Messages in this thread Patch in this message | | | Date | Fri, 14 Nov 2014 02:38:20 +0100 | From | Oleg Nesterov <> | Subject | [PATCH 3/5] exit: wait: drop tasklist_lock before psig->c* accounting |
| |
wait_task_zombie() no longer needs tasklist_lock to accumulate the psig->c* counters, we can drop it right after cmpxchg(exit_state).
Signed-off-by: Oleg Nesterov <oleg@redhat.com> --- kernel/exit.c | 10 ++++------ 1 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/kernel/exit.c b/kernel/exit.c index 40d53de..e0914eb 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1003,6 +1003,10 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; + /* + * We own this thread, nobody else can reap it. + */ + read_unlock(&tasklist_lock); /* * Check thread_group_leader() to exclude the traced sub-threads. @@ -1062,12 +1066,6 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) spin_unlock_irq(¤t->sighand->siglock); } - /* - * Now we are sure this task is interesting, and no other - * thread can reap it because we its state == DEAD/TRACE. - */ - read_unlock(&tasklist_lock); - retval = wo->wo_rusage ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) -- 1.5.5.1
| |