Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  cpu: Export cpu_up()
  rcu: Apply ACCESS_ONCE() to rcu_boost() return value
  Revert "rcu: Permit rt_mutex_unlock() with irqs disabled"
  docs: Additional LWN links to RCU API
  rcu: Augment rcu_batch_end tracing for idle and callback state
  rcu: Add rcutorture tests for srcu_read_lock_raw()
  rcu: Make rcutorture test for hotpluggability before offlining CPUs
  driver-core/cpu: Expose hotpluggability to the rest of the kernel
  rcu: Remove redundant rcu_cpu_stall_suppress declaration
  rcu: Adaptive dyntick-idle preparation
  rcu: Keep invoking callbacks if CPU otherwise idle
  rcu: Irq nesting is always 0 on rcu_enter_idle_common
  rcu: Don't check irq nesting from rcu idle entry/exit
  rcu: Permit dyntick-idle with callbacks pending
  rcu: Document same-context read-side constraints
  rcu: Identify dyntick-idle CPUs on first force_quiescent_state() pass
  rcu: Remove dynticks false positives and RCU failures
  rcu: Reduce latency of rcu_prepare_for_idle()
  rcu: Eliminate RCU_FAST_NO_HZ grace-period hang
  rcu: Avoid needlessly IPIing CPUs at GP end
  ...

17 files changed, 933 insertions, 243 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 563f13609470..9d448ddb2247 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -380,6 +380,7 @@ out:
 	cpu_maps_update_done();
 	return err;
 }
+EXPORT_SYMBOL_GPL(cpu_up);
 
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 5532dd37aa86..7d6fb40d2188 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -636,7 +636,7 @@ char kdb_task_state_char (const struct task_struct *p)
 		(p->exit_state & EXIT_ZOMBIE) ? 'Z' :
 		(p->exit_state & EXIT_DEAD) ? 'E' :
 		(p->state & TASK_INTERRUPTIBLE) ? 'S' : '?';
-	if (p->pid == 0) {
+	if (is_idle_task(p)) {
 		/* Idle task.  Is it really idle, apart from the kdb
 		 * interrupt? */
 		if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 58690af323e4..fc0e7ff11dda 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5366,7 +5366,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	regs = get_irq_regs();
 
 	if (regs && !perf_exclude_event(event, regs)) {
-		if (!(event->attr.exclude_idle && current->pid == 0))
+		if (!(event->attr.exclude_idle && is_idle_task(current)))
 			if (perf_event_overflow(event, &data, regs))
 				ret = HRTIMER_NORESTART;
 	}
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e69d633d6aa6..8fb755132322 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4181,6 +4181,28 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	printk("%s:%d %s!\n", file, line, s);
 	printk("\nother info that might help us debug this:\n\n");
 	printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks);
+
+	/*
+	 * If a CPU is in the RCU-free window in idle (ie: in the section
+	 * between rcu_idle_enter() and rcu_idle_exit(), then RCU
+	 * considers that CPU to be in an "extended quiescent state",
+	 * which means that RCU will be completely ignoring that CPU.
+	 * Therefore, rcu_read_lock() and friends have absolutely no
+	 * effect on a CPU running in that state. In other words, even if
+	 * such an RCU-idle CPU has called rcu_read_lock(), RCU might well
+	 * delete data structures out from under it.  RCU really has no
+	 * choice here: we need to keep an RCU-free window in idle where
+	 * the CPU may possibly enter into low power mode. This way we can
+	 * notice an extended quiescent state to other CPUs that started a grace
+	 * period. Otherwise we would delay any grace period as long as we run
+	 * in the idle task.
+	 *
+	 * So complain bitterly if someone does call rcu_read_lock(),
+	 * rcu_read_lock_bh() and so on from extended quiescent states.
+	 */
+	if (rcu_is_cpu_idle())
+		printk("RCU used illegally from extended quiescent state!\n");
+
 	lockdep_print_held_locks(curr);
 	printk("\nstack backtrace:\n");
 	dump_stack();
diff --git a/kernel/rcu.h b/kernel/rcu.h
index f600868d550d..aa88baab5f78 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -30,6 +30,13 @@
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
 /*
+ * Process-level increment to ->dynticks_nesting field.  This allows for
+ * architectures that use half-interrupts and half-exceptions from
+ * process context.
+ */
+#define DYNTICK_TASK_NESTING (LLONG_MAX / 2 - 1)
+
+/*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
  * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index c5b98e565aee..2bc4e135ff23 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -93,6 +93,8 @@ int rcu_read_lock_bh_held(void)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
+	if (rcu_is_cpu_idle())
+		return 0;
 	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
@@ -316,3 +318,13 @@ struct debug_obj_descr rcuhead_debug_descr = {
 };
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp)
+{
+	trace_rcu_torture_read(rcutorturename, rhp);
+}
+EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
+#else
+#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#endif
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 636af6d9c6e5..977296dca0a4 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -53,31 +53,137 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "rcutiny_plugin.h"
 
-#ifdef CONFIG_NO_HZ
+static long long rcu_dynticks_nesting = DYNTICK_TASK_NESTING;
 
-static long rcu_dynticks_nesting = 1;
+/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
+static void rcu_idle_enter_common(long long oldval)
+{
+	if (rcu_dynticks_nesting) {
+		RCU_TRACE(trace_rcu_dyntick("--=",
+					    oldval, rcu_dynticks_nesting));
+		return;
+	}
+	RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting));
+	if (!is_idle_task(current)) {
+		struct task_struct *idle = idle_task(smp_processor_id());
+
+		RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
+					    oldval, rcu_dynticks_nesting));
+		ftrace_dump(DUMP_ALL);
+		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
+			  current->pid, current->comm,
+			  idle->pid, idle->comm); /* must be idle task! */
+	}
+	rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
 
 /*
- * Enter dynticks-idle mode, which is an extended quiescent state
- * if we have fully entered that mode (i.e., if the new value of
- * dynticks_nesting is zero).
+ * Enter idle, which is an extended quiescent state if we have fully
+ * entered that mode (i.e., if the new value of dynticks_nesting is zero).
  */
-void rcu_enter_nohz(void)
+void rcu_idle_enter(void)
 {
-	if (--rcu_dynticks_nesting == 0)
-		rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+	unsigned long flags;
+	long long oldval;
+
+	local_irq_save(flags);
+	oldval = rcu_dynticks_nesting;
+	rcu_dynticks_nesting = 0;
+	rcu_idle_enter_common(oldval);
+	local_irq_restore(flags);
 }
 
 /*
- * Exit dynticks-idle mode, so that we are no longer in an extended
- * quiescent state.
+ * Exit an interrupt handler towards idle.
  */
-void rcu_exit_nohz(void)
+void rcu_irq_exit(void)
+{
+	unsigned long flags;
+	long long oldval;
+
+	local_irq_save(flags);
+	oldval = rcu_dynticks_nesting;
+	rcu_dynticks_nesting--;
+	WARN_ON_ONCE(rcu_dynticks_nesting < 0);
+	rcu_idle_enter_common(oldval);
+	local_irq_restore(flags);
+}
+
+/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
+static void rcu_idle_exit_common(long long oldval)
 {
+	if (oldval) {
+		RCU_TRACE(trace_rcu_dyntick("++=",
+					    oldval, rcu_dynticks_nesting));
+		return;
+	}
+	RCU_TRACE(trace_rcu_dyntick("End", oldval, rcu_dynticks_nesting));
+	if (!is_idle_task(current)) {
+		struct task_struct *idle = idle_task(smp_processor_id());
+
+		RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task",
+			  oldval, rcu_dynticks_nesting));
+		ftrace_dump(DUMP_ALL);
+		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
+			  current->pid, current->comm,
+			  idle->pid, idle->comm); /* must be idle task! */
+	}
+}
+
+/*
+ * Exit idle, so that we are no longer in an extended quiescent state.
+ */
+void rcu_idle_exit(void)
+{
+	unsigned long flags;
+	long long oldval;
+
+	local_irq_save(flags);
+	oldval = rcu_dynticks_nesting;
+	WARN_ON_ONCE(oldval != 0);
+	rcu_dynticks_nesting = DYNTICK_TASK_NESTING;
+	rcu_idle_exit_common(oldval);
+	local_irq_restore(flags);
+}
+
+/*
+ * Enter an interrupt handler, moving away from idle.
+ */
+void rcu_irq_enter(void)
+{
+	unsigned long flags;
+	long long oldval;
+
+	local_irq_save(flags);
+	oldval = rcu_dynticks_nesting;
 	rcu_dynticks_nesting++;
+	WARN_ON_ONCE(rcu_dynticks_nesting == 0);
+	rcu_idle_exit_common(oldval);
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_PROVE_RCU
+
+/*
+ * Test whether RCU thinks that the current CPU is idle.
+ */
+int rcu_is_cpu_idle(void)
+{
+	return !rcu_dynticks_nesting;
 }
+EXPORT_SYMBOL(rcu_is_cpu_idle);
+
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
-#endif /* #ifdef CONFIG_NO_HZ */
+/*
+ * Test whether the current CPU was interrupted from idle.  Nested
+ * interrupts don't count, we must be running at the first interrupt
+ * level.
+ */
+int rcu_is_cpu_rrupt_from_idle(void)
+{
+	return rcu_dynticks_nesting <= 0;
+}
 
 /*
  * Helper function for rcu_sched_qs() and rcu_bh_qs().
@@ -126,14 +232,13 @@ void rcu_bh_qs(int cpu)
 
 /*
  * Check to see if the scheduling-clock interrupt came from an extended
- * quiescent state, and, if so, tell RCU about it.
+ * quiescent state, and, if so, tell RCU about it.  This function must
+ * be called from hardirq context.  It is normally called from the
+ * scheduling-clock interrupt.
  */
 void rcu_check_callbacks(int cpu, int user)
 {
-	if (user ||
-	    (idle_cpu(cpu) &&
-	     !in_softirq() &&
-	     hardirq_count() <= (1 << HARDIRQ_SHIFT)))
+	if (user || rcu_is_cpu_rrupt_from_idle())
 		rcu_sched_qs(cpu);
 	else if (!in_softirq())
 		rcu_bh_qs(cpu);
@@ -154,7 +259,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	/* If no RCU callbacks ready to invoke, just return. */
 	if (&rcp->rcucblist == rcp->donetail) {
 		RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1));
-		RCU_TRACE(trace_rcu_batch_end(rcp->name, 0));
+		RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
+					      ACCESS_ONCE(rcp->rcucblist),
+					      need_resched(),
+					      is_idle_task(current),
+					      rcu_is_callbacks_kthread()));
 		return;
 	}
 
@@ -183,7 +292,9 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		RCU_TRACE(cb_count++);
 	}
 	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
-	RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count));
+	RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(),
+				      is_idle_task(current),
+				      rcu_is_callbacks_kthread()));
 }
 
 static void rcu_process_callbacks(struct softirq_action *unused)
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 2b0484a5dc28..9cb1ae4aabdd 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -312,8 +312,8 @@ static int rcu_boost(void)
 	rt_mutex_lock(&mtx);
 	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
 
-	return rcu_preempt_ctrlblk.boost_tasks != NULL ||
-	       rcu_preempt_ctrlblk.exp_tasks != NULL;
+	return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL ||
+	       ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL;
 }
 
 /*
@@ -885,6 +885,19 @@ static void invoke_rcu_callbacks(void)
 	wake_up(&rcu_kthread_wq);
 }
 
+#ifdef CONFIG_RCU_TRACE
+
+/*
+ * Is the current CPU running the RCU-callbacks kthread?
+ * Caller must have preemption disabled.
+ */
+static bool rcu_is_callbacks_kthread(void)
+{
+	return rcu_kthread_task == current;
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
 /*
  * This kthread invokes RCU callbacks whose grace periods have
  * elapsed.  It is awakened as needed, and takes the place of the
@@ -938,6 +951,18 @@ void invoke_rcu_callbacks(void)
 	raise_softirq(RCU_SOFTIRQ);
 }
 
+#ifdef CONFIG_RCU_TRACE
+
+/*
+ * There is no callback kthread, so this thread is never it.
+ */
+static bool rcu_is_callbacks_kthread(void)
+{
+	return false;
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
 void rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 764825c2685c..88f17b8a3b1d 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -61,9 +61,11 @@ static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
 static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
 static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static int irqreader = 1;	/* RCU readers from irq (timers). */
-static int fqs_duration = 0;	/* Duration of bursts (us), 0 to disable. */
-static int fqs_holdoff = 0;	/* Hold time within burst (us). */
+static int fqs_duration;	/* Duration of bursts (us), 0 to disable. */
+static int fqs_holdoff;		/* Hold time within burst (us). */
 static int fqs_stutter = 3;	/* Wait time between bursts (s). */
+static int onoff_interval;	/* Wait time between CPU hotplugs, 0=disable. */
+static int shutdown_secs;	/* Shutdown time (s).  <=0 for no shutdown. */
 static int test_boost = 1;	/* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */
 static int test_boost_interval = 7; /* Interval between boost tests, seconds. */
 static int test_boost_duration = 4; /* Duration of each boost test, seconds. */
@@ -91,6 +93,10 @@ module_param(fqs_holdoff, int, 0444);
 MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
 module_param(fqs_stutter, int, 0444);
 MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(onoff_interval, int, 0444);
+MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
+module_param(shutdown_secs, int, 0444);
+MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable.");
 module_param(test_boost, int, 0444);
 MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
 module_param(test_boost_interval, int, 0444);
@@ -119,6 +125,10 @@ static struct task_struct *shuffler_task;
 static struct task_struct *stutter_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
+static struct task_struct *shutdown_task;
+#ifdef CONFIG_HOTPLUG_CPU
+static struct task_struct *onoff_task;
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -149,6 +159,10 @@ static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static long n_rcu_torture_timers;
+static long n_offline_attempts;
+static long n_offline_successes;
+static long n_online_attempts;
+static long n_online_successes;
 static struct list_head rcu_torture_removed;
 static cpumask_var_t shuffle_tmp_mask;
 
@@ -160,6 +174,8 @@ static int stutter_pause_test;
 #define RCUTORTURE_RUNNABLE_INIT 0
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+module_param(rcutorture_runnable, int, 0444);
+MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
 
 #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
@@ -167,6 +183,7 @@ int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 #define rcu_can_boost() 0
 #endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 
+static unsigned long shutdown_time;	/* jiffies to system shutdown. */
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
 					/*  and boost task create/destroy. */
@@ -182,6 +199,9 @@ static int fullstop = FULLSTOP_RMMOD;
  */
 static DEFINE_MUTEX(fullstop_mutex);
 
+/* Forward reference. */
+static void rcu_torture_cleanup(void);
+
 /*
  * Detect and respond to a system shutdown.
  */
@@ -612,6 +632,30 @@ static struct rcu_torture_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl)
+{
+	return srcu_read_lock_raw(&srcu_ctl);
+}
+
+static void srcu_torture_read_unlock_raw(int idx) __releases(&srcu_ctl)
+{
+	srcu_read_unlock_raw(&srcu_ctl, idx);
+}
+
+static struct rcu_torture_ops srcu_raw_ops = {
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock_raw,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock_raw,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu_raw"
+};
+
 static void srcu_torture_synchronize_expedited(void)
 {
 	synchronize_srcu_expedited(&srcu_ctl);
@@ -913,6 +957,18 @@ rcu_torture_fakewriter(void *arg)
 	return 0;
 }
 
+void rcutorture_trace_dump(void)
+{
+	static atomic_t beenhere = ATOMIC_INIT(0);
+
+	if (atomic_read(&beenhere))
+		return;
+	if (atomic_xchg(&beenhere, 1) != 0)
+		return;
+	do_trace_rcu_torture_read(cur_ops->name, (struct rcu_head *)~0UL);
+	ftrace_dump(DUMP_ALL);
+}
+
 /*
  * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -934,6 +990,7 @@ static void rcu_torture_timer(unsigned long unused)
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
 				  srcu_read_lock_held(&srcu_ctl));
+	do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu);
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -951,6 +1008,8 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
+	if (pipe_count > 1)
+		rcutorture_trace_dump();
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
 	completed = cur_ops->completed() - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
@@ -994,6 +1053,7 @@ rcu_torture_reader(void *arg)
 					  rcu_read_lock_bh_held() ||
 					  rcu_read_lock_sched_held() ||
 					  srcu_read_lock_held(&srcu_ctl));
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu);
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -1009,6 +1069,8 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
+		if (pipe_count > 1)
+			rcutorture_trace_dump();
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
 		completed = cur_ops->completed() - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
@@ -1056,7 +1118,8 @@ rcu_torture_printk(char *page)
 	cnt += sprintf(&page[cnt],
 		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
 		       "rtmbe: %d rtbke: %ld rtbre: %ld "
-		       "rtbf: %ld rtb: %ld nt: %ld",
+		       "rtbf: %ld rtb: %ld nt: %ld "
+		       "onoff: %ld/%ld:%ld/%ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
 		       list_empty(&rcu_torture_freelist),
@@ -1068,7 +1131,11 @@ rcu_torture_printk(char *page)
 		       n_rcu_torture_boost_rterror,
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
-		       n_rcu_torture_timers);
+		       n_rcu_torture_timers,
+		       n_online_successes,
+		       n_online_attempts,
+		       n_offline_successes,
+		       n_offline_attempts);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
@@ -1232,12 +1299,14 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
 		"shuffle_interval=%d stutter=%d irqreader=%d "
 		"fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
 		"test_boost=%d/%d test_boost_interval=%d "
-		"test_boost_duration=%d\n",
+		"test_boost_duration=%d shutdown_secs=%d "
+		"onoff_interval=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
 		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
 		test_boost, cur_ops->can_boost,
-		test_boost_interval, test_boost_duration);
+		test_boost_interval, test_boost_duration, shutdown_secs,
+		onoff_interval);
 }
 
 static struct notifier_block rcutorture_shutdown_nb = {
@@ -1287,6 +1356,131 @@ static int rcutorture_booster_init(int cpu)
 	return 0;
 }
 
+/*
+ * Cause the rcutorture test to shutdown the system after the test has
+ * run for the time specified by the shutdown_secs module parameter.
+ */
+static int
+rcu_torture_shutdown(void *arg)
+{
+	long delta;
+	unsigned long jiffies_snap;
+
+	VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started");
+	jiffies_snap = ACCESS_ONCE(jiffies);
+	while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
+	       !kthread_should_stop()) {
+		delta = shutdown_time - jiffies_snap;
+		if (verbose)
+			printk(KERN_ALERT "%s" TORTURE_FLAG
+			       "rcu_torture_shutdown task: %lu "
+			       "jiffies remaining\n",
+			       torture_type, delta);
+		schedule_timeout_interruptible(delta);
+		jiffies_snap = ACCESS_ONCE(jiffies);
+	}
+	if (kthread_should_stop()) {
+		VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping");
+		return 0;
+	}
+
+	/* OK, shut down the system. */
+
+	VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system");
+	shutdown_task = NULL;	/* Avoid self-kill deadlock. */
+	rcu_torture_cleanup();	/* Get the success/failure message. */
+	kernel_power_off();	/* Shut down the system. */
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Execute random CPU-hotplug operations at the interval specified
+ * by the onoff_interval.
+ */
+static int
+rcu_torture_onoff(void *arg)
+{
+	int cpu;
+	int maxcpu = -1;
+	DEFINE_RCU_RANDOM(rand);
+
+	VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
+	for_each_online_cpu(cpu)
+		maxcpu = cpu;
+	WARN_ON(maxcpu < 0);
+	while (!kthread_should_stop()) {
+		cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
+		if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
+			if (verbose)
+				printk(KERN_ALERT "%s" TORTURE_FLAG
+				       "rcu_torture_onoff task: offlining %d\n",
+				       torture_type, cpu);
+			n_offline_attempts++;
+			if (cpu_down(cpu) == 0) {
+				if (verbose)
+					printk(KERN_ALERT "%s" TORTURE_FLAG
+					       "rcu_torture_onoff task: "
+					       "offlined %d\n",
+					       torture_type, cpu);
+				n_offline_successes++;
+			}
+		} else if (cpu_is_hotpluggable(cpu)) {
+			if (verbose)
+				printk(KERN_ALERT "%s" TORTURE_FLAG
+				       "rcu_torture_onoff task: onlining %d\n",
+				       torture_type, cpu);
+			n_online_attempts++;
+			if (cpu_up(cpu) == 0) {
+				if (verbose)
+					printk(KERN_ALERT "%s" TORTURE_FLAG
+					       "rcu_torture_onoff task: "
+					       "onlined %d\n",
+					       torture_type, cpu);
+				n_online_successes++;
+			}
+		}
+		schedule_timeout_interruptible(onoff_interval * HZ);
+	}
+	VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping");
+	return 0;
+}
+
+static int
+rcu_torture_onoff_init(void)
+{
+	if (onoff_interval <= 0)
+		return 0;
+	onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff");
+	if (IS_ERR(onoff_task)) {
+		onoff_task = NULL;
+		return PTR_ERR(onoff_task);
+	}
+	return 0;
+}
+
+static void rcu_torture_onoff_cleanup(void)
+{
+	if (onoff_task == NULL)
+		return;
+	VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
+	kthread_stop(onoff_task);
+}
+
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void
+rcu_torture_onoff_init(void)
+{
+}
+
+static void rcu_torture_onoff_cleanup(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+
 static int rcutorture_cpu_notify(struct notifier_block *self,
 				 unsigned long action, void *hcpu)
 {
@@ -1391,6 +1585,11 @@ rcu_torture_cleanup(void)
 		for_each_possible_cpu(i)
 			rcutorture_booster_cleanup(i);
 	}
+	if (shutdown_task != NULL) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
+		kthread_stop(shutdown_task);
+	}
+	rcu_torture_onoff_cleanup();
 
 	/* Wait for all RCU callbacks to fire.  */
 
@@ -1416,7 +1615,7 @@ rcu_torture_init(void)
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
 		  &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
-		  &srcu_ops, &srcu_expedited_ops,
+		  &srcu_ops, &srcu_raw_ops, &srcu_expedited_ops,
 		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
 
 	mutex_lock(&fullstop_mutex);
@@ -1607,6 +1806,18 @@ rcu_torture_init(void)
 			}
 		}
 	}
+	if (shutdown_secs > 0) {
+		shutdown_time = jiffies + shutdown_secs * HZ;
+		shutdown_task = kthread_run(rcu_torture_shutdown, NULL,
+					    "rcu_torture_shutdown");
+		if (IS_ERR(shutdown_task)) {
+			firsterr = PTR_ERR(shutdown_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
+			shutdown_task = NULL;
+			goto unwind;
+		}
+	}
+	rcu_torture_onoff_init();
 	register_reboot_notifier(&rcutorture_shutdown_nb);
 	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 6b76d812740c..6c4a6722abfd 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -69,7 +69,7 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 		NUM_RCU_LVL_3, \
 		NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \
 	}, \
-	.signaled = RCU_GP_IDLE, \
+	.fqs_state = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
 	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \
@@ -195,12 +195,10 @@ void rcu_note_context_switch(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-#ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = 1,
+	.dynticks_nesting = DYNTICK_TASK_NESTING,
 	.dynticks = ATOMIC_INIT(1),
 };
-#endif /* #ifdef CONFIG_NO_HZ */
 
 static int blimit = 10;		/* Maximum callbacks per rcu_do_batch. */
 static int qhimark = 10000;	/* If this many pending, ignore blimit. */
@@ -328,11 +326,11 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 		return 1;
 	}
 
-	/* If preemptible RCU, no point in sending reschedule IPI. */
-	if (rdp->preemptible)
-		return 0;
-
-	/* The CPU is online, so send it a reschedule IPI. */
+	/*
+	 * The CPU is online, so send it a reschedule IPI.  This forces
+	 * it through the scheduler, and (inefficiently) also handles cases
+	 * where idle loops fail to inform RCU about the CPU being idle.
+	 */
 	if (rdp->cpu != smp_processor_id())
 		smp_send_reschedule(rdp->cpu);
 	else
@@ -343,59 +341,181 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 
 #endif /* #ifdef CONFIG_SMP */
 
-#ifdef CONFIG_NO_HZ
+/*
+ * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
+ *
+ * If the new value of the ->dynticks_nesting counter now is zero,
+ * we really have entered idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
+{
+	trace_rcu_dyntick("Start", oldval, 0);
+	if (!is_idle_task(current)) {
+		struct task_struct *idle = idle_task(smp_processor_id());
+
+		trace_rcu_dyntick("Error on entry: not idle task", oldval, 0);
+		ftrace_dump(DUMP_ALL);
+		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
+			  current->pid, current->comm,
+			  idle->pid, idle->comm); /* must be idle task! */
+	}
+	rcu_prepare_for_idle(smp_processor_id());
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+}
 
 /**
- * rcu_enter_nohz - inform RCU that current CPU is entering nohz
+ * rcu_idle_enter - inform RCU that current CPU is entering idle
  *
- * Enter nohz mode, in other words, -leave- the mode in which RCU
+ * Enter idle mode, in other words, -leave- the mode in which RCU
  * read-side critical sections can occur.  (Though RCU read-side
- * critical sections can occur in irq handlers in nohz mode, a possibility
- * handled by rcu_irq_enter() and rcu_irq_exit()).
+ * critical sections can occur in irq handlers in idle, a possibility
+ * handled by irq_enter() and irq_exit().)
+ *
+ * We crowbar the ->dynticks_nesting field to zero to allow for
+ * the possibility of usermode upcalls having messed up our count
+ * of interrupt nesting level during the prior busy period.
  */
-void rcu_enter_nohz(void)
+void rcu_idle_enter(void)
 {
 	unsigned long flags;
+	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (--rdtp->dynticks_nesting) {
-		local_irq_restore(flags);
-		return;
-	}
-	trace_rcu_dyntick("Start");
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic_inc();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	oldval = rdtp->dynticks_nesting;
+	rdtp->dynticks_nesting = 0;
+	rcu_idle_enter_common(rdtp, oldval);
 	local_irq_restore(flags);
 }
 
-/*
- * rcu_exit_nohz - inform RCU that current CPU is leaving nohz
+/**
+ * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
+ *
+ * Exit from an interrupt handler, which might possibly result in entering
+ * idle mode, in other words, leaving the mode in which read-side critical
+ * sections can occur.
  *
- * Exit nohz mode, in other words, -enter- the mode in which RCU
- * read-side critical sections normally occur.
+ * This code assumes that the idle loop never does anything that might
+ * result in unbalanced calls to irq_enter() and irq_exit().  If your
+ * architecture violates this assumption, RCU will give you what you
+ * deserve, good and hard.  But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
  */
-void rcu_exit_nohz(void)
+void rcu_irq_exit(void)
 {
 	unsigned long flags;
+	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (rdtp->dynticks_nesting++) {
-		local_irq_restore(flags);
-		return;
-	}
+	oldval = rdtp->dynticks_nesting;
+	rdtp->dynticks_nesting--;
+	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+	if (rdtp->dynticks_nesting)
+		trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting);
+	else
+		rcu_idle_enter_common(rdtp, oldval);
+	local_irq_restore(flags);
+}
+
+/*
+ * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle
+ *
+ * If the new value of the ->dynticks_nesting counter was previously zero,
+ * we really have exited idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
+{
 	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
 	smp_mb__after_atomic_inc();  /* See above. */
 	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
-	trace_rcu_dyntick("End");
+	rcu_cleanup_after_idle(smp_processor_id());
+	trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting);
+	if (!is_idle_task(current)) {
+		struct task_struct *idle = idle_task(smp_processor_id());
+
+		trace_rcu_dyntick("Error on exit: not idle task",
+				  oldval, rdtp->dynticks_nesting);
+		ftrace_dump(DUMP_ALL);
+		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
+			  current->pid, current->comm,
+			  idle->pid, idle->comm); /* must be idle task! */
+	}
+}
+
+/**
+ * rcu_idle_exit - inform RCU that current CPU is leaving idle
+ *
+ * Exit idle mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections can occur.
+ *
+ * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NESTING to
+ * allow for the possibility of usermode upcalls messing up our count
+ * of interrupt nesting level during the busy period that is just
+ * now starting.
+ */
+void rcu_idle_exit(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+	long long oldval;
+
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	oldval = rdtp->dynticks_nesting;
+	WARN_ON_ONCE(oldval != 0);
+	rdtp->dynticks_nesting = DYNTICK_TASK_NESTING;
+	rcu_idle_exit_common(rdtp, oldval);
+	local_irq_restore(flags);
+}
+
+/**
+ * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
+ *
+ * Enter an interrupt handler, which might possibly result in exiting
+ * idle mode, in other words, entering the mode in which read-side critical
+ * sections can occur.
+ *
+ * Note that the Linux kernel is fully capable of entering an interrupt
+ * handler that it never exits, for example when doing upcalls to
+ * user mode!  This code assumes that the idle loop never does upcalls to
+ * user mode.  If your architecture does do upcalls from the idle loop (or
+ * does anything else that results in unbalanced calls to the irq_enter()
+ * and irq_exit() functions), RCU will give you what you deserve, good
+ * and hard.  But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
+ */
+void rcu_irq_enter(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+	long long oldval;
+
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	oldval = rdtp->dynticks_nesting;
+	rdtp->dynticks_nesting++;
+	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+	if (oldval)
+		trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting);
+	else
+		rcu_idle_exit_common(rdtp, oldval);
 	local_irq_restore(flags);
 }
 
@@ -442,27 +562,37 @@ void rcu_nmi_exit(void)
 	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
+#ifdef CONFIG_PROVE_RCU
+
 /**
- * rcu_irq_enter - inform RCU of entry to hard irq context
+ * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
  *
- * If the CPU was idle with dynamic ticks active, this updates the
- * rdtp->dynticks to let the RCU handling know that the CPU is active.
+ * If the current CPU is in its idle loop and is neither in an interrupt
+ * or NMI handler, return true.
  */
-void rcu_irq_enter(void)
+int rcu_is_cpu_idle(void)
 {
-	rcu_exit_nohz();
+	int ret;
+
+	preempt_disable();
+	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
+	preempt_enable();
+	return ret;
 }
+EXPORT_SYMBOL(rcu_is_cpu_idle);
+
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
 /**
- * rcu_irq_exit - inform RCU of exit from hard irq context
+ * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
  *
- * If the CPU was idle with dynamic ticks active, update the rdp->dynticks
- * to put let the RCU handling be aware that the CPU is going back to idle
- * with no ticks.
+ * If the current CPU is idle or running at a first-level (not nested)
+ * interrupt from idle, return true.  The caller must have at least
+ * disabled preemption.
  */
-void rcu_irq_exit(void)
+int rcu_is_cpu_rrupt_from_idle(void)
 {
-	rcu_enter_nohz();
+	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
 }
 
 #ifdef CONFIG_SMP
@@ -475,7 +605,7 @@ void rcu_irq_exit(void)
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
-	return 0;
+	return (rdp->dynticks_snap & 0x1) == 0;
 }
 
 /*
@@ -512,26 +642,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #endif /* #ifdef CONFIG_SMP */
 
-#else /* #ifdef CONFIG_NO_HZ */
-
-#ifdef CONFIG_SMP
-
-static int dyntick_save_progress_counter(struct rcu_data *rdp)
-{
-	return 0;
-}
-
-static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
-{
-	return rcu_implicit_offline_qs(rdp);
-}
-
-#endif /* #ifdef CONFIG_SMP */
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
-int rcu_cpu_stall_suppress __read_mostly;
-
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
@@ -866,8 +976,8 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	/* Advance to a new grace period and initialize state. */
 	rsp->gpnum++;
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, "start");
-	WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT);
-	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
+	WARN_ON_ONCE(rsp->fqs_state == RCU_GP_INIT);
+	rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);
 
@@ -877,7 +987,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
 		rnp->completed = rsp->completed;
-		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+		rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state OK */
 		rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
 		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
@@ -927,7 +1037,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
-	rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+	rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
@@ -991,7 +1101,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 
 	rsp->completed = rsp->gpnum;  /* Declare the grace period complete. */
 	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
-	rsp->signaled = RCU_GP_IDLE;
+	rsp->fqs_state = RCU_GP_IDLE;
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
 }
 
@@ -1221,7 +1331,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	else
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (need_report & RCU_OFL_TASKS_EXP_GP)
-		rcu_report_exp_rnp(rsp, rnp);
+		rcu_report_exp_rnp(rsp, rnp, true);
 	rcu_node_kthread_setaffinity(rnp, -1);
 }
 
@@ -1263,7 +1373,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* If no callbacks are ready, just return.*/
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
 		trace_rcu_batch_start(rsp->name, 0, 0);
-		trace_rcu_batch_end(rsp->name, 0);
+		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
+				    need_resched(), is_idle_task(current),
+				    rcu_is_callbacks_kthread());
 		return;
 	}
 
@@ -1291,12 +1403,17 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 		debug_rcu_head_unqueue(list);
 		__rcu_reclaim(rsp->name, list);
 		list = next;
-		if (++count >= bl)
+		/* Stop only if limit reached and CPU has something to do. */
+		if (++count >= bl &&
+		    (need_resched() ||
+		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
 			break;
 	}
 
 	local_irq_save(flags);
-	trace_rcu_batch_end(rsp->name, count);
+	trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
+			    is_idle_task(current),
+			    rcu_is_callbacks_kthread());
 
 	/* Update count, and requeue any remaining callbacks. */
 	rdp->qlen -= count;
@@ -1334,16 +1451,14 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
  * Also schedule RCU core processing.
  *
- * This function must be called with hardirqs disabled.  It is normally
+ * This function must be called from hardirq context.  It is normally
  * invoked from the scheduling-clock interrupt.  If rcu_pending returns
  * false, there is no point in invoking rcu_check_callbacks().
  */
 void rcu_check_callbacks(int cpu, int user)
 {
 	trace_rcu_utilization("Start scheduler-tick");
-	if (user ||
-	    (idle_cpu(cpu) && rcu_scheduler_active &&
-	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	if (user || rcu_is_cpu_rrupt_from_idle()) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
@@ -1457,7 +1572,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		goto unlock_fqs_ret;  /* no GP in progress, time updated. */
 	}
 	rsp->fqs_active = 1;
-	switch (rsp->signaled) {
+	switch (rsp->fqs_state) {
 	case RCU_GP_IDLE:
 	case RCU_GP_INIT:
 
@@ -1473,7 +1588,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		force_qs_rnp(rsp, dyntick_save_progress_counter);
 		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
 		if (rcu_gp_in_progress(rsp))
-			rsp->signaled = RCU_FORCE_QS;
+			rsp->fqs_state = RCU_FORCE_QS;
 		break;
 
 	case RCU_FORCE_QS:
@@ -1812,7 +1927,7 @@ static int rcu_pending(int cpu)
  * by the current CPU, even if none need be done immediately, returning
  * 1 if so.
  */
-static int rcu_needs_cpu_quick_check(int cpu)
+static int rcu_cpu_has_callbacks(int cpu)
 {
 	/* RCU callbacks either ready or pending? */
 	return per_cpu(rcu_sched_data, cpu).nxtlist ||
@@ -1913,9 +2028,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
 	rdp->qlen = 0;
-#ifdef CONFIG_NO_HZ
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-#endif /* #ifdef CONFIG_NO_HZ */
+	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING);
+	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1942,6 +2057,10 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
+	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_NESTING;
+	atomic_set(&rdp->dynticks->dynticks,
+		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
+	rcu_prepare_for_idle_init(cpu);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/*
@@ -2023,6 +2142,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		rcu_send_cbs_to_online(&rcu_bh_state);
 		rcu_send_cbs_to_online(&rcu_sched_state);
 		rcu_preempt_send_cbs_to_online();
+		rcu_cleanup_after_idle(cpu);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 849ce9ec51fe..fddff92d6676 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,9 +84,10 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track irq/process nesting level. */
-	int dynticks_nmi_nesting; /* Track NMI nesting level. */
-	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
+	long long dynticks_nesting; /* Track irq/process nesting level. */
+				    /* Process level is worth LLONG_MAX/2. */
+	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
+	atomic_t dynticks;	    /* Even value for idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -274,16 +275,12 @@ struct rcu_data {
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
 
-#ifdef CONFIG_NO_HZ
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-#endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
-#ifdef CONFIG_NO_HZ
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
-#endif /* #ifdef CONFIG_NO_HZ */
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long resched_ipi;	/* Sent a resched IPI. */
 
@@ -302,16 +299,12 @@ struct rcu_data {
 	struct rcu_state *rsp;
 };
 
-/* Values for signaled field in struct rcu_state. */
+/* Values for fqs_state field in struct rcu_state. */
 #define RCU_GP_IDLE		0	/* No grace period in progress. */
 #define RCU_GP_INIT		1	/* Grace period being initialized. */
 #define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
 #define RCU_FORCE_QS		3	/* Need to force quiescent state. */
-#ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
-#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT		RCU_FORCE_QS
-#endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
 
@@ -361,7 +354,7 @@ struct rcu_state {
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
-	u8	signaled ____cacheline_internodealigned_in_smp;
+	u8	fqs_state ____cacheline_internodealigned_in_smp;
 						/* Force QS state. */
 	u8	fqs_active;			/* force_quiescent_state() */
 						/*  is running. */
@@ -451,7 +444,8 @@ static void rcu_preempt_check_callbacks(int cpu);
 static void rcu_preempt_process_callbacks(void);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake);
 #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
 static int rcu_preempt_pending(int cpu);
 static int rcu_preempt_needs_cpu(int cpu);
@@ -461,6 +455,7 @@ static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
+static bool rcu_is_callbacks_kthread(void);
 #ifdef CONFIG_RCU_BOOST
 static void rcu_preempt_do_callbacks(void);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
@@ -473,5 +468,8 @@ static void rcu_yield(void (*f)(unsigned long), unsigned long arg);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
 static void __cpuinit rcu_prepare_kthreads(int cpu);
+static void rcu_prepare_for_idle_init(int cpu);
+static void rcu_cleanup_after_idle(int cpu);
+static void rcu_prepare_for_idle(int cpu);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 4b9b9f8a4184..8bb35d73e1f9 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -312,6 +312,7 @@ static noinline void rcu_read_unlock_special(struct task_struct *t)
 {
 	int empty;
 	int empty_exp;
+	int empty_exp_now;
 	unsigned long flags;
 	struct list_head *np;
 #ifdef CONFIG_RCU_BOOST
@@ -382,8 +383,10 @@ static noinline void rcu_read_unlock_special(struct task_struct *t)
 		/*
 		 * If this was the last task on the current list, and if
 		 * we aren't waiting on any CPUs, report the quiescent state.
-		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
+		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
+		 * so we must take a snapshot of the expedited state.
 		 */
+		empty_exp_now = !rcu_preempted_readers_exp(rnp);
 		if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report("preempt_rcu",
 							 rnp->gpnum,
@@ -406,8 +409,8 @@ static noinline void rcu_read_unlock_special(struct task_struct *t)
 		 * If this was the last task on the expedited lists,
 		 * then we need to report up the rcu_node hierarchy.
 		 */
-		if (!empty_exp && !rcu_preempted_readers_exp(rnp))
-			rcu_report_exp_rnp(&rcu_preempt_state, rnp);
+		if (!empty_exp && empty_exp_now)
+			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -729,9 +732,13 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
  *
+ * Most callers will set the "wake" flag, but the task initiating the
+ * expedited grace period need not wake itself.
+ *
  * Caller must hold sync_rcu_preempt_exp_mutex.
  */
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -744,7 +751,8 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			wake_up(&sync_rcu_preempt_exp_wq);
+			if (wake)
+				wake_up(&sync_rcu_preempt_exp_wq);
 			break;
 		}
 		mask = rnp->grpmask;
@@ -777,7 +785,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 		must_wait = 1;
 	}
 	if (!must_wait)
-		rcu_report_exp_rnp(rsp, rnp);
+		rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */
 }
 
 /*
@@ -1069,9 +1077,9 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
  * report on tasks preempted in RCU read-side critical sections during
  * expedited RCU grace periods.
  */
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake)
 {
-	return;
 }
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -1157,8 +1165,6 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
-static struct lock_class_key rcu_boost_class;
-
 /*
  * Carry out RCU priority boosting on the task indicated by ->exp_tasks
  * or ->boost_tasks, advancing the pointer to the next task in the
@@ -1221,15 +1227,13 @@ static int rcu_boost(struct rcu_node *rnp)
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
-	/* Avoid lockdep false positives.  This rt_mutex is its own thing. */
-	lockdep_set_class_and_name(&mtx.wait_lock, &rcu_boost_class,
-				   "rcu_boost_mutex");
 	t->rcu_boost_mutex = &mtx;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
 	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
 
-	return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL;
+	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
+	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
 }
 
 /*
@@ -1329,6 +1333,15 @@ static void invoke_rcu_callbacks_kthread(void)
 }
 
 /*
+ * Is the current CPU running the RCU-callbacks kthread?
+ * Caller must have preemption disabled.
+ */
+static bool rcu_is_callbacks_kthread(void)
+{
+	return __get_cpu_var(rcu_cpu_kthread_task) == current;
+}
+
+/*
  * Set the affinity of the boost kthread.  The CPU-hotplug locks are
  * held, so no one should be messing with the existence of the boost
  * kthread.
@@ -1772,6 +1785,11 @@ static void invoke_rcu_callbacks_kthread(void)
 	WARN_ON_ONCE(1);
 }
 
+static bool rcu_is_callbacks_kthread(void)
+{
+	return false;
+}
+
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
@@ -1907,7 +1925,7 @@ void synchronize_sched_expedited(void)
 		 * grace period works for us.
 		 */
 		get_online_cpus();
-		snap = atomic_read(&sync_sched_expedited_started) - 1;
+		snap = atomic_read(&sync_sched_expedited_started);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
 
@@ -1939,88 +1957,243 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
  * 1 if so.  This function is part of the RCU implementation; it is -not-
  * an exported member of the RCU API.
  *
- * Because we have preemptible RCU, just check whether this CPU needs
- * any flavor of RCU.  Do not chew up lots of CPU cycles with preemption
- * disabled in a most-likely vain attempt to cause RCU not to need this CPU.
+ * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
+ * any flavor of RCU.
  */
 int rcu_needs_cpu(int cpu)
 {
-	return rcu_needs_cpu_quick_check(cpu);
+	return rcu_cpu_has_callbacks(cpu);
+}
+
+/*
+ * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it.
+ */
+static void rcu_prepare_for_idle_init(int cpu)
+{
+}
+
+/*
+ * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
+ * after it.
+ */
+static void rcu_cleanup_after_idle(int cpu)
+{
+}
+
+/*
+ * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=y,
+ * is nothing.
+ */
+static void rcu_prepare_for_idle(int cpu)
+{
 }
 
 #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
-#define RCU_NEEDS_CPU_FLUSHES 5
+/*
+ * This code is invoked when a CPU goes idle, at which point we want
+ * to have the CPU do everything required for RCU so that it can enter
+ * the energy-efficient dyntick-idle mode.  This is handled by a
+ * state machine implemented by rcu_prepare_for_idle() below.
+ *
+ * The following three proprocessor symbols control this state machine:
+ *
+ * RCU_IDLE_FLUSHES gives the maximum number of times that we will attempt
+ *	to satisfy RCU.  Beyond this point, it is better to incur a periodic
+ *	scheduling-clock interrupt than to loop through the state machine
+ *	at full power.
+ * RCU_IDLE_OPT_FLUSHES gives the number of RCU_IDLE_FLUSHES that are
+ *	optional if RCU does not need anything immediately from this
+ *	CPU, even if this CPU still has RCU callbacks queued.  The first
+ *	times through the state machine are mandatory: we need to give
+ *	the state machine a chance to communicate a quiescent state
+ *	to the RCU core.
+ * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
+ *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
+ *	is sized to be roughly one RCU grace period.  Those energy-efficiency
+ *	benchmarkers who might otherwise be tempted to set this to a large
+ *	number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
+ *	system.  And if you are -that- concerned about energy efficiency,
+ *	just power the system down and be done with it!
+ *
+ * The values below work well in practice.  If future workloads require
+ * adjustment, they can be converted into kernel config parameters, though
+ * making the state machine smarter might be a better option.
+ */
+#define RCU_IDLE_FLUSHES 5		/* Number of dyntick-idle tries. */
+#define RCU_IDLE_OPT_FLUSHES 3		/* Optional dyntick-idle tries. */
+#define RCU_IDLE_GP_DELAY 6		/* Roughly one grace period. */
+
 static DEFINE_PER_CPU(int, rcu_dyntick_drain);
 static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
+static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer);
+static ktime_t rcu_idle_gp_wait;
 
 /*
- * Check to see if any future RCU-related work will need to be done
- * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
+ * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
+ * callbacks on this CPU, (2) this CPU has not yet attempted to enter
+ * dyntick-idle mode, or (3) this CPU is in the process of attempting to
+ * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
+ * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
+ * it is better to incur scheduling-clock interrupts than to spin
+ * continuously for the same time duration!
+ */
+int rcu_needs_cpu(int cpu)
+{
+	/* If no callbacks, RCU doesn't need the CPU. */
+	if (!rcu_cpu_has_callbacks(cpu))
+		return 0;
+	/* Otherwise, RCU needs the CPU only if it recently tried and failed. */
+	return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
+}
+
+/*
+ * Timer handler used to force CPU to start pushing its remaining RCU
+ * callbacks in the case where it entered dyntick-idle mode with callbacks
+ * pending.  The hander doesn't really need to do anything because the
+ * real work is done upon re-entry to idle, or by the next scheduling-clock
+ * interrupt should idle not be re-entered.
+ */
+static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
+{
+	trace_rcu_prep_idle("Timer");
+	return HRTIMER_NORESTART;
+}
+
+/*
+ * Initialize the timer used to pull CPUs out of dyntick-idle mode.
+ */
+static void rcu_prepare_for_idle_init(int cpu)
+{
+	static int firsttime = 1;
+	struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
+
+	hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtp->function = rcu_idle_gp_timer_func;
+	if (firsttime) {
+		unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY);
+
+		rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000);
+		firsttime = 0;
+	}
+}
+
+/*
+ * Clean up for exit from idle.  Because we are exiting from idle, there
+ * is no longer any point to rcu_idle_gp_timer, so cancel it.  This will
+ * do nothing if this timer is not active, so just cancel it unconditionally.
+ */
+static void rcu_cleanup_after_idle(int cpu)
+{
+	hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu));
+}
+
+/*
+ * Check to see if any RCU-related work can be done by the current CPU,
+ * and if so, schedule a softirq to get it done.  This function is part
+ * of the RCU implementation; it is -not- an exported member of the RCU API.
  *
- * Because we are not supporting preemptible RCU, attempt to accelerate
- * any current grace periods so that RCU no longer needs this CPU, but
- * only if all other CPUs are already in dynticks-idle mode.  This will
- * allow the CPU cores to be powered down immediately, as opposed to after
- * waiting many milliseconds for grace periods to elapse.
+ * The idea is for the current CPU to clear out all work required by the
+ * RCU core for the current grace period, so that this CPU can be permitted
+ * to enter dyntick-idle mode.  In some cases, it will need to be awakened
+ * at the end of the grace period by whatever CPU ends the grace period.
+ * This allows CPUs to go dyntick-idle more quickly, and to reduce the
+ * number of wakeups by a modest integer factor.
  *
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
  * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
  * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ *
+ * The caller must have disabled interrupts.
  */
-int rcu_needs_cpu(int cpu)
+static void rcu_prepare_for_idle(int cpu)
 {
-	int c = 0;
-	int snap;
-	int thatcpu;
-
-	/* Check for being in the holdoff period. */
-	if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies)
-		return rcu_needs_cpu_quick_check(cpu);
-
-	/* Don't bother unless we are the last non-dyntick-idle CPU. */
-	for_each_online_cpu(thatcpu) {
-		if (thatcpu == cpu)
-			continue;
-		snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
-						     thatcpu).dynticks);
-		smp_mb(); /* Order sampling of snap with end of grace period. */
-		if ((snap & 0x1) != 0) {
-			per_cpu(rcu_dyntick_drain, cpu) = 0;
-			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
-			return rcu_needs_cpu_quick_check(cpu);
-		}
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	/*
+	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
+	 * Also reset state to avoid prejudicing later attempts.
+	 */
+	if (!rcu_cpu_has_callbacks(cpu)) {
+		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+		per_cpu(rcu_dyntick_drain, cpu) = 0;
+		local_irq_restore(flags);
+		trace_rcu_prep_idle("No callbacks");
+		return;
+	}
+
+	/*
+	 * If in holdoff mode, just return.  We will presumably have
+	 * refrained from disabling the scheduling-clock tick.
+	 */
+	if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
+		local_irq_restore(flags);
+		trace_rcu_prep_idle("In holdoff");
+		return;
 	}
 
 	/* Check and update the rcu_dyntick_drain sequencing. */
 	if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
 		/* First time through, initialize the counter. */
-		per_cpu(rcu_dyntick_drain, cpu) = RCU_NEEDS_CPU_FLUSHES;
+		per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
+	} else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
+		   !rcu_pending(cpu)) {
+		/* Can we go dyntick-idle despite still having callbacks? */
+		trace_rcu_prep_idle("Dyntick with callbacks");
+		per_cpu(rcu_dyntick_drain, cpu) = 0;
+		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+		hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
+			      rcu_idle_gp_wait, HRTIMER_MODE_REL);
+		return; /* Nothing more to do immediately. */
 	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
 		/* We have hit the limit, so time to give up. */
 		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
-		return rcu_needs_cpu_quick_check(cpu);
+		local_irq_restore(flags);
+		trace_rcu_prep_idle("Begin holdoff");
+		invoke_rcu_core();  /* Force the CPU out of dyntick-idle. */
+		return;
 	}
 
-	/* Do one step pushing remaining RCU callbacks through. */
+	/*
+	 * Do one step of pushing the remaining RCU callbacks through
+	 * the RCU core state machine.
+	 */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	if (per_cpu(rcu_preempt_data, cpu).nxtlist) {
+		local_irq_restore(flags);
+		rcu_preempt_qs(cpu);
+		force_quiescent_state(&rcu_preempt_state, 0);
+		local_irq_save(flags);
+	}
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 	if (per_cpu(rcu_sched_data, cpu).nxtlist) {
+		local_irq_restore(flags);
 		rcu_sched_qs(cpu);
 		force_quiescent_state(&rcu_sched_state, 0);
-		c = c || per_cpu(rcu_sched_data, cpu).nxtlist;
+		local_irq_save(flags);
 	}
 	if (per_cpu(rcu_bh_data, cpu).nxtlist) {
+		local_irq_restore(flags);
 		rcu_bh_qs(cpu);
 		force_quiescent_state(&rcu_bh_state, 0);
-		c = c || per_cpu(rcu_bh_data, cpu).nxtlist;
+		local_irq_save(flags);
 	}
 
-	/* If RCU callbacks are still pending, RCU still needs this CPU. */
-	if (c)
+	/*
+	 * If RCU callbacks are still pending, RCU still needs this CPU.
+	 * So try forcing the callbacks through the grace period.
+	 */
+	if (rcu_cpu_has_callbacks(cpu)) {
+		local_irq_restore(flags);
+		trace_rcu_prep_idle("More callbacks");
 		invoke_rcu_core();
-	return c;
+	} else {
+		local_irq_restore(flags);
+		trace_rcu_prep_idle("Callbacks drained");
+	}
 }
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 9feffa4c0695..654cfe67f0d1 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -67,13 +67,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
 		   rdp->qs_pending);
-#ifdef CONFIG_NO_HZ
-	seq_printf(m, " dt=%d/%d/%d df=%lu",
+	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
 		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
-#endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
 	seq_printf(m, " ql=%ld qs=%c%c%c%c",
 		   rdp->qlen,
@@ -141,13 +139,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesce, rdp->passed_quiesce_gpnum,
 		   rdp->qs_pending);
-#ifdef CONFIG_NO_HZ
-	seq_printf(m, ",%d,%d,%d,%lu",
+	seq_printf(m, ",%d,%llx,%d,%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
 		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
-#endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
 	seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen,
 		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
@@ -171,9 +167,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
 	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\",");
-#ifdef CONFIG_NO_HZ
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
-#endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\"");
 #ifdef CONFIG_RCU_BOOST
 	seq_puts(m, "\"kt\",\"ktl\"");
@@ -278,7 +272,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 	gpnum = rsp->gpnum;
 	seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
 		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
-		   rsp->completed, gpnum, rsp->signaled,
+		   rsp->completed, gpnum, rsp->fqs_state,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index f9d8482dd487..a242e691c993 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -579,7 +579,6 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct rt_mutex_waiter *waiter)
 {
 	int ret = 0;
-	int was_disabled;
 
 	for (;;) {
 		/* Try to acquire the lock: */
@@ -602,17 +601,10 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 		raw_spin_unlock(&lock->wait_lock);
 
-		was_disabled = irqs_disabled();
-		if (was_disabled)
-			local_irq_enable();
-
 		debug_rt_mutex_print_deadlock(waiter);
 
 		schedule_rt_mutex(lock);
 
-		if (was_disabled)
-			local_irq_disable();
-
 		raw_spin_lock(&lock->wait_lock);
 		set_current_state(state);
 	}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 2c71d91efff0..4eb3a0fa351e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -347,12 +347,12 @@ void irq_exit(void)
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
-	rcu_irq_exit();
 #ifdef CONFIG_NO_HZ
 	/* Make sure that timer wheel updates are propagated */
 	if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
-		tick_nohz_stop_sched_tick(0);
+		tick_nohz_irq_exit();
 #endif
+	rcu_irq_exit();
 	preempt_enable_no_resched();
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 40420644d0ba..0ec8b832ab6b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -275,42 +275,17 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
-/**
- * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
- *
- * When the next event is more than a tick into the future, stop the idle tick
- * Called either from the idle loop or from irq_exit() when an idle period was
- * just interrupted by an interrupt which did not cause a reschedule.
- */
-void tick_nohz_stop_sched_tick(int inidle)
+static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 {
-	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
-	struct tick_sched *ts;
+	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
 	ktime_t last_update, expires, now;
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
 	int cpu;
 
-	local_irq_save(flags);
-
 	cpu = smp_processor_id();
 	ts = &per_cpu(tick_cpu_sched, cpu);
 
-	/*
-	 * Call to tick_nohz_start_idle stops the last_update_time from being
-	 * updated. Thus, it must not be called in the event we are called from
-	 * irq_exit() with the prior state different than idle.
-	 */
-	if (!inidle && !ts->inidle)
-		goto end;
-
-	/*
-	 * Set ts->inidle unconditionally. Even if the system did not
-	 * switch to NOHZ mode the cpu frequency governers rely on the
-	 * update of the idle time accounting in tick_nohz_start_idle().
-	 */
-	ts->inidle = 1;
-
 	now = tick_nohz_start_idle(cpu, ts);
 
 	/*
@@ -326,10 +301,10 @@ void tick_nohz_stop_sched_tick(int inidle)
 	}
 
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
-		goto end;
+		return;
 
 	if (need_resched())
-		goto end;
+		return;
 
 	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
 		static int ratelimit;
@@ -339,7 +314,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 			       (unsigned int) local_softirq_pending());
 			ratelimit++;
 		}
-		goto end;
+		return;
 	}
 
 	ts->idle_calls++;
@@ -434,7 +409,6 @@ void tick_nohz_stop_sched_tick(int inidle)
 			ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
-			rcu_enter_nohz();
 		}
 
 		ts->idle_sleeps++;
@@ -472,8 +446,56 @@ out:
 	ts->next_jiffies = next_jiffies;
 	ts->last_jiffies = last_jiffies;
 	ts->sleep_length = ktime_sub(dev->next_event, now);
-end:
-	local_irq_restore(flags);
+}
+
+/**
+ * tick_nohz_idle_enter - stop the idle tick from the idle task
+ *
+ * When the next event is more than a tick into the future, stop the idle tick
+ * Called when we start the idle loop.
+ *
+ * The arch is responsible of calling:
+ *
+ * - rcu_idle_enter() after its last use of RCU before the CPU is put
+ *  to sleep.
+ * - rcu_idle_exit() before the first use of RCU after the CPU is woken up.
+ */
+void tick_nohz_idle_enter(void)
+{
+	struct tick_sched *ts;
+
+	WARN_ON_ONCE(irqs_disabled());
+
+	local_irq_disable();
+
+	ts = &__get_cpu_var(tick_cpu_sched);
+	/*
+	 * set ts->inidle unconditionally. even if the system did not
+	 * switch to nohz mode the cpu frequency governers rely on the
+	 * update of the idle time accounting in tick_nohz_start_idle().
+	 */
+	ts->inidle = 1;
+	tick_nohz_stop_sched_tick(ts);
+
+	local_irq_enable();
+}
+
+/**
+ * tick_nohz_irq_exit - update next tick event from interrupt exit
+ *
+ * When an interrupt fires while we are idle and it doesn't cause
+ * a reschedule, it may still add, modify or delete a timer, enqueue
+ * an RCU callback, etc...
+ * So we need to re-calculate and reprogram the next tick event.
+ */
+void tick_nohz_irq_exit(void)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+	if (!ts->inidle)
+		return;
+
+	tick_nohz_stop_sched_tick(ts);
 }
 
 /**
@@ -515,11 +537,13 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 }
 
 /**
- * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
+ * tick_nohz_idle_exit - restart the idle tick from the idle task
  *
  * Restart the idle tick when the CPU is woken up from idle
+ * This also exit the RCU extended quiescent state. The CPU
+ * can use RCU again after this function is called.
  */
-void tick_nohz_restart_sched_tick(void)
+void tick_nohz_idle_exit(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -529,6 +553,7 @@ void tick_nohz_restart_sched_tick(void)
 	ktime_t now;
 
 	local_irq_disable();
+
 	if (ts->idle_active || (ts->inidle && ts->tick_stopped))
 		now = ktime_get();
 
@@ -543,8 +568,6 @@ void tick_nohz_restart_sched_tick(void)
 
 	ts->inidle = 0;
 
-	rcu_exit_nohz();
-
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	tick_do_update_jiffies64(now);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f2bd275bb60f..a043d224adf6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4775,6 +4775,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
 	__ftrace_dump(true, oops_dump_mode);
 }
+EXPORT_SYMBOL_GPL(ftrace_dump);
 
 __init static int tracer_alloc_buffers(void)
 {