diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 4f5c42a0924c..2ce9cc2717ac 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -568,7 +568,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
-		preempt_disable();
+		migrate_disable();
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
@@ -587,7 +587,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			local_irq_enable();
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
-			preempt_enable();
+			migrate_enable();
 			continue;
 		}
 
@@ -641,7 +641,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		kvm_vgic_sync_hwstate(vcpu);
 
-		preempt_enable();
+		migrate_enable();
 
 		ret = handle_exit(vcpu, run, ret);
 	}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 8aee3aeec3e6..c1492ba1f6d1 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -186,20 +186,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
-static DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(step_hook_lock);
 
 void register_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_add(&hook->node, &step_hook);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_add_rcu(&hook->node, &step_hook);
+	spin_unlock(&step_hook_lock);
 }
 
 void unregister_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&step_hook_lock);
+	synchronize_rcu();
 }
 
 /*
@@ -213,15 +214,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	struct step_hook *hook;
 	int retval = DBG_HOOK_ERROR;
 
-	read_lock(&step_hook_lock);
+	rcu_read_lock();
 
-	list_for_each_entry(hook, &step_hook, node)	{
+	list_for_each_entry_rcu(hook, &step_hook, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
 	}
 
-	read_unlock(&step_hook_lock);
+	rcu_read_unlock();
 
 	return retval;
 }
diff --git a/include/linux/locallock.h b/include/linux/locallock.h
index 339ba00adb9a..6fe5928fc2ab 100644
--- a/include/linux/locallock.h
+++ b/include/linux/locallock.h
@@ -43,9 +43,9 @@ struct local_irq_lock {
  * for CONFIG_PREEMPT_BASE map to the normal spin_* calls.
  */
 #ifdef CONFIG_PREEMPT_RT_FULL
-# define spin_lock_local(lock)			rt_spin_lock(lock)
-# define spin_trylock_local(lock)		rt_spin_trylock(lock)
-# define spin_unlock_local(lock)		rt_spin_unlock(lock)
+# define spin_lock_local(lock)			rt_spin_lock__no_mg(lock)
+# define spin_trylock_local(lock)		rt_spin_trylock__no_mg(lock)
+# define spin_unlock_local(lock)		rt_spin_unlock__no_mg(lock)
 #else
 # define spin_lock_local(lock)			spin_lock(lock)
 # define spin_trylock_local(lock)		spin_trylock(lock)
diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
index f757096b230c..3b2825537531 100644
--- a/include/linux/spinlock_rt.h
+++ b/include/linux/spinlock_rt.h
@@ -18,6 +18,10 @@ do {							\
 	__rt_spin_lock_init(slock, #slock, &__key);	\
 } while (0)
 
+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock);
+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock);
+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock);
+
 extern void __lockfunc rt_spin_lock(spinlock_t *lock);
 extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
 extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
@@ -32,20 +36,16 @@ extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock);
  * lockdep-less calls, for derived types like rwlock:
  * (for trylock they can use rt_mutex_trylock() directly.
  */
+extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock);
 extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
 extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
 extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
 
-#define spin_lock(lock)				\
-	do {					\
-		migrate_disable();		\
-		rt_spin_lock(lock);		\
-	} while (0)
+#define spin_lock(lock)			rt_spin_lock(lock)
 
 #define spin_lock_bh(lock)			\
 	do {					\
 		local_bh_disable();		\
-		migrate_disable();		\
 		rt_spin_lock(lock);		\
 	} while (0)
 
@@ -56,24 +56,19 @@ extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
 #define spin_trylock(lock)			\
 ({						\
 	int __locked;				\
-	migrate_disable();			\
 	__locked = spin_do_trylock(lock);	\
-	if (!__locked)				\
-		migrate_enable();		\
 	__locked;				\
 })
 
 #ifdef CONFIG_LOCKDEP
 # define spin_lock_nested(lock, subclass)		\
 	do {						\
-		migrate_disable();			\
 		rt_spin_lock_nested(lock, subclass);	\
 	} while (0)
 
 #define spin_lock_bh_nested(lock, subclass)		\
 	do {						\
 		local_bh_disable();			\
-		migrate_disable();			\
 		rt_spin_lock_nested(lock, subclass);	\
 	} while (0)
 
@@ -81,7 +76,6 @@ extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
 	do {						 \
 		typecheck(unsigned long, flags);	 \
 		flags = 0;				 \
-		migrate_disable();			 \
 		rt_spin_lock_nested(lock, subclass);	 \
 	} while (0)
 #else
@@ -117,16 +111,11 @@ static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
 /* FIXME: we need rt_spin_lock_nest_lock */
 #define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
 
-#define spin_unlock(lock)				\
-	do {						\
-		rt_spin_unlock(lock);			\
-		migrate_enable();			\
-	} while (0)
+#define spin_unlock(lock)			rt_spin_unlock(lock)
 
 #define spin_unlock_bh(lock)				\
 	do {						\
 		rt_spin_unlock(lock);			\
-		migrate_enable();			\
 		local_bh_enable();			\
 	} while (0)
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 51aafc259546..8edd3c716092 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -127,8 +127,8 @@ struct hotplug_pcp {
 };
 
 #ifdef CONFIG_PREEMPT_RT_FULL
-# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock)
-# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock)
+# define hotplug_lock(hp) rt_spin_lock__no_mg(&(hp)->lock)
+# define hotplug_unlock(hp) rt_spin_unlock__no_mg(&(hp)->lock)
 #else
 # define hotplug_lock(hp) mutex_lock(&(hp)->mutex)
 # define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex)
diff --git a/kernel/futex.c b/kernel/futex.c
index 11bca4377cd3..af4f1b4d682b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1226,7 +1226,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (pi_state->owner != current)
 		return -EINVAL;
 
-	raw_spin_lock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
 	/*
@@ -1252,22 +1252,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	else if (curval != uval)
 		ret = -EINVAL;
 	if (ret) {
-		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
 	}
 
-	raw_spin_lock_irq(&pi_state->owner->pi_lock);
+	raw_spin_lock(&pi_state->owner->pi_lock);
 	WARN_ON(list_empty(&pi_state->list));
 	list_del_init(&pi_state->list);
-	raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+	raw_spin_unlock(&pi_state->owner->pi_lock);
 
-	raw_spin_lock_irq(&new_owner->pi_lock);
+	raw_spin_lock(&new_owner->pi_lock);
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &new_owner->pi_state_list);
 	pi_state->owner = new_owner;
-	raw_spin_unlock_irq(&new_owner->pi_lock);
+	raw_spin_unlock(&new_owner->pi_lock);
 
-	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
 	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q,
 					&wake_sleeper_q);
@@ -2144,11 +2144,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * we returned due to timeout or signal without taking the
 		 * rt_mutex. Too late.
 		 */
-		raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
 		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
 		if (!owner)
 			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
 		ret = fixup_pi_state_owner(uaddr, q, owner);
 		goto out;
 	}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ba2a42a37025..8e89554aa345 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -2060,7 +2060,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
  *	This call sets the internal irqchip state of an interrupt,
  *	depending on the value of @which.
  *
- *	This function should be called with preemption disabled if the
+ *	This function should be called with migration disabled if the
  *	interrupt controller has per-cpu registers.
  */
 int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c
index d8be4fcc14f8..51bfe64e7d16 100644
--- a/kernel/locking/lglock.c
+++ b/kernel/locking/lglock.c
@@ -10,7 +10,7 @@
 # define lg_do_unlock(l)	arch_spin_unlock(l)
 #else
 # define lg_lock_ptr		struct rt_mutex
-# define lg_do_lock(l)		__rt_spin_lock(l)
+# define lg_do_lock(l)		__rt_spin_lock__no_mg(l)
 # define lg_do_unlock(l)	__rt_spin_unlock(l)
 #endif
 /*
diff --git a/kernel/locking/rt.c b/kernel/locking/rt.c
index 1bbbcad5e360..d4ab61c1848b 100644
--- a/kernel/locking/rt.c
+++ b/kernel/locking/rt.c
@@ -235,7 +235,6 @@ EXPORT_SYMBOL(rt_read_trylock);
 void __lockfunc rt_write_lock(rwlock_t *rwlock)
 {
 	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
-	migrate_disable();
 	__rt_spin_lock(&rwlock->lock);
 }
 EXPORT_SYMBOL(rt_write_lock);
@@ -249,7 +248,6 @@ void __lockfunc rt_read_lock(rwlock_t *rwlock)
 	 * recursive read locks succeed when current owns the lock
 	 */
 	if (rt_mutex_owner(lock) != current) {
-		migrate_disable();
 		rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
 		__rt_spin_lock(lock);
 	}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index e1ddae39d56b..66971005cc12 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -111,13 +111,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
  * 2) Drop lock->wait_lock
  * 3) Try to unlock the lock with cmpxchg
  */
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+					unsigned long flags)
 	__releases(lock->wait_lock)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 
 	clear_rt_mutex_waiters(lock);
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 	/*
 	 * If a new waiter comes in between the unlock and the cmpxchg
 	 * we have two situations:
@@ -159,11 +160,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 /*
  * Simple slow path only version: lock->owner is protected by lock->wait_lock.
  */
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+					unsigned long flags)
 	__releases(lock->wait_lock)
 {
 	lock->owner = NULL;
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 	return true;
 }
 #endif
@@ -454,7 +456,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	int ret = 0, depth = 0;
 	struct rt_mutex *lock;
 	bool detect_deadlock;
-	unsigned long flags;
 	bool requeue = true;
 
 	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
@@ -497,7 +498,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	/*
 	 * [1] Task cannot go away as we did a get_task() before !
 	 */
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock_irq(&task->pi_lock);
 
 	/*
 	 * [2] Get the waiter on which @task is blocked on.
@@ -581,7 +582,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * operations.
 	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock_irq(&task->pi_lock);
 		cpu_relax();
 		goto retry;
 	}
@@ -612,7 +613,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		/*
 		 * No requeue[7] here. Just release @task [8]
 		 */
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&task->pi_lock);
 		put_task_struct(task);
 
 		/*
@@ -620,14 +621,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * If there is no owner of the lock, end of chain.
 		 */
 		if (!rt_mutex_owner(lock)) {
-			raw_spin_unlock(&lock->wait_lock);
+			raw_spin_unlock_irq(&lock->wait_lock);
 			return 0;
 		}
 
 		/* [10] Grab the next task, i.e. owner of @lock */
 		task = rt_mutex_owner(lock);
 		get_task_struct(task);
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
+		raw_spin_lock(&task->pi_lock);
 
 		/*
 		 * No requeue [11] here. We just do deadlock detection.
@@ -642,8 +643,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		top_waiter = rt_mutex_top_waiter(lock);
 
 		/* [13] Drop locks */
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock(&task->pi_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 
 		/* If owner is not blocked, end of chain. */
 		if (!next_lock)
@@ -664,7 +665,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 	put_task_struct(task);
 
 	/*
@@ -685,14 +686,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		lock_top_waiter = rt_mutex_top_waiter(lock);
 		if (prerequeue_top_waiter != lock_top_waiter)
 			rt_mutex_wake_waiter(lock_top_waiter);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}
 
 	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 
 	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
@@ -746,8 +747,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* [13] Drop the locks */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock(&task->pi_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	/*
 	 * Make the actual exit decisions [12], based on the stored
@@ -770,7 +771,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	goto again;
 
  out_unlock_pi:
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock_irq(&task->pi_lock);
  out_put_task:
 	put_task_struct(task);
 
@@ -799,7 +800,7 @@ static inline int lock_is_stealable(struct task_struct *task,
 /*
  * Try to take an rt-mutex
  *
- * Must be called with lock->wait_lock held.
+ * Must be called with lock->wait_lock held and interrupts disabled
  *
  * @lock:   The lock to be acquired.
  * @task:   The task which wants to acquire the lock
@@ -810,8 +811,6 @@ static int __try_to_take_rt_mutex(struct rt_mutex *lock,
 				  struct task_struct *task,
 				  struct rt_mutex_waiter *waiter, int mode)
 {
-	unsigned long flags;
-
 	/*
 	 * Before testing whether we can acquire @lock, we set the
 	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -894,7 +893,7 @@ static int __try_to_take_rt_mutex(struct rt_mutex *lock,
 	 * case, but conditionals are more expensive than a redundant
 	 * store.
 	 */
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 	task->pi_blocked_on = NULL;
 	/*
 	 * Finish the lock acquisition. @task is the new owner. If
@@ -903,7 +902,7 @@ static int __try_to_take_rt_mutex(struct rt_mutex *lock,
 	 */
 	if (rt_mutex_has_waiters(lock))
 		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 takeit:
 	/* We got the lock. */
@@ -925,14 +924,19 @@ static int __try_to_take_rt_mutex(struct rt_mutex *lock,
  * preemptible spin_lock functions:
  */
 static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
-					 void  (*slowfn)(struct rt_mutex *lock))
+					 void  (*slowfn)(struct rt_mutex *lock,
+							 bool mg_off),
+					 bool do_mig_dis)
 {
 	might_sleep_no_state_check();
 
+	if (do_mig_dis)
+		migrate_disable();
+
 	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		rt_mutex_deadlock_account_lock(lock, current);
 	else
-		slowfn(lock);
+		slowfn(lock, do_mig_dis);
 }
 
 static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock,
@@ -979,9 +983,6 @@ static int adaptive_wait(struct rt_mutex *lock,
 }
 #endif
 
-# define pi_lock(lock)		raw_spin_lock_irq(lock)
-# define pi_unlock(lock)	raw_spin_unlock_irq(lock)
-
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
 				   struct task_struct *task,
@@ -993,18 +994,20 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  * We store the current state under p->pi_lock in p->saved_state and
  * the try_to_wake_up() code handles this accordingly.
  */
-static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
+static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock,
+						    bool mg_off)
 {
 	struct task_struct *lock_owner, *self = current;
 	struct rt_mutex_waiter waiter, *top_waiter;
+	unsigned long flags;
 	int ret;
 
 	rt_mutex_init_waiter(&waiter, true);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) {
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return;
 	}
 
@@ -1016,10 +1019,10 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 	 * as well. We are serialized via pi_lock against wakeups. See
 	 * try_to_wake_up().
 	 */
-	pi_lock(&self->pi_lock);
+	raw_spin_lock(&self->pi_lock);
 	self->saved_state = self->state;
 	__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
-	pi_unlock(&self->pi_lock);
+	raw_spin_unlock(&self->pi_lock);
 
 	ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK);
 	BUG_ON(ret);
@@ -1032,18 +1035,23 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 		top_waiter = rt_mutex_top_waiter(lock);
 		lock_owner = rt_mutex_owner(lock);
 
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 		debug_rt_mutex_print_deadlock(&waiter);
 
-		if (top_waiter != &waiter || adaptive_wait(lock, lock_owner))
+		if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) {
+			if (mg_off)
+				migrate_enable();
 			schedule();
+			if (mg_off)
+				migrate_disable();
+		}
 
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-		pi_lock(&self->pi_lock);
+		raw_spin_lock(&self->pi_lock);
 		__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
-		pi_unlock(&self->pi_lock);
+		raw_spin_unlock(&self->pi_lock);
 	}
 
 	/*
@@ -1053,10 +1061,10 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 	 * happened while we were blocked. Clear saved_state so
 	 * try_to_wakeup() does not get confused.
 	 */
-	pi_lock(&self->pi_lock);
+	raw_spin_lock(&self->pi_lock);
 	__set_current_state_no_track(self->saved_state);
 	self->saved_state = TASK_RUNNING;
-	pi_unlock(&self->pi_lock);
+	raw_spin_unlock(&self->pi_lock);
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -1067,7 +1075,7 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 	BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock));
 	BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry));
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	debug_rt_mutex_free_waiter(&waiter);
 }
@@ -1080,10 +1088,11 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
  */
 static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 {
+	unsigned long flags;
 	WAKE_Q(wake_q);
 	WAKE_Q(wake_sleeper_q);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	debug_rt_mutex_unlock(lock);
 
@@ -1091,13 +1100,13 @@ static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 
 	if (!rt_mutex_has_waiters(lock)) {
 		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return;
 	}
 
 	mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 	wake_up_q(&wake_q);
 	wake_up_q_sleeper(&wake_sleeper_q);
 
@@ -1105,33 +1114,55 @@ static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 	rt_mutex_adjust_prio(current);
 }
 
+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, false);
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock__no_mg);
+
 void __lockfunc rt_spin_lock(spinlock_t *lock)
 {
-	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 }
 EXPORT_SYMBOL(rt_spin_lock);
 
 void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
 {
-	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, true);
 }
 EXPORT_SYMBOL(__rt_spin_lock);
 
+void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, false);
+}
+EXPORT_SYMBOL(__rt_spin_lock__no_mg);
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
 {
-	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
 	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
 }
 EXPORT_SYMBOL(rt_spin_lock_nested);
 #endif
 
+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(rt_spin_unlock__no_mg);
+
 void __lockfunc rt_spin_unlock(spinlock_t *lock)
 {
 	/* NOTE: we always pass in '1' for nested, for simplicity */
 	spin_release(&lock->dep_map, 1, _RET_IP_);
 	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+	migrate_enable();
 }
 EXPORT_SYMBOL(rt_spin_unlock);
 
@@ -1158,14 +1189,29 @@ int __lockfunc __rt_spin_trylock(struct rt_mutex *lock)
 	return rt_mutex_trylock(lock);
 }
 
-int __lockfunc rt_spin_trylock(spinlock_t *lock)
+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock)
 {
-	int ret = rt_mutex_trylock(&lock->lock);
+	int ret;
 
+	ret = rt_mutex_trylock(&lock->lock);
 	if (ret)
 		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 	return ret;
 }
+EXPORT_SYMBOL(rt_spin_trylock__no_mg);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+	int ret;
+
+	migrate_disable();
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	else
+		migrate_enable();
+	return ret;
+}
 EXPORT_SYMBOL(rt_spin_trylock);
 
 int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
@@ -1202,12 +1248,10 @@ int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
 	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
 	if (atomic_add_unless(atomic, -1, 1))
 		return 0;
-	migrate_disable();
 	rt_spin_lock(lock);
 	if (atomic_dec_and_test(atomic))
 		return 1;
 	rt_spin_unlock(lock);
-	migrate_enable();
 	return 0;
 }
 EXPORT_SYMBOL(atomic_dec_and_spin_lock);
@@ -1273,7 +1317,7 @@ try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
  *
  * Prepare waiter and propagate pi chain
  *
- * This must be called with lock->wait_lock held.
+ * This must be called with lock->wait_lock held and interrupts disabled
  */
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
@@ -1284,7 +1328,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	struct rt_mutex_waiter *top_waiter = waiter;
 	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
-	unsigned long flags;
 
 	/*
 	 * Early deadlock detection. We really don't want the task to
@@ -1298,7 +1341,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (owner == task)
 		return -EDEADLK;
 
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 
 	/*
 	 * In the case of futex requeue PI, this will be a proxy
@@ -1310,7 +1353,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 * the task if PI_WAKEUP_INPROGRESS is set.
 	 */
 	if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&task->pi_lock);
 		return -EAGAIN;
 	}
 
@@ -1328,12 +1371,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	task->pi_blocked_on = waiter;
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 	if (!owner)
 		return 0;
 
-	raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock(&owner->pi_lock);
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
@@ -1348,7 +1391,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	/* Store the lock on which owner is blocked or NULL */
 	next_lock = task_blocked_on_lock(owner);
 
-	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	raw_spin_unlock(&owner->pi_lock);
 	/*
 	 * Even if full deadlock detection is on, if the owner is not
 	 * blocked itself, we can avoid finding this out in the chain
@@ -1364,12 +1407,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	return res;
 }
@@ -1378,16 +1421,15 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  * Remove the top waiter from the current tasks pi waiter tree and
  * queue it up.
  *
- * Called with lock->wait_lock held.
+ * Called with lock->wait_lock held and interrupts disabled.
  */
 static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 				    struct wake_q_head *wake_sleeper_q,
 				    struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *waiter;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 
 	waiter = rt_mutex_top_waiter(lock);
 
@@ -1409,7 +1451,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	 */
 	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	if (waiter->savestate)
 		wake_q_add(wake_sleeper_q, waiter->task);
@@ -1420,7 +1462,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 /*
  * Remove a waiter from a lock and give up
  *
- * Must be called with lock->wait_lock held and
+ * Must be called with lock->wait_lock held and interrupts disabled. I must
  * have just failed to try_to_take_rt_mutex().
  */
 static void remove_waiter(struct rt_mutex *lock,
@@ -1429,12 +1471,11 @@ static void remove_waiter(struct rt_mutex *lock,
 	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock = NULL;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	/*
 	 * Only update priority if the waiter was the highest priority
@@ -1443,7 +1484,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	if (!owner || !is_top_waiter)
 		return;
 
-	raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock(&owner->pi_lock);
 
 	rt_mutex_dequeue_pi(owner, waiter);
 
@@ -1456,7 +1497,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	if (rt_mutex_real_waiter(owner->pi_blocked_on))
 		next_lock = task_blocked_on_lock(owner);
 
-	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	raw_spin_unlock(&owner->pi_lock);
 
 	/*
 	 * Don't walk the chain, if the owner task is not blocked
@@ -1468,12 +1509,12 @@ static void remove_waiter(struct rt_mutex *lock,
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
 				   next_lock, NULL, current);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 }
 
 /*
@@ -1509,11 +1550,11 @@ void rt_mutex_adjust_pi(struct task_struct *task)
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
  * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
- * 			 or TASK_UNINTERRUPTIBLE)
+ *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
  *
- * lock->wait_lock must be held by the caller.
+ * Must be called with lock->wait_lock held and interrupts disabled
  */
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
@@ -1548,13 +1589,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 				break;
 		}
 
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 
 		debug_rt_mutex_print_deadlock(waiter);
 
 		schedule();
 
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irq(&lock->wait_lock);
 		set_current_state(state);
 	}
 
@@ -1668,17 +1709,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct ww_acquire_ctx *ww_ctx)
 {
 	struct rt_mutex_waiter waiter;
+	unsigned long flags;
 	int ret = 0;
 
 	rt_mutex_init_waiter(&waiter, false);
 
-	raw_spin_lock(&lock->wait_lock);
+	/*
+	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
+	 * be called in early boot if the cmpxchg() fast path is disabled
+	 * (debug, no architecture support). In this case we will acquire the
+	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
+	 * enable interrupts in that early boot case. So we need to use the
+	 * irqsave/restore variants.
+	 */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
 		if (ww_ctx)
 			ww_mutex_account_lock(lock, ww_ctx);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return 0;
 	}
 
@@ -1717,7 +1767,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* Remove pending timer: */
 	if (unlikely(timeout))
@@ -1733,6 +1783,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
  */
 static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
+	unsigned long flags;
 	int ret;
 
 	/*
@@ -1744,10 +1795,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 		return 0;
 
 	/*
-	 * The mutex has currently no owner. Lock the wait lock and
-	 * try to acquire the lock.
+	 * The mutex has currently no owner. Lock the wait lock and try to
+	 * acquire the lock. We use irqsave here to support early boot calls.
 	 */
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	ret = try_to_take_rt_mutex(lock, current, NULL);
 
@@ -1757,7 +1808,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	return ret;
 }
@@ -1770,7 +1821,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 					struct wake_q_head *wake_q,
 					struct wake_q_head *wake_sleeper_q)
 {
-	raw_spin_lock(&lock->wait_lock);
+	unsigned long flags;
+
+	/* irqsave required to support early boot calls */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	debug_rt_mutex_unlock(lock);
 
@@ -1809,10 +1863,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 */
 	while (!rt_mutex_has_waiters(lock)) {
 		/* Drops lock->wait_lock ! */
-		if (unlock_rt_mutex_safe(lock) == true)
+		if (unlock_rt_mutex_safe(lock, flags) == true)
 			return false;
 		/* Relock the rtmutex and try again */
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
 	}
 
 	/*
@@ -1823,7 +1877,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 */
 	mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* check PI boosting */
 	return true;
@@ -2135,10 +2189,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 {
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	if (try_to_take_rt_mutex(lock, task, NULL)) {
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 		return 1;
 	}
 
@@ -2161,14 +2215,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	 * PI_REQUEUE_INPROGRESS, so that if the task is waking up
 	 * it will know that we are in the process of requeuing it.
 	 */
-	raw_spin_lock_irq(&task->pi_lock);
+	raw_spin_lock(&task->pi_lock);
 	if (task->pi_blocked_on) {
-		raw_spin_unlock_irq(&task->pi_lock);
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock(&task->pi_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 		return -EAGAIN;
 	}
 	task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
-	raw_spin_unlock_irq(&task->pi_lock);
+	raw_spin_unlock(&task->pi_lock);
 #endif
 
 	/* We enforce deadlock detection for futexes */
@@ -2188,7 +2242,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (ret && rt_mutex_has_waiters(lock))
 		remove_waiter(lock, waiter);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	debug_rt_mutex_print_deadlock(waiter);
 
@@ -2236,7 +2290,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 {
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
@@ -2252,7 +2306,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5359091fecaa..64098d35de19 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -454,11 +454,13 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
 /*
  * Return the number of RCU BH batches started thus far for debug & stats.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 unsigned long rcu_batches_started_bh(void)
 {
 	return rcu_bh_state.gpnum;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+#endif
 
 /*
  * Return the number of RCU batches completed thus far for debug & stats.
@@ -563,9 +565,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 	case RCU_FLAVOR:
 		rsp = rcu_state_p;
 		break;
+#ifndef CONFIG_PREEMPT_RT_FULL
 	case RCU_BH_FLAVOR:
 		rsp = &rcu_bh_state;
 		break;
+#endif
 	case RCU_SCHED_FLAVOR:
 		rsp = &rcu_sched_state;
 		break;
@@ -4695,7 +4699,9 @@ void __init rcu_init(void)
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
+#ifndef CONFIG_PREEMPT_RT_FULL
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
+#endif
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	if (dump_tree)
 		rcu_dump_rcu_node_tree(&rcu_sched_state);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 588509d94bbd..2ba8f6c2e81e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -557,7 +557,9 @@ extern struct list_head rcu_struct_flavors;
  */
 extern struct rcu_state rcu_sched_state;
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern struct rcu_state rcu_bh_state;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1217926b500d..40c1e29416c0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3157,7 +3157,7 @@ void migrate_disable(void)
 {
 	struct task_struct *p = current;
 
-	if (in_atomic()) {
+	if (in_atomic() || irqs_disabled()) {
 #ifdef CONFIG_SCHED_DEBUG
 		p->migrate_disable_atomic++;
 #endif
@@ -3188,7 +3188,7 @@ void migrate_enable(void)
 {
 	struct task_struct *p = current;
 
-	if (in_atomic()) {
+	if (in_atomic() || irqs_disabled()) {
 #ifdef CONFIG_SCHED_DEBUG
 		p->migrate_disable_atomic--;
 #endif
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d1e999e74d23..2ca63cc1469e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -563,8 +563,10 @@ static void do_current_softirqs(void)
 			do_single_softirq(i);
 		}
 		softirq_clr_runner(i);
-		unlock_softirq(i);
 		WARN_ON(current->softirq_nestcnt != 1);
+		local_irq_enable();
+		unlock_softirq(i);
+		local_irq_disable();
 	}
 }
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 2c5acc882bad..f84d3b45cda7 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -30,7 +30,7 @@ struct cpu_stop_done {
 	atomic_t		nr_todo;	/* nr left to execute */
 	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
-	struct task_struct	*waiter;	/* woken when nr_todo reaches 0 */
+	struct completion	completion;	/* fired if nr_todo reaches 0 */
 };
 
 /* the actual stopper, one per every possible cpu, enabled on online cpus */
@@ -59,7 +59,7 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 {
 	memset(done, 0, sizeof(*done));
 	atomic_set(&done->nr_todo, nr_todo);
-	done->waiter = current;
+	init_completion(&done->completion);
 }
 
 /* signal completion unless @done is NULL */
@@ -68,10 +68,8 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
 	if (done) {
 		if (executed)
 			done->executed = true;
-		if (atomic_dec_and_test(&done->nr_todo)) {
-			wake_up_process(done->waiter);
-			done->waiter = NULL;
-		}
+		if (atomic_dec_and_test(&done->nr_todo))
+			complete(&done->completion);
 	}
 }
 
@@ -96,22 +94,6 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 }
 
-static void wait_for_stop_done(struct cpu_stop_done *done)
-{
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	while (atomic_read(&done->nr_todo)) {
-		schedule();
-		set_current_state(TASK_UNINTERRUPTIBLE);
-	}
-	/*
-	 * We need to wait until cpu_stop_signal_done() has cleared
-	 * done->waiter.
-	 */
-	while (done->waiter)
-		cpu_relax();
-	set_current_state(TASK_RUNNING);
-}
-
 /**
  * stop_one_cpu - stop a cpu
  * @cpu: cpu to stop
@@ -143,7 +125,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 
 	cpu_stop_init_done(&done, 1);
 	cpu_stop_queue_work(cpu, &work);
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -302,7 +284,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 
 	preempt_enable_nort();
 
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 
 	return done.executed ? done.ret : -ENOENT;
 }
@@ -364,7 +346,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
 	queue_stop_cpus_work(cpumask, fn, arg, &done, false);
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -495,13 +477,7 @@ static void cpu_stopper_thread(unsigned int cpu)
 			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
 					  ksym_buf), arg);
 
-		/*
-		 * Make sure that the wakeup and setting done->waiter
-		 * to NULL is atomic.
-		 */
-		local_irq_disable();
 		cpu_stop_signal_done(done, true);
-		local_irq_enable();
 		goto repeat;
 	}
 }
@@ -663,7 +639,7 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	ret = multi_cpu_stop(&msdata);
 
 	/* Busy wait for completion. */
-	while (atomic_read(&done.nr_todo))
+	while (!completion_done(&done.completion))
 		cpu_relax();
 
 	mutex_unlock(&stop_cpus_mutex);
diff --git a/localversion-rt b/localversion-rt
index 0efe7ba1930e..8fc605d80667 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt5
+-rt6
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7340353f8aea..b2ca2908b808 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -457,9 +457,9 @@ void wb_congested_put(struct bdi_writeback_congested *congested)
 {
 	unsigned long flags;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) {
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		return;
 	}