[PATCH] namespaces: utsname: implement CLONE_NEWUTS flag

Implement a CLONE_NEWUTS flag, and use it at clone and sys_unshare.

[clg@fr.ibm.com: IPC unshare fix]
[bunk@stusta.de: 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: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 83 insertions, 4 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 46d6f5be72f2..a973e7012315 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -24,6 +24,7 @@
 #define CLONE_UNTRACED          0x00800000      /* set if the tracing process can't force CLONE_PTRACE on this clone */
 #define CLONE_CHILD_SETTID      0x01000000      /* set the TID in the child */
 #define CLONE_STOPPED           0x02000000      /* Start in stopped state */
+#define CLONE_NEWUTS            0x04000000      /* New utsname group? */
 
 /*
  * Scheduling policies
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 99e522369f4f..02e4b6972064 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -47,6 +47,8 @@ static inline void get_uts_ns(struct uts_namespace *ns)
 }
 
 #ifdef CONFIG_UTS_NS
+extern int unshare_utsname(unsigned long unshare_flags,
+                                struct uts_namespace **new_uts);
 extern int copy_utsname(int flags, struct task_struct *tsk);
 extern void free_uts_ns(struct kref *kref);
 
@@ -55,6 +57,15 @@ static inline void put_uts_ns(struct uts_namespace *ns)
         kref_put(&ns->kref, free_uts_ns);
 }
 #else
+static inline int unshare_utsname(unsigned long unshare_flags,
+                        struct uts_namespace **new_uts)
+{
+        if (unshare_flags & CLONE_NEWUTS)
+                return -EINVAL;
+
+        return 0;
+}
+
 static inline int copy_utsname(int flags, struct task_struct *tsk)
 {
         return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 33fcf0733ca6..c08cf05dd59b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1607,13 +1607,14 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
         struct files_struct *fd, *new_fd = NULL;
         struct sem_undo_list *new_ulist = NULL;
         struct nsproxy *new_nsproxy, *old_nsproxy;
+        struct uts_namespace *uts, *new_uts = NULL;
 
         check_unshare_flags(&unshare_flags);
 
         /* Return -EINVAL for all unsupported flags */
         err = -EINVAL;
         if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
-                                CLONE_VM|CLONE_FILES|CLONE_SYSVSEM))
+                                CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|CLONE_NEWUTS))
                 goto bad_unshare_out;
 
         if ((err = unshare_thread(unshare_flags)))
@@ -1630,14 +1631,17 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
                 goto bad_unshare_cleanup_vm;
         if ((err = unshare_semundo(unshare_flags, &new_ulist)))
                 goto bad_unshare_cleanup_fd;
+        if ((err = unshare_utsname(unshare_flags, &new_uts)))
+                goto bad_unshare_cleanup_semundo;
 
-        if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) {
+        if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist ||
+                                new_uts) {
 
                 old_nsproxy = current->nsproxy;
                 new_nsproxy = dup_namespaces(old_nsproxy);
                 if (!new_nsproxy) {
                         err = -ENOMEM;
-                        goto bad_unshare_cleanup_semundo;
+                        goto bad_unshare_cleanup_uts;
                 }
 
                 task_lock(current);
@@ -1676,10 +1680,20 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
                         new_fd = fd;
                 }
 
+                if (new_uts) {
+                        uts = current->nsproxy->uts_ns;
+                        current->nsproxy->uts_ns = new_uts;
+                        new_uts = uts;
+                }
+
                 task_unlock(current);
                 put_nsproxy(old_nsproxy);
         }
 
+bad_unshare_cleanup_uts:
+        if (new_uts)
+                put_uts_ns(new_uts);
+
 bad_unshare_cleanup_semundo:
 bad_unshare_cleanup_fd:
         if (new_fd)
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 47c19280c55b..8246813335cc 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -82,7 +82,7 @@ int copy_namespaces(int flags, struct task_struct *tsk)
 
         get_nsproxy(old_ns);
 
-        if (!(flags & CLONE_NEWNS))
+        if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS)))
                 return 0;
 
         new_ns = clone_namespaces(old_ns);
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 1824384ecfa3..c859164a6993 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -15,6 +15,41 @@
 #include <linux/version.h>
 
 /*
+ * Clone a new ns copying an original utsname, setting refcount to 1
+ * @old_ns: namespace to clone
+ * Return NULL on error (failure to kmalloc), new ns otherwise
+ */
+static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
+{
+        struct uts_namespace *ns;
+
+        ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+        if (ns) {
+                memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+                kref_init(&ns->kref);
+        }
+        return ns;
+}
+
+/*
+ * unshare the current process' utsname namespace.
+ * called only in sys_unshare()
+ */
+int unshare_utsname(unsigned long unshare_flags, struct uts_namespace **new_uts)
+{
+        if (unshare_flags & CLONE_NEWUTS) {
+                if (!capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+
+                *new_uts = clone_uts_ns(current->nsproxy->uts_ns);
+                if (!*new_uts)
+                        return -ENOMEM;
+        }
+
+        return 0;
+}
+
+/*
  * 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
@@ -23,6 +58,7 @@
 int copy_utsname(int flags, struct task_struct *tsk)
 {
         struct uts_namespace *old_ns = tsk->nsproxy->uts_ns;
+        struct uts_namespace *new_ns;
         int err = 0;
 
         if (!old_ns)
@@ -30,6 +66,23 @@ int copy_utsname(int flags, struct task_struct *tsk)
 
         get_uts_ns(old_ns);
 
+        if (!(flags & CLONE_NEWUTS))
+                return 0;
+
+        if (!capable(CAP_SYS_ADMIN)) {
+                err = -EPERM;
+                goto out;
+        }
+
+        new_ns = clone_uts_ns(old_ns);
+        if (!new_ns) {
+                err = -ENOMEM;
+                goto out;
+        }
+        tsk->nsproxy->uts_ns = new_ns;
+
+out:
+        put_uts_ns(old_ns);
         return err;
 }