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_tag_types with the type and it's operations
- call sysfs_make_tagged_dir with the tag type on directories
to be managed by this tag type
- sysfs_exit_tag when an individual tag is no longer valid
- Implement mount_tag() which returns the tag of the calling process
so we can attach it to a sysfs superblock.
- Implement ktype.sysfs_tag() which returns the tag of a syfs kobject.
Everything else is left up to sysfs and the driver layer.
For the network namespace mount_tag and sysfs_tag 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>
---
fs/sysfs/bin.c | 2 +-
fs/sysfs/dir.c | 139 ++++++++++++++++++++++++++++++++++++++++++-----
fs/sysfs/file.c | 10 ++--
fs/sysfs/group.c | 4 +-
fs/sysfs/inode.c | 7 ++-
fs/sysfs/mount.c | 115 +++++++++++++++++++++++++++++++++++++--
fs/sysfs/symlink.c | 2 +-
fs/sysfs/sysfs.h | 19 ++++++-
include/linux/kobject.h | 1 +
include/linux/sysfs.h | 29 ++++++++++
10 files changed, 295 insertions(+), 33 deletions(-)
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 006fc64..86e1128 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -252,7 +252,7 @@ int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr)
void sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr)
{
- sysfs_hash_and_remove(kobj->sd, attr->attr.name);
+ sysfs_hash_and_remove(kobj, kobj->sd, attr->attr.name);
}
EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index b2d92ea..6dc3376 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -30,6 +30,30 @@ DEFINE_SPINLOCK(sysfs_assoc_lock);
static DEFINE_SPINLOCK(sysfs_ino_lock);
static DEFINE_IDA(sysfs_ino_ida);
+static const void *sysfs_creation_tag(struct sysfs_dirent *parent_sd,
+ struct sysfs_dirent *sd)
+{
+ const void *tag = NULL;
+
+ if (sysfs_tag_type(parent_sd)) {
+ struct kobject *kobj;
+ switch (sysfs_type(sd)) {
+ case SYSFS_DIR:
+ kobj = sd->s_dir.kobj;
+ break;
+ case SYSFS_KOBJ_LINK:
+ kobj = sd->s_symlink.target_sd->s_dir.kobj;
+ break;
+ default:
+ BUG();
+ }
+ tag = kobj->ktype->sysfs_tag(kobj);
+ /* NULL tags are reserved for internal use */
+ BUG_ON(tag == NULL);
+ }
+ return tag;
+}
+
/**
* sysfs_link_sibling - link sysfs_dirent into sibling list
* @sd: sysfs_dirent of interest
@@ -101,8 +125,19 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
struct dentry *sysfs_get_dentry(struct super_block *sb,
struct sysfs_dirent *sd)
{
- struct dentry *dentry = dget(sb->s_root);
+ struct dentry *dentry;
+
+ /* Bail if this sd won't show up in this superblock */
+ if (sd->s_parent) {
+ enum sysfs_tag_type type;
+ const void *tag;
+ type = sysfs_tag_type(sd->s_parent);
+ tag = sysfs_info(sb)->tag[type];
+ if (sd->s_tag != tag)
+ return ERR_PTR(-EXDEV);
+ }
+ dentry = dget(sb->s_root);
while (dentry->d_fsdata != sd) {
struct sysfs_dirent *cur;
struct dentry *parent;
@@ -421,10 +456,15 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
*/
int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
- if (sysfs_find_dirent(acxt->parent_sd, sd->s_name))
+ const void *tag = NULL;
+
+ tag = sysfs_creation_tag(acxt->parent_sd, sd);
+
+ if (sysfs_find_dirent(acxt->parent_sd, tag, sd->s_name))
return -EEXIST;
sd->s_parent = sysfs_get(acxt->parent_sd);
+ sd->s_tag = tag;
if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
inc_nlink(acxt->parent_inode);
@@ -572,13 +612,17 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
* Pointer to sysfs_dirent if found, NULL if not.
*/
struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
+ const void *tag,
const unsigned char *name)
{
struct sysfs_dirent *sd;
- for (sd = parent_sd->s_dir.children; sd; sd = sd->s_sibling)
+ for (sd = parent_sd->s_dir.children; sd; sd = sd->s_sibling) {
+ if (sd->s_tag != tag)
+ continue;
if (!strcmp(sd->s_name, name))
return sd;
+ }
return NULL;
}
@@ -602,7 +646,7 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
struct sysfs_dirent *sd;
mutex_lock(&sysfs_mutex);
- sd = sysfs_find_dirent(parent_sd, name);
+ sd = sysfs_find_dirent(parent_sd, NULL, name);
sysfs_get(sd);
mutex_unlock(&sysfs_mutex);
@@ -668,13 +712,18 @@ 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 dentry *parent = dentry->d_parent;
+ struct sysfs_dirent *parent_sd = parent->d_fsdata;
struct sysfs_dirent *sd;
struct inode *inode;
+ enum sysfs_tag_type type;
+ const void *tag;
mutex_lock(&sysfs_mutex);
- sd = sysfs_find_dirent(parent_sd, dentry->d_name.name);
+ type = sysfs_tag_type(parent_sd);
+ tag = sysfs_info(parent->d_sb)->tag[type];
+ sd = sysfs_find_dirent(parent_sd, tag, dentry->d_name.name);
/* no such entry */
if (!sd) {
@@ -882,19 +931,24 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
struct sysfs_rename_struct *srs;
struct inode *parent_inode = NULL;
const char *dup_name = NULL;
+ const void *old_tag, *tag;
int error;
INIT_LIST_HEAD(&todo);
mutex_lock(&sysfs_rename_mutex);
+ old_tag = sd->s_tag;
+ tag = sysfs_creation_tag(sd->s_parent, sd);
error = 0;
- if (strcmp(sd->s_name, new_name) == 0)
+ if ((old_tag == tag) && (strcmp(sd->s_name, new_name) == 0))
goto out; /* nothing to rename */
sysfs_grab_supers();
- error = prep_rename(&todo, sd, sd->s_parent, new_name);
- if (error)
- goto out_release;
+ if (old_tag == tag) {
+ error = prep_rename(&todo, sd, sd->s_parent, new_name);
+ if (error)
+ goto out_release;
+ }
error = -ENOMEM;
mutex_lock(&sysfs_mutex);
@@ -907,7 +961,7 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
mutex_lock(&sysfs_mutex);
error = -EEXIST;
- if (sysfs_find_dirent(sd->s_parent, new_name))
+ if (sysfs_find_dirent(sd->s_parent, tag, new_name))
goto out_unlock;
/* rename sysfs_dirent */
@@ -918,6 +972,7 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
dup_name = sd->s_name;
sd->s_name = new_name;
+ sd->s_tag = tag;
/* rename */
list_for_each_entry(srs, &todo, list) {
@@ -925,6 +980,20 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
d_move(srs->old_dentry, srs->new_dentry);
}
+ /* If we are moving across superblocks drop the dcache entries */
+ if (old_tag != tag) {
+ struct super_block *sb;
+ struct dentry *dentry;
+ list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) {
+ dentry = __sysfs_get_dentry(sb, sd);
+ if (!dentry)
+ continue;
+ shrink_dcache_parent(dentry);
+ d_drop(dentry);
+ dput(dentry);
+ }
+ }
+
error = 0;
out_unlock:
mutex_unlock(&sysfs_mutex);
@@ -947,11 +1016,13 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
struct sysfs_rename_struct *srs;
struct inode *old_parent_inode = NULL, *new_parent_inode = NULL;
int error;
+ const void *tag;
INIT_LIST_HEAD(&todo);
mutex_lock(&sysfs_rename_mutex);
BUG_ON(!sd->s_parent);
new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root;
+ tag
...
OpenVZ Forum
Members
Search
Help
Register
Login
Home
