1 files changed, 38 insertions, 30 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 4db020015f14..d8bd3b425fa7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -52,6 +52,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/oom.h>
 #include <linux/writeback.h>
+#include <linux/shm.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -424,7 +425,7 @@ void daemonize(const char *name, ...)
          */
         exit_mm(current);
         /*
-         * We don't want to have TIF_FREEZE set if the system-wide hibernation
+         * We don't want to get frozen, in case system-wide hibernation
          * or suspend transition begins right now.
          */
         current->flags |= (PF_NOFREEZE | PF_KTHREAD);
@@ -686,11 +687,11 @@ static void exit_mm(struct task_struct * tsk)
 }
 
 /*
- * When we die, we re-parent all our children.
- * Try to give them to another thread in our thread
- * group, and if no such member exists, give it to
- * the child reaper process (ie "init") in our pid
- * space.
+ * When we die, we re-parent all our children, and try to:
+ * 1. give them to another thread in our thread group, if such a member exists
+ * 2. give it to the first ancestor process which prctl'd itself as a
+ *    child_subreaper for its children (like a service manager)
+ * 3. give it to the init process (PID 1) in our pid namespace
  */
 static struct task_struct *find_new_reaper(struct task_struct *father)
         __releases(&tasklist_lock)
@@ -710,8 +711,11 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 
         if (unlikely(pid_ns->child_reaper == father)) {
                 write_unlock_irq(&tasklist_lock);
-                if (unlikely(pid_ns == &init_pid_ns))
-                        panic("Attempted to kill init!");
+                if (unlikely(pid_ns == &init_pid_ns)) {
+                        panic("Attempted to kill init! exitcode=0x%08x\n",
+                                father->signal->group_exit_code ?:
+                                        father->exit_code);
+                }
 
                 zap_pid_ns_processes(pid_ns);
                 write_lock_irq(&tasklist_lock);
@@ -721,6 +725,29 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
                  * forget_original_parent() must move them somewhere.
                  */
                 pid_ns->child_reaper = init_pid_ns.child_reaper;
+        } else if (father->signal->has_child_subreaper) {
+                struct task_struct *reaper;
+
+                /*
+                 * Find the first ancestor marked as child_subreaper.
+                 * Note that the code below checks same_thread_group(reaper,
+                 * pid_ns->child_reaper).  This is what we need to DTRT in a
+                 * PID namespace. However we still need the check above, see
+                 * http://marc.info/?l=linux-kernel&m=131385460420380
+                 */
+                for (reaper = father->real_parent;
+                     reaper != &init_task;
+                     reaper = reaper->real_parent) {
+                        if (same_thread_group(reaper, pid_ns->child_reaper))
+                                break;
+                        if (!reaper->signal->is_child_subreaper)
+                                continue;
+                        thread = reaper;
+                        do {
+                                if (!(thread->flags & PF_EXITING))
+                                        return reaper;
+                        } while_each_thread(reaper, thread);
+                }
         }
 
         return pid_ns->child_reaper;
@@ -818,25 +845,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
         if (group_dead)
                 kill_orphaned_pgrp(tsk->group_leader, NULL);
 
-        /* Let father know we died
-         *
-         * Thread signals are configurable, but you aren't going to use
-         * that to send signals to arbitrary processes.
-         * That stops right now.
-         *
-         * If the parent exec id doesn't match the exec id we saved
-         * when we started then we know the parent has changed security
-         * domain.
-         *
-         * If our self_exec id doesn't match our parent_exec_id then
-         * we have changed execution domain as these two values started
-         * the same after a fork.
-         */
-        if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
-            (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
-             tsk->self_exec_id != tsk->parent_exec_id))
-                tsk->exit_signal = SIGCHLD;
-
         if (unlikely(tsk->ptrace)) {
                 int sig = thread_group_leader(tsk) &&
                                 thread_group_empty(tsk) &&
@@ -935,8 +943,6 @@ void do_exit(long code)
                 schedule();
         }
 
-        exit_irq_thread();
-
         exit_signals(tsk);  /* sets PF_EXITING */
         /*
          * tsk->flags are checked in the futex code to protect against
@@ -945,6 +951,8 @@ void do_exit(long code)
         smp_mb();
         raw_spin_unlock_wait(&tsk->pi_lock);
 
+        exit_irq_thread();
+
         if (unlikely(in_atomic()))
                 printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
                                 current->comm, task_pid_nr(current),
@@ -953,7 +961,7 @@ void do_exit(long code)
         acct_update_integrals(tsk);
         /* sync mm's RSS info before statistics gathering */
         if (tsk->mm)
-                sync_mm_rss(tsk, tsk->mm);
+                sync_mm_rss(tsk->mm);
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
                 hrtimer_cancel(&tsk->signal->real_timer);