Merge tag 'for_v4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "Amir's patches to implement superblock fanotify watches, Xiaoming's
  patch to enable reporting of thread IDs in fanotify events instead of
  TGIDs (sadly the patch got mis-attributed to Amir and I've noticed
  only now), and a fix of possible oops on umount caused by fsnotify
  infrastructure"

* tag 'for_v4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  fsnotify: Fix busy inodes during unmount
  fs: group frequently accessed fields of struct super_block together
  fanotify: support reporting thread id instead of process id
  fanotify: add BUILD_BUG_ON() to count the bits of fanotify constants
  fsnotify: convert runtime BUG_ON() to BUILD_BUG_ON()
  fanotify: deprecate uapi FAN_ALL_* constants
  fanotify: simplify handling of FAN_ONDIR
  fsnotify: generalize handling of extra event flags
  fanotify: fix collision of internal and uapi mark flags
  fanotify: store fanotify_init() flags in group's fanotify_data
  fanotify: add API to attach/detach super block mark
  fsnotify: send path type events to group with super block marks
  fsnotify: add super block object type

4 files changed, 115 insertions, 21 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 096c96f4f16a..a5a60691e48b 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -4,6 +4,61 @@
 
 #include <uapi/linux/fanotify.h>
 
-/* not valid from userspace, only kernel internal */
-#define FAN_MARK_ONDIR		0x00000100
+#define FAN_GROUP_FLAG(group, flag) \
+	((group)->fanotify_data.flags & (flag))
+
+/*
+ * Flags allowed to be passed from/to userspace.
+ *
+ * We intentionally do not add new bits to the old FAN_ALL_* constants, because
+ * they are uapi exposed constants. If there are programs out there using
+ * these constant, the programs may break if re-compiled with new uapi headers
+ * and then run on an old kernel.
+ */
+#define FANOTIFY_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
+				 FAN_CLASS_PRE_CONTENT)
+
+#define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | \
+				 FAN_REPORT_TID | \
+				 FAN_CLOEXEC | FAN_NONBLOCK | \
+				 FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS)
+
+#define FANOTIFY_MARK_TYPE_BITS	(FAN_MARK_INODE | FAN_MARK_MOUNT | \
+				 FAN_MARK_FILESYSTEM)
+
+#define FANOTIFY_MARK_FLAGS	(FANOTIFY_MARK_TYPE_BITS | \
+				 FAN_MARK_ADD | \
+				 FAN_MARK_REMOVE | \
+				 FAN_MARK_DONT_FOLLOW | \
+				 FAN_MARK_ONLYDIR | \
+				 FAN_MARK_IGNORED_MASK | \
+				 FAN_MARK_IGNORED_SURV_MODIFY | \
+				 FAN_MARK_FLUSH)
+
+/* Events that user can request to be notified on */
+#define FANOTIFY_EVENTS		(FAN_ACCESS | FAN_MODIFY | \
+				 FAN_CLOSE | FAN_OPEN)
+
+/* Events that require a permission response from user */
+#define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM)
+
+/* Extra flags that may be reported with event or control handling of events */
+#define FANOTIFY_EVENT_FLAGS	(FAN_EVENT_ON_CHILD | FAN_ONDIR)
+
+/* Events that may be reported to user */
+#define FANOTIFY_OUTGOING_EVENTS	(FANOTIFY_EVENTS | \
+					 FANOTIFY_PERM_EVENTS | \
+					 FAN_Q_OVERFLOW)
+
+#define ALL_FANOTIFY_EVENT_BITS		(FANOTIFY_OUTGOING_EVENTS | \
+					 FANOTIFY_EVENT_FLAGS)
+
+/* Do not use these old uapi constants internally */
+#undef FAN_ALL_CLASS_BITS
+#undef FAN_ALL_INIT_FLAGS
+#undef FAN_ALL_MARK_FLAGS
+#undef FAN_ALL_EVENTS
+#undef FAN_ALL_PERM_EVENTS
+#undef FAN_ALL_OUTGOING_EVENTS
+
 #endif /* _LINUX_FANOTIFY_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 771341470bce..8252df30b9a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1412,17 +1412,26 @@ struct super_block {
 
 	struct sb_writers	s_writers;
 
+	/*
+	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
+	 * s_fsnotify_marks together for cache efficiency. They are frequently
+	 * accessed and rarely modified.
+	 */
+	void			*s_fs_info;	/* Filesystem private info */
+
+	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
+	u32			s_time_gran;
+#ifdef CONFIG_FSNOTIFY
+	__u32			s_fsnotify_mask;
+	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
+#endif
+
 	char			s_id[32];	/* Informational name */
 	uuid_t			s_uuid;		/* UUID */
 
-	void 			*s_fs_info;	/* Filesystem private info */
 	unsigned int		s_max_links;
 	fmode_t			s_mode;
 
-	/* Granularity of c/m/atime in ns.
-	   Cannot be worse than a second */
-	u32		   s_time_gran;
-
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
 	 * even looking at it. You had been warned.
@@ -1447,6 +1456,9 @@ struct super_block {
 	/* Number of inodes with nlink == 0 but still referenced */
 	atomic_long_t s_remove_count;
 
+	/* Pending fsnotify inode refs */
+	atomic_long_t s_fsnotify_inode_refs;
+
 	/* Being remounted read-only */
 	int s_readonly_remount;
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index b8f4182f42f1..135b973e44d1 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -68,15 +68,20 @@
 
 #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM)
 
+/* Events that can be reported to backends */
 #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_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \
+			     FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME)
+
+/* Extra flags that may be reported with event or control handling of events */
+#define ALL_FSNOTIFY_FLAGS  (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \
 			     FS_DN_MULTISHOT | FS_EVENT_ON_CHILD)
 
+#define ALL_FSNOTIFY_BITS   (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS)
+
 struct fsnotify_group;
 struct fsnotify_event;
 struct fsnotify_mark;
@@ -189,10 +194,10 @@ struct fsnotify_group {
 			/* allows a group to block waiting for a userspace response */
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
-			int f_flags;
+			int flags;           /* flags from fanotify_init() */
+			int f_flags; /* event_f_flags from fanotify_init() */
 			unsigned int max_marks;
 			struct user_struct *user;
-			bool audit;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
@@ -206,12 +211,14 @@ struct fsnotify_group {
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
 	FSNOTIFY_OBJ_TYPE_VFSMOUNT,
+	FSNOTIFY_OBJ_TYPE_SB,
 	FSNOTIFY_OBJ_TYPE_COUNT,
 	FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT
 };
 
 #define FSNOTIFY_OBJ_TYPE_INODE_FL	(1U << FSNOTIFY_OBJ_TYPE_INODE)
 #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL	(1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+#define FSNOTIFY_OBJ_TYPE_SB_FL		(1U << FSNOTIFY_OBJ_TYPE_SB)
 #define FSNOTIFY_OBJ_ALL_TYPES_MASK	((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1)
 
 static inline bool fsnotify_valid_obj_type(unsigned int type)
@@ -255,6 +262,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
 
 FSNOTIFY_ITER_FUNCS(inode, INODE)
 FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT)
+FSNOTIFY_ITER_FUNCS(sb, SB)
 
 #define fsnotify_foreach_obj_type(type) \
 	for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++)
@@ -267,8 +275,8 @@ struct fsnotify_mark_connector;
 typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
 
 /*
- * Inode / vfsmount point to this structure which tracks all marks attached to
- * the inode / vfsmount. The reference to inode / vfsmount is held by this
+ * Inode/vfsmount/sb point to this structure which tracks all marks attached to
+ * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this
  * structure. We destroy this structure when there are no more marks attached
  * to it. The structure is protected by fsnotify_mark_srcu.
  */
@@ -335,6 +343,7 @@ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int dat
 extern int __fsnotify_parent(const 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 void fsnotify_sb_delete(struct super_block *sb);
 extern u32 fsnotify_get_cookie(void);
 
 static inline int fsnotify_inode_watches_children(struct inode *inode)
@@ -455,9 +464,13 @@ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *gr
 {
 	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL);
 }
+/* run all the marks in a group, and clear all of the sn marks */
+static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
+{
+	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL);
+}
 extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
-extern void fsnotify_unmount_inodes(struct super_block *sb);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
 
@@ -484,6 +497,9 @@ static inline void __fsnotify_inode_delete(struct inode *inode)
 static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
 {}
 
+static inline void fsnotify_sb_delete(struct super_block *sb)
+{}
+
 static inline void fsnotify_update_flags(struct dentry *dentry)
 {}
 
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index 74247917de04..b86740d1c50a 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -27,10 +27,12 @@
 #define FAN_CLOEXEC		0x00000001
 #define FAN_NONBLOCK		0x00000002
 
-/* These are NOT bitwise flags.  Both bits are used togther.  */
+/* These are NOT bitwise flags.  Both bits are used together.  */
 #define FAN_CLASS_NOTIF		0x00000000
 #define FAN_CLASS_CONTENT	0x00000004
 #define FAN_CLASS_PRE_CONTENT	0x00000008
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_CLASS_BITS	(FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
 				 FAN_CLASS_PRE_CONTENT)
 
@@ -38,6 +40,10 @@
 #define FAN_UNLIMITED_MARKS	0x00000020
 #define FAN_ENABLE_AUDIT	0x00000040
 
+/* Flags to determine fanotify event format */
+#define FAN_REPORT_TID		0x00000100	/* event->pid is thread id */
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
 				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
 				 FAN_UNLIMITED_MARKS)
@@ -47,11 +53,18 @@
 #define FAN_MARK_REMOVE		0x00000002
 #define FAN_MARK_DONT_FOLLOW	0x00000004
 #define FAN_MARK_ONLYDIR	0x00000008
-#define FAN_MARK_MOUNT		0x00000010
+/* FAN_MARK_MOUNT is		0x00000010 */
 #define FAN_MARK_IGNORED_MASK	0x00000020
 #define FAN_MARK_IGNORED_SURV_MODIFY	0x00000040
 #define FAN_MARK_FLUSH		0x00000080
+/* FAN_MARK_FILESYSTEM is	0x00000100 */
 
+/* These are NOT bitwise flags.  Both bits can be used togther.  */
+#define FAN_MARK_INODE		0x00000000
+#define FAN_MARK_MOUNT		0x00000010
+#define FAN_MARK_FILESYSTEM	0x00000100
+
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_MARK_FLAGS	(FAN_MARK_ADD |\
 				 FAN_MARK_REMOVE |\
 				 FAN_MARK_DONT_FOLLOW |\
@@ -61,11 +74,7 @@
 				 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
- * the future and not break backward compatibility.  Apps will get only the
- * events that they originally wanted.  Be sure to add new events here!
- */
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_EVENTS (FAN_ACCESS |\
 			FAN_MODIFY |\
 			FAN_CLOSE |\
@@ -74,9 +83,11 @@
 /*
  * All events which require a permission response from userspace
  */
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\
 			     FAN_ACCESS_PERM)
 
+/* Deprecated - do not use this in programs and do not add new flags here! */
 #define FAN_ALL_OUTGOING_EVENTS	(FAN_ALL_EVENTS |\
 				 FAN_ALL_PERM_EVENTS |\
 				 FAN_Q_OVERFLOW)