diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index f150e69ab81d..d7f7e436c3af 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -19,11 +19,13 @@
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
   extern void lockdep_softirqs_off(unsigned long ip);
+  extern void lockdep_hardirqs_on_prepare(unsigned long ip);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
+  static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4418f5cb8324..658de6164853 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -983,6 +983,7 @@ struct task_struct {
 	unsigned int			hardirq_disable_event;
 	int				hardirqs_enabled;
 	int				hardirq_context;
+	u64				hardirq_chain_key;
 	unsigned long			softirq_disable_ip;
 	unsigned long			softirq_enable_ip;
 	unsigned int			softirq_disable_event;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ac10db66cc63..9ccd675a8b5a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3635,13 +3635,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 /*
  * Hardirqs will be enabled:
  */
-static void __trace_hardirqs_on_caller(unsigned long ip)
+static void __trace_hardirqs_on_caller(void)
 {
 	struct task_struct *curr = current;
 
-	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
-
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -3654,15 +3651,19 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
-			return;
-
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(hardirqs_on_events);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 }
 
-void lockdep_hardirqs_on(unsigned long ip)
+/**
+ * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
+ * @ip:		Caller address
+ *
+ * Invoked before a possible transition to RCU idle from exit to user or
+ * guest mode. This ensures that all RCU operations are done before RCU
+ * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
+ * invoked to set the final state.
+ */
+void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3698,20 +3699,62 @@ void lockdep_hardirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
 		return;
 
+	current->hardirq_chain_key = current->curr_chain_key;
+
 	current->lockdep_recursion++;
-	__trace_hardirqs_on_caller(ip);
+	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_on);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
+
+void noinstr lockdep_hardirqs_on(unsigned long ip)
+{
+	struct task_struct *curr = current;
+
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
+		return;
+
+	if (curr->hardirqs_enabled) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
+	/*
+	 * We're enabling irqs and according to our state above irqs weren't
+	 * already enabled, yet we find the hardware thinks they are in fact
+	 * enabled.. someone messed up their IRQ state tracing.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return;
+
+	/*
+	 * Ensure the lock stack remained unchanged between
+	 * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on().
+	 */
+	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
+			    current->curr_chain_key);
+
+	/* we'll do an OFF -> ON transition: */
+	curr->hardirqs_enabled = 1;
+	curr->hardirq_enable_ip = ip;
+	curr->hardirq_enable_event = ++curr->irq_events;
+	debug_atomic_inc(hardirqs_on_events);
+}
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void lockdep_hardirqs_off(unsigned long ip)
+void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
 		return;
 
 	/*
@@ -3729,10 +3772,11 @@ void lockdep_hardirqs_off(unsigned long ip)
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
-	} else
+	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
+	}
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_off);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
@@ -4408,8 +4452,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 	dump_stack();
 }
 
-static int match_held_lock(const struct held_lock *hlock,
-					const struct lockdep_map *lock)
+static noinstr int match_held_lock(const struct held_lock *hlock,
+				   const struct lockdep_map *lock)
 {
 	if (hlock->instance == lock)
 		return 1;
@@ -4696,7 +4740,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip)
 	return 0;
 }
 
-static nokprobe_inline
+static __always_inline
 int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
@@ -4956,7 +5000,7 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
-int lock_is_held_type(const struct lockdep_map *lock, int read)
+noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
 	int ret = 0;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index c00880162b06..fb0691b8a88d 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,6 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -93,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index a75ee30b77cb..06d3135bd184 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent);
 /*
  * Generic 'turn off all lock debugging' function:
  */
-int debug_locks_off(void)
+noinstr int debug_locks_off(void)
 {
 	if (debug_locks && __debug_locks_off()) {
 		if (!debug_locks_silent) {