diff options
Diffstat (limited to 'fs/sysfs')
| -rw-r--r-- | fs/sysfs/Kconfig | 2 | ||||
| -rw-r--r-- | fs/sysfs/Makefile | 4 | ||||
| -rw-r--r-- | fs/sysfs/bin.c | 507 | ||||
| -rw-r--r-- | fs/sysfs/dir.c | 1070 | ||||
| -rw-r--r-- | fs/sysfs/file.c | 1209 | ||||
| -rw-r--r-- | fs/sysfs/group.c | 560 | ||||
| -rw-r--r-- | fs/sysfs/inode.c | 354 | ||||
| -rw-r--r-- | fs/sysfs/mount.c | 224 | ||||
| -rw-r--r-- | fs/sysfs/symlink.c | 266 | ||||
| -rw-r--r-- | fs/sysfs/sysfs.h | 233 |
10 files changed, 1330 insertions, 3099 deletions
diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig index 8c41feacbac5..b0fe1cce33a0 100644 --- a/fs/sysfs/Kconfig +++ b/fs/sysfs/Kconfig @@ -1,6 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only config SYSFS bool "sysfs file system support" if EXPERT default y + select KERNFS help The sysfs filesystem is a virtual filesystem that the kernel uses to export internal kernel objects, their attributes, and their diff --git a/fs/sysfs/Makefile b/fs/sysfs/Makefile index 7a1ceb946b80..0906b9e522fe 100644 --- a/fs/sysfs/Makefile +++ b/fs/sysfs/Makefile @@ -1,6 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the sysfs virtual filesystem # -obj-y := inode.o file.o dir.o symlink.o mount.o bin.o \ - group.o +obj-y := file.o dir.o symlink.o mount.o group.o diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c deleted file mode 100644 index 15c68f9489ae..000000000000 --- a/fs/sysfs/bin.c +++ /dev/null @@ -1,507 +0,0 @@ -/* - * fs/sysfs/bin.c - sysfs binary file implementation - * - * Copyright (c) 2003 Patrick Mochel - * Copyright (c) 2003 Matthew Wilcox - * Copyright (c) 2004 Silicon Graphics, Inc. - * Copyright (c) 2007 SUSE Linux Products GmbH - * Copyright (c) 2007 Tejun Heo <teheo@suse.de> - * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. - */ - -#undef DEBUG - -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/kernel.h> -#include <linux/kobject.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/mutex.h> -#include <linux/mm.h> - -#include <asm/uaccess.h> - -#include "sysfs.h" - -/* - * There's one bin_buffer for each open file. - * - * filp->private_data points to bin_buffer and - * sysfs_dirent->s_bin_attr.buffers points to a the bin_buffer s - * sysfs_dirent->s_bin_attr.buffers is protected by sysfs_bin_lock - */ -static DEFINE_MUTEX(sysfs_bin_lock); - -struct bin_buffer { - struct mutex mutex; - void *buffer; - int mmapped; - const struct vm_operations_struct *vm_ops; - struct file *file; - struct hlist_node list; -}; - -static int -fill_read(struct file *file, char *buffer, loff_t off, size_t count) -{ - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - int rc; - - /* need attr_sd for attr, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; - - rc = -EIO; - if (attr->read) - rc = attr->read(file, kobj, attr, buffer, off, count); - - sysfs_put_active(attr_sd); - - return rc; -} - -static ssize_t -read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) -{ - struct bin_buffer *bb = file->private_data; - int size = file_inode(file)->i_size; - loff_t offs = *off; - int count = min_t(size_t, bytes, PAGE_SIZE); - char *temp; - - if (!bytes) - return 0; - - if (size) { - if (offs > size) - return 0; - if (offs + count > size) - count = size - offs; - } - - temp = kmalloc(count, GFP_KERNEL); - if (!temp) - return -ENOMEM; - - mutex_lock(&bb->mutex); - - count = fill_read(file, bb->buffer, offs, count); - if (count < 0) { - mutex_unlock(&bb->mutex); - goto out_free; - } - - memcpy(temp, bb->buffer, count); - - mutex_unlock(&bb->mutex); - - if (copy_to_user(userbuf, temp, count)) { - count = -EFAULT; - goto out_free; - } - - pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count); - - *off = offs + count; - - out_free: - kfree(temp); - return count; -} - -static int -flush_write(struct file *file, char *buffer, loff_t offset, size_t count) -{ - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - int rc; - - /* need attr_sd for attr, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; - - rc = -EIO; - if (attr->write) - rc = attr->write(file, kobj, attr, buffer, offset, count); - - sysfs_put_active(attr_sd); - - return rc; -} - -static ssize_t write(struct file *file, const char __user *userbuf, - size_t bytes, loff_t *off) -{ - struct bin_buffer *bb = file->private_data; - int size = file_inode(file)->i_size; - loff_t offs = *off; - int count = min_t(size_t, bytes, PAGE_SIZE); - char *temp; - - if (!bytes) - return 0; - - if (size) { - if (offs > size) - return 0; - if (offs + count > size) - count = size - offs; - } - - temp = memdup_user(userbuf, count); - if (IS_ERR(temp)) - return PTR_ERR(temp); - - mutex_lock(&bb->mutex); - - memcpy(bb->buffer, temp, count); - - count = flush_write(file, bb->buffer, offs, count); - mutex_unlock(&bb->mutex); - - if (count > 0) - *off = offs + count; - - kfree(temp); - return count; -} - -static void bin_vma_open(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - - if (!bb->vm_ops) - return; - - if (!sysfs_get_active(attr_sd)) - return; - - if (bb->vm_ops->open) - bb->vm_ops->open(vma); - - sysfs_put_active(attr_sd); -} - -static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - int ret; - - if (!bb->vm_ops) - return VM_FAULT_SIGBUS; - - if (!sysfs_get_active(attr_sd)) - return VM_FAULT_SIGBUS; - - ret = VM_FAULT_SIGBUS; - if (bb->vm_ops->fault) - ret = bb->vm_ops->fault(vma, vmf); - - sysfs_put_active(attr_sd); - return ret; -} - -static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - int ret; - - if (!bb->vm_ops) - return VM_FAULT_SIGBUS; - - if (!sysfs_get_active(attr_sd)) - return VM_FAULT_SIGBUS; - - ret = 0; - if (bb->vm_ops->page_mkwrite) - ret = bb->vm_ops->page_mkwrite(vma, vmf); - else - file_update_time(file); - - sysfs_put_active(attr_sd); - return ret; -} - -static int bin_access(struct vm_area_struct *vma, unsigned long addr, - void *buf, int len, int write) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - int ret; - - if (!bb->vm_ops) - return -EINVAL; - - if (!sysfs_get_active(attr_sd)) - return -EINVAL; - - ret = -EINVAL; - if (bb->vm_ops->access) - ret = bb->vm_ops->access(vma, addr, buf, len, write); - - sysfs_put_active(attr_sd); - return ret; -} - -#ifdef CONFIG_NUMA -static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - int ret; - - if (!bb->vm_ops) - return 0; - - if (!sysfs_get_active(attr_sd)) - return -EINVAL; - - ret = 0; - if (bb->vm_ops->set_policy) - ret = bb->vm_ops->set_policy(vma, new); - - sysfs_put_active(attr_sd); - return ret; -} - -static struct mempolicy *bin_get_policy(struct vm_area_struct *vma, - unsigned long addr) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct mempolicy *pol; - - if (!bb->vm_ops) - return vma->vm_policy; - - if (!sysfs_get_active(attr_sd)) - return vma->vm_policy; - - pol = vma->vm_policy; - if (bb->vm_ops->get_policy) - pol = bb->vm_ops->get_policy(vma, addr); - - sysfs_put_active(attr_sd); - return pol; -} - -static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, - const nodemask_t *to, unsigned long flags) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - int ret; - - if (!bb->vm_ops) - return 0; - - if (!sysfs_get_active(attr_sd)) - return 0; - - ret = 0; - if (bb->vm_ops->migrate) - ret = bb->vm_ops->migrate(vma, from, to, flags); - - sysfs_put_active(attr_sd); - return ret; -} -#endif - -static const struct vm_operations_struct bin_vm_ops = { - .open = bin_vma_open, - .fault = bin_fault, - .page_mkwrite = bin_page_mkwrite, - .access = bin_access, -#ifdef CONFIG_NUMA - .set_policy = bin_set_policy, - .get_policy = bin_get_policy, - .migrate = bin_migrate, -#endif -}; - -static int mmap(struct file *file, struct vm_area_struct *vma) -{ - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - int rc; - - mutex_lock(&bb->mutex); - - /* need attr_sd for attr, its parent for kobj */ - rc = -ENODEV; - if (!sysfs_get_active(attr_sd)) - goto out_unlock; - - rc = -EINVAL; - if (!attr->mmap) - goto out_put; - - rc = attr->mmap(file, kobj, attr, vma); - if (rc) - goto out_put; - - /* - * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() - * to satisfy versions of X which crash if the mmap fails: that - * substitutes a new vm_file, and we don't then want bin_vm_ops. - */ - if (vma->vm_file != file) - goto out_put; - - rc = -EINVAL; - if (bb->mmapped && bb->vm_ops != vma->vm_ops) - goto out_put; - - /* - * It is not possible to successfully wrap close. - * So error if someone is trying to use close. - */ - rc = -EINVAL; - if (vma->vm_ops && vma->vm_ops->close) - goto out_put; - - rc = 0; - bb->mmapped = 1; - bb->vm_ops = vma->vm_ops; - vma->vm_ops = &bin_vm_ops; -out_put: - sysfs_put_active(attr_sd); -out_unlock: - mutex_unlock(&bb->mutex); - - return rc; -} - -static int open(struct inode * inode, struct file * file) -{ - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr; - struct bin_buffer *bb = NULL; - int error; - - /* binary file operations requires both @sd and its parent */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; - - error = -EACCES; - if ((file->f_mode & FMODE_WRITE) && !(attr->write || attr->mmap)) - goto err_out; - if ((file->f_mode & FMODE_READ) && !(attr->read || attr->mmap)) - goto err_out; - - error = -ENOMEM; - bb = kzalloc(sizeof(*bb), GFP_KERNEL); - if (!bb) - goto err_out; - - bb->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!bb->buffer) - goto err_out; - - mutex_init(&bb->mutex); - bb->file = file; - file->private_data = bb; - - mutex_lock(&sysfs_bin_lock); - hlist_add_head(&bb->list, &attr_sd->s_bin_attr.buffers); - mutex_unlock(&sysfs_bin_lock); - - /* open succeeded, put active references */ - sysfs_put_active(attr_sd); - return 0; - - err_out: - sysfs_put_active(attr_sd); - kfree(bb); - return error; -} - -static int release(struct inode * inode, struct file * file) -{ - struct bin_buffer *bb = file->private_data; - - mutex_lock(&sysfs_bin_lock); - hlist_del(&bb->list); - mutex_unlock(&sysfs_bin_lock); - - kfree(bb->buffer); - kfree(bb); - return 0; -} - -const struct file_operations bin_fops = { - .read = read, - .write = write, - .mmap = mmap, - .llseek = generic_file_llseek, - .open = open, - .release = release, -}; - - -void unmap_bin_file(struct sysfs_dirent *attr_sd) -{ - struct bin_buffer *bb; - - if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR) - return; - - mutex_lock(&sysfs_bin_lock); - - hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) { - struct inode *inode = file_inode(bb->file); - - unmap_mapping_range(inode->i_mapping, 0, 0, 1); - } - - mutex_unlock(&sysfs_bin_lock); -} - -/** - * sysfs_create_bin_file - create binary file for object. - * @kobj: object. - * @attr: attribute descriptor. - */ - -int sysfs_create_bin_file(struct kobject *kobj, - const struct bin_attribute *attr) -{ - BUG_ON(!kobj || !kobj->sd || !attr); - - return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR); -} - - -/** - * sysfs_remove_bin_file - remove binary file for object. - * @kobj: object. - * @attr: attribute descriptor. - */ - -void sysfs_remove_bin_file(struct kobject *kobj, - const struct bin_attribute *attr) -{ - sysfs_hash_and_remove(kobj->sd, NULL, attr->attr.name); -} - -EXPORT_SYMBOL_GPL(sysfs_create_bin_file); -EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index e068e744dbdd..94e12efd92f2 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/dir.c - sysfs core and dir operation implementation * @@ -5,847 +6,66 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ -#undef DEBUG +#define pr_fmt(fmt) "sysfs: " fmt #include <linux/fs.h> -#include <linux/mount.h> -#include <linux/module.h> #include <linux/kobject.h> -#include <linux/namei.h> -#include <linux/idr.h> -#include <linux/completion.h> -#include <linux/mutex.h> #include <linux/slab.h> -#include <linux/security.h> -#include <linux/hash.h> #include "sysfs.h" -DEFINE_MUTEX(sysfs_mutex); -DEFINE_SPINLOCK(sysfs_assoc_lock); - -#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb); - -static DEFINE_SPINLOCK(sysfs_ino_lock); -static DEFINE_IDA(sysfs_ino_ida); - -/** - * sysfs_name_hash - * @ns: Namespace tag to hash - * @name: Null terminated string to hash - * - * Returns 31 bit hash of ns + name (so it fits in an off_t ) - */ -static unsigned int sysfs_name_hash(const void *ns, const char *name) -{ - unsigned long hash = init_name_hash(); - unsigned int len = strlen(name); - while (len--) - hash = partial_name_hash(*name++, hash); - hash = ( end_name_hash(hash) ^ hash_ptr( (void *)ns, 31 ) ); - hash &= 0x7fffffffU; - /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ - if (hash < 1) - hash += 2; - if (hash >= INT_MAX) - hash = INT_MAX - 1; - return hash; -} - -static int sysfs_name_compare(unsigned int hash, const void *ns, - const char *name, const struct sysfs_dirent *sd) -{ - if (hash != sd->s_hash) - return hash - sd->s_hash; - if (ns != sd->s_ns) - return ns - sd->s_ns; - return strcmp(name, sd->s_name); -} - -static int sysfs_sd_compare(const struct sysfs_dirent *left, - const struct sysfs_dirent *right) -{ - return sysfs_name_compare(left->s_hash, left->s_ns, left->s_name, - right); -} - -/** - * sysfs_link_sibling - link sysfs_dirent into sibling rbtree - * @sd: sysfs_dirent of interest - * - * Link @sd into its sibling rbtree which starts from - * sd->s_parent->s_dir.children. - * - * Locking: - * mutex_lock(sysfs_mutex) - * - * RETURNS: - * 0 on susccess -EEXIST on failure. - */ -static int sysfs_link_sibling(struct sysfs_dirent *sd) -{ - struct rb_node **node = &sd->s_parent->s_dir.children.rb_node; - struct rb_node *parent = NULL; - - if (sysfs_type(sd) == SYSFS_DIR) - sd->s_parent->s_dir.subdirs++; - - while (*node) { - struct sysfs_dirent *pos; - int result; - - pos = to_sysfs_dirent(*node); - parent = *node; - result = sysfs_sd_compare(sd, pos); - if (result < 0) - node = &pos->s_rb.rb_left; - else if (result > 0) - node = &pos->s_rb.rb_right; - else - return -EEXIST; - } - /* add new node and rebalance the tree */ - rb_link_node(&sd->s_rb, parent, node); - rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children); - return 0; -} - -/** - * sysfs_unlink_sibling - unlink sysfs_dirent from sibling rbtree - * @sd: sysfs_dirent of interest - * - * Unlink @sd from its sibling rbtree which starts from - * sd->s_parent->s_dir.children. - * - * Locking: - * mutex_lock(sysfs_mutex) - */ -static void sysfs_unlink_sibling(struct sysfs_dirent *sd) -{ - if (sysfs_type(sd) == SYSFS_DIR) - sd->s_parent->s_dir.subdirs--; - - rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children); -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - -/* Test for attributes that want to ignore lockdep for read-locking */ -static bool ignore_lockdep(struct sysfs_dirent *sd) -{ - return sysfs_type(sd) == SYSFS_KOBJ_ATTR && - sd->s_attr.attr->ignore_lockdep; -} - -#else - -static inline bool ignore_lockdep(struct sysfs_dirent *sd) -{ - return true; -} - -#endif - -/** - * sysfs_get_active - get an active reference to sysfs_dirent - * @sd: sysfs_dirent to get an active reference to - * - * Get an active reference of @sd. This function is noop if @sd - * is NULL. - * - * RETURNS: - * Pointer to @sd on success, NULL on failure. - */ -struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) -{ - if (unlikely(!sd)) - return NULL; - - if (!atomic_inc_unless_negative(&sd->s_active)) - return NULL; - - if (likely(!ignore_lockdep(sd))) - rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); - return sd; -} - -/** - * sysfs_put_active - put an active reference to sysfs_dirent - * @sd: sysfs_dirent to put an active reference to - * - * Put an active reference to @sd. This function is noop if @sd - * is NULL. - */ -void sysfs_put_active(struct sysfs_dirent *sd) -{ - int v; - - if (unlikely(!sd)) - return; - - if (likely(!ignore_lockdep(sd))) - rwsem_release(&sd->dep_map, 1, _RET_IP_); - v = atomic_dec_return(&sd->s_active); - if (likely(v != SD_DEACTIVATED_BIAS)) - return; - - /* atomic_dec_return() is a mb(), we'll always see the updated - * sd->u.completion. - */ - complete(sd->u.completion); -} - -/** - * sysfs_deactivate - deactivate sysfs_dirent - * @sd: sysfs_dirent to deactivate - * - * Deny new active references and drain existing ones. - */ -static void sysfs_deactivate(struct sysfs_dirent *sd) -{ - DECLARE_COMPLETION_ONSTACK(wait); - int v; - - BUG_ON(!(sd->s_flags & SYSFS_FLAG_REMOVED)); - - if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF)) - return; - - sd->u.completion = (void *)&wait; - - rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_); - /* atomic_add_return() is a mb(), put_active() will always see - * the updated sd->u.completion. - */ - v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active); - - if (v != SD_DEACTIVATED_BIAS) { - lock_contended(&sd->dep_map, _RET_IP_); - wait_for_completion(&wait); - } - - lock_acquired(&sd->dep_map, _RET_IP_); - rwsem_release(&sd->dep_map, 1, _RET_IP_); -} - -static int sysfs_alloc_ino(unsigned int *pino) -{ - int ino, rc; - - retry: - spin_lock(&sysfs_ino_lock); - rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino); - spin_unlock(&sysfs_ino_lock); - - if (rc == -EAGAIN) { - if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL)) - goto retry; - rc = -ENOMEM; - } - - *pino = ino; - return rc; -} - -static void sysfs_free_ino(unsigned int ino) -{ - spin_lock(&sysfs_ino_lock); - ida_remove(&sysfs_ino_ida, ino); - spin_unlock(&sysfs_ino_lock); -} +DEFINE_SPINLOCK(sysfs_symlink_target_lock); -void release_sysfs_dirent(struct sysfs_dirent * sd) +void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { - struct sysfs_dirent *parent_sd; - - repeat: - /* Moving/renaming is always done while holding reference. - * sd->s_parent won't change beneath us. - */ - parent_sd = sd->s_parent; + char *buf; - WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED), - "sysfs: free using entry: %s/%s\n", - parent_sd ? parent_sd->s_name : "", sd->s_name); + buf = kzalloc(PATH_MAX, GFP_KERNEL); + if (buf) + kernfs_path(parent, buf, PATH_MAX); - if (sysfs_type(sd) == SYSFS_KOBJ_LINK) - sysfs_put(sd->s_symlink.target_sd); - if (sysfs_type(sd) & SYSFS_COPY_NAME) - kfree(sd->s_name); - if (sd->s_iattr && sd->s_iattr->ia_secdata) - security_release_secctx(sd->s_iattr->ia_secdata, - sd->s_iattr->ia_secdata_len); - kfree(sd->s_iattr); - sysfs_free_ino(sd->s_ino); - kmem_cache_free(sysfs_dir_cachep, sd); - - sd = parent_sd; - if (sd && atomic_dec_and_test(&sd->s_count)) - goto repeat; -} + pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name); + dump_stack(); -static int sysfs_dentry_delete(const struct dentry *dentry) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED)); -} - -static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags) -{ - struct sysfs_dirent *sd; - int is_dir; - int type; - - if (flags & LOOKUP_RCU) - return -ECHILD; - - sd = dentry->d_fsdata; - mutex_lock(&sysfs_mutex); - - /* The sysfs dirent has been deleted */ - if (sd->s_flags & SYSFS_FLAG_REMOVED) - goto out_bad; - - /* The sysfs dirent has been moved? */ - if (dentry->d_parent->d_fsdata != sd->s_parent) - goto out_bad; - - /* The sysfs dirent has been renamed */ - if (strcmp(dentry->d_name.name, sd->s_name) != 0) - goto out_bad; - - /* The sysfs dirent has been moved to a different namespace */ - type = KOBJ_NS_TYPE_NONE; - if (sd->s_parent) { - type = sysfs_ns_type(sd->s_parent); - if (type != KOBJ_NS_TYPE_NONE && - sysfs_info(dentry->d_sb)->ns[type] != sd->s_ns) - goto out_bad; - } - - mutex_unlock(&sysfs_mutex); -out_valid: - return 1; -out_bad: - /* Remove the dentry from the dcache hashes. - * If this is a deleted dentry we use d_drop instead of d_delete - * so sysfs doesn't need to cope with negative dentries. - * - * If this is a dentry that has simply been renamed we - * use d_drop to remove it from the dcache lookup on its - * old parent. If this dentry persists later when a lookup - * is performed at its new name the dentry will be readded - * to the dcache hashes. - */ - is_dir = (sysfs_type(sd) == SYSFS_DIR); - mutex_unlock(&sysfs_mutex); - if (is_dir) { - /* If we have submounts we must allow the vfs caches - * to lie about the state of the filesystem to prevent - * leaks and other nasty things. - */ - if (have_submounts(dentry)) - goto out_valid; - shrink_dcache_parent(dentry); - } - d_drop(dentry); - return 0; -} - -static void sysfs_dentry_release(struct dentry *dentry) -{ - sysfs_put(dentry->d_fsdata); -} - -const struct dentry_operations sysfs_dentry_ops = { - .d_revalidate = sysfs_dentry_revalidate, - .d_delete = sysfs_dentry_delete, - .d_release = sysfs_dentry_release, -}; - -struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) -{ - char *dup_name = NULL; - struct sysfs_dirent *sd; - - if (type & SYSFS_COPY_NAME) { - name = dup_name = kstrdup(name, GFP_KERNEL); - if (!name) - return NULL; - } - - sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL); - if (!sd) - goto err_out1; - - if (sysfs_alloc_ino(&sd->s_ino)) - goto err_out2; - - atomic_set(&sd->s_count, 1); - atomic_set(&sd->s_active, 0); - - sd->s_name = name; - sd->s_mode = mode; - sd->s_flags = type | SYSFS_FLAG_REMOVED; - - return sd; - - err_out2: - kmem_cache_free(sysfs_dir_cachep, sd); - err_out1: - kfree(dup_name); - return NULL; + kfree(buf); } /** - * sysfs_addrm_start - prepare for sysfs_dirent add/remove - * @acxt: pointer to sysfs_addrm_cxt to be used - * @parent_sd: parent sysfs_dirent - * - * This function is called when the caller is about to add or - * remove sysfs_dirent under @parent_sd. This function acquires - * sysfs_mutex. @acxt is used to keep and pass context to - * other addrm functions. - * - * LOCKING: - * Kernel thread context (may sleep). sysfs_mutex is locked on - * return. - */ -void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt, - struct sysfs_dirent *parent_sd) -{ - memset(acxt, 0, sizeof(*acxt)); - acxt->parent_sd = parent_sd; - - mutex_lock(&sysfs_mutex); -} - -/** - * __sysfs_add_one - add sysfs_dirent to parent without warning - * @acxt: addrm context to use - * @sd: sysfs_dirent to be added - * - * Get @acxt->parent_sd and set sd->s_parent to it and increment - * nlink of parent inode if @sd is a directory and link into the - * children list of the parent. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - * - * RETURNS: - * 0 on success, -EEXIST if entry with the given name already - * exists. + * sysfs_create_dir_ns - create a directory for an object with a namespace tag + * @kobj: object we're creating directory for + * @ns: the namespace tag to use */ -int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) +int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { - struct sysfs_inode_attrs *ps_iattr; - int ret; + struct kernfs_node *parent, *kn; + kuid_t uid; + kgid_t gid; - if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) { - WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(acxt->parent_sd)? "required": "invalid", - acxt->parent_sd->s_name, sd->s_name); + if (WARN_ON(!kobj)) return -EINVAL; - } - - sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name); - sd->s_parent = sysfs_get(acxt->parent_sd); - - ret = sysfs_link_sibling(sd); - if (ret) - return ret; - - /* Update timestamps on the parent */ - ps_iattr = acxt->parent_sd->s_iattr; - if (ps_iattr) { - struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; - } - - /* Mark the entry added into directory tree */ - sd->s_flags &= ~SYSFS_FLAG_REMOVED; - - return 0; -} - -/** - * sysfs_pathname - return full path to sysfs dirent - * @sd: sysfs_dirent whose path we want - * @path: caller allocated buffer of size PATH_MAX - * - * Gives the name "/" to the sysfs_root entry; any path returned - * is relative to wherever sysfs is mounted. - */ -static char *sysfs_pathname(struct sysfs_dirent *sd, char *path) -{ - if (sd->s_parent) { - sysfs_pathname(sd->s_parent, path); - strlcat(path, "/", PATH_MAX); - } - strlcat(path, sd->s_name, PATH_MAX); - return path; -} - -/** - * sysfs_add_one - add sysfs_dirent to parent - * @acxt: addrm context to use - * @sd: sysfs_dirent to be added - * - * Get @acxt->parent_sd and set sd->s_parent to it and increment - * nlink of parent inode if @sd is a directory and link into the - * children list of the parent. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - * - * RETURNS: - * 0 on success, -EEXIST if entry with the given name already - * exists. - */ -int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) -{ - int ret; - - ret = __sysfs_add_one(acxt, sd); - if (ret == -EEXIST) { - char *path = kzalloc(PATH_MAX, GFP_KERNEL); - WARN(1, KERN_WARNING - "sysfs: cannot create duplicate filename '%s'\n", - (path == NULL) ? sd->s_name - : (sysfs_pathname(acxt->parent_sd, path), - strlcat(path, "/", PATH_MAX), - strlcat(path, sd->s_name, PATH_MAX), - path)); - kfree(path); - } - - return ret; -} - -/** - * sysfs_remove_one - remove sysfs_dirent from parent - * @acxt: addrm context to use - * @sd: sysfs_dirent to be removed - * - * Mark @sd removed and drop nlink of parent inode if @sd is a - * directory. @sd is unlinked from the children list. - * - * This function should be called between calls to - * sysfs_addrm_start() and sysfs_addrm_finish() and should be - * passed the same @acxt as passed to sysfs_addrm_start(). - * - * LOCKING: - * Determined by sysfs_addrm_start(). - */ -void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) -{ - struct sysfs_inode_attrs *ps_iattr; - - BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED); - - sysfs_unlink_sibling(sd); - - /* Update timestamps on the parent */ - ps_iattr = acxt->parent_sd->s_iattr; - if (ps_iattr) { - struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME; - } - - sd->s_flags |= SYSFS_FLAG_REMOVED; - sd->u.removed_list = acxt->removed; - acxt->removed = sd; -} - -/** - * sysfs_addrm_finish - finish up sysfs_dirent add/remove - * @acxt: addrm context to finish up - * - * Finish up sysfs_dirent add/remove. Resources acquired by - * sysfs_addrm_start() are released and removed sysfs_dirents are - * cleaned up. - * - * LOCKING: - * sysfs_mutex is released. - */ -void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt) -{ - /* release resources acquired by sysfs_addrm_start() */ - mutex_unlock(&sysfs_mutex); - - /* kill removed sysfs_dirents */ - while (acxt->removed) { - struct sysfs_dirent *sd = acxt->removed; - - acxt->removed = sd->u.removed_list; - - sysfs_deactivate(sd); - unmap_bin_file(sd); - sysfs_put(sd); - } -} - -/** - * sysfs_find_dirent - find sysfs_dirent with the given name - * @parent_sd: sysfs_dirent to search under - * @name: name to look for - * - * Look for sysfs_dirent with name @name under @parent_sd. - * - * LOCKING: - * mutex_lock(sysfs_mutex) - * - * RETURNS: - * Pointer to sysfs_dirent if found, NULL if not. - */ -struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, - const void *ns, - const unsigned char *name) -{ - struct rb_node *node = parent_sd->s_dir.children.rb_node; - unsigned int hash; - - if (!!sysfs_ns_type(parent_sd) != !!ns) { - WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n", - sysfs_ns_type(parent_sd)? "required": "invalid", - parent_sd->s_name, name); - return NULL; - } - - hash = sysfs_name_hash(ns, name); - while (node) { - struct sysfs_dirent *sd; - int result; - - sd = to_sysfs_dirent(node); - result = sysfs_name_compare(hash, ns, name, sd); - if (result < 0) - node = node->rb_left; - else if (result > 0) - node = node->rb_right; - else - return sd; - } - return NULL; -} - -/** - * sysfs_get_dirent - find and get sysfs_dirent with the given name - * @parent_sd: sysfs_dirent to search under - * @name: name to look for - * - * Look for sysfs_dirent with name @name under @parent_sd and get - * it if found. - * - * LOCKING: - * Kernel thread context (may sleep). Grabs sysfs_mutex. - * - * RETURNS: - * Pointer to sysfs_dirent if found, NULL if not. - */ -struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, - const void *ns, - const unsigned char *name) -{ - struct sysfs_dirent *sd; - - mutex_lock(&sysfs_mutex); - sd = sysfs_find_dirent(parent_sd, ns, name); - sysfs_get(sd); - mutex_unlock(&sysfs_mutex); - - return sd; -} -EXPORT_SYMBOL_GPL(sysfs_get_dirent); - -static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd, - enum kobj_ns_type type, const void *ns, const char *name, - struct sysfs_dirent **p_sd) -{ - umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - int rc; - - /* allocate */ - sd = sysfs_new_dirent(name, mode, SYSFS_DIR); - if (!sd) - return -ENOMEM; - - sd->s_flags |= (type << SYSFS_NS_TYPE_SHIFT); - sd->s_ns = ns; - sd->s_dir.kobj = kobj; - - /* link in */ - sysfs_addrm_start(&acxt, parent_sd); - rc = sysfs_add_one(&acxt, sd); - sysfs_addrm_finish(&acxt); - - if (rc == 0) - *p_sd = sd; - else - sysfs_put(sd); - - return rc; -} - -int sysfs_create_subdir(struct kobject *kobj, const char *name, - struct sysfs_dirent **p_sd) -{ - return create_dir(kobj, kobj->sd, - KOBJ_NS_TYPE_NONE, NULL, name, p_sd); -} - -/** - * sysfs_read_ns_type: return associated ns_type - * @kobj: the kobject being queried - * - * Each kobject can be tagged with exactly one namespace type - * (i.e. network or user). Return the ns_type associated with - * this object if any - */ -static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj) -{ - const struct kobj_ns_type_operations *ops; - enum kobj_ns_type type; - - ops = kobj_child_ns_ops(kobj); - if (!ops) - return KOBJ_NS_TYPE_NONE; - - type = ops->type; - BUG_ON(type <= KOBJ_NS_TYPE_NONE); - BUG_ON(type >= KOBJ_NS_TYPES); - BUG_ON(!kobj_ns_type_registered(type)); - - return type; -} - -/** - * sysfs_create_dir - create a directory for an object. - * @kobj: object we're creating directory for. - */ -int sysfs_create_dir(struct kobject * kobj) -{ - enum kobj_ns_type type; - struct sysfs_dirent *parent_sd, *sd; - const void *ns = NULL; - int error = 0; - - BUG_ON(!kobj); if (kobj->parent) - parent_sd = kobj->parent->sd; + parent = kobj->parent->sd; else - parent_sd = &sysfs_root; + parent = sysfs_root_kn; - if (!parent_sd) + if (!parent) return -ENOENT; - if (sysfs_ns_type(parent_sd)) - ns = kobj->ktype->namespace(kobj); - type = sysfs_read_ns_type(kobj); - - error = create_dir(kobj, parent_sd, type, ns, kobject_name(kobj), &sd); - if (!error) - kobj->sd = sd; - return error; -} - -static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, - unsigned int flags) -{ - struct dentry *ret = NULL; - struct dentry *parent = dentry->d_parent; - struct sysfs_dirent *parent_sd = parent->d_fsdata; - struct sysfs_dirent *sd; - struct inode *inode; - enum kobj_ns_type type; - const void *ns; - - mutex_lock(&sysfs_mutex); - - type = sysfs_ns_type(parent_sd); - ns = sysfs_info(dir->i_sb)->ns[type]; - - sd = sysfs_find_dirent(parent_sd, ns, dentry->d_name.name); + kobject_get_ownership(kobj, &uid, &gid); - /* no such entry */ - if (!sd) { - ret = ERR_PTR(-ENOENT); - goto out_unlock; + kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid, + kobj, ns); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, kobject_name(kobj)); + return PTR_ERR(kn); } - dentry->d_fsdata = sysfs_get(sd); - - /* attach dentry and inode */ - inode = sysfs_get_inode(dir->i_sb, sd); - if (!inode) { - ret = ERR_PTR(-ENOMEM); - goto out_unlock; - } - - /* instantiate and hash dentry */ - ret = d_materialise_unique(dentry, inode); - out_unlock: - mutex_unlock(&sysfs_mutex); - return ret; -} -const struct inode_operations sysfs_dir_inode_operations = { - .lookup = sysfs_lookup, - .permission = sysfs_permission, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .setxattr = sysfs_setxattr, -}; - -static void remove_dir(struct sysfs_dirent *sd) -{ - struct sysfs_addrm_cxt acxt; - - sysfs_addrm_start(&acxt, sd->s_parent); - sysfs_remove_one(&acxt, sd); - sysfs_addrm_finish(&acxt); -} - -void sysfs_remove_subdir(struct sysfs_dirent *sd) -{ - remove_dir(sd); -} - - -static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd) -{ - struct sysfs_addrm_cxt acxt; - struct rb_node *pos; - - if (!dir_sd) - return; - - pr_debug("sysfs %s: removing dir\n", dir_sd->s_name); - sysfs_addrm_start(&acxt, dir_sd); - pos = rb_first(&dir_sd->s_dir.children); - while (pos) { - struct sysfs_dirent *sd = to_sysfs_dirent(pos); - pos = rb_next(pos); - if (sysfs_type(sd) != SYSFS_DIR) - sysfs_remove_one(&acxt, sd); - } - sysfs_addrm_finish(&acxt); - - remove_dir(dir_sd); + kobj->sd = kn; + return 0; } /** @@ -856,198 +76,86 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd) * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ - -void sysfs_remove_dir(struct kobject * kobj) +void sysfs_remove_dir(struct kobject *kobj) { - struct sysfs_dirent *sd = kobj->sd; + struct kernfs_node *kn = kobj->sd; - spin_lock(&sysfs_assoc_lock); + /* + * In general, kobject owner is responsible for ensuring removal + * doesn't race with other operations and sysfs doesn't provide any + * protection; however, when @kobj is used as a symlink target, the + * symlinking entity usually doesn't own @kobj and thus has no + * control over removal. @kobj->sd may be removed anytime + * and symlink code may end up dereferencing an already freed node. + * + * sysfs_symlink_target_lock synchronizes @kobj->sd + * disassociation against symlink operations so that symlink code + * can safely dereference @kobj->sd. + */ + spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; - spin_unlock(&sysfs_assoc_lock); + spin_unlock(&sysfs_symlink_target_lock); - __sysfs_remove_dir(sd); -} - -int sysfs_rename(struct sysfs_dirent *sd, - struct sysfs_dirent *new_parent_sd, const void *new_ns, - const char *new_name) -{ - int error; - - mutex_lock(&sysfs_mutex); - - error = 0; - if ((sd->s_parent == new_parent_sd) && (sd->s_ns == new_ns) && - (strcmp(sd->s_name, new_name) == 0)) - goto out; /* nothing to rename */ - - error = -EEXIST; - if (sysfs_find_dirent(new_parent_sd, new_ns, new_name)) - goto out; - - /* rename sysfs_dirent */ - if (strcmp(sd->s_name, new_name) != 0) { - error = -ENOMEM; - new_name = kstrdup(new_name, GFP_KERNEL); - if (!new_name) - goto out; - - kfree(sd->s_name); - sd->s_name = new_name; + if (kn) { + WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); + kernfs_remove(kn); } - - /* Move to the appropriate place in the appropriate directories rbtree. */ - sysfs_unlink_sibling(sd); - sysfs_get(new_parent_sd); - sysfs_put(sd->s_parent); - sd->s_ns = new_ns; - sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name); - sd->s_parent = new_parent_sd; - sysfs_link_sibling(sd); - - error = 0; - out: - mutex_unlock(&sysfs_mutex); - return error; } -int sysfs_rename_dir(struct kobject *kobj, const char *new_name) +int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, + const void *new_ns) { - struct sysfs_dirent *parent_sd = kobj->sd->s_parent; - const void *new_ns = NULL; - - if (sysfs_ns_type(parent_sd)) - new_ns = kobj->ktype->namespace(kobj); + struct kernfs_node *parent; + int ret; - return sysfs_rename(kobj->sd, parent_sd, new_ns, new_name); + parent = kernfs_get_parent(kobj->sd); + ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); + kernfs_put(parent); + return ret; } -int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) +int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, + const void *new_ns) { - struct sysfs_dirent *sd = kobj->sd; - struct sysfs_dirent *new_parent_sd; - const void *new_ns = NULL; + struct kernfs_node *kn = kobj->sd; + struct kernfs_node *new_parent; - BUG_ON(!sd->s_parent); - if (sysfs_ns_type(sd->s_parent)) - new_ns = kobj->ktype->namespace(kobj); - new_parent_sd = new_parent_kobj && new_parent_kobj->sd ? - new_parent_kobj->sd : &sysfs_root; + new_parent = new_parent_kobj && new_parent_kobj->sd ? + new_parent_kobj->sd : sysfs_root_kn; - return sysfs_rename(sd, new_parent_sd, new_ns, sd->s_name); -} - -/* Relationship between s_mode and the DT_xxx types */ -static inline unsigned char dt_type(struct sysfs_dirent *sd) -{ - return (sd->s_mode >> 12) & 15; -} - -static int sysfs_dir_release(struct inode *inode, struct file *filp) -{ - sysfs_put(filp->private_data); - return 0; + return kernfs_rename_ns(kn, new_parent, NULL, new_ns); } -static struct sysfs_dirent *sysfs_dir_pos(const void *ns, - struct sysfs_dirent *parent_sd, loff_t hash, struct sysfs_dirent *pos) +/** + * sysfs_create_mount_point - create an always empty directory + * @parent_kobj: kobject that will contain this always empty directory + * @name: The name of the always empty directory to add + */ +int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) { - if (pos) { - int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) && - pos->s_parent == parent_sd && - hash == pos->s_hash; - sysfs_put(pos); - if (!valid) - pos = NULL; - } - if (!pos && (hash > 1) && (hash < INT_MAX)) { - struct rb_node *node = parent_sd->s_dir.children.rb_node; - while (node) { - pos = to_sysfs_dirent(node); + struct kernfs_node *kn, *parent = parent_kobj->sd; - if (hash < pos->s_hash) - node = node->rb_left; - else if (hash > pos->s_hash) - node = node->rb_right; - else - break; - } + kn = kernfs_create_empty_dir(parent, name); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, name); + return PTR_ERR(kn); } - /* Skip over entries in the wrong namespace */ - while (pos && pos->s_ns != ns) { - struct rb_node *node = rb_next(&pos->s_rb); - if (!node) - pos = NULL; - else - pos = to_sysfs_dirent(node); - } - return pos; -} - -static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns, - struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos) -{ - pos = sysfs_dir_pos(ns, parent_sd, ino, pos); - if (pos) do { - struct rb_node *node = rb_next(&pos->s_rb); - if (!node) - pos = NULL; - else - pos = to_sysfs_dirent(node); - } while (pos && pos->s_ns != ns); - return pos; -} - -static int sysfs_readdir(struct file *file, struct dir_context *ctx) -{ - struct dentry *dentry = file->f_path.dentry; - struct sysfs_dirent * parent_sd = dentry->d_fsdata; - struct sysfs_dirent *pos = file->private_data; - enum kobj_ns_type type; - const void *ns; - type = sysfs_ns_type(parent_sd); - ns = sysfs_info(dentry->d_sb)->ns[type]; - - if (!dir_emit_dots(file, ctx)) - return 0; - mutex_lock(&sysfs_mutex); - for (pos = sysfs_dir_pos(ns, parent_sd, ctx->pos, pos); - pos; - pos = sysfs_dir_next_pos(ns, parent_sd, ctx->pos, pos)) { - const char *name = pos->s_name; - unsigned int type = dt_type(pos); - int len = strlen(name); - ino_t ino = pos->s_ino; - ctx->pos = pos->s_hash; - file->private_data = sysfs_get(pos); - - mutex_unlock(&sysfs_mutex); - if (!dir_emit(ctx, name, len, ino, type)) - return 0; - mutex_lock(&sysfs_mutex); - } - mutex_unlock(&sysfs_mutex); - file->private_data = NULL; - ctx->pos = INT_MAX; return 0; } +EXPORT_SYMBOL_GPL(sysfs_create_mount_point); -static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence) +/** + * sysfs_remove_mount_point - remove an always empty directory. + * @parent_kobj: kobject that will contain this always empty directory + * @name: The name of the always empty directory to remove + * + */ +void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) { - struct inode *inode = file_inode(file); - loff_t ret; - - mutex_lock(&inode->i_mutex); - ret = generic_file_llseek(file, offset, whence); - mutex_unlock(&inode->i_mutex); + struct kernfs_node *parent = parent_kobj->sd; - return ret; + kernfs_remove_by_name_ns(parent, name, NULL); } - -const struct file_operations sysfs_dir_operations = { - .read = generic_read_dir, - .iterate = sysfs_readdir, - .release = sysfs_dir_release, - .llseek = sysfs_dir_llseek, -}; +EXPORT_SYMBOL_GPL(sysfs_remove_mount_point); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index d2bb7ed8fa74..3825e780cc58 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/file.c - sysfs regular (text) file implementation * @@ -5,580 +6,376 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/module.h> #include <linux/kobject.h> -#include <linux/kallsyms.h> #include <linux/slab.h> -#include <linux/fsnotify.h> -#include <linux/namei.h> -#include <linux/poll.h> #include <linux/list.h> #include <linux/mutex.h> -#include <linux/limits.h> -#include <asm/uaccess.h> +#include <linux/seq_file.h> +#include <linux/mm.h> #include "sysfs.h" +static struct kobject *sysfs_file_kobj(struct kernfs_node *kn) +{ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + /* - * There's one sysfs_buffer for each open file and one - * sysfs_open_dirent for each sysfs_dirent with one or more open - * files. - * - * filp->private_data points to sysfs_buffer and - * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open - * is protected by sysfs_open_dirent_lock. + * Determine ktype->sysfs_ops for the given kernfs_node. This function + * must be called while holding an active reference. */ -static DEFINE_SPINLOCK(sysfs_open_dirent_lock); - -struct sysfs_open_dirent { - atomic_t refcnt; - atomic_t event; - wait_queue_head_t poll; - struct list_head buffers; /* goes through sysfs_buffer.list */ -}; +static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) +{ + struct kobject *kobj = sysfs_file_kobj(kn); -struct sysfs_buffer { - size_t count; - loff_t pos; - char * page; - const struct sysfs_ops * ops; - struct mutex mutex; - int needs_read_fill; - int event; - struct list_head list; -}; + if (kn->flags & KERNFS_LOCKDEP) + lockdep_assert_held(kn); + return kobj->ktype ? kobj->ktype->sysfs_ops : NULL; +} -/** - * fill_read_buffer - allocate and fill buffer from object. - * @dentry: dentry pointer. - * @buffer: data buffer for file. - * - * Allocate @buffer->page, if it hasn't been already, then call the - * kobject's show() method to fill the buffer with this attribute's - * data. - * This is called only once, on the file's first read unless an error - * is returned. +/* + * Reads on sysfs are handled through seq_file, which takes care of hairy + * details like buffering and seeking. The following function pipes + * sysfs_ops->show() result through seq_file. */ -static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer) +static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { - struct sysfs_dirent *attr_sd = dentry->d_fsdata; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - const struct sysfs_ops * ops = buffer->ops; - int ret = 0; + struct kernfs_open_file *of = sf->private; + struct kobject *kobj = sysfs_file_kobj(of->kn); + const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; + char *buf; - if (!buffer->page) - buffer->page = (char *) get_zeroed_page(GFP_KERNEL); - if (!buffer->page) - return -ENOMEM; - - /* need attr_sd for attr and ops, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; + if (WARN_ON_ONCE(!ops->show)) + return -EINVAL; - buffer->event = atomic_read(&attr_sd->s_attr.open->event); - count = ops->show(kobj, attr_sd->s_attr.attr, buffer->page); + /* acquire buffer and ensure that it's >= PAGE_SIZE and clear */ + count = seq_get_buf(sf, &buf); + if (count < PAGE_SIZE) { + seq_commit(sf, -1); + return 0; + } + memset(buf, 0, PAGE_SIZE); - sysfs_put_active(attr_sd); + count = ops->show(kobj, of->kn->priv, buf); + if (count < 0) + return count; /* * The code works fine with PAGE_SIZE return but it's likely to * indicate truncated result or overflow in normal use cases. */ if (count >= (ssize_t)PAGE_SIZE) { - print_symbol("fill_read_buffer: %s returned bad count\n", - (unsigned long)ops->show); + printk("fill_read_buffer: %pS returned bad count\n", + ops->show); /* Try to struggle along */ count = PAGE_SIZE - 1; } - if (count >= 0) { - buffer->needs_read_fill = 0; - buffer->count = count; - } else { - ret = count; - } - return ret; -} - -/** - * sysfs_read_file - read an attribute. - * @file: file pointer. - * @buf: buffer to fill. - * @count: number of bytes to read. - * @ppos: starting offset in file. - * - * Userspace wants to read an attribute file. The attribute descriptor - * is in the file's ->d_fsdata. The target object is in the directory's - * ->d_fsdata. - * - * We call fill_read_buffer() to allocate and fill the buffer from the - * object's show() method exactly once (if the read is happening from - * the beginning of the file). That should fill the entire buffer with - * all the data the object has to offer for that attribute. - * We then call flush_read_buffer() to copy the buffer to userspace - * in the increments specified. - */ - -static ssize_t -sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) -{ - struct sysfs_buffer * buffer = file->private_data; - ssize_t retval = 0; - - mutex_lock(&buffer->mutex); - if (buffer->needs_read_fill || *ppos == 0) { - retval = fill_read_buffer(file->f_path.dentry,buffer); - if (retval) - goto out; - } - pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n", - __func__, count, *ppos, buffer->page); - retval = simple_read_from_buffer(buf, count, ppos, buffer->page, - buffer->count); -out: - mutex_unlock(&buffer->mutex); - return retval; -} - -/** - * fill_write_buffer - copy buffer from userspace. - * @buffer: data buffer for file. - * @buf: data from user. - * @count: number of bytes in @userbuf. - * - * Allocate @buffer->page if it hasn't been already, then - * copy the user-supplied buffer into it. - */ - -static int -fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t count) -{ - int error; - - if (!buffer->page) - buffer->page = (char *)get_zeroed_page(GFP_KERNEL); - if (!buffer->page) - return -ENOMEM; - - if (count >= PAGE_SIZE) - count = PAGE_SIZE - 1; - error = copy_from_user(buffer->page,buf,count); - buffer->needs_read_fill = 1; - /* if buf is assumed to contain a string, terminate it by \0, - so e.g. sscanf() can scan the string easily */ - buffer->page[count] = 0; - return error ? -EFAULT : count; + seq_commit(sf, count); + return 0; } - -/** - * flush_write_buffer - push buffer to kobject. - * @dentry: dentry to the attribute - * @buffer: data buffer for file. - * @count: number of bytes - * - * Get the correct pointers for the kobject and the attribute we're - * dealing with, then call the store() method for the attribute, - * passing the buffer that we acquired in fill_write_buffer(). - */ - -static int -flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t count) +static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct sysfs_dirent *attr_sd = dentry->d_fsdata; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - const struct sysfs_ops * ops = buffer->ops; - int rc; + const struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); + loff_t size = file_inode(of->file)->i_size; - /* need attr_sd for attr and ops, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; + if (!count) + return 0; - rc = ops->store(kobj, attr_sd->s_attr.attr, buffer->page, count); + if (size) { + if (pos >= size) + return 0; + if (pos + count > size) + count = size - pos; + } - sysfs_put_active(attr_sd); + if (!battr->read) + return -EIO; - return rc; + return battr->read(of->file, kobj, battr, buf, pos, count); } - -/** - * sysfs_write_file - write an attribute. - * @file: file pointer - * @buf: data to write - * @count: number of bytes - * @ppos: starting offset - * - * Similar to sysfs_read_file(), though working in the opposite direction. - * We allocate and fill the data from the user in fill_write_buffer(), - * then push it to the kobject in flush_write_buffer(). - * There is no easy way for us to know if userspace is only doing a partial - * write, so we don't support them. We expect the entire buffer to come - * on the first write. - * Hint: if you're writing a value, first read the file, modify only the - * the value you're changing, then write entire buffer back. - */ - -static ssize_t -sysfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +/* kernfs read callback for regular sysfs files with pre-alloc */ +static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct sysfs_buffer * buffer = file->private_data; + const struct sysfs_ops *ops = sysfs_file_ops(of->kn); + struct kobject *kobj = sysfs_file_kobj(of->kn); ssize_t len; - mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, buf, count); - if (len > 0) - len = flush_write_buffer(file->f_path.dentry, buffer, len); - if (len > 0) - *ppos += len; - mutex_unlock(&buffer->mutex); - return len; + /* + * If buf != of->prealloc_buf, we don't know how + * large it is, so cannot safely pass it to ->show + */ + if (WARN_ON_ONCE(buf != of->prealloc_buf)) + return 0; + len = ops->show(kobj, of->kn->priv, buf); + if (len < 0) + return len; + if (pos) { + if (len <= pos) + return 0; + len -= pos; + memmove(buf, buf + pos, len); + } + return min_t(ssize_t, count, len); } -/** - * sysfs_get_open_dirent - get or create sysfs_open_dirent - * @sd: target sysfs_dirent - * @buffer: sysfs_buffer for this instance of open - * - * If @sd->s_attr.open exists, increment its reference count; - * otherwise, create one. @buffer is chained to the buffers - * list. - * - * LOCKING: - * Kernel thread context (may sleep). - * - * RETURNS: - * 0 on success, -errno on failure. - */ -static int sysfs_get_open_dirent(struct sysfs_dirent *sd, - struct sysfs_buffer *buffer) +/* kernfs write callback for regular sysfs files */ +static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) { - struct sysfs_open_dirent *od, *new_od = NULL; + const struct sysfs_ops *ops = sysfs_file_ops(of->kn); + struct kobject *kobj = sysfs_file_kobj(of->kn); - retry: - spin_lock_irq(&sysfs_open_dirent_lock); + if (!count) + return 0; - if (!sd->s_attr.open && new_od) { - sd->s_attr.open = new_od; - new_od = NULL; - } + return ops->store(kobj, of->kn->priv, buf, count); +} - od = sd->s_attr.open; - if (od) { - atomic_inc(&od->refcnt); - list_add_tail(&buffer->list, &od->buffers); +/* kernfs write callback for bin sysfs files */ +static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, + size_t count, loff_t pos) +{ + const struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); + loff_t size = file_inode(of->file)->i_size; + + if (size) { + if (size <= pos) + return -EFBIG; + count = min_t(ssize_t, count, size - pos); } - - spin_unlock_irq(&sysfs_open_dirent_lock); - - if (od) { - kfree(new_od); + if (!count) return 0; - } - /* not there, initialize a new one and retry */ - new_od = kmalloc(sizeof(*new_od), GFP_KERNEL); - if (!new_od) - return -ENOMEM; + if (!battr->write) + return -EIO; - atomic_set(&new_od->refcnt, 0); - atomic_set(&new_od->event, 1); - init_waitqueue_head(&new_od->poll); - INIT_LIST_HEAD(&new_od->buffers); - goto retry; + return battr->write(of->file, kobj, battr, buf, pos, count); } -/** - * sysfs_put_open_dirent - put sysfs_open_dirent - * @sd: target sysfs_dirent - * @buffer: associated sysfs_buffer - * - * Put @sd->s_attr.open and unlink @buffer from the buffers list. - * If reference count reaches zero, disassociate and free it. - * - * LOCKING: - * None. - */ -static void sysfs_put_open_dirent(struct sysfs_dirent *sd, - struct sysfs_buffer *buffer) +static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, + struct vm_area_struct *vma) { - struct sysfs_open_dirent *od = sd->s_attr.open; - unsigned long flags; - - spin_lock_irqsave(&sysfs_open_dirent_lock, flags); - - list_del(&buffer->list); - if (atomic_dec_and_test(&od->refcnt)) - sd->s_attr.open = NULL; - else - od = NULL; - - spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags); + const struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); - kfree(od); + return battr->mmap(of->file, kobj, battr, vma); } -static int sysfs_open_file(struct inode *inode, struct file *file) +static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, + int whence) { - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_buffer *buffer; - const struct sysfs_ops *ops; - int error = -EACCES; - - /* need attr_sd for attr and ops, its parent for kobj */ - if (!sysfs_get_active(attr_sd)) - return -ENODEV; - - /* every kobject with an attribute needs a ktype assigned */ - if (kobj->ktype && kobj->ktype->sysfs_ops) - ops = kobj->ktype->sysfs_ops; - else { - WARN(1, KERN_ERR "missing sysfs attribute operations for " - "kobject: %s\n", kobject_name(kobj)); - goto err_out; - } - - /* File needs write support. - * The inode's perms must say it's ok, - * and we must have a store method. - */ - if (file->f_mode & FMODE_WRITE) { - if (!(inode->i_mode & S_IWUGO) || !ops->store) - goto err_out; - } + const struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); - /* File needs read support. - * The inode's perms must say it's ok, and we there - * must be a show method for it. - */ - if (file->f_mode & FMODE_READ) { - if (!(inode->i_mode & S_IRUGO) || !ops->show) - goto err_out; - } - - /* No error? Great, allocate a buffer for the file, and store it - * it in file->private_data for easy access. - */ - error = -ENOMEM; - buffer = kzalloc(sizeof(struct sysfs_buffer), GFP_KERNEL); - if (!buffer) - goto err_out; - - mutex_init(&buffer->mutex); - buffer->needs_read_fill = 1; - buffer->ops = ops; - file->private_data = buffer; - - /* make sure we have open dirent struct */ - error = sysfs_get_open_dirent(attr_sd, buffer); - if (error) - goto err_free; - - /* open succeeded, put active references */ - sysfs_put_active(attr_sd); - return 0; - - err_free: - kfree(buffer); - err_out: - sysfs_put_active(attr_sd); - return error; + if (battr->llseek) + return battr->llseek(of->file, kobj, battr, offset, whence); + else + return generic_file_llseek(of->file, offset, whence); } -static int sysfs_release(struct inode *inode, struct file *filp) +static int sysfs_kf_bin_open(struct kernfs_open_file *of) { - struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata; - struct sysfs_buffer *buffer = filp->private_data; - - sysfs_put_open_dirent(sd, buffer); + const struct bin_attribute *battr = of->kn->priv; - if (buffer->page) - free_page((unsigned long)buffer->page); - kfree(buffer); + if (battr->f_mapping) + of->file->f_mapping = battr->f_mapping(); return 0; } -/* Sysfs attribute files are pollable. The idea is that you read - * the content and then you use 'poll' or 'select' to wait for - * the content to change. When the content changes (assuming the - * manager for the kobject supports notification), poll will - * return POLLERR|POLLPRI, and select will return the fd whether - * it is waiting for read, write, or exceptions. - * Once poll/select indicates that the value has changed, you - * need to close and re-open the file, or seek to 0 and read again. - * Reminder: this only works for attributes which actively support - * it, and it is not possible to test an attribute from userspace - * to see if it supports poll (Neither 'poll' nor 'select' return - * an appropriate error code). When in doubt, set a suitable timeout value. - */ -static unsigned int sysfs_poll(struct file *filp, poll_table *wait) +void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { - struct sysfs_buffer * buffer = filp->private_data; - struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata; - struct sysfs_open_dirent *od = attr_sd->s_attr.open; - - /* need parent for the kobj, grab both */ - if (!sysfs_get_active(attr_sd)) - goto trigger; + struct kernfs_node *kn = kobj->sd, *tmp; - poll_wait(filp, &od->poll, wait); + if (kn && dir) + kn = kernfs_find_and_get(kn, dir); + else + kernfs_get(kn); - sysfs_put_active(attr_sd); + if (kn && attr) { + tmp = kernfs_find_and_get(kn, attr); + kernfs_put(kn); + kn = tmp; + } - if (buffer->event != atomic_read(&od->event)) - goto trigger; + if (kn) { + kernfs_notify(kn); + kernfs_put(kn); + } +} +EXPORT_SYMBOL_GPL(sysfs_notify); - return DEFAULT_POLLMASK; +static const struct kernfs_ops sysfs_file_kfops_empty = { +}; - trigger: - buffer->needs_read_fill = 1; - return DEFAULT_POLLMASK|POLLERR|POLLPRI; -} +static const struct kernfs_ops sysfs_file_kfops_ro = { + .seq_show = sysfs_kf_seq_show, +}; -void sysfs_notify_dirent(struct sysfs_dirent *sd) -{ - struct sysfs_open_dirent *od; - unsigned long flags; +static const struct kernfs_ops sysfs_file_kfops_wo = { + .write = sysfs_kf_write, +}; - spin_lock_irqsave(&sysfs_open_dirent_lock, flags); +static const struct kernfs_ops sysfs_file_kfops_rw = { + .seq_show = sysfs_kf_seq_show, + .write = sysfs_kf_write, +}; - if (!WARN_ON(sysfs_type(sd) != SYSFS_KOBJ_ATTR)) { - od = sd->s_attr.open; - if (od) { - atomic_inc(&od->event); - wake_up_interruptible(&od->poll); - } - } +static const struct kernfs_ops sysfs_prealloc_kfops_ro = { + .read = sysfs_kf_read, + .prealloc = true, +}; - spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags); -} -EXPORT_SYMBOL_GPL(sysfs_notify_dirent); +static const struct kernfs_ops sysfs_prealloc_kfops_wo = { + .write = sysfs_kf_write, + .prealloc = true, +}; -void sysfs_notify(struct kobject *k, const char *dir, const char *attr) -{ - struct sysfs_dirent *sd = k->sd; +static const struct kernfs_ops sysfs_prealloc_kfops_rw = { + .read = sysfs_kf_read, + .write = sysfs_kf_write, + .prealloc = true, +}; - mutex_lock(&sysfs_mutex); +static const struct kernfs_ops sysfs_bin_kfops_ro = { + .read = sysfs_kf_bin_read, +}; - if (sd && dir) - sd = sysfs_find_dirent(sd, NULL, dir); - if (sd && attr) - sd = sysfs_find_dirent(sd, NULL, attr); - if (sd) - sysfs_notify_dirent(sd); +static const struct kernfs_ops sysfs_bin_kfops_wo = { + .write = sysfs_kf_bin_write, +}; - mutex_unlock(&sysfs_mutex); -} -EXPORT_SYMBOL_GPL(sysfs_notify); +static const struct kernfs_ops sysfs_bin_kfops_rw = { + .read = sysfs_kf_bin_read, + .write = sysfs_kf_bin_write, +}; -const struct file_operations sysfs_file_operations = { - .read = sysfs_read_file, - .write = sysfs_write_file, - .llseek = generic_file_llseek, - .open = sysfs_open_file, - .release = sysfs_release, - .poll = sysfs_poll, +static const struct kernfs_ops sysfs_bin_kfops_mmap = { + .read = sysfs_kf_bin_read, + .write = sysfs_kf_bin_write, + .mmap = sysfs_kf_bin_mmap, + .open = sysfs_kf_bin_open, + .llseek = sysfs_kf_bin_llseek, }; -static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr, - const void **pns) +int sysfs_add_file_mode_ns(struct kernfs_node *parent, + const struct attribute *attr, umode_t mode, kuid_t uid, + kgid_t gid, const void *ns) { - struct sysfs_dirent *dir_sd = kobj->sd; - const struct sysfs_ops *ops; - const void *ns = NULL; - int err; + struct kobject *kobj = parent->priv; + const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops; + struct lock_class_key *key = NULL; + const struct kernfs_ops *ops = NULL; + struct kernfs_node *kn; - if (!dir_sd) { - WARN(1, KERN_ERR "sysfs: kobject %s without dirent\n", - kobject_name(kobj)); - return -ENOENT; + /* every kobject with an attribute needs a ktype assigned */ + if (WARN(!sysfs_ops, KERN_ERR + "missing sysfs attribute operations for kobject: %s\n", + kobject_name(kobj))) + return -EINVAL; + + if (mode & SYSFS_PREALLOC) { + if (sysfs_ops->show && sysfs_ops->store) + ops = &sysfs_prealloc_kfops_rw; + else if (sysfs_ops->show) + ops = &sysfs_prealloc_kfops_ro; + else if (sysfs_ops->store) + ops = &sysfs_prealloc_kfops_wo; + } else { + if (sysfs_ops->show && sysfs_ops->store) + ops = &sysfs_file_kfops_rw; + else if (sysfs_ops->show) + ops = &sysfs_file_kfops_ro; + else if (sysfs_ops->store) + ops = &sysfs_file_kfops_wo; } - err = 0; - if (!sysfs_ns_type(dir_sd)) - goto out; - - err = -EINVAL; - if (!kobj->ktype) - goto out; - ops = kobj->ktype->sysfs_ops; if (!ops) - goto out; - if (!ops->namespace) - goto out; - - err = 0; - ns = ops->namespace(kobj, attr); -out: - if (err) { - WARN(1, KERN_ERR "missing sysfs namespace attribute operation for " - "kobject: %s\n", kobject_name(kobj)); + ops = &sysfs_file_kfops_empty; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (!attr->ignore_lockdep) + key = attr->key ?: (struct lock_class_key *)&attr->skey; +#endif + + kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, + PAGE_SIZE, ops, (void *)attr, ns, key); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, attr->name); + return PTR_ERR(kn); } - *pns = ns; - return err; -} - -int sysfs_add_file_mode(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type, umode_t amode) -{ - umode_t mode = (amode & S_IALLUGO) | S_IFREG; - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - const void *ns; - int rc; - - rc = sysfs_attr_ns(dir_sd->s_dir.kobj, attr, &ns); - if (rc) - return rc; - - sd = sysfs_new_dirent(attr->name, mode, type); - if (!sd) - return -ENOMEM; - - sd->s_ns = ns; - sd->s_attr.attr = (void *)attr; - sysfs_dirent_init_lockdep(sd); - - sysfs_addrm_start(&acxt, dir_sd); - rc = sysfs_add_one(&acxt, sd); - sysfs_addrm_finish(&acxt); - - if (rc) - sysfs_put(sd); - - return rc; + return 0; } - -int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr, - int type) +int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, + const struct bin_attribute *battr, umode_t mode, size_t size, + kuid_t uid, kgid_t gid, const void *ns) { - return sysfs_add_file_mode(dir_sd, attr, type, attr->mode); + const struct attribute *attr = &battr->attr; + struct lock_class_key *key = NULL; + const struct kernfs_ops *ops; + struct kernfs_node *kn; + + if (battr->mmap) + ops = &sysfs_bin_kfops_mmap; + else if (battr->read && battr->write) + ops = &sysfs_bin_kfops_rw; + else if (battr->read) + ops = &sysfs_bin_kfops_ro; + else if (battr->write) + ops = &sysfs_bin_kfops_wo; + else + ops = &sysfs_file_kfops_empty; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + if (!attr->ignore_lockdep) + key = attr->key ?: (struct lock_class_key *)&attr->skey; +#endif + + kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, + size, ops, (void *)attr, ns, key); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, attr->name); + return PTR_ERR(kn); + } + return 0; } - /** - * sysfs_create_file - create an attribute file for an object. - * @kobj: object we're creating for. - * @attr: attribute descriptor. + * sysfs_create_file_ns - create an attribute file for an object with custom ns + * @kobj: object we're creating for + * @attr: attribute descriptor + * @ns: namespace the new file should belong to */ - -int sysfs_create_file(struct kobject * kobj, const struct attribute * attr) +int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, + const void *ns) { - BUG_ON(!kobj || !kobj->sd || !attr); + kuid_t uid; + kgid_t gid; - return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR); + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; + kobject_get_ownership(kobj, &uid, &gid); + return sysfs_add_file_mode_ns(kobj->sd, attr, attr->mode, uid, gid, ns); } +EXPORT_SYMBOL_GPL(sysfs_create_file_ns); -int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) +int sysfs_create_files(struct kobject *kobj, const struct attribute * const *ptr) { int err = 0; int i; @@ -590,6 +387,7 @@ int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) sysfs_remove_file(kobj, ptr[i]); return err; } +EXPORT_SYMBOL_GPL(sysfs_create_files); /** * sysfs_add_file_to_group - add an attribute file to a pre-existing group. @@ -600,19 +398,25 @@ int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; + kuid_t uid; + kgid_t gid; int error; - if (group) - dir_sd = sysfs_get_dirent(kobj->sd, NULL, group); - else - dir_sd = sysfs_get(kobj->sd); + if (group) { + parent = kernfs_find_and_get(kobj->sd, group); + } else { + parent = kobj->sd; + kernfs_get(parent); + } - if (!dir_sd) + if (!parent) return -ENOENT; - error = sysfs_add_file(dir_sd, attr, SYSFS_KOBJ_ATTR); - sysfs_put(dir_sd); + kobject_get_ownership(kobj, &uid, &gid); + error = sysfs_add_file_mode_ns(parent, attr, attr->mode, uid, gid, + NULL); + kernfs_put(parent); return error; } @@ -628,57 +432,119 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode) { - struct sysfs_dirent *sd; + struct kernfs_node *kn; struct iattr newattrs; - const void *ns; int rc; - rc = sysfs_attr_ns(kobj, attr, &ns); - if (rc) - return rc; - - mutex_lock(&sysfs_mutex); - - rc = -ENOENT; - sd = sysfs_find_dirent(kobj->sd, ns, attr->name); - if (!sd) - goto out; + kn = kernfs_find_and_get(kobj->sd, attr->name); + if (!kn) + return -ENOENT; - newattrs.ia_mode = (mode & S_IALLUGO) | (sd->s_mode & ~S_IALLUGO); + newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE; - rc = sysfs_sd_setattr(sd, &newattrs); - out: - mutex_unlock(&sysfs_mutex); + rc = kernfs_setattr(kn, &newattrs); + + kernfs_put(kn); return rc; } EXPORT_SYMBOL_GPL(sysfs_chmod_file); +/** + * sysfs_break_active_protection - break "active" protection + * @kobj: The kernel object @attr is associated with. + * @attr: The attribute to break the "active" protection for. + * + * With sysfs, just like kernfs, deletion of an attribute is postponed until + * all active .show() and .store() callbacks have finished unless this function + * is called. Hence this function is useful in methods that implement self + * deletion. + */ +struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, + const struct attribute *attr) +{ + struct kernfs_node *kn; + + kobject_get(kobj); + kn = kernfs_find_and_get(kobj->sd, attr->name); + if (kn) + kernfs_break_active_protection(kn); + else + kobject_put(kobj); + return kn; +} +EXPORT_SYMBOL_GPL(sysfs_break_active_protection); /** - * sysfs_remove_file - remove an object attribute. - * @kobj: object we're acting for. - * @attr: attribute descriptor. + * sysfs_unbreak_active_protection - restore "active" protection + * @kn: Pointer returned by sysfs_break_active_protection(). + * + * Undo the effects of sysfs_break_active_protection(). Since this function + * calls kernfs_put() on the kernfs node that corresponds to the 'attr' + * argument passed to sysfs_break_active_protection() that attribute may have + * been removed between the sysfs_break_active_protection() and + * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after + * this function has returned. + */ +void sysfs_unbreak_active_protection(struct kernfs_node *kn) +{ + struct kobject *kobj = sysfs_file_kobj(kn); + + kernfs_unbreak_active_protection(kn); + kernfs_put(kn); + kobject_put(kobj); +} +EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); + +/** + * sysfs_remove_file_ns - remove an object attribute with a custom ns tag + * @kobj: object we're acting for + * @attr: attribute descriptor + * @ns: namespace tag of the file to remove * - * Hash the attribute name and kill the victim. + * Hash the attribute name and namespace tag and kill the victim. */ +void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, + const void *ns) +{ + struct kernfs_node *parent = kobj->sd; -void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr) + kernfs_remove_by_name_ns(parent, attr->name, ns); +} +EXPORT_SYMBOL_GPL(sysfs_remove_file_ns); + +/** + * sysfs_remove_file_self - remove an object attribute from its own method + * @kobj: object we're acting for + * @attr: attribute descriptor + * + * See kernfs_remove_self() for details. + */ +bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) { - const void *ns; + struct kernfs_node *parent = kobj->sd; + struct kernfs_node *kn; + bool ret; - if (sysfs_attr_ns(kobj, attr, &ns)) - return; + kn = kernfs_find_and_get(parent, attr->name); + if (WARN_ON_ONCE(!kn)) + return false; - sysfs_hash_and_remove(kobj->sd, ns, attr->name); + ret = kernfs_remove_self(kn); + + kernfs_put(kn); + return ret; } +EXPORT_SYMBOL_GPL(sysfs_remove_file_self); -void sysfs_remove_files(struct kobject * kobj, const struct attribute **ptr) +void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; + for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } +EXPORT_SYMBOL_GPL(sysfs_remove_files); /** * sysfs_remove_file_from_group - remove an attribute file from a group. @@ -689,113 +555,266 @@ void sysfs_remove_files(struct kobject * kobj, const struct attribute **ptr) void sysfs_remove_file_from_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; - if (group) - dir_sd = sysfs_get_dirent(kobj->sd, NULL, group); - else - dir_sd = sysfs_get(kobj->sd); - if (dir_sd) { - sysfs_hash_and_remove(dir_sd, NULL, attr->name); - sysfs_put(dir_sd); + if (group) { + parent = kernfs_find_and_get(kobj->sd, group); + } else { + parent = kobj->sd; + kernfs_get(parent); + } + + if (parent) { + kernfs_remove_by_name(parent, attr->name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); -struct sysfs_schedule_callback_struct { - struct list_head workq_list; - struct kobject *kobj; - void (*func)(void *); - void *data; - struct module *owner; - struct work_struct work; -}; +/** + * sysfs_create_bin_file - create binary file for object. + * @kobj: object. + * @attr: attribute descriptor. + */ +int sysfs_create_bin_file(struct kobject *kobj, + const struct bin_attribute *attr) +{ + kuid_t uid; + kgid_t gid; + + if (WARN_ON(!kobj || !kobj->sd || !attr)) + return -EINVAL; -static struct workqueue_struct *sysfs_workqueue; -static DEFINE_MUTEX(sysfs_workq_mutex); -static LIST_HEAD(sysfs_workq); -static void sysfs_schedule_callback_work(struct work_struct *work) + kobject_get_ownership(kobj, &uid, &gid); + return sysfs_add_bin_file_mode_ns(kobj->sd, attr, attr->attr.mode, + attr->size, uid, gid, NULL); +} +EXPORT_SYMBOL_GPL(sysfs_create_bin_file); + +/** + * sysfs_remove_bin_file - remove binary file for object. + * @kobj: object. + * @attr: attribute descriptor. + */ +void sysfs_remove_bin_file(struct kobject *kobj, + const struct bin_attribute *attr) { - struct sysfs_schedule_callback_struct *ss = container_of(work, - struct sysfs_schedule_callback_struct, work); + kernfs_remove_by_name(kobj->sd, attr->attr.name); +} +EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); - (ss->func)(ss->data); - kobject_put(ss->kobj); - module_put(ss->owner); - mutex_lock(&sysfs_workq_mutex); - list_del(&ss->workq_list); - mutex_unlock(&sysfs_workq_mutex); - kfree(ss); +static int internal_change_owner(struct kernfs_node *kn, kuid_t kuid, + kgid_t kgid) +{ + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + return kernfs_setattr(kn, &newattrs); } /** - * sysfs_schedule_callback - helper to schedule a callback for a kobject - * @kobj: object we're acting for. - * @func: callback function to invoke later. - * @data: argument to pass to @func. - * @owner: module owning the callback code + * sysfs_link_change_owner - change owner of a sysfs file. + * @kobj: object of the kernfs_node the symlink is located in. + * @targ: object of the kernfs_node the symlink points to. + * @name: name of the link. + * @kuid: new owner's kuid + * @kgid: new owner's kgid * - * sysfs attribute methods must not unregister themselves or their parent - * kobject (which would amount to the same thing). Attempts to do so will - * deadlock, since unregistration is mutually exclusive with driver - * callbacks. + * This function looks up the sysfs symlink entry @name under @kobj and changes + * the ownership to @kuid/@kgid. The symlink is looked up in the namespace of + * @targ. * - * Instead methods can call this routine, which will attempt to allocate - * and schedule a workqueue request to call back @func with @data as its - * argument in the workqueue's process context. @kobj will be pinned - * until @func returns. + * Returns 0 on success or error code on failure. + */ +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid) +{ + struct kernfs_node *kn = NULL; + int error; + + if (!name || !kobj->state_in_sysfs || !targ->state_in_sysfs) + return -EINVAL; + + error = -ENOENT; + kn = kernfs_find_and_get_ns(kobj->sd, name, targ->sd->ns); + if (!kn) + goto out; + + error = -EINVAL; + if (kernfs_type(kn) != KERNFS_LINK) + goto out; + if (kn->symlink.target_kn->priv != targ) + goto out; + + error = internal_change_owner(kn, kuid, kgid); + +out: + kernfs_put(kn); + return error; +} + +/** + * sysfs_file_change_owner - change owner of a sysfs file. + * @kobj: object. + * @name: name of the file to change. + * @kuid: new owner's kuid + * @kgid: new owner's kgid * - * Returns 0 if the request was submitted, -ENOMEM if storage could not - * be allocated, -ENODEV if a reference to @owner isn't available, - * -EAGAIN if a callback has already been scheduled for @kobj. + * This function looks up the sysfs entry @name under @kobj and changes the + * ownership to @kuid/@kgid. + * + * Returns 0 on success or error code on failure. */ -int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), - void *data, struct module *owner) -{ - struct sysfs_schedule_callback_struct *ss, *tmp; - - if (!try_module_get(owner)) - return -ENODEV; - - mutex_lock(&sysfs_workq_mutex); - list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list) - if (ss->kobj == kobj) { - module_put(owner); - mutex_unlock(&sysfs_workq_mutex); - return -EAGAIN; - } - mutex_unlock(&sysfs_workq_mutex); - - if (sysfs_workqueue == NULL) { - sysfs_workqueue = create_singlethread_workqueue("sysfsd"); - if (sysfs_workqueue == NULL) { - module_put(owner); - return -ENOMEM; - } - } +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *kn; + int error; + + if (!name) + return -EINVAL; + + if (!kobj->state_in_sysfs) + return -EINVAL; - ss = kmalloc(sizeof(*ss), GFP_KERNEL); - if (!ss) { - module_put(owner); - return -ENOMEM; + kn = kernfs_find_and_get(kobj->sd, name); + if (!kn) + return -ENOENT; + + error = internal_change_owner(kn, kuid, kgid); + + kernfs_put(kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_file_change_owner); + +/** + * sysfs_change_owner - change owner of the given object. + * @kobj: object. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Change the owner of the default directory, files, groups, and attributes of + * @kobj to @kuid/@kgid. Note that sysfs_change_owner mirrors how the sysfs + * entries for a kobject are added by driver core. In summary, + * sysfs_change_owner() takes care of the default directory entry for @kobj, + * the default attributes associated with the ktype of @kobj and the default + * attributes associated with the ktype of @kobj. + * Additional properties not added by driver core have to be changed by the + * driver or subsystem which created them. This is similar to how + * driver/subsystem specific entries are removed. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + int error; + const struct kobj_type *ktype; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + /* Change the owner of the kobject itself. */ + error = internal_change_owner(kobj->sd, kuid, kgid); + if (error) + return error; + + ktype = get_ktype(kobj); + if (ktype) { + /* + * Change owner of the default groups associated with the + * ktype of @kobj. + */ + error = sysfs_groups_change_owner(kobj, ktype->default_groups, + kuid, kgid); + if (error) + return error; } - kobject_get(kobj); - ss->kobj = kobj; - ss->func = func; - ss->data = data; - ss->owner = owner; - INIT_WORK(&ss->work, sysfs_schedule_callback_work); - INIT_LIST_HEAD(&ss->workq_list); - mutex_lock(&sysfs_workq_mutex); - list_add_tail(&ss->workq_list, &sysfs_workq); - mutex_unlock(&sysfs_workq_mutex); - queue_work(sysfs_workqueue, &ss->work); + return 0; } -EXPORT_SYMBOL_GPL(sysfs_schedule_callback); +EXPORT_SYMBOL_GPL(sysfs_change_owner); +/** + * sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer. + * @buf: start of PAGE_SIZE buffer. + * @fmt: format + * @...: optional arguments to @format + * + * + * Returns number of characters written to @buf. + */ +int sysfs_emit(char *buf, const char *fmt, ...) +{ + va_list args; + int len; -EXPORT_SYMBOL_GPL(sysfs_create_file); -EXPORT_SYMBOL_GPL(sysfs_remove_file); -EXPORT_SYMBOL_GPL(sysfs_remove_files); -EXPORT_SYMBOL_GPL(sysfs_create_files); + if (WARN(!buf || offset_in_page(buf), + "invalid sysfs_emit: buf:%p\n", buf)) + return 0; + + va_start(args, fmt); + len = vscnprintf(buf, PAGE_SIZE, fmt, args); + va_end(args); + + return len; +} +EXPORT_SYMBOL_GPL(sysfs_emit); + +/** + * sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer. + * @buf: start of PAGE_SIZE buffer. + * @at: offset in @buf to start write in bytes + * @at must be >= 0 && < PAGE_SIZE + * @fmt: format + * @...: optional arguments to @fmt + * + * + * Returns number of characters written starting at &@buf[@at]. + */ +int sysfs_emit_at(char *buf, int at, const char *fmt, ...) +{ + va_list args; + int len; + + if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE, + "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at)) + return 0; + + va_start(args, fmt); + len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args); + va_end(args); + + return len; +} +EXPORT_SYMBOL_GPL(sysfs_emit_at); + +/** + * sysfs_bin_attr_simple_read - read callback to simply copy from memory. + * @file: attribute file which is being read. + * @kobj: object to which the attribute belongs. + * @attr: attribute descriptor. + * @buf: destination buffer. + * @off: offset in bytes from which to read. + * @count: maximum number of bytes to read. + * + * Simple ->read() callback for bin_attributes backed by a buffer in memory. + * The @private and @size members in struct bin_attribute must be set to the + * buffer's location and size before the bin_attribute is created in sysfs. + * + * Bounds check for @off and @count is done in sysfs_kf_bin_read(). + * Negative value check for @off is done in vfs_setpos() and default_llseek(). + * + * Returns number of bytes written to @buf. + */ +ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, + const struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + memcpy(buf, attr->private + off, count); + return count; +} +EXPORT_SYMBOL_GPL(sysfs_bin_attr_simple_read); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index aec3d5c98c94..e1e639f515a0 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -1,11 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/group.c - Operations for adding/removing multiple files at once. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab - * - * This file is released undert the GPL v2. - * + * Copyright (c) 2013 Greg Kroah-Hartman + * Copyright (c) 2013 The Linux Foundation */ #include <linux/kobject.h> @@ -13,45 +13,115 @@ #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> +#include <linux/fs.h> #include "sysfs.h" -static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, +static void remove_files(struct kernfs_node *parent, const struct attribute_group *grp) { - struct attribute *const* attr; - int i; + struct attribute *const *attr; + const struct bin_attribute *const *bin_attr; + + if (grp->attrs) + for (attr = grp->attrs; *attr; attr++) + kernfs_remove_by_name(parent, (*attr)->name); + if (grp->bin_attrs) + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) + kernfs_remove_by_name(parent, (*bin_attr)->attr.name); +} + +static umode_t __first_visible(const struct attribute_group *grp, struct kobject *kobj) +{ + if (grp->attrs && grp->attrs[0] && grp->is_visible) + return grp->is_visible(kobj, grp->attrs[0], 0); + + if (grp->attrs && grp->attrs[0] && grp->is_visible_const) + return grp->is_visible_const(kobj, grp->attrs[0], 0); + + if (grp->bin_attrs && grp->bin_attrs[0] && grp->is_bin_visible) + return grp->is_bin_visible(kobj, grp->bin_attrs[0], 0); - for (i = 0, attr = grp->attrs; *attr; i++, attr++) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); + return 0; } -static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, +static int create_files(struct kernfs_node *parent, struct kobject *kobj, + kuid_t uid, kgid_t gid, const struct attribute_group *grp, int update) { - struct attribute *const* attr; + struct attribute *const *attr; + const struct bin_attribute *const *bin_attr; int error = 0, i; - for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { - umode_t mode = 0; + if (grp->attrs) { + for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { + umode_t mode = (*attr)->mode; + + /* + * In update mode, we're changing the permissions or + * visibility. Do this by first removing then + * re-adding (if required) the file. + */ + if (update) + kernfs_remove_by_name(parent, (*attr)->name); + if (grp->is_visible || grp->is_visible_const) { + if (grp->is_visible) + mode = grp->is_visible(kobj, *attr, i); + else + mode = grp->is_visible_const(kobj, *attr, i); + mode &= ~SYSFS_GROUP_INVISIBLE; + if (!mode) + continue; + } + + WARN(mode & ~(SYSFS_PREALLOC | 0664), + "Attribute %s: Invalid permissions 0%o\n", + (*attr)->name, mode); + + mode &= SYSFS_PREALLOC | 0664; + error = sysfs_add_file_mode_ns(parent, *attr, mode, uid, + gid, NULL); + if (unlikely(error)) + break; + } + if (error) { + remove_files(parent, grp); + goto exit; + } + } - /* in update mode, we're changing the permissions or - * visibility. Do this by first removing then - * re-adding (if required) the file */ - if (update) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); - if (grp->is_visible) { - mode = grp->is_visible(kobj, *attr, i); - if (!mode) - continue; + if (grp->bin_attrs) { + for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { + umode_t mode = (*bin_attr)->attr.mode; + size_t size = (*bin_attr)->size; + + if (update) + kernfs_remove_by_name(parent, + (*bin_attr)->attr.name); + if (grp->is_bin_visible) { + mode = grp->is_bin_visible(kobj, *bin_attr, i); + mode &= ~SYSFS_GROUP_INVISIBLE; + if (!mode) + continue; + } + if (grp->bin_size) + size = grp->bin_size(kobj, *bin_attr, i); + + WARN(mode & ~(SYSFS_PREALLOC | 0664), + "Attribute %s: Invalid permissions 0%o\n", + (*bin_attr)->attr.name, mode); + + mode &= SYSFS_PREALLOC | 0664; + error = sysfs_add_bin_file_mode_ns(parent, *bin_attr, + mode, size, uid, gid, + NULL); + if (error) + break; } - error = sysfs_add_file_mode(dir_sd, *attr, SYSFS_KOBJ_ATTR, - (*attr)->mode | mode); - if (unlikely(error)) - break; + if (error) + remove_files(parent, grp); } - if (error) - remove_files(dir_sd, kobj, grp); +exit: return error; } @@ -59,32 +129,73 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { - struct sysfs_dirent *sd; + struct kernfs_node *kn; + kuid_t uid; + kgid_t gid; int error; - BUG_ON(!kobj || (!update && !kobj->sd)); + if (WARN_ON(!kobj || (!update && !kobj->sd))) + return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; - if (!grp->attrs) { - WARN(1, "sysfs: attrs not set by subsystem for group: %s/%s\n", - kobj->name, grp->name ? "" : grp->name); - return -EINVAL; + + if (!grp->attrs && !grp->bin_attrs) { + pr_debug("sysfs: (bin_)attrs not set by subsystem for group: %s/%s, skipping\n", + kobj->name, grp->name ?: ""); + return 0; } + + kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { - error = sysfs_create_subdir(kobj, grp->name, &sd); - if (error) - return error; - } else - sd = kobj->sd; - sysfs_get(sd); - error = create_files(sd, kobj, grp, update); + umode_t mode = __first_visible(grp, kobj); + + if (mode & SYSFS_GROUP_INVISIBLE) + mode = 0; + else + mode = S_IRWXU | S_IRUGO | S_IXUGO; + + if (update) { + kn = kernfs_find_and_get(kobj->sd, grp->name); + if (!kn) { + pr_debug("attr grp %s/%s not created yet\n", + kobj->name, grp->name); + /* may have been invisible prior to this update */ + update = 0; + } else if (!mode) { + sysfs_remove_group(kobj, grp); + kernfs_put(kn); + return 0; + } + } + + if (!update) { + if (!mode) + return 0; + kn = kernfs_create_dir_ns(kobj->sd, grp->name, mode, + uid, gid, kobj, NULL); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(kobj->sd, grp->name); + return PTR_ERR(kn); + } + } + } else { + kn = kobj->sd; + } + + kernfs_get(kn); + error = create_files(kn, kobj, uid, gid, grp, update); if (error) { if (grp->name) - sysfs_remove_subdir(sd); + kernfs_remove(kn); } - sysfs_put(sd); + kernfs_put(kn); + + if (grp->name && update) + kernfs_put(kn); + return error; } @@ -96,13 +207,72 @@ static int internal_create_group(struct kobject *kobj, int update, * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * - * Returns 0 on success or error. + * Returns 0 on success or error code on failure. */ int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 0, grp); } +EXPORT_SYMBOL_GPL(sysfs_create_group); + +static int internal_create_groups(struct kobject *kobj, int update, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = internal_create_group(kobj, update, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(kobj, groups[i]); + break; + } + } + return error; +} + +/** + * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups + * @kobj: The kobject to create the group on + * @groups: The attribute groups to create, NULL terminated + * + * This function creates a bunch of attribute groups. If an error occurs when + * creating a group, all previously created groups will be removed, unwinding + * everything back to the original state when this function was called. + * It will explicitly warn and error if any of the attribute files being + * created already exist. + * + * Returns 0 on success or error code from sysfs_create_group on failure. + */ +int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + return internal_create_groups(kobj, 0, groups); +} +EXPORT_SYMBOL_GPL(sysfs_create_groups); + +/** + * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups + * @kobj: The kobject to update the group on + * @groups: The attribute groups to update, NULL terminated + * + * This function update a bunch of attribute groups. If an error occurs when + * updating a group, all previously updated groups will be removed together + * with already existing (not updated) attributes. + * + * Returns 0 on success or error code from sysfs_update_group on failure. + */ +int sysfs_update_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + return internal_create_groups(kobj, 1, groups); +} +EXPORT_SYMBOL_GPL(sysfs_update_groups); /** * sysfs_update_group - given a directory kobject, update an attribute group @@ -114,93 +284,129 @@ int sysfs_create_group(struct kobject *kobj, * of the attribute files being created already exist. Furthermore, * if the visibility of the files has changed through the is_visible() * callback, it will update the permissions and add or remove the - * relevant files. + * relevant files. Changing a group's name (subdirectory name under + * kobj's directory in sysfs) is not allowed. * * The primary use for this function is to call it after making a change * that affects group visibility. * - * Returns 0 on success or error. + * Returns 0 on success or error code on failure. */ int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 1, grp); } +EXPORT_SYMBOL_GPL(sysfs_update_group); - - -void sysfs_remove_group(struct kobject * kobj, - const struct attribute_group * grp) +/** + * sysfs_remove_group: remove a group from a kobject + * @kobj: kobject to remove the group from + * @grp: group to remove + * + * This function removes a group of attributes from a kobject. The attributes + * previously have to have been created for this group, otherwise it will fail. + */ +void sysfs_remove_group(struct kobject *kobj, + const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd = kobj->sd; - struct sysfs_dirent *sd; + struct kernfs_node *parent = kobj->sd; + struct kernfs_node *kn; if (grp->name) { - sd = sysfs_get_dirent(dir_sd, NULL, grp->name); - if (!sd) { - WARN(!sd, KERN_WARNING "sysfs group %p not found for " - "kobject '%s'\n", grp, kobject_name(kobj)); + kn = kernfs_find_and_get(parent, grp->name); + if (!kn) { + pr_debug("sysfs group '%s' not found for kobject '%s'\n", + grp->name, kobject_name(kobj)); return; } - } else - sd = sysfs_get(dir_sd); + } else { + kn = parent; + kernfs_get(kn); + } - remove_files(sd, kobj, grp); + remove_files(kn, grp); if (grp->name) - sysfs_remove_subdir(sd); + kernfs_remove(kn); + + kernfs_put(kn); +} +EXPORT_SYMBOL_GPL(sysfs_remove_group); - sysfs_put(sd); +/** + * sysfs_remove_groups - remove a list of groups + * + * @kobj: The kobject for the groups to be removed from + * @groups: NULL terminated list of groups to be removed + * + * If groups is not NULL, remove the specified groups from the kobject. + */ +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + int i; + + if (!groups) + return; + for (i = 0; groups[i]; i++) + sysfs_remove_group(kobj, groups[i]); } +EXPORT_SYMBOL_GPL(sysfs_remove_groups); /** - * sysfs_merge_group - merge files into a pre-existing attribute group. + * sysfs_merge_group - merge files into a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to create and the attribute group they belong to. * - * This function returns an error if the group doesn't exist or any of the - * files already exist in that group, in which case none of the new files - * are created. + * This function returns an error if the group doesn't exist, the .name field is + * NULL or any of the files already exist in that group, in which case none of + * the new files are created. */ int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; + kuid_t uid; + kgid_t gid; int error = 0; struct attribute *const *attr; int i; - dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name); - if (!dir_sd) + parent = kernfs_find_and_get(kobj->sd, grp->name); + if (!parent) return -ENOENT; + kobject_get_ownership(kobj, &uid, &gid); + for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) - error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR); + error = sysfs_add_file_mode_ns(parent, *attr, (*attr)->mode, + uid, gid, NULL); if (error) { while (--i >= 0) - sysfs_hash_and_remove(dir_sd, NULL, (*--attr)->name); + kernfs_remove_by_name(parent, (*--attr)->name); } - sysfs_put(dir_sd); + kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_merge_group); /** - * sysfs_unmerge_group - remove files from a pre-existing attribute group. + * sysfs_unmerge_group - remove files from a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to remove and the attribute group they belong to. */ void sysfs_unmerge_group(struct kobject *kobj, const struct attribute_group *grp) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; struct attribute *const *attr; - dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name); - if (dir_sd) { + parent = kernfs_find_and_get(kobj->sd, grp->name); + if (parent) { for (attr = grp->attrs; *attr; ++attr) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); - sysfs_put(dir_sd); + kernfs_remove_by_name(parent, (*attr)->name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_unmerge_group); @@ -215,15 +421,15 @@ EXPORT_SYMBOL_GPL(sysfs_unmerge_group); int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; int error = 0; - dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name); - if (!dir_sd) + parent = kernfs_find_and_get(kobj->sd, group_name); + if (!parent) return -ENOENT; - error = sysfs_create_link_sd(dir_sd, target, link_name); - sysfs_put(dir_sd); + error = sysfs_create_link_sd(parent, target, link_name); + kernfs_put(parent); return error; } @@ -238,16 +444,192 @@ EXPORT_SYMBOL_GPL(sysfs_add_link_to_group); void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name) { - struct sysfs_dirent *dir_sd; + struct kernfs_node *parent; - dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name); - if (dir_sd) { - sysfs_hash_and_remove(dir_sd, NULL, link_name); - sysfs_put(dir_sd); + parent = kernfs_find_and_get(kobj->sd, group_name); + if (parent) { + kernfs_remove_by_name(parent, link_name); + kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); -EXPORT_SYMBOL_GPL(sysfs_create_group); -EXPORT_SYMBOL_GPL(sysfs_update_group); -EXPORT_SYMBOL_GPL(sysfs_remove_group); +/** + * compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing + * to a group or an attribute + * @kobj: The kobject containing the group. + * @target_kobj: The target kobject. + * @target_name: The name of the target group or attribute. + * @symlink_name: The name of the symlink file (target_name will be + * considered if symlink_name is NULL). + */ +int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, + struct kobject *target_kobj, + const char *target_name, + const char *symlink_name) +{ + struct kernfs_node *target; + struct kernfs_node *entry; + struct kernfs_node *link; + + /* + * We don't own @target_kobj and it may be removed at any time. + * Synchronize using sysfs_symlink_target_lock. See sysfs_remove_dir() + * for details. + */ + spin_lock(&sysfs_symlink_target_lock); + target = target_kobj->sd; + if (target) + kernfs_get(target); + spin_unlock(&sysfs_symlink_target_lock); + if (!target) + return -ENOENT; + + entry = kernfs_find_and_get(target, target_name); + if (!entry) { + kernfs_put(target); + return -ENOENT; + } + + if (!symlink_name) + symlink_name = target_name; + + link = kernfs_create_link(kobj->sd, symlink_name, entry); + if (PTR_ERR(link) == -EEXIST) + sysfs_warn_dup(kobj->sd, symlink_name); + + kernfs_put(entry); + kernfs_put(target); + return PTR_ERR_OR_ZERO(link); +} +EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); + +static int sysfs_group_attrs_change_owner(struct kobject *kobj, + struct kernfs_node *grp_kn, + const struct attribute_group *grp, + struct iattr *newattrs) +{ + struct kernfs_node *kn; + int error, i; + umode_t mode; + + if (grp->attrs) { + struct attribute *const *attr; + + for (i = 0, attr = grp->attrs; *attr; i++, attr++) { + if (grp->is_visible) { + mode = grp->is_visible(kobj, *attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } + kn = kernfs_find_and_get(grp_kn, (*attr)->name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + if (grp->bin_attrs) { + const struct bin_attribute *const *bin_attr; + + for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { + if (grp->is_bin_visible) { + mode = grp->is_bin_visible(kobj, *bin_attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } + kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + return 0; +} + +/** + * sysfs_group_change_owner - change owner of an attribute group. + * @kobj: The kobject containing the group. + * @grp: The attribute group. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *grp, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *grp_kn; + int error; + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (grp->name) { + grp_kn = kernfs_find_and_get(kobj->sd, grp->name); + } else { + kernfs_get(kobj->sd); + grp_kn = kobj->sd; + } + if (!grp_kn) + return -ENOENT; + + error = kernfs_setattr(grp_kn, &newattrs); + if (!error) + error = sysfs_group_attrs_change_owner(kobj, grp_kn, grp, &newattrs); + + kernfs_put(grp_kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_group_change_owner); + +/** + * sysfs_groups_change_owner - change owner of a set of attribute groups. + * @kobj: The kobject containing the groups. + * @groups: The attribute groups. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + int error = 0, i; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); + if (error) + break; + } + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c deleted file mode 100644 index 3e2837a633ed..000000000000 --- a/fs/sysfs/inode.c +++ /dev/null @@ -1,354 +0,0 @@ -/* - * fs/sysfs/inode.c - basic sysfs inode and dentry operations - * - * Copyright (c) 2001-3 Patrick Mochel - * Copyright (c) 2007 SUSE Linux Products GmbH - * Copyright (c) 2007 Tejun Heo <teheo@suse.de> - * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. - */ - -#undef DEBUG - -#include <linux/pagemap.h> -#include <linux/namei.h> -#include <linux/backing-dev.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/sysfs.h> -#include <linux/xattr.h> -#include <linux/security.h> -#include "sysfs.h" - -static const struct address_space_operations sysfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - -static struct backing_dev_info sysfs_backing_dev_info = { - .name = "sysfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - -static const struct inode_operations sysfs_inode_operations ={ - .permission = sysfs_permission, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .setxattr = sysfs_setxattr, -}; - -int __init sysfs_inode_init(void) -{ - return bdi_init(&sysfs_backing_dev_info); -} - -static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd) -{ - struct sysfs_inode_attrs *attrs; - struct iattr *iattrs; - - attrs = kzalloc(sizeof(struct sysfs_inode_attrs), GFP_KERNEL); - if (!attrs) - return NULL; - iattrs = &attrs->ia_iattr; - - /* assign default attributes */ - iattrs->ia_mode = sd->s_mode; - iattrs->ia_uid = GLOBAL_ROOT_UID; - iattrs->ia_gid = GLOBAL_ROOT_GID; - iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; - - return attrs; -} - -int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr * iattr) -{ - struct sysfs_inode_attrs *sd_attrs; - struct iattr *iattrs; - unsigned int ia_valid = iattr->ia_valid; - - sd_attrs = sd->s_iattr; - - if (!sd_attrs) { - /* setting attributes for the first time, allocate now */ - sd_attrs = sysfs_init_inode_attrs(sd); - if (!sd_attrs) - return -ENOMEM; - sd->s_iattr = sd_attrs; - } - /* attributes were changed at least once in past */ - iattrs = &sd_attrs->ia_iattr; - - if (ia_valid & ATTR_UID) - iattrs->ia_uid = iattr->ia_uid; - if (ia_valid & ATTR_GID) - iattrs->ia_gid = iattr->ia_gid; - if (ia_valid & ATTR_ATIME) - iattrs->ia_atime = iattr->ia_atime; - if (ia_valid & ATTR_MTIME) - iattrs->ia_mtime = iattr->ia_mtime; - if (ia_valid & ATTR_CTIME) - iattrs->ia_ctime = iattr->ia_ctime; - if (ia_valid & ATTR_MODE) { - umode_t mode = iattr->ia_mode; - iattrs->ia_mode = sd->s_mode = mode; - } - return 0; -} - -int sysfs_setattr(struct dentry *dentry, struct iattr *iattr) -{ - struct inode *inode = dentry->d_inode; - struct sysfs_dirent *sd = dentry->d_fsdata; - int error; - - if (!sd) - return -EINVAL; - - mutex_lock(&sysfs_mutex); - error = inode_change_ok(inode, iattr); - if (error) - goto out; - - error = sysfs_sd_setattr(sd, iattr); - if (error) - goto out; - - /* this ignores size changes */ - setattr_copy(inode, iattr); - -out: - mutex_unlock(&sysfs_mutex); - return error; -} - -static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, u32 *secdata_len) -{ - struct sysfs_inode_attrs *iattrs; - void *old_secdata; - size_t old_secdata_len; - - if (!sd->s_iattr) { - sd->s_iattr = sysfs_init_inode_attrs(sd); - if (!sd->s_iattr) - return -ENOMEM; - } - - iattrs = sd->s_iattr; - old_secdata = iattrs->ia_secdata; - old_secdata_len = iattrs->ia_secdata_len; - - iattrs->ia_secdata = *secdata; - iattrs->ia_secdata_len = *secdata_len; - - *secdata = old_secdata; - *secdata_len = old_secdata_len; - return 0; -} - -int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - void *secdata; - int error; - u32 secdata_len = 0; - - if (!sd) - return -EINVAL; - - if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { - const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - error = security_inode_setsecurity(dentry->d_inode, suffix, - value, size, flags); - if (error) - goto out; - error = security_inode_getsecctx(dentry->d_inode, - &secdata, &secdata_len); - if (error) - goto out; - - mutex_lock(&sysfs_mutex); - error = sysfs_sd_setsecdata(sd, &secdata, &secdata_len); - mutex_unlock(&sysfs_mutex); - - if (secdata) - security_release_secctx(secdata, secdata_len); - } else - return -EINVAL; -out: - return error; -} - -static inline void set_default_inode_attr(struct inode * inode, umode_t mode) -{ - inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; -} - -static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) -{ - inode->i_uid = iattr->ia_uid; - inode->i_gid = iattr->ia_gid; - inode->i_atime = iattr->ia_atime; - inode->i_mtime = iattr->ia_mtime; - inode->i_ctime = iattr->ia_ctime; -} - -static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode) -{ - struct sysfs_inode_attrs *iattrs = sd->s_iattr; - - inode->i_mode = sd->s_mode; - if (iattrs) { - /* sysfs_dirent has non-default attributes - * get them from persistent copy in sysfs_dirent - */ - set_inode_attr(inode, &iattrs->ia_iattr); - security_inode_notifysecctx(inode, - iattrs->ia_secdata, - iattrs->ia_secdata_len); - } - - if (sysfs_type(sd) == SYSFS_DIR) - set_nlink(inode, sd->s_dir.subdirs + 2); -} - -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - struct inode *inode = dentry->d_inode; - - mutex_lock(&sysfs_mutex); - sysfs_refresh_inode(sd, inode); - mutex_unlock(&sysfs_mutex); - - generic_fillattr(inode, stat); - return 0; -} - -static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) -{ - struct bin_attribute *bin_attr; - - inode->i_private = sysfs_get(sd); - inode->i_mapping->a_ops = &sysfs_aops; - inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; - inode->i_op = &sysfs_inode_operations; - - set_default_inode_attr(inode, sd->s_mode); - sysfs_refresh_inode(sd, inode); - - /* initialize inode according to type */ - switch (sysfs_type(sd)) { - case SYSFS_DIR: - inode->i_op = &sysfs_dir_inode_operations; - inode->i_fop = &sysfs_dir_operations; - break; - case SYSFS_KOBJ_ATTR: - inode->i_size = PAGE_SIZE; - inode->i_fop = &sysfs_file_operations; - break; - case SYSFS_KOBJ_BIN_ATTR: - bin_attr = sd->s_bin_attr.bin_attr; - inode->i_size = bin_attr->size; - inode->i_fop = &bin_fops; - break; - case SYSFS_KOBJ_LINK: - inode->i_op = &sysfs_symlink_inode_operations; - break; - default: - BUG(); - } - - unlock_new_inode(inode); -} - -/** - * sysfs_get_inode - get inode for sysfs_dirent - * @sb: super block - * @sd: sysfs_dirent to allocate inode for - * - * Get inode for @sd. 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). - * - * RETURNS: - * Pointer to allocated inode on success, NULL on failure. - */ -struct inode * sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd) -{ - struct inode *inode; - - inode = iget_locked(sb, sd->s_ino); - if (inode && (inode->i_state & I_NEW)) - sysfs_init_inode(sd, inode); - - return inode; -} - -/* - * The sysfs_dirent serves as both an inode and a directory entry for sysfs. - * To prevent the sysfs inode numbers from being freed prematurely we take a - * reference to sysfs_dirent from the sysfs inode. A - * super_operations.evict_inode() implementation is needed to drop that - * reference upon inode destruction. - */ -void sysfs_evict_inode(struct inode *inode) -{ - struct sysfs_dirent *sd = inode->i_private; - - truncate_inode_pages(&inode->i_data, 0); - clear_inode(inode); - sysfs_put(sd); -} - -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name) -{ - struct sysfs_addrm_cxt acxt; - struct sysfs_dirent *sd; - - if (!dir_sd) { - WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n", - name); - return -ENOENT; - } - - sysfs_addrm_start(&acxt, dir_sd); - - sd = sysfs_find_dirent(dir_sd, ns, name); - if (sd) - sysfs_remove_one(&acxt, sd); - - sysfs_addrm_finish(&acxt); - - if (sd) - return 0; - else - return -ENOENT; -} - -int sysfs_permission(struct inode *inode, int mask) -{ - struct sysfs_dirent *sd; - - if (mask & MAY_NOT_BLOCK) - return -ECHILD; - - sd = inode->i_private; - - mutex_lock(&sysfs_mutex); - sysfs_refresh_inode(sd, inode); - mutex_unlock(&sysfs_mutex); - - return generic_permission(inode, mask); -} diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index afd83273e6ce..98467bb76737 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - operations for initializing and mounting sysfs * @@ -5,201 +6,110 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ -#define DEBUG - #include <linux/fs.h> +#include <linux/magic.h> #include <linux/mount.h> -#include <linux/pagemap.h> #include <linux/init.h> -#include <linux/module.h> -#include <linux/magic.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/fs_context.h> +#include <net/net_namespace.h> #include "sysfs.h" +static struct kernfs_root *sysfs_root; +struct kernfs_node *sysfs_root_kn; -static struct vfsmount *sysfs_mnt; -struct kmem_cache *sysfs_dir_cachep; - -static const struct super_operations sysfs_ops = { - .statfs = simple_statfs, - .drop_inode = generic_delete_inode, - .evict_inode = sysfs_evict_inode, -}; - -struct sysfs_dirent sysfs_root = { - .s_name = "", - .s_count = ATOMIC_INIT(1), - .s_flags = SYSFS_DIR | (KOBJ_NS_TYPE_NONE << SYSFS_NS_TYPE_SHIFT), - .s_mode = S_IFDIR | S_IRUGO | S_IXUGO, - .s_ino = 1, -}; - -static int sysfs_fill_super(struct super_block *sb, void *data, int silent) +static int sysfs_get_tree(struct fs_context *fc) { - struct inode *inode; - struct dentry *root; - - sb->s_blocksize = PAGE_CACHE_SIZE; - sb->s_blocksize_bits = PAGE_CACHE_SHIFT; - sb->s_magic = SYSFS_MAGIC; - sb->s_op = &sysfs_ops; - sb->s_time_gran = 1; - - /* get root inode, initialize and unlock it */ - mutex_lock(&sysfs_mutex); - inode = sysfs_get_inode(sb, &sysfs_root); - mutex_unlock(&sysfs_mutex); - if (!inode) { - pr_debug("sysfs: could not get root inode\n"); - return -ENOMEM; - } + struct kernfs_fs_context *kfc = fc->fs_private; + int ret; - /* instantiate and link root dentry */ - root = d_make_root(inode); - if (!root) { - pr_debug("%s: could not get root dentry!\n",__func__); - return -ENOMEM; - } - root->d_fsdata = &sysfs_root; - sb->s_root = root; - sb->s_d_op = &sysfs_dentry_ops; + ret = kernfs_get_tree(fc); + if (ret) + return ret; + + if (kfc->new_sb_created) + fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE; return 0; } -static int sysfs_test_super(struct super_block *sb, void *data) +static void sysfs_fs_context_free(struct fs_context *fc) { - struct sysfs_super_info *sb_info = sysfs_info(sb); - struct sysfs_super_info *info = data; - enum kobj_ns_type type; - int found = 1; - - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) { - if (sb_info->ns[type] != info->ns[type]) - found = 0; - } - return found; -} + struct kernfs_fs_context *kfc = fc->fs_private; -static int sysfs_set_super(struct super_block *sb, void *data) -{ - int error; - error = set_anon_super(sb, data); - if (!error) - sb->s_fs_info = data; - return error; + if (kfc->ns_tag) + kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag); + kernfs_free_fs_context(fc); + kfree(kfc); } -static void free_sysfs_super_info(struct sysfs_super_info *info) -{ - int type; - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) - kobj_ns_drop(type, info->ns[type]); - kfree(info); -} +static const struct fs_context_operations sysfs_fs_context_ops = { + .free = sysfs_fs_context_free, + .get_tree = sysfs_get_tree, +}; -static struct dentry *sysfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int sysfs_init_fs_context(struct fs_context *fc) { - struct sysfs_super_info *info; - enum kobj_ns_type type; - struct super_block *sb; - int error; - - if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs) - return ERR_PTR(-EPERM); - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return ERR_PTR(-ENOMEM); - - for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) - info->ns[type] = kobj_ns_grab_current(type); - - sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info); - if (IS_ERR(sb) || sb->s_fs_info != info) - free_sysfs_super_info(info); - if (IS_ERR(sb)) - return ERR_CAST(sb); - if (!sb->s_root) { - error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(sb); - return ERR_PTR(error); - } - sb->s_flags |= MS_ACTIVE; + struct kernfs_fs_context *kfc; + struct net *netns; + + if (!(fc->sb_flags & SB_KERNMOUNT)) { + if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) + return -EPERM; } - return dget(sb->s_root); + kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL); + if (!kfc) + return -ENOMEM; + + kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); + kfc->root = sysfs_root; + kfc->magic = SYSFS_MAGIC; + fc->fs_private = kfc; + fc->ops = &sysfs_fs_context_ops; + if (netns) { + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(netns->user_ns); + } + fc->global = true; + return 0; } static void sysfs_kill_sb(struct super_block *sb) { - struct sysfs_super_info *info = sysfs_info(sb); - /* Remove the superblock from fs_supers/s_instances - * so we can't find it, before freeing sysfs_super_info. - */ - kill_anon_super(sb); - free_sysfs_super_info(info); + void *ns = (void *)kernfs_super_ns(sb); + + kernfs_kill_sb(sb); + kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); } static struct file_system_type sysfs_fs_type = { - .name = "sysfs", - .mount = sysfs_mount, - .kill_sb = sysfs_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .name = "sysfs", + .init_fs_context = sysfs_init_fs_context, + .kill_sb = sysfs_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; int __init sysfs_init(void) { - int err = -ENOMEM; + int err; - sysfs_dir_cachep = kmem_cache_create("sysfs_dir_cache", - sizeof(struct sysfs_dirent), - 0, 0, NULL); - if (!sysfs_dir_cachep) - goto out; + sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, + NULL); + if (IS_ERR(sysfs_root)) + return PTR_ERR(sysfs_root); - err = sysfs_inode_init(); - if (err) - goto out_err; + sysfs_root_kn = kernfs_root_to_node(sysfs_root); err = register_filesystem(&sysfs_fs_type); - if (!err) { - sysfs_mnt = kern_mount(&sysfs_fs_type); - if (IS_ERR(sysfs_mnt)) { - printk(KERN_ERR "sysfs: could not mount!\n"); - err = PTR_ERR(sysfs_mnt); - sysfs_mnt = NULL; - unregister_filesystem(&sysfs_fs_type); - goto out_err; - } - } else - goto out_err; -out: - return err; -out_err: - kmem_cache_destroy(sysfs_dir_cachep); - sysfs_dir_cachep = NULL; - goto out; -} - -#undef sysfs_get -struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd) -{ - return __sysfs_get(sd); -} -EXPORT_SYMBOL_GPL(sysfs_get); + if (err) { + kernfs_destroy_root(sysfs_root); + return err; + } -#undef sysfs_put -void sysfs_put(struct sysfs_dirent *sd) -{ - __sysfs_put(sd); + return 0; } -EXPORT_SYMBOL_GPL(sysfs_put); diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 8c940df97a52..5603530a1a52 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - sysfs symlink implementation * @@ -5,113 +6,78 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * - * This file is released under the GPLv2. - * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/fs.h> -#include <linux/gfp.h> -#include <linux/mount.h> #include <linux/module.h> #include <linux/kobject.h> -#include <linux/namei.h> #include <linux/mutex.h> #include <linux/security.h> #include "sysfs.h" -static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd, - struct kobject *target, +static int sysfs_do_create_link_sd(struct kernfs_node *parent, + struct kobject *target_kobj, const char *name, int warn) { - struct sysfs_dirent *target_sd = NULL; - struct sysfs_dirent *sd = NULL; - struct sysfs_addrm_cxt acxt; - enum kobj_ns_type ns_type; - int error; + struct kernfs_node *kn, *target = NULL; - BUG_ON(!name || !parent_sd); + if (WARN_ON(!name || !parent)) + return -EINVAL; - /* target->sd can go away beneath us but is protected with - * sysfs_assoc_lock. Fetch target_sd from it. + /* + * We don't own @target_kobj and it may be removed at any time. + * Synchronize using sysfs_symlink_target_lock. See + * sysfs_remove_dir() for details. */ - spin_lock(&sysfs_assoc_lock); - if (target->sd) - target_sd = sysfs_get(target->sd); - spin_unlock(&sysfs_assoc_lock); - - error = -ENOENT; - if (!target_sd) - goto out_put; - - error = -ENOMEM; - sd = sysfs_new_dirent(name, S_IFLNK|S_IRWXUGO, SYSFS_KOBJ_LINK); - if (!sd) - goto out_put; - - ns_type = sysfs_ns_type(parent_sd); - if (ns_type) - sd->s_ns = target->ktype->namespace(target); - sd->s_symlink.target_sd = target_sd; - target_sd = NULL; /* reference is now owned by the symlink */ - - sysfs_addrm_start(&acxt, parent_sd); - /* Symlinks must be between directories with the same ns_type */ - if (!ns_type || - (ns_type == sysfs_ns_type(sd->s_symlink.target_sd->s_parent))) { - if (warn) - error = sysfs_add_one(&acxt, sd); - else - error = __sysfs_add_one(&acxt, sd); - } else { - error = -EINVAL; - WARN(1, KERN_WARNING - "sysfs: symlink across ns_types %s/%s -> %s/%s\n", - parent_sd->s_name, - sd->s_name, - sd->s_symlink.target_sd->s_parent->s_name, - sd->s_symlink.target_sd->s_name); + spin_lock(&sysfs_symlink_target_lock); + if (target_kobj->sd) { + target = target_kobj->sd; + kernfs_get(target); } - sysfs_addrm_finish(&acxt); + spin_unlock(&sysfs_symlink_target_lock); - if (error) - goto out_put; + if (!target) + return -ENOENT; - return 0; + kn = kernfs_create_link(parent, name, target); + kernfs_put(target); - out_put: - sysfs_put(target_sd); - sysfs_put(sd); - return error; + if (!IS_ERR(kn)) + return 0; + + if (warn && PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, name); + return PTR_ERR(kn); } /** * sysfs_create_link_sd - create symlink to a given object. - * @sd: directory we're creating the link in. + * @kn: directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ -int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target, +int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name) { - return sysfs_do_create_link_sd(sd, target, name, 1); + return sysfs_do_create_link_sd(kn, target, name, 1); } static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target, const char *name, int warn) { - struct sysfs_dirent *parent_sd = NULL; + struct kernfs_node *parent = NULL; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; - if (!parent_sd) + if (!parent) return -EFAULT; - return sysfs_do_create_link_sd(parent_sd, target, name, warn); + return sysfs_do_create_link_sd(parent, target, name, warn); } /** @@ -125,6 +91,7 @@ int sysfs_create_link(struct kobject *kobj, struct kobject *target, { return sysfs_do_create_link(kobj, target, name, 1); } +EXPORT_SYMBOL_GPL(sysfs_create_link); /** * sysfs_create_link_nowarn - create symlink between two objects. @@ -140,6 +107,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target, { return sysfs_do_create_link(kobj, target, name, 0); } +EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); /** * sysfs_delete_link - remove symlink in object's directory. @@ -154,11 +122,17 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, const char *name) { const void *ns = NULL; - spin_lock(&sysfs_assoc_lock); - if (targ->sd && sysfs_ns_type(kobj->sd)) - ns = targ->sd->s_ns; - spin_unlock(&sysfs_assoc_lock); - sysfs_hash_and_remove(kobj->sd, ns, name); + + /* + * We don't own @target and it may be removed at any time. + * Synchronize using sysfs_symlink_target_lock. See + * sysfs_remove_dir() for details. + */ + spin_lock(&sysfs_symlink_target_lock); + if (targ->sd && kernfs_ns_enabled(kobj->sd)) + ns = targ->sd->ns; + spin_unlock(&sysfs_symlink_target_lock); + kernfs_remove_by_name_ns(kobj->sd, name, ns); } /** @@ -166,161 +140,59 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, * @kobj: object we're acting for. * @name: name of the symlink to remove. */ - -void sysfs_remove_link(struct kobject * kobj, const char * name) +void sysfs_remove_link(struct kobject *kobj, const char *name) { - struct sysfs_dirent *parent_sd = NULL; + struct kernfs_node *parent = NULL; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; - sysfs_hash_and_remove(parent_sd, NULL, name); + kernfs_remove_by_name(parent, name); } +EXPORT_SYMBOL_GPL(sysfs_remove_link); /** - * sysfs_rename_link - rename symlink in object's directory. + * sysfs_rename_link_ns - rename symlink in object's directory. * @kobj: object we're acting for. * @targ: object we're pointing to. * @old: previous name of the symlink. * @new: new name of the symlink. + * @new_ns: new namespace of the symlink. * * A helper function for the common rename symlink idiom. */ -int sysfs_rename_link(struct kobject *kobj, struct kobject *targ, - const char *old, const char *new) +int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ, + const char *old, const char *new, const void *new_ns) { - struct sysfs_dirent *parent_sd, *sd = NULL; - const void *old_ns = NULL, *new_ns = NULL; + struct kernfs_node *parent, *kn = NULL; + const void *old_ns = NULL; int result; if (!kobj) - parent_sd = &sysfs_root; + parent = sysfs_root_kn; else - parent_sd = kobj->sd; + parent = kobj->sd; if (targ->sd) - old_ns = targ->sd->s_ns; + old_ns = targ->sd->ns; result = -ENOENT; - sd = sysfs_get_dirent(parent_sd, old_ns, old); - if (!sd) + kn = kernfs_find_and_get_ns(parent, old, old_ns); + if (!kn) goto out; result = -EINVAL; - if (sysfs_type(sd) != SYSFS_KOBJ_LINK) + if (kernfs_type(kn) != KERNFS_LINK) goto out; - if (sd->s_symlink.target_sd->s_dir.kobj != targ) + if (kn->symlink.target_kn->priv != targ) goto out; - if (sysfs_ns_type(parent_sd)) - new_ns = targ->ktype->namespace(targ); - - result = sysfs_rename(sd, parent_sd, new_ns, new); + result = kernfs_rename_ns(kn, parent, new, new_ns); out: - sysfs_put(sd); + kernfs_put(kn); return result; } - -static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, - struct sysfs_dirent *target_sd, char *path) -{ - struct sysfs_dirent *base, *sd; - char *s = path; - int len = 0; - - /* go up to the root, stop at the base */ - base = parent_sd; - while (base->s_parent) { - sd = target_sd->s_parent; - while (sd->s_parent && base != sd) - sd = sd->s_parent; - - if (base == sd) - break; - - strcpy(s, "../"); - s += 3; - base = base->s_parent; - } - - /* determine end of target string for reverse fillup */ - sd = target_sd; - while (sd->s_parent && sd != base) { - len += strlen(sd->s_name) + 1; - sd = sd->s_parent; - } - - /* 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 */ - sd = target_sd; - while (sd->s_parent && sd != base) { - int slen = strlen(sd->s_name); - - len -= slen; - strncpy(s + len, sd->s_name, slen); - if (len) - s[--len] = '/'; - - sd = sd->s_parent; - } - - return 0; -} - -static int sysfs_getlink(struct dentry *dentry, char * path) -{ - struct sysfs_dirent *sd = dentry->d_fsdata; - struct sysfs_dirent *parent_sd = sd->s_parent; - struct sysfs_dirent *target_sd = sd->s_symlink.target_sd; - int error; - - mutex_lock(&sysfs_mutex); - error = sysfs_get_target_path(parent_sd, target_sd, path); - mutex_unlock(&sysfs_mutex); - - return error; -} - -static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - int error = -ENOMEM; - unsigned long page = get_zeroed_page(GFP_KERNEL); - if (page) { - error = sysfs_getlink(dentry, (char *) page); - if (error < 0) - free_page((unsigned long)page); - } - nd_set_link(nd, error ? ERR_PTR(error) : (char *)page); - return NULL; -} - -static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) -{ - char *page = nd_get_link(nd); - if (!IS_ERR(page)) - free_page((unsigned long)page); -} - -const struct inode_operations sysfs_symlink_inode_operations = { - .setxattr = sysfs_setxattr, - .readlink = generic_readlink, - .follow_link = sysfs_follow_link, - .put_link = sysfs_put_link, - .setattr = sysfs_setattr, - .getattr = sysfs_getattr, - .permission = sysfs_permission, -}; - - -EXPORT_SYMBOL_GPL(sysfs_create_link); -EXPORT_SYMBOL_GPL(sysfs_remove_link); -EXPORT_SYMBOL_GPL(sysfs_rename_link); +EXPORT_SYMBOL_GPL(sysfs_rename_link_ns); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index d1e4043eb0c3..8e012f25e1c0 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -1,244 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * fs/sysfs/sysfs.h - sysfs internal header file * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> - * - * This file is released under the GPLv2. */ -#include <linux/lockdep.h> -#include <linux/kobject_ns.h> -#include <linux/fs.h> -#include <linux/rbtree.h> - -struct sysfs_open_dirent; - -/* type-specific structures for sysfs_dirent->s_* union members */ -struct sysfs_elem_dir { - struct kobject *kobj; - - unsigned long subdirs; - /* children rbtree starts here and goes through sd->s_rb */ - struct rb_root children; -}; - -struct sysfs_elem_symlink { - struct sysfs_dirent *target_sd; -}; - -struct sysfs_elem_attr { - struct attribute *attr; - struct sysfs_open_dirent *open; -}; +#ifndef __SYSFS_INTERNAL_H +#define __SYSFS_INTERNAL_H -struct sysfs_elem_bin_attr { - struct bin_attribute *bin_attr; - struct hlist_head buffers; -}; - -struct sysfs_inode_attrs { - struct iattr ia_iattr; - void *ia_secdata; - u32 ia_secdata_len; -}; - -/* - * sysfs_dirent - the building block of sysfs hierarchy. Each and - * every sysfs node is represented by single sysfs_dirent. - * - * As long as s_count reference is held, the sysfs_dirent itself is - * accessible. Dereferencing s_elem or any other outer entity - * requires s_active reference. - */ -struct sysfs_dirent { - atomic_t s_count; - atomic_t s_active; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif - struct sysfs_dirent *s_parent; - const char *s_name; - - struct rb_node s_rb; - - union { - struct completion *completion; - struct sysfs_dirent *removed_list; - } u; - - const void *s_ns; /* namespace tag */ - unsigned int s_hash; /* ns + name hash */ - union { - struct sysfs_elem_dir s_dir; - struct sysfs_elem_symlink s_symlink; - struct sysfs_elem_attr s_attr; - struct sysfs_elem_bin_attr s_bin_attr; - }; - - unsigned short s_flags; - umode_t s_mode; - unsigned int s_ino; - struct sysfs_inode_attrs *s_iattr; -}; - -#define SD_DEACTIVATED_BIAS INT_MIN - -#define SYSFS_TYPE_MASK 0x00ff -#define SYSFS_DIR 0x0001 -#define SYSFS_KOBJ_ATTR 0x0002 -#define SYSFS_KOBJ_BIN_ATTR 0x0004 -#define SYSFS_KOBJ_LINK 0x0008 -#define SYSFS_COPY_NAME (SYSFS_DIR | SYSFS_KOBJ_LINK) -#define SYSFS_ACTIVE_REF (SYSFS_KOBJ_ATTR | SYSFS_KOBJ_BIN_ATTR) - -/* identify any namespace tag on sysfs_dirents */ -#define SYSFS_NS_TYPE_MASK 0xf00 -#define SYSFS_NS_TYPE_SHIFT 8 - -#define SYSFS_FLAG_MASK ~(SYSFS_NS_TYPE_MASK|SYSFS_TYPE_MASK) -#define SYSFS_FLAG_REMOVED 0x02000 - -static inline unsigned int sysfs_type(struct sysfs_dirent *sd) -{ - return sd->s_flags & SYSFS_TYPE_MASK; -} - -/* - * Return any namespace tags on this dirent. - * enum kobj_ns_type is defined in linux/kobject.h - */ -static inline enum kobj_ns_type sysfs_ns_type(struct sysfs_dirent *sd) -{ - return (sd->s_flags & SYSFS_NS_TYPE_MASK) >> SYSFS_NS_TYPE_SHIFT; -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -#define sysfs_dirent_init_lockdep(sd) \ -do { \ - struct attribute *attr = sd->s_attr.attr; \ - struct lock_class_key *key = attr->key; \ - if (!key) \ - key = &attr->skey; \ - \ - lockdep_init_map(&sd->dep_map, "s_active", key, 0); \ -} while(0) -#else -#define sysfs_dirent_init_lockdep(sd) do {} while(0) -#endif - -/* - * Context structure to be used while adding/removing nodes. - */ -struct sysfs_addrm_cxt { - struct sysfs_dirent *parent_sd; - struct sysfs_dirent *removed; -}; +#include <linux/sysfs.h> /* * mount.c */ - -/* - * Each sb is associated with a set of namespace tags (i.e. - * the network namespace of the task which mounted this sysfs - * instance). - */ -struct sysfs_super_info { - void *ns[KOBJ_NS_TYPES]; -}; -#define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info)) -extern struct sysfs_dirent sysfs_root; -extern struct kmem_cache *sysfs_dir_cachep; +extern struct kernfs_node *sysfs_root_kn; /* * dir.c */ -extern struct mutex sysfs_mutex; -extern spinlock_t sysfs_assoc_lock; -extern const struct dentry_operations sysfs_dentry_ops; - -extern const struct file_operations sysfs_dir_operations; -extern const struct inode_operations sysfs_dir_inode_operations; - -struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd); -struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd); -void sysfs_put_active(struct sysfs_dirent *sd); -void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt, - struct sysfs_dirent *parent_sd); -int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd); -int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd); -void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd); -void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt); - -struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, - const void *ns, - const unsigned char *name); -struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, - const void *ns, - const unsigned char *name); -struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type); - -void release_sysfs_dirent(struct sysfs_dirent *sd); +extern spinlock_t sysfs_symlink_target_lock; -int sysfs_create_subdir(struct kobject *kobj, const char *name, - struct sysfs_dirent **p_sd); -void sysfs_remove_subdir(struct sysfs_dirent *sd); - -int sysfs_rename(struct sysfs_dirent *sd, - struct sysfs_dirent *new_parent_sd, const void *ns, const char *new_name); - -static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd) -{ - if (sd) { - WARN_ON(!atomic_read(&sd->s_count)); - atomic_inc(&sd->s_count); - } - return sd; -} -#define sysfs_get(sd) __sysfs_get(sd) - -static inline void __sysfs_put(struct sysfs_dirent *sd) -{ - if (sd && atomic_dec_and_test(&sd->s_count)) - release_sysfs_dirent(sd); -} -#define sysfs_put(sd) __sysfs_put(sd) - -/* - * inode.c - */ -struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd); -void sysfs_evict_inode(struct inode *inode); -int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr); -int sysfs_permission(struct inode *inode, int mask); -int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); -int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); -int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags); -int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name); -int sysfs_inode_init(void); +void sysfs_warn_dup(struct kernfs_node *parent, const char *name); /* * file.c */ -extern const struct file_operations sysfs_file_operations; - -int sysfs_add_file(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type); - -int sysfs_add_file_mode(struct sysfs_dirent *dir_sd, - const struct attribute *attr, int type, umode_t amode); -/* - * bin.c - */ -extern const struct file_operations bin_fops; -void unmap_bin_file(struct sysfs_dirent *attr_sd); +int sysfs_add_file_mode_ns(struct kernfs_node *parent, + const struct attribute *attr, umode_t amode, kuid_t uid, + kgid_t gid, const void *ns); +int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, + const struct bin_attribute *battr, umode_t mode, size_t size, + kuid_t uid, kgid_t gid, const void *ns); /* * symlink.c */ -extern const struct inode_operations sysfs_symlink_inode_operations; -int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target, +int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name); + +#endif /* __SYSFS_INTERNAL_H */ |