diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index fa57139..f773a26 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -12,6 +12,8 @@
 	- RCU Lockdep splats explained.
 NMI-RCU.txt
 	- Using RCU to Protect Dynamic NMI Handlers
+rcu_dereference.txt
+	- Proper care and feeding of return values from rcu_dereference()
 rcubarrier.txt
 	- RCU and Unloadable Modules
 rculist_nulls.txt
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 9d10d1d..8779471 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -114,12 +114,16 @@
 			http://www.openvms.compaq.com/wizard/wiz_2637.html
 
 		The rcu_dereference() primitive is also an excellent
-		documentation aid, letting the person reading the code
-		know exactly which pointers are protected by RCU.
+		documentation aid, letting the person reading the
+		code know exactly which pointers are protected by RCU.
 		Please note that compilers can also reorder code, and
 		they are becoming increasingly aggressive about doing
-		just that.  The rcu_dereference() primitive therefore
-		also prevents destructive compiler optimizations.
+		just that.  The rcu_dereference() primitive therefore also
+		prevents destructive compiler optimizations.  However,
+		with a bit of devious creativity, it is possible to
+		mishandle the return value from rcu_dereference().
+		Please see rcu_dereference.txt in this directory for
+		more information.
 
 		The rcu_dereference() primitive is used by the
 		various "_rcu()" list-traversal primitives, such
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
new file mode 100644
index 0000000..ceb05da
--- /dev/null
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -0,0 +1,371 @@
+PROPER CARE AND FEEDING OF RETURN VALUES FROM rcu_dereference()
+
+Most of the time, you can use values from rcu_dereference() or one of
+the similar primitives without worries.  Dereferencing (prefix "*"),
+field selection ("->"), assignment ("="), address-of ("&"), addition and
+subtraction of constants, and casts all work quite naturally and safely.
+
+It is nevertheless possible to get into trouble with other operations.
+Follow these rules to keep your RCU code working properly:
+
+o	You must use one of the rcu_dereference() family of primitives
+	to load an RCU-protected pointer, otherwise CONFIG_PROVE_RCU
+	will complain.  Worse yet, your code can see random memory-corruption
+	bugs due to games that compilers and DEC Alpha can play.
+	Without one of the rcu_dereference() primitives, compilers
+	can reload the value, and won't your code have fun with two
+	different values for a single pointer!  Without rcu_dereference(),
+	DEC Alpha can load a pointer, dereference that pointer, and
+	return data preceding initialization that preceded the store of
+	the pointer.
+
+	In addition, the volatile cast in rcu_dereference() prevents the
+	compiler from deducing the resulting pointer value.  Please see
+	the section entitled "EXAMPLE WHERE THE COMPILER KNOWS TOO MUCH"
+	for an example where the compiler can in fact deduce the exact
+	value of the pointer, and thus cause misordering.
+
+o	Do not use single-element RCU-protected arrays.  The compiler
+	is within its right to assume that the value of an index into
+	such an array must necessarily evaluate to zero.  The compiler
+	could then substitute the constant zero for the computation, so
+	that the array index no longer depended on the value returned
+	by rcu_dereference().  If the array index no longer depends
+	on rcu_dereference(), then both the compiler and the CPU
+	are within their rights to order the array access before the
+	rcu_dereference(), which can cause the array access to return
+	garbage.
+
+o	Avoid cancellation when using the "+" and "-" infix arithmetic
+	operators.  For example, for a given variable "x", avoid
+	"(x-x)".  There are similar arithmetic pitfalls from other
+	arithmetic operatiors, 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.
+
+	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
+	interact directly with the hardware to flush instruction caches.
+	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 a[2];
+		int index;
+		int force_zero_index = 1;
+
+		...
+
+		r1 = rcu_dereference(i1)
+		r2 = a[r1 && force_zero_index];  /* 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:
+
+		int a[2];
+		int index;
+		int flip_index = 0;
+
+		...
+
+		r1 = rcu_dereference(i1)
+		r2 = a[r1 != flip_index];  /* BUGGY!!! */
+
+	As before, the reason this is buggy is that relational operators
+	are often compiled using branches.  And as before, although
+	weak-memory machines such as ARM or PowerPC do order stores
+	after such branches, but can speculate loads, which can again
+	result in misordering bugs.
+
+o	Be very careful about comparing pointers obtained from
+	rcu_dereference() against non-NULL values.  As Linus Torvalds
+	explained, if the two pointers are equal, the compiler could
+	substitute the pointer you are comparing against for the pointer
+	obtained from rcu_dereference().  For example:
+
+		p = rcu_dereference(gp);
+		if (p == &default_struct)
+			do_default(p->a);
+
+	Because the compiler now knows that the value of "p" is exactly
+	the address of the variable "default_struct", it is free to
+	transform this code into the following:
+
+		p = rcu_dereference(gp);
+		if (p == &default_struct)
+			do_default(default_struct.a);
+
+	On ARM and Power hardware, the load from "default_struct.a"
+	can now be speculated, such that it might happen before the
+	rcu_dereference().  This could result in bugs due to misordering.
+
+	However, comparisons are OK in the following cases:
+
+	o	The comparison was against the NULL pointer.  If the
+		compiler knows that the pointer is NULL, you had better
+		not be dereferencing it anyway.  If the comparison is
+		non-equal, the compiler is none the wiser.  Therefore,
+		it is safe to compare pointers from rcu_dereference()
+		against NULL pointers.
+
+	o	The pointer is never dereferenced after being compared.
+		Since there are no subsequent dereferences, the compiler
+		cannot use anything it learned from the comparison
+		to reorder the non-existent subsequent dereferences.
+		This sort of comparison occurs frequently when scanning
+		RCU-protected circular linked lists.
+
+	o	The comparison is against a pointer that references memory
+		that was initialized "a long time ago."  The reason
+		this is safe is that even if misordering occurs, the
+		misordering will not affect the accesses that follow
+		the comparison.  So exactly how long ago is "a long
+		time ago"?  Here are some possibilities:
+
+		o	Compile time.
+
+		o	Boot time.
+
+		o	Module-init time for module code.
+
+		o	Prior to kthread creation for kthread code.
+
+		o	During some prior acquisition of the lock that
+			we now hold.
+
+		o	Before mod_timer() time for a timer handler.
+
+		There are many other possibilities involving the Linux
+		kernel's wide array of primitives that cause code to
+		be invoked at a later time.
+
+	o	The pointer being compared against also came from
+		rcu_dereference().  In this case, both pointers depend
+		on one rcu_dereference() or another, so you get proper
+		ordering either way.
+
+		That said, this situation can make certain RCU usage
+		bugs more likely to happen.  Which can be a good thing,
+		at least if they happen during testing.  An example
+		of such an RCU usage bug is shown in the section titled
+		"EXAMPLE OF AMPLIFIED RCU-USAGE BUG".
+
+	o	All of the accesses following the comparison are stores,
+		so that a control dependency preserves the needed ordering.
+		That said, it is easy to get control dependencies wrong.
+		Please see the "CONTROL DEPENDENCIES" section of
+		Documentation/memory-barriers.txt for more details.
+
+	o	The pointers are not equal -and- the compiler does
+		not have enough information to deduce the value of the
+		pointer.  Note that the volatile cast in rcu_dereference()
+		will normally prevent the compiler from knowing too much.
+
+o	Disable any value-speculation optimizations that your compiler
+	might provide, especially if you are making use of feedback-based
+	optimizations that take data collected from prior runs.  Such
+	value-speculation optimizations reorder operations by design.
+
+	There is one exception to this rule:  Value-speculation
+	optimizations that leverage the branch-prediction hardware are
+	safe on strongly ordered systems (such as x86), but not on weakly
+	ordered systems (such as ARM or Power).  Choose your compiler
+	command-line options wisely!
+
+
+EXAMPLE OF AMPLIFIED RCU-USAGE BUG
+
+Because updaters can run concurrently with RCU readers, RCU readers can
+see stale and/or inconsistent values.  If RCU readers need fresh or
+consistent values, which they sometimes do, they need to take proper
+precautions.  To see this, consider the following code fragment:
+
+	struct foo {
+		int a;
+		int b;
+		int c;
+	};
+	struct foo *gp1;
+	struct foo *gp2;
+
+	void updater(void)
+	{
+		struct foo *p;
+
+		p = kmalloc(...);
+		if (p == NULL)
+			deal_with_it();
+		p->a = 42;  /* Each field in its own cache line. */
+		p->b = 43;
+		p->c = 44;
+		rcu_assign_pointer(gp1, p);
+		p->b = 143;
+		p->c = 144;
+		rcu_assign_pointer(gp2, p);
+	}
+
+	void reader(void)
+	{
+		struct foo *p;
+		struct foo *q;
+		int r1, r2;
+
+		p = rcu_dereference(gp2);
+		if (p == NULL)
+			return;
+		r1 = p->b;  /* Guaranteed to get 143. */
+		q = rcu_dereference(gp1);  /* Guaranteed non-NULL. */
+		if (p == q) {
+			/* The compiler decides that q->c is same as p->c. */
+			r2 = p->c; /* Could get 44 on weakly order system. */
+		}
+		do_something_with(r1, r2);
+	}
+
+You might be surprised that the outcome (r1 == 143 && r2 == 44) is possible,
+but you should not be.  After all, the updater might have been invoked
+a second time between the time reader() loaded into "r1" and the time
+that it loaded into "r2".  The fact that this same result can occur due
+to some reordering from the compiler and CPUs is beside the point.
+
+But suppose that the reader needs a consistent view?
+
+Then one approach is to use locking, for example, as follows:
+
+	struct foo {
+		int a;
+		int b;
+		int c;
+		spinlock_t lock;
+	};
+	struct foo *gp1;
+	struct foo *gp2;
+
+	void updater(void)
+	{
+		struct foo *p;
+
+		p = kmalloc(...);
+		if (p == NULL)
+			deal_with_it();
+		spin_lock(&p->lock);
+		p->a = 42;  /* Each field in its own cache line. */
+		p->b = 43;
+		p->c = 44;
+		spin_unlock(&p->lock);
+		rcu_assign_pointer(gp1, p);
+		spin_lock(&p->lock);
+		p->b = 143;
+		p->c = 144;
+		spin_unlock(&p->lock);
+		rcu_assign_pointer(gp2, p);
+	}
+
+	void reader(void)
+	{
+		struct foo *p;
+		struct foo *q;
+		int r1, r2;
+
+		p = rcu_dereference(gp2);
+		if (p == NULL)
+			return;
+		spin_lock(&p->lock);
+		r1 = p->b;  /* Guaranteed to get 143. */
+		q = rcu_dereference(gp1);  /* Guaranteed non-NULL. */
+		if (p == q) {
+			/* The compiler decides that q->c is same as p->c. */
+			r2 = p->c; /* Locking guarantees r2 == 144. */
+		}
+		spin_unlock(&p->lock);
+		do_something_with(r1, r2);
+	}
+
+As always, use the right tool for the job!
+
+
+EXAMPLE WHERE THE COMPILER KNOWS TOO MUCH
+
+If a pointer obtained from rcu_dereference() compares not-equal to some
+other pointer, the compiler normally has no clue what the value of the
+first pointer might be.  This lack of knowledge prevents the compiler
+from carrying out optimizations that otherwise might destroy the ordering
+guarantees that RCU depends on.  And the volatile cast in rcu_dereference()
+should prevent the compiler from guessing the value.
+
+But without rcu_dereference(), the compiler knows more than you might
+expect.  Consider the following code fragment:
+
+	struct foo {
+		int a;
+		int b;
+	};
+	static struct foo variable1;
+	static struct foo variable2;
+	static struct foo *gp = &variable1;
+
+	void updater(void)
+	{
+		initialize_foo(&variable2);
+		rcu_assign_pointer(gp, &variable2);
+		/*
+		 * The above is the only store to gp in this translation unit,
+		 * and the address of gp is not exported in any way.
+		 */
+	}
+
+	int reader(void)
+	{
+		struct foo *p;
+
+		p = gp;
+		barrier();
+		if (p == &variable1)
+			return p->a; /* Must be variable1.a. */
+		else
+			return p->b; /* Must be variable2.b. */
+	}
+
+Because the compiler can see all stores to "gp", it knows that the only
+possible values of "gp" are "variable1" on the one hand and "variable2"
+on the other.  The comparison in reader() therefore tells the compiler
+the exact value of "p" even in the not-equals case.  This allows the
+compiler to make the return values independent of the load from "gp",
+in turn destroying the ordering between this load and the loads of the
+return values.  This can result in "p->b" returning pre-initialization
+garbage values.
+
+In short, rcu_dereference() is -not- optional when you are going to
+dereference the resulting pointer.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 6f3a005..68fe3ad 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -24,7 +24,7 @@
 	timing of the next warning for the current stall.
 
 	Stall-warning messages may be enabled and disabled completely via
-	/sys/module/rcutree/parameters/rcu_cpu_stall_suppress.
+	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
 
 CONFIG_RCU_CPU_STALL_VERBOSE
 
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 0f0fb7c..49b8551 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -326,11 +326,11 @@
 a.	synchronize_rcu()	rcu_read_lock() / rcu_read_unlock()
 	call_rcu()		rcu_dereference()
 
-b.	call_rcu_bh()		rcu_read_lock_bh() / rcu_read_unlock_bh()
-				rcu_dereference_bh()
+b.	synchronize_rcu_bh()	rcu_read_lock_bh() / rcu_read_unlock_bh()
+	call_rcu_bh()		rcu_dereference_bh()
 
 c.	synchronize_sched()	rcu_read_lock_sched() / rcu_read_unlock_sched()
-				preempt_disable() / preempt_enable()
+	call_rcu_sched()	preempt_disable() / preempt_enable()
 				local_irq_save() / local_irq_restore()
 				hardirq enter / hardirq exit
 				NMI enter / NMI exit
@@ -794,10 +794,22 @@
 
 RCU list traversal:
 
+	list_entry_rcu
+	list_first_entry_rcu
+	list_next_rcu
 	list_for_each_entry_rcu
-	hlist_for_each_entry_rcu
-	hlist_nulls_for_each_entry_rcu
 	list_for_each_entry_continue_rcu
+	hlist_first_rcu
+	hlist_next_rcu
+	hlist_pprev_rcu
+	hlist_for_each_entry_rcu
+	hlist_for_each_entry_rcu_bh
+	hlist_for_each_entry_continue_rcu
+	hlist_for_each_entry_continue_rcu_bh
+	hlist_nulls_first_rcu
+	hlist_nulls_for_each_entry_rcu
+	hlist_bl_first_rcu
+	hlist_bl_for_each_entry_rcu
 
 RCU pointer/list update:
 
@@ -806,28 +818,38 @@
 	list_add_tail_rcu
 	list_del_rcu
 	list_replace_rcu
-	hlist_del_rcu
 	hlist_add_after_rcu
 	hlist_add_before_rcu
 	hlist_add_head_rcu
+	hlist_del_rcu
+	hlist_del_init_rcu
 	hlist_replace_rcu
 	list_splice_init_rcu()
+	hlist_nulls_del_init_rcu
+	hlist_nulls_del_rcu
+	hlist_nulls_add_head_rcu
+	hlist_bl_add_head_rcu
+	hlist_bl_del_init_rcu
+	hlist_bl_del_rcu
+	hlist_bl_set_first_rcu
 
 RCU:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock		synchronize_net		rcu_barrier
 	rcu_read_unlock		synchronize_rcu
 	rcu_dereference		synchronize_rcu_expedited
-				call_rcu
-				kfree_rcu
-
+	rcu_read_lock_held	call_rcu
+	rcu_dereference_check	kfree_rcu
+	rcu_dereference_protected
 
 bh:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
 	rcu_read_unlock_bh	synchronize_rcu_bh
 	rcu_dereference_bh	synchronize_rcu_bh_expedited
-
+	rcu_dereference_bh_check
+	rcu_dereference_bh_protected
+	rcu_read_lock_bh_held
 
 sched:	Critical sections	Grace period		Barrier
 
@@ -835,7 +857,12 @@
 	rcu_read_unlock_sched	call_rcu_sched
 	[preempt_disable]	synchronize_sched_expedited
 	[and friends]
+	rcu_read_lock_sched_notrace
+	rcu_read_unlock_sched_notrace
 	rcu_dereference_sched
+	rcu_dereference_sched_check
+	rcu_dereference_sched_protected
+	rcu_read_lock_sched_held
 
 
 SRCU:	Critical sections	Grace period		Barrier
@@ -843,6 +870,8 @@
 	srcu_read_lock		synchronize_srcu	srcu_barrier
 	srcu_read_unlock	call_srcu
 	srcu_dereference	synchronize_srcu_expedited
+	srcu_dereference_check
+	srcu_read_lock_held
 
 SRCU:	Initialization/cleanup
 	init_srcu_struct
@@ -850,9 +879,13 @@
 
 All:  lockdep-checked RCU-protected pointer access
 
-	rcu_dereference_check
-	rcu_dereference_protected
+	rcu_access_index
 	rcu_access_pointer
+	rcu_dereference_index_check
+	rcu_dereference_raw
+	rcu_lockdep_assert
+	rcu_sleep_check
+	RCU_NONIDLE
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index e7a0b95e..495c654 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -639,7 +639,7 @@
 #  define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
 # define raw_cpu_add_return(pcp, val)	\
-	__pcpu_size_call_return2(raw_add_return_, pcp, val)
+	__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
 #endif
 
 #define raw_cpu_sub_return(pcp, val)	raw_cpu_add_return(pcp, -(typeof(pcp))(val))
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3c5ef02..a6f2664 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,6 +44,7 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/percpu.h>
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -51,7 +52,17 @@
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+enum rcutorture_type {
+	RTORT_BUSTED,
+	RTORT_RCU,
+	RTORT_RCU_BH,
+	RTORT_RCU_SCHED,
+	RTORT_SRCU
+};
+
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
+			    unsigned long *gpnum, unsigned long *completed);
 void rcutorture_record_test_transition(void);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -60,6 +71,15 @@
 			       unsigned long c_old,
 			       unsigned long c);
 #else
+static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
+					  int *flags,
+					  unsigned long *gpnum,
+					  unsigned long *completed)
+{
+	*flags = 0;
+	*gpnum = 0;
+	*completed = 0;
+}
 static inline void rcutorture_record_test_transition(void)
 {
 }
@@ -268,6 +288,41 @@
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
+ * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
+ */
+
+#define RCU_COND_RESCHED_LIM 256	/* ms vs. 100s of ms. */
+DECLARE_PER_CPU(int, rcu_cond_resched_count);
+void rcu_resched(void);
+
+/*
+ * Is it time to report RCU quiescent states?
+ *
+ * Note unsynchronized access to rcu_cond_resched_count.  Yes, we might
+ * increment some random CPU's count, and possibly also load the result from
+ * yet another CPU's count.  We might even clobber some other CPU's attempt
+ * to zero its counter.  This is all OK because the goal is not precision,
+ * but rather reasonable amortization of rcu_note_context_switch() overhead
+ * and extremely high probability of avoiding RCU CPU stall warnings.
+ * Note that this function has to be preempted in just the wrong place,
+ * many thousands of times in a row, for anything bad to happen.
+ */
+static inline bool rcu_should_resched(void)
+{
+	return raw_cpu_inc_return(rcu_cond_resched_count) >=
+	       RCU_COND_RESCHED_LIM;
+}
+
+/*
+ * Report quiscent states to RCU if it is time to do so.
+ */
+static inline void rcu_cond_resched(void)
+{
+	if (unlikely(rcu_should_resched()))
+		rcu_resched();
+}
+
+/*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
  */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 425c659..d40a6a4 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -119,6 +119,10 @@
 {
 }
 
+static inline void show_rcu_gp_kthreads(void)
+{
+}
+
 static inline void rcu_cpu_stall_reset(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index a59ca05..3e2f5d4 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -84,6 +84,7 @@
 long rcu_batches_completed(void);
 long rcu_batches_completed_bh(void);
 long rcu_batches_completed_sched(void);
+void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
diff --git a/include/linux/torture.h b/include/linux/torture.h
index b2e2b46..5ca58fc 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -49,12 +49,6 @@
 #define VERBOSE_TOROUT_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0)
 
-/* Definitions for a non-string torture-test module parameter. */
-#define torture_parm(type, name, init, msg) \
-	static type name = init; \
-	module_param(name, type, 0444); \
-	MODULE_PARM_DESC(name, msg);
-
 /* Definitions for online/offline exerciser. */
 int torture_onoff_init(long ooholdoff, long oointerval);
 char *torture_onoff_stats(char *page);
@@ -81,7 +75,7 @@
 int torture_stutter_init(int s);
 
 /* Initialization and cleanup. */
-void torture_init_begin(char *ttype, bool v, int *runnable);
+bool torture_init_begin(char *ttype, bool v, int *runnable);
 void torture_init_end(void);
 bool torture_cleanup(void);
 bool torture_must_stop(void);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f26b1a1..dbafeac 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -82,14 +82,14 @@
 };
 static struct lock_writer_stress_stats *lwsa;
 
-#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE)
+#if defined(MODULE)
 #define LOCKTORTURE_RUNNABLE_INIT 1
 #else
 #define LOCKTORTURE_RUNNABLE_INIT 0
 #endif
 int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
 module_param(locktorture_runnable, int, 0444);
-MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot");
+MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init");
 
 /* Forward reference. */
 static void lock_torture_cleanup(void);
@@ -219,7 +219,8 @@
 	set_user_nice(current, 19);
 
 	do {
-		schedule_timeout_uninterruptible(1);
+		if ((torture_random(&rand) & 0xfffff) == 0)
+			schedule_timeout_uninterruptible(1);
 		cur_ops->writelock();
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lwsp->n_write_lock_fail++;
@@ -354,7 +355,8 @@
 		&lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
 	};
 
-	torture_init_begin(torture_type, verbose, &locktorture_runnable);
+	if (!torture_init_begin(torture_type, verbose, &locktorture_runnable))
+		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index bd30bc6..1d85591 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -58,9 +58,11 @@
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
 torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(bool, gp_normal, false,
 	     "Use normal (non-expedited) GP wait primitives");
+torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives");
 torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
 torture_param(int, n_barrier_cbs, 0,
 	     "# of callbacks/kthreads for barrier testing");
@@ -138,6 +140,18 @@
 static long n_barrier_successes;
 static struct list_head rcu_torture_removed;
 
+static int rcu_torture_writer_state;
+#define RTWS_FIXED_DELAY	0
+#define RTWS_DELAY		1
+#define RTWS_REPLACE		2
+#define RTWS_DEF_FREE		3
+#define RTWS_EXP_SYNC		4
+#define RTWS_COND_GET		5
+#define RTWS_COND_SYNC		6
+#define RTWS_SYNC		7
+#define RTWS_STUTTER		8
+#define RTWS_STOPPING		9
+
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
 #else
@@ -214,6 +228,7 @@
  */
 
 struct rcu_torture_ops {
+	int ttype;
 	void (*init)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
@@ -222,6 +237,8 @@
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
+	unsigned long (*get_state)(void);
+	void (*cond_sync)(unsigned long oldstate);
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
@@ -273,10 +290,48 @@
 	return rcu_batches_completed();
 }
 
+/*
+ * Update callback in the pipe.  This should be invoked after a grace period.
+ */
+static bool
+rcu_torture_pipe_update_one(struct rcu_torture *rp)
+{
+	int i;
+
+	i = rp->rtort_pipe_count;
+	if (i > RCU_TORTURE_PIPE_LEN)
+		i = RCU_TORTURE_PIPE_LEN;
+	atomic_inc(&rcu_torture_wcount[i]);
+	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+		rp->rtort_mbtest = 0;
+		return true;
+	}
+	return false;
+}
+
+/*
+ * Update all callbacks in the pipe.  Suitable for synchronous grace-period
+ * primitives.
+ */
+static void
+rcu_torture_pipe_update(struct rcu_torture *old_rp)
+{
+	struct rcu_torture *rp;
+	struct rcu_torture *rp1;
+
+	if (old_rp)
+		list_add(&old_rp->rtort_free, &rcu_torture_removed);
+	list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) {
+		if (rcu_torture_pipe_update_one(rp)) {
+			list_del(&rp->rtort_free);
+			rcu_torture_free(rp);
+		}
+	}
+}
+
 static void
 rcu_torture_cb(struct rcu_head *p)
 {
-	int i;
 	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
 
 	if (torture_must_stop_irq()) {
@@ -284,16 +339,10 @@
 		/* The next initialization will pick up the pieces. */
 		return;
 	}
-	i = rp->rtort_pipe_count;
-	if (i > RCU_TORTURE_PIPE_LEN)
-		i = RCU_TORTURE_PIPE_LEN;
-	atomic_inc(&rcu_torture_wcount[i]);
-	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
-		rp->rtort_mbtest = 0;
+	if (rcu_torture_pipe_update_one(rp))
 		rcu_torture_free(rp);
-	} else {
+	else
 		cur_ops->deferred_free(rp);
-	}
 }
 
 static int rcu_no_completed(void)
@@ -312,6 +361,7 @@
 }
 
 static struct rcu_torture_ops rcu_ops = {
+	.ttype		= RTORT_RCU,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
@@ -320,6 +370,8 @@
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
+	.get_state	= get_state_synchronize_rcu,
+	.cond_sync	= cond_synchronize_rcu,
 	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
@@ -355,6 +407,7 @@
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
+	.ttype		= RTORT_RCU_BH,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -397,6 +450,7 @@
 }
 
 static struct rcu_torture_ops rcu_busted_ops = {
+	.ttype		= RTORT_BUSTED,
 	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -473,15 +527,16 @@
 
 static void srcu_torture_stats(char *page)
 {
+	long c0, c1;
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
 	page += sprintf(page, "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		page += sprintf(page, " %d(%lu,%lu)", cpu,
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
-			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
+		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
+		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+		page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1);
 	}
 	sprintf(page, "\n");
 }
@@ -492,6 +547,7 @@
 }
 
 static struct rcu_torture_ops srcu_ops = {
+	.ttype		= RTORT_SRCU,
 	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
@@ -527,6 +583,7 @@
 }
 
 static struct rcu_torture_ops sched_ops = {
+	.ttype		= RTORT_RCU_SCHED,
 	.init		= rcu_sync_torture_init,
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
@@ -688,23 +745,59 @@
 static int
 rcu_torture_writer(void *arg)
 {
-	bool exp;
+	unsigned long gp_snap;
+	bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
+	bool gp_sync1 = gp_sync;
 	int i;
 	struct rcu_torture *rp;
-	struct rcu_torture *rp1;
 	struct rcu_torture *old_rp;
 	static DEFINE_TORTURE_RANDOM(rand);
+	int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC,
+			   RTWS_COND_GET, RTWS_SYNC };
+	int nsynctypes = 0;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
-	set_user_nice(current, MAX_NICE);
+
+	/* Initialize synctype[] array.  If none set, take default. */
+	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync)
+		gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true;
+	if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync)
+		synctype[nsynctypes++] = RTWS_COND_GET;
+	else if (gp_cond && (!cur_ops->get_state || !cur_ops->cond_sync))
+		pr_alert("rcu_torture_writer: gp_cond without primitives.\n");
+	if (gp_exp1 && cur_ops->exp_sync)
+		synctype[nsynctypes++] = RTWS_EXP_SYNC;
+	else if (gp_exp && !cur_ops->exp_sync)
+		pr_alert("rcu_torture_writer: gp_exp without primitives.\n");
+	if (gp_normal1 && cur_ops->deferred_free)
+		synctype[nsynctypes++] = RTWS_DEF_FREE;
+	else if (gp_normal && !cur_ops->deferred_free)
+		pr_alert("rcu_torture_writer: gp_normal without primitives.\n");
+	if (gp_sync1 && cur_ops->sync)
+		synctype[nsynctypes++] = RTWS_SYNC;
+	else if (gp_sync && !cur_ops->sync)
+		pr_alert("rcu_torture_writer: gp_sync without primitives.\n");
+	if (WARN_ONCE(nsynctypes == 0,
+		      "rcu_torture_writer: No update-side primitives.\n")) {
+		/*
+		 * No updates primitives, so don't try updating.
+		 * The resulting test won't be testing much, hence the
+		 * above WARN_ONCE().
+		 */
+		rcu_torture_writer_state = RTWS_STOPPING;
+		torture_kthread_stopping("rcu_torture_writer");
+	}
 
 	do {
+		rcu_torture_writer_state = RTWS_FIXED_DELAY;
 		schedule_timeout_uninterruptible(1);
 		rp = rcu_torture_alloc();
 		if (rp == NULL)
 			continue;
 		rp->rtort_pipe_count = 0;
+		rcu_torture_writer_state = RTWS_DELAY;
 		udelay(torture_random(&rand) & 0x3ff);
+		rcu_torture_writer_state = RTWS_REPLACE;
 		old_rp = rcu_dereference_check(rcu_torture_current,
 					       current == writer_task);
 		rp->rtort_mbtest = 1;
@@ -716,35 +809,42 @@
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			if (gp_normal == gp_exp)
-				exp = !!(torture_random(&rand) & 0x80);
-			else
-				exp = gp_exp;
-			if (!exp) {
+			switch (synctype[torture_random(&rand) % nsynctypes]) {
+			case RTWS_DEF_FREE:
+				rcu_torture_writer_state = RTWS_DEF_FREE;
 				cur_ops->deferred_free(old_rp);
-			} else {
+				break;
+			case RTWS_EXP_SYNC:
+				rcu_torture_writer_state = RTWS_EXP_SYNC;
 				cur_ops->exp_sync();
-				list_add(&old_rp->rtort_free,
-					 &rcu_torture_removed);
-				list_for_each_entry_safe(rp, rp1,
-							 &rcu_torture_removed,
-							 rtort_free) {
-					i = rp->rtort_pipe_count;
-					if (i > RCU_TORTURE_PIPE_LEN)
-						i = RCU_TORTURE_PIPE_LEN;
-					atomic_inc(&rcu_torture_wcount[i]);
-					if (++rp->rtort_pipe_count >=
-					    RCU_TORTURE_PIPE_LEN) {
-						rp->rtort_mbtest = 0;
-						list_del(&rp->rtort_free);
-						rcu_torture_free(rp);
-					}
-				 }
+				rcu_torture_pipe_update(old_rp);
+				break;
+			case RTWS_COND_GET:
+				rcu_torture_writer_state = RTWS_COND_GET;
+				gp_snap = cur_ops->get_state();
+				i = torture_random(&rand) % 16;
+				if (i != 0)
+					schedule_timeout_interruptible(i);
+				udelay(torture_random(&rand) % 1000);
+				rcu_torture_writer_state = RTWS_COND_SYNC;
+				cur_ops->cond_sync(gp_snap);
+				rcu_torture_pipe_update(old_rp);
+				break;
+			case RTWS_SYNC:
+				rcu_torture_writer_state = RTWS_SYNC;
+				cur_ops->sync();
+				rcu_torture_pipe_update(old_rp);
+				break;
+			default:
+				WARN_ON_ONCE(1);
+				break;
 			}
 		}
 		rcutorture_record_progress(++rcu_torture_current_version);
+		rcu_torture_writer_state = RTWS_STUTTER;
 		stutter_wait("rcu_torture_writer");
 	} while (!torture_must_stop());
+	rcu_torture_writer_state = RTWS_STOPPING;
 	torture_kthread_stopping("rcu_torture_writer");
 	return 0;
 }
@@ -784,7 +884,7 @@
 	return 0;
 }
 
-void rcutorture_trace_dump(void)
+static void rcutorture_trace_dump(void)
 {
 	static atomic_t beenhere = ATOMIC_INIT(0);
 
@@ -918,11 +1018,13 @@
 		__this_cpu_inc(rcu_torture_batch[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
-		schedule();
+		cond_resched();
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
-	if (irqreader && cur_ops->irq_capable)
+	if (irqreader && cur_ops->irq_capable) {
 		del_timer_sync(&t);
+		destroy_timer_on_stack(&t);
+	}
 	torture_kthread_stopping("rcu_torture_reader");
 	return 0;
 }
@@ -937,6 +1039,7 @@
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	static unsigned long rtcv_snap = ULONG_MAX;
 
 	for_each_possible_cpu(cpu) {
 		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
@@ -997,6 +1100,22 @@
 	page += sprintf(page, "\n");
 	if (cur_ops->stats)
 		cur_ops->stats(page);
+	if (rtcv_snap == rcu_torture_current_version &&
+	    rcu_torture_current != NULL) {
+		int __maybe_unused flags;
+		unsigned long __maybe_unused gpnum;
+		unsigned long __maybe_unused completed;
+
+		rcutorture_get_gp_data(cur_ops->ttype,
+				       &flags, &gpnum, &completed);
+		page += sprintf(page,
+				"??? Writer stall state %d g%lu c%lu f%#x\n",
+				rcu_torture_writer_state,
+				gpnum, completed, flags);
+		show_rcu_gp_kthreads();
+		rcutorture_trace_dump();
+	}
+	rtcv_snap = rcu_torture_current_version;
 }
 
 /*
@@ -1146,7 +1265,7 @@
 }
 
 /* Callback function for RCU barrier testing. */
-void rcu_torture_barrier_cbf(struct rcu_head *rcu)
+static void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 {
 	atomic_inc(&barrier_cbs_invoked);
 }
@@ -1416,7 +1535,8 @@
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
 	};
 
-	torture_init_begin(torture_type, verbose, &rcutorture_runnable);
+	if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
+		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -1441,10 +1561,13 @@
 	if (cur_ops->init)
 		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
 
-	if (nreaders >= 0)
+	if (nreaders >= 0) {
 		nrealreaders = nreaders;
-	else
-		nrealreaders = 2 * num_online_cpus();
+	} else {
+		nrealreaders = num_online_cpus() - 1;
+		if (nrealreaders <= 0)
+			nrealreaders = 1;
+	}
 	rcu_torture_print_module_parms(cur_ops, "Start of test");
 
 	/* Set up the freelist. */
@@ -1533,7 +1656,8 @@
 		fqs_duration = 0;
 	if (fqs_duration) {
 		/* Create the fqs thread */
-		torture_create_kthread(rcu_torture_fqs, NULL, fqs_task);
+		firsterr = torture_create_kthread(rcu_torture_fqs, NULL,
+						  fqs_task);
 		if (firsterr)
 			goto unwind;
 	}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d3e023e..9418bf0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -289,6 +289,21 @@
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
 /*
+ * Show the state of the grace-period kthreads.
+ */
+void show_rcu_gp_kthreads(void)
+{
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp) {
+		pr_info("%s: wait state: %d ->state: %#lx\n",
+			rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+		/* sched_show_task(rsp->gp_kthread); */
+	}
+}
+EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+
+/*
  * Record the number of times rcutorture tests have been initiated and
  * terminated.  This information allows the debugfs tracing stats to be
  * correlated to the rcutorture messages, even when the rcutorture module
@@ -303,6 +318,24 @@
 EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
 
 /*
+ * Send along grace-period-related data for rcutorture diagnostics.
+ */
+void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
+			    unsigned long *gpnum, unsigned long *completed)
+{
+	if (test_type == RTORT_SRCU || test_type == RTORT_BUSTED) {
+		*flags = 0;
+		*gpnum = 0;
+		*completed = 0;
+		return;
+	}
+	*flags = ACCESS_ONCE(rcu_state->gp_flags);
+	*gpnum = ACCESS_ONCE(rcu_state->gpnum);
+	*completed = ACCESS_ONCE(rcu_state->completed);
+}
+EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
+
+/*
  * Record the number of writer passes through the current rcutorture test.
  * This is also used to correlate debugfs tracing stats with the rcutorture
  * messages.
@@ -1652,6 +1685,7 @@
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
+			rsp->gp_state = RCU_GP_WAIT_GPS;
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
@@ -1679,6 +1713,7 @@
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
+			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
 					((gf = ACCESS_ONCE(rsp->gp_flags)) &
 					 RCU_GP_FLAG_FQS) ||
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index cdbb392..bf2c1e6 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -405,7 +405,8 @@
 	unsigned long completed;		/* # of last completed gp. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	wait_queue_head_t gp_wq;		/* Where GP task waits. */
-	int gp_flags;				/* Commands for GP task. */
+	short gp_flags;				/* Commands for GP task. */
+	short gp_state;				/* GP kthread sleep state. */
 
 	/* End of fields guarded by root rcu_node's lock. */
 
@@ -467,6 +468,11 @@
 #define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
 
+/* Values for rcu_state structure's gp_flags field. */
+#define RCU_GP_WAIT_INIT 0	/* Initial state. */
+#define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
+#define RCU_GP_WAIT_FQS  2	/* Wait for force-quiescent-state time. */
+
 extern struct list_head rcu_struct_flavors;
 
 /* Sequence through rcu_state structures for each RCU flavor. */
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c0a9b0..ed7a0d7 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -338,3 +338,21 @@
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
+/*
+ * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
+ */
+
+DEFINE_PER_CPU(int, rcu_cond_resched_count);
+
+/*
+ * Report a set of RCU quiescent states, for use by cond_resched()
+ * and friends.  Out of line due to being called infrequently.
+ */
+void rcu_resched(void)
+{
+	preempt_disable();
+	__this_cpu_write(rcu_cond_resched_count, 0);
+	rcu_note_context_switch(smp_processor_id());
+	preempt_enable();
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 268a45e..9f530c9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4051,6 +4051,7 @@
 
 int __sched _cond_resched(void)
 {
+	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4069,15 +4070,18 @@
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
+	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched) {
+	if (spin_needbreak(lock) || resched || need_rcu_resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
+		else if (unlikely(need_rcu_resched))
+			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4091,6 +4095,7 @@
 {
 	BUG_ON(!in_softirq());
 
+	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
diff --git a/kernel/torture.c b/kernel/torture.c
index acc9afc..db8de70 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -335,13 +335,8 @@
 	shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask);
 	if (shuffle_idle_cpu >= nr_cpu_ids)
 		shuffle_idle_cpu = -1;
-	if (shuffle_idle_cpu != -1) {
+	else
 		cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
-		if (cpumask_empty(shuffle_tmp_mask)) {
-			put_online_cpus();
-			return;
-		}
-	}
 
 	mutex_lock(&shuffle_task_mutex);
 	list_for_each_entry(stp, &shuffle_task_list, st_l)
@@ -533,7 +528,11 @@
 	while (ACCESS_ONCE(stutter_pause_test) ||
 	       (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
 		if (stutter_pause_test)
-			schedule_timeout_interruptible(1);
+			if (ACCESS_ONCE(stutter_pause_test) == 1)
+				schedule_timeout_interruptible(1);
+			else
+				while (ACCESS_ONCE(stutter_pause_test))
+					cond_resched();
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
 		torture_shutdown_absorb(title);
@@ -550,7 +549,11 @@
 	VERBOSE_TOROUT_STRING("torture_stutter task started");
 	do {
 		if (!torture_must_stop()) {
-			schedule_timeout_interruptible(stutter);
+			if (stutter > 1) {
+				schedule_timeout_interruptible(stutter - 1);
+				ACCESS_ONCE(stutter_pause_test) = 2;
+			}
+			schedule_timeout_interruptible(1);
 			ACCESS_ONCE(stutter_pause_test) = 1;
 		}
 		if (!torture_must_stop())
@@ -596,21 +599,27 @@
  * The runnable parameter points to a flag that controls whether or not
  * the test is currently runnable.  If there is no such flag, pass in NULL.
  */
-void __init torture_init_begin(char *ttype, bool v, int *runnable)
+bool torture_init_begin(char *ttype, bool v, int *runnable)
 {
 	mutex_lock(&fullstop_mutex);
+	if (torture_type != NULL) {
+		pr_alert("torture_init_begin: refusing %s init: %s running",
+			 ttype, torture_type);
+		mutex_unlock(&fullstop_mutex);
+		return false;
+	}
 	torture_type = ttype;
 	verbose = v;
 	torture_runnable = runnable;
 	fullstop = FULLSTOP_DONTSTOP;
-
+	return true;
 }
 EXPORT_SYMBOL_GPL(torture_init_begin);
 
 /*
  * Tell the torture module that initialization is complete.
  */
-void __init torture_init_end(void)
+void torture_init_end(void)
 {
 	mutex_unlock(&fullstop_mutex);
 	register_reboot_notifier(&torture_shutdown_nb);
@@ -642,6 +651,9 @@
 	torture_shuffle_cleanup();
 	torture_stutter_cleanup();
 	torture_onoff_cleanup();
+	mutex_lock(&fullstop_mutex);
+	torture_type = NULL;
+	mutex_unlock(&fullstop_mutex);
 	return false;
 }
 EXPORT_SYMBOL_GPL(torture_cleanup);
@@ -674,8 +686,11 @@
  */
 void torture_kthread_stopping(char *title)
 {
+	char buf[128];
+
+	snprintf(buf, sizeof(buf), "Stopping %s", title);
 	if (verbose)
-		VERBOSE_TOROUT_STRING(title);
+		VERBOSE_TOROUT_STRING(buf);
 	while (!kthread_should_stop()) {
 		torture_shutdown_absorb(title);
 		schedule_timeout_uninterruptible(1);
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index a1be6e6..9c3f3d3 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -62,7 +62,7 @@
 echo "cat - $c" >> $T/upd.sh
 make mrproper
 make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc defconfig > $builddir/Make.defconfig.out 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 9b17e81..efa9586 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -76,15 +76,36 @@
 	grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1"
 }
 
+# identify_boot_image qemu-cmd
+#
+# Returns the relative path to the kernel build image.  This will be
+# arch/<arch>/boot/bzImage unless overridden with the TORTURE_BOOT_IMAGE
+# environment variable.
+identify_boot_image () {
+	if test -n "$TORTURE_BOOT_IMAGE"
+	then
+		echo $TORTURE_BOOT_IMAGE
+	else
+		case "$1" in
+		qemu-system-x86_64|qemu-system-i386)
+			echo arch/x86/boot/bzImage
+			;;
+		qemu-system-ppc64)
+			echo arch/powerpc/boot/bzImage
+			;;
+		esac
+	fi
+}
+
 # identify_qemu builddir
 #
 # Returns our best guess as to which qemu command is appropriate for
-# the kernel at hand.  Override with the RCU_QEMU_CMD environment variable.
+# the kernel at hand.  Override with the TORTURE_QEMU_CMD environment variable.
 identify_qemu () {
 	local u="`file "$1"`"
-	if test -n "$RCU_QEMU_CMD"
+	if test -n "$TORTURE_QEMU_CMD"
 	then
-		echo $RCU_QEMU_CMD
+		echo $TORTURE_QEMU_CMD
 	elif echo $u | grep -q x86-64
 	then
 		echo qemu-system-x86_64
@@ -98,7 +119,7 @@
 		echo Cannot figure out what qemu command to use! 1>&2
 		echo file $1 output: $u
 		# Usually this will be one of /usr/bin/qemu-system-*
-		# Use RCU_QEMU_CMD environment variable or appropriate
+		# Use TORTURE_QEMU_CMD environment variable or appropriate
 		# argument to top-level script.
 		exit 1
 	fi
@@ -107,14 +128,14 @@
 # identify_qemu_append qemu-cmd
 #
 # Output arguments for the qemu "-append" string based on CPU type
-# and the RCU_QEMU_INTERACTIVE environment variable.
+# and the TORTURE_QEMU_INTERACTIVE environment variable.
 identify_qemu_append () {
 	case "$1" in
 	qemu-system-x86_64|qemu-system-i386)
 		echo noapic selinux=0 initcall_debug debug
 		;;
 	esac
-	if test -n "$RCU_QEMU_INTERACTIVE"
+	if test -n "$TORTURE_QEMU_INTERACTIVE"
 	then
 		echo root=/dev/sda
 	else
@@ -124,8 +145,8 @@
 
 # identify_qemu_args qemu-cmd serial-file
 #
-# Output arguments for qemu arguments based on the RCU_QEMU_MAC
-# and RCU_QEMU_INTERACTIVE environment variables.
+# Output arguments for qemu arguments based on the TORTURE_QEMU_MAC
+# and TORTURE_QEMU_INTERACTIVE environment variables.
 identify_qemu_args () {
 	case "$1" in
 	qemu-system-x86_64|qemu-system-i386)
@@ -133,17 +154,17 @@
 	qemu-system-ppc64)
 		echo -enable-kvm -M pseries -cpu POWER7 -nodefaults
 		echo -device spapr-vscsi
-		if test -n "$RCU_QEMU_INTERACTIVE" -a -n "$RCU_QEMU_MAC"
+		if test -n "$TORTURE_QEMU_INTERACTIVE" -a -n "$TORTURE_QEMU_MAC"
 		then
-			echo -device spapr-vlan,netdev=net0,mac=$RCU_QEMU_MAC
+			echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC
 			echo -netdev bridge,br=br0,id=net0
-		elif test -n "$RCU_QEMU_INTERACTIVE"
+		elif test -n "$TORTURE_QEMU_INTERACTIVE"
 		then
 			echo -net nic -net user
 		fi
 		;;
 	esac
-	if test -n "$RCU_QEMU_INTERACTIVE"
+	if test -n "$TORTURE_QEMU_INTERACTIVE"
 	then
 		echo -monitor stdio -serial pty -S
 	else
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 197901e..6d0b76d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -45,9 +45,9 @@
 trap 'rm -rf $T' 0
 mkdir $T
 
-cat ${config_template} | grep -v CONFIG_RCU_TORTURE_TEST > $T/config
+cat ${config_template} | grep -v 'CONFIG_[A-Z]*_TORTURE_TEST' > $T/config
 cat << ___EOF___ >> $T/config
-CONFIG_INITRAMFS_SOURCE="$RCU_INITRD"
+CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD"
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
@@ -60,7 +60,7 @@
 	exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $RCU_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
 retval=$?
 if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
 then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
index 829186e..7f1ff1a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -35,7 +35,7 @@
 ncs=`grep "Writes:  Total:" $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* Total: //' -e 's/ .*$//'`
 if test -z "$ncs"
 then
-	echo $configfile
+	echo "$configfile -------"
 else
 	title="$configfile ------- $ncs acquisitions/releases"
 	dur=`sed -e 's/^.* locktorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index d75b1dc5..307c4b9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -35,7 +35,7 @@
 ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
 if test -z "$ngps"
 then
-	echo $configfile
+	echo "$configfile -------"
 else
 	title="$configfile ------- $ngps grace periods"
 	dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index a44daaa..ee1f6ca 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -25,6 +25,7 @@
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
+. tools/testing/selftests/rcutorture/bin/functions.sh
 for rd in "$@"
 do
 	firsttime=1
@@ -39,13 +40,24 @@
 		fi
 		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
 		kvm-recheck-${TORTURE_SUITE}.sh $i
-		configcheck.sh $i/.config $i/ConfigFragment
-		parse-build.sh $i/Make.out $configfile
-		parse-rcutorture.sh $i/console.log $configfile
-		parse-console.sh $i/console.log $configfile
-		if test -r $i/Warnings
+		if test -f "$i/console.log"
 		then
-			cat $i/Warnings
+			configcheck.sh $i/.config $i/ConfigFragment
+			parse-build.sh $i/Make.out $configfile
+			parse-torture.sh $i/console.log $configfile
+			parse-console.sh $i/console.log $configfile
+			if test -r $i/Warnings
+			then
+				cat $i/Warnings
+			fi
+		else
+			if test -f "$i/qemu-cmd"
+			then
+				print_bug qemu failed
+			else
+				print_bug Build failed
+			fi
+			echo "   $i"
 		fi
 	done
 done
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 94b28bb..67e89f0 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -94,9 +94,11 @@
 # CONFIG_YENTA=n
 if kvm-build.sh $config_template $builddir $T
 then
+	QEMU="`identify_qemu $builddir/vmlinux`"
+	BOOT_IMAGE="`identify_boot_image $QEMU`"
 	cp $builddir/Make*.out $resdir
 	cp $builddir/.config $resdir
-	cp $builddir/arch/x86/boot/bzImage $resdir
+	cp $builddir/$BOOT_IMAGE $resdir
 	parse-build.sh $resdir/Make.out $title
 	if test -f $builddir.wait
 	then
@@ -104,6 +106,7 @@
 	fi
 else
 	cp $builddir/Make*.out $resdir
+	cp $builddir/.config $resdir || :
 	echo Build failed, not running KVM, see $resdir.
 	if test -f $builddir.wait
 	then
@@ -124,9 +127,6 @@
 kstarttime=`awk 'BEGIN { print systime() }' < /dev/null`
 echo ' ---' `date`: Starting kernel
 
-# Determine the appropriate flavor of qemu command.
-QEMU="`identify_qemu $builddir/vmlinux`"
-
 # Generate -smp qemu argument.
 qemu_args="-nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
@@ -151,27 +151,39 @@
 # Generate kernel-version-specific boot parameters
 boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`"
 
-echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
-if test -n "$RCU_BUILDONLY"
+echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+if test -n "$TORTURE_BUILDONLY"
 then
 	echo Build-only run specified, boot/test omitted.
 	exit 0
 fi
-$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append $boot_args" &
+( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
 commandcompleted=0
 echo Monitoring qemu job at pid $qemu_pid
-for ((i=0;i<$seconds;i++))
+while :
 do
+	kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 	if kill -0 $qemu_pid > /dev/null 2>&1
 	then
+		if test $kruntime -ge $seconds
+		then
+			break;
+		fi
 		sleep 1
 	else
 		commandcompleted=1
-		kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 		if test $kruntime -lt $seconds
 		then
 			echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
+			grep "^(qemu) qemu:" $resdir/kvm-test-1-run.sh.out >> $resdir/Warnings 2>&1
+			killpid="`grep "^(qemu) qemu: terminating on signal [0-9]* from pid" $resdir/kvm-test-1-run.sh.out`"
+			if test -n "$killpid"
+			then
+				pscmd="`echo $killpid | sed -e 's/^.*from pid/ps -ef | grep/'`"
+				echo $pscmd >> $resdir/Warnings
+				echo $pscmd | sh >> $resdir/Warnings 2>&1
+			fi
 		else
 			echo ' ---' `date`: Kernel done
 		fi
@@ -181,23 +193,25 @@
 if test $commandcompleted -eq 0
 then
 	echo Grace period for qemu job at pid $qemu_pid
-	for ((i=0;i<=$grace;i++))
+	while :
 	do
+		kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
 		if kill -0 $qemu_pid > /dev/null 2>&1
 		then
-			sleep 1
+			:
 		else
 			break
 		fi
-		if test $i -eq $grace
+		if test $kruntime -ge $((seconds + grace))
 		then
-			kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }'`
 			echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
 			kill -KILL $qemu_pid
+			break
 		fi
+		sleep 1
 	done
 fi
 
 cp $builddir/console.log $resdir
-parse-${TORTURE_SUITE}torture.sh $resdir/console.log $title
+parse-torture.sh $resdir/console.log $title
 parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 5a78cbf..9166184 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -38,9 +38,10 @@
 dryrun=""
 KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
 PATH=${KVM}/bin:$PATH; export PATH
-builddir="${KVM}/b1"
-RCU_INITRD="$KVM/initrd"; export RCU_INITRD
-RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG
+TORTURE_DEFCONFIG=defconfig
+TORTURE_BOOT_IMAGE=""
+TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_KMAKE_ARG=""
 TORTURE_SUITE=rcu
 resdir=""
 configs=""
@@ -53,11 +54,12 @@
 usage () {
 	echo "Usage: $scriptname optional arguments:"
 	echo "       --bootargs kernel-boot-arguments"
-	echo "       --builddir absolute-pathname"
+	echo "       --bootimage relative-path-to-kernel-boot-image"
 	echo "       --buildonly"
 	echo "       --configs \"config-file list\""
 	echo "       --cpus N"
 	echo "       --datestamp string"
+	echo "       --defconfig string"
 	echo "       --dryrun sched|script"
 	echo "       --duration minutes"
 	echo "       --interactive"
@@ -67,7 +69,6 @@
 	echo "       --no-initrd"
 	echo "       --qemu-args qemu-system-..."
 	echo "       --qemu-cmd qemu-system-..."
-	echo "       --relbuilddir relative-pathname"
 	echo "       --results absolute-pathname"
 	echo "       --torture rcu"
 	exit 1
@@ -78,17 +79,16 @@
 	case "$1" in
 	--bootargs)
 		checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--'
-		RCU_BOOTARGS="$2"
+		TORTURE_BOOTARGS="$2"
 		shift
 		;;
-	--builddir)
-		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' '^error'
-		builddir=$2
-		gotbuilddir=1
+	--bootimage)
+		checkarg --bootimage "(relative path to kernel boot image)" "$#" "$2" '[a-zA-Z0-9][a-zA-Z0-9_]*' '^--'
+		TORTURE_BOOT_IMAGE="$2"
 		shift
 		;;
 	--buildonly)
-		RCU_BUILDONLY=1; export RCU_BUILDONLY
+		TORTURE_BUILDONLY=1
 		;;
 	--configs)
 		checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--'
@@ -105,6 +105,11 @@
 		ds=$2
 		shift
 		;;
+	--defconfig)
+		checkarg --defconfig "defconfigtype" "$#" "$2" '^[^/][^/]*$' '^--'
+		TORTURE_DEFCONFIG=$2
+		shift
+		;;
 	--dryrun)
 		checkarg --dryrun "sched|script" $# "$2" 'sched\|script' '^--'
 		dryrun=$2
@@ -116,11 +121,11 @@
 		shift
 		;;
 	--interactive)
-		RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE
+		TORTURE_QEMU_INTERACTIVE=1; export TORTURE_QEMU_INTERACTIVE
 		;;
 	--kmake-arg)
 		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
-		RCU_KMAKE_ARG="$2"; export RCU_KMAKE_ARG
+		TORTURE_KMAKE_ARG="$2"
 		shift
 		;;
 	--kversion)
@@ -130,27 +135,20 @@
 		;;
 	--mac)
 		checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error
-		RCU_QEMU_MAC=$2; export RCU_QEMU_MAC
+		TORTURE_QEMU_MAC=$2; export TORTURE_QEMU_MAC
 		shift
 		;;
 	--no-initrd)
-		RCU_INITRD=""; export RCU_INITRD
+		TORTURE_INITRD=""; export TORTURE_INITRD
 		;;
 	--qemu-args)
 		checkarg --qemu-args "-qemu args" $# "$2" '^-' '^error'
-		RCU_QEMU_ARG="$2"
+		TORTURE_QEMU_ARG="$2"
 		shift
 		;;
 	--qemu-cmd)
 		checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--'
-		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
-		shift
-		;;
-	--relbuilddir)
-		checkarg --relbuilddir "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
-		relbuilddir=$2
-		gotrelbuilddir=1
-		builddir=${KVM}/${relbuilddir}
+		TORTURE_QEMU_CMD="$2"; export TORTURE_QEMU_CMD
 		shift
 		;;
 	--results)
@@ -184,30 +182,6 @@
 	resdir=$KVM/res
 fi
 
-if test "$dryrun" = ""
-then
-	if ! test -e $resdir
-	then
-		mkdir -p "$resdir" || :
-	fi
-	mkdir $resdir/$ds
-
-	# Be noisy only if running the script.
-	echo Results directory: $resdir/$ds
-	echo $scriptname $args
-
-	touch $resdir/$ds/log
-	echo $scriptname $args >> $resdir/$ds/log
-	echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE
-
-	pwd > $resdir/$ds/testid.txt
-	if test -d .git
-	then
-		git status >> $resdir/$ds/testid.txt
-		git rev-parse HEAD >> $resdir/$ds/testid.txt
-	fi
-fi
-
 # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus.
 touch $T/cfgcpu
 for CF in $configs
@@ -274,7 +248,41 @@
 
 # Generate a script to execute the tests in appropriate batches.
 cat << ___EOF___ > $T/script
+CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG
+KVM="$KVM"; export KVM
+KVPATH="$KVPATH"; export KVPATH
+PATH="$PATH"; export PATH
+TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
+TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
+TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG
+TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD
+TORTURE_KMAKE_ARG="$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
+TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC
 TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE
+if ! test -e $resdir
+then
+	mkdir -p "$resdir" || :
+fi
+mkdir $resdir/$ds
+echo Results directory: $resdir/$ds
+echo $scriptname $args
+touch $resdir/$ds/log
+echo $scriptname $args >> $resdir/$ds/log
+echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE
+pwd > $resdir/$ds/testid.txt
+if test -d .git
+then
+	git status >> $resdir/$ds/testid.txt
+	git rev-parse HEAD >> $resdir/$ds/testid.txt
+	git diff HEAD > $T/git-diff 2>&1
+	if test -s $T/git-diff
+	then
+		cp $T/git-diff $resdir/$ds
+	fi
+fi
 ___EOF___
 awk < $T/cfgcpu.pack \
 	-v CONFIGDIR="$CONFIGFRAG/$kversion/" \
@@ -282,8 +290,8 @@
 	-v ncpus=$cpus \
 	-v rd=$resdir/$ds/ \
 	-v dur=$dur \
-	-v RCU_QEMU_ARG=$RCU_QEMU_ARG \
-	-v RCU_BOOTARGS=$RCU_BOOTARGS \
+	-v TORTURE_QEMU_ARG="$TORTURE_QEMU_ARG" \
+	-v TORTURE_BOOTARGS="$TORTURE_BOOTARGS" \
 'BEGIN {
 	i = 0;
 }
@@ -320,7 +328,7 @@
 		print "touch " builddir ".wait";
 		print "mkdir " builddir " > /dev/null 2>&1 || :";
 		print "mkdir " rd cfr[jn] " || :";
-		print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" RCU_QEMU_ARG "\" \"" RCU_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
+		print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" TORTURE_QEMU_ARG "\" \"" TORTURE_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
 		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date`";
 		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` >> " rd "/log";
 		print "while test -f " builddir ".wait"
@@ -374,28 +382,26 @@
 		dump(first, i);
 }' >> $T/script
 
+cat << ___EOF___ >> $T/script
+echo
+echo
+echo " --- `date` Test summary:"
+echo Results directory: $resdir/$ds
+if test -z "$TORTURE_BUILDONLY"
+then
+	kvm-recheck.sh $resdir/$ds
+fi
+___EOF___
+
 if test "$dryrun" = script
 then
-	# Dump out the script, but define the environment variables that
-	# it needs to run standalone.
-	echo CONFIGFRAG="$CONFIGFRAG; export CONFIGFRAG"
-	echo KVM="$KVM; export KVM"
-	echo KVPATH="$KVPATH; export KVPATH"
-	echo PATH="$PATH; export PATH"
-	echo RCU_BUILDONLY="$RCU_BUILDONLY; export RCU_BUILDONLY"
-	echo RCU_INITRD="$RCU_INITRD; export RCU_INITRD"
-	echo RCU_KMAKE_ARG="$RCU_KMAKE_ARG; export RCU_KMAKE_ARG"
-	echo RCU_QEMU_CMD="$RCU_QEMU_CMD; export RCU_QEMU_CMD"
-	echo RCU_QEMU_INTERACTIVE="$RCU_QEMU_INTERACTIVE; export RCU_QEMU_INTERACTIVE"
-	echo RCU_QEMU_MAC="$RCU_QEMU_MAC; export RCU_QEMU_MAC"
-	echo "mkdir -p "$resdir" || :"
-	echo "mkdir $resdir/$ds"
 	cat $T/script
 	exit 0
 elif test "$dryrun" = sched
 then
 	# Extract the test run schedule from the script.
-	egrep 'start batch|Starting build\.' $T/script |
+	egrep 'Start batch|Starting build\.' $T/script |
+		grep -v ">>" |
 		sed -e 's/:.*$//' -e 's/^echo //'
 	exit 0
 else
@@ -404,9 +410,3 @@
 fi
 
 # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
-
-echo
-echo
-echo " --- `date` Test summary:"
-echo Results directory: $resdir/$ds
-kvm-recheck.sh $resdir/$ds
diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
similarity index 79%
rename from tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
rename to tools/testing/selftests/rcutorture/bin/parse-torture.sh
index dd0a275d..3455560 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
@@ -1,14 +1,14 @@
 #!/bin/sh
 #
-# Check the console output from an rcutorture run for goodness.
+# Check the console output from a torture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
 # a text string for error-message purposes.
 #
-# The file must contain rcutorture output, but can be interspersed
-# with other dmesg text.
+# The file must contain torture output, but can be interspersed
+# with other dmesg text, as in console-log output.
 #
 # Usage:
-#	sh parse-rcutorture.sh file title
+#	sh parse-torture.sh file title
 #
 # 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
@@ -28,7 +28,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/parse-rcutorture.sh.$$
+T=/tmp/parse-torture.sh.$$
 file="$1"
 title="$2"
 
@@ -36,13 +36,13 @@
 
 . functions.sh
 
-# check for presence of rcutorture.txt file
+# check for presence of torture output file.
 
 if test -f "$file" -a -r "$file"
 then
 	:
 else
-	echo $title unreadable rcutorture.txt file: $file
+	echo $title unreadable torture output file: $file
 	exit 1
 fi
 
@@ -76,9 +76,9 @@
 END	{
 	if (badseq) {
 		if (badseqno1 == badseqno2 && badseqno2 == ver)
-			print "RCU GP HANG at " ver " rcutorture stat " badseqnr;
+			print "GP HANG at " ver " torture stat " badseqnr;
 		else
-			print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " RCU version " badseqnr;
+			print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
 	}
 	}' > $T.seq
 
@@ -91,13 +91,13 @@
 		exit 2
 	fi
 else
-	if grep -q RCU_HOTPLUG $file
+	if grep -q "_HOTPLUG:" $file
 	then
 		print_warning HOTPLUG FAILURES $title `cat $T.seq`
 		echo "   " $file
 		exit 3
 	fi
-	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful RCU version messages
+	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
 	if test -s $T.seq
 	then
 		print_warning $title `cat $T.seq`
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
new file mode 100644
index 0000000..61c8d9c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -0,0 +1,25 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_LEAF=3
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=y
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
new file mode 100644
index 0000000..3b42b8b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=sched