diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5919eb451bb9..7ad24aa57040 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -192,8 +192,6 @@ int __cpuinit __cpu_disable(void)
 	flush_cache_louis();
 	local_flush_tlb_all();
 
-	clear_tasks_mm_cpumask(cpu);
-
 	return 0;
 }
 
@@ -209,6 +207,9 @@ void __cpuinit __cpu_die(unsigned int cpu)
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
+
+	clear_tasks_mm_cpumask(cpu);
+
 	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
 
 	/*
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 66e274a3d968..37aee503a7ba 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -114,7 +114,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	const unsigned cpu = get_cpu();
+	const unsigned cpu = get_cpu_light();
 	unsigned long *irq_stack_end =
 		(unsigned long *)per_cpu(irq_stack_ptr, cpu);
 	unsigned used = 0;
@@ -191,7 +191,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * This handles the process stack:
 	 */
 	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
-	put_cpu();
+	put_cpu_light();
 }
 EXPORT_SYMBOL(dump_trace);
 
@@ -205,7 +205,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	int cpu;
 	int i;
 
-	preempt_disable();
+	migrate_disable();
 	cpu = smp_processor_id();
 
 	irq_stack_end	= (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
@@ -238,7 +238,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		pr_cont(" %016lx", *stack++);
 		touch_nmi_watchdog();
 	}
-	preempt_enable();
+	migrate_enable();
 
 	pr_cont("\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 4a8c7a2df480..ccd736ebee9e 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -44,4 +44,10 @@ bool irq_work_needs_cpu(void);
 static inline bool irq_work_needs_cpu(void) { return false; }
 #endif
 
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void);
+#else
+static inline void irq_work_tick_soft(void) { }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e5586caff67a..1ff7042e572d 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -55,9 +55,9 @@ TRACE_EVENT(sched_kthread_stop_ret,
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(p, success),
+	TP_ARGS(p),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -71,28 +71,40 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->success	= success;
+		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	)
 	TP_perf_assign(
 		__perf_task(p);
 	),
 
-	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
+	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->target_cpu)
+		  __entry->target_cpu)
 );
 
+/*
+ * Tracepoint called when waking a task; this tracepoint is guaranteed to be
+ * called from the waking context.
+ */
+DEFINE_EVENT(sched_wakeup_template, sched_waking,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+
+/*
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * It it not always called from the waking context.
+ */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for waking up a new task:
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
 static inline long __trace_sched_switch_state(struct task_struct *p)
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index af8ceafc94e4..883bb73698b9 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -163,8 +163,17 @@ void irq_work_tick(void)
 
 	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
 		irq_work_run_list(raised);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void)
+{
 	irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
+#endif
 
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 5388ba98acaf..a809539f443c 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -1166,7 +1166,7 @@ static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	pi_unlock(&self->pi_lock);
 
-	ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK);
 	BUG_ON(ret);
 
 	for (;;) {
@@ -1636,7 +1636,7 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 			enum rtmutex_chainwalk chwalk,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
-				      int detect_deadlock))
+				      enum rtmutex_chainwalk chwalk))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
 	    likely(rt_mutex_cmpxchg(lock, NULL, current))) {
@@ -1914,7 +1914,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		ret = 0;
 	}
 
-	if (unlikely(ret))
+	if (ret && rt_mutex_has_waiters(lock))
 		remove_waiter(lock, waiter);
 
 	raw_spin_unlock(&lock->wait_lock);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 23e289ae4270..6c21a28689b9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1394,9 +1394,9 @@ static void
 ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	check_preempt_curr(rq, p, wake_flags);
-	trace_sched_wakeup(p, true);
-
 	p->state = TASK_RUNNING;
+	trace_sched_wakeup(p);
+
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
 		p->sched_class->task_woken(rq, p);
@@ -1579,6 +1579,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (!(wake_flags & WF_LOCK_SLEEPER))
 		p->saved_state = TASK_RUNNING;
 
+	trace_sched_waking(p);
+
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
@@ -1830,7 +1832,7 @@ void wake_up_new_task(struct task_struct *p)
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = 1;
-	trace_sched_wakeup_new(p, true);
+	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
diff --git a/kernel/timer.c b/kernel/timer.c
index ff272e20ee0c..2fd6ea5c6519 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1450,7 +1450,7 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
-#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL)
+#if defined(CONFIG_IRQ_WORK)
 	if (in_irq())
 		irq_work_run();
 #endif
@@ -1466,9 +1466,7 @@ static void run_timer_softirq(struct softirq_action *h)
 
 	hrtimer_run_pending();
 
-#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
-	irq_work_tick();
-#endif
+	irq_work_tick_soft();
 
 	if (time_after_eq(jiffies, base->timer_jiffies))
 		__run_timers(base);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 4e98e3b257a3..82fe794af532 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -106,7 +106,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e15d815..8e967ca56006 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -458,7 +458,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(void *ignore, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();
diff --git a/localversion-rt b/localversion-rt
index b4e5b00e24e1..8111d0b4d38d 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt105
+-rt106
diff --git a/net/core/dev.c b/net/core/dev.c
index a478f77e4322..864f7ae42c08 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5838,7 +5838,7 @@ EXPORT_SYMBOL(free_netdev);
 void synchronize_net(void)
 {
 	might_sleep();
-	if (rtnl_is_locked())
+	if (rtnl_is_locked() && !IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
 		synchronize_rcu_expedited();
 	else
 		synchronize_rcu();
@@ -6088,7 +6088,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		netif_rx(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
+	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
 		netif_rx(skb);
 		input_queue_head_incr(oldsd);
 	}