1 files changed, 457 insertions, 384 deletions

diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 13b01351dd1c..4b263c328ed2 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -2,16 +2,20 @@
 /*
  *  inode.c - part of debugfs, a tiny little debug file system
  *
- *  Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
+ *  Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com>
  *  Copyright (C) 2004 IBM Inc.
+ *  Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org>
  *
  *  debugfs is for people to use instead of /proc or /sys.
  *  See ./Documentation/core-api/kernel-api.rst for more details.
  */
 
+#define pr_fmt(fmt)	"debugfs: " fmt
+
 #include <linux/module.h>
 #include <linux/fs.h>
-#include <linux/mount.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
 #include <linux/kobject.h>
@@ -20,9 +24,9 @@
 #include <linux/fsnotify.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
-#include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -31,220 +35,298 @@
 static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
 static bool debugfs_registered;
+static bool debugfs_enabled __ro_after_init = IS_ENABLED(CONFIG_DEBUG_FS_ALLOW_ALL);
+
+/*
+ * Don't allow access attributes to be changed whilst the kernel is locked down
+ * so that we can use the file mode as part of a heuristic to determine whether
+ * to lock down individual files.
+ */
+static int debugfs_setattr(struct mnt_idmap *idmap,
+			   struct dentry *dentry, struct iattr *ia)
+{
+	int ret;
+
+	if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) {
+		ret = security_locked_down(LOCKDOWN_DEBUGFS);
+		if (ret)
+			return ret;
+	}
+	return simple_setattr(&nop_mnt_idmap, dentry, ia);
+}
+
+static const struct inode_operations debugfs_file_inode_operations = {
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_symlink_inode_operations = {
+	.get_link	= simple_get_link,
+	.setattr	= debugfs_setattr,
+};
 
 static struct inode *debugfs_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->i_ctime = current_time(inode);
+		simple_inode_init_ts(inode);
 	}
 	return inode;
 }
 
-struct debugfs_mount_opts {
+struct debugfs_fs_info {
 	kuid_t uid;
 	kgid_t gid;
 	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
 };
 
 enum {
 	Opt_uid,
 	Opt_gid,
 	Opt_mode,
-	Opt_err
+	Opt_source,
 };
 
-static const match_table_t tokens = {
-	{Opt_uid, "uid=%u"},
-	{Opt_gid, "gid=%u"},
-	{Opt_mode, "mode=%o"},
-	{Opt_err, NULL}
+static const struct fs_parameter_spec debugfs_param_specs[] = {
+	fsparam_gid	("gid",		Opt_gid),
+	fsparam_u32oct	("mode",	Opt_mode),
+	fsparam_uid	("uid",		Opt_uid),
+	fsparam_string	("source",	Opt_source),
+	{}
 };
 
-struct debugfs_fs_info {
-	struct debugfs_mount_opts mount_opts;
-};
-
-static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
+static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	substring_t args[MAX_OPT_ARGS];
-	int option;
-	int token;
-	kuid_t uid;
-	kgid_t gid;
-	char *p;
-
-	opts->mode = DEBUGFS_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;
+	struct debugfs_fs_info *opts = fc->s_fs_info;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, debugfs_param_specs, param, &result);
+	if (opt < 0) {
 		/*
-		 * We might like to report bad mount options here;
-		 * but traditionally debugfs has ignored all mount options
-		 */
-		}
+                * We might like to report bad mount options here; but
+                * traditionally debugfs has ignored all mount options
+                */
+		if (opt == -ENOPARAM)
+			return 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;
+	case Opt_source:
+		if (fc->source)
+			return invalfc(fc, "Multiple sources specified");
+		fc->source = param->string;
+		param->string = NULL;
+		break;
+	/*
+	 * We might like to report bad mount options here;
+	 * but traditionally debugfs has ignored all mount options
+	 */
 	}
 
+	opts->opts |= BIT(opt);
+
 	return 0;
 }
 
-static int debugfs_apply_options(struct super_block *sb)
+static void _debugfs_apply_options(struct super_block *sb, bool remount)
 {
 	struct debugfs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = d_inode(sb->s_root);
-	struct debugfs_mount_opts *opts = &fsi->mount_opts;
 
-	inode->i_mode &= ~S_IALLUGO;
-	inode->i_mode |= opts->mode;
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
 
-	inode->i_uid = opts->uid;
-	inode->i_gid = opts->gid;
+	if (!remount || fsi->opts & BIT(Opt_mode)) {
+		inode->i_mode &= ~S_IALLUGO;
+		inode->i_mode |= fsi->mode;
+	}
 
-	return 0;
+	if (!remount || fsi->opts & BIT(Opt_uid))
+		inode->i_uid = fsi->uid;
+
+	if (!remount || fsi->opts & BIT(Opt_gid))
+		inode->i_gid = fsi->gid;
 }
 
-static int debugfs_remount(struct super_block *sb, int *flags, char *data)
+static void debugfs_apply_options(struct super_block *sb)
 {
-	int err;
-	struct debugfs_fs_info *fsi = sb->s_fs_info;
+	_debugfs_apply_options(sb, false);
+}
+
+static void debugfs_apply_options_remount(struct super_block *sb)
+{
+	_debugfs_apply_options(sb, true);
+}
+
+static int debugfs_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	struct debugfs_fs_info *sb_opts = sb->s_fs_info;
+	struct debugfs_fs_info *new_opts = fc->s_fs_info;
+
+	if (!new_opts)
+		return 0;
 
 	sync_filesystem(sb);
-	err = debugfs_parse_options(data, &fsi->mount_opts);
-	if (err)
-		goto fail;
 
-	debugfs_apply_options(sb);
+	/* structure copy of new mount options to sb */
+	*sb_opts = *new_opts;
+	debugfs_apply_options_remount(sb);
 
-fail:
-	return err;
+	return 0;
 }
 
 static int debugfs_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct debugfs_fs_info *fsi = root->d_sb->s_fs_info;
-	struct debugfs_mount_opts *opts = &fsi->mount_opts;
 
-	if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
+	if (!uid_eq(fsi->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))
+			   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, opts->gid));
-	if (opts->mode != DEBUGFS_DEFAULT_MODE)
-		seq_printf(m, ",mode=%o", opts->mode);
+			   from_kgid_munged(&init_user_ns, fsi->gid));
+	if (fsi->mode != DEBUGFS_DEFAULT_MODE)
+		seq_printf(m, ",mode=%o", fsi->mode);
 
 	return 0;
 }
 
-static void debugfs_evict_inode(struct inode *inode)
+static struct kmem_cache *debugfs_inode_cachep __ro_after_init;
+
+static void init_once(void *foo)
+{
+	struct debugfs_inode_info *info = foo;
+	inode_init_once(&info->vfs_inode);
+}
+
+static struct inode *debugfs_alloc_inode(struct super_block *sb)
+{
+	struct debugfs_inode_info *info;
+	info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL);
+	if (!info)
+		return NULL;
+	return &info->vfs_inode;
+}
+
+static void debugfs_free_inode(struct inode *inode)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode));
 }
 
 static const struct super_operations debugfs_super_operations = {
 	.statfs		= simple_statfs,
-	.remount_fs	= debugfs_remount,
 	.show_options	= debugfs_show_options,
-	.evict_inode	= debugfs_evict_inode,
+	.alloc_inode	= debugfs_alloc_inode,
+	.free_inode	= debugfs_free_inode,
 };
 
 static void debugfs_release_dentry(struct dentry *dentry)
 {
-	void *fsd = dentry->d_fsdata;
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 
-	if (!((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
-		kfree(dentry->d_fsdata);
+	if (fsd) {
+		WARN_ON(!list_empty(&fsd->cancellations));
+		mutex_destroy(&fsd->cancellations_mtx);
+	}
+	kfree(fsd);
 }
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	debugfs_automount_t f;
-	f = (debugfs_automount_t)path->dentry->d_fsdata;
-	return f(path->dentry, d_inode(path->dentry)->i_private);
+	struct inode *inode = path->dentry->d_inode;
+
+	return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {
-	.d_delete = always_delete_dentry,
 	.d_release = debugfs_release_dentry,
 	.d_automount = debugfs_automount,
 };
 
-static int debug_fill_super(struct super_block *sb, void *data, int silent)
+static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	static const struct tree_descr debug_files[] = {{""}};
-	struct debugfs_fs_info *fsi;
 	int err;
 
-	fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
-	sb->s_fs_info = fsi;
-	if (!fsi) {
-		err = -ENOMEM;
-		goto fail;
-	}
-
-	err = debugfs_parse_options(data, &fsi->mount_opts);
-	if (err)
-		goto fail;
-
-	err  =  simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
+	err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files);
 	if (err)
-		goto fail;
+		return err;
 
 	sb->s_op = &debugfs_super_operations;
-	sb->s_d_op = &debugfs_dops;
+	set_default_d_op(sb, &debugfs_dops);
+	sb->s_d_flags |= DCACHE_DONTCACHE;
 
 	debugfs_apply_options(sb);
 
 	return 0;
+}
+
+static int debugfs_get_tree(struct fs_context *fc)
+{
+	int err;
 
-fail:
-	kfree(fsi);
-	sb->s_fs_info = NULL;
-	return err;
+	err = get_tree_single(fc, debugfs_fill_super);
+	if (err)
+		return err;
+
+	return debugfs_reconfigure(fc);
 }
 
-static struct dentry *debug_mount(struct file_system_type *fs_type,
-			int flags, const char *dev_name,
-			void *data)
+static void debugfs_free_fc(struct fs_context *fc)
 {
-	return mount_single(fs_type, flags, data, debug_fill_super);
+	kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations debugfs_context_ops = {
+	.free		= debugfs_free_fc,
+	.parse_param	= debugfs_parse_param,
+	.get_tree	= debugfs_get_tree,
+	.reconfigure	= debugfs_reconfigure,
+};
+
+static int debugfs_init_fs_context(struct fs_context *fc)
+{
+	struct debugfs_fs_info *fsi;
+
+	fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
+	if (!fsi)
+		return -ENOMEM;
+
+	fsi->mode = DEBUGFS_DEFAULT_MODE;
+
+	fc->s_fs_info = fsi;
+	fc->ops = &debugfs_context_ops;
+	return 0;
 }
 
 static struct file_system_type debug_fs_type = {
 	.owner =	THIS_MODULE,
 	.name =		"debugfs",
-	.mount =	debug_mount,
-	.kill_sb =	kill_litter_super,
+	.init_fs_context = debugfs_init_fs_context,
+	.parameters =	debugfs_param_specs,
+	.kill_sb =	kill_anon_super,
 };
 MODULE_ALIAS_FS("debugfs");
 
@@ -264,37 +346,42 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
 {
 	struct dentry *dentry;
 
-	if (IS_ERR(parent))
+	if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent))
 		return NULL;
 
 	if (!parent)
 		parent = debugfs_mount->mnt_root;
 
-	dentry = lookup_one_len_unlocked(name, parent, strlen(name));
+	dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent);
 	if (IS_ERR(dentry))
 		return NULL;
-	if (!d_really_is_positive(dentry)) {
-		dput(dentry);
-		return NULL;
-	}
 	return dentry;
 }
 EXPORT_SYMBOL_GPL(debugfs_lookup);
 
-static struct dentry *start_creating(const char *name, struct dentry *parent)
+static struct dentry *debugfs_start_creating(const char *name,
+					     struct dentry *parent)
 {
 	struct dentry *dentry;
 	int error;
 
-	pr_debug("debugfs: creating file '%s'\n",name);
+	if (!debugfs_enabled)
+		return ERR_PTR(-EPERM);
+
+	if (!debugfs_initialized())
+		return ERR_PTR(-ENOENT);
+
+	pr_debug("creating file '%s'\n", name);
 
 	if (IS_ERR(parent))
 		return parent;
 
 	error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
 			      &debugfs_mount_count);
-	if (error)
+	if (error) {
+		pr_err("Unable to pin filesystem for file '%s'\n", name);
 		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
@@ -304,39 +391,33 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	if (!parent)
 		parent = debugfs_mount->mnt_root;
 
-	inode_lock(d_inode(parent));
-	dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
+	dentry = simple_start_creating(parent, name);
 	if (IS_ERR(dentry)) {
-		inode_unlock(d_inode(parent));
+		if (dentry == ERR_PTR(-EEXIST))
+			pr_err("'%s' already exists in '%pd'\n", name, parent);
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	}
-
 	return dentry;
 }
 
-static struct dentry *failed_creating(struct dentry *dentry)
+static struct dentry *debugfs_failed_creating(struct dentry *dentry)
 {
-	inode_unlock(d_inode(dentry->d_parent));
-	dput(dentry);
+	simple_done_creating(dentry);
 	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
-static struct dentry *end_creating(struct dentry *dentry)
+static struct dentry *debugfs_end_creating(struct dentry *dentry)
 {
-	inode_unlock(d_inode(dentry->d_parent));
-	return dentry;
+	simple_done_creating(dentry);
+	return dentry; // borrowed
 }
 
 static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 				struct dentry *parent, void *data,
+				const void *aux,
 				const struct file_operations *proxy_fops,
-				const struct file_operations *real_fops)
+				const void *real_fops)
 {
 	struct dentry *dentry;
 	struct inode *inode;
@@ -344,64 +425,54 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	if (!(mode & S_IFMT))
 		mode |= S_IFREG;
 	BUG_ON(!S_ISREG(mode));
-	dentry = start_creating(name, parent);
+	dentry = debugfs_start_creating(name, parent);
 
 	if (IS_ERR(dentry))
-		return NULL;
+		return dentry;
 
 	inode = debugfs_get_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
+	if (unlikely(!inode)) {
+		pr_err("out of free dentries, can not create file '%s'\n",
+		       name);
+		return debugfs_failed_creating(dentry);
+	}
 
 	inode->i_mode = mode;
 	inode->i_private = data;
 
+	inode->i_op = &debugfs_file_inode_operations;
+	if (!real_fops)
+		proxy_fops = &debugfs_noop_file_operations;
 	inode->i_fop = proxy_fops;
-	dentry->d_fsdata = (void *)((unsigned long)real_fops |
-				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
+	DEBUGFS_I(inode)->raw = real_fops;
+	DEBUGFS_I(inode)->aux = (void *)aux;
 
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 	fsnotify_create(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return debugfs_end_creating(dentry);
 }
 
-/**
- * debugfs_create_file - create a file in the debugfs 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 debugfs 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 debugfs.  It allows for a
- * wide range of flexibility in creating a file, or a directory (if you want
- * to create a directory, the debugfs_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 debugfs_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 debugfs is not enabled in the kernel, the value -%ENODEV will be
- * returned.
- */
-struct dentry *debugfs_create_file(const char *name, umode_t mode,
-				   struct dentry *parent, void *data,
-				   const struct file_operations *fops)
+struct dentry *debugfs_create_file_full(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const void *aux,
+					const struct file_operations *fops)
 {
+	return __debugfs_create_file(name, mode, parent, data, aux,
+				&debugfs_full_proxy_file_operations,
+				fops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_file_full);
 
-	return __debugfs_create_file(name, mode, parent, data,
-				fops ? &debugfs_full_proxy_file_operations :
-					&debugfs_noop_file_operations,
+struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const void *aux,
+					const struct debugfs_short_fops *fops)
+{
+	return __debugfs_create_file(name, mode, parent, data, aux,
+				&debugfs_full_short_proxy_file_operations,
 				fops);
 }
-EXPORT_SYMBOL_GPL(debugfs_create_file);
+EXPORT_SYMBOL_GPL(debugfs_create_file_short);
 
 /**
  * debugfs_create_file_unsafe - create a file in the debugfs filesystem
@@ -422,8 +493,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  * debugfs core.
  *
  * It is your responsibility to protect your struct file_operation
- * methods against file removals by means of debugfs_use_file_start()
- * and debugfs_use_file_finish(). ->open() is still protected by
+ * methods against file removals by means of debugfs_file_get()
+ * and debugfs_file_put(). ->open() is still protected by
  * debugfs though.
  *
  * Any struct file_operations defined by means of
@@ -435,9 +506,8 @@ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
 				   const struct file_operations *fops)
 {
 
-	return __debugfs_create_file(name, mode, parent, data,
-				fops ? &debugfs_open_proxy_file_operations :
-					&debugfs_noop_file_operations,
+	return __debugfs_create_file(name, mode, parent, data, NULL,
+				&debugfs_open_proxy_file_operations,
 				fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
@@ -460,25 +530,16 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
  * wide range of flexibility in creating a file, or a directory (if you want
  * to create a directory, the debugfs_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 debugfs_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 debugfs is not enabled in the kernel, the value -%ENODEV will be
- * returned.
  */
-struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
-					struct dentry *parent, void *data,
-					const struct file_operations *fops,
-					loff_t file_size)
+void debugfs_create_file_size(const char *name, umode_t mode,
+			      struct dentry *parent, void *data,
+			      const struct file_operations *fops,
+			      loff_t file_size)
 {
 	struct dentry *de = debugfs_create_file(name, mode, parent, data, fops);
 
-	if (de)
+	if (!IS_ERR(de))
 		d_inode(de)->i_size = file_size;
-	return de;
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file_size);
 
@@ -495,33 +556,42 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size);
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_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.
+ * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
+ * returned.
  *
  * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.
+ *
+ * NOTE: it's expected that most callers should _ignore_ the errors returned
+ * by this function. Other debugfs functions handle the fact that the "dentry"
+ * passed to them could be an error and they don't crash in that case.
+ * Drivers should generally work fine even if debugfs fails to init anyway.
  */
 struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry = debugfs_start_creating(name, parent);
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
-		return NULL;
+		return dentry;
 
 	inode = debugfs_get_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
+	if (unlikely(!inode)) {
+		pr_err("out of free dentries, can not create directory '%s'\n",
+		       name);
+		return debugfs_failed_creating(dentry);
+	}
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	inode->i_op = &simple_dir_inode_operations;
+	inode->i_op = &debugfs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 	inc_nlink(d_inode(dentry->d_parent));
 	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return debugfs_end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_dir);
 
@@ -541,26 +611,29 @@ struct dentry *debugfs_create_automount(const char *name,
 					debugfs_automount_t f,
 					void *data)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry = debugfs_start_creating(name, parent);
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
-		return NULL;
+		return dentry;
 
 	inode = debugfs_get_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
+	if (unlikely(!inode)) {
+		pr_err("out of free dentries, can not create automount '%s'\n",
+		       name);
+		return debugfs_failed_creating(dentry);
+	}
 
 	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
-	dentry->d_fsdata = (void *)f;
+	DEBUGFS_I(inode)->automount = f;
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 	inc_nlink(d_inode(dentry->d_parent));
 	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return debugfs_end_creating(dentry);
 }
 EXPORT_SYMBOL(debugfs_create_automount);
 
@@ -581,8 +654,8 @@ EXPORT_SYMBOL(debugfs_create_automount);
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the symbolic
  * link 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.
+ * unloaded, you are responsible here.)  If an error occurs, ERR_PTR(-ERROR)
+ * will be returned.
  *
  * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.
@@ -594,34 +667,33 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 	struct inode *inode;
 	char *link = kstrdup(target, GFP_KERNEL);
 	if (!link)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
-	dentry = start_creating(name, parent);
+	dentry = debugfs_start_creating(name, parent);
 	if (IS_ERR(dentry)) {
 		kfree(link);
-		return NULL;
+		return dentry;
 	}
 
 	inode = debugfs_get_inode(dentry->d_sb);
 	if (unlikely(!inode)) {
+		pr_err("out of free dentries, can not create symlink '%s'\n",
+		       name);
 		kfree(link);
-		return failed_creating(dentry);
+		return debugfs_failed_creating(dentry);
 	}
 	inode->i_mode = S_IFLNK | S_IRWXUGO;
-	inode->i_op = &simple_symlink_inode_operations;
+	inode->i_op = &debugfs_symlink_inode_operations;
 	inode->i_link = link;
-	d_instantiate(dentry, inode);
-	return end_creating(dentry);
+	d_make_persistent(dentry, inode);
+	return debugfs_end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_symlink);
 
-static void __debugfs_remove_file(struct dentry *dentry, struct dentry *parent)
+static void __debugfs_file_removed(struct dentry *dentry)
 {
 	struct debugfs_fsdata *fsd;
 
-	simple_unlink(d_inode(parent), dentry);
-	d_delete(dentry);
-
 	/*
 	 * Paired with the closing smp_mb() implied by a successful
 	 * cmpxchg() in debugfs_file_get(): either
@@ -630,66 +702,65 @@ static void __debugfs_remove_file(struct dentry *dentry, struct dentry *parent)
 	 */
 	smp_mb();
 	fsd = READ_ONCE(dentry->d_fsdata);
-	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
+	if (!fsd)
 		return;
-	if (!refcount_dec_and_test(&fsd->active_users))
-		wait_for_completion(&fsd->active_users_drained);
-}
 
-static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
-{
-	int ret = 0;
+	/* if this was the last reference, we're done */
+	if (refcount_dec_and_test(&fsd->active_users))
+		return;
 
-	if (simple_positive(dentry)) {
-		dget(dentry);
-		if (!d_is_reg(dentry)) {
-			if (d_is_dir(dentry))
-				ret = simple_rmdir(d_inode(parent), dentry);
-			else
-				simple_unlink(d_inode(parent), dentry);
-			if (!ret)
-				d_delete(dentry);
-		} else {
-			__debugfs_remove_file(dentry, parent);
+	/*
+	 * If there's still a reference, the code that obtained it can
+	 * be in different states:
+	 *  - The common case of not using cancellations, or already
+	 *    after debugfs_leave_cancellation(), where we just need
+	 *    to wait for debugfs_file_put() which signals the completion;
+	 *  - inside a cancellation section, i.e. between
+	 *    debugfs_enter_cancellation() and debugfs_leave_cancellation(),
+	 *    in which case we need to trigger the ->cancel() function,
+	 *    and then wait for debugfs_file_put() just like in the
+	 *    previous case;
+	 *  - before debugfs_enter_cancellation() (but obviously after
+	 *    debugfs_file_get()), in which case we may not see the
+	 *    cancellation in the list on the first round of the loop,
+	 *    but debugfs_enter_cancellation() signals the completion
+	 *    after adding it, so this code gets woken up to call the
+	 *    ->cancel() function.
+	 */
+	while (refcount_read(&fsd->active_users)) {
+		struct debugfs_cancellation *c;
+
+		/*
+		 * Lock the cancellations. Note that the cancellations
+		 * structs are meant to be on the stack, so we need to
+		 * ensure we either use them here or don't touch them,
+		 * and debugfs_leave_cancellation() will wait for this
+		 * to be finished processing before exiting one. It may
+		 * of course win and remove the cancellation, but then
+		 * chances are we never even got into this bit, we only
+		 * do if the refcount isn't zero already.
+		 */
+		mutex_lock(&fsd->cancellations_mtx);
+		while ((c = list_first_entry_or_null(&fsd->cancellations,
+						     typeof(*c), list))) {
+			list_del_init(&c->list);
+			c->cancel(dentry, c->cancel_data);
 		}
-		dput(dentry);
+		mutex_unlock(&fsd->cancellations_mtx);
+
+		wait_for_completion(&fsd->active_users_drained);
 	}
-	return ret;
 }
 
-/**
- * debugfs_remove - removes a file or directory from the debugfs filesystem
- * @dentry: a pointer to a the dentry of the file or directory to be
- *          removed.  If this parameter is NULL or an error value, nothing
- *          will be done.
- *
- * This function removes a file or directory in debugfs that was previously
- * created with a call to another debugfs function (like
- * debugfs_create_file() or variants thereof.)
- *
- * This function is required to be called in order for the file to be
- * removed, no automatic cleanup of files will happen when a module is
- * removed, you are responsible here.
- */
-void debugfs_remove(struct dentry *dentry)
+static void remove_one(struct dentry *victim)
 {
-	struct dentry *parent;
-	int ret;
-
-	if (IS_ERR_OR_NULL(dentry))
-		return;
-
-	parent = dentry->d_parent;
-	inode_lock(d_inode(parent));
-	ret = __debugfs_remove(dentry, parent);
-	inode_unlock(d_inode(parent));
-	if (!ret)
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+        if (d_is_reg(victim))
+		__debugfs_file_removed(victim);
+	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
-EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
- * debugfs_remove_recursive - recursively removes a directory
+ * debugfs_remove - recursively removes a directory
  * @dentry: a pointer to a the dentry of the directory to be removed.  If this
  *          parameter is NULL or an error value, nothing will be done.
  *
@@ -701,128 +772,100 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  * removed, no automatic cleanup of files will happen when a module is
  * removed, you are responsible here.
  */
-void debugfs_remove_recursive(struct dentry *dentry)
+void debugfs_remove(struct dentry *dentry)
 {
-	struct dentry *child, *parent;
-
 	if (IS_ERR_OR_NULL(dentry))
 		return;
 
-	parent = dentry;
- down:
-	inode_lock(d_inode(parent));
- loop:
-	/*
-	 * The parent->d_subdirs is protected by the d_lock. Outside that
-	 * lock, the child can be unlinked and set to be freed which can
-	 * use the d_u.d_child as the rcu head and corrupt this list.
-	 */
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!simple_positive(child))
-			continue;
-
-		/* perhaps simple_empty(child) makes more sense */
-		if (!list_empty(&child->d_subdirs)) {
-			spin_unlock(&parent->d_lock);
-			inode_unlock(d_inode(parent));
-			parent = child;
-			goto down;
-		}
-
-		spin_unlock(&parent->d_lock);
-
-		if (!__debugfs_remove(child, parent))
-			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-
-		/*
-		 * The parent->d_lock protects agaist child from unlinking
-		 * from d_subdirs. When releasing the parent->d_lock we can
-		 * no longer trust that the next pointer is valid.
-		 * Restart the loop. We'll skip this one with the
-		 * simple_positive() check.
-		 */
-		goto loop;
-	}
-	spin_unlock(&parent->d_lock);
+	simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count);
+	simple_recursive_removal(dentry, remove_one);
+	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+}
+EXPORT_SYMBOL_GPL(debugfs_remove);
 
-	inode_unlock(d_inode(parent));
-	child = parent;
-	parent = parent->d_parent;
-	inode_lock(d_inode(parent));
+/**
+ * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
+ * @name: a pointer to a string containing the name of the item to look up.
+ * @parent: a pointer to the parent dentry of the item.
+ *
+ * This is the equlivant of doing something like
+ * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
+ * handled for the directory being looked up.
+ */
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
 
-	if (child != dentry)
-		/* go up */
-		goto loop;
+	dentry = debugfs_lookup(name, parent);
+	if (!dentry)
+		return;
 
-	if (!__debugfs_remove(child, parent))
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-	inode_unlock(d_inode(parent));
+	debugfs_remove(dentry);
+	dput(dentry);
 }
-EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
+EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
 
 /**
- * debugfs_rename - rename a file/directory in the debugfs filesystem
- * @old_dir: a pointer to the parent dentry for the renamed object. This
- *          should be a directory dentry.
- * @old_dentry: dentry of an object to be renamed.
- * @new_dir: a pointer to the parent dentry where the object should be
- *          moved. This should be a directory dentry.
- * @new_name: a pointer to a string containing the target name.
+ * debugfs_change_name - rename a file/directory in the debugfs filesystem
+ * @dentry: dentry of an object to be renamed.
+ * @fmt: format for new name
  *
  * This function renames a file/directory in debugfs.  The target must not
  * exist for rename to succeed.
  *
- * This function will return a pointer to old_dentry (which is updated to
- * reflect renaming) if it succeeds. If an error occurs, %NULL will be
- * returned.
+ * This function will return 0 on success and -E... on failure.
  *
  * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.
  */
-struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-		struct dentry *new_dir, const char *new_name)
+int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...)
 {
-	int error;
-	struct dentry *dentry = NULL, *trap;
+	int error = 0;
+	const char *new_name;
 	struct name_snapshot old_name;
+	struct dentry *target;
+	struct renamedata rd = {};
+	struct inode *dir;
+	va_list ap;
 
-	trap = lock_rename(new_dir, old_dir);
-	/* Source or destination directories don't exist? */
-	if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
-		goto exit;
-	/* Source does not exist, cyclic rename, or mountpoint? */
-	if (d_really_is_negative(old_dentry) || old_dentry == trap ||
-	    d_mountpoint(old_dentry))
-		goto exit;
-	dentry = lookup_one_len(new_name, new_dir, strlen(new_name));
-	/* Lookup failed, cyclic rename or target exists? */
-	if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
-		goto exit;
-
-	take_dentry_name_snapshot(&old_name, old_dentry);
-
-	error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
-			      dentry, 0);
+	if (IS_ERR_OR_NULL(dentry))
+		return 0;
+
+	va_start(ap, fmt);
+	new_name = kvasprintf_const(GFP_KERNEL, fmt, ap);
+	va_end(ap);
+	if (!new_name)
+		return -ENOMEM;
+
+	rd.old_parent = dget_parent(dentry);
+	rd.new_parent = rd.old_parent;
+	rd.flags = RENAME_NOREPLACE;
+	target = lookup_noperm_unlocked(&QSTR(new_name), rd.new_parent);
+	if (IS_ERR(target))
+		return PTR_ERR(target);
+
+	error = start_renaming_two_dentries(&rd, dentry, target);
 	if (error) {
-		release_dentry_name_snapshot(&old_name);
-		goto exit;
+		if (error == -EEXIST && target == dentry)
+			/* it isn't an error to rename a thing to itself */
+			error = 0;
+		goto out;
 	}
-	d_move(old_dentry, dentry);
-	fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name,
-		d_is_dir(old_dentry),
-		NULL, old_dentry);
+
+	dir = d_inode(rd.old_parent);
+	take_dentry_name_snapshot(&old_name, dentry);
+	simple_rename_timestamp(dir, dentry, dir, rd.new_dentry);
+	d_move(dentry, rd.new_dentry);
+	fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry);
 	release_dentry_name_snapshot(&old_name);
-	unlock_rename(new_dir, old_dir);
-	dput(dentry);
-	return old_dentry;
-exit:
-	if (dentry && !IS_ERR(dentry))
-		dput(dentry);
-	unlock_rename(new_dir, old_dir);
-	return NULL;
+	end_renaming(&rd);
+out:
+	dput(rd.old_parent);
+	dput(target);
+	kfree_const(new_name);
+	return error;
 }
-EXPORT_SYMBOL_GPL(debugfs_rename);
+EXPORT_SYMBOL_GPL(debugfs_change_name);
 
 /**
  * debugfs_initialized - Tells whether debugfs has been registered
@@ -833,21 +876,51 @@ bool debugfs_initialized(void)
 }
 EXPORT_SYMBOL_GPL(debugfs_initialized);
 
+static int __init debugfs_kernel(char *str)
+{
+	if (str) {
+		if (!strcmp(str, "on"))
+			debugfs_enabled = true;
+		else if (!strcmp(str, "off"))
+			debugfs_enabled = false;
+		else if (!strcmp(str, "no-mount")) {
+			pr_notice("debugfs=no-mount is a deprecated alias "
+				  "for debugfs=off\n");
+			debugfs_enabled = false;
+		}
+	}
+
+	return 0;
+}
+early_param("debugfs", debugfs_kernel);
+
 static int __init debugfs_init(void)
 {
 	int retval;
 
+	if (!debugfs_enabled)
+		return -EPERM;
+
 	retval = sysfs_create_mount_point(kernel_kobj, "debug");
 	if (retval)
 		return retval;
 
-	retval = register_filesystem(&debug_fs_type);
-	if (retval)
+	debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache",
+				sizeof(struct debugfs_inode_info), 0,
+				SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+				init_once);
+	if (debugfs_inode_cachep == NULL) {
 		sysfs_remove_mount_point(kernel_kobj, "debug");
-	else
-		debugfs_registered = true;
+		return -ENOMEM;
+	}
 
-	return retval;
+	retval = register_filesystem(&debug_fs_type);
+	if (retval) { // Really not going to happen
+		sysfs_remove_mount_point(kernel_kobj, "debug");
+		kmem_cache_destroy(debugfs_inode_cachep);
+		return retval;
+	}
+	debugfs_registered = true;
+	return 0;
 }
 core_initcall(debugfs_init);
-