![Louis Rilling](/assets/img/avatar_default.png)
When attaching default groups (subdirs) of a new group (in mkdir() or in configfs_register()), configfs recursively takes inode's mutexes along the path from the parent of the new group to the default subdirs. This is needed to ensure that the VFS will not race with operations on these sub-dirs. This is safe for the following reasons: - the VFS allows one to lock first an inode and second one of its children (The lock subclasses for this pattern are respectively I_MUTEX_PARENT and I_MUTEX_CHILD); - from this rule any inode path can be recursively locked in descending order as long as it stays under a single mountpoint and does not follow symlinks. Unfortunately lockdep does not know (yet?) how to handle such recursion. I've tried to use Peter Zijlstra's lock_set_subclass() helper to upgrade i_mutexes from I_MUTEX_CHILD to I_MUTEX_PARENT when we know that we might recursively lock some of their descendant, but this usage does not seem to fit the purpose of lock_set_subclass() because it leads to several i_mutex locked with subclass I_MUTEX_PARENT by the same task. >From inside configfs it is not possible to serialize those recursive locking with a top-level one, because mkdir() and rmdir() are already called with inodes locked by the VFS. So using some mutex_lock_nest_lock() is not an option. I am proposing two solutions: 1) one that wraps recursive mutex_lock()s with lockdep_off()/lockdep_on(). 2) (as suggested earlier by Peter Zijlstra) one that puts the i_mutexes recursively locked in different classes based on their depth from the top-level config_group created. This induces an arbitrary limit (MAX_LOCK_DEPTH - 2 == 46) on the nesting of configfs default groups whenever lockdep is activated but this limit looks reasonably high. Unfortunately, this also isolates VFS operations on configfs default groups from the others and thus lowers the chances to detect locking issues. Nobody likes solution 1), which I can understand. This patch implements solution 2). However lockdep is still not happy with configfs_depend_item(). Next patch reworks the locking of configfs_depend_item() and finally makes lockdep happy. [ Note: This hides a few locking interactions with the VFS from lockdep. That was my big concern, because we like lockdep's protection. However, the current state always dumps a spurious warning. The locking is correct, so I tell people to ignore the warning and that we'll keep our eyes on the locking to make sure it stays correct. With this patch, we eliminate the warning. We do lose some of the lockdep protections, but this only means that we still have to keep our eyes on the locking. We're going to do that anyway. -- Joel ] Signed-off-by: Louis Rilling <louis.rilling@kerlabs.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
305 lines
7.8 KiB
C
305 lines
7.8 KiB
C
/* -*- mode: c; c-basic-offset: 8; -*-
|
|
* vim: noexpandtab sw=8 ts=8 sts=0:
|
|
*
|
|
* inode.c - basic inode and dentry operations.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2 of the License, or (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*
|
|
* Based on sysfs:
|
|
* sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
|
|
*
|
|
* configfs Copyright (C) 2005 Oracle. All rights reserved.
|
|
*
|
|
* Please see Documentation/filesystems/configfs.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/sched.h>
|
|
#include <linux/lockdep.h>
|
|
|
|
#include <linux/configfs.h>
|
|
#include "configfs_internal.h"
|
|
|
|
#ifdef CONFIG_LOCKDEP
|
|
static struct lock_class_key default_group_class[MAX_LOCK_DEPTH];
|
|
#endif
|
|
|
|
extern struct super_block * configfs_sb;
|
|
|
|
static const struct address_space_operations configfs_aops = {
|
|
.readpage = simple_readpage,
|
|
.write_begin = simple_write_begin,
|
|
.write_end = simple_write_end,
|
|
};
|
|
|
|
static struct backing_dev_info configfs_backing_dev_info = {
|
|
.ra_pages = 0, /* No readahead */
|
|
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
|
|
};
|
|
|
|
static const struct inode_operations configfs_inode_operations ={
|
|
.setattr = configfs_setattr,
|
|
};
|
|
|
|
int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
|
|
{
|
|
struct inode * inode = dentry->d_inode;
|
|
struct configfs_dirent * sd = dentry->d_fsdata;
|
|
struct iattr * sd_iattr;
|
|
unsigned int ia_valid = iattr->ia_valid;
|
|
int error;
|
|
|
|
if (!sd)
|
|
return -EINVAL;
|
|
|
|
sd_iattr = sd->s_iattr;
|
|
|
|
error = inode_change_ok(inode, iattr);
|
|
if (error)
|
|
return error;
|
|
|
|
error = inode_setattr(inode, iattr);
|
|
if (error)
|
|
return error;
|
|
|
|
if (!sd_iattr) {
|
|
/* setting attributes for the first time, allocate now */
|
|
sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL);
|
|
if (!sd_iattr)
|
|
return -ENOMEM;
|
|
/* assign default attributes */
|
|
sd_iattr->ia_mode = sd->s_mode;
|
|
sd_iattr->ia_uid = 0;
|
|
sd_iattr->ia_gid = 0;
|
|
sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME;
|
|
sd->s_iattr = sd_iattr;
|
|
}
|
|
|
|
/* attributes were changed atleast once in past */
|
|
|
|
if (ia_valid & ATTR_UID)
|
|
sd_iattr->ia_uid = iattr->ia_uid;
|
|
if (ia_valid & ATTR_GID)
|
|
sd_iattr->ia_gid = iattr->ia_gid;
|
|
if (ia_valid & ATTR_ATIME)
|
|
sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime,
|
|
inode->i_sb->s_time_gran);
|
|
if (ia_valid & ATTR_MTIME)
|
|
sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime,
|
|
inode->i_sb->s_time_gran);
|
|
if (ia_valid & ATTR_CTIME)
|
|
sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime,
|
|
inode->i_sb->s_time_gran);
|
|
if (ia_valid & ATTR_MODE) {
|
|
umode_t mode = iattr->ia_mode;
|
|
|
|
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
|
|
mode &= ~S_ISGID;
|
|
sd_iattr->ia_mode = sd->s_mode = mode;
|
|
}
|
|
|
|
return error;
|
|
}
|
|
|
|
static inline void set_default_inode_attr(struct inode * inode, mode_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_mode = iattr->ia_mode;
|
|
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;
|
|
}
|
|
|
|
struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd)
|
|
{
|
|
struct inode * inode = new_inode(configfs_sb);
|
|
if (inode) {
|
|
inode->i_mapping->a_ops = &configfs_aops;
|
|
inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
|
|
inode->i_op = &configfs_inode_operations;
|
|
|
|
if (sd->s_iattr) {
|
|
/* sysfs_dirent has non-default attributes
|
|
* get them for the new inode from persistent copy
|
|
* in sysfs_dirent
|
|
*/
|
|
set_inode_attr(inode, sd->s_iattr);
|
|
} else
|
|
set_default_inode_attr(inode, mode);
|
|
}
|
|
return inode;
|
|
}
|
|
|
|
#ifdef CONFIG_LOCKDEP
|
|
|
|
static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
|
|
struct inode *inode)
|
|
{
|
|
int depth = sd->s_depth;
|
|
|
|
if (depth > 0) {
|
|
if (depth <= ARRAY_SIZE(default_group_class)) {
|
|
lockdep_set_class(&inode->i_mutex,
|
|
&default_group_class[depth - 1]);
|
|
} else {
|
|
/*
|
|
* In practice the maximum level of locking depth is
|
|
* already reached. Just inform about possible reasons.
|
|
*/
|
|
printk(KERN_INFO "configfs: Too many levels of inodes"
|
|
" for the locking correctness validator.\n");
|
|
printk(KERN_INFO "Spurious warnings may appear.\n");
|
|
}
|
|
}
|
|
}
|
|
|
|
#else /* CONFIG_LOCKDEP */
|
|
|
|
static void configfs_set_inode_lock_class(struct configfs_dirent *sd,
|
|
struct inode *inode)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_LOCKDEP */
|
|
|
|
int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *))
|
|
{
|
|
int error = 0;
|
|
struct inode * inode = NULL;
|
|
if (dentry) {
|
|
if (!dentry->d_inode) {
|
|
struct configfs_dirent *sd = dentry->d_fsdata;
|
|
if ((inode = configfs_new_inode(mode, sd))) {
|
|
if (dentry->d_parent && dentry->d_parent->d_inode) {
|
|
struct inode *p_inode = dentry->d_parent->d_inode;
|
|
p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
|
|
}
|
|
configfs_set_inode_lock_class(sd, inode);
|
|
goto Proceed;
|
|
}
|
|
else
|
|
error = -ENOMEM;
|
|
} else
|
|
error = -EEXIST;
|
|
} else
|
|
error = -ENOENT;
|
|
goto Done;
|
|
|
|
Proceed:
|
|
if (init)
|
|
error = init(inode);
|
|
if (!error) {
|
|
d_instantiate(dentry, inode);
|
|
if (S_ISDIR(mode) || S_ISLNK(mode))
|
|
dget(dentry); /* pin link and directory dentries in core */
|
|
} else
|
|
iput(inode);
|
|
Done:
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* Get the name for corresponding element represented by the given configfs_dirent
|
|
*/
|
|
const unsigned char * configfs_get_name(struct configfs_dirent *sd)
|
|
{
|
|
struct configfs_attribute *attr;
|
|
|
|
BUG_ON(!sd || !sd->s_element);
|
|
|
|
/* These always have a dentry, so use that */
|
|
if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
|
|
return sd->s_dentry->d_name.name;
|
|
|
|
if (sd->s_type & CONFIGFS_ITEM_ATTR) {
|
|
attr = sd->s_element;
|
|
return attr->ca_name;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
|
|
/*
|
|
* Unhashes the dentry corresponding to given configfs_dirent
|
|
* Called with parent inode's i_mutex held.
|
|
*/
|
|
void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
|
|
{
|
|
struct dentry * dentry = sd->s_dentry;
|
|
|
|
if (dentry) {
|
|
spin_lock(&dcache_lock);
|
|
spin_lock(&dentry->d_lock);
|
|
if (!(d_unhashed(dentry) && dentry->d_inode)) {
|
|
dget_locked(dentry);
|
|
__d_drop(dentry);
|
|
spin_unlock(&dentry->d_lock);
|
|
spin_unlock(&dcache_lock);
|
|
simple_unlink(parent->d_inode, dentry);
|
|
} else {
|
|
spin_unlock(&dentry->d_lock);
|
|
spin_unlock(&dcache_lock);
|
|
}
|
|
}
|
|
}
|
|
|
|
void configfs_hash_and_remove(struct dentry * dir, const char * name)
|
|
{
|
|
struct configfs_dirent * sd;
|
|
struct configfs_dirent * parent_sd = dir->d_fsdata;
|
|
|
|
if (dir->d_inode == NULL)
|
|
/* no inode means this hasn't been made visible yet */
|
|
return;
|
|
|
|
mutex_lock(&dir->d_inode->i_mutex);
|
|
list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
|
|
if (!sd->s_element)
|
|
continue;
|
|
if (!strcmp(configfs_get_name(sd), name)) {
|
|
spin_lock(&configfs_dirent_lock);
|
|
list_del_init(&sd->s_sibling);
|
|
spin_unlock(&configfs_dirent_lock);
|
|
configfs_drop_dentry(sd, dir);
|
|
configfs_put(sd);
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&dir->d_inode->i_mutex);
|
|
}
|
|
|
|
int __init configfs_inode_init(void)
|
|
{
|
|
return bdi_init(&configfs_backing_dev_info);
|
|
}
|
|
|
|
void __exit configfs_inode_exit(void)
|
|
{
|
|
bdi_destroy(&configfs_backing_dev_info);
|
|
}
|