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

Pull RCU updates from Paul E. McKenney:

"
 * Update RCU documentation.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/611.

 * Miscellaneous fixes.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/619.

 * Full-system idle detection.  This is for use by Frederic
   Weisbecker's adaptive-ticks mechanism.  Its purpose is
   to allow the timekeeping CPU to shut off its tick when
   all other CPUs are idle.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/648.

 * Improve rcutorture test coverage.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/675.
"

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

Documentation/RCU/rcubarrier.txt

@@ -70,10 +70,14 @@ in realtime kernels in order to avoid excessive scheduling latencies.
 
 rcu_barrier()
 
-We instead need the rcu_barrier() primitive. This primitive is similar
-to synchronize_rcu(), but instead of waiting solely for a grace
-period to elapse, it also waits for all outstanding RCU callbacks to
-complete. Pseudo-code using rcu_barrier() is as follows:
+We instead need the rcu_barrier() primitive.  Rather than waiting for
+a grace period to elapse, rcu_barrier() waits for all outstanding RCU
+callbacks to complete.  Please note that rcu_barrier() does -not- imply
+synchronize_rcu(), in particular, if there are no RCU callbacks queued
+anywhere, rcu_barrier() is within its rights to return immediately,
+without waiting for a grace period to elapse.
+
+Pseudo-code using rcu_barrier() is as follows:
 
    1. Prevent any new RCU callbacks from being posted.
    2. Execute rcu_barrier().

Documentation/RCU/torture.txt

@@ -42,6 +42,16 @@ fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
 fqs_stutter	Wait time (in seconds) between consecutive bursts
 		of calls to force_quiescent_state().
 
+gp_normal	Make the fake writers use normal synchronous grace-period
+		primitives.
+
+gp_exp		Make the fake writers use expedited synchronous grace-period
+		primitives.  If both gp_normal and gp_exp are set, or
+		if neither gp_normal nor gp_exp are set, then randomly
+		choose the primitive so that about 50% are normal and
+		50% expedited.  By default, neither are set, which
+		gives best overall test coverage.
+
 irqreader	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do

Documentation/memory-barriers.txt

@@ -531,9 +531,10 @@ dependency barrier to make it work correctly.  Consider the following bit of
 code:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<data dependency barrier>
 		q = &b;
-	<data dependency barrier>
+	}
 	x = *q;
 
 This will not have the desired effect because there is no actual data
@@ -542,9 +543,10 @@ attempting to predict the outcome in advance.  In such a case what's actually
 required is:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<read barrier>
 		q = &b;
-	<read barrier>
+	}
 	x = *q;
 
 

Documentation/timers/NO_HZ.txt

@@ -24,8 +24,8 @@ There are three main ways of managing scheduling-clock interrupts
 	workloads, you will normally -not- want this option.
 
 These three cases are described in the following three sections, followed
-by a third section on RCU-specific considerations and a fourth and final
-section listing known issues.
+by a third section on RCU-specific considerations, a fourth section
+discussing testing, and a fifth and final section listing known issues.
 
 
 NEVER OMIT SCHEDULING-CLOCK TICKS
@@ -121,14 +121,15 @@ boot parameter specifies the adaptive-ticks CPUs.  For example,
 "nohz_full=1,6-8" says that CPUs 1, 6, 7, and 8 are to be adaptive-ticks
 CPUs.  Note that you are prohibited from marking all of the CPUs as
 adaptive-tick CPUs:  At least one non-adaptive-tick CPU must remain
-online to handle timekeeping tasks in order to ensure that system calls
-like gettimeofday() returns accurate values on adaptive-tick CPUs.
-(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no
-running user processes to observe slight drifts in clock rate.)
-Therefore, the boot CPU is prohibited from entering adaptive-ticks
-mode.  Specifying a "nohz_full=" mask that includes the boot CPU will
-result in a boot-time error message, and the boot CPU will be removed
-from the mask.
+online to handle timekeeping tasks in order to ensure that system
+calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
+(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
+user processes to observe slight drifts in clock rate.)  Therefore, the
+boot CPU is prohibited from entering adaptive-ticks mode.  Specifying a
+"nohz_full=" mask that includes the boot CPU will result in a boot-time
+error message, and the boot CPU will be removed from the mask.  Note that
+this means that your system must have at least two CPUs in order for
+CONFIG_NO_HZ_FULL=y to do anything for you.
 
 Alternatively, the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter specifies
 that all CPUs other than the boot CPU are adaptive-ticks CPUs.  This
@@ -232,6 +233,29 @@ scheduler will decide where to run them, which might or might not be
 where you want them to run.
 
 
+TESTING
+
+So you enable all the OS-jitter features described in this document,
+but do not see any change in your workload's behavior.  Is this because
+your workload isn't affected that much by OS jitter, or is it because
+something else is in the way?  This section helps answer this question
+by providing a simple OS-jitter test suite, which is available on branch
+master of the following git archive:
+
+git://git.kernel.org/pub/scm/linux/kernel/git/frederic/dynticks-testing.git
+
+Clone this archive and follow the instructions in the README file.
+This test procedure will produce a trace that will allow you to evaluate
+whether or not you have succeeded in removing OS jitter from your system.
+If this trace shows that you have removed OS jitter as much as is
+possible, then you can conclude that your workload is not all that
+sensitive to OS jitter.
+
+Note: this test requires that your system have at least two CPUs.
+We do not currently have a good way to remove OS jitter from single-CPU
+systems.
+
+
 KNOWN ISSUES
 
 o	Dyntick-idle slows transitions to and from idle slightly.

include/asm-generic/vmlinux.lds.h

@@ -122,8 +122,12 @@
 #define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .;      \
 			 *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \
 			 VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .;
+#define TRACEPOINT_STR() VMLINUX_SYMBOL(__start___tracepoint_str) = .;	\
+			 *(__tracepoint_str) /* Trace_printk fmt' pointer */ \
+			 VMLINUX_SYMBOL(__stop___tracepoint_str) = .;
 #else
 #define TRACE_PRINTKS()
+#define TRACEPOINT_STR()
 #endif
 
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -190,7 +194,8 @@
 	VMLINUX_SYMBOL(__stop___verbose) = .;				\
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
-	TRACE_PRINTKS()
+	TRACE_PRINTKS()							\
+	TRACEPOINT_STR()
 
 /*
  * Data section helpers

include/linux/debugobjects.h

@@ -63,7 +63,7 @@ struct debug_obj_descr {
 extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
 extern void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
-extern void debug_object_activate  (void *addr, struct debug_obj_descr *descr);
+extern int debug_object_activate  (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
@@ -85,8 +85,8 @@ static inline void
 debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
 static inline void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
-static inline void
-debug_object_activate  (void *addr, struct debug_obj_descr *descr) { }
+static inline int
+debug_object_activate  (void *addr, struct debug_obj_descr *descr) { return 0; }
 static inline void
 debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
 static inline void

include/linux/ftrace_event.h

@@ -359,6 +359,40 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
+/**
+ * tracepoint_string - register constant persistent string to trace system
+ * @str - a constant persistent string that will be referenced in tracepoints
+ *
+ * If constant strings are being used in tracepoints, it is faster and
+ * more efficient to just save the pointer to the string and reference
+ * that with a printf "%s" instead of saving the string in the ring buffer
+ * and wasting space and time.
+ *
+ * The problem with the above approach is that userspace tools that read
+ * the binary output of the trace buffers do not have access to the string.
+ * Instead they just show the address of the string which is not very
+ * useful to users.
+ *
+ * With tracepoint_string(), the string will be registered to the tracing
+ * system and exported to userspace via the debugfs/tracing/printk_formats
+ * file that maps the string address to the string text. This way userspace
+ * tools that read the binary buffers have a way to map the pointers to
+ * the ASCII strings they represent.
+ *
+ * The @str used must be a constant string and persistent as it would not
+ * make sense to show a string that no longer exists. But it is still fine
+ * to be used with modules, because when modules are unloaded, if they
+ * had tracepoints, the ring buffers are cleared too. As long as the string
+ * does not change during the life of the module, it is fine to use
+ * tracepoint_string() within a module.
+ */
+#define tracepoint_string(str)						\
+	({								\
+		static const char *___tp_str __tracepoint_string = str; \
+		___tp_str;						\
+	})
+#define __tracepoint_string	__attribute__((section("__tracepoint_str")))
+
 #ifdef CONFIG_PERF_EVENTS
 struct perf_event;
 

include/linux/jiffies.h

@@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after(a,b)		\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(b) - (long)(a) < 0))
+	 ((long)((b) - (a)) < 0))
 #define time_before(a,b)	time_after(b,a)
 
 #define time_after_eq(a,b)	\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(a) - (long)(b) >= 0))
+	 ((long)((a) - (b)) >= 0))
 #define time_before_eq(a,b)	time_after_eq(b,a)
 
 /*
@@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void)
 #define time_after64(a,b)	\
 	(typecheck(__u64, a) &&	\
 	 typecheck(__u64, b) && \
-	 ((__s64)(b) - (__s64)(a) < 0))
+	 ((__s64)((b) - (a)) < 0))
 #define time_before64(a,b)	time_after64(b,a)
 
 #define time_after_eq64(a,b)	\
 	(typecheck(__u64, a) && \
 	 typecheck(__u64, b) && \
-	 ((__s64)(a) - (__s64)(b) >= 0))
+	 ((__s64)((a) - (b)) >= 0))
 #define time_before_eq64(a,b)	time_after_eq64(b,a)
 
 #define time_in_range64(a, b, c) \

include/linux/rculist.h

@@ -267,8 +267,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  */
 #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; \
+	  struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+	  likely(__ptr != __next) ? \
+		list_entry_rcu(__next, type, member) : NULL; \
 	})
 
 /**

include/linux/rcupdate.h

@@ -52,7 +52,7 @@ extern int rcutorture_runnable; /* for sysctl */
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 extern void rcutorture_record_test_transition(void);
 extern void rcutorture_record_progress(unsigned long vernum);
-extern void do_trace_rcu_torture_read(char *rcutorturename,
+extern void do_trace_rcu_torture_read(const char *rcutorturename,
 				      struct rcu_head *rhp,
 				      unsigned long secs,
 				      unsigned long c_old,
@@ -65,7 +65,7 @@ static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
 #ifdef CONFIG_RCU_TRACE
-extern void do_trace_rcu_torture_read(char *rcutorturename,
+extern void do_trace_rcu_torture_read(const char *rcutorturename,
 				      struct rcu_head *rhp,
 				      unsigned long secs,
 				      unsigned long c_old,
@@ -229,13 +229,9 @@ extern void rcu_irq_exit(void);
 #ifdef CONFIG_RCU_USER_QS
 extern void rcu_user_enter(void);
 extern void rcu_user_exit(void);
-extern void rcu_user_enter_after_irq(void);
-extern void rcu_user_exit_after_irq(void);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
-static inline void rcu_user_enter_after_irq(void) { }
-static inline void rcu_user_exit_after_irq(void) { }
 static inline void rcu_user_hooks_switch(struct task_struct *prev,
 					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
@@ -1015,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 
+/* Only for use by adaptive-ticks code. */
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+extern bool rcu_sys_is_idle(void);
+extern void rcu_sysidle_force_exit(void);
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+static inline bool rcu_sys_is_idle(void)
+{
+	return false;
+}
+
+static inline void rcu_sysidle_force_exit(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+
 #endif /* __LINUX_RCUPDATE_H */

include/trace/events/rcu.h

@@ -19,12 +19,12 @@
  */
 TRACE_EVENT(rcu_utilization,
 
-	TP_PROTO(char *s),
+	TP_PROTO(const char *s),
 
 	TP_ARGS(s),
 
 	TP_STRUCT__entry(
-		__field(char *, s)
+		__field(const char *, s)
 	),
 
 	TP_fast_assign(
@@ -51,14 +51,14 @@ TRACE_EVENT(rcu_utilization,
  */
 TRACE_EVENT(rcu_grace_period,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
 
 	TP_ARGS(rcuname, gpnum, gpevent),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
-		__field(char *, gpevent)
+		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
@@ -89,21 +89,21 @@ TRACE_EVENT(rcu_grace_period,
  */
 TRACE_EVENT(rcu_future_grace_period,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum, unsigned long completed,
+	TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
 		 unsigned long c, u8 level, int grplo, int grphi,
-		 char *gpevent),
+		 const char *gpevent),
 
 	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const 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)
+		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
@@ -132,13 +132,13 @@ TRACE_EVENT(rcu_future_grace_period,
  */
 TRACE_EVENT(rcu_grace_period_init,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum, u8 level,
+	TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
 		 int grplo, int grphi, unsigned long qsmask),
 
 	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
 		__field(u8, level)
 		__field(int, grplo)
@@ -168,12 +168,12 @@ TRACE_EVENT(rcu_grace_period_init,
  */
 TRACE_EVENT(rcu_preempt_task,
 
-	TP_PROTO(char *rcuname, int pid, unsigned long gpnum),
+	TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
 
 	TP_ARGS(rcuname, pid, gpnum),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
 		__field(int, pid)
 	),
@@ -195,12 +195,12 @@ TRACE_EVENT(rcu_preempt_task,
  */
 TRACE_EVENT(rcu_unlock_preempted_task,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum, int pid),
+	TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
 
 	TP_ARGS(rcuname, gpnum, pid),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
 		__field(int, pid)
 	),
@@ -224,14 +224,14 @@ TRACE_EVENT(rcu_unlock_preempted_task,
  */
 TRACE_EVENT(rcu_quiescent_state_report,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum,
+	TP_PROTO(const char *rcuname, unsigned long gpnum,
 		 unsigned long mask, unsigned long qsmask,
 		 u8 level, int grplo, int grphi, int gp_tasks),
 
 	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
 		__field(unsigned long, mask)
 		__field(unsigned long, qsmask)
@@ -268,15 +268,15 @@ TRACE_EVENT(rcu_quiescent_state_report,
  */
 TRACE_EVENT(rcu_fqs,
 
-	TP_PROTO(char *rcuname, unsigned long gpnum, int cpu, char *qsevent),
+	TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
 
 	TP_ARGS(rcuname, gpnum, cpu, qsevent),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(unsigned long, gpnum)
 		__field(int, cpu)
-		__field(char *, qsevent)
+		__field(const char *, qsevent)
 	),
 
 	TP_fast_assign(
@@ -308,12 +308,12 @@ TRACE_EVENT(rcu_fqs,
  */
 TRACE_EVENT(rcu_dyntick,
 
-	TP_PROTO(char *polarity, long long oldnesting, long long newnesting),
+	TP_PROTO(const char *polarity, long long oldnesting, long long newnesting),
 
 	TP_ARGS(polarity, oldnesting, newnesting),
 
 	TP_STRUCT__entry(
-		__field(char *, polarity)
+		__field(const char *, polarity)
 		__field(long long, oldnesting)
 		__field(long long, newnesting)
 	),
@@ -352,12 +352,12 @@ TRACE_EVENT(rcu_dyntick,
  */
 TRACE_EVENT(rcu_prep_idle,
 
-	TP_PROTO(char *reason),
+	TP_PROTO(const char *reason),
 
 	TP_ARGS(reason),
 
 	TP_STRUCT__entry(
-		__field(char *, reason)
+		__field(const char *, reason)
 	),
 
 	TP_fast_assign(
@@ -376,13 +376,13 @@ TRACE_EVENT(rcu_prep_idle,
  */
 TRACE_EVENT(rcu_callback,
 
-	TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy,
+	TP_PROTO(const char *rcuname, struct rcu_head *rhp, long qlen_lazy,
 		 long qlen),
 
 	TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(void *, rhp)
 		__field(void *, func)
 		__field(long, qlen_lazy)
@@ -412,13 +412,13 @@ TRACE_EVENT(rcu_callback,
  */
 TRACE_EVENT(rcu_kfree_callback,
 
-	TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset,
+	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset,
 		 long qlen_lazy, long qlen),
 
 	TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(void *, rhp)
 		__field(unsigned long, offset)
 		__field(long, qlen_lazy)
@@ -447,12 +447,12 @@ TRACE_EVENT(rcu_kfree_callback,
  */
 TRACE_EVENT(rcu_batch_start,
 
-	TP_PROTO(char *rcuname, long qlen_lazy, long qlen, long blimit),
+	TP_PROTO(const char *rcuname, long qlen_lazy, long qlen, long blimit),
 
 	TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(long, qlen_lazy)
 		__field(long, qlen)
 		__field(long, blimit)
@@ -477,12 +477,12 @@ TRACE_EVENT(rcu_batch_start,
  */
 TRACE_EVENT(rcu_invoke_callback,
 
-	TP_PROTO(char *rcuname, struct rcu_head *rhp),
+	TP_PROTO(const char *rcuname, struct rcu_head *rhp),
 
 	TP_ARGS(rcuname, rhp),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(void *, rhp)
 		__field(void *, func)
 	),
@@ -506,12 +506,12 @@ TRACE_EVENT(rcu_invoke_callback,
  */
 TRACE_EVENT(rcu_invoke_kfree_callback,
 
-	TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset),
+	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset),
 
 	TP_ARGS(rcuname, rhp, offset),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(void *, rhp)
 		__field(unsigned long, offset)
 	),
@@ -539,13 +539,13 @@ TRACE_EVENT(rcu_invoke_kfree_callback,
  */
 TRACE_EVENT(rcu_batch_end,
 
-	TP_PROTO(char *rcuname, int callbacks_invoked,
+	TP_PROTO(const char *rcuname, int callbacks_invoked,
 		 bool cb, bool nr, bool iit, bool risk),
 
 	TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk),
 
 	TP_STRUCT__entry(
-		__field(char *, rcuname)
+		__field(const char *, rcuname)
 		__field(int, callbacks_invoked)
 		__field(bool, cb)
 		__field(bool, nr)
@@ -577,13 +577,13 @@ TRACE_EVENT(rcu_batch_end,
  */
 TRACE_EVENT(rcu_torture_read,
 
-	TP_PROTO(char *rcutorturename, struct rcu_head *rhp,
+	TP_PROTO(const char *rcutorturename, struct rcu_head *rhp,
 		 unsigned long secs, unsigned long c_old, unsigned long c),
 
 	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
 
 	TP_STRUCT__entry(
-		__field(char *, rcutorturename)
+		__field(const char *, rcutorturename)
 		__field(struct rcu_head *, rhp)
 		__field(unsigned long, secs)
 		__field(unsigned long, c_old)
@@ -623,13 +623,13 @@ TRACE_EVENT(rcu_torture_read,
  */
 TRACE_EVENT(rcu_barrier,
 
-	TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done),
+	TP_PROTO(const char *rcuname, const 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(const char *, rcuname)
+		__field(const char *, s)
 		__field(int, cpu)
 		__field(int, cnt)
 		__field(unsigned long, done)

init/Kconfig

@@ -470,6 +470,7 @@ config TREE_RCU
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or

kernel/rcu.h

@@ -67,12 +67,15 @@
 
 extern struct debug_obj_descr rcuhead_debug_descr;
 
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
-	debug_object_activate(head, &rcuhead_debug_descr);
+	int r1;
+
+	r1 = debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
 				  STATE_RCU_HEAD_QUEUED);
+	return r1;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -83,8 +86,9 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 	debug_object_deactivate(head, &rcuhead_debug_descr);
 }
 #else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
+	return 0;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -94,7 +98,7 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 
 extern void kfree(const void *);
 
-static inline bool __rcu_reclaim(char *rn, struct rcu_head *head)
+static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
 

kernel/rcupdate.c

@@ -211,43 +211,6 @@ static inline void debug_rcu_head_free(struct rcu_head *head)
 	debug_object_free(head, &rcuhead_debug_descr);
 }
 
-/*
- * fixup_init is called when:
- * - an active object is initialized
- */
-static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_init(head, &rcuhead_debug_descr);
-		return 1;
-	default:
-		return 0;
-	}
-}
-
 /*
  * fixup_activate is called when:
  * - an active object is activated
@@ -268,69 +231,8 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
 		debug_object_init(head, &rcuhead_debug_descr);
 		debug_object_activate(head, &rcuhead_debug_descr);
 		return 0;
-
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_activate(head, &rcuhead_debug_descr);
-		return 1;
 	default:
-		return 0;
-	}
-}
-
-/*
- * fixup_free is called when:
- * - an active object is freed
- */
-static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_free(head, &rcuhead_debug_descr);
 		return 1;
-	default:
-		return 0;
 	}
 }
 
@@ -369,15 +271,13 @@ EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
 
 struct debug_obj_descr rcuhead_debug_descr = {
 	.name = "rcu_head",
-	.fixup_init = rcuhead_fixup_init,
 	.fixup_activate = rcuhead_fixup_activate,
-	.fixup_free = rcuhead_fixup_free,
 };
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
-void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp,
+void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
 			       unsigned long secs,
 			       unsigned long c_old, unsigned long c)
 {

kernel/rcutiny.c

@@ -264,7 +264,7 @@ void rcu_check_callbacks(int cpu, int user)
  */
 static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 {
-	char *rn = NULL;
+	const char *rn = NULL;
 	struct rcu_head *next, *list;
 	unsigned long flags;
 	RCU_TRACE(int cb_count = 0);

kernel/rcutiny_plugin.h

@@ -36,7 +36,7 @@ struct rcu_ctrlblk {
 	RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */
 	RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */
 	RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */
-	RCU_TRACE(char *name);		/* Name of RCU type. */
+	RCU_TRACE(const char *name);	/* Name of RCU type. */
 };
 
 /* Definition for rcupdate control block. */

kernel/rcutree.h

@@ -88,6 +88,14 @@ struct rcu_dynticks {
 				    /* Process level is worth LLONG_MAX/2. */
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	long long dynticks_idle_nesting;
+				    /* irq/process nesting level from idle. */
+	atomic_t dynticks_idle;	    /* Even value for idle, else odd. */
+				    /*  "Idle" excludes userspace execution. */
+	unsigned long dynticks_idle_jiffies;
+				    /* End of last non-NMI non-idle period. */
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	bool all_lazy;		    /* Are all CPU's CBs lazy? */
 	unsigned long nonlazy_posted;
@@ -445,7 +453,7 @@ struct rcu_state {
 						/*  for CPU stalls. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
-	char *name;				/* Name of structure. */
+	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
 	struct irq_work wakeup_work;		/* Postponed wakeups */
@@ -545,6 +553,15 @@ static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
+static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
+				  unsigned long *maxj);
+static bool is_sysidle_rcu_state(struct rcu_state *rsp);
+static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
+				  unsigned long maxj);
+static void rcu_bind_gp_kthread(void);
+static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */