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)

7 files changed, 14 insertions, 1 deletions

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index f1605b5..c3fd93c 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -60,6 +60,8 @@ struct ipc_namespace {
 
 	/* user_ns which owns the ipc ns */
 	struct user_namespace *user_ns;
+
+	unsigned int	proc_inum;
 };
 
 extern struct ipc_namespace init_ipc_ns;
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 7fe24fd..4476019 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -8,6 +8,7 @@
 
 struct mnt_namespace {
 	atomic_t		count;
+	unsigned int		proc_inum;
 	struct vfsmount *	root;
 	struct list_head	list;
 	struct user_namespace	*user_ns;
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 38d1032..5c3b7a7 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -30,6 +30,7 @@ struct pid_namespace {
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct bsd_acct_struct *bacct;
 #endif
+	unsigned int proc_inum;
 };
 
 extern struct pid_namespace init_pid_ns;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 7d48920..3accff7 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -28,7 +28,11 @@ struct mm_struct;
  */
 
 enum {
-	PROC_ROOT_INO = 1,
+	PROC_ROOT_INO		= 1,
+	PROC_IPC_INIT_INO	= 0xEFFFFFFFU,
+	PROC_UTS_INIT_INO	= 0xEFFFFFFEU,
+	PROC_USER_INIT_INO	= 0xEFFFFFFDU,
+	PROC_PID_INIT_INO	= 0xEFFFFFFCU,
 };
 
 /*
@@ -263,6 +267,7 @@ struct proc_ns_operations {
 	void *(*get)(struct task_struct *task);
 	void (*put)(void *ns);
 	int (*install)(struct nsproxy *nsproxy, void *ns);
+	unsigned int (*inum)(void *ns);
 };
 extern const struct proc_ns_operations netns_operations;
 extern const struct proc_ns_operations utsns_operations;
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index faf4679..5ecc988 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -14,6 +14,7 @@ struct user_namespace {
 	struct hlist_head	uidhash_table[UIDHASH_SZ];
 	struct user_struct	*creator;
 	struct work_struct	destroyer;
+	unsigned int		proc_inum;
 };
 
 extern struct user_namespace init_user_ns;
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 4e5b021..03db764 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -44,6 +44,7 @@ struct uts_namespace {
 	struct kref kref;
 	struct new_utsname name;
 	struct user_namespace *user_ns;
+	unsigned int proc_inum;
 };
 extern struct uts_namespace init_uts_ns;
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index aef430d..850799f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -52,6 +52,8 @@ struct net {
 	struct list_head	cleanup_list;	/* namespaces on death row */
 	struct list_head	exit_list;	/* Use only net_mutex */
 
+	unsigned int		proc_inum;
+
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;