pid namespaces: define is_global_init() and is_container_init()

is_init() is an ambiguous name for the pid==1 check.  Split it into
is_global_init() and is_container_init().

A cgroup init has it's tsk->pid == 1.

A global init also has it's tsk->pid == 1 and it's active pid namespace
is the init_pid_ns.  But rather than check the active pid namespace,
compare the task structure with 'init_pid_ns.child_reaper', which is
initialized during boot to the /sbin/init process and never changes.

Changelog:

	2.6.22-rc4-mm2-pidns1:
	- Use 'init_pid_ns.child_reaper' to determine if a given task is the
	  global init (/sbin/init) process. This would improve performance
	  and remove dependence on the task_pid().

	2.6.21-mm2-pidns2:

	- [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc,
	  ppc,avr32}/traps.c for the _exception() call to is_global_init().
	  This way, we kill only the cgroup if the cgroup's init has a
	  bug rather than force a kernel panic.

[akpm@linux-foundation.org: fix comment]
[sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c]
[bunk@stusta.de: kernel/pid.c: remove unused exports]
[sukadev@us.ibm.com: Fix capability.c to work with threaded init]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Acked-by: Pavel Emelianov <xemul@openvz.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Herbert Poetzel <herbert@13thfloor.at>
Cc: Kirill Korotaev <dev@sw.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 11 insertions, 5 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index cbc5fd60c0f3..f02ad47320b9 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
 
 /*
@@ -129,7 +130,7 @@ static inline int cap_set_all(kernel_cap_t *effective,
      int found = 0;
 
      do_each_thread(g, target) {
-             if (target == current || is_init(target))
+             if (target == current || is_container_init(target->group_leader))
                      continue;
              found = 1;
              if (security_capset_check(target, effective, inheritable,
diff --git a/kernel/exit.c b/kernel/exit.c
index d1eddc753fe3..d22aefabb129 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -221,7 +221,7 @@ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignor
         do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
                 if (p == ignored_task
                                 || p->exit_state
-                                || is_init(p->real_parent))
+                                || is_global_init(p->real_parent))
                         continue;
                 if (task_pgrp(p->real_parent) != pgrp &&
                     task_session(p->real_parent) == task_session(p)) {
diff --git a/kernel/kexec.c b/kernel/kexec.c
index e9f1b4ea504d..fbffdb457cce 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -51,7 +51,7 @@ struct resource crashk_res = {
 
 int kexec_should_crash(struct task_struct *p)
 {
-        if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
+        if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
                 return 1;
         return 0;
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index 78c0dbffde65..bb0785109d39 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -70,6 +70,11 @@ struct pid_namespace init_pid_ns = {
         .child_reaper = &init_task
 };
 
+int is_global_init(struct task_struct *tsk)
+{
+        return tsk == init_pid_ns.child_reaper;
+}
+
 /*
  * Note: disable interrupts while the pidmap_lock is held as an
  * interrupt might come in and do read_lock(&tasklist_lock).
diff --git a/kernel/signal.c b/kernel/signal.c
index 0a6d3726cb80..8214ffad54bc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -256,7 +256,7 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
-        if (is_init(tsk))
+        if (is_global_init(tsk))
                 return 1;
         if (tsk->ptrace & PT_PTRACED)
                 return 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 067554bda8b7..44868e4df1d3 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1888,7 +1888,7 @@ int proc_dointvec_bset(struct ctl_table *table, int write, struct file *filp,
                 return -EPERM;
         }
 
-        op = is_init(current) ? OP_SET : OP_AND;
+        op = is_global_init(current) ? OP_SET : OP_AND;
         return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
                                 do_proc_dointvec_bset_conv,&op);
 }