Resguardo inicial

linux-7.2.3/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
+

linux-7.2.3/fs/tracefs/event_inode.c

@@ -0,0 +1,924 @@
+// 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 <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.
+ *
+ *  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"
+
+/*
+ * eventfs_mutex protects the eventfs_inode (ei) dentry. Any access
+ * to the ei->dentry must be done under this mutex and after checking
+ * if ei->is_freed is not set. When ei->is_freed is set, the dentry
+ * is on its way to being freed after the last dput() is made on it.
+ */
+static DEFINE_MUTEX(eventfs_mutex);
+
+/* Choose something "unique" ;-) */
+#define EVENTFS_FILE_INODE_INO		0x12c4e37
+
+struct eventfs_root_inode {
+	struct eventfs_inode		ei;
+	struct dentry			*events_dir;
+};
+
+static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei)
+{
+	WARN_ON_ONCE(!ei->is_events);
+	return container_of(ei, struct eventfs_root_inode, ei);
+}
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+	if (!ei->ino) {
+		ei->ino = get_next_ino();
+		/* Must not have the file inode number */
+		if (ei->ino == EVENTFS_FILE_INODE_INO)
+			ei->ino = get_next_ino();
+	}
+
+	return ei->ino;
+}
+
+/*
+ * The eventfs_inode (ei) itself is protected by SRCU. It is released from
+ * its parent's list and will have is_freed set (under eventfs_mutex).
+ * After the SRCU grace period is over and the last dput() is called
+ * the ei is freed.
+ */
+DEFINE_STATIC_SRCU(eventfs_srcu);
+
+/* Mode is unsigned short, use the upper bits for flags */
+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 void free_ei_rcu(struct rcu_head *rcu)
+{
+	struct eventfs_inode *ei = container_of(rcu, struct eventfs_inode, rcu);
+	struct eventfs_root_inode *rei;
+
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	if (ei->is_events) {
+		rei = get_root_inode(ei);
+		kfree(rei);
+	} else {
+		kfree(ei);
+	}
+}
+
+/*
+ * eventfs_inode reference count management.
+ *
+ * NOTE! We count only references from dentries, in the
+ * form 'dentry->d_fsdata'. There are also references from
+ * directory inodes ('ti->private'), but the dentry reference
+ * count is always a superset of the inode reference count.
+ */
+static void release_ei(struct kref *ref)
+{
+	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+	const struct eventfs_entry *entry;
+
+	WARN_ON_ONCE(!ei->is_freed);
+
+	for (int i = 0; i < ei->nr_entries; i++) {
+		entry = &ei->entries[i];
+		if (entry->release)
+			entry->release(entry->name, ei->data);
+	}
+
+	call_srcu(&eventfs_srcu, &ei->rcu, free_ei_rcu);
+}
+
+static inline void put_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_put(&ei->kref, release_ei);
+}
+
+static inline void free_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		/* The ei should have no children if it is being freed. */
+		WARN_ON_ONCE(!list_empty(&ei->children));
+		ei->is_freed = 1;
+		/*
+		 * The SRCU iteration has a smp_rmb() to make sure it
+		 * sees a child (that may have already been freed)
+		 * before it reads is_free. If is_free is set, it must
+		 * not use the child it acquired from ei->children, as
+		 * the list may be used for SRCU.
+		 */
+		smp_wmb();
+		put_ei(ei);
+	}
+}
+
+/*
+ * Called when creation of an ei fails, do not call release() functions.
+ */
+static inline void cleanup_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		/* Set nr_entries to 0 to prevent release() function being called */
+		ei->nr_entries = 0;
+		free_ei(ei);
+	}
+}
+
+static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_get(&ei->kref);
+	return ei;
+}
+
+static struct dentry *eventfs_root_lookup(struct inode *dir,
+					  struct dentry *dentry,
+					  unsigned int flags);
+static int eventfs_iterate(struct file *file, struct dir_context *ctx);
+
+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;
+
+	guard(mutex)(&eventfs_mutex);
+	ei = dentry->d_fsdata;
+	/* Do not allow changes if the event is about to be removed. */
+	if (ei->is_freed)
+		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_objs(*ei->entry_attrs,
+						       ei->nr_entries, GFP_NOFS);
+			if (!ei->entry_attrs)
+				return -ENOMEM;
+		}
+	}
+
+	ret = simple_setattr(idmap, dentry, iattr);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * 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) {
+		/* Just use the inode permissions for the events directory */
+		if (!ei->is_events)
+			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;
+			}
+		}
+	}
+	return ret;
+}
+
+static const struct inode_operations eventfs_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 = {
+	.read		= generic_read_dir,
+	.iterate_shared	= eventfs_iterate,
+	.llseek		= generic_file_llseek,
+};
+
+static void eventfs_set_attrs(struct eventfs_inode *ei, bool update_uid, kuid_t uid,
+			      bool update_gid, kgid_t gid, int level)
+{
+	struct eventfs_inode *ei_child;
+
+	lockdep_assert_held(&eventfs_mutex);
+
+	/* Update events/<system>/<event> */
+	if (WARN_ON_ONCE(level > 3))
+		return;
+
+	if (update_uid) {
+		ei->attr.mode &= ~EVENTFS_SAVE_UID;
+		ei->attr.uid = uid;
+	}
+
+	if (update_gid) {
+		ei->attr.mode &= ~EVENTFS_SAVE_GID;
+		ei->attr.gid = gid;
+	}
+
+	list_for_each_entry(ei_child, &ei->children, list) {
+		eventfs_set_attrs(ei_child, update_uid, uid, update_gid, gid, level + 1);
+	}
+
+	if (!ei->entry_attrs)
+		return;
+
+	for (int i = 0; i < ei->nr_entries; i++) {
+		if (update_uid) {
+			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID;
+			ei->entry_attrs[i].uid = uid;
+		}
+		if (update_gid) {
+			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID;
+			ei->entry_attrs[i].gid = gid;
+		}
+	}
+
+}
+
+/*
+ * On a remount of tracefs, if UID or GID options are set, then
+ * the mount point inode permissions should be used.
+ * Reset the saved permission flags appropriately.
+ */
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid)
+{
+	struct eventfs_inode *ei = ti->private;
+
+	/* Only the events directory does the updates */
+	if (!ei || !ei->is_events || ei->is_freed)
+		return;
+
+	eventfs_set_attrs(ei, update_uid, ti->vfs_inode.i_uid,
+			  update_gid, ti->vfs_inode.i_gid, 0);
+}
+
+static void update_inode_attr(struct inode *inode, umode_t mode,
+			      struct eventfs_attr *attr, struct eventfs_root_inode *rei)
+{
+	if (attr && attr->mode & EVENTFS_SAVE_MODE)
+		inode->i_mode = attr->mode & EVENTFS_MODE_MASK;
+	else
+		inode->i_mode = mode;
+
+	if (attr && attr->mode & EVENTFS_SAVE_UID)
+		inode->i_uid = attr->uid;
+	else
+		inode->i_uid = rei->ei.attr.uid;
+
+	if (attr && attr->mode & EVENTFS_SAVE_GID)
+		inode->i_gid = attr->gid;
+	else
+		inode->i_gid = rei->ei.attr.gid;
+}
+
+static struct inode *eventfs_get_inode(struct dentry *dentry, struct eventfs_attr *attr,
+				       umode_t mode,  struct eventfs_inode *ei)
+{
+	struct eventfs_root_inode *rei;
+	struct eventfs_inode *pei;
+	struct tracefs_inode *ti;
+	struct inode *inode;
+
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (!inode)
+		return NULL;
+
+	ti = get_tracefs(inode);
+	ti->private = ei;
+	ti->flags |= TRACEFS_EVENT_INODE;
+
+	/* Find the top dentry that holds the "events" directory */
+	do {
+		dentry = dentry->d_parent;
+		/* Directories always have d_fsdata */
+		pei = dentry->d_fsdata;
+	} while (!pei->is_events);
+
+	rei = get_root_inode(pei);
+
+	update_inode_attr(inode, mode, attr, rei);
+
+	return inode;
+}
+
+/**
+ * lookup_file - look up a file in the tracefs filesystem
+ * @parent_ei: Pointer to the eventfs_inode that represents parent of the file
+ * @dentry: the dentry to look up
+ * @mode: the permission that the file should have.
+ * @attr: saved attributes changed by user
+ * @data: something that the caller will want to get to later on.
+ * @fop: struct file_operations that should be used for this file.
+ *
+ * This 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 *lookup_file(struct eventfs_inode *parent_ei,
+				  struct dentry *dentry,
+				  umode_t mode,
+				  struct eventfs_attr *attr,
+				  void *data,
+				  const struct file_operations *fop)
+{
+	struct inode *inode;
+
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
+
+	if (WARN_ON_ONCE(!S_ISREG(mode)))
+		return ERR_PTR(-EIO);
+
+	/* Only directories have ti->private set to an ei, not files */
+	inode = eventfs_get_inode(dentry, attr, mode, NULL);
+	if (unlikely(!inode))
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_op = &eventfs_file_inode_operations;
+	inode->i_fop = fop;
+	inode->i_private = data;
+
+	/* All files will have the same inode number */
+	inode->i_ino = EVENTFS_FILE_INODE_INO;
+
+	// Files have their parent's ei as their fsdata
+	dentry->d_fsdata = get_ei(parent_ei);
+
+	return d_splice_alias(inode, dentry);
+};
+
+/**
+ * lookup_dir_entry - look up a dir in the tracefs filesystem
+ * @dentry: the directory to look up
+ * @pei: Pointer to the parent eventfs_inode if available
+ * @ei: the eventfs_inode that represents the directory to create
+ *
+ * This function will look up a dentry for a directory represented by
+ * a eventfs_inode.
+ */
+static struct dentry *lookup_dir_entry(struct dentry *dentry,
+	struct eventfs_inode *pei, struct eventfs_inode *ei)
+{
+	struct inode *inode;
+	umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+
+	inode = eventfs_get_inode(dentry, &ei->attr, mode, ei);
+	if (unlikely(!inode))
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_op = &eventfs_dir_inode_operations;
+	inode->i_fop = &eventfs_file_operations;
+
+	/* All directories will have the same inode number */
+	inode->i_ino = eventfs_dir_ino(ei);
+
+	dentry->d_fsdata = get_ei(ei);
+
+	return d_splice_alias(inode, dentry);
+}
+
+static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char *name)
+{
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name)
+		return NULL;
+	kref_init(&ei->kref);
+	return ei;
+}
+
+static inline struct eventfs_inode *alloc_ei(const char *name)
+{
+	struct eventfs_inode *ei = kzalloc_obj(*ei);
+	struct eventfs_inode *result;
+
+	if (!ei)
+		return NULL;
+
+	result = init_ei(ei, name);
+	if (!result)
+		kfree(ei);
+
+	return result;
+}
+
+static inline struct eventfs_inode *alloc_root_ei(const char *name)
+{
+	struct eventfs_root_inode *rei = kzalloc_obj(*rei);
+	struct eventfs_inode *ei;
+
+	if (!rei)
+		return NULL;
+
+	rei->ei.is_events = 1;
+	ei = init_ei(&rei->ei, name);
+	if (!ei)
+		kfree(rei);
+
+	return ei;
+}
+
+/**
+ * eventfs_d_release - dentry is going away
+ * @dentry: dentry which has the reference to remove.
+ *
+ * Remove the association between a dentry from an eventfs_inode.
+ */
+void eventfs_d_release(struct dentry *dentry)
+{
+	put_ei(dentry->d_fsdata);
+}
+
+/**
+ * lookup_file_dentry - create a dentry for a file of an eventfs_inode
+ * @dentry: The parent dentry under which the new file's dentry will be created
+ * @ei: the eventfs_inode that the file will be created under
+ * @idx: the index into the entry_attrs[] of the @ei
+ * @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.
+ *
+ * This function creates a dentry for a file associated with an
+ * eventfs_inode @ei. It uses the entry attributes specified by @idx,
+ * if available. The file will have the specified @mode and its inode will be
+ * set up with @data upon open. The file operations will be set to @fops.
+ *
+ * Return: Returns a pointer to the newly created file's dentry or an error
+ * pointer.
+ */
+static struct dentry *
+lookup_file_dentry(struct dentry *dentry,
+		   struct eventfs_inode *ei, int idx,
+		   umode_t mode, void *data,
+		   const struct file_operations *fops)
+{
+	struct eventfs_attr *attr = NULL;
+
+	if (ei->entry_attrs)
+		attr = &ei->entry_attrs[idx];
+
+	return lookup_file(ei, dentry, mode, attr, data, fops);
+}
+
+/**
+ * eventfs_root_lookup - lookup routine to create file/dir
+ * @dir: in which a lookup is being done
+ * @dentry: file/dir dentry
+ * @flags: Just passed to simple_lookup()
+ *
+ * Used to create dynamic file/dir with-in @dir, search with-in @ei
+ * list, if @dentry found go ahead and create the file/dir
+ */
+
+static struct dentry *eventfs_root_lookup(struct inode *dir,
+					  struct dentry *dentry,
+					  unsigned int flags)
+{
+	struct eventfs_inode *ei_child;
+	struct tracefs_inode *ti;
+	struct eventfs_inode *ei;
+	const char *name = dentry->d_name.name;
+
+	ti = get_tracefs(dir);
+	if (WARN_ON_ONCE(!(ti->flags & TRACEFS_EVENT_INODE)))
+		return ERR_PTR(-EIO);
+
+	guard(mutex)(&eventfs_mutex);
+
+	ei = ti->private;
+	if (!ei || ei->is_freed)
+		return NULL;
+
+	list_for_each_entry(ei_child, &ei->children, list) {
+		if (strcmp(ei_child->name, name) != 0)
+			continue;
+		/* A child is freed and removed from the list at the same time */
+		if (WARN_ON_ONCE(ei_child->is_freed))
+			return NULL;
+		return lookup_dir_entry(dentry, ei, ei_child);
+	}
+
+	for (int i = 0; i < ei->nr_entries; i++) {
+		void *data;
+		umode_t mode;
+		const struct file_operations *fops;
+		const struct eventfs_entry *entry = &ei->entries[i];
+
+		if (strcmp(name, entry->name) != 0)
+			continue;
+
+		data = ei->data;
+		if (entry->callback(name, &mode, &data, &fops) <= 0)
+			return NULL;
+
+		return lookup_file_dentry(dentry, ei, i, mode, data, fops);
+
+	}
+	return NULL;
+}
+
+/*
+ * Walk the children of a eventfs_inode to fill in getdents().
+ */
+static int eventfs_iterate(struct file *file, struct dir_context *ctx)
+{
+	const struct file_operations *fops;
+	struct inode *f_inode = file_inode(file);
+	const struct eventfs_entry *entry;
+	struct eventfs_inode *ei_child;
+	struct tracefs_inode *ti;
+	struct eventfs_inode *ei;
+	const char *name;
+	umode_t mode;
+	int ino;
+	int i, r, c;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	ti = get_tracefs(f_inode);
+	if (!(ti->flags & TRACEFS_EVENT_INODE))
+		return -EINVAL;
+
+	c = ctx->pos - 2;
+
+	guard(srcu)(&eventfs_srcu);
+
+	scoped_guard(mutex, &eventfs_mutex) {
+		ei = READ_ONCE(ti->private);
+		if (!ei || ei->is_freed)
+			return -EINVAL;
+	}
+
+	/*
+	 * Need to create the dentries and inodes to have a consistent
+	 * inode number.
+	 */
+
+	/* Start at 'c' to jump over already read entries */
+	for (i = c; i < ei->nr_entries; i++, ctx->pos++) {
+		void *cdata = ei->data;
+
+		entry = &ei->entries[i];
+		name = entry->name;
+
+		/* If ei->is_freed then just bail here, nothing more to do */
+		scoped_guard(mutex, &eventfs_mutex) {
+			if (ei->is_freed)
+				return -EINVAL;
+			r = entry->callback(name, &mode, &cdata, &fops);
+		}
+		if (r <= 0)
+			continue;
+
+		ino = EVENTFS_FILE_INODE_INO;
+
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_REG))
+			return -EINVAL;
+	}
+
+	/* Subtract the skipped entries above */
+	c -= min((unsigned int)c, (unsigned int)ei->nr_entries);
+
+	list_for_each_entry_srcu(ei_child, &ei->children, list,
+				 srcu_read_lock_held(&eventfs_srcu)) {
+
+		/*
+		 * If the ei is being freed, then the ei->children may be
+		 * being used as the rcu list, which means the next element
+		 * may be garbage. The ei->is_free is set before switching
+		 * the ei->children over to ei->rcu. The read memory barrier
+		 * here makes sure the ei_child is read before is_free is
+		 * updated.
+		 *
+		 * Matches the smp_wmb() in free_ei()
+		 */
+		smp_rmb();
+		if (ei->is_freed)
+			return -EINVAL;
+
+		if (c > 0) {
+			c--;
+			continue;
+		}
+
+		ctx->pos++;
+
+		if (ei_child->is_freed)
+			continue;
+
+		name = ei_child->name;
+
+		ino = eventfs_dir_ino(ei_child);
+
+		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR)) {
+			/* Incremented ctx->pos without adding something, reset it */
+			ctx->pos--;
+			return -EINVAL;
+		}
+	}
+	return 1;
+}
+
+/**
+ * eventfs_create_dir - Create the eventfs_inode for this directory
+ * @name: The name of the directory to create.
+ * @parent: The eventfs_inode of the parent directory.
+ * @entries: A list of entries that represent the files under this directory
+ * @size: The number of @entries
+ * @data: The default data to pass to the files (an entry may override it).
+ *
+ * This function creates the descriptor to represent a directory in the
+ * eventfs. This descriptor is an eventfs_inode, and it is returned to be
+ * used to create other children underneath.
+ *
+ * The @entries is an array of eventfs_entry structures which has:
+ *	const char		 *name
+ *	eventfs_callback	callback;
+ *
+ * The name is the name of the file, and the callback is a pointer to a function
+ * that will be called when the file is reference (either by lookup or by
+ * reading a directory). The callback is of the prototype:
+ *
+ *    int callback(const char *name, umode_t *mode, void **data,
+ *		   const struct file_operations **fops);
+ *
+ * When a file needs to be created, this callback will be called with
+ *   name = the name of the file being created (so that the same callback
+ *          may be used for multiple files).
+ *   mode = a place to set the file's mode
+ *   data = A pointer to @data, and the callback may replace it, which will
+ *         cause the file created to pass the new data to the open() call.
+ *   fops = the fops to use for the created file.
+ *
+ * NB. @callback is called while holding internal locks of the eventfs
+ *     system. The callback must not call any code that might also call into
+ *     the tracefs or eventfs system or it will risk creating a deadlock.
+ */
+struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent,
+					 const struct eventfs_entry *entries,
+					 int size, void *data)
+{
+	struct eventfs_inode *ei;
+
+	if (!parent)
+		return ERR_PTR(-EINVAL);
+
+	ei = alloc_ei(name);
+	if (!ei)
+		return ERR_PTR(-ENOMEM);
+
+	ei->entries = entries;
+	ei->nr_entries = size;
+	ei->data = data;
+	INIT_LIST_HEAD(&ei->children);
+	INIT_LIST_HEAD(&ei->list);
+
+	scoped_guard(mutex, &eventfs_mutex) {
+		if (!parent->is_freed)
+			list_add_tail_rcu(&ei->list, &parent->children);
+	}
+	/* Was the parent freed? */
+	if (list_empty(&ei->list)) {
+		cleanup_ei(ei);
+		ei = ERR_PTR(-EBUSY);
+	}
+	return ei;
+}
+
+/**
+ * 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 eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent,
+						const struct eventfs_entry *entries,
+						int size, void *data)
+{
+	struct dentry *dentry;
+	struct eventfs_root_inode *rei;
+	struct eventfs_inode *ei;
+	struct tracefs_inode *ti;
+	struct inode *inode;
+	kuid_t uid;
+	kgid_t gid;
+
+	if (security_locked_down(LOCKDOWN_TRACEFS))
+		return NULL;
+
+	dentry = tracefs_start_creating(name, parent);
+	if (IS_ERR(dentry))
+		return ERR_CAST(dentry);
+
+	ei = alloc_root_ei(name);
+	if (!ei)
+		goto fail;
+
+	inode = tracefs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		goto fail;
+
+	// Note: we have a ref to the dentry from tracefs_start_creating()
+	rei = get_root_inode(ei);
+	rei->events_dir = dentry;
+
+	ei->entries = entries;
+	ei->nr_entries = size;
+	ei->data = data;
+
+	/* Save the ownership of this directory */
+	uid = d_inode(dentry->d_parent)->i_uid;
+	gid = d_inode(dentry->d_parent)->i_gid;
+
+	/*
+	 * The ei->attr will be used as the default values for the
+	 * files beneath this directory.
+	 */
+	ei->attr.uid = uid;
+	ei->attr.gid = gid;
+
+	INIT_LIST_HEAD(&ei->children);
+	INIT_LIST_HEAD(&ei->list);
+
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_EVENT_INODE;
+	ti->private = ei;
+
+	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	inode->i_uid = uid;
+	inode->i_gid = gid;
+	inode->i_op = &eventfs_dir_inode_operations;
+	inode->i_fop = &eventfs_file_operations;
+
+	dentry->d_fsdata = get_ei(ei);
+
+	/*
+	 * Keep all eventfs directories with i_nlink == 1.
+	 * Due to the dynamic nature of the dentry creations and not
+	 * wanting to add a pointer to the parent eventfs_inode in the
+	 * eventfs_inode structure, keeping the i_nlink in sync with the
+	 * number of directories would cause too much complexity for
+	 * something not worth much. Keeping directory links at 1
+	 * tells userspace not to trust the link number.
+	 */
+	d_make_persistent(dentry, inode);
+	/* The dentry of the "events" parent does keep track though */
+	inc_nlink(dentry->d_parent->d_inode);
+	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+	tracefs_end_creating(dentry);
+
+	return ei;
+
+ fail:
+	cleanup_ei(ei);
+	tracefs_failed_creating(dentry);
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * eventfs_remove_rec - remove eventfs dir or file from list
+ * @ei: eventfs_inode to be removed.
+ * @level: prevent recursion from going more than 3 levels deep.
+ *
+ * This function recursively removes eventfs_inodes which
+ * contains info of files and/or directories.
+ */
+static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
+{
+	struct eventfs_inode *ei_child, *tmp;
+
+	/*
+	 * 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;
+
+	/* search for nested folders or files */
+	list_for_each_entry_safe(ei_child, tmp, &ei->children, list)
+		eventfs_remove_rec(ei_child, level + 1);
+
+	list_del_rcu(&ei->list);
+	free_ei(ei);
+}
+
+/**
+ * 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_dir(struct eventfs_inode *ei)
+{
+	if (!ei)
+		return;
+
+	guard(mutex)(&eventfs_mutex);
+	eventfs_remove_rec(ei, 0);
+}
+
+/**
+ * eventfs_remove_events_dir - remove the top level eventfs directory
+ * @ei: the event_inode returned by eventfs_create_events_dir().
+ *
+ * This function removes the events main directory
+ */
+void eventfs_remove_events_dir(struct eventfs_inode *ei)
+{
+	struct eventfs_root_inode *rei;
+	struct dentry *dentry;
+
+	rei = get_root_inode(ei);
+	dentry = rei->events_dir;
+	if (!dentry)
+		return;
+
+	rei->events_dir = NULL;
+	eventfs_remove_dir(ei);
+
+	/*
+	 * Matches the dget() done by tracefs_start_creating()
+	 * in eventfs_create_events_dir() when it the dentry was
+	 * created. In other words, it's a normal dentry that
+	 * sticks around while the other ei->dentry are created
+	 * and destroyed dynamically.
+	 */
+	d_invalidate(dentry);
+	d_make_discardable(dentry);
+}
+
+int eventfs_remount_lock(void)
+{
+	mutex_lock(&eventfs_mutex);
+	return srcu_read_lock(&eventfs_srcu);
+}
+
+void eventfs_remount_unlock(int srcu_idx)
+{
+	srcu_read_unlock(&eventfs_srcu, srcu_idx);
+	mutex_unlock(&eventfs_mutex);
+}

linux-7.2.3/fs/tracefs/inode.c

@@ -0,0 +1,809 @@
+// 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/fs_context.h>
+#include <linux/fs_parser.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/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;
+
+/*
+ * Keep track of all tracefs_inodes in order to update their
+ * flags if necessary on a remount.
+ */
+static DEFINE_SPINLOCK(tracefs_inode_lock);
+static LIST_HEAD(tracefs_inodes);
+
+static struct inode *tracefs_alloc_inode(struct super_block *sb)
+{
+	struct tracefs_inode *ti;
+	unsigned long flags;
+
+	ti = alloc_inode_sb(sb, tracefs_inode_cachep, GFP_KERNEL);
+	if (!ti)
+		return NULL;
+
+	spin_lock_irqsave(&tracefs_inode_lock, flags);
+	list_add_rcu(&ti->list, &tracefs_inodes);
+	spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+
+	return &ti->vfs_inode;
+}
+
+static void tracefs_free_inode(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	kmem_cache_free(tracefs_inode_cachep, ti);
+}
+
+static void tracefs_destroy_inode(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tracefs_inode_lock, flags);
+	list_del_rcu(&ti->list);
+	spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+}
+
+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 struct dentry *tracefs_syscall_mkdir(struct mnt_idmap *idmap,
+					    struct inode *inode, struct dentry *dentry,
+					    umode_t mode)
+{
+	struct tracefs_inode *ti;
+	struct name_snapshot name;
+	int ret;
+
+	/*
+	 * This is a new directory that does not take the default of
+	 * the rootfs. It becomes the default permissions for all the
+	 * files and directories underneath it.
+	 */
+	ti = get_tracefs(inode);
+	ti->flags |= TRACEFS_INSTANCE_INODE;
+	ti->private = inode;
+
+	/*
+	 * The mkdir call can call the generic functions that create
+	 * the files within the tracefs system. It is up to the individual
+	 * mkdir routine to handle races.
+	 */
+	take_dentry_name_snapshot(&name, dentry);
+	inode_unlock(inode);
+	ret = tracefs_ops.mkdir(name.name.name);
+	inode_lock(inode);
+	release_dentry_name_snapshot(&name);
+
+	return ERR_PTR(ret);
+}
+
+static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
+{
+	struct name_snapshot name;
+	int ret;
+
+	/*
+	 * 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.
+	 */
+	take_dentry_name_snapshot(&name, dentry);
+	inode_unlock(inode);
+	inode_unlock(d_inode(dentry));
+
+	ret = tracefs_ops.rmdir(name.name.name);
+
+	inode_lock_nested(inode, I_MUTEX_PARENT);
+	inode_lock(d_inode(dentry));
+	release_dentry_name_snapshot(&name);
+
+	return ret;
+}
+
+static void set_tracefs_inode_owner(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+	struct inode *root_inode = ti->private;
+	kuid_t uid;
+	kgid_t gid;
+
+	uid = root_inode->i_uid;
+	gid = root_inode->i_gid;
+
+	/*
+	 * If the root is not the mount point, then check the root's
+	 * permissions. If it was never set, then default to the
+	 * mount point.
+	 */
+	if (root_inode != d_inode(root_inode->i_sb->s_root)) {
+		struct tracefs_inode *rti;
+
+		rti = get_tracefs(root_inode);
+		root_inode = d_inode(root_inode->i_sb->s_root);
+
+		if (!(rti->flags & TRACEFS_UID_PERM_SET))
+			uid = root_inode->i_uid;
+
+		if (!(rti->flags & TRACEFS_GID_PERM_SET))
+			gid = root_inode->i_gid;
+	}
+
+	/*
+	 * If this inode has never been referenced, then update
+	 * the permissions to the superblock.
+	 */
+	if (!(ti->flags & TRACEFS_UID_PERM_SET))
+		inode->i_uid = uid;
+
+	if (!(ti->flags & TRACEFS_GID_PERM_SET))
+		inode->i_gid = gid;
+}
+
+static int tracefs_permission(struct mnt_idmap *idmap,
+			      struct inode *inode, int mask)
+{
+	set_tracefs_inode_owner(inode);
+	return generic_permission(idmap, inode, mask);
+}
+
+static int tracefs_getattr(struct mnt_idmap *idmap,
+			   const struct path *path, struct kstat *stat,
+			   u32 request_mask, unsigned int flags)
+{
+	struct inode *inode = d_backing_inode(path->dentry);
+
+	set_tracefs_inode_owner(inode);
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			   struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	struct inode *inode = d_inode(dentry);
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	if (ia_valid & ATTR_UID)
+		ti->flags |= TRACEFS_UID_PERM_SET;
+
+	if (ia_valid & ATTR_GID)
+		ti->flags |= TRACEFS_GID_PERM_SET;
+
+	return simple_setattr(idmap, dentry, attr);
+}
+
+static const struct inode_operations tracefs_instance_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.mkdir		= tracefs_syscall_mkdir,
+	.rmdir		= tracefs_syscall_rmdir,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+static const struct inode_operations tracefs_file_inode_operations = {
+	.permission	= tracefs_permission,
+	.getattr	= tracefs_getattr,
+	.setattr	= tracefs_setattr,
+};
+
+struct inode *tracefs_get_inode(struct super_block *sb)
+{
+	struct inode *inode = new_inode(sb);
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		simple_inode_init_ts(inode);
+	}
+	return inode;
+}
+
+struct tracefs_fs_info {
+	kuid_t uid;
+	kgid_t gid;
+	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
+};
+
+enum {
+	Opt_uid,
+	Opt_gid,
+	Opt_mode,
+};
+
+static const struct fs_parameter_spec tracefs_param_specs[] = {
+	fsparam_gid	("gid",		Opt_gid),
+	fsparam_u32oct	("mode",	Opt_mode),
+	fsparam_uid	("uid",		Opt_uid),
+	{}
+};
+
+static int tracefs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct tracefs_fs_info *opts = fc->s_fs_info;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, tracefs_param_specs, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_uid:
+		opts->uid = result.uid;
+		break;
+	case Opt_gid:
+		opts->gid = result.gid;
+		break;
+	case Opt_mode:
+		opts->mode = result.uint_32 & S_IALLUGO;
+		break;
+	/*
+	 * We might like to report bad mount options here;
+	 * but traditionally tracefs has ignored all mount options
+	 */
+	}
+
+	opts->opts |= BIT(opt);
+
+	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_inode *ti;
+	bool update_uid, update_gid;
+	int srcu_idx;
+	umode_t tmp_mode;
+
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
+
+	if (!remount || fsi->opts & BIT(Opt_mode)) {
+		tmp_mode = READ_ONCE(inode->i_mode) & ~S_IALLUGO;
+		tmp_mode |= fsi->mode;
+		WRITE_ONCE(inode->i_mode, tmp_mode);
+	}
+
+	if (!remount || fsi->opts & BIT(Opt_uid))
+		inode->i_uid = fsi->uid;
+
+	if (!remount || fsi->opts & BIT(Opt_gid))
+		inode->i_gid = fsi->gid;
+
+	if (remount && (fsi->opts & BIT(Opt_uid) || fsi->opts & BIT(Opt_gid))) {
+
+		update_uid = fsi->opts & BIT(Opt_uid);
+		update_gid = fsi->opts & BIT(Opt_gid);
+
+		srcu_idx = eventfs_remount_lock();
+		rcu_read_lock();
+		list_for_each_entry_rcu(ti, &tracefs_inodes, list) {
+			if (update_uid) {
+				ti->flags &= ~TRACEFS_UID_PERM_SET;
+				ti->vfs_inode.i_uid = fsi->uid;
+			}
+
+			if (update_gid) {
+				ti->flags &= ~TRACEFS_GID_PERM_SET;
+				ti->vfs_inode.i_gid = fsi->gid;
+			}
+
+			/*
+			 * Note, the above ti->vfs_inode updates are
+			 * used in eventfs_remount() so they must come
+			 * before calling it.
+			 */
+			if (ti->flags & TRACEFS_EVENT_INODE)
+				eventfs_remount(ti, update_uid, update_gid);
+		}
+		rcu_read_unlock();
+		eventfs_remount_unlock(srcu_idx);
+	}
+
+	return 0;
+}
+
+static int tracefs_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	struct tracefs_fs_info *sb_opts = sb->s_fs_info;
+	struct tracefs_fs_info *new_opts = fc->s_fs_info;
+
+	if (!new_opts)
+		return 0;
+
+	sync_filesystem(sb);
+	/* structure copy of new mount options to sb */
+	*sb_opts = *new_opts;
+
+	return tracefs_apply_options(sb, true);
+}
+
+static int tracefs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct tracefs_fs_info *fsi = root->d_sb->s_fs_info;
+
+	if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, fsi->uid));
+	if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, fsi->gid));
+	if (fsi->mode != TRACEFS_DEFAULT_MODE)
+		seq_printf(m, ",mode=%o", fsi->mode);
+
+	return 0;
+}
+
+static int tracefs_drop_inode(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	/*
+	 * This inode is being freed and cannot be used for
+	 * eventfs. Clear the flag so that it doesn't call into
+	 * eventfs during the remount flag updates. The eventfs_inode
+	 * gets freed after an SRCU cycle, so the content will still
+	 * be safe if the iteration is going on now.
+	 */
+	ti->flags &= ~TRACEFS_EVENT_INODE;
+
+	return 1;
+}
+
+static const struct super_operations tracefs_super_operations = {
+	.alloc_inode    = tracefs_alloc_inode,
+	.free_inode     = tracefs_free_inode,
+	.destroy_inode  = tracefs_destroy_inode,
+	.drop_inode     = tracefs_drop_inode,
+	.statfs		= simple_statfs,
+	.show_options	= tracefs_show_options,
+};
+
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
+{
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
+
+static int tracefs_d_revalidate(struct inode *inode, const struct qstr *name,
+				struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
+
+	return !(ei && ei->is_freed);
+}
+
+static int tracefs_d_delete(const struct dentry *dentry)
+{
+	/*
+	 * We want to keep eventfs dentries around but not tracefs
+	 * ones. eventfs dentries have content in d_fsdata.
+	 * Use d_fsdata to determine if it's a eventfs dentry or not.
+	 */
+	return dentry->d_fsdata == NULL;
+}
+
+static const struct dentry_operations tracefs_dentry_operations = {
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
+	.d_delete = tracefs_d_delete,
+};
+
+static int tracefs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	static const struct tree_descr trace_files[] = {{""}};
+	int err;
+
+	err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files);
+	if (err)
+		return err;
+
+	sb->s_op = &tracefs_super_operations;
+	tracefs_apply_options(sb, false);
+	set_default_d_op(sb, &tracefs_dentry_operations);
+
+	return 0;
+}
+
+static int tracefs_get_tree(struct fs_context *fc)
+{
+	int err = get_tree_single(fc, tracefs_fill_super);
+
+	if (err)
+		return err;
+
+	return tracefs_reconfigure(fc);
+}
+
+static void tracefs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations tracefs_context_ops = {
+	.free		= tracefs_free_fc,
+	.parse_param	= tracefs_parse_param,
+	.get_tree	= tracefs_get_tree,
+	.reconfigure	= tracefs_reconfigure,
+};
+
+static int tracefs_init_fs_context(struct fs_context *fc)
+{
+	struct tracefs_fs_info *fsi;
+
+	fsi = kzalloc_obj(struct tracefs_fs_info);
+	if (!fsi)
+		return -ENOMEM;
+
+	fsi->mode = TRACEFS_DEFAULT_MODE;
+
+	fc->s_fs_info = fsi;
+	fc->ops = &tracefs_context_ops;
+	return 0;
+}
+
+static struct file_system_type trace_fs_type = {
+	.owner =	THIS_MODULE,
+	.name =		"tracefs",
+	.init_fs_context = tracefs_init_fs_context,
+	.parameters	= tracefs_param_specs,
+	.kill_sb =	kill_anon_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;
+
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry))
+		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+
+	return dentry;
+}
+
+struct dentry *tracefs_failed_creating(struct dentry *dentry)
+{
+	simple_done_creating(dentry);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	return NULL;
+}
+
+struct dentry *tracefs_end_creating(struct dentry *dentry)
+{
+	simple_done_creating(dentry);
+	return dentry;	// borrowed
+}
+
+/* Find the inode that this will use for default */
+static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
+{
+	struct tracefs_inode *ti;
+
+	/* If parent is NULL then use root inode */
+	if (!parent)
+		return d_inode(inode->i_sb->s_root);
+
+	/* Find the inode that is flagged as an instance or the root inode */
+	while (!IS_ROOT(parent)) {
+		ti = get_tracefs(d_inode(parent));
+		if (ti->flags & TRACEFS_INSTANCE_INODE)
+			break;
+		parent = parent->d_parent;
+	}
+
+	return d_inode(parent);
+}
+
+/**
+ * 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 tracefs_inode *ti;
+	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);
+
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
+	inode->i_mode = mode;
+	inode->i_op = &tracefs_file_inode_operations;
+	inode->i_fop = fops ? fops : &tracefs_file_operations;
+	inode->i_private = data;
+	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
+	d_make_persistent(dentry, inode);
+	fsnotify_create(d_inode(dentry->d_parent), dentry);
+	return tracefs_end_creating(dentry);
+}
+EXPORT_SYMBOL_GPL(tracefs_create_file);
+
+static struct dentry *__create_dir(const char *name, struct dentry *parent,
+				   const struct inode_operations *ops)
+{
+	struct tracefs_inode *ti;
+	struct dentry *dentry = tracefs_start_creating(name, parent);
+	struct inode *inode;
+
+	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;
+
+	ti = get_tracefs(inode);
+	ti->private = instance_inode(parent, inode);
+
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(inode);
+	d_make_persistent(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, &tracefs_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_instance_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() calls memset() on the vfs_inode portion */
+	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
+}
+
+static int __init tracefs_init(void)
+{
+	int retval;
+
+	tracefs_inode_cachep = kmem_cache_create("tracefs_inode_cache",
+						 sizeof(struct tracefs_inode),
+						 0, (SLAB_RECLAIM_ACCOUNT|
+						     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);

linux-7.2.3/fs/tracefs/internal.h

@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TRACEFS_INTERNAL_H
+#define _TRACEFS_INTERNAL_H
+
+enum {
+	TRACEFS_EVENT_INODE		= BIT(1),
+	TRACEFS_GID_PERM_SET		= BIT(2),
+	TRACEFS_UID_PERM_SET		= BIT(3),
+	TRACEFS_INSTANCE_INODE		= BIT(4),
+};
+
+struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
+	struct list_head	list;
+	unsigned long           flags;
+	void                    *private;
+};
+
+/*
+ * struct eventfs_attr - cache the mode and ownership of a eventfs entry
+ * @mode:	saved mode plus flags of what is saved
+ * @uid:	saved uid if changed
+ * @gid:	saved gid if changed
+ */
+struct eventfs_attr {
+	int				mode;
+	kuid_t				uid;
+	kgid_t				gid;
+};
+
+/*
+ * struct eventfs_inode - hold the properties of the eventfs directories.
+ * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
+ * @entries:	the array of entries representing the files in the directory
+ * @name:	the name of the directory to create
+ * @entry_attrs: Saved mode and ownership of the @d_children
+ * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
+ * @is_freed:	Flag set if the eventfs is on its way to be freed
+ *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
+ * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
+ */
+struct eventfs_inode {
+	struct list_head	list;
+	union {
+		struct list_head	children;
+		struct rcu_head		rcu;
+	};
+	const struct eventfs_entry	*entries;
+	const char			*name;
+	struct eventfs_attr		*entry_attrs;
+	void				*data;
+	struct eventfs_attr		attr;
+	struct kref			kref;
+	unsigned int			is_freed:1;
+	unsigned int			is_events:1;
+	unsigned int			nr_entries:30;
+	unsigned int			ino;
+};
+
+static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
+{
+	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);
+
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid);
+void eventfs_d_release(struct dentry *dentry);
+
+int eventfs_remount_lock(void);
+void eventfs_remount_unlock(int srcu_idx);
+
+#endif /* _TRACEFS_INTERNAL_H */