linux/fs/sysfs/dir.c

162 lines
4.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/sysfs/dir.c - sysfs core and dir operation implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007 Tejun Heo <teheo@suse.de>
*
* Please see Documentation/filesystems/sysfs.txt for more information.
*/
#define pr_fmt(fmt) "sysfs: " fmt
#include <linux/fs.h>
#include <linux/kobject.h>
#include <linux/slab.h>
#include "sysfs.h"
DEFINE_SPINLOCK(sysfs_symlink_target_lock);
void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
{
char *buf;
buf = kzalloc(PATH_MAX, GFP_KERNEL);
if (buf)
kernfs_path(parent, buf, PATH_MAX);
pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name);
dump_stack();
kfree(buf);
}
/**
2013-09-12 02:29:05 +00:00
* 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
*/
2013-09-12 02:29:05 +00:00
int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
{
struct kernfs_node *parent, *kn;
kuid_t uid;
kgid_t gid;
BUG_ON(!kobj);
if (kobj->parent)
parent = kobj->parent->sd;
else
parent = sysfs_root_kn;
if (!parent)
sysfs: handle 'parent deleted before child added' In scsi at least two cases of the parent device being deleted before the child is added have been observed. 1/ scsi is performing async scans and the device is removed prior to the async can thread running (can happen with an in-opportune / unlikely unplug during initial scan). 2/ libsas discovery event running after the parent port has been torn down (this is a bug in libsas). Result in crash signatures like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 IP: [<ffffffff8115e100>] sysfs_create_dir+0x32/0xb6 ... Process scsi_scan_8 (pid: 5417, threadinfo ffff88080bd16000, task ffff880801b8a0b0) Stack: 00000000fffffffe ffff880813470628 ffff88080bd17cd0 ffff88080614b7e8 ffff88080b45c108 00000000fffffffe ffff88080bd17d20 ffffffff8125e4a8 ffff88080bd17cf0 ffffffff81075149 ffff88080bd17d30 ffff88080614b7e8 Call Trace: [<ffffffff8125e4a8>] kobject_add_internal+0x120/0x1e3 [<ffffffff81075149>] ? trace_hardirqs_on+0xd/0xf [<ffffffff8125e641>] kobject_add_varg+0x41/0x50 [<ffffffff8125e70b>] kobject_add+0x64/0x66 [<ffffffff8131122b>] device_add+0x12d/0x63a In this scenario the parent is still valid (because we have a reference), but it has been device_del()'d which means its kobj->sd pointer is NULL'd via: device_del()->kobject_del()->sysfs_remove_dir() ...and then sysfs_create_dir() (without this fix) goes ahead and de-references parent_sd via sysfs_ns_type(): return (sd->s_flags & SYSFS_NS_TYPE_MASK) >> SYSFS_NS_TYPE_SHIFT; This scenario is being fixed in scsi/libsas, but if other subsystems present the same ordering the system need not immediately crash. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: James Bottomley <JBottomley@parallels.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-04-06 20:41:06 +00:00
return -ENOENT;
kobject_get_ownership(kobj, &uid, &gid);
kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
S_IRWXU | S_IRUGO | S_IXUGO, uid, gid,
kobj, ns);
if (IS_ERR(kn)) {
if (PTR_ERR(kn) == -EEXIST)
sysfs_warn_dup(parent, kobject_name(kobj));
return PTR_ERR(kn);
}
kobj->sd = kn;
return 0;
}
/**
* 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 kernfs_node *kn = 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 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_symlink_target_lock);
if (kn) {
WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR);
kernfs_remove(kn);
}
}
2013-09-12 02:29:05 +00:00
int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
const void *new_ns)
{
struct kernfs_node *parent;
int ret;
sysfs: Implement sysfs tagged directory support. The problem. When implementing a network namespace I need to be able to have multiple network devices with the same name. Currently this is a problem for /sys/class/net/*, /sys/devices/virtual/net/*, and potentially a few other directories of the form /sys/ ... /net/*. What this patch does is to add an additional tag field to the sysfs dirent structure. For directories that should show different contents depending on the context such as /sys/class/net/, and /sys/devices/virtual/net/ this tag field is used to specify the context in which those directories should be visible. Effectively this is the same as creating multiple distinct directories with the same name but internally to sysfs the result is nicer. I am calling the concept of a single directory that looks like multiple directories all at the same path in the filesystem tagged directories. For the networking namespace the set of directories whose contents I need to filter with tags can depend on the presence or absence of hotplug hardware or which modules are currently loaded. Which means I need a simple race free way to setup those directories as tagged. To achieve a reace free design all tagged directories are created and managed by sysfs itself. Users of this interface: - define a type in the sysfs_tag_type enumeration. - call sysfs_register_ns_types with the type and it's operations - sysfs_exit_ns when an individual tag is no longer valid - Implement mount_ns() which returns the ns of the calling process so we can attach it to a sysfs superblock. - Implement ktype.namespace() which returns the ns of a syfs kobject. Everything else is left up to sysfs and the driver layer. For the network namespace mount_ns and namespace() are essentially one line functions, and look to remain that. Tags are currently represented a const void * pointers as that is both generic, prevides enough information for equality comparisons, and is trivial to create for current users, as it is just the existing namespace pointer. The work needed in sysfs is more extensive. At each directory or symlink creating I need to check if the directory it is being created in is a tagged directory and if so generate the appropriate tag to place on the sysfs_dirent. Likewise at each symlink or directory removal I need to check if the sysfs directory it is being removed from is a tagged directory and if so figure out which tag goes along with the name I am deleting. Currently only directories which hold kobjects, and symlinks are supported. There is not enough information in the current file attribute interfaces to give us anything to discriminate on which makes it useless, and there are no potential users which makes it an uninteresting problem to solve. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Benjamin Thery <benjamin.thery@bull.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-03-30 18:31:26 +00:00
parent = kernfs_get_parent(kobj->sd);
ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
kernfs_put(parent);
return ret;
}
2013-09-12 02:29:05 +00:00
int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
const void *new_ns)
{
struct kernfs_node *kn = kobj->sd;
struct kernfs_node *new_parent;
new_parent = new_parent_kobj && new_parent_kobj->sd ?
new_parent_kobj->sd : sysfs_root_kn;
return kernfs_rename_ns(kn, new_parent, kn->name, new_ns);
}
/**
* 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)
{
struct kernfs_node *kn, *parent = parent_kobj->sd;
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);
}
return 0;
}
EXPORT_SYMBOL_GPL(sysfs_create_mount_point);
/**
* 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 kernfs_node *parent = parent_kobj->sd;
kernfs_remove_by_name_ns(parent, name, NULL);
}
EXPORT_SYMBOL_GPL(sysfs_remove_mount_point);