From 622996bf8475bf1d06cbb523dacc7469e7b9c864 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 25 Jun 2011 09:21:04 +0200
Subject: [PATCH 169/323] sched: Add saved_state for tasks blocked on sleeping
 locks
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz

Spinlocks are state preserving in !RT. RT changes the state when a
task gets blocked on a lock. So we need to remember the state before
the lock contention. If a regular wakeup (not a RTmutex related
wakeup) happens, the saved_state is updated to running. When the lock
sleep is done, the saved state is restored.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/sched.h |  3 +++
 kernel/sched/core.c   | 34 ++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h  |  1 +
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d31da4867bb2..73defe42fd23 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -659,6 +659,8 @@ struct task_struct {
 #endif
 	/* -1 unrunnable, 0 runnable, >0 stopped: */
 	volatile long			state;
+	/* saved state for "spinlock sleepers" */
+	volatile long			saved_state;
 
 	/*
 	 * This begins the randomizable portion of task_struct. Only
@@ -1782,6 +1784,7 @@ extern struct task_struct *find_get_task_by_vpid(pid_t nr);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
+extern int wake_up_lock_sleeper(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 390b51366f5e..f6d40256c0d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3305,7 +3305,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	int cpu, success = 0;
 
 	preempt_disable();
-	if (p == current) {
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && p == current) {
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
@@ -3335,8 +3335,26 @@ 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 (!(p->state & state))
+	if (!(p->state & state)) {
+		/*
+		 * The task might be running due to a spinlock sleeper
+		 * wakeup. Check the saved state and set it to running
+		 * if the wakeup condition is true.
+		 */
+		if (!(wake_flags & WF_LOCK_SLEEPER)) {
+			if (p->saved_state & state) {
+				p->saved_state = TASK_RUNNING;
+				success = 1;
+			}
+		}
 		goto unlock;
+	}
+	/*
+	 * If this is a regular wakeup, then we can unconditionally
+	 * clear the saved state of a "lock sleeper".
+	 */
+	if (!(wake_flags & WF_LOCK_SLEEPER))
+		p->saved_state = TASK_RUNNING;
 
 	trace_sched_waking(p);
 
@@ -3525,6 +3543,18 @@ int wake_up_process(struct task_struct *p)
 }
 EXPORT_SYMBOL(wake_up_process);
 
+/**
+ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
+ * @p: The process to be woken up.
+ *
+ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
+ * the nature of the wakeup.
+ */
+int wake_up_lock_sleeper(struct task_struct *p)
+{
+	return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER);
+}
+
 int wake_up_state(struct task_struct *p, unsigned int state)
 {
 	return try_to_wake_up(p, state, 0);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c26b1c7009f4..d4bfc51358d3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1753,6 +1753,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_FORK			0x02		/* Child wakeup after fork */
 #define WF_MIGRATED		0x04		/* Internal use, task got migrated */
 #define WF_ON_CPU		0x08		/* Wakee is on_cpu */
+#define WF_LOCK_SLEEPER		0x10		/* Wakeup spinlock "sleeper" */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
-- 
2.43.0