Resguardo inicial

linux-7.2.3/fs/kernfs/Kconfig

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+	bool
+	default n

linux-7.2.3/fs/kernfs/Makefile

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the kernfs pseudo filesystem
+#
+
+obj-y		:= mount.o inode.o dir.o file.o symlink.o

linux-7.2.3/fs/kernfs/inode.c

@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/kernfs/inode.c - kernfs inode implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ */
+
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "kernfs-internal.h"
+
+static const struct inode_operations kernfs_iops = {
+	.permission	= kernfs_iop_permission,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.listxattr	= kernfs_iop_listxattr,
+};
+
+static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, bool alloc)
+{
+	struct kernfs_iattrs *ret __free(kfree) = NULL;
+	struct kernfs_iattrs *attr;
+
+	attr = READ_ONCE(kn->iattr);
+	if (attr || !alloc)
+		return attr;
+
+	ret = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	INIT_LIST_HEAD_RCU(&ret->xattrs);
+	/* assign default attributes */
+	ret->ia_uid = GLOBAL_ROOT_UID;
+	ret->ia_gid = GLOBAL_ROOT_GID;
+
+	ktime_get_real_ts64(&ret->ia_atime);
+	ret->ia_mtime = ret->ia_atime;
+	ret->ia_ctime = ret->ia_atime;
+
+	simple_xattr_limits_init(&ret->xattr_limits);
+
+	/* If someone raced us, recognize it. */
+	if (!try_cmpxchg(&kn->iattr, &attr, ret))
+		return READ_ONCE(kn->iattr);
+
+	return no_free_ptr(ret);
+}
+
+static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
+{
+	return __kernfs_iattrs(kn, true);
+}
+
+static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn)
+{
+	return __kernfs_iattrs(kn, false);
+}
+
+int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	struct kernfs_iattrs *attrs;
+	unsigned int ia_valid = iattr->ia_valid;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (ia_valid & ATTR_UID)
+		attrs->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		attrs->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		attrs->ia_atime = iattr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		attrs->ia_mtime = iattr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		attrs->ia_ctime = iattr->ia_ctime;
+	if (ia_valid & ATTR_MODE)
+		kn->mode = iattr->ia_mode;
+	return 0;
+}
+
+/**
+ * kernfs_setattr - set iattr on a node
+ * @kn: target node
+ * @iattr: iattr to set
+ *
+ * Return: %0 on success, -errno on failure.
+ */
+int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	int ret;
+	struct kernfs_root *root = kernfs_root(kn);
+
+	down_write(&root->kernfs_iattr_rwsem);
+	ret = __kernfs_setattr(kn, iattr);
+	up_write(&root->kernfs_iattr_rwsem);
+	return ret;
+}
+
+int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		       struct iattr *iattr)
+{
+	struct inode *inode = d_inode(dentry);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root;
+	int error;
+
+	if (!kn)
+		return -EINVAL;
+
+	root = kernfs_root(kn);
+	down_write(&root->kernfs_iattr_rwsem);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
+	if (error)
+		goto out;
+
+	error = __kernfs_setattr(kn, iattr);
+	if (error)
+		goto out;
+
+	/* this ignores size changes */
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
+
+out:
+	up_write(&root->kernfs_iattr_rwsem);
+	return error;
+}
+
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
+{
+	struct kernfs_node *kn = kernfs_dentry_node(dentry);
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
+}
+
+static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
+{
+	inode->i_mode = mode;
+	simple_inode_init_ts(inode);
+}
+
+static inline void set_inode_attr(struct inode *inode,
+				  struct kernfs_iattrs *attrs)
+{
+	inode->i_uid = attrs->ia_uid;
+	inode->i_gid = attrs->ia_gid;
+	inode_set_atime_to_ts(inode, attrs->ia_atime);
+	inode_set_mtime_to_ts(inode, attrs->ia_mtime);
+	inode_set_ctime_to_ts(inode, attrs->ia_ctime);
+}
+
+static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	struct kernfs_iattrs *attrs;
+
+	inode->i_mode = kn->mode;
+	attrs = kernfs_iattrs_noalloc(kn);
+	if (attrs)
+		/*
+		 * kernfs_node has non-default attributes get them from
+		 * persistent copy in kernfs_node.
+		 */
+		set_inode_attr(inode, attrs);
+
+	if (kernfs_type(kn) == KERNFS_DIR && !(kn->flags & KERNFS_REMOVING))
+		set_nlink(inode, kn->dir.subdirs + 2);
+}
+
+int kernfs_iop_getattr(struct mnt_idmap *idmap,
+		       const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root = kernfs_root(kn);
+
+	down_read(&root->kernfs_iattr_rwsem);
+	kernfs_refresh_inode(kn, inode);
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	up_read(&root->kernfs_iattr_rwsem);
+
+	return 0;
+}
+
+static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	kernfs_get(kn);
+	inode->i_private = kn;
+	inode->i_mapping->a_ops = &ram_aops;
+	inode->i_op = &kernfs_iops;
+	inode->i_generation = kernfs_gen(kn);
+
+	set_default_inode_attr(inode, kn->mode);
+	kernfs_refresh_inode(kn, inode);
+
+	/* initialize inode according to type */
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		inode->i_op = &kernfs_dir_iops;
+		inode->i_fop = &kernfs_dir_fops;
+		if (kn->flags & KERNFS_EMPTY_DIR)
+			make_empty_dir_inode(inode);
+		break;
+	case KERNFS_FILE:
+		inode->i_size = kn->attr.size;
+		inode->i_fop = &kernfs_file_fops;
+		break;
+	case KERNFS_LINK:
+		inode->i_op = &kernfs_symlink_iops;
+		break;
+	default:
+		BUG();
+	}
+
+	unlock_new_inode(inode);
+}
+
+/**
+ *	kernfs_get_inode - get inode for kernfs_node
+ *	@sb: super block
+ *	@kn: kernfs_node to allocate inode for
+ *
+ *	Get inode for @kn.  If such inode doesn't exist, a new inode is
+ *	allocated and basics are initialized.  New inode is returned
+ *	locked.
+ *
+ *	Locking:
+ *	Kernel thread context (may sleep).
+ *
+ *	Return:
+ *	Pointer to allocated inode on success, %NULL on failure.
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
+{
+	struct inode *inode;
+
+	inode = iget_locked(sb, kernfs_ino(kn));
+	if (inode && (inode_state_read_once(inode) & I_NEW))
+		kernfs_init_inode(kn, inode);
+
+	return inode;
+}
+
+/*
+ * The kernfs_node serves as both an inode and a directory entry for
+ * kernfs.  To prevent the kernfs inode numbers from being freed
+ * prematurely we take a reference to kernfs_node from the kernfs inode.  A
+ * super_operations.evict_inode() implementation is needed to drop that
+ * reference upon inode destruction.
+ */
+void kernfs_evict_inode(struct inode *inode)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kernfs_put(kn);
+}
+
+int kernfs_iop_permission(struct mnt_idmap *idmap,
+			  struct inode *inode, int mask)
+{
+	struct kernfs_node *kn;
+	struct kernfs_root *root;
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	kn = inode->i_private;
+	root = kernfs_root(kn);
+
+	down_read(&root->kernfs_iattr_rwsem);
+	kernfs_refresh_inode(kn, inode);
+	ret = generic_permission(&nop_mnt_idmap, inode, mask);
+	up_read(&root->kernfs_iattr_rwsem);
+
+	return ret;
+}
+
+int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
+		     void *value, size_t size)
+{
+	struct kernfs_iattrs *attrs = kernfs_iattrs_noalloc(kn);
+	struct simple_xattr_cache *cache = &kernfs_root(kn)->xa_cache;
+
+	if (!attrs)
+		return -ENODATA;
+
+	return simple_xattr_get(cache, &attrs->xattrs, name, value, size);
+}
+
+int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
+		     const void *value, size_t size, int flags)
+{
+	struct simple_xattr *old_xattr;
+	struct kernfs_iattrs *attrs;
+	struct simple_xattr_cache *cache = &kernfs_root(kn)->xa_cache;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	/*
+	 * Protect xattr modifications with the hashed per-node mutex.
+	 * Multiple superblocks (with different namespaces) can share the same
+	 * kernfs_node, so inode locking alone is insufficient. The hashed mutex
+	 * ensures serialization of concurrent xattr operations on the same node,
+	 * including the lazy allocation of the xattrs structure itself.
+	 */
+	CLASS(kernfs_node_lock, lock)(kn);
+
+	old_xattr = simple_xattr_set(cache, &attrs->xattrs, name, value, size, flags);
+	if (IS_ERR(old_xattr))
+		return PTR_ERR(old_xattr);
+
+	simple_xattr_free_rcu(old_xattr);
+	return 0;
+}
+
+static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
+				struct dentry *unused, struct inode *inode,
+				const char *suffix, void *value, size_t size)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+
+	return kernfs_xattr_get(kn, name, value, size);
+}
+
+static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
+				struct mnt_idmap *idmap,
+				struct dentry *unused, struct inode *inode,
+				const char *suffix, const void *value,
+				size_t size, int flags)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+
+	return kernfs_xattr_set(kn, name, value, size, flags);
+}
+
+static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+				     struct mnt_idmap *idmap,
+				     struct dentry *unused, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_iattrs *attrs;
+
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
+		return -EOPNOTSUPP;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	/* See comment in kernfs_xattr_set() about locking. */
+	CLASS(kernfs_node_lock, lock)(kn);
+
+	return simple_xattr_set_limited(&kernfs_root(kn)->xa_cache,
+					&attrs->xattrs, &attrs->xattr_limits,
+					full_name, value, size, flags);
+}
+
+static const struct xattr_handler kernfs_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_xattr_set,
+};
+
+static const struct xattr_handler kernfs_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_xattr_set,
+};
+
+static const struct xattr_handler kernfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_user_xattr_set,
+};
+
+const struct xattr_handler * const kernfs_xattr_handlers[] = {
+	&kernfs_trusted_xattr_handler,
+	&kernfs_security_xattr_handler,
+	&kernfs_user_xattr_handler,
+	NULL
+};

linux-7.2.3/fs/kernfs/kernfs-internal.h

@@ -0,0 +1,236 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * fs/kernfs/kernfs-internal.h - kernfs internal header file
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de>
+ */
+
+#ifndef __KERNFS_INTERNAL_H
+#define __KERNFS_INTERNAL_H
+
+#include <linux/lockdep.h>
+#include <linux/fs.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/xattr.h>
+
+#include <linux/kernfs.h>
+#include <linux/fs_context.h>
+
+struct kernfs_iattrs {
+	kuid_t			ia_uid;
+	kgid_t			ia_gid;
+	struct timespec64	ia_atime;
+	struct timespec64	ia_mtime;
+	struct timespec64	ia_ctime;
+
+	struct list_head	xattrs;
+	struct simple_xattr_limits xattr_limits;
+};
+
+struct kernfs_root {
+	/* published fields */
+	struct kernfs_node	*kn;
+	unsigned int		flags;	/* KERNFS_ROOT_* flags */
+
+	/* private fields, do not use outside kernfs proper */
+	struct idr		ino_idr;
+	spinlock_t		kernfs_idr_lock;	/* root->ino_idr */
+	u32			last_id_lowbits;
+	u32			id_highbits;
+	struct kernfs_syscall_ops *syscall_ops;
+
+	/* list of kernfs_super_info of this root, protected by kernfs_rwsem */
+	struct list_head	supers;
+
+	wait_queue_head_t	deactivate_waitq;
+	struct rw_semaphore	kernfs_rwsem;
+	struct rw_semaphore	kernfs_iattr_rwsem;
+	struct rw_semaphore	kernfs_supers_rwsem;
+
+	/* kn->parent and kn->name */
+	rwlock_t		kernfs_rename_lock;
+
+	struct rcu_head		rcu;
+
+	struct simple_xattr_cache xa_cache;
+};
+
+/* +1 to avoid triggering overflow warning when negating it */
+#define KN_DEACTIVATED_BIAS		(INT_MIN + 1)
+
+/* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
+
+/**
+ * kernfs_root - find out the kernfs_root a kernfs_node belongs to
+ * @kn: kernfs_node of interest
+ *
+ * Return: the kernfs_root @kn belongs to.
+ */
+static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn)
+{
+	const struct kernfs_node *knp;
+	/* if parent exists, it's always a dir; otherwise, @sd is a dir */
+	guard(rcu)();
+	knp = rcu_dereference(kn->__parent);
+	if (knp)
+		kn = knp;
+	return kn->dir.root;
+}
+
+/*
+ * mount.c
+ */
+struct kernfs_super_info {
+	struct super_block	*sb;
+
+	/*
+	 * The root associated with this super_block.  Each super_block is
+	 * identified by the root and ns it's associated with.
+	 */
+	struct kernfs_root	*root;
+
+	/*
+	 * Each sb is associated with one namespace tag, currently the
+	 * network namespace of the task which mounted this kernfs
+	 * instance.  If multiple tags become necessary, make the following
+	 * an array and compare kernfs_node tag against every entry.
+	 */
+	const struct ns_common	*ns;
+
+	/* anchored at kernfs_root->supers, protected by kernfs_rwsem */
+	struct list_head	node;
+};
+#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
+
+static inline bool kernfs_root_is_locked(const struct kernfs_node *kn)
+{
+	return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem);
+}
+
+static inline bool kernfs_rename_is_locked(const struct kernfs_node *kn)
+{
+	return lockdep_is_held(&kernfs_root(kn)->kernfs_rename_lock);
+}
+
+static inline const char *kernfs_rcu_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, kernfs_root_is_locked(kn));
+}
+
+static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn)
+{
+	/*
+	 * The kernfs_node::__parent remains valid within a RCU section. The kn
+	 * can be reparented (and renamed) which changes the entry. This can be
+	 * avoided by locking kernfs_root::kernfs_rwsem or
+	 * kernfs_root::kernfs_rename_lock.
+	 * Both locks can be used to obtain a reference on __parent. Once the
+	 * reference count reaches 0 then the node is about to be freed
+	 * and can not be renamed (or become a different parent) anymore.
+	 */
+	return rcu_dereference_check(kn->__parent,
+				     kernfs_root_is_locked(kn) ||
+				     kernfs_rename_is_locked(kn) ||
+				     !atomic_read(&kn->count));
+}
+
+static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry)
+{
+	if (d_really_is_negative(dentry))
+		return NULL;
+	return d_inode(dentry)->i_private;
+}
+
+static inline void kernfs_set_rev(struct kernfs_node *parent,
+				  struct dentry *dentry)
+{
+	dentry->d_time = parent->dir.rev;
+}
+
+static inline void kernfs_inc_rev(struct kernfs_node *parent)
+{
+	parent->dir.rev++;
+}
+
+static inline bool kernfs_dir_changed(struct kernfs_node *parent,
+				      struct dentry *dentry)
+{
+	if (parent->dir.rev != dentry->d_time)
+		return true;
+	return false;
+}
+
+extern const struct super_operations kernfs_sops;
+extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
+
+/*
+ * inode.c
+ */
+extern const struct xattr_handler * const kernfs_xattr_handlers[];
+void kernfs_evict_inode(struct inode *inode);
+int kernfs_iop_permission(struct mnt_idmap *idmap,
+			  struct inode *inode, int mask);
+int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		       struct iattr *iattr);
+int kernfs_iop_getattr(struct mnt_idmap *idmap,
+		       const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags);
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
+int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
+
+/*
+ * dir.c
+ */
+extern const struct dentry_operations kernfs_dops;
+extern const struct file_operations kernfs_dir_fops;
+extern const struct inode_operations kernfs_dir_iops;
+
+struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
+void kernfs_put_active(struct kernfs_node *kn);
+int kernfs_add_one(struct kernfs_node *kn);
+struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
+				    const char *name, umode_t mode,
+				    kuid_t uid, kgid_t gid,
+				    unsigned flags);
+
+/*
+ * file.c
+ */
+extern const struct file_operations kernfs_file_fops;
+
+bool kernfs_should_drain_open_files(struct kernfs_node *kn);
+void kernfs_drain_open_files(struct kernfs_node *kn);
+
+/*
+ * symlink.c
+ */
+extern const struct inode_operations kernfs_symlink_iops;
+
+/*
+ * kernfs locks
+ */
+extern struct kernfs_global_locks *kernfs_locks;
+
+/* Hashed mutex helpers - protect per-node data structures */
+static inline struct mutex *kernfs_node_lock_ptr(struct kernfs_node *kn)
+{
+	int idx = hash_ptr(kn, NR_KERNFS_LOCK_BITS);
+
+	return &kernfs_locks->node_mutex[idx];
+}
+
+static inline struct mutex *kernfs_node_lock(struct kernfs_node *kn)
+{
+	struct mutex *lock = kernfs_node_lock_ptr(kn);
+
+	mutex_lock(lock);
+	return lock;
+}
+
+DEFINE_CLASS(kernfs_node_lock, struct mutex *,
+	     mutex_unlock(_T), kernfs_node_lock(kn), struct kernfs_node *kn)
+
+#endif	/* __KERNFS_INTERNAL_H */

linux-7.2.3/fs/kernfs/mount.c

@@ -0,0 +1,472 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/kernfs/mount.c - kernfs mount implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include <linux/namei.h>
+#include <linux/seq_file.h>
+#include <linux/exportfs.h>
+#include <linux/uuid.h>
+#include <linux/statfs.h>
+
+#include "kernfs-internal.h"
+
+struct kmem_cache *kernfs_node_cache __ro_after_init;
+struct kmem_cache *kernfs_iattrs_cache __ro_after_init;
+struct kernfs_global_locks *kernfs_locks __ro_after_init;
+
+static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
+{
+	struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->show_options)
+		return scops->show_options(sf, root);
+	return 0;
+}
+
+static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
+{
+	struct kernfs_node *node = kernfs_dentry_node(dentry);
+	struct kernfs_root *root = kernfs_root(node);
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->show_path)
+		return scops->show_path(sf, node, root);
+
+	seq_dentry(sf, dentry, " \t\n\\");
+	return 0;
+}
+
+static int kernfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	simple_statfs(dentry, buf);
+	buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b);
+	return 0;
+}
+
+const struct super_operations kernfs_sops = {
+	.statfs		= kernfs_statfs,
+	.drop_inode	= inode_just_drop,
+	.evict_inode	= kernfs_evict_inode,
+
+	.show_options	= kernfs_sop_show_options,
+	.show_path	= kernfs_sop_show_path,
+
+	/*
+	 * sysfs is built on top of kernfs and sysfs provides the power
+	 * management infrastructure to support suspend/hibernate by
+	 * writing to various files in /sys/power/. As filesystems may
+	 * be automatically frozen during suspend/hibernate implementing
+	 * freeze/thaw support for kernfs generically will cause
+	 * deadlocks as the suspending/hibernation initiating task will
+	 * hold a VFS lock that it will then wait upon to be released.
+	 * If freeze/thaw for kernfs is needed talk to the VFS.
+	 */
+	.freeze_fs	= NULL,
+	.unfreeze_fs	= NULL,
+	.freeze_super	= NULL,
+	.thaw_super	= NULL,
+};
+
+static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	if (*max_len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
+	}
+
+	*max_len = 2;
+	*(u64 *)fh = kn->id;
+	return FILEID_KERNFS;
+}
+
+static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
+					    struct fid *fid, int fh_len,
+					    int fh_type, bool get_parent)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_node *kn;
+	struct inode *inode;
+	u64 id;
+
+	if (fh_len < 2)
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_KERNFS:
+		id = *(u64 *)fid;
+		break;
+	case FILEID_INO32_GEN:
+	case FILEID_INO32_GEN_PARENT:
+		/*
+		 * blk_log_action() exposes "LOW32,HIGH32" pair without
+		 * type and userland can call us with generic fid
+		 * constructed from them.  Combine it back to ID.  See
+		 * blk_log_action().
+		 */
+		id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
+		break;
+	default:
+		return NULL;
+	}
+
+	kn = kernfs_find_and_get_node_by_id(info->root, id);
+	if (!kn)
+		return ERR_PTR(-ESTALE);
+
+	if (get_parent) {
+		struct kernfs_node *parent;
+
+		parent = kernfs_get_parent(kn);
+		kernfs_put(kn);
+		kn = parent;
+		if (!kn)
+			return ERR_PTR(-ESTALE);
+	}
+
+	inode = kernfs_get_inode(sb, kn);
+	kernfs_put(kn);
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
+}
+
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
+}
+
+static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
+{
+	struct kernfs_node *kn = kernfs_dentry_node(child);
+	struct kernfs_root *root = kernfs_root(kn);
+
+	guard(rwsem_read)(&root->kernfs_rwsem);
+	return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn)));
+}
+
+static const struct export_operations kernfs_export_ops = {
+	.encode_fh	= kernfs_encode_fh,
+	.fh_to_dentry	= kernfs_fh_to_dentry,
+	.fh_to_parent	= kernfs_fh_to_parent,
+	.get_parent	= kernfs_get_parent_dentry,
+};
+
+/**
+ * kernfs_root_from_sb - determine kernfs_root associated with a super_block
+ * @sb: the super_block in question
+ *
+ * Return: the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * %NULL is returned.
+ */
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{
+	if (sb->s_op == &kernfs_sops)
+		return kernfs_info(sb)->root;
+	return NULL;
+}
+
+/*
+ * find the next ancestor in the path down to @child, where @parent was the
+ * ancestor whose descendant we want to find.
+ *
+ * Say the path is /a/b/c/d.  @child is d, @parent is %NULL.  We return the root
+ * node.  If @parent is b, then we return the node for c.
+ * Passing in d as @parent is not ok.
+ */
+static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
+					      struct kernfs_node *parent)
+{
+	if (child == parent) {
+		pr_crit_once("BUG in find_next_ancestor: called with parent == child");
+		return NULL;
+	}
+
+	while (kernfs_parent(child) != parent) {
+		child = kernfs_parent(child);
+		if (!child)
+			return NULL;
+	}
+
+	return child;
+}
+
+/**
+ * kernfs_node_dentry - get a dentry for the given kernfs_node
+ * @kn: kernfs_node for which a dentry is needed
+ * @sb: the kernfs super_block
+ *
+ * Return: the dentry pointer
+ */
+struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
+				  struct super_block *sb)
+{
+	struct dentry *dentry;
+	struct kernfs_node *knparent;
+	struct kernfs_root *root;
+
+	BUG_ON(sb->s_op != &kernfs_sops);
+
+	dentry = dget(sb->s_root);
+
+	/* Check if this is the root kernfs_node */
+	if (!rcu_access_pointer(kn->__parent))
+		return dentry;
+
+	root = kernfs_root(kn);
+	/*
+	 * As long as kn is valid, its parent can not vanish. This is cgroup's
+	 * kn so it can't have its parent replaced. Therefore it is safe to use
+	 * the ancestor node outside of the RCU or locked section.
+	 */
+	if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)))
+		return ERR_PTR(-EINVAL);
+	scoped_guard(rcu) {
+		knparent = find_next_ancestor(kn, NULL);
+	}
+	if (WARN_ON(!knparent)) {
+		dput(dentry);
+		return ERR_PTR(-EINVAL);
+	}
+
+	do {
+		struct dentry *dtmp;
+		struct kernfs_node *kntmp;
+		const char *name;
+
+		if (kn == knparent)
+			return dentry;
+
+		scoped_guard(rwsem_read, &root->kernfs_rwsem) {
+			kntmp = find_next_ancestor(kn, knparent);
+			if (WARN_ON(!kntmp)) {
+				dput(dentry);
+				return ERR_PTR(-EINVAL);
+			}
+			name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL);
+		}
+		if (!name) {
+			dput(dentry);
+			return ERR_PTR(-ENOMEM);
+		}
+		dtmp = lookup_noperm_positive_unlocked(&QSTR(name), dentry);
+		dput(dentry);
+		kfree(name);
+		if (IS_ERR(dtmp))
+			return dtmp;
+		knparent = kntmp;
+		dentry = dtmp;
+	} while (true);
+}
+
+static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_root *kf_root = kfc->root;
+	struct inode *inode;
+	struct dentry *root;
+
+	info->sb = sb;
+	/* Userspace would break if executables or devices appear on sysfs */
+	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+	sb->s_magic = kfc->magic;
+	sb->s_op = &kernfs_sops;
+	sb->s_xattr = kernfs_xattr_handlers;
+	if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
+		sb->s_export_op = &kernfs_export_ops;
+	sb->s_time_gran = 1;
+	sb->s_maxbytes  = MAX_LFS_FILESIZE;
+
+	/* sysfs dentries and inodes don't require IO to create */
+	sb->s_shrink->seeks = 0;
+
+	/* get root inode, initialize and unlock it */
+	down_read(&kf_root->kernfs_rwsem);
+	inode = kernfs_get_inode(sb, info->root->kn);
+	up_read(&kf_root->kernfs_rwsem);
+	if (!inode) {
+		pr_debug("kernfs: could not get root inode\n");
+		return -ENOMEM;
+	}
+
+	/* instantiate and link root dentry */
+	root = d_make_root(inode);
+	if (!root) {
+		pr_debug("%s: could not get root dentry!\n", __func__);
+		return -ENOMEM;
+	}
+	sb->s_root = root;
+	set_default_d_op(sb, &kernfs_dops);
+	return 0;
+}
+
+static int kernfs_test_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct kernfs_super_info *sb_info = kernfs_info(sb);
+	struct kernfs_super_info *info = fc->s_fs_info;
+
+	return sb_info->root == info->root && sb_info->ns == info->ns;
+}
+
+static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	kfc->ns_tag = NULL;
+	return set_anon_super_fc(sb, fc);
+}
+
+/**
+ * kernfs_super_ns - determine the namespace tag of a kernfs super_block
+ * @sb: super_block of interest
+ *
+ * Return: the namespace tag associated with kernfs super_block @sb.
+ */
+const struct ns_common *kernfs_super_ns(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+
+	return info->ns;
+}
+
+/**
+ * kernfs_get_tree - kernfs filesystem access/retrieval helper
+ * @fc: The filesystem context.
+ *
+ * This is to be called from each kernfs user's fs_context->ops->get_tree()
+ * implementation, which should set the specified ->@fs_type and ->@flags, and
+ * specify the hierarchy and namespace tag to mount via ->@root and ->@ns,
+ * respectively.
+ *
+ * Return: %0 on success, -errno on failure.
+ */
+int kernfs_get_tree(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+	struct super_block *sb;
+	struct kernfs_super_info *info;
+	int error;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return -ENOMEM;
+
+	info->root = kfc->root;
+	info->ns = kfc->ns_tag;
+	INIT_LIST_HEAD(&info->node);
+
+	fc->s_fs_info = info;
+	sb = sget_fc(fc, kernfs_test_super, kernfs_set_super);
+	if (IS_ERR(sb))
+		return PTR_ERR(sb);
+
+	if (!sb->s_root) {
+		struct kernfs_super_info *info = kernfs_info(sb);
+		struct kernfs_root *root = kfc->root;
+
+		kfc->new_sb_created = true;
+
+		error = kernfs_fill_super(sb, kfc);
+		if (error) {
+			deactivate_locked_super(sb);
+			return error;
+		}
+		sb->s_flags |= SB_ACTIVE;
+
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
+
+		down_write(&root->kernfs_supers_rwsem);
+		list_add(&info->node, &info->root->supers);
+		up_write(&root->kernfs_supers_rwsem);
+	}
+
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+void kernfs_free_fs_context(struct fs_context *fc)
+{
+	/* Note that we don't deal with kfc->ns_tag here. */
+	kfree(fc->s_fs_info);
+	fc->s_fs_info = NULL;
+}
+
+/**
+ * kernfs_kill_sb - kill_sb for kernfs
+ * @sb: super_block being killed
+ *
+ * This can be used directly for file_system_type->kill_sb().  If a kernfs
+ * user needs extra cleanup, it can implement its own kill_sb() and call
+ * this function at the end.
+ */
+void kernfs_kill_sb(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_root *root = info->root;
+
+	down_write(&root->kernfs_supers_rwsem);
+	list_del(&info->node);
+	up_write(&root->kernfs_supers_rwsem);
+
+	/*
+	 * Remove the superblock from fs_supers/s_instances
+	 * so we can't find it, before freeing kernfs_super_info.
+	 */
+	kill_anon_super(sb);
+	kfree(info);
+}
+
+static void __init kernfs_mutex_init(void)
+{
+	int count;
+
+	for (count = 0; count < NR_KERNFS_LOCKS; count++)
+		mutex_init(&kernfs_locks->node_mutex[count]);
+}
+
+static void __init kernfs_lock_init(void)
+{
+	kernfs_locks = kmalloc_obj(struct kernfs_global_locks);
+	WARN_ON(!kernfs_locks);
+
+	kernfs_mutex_init();
+}
+
+void __init kernfs_init(void)
+{
+	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
+					      sizeof(struct kernfs_node),
+					      0, SLAB_PANIC, NULL);
+
+	/* Creates slab cache for kernfs inode attributes */
+	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",
+					      sizeof(struct kernfs_iattrs),
+					      0, SLAB_PANIC, NULL);
+
+	kernfs_lock_init();
+}

linux-7.2.3/fs/kernfs/symlink.c

@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/kernfs/symlink.c - kernfs symlink implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ */
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/namei.h>
+
+#include "kernfs-internal.h"
+
+/**
+ * kernfs_create_link - create a symlink
+ * @parent: directory to create the symlink in
+ * @name: name of the symlink
+ * @target: target node for the symlink to point to
+ *
+ * Return: the created node on success, ERR_PTR() value on error.
+ * Ownership of the link matches ownership of the target.
+ */
+struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
+				       const char *name,
+				       struct kernfs_node *target)
+{
+	struct kernfs_node *kn;
+	int error;
+	kuid_t uid = GLOBAL_ROOT_UID;
+	kgid_t gid = GLOBAL_ROOT_GID;
+
+	if (target->iattr) {
+		uid = target->iattr->ia_uid;
+		gid = target->iattr->ia_gid;
+	}
+
+	kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	if (kernfs_ns_enabled(parent))
+		kn->ns = target->ns;
+	kn->symlink.target_kn = target;
+	kernfs_get(target);	/* ref owned by symlink */
+
+	error = kernfs_add_one(kn);
+	if (!error)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(error);
+}
+
+static int kernfs_get_target_path(struct kernfs_node *parent,
+				  struct kernfs_node *target, char *path)
+{
+	struct kernfs_node *base, *kn;
+	char *s = path;
+	int len = 0;
+
+	/* go up to the root, stop at the base */
+	base = parent;
+	while (kernfs_parent(base)) {
+		kn = kernfs_parent(target);
+		while (kernfs_parent(kn) && base != kn)
+			kn = kernfs_parent(kn);
+
+		if (base == kn)
+			break;
+
+		if ((s - path) + 3 >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		strcpy(s, "../");
+		s += 3;
+		base = kernfs_parent(base);
+	}
+
+	/* determine end of target string for reverse fillup */
+	kn = target;
+	while (kernfs_parent(kn) && kn != base) {
+		len += strlen(kernfs_rcu_name(kn)) + 1;
+		kn = kernfs_parent(kn);
+	}
+
+	/* check limits */
+	if (len < 2)
+		return -EINVAL;
+	len--;
+	if ((s - path) + len >= PATH_MAX)
+		return -ENAMETOOLONG;
+
+	/* reverse fillup of target string from target to base */
+	kn = target;
+	while (kernfs_parent(kn) && kn != base) {
+		const char *name = kernfs_rcu_name(kn);
+		int slen = strlen(name);
+
+		len -= slen;
+		memcpy(s + len, name, slen);
+		if (len)
+			s[--len] = '/';
+
+		kn = kernfs_parent(kn);
+	}
+
+	return 0;
+}
+
+static int kernfs_getlink(struct inode *inode, char *path)
+{
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_node *parent;
+	struct kernfs_node *target = kn->symlink.target_kn;
+	struct kernfs_root *root = kernfs_root(kn);
+	int error;
+
+	down_read(&root->kernfs_rwsem);
+	parent = kernfs_parent(kn);
+	error = kernfs_get_target_path(parent, target, path);
+	up_read(&root->kernfs_rwsem);
+
+	return error;
+}
+
+static const char *kernfs_iop_get_link(struct dentry *dentry,
+				       struct inode *inode,
+				       struct delayed_call *done)
+{
+	char *body;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	body = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!body)
+		return ERR_PTR(-ENOMEM);
+	error = kernfs_getlink(inode, body);
+	if (unlikely(error < 0)) {
+		kfree(body);
+		return ERR_PTR(error);
+	}
+	set_delayed_call(done, kfree_link, body);
+	return body;
+}
+
+const struct inode_operations kernfs_symlink_iops = {
+	.listxattr	= kernfs_iop_listxattr,
+	.get_link	= kernfs_iop_get_link,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.permission	= kernfs_iop_permission,
+};