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

Pull RCU changes from Ingo Molnar:
 "Quoting from Paul, the major features of this series are:

  1. Preventing latency spikes of more than 200 microseconds for
     kernels built with NR_CPUS=4096, which is reportedly becoming the
     default for some distros.  This is a first step, as it does not
     help with systems that actually -have- 4096 CPUs (work on this case
     is in progress, but is not yet ready for mainline).

     This category also includes improving concurrency of rcu_barrier(),
     placed here due to conflicts.  Posted to LKML at:

      https://lkml.org/lkml/2012/6/22/381

     Note that patches 18-22 of that series have been defered to 3.7, as
     they have not yet proven themselves to be mainline-ready (and yes,
     these are the ones intended to get rid of RCU's latency spikes for
     systems that actually have 4096 CPUs).

  2. Updates to documentation and rcutorture fixes, the latter category
     including improvements to rcu_barrier() testing.  Posted to LKML at

      http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/04094.html.

  3. Miscellaneous fixes posted to LKML at:

      https://lkml.org/lkml/2012/6/22/500

     with the exception of the last commit, which was posted here:

      http://www.gossamer-threads.com/lists/linux/kernel/1561830

  4. RCU_FAST_NO_HZ fixes and improvements.  Posted to LKML at:

      http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/00006.html
      http://www.gossamer-threads.com/lists/linux/kernel/1561833

     The first four patches of the first series went into 3.5 to fix a
     regression.

  5. Code-style fixes.  These were posted to LKML at

      http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01180.html
      http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01181.html"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  rcu: Fix broken strings in RCU's source code.
  rcu: Fix code-style issues involving "else"
  rcu: Introduce check for callback list/count mismatch
  rcu: Make RCU_FAST_NO_HZ respect nohz= boot parameter
  rcu: Fix qlen_lazy breakage
  rcu: Round FAST_NO_HZ lazy timeout to nearest second
  rcu: The rcu_needs_cpu() function is not a quiescent state
  rcu: Dump only the current CPU's buffers for idle-entry/exit warnings
  rcu: Add check for CPUs going offline with callbacks queued
  rcu: Disable preemption in rcu_blocking_is_gp()
  rcu: Prevent uninitialized string in RCU CPU stall info
  rcu: Fix rcu_is_cpu_idle() #ifdef in TINY_RCU
  rcu: Split RCU core processing out of __call_rcu()
  rcu: Prevent __call_rcu() from invoking RCU core on offline CPUs
  rcu: Make __call_rcu() handle invocation from idle
  rcu: Remove function versions of __kfree_rcu and __is_kfree_rcu_offset
  rcu: Consolidate tree/tiny __rcu_read_{,un}lock() implementations
  rcu: Remove return value from rcu_assign_pointer()
  key: Remove extraneous parentheses from rcu_assign_keypointer()
  rcu: Remove return value from RCU_INIT_POINTER()
  ...

19 files changed, 669 insertions, 590 deletions

diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 5c8d74968090..fc103d7a0474 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -162,9 +162,9 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh() or
-	call_rcu_sched(), is used, the callback function must be
-	written to be called from softirq context.  In particular,
+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.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
@@ -202,11 +202,12 @@ over a rather long period of time, but improvements are always welcome!
 	updater uses call_rcu_sched() or synchronize_sched(), then
 	the corresponding readers must disable preemption, possibly
 	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
-	If the updater uses synchronize_srcu(), the the corresponding
-	readers must use srcu_read_lock() and srcu_read_unlock(),
-	and with the same srcu_struct.	The rules for the expedited
-	primitives are the same as for their non-expedited counterparts.
-	Mixing things up will result in confusion and broken kernels.
+	If the updater uses synchronize_srcu() or call_srcu(),
+	the the corresponding readers must use srcu_read_lock() and
+	srcu_read_unlock(), and with the same srcu_struct.  The rules for
+	the expedited primitives are the same as for their non-expedited
+	counterparts.  Mixing things up will result in confusion and
+	broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -333,14 +334,14 @@ over a rather long period of time, but improvements are always welcome!
 	victim CPU from ever going offline.)
 
 14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
-	synchronize_srcu(), and synchronize_srcu_expedited()) 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.
+	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.
 
 	If you need to enter your read-side critical section in a
 	hardirq or exception handler, and then exit that same read-side
@@ -353,8 +354,8 @@ over a rather long period of time, but improvements are always welcome!
 	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(), and synchronize_srcu_expedited().  A given
-	synchronize_srcu() waits only for SRCU read-side critical
+	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 --
@@ -374,7 +375,7 @@ over a rather long period of time, but improvements are always welcome!
 	requiring SRCU's read-side deadlock immunity or low read-side
 	realtime latency.
 
-	Note that, rcu_assign_pointer() relates to SRCU just as they do
+	Note that, rcu_assign_pointer() relates to SRCU just as it does
 	to other forms of RCU.
 
 15.	The whole point of call_rcu(), synchronize_rcu(), and friends
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index e439a0edee22..38428c125135 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -79,8 +79,6 @@ complete. Pseudo-code using rcu_barrier() is as follows:
    2. Execute rcu_barrier().
    3. Allow the module to be unloaded.
 
-Quick Quiz #1: Why is there no srcu_barrier()?
-
 The rcutorture module makes use of rcu_barrier in its exit function
 as follows:
 
@@ -162,7 +160,7 @@ for any pre-existing callbacks to complete.
 Then lines 55-62 print status and do operation-specific cleanup, and
 then return, permitting the module-unload operation to be completed.
 
-Quick Quiz #2: Is there any other situation where rcu_barrier() might
+Quick Quiz #1: Is there any other situation where rcu_barrier() might
 	be required?
 
 Your module might have additional complications. For example, if your
@@ -242,7 +240,7 @@ reaches zero, as follows:
  4 complete(&rcu_barrier_completion);
  5 }
 
-Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes
 	immediately (thus incrementing rcu_barrier_cpu_count to the
 	value one), but the other CPU's rcu_barrier_func() invocations
 	are delayed for a full grace period? Couldn't this result in
@@ -259,12 +257,7 @@ so that your module may be safely unloaded.
 
 Answers to Quick Quizzes
 
-Quick Quiz #1: Why is there no srcu_barrier()?
-
-Answer: Since there is no call_srcu(), there can be no outstanding SRCU
-	callbacks. Therefore, there is no need to wait for them.
-
-Quick Quiz #2: Is there any other situation where rcu_barrier() might
+Quick Quiz #1: Is there any other situation where rcu_barrier() might
 	be required?
 
 Answer: Interestingly enough, rcu_barrier() was not originally
@@ -278,7 +271,7 @@ Answer: Interestingly enough, rcu_barrier() was not originally
 	implementing rcutorture, and found that rcu_barrier() solves
 	this problem as well.
 
-Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes
 	immediately (thus incrementing rcu_barrier_cpu_count to the
 	value one), but the other CPU's rcu_barrier_func() invocations
 	are delayed for a full grace period? Couldn't this result in
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 4ddf3913fd8c..7dce8a17eac2 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -174,11 +174,20 @@ torture_type	The type of RCU to test, with string values as follows:
 			and synchronize_rcu_bh_expedited().
 
 		"srcu": srcu_read_lock(), srcu_read_unlock() and
+			call_srcu().
+
+		"srcu_sync": srcu_read_lock(), srcu_read_unlock() and
 			synchronize_srcu().
 
 		"srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
 			synchronize_srcu_expedited().
 
+		"srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(),
+			and call_srcu().
+
+		"srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(),
+			and synchronize_srcu().
+
 		"sched": preempt_disable(), preempt_enable(), and
 			call_rcu_sched().
 
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 6bbe8dcdc3da..69ee188515e7 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -833,9 +833,9 @@ sched:	Critical sections	Grace period		Barrier
 
 SRCU:	Critical sections	Grace period		Barrier
 
-	srcu_read_lock		synchronize_srcu	N/A
-	srcu_read_unlock	synchronize_srcu_expedited
-	srcu_read_lock_raw
+	srcu_read_lock		synchronize_srcu	srcu_barrier
+	srcu_read_unlock	call_srcu
+	srcu_read_lock_raw	synchronize_srcu_expedited
 	srcu_read_unlock_raw
 	srcu_dereference
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a92c5ebf373e..12783fa833c3 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2367,6 +2367,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to process
 			in one batch.
 
+	rcutree.fanout_leaf=	[KNL,BOOT]
+			Increase the number of CPUs assigned to each
+			leaf rcu_node structure.  Useful for very large
+			systems.
+
 	rcutree.qhimark=	[KNL,BOOT]
 			Set threshold of queued
 			RCU callbacks over which batch limiting is disabled.
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 9e65eff6af3b..8a7476186990 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -168,8 +168,8 @@ extern struct cred init_cred;
 	.children	= LIST_HEAD_INIT(tsk.children),			\
 	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
 	.group_leader	= &tsk,						\
-	RCU_INIT_POINTER(.real_cred, &init_cred),			\
-	RCU_INIT_POINTER(.cred, &init_cred),				\
+	RCU_POINTER_INITIALIZER(real_cred, &init_cred),			\
+	RCU_POINTER_INITIALIZER(cred, &init_cred),			\
 	.comm		= INIT_TASK_COMM,				\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
diff --git a/include/linux/key.h b/include/linux/key.h
index 4cd22ed627ef..cef3b315ba7c 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -303,7 +303,9 @@ static inline bool key_is_instantiated(const struct key *key)
 				   rwsem_is_locked(&((struct key *)(KEY))->sem)))
 
 #define rcu_assign_keypointer(KEY, PAYLOAD)				\
-	(rcu_assign_pointer((KEY)->payload.rcudata, PAYLOAD))
+do {									\
+	rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD));		\
+} while (0)
 
 #ifdef CONFIG_SYSCTL
 extern ctl_table key_sysctls[];
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 9cac722b169c..115ead2b5155 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -147,6 +147,7 @@ extern void synchronize_sched(void);
 
 extern void __rcu_read_lock(void);
 extern void __rcu_read_unlock(void);
+extern void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -255,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP)
+extern int rcu_is_cpu_idle(void);
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */
+
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
 bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
@@ -266,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
-#ifdef CONFIG_PROVE_RCU
-extern int rcu_is_cpu_idle(void);
-#else /* !CONFIG_PROVE_RCU */
-static inline int rcu_is_cpu_idle(void)
-{
-	return 0;
-}
-#endif /* else !CONFIG_PROVE_RCU */
-
 static inline void rcu_lock_acquire(struct lockdep_map *map)
 {
 	lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
@@ -431,8 +427,7 @@ extern int rcu_my_thread_group_empty(void);
 static inline void rcu_preempt_sleep_check(void)
 {
 	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
-			   "Illegal context switch in RCU read-side "
-			   "critical section");
+			   "Illegal context switch in RCU read-side critical section");
 }
 #else /* #ifdef CONFIG_PROVE_RCU */
 static inline void rcu_preempt_sleep_check(void)
@@ -513,10 +508,10 @@ static inline void rcu_preempt_sleep_check(void)
 		(_________p1); \
 	})
 #define __rcu_assign_pointer(p, v, space) \
-	({ \
+	do { \
 		smp_wmb(); \
 		(p) = (typeof(*v) __force space *)(v); \
-	})
+	} while (0)
 
 
 /**
@@ -851,7 +846,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  *
  * Assigns the specified value to the specified RCU-protected
  * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.  Returns the value assigned.
+ * any prior initialization.
  *
  * Inserts memory barriers on architectures that require them
  * (which is most of them), and also prevents the compiler from
@@ -903,25 +898,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * the reader-accessible portions of the linked structure.
  */
 #define RCU_INIT_POINTER(p, v) \
-		p = (typeof(*v) __force __rcu *)(v)
-
-static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
-{
-	return offset < 4096;
-}
-
-static __always_inline
-void __kfree_rcu(struct rcu_head *head, unsigned long offset)
-{
-	typedef void (*rcu_callback)(struct rcu_head *);
-
-	BUILD_BUG_ON(!__builtin_constant_p(offset));
-
-	/* See the kfree_rcu() header comment. */
-	BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+	do { \
+		p = (typeof(*v) __force __rcu *)(v); \
+	} while (0)
 
-	kfree_call_rcu(head, (rcu_callback)offset);
-}
+/**
+ * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
+ *
+ * GCC-style initialization for an RCU-protected pointer in a structure field.
+ */
+#define RCU_POINTER_INITIALIZER(p, v) \
+		.p = (typeof(*v) __force __rcu *)(v)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
@@ -935,7 +922,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 #define __kfree_rcu(head, offset) \
 	do { \
 		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
-		call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
+		kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
 	} while (0)
 
 /**
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d274734b2aa4..5bde94d8585b 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -541,6 +541,50 @@ TRACE_EVENT(rcu_torture_read,
 		  __entry->rcutorturename, __entry->rhp)
 );
 
+/*
+ * Tracepoint for _rcu_barrier() execution.  The string "s" describes
+ * the _rcu_barrier phase:
+ *	"Begin": rcu_barrier_callback() started.
+ *	"Check": rcu_barrier_callback() checking for piggybacking.
+ *	"EarlyExit": rcu_barrier_callback() piggybacked, thus early exit.
+ *	"Inc1": rcu_barrier_callback() piggyback check counter incremented.
+ *	"Offline": rcu_barrier_callback() found offline CPU
+ *	"OnlineQ": rcu_barrier_callback() found online CPU with callbacks.
+ *	"OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks.
+ *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
+ *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
+ *	"LastCB": An rcu_barrier_callback() invoked the last callback.
+ *	"Inc2": rcu_barrier_callback() piggyback check counter incremented.
+ * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
+ * is the count of remaining callbacks, and "done" is the piggybacking count.
+ */
+TRACE_EVENT(rcu_barrier,
+
+	TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done),
+
+	TP_ARGS(rcuname, s, cpu, cnt, done),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(char *, s)
+		__field(int, cpu)
+		__field(int, cnt)
+		__field(unsigned long, done)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->s = s;
+		__entry->cpu = cpu;
+		__entry->cnt = cnt;
+		__entry->done = done;
+	),
+
+	TP_printk("%s %s cpu %d remaining %d # %lu",
+		  __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt,
+		  __entry->done)
+);
+
 #else /* #ifdef CONFIG_RCU_TRACE */
 
 #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
@@ -564,6 +608,7 @@ TRACE_EVENT(rcu_torture_read,
 #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
 	do { } while (0)
 #define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 95cba41ce1e9..4e6a61b15e86 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -54,6 +54,50 @@
 #ifdef CONFIG_PREEMPT_RCU
 
 /*
+ * Preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+	current->rcu_read_lock_nesting++;
+	barrier();  /* critical section after entry code. */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting != 1) {
+		--t->rcu_read_lock_nesting;
+	} else {
+		barrier();  /* critical section before exit code. */
+		t->rcu_read_lock_nesting = INT_MIN;
+		barrier();  /* assign before ->rcu_read_unlock_special load */
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+			rcu_read_unlock_special(t);
+		barrier();  /* ->rcu_read_unlock_special load before assign */
+		t->rcu_read_lock_nesting = 0;
+	}
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+
+		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+	}
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
  * Check for a task exiting while in a preemptible-RCU read-side
  * critical section, clean up if so.  No need to issue warnings,
  * as debug_check_no_locks_held() already does this if lockdep
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 37a5444204d2..547b1fe5b052 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -172,7 +172,7 @@ void rcu_irq_enter(void)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_PROVE_RCU
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 /*
  * Test whether RCU thinks that the current CPU is idle.
@@ -183,7 +183,7 @@ int rcu_is_cpu_idle(void)
 }
 EXPORT_SYMBOL(rcu_is_cpu_idle);
 
-#endif /* #ifdef CONFIG_PROVE_RCU */
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
  * Test whether the current CPU was interrupted from idle.  Nested
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index fc31a2d65100..918fd1e8509c 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
 	RCU_TRACE(.rcb.name = "rcu_preempt")
 };
 
-static void rcu_read_unlock_special(struct task_struct *t);
 static int rcu_preempted_readers_exp(void);
 static void rcu_report_exp_done(void);
 
@@ -351,8 +350,9 @@ static int rcu_initiate_boost(void)
 			rcu_preempt_ctrlblk.boost_tasks =
 				rcu_preempt_ctrlblk.gp_tasks;
 		invoke_rcu_callbacks();
-	} else
+	} else {
 		RCU_TRACE(rcu_initiate_boost_trace());
+	}
 	return 1;
 }
 
@@ -527,23 +527,11 @@ void rcu_preempt_note_context_switch(void)
 }
 
 /*
- * Tiny-preemptible RCU implementation for rcu_read_lock().
- * Just increment ->rcu_read_lock_nesting, shared state will be updated
- * if we block.
- */
-void __rcu_read_lock(void)
-{
-	current->rcu_read_lock_nesting++;
-	barrier();  /* needed if we ever invoke rcu_read_lock in rcutiny.c */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-/*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-static noinline void rcu_read_unlock_special(struct task_struct *t)
+void rcu_read_unlock_special(struct task_struct *t)
 {
 	int empty;
 	int empty_exp;
@@ -627,38 +615,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t)
 }
 
 /*
- * Tiny-preemptible RCU implementation for rcu_read_unlock().
- * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
- * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
- * invoke rcu_read_unlock_special() to clean up after a context switch
- * in an RCU read-side critical section and other special cases.
- */
-void __rcu_read_unlock(void)
-{
-	struct task_struct *t = current;
-
-	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutiny.c */
-	if (t->rcu_read_lock_nesting != 1)
-		--t->rcu_read_lock_nesting;
-	else {
-		t->rcu_read_lock_nesting = INT_MIN;
-		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
-			rcu_read_unlock_special(t);
-		barrier();  /* ->rcu_read_unlock_special load before assign */
-		t->rcu_read_lock_nesting = 0;
-	}
-#ifdef CONFIG_PROVE_LOCKING
-	{
-		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
-
-		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
-	}
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-/*
  * Check for a quiescent state from the current CPU.  When a task blocks,
  * the task is recorded in the rcu_preempt_ctrlblk structure, which is
  * checked elsewhere.  This is called from the scheduling-clock interrupt.
@@ -823,9 +779,9 @@ void synchronize_rcu_expedited(void)
 		rpcp->exp_tasks = NULL;
 
 	/* Wait for tail of ->blkd_tasks list to drain. */
-	if (!rcu_preempted_readers_exp())
+	if (!rcu_preempted_readers_exp()) {
 		local_irq_restore(flags);
-	else {
+	} else {
 		rcu_initiate_boost();
 		local_irq_restore(flags);
 		wait_event(sync_rcu_preempt_exp_wq,
@@ -846,8 +802,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
  */
 int rcu_preempt_needs_cpu(void)
 {
-	if (!rcu_preempt_running_reader())
-		rcu_preempt_cpu_qs();
 	return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
 }
 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index e66b34ab7555..25b15033c61f 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -49,8 +49,7 @@
 #include <asm/byteorder.h>
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
-	      "Josh Triplett <josh@freedesktop.org>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
 
 static int nreaders = -1;	/* # reader threads, defaults to 2*ncpus */
 static int nfakewriters = 4;	/* # fake writer threads */
@@ -206,6 +205,7 @@ static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
 					/*  and boost task create/destroy. */
 static atomic_t barrier_cbs_count;	/* Barrier callbacks registered. */
+static bool barrier_phase;		/* Test phase. */
 static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
 static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
 static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
@@ -407,8 +407,9 @@ rcu_torture_cb(struct rcu_head *p)
 	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
 		rp->rtort_mbtest = 0;
 		rcu_torture_free(rp);
-	} else
+	} else {
 		cur_ops->deferred_free(rp);
+	}
 }
 
 static int rcu_no_completed(void)
@@ -635,6 +636,17 @@ static void srcu_torture_synchronize(void)
 	synchronize_srcu(&srcu_ctl);
 }
 
+static void srcu_torture_call(struct rcu_head *head,
+			      void (*func)(struct rcu_head *head))
+{
+	call_srcu(&srcu_ctl, head, func);
+}
+
+static void srcu_torture_barrier(void)
+{
+	srcu_barrier(&srcu_ctl);
+}
+
 static int srcu_torture_stats(char *page)
 {
 	int cnt = 0;
@@ -661,8 +673,8 @@ static struct rcu_torture_ops srcu_ops = {
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
-	.call		= NULL,
-	.cb_barrier	= NULL,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu"
 };
@@ -1013,7 +1025,11 @@ rcu_torture_fakewriter(void *arg)
 	do {
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
-		cur_ops->sync();
+		if (cur_ops->cb_barrier != NULL &&
+		    rcu_random(&rand) % (nfakewriters * 8) == 0)
+			cur_ops->cb_barrier();
+		else
+			cur_ops->sync();
 		rcu_stutter_wait("rcu_torture_fakewriter");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 
@@ -1183,27 +1199,27 @@ rcu_torture_printk(char *page)
 	}
 	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
 	cnt += sprintf(&page[cnt],
-		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
-		       "rtmbe: %d rtbke: %ld rtbre: %ld "
-		       "rtbf: %ld rtb: %ld nt: %ld "
-		       "onoff: %ld/%ld:%ld/%ld "
-		       "barrier: %ld/%ld:%ld",
+		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
 		       list_empty(&rcu_torture_freelist),
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
-		       atomic_read(&n_rcu_torture_free),
+		       atomic_read(&n_rcu_torture_free));
+	cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
-		       n_rcu_torture_boost_rterror,
+		       n_rcu_torture_boost_rterror);
+	cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
-		       n_rcu_torture_timers,
+		       n_rcu_torture_timers);
+	cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ",
 		       n_online_successes,
 		       n_online_attempts,
 		       n_offline_successes,
-		       n_offline_attempts,
+		       n_offline_attempts);
+	cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
 		       n_barrier_successes,
 		       n_barrier_attempts,
 		       n_rcu_torture_barrier_error);
@@ -1445,8 +1461,7 @@ rcu_torture_shutdown(void *arg)
 		delta = shutdown_time - jiffies_snap;
 		if (verbose)
 			printk(KERN_ALERT "%s" TORTURE_FLAG
-			       "rcu_torture_shutdown task: %lu "
-			       "jiffies remaining\n",
+			       "rcu_torture_shutdown task: %lu jiffies remaining\n",
 			       torture_type, delta);
 		schedule_timeout_interruptible(delta);
 		jiffies_snap = ACCESS_ONCE(jiffies);
@@ -1498,8 +1513,7 @@ rcu_torture_onoff(void *arg)
 			if (cpu_down(cpu) == 0) {
 				if (verbose)
 					printk(KERN_ALERT "%s" TORTURE_FLAG
-					       "rcu_torture_onoff task: "
-					       "offlined %d\n",
+					       "rcu_torture_onoff task: offlined %d\n",
 					       torture_type, cpu);
 				n_offline_successes++;
 			}
@@ -1512,8 +1526,7 @@ rcu_torture_onoff(void *arg)
 			if (cpu_up(cpu) == 0) {
 				if (verbose)
 					printk(KERN_ALERT "%s" TORTURE_FLAG
-					       "rcu_torture_onoff task: "
-					       "onlined %d\n",
+					       "rcu_torture_onoff task: onlined %d\n",
 					       torture_type, cpu);
 				n_online_successes++;
 			}
@@ -1631,6 +1644,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
+	bool lastphase = 0;
 	struct rcu_head rcu;
 
 	init_rcu_head_on_stack(&rcu);
@@ -1638,9 +1652,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 	set_user_nice(current, 19);
 	do {
 		wait_event(barrier_cbs_wq[myid],
-			   atomic_read(&barrier_cbs_count) == n_barrier_cbs ||
+			   barrier_phase != lastphase ||
 			   kthread_should_stop() ||
 			   fullstop != FULLSTOP_DONTSTOP);
+		lastphase = barrier_phase;
+		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
 		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
@@ -1665,7 +1681,8 @@ static int rcu_torture_barrier(void *arg)
 	do {
 		atomic_set(&barrier_cbs_invoked, 0);
 		atomic_set(&barrier_cbs_count, n_barrier_cbs);
-		/* wake_up() path contains the required barriers. */
+		smp_mb(); /* Ensure barrier_phase after prior assignments. */
+		barrier_phase = !barrier_phase;
 		for (i = 0; i < n_barrier_cbs; i++)
 			wake_up(&barrier_cbs_wq[i]);
 		wait_event(barrier_wq,
@@ -1684,7 +1701,7 @@ static int rcu_torture_barrier(void *arg)
 		schedule_timeout_interruptible(HZ / 10);
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
-	rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
+	rcutorture_shutdown_absorb("rcu_torture_barrier");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(1);
 	return 0;
@@ -1908,8 +1925,8 @@ rcu_torture_init(void)
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
 		  &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
-		  &srcu_ops, &srcu_sync_ops, &srcu_raw_ops,
-		  &srcu_raw_sync_ops, &srcu_expedited_ops,
+		  &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops,
+		  &srcu_raw_ops, &srcu_raw_sync_ops,
 		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
 
 	mutex_lock(&fullstop_mutex);
@@ -1931,8 +1948,7 @@ rcu_torture_init(void)
 		return -EINVAL;
 	}
 	if (cur_ops->fqs == NULL && fqs_duration != 0) {
-		printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero "
-				  "fqs_duration, fqs disabled.\n");
+		printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
 		fqs_duration = 0;
 	}
 	if (cur_o