ptrace: fix ptrace vs tasklist_lock race

As explained by Alexander Fyodorov <halcy@yandex.ru>:

|read_lock(&tasklist_lock) in ptrace_stop() is converted to mutex on RT kernel,
|and it can remove __TASK_TRACED from task->state (by moving  it to
|task->saved_state). If parent does wait() on child followed by a sys_ptrace
|call, the following race can happen:
|
|- child sets __TASK_TRACED in ptrace_stop()
|- parent does wait() which eventually calls wait_task_stopped() and returns
|  child's pid
|- child blocks on read_lock(&tasklist_lock) in ptrace_stop() and moves
|  __TASK_TRACED flag to saved_state
|- parent calls sys_ptrace, which calls ptrace_check_attach() and wait_task_inactive()

The patch is based on his initial patch where an additional check is
added in case the __TASK_TRACED moved to ->saved_state. The pi_lock is
taken in case the caller is interrupted between looking into ->state and
->saved_state.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

1 files changed, 16 insertions, 3 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 72801e0..ae6b232 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1024,6 +1024,18 @@ struct migration_arg {
 
 static int migration_cpu_stop(void *data);
 
+static bool check_task_state(struct task_struct *p, long match_state)
+{
+	bool match = false;
+
+	raw_spin_lock_irq(&p->pi_lock);
+	if (p->state == match_state || p->saved_state == match_state)
+		match = true;
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	return match;
+}
+
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
@@ -1068,7 +1080,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * is actually now running somewhere else!
 		 */
 		while (task_running(rq, p)) {
-			if (match_state && unlikely(p->state != match_state))
+			if (match_state && !check_task_state(p, match_state))
 				return 0;
 			cpu_relax();
 		}
@@ -1083,7 +1095,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		running = task_running(rq, p);
 		on_rq = p->on_rq;
 		ncsw = 0;
-		if (!match_state || p->state == match_state)
+		if (!match_state || p->state == match_state
+		    || p->saved_state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
 		task_rq_unlock(rq, p, &flags);
 
@@ -1579,7 +1592,7 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-	WARN_ON(task_is_stopped_or_traced(p));
+	WARN_ON(__task_is_stopped_or_traced(p));
 	return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);