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 are:

   - Documentation updates, including fixes to the design-level
     requirements documentation and a fixed version of the design-level
     data-structure documentation.  These fixes include removing
     cartoons and getting rid of the html/htmlx duplication.

   - Further improvements to the new-age expedited grace periods.

   - Miscellaneous fixes.

   - Torture-test changes, including a new rcuperf module for measuring
     RCU grace-period performance and scalability, which is useful for
     the expedited-grace-period changes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  rcutorture: Add boot-time adjustment of leaf fanout
  rcutorture: Add irqs-disabled test for call_rcu()
  rcutorture: Dump trace buffer upon shutdown
  rcutorture: Don't rebuild identical kernel
  rcutorture: Add OS-jitter capability
  documentation: Add documentation for RCU's major data structures
  rcutorture: Convert test duration to seconds early
  torture: Kill qemu, not parent process
  torture: Clarify refusal to run more than one torture test
  rcutorture: Consider FROZEN hotplug notifier transitions
  rcutorture: Remove redundant initialization to zero
  rcuperf: Do not wake up shutdown wait queue if "shutdown" is false.
  rcutorture: Add largish-system rcuperf scenario
  rcutorture: Avoid RCU CPU stall warning and RT throttling
  rcutorture: Add rcuperf holdoff boot parameter to reduce interference
  rcutorture: Make scripts analyze rcuperf trace data, if present
  rcutorture: Make rcuperf collect expedited event-trace data
  rcutorture: Print measure of batching efficiency
  rcutorture: Set rcuperf writer kthreads to real-time priority
  rcutorture: Bind rcuperf reader/writer kthreads to CPUs
  ...

4 files changed, 109 insertions, 18 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2657aff2725b..5f1533e3d032 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -508,14 +508,7 @@ int rcu_read_lock_bh_held(void);
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.
  */
-#ifdef CONFIG_PREEMPT_COUNT
 int rcu_read_lock_sched_held(void);
-#else /* #ifdef CONFIG_PREEMPT_COUNT */
-static inline int rcu_read_lock_sched_held(void)
-{
-	return 1;
-}
-#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
@@ -532,18 +525,10 @@ static inline int rcu_read_lock_bh_held(void)
 	return 1;
 }
 
-#ifdef CONFIG_PREEMPT_COUNT
 static inline int rcu_read_lock_sched_held(void)
 {
-	return preempt_count() != 0 || irqs_disabled();
-}
-#else /* #ifdef CONFIG_PREEMPT_COUNT */
-static inline int rcu_read_lock_sched_held(void)
-{
-	return 1;
+	return !preemptible();
 }
-#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
-
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 #ifdef CONFIG_PROVE_RCU
@@ -1144,4 +1129,17 @@ static inline void rcu_sysidle_force_exit(void)
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 
 
+/*
+ * Dump the ftrace buffer, but only one time per callsite per boot.
+ */
+#define rcu_ftrace_dump(oops_dump_mode) \
+do { \
+	static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \
+	\
+	if (!atomic_read(&___rfd_beenhere) && \
+	    !atomic_xchg(&___rfd_beenhere, 1)) \
+		ftrace_dump(oops_dump_mode); \
+} while (0)
+
+
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 64809aea661c..93aea75029fb 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -149,6 +149,22 @@ static inline unsigned long rcu_batches_completed_sched(void)
 	return 0;
 }
 
+/*
+ * Return the number of expedited grace periods completed.
+ */
+static inline unsigned long rcu_exp_batches_completed(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of expedited sched grace periods completed.
+ */
+static inline unsigned long rcu_exp_batches_completed_sched(void)
+{
+	return 0;
+}
+
 static inline void rcu_force_quiescent_state(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index ad1eda9fa4da..5043cb823fb2 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -87,6 +87,8 @@ unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
 unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_exp_batches_completed(void);
+unsigned long rcu_exp_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index ef72c4aada56..d3e756539d44 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -172,6 +172,77 @@ TRACE_EVENT(rcu_grace_period_init,
 );
 
 /*
+ * Tracepoint for expedited grace-period events.  Takes a string identifying
+ * the RCU flavor, the expedited grace-period sequence number, and a string
+ * identifying the grace-period-related event as follows:
+ *
+ *	"snap": Captured snapshot of expedited grace period sequence number.
+ *	"start": Started a real expedited grace period.
+ *	"end": Ended a real expedited grace period.
+ *	"endwake": Woke piggybackers up.
+ *	"done": Someone else did the expedited grace period for us.
+ */
+TRACE_EVENT(rcu_exp_grace_period,
+
+	TP_PROTO(const char *rcuname, unsigned long gpseq, const char *gpevent),
+
+	TP_ARGS(rcuname, gpseq, gpevent),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(unsigned long, gpseq)
+		__field(const char *, gpevent)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->gpseq = gpseq;
+		__entry->gpevent = gpevent;
+	),
+
+	TP_printk("%s %lu %s",
+		  __entry->rcuname, __entry->gpseq, __entry->gpevent)
+);
+
+/*
+ * Tracepoint for expedited grace-period funnel-locking events.  Takes a
+ * string identifying the RCU flavor, an integer identifying the rcu_node
+ * combining-tree level, another pair of integers identifying the lowest-
+ * and highest-numbered CPU associated with the current rcu_node structure,
+ * and a string.  identifying the grace-period-related event as follows:
+ *
+ *	"nxtlvl": Advance to next level of rcu_node funnel
+ *	"wait": Wait for someone else to do expedited GP
+ */
+TRACE_EVENT(rcu_exp_funnel_lock,
+
+	TP_PROTO(const char *rcuname, u8 level, int grplo, int grphi,
+		 const char *gpevent),
+
+	TP_ARGS(rcuname, level, grplo, grphi, gpevent),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(u8, level)
+		__field(int, grplo)
+		__field(int, grphi)
+		__field(const char *, gpevent)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->level = level;
+		__entry->grplo = grplo;
+		__entry->grphi = grphi;
+		__entry->gpevent = gpevent;
+	),
+
+	TP_printk("%s %d %d %d %s",
+		  __entry->rcuname, __entry->level, __entry->grplo,
+		  __entry->grphi, __entry->gpevent)
+);
+
+/*
  * Tracepoint for RCU no-CBs CPU callback handoffs.  This event is intended
  * to assist debugging of these handoffs.
  *
@@ -704,11 +775,15 @@ TRACE_EVENT(rcu_barrier,
 #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_future_grace_period(rcuname, gpnum, completed, c, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
+#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+				    qsmask) do { } while (0)
+#define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
+	do { } while (0)
+#define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
+	do { } while (0)
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) 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)