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

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  rcu: Move propagation of ->completed from rcu_start_gp() to rcu_report_qs_rsp()
  rcu: Remove rcu_needs_cpu_flush() to avoid false quiescent states
  rcu: Wire up RCU_BOOST_PRIO for rcutree
  rcu: Make rcu_torture_boost() exit loops at end of test
  rcu: Make rcu_torture_fqs() exit loops at end of test
  rcu: Permit rt_mutex_unlock() with irqs disabled
  rcu: Avoid having just-onlined CPU resched itself when RCU is idle
  rcu: Suppress NMI backtraces when stall ends before dump
  rcu: Prohibit grace periods during early boot
  rcu: Simplify unboosting checks
  rcu: Prevent early boot set_need_resched() from __rcu_pending()
  rcu: Dump local stack if cannot dump all CPUs' stacks
  rcu: Move __rcu_read_unlock()'s barrier() within if-statement
  rcu: Improve rcu_assign_pointer() and RCU_INIT_POINTER() documentation
  rcu: Make rcu_assign_pointer() unconditionally insert a memory barrier
  rcu: Make rcu_implicit_dynticks_qs() locals be correct size
  rcu: Eliminate in_irq() checks in rcu_enter_nohz()
  nohz: Remove nohz_cpu_mask
  rcu: Document interpretation of RCU-lockdep splats
  rcu: Allow rcutorture's stat_interval parameter to be changed at runtime
  ...

7 files changed, 628 insertions, 169 deletions

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index ef820a3c378..b6a56e37284 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -548,7 +548,7 @@ do {									\
 #endif
 
 #ifdef CONFIG_PROVE_RCU
-extern void lockdep_rcu_dereference(const char *file, const int line);
+void lockdep_rcu_suspicious(const char *file, const int line, const char *s);
 #endif
 
 #endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 8f4f881a0ad..2cf4226ade7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -33,6 +33,7 @@
 #ifndef __LINUX_RCUPDATE_H
 #define __LINUX_RCUPDATE_H
 
+#include <linux/types.h>
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
@@ -64,32 +65,74 @@ static inline void rcutorture_record_progress(unsigned long vernum)
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
 
+/* Exported common interfaces */
+
+#ifdef CONFIG_PREEMPT_RCU
+
 /**
- * struct rcu_head - callback structure for use with RCU
- * @next: next update requests in a list
- * @func: actual update function to call after the grace period.
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.  However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.  RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
  */
-struct rcu_head {
-	struct rcu_head *next;
-	void (*func)(struct rcu_head *head);
-};
+extern void call_rcu(struct rcu_head *head,
+			      void (*func)(struct rcu_head *head));
 
-/* Exported common interfaces */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+/* In classic RCU, call_rcu() is just call_rcu_sched(). */
+#define	call_rcu	call_rcu_sched
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
+/**
+ * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_bh() assumes
+ * that the read-side critical sections end on completion of a softirq
+ * handler. This means that read-side critical sections in process
+ * context must not be interrupted by softirqs. This interface is to be
+ * used when most of the read-side critical sections are in softirq context.
+ * RCU read-side critical sections are delimited by :
+ *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
+ *  OR
+ *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *  These may be nested.
+ */
+extern void call_rcu_bh(struct rcu_head *head,
+			void (*func)(struct rcu_head *head));
+
+/**
+ * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_sched() assumes
+ * that the read-side critical sections end on enabling of preemption
+ * or on voluntary preemption.
+ * RCU read-side critical sections are delimited by :
+ *  - rcu_read_lock_sched() and  rcu_read_unlock_sched(),
+ *  OR
+ *  anything that disables preemption.
+ *  These may be nested.
+ */
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
-extern void synchronize_sched(void);
-extern void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
-
-static inline void __rcu_read_lock_bh(void)
-{
-	local_bh_disable();
-}
 
-static inline void __rcu_read_unlock_bh(void)
-{
-	local_bh_enable();
-}
+extern void synchronize_sched(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -152,6 +195,15 @@ static inline void rcu_exit_nohz(void)
 
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
+/*
+ * Infrastructure to implement the synchronize_() primitives in
+ * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
+ */
+
+typedef void call_rcu_func_t(struct rcu_head *head,
+			     void (*func)(struct rcu_head *head));
+void wait_rcu_gp(call_rcu_func_t crf);
+
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
 #elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
@@ -297,19 +349,31 @@ extern int rcu_my_thread_group_empty(void);
 /**
  * rcu_lockdep_assert - emit lockdep splat if specified condition not met
  * @c: condition to check
+ * @s: informative message
  */
-#define rcu_lockdep_assert(c)						\
+#define rcu_lockdep_assert(c, s)					\
 	do {								\
 		static bool __warned;					\
 		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
 			__warned = true;				\
-			lockdep_rcu_dereference(__FILE__, __LINE__);	\
+			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
 		}							\
 	} while (0)
 
+#define rcu_sleep_check()						\
+	do {								\
+		rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),	\
+				   "Illegal context switch in RCU-bh"	\
+				   " read-side critical section");	\
+		rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),	\
+				   "Illegal context switch in RCU-sched"\
+				   " read-side critical section");	\
+	} while (0)
+
 #else /* #ifdef CONFIG_PROVE_RCU */
 
-#define rcu_lockdep_assert(c) do { } while (0)
+#define rcu_lockdep_assert(c, s) do { } while (0)
+#define rcu_sleep_check() do { } while (0)
 
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
 
@@ -338,14 +402,16 @@ extern int rcu_my_thread_group_empty(void);
 #define __rcu_dereference_check(p, c, space) \
 	({ \
 		typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
-		rcu_lockdep_assert(c); \
+		rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \
+				      " usage"); \
 		rcu_dereference_sparse(p, space); \
 		smp_read_barrier_depends(); \
 		((typeof(*p) __force __kernel *)(_________p1)); \
 	})
 #define __rcu_dereference_protected(p, c, space) \
 	({ \
-		rcu_lockdep_assert(c); \
+		rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \
+				      " usage"); \
 		rcu_dereference_sparse(p, space); \
 		((typeof(*p) __force __kernel *)(p)); \
 	})
@@ -359,15 +425,15 @@ extern int rcu_my_thread_group_empty(void);
 #define __rcu_dereference_index_check(p, c) \
 	({ \
 		typeof(p) _________p1 = ACCESS_ONCE(p); \
-		rcu_lockdep_assert(c); \
+		rcu_lockdep_assert(c, \
+				   "suspicious rcu_dereference_index_check()" \
+				   " usage"); \
 		smp_read_barrier_depends(); \
 		(_________p1); \
 	})
 #define __rcu_assign_pointer(p, v, space) \
 	({ \
-		if (!__builtin_constant_p(v) || \
-		    ((v) != NULL)) \
-			smp_wmb(); \
+		smp_wmb(); \
 		(p) = (typeof(*v) __force space *)(v); \
 	})
 
@@ -500,26 +566,6 @@ extern int rcu_my_thread_group_empty(void);
 #define rcu_dereference_protected(p, c) \
 	__rcu_dereference_protected((p), (c), __rcu)
 
-/**
- * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * This is the RCU-bh counterpart to rcu_dereference_protected().
- */
-#define rcu_dereference_bh_protected(p, c) \
-	__rcu_dereference_protected((p), (c), __rcu)
-
-/**
- * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * This is the RCU-sched counterpart to rcu_dereference_protected().
- */
-#define rcu_dereference_sched_protected(p, c) \
-	__rcu_dereference_protected((p), (c), __rcu)
-
 
 /**
  * rcu_dereference() - fetch RCU-protected pointer for dereferencing
@@ -630,7 +676,7 @@ static inline void rcu_read_unlock(void)
  */
 static inline void rcu_read_lock_bh(void)
 {
-	__rcu_read_lock_bh();
+	local_bh_disable();
 	__acquire(RCU_BH);
 	rcu_read_acquire_bh();
 }
@@ -644,7 +690,7 @@ static inline void rcu_read_unlock_bh(void)
 {
 	rcu_read_release_bh();
 	__release(RCU_BH);
-	__rcu_read_unlock_bh();
+	local_bh_enable();
 }
 
 /**
@@ -698,11 +744,18 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * any prior initialization.  Returns the value assigned.
  *
  * Inserts memory barriers on architectures that require them
- * (pretty much all of them other than x86), and also prevents
- * the compiler from reordering the code that initializes the
- * structure after the pointer assignment.  More importantly, this
- * call documents which pointers will be dereferenced by RCU read-side
- * code.
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
  */
 #define rcu_assign_pointer(p, v) \
 	__rcu_assign_pointer((p), (v), __rcu)
@@ -710,105 +763,38 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 /**
  * RCU_INIT_POINTER() - initialize an RCU protected pointer
  *
- * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep
- * splats.
+ * Initialize an RCU-protected pointer in special cases where readers
+ * do not need ordering constraints on the CPU or the compiler.  These
+ * special cases are:
+ *
+ * 1.	This use of RCU_INIT_POINTER() is NULLing out the pointer -or-
+ * 2.	The caller has taken whatever steps are required to prevent
+ *	RCU readers from concurrently accessing this pointer -or-
+ * 3.	The referenced data structure has already been exposed to
+ *	readers either at compile time or via rcu_assign_pointer() -and-
+ *	a.	You have not made -any- reader-visible changes to
+ *		this structure since then -or-
+ *	b.	It is OK for readers accessing this structure from its
+ *		new location to see the old state of the structure.  (For
+ *		example, the changes were to statistical counters or to
+ *		other state where exact synchronization is not required.)
+ *
+ * Failure to follow these rules governing use of RCU_INIT_POINTER() will
+ * result in impossible-to-diagnose memory corruption.  As in the structures
+ * will look OK in crash dumps, but any concurrent RCU readers might
+ * see pre-initialized values of the referenced data structure.  So
+ * please be very careful how you use RCU_INIT_POINTER()!!!
+ *
+ * If you are creating an RCU-protected linked structure that is accessed
+ * by a single external-to-structure RCU-protected pointer, then you may
+ * use RCU_INIT_POINTER() to initialize the internal RCU-protected
+ * pointers, but you must use rcu_assign_pointer() to initialize the
+ * external-to-structure pointer -after- you have completely initialized
+ * the reader-accessible portions of the linked structure.
  */
 #define RCU_INIT_POINTER(p, v) \
 		p = (typeof(*v) __force __rcu *)(v)
 
-/* Infrastructure to implement the synchronize_() primitives. */
-
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
-};
-
-extern void wakeme_after_rcu(struct rcu_head  *head);
-
-#ifdef CONFIG_PREEMPT_RCU
-
-/**
- * call_rcu() - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all pre-existing RCU read-side
- * critical sections have completed.  However, the callback function
- * might well execute concurrently with RCU read-side critical sections
- * that started after call_rcu() was invoked.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-extern void call_rcu(struct rcu_head *head,
-			      void (*func)(struct rcu_head *head));
-
-#else /* #ifdef CONFIG_PREEMPT_RCU */
-
-/* In classic RCU, call_rcu() is just call_rcu_sched(). */
-#define	call_rcu	call_rcu_sched
-
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
-/**
- * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_bh() assumes
- * that the read-side critical sections end on completion of a softirq
- * handler. This means that read-side critical sections in process
- * context must not be interrupted by softirqs. This interface is to be
- * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
- */
-extern void call_rcu_bh(struct rcu_head *head,
-			void (*func)(struct rcu_head *head));
-
-/*
- * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
- * by call_rcu() and rcu callback execution, and are therefore not part of the
- * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
- */
-
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-# define STATE_RCU_HEAD_READY	0
-# define STATE_RCU_HEAD_QUEUED	1
-
-extern struct debug_obj_descr rcuhead_debug_descr;
-
-static inline void debug_rcu_head_queue(struct rcu_head *head)
-{
-	WARN_ON_ONCE((unsigned long)head & 0x3);
-	debug_object_activate(head, &rcuhead_debug_descr);
-	debug_object_active_state(head, &rcuhead_debug_descr,
-				  STATE_RCU_HEAD_READY,
-				  STATE_RCU_HEAD_QUEUED);
-}
-
-static inline void debug_rcu_head_unqueue(struct rcu_head *head)
-{
-	debug_object_active_state(head, &rcuhead_debug_descr,
-				  STATE_RCU_HEAD_QUEUED,
-				  STATE_RCU_HEAD_READY);
-	debug_object_deactivate(head, &rcuhead_debug_descr);
-}
-#else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-static inline void debug_rcu_head_queue(struct rcu_head *head)
-{
-}
-
-static inline void debug_rcu_head_unqueue(struct rcu_head *head)
-{
-}
-#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-
 static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
 {
 	return offset < 4096;
@@ -827,18 +813,6 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 	call_rcu(head, (rcu_callback)offset);
 }
 
-extern void kfree(const void *);
-
-static inline void __rcu_reclaim(struct rcu_head *head)
-{
-	unsigned long offset = (unsigned long)head->func;
-
-	if (__is_kfree_rcu_offset(offset))
-		kfree((void *)head - offset);
-	else
-		head->func(head);
-}
-
 /**
  * kfree_rcu() - kfree an object after a grace period.
  * @ptr:	pointer to kfree
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 52b3e0281fd..00b7a5e493d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,9 +27,23 @@
 
 #include <linux/cache.h>
 
+#ifdef CONFIG_RCU_BOOST
 static inline void rcu_init(void)
 {
 }
+#else /* #ifdef CONFIG_RCU_BOOST */
+void rcu_init(void);
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+static inline void rcu_barrier_bh(void)
+{
+	wait_rcu_gp(call_rcu_bh);
+}
+
+static inline void rcu_barrier_sched(void)
+{
+	wait_rcu_gp(call_rcu_sched);
+}
 
 #ifdef CONFIG_TINY_RCU
 
@@ -45,9 +59,13 @@ static inline void rcu_barrier(void)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
-void rcu_barrier(void);
 void synchronize_rcu_expedited(void);
 
+static inline void rcu_barrier(void)
+{
+	wait_rcu_gp(call_rcu);
+}
+
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 static inline void synchronize_rcu_bh(void)
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index e65d06634dd..67458468f1a 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -67,6 +67,8 @@ static inline void synchronize_rcu_bh_expedited(void)
 }
 
 extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1be699dd32a..ede8a6585e3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -270,7 +270,6 @@ extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern int runqueue_is_locked(int cpu);
 
-extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern void select_nohz_load_balancer(int stop_tick);
 extern int get_nohz_timer_target(void);
@@ -1260,9 +1259,6 @@ struct task_struct {
 #ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
 	char rcu_read_unlock_special;
-#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU)
-	int rcu_boosted;
-#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */
 	struct list_head rcu_node_entry;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TREE_PREEMPT_RCU
diff --git a/include/linux/types.h b/include/linux/types.h
index 176da8c1fbb..57a97234bec 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -238,6 +238,16 @@ struct ustat {
 	char			f_fpack[6];
 };
 
+/**
+ * struct rcu_head - callback structure for use with RCU
+ * @next: next update requests in a list
+ * @func: actual update function to call after the grace period.
+ */
+struct rcu_head {
+	struct rcu_head *next;
+	void (*func)(struct rcu_head *head);
+};
+
 #endif	/* __KERNEL__ */
 #endif /*  __ASSEMBLY__ */
 #endif /* _LINUX_TYPES_H */
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
new file mode 100644
index 00000000000..669fbd62ec2
--- /dev/null
+++ b/include/trace/events/rcu.h
@@ -0,0 +1,459 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rcu
+
+#if !defined(_TRACE_RCU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RCU_H
+
+#include <linux/tracepoint.h>
+
+/*
+ * Tracepoint for start/end markers used for utilization calculations.
+ * By convention, the string is of the following forms:
+ *
+ * "Start <activity>" -- Mark the start of the specified activity,
+ *			 such as "context switch".  Nesting is permitted.
+ * "End <activity>" -- Mark the end of the specified activity.
+ *
+ * An "@" character within "<activity>" is a comment character: Data
+ * reduction scripts will ignore the "@" and the remainder of the line.
+ */
+TRACE_EVENT(rcu_utilization,
+
+	TP_PROTO(char *s),
+
+	TP_ARGS(s),
+
+	TP_STRUCT__entry(
+		__field(char *, s)
+	),
+
+	TP_fast_assign(
+		__entry->s = s;
+	),
+
+	TP_printk("%s", __entry->s)
+);
+
+#ifdef CONFIG_RCU_TRACE
+
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+
+/*
+ * Tracepoint for grace-period events: starting and ending a grace
+ * period ("start" and "end", respectively), a CPU noting the start
+ * of a new grace period or the end of an old grace period ("cpustart"
+ * and "cpuend", respectively), a CPU passing through a quiescent
+ * state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
+ * and "cpuofl", respectively), and a CPU being kicked for being too
+ * long in dyntick-idle mode ("kick").
+ */
+TRACE_EVENT(rcu_grace_period,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent),
+
+	TP_ARGS(rcuname, gpnum, gpevent),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(char *, gpevent)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->gpevent = gpevent;
+	),
+
+	TP_printk("%s %lu %s",
+		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
+);
+
+/*
+ * Tracepoint for grace-period-initialization events.  These are
+ * distinguished by the type of RCU, the new grace-period number, the
+ * rcu_node structure level, the starting and ending CPU covered by the
+ * rcu_node structure, and the mask of CPUs that will be waited for.
+ * All but the type of RCU are extracted from the rcu_node structure.
+ */
+TRACE_EVENT(rcu_grace_period_init,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum, u8 level,
+		 int grplo, int grphi, unsigned long qsmask),
+
+	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(u8, level)
+		__field(int, grplo)
+		__field(int, grphi)
+		__field(unsigned long, qsmask)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->level = level;
+		__entry->grplo = grplo;
+		__entry->grphi = grphi;
+		__entry->qsmask = qsmask;
+	),
+
+	TP_printk("%s %lu %u %d %d %lx",
+		  __entry->rcuname, __entry->gpnum, __entry->level,
+		  __entry->grplo, __entry->grphi, __entry->qsmask)
+);
+
+/*
+ * Tracepoint for tasks blocking within preemptible-RCU read-side
+ * critical sections.  Track the type of RCU (which one day might
+ * include SRCU), the grace-period number that the task is blocking
+ * (the current or the next), and the task's PID.
+ */
+TRACE_EVENT(rcu_preempt_task,
+
+	TP_PROTO(char *rcuname, int pid, unsigned long gpnum),
+
+	TP_ARGS(rcuname, pid, gpnum),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->pid = pid;
+	),
+
+	TP_printk("%s %lu %d",
+		  __entry->rcuname, __entry->gpnum, __entry->pid)
+);
+
+/*
+ * Tracepoint for tasks that blocked within a given preemptible-RCU
+ * read-side critical section exiting that critical section.  Track the
+ * type of RCU (which one day might include SRCU) and the task's PID.
+ */
+TRACE_EVENT(rcu_unlock_preempted_task,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum, int pid),
+
+	TP_ARGS(rcuname, gpnum, pid),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(int, pid)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->pid = pid;
+	),
+
+	TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+);
+
+/*
+ * Tracepoint for quiescent-state-reporting events.  These are
+ * distinguished by the type of RCU, the grace-period number, the
+ * mask of quiescent lower-level entities, the rcu_node structure level,
+ * the starting and ending CPU covered by the rcu_node structure, and
+ * whether there are any blocked tasks blocking the current grace period.
+ * All but the type of RCU are extracted from the rcu_node structure.
+ */
+TRACE_EVENT(rcu_quiescent_state_report,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum,
+		 unsigned long mask, unsigned long qsmask,
+		 u8 level, int grplo, int grphi, int gp_tasks),
+
+	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(unsigned long, mask)
+		__field(unsigned long, qsmask)
+		__field(u8, level)
+		__field(int, grplo)
+		__field(int, grphi)
+		__field(u8, gp_tasks)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->mask = mask;
+		__entry->qsmask = qsmask;
+		__entry->level = level;
+		__entry->grplo = grplo;
+		__entry->grphi = grphi;
+		__entry->gp_tasks = gp_tasks;
+	),
+
+	TP_printk("%s %lu %lx>%lx %u %d %d %u",
+		  __entry->rcuname, __entry->gpnum,
+		  __entry->mask, __entry->qsmask, __entry->level,
+		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
+);
+
+/*
+ * 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, "ofl" for CPU offline,
+ * or "kick" when kicking a CPU that has been in dyntick-idle mode for
+ * too long.
+ */
+TRACE_EVENT(rcu_fqs,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum, int cpu, char *qsevent),
+
+	TP_ARGS(rcuname, gpnum, cpu, qsevent),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(int, cpu)
+		__field(char *, qsevent)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->cpu = cpu;
+		__entry->qsevent = qsevent;
+	),
+
+	TP_printk("%s %lu %d %s",
+		  __entry->rcuname, __entry->gpnum,
+		  __entry->cpu, __entry->qsevent)
+);
+
+#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+
+/*
+ * Tracepoint for dyntick-idle entry/exit events.  These take a string
+ * as argument: "Start" for entering dyntick-idle mode and "End" for
+ * leaving it.
+ */
+TRACE_EVENT(rcu_dyntick,
+
+	TP_PROTO(char *polarity),
+
+	TP_ARGS(polarity),
+
+	TP_STRUCT__entry(
+		__field(char *, polarity)
+	),
+
+	TP_fast_assign(
+		__entry->polarity = polarity;
+	),
+
+	TP_printk("%s", __entry->polarity)
+);
+
+/*
+ * Tracepoint for the registration of a single RCU callback function.
+ * The first argument is the type of RCU, the second argument is
+ * a pointer to the RCU callback itself, and the third element is the
+ * new RCU callback queue length for the current CPU.
+ */
+TRACE_EVENT(rcu_callback,
+
+	TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen),
+
+	TP_ARGS(rcuname, rhp, qlen),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(void *, rhp)
+		__field(void *, func)
+		__field(long, qlen)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->rhp = rhp;
+		__entry->func = rhp->func;
+		__entry->qlen = qlen;
+	),
+
+	TP_printk("%s rhp=%p func=%pf %ld",
+		  __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen)
+);
+
+/*
+ * Tracepoint for the registration of a single RCU callback of the special
+ * kfree() form.  The first argument is the RCU type, the second argument
+ * is a pointer to the RCU callback, the third argument is the offset
+ * of the callback within the enclosing RCU-protected data structure,
+ * and the fourth argument is the new RCU callback queue length for the
+ * current CPU.
+ */
+TRACE_EVENT(rcu_kfree_callback,
+
+	TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset,
+		 long qlen),
+
+	TP_ARGS(rcuname, rhp, offset, qlen),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(void *, rhp)
+		__field(unsigned long, offset)
+		__field(long, qlen)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->rhp = rhp;
+		__entry->offset = offset;
+		__entry->qlen = qlen;
+	),
+
+	TP_printk("%s rhp=%p func=%ld %ld",
+		  __entry->rcuname, __entry->rhp, __entry->offset,
+		  __entry->qlen)
+);
+
+/*
+ * Tracepoint for marking the beginning rcu_do_batch, performed to start
+ * RCU callback invocation.  The first argument is the RCU flavor,
+ * the second is the total number of callbacks (including those that
+ * are not yet ready to be invoked), and the third argument is the
+ * current RCU-callback batch limit.
+ */
+TRACE_EVENT(rcu_batch_start,
+
+	TP_PROTO(char *rcuname, long qlen, int blimit),
+
+	TP_ARGS(rcuname, qlen, blimit),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(long, qlen)
+		__field(int, blimit)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->qlen = qlen;
+		__entry->blimit = blimit;
+	),
+
+	TP_printk("%s CBs=%ld bl=%d",
+		  __entry->rcuname, __entry->qlen, __entry->blimit)
+);
+
+/*
+ * Tracepoint for the invocation of a single RCU callback function.
+ * The first argument is the type of RCU, and the second argument is
+ * a pointer to the RCU callback itself.
+ */
+TRACE_EVENT(rcu_invoke_callback,
+
+	TP_PROTO(char *rcuname, struct rcu_head *rhp),
+
+	TP_ARGS(rcuname, rhp),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(void *, rhp)
+		__field(void *, func)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->rhp = rhp;
+		__entry->func = rhp->func;
+	),
+
+	TP_printk("%s rhp=%p func=%pf",
+		  __entry->rcuname, __entry->rhp, __entry->func)
+);
+
+/*
+ * Tracepoint for the invocation of a single RCU callback of the special
+ * kfree() form.  The first argument is the RCU flavor, the second
+ * argument is a pointer to the RCU callback, and the third argument
+ * is the offset of the callback within the enclosing RCU-protected
+ * data structure.
+ */
+TRACE_EVENT(rcu_invoke_kfree_callback,
+
+	TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset),
+
+	TP_ARGS(rcuname, rhp, offset),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(void *, rhp)
+		__field(unsigned long, offset)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->rhp = rhp;
+		__entry->offset	= offset;
+	),
+
+	TP_printk("%s rhp=%p func=%ld",
+		  __entry->rcuname, __entry->rhp, __entry->offset)
+);
+
+/*
+ * Tracepoint for exiting rcu_do_batch after RCU callbacks have been
+ * invoked.  The first argument is the name of the RCU flavor and
+ * the second argument is number of callbacks actually invoked.
+ */
+TRACE_EVENT(rcu_batch_end,
+
+	TP_PROTO(char *rcuname, int callbacks_invoked),
+
+	TP_ARGS(rcuname, callbacks_invoked),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(int, callbacks_invoked)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->callbacks_invoked = callbacks_invoked;
+	),
+
+	TP_printk("%s CBs-invoked=%d",
+		  __entry->rcuname, __entry->callbacks_invoked)
+);
+
+#else /* #ifdef CONFIG_RCU_TRACE */
+
+#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
+#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0)
+#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
+#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0)
+#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
+#define trace_rcu_dyntick(polarity) do { } while (0)
+#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0)
+#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0)
+#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0)
+#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
+#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
+#define trace_rcu_batch_end(rcuname, callbacks_invoked) do { } while (0)
+
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+#endif /* _TRACE_RCU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>