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

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle are:

   - Documentation updates.

   - Miscellaneous fixes.

   - Preemptible-RCU fixes, including fixing an old bug in the
     interaction of RCU priority boosting and CPU hotplug.

   - SRCU updates.

   - RCU CPU stall-warning updates.

   - RCU torture-test updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  rcu: Initialize tiny RCU stall-warning timeouts at boot
  rcu: Fix RCU CPU stall detection in tiny implementation
  rcu: Add GP-kthread-starvation checks to CPU stall warnings
  rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors
  rcu: Optionally run grace-period kthreads at real-time priority
  ksoftirqd: Use new cond_resched_rcu_qs() function
  ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
  rcutorture: Add more diagnostics in rcu_barrier() test failure case
  torture: Flag console.log file to prevent holdovers from earlier runs
  torture: Add "-enable-kvm -soundhw pcspk" to qemu command line
  rcutorture: Handle different mpstat versions
  rcutorture: Check from beginning to end of grace period
  rcu: Remove redundant rcu_batches_completed() declaration
  rcutorture: Drop rcu_torture_completed() and friends
  rcu: Provide rcu_batches_completed_sched() for TINY_RCU
  rcutorture: Use unsigned for Reader Batch computations
  rcutorture: Make build-output parsing correctly flag RCU's warnings
  rcu: Make _batches_completed() functions return unsigned long
  rcutorture: Issue warnings on close calls due to Reader Batch blows
  documentation: Fix smp typo in memory-barriers.txt
  ...

14 files changed, 440 insertions, 518 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5d220234b3ca..1972b161c61e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -58,22 +58,23 @@ static int cpu_hotplug_disabled;
 
 static struct {
 	struct task_struct *active_writer;
-	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/* wait queue to wake up the active_writer */
+	wait_queue_head_t wq;
+	/* verifies that no writer will get active while readers are active */
+	struct mutex lock;
 	/*
 	 * Also blocks the new readers during
 	 * an ongoing cpu hotplug operation.
 	 */
-	int refcount;
-	/* And allows lockless put_online_cpus(). */
-	atomic_t puts_pending;
+	atomic_t refcount;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif
 } cpu_hotplug = {
 	.active_writer = NULL,
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-	.refcount = 0,
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	.dep_map = {.name = "cpu_hotplug.lock" },
 #endif
@@ -86,15 +87,6 @@ static struct {
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
-static void apply_puts_pending(int max)
-{
-	int delta;
-
-	if (atomic_read(&cpu_hotplug.puts_pending) >= max) {
-		delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
-		cpu_hotplug.refcount -= delta;
-	}
-}
 
 void get_online_cpus(void)
 {
@@ -103,8 +95,7 @@ void get_online_cpus(void)
 		return;
 	cpuhp_lock_acquire_read();
 	mutex_lock(&cpu_hotplug.lock);
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 }
 EXPORT_SYMBOL_GPL(get_online_cpus);
@@ -116,8 +107,7 @@ bool try_get_online_cpus(void)
 	if (!mutex_trylock(&cpu_hotplug.lock))
 		return false;
 	cpuhp_lock_acquire_tryread();
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 	return true;
 }
@@ -125,20 +115,18 @@ EXPORT_SYMBOL_GPL(try_get_online_cpus);
 
 void put_online_cpus(void)
 {
+	int refcount;
+
 	if (cpu_hotplug.active_writer == current)
 		return;
-	if (!mutex_trylock(&cpu_hotplug.lock)) {
-		atomic_inc(&cpu_hotplug.puts_pending);
-		cpuhp_lock_release();
-		return;
-	}
 
-	if (WARN_ON(!cpu_hotplug.refcount))
-		cpu_hotplug.refcount++; /* try to fix things up */
+	refcount = atomic_dec_return(&cpu_hotplug.refcount);
+	if (WARN_ON(refcount < 0)) /* try to fix things up */
+		atomic_inc(&cpu_hotplug.refcount);
+
+	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
+		wake_up(&cpu_hotplug.wq);
 
-	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
-		wake_up_process(cpu_hotplug.active_writer);
-	mutex_unlock(&cpu_hotplug.lock);
 	cpuhp_lock_release();
 
 }
@@ -168,18 +156,20 @@ EXPORT_SYMBOL_GPL(put_online_cpus);
  */
 void cpu_hotplug_begin(void)
 {
-	cpu_hotplug.active_writer = current;
+	DEFINE_WAIT(wait);
 
+	cpu_hotplug.active_writer = current;
 	cpuhp_lock_acquire();
+
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
-		apply_puts_pending(1);
-		if (likely(!cpu_hotplug.refcount))
-			break;
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (likely(!atomic_read(&cpu_hotplug.refcount)))
+				break;
 		mutex_unlock(&cpu_hotplug.lock);
 		schedule();
 	}
+	finish_wait(&cpu_hotplug.wq, &wait);
 }
 
 void cpu_hotplug_done(void)
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 4803da6eab62..ae9fc7cc360e 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -402,6 +402,7 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
 
+#ifdef CONFIG_SRCU
 /*
  *	SRCU notifier chain routines.    Registration and unregistration
  *	use a mutex, and call_chain is synchronized by SRCU (no locks).
@@ -528,6 +529,8 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh)
 }
 EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
 
+#endif /* CONFIG_SRCU */
+
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
 int notrace notify_die(enum die_val val, const char *str,
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 48b28d387c7f..7e01f78f0417 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -251,6 +251,7 @@ config APM_EMULATION
 
 config PM_OPP
 	bool
+	select SRCU
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
 	  voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index e6fae503d1bc..50a808424b06 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,4 +1,5 @@
-obj-y += update.o srcu.o
+obj-y += update.o
+obj-$(CONFIG_SRCU) += srcu.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_PREEMPT_RCU) += tree.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 07bb02eda844..80adef7d4c3d 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -137,4 +137,10 @@ int rcu_jiffies_till_stall_check(void);
 
 void rcu_early_boot_tests(void);
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 4d559baf06e0..30d42aa55d83 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -244,7 +244,8 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	int (*completed)(void);
+	unsigned long (*started)(void);
+	unsigned long (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -296,11 +297,6 @@ static void rcu_torture_read_unlock(int idx) __releases(RCU)
 	rcu_read_unlock();
 }
 
-static int rcu_torture_completed(void)
-{
-	return rcu_batches_completed();
-}
-
 /*
  * Update callback in the pipe.  This should be invoked after a grace period.
  */
@@ -356,7 +352,7 @@ rcu_torture_cb(struct rcu_head *p)
 		cur_ops->deferred_free(rp);
 }
 
-static int rcu_no_completed(void)
+static unsigned long rcu_no_completed(void)
 {
 	return 0;
 }
@@ -377,7 +373,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
+	.started	= rcu_batches_started,
+	.completed	= rcu_batches_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -407,11 +404,6 @@ static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
 	rcu_read_unlock_bh();
 }
 
-static int rcu_bh_torture_completed(void)
-{
-	return rcu_batches_completed_bh();
-}
-
 static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 {
 	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
@@ -423,7 +415,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
+	.started	= rcu_batches_started_bh,
+	.completed	= rcu_batches_completed_bh,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -466,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
@@ -510,7 +504,7 @@ static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
 	srcu_read_unlock(&srcu_ctl, idx);
 }
 
-static int srcu_torture_completed(void)
+static unsigned long srcu_torture_completed(void)
 {
 	return srcu_batches_completed(&srcu_ctl);
 }
@@ -564,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
@@ -600,7 +595,8 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
+	.started	= rcu_batches_started_sched,
+	.completed	= rcu_batches_completed_sched,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -638,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
@@ -1015,8 +1012,8 @@ static void rcutorture_trace_dump(void)
 static void rcu_torture_timer(unsigned long unused)
 {
 	int idx;
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	static DEFINE_TORTURE_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
@@ -1024,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused)
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
+	if (cur_ops->started)
+		started = cur_ops->started();
+	else
+		started = cur_ops->completed();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1047,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed_end = cur_ops->completed();
+	completed = cur_ops->completed();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
+					  started, completed);
 		rcutorture_trace_dump();
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
+	completed = completed - started;
+	if (cur_ops->started)
+		completed++;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1073,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused)
 static int
 rcu_torture_reader(void *arg)
 {
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct rcu_torture *p;
@@ -1093,7 +1095,10 @@ rcu_torture_reader(void *arg)
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
+		if (cur_ops->started)
+			started = cur_ops->started();
+		else
+			started = cur_ops->completed();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1114,14 +1119,16 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed_end = cur_ops->completed();
+		completed = cur_ops->completed();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
+						  ts, started, completed);
 			rcutorture_trace_dump();
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
+		completed = completed - started;
+		if (cur_ops->started)
+			completed++;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
@@ -1420,6 +1427,9 @@ static int rcu_torture_barrier(void *arg)
 		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
+			pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
+			       atomic_read(&barrier_cbs_invoked),
+			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
 		}
 		n_barrier_successes++;
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e037f3eb2f7b..445bf8ffe3fb 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 0db5649f8817..cc9ceca7bde1 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -47,54 +47,14 @@ static void __call_rcu(struct rcu_head *head,
 		       void (*func)(struct rcu_head *rcu),
 		       struct rcu_ctrlblk *rcp);
 
-static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-
 #include "tiny_plugin.h"
 
-/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */
-static void rcu_idle_enter_common(long long newval)
-{
-	if (newval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("--="),
-					    rcu_dynticks_nesting, newval));
-		rcu_dynticks_nesting = newval;
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
-				    rcu_dynticks_nesting, newval));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
-					    rcu_dynticks_nesting, newval));
-		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(); /* implies rcu_bh_inc() */
-	barrier();
-	rcu_dynticks_nesting = newval;
-}
-
 /*
  * 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).
+ * entered that mode.
  */
 void rcu_idle_enter(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) ==
-	    DYNTICK_TASK_NEST_VALUE)
-		newval = 0;
-	else
-		newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE;
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
@@ -103,55 +63,14 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
  */
 void rcu_irq_exit(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	newval = rcu_dynticks_nesting - 1;
-	WARN_ON_ONCE(newval < 0);
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_exit);
 
-/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */
-static void rcu_idle_exit_common(long long oldval)
-{
-	if (oldval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("++="),
-					    oldval, rcu_dynticks_nesting));
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: 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(rcu_dynticks_nesting < 0);
-	if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK)
-		rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
-		rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_idle_exit_common(oldval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
@@ -160,15 +79,6 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit);
  */
 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);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
@@ -179,23 +89,13 @@ EXPORT_SYMBOL_GPL(rcu_irq_enter);
  */
 bool notrace __rcu_is_watching(void)
 {
-	return rcu_dynticks_nesting;
+	return true;
 }
 EXPORT_SYMBOL(__rcu_is_watching);
 
 #endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
 /*
- * Test whether the current CPU was interrupted from idle.  Nested
- * interrupts don't count, we must be running at the first interrupt
- * level.
- */
-static int rcu_is_cpu_rrupt_from_idle(void)
-{
-	return rcu_dynticks_nesting <= 1;
-}
-
-/*
  * Helper function for rcu_sched_qs() and rcu_bh_qs().
  * Also irqs are disabled to avoid confusion due to interrupt handlers
  * invoking call_rcu().
@@ -250,7 +150,7 @@ void rcu_bh_qs(void)
 void rcu_check_callbacks(int user)
 {
 	RCU_TRACE(check_cpu_stalls());
-	if (user || rcu_is_cpu_rrupt_from_idle())
+	if (user)
 		rcu_sched_qs();
 	else if (!in_softirq())
 		rcu_bh_qs();
@@ -357,6 +257,11 @@ static void __call_rcu(struct rcu_head *head,
 	rcp->curtail = &head->next;
 	RCU_TRACE(rcp->qlen++);
 	local_irq_restore(flags);
+
+	if (unlikely(is_idle_task(current))) {
+		/* force scheduling for rcu_sched_qs() */
+		resched_cpu(0);
+	}
 }
 
 /*
@@ -383,6 +288,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
 
 	rcu_early_boot_tests();
 }
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 858c56569127..f94e209a10d6 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -145,17 +145,16 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 	rcp->ticks_this_gp++;
 	j = jiffies;
 	js = ACCESS_ONCE(rcp->jiffies_stall);
-	if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
+	if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
-		       rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
+		       rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
 		       jiffies - rcp->gp_start, rcp->qlen);
 		dump_stack();
-	}
-	if (*rcp->curtail && ULONG_CMP_GE(j, js))
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
 			3 * rcu_jiffies_till_stall_check() + 3;
-	else if (ULONG_CMP_GE(j, js))
+	} else if (ULONG_CMP_GE(j, js)) {
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+	}
 }
 
 static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7680fc275036..48d640ca1a05 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -156,6 +156,10 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
+/* rcuc/rcub kthread realtime priority */
+static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+module_param(kthread_prio, int, 0644);
+
 /*
  * Track the rcutorture test sequence number and the update version
  * number within a given test.  The rcutorture_testseq is incremented
@@ -215,6 +219,9 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
+DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
+
 /*
  * Let the RCU core know that this CPU has gone through the scheduler,
  * which is a quiescent state.  This is called when the need for a
@@ -284,6 +291,22 @@ void rcu_note_context_switch(void)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
+/*
+ * Register a quiesecent state for all RCU flavors.  If there is an
+ * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
+ * dyntick-idle quiescent state visible to other CPUs (but only for those
+ * RCU flavors in desparate need of a quiescent state, which will normally
+ * be none of them).  Either way, do a lightweight quiescent state for
+ * all RCU flavors.
+ */
+void rcu_all_qs(void)
+{
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
+	this_cpu_inc(rcu_qs_ctr);
+}
+EXPORT_SYMBOL_GPL(rcu_all_qs);
+
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -315,18 +338,54 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU-sched batches processed thus far for debug & stats.
+ * Return the number of RCU batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started(void)
+{
+	return rcu_state_p->gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started);
+
+/*
+ * Return the number of RCU-sched batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_sched(void)
+{
+	return rcu_sched_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+
+/*
+ * Return the number of RCU BH batches started thus far for debug & stats.
  */
-long rcu_batches_completed_sched(void)
+unsigned long rcu_batches_started_bh(void)
+{
+	return rcu_bh_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+
+/*
+ * Return the number of RCU batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed(void)
+{
+	return rcu_state_p->completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU-sched batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed_sched(void)
 {
 	return rcu_sched_state.completed;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
- * Return the number of RCU BH batches processed thus far for debug & stats.
+ * Return the number of RCU BH batches completed thus far for debug & stats.
  */
-long rcu_batches_completed_bh(void)
+unsigned long rcu_batches_completed_bh(void)
 {
 	return rcu_bh_state.completed;
 }
@@ -759,39 +818,71 @@ void rcu_irq_enter(void)
 /**
  * rcu_nmi_enter - inform RCU of entry to NMI context
  *
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is active.
+ * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
+ * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
+ * that the CPU is active.  This implementation permits nested NMIs, as
+ * long as the nesting level does not overflow an int.  (You will probably
+ * run out of stack space first.)
  */
 void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int incby = 2;
 
-	if (rdtp->dynticks_nmi_nesting == 0 &&
-	    (atomic_read(&rdtp->dynticks) & 0x1))
-		return;
-	rdtp->dynticks_nmi_nesting++;
-	smp_mb__before_atomic();  /* Force delay from prior write. */
-	atomic_inc(&rdtp->dynticks);
-	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
-	smp_mb__after_atomic();  /* See above. */
-	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	/* Complain about underflow. */
+	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0);
+
+	/*
+	 * If idle from RCU viewpoint, atomically increment ->dynticks
+	 * to mark non-idle and increment ->dynticks_nmi_nesting by one.
+	 * Otherwise, increment ->dynticks_nmi_nesting by two.  This means
+	 * if ->dynticks_nmi_nesting is equal to one, we are guaranteed
+	 * to be in the outermost NMI handler that interrupted an RCU-idle
+	 * period (observation due to Andy Lutomirski).
+	 */
+	if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
+		smp_mb__before_atomic();  /* Force delay from prior write. */
+		atomic_inc(&rdtp->dynticks);
+		/* atomic_inc() before later RCU read-side crit sects */
+		smp_mb__after_atomic();  /* See above. */
+		WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+		incby = 1;
+	}
+	rdtp->dynticks_nmi_nesting += incby;
+	barrier();
 }
 
 /**
  * rcu_nmi_exit - inform RCU of exit from NMI context
  *
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is no longer active.
+ * If we are returning from the outermost NMI handler that interrupted an
+ * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
+ * to let the RCU grace-period handling know that the CPU is back to
+ * being RCU-idle.
  */
 void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
-	if (rdtp->dynticks_nmi_nesting == 0 ||
-	    --rdtp->dynticks_nmi_nesting != 0)
+	/*
+	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
+	 * (We are exiting an NMI handler, so RCU better be paying attention
+	 * to us!)
+	 */
+	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+
+	/*
+	 * If the nesting level is not 1, the CPU wasn't RCU-idle, so
+	 * leave it in non-RCU-idle state.
+	 */
+	if (rdtp->dynticks_nmi_nesting != 1) {
+		rdtp->dynticks_nmi_nesting -= 2;
 		return;
+	}
+
+	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
+	rdtp->dynticks_nmi_nesting = 0;
 	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
 	smp_mb__before_atomic();  /* See above. */
 	atomic_inc(&rdtp->dynticks);
@@ -898,17 +989,14 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		return 1;
 	} else {
+		if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+				 rdp->mynode->gpnum))
+			ACCESS_ONCE(rdp->gpwrap) = true;
 		return 0;
 	}
 }
 
 /*
- * This function really isn't for public consumption, but RCU is special in
- * that context switches can allow the state machine to make progress.
- */
-extern void resched_cpu(int cpu);
-
-/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -1011,6 +1099,22 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	j1 = rcu_jiffies_till_stall_check();
 	ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
 	rsp->jiffies_resched = j + j1 / 2;
+	rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+}
+
+/*
+ * Complain about starvation of grace-period kthread.
+ */
+static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
+{
+	unsigned long gpa;
+	unsigned long j;
+
+	j = jiffies;
+	gpa = ACCESS_ONCE(rsp->gp_activity);
+	if (j - gpa > 2 * HZ)
+		pr_err("%s kthread starved for %ld jiffies!\n",
+		       rsp->name, j - gpa);
 }
 
 /*
@@ -1033,11 +1137,13 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 	}
 }
 
-static void print_other_cpu_stall(struct rcu_state *rsp)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 {
 	int cpu;
 	long delta;
 	unsigned long flags;
+	unsigned long gpa;
+	unsigned long j;
 	int ndetected = 0;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	long totqlen = 0;
@@ -1075,30 +1181,34 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
-	/*
-	 * Now rat on any tasks that got kicked up to the root rcu_node
-	 * due to CPU offlining.
-	 */
-	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	ndetected += rcu_print_task_stall(rnp);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
 		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
 	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
-	if (ndetected == 0)
-		pr_err("INFO: Stall ended before state dump start\n");
-	else
+	if (ndetected) {
 		rcu_dump_cpu