static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
{
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent **pos;
if (!dir_sd)
return;
pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
sysfs_addrm_start(&acxt, dir_sd);
pos = &dir_sd->s_children;
while (*pos) {
struct sysfs_dirent *sd = *pos;
if (sysfs_type(sd) && sysfs_type(sd) != SYSFS_DIR) {
*pos = sd->s_sibling;
sd->s_sibling = NULL;
sysfs_remove_one(&acxt, sd);
} else
pos = &(*pos)->s_sibling;
}
sysfs_addrm_finish(&acxt);
remove_dir(dir_sd);
}
void release_sysfs_dirent(struct sysfs_dirent *sd)
{
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;
WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED),
"sysfs: free using entry: %s/%s\n",
parent_sd ? parent_sd->s_name : "", sd->s_name);
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;
}
/**
* sysfs_remove_dir - remove an object's directory.
* @kobj: object.
*
* The only thing special about this is that we remove any files in
* 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)
{
struct sysfs_dirent *sd = kobj->sd;
/*
* In general, kboject 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 sd.
*
* 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_symlink_target_lock);
if (sd) {
WARN_ON_ONCE(sysfs_type(sd) != SYSFS_DIR);
sysfs_remove(sd);
}
}
/**
* 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;
}
int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name)
{
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent **pos, *sd;
if (!dir_sd)
return -ENOENT;
sysfs_addrm_start(&acxt, dir_sd);
for (pos = &dir_sd->s_children; *pos; pos = &(*pos)->s_sibling) {
sd = *pos;
if (!sysfs_type(sd))
continue;
if (!strcmp(sd->s_name, name)) {
*pos = sd->s_sibling;
sd->s_sibling = NULL;
sysfs_remove_one(&acxt, sd);
break;
}
}
if (sysfs_addrm_finish(&acxt))
return 0;
return -ENOENT;
}
/**
* 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_);
}
/**
* 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);
}
/**
* 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. @sd is NOT
* linked into the children list of the parent. The caller
* should invoke sysfs_link_sibling() after this function
* completes if @sd needs to be on 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_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
sd->s_parent = sysfs_get(acxt->parent_sd);
if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
inc_nlink(acxt->parent_inode);
acxt->cnt++;
}
/**
* 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 unsigned char *name)
{
struct sysfs_dirent *sd;
for (sd = parent_sd->s_children; sd; sd = sd->s_sibling)
if (sysfs_type(sd) && !strcmp(sd->s_name, name))
return sd;
return NULL;
}
static int sysfs_count_nlink(struct sysfs_dirent *sd)
{
struct sysfs_dirent *child;
int nr = 0;
for (child = sd->s_children; child; child = child->s_sibling)
if (sysfs_type(child) == SYSFS_DIR)
nr++;
return nr + 2;
}
/**
* sysfs_remove_one - remove sysfs_dirent from parent
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
*
* Mark @sd removed and drop nlink of parent inode if @sd is a
* directory. @sd is NOT unlinked from the children list of the
* parent. The caller is repsonsible for removing @sd from the
* children list before calling this function.
*
* 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)
{
BUG_ON(sd->s_sibling || (sd->s_flags & SYSFS_FLAG_REMOVED));
sd->s_flags |= SYSFS_FLAG_REMOVED;
sd->s_sibling = acxt->removed;
acxt->removed = sd;
if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
drop_nlink(acxt->parent_inode);
acxt->cnt++;
}
void release_sysfs_dirent(struct sysfs_dirent * sd)
{
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;
if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
sysfs_put(sd->s_elem.symlink.target_sd);
if (sysfs_type(sd) & SYSFS_COPY_NAME)
kfree(sd->s_name);
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;
}
static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
{
struct bin_attribute *bin_attr;
struct sysfs_inode_attrs *iattrs;
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;
inode->i_ino = sd->s_ino;
lockdep_set_class(&inode->i_mutex, &sysfs_inode_imutex_key);
iattrs = sd->s_iattr;
if (iattrs) {
/* sysfs_dirent has non-default attributes
* get them for the new inode from persistent copy
* in sysfs_dirent
*/
set_inode_attr(inode, &iattrs->ia_iattr);
if (iattrs->ia_secdata)
security_inode_notifysecctx(inode,
iattrs->ia_secdata,
iattrs->ia_secdata_len);
} else
set_default_inode_attr(inode, sd->s_mode);
/* 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;
inode->i_nlink = sysfs_count_nlink(sd);
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);
}
static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
int is_dir;
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;
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_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)
inode->i_nlink = sysfs_count_nlink(sd);
}
static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin)
{
struct dentry * dentry = file->f_path.dentry;
switch (origin) {
case 1:
offset += file->f_pos;
case 0:
if (offset >= 0)
break;
default:
return -EINVAL;
}
if (offset != file->f_pos) {
mutex_lock(&sysfs_mutex);
file->f_pos = offset;
if (file->f_pos >= 2) {
struct sysfs_dirent *sd = dentry->d_fsdata;
struct sysfs_dirent *cursor = file->private_data;
struct sysfs_dirent **pos;
loff_t n = file->f_pos - 2;
sysfs_unlink_sibling(cursor);
pos = &sd->s_children;
while (n && *pos) {
struct sysfs_dirent *next = *pos;
if (sysfs_type(next))
n--;
pos = &(*pos)->s_sibling;
}
cursor->s_sibling = *pos;
*pos = cursor;
}
mutex_unlock(&sysfs_mutex);
}
return offset;
}
/**
* sysfs_drop_dentry - drop dentry for the specified sysfs_dirent
* @sd: target sysfs_dirent
*
* Drop dentry for @sd. @sd must have been unlinked from its
* parent on entry to this function such that it can't be looked
* up anymore.
*
* @sd->s_dentry which is protected with sysfs_assoc_lock points
* to the currently associated dentry but we're not holding a
* reference to it and racing with dput(). Grab dcache_lock and
* verify dentry before dropping it. If @sd->s_dentry is NULL or
* dput() beats us, no need to bother.
*/
static void sysfs_drop_dentry(struct sysfs_dirent *sd)
{
struct dentry *dentry = NULL;
struct inode *inode;
/* We're not holding a reference to ->s_dentry dentry but the
* field will stay valid as long as sysfs_assoc_lock is held.
*/
spin_lock(&sysfs_assoc_lock);
spin_lock(&dcache_lock);
/* drop dentry if it's there and dput() didn't kill it yet */
if (sd->s_dentry && sd->s_dentry->d_inode) {
dentry = dget_locked(sd->s_dentry);
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
}
spin_unlock(&dcache_lock);
spin_unlock(&sysfs_assoc_lock);
/* dentries for shadowed inodes are pinned, unpin */
if (dentry && sysfs_is_shadowed_inode(dentry->d_inode))
dput(dentry);
dput(dentry);
/* adjust nlink and update timestamp */
inode = ilookup(sysfs_sb, sd->s_ino);
if (inode) {
mutex_lock(&inode->i_mutex);
inode->i_ctime = CURRENT_TIME;
drop_nlink(inode);
if (sysfs_type(sd) == SYSFS_DIR)
drop_nlink(inode);
mutex_unlock(&inode->i_mutex);
iput(inode);
}
}
static struct sysfs_dirent *sysfs_leftmost_descendant(struct sysfs_dirent *pos)
{
struct sysfs_dirent *last;
while (true) {
struct rb_node *rbn;
last = pos;
if (sysfs_type(pos) != SYSFS_DIR)
break;
rbn = rb_first(&pos->s_dir.children);
if (!rbn)
break;
pos = to_sysfs_dirent(rbn);
}
return last;
}
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);
}
static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
struct dentry *dentry = filp->f_path.dentry;
struct sysfs_dirent * parent_sd = dentry->d_fsdata;
struct sysfs_dirent *cursor = filp->private_data;
struct sysfs_dirent **pos;
ino_t ino;
int i = filp->f_pos;
switch (i) {
case 0:
ino = parent_sd->s_ino;
if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
break;
filp->f_pos++;
i++;
/* fallthrough */
case 1:
if (parent_sd->s_parent)
ino = parent_sd->s_parent->s_ino;
else
ino = parent_sd->s_ino;
if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
break;
filp->f_pos++;
i++;
/* fallthrough */
default:
mutex_lock(&sysfs_mutex);
pos = &parent_sd->s_children;
while (*pos != cursor)
pos = &(*pos)->s_sibling;
/* unlink cursor */
*pos = cursor->s_sibling;
if (filp->f_pos == 2)
pos = &parent_sd->s_children;
for ( ; *pos; pos = &(*pos)->s_sibling) {
struct sysfs_dirent *next = *pos;
const char * name;
int len;
if (!sysfs_type(next))
continue;
name = next->s_name;
len = strlen(name);
ino = next->s_ino;
if (filldir(dirent, name, len, filp->f_pos, ino,
dt_type(next)) < 0)
break;
filp->f_pos++;
}
/* put cursor back in */
cursor->s_sibling = *pos;
*pos = cursor;
mutex_unlock(&sysfs_mutex);
}
return 0;
}
static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct dentry *ret = NULL;
struct sysfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
struct sysfs_dirent * sd;
struct bin_attribute *bin_attr;
struct inode *inode;
int found = 0;
mutex_lock(&sysfs_mutex);
for (sd = parent_sd->s_children; sd; sd = sd->s_sibling) {
if (sysfs_type(sd) &&
!strcmp(sd->s_name, dentry->d_name.name)) {
found = 1;
break;
}
}
/* no such entry */
if (!found)
goto out_unlock;
/* attach dentry and inode */
inode = sysfs_get_inode(sd);
if (!inode) {
ret = ERR_PTR(-ENOMEM);
goto out_unlock;
}
if (inode->i_state & I_NEW) {
/* 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;
inode->i_nlink = sysfs_count_nlink(sd);
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_elem.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();
}
}
sysfs_instantiate(dentry, inode);
sysfs_attach_dentry(sd, dentry);
out_unlock:
mutex_unlock(&sysfs_mutex);
return ret;
}
static bool sysfs_is_bin(struct sysfs_dirent *sd)
{
return sysfs_type(sd) == SYSFS_KOBJ_BIN_ATTR;
}
