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

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle are:

   - Documentation updates.

   - Miscellaneous fixes.

   - Preemptible-RCU fixes, including fixing an old bug in the
     interaction of RCU priority boosting and CPU hotplug.

   - SRCU updates.

   - RCU CPU stall-warning updates.

   - RCU torture-test updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  rcu: Initialize tiny RCU stall-warning timeouts at boot
  rcu: Fix RCU CPU stall detection in tiny implementation
  rcu: Add GP-kthread-starvation checks to CPU stall warnings
  rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors
  rcu: Optionally run grace-period kthreads at real-time priority
  ksoftirqd: Use new cond_resched_rcu_qs() function
  ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
  rcutorture: Add more diagnostics in rcu_barrier() test failure case
  torture: Flag console.log file to prevent holdovers from earlier runs
  torture: Add "-enable-kvm -soundhw pcspk" to qemu command line
  rcutorture: Handle different mpstat versions
  rcutorture: Check from beginning to end of grace period
  rcu: Remove redundant rcu_batches_completed() declaration
  rcutorture: Drop rcu_torture_completed() and friends
  rcu: Provide rcu_batches_completed_sched() for TINY_RCU
  rcutorture: Use unsigned for Reader Batch computations
  rcutorture: Make build-output parsing correctly flag RCU's warnings
  rcu: Make _batches_completed() functions return unsigned long
  rcutorture: Issue warnings on close calls due to Reader Batch blows
  documentation: Fix smp typo in memory-barriers.txt
  ...

include/linux/compiler.h

@@ -385,7 +385,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 
 /* Is this type a native word size -- useful for atomic operations */
 #ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 #endif
 
 /* Compile time object size, -1 for unknown */

include/linux/rculist.h

@@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu(pos, member)			\
-	for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     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))
 
 /**
  * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point
@@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu_bh(pos, member)		\
-	for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(  \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point

include/linux/rcupdate.h

@@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void)
 extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
+		rcu_all_qs(); \
 		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
 			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
-#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#define rcu_note_voluntary_context_switch(t)	rcu_all_qs()
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
@@ -582,11 +583,11 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_check(p, c, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
 	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
@@ -603,10 +604,10 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_index_check(p, c) \
 ({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(p) _________p1 = lockless_dereference(p); \
 	rcu_lockdep_assert(c, \
 			   "suspicious rcu_dereference_index_check() usage"); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
 

include/linux/rcutiny.h

@@ -92,17 +92,49 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 /*
- * Return the number of grace periods.
+ * Return the number of grace periods started.
  */
-static inline long rcu_batches_completed(void)
+static inline unsigned long rcu_batches_started(void)
 {
 	return 0;
 }
 
 /*
- * Return the number of bottom-half grace periods.
+ * Return the number of bottom-half grace periods started.
  */
-static inline long rcu_batches_completed_bh(void)
+static inline unsigned long rcu_batches_started_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods started.
+ */
+static inline unsigned long rcu_batches_started_sched(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_sched(void)
 {
 	return 0;
 }
@@ -154,7 +186,10 @@ static inline bool rcu_is_watching(void)
 	return true;
 }
 
-
 #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
+static inline void rcu_all_qs(void)
+{
+}
+
 #endif /* __LINUX_RCUTINY_H */

include/linux/rcutree.h

@@ -81,9 +81,12 @@ void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-long rcu_batches_completed(void);
-long rcu_batches_completed_bh(void);
-long rcu_batches_completed_sched(void);
+unsigned long rcu_batches_started(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_started_sched(void);
+unsigned long rcu_batches_completed(void);
+unsigned long rcu_batches_completed_bh(void);
+unsigned long rcu_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
@@ -97,4 +100,6 @@ extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
 
+void rcu_all_qs(void);
+
 #endif /* __LINUX_RCUTREE_H */

include/linux/srcu.h

@@ -45,7 +45,7 @@ struct rcu_batch {
 #define RCU_BATCH_INIT(name) { NULL, &(name.head) }
 
 struct srcu_struct {
-	unsigned completed;
+	unsigned long completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
@@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work);
  * define and init a srcu struct at build time.
  * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
  */
-#define DEFINE_SRCU(name)						\
+#define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
-
-#define DEFINE_STATIC_SRCU(name)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
+#define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
@@ -135,7 +133,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
-long srcu_batches_completed(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC