1 files changed, 92 insertions, 17 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 37bec9b05e31..c4462c454ab9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3776,6 +3776,55 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 }
 
 /*
+ * Invoked from try_to_wake_up() to check whether the task can be woken up.
+ *
+ * The caller holds p::pi_lock if p != current or has preemption
+ * disabled when p == current.
+ *
+ * The rules of PREEMPT_RT saved_state:
+ *
+ *   The related locking code always holds p::pi_lock when updating
+ *   p::saved_state, which means the code is fully serialized in both cases.
+ *
+ *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
+ *   bits set. This allows to distinguish all wakeup scenarios.
+ */
+static __always_inline
+bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
+		WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
+			     state != TASK_RTLOCK_WAIT);
+	}
+
+	if (READ_ONCE(p->__state) & state) {
+		*success = 1;
+		return true;
+	}
+
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * Saved state preserves the task state across blocking on
+	 * an RT lock.  If the state matches, set p::saved_state to
+	 * TASK_RUNNING, but do not wake the task because it waits
+	 * for a lock wakeup. Also indicate success because from
+	 * the regular waker's point of view this has succeeded.
+	 *
+	 * After acquiring the lock the task will restore p::__state
+	 * from p::saved_state which ensures that the regular
+	 * wakeup is not lost. The restore will also set
+	 * p::saved_state to TASK_RUNNING so any further tests will
+	 * not result in false positives vs. @success
+	 */
+	if (p->saved_state & state) {
+		p->saved_state = TASK_RUNNING;
+		*success = 1;
+	}
+#endif
+	return false;
+}
+
+/*
  * Notes on Program-Order guarantees on SMP systems.
  *
  *  MIGRATION
@@ -3914,10 +3963,9 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
-		if (!(READ_ONCE(p->__state) & state))
+		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
-		success = 1;
 		trace_sched_waking(p);
 		WRITE_ONCE(p->__state, TASK_RUNNING);
 		trace_sched_wakeup(p);
@@ -3932,14 +3980,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
-	if (!(READ_ONCE(p->__state) & state))
+	if (!ttwu_state_match(p, state, &success))
 		goto unlock;
 
 	trace_sched_waking(p);
 
-	/* We're going to change ->state: */
-	success = 1;
-
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
@@ -6061,6 +6106,24 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 #endif /* CONFIG_SCHED_CORE */
 
 /*
+ * Constants for the sched_mode argument of __schedule().
+ *
+ * The mode argument allows RT enabled kernels to differentiate a
+ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
+ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
+ * optimize the AND operation out and just check for zero.
+ */
+#define SM_NONE			0x0
+#define SM_PREEMPT		0x1
+#define SM_RTLOCK_WAIT		0x2
+
+#ifndef CONFIG_PREEMPT_RT
+# define SM_MASK_PREEMPT	(~0U)
+#else
+# define SM_MASK_PREEMPT	SM_PREEMPT
+#endif
+
+/*
  * __schedule() is the main scheduler function.
  *
  * The main means of driving the scheduler and thus entering this function are:
@@ -6099,7 +6162,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(bool preempt)
+static void __sched notrace __schedule(unsigned int sched_mode)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -6112,13 +6175,13 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, preempt);
+	schedule_debug(prev, !!sched_mode);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(preempt);
+	rcu_note_context_switch(!!sched_mode);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -6152,7 +6215,7 @@ static void __sched notrace __schedule(bool preempt)
 	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!preempt && prev_state) {
+	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
@@ -6218,7 +6281,7 @@ static void __sched notrace __schedule(bool preempt)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(preempt, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -6239,7 +6302,7 @@ void __noreturn do_task_dead(void)
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
 
-	__schedule(false);
+	__schedule(SM_NONE);
 	BUG();
 
 	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
@@ -6300,7 +6363,7 @@ asmlinkage __visible void __sched schedule(void)
 	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(false);
+		__schedule(SM_NONE);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
 	sched_update_worker(tsk);
@@ -6328,7 +6391,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(false);
+		__schedule(SM_NONE);
 	} while (need_resched());
 }
 
@@ -6363,6 +6426,18 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
+#ifdef CONFIG_PREEMPT_RT
+void __sched notrace schedule_rtlock(void)
+{
+	do {
+		preempt_disable();
+		__schedule(SM_RTLOCK_WAIT);
+		sched_preempt_enable_no_resched();
+	} while (need_resched());
+}
+NOKPROBE_SYMBOL(schedule_rtlock);
+#endif
+
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
@@ -6381,7 +6456,7 @@ static void __sched notrace preempt_schedule_common(void)
 		 */
 		preempt_disable_notrace();
 		preempt_latency_start(1);
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		preempt_latency_stop(1);
 		preempt_enable_no_resched_notrace();
 
@@ -6460,7 +6535,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 		 * an infinite recursion.
 		 */
 		prev_ctx = exception_enter();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		exception_exit(prev_ctx);
 
 		preempt_latency_stop(1);
@@ -6609,7 +6684,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	do {
 		preempt_disable();
 		local_irq_enable();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		local_irq_disable();
 		sched_preempt_enable_no_resched();
 	} while (need_resched());