From 3e9cc688e56cc2abb9b6067f57c8397f6c96d42c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 23 Sep 2021 18:54:44 +0200
Subject: [PATCH] sched: Make cond_resched_lock() variants RT aware
Git-commit: 3e9cc688e56cc2abb9b6067f57c8397f6c96d42c
Patch-mainline: v5.16-rc1
References: bsc#1190137 bsc#1189998

The __might_resched() checks in the cond_resched_lock() variants use
PREEMPT_LOCK_OFFSET for preempt count offset checking which takes the
preemption disable by the spin_lock() which is still held at that point
into account.

On PREEMPT_RT enabled kernels spin/rw_lock held sections stay preemptible
which means PREEMPT_LOCK_OFFSET is 0, but that still triggers the
__might_resched() check because that takes RCU read side nesting into
account.

On RT enabled kernels spin/read/write_lock() issue rcu_read_lock() to
resemble the !RT semantics, which means in cond_resched_lock() the might
resched check will see preempt_count() == 0 and rcu_preempt_depth() == 1.

Introduce PREEMPT_LOCK_SCHED_OFFSET for those might resched checks and map
them depending on CONFIG_PREEMPT_RT.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210923165358.305969211@linutronix.de
Signed-off-by: Davidlohr Bueso <dbueso@suse.de> 

---
 include/linux/preempt.h |  5 +++--
 include/linux/sched.h   | 34 +++++++++++++++++++++++++---------
 2 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 4d244e295e85..031898b38d06 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -122,9 +122,10 @@
  * The preempt_count offset after spin_lock()
  */
 #if !defined(CONFIG_PREEMPT_RT)
-#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+#define PREEMPT_LOCK_OFFSET		PREEMPT_DISABLE_OFFSET
 #else
-#define PREEMPT_LOCK_OFFSET	0
+/* Locks on RT do not disable preemption */
+#define PREEMPT_LOCK_OFFSET		0
 #endif
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b448c7460577..21b7cd00bf1d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2049,19 +2049,35 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 #define MIGHT_RESCHED_RCU_SHIFT		8
 #define MIGHT_RESCHED_PREEMPT_MASK	((1U << MIGHT_RESCHED_RCU_SHIFT) - 1)
 
-#define cond_resched_lock(lock) ({					\
-	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
-	__cond_resched_lock(lock);					\
+#ifndef CONFIG_PREEMPT_RT
+/*
+ * Non RT kernels have an elevated preempt count due to the held lock,
+ * but are not allowed to be inside a RCU read side critical section
+ */
+# define PREEMPT_LOCK_RESCHED_OFFSETS	PREEMPT_LOCK_OFFSET
+#else
+/*
+ * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in
+ * cond_resched*lock() has to take that into account because it checks for
+ * preempt_count() and rcu_preempt_depth().
+ */
+# define PREEMPT_LOCK_RESCHED_OFFSETS	\
+	(PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT))
+#endif
+
+#define cond_resched_lock(lock) ({						\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_lock(lock);						\
 })
 
-#define cond_resched_rwlock_read(lock) ({				\
-	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
-	__cond_resched_rwlock_read(lock);				\
+#define cond_resched_rwlock_read(lock) ({					\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_rwlock_read(lock);					\
 })
 
-#define cond_resched_rwlock_write(lock) ({				\
-	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
-	__cond_resched_rwlock_write(lock);				\
+#define cond_resched_rwlock_write(lock) ({					\
+	__might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS);	\
+	__cond_resched_rwlock_write(lock);					\
 })
 
 static inline void cond_resched_rcu(void)
-- 
2.26.2