10 files changed, 264 insertions, 285 deletions

diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index caaaf9dfe353..44523f4a6084 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -69,8 +69,8 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
 	if (old_mask == new_mask)
 		return;
 
-	if (fsn_mark->i.inode)
-		fsnotify_recalc_inode_mask(fsn_mark->i.inode);
+	if (fsn_mark->inode)
+		fsnotify_recalc_inode_mask(fsn_mark->inode);
 }
 
 /*
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 9d7e2b9659cb..58b7cdb63da9 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -20,25 +20,24 @@
 
 #if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY)
 
-static int show_fdinfo(struct seq_file *m, struct file *f,
-		       int (*show)(struct seq_file *m, struct fsnotify_mark *mark))
+static void show_fdinfo(struct seq_file *m, struct file *f,
+			void (*show)(struct seq_file *m,
+				     struct fsnotify_mark *mark))
 {
 	struct fsnotify_group *group = f->private_data;
 	struct fsnotify_mark *mark;
-	int ret = 0;
 
 	mutex_lock(&group->mark_mutex);
 	list_for_each_entry(mark, &group->marks_list, g_list) {
-		ret = show(m, mark);
-		if (ret)
+		show(m, mark);
+		if (seq_has_overflowed(m))
 			break;
 	}
 	mutex_unlock(&group->mark_mutex);
-	return ret;
 }
 
 #if defined(CONFIG_EXPORTFS)
-static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
 	struct {
 		struct file_handle handle;
@@ -52,98 +51,85 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 	ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
 	if ((ret == FILEID_INVALID) || (ret < 0)) {
 		WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
-		return 0;
+		return;
 	}
 
 	f.handle.handle_type = ret;
 	f.handle.handle_bytes = size * sizeof(u32);
 
-	ret = seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
-			 f.handle.handle_bytes, f.handle.handle_type);
+	seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
+		   f.handle.handle_bytes, f.handle.handle_type);
 
 	for (i = 0; i < f.handle.handle_bytes; i++)
-		ret |= seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
-
-	return ret;
+		seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
 }
 #else
-static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
+static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
-	return 0;
 }
 #endif
 
 #ifdef CONFIG_INOTIFY_USER
 
-static int inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 {
 	struct inotify_inode_mark *inode_mark;
 	struct inode *inode;
-	int ret = 0;
 
 	if (!(mark->flags & (FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_INODE)))
-		return 0;
+		return;
 
 	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
-	inode = igrab(mark->i.inode);
+	inode = igrab(mark->inode);
 	if (inode) {
-		ret = seq_printf(m, "inotify wd:%x ino:%lx sdev:%x "
-				 "mask:%x ignored_mask:%x ",
-				 inode_mark->wd, inode->i_ino,
-				 inode->i_sb->s_dev,
-				 mark->mask, mark->ignored_mask);
-		ret |= show_mark_fhandle(m, inode);
-		ret |= seq_putc(m, '\n');
+		seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
+			   inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
+			   mark->mask, mark->ignored_mask);
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
 		iput(inode);
 	}
-
-	return ret;
 }
 
-int inotify_show_fdinfo(struct seq_file *m, struct file *f)
+void inotify_show_fdinfo(struct seq_file *m, struct file *f)
 {
-	return show_fdinfo(m, f, inotify_fdinfo);
+	show_fdinfo(m, f, inotify_fdinfo);
 }
 
 #endif /* CONFIG_INOTIFY_USER */
 
 #ifdef CONFIG_FANOTIFY
 
-static int fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
+static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 {
 	unsigned int mflags = 0;
 	struct inode *inode;
-	int ret = 0;
 
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE))
-		return 0;
+		return;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
 		mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = igrab(mark->i.inode);
+		inode = igrab(mark->inode);
 		if (!inode)
-			goto out;
-		ret = seq_printf(m, "fanotify ino:%lx sdev:%x "
-				 "mflags:%x mask:%x ignored_mask:%x ",
-				 inode->i_ino, inode->i_sb->s_dev,
-				 mflags, mark->mask, mark->ignored_mask);
-		ret |= show_mark_fhandle(m, inode);
-		ret |= seq_putc(m, '\n');
+			return;
+		seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
+			   inode->i_ino, inode->i_sb->s_dev,
+			   mflags, mark->mask, mark->ignored_mask);
+		show_mark_fhandle(m, inode);
+		seq_putc(m, '\n');
 		iput(inode);
 	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) {
-		struct mount *mnt = real_mount(mark->m.mnt);
+		struct mount *mnt = real_mount(mark->mnt);
 
-		ret = seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x "
-				 "ignored_mask:%x\n", mnt->mnt_id, mflags,
-				 mark->mask, mark->ignored_mask);
+		seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
 	}
-out:
-	return ret;
 }
 
-int fanotify_show_fdinfo(struct seq_file *m, struct file *f)
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct fsnotify_group *group = f->private_data;
 	unsigned int flags = 0;
@@ -169,7 +155,7 @@ int fanotify_show_fdinfo(struct seq_file *m, struct file *f)
 	seq_printf(m, "fanotify flags:%x event-flags:%x\n",
 		   flags, group->fanotify_data.f_flags);
 
-	return show_fdinfo(m, f, fanotify_fdinfo);
+	show_fdinfo(m, f, fanotify_fdinfo);
 }
 
 #endif /* CONFIG_FANOTIFY */
diff --git a/fs/notify/fdinfo.h b/fs/notify/fdinfo.h
index 556afda990e9..9664c4904d6b 100644
--- a/fs/notify/fdinfo.h
+++ b/fs/notify/fdinfo.h
@@ -10,11 +10,11 @@ struct file;
 #ifdef CONFIG_PROC_FS
 
 #ifdef CONFIG_INOTIFY_USER
-extern int inotify_show_fdinfo(struct seq_file *m, struct file *f);
+void inotify_show_fdinfo(struct seq_file *m, struct file *f);
 #endif
 
 #ifdef CONFIG_FANOTIFY
-extern int fanotify_show_fdinfo(struct seq_file *m, struct file *f);
+void fanotify_show_fdinfo(struct seq_file *m, struct file *f);
 #endif
 
 #else /* CONFIG_PROC_FS */
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 9d3e9c50066a..dd3fb0b17be7 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	/* run all of the dentries associated with this inode.  Since this is a
 	 * directory, there damn well better only be one item on this list */
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		struct dentry *child;
 
 		/* run all of the children of the original inode and fix their
 		 * d_flags to indicate parental interest (their parent is the
 		 * original inode) */
 		spin_lock(&alias->d_lock);
-		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+		list_for_each_entry(child, &alias->d_subdirs, d_child) {
 			if (!child->d_inode)
 				continue;
 
@@ -229,36 +229,42 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 					      &fsnotify_mark_srcu);
 	}
 
+	/*
+	 * We need to merge inode & vfsmount mark lists so that inode mark
+	 * ignore masks are properly reflected for mount mark notifications.
+	 * That's why this traversal is so complicated...
+	 */
 	while (inode_node || vfsmount_node) {
-		inode_group = vfsmount_group = NULL;
+		inode_group = NULL;
+		inode_mark = NULL;
+		vfsmount_group = NULL;
+		vfsmount_mark = NULL;
 
 		if (inode_node) {
 			inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
-						 struct fsnotify_mark, i.i_list);
+						 struct fsnotify_mark, obj_list);
 			inode_group = inode_mark->group;
 		}
 
 		if (vfsmount_node) {
 			vfsmount_mark = hlist_entry(srcu_dereference(vfsmount_node, &fsnotify_mark_srcu),
-							struct fsnotify_mark, m.m_list);
+						    struct fsnotify_mark, obj_list);
 			vfsmount_group = vfsmount_mark->group;
 		}
 
-		if (inode_group > vfsmount_group) {
-			/* handle inode */
-			ret = send_to_group(to_tell, inode_mark, NULL, mask,
-					    data, data_is, cookie, file_name);
-			/* we didn't use the vfsmount_mark */
-			vfsmount_group = NULL;
-		} else if (vfsmount_group > inode_group) {
-			ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
-					    data, data_is, cookie, file_name);
-			inode_group = NULL;
-		} else {
-			ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
-					    mask, data, data_is, cookie,
-					    file_name);
+		if (inode_group && vfsmount_group) {
+			int cmp = fsnotify_compare_groups(inode_group,
+							  vfsmount_group);
+			if (cmp > 0) {
+				inode_group = NULL;
+				inode_mark = NULL;
+			} else if (cmp < 0) {
+				vfsmount_group = NULL;
+				vfsmount_mark = NULL;
+			}
 		}
+		ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
+				    data, data_is, cookie, file_name);
 
 		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
 			goto out;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 9c0898c4cfe1..13a00be516d2 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,8 +12,19 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
+/* Calculate mask of events for a list of marks */
+extern u32 fsnotify_recalc_mask(struct hlist_head *head);
+
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+				   struct fsnotify_group *b);
+
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
 						__u32 mask);
+/* Add mark to a proper place in mark list */
+extern int fsnotify_add_mark_list(struct hlist_head *head,
+				  struct fsnotify_mark *mark,
+				  int allow_dups);
 /* add a mark to an inode */
 extern int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 				   struct fsnotify_group *group, struct inode *inode,
@@ -27,6 +38,11 @@ extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
 /* inode specific destruction of a mark */
 extern void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark);
+/* Destroy all marks in the given list */
+extern void fsnotify_destroy_marks(struct list_head *to_free);
+/* Find mark belonging to given group in the list of marks */
+extern struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+						struct fsnotify_group *group);
 /* run the list of all marks associated with inode and flag them to be freed */
 extern void fsnotify_clear_marks_by_inode(struct inode *inode);
 /* run the list of all marks associated with vfsmount and flag them to be freed */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 9ce062218de9..3daf513ee99e 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -31,28 +31,13 @@
 #include "../internal.h"
 
 /*
- * Recalculate the mask of events relevant to a given inode locked.
- */
-static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
-{
-	struct fsnotify_mark *mark;
-	__u32 new_mask = 0;
-
-	assert_spin_locked(&inode->i_lock);
-
-	hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list)
-		new_mask |= mark->mask;
-	inode->i_fsnotify_mask = new_mask;
-}
-
-/*
  * Recalculate the inode->i_fsnotify_mask, or the mask of all FS_* event types
  * any notifier is interested in hearing for this inode.
  */
 void fsnotify_recalc_inode_mask(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	fsnotify_recalc_inode_mask_locked(inode);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	__fsnotify_update_child_dentry_flags(inode);
@@ -60,23 +45,22 @@ void fsnotify_recalc_inode_mask(struct inode *inode)
 
 void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
 {
-	struct inode *inode = mark->i.inode;
+	struct inode *inode = mark->inode;
 
 	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&inode->i_lock);
 
-	hlist_del_init_rcu(&mark->i.i_list);
-	mark->i.inode = NULL;
+	hlist_del_init_rcu(&mark->obj_list);
+	mark->inode = NULL;
 
 	/*
 	 * this mark is now off the inode->i_fsnotify_marks list and we
 	 * hold the inode->i_lock, so this is the perfect time to update the
 	 * inode->i_fsnotify_mask
 	 */
-	fsnotify_recalc_inode_mask_locked(inode);
-
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -85,30 +69,19 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
  */
 void fsnotify_clear_marks_by_inode(struct inode *inode)
 {
-	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_mark *mark;
 	struct hlist_node *n;
 	LIST_HEAD(free_list);
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) {
-		list_add(&mark->i.free_i_list, &free_list);
-		hlist_del_init_rcu(&mark->i.i_list);
+	hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, obj_list) {
+		list_add(&mark->free_list, &free_list);
+		hlist_del_init_rcu(&mark->obj_list);
 		fsnotify_get_mark(mark);
 	}
 	spin_unlock(&inode->i_lock);
 
-	list_for_each_entry_safe(mark, lmark, &free_list, i.free_i_list) {
-		struct fsnotify_group *group;
-
-		spin_lock(&mark->lock);
-		fsnotify_get_group(mark->group);
-		group = mark->group;
-		spin_unlock(&mark->lock);
-
-		fsnotify_destroy_mark(mark, group);
-		fsnotify_put_mark(mark);
-		fsnotify_put_group(group);
-	}
+	fsnotify_destroy_marks(&free_list);
 }
 
 /*
@@ -123,34 +96,13 @@ void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
  * given a group and inode, find the mark associated with that combination.
  * if found take a reference to that mark and return it, else return NULL
  */
-static struct fsnotify_mark *fsnotify_find_inode_mark_locked(
-		struct fsnotify_group *group,
-		struct inode *inode)
-{
-	struct fsnotify_mark *mark;
-
-	assert_spin_locked(&inode->i_lock);
-
-	hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) {
-		if (mark->group == group) {
-			fsnotify_get_mark(mark);
-			return mark;
-		}
-	}
-	return NULL;
-}
-
-/*
- * given a group and inode, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
 struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
 					       struct inode *inode)
 {
 	struct fsnotify_mark *mark;
 
 	spin_lock(&inode->i_lock);
-	mark = fsnotify_find_inode_mark_locked(group, inode);
+	mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	spin_unlock(&inode->i_lock);
 
 	return mark;
@@ -168,10 +120,10 @@ void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	if (mask &&
-	    mark->i.inode &&
+	    mark->inode &&
 	    !(mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED)) {
 		mark->flags |= FSNOTIFY_MARK_FLAG_OBJECT_PINNED;
-		inode = igrab(mark->i.inode);
+		inode = igrab(mark->inode);
 		/*
 		 * we shouldn't be able to get here if the inode wasn't
 		 * already safely held in memory.  But bug in case it
@@ -192,8 +144,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 			    struct fsnotify_group *group, struct inode *inode,
 			    int allow_dups)
 {
-	struct fsnotify_mark *lmark, *last = NULL;
-	int ret = 0;
+	int ret;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
@@ -201,40 +152,10 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&inode->i_lock);
-
-	mark->i.inode = inode;
-
-	/* is mark the first mark? */
-	if (hlist_empty(&inode->i_fsnotify_marks)) {
-		hlist_add_head_rcu(&mark->i.i_list, &inode->i_fsnotify_marks);
-		goto out;
-	}
-
-	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) {
-		last = lmark;
-
-		if ((lmark->group == group) && !allow_dups) {
-			ret = -EEXIST;
-			goto out;
-		}
-
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
-			continue;
-
-		hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
-		goto out;
-	}
-
-	BUG_ON(last == NULL);
-	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_behind_rcu(&mark->i.i_list, &last->i.i_list);
-out:
-	fsnotify_recalc_inode_mask_locked(inode);
+	mark->inode = inode;
+	ret = fsnotify_add_mark_list(&inode->i_fsnotify_marks, mark,
+				     allow_dups);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	return ret;
@@ -288,20 +209,25 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
-		if ((&next_i->i_sb_list != list) &&
-		    atomic_read(&next_i->i_count)) {
+		while (&next_i->i_sb_list != list) {
 			spin_lock(&next_i->i_lock);
-			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
+						atomic_read(&next_i->i_count)) {
 				__iget(next_i);
 				need_iput = next_i;
+				spin_unlock(&next_i->i_lock);
+				break;
 			}
 			spin_unlock(&next_i->i_lock);
+			next_i = list_entry(next_i->i_sb_list.next,
+						struct inode, i_sb_list);
 		}
 
 		/*
-		 * We can safely drop inode_sb_list_lock here because we hold
-		 * references on both inode and next_i.  Also no new inodes
-		 * will be added since the umount has begun.
+		 * We can safely drop inode_sb_list_lock here because either
+		 * we actually hold references on both inode and next_i or
+		 * end of list.  Also no new inodes will be added since the
+		 * umount has begun.
 		 */
 		spin_unlock(&inode_sb_list_lock);
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 7d888d77d59a..2cd900c2c737 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -156,7 +156,7 @@ static int idr_callback(int id, void *p, void *data)
 	 */
 	if (fsn_mark)
 		printk(KERN_WARNING "fsn_mark->group=%p inode=%p wd=%d\n",
-			fsn_mark->group, fsn_mark->i.inode, i_mark->wd);
+			fsn_mark->group, fsn_mark->inode, i_mark->wd);
 	return 0;
 }
 
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index daf76652fe58..450648697433 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -227,14 +227,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 	struct fsnotify_event *kevent;
 	char __user *start;
 	int ret;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	start = buf;
 	group = file->private_data;
 
+	add_wait_queue(&group->notification_waitq, &wait);
 	while (1) {
-		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
 		mutex_lock(&group->notification_mutex);
 		kevent = get_one_event(group, count);
 		mutex_unlock(&group->notification_mutex);
@@ -264,10 +263,10 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 		if (start != buf)
 			break;
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
+	remove_wait_queue(&group->notification_waitq, &wait);
 
-	finish_wait(&group->notification_waitq, &wait);
 	if (start != buf && ret != -EFAULT)
 		ret = buf - start;
 	return ret;
@@ -434,7 +433,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (wd == -1) {
 		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -443,7 +442,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (unlikely(!found_i_mark)) {
 		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -457,9 +456,9 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 			"mark->inode=%p found_i_mark=%p found_i_mark->wd=%d "
 			"found_i_mark->group=%p found_i_mark->inode=%p\n",
 			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group,
-			i_mark->fsn_mark.i.inode, found_i_mark, found_i_mark->wd,
+			i_mark->fsn_mark.inode, found_i_mark, found_i_mark->wd,
 			found_i_mark->fsn_mark.group,
-			found_i_mark->fsn_mark.i.inode);
+			found_i_mark->fsn_mark.inode);
 		goto out;
 	}
 
@@ -471,7 +470,7 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 3)) {
 		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
 			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.i.inode);
+			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
 		/* we can't really recover with bad ref cnting.. */
 		BUG();
 	}
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d90deaa08e78..92e48c70f0f0 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -110,6 +110,17 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	}
 }
 
+/* Calculate mask of events for a list of marks */
+u32 fsnotify_recalc_mask(struct hlist_head *head)
+{
+	u32 new_mask = 0;
+	struct fsnotify_mark *mark;
+
+	hlist_for_each_entry(mark, head, obj_list)
+		new_mask |= mark->mask;
+	return new_mask;
+}
+
 /*
  * Any time a mark is getting freed we end up here.
  * The caller had better be holding a reference to this mark so we don't actually
@@ -133,7 +144,7 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = mark->i.inode;
+		inode = mark->inode;
 		fsnotify_destroy_inode_mark(mark);
 	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT)
 		fsnotify_destroy_vfsmount_mark(mark);
@@ -150,7 +161,7 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
-	list_add(&mark->destroy_list, &destroy_list);
+	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
 	/*
@@ -192,6 +203,27 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 }
 
+/*
+ * Destroy all marks in the given list. The marks must be already detached from
+ * the original inode / vfsmount.
+ */
+void fsnotify_destroy_marks(struct list_head *to_free)
+{
+	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_group *group;
+
+	list_for_each_entry_safe(mark, lmark, to_free, free_list) {
+		spin_lock(&mark->lock);
+		fsnotify_get_group(mark->group);
+		group = mark->group;
+		spin_unlock(&mark->lock);
+
+		fsnotify_destroy_mark(mark, group);
+		fsnotify_put_mark(mark);
+		fsnotify_put_group(group);
+	}
+}
+
 void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
 {
 	assert_spin_locked(&mark->lock);
@@ -210,6 +242,75 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
 }
 
 /*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+	if (a == b)
+		return 0;
+	if (!a)
+		return 1;
+	if (!b)
+		return -1;
+	if (a->priority < b->priority)
+		return 1;
+	if (a->priority > b->priority)
+		return -1;
+	if (a < b)
+		return 1;
+	return -1;
+}
+
+/* Add mark into proper place in given list of marks */
+int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
+			   int allow_dups)
+{
+	struct fsnotify_mark *lmark, *last = NULL;
+	int cmp;
+
+	/* is mark the first mark? */
+	if (hlist_empty(head)) {
+		hlist_add_head_rcu(&mark->obj_list, head);
+		return 0;
+	}
+
+	/* should mark be in the middle of the current list? */
+	hlist_for_each_entry(lmark, head, obj_list) {
+		last = lmark;
+
+		if ((lmark->group == mark->group) && !allow_dups)
+			return -EEXIST;
+
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp >= 0) {
+			hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
+			return 0;
+		}
+	}
+
+	BUG_ON(last == NULL);
+	/* mark should be the last entry.  last is the current last entry */
+	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
+	return 0;
+}
+
+/*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
@@ -269,7 +370,7 @@ err:
 	spin_unlock(&mark->lock);
 
 	spin_lock(&destroy_lock);
-	list_add(&mark->destroy_list, &destroy_list);
+	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
 
@@ -287,6 +388,24 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 }
 
 /*
+ * Given a list of marks, find the mark associated with given group. If found
+ * take a reference to that mark and return it, else return NULL.
+ */
+struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+					 struct fsnotify_group *group)
+{
+	struct fsnotify_mark *mark;
+
+	hlist_for_each_entry(mark, head, obj_list) {
+		if (mark->group == group) {
+			fsnotify_get_mark(mark);
+			return mark;
+		}
+	}
+	return NULL;
+}
+
+/*
  * clear any marks in a group in which mark->flags & flags is true
  */
 void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
@@ -316,8 +435,8 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group)
 void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
 {
 	assert_spin_locked(&old->lock);
-	new->i.inode = old->i.inode;
-	new->m.mnt = old->m.mnt;
+	new->inode = old->inode;
+	new->mnt = old->mnt;
 	if (old->group)
 		fsnotify_get_group(old->group);
 	new->group = old->group;
@@ -350,8 +469,8 @@ static int fsnotify_mark_destroy(void *ignored)
 
 		synchronize_srcu(&fsnotify_mark_srcu);
 
-		list_for_each_entry_safe(mark, next, &private_destroy_list, destroy_list) {
-			list_del_init(&mark->destroy_list);
+		list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+			list_del_init(&mark->g_list);
 			fsnotify_put_mark(mark);
 		}
 
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index ac851e8376b1..326b148e623c 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -32,31 +32,20 @@
 
 void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
 {
-	struct fsnotify_mark *mark, *lmark;
+	struct fsnotify_mark *mark;
 	struct hlist_node *n;
 	struct mount *m = real_mount(mnt);
 	LIST_HEAD(free_list);
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) {
-		list_add(&mark->m.free_m_list, &free_list);
-		hlist_del_init_rcu(&mark->m.m_list);
+	hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, obj_list) {
+		list_add(&mark->free_list, &free_list);
+		hlist_del_init_rcu(&mark->obj_list);
 		fsnotify_get_mark(mark);
 	}
 	spin_unlock(&mnt->mnt_root->d_lock);
 
-	list_for_each_entry_safe(mark, lmark, &free_list, m.free_m_list) {
-		struct fsnotify_group *group;
-
-		spin_lock(&mark->lock);
-		fsnotify_get_group(mark->group);
-		group = mark->group;
-		spin_unlock(&mark->lock);
-
-		fsnotify_destroy_mark(mark, group);
-		fsnotify_put_mark(mark);
-		fsnotify_put_group(group);
-	}
+	fsnotify_destroy_marks(&free_list);
 }
 
 void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
@@ -65,66 +54,35 @@ void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
 }
 
 /*
- * Recalculate the mask of events relevant to a given vfsmount locked.
- */
-static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *mark;
-	__u32 new_mask = 0;
-
-	assert_spin_locked(&mnt->mnt_root->d_lock);
-
-	hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list)
-		new_mask |= mark->mask;
-	m->mnt_fsnotify_mask = new_mask;
-}
-
-/*
  * Recalculate the mnt->mnt_fsnotify_mask, or the mask of all FS_* event types
  * any notifier is interested in hearing for this mount point
  */
 void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
 {
+	struct mount *m = real_mount(mnt);
+
 	spin_lock(&mnt->mnt_root->d_lock);
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
 void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
 {
-	struct vfsmount *mnt = mark->m.mnt;
+	struct vfsmount *mnt = mark->mnt;
+	struct mount *m = real_mount(mnt);
 
 	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
 
-	hlist_del_init_rcu(&mark->m.m_list);
-	mark->m.mnt = NULL;
-
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	hlist_del_init_rcu(&mark->obj_list);
+	mark->mnt = NULL;
 
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
-static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_group *group,
-								struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *mark;
-
-	assert_spin_locked(&mnt->mnt_root->d_lock);
-
-	hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) {
-		if (mark->group == group) {
-			fsnotify_get_mark(mark);
-			return mark;
-		}
-	}
-	return NULL;
-}
-
 /*
  * given a group and vfsmount, find the mark associated with that combination.
  * if found take a reference to that mark and return it, else return NULL
@@ -132,10 +90,11 @@ static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_
 struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
 						  struct vfsmount *mnt)
 {
+	struct mount *m = real_mount(mnt);
 	struct fsnotify_mark *mark;
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	mark = fsnotify_find_vfsmount_mark_locked(group, mnt);
+	mark = fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return mark;
@@ -151,8 +110,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 			       int allow_dups)
 {
 	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *lmark, *last = NULL;
-	int ret = 0;
+	int ret;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
@@ -160,40 +118,9 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 	assert_spin_locked(&mark->lock);
 
 	spin_lock(&mnt->mnt_root->d_lock);
-
-	mark->m.mnt = mnt;
-
-	/* is mark the first mark? */
-	if (hlist_empty(&m->mnt_fsnotify_marks)) {
-		hlist_add_head_rcu(&mark->m.m_list, &m->mnt_fsnotify_marks);
-		goto out;
-	}
-
-	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) {
-		last = lmark;
-
-		if ((lmark->group == group) && !allow_dups) {
-			ret = -EEXIST;
-			goto out;
-		}
-
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
-			continue;
-
-		hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
-		goto out;
-	}
-
-	BUG_ON(last == NULL);
-	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_behind_rcu(&mark->m.m_list, &last->m.m_list);
-out:
-	fsnotify_recalc_vfsmount_mask_locked(mnt);
+	mark->mnt = mnt;
+	ret = fsnotify_add_mark_list(&m->mnt_fsnotify_marks, mark, allow_dups);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return ret;