[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20241121112218.8249-3-jack@suse.cz>
Date: Thu, 21 Nov 2024 12:22:01 +0100
From: Jan Kara <jack@...e.cz>
To: <linux-fsdevel@...r.kernel.org>
Cc: Amir Goldstein <amir73il@...il.com>,
Josef Bacik <josef@...icpanda.com>,
brauner@...nel.org,
Linus Torvalds <torvalds@...ux-foundation.org>,
Al Viro <viro@...IV.linux.org.uk>,
linux-xfs@...r.kernel.org,
linux-btrfs@...r.kernel.org,
linux-ext4@...r.kernel.org,
linux-mm@...ck.org,
Jan Kara <jack@...e.cz>
Subject: [PATCH 02/19] fsnotify: opt-in for permission events at file open time
From: Amir Goldstein <amir73il@...il.com>
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.
Suggested-by: Linus Torvalds <torvalds@...ux-foundation.org>
Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wj8L=mtcRTi=NECHMGfZQgXOp_uix1YVh04fEmrKaMnXA@mail.gmail.com/
Signed-off-by: Amir Goldstein <amir73il@...il.com>
Signed-off-by: Jan Kara <jack@...e.cz>
Link: https://patch.msgid.link/5ea5f8e283d1edb55aa79c35187bfe344056af14.1731684329.git.josef@toxicpanda.com
---
fs/notify/fsnotify.c | 38 ++++++++++++++++++++++++++++++++++++++
fs/open.c | 8 +++++++-
include/linux/fs.h | 37 ++++++++++++++++++++++++++++++++-----
include/linux/fsnotify.h | 39 +++++++++++++++++++++++----------------
4 files changed, 100 insertions(+), 22 deletions(-)
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index f976949d2634..569ec356e4ce 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -623,6 +623,44 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
}
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;
diff --git a/fs/open.c b/fs/open.c
index 480c3798da2a..9b1fa59d52bf 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -918,7 +918,7 @@ 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;
}
@@ -946,6 +946,12 @@ 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;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 24598d707578..6a170c2c5326 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -171,13 +171,20 @@ 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))
+
+/*
+ * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be
+ * generated (see below)
+ */
+#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25))
-/* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26))
+/*
+ * 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))
@@ -188,6 +195,26 @@ 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)
+#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)
+
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 278620e063ab..8d1849137a96 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -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_file(struct file *file, __u32 mask)
+static inline int fsnotify_path(const struct path *path, __u32 mask)
{
- const struct path *path;
+ return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+}
+static inline int fsnotify_file(struct file *file, __u32 mask)
+{
/*
* 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)
{
--
2.35.3
Powered by blists - more mailing lists