Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull the RCU tree from Paul E. McKenney:

"The major features of this series are:

1.	Preventing latency spikes of more than 200 microseconds for
	kernels built with NR_CPUS=4096, which is reportedly becoming
	the default for some distros.  This is a first step, as it does
	not help with systems that actually -have- 4096 CPUs (work on
	this case is in progress, but is not yet ready for mainline).
	This category also includes improving concurrency of rcu_barrier(),
	placed here due to conflicts.  Posted to LKML at:
	https://lkml.org/lkml/2012/6/22/381.  Note that patches 18-22
	of that series have been defered to 3.7, as they have not yet
	proven themselves to be mainline-ready (and yes, these are the
	ones intended to get rid of RCU's latency spikes for systems
	that actually have 4096 CPUs).
2.	Updates to documentation and rcutorture fixes, the latter category
	including improvements to rcu_barrier() testing.  Posted to LKML at:
	http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/04094.html.
3.	Miscellaneous fixes posted to LKML at:
	https://lkml.org/lkml/2012/6/22/500, with the exception of the
	last commit, which was posted here:
	http://www.gossamer-threads.com/lists/linux/kernel/1561830
4.	RCU_FAST_NO_HZ fixes and improvements.  Posted to LKML at:
	http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/00006.html
	and http://www.gossamer-threads.com/lists/linux/kernel/1561833.
	The first four patches of the first series went into 3.5 to fix
	a regression.
5.	Code-style fixes.  These were posted to LKML at
	http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01180.html and
	http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01181.html.
"

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 76 insertions, 47 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 9e65eff6af3b..8a7476186990 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -168,8 +168,8 @@ extern struct cred init_cred;
 	.children	= LIST_HEAD_INIT(tsk.children),			\
 	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
 	.group_leader	= &tsk,						\
-	RCU_INIT_POINTER(.real_cred, &init_cred),			\
-	RCU_INIT_POINTER(.cred, &init_cred),				\
+	RCU_POINTER_INITIALIZER(real_cred, &init_cred),			\
+	RCU_POINTER_INITIALIZER(cred, &init_cred),			\
 	.comm		= INIT_TASK_COMM,				\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
diff --git a/include/linux/key.h b/include/linux/key.h
index 4cd22ed627ef..cef3b315ba7c 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -303,7 +303,9 @@ static inline bool key_is_instantiated(const struct key *key)
 				   rwsem_is_locked(&((struct key *)(KEY))->sem)))
 
 #define rcu_assign_keypointer(KEY, PAYLOAD)				\
-	(rcu_assign_pointer((KEY)->payload.rcudata, PAYLOAD))
+do {									\
+	rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD));		\
+} while (0)
 
 #ifdef CONFIG_SYSCTL
 extern ctl_table key_sysctls[];
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 26d1a47591f1..115ead2b5155 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -147,6 +147,7 @@ extern void synchronize_sched(void);
 
 extern void __rcu_read_lock(void);
 extern void __rcu_read_unlock(void);
+extern void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -184,7 +185,6 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
-extern void rcu_preempt_note_context_switch(void);
 extern void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 extern void rcu_idle_enter(void);
@@ -256,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP)
+extern int rcu_is_cpu_idle(void);
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */
+
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
 bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
@@ -267,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
-#ifdef CONFIG_PROVE_RCU
-extern int rcu_is_cpu_idle(void);
-#else /* !CONFIG_PROVE_RCU */
-static inline int rcu_is_cpu_idle(void)
-{
-	return 0;
-}
-#endif /* else !CONFIG_PROVE_RCU */
-
 static inline void rcu_lock_acquire(struct lockdep_map *map)
 {
 	lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
@@ -432,8 +427,7 @@ extern int rcu_my_thread_group_empty(void);
 static inline void rcu_preempt_sleep_check(void)
 {
 	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
-			   "Illegal context switch in RCU read-side "
-			   "critical section");
+			   "Illegal context switch in RCU read-side critical section");
 }
 #else /* #ifdef CONFIG_PROVE_RCU */
 static inline void rcu_preempt_sleep_check(void)
@@ -514,10 +508,10 @@ static inline void rcu_preempt_sleep_check(void)
 		(_________p1); \
 	})
 #define __rcu_assign_pointer(p, v, space) \
-	({ \
+	do { \
 		smp_wmb(); \
 		(p) = (typeof(*v) __force space *)(v); \
-	})
+	} while (0)
 
 
 /**
@@ -852,7 +846,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  *
  * Assigns the specified value to the specified RCU-protected
  * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.  Returns the value assigned.
+ * any prior initialization.
  *
  * Inserts memory barriers on architectures that require them
  * (which is most of them), and also prevents the compiler from
@@ -904,25 +898,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * the reader-accessible portions of the linked structure.
  */
 #define RCU_INIT_POINTER(p, v) \
-		p = (typeof(*v) __force __rcu *)(v)
-
-static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
-{
-	return offset < 4096;
-}
-
-static __always_inline
-void __kfree_rcu(struct rcu_head *head, unsigned long offset)
-{
-	typedef void (*rcu_callback)(struct rcu_head *);
-
-	BUILD_BUG_ON(!__builtin_constant_p(offset));
-
-	/* See the kfree_rcu() header comment. */
-	BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+	do { \
+		p = (typeof(*v) __force __rcu *)(v); \
+	} while (0)
 
-	kfree_call_rcu(head, (rcu_callback)offset);
-}
+/**
+ * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
+ *
+ * GCC-style initialization for an RCU-protected pointer in a structure field.
+ */
+#define RCU_POINTER_INITIALIZER(p, v) \
+		.p = (typeof(*v) __force __rcu *)(v)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
@@ -936,7 +922,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 #define __kfree_rcu(head, offset) \
 	do { \
 		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
-		call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
+		kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
 	} while (0)
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 854dc4c5c271..4e56a9c69a35 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -87,6 +87,10 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 #ifdef CONFIG_TINY_RCU
 
+static inline void rcu_preempt_note_context_switch(void)
+{
+}
+
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
@@ -95,6 +99,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
+void rcu_preempt_note_context_switch(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
@@ -108,6 +113,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch();
 }
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4059c0f33f07..06a4c5f4f55c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1871,22 +1871,12 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-	if (prev->rcu_read_lock_nesting != 0)
-		rcu_preempt_note_context_switch();
-}
-
 #else
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
 }
 
-static inline void rcu_switch_from(struct task_struct *prev)
-{
-}
-
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d274734b2aa4..5bde94d8585b 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -541,6 +541,50 @@ TRACE_EVENT(rcu_torture_read,
 		  __entry->rcutorturename, __entry->rhp)
 );
 
+/*
+ * Tracepoint for _rcu_barrier() execution.  The string "s" describes
+ * the _rcu_barrier phase:
+ *	"Begin": rcu_barrier_callback() started.
+ *	"Check": rcu_barrier_callback() checking for piggybacking.
+ *	"EarlyExit": rcu_barrier_callback() piggybacked, thus early exit.
+ *	"Inc1": rcu_barrier_callback() piggyback check counter incremented.
+ *	"Offline": rcu_barrier_callback() found offline CPU
+ *	"OnlineQ": rcu_barrier_callback() found online CPU with callbacks.
+ *	"OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks.
+ *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
+ *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
+ *	"LastCB": An rcu_barrier_callback() invoked the last callback.
+ *	"Inc2": rcu_barrier_callback() 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.
+ */
+TRACE_EVENT(rcu_barrier,
+
+	TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done),
+
+	TP_ARGS(rcuname, s, cpu, cnt, done),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(char *, s)
+		__field(int, cpu)
+		__field(int, cnt)
+		__field(unsigned long, done)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->s = s;
+		__entry->cpu = cpu;
+		__entry->cnt = cnt;
+		__entry->done = done;
+	),
+
+	TP_printk("%s %s cpu %d remaining %d # %lu",
+		  __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt,
+		  __entry->done)
+);
+
 #else /* #ifdef CONFIG_RCU_TRACE */
 
 #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
@@ -564,6 +608,7 @@ TRACE_EVENT(rcu_torture_read,
 #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
 	do { } while (0)
 #define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */