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 race free design all tagged directories are created
and managed by sysfs itself. The upper level code that knows what
tagged directories we need provides just two methods that enable
this:
  sb_tag() - that returns a "void *" tag that identifies the context of
	the process that mounted sysfs.
  kobject_tag(kobj) - that returns a "void *" tag that identifies the context
	a kobject should be in.
Everything else is left up to sysfs.

For the network namespace sb_tag and kobject_tag are essentially
one line functions, and look to remain that.

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        |  185 ++++++++++++++++++++++++++++++++++++++++++++++----
 fs/sysfs/file.c       |    8 +-
 fs/sysfs/group.c      |    4 -
 fs/sysfs/inode.c      |    7 +
 fs/sysfs/mount.c      |   44 ++++++++++-
 fs/sysfs/symlink.c    |    2 
 fs/sysfs/sysfs.h      |   17 ++++
 include/linux/sysfs.h |   17 ++++
 9 files changed, 257 insertions(+), 29 deletions(-)

Index: linux-mm/fs/sysfs/bin.c
===================================================================
--- linux-mm.orig/fs/sysfs/bin.c
+++ linux-mm/fs/sysfs/bin.c
@@ -252,7 +252,7 @@ int sysfs_create_bin_file(struct kobject
 
 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);
Index: linux-mm/fs/sysfs/dir.c
===================================================================
--- linux-mm.orig/fs/sysfs/dir.c
+++ linux-mm/fs/sysfs/dir.c
@@ -103,8 +103,17 @@ static void sysfs_unlink_sibling(struct 
 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 && sd->s_parent->s_flags & SYSFS_FLAG_TAGGED) {
+		const void *tag;
+		tag = sysfs_lookup_tag(sd->s_parent, sb);
+		if (sd->s_tag.tag != tag)
+			return ERR_PTR(-EXDEV);
+	}
 
+	dentry = dget(sb->s_root);
 	while (dentry->d_fsdata != sd) {
 		struct sysfs_dirent *cur;
 		struct dentry *parent;
@@ -423,7 +432,11 @@ void sysfs_addrm_start(struct sysfs_addr
  */
 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)) {
 		printk(KERN_WARNING "sysfs: duplicate filename '%s' "
 		       "can not be created\n", sd->s_name);
 		WARN_ON(1);
@@ -439,6 +452,9 @@ int sysfs_add_one(struct sysfs_addrm_cxt
 
 	sd->s_parent = sysfs_get(acxt->parent_sd);
 
+	if (sd->s_parent->s_flags & SYSFS_FLAG_TAGGED)
+		sd->s_tag.tag = tag;
+
 	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
 		inc_nlink(acxt->parent_inode);
 
@@ -585,13 +601,18 @@ void sysfs_addrm_finish(struct sysfs_add
  *	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 ((parent_sd->s_flags & SYSFS_FLAG_TAGGED) &&
+		    (sd->s_tag.tag != tag))
+			continue;
 		if (!strcmp(sd->s_name, name))
 			return sd;
+	}
 	return NULL;
 }
 
@@ -615,7 +636,7 @@ struct sysfs_dirent *sysfs_get_dirent(st
 	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);
 
@@ -681,13 +702,16 @@ static struct dentry * sysfs_lookup(stru
 				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;
+	const void *tag;
 
 	mutex_lock(&sysfs_mutex);
 
-	sd = sysfs_find_dirent(parent_sd, dentry->d_name.name);
+	tag = sysfs_lookup_tag(parent_sd, parent->d_sb);
+	sd = sysfs_find_dirent(parent_sd, tag, dentry->d_name.name);
 
 	/* no such entry */
 	if (!sd) {
@@ -895,19 +919,24 @@ int sysfs_rename_dir(struct kobject * ko
 	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 = sysfs_dirent_tag(sd);
+	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);
@@ -920,7 +949,7 @@ int sysfs_rename_dir(struct kobject * ko
 	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 kobject and sysfs_dirent */
@@ -935,6 +964,8 @@ int sysfs_rename_dir(struct kobject * ko
 
 	dup_name = sd->s_name;
 	sd->s_name = new_name;
+	if (sd->s_parent->s_flags & SYSFS_FLAG_TAGGED)
+		sd->s_tag.tag = tag;
 
 	/* rename */
 	list_for_each_entry(srs, &todo, list) {
@@ -942,6 +973,20 @@ int sysfs_rename_dir(struct kobject * ko
 		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);
@@ -964,11 +1009,13 @@ int sysfs_move_dir(struct kobject *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 = sysfs_dirent_tag(sd);
 
 	error = 0;
 	if (sd->s_parent == new_parent_sd)
@@ -1002,7 +1049,7 @@ again:
 	mutex_lock(&sysfs_mutex);
 
 	error = -EEXIST;
-	if (sysfs_find_dirent(new_parent_sd, sd->s_name))
+	if (sysfs_find_dirent(new_parent_sd, tag, sd->s_name))
 		goto out_unlock;
 
 	error = 0;
@@ -1041,10 +1088,11 @@ static inline unsigned char dt_type(stru
 
 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 dentry *parent = filp->f_path.dentry;
+	struct sysfs_dirent *parent_sd = parent->d_fsdata;
 	struct sysfs_dirent *pos;
 	ino_t ino;
+	const void *tag;
 
 	if (filp->f_pos == 0) {
 		ino = parent_sd->s_ino;
@@ -1062,6 +1110,8 @@ static int sysfs_readdir(struct file * f
 	if ((filp->f_pos > 1) && (filp->f_pos < INT_MAX)) {
 		mutex_lock(&sysfs_mutex);
 
+		tag = sysfs_lookup_tag(parent_sd, parent->d_sb);
+
 		/* Skip the dentries we have a