[PATCH v2] ptrace: fix ptrace vs tasklist_lock race on PREEMPT_RT.

[Sebastian Andrzej Siewior <bigeasy@linutronix.de>]

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

|read_lock(&tasklist_lock) in ptrace_stop() is converted to sleeping
|lock on a PREEMPT_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
acquired to have stable view on ->__state and ->saved_state.

wait_task_inactive() needs to check both task states while waiting for the
expected task state. Should the expected task state be in ->saved_state then
the task is blocked on a sleeping lock. In this case wait_task_inactive() needs
to wait until the lock situtation has been resolved (the expected state is in
->__state). This ensures that the task is idle and does not wakeup as part of
lock resolving and races for instance with __switch_to_xtra() while the
debugger clears TIF_BLOCKSTEP() (noted by Oleg Nesterov).

[ Fix for ptrace_unfreeze_traced() by Oleg Nesterov ]

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2:
  - Use also ->saved_state in task_state_match_and_set().
  - Wait in wait_task_inactive() until the desired task state is in
    ->__state so that the task won't wake up a as part of lock
    resolving. Pointed out by Oleg Nesterov.

 include/linux/sched.h |  128 ++++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/ptrace.c       |   25 +++++----
 kernel/sched/core.c   |   11 +++-
 3 files changed, 146 insertions(+), 18 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,12 +118,8 @@ struct task_group;
 
 #define task_is_running(task)		(READ_ONCE((task)->__state) == TASK_RUNNING)
 
-#define task_is_traced(task)		((READ_ONCE(task->__state) & __TASK_TRACED) != 0)
-
 #define task_is_stopped(task)		((READ_ONCE(task->__state) & __TASK_STOPPED) != 0)
 
-#define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
-
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().
@@ -2009,6 +2005,130 @@ static inline int test_tsk_need_resched(
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+#ifdef CONFIG_PREEMPT_RT
+
+static inline bool task_state_match_and(struct task_struct *tsk, long state)
+{
+	unsigned long flags;
+	bool match = false;
+
+	raw_spin_lock_irqsave(&tsk->pi_lock, flags);
+	if (READ_ONCE(tsk->__state) & state)
+		match = true;
+	else if (tsk->saved_state & state)
+		match = true;
+	raw_spin_unlock_irqrestore(&tsk->pi_lock, flags);
+	return match;
+}
+
+static inline int __task_state_match_eq(struct task_struct *tsk, long state)
+{
+	int match = 0;
+
+	if (READ_ONCE(tsk->__state) == state)
+		match = 1;
+	else if (tsk->saved_state == state)
+		match = -1;
+
+	return match;
+}
+
+static inline int task_state_match_eq(struct task_struct *tsk, long state)
+{
+	unsigned long flags;
+	int match;
+
+	raw_spin_lock_irqsave(&tsk->pi_lock, flags);
+	match = __task_state_match_eq(tsk, state);
+	raw_spin_unlock_irqrestore(&tsk->pi_lock, flags);
+	return match;
+}
+
+static inline bool task_state_match_and_set(struct task_struct *tsk, long state,
+					    long new_state)
+{
+	unsigned long flags;
+	bool match = false;
+
+	raw_spin_lock_irqsave(&tsk->pi_lock, flags);
+	if (READ_ONCE(tsk->__state) & state) {
+		WRITE_ONCE(tsk->__state, new_state);
+		match = true;
+	} else if (tsk->saved_state & state) {
+		tsk->saved_state = new_state;
+		match = true;
+	}
+	raw_spin_unlock_irqrestore(&tsk->pi_lock, flags);
+	return match;
+}
+
+static inline bool task_state_match_eq_set(struct task_struct *tsk, long state,
+					   long new_state)
+{
+	unsigned long flags;
+	bool match = false;
+
+	raw_spin_lock_irqsave(&tsk->pi_lock, flags);
+	if (READ_ONCE(tsk->__state) == state) {
+		WRITE_ONCE(tsk->__state, new_state);
+		match = true;
+	} else if (tsk->saved_state == state) {
+		tsk->saved_state = new_state;
+		match = true;
+	}
+	raw_spin_unlock_irqrestore(&tsk->pi_lock, flags);
+	return match;
+}
+
+#else
+
+static inline bool task_state_match_and(struct task_struct *tsk, long state)
+{
+	return READ_ONCE(tsk->__state) & state;
+}
+
+static inline int __task_state_match_eq(struct task_struct *tsk, long state)
+{
+	return READ_ONCE(tsk->__state) == state;
+}
+
+static inline int task_state_match_eq(struct task_struct *tsk, long state)
+{
+	return __task_state_match_eq(tsk, state);
+}
+
+static inline bool task_state_match_and_set(struct task_struct *tsk, long state,
+					    long new_state)
+{
+	if (READ_ONCE(tsk->__state) & state) {
+		WRITE_ONCE(tsk->__state, new_state);
+		return true;
+	}
+	return false;
+}
+
+static inline bool task_state_match_eq_set(struct task_struct *tsk, long state,
+					   long new_state)
+{
+	if (READ_ONCE(tsk->__state) == state) {
+		WRITE_ONCE(tsk->__state, new_state);
+		return true;
+	}
+	return false;
+}
+
+#endif
+
+static inline bool task_is_traced(struct task_struct *tsk)
+{
+	return task_state_match_and(tsk, __TASK_TRACED);
+}
+
+static inline bool task_is_stopped_or_traced(struct task_struct *tsk)
+{
+	return task_state_match_and(tsk, __TASK_STOPPED | __TASK_TRACED);
+}
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -195,10 +195,10 @@ static bool ptrace_freeze_traced(struct
 		return ret;
 
 	spin_lock_irq(&task->sighand->siglock);
-	if (task_is_traced(task) && !looks_like_a_spurious_pid(task) &&
-	    !__fatal_signal_pending(task)) {
-		WRITE_ONCE(task->__state, __TASK_TRACED);
-		ret = true;
+	if (!looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) {
+
+		ret = task_state_match_and_set(task, __TASK_TRACED,
+					       __TASK_TRACED);
 	}
 	spin_unlock_irq(&task->sighand->siglock);
 
@@ -207,7 +207,10 @@ static bool ptrace_freeze_traced(struct
 
 static void ptrace_unfreeze_traced(struct task_struct *task)
 {
-	if (READ_ONCE(task->__state) != __TASK_TRACED)
+	bool frozen;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+	    READ_ONCE(task->__state) != __TASK_TRACED)
 		return;
 
 	WARN_ON(!task->ptrace || task->parent != current);
@@ -217,12 +220,12 @@ static void ptrace_unfreeze_traced(struc
 	 * Recheck state under the lock to close this race.
 	 */
 	spin_lock_irq(&task->sighand->siglock);
-	if (READ_ONCE(task->__state) == __TASK_TRACED) {
-		if (__fatal_signal_pending(task))
-			wake_up_state(task, __TASK_TRACED);
-		else
-			WRITE_ONCE(task->__state, TASK_TRACED);
-	}
+
+	frozen = task_state_match_eq_set(task, __TASK_TRACED, TASK_TRACED);
+
+	if (frozen && __fatal_signal_pending(task))
+		wake_up_state(task, __TASK_TRACED);
+
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3219,6 +3219,8 @@ unsigned long wait_task_inactive(struct
 	struct rq *rq;
 
 	for (;;) {
+		int match_type = 0;
+
 		/*
 		 * We do the initial early heuristics without holding
 		 * any task-queue locks at all. We'll only try to get
@@ -3239,7 +3241,8 @@ unsigned long wait_task_inactive(struct
 		 * is actually now running somewhere else!
 		 */
 		while (task_running(rq, p)) {
-			if (match_state && unlikely(READ_ONCE(p->__state) != match_state))
+			if (match_state &&
+			    unlikely(!task_state_match_eq(p, match_state)))
 				return 0;
 			cpu_relax();
 		}
@@ -3254,7 +3257,9 @@ unsigned long wait_task_inactive(struct
 		running = task_running(rq, p);
 		queued = task_on_rq_queued(p);
 		ncsw = 0;
-		if (!match_state || READ_ONCE(p->__state) == match_state)
+		if (match_state)
+			match_type = __task_state_match_eq(p, match_state);
+		if (!match_state || match_type)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
 		task_rq_unlock(rq, p, &rf);
 
@@ -3284,7 +3289,7 @@ unsigned long wait_task_inactive(struct
 		 * running right now), it's preempted, and we should
 		 * yield - it could be a while.
 		 */
-		if (unlikely(queued)) {
+		if (unlikely(queued || match_type < 0)) {
 			ktime_t to = NSEC_PER_SEC / HZ;
 
 			set_current_state(TASK_UNINTERRUPTIBLE);