Merge branches 'array.2015.05.27a', 'doc.2015.05.27a', 'fixes.2015.05…

….27a', 'hotplug.2015.05.27a', 'init.2015.05.27a', 'tiny.2015.05.27a' and 'torture.2015.05.27a' into HEAD

array.2015.05.27a:  Remove all uses of RCU-protected array indexes.
doc.2015.05.27a:  Docuemntation updates.
fixes.2015.05.27a:  Miscellaneous fixes.
hotplug.2015.05.27a:  CPU-hotplug updates.
init.2015.05.27a:  Initialization/Kconfig updates.
tiny.2015.05.27a:  Updates to Tiny RCU.
torture.2015.05.27a:  Torture-testing updates.

Documentation/RCU/rcu_dereference.txt

@@ -184,6 +184,11 @@ o	Be very careful about comparing pointers obtained from
 		pointer.  Note that the volatile cast in rcu_dereference()
 		will normally prevent the compiler from knowing too much.
 
+		However, please note that if the compiler knows that the
+		pointer takes on only one of two values, a not-equal
+		comparison will provide exactly the information that the
+		compiler needs to deduce the value of the pointer.
+
 o	Disable any value-speculation optimizations that your compiler
 	might provide, especially if you are making use of feedback-based
 	optimizations that take data collected from prior runs.  Such

Documentation/RCU/whatisRCU.txt

@@ -256,7 +256,9 @@ rcu_dereference()
 	If you are going to be fetching multiple fields from the
 	RCU-protected structure, using the local variable is of
 	course preferred.  Repeated rcu_dereference() calls look
-	ugly and incur unnecessary overhead on Alpha CPUs.
+	ugly, do not guarantee that the same pointer will be returned
+	if an update happened while in the critical section, and incur
+	unnecessary overhead on Alpha CPUs.
 
 	Note that the value returned by rcu_dereference() is valid
 	only within the enclosing RCU read-side critical section.

Documentation/kernel-parameters.txt

@@ -2992,11 +2992,34 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.dump_tree=	[KNL]
+			Dump the structure of the rcu_node combining tree
+			out at early boot.  This is used for diagnostic
+			purposes, to verify correct tree setup.
+
+	rcutree.gp_cleanup_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period cleanup.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
+
 	rcutree.gp_init_delay=	[KNL]
 			Set the number of jiffies to delay each step of
 			RCU grace-period initialization.  This only has
-			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
-			set.
+			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+			is set.
+
+	rcutree.gp_preinit_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period pre-initialization, that is,
+			the propagation of recent CPU-hotplug changes up
+			the rcu_node combining tree.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
+
+	rcutree.rcu_fanout_exact= [KNL]
+			Disable autobalancing of the rcu_node combining
+			tree.  This is used by rcutorture, and might
+			possibly be useful for architectures having high
+			cache-to-cache transfer latencies.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -3101,7 +3124,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			test, hence the "fake".
 
 	rcutorture.nreaders= [KNL]
-			Set number of RCU readers.
+			Set number of RCU readers.  The value -1 selects
+			N-1, where N is the number of CPUs.  A value
+			"n" less than -1 selects N-n-2, where N is again
+			the number of CPUs.  For example, -2 selects N
+			(the number of CPUs), -3 selects N+1, and so on.
 
 	rcutorture.object_debug= [KNL]
 			Enable debug-object double-call_rcu() testing.

Documentation/memory-barriers.txt

@@ -617,16 +617,16 @@ case what's actually required is:
 However, stores are not speculated.  This means that ordering -is- provided
 for load-store control dependencies, as in the following example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 	}
 
-Control dependencies pair normally with other types of barriers.
-That said, please note that ACCESS_ONCE() is not optional!  Without the
-ACCESS_ONCE(), might combine the load from 'a' with other loads from
-'a', and the store to 'b' with other stores to 'b', with possible highly
-counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers.  That
+said, please note that READ_ONCE_CTRL() is not optional!  Without the
+READ_ONCE_CTRL(), the compiler might combine the load from 'a' with
+other loads from 'a', and the store to 'b' with other stores to 'b',
+with possible highly counterintuitive effects on ordering.
 
 Worse yet, if the compiler is able to prove (say) that the value of
 variable 'a' is always non-zero, it would be well within its rights
@@ -636,12 +636,15 @@ as follows:
 	q = a;
 	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
 
-So don't leave out the ACCESS_ONCE().
+Finally, the READ_ONCE_CTRL() includes an smp_read_barrier_depends()
+that DEC Alpha needs in order to respect control depedencies.
+
+So don't leave out the READ_ONCE_CTRL().
 
 It is tempting to try to enforce ordering on identical stores on both
 branches of the "if" statement as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		barrier();
 		ACCESS_ONCE(b) = p;
@@ -655,7 +658,7 @@ branches of the "if" statement as follows:
 Unfortunately, current compilers will transform this as follows at high
 optimization levels:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	barrier();
 	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
@@ -685,7 +688,7 @@ memory barriers, for example, smp_store_release():
 In contrast, without explicit memory barriers, two-legged-if control
 ordering is guaranteed only when the stores differ, for example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -694,14 +697,14 @@ ordering is guaranteed only when the stores differ, for example:
 		do_something_else();
 	}
 
-The initial ACCESS_ONCE() is still required to prevent the compiler from
-proving the value of 'a'.
+The initial READ_ONCE_CTRL() is still required to prevent the compiler
+from proving the value of 'a'.
 
 In addition, you need to be careful what you do with the local variable 'q',
 otherwise the compiler might be able to guess the value and again remove
 the needed conditional.  For example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -714,7 +717,7 @@ If MAX is defined to be 1, then the compiler knows that (q % MAX) is
 equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = p;
 	do_something_else();
 
@@ -725,7 +728,7 @@ is gone, and the barrier won't bring it back.  Therefore, if you are
 relying on this ordering, you should make sure that MAX is greater than
 one, perhaps as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
@@ -742,14 +745,15 @@ of the 'if' statement.
 You must also be careful not to rely too much on boolean short-circuit
 evaluation.  Consider this example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (a || 1 > 0)
 		ACCESS_ONCE(b) = 1;
 
-Because the second condition is always true, the compiler can transform
-this example as following, defeating control dependency:
+Because the first condition cannot fault and the second condition is
+always true, the compiler can transform this example as following,
+defeating control dependency:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = 1;
 
 This example underscores the need to ensure that the compiler cannot
@@ -762,8 +766,8 @@ demonstrated by two related examples, with the initial values of
 x and y both being zero:
 
 	CPU 0                     CPU 1
-	=====================     =====================
-	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+	=======================   =======================
+	r1 = READ_ONCE_CTRL(x);   r2 = READ_ONCE_CTRL(y);
 	if (r1 > 0)               if (r2 > 0)
 	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
 
@@ -783,14 +787,21 @@ But because control dependencies do -not- provide transitivity, the above
 assertion can fail after the combined three-CPU example completes.  If you
 need the three-CPU example to provide ordering, you will need smp_mb()
 between the loads and stores in the CPU 0 and CPU 1 code fragments,
-that is, just before or just after the "if" statements.
+that is, just before or just after the "if" statements.  Furthermore,
+the original two-CPU example is very fragile and should be avoided.
 
 These two examples are the LB and WWC litmus tests from this paper:
 http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this
 site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html.
 
 In summary:
 
+  (*) Control dependencies must be headed by READ_ONCE_CTRL().
+      Or, as a much less preferable alternative, interpose
+      be headed by READ_ONCE() or an ACCESS_ONCE() read and must
+      have smp_read_barrier_depends() between this read and the
+      control-dependent write.
+
   (*) Control dependencies can order prior loads against later stores.
       However, they do -not- guarantee any other sort of ordering:
       Not prior loads against later loads, nor prior stores against
@@ -1784,10 +1795,9 @@ for each construct.  These operations all imply certain barriers:
 
      Memory operations issued before the ACQUIRE may be completed after
      the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
-     combined with a following ACQUIRE, orders prior loads against
-     subsequent loads and stores and also orders prior stores against
-     subsequent stores.  Note that this is weaker than smp_mb()!  The
-     smp_mb__before_spinlock() primitive is free on many architectures.
+     combined with a following ACQUIRE, orders prior stores against
+     subsequent loads and stores. Note that this is weaker than smp_mb()!
+     The smp_mb__before_spinlock() primitive is free on many architectures.
 
  (2) RELEASE operation implication:
 

arch/powerpc/include/asm/barrier.h

@@ -89,5 +89,6 @@ do {									\
 
 #define smp_mb__before_atomic()     smp_mb()
 #define smp_mb__after_atomic()      smp_mb()
+#define smp_mb__before_spinlock()   smp_mb()
 
 #endif /* _ASM_POWERPC_BARRIER_H */

include/linux/compiler.h

@@ -252,6 +252,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #define WRITE_ONCE(x, val) \
 	({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
 
+/**
+ * READ_ONCE_CTRL - Read a value heading a control dependency
+ * @x: The value to be read, heading the control dependency
+ *
+ * Control dependencies are tricky.  See Documentation/memory-barriers.txt
+ * for important information on how to use them.  Note that in many cases,
+ * use of smp_load_acquire() will be much simpler.  Control dependencies
+ * should be avoided except on the hottest of hotpaths.
+ */
+#define READ_ONCE_CTRL(x) \
+({ \
+	typeof(x) __val = READ_ONCE(x); \
+	smp_read_barrier_depends(); /* Enforce control dependency. */ \
+	__val; \
+})
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */

include/linux/rculist.h

@@ -549,8 +549,8 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  */
 #define hlist_for_each_entry_from_rcu(pos, member)			\
 	for (; pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 #endif	/* __KERNEL__ */
 #endif

include/linux/rcupdate.h

@@ -292,10 +292,6 @@ void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 struct notifier_block;
-void rcu_idle_enter(void);
-void rcu_idle_exit(void);
-void rcu_irq_enter(void);
-void rcu_irq_exit(void);
 int rcu_cpu_notify(struct notifier_block *self,
 		   unsigned long action, void *hcpu);
 
@@ -1103,13 +1099,13 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
-#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
+#ifdef CONFIG_TINY_RCU
 static inline int rcu_needs_cpu(unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
 	return 0;
 }
-#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
+#endif /* #ifdef CONFIG_TINY_RCU */
 
 #if defined(CONFIG_RCU_NOCB_CPU_ALL)
 static inline bool rcu_is_nocb_cpu(int cpu) { return true; }

include/linux/rcutiny.h

@@ -159,6 +159,22 @@ static inline void rcu_cpu_stall_reset(void)
 {
 }
 
+static inline void rcu_idle_enter(void)
+{
+}
+
+static inline void rcu_idle_exit(void)
+{
+}
+
+static inline void rcu_irq_enter(void)
+{
+}
+
+static inline void rcu_irq_exit(void)
+{
+}
+
 static inline void exit_rcu(void)
 {
 }

include/linux/rcutree.h

@@ -31,9 +31,7 @@
 #define __LINUX_RCUTREE_H
 
 void rcu_note_context_switch(void);
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(unsigned long *delta_jiffies);
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 void rcu_cpu_stall_reset(void);
 
 /*
@@ -93,6 +91,11 @@ void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
 
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
+
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);

include/linux/spinlock.h

@@ -120,7 +120,7 @@ do {								\
 /*
  * Despite its name it doesn't necessarily has to be a full barrier.
  * It should only guarantee that a STORE before the critical section
- * can not be reordered with a LOAD inside this section.
+ * can not be reordered with LOADs and STOREs inside this section.
  * spin_lock() is the one-way barrier, this LOAD can not escape out
  * of the region. So the default implementation simply ensures that
  * a STORE can not move into the critical section, smp_wmb() should