[PATCH] namespaces: utsname: implement utsname namespaces

This patch defines the uts namespace and some manipulators.
Adds the uts namespace to task_struct, and initializes a
system-wide init namespace.

It leaves a #define for system_utsname so sysctl will compile.
This define will be removed in a separate patch.

[akpm@osdl.org: build fix, cleanup]
Signed-off-by: Serge Hallyn <serue@us.ibm.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Andrey Savochkin <saw@sw.ru>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/init_task.h

@@ -4,6 +4,7 @@
 #include <linux/file.h>
 #include <linux/rcupdate.h>
 #include <linux/irqflags.h>
+#include <linux/utsname.h>
 #include <linux/lockdep.h>
 
 #define INIT_FDTABLE \
@@ -72,6 +73,7 @@ extern struct nsproxy init_nsproxy;
 #define INIT_NSPROXY(nsproxy) {						\
 	.count		= ATOMIC_INIT(1),				\
 	.nslock		= SPIN_LOCK_UNLOCKED,				\
+	.uts_ns		= &init_uts_ns,					\
 	.namespace	= NULL,						\
 }
 

include/linux/nsproxy.h

@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 
 struct namespace;
+struct uts_namespace;
 
 /*
  * A structure to contain pointers to all per-process
@@ -21,6 +22,7 @@ struct namespace;
 struct nsproxy {
 	atomic_t count;
 	spinlock_t nslock;
+	struct uts_namespace *uts_ns;
 	struct namespace *namespace;
 };
 extern struct nsproxy init_nsproxy;

include/linux/sched.h

@@ -753,6 +753,7 @@ static inline void prefetch_stack(struct task_struct *t) { }
 struct audit_context;		/* See audit.c */
 struct mempolicy;
 struct pipe_inode_info;
+struct uts_namespace;
 
 enum sleep_type {
 	SLEEP_NORMAL,

include/linux/utsname.h

@@ -1,6 +1,11 @@
 #ifndef _LINUX_UTSNAME_H
 #define _LINUX_UTSNAME_H
 
+#include <linux/sched.h>
+#include <linux/kref.h>
+#include <linux/nsproxy.h>
+#include <asm/atomic.h>
+
 #define __OLD_UTS_LEN 8
 
 struct oldold_utsname {
@@ -30,17 +35,46 @@ struct new_utsname {
 	char domainname[65];
 };
 
-extern struct new_utsname system_utsname;
+struct uts_namespace {
+	struct kref kref;
+	struct new_utsname name;
+};
+extern struct uts_namespace init_uts_ns;
+
+static inline void get_uts_ns(struct uts_namespace *ns)
+{
+	kref_get(&ns->kref);
+}
+
+#ifdef CONFIG_UTS_NS
+extern int copy_utsname(int flags, struct task_struct *tsk);
+extern void free_uts_ns(struct kref *kref);
+
+static inline void put_uts_ns(struct uts_namespace *ns)
+{
+	kref_put(&ns->kref, free_uts_ns);
+}
+#else
+static inline int copy_utsname(int flags, struct task_struct *tsk)
+{
+	return 0;
+}
+static inline void put_uts_ns(struct uts_namespace *ns)
+{
+}
+#endif
 
 static inline struct new_utsname *utsname(void)
 {
-	return &system_utsname;
+	return &current->nsproxy->uts_ns->name;
 }
 
 static inline struct new_utsname *init_utsname(void)
 {
-	return &system_utsname;
+	return &init_uts_ns.name;
 }
 
+#define system_utsname init_uts_ns.name
+
 extern struct rw_semaphore uts_sem;
 #endif

init/Kconfig

@@ -182,6 +182,14 @@ config TASK_DELAY_ACCT
 
 	  Say N if unsure.
 
+config UTS_NS
+	bool "UTS Namespaces"
+	default n
+	help
+	  Support uts namespaces.  This allows containers, i.e.
+	  vservers, to use uts namespaces to provide different
+	  uts info for different servers.  If unsure, say N.
+
 config AUDIT
 	bool "Auditing support"
 	depends on NET

init/version.c

@@ -12,22 +12,27 @@
 #include <linux/utsname.h>
 #include <linux/utsrelease.h>
 #include <linux/version.h>
+#include <linux/sched.h>
 
 #define version(a) Version_ ## a
 #define version_string(a) version(a)
 
 int version_string(LINUX_VERSION_CODE);
 
-struct new_utsname system_utsname = {
-	.sysname	= UTS_SYSNAME,
-	.nodename	= UTS_NODENAME,
-	.release	= UTS_RELEASE,
-	.version	= UTS_VERSION,
-	.machine	= UTS_MACHINE,
-	.domainname	= UTS_DOMAINNAME,
+struct uts_namespace init_uts_ns = {
+	.kref = {
+		.refcount	= ATOMIC_INIT(2),
+	},
+	.name = {
+		.sysname	= UTS_SYSNAME,
+		.nodename	= UTS_NODENAME,
+		.release	= UTS_RELEASE,
+		.version	= UTS_VERSION,
+		.machine	= UTS_MACHINE,
+		.domainname	= UTS_DOMAINNAME,
+	},
 };
-
-EXPORT_SYMBOL(system_utsname);
+EXPORT_SYMBOL_GPL(init_uts_ns);
 
 const char linux_banner[] =
 	"Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@"

kernel/Makefile

@@ -48,6 +48,7 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
+obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 

kernel/nsproxy.c

@@ -14,6 +14,7 @@
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
 #include <linux/namespace.h>
+#include <linux/utsname.h>
 
 struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
 
@@ -59,6 +60,8 @@ struct nsproxy *dup_namespaces(struct nsproxy *orig)
 	if (ns) {
 		if (ns->namespace)
 			get_namespace(ns->namespace);
+		if (ns->uts_ns)
+			get_uts_ns(ns->uts_ns);
 	}
 
 	return ns;
@@ -97,6 +100,15 @@ int copy_namespaces(int flags, struct task_struct *tsk)
 		goto out;
 	}
 
+	err = copy_utsname(flags, tsk);
+	if (err) {
+		if (new_ns->namespace)
+			put_namespace(new_ns->namespace);
+		tsk->nsproxy = old_ns;
+		put_nsproxy(new_ns);
+		goto out;
+	}
+
 out:
 	put_nsproxy(old_ns);
 	return err;
@@ -106,5 +118,7 @@ void free_nsproxy(struct nsproxy *ns)
 {
 		if (ns->namespace)
 			put_namespace(ns->namespace);
+		if (ns->uts_ns)
+			put_uts_ns(ns->uts_ns);
 		kfree(ns);
 }

kernel/utsname.c

@@ -0,0 +1,42 @@
+/*
+ *  Copyright (C) 2004 IBM Corporation
+ *
+ *  Author: Serge Hallyn <serue@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation, version 2 of the
+ *  License.
+ */
+
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
+
+/*
+ * Copy task tsk's utsname namespace, or clone it if flags
+ * specifies CLONE_NEWUTS.  In latter case, changes to the
+ * utsname of this process won't be seen by parent, and vice
+ * versa.
+ */
+int copy_utsname(int flags, struct task_struct *tsk)
+{
+	struct uts_namespace *old_ns = tsk->nsproxy->uts_ns;
+	int err = 0;
+
+	if (!old_ns)
+		return 0;
+
+	get_uts_ns(old_ns);
+
+	return err;
+}
+
+void free_uts_ns(struct kref *kref)
+{
+	struct uts_namespace *ns;
+
+	ns = container_of(kref, struct uts_namespace, kref);
+	kfree(ns);
+}