Skip to contentSkip to conversation

ptrace: kill __ptrace_detach(), fix ->exit_state check

PATCH In review Oleg Nesterov 2 participants 2 messages Jan 29, 2009 – Feb 5, 2009 ptrace support

lore
Share & tools
lore

Oleg Nesterov

author maintainer
#0 lore raw

PATCH 1/4 ptrace: kill __ptrace_detach(), fix ->exit_state check

Move the code from __ptrace_detach() to its single caller and kill this helper.

Also, fix the ->exit_state check, we shouldn't wake up EXIT_DEAD tasks. Actually, I think task_is_stopped_or_traced() makes more sense, but this needs another patch.

kernel/ptrace.c renamed from kernel/ptrace.c~1_KILL_DETACH +9 -13
@@ -235,16 +235,6 @@ out:
 	return retval;
 }
 
-static inline void __ptrace_detach(struct task_struct *child, unsigned int data)
-{
-	child->exit_code = data;
-	/* .. re-parent .. */
-	__ptrace_unlink(child);
-	/* .. and wake it up. */
-	if (child->exit_state != EXIT_ZOMBIE)
-		wake_up_process(child);
-}
-
 int ptrace_detach(struct task_struct *child, unsigned int data)
 {
 	if (!valid_signal(data))
@@ -254,10 +244,16 @@ int ptrace_detach(struct task_struct *ch
 	ptrace_disable(child);
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 
-	write_lock_irq(&tasklist_lock);
 	/* protect against de_thread()->release_task() */
-	if (child->ptrace)
-		__ptrace_detach(child, data);
+	write_lock_irq(&tasklist_lock);
+	if (child->ptrace) {
+		child->exit_code = data;
+
+		__ptrace_unlink(child);
+
+		if (!child->exit_state)
+			wake_up_process(child);
+	}
 	write_unlock_irq(&tasklist_lock);
 
 	return 0;
Acked-by on v1 1/4
#1 lore raw
Quoted 4 lines

Move the code from __ptrace_detach() to its single caller and kill this helper.

Also, fix the ->exit_state check, we shouldn't wake up EXIT_DEAD tasks.

Yes, though that is probably impossible anyway. Perhaps in a de_thread race, but probably harmlessly does nothing. Anyway, certainly fine to change the test to match all others of the same ilk.

Quoted 2 lines

Actually, I think task_is_stopped_or_traced() makes more sense, but this needs another patch.

Agreed. It is one of those nasty cases where the old semantics are "clearly" wrong, but it's very hard not to worry that some obscure combination of circumstances means that some common-enough case actually depends on the "wrong" wakeup.

Quoted 1 line

Thanks,
Roland