FAN_DIR_MODIFY has been enabled by commit 44d705b037 ("fanotify:
report name info for FAN_DIR_MODIFY event") in 5.7-rc1. Now we are
planning further extensions to the fanotify API and during that we
realized that FAN_DIR_MODIFY may behave slightly differently to be more
consistent with extensions we plan. So until we finalize these
extensions, let's not bind our hands with exposing FAN_DIR_MODIFY to
userland.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Clang warns:
fs/notify/fanotify/fanotify.c:28:23: warning: self-comparison always
evaluates to true [-Wtautological-compare]
return fsid1->val[0] == fsid1->val[0] && fsid2->val[1] == fsid2->val[1];
^
fs/notify/fanotify/fanotify.c:28:57: warning: self-comparison always
evaluates to true [-Wtautological-compare]
return fsid1->val[0] == fsid1->val[0] && fsid2->val[1] == fsid2->val[1];
^
2 warnings generated.
The intention was clearly to compare val[0] and val[1] in the two
different fsid structs. Fix it otherwise this function always returns
true.
Fixes: afc894c784 ("fanotify: Store fanotify handles differently")
Link: https://github.com/ClangBuiltLinux/linux/issues/952
Link: https://lore.kernel.org/r/20200327171030.30625-1-natechancellor@gmail.com
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Report event FAN_DIR_MODIFY with name in a variable length record similar
to how fid's are reported. With name info reporting implemented, setting
FAN_DIR_MODIFY in mark mask is now allowed.
When events are reported with name, the reported fid identifies the
directory and the name follows the fid. The info record type for this
event info is FAN_EVENT_INFO_TYPE_DFID_NAME.
For now, all reported events have at most one info record which is
either FAN_EVENT_INFO_TYPE_FID or FAN_EVENT_INFO_TYPE_DFID_NAME (for
FAN_DIR_MODIFY). Later on, events "on child" will report both records.
There are several ways that an application can use this information:
1. When watching a single directory, the name is always relative to
the watched directory, so application need to fstatat(2) the name
relative to the watched directory.
2. When watching a set of directories, the application could keep a map
of dirfd for all watched directories and hash the map by fid obtained
with name_to_handle_at(2). When getting a name event, the fid in the
event info could be used to lookup the base dirfd in the map and then
call fstatat(2) with that dirfd.
3. When watching a filesystem (FAN_MARK_FILESYSTEM) or a large set of
directories, the application could use open_by_handle_at(2) with the fid
in event info to obtain dirfd for the directory where event happened and
call fstatat(2) with this dirfd.
The last option scales better for a large number of watched directories.
The first two options may be available in the future also for non
privileged fanotify watchers, because open_by_handle_at(2) requires
the CAP_DAC_READ_SEARCH capability.
Link: https://lore.kernel.org/r/20200319151022.31456-15-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
For FAN_DIR_MODIFY event, allocate a variable size event struct to store
the dir entry name along side the directory file handle.
At this point, name info reporting is not yet implemented, so trying to
set FAN_DIR_MODIFY in mark mask will return -EINVAL.
Link: https://lore.kernel.org/r/20200319151022.31456-14-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
When some events have directory id and some object id,
fanotify_event_has_fid() becomes mostly useless and confusing because we
usually need to know which type of file handle the event has. So just
drop the function and use fanotify_event_object_fh() instead.
Signed-off-by: Jan Kara <jack@suse.cz>
For some events, we are going to report both child and parent fid's,
so pass fsid and file handle as arguments to copy_fid_to_user(),
which is going to be called with parent and child file handles.
Link: https://lore.kernel.org/r/20200319151022.31456-13-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Dirent events are going to be supported in two flavors:
1. Directory fid info + mask that includes the specific event types
(e.g. FAN_CREATE) and an optional FAN_ONDIR flag.
2. Directory fid info + name + mask that includes only FAN_DIR_MODIFY.
To request the second event flavor, user needs to set the event type
FAN_DIR_MODIFY in the mark mask.
The first flavor is supported since kernel v5.1 for groups initialized
with flag FAN_REPORT_FID. It is intended to be used for watching
directories in "batch mode" - the watcher is notified when directory is
changed and re-scans the directory content in response. This event
flavor is stored more compactly in the event queue, so it is optimal
for workloads with frequent directory changes.
The second event flavor is intended to be used for watching large
directories, where the cost of re-scan of the directory on every change
is considered too high. The watcher getting the event with the directory
fid and entry name is expected to call fstatat(2) to query the content of
the entry after the change.
Legacy inotify events are reported with name and event mask (e.g. "foo",
FAN_CREATE | FAN_ONDIR). That can lead users to the conclusion that
there is *currently* an entry "foo" that is a sub-directory, when in fact
"foo" may be negative or non-dir by the time user gets the event.
To make it clear that the current state of the named entry is unknown,
when reporting an event with name info, fanotify obfuscates the specific
event types (e.g. create,delete,rename) and uses a common event type -
FAN_DIR_MODIFY to describe the change. This should make it harder for
users to make wrong assumptions and write buggy filesystem monitors.
At this point, name info reporting is not yet implemented, so trying to
set FAN_DIR_MODIFY in mark mask will return -EINVAL.
Link: https://lore.kernel.org/r/20200319151022.31456-12-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Breakup the union and make them both inherit from abstract fanotify_event.
fanotify_path_event, fanotify_fid_event and fanotify_perm_event inherit
from fanotify_event.
type field in abstract fanotify_event determines the concrete event type.
fanotify_path_event, fanotify_fid_event and fanotify_perm_event are
allocated from separate memcache pools.
Rename fanotify_perm_event casting macro to FANOTIFY_PERM(), so that
FANOTIFY_PE() and FANOTIFY_FE() can be used as casting macros to
fanotify_path_event and fanotify_fid_event.
[JK: Cleanup FANOTIFY_PE() and FANOTIFY_FE() to be proper inline
functions and remove requirement that fanotify_event is the first in
event structures]
Link: https://lore.kernel.org/r/20200319151022.31456-11-amir73il@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Currently, struct fanotify_fid groups fsid and file handle and is
unioned together with struct path to save space. Also there is fh_type
and fh_len directly in struct fanotify_event to avoid padding overhead.
In the follwing patches, we will be adding more event types and this
packing makes code difficult to follow. So unpack everything and create
struct fanotify_fh which groups members logically related to file handle
to make code easier to follow. In the following patch we will pack
things again differently to make events smaller.
Signed-off-by: Jan Kara <jack@suse.cz>
create_fd() is never used with invalid path. Also the only thing it
needs to know from fanotify_event is the path. Simplify the function to
take path directly and assume it is correct.
Signed-off-by: Jan Kara <jack@suse.cz>
Change the logic of FAN_ONDIR in two ways that are similar to the logic
of FAN_EVENT_ON_CHILD, that was fixed in commit 54a307ba8d ("fanotify:
fix logic of events on child"):
1. The flag is meaningless in ignore mask
2. The flag refers only to events in the mask of the mark where it is set
This is what the fanotify_mark.2 man page says about FAN_ONDIR:
"Without this flag, only events for files are created." It doesn't
say anything about setting this flag in ignore mask to stop getting
events on directories nor can I think of any setup where this capability
would be useful.
Currently, when marks masks are merged, the FAN_ONDIR flag set in one
mark affects the events that are set in another mark's mask and this
behavior causes unexpected results. For example, a user adds a mark on a
directory with mask FAN_ATTRIB | FAN_ONDIR and a mount mark with mask
FAN_OPEN (without FAN_ONDIR). An opendir() of that directory (which is
inside that mount) generates a FAN_OPEN event even though neither of the
marks requested to get open events on directories.
Link: https://lore.kernel.org/r/20200319151022.31456-10-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
With inotify, when a watch is set on a directory and on its child, an
event on the child is reported twice, once with wd of the parent watch
and once with wd of the child watch without the filename.
With fanotify, when a watch is set on a directory and on its child, an
event on the child is reported twice, but it has the exact same
information - either an open file descriptor of the child or an encoded
fid of the child.
The reason that the two identical events are not merged is because the
object id used for merging events in the queue is the child inode in one
event and parent inode in the other.
For events with path or dentry data, use the victim inode instead of the
watched inode as the object id for event merging, so that the event
reported on parent will be merged with the event reported on the child.
Link: https://lore.kernel.org/r/20200319151022.31456-9-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
The event inode field is used only for comparison in queue merges and
cannot be dereferenced after handle_event(), because it does not hold a
refcount on the inode.
Replace it with an abstract id to do the same thing.
Link: https://lore.kernel.org/r/20200319151022.31456-8-amir73il@gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
The .ioctl and .compat_ioctl file operations have the same prototype so
they can both point to the same function, which works great almost all
the time when all the commands are compatible.
One exception is the s390 architecture, where a compat pointer is only
31 bit wide, and converting it into a 64-bit pointer requires calling
compat_ptr(). Most drivers here will never run in s390, but since we now
have a generic helper for it, it's easy enough to use it consistently.
I double-checked all these drivers to ensure that all ioctl arguments
are used as pointers or are ignored, but are not interpreted as integer
values.
Acked-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: David Sterba <dsterba@suse.com>
Acked-by: Darren Hart (VMware) <dvhart@infradead.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
-----BEGIN PGP SIGNATURE-----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=n4ht
-----END PGP SIGNATURE-----
Merge tag 'selinux-pr-20190917' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux
Pull selinux updates from Paul Moore:
- Add LSM hooks, and SELinux access control hooks, for dnotify,
fanotify, and inotify watches. This has been discussed with both the
LSM and fs/notify folks and everybody is good with these new hooks.
- The LSM stacking changes missed a few calls to current_security() in
the SELinux code; we fix those and remove current_security() for
good.
- Improve our network object labeling cache so that we always return
the object's label, even when under memory pressure. Previously we
would return an error if we couldn't allocate a new cache entry, now
we always return the label even if we can't create a new cache entry
for it.
- Convert the sidtab atomic_t counter to a normal u32 with
READ/WRITE_ONCE() and memory barrier protection.
- A few patches to policydb.c to clean things up (remove forward
declarations, long lines, bad variable names, etc)
* tag 'selinux-pr-20190917' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux:
lsm: remove current_security()
selinux: fix residual uses of current_security() for the SELinux blob
selinux: avoid atomic_t usage in sidtab
fanotify, inotify, dnotify, security: add security hook for fs notifications
selinux: always return a secid from the network caches if we find one
selinux: policydb - rename type_val_to_struct_array
selinux: policydb - fix some checkpatch.pl warnings
selinux: shuffle around policydb.c to get rid of forward declarations
As of now, setting watches on filesystem objects has, at most, applied a
check for read access to the inode, and in the case of fanotify, requires
CAP_SYS_ADMIN. No specific security hook or permission check has been
provided to control the setting of watches. Using any of inotify, dnotify,
or fanotify, it is possible to observe, not only write-like operations, but
even read access to a file. Modeling the watch as being merely a read from
the file is insufficient for the needs of SELinux. This is due to the fact
that read access should not necessarily imply access to information about
when another process reads from a file. Furthermore, fanotify watches grant
more power to an application in the form of permission events. While
notification events are solely, unidirectional (i.e. they only pass
information to the receiving application), permission events are blocking.
Permission events make a request to the receiving application which will
then reply with a decision as to whether or not that action may be
completed. This causes the issue of the watching application having the
ability to exercise control over the triggering process. Without drawing a
distinction within the permission check, the ability to read would imply
the greater ability to control an application. Additionally, mount and
superblock watches apply to all files within the same mount or superblock.
Read access to one file should not necessarily imply the ability to watch
all files accessed within a given mount or superblock.
In order to solve these issues, a new LSM hook is implemented and has been
placed within the system calls for marking filesystem objects with inotify,
fanotify, and dnotify watches. These calls to the hook are placed at the
point at which the target path has been resolved and are provided with the
path struct, the mask of requested notification events, and the type of
object on which the mark is being set (inode, superblock, or mount). The
mask and obj_type have already been translated into common FS_* values
shared by the entirety of the fs notification infrastructure. The path
struct is passed rather than just the inode so that the mount is available,
particularly for mount watches. This also allows for use of the hook by
pathname-based security modules. However, since the hook is intended for
use even by inode based security modules, it is not placed under the
CONFIG_SECURITY_PATH conditional. Otherwise, the inode-based security
modules would need to enable all of the path hooks, even though they do not
use any of them.
This only provides a hook at the point of setting a watch, and presumes
that permission to set a particular watch implies the ability to receive
all notification about that object which match the mask. This is all that
is required for SELinux. If other security modules require additional hooks
or infrastructure to control delivery of notification, these can be added
by them. It does not make sense for us to propose hooks for which we have
no implementation. The understanding that all notifications received by the
requesting application are all strictly of a type for which the application
has been granted permission shows that this implementation is sufficient in
its coverage.
Security modules wishing to provide complete control over fanotify must
also implement a security_file_open hook that validates that the access
requested by the watching application is authorized. Fanotify has the issue
that it returns a file descriptor with the file mode specified during
fanotify_init() to the watching process on event. This is already covered
by the LSM security_file_open hook if the security module implements
checking of the requested file mode there. Otherwise, a watching process
can obtain escalated access to a file for which it has not been authorized.
The selinux_path_notify hook implementation works by adding five new file
permissions: watch, watch_mount, watch_sb, watch_reads, and watch_with_perm
(descriptions about which will follow), and one new filesystem permission:
watch (which is applied to superblock checks). The hook then decides which
subset of these permissions must be held by the requesting application
based on the contents of the provided mask and the obj_type. The
selinux_file_open hook already checks the requested file mode and therefore
ensures that a watching process cannot escalate its access through
fanotify.
The watch, watch_mount, and watch_sb permissions are the baseline
permissions for setting a watch on an object and each are a requirement for
any watch to be set on a file, mount, or superblock respectively. It should
be noted that having either of the other two permissions (watch_reads and
watch_with_perm) does not imply the watch, watch_mount, or watch_sb
permission. Superblock watches further require the filesystem watch
permission to the superblock. As there is no labeled object in view for
mounts, there is no specific check for mount watches beyond watch_mount to
the inode. Such a check could be added in the future, if a suitable labeled
object existed representing the mount.
The watch_reads permission is required to receive notifications from
read-exclusive events on filesystem objects. These events include accessing
a file for the purpose of reading and closing a file which has been opened
read-only. This distinction has been drawn in order to provide a direct
indication in the policy for this otherwise not obvious capability. Read
access to a file should not necessarily imply the ability to observe read
events on a file.
Finally, watch_with_perm only applies to fanotify masks since it is the
only way to set a mask which allows for the blocking, permission event.
This permission is needed for any watch which is of this type. Though
fanotify requires CAP_SYS_ADMIN, this is insufficient as it gives implicit
trust to root, which we do not do, and does not support least privilege.
Signed-off-by: Aaron Goidel <acgoide@tycho.nsa.gov>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Commit d46eb14b73 ("fs: fsnotify: account fsnotify metadata to
kmemcg") added remote memcg charging for fanotify and inotify event
objects. The aim was to charge the memory to the listener who is
interested in the events but without triggering the OOM killer.
Otherwise there would be security concerns for the listener.
At the time, oom-kill trigger was not in the charging path. A parallel
work added the oom-kill back to charging path i.e. commit 29ef680ae7
("memcg, oom: move out_of_memory back to the charge path"). So to not
trigger oom-killer in the remote memcg, explicitly add
__GFP_RETRY_MAYFAIL to the fanotigy and inotify event allocations.
Link: http://lkml.kernel.org/r/20190514212259.156585-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When implementing connector fsid cache, we only initialized the cache
when the first mark added to object was added by FAN_REPORT_FID group.
We forgot to update conn->fsid when the second mark is added by
FAN_REPORT_FID group to an already attached connector without fsid
cache.
Reported-and-tested-by: syzbot+c277e8e2f46414645508@syzkaller.appspotmail.com
Fixes: 77115225ac ("fanotify: cache fsid in fsnotify_mark_connector")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Proc filesystem has special locking rules for various files. Thus
fanotify which opens files on event delivery can easily deadlock
against another process that waits for fanotify permission event to be
handled. Since permission events on /proc have doubtful value anyway,
just disallow them.
Link: https://lore.kernel.org/linux-fsdevel/20190320131642.GE9485@quack2.suse.cz/
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Add SPDX license identifiers to all Make/Kconfig files which:
- Have no license information of any form
These files fall under the project license, GPL v2 only. The resulting SPDX
license identifier is:
GPL-2.0-only
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Pull misc dcache updates from Al Viro:
"Most of this pile is putting name length into struct name_snapshot and
making use of it.
The beginning of this series ("ovl_lookup_real_one(): don't bother
with strlen()") ought to have been split in two (separate switch of
name_snapshot to struct qstr from overlayfs reaping the trivial
benefits of that), but I wanted to avoid a rebase - by the time I'd
spotted that it was (a) in -next and (b) close to 5.1-final ;-/"
* 'work.dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
audit_compare_dname_path(): switch to const struct qstr *
audit_update_watch(): switch to const struct qstr *
inotify_handle_event(): don't bother with strlen()
fsnotify: switch send_to_group() and ->handle_event to const struct qstr *
fsnotify(): switch to passing const struct qstr * for file_name
switch fsnotify_move() to passing const struct qstr * for old_name
ovl_lookup_real_one(): don't bother with strlen()
sysv: bury the broken "quietly truncate the long filenames" logics
nsfs: unobfuscate
unexport d_alloc_pseudo()
-----BEGIN PGP SIGNATURE-----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=LH11
-----END PGP SIGNATURE-----
Merge tag 'pidfd-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull pidfd updates from Christian Brauner:
"This patchset makes it possible to retrieve pidfds at process creation
time by introducing the new flag CLONE_PIDFD to the clone() system
call. Linus originally suggested to implement this as a new flag to
clone() instead of making it a separate system call.
After a thorough review from Oleg CLONE_PIDFD returns pidfds in the
parent_tidptr argument. This means we can give back the associated pid
and the pidfd at the same time. Access to process metadata information
thus becomes rather trivial.
As has been agreed, CLONE_PIDFD creates file descriptors based on
anonymous inodes similar to the new mount api. They are made
unconditional by this patchset as they are now needed by core kernel
code (vfs, pidfd) even more than they already were before (timerfd,
signalfd, io_uring, epoll etc.). The core patchset is rather small.
The bulky looking changelist is caused by David's very simple changes
to Kconfig to make anon inodes unconditional.
A pidfd comes with additional information in fdinfo if the kernel
supports procfs. The fdinfo file contains the pid of the process in
the callers pid namespace in the same format as the procfs status
file, i.e. "Pid:\t%d".
To remove worries about missing metadata access this patchset comes
with a sample/test program that illustrates how a combination of
CLONE_PIDFD and pidfd_send_signal() can be used to gain race-free
access to process metadata through /proc/<pid>.
Further work based on this patchset has been done by Joel. His work
makes pidfds pollable. It finished too late for this merge window. I
would prefer to have it sitting in linux-next for a while and send it
for inclusion during the 5.3 merge window"
* tag 'pidfd-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
samples: show race-free pidfd metadata access
signal: support CLONE_PIDFD with pidfd_send_signal
clone: add CLONE_PIDFD
Make anon_inodes unconditional
fanotify_get_fsid() is reading mark->connector->fsid under srcu. It can
happen that it sees mark not fully initialized or mark that is already
detached from the object list. In these cases mark->connector
can be NULL leading to NULL ptr dereference. Fix the problem by
being careful when reading mark->connector and check it for being NULL.
Also use WRITE_ONCE when writing the mark just to prevent compiler from
doing something stupid.
Reported-by: syzbot+15927486a4f1bfcbaf91@syzkaller.appspotmail.com
Fixes: 77115225ac ("fanotify: cache fsid in fsnotify_mark_connector")
Signed-off-by: Jan Kara <jack@suse.cz>
note that conditions surrounding accesses to dname in audit_watch_handle_event()
and audit_mark_handle_event() guarantee that dname won't have been NULL.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Make the anon_inodes facility unconditional so that it can be used by core
VFS code and pidfd code.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
[christian@brauner.io: adapt commit message to mention pidfds]
Signed-off-by: Christian Brauner <christian@brauner.io>
When file handle is embedded inside fanotify_event and usercopy checks
are enabled, we get a warning like:
Bad or missing usercopy whitelist? Kernel memory exposure attempt detected
from SLAB object 'fanotify_event' (offset 40, size 8)!
WARNING: CPU: 1 PID: 7649 at mm/usercopy.c:78 usercopy_warn+0xeb/0x110
mm/usercopy.c:78
Annotate handling in fanotify_event properly to mark copying it to
userspace is fine.
Reported-by: syzbot+2c49971e251e36216d1f@syzkaller.appspotmail.com
Fixes: a8b13aa20a ("fanotify: enable FAN_REPORT_FID init flag")
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Making waits for response to fanotify permission events interruptible
can result in EINTR returns from open(2) or other syscalls when there's
e.g. AV software that's monitoring the file. Orion reports that e.g.
bash is complaining like:
bash: /etc/bash_completion.d/itweb-settings.bash: Interrupted system call
So for now convert the wait from interruptible to only killable one.
That is mostly invisible to userspace. Sadly this breaks hibernation
with fanotify permission events pending again but we have to put more
thought into how to fix this without regressing userspace visible
behavior.
Reported-by: Orion Poplawski <orion@nwra.com>
Signed-off-by: Jan Kara <jack@suse.cz>
When waiting for response to fanotify permission events, we currently
use uninterruptible waits. That makes code simple however it can cause
lots of processes to end up in uninterruptible sleep with hard reboot
being the only alternative in case fanotify listener process stops
responding (e.g. due to a bug in its implementation). Uninterruptible
sleep also makes system hibernation fail if the listener gets frozen
before the process generating fanotify permission event.
Fix these problems by using interruptible sleep for waiting for response
to fanotify event. This is slightly tricky though - we have to
detect when the event got already reported to userspace as in that
case we must not free the event. Instead we push the responsibility for
freeing the event to the process that will write response to the
event.
Reported-by: Orion Poplawski <orion@nwra.com>
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Track whether permission event got already reported to userspace and
whether userspace already answered to the permission event. Protect
stores to this field together with updates to ->response field by
group->notification_lock. This will allow aborting wait for reply to
permission event from userspace.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Simplify iteration cleaning access_list in fanotify_release(). That will
make following changes more obvious.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
get_one_event() has a single caller and that just locks
notification_lock around the call. Move locking inside get_one_event()
as that will make using ->response field for permission event state
easier.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Fold dequeue_event() into process_access_response(). This will make
changes to use of ->response field easier.
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Fanotify now uses exportfs_encode_inode_fh() so it needs to select
EXPORTFS.
Fixes: e9e0c89030 "fanotify: encode file identifier for FAN_REPORT_FID"
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jan Kara <jack@suse.cz>
dirent modification events (create/delete/move) do not carry the
child entry name/inode information. Instead, we report FAN_ONDIR
for mkdir/rmdir so user can differentiate them from creat/unlink.
This is consistent with inotify reporting IN_ISDIR with dirent events
and is useful for implementing recursive directory tree watcher.
We avoid merging dirent events referring to subdirs with dirent events
referring to non subdirs, otherwise, user won't be able to tell from a
mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+unlink pair
or rmdir+create pair of events.
For backward compatibility and consistency, do not report FAN_ONDIR
to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
to user in FAN_REPORT_FID mode for all event types.
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Add support for events with data type FSNOTIFY_EVENT_INODE
(e.g. create/attrib/move/delete) for inode and filesystem mark types.
The "inode" events do not carry enough information (i.e. path) to
report event->fd, so we do not allow setting a mask for those events
unless group supports reporting fid.
The "inode" events are not supported on a mount mark, because they do
not carry enough information (i.e. path) to be filtered by mount point.
The "dirent" events (create/move/delete) report the fid of the parent
directory where events took place without specifying the filename of the
child. In the future, fanotify may get support for reporting filename
information for those events.
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
When event data type is FSNOTIFY_EVENT_INODE, we don't have a refernece
to the mount, so we will not be able to open a file descriptor when user
reads the event. However, if the listener has enabled reporting file
identifier with the FAN_REPORT_FID init flag, we allow reporting those
events and we use an identifier inode to encode fid.
The inode to use as identifier when reporting fid depends on the event.
For dirent modification events, we report the modified directory inode
and we report the "victim" inode otherwise.
For example:
FS_ATTRIB reports the child inode even if reported on a watched parent.
FS_CREATE reports the modified dir inode and not the created inode.
[JK: Fixup condition in fanotify_group_event_mask()]
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
All fsnotify hooks set the FS_ISDIR flag for events that happen
on directory victim inodes except for fsnotify_perm().
Add the missing FS_ISDIR flag in fsnotify_perm() hook and let
fanotify_group_event_mask() check the FS_ISDIR flag instead of
checking if path argument is a directory.
This is needed for fanotify support for event types that do not
carry path information.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
For FAN_REPORT_FID, we need to encode fid with fsid of the filesystem on
every event. To avoid having to call vfs_statfs() on every event to get
fsid, we store the fsid in fsnotify_mark_connector on the first time we
add a mark and on handle event we use the cached fsid.
Subsequent calls to add mark on the same object are expected to pass the
same fsid, so the call will fail on cached fsid mismatch.
If an event is reported on several mark types (inode, mount, filesystem),
all connectors should already have the same fsid, so we use the cached
fsid from the first connector.
[JK: Simplify code flow around fanotify_get_fid()
make fsid argument of fsnotify_add_mark_locked() unconditional]
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
When setting up an fanotify listener, user may request to get fid
information in event instead of an open file descriptor.
The fid obtained with event on a watched object contains the file
handle returned by name_to_handle_at(2) and fsid returned by statfs(2).
Restrict FAN_REPORT_FID to class FAN_CLASS_NOTIF, because we have have
no good reason to support reporting fid on permission events.
When setting a mark, we need to make sure that the filesystem
supports encoding file handles with name_to_handle_at(2) and that
statfs(2) encodes a non-zero fsid.
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
If group requested FAN_REPORT_FID and event has file identifier,
copy that information to user reading the event after event metadata.
fid information is formatted as struct fanotify_event_info_fid
that includes a generic header struct fanotify_event_info_header,
so that other info types could be defined in the future using the
same header.
metadata->event_len includes the length of the fid information.
The fid information includes the filesystem's fsid (see statfs(2))
followed by an NFS file handle of the file that could be passed as
an argument to open_by_handle_at(2).
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
When user requests the flag FAN_REPORT_FID in fanotify_init(),
a unique file identifier of the event target object will be reported
with the event.
The file identifier includes the filesystem's fsid (i.e. from statfs(2))
and an NFS file handle of the file (i.e. from name_to_handle_at(2)).
The file identifier makes holding the path reference and passing a file
descriptor to user redundant, so those are disabled in a group with
FAN_REPORT_FID.
Encode fid and store it in event for a group with FAN_REPORT_FID.
Up to 12 bytes of file handle on 32bit arch (16 bytes on 64bit arch)
are stored inline in fanotify_event struct. Larger file handles are
stored in an external allocated buffer.
On failure to encode fid, we print a warning and queue the event
without the fid information.
[JK: Fold part of later patched into this one to use
exportfs_encode_inode_fh() right away]
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
The helper is quite trivial and open coding it will make it easier
to implement copying event fid info to user.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
struct fanotify_event_info "inherits" from struct fsnotify_event and
therefore a more appropriate (and short) name for it is fanotify_event.
Same for struct fanotify_perm_event_info, which now "inherits" from
struct fanotify_event.
We plan to reuse the name struct fanotify_event_info for user visible
event info record format.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Common fsnotify_event helpers have no need for the mask field.
It is only used by backend code, so move the field out of the
abstract fsnotify_event struct and into the concrete backend
event structs.
This change packs struct inotify_event_info better on 64bit
machine and will allow us to cram some more fields into
struct fanotify_event_info.
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Use the aptly named function rather than opencoding i_writecount check.
No functional changes.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Jan Kara <jack@suse.cz>
As a precaution, make sure we check event_len when copying to userspace.
Based on old feedback: https://lkml.kernel.org/r/542D9FE5.3010009@gmx.de
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jan Kara <jack@suse.cz>
A new event mask FAN_OPEN_EXEC_PERM has been defined. This allows users
to receive events and grant access to files that are intending to be
opened for execution. Events of FAN_OPEN_EXEC_PERM type will be
generated when a file has been opened by using either execve(),
execveat() or uselib() system calls.
This acts in the same manner as previous permission event mask, meaning
that an access response is required from the user application in order
to permit any further operations on the file.
Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Amir Goldstein