mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/
synced 2025-04-19 20:58:31 +09:00

Using RCU lifetime rules to access kernfs_node::name can avoid the trouble with kernfs_rename_lock in kernfs_name() and kernfs_path_from_node() if the fs was created with KERNFS_ROOT_INVARIANT_PARENT. This is usefull as it allows to implement kernfs_path_from_node() only with RCU protection and avoiding kernfs_rename_lock. The lock is only required if the __parent node can be changed and the function requires an unchanged hierarchy while it iterates from the node to its parent. The change is needed to allow the lookup of the node's path (kernfs_path_from_node()) from context which runs always with disabled preemption and or interrutps even on PREEMPT_RT. The problem is that kernfs_rename_lock becomes a sleeping lock on PREEMPT_RT. I went through all ::name users and added the required access for the lookup with a few extensions: - rdtgroup_pseudo_lock_create() drops all locks and then uses the name later on. resctrl supports rename with different parents. Here I made a temporal copy of the name while it is used outside of the lock. - kernfs_rename_ns() accepts NULL as new_parent. This simplifies sysfs_move_dir_ns() where it can set NULL in order to reuse the current name. - kernfs_rename_ns() is only using kernfs_rename_lock if the parents are different. All users use either kernfs_rwsem (for stable path view) or just RCU for the lookup. The ::name uses always RCU free. Use RCU lifetime guarantees to access kernfs_node::name. Suggested-by: Tejun Heo <tj@kernel.org> Acked-by: Tejun Heo <tj@kernel.org> Reported-by: syzbot+6ea37e2e6ffccf41a7e6@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/67251dc6.050a0220.529b6.015e.GAE@google.com/ Reported-by: Hillf Danton <hdanton@sina.com> Closes: https://lore.kernel.org/20241102001224.2789-1-hdanton@sina.com Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lore.kernel.org/r/20250213145023.2820193-7-bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
208 lines
5.6 KiB
C
208 lines
5.6 KiB
C
/* 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>
|
|
|
|
extern rwlock_t kernfs_rename_lock;
|
|
|
|
struct kernfs_iattrs {
|
|
kuid_t ia_uid;
|
|
kgid_t ia_gid;
|
|
struct timespec64 ia_atime;
|
|
struct timespec64 ia_mtime;
|
|
struct timespec64 ia_ctime;
|
|
|
|
struct simple_xattrs xattrs;
|
|
atomic_t nr_user_xattrs;
|
|
atomic_t user_xattr_size;
|
|
};
|
|
|
|
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;
|
|
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;
|
|
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
/* +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 void *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 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_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) ||
|
|
lockdep_is_held(&kernfs_rename_lock) ||
|
|
!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;
|
|
#endif /* __KERNFS_INTERNAL_H */
|