From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 22 Jun 2022 12:27:05 +0200
Subject: [PATCH] sched: Consider task_struct::saved_state in
 wait_task_inactive().

Ptrace is using wait_task_inactive() to wait for the tracee to reach a
certain task state. On PREEMPT_RT that state may be stored in
task_struct::saved_state while the tracee blocks on a sleeping lock and
task_struct::__state is set to TASK_RTLOCK_WAIT.
It is not possible to check only for TASK_RTLOCK_WAIT to be sure that the task
is blocked on a sleeping lock because during wake up (after the sleeping lock
has been acquired) the task state is set TASK_RUNNING. After the task in on CPU
and acquired the pi_lock it will reset the state accordingly but until then
TASK_RUNNING will be observed (with the desired state saved in saved_state).

Check also for task_struct::saved_state if the desired match was not found in
task_struct::__state on PREEMPT_RT. If the state was found in saved_state, wait
until the task is idle and state is visible in task_struct::__state.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/Yt%2FpQAFQ1xKNK0RY@linutronix.de
---
 kernel/sched/core.c |   76 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 71 insertions(+), 5 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3251,6 +3251,70 @@ int migrate_swap(struct task_struct *cur
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_PREEMPT_RT
+
+/*
+ * Consider:
+ *
+ *  set_special_state(X);
+ *
+ *  do_things()
+ *    // Somewhere in there is an rtlock that can be contended:
+ *    current_save_and_set_rtlock_wait_state();
+ *    [...]
+ *    schedule_rtlock(); (A)
+ *    [...]
+ *    current_restore_rtlock_saved_state();
+ *
+ *  schedule(); (B)
+ *
+ * If p->saved_state is anything else than TASK_RUNNING, then p blocked on an
+ * rtlock (A) *before* voluntarily calling into schedule() (B) after setting its
+ * state to X. For things like ptrace (X=TASK_TRACED), the task could have more
+ * work to do upon acquiring the lock in do_things() before whoever called
+ * wait_task_inactive() should return. IOW, we have to wait for:
+ *
+ *   p.saved_state = TASK_RUNNING
+ *   p.__state     = X
+ *
+ * which implies the task isn't blocked on an RT lock and got to schedule() (B).
+ *
+ * Also see comments in ttwu_state_match().
+ */
+
+static __always_inline bool state_mismatch(struct task_struct *p, unsigned int match_state)
+{
+	unsigned long flags;
+	bool mismatch;
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	mismatch = READ_ONCE(p->__state) != match_state &&
+		READ_ONCE(p->saved_state) != match_state;
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+	return mismatch;
+}
+static __always_inline bool state_match(struct task_struct *p, unsigned int match_state,
+					bool *wait)
+{
+	if (READ_ONCE(p->__state) == match_state)
+		return true;
+	if (READ_ONCE(p->saved_state) != match_state)
+		return false;
+	*wait = true;
+	return true;
+}
+#else
+static __always_inline bool state_mismatch(struct task_struct *p, unsigned int match_state)
+{
+	return READ_ONCE(p->__state) != match_state;
+}
+static __always_inline bool state_match(struct task_struct *p, unsigned int match_state,
+					bool *wait)
+{
+	return READ_ONCE(p->__state) == match_state;
+}
+#endif
+
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
@@ -3269,7 +3333,7 @@ int migrate_swap(struct task_struct *cur
  */
 unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
 {
-	int running, queued;
+	bool running, wait;
 	struct rq_flags rf;
 	unsigned long ncsw;
 	struct rq *rq;
@@ -3295,7 +3359,7 @@ 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 && state_mismatch(p, match_state))
 				return 0;
 			cpu_relax();
 		}
@@ -3308,10 +3372,12 @@ unsigned long wait_task_inactive(struct
 		rq = task_rq_lock(p, &rf);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
-		queued = task_on_rq_queued(p);
+		wait = task_on_rq_queued(p);
 		ncsw = 0;
-		if (!match_state || READ_ONCE(p->__state) == match_state)
+
+		if (!match_state || state_match(p, match_state, &wait))
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
+
 		task_rq_unlock(rq, p, &rf);
 
 		/*
@@ -3340,7 +3406,7 @@ 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(wait)) {
 			ktime_t to = NSEC_PER_SEC / HZ;
 
 			set_current_state(TASK_UNINTERRUPTIBLE);