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

* 'for-linus' of git://git.infradead.org/users/eparis/notify:
  fsnotify: allow groups to set freeing_mark to null
  inotify/dnotify: should_send_event shouldn't match on FS_EVENT_ON_CHILD
  dnotify: do not bother to lock entry->lock when reading mask
  dnotify: do not use ?true:false when assigning to a bool
  fsnotify: move events should indicate the event was on a child
  inotify: reimplement inotify using fsnotify
  fsnotify: handle filesystem unmounts with fsnotify marks
  fsnotify: fsnotify marks on inodes pin them in core
  fsnotify: allow groups to add private data to events
  fsnotify: add correlations between events
  fsnotify: include pathnames with entries when possible
  fsnotify: generic notification queue and waitq
  dnotify: reimplement dnotify using fsnotify
  fsnotify: parent event notification
  fsnotify: add marks to inodes so groups can interpret how to handle those inodes
  fsnotify: unified filesystem notification backend

5 files changed, 521 insertions, 104 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 15156364d196..97978004338d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -180,10 +180,12 @@ d_iput:		no		no		no       yes
 #define DCACHE_REFERENCED       0x0008  /* Recently used, don't discard. */
 #define DCACHE_UNHASHED         0x0010  
 
-#define DCACHE_INOTIFY_PARENT_WATCHED   0x0020 /* Parent inode is watched */
+#define DCACHE_INOTIFY_PARENT_WATCHED   0x0020 /* Parent inode is watched by inotify */
 
 #define DCACHE_COOKIE           0x0040  /* For use by dcookie subsystem */
 
+#define DCACHE_FSNOTIFY_PARENT_WATCHED  0x0080 /* Parent inode is watched by some fsnotify listener */
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h
index 102a902b4396..ecc06286226d 100644
--- a/include/linux/dnotify.h
+++ b/include/linux/dnotify.h
@@ -10,7 +10,7 @@
 
 struct dnotify_struct {
         struct dnotify_struct * dn_next;
-        unsigned long           dn_mask;
+        __u32                   dn_mask;
         int                     dn_fd;
         struct file *           dn_filp;
         fl_owner_t              dn_owner;
@@ -21,23 +21,18 @@ struct dnotify_struct {
 
 #ifdef CONFIG_DNOTIFY
 
-extern void __inode_dir_notify(struct inode *, unsigned long);
+#define DNOTIFY_ALL_EVENTS (FS_DELETE | FS_DELETE_CHILD |\
+                            FS_MODIFY | FS_MODIFY_CHILD |\
+                            FS_ACCESS | FS_ACCESS_CHILD |\
+                            FS_ATTRIB | FS_ATTRIB_CHILD |\
+                            FS_CREATE | FS_DN_RENAME |\
+                            FS_MOVED_FROM | FS_MOVED_TO)
+
 extern void dnotify_flush(struct file *, fl_owner_t);
 extern int fcntl_dirnotify(int, struct file *, unsigned long);
-extern void dnotify_parent(struct dentry *, unsigned long);
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-        if (inode->i_dnotify_mask & (event))
-                __inode_dir_notify(inode, event);
-}
 
 #else
 
-static inline void __inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 static inline void dnotify_flush(struct file *filp, fl_owner_t id)
 {
 }
@@ -47,14 +42,6 @@ static inline int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
         return -EINVAL;
 }
 
-static inline void dnotify_parent(struct dentry *dentry, unsigned long event)
-{
-}
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 #endif /* CONFIG_DNOTIFY */
 
 #endif /* __KERNEL __ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 83d6b4397245..323b5ce474c1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -755,9 +755,9 @@ struct inode {
 
         __u32                   i_generation;
 
-#ifdef CONFIG_DNOTIFY
-        unsigned long           i_dnotify_mask; /* Directory notify events */
-        struct dnotify_struct   *i_dnotify; /* for directory notifications */
+#ifdef CONFIG_FSNOTIFY
+        __u32                   i_fsnotify_mask; /* all events this inode cares about */
+        struct hlist_head       i_fsnotify_mark_entries; /* fsnotify mark entries */
 #endif
 
 #ifdef CONFIG_INOTIFY
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 00fbd5b245c9..936f9aa8bb97 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -13,6 +13,7 @@
 
 #include <linux/dnotify.h>
 #include <linux/inotify.h>
+#include <linux/fsnotify_backend.h>
 #include <linux/audit.h>
 
 /*
@@ -22,19 +23,45 @@
 static inline void fsnotify_d_instantiate(struct dentry *entry,
                                                 struct inode *inode)
 {
+        __fsnotify_d_instantiate(entry, inode);
+
         inotify_d_instantiate(entry, inode);
 }
 
+/* Notify this dentry's parent about a child's events. */
+static inline void fsnotify_parent(struct dentry *dentry, __u32 mask)
+{
+        __fsnotify_parent(dentry, mask);
+
+        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+}
+
 /*
  * fsnotify_d_move - entry has been moved
  * Called with dcache_lock and entry->d_lock held.
  */
 static inline void fsnotify_d_move(struct dentry *entry)
 {
+        /*
+         * On move we need to update entry->d_flags to indicate if the new parent
+         * cares about events from this entry.
+         */
+        __fsnotify_update_dcache_flags(entry);
+
         inotify_d_move(entry);
 }
 
 /*
+ * fsnotify_link_count - inode's link count changed
+ */
+static inline void fsnotify_link_count(struct inode *inode)
+{
+        inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+
+        fsnotify(inode, FS_ATTRIB, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+/*
  * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir
  */
 static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
@@ -42,42 +69,62 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
                                  int isdir, struct inode *target, struct dentry *moved)
 {
         struct inode *source = moved->d_inode;
-        u32 cookie = inotify_get_cookie();
+        u32 in_cookie = inotify_get_cookie();
+        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);
 
         if (old_dir == new_dir)
-                inode_dir_notify(old_dir, DN_RENAME);
-        else {
-                inode_dir_notify(old_dir, DN_DELETE);
-                inode_dir_notify(new_dir, DN_CREATE);
-        }
+                old_dir_mask |= FS_DN_RENAME;
 
-        if (isdir)
+        if (isdir) {
                 isdir = IN_ISDIR;
-        inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name,
+                old_dir_mask |= FS_IN_ISDIR;
+                new_dir_mask |= FS_IN_ISDIR;
+        }
+
+        inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir, in_cookie, old_name,
                                   source);
-        inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name,
+        inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, in_cookie, new_name,
                                   source);
 
+        fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
+        fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+
         if (target) {
                 inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL, NULL);
                 inotify_inode_is_dead(target);
+
+                /* this is really a link_count change not a removal */
+                fsnotify_link_count(target);
         }
 
         if (source) {
                 inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL);
+                fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
         }
         audit_inode_child(new_name, moved, new_dir);
 }
 
 /*
+ * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed
+ */
+static inline void fsnotify_inode_delete(struct inode *inode)
+{
+        __fsnotify_inode_delete(inode);
+}
+
+/*
  * fsnotify_nameremove - a filename was removed from a directory
  */
 static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 {
+        __u32 mask = FS_DELETE;
+
         if (isdir)
-                isdir = IN_ISDIR;
-        dnotify_parent(dentry, DN_DELETE);
-        inotify_dentry_parent_queue_event(dentry, IN_DELETE|isdir, 0, dentry->d_name.name);
+                mask |= FS_IN_ISDIR;
+
+        fsnotify_parent(dentry, mask);
 }
 
 /*
@@ -87,14 +134,9 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 {
         inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL);
         inotify_inode_is_dead(inode);
-}
 
-/*
- * fsnotify_link_count - inode's link count changed
- */
-static inline void fsnotify_link_count(struct inode *inode)
-{
-        inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+        fsnotify(inode, FS_DELETE_SELF, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+        __fsnotify_inode_delete(inode);
 }
 
 /*
@@ -102,10 +144,11 @@ static inline void fsnotify_link_count(struct inode *inode)
  */
 static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
-        inode_dir_notify(inode, DN_CREATE);
         inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name,
                                   dentry->d_inode);
         audit_inode_child(dentry->d_name.name, dentry, inode);
+
+        fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -115,11 +158,12 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
  */
 static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry)
 {
-        inode_dir_notify(dir, DN_CREATE);
         inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name,
                                   inode);
         fsnotify_link_count(inode);
         audit_inode_child(new_dentry->d_name.name, new_dentry, dir);
+
+        fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, new_dentry->d_name.name, 0);
 }
 
 /*
@@ -127,10 +171,13 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
  */
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
-        inode_dir_notify(inode, DN_CREATE);
-        inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, 
-                                  dentry->d_name.name, dentry->d_inode);
+        __u32 mask = (FS_CREATE | FS_IN_ISDIR);
+        struct inode *d_inode = dentry->d_inode;
+
+        inotify_inode_queue_event(inode, mask, 0, dentry->d_name.name, d_inode);
         audit_inode_child(dentry->d_name.name, dentry, inode);
+
+        fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -139,14 +186,15 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 static inline void fsnotify_access(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_ACCESS;
+        __u32 mask = FS_ACCESS;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        dnotify_parent(dentry, DN_ACCESS);
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -155,14 +203,15 @@ static inline void fsnotify_access(struct dentry *dentry)
 static inline void fsnotify_modify(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_MODIFY;
+        __u32 mask = FS_MODIFY;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        dnotify_parent(dentry, DN_MODIFY);
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -171,13 +220,15 @@ static inline void fsnotify_modify(struct dentry *dentry)
 static inline void fsnotify_open(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_OPEN;
+        __u32 mask = FS_OPEN;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -187,15 +238,16 @@ static inline void fsnotify_close(struct file *file)
 {
         struct dentry *dentry = file->f_path.dentry;
         struct inode *inode = dentry->d_inode;
-        const char *name = dentry->d_name.name;
         fmode_t mode = file->f_mode;
-        u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
+        __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0);
 }
 
 /*
@@ -204,13 +256,15 @@ static inline void fsnotify_close(struct file *file)
 static inline void fsnotify_xattr(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_ATTRIB;
+        __u32 mask = FS_ATTRIB;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -220,50 +274,37 @@ static inline void fsnotify_xattr(struct dentry *dentry)
 static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 {
         struct inode *inode = dentry->d_inode;
-        int dn_mask = 0;
-        u32 in_mask = 0;
+        __u32 mask = 0;
+
+        if (ia_valid & ATTR_UID)
+                mask |= FS_ATTRIB;
+        if (ia_valid & ATTR_GID)
+                mask |= FS_ATTRIB;
+        if (ia_valid & ATTR_SIZE)
+                mask |= FS_MODIFY;
 
-        if (ia_valid & ATTR_UID) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
-        if (ia_valid & ATTR_GID) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
-        if (ia_valid & ATTR_SIZE) {
-                in_mask |= IN_MODIFY;
-                dn_mask |= DN_MODIFY;
-        }
         /* both times implies a utime(s) call */
         if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME))
-        {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        } else if (ia_valid & ATTR_ATIME) {
-                in_mask |= IN_ACCESS;
-                dn_mask |= DN_ACCESS;
-        } else if (ia_valid & ATTR_MTIME) {
-                in_mask |= IN_MODIFY;
-                dn_mask |= DN_MODIFY;
-        }
-        if (ia_valid & ATTR_MODE) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
+                mask |= FS_ATTRIB;
+        else if (ia_valid & ATTR_ATIME)
+                mask |= FS_ACCESS;
+        else if (ia_valid & ATTR_MTIME)
+                mask |= FS_MODIFY;
+
+        if (ia_valid & ATTR_MODE)
+                mask |= FS_ATTRIB;
 
-        if (dn_mask)
-                dnotify_parent(dentry, dn_mask);
-        if (in_mask) {
+        if (mask) {
                 if (S_ISDIR(inode->i_mode))
-                        in_mask |= IN_ISDIR;
-                inotify_inode_queue_event(inode, in_mask, 0, NULL, NULL);
-                inotify_dentry_parent_queue_event(dentry, in_mask, 0,
-                                                  dentry->d_name.name);
+                        mask |= FS_IN_ISDIR;
+                inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+                fsnotify_parent(dentry, mask);
+                fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
         }
 }
 
-#ifdef CONFIG_INOTIFY   /* inotify helpers */
+#if defined(CONFIG_INOTIFY) || defined(CONFIG_FSNOTIFY) /* notify helpers */
 
 /*
  * fsnotify_oldname_init - save off the old filename before we change it
@@ -281,7 +322,7 @@ static inline void fsnotify_oldname_free(const char *old_name)
         kfree(old_name);
 }
 
-#else   /* CONFIG_INOTIFY */
+#else   /* CONFIG_INOTIFY || CONFIG_FSNOTIFY */
 
 static inline const char *fsnotify_oldname_init(const char *name)
 {
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
new file mode 100644
index 000000000000..44848aa830dc
--- /dev/null
+++ b/include/linux/fsnotify_backend.h
@@ -0,0 +1,387 @@
+/*
+ * Filesystem access notification for Linux
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#ifndef __LINUX_FSNOTIFY_BACKEND_H
+#define __LINUX_FSNOTIFY_BACKEND_H
+
+#ifdef __KERNEL__
+
+#include <linux/idr.h> /* inotify uses this */
+#include <linux/fs.h> /* struct inode */
+#include <linux/list.h>
+#include <linux/path.h> /* struct path */
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/atomic.h>
+
+/*
+ * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
+ * convert between them.  dnotify only needs conversion at watch creation
+ * so no perf loss there.  fanotify isn't defined yet, so it can use the
+ * wholes if it needs more events.
+ */
+#define FS_ACCESS               0x00000001      /* File was accessed */
+#define FS_MODIFY               0x00000002      /* File was modified */
+#define FS_ATTRIB               0x00000004      /* Metadata changed */
+#define FS_CLOSE_WRITE          0x00000008      /* Writtable file was closed */
+#define FS_CLOSE_NOWRITE        0x00000010      /* Unwrittable file closed */
+#define FS_OPEN                 0x00000020      /* File was opened */
+#define FS_MOVED_FROM           0x00000040      /* File was moved from X */
+#define FS_MOVED_TO             0x00000080      /* File was moved to Y */
+#define FS_CREATE               0x00000100      /* Subfile was created */
+#define FS_DELETE               0x00000200      /* Subfile was deleted */
+#define FS_DELETE_SELF          0x00000400      /* Self was deleted */
+#define FS_MOVE_SELF            0x00000800      /* Self was moved */
+
+#define FS_UNMOUNT              0x00002000      /* inode on umount fs */
+#define FS_Q_OVERFLOW           0x00004000      /* Event queued overflowed */
+#define FS_IN_IGNORED           0x00008000      /* last inotify event here */
+
+#define FS_IN_ISDIR             0x40000000      /* event occurred against dir */
+#define FS_IN_ONESHOT           0x80000000      /* only send event once */
+
+#define FS_DN_RENAME            0x10000000      /* file renamed */
+#define FS_DN_MULTISHOT         0x20000000      /* dnotify multishot */
+
+/* This inode cares about things that happen to its children.  Always set for
+ * 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)
+
+/* listeners that hard code group numbers near the top */
+#define DNOTIFY_GROUP_NUM       UINT_MAX
+#define INOTIFY_GROUP_NUM       (DNOTIFY_GROUP_NUM-1)
+
+struct fsnotify_group;
+struct fsnotify_event;
+struct fsnotify_mark_entry;
+struct fsnotify_event_private_data;
+
+/*
+ * Each group much define these ops.  The fsnotify infrastructure will call
+ * these operations for each relevant group.
+ *
+ * should_send_event - given a group, inode, and mask this function determines
+ *              if the group is interested in this event.
+ * handle_event - main call for a group to handle an fs event
+ * free_group_priv - called when a group refcnt hits 0 to clean up the private union
+ * freeing-mark - this means that a mark has been flagged to die when everything
+ *              finishes using it.  The function is supplied with what must be a
+ *              valid group and inode to use to clean up.
+ */
+struct fsnotify_ops {
+        bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, __u32 mask);
+        int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event);
+        void (*free_group_priv)(struct fsnotify_group *group);
+        void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group);
+        void (*free_event_priv)(struct fsnotify_event_private_data *priv);
+};
+
+/*
+ * A group is a "thing" that wants to receive notification about filesystem
+ * events.  The mask holds the subset of event types this group cares about.
+ * refcnt on a group is up to the implementor and at any moment if it goes 0
+ * everything will be cleaned up.
+ */
+struct fsnotify_group {
+        /*
+         * global list of all groups receiving events from fsnotify.
+         * anchored by fsnotify_groups and protected by either fsnotify_grp_mutex
+         * or fsnotify_grp_srcu depending on write vs read.
+         */
+        struct list_head group_list;
+
+        /*
+         * Defines all of the event types in which this group is interested.
+         * This mask is a bitwise OR of the FS_* events from above.  Each time
+         * this mask changes for a group (if it changes) the correct functions
+         * must be called to update the global structures which indicate global
+         * interest in event types.
+         */
+        __u32 mask;
+
+        /*
+         * How the refcnt is used is up to each group.  When the refcnt hits 0
+         * fsnotify will clean up all of the resources associated with this group.
+         * As an example, the dnotify group will always have a refcnt=1 and that
+         * will never change.  Inotify, on the other hand, has a group per
+         * inotify_init() and the refcnt will hit 0 only when that fd has been
+         * closed.
+         */
+        atomic_t refcnt;                /* things with interest in this group */
+        unsigned int group_num;         /* simply prevents accidental group collision */
+
+        const struct fsnotify_ops *ops; /* how this group handles things */
+
+        /* needed to send notification to userspace */
+        struct mutex notification_mutex;        /* protect the notification_list */
+        struct list_head notification_list;     /* list of event_holder this group needs to send to userspace */
+        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 */
+
+        /* stores all fastapth entries assoc with this group so they can be cleaned on unregister */
+        spinlock_t mark_lock;           /* protect mark_entries list */
+        atomic_t num_marks;             /* 1 for each mark entry and 1 for not being
+                                         * past the point of no return when freeing
+                                         * a group */
+        struct list_head mark_entries;  /* all inode mark entries for this group */
+
+        /* prevents double list_del of group_list.  protected by global fsnotify_grp_mutex */
+        bool on_group_list;
+
+        /* groups can define private fields here or use the void *private */
+        union {
+                void *private;
+#ifdef CONFIG_INOTIFY_USER
+                struct inotify_group_private_data {
+                        spinlock_t      idr_lock;
+                        struct idr      idr;
+                        u32             last_wd;
+                        struct fasync_struct    *fa;    /* async notification */
+                        struct user_struct      *user;
+                } inotify_data;
+#endif
+        };
+};
+
+/*
+ * A single event can be queued in multiple group->notification_lists.
+ *
+ * each group->notification_list will point to an event_holder which in turns points
+ * to the actual event that needs to be sent to userspace.
+ *
+ * Seemed cheaper to create a refcnt'd event and a small holder for every group
+ * than create a different event for every group
+ *
+ */
+struct fsnotify_event_holder {
+        struct fsnotify_event *event;
+        struct list_head event_list;
+};
+
+/*
+ * Inotify needs to tack data onto an event.  This struct lets us later find the
+ * correct private data of the correct group.
+ */
+struct fsnotify_event_private_data {
+        struct fsnotify_group *group;
+        struct list_head event_list;
+};
+
+/*
+ * all of the information about the original object we want to now send to
+ * a group.  If you want to carry more info from the accessing task to the
+ * listener this structure is where you need to be adding fields.
+ */
+struct fsnotify_event {
+        /*
+         * If we create an event we are also likely going to need a holder
+         * to link to a group.  So embed one holder in the event.  Means only
+         * one allocation for the common case where we only have one group
+         */
+        struct fsnotify_event_holder holder;
+        spinlock_t lock;        /* protection for the associated event_holder and private_list */
+        /* to_tell may ONLY be dereferenced during handle_event(). */
+        struct inode *to_tell;  /* either the inode the event happened to or its parent */
+        /*
+         * depending on the event type we should have either a path or inode
+         * We hold a reference on path, but NOT on inode.  Since we have the ref on
+         * the path, it may be dereferenced at any point during this object's
+         * lifetime.  That reference is dropped when this object's refcnt hits
+         * 0.  If this event contains an inode instead of a path, the inode may
+         * ONLY be used during handle_event().
+         */
+        union {
+                struct path path;
+                struct inode *inode;
+        };
+/* when calling fsnotify tell it if the data is a path or inode */
+#define FSNOTIFY_EVENT_NONE     0
+#define FSNOTIFY_EVENT_PATH     1
+#define FSNOTIFY_EVENT_INODE    2
+#define FSNOTIFY_EVENT_FILE     3
+        int data_type;          /* which of the above union we have */
+        atomic_t refcnt;        /* how many groups still are using/need to send this event */
+        __u32 mask;             /* the type of access, bitwise OR for FS_* event types */
+
+        u32 sync_cookie;        /* used to corrolate events, namely inotify mv events */
+        char *file_name;
+        size_t name_len;
+
+        struct list_head private_data_list;     /* groups can store private data here */
+};
+
+/*
+ * a mark is simply an entry attached to an in core inode which allows an
+ * fsnotify listener to indicate they are either no longer interested in events
+ * of a type matching mask or only interested in those events.
+ *
+ * these are flushed when an inode is evicted from core and may be flushed
+ * when the inode is modified (as seen by fsnotify_access).  Some fsnotify users
+ * (such as dnotify) will flush these when the open fd is closed and not at
+ * inode eviction or modification.
+ */
+struct fsnotify_mark_entry {
+        __u32 mask;                     /* mask this mark entry is for */
+        /* we hold ref for each i_list and g_list.  also one ref for each 'thing'
+         * in kernel that found and may be using this mark. */
+        atomic_t refcnt;                /* active things looking at this mark */
+        struct inode *inode;            /* inode this entry is associated with */
+        struct fsnotify_group *group;   /* group this mark entry is for */
+        struct hlist_node i_list;       /* list of mark_entries by inode->i_fsnotify_mark_entries */
+        struct list_head g_list;        /* list of mark_entries by group->i_fsnotify_mark_entries */
+        spinlock_t lock;                /* protect group, inode, and killme */
+        struct list_head free_i_list;   /* tmp list used when freeing this mark */
+        struct list_head free_g_list;   /* tmp list used when freeing this mark */
+        void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */
+};
+
+#ifdef CONFIG_FSNOTIFY
+
+/* called from the vfs helpers */
+
+/* main fsnotify call to send events */
+extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+                     const char *name, u32 cookie);
+extern void __fsnotify_parent(struct dentry *dentry, __u32 mask);
+extern void __fsnotify_inode_delete(struct inode *inode);
+extern u32 fsnotify_get_cookie(void);
+
+static inline int fsnotify_inode_watches_children(struct inode *inode)
+{
+        /* FS_EVENT_ON_CHILD is set if the inode may care */
+        if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD))
+                return 0;
+        /* this inode might care about child events, does it care about the
+         * specific set of events that can happen on a child? */
+        return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD;
+}
+
+/*
+ * Update the dentry with a flag indicating the interest of its parent to receive
+ * filesystem events when those events happens to this dentry->d_inode.
+ */
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{
+        struct dentry *parent;
+
+        assert_spin_locked(&dcache_lock);
+        assert_spin_locked(&dentry->d_lock);
+
+        parent = dentry->d_parent;
+        if (fsnotify_inode_watches_children(parent->d_inode))
+                dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+        else
+                dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+}
+
+/*
+ * fsnotify_d_instantiate - instantiate a dentry for inode
+ * Called with dcache_lock held.
+ */
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{
+        if (!inode)
+                return;
+
+        assert_spin_locked(&dcache_lock);
+
+        spin_lock(&dentry->d_lock);
+        __fsnotify_update_dcache_flags(dentry);
+        spin_unlock(&dentry->d_lock);
+}
+
+/* called from fsnotify listeners, such as fanotify or dnotify */
+
+/* must call when a group changes its ->mask */
+extern void fsnotify_recalc_global_mask(void);
+/* get a reference to an existing or create a new group */
+extern struct fsnotify_group *fsnotify_obtain_group(unsigned int group_num,
+                                                    __u32 mask,
+                                                    const struct fsnotify_ops *ops);
+/* run all marks associated with this group and update group->mask */
+extern void fsnotify_recalc_group_mask(struct fsnotify_group *group);
+/* drop reference on a group from fsnotify_obtain_group */
+extern void fsnotify_put_group(struct fsnotify_group *group);
+
+/* take a reference to an event */
+extern void fsnotify_get_event(struct fsnotify_event *event);
+extern void fsnotify_put_event(struct fsnotify_event *event);
+/* find private data previously attached to an event and unlink it */
+extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struct fsnotify_group *group,
+                                                                           struct fsnotify_event *event);
+
+/* attach the event to the group notification queue */
+extern int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event,
+                                     struct fsnotify_event_private_data *priv);
+/* true if the group notification queue is empty */
+extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
+/* return, but do not dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group);
+/* return AND dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group);
+
+/* functions used to manipulate the marks attached to inodes */
+
+/* run all marks associated with an inode and update inode->i_fsnotify_mask */
+extern void fsnotify_recalc_inode_mask(struct inode *inode);
+extern void fsnotify_init_mark(struct fsnotify_mark_entry *entry, void (*free_mark)(struct fsnotify_mark_entry *entry));
+/* find (and take a reference) to a mark associated with group and inode */
+extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode);
+/* attach the mark to both the group and the inode */
+extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode);
+/* given a mark, flag it to be freed when all references are dropped */
+extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry);
+/* run all the marks in a group, and flag them to be freed */
+extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group);
+extern void fsnotify_get_mark(struct fsnotify_mark_entry *entry);
+extern void fsnotify_put_mark(struct fsnotify_mark_entry *entry);
+extern void fsnotify_unmount_inodes(struct list_head *list);
+
+/* put here because inotify does some weird stuff when destroying watches */
+extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
+                                                    void *data, int data_is, const char *name,
+                                                    u32 cookie);
+
+#else
+
+static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+                            const char *name, u32 cookie)
+{}
+
+static inline void __fsnotify_parent(struct dentry *dentry, __u32 mask)
+{}
+
+static inline void __fsnotify_inode_delete(struct inode *inode)
+{}
+
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{}
+
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{}
+
+static inline u32 fsnotify_get_cookie(void)
+{
+        return 0;
+}
+
+static inline void fsnotify_unmount_inodes(struct list_head *list)
+{}
+
+#endif  /* CONFIG_FSNOTIFY */
+
+#endif  /* __KERNEL __ */
+
+#endif  /* __LINUX_FSNOTIFY_BACKEND_H */