Pull integrity updates from James Morris:
"This contains a mixture of bug fixes, code cleanup, and new
functionality. Of note is the integrity cache locking fix, file change
detection, and support for a new EVM portable and immutable signature
type.
The re-introduction of the integrity cache lock (iint) fixes the
problem of attempting to take the i_rwsem shared a second time, when
it was previously taken exclusively. Defining atomic flags resolves
the original iint/i_rwsem circular locking - accessing the file data
vs. modifying the file metadata. Although it fixes the O_DIRECT
problem as well, a subsequent patch is needed to remove the explicit
O_DIRECT prevention.
For performance reasons, detecting when a file has changed and needs
to be re-measured, re-appraised, and/or re-audited, was limited to
after the last writer has closed, and only if the file data has
changed. Detecting file change is based on i_version. For filesystems
that do not support i_version, remote filesystems, or userspace
filesystems, the file was measured, appraised and/or audited once and
never re-evaluated. Now local filesystems, which do not support
i_version or are not mounted with the i_version option, assume the
file has changed and are required to re-evaluate the file. This change
does not address detecting file change on remote or userspace
filesystems.
Unlike file data signatures, which can be included and distributed in
software packages (eg. rpm, deb), the existing EVM signature, which
protects the file metadata, could not be included in software
packages, as it includes file system specific information (eg. i_ino,
possibly the UUID). This pull request defines a new EVM portable and
immutable file metadata signature format, which can be included in
software packages"
* 'next-integrity' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
ima/policy: fix parsing of fsuuid
ima: Use i_version only when filesystem supports it
integrity: remove unneeded initializations in integrity_iint_cache entries
ima: log message to module appraisal error
ima: pass filename to ima_rdwr_violation_check()
ima: Fix line continuation format
ima: support new "hash" and "dont_hash" policy actions
ima: re-introduce own integrity cache lock
EVM: Add support for portable signature format
EVM: Allow userland to permit modification of EVM-protected metadata
ima: relax requiring a file signature for new files with zero length
Pull poll annotations from Al Viro:
"This introduces a __bitwise type for POLL### bitmap, and propagates
the annotations through the tree. Most of that stuff is as simple as
'make ->poll() instances return __poll_t and do the same to local
variables used to hold the future return value'.
Some of the obvious brainos found in process are fixed (e.g. POLLIN
misspelled as POLL_IN). At that point the amount of sparse warnings is
low and most of them are for genuine bugs - e.g. ->poll() instance
deciding to return -EINVAL instead of a bitmap. I hadn't touched those
in this series - it's large enough as it is.
Another problem it has caught was eventpoll() ABI mess; select.c and
eventpoll.c assumed that corresponding POLL### and EPOLL### were
equal. That's true for some, but not all of them - EPOLL### are
arch-independent, but POLL### are not.
The last commit in this series separates userland POLL### values from
the (now arch-independent) kernel-side ones, converting between them
in the few places where they are copied to/from userland. AFAICS, this
is the least disruptive fix preserving poll(2) ABI and making epoll()
work on all architectures.
As it is, it's simply broken on sparc - try to give it EPOLLWRNORM and
it will trigger only on what would've triggered EPOLLWRBAND on other
architectures. EPOLLWRBAND and EPOLLRDHUP, OTOH, are never triggered
at all on sparc. With this patch they should work consistently on all
architectures"
* 'misc.poll' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (37 commits)
make kernel-side POLL... arch-independent
eventpoll: no need to mask the result of epi_item_poll() again
eventpoll: constify struct epoll_event pointers
debugging printk in sg_poll() uses %x to print POLL... bitmap
annotate poll(2) guts
9p: untangle ->poll() mess
->si_band gets POLL... bitmap stored into a user-visible long field
ring_buffer_poll_wait() return value used as return value of ->poll()
the rest of drivers/*: annotate ->poll() instances
media: annotate ->poll() instances
fs: annotate ->poll() instances
ipc, kernel, mm: annotate ->poll() instances
net: annotate ->poll() instances
apparmor: annotate ->poll() instances
tomoyo: annotate ->poll() instances
sound: annotate ->poll() instances
acpi: annotate ->poll() instances
crypto: annotate ->poll() instances
block: annotate ->poll() instances
x86: annotate ->poll() instances
...
Pull RCU updates from Ingo Molnar:
"The main RCU changes in this cycle were:
- Updates to use cond_resched() instead of cond_resched_rcu_qs()
where feasible (currently everywhere except in kernel/rcu and in
kernel/torture.c). Also a couple of fixes to avoid sending IPIs to
offline CPUs.
- Updates to simplify RCU's dyntick-idle handling.
- Updates to remove almost all uses of smp_read_barrier_depends() and
read_barrier_depends().
- Torture-test updates.
- Miscellaneous fixes"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
torture: Save a line in stutter_wait(): while -> for
torture: Eliminate torture_runnable and perf_runnable
torture: Make stutter less vulnerable to compilers and races
locking/locktorture: Fix num reader/writer corner cases
locking/locktorture: Fix rwsem reader_delay
torture: Place all torture-test modules in one MAINTAINERS group
rcutorture/kvm-build.sh: Skip build directory check
rcutorture: Simplify functions.sh include path
rcutorture: Simplify logging
rcutorture/kvm-recheck-*: Improve result directory readability check
rcutorture/kvm.sh: Support execution from any directory
rcutorture/kvm.sh: Use consistent help text for --qemu-args
rcutorture/kvm.sh: Remove unused variable, `alldone`
rcutorture: Remove unused script, config2frag.sh
rcutorture/configinit: Fix build directory error message
rcutorture: Preempt RCU-preempt readers more vigorously
torture: Reduce #ifdefs for preempt_schedule()
rcu: Remove have_rcu_nocb_mask from tree_plugin.h
rcu: Add comment giving debug strategy for double call_rcu()
tracing, rcu: Hide trace event rcu_nocb_wake when not used
...
-----BEGIN PGP SIGNATURE-----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=iihN
-----END PGP SIGNATURE-----
Merge tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux
Pull inode->i_version rework from Jeff Layton:
"This pile of patches is a rework of the inode->i_version field. We
have traditionally incremented that field on every inode data or
metadata change. Typically this increment needs to be logged on disk
even when nothing else has changed, which is rather expensive.
It turns out though that none of the consumers of that field actually
require this behavior. The only real requirement for all of them is
that it be different iff the inode has changed since the last time the
field was checked.
Given that, we can optimize away most of the i_version increments and
avoid dirtying inode metadata when the only change is to the i_version
and no one is querying it. Queries of the i_version field are rather
rare, so we can help write performance under many common workloads.
This patch series converts existing accesses of the i_version field to
a new API, and then converts all of the in-kernel filesystems to use
it. The last patch in the series then converts the backend
implementation to a scheme that optimizes away a large portion of the
metadata updates when no one is looking at it.
In my own testing this series significantly helps performance with
small I/O sizes. I also got this email for Christmas this year from
the kernel test robot (a 244% r/w bandwidth improvement with XFS over
DAX, with 4k writes):
https://lkml.org/lkml/2017/12/25/8
A few of the earlier patches in this pile are also flowing to you via
other trees (mm, integrity, and nfsd trees in particular)".
* tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux: (22 commits)
fs: handle inode->i_version more efficiently
btrfs: only dirty the inode in btrfs_update_time if something was changed
xfs: avoid setting XFS_ILOG_CORE if i_version doesn't need incrementing
fs: only set S_VERSION when updating times if necessary
IMA: switch IMA over to new i_version API
xfs: convert to new i_version API
ufs: use new i_version API
ocfs2: convert to new i_version API
nfsd: convert to new i_version API
nfs: convert to new i_version API
ext4: convert to new i_version API
ext2: convert to new i_version API
exofs: switch to new i_version API
btrfs: convert to new i_version API
afs: convert to new i_version API
affs: convert to new i_version API
fat: convert to new i_version API
fs: don't take the i_lock in inode_inc_iversion
fs: new API for handling inode->i_version
ntfs: remove i_version handling
...
The switch to uuid_t invereted the logic of verfication that &entry->fsuuid
is zero during parsing of "fsuuid=" rule. Instead of making sure the
&entry->fsuuid field is not attempted to be overwritten, we bail out for
perfectly correct rule.
Fixes: 787d8c530a ("ima/policy: switch to use uuid_t")
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Pull x86 pti updates from Thomas Gleixner:
"This contains:
- a PTI bugfix to avoid setting reserved CR3 bits when PCID is
disabled. This seems to cause issues on a virtual machine at least
and is incorrect according to the AMD manual.
- a PTI bugfix which disables the perf BTS facility if PTI is
enabled. The BTS AUX buffer is not globally visible and causes the
CPU to fault when the mapping disappears on switching CR3 to user
space. A full fix which restores BTS on PTI is non trivial and will
be worked on.
- PTI bugfixes for EFI and trusted boot which make sure that the user
space visible page table entries have the NX bit cleared
- removal of dead code in the PTI pagetable setup functions
- add PTI documentation
- add a selftest for vsyscall to verify that the kernel actually
implements what it advertises.
- a sysfs interface to expose vulnerability and mitigation
information so there is a coherent way for users to retrieve the
status.
- the initial spectre_v2 mitigations, aka retpoline:
+ The necessary ASM thunk and compiler support
+ The ASM variants of retpoline and the conversion of affected ASM
code
+ Make LFENCE serializing on AMD so it can be used as speculation
trap
+ The RSB fill after vmexit
- initial objtool support for retpoline
As I said in the status mail this is the most of the set of patches
which should go into 4.15 except two straight forward patches still on
hold:
- the retpoline add on of LFENCE which waits for ACKs
- the RSB fill after context switch
Both should be ready to go early next week and with that we'll have
covered the major holes of spectre_v2 and go back to normality"
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
x86,perf: Disable intel_bts when PTI
security/Kconfig: Correct the Documentation reference for PTI
x86/pti: Fix !PCID and sanitize defines
selftests/x86: Add test_vsyscall
x86/retpoline: Fill return stack buffer on vmexit
x86/retpoline/irq32: Convert assembler indirect jumps
x86/retpoline/checksum32: Convert assembler indirect jumps
x86/retpoline/xen: Convert Xen hypercall indirect jumps
x86/retpoline/hyperv: Convert assembler indirect jumps
x86/retpoline/ftrace: Convert ftrace assembler indirect jumps
x86/retpoline/entry: Convert entry assembler indirect jumps
x86/retpoline/crypto: Convert crypto assembler indirect jumps
x86/spectre: Add boot time option to select Spectre v2 mitigation
x86/retpoline: Add initial retpoline support
objtool: Allow alternatives to be ignored
objtool: Detect jumps to retpoline thunks
x86/pti: Make unpoison of pgd for trusted boot work for real
x86/alternatives: Fix optimize_nops() checking
sysfs/cpu: Fix typos in vulnerability documentation
x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC
...
The intended behaviour in apparmor profile matching is to flag a
conflict if two profiles match equally well. However, right now a
conflict is generated if another profile has the same match length even
if that profile doesn't actually match. Fix the logic so we only
generate a conflict if the profiles match.
Fixes: 844b8292b6 ("apparmor: ensure that undecidable profile attachments fail")
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
Given a label with a profile stack of
A//&B or A//&C ...
A ptrace rule should be able to specify a generic trace pattern with
a rule like
ptrace trace A//&**,
however this is failing because while the correct label match routine
is called, it is being done post label decomposition so it is always
being done against a profile instead of the stacked label.
To fix this refactor the cross check to pass the full peer label in to
the label_match.
Fixes: 290f458a4f ("apparmor: allow ptrace checks to be finer grained than just capability")
Cc: Stable <stable@vger.kernel.org>
Reported-by: Matthew Garrett <mjg59@google.com>
Tested-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
-----BEGIN PGP SIGNATURE-----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=b5fz
-----END PGP SIGNATURE-----
Merge tag 'apparmor-pr-2018-01-07' of git://git.kernel.org/pub/scm/linux/kernel/git/jj/linux-apparmor
Pull apparmor fix from John Johansen:
"This fixes a regression when the kernel feature set is reported as
supporting mount and policy is pinned to a feature set that does not
support mount mediation"
* tag 'apparmor-pr-2018-01-07' of git://git.kernel.org/pub/scm/linux/kernel/git/jj/linux-apparmor:
apparmor: fix regression in mount mediation when feature set is pinned
When the mount code was refactored for Labels it was not correctly
updated to check whether policy supported mediation of the mount
class. This causes a regression when the kernel feature set is
reported as supporting mount and policy is pinned to a feature set
that does not support mount mediation.
BugLink: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=882697#41
Fixes: 2ea3ffb778 ("apparmor: add mount mediation")
Reported-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: John Johansen <john.johansen@canonical.com>
Pull x86 page table isolation fixes from Thomas Gleixner:
"A couple of urgent fixes for PTI:
- Fix a PTE mismatch between user and kernel visible mapping of the
cpu entry area (differs vs. the GLB bit) and causes a TLB mismatch
MCE on older AMD K8 machines
- Fix the misplaced CR3 switch in the SYSCALL compat entry code which
causes access to unmapped kernel memory resulting in double faults.
- Fix the section mismatch of the cpu_tss_rw percpu storage caused by
using a different mechanism for declaration and definition.
- Two fixes for dumpstack which help to decode entry stack issues
better
- Enable PTI by default in Kconfig. We should have done that earlier,
but it slipped through the cracks.
- Exclude AMD from the PTI enforcement. Not necessarily a fix, but if
AMD is so confident that they are not affected, then we should not
burden users with the overhead"
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/process: Define cpu_tss_rw in same section as declaration
x86/pti: Switch to kernel CR3 at early in entry_SYSCALL_compat()
x86/dumpstack: Print registers for first stack frame
x86/dumpstack: Fix partial register dumps
x86/pti: Make sure the user/kernel PTEs match
x86/cpu, x86/pti: Do not enable PTI on AMD processors
x86/pti: Enable PTI by default
This really want's to be enabled by default. Users who know what they are
doing can disable it either in the config or on the kernel command line.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Pull RCU updates from Paul E. McKenney:
- Updates to use cond_resched() instead of cond_resched_rcu_qs()
where feasible (currently everywhere except in kernel/rcu and
in kernel/torture.c). Also a couple of fixes to avoid sending
IPIs to offline CPUs.
- Updates to simplify RCU's dyntick-idle handling.
- Updates to remove almost all uses of smp_read_barrier_depends()
and read_barrier_depends().
- Miscellaneous fixes.
- Torture-test updates.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If userspace attempted to set a "security.capability" xattr shorter than
4 bytes (e.g. 'setfattr -n security.capability -v x file'), then
cap_convert_nscap() read past the end of the buffer containing the xattr
value because it accessed the ->magic_etc field without verifying that
the xattr value is long enough to contain that field.
Fix it by validating the xattr value size first.
This bug was found using syzkaller with KASAN. The KASAN report was as
follows (cleaned up slightly):
BUG: KASAN: slab-out-of-bounds in cap_convert_nscap+0x514/0x630 security/commoncap.c:498
Read of size 4 at addr ffff88002d8741c0 by task syz-executor1/2852
CPU: 0 PID: 2852 Comm: syz-executor1 Not tainted 4.15.0-rc6-00200-gcc0aac99d977 #253
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-20171110_100015-anatol 04/01/2014
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0xe3/0x195 lib/dump_stack.c:53
print_address_description+0x73/0x260 mm/kasan/report.c:252
kasan_report_error mm/kasan/report.c:351 [inline]
kasan_report+0x235/0x350 mm/kasan/report.c:409
cap_convert_nscap+0x514/0x630 security/commoncap.c:498
setxattr+0x2bd/0x350 fs/xattr.c:446
path_setxattr+0x168/0x1b0 fs/xattr.c:472
SYSC_setxattr fs/xattr.c:487 [inline]
SyS_setxattr+0x36/0x50 fs/xattr.c:483
entry_SYSCALL_64_fastpath+0x18/0x85
Fixes: 8db6c34f1d ("Introduce v3 namespaced file capabilities")
Cc: <stable@vger.kernel.org> # v4.14+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
Pull x86 page table isolation updates from Thomas Gleixner:
"This is the final set of enabling page table isolation on x86:
- Infrastructure patches for handling the extra page tables.
- Patches which map the various bits and pieces which are required to
get in and out of user space into the user space visible page
tables.
- The required changes to have CR3 switching in the entry/exit code.
- Optimizations for the CR3 switching along with documentation how
the ASID/PCID mechanism works.
- Updates to dump pagetables to cover the user space page tables for
W+X scans and extra debugfs files to analyze both the kernel and
the user space visible page tables
The whole functionality is compile time controlled via a config switch
and can be turned on/off on the command line as well"
* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
x86/ldt: Make the LDT mapping RO
x86/mm/dump_pagetables: Allow dumping current pagetables
x86/mm/dump_pagetables: Check user space page table for WX pages
x86/mm/dump_pagetables: Add page table directory to the debugfs VFS hierarchy
x86/mm/pti: Add Kconfig
x86/dumpstack: Indicate in Oops whether PTI is configured and enabled
x86/mm: Clarify the whole ASID/kernel PCID/user PCID naming
x86/mm: Use INVPCID for __native_flush_tlb_single()
x86/mm: Optimize RESTORE_CR3
x86/mm: Use/Fix PCID to optimize user/kernel switches
x86/mm: Abstract switching CR3
x86/mm: Allow flushing for future ASID switches
x86/pti: Map the vsyscall page if needed
x86/pti: Put the LDT in its own PGD if PTI is on
x86/mm/64: Make a full PGD-entry size hole in the memory map
x86/events/intel/ds: Map debug buffers in cpu_entry_area
x86/cpu_entry_area: Add debugstore entries to cpu_entry_area
x86/mm/pti: Map ESPFIX into user space
x86/mm/pti: Share entry text PMD
x86/entry: Align entry text section to PMD boundary
...
Finally allow CONFIG_PAGE_TABLE_ISOLATION to be enabled.
PARAVIRT generally requires that the kernel not manage its own page tables.
It also means that the hypervisor and kernel must agree wholeheartedly
about what format the page tables are in and what they contain.
PAGE_TABLE_ISOLATION, unfortunately, changes the rules and they
can not be used together.
I've seen conflicting feedback from maintainers lately about whether they
want the Kconfig magic to go first or last in a patch series. It's going
last here because the partially-applied series leads to kernels that can
not boot in a bunch of cases. I did a run through the entire series with
CONFIG_PAGE_TABLE_ISOLATION=y to look for build errors, though.
[ tglx: Removed SMP and !PARAVIRT dependencies as they not longer exist ]
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: linux-mm@kvack.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
i_version is only supported by a filesystem when the SB_I_VERSION
flag is set. This patch tests for the SB_I_VERSION flag before using
i_version. If we can't use i_version to detect a file change then we
must assume the file has changed in the last_writer path and remeasure
it.
On filesystems without i_version support IMA used to measure a file
only once and didn't detect any changes to a file. With this patch
IMA now works properly on these filesystems.
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
The init_once routine memsets the whole object to 0, and then
explicitly sets some of the fields to 0 again. Just remove the explicit
initializations.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Simple but useful message log to the user in case of module appraise is
forced and fails due to the lack of file descriptor, that might be
caused by kmod calls to compressed modules.
Signed-off-by: Bruno E. O. Meneguele <brdeoliv@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
ima_rdwr_violation_check() retrieves the full path of a measured file by
calling ima_d_path(). If process_measurement() calls this function, it
reuses the pointer and passes it to the functions to measure/appraise/audit
an accessed file.
After commit bc15ed663e ("ima: fix ima_d_path() possible race with
rename"), ima_d_path() first tries to retrieve the full path by calling
d_absolute_path() and, if there is an error, copies the dentry name to the
buffer passed as argument.
However, ima_rdwr_violation_check() passes to ima_d_path() the pointer of a
local variable. process_measurement() might be reusing the pointer to an
area in the stack which may have been already overwritten after
ima_rdwr_violation_check() returned.
Correct this issue by passing to ima_rdwr_violation_check() the pointer of
a buffer declared in process_measurement().
Fixes: bc15ed663e ("ima: fix ima_d_path() possible race with rename")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Line continuations with excess spacing causes unexpected output.
Based on commit 6f76b6fcaa ("CodingStyle: Document the exception of
not splitting user-visible strings, for grepping") recommendation.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
The builtin ima_appraise_tcb policy, which is specified on the boot
command line, can be replaced with a custom policy, normally early in
the boot process. Custom policies can be more restrictive in some ways,
like requiring file signatures, but can be less restrictive in other
ways, like not appraising mutable files. With a less restrictive policy
in place, files in the builtin policy might not be hashed and labeled
with a security.ima hash. On reboot, files which should be labeled in
the ima_appraise_tcb are not labeled, possibly preventing the system
from booting properly.
To resolve this problem, this patch extends the existing IMA policy
actions "measure", "dont_measure", "appraise", "dont_appraise", and
"audit" with "hash" and "dont_hash". The new "hash" action will write
the file hash as security.ima, but without requiring the file to be
appraised as well.
For example, the builtin ima_appraise_tcb policy includes the rule,
"appraise fowner=0". Adding the "hash fowner=0" rule to a custom
policy, will cause the needed file hashes to be calculated and written
as security.ima xattrs.
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
i_version is only supported by a filesystem when the SB_I_VERSION
flag is set. This patch tests for the SB_I_VERSION flag before using
i_version. If we can't use i_version to detect a file change then we
must assume the file has changed in the last_writer path and remeasure
it.
On filesystems without i_version support IMA used to measure a file
only once and didn't detect any changes to a file. With this patch
IMA now works properly on these filesystems.
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Before IMA appraisal was introduced, IMA was using own integrity cache
lock along with i_mutex. process_measurement and ima_file_free took
the iint->mutex first and then the i_mutex, while setxattr, chmod and
chown took the locks in reverse order. To resolve the potential deadlock,
i_mutex was moved to protect entire IMA functionality and the redundant
iint->mutex was eliminated.
Solution was based on the assumption that filesystem code does not take
i_mutex further. But when file is opened with O_DIRECT flag, direct-io
implementation takes i_mutex and produces deadlock. Furthermore, certain
other filesystem operations, such as llseek, also take i_mutex.
More recently some filesystems have replaced their filesystem specific
lock with the global i_rwsem to read a file. As a result, when IMA
attempts to calculate the file hash, reading the file attempts to take
the i_rwsem again.
To resolve O_DIRECT related deadlock problem, this patch re-introduces
iint->mutex. But to eliminate the original chmod() related deadlock
problem, this patch eliminates the requirement for chmod hooks to take
the iint->mutex by introducing additional atomic iint->attr_flags to
indicate calling of the hooks. The allowed locking order is to take
the iint->mutex first and then the i_rwsem.
Original flags were cleared in chmod(), setxattr() or removwxattr()
hooks and tested when file was closed or opened again. New atomic flags
are set or cleared in those hooks and tested to clear iint->flags on
close or on open.
Atomic flags are following:
* IMA_CHANGE_ATTR - indicates that chATTR() was called (chmod, chown,
chgrp) and file attributes have changed. On file open, it causes IMA
to clear iint->flags to re-evaluate policy and perform IMA functions
again.
* IMA_CHANGE_XATTR - indicates that setxattr or removexattr was called
and extended attributes have changed. On file open, it causes IMA to
clear iint->flags IMA_DONE_MASK to re-appraise.
* IMA_UPDATE_XATTR - indicates that security.ima needs to be updated.
It is cleared if file policy changes and no update is needed.
* IMA_DIGSIG - indicates that file security.ima has signature and file
security.ima must not update to file has on file close.
* IMA_MUST_MEASURE - indicates the file is in the measurement policy.
Fixes: Commit 6552321831 ("xfs: remove i_iolock and use i_rwsem in
the VFS inode instead")
Signed-off-by: Dmitry Kasatkin <dmitry.kasatkin@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
The EVM signature includes the inode number and (optionally) the
filesystem UUID, making it impractical to ship EVM signatures in
packages. This patch adds a new portable format intended to allow
distributions to include EVM signatures. It is identical to the existing
format but hardcodes the inode and generation numbers to 0 and does not
include the filesystem UUID even if the kernel is configured to do so.
Removing the inode means that the metadata and signature from one file
could be copied to another file without invalidating it. This is avoided
by ensuring that an IMA xattr is present during EVM validation.
Portable signatures are intended to be immutable - ie, they will never
be transformed into HMACs.
Based on earlier work by Dmitry Kasatkin and Mikhail Kurinnoi.
Signed-off-by: Matthew Garrett <mjg59@google.com>
Cc: Dmitry Kasatkin <dmitry.kasatkin@huawei.com>
Cc: Mikhail Kurinnoi <viewizard@viewizard.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
When EVM is enabled it forbids modification of metadata protected by
EVM unless there is already a valid EVM signature. If any modification
is made, the kernel will then generate a new EVM HMAC. However, this
does not map well on use cases which use only asymmetric EVM signatures,
as in this scenario the kernel is unable to generate new signatures.
This patch extends the /sys/kernel/security/evm interface to allow
userland to request that modification of these xattrs be permitted. This
is only permitted if no keys have already been loaded. In this
configuration, modifying the metadata will invalidate the EVM appraisal
on the file in question. This allows packaging systems to write out new
files, set the relevant extended attributes and then move them into
place.
There's also some refactoring of the use of evm_initialized in order to
avoid heading down codepaths that assume there's a key available.
Signed-off-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Custom policies can require file signatures based on LSM labels. These
files are normally created and only afterwards labeled, requiring them
to be signed.
Instead of requiring file signatures based on LSM labels, entire
filesystems could require file signatures. In this case, we need the
ability of writing new files without requiring file signatures.
The definition of a "new" file was originally defined as any file with
a length of zero. Subsequent patches redefined a "new" file to be based
on the FILE_CREATE open flag. By combining the open flag with a file
size of zero, this patch relaxes the file signature requirement.
Fixes: 1ac202e978 ima: accept previously set IMA_NEW_FILE
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
keyctl_restrict_keyring() allows through a NULL restriction when the
"type" is non-NULL, which causes a NULL pointer dereference in
asymmetric_lookup_restriction() when it calls strcmp() on the
restriction string.
But no key types actually use a "NULL restriction" to mean anything, so
update keyctl_restrict_keyring() to reject it with EINVAL.
Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: 97d3aa0f31 ("KEYS: Add a lookup_restriction function for the asymmetric key type")
Cc: <stable@vger.kernel.org> # v4.12+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Variable key_ref is being assigned a value that is never read;
key_ref is being re-assigned a few statements later. Hence this
assignment is redundant and can be removed.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: James Morris <james.l.morris@oracle.com>
When the request_key() syscall is not passed a destination keyring, it
links the requested key (if constructed) into the "default" request-key
keyring. This should require Write permission to the keyring. However,
there is actually no permission check.
This can be abused to add keys to any keyring to which only Search
permission is granted. This is because Search permission allows joining
the keyring. keyctl_set_reqkey_keyring(KEY_REQKEY_DEFL_SESSION_KEYRING)
then will set the default request-key keyring to the session keyring.
Then, request_key() can be used to add keys to the keyring.
Both negatively and positively instantiated keys can be added using this
method. Adding negative keys is trivial. Adding a positive key is a
bit trickier. It requires that either /sbin/request-key positively
instantiates the key, or that another thread adds the key to the process
keyring at just the right time, such that request_key() misses it
initially but then finds it in construct_alloc_key().
Fix this bug by checking for Write permission to the keyring in
construct_get_dest_keyring() when the default keyring is being used.
We don't do the permission check for non-default keyrings because that
was already done by the earlier call to lookup_user_key(). Also,
request_key_and_link() is currently passed a 'struct key *' rather than
a key_ref_t, so the "possessed" bit is unavailable.
We also don't do the permission check for the "requestor keyring", to
continue to support the use case described by commit 8bbf4976b5
("KEYS: Alter use of key instantiation link-to-keyring argument") where
/sbin/request-key recursively calls request_key() to add keys to the
original requestor's destination keyring. (I don't know of any users
who actually do that, though...)
Fixes: 3e30148c3d ("[PATCH] Keys: Make request-key create an authorisation key")
Cc: <stable@vger.kernel.org> # v2.6.13+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
In request_key_and_link(), in the case where the dest_keyring was
explicitly specified, there is no need to get another reference to
dest_keyring before calling key_link(), then drop it afterwards. This
is because by definition, we already have a reference to dest_keyring.
This change is useful because we'll be making
construct_get_dest_keyring() able to return an error code, and we don't
want to have to handle that error here for no reason.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Now that the associative-array library properly heads dependency chains,
the various smp_read_barrier_depends() calls in security/keys/keyring.c
are no longer needed. This commit therefore removes them.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: <keyrings@vger.kernel.org>
Cc: <linux-security-module@vger.kernel.org>
Reviewed-by: James Morris <james.l.morris@oracle.com>
This is a pure automated search-and-replace of the internal kernel
superblock flags.
The s_flags are now called SB_*, with the names and the values for the
moment mirroring the MS_* flags that they're equivalent to.
Note how the MS_xyz flags are the ones passed to the mount system call,
while the SB_xyz flags are what we then use in sb->s_flags.
The script to do this was:
# places to look in; re security/*: it generally should *not* be
# touched (that stuff parses mount(2) arguments directly), but
# there are two places where we really deal with superblock flags.
FILES="drivers/mtd drivers/staging/lustre fs ipc mm \
include/linux/fs.h include/uapi/linux/bfs_fs.h \
security/apparmor/apparmorfs.c security/apparmor/include/lib.h"
# the list of MS_... constants
SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \
DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \
POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \
I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \
ACTIVE NOUSER"
SED_PROG=
for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done
# we want files that contain at least one of MS_...,
# with fs/namespace.c and fs/pnode.c excluded.
L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c')
for f in $L; do sed -i $f $SED_PROG; done
Requested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull timer updates from Thomas Gleixner:
- The final conversion of timer wheel timers to timer_setup().
A few manual conversions and a large coccinelle assisted sweep and
the removal of the old initialization mechanisms and the related
code.
- Remove the now unused VSYSCALL update code
- Fix permissions of /proc/timer_list. I still need to get rid of that
file completely
- Rename a misnomed clocksource function and remove a stale declaration
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
m68k/macboing: Fix missed timer callback assignment
treewide: Remove TIMER_FUNC_TYPE and TIMER_DATA_TYPE casts
timer: Remove redundant __setup_timer*() macros
timer: Pass function down to initialization routines
timer: Remove unused data arguments from macros
timer: Switch callback prototype to take struct timer_list * argument
timer: Pass timer_list pointer to callbacks unconditionally
Coccinelle: Remove setup_timer.cocci
timer: Remove setup_*timer() interface
timer: Remove init_timer() interface
treewide: setup_timer() -> timer_setup() (2 field)
treewide: setup_timer() -> timer_setup()
treewide: init_timer() -> setup_timer()
treewide: Switch DEFINE_TIMER callbacks to struct timer_list *
s390: cmm: Convert timers to use timer_setup()
lightnvm: Convert timers to use timer_setup()
drivers/net: cris: Convert timers to use timer_setup()
drm/vc4: Convert timers to use timer_setup()
block/laptop_mode: Convert timers to use timer_setup()
net/atm/mpc: Avoid open-coded assignment of timer callback function
...
Pull keys update from James Morris:
"There's nothing too controversial here:
- Doc fix for keyctl_read().
- time_t -> time64_t replacement.
- Set the module licence on things to prevent tainting"
* 'next-keys' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
pkcs7: Set the module licence to prevent tainting
security: keys: Replace time_t with time64_t for struct key_preparsed_payload
security: keys: Replace time_t/timespec with time64_t
KEYS: fix in-kernel documentation for keyctl_read()
This changes all DEFINE_TIMER() callbacks to use a struct timer_list
pointer instead of unsigned long. Since the data argument has already been
removed, none of these callbacks are using their argument currently, so
this renames the argument to "unused".
Done using the following semantic patch:
@match_define_timer@
declarer name DEFINE_TIMER;
identifier _timer, _callback;
@@
DEFINE_TIMER(_timer, _callback);
@change_callback depends on match_define_timer@
identifier match_define_timer._callback;
type _origtype;
identifier _origarg;
@@
void
-_callback(_origtype _origarg)
+_callback(struct timer_list *unused)
{ ... }
Signed-off-by: Kees Cook <keescook@chromium.org>
It used to be that unconfined would never attach. However that is not
the case anymore as some special profiles can be marked as unconfined,
that are not the namespaces unconfined profile, and may have an
attachment.
Fixes: f1bd904175 ("apparmor: add the base fns() for domain labels")
Signed-off-by: John Johansen <john.johansen@canonical.com>
Profiles that have an undecidable overlap in their attachments are
being incorrectly handled. Instead of failing to attach the first one
encountered is being used.
eg.
profile A /** { .. }
profile B /*foo { .. }
have an unresolvable longest left attachment, they both have an exact
match on / and then have an overlapping expression that has no clear
winner.
Currently the winner will be the profile that is loaded first which
can result in non-deterministic behavior. Instead in this situation
the exec should fail.
Fixes: 898127c34e ("AppArmor: functions for domain transitions")
Signed-off-by: John Johansen <john.johansen@canonical.com>
Fixes: d07881d2ed ("apparmor: move new_null_profile to after profile lookup fns()")
Reported-by: Seth Arnold <seth.arnold@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
The boolean variable 'stop' is being set but never read. This
is a redundant variable and can be removed.
Cleans up clang warning: Value stored to 'stop' is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
