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

Pull the v3.5 RCU tree from Paul E. McKenney:

 1)	A set of improvements and fixes to the RCU_FAST_NO_HZ feature
	(with more on the way for 3.6).  Posted to LKML:
	https://lkml.org/lkml/2012/4/23/324 (commits 1-3 and 5),
	https://lkml.org/lkml/2012/4/16/611 (commit 4),
	https://lkml.org/lkml/2012/4/30/390 (commit 6), and
	https://lkml.org/lkml/2012/5/4/410 (commit 7, combined with
	the other commits for the convenience of the tester).

 2)	Changes to make rcu_barrier() avoid disrupting execution of CPUs
	that have no RCU callbacks.  Posted to LKML:
	https://lkml.org/lkml/2012/4/23/322.

 3)	A couple of commits that improve the efficiency of the interaction
	between preemptible RCU and the scheduler, these two being all
	that survived an abortive attempt to allow preemptible RCU's
	__rcu_read_lock() to be inlined.  The full set was posted to
	LKML at https://lkml.org/lkml/2012/4/14/143, and the first and
	third patches of that set remain.

 4)	Lai Jiangshan's algorithmic implementation of SRCU, which includes
	call_srcu() and srcu_barrier().  A major feature of this new
	implementation is that synchronize_srcu() no longer disturbs
	the execution of other CPUs.  This work is based on earlier
	implementations by Peter Zijlstra and Paul E. McKenney.  Posted to
	LKML: https://lkml.org/lkml/2012/2/22/82.

 5)	A number of miscellaneous bug fixes and improvements which were
	posted to LKML at: https://lkml.org/lkml/2012/4/23/353 with
	subsequent updates posted to LKML.

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

7 files changed, 106 insertions, 44 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index d079290843a..e0f0fab2041 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -30,6 +30,7 @@
  * This is only for internal list manipulation where we know
  * the prev/next entries already!
  */
+#ifndef CONFIG_DEBUG_LIST
 static inline void __list_add_rcu(struct list_head *new,
 		struct list_head *prev, struct list_head *next)
 {
@@ -38,6 +39,10 @@ static inline void __list_add_rcu(struct list_head *new,
 	rcu_assign_pointer(list_next_rcu(prev), new);
 	next->prev = new;
 }
+#else
+extern void __list_add_rcu(struct list_head *new,
+		struct list_head *prev, struct list_head *next);
+#endif
 
 /**
  * list_add_rcu - add a new entry to rcu-protected list
@@ -108,7 +113,7 @@ static inline void list_add_tail_rcu(struct list_head *new,
  */
 static inline void list_del_rcu(struct list_head *entry)
 {
-	__list_del(entry->prev, entry->next);
+	__list_del_entry(entry);
 	entry->prev = LIST_POISON2;
 }
 
@@ -228,18 +233,43 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	})
 
 /**
- * list_first_entry_rcu - get the first element from a list
+ * Where are list_empty_rcu() and list_first_entry_rcu()?
+ *
+ * Implementing those functions following their counterparts list_empty() and
+ * list_first_entry() is not advisable because they lead to subtle race
+ * conditions as the following snippet shows:
+ *
+ * if (!list_empty_rcu(mylist)) {
+ *	struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member);
+ *	do_something(bar);
+ * }
+ *
+ * The list may not be empty when list_empty_rcu checks it, but it may be when
+ * list_first_entry_rcu rereads the ->next pointer.
+ *
+ * Rereading the ->next pointer is not a problem for list_empty() and
+ * list_first_entry() because they would be protected by a lock that blocks
+ * writers.
+ *
+ * See list_first_or_null_rcu for an alternative.
+ */
+
+/**
+ * list_first_or_null_rcu - get the first element from a list
  * @ptr:        the list head to take the element from.
  * @type:       the type of the struct this is embedded in.
  * @member:     the name of the list_struct within the struct.
  *
- * Note, that list is expected to be not empty.
+ * Note that if the list is empty, it returns NULL.
  *
  * This primitive may safely run concurrently with the _rcu list-mutation
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
-#define list_first_entry_rcu(ptr, type, member) \
-	list_entry_rcu((ptr)->next, type, member)
+#define list_first_or_null_rcu(ptr, type, member) \
+	({struct list_head *__ptr = (ptr); \
+	  struct list_head __rcu *__next = list_next_rcu(__ptr); \
+	  likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+	})
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 20fb776a1d4..26d1a47591f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,12 +184,14 @@ 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);
 extern void rcu_idle_exit(void);
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
+extern void exit_rcu(void);
 
 /**
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
@@ -922,6 +924,21 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 	kfree_call_rcu(head, (rcu_callback)offset);
 }
 
+/*
+ * Does the specified offset indicate that the corresponding rcu_head
+ * structure can be handled by kfree_rcu()?
+ */
+#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
+
+/*
+ * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
+ */
+#define __kfree_rcu(head, offset) \
+	do { \
+		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
+		call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
+	} while (0)
+
 /**
  * kfree_rcu() - kfree an object after a grace period.
  * @ptr:	pointer to kfree
@@ -944,6 +961,9 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
  *
  * Note that the allowable offset might decrease in the future, for example,
  * to allow something like kmem_cache_free_rcu().
+ *
+ * The BUILD_BUG_ON check must not involve any function calls, hence the
+ * checks are done in macros here.
  */
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index e93df77176d..adb5e5a38ca 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -87,14 +87,6 @@ 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 void exit_rcu(void)
-{
-}
-
 static inline int rcu_needs_cpu(int cpu)
 {
 	return 0;
@@ -102,8 +94,6 @@ static inline int rcu_needs_cpu(int cpu)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
-void rcu_preempt_note_context_switch(void);
-extern void exit_rcu(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu)
@@ -116,7 +106,6 @@ static inline int rcu_needs_cpu(int cpu)
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
-	rcu_preempt_note_context_switch();
 }
 
 /*
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index e8ee5dd0854..3c6083cde4f 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -45,18 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch(cpu);
 }
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-extern void exit_rcu(void);
-
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-static inline void exit_rcu(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
-
 extern void synchronize_rcu_bh(void);
 extern void synchronize_sched_expedited(void);
 extern void synchronize_rcu_expedited(void);
@@ -98,13 +86,6 @@ extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
-/* A context switch is a grace period for RCU-sched and RCU-bh. */
-static inline int rcu_blocking_is_gp(void)
-{
-	might_sleep();  /* Check for RCU read-side critical section. */
-	return num_online_cpus() == 1;
-}
-
 extern void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 81a173c0897..8f3fd945070 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1905,12 +1905,22 @@ 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/linux/srcu.h b/include/linux/srcu.h
index d3d5fa54f25..55a5c52cbb2 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -29,26 +29,35 @@
 
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
+#include <linux/workqueue.h>
 
 struct srcu_struct_array {
-	int c[2];
+	unsigned long c[2];
+	unsigned long seq[2];
+};
+
+struct rcu_batch {
+	struct rcu_head *head, **tail;
 };
 
 struct srcu_struct {
-	int completed;
+	unsigned completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
-	struct mutex mutex;
+	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
+	bool running;
+	/* callbacks just queued */
+	struct rcu_batch batch_queue;
+	/* callbacks try to do the first check_zero */
+	struct rcu_batch batch_check0;
+	/* callbacks done with the first check_zero and the flip */
+	struct rcu_batch batch_check1;
+	struct rcu_batch batch_done;
+	struct delayed_work work;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
-#ifndef CONFIG_PREEMPT
-#define srcu_barrier() barrier()
-#else /* #ifndef CONFIG_PREEMPT */
-#define srcu_barrier()
-#endif /* #else #ifndef CONFIG_PREEMPT */
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int __init_srcu_struct(struct srcu_struct *sp, const char *name,
@@ -67,12 +76,33 @@ int init_srcu_struct(struct srcu_struct *sp);
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/**
+ * call_srcu() - Queue a callback for invocation after an SRCU grace period
+ * @sp: srcu_struct in queue the callback
+ * @head: structure to be used for queueing the SRCU callback.
+ * @func: function to be invoked after the SRCU grace period
+ *
+ * The callback function will be invoked some time after a full SRCU
+ * grace period elapses, in other words after all pre-existing SRCU
+ * read-side critical sections have completed.  However, the callback
+ * function might well execute concurrently with other SRCU read-side
+ * critical sections that started after call_srcu() was invoked.  SRCU
+ * read-side critical sections are delimited by srcu_read_lock() and
+ * srcu_read_unlock(), and may be nested.
+ *
+ * The callback will be invoked from process context, but must nevertheless
+ * be fast and must not block.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+		void (*func)(struct rcu_head *head));
+
 void cleanup_srcu_struct(struct srcu_struct *sp);
 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);
+void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 337099783f3..1480900c511 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -292,6 +292,8 @@ TRACE_EVENT(rcu_dyntick,
  *	"More callbacks": Still more callbacks, try again to clear them out.
  *	"Callbacks drained": All callbacks processed, off to dyntick idle!
  *	"Timer": Timer fired to cause CPU to continue processing callbacks.
+ *	"Demigrate": Timer fired on wrong CPU, woke up correct CPU.
+ *	"Cleanup after idle": Idle exited, timer canceled.
  */
 TRACE_EVENT(rcu_prep_idle,