pid namespaces: miscellaneous preparations for pid namespaces

* remove pid.h from pid_namespaces.h;
* rework is_(cgroup|global)_init;
* optimize (get|put)_pid_ns for init_pid_ns;
* declare task_child_reaper to return actual reaper.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 416d4e4..0135c76 100644 (file)
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -4,7 +4,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/threads.h>
-#include <linux/pid.h>
 #include <linux/nsproxy.h>
 #include <linux/kref.h>
 
@@ -32,7 +31,8 @@ extern struct pid_namespace init_pid_ns;
 
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
-       kref_get(&ns->kref);
+       if (ns != &init_pid_ns)
+               kref_get(&ns->kref);
        return ns;
 }
 
@@ -41,7 +41,8 @@ extern void free_pid_ns(struct kref *kref);
 
 static inline void put_pid_ns(struct pid_namespace *ns)
 {
-       kref_put(&ns->kref, free_pid_ns);
+       if (ns != &init_pid_ns)
+               kref_put(&ns->kref, free_pid_ns);
 }
 
 static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
@@ -51,7 +52,8 @@ static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 
 static inline struct task_struct *task_child_reaper(struct task_struct *tsk)
 {
-       return init_pid_ns.child_reaper;
+       BUG_ON(tsk != current);
+       return tsk->nsproxy->pid_ns->child_reaper;
 }
 
 #endif /* _LINUX_PID_NS_H */

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 511cc45..b0bf326 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1329,19 +1329,17 @@ static inline int pid_alive(struct task_struct *p)
  * @tsk: Task structure to be checked.
  *
  * Check if a task structure is the first user space task the kernel created.
- *
- * TODO: We should inline this function after some cleanups in pid_namespace.h
  */
-extern int is_global_init(struct task_struct *tsk);
+static inline int is_global_init(struct task_struct *tsk)
+{
+       return tsk->pid == 1;
+}
 
 /*
  * is_container_init:
  * check whether in the task is init in its own pid namespace.
  */
-static inline int is_container_init(struct task_struct *tsk)
-{
-       return tsk->pid == 1;
-}
+extern int is_container_init(struct task_struct *tsk);
 
 extern struct pid *cad_pid;
 

diff --git a/kernel/pid.c b/kernel/pid.c
index a2b4cbb..4b17acd 100644 (file)
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -73,10 +73,20 @@ struct pid_namespace init_pid_ns = {
 };
 EXPORT_SYMBOL_GPL(init_pid_ns);
 
-int is_global_init(struct task_struct *tsk)
+int is_container_init(struct task_struct *tsk)
 {
-       return tsk == init_pid_ns.child_reaper;
+       int ret = 0;
+       struct pid *pid;
+
+       rcu_read_lock();
+       pid = task_pid(tsk);
+       if (pid != NULL && pid->numbers[pid->level].nr == 1)
+               ret = 1;
+       rcu_read_unlock();
+
+       return ret;
 }
+EXPORT_SYMBOL(is_container_init);
 
 /*
  * Note: disable interrupts while the pidmap_lock is held as an
@@ -192,8 +202,7 @@ fastcall void put_pid(struct pid *pid)
        if ((atomic_read(&pid->count) == 1) ||
             atomic_dec_and_test(&pid->count)) {
                kmem_cache_free(ns->pid_cachep, pid);
-               if (ns != &init_pid_ns)
-                       put_pid_ns(ns);
+               put_pid_ns(ns);
        }
 }
 EXPORT_SYMBOL_GPL(put_pid);
@@ -244,9 +253,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
                tmp = tmp->parent;
        }
 
-       if (ns != &init_pid_ns)
-               get_pid_ns(ns);
-
+       get_pid_ns(ns);
        pid->level = ns->level;
        pid->nr = pid->numbers[0].nr;
        atomic_set(&pid->count, 1);