fsnotify: opt-in for permission events at file open time

Legacy inotify/fanotify listeners can add watches for events on inode,
parent or mount and expect to get events (e.g. FS_MODIFY) on files that
were already open at the time of setting up the watches.

fanotify permission events are typically used by Anti-malware sofware,
that is watching the entire mount and it is not common to have more that
one Anti-malware engine installed on a system.

To reduce the overhead of the fsnotify_file_perm() hooks on every file
access, relax the semantics of the legacy FAN_ACCESS_PERM event to generate
events only if there were *any* permission event listeners on the
filesystem at the time that the file was opened.

The new semantic is implemented by extending the FMODE_NONOTIFY bit into
two FMODE_NONOTIFY_* bits, that are used to store a mode for which of the
events types to report.

This is going to apply to the new fanotify pre-content events in order
to reduce the cost of the new pre-content event vfs hooks.

[Thanks to Bert Karwatzki <spasswolf@web.de> for reporting a bug in this
code with CONFIG_FANOTIFY_ACCESS_PERMISSIONS disabled]

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wj8L=mtcRTi=NECHMGfZQgXOp_uix1YVh04fEmrKaMnXA@mail.gmail.com/
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/5ea5f8e283d1edb55aa79c35187bfe344056af14.1731684329.git.josef@toxicpanda.com
This commit is contained in:
Amir Goldstein 2024-11-15 10:30:15 -05:00 committed by Jan Kara
parent ebe559609d
commit a94204f4d4
4 changed files with 106 additions and 22 deletions

View file

@ -623,6 +623,44 @@ out:
}
EXPORT_SYMBOL_GPL(fsnotify);
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
/*
* At open time we check fsnotify_sb_has_priority_watchers() and set the
* FMODE_NONOTIFY_ mode bits accordignly.
* Later, fsnotify permission hooks do not check if there are permission event
* watches, but that there were permission event watches at open time.
*/
void file_set_fsnotify_mode(struct file *file)
{
struct super_block *sb = file->f_path.dentry->d_sb;
/* Is it a file opened by fanotify? */
if (FMODE_FSNOTIFY_NONE(file->f_mode))
return;
/*
* Permission events is a super set of pre-content events, so if there
* are no permission event watchers, there are also no pre-content event
* watchers and this is implied from the single FMODE_NONOTIFY_PERM bit.
*/
if (likely(!fsnotify_sb_has_priority_watchers(sb,
FSNOTIFY_PRIO_CONTENT))) {
file->f_mode |= FMODE_NONOTIFY_PERM;
return;
}
/*
* If there are permission event watchers but no pre-content event
* watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
*/
if (likely(!fsnotify_sb_has_priority_watchers(sb,
FSNOTIFY_PRIO_PRE_CONTENT))) {
file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
return;
}
}
#endif
static __init int fsnotify_init(void)
{
int ret;

View file

@ -901,7 +901,7 @@ static int do_dentry_open(struct file *f,
f->f_sb_err = file_sample_sb_err(f);
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY;
f->f_op = &empty_fops;
return 0;
}
@ -929,6 +929,12 @@ static int do_dentry_open(struct file *f,
if (error)
goto cleanup_all;
/*
* Set FMODE_NONOTIFY_* bits according to existing permission watches.
* If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't
* change anything.
*/
file_set_fsnotify_mode(f);
error = fsnotify_open_perm(f);
if (error)
goto cleanup_all;

View file

@ -173,13 +173,20 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
#define FMODE_NOREUSE ((__force fmode_t)(1 << 23))
/* FMODE_* bit 24 */
/* File is embedded in backing_file object */
#define FMODE_BACKING ((__force fmode_t)(1 << 25))
#define FMODE_BACKING ((__force fmode_t)(1 << 24))
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26))
/*
* Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be
* generated (see below)
*/
#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25))
/*
* Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be
* generated (see below)
*/
#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26))
/* File is capable of returning -EAGAIN if I/O will block */
#define FMODE_NOWAIT ((__force fmode_t)(1 << 27))
@ -190,6 +197,32 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/* File does not contribute to nr_files count */
#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29))
/*
* The two FMODE_NONOTIFY* define which fsnotify events should not be generated
* for a file. These are the possible values of (f->f_mode &
* FMODE_FSNOTIFY_MASK) and their meaning:
*
* FMODE_NONOTIFY - suppress all (incl. non-permission) events.
* FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events.
* FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events.
*/
#define FMODE_FSNOTIFY_MASK \
(FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)
#define FMODE_FSNOTIFY_NONE(mode) \
((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY)
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
#define FMODE_FSNOTIFY_PERM(mode) \
((mode & FMODE_FSNOTIFY_MASK) == 0 || \
(mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM))
#define FMODE_FSNOTIFY_HSM(mode) \
((mode & FMODE_FSNOTIFY_MASK) == 0)
#else
#define FMODE_FSNOTIFY_PERM(mode) 0
#define FMODE_FSNOTIFY_HSM(mode) 0
#endif
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!

View file

@ -108,38 +108,35 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
}
static inline int fsnotify_path(const struct path *path, __u32 mask)
{
return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
}
static inline int fsnotify_file(struct file *file, __u32 mask)
{
const struct path *path;
/*
* FMODE_NONOTIFY are fds generated by fanotify itself which should not
* generate new events. We also don't want to generate events for
* FMODE_PATH fds (involves open & close events) as they are just
* handle creation / destruction events and not "real" file events.
*/
if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH))
if (FMODE_FSNOTIFY_NONE(file->f_mode))
return 0;
path = &file->f_path;
/* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */
if (mask & ALL_FSNOTIFY_PERM_EVENTS &&
!fsnotify_sb_has_priority_watchers(path->dentry->d_sb,
FSNOTIFY_PRIO_CONTENT))
return 0;
return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
return fsnotify_path(&file->f_path, mask);
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
void file_set_fsnotify_mode(struct file *file);
/*
* fsnotify_file_area_perm - permission hook before access to file range
*/
static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
const loff_t *ppos, size_t count)
{
__u32 fsnotify_mask = FS_ACCESS_PERM;
/*
* filesystem may be modified in the context of permission events
* (e.g. by HSM filling a file on access), so sb freeze protection
@ -150,7 +147,10 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
if (!(perm_mask & MAY_READ))
return 0;
return fsnotify_file(file, fsnotify_mask);
if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
return 0;
return fsnotify_path(&file->f_path, FS_ACCESS_PERM);
}
/*
@ -168,16 +168,23 @@ static inline int fsnotify_open_perm(struct file *file)
{
int ret;
if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
return 0;
if (file->f_flags & __FMODE_EXEC) {
ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
if (ret)
return ret;
}
return fsnotify_file(file, FS_OPEN_PERM);
return fsnotify_path(&file->f_path, FS_OPEN_PERM);
}
#else
static inline void file_set_fsnotify_mode(struct file *file)
{
}
static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
const loff_t *ppos, size_t count)
{