Merge tag 'trace-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Remove eventfs_file descriptor

   This is the biggest change, and the second part of making eventfs
   create its files dynamically.

   In 6.6 the first part was added, and that maintained a one to one
   mapping between eventfs meta descriptors and the directories and file
   inodes and dentries that were dynamically created. The directories
   were represented by a eventfs_inode and the files were represented by
   a eventfs_file.

   In v6.7 the eventfs_file is removed. As all events have the same
   directory make up (sched_switch has an "enable", "id", "format", etc
   files), the handing of what files are underneath each leaf eventfs
   directory is moved back to the tracing subsystem via a callback.

   When an event is added to the eventfs, it registers an array of
   evenfs_entry's. These hold the names of the files and the callbacks
   to call when the file is referenced. The callback gets the name so
   that the same callback may be used by multiple files. The callback
   then supplies the filesystem_operations structure needed to create
   this file.

   This has brought the memory footprint of creating multiple eventfs
   instances down by 2 megs each!

 - User events now has persistent events that are not associated to a
   single processes. These are privileged events that hang around even
   if no process is attached to them

 - Clean up of seq_buf

   There's talk about using seq_buf more to replace strscpy() and
   friends. But this also requires some minor modifications of seq_buf
   to be able to do this

 - Expand instance ring buffers individually

   Currently if boot up creates an instance, and a trace event is
   enabled on that instance, the ring buffer for that instance and the
   top level ring buffer are expanded (1.4 MB per CPU). This wastes
   memory as this happens when nothing is using the top level instance

 - Other minor clean ups and fixes

* tag 'trace-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (34 commits)
  seq_buf: Export seq_buf_puts()
  seq_buf: Export seq_buf_putc()
  eventfs: Use simple_recursive_removal() to clean up dentries
  eventfs: Remove special processing of dput() of events directory
  eventfs: Delete eventfs_inode when the last dentry is freed
  eventfs: Hold eventfs_mutex when calling callback functions
  eventfs: Save ownership and mode
  eventfs: Test for ei->is_freed when accessing ei->dentry
  eventfs: Have a free_ei() that just frees the eventfs_inode
  eventfs: Remove "is_freed" union with rcu head
  eventfs: Fix kerneldoc of eventfs_remove_rec()
  tracing: Have the user copy of synthetic event address use correct context
  eventfs: Remove extra dget() in eventfs_create_events_dir()
  tracing: Have trace_event_file have ref counters
  seq_buf: Introduce DECLARE_SEQ_BUF and seq_buf_str()
  eventfs: Fix typo in eventfs_inode union comment
  eventfs: Fix WARN_ON() in create_file_dentry()
  powerpc: Remove initialisation of readpos
  tracing/histograms: Simplify last_cmd_set()
  seq_buf: fix a misleading comment
  ...

3 files changed, 688 insertions, 461 deletions

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 8c8d64e76103..f8a594a50ae6 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.
@@ -23,48 +24,30 @@
 #include <linux/delay.h>
 #include "internal.h"
 
-struct eventfs_inode {
-	struct list_head	e_top_files;
-};
+/*
+ * 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. The ei->dentry is released under the
+ * mutex at the same time ei->is_freed is set. If ei->is_freed is set
+ * then the ei->dentry is invalid.
+ */
+static DEFINE_MUTEX(eventfs_mutex);
 
 /*
- * 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
- * @mode:	the permission that the file or directory should have
+ * 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, the ei may be freed.
  */
-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
-	 * @del_list:	list of eventfs_file to delete
-	 * @rcu:	eventfs_file to delete in RCU
-	 * @is_freed:	node is freed if one of the above is set
-	 */
-	union {
-		struct list_head	del_list;
-		struct rcu_head		rcu;
-		unsigned long		is_freed;
-	};
-	void				*data;
-	umode_t				mode;
+DEFINE_STATIC_SRCU(eventfs_srcu);
+
+/* Mode is unsigned short, use the upper bits for flags */
+enum {
+	EVENTFS_SAVE_MODE	= BIT(16),
+	EVENTFS_SAVE_UID	= BIT(17),
+	EVENTFS_SAVE_GID	= BIT(18),
 };
 
-static DEFINE_MUTEX(eventfs_mutex);
-DEFINE_STATIC_SRCU(eventfs_srcu);
+#define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
@@ -73,8 +56,88 @@ 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 void update_attr(struct eventfs_attr *attr, struct iattr *iattr)
+{
+	unsigned int ia_valid = iattr->ia_valid;
+
+	if (ia_valid & ATTR_MODE) {
+		attr->mode = (attr->mode & ~EVENTFS_MODE_MASK) |
+			(iattr->ia_mode & EVENTFS_MODE_MASK) |
+			EVENTFS_SAVE_MODE;
+	}
+	if (ia_valid & ATTR_UID) {
+		attr->mode |= EVENTFS_SAVE_UID;
+		attr->uid = iattr->ia_uid;
+	}
+	if (ia_valid & ATTR_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)
+{
+	const struct eventfs_entry *entry;
+	struct eventfs_inode *ei;
+	const char *name;
+	int ret;
+
+	mutex_lock(&eventfs_mutex);
+	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 = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries,
+						  GFP_KERNEL);
+			if (!ei->entry_attrs) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+
+	ret = simple_setattr(idmap, dentry, 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) {
+		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 const struct inode_operations eventfs_root_dir_inode_operations = {
 	.lookup		= eventfs_root_lookup,
+	.setattr	= eventfs_set_attr,
+};
+
+static const struct inode_operations eventfs_file_inode_operations = {
+	.setattr	= eventfs_set_attr,
 };
 
 static const struct file_operations eventfs_file_operations = {
@@ -85,26 +148,40 @@ static const struct file_operations eventfs_file_operations = {
 	.release	= eventfs_release,
 };
 
+static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, umode_t mode)
+{
+	if (!attr) {
+		inode->i_mode = mode;
+		return;
+	}
+
+	if (attr->mode & EVENTFS_SAVE_MODE)
+		inode->i_mode = attr->mode & EVENTFS_MODE_MASK;
+	else
+		inode->i_mode = mode;
+
+	if (attr->mode & EVENTFS_SAVE_UID)
+		inode->i_uid = attr->uid;
+
+	if (attr->mode & EVENTFS_SAVE_GID)
+		inode->i_gid = attr->gid;
+}
+
 /**
  * create_file - create a file in the tracefs filesystem
  * @name: the name of the file to create.
  * @mode: the permission that the file should have.
+ * @attr: saved attributes changed by user
  * @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.
  *
- * 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(const char *name, umode_t mode,
+				  struct eventfs_attr *attr,
 				  struct dentry *parent, void *data,
 				  const struct file_operations *fop)
 {
@@ -118,6 +195,7 @@ static struct dentry *create_file(const char *name, umode_t mode,
 	if (WARN_ON_ONCE(!S_ISREG(mode)))
 		return NULL;
 
+	WARN_ON_ONCE(!parent);
 	dentry = eventfs_start_creating(name, parent);
 
 	if (IS_ERR(dentry))
@@ -127,7 +205,10 @@ static struct dentry *create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return eventfs_failed_creating(dentry);
 
-	inode->i_mode = mode;
+	/* If the user updated the directory's attributes, use them */
+	update_inode_attr(inode, attr, mode);
+
+	inode->i_op = &eventfs_file_inode_operations;
 	inode->i_fop = fop;
 	inode->i_private = data;
 
@@ -140,28 +221,19 @@ static struct dentry *create_file(const char *name, umode_t mode,
 
 /**
  * create_dir - create a dir in the tracefs filesystem
- * @name: the name of the file to create.
+ * @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 create a dentry for a directory represented by
+ * a eventfs_inode.
  */
-static struct dentry *create_dir(const char *name, struct dentry *parent, void *data)
+static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent)
 {
 	struct tracefs_inode *ti;
 	struct dentry *dentry;
 	struct inode *inode;
 
-	dentry = eventfs_start_creating(name, parent);
+	dentry = eventfs_start_creating(ei->name, parent);
 	if (IS_ERR(dentry))
 		return dentry;
 
@@ -169,10 +241,11 @@ static struct dentry *create_dir(const char *name, struct dentry *parent, void *
 	if (unlikely(!inode))
 		return eventfs_failed_creating(dentry);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	/* If the user updated the directory's attributes, use them */
+	update_inode_attr(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;
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
@@ -184,117 +257,198 @@ static struct dentry *create_dir(const char *name, struct dentry *parent, void *
 	return eventfs_end_creating(dentry);
 }
 
+static void free_ei(struct eventfs_inode *ei)
+{
+	kfree_const(ei->name);
+	kfree(ei->d_children);
+	kfree(ei->entry_attrs);
+	kfree(ei);
+}
+
 /**
- * eventfs_set_ef_status_free - set the ef->status to free
+ * eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode
  * @ti: the tracefs_inode of the dentry
- * @dentry: dentry who's status to be freed
+ * @dentry: dentry which has the reference to remove.
  *
- * eventfs_set_ef_status_free will be called if no more
- * references remain
+ * Remove the association between a dentry from an eventfs_inode.
  */
-void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry)
+void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
 {
-	struct tracefs_inode *ti_parent;
 	struct eventfs_inode *ei;
-	struct eventfs_file *ef, *tmp;
-
-	/* The top level events directory may be freed by this */
-	if (unlikely(ti->flags & TRACEFS_EVENT_TOP_INODE)) {
-		LIST_HEAD(ef_del_list);
+	int i;
 
-		mutex_lock(&eventfs_mutex);
+	mutex_lock(&eventfs_mutex);
 
-		ei = ti->private;
+	ei = dentry->d_fsdata;
+	if (!ei)
+		goto out;
 
-		/* Record all the top level files */
-		list_for_each_entry_srcu(ef, &ei->e_top_files, list,
-					 lockdep_is_held(&eventfs_mutex)) {
-			list_add_tail(&ef->del_list, &ef_del_list);
+	/* This could belong to one of the files of the ei */
+	if (ei->dentry != dentry) {
+		for (i = 0; i < ei->nr_entries; i++) {
+			if (ei->d_children[i] == dentry)
+				break;
 		}
+		if (WARN_ON_ONCE(i == ei->nr_entries))
+			goto out;
+		ei->d_children[i] = NULL;
+	} else if (ei->is_freed) {
+		free_ei(ei);
+	} else {
+		ei->dentry = NULL;
+	}
+
+	dentry->d_fsdata = NULL;
+ out:
+	mutex_unlock(&eventfs_mutex);
+}
 
-		/* Nothing should access this, but just in case! */
-		ti->private = NULL;
+/**
+ * create_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 d_children[] 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.
+ * @lookup: If called by the lookup routine, in which case, dput() the created dentry.
+ *
+ * Create a dentry for a file of an eventfs_inode @ei and place it into the
+ * address located at @e_dentry. If the @e_dentry already has a dentry, then
+ * just do a dget() on it and return. Otherwise create the dentry and attach it.
+ */
+static struct dentry *
+create_file_dentry(struct eventfs_inode *ei, int idx,
+		   struct dentry *parent, const char *name, umode_t mode, void *data,
+		   const struct file_operations *fops, bool lookup)
+{
+	struct eventfs_attr *attr = NULL;
+	struct dentry **e_dentry = &ei->d_children[idx];
+	struct dentry *dentry;
+	bool invalidate = false;
 
+	mutex_lock(&eventfs_mutex);
+	if (ei->is_freed) {
 		mutex_unlock(&eventfs_mutex);
+		return NULL;
+	}
+	/* If the e_dentry already has a dentry, use it */
+	if (*e_dentry) {
+		/* lookup does not need to up the ref count */
+		if (!lookup)
+			dget(*e_dentry);
+		mutex_unlock(&eventfs_mutex);
+		return *e_dentry;
+	}
 
-		/* Now safely free the top level files and their children */
-		list_for_each_entry_safe(ef, tmp, &ef_del_list, del_list) {
-			list_del(&ef->del_list);
-			eventfs_remove(ef);
-		}
+	/* ei->entry_attrs are protected by SRCU */
+	if (ei->entry_attrs)
+		attr = &ei->entry_attrs[idx];
 
-		kfree(ei);
-		return;
-	}
+	mutex_unlock(&eventfs_mutex);
 
-	mutex_lock(&eventfs_mutex);
+	/* The lookup already has the parent->d_inode locked */
+	if (!lookup)
+		inode_lock(parent->d_inode);
 
-	ti_parent = get_tracefs(dentry->d_parent->d_inode);
-	if (!ti_parent || !(ti_parent->flags & TRACEFS_EVENT_INODE))
-		goto out;
+	dentry = create_file(name, mode, attr, parent, data, fops);
 
-	ef = dentry->d_fsdata;
-	if (!ef)
-		goto out;
+	if (!lookup)
+		inode_unlock(parent->d_inode);
 
-	/*
-	 * If ef was freed, then the LSB bit is set for d_fsdata.
-	 * But this should not happen, as it should still have a
-	 * ref count that prevents it. Warn in case it does.
-	 */
-	if (WARN_ON_ONCE((unsigned long)ef & 1))
-		goto out;
+	mutex_lock(&eventfs_mutex);
 
-	dentry->d_fsdata = NULL;
-	ef->dentry = NULL;
-out:
+	if (IS_ERR_OR_NULL(dentry)) {
+		/*
+		 * When the mutex was released, something else could have
+		 * created the dentry for this e_dentry. In which case
+		 * use that one.
+		 *
+		 * Note, with the mutex held, the e_dentry cannot have content
+		 * and the ei->is_freed be true at the same time.
+		 */
+		dentry = *e_dentry;
+		if (WARN_ON_ONCE(dentry && ei->is_freed))
+			dentry = NULL;
+		/* The lookup does not need to up the dentry refcount */
+		if (dentry && !lookup)
+			dget(dentry);
+		mutex_unlock(&eventfs_mutex);
+		return dentry;
+	}
+
+	if (!*e_dentry && !ei->is_freed) {
+		*e_dentry = dentry;
+		dentry->d_fsdata = ei;
+	} else {
+		/*
+		 * Should never happen unless we get here due to being freed.
+		 * Otherwise it means two dentries exist with the same name.
+		 */
+		WARN_ON_ONCE(!ei->is_freed);
+		invalidate = true;
+	}
 	mutex_unlock(&eventfs_mutex);
+
+	if (invalidate)
+		d_invalidate(dentry);
+
+	if (lookup || invalidate)
+		dput(dentry);
+
+	return invalidate ? NULL : dentry;
 }
 
 /**
  * eventfs_post_create_dir - post create dir routine
- * @ef: eventfs_file of recently created dir
+ * @ei: eventfs_inode of recently created dir
  *
  * Map the meta-data of files within an eventfs dir to their parent dentry
  */
-static void eventfs_post_create_dir(struct eventfs_file *ef)
+static void eventfs_post_create_dir(struct eventfs_inode *ei)
 {
-	struct eventfs_file *ef_child;
+	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 
+	lockdep_assert_held(&eventfs_mutex);
+
 	/* srcu lock already held */
 	/* fill parent-child relation */
-	list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list,
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
-		ef_child->d_parent = ef->dentry;
+		ei_child->d_parent = ei->dentry;
 	}
 
-	ti = get_tracefs(ef->dentry->d_inode);
-	ti->private = ef->ei;
+	ti = get_tracefs(ei->dentry->d_inode);
+	ti->private = ei;
 }
 
 /**
- * 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
+ * create_dir_dentry - Create a directory dentry for the eventfs_inode
+ * @pei: The eventfs_inode parent of ei.
+ * @ei: The eventfs_inode to create the directory for
+ * @parent: The dentry of the parent of this directory
+ * @lookup: True if this is called by the lookup code
  *
- * Used to create a dentry for file/dir, executes post dentry creation routine
+ * This creates and attaches a directory dentry to the eventfs_inode @ei.
  */
 static struct dentry *
-create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
+create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
+		  struct dentry *parent, bool lookup)
 {
 	bool invalidate = false;
-	struct dentry *dentry;
+	struct dentry *dentry = NULL;
 
 	mutex_lock(&eventfs_mutex);
-	if (ef->is_freed) {
+	if (pei->is_freed || ei->is_freed) {
 		mutex_unlock(&eventfs_mutex);
 		return NULL;
 	}
-	if (ef->dentry) {
-		dentry = ef->dentry;
-		/* On dir open, up the ref count */
+	if (ei->dentry) {
+		/* If the dentry already has a dentry, use it */
+		dentry = ei->dentry;
+		/* lookup does not need to up the ref count */
 		if (!lookup)
 			dget(dentry);
 		mutex_unlock(&eventfs_mutex);
@@ -302,42 +456,44 @@ create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
 	}
 	mutex_unlock(&eventfs_mutex);
 
+	/* The lookup already has the parent->d_inode locked */
 	if (!lookup)
 		inode_lock(parent->d_inode);
 
-	if (ef->ei)
-		dentry = create_dir(ef->name, parent, ef->data);
-	else
-		dentry = create_file(ef->name, ef->mode, parent,
-				     ef->data, ef->fop);
+	dentry = create_dir(ei, parent);
 
 	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 (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
+		/*
+		 * When the mutex was released, something else could have
+		 * created the dentry for this e_dentry. In which case
+		 * use that one.
+		 *
+		 * Note, with the mutex held, the e_dentry cannot have content
+		 * and the ei->is_freed be true at the same time.
+		 */
+		dentry = ei->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;
+	if (!ei->dentry && !ei->is_freed) {
+		ei->dentry = dentry;
+		eventfs_post_create_dir(ei);
+		dentry->d_fsdata = ei;
 	} 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);
+		WARN_ON_ONCE(!ei->is_freed);
+		invalidate = true;
 	}
 	mutex_unlock(&eventfs_mutex);
 	if (invalidate)
@@ -349,50 +505,90 @@ create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
 	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;
-}
-
 /**
  * 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)
 {
+	const struct file_operations *fops;
+	const struct eventfs_entry *entry;
+	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
+	struct dentry *ei_dentry = NULL;
 	struct dentry *ret = NULL;
+	const char *name = dentry->d_name.name;
+	bool created = false;
+	umode_t mode;
+	void *data;
 	int idx;
+	int i;
+	int r;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
 		return NULL;
 
-	ei = ti->private;
+	/* Grab srcu to prevent the ei from going away */
 	idx = srcu_read_lock(&eventfs_srcu);
-	list_for_each_entry_srcu(ef, &ei->e_top_files, list,
+
+	/*
+	 * Grab the eventfs_mutex to consistent value from ti->private.
+	 * This s
+	 */
+	mutex_lock(&eventfs_mutex);
+	ei = READ_ONCE(ti->private);
+	if (ei && !ei->is_freed)
+		ei_dentry = READ_ONCE(ei->dentry);
+	mutex_unlock(&eventfs_mutex);
+
+	if (!ei || !ei_dentry)
+		goto out;
+
+	data = ei->data;
+
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
-		if (!match_event_file(ef, dentry->d_name.name))
+		if (strcmp(ei_child->name, name) != 0)
 			continue;
 		ret = simple_lookup(dir, dentry, flags);
-		create_dentry(ef, ef->d_parent, true);
+		create_dir_dentry(ei, ei_child, ei_dentry, true);
+		created = true;
 		break;
 	}
+
+	if (created)
+		goto out;
+
+	for (i = 0; i < ei->nr_entries; i++) {
+		entry = &ei->entries[i];
+		if (strcmp(name, entry->name) == 0) {
+			void *cdata = data;
+			mutex_lock(&eventfs_mutex);
+			/* If ei->is_freed, then the event itself may be too */
+			if (!ei->is_freed)
+				r = entry->callback(name, &mode, &cdata, &fops);
+			else
+				r = -1;
+			mutex_unlock(&eventfs_mutex);
+			if (r <= 0)
+				continue;
+			ret = simple_lookup(dir, dentry, flags);
+			create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
+					   fops, true);
+			break;
+		}
+	}
+ out:
 	srcu_read_unlock(&eventfs_srcu, idx);
 	return ret;
 }
@@ -432,29 +628,48 @@ static int eventfs_release(struct inode *inode, struct file *file)
 	return dcache_dir_close(inode, file);
 }
 
+static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt)
+{
+	struct dentry **tmp;
+
+	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_KERNEL);
+	if (!tmp)
+		return -1;
+	tmp[cnt] = d;
+	tmp[cnt + 1] = NULL;
+	*dentries = tmp;
+	return 0;
+}
+
 /**
  * dcache_dir_open_wrapper - eventfs open wrapper
  * @inode: not used
- * @file: dir to be opened (to create its child)
+ * @file: dir to be opened (to create it's children)
  *
- * 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.
+ * Used to dynamic create file/dir with-in @file, all the
+ * file/dir will be created. If already created then references
+ * will be increased
  */
 static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 {
+	const struct file_operations *fops;
+	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 *parent = file_dentry(file);
 	struct dentry *d;
 	struct inode *f_inode = file_inode(file);
+	const char *name = parent->d_name.name;
+	umode_t mode;
+	void *data;
 	int cnt = 0;
 	int idx;
 	int ret;
+	int i;
+	int r;
 
 	ti = get_tracefs(f_inode);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
@@ -463,25 +678,56 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 	if (WARN_ON_ONCE(file->private_data))
 		return -EINVAL;
 
+	idx = srcu_read_lock(&eventfs_srcu);
+
+	mutex_lock(&eventfs_mutex);
+	ei = READ_ONCE(ti->private);
+	mutex_unlock(&eventfs_mutex);
+
+	if (!ei) {
+		srcu_read_unlock(&eventfs_srcu, idx);
+		return -EINVAL;
+	}
+
+
+	data = ei->data;
+
 	dlist = kmalloc(sizeof(*dlist), GFP_KERNEL);
-	if (!dlist)
+	if (!dlist) {
+		srcu_read_unlock(&eventfs_srcu, idx);
 		return -ENOMEM;
+	}
 
-	ei = ti->private;
-	idx = srcu_read_lock(&eventfs_srcu);
-	list_for_each_entry_srcu(ef, &ei->e_top_files, list,
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
-		d = create_dentry(ef, dentry, false);
+		d = create_dir_dentry(ei, ei_child, parent, false);
 		if (d) {
-			struct dentry **tmp;
+			ret = add_dentries(&dentries, d, cnt);
+			if (ret < 0)
+				break;
+			cnt++;
+		}
+	}
 
-			tmp = krealloc(dentries, sizeof(d) * (cnt + 2), GFP_KERNEL);
-			if (!tmp)
+	for (i = 0; i < ei->nr_entries; i++) {
+		void *cdata = data;
+		entry = &ei->entries[i];
+		name = entry->name;
+		mutex_lock(&eventfs_mutex);
+		/* If ei->is_freed, then the event itself may be too */
+		if (!ei->is_freed)
+			r = entry->callback(name, &mode, &cdata, &fops);
+		else
+			r = -1;
+		mutex_unlock(&eventfs_mutex);
+		if (r <= 0)
+			continue;
+		d = create_file_dentry(ei, i, parent, name, mode, cdata, fops, false);
+		if (d) {
+			ret = add_dentries(&dentries, d, cnt);
+			if (ret < 0)
 				break;
-			tmp[cnt] = d;
-			tmp[cnt + 1] = NULL;
 			cnt++;
-			dentries = tmp;
 		}
 	}
 	srcu_read_unlock(&eventfs_srcu, idx);
@@ -514,63 +760,104 @@ static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx)
 }
 
 /**
- * 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.
+ * 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;
  *
- * This function allocates and fills the eventfs_file structure.
+ * 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.
+ *
+ * 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.
  */
-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_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent,
+					 const struct eventfs_entry *entries,
+					 int size, void *data)
 {
-	struct eventfs_file *ef;
+	struct eventfs_inode *ei;
 
-	ef = kzalloc(sizeof(*ef), GFP_KERNEL);
-	if (!ef)
+	if (!parent)
+		return ERR_PTR(-EINVAL);
+
+	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	if (!ei)
 		return ERR_PTR(-ENOMEM);
 
-	ef->name = kstrdup(name, GFP_KERNEL);
-	if (!ef->name) {
-		kfree(ef);
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name) {
+		kfree(ei);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (S_ISDIR(mode)) {
-		ef->ei = kzalloc(sizeof(*ef->ei), GFP_KERNEL);
-		if (!ef->ei) {
-			kfree(ef->name);
-			kfree(ef);
+	if (size) {
+		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
+		if (!ei->d_children) {
+			kfree_const(ei->name);
+			kfree(ei);
 			return ERR_PTR(-ENOMEM);
 		}
-		INIT_LIST_HEAD(&ef->ei->e_top_files);
-	} else {
-		ef->ei = NULL;
 	}
 
-	ef->iop = iop;
-	ef->fop = fop;
-	ef->mode = mode;
-	ef->data = data;
-	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);
+	if (!parent->is_freed) {
+		list_add_tail(&ei->list, &parent->children);
+		ei->d_parent = parent->dentry;
+	}
+	mutex_unlock(&eventfs_mutex);
+
+	/* Was the parent freed? */
+	if (list_empty(&ei->list)) {
+		free_ei(ei);
+		ei = NULL;
+	}
+	return ei;
 }
 
 /**
- * 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.
+ * 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 creates the top of the trace event directory.
+ *
+ * See eventfs_create_dir() for use of @entries.
  */
-struct dentry *eventfs_create_events_dir(const char *name,
-					 struct dentry *parent)
+struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent,
+						const struct eventfs_entry *entries,
+						int size, void *data)
 {
 	struct dentry *dentry = tracefs_start_creating(name, parent);
 	struct eventfs_inode *ei;
@@ -581,19 +868,32 @@ struct dentry *eventfs_create_events_dir(const char *name,
 		return NULL;
 
 	if (IS_ERR(dentry))
-		return dentry;
+		return ERR_CAST(dentry);
 
 	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
 	if (!ei)
-		return ERR_PTR(-ENOMEM);
+		goto fail_ei;
+
 	inode = tracefs_get_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		kfree(ei);
-		tracefs_failed_creating(dentry);
-		return ERR_PTR(-ENOMEM);
+	if (unlikely(!inode))
+		goto fail;
+
+	if (size) {
+		ei->d_children = kzalloc(sizeof(*ei->d_children) * size, GFP_KERNEL);
+		if (!ei->d_children)
+			goto fail;
 	}
 
-	INIT_LIST_HEAD(&ei->e_top_files);
+	ei->dentry = dentry;
+	ei->entries = entries;
+	ei->nr_entries = size;
+	ei->data = data;
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name)
+		goto fail;
+
+	INIT_LIST_HEAD(&ei->children);
+	INIT_LIST_HEAD(&ei->list);
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
@@ -603,198 +903,97 @@ struct dentry *eventfs_create_events_dir(const char *name,
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
+	dentry->d_fsdata = ei;
+
 	/* 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);
-}
-
-/**
- * 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.
- *
- * 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.
- */
-struct eventfs_file *eventfs_add_subsystem_dir(const char *name,
-					       struct dentry *parent)
-{
-	struct tracefs_inode *ti_parent;
-	struct eventfs_inode *ei_parent;
-	struct eventfs_file *ef;
-
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return NULL;
-
-	if (!parent)
-		return ERR_PTR(-EINVAL);
-
-	ti_parent = get_tracefs(parent->d_inode);
-	ei_parent = ti_parent->private;
+	tracefs_end_creating(dentry);
 
-	ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL);
-	if (IS_ERR(ef))
-		return ef;
+	return ei;
 
-	mutex_lock(&eventfs_mutex);
-	list_add_tail(&ef->list, &ei_parent->e_top_files);
-	ef->d_parent = parent;
-	mutex_unlock(&eventfs_mutex);
-	return ef;
+ fail:
+	kfree(ei->d_children);
+	kfree(ei);
+ fail_ei:
+	tracefs_failed_creating(dentry);
+	return ERR_PTR(-ENOMEM);
 }
 
-/**
- * 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;
+static LLIST_HEAD(free_list);
 
-	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;
-}
-
-/**
- * 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.
- *
- * 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.
- */
-int eventfs_add_events_file(const char *name, umode_t mode,
-			 struct dentry *parent, void *data,
-			 const struct file_operations *fop)
+static void eventfs_workfn(struct work_struct *work)
 {
-	struct tracefs_inode *ti;
-	struct eventfs_inode *ei;
-	struct eventfs_file *ef;
-
-	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;
+        struct eventfs_inode *ei, *tmp;
+        struct llist_node *llnode;
+
+	llnode = llist_del_all(&free_list);
+        llist_for_each_entry_safe(ei, tmp, llnode, llist) {
+		/* This dput() matches the dget() from unhook_dentry() */
+		for (int i = 0; i < ei->nr_entries; i++) {
+			if (ei->d_children[i])
+				dput(ei->d_children[i]);
+		}
+		/* This should only get here if it had a dentry */
+		if (!WARN_ON_ONCE(!ei->dentry))
+			dput(ei->dentry);
+        }
 }
 
-/**
- * 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;
-
-	if (security_locked_down(LOCKDOWN_TRACEFS))
-		return -ENODEV;
+static DECLARE_WORK(eventfs_work, eventfs_workfn);
 
-	if (!ef_parent)
-		return -EINVAL;
+static void free_rcu_ei(struct rcu_head *head)
+{
+	struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu);
 
-	if (!(mode & S_IFMT))
-		mode |= S_IFREG;
+	if (ei->dentry) {
+		/* Do not free the ei until all references of dentry are gone */
+		if (llist_add(&ei->llist, &free_list))
+			queue_work(system_unbound_wq, &eventfs_work);
+		return;
+	}
 
-	ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
-	if (IS_ERR(ef))
-		return -ENOMEM;
+	/* If the ei doesn't have a dentry, neither should its children */
+	for (int i = 0; i < ei->nr_entries; i++) {
+		WARN_ON_ONCE(ei->d_children[i]);
+	}
 
-	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;
+	free_ei(ei);
 }
 
-static void free_ef(struct rcu_head *head)
+static void unhook_dentry(struct dentry *dentry)
 {
-	struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu);
+	if (!dentry)
+		return;
+	/*
+	 * Need to add a reference to the dentry that is expected by
+	 * simple_recursive_removal(), which will include a dput().
+	 */
+	dget(dentry);
 
-	kfree(ef->name);
-	kfree(ef->ei);
-	kfree(ef);
+	/*
+	 * 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);
 }
 
 /**
  * eventfs_remove_rec - remove eventfs dir or file from list
- * @ef: eventfs_file to be removed.
- * @head: to create list of eventfs_file to be deleted
- * @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, struct list_head *head, 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)
+	if (!ei)
 		return;
 	/*
 	 * Check recursion depth. It should never be greater than 3:
@@ -806,100 +1005,76 @@ static void eventfs_remove_rec(struct eventfs_file *ef, struct list_head *head,
 	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, head, level + 1);
+	/* search for nested folders or files */
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 lockdep_is_held(&eventfs_mutex)) {
+		/* Children only have dentry if parent does */
+		WARN_ON_ONCE(ei_child->dentry && !ei->dentry);
+		eventfs_remove_rec(ei_child, level + 1);
+	}
+
+
+	ei->is_freed = 1;
+
+	for (int i = 0; i < ei->nr_entries; i++) {
+		if (ei->d_children[i]) {
+			/* Children only have dentry if parent does */
+			WARN_ON_ONCE(!ei->dentry);
+			unhook_dentry(ei->d_children[i]);
 		}
 	}
 
-	list_del_rcu(&ef->list);
-	list_add_tail(&ef->del_list, head);
+	unhook_dentry(ei->dentry);
+
+	list_del_rcu(&ei->list);
+	call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_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 eventfs_file *tmp;
-	LIST_HEAD(ef_del_list);
-	struct dentry *dentry_list = NULL;
 	struct dentry *dentry;
 
-	if (!ef)
+	if (!ei)
 		return;
 
 	mutex_lock(&eventfs_mutex);
-	eventfs_remove_rec(ef, &ef_del_list, 0);
-	list_for_each_entry_safe(ef, tmp, &ef_del_list, del_list) {
-		if (ef->dentry) {
-			unsigned long ptr = (unsigned long)dentry_list;
-
-			/* Keep the dentry from being freed yet */
-			dget(ef->dentry);
-
-			/*
-			 * Paranoid: The dget() above should prevent the dentry
-			 * from being freed and calling eventfs_set_ef_status_free().
-			 * But just in case, set the link list LSB pointer to 1
-			 * and have eventfs_set_ef_status_free() check that to
-			 * make sure that if it does happen, it will not think
-			 * the d_fsdata is an event_file.
-			 *
-			 * For this to work, no event_file should be allocated
-			 * on a odd space, as the ef should always be allocated
-			 * to be at least word aligned. Check for that too.
-			 */
-			WARN_ON_ONCE(ptr & 1);
-
-			ef->dentry->d_fsdata = (void *)(ptr | 1);
-			dentry_list = ef->dentry;
-			ef->dentry = NULL;
-		}
-		call_srcu(&eventfs_srcu, &ef->rcu, free_ef);
-	}
+	dentry = ei->dentry;
+	eventfs_remove_rec(ei, 0);
 	mutex_unlock(&eventfs_mutex);
 
-	while (dentry_list) {
-		unsigned long ptr;
-
-		dentry = dentry_list;
-		ptr = (unsigned long)dentry->d_fsdata & ~1UL;
-		dentry_list = (struct dentry *)ptr;
-		dentry->d_fsdata = NULL;
-		d_invalidate(dentry);
-		mutex_lock(&eventfs_mutex);
-		/* dentry should now have at least a single reference */
-		WARN_ONCE((int)d_count(dentry) < 1,
-			  "dentry %p less than one reference (%d) after invalidate\n",
-			  dentry, d_count(dentry));
-		mutex_unlock(&eventfs_mutex);
-		dput(dentry);
-	}
+	/*
+	 * 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 tracefs_inode *ti;
-
-	if (!dentry || !dentry->d_inode)
-		return;
+	struct dentry *dentry;
 
-	ti = get_tracefs(dentry->d_inode);
-	if (!ti || !(ti->flags & TRACEFS_EVENT_INODE))
-		return;
+	dentry = ei->dentry;
+	eventfs_remove_dir(ei);
 
-	d_invalidate(dentry);
+	/*
+	 * 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.
+	 */
 	dput(dentry);
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 429603d865a9..5b54948514fe 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -385,7 +385,7 @@ static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
 
 	ti = get_tracefs(inode);
 	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ef_status_free(ti, dentry);
+		eventfs_set_ei_status_free(ti, dentry);
 	iput(inode);
 }
 
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 4f2e49e2197b..ccee18ca66c7 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -13,6 +13,58 @@ struct tracefs_inode {
 	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
+ * @entries:	the array of entries representing the files in the directory
+ * @name:	the name of the directory to create
+ * @children:	link list into the child eventfs_inode
+ * @dentry:     the dentry of the directory
+ * @d_parent:   pointer to the parent's dentry
+ * @d_children: The array of dentries to represent the files when created
+ * @entry_attrs: Saved mode and ownership of the @d_children
+ * @attr:	Saved mode and ownership of eventfs_inode itself
+ * @data:	The private data to pass to the callbacks
+ * @is_freed:	Flag set if the eventfs is on its way to be freed
+ *                Note if is_freed is set, then dentry is corrupted.
+ * @nr_entries: The number of items in @entries
+ */
+struct eventfs_inode {
+	struct list_head		list;
+	const struct eventfs_entry	*entries;
+	const char			*name;
+	struct list_head		children;
+	struct dentry			*dentry; /* Check is_freed to access */
+	struct dentry			*d_parent;
+	struct dentry			**d_children;
+	struct eventfs_attr		*entry_attrs;
+	struct eventfs_attr		attr;
+	void				*data;
+	/*
+	 * Union - used for deletion
+	 * @llist:	for calling dput() if needed after RCU
+	 * @rcu:	eventfs_inode to delete in RCU
+	 */
+	union {
+		struct llist_node	llist;
+		struct rcu_head		rcu;
+	};
+	unsigned int			is_freed:1;
+	unsigned int			nr_entries:31;
+};
+
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
 {
 	return container_of(inode, struct tracefs_inode, vfs_inode);
@@ -25,6 +77,6 @@ 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_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */