proc: Usable inode numbers for the namespace file descriptors.

Assign a unique proc inode to each namespace, and use that
inode number to ensure we only allocate at most one proc
inode for every namespace in proc.

A single proc inode per namespace allows userspace to test
to see if two processes are in the same namespace.

This has been a long requested feature and only blocked because
a naive implementation would put the id in a global space and
would ultimately require having a namespace for the names of
namespaces, making migration and certain virtualization tricks
impossible.

We still don't have per superblock inode numbers for proc, which
appears necessary for application unaware checkpoint/restart and
migrations (if the application is using namespace file descriptors)
but that is now allowd by the design if it becomes important.

I have preallocated the ipc and uts initial proc inode numbers so
their structures can be statically initialized.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
(cherry picked from commit 98f842e675f96ffac96e6c50315790912b2812be)

2 files changed, 28 insertions, 10 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 10d8969..ef0d97f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2403,6 +2403,7 @@ dput_out:
 
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
+	proc_free_inum(ns->proc_inum);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
@@ -2419,10 +2420,16 @@ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 {
 	struct mnt_namespace *new_ns;
+	int ret;
 
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
+	ret = proc_alloc_inum(&new_ns->proc_inum);
+	if (ret) {
+		kfree(new_ns);
+		return ERR_PTR(ret);
+	}
 	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	atomic_set(&new_ns->count, 1);
 	new_ns->root = NULL;
@@ -2830,10 +2837,17 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
 	return 0;
 }
 
+static unsigned int mntns_inum(void *ns)
+{
+	struct mnt_namespace *mnt_ns = ns;
+	return mnt_ns->proc_inum;
+}
+
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
 	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,
+	.inum		= mntns_inum,
 };
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 3d6df8c..70a62c0 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -79,7 +79,7 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	inode = new_inode(sb);
+	inode = iget_locked(sb, ns_ops->inum(ns));
 	if (!inode) {
 		dput(dentry);
 		ns_ops->put(ns);
@@ -87,13 +87,17 @@ static struct dentry *proc_ns_get_dentry(struct super_block *sb,
 	}
 
 	ei = PROC_I(inode);
-	inode->i_ino = get_next_ino();
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-	inode->i_op = &ns_inode_operations;
-	inode->i_mode = S_IFREG | S_IRUGO;
-	inode->i_fop = &ns_file_operations;
-	ei->ns_ops = ns_ops;
-	ei->ns = ns;
+	if (inode->i_state & I_NEW) {
+		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		inode->i_op = &ns_inode_operations;
+		inode->i_mode = S_IFREG | S_IRUGO;
+		inode->i_fop = &ns_file_operations;
+		ei->ns_ops = ns_ops;
+		ei->ns = ns;
+		unlock_new_inode(inode);
+	} else {
+		ns_ops->put(ns);
+	}
 
 	d_set_d_op(dentry, &ns_dentry_operations);
 	result = d_instantiate_unique(dentry, inode);
@@ -159,12 +163,12 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ns)
 		goto out_put_task;
 
-	snprintf(name, sizeof(name), "%s", ns_ops->name);
+	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
 	len = strlen(name);
 
 	if (len > buflen)
 		len = buflen;
-	if (copy_to_user(buffer, ns_ops->name, len))
+	if (copy_to_user(buffer, name, len))
 		len = -EFAULT;
 
 	ns_ops->put(ns);