UBUNTU: Ubuntu-2.6.38-12.51

[linux-flexiantxendom0-natty.git] / kernel / exit.c

diff --git a/kernel/exit.c b/kernel/exit.c
index b194feb..557a348 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -69,7 +69,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 
                list_del_rcu(&p->tasks);
                list_del_init(&p->sibling);
-               __get_cpu_var(process_counts)--;
+               __this_cpu_dec(process_counts);
        }
        list_del_rcu(&p->thread_group);
 }
@@ -96,6 +96,14 @@ static void __exit_signal(struct task_struct *tsk)
                sig->tty = NULL;
        } else {
                /*
+                * This can only happen if the caller is de_thread().
+                * FIXME: this is the temporary hack, we should teach
+                * posix-cpu-timers to handle this case correctly.
+                */
+               if (unlikely(has_group_leader_pid(tsk)))
+                       posix_cpu_timers_exit_group(tsk);
+
+               /*
                 * If there is any task waiting for the group exit
                 * then notify it:
                 */
@@ -906,6 +914,15 @@ NORET_TYPE void do_exit(long code)
        if (unlikely(!tsk->pid))
                panic("Attempted to kill the idle task!");
 
+       /*
+        * If do_exit is called because this processes oopsed, it's possible
+        * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
+        * continuing. Amongst other possible reasons, this is to prevent
+        * mm_release()->clear_child_tid() from writing to a user-controlled
+        * kernel address.
+        */
+       set_fs(USER_DS);
+
        tracehook_report_exit(&code);
 
        validate_creds_for_do_exit(tsk);
@@ -977,6 +994,15 @@ NORET_TYPE void do_exit(long code)
        exit_fs(tsk);
        check_stack_usage();
        exit_thread();
+
+       /*
+        * Flush inherited counters to the parent - before the parent
+        * gets woken up by child-exit notifications.
+        *
+        * because of cgroup mode, must be called before cgroup_exit()
+        */
+       perf_event_exit_task(tsk);
+
        cgroup_exit(tsk, 1);
 
        if (group_dead)
@@ -989,12 +1015,7 @@ NORET_TYPE void do_exit(long code)
        /*
         * FIXME: do that only when needed, using sched_exit tracepoint
         */
-       flush_ptrace_hw_breakpoint(tsk);
-       /*
-        * Flush inherited counters to the parent - before the parent
-        * gets woken up by child-exit notifications.
-        */
-       perf_event_exit_task(tsk);
+       ptrace_put_breakpoints(tsk);
 
        exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA