[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, 89 insertions, 28 deletions

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 14e9b5aaf863..4caa5f774fb7 100644
--- a/fs/proc/proc_net.c
+++ b/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);
-        if (!root)
+        netd = kzalloc(sizeof(*netd), GFP_KERNEL);
+        if (!netd)
                 goto out;
 
-        err = -EEXIST;
-        netd = proc_net_mkdir(net, "net", root);
-        if (!netd)
-                goto free_root;
+        netd->data = net;
+        netd->nlink = 2;
+        netd->name = "net";
+        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_root);
+        kfree(net->proc_net);
 }
 
 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);
-        shadow_pde->shadow_proc = proc_net_shadow;
+        proc_symlink("net", NULL, "self/net");
 
         return register_pernet_subsys(&proc_net_ns_ops);
 }