tpm2_find_hash_alg()` in the driver, and substitute
the redundant code in 'trusted_tpm2' with a call to the new function.
Reviewed-by: Jonathan McDowell <noodles@meta.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Disconnected files or directories can appear when they are visible and
opened from a bind mount, but have been renamed or moved from the source
of the bind mount in a way that makes them inaccessible from the mount
point (i.e. out of scope).
Previously, access rights tied to files or directories opened through a
disconnected directory were collected by walking the related hierarchy
down to the root of the filesystem, without taking into account the
mount point because it couldn't be found. This could lead to
inconsistent access results, potential access right widening, and
hard-to-debug renames, especially since such paths cannot be printed.
For a sandboxed task to create a disconnected directory, it needs to
have write access (i.e. FS_MAKE_REG, FS_REMOVE_FILE, and FS_REFER) to
the underlying source of the bind mount, and read access to the related
mount point. Because a sandboxed task cannot acquire more access
rights than those defined by its Landlock domain, this could lead to
inconsistent access rights due to missing permissions that should be
inherited from the mount point hierarchy, while inheriting permissions
from the filesystem hierarchy hidden by this mount point instead.
Landlock now handles files and directories opened from disconnected
directories by taking into account the filesystem hierarchy when the
mount point is not found in the hierarchy walk, and also always taking
into account the mount point from which these disconnected directories
were opened. This ensures that a rename is not allowed if it would
widen access rights [1].
The rationale is that, even if disconnected hierarchies might not be
visible or accessible to a sandboxed task, relying on the collected
access rights from them improves the guarantee that access rights will
not be widened during a rename because of the access right comparison
between the source and the destination (see LANDLOCK_ACCESS_FS_REFER).
It may look like this would grant more access on disconnected files and
directories, but the security policies are always enforced for all the
evaluated hierarchies. This new behavior should be less surprising to
users and safer from an access control perspective.
Remove a wrong WARN_ON_ONCE() canary in collect_domain_accesses() and
fix the related comment.
Because opened files have their access rights stored in the related file
security properties, there is no impact for disconnected or unlinked
files.
Cc: Christian Brauner <brauner@kernel.org>
Cc: Günther Noack <gnoack@google.com>
Cc: Song Liu <song@kernel.org>
Reported-by: Tingmao Wang <m@maowtm.org>
Closes: https://lore.kernel.org/r/027d5190-b37a-40a8-84e9-4ccbc352bcdf@maowtm.org
Closes: https://lore.kernel.org/r/09b24128f86973a6022e6aa8338945fcfb9a33e4.1749925391.git.m@maowtm.org
Fixes: b91c3e4ea7 ("landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER")
Fixes: cb2c7d1a17 ("landlock: Support filesystem access-control")
Link: https://lore.kernel.org/r/b0f46246-f2c5-42ca-93ce-0d629702a987@maowtm.org [1]
Reviewed-by: Tingmao Wang <m@maowtm.org>
Link: https://lore.kernel.org/r/20251128172200.760753-2-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
strncpy() is deprecated for NUL-terminated destination buffers; use
strscpy_pad() instead to retain the NUL-padding behavior of strncpy().
The destination buffer is initialized using kzalloc() with a 'signature'
size of ECRYPTFS_PASSWORD_SIG_SIZE + 1. strncpy() then copies up to
ECRYPTFS_PASSWORD_SIG_SIZE bytes from 'key_desc', NUL-padding any
remaining bytes if needed, but expects the last byte to be zero.
strscpy_pad() also copies the source string to 'signature', and NUL-pads
the destination buffer if needed, but ensures it's always NUL-terminated
without relying on it being zero-initialized.
strscpy_pad() automatically determines the size of the fixed-length
destination buffer via sizeof() when the optional size argument is
omitted, making an explicit size unnecessary.
In encrypted_init(), the source string 'key_desc' is validated by
valid_ecryptfs_desc() before calling ecryptfs_fill_auth_tok(), and is
therefore NUL-terminated and satisfies the __must_be_cstr() requirement
of strscpy_pad().
Link: https://github.com/KSPP/linux/issues/90
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
The local variables 'size_t datalen' are unsigned and cannot be less
than zero. Remove the redundant conditions.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Pull selinux fixes from Paul Moore:
"Three SELinux patches for v6.18 to fix issues around accessing the
per-task decision cache that we introduced in v6.16 to help reduce
SELinux overhead on path walks. The problem was that despite the cache
being located in the SELinux "task_security_struct", the parent struct
wasn't actually tied to the task, it was tied to a cred.
Historically SELinux did locate the task_security_struct in the
task_struct's security blob, but it was later relocated to the cred
struct when the cred work happened, as it made the most sense at the
time.
Unfortunately we never did the task_security_struct to
cred_security_struct rename work (avoid code churn maybe? who knows)
because it didn't really matter at the time. However, it suddenly
became a problem when we added a per-task cache to a per-cred object
and didn't notice because of the old, no-longer-correct struct naming.
Thanks to KCSAN for flagging this, as the silly humans running things
forgot that the task_security_struct was a big lie.
This contains three patches, only one of which actually fixes the
problem described above and moves the SELinux decision cache from the
per-cred struct to a newly (re)created per-task struct.
The other two patches, which form the bulk of the diffstat, take care
of the associated renaming tasks so we can hopefully avoid making the
same stupid mistake in the future.
For the record, I did contemplate sending just a fix for the cache,
leaving the renaming patches for the upcoming merge window, but the
type/variable naming ended up being pretty awful and would have made
v6.18 an outlier stuck between the "old" names and the "new" names in
v6.19. The renaming patches are also fairly mechanical/trivial and
shouldn't pose much risk despite their size.
TLDR; naming things may be hard, but if you mess it up bad things
happen"
* tag 'selinux-pr-20251121' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux:
selinux: rename the cred_security_struct variables to "crsec"
selinux: move avdcache to per-task security struct
selinux: rename task_security_struct to cred_security_struct
In ima_match_rules(), if ima_filter_rule_match() returns -ENOENT due to
the rule being NULL, the function incorrectly skips the 'if (!rc)' check
and sets 'result = true'. The LSM rule is considered a match, causing
extra files to be measured by IMA.
This issue can be reproduced in the following scenario:
After unloading the SELinux policy module via 'semodule -d', if an IMA
measurement is triggered before ima_lsm_rules is updated,
in ima_match_rules(), the first call to ima_filter_rule_match() returns
-ESTALE. This causes the code to enter the 'if (rc == -ESTALE &&
!rule_reinitialized)' block, perform ima_lsm_copy_rule() and retry. In
ima_lsm_copy_rule(), since the SELinux module has been removed, the rule
becomes NULL, and the second call to ima_filter_rule_match() returns
-ENOENT. This bypasses the 'if (!rc)' check and results in a false match.
Call trace:
selinux_audit_rule_match+0x310/0x3b8
security_audit_rule_match+0x60/0xa0
ima_match_rules+0x2e4/0x4a0
ima_match_policy+0x9c/0x1e8
ima_get_action+0x48/0x60
process_measurement+0xf8/0xa98
ima_bprm_check+0x98/0xd8
security_bprm_check+0x5c/0x78
search_binary_handler+0x6c/0x318
exec_binprm+0x58/0x1b8
bprm_execve+0xb8/0x130
do_execveat_common.isra.0+0x1a8/0x258
__arm64_sys_execve+0x48/0x68
invoke_syscall+0x50/0x128
el0_svc_common.constprop.0+0xc8/0xf0
do_el0_svc+0x24/0x38
el0_svc+0x44/0x200
el0t_64_sync_handler+0x100/0x130
el0t_64_sync+0x3c8/0x3d0
Fix this by changing 'if (!rc)' to 'if (rc <= 0)' to ensure that error
codes like -ENOENT do not bypass the check and accidentally result in a
successful match.
Fixes: 4af4662fa4 ("integrity: IMA policy")
Signed-off-by: Zhao Yipeng <zhaoyipeng5@huawei.com>
Reviewed-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Along with the renaming from task_security_struct to cred_security_struct,
rename the local variables to "crsec" from "tsec". This both fits with
existing conventions and helps distinguish between task and cred related
variables.
No functional changes.
Acked-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
The avdcache is meant to be per-task; move it to a new
task_security_struct that is duplicated per-task.
Cc: stable@vger.kernel.org
Fixes: 5d7ddc59b3 ("selinux: reduce path walk overhead")
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
[PM: line length fixes]
Signed-off-by: Paul Moore <paul@paul-moore.com>
Before Linux had cred structures, the SELinux task_security_struct was
per-task and although the structure was switched to being per-cred
long ago, the name was never updated. This change renames it to
cred_security_struct to avoid confusion and pave the way for the
introduction of an actual per-task security structure for SELinux. No
functional change.
Cc: stable@vger.kernel.org
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
We need to directly allocate the cred's LSM state for the initial task
when we initialize the LSM framework. Unfortunately, this results in a
RCU related type mismatch, use the unrcu_pointer() macro to handle this
a bit more elegantly.
The explicit type casting still remains as we need to work around the
constification of current->cred in this particular case.
Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Currently, when in-kernel module decompression (CONFIG_MODULE_DECOMPRESS)
is enabled, IMA has no way to verify the appended module signature as it
can't decompress the module.
Define a new kernel_read_file_id enumerate READING_MODULE_COMPRESSED so
IMA can calculate the compressed kernel module data hash on
READING_MODULE_COMPRESSED and defer appraising/measuring it until on
READING_MODULE when the module has been decompressed.
Before enabling in-kernel module decompression, a kernel module in
initramfs can still be loaded with ima_policy=secure_boot. So adjust the
kernel module rule in secure_boot policy to allow either an IMA
signature OR an appended signature i.e. to use
"appraise func=MODULE_CHECK appraise_type=imasig|modsig".
Reported-by: Karel Srot <ksrot@redhat.com>
Suggested-by: Mimi Zohar <zohar@linux.ibm.com>
Suggested-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Coiby Xu <coxu@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Split most of the rootid_owns_currentns() functionality
into a more generic rootid_owns_ns() function which
will be easier to write tests for.
Rename the functions and variables to make clear that
the ids being tested could be any uid.
Signed-off-by: Serge Hallyn <serge@hallyn.com>
CC: Ryan Foster <foster.ryan.r@gmail.com>
CC: Christian Brauner <brauner@kernel.org>
---
v2: change the function parameter documentation to mollify the bot.
At this point there are very few call chains that might lead to
d_make_discardable() on a dentry that hadn't been made persistent:
calls of simple_unlink() and simple_rmdir() in configfs and
apparmorfs.
Both filesystems do pin (part of) their contents in dcache, but
they are currently playing very unusual games with that. Converting
them to more usual patterns might be possible, but it's definitely
going to be a long series of changes in both cases.
For now the easiest solution is to have both stop using simple_unlink()
and simple_rmdir() - that allows to make d_make_discardable() warn
when given a non-persistent dentry.
Rather than giving them full-blown private copies (with calls of
d_make_discardable() replaced with dput()), let's pull the parts of
simple_unlink() and simple_rmdir() that deal with timestamps and link
counts into separate helpers (__simple_unlink() and __simple_rmdir()
resp.) and have those used by configfs and apparmorfs.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
securityfs uses simple_recursive_removal(), but does not bother to mark
dentries persistent. This is the only place where it still happens; get
rid of that irregularity.
* use simple_{start,done}_creating() and d_make_persitent(); kill_litter_super()
use was already gone, since we empty the filesystem instance before it gets
shut down.
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Tree has invariant part + two subtrees that get replaced upon each
policy load. Invariant parts stay for the lifetime of filesystem,
these two subdirs - from policy load to policy load (serialized
on lock_rename(root, ...)).
All object creations are via d_alloc_name()+d_add() inside selinuxfs,
all removals are via simple_recursive_removal().
Turn those d_add() into d_make_persistent()+dput() and that's mostly it.
Acked-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
allocating dentry after the inode has been set up reduces the amount
of boilerplate - "attach this inode under that name and this parent
or drop inode in case of failure" simplifies quite a few places.
Acked-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Don't bother to store the dentry of /policy_capabilities - it belongs
to invariant part of tree and we only use it to populate that directory,
so there's no reason to keep it around afterwards.
Same situation as with /avc, /ss, etc. There are two directories that
get replaced on policy load - /class and /booleans. These we need to
stash (and update the pointers on policy reload); /policy_capabilities
is not in the same boat.
Acked-by: Paul Moore <paul@paul-moore.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Entirely static tree populated by simple_fill_super(). Can use
kill_anon_super() as-is.
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
These are guaranteed to be empty by the time they are shut down;
both are single-instance and there is an internal mount maintained
for as long as there is any contents.
Both have that internal mount pinned by every object in root.
In other words, kill_litter_super() boils down to kill_anon_super()
for those.
Reviewed-by: Joel Becker <jlbec@evilplan.org>
Acked-by: Paul Moore <paul@paul-moore> (LSM)
Acked-by: Andreas Hindborg <a.hindborg@kernel.org> (configfs)
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
A few callers want to lock for a rename and already have both dentries.
Also debugfs does want to perform a lookup but doesn't want permission
checking, so start_renaming_dentry() cannot be used.
This patch introduces start_renaming_two_dentries() which is given both
dentries. debugfs performs one lookup itself. As it will only continue
with a negative dentry and as those cannot be renamed or unlinked, it is
safe to do the lookup before getting the rename locks.
overlayfs uses start_renaming_two_dentries() in three places and selinux
uses it twice in sel_make_policy_nodes().
In sel_make_policy_nodes() we now lock for rename twice instead of just
once so the combined operation is no longer atomic w.r.t the parent
directory locks. As selinux_state.policy_mutex is held across the whole
operation this does not open up any interesting races.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/20251113002050.676694-13-neilb@ownmail.net
Signed-off-by: Christian Brauner <brauner@kernel.org>
start_removing_dentry() is similar to start_removing() but instead of
providing a name for lookup, the target dentry is given.
start_removing_dentry() checks that the dentry is still hashed and in
the parent, and if so it locks and increases the refcount so that
end_removing() can be used to finish the operation.
This is used in cachefiles, overlayfs, smb/server, and apparmor.
There will be other users including ecryptfs.
As start_removing_dentry() takes an extra reference to the dentry (to be
put by end_removing()), there is no need to explicitly take an extra
reference to stop d_delete() from using dentry_unlink_inode() to negate
the dentry - as in cachefiles_delete_object(), and ksmbd_vfs_unlink().
cachefiles_bury_object() now gets an extra ref to the victim, which is
drops. As it includes the needed end_removing() calls, the caller
doesn't need them.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/20251113002050.676694-9-neilb@ownmail.net
Signed-off-by: Christian Brauner <brauner@kernel.org>
Replace set_access(), set_majmin(), and type_to_char() with new helpers
seq_putaccess(), seq_puttype(), and seq_putversion() that write directly
to 'seq_file'.
Simplify devcgroup_seq_show() by hard-coding "a *:* rwm", and use the
new seq_put* helper functions to list the exceptions otherwise.
This allows us to remove the intermediate string buffers while
maintaining the same functionality, including wildcard handling.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
On mobile device high-load situations, permission check can happen
more than 90,000/s (8 core system). With default 512 cache nodes
configuration, avc cache miss happens more often and occasionally
leads to long time (>2ms) irqs off on both big and little cores,
which decreases system real-time capability.
An actual call stack is as follows:
=> avc_compute_av
=> avc_perm_nonode
=> avc_has_perm_noaudit
=> selinux_capable
=> security_capable
=> capable
=> __sched_setscheduler
=> do_sched_setscheduler
=> __arm64_sys_sched_setscheduler
=> invoke_syscall
=> el0_svc_common
=> do_el0_svc
=> el0_svc
=> el0t_64_sync_handler
=> el0t_64_sync
Although we can expand avc nodes through /sys/fs/selinux/cache_threshold
to mitigate long time irqs off, hash conflicts make the bucket average
length longer because of the fixed size of cache slots, leading to
avc_search_node() latency increase.
So introduce a new config to make avc cache slot size also configurable,
and with fine tuning, we can mitigate long time irqs off with slightly
avc_search_node() performance regression.
Theoretically, the main overhead is memory consumption.
Signed-off-by: Hongru Zhang <zhanghongru@xiaomi.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Instead of passing pkey_info into dump_options by value, using a
pointer instead.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Prior to this change, no security hooks were called at the creation of a
memfd file. It means that, for SELinux as an example, it will receive
the default type of the filesystem that backs the in-memory inode. In
most cases, that would be tmpfs, but if MFD_HUGETLB is passed, it will
be hugetlbfs. Both can be considered implementation details of memfd.
It also means that it is not possible to differentiate between a file
coming from memfd_create and a file coming from a standard tmpfs mount
point.
Additionally, no permission is validated at creation, which differs from
the similar memfd_secret syscall.
Call security_inode_init_security_anon during creation. This ensures
that the file is setup similarly to other anonymous inodes. On SELinux,
it means that the file will receive the security context of its task.
The ability to limit fexecve on memfd has been of interest to avoid
potential pitfalls where /proc/self/exe or similar would be executed
[1][2]. Reuse the "execute_no_trans" and "entrypoint" access vectors,
similarly to the file class. These access vectors may not make sense for
the existing "anon_inode" class. Therefore, define and assign a new
class "memfd_file" to support such access vectors.
Guard these changes behind a new policy capability named "memfd_class".
[1] https://crbug.com/1305267
[2] https://lore.kernel.org/lkml/20221215001205.51969-1-jeffxu@google.com/
Signed-off-by: Thiébaud Weksteen <tweek@google.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
[PM: subj tweak]
Signed-off-by: Paul Moore <paul@paul-moore.com>
The LSM framework itself registers a small number of initcalls, this
patch converts these initcalls into the new initcall mechanism.
Reviewed-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: John Johansen <john.johhansen@canonical.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
SELinux currently has a number of initcalls so we've created a new
function, selinux_initcall(), which wraps all of these initcalls so
that we have a single initcall function that can be registered with the
LSM framework.
Signed-off-by: Paul Moore <paul@paul-moore.com>
This patch converts IMA and EVM to use the LSM frameworks's initcall
mechanism. It moved the integrity_fs_init() call to ima_fs_init() and
evm_init_secfs(), to work around the fact that there is no "integrity" LSM,
and introduced integrity_fs_fini() to remove the integrity directory, if
empty. Both integrity_fs_init() and integrity_fs_fini() support the
scenario of being called by both the IMA and EVM LSMs.
This patch does not touch any of the platform certificate code that
lives under the security/integrity/platform_certs directory as the
IMA/EVM developers would prefer to address that in a future patchset.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
[PM: adjust description as discussed over email]
Signed-off-by: Paul Moore <paul@paul-moore.com>
As the LSM framework only supports one LSM initcall callback for each
initcall type, the init_smk_fs() and smack_nf_ip_init() functions were
wrapped with a new function, smack_initcall() that is registered with
the LSM framework.
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: John Johansen <john.johhansen@canonical.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
