user namespace: add the framework

Basically, it will allow a process to unshare its user_struct table,
resetting at the same time its own user_struct and all the associated
accounting.

A new root user (uid == 0) is added to the user namespace upon creation.
Such root users have full privileges and it seems that theses privileges
should be controlled through some means (process capabilities ?)

The unshare is not included in this patch.

Changes since [try #4]:
	- Updated get_user_ns and put_user_ns to accept NULL, and
	  get_user_ns to return the namespace.

Changes since [try #3]:
	- moved struct user_namespace to files user_namespace.{c,h}

Changes since [try #2]:
	- removed struct user_namespace* argument from find_user()

Changes since [try #1]:
	- removed struct user_namespace* argument from find_user()
	- added a root_user per user namespace

Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: Pavel Emelianov <xemul@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: James Morris <jmorris@namei.org>
Cc: Andrew Morgan <agm@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 62 insertions, 1 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 276ccaa2670..cab741c2d60 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -8,6 +8,7 @@
 #include <linux/lockdep.h>
 #include <linux/ipc.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 
 #define INIT_FDTABLE \
 {							\
@@ -78,6 +79,7 @@ extern struct nsproxy init_nsproxy;
 	.uts_ns		= &init_uts_ns,					\
 	.mnt_ns		= NULL,						\
 	INIT_IPC_NS(ipc_ns)						\
+	.user_ns	= &init_user_ns,				\
 }
 
 #define INIT_SIGHAND(sighand) {						\
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 189e0dc993a..6d179a397bf 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -28,6 +28,7 @@ struct nsproxy {
 	struct ipc_namespace *ipc_ns;
 	struct mnt_namespace *mnt_ns;
 	struct pid_namespace *pid_ns;
+	struct user_namespace *user_ns;
 };
 extern struct nsproxy init_nsproxy;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b579624477f..c667255d70d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -287,6 +287,7 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
 
 struct nsproxy;
+struct user_namespace;
 
 /* Maximum number of active map areas.. This is a random (large) number */
 #define DEFAULT_MAX_MAP_COUNT	65536
@@ -1408,7 +1409,7 @@ extern struct task_struct *find_task_by_pid_type(int type, int pid);
 extern void __set_special_pids(pid_t session, pid_t pgrp);
 
 /* per-UID process charging. */
-extern struct user_struct * alloc_uid(uid_t);
+extern struct user_struct * alloc_uid(struct user_namespace *, uid_t);
 static inline struct user_struct *get_uid(struct user_struct *u)
 {
 	atomic_inc(&u->__count);
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
new file mode 100644
index 00000000000..92a45867ecf
--- /dev/null
+++ b/include/linux/user_namespace.h
@@ -0,0 +1,57 @@
+#ifndef _LINUX_USER_NAMESPACE_H
+#define _LINUX_USER_NAMESPACE_H
+
+#include <linux/kref.h>
+#include <linux/nsproxy.h>
+#include <linux/sched.h>
+
+#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 8)
+#define UIDHASH_SZ	(1 << UIDHASH_BITS)
+
+struct user_namespace {
+	struct kref		kref;
+	struct list_head	uidhash_table[UIDHASH_SZ];
+	struct user_struct	*root_user;
+};
+
+extern struct user_namespace init_user_ns;
+
+#ifdef CONFIG_USER_NS
+
+static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
+{
+	if (ns)
+		kref_get(&ns->kref);
+	return ns;
+}
+
+extern struct user_namespace *copy_user_ns(int flags,
+					   struct user_namespace *old_ns);
+extern void free_user_ns(struct kref *kref);
+
+static inline void put_user_ns(struct user_namespace *ns)
+{
+	if (ns)
+		kref_put(&ns->kref, free_user_ns);
+}
+
+#else
+
+static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
+{
+	return &init_user_ns;
+}
+
+static inline struct user_namespace *copy_user_ns(int flags,
+						  struct user_namespace *old_ns)
+{
+	return NULL;
+}
+
+static inline void put_user_ns(struct user_namespace *ns)
+{
+}
+
+#endif
+
+#endif /* _LINUX_USER_H */