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 RCU changes in this cycle are:

   - Dynticks updates, consolidating open-coded counter accesses into a
     well-defined API

   - SRCU updates: Simplify algorithm, add formal verification

   - Documentation updates

   - Miscellaneous fixes

   - Torture-test updates

  Most of the diffstat comes from the relatively large documentation
  update"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  srcu: Reduce probability of SRCU ->unlock_count[] counter overflow
  rcutorture: Add CBMC-based formal verification for SRCU
  srcu: Force full grace-period ordering
  srcu: Implement more-efficient reader counts
  rcu: Adjust FQS offline checks for exact online-CPU detection
  rcu: Check cond_resched_rcu_qs() state less often to reduce GP overhead
  rcu: Abstract extended quiescent state determination
  rcu: Abstract dynticks extended quiescent state enter/exit operations
  rcu: Add lockdep checks to synchronous expedited primitives
  rcu: Eliminate unused expedited_normal counter
  llist: Clarify comments about when locking is needed
  rcu: Fix comment in rcu_organize_nocb_kthreads()
  rcu: Enable RCU tracepoints by default to aid in debugging
  rcu: Make rcu_cpu_starting() use its "cpu" argument
  rcu: Add comment headers to expedited-grace-period counter functions
  rcu: Don't wake rcuc/X kthreads on NOCB CPUs
  rcu: Re-enable TASKS_RCU for User Mode Linux
  rcu: Once again use NMI-based stack traces in stall warnings
  rcu: Remove short-term CPU kicking
  rcu: Add long-term CPU kicking
  ...

5 files changed, 49 insertions, 26 deletions

diff --git a/include/linux/llist.h b/include/linux/llist.h
index fd4ca0b4fe0f..171baa90f6f6 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -3,28 +3,33 @@
 /*
  * Lock-less NULL terminated single linked list
  *
- * If there are multiple producers and multiple consumers, llist_add
- * can be used in producers and llist_del_all can be used in
- * consumers.  They can work simultaneously without lock.  But
- * llist_del_first can not be used here.  Because llist_del_first
- * depends on list->first->next does not changed if list->first is not
- * changed during its operation, but llist_del_first, llist_add,
- * llist_add (or llist_del_all, llist_add, llist_add) sequence in
- * another consumer may violate that.
- *
- * If there are multiple producers and one consumer, llist_add can be
- * used in producers and llist_del_all or llist_del_first can be used
- * in the consumer.
- *
- * This can be summarized as follow:
+ * Cases where locking is not needed:
+ * If there are multiple producers and multiple consumers, llist_add can be
+ * used in producers and llist_del_all can be used in consumers simultaneously
+ * without locking. Also a single consumer can use llist_del_first while
+ * multiple producers simultaneously use llist_add, without any locking.
+ *
+ * Cases where locking is needed:
+ * If we have multiple consumers with llist_del_first used in one consumer, and
+ * llist_del_first or llist_del_all used in other consumers, then a lock is
+ * needed.  This is because llist_del_first depends on list->first->next not
+ * changing, but without lock protection, there's no way to be sure about that
+ * if a preemption happens in the middle of the delete operation and on being
+ * preempted back, the list->first is the same as before causing the cmpxchg in
+ * llist_del_first to succeed. For example, while a llist_del_first operation
+ * is in progress in one consumer, then a llist_del_first, llist_add,
+ * llist_add (or llist_del_all, llist_add, llist_add) sequence in another
+ * consumer may cause violations.
+ *
+ * This can be summarized as follows:
  *
  *           |   add    | del_first |  del_all
  * add       |    -     |     -     |     -
  * del_first |          |     L     |     L
  * del_all   |          |           |     -
  *
- * Where "-" stands for no lock is needed, while "L" stands for lock
- * is needed.
+ * Where, a particular row's operation can happen concurrently with a column's
+ * operation, with "-" being no lock needed, while "L" being lock is needed.
  *
  * The list entries deleted via llist_del_all can be traversed with
  * traversing function such as llist_for_each etc.  But the list
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 01f71e1d2e94..6ade6a52d9d4 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1161,5 +1161,17 @@ do { \
 		ftrace_dump(oops_dump_mode); \
 } while (0)
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair acts as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifdef CONFIG_PPC
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+#else /* #ifdef CONFIG_PPC */
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif /* #else #ifdef CONFIG_PPC */
+
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ac81e4063b40..4f9b2fa2173d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,6 +27,12 @@
 
 #include <linux/cache.h>
 
+struct rcu_dynticks;
+static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+	return 0;
+}
+
 static inline unsigned long get_state_synchronize_rcu(void)
 {
 	return 0;
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index dc8eb63c6568..a598cf3ac70c 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -33,9 +33,9 @@
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-struct srcu_struct_array {
-	unsigned long c[2];
-	unsigned long seq[2];
+struct srcu_array {
+	unsigned long lock_count[2];
+	unsigned long unlock_count[2];
 };
 
 struct rcu_batch {
@@ -46,7 +46,7 @@ struct rcu_batch {
 
 struct srcu_struct {
 	unsigned long completed;
-	struct srcu_struct_array __percpu *per_cpu_ref;
+	struct srcu_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
 	/* callbacks just queued */
@@ -118,7 +118,7 @@ void process_srcu(struct work_struct *work);
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
 	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)
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 9d4f9b3a2b7b..e3facb356838 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -385,11 +385,11 @@ 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, "ofl" for CPU offline,
- * or "kick" when kicking a CPU that has been in dyntick-idle mode for
- * too long.
+ * 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, "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.
  */
 TRACE_EVENT(rcu_fqs,