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 main changes in this cycle are mostly related to preparatory work
  for the full-dynticks work:

   - Remove restrictions on no-CBs CPUs, make RCU_FAST_NO_HZ take
     advantage of numbered callbacks, do callback accelerations based on
     numbered callbacks.  Posted to LKML at
        https://lkml.org/lkml/2013/3/18/960

   - RCU documentation updates.  Posted to LKML at
        https://lkml.org/lkml/2013/3/18/570

   - Miscellaneous fixes.  Posted to LKML at
        https://lkml.org/lkml/2013/3/18/594"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  rcu: Make rcu_accelerate_cbs() note need for future grace periods
  rcu: Abstract rcu_start_future_gp() from rcu_nocb_wait_gp()
  rcu: Rename n_nocb_gp_requests to need_future_gp
  rcu: Push lock release to rcu_start_gp()'s callers
  rcu: Repurpose no-CBs event tracing to future-GP events
  rcu: Rearrange locking in rcu_start_gp()
  rcu: Make RCU_FAST_NO_HZ take advantage of numbered callbacks
  rcu: Accelerate RCU callbacks at grace-period end
  rcu: Export RCU_FAST_NO_HZ parameters to sysfs
  rcu: Distinguish "rcuo" kthreads by RCU flavor
  rcu: Add event tracing for no-CBs CPUs' grace periods
  rcu: Add event tracing for no-CBs CPUs' callback registration
  rcu: Introduce proper blocking to no-CBs kthreads GP waits
  rcu: Provide compile-time control for no-CBs CPUs
  rcu: Tone down debugging during boot-up and shutdown.
  rcu: Add softirq-stall indications to stall-warning messages
  rcu: Documentation update
  rcu: Make bugginess of code sample more evident
  rcu: Fix hlist_bl_set_first_rcu() annotation
  rcu: Delete unused rcu_node "wakemask" field
  ...

include/linux/list_bl.h

@@ -125,6 +125,11 @@ static inline void hlist_bl_unlock(struct hlist_bl_head *b)
 	__bit_spin_unlock(0, (unsigned long *)b);
 }
 
+static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
+{
+	return bit_spin_is_locked(0, (unsigned long *)b);
+}
+
 /**
  * hlist_bl_for_each_entry	- iterate over list of given type
  * @tpos:	the type * to use as a loop cursor.

include/linux/rculist_bl.h

@@ -20,7 +20,7 @@ static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h,
 static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)
 {
 	return (struct hlist_bl_node *)
-		((unsigned long)rcu_dereference(h->first) & ~LIST_BL_LOCKMASK);
+		((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK);
 }
 
 /**

include/linux/rcupdate.h

@@ -80,6 +80,7 @@ extern void do_trace_rcu_torture_read(char *rcutorturename,
 #define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
+#define ulong2long(a)		(*(long *)(&(a)))
 
 /* Exported common interfaces */
 

include/trace/events/rcu.h

@@ -71,6 +71,58 @@ TRACE_EVENT(rcu_grace_period,
 		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
 );
 
+/*
+ * Tracepoint for future grace-period events, including those for no-callbacks
+ * CPUs.  The caller should pull the data from the rcu_node structure,
+ * other than rcuname, which comes from the rcu_state structure, and event,
+ * which is one of the following:
+ *
+ * "Startleaf": Request a nocb grace period based on leaf-node data.
+ * "Startedleaf": Leaf-node start proved sufficient.
+ * "Startedleafroot": Leaf-node start proved sufficient after checking root.
+ * "Startedroot": Requested a nocb grace period based on root-node data.
+ * "StartWait": Start waiting for the requested grace period.
+ * "ResumeWait": Resume waiting after signal.
+ * "EndWait": Complete wait.
+ * "Cleanup": Clean up rcu_node structure after previous GP.
+ * "CleanupMore": Clean up, and another no-CB GP is needed.
+ */
+TRACE_EVENT(rcu_future_grace_period,
+
+	TP_PROTO(char *rcuname, unsigned long gpnum, unsigned long completed,
+		 unsigned long c, u8 level, int grplo, int grphi,
+		 char *gpevent),
+
+	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
+
+	TP_STRUCT__entry(
+		__field(char *, rcuname)
+		__field(unsigned long, gpnum)
+		__field(unsigned long, completed)
+		__field(unsigned long, c)
+		__field(u8, level)
+		__field(int, grplo)
+		__field(int, grphi)
+		__field(char *, gpevent)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpnum = gpnum;
+		__entry->completed = completed;
+		__entry->c = c;
+		__entry->level = level;
+		__entry->grplo = grplo;
+		__entry->grphi = grphi;
+		__entry->gpevent = gpevent;
+	),
+
+	TP_printk("%s %lu %lu %lu %u %d %d %s",
+		  __entry->rcuname, __entry->gpnum, __entry->completed,
+		  __entry->c, __entry->level, __entry->grplo, __entry->grphi,
+		  __entry->gpevent)
+);
+
 /*
  * Tracepoint for grace-period-initialization events.  These are
  * distinguished by the type of RCU, the new grace-period number, the
@@ -601,6 +653,9 @@ TRACE_EVENT(rcu_barrier,
 #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_future_grace_period(rcuname, gpnum, completed, c, \
+				      level, grplo, grphi, event) \
+				      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, \