fanotify: send FAN_DIR_MODIFY event flavor with dir inode and name

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/[email protected]
Signed-off-by: Amir Goldstein <[email protected]>
Signed-off-by: Jan Kara <[email protected]>

Author: amir73il

fs/notify/fanotify/fanotify.c

@@ -235,9 +235,9 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 	test_mask = event_mask & marks_mask & ~marks_ignored_mask;
 
 	/*
-	 * 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.
+	 * For dirent modification events (create/delete/move) that do not carry
+	 * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
+	 * so user can differentiate them from creat/unlink.
 	 *
 	 * For backward compatibility and consistency, do not report FAN_ONDIR
 	 * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
@@ -463,6 +463,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
 	BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
 	BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
+	BUILD_BUG_ON(FAN_DIR_MODIFY != FS_DIR_MODIFY);
 	BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
 	BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
 	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);

fs/notify/fsnotify.c

@@ -383,7 +383,7 @@ static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)

include/linux/fsnotify.h

@@ -30,6 +30,12 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask,
 				 const struct qstr *name, u32 cookie)
 {
 	fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie);
+	/*
+	 * Send another flavor of the event without child inode data and
+	 * without the specific event type (e.g. FS_CREATE|FS_IS_DIR).
+	 * The name is relative to the dir inode the event is reported to.
+	 */
+	fsnotify(dir, FS_DIR_MODIFY, dir, FSNOTIFY_EVENT_INODE, name, 0);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,

include/linux/fsnotify_backend.h

@@ -47,6 +47,7 @@
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
+#define FS_DIR_MODIFY		0x00080000	/* Directory entry was modified */
 
 #define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
 /* This inode cares about things that happen to its children.  Always set for
@@ -66,7 +67,8 @@
  * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event
  * when a directory entry inside a child subdir changes.
  */
-#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE)
+#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE | \
+					 FS_DIR_MODIFY)
 
 #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
 				  FS_OPEN_EXEC_PERM)

include/uapi/linux/fanotify.h

@@ -24,6 +24,7 @@
 #define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
 #define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
 #define FAN_OPEN_EXEC_PERM	0x00040000	/* File open/exec in perm check */
+#define FAN_DIR_MODIFY		0x00080000	/* Directory entry was modified */
 
 #define FAN_EVENT_ON_CHILD	0x08000000	/* Interested in child events */