[NET]: Make /proc/net a symlink on /proc/self/net (v3)

Current /proc/net is done with so called "shadows", but current
implementation is broken and has little chances to get fixed.

The problem is that dentries subtree of /proc/net directory has
fancy revalidation rules to make processes living in different
net namespaces see different entries in /proc/net subtree, but
currently, tasks see in the /proc/net subdir the contents of any
other namespace, depending on who opened the file first.

The proposed fix is to turn /proc/net into a symlink, which points
to /proc/self/net, which in turn shows what previously was in
/proc/net - the network-related info, from the net namespace the
appropriate task lives in.

# ls -l /proc/net
lrwxrwxrwx  1 root root 8 Mar  5 15:17 /proc/net -> self/net

In other words - this behaves like /proc/mounts, but unlike
"mounts", "net" is not a file, but a directory.

Changes from v2:
* Fixed discrepancy of /proc/net nlink count and selinux labeling
  screwup pointed out by Stephen.

  To get the correct nlink count the ->getattr callback for /proc/net
  is overridden to read one from the net->proc_net entry.

  To make selinux still work the net->proc_net entry is initialized
  properly, i.e. with the "net" name and the proc_net parent.

Selinux fixes are
Acked-by:  Stephen Smalley <sds@tycho.nsa.gov>

Changes from v1:
* Fixed a task_struct leak in get_proc_task_net, pointed out by Paul.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 17 insertions, 9 deletions

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 68971e66cd4..a36ad3c75cf 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -377,15 +377,14 @@ static struct dentry_operations proc_dentry_operations =
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
  */
-struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
+		struct dentry *dentry)
 {
 	struct inode *inode = NULL;
-	struct proc_dir_entry * de;
 	int error = -ENOENT;
 
 	lock_kernel();
 	spin_lock(&proc_subdir_lock);
-	de = PDE(dir);
 	if (de) {
 		for (de = de->subdir; de ; de = de->next) {
 			if (de->namelen != dentry->d_name.len)
@@ -393,8 +392,6 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam
 			if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
 				unsigned int ino;
 
-				if (de->shadow_proc)
-					de = de->shadow_proc(current, de);
 				ino = de->low_ino;
 				de_get(de);
 				spin_unlock(&proc_subdir_lock);
@@ -417,6 +414,12 @@ out_unlock:
 	return ERR_PTR(error);
 }
 
+struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
+		struct nameidata *nd)
+{
+	return proc_lookup_de(PDE(dir), dir, dentry);
+}
+
 /*
  * This returns non-zero if at EOF, so that the /proc
  * root directory can use this and check if it should
@@ -426,10 +429,9 @@ out_unlock:
  * value of the readdir() call, as long as it's non-negative
  * for success..
  */
-int proc_readdir(struct file * filp,
-	void * dirent, filldir_t filldir)
+int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
+		filldir_t filldir)
 {
-	struct proc_dir_entry * de;
 	unsigned int ino;
 	int i;
 	struct inode *inode = filp->f_path.dentry->d_inode;
@@ -438,7 +440,6 @@ int proc_readdir(struct file * filp,
 	lock_kernel();
 
 	ino = inode->i_ino;
-	de = PDE(inode);
 	if (!de) {
 		ret = -EINVAL;
 		goto out;
@@ -499,6 +500,13 @@ out:	unlock_kernel();
 	return ret;	
 }
 
+int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+
+	return proc_readdir_de(PDE(inode), filp, dirent, filldir);
+}
+
 /*
  * These are the generic /proc directory operations. They
  * use the in-memory "struct proc_dir_entry" tree to parse