Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 751 insertions, 837 deletions

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index efbdc47c74..110e8a2721 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -2,8 +2,9 @@
 /*
  *  event_inode.c - part of tracefs, a pseudo file system for activating tracing
  *
- *  Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt (VMware) <rostedt@goodmis.org>
+ *  Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt <rostedt@goodmis.org>
  *  Copyright (C) 2020-23 VMware Inc, author: Ajay Kaher <akaher@vmware.com>
+ *  Copyright (C) 2023 Google, author: Steven Rostedt <rostedt@goodmis.org>
  *
  *  eventfs is used to dynamically create inodes and dentries based on the
  *  meta data provided by the tracing system.
@@ -23,51 +24,32 @@
 #include <linux/delay.h>
 #include "internal.h"
 
-struct eventfs_inode {
-	struct list_head	e_top_files;
-};
-
 /*
- * struct eventfs_file - hold the properties of the eventfs files and
- *                       directories.
- * @name:	the name of the file or directory to create
- * @d_parent:   holds parent's dentry
- * @dentry:     once accessed holds dentry
- * @list:	file or directory to be added to parent directory
- * @ei:		list of files and directories within directory
- * @fop:	file_operations for file or directory
- * @iop:	inode_operations for file or directory
- * @data:	something that the caller will want to get to later on
- * @is_freed:	Flag set if the eventfs is on its way to be freed
- * @mode:	the permission that the file or directory should have
- * @uid:	saved uid if changed
- * @gid:	saved gid if changed
+ * eventfs_mutex protects the eventfs_inode (ei) dentry. Any access
+ * to the ei->dentry must be done under this mutex and after checking
+ * if ei->is_freed is not set. When ei->is_freed is set, the dentry
+ * is on its way to being freed after the last dput() is made on it.
  */
-struct eventfs_file {
-	const char			*name;
-	struct dentry			*d_parent;
-	struct dentry			*dentry;
-	struct list_head		list;
-	struct eventfs_inode		*ei;
-	const struct file_operations	*fop;
-	const struct inode_operations	*iop;
-	/*
-	 * Union - used for deletion
-	 * @llist:	for calling dput() if needed after RCU
-	 * @rcu:	eventfs_file to delete in RCU
-	 */
-	union {
-		struct llist_node	llist;
-		struct rcu_head		rcu;
-	};
-	void				*data;
-	unsigned int			is_freed:1;
-	unsigned int			mode:31;
-	kuid_t				uid;
-	kgid_t				gid;
-};
-
 static DEFINE_MUTEX(eventfs_mutex);
+
+/* Choose something "unique" ;-) */
+#define EVENTFS_FILE_INODE_INO		0x12c4e37
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+	if (!ei->ino)
+		ei->ino = get_next_ino();
+
+	return ei->ino;
+}
+
+/*
+ * The eventfs_inode (ei) itself is protected by SRCU. It is released from
+ * its parent's list and will have is_freed set (under eventfs_mutex).
+ * After the SRCU grace period is over and the last dput() is called
+ * the ei is freed.
+ */
 DEFINE_STATIC_SRCU(eventfs_srcu);
 
 /* Mode is unsigned short, use the upper bits for flags */
@@ -75,60 +57,202 @@ enum {
 	EVENTFS_SAVE_MODE	= BIT(16),
 	EVENTFS_SAVE_UID	= BIT(17),
 	EVENTFS_SAVE_GID	= BIT(18),
+	EVENTFS_TOPLEVEL	= BIT(19),
 };
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
+/*
+ * eventfs_inode reference count management.
+ *
+ * NOTE! We count only references from dentries, in the
+ * form 'dentry->d_fsdata'. There are also references from
+ * directory inodes ('ti->private'), but the dentry reference
+ * count is always a superset of the inode reference count.
+ */
+static void release_ei(struct kref *ref)
+{
+	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+
+	WARN_ON_ONCE(!ei->is_freed);
+
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	kfree_rcu(ei, rcu);
+}
+
+static inline void put_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_put(&ei->kref, release_ei);
+}
+
+static inline void free_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		ei->is_freed = 1;
+		put_ei(ei);
+	}
+}
+
+static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_get(&ei->kref);
+	return ei;
+}
+
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags);
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file);
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx);
-static int eventfs_release(struct inode *inode, struct file *file);
+static int eventfs_iterate(struct file *file, struct dir_context *ctx);
 
-static void update_attr(struct eventfs_file *ef, struct iattr *iattr)
+static void update_attr(struct eventfs_attr *attr, struct iattr *iattr)
 {
 	unsigned int ia_valid = iattr->ia_valid;
 
 	if (ia_valid & ATTR_MODE) {
-		ef->mode = (ef->mode & ~EVENTFS_MODE_MASK) |
+		attr->mode = (attr->mode & ~EVENTFS_MODE_MASK) |
 			(iattr->ia_mode & EVENTFS_MODE_MASK) |
 			EVENTFS_SAVE_MODE;
 	}
 	if (ia_valid & ATTR_UID) {
-		ef->mode |= EVENTFS_SAVE_UID;
-		ef->uid = iattr->ia_uid;
+		attr->mode |= EVENTFS_SAVE_UID;
+		attr->uid = iattr->ia_uid;
 	}
 	if (ia_valid & ATTR_GID) {
-		ef->mode |= EVENTFS_SAVE_GID;
-		ef->gid = iattr->ia_gid;
+		attr->mode |= EVENTFS_SAVE_GID;
+		attr->gid = iattr->ia_gid;
 	}
 }
 
 static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
-			     struct iattr *iattr)
+			    struct iattr *iattr)
 {
-	struct eventfs_file *ef;
+	const struct eventfs_entry *entry;
+	struct eventfs_inode *ei;
+	const char *name;
 	int ret;
 
 	mutex_lock(&eventfs_mutex);
-	ef = dentry->d_fsdata;
-	if (ef && ef->is_freed) {
+	ei = dentry->d_fsdata;
+	if (ei->is_freed) {
 		/* Do not allow changes if the event is about to be removed. */
 		mutex_unlock(&eventfs_mutex);
 		return -ENODEV;
 	}
 
+	/* Preallocate the children mode array if necessary */
+	if (!(dentry->d_inode->i_mode & S_IFDIR)) {
+		if (!ei->entry_attrs) {
+			ei->entry_attrs = kcalloc(ei->nr_entries, sizeof(*ei->entry_attrs),
+						  GFP_NOFS);
+			if (!ei->entry_attrs) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+
 	ret = simple_setattr(idmap, dentry, iattr);
-	if (!ret && ef)
-		update_attr(ef, iattr);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * If this is a dir, then update the ei cache, only the file
+	 * mode is saved in the ei->m_children, and the ownership is
+	 * determined by the parent directory.
+	 */
+	if (dentry->d_inode->i_mode & S_IFDIR) {
+		/*
+		 * The events directory dentry is never freed, unless its
+		 * part of an instance that is deleted. It's attr is the
+		 * default for its child files and directories.
+		 * Do not update it. It's not used for its own mode or ownership.
+		 */
+		if (ei->is_events) {
+			/* But it still needs to know if it was modified */
+			if (iattr->ia_valid & ATTR_UID)
+				ei->attr.mode |= EVENTFS_SAVE_UID;
+			if (iattr->ia_valid & ATTR_GID)
+				ei->attr.mode |= EVENTFS_SAVE_GID;
+		} else {
+			update_attr(&ei->attr, iattr);
+		}
+
+	} else {
+		name = dentry->d_name.name;
+
+		for (int i = 0; i < ei->nr_entries; i++) {
+			entry = &ei->entries[i];
+			if (strcmp(name, entry->name) == 0) {
+				update_attr(&ei->entry_attrs[i], iattr);
+				break;
+			}
+		}
+	}
+ out:
 	mutex_unlock(&eventfs_mutex);
 	return ret;
 }
 
+static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
+{
+	struct inode *root;
+
+	/* Only update if the "events" was on the top level */
+	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	/* Get the tracefs root inode. */
+	root = d_inode(sb->s_root);
+	ei->attr.uid = root->i_uid;
+	ei->attr.gid = root->i_gid;
+}
+
+static void set_top_events_ownership(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct eventfs_inode *ei = ti->private;
+
+	/* The top events directory doesn't get automatically updated */
+	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+		return;
+
+	update_top_events_attr(ei, inode->i_sb);
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
+		inode->i_uid = ei->attr.uid;
+
+	if (!(ei->attr.mode & EVENTFS_SAVE_GID))
+		inode->i_gid = ei->attr.gid;
+}
+
+static int eventfs_get_attr(struct mnt_idmap *idmap,
+			    const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int flags)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_backing_inode(dentry);
+
+	set_top_events_ownership(inode);
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int eventfs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_top_events_ownership(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
 static const struct inode_operations eventfs_root_dir_inode_operations = {
 	.lookup		= eventfs_root_lookup,
 	.setattr	= eventfs_set_attr,
+	.getattr	= eventfs_get_attr,
+	.permission	= eventfs_permission,
 };
 
 static const struct inode_operations eventfs_file_inode_operations = {
@@ -136,764 +260,548 @@ static const struct inode_operations eventfs_file_inode_operations = {
 };
 
 static const struct file_operations eventfs_file_operations = {
-	.open		= dcache_dir_open_wrapper,
 	.read		= generic_read_dir,
-	.iterate_shared	= dcache_readdir_wrapper,
+	.iterate_shared	= eventfs_iterate,
 	.llseek		= generic_file_llseek,
-	.release	= eventfs_release,
 };
 
-static void update_inode_attr(struct inode *inode, struct eventfs_file *ef)
+/* Return the evenfs_inode of the "events" directory */
+static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
+{
+	struct eventfs_inode *ei;
+
+	do {
+		// The parent is stable because we do not do renames
+		dentry = dentry->d_parent;
+		// ... and directories always have d_fsdata
+		ei = dentry->d_fsdata;
+
+		/*
+		 * If the ei is being freed, the ownership of the children
+		 * doesn't matter.
+		 */
+		if (ei->is_freed) {
+			ei = NULL;
+			break;
+		}
+		// Walk upwards until you find the events inode
+	} while (!ei->is_events);
+
+	update_top_events_attr(ei, dentry->d_sb);
+
+	return ei;
+}
+
+static void update_inode_attr(struct dentry *dentry, struct inode *inode,
+			      struct eventfs_attr *attr, umode_t mode)
 {
-	inode->i_mode = ef->mode & EVENTFS_MODE_MASK;
+	struct eventfs_inode *events_ei = eventfs_find_events(dentry);
+
+	if (!events_ei)
+		return;
+
+	inode->i_mode = mode;
+	inode->i_uid = events_ei->attr.uid;
+	inode->i_gid = events_ei->attr.gid;
+
+	if (!attr)
+		return;
+
+	if (attr->mode & EVENTFS_SAVE_MODE)
+		inode->i_mode = attr->mode & EVENTFS_MODE_MASK;
 
-	if (ef->mode & EVENTFS_SAVE_UID)
-		inode->i_uid = ef->uid;
+	if (attr->mode & EVENTFS_SAVE_UID)
+		inode->i_uid = attr->uid;
 
-	if (ef->mode & EVENTFS_SAVE_GID)
-		inode->i_gid = ef->gid;
+	if (attr->mode & EVENTFS_SAVE_GID)
+		inode->i_gid = attr->gid;
 }
 
 /**
- * create_file - create a file in the tracefs filesystem
- * @ef: the eventfs_file
- * @parent: parent dentry for this file.
+ * lookup_file - look up a file in the tracefs filesystem
+ * @dentry: the dentry to look up
+ * @mode: the permission that the file should have.
+ * @attr: saved attributes changed by user
  * @data: something that the caller will want to get to later on.
  * @fop: struct file_operations that should be used for this file.
  *
- * This is the basic "create a file" function for tracefs.  It allows for a
- * wide range of flexibility in creating a file.
- *
- * This function will return a pointer to a dentry if it succeeds.  This
- * pointer must be passed to the tracefs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, %NULL will be returned.
- *
- * If tracefs is not enabled in the kernel, the value -%ENODEV will be
- * returned.
+ * This function creates a dentry that represents a file in the eventsfs_inode
+ * directory. The inode.i_private pointer will point to @data in the open()
+ * call.
  */
-static struct dentry *create_file(struct eventfs_file *ef,
-				  struct dentry *parent, void *data,
+static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
+				  struct dentry *dentry,
+				  umode_t mode,
+				  struct eventfs_attr *attr,
+				  void *data,
 				  const struct file_operations *fop)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
-	if (!(ef->mode & S_IFMT))
-		ef->mode |= S_IFREG;
-
-	if (WARN_ON_ONCE(!S_ISREG(ef->mode)))
-		return NULL;
-
-	dentry = eventfs_start_creating(ef->name, parent);
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
 
-	if (IS_ERR(dentry))
-		return dentry;
+	if (WARN_ON_ONCE(!S_ISREG(mode)))
+		return ERR_PTR(-EIO);
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
-	update_inode_attr(inode, ef);
+	update_inode_attr(dentry, inode, attr, mode);
 
 	inode->i_op = &eventfs_file_inode_operations;
 	inode->i_fop = fop;
 	inode->i_private = data;
 
+	/* All files will have the same inode number */
+	inode->i_ino = EVENTFS_FILE_INODE_INO;
+
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
-	d_instantiate(dentry, inode);
-	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+
+	// Files have their parent's ei as their fsdata
+	dentry->d_fsdata = get_ei(parent_ei);
+
+	d_add(dentry, inode);
+	return NULL;
 };
 
 /**
- * create_dir - create a dir in the tracefs filesystem
+ * lookup_dir_entry - look up a dir in the tracefs filesystem
+ * @dentry: the directory to look up
  * @ei: the eventfs_inode that represents the directory to create
- * @parent: parent dentry for this file.
- * @data: something that the caller will want to get to later on.
  *
- * This is the basic "create a dir" function for eventfs.  It allows for a
- * wide range of flexibility in creating a dir.
- *
- * This function will return a pointer to a dentry if it succeeds.  This
- * pointer must be passed to the tracefs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, %NULL will be returned.
- *
- * If tracefs is not enabled in the kernel, the value -%ENODEV will be
- * returned.
+ * This function will look up a dentry for a directory represented by
+ * a eventfs_inode.
  */
-static struct dentry *create_dir(struct eventfs_file *ef,
-				 struct dentry *parent, void *data)
+static struct dentry *lookup_dir_entry(struct dentry *dentry,
+	struct eventfs_inode *pei, struct eventfs_inode *ei)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
-	dentry = eventfs_start_creating(ef->name, parent);
-	if (IS_ERR(dentry))
-		return dentry;
-
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
-	update_inode_attr(inode, ef);
+	/* If the user updated the directory's attributes, use them */
+	update_inode_attr(dentry, inode, &ei->attr,
+			  S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
 
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
-	inode->i_private = data;
+
+	/* All directories will have the same inode number */
+	inode->i_ino = eventfs_dir_ino(ei);
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
+	/* Only directories have ti->private set to an ei, not files */
+	ti->private = ei;
 
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
-}
+	dentry->d_fsdata = get_ei(ei);
 
-static void free_ef(struct eventfs_file *ef)
-{
-	kfree(ef->name);
-	kfree(ef->ei);
-	kfree(ef);
+	d_add(dentry, inode);
+	return NULL;
 }
 
-/**
- * eventfs_set_ef_status_free - set the ef->status to free
- * @ti: the tracefs_inode of the dentry
- * @dentry: dentry who's status to be freed
- *
- * eventfs_set_ef_status_free will be called if no more
- * references remain
- */
-void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry)
+static inline struct eventfs_inode *alloc_ei(const char *name)
 {
-	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
+	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
 
-	/* The top level events directory may be freed by this */
-	if (unlikely(ti->flags & TRACEFS_EVENT_TOP_INODE)) {
-		mutex_lock(&eventfs_mutex);
-		ei = ti->private;
-
-		/* Nothing should access this, but just in case! */
-		ti->private = NULL;
-		mutex_unlock(&eventfs_mutex);
-
-		ef = dentry->d_fsdata;
-		if (ef)
-			free_ef(ef);
-		return;
-	}
-
-	mutex_lock(&eventfs_mutex);
-
-	ef = dentry->d_fsdata;
-	if (!ef)
-		goto out;
+	if (!ei)
+		return NULL;
 
-	if (ef->is_freed) {
-		free_ef(ef);
-	} else {
-		ef->dentry = NULL;
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name) {
+		kfree(ei);
+		return NULL;
 	}
-
-	dentry->d_fsdata = NULL;
-out:
-	mutex_unlock(&eventfs_mutex);
+	kref_init(&ei->kref);
+	return ei;
 }
 
 /**
- * eventfs_post_create_dir - post create dir routine
- * @ef: eventfs_file of recently created dir
+ * eventfs_d_release - dentry is going away
+ * @dentry: dentry which has the reference to remove.
  *
- * Map the meta-data of files within an eventfs dir to their parent dentry
+ * Remove the association between a dentry from an eventfs_inode.
  */
-static void eventfs_post_create_dir(struct eventfs_file *ef)
+void eventfs_d_release(struct dentry *dentry)
 {
-	struct eventfs_file *ef_child;
-	struct tracefs_inode *ti;
-
-	/* srcu lock already held */
-	/* fill parent-child relation */
-	list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		ef_child->d_parent = ef->dentry;
-	}
-
-	ti = get_tracefs(ef->dentry->d_inode);
-	ti->private = ef->ei;
+	put_ei(dentry->d_fsdata);
 }
 
 /**
- * create_dentry - helper function to create dentry
- * @ef: eventfs_file of file or directory to create
- * @parent: parent dentry
- * @lookup: true if called from lookup routine
+ * lookup_file_dentry - create a dentry for a file of an eventfs_inode
+ * @ei: the eventfs_inode that the file will be created under
+ * @idx: the index into the entry_attrs[] of the @ei
+ * @parent: The parent dentry of the created file.
+ * @name: The name of the file to create
+ * @mode: The mode of the file.
+ * @data: The data to use to set the inode of the file with on open()
+ * @fops: The fops of the file to be created.
  *
- * Used to create a dentry for file/dir, executes post dentry creation routine
+ * Create a dentry for a file of an eventfs_inode @ei and place it into the
+ * address located at @e_dentry.
  */
 static struct dentry *
-create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
+lookup_file_dentry(struct dentry *dentry,
+		   struct eventfs_inode *ei, int idx,
+		   umode_t mode, void *data,
+		   const struct file_operations *fops)
 {
-	bool invalidate = false;
-	struct dentry *dentry;
+	struct eventfs_attr *attr = NULL;
 
-	mutex_lock(&eventfs_mutex);
-	if (ef->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	if (ef->dentry) {
-		dentry = ef->dentry;
-		/* On dir open, up the ref count */
-		if (!lookup)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	if (!lookup)
-		inode_lock(parent->d_inode);
-
-	if (ef->ei)
-		dentry = create_dir(ef, parent, ef->data);
-	else
-		dentry = create_file(ef, parent, ef->data, ef->fop);
+	if (ei->entry_attrs)
+		attr = &ei->entry_attrs[idx];
 
-	if (!lookup)
-		inode_unlock(parent->d_inode);
-
-	mutex_lock(&eventfs_mutex);
-	if (IS_ERR_OR_NULL(dentry)) {
-		/* If the ef was already updated get it */
-		dentry = ef->dentry;
-		if (dentry && !lookup)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!ef->dentry && !ef->is_freed) {
-		ef->dentry = dentry;
-		if (ef->ei)
-			eventfs_post_create_dir(ef);
-		dentry->d_fsdata = ef;
-	} else {
-		/* A race here, should try again (unless freed) */
-		invalidate = true;
-
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ef->is_freed);
-	}
-	mutex_unlock(&eventfs_mutex);
-	if (invalidate)
-		d_invalidate(dentry);
-
-	if (lookup || invalidate)
-		dput(dentry);
-
-	return invalidate ? NULL : dentry;
-}
-
-static bool match_event_file(struct eventfs_file *ef, const char *name)
-{
-	bool ret;
-
-	mutex_lock(&eventfs_mutex);
-	ret = !ef->is_freed && strcmp(ef->name, name) == 0;
-	mutex_unlock(&eventfs_mutex);
-
-	return ret;
+	return lookup_file(ei, dentry, mode, attr, data, fops);
 }
 
 /**
  * eventfs_root_lookup - lookup routine to create file/dir
  * @dir: in which a lookup is being done
  * @dentry: file/dir dentry
- * @flags: to pass as flags parameter to simple lookup
+ * @flags: Just passed to simple_lookup()
  *
- * Used to create a dynamic file/dir within @dir. Use the eventfs_inode
- * list of meta data to find the information needed to create the file/dir.
+ * Used to create dynamic file/dir with-in @dir, search with-in @ei
+ * list, if @dentry found go ahead and create the file/dir
  */
+
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags)
 {
+	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
-	struct dentry *ret = NULL;
-	int idx;
+	const char *name = dentry->d_name.name;
+	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return NULL;
+		return ERR_PTR(-EIO);
+
+	mutex_lock(&eventfs_mutex);
 
 	ei = ti->private;
-	idx = srcu_read_lock(&eventfs_srcu);
-	list_for_each_entry_srcu(ef, &ei->e_top_files, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		if (!match_event_file(ef, dentry->d_name.name))
+	if (!ei || ei->is_freed)
+		goto out;
+
+	list_for_each_entry(ei_child, &ei->children, list) {
+		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		ret = simple_lookup(dir, dentry, flags);
-		create_dentry(ef, ef->d_parent, true);
-		break;
+		if (ei_child->is_freed)
+			goto out;
+		result = lookup_dir_entry(dentry, ei, ei_child);
+		goto out;
 	}
-	srcu_read_unlock(&eventfs_srcu, idx);
-	return ret;
-}
 
-struct dentry_list {
-	void			*cursor;
-	struct dentry		**dentries;
-};
-
-/**
- * eventfs_release - called to release eventfs file/dir
- * @inode: inode to be released
- * @file: file to be released (not used)
- */
-static int eventfs_release(struct inode *inode, struct file *file)
-{
-	struct tracefs_inode *ti;
-	struct dentry_list *dlist = file->private_data;
-	void *cursor;
-	int i;
+	for (int i = 0; i < ei->nr_entries; i++) {
+		void *data;
+		umode_t mode;
+		const struct file_operations *fops;
+		const struct eventfs_entry *entry = &ei->entries[i];
 
-	ti = get_tracefs(inode);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return -EINVAL;
+		if (strcmp(name, entry->name) != 0)
+			continue;
 
-	if (WARN_ON_ONCE(!dlist))
-		return -EINVAL;
+		data = ei->data;
+		if (entry->callback(name, &mode, &data, &fops) <= 0)
+			goto out;
 
-	for (i = 0; dlist->dentries && dlist->dentries[i]; i++) {
-		dput(dlist->dentries[i]);
+		result = lookup_file_dentry(dentry, ei, i, mode, data, fops);
+		goto out;
 	}
-
-	cursor = dlist->cursor;
-	kfree(dlist->dentries);
-	kfree(dlist);
-	file->private_data = cursor;
-	return dcache_dir_close(inode, file);
+ out:
+	mutex_unlock(&eventfs_mutex);
+	return result;
 }
 
-/**
- * dcache_dir_open_wrapper - eventfs open wrapper
- * @inode: not used
- * @file: dir to be opened (to create its child)
- *
- * Used to dynamically create the file/dir within @file. @file is really a
- * directory and all the files/dirs of the children within @file will be
- * created. If any of the files/dirs have already been created, their
- * reference count will be incremented.
+/*
+ * Walk the children of a eventfs_inode to fill in getdents().
  */
-static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
+static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 {
+	const struct file_operations *fops;
+	struct inode *f_inode = file_inode(file);
+	const struct eventfs_entry *entry;
+	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
-	struct dentry_list *dlist;
-	struct dentry **dentries = NULL;
-	struct dentry *dentry = file_dentry(file);
-	struct dentry *d;
-	struct inode *f_inode = file_inode(file);
-	int cnt = 0;
+	const char *name;
+	umode_t mode;
 	int idx;
-	int ret;
+	int ret = -EINVAL;
+	int ino;
+	int i, r, c;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
 
 	ti = get_tracefs(f_inode);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
 		return -EINVAL;
 
-	if (WARN_ON_ONCE(file->private_data))
-		return -EINVAL;
-
-	dlist = kmalloc(sizeof(*dlist), GFP_KERNEL);
-	if (!dlist)
-		return -ENOMEM;
+	c = ctx->pos - 2;
 
-	ei = ti->private;
 	idx = srcu_read_lock(&eventfs_srcu);
-	list_for_each_entry_srcu(ef, &ei->e_top_files, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		d = create_dentry(ef, dentry, false);
-		if (d) {
-			struct dentry **tmp;
 
+	mutex_lock(&eventfs_mutex);
+	ei = READ_ONCE(ti->private);
+	if (ei && ei->is_freed)
+		ei = NULL;
+	mutex_unlock(&eventfs_mutex);
 
-			tmp = krealloc(dentries, sizeof(d) * (cnt + 2), GFP_KERNEL);
-			if (!tmp)
-				break;
-			tmp[cnt] = d;
-			tmp[cnt + 1] = NULL;
-			cnt++;
-			dentries = tmp;
-		}
-	}
-	srcu_read_unlock(&eventfs_srcu, idx);
-	ret = dcache_dir_open(inode, file);
+	if (!ei)
+		goto out;
 
 	/*
-	 * dcache_dir_open() sets file->private_data to a dentry cursor.
-	 * Need to save that but also save all the dentries that were
-	 * opened by this function.
+	 * Need to create the dentries and inodes to have a consistent
+	 * inode number.
 	 */
-	dlist->cursor = file->private_data;
-	dlist->dentries = dentries;
-	file->private_data = dlist;
-	return ret;
-}
+	ret = 0;
 
-/*
- * This just sets the file->private_data back to the cursor and back.
- */
-static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx)
-{
-	struct dentry_list *dlist = file->private_data;
-	int ret;
+	/* Start at 'c' to jump over already read entries */
+	for (i = c; i < ei->nr_entries; i++, ctx->pos++) {
+		void *cdata = ei->data;
 
-	file->private_data = dlist->cursor;
-	ret = dcache_readdir(file, ctx);
-	dlist->cursor = file->private_data;
-	file->private_data = dlist;
-	return ret;
-}
+		entry = &ei->entries[i];
+		name = entry->name;
 
-/**
- * eventfs_prepare_ef - helper function to prepare eventfs_file
- * @name: the name of the file/directory to create.
- * @mode: the permission that the file should have.
- * @fop: struct file_operations that should be used for this file/directory.
- * @iop: struct inode_operations that should be used for this file/directory.
- * @data: something that the caller will want to get to later on. The
- *        inode.i_private pointer will point to this value on the open() call.
- *
- * This function allocates and fills the eventfs_file structure.
- */
-static struct eventfs_file *eventfs_prepare_ef(const char *name, umode_t mode,
-					const struct file_operations *fop,
-					const struct inode_operations *iop,
-					void *data)
-{
-	struct eventfs_file *ef;
+		mutex_lock(&eventfs_mutex);
+		/* If ei->is_freed then just bail here, nothing more to do */
+		if (ei->is_freed) {
+			mutex_unlock(&eventfs_mutex);
+			goto out;
+		}
+		r = entry->callback(name, &mode, &cdata, &fops);
+		mutex_unlock(&eventfs_mutex);
+		if (r <= 0)
+			continue;
 
-	ef = kzalloc(sizeof(*ef), GFP_KERNEL);
-	if (!ef)
-		return ERR_PTR(-ENOMEM);
+		ino = EVENTFS_FILE_INODE_INO;
 
-	ef->name = kstrdup(name, GFP_KERNEL);
-	if (!ef->name) {
-		kfree(ef);
-		return ERR_PTR(-ENOMEM);
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
+			goto out;
 	}
 
-	if (S_ISDIR(mode)) {
-		ef->ei = kzalloc(sizeof(*ef->ei), GFP_KERNEL);
-		if (!ef->ei) {
-			kfree(ef->name);
-			kfree(ef);
-			return ERR_PTR(-ENOMEM);
-		}
-		INIT_LIST_HEAD(&ef->ei->e_top_files);
-		ef->mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	} else {
-		ef->ei = NULL;
-		ef->mode = mode;
-	}
+	/* Subtract the skipped entries above */
+	c -= min((unsigned int)c, (unsigned int)ei->nr_entries);
 
-	ef->iop = iop;
-	ef->fop = fop;
-	ef->data = data;
-	return ef;
-}
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
 
-/**
- * eventfs_create_events_dir - create the trace event structure
- * @name: the name of the directory to create.
- * @parent: parent dentry for this file.  This should be a directory dentry
- *          if set.  If this parameter is NULL, then the directory will be
- *          created in the root of the tracefs filesystem.
- *
- * This function creates the top of the trace event directory.
- */
-struct dentry *eventfs_create_events_dir(const char *name,
-					 struct dentry *parent)
-{
-	struct dentry *dentry = tracefs_start_creating(name, parent);
-	struct eventfs_inode *ei;
-	struct tracefs_inode *ti;
-	struct inode *inode;
+		if (c > 0) {
+			c--;
+			continue;
+		}
 
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return NULL;
+		ctx->pos++;
 
-	if (IS_ERR(dentry))
-		return dentry;
+		if (ei_child->is_freed)
+			continue;
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
-	if (!ei)
-		return ERR_PTR(-ENOMEM);
-	inode = tracefs_get_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		kfree(ei);
-		tracefs_failed_creating(dentry);
-		return ERR_PTR(-ENOMEM);
-	}
+		name = ei_child->name;
 
-	INIT_LIST_HEAD(&ei->e_top_files);
+		ino = eventfs_dir_ino(ei_child);
 
-	ti = get_tracefs(inode);
-	ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
-	ti->private = ei;
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
+			goto out_dec;
+	}
+	ret = 1;
+ out:
+	srcu_read_unlock(&eventfs_srcu, idx);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	inode->i_op = &eventfs_root_dir_inode_operations;
-	inode->i_fop = &eventfs_file_operations;
+	return ret;
 
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return tracefs_end_creating(dentry);
+ out_dec:
+	/* Incremented ctx->pos without adding something, reset it */
+	ctx->pos--;
+	goto out;
 }
 
 /**
- * eventfs_add_subsystem_dir - add eventfs subsystem_dir to list to create later
- * @name: the name of the file to create.
- * @parent: parent dentry for this dir.
+ * eventfs_create_dir - Create the eventfs_inode for this directory
+ * @name: The name of the directory to create.
+ * @parent: The eventfs_inode of the parent directory.
+ * @entries: A list of entries that represent the files under this directory
+ * @size: The number of @entries
+ * @data: The default data to pass to the files (an entry may override it).
+ *
+ * This function creates the descriptor to represent a directory in the
+ * eventfs. This descriptor is an eventfs_inode, and it is returned to be
+ * used to create other children underneath.
+ *
+ * The @entries is an array of eventfs_entry structures which has:
+ *	const char		 *name
+ *	eventfs_callback	callback;
+ *
+ * The name is the name of the file, and the callback is a pointer to a function
+ * that will be called when the file is reference (either by lookup or by
+ * reading a directory). The callback is of the prototype:
+ *
+ *    int callback(const char *name, umode_t *mode, void **data,
+ *		   const struct file_operations **fops);
+ *
+ * When a file needs to be created, this callback will be called with
+ *   name = the name of the file being created (so that the same callback
+ *          may be used for multiple files).
+ *   mode = a place to set the file's mode
+ *   data = A pointer to @data, and the callback may replace it, which will
+ *         cause the file created to pass the new data to the open() call.
+ *   fops = the fops to use for the created file.
  *
- * This function adds eventfs subsystem dir to list.
- * And all these dirs are created on the fly when they are looked up,
- * and the dentry and inodes will be removed when they are done.
+ * NB. @callback is called while holding internal locks of the eventfs
+ *     system. The callback must not call any code that might also call into
+ *     the tracefs or eventfs system or it will risk creating a deadlock.
  */
-struct eventfs_file *eventfs_add_subsystem_dir(const char *name,
-					       struct dentry *parent)
+struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent,
+					 const struct eventfs_entry *entries,
+					 int size, void *data)
 {
-	struct tracefs_inode *ti_parent;
-	struct eventfs_inode *ei_parent;
-	struct eventfs_file *ef;
-
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return NULL;
+	struct eventfs_inode *ei;
 
 	if (!parent)
 		return ERR_PTR(-EINVAL);
 
-	ti_parent = get_tracefs(parent->d_inode);
-	ei_parent = ti_parent->private;
+	ei = alloc_ei(name);
+	if (!ei)
+		return ERR_PTR(-ENOMEM);
 
-	ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL);
-	if (IS_ERR(ef))
-		return ef;
+	ei->entries = entries;
+	ei->nr_entries = size;
+	ei->data = data;
+	INIT_LIST_HEAD(&ei->children);
+	INIT_LIST_HEAD(&ei->list);
 
 	mutex_lock(&eventfs_mutex);
-	list_add_tail(&ef->list, &ei_parent->e_top_files);
-	ef->d_parent = parent;
+	if (!parent->is_freed)
+		list_add_tail(&ei->list, &parent->children);
 	mutex_unlock(&eventfs_mutex);
-	return ef;
-}
-
-/**
- * eventfs_add_dir - add eventfs dir to list to create later
- * @name: the name of the file to create.
- * @ef_parent: parent eventfs_file for this dir.
- *
- * This function adds eventfs dir to list.
- * And all these dirs are created on the fly when they are looked up,
- * and the dentry and inodes will be removed when they are done.
- */
-struct eventfs_file *eventfs_add_dir(const char *name,
-				     struct eventfs_file *ef_parent)
-{
-	struct eventfs_file *ef;
-
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return NULL;
-
-	if (!ef_parent)
-		return ERR_PTR(-EINVAL);
-
-	ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL);
-	if (IS_ERR(ef))
-		return ef;
 
-	mutex_lock(&eventfs_mutex);
-	list_add_tail(&ef->list, &ef_parent->ei->e_top_files);
-	ef->d_parent = ef_parent->dentry;
-	mutex_unlock(&eventfs_mutex);
-	return ef;
+	/* Was the parent freed? */
+	if (list_empty(&ei->list)) {
+		free_ei(ei);
+		ei = NULL;
+	}
+	return ei;
 }
 
 /**
- * eventfs_add_events_file - add the data needed to create a file for later reference
- * @name: the name of the file to create.
- * @mode: the permission that the file should have.
- * @parent: parent dentry for this file.
- * @data: something that the caller will want to get to later on.
- * @fop: struct file_operations that should be used for this file.
+ * eventfs_create_events_dir - create the top level events directory
+ * @name: The name of the top level directory to create.
+ * @parent: Parent dentry for this file in the tracefs directory.
+ * @entries: A list of entries that represent the files under this directory
+ * @size: The number of @entries
+ * @data: The default data to pass to the files (an entry may override it).
  *
- * This function is used to add the information needed to create a
- * dentry/inode within the top level events directory. The file created
- * will have the @mode permissions. The @data will be used to fill the
- * inode.i_private when the open() call is done. The dentry and inodes are
- * all created when they are referenced, and removed when they are no
- * longer referenced.
+ * This function creates the top of the trace event directory.
+ *
+ * See eventfs_create_dir() for use of @entries.
  */
-int eventfs_add_events_file(const char *name, umode_t mode,
-			 struct dentry *parent, void *data,
-			 const struct file_operations *fop)
+struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent,
+						const struct eventfs_entry *entries,
+						int size, void *data)
 {
-	struct tracefs_inode *ti;
+	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
+	struct tracefs_inode *ti;
+	struct inode *inode;
+	kuid_t uid;
+	kgid_t gid;
 
 	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return -ENODEV;
-
-	if (!parent)
-		return -EINVAL;
-
-	if (!(mode & S_IFMT))
-		mode |= S_IFREG;
-
-	if (!parent->d_inode)
-		return -EINVAL;
-
-	ti = get_tracefs(parent->d_inode);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return -EINVAL;
-
-	ei = ti->private;
-	ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
-
-	if (IS_ERR(ef))
-		return -ENOMEM;
-
-	mutex_lock(&eventfs_mutex);
-	list_add_tail(&ef->list, &ei->e_top_files);
-	ef->d_parent = parent;
-	mutex_unlock(&eventfs_mutex);
-	return 0;
-}
-
-/**
- * eventfs_add_file - add eventfs file to list to create later
- * @name: the name of the file to create.
- * @mode: the permission that the file should have.
- * @ef_parent: parent eventfs_file for this file.
- * @data: something that the caller will want to get to later on.
- * @fop: struct file_operations that should be used for this file.
- *
- * This function is used to add the information needed to create a
- * file within a subdirectory of the events directory. The file created
- * will have the @mode permissions. The @data will be used to fill the
- * inode.i_private when the open() call is done. The dentry and inodes are
- * all created when they are referenced, and removed when they are no
- * longer referenced.
- */
-int eventfs_add_file(const char *name, umode_t mode,
-		     struct eventfs_file *ef_parent,
-		     void *data,
-		     const struct file_operations *fop)
-{
-	struct eventfs_file *ef;
+		return NULL;
 
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return -ENODEV;
+	if (IS_ERR(dentry))
+		return ERR_CAST(dentry);
 
-	if (!ef_parent)
-		return -EINVAL;
+	ei = alloc_ei(name);
+	if (!ei)
+		goto fail;
 
-	if (!(mode & S_IFMT))
-		mode |= S_IFREG;
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		goto fail;
 
-	ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
-	if (IS_ERR(ef))
-		return -ENOMEM;
+	// Note: we have a ref to the dentry from tracefs_start_creating()
+	ei->events_dir = dentry;
+	ei->entries = entries;
+	ei->nr_entries = size;
+	ei->is_events = 1;
+	ei->data = data;
 
-	mutex_lock(&eventfs_mutex);
-	list_add_tail(&ef->list, &ef_parent->ei->e_top_files);
-	ef->d_parent = ef_parent->dentry;
-	mutex_unlock(&eventfs_mutex);
-	return 0;
-}
+	/* Save the ownership of this directory */
+	uid = d_inode(dentry->d_parent)->i_uid;
+	gid = d_inode(dentry->d_parent)->i_gid;
 
-static LLIST_HEAD(free_list);
+	/*
+	 * If the events directory is of the top instance, then parent
+	 * is NULL. Set the attr.mode to reflect this and its permissions will
+	 * default to the tracefs root dentry.
+	 */
+	if (!parent)
+		ei->attr.mode = EVENTFS_TOPLEVEL;
 
-static void eventfs_workfn(struct work_struct *work)
-{
-        struct eventfs_file *ef, *tmp;
-        struct llist_node *llnode;
-
-	llnode = llist_del_all(&free_list);
-        llist_for_each_entry_safe(ef, tmp, llnode, llist) {
-		/* This should only get here if it had a dentry */
-		if (!WARN_ON_ONCE(!ef->dentry))
-			dput(ef->dentry);
-        }
-}
+	/* This is used as the default ownership of the files and directories */
+	ei->attr.uid = uid;
+	ei->attr.gid = gid;
 
-static DECLARE_WORK(eventfs_work, eventfs_workfn);
+	INIT_LIST_HEAD(&ei->children);
+	INIT_LIST_HEAD(&ei->list);
 
-static void free_rcu_ef(struct rcu_head *head)
-{
-	struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu);
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
+	ti->private = ei;
 
-	if (ef->dentry) {
-		/* Do not free the ef until all references of dentry are gone */
-		if (llist_add(&ef->llist, &free_list))
-			queue_work(system_unbound_wq, &eventfs_work);
-		return;
-	}
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_uid = uid;
+	inode->i_gid = gid;
+	inode->i_op = &eventfs_root_dir_inode_operations;
+	inode->i_fop = &eventfs_file_operations;
 
-	free_ef(ef);
-}
+	dentry->d_fsdata = get_ei(ei);
 
-static void unhook_dentry(struct dentry *dentry)
-{
-	if (!dentry)
-		return;
 	/*
-	 * Need to add a reference to the dentry that is expected by
-	 * simple_recursive_removal(), which will include a dput().
+	 * Keep all eventfs directories with i_nlink == 1.
+	 * Due to the dynamic nature of the dentry creations and not
+	 * wanting to add a pointer to the parent eventfs_inode in the
+	 * eventfs_inode structure, keeping the i_nlink in sync with the
+	 * number of directories would cause too much complexity for
+	 * something not worth much. Keeping directory links at 1
+	 * tells userspace not to trust the link number.
 	 */
-	dget(dentry);
+	d_instantiate(dentry, inode);
+	/* The dentry of the "events" parent does keep track though */
+	inc_nlink(dentry->d_parent->d_inode);
+	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+	tracefs_end_creating(dentry);
 
-	/*
-	 * Also add a reference for the dput() in eventfs_workfn().
-	 * That is required as that dput() will free the ei after
-	 * the SRCU grace period is over.
-	 */
-	dget(dentry);
+	return ei;
+
+ fail:
+	free_ei(ei);
+	tracefs_failed_creating(dentry);
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
  * eventfs_remove_rec - remove eventfs dir or file from list
- * @ef: eventfs_file to be removed.
- * @level: to check recursion depth
+ * @ei: eventfs_inode to be removed.
+ * @level: prevent recursion from going more than 3 levels deep.
  *
- * The helper function eventfs_remove_rec() is used to clean up and free the
- * associated data from eventfs for both of the added functions.
+ * This function recursively removes eventfs_inodes which
+ * contains info of files and/or directories.
  */
-static void eventfs_remove_rec(struct eventfs_file *ef, int level)
+static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 {
-	struct eventfs_file *ef_child;
+	struct eventfs_inode *ei_child;
 
-	if (!ef)
-		return;
 	/*
 	 * Check recursion depth. It should never be greater than 3:
 	 * 0 - events/
@@ -904,72 +812,54 @@ static void eventfs_remove_rec(struct eventfs_file *ef, int level)
 	if (WARN_ON_ONCE(level > 3))
 		return;
 
-	if (ef->ei) {
-		/* search for nested folders or files */
-		list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list,
-					 lockdep_is_held(&eventfs_mutex)) {
-			eventfs_remove_rec(ef_child, level + 1);
-		}
-	}
-
-	ef->is_freed = 1;
+	/* search for nested folders or files */
+	list_for_each_entry(ei_child, &ei->children, list)
+		eventfs_remove_rec(ei_child, level + 1);
 
-	unhook_dentry(ef->dentry);
-
-	list_del_rcu(&ef->list);
-	call_srcu(&eventfs_srcu, &ef->rcu, free_rcu_ef);
+	list_del(&ei->list);
+	free_ei(ei);
 }
 
 /**
- * eventfs_remove - remove eventfs dir or file from list
- * @ef: eventfs_file to be removed.
+ * eventfs_remove_dir - remove eventfs dir or file from list
+ * @ei: eventfs_inode to be removed.
  *
  * This function acquire the eventfs_mutex lock and call eventfs_remove_rec()
  */
-void eventfs_remove(struct eventfs_file *ef)
+void eventfs_remove_dir(struct eventfs_inode *ei)
 {
-	struct dentry *dentry;
-
-	if (!ef)
+	if (!ei)
 		return;
 
 	mutex_lock(&eventfs_mutex);
-	dentry = ef->dentry;
-	eventfs_remove_rec(ef, 0);
+	eventfs_remove_rec(ei, 0);
 	mutex_unlock(&eventfs_mutex);
-
-	/*
-	 * If any of the ei children has a dentry, then the ei itself
-	 * must have a dentry.
-	 */
-	if (dentry)
-		simple_recursive_removal(dentry, NULL);
 }
 
 /**
- * eventfs_remove_events_dir - remove eventfs dir or file from list
- * @dentry: events's dentry to be removed.
+ * eventfs_remove_events_dir - remove the top level eventfs directory
+ * @ei: the event_inode returned by eventfs_create_events_dir().
  *
- * This function remove events main directory
+ * This function removes the events main directory
  */
-void eventfs_remove_events_dir(struct dentry *dentry)
+void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
-	struct eventfs_file *ef_child;
-	struct eventfs_inode *ei;
-	struct tracefs_inode *ti;
+	struct dentry *dentry;
 
-	if (!dentry || !dentry->d_inode)
+	dentry = ei->events_dir;
+	if (!dentry)
 		return;
 
-	ti = get_tracefs(dentry->d_inode);
-	if (!ti || !(ti->flags & TRACEFS_EVENT_INODE))
-		return;
+	ei->events_dir = NULL;
+	eventfs_remove_dir(ei);
 
-	mutex_lock(&eventfs_mutex);
-	ei = ti->private;
-	list_for_each_entry_srcu(ef_child, &ei->e_top_files, list,
-				 lockdep_is_held(&eventfs_mutex)) {
-		eventfs_remove_rec(ef_child, 0);
-	}
-	mutex_unlock(&eventfs_mutex);
+	/*
+	 * Matches the dget() done by tracefs_start_creating()
+	 * in eventfs_create_events_dir() when it the dentry was
+	 * created. In other words, it's a normal dentry that
+	 * sticks around while the other ei->dentry are created
+	 * and destroyed dynamically.
+	 */
+	d_invalidate(dentry);
+	dput(dentry);
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 0292c6a2be..d65ffad4c3 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
 	if (!ti)
 		return NULL;
 
-	ti->flags = 0;
-
 	return &ti->vfs_inode;
 }
 
@@ -91,6 +89,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 				 struct inode *inode, struct dentry *dentry,
 				 umode_t mode)
 {
+	struct tracefs_inode *ti;
 	char *name;
 	int ret;
 
@@ -99,6 +98,15 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
 		return -ENOMEM;
 
 	/*
+	 * This is a new directory that does not take the default of
+	 * the rootfs. It becomes the default permissions for all the
+	 * files and directories underneath it.
+	 */
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_INSTANCE_INODE;
+	ti->private = inode;
+
+	/*
 	 * The mkdir call can call the generic functions that create
 	 * the files within the tracefs system. It is up to the individual
 	 * mkdir routine to handle races.
@@ -141,10 +149,76 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
 	return ret;
 }
 
-static const struct inode_operations tracefs_dir_inode_operations = {
+static void set_tracefs_inode_owner(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct inode *root_inode = ti->private;
+
+	/*
+	 * If this inode has never been referenced, then update
+	 * the permissions to the superblock.
+	 */
+	if (!(ti->flags & TRACEFS_UID_PERM_SET))
+		inode->i_uid = root_inode->i_uid;
+
+	if (!(ti->flags & TRACEFS_GID_PERM_SET))
+		inode->i_gid = root_inode->i_gid;
+}
+
+static int tracefs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_tracefs_inode_owner(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
+static int tracefs_getattr(struct mnt_idmap *idmap,
+			   const struct path *path, struct kstat *stat,
+			   u32 request_mask, unsigned int flags)
+{
+	struct inode *inode = d_backing_inode(path->dentry);
+
+	set_tracefs_inode_owner(inode);
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			   struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	struct inode *inode = d_inode(dentry);
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	if (ia_valid & ATTR_UID)
+		ti->flags |= TRACEFS_UID_PERM_SET;
+
+	if (ia_valid & ATTR_GID)
+		ti->flags |= TRACEFS_GID_PERM_SET;
+
+	return simple_setattr(idmap, dentry, attr);
+}
+
+static const struct inode_operations tracefs_instance_dir_inode_operations = {
 	.lookup		= simple_lookup,
 	.mkdir		= tracefs_syscall_mkdir,
 	.rmdir		= tracefs_syscall_rmdir,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_file_inode_operations = {
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
 };
 
 struct inode *tracefs_get_inode(struct super_block *sb)
@@ -152,7 +226,7 @@ struct inode *tracefs_get_inode(struct super_block *sb)
 	struct inode *inode = new_inode(sb);
 	if (inode) {
 		inode->i_ino = get_next_ino();
-		inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
+		simple_inode_init_ts(inode);
 	}
 	return inode;
 }
@@ -183,77 +257,6 @@ struct tracefs_fs_info {
 	struct tracefs_mount_opts mount_opts;
 };
 
-static void change_gid(struct dentry *dentry, kgid_t gid)
-{
-	if (!dentry->d_inode)
-		return;
-	dentry->d_inode->i_gid = gid;
-}
-
-/*
- * Taken from d_walk, but without he need for handling renames.
- * Nothing can be renamed while walking the list, as tracefs
- * does not support renames. This is only called when mounting
- * or remounting the file system, to set all the files to
- * the given gid.
- */
-static void set_gid(struct dentry *parent, kgid_t gid)
-{
-	struct dentry *this_parent;
-	struct list_head *next;
-
-	this_parent = parent;
-	spin_lock(&this_parent->d_lock);
-
-	change_gid(this_parent, gid);
-repeat:
-	next = this_parent->d_subdirs.next;
-resume:
-	while (next != &this_parent->d_subdirs) {
-		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
-		next = tmp->next;
-
-		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-
-		change_gid(dentry, gid);
-
-		if (!list_empty(&dentry->d_subdirs)) {
-			spin_unlock(&this_parent->d_lock);
-			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
-			this_parent = dentry;
-			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
-			goto repeat;
-		}
-		spin_unlock(&dentry->d_lock);
-	}
-	/*
-	 * All done at this level ... ascend and resume the search.
-	 */
-	rcu_read_lock();
-ascend:
-	if (this_parent != parent) {
-		struct dentry *child = this_parent;
-		this_parent = child->d_parent;
-
-		spin_unlock(&child->d_lock);
-		spin_lock(&this_parent->d_lock);
-
-		/* go into the first sibling still alive */
-		do {
-			next = child->d_child.next;
-			if (next == &this_parent->d_subdirs)
-				goto ascend;
-			child = list_entry(next, struct dentry, d_child);
-		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
-		rcu_read_unlock();
-		goto resume;
-	}
-	rcu_read_unlock();
-	spin_unlock(&this_parent->d_lock);
-	return;
-}
-
 static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
@@ -326,10 +329,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	if (!remount || opts->opts & BIT(Opt_uid))
 		inode->i_uid = opts->uid;
 
-	if (!remount || opts->opts & BIT(Opt_gid)) {
-		/* Set all the group ids to the mount option */
-		set_gid(sb->s_root, opts->gid);
-	}
+	if (!remount || opts->opts & BIT(Opt_gid))
+		inode->i_gid = opts->gid;
 
 	return 0;
 }
@@ -376,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
 	.show_options	= tracefs_show_options,
 };
 
-static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
 {
-	struct tracefs_inode *ti;
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
 
-	if (!dentry || !inode)
-		return;
+static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
 
-	ti = get_tracefs(inode);
-	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ef_status_free(ti, dentry);
-	iput(inode);
+	return !(ei && ei->is_freed);
 }
 
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_dentry_iput,
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
 };
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
@@ -494,73 +504,24 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
-/**
- * eventfs_start_creating - start the process of creating a dentry
- * @name: Name of the file created for the dentry
- * @parent: The parent dentry where this dentry will be created
- *
- * This is a simple helper function for the dynamically created eventfs
- * files. When the directory of the eventfs files are accessed, their
- * dentries are created on the fly. This function is used to start that
- * process.
- */
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
+/* Find the inode that this will use for default */
+static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
 {
-	struct dentry *dentry;
-	int error;
-
-	/* Must always have a parent. */
-	if (WARN_ON_ONCE(!parent))
-		return ERR_PTR(-EINVAL);
-
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
-	if (error)
-		return ERR_PTR(error);
+	struct tracefs_inode *ti;
 
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
+	/* If parent is NULL then use root inode */
+	if (!parent)
+		return d_inode(inode->i_sb->s_root);
 
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
+	/* Find the inode that is flagged as an instance or the root inode */
+	while (!IS_ROOT(parent)) {
+		ti = get_tracefs(d_inode(parent));
+		if (ti->flags & TRACEFS_INSTANCE_INODE)
+			break;
+		parent = parent->d_parent;
 	}
 
-	if (IS_ERR(dentry))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-	return dentry;
-}
-
-/**
- * eventfs_failed_creating - clean up a failed eventfs dentry creation
- * @dentry: The dentry to clean up
- *
- * If after calling eventfs_start_creating(), a failure is detected, the
- * resources created by eventfs_start_creating() needs to be cleaned up. In
- * that case, this function should be called to perform that clean up.
- */
-struct dentry *eventfs_failed_creating(struct dentry *dentry)
-{
-	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	return NULL;
-}
-
-/**
- * eventfs_end_creating - Finish the process of creating a eventfs dentry
- * @dentry: The dentry that has successfully been created.
- *
- * This function is currently just a place holder to match
- * eventfs_start_creating(). In case any synchronization needs to be added,
- * this function will be used to implement that without having to modify
- * the callers of eventfs_start_creating().
- */
-struct dentry *eventfs_end_creating(struct dentry *dentry)
-{
-	return dentry;
+	return d_inode(parent);
 }
 
 /**
@@ -593,6 +554,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry;
 	struct inode *inode;
 
@@ -611,7 +573,11 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return tracefs_failed_creating(dentry);
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	inode->i_mode = mode;
+	inode->i_op = &tracefs_file_inode_operations;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
 	inode->i_private = data;
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
@@ -624,6 +590,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 static struct dentry *__create_dir(const char *name, struct dentry *parent,
 				   const struct inode_operations *ops)
 {
+	struct tracefs_inode *ti;
 	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct inode *inode;
 
@@ -641,6 +608,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
 	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -671,7 +641,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
 
-	return __create_dir(name, parent, &simple_dir_inode_operations);
+	return __create_dir(name, parent, &tracefs_dir_inode_operations);
 }
 
 /**
@@ -702,7 +672,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name,
 	if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
 		return NULL;
 
-	dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+	dentry = __create_dir(name, parent, &tracefs_instance_dir_inode_operations);
 	if (!dentry)
 		return NULL;
 
@@ -747,7 +717,11 @@ static void init_once(void *foo)
 {
 	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
 
+	/* inode_init_once() calls memset() on the vfs_inode portion */
 	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
 }
 
 static int __init tracefs_init(void)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 4f2e49e219..beb3dcd0e4 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -5,12 +5,64 @@
 enum {
 	TRACEFS_EVENT_INODE		= BIT(1),
 	TRACEFS_EVENT_TOP_INODE		= BIT(2),
+	TRACEFS_GID_PERM_SET		= BIT(3),
+	TRACEFS_UID_PERM_SET		= BIT(4),
+	TRACEFS_INSTANCE_INODE		= BIT(5),
 };
 
 struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
 	unsigned long           flags;
 	void                    *private;
-	struct inode            vfs_inode;
+};
+
+/*
+ * struct eventfs_attr - cache the mode and ownership of a eventfs entry
+ * @mode:	saved mode plus flags of what is saved
+ * @uid:	saved uid if changed
+ * @gid:	saved gid if changed
+ */
+struct eventfs_attr {
+	int				mode;
+	kuid_t				uid;
+	kgid_t				gid;
+};
+
+/*
+ * struct eventfs_inode - hold the properties of the eventfs directories.
+ * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
+ * @entries:	the array of entries representing the files in the directory
+ * @name:	the name of the directory to create
+ * @events_dir: the dentry of the events directory
+ * @entry_attrs: Saved mode and ownership of the @d_children
+ * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
+ * @is_freed:	Flag set if the eventfs is on its way to be freed
+ *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
+ * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
+ */
+struct eventfs_inode {
+	union {
+		struct list_head	list;
+		struct rcu_head		rcu;
+	};
+	struct list_head		children;
+	const struct eventfs_entry	*entries;
+	const char			*name;
+	struct dentry			*events_dir;
+	struct eventfs_attr		*entry_attrs;
+	void				*data;
+	struct eventfs_attr		attr;
+	struct kref			kref;
+	unsigned int			is_freed:1;
+	unsigned int			is_events:1;
+	unsigned int			nr_entries:30;
+	unsigned int			ino;
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@@ -22,9 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
-struct dentry *eventfs_failed_creating(struct dentry *dentry);
-struct dentry *eventfs_end_creating(struct dentry *dentry);
-void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry);
+
+void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */