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

Pull RCU updates from Ingo Molnad:
 "The main RCU related changes in this cycle were:

   - Removal of spin_unlock_wait()
   - SRCU updates
   - RCU torture-test updates
   - RCU Documentation updates
   - Extend the sys_membarrier() ABI with the MEMBARRIER_CMD_PRIVATE_EXPEDITED variant
   - Miscellaneous RCU fixes
   - CPU-hotplug fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  arch: Remove spin_unlock_wait() arch-specific definitions
  locking: Remove spin_unlock_wait() generic definitions
  drivers/ata: Replace spin_unlock_wait() with lock/unlock pair
  ipc: Replace spin_unlock_wait() with lock/unlock pair
  exit: Replace spin_unlock_wait() with lock/unlock pair
  completion: Replace spin_unlock_wait() with lock/unlock pair
  doc: Set down RCU's scheduling-clock-interrupt needs
  doc: No longer allowed to use rcu_dereference on non-pointers
  doc: Add RCU files to docbook-generation files
  doc: Update memory-barriers.txt for read-to-write dependencies
  doc: Update RCU documentation
  membarrier: Provide expedited private command
  rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter()
  rcu: Add warning to rcu_idle_enter() for irqs enabled
  rcu: Make rcu_idle_enter() rely on callers disabling irqs
  rcu: Add assertions verifying blocked-tasks list
  rcu/tracing: Set disable_rcu_irq_enter on rcu_eqs_exit()
  rcu: Add TPS() protection for _rcu_barrier_trace strings
  rcu: Use idle versions of swait to make idle-hack clear
  swait: Add idle variants which don't contribute to load average
  ...

85 files changed, 1237 insertions, 1323 deletions

diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 95b30fa25d56..62e847bcdcdd 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -2080,6 +2080,8 @@ Some of the relevant points of interest are as follows:
 <li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
 <li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
 <li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
+<li>	<a href="#Scheduling-Clock Interrupts and RCU">
+	Scheduling-Clock Interrupts and RCU</a>.
 <li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
 <li>	<a href="#Performance, Scalability, Response Time, and Reliability">
 	Performance, Scalability, Response Time, and Reliability</a>.
@@ -2532,6 +2534,134 @@ I learned of many of these requirements via angry phone calls:
 Flaming me on the Linux-kernel mailing list was apparently not
 sufficient to fully vent their ire at RCU's energy-efficiency bugs!
 
+<h3><a name="Scheduling-Clock Interrupts and RCU">
+Scheduling-Clock Interrupts and RCU</a></h3>
+
+<p>
+The kernel transitions between in-kernel non-idle execution, userspace
+execution, and the idle loop.
+Depending on kernel configuration, RCU handles these states differently:
+
+<table border=3>
+<tr><th><tt>HZ</tt> Kconfig</th>
+	<th>In-Kernel</th>
+		<th>Usermode</th>
+			<th>Idle</th></tr>
+<tr><th align="left"><tt>HZ_PERIODIC</tt></th>
+	<td>Can rely on scheduling-clock interrupt.</td>
+		<td>Can rely on scheduling-clock interrupt and its
+		    detection of interrupt from usermode.</td>
+			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
+<tr><th align="left"><tt>NO_HZ_IDLE</tt></th>
+	<td>Can rely on scheduling-clock interrupt.</td>
+		<td>Can rely on scheduling-clock interrupt and its
+		    detection of interrupt from usermode.</td>
+			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
+<tr><th align="left"><tt>NO_HZ_FULL</tt></th>
+	<td>Can only sometimes rely on scheduling-clock interrupt.
+	    In other cases, it is necessary to bound kernel execution
+	    times and/or use IPIs.</td>
+		<td>Can rely on RCU's dyntick-idle detection.</td>
+			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
+</table>
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Why can't <tt>NO_HZ_FULL</tt> in-kernel execution rely on the
+	scheduling-clock interrupt, just like <tt>HZ_PERIODIC</tt>
+	and <tt>NO_HZ_IDLE</tt> do?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	Because, as a performance optimization, <tt>NO_HZ_FULL</tt>
+	does not necessarily re-enable the scheduling-clock interrupt
+	on entry to each and every system call.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<p>
+However, RCU must be reliably informed as to whether any given
+CPU is currently in the idle loop, and, for <tt>NO_HZ_FULL</tt>,
+also whether that CPU is executing in usermode, as discussed
+<a href="#Energy Efficiency">earlier</a>.
+It also requires that the scheduling-clock interrupt be enabled when
+RCU needs it to be:
+
+<ol>
+<li>	If a CPU is either idle or executing in usermode, and RCU believes
+	it is non-idle, the scheduling-clock tick had better be running.
+	Otherwise, you will get RCU CPU stall warnings.  Or at best,
+	very long (11-second) grace periods, with a pointless IPI waking
+	the CPU from time to time.
+<li>	If a CPU is in a portion of the kernel that executes RCU read-side
+	critical sections, and RCU believes this CPU to be idle, you will get
+	random memory corruption.  <b>DON'T DO THIS!!!</b>
+
+	<br>This is one reason to test with lockdep, which will complain
+	about this sort of thing.
+<li>	If a CPU is in a portion of the kernel that is absolutely
+	positively no-joking guaranteed to never execute any RCU read-side
+	critical sections, and RCU believes this CPU to to be idle,
+	no problem.  This sort of thing is used by some architectures
+	for light-weight exception handlers, which can then avoid the
+	overhead of <tt>rcu_irq_enter()</tt> and <tt>rcu_irq_exit()</tt>
+	at exception entry and exit, respectively.
+	Some go further and avoid the entireties of <tt>irq_enter()</tt>
+	and <tt>irq_exit()</tt>.
+
+	<br>Just make very sure you are running some of your tests with
+	<tt>CONFIG_PROVE_RCU=y</tt>, just in case one of your code paths
+	was in fact joking about not doing RCU read-side critical sections.
+<li>	If a CPU is executing in the kernel with the scheduling-clock
+	interrupt disabled and RCU believes this CPU to be non-idle,
+	and if the CPU goes idle (from an RCU perspective) every few
+	jiffies, no problem.  It is usually OK for there to be the
+	occasional gap between idle periods of up to a second or so.
+
+	<br>If the gap grows too long, you get RCU CPU stall warnings.
+<li>	If a CPU is either idle or executing in usermode, and RCU believes
+	it to be idle, of course no problem.
+<li>	If a CPU is executing in the kernel, the kernel code
+	path is passing through quiescent states at a reasonable
+	frequency (preferably about once per few jiffies, but the
+	occasional excursion to a second or so is usually OK) and the
+	scheduling-clock interrupt is enabled, of course no problem.
+
+	<br>If the gap between a successive pair of quiescent states grows
+	too long, you get RCU CPU stall warnings.
+</ol>
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	But what if my driver has a hardware interrupt handler
+	that can run for many seconds?
+	I cannot invoke <tt>schedule()</tt> from an hardware
+	interrupt handler, after all!
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	One approach is to do <tt>rcu_irq_exit();rcu_irq_enter();</tt>
+	every so often.
+	But given that long-running interrupt handlers can cause
+	other problems, not least for response time, shouldn't you
+	work to keep your interrupt handler's runtime within reasonable
+	bounds?
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<p>
+But as long as RCU is properly informed of kernel state transitions between
+in-kernel execution, usermode execution, and idle, and as long as the
+scheduling-clock interrupt is enabled when RCU needs it to be, you
+can rest assured that the bugs you encounter will be in some other
+part of RCU or some other part of the kernel!
+
 <h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
 
 <p>
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 6beda556faf3..49747717d905 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -23,6 +23,14 @@ over a rather long period of time, but improvements are always welcome!
 	Yet another exception is where the low real-time latency of RCU's
 	read-side primitives is critically important.
 
+	One final exception is where RCU readers are used to prevent
+	the ABA problem (https://en.wikipedia.org/wiki/ABA_problem)
+	for lockless updates.  This does result in the mildly
+	counter-intuitive situation where rcu_read_lock() and
+	rcu_read_unlock() are used to protect updates, however, this
+	approach provides the same potential simplifications that garbage
+	collectors do.
+
 1.	Does the update code have proper mutual exclusion?
 
 	RCU does allow -readers- to run (almost) naked, but -writers- must
@@ -40,7 +48,9 @@ over a rather long period of time, but improvements are always welcome!
 	explain how this single task does not become a major bottleneck on
 	big multiprocessor machines (for example, if the task is updating
 	information relating to itself that other tasks can read, there
-	by definition can be no bottleneck).
+	by definition can be no bottleneck).  Note that the definition
+	of "large" has changed significantly:  Eight CPUs was "large"
+	in the year 2000, but a hundred CPUs was unremarkable in 2017.
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
@@ -55,6 +65,12 @@ over a rather long period of time, but improvements are always welcome!
 	Disabling of preemption can serve as rcu_read_lock_sched(), but
 	is less readable.
 
+	Letting RCU-protected pointers "leak" out of an RCU read-side
+	critical section is every bid as bad as letting them leak out
+	from under a lock.  Unless, of course, you have arranged some
+	other means of protection, such as a lock or a reference count
+	-before- letting them out of the RCU read-side critical section.
+
 3.	Does the update code tolerate concurrent accesses?
 
 	The whole point of RCU is to permit readers to run without
@@ -78,10 +94,10 @@ over a rather long period of time, but improvements are always welcome!
 
 		This works quite well, also.
 
-	c.	Make updates appear atomic to readers.  For example,
+	c.	Make updates appear atomic to readers.	For example,
 		pointer updates to properly aligned fields will
 		appear atomic, as will individual atomic primitives.
-		Sequences of perations performed under a lock will -not-
+		Sequences of operations performed under a lock will -not-
 		appear to be atomic to RCU readers, nor will sequences
 		of multiple atomic primitives.
 
@@ -168,8 +184,8 @@ over a rather long period of time, but improvements are always welcome!
 
 5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
 	call_rcu_sched(), or call_srcu() is used, the callback function
-	must be written to be called from softirq context.  In particular,
-	it cannot block.
+	will be called from softirq context.  In particular, it cannot
+	block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
 	any sort of irq context.  The same rule applies for
@@ -178,11 +194,14 @@ over a rather long period of time, but improvements are always welcome!
 	synchronize_sched_expedite(), and synchronize_srcu_expedited().
 
 	The expedited forms of these primitives have the same semantics
-	as the non-expedited forms, but expediting is both expensive
-	and unfriendly to real-time workloads.	Use of the expedited
-	primitives should be restricted to rare configuration-change
-	operations that would not normally be undertaken while a real-time
-	workload is running.
+	as the non-expedited forms, but expediting is both expensive and
+	(with the exception of synchronize_srcu_expedited()) unfriendly
+	to real-time workloads.  Use of the expedited primitives should
+	be restricted to rare configuration-change operations that would
+	not normally be undertaken while a real-time workload is running.
+	However, real-time workloads can use rcupdate.rcu_normal kernel
+	boot parameter to completely disable expedited grace periods,
+	though this might have performance implications.
 
 	In particular, if you find yourself invoking one of the expedited
 	primitives repeatedly in a loop, please do everyone a favor:
@@ -193,11 +212,6 @@ over a rather long period of time, but improvements are always welcome!
 	of the system, especially to real-time workloads running on
 	the rest of the system.
 
-	In addition, it is illegal to call the expedited forms from
-	a CPU-hotplug notifier, or while holding a lock that is acquired
-	by a CPU-hotplug notifier.  Failing to observe this restriction
-	will result in deadlock.
-
 7.	If the updater uses call_rcu() or synchronize_rcu(), then the
 	corresponding readers must use rcu_read_lock() and
 	rcu_read_unlock().  If the updater uses call_rcu_bh() or
@@ -321,7 +335,7 @@ over a rather long period of time, but improvements are always welcome!
 	Similarly, disabling preemption is not an acceptable substitute
 	for rcu_read_lock().  Code that attempts to use preemption
 	disabling where it should be using rcu_read_lock() will break
-	in real-time kernel builds.
+	in CONFIG_PREEMPT=y kernel builds.
 
 	If you want to wait for interrupt handlers, NMI handlers, and
 	code under the influence of preempt_disable(), you instead
@@ -356,23 +370,22 @@ over a rather long period of time, but improvements are always welcome!
 	not the case, a self-spawning RCU callback would prevent the
 	victim CPU from ever going offline.)
 
-14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
-	synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu())
-	may only be invoked from process context.  Unlike other forms of
-	RCU, it -is- permissible to block in an SRCU read-side critical
-	section (demarked by srcu_read_lock() and srcu_read_unlock()),
-	hence the "SRCU": "sleepable RCU".  Please note that if you
-	don't need to sleep in read-side critical sections, you should be
-	using RCU rather than SRCU, because RCU is almost always faster
-	and easier to use than is SRCU.
-
-	Also unlike other forms of RCU, explicit initialization
-	and cleanup is required via init_srcu_struct() and
-	cleanup_srcu_struct().	These are passed a "struct srcu_struct"
-	that defines the scope of a given SRCU domain.	Once initialized,
-	the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-	synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
-	A given synchronize_srcu() waits only for SRCU read-side critical
+14.	Unlike other forms of RCU, it -is- permissible to block in an
+	SRCU read-side critical section (demarked by srcu_read_lock()
+	and srcu_read_unlock()), hence the "SRCU": "sleepable RCU".
+	Please note that if you don't need to sleep in read-side critical
+	sections, you should be using RCU rather than SRCU, because RCU
+	is almost always faster and easier to use than is SRCU.
+
+	Also unlike other forms of RCU, explicit initialization and
+	cleanup is required either at build time via DEFINE_SRCU()
+	or DEFINE_STATIC_SRCU() or at runtime via init_srcu_struct()
+	and cleanup_srcu_struct().  These last two are passed a
+	"struct srcu_struct" that defines the scope of a given
+	SRCU domain.  Once initialized, the srcu_struct is passed
+	to srcu_read_lock(), srcu_read_unlock() synchronize_srcu(),
+	synchronize_srcu_expedited(), and call_srcu().	A given
+	synchronize_srcu() waits only for SRCU read-side critical
 	sections governed by srcu_read_lock() and srcu_read_unlock()
 	calls that have been passed the same srcu_struct.  This property
 	is what makes sleeping read-side critical sections tolerable --
@@ -390,10 +403,16 @@ over a rather long period of time, but improvements are always welcome!
 	Therefore, SRCU should be used in preference to rw_semaphore
 	only in extremely read-intensive situations, or in situations
 	requiring SRCU's read-side deadlock immunity or low read-side
-	realtime latency.
+	realtime latency.  You should also consider percpu_rw_semaphore
+	when you need lightweight readers.
 
-	Note that, rcu_assign_pointer() relates to SRCU just as it does
-	to other forms of RCU.
+	SRCU's expedited primitive (synchronize_srcu_expedited())
+	never sends IPIs to other CPUs, so it is easier on
+	real-time workloads than is synchronize_rcu_expedited(),
+	synchronize_rcu_bh_expedited() or synchronize_sched_expedited().
+
+	Note that rcu_dereference() and rcu_assign_pointer() relate to
+	SRCU just as they do to other forms of RCU.
 
 15.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
@@ -435,3 +454,33 @@ over a rather long period of time, but improvements are always welcome!
 
 	These debugging aids can help you find problems that are
 	otherwise extremely difficult to spot.
+
+18.	If you register a callback using call_rcu(), call_rcu_bh(),
+	call_rcu_sched(), or call_srcu(), and pass in a function defined
+	within a loadable module, then it in necessary to wait for
+	all pending callbacks to be invoked after the last invocation
+	and before unloading that module.  Note that it is absolutely
+	-not- sufficient to wait for a grace period!  The current (say)
+	synchronize_rcu() implementation waits only for all previous
+	callbacks registered on the CPU that synchronize_rcu() is running
+	on, but it is -not- guaranteed to wait for callbacks registered
+	on other CPUs.
+
+	You instead need to use one of the barrier functions:
+
+	o	call_rcu() -> rcu_barrier()
+	o	call_rcu_bh() -> rcu_barrier_bh()
+	o	call_rcu_sched() -> rcu_barrier_sched()
+	o	call_srcu() -> srcu_barrier()
+
+	However, these barrier functions are absolutely -not- guaranteed
+	to wait for a grace period.  In fact, if there are no call_rcu()
+	callbacks waiting anywhere in the system, rcu_barrier() is within
+	its rights to return immediately.
+
+	So if you need to wait for both an RCU grace period and for
+	all pre-existing call_rcu() callbacks, you will need to execute
+	both rcu_barrier() and synchronize_rcu(), if necessary, using
+	something like workqueues to to execute them concurrently.
+
+	See rcubarrier.txt for more information.
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 745f429fda79..7d4ae110c2c9 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -76,15 +76,12 @@ o	I hear that RCU is patented?  What is with that?
 	Of these, one was allowed to lapse by the assignee, and the
 	others have been contributed to the Linux kernel under GPL.
 	There are now also LGPL implementations of user-level RCU
-	available (http://lttng.org/?q=node/18).
+	available (http://liburcu.org/).
 
 o	I hear that RCU needs work in order to support realtime kernels?
 
-	This work is largely completed.  Realtime-friendly RCU can be
-	enabled via the CONFIG_PREEMPT_RCU kernel configuration
-	parameter.  However, work is in progress for enabling priority
-	boosting of preempted RCU read-side critical sections.	This is
-	needed if you have CPU-bound realtime threads.
+	Realtime-friendly RCU can be enabled via the CONFIG_PREEMPT_RCU
+	kernel configuration parameter.
 
 o	Where can I find more information on RCU?
 
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index b2a613f16d74..1acb26b09b48 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -25,35 +25,35 @@ o	You must use one of the rcu_dereference() family of primitives
 	for an example where the compiler can in fact deduce the exact
 	value of the pointer, and thus cause misordering.
 
+o	You are only permitted to use rcu_dereference on pointer values.
+	The compiler simply knows too much about integral values to
+	trust it to carry dependencies through integer operations.
+	There are a very few exceptions, namely that you can temporarily
+	cast the pointer to uintptr_t in order to:
+
+	o	Set bits and clear bits down in the must-be-zero low-order
+		bits of that pointer.  This clearly means that the pointer
+		must have alignment constraints, for example, this does
+		-not- work in general for char* pointers.
+
+	o	XOR bits to translate pointers, as is done in some
+		classic buddy-allocator algorithms.
+
+	It is important to cast the value back to pointer before
+	doing much of anything else with it.
+
 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
-	arithmetic operators, such as "(x*0)", "(x/(x+1))" or "(x%1)".
-	The compiler is within its rights to substitute zero for all of
-	these expressions, so that subsequent accesses no longer depend
-	on the rcu_dereference(), again possibly resulting in bugs due
-	to misordering.
+	"(x-(uintptr_t)x)" for char* pointers.	The compiler is within its
+	rights to substitute zero for this sort of expression, so that
+	subsequent accesses no longer depend on the rcu_dereference(),
+	again possibly resulting in bugs due to misordering.
 
 	Of course, if "p" is a pointer from rcu_dereference(), and "a"
 	and "b" are integers that happen to be equal, the expression
 	"p+a-b" is safe because its value still necessarily depends on
 	the rcu_dereference(), thus maintaining proper ordering.
 
-o	Avoid all-zero operands to the bitwise "&" operator, and
-	similarly avoid all-ones operands to the bitwise "|" operator.
-	If the compiler is able to deduce the value of such operands,
-	it is within its rights to substitute the corresponding constant
-	for the bitwise operation.  Once again, this causes subsequent
-	accesses to no longer depend on the rcu_dereference(), causing
-	bugs due to misordering.
-
-	Please note that single-bit operands to bitwise "&" can also
-	be dangerous.  At this point, the compiler knows that the
-	resulting value can only take on one of two possible values.
-	Therefore, a very small amount of additional information will
-	allow the compiler to deduce the exact value, which again can
-	result in misordering.
-
 o	If you are using RCU to protect JITed functions, so that the
 	"()" function-invocation operator is applied to a value obtained
 	(directly or indirectly) from rcu_dereference(), you may need to
@@ -61,25 +61,6 @@ o	If you are using RCU to protect JITed functions, so that the
 	This issue arises on some systems when a newly JITed function is
 	using the same memory that was used by an earlier JITed function.
 
-o	Do not use the results from the boolean "&&" and "||" when
-	dereferencing.	For example, the following (rather improbable)
-	code is buggy:
-
-		int *p;
-		int *q;
-
-		...
-
-		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
-	do order stores after such branches, they can speculate loads,
-	which can result in misordering bugs.
-
 o	Do not use the results from relational operators ("==", "!=",
 	">", ">=", "<", or "<=") when dereferencing.  For example,
 	the following (quite strange) code is buggy:
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index b10cfe711e68..5d7759071a3e 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -263,6 +263,11 @@ Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes
 	are delayed for a full grace period? Couldn't this result in
 	rcu_barrier() returning prematurely?
 
+The current rcu_barrier() implementation is more complex, due to the need
+to avoid disturbing idle CPUs (especially on battery-powered systems)
+and the need to minimally disturb non-idle CPUs in real-time systems.
+However, the code above illustrates the concepts.
+
 
 rcu_barrier() Summary
 
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 278f6a9383b6..55918b54808b 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -276,15 +276,17 @@ o	"Free-Block Circulation": Shows the number of torture structures
 	somehow gets incremented farther than it should.
 
 Different implementations of RCU can provide implementation-specific
-additional information.  For example, SRCU provides the following
+additional information.  For example, Tree SRCU provides the following
 additional line:
 
-	srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
+	srcud-torture: Tree SRCU per-CPU(idx=0): 0(35,-21) 1(-4,24) 2(1,1) 3(-26,20) 4(28,-47) 5(-9,4) 6(-10,14) 7(-14,11) T(1,6)
 
-This line shows the per-CPU counter state.  The numbers in parentheses are
-the values of the "old" and "current" counters for the corresponding CPU.
-The "idx" value maps the "old" and "current" values to the underlying
-array, and is useful for debugging.
+This line shows the per-CPU counter state, in this case for Tree SRCU
+using a dynamically allocated srcu_struct (hence "srcud-" rather than
+"srcu-").  The numbers in parentheses are the values of the "old" and
+"current" counters for the corresponding CPU.  The "idx" value maps the
+"old" and "current" values to the underlying array, and is useful for
+debugging.  The final "T" entry contains the totals of the counters.
 
 
 USAGE
@@ -304,3 +306,9 @@ checked for such errors.  The "rmmod" command forces a "SUCCESS",
 "FAILURE", or "RCU_HOTPLUG" indication to be printk()ed.  The first
 two are self-explanatory, while the last indicates that while there
 were no RCU failures, CPU-hotplug problems were detected.
+
+However, the tools/testing/selftests/rcutorture/bin/kvm.sh script
+provides better automation, including automatic failure analysis.
+It assumes a qemu/kvm-enabled platform, and runs guest OSes out of initrd.
+See tools/testing/selftests/rcutorture/doc/initrd.txt for instructions
+on setting up such an initrd.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 8ed6c9f6133c..df62466da4e0 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -890,6 +890,8 @@ SRCU:	Critical sections	Grace period		Barrier
 	srcu_read_lock_held
 
 SRCU:	Initialization/cleanup
+	DEFINE_SRCU
+	DEFINE_STATIC_SRCU
 	init_srcu_struct
 	cleanup_srcu_struct
 
@@ -913,7 +915,8 @@ a.	Will readers need to block?  If so, you need SRCU.
 b.	What about the -rt patchset?  If readers would need to block
 	in an non-rt kernel, you need SRCU.  If readers would block
 	in a -rt kernel, but not in a non-rt kernel, SRCU is not
-	necessary.
+	necessary.  (The -rt patchset turns spinlocks into sleeplocks,
+	hence this distinction.)
 
 c.	Do you need to treat NMI handlers, hardirq handlers,
 	and code segments with preemption disabled (whether
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d9c171ce4190..3a99cc96b6b1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2633,9 +2633,10 @@
 			In kernels built with CONFIG_NO_HZ_FULL=y, set
 			the specified list of CPUs whose tick will be stopped
 			whenever possible. The boot CPU will be forced outside
-			the range to maintain the timekeeping.
-			The CPUs in this range must also be included in the
-			rcu_nocbs= set.
+			the range to maintain the timekeeping.  Any CPUs
+			in this list will have their RCU callbacks offloaded,
+			just as if they had also been called out in the
+			rcu_nocbs= boot parameter.
 
 	noiotrap	[SH] Disables trapped I/O port accesses.
 
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 17b00914c6ab..8282099e0cbf 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -344,3 +344,52 @@ codecs, and devices with strict requirements for interface clocking.
 
 .. kernel-doc:: include/linux/clk.h
    :internal:
+
+Synchronization Primitives
+==========================
+
+Read-Copy Update (RCU)
+----------------------
+
+.. kernel-doc:: include/linux/rcupdate.h
+   :external:
+
+.. kernel-doc:: include/linux/rcupdate_wait.h
+   :external:
+
+.. kernel-doc:: include/linux/rcutree.h
+   :external:
+
+.. kernel-doc:: kernel/rcu/tree.c
+   :external:
+
+.. kernel-doc:: kernel/rcu/tree_plugin.h
+   :external:
+
+.. kernel-doc:: kernel/rcu/tree_exp.h
+   :external:
+
+.. kernel-doc:: kernel/rcu/update.c
+   :external:
+
+.. kernel-doc:: include/linux/srcu.h
+   :external:
+
+.. kernel-doc:: kernel/rcu/srcutree.c
+   :external:
+
+.. kernel-doc:: include/linux/rculist_bl.h
+   :external:
+
+.. kernel-doc:: include/linux/rculist.h
+   :external:
+
+.. kernel-doc:: include/linux/rculist_nulls.h
+   :external:
+
+.. kernel-doc:: include/linux/rcu_sync.h
+   :external:
+
+.. kernel-doc:: kernel/rcu/sync.c
+   :external:
+
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index c4ddfcd5ee32..e2ee0a1c299a 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -594,7 +594,24 @@ between the address load and the data load:
 This enforces the occurrence of one of the two implications, and prevents the
 third possibility from arising.
 
-A data-dependency barrier must also order against dependent writes:
+
+[!] Note that this extremely counterintuitive situation arises most easily on
+machines with split caches, so that, for example, one cache bank processes
+even-numbered cache lines and the other bank processes odd-numbered cache
+lines.  The pointer P might be stored in an odd-numbered cache line, and the
+variable B might be stored in an even-numbered cache line.  Then, if the
+even-numbered bank of the reading CPU's cache is extremely busy while the
+odd-numbered bank is idle, one can see the new value of the pointer P (&B),
+but the old value of the variable B (2).
+
+
+A data-dependency barrier is not required to order dependent writes
+because the CPUs that the Linux kernel supports don't do writes
+until they are certain (1) that the write will actually happen, (2)
+of the location of the write, and (3) of the value to be written.
+But please carefully read the "CONTROL DEPENDENCIES" section and the
+Documentation/RCU/rcu_dereference.txt file:  The compiler can and does
+break dependencies in a great many highly creative ways.
 
 	CPU 1		      CPU 2
 	===============	      ===============
@@ -603,29 +620,19 @@ A data-dependency barrier must also order against dependent writes:
 	<write barrier>
 	WRITE_ONCE(P, &B);
 			      Q = READ_ONCE(P);
-			      <data dependency barrier>
-			      *Q = 5;
+			      WRITE_ONCE(*Q, 5);
 
-The data-dependency barrier must order the read into Q with the store
-into *Q.  This prohibits this outcome:
+Therefore, no data-dependency barrier is required to order the read into
+Q with the store into *Q.  In other words, this outcome is prohibited,
+even without a data-dependency barrier:
 
 	(Q == &B) && (B == 4)
 
 Please note that this pattern should be rare.  After all, the whole point
 of dependency ordering is to -prevent- writes to the data structure, along
 with the expensive cache misses associated with those writes.  This pattern
-can be used to record rare error conditions and the like, and the ordering
-prevents such records from being lost.
-
-
-[!] Note that this extremely counterintuitive situation arises most easily on
-machines with split caches, so that, for example, one cache bank processes
-even-numbered cache lines and the other bank processes odd-numbered cache
-lines.  The pointer P might be stored in an odd-numbered cache line, and the
-variable B might be stored in an even-numbered cache line.  Then, if the
-even-numbered bank of the reading CPU's cache is extremely busy while the
-odd-numbered bank is idle, one can see the new value of the pointer P (&B),
-but the old value of the variable B (2).
+can be used to record rare error conditions and the like, and the CPUs'
+naturally occurring ordering prevents such records from being lost.
 
 
 The data dependency barrier is very important to the RCU system,
diff --git a/MAINTAINERS b/MAINTAINERS
index a2add4a4f7f3..f1c919513d69 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8649,7 +8649,7 @@ M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	kernel/membarrier.c
+F:	kernel/sched/membarrier.c
 F:	include/uapi/linux/membarrier.h
 
 MEMORY MANAGEMENT
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index a40b9fc0c6c3..718ac0b64adf 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -16,11 +16,6 @@
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_is_locked(x)	((x)->lock != 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, !VAL);
-}
-
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
         return lock.lock == 0;
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 233d5ffe6ec7..a325e6a36523 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -16,11 +16,6 @@
 #define arch_spin_is_locked(x)	((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__)
 #define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, !VAL);
-}
-
 #ifdef CONFIG_ARC_HAS_LLSC
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 4bec45442072..c030143c18c6 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -52,22 +52,6 @@ static inline void dsb_sev(void)
  * memory.
  */
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	u16 owner = READ_ONCE(lock->tickets.owner);
-
-	for (;;) {
-		arch_spinlock_t tmp = READ_ONCE(*lock);
-
-		if (tmp.tickets.owner == tmp.tickets.next ||
-		    tmp.tickets.owner != owner)
-			break;
-
-		wfe();
-	}
-	smp_acquire__after_ctrl_dep();
-}
-
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index cae331d553f8..f445bd7f2b9f 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -26,58 +26,6 @@
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
  */
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	unsigned int tmp;
-	arch_spinlock_t lockval;
-	u32 owner;
-
-	/*
-	 * Ensure prior spin_lock operations to other locks have completed
-	 * on this CPU before we test whether "lock" is locked.
-	 */
-	smp_mb();
-	owner = READ_ONCE(lock->owner) << 16;
-
-	asm volatile(
-"	sevl\n"
-"1:	wfe\n"
-"2:	ldaxr	%w0, %2\n"
-	/* Is the lock free? */
-"	eor	%w1, %w0, %w0, ror #16\n"
-"	cbz	%w1, 3f\n"
-	/* Lock taken -- has there been a subsequent unlock->lock transition? */
-"	eor	%w1, %w3, %w0, lsl #16\n"
-"	cbz	%w1, 1b\n"
-	/*
-	 * The owner has been updated, so there was an unlock->lock
-	 * transition that we missed. That means we can rely on the
-	 * store-release of the unlock operation paired with the
-	 * load-acquire of the lock operation to publish any of our
-	 * previous stores to the new lock owner and therefore don't
-	 * need to bother with the writeback below.
-	 */
-"	b	4f\n"
-"3:\n"
-	/*
-	 * Serialise against any concurrent lockers by writing back the
-	 * unlocked lock value
-	 */
-	ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-"	stxr	%w1, %w0, %2\n"
-	__nops(2),
-	/* LSE atomics */
-"	mov	%w1, %w0\n"
-"	cas	%w0, %w0, %2\n"
-"	eor	%w1, %w1, %w0\n")
-	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
-"	cbnz	%w1, 2b\n"
-"4:"
-	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	: "r" (owner)
-	: "memory");
-}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
@@ -176,7 +124,11 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	smp_mb(); /* See arch_spin_unlock_wait */
+	/*
+	 * Ensure prior spin_lock operations to other locks have completed
+	 * on this CPU before we test whether "lock" is locked.
+	 */
+	smp_mb(); /* ^^^ */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 659ae8094ed5..c8f7d98d8cb9 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -360,6 +360,8 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
 	 * the thread migrates to a different CPU.
+	 * This full barrier is also required by the membarrier system
+	 * call.
 	 */
 	dsb(ish);
 
diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h
index c58f4a83ed6f..f6431439d15d 100644
--- a/arch/blackfin/include/asm/spinlock.h
+++ b/arch/blackfin/include/asm/spinlock.h
@@ -48,11 +48,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	__raw_spin_unlock_asm(&lock->lock);
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, !VAL);
-}
-
 static inline int arch_read_can_lock(arch_rwlock_t *rw)
 {
 	return __raw_uncached_fetch_asm(&rw->lock) > 0;
diff --git a/arch/blackfin/kernel/module.c b/arch/blackfin/kernel/module.c
index 0188c933b155..15af5768c403 100644
--- a/arch/blackfin/kernel/module.c
+++ b/arch/blackfin/kernel/module.c
@@ -4,8 +4,6 @@
  * Licensed under the GPL-2 or later
  */
 
-#define pr_fmt(fmt) "module %s: " fmt, mod->name
-
 #include <linux/moduleloader.h>
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
@@ -16,6 +14,11 @@
 #include <asm/cacheflush.h>
 #include <linux/uaccess.h>
 
+#define mod_err(mod, fmt, ...)						\
+	pr_err("module %s: " fmt, (mod)->name, ##__VA_ARGS__)
+#define mod_debug(mod, fmt, ...)					\
+	pr_debug("module %s: " fmt, (mod)->name, ##__VA_ARGS__)
+
 /* Transfer the section to the L1 memory */
 int
 module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
@@ -44,7 +47,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l1_inst_sram_alloc(s->sh_size);
 			mod->arch.text_l1 = dest;
 			if (dest == NULL) {
-				pr_err("L1 inst memory allocation failed\n");
+				mod_err(mod, "L1 inst memory allocation failed\n");
 				return -1;
 			}
 			dma_memcpy(dest, (void *)s->sh_addr, s->sh_size);
@@ -56,7 +59,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l1_data_sram_alloc(s->sh_size);
 			mod->arch.data_a_l1 = dest;
 			if (dest == NULL) {
-				pr_err("L1 data memory allocation failed\n");
+				mod_err(mod, "L1 data memory allocation failed\n");
 				return -1;
 			}
 			memcpy(dest, (void *)s->sh_addr, s->sh_size);
@@ -68,7 +71,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l1_data_sram_zalloc(s->sh_size);
 			mod->arch.bss_a_l1 = dest;
 			if (dest == NULL) {
-				pr_err("L1 data memory allocation failed\n");
+				mod_err(mod, "L1 data memory allocation failed\n");
 				return -1;
 			}
 
@@ -77,7 +80,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l1_data_B_sram_alloc(s->sh_size);
 			mod->arch.data_b_l1 = dest;
 			if (dest == NULL) {
-				pr_err("L1 data memory allocation failed\n");
+				mod_err(mod, "L1 data memory allocation failed\n");
 				return -1;
 			}
 			memcpy(dest, (void *)s->sh_addr, s->sh_size);
@@ -87,7 +90,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l1_data_B_sram_alloc(s->sh_size);
 			mod->arch.bss_b_l1 = dest;
 			if (dest == NULL) {
-				pr_err("L1 data memory allocation failed\n");
+				mod_err(mod, "L1 data memory allocation failed\n");
 				return -1;
 			}
 			memset(dest, 0, s->sh_size);
@@ -99,7 +102,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l2_sram_alloc(s->sh_size);
 			mod->arch.text_l2 = dest;
 			if (dest == NULL) {
-				pr_err("L2 SRAM allocation failed\n");
+				mod_err(mod, "L2 SRAM allocation failed\n");
 				return -1;
 			}
 			memcpy(dest, (void *)s->sh_addr, s->sh_size);
@@ -111,7 +114,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l2_sram_alloc(s->sh_size);
 			mod->arch.data_l2 = dest;
 			if (dest == NULL) {
-				pr_err("L2 SRAM allocation failed\n");
+				mod_err(mod, "L2 SRAM allocation failed\n");
 				return -1;
 			}
 			memcpy(dest, (void *)s->sh_addr, s->sh_size);
@@ -123,7 +126,7 @@ module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			dest = l2_sram_zalloc(s->sh_size);
 			mod->arch.bss_l2 = dest;
 			if (dest == NULL) {
-				pr_err("L2 SRAM allocation failed\n");
+				mod_err(mod, "L2 SRAM allocation failed\n");
 				return -1;
 			}
 
@@ -157,8 +160,8 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf32_Sym *sym;
 	unsigned long location, value, size;
 
-	pr_debug("applying relocate section %u to %u\n",
-		relsec, sechdrs[relsec].sh_info);
+	mod_debug(mod, "applying relocate section %u to %u\n",
+		  relsec, sechdrs[relsec].sh_info);
 
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
 		/* This is where to make the change */
@@ -174,14 +177,14 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 
 #ifdef CONFIG_SMP
 		if (location >= COREB_L1_DATA_A_START) {
-			pr_err("cannot relocate in L1: %u (SMP kernel)\n",
+			mod_err(mod, "cannot relocate in L1: %u (SMP kernel)\n",
 				ELF32_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 		}
 #endif
 
-		pr_debug("location is %lx, value is %lx type is %d\n",
-			location, value, ELF32_R_TYPE(rel[i].r_info));
+		mod_debug(mod, "location is %lx, value is %lx type is %d\n",
+			  location, value, ELF32_R_TYPE(rel[i].r_info));
 
 		switch (ELF32_R_TYPE(rel[i].r_info)) {
 
@@ -200,12 +203,12 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		case R_BFIN_PCREL12_JUMP:
 		case R_BFIN_PCREL12_JUMP_S:
 		case R_BFIN_PCREL10:
-			pr_err("unsupported relocation: %u (no -mlong-calls?)\n",
+			mod_err(mod, "unsupported relocation: %u (no -mlong-calls?)\n",
 				ELF32_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 
 		default:
-			pr_err("unknown relocation: %u\n",
+			mod_err(mod, "unknown relocation: %u\n",
 				ELF32_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 		}
@@ -222,7 +225,7 @@ apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			isram_memcpy((void *)location, &value, size);
 			break;
 		default:
-			pr_err("invalid relocation for %#lx\n", location);
+			mod_err(mod, "invalid relocation for %#lx\n", location);
 			return -ENOEXEC;
 		}
 	}
diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h
index a1c55788c5d6..53a8d5885887 100644
--- a/arch/hexagon/include/asm/spinlock.h
+++ b/arch/hexagon/include/asm/spinlock.h
@@ -179,11 +179,6 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
  */
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, !VAL);
-}
-
 #define arch_spin_is_locked(x) ((x)->lock != 0)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index ca9e76149a4a..df2c121164b8 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -76,22 +76,6 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
 }
 
-static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	int	*p = (int *)&lock->lock, ticket;
-
-	ia64_invala();
-
-	for (;;) {
-		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(ticket) : "r"(p) : "memory");
-		if (!(((ticket >> TICKET_SHIFT) ^ ticket) & TICKET_MASK))
-			return;
-		cpu_relax();
-	}
-
-	smp_acquire__after_ctrl_dep();
-}
-
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	long tmp = ACCESS_ONCE(lock->lock);
@@ -143,11 +127,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 	arch_spin_lock(lock);
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	__ticket_spin_unlock_wait(lock);
-}
-
 #define arch_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
 #define arch_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
 
diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h
index 323c7fc953cd..a56825592b90 100644
--- a/arch/m32r/include/asm/spinlock.h
+++ b/arch/m32r/include/asm/spinlock.h
@@ -30,11 +30,6 @@
 #define arch_spin_is_locked(x)		(*(volatile int *)(&(x)->slock) <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, VAL > 0);
-}
-
 /**
  * arch_spin_trylock - Try spin lock and return a result
  * @lock: Pointer to the lock variable
diff --git a/arch/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h
index c0c7a22be1ae..ddf7fe5708a6 100644
--- a/arch/metag/include/asm/spinlock.h
+++ b/arch/metag/include/asm/spinlock.h
@@ -15,11 +15,6 @@
  * locked.
  */
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, !VAL);
-}
-
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 #define	arch_read_lock_flags(lock, flags) arch_read_lock(lock)
diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h
index 9c7b8f7942d8..fe413b41df6c 100644
--- a/arch/mn10300/include/asm/spinlock.h
+++ b/arch/mn10300/include/asm/spinlock.h
@@ -26,11 +26,6 @@
 
 #define arch_spin_is_locked(x)	(*(volatile signed char *)(&(x)->slock) != 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, !VAL);
-}
-
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	asm volatile(
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index e32936cd7f10..55bfe4affca3 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -14,13 +14,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x)
 
 #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *x)
-{
-	volatile unsigned int *a = __ldcw_align(x);
-
-	smp_cond_load_acquire(a, VAL);
-}
-
 static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 					 unsigned long flags)
 {
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 8c1b913de6d7..d256e448ea49 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -170,39 +170,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->slock = 0;
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	arch_spinlock_t lock_val;
-
-	smp_mb();
-
-	/*
-	 * Atomically load and store back the lock value (unchanged). This
-	 * ensures that our observation of the lock value is ordered with
-	 * respect to other lock operations.
-	 */
-	__asm__ __volatile__(
-"1:	" PPC_LWARX(%0, 0, %2, 0) "\n"
-"	stwcx. %0, 0, %2\n"
-"	bne- 1b\n"
-	: "=&r" (lock_val), "+m" (*lock)
-	: "r" (lock)
-	: "cr0", "xer");
-
-	if (arch_spin_value_unlocked(lock_val))
-		goto out;
-
-	while (lock->slock) {
-		HMT_low();
-		if (SHARED_PROCESSOR)
-			__spin_yield(lock);
-	}
-	HMT_medium();
-
-out:
-	smp_mb();
-}
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index f7838ecd83c6..217ee5210c32 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -98,13 +98,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
 		: "cc", "memory");
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	while (arch_spin_is_locked(lock))
-		arch_spin_relax(lock);
-	smp_acquire__after_ctrl_dep();
-}
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
diff --git a/arch/sh/include/asm/spinlock-cas.h b/arch/sh/include/asm/spinlock-cas.h
index c46e8cc7b515..5ed7dbbd94ff 100644
--- a/arch/sh/include/asm/spinlock-cas.h
+++ b/arch/sh/include/asm/spinlock-cas.h
@@ -29,11 +29,6 @@ static inline unsigned __sl_cas(volatile unsigned *p, unsigned old, unsigned new
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, VAL > 0);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	while (!__sl_cas(&lock->lock, 1, 0));
diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h
index cec78143fa83..f77263aae760 100644
--- a/arch/sh/include/asm/spinlock-llsc.h
+++ b/arch/sh/include/asm/spinlock-llsc.h
@@ -21,11 +21,6 @@
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, VAL > 0);
-}
-
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
  * on the local processor, one does not.
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index 8011e79f59c9..67345b2dc408 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -14,11 +14,6 @@
 
 #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->lock, !VAL);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	__asm__ __volatile__(
diff --git a/arch/tile/include/asm/spinlock_32.h b/arch/tile/include/asm/spinlock_32.h
index b14b1ba5bf9c..cba8ba9b8da6 100644
--- a/arch/tile/include/asm/spinlock_32.h
+++ b/arch/tile/include/asm/spinlock_32.h
@@ -64,8 +64,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->current_ticket = old_ticket + TICKET_QUANTUM;
 }
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock);
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h
index b9718fb4e74a..9a2c2d605752 100644
--- a/arch/tile/include/asm/spinlock_64.h
+++ b/arch/tile/include/asm/spinlock_64.h
@@ -58,8 +58,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	__insn_fetchadd4(&lock->lock, 1U << __ARCH_SPIN_CURRENT_SHIFT);
 }
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock);
-
 void arch_spin_lock_slow(arch_spinlock_t *lock, u32 val);
 
 /* Grab the "next" ticket number and bump it atomically.
diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c
index 076c6cc43113..db9333f2447c 100644
--- a/arch/tile/lib/spinlock_32.c
+++ b/arch/tile/lib/spinlock_32.c
@@ -62,29 +62,6 @@ int arch_spin_trylock(arch_spinlock_t *lock)
 }
 EXPORT_SYMBOL(arch_spin_trylock);
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	u32 iterations = 0;
-	int curr = READ_ONCE(lock->current_ticket);
-	int next = READ_ONCE(lock->next_ticket);
-
-	/* Return immediately if unlocked. */
-	if (next == curr)
-		return;
-
-	/* Wait until the current locker has released the lock. */
-	do {
-		delay_backoff(iterations++);
-	} while (READ_ONCE(lock->current_ticket) == curr);
-
-	/*
-	 * The TILE architecture doesn't do read speculation; therefore
-	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
-	 */
-	barrier();
-}
-EXPORT_SYMBOL(arch_spin_unlock_wait);
-
 /*
  * The low byte is always reserved to be the marker for a "tns" operation
  * since the low bit is set to "1" by a tns.  The next seven bits are
diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c
index a4b5b2cbce93..de414c22892f 100644
--- a/arch/tile/lib/spinlock_64.c
+++ b/arch/tile/lib/spinlock_64.c
@@ -62,28 +62,6 @@ int arch_spin_trylock(arch_spinlock_t *lock)
 }
 EXPORT_SYMBOL(arch_spin_trylock);
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	u32 iterations = 0;
-	u32 val = READ_ONCE(lock->lock);
-	u32 curr = arch_spin_current(val);
-
-	/* Return immediately if unlocked. */
-	if (arch_spin_next(val) == curr)
-		return;
-
-	/* Wait until the current locker has released the lock. */
-	do {
-		delay_backoff(iterations++);
-	} while (arch_spin_current(READ_ONCE(lock->lock)) == curr);
-
-	/*
-	 * The TILE architecture doesn't do read speculation; therefore
-	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
-	 */
-	barrier();
-}
-EXPORT_SYMBOL(arch_spin_unlock_wait);
 
 /*
  * If the read lock fails due to a writer, we retry periodically
diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h
index a36221cf6363..3bb49681ee24 100644
--- a/arch/xtensa/include/asm/spinlock.h
+++ b/arch/xtensa/include/asm/spinlock.h
@@ -33,11 +33,6 @@
 
 #define arch_spin_is_locked(x) ((x)->slock != 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, !VAL);
-}
-
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 3dbd05532c09..e4effef0c83f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -645,12 +645,11 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 	 * completions are honored.  A scmd is determined to have
 	 * timed out iff its associated qc is active and not failed.
 	 */
+	spin_lock_irqsave(ap->lock, flags);
 	if (ap->ops->error_handler) {
 		struct scsi_cmnd *scmd, *tmp;
 		int nr_timedout = 0;
 
-		spin_lock_irqsave(ap->lock, flags);
-
 		/* This must occur under the ap->lock as we don't want
 		   a polled recovery to race the real interrupt handler
 
@@ -700,12 +699,11 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		if (nr_timedout)
 			__ata_port_freeze(ap);
 
-		spin_unlock_irqrestore(ap->lock, flags);
 
 		/* initialize eh_tries */
 		ap->eh_tries = ATA_EH_MAX_TRIES;
-	} else
-		spin_unlock_wait(ap->lock);
+	}
+	spin_unlock_irqrestore(ap->lock, flags);
 
 }
 EXPORT_SYMBOL(ata_scsi_cmd_error_handler);
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 9f0681bf1e87..66260777d644 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -22,17 +22,6 @@
 #include <asm-generic/qspinlock_types.h>
 
 /**
- * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-#ifndef queued_spin_unlock_wait
-extern void queued_spin_unlock_wait(struct qspinlock *lock);
-#endif
-
-/**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
@@ -41,8 +30,6 @@ extern void queued_spin_unlock_wait(struct qspinlock *lock);
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
 	/*
-	 * See queued_spin_unlock_wait().
-	 *
 	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
 	 * isn't immediately observable.
 	 */
@@ -135,6 +122,5 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #define arch_spin_trylock(l)		queued_spin_trylock(l)
 #define arch_spin_unlock(l)		queued_spin_unlock(l)
 #define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
-#define arch_spin_unlock_wait(l)	queued_spin_unlock_wait(l)
 
 #endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index a2f6707e9fc0..0e849715e5be 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -126,17 +126,11 @@ extern struct group_info init_groups;
 #endif
 
 #ifdef CONFIG_PREEMPT_RCU
-#define INIT_TASK_RCU_TREE_PREEMPT()					\
-	.rcu_blocked_node = NULL,
-#else
-#define INIT_TASK_RCU_TREE_PREEMPT(tsk)
-#endif
-#ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)					\
 	.rcu_read_lock_nesting = 0,					\
 	.rcu_read_unlock_special.s = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
-	INIT_TASK_RCU_TREE_PREEMPT()
+	.rcu_blocked_node = NULL,
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f816fc72b51e..96f1baf62ab8 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -58,8 +58,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void call_rcu_bh(struct rcu_head *head, rcu_callback_t func);
 void call_rcu_sched(struct rcu_head *head, rcu_callback_t func);
 void synchronize_sched(void);
-void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
-void synchronize_rcu_tasks(void);
 void rcu_barrier_tasks(void);
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -105,11 +103,13 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
+extern int rcu_scheduler_active __read_mostly;
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcu_cpu_starting(unsigned int cpu);
+void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
@@ -164,8 +164,6 @@ static inline void rcu_init_nohz(void) { }
  * macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
-#define TASKS_RCU(x) x
-extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch_lite(t) \
 	do { \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
@@ -176,10 +174,17 @@ extern struct srcu_struct tasks_rcu_exit_srcu;
 		rcu_all_qs(); \
 		rcu_note_voluntary_context_switch_lite(t); \
 	} while (0)
+void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
+void synchronize_rcu_tasks(void);
+void exit_tasks_rcu_start(void);
+void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
-#define TASKS_RCU(x) do { } while (0)
 #define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
+#define call_rcu_tasks call_rcu_sched
+#define synchronize_rcu_tasks synchronize_sched
+static inline void exit_tasks_rcu_start(void) { }
+static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 5becbbccb998..b3dbf9502fd0 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -116,13 +116,11 @@ static inline void rcu_irq_exit_irqson(void) { }
 static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void exit_rcu(void) { }
-
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
-extern int rcu_scheduler_active __read_mostly;
+#ifdef CONFIG_SRCU
 void rcu_scheduler_starting(void);
-#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
+#else /* #ifndef CONFIG_SRCU */
 static inline void rcu_scheduler_starting(void) { }
-#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
+#endif /* #else #ifndef CONFIG_SRCU */
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_is_watching(void) { return true; }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c05ac5f5aa03..b57c7bedb534 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -589,9 +589,10 @@ struct task_struct {
 
 #ifdef CONFIG_TASKS_RCU
 	unsigned long			rcu_tasks_nvcsw;
-	bool				rcu_tasks_holdout;
-	struct list_head		rcu_tasks_holdout_list;
+	u8				rcu_tasks_holdout;
+	u8				rcu_tasks_idx;
 	int				rcu_tasks_idle_cpu;
+	struct list_head		rcu_tasks_holdout_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 	struct sched_info		sched_info;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index d9510e8522d4..ef018a6e4985 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -130,12 +130,6 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
-/**
- * raw_spin_unlock_wait - wait until the spinlock gets unlocked
- * @lock: the spinlock in question.
- */
-#define raw_spin_unlock_wait(lock)	arch_spin_unlock_wait(&(lock)->raw_lock)
-
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
 #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock)
@@ -369,31 +363,6 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
-/**
- * spin_unlock_wait - Interpose between successive critical sections
- * @lock: the spinlock whose critical sections are to be interposed.
- *
- * Semantically this is equivalent to a spin_lock() immediately
- * followed by a spin_unlock().  However, most architectures have
- * more efficient implementations in which the spin_unlock_wait()
- * cannot block concurrent lock acquisition, and in some cases
- * where spin_unlock_wait() does not write to the lock variable.
- * Nevertheless, spin_unlock_wait() can have high overhead, so if
- * you feel the need to use it, please check to see if there is
- * a better way to get your job done.
- *
- * The ordering guarantees provided by spin_unlock_wait() are:
- *
- * 1.  All accesses preceding the spin_unlock_wait() happen before
- *     any accesses in later critical sections for this same lock.
- * 2.  All accesses following the spin_unlock_wait() happen after
- *     any accesses in earlier critical sections for this same lock.
- */
-static __always_inline void spin_unlock_wait(spinlock_t *lock)
-{
-	raw_spin_unlock_wait(&lock->rlock);
-}
-
 static __always_inline int spin_is_locked(spinlock_t *lock)
 {
 	return raw_spin_is_locked(&lock->rlock);
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 0d9848de677d..612fb530af41 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -26,11 +26,6 @@
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define arch_spin_is_locked(x)		((x)->slock == 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, VAL);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
@@ -73,7 +68,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
-#define arch_spin_unlock_wait(lock)	do { barrier(); (void)(lock); } while (0)
 /* for sched/core.c and kernel_lock.c: */
 # define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
 # define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index cfbfc540cafc..261471f407a5 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -87,4 +87,17 @@ static inline void srcu_barrier(struct srcu_struct *sp)
 	synchronize_srcu(sp);
 }
 
+/* Defined here to avoid size increase for non-torture kernels. */
+static inline void srcu_torture_stats_print(struct srcu_struct *sp,
+					    char *tt, char *tf)
+{
+	int idx;
+
+	idx = READ_ONCE(sp->srcu_idx) & 0x1;
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
+		 tt, tf, idx,
+		 READ_ONCE(sp->srcu_lock_nesting[!idx]),
+		 READ_ONCE(sp->srcu_lock_nesting[idx]));
+}
+
 #endif
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 42973f787e7e..a949f4f9e4d7 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -104,8 +104,6 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN1	1
 #define SRCU_STATE_SCAN2	2
 
-void process_srcu(struct work_struct *work);
-
 #define __SRCU_STRUCT_INIT(name)					\
 	{								\
 		.sda = &name##_srcu_data,				\
@@ -141,5 +139,6 @@ void process_srcu(struct work_struct *work);
 
 void synchronize_srcu_expedited(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
+void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf);
 
 #endif
diff --git a/include/linux/swait.h b/include/linux/swait.h
index c1f9c62a8a50..4a4e180d0a35 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -169,4 +169,59 @@ do {									\
 	__ret;								\
 })
 
+#define __swait_event_idle(wq, condition)				\
+	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
+
+/**
+ * swait_event_idle - wait without system load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ */
+#define swait_event_idle(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event_idle(wq, condition);				\
+} while (0)
+
+#define __swait_event_idle_timeout(wq, condition, timeout)		\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		       TASK_IDLE, timeout,				\
+		       __ret = schedule_timeout(__ret))
+
+/**
+ * swait_event_idle_timeout - wait up to timeout without load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout at which we'll give up in jiffies
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ *
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
+ */
+#define swait_event_idle_timeout(wq, condition, timeout)		\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_idle_timeout(wq,			\
+						   condition, timeout);	\
+	__ret;								\
+})
+
 #endif /* _LINUX_SWAIT_H */
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 91dc089d65b7..e91ae1f2290d 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -703,6 +703,7 @@ TRACE_EVENT(rcu_batch_end,
  * at the beginning and end of the read, respectively.  Note that the
  * callback address can be NULL.
  */
+#define RCUTORTURENAME_LEN 8
 TRACE_EVENT(rcu_torture_read,
 
 	TP_PROTO(const char *rcutorturename, struct rcu_head *rhp,
@@ -711,7 +712,7 @@ TRACE_EVENT(rcu_torture_read,
 	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
 
 	TP_STRUCT__entry(
-		__field(const char *, rcutorturename)
+		__field(char, rcutorturename[RCUTORTURENAME_LEN])
 		__field(struct rcu_head *, rhp)
 		__field(unsigned long, secs)
 		__field(unsigned long, c_old)
@@ -719,7 +720,9 @@ TRACE_EVENT(rcu_torture_read,
 	),
 
 	TP_fast_assign(
-		__entry->rcutorturename = rcutorturename;
+		strncpy(__entry->rcutorturename, rcutorturename,
+			RCUTORTURENAME_LEN);
+		__entry->rcutorturename[RCUTORTURENAME_LEN - 1] = 0;
 		__entry->rhp = rhp;
 		__entry->secs = secs;
 		__entry->c_old = c_old;
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index e0b108bd2624..6d47b3249d8a 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -40,14 +40,33 @@
  *                          (non-running threads are de facto in such a
  *                          state). This covers threads from all processes
  *                          running on the system. This command returns 0.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED:
+ *                          Execute a memory barrier on each running
+ *                          thread belonging to the same process as the current
+ *                          thread. Upon return from system call, the
+ *                          caller thread is ensured that all its running
+ *                          threads siblings have passed through a state
+ *                          where all memory accesses to user-space
+ *                          addresses match program order between entry
+ *                          to and return from the system call
+ *                          (non-running threads are de facto in such a
+ *                          state). This only covers threads from the
+ *                          same processes as the caller thread. This
+ *                          command returns 0. The "expedited" commands
+ *                          complete faster than the non-expedited ones,
+ *                          they never block, but have the downside of
+ *                          causing extra overhead.
  *
  * Command to be passed to the membarrier system call. The commands need to
  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
  * the value 0.
  */
 enum membarrier_cmd {
-	MEMBARRIER_CMD_QUERY = 0,
-	MEMBARRIER_CMD_SHARED = (1 << 0),
+	MEMBARRIER_CMD_QUERY			= 0,
+	MEMBARRIER_CMD_SHARED			= (1 << 0),
+	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
+	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED	= (1 << 3),
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/ipc/sem.c b/ipc/sem.c
index 38371e93bfa5..c6c50370504c 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2091,7 +2091,8 @@ void exit_sem(struct task_struct *tsk)
 			 * possibility where we exit while freeary() didn't
 			 * finish unlocking sem_undo_list.
 			 */
-			spin_unlock_wait(&ulp->lock);
+			spin_lock(&ulp->lock);
+			spin_unlock(&ulp->lock);
 			rcu_read_unlock();
 			break;
 		}
diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb8e8b23c6e..9c323a6daa46 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -108,7 +108,6 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 obj-$(CONFIG_TORTURE_TEST) += torture.o
-obj-$(CONFIG_MEMBARRIER) += membarrier.o
 
 obj-$(CONFIG_HAS_IOMEM) += memremap.o
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index eee033134262..bfbd649ccdc8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -650,6 +650,7 @@ static int takedown_cpu(unsigned int cpu)
 	__cpu_die(cpu);
 
 	tick_cleanup_dead_cpu(cpu);
+	rcutree_migrate_callbacks(cpu);
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c5548faa9f37..f9ef3ecc78c1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -764,7 +764,6 @@ void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
-	TASKS_RCU(int tasks_rcu_i);
 
 	profile_task_exit(tsk);
 	kcov_task_exit(tsk);
@@ -819,7 +818,8 @@ void __noreturn do_exit(long code)
 	 * Ensure that we must observe the pi_state in exit_mm() ->
 	 * mm_release() -> exit_pi_state_list().
 	 */
-	raw_spin_unlock_wait(&tsk->pi_lock);
+	raw_spin_lock_irq(&tsk->pi_lock);
+	raw_spin_unlock_irq(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
@@ -881,9 +881,7 @@ void __noreturn do_exit(long code)
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
-	TASKS_RCU(preempt_disable());
-	TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
-	TASKS_RCU(preempt_enable());
+	exit_tasks_rcu_start();
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
 	mpol_put_task_policy(tsk);
@@ -918,7 +916,7 @@ void __noreturn do_exit(long code)
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
-	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
+	exit_tasks_rcu_finish();
 
 	do_task_dead();
 }
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index fd24153e8a48..294294c71ba4 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -268,123 +268,6 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
-/*
- * Various notes on spin_is_locked() and spin_unlock_wait(), which are
- * 'interesting' functions:
- *
- * PROBLEM: some architectures have an interesting issue with atomic ACQUIRE
- * operations in that the ACQUIRE applies to the LOAD _not_ the STORE (ARM64,
- * PPC). Also qspinlock has a similar issue per construction, the setting of
- * the locked byte can be unordered acquiring the lock proper.
- *
- * This gets to be 'interesting' in the following cases, where the /should/s
- * end up false because of this issue.
- *
- *
- * CASE 1:
- *
- * So the spin_is_locked() correctness issue comes from something like:
- *
- *   CPU0				CPU1
- *
- *   global_lock();			local_lock(i)
- *     spin_lock(&G)			  spin_lock(&L[i])
- *     for (i)				  if (!spin_is_locked(&G)) {
- *       spin_unlock_wait(&L[i]);	    smp_acquire__after_ctrl_dep();
- *					    return;
- *					  }
- *					  // deal with fail
- *
- * Where it is important CPU1 sees G locked or CPU0 sees L[i] locked such
- * that there is exclusion between the two critical sections.
- *
- * The load from spin_is_locked(&G) /should/ be constrained by the ACQUIRE from
- * spin_lock(&L[i]), and similarly the load(s) from spin_unlock_wait(&L[i])
- * /should/ be constrained by the ACQUIRE from spin_lock(&G).
- *
- * Similarly, later stuff is constrained by the ACQUIRE from CTRL+RMB.
- *
- *
- * CASE 2:
- *
- * For spin_unlock_wait() there is a second correctness issue, namely:
- *
- *   CPU0				CPU1
- *
- *   flag = set;
- *   smp_mb();				spin_lock(&l)
- *   spin_unlock_wait(&l);		if (!flag)
- *					  // add to lockless list
- *					spin_unlock(&l);
- *   // iterate lockless list
- *
- * Which wants to ensure that CPU1 will stop adding bits to the list and CPU0
- * will observe the last entry on the list (if spin_unlock_wait() had ACQUIRE
- * semantics etc..)
- *
- * Where flag /should/ be ordered against the locked store of l.
- */
-
-/*
- * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
- * issuing an _unordered_ store to set _Q_LOCKED_VAL.
- *
- * This means that the store can be delayed, but no later than the
- * store-release from the unlock. This means that simply observing
- * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
- *
- * There are two paths that can issue the unordered store:
- *
- *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
- *
- *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
- *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
- *
- * However, in both cases we have other !0 state we've set before to queue
- * ourseves:
- *
- * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
- * load is constrained by that ACQUIRE to not pass before that, and thus must
- * observe the store.
- *
- * For (2) we have a more intersting scenario. We enqueue ourselves using
- * xchg_tail(), which ends up being a RELEASE. This in itself is not
- * sufficient, however that is followed by an smp_cond_acquire() on the same
- * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
- * guarantees we must observe that store.
- *
- * Therefore both cases have other !0 state that is observable before the
- * unordered locked byte store comes through. This means we can use that to
- * wait for the lock store, and then wait for an unlock.
- */
-#ifndef queued_spin_unlock_wait
-void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	u32 val;
-
-	for (;;) {
-		val = atomic_read(&lock->val);
-
-		if (!val) /* not locked, we're done */
-			goto done;
-
-		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
-			break;
-
-		/* not locked, but pending, wait until we observe the lock */
-		cpu_relax();
-	}
-
-	/* any unlock is good */
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-
-done:
-	smp_acquire__after_ctrl_dep();
-}
-EXPORT_SYMBOL(queued_spin_unlock_wait);
-#endif
-
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
deleted file mode 100644
index 9f9284f37f8d..000000000000
--- a/kernel/membarrier.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (C) 2010, 2015 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- *
- * membarrier system call
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/syscalls.h>
-#include <linux/membarrier.h>
-#include <linux/tick.h>
-
-/*
- * Bitmask made from a "or" of all commands within enum membarrier_cmd,
- * except MEMBARRIER_CMD_QUERY.
- */
-#define MEMBARRIER_CMD_BITMASK	(MEMBARRIER_CMD_SHARED)
-
-/**
- * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
- *
- * If this system call is not implemented, -ENOSYS is returned. If the
- * command specified does not exist, or if the command argument is invalid,
- * this system call returns -EINVAL. For a given command, with flags argument
- * set to 0, this system call is guaranteed to always return the same value
- * until reboot.
- *
- * All memory accesses performed in program order from each targeted thread
- * is guaranteed to be ordered with respect to sys_membarrier(). If we use
- * the semantic "barrier()" to represent a compiler barrier forcing memory
- * accesses to be performed in program order across the barrier, and
- * smp_mb() to represent explicit memory barriers forcing full memory
- * ordering across the barrier, we have the following ordering table for
- * each pair of barrier(), sys_membarrier() and smp_mb():
- *
- * The pair ordering is detailed as (O: ordered, X: not ordered):
- *
- *                        barrier()   smp_mb() sys_membarrier()
- *        barrier()          X           X            O
- *        smp_mb()           X           O            O
- *        sys_membarrier()   O           O            O
- */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
-{
-	/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
-	if (tick_nohz_full_enabled())
-		return -ENOSYS;
-	if (unlikely(flags))
-		return -EINVAL;
-	switch (cmd) {
-	case MEMBARRIER_CMD_QUERY:
-		return MEMBARRIER_CMD_BITMASK;
-	case MEMBARRIER_CMD_SHARED:
-		if (num_online_cpus() > 1)
-			synchronize_sched();
-		return 0;
-	default:
-		return -EINVAL;
-	}
-}
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index be90c945063f..9210379c0353 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -69,8 +69,7 @@ config TREE_SRCU
 	  This option selects the full-fledged version of SRCU.
 
 config TASKS_RCU
-	bool
-	default n
+	def_bool PREEMPT
 	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 808b8c85f626..e4b43fef89f5 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -356,22 +356,10 @@ do {									\
 
 #ifdef CONFIG_TINY_RCU
 /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
-static inline bool rcu_gp_is_normal(void)  /* Internal RCU use. */
-{
-	return true;
-}
-static inline bool rcu_gp_is_expedited(void)  /* Internal RCU use. */
-{
-	return false;
-}
-
-static inline void rcu_expedite_gp(void)
-{
-}
-
-static inline void rcu_unexpedite_gp(void)
-{
-}
+static inline bool rcu_gp_is_normal(void) { return true; }
+static inline bool rcu_gp_is_expedited(void) { return false; }
+static inline void rcu_expedite_gp(void) { }
+static inline void rcu_unexpedite_gp(void) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 bool rcu_gp_is_normal(void);     /* Internal RCU use. */
 bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
@@ -419,12 +407,8 @@ static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 	*gpnum = 0;
 	*completed = 0;
 }
-static inline void rcutorture_record_test_transition(void)
-{
-}
-static inline void rcutorture_record_progress(unsigned long vernum)
-{
-}
+static inline void rcutorture_record_test_transition(void) { }
+static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
@@ -460,92 +444,20 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
-
-/*
- * Return the number of grace periods started.
- */
-static inline unsigned long rcu_batches_started(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of bottom-half grace periods started.
- */
-static inline unsigned long rcu_batches_started_bh(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of sched grace periods started.
- */
-static inline unsigned long rcu_batches_started_sched(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of grace periods completed.
- */
-static inline unsigned long rcu_batches_completed(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of bottom-half grace periods completed.
- */
-static inline unsigned long rcu_batches_completed_bh(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of sched grace periods completed.
- */
-static inline unsigned long rcu_batches_completed_sched(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of expedited grace periods completed.
- */
-static inline unsigned long rcu_exp_batches_completed(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of expedited sched grace periods completed.
- */
-static inline unsigned long rcu_exp_batches_completed_sched(void)
-{
-	return 0;
-}
-
-static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
-{
-	return 0;
-}
-
-static inline void rcu_force_quiescent_state(void)
-{
-}
-
-static inline void rcu_bh_force_quiescent_state(void)
-{
-}
-
-static inline void rcu_sched_force_quiescent_state(void)
-{
-}
-
-static inline void show_rcu_gp_kthreads(void)
-{
-}
-
+static inline unsigned long rcu_batches_started(void) { return 0; }
+static inline unsigned long rcu_batches_started_bh(void) { return 0; }
+static inline unsigned long rcu_batches_started_sched(void) { return 0; }
+static inline unsigned long rcu_batches_completed(void) { return 0; }
+static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
+static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
+static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
+static inline unsigned long
+srcu_batches_completed(struct srcu_struct *sp) { return 0; }
+static inline void rcu_force_quiescent_state(void) { }
+static inline void rcu_bh_force_quiescent_state(void) { }
+static inline void rcu_sched_force_quiescent_state(void) { }
+static inline void show_rcu_gp_kthreads(void) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 2b62a38b080f..7649fcd2c4c7 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -36,24 +36,6 @@ void rcu_cblist_init(struct rcu_cblist *rclp)
 }
 
 /*
- * Debug function to actually count the number of callbacks.
- * If the number exceeds the limit specified, return -1.
- */
-long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim)
-{
-	int cnt = 0;
-	struct rcu_head **rhpp = &rclp->head;
-
-	for (;;) {
-		if (!*rhpp)
-			return cnt;
-		if (++cnt > lim)
-			return -1;
-		rhpp = &(*rhpp)->next;
-	}
-}
-
-/*
  * Dequeue the oldest rcu_head structure from the specified callback
  * list.  This function assumes that the callback is non-lazy, but
  * the caller can later invoke rcu_cblist_dequeued_lazy() if it
@@ -103,17 +85,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Is the specified segment of the specified rcu_segcblist structure
- * empty of callbacks?
- */
-bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
-{
-	if (seg == RCU_DONE_TAIL)
-		return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
-	return rsclp->tails[seg - 1] == rsclp->tails[seg];
-}
-
-/*
  * Does the specified rcu_segcblist structure contain callbacks that
  * are ready to be invoked?
  */
@@ -134,50 +105,6 @@ bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Dequeue and return the first ready-to-invoke callback.  If there
- * are no ready-to-invoke callbacks, return NULL.  Disables interrupts
- * to avoid interference.  Does not protect from interference from other
- * CPUs or tasks.
- */
-struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp)
-{
-	unsigned long flags;
-	int i;
-	struct rcu_head *rhp;
-
-	local_irq_save(flags);
-	if (!rcu_segcblist_ready_cbs(rsclp)) {
-		local_irq_restore(flags);
-		return NULL;
-	}
-	rhp = rsclp->head;
-	BUG_ON(!rhp);
-	rsclp->head = rhp->next;
-	for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) {
-		if (rsclp->tails[i] != &rhp->next)
-			break;
-		rsclp->tails[i] = &rsclp->head;
-	}
-	smp_mb(); /* Dequeue before decrement for rcu_barrier(). */
-	WRITE_ONCE(rsclp->len, rsclp->len - 1);
-	local_irq_restore(flags);
-	return rhp;
-}
-
-/*
- * Account for the fact that a previously dequeued callback turned out
- * to be marked as lazy.
- */
-void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	rsclp->len_lazy--;
-	local_irq_restore(flags);
-}
-
-/*
  * Return a pointer to the first callback in the specified rcu_segcblist
  * structure.  This is useful for diagnostics.
  */
@@ -203,17 +130,6 @@ struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Does the specified rcu_segcblist structure contain callbacks that
- * have not yet been processed beyond having been posted, that is,
- * does it contain callbacks in its last segment?
- */
-bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp)
-{
-	return rcu_segcblist_is_enabled(rsclp) &&
-	       !rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL);
-}
-
-/*
  * Enqueue the specified callback onto the specified rcu_segcblist
  * structure, updating accounting as needed.  Note that the ->len
  * field may be accessed locklessly, hence the WRITE_ONCE().
@@ -503,3 +419,27 @@ bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
 			return true;
 	return false;
 }
+
+/*
+ * Merge the source rcu_segcblist structure into the destination
+ * rcu_segcblist structure, then initialize the source.  Any pending
+ * callbacks from the source get to start over.  It is best to
+ * advance and accelerate both the destination and the source
+ * before merging.
+ */
+void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
+			 struct rcu_segcblist *src_rsclp)
+{
+	struct rcu_cblist donecbs;
+	struct rcu_cblist pendcbs;
+
+	rcu_cblist_init(&donecbs);
+	rcu_cblist_init(&pendcbs);
+	rcu_segcblist_extract_count(src_rsclp, &donecbs);
+	rcu_segcblist_extract_done_cbs(src_rsclp, &donecbs);
+	rcu_segcblist_extract_pend_cbs(src_rsclp, &pendcbs);
+	rcu_segcblist_insert_count(dst_rsclp, &donecbs);
+	rcu_segcblist_insert_done_cbs(dst_rsclp, &donecbs);
+	rcu_segcblist_insert_pend_cbs(dst_rsclp, &pendcbs);
+	rcu_segcblist_init(src_rsclp);
+}
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 6e36e36478cd..581c12b63544 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -31,29 +31,7 @@ static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
 	rclp->len_lazy--;
 }
 
-/*
- * Interim function to return rcu_cblist head pointer.  Longer term, the
- * rcu_cblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
-{
-	return rclp->head;
-}
-
-/*
- * Interim function to return rcu_cblist head pointer.  Longer term, the
- * rcu_cblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
-{
-	WARN_ON_ONCE(!rclp->head);
-	return rclp->tail;
-}
-
 void rcu_cblist_init(struct rcu_cblist *rclp);
-long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim);
 struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
 
 /*
@@ -134,14 +112,10 @@ static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
 
 void rcu_segcblist_init(struct rcu_segcblist *rsclp);
 void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
-bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg);
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
-struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp);
-void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
-bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp);
 void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
 			   struct rcu_head *rhp, bool lazy);
 bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
@@ -162,3 +136,5 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
 bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
 bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
 				    unsigned long seq);
+void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
+			 struct rcu_segcblist *src_rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 3cc18110b612..1f87a02c3399 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -317,8 +317,6 @@ static struct rcu_perf_ops sched_ops = {
 	.name		= "sched"
 };
 
-#ifdef CONFIG_TASKS_RCU
-
 /*
  * Definitions for RCU-tasks perf testing.
  */
@@ -346,24 +344,11 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-#define RCUPERF_TASKS_OPS &tasks_ops,
-
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
 }
 
-#else /* #ifdef CONFIG_TASKS_RCU */
-
-#define RCUPERF_TASKS_OPS
-
-static bool __maybe_unused torturing_tasks(void)
-{
-	return false;
-}
-
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
-
 /*
  * If performance tests complete, wait for shutdown to commence.
  */
@@ -658,7 +643,7 @@ rcu_perf_init(void)
 	int firsterr = 0;
 	static struct rcu_perf_ops *perf_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops,
-		RCUPERF_TASKS_OPS
+		&tasks_ops,
 	};
 
 	if (!torture_init_begin(perf_type, verbose, &perf_runnable))
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index b8f7f8ce8575..45f2ffbc1e78 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -199,7 +199,8 @@ MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
 static u64 notrace rcu_trace_clock_local(void)
 {
 	u64 ts = trace_clock_local();
-	unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC);
+
+	(void)do_div(ts, NSEC_PER_USEC);
 	return ts;
 }
 #else /* #ifdef CONFIG_RCU_TRACE */
@@ -496,7 +497,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
-	.name		= "rcu_busted"
+	.name		= "busted"
 };
 
 /*
@@ -522,7 +523,7 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
 
 	delay = torture_random(rrsp) %
 		(nrealreaders * 2 * longdelay * uspertick);
-	if (!delay)
+	if (!delay && in_task())
 		schedule_timeout_interruptible(longdelay);
 	else
 		rcu_read_delay(rrsp);
@@ -561,44 +562,7 @@ static void srcu_torture_barrier(void)
 
 static void srcu_torture_stats(void)
 {
-	int __maybe_unused cpu;
-	int idx;
-
-#ifdef CONFIG_TREE_SRCU
-	idx = srcu_ctlp->srcu_idx & 0x1;
-	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
-		 torture_type, TORTURE_FLAG, idx);
-	for_each_possible_cpu(cpu) {
-		unsigned long l0, l1;
-		unsigned long u0, u1;
-		long c0, c1;
-		struct srcu_data *counts;
-
-		counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
-		u0 = counts->srcu_unlock_count[!idx];
-		u1 = counts->srcu_unlock_count[idx];
-
-		/*
-		 * Make sure that a lock is always counted if the corresponding
-		 * unlock is counted.
-		 */
-		smp_rmb();
-
-		l0 = counts->srcu_lock_count[!idx];
-		l1 = counts->srcu_lock_count[idx];
-
-		c0 = l0 - u0;
-		c1 = l1 - u1;
-		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
-	}
-	pr_cont("\n");
-#elif defined(CONFIG_TINY_SRCU)
-	idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
-	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
-		 torture_type, TORTURE_FLAG, idx,
-		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
-		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
-#endif
+	srcu_torture_stats_print(srcu_ctlp, torture_type, TORTURE_FLAG);
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -620,6 +584,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
 	.name		= "srcu"
 };
 
@@ -652,6 +617,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
 	.name		= "srcud"
 };
 
@@ -696,8 +662,6 @@ static struct rcu_torture_ops sched_ops = {
 	.name		= "sched"
 };
 
-#ifdef CONFIG_TASKS_RCU
-
 /*
  * Definitions for RCU-tasks torture testing.
  */
@@ -735,24 +699,11 @@ static struct rcu_torture_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-#define RCUTORTURE_TASKS_OPS &tasks_ops,
-
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
 }
 
-#else /* #ifdef CONFIG_TASKS_RCU */
-
-#define RCUTORTURE_TASKS_OPS
-
-static bool __maybe_unused torturing_tasks(void)
-{
-	return false;
-}
-
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
-
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -1114,6 +1065,11 @@ rcu_torture_fakewriter(void *arg)
 	return 0;
 }
 
+static void rcu_torture_timer_cb(struct rcu_head *rhp)
+{
+	kfree(rhp);
+}
+
 /*
  * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -1176,6 +1132,14 @@ static void rcu_torture_timer(unsigned long unused)
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
+
+	/* Test call_rcu() invocation from interrupt handler. */
+	if (cur_ops->call) {
+		struct rcu_head *rhp = kmalloc(sizeof(*rhp), GFP_NOWAIT);
+
+		if (rhp)
+			cur_ops->call(rhp, rcu_torture_timer_cb);
+	}
 }
 
 /*
@@ -1354,11 +1318,12 @@ rcu_torture_stats_print(void)
 		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
 					&flags, &gpnum, &completed);
 		wtp = READ_ONCE(writer_task);
-		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
 			 rcu_torture_writer_state_getname(),
 			 rcu_torture_writer_state,
 			 gpnum, completed, flags,
-			 wtp == NULL ? ~0UL : wtp->state);
+			 wtp == NULL ? ~0UL : wtp->state,
+			 wtp == NULL ? -1 : (int)task_cpu(wtp));
 		show_rcu_gp_kthreads();
 		rcu_ftrace_dump(DUMP_ALL);
 	}
@@ -1749,7 +1714,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&sched_ops, RCUTORTURE_TASKS_OPS
+		&sched_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 1a1c1047d2ed..76ac5f50b2c7 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -33,6 +33,8 @@
 #include "rcu_segcblist.h"
 #include "rcu.h"
 
+int rcu_scheduler_active __read_mostly;
+
 static int init_srcu_struct_fields(struct srcu_struct *sp)
 {
 	sp->srcu_lock_nesting[0] = 0;
@@ -193,3 +195,9 @@ void synchronize_srcu(struct srcu_struct *sp)
 	destroy_rcu_head_on_stack(&rs.head);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/* Lockdep diagnostics.  */
+void __init rcu_scheduler_starting(void)
+{
+	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index d0ca524bf042..729a8706751d 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -51,6 +51,7 @@ module_param(counter_wrap_check, ulong, 0444);
 
 static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+static void process_srcu(struct work_struct *work);
 
 /*
  * Initialize SRCU combining tree.  Note that statically allocated
@@ -896,6 +897,15 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
 	__call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
 	wait_for_completion(&rcu.completion);
 	destroy_rcu_head_on_stack(&rcu.head);
+
+	/*
+	 * Make sure that later code is ordered after the SRCU grace
+	 * period.  This pairs with the raw_spin_lock_irq_rcu_node()
+	 * in srcu_invoke_callbacks().  Unlike Tree RCU, this is needed
+	 * because the current CPU might have been totally uninvolved with
+	 * (and thus unordered against) that grace period.
+	 */
+	smp_mb();
 }
 
 /**
@@ -1194,7 +1204,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 /*
  * This is the work-queue function that handles SRCU grace periods.
  */
-void process_srcu(struct work_struct *work)
+static void process_srcu(struct work_struct *work)
 {
 	struct srcu_struct *sp;
 
@@ -1203,7 +1213,6 @@ void process_srcu(struct work_struct *work)
 	srcu_advance_state(sp);
 	srcu_reschedule(sp, srcu_get_delay(sp));
 }
-EXPORT_SYMBOL_GPL(process_srcu);
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
@@ -1217,6 +1226,43 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
+void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
+{
+	int cpu;
+	int idx;
+	unsigned long s0 = 0, s1 = 0;
+
+	idx = sp->srcu_idx & 0x1;
+	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+	for_each_possible_cpu(cpu) {
+		unsigned long l0, l1;
+		unsigned long u0, u1;
+		long c0, c1;
+		struct srcu_data *counts;
+
+		counts = per_cpu_ptr(sp->sda, cpu);
+		u0 = counts->srcu_unlock_count[!idx];
+		u1 = counts->srcu_unlock_count[idx];
+
+		/*
+		 * Make sure that a lock is always counted if the corresponding
+		 * unlock is counted.
+		 */
+		smp_rmb();
+
+		l0 = counts->srcu_lock_count[!idx];
+		l1 = counts->srcu_lock_count[idx];
+
+		c0 = l0 - u0;
+		c1 = l1 - u1;
+		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+		s0 += c0;
+		s1 += c1;
+	}
+	pr_cont(" T(%ld,%ld)\n", s0, s1);
+}
+EXPORT_SYMBOL_GPL(srcu_torture_stats_print);
+
 static int __init srcu_bootup_announce(void)
 {
 	pr_info("Hierarchical SRCU implementation.\n");
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index f8488965250f..a64eee0db39e 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -56,8 +56,6 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.curtail	= &rcu_bh_ctrlblk.rcucblist,
 };
 
-#include "tiny_plugin.h"
-
 void rcu_barrier_bh(void)
 {
 	wait_rcu_gp(call_rcu_bh);
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
deleted file mode 100644
index f0a01b2a3062..000000000000
--- a/kernel/rcu/tiny_plugin.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition
- * Internal non-public definitions that provide either classic
- * or preemptible semantics.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
- * Copyright (c) 2010 Linaro
- *
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
- */
-
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
-#include <linux/kernel_stat.h>
-
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-
-/*
- * During boot, we forgive RCU lockdep issues.  After this function is
- * invoked, we start taking RCU lockdep issues seriously.  Note that unlike
- * Tree RCU, Tiny RCU transitions directly from RCU_SCHEDULER_INACTIVE
- * to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
- * The reason for this is that Tiny RCU does not need kthreads, so does
- * not have to care about the fact that the scheduler is half-initialized
- * at a certain phase of the boot process.  Unless SRCU is in the mix.
- */
-void __init rcu_scheduler_starting(void)
-{
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = IS_ENABLED(CONFIG_SRCU)
-		? RCU_SCHEDULER_INIT : RCU_SCHEDULER_RUNNING;
-}
-
-#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 51d4c3acf32d..84fe96641b2e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -97,9 +97,6 @@ struct rcu_state sname##_state = { \
 	.gp_state = RCU_GP_IDLE, \
 	.gpnum = 0UL - 300UL, \
 	.completed = 0UL - 300UL, \
-	.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
-	.orphan_pend = RCU_CBLIST_INITIALIZER(sname##_state.orphan_pend), \
-	.orphan_done = RCU_CBLIST_INITIALIZER(sname##_state.orphan_done), \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
@@ -843,13 +840,9 @@ static void rcu_eqs_enter(bool user)
  */
 void rcu_idle_enter(void)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_idle_enter() invoked with irqs enabled!!!");
 	rcu_eqs_enter(false);
-	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
@@ -862,7 +855,8 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
  */
 void rcu_user_enter(void)
 {
-	rcu_eqs_enter(1);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_user_enter() invoked with irqs enabled!!!");
+	rcu_eqs_enter(true);
 }
 #endif /* CONFIG_NO_HZ_FULL */
 
@@ -955,8 +949,10 @@ static void rcu_eqs_exit(bool user)
 	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
 	} else {
+		__this_cpu_inc(disable_rcu_irq_enter);
 		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 		rcu_eqs_exit_common(oldval, user);
+		__this_cpu_dec(disable_rcu_irq_enter);
 	}
 }
 
@@ -979,7 +975,6 @@ void rcu_idle_exit(void)
 	rcu_eqs_exit(false);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
@@ -1358,12 +1353,13 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n",
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rsp->name, j - gpa,
 		       rsp->gpnum, rsp->completed,
 		       rsp->gp_flags,
 		       gp_state_getname(rsp->gp_state), rsp->gp_state,
-		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0);
+		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
+		       rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1);
 		if (rsp->gp_kthread) {
 			sched_show_task(rsp->gp_kthread);
 			wake_up_process(rsp->gp_kthread);
@@ -2067,8 +2063,8 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
- * Helper function for wait_event_interruptible_timeout() wakeup
- * at force-quiescent-state time.
+ * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * time.
  */
 static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
 {
@@ -2206,9 +2202,8 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			swait_event_interruptible(rsp->gp_wq,
-						 READ_ONCE(rsp->gp_flags) &
-						 RCU_GP_FLAG_INIT);
+			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+						     RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
@@ -2239,7 +2234,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = swait_event_interruptible_timeout(rsp->gp_wq,
+			ret = swait_event_idle_timeout(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
@@ -2409,6 +2404,8 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			return;
 		}
 		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
+		WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 &&
+			     rcu_preempt_blocked_readers_cgp(rnp));
 		rnp->qsmask &= ~mask;
 		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
 						 mask, rnp->qsmask, rnp->level,
@@ -2563,85 +2560,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * Send the specified CPU's RCU callbacks to the orphanage.  The
- * specified CPU must be offline, and the caller must hold the
- * ->orphan_lock.
- */
-static void
-rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
-			  struct rcu_node *rnp, struct rcu_data *rdp)
-{
-	lockdep_assert_held(&rsp->orphan_lock);
-
-	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
-		return;
-
-	/*
-	 * Orphan the callbacks.  First adjust the counts.  This is safe
-	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
-	 * cannot be running now.  Thus no memory barrier is required.
-	 */
-	rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist);
-	rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done);
-
-	/*
-	 * Next, move those callbacks still needing a grace period to
-	 * the orphanage, where some other CPU will pick them up.
-	 * Some of the callbacks might have gone partway through a grace
-	 * period, but that is too bad.  They get to start over because we
-	 * cannot assume that grace periods are synchronized across CPUs.
-	 */
-	rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
-
-	/*
-	 * Then move the ready-to-invoke callbacks to the orphanage,
-	 * where some other CPU will pick them up.  These will not be
-	 * required to pass though another grace period: They are done.
-	 */
-	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done);
-
-	/* Finally, disallow further callbacks on this CPU.  */
-	rcu_segcblist_disable(&rdp->cblist);
-}
-
-/*
- * Adopt the RCU callbacks from the specified rcu_state structure's
- * orphanage.  The caller must hold the ->orphan_lock.
- */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
-{
-	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
-
-	lockdep_assert_held(&rsp->orphan_lock);
-
-	/* No-CBs CPUs are handled specially. */
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
-		return;
-
-	/* Do the accounting first. */
-	rdp->n_cbs_adopted += rsp->orphan_done.len;
-	if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
-		rcu_idle_count_callbacks_posted();
-	rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done);
-
-	/*
-	 * We do not need a memory barrier here because the only way we
-	 * can get here if there is an rcu_barrier() in flight is if
-	 * we are the task doing the rcu_barrier().
-	 */
-
-	/* First adopt the ready-to-invoke callbacks, then the done ones. */
-	rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done);
-	WARN_ON_ONCE(rsp->orphan_done.head);
-	rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
-	WARN_ON_ONCE(rsp->orphan_pend.head);
-	WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) !=
-		     !rcu_segcblist_n_cbs(&rdp->cblist));
-}
-
-/*
  * Trace the fact that this CPU is going offline.
  */
 static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
@@ -2704,14 +2622,12 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 
 /*
  * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context.  Do the remainder of the cleanup,
- * including orphaning the outgoing CPU's RCU callbacks, and also
- * adopting them.  There can only be one CPU hotplug operation at a time,
- * so no other CPU can be attempting to update rcu_cpu_kthread_task.
+ * this fact from process context.  Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
  */
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
@@ -2720,18 +2636,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
-
-	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
-	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
-	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp, flags);
-	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
-
-	WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
-		  !rcu_segcblist_empty(&rdp->cblist),
-		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
-		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
-		  rcu_segcblist_first_cb(&rdp->cblist));
 }
 
 /*
@@ -3569,10 +3473,11 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
 	struct rcu_state *rsp = rdp->rsp;
 
 	if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
-		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence);
+		_rcu_barrier_trace(rsp, TPS("LastCB"), -1,
+				   rsp->barrier_sequence);
 		complete(&rsp->barrier_completion);
 	} else {
-		_rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence);
+		_rcu_barrier_trace(rsp, TPS("CB"), -1, rsp->barrier_sequence);
 	}
 }
 
@@ -3584,14 +3489,15 @@ static void rcu_barrier_func(void *type)
 	struct rcu_state *rsp = type;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
-	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence);
+	_rcu_barrier_trace(rsp, TPS("IRQ"), -1, rsp->barrier_sequence);
 	rdp->barrier_head.func = rcu_barrier_callback;
 	debug_rcu_head_queue(&rdp->barrier_head);
 	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
 		atomic_inc(&rsp->barrier_cpu_count);
 	} else {
 		debug_rcu_head_unqueue(&rdp->barrier_head);
-		_rcu_barrier_trace(rsp, "IRQNQ", -1, rsp->barrier_sequence);
+		_rcu_barrier_trace(rsp, TPS("IRQNQ"), -1,
+				   rsp->barrier_sequence);
 	}
 }
 
@@ -3605,14 +3511,15 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	unsigned long s = rcu_seq_snap(&rsp->barrier_sequence);
 
-	_rcu_barrier_trace(rsp, "Begin", -1, s);
+	_rcu_barrier_trace(rsp, TPS("Begin"), -1, s);
 
 	/* Take mutex to serialize concurrent rcu_barrier() requests. */
 	mutex_lock(&rsp->barrier_mutex);
 
 	/* Did someone else do our work for us? */
 	if (rcu_seq_done(&rsp->barrier_sequence, s)) {
-		_rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence);
+		_rcu_barrier_trace(rsp, TPS("EarlyExit"), -1,
+				   rsp->barrier_sequence);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
 		return;
@@ -3620,7 +3527,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/* Mark the start of the barrier operation. */
 	rcu_seq_start(&rsp->barrier_sequence);
-	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence);
+	_rcu_barrier_trace(rsp, TPS("Inc1"), -1, rsp->barrier_sequence);
 
 	/*
 	 * Initialize the count to one rather than to zero in order to
@@ -3643,10 +3550,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
 		rdp = per_cpu_ptr(rsp->rda, cpu);
 		if (rcu_is_nocb_cpu(cpu)) {
 			if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
-				_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
+				_rcu_barrier_trace(rsp, TPS("OfflineNoCB"), cpu,
 						   rsp->barrier_sequence);
 			} else {
-				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+				_rcu_barrier_trace(rsp, TPS("OnlineNoCB"), cpu,
 						   rsp->barrier_sequence);
 				smp_mb__before_atomic();
 				atomic_inc(&rsp->barrier_cpu_count);
@@ -3654,11 +3561,11 @@ static void _rcu_barrier(struct rcu_state *rsp)
 					   rcu_barrier_callback, rsp, cpu, 0);
 			}
 		} else if (rcu_segcblist_n_cbs(&rdp->cblist)) {
-			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
+			_rcu_barrier_trace(rsp, TPS("OnlineQ"), cpu,
 					   rsp->barrier_sequence);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
 		} else {
-			_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
+			_rcu_barrier_trace(rsp, TPS("OnlineNQ"), cpu,
 					   rsp->barrier_sequence);
 		}
 	}
@@ -3675,7 +3582,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	wait_for_completion(&rsp->barrier_completion);
 
 	/* Mark the end of the barrier operation. */
-	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence);
+	_rcu_barrier_trace(rsp, TPS("Inc2"), -1, rsp->barrier_sequence);
 	rcu_seq_end(&rsp->barrier_sequence);
 
 	/* Other rcu_barrier() invocations can now safely proceed. */
@@ -3777,8 +3684,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	 */
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
-	if (!rdp->beenonline)
-		WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
 	rdp->beenonline = true;	 /* We have now been online. */
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
@@ -3882,6 +3787,8 @@ void rcu_cpu_starting(unsigned int cpu)
 {
 	unsigned long flags;
 	unsigned long mask;
+	int nbits;
+	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp;
@@ -3892,9 +3799,15 @@ void rcu_cpu_starting(unsigned int cpu)
 		mask = rdp->grpmask;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rnp->qsmaskinitnext |= mask;
+		oldmask = rnp->expmaskinitnext;
 		rnp->expmaskinitnext |= mask;
+		oldmask ^= rnp->expmaskinitnext;
+		nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
+		/* Allow lockless access for expedited grace periods. */
+		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
+	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -3937,6 +3850,50 @@ void rcu_report_dead(unsigned int cpu)
 	for_each_rcu_flavor(rsp)
 		rcu_cleanup_dying_idle_cpu(cpu, rsp);
 }
+
+/* Migrate the dead CPU's callbacks to the current CPU. */
+static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_data *my_rdp;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+
+	if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
+		return;  /* No callbacks to migrate. */
+
+	local_irq_save(flags);
+	my_rdp = this_cpu_ptr(rsp->rda);
+	if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) {
+		local_irq_restore(flags);
+		return;
+	}
+	raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */
+	rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */
+	rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
+	WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
+		     !rcu_segcblist_n_cbs(&my_rdp->cblist));
+	raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
+	WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
+		  !rcu_segcblist_empty(&rdp->cblist),
+		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
+		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
+		  rcu_segcblist_first_cb(&rdp->cblist));
+}
+
+/*
+ * The outgoing CPU has just passed through the dying-idle state,
+ * and we are being invoked from the CPU that was IPIed to continue the
+ * offline operation.  We need to migrate the outgoing CPU's callbacks.
+ */
+void rcutree_migrate_callbacks(int cpu)
+{
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp)
+		rcu_migrate_callbacks(cpu, rsp);
+}
 #endif
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9af0f31d6847..8e1f285f0a70 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -219,8 +219,6 @@ struct rcu_data {
 					/* qlen at last check for QS forcing */
 	unsigned long	n_cbs_invoked;	/* count of RCU cbs invoked. */
 	unsigned long	n_nocbs_invoked; /* count of no-CBs RCU cbs invoked. */
-	unsigned long   n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
-	unsigned long   n_cbs_adopted;  /* RCU cbs adopted from dying CPU */
 	unsigned long	n_force_qs_snap;
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
@@ -268,7 +266,9 @@ struct rcu_data {
 	struct rcu_head **nocb_follower_tail;
 	struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
+	raw_spinlock_t nocb_lock;	/* Guard following pair of fields. */
 	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
+	struct timer_list nocb_timer;	/* Enforce finite deferral. */
 
 	/* The following fields are used by the leader, hence own cacheline. */
 	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
@@ -350,15 +350,6 @@ struct rcu_state {
 
 	/* End of fields guarded by root rcu_node's lock. */
 
-	raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
-						/* Protect following fields. */
-	struct rcu_cblist orphan_pend;		/* Orphaned callbacks that */
-						/*  need a grace period. */
-	struct rcu_cblist orphan_done;		/* Orphaned callbacks that */
-						/*  are ready to invoke. */
-						/* (Contains counts.) */
-	/* End of fields guarded by orphan_lock. */
-
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
 	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
 	struct completion barrier_completion;	/* Wake at barrier end. */
@@ -495,7 +486,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags);
-static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 				      struct rcu_data *rdp,
 				      unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index dd21ca47e4b4..46d61b597731 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -73,7 +73,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 	unsigned long flags;
 	unsigned long mask;
 	unsigned long oldmask;
-	int ncpus = READ_ONCE(rsp->ncpus);
+	int ncpus = smp_load_acquire(&rsp->ncpus); /* Order against locking. */
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_up;
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 908b309d60d7..55bde94b9572 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -180,6 +180,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	struct task_struct *t = current;
 
 	lockdep_assert_held(&rnp->lock);
+	WARN_ON_ONCE(rdp->mynode != rnp);
+	WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
 
 	/*
 	 * Decide where to queue the newly blocked task.  In theory,
@@ -261,6 +263,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		rnp->gp_tasks = &t->rcu_node_entry;
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
+	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
+		     !(rnp->qsmask & rdp->grpmask));
+	WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) !=
+		     !(rnp->expmask & rdp->grpmask));
 	raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */
 
 	/*
@@ -482,6 +488,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		rnp = t->rcu_blocked_node;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
+		WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -495,10 +502,10 @@ void rcu_read_unlock_special(struct task_struct *t)
 		if (&t->rcu_node_entry == rnp->exp_tasks)
 			rnp->exp_tasks = np;
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
-			if (&t->rcu_node_entry == rnp->boost_tasks)
-				rnp->boost_tasks = np;
 			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
 			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+			if (&t->rcu_node_entry == rnp->boost_tasks)
+				rnp->boost_tasks = np;
 		}
 
 		/*
@@ -636,10 +643,17 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 {
+	struct task_struct *t;
+
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
 	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
-	if (rcu_preempt_has_tasks(rnp))
+	if (rcu_preempt_has_tasks(rnp)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
+		t = container_of(rnp->gp_tasks, struct task_struct,
+				 rcu_node_entry);
+		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
+						rnp->gpnum, t->pid);
+	}
 	WARN_ON_ONCE(rnp->qsmask);
 }
 
@@ -1788,23 +1802,62 @@ bool rcu_is_nocb_cpu(int cpu)
 }
 
 /*
- * Kick the leader kthread for this NOCB group.
+ * Kick the leader kthread for this NOCB group.  Caller holds ->nocb_lock
+ * and this function releases it.
  */
-static void wake_nocb_leader(struct rcu_data *rdp, bool force)
+static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
+			       unsigned long flags)
+	__releases(rdp->nocb_lock)
 {
 	struct rcu_data *rdp_leader = rdp->nocb_leader;
 
-	if (!READ_ONCE(rdp_leader->nocb_kthread))
+	lockdep_assert_held(&rdp->nocb_lock);
+	if (!READ_ONCE(rdp_leader->nocb_kthread)) {
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		return;
-	if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+	}
+	if (rdp_leader->nocb_leader_sleep || force) {
 		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
+		del_timer(&rdp->nocb_timer);
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
 		swake_up(&rdp_leader->nocb_wq);
+	} else {
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	}
 }
 
 /*
+ * Kick the leader kthread for this NOCB group, but caller has not
+ * acquired locks.
+ */
+static void wake_nocb_leader(struct rcu_data *rdp, bool force)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
+	__wake_nocb_leader(rdp, force, flags);
+}
+
+/*
+ * Arrange to wake the leader kthread for this NOCB group at some
+ * future time when it is safe to do so.
+ */
+static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype,
+				   const char *reason)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
+	if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT)
+		mod_timer(&rdp->nocb_timer, jiffies + 1);
+	WRITE_ONCE(rdp->nocb_defer_wakeup, waketype);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, reason);
+	raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
+}
+
+/*
  * Does the specified CPU need an RCU callback for the specified flavor
  * of rcu_barrier()?
  */
@@ -1891,11 +1944,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE);
-			/* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
-			smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("WakeEmptyIsDeferred"));
+			wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE,
+					       TPS("WakeEmptyIsDeferred"));
 		}
 		rdp->qlen_last_fqs_check = 0;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
@@ -1905,11 +1955,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeOvf"));
 		} else {
-			WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_FORCE);
-			/* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
-			smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("WakeOvfIsDeferred"));
+			wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE,
+					       TPS("WakeOvfIsDeferred"));
 		}
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
 	} else {
@@ -1961,30 +2008,19 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * Adopt orphaned callbacks on a no-CBs CPU, or return 0 if this is
  * not a no-CBs CPU.
  */
-static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 						     struct rcu_data *rdp,
 						     unsigned long flags)
 {
-	long ql = rsp->orphan_done.len;
-	long qll = rsp->orphan_done.len_lazy;
-
-	/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_nocb_adopt_orphan_cbs() invoked with irqs enabled!!!");
 	if (!rcu_is_nocb_cpu(smp_processor_id()))
-		return false;
-
-	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
-	if (rsp->orphan_done.head) {
-		__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_done),
-					rcu_cblist_tail(&rsp->orphan_done),
-					ql, qll, flags);
-	}
-	if (rsp->orphan_pend.head) {
-		__call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_pend),
-					rcu_cblist_tail(&rsp->orphan_pend),
-					ql, qll, flags);
-	}
-	rcu_cblist_init(&rsp->orphan_done);
-	rcu_cblist_init(&rsp->orphan_pend);
+		return false; /* Not NOCBs CPU, caller must migrate CBs. */
+	__call_rcu_nocb_enqueue(my_rdp, rcu_segcblist_head(&rdp->cblist),
+				rcu_segcblist_tail(&rdp->cblist),
+				rcu_segcblist_n_cbs(&rdp->cblist),
+				rcu_segcblist_n_lazy_cbs(&rdp->cblist), flags);
+	rcu_segcblist_init(&rdp->cblist);
+	rcu_segcblist_disable(&rdp->cblist);
 	return true;
 }
 
@@ -2031,6 +2067,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 static void nocb_leader_wait(struct rcu_data *my_rdp)
 {
 	bool firsttime = true;
+	unsigned long flags;
 	bool gotcbs;
 	struct rcu_data *rdp;
 	struct rcu_head **tail;
@@ -2039,13 +2076,17 @@ wait_again:
 
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
-		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
 		swait_event_interruptible(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
-		/* Memory barrier handled by smp_mb() calls below and repoll. */
+		raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
+		my_rdp->nocb_leader_sleep = true;
+		WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+		del_timer(&my_rdp->nocb_timer);
+		raw_spin_unlock_irqrestore(&my_rdp->nocb_lock, flags);
 	} else if (firsttime) {
 		firsttime = false; /* Don't drown trace log with "Poll"! */
-		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Poll");
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Poll"));
 	}
 
 	/*
@@ -2054,7 +2095,7 @@ wait_again:
 	 * nocb_gp_head, where they await a grace period.
 	 */
 	gotcbs = false;
-	smp_mb(); /* wakeup before ->nocb_head reads. */
+	smp_mb(); /* wakeup and _sleep before ->nocb_head reads. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
 		rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
 		if (!rdp->nocb_gp_head)
@@ -2066,56 +2107,41 @@ wait_again:
 		gotcbs = true;
 	}
 
-	/*
-	 * If there were no callbacks, sleep a bit, rescan after a
-	 * memory barrier, and go retry.
-	 */
+	/* No callbacks?  Sleep a bit if polling, and go retry.  */
 	if (unlikely(!gotcbs)) {
-		if (!rcu_nocb_poll)
-			trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
-					    "WokeEmpty");
 		WARN_ON(signal_pending(current));
-		schedule_timeout_interruptible(1);
-
-		/* Rescan in case we were a victim of memory ordering. */
-		my_rdp->nocb_leader_sleep = true;
-		smp_mb();  /* Ensure _sleep true before scan. */
-		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
-			if (READ_ONCE(rdp->nocb_head)) {
-				/* Found CB, so short-circuit next wait. */
-				my_rdp->nocb_leader_sleep = false;
-				break;
-			}
+		if (rcu_nocb_poll) {
+			schedule_timeout_interruptible(1);
+		} else {
+			trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
+					    TPS("WokeEmpty"));
+		}
 		goto wait_again;
 	}
 
 	/* Wait for one grace period. */
 	rcu_nocb_wait_gp(my_rdp);
 
-	/*
-	 * We left ->nocb_leader_sleep unset to reduce cache thrashing.
-	 * We set it now, but recheck for new callbacks while
-	 * traversing our follower list.
-	 */
-	my_rdp->nocb_leader_sleep = true;
-	smp_mb(); /* Ensure _sleep true before scan of ->nocb_head. */
-
 	/* Each pass through the following loop wakes a follower, if needed. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
-		if (READ_ONCE(rdp->nocb_head))
+		if (!rcu_nocb_poll &&
+		    READ_ONCE(rdp->nocb_head) &&
+		    READ_ONCE(my_rdp->nocb_leader_sleep)) {
+			raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
 			my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
+			raw_spin_unlock_irqrestore(&my_rdp->nocb_lock, flags);
+		}
 		if (!rdp->nocb_gp_head)
 			continue; /* No CBs, so no need to wake follower. */
 
 		/* Append callbacks to follower's "done" list. */
-		tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail);
+		raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
+		tail = rdp->nocb_follower_tail;
+		rdp->nocb_follower_tail = rdp->nocb_gp_tail;
 		*tail = rdp->nocb_gp_head;
-		smp_mb__after_atomic(); /* Store *tail before wakeup. */
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
-			/*
-			 * List was empty, wake up the follower.
-			 * Memory barriers supplied by atomic_long_add().
-			 */
+			/* List was empty, so wake up the follower.  */
 			swake_up(&rdp->nocb_wq);
 		}
 	}
@@ -2131,28 +2157,16 @@ wait_again:
  */
 static void nocb_follower_wait(struct rcu_data *rdp)
 {
-	bool firsttime = true;
-
 	for (;;) {
-		if (!rcu_nocb_poll) {
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    "FollowerSleep");
-			swait_event_interruptible(rdp->nocb_wq,
-						 READ_ONCE(rdp->nocb_follower_head));
-		} else if (firsttime) {
-			/* Don't drown trace log with "Poll"! */
-			firsttime = false;
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "Poll");
-		}
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
+		swait_event_interruptible(rdp->nocb_wq,
+					 READ_ONCE(rdp->nocb_follower_head));
 		if (smp_load_acquire(&rdp->nocb_follower_head)) {
 			/* ^^^ Ensure CB invocation follows _head test. */
 			return;
 		}
-		if (!rcu_nocb_poll)
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    "WokeEmpty");
 		WARN_ON(signal_pending(current));
-		schedule_timeout_interruptible(1);
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WokeEmpty"));
 	}
 }
 
@@ -2165,6 +2179,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 static int rcu_nocb_kthread(void *arg)
 {
 	int c, cl;
+	unsigned long flags;
 	struct rcu_head *list;
 	struct rcu_head *next;
 	struct rcu_head **tail;
@@ -2179,11 +2194,14 @@ static int rcu_nocb_kthread(void *arg)
 			nocb_follower_wait(rdp);
 
 		/* Pull the ready-to-invoke callbacks onto local list. */
-		list = READ_ONCE(rdp->nocb_follower_head);
+		raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
+		list = rdp->nocb_follower_head;
+		rdp->nocb_follower_head = NULL;
+		tail = rdp->nocb_follower_tail;
+		rdp->nocb_follower_tail = &rdp->nocb_follower_head;
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		BUG_ON(!list);
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
-		WRITE_ONCE(rdp->nocb_follower_head, NULL);
-		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WokeNonEmpty"));
 
 		/* Each pass through the following loop invokes a callback. */
 		trace_rcu_batch_start(rdp->rsp->name,
@@ -2226,18 +2244,39 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
-static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
 {
+	unsigned long flags;
 	int ndw;
 
-	if (!rcu_nocb_need_deferred_wakeup(rdp))
+	raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
+	if (!rcu_nocb_need_deferred_wakeup(rdp)) {
+		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		return;
+	}
 	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
 	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
-	wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE);
+	__wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
 }
 
+/* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */
+static void do_nocb_deferred_wakeup_timer(unsigned long x)
+{
+	do_nocb_deferred_wakeup_common((struct rcu_data *)x);
+}
+
+/*
+ * Do a deferred wakeup of rcu_nocb_kthread() from fastpath.
+ * This means we do an inexact common-case check.  Note that if
+ * we miss, ->nocb_timer will eventually clean things up.
+ */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+	if (rcu_nocb_need_deferred_wakeup(rdp))
+		do_nocb_deferred_wakeup_common(rdp);
+}
+
 void __init rcu_init_nohz(void)
 {
 	int cpu;
@@ -2287,6 +2326,9 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 	rdp->nocb_tail = &rdp->nocb_head;
 	init_swait_queue_head(&rdp->nocb_wq);
 	rdp->nocb_follower_tail = &rdp->nocb_follower_head;
+	raw_spin_lock_init(&rdp->nocb_lock);
+	setup_timer(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer,
+		    (unsigned long)rdp);
 }
 
 /*
@@ -2459,7 +2501,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 	return false;
 }
 
-static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 						     struct rcu_data *rdp,
 						     unsigned long flags)
 {
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 00e77c470017..5033b66d2753 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -568,7 +568,7 @@ static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
 static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
 
 /* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_SRCU(tasks_rcu_exit_srcu);
+DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
 /* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
 #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
@@ -875,6 +875,22 @@ static void rcu_spawn_tasks_kthread(void)
 	mutex_unlock(&rcu_tasks_kthread_mutex);
 }
 
+/* Do the srcu_read_lock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_start(void)
+{
+	preempt_disable();
+	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+	preempt_enable();
+}
+
+/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_finish(void)
+{
+	preempt_disable();
+	__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
+	preempt_enable();
+}
+
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 #ifndef CONFIG_TINY_RCU
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 53f0164ed362..78f54932ea1d 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -25,3 +25,4 @@ obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
+obj-$(CONFIG_MEMBARRIER) += membarrier.o
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 13fc5ae9bf2f..c9524d2d9316 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -300,6 +300,8 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
+	unsigned long flags;
+
 	if (!READ_ONCE(x->done))
 		return false;
 
@@ -307,14 +309,9 @@ bool completion_done(struct completion *x)
 	 * If ->done, we need to wait for complete() to release ->wait.lock
 	 * otherwise we can end up freeing the completion before complete()
 	 * is done referencing it.
-	 *
-	 * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
-	 * the loads of ->done and ->wait.lock such that we cannot observe
-	 * the lock before complete() acquires it while observing the ->done
-	 * after it's acquired the lock.
 	 */
-	smp_rmb();
-	spin_unlock_wait(&x->wait.lock);
+	spin_lock_irqsave(&x->wait.lock, flags);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
 	return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0869b20fba81..e053c31d96da 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -951,8 +951,13 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (unlikely(!cpu_active(dest_cpu)))
-		return rq;
+	if (p->flags & PF_KTHREAD) {
+		if (unlikely(!cpu_online(dest_cpu)))
+			return rq;
+	} else {
+		if (unlikely(!cpu_active(dest_cpu)))
+			return rq;
+	}
 
 	/* Affinity changed (again). */
 	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
@@ -2635,6 +2640,16 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	prev_state = prev->state;
 	vtime_task_switch(prev);
 	perf_event_task_sched_in(prev, current);
+	/*
+	 * The membarrier system call requires a full memory barrier
+	 * after storing to rq->curr, before going back to user-space.
+	 *
+	 * TODO: This smp_mb__after_unlock_lock can go away if PPC end
+	 * up adding a full barrier to switch_mm(), or we should figure
+	 * out if a smp_mb__after_unlock_lock is really the proper API
+	 * to use.
+	 */
+	smp_mb__after_unlock_lock();
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
 
@@ -3324,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt)
 	if (likely(prev != next)) {
 		rq->nr_switches++;
 		rq->curr = next;
+		/*
+		 * The membarrier system call requires each architecture
+		 * to have a full memory barrier after updating
+		 * rq->curr, before returning to user-space. For TSO
+		 * (e.g. x86), the architecture must provide its own
+		 * barrier in switch_mm(). For weakly ordered machines
+		 * for which spin_unlock() acts as a full memory
+		 * barrier, finish_lock_switch() in common code takes
+		 * care of this barrier. For weakly ordered machines for
+		 * which spin_unlock() acts as a RELEASE barrier (only
+		 * arm64 and PowerPC), arm64 has a full barrier in
+		 * switch_to(), and PowerPC has
+		 * smp_mb__after_unlock_lock() before
+		 * finish_lock_switch().
+		 */
 		++*switch_count;
 
 		trace_sched_switch(preempt, prev, next);
@@ -3352,8 +3382,8 @@ void __noreturn do_task_dead(void)
 	 * To avoid it, we have to wait for releasing tsk->pi_lock which
 	 * is held by try_to_wake_up()
 	 */
-	smp_mb();
-	raw_spin_unlock_wait(&current->pi_lock);
+	raw_spin_lock_irq(&current->pi_lock);
+	raw_spin_unlock_irq(&current->pi_lock);
 
 	/* Causes final put_task_struct in finish_task_switch(): */
 	__set_current_state(TASK_DEAD);
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
new file mode 100644
index 000000000000..a92fddc22747
--- /dev/null
+++ b/kernel/sched/membarrier.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * membarrier system call
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/syscalls.h>
+#include <linux/membarrier.h>
+#include <linux/tick.h>
+#include <linux/cpumask.h>
+
+#include "sched.h"	/* for cpu_rq(). */
+
+/*
+ * Bitmask made from a "or" of all commands within enum membarrier_cmd,
+ * except MEMBARRIER_CMD_QUERY.
+ */
+#define MEMBARRIER_CMD_BITMASK	\
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+
+static void ipi_mb(void *info)
+{
+	smp_mb();	/* IPIs should be serializing but paranoid. */
+}
+
+static void membarrier_private_expedited(void)
+{
+	int cpu;
+	bool fallback = false;
+	cpumask_var_t tmpmask;
+
+	if (num_online_cpus() == 1)
+		return;
+
+	/*
+	 * Matches memory barriers around rq->curr modification in
+	 * scheduler.
+	 */
+	smp_mb();	/* system call entry is not a mb. */
+
+	/*
+	 * Expedited membarrier commands guarantee that they won't
+	 * block, hence the GFP_NOWAIT allocation flag and fallback
+	 * implementation.
+	 */
+	if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) {
+		/* Fallback for OOM. */
+		fallback = true;
+	}
+
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct task_struct *p;
+
+		/*
+		 * Skipping the current CPU is OK even through we can be
+		 * migrated at any point. The current CPU, at the point
+		 * where we read raw_smp_processor_id(), is ensured to
+		 * be in program order with respect to the caller
+		 * thread. Therefore, we can skip this CPU from the
+		 * iteration.
+		 */
+		if (cpu == raw_smp_processor_id())
+			continue;
+		rcu_read_lock();
+		p = task_rcu_dereference(&cpu_rq(cpu)->curr);
+		if (p && p->mm == current->mm) {
+			if (!fallback)
+				__cpumask_set_cpu(cpu, tmpmask);
+			else
+				smp_call_function_single(cpu, ipi_mb, NULL, 1);
+		}
+		rcu_read_unlock();
+	}
+	if (!fallback) {
+		smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+		free_cpumask_var(tmpmask);
+	}
+	cpus_read_unlock();
+
+	/*
+	 * Memory barrier on the caller thread _after_ we finished
+	 * waiting for the last IPI. Matches memory barriers around
+	 * rq->curr modification in scheduler.
+	 */
+	smp_mb();	/* exit from system call is not a mb */
+}
+
+/**
+ * sys_membarrier - issue memory barriers on a set of threads
+ * @cmd:   Takes command values defined in enum membarrier_cmd.
+ * @flags: Currently needs to be 0. For future extensions.
+ *
+ * If this system call is not implemented, -ENOSYS is returned. If the
+ * command specified does not exist, not available on the running
+ * kernel, or if the command argument is invalid, this system call
+ * returns -EINVAL. For a given command, with flags argument set to 0,
+ * this system call is guaranteed to always return the same value until
+ * reboot.
+ *
+ * All memory accesses performed in program order from each targeted thread
+ * is guaranteed to be ordered with respect to sys_membarrier(). If we use
+ * the semantic "barrier()" to represent a compiler barrier forcing memory
+ * accesses to be performed in program order across the barrier, and
+ * smp_mb() to represent explicit memory barriers forcing full memory
+ * ordering across the barrier, we have the following ordering table for
+ * each pair of barrier(), sys_membarrier() and smp_mb():
+ *
+ * The pair ordering is detailed as (O: ordered, X: not ordered):
+ *
+ *                        barrier()   smp_mb() sys_membarrier()
+ *        barrier()          X           X            O
+ *        smp_mb()           X           O            O
+ *        sys_membarrier()   O           O            O
+ */
+SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+{
+	if (unlikely(flags))
+		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_QUERY:
+	{
+		int cmd_mask = MEMBARRIER_CMD_BITMASK;
+
+		if (tick_nohz_full_enabled())
+			cmd_mask &= ~MEMBARRIER_CMD_SHARED;
+		return cmd_mask;
+	}
+	case MEMBARRIER_CMD_SHARED:
+		/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+		if (tick_nohz_full_enabled())
+			return -EINVAL;
+		if (num_online_cpus() > 1)
+			synchronize_sched();
+		return 0;
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
+		membarrier_private_expedited();
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
diff --git a/kernel/task_work.c b/kernel/task_work.c
index d513051fcca2..836a72a66fba 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -96,20 +96,16 @@ void task_work_run(void)
 		 * work->func() can do task_work_add(), do not set
 		 * work_exited unless the list is empty.
 		 */
+		raw_spin_lock_irq(&task->pi_lock);
 		do {
 			work = READ_ONCE(task->task_works);
 			head = !work && (task->flags & PF_EXITING) ?
 				&work_exited : NULL;
 		} while (cmpxchg(&task->task_works, work, head) != work);
+		raw_spin_unlock_irq(&task->pi_lock);
 
 		if (!work)
 			break;
-		/*
-		 * Synchronize with task_work_cancel(). It can't remove
-		 * the first entry == work, cmpxchg(task_works) should
-		 * fail, but it can play with *work and other entries.
-		 */
-		raw_spin_unlock_wait(&task->pi_lock);
 
 		do {
 			next = work->next;
diff --git a/kernel/torture.c b/kernel/torture.c
index 55de96529287..637e172835d8 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -117,7 +117,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 				 torture_type, cpu);
 		(*n_offl_successes)++;
 		delta = jiffies - starttime;
-		sum_offl += delta;
+		*sum_offl += delta;
 		if (*min_offl < 0) {
 			*min_offl = delta;
 			*max_offl = delta;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9979f46c81dc..51390febd5e3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -96,19 +96,26 @@ static struct conntrack_gc_work conntrack_gc_work;
 
 void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 {
+	/* 1) Acquire the lock */
 	spin_lock(lock);
-	while (unlikely(nf_conntrack_locks_all)) {
-		spin_unlock(lock);
 
-		/*
-		 * Order the 'nf_conntrack_locks_all' load vs. the
-		 * spin_unlock_wait() loads below, to ensure
-		 * that 'nf_conntrack_locks_all_lock' is indeed held:
-		 */
-		smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
-		spin_unlock_wait(&nf_conntrack_locks_all_lock);
-		spin_lock(lock);
-	}
+	/* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
+	 * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
+	 */
+	if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
+		return;
+
+	/* fast path failed, unlock */
+	spin_unlock(lock);
+
+	/* Slow path 1) get global lock */
+	spin_lock(&nf_conntrack_locks_all_lock);
+
+	/* Slow path 2) get the lock we want */
+	spin_lock(lock);
+
+	/* Slow path 3) release the global lock */
+	spin_unlock(&nf_conntrack_locks_all_lock);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_lock);
 
@@ -149,28 +156,27 @@ static void nf_conntrack_all_lock(void)
 	int i;
 
 	spin_lock(&nf_conntrack_locks_all_lock);
-	nf_conntrack_locks_all = true;
 
-	/*
-	 * Order the above store of 'nf_conntrack_locks_all' against
-	 * the spin_unlock_wait() loads below, such that if
-	 * nf_conntrack_lock() observes 'nf_conntrack_locks_all'
-	 * we must observe nf_conntrack_locks[] held:
-	 */
-	smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
+	nf_conntrack_locks_all = true;
 
 	for (i = 0; i < CONNTRACK_LOCKS; i++) {
-		spin_unlock_wait(&nf_conntrack_locks[i]);
+		spin_lock(&nf_conntrack_locks[i]);
+
+		/* This spin_unlock provides the "release" to ensure that
+		 * nf_conntrack_locks_all==true is visible to everyone that
+		 * acquired spin_lock(&nf_conntrack_locks[]).
+		 */
+		spin_unlock(&nf_conntrack_locks[i]);
 	}
 }
 
 static void nf_conntrack_all_unlock(void)
 {
-	/*
-	 * All prior stores must be complete before we clear
+	/* All prior stores must be complete before we clear
 	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
 	 * might observe the false value but not the entire
-	 * critical section:
+	 * critical section.
+	 * It pairs with the smp_load_acquire() in nf_conntrack_lock()
 	 */
 	smp_store_release(&nf_conntrack_locks_all, false);
 	spin_unlock(&nf_conntrack_locks_all_lock);
diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh
new file mode 100755
index 000000000000..49fa51726ce3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/config_override.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+#
+# config_override.sh base override
+#
+# Combines base and override, removing any Kconfig options from base
+# that conflict with any in override, concatenating what remains and
+# sending the result to standard output.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2017
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+base=$1
+if test -r $base
+then
+	:
+else
+	echo Base file $base unreadable!!!
+	exit 1
+fi
+
+override=$2
+if test -r $override
+then
+	:
+else
+	echo Override file $override unreadable!!!
+	exit 1
+fi
+
+T=/tmp/config_override.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+sed < $override -e 's/^/grep -v "/' -e 's/=.*$/="/' |
+	awk '
+	{
+		if (last)
+			print last " |";
+		last = $0;
+	}
+	END {
+		if (last)
+			print last;
+	}' > $T/script
+sh $T/script < $base
+cat $override
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 1426a9b97494..07a13779eece 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -66,9 +66,34 @@ configfrag_boot_params () {
 
 # configfrag_boot_cpus bootparam-string config-fragment-file config-cpus
 #
-# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+# Decreases number of CPUs based on any nr_cpus= boot parameters specified.
 configfrag_boot_cpus () {
 	local bootargs="`configfrag_boot_params "$1" "$2"`"
+	local nr_cpus
+	if echo "${bootargs}" | grep -q 'nr_cpus=[0-9]'
+	then
+		nr_cpus="`echo "${bootargs}" | sed -e 's/^.*nr_cpus=\([0-9]*\).*$/\1/'`"
+		if test "$3" -gt "$nr_cpus"
+		then
+			echo $nr_cpus
+		else
+			echo $3
+		fi
+	else
+		echo $3
+	fi
+}
+
+# configfrag_boot_maxcpus bootparam-string config-fragment-file config-cpus
+#
+# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+# This allows tests where additional CPUs come online later during the
+# test run.  However, the torture parameters will be set based on the
+# number of CPUs initially present, so the scripting should schedule
+# test runs based on the maxcpus= boot parameter controlling the initial
+# number of CPUs instead of on the ultimate number of CPUs.
+configfrag_boot_maxcpus () {
+	local bootargs="`configfrag_boot_params "$1" "$2"`"
 	local maxcpus
 	if echo "${bootargs}" | grep -q 'maxcpus=[0-9]'
 	then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index c29f2ec0bf9f..46752c164676 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir more-configs
+# Usage: kvm-build.sh config-template build-dir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -34,24 +34,17 @@ then
 	echo "kvm-build.sh :$builddir: Not a writable directory, cannot build into it"
 	exit 1
 fi
-moreconfigs=${3}
-if test -z "$moreconfigs" -o ! -r "$moreconfigs"
-then
-	echo "kvm-build.sh :$moreconfigs: Not a readable file"
-	exit 1
-fi
 
 T=/tmp/test-linux.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
-grep -v 'CONFIG_[A-Z]*_TORTURE_TEST=' < ${config_template} > $T/config
+cp ${config_template} $T/config
 cat << ___EOF___ >> $T/config
 CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD"
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
-cat $moreconfigs >> $T/config
 
 configinit.sh $T/config O=$builddir
 retval=$?
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 93eede4e8fbe..0af36a721b9c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -40,7 +40,7 @@
 
 T=/tmp/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
-touch $T
+mkdir $T
 
 . $KVM/bin/functions.sh
 . $CONFIGFRAG/ver_functions.sh
@@ -60,37 +60,33 @@ then
 	echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it"
 	exit 1
 fi
-cp $config_template $resdir/ConfigFragment
 echo ' ---' `date`: Starting build
 echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
+touch $resdir/ConfigFragment.input $resdir/ConfigFragment
 if test -r "$config_dir/CFcommon"
 then
-	cat < $config_dir/CFcommon >> $T
+	echo " --- $config_dir/CFcommon" >> $resdir/ConfigFragment.input
+	cat < $config_dir/CFcommon >> $resdir/ConfigFragment.input
+	config_override.sh $config_dir/CFcommon $config_template > $T/Kc1
+	grep '#CHECK#' $config_dir/CFcommon >> $resdir/ConfigFragment
+else
+	cp $config_template $T/Kc1
 fi
-# Optimizations below this point
-# CONFIG_USB=n
-# CONFIG_SECURITY=n
-# CONFIG_NFS_FS=n
-# CONFIG_SOUND=n
-# CONFIG_INPUT_JOYSTICK=n
-# CONFIG_INPUT_TABLET=n
-# CONFIG_INPUT_TOUCHSCREEN=n
-# CONFIG_INPUT_MISC=n
-# CONFIG_INPUT_MOUSE=n
-# # CONFIG_NET=n # disables console access, so accept the slower build.
-# CONFIG_SCSI=n
-# CONFIG_ATA=n
-# CONFIG_FAT_FS=n
-# CONFIG_MSDOS_FS=n
-# CONFIG_VFAT_FS=n
-# CONFIG_ISO9660_FS=n
-# CONFIG_QUOTA=n
-# CONFIG_HID=n
-# CONFIG_CRYPTO=n
-# CONFIG_PCCARD=n
-# CONFIG_PCMCIA=n
-# CONFIG_CARDBUS=n
-# CONFIG_YENTA=n
+echo " --- $config_template" >> $resdir/ConfigFragment.input
+cat $config_template >> $resdir/ConfigFragment.input
+grep '#CHECK#' $config_template >> $resdir/ConfigFragment
+if test -n "$TORTURE_KCONFIG_ARG"
+then
+	echo $TORTURE_KCONFIG_ARG | tr -s " " "\012" > $T/cmdline
+	echo " --- --kconfig argument" >> $resdir/ConfigFragment.input
+	cat $T/cmdline >> $resdir/ConfigFragment.input
+	config_override.sh $T/Kc1 $T/cmdline > $T/Kc2
+	# Note that "#CHECK#" is not permitted on commandline.
+else
+	cp $T/Kc1 $T/Kc2
+fi
+cat $T/Kc2 >> $resdir/ConfigFragment
+
 base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
 if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux
 then
@@ -100,7 +96,9 @@ then
 	KERNEL=$base_resdir/${BOOT_IMAGE##*/} # use the last component of ${BOOT_IMAGE}
 	ln -s $base_resdir/Make*.out $resdir  # for kvm-recheck.sh
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
-elif kvm-build.sh $config_template $builddir $T
+	# Arch-independent indicator
+	touch $resdir/builtkernel
+elif kvm-build.sh $T/Kc2 $builddir
 then
 	# Had to build a kernel for this test.
 	QEMU="`identify_qemu $builddir/vmlinux`"
@@ -112,6 +110,8 @@ then
 	then
 		cp $builddir/$BOOT_IMAGE $resdir
 		KERNEL=$resdir/${BOOT_IMAGE##*/}
+		# Arch-independent indicator
+		touch $resdir/builtkernel
 	else
 		echo No identifiable boot image, not running KVM, see $resdir.
 		echo Do the torture scripts know about your architecture?
@@ -149,7 +149,7 @@ fi
 
 # Generate -smp qemu argument.
 qemu_args="-enable-kvm -nographic $qemu_args"
-cpu_count=`configNR_CPUS.sh $config_template`
+cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment`
 cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
 if test $cpu_count -gt $vcpus
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 50091de3a911..b55895fb10ed 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -41,6 +41,7 @@ PATH=${KVM}/bin:$PATH; export PATH
 TORTURE_DEFCONFIG=defconfig
 TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_KCONFIG_ARG=""
 TORTURE_KMAKE_ARG=""
 TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
@@ -65,6 +66,7 @@ usage () {
 	echo "       --duration minutes"
 	echo "       --interactive"
 	echo "       --jitter N [ maxsleep (us) [ maxspin (us) ] ]"
+	echo "       --kconfig Kconfig-options"
 	echo "       --kmake-arg kernel-make-arguments"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
 	echo "       --no-initrd"
@@ -129,6 +131,11 @@ do
 		jitter="$2"
 		shift
 		;;
+	--kconfig)
+		checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
+		TORTURE_KCONFIG_ARG="$2"
+		shift
+		;;
 	--kmake-arg)
 		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
 		TORTURE_KMAKE_ARG="$2"
@@ -205,6 +212,7 @@ do
 	then
 		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1`
 		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
+		cpu_count=`configfrag_boot_maxcpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"`
 		for ((cur_rep=0;cur_rep<$config_reps;cur_rep++))
 		do
 			echo $CF1 $cpu_count >> $T/cfgcpu
@@ -275,6 +283,7 @@ TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
 TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
 TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG
 TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD
+TORTURE_KCONFIG_ARG="$TORTURE_KCONFIG_ARG"; export TORTURE_KCONFIG_ARG
 TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
@@ -324,6 +333,7 @@ function dump(first, pastlast, batchnum)
 {
 	print "echo ----Start batch " batchnum ": `date`";
 	print "echo ----Start batch " batchnum ": `date` >> " rd "/log";
+	print "needqemurun="
 	jn=1
 	for (j = first; j < pastlast; j++) {
 		builddir=KVM "/b" jn
@@ -359,10 +369,11 @@ function dump(first, pastlast, batchnum)
 	for (j = 1; j < jn; j++) {
 		builddir=KVM "/b" j
 		print "rm -f " builddir ".ready"
-		print "if test -z \"$TORTURE_BUILDONLY\""
+		print "if test -f \"" rd cfr[j] "/builtkernel\""
 		print "then"
-		print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`";
-		print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log";
+		print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date`";
+		print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date` >> " rd "/log";
+		print "\tneedqemurun=1"
 		print "fi"
 	}
 	njitter = 0;
@@ -377,13 +388,22 @@ function dump(first, pastlast, batchnum)
 		njitter = 0;
 		print "echo Build-only run, so suppressing jitter >> " rd "/log"
 	}
-	for (j = 0; j < njitter; j++)
-		print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&"
-	print "wait"
-	print "if test -z \"$TORTURE_BUILDONLY\""
+	if (TORTURE_BUILDONLY) {
+		print "needqemurun="
+	}
+	print "if test -n \"$needqemurun\""
 	print "then"
+	print "\techo ---- Starting kernels. `date`";
+	print "\techo ---- Starting kernels. `date` >> " rd "/log";
+	for (j = 0; j < njitter; j++)
+		print "\tjitter.sh " j " " dur " " ja[2] " " ja[3] "&"
+	print "\twait"
 	print "\techo ---- All kernel runs complete. `date`";
 	print "\techo ---- All kernel runs complete. `date` >> " rd "/log";
+	print "else"
+	print "\twait"
+	print "\techo ---- No kernel runs. `date`";
+	print "\techo ---- No kernel runs. `date` >> " rd "/log";
 	print "fi"
 	for (j = 1; j < jn; j++) {
 		builddir=KVM "/b" j
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
index 6804f9dcfc1b..be7728db42fd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_busted
+rcutorture.torture_type=busted
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot
deleted file mode 100644
index 84a7d51b7481..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-C.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutorture.torture_type=srcud
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
index 6bc24e99862f..c15ada821e45 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
@@ -4,6 +4,7 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TINY_SRCU=y
 CONFIG_RCU_TRACE=n
-CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 1d14e1383016..9f3a4d28e508 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1,4 +1,4 @@
-rcutorture.torture_type=rcu_bh maxcpus=8
+rcutorture.torture_type=rcu_bh maxcpus=8 nr_cpus=43
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 9ad3f89c8dc7..af6fca03602f 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -69,11 +69,11 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE
 CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
 CONFIG_TINY_RCU
+CONFIG_TASKS_RCU
 
 	These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP.
 
 CONFIG_SRCU
-CONFIG_TASKS_RCU
 
 	Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable.