Adding upstream version 6.6.15.upstream/6.6.15

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

4 files changed, 1787 insertions, 0 deletions

diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile
new file mode 100644
index 0000000000..73c56da8e2
--- /dev/null
+++ b/fs/tracefs/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+tracefs-objs	:= inode.o
+tracefs-objs	+= event_inode.o
+
+obj-$(CONFIG_TRACING)	+= tracefs.o
+
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
new file mode 100644
index 0000000000..efbdc47c74
--- /dev/null
+++ b/fs/tracefs/event_inode.c
@@ -0,0 +1,975 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  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: Ajay Kaher <akaher@vmware.com>
+ *
+ *  eventfs is used to dynamically create inodes and dentries based on the
+ *  meta data provided by the tracing system.
+ *
+ *  eventfs stores the meta-data of files/dirs and holds off on creating
+ *  inodes/dentries of the files. When accessed, the eventfs will create the
+ *  inodes/dentries in a just-in-time (JIT) manner. The eventfs will clean up
+ *  and delete the inodes/dentries when they are no longer referenced.
+ */
+#include <linux/fsnotify.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/workqueue.h>
+#include <linux/security.h>
+#include <linux/tracefs.h>
+#include <linux/kref.h>
+#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
+ */
+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);
+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),
+};
+
+#define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
+
+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 void update_attr(struct eventfs_file *ef, struct iattr *iattr)
+{
+	unsigned int ia_valid = iattr->ia_valid;
+
+	if (ia_valid & ATTR_MODE) {
+		ef->mode = (ef->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;
+	}
+	if (ia_valid & ATTR_GID) {
+		ef->mode |= EVENTFS_SAVE_GID;
+		ef->gid = iattr->ia_gid;
+	}
+}
+
+static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
+			     struct iattr *iattr)
+{
+	struct eventfs_file *ef;
+	int ret;
+
+	mutex_lock(&eventfs_mutex);
+	ef = dentry->d_fsdata;
+	if (ef && ef->is_freed) {
+		/* Do not allow changes if the event is about to be removed. */
+		mutex_unlock(&eventfs_mutex);
+		return -ENODEV;
+	}
+
+	ret = simple_setattr(idmap, dentry, iattr);
+	if (!ret && ef)
+		update_attr(ef, iattr);
+	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 = {
+	.open		= dcache_dir_open_wrapper,
+	.read		= generic_read_dir,
+	.iterate_shared	= dcache_readdir_wrapper,
+	.llseek		= generic_file_llseek,
+	.release	= eventfs_release,
+};
+
+static void update_inode_attr(struct inode *inode, struct eventfs_file *ef)
+{
+	inode->i_mode = ef->mode & EVENTFS_MODE_MASK;
+
+	if (ef->mode & EVENTFS_SAVE_UID)
+		inode->i_uid = ef->uid;
+
+	if (ef->mode & EVENTFS_SAVE_GID)
+		inode->i_gid = ef->gid;
+}
+
+/**
+ * create_file - create a file in the tracefs filesystem
+ * @ef: the eventfs_file
+ * @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.
+ */
+static struct dentry *create_file(struct eventfs_file *ef,
+				  struct dentry *parent, 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 (IS_ERR(dentry))
+		return dentry;
+
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return eventfs_failed_creating(dentry);
+
+	/* If the user updated the directory's attributes, use them */
+	update_inode_attr(inode, ef);
+
+	inode->i_op = &eventfs_file_inode_operations;
+	inode->i_fop = fop;
+	inode->i_private = data;
+
+	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);
+};
+
+/**
+ * create_dir - create a dir in the tracefs filesystem
+ * @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.
+ */
+static struct dentry *create_dir(struct eventfs_file *ef,
+				 struct dentry *parent, void *data)
+{
+	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);
+
+	update_inode_attr(inode, ef);
+
+	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;
+
+	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);
+}
+
+static void free_ef(struct eventfs_file *ef)
+{
+	kfree(ef->name);
+	kfree(ef->ei);
+	kfree(ef);
+}
+
+/**
+ * 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)
+{
+	struct eventfs_inode *ei;
+	struct eventfs_file *ef;
+
+	/* 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 (ef->is_freed) {
+		free_ef(ef);
+	} else {
+		ef->dentry = NULL;
+	}
+
+	dentry->d_fsdata = NULL;
+out:
+	mutex_unlock(&eventfs_mutex);
+}
+
+/**
+ * eventfs_post_create_dir - post create dir routine
+ * @ef: eventfs_file 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)
+{
+	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;
+}
+
+/**
+ * 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
+ *
+ * Used to create a dentry for file/dir, executes post dentry creation routine
+ */
+static struct dentry *
+create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup)
+{
+	bool invalidate = false;
+	struct dentry *dentry;
+
+	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 (!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;
+}
+
+/**
+ * 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
+ *
+ * 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.
+ */
+static struct dentry *eventfs_root_lookup(struct inode *dir,
+					  struct dentry *dentry,
+					  unsigned int flags)
+{
+	struct tracefs_inode *ti;
+	struct eventfs_inode *ei;
+	struct eventfs_file *ef;
+	struct dentry *ret = NULL;
+	int idx;
+
+	ti = get_tracefs(dir);
+	if (!(ti->flags & TRACEFS_EVENT_INODE))
+		return NULL;
+
+	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))
+			continue;
+		ret = simple_lookup(dir, dentry, flags);
+		create_dentry(ef, ef->d_parent, true);
+		break;
+	}
+	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;
+
+	ti = get_tracefs(inode);
+	if (!(ti->flags & TRACEFS_EVENT_INODE))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(!dlist))
+		return -EINVAL;
+
+	for (i = 0; dlist->dentries && dlist->dentries[i]; i++) {
+		dput(dlist->dentries[i]);
+	}
+
+	cursor = dlist->cursor;
+	kfree(dlist->dentries);
+	kfree(dlist);
+	file->private_data = cursor;
+	return dcache_dir_close(inode, file);
+}
+
+/**
+ * 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.
+ */
+static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
+{
+	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;
+	int idx;
+	int ret;
+
+	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;
+
+	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;
+
+
+			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);
+
+	/*
+	 * 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.
+	 */
+	dlist->cursor = file->private_data;
+	dlist->dentries = dentries;
+	file->private_data = dlist;
+	return ret;
+}
+
+/*
+ * 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;
+
+	file->private_data = dlist->cursor;
+	ret = dcache_readdir(file, ctx);
+	dlist->cursor = file->private_data;
+	file->private_data = dlist;
+	return ret;
+}
+
+/**
+ * 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;
+
+	ef = kzalloc(sizeof(*ef), GFP_KERNEL);
+	if (!ef)
+		return ERR_PTR(-ENOMEM);
+
+	ef->name = kstrdup(name, GFP_KERNEL);
+	if (!ef->name) {
+		kfree(ef);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	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;
+	}
+
+	ef->iop = iop;
+	ef->fop = fop;
+	ef->data = data;
+	return ef;
+}
+
+/**
+ * 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 (security_locked_down(LOCKDOWN_TRACEFS))
+		return NULL;
+
+	if (IS_ERR(dentry))
+		return dentry;
+
+	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);
+	}
+
+	INIT_LIST_HEAD(&ei->e_top_files);
+
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
+	ti->private = ei;
+
+	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;
+
+	/* 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;
+
+	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, &ei_parent->e_top_files);
+	ef->d_parent = parent;
+	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;
+}
+
+/**
+ * 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)
+{
+	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;
+}
+
+/**
+ * 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;
+
+	if (!ef_parent)
+		return -EINVAL;
+
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
+
+	ef = eventfs_prepare_ef(name, mode, fop, NULL, data);
+	if (IS_ERR(ef))
+		return -ENOMEM;
+
+	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;
+}
+
+static LLIST_HEAD(free_list);
+
+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);
+        }
+}
+
+static DECLARE_WORK(eventfs_work, eventfs_workfn);
+
+static void free_rcu_ef(struct rcu_head *head)
+{
+	struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu);
+
+	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;
+	}
+
+	free_ef(ef);
+}
+
+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().
+	 */
+	dget(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);
+}
+
+/**
+ * eventfs_remove_rec - remove eventfs dir or file from list
+ * @ef: eventfs_file to be removed.
+ * @level: to check recursion depth
+ *
+ * The helper function eventfs_remove_rec() is used to clean up and free the
+ * associated data from eventfs for both of the added functions.
+ */
+static void eventfs_remove_rec(struct eventfs_file *ef, int level)
+{
+	struct eventfs_file *ef_child;
+
+	if (!ef)
+		return;
+	/*
+	 * Check recursion depth. It should never be greater than 3:
+	 * 0 - events/
+	 * 1 - events/group/
+	 * 2 - events/group/event/
+	 * 3 - events/group/event/file
+	 */
+	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;
+
+	unhook_dentry(ef->dentry);
+
+	list_del_rcu(&ef->list);
+	call_srcu(&eventfs_srcu, &ef->rcu, free_rcu_ef);
+}
+
+/**
+ * eventfs_remove - remove eventfs dir or file from list
+ * @ef: eventfs_file to be removed.
+ *
+ * This function acquire the eventfs_mutex lock and call eventfs_remove_rec()
+ */
+void eventfs_remove(struct eventfs_file *ef)
+{
+	struct dentry *dentry;
+
+	if (!ef)
+		return;
+
+	mutex_lock(&eventfs_mutex);
+	dentry = ef->dentry;
+	eventfs_remove_rec(ef, 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.
+ *
+ * This function remove events main directory
+ */
+void eventfs_remove_events_dir(struct dentry *dentry)
+{
+	struct eventfs_file *ef_child;
+	struct eventfs_inode *ei;
+	struct tracefs_inode *ti;
+
+	if (!dentry || !dentry->d_inode)
+		return;
+
+	ti = get_tracefs(dentry->d_inode);
+	if (!ti || !(ti->flags & TRACEFS_EVENT_INODE))
+		return;
+
+	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);
+}
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
new file mode 100644
index 0000000000..0292c6a2be
--- /dev/null
+++ b/fs/tracefs/inode.c
@@ -0,0 +1,776 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  inode.c - part of tracefs, a pseudo file system for activating tracing
+ *
+ * Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com>
+ *
+ *  Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com>
+ *
+ * tracefs is the file system that is used by the tracing infrastructure.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/kobject.h>
+#include <linux/namei.h>
+#include <linux/tracefs.h>
+#include <linux/fsnotify.h>
+#include <linux/security.h>
+#include <linux/seq_file.h>
+#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+#define TRACEFS_DEFAULT_MODE	0700
+static struct kmem_cache *tracefs_inode_cachep __ro_after_init;
+
+static struct vfsmount *tracefs_mount;
+static int tracefs_mount_count;
+static bool tracefs_registered;
+
+static struct inode *tracefs_alloc_inode(struct super_block *sb)
+{
+	struct tracefs_inode *ti;
+
+	ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
+	if (!ti)
+		return NULL;
+
+	ti->flags = 0;
+
+	return &ti->vfs_inode;
+}
+
+static void tracefs_free_inode(struct inode *inode)
+{
+	kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode));
+}
+
+static ssize_t default_read_file(struct file *file, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	return 0;
+}
+
+static ssize_t default_write_file(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	return count;
+}
+
+static const struct file_operations tracefs_file_operations = {
+	.read =		default_read_file,
+	.write =	default_write_file,
+	.open =		simple_open,
+	.llseek =	noop_llseek,
+};
+
+static struct tracefs_dir_ops {
+	int (*mkdir)(const char *name);
+	int (*rmdir)(const char *name);
+} tracefs_ops __ro_after_init;
+
+static char *get_dname(struct dentry *dentry)
+{
+	const char *dname;
+	char *name;
+	int len = dentry->d_name.len;
+
+	dname = dentry->d_name.name;
+	name = kmalloc(len + 1, GFP_KERNEL);
+	if (!name)
+		return NULL;
+	memcpy(name, dname, len);
+	name[len] = 0;
+	return name;
+}
+
+static int tracefs_syscall_mkdir(struct mnt_idmap *idmap,
+				 struct inode *inode, struct dentry *dentry,
+				 umode_t mode)
+{
+	char *name;
+	int ret;
+
+	name = get_dname(dentry);
+	if (!name)
+		return -ENOMEM;
+
+	/*
+	 * 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.
+	 */
+	inode_unlock(inode);
+	ret = tracefs_ops.mkdir(name);
+	inode_lock(inode);
+
+	kfree(name);
+
+	return ret;
+}
+
+static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
+{
+	char *name;
+	int ret;
+
+	name = get_dname(dentry);
+	if (!name)
+		return -ENOMEM;
+
+	/*
+	 * The rmdir call can call the generic functions that create
+	 * the files within the tracefs system. It is up to the individual
+	 * rmdir routine to handle races.
+	 * This time we need to unlock not only the parent (inode) but
+	 * also the directory that is being deleted.
+	 */
+	inode_unlock(inode);
+	inode_unlock(d_inode(dentry));
+
+	ret = tracefs_ops.rmdir(name);
+
+	inode_lock_nested(inode, I_MUTEX_PARENT);
+	inode_lock(d_inode(dentry));
+
+	kfree(name);
+
+	return ret;
+}
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.mkdir		= tracefs_syscall_mkdir,
+	.rmdir		= tracefs_syscall_rmdir,
+};
+
+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);
+	}
+	return inode;
+}
+
+struct tracefs_mount_opts {
+	kuid_t uid;
+	kgid_t gid;
+	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
+};
+
+enum {
+	Opt_uid,
+	Opt_gid,
+	Opt_mode,
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{Opt_uid, "uid=%u"},
+	{Opt_gid, "gid=%u"},
+	{Opt_mode, "mode=%o"},
+	{Opt_err, NULL}
+};
+
+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];
+	int option;
+	int token;
+	kuid_t uid;
+	kgid_t gid;
+	char *p;
+
+	opts->opts = 0;
+	opts->mode = TRACEFS_DEFAULT_MODE;
+
+	while ((p = strsep(&data, ",")) != NULL) {
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_uid:
+			if (match_int(&args[0], &option))
+				return -EINVAL;
+			uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(uid))
+				return -EINVAL;
+			opts->uid = uid;
+			break;
+		case Opt_gid:
+			if (match_int(&args[0], &option))
+				return -EINVAL;
+			gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(gid))
+				return -EINVAL;
+			opts->gid = gid;
+			break;
+		case Opt_mode:
+			if (match_octal(&args[0], &option))
+				return -EINVAL;
+			opts->mode = option & S_IALLUGO;
+			break;
+		/*
+		 * We might like to report bad mount options here;
+		 * but traditionally tracefs has ignored all mount options
+		 */
+		}
+
+		opts->opts |= BIT(token);
+	}
+
+	return 0;
+}
+
+static int tracefs_apply_options(struct super_block *sb, bool remount)
+{
+	struct tracefs_fs_info *fsi = sb->s_fs_info;
+	struct inode *inode = d_inode(sb->s_root);
+	struct tracefs_mount_opts *opts = &fsi->mount_opts;
+	umode_t tmp_mode;
+
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
+
+	if (!remount || opts->opts & BIT(Opt_mode)) {
+		tmp_mode = READ_ONCE(inode->i_mode) & ~S_IALLUGO;
+		tmp_mode |= opts->mode;
+		WRITE_ONCE(inode->i_mode, tmp_mode);
+	}
+
+	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);
+	}
+
+	return 0;
+}
+
+static int tracefs_remount(struct super_block *sb, int *flags, char *data)
+{
+	int err;
+	struct tracefs_fs_info *fsi = sb->s_fs_info;
+
+	sync_filesystem(sb);
+	err = tracefs_parse_options(data, &fsi->mount_opts);
+	if (err)
+		goto fail;
+
+	tracefs_apply_options(sb, true);
+
+fail:
+	return err;
+}
+
+static int tracefs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct tracefs_fs_info *fsi = root->d_sb->s_fs_info;
+	struct tracefs_mount_opts *opts = &fsi->mount_opts;
+
+	if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, opts->uid));
+	if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, opts->gid));
+	if (opts->mode != TRACEFS_DEFAULT_MODE)
+		seq_printf(m, ",mode=%o", opts->mode);
+
+	return 0;
+}
+
+static const struct super_operations tracefs_super_operations = {
+	.alloc_inode    = tracefs_alloc_inode,
+	.free_inode     = tracefs_free_inode,
+	.drop_inode     = generic_delete_inode,
+	.statfs		= simple_statfs,
+	.remount_fs	= tracefs_remount,
+	.show_options	= tracefs_show_options,
+};
+
+static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+{
+	struct tracefs_inode *ti;
+
+	if (!dentry || !inode)
+		return;
+
+	ti = get_tracefs(inode);
+	if (ti && ti->flags & TRACEFS_EVENT_INODE)
+		eventfs_set_ef_status_free(ti, dentry);
+	iput(inode);
+}
+
+static const struct dentry_operations tracefs_dentry_operations = {
+	.d_iput = tracefs_dentry_iput,
+};
+
+static int trace_fill_super(struct super_block *sb, void *data, int silent)
+{
+	static const struct tree_descr trace_files[] = {{""}};
+	struct tracefs_fs_info *fsi;
+	int err;
+
+	fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL);
+	sb->s_fs_info = fsi;
+	if (!fsi) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	err = tracefs_parse_options(data, &fsi->mount_opts);
+	if (err)
+		goto fail;
+
+	err  =  simple_fill_super(sb, TRACEFS_MAGIC, trace_files);
+	if (err)
+		goto fail;
+
+	sb->s_op = &tracefs_super_operations;
+	sb->s_d_op = &tracefs_dentry_operations;
+
+	tracefs_apply_options(sb, false);
+
+	return 0;
+
+fail:
+	kfree(fsi);
+	sb->s_fs_info = NULL;
+	return err;
+}
+
+static struct dentry *trace_mount(struct file_system_type *fs_type,
+			int flags, const char *dev_name,
+			void *data)
+{
+	return mount_single(fs_type, flags, data, trace_fill_super);
+}
+
+static struct file_system_type trace_fs_type = {
+	.owner =	THIS_MODULE,
+	.name =		"tracefs",
+	.mount =	trace_mount,
+	.kill_sb =	kill_litter_super,
+};
+MODULE_ALIAS_FS("tracefs");
+
+struct dentry *tracefs_start_creating(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+	int error;
+
+	pr_debug("tracefs: creating file '%s'\n",name);
+
+	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
+			      &tracefs_mount_count);
+	if (error)
+		return ERR_PTR(error);
+
+	/* If the parent is not specified, we create it in the root.
+	 * We need the root dentry to do this, which is in the super
+	 * block. A pointer to that is in the struct vfsmount that we
+	 * have around.
+	 */
+	if (!parent)
+		parent = tracefs_mount->mnt_root;
+
+	inode_lock(d_inode(parent));
+	if (unlikely(IS_DEADDIR(d_inode(parent))))
+		dentry = ERR_PTR(-ENOENT);
+	else
+		dentry = lookup_one_len(name, parent, strlen(name));
+	if (!IS_ERR(dentry) && d_inode(dentry)) {
+		dput(dentry);
+		dentry = ERR_PTR(-EEXIST);
+	}
+
+	if (IS_ERR(dentry)) {
+		inode_unlock(d_inode(parent));
+		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	}
+
+	return dentry;
+}
+
+struct dentry *tracefs_failed_creating(struct dentry *dentry)
+{
+	inode_unlock(d_inode(dentry->d_parent));
+	dput(dentry);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	return NULL;
+}
+
+struct dentry *tracefs_end_creating(struct dentry *dentry)
+{
+	inode_unlock(d_inode(dentry->d_parent));
+	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)
+{
+	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);
+
+	if (unlikely(IS_DEADDIR(parent->d_inode)))
+		dentry = ERR_PTR(-ENOENT);
+	else
+		dentry = lookup_one_len(name, parent, strlen(name));
+
+	if (!IS_ERR(dentry) && dentry->d_inode) {
+		dput(dentry);
+		dentry = ERR_PTR(-EEXIST);
+	}
+
+	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;
+}
+
+/**
+ * tracefs_create_file - create a file in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is NULL, then the
+ *          file will be created in the root of the tracefs filesystem.
+ * @data: a pointer to 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.
+ * @fops: a pointer to a 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, or a directory (if you want
+ * to create a directory, the tracefs_create_dir() function is
+ * recommended to be used instead.)
+ *
+ * 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.
+ */
+struct dentry *tracefs_create_file(const char *name, umode_t mode,
+				   struct dentry *parent, void *data,
+				   const struct file_operations *fops)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	if (security_locked_down(LOCKDOWN_TRACEFS))
+		return NULL;
+
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
+	BUG_ON(!S_ISREG(mode));
+	dentry = tracefs_start_creating(name, parent);
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return tracefs_failed_creating(dentry);
+
+	inode->i_mode = mode;
+	inode->i_fop = fops ? fops : &tracefs_file_operations;
+	inode->i_private = data;
+	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
+	d_instantiate(dentry, inode);
+	fsnotify_create(d_inode(dentry->d_parent), dentry);
+	return tracefs_end_creating(dentry);
+}
+
+static struct dentry *__create_dir(const char *name, struct dentry *parent,
+				   const struct inode_operations *ops)
+{
+	struct dentry *dentry = tracefs_start_creating(name, parent);
+	struct inode *inode;
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return tracefs_failed_creating(dentry);
+
+	/* Do not set bits for OTH */
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
+	inode->i_op = ops;
+	inode->i_fop = &simple_dir_operations;
+	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
+
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(inode);
+	d_instantiate(dentry, inode);
+	inc_nlink(d_inode(dentry->d_parent));
+	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
+	return tracefs_end_creating(dentry);
+}
+
+/**
+ * tracefs_create_dir - create a directory in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the directory to
+ *        create.
+ * @parent: a pointer to the 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 a directory in tracefs with the given name.
+ *
+ * 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. If an error occurs, %NULL will be returned.
+ *
+ * If tracing is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+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);
+}
+
+/**
+ * tracefs_create_instance_dir - create the tracing instances directory
+ * @name: The name of the instances directory to create
+ * @parent: The parent directory that the instances directory will exist
+ * @mkdir: The function to call when a mkdir is performed.
+ * @rmdir: The function to call when a rmdir is performed.
+ *
+ * Only one instances directory is allowed.
+ *
+ * The instances directory is special as it allows for mkdir and rmdir
+ * to be done by userspace. When a mkdir or rmdir is performed, the inode
+ * locks are released and the methods passed in (@mkdir and @rmdir) are
+ * called without locks and with the name of the directory being created
+ * within the instances directory.
+ *
+ * Returns the dentry of the instances directory.
+ */
+__init struct dentry *tracefs_create_instance_dir(const char *name,
+					  struct dentry *parent,
+					  int (*mkdir)(const char *name),
+					  int (*rmdir)(const char *name))
+{
+	struct dentry *dentry;
+
+	/* Only allow one instance of the instances directory. */
+	if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
+		return NULL;
+
+	dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+	if (!dentry)
+		return NULL;
+
+	tracefs_ops.mkdir = mkdir;
+	tracefs_ops.rmdir = rmdir;
+
+	return dentry;
+}
+
+static void remove_one(struct dentry *victim)
+{
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+}
+
+/**
+ * tracefs_remove - recursively removes a directory
+ * @dentry: a pointer to a the dentry of the directory to be removed.
+ *
+ * This function recursively removes a directory tree in tracefs that
+ * was previously created with a call to another tracefs function
+ * (like tracefs_create_file() or variants thereof.)
+ */
+void tracefs_remove(struct dentry *dentry)
+{
+	if (IS_ERR_OR_NULL(dentry))
+		return;
+
+	simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count);
+	simple_recursive_removal(dentry, remove_one);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+}
+
+/**
+ * tracefs_initialized - Tells whether tracefs has been registered
+ */
+bool tracefs_initialized(void)
+{
+	return tracefs_registered;
+}
+
+static void init_once(void *foo)
+{
+	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
+
+	inode_init_once(&ti->vfs_inode);
+}
+
+static int __init tracefs_init(void)
+{
+	int retval;
+
+	tracefs_inode_cachep = kmem_cache_create("tracefs_inode_cache",
+						 sizeof(struct tracefs_inode),
+						 0, (SLAB_RECLAIM_ACCOUNT|
+						     SLAB_MEM_SPREAD|
+						     SLAB_ACCOUNT),
+						 init_once);
+	if (!tracefs_inode_cachep)
+		return -ENOMEM;
+
+	retval = sysfs_create_mount_point(kernel_kobj, "tracing");
+	if (retval)
+		return -EINVAL;
+
+	retval = register_filesystem(&trace_fs_type);
+	if (!retval)
+		tracefs_registered = true;
+
+	return retval;
+}
+core_initcall(tracefs_init);
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
new file mode 100644
index 0000000000..4f2e49e219
--- /dev/null
+++ b/fs/tracefs/internal.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TRACEFS_INTERNAL_H
+#define _TRACEFS_INTERNAL_H
+
+enum {
+	TRACEFS_EVENT_INODE		= BIT(1),
+	TRACEFS_EVENT_TOP_INODE		= BIT(2),
+};
+
+struct tracefs_inode {
+	unsigned long           flags;
+	void                    *private;
+	struct inode            vfs_inode;
+};
+
+static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
+{
+	return container_of(inode, struct tracefs_inode, vfs_inode);
+}
+
+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);
+
+#endif /* _TRACEFS_INTERNAL_H */