9 files changed, 169 insertions, 161 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 4786c2235b98..e91ec9ddcd30 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -182,7 +182,7 @@ static inline void list_replace_rcu(struct list_head *old,
  * @list:       the RCU-protected list to splice
  * @prev:       points to the last element of the existing list
  * @next:       points to the first element of the existing list
- * @sync:       function to sync: synchronize_rcu(), synchronize_sched(), ...
+ * @sync:       synchronize_rcu, synchronize_rcu_expedited, ...
  *
  * The list pointed to by @prev and @next can be RCU-read traversed
  * concurrently with this function.
@@ -240,7 +240,7 @@ static inline void __list_splice_init_rcu(struct list_head *list,
  *                        designed for stacks.
  * @list:       the RCU-protected list to splice
  * @head:       the place in the existing list to splice the first list into
- * @sync:       function to sync: synchronize_rcu(), synchronize_sched(), ...
+ * @sync:       synchronize_rcu, synchronize_rcu_expedited, ...
  */
 static inline void list_splice_init_rcu(struct list_head *list,
                                         struct list_head *head,
@@ -255,7 +255,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  *                             list, designed for queues.
  * @list:       the RCU-protected list to splice
  * @head:       the place in the existing list to splice the first list into
- * @sync:       function to sync: synchronize_rcu(), synchronize_sched(), ...
+ * @sync:       synchronize_rcu, synchronize_rcu_expedited, ...
  */
 static inline void list_splice_tail_init_rcu(struct list_head *list,
                                              struct list_head *head,
@@ -359,13 +359,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @type:       the type of the struct this is embedded in.
  * @member:     the name of the list_head within the struct.
  *
- * This primitive may safely run concurrently with the _rcu list-mutation
- * primitives such as list_add_rcu(), but requires some implicit RCU
- * read-side guarding.  One example is running within a special
- * exception-time environment where preemption is disabled and where
- * lockdep cannot be invoked (in which case updaters must use RCU-sched,
- * as in synchronize_sched(), call_rcu_sched(), and friends).  Another
- * example is when items are added to the list, but never deleted.
+ * This primitive may safely run concurrently with the _rcu
+ * list-mutation primitives such as list_add_rcu(), but requires some
+ * implicit RCU read-side guarding.  One example is running within a special
+ * exception-time environment where preemption is disabled and where lockdep
+ * cannot be invoked.  Another example is when items are added to the list,
+ * but never deleted.
  */
 #define list_entry_lockless(ptr, type, member) \
         container_of((typeof(ptr))READ_ONCE(ptr), type, member)
@@ -376,13 +375,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @head:       the head for your list.
  * @member:     the name of the list_struct within the struct.
  *
- * This primitive may safely run concurrently with the _rcu list-mutation
- * primitives such as list_add_rcu(), but requires some implicit RCU
- * read-side guarding.  One example is running within a special
- * exception-time environment where preemption is disabled and where
- * lockdep cannot be invoked (in which case updaters must use RCU-sched,
- * as in synchronize_sched(), call_rcu_sched(), and friends).  Another
- * example is when items are added to the list, but never deleted.
+ * This primitive may safely run concurrently with the _rcu
+ * list-mutation primitives such as list_add_rcu(), but requires some
+ * implicit RCU read-side guarding.  One example is running within a special
+ * exception-time environment where preemption is disabled and where lockdep
+ * cannot be invoked.  Another example is when items are added to the list,
+ * but never deleted.
  */
 #define list_for_each_entry_lockless(pos, head, member) \
         for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 75e5b393cf44..4db8bcacc51a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -48,23 +48,14 @@
 #define ulong2long(a)           (*(long *)(&(a)))
 
 /* Exported common interfaces */
-
-#ifdef CONFIG_PREEMPT_RCU
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
-#else /* #ifdef CONFIG_PREEMPT_RCU */
-#define call_rcu        call_rcu_sched
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
-void call_rcu_bh(struct rcu_head *head, rcu_callback_t func);
-void call_rcu_sched(struct rcu_head *head, rcu_callback_t func);
-void synchronize_sched(void);
 void rcu_barrier_tasks(void);
+void synchronize_rcu(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
 void __rcu_read_lock(void);
 void __rcu_read_unlock(void);
-void synchronize_rcu(void);
 
 /*
  * Defined as a macro as it is a very low level header included from
@@ -88,11 +79,6 @@ static inline void __rcu_read_unlock(void)
                 preempt_enable();
 }
 
-static inline void synchronize_rcu(void)
-{
-        synchronize_sched();
-}
-
 static inline int rcu_preempt_depth(void)
 {
         return 0;
@@ -103,8 +89,6 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 void rcu_init(void);
 extern int rcu_scheduler_active __read_mostly;
-void rcu_sched_qs(void);
-void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
@@ -135,11 +119,10 @@ static inline void rcu_init_nohz(void) { }
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
  * @a: Code that RCU needs to pay attention to.
  *
- * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden
- * in the inner idle loop, that is, between the rcu_idle_enter() and
- * the rcu_idle_exit() -- RCU will happily ignore any such read-side
- * critical sections.  However, things like powertop need tracepoints
- * in the inner idle loop.
+ * RCU read-side critical sections are forbidden in the inner idle loop,
+ * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU
+ * will happily ignore any such read-side critical sections.  However,
+ * things like powertop need tracepoints in the inner idle loop.
  *
  * This macro provides the way out:  RCU_NONIDLE(do_something_with_RCU())
  * will tell RCU that it needs to pay attention, invoke its argument
@@ -167,20 +150,16 @@ static inline void rcu_init_nohz(void) { }
                 if (READ_ONCE((t)->rcu_tasks_holdout)) \
                         WRITE_ONCE((t)->rcu_tasks_holdout, false); \
         } while (0)
-#define rcu_note_voluntary_context_switch(t) \
-        do { \
-                rcu_all_qs(); \
-                rcu_tasks_qs(t); \
-        } while (0)
+#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define rcu_tasks_qs(t) do { } while (0)
-#define rcu_note_voluntary_context_switch(t)            rcu_all_qs()
-#define call_rcu_tasks call_rcu_sched
-#define synchronize_rcu_tasks synchronize_sched
+#define rcu_note_voluntary_context_switch(t) do { } while (0)
+#define call_rcu_tasks call_rcu
+#define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }
 static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
@@ -325,9 +304,8 @@ static inline void rcu_preempt_sleep_check(void) { }
  * Helper functions for rcu_dereference_check(), rcu_dereference_protected()
  * and rcu_assign_pointer().  Some of these could be folded into their
  * callers, but they are left separate in order to ease introduction of
- * multiple flavors of pointers to match the multiple flavors of RCU
- * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in
- * the future.
+ * multiple pointers markings to match different RCU implementations
+ * (e.g., __srcu), should this make sense in the future.
  */
 
 #ifdef __CHECKER__
@@ -686,14 +664,9 @@ static inline void rcu_read_unlock(void)
 /**
  * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
  *
- * This is equivalent of rcu_read_lock(), but to be used when updates
- * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since
- * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a
- * softirq handler to be a quiescent state, a process in RCU read-side
- * critical section must be protected by disabling softirqs. Read-side
- * critical sections in interrupt context can use just rcu_read_lock(),
- * though this should at least be commented to avoid confusing people
- * reading the code.
+ * This is equivalent of rcu_read_lock(), but also disables softirqs.
+ * Note that anything else that disables softirqs can also serve as
+ * an RCU read-side critical section.
  *
  * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh()
  * must occur in the same context, for example, it is illegal to invoke
@@ -726,10 +699,9 @@ static inline void rcu_read_unlock_bh(void)
 /**
  * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
  *
- * This is equivalent of rcu_read_lock(), but to be used when updates
- * are being done using call_rcu_sched() or synchronize_rcu_sched().
- * Read-side critical sections can also be introduced by anything that
- * disables preemption, including local_irq_disable() and friends.
+ * This is equivalent of rcu_read_lock(), but disables preemption.
+ * Read-side critical sections can also be introduced by anything else
+ * that disables preemption, including local_irq_disable() and friends.
  *
  * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched()
  * must occur in the same context, for example, it is illegal to invoke
@@ -885,4 +857,96 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
 
 
+/* Has the specified rcu_head structure been handed to call_rcu()? */
+
+/*
+ * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu()
+ * @rhp: The rcu_head structure to initialize.
+ *
+ * If you intend to invoke rcu_head_after_call_rcu() to test whether a
+ * given rcu_head structure has already been passed to call_rcu(), then
+ * you must also invoke this rcu_head_init() function on it just after
+ * allocating that structure.  Calls to this function must not race with
+ * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation.
+ */
+static inline void rcu_head_init(struct rcu_head *rhp)
+{
+        rhp->func = (rcu_callback_t)~0L;
+}
+
+/*
+ * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()?
+ * @rhp: The rcu_head structure to test.
+ * @func: The function passed to call_rcu() along with @rhp.
+ *
+ * Returns @true if the @rhp has been passed to call_rcu() with @func,
+ * and @false otherwise.  Emits a warning in any other case, including
+ * the case where @rhp has already been invoked after a grace period.
+ * Calls to this function must not race with callback invocation.  One way
+ * to avoid such races is to enclose the call to rcu_head_after_call_rcu()
+ * in an RCU read-side critical section that includes a read-side fetch
+ * of the pointer to the structure containing @rhp.
+ */
+static inline bool
+rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
+{
+        if (READ_ONCE(rhp->func) == f)
+                return true;
+        WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L);
+        return false;
+}
+
+
+/* Transitional pre-consolidation compatibility definitions. */
+
+static inline void synchronize_rcu_bh(void)
+{
+        synchronize_rcu();
+}
+
+static inline void synchronize_rcu_bh_expedited(void)
+{
+        synchronize_rcu_expedited();
+}
+
+static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
+{
+        call_rcu(head, func);
+}
+
+static inline void rcu_barrier_bh(void)
+{
+        rcu_barrier();
+}
+
+static inline void synchronize_sched(void)
+{
+        synchronize_rcu();
+}
+
+static inline void synchronize_sched_expedited(void)
+{
+        synchronize_rcu_expedited();
+}
+
+static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
+{
+        call_rcu(head, func);
+}
+
+static inline void rcu_barrier_sched(void)
+{
+        rcu_barrier();
+}
+
+static inline unsigned long get_state_synchronize_sched(void)
+{
+        return get_state_synchronize_rcu();
+}
+
+static inline void cond_synchronize_sched(unsigned long oldstate)
+{
+        cond_synchronize_rcu(oldstate);
+}
+
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
index 57f371344152..8a16c3eb3dd0 100644
--- a/include/linux/rcupdate_wait.h
+++ b/include/linux/rcupdate_wait.h
@@ -33,17 +33,17 @@ do {									\
 
 /**
  * synchronize_rcu_mult - Wait concurrently for multiple grace periods
- * @...: List of call_rcu() functions for the flavors to wait on.
+ * @...: List of call_rcu() functions for different grace periods to wait on
  *
- * This macro waits concurrently for multiple flavors of RCU grace periods.
- * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait
- * on concurrent RCU and RCU-bh grace periods.  Waiting on a give SRCU
+ * This macro waits concurrently for multiple types of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait
+ * on concurrent RCU and RCU-tasks grace periods.  Waiting on a give SRCU
  * domain requires you to write a wrapper function for that SRCU domain's
  * call_srcu() function, supplying the corresponding srcu_struct.
  *
- * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU
- * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called
- * is automatically a grace period.
+ * If Tiny RCU, tell _wait_rcu_gp() does not bother waiting for RCU,
+ * given that anywhere synchronize_rcu_mult() can be called is automatically
+ * a grace period.
  */
 #define synchronize_rcu_mult(...) \
         _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 8d9a0ea8f0b5..af65d1f36ddb 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,12 +27,6 @@
 
 #include <linux/ktime.h>
 
-struct rcu_dynticks;
-static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
-{
-        return 0;
-}
-
 /* Never flag non-existent other CPUs! */
 static inline bool rcu_eqs_special_set(int cpu) { return false; }
 
@@ -46,53 +40,28 @@ static inline void cond_synchronize_rcu(unsigned long oldstate)
         might_sleep();
 }
 
-static inline unsigned long get_state_synchronize_sched(void)
-{
-        return 0;
-}
-
-static inline void cond_synchronize_sched(unsigned long oldstate)
-{
-        might_sleep();
-}
-
-extern void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
+extern void rcu_barrier(void);
 
 static inline void synchronize_rcu_expedited(void)
 {
-        synchronize_sched();    /* Only one CPU, so pretty fast anyway!!! */
+        synchronize_rcu();
 }
 
-static inline void rcu_barrier(void)
+static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-        rcu_barrier_sched();  /* Only one CPU, so only one list of callbacks! */
-}
-
-static inline void synchronize_rcu_bh(void)
-{
-        synchronize_sched();
-}
-
-static inline void synchronize_rcu_bh_expedited(void)
-{
-        synchronize_sched();
+        call_rcu(head, func);
 }
 
-static inline void synchronize_sched_expedited(void)
-{
-        synchronize_sched();
-}
+void rcu_qs(void);
 
-static inline void kfree_call_rcu(struct rcu_head *head,
-                                  rcu_callback_t func)
+static inline void rcu_softirq_qs(void)
 {
-        call_rcu(head, func);
+        rcu_qs();
 }
 
 #define rcu_note_context_switch(preempt) \
         do { \
-                rcu_sched_qs(); \
+                rcu_qs(); \
                 rcu_tasks_qs(current); \
         } while (0)
 
@@ -108,6 +77,7 @@ static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
  */
 static inline void rcu_virt_note_context_switch(int cpu) { }
 static inline void rcu_cpu_stall_reset(void) { }
+static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; }
 static inline void rcu_idle_enter(void) { }
 static inline void rcu_idle_exit(void) { }
 static inline void rcu_irq_enter(void) { }
@@ -115,6 +85,11 @@ static inline void rcu_irq_exit_irqson(void) { }
 static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void exit_rcu(void) { }
+static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
+{
+        return false;
+}
+static inline void rcu_preempt_deferred_qs(struct task_struct *t) { }
 #ifdef CONFIG_SRCU
 void rcu_scheduler_starting(void);
 #else /* #ifndef CONFIG_SRCU */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 914655848ef6..7f83179177d1 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,6 +30,7 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
+void rcu_softirq_qs(void);
 void rcu_note_context_switch(bool preempt);
 int rcu_needs_cpu(u64 basem, u64 *nextevt);
 void rcu_cpu_stall_reset(void);
@@ -44,41 +45,13 @@ static inline void rcu_virt_note_context_switch(int cpu)
         rcu_note_context_switch(false);
 }
 
-void synchronize_rcu_bh(void);
-void synchronize_sched_expedited(void);
 void synchronize_rcu_expedited(void);
-
 void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
 
-/**
- * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period
- *
- * Wait for an RCU-bh grace period to elapse, but use a "big hammer"
- * approach to force the grace period to end quickly.  This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code.  In fact,
- * if you are using synchronize_rcu_bh_expedited() in a loop, please
- * restructure your code to batch your updates, and then use a single
- * synchronize_rcu_bh() instead.
- *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
- */
-static inline void synchronize_rcu_bh_expedited(void)
-{
-        synchronize_sched_expedited();
-}
-
 void rcu_barrier(void);
-void rcu_barrier_bh(void);
-void rcu_barrier_sched(void);
 bool rcu_eqs_special_set(int cpu);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
-unsigned long get_state_synchronize_sched(void);
-void cond_synchronize_sched(unsigned long oldstate);
 
 void rcu_idle_enter(void);
 void rcu_idle_exit(void);
@@ -93,7 +66,9 @@ void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
 bool rcu_is_watching(void);
+#ifndef CONFIG_PREEMPT
 void rcu_all_qs(void);
+#endif
 
 /* RCUtree hotplug events */
 int rcutree_prepare_cpu(unsigned int cpu);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 977cb57d7bc9..004ca21f7e80 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -571,12 +571,8 @@ union rcu_special {
         struct {
                 u8                      blocked;
                 u8                      need_qs;
-                u8                      exp_need_qs;
-
-                /* Otherwise the compiler can store garbage here: */
-                u8                      pad;
         } b; /* Bits. */
-        u32 s; /* Set of bits. */
+        u16 s; /* Set of bits. */
 };
 
 enum perf_event_task_context {
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 745d4ca4dd50..0ae91b3a7406 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -105,12 +105,13 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN2        2
 
 #define __SRCU_STRUCT_INIT(name, pcpu_name)                             \
-        {                                                               \
-                .sda = &pcpu_name,                                      \
-                .lock = __SPIN_LOCK_UNLOCKED(name.lock),                \
-                .srcu_gp_seq_needed = 0 - 1,                            \
-                __SRCU_DEP_MAP_INIT(name)                               \
-        }
+{                                                                       \
+        .sda = &pcpu_name,                                              \
+        .lock = __SPIN_LOCK_UNLOCKED(name.lock),                        \
+        .srcu_gp_seq_needed = -1UL,                                     \
+        .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0),         \
+        __SRCU_DEP_MAP_INIT(name)                                       \
+}
 
 /*
  * Define and initialize a srcu struct at build time.
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 61dfd93b6ee4..48fad21109fc 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -77,7 +77,7 @@ void torture_shutdown_absorb(const char *title);
 int torture_shutdown_init(int ssecs, void (*cleanup)(void));
 
 /* Task stuttering, which forces load/no-load transitions. */
-void stutter_wait(const char *title);
+bool stutter_wait(const char *title);
 int torture_stutter_init(int s);
 
 /* Initialization and cleanup. */
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index a8d07feff6a0..f0c4d10e614b 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -393,9 +393,8 @@ TRACE_EVENT(rcu_quiescent_state_report,
  * Tracepoint for quiescent states detected by force_quiescent_state().
  * These trace events include the type of RCU, the grace-period number
  * that was blocked by the CPU, the CPU itself, and the type of quiescent
- * state, which can be "dti" for dyntick-idle mode, "kick" when kicking
- * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the
- * CPU got a quiescent state via its rcu_qs_ctr.
+ * state, which can be "dti" for dyntick-idle mode or "kick" when kicking
+ * a CPU that has been in dyntick-idle mode for too long.
  */
 TRACE_EVENT(rcu_fqs,
 
@@ -705,20 +704,20 @@ TRACE_EVENT(rcu_torture_read,
 );
 
 /*
- * Tracepoint for _rcu_barrier() execution.  The string "s" describes
- * the _rcu_barrier phase:
- *      "Begin": _rcu_barrier() started.
- *      "EarlyExit": _rcu_barrier() piggybacked, thus early exit.
- *      "Inc1": _rcu_barrier() piggyback check counter incremented.
- *      "OfflineNoCB": _rcu_barrier() found callback on never-online CPU
- *      "OnlineNoCB": _rcu_barrier() found online no-CBs CPU.
- *      "OnlineQ": _rcu_barrier() found online CPU with callbacks.
- *      "OnlineNQ": _rcu_barrier() found online CPU, no callbacks.
+ * Tracepoint for rcu_barrier() execution.  The string "s" describes
+ * the rcu_barrier phase:
+ *      "Begin": rcu_barrier() started.
+ *      "EarlyExit": rcu_barrier() piggybacked, thus early exit.
+ *      "Inc1": rcu_barrier() piggyback check counter incremented.
+ *      "OfflineNoCB": rcu_barrier() found callback on never-online CPU
+ *      "OnlineNoCB": rcu_barrier() found online no-CBs CPU.
+ *      "OnlineQ": rcu_barrier() found online CPU with callbacks.
+ *      "OnlineNQ": rcu_barrier() found online CPU, no callbacks.
  *      "IRQ": An rcu_barrier_callback() callback posted on remote CPU.
  *      "IRQNQ": An rcu_barrier_callback() callback found no callbacks.
  *      "CB": An rcu_barrier_callback() invoked a callback, not the last.
  *      "LastCB": An rcu_barrier_callback() invoked the last callback.
- *      "Inc2": _rcu_barrier() piggyback check counter incremented.
+ *      "Inc2": rcu_barrier() piggyback check counter incremented.
  * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
  * is the count of remaining callbacks, and "done" is the piggybacking count.
  */