Merge branch 'for-linus' of git://git.infradead.org/users/eparis/notify

* 'for-linus' of git://git.infradead.org/users/eparis/notify: (22 commits)
  Ensure FMODE_NONOTIFY is not set by userspace
  make fanotify_read() restartable across signals
  fsnotify: remove alignment padding from fsnotify_mark on 64 bit builds
  fs/notify/fanotify/fanotify_user.c: fix warnings
  fanotify: Fix FAN_CLOSE comments
  fanotify: do not recalculate the mask if the ignored mask changed
  fanotify: ignore events on directories unless specifically requested
  fsnotify: rename FS_IN_ISDIR to FS_ISDIR
  fanotify: do not send events for irregular files
  fanotify: limit number of listeners per user
  fanotify: allow userspace to override max marks
  fanotify: limit the number of marks in a single fanotify group
  fanotify: allow userspace to override max queue depth
  fsnotify: implement a default maximum queue depth
  fanotify: ignore fanotify ignore marks if open writers
  fanotify: allow userspace to flush all marks
  fsnotify: call fsnotify_parent in perm events
  fsnotify: correctly handle return codes from listeners
  fanotify: use __aligned_u64 in fanotify userspace metadata
  fanotify: implement fanotify listener ordering
  ...

include/linux/Kbuild

@@ -118,6 +118,7 @@ header-y += eventpoll.h
 header-y += ext2_fs.h
 header-y += fadvise.h
 header-y += falloc.h
+header-y += fanotify.h
 header-y += fb.h
 header-y += fcntl.h
 header-y += fd.h

include/linux/fanotify.h

@@ -6,18 +6,19 @@
 /* the following events that user-space can register for */
 #define FAN_ACCESS		0x00000001	/* File was accessed */
 #define FAN_MODIFY		0x00000002	/* File was modified */
-#define FAN_CLOSE_WRITE		0x00000008	/* Unwrittable file closed */
-#define FAN_CLOSE_NOWRITE	0x00000010	/* Writtable file closed */
+#define FAN_CLOSE_WRITE		0x00000008	/* Writtable file closed */
+#define FAN_CLOSE_NOWRITE	0x00000010	/* Unwrittable file closed */
 #define FAN_OPEN		0x00000020	/* File was opened */
 
-#define FAN_EVENT_ON_CHILD	0x08000000	/* interested in child events */
-
-/* FIXME currently Q's have no limit.... */
 #define FAN_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
 
 #define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
 #define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
 
+#define FAN_ONDIR		0x40000000	/* event occurred against dir */
+
+#define FAN_EVENT_ON_CHILD	0x08000000	/* interested in child events */
+
 /* helper events */
 #define FAN_CLOSE		(FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */
 
@@ -25,7 +26,19 @@
 #define FAN_CLOEXEC		0x00000001
 #define FAN_NONBLOCK		0x00000002
 
-#define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK)
+/* These are NOT bitwise flags.  Both bits are used togther.  */
+#define FAN_CLASS_NOTIF		0x00000000
+#define FAN_CLASS_CONTENT	0x00000004
+#define FAN_CLASS_PRE_CONTENT	0x00000008
+#define FAN_ALL_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
+				 FAN_CLASS_PRE_CONTENT)
+
+#define FAN_UNLIMITED_QUEUE	0x00000010
+#define FAN_UNLIMITED_MARKS	0x00000020
+
+#define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
+				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
+				 FAN_UNLIMITED_MARKS)
 
 /* flags used for fanotify_modify_mark() */
 #define FAN_MARK_ADD		0x00000001
@@ -36,6 +49,10 @@
 #define FAN_MARK_IGNORED_MASK	0x00000020
 #define FAN_MARK_IGNORED_SURV_MODIFY	0x00000040
 #define FAN_MARK_FLUSH		0x00000080
+#ifdef __KERNEL__
+/* not valid from userspace, only kernel internal */
+#define FAN_MARK_ONDIR		0x00000100
+#endif
 
 #define FAN_ALL_MARK_FLAGS	(FAN_MARK_ADD |\
 				 FAN_MARK_REMOVE |\
@@ -43,7 +60,8 @@
 				 FAN_MARK_ONLYDIR |\
 				 FAN_MARK_MOUNT |\
 				 FAN_MARK_IGNORED_MASK |\
-				 FAN_MARK_IGNORED_SURV_MODIFY)
+				 FAN_MARK_IGNORED_SURV_MODIFY |\
+				 FAN_MARK_FLUSH)
 
 /*
  * All of the events - we build the list by hand so that we can add flags in
@@ -70,10 +88,10 @@
 struct fanotify_event_metadata {
 	__u32 event_len;
 	__u32 vers;
-	__u64 mask;
+	__aligned_u64 mask;
 	__s32 fd;
 	__s32 pid;
-} __attribute__ ((packed));
+};
 
 struct fanotify_response {
 	__s32 fd;

include/linux/fsnotify.h

@@ -26,12 +26,12 @@ static inline void fsnotify_d_instantiate(struct dentry *dentry,
 }
 
 /* Notify this dentry's parent about a child's events. */
-static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
+static inline int fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 {
 	if (!dentry)
 		dentry = path->dentry;
 
-	__fsnotify_parent(path, dentry, mask);
+	return __fsnotify_parent(path, dentry, mask);
 }
 
 /* simple call site for access decisions */
@@ -40,6 +40,7 @@ static inline int fsnotify_perm(struct file *file, int mask)
 	struct path *path = &file->f_path;
 	struct inode *inode = path->dentry->d_inode;
 	__u32 fsnotify_mask = 0;
+	int ret;
 
 	if (file->f_mode & FMODE_NONOTIFY)
 		return 0;
@@ -52,6 +53,10 @@ static inline int fsnotify_perm(struct file *file, int mask)
 	else
 		BUG();
 
+	ret = fsnotify_parent(path, NULL, fsnotify_mask);
+	if (ret)
+		return ret;
+
 	return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
 
@@ -93,8 +98,8 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		old_dir_mask |= FS_DN_RENAME;
 
 	if (isdir) {
-		old_dir_mask |= FS_IN_ISDIR;
-		new_dir_mask |= FS_IN_ISDIR;
+		old_dir_mask |= FS_ISDIR;
+		new_dir_mask |= FS_ISDIR;
 	}
 
 	fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
@@ -132,7 +137,7 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 	__u32 mask = FS_DELETE;
 
 	if (isdir)
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
 	fsnotify_parent(NULL, dentry, mask);
 }
@@ -174,7 +179,7 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
  */
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
-	__u32 mask = (FS_CREATE | FS_IN_ISDIR);
+	__u32 mask = (FS_CREATE | FS_ISDIR);
 	struct inode *d_inode = dentry->d_inode;
 
 	audit_inode_child(dentry, inode);
@@ -192,7 +197,7 @@ static inline void fsnotify_access(struct file *file)
 	__u32 mask = FS_ACCESS;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
 	if (!(file->f_mode & FMODE_NONOTIFY)) {
 		fsnotify_parent(path, NULL, mask);
@@ -210,7 +215,7 @@ static inline void fsnotify_modify(struct file *file)
 	__u32 mask = FS_MODIFY;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
 	if (!(file->f_mode & FMODE_NONOTIFY)) {
 		fsnotify_parent(path, NULL, mask);
@@ -228,12 +233,13 @@ static inline void fsnotify_open(struct file *file)
 	__u32 mask = FS_OPEN;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
-	if (!(file->f_mode & FMODE_NONOTIFY)) {
-		fsnotify_parent(path, NULL, mask);
-		fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
-	}
+	/* FMODE_NONOTIFY must never be set from user */
+	file->f_mode &= ~FMODE_NONOTIFY;
+
+	fsnotify_parent(path, NULL, mask);
+	fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
 
 /*
@@ -247,7 +253,7 @@ static inline void fsnotify_close(struct file *file)
 	__u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
 	if (!(file->f_mode & FMODE_NONOTIFY)) {
 		fsnotify_parent(path, NULL, mask);
@@ -264,7 +270,7 @@ static inline void fsnotify_xattr(struct dentry *dentry)
 	__u32 mask = FS_ATTRIB;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= FS_IN_ISDIR;
+		mask |= FS_ISDIR;
 
 	fsnotify_parent(NULL, dentry, mask);
 	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
@@ -299,7 +305,7 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 
 	if (mask) {
 		if (S_ISDIR(inode->i_mode))
-			mask |= FS_IN_ISDIR;
+			mask |= FS_ISDIR;
 
 		fsnotify_parent(NULL, dentry, mask);
 		fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);

include/linux/fsnotify_backend.h

@@ -45,7 +45,7 @@
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 
 #define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
-#define FS_IN_ISDIR		0x40000000	/* event occurred against dir */
+#define FS_ISDIR		0x40000000	/* event occurred against dir */
 #define FS_IN_ONESHOT		0x80000000	/* only send event once */
 
 #define FS_DN_RENAME		0x10000000	/* file renamed */
@@ -64,13 +64,15 @@
 
 #define FS_MOVE			(FS_MOVED_FROM | FS_MOVED_TO)
 
+#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM)
+
 #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \
 			     FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \
 			     FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \
 			     FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \
 			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
 			     FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \
-			     FS_IN_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \
+			     FS_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \
 			     FS_DN_MULTISHOT | FS_EVENT_ON_CHILD)
 
 struct fsnotify_group;
@@ -129,6 +131,14 @@ struct fsnotify_group {
 	wait_queue_head_t notification_waitq;	/* read() on the notification file blocks on this waitq */
 	unsigned int q_len;			/* events on the queue */
 	unsigned int max_events;		/* maximum events allowed on the list */
+	/*
+	 * Valid fsnotify group priorities.  Events are send in order from highest
+	 * priority to lowest priority.  We default to the lowest priority.
+	 */
+	#define FS_PRIO_0	0 /* normal notifiers, no permissions */
+	#define FS_PRIO_1	1 /* fanotify content based access control */
+	#define FS_PRIO_2	2 /* fanotify pre-content access */
+	unsigned int priority;
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	spinlock_t mark_lock;		/* protect marks_list */
@@ -159,6 +169,8 @@ struct fsnotify_group {
 			bool bypass_perm; /* protected by access_mutex */
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
 			int f_flags;
+			unsigned int max_marks;
+			struct user_struct *user;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
@@ -275,8 +287,8 @@ struct fsnotify_mark {
 		struct fsnotify_inode_mark i;
 		struct fsnotify_vfsmount_mark m;
 	};
-	__u32 ignored_mask;		/* events types to ignore */
 	struct list_head free_g_list;	/* tmp list used when freeing this mark */
+	__u32 ignored_mask;		/* events types to ignore */
 #define FSNOTIFY_MARK_FLAG_INODE		0x01
 #define FSNOTIFY_MARK_FLAG_VFSMOUNT		0x02
 #define FSNOTIFY_MARK_FLAG_OBJECT_PINNED	0x04
@@ -294,7 +306,7 @@ struct fsnotify_mark {
 /* main fsnotify call to send events */
 extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 		    const unsigned char *name, u32 cookie);
-extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask);
+extern int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask);
 extern void __fsnotify_inode_delete(struct inode *inode);
 extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
 extern u32 fsnotify_get_cookie(void);
@@ -423,8 +435,10 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int da
 	return 0;
 }
 
-static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
-{}
+static inline int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
+{
+	return 0;
+}
 
 static inline void __fsnotify_inode_delete(struct inode *inode)
 {}

include/linux/sched.h

@@ -672,6 +672,9 @@ struct user_struct {
 	atomic_t inotify_watches; /* How many inotify watches does this user have? */
 	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
 #endif
+#ifdef CONFIG_FANOTIFY
+	atomic_t fanotify_listeners;
+#endif
 #ifdef CONFIG_EPOLL
 	atomic_t epoll_watches;	/* The number of file descriptors currently watched */
 #endif