Merge tag 'fsnotify_for_v5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fanotify updates from Jan Kara:
 "Support for fanotify directory events and changes to make waiting for
  fanotify permission event response killable"

* tag 'fsnotify_for_v5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (25 commits)
  fanotify: Make waits for fanotify events only killable
  fanotify: Use interruptible wait when waiting for permission events
  fanotify: Track permission event state
  fanotify: Simplify cleaning of access_list
  fsnotify: Create function to remove event from notification list
  fanotify: Move locking inside get_one_event()
  fanotify: Fold dequeue_event() into process_access_response()
  fanotify: Select EXPORTFS
  fanotify: report FAN_ONDIR to listener with FAN_REPORT_FID
  fanotify: add support for create/attrib/move/delete events
  fanotify: support events with data type FSNOTIFY_EVENT_INODE
  fanotify: check FS_ISDIR flag instead of d_is_dir()
  fsnotify: report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events
  fanotify: use vfs_get_fsid() helper instead of vfs_statfs()
  vfs: add vfs_get_fsid() helper
  fanotify: cache fsid in fsnotify_mark_connector
  fanotify: enable FAN_REPORT_FID init flag
  fanotify: copy event fid info to user
  fanotify: encode file identifier for FAN_REPORT_FID
  fanotify: open code fill_event_metadata()
  ...

4 files changed, 128 insertions, 41 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 9e2142795335..b79fa9bb7359 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -19,7 +19,7 @@
 				 FAN_CLASS_PRE_CONTENT)
 
 #define FANOTIFY_INIT_FLAGS	(FANOTIFY_CLASS_BITS | \
-				 FAN_REPORT_TID | \
+				 FAN_REPORT_TID | FAN_REPORT_FID | \
 				 FAN_CLOEXEC | FAN_NONBLOCK | \
 				 FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS)
 
@@ -35,10 +35,28 @@
 				 FAN_MARK_IGNORED_SURV_MODIFY | \
 				 FAN_MARK_FLUSH)
 
-/* Events that user can request to be notified on */
-#define FANOTIFY_EVENTS		(FAN_ACCESS | FAN_MODIFY | \
+/*
+ * Events that can be reported with data type FSNOTIFY_EVENT_PATH.
+ * Note that FAN_MODIFY can also be reported with data type
+ * FSNOTIFY_EVENT_INODE.
+ */
+#define FANOTIFY_PATH_EVENTS	(FAN_ACCESS | FAN_MODIFY | \
 				 FAN_CLOSE | FAN_OPEN | FAN_OPEN_EXEC)
 
+/*
+ * Directory entry modification events - reported only to directory
+ * where entry is modified and not to a watching parent.
+ */
+#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
+
+/* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
+#define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \
+				 FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF)
+
+/* Events that user can request to be notified on */
+#define FANOTIFY_EVENTS		(FANOTIFY_PATH_EVENTS | \
+				 FANOTIFY_INODE_EVENTS)
+
 /* Events that require a permission response from user */
 #define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM | \
 				 FAN_OPEN_EXEC_PERM)
@@ -49,7 +67,7 @@
 /* Events that may be reported to user */
 #define FANOTIFY_OUTGOING_EVENTS	(FANOTIFY_EVENTS | \
 					 FANOTIFY_PERM_EVENTS | \
-					 FAN_Q_OVERFLOW)
+					 FAN_Q_OVERFLOW | FAN_ONDIR)
 
 #define ALL_FANOTIFY_EVENT_BITS		(FANOTIFY_OUTGOING_EVENTS | \
 					 FANOTIFY_EVENT_FLAGS)
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 2ccb08cb5d6a..09587e2860b5 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -17,8 +17,22 @@
 #include <linux/slab.h>
 #include <linux/bug.h>
 
+/*
+ * Notify this @dir inode about a change in the directory entry @dentry.
+ *
+ * Unlike fsnotify_parent(), the event will be reported regardless of the
+ * FS_EVENT_ON_CHILD mask on the parent inode.
+ */
+static inline int fsnotify_dirent(struct inode *dir, struct dentry *dentry,
+				  __u32 mask)
+{
+	return fsnotify(dir, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE,
+			dentry->d_name.name, 0);
+}
+
 /* Notify this dentry's parent about a child's events. */
-static inline int fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
+static inline int fsnotify_parent(const struct path *path,
+				  struct dentry *dentry, __u32 mask)
 {
 	if (!dentry)
 		dentry = path->dentry;
@@ -65,6 +79,9 @@ static inline int fsnotify_perm(struct file *file, int mask)
 		fsnotify_mask = FS_ACCESS_PERM;
 	}
 
+	if (S_ISDIR(inode->i_mode))
+		fsnotify_mask |= FS_ISDIR;
+
 	return fsnotify_path(inode, path, fsnotify_mask);
 }
 
@@ -73,7 +90,12 @@ static inline int fsnotify_perm(struct file *file, int mask)
  */
 static inline void fsnotify_link_count(struct inode *inode)
 {
-	fsnotify(inode, FS_ATTRIB, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	__u32 mask = FS_ATTRIB;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -81,12 +103,14 @@ static inline void fsnotify_link_count(struct inode *inode)
  */
 static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 				 const unsigned char *old_name,
-				 int isdir, struct inode *target, struct dentry *moved)
+				 int isdir, struct inode *target,
+				 struct dentry *moved)
 {
 	struct inode *source = moved->d_inode;
 	u32 fs_cookie = fsnotify_get_cookie();
-	__u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM);
-	__u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO);
+	__u32 old_dir_mask = FS_MOVED_FROM;
+	__u32 new_dir_mask = FS_MOVED_TO;
+	__u32 mask = FS_MOVE_SELF;
 	const unsigned char *new_name = moved->d_name.name;
 
 	if (old_dir == new_dir)
@@ -95,6 +119,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 	if (isdir) {
 		old_dir_mask |= FS_ISDIR;
 		new_dir_mask |= FS_ISDIR;
+		mask |= FS_ISDIR;
 	}
 
 	fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name,
@@ -106,7 +131,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		fsnotify_link_count(target);
 
 	if (source)
-		fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+		fsnotify(source, mask, source, FSNOTIFY_EVENT_INODE, NULL, 0);
 	audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE);
 }
 
@@ -128,15 +153,35 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt)
 
 /*
  * fsnotify_nameremove - a filename was removed from a directory
+ *
+ * This is mostly called under parent vfs inode lock so name and
+ * dentry->d_parent should be stable. However there are some corner cases where
+ * inode lock is not held. So to be on the safe side and be reselient to future
+ * callers and out of tree users of d_delete(), we do not assume that d_parent
+ * and d_name are stable and we use dget_parent() and
+ * take_dentry_name_snapshot() to grab stable references.
  */
 static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 {
+	struct dentry *parent;
+	struct name_snapshot name;
 	__u32 mask = FS_DELETE;
 
+	/* d_delete() of pseudo inode? (e.g. __ns_get_path() playing tricks) */
+	if (IS_ROOT(dentry))
+		return;
+
 	if (isdir)
 		mask |= FS_ISDIR;
 
-	fsnotify_parent(NULL, dentry, mask);
+	parent = dget_parent(dentry);
+	take_dentry_name_snapshot(&name, dentry);
+
+	fsnotify(d_inode(parent), mask, d_inode(dentry), FSNOTIFY_EVENT_INODE,
+		 name.name, 0);
+
+	release_dentry_name_snapshot(&name);
+	dput(parent);
 }
 
 /*
@@ -144,7 +189,12 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
  */
 static inline void fsnotify_inoderemove(struct inode *inode)
 {
-	fsnotify(inode, FS_DELETE_SELF, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	__u32 mask = FS_DELETE_SELF;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 	__fsnotify_inode_delete(inode);
 }
 
@@ -155,7 +205,7 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
 	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
+	fsnotify_dirent(inode, dentry, FS_CREATE);
 }
 
 /*
@@ -176,12 +226,9 @@ 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_ISDIR);
-	struct inode *d_inode = dentry->d_inode;
-
 	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
+	fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR);
 }
 
 /*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 7639774e7475..dfc28fcb4de8 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -59,27 +59,33 @@
  * dnotify and inotify. */
 #define FS_EVENT_ON_CHILD	0x08000000
 
-/* This is a list of all events that may get sent to a parernt based on fs event
- * happening to inodes inside that directory */
-#define FS_EVENTS_POSS_ON_CHILD   (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_OPEN_PERM | FS_ACCESS_PERM | \
-				   FS_OPEN_EXEC | FS_OPEN_EXEC_PERM)
-
 #define FS_MOVE			(FS_MOVED_FROM | FS_MOVED_TO)
 
+/*
+ * Directory entry modification events - reported only to directory
+ * where entry is modified and not to a watching parent.
+ * 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_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
 				  FS_OPEN_EXEC_PERM)
 
+/*
+ * This is a list of all events that may get sent to a parent based on fs event
+ * happening to inodes inside that directory.
+ */
+#define FS_EVENTS_POSS_ON_CHILD   (ALL_FSNOTIFY_PERM_EVENTS | \
+				   FS_ACCESS | FS_MODIFY | FS_ATTRIB | \
+				   FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \
+				   FS_OPEN | FS_OPEN_EXEC)
+
 /* 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_DN_RENAME | \
-			     FS_OPEN_EXEC | FS_OPEN_EXEC_PERM)
+#define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
+			     FS_EVENTS_POSS_ON_CHILD | \
+			     FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \
+			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED)
 
 /* 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 | \
@@ -129,7 +135,6 @@ struct fsnotify_event {
 	struct list_head list;
 	/* inode may ONLY be dereferenced during handle_event(). */
 	struct inode *inode;	/* either the inode the event happened to or its parent */
-	u32 mask;		/* the type of access, bitwise OR for FS_* event types */
 };
 
 /*
@@ -288,6 +293,7 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
 struct fsnotify_mark_connector {
 	spinlock_t lock;
 	unsigned int type;	/* Type of object [lock] */
+	__kernel_fsid_t fsid;	/* fsid of filesystem containing object */
 	union {
 		/* Object pointer [lock] */
 		fsnotify_connp_t *obj;
@@ -416,6 +422,9 @@ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group);
 /* return AND dequeue the first event on the notification queue */
 extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group);
+/* Remove event queued in the notification list */
+extern void fsnotify_remove_queued_event(struct fsnotify_group *group,
+					 struct fsnotify_event *event);
 
 /* functions used to manipulate the marks attached to inodes */
 
@@ -428,28 +437,35 @@ extern void fsnotify_init_mark(struct fsnotify_mark *mark,
 /* Find mark belonging to given group in the list of marks */
 extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
 						struct fsnotify_group *group);
+/* Get cached fsid of filesystem containing object */
+extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn,
+				  __kernel_fsid_t *fsid);
 /* attach the mark to the object */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int type,
-			     int allow_dups);
+			     int allow_dups, __kernel_fsid_t *fsid);
 extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
-				    fsnotify_connp_t *connp, unsigned int type,
-				    int allow_dups);
+				    fsnotify_connp_t *connp,
+				    unsigned int type, int allow_dups,
+				    __kernel_fsid_t *fsid);
+
 /* attach the mark to the inode */
 static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 					  struct inode *inode,
 					  int allow_dups)
 {
 	return fsnotify_add_mark(mark, &inode->i_fsnotify_marks,
-				 FSNOTIFY_OBJ_TYPE_INODE, allow_dups);
+				 FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL);
 }
 static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
 						 struct inode *inode,
 						 int allow_dups)
 {
 	return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks,
-					FSNOTIFY_OBJ_TYPE_INODE, allow_dups);
+					FSNOTIFY_OBJ_TYPE_INODE, allow_dups,
+					NULL);
 }
+
 /* given a group and a mark, flag mark to be freed when all references are dropped */
 extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 				  struct fsnotify_group *group);
@@ -479,9 +495,12 @@ extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
 
-/* put here because inotify does some weird stuff when destroying watches */
-extern void fsnotify_init_event(struct fsnotify_event *event,
-				struct inode *to_tell, u32 mask);
+static inline void fsnotify_init_event(struct fsnotify_event *event,
+				       struct inode *inode)
+{
+	INIT_LIST_HEAD(&event->list);
+	event->inode = inode;
+}
 
 #else
 
diff --git a/include/linux/statfs.h b/include/linux/statfs.h
index 3142e98546ac..9bc69edb8f18 100644
--- a/include/linux/statfs.h
+++ b/include/linux/statfs.h
@@ -41,4 +41,7 @@ struct kstatfs {
 #define ST_NODIRATIME	0x0800	/* do not update directory access times */
 #define ST_RELATIME	0x1000	/* update atime relative to mtime/ctime */
 
+struct dentry;
+extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid);
+
 #endif