[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>

fs/proc/base.c

@@ -2274,6 +2274,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	DIR("task",       S_IRUGO|S_IXUGO, task),
 	DIR("fd",         S_IRUSR|S_IXUSR, fd),
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, fdinfo),
+	DIR("net",        S_IRUGO|S_IXUSR, net),
 	REG("environ",    S_IRUSR, environ),
 	INF("auxv",       S_IRUSR, pid_auxv),
 	ONE("status",     S_IRUGO, pid_status),

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,
+int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
-	void * dirent, filldir_t filldir)
+		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

fs/proc/internal.h

@@ -64,6 +64,8 @@ extern const struct file_operations proc_numa_maps_operations;
 extern const struct file_operations proc_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;
+extern const struct file_operations proc_net_operations;
+extern const struct inode_operations proc_net_inode_operations;
 
 void free_proc_entry(struct proc_dir_entry *de);
 
@@ -83,3 +85,8 @@ static inline int proc_fd(struct inode *inode)
 {
 	return PROC_I(inode)->fd;
 }
+
+struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
+		struct dentry *dentry);
+int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
+		filldir_t filldir);

fs/proc/proc_net.c

@@ -63,6 +63,82 @@ int seq_release_net(struct inode *ino, struct file *f)
 }
 EXPORT_SYMBOL_GPL(seq_release_net);
 
+static struct net *get_proc_task_net(struct inode *dir)
+{
+	struct task_struct *task;
+	struct nsproxy *ns;
+	struct net *net = NULL;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(dir), PIDTYPE_PID);
+	if (task != NULL) {
+		ns = task_nsproxy(task);
+		if (ns != NULL)
+			net = get_net(ns->net_ns);
+	}
+	rcu_read_unlock();
+
+	return net;
+}
+
+static struct dentry *proc_tgid_net_lookup(struct inode *dir,
+		struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *de;
+	struct net *net;
+
+	de = ERR_PTR(-ENOENT);
+	net = get_proc_task_net(dir);
+	if (net != NULL) {
+		de = proc_lookup_de(net->proc_net, dir, dentry);
+		put_net(net);
+	}
+	return de;
+}
+
+static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	struct net *net;
+
+	net = get_proc_task_net(inode);
+
+	generic_fillattr(inode, stat);
+
+	if (net != NULL) {
+		stat->nlink = net->proc_net->nlink;
+		put_net(net);
+	}
+
+	return 0;
+}
+
+const struct inode_operations proc_net_inode_operations = {
+	.lookup		= proc_tgid_net_lookup,
+	.getattr	= proc_tgid_net_getattr,
+};
+
+static int proc_tgid_net_readdir(struct file *filp, void *dirent,
+		filldir_t filldir)
+{
+	int ret;
+	struct net *net;
+
+	ret = -EINVAL;
+	net = get_proc_task_net(filp->f_path.dentry->d_inode);
+	if (net != NULL) {
+		ret = proc_readdir_de(net->proc_net, filp, dirent, filldir);
+		put_net(net);
+	}
+	return ret;
+}
+
+const struct file_operations proc_net_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_tgid_net_readdir,
+};
+
 
 struct proc_dir_entry *proc_net_fops_create(struct net *net,
 	const char *name, mode_t mode, const struct file_operations *fops)
@@ -83,14 +159,6 @@ struct net *get_proc_net(const struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(get_proc_net);
 
-static struct proc_dir_entry *shadow_pde;
-
-static struct proc_dir_entry *proc_net_shadow(struct task_struct *task,
-						struct proc_dir_entry *de)
-{
-	return task->nsproxy->net_ns->proc_net;
-}
-
 struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 		struct proc_dir_entry *parent)
 {
@@ -104,45 +172,39 @@ EXPORT_SYMBOL_GPL(proc_net_mkdir);
 
 static __net_init int proc_net_ns_init(struct net *net)
 {
-	struct proc_dir_entry *root, *netd, *net_statd;
+	struct proc_dir_entry *netd, *net_statd;
 	int err;
 
 	err = -ENOMEM;
-	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	netd = kzalloc(sizeof(*netd), GFP_KERNEL);
-	if (!root)
+	if (!netd)
 		goto out;
 
-	err = -EEXIST;
+	netd->data = net;
-	netd = proc_net_mkdir(net, "net", root);
+	netd->nlink = 2;
-	if (!netd)
+	netd->name = "net";
-		goto free_root;
+	netd->namelen = 3;
+	netd->parent = &proc_root;
 
 	err = -EEXIST;
 	net_statd = proc_net_mkdir(net, "stat", netd);
 	if (!net_statd)
 		goto free_net;
 
-	root->data = net;
-
-	net->proc_net_root = root;
 	net->proc_net = netd;
 	net->proc_net_stat = net_statd;
-	err = 0;
+	return 0;
 
+free_net:
+	kfree(netd);
 out:
 	return err;
-free_net:
-	remove_proc_entry("net", root);
-free_root:
-	kfree(root);
-	goto out;
 }
 
 static __net_exit void proc_net_ns_exit(struct net *net)
 {
 	remove_proc_entry("stat", net->proc_net);
-	remove_proc_entry("net", net->proc_net_root);
+	kfree(net->proc_net);
-	kfree(net->proc_net_root);
 }
 
 static struct pernet_operations __net_initdata proc_net_ns_ops = {
@@ -152,8 +214,7 @@ static struct pernet_operations __net_initdata proc_net_ns_ops = {
 
 int __init proc_net_init(void)
 {
-	shadow_pde = proc_mkdir("net", NULL);
+	proc_symlink("net", NULL, "self/net");
-	shadow_pde->shadow_proc = proc_net_shadow;
 
 	return register_pernet_subsys(&proc_net_ns_ops);
 }

include/linux/proc_fs.h

@@ -50,8 +50,6 @@ typedef	int (read_proc_t)(char *page, char **start, off_t off,
 typedef	int (write_proc_t)(struct file *file, const char __user *buffer,
 			   unsigned long count, void *data);
 typedef int (get_info_t)(char *, char **, off_t, int);
-typedef struct proc_dir_entry *(shadow_proc_t)(struct task_struct *task,
-						struct proc_dir_entry *pde);
 
 struct proc_dir_entry {
 	unsigned int low_ino;
@@ -82,7 +80,6 @@ struct proc_dir_entry {
 	int pde_users;	/* number of callers into module in progress */
 	spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
 	struct completion *pde_unload_completion;
-	shadow_proc_t *shadow_proc;
 };
 
 struct kcore_list {

include/net/net_namespace.h

@@ -31,7 +31,6 @@ struct net {
 
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
-	struct proc_dir_entry 	*proc_net_root;
 
 	struct list_head	sysctl_table_headers;