diff --git a/Documentation/RCU/arrayRCU.txt b/Documentation/RCU/arrayRCU.txt
index 453ebe69..f05a9af 100644
--- a/Documentation/RCU/arrayRCU.txt
+++ b/Documentation/RCU/arrayRCU.txt
@@ -10,7 +10,19 @@
 
 3.  Resizeable Arrays
 
-Each of these situations are discussed below.
+Each of these three situations involves an RCU-protected pointer to an
+array that is separately indexed.  It might be tempting to consider use
+of RCU to instead protect the index into an array, however, this use
+case is -not- supported.  The problem with RCU-protected indexes into
+arrays is that compilers can play way too many optimization games with
+integers, which means that the rules governing handling of these indexes
+are far more trouble than they are worth.  If RCU-protected indexes into
+arrays prove to be particularly valuable (which they have not thus far),
+explicit cooperation from the compiler will be required to permit them
+to be safely used.
+
+That aside, each of the three RCU-protected pointer situations are
+described in the following sections.
 
 
 Situation 1: Hash Tables
@@ -36,9 +48,9 @@
 Situation 3: Resizeable Arrays
 
 Use of RCU for resizeable arrays is demonstrated by the grow_ary()
-function used by the System V IPC code.  The array is used to map from
-semaphore, message-queue, and shared-memory IDs to the data structure
-that represents the corresponding IPC construct.  The grow_ary()
+function formerly used by the System V IPC code.  The array is used
+to map from semaphore, message-queue, and shared-memory IDs to the data
+structure that represents the corresponding IPC construct.  The grow_ary()
 function does not acquire any locks; instead its caller must hold the
 ids->sem semaphore.
 
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
index cd83d23..da51d30 100644
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@@ -47,11 +47,6 @@
 		Use explicit check expression "c" along with
 		srcu_read_lock_held()().  This is useful in code that
 		is invoked by both SRCU readers and updaters.
-	rcu_dereference_index_check(p, c):
-		Use explicit check expression "c", but the caller
-		must supply one of the rcu_read_lock_held() functions.
-		This is useful in code that uses RCU-protected arrays
-		that is invoked by both RCU readers and updaters.
 	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
 	rcu_dereference_protected(p, c):
@@ -64,11 +59,6 @@
 		but retain the compiler constraints that prevent duplicating
 		or coalescsing.  This is useful when when testing the
 		value of the pointer itself, for example, against NULL.
-	rcu_access_index(idx):
-		Return the value of the index and omit all barriers, but
-		retain the compiler constraints that prevent duplicating
-		or coalescsing.  This is useful when when testing the
-		value of the index itself, for example, against -1.
 
 The rcu_dereference_check() check expression can be any boolean
 expression, but would normally include a lockdep expression.  However,
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index ceb05da..1e6c0da 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -25,17 +25,6 @@
 	for an example where the compiler can in fact deduce the exact
 	value of the pointer, and thus cause misordering.
 
-o	Do not use single-element RCU-protected arrays.  The compiler
-	is within its right to assume that the value of an index into
-	such an array must necessarily evaluate to zero.  The compiler
-	could then substitute the constant zero for the computation, so
-	that the array index no longer depended on the value returned
-	by rcu_dereference().  If the array index no longer depends
-	on rcu_dereference(), then both the compiler and the CPU
-	are within their rights to order the array access before the
-	rcu_dereference(), which can cause the array access to return
-	garbage.
-
 o	Avoid cancellation when using the "+" and "-" infix arithmetic
 	operators.  For example, for a given variable "x", avoid
 	"(x-x)".  There are similar arithmetic pitfalls from other
@@ -76,14 +65,15 @@
 	dereferencing.	For example, the following (rather improbable)
 	code is buggy:
 
-		int a[2];
-		int index;
-		int force_zero_index = 1;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 && force_zero_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p != &oom_p1 && p != &oom_p2;
+		r1 = *q;  /* BUGGY!!! */
 
 	The reason this is buggy is that "&&" and "||" are often compiled
 	using branches.  While weak-memory machines such as ARM or PowerPC
@@ -94,14 +84,15 @@
 	">", ">=", "<", or "<=") when dereferencing.  For example,
 	the following (quite strange) code is buggy:
 
-		int a[2];
-		int index;
-		int flip_index = 0;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 != flip_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p > &oom_p;
+		r1 = *q;  /* BUGGY!!! */
 
 	As before, the reason this is buggy is that relational operators
 	are often compiled using branches.  And as before, although
@@ -193,6 +184,11 @@
 		pointer.  Note that the volatile cast in rcu_dereference()
 		will normally prevent the compiler from knowing too much.
 
+		However, please note that if the compiler knows that the
+		pointer takes on only one of two values, a not-equal
+		comparison will provide exactly the information that the
+		compiler needs to deduce the value of the pointer.
+
 o	Disable any value-speculation optimizations that your compiler
 	might provide, especially if you are making use of feedback-based
 	optimizations that take data collected from prior runs.  Such
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 88dfce1..5746b0c 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -256,7 +256,9 @@
 	If you are going to be fetching multiple fields from the
 	RCU-protected structure, using the local variable is of
 	course preferred.  Repeated rcu_dereference() calls look
-	ugly and incur unnecessary overhead on Alpha CPUs.
+	ugly, do not guarantee that the same pointer will be returned
+	if an update happened while in the critical section, and incur
+	unnecessary overhead on Alpha CPUs.
 
 	Note that the value returned by rcu_dereference() is valid
 	only within the enclosing RCU read-side critical section.
@@ -879,9 +881,7 @@
 
 All:  lockdep-checked RCU-protected pointer access
 
-	rcu_access_index
 	rcu_access_pointer
-	rcu_dereference_index_check
 	rcu_dereference_raw
 	rcu_lockdep_assert
 	rcu_sleep_check
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f6befa9..ce8f46f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2992,11 +2992,34 @@
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.dump_tree=	[KNL]
+			Dump the structure of the rcu_node combining tree
+			out at early boot.  This is used for diagnostic
+			purposes, to verify correct tree setup.
+
+	rcutree.gp_cleanup_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period cleanup.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
+
 	rcutree.gp_init_delay=	[KNL]
 			Set the number of jiffies to delay each step of
 			RCU grace-period initialization.  This only has
-			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
-			set.
+			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+			is set.
+
+	rcutree.gp_preinit_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period pre-initialization, that is,
+			the propagation of recent CPU-hotplug changes up
+			the rcu_node combining tree.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
+
+	rcutree.rcu_fanout_exact= [KNL]
+			Disable autobalancing of the rcu_node combining
+			tree.  This is used by rcutorture, and might
+			possibly be useful for architectures having high
+			cache-to-cache transfer latencies.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -3101,7 +3124,11 @@
 			test, hence the "fake".
 
 	rcutorture.nreaders= [KNL]
-			Set number of RCU readers.
+			Set number of RCU readers.  The value -1 selects
+			N-1, where N is the number of CPUs.  A value
+			"n" less than -1 selects N-n-2, where N is again
+			the number of CPUs.  For example, -2 selects N
+			(the number of CPUs), -3 selects N+1, and so on.
 
 	rcutorture.object_debug= [KNL]
 			Enable debug-object double-call_rcu() testing.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a3014bc..360841d 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1795,10 +1795,9 @@
 
      Memory operations issued before the ACQUIRE may be completed after
      the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
-     combined with a following ACQUIRE, orders prior loads against
-     subsequent loads and stores and also orders prior stores against
-     subsequent stores.  Note that this is weaker than smp_mb()!  The
-     smp_mb__before_spinlock() primitive is free on many architectures.
+     combined with a following ACQUIRE, orders prior stores against
+     subsequent loads and stores. Note that this is weaker than smp_mb()!
+     The smp_mb__before_spinlock() primitive is free on many architectures.
 
  (2) RELEASE operation implication:
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cca5b87..8ef0ef0 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -218,15 +218,13 @@
 	return 0;
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -272,7 +270,7 @@
 	 * this returns, power and/or clocks can be removed at any point
 	 * from this CPU and its cache by platform_cpu_kill().
 	 */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Ensure that the cache lines associated with that completion are
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2cb0081..a899c1b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -253,15 +253,13 @@
 	return cpu_ops[cpu]->cpu_kill(cpu);
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_crit("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -294,7 +292,7 @@
 	local_irq_disable();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Actually shutdown the CPU. This must never fail. The specific hotplug
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e535533..d4298fe 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -53,9 +53,12 @@
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
-	rcu_dereference_index_check((p), \
-			      rcu_read_lock_sched_held() || \
-			      lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+			   lockdep_is_held(&mce_chrdev_read_mutex), \
+			   "suspicious rcu_dereference_check_mce() usage"); \
+	smp_load_acquire(&(p)); \
+})
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -1884,7 +1887,7 @@
 static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
-	if (rcu_access_index(mcelog.next))
+	if (READ_ONCE(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
@@ -1929,8 +1932,8 @@
 }
 EXPORT_SYMBOL_GPL(register_mce_write_callback);
 
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-			 size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
 {
 	if (mce_write)
 		return mce_write(filp, ubuf, usize, off);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 2bc56e2..3290177 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -181,7 +181,7 @@
 	rcu_read_lock();
 	if (rdev == NULL)
 		/* start at the beginning */
-		rdev = list_entry_rcu(&mddev->disks, struct md_rdev, same_set);
+		rdev = list_entry_rcu(mddev->disks.next, struct md_rdev, same_set);
 	else {
 		/* release the previous rdev and start from there. */
 		rdev_dec_pending(rdev, mddev);
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 6653972..c881741 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -247,10 +247,7 @@
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-({ \
-	typeof(*ptr) __rcu *__ptr = (typeof(*ptr) __rcu __force *)ptr; \
-	container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \
-})
+	container_of((typeof(ptr))rcu_dereference_raw(ptr), type, member)
 
 /**
  * Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -549,8 +546,8 @@
  */
 #define hlist_for_each_entry_from_rcu(pos, member)			\
 	for (; pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 #endif	/* __KERNEL__ */
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5ec20bc4..03a899a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -292,10 +292,6 @@
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 struct notifier_block;
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
 int rcu_cpu_notify(struct notifier_block *self,
 		   unsigned long action, void *hcpu);
 
@@ -628,21 +624,6 @@
 	((typeof(*p) __force __kernel *)(p)); \
 })
 
-#define __rcu_access_index(p, space) \
-({ \
-	typeof(p) _________p1 = READ_ONCE(p); \
-	rcu_dereference_sparse(p, space); \
-	(_________p1); \
-})
-#define __rcu_dereference_index_check(p, c) \
-({ \
-	/* Dependency order vs. p above. */ \
-	typeof(p) _________p1 = lockless_dereference(p); \
-	rcu_lockdep_assert(c, \
-			   "suspicious rcu_dereference_index_check() usage"); \
-	(_________p1); \
-})
-
 /**
  * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
  * @v: The value to statically initialize with.
@@ -787,41 +768,6 @@
 #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
 
 /**
- * rcu_access_index() - fetch RCU index with no dereferencing
- * @p: The index to read
- *
- * Return the value of the specified RCU-protected index, but omit the
- * smp_read_barrier_depends() and keep the READ_ONCE().  This is useful
- * when the value of this index is accessed, but the index is not
- * dereferenced, for example, when testing an RCU-protected index against
- * -1.  Although rcu_access_index() may also be used in cases where
- * update-side locks prevent the value of the index from changing, you
- * should instead use rcu_dereference_index_protected() for this use case.
- */
-#define rcu_access_index(p) __rcu_access_index((p), __rcu)
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices.  Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer.  Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections.  If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
-	__rcu_dereference_index_check((p), (c))
-
-/**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
  * @p: The pointer to read, prior to dereferencing
  * @c: The conditions under which the dereference will take place
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 937edae..3df6c1e 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -159,6 +159,22 @@
 {
 }
 
+static inline void rcu_idle_enter(void)
+{
+}
+
+static inline void rcu_idle_exit(void)
+{
+}
+
+static inline void rcu_irq_enter(void)
+{
+}
+
+static inline void rcu_irq_exit(void)
+{
+}
+
 static inline void exit_rcu(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 0bd400b..3fa4a43 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -91,6 +91,11 @@
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
 
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
+
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 3e18379..0063b24 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -120,7 +120,7 @@
 /*
  * Despite its name it doesn't necessarily has to be a full barrier.
  * It should only guarantee that a STORE before the critical section
- * can not be reordered with a LOAD inside this section.
+ * can not be reordered with LOADs and STOREs inside this section.
  * spin_lock() is the one-way barrier, this LOAD can not escape out
  * of the region. So the default implementation simply ensures that
  * a STORE can not move into the critical section, smp_wmb() should
diff --git a/init/Kconfig b/init/Kconfig
index dc24dec..4c081970 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -465,13 +465,9 @@
 
 menu "RCU Subsystem"
 
-choice
-	prompt "RCU Implementation"
-	default TREE_RCU
-
 config TREE_RCU
-	bool "Tree-based hierarchical RCU"
-	depends on !PREEMPT && SMP
+	bool
+	default y if !PREEMPT && SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -479,8 +475,8 @@
 	  smaller systems.
 
 config PREEMPT_RCU
-	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT
+	bool
+	default y if PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -491,15 +487,28 @@
 	  Select this option if you are unsure.
 
 config TINY_RCU
-	bool "UP-only small-memory-footprint RCU"
-	depends on !PREEMPT && !SMP
+	bool
+	default y if !PREEMPT && !SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for UP systems from which real-time response
 	  is not required.  This option greatly reduces the
 	  memory footprint of RCU.
 
-endchoice
+config RCU_EXPERT
+	bool "Make expert-level adjustments to RCU configuration"
+	default n
+	help
+	  This option needs to be enabled if you wish to make
+	  expert-level adjustments to RCU configuration.  By default,
+	  no such adjustments can be made, which has the often-beneficial
+	  side-effect of preventing "make oldconfig" from asking you all
+	  sorts of detailed questions about how you would like numerous
+	  obscure RCU options to be set up.
+
+	  Say Y if you need to make expert-level adjustments to RCU.
+
+	  Say N if you are unsure.
 
 config SRCU
 	bool
@@ -509,7 +518,7 @@
 	  sections.
 
 config TASKS_RCU
-	bool "Task_based RCU implementation using voluntary context switch"
+	bool
 	default n
 	select SRCU
 	help
@@ -517,8 +526,6 @@
 	  only voluntary context switch (not preemption!), idle, and
 	  user-mode execution as quiescent states.
 
-	  If unsure, say N.
-
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
 	help
@@ -531,9 +538,7 @@
        bool
 
 config RCU_USER_QS
-	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_CONTEXT_TRACKING && SMP
-	select CONTEXT_TRACKING
+	bool
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
@@ -541,12 +546,6 @@
 	  excluded from the global RCU state machine and thus doesn't
 	  try to keep the timer tick on for RCU.
 
-	  Unless you want to hack and help the development of the full
-	  dynticks mode, you shouldn't enable this option.  It also
-	  adds unnecessary overhead.
-
-	  If unsure say N
-
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
@@ -578,7 +577,7 @@
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on TREE_RCU || PREEMPT_RCU
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -596,9 +595,9 @@
 
 config RCU_FANOUT_LEAF
 	int "Tree-based hierarchical RCU leaf-level fanout value"
-	range 2 RCU_FANOUT if 64BIT
-	range 2 RCU_FANOUT if !64BIT
-	depends on TREE_RCU || PREEMPT_RCU
+	range 2 64 if 64BIT
+	range 2 32 if !64BIT
+	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
 	default 16
 	help
 	  This option controls the leaf-level fanout of hierarchical
@@ -621,23 +620,9 @@
 
 	  Take the default if unsure.
 
-config RCU_FANOUT_EXACT
-	bool "Disable tree-based hierarchical RCU auto-balancing"
-	depends on TREE_RCU || PREEMPT_RCU
-	default n
-	help
-	  This option forces use of the exact RCU_FANOUT value specified,
-	  regardless of imbalances in the hierarchy.  This is useful for
-	  testing RCU itself, and might one day be useful on systems with
-	  strong NUMA behavior.
-
-	  Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
-
-	  Say N if unsure.
-
 config RCU_FAST_NO_HZ
 	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP
+	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
 	default n
 	help
 	  This option permits CPUs to enter dynticks-idle state even if
@@ -663,7 +648,7 @@
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
 	default n
 	help
 	  This option boosts the priority of preempted RCU readers that
@@ -680,6 +665,7 @@
 	range 0 99 if !RCU_BOOST
 	default 1 if RCU_BOOST
 	default 0 if !RCU_BOOST
+	depends on RCU_EXPERT
 	help
 	  This option specifies the SCHED_FIFO priority value that will be
 	  assigned to the rcuc/n and rcub/n threads and is also the value
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 94bbe46..9c9c9fa 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -398,7 +398,6 @@
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 		goto out_release;
 	}
@@ -463,6 +462,7 @@
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 
+	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
 		smpboot_unpark_threads(cpu);
 		break;
@@ -479,7 +479,7 @@
 	.priority = CPU_PRI_SMPBOOT,
 };
 
-void __cpuinit smpboot_thread_init(void)
+void smpboot_thread_init(void)
 {
 	register_cpu_notifier(&smpboot_thread_notifier);
 }
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index ec8cce25..3224418 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -122,12 +122,12 @@
 
 static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 {
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a long delay occasionally to force massive contention.  */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 #ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
 		preempt_schedule();  /* Allow test to be preempted. */
@@ -160,14 +160,14 @@
 static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 {
 	const unsigned long shortdelay_us = 2;
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a short delay mostly to emulate likely code, and
 	 * we want a long delay occasionally to force massive contention.
 	 */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
@@ -309,7 +309,7 @@
 static void torture_rwlock_read_unlock_irq(void)
 __releases(torture_rwlock)
 {
-	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+	read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
 }
 
 static struct lock_torture_ops rw_lock_irq_ops = {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index a67ef6f..59e3268 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -241,6 +241,7 @@
 struct rcu_torture_ops {
 	int ttype;
 	void (*init)(void);
+	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
@@ -477,10 +478,12 @@
  */
 
 DEFINE_STATIC_SRCU(srcu_ctl);
+static struct srcu_struct srcu_ctld;
+static struct srcu_struct *srcu_ctlp = &srcu_ctl;
 
-static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
+static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
 {
-	return srcu_read_lock(&srcu_ctl);
+	return srcu_read_lock(srcu_ctlp);
 }
 
 static void srcu_read_delay(struct torture_random_state *rrsp)
@@ -499,49 +502,49 @@
 		rcu_read_delay(rrsp);
 }
 
-static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
+static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
 {
-	srcu_read_unlock(&srcu_ctl, idx);
+	srcu_read_unlock(srcu_ctlp, idx);
 }
 
 static unsigned long srcu_torture_completed(void)
 {
-	return srcu_batches_completed(&srcu_ctl);
+	return srcu_batches_completed(srcu_ctlp);
 }
 
 static void srcu_torture_deferred_free(struct rcu_torture *rp)
 {
-	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+	call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb);
 }
 
 static void srcu_torture_synchronize(void)
 {
-	synchronize_srcu(&srcu_ctl);
+	synchronize_srcu(srcu_ctlp);
 }
 
 static void srcu_torture_call(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head))
 {
-	call_srcu(&srcu_ctl, head, func);
+	call_srcu(srcu_ctlp, head, func);
 }
 
 static void srcu_torture_barrier(void)
 {
-	srcu_barrier(&srcu_ctl);
+	srcu_barrier(srcu_ctlp);
 }
 
 static void srcu_torture_stats(void)
 {
 	int cpu;
-	int idx = srcu_ctl.completed & 0x1;
+	int idx = srcu_ctlp->completed & 0x1;
 
 	pr_alert("%s%s per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		long c0, c1;
 
-		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
-		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+		c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
+		c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
@@ -549,7 +552,7 @@
 
 static void srcu_torture_synchronize_expedited(void)
 {
-	synchronize_srcu_expedited(&srcu_ctl);
+	synchronize_srcu_expedited(srcu_ctlp);
 }
 
 static struct rcu_torture_ops srcu_ops = {
@@ -569,6 +572,38 @@
 	.name		= "srcu"
 };
 
+static void srcu_torture_init(void)
+{
+	rcu_sync_torture_init();
+	WARN_ON(init_srcu_struct(&srcu_ctld));
+	srcu_ctlp = &srcu_ctld;
+}
+
+static void srcu_torture_cleanup(void)
+{
+	cleanup_srcu_struct(&srcu_ctld);
+	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
+}
+
+/* As above, but dynamically allocated. */
+static struct rcu_torture_ops srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.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,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.name		= "srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -672,8 +707,8 @@
 	struct rcu_boost_inflight *rbip =
 		container_of(head, struct rcu_boost_inflight, rcu);
 
-	smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
-	rbip->inflight = 0;
+	/* Ensure RCU-core accesses precede clearing ->inflight */
+	smp_store_release(&rbip->inflight, 0);
 }
 
 static int rcu_torture_boost(void *arg)
@@ -710,9 +745,9 @@
 		call_rcu_time = jiffies;
 		while (ULONG_CMP_LT(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
-			if (!rbi.inflight) {
-				smp_mb(); /* RCU core before ->inflight = 1. */
-				rbi.inflight = 1;
+			if (!smp_load_acquire(&rbi.inflight)) {
+				/* RCU core before ->inflight = 1. */
+				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
 				if (jiffies - call_rcu_time >
 					 test_boost_duration * HZ - HZ / 2) {
@@ -751,11 +786,10 @@
 	} while (!torture_must_stop());
 
 	/* Clean up and exit. */
-	while (!kthread_should_stop() || rbi.inflight) {
+	while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
 		torture_shutdown_absorb("rcu_torture_boost");
 		schedule_timeout_uninterruptible(1);
 	}
-	smp_mb(); /* order accesses to ->inflight before stack-frame death. */
 	destroy_rcu_head_on_stack(&rbi.rcu);
 	torture_kthread_stopping("rcu_torture_boost");
 	return 0;
@@ -1054,7 +1088,7 @@
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
-				  srcu_read_lock_held(&srcu_ctl));
+				  srcu_read_lock_held(srcu_ctlp));
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -1128,7 +1162,7 @@
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
 					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(&srcu_ctl));
+					  srcu_read_lock_held(srcu_ctlp));
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -1413,12 +1447,15 @@
 	do {
 		wait_event(barrier_cbs_wq[myid],
 			   (newphase =
-			    READ_ONCE(barrier_phase)) != lastphase ||
+			    smp_load_acquire(&barrier_phase)) != lastphase ||
 			   torture_must_stop());
 		lastphase = newphase;
-		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (torture_must_stop())
 			break;
+		/*
+		 * The above smp_load_acquire() ensures barrier_phase load
+		 * is ordered before the folloiwng ->call().
+		 */
 		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
@@ -1439,8 +1476,8 @@
 	do {
 		atomic_set(&barrier_cbs_invoked, 0);
 		atomic_set(&barrier_cbs_count, n_barrier_cbs);
-		smp_mb(); /* Ensure barrier_phase after prior assignments. */
-		barrier_phase = !barrier_phase;
+		/* Ensure barrier_phase ordered after prior assignments. */
+		smp_store_release(&barrier_phase, !barrier_phase);
 		for (i = 0; i < n_barrier_cbs; i++)
 			wake_up(&barrier_cbs_wq[i]);
 		wait_event(barrier_wq,
@@ -1588,10 +1625,14 @@
 			rcutorture_booster_cleanup(i);
 	}
 
-	/* Wait for all RCU callbacks to fire.  */
-
+	/*
+	 * Wait for all RCU callbacks to fire, then do flavor-specific
+	 * cleanup operations.
+	 */
 	if (cur_ops->cb_barrier != NULL)
 		cur_ops->cb_barrier();
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
@@ -1668,8 +1709,8 @@
 	int cpu;
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
-		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
-		RCUTORTURE_TASKS_OPS
+		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
+		&sched_ops, RCUTORTURE_TASKS_OPS
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
@@ -1701,7 +1742,7 @@
 	if (nreaders >= 0) {
 		nrealreaders = nreaders;
 	} else {
-		nrealreaders = num_online_cpus() - 1;
+		nrealreaders = num_online_cpus() - 2 - nreaders;
 		if (nrealreaders <= 0)
 			nrealreaders = 1;
 	}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 069742d..591af0c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -49,39 +49,6 @@
 
 #include "tiny_plugin.h"
 
-/*
- * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode.
- */
-void rcu_idle_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
-
-/*
- * Exit an interrupt handler towards idle.
- */
-void rcu_irq_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_exit);
-
-/*
- * Exit idle, so that we are no longer in an extended quiescent state.
- */
-void rcu_idle_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
-
-/*
- * Enter an interrupt handler, moving away from idle.
- */
-void rcu_irq_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_enter);
-
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
@@ -170,6 +137,11 @@
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
+	if (rcp->donetail == &rcp->rcucblist) {
+		/* No callbacks ready, so just leave. */
+		local_irq_restore(flags);
+		return;
+	}
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index fdbf30c..7651d7d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -114,17 +114,18 @@
 static struct rcu_data __percpu *const rcu_data_p;
 LIST_HEAD(rcu_struct_flavors);
 
-/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
-static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
+/* Dump rcu_node combining tree at boot to verify correct setup. */
+static bool dump_tree;
+module_param(dump_tree, bool, 0444);
+/* Control rcu_node-tree auto-balancing at boot time. */
+static bool rcu_fanout_exact;
+module_param(rcu_fanout_exact, bool, 0444);
+/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
+static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
 module_param(rcu_fanout_leaf, int, 0444);
 int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
-static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
-	NUM_RCU_LVL_0,
-	NUM_RCU_LVL_1,
-	NUM_RCU_LVL_2,
-	NUM_RCU_LVL_3,
-	NUM_RCU_LVL_4,
-};
+/* Number of rcu_nodes at specified level. */
+static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
 int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
 
 /*
@@ -160,14 +161,46 @@
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
 /* rcuc/rcub kthread realtime priority */
+#ifdef CONFIG_RCU_KTHREAD_PRIO
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
+static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
+#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
 module_param(kthread_prio, int, 0644);
 
-/* Delay in jiffies for grace-period initialization delays. */
-static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT)
-				? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
-				: 0;
+/* Delay in jiffies for grace-period initialization delays, debug only. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
+static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
+module_param(gp_preinit_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+static const int gp_preinit_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
 module_param(gp_init_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+static const int gp_init_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
+static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
+module_param(gp_cleanup_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+static const int gp_cleanup_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+
+/*
+ * Number of grace periods between delays, normalized by the duration of
+ * the delay.  The longer the the delay, the more the grace periods between
+ * each delay.  The reason for this normalization is that it means that,
+ * for non-zero delays, the overall slowdown of grace periods is constant
+ * regardless of the duration of the delay.  This arrangement balances
+ * the need for long delays to increase some race probabilities with the
+ * need for fast grace periods to increase other race probabilities.
+ */
+#define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
 /*
  * Track the rcutorture test sequence number and the update version
@@ -583,7 +616,8 @@
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -602,7 +636,8 @@
 	smp_mb__before_atomic();  /* See above. */
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     atomic_read(&rdtp->dynticks) & 0x1);
 	rcu_dynticks_task_enter();
 
 	/*
@@ -628,7 +663,8 @@
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
 		rcu_eqs_enter_common(oldval, user);
@@ -701,7 +737,8 @@
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting < 0);
 	if (rdtp->dynticks_nesting)
 		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
 	else
@@ -726,10 +763,12 @@
 	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));
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     !(atomic_read(&rdtp->dynticks) & 0x1));
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -753,7 +792,7 @@
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE(oldval < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
 	} else {
@@ -826,7 +865,8 @@
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting == 0);
 	if (oldval)
 		trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
 	else
@@ -1731,6 +1771,13 @@
 		rcu_gp_kthread_wake(rsp);
 }
 
+static void rcu_gp_slow(struct rcu_state *rsp, int delay)
+{
+	if (delay > 0 &&
+	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+		schedule_timeout_uninterruptible(delay);
+}
+
 /*
  * Initialize a new grace period.  Return 0 if no grace period required.
  */
@@ -1773,6 +1820,7 @@
 	 * will handle subsequent offline CPUs.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_preinit_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -1829,6 +1877,7 @@
 	 * process finishes, because this kthread handles both.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
@@ -1846,10 +1895,6 @@
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
-		if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) &&
-		    gp_init_delay > 0 &&
-		    !(rsp->gpnum % (rcu_num_nodes * 10)))
-			schedule_timeout_uninterruptible(gp_init_delay);
 	}
 
 	return 1;
@@ -1944,6 +1989,7 @@
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
+		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -2336,8 +2382,6 @@
 	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Send the specified CPU's RCU callbacks to the orphanage.  The
  * specified CPU must be offline, and the caller must hold the
@@ -2348,7 +2392,7 @@
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (rcu_is_nocb_cpu(rdp->cpu))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
 		return;
 
 	/*
@@ -2407,7 +2451,8 @@
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2454,6 +2499,9 @@
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	RCU_TRACE(mask = rdp->grpmask);
 	trace_rcu_grace_period(rsp->name,
 			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
@@ -2482,7 +2530,8 @@
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2513,6 +2562,9 @@
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -2534,6 +2586,9 @@
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
@@ -2548,26 +2603,6 @@
 		  cpu, rdp->qlen, rdp->nxtlist);
 }
 
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
-{
-}
-
-static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
-{
-}
-
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
@@ -2732,10 +2767,6 @@
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		if (!rcu_gp_in_progress(rsp)) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			return;
-		}
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2765,8 +2796,6 @@
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
-				if ((rnp->qsmaskinit & bit) == 0)
-					*isidle = false; /* Pending hotplug. */
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
@@ -3781,7 +3810,7 @@
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
 	rdp->passed_quiesce = false;
-	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->qs_pending = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3925,24 +3954,24 @@
 
 /*
  * Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
  */
-static void __init rcu_init_levelspread(struct rcu_state *rsp)
+static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
 {
 	int i;
 
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
-		rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+	if (rcu_fanout_exact) {
+		levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
-			rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+			levelspread[i] = RCU_FANOUT;
 	} else {
 		int ccur;
 		int cprv;
 
 		cprv = nr_cpu_ids;
 		for (i = rcu_num_lvls - 1; i >= 0; i--) {
-			ccur = rsp->levelcnt[i];
-			rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+			ccur = levelcnt[i];
+			levelspread[i] = (cprv + ccur - 1) / ccur;
 			cprv = ccur;
 		}
 	}
@@ -3954,44 +3983,39 @@
 static void __init rcu_init_one(struct rcu_state *rsp,
 		struct rcu_data __percpu *rda)
 {
-	static const char * const buf[] = {
-		"rcu_node_0",
-		"rcu_node_1",
-		"rcu_node_2",
-		"rcu_node_3" };  /* Match MAX_RCU_LVLS */
-	static const char * const fqs[] = {
-		"rcu_node_fqs_0",
-		"rcu_node_fqs_1",
-		"rcu_node_fqs_2",
-		"rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const buf[] = RCU_NODE_NAME_INIT;
+	static const char * const fqs[] = RCU_FQS_NAME_INIT;
 	static u8 fl_mask = 0x1;
+
+	int levelcnt[RCU_NUM_LVLS];		/* # nodes in each level. */
+	int levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
 	int cpustride = 1;
 	int i;
 	int j;
 	struct rcu_node *rnp;
 
-	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
+	BUILD_BUG_ON(RCU_NUM_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
-	/* Silence gcc 4.8 warning about array index out of range. */
-	if (rcu_num_lvls > RCU_NUM_LVLS)
-		panic("rcu_init_one: rcu_num_lvls overflow");
+	/* Silence gcc 4.8 false positive about array index out of range. */
+	if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
+		panic("rcu_init_one: rcu_num_lvls out of range");
 
 	/* Initialize the level-tracking arrays. */
 
 	for (i = 0; i < rcu_num_lvls; i++)
-		rsp->levelcnt[i] = num_rcu_lvl[i];
+		levelcnt[i] = num_rcu_lvl[i];
 	for (i = 1; i < rcu_num_lvls; i++)
-		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
-	rcu_init_levelspread(rsp);
+		rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1];
+	rcu_init_levelspread(levelspread, levelcnt);
 	rsp->flavor_mask = fl_mask;
 	fl_mask <<= 1;
 
 	/* Initialize the elements themselves, starting from the leaves. */
 
 	for (i = rcu_num_lvls - 1; i >= 0; i--) {
-		cpustride *= rsp->levelspread[i];
+		cpustride *= levelspread[i];
 		rnp = rsp->level[i];
-		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
+		for (j = 0; j < levelcnt[i]; j++, rnp++) {
 			raw_spin_lock_init(&rnp->lock);
 			lockdep_set_class_and_name(&rnp->lock,
 						   &rcu_node_class[i], buf[i]);
@@ -4011,10 +4035,10 @@
 				rnp->grpmask = 0;
 				rnp->parent = NULL;
 			} else {
-				rnp->grpnum = j % rsp->levelspread[i - 1];
+				rnp->grpnum = j % levelspread[i - 1];
 				rnp->grpmask = 1UL << rnp->grpnum;
 				rnp->parent = rsp->level[i - 1] +
-					      j / rsp->levelspread[i - 1];
+					      j / levelspread[i - 1];
 			}
 			rnp->level = i;
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
@@ -4042,9 +4066,7 @@
 {
 	ulong d;
 	int i;
-	int j;
-	int n = nr_cpu_ids;
-	int rcu_capacity[MAX_RCU_LVLS + 1];
+	int rcu_capacity[RCU_NUM_LVLS];
 
 	/*
 	 * Initialize any unspecified boot parameters.
@@ -4060,7 +4082,7 @@
 		jiffies_till_next_fqs = d;
 
 	/* If the compile-time values are accurate, just leave. */
-	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
+	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
 	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
@@ -4068,46 +4090,67 @@
 
 	/*
 	 * Compute number of nodes that can be handled an rcu_node tree
-	 * with the given number of levels.  Setting rcu_capacity[0] makes
-	 * some of the arithmetic easier.
+	 * with the given number of levels.
 	 */
-	rcu_capacity[0] = 1;
-	rcu_capacity[1] = rcu_fanout_leaf;
-	for (i = 2; i <= MAX_RCU_LVLS; i++)
-		rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;
+	rcu_capacity[0] = rcu_fanout_leaf;
+	for (i = 1; i < RCU_NUM_LVLS; i++)
+		rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
 
 	/*
+	 * The tree must be able to accommodate the configured number of CPUs.
+	 * If this limit is exceeded than we have a serious problem elsewhere.
+	 *
 	 * The boot-time rcu_fanout_leaf parameter is only permitted
 	 * to increase the leaf-level fanout, not decrease it.  Of course,
 	 * the leaf-level fanout cannot exceed the number of bits in
-	 * the rcu_node masks.  Finally, the tree must be able to accommodate
-	 * the configured number of CPUs.  Complain and fall back to the
-	 * compile-time values if these limits are exceeded.
+	 * the rcu_node masks.  Complain and fall back to the compile-
+	 * time values if these limits are exceeded.
 	 */
-	if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
-	    rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
-	    n > rcu_capacity[MAX_RCU_LVLS]) {
+	if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1])
+		panic("rcu_init_geometry: rcu_capacity[] is too small");
+	else if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
+		 rcu_fanout_leaf > sizeof(unsigned long) * 8) {
 		WARN_ON(1);
 		return;
 	}
 
+	/* Calculate the number of levels in the tree. */
+	for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) {
+	}
+	rcu_num_lvls = i + 1;
+
 	/* Calculate the number of rcu_nodes at each level of the tree. */
-	for (i = 1; i <= MAX_RCU_LVLS; i++)
-		if (n <= rcu_capacity[i]) {
-			for (j = 0; j <= i; j++)
-				num_rcu_lvl[j] =
-					DIV_ROUND_UP(n, rcu_capacity[i - j]);
-			rcu_num_lvls = i;
-			for (j = i + 1; j <= MAX_RCU_LVLS; j++)
-				num_rcu_lvl[j] = 0;
-			break;
-		}
+	for (i = 0; i < rcu_num_lvls; i++) {
+		int cap = rcu_capacity[(rcu_num_lvls - 1) - i];
+		num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap);
+	}
 
 	/* Calculate the total number of rcu_node structures. */
 	rcu_num_nodes = 0;
-	for (i = 0; i <= MAX_RCU_LVLS; i++)
+	for (i = 0; i < rcu_num_lvls; i++)
 		rcu_num_nodes += num_rcu_lvl[i];
-	rcu_num_nodes -= n;
+}
+
+/*
+ * Dump out the structure of the rcu_node combining tree associated
+ * with the rcu_state structure referenced by rsp.
+ */
+static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
+{
+	int level = 0;
+	struct rcu_node *rnp;
+
+	pr_info("rcu_node tree layout dump\n");
+	pr_info(" ");
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		if (rnp->level != level) {
+			pr_cont("\n");
+			pr_info(" ");
+			level = rnp->level;
+		}
+		pr_cont("%d:%d ^%d  ", rnp->grplo, rnp->grphi, rnp->grpnum);
+	}
+	pr_cont("\n");
 }
 
 void __init rcu_init(void)
@@ -4120,6 +4163,8 @@
 	rcu_init_geometry();
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	if (dump_tree)
+		rcu_dump_rcu_node_tree(&rcu_sched_state);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8079c5b..f68ba68 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -35,47 +35,70 @@
  * In practice, this did work well going from three levels to four.
  * Of course, your mileage may vary.
  */
-#define MAX_RCU_LVLS 4
-#define RCU_FANOUT_1	      (CONFIG_RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT_LEAF 64
+# else
+# define RCU_FANOUT_LEAF 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2	      (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3	      (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4	      (RCU_FANOUT_3 * RCU_FANOUT)
 
 #if NR_CPUS <= RCU_FANOUT_1
 #  define RCU_NUM_LVLS	      1
 #  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_LVL_1	      (NR_CPUS)
-#  define NUM_RCU_LVL_2	      0
-#  define NUM_RCU_LVL_3	      0
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      NUM_RCU_LVL_0
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
 #elif NR_CPUS <= RCU_FANOUT_2
 #  define RCU_NUM_LVLS	      2
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_2	      (NR_CPUS)
-#  define NUM_RCU_LVL_3	      0
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
 #elif NR_CPUS <= RCU_FANOUT_3
 #  define RCU_NUM_LVLS	      3
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
 #  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_3	      (NR_CPUS)
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
 #elif NR_CPUS <= RCU_FANOUT_4
 #  define RCU_NUM_LVLS	      4
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
 #  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
 #  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_4	      (NR_CPUS)
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
 #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
 
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
-#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
-
 extern int rcu_num_lvls;
 extern int rcu_num_nodes;
 
@@ -421,8 +444,6 @@
 struct rcu_state {
 	struct rcu_node node[NUM_RCU_NODES];	/* Hierarchy. */
 	struct rcu_node *level[RCU_NUM_LVLS];	/* Hierarchy levels. */
-	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
-	u8 levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
 	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 853c7b8..a2f64e4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -70,11 +70,11 @@
 {
 	if (IS_ENABLED(CONFIG_RCU_TRACE))
 		pr_info("\tRCU debugfs-based tracing is enabled.\n");
-	if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
-	    (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
+	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
 		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       CONFIG_RCU_FANOUT);
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+		       RCU_FANOUT);
+	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
 		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
@@ -84,12 +84,12 @@
 		pr_info("\tRCU torture testing starts during boot.\n");
 	if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO))
 		pr_info("\tAdditional per-CPU info printed with stalls.\n");
-	if (NUM_RCU_LVL_4 != 0)
-		pr_info("\tFour-level hierarchy is enabled.\n");
-	if (CONFIG_RCU_FANOUT_LEAF != 16)
+	if (RCU_NUM_LVLS >= 4)
+		pr_info("\tFour(or more)-level hierarchy is enabled.\n");
+	if (RCU_FANOUT_LEAF != 16)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
-			CONFIG_RCU_FANOUT_LEAF);
-	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
+			RCU_FANOUT_LEAF);
+	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
@@ -315,9 +315,11 @@
 		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
-		 * Remove this task from the list it blocked on.  The
-		 * task can migrate while we acquire the lock, but at
-		 * most one time.  So at most two passes through loop.
+		 * Remove this task from the list it blocked on.  The task
+		 * now remains queued on the rcu_node corresponding to
+		 * the CPU it first blocked on, so the first attempt to
+		 * acquire the task's rcu_node's ->lock will succeed.
+		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
@@ -325,6 +327,7 @@
 			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
+			WARN_ON_ONCE(1);
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1767057..b908048 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1233,6 +1233,7 @@
 	depends on DEBUG_KERNEL
 	select TORTURE_TEST
 	select SRCU
+	select TASKS_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -1261,12 +1262,38 @@
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_TORTURE_TEST_SLOW_PREINIT
+	bool "Slow down RCU grace-period pre-initialization to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period pre-initialization (the
+	  propagation of CPU-hotplug changes up the rcu_node combining
+	  tree) for a few jiffies between initializing each pair of
+	  consecutive rcu_node structures.  This helps to expose races
+	  involving grace-period pre-initialization, in other words, it
+	  makes your kernel less stable.  It can also greatly increase
+	  grace-period latency, especially on systems with large numbers
+	  of CPUs.  This is useful when torture-testing RCU, but in
+	  almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+	int "How much to slow down RCU grace-period pre-initialization"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_PREINIT
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure pre-initialization step.
+
 config RCU_TORTURE_TEST_SLOW_INIT
 	bool "Slow down RCU grace-period initialization to expose races"
 	depends on RCU_TORTURE_TEST
 	help
-	  This option makes grace-period initialization block for a
-	  few jiffies between initializing each pair of consecutive
+	  This option delays grace-period initialization for a few
+	  jiffies between initializing each pair of consecutive
 	  rcu_node structures.	This helps to expose races involving
 	  grace-period initialization, in other words, it makes your
 	  kernel less stable.  It can also greatly increase grace-period
@@ -1281,10 +1308,35 @@
 	int "How much to slow down RCU grace-period initialization"
 	range 0 5
 	default 3
+	depends on RCU_TORTURE_TEST_SLOW_INIT
 	help
 	  This option specifies the number of jiffies to wait between
 	  each rcu_node structure initialization.
 
+config RCU_TORTURE_TEST_SLOW_CLEANUP
+	bool "Slow down RCU grace-period cleanup to expose races"
+	depends on RCU_TORTURE_TEST
+	help
+	  This option delays grace-period cleanup for a few jiffies
+	  between cleaning up each pair of consecutive rcu_node
+	  structures.  This helps to expose races involving grace-period
+	  cleanup, in other words, it makes your kernel less stable.
+	  It can also greatly increase grace-period latency, especially
+	  on systems with large numbers of CPUs.  This is useful when
+	  torture-testing RCU, but in almost no other circumstance.
+
+	  Say Y here if you want your system to crash and hang more often.
+	  Say N if you want a sane system.
+
+config RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+	int "How much to slow down RCU grace-period cleanup"
+	range 0 5
+	default 3
+	depends on RCU_TORTURE_TEST_SLOW_CLEANUP
+	help
+	  This option specifies the number of jiffies to wait between
+	  each rcu_node structure cleanup operation.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON
@@ -1321,6 +1373,17 @@
 	  Say Y here if you want to enable RCU tracing
 	  Say N if you are unsure.
 
+config RCU_EQS_DEBUG
+	bool "Use this when adding any sort of NO_HZ support to your arch"
+	depends on DEBUG_KERNEL
+	help
+	  This option provides consistency checks in RCU's handling of
+	  NO_HZ.  These checks have proven quite helpful in detecting
+	  bugs in arch-specific NO_HZ code.
+
+	  Say N here if you need ultimate kernel/user switch latencies
+	  Say Y if you are unsure
+
 endmenu # "RCU Debugging"
 
 config DEBUG_BLOCK_EXT_DEVT
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index e616301..ad70195 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -166,7 +166,7 @@
 	/* We may already have this, but read-locks nest anyway */
 	rcu_read_lock();
 
-	elem = list_entry_rcu(&nf_hooks[state->pf][state->hook],
+	elem = list_entry_rcu(nf_hooks[state->pf][state->hook].next,
 			      struct nf_hook_ops, list);
 next_hook:
 	verdict = nf_iterate(&nf_hooks[state->pf][state->hook], skb, state,
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 15f1a17..3f81a10 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -66,7 +66,7 @@
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
+yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 4f5b20f36..d86bdd6 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -43,6 +43,10 @@
 		if test -f "$i/console.log"
 		then
 			configcheck.sh $i/.config $i/ConfigFragment
+			if test -r $i/Make.oldconfig.err
+			then
+				cat $i/Make.oldconfig.err
+			fi
 			parse-build.sh $i/Make.out $configfile
 			parse-torture.sh $i/console.log $configfile
 			parse-console.sh $i/console.log $configfile
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index dd2812c..fbe2dbf 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -55,7 +55,7 @@
 	echo "       --bootargs kernel-boot-arguments"
 	echo "       --bootimage relative-path-to-kernel-boot-image"
 	echo "       --buildonly"
-	echo "       --configs \"config-file list\""
+	echo "       --configs \"config-file list w/ repeat factor (3*TINY01)\""
 	echo "       --cpus N"
 	echo "       --datestamp string"
 	echo "       --defconfig string"
@@ -178,13 +178,26 @@
 touch $T/cfgcpu
 for CF in $configs
 do
-	if test -f "$CONFIGFRAG/$CF"
+	case $CF in
+	[0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+		config_reps=`echo $CF | sed -e 's/\*.*$//'`
+		CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
+		;;
+	*)
+		config_reps=1
+		CF1=$CF
+		;;
+	esac
+	if test -f "$CONFIGFRAG/$CF1"
 	then
-		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF`
-		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF" "$cpu_count"`
-		echo $CF $cpu_count >> $T/cfgcpu
+		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1`
+		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
+		for ((cur_rep=0;cur_rep<$config_reps;cur_rep++))
+		do
+			echo $CF1 $cpu_count >> $T/cfgcpu
+		done
 	else
-		echo "The --configs file $CF does not exist, terminating."
+		echo "The --configs file $CF1 does not exist, terminating."
 		exit 1
 	fi
 done
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
index 4970121..f824b4c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -1,3 +1,5 @@
 CONFIG_RCU_TORTURE_TEST=y
 CONFIG_PRINTK_TIME=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
 CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 9fbb41b..1a087c3 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -5,3 +5,4 @@
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
index 4b6f272..4837430 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P
@@ -5,3 +5,4 @@
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index 238bfe3..84a7d51 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1 +1 @@
-rcutorture.torture_type=srcu
+rcutorture.torture_type=srcud
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
index 97f0a0b..2cc0e60 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
@@ -5,5 +5,6 @@
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_RCU=y
-CONFIG_TASKS_RCU=y
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
index 696d2ea7..ad2be91 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -2,4 +2,3 @@
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
-CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
index 9c60da5..c70c51d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -6,8 +6,8 @@
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
-CONFIG_TASKS_RCU=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
 CONFIG_NO_HZ_FULL_ALL=y
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index 36e41df..f1892e0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -8,7 +8,7 @@
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
index 0f08027..6c1a292 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
@@ -1,2 +1,3 @@
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_bh=1
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index f8a10a7..8e9137f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -16,3 +16,4 @@
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 629122f..aeea6a20 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -14,10 +14,10 @@
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
index a25de47..2ac9e68 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -14,7 +14,6 @@
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index 53f24e0..72aa7d8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
+CONFIG_NR_CPUS=16
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -9,12 +9,12 @@
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_FANOUT=4
-CONFIG_RCU_FANOUT_LEAF=4
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=y
 CONFIG_RCU_KTHREAD_PRIO=2
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
new file mode 100644
index 0000000..120c0c8
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -0,0 +1 @@
+rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 0f84db3..3f51127 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -13,10 +13,10 @@
 CONFIG_HOTPLUG_CPU=n
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
-CONFIG_RCU_FANOUT=2
-CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_FANOUT=4
+CONFIG_RCU_FANOUT_LEAF=4
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 212e3bf..c04dfea 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -12,11 +12,11 @@
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_NONE=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 7eee63b..f51d2c7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -14,10 +14,10 @@
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
index da9a03a..dd90f28 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
@@ -1,3 +1,4 @@
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_bh=1
 rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 92a97fa..f422af4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -15,8 +15,8 @@
 CONFIG_HOTPLUG_CPU=y
 CONFIG_RCU_FANOUT=2
 CONFIG_RCU_FANOUT_LEAF=2
-CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 5812027..a24d2ca 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=16
+CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -13,13 +13,13 @@
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
+#CHECK#CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index 3eaecca..b2b8cea 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -13,7 +13,6 @@
 CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
-CONFIG_RCU_FANOUT_EXACT=y
 CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
new file mode 100644
index 0000000..883149b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
@@ -0,0 +1 @@
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
index 2561daf..fb066dc 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -1,3 +1,4 @@
 rcutorture.torture_type=sched
 rcupdate.rcu_self_test=1
 rcupdate.rcu_self_test_sched=1
+rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 6076b36..aa4ed08 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -16,3 +16,4 @@
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+#CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index ec03c88..b24c000 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -12,13 +12,12 @@
 CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE.
 CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
-CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
-CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not.
+CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
 CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
 CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
-CONFIG_RCU_CPU_STALL_INFO -- Do one.
-CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
-CONFIG_RCU_FANOUT_EXACT -- Do one.
+CONFIG_RCU_CPU_STALL_INFO -- Now default, avoid at least twice.
+CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
 CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
 CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL.
 CONFIG_RCU_NOCB_CPU -- Do three, see below.
@@ -27,28 +26,19 @@
 CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
 CONFIG_RCU_TRACE -- Do half.
 CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
+!RCU_EXPERT -- Do a few, but these have to be vanilla configurations.
 RCU-bh: Do one with PREEMPT and one with !PREEMPT.
 RCU-sched: Do one with PREEMPT but not BOOST.
 
 
-Hierarchy:
+Boot parameters:
 
-TREE01.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=8, CONFIG_RCU_FANOUT_EXACT=n.
-TREE02.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=3.
-TREE03.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=4, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=4.
-TREE04.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE05.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=n
-	CONFIG_RCU_FANOUT_LEAF=6.
-TREE06.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=y
-	CONFIG_RCU_FANOUT_LEAF=6.
-TREE07.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE08.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=y,
-	CONFIG_RCU_FANOUT_LEAF=2.
-TREE09.	CONFIG_NR_CPUS=1.
+nohz_full - do at least one.
+maxcpu -- do at least one.
+rcupdate.rcu_self_test_bh -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test_sched -- Do at least one each, offloaded and not.
+rcupdate.rcu_self_test -- Do at least one each, offloaded and not.
+rcutree.rcu_fanout_exact -- Do at least one.
 
 
 Kconfig Parameters Ignored: